diff options
Diffstat (limited to 'arch')
114 files changed, 1165 insertions, 762 deletions
diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index ce8101834518..6b5c54576f54 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -8,5 +8,6 @@ menuconfig ARC_SOC_HSDK select ARC_HAS_ACCL_REGS select ARC_IRQ_NO_AUTOSAVE select CLK_HSDK + select RESET_CONTROLLER select RESET_HSDK select HAVE_PCI diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi index 911d8cf77f2c..0339a46fa71c 100644 --- a/arch/arm/boot/dts/imx6sl.dtsi +++ b/arch/arm/boot/dts/imx6sl.dtsi @@ -939,8 +939,10 @@ }; rngb: rngb@21b4000 { + compatible = "fsl,imx6sl-rngb", "fsl,imx25-rngb"; reg = <0x021b4000 0x4000>; interrupts = <0 5 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clks IMX6SL_CLK_DUMMY>; }; weim: weim@21b8000 { diff --git a/arch/arm/boot/dts/iwg20d-q7-common.dtsi b/arch/arm/boot/dts/iwg20d-q7-common.dtsi index ebbe1518ef8a..63cafd220dba 100644 --- a/arch/arm/boot/dts/iwg20d-q7-common.dtsi +++ b/arch/arm/boot/dts/iwg20d-q7-common.dtsi @@ -57,7 +57,7 @@ lvds-receiver { compatible = "ti,ds90cf384a", "lvds-decoder"; - powerdown-gpios = <&gpio7 25 GPIO_ACTIVE_LOW>; + power-supply = <&vcc_3v3_tft1>; ports { #address-cells = <1>; @@ -81,6 +81,7 @@ panel { compatible = "edt,etm0700g0dh6"; backlight = <&lcd_backlight>; + power-supply = <&vcc_3v3_tft1>; port { panel_in: endpoint { @@ -113,6 +114,17 @@ }; }; + vcc_3v3_tft1: regulator-panel { + compatible = "regulator-fixed"; + + regulator-name = "vcc-3v3-tft1"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + enable-active-high; + startup-delay-us = <500>; + gpio = <&gpio7 25 GPIO_ACTIVE_HIGH>; + }; + vcc_sdhi1: regulator-vcc-sdhi1 { compatible = "regulator-fixed"; @@ -207,6 +219,7 @@ reg = <0x38>; interrupt-parent = <&gpio2>; interrupts = <12 IRQ_TYPE_EDGE_FALLING>; + vcc-supply = <&vcc_3v3_tft1>; }; }; diff --git a/arch/arm/boot/dts/meson8.dtsi b/arch/arm/boot/dts/meson8.dtsi index eedb92526968..a4ab8b96d0eb 100644 --- a/arch/arm/boot/dts/meson8.dtsi +++ b/arch/arm/boot/dts/meson8.dtsi @@ -239,8 +239,6 @@ <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 172 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 173 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/boot/dts/owl-s500.dtsi b/arch/arm/boot/dts/owl-s500.dtsi index 5ceb6cc4451d..1dbe4e8b38ac 100644 --- a/arch/arm/boot/dts/owl-s500.dtsi +++ b/arch/arm/boot/dts/owl-s500.dtsi @@ -84,21 +84,21 @@ global_timer: timer@b0020200 { compatible = "arm,cortex-a9-global-timer"; reg = <0xb0020200 0x100>; - interrupts = <GIC_PPI 0 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + interrupts = <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; status = "disabled"; }; twd_timer: timer@b0020600 { compatible = "arm,cortex-a9-twd-timer"; reg = <0xb0020600 0x20>; - interrupts = <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; status = "disabled"; }; twd_wdt: wdt@b0020620 { compatible = "arm,cortex-a9-twd-wdt"; reg = <0xb0020620 0xe0>; - interrupts = <GIC_PPI 3 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts b/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts index 5700e6b700d3..b85025d00943 100644 --- a/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts +++ b/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts @@ -121,8 +121,6 @@ reset-gpios = <&gpiog 0 GPIO_ACTIVE_LOW>; /* ETH_RST# */ interrupt-parent = <&gpioa>; interrupts = <6 IRQ_TYPE_EDGE_FALLING>; /* ETH_MDINT# */ - rxc-skew-ps = <1860>; - txc-skew-ps = <1860>; reset-assert-us = <10000>; reset-deassert-us = <300>; micrel,force-master; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi index 7c4bd615b311..e4e3c92eb30d 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi @@ -11,7 +11,6 @@ serial0 = &uart4; serial1 = &usart3; serial2 = &uart8; - ethernet0 = ðernet0; }; chosen { @@ -26,23 +25,13 @@ display_bl: display-bl { compatible = "pwm-backlight"; - pwms = <&pwm2 0 500000 PWM_POLARITY_INVERTED>; + pwms = <&pwm2 3 500000 PWM_POLARITY_INVERTED>; brightness-levels = <0 16 22 30 40 55 75 102 138 188 255>; default-brightness-level = <8>; enable-gpios = <&gpioi 0 GPIO_ACTIVE_HIGH>; status = "okay"; }; - ethernet_vio: vioregulator { - compatible = "regulator-fixed"; - regulator-name = "vio"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - gpio = <&gpiog 3 GPIO_ACTIVE_LOW>; - regulator-always-on; - regulator-boot-on; - }; - gpio-keys-polled { compatible = "gpio-keys-polled"; #size-cells = <0>; @@ -141,28 +130,6 @@ status = "okay"; }; -ðernet0 { - status = "okay"; - pinctrl-0 = <ðernet0_rmii_pins_a>; - pinctrl-1 = <ðernet0_rmii_sleep_pins_a>; - pinctrl-names = "default", "sleep"; - phy-mode = "rmii"; - max-speed = <100>; - phy-handle = <&phy0>; - st,eth-ref-clk-sel; - phy-reset-gpios = <&gpioh 15 GPIO_ACTIVE_LOW>; - - mdio0 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "snps,dwmac-mdio"; - - phy0: ethernet-phy@1 { - reg = <1>; - }; - }; -}; - &i2c2 { /* Header X22 */ pinctrl-names = "default"; pinctrl-0 = <&i2c2_pins_a>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index ba905196fb54..a87ebc484396 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -9,6 +9,10 @@ #include <dt-bindings/mfd/st,stpmic1.h> / { + aliases { + ethernet0 = ðernet0; + }; + memory@c0000000 { device_type = "memory"; reg = <0xC0000000 0x40000000>; @@ -55,6 +59,16 @@ no-map; }; }; + + ethernet_vio: vioregulator { + compatible = "regulator-fixed"; + regulator-name = "vio"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpiog 3 GPIO_ACTIVE_LOW>; + regulator-always-on; + regulator-boot-on; + }; }; &adc { @@ -94,6 +108,28 @@ status = "okay"; }; +ðernet0 { + status = "okay"; + pinctrl-0 = <ðernet0_rmii_pins_a>; + pinctrl-1 = <ðernet0_rmii_sleep_pins_a>; + pinctrl-names = "default", "sleep"; + phy-mode = "rmii"; + max-speed = <100>; + phy-handle = <&phy0>; + st,eth-ref-clk-sel; + phy-reset-gpios = <&gpioh 3 GPIO_ACTIVE_LOW>; + + mdio0 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + phy0: ethernet-phy@1 { + reg = <1>; + }; + }; +}; + &i2c4 { pinctrl-names = "default"; pinctrl-0 = <&i2c4_pins_a>; @@ -249,7 +285,7 @@ compatible = "ti,tsc2004"; reg = <0x49>; vio-supply = <&v3v3>; - interrupts-extended = <&gpioh 3 IRQ_TYPE_EDGE_FALLING>; + interrupts-extended = <&gpioh 15 IRQ_TYPE_EDGE_FALLING>; }; eeprom@50 { diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi index 930202742a3f..905cd7bb98cf 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi @@ -295,9 +295,9 @@ &sdmmc2 { pinctrl-names = "default", "opendrain", "sleep"; - pinctrl-0 = <&sdmmc2_b4_pins_a &sdmmc2_d47_pins_b>; - pinctrl-1 = <&sdmmc2_b4_od_pins_a &sdmmc2_d47_pins_b>; - pinctrl-2 = <&sdmmc2_b4_sleep_pins_a &sdmmc2_d47_sleep_pins_b>; + pinctrl-0 = <&sdmmc2_b4_pins_a &sdmmc2_d47_pins_c>; + pinctrl-1 = <&sdmmc2_b4_od_pins_a &sdmmc2_d47_pins_c>; + pinctrl-2 = <&sdmmc2_b4_sleep_pins_a &sdmmc2_d47_sleep_pins_c>; bus-width = <8>; mmc-ddr-1_8v; no-sd; diff --git a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts index 42d62d1ba1dc..ea15073f0c79 100644 --- a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts +++ b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts @@ -223,16 +223,16 @@ }; ®_dc1sw { - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-name = "vcc-gmac-phy"; }; ®_dcdc1 { regulator-always-on; - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; - regulator-name = "vcc-3v0"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc-3v3"; }; ®_dcdc2 { diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 2aab043441e8..eae8aaaadc3b 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -800,6 +800,7 @@ static void __init at91_pm_init(void (*pm_idle)(void)) pmc_np = of_find_matching_node_and_match(NULL, atmel_pmc_ids, &of_id); soc_pm.data.pmc = of_iomap(pmc_np, 0); + of_node_put(pmc_np); if (!soc_pm.data.pmc) { pr_err("AT91: PM not supported, PMC not found\n"); return; diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index 6f5f89711f25..a92d277f81a0 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -174,8 +174,10 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, */ if (mpuss_can_lose_context) { error = cpu_cluster_pm_enter(); - if (error) + if (error) { + omap_set_pwrdm_state(mpu_pd, PWRDM_POWER_ON); goto cpu_cluster_pm_out; + } } } diff --git a/arch/arm/mach-s3c24xx/mach-at2440evb.c b/arch/arm/mach-s3c24xx/mach-at2440evb.c index 58c5ef3cf1d7..2d370f7f75fa 100644 --- a/arch/arm/mach-s3c24xx/mach-at2440evb.c +++ b/arch/arm/mach-s3c24xx/mach-at2440evb.c @@ -143,7 +143,7 @@ static struct gpiod_lookup_table at2440evb_mci_gpio_table = { .dev_id = "s3c2410-sdi", .table = { /* Card detect S3C2410_GPG(10) */ - GPIO_LOOKUP("GPG", 10, "cd", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOG", 10, "cd", GPIO_ACTIVE_LOW), { }, }, }; diff --git a/arch/arm/mach-s3c24xx/mach-h1940.c b/arch/arm/mach-s3c24xx/mach-h1940.c index e1c372e5447b..82cc37513779 100644 --- a/arch/arm/mach-s3c24xx/mach-h1940.c +++ b/arch/arm/mach-s3c24xx/mach-h1940.c @@ -468,9 +468,9 @@ static struct gpiod_lookup_table h1940_mmc_gpio_table = { .dev_id = "s3c2410-sdi", .table = { /* Card detect S3C2410_GPF(5) */ - GPIO_LOOKUP("GPF", 5, "cd", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOF", 5, "cd", GPIO_ACTIVE_LOW), /* Write protect S3C2410_GPH(8) */ - GPIO_LOOKUP("GPH", 8, "wp", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOH", 8, "wp", GPIO_ACTIVE_LOW), { }, }, }; diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c index 9035f868fb34..3a5b1124037b 100644 --- a/arch/arm/mach-s3c24xx/mach-mini2440.c +++ b/arch/arm/mach-s3c24xx/mach-mini2440.c @@ -244,9 +244,9 @@ static struct gpiod_lookup_table mini2440_mmc_gpio_table = { .dev_id = "s3c2410-sdi", .table = { /* Card detect S3C2410_GPG(8) */ - GPIO_LOOKUP("GPG", 8, "cd", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOG", 8, "cd", GPIO_ACTIVE_LOW), /* Write protect S3C2410_GPH(8) */ - GPIO_LOOKUP("GPH", 8, "wp", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("GPIOH", 8, "wp", GPIO_ACTIVE_HIGH), { }, }, }; diff --git a/arch/arm/mach-s3c24xx/mach-n30.c b/arch/arm/mach-s3c24xx/mach-n30.c index d856f23939af..ffa20f52aa83 100644 --- a/arch/arm/mach-s3c24xx/mach-n30.c +++ b/arch/arm/mach-s3c24xx/mach-n30.c @@ -359,9 +359,9 @@ static struct gpiod_lookup_table n30_mci_gpio_table = { .dev_id = "s3c2410-sdi", .table = { /* Card detect S3C2410_GPF(1) */ - GPIO_LOOKUP("GPF", 1, "cd", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOF", 1, "cd", GPIO_ACTIVE_LOW), /* Write protect S3C2410_GPG(10) */ - GPIO_LOOKUP("GPG", 10, "wp", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOG", 10, "wp", GPIO_ACTIVE_LOW), { }, }, }; diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c index fde98b175c75..c0a06f123cfe 100644 --- a/arch/arm/mach-s3c24xx/mach-rx1950.c +++ b/arch/arm/mach-s3c24xx/mach-rx1950.c @@ -571,9 +571,9 @@ static struct gpiod_lookup_table rx1950_mmc_gpio_table = { .dev_id = "s3c2410-sdi", .table = { /* Card detect S3C2410_GPF(5) */ - GPIO_LOOKUP("GPF", 5, "cd", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOF", 5, "cd", GPIO_ACTIVE_LOW), /* Write protect S3C2410_GPH(8) */ - GPIO_LOOKUP("GPH", 8, "wp", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOH", 8, "wp", GPIO_ACTIVE_LOW), { }, }, }; diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 12c26eb88afb..43d91bfd2360 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -1249,20 +1249,28 @@ static void __init l2c310_of_parse(const struct device_node *np, ret = of_property_read_u32(np, "prefetch-data", &val); if (ret == 0) { - if (val) + if (val) { prefetch |= L310_PREFETCH_CTRL_DATA_PREFETCH; - else + *aux_val |= L310_PREFETCH_CTRL_DATA_PREFETCH; + } else { prefetch &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; + *aux_val &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; + } + *aux_mask &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; } else if (ret != -EINVAL) { pr_err("L2C-310 OF prefetch-data property value is missing\n"); } ret = of_property_read_u32(np, "prefetch-instr", &val); if (ret == 0) { - if (val) + if (val) { prefetch |= L310_PREFETCH_CTRL_INSTR_PREFETCH; - else + *aux_val |= L310_PREFETCH_CTRL_INSTR_PREFETCH; + } else { prefetch &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; + *aux_val &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; + } + *aux_mask &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; } else if (ret != -EINVAL) { pr_err("L2C-310 OF prefetch-instr property value is missing\n"); } diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index d5fe7c9e0be1..5a3442346418 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,14 +10,14 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=--no-undefined -X +LDFLAGS_vmlinux :=--no-undefined -X -z norelro CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET) ifeq ($(CONFIG_RELOCATABLE), y) # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour # for relative relocs, since this leads to better Image compression # with the relocation offsets always being zero. -LDFLAGS_vmlinux += -shared -Bsymbolic -z notext -z norelro \ +LDFLAGS_vmlinux += -shared -Bsymbolic -z notext \ $(call ld-option, --no-apply-dynamic-relocs) endif diff --git a/arch/arm64/boot/dts/actions/s700.dtsi b/arch/arm64/boot/dts/actions/s700.dtsi index 2006ad5424fa..f8eb72bb4125 100644 --- a/arch/arm64/boot/dts/actions/s700.dtsi +++ b/arch/arm64/boot/dts/actions/s700.dtsi @@ -231,7 +231,7 @@ pinctrl: pinctrl@e01b0000 { compatible = "actions,s700-pinctrl"; - reg = <0x0 0xe01b0000 0x0 0x1000>; + reg = <0x0 0xe01b0000 0x0 0x100>; clocks = <&cmu CLK_GPIO>; gpio-controller; gpio-ranges = <&pinctrl 0 0 136>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi index 4462a68c0681..cdc4209f94d0 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi @@ -125,8 +125,7 @@ <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>; + <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "gp", "gpmmu", "pp", @@ -137,8 +136,7 @@ "pp2", "ppmmu2", "pp3", - "ppmmu3", - "pmu"; + "ppmmu3"; clocks = <&ccu CLK_BUS_GPU>, <&ccu CLK_GPU>; clock-names = "bus", "core"; resets = <&ccu RST_BUS_GPU>; diff --git a/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi b/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi index ff5ba85b7562..833bbc3359c4 100644 --- a/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi @@ -41,13 +41,13 @@ led-white { label = "vim3:white:sys"; - gpios = <&gpio_ao GPIOAO_4 GPIO_ACTIVE_LOW>; + gpios = <&gpio_ao GPIOAO_4 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; }; led-red { label = "vim3:red"; - gpios = <&gpio_expander 5 GPIO_ACTIVE_LOW>; + gpios = <&gpio_expander 5 GPIO_ACTIVE_HIGH>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 66ac66856e7e..077e12a0de3f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -614,6 +614,7 @@ gpc: gpc@303a0000 { compatible = "fsl,imx8mq-gpc"; reg = <0x303a0000 0x10000>; + interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; interrupt-controller; #interrupt-cells = <3>; diff --git a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi index a5a12b2599a4..01522dd10603 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi @@ -431,12 +431,11 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&nor_gpio1_pins>; - bus-width = <8>; - max-frequency = <50000000>; - non-removable; + flash@0 { compatible = "jedec,spi-nor"; reg = <0>; + spi-max-frequency = <50000000>; }; }; diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index 32bd140ac9fd..103d2226c579 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -228,14 +228,14 @@ }; thermal-zones { - cpu0_1-thermal { + cpu0-1-thermal { polling-delay-passive = <250>; polling-delay = <1000>; thermal-sensors = <&tsens 5>; trips { - cpu0_1_alert0: trip-point@0 { + cpu0_1_alert0: trip-point0 { temperature = <75000>; hysteresis = <2000>; type = "passive"; @@ -258,7 +258,7 @@ }; }; - cpu2_3-thermal { + cpu2-3-thermal { polling-delay-passive = <250>; polling-delay = <1000>; @@ -1021,7 +1021,7 @@ reg-names = "mdp_phys"; interrupt-parent = <&mdss>; - interrupts = <0 0>; + interrupts = <0>; clocks = <&gcc GCC_MDSS_AHB_CLK>, <&gcc GCC_MDSS_AXI_CLK>, @@ -1053,7 +1053,7 @@ reg-names = "dsi_ctrl"; interrupt-parent = <&mdss>; - interrupts = <4 0>; + interrupts = <4>; assigned-clocks = <&gcc BYTE0_CLK_SRC>, <&gcc PCLK0_CLK_SRC>; diff --git a/arch/arm64/boot/dts/qcom/pm8916.dtsi b/arch/arm64/boot/dts/qcom/pm8916.dtsi index 0bcdf0471107..adf9a5988cdc 100644 --- a/arch/arm64/boot/dts/qcom/pm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/pm8916.dtsi @@ -119,7 +119,7 @@ wcd_codec: codec@f000 { compatible = "qcom,pm8916-wcd-analog-codec"; - reg = <0xf000 0x200>; + reg = <0xf000>; reg-names = "pmic-codec-core"; clocks = <&gcc GCC_CODEC_DIGCODEC_CLK>; clock-names = "mclk"; diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index 31b9217bb5bf..7f1b75b2bcee 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -2193,7 +2193,7 @@ system-cache-controller@9200000 { compatible = "qcom,sc7180-llcc"; - reg = <0 0x09200000 0 0x200000>, <0 0x09600000 0 0x50000>; + reg = <0 0x09200000 0 0x50000>, <0 0x09600000 0 0x50000>; reg-names = "llcc_base", "llcc_broadcast_base"; interrupts = <GIC_SPI 582 IRQ_TYPE_LEVEL_HIGH>; }; @@ -2357,7 +2357,7 @@ <19200000>; interrupt-parent = <&mdss>; - interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <0>; status = "disabled"; @@ -2380,7 +2380,7 @@ reg-names = "dsi_ctrl"; interrupt-parent = <&mdss>; - interrupts = <4 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <4>; clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK>, <&dispcc DISP_CC_MDSS_BYTE0_INTF_CLK>, diff --git a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi index 42171190cce4..065e8fe3a071 100644 --- a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi @@ -1214,9 +1214,8 @@ reg = <0 0xe6ea0000 0 0x0064>; interrupts = <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cpg CPG_MOD 210>; - dmas = <&dmac1 0x43>, <&dmac1 0x42>, - <&dmac2 0x43>, <&dmac2 0x42>; - dma-names = "tx", "rx", "tx", "rx"; + dmas = <&dmac0 0x43>, <&dmac0 0x42>; + dma-names = "tx", "rx"; power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>; resets = <&cpg 210>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/renesas/r8a77990.dtsi b/arch/arm64/boot/dts/renesas/r8a77990.dtsi index 1991bdc36792..27f74df8efbd 100644 --- a/arch/arm64/boot/dts/renesas/r8a77990.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77990.dtsi @@ -1192,9 +1192,8 @@ reg = <0 0xe6ea0000 0 0x0064>; interrupts = <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cpg CPG_MOD 210>; - dmas = <&dmac1 0x43>, <&dmac1 0x42>, - <&dmac2 0x43>, <&dmac2 0x42>; - dma-names = "tx", "rx", "tx", "rx"; + dmas = <&dmac0 0x43>, <&dmac0 0x42>; + dma-names = "tx", "rx"; power-domains = <&sysc R8A77990_PD_ALWAYS_ON>; resets = <&cpg 210>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 9174ddc76bdc..b8d04c5748bf 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -500,7 +500,7 @@ }; i2c0: i2c@ff020000 { - compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 17 4>; @@ -511,7 +511,7 @@ }; i2c1: i2c@ff030000 { - compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 18 4>; diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 0bc46149e491..4b39293d0f72 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -359,9 +359,13 @@ __AARCH64_INSN_FUNCS(brk, 0xFFE0001F, 0xD4200000) __AARCH64_INSN_FUNCS(exception, 0xFF000000, 0xD4000000) __AARCH64_INSN_FUNCS(hint, 0xFFFFF01F, 0xD503201F) __AARCH64_INSN_FUNCS(br, 0xFFFFFC1F, 0xD61F0000) +__AARCH64_INSN_FUNCS(br_auth, 0xFEFFF800, 0xD61F0800) __AARCH64_INSN_FUNCS(blr, 0xFFFFFC1F, 0xD63F0000) +__AARCH64_INSN_FUNCS(blr_auth, 0xFEFFF800, 0xD63F0800) __AARCH64_INSN_FUNCS(ret, 0xFFFFFC1F, 0xD65F0000) +__AARCH64_INSN_FUNCS(ret_auth, 0xFFFFFBFF, 0xD65F0BFF) __AARCH64_INSN_FUNCS(eret, 0xFFFFFFFF, 0xD69F03E0) +__AARCH64_INSN_FUNCS(eret_auth, 0xFFFFFBFF, 0xD69F0BFF) __AARCH64_INSN_FUNCS(mrs, 0xFFF00000, 0xD5300000) __AARCH64_INSN_FUNCS(msr_imm, 0xFFF8F01F, 0xD500401F) __AARCH64_INSN_FUNCS(msr_reg, 0xFFF00000, 0xD5100000) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index a1871bb32bb1..d207f63eb68e 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -163,7 +163,6 @@ extern u64 vabits_actual; #include <linux/bitops.h> #include <linux/mmdebug.h> -extern s64 physvirt_offset; extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ #define PHYS_OFFSET ({ VM_BUG_ON(memstart_addr & 1); memstart_addr; }) @@ -239,7 +238,7 @@ static inline const void *__tag_set(const void *addr, u8 tag) */ #define __is_lm_address(addr) (!(((u64)addr) & BIT(vabits_actual - 1))) -#define __lm_to_phys(addr) (((addr) + physvirt_offset)) +#define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) #define __virt_to_phys_nodebug(x) ({ \ @@ -257,7 +256,7 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #define __phys_addr_symbol(x) __pa_symbol_nodebug(x) #endif /* CONFIG_DEBUG_VIRTUAL */ -#define __phys_to_virt(x) ((unsigned long)((x) - physvirt_offset)) +#define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET) #define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset)) /* diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 758e2d1577d0..a1745d6ea4b5 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -23,6 +23,8 @@ #define VMALLOC_START (MODULES_END) #define VMALLOC_END (- PUD_SIZE - VMEMMAP_SIZE - SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) + #define FIRST_USER_ADDRESS 0UL #ifndef __ASSEMBLY__ @@ -33,8 +35,6 @@ #include <linux/mm_types.h> #include <linux/sched.h> -extern struct page *vmemmap; - extern void __pte_error(const char *file, int line, unsigned long val); extern void __pmd_error(const char *file, int line, unsigned long val); extern void __pud_error(const char *file, int line, unsigned long val); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 422ed2e38a6c..d8a2bacf4e0a 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -234,14 +234,17 @@ static int detect_harden_bp_fw(void) smccc_end = NULL; break; -#if IS_ENABLED(CONFIG_KVM) case SMCCC_CONDUIT_SMC: cb = call_smc_arch_workaround_1; +#if IS_ENABLED(CONFIG_KVM) smccc_start = __smccc_workaround_1_smc; smccc_end = __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ; - break; +#else + smccc_start = NULL; + smccc_end = NULL; #endif + break; default: return -1; @@ -454,6 +457,12 @@ out_printmsg: return required; } +static void cpu_enable_ssbd_mitigation(const struct arm64_cpu_capabilities *cap) +{ + if (ssbd_state != ARM64_SSBD_FORCE_DISABLE) + cap->matches(cap, SCOPE_LOCAL_CPU); +} + /* known invulnerable cores */ static const struct midr_range arm64_ssb_cpus[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), @@ -596,6 +605,12 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope) return (need_wa > 0); } +static void +cpu_enable_branch_predictor_hardening(const struct arm64_cpu_capabilities *cap) +{ + cap->matches(cap, SCOPE_LOCAL_CPU); +} + static const __maybe_unused struct midr_range tx2_family_cpus[] = { MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), @@ -887,9 +902,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = { }, #endif { + .desc = "Branch predictor hardening", .capability = ARM64_HARDEN_BRANCH_PREDICTOR, .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = check_branch_predictor, + .cpu_enable = cpu_enable_branch_predictor_hardening, }, #ifdef CONFIG_HARDEN_EL2_VECTORS { @@ -903,6 +920,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .capability = ARM64_SSBD, .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = has_ssbd_mitigation, + .cpu_enable = cpu_enable_ssbd_mitigation, .midr_range_list = arm64_ssb_cpus, }, #ifdef CONFIG_ARM64_ERRATUM_1418040 diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index a107375005bc..ccc8c9e22b25 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -176,7 +176,7 @@ bool __kprobes aarch64_insn_uses_literal(u32 insn) bool __kprobes aarch64_insn_is_branch(u32 insn) { - /* b, bl, cb*, tb*, b.cond, br, blr */ + /* b, bl, cb*, tb*, ret*, b.cond, br*, blr* */ return aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn) || @@ -185,8 +185,11 @@ bool __kprobes aarch64_insn_is_branch(u32 insn) aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn) || aarch64_insn_is_ret(insn) || + aarch64_insn_is_ret_auth(insn) || aarch64_insn_is_br(insn) || + aarch64_insn_is_br_auth(insn) || aarch64_insn_is_blr(insn) || + aarch64_insn_is_blr_auth(insn) || aarch64_insn_is_bcond(insn); } diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 581602413a13..c26d84ff0e22 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -510,6 +510,11 @@ static u32 armv8pmu_event_cnten_mask(struct perf_event *event) static inline void armv8pmu_enable_counter(u32 mask) { + /* + * Make sure event configuration register writes are visible before we + * enable the counter. + * */ + isb(); write_sysreg(mask, pmcntenset_el0); } diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c index 263d5fba4c8a..c541fb48886e 100644 --- a/arch/arm64/kernel/probes/decode-insn.c +++ b/arch/arm64/kernel/probes/decode-insn.c @@ -29,7 +29,8 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn) aarch64_insn_is_msr_imm(insn) || aarch64_insn_is_msr_reg(insn) || aarch64_insn_is_exception(insn) || - aarch64_insn_is_eret(insn)) + aarch64_insn_is_eret(insn) || + aarch64_insn_is_eret_auth(insn)) return false; /* diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 1e93cfc7c47a..ca4410eb230a 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -54,12 +54,6 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); -s64 physvirt_offset __ro_after_init; -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 @@ -290,20 +284,6 @@ void __init arm64_memblock_init(void) memstart_addr = round_down(memblock_start_of_DRAM(), ARM64_MEMSTART_ALIGN); - physvirt_offset = PHYS_OFFSET - PAGE_OFFSET; - - vmemmap = ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)); - - /* - * If we are running with a 52-bit kernel VA config on a system that - * does not support it, we have to offset our vmemmap and physvirt_offset - * s.t. we avoid the 52-bit portion of the direct linear map - */ - if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) { - vmemmap += (_PAGE_OFFSET(48) - _PAGE_OFFSET(52)) >> PAGE_SHIFT; - physvirt_offset = PHYS_OFFSET - _PAGE_OFFSET(48); - } - /* * Remove the memory that we will not be able to cover with the * linear mapping. Take care not to clip the kernel which may be @@ -319,6 +299,16 @@ void __init arm64_memblock_init(void) } /* + * If we are running with a 52-bit kernel VA config on a system that + * does not support it, we have to place the available physical + * memory in the 48-bit addressable part of the linear region, i.e., + * we have to move it upward. Since memstart_addr represents the + * physical address of PAGE_OFFSET, we have to *subtract* from it. + */ + if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) + memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52); + + /* * Apply the memory limit if it was set. Since the kernel may be loaded * high up in memory, add back the kernel region that must be accessible * via the linear mapping. diff --git a/arch/m68k/coldfire/device.c b/arch/m68k/coldfire/device.c index 9ef4ec0aea00..59f7dfe50a4d 100644 --- a/arch/m68k/coldfire/device.c +++ b/arch/m68k/coldfire/device.c @@ -554,7 +554,7 @@ static struct platform_device mcf_edma = { }; #endif /* IS_ENABLED(CONFIG_MCF_EDMA) */ -#if IS_ENABLED(CONFIG_MMC) +#ifdef MCFSDHC_BASE static struct mcf_esdhc_platform_data mcf_esdhc_data = { .max_bus_width = 4, .cd_type = ESDHC_CD_NONE, @@ -579,7 +579,7 @@ static struct platform_device mcf_esdhc = { .resource = mcf_esdhc_resources, .dev.platform_data = &mcf_esdhc_data, }; -#endif /* IS_ENABLED(CONFIG_MMC) */ +#endif /* MCFSDHC_BASE */ static struct platform_device *mcf_devices[] __initdata = { &mcf_uart, @@ -613,7 +613,7 @@ static struct platform_device *mcf_devices[] __initdata = { #if IS_ENABLED(CONFIG_MCF_EDMA) &mcf_edma, #endif -#if IS_ENABLED(CONFIG_MMC) +#ifdef MCFSDHC_BASE &mcf_esdhc, #endif }; diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 2e87a9b6d312..63bce836b9f1 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h generic-y += extable.h -generic-y += hw_irq.h generic-y += kvm_para.h generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h index 17c24f14615f..6839f8fcf76b 100644 --- a/arch/openrisc/include/asm/uaccess.h +++ b/arch/openrisc/include/asm/uaccess.h @@ -164,19 +164,19 @@ struct __large_struct { #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; \ - 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; \ + long __gu_err = -EFAULT; \ + const __typeof__(*(ptr)) *__gu_addr = (ptr); \ + if (access_ok(__gu_addr, size)) \ + __get_user_size((x), __gu_addr, (size), __gu_err); \ + else \ + (x) = (__typeof__(*(ptr))) 0; \ __gu_err; \ }) @@ -190,11 +190,13 @@ do { \ case 2: __get_user_asm(x, ptr, retval, "l.lhz"); break; \ case 4: __get_user_asm(x, ptr, retval, "l.lwz"); break; \ case 8: __get_user_asm2(x, ptr, retval); break; \ - default: (x) = __get_user_bad(); \ + default: (x) = (__typeof__(*(ptr)))__get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, err, op) \ +{ \ + unsigned long __gu_tmp; \ __asm__ __volatile__( \ "1: "op" %1,0(%2)\n" \ "2:\n" \ @@ -208,10 +210,14 @@ do { \ " .align 2\n" \ " .long 1b,3b\n" \ ".previous" \ - : "=r"(err), "=r"(x) \ - : "r"(addr), "i"(-EFAULT), "0"(err)) + : "=r"(err), "=r"(__gu_tmp) \ + : "r"(addr), "i"(-EFAULT), "0"(err)); \ + (x) = (__typeof__(*(addr)))__gu_tmp; \ +} #define __get_user_asm2(x, addr, err) \ +{ \ + unsigned long long __gu_tmp; \ __asm__ __volatile__( \ "1: l.lwz %1,0(%2)\n" \ "2: l.lwz %H1,4(%2)\n" \ @@ -228,8 +234,11 @@ do { \ " .long 1b,4b\n" \ " .long 2b,4b\n" \ ".previous" \ - : "=r"(err), "=&r"(x) \ - : "r"(addr), "i"(-EFAULT), "0"(err)) + : "=r"(err), "=&r"(__gu_tmp) \ + : "r"(addr), "i"(-EFAULT), "0"(err)); \ + (x) = (__typeof__(*(addr)))( \ + (__typeof__((x)-(x)))__gu_tmp); \ +} /* more complex routines */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 9fa23eb320ff..cf78ad7ff0b7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -135,7 +135,7 @@ config PPC select ARCH_HAS_STRICT_KERNEL_RWX if (PPC32 && !HIBERNATION) select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE - select ARCH_HAS_UACCESS_MCSAFE if PPC64 + select ARCH_HAS_COPY_MC if PPC64 select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_KEEP_MEMBLOCK diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 3f9ae3585ab9..80c953414882 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -13,20 +13,19 @@ */ #define MAX_EA_BITS_PER_CONTEXT 46 -#define REGION_SHIFT (MAX_EA_BITS_PER_CONTEXT - 2) /* - * Our page table limit us to 64TB. Hence for the kernel mapping, - * each MAP area is limited to 16 TB. - * The four map areas are: linear mapping, vmap, IO and vmemmap + * Our page table limit us to 64TB. For 64TB physical memory, we only need 64GB + * of vmemmap space. To better support sparse memory layout, we use 61TB + * linear map range, 1TB of vmalloc, 1TB of I/O and 1TB of vmememmap. */ +#define REGION_SHIFT (40) #define H_KERN_MAP_SIZE (ASM_CONST(1) << REGION_SHIFT) /* - * Define the address range of the kernel non-linear virtual area - * 16TB + * Define the address range of the kernel non-linear virtual area (61TB) */ -#define H_KERN_VIRT_START ASM_CONST(0xc000100000000000) +#define H_KERN_VIRT_START ASM_CONST(0xc0003d0000000000) #ifndef __ASSEMBLY__ #define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 414d209f45bb..c711fe890110 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -8,14 +8,13 @@ #ifndef _ASM_POWERPC_LMB_H #define _ASM_POWERPC_LMB_H +#include <linux/sched.h> + struct drmem_lmb { u64 base_addr; u32 drc_index; u32 aa_index; u32 flags; -#ifdef CONFIG_MEMORY_HOTPLUG - int nid; -#endif }; struct drmem_lmb_info { @@ -26,8 +25,22 @@ struct drmem_lmb_info { extern struct drmem_lmb_info *drmem_info; +static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb, + const struct drmem_lmb *start) +{ + /* + * DLPAR code paths can take several milliseconds per element + * when interacting with firmware. Ensure that we don't + * unfairly monopolize the CPU. + */ + if (((++lmb - start) % 16) == 0) + cond_resched(); + + return lmb; +} + #define for_each_drmem_lmb_in_range(lmb, start, end) \ - for ((lmb) = (start); (lmb) < (end); (lmb)++) + for ((lmb) = (start); (lmb) < (end); lmb = drmem_lmb_next(lmb, start)) #define for_each_drmem_lmb(lmb) \ for_each_drmem_lmb_in_range((lmb), \ @@ -104,22 +117,4 @@ static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb) lmb->aa_index = 0xffffffff; } -#ifdef CONFIG_MEMORY_HOTPLUG -static inline void lmb_set_nid(struct drmem_lmb *lmb) -{ - lmb->nid = memory_add_physaddr_to_nid(lmb->base_addr); -} -static inline void lmb_clear_nid(struct drmem_lmb *lmb) -{ - lmb->nid = -1; -} -#else -static inline void lmb_set_nid(struct drmem_lmb *lmb) -{ -} -static inline void lmb_clear_nid(struct drmem_lmb *lmb) -{ -} -#endif - #endif /* _ASM_POWERPC_LMB_H */ diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index cb424799da0d..5a00da670a40 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -40,6 +40,7 @@ struct arch_hw_breakpoint { #else #define HW_BREAKPOINT_SIZE 0x8 #endif +#define HW_BREAKPOINT_SIZE_QUADWORD 0x10 #define DABR_MAX_LEN 8 #define DAWR_MAX_LEN 512 diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 88e6c78100d9..c750afc62887 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -815,7 +815,7 @@ #define THRM1_TIN (1 << 31) #define THRM1_TIV (1 << 30) #define THRM1_THRES(x) ((x&0x7f)<<23) -#define THRM3_SITV(x) ((x&0x3fff)<<1) +#define THRM3_SITV(x) ((x & 0x1fff) << 1) #define THRM1_TID (1<<2) #define THRM1_TIE (1<<1) #define THRM1_V (1<<0) diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index b72692702f35..9bf6dffb4090 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -53,9 +53,7 @@ void *__memmove(void *to, const void *from, __kernel_size_t n); #ifndef CONFIG_KASAN #define __HAVE_ARCH_MEMSET32 #define __HAVE_ARCH_MEMSET64 -#define __HAVE_ARCH_MEMCPY_MCSAFE -extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz); extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t); extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t); extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t); diff --git a/arch/powerpc/include/asm/svm.h b/arch/powerpc/include/asm/svm.h index 85580b30aba4..7546402d796a 100644 --- a/arch/powerpc/include/asm/svm.h +++ b/arch/powerpc/include/asm/svm.h @@ -15,6 +15,8 @@ static inline bool is_secure_guest(void) return mfmsr() & MSR_S; } +void __init svm_swiotlb_init(void); + void dtl_cache_ctor(void *addr); #define get_dtl_cache_ctor() (is_secure_guest() ? dtl_cache_ctor : NULL) @@ -25,6 +27,8 @@ static inline bool is_secure_guest(void) return false; } +static inline void svm_swiotlb_init(void) {} + #define get_dtl_cache_ctor() NULL #endif /* CONFIG_PPC_SVM */ diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index 862985cf5180..cf87bbdcfdcb 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -67,19 +67,6 @@ static inline int mm_is_thread_local(struct mm_struct *mm) return false; return cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)); } -static inline void mm_reset_thread_local(struct mm_struct *mm) -{ - WARN_ON(atomic_read(&mm->context.copros) > 0); - /* - * It's possible for mm_access to take a reference on mm_users to - * access the remote mm from another thread, but it's not allowed - * to set mm_cpumask, so mm_users may be > 1 here. - */ - WARN_ON(current->mm != mm); - atomic_set(&mm->context.active_cpus, 1); - cpumask_clear(mm_cpumask(mm)); - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); -} #else /* CONFIG_PPC_BOOK3S_64 */ static inline int mm_is_thread_local(struct mm_struct *mm) { diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 64c04ab09112..97506441c15b 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -436,6 +436,32 @@ do { \ extern unsigned long __copy_tofrom_user(void __user *to, const void __user *from, unsigned long size); +#ifdef CONFIG_ARCH_HAS_COPY_MC +unsigned long __must_check +copy_mc_generic(void *to, const void *from, unsigned long size); + +static inline unsigned long __must_check +copy_mc_to_kernel(void *to, const void *from, unsigned long size) +{ + return copy_mc_generic(to, from, size); +} +#define copy_mc_to_kernel copy_mc_to_kernel + +static inline unsigned long __must_check +copy_mc_to_user(void __user *to, const void *from, unsigned long n) +{ + if (likely(check_copy_size(from, n, true))) { + if (access_ok(to, n)) { + allow_write_to_user(to, n); + n = copy_mc_generic((void *)to, from, n); + prevent_write_to_user(to, n); + } + } + + return n; +} +#endif + #ifdef __powerpc64__ static inline unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) @@ -524,20 +550,6 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) return ret; } -static __always_inline unsigned long __must_check -copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n) -{ - if (likely(check_copy_size(from, n, true))) { - if (access_ok(to, n)) { - allow_write_to_user(to, n); - n = memcpy_mcsafe((void *)to, from, n); - prevent_write_to_user(to, n); - } - } - - return n; -} - unsigned long __arch_clear_user(void __user *addr, unsigned long size); static inline unsigned long clear_user(void __user *addr, unsigned long size) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index c55e67bab271..2190be70c7fd 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -519,9 +519,17 @@ static bool ea_hw_range_overlaps(unsigned long ea, int size, struct arch_hw_breakpoint *info) { unsigned long hw_start_addr, hw_end_addr; + unsigned long align_size = HW_BREAKPOINT_SIZE; - hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE); - hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE); + /* + * On p10 predecessors, quadword is handle differently then + * other instructions. + */ + if (!cpu_has_feature(CPU_FTR_ARCH_31) && size == 16) + align_size = HW_BREAKPOINT_SIZE_QUADWORD; + + hw_start_addr = ALIGN_DOWN(info->address, align_size); + hw_end_addr = ALIGN(info->address + info->len, align_size); return ((ea < hw_end_addr) && (ea + size > hw_start_addr)); } @@ -635,6 +643,8 @@ static void get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, if (*type == CACHEOP) { *size = cache_op_size(); *ea &= ~(*size - 1); + } else if (*type == LOAD_VMX || *type == STORE_VMX) { + *ea &= ~(*size - 1); } } diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 05b1cc0e009e..3a22281a8264 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -214,7 +214,7 @@ void replay_soft_interrupts(void) struct pt_regs regs; ppc_save_regs(®s); - regs.softe = IRQS_ALL_DISABLED; + regs.softe = IRQS_ENABLED; again: if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) @@ -368,6 +368,12 @@ notrace void arch_local_irq_restore(unsigned long mask) } } + /* + * Disable preempt here, so that the below preempt_enable will + * perform resched if required (a replayed interrupt may set + * need_resched). + */ + preempt_disable(); irq_soft_mask_set(IRQS_ALL_DISABLED); trace_hardirqs_off(); @@ -377,6 +383,7 @@ notrace void arch_local_irq_restore(unsigned long mask) trace_hardirqs_on(); irq_soft_mask_set(IRQS_ENABLED); __hard_irq_enable(); + preempt_enable(); } EXPORT_SYMBOL(arch_local_irq_restore); diff --git a/arch/powerpc/kernel/ptrace/ptrace-noadv.c b/arch/powerpc/kernel/ptrace/ptrace-noadv.c index 697c7e4b5877..8bd8d8de5c40 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-noadv.c +++ b/arch/powerpc/kernel/ptrace/ptrace-noadv.c @@ -219,6 +219,7 @@ long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_inf brk.address = ALIGN_DOWN(bp_info->addr, HW_BREAKPOINT_SIZE); brk.type = HW_BRK_TYPE_TRANSLATE; brk.len = DABR_MAX_LEN; + brk.hw_len = DABR_MAX_LEN; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) brk.type |= HW_BRK_TYPE_READ; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index e2ab8a111b69..0b4694b8d248 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -13,13 +13,14 @@ */ #include <linux/errno.h> -#include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/param.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/init.h> +#include <linux/delay.h> +#include <linux/workqueue.h> #include <asm/io.h> #include <asm/reg.h> @@ -39,9 +40,7 @@ static struct tau_temp unsigned char grew; } tau[NR_CPUS]; -struct timer_list tau_timer; - -#undef DEBUG +static bool tau_int_enable; /* TODO: put these in a /proc interface, with some sanity checks, and maybe * dynamic adjustment to minimize # of interrupts */ @@ -50,72 +49,49 @@ struct timer_list tau_timer; #define step_size 2 /* step size when temp goes out of range */ #define window_expand 1 /* expand the window by this much */ /* configurable values for shrinking the window */ -#define shrink_timer 2*HZ /* period between shrinking the window */ +#define shrink_timer 2000 /* period between shrinking the window */ #define min_window 2 /* minimum window size, degrees C */ static void set_thresholds(unsigned long cpu) { -#ifdef CONFIG_TAU_INT - /* - * setup THRM1, - * threshold, valid bit, enable interrupts, interrupt when below threshold - */ - mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TIE | THRM1_TID); + u32 maybe_tie = tau_int_enable ? THRM1_TIE : 0; - /* setup THRM2, - * threshold, valid bit, enable interrupts, interrupt when above threshold - */ - mtspr (SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | THRM1_TIE); -#else - /* same thing but don't enable interrupts */ - mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TID); - mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V); -#endif + /* setup THRM1, threshold, valid bit, interrupt when below threshold */ + mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | maybe_tie | THRM1_TID); + + /* setup THRM2, threshold, valid bit, interrupt when above threshold */ + mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | maybe_tie); } static void TAUupdate(int cpu) { - unsigned thrm; - -#ifdef DEBUG - printk("TAUupdate "); -#endif + u32 thrm; + u32 bits = THRM1_TIV | THRM1_TIN | THRM1_V; /* if both thresholds are crossed, the step_sizes cancel out * and the window winds up getting expanded twice. */ - if((thrm = mfspr(SPRN_THRM1)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed low threshold */ - if (tau[cpu].low >= step_size){ - tau[cpu].low -= step_size; - tau[cpu].high -= (step_size - window_expand); - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("low threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM1); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM1, 0); + + if (tau[cpu].low >= step_size) { + tau[cpu].low -= step_size; + tau[cpu].high -= (step_size - window_expand); } + tau[cpu].grew = 1; + pr_debug("%s: low threshold crossed\n", __func__); } - if((thrm = mfspr(SPRN_THRM2)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed high threshold */ - if (tau[cpu].high <= 127-step_size){ - tau[cpu].low += (step_size - window_expand); - tau[cpu].high += step_size; - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("high threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM2); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM2, 0); + + if (tau[cpu].high <= 127 - step_size) { + tau[cpu].low += (step_size - window_expand); + tau[cpu].high += step_size; } + tau[cpu].grew = 1; + pr_debug("%s: high threshold crossed\n", __func__); } - -#ifdef DEBUG - printk("grew = %d\n", tau[cpu].grew); -#endif - -#ifndef CONFIG_TAU_INT /* tau_timeout will do this if not using interrupts */ - set_thresholds(cpu); -#endif - } #ifdef CONFIG_TAU_INT @@ -140,17 +116,16 @@ void TAUException(struct pt_regs * regs) static void tau_timeout(void * info) { int cpu; - unsigned long flags; int size; int shrink; - /* disabling interrupts *should* be okay */ - local_irq_save(flags); cpu = smp_processor_id(); -#ifndef CONFIG_TAU_INT - TAUupdate(cpu); -#endif + if (!tau_int_enable) + TAUupdate(cpu); + + /* Stop thermal sensor comparisons and interrupts */ + mtspr(SPRN_THRM3, 0); size = tau[cpu].high - tau[cpu].low; if (size > min_window && ! tau[cpu].grew) { @@ -173,32 +148,26 @@ static void tau_timeout(void * info) set_thresholds(cpu); - /* - * Do the enable every time, since otherwise a bunch of (relatively) - * complex sleep code needs to be added. One mtspr every time - * tau_timeout is called is probably not a big deal. - * - * Enable thermal sensor and set up sample interval timer - * need 20 us to do the compare.. until a nice 'cpu_speed' function - * call is implemented, just assume a 500 mhz clock. It doesn't really - * matter if we take too long for a compare since it's all interrupt - * driven anyway. - * - * use a extra long time.. (60 us @ 500 mhz) + /* Restart thermal sensor comparisons and interrupts. + * The "PowerPC 740 and PowerPC 750 Microprocessor Datasheet" + * recommends that "the maximum value be set in THRM3 under all + * conditions." */ - mtspr(SPRN_THRM3, THRM3_SITV(500*60) | THRM3_E); - - local_irq_restore(flags); + mtspr(SPRN_THRM3, THRM3_SITV(0x1fff) | THRM3_E); } -static void tau_timeout_smp(struct timer_list *unused) -{ +static struct workqueue_struct *tau_workq; - /* schedule ourselves to be run again */ - mod_timer(&tau_timer, jiffies + shrink_timer) ; +static void tau_work_func(struct work_struct *work) +{ + msleep(shrink_timer); on_each_cpu(tau_timeout, NULL, 0); + /* schedule ourselves to be run again */ + queue_work(tau_workq, work); } +DECLARE_WORK(tau_work, tau_work_func); + /* * setup the TAU * @@ -231,21 +200,19 @@ static int __init TAU_init(void) return 1; } + tau_int_enable = IS_ENABLED(CONFIG_TAU_INT) && + !strcmp(cur_cpu_spec->platform, "ppc750"); - /* first, set up the window shrinking timer */ - timer_setup(&tau_timer, tau_timeout_smp, 0); - tau_timer.expires = jiffies + shrink_timer; - add_timer(&tau_timer); + tau_workq = alloc_workqueue("tau", WQ_UNBOUND, 1, 0); + if (!tau_workq) + return -ENOMEM; on_each_cpu(TAU_init_smp, NULL, 0); - printk("Thermal assist unit "); -#ifdef CONFIG_TAU_INT - printk("using interrupts, "); -#else - printk("using timers, "); -#endif - printk("shrink_timer: %d jiffies\n", shrink_timer); + queue_work(tau_workq, &tau_work); + + pr_info("Thermal assist unit using %s, shrink_timer: %d ms\n", + tau_int_enable ? "interrupts" : "workqueue", shrink_timer); tau_initialized = 1; return 0; diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 5e994cda8e40..c254f5f733a8 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -39,7 +39,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \ memcpy_power7.o obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \ - memcpy_64.o memcpy_mcsafe_64.o + memcpy_64.o copy_mc_64.o obj64-$(CONFIG_SMP) += locks.o obj64-$(CONFIG_ALTIVEC) += vmx-helper.o diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/copy_mc_64.S index cb882d9a6d8a..88d46c471493 100644 --- a/arch/powerpc/lib/memcpy_mcsafe_64.S +++ b/arch/powerpc/lib/copy_mc_64.S @@ -50,7 +50,7 @@ err3; stb r0,0(r3) blr -_GLOBAL(memcpy_mcsafe) +_GLOBAL(copy_mc_generic) mr r7,r5 cmpldi r5,16 blt .Lshort_copy @@ -239,4 +239,4 @@ err1; stb r0,0(r3) 15: li r3,0 blr -EXPORT_SYMBOL_GPL(memcpy_mcsafe); +EXPORT_SYMBOL_GPL(copy_mc_generic); diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index b5cc9b23cf02..277a07772e7d 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -644,19 +644,29 @@ static void do_exit_flush_lazy_tlb(void *arg) struct mm_struct *mm = arg; unsigned long pid = mm->context.id; + /* + * A kthread could have done a mmget_not_zero() after the flushing CPU + * checked mm_is_singlethreaded, and be in the process of + * kthread_use_mm when interrupted here. In that case, current->mm will + * be set to mm, because kthread_use_mm() setting ->mm and switching to + * the mm is done with interrupts off. + */ if (current->mm == mm) - return; /* Local CPU */ + goto out_flush; if (current->active_mm == mm) { - /* - * Must be a kernel thread because sender is single-threaded. - */ - BUG_ON(current->mm); + WARN_ON_ONCE(current->mm != NULL); + /* Is a kernel thread and is using mm as the lazy tlb */ mmgrab(&init_mm); - switch_mm(mm, &init_mm, current); current->active_mm = &init_mm; + switch_mm_irqs_off(mm, &init_mm, current); mmdrop(mm); } + + atomic_dec(&mm->context.active_cpus); + cpumask_clear_cpu(smp_processor_id(), mm_cpumask(mm)); + +out_flush: _tlbiel_pid(pid, RIC_FLUSH_ALL); } @@ -671,7 +681,6 @@ static void exit_flush_lazy_tlbs(struct mm_struct *mm) */ smp_call_function_many(mm_cpumask(mm), do_exit_flush_lazy_tlb, (void *)mm, 1); - mm_reset_thread_local(mm); } void radix__flush_tlb_mm(struct mm_struct *mm) diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index 59327cefbc6a..873fcfc7b875 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -362,10 +362,8 @@ static void __init init_drmem_v1_lmbs(const __be32 *prop) if (!drmem_info->lmbs) return; - for_each_drmem_lmb(lmb) { + for_each_drmem_lmb(lmb) read_drconf_v1_cell(lmb, &prop); - lmb_set_nid(lmb); - } } static void __init init_drmem_v2_lmbs(const __be32 *prop) @@ -410,8 +408,6 @@ static void __init init_drmem_v2_lmbs(const __be32 *prop) lmb->aa_index = dr_cell.aa_index; lmb->flags = dr_cell.flags; - - lmb_set_nid(lmb); } } } diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 019b0c0bbbf3..ca91d04d0a7a 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -121,8 +121,7 @@ void __init kasan_mmu_init(void) { int ret; - if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) || - IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) { ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); if (ret) @@ -133,11 +132,11 @@ void __init kasan_mmu_init(void) void __init kasan_init(void) { struct memblock_region *reg; + int ret; for_each_memblock(memory, reg) { phys_addr_t base = reg->base; phys_addr_t top = min(base + reg->size, total_lowmem); - int ret; if (base >= top) continue; @@ -147,6 +146,13 @@ void __init kasan_init(void) panic("kasan: kasan_init_region() failed"); } + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); + + if (ret) + panic("kasan: kasan_init_shadow_page_tables() failed"); + } + kasan_remap_early_shadow_ro(); clear_page(kasan_early_shadow_page); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index c2c11eb8dcfc..0f21bcb16405 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -50,6 +50,7 @@ #include <asm/swiotlb.h> #include <asm/rtas.h> #include <asm/kasan.h> +#include <asm/svm.h> #include <mm/mmu_decl.h> @@ -290,7 +291,10 @@ void __init mem_init(void) * back to to-down. */ memblock_set_bottom_up(true); - swiotlb_init(0); + if (is_secure_guest()) + svm_swiotlb_init(); + else + swiotlb_init(0); #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h index e608f9db12dd..8965b4463d43 100644 --- a/arch/powerpc/perf/hv-gpci-requests.h +++ b/arch/powerpc/perf/hv-gpci-requests.h @@ -95,7 +95,7 @@ REQUEST(__field(0, 8, partition_id) #define REQUEST_NAME system_performance_capabilities #define REQUEST_NUM 0x40 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__field(0, 1, perf_collect_privileged) __field(0x1, 1, capability_mask) @@ -223,7 +223,7 @@ REQUEST(__field(0, 2, partition_id) #define REQUEST_NAME system_hypervisor_times #define REQUEST_NUM 0xF0 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) __count(0x8, 8, time_spent_processing_virtual_processor_timers) @@ -234,7 +234,7 @@ REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) #define REQUEST_NAME system_tlbie_count_and_time #define REQUEST_NUM 0xF4 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, tlbie_instructions_issued) /* diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 4c86da5eb28a..0b5c8f4fbdbf 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -269,6 +269,15 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) mask |= CNST_PMC_MASK(pmc); value |= CNST_PMC_VAL(pmc); + + /* + * PMC5 and PMC6 are used to count cycles and instructions and + * they do not support most of the constraint bits. Add a check + * to exclude PMC5/6 from most of the constraints except for + * EBB/BHRB. + */ + if (pmc >= 5) + goto ebb_bhrb; } if (pmc <= 4) { @@ -335,6 +344,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) } } +ebb_bhrb: if (!pmc && ebb) /* EBB events must specify the PMC */ return -1; diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index fb7515b4fa9c..b439b027a42f 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -223,12 +223,11 @@ config TAU temperature within 2-4 degrees Celsius. This option shows the current on-die temperature in /proc/cpuinfo if the cpu supports it. - Unfortunately, on some chip revisions, this sensor is very inaccurate - and in many cases, does not work at all, so don't assume the cpu - temp is actually what /proc/cpuinfo says it is. + Unfortunately, this sensor is very inaccurate when uncalibrated, so + don't assume the cpu temp is actually what /proc/cpuinfo says it is. config TAU_INT - bool "Interrupt driven TAU driver (DANGEROUS)" + bool "Interrupt driven TAU driver (EXPERIMENTAL)" depends on TAU help The TAU supports an interrupt driven mode which causes an interrupt @@ -236,12 +235,7 @@ config TAU_INT to get notified the temp has exceeded a range. With this option off, a timer is used to re-check the temperature periodically. - However, on some cpus it appears that the TAU interrupt hardware - is buggy and can cause a situation which would lead unexplained hard - lockups. - - Unless you are extending the TAU driver, or enjoy kernel/hardware - debugging, leave this option off. + If in doubt, say N here. config TAU_AVERAGE bool "Average high and low temp" diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 543c816fa99e..0e6693bacb7e 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -318,15 +318,14 @@ static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj, return count; } -static struct dump_obj *create_dump_obj(uint32_t id, size_t size, - uint32_t type) +static void create_dump_obj(uint32_t id, size_t size, uint32_t type) { struct dump_obj *dump; int rc; dump = kzalloc(sizeof(*dump), GFP_KERNEL); if (!dump) - return NULL; + return; dump->kobj.kset = dump_kset; @@ -346,21 +345,39 @@ static struct dump_obj *create_dump_obj(uint32_t id, size_t size, rc = kobject_add(&dump->kobj, NULL, "0x%x-0x%x", type, id); if (rc) { kobject_put(&dump->kobj); - return NULL; + return; } + /* + * As soon as the sysfs file for this dump is created/activated there is + * a chance the opal_errd daemon (or any userspace) might read and + * acknowledge the dump before kobject_uevent() is called. If that + * happens then there is a potential race between + * dump_ack_store->kobject_put() and kobject_uevent() which leads to a + * use-after-free of a kernfs object resulting in a kernel crash. + * + * To avoid that, we need to take a reference on behalf of the bin file, + * so that our reference remains valid while we call kobject_uevent(). + * We then drop our reference before exiting the function, leaving the + * bin file to drop the last reference (if it hasn't already). + */ + + /* Take a reference for the bin file */ + kobject_get(&dump->kobj); rc = sysfs_create_bin_file(&dump->kobj, &dump->dump_attr); - if (rc) { + if (rc == 0) { + kobject_uevent(&dump->kobj, KOBJ_ADD); + + pr_info("%s: New platform dump. ID = 0x%x Size %u\n", + __func__, dump->id, dump->size); + } else { + /* Drop reference count taken for bin file */ kobject_put(&dump->kobj); - return NULL; } - pr_info("%s: New platform dump. ID = 0x%x Size %u\n", - __func__, dump->id, dump->size); - - kobject_uevent(&dump->kobj, KOBJ_ADD); - - return dump; + /* Drop our reference */ + kobject_put(&dump->kobj); + return; } static irqreturn_t process_dump(int irq, void *data) diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 8b748690dac2..9f236149b402 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -356,25 +356,32 @@ static int dlpar_add_lmb(struct drmem_lmb *); static int dlpar_remove_lmb(struct drmem_lmb *lmb) { + struct memory_block *mem_block; unsigned long block_sz; int rc; if (!lmb_is_removable(lmb)) return -EINVAL; + mem_block = lmb_to_memblock(lmb); + if (mem_block == NULL) + return -EINVAL; + rc = dlpar_offline_lmb(lmb); - if (rc) + if (rc) { + put_device(&mem_block->dev); return rc; + } block_sz = pseries_memory_block_size(); - __remove_memory(lmb->nid, lmb->base_addr, block_sz); + __remove_memory(mem_block->nid, lmb->base_addr, block_sz); + put_device(&mem_block->dev); /* Update memory regions for memory remove */ memblock_remove(lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); - lmb_clear_nid(lmb); lmb->flags &= ~DRCONF_MEM_ASSIGNED; return 0; @@ -631,7 +638,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) static int dlpar_add_lmb(struct drmem_lmb *lmb) { unsigned long block_sz; - int rc; + int nid, rc; if (lmb->flags & DRCONF_MEM_ASSIGNED) return -EINVAL; @@ -642,11 +649,13 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) return rc; } - lmb_set_nid(lmb); block_sz = memory_block_size_bytes(); + /* Find the node id for this address. */ + nid = memory_add_physaddr_to_nid(lmb->base_addr); + /* Add the memory */ - rc = __add_memory(lmb->nid, lmb->base_addr, block_sz); + rc = __add_memory(nid, lmb->base_addr, block_sz); if (rc) { invalidate_lmb_associativity_index(lmb); return rc; @@ -654,9 +663,8 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) rc = dlpar_online_lmb(lmb); if (rc) { - __remove_memory(lmb->nid, lmb->base_addr, block_sz); + __remove_memory(nid, lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); - lmb_clear_nid(lmb); } else { lmb->flags |= DRCONF_MEM_ASSIGNED; } diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 9c569078a09f..6c2c66450dac 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -702,6 +702,9 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) p->bus_desc.of_node = p->pdev->dev.of_node; p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL); + /* Set the dimm command family mask to accept PDSMs */ + set_bit(NVDIMM_FAMILY_PAPR, &p->bus_desc.dimm_family_mask); + if (!p->bus_desc.provider_name) return -ENOMEM; diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 13c86a292c6d..b2b245b25edb 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -521,18 +521,55 @@ int pSeries_system_reset_exception(struct pt_regs *regs) return 0; /* need to perform reset */ } +static int mce_handle_err_realmode(int disposition, u8 error_type) +{ +#ifdef CONFIG_PPC_BOOK3S_64 + if (disposition == RTAS_DISP_NOT_RECOVERED) { + switch (error_type) { + case MC_ERROR_TYPE_SLB: + case MC_ERROR_TYPE_ERAT: + /* + * Store the old slb content in paca before flushing. + * Print this when we go to virtual mode. + * There are chances that we may hit MCE again if there + * is a parity error on the SLB entry we trying to read + * for saving. Hence limit the slb saving to single + * level of recursion. + */ + if (local_paca->in_mce == 1) + slb_save_contents(local_paca->mce_faulty_slbs); + flush_and_reload_slb(); + disposition = RTAS_DISP_FULLY_RECOVERED; + break; + default: + break; + } + } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) { + /* Platform corrected itself but could be degraded */ + pr_err("MCE: limited recovery, system may be degraded\n"); + disposition = RTAS_DISP_FULLY_RECOVERED; + } +#endif + return disposition; +} -static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) +static int mce_handle_err_virtmode(struct pt_regs *regs, + struct rtas_error_log *errp, + struct pseries_mc_errorlog *mce_log, + int disposition) { struct mce_error_info mce_err = { 0 }; - unsigned long eaddr = 0, paddr = 0; - struct pseries_errorlog *pseries_log; - struct pseries_mc_errorlog *mce_log; - int disposition = rtas_error_disposition(errp); int initiator = rtas_error_initiator(errp); int severity = rtas_error_severity(errp); + unsigned long eaddr = 0, paddr = 0; u8 error_type, err_sub_type; + if (!mce_log) + goto out; + + error_type = mce_log->error_type; + err_sub_type = rtas_mc_error_sub_type(mce_log); + if (initiator == RTAS_INITIATOR_UNKNOWN) mce_err.initiator = MCE_INITIATOR_UNKNOWN; else if (initiator == RTAS_INITIATOR_CPU) @@ -571,18 +608,7 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN; mce_err.error_class = MCE_ECLASS_UNKNOWN; - if (!rtas_error_extended(errp)) - goto out; - - pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); - if (pseries_log == NULL) - goto out; - - mce_log = (struct pseries_mc_errorlog *)pseries_log->data; - error_type = mce_log->error_type; - err_sub_type = rtas_mc_error_sub_type(mce_log); - - switch (mce_log->error_type) { + switch (error_type) { case MC_ERROR_TYPE_UE: mce_err.error_type = MCE_ERROR_TYPE_UE; mce_common_process_ue(regs, &mce_err); @@ -682,37 +708,31 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN; break; } +out: + save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED, + &mce_err, regs->nip, eaddr, paddr); + return disposition; +} -#ifdef CONFIG_PPC_BOOK3S_64 - if (disposition == RTAS_DISP_NOT_RECOVERED) { - switch (error_type) { - case MC_ERROR_TYPE_SLB: - case MC_ERROR_TYPE_ERAT: - /* - * Store the old slb content in paca before flushing. - * Print this when we go to virtual mode. - * There are chances that we may hit MCE again if there - * is a parity error on the SLB entry we trying to read - * for saving. Hence limit the slb saving to single - * level of recursion. - */ - if (local_paca->in_mce == 1) - slb_save_contents(local_paca->mce_faulty_slbs); - flush_and_reload_slb(); - disposition = RTAS_DISP_FULLY_RECOVERED; - break; - default: - break; - } - } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) { - /* Platform corrected itself but could be degraded */ - printk(KERN_ERR "MCE: limited recovery, system may " - "be degraded\n"); - disposition = RTAS_DISP_FULLY_RECOVERED; - } -#endif +static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) +{ + struct pseries_errorlog *pseries_log; + struct pseries_mc_errorlog *mce_log = NULL; + int disposition = rtas_error_disposition(errp); + u8 error_type; + + if (!rtas_error_extended(errp)) + goto out; + + pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); + if (!pseries_log) + goto out; + + mce_log = (struct pseries_mc_errorlog *)pseries_log->data; + error_type = mce_log->error_type; + + disposition = mce_handle_err_realmode(disposition, error_type); -out: /* * Enable translation as we will be accessing per-cpu variables * in save_mce_event() which may fall outside RMO region, also @@ -723,10 +743,10 @@ out: * Note: All the realmode handling like flushing SLB entries for * SLB multihit is done by now. */ +out: mtmsr(mfmsr() | MSR_IR | MSR_DR); - save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED, - &mce_err, regs->nip, eaddr, paddr); - + disposition = mce_handle_err_virtmode(regs, errp, mce_log, + disposition); return disposition; } diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c index bbb97169bf63..6268545947b8 100644 --- a/arch/powerpc/platforms/pseries/rng.c +++ b/arch/powerpc/platforms/pseries/rng.c @@ -36,6 +36,7 @@ static __init int rng_init(void) ppc_md.get_random_seed = pseries_get_random_long; + of_node_put(dn); return 0; } machine_subsys_initcall(pseries, rng_init); diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index 40c0637203d5..81085eb8f225 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -7,6 +7,7 @@ */ #include <linux/mm.h> +#include <linux/memblock.h> #include <asm/machdep.h> #include <asm/svm.h> #include <asm/swiotlb.h> @@ -34,6 +35,31 @@ static int __init init_svm(void) } machine_early_initcall(pseries, init_svm); +/* + * Initialize SWIOTLB. Essentially the same as swiotlb_init(), except that it + * can allocate the buffer anywhere in memory. Since the hypervisor doesn't have + * any addressing limitation, we don't need to allocate it in low addresses. + */ +void __init svm_swiotlb_init(void) +{ + unsigned char *vstart; + unsigned long bytes, io_tlb_nslabs; + + io_tlb_nslabs = (swiotlb_size_or_default() >> IO_TLB_SHIFT); + io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + + bytes = io_tlb_nslabs << IO_TLB_SHIFT; + + vstart = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE); + if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, false)) + return; + + if (io_tlb_start) + memblock_free_early(io_tlb_start, + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + panic("SVM: Cannot allocate SWIOTLB buffer"); +} + int set_memory_encrypted(unsigned long addr, int numpages) { if (!PAGE_ALIGNED(addr)) diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index ad8117148ea3..21b9d1bf39ff 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -174,6 +174,7 @@ int icp_hv_init(void) icp_ops = &icp_hv_ops; + of_node_put(np); return 0; } diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 7efe4bc3ccf6..ac5862cee142 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -962,6 +962,7 @@ static void insert_cpu_bpts(void) brk.address = dabr[i].address; brk.type = (dabr[i].enabled & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL; brk.len = 8; + brk.hw_len = 8; __set_breakpoint(i, &brk); } } diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 5967f3014156..c93486a9989b 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -197,9 +197,10 @@ void pcibios_bus_add_device(struct pci_dev *pdev) * With pdev->no_vf_scan the common PCI probing code does not * perform PF/VF linking. */ - if (zdev->vfn) + if (zdev->vfn) { zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn); - + pdev->no_command_memory = 1; + } } static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 8735c468230a..555203e3e7b4 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1403,7 +1403,7 @@ static int vector_net_load_bpf_flash(struct net_device *dev, kfree(vp->bpf->filter); vp->bpf->filter = NULL; } else { - vp->bpf = kmalloc(sizeof(struct sock_fprog), GFP_KERNEL); + vp->bpf = kmalloc(sizeof(struct sock_fprog), GFP_ATOMIC); if (vp->bpf == NULL) { netdev_err(dev, "failed to allocate memory for firmware\n"); goto flash_fail; @@ -1415,7 +1415,7 @@ static int vector_net_load_bpf_flash(struct net_device *dev, if (request_firmware(&fw, efl->data, &vdevice->pdev.dev)) goto flash_fail; - vp->bpf->filter = kmemdup(fw->data, fw->size, GFP_KERNEL); + vp->bpf->filter = kmemdup(fw->data, fw->size, GFP_ATOMIC); if (!vp->bpf->filter) goto free_buffer; diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 25eaa6a0c658..c07436e89e59 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -70,13 +70,17 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg, * read of the message and write of the ACK. */ if (mode != TTMH_READ) { + bool disabled = irqs_disabled(); + + BUG_ON(mode == TTMH_IDLE && !disabled); + + if (disabled) + local_irq_enable(); while (os_poll(1, &time_travel_ext_fd) != 0) { - if (mode == TTMH_IDLE) { - BUG_ON(!irqs_disabled()); - local_irq_enable(); - local_irq_disable(); - } + /* nothing */ } + if (disabled) + local_irq_disable(); } ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg)); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 883da0abf779..1f4104f8852b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -75,7 +75,7 @@ config X86 select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 - select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE + select ARCH_HAS_COPY_MC if X86_64 select ARCH_HAS_SET_MEMORY select ARCH_HAS_SET_DIRECT_MAP select ARCH_HAS_STRICT_KERNEL_RWX diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 0dd319e6e5b4..ec98b400e38f 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -59,7 +59,7 @@ config EARLY_PRINTK_USB_XDBC You should normally say N here, unless you want to debug early crashes or need a very simple printk logging facility. -config MCSAFE_TEST +config COPY_MC_TEST def_bool n config EFI_PGT_DUMP diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 26c36357c4c9..a023cbe21230 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -89,6 +89,7 @@ struct perf_ibs { u64 max_period; unsigned long offset_mask[1]; int offset_max; + unsigned int fetch_count_reset_broken : 1; struct cpu_perf_ibs __percpu *pcpu; struct attribute **format_attrs; @@ -363,7 +364,12 @@ perf_ibs_event_update(struct perf_ibs *perf_ibs, struct perf_event *event, static inline void perf_ibs_enable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { - wrmsrl(hwc->config_base, hwc->config | config | perf_ibs->enable_mask); + u64 tmp = hwc->config | config; + + if (perf_ibs->fetch_count_reset_broken) + wrmsrl(hwc->config_base, tmp & ~perf_ibs->enable_mask); + + wrmsrl(hwc->config_base, tmp | perf_ibs->enable_mask); } /* @@ -733,6 +739,13 @@ static __init void perf_event_ibs_init(void) { struct attribute **attr = ibs_op_format_attrs; + /* + * Some chips fail to reset the fetch count when it is written; instead + * they need a 0-1 transition of IbsFetchEn. + */ + if (boot_cpu_data.x86 >= 0x16 && boot_cpu_data.x86 <= 0x18) + perf_ibs_fetch.fetch_count_reset_broken = 1; + perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch"); if (ibs_caps & IBS_CAPS_OPCNT) { diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c index fb616203ce42..be50ef8572cc 100644 --- a/arch/x86/events/amd/iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -379,7 +379,7 @@ static __init int _init_events_attrs(void) while (amd_iommu_v2_event_descs[i].attr.attr.name) i++; - attrs = kcalloc(i + 1, sizeof(struct attribute **), GFP_KERNEL); + attrs = kcalloc(i + 1, sizeof(*attrs), GFP_KERNEL); if (!attrs) return -ENOMEM; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 4103665c6e03..29640b4079af 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1087,8 +1087,10 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, cpuc->event_list[n] = event; n++; - if (is_counter_pair(&event->hw)) + if (is_counter_pair(&event->hw)) { cpuc->n_pair++; + cpuc->n_txn_pair++; + } } return n; } @@ -1953,6 +1955,7 @@ static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) perf_pmu_disable(pmu); __this_cpu_write(cpu_hw_events.n_txn, 0); + __this_cpu_write(cpu_hw_events.n_txn_pair, 0); } /* @@ -1978,6 +1981,7 @@ static void x86_pmu_cancel_txn(struct pmu *pmu) */ __this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn)); __this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn)); + __this_cpu_sub(cpu_hw_events.n_pair, __this_cpu_read(cpu_hw_events.n_txn_pair)); perf_pmu_enable(pmu); } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index dc43cc124e09..221d1766d6e6 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -670,9 +670,7 @@ unlock: static inline void intel_pmu_drain_pebs_buffer(void) { - struct pt_regs regs; - - x86_pmu.drain_pebs(®s); + x86_pmu.drain_pebs(NULL); } /* @@ -1737,6 +1735,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, struct x86_perf_regs perf_regs; struct pt_regs *regs = &perf_regs.regs; void *at = get_next_pebs_record_by_bit(base, top, bit); + struct pt_regs dummy_iregs; if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { /* @@ -1749,6 +1748,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event, } else if (!intel_pmu_save_and_restart(event)) return; + if (!iregs) + iregs = &dummy_iregs; + while (count > 1) { setup_sample(event, iregs, at, &data, regs); perf_event_output(event, &data, regs); @@ -1758,16 +1760,22 @@ static void __intel_pmu_pebs_event(struct perf_event *event, } setup_sample(event, iregs, at, &data, regs); - - /* - * All but the last records are processed. - * The last one is left to be able to call the overflow handler. - */ - if (perf_event_overflow(event, &data, regs)) { - x86_pmu_stop(event, 0); - return; + if (iregs == &dummy_iregs) { + /* + * The PEBS records may be drained in the non-overflow context, + * e.g., large PEBS + context switch. Perf should treat the + * last record the same as other PEBS records, and doesn't + * invoke the generic overflow handler. + */ + perf_event_output(event, &data, regs); + } else { + /* + * All but the last records are processed. + * The last one is left to be able to call the overflow handler. + */ + if (perf_event_overflow(event, &data, regs)) + x86_pmu_stop(event, 0); } - } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 1038e9f1e354..3b70c2ff177c 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -115,6 +115,10 @@ #define ICL_UNC_CBO_0_PER_CTR0 0x702 #define ICL_UNC_CBO_MSR_OFFSET 0x8 +/* ICL ARB register */ +#define ICL_UNC_ARB_PER_CTR 0x3b1 +#define ICL_UNC_ARB_PERFEVTSEL 0x3b3 + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); @@ -302,15 +306,21 @@ void skl_uncore_cpu_init(void) snb_uncore_arb.ops = &skl_uncore_msr_ops; } +static struct intel_uncore_ops icl_uncore_msr_ops = { + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + static struct intel_uncore_type icl_uncore_cbox = { .name = "cbox", - .num_counters = 4, + .num_counters = 2, .perf_ctr_bits = 44, .perf_ctr = ICL_UNC_CBO_0_PER_CTR0, .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, .event_mask = SNB_UNC_RAW_EVENT_MASK, .msr_offset = ICL_UNC_CBO_MSR_OFFSET, - .ops = &skl_uncore_msr_ops, + .ops = &icl_uncore_msr_ops, .format_group = &snb_uncore_format_group, }; @@ -339,13 +349,25 @@ static struct intel_uncore_type icl_uncore_clockbox = { .single_fixed = 1, .event_mask = SNB_UNC_CTL_EV_SEL_MASK, .format_group = &icl_uncore_clock_format_group, - .ops = &skl_uncore_msr_ops, + .ops = &icl_uncore_msr_ops, .event_descs = icl_uncore_events, }; +static struct intel_uncore_type icl_uncore_arb = { + .name = "arb", + .num_counters = 1, + .num_boxes = 1, + .perf_ctr_bits = 44, + .perf_ctr = ICL_UNC_ARB_PER_CTR, + .event_ctl = ICL_UNC_ARB_PERFEVTSEL, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .ops = &icl_uncore_msr_ops, + .format_group = &snb_uncore_format_group, +}; + static struct intel_uncore_type *icl_msr_uncores[] = { &icl_uncore_cbox, - &snb_uncore_arb, + &icl_uncore_arb, &icl_uncore_clockbox, NULL, }; @@ -363,7 +385,6 @@ void icl_uncore_cpu_init(void) { uncore_msr_uncores = icl_msr_uncores; icl_uncore_cbox.num_boxes = icl_get_cbox_num(); - snb_uncore_arb.ops = &skl_uncore_msr_ops; } enum { diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 07652fa20ebb..6a03fe8054a8 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -4550,10 +4550,10 @@ static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = { INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"), INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(read.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(write.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"), { /* end: all zeroes */ }, }; @@ -5009,17 +5009,17 @@ static struct uncore_event_desc icx_uncore_imc_freerunning_events[] = { INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"), INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(read.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(write.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(ddrt_read, "event=0xff,umask=0x30"), - INTEL_UNCORE_EVENT_DESC(ddrt_read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(ddrt_read.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(ddrt_read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(ddrt_write, "event=0xff,umask=0x31"), - INTEL_UNCORE_EVENT_DESC(ddrt_write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(ddrt_write.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(ddrt_write.unit, "MiB"), { /* end: all zeroes */ }, }; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index e17a3d8a47ed..d4d482d16fe1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -198,6 +198,7 @@ struct cpu_hw_events { they've never been enabled yet */ int n_txn; /* the # last events in the below arrays; added in the current transaction */ + int n_txn_pair; int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ u64 tags[X86_PMC_IDX_MAX]; diff --git a/arch/x86/include/asm/copy_mc_test.h b/arch/x86/include/asm/copy_mc_test.h new file mode 100644 index 000000000000..e4991ba96726 --- /dev/null +++ b/arch/x86/include/asm/copy_mc_test.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _COPY_MC_TEST_H_ +#define _COPY_MC_TEST_H_ + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_COPY_MC_TEST +extern unsigned long copy_mc_test_src; +extern unsigned long copy_mc_test_dst; + +static inline void copy_mc_inject_src(void *addr) +{ + if (addr) + copy_mc_test_src = (unsigned long) addr; + else + copy_mc_test_src = ~0UL; +} + +static inline void copy_mc_inject_dst(void *addr) +{ + if (addr) + copy_mc_test_dst = (unsigned long) addr; + else + copy_mc_test_dst = ~0UL; +} +#else /* CONFIG_COPY_MC_TEST */ +static inline void copy_mc_inject_src(void *addr) +{ +} + +static inline void copy_mc_inject_dst(void *addr) +{ +} +#endif /* CONFIG_COPY_MC_TEST */ + +#else /* __ASSEMBLY__ */ +#include <asm/export.h> + +#ifdef CONFIG_COPY_MC_TEST +.macro COPY_MC_TEST_CTL + .pushsection .data + .align 8 + .globl copy_mc_test_src + copy_mc_test_src: + .quad 0 + EXPORT_SYMBOL_GPL(copy_mc_test_src) + .globl copy_mc_test_dst + copy_mc_test_dst: + .quad 0 + EXPORT_SYMBOL_GPL(copy_mc_test_dst) + .popsection +.endm + +.macro COPY_MC_TEST_SRC reg count target + leaq \count(\reg), %r9 + cmp copy_mc_test_src, %r9 + ja \target +.endm + +.macro COPY_MC_TEST_DST reg count target + leaq \count(\reg), %r9 + cmp copy_mc_test_dst, %r9 + ja \target +.endm +#else +.macro COPY_MC_TEST_CTL +.endm + +.macro COPY_MC_TEST_SRC reg count target +.endm + +.macro COPY_MC_TEST_DST reg count target +.endm +#endif /* CONFIG_COPY_MC_TEST */ +#endif /* __ASSEMBLY__ */ +#endif /* _COPY_MC_TEST_H_ */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index cf503824529c..9b9112e4379a 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -174,6 +174,15 @@ extern void mce_unregister_decode_chain(struct notifier_block *nb); extern int mce_p5_enabled; +#ifdef CONFIG_ARCH_HAS_COPY_MC +extern void enable_copy_mc_fragile(void); +unsigned long __must_check copy_mc_fragile(void *dst, const void *src, unsigned cnt); +#else +static inline void enable_copy_mc_fragile(void) +{ +} +#endif + #ifdef CONFIG_X86_MCE int mcheck_init(void); void mcheck_cpu_init(struct cpuinfo_x86 *c); diff --git a/arch/x86/include/asm/mcsafe_test.h b/arch/x86/include/asm/mcsafe_test.h deleted file mode 100644 index eb59804b6201..000000000000 --- a/arch/x86/include/asm/mcsafe_test.h +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _MCSAFE_TEST_H_ -#define _MCSAFE_TEST_H_ - -#ifndef __ASSEMBLY__ -#ifdef CONFIG_MCSAFE_TEST -extern unsigned long mcsafe_test_src; -extern unsigned long mcsafe_test_dst; - -static inline void mcsafe_inject_src(void *addr) -{ - if (addr) - mcsafe_test_src = (unsigned long) addr; - else - mcsafe_test_src = ~0UL; -} - -static inline void mcsafe_inject_dst(void *addr) -{ - if (addr) - mcsafe_test_dst = (unsigned long) addr; - else - mcsafe_test_dst = ~0UL; -} -#else /* CONFIG_MCSAFE_TEST */ -static inline void mcsafe_inject_src(void *addr) -{ -} - -static inline void mcsafe_inject_dst(void *addr) -{ -} -#endif /* CONFIG_MCSAFE_TEST */ - -#else /* __ASSEMBLY__ */ -#include <asm/export.h> - -#ifdef CONFIG_MCSAFE_TEST -.macro MCSAFE_TEST_CTL - .pushsection .data - .align 8 - .globl mcsafe_test_src - mcsafe_test_src: - .quad 0 - EXPORT_SYMBOL_GPL(mcsafe_test_src) - .globl mcsafe_test_dst - mcsafe_test_dst: - .quad 0 - EXPORT_SYMBOL_GPL(mcsafe_test_dst) - .popsection -.endm - -.macro MCSAFE_TEST_SRC reg count target - leaq \count(\reg), %r9 - cmp mcsafe_test_src, %r9 - ja \target -.endm - -.macro MCSAFE_TEST_DST reg count target - leaq \count(\reg), %r9 - cmp mcsafe_test_dst, %r9 - ja \target -.endm -#else -.macro MCSAFE_TEST_CTL -.endm - -.macro MCSAFE_TEST_SRC reg count target -.endm - -.macro MCSAFE_TEST_DST reg count target -.endm -#endif /* CONFIG_MCSAFE_TEST */ -#endif /* __ASSEMBLY__ */ -#endif /* _MCSAFE_TEST_H_ */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index eb8e781c4353..b8f7c9659ef6 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -11,45 +11,47 @@ #include <linux/jump_label.h> /* - * Volatile isn't enough to prevent the compiler from reordering the - * read/write functions for the control registers and messing everything up. - * A memory clobber would solve the problem, but would prevent reordering of - * all loads stores around it, which can hurt performance. Solution is to - * use a variable and mimic reads and writes to it to enforce serialization + * The compiler should not reorder volatile asm statements with respect to each + * other: they should execute in program order. However GCC 4.9.x and 5.x have + * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder + * volatile asm. The write functions are not affected since they have memory + * clobbers preventing reordering. To prevent reads from being reordered with + * respect to writes, use a dummy memory operand. */ -extern unsigned long __force_order; + +#define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL) void native_write_cr0(unsigned long val); static inline unsigned long native_read_cr0(void) { unsigned long val; - asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order)); + asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline unsigned long native_read_cr2(void) { unsigned long val; - asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order)); + asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline void native_write_cr2(unsigned long val) { - asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); + asm volatile("mov %0,%%cr2": : "r" (val) : "memory"); } static inline unsigned long __native_read_cr3(void) { unsigned long val; - asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); + asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static inline void native_write_cr3(unsigned long val) { - asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order)); + asm volatile("mov %0,%%cr3": : "r" (val) : "memory"); } static inline unsigned long native_read_cr4(void) @@ -64,10 +66,10 @@ static inline unsigned long native_read_cr4(void) asm volatile("1: mov %%cr4, %0\n" "2:\n" _ASM_EXTABLE(1b, 2b) - : "=r" (val), "=m" (__force_order) : "0" (0)); + : "=r" (val) : "0" (0), __FORCE_ORDER); #else /* CR4 always exists on x86_64. */ - asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); + asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER); #endif return val; } diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 75314c3dbe47..6e450827f677 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -82,38 +82,6 @@ int strcmp(const char *cs, const char *ct); #endif -#define __HAVE_ARCH_MEMCPY_MCSAFE 1 -__must_check unsigned long __memcpy_mcsafe(void *dst, const void *src, - size_t cnt); -DECLARE_STATIC_KEY_FALSE(mcsafe_key); - -/** - * memcpy_mcsafe - copy memory with indication if a machine check happened - * - * @dst: destination address - * @src: source address - * @cnt: number of bytes to copy - * - * Low level memory copy function that catches machine checks - * We only call into the "safe" function on systems that can - * actually do machine check recovery. Everyone else can just - * use memcpy(). - * - * Return 0 for success, or number of bytes not copied if there was an - * exception. - */ -static __always_inline __must_check unsigned long -memcpy_mcsafe(void *dst, const void *src, size_t cnt) -{ -#ifdef CONFIG_X86_MCE - if (static_branch_unlikely(&mcsafe_key)) - return __memcpy_mcsafe(dst, src, cnt); - else -#endif - memcpy(dst, src, cnt); - return 0; -} - #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE #define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1 void __memcpy_flushcache(void *dst, const void *src, size_t cnt); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 2f3e8f2a958f..9bfca52b4641 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -455,6 +455,15 @@ extern __must_check long strnlen_user(const char __user *str, long n); unsigned long __must_check clear_user(void __user *mem, unsigned long len); unsigned long __must_check __clear_user(void __user *mem, unsigned long len); +#ifdef CONFIG_ARCH_HAS_COPY_MC +unsigned long __must_check +copy_mc_to_kernel(void *to, const void *from, unsigned len); +#define copy_mc_to_kernel copy_mc_to_kernel + +unsigned long __must_check +copy_mc_to_user(void *to, const void *from, unsigned len); +#endif + /* * movsl can be slow when source and dest are not both 8-byte aligned */ diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index bc10e3dc64fe..e7265a552f4f 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -47,22 +47,6 @@ copy_user_generic(void *to, const void *from, unsigned len) } static __always_inline __must_check unsigned long -copy_to_user_mcsafe(void *to, const void *from, unsigned len) -{ - unsigned long ret; - - __uaccess_begin(); - /* - * Note, __memcpy_mcsafe() is explicitly used since it can - * handle exceptions / faults. memcpy_mcsafe() may fall back to - * memcpy() which lacks this handling. - */ - ret = __memcpy_mcsafe(to, from, len); - __uaccess_end(); - return ret; -} - -static __always_inline __must_check unsigned long raw_copy_from_user(void *dst, const void __user *src, unsigned long size) { return copy_user_generic(dst, (__force void *)src, size); @@ -102,8 +86,4 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) kasan_check_write(dst, size); return __copy_user_flushcache(dst, src, size); } - -unsigned long -mcsafe_handle_tail(char *to, char *from, unsigned len); - #endif /* _ASM_X86_UACCESS_64_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 95c090a45b4b..d8ef789e00c1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -358,7 +358,7 @@ void native_write_cr0(unsigned long val) unsigned long bits_missing = 0; set_register: - asm volatile("mov %0,%%cr0": "+r" (val), "+m" (__force_order)); + asm volatile("mov %0,%%cr0": "+r" (val) : : "memory"); if (static_branch_likely(&cr_pinning)) { if (unlikely((val & X86_CR0_WP) != X86_CR0_WP)) { @@ -377,7 +377,7 @@ void native_write_cr4(unsigned long val) unsigned long bits_changed = 0; set_register: - asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits)); + asm volatile("mov %0,%%cr4": "+r" (val) : : "memory"); if (static_branch_likely(&cr_pinning)) { if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) { diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 14e4b4d17ee5..69b2bb305a5a 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -40,7 +40,6 @@ #include <linux/debugfs.h> #include <linux/irq_work.h> #include <linux/export.h> -#include <linux/jump_label.h> #include <linux/set_memory.h> #include <linux/task_work.h> #include <linux/hardirq.h> @@ -370,42 +369,105 @@ static int msr_to_offset(u32 msr) return -1; } +__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr, + unsigned long error_code, + unsigned long fault_addr) +{ + pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", + (unsigned int)regs->cx, regs->ip, (void *)regs->ip); + + show_stack_regs(regs); + + panic("MCA architectural violation!\n"); + + while (true) + cpu_relax(); + + return true; +} + /* MSR access wrappers used for error injection */ -static u64 mce_rdmsrl(u32 msr) +static noinstr u64 mce_rdmsrl(u32 msr) { - u64 v; + DECLARE_ARGS(val, low, high); if (__this_cpu_read(injectm.finished)) { - int offset = msr_to_offset(msr); + int offset; + u64 ret; + + instrumentation_begin(); + offset = msr_to_offset(msr); if (offset < 0) - return 0; - return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset); - } + ret = 0; + else + ret = *(u64 *)((char *)this_cpu_ptr(&injectm) + offset); - if (rdmsrl_safe(msr, &v)) { - WARN_ONCE(1, "mce: Unable to read MSR 0x%x!\n", msr); - /* - * Return zero in case the access faulted. This should - * not happen normally but can happen if the CPU does - * something weird, or if the code is buggy. - */ - v = 0; + instrumentation_end(); + + return ret; } - return v; + /* + * RDMSR on MCA MSRs should not fault. If they do, this is very much an + * architectural violation and needs to be reported to hw vendor. Panic + * the box to not allow any further progress. + */ + asm volatile("1: rdmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_fault) + : EAX_EDX_RET(val, low, high) : "c" (msr)); + + + return EAX_EDX_VAL(val, low, high); +} + +__visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr, + unsigned long error_code, + unsigned long fault_addr) +{ + pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", + (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax, + regs->ip, (void *)regs->ip); + + show_stack_regs(regs); + + panic("MCA architectural violation!\n"); + + while (true) + cpu_relax(); + + return true; } -static void mce_wrmsrl(u32 msr, u64 v) +static noinstr void mce_wrmsrl(u32 msr, u64 v) { + u32 low, high; + if (__this_cpu_read(injectm.finished)) { - int offset = msr_to_offset(msr); + int offset; + instrumentation_begin(); + + offset = msr_to_offset(msr); if (offset >= 0) *(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v; + + instrumentation_end(); + return; } - wrmsrl(msr, v); + + low = (u32)v; + high = (u32)(v >> 32); + + /* See comment in mce_rdmsrl() */ + asm volatile("1: wrmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_fault) + : : "c" (msr), "a"(low), "d" (high) : "memory"); } /* @@ -2059,7 +2121,7 @@ void mce_disable_bank(int bank) and older. * mce=nobootlog Don't log MCEs from before booting. * mce=bios_cmci_threshold Don't program the CMCI threshold - * mce=recovery force enable memcpy_mcsafe() + * mce=recovery force enable copy_mc_fragile() */ static int __init mcheck_enable(char *str) { @@ -2667,13 +2729,10 @@ static void __init mcheck_debugfs_init(void) static void __init mcheck_debugfs_init(void) { } #endif -DEFINE_STATIC_KEY_FALSE(mcsafe_key); -EXPORT_SYMBOL_GPL(mcsafe_key); - static int __init mcheck_late_init(void) { if (mca_cfg.recovery) - static_branch_inc(&mcsafe_key); + enable_copy_mc_fragile(); mcheck_debugfs_init(); diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 6473070b5da4..b122610e9046 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -185,4 +185,14 @@ extern bool amd_filter_mce(struct mce *m); static inline bool amd_filter_mce(struct mce *m) { return false; }; #endif +__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr, + unsigned long error_code, + unsigned long fault_addr); + +__visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr, + unsigned long error_code, + unsigned long fault_addr); + #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index e1da619add19..567ce09a0286 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -9,9 +9,11 @@ #include <linux/seq_file.h> #include <linux/init.h> #include <linux/debugfs.h> -#include <asm/mce.h> #include <linux/uaccess.h> +#include <asm/mce.h> +#include <asm/intel-family.h> + #include "internal.h" /* @@ -40,9 +42,14 @@ static struct severity { unsigned char context; unsigned char excp; unsigned char covered; + unsigned char cpu_model; + unsigned char cpu_minstepping; + unsigned char bank_lo, bank_hi; char *msg; } severities[] = { #define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c } +#define BANK_RANGE(l, h) .bank_lo = l, .bank_hi = h +#define MODEL_STEPPING(m, s) .cpu_model = m, .cpu_minstepping = s #define KERNEL .context = IN_KERNEL #define USER .context = IN_USER #define KERNEL_RECOV .context = IN_KERNEL_RECOV @@ -97,7 +104,6 @@ static struct severity { KEEP, "Corrected error", NOSER, BITCLR(MCI_STATUS_UC) ), - /* * known AO MCACODs reported via MCE or CMC: * @@ -113,6 +119,18 @@ static struct severity { AO, "Action optional: last level cache writeback error", SER, MASK(MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB) ), + /* + * Quirk for Skylake/Cascade Lake. Patrol scrubber may be configured + * to report uncorrected errors using CMCI with a special signature. + * UC=0, MSCOD=0x0010, MCACOD=binary(000X 0000 1100 XXXX) reported + * in one of the memory controller banks. + * Set severity to "AO" for same action as normal patrol scrub error. + */ + MCESEV( + AO, "Uncorrected Patrol Scrub Error", + SER, MASK(MCI_STATUS_UC|MCI_ADDR|0xffffeff0, MCI_ADDR|0x001000c0), + MODEL_STEPPING(INTEL_FAM6_SKYLAKE_X, 4), BANK_RANGE(13, 18) + ), /* ignore OVER for UCNA */ MCESEV( @@ -324,6 +342,12 @@ static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_e continue; if (s->excp && excp != s->excp) continue; + if (s->cpu_model && boot_cpu_data.x86_model != s->cpu_model) + continue; + if (s->cpu_minstepping && boot_cpu_data.x86_stepping < s->cpu_minstepping) + continue; + if (s->bank_lo && (m->bank < s->bank_lo || m->bank > s->bank_hi)) + continue; if (msg) *msg = s->msg; s->covered = 1; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 7401cc12c3cc..42679610c9be 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -115,7 +115,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) unsigned long prologue = regs->ip - PROLOGUE_SIZE; if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { - printk("%sCode: Bad RIP value.\n", loglvl); + printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", + loglvl, prologue); } else { printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 61ddc3a5e5c2..f8ff895aaf7e 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -243,9 +243,9 @@ static void __init fpu__init_system_ctx_switch(void) */ static void __init fpu__init_parse_early_param(void) { - char arg[32]; + char arg[128]; char *argptr = arg; - int bit; + int arglen, res, bit; #ifdef CONFIG_X86_32 if (cmdline_find_option_bool(boot_command_line, "no387")) @@ -268,12 +268,26 @@ static void __init fpu__init_parse_early_param(void) if (cmdline_find_option_bool(boot_command_line, "noxsaves")) setup_clear_cpu_cap(X86_FEATURE_XSAVES); - if (cmdline_find_option(boot_command_line, "clearcpuid", arg, - sizeof(arg)) && - get_option(&argptr, &bit) && - bit >= 0 && - bit < NCAPINTS * 32) - setup_clear_cpu_cap(bit); + arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg)); + if (arglen <= 0) + return; + + pr_info("Clearing CPUID bits:"); + do { + res = get_option(&argptr, &bit); + if (res == 0 || res == 3) + break; + + /* If the argument was too long, the last bit may be cut off */ + if (res == 1 && arglen >= sizeof(arg)) + break; + + if (bit >= 0 && bit < NCAPINTS * 32) { + pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); + setup_clear_cpu_cap(bit); + } + } while (res == 2); + pr_cont("\n"); } /* diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index d7c5e44b26f7..091752c3a19e 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -102,7 +102,6 @@ fs_initcall(nmi_warning_debugfs); static void nmi_check_duration(struct nmiaction *action, u64 duration) { - u64 whole_msecs = READ_ONCE(action->max_duration); int remainder_ns, decimal_msecs; if (duration < nmi_longest_ns || duration < action->max_duration) @@ -110,12 +109,12 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration) action->max_duration = duration; - remainder_ns = do_div(whole_msecs, (1000 * 1000)); + remainder_ns = do_div(duration, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; printk_ratelimited(KERN_INFO "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", - action->handler, whole_msecs, decimal_msecs); + action->handler, duration, decimal_msecs); } static int nmi_handle(unsigned int type, struct pt_regs *regs) diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 896d74cb5081..e0296983a238 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -8,6 +8,7 @@ #include <asm/hpet.h> #include <asm/setup.h> +#include <asm/mce.h> #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI) @@ -624,10 +625,6 @@ static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3, amd_disable_seq_and_redirect_scrub); -#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE) -#include <linux/jump_label.h> -#include <asm/string_64.h> - /* Ivy Bridge, Haswell, Broadwell */ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev) { @@ -636,7 +633,7 @@ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev) pci_read_config_dword(pdev, 0x84, &capid0); if (capid0 & 0x10) - static_branch_inc(&mcsafe_key); + enable_copy_mc_fragile(); } /* Skylake */ @@ -653,7 +650,7 @@ static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev) * enabled, so memory machine check recovery is also enabled. */ if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0)) - static_branch_inc(&mcsafe_key); + enable_copy_mc_fragile(); } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap); @@ -661,7 +658,6 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap); #endif -#endif bool x86_apple_machine; EXPORT_SYMBOL(x86_apple_machine); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 69cc82310974..d43df8de75a6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -196,7 +196,7 @@ static __always_inline void __user *error_get_trap_addr(struct pt_regs *regs) DEFINE_IDTENTRY(exc_divide_error) { - do_error_trap(regs, 0, "divide_error", X86_TRAP_DE, SIGFPE, + do_error_trap(regs, 0, "divide error", X86_TRAP_DE, SIGFPE, FPE_INTDIV, error_get_trap_addr(regs)); } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index d0e2825ae617..571cb8657e53 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3594,7 +3594,7 @@ static int em_rdpid(struct x86_emulate_ctxt *ctxt) u64 tsc_aux = 0; if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) - return emulate_gp(ctxt, 0); + return emulate_ud(ctxt); ctxt->dst.val = tsc_aux; return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index d057376bd3d3..698969e18fe3 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -197,12 +197,9 @@ static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq) /* * If no longer has pending EOI in LAPICs, update - * EOI for this vetor. + * EOI for this vector. */ rtc_irq_eoi(ioapic, vcpu, entry->fields.vector); - kvm_ioapic_update_eoi_one(vcpu, ioapic, - entry->fields.trig_mode, - irq); break; } } diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index cfe83d4ae625..ca0781b41df9 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -7,7 +7,7 @@ #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD) + | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD) #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4ce2ddd26c0b..ccb72af1bcb5 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -490,6 +490,12 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) } } +void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec) +{ + apic_clear_irr(vec, vcpu->arch.apic); +} +EXPORT_SYMBOL_GPL(kvm_apic_clear_irr); + static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { struct kvm_vcpu *vcpu; @@ -2462,6 +2468,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) __apic_update_ppr(apic, &ppr); return apic_has_interrupt_for_ppr(apic, ppr); } +EXPORT_SYMBOL_GPL(kvm_apic_has_interrupt); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 754f29beb83e..4fb86e3a9dd3 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -89,6 +89,7 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int shorthand, unsigned int dest, int dest_mode); int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); +void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec); bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr); bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr); void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1e6724c30cc0..57cd70801216 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6341,6 +6341,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) cond_resched_lock(&kvm->mmu_lock); } } + kvm_mmu_commit_zap_page(kvm, &invalid_list); spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index e80daa98682f..b74722e0abb5 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -868,6 +868,7 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * - Tell IOMMU to use legacy mode for this interrupt. * - Retrieve ga_tag of prior interrupt remapping data. */ + pi.prev_ga_tag = 0; pi.is_guest_mode = false; ret = irq_set_vcpu_affinity(host_irq, &pi); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index a5810928b011..27e41fac9196 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2402,6 +2402,8 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base); vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); + + vmx->segment_cache.bitmask = 0; } if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & @@ -3295,8 +3297,10 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, prepare_vmcs02_early(vmx, vmcs12); if (from_vmentry) { - if (unlikely(!nested_get_vmcs12_pages(vcpu))) + if (unlikely(!nested_get_vmcs12_pages(vcpu))) { + vmx_switch_vmcs(vcpu, &vmx->vmcs01); return NVMX_VMENTRY_KVM_INTERNAL_ERROR; + } if (nested_vmx_check_vmentry_hw(vcpu)) { vmx_switch_vmcs(vcpu, &vmx->vmcs01); @@ -3480,6 +3484,14 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (unlikely(status != NVMX_VMENTRY_SUCCESS)) goto vmentry_failed; + /* Emulate processing of posted interrupts on VM-Enter. */ + if (nested_cpu_has_posted_intr(vmcs12) && + kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) { + vmx->nested.pi_pending = true; + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv); + } + /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 6110bce7237b..02c3cec7e515 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o +lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c new file mode 100644 index 000000000000..c13e8c9ee926 --- /dev/null +++ b/arch/x86/lib/copy_mc.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */ + +#include <linux/jump_label.h> +#include <linux/uaccess.h> +#include <linux/export.h> +#include <linux/string.h> +#include <linux/types.h> + +#include <asm/mce.h> + +#ifdef CONFIG_X86_MCE +/* + * See COPY_MC_TEST for self-test of the copy_mc_fragile() + * implementation. + */ +static DEFINE_STATIC_KEY_FALSE(copy_mc_fragile_key); + +void enable_copy_mc_fragile(void) +{ + static_branch_inc(©_mc_fragile_key); +} +#define copy_mc_fragile_enabled (static_branch_unlikely(©_mc_fragile_key)) + +/* + * Similar to copy_user_handle_tail, probe for the write fault point, or + * source exception point. + */ +__visible notrace unsigned long +copy_mc_fragile_handle_tail(char *to, char *from, unsigned len) +{ + for (; len; --len, to++, from++) + if (copy_mc_fragile(to, from, 1)) + break; + return len; +} +#else +/* + * No point in doing careful copying, or consulting a static key when + * there is no #MC handler in the CONFIG_X86_MCE=n case. + */ +void enable_copy_mc_fragile(void) +{ +} +#define copy_mc_fragile_enabled (0) +#endif + +unsigned long copy_mc_enhanced_fast_string(void *dst, const void *src, unsigned len); + +/** + * copy_mc_to_kernel - memory copy that handles source exceptions + * + * @dst: destination address + * @src: source address + * @len: number of bytes to copy + * + * Call into the 'fragile' version on systems that benefit from avoiding + * corner case poison consumption scenarios, For example, accessing + * poison across 2 cachelines with a single instruction. Almost all + * other uses case can use copy_mc_enhanced_fast_string() for a fast + * recoverable copy, or fallback to plain memcpy. + * + * Return 0 for success, or number of bytes not copied if there was an + * exception. + */ +unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len) +{ + if (copy_mc_fragile_enabled) + return copy_mc_fragile(dst, src, len); + if (static_cpu_has(X86_FEATURE_ERMS)) + return copy_mc_enhanced_fast_string(dst, src, len); + memcpy(dst, src, len); + return 0; +} +EXPORT_SYMBOL_GPL(copy_mc_to_kernel); + +unsigned long __must_check copy_mc_to_user(void *dst, const void *src, unsigned len) +{ + unsigned long ret; + + if (copy_mc_fragile_enabled) { + __uaccess_begin(); + ret = copy_mc_fragile(dst, src, len); + __uaccess_end(); + return ret; + } + + if (static_cpu_has(X86_FEATURE_ERMS)) { + __uaccess_begin(); + ret = copy_mc_enhanced_fast_string(dst, src, len); + __uaccess_end(); + return ret; + } + + return copy_user_generic(dst, src, len); +} diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S new file mode 100644 index 000000000000..892d8915f609 --- /dev/null +++ b/arch/x86/lib/copy_mc_64.S @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */ + +#include <linux/linkage.h> +#include <asm/copy_mc_test.h> +#include <asm/export.h> +#include <asm/asm.h> + +#ifndef CONFIG_UML + +#ifdef CONFIG_X86_MCE +COPY_MC_TEST_CTL + +/* + * copy_mc_fragile - copy memory with indication if an exception / fault happened + * + * The 'fragile' version is opted into by platform quirks and takes + * pains to avoid unrecoverable corner cases like 'fast-string' + * instruction sequences, and consuming poison across a cacheline + * boundary. The non-fragile version is equivalent to memcpy() + * regardless of CPU machine-check-recovery capability. + */ +SYM_FUNC_START(copy_mc_fragile) + cmpl $8, %edx + /* Less than 8 bytes? Go to byte copy loop */ + jb .L_no_whole_words + + /* Check for bad alignment of source */ + testl $7, %esi + /* Already aligned */ + jz .L_8byte_aligned + + /* Copy one byte at a time until source is 8-byte aligned */ + movl %esi, %ecx + andl $7, %ecx + subl $8, %ecx + negl %ecx + subl %ecx, %edx +.L_read_leading_bytes: + movb (%rsi), %al + COPY_MC_TEST_SRC %rsi 1 .E_leading_bytes + COPY_MC_TEST_DST %rdi 1 .E_leading_bytes +.L_write_leading_bytes: + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_read_leading_bytes + +.L_8byte_aligned: + movl %edx, %ecx + andl $7, %edx + shrl $3, %ecx + jz .L_no_whole_words + +.L_read_words: + movq (%rsi), %r8 + COPY_MC_TEST_SRC %rsi 8 .E_read_words + COPY_MC_TEST_DST %rdi 8 .E_write_words +.L_write_words: + movq %r8, (%rdi) + addq $8, %rsi + addq $8, %rdi + decl %ecx + jnz .L_read_words + + /* Any trailing bytes? */ +.L_no_whole_words: + andl %edx, %edx + jz .L_done_memcpy_trap + + /* Copy trailing bytes */ + movl %edx, %ecx +.L_read_trailing_bytes: + movb (%rsi), %al + COPY_MC_TEST_SRC %rsi 1 .E_trailing_bytes + COPY_MC_TEST_DST %rdi 1 .E_trailing_bytes +.L_write_trailing_bytes: + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_read_trailing_bytes + + /* Copy successful. Return zero */ +.L_done_memcpy_trap: + xorl %eax, %eax +.L_done: + ret +SYM_FUNC_END(copy_mc_fragile) +EXPORT_SYMBOL_GPL(copy_mc_fragile) + + .section .fixup, "ax" + /* + * Return number of bytes not copied for any failure. Note that + * there is no "tail" handling since the source buffer is 8-byte + * aligned and poison is cacheline aligned. + */ +.E_read_words: + shll $3, %ecx +.E_leading_bytes: + addl %edx, %ecx +.E_trailing_bytes: + mov %ecx, %eax + jmp .L_done + + /* + * For write fault handling, given the destination is unaligned, + * we handle faults on multi-byte writes with a byte-by-byte + * copy up to the write-protected page. + */ +.E_write_words: + shll $3, %ecx + addl %edx, %ecx + movl %ecx, %edx + jmp copy_mc_fragile_handle_tail + + .previous + + _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes) + _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words) + _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes) + _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes) + _ASM_EXTABLE(.L_write_words, .E_write_words) + _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes) +#endif /* CONFIG_X86_MCE */ + +/* + * copy_mc_enhanced_fast_string - memory copy with exception handling + * + * Fast string copy + fault / exception handling. If the CPU does + * support machine check exception recovery, but does not support + * recovering from fast-string exceptions then this CPU needs to be + * added to the copy_mc_fragile_key set of quirks. Otherwise, absent any + * machine check recovery support this version should be no slower than + * standard memcpy. + */ +SYM_FUNC_START(copy_mc_enhanced_fast_string) + movq %rdi, %rax + movq %rdx, %rcx +.L_copy: + rep movsb + /* Copy successful. Return zero */ + xorl %eax, %eax + ret +SYM_FUNC_END(copy_mc_enhanced_fast_string) + + .section .fixup, "ax" +.E_copy: + /* + * On fault %rcx is updated such that the copy instruction could + * optionally be restarted at the fault position, i.e. it + * contains 'bytes remaining'. A non-zero return indicates error + * to copy_mc_generic() users, or indicate short transfers to + * user-copy routines. + */ + movq %rcx, %rax + ret + + .previous + + _ASM_EXTABLE_FAULT(.L_copy, .E_copy) +#endif /* !CONFIG_UML */ diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index bbcc05bcefad..037faac46b0c 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -4,7 +4,6 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> -#include <asm/mcsafe_test.h> #include <asm/alternative-asm.h> #include <asm/export.h> @@ -187,117 +186,3 @@ SYM_FUNC_START_LOCAL(memcpy_orig) SYM_FUNC_END(memcpy_orig) .popsection - -#ifndef CONFIG_UML - -MCSAFE_TEST_CTL - -/* - * __memcpy_mcsafe - memory copy with machine check exception handling - * Note that we only catch machine checks when reading the source addresses. - * Writes to target are posted and don't generate machine checks. - */ -SYM_FUNC_START(__memcpy_mcsafe) - cmpl $8, %edx - /* Less than 8 bytes? Go to byte copy loop */ - jb .L_no_whole_words - - /* Check for bad alignment of source */ - testl $7, %esi - /* Already aligned */ - jz .L_8byte_aligned - - /* Copy one byte at a time until source is 8-byte aligned */ - movl %esi, %ecx - andl $7, %ecx - subl $8, %ecx - negl %ecx - subl %ecx, %edx -.L_read_leading_bytes: - movb (%rsi), %al - MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes - MCSAFE_TEST_DST %rdi 1 .E_leading_bytes -.L_write_leading_bytes: - movb %al, (%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz .L_read_leading_bytes - -.L_8byte_aligned: - movl %edx, %ecx - andl $7, %edx - shrl $3, %ecx - jz .L_no_whole_words - -.L_read_words: - movq (%rsi), %r8 - MCSAFE_TEST_SRC %rsi 8 .E_read_words - MCSAFE_TEST_DST %rdi 8 .E_write_words -.L_write_words: - movq %r8, (%rdi) - addq $8, %rsi - addq $8, %rdi - decl %ecx - jnz .L_read_words - - /* Any trailing bytes? */ -.L_no_whole_words: - andl %edx, %edx - jz .L_done_memcpy_trap - - /* Copy trailing bytes */ - movl %edx, %ecx -.L_read_trailing_bytes: - movb (%rsi), %al - MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes - MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes -.L_write_trailing_bytes: - movb %al, (%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz .L_read_trailing_bytes - - /* Copy successful. Return zero */ -.L_done_memcpy_trap: - xorl %eax, %eax -.L_done: - ret -SYM_FUNC_END(__memcpy_mcsafe) -EXPORT_SYMBOL_GPL(__memcpy_mcsafe) - - .section .fixup, "ax" - /* - * Return number of bytes not copied for any failure. Note that - * there is no "tail" handling since the source buffer is 8-byte - * aligned and poison is cacheline aligned. - */ -.E_read_words: - shll $3, %ecx -.E_leading_bytes: - addl %edx, %ecx -.E_trailing_bytes: - mov %ecx, %eax - jmp .L_done - - /* - * For write fault handling, given the destination is unaligned, - * we handle faults on multi-byte writes with a byte-by-byte - * copy up to the write-protected page. - */ -.E_write_words: - shll $3, %ecx - addl %edx, %ecx - movl %ecx, %edx - jmp mcsafe_handle_tail - - .previous - - _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes) - _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words) - _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes) - _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes) - _ASM_EXTABLE(.L_write_words, .E_write_words) - _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes) -#endif diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 1847e993ac63..508c81e97ab1 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -56,27 +56,6 @@ unsigned long clear_user(void __user *to, unsigned long n) } EXPORT_SYMBOL(clear_user); -/* - * Similar to copy_user_handle_tail, probe for the write fault point, - * but reuse __memcpy_mcsafe in case a new read error is encountered. - * clac() is handled in _copy_to_iter_mcsafe(). - */ -__visible notrace unsigned long -mcsafe_handle_tail(char *to, char *from, unsigned len) -{ - for (; len; --len, to++, from++) { - /* - * Call the assembly routine back directly since - * memcpy_mcsafe() may silently fallback to memcpy. - */ - unsigned long rem = __memcpy_mcsafe(to, from, 1); - - if (rem) - break; - } - return len; -} - #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /** * clean_cache_range - write back a cache range with CLWB diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 00c62115f39c..0aaf31917061 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -33,6 +33,7 @@ #include <asm/hw_irq.h> #include <asm/io_apic.h> #include <asm/intel-mid.h> +#include <asm/acpi.h> #define PCIE_CAP_OFFSET 0x100 diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index c46b9f2e732f..6e39eda00c2c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1438,6 +1438,15 @@ asmlinkage __visible void __init xen_start_kernel(void) x86_init.mpparse.get_smp_config = x86_init_uint_noop; xen_boot_params_init_edd(); + +#ifdef CONFIG_ACPI + /* + * Disable selecting "Firmware First mode" for correctable + * memory errors, as this is the duty of the hypervisor to + * decide. + */ + acpi_disable_cmcff = 1; +#endif } if (!boot_params.screen_info.orig_video_isVGA) |