diff options
Diffstat (limited to 'arch')
271 files changed, 4176 insertions, 1589 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index fabe39169b12..4c97cb40eebb 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -83,6 +83,7 @@ config ARM select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32 select HAVE_CONTEXT_TRACKING select HAVE_C_RECORDMCOUNT + select HAVE_BUILDTIME_MCOUNT_SORT select HAVE_DEBUG_KMEMLEAK if !XIP_KERNEL select HAVE_DMA_CONTIGUOUS if MMU select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 235ad559acb2..e41eca79c950 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -806,6 +806,7 @@ dtb-$(CONFIG_ARCH_OMAP3) += \ logicpd-som-lv-37xx-devkit.dtb \ omap3430-sdp.dtb \ omap3-beagle.dtb \ + omap3-beagle-ab4.dtb \ omap3-beagle-xm.dtb \ omap3-beagle-xm-ab.dtb \ omap3-cm-t3517.dtb \ diff --git a/arch/arm/boot/dts/am335x-wega.dtsi b/arch/arm/boot/dts/am335x-wega.dtsi index 673159d93a6a..f957fea8208e 100644 --- a/arch/arm/boot/dts/am335x-wega.dtsi +++ b/arch/arm/boot/dts/am335x-wega.dtsi @@ -55,7 +55,7 @@ 2 1 0 0 /* # 0: INACTIVE, 1: TX, 2: RX */ >; tx-num-evt = <16>; - rt-num-evt = <16>; + rx-num-evt = <16>; status = "okay"; }; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 6b485cbed8d5..42bff117656c 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -160,7 +160,7 @@ target-module@48210000 { compatible = "ti,sysc-omap4-simple", "ti,sysc"; power-domains = <&prm_mpu>; - clocks = <&mpu_clkctrl DRA7_MPU_CLKCTRL 0>; + clocks = <&mpu_clkctrl DRA7_MPU_MPU_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; @@ -875,10 +875,10 @@ <0x58000014 4>; reg-names = "rev", "syss"; ti,syss-mask = <1>; - clocks = <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 0>, - <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 9>, - <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 10>, - <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 11>; + clocks = <&dss_clkctrl DRA7_DSS_DSS_CORE_CLKCTRL 0>, + <&dss_clkctrl DRA7_DSS_DSS_CORE_CLKCTRL 9>, + <&dss_clkctrl DRA7_DSS_DSS_CORE_CLKCTRL 10>, + <&dss_clkctrl DRA7_DSS_DSS_CORE_CLKCTRL 11>; clock-names = "fck", "hdmi_clk", "sys_clk", "tv_clk"; #address-cells = <1>; #size-cells = <1>; @@ -912,7 +912,7 @@ SYSC_OMAP2_SOFTRESET | SYSC_OMAP2_AUTOIDLE)>; ti,syss-mask = <1>; - clocks = <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 8>; + clocks = <&dss_clkctrl DRA7_DSS_DSS_CORE_CLKCTRL 8>; clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; @@ -939,8 +939,8 @@ <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; ti,sysc-mask = <(SYSC_OMAP4_SOFTRESET)>; - clocks = <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 9>, - <&dss_clkctrl DRA7_DSS_CORE_CLKCTRL 8>; + clocks = <&dss_clkctrl DRA7_DSS_DSS_CORE_CLKCTRL 9>, + <&dss_clkctrl DRA7_DSS_DSS_CORE_CLKCTRL 8>; clock-names = "fck", "dss_clk"; #address-cells = <1>; #size-cells = <1>; @@ -979,7 +979,7 @@ compatible = "vivante,gc"; reg = <0x0 0x700>; interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&dss_clkctrl DRA7_BB2D_CLKCTRL 0>; + clocks = <&dss_clkctrl DRA7_DSS_BB2D_CLKCTRL 0>; clock-names = "core"; }; }; @@ -1333,7 +1333,7 @@ ti,no-reset-on-init; ti,no-idle; timer@0 { - assigned-clocks = <&wkupaon_clkctrl DRA7_TIMER1_CLKCTRL 24>; + assigned-clocks = <&wkupaon_clkctrl DRA7_WKUPAON_TIMER1_CLKCTRL 24>; assigned-clock-parents = <&sys_32k_ck>; }; }; diff --git a/arch/arm/boot/dts/imx23-evk.dts b/arch/arm/boot/dts/imx23-evk.dts index 8cbaf1c81174..3b609d987d88 100644 --- a/arch/arm/boot/dts/imx23-evk.dts +++ b/arch/arm/boot/dts/imx23-evk.dts @@ -79,7 +79,6 @@ MX23_PAD_LCD_RESET__GPIO_1_18 MX23_PAD_PWM3__GPIO_1_29 MX23_PAD_PWM4__GPIO_1_30 - MX23_PAD_SSP1_DETECT__SSP1_DETECT >; fsl,drive-strength = <MXS_DRIVE_4mA>; fsl,voltage = <MXS_VOLTAGE_HIGH>; diff --git a/arch/arm/boot/dts/imx6qdl-udoo.dtsi b/arch/arm/boot/dts/imx6qdl-udoo.dtsi index d07d8f83456d..ccfa8e320be6 100644 --- a/arch/arm/boot/dts/imx6qdl-udoo.dtsi +++ b/arch/arm/boot/dts/imx6qdl-udoo.dtsi @@ -5,6 +5,8 @@ * Author: Fabio Estevam <fabio.estevam@freescale.com> */ +#include <dt-bindings/gpio/gpio.h> + / { aliases { backlight = &backlight; @@ -226,6 +228,7 @@ MX6QDL_PAD_SD3_DAT1__SD3_DATA1 0x17059 MX6QDL_PAD_SD3_DAT2__SD3_DATA2 0x17059 MX6QDL_PAD_SD3_DAT3__SD3_DATA3 0x17059 + MX6QDL_PAD_SD3_DAT5__GPIO7_IO00 0x1b0b0 >; }; @@ -304,7 +307,7 @@ &usdhc3 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usdhc3>; - non-removable; + cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx7ulp.dtsi b/arch/arm/boot/dts/imx7ulp.dtsi index b7ea37ad4e55..bcec98b96411 100644 --- a/arch/arm/boot/dts/imx7ulp.dtsi +++ b/arch/arm/boot/dts/imx7ulp.dtsi @@ -259,7 +259,7 @@ interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; clocks = <&pcc2 IMX7ULP_CLK_WDG1>; assigned-clocks = <&pcc2 IMX7ULP_CLK_WDG1>; - assigned-clocks-parents = <&scg1 IMX7ULP_CLK_FIRC_BUS_CLK>; + assigned-clock-parents = <&scg1 IMX7ULP_CLK_FIRC_BUS_CLK>; timeout-sec = <40>; }; diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi index 3be7cba603d5..26eaba3fa96f 100644 --- a/arch/arm/boot/dts/meson.dtsi +++ b/arch/arm/boot/dts/meson.dtsi @@ -59,7 +59,7 @@ }; uart_A: serial@84c0 { - compatible = "amlogic,meson6-uart", "amlogic,meson-uart"; + compatible = "amlogic,meson6-uart"; reg = <0x84c0 0x18>; interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>; fifo-size = <128>; @@ -67,7 +67,7 @@ }; uart_B: serial@84dc { - compatible = "amlogic,meson6-uart", "amlogic,meson-uart"; + compatible = "amlogic,meson6-uart"; reg = <0x84dc 0x18>; interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>; status = "disabled"; @@ -105,7 +105,7 @@ }; uart_C: serial@8700 { - compatible = "amlogic,meson6-uart", "amlogic,meson-uart"; + compatible = "amlogic,meson6-uart"; reg = <0x8700 0x18>; interrupts = <GIC_SPI 93 IRQ_TYPE_EDGE_RISING>; status = "disabled"; @@ -228,7 +228,7 @@ }; uart_AO: serial@4c0 { - compatible = "amlogic,meson6-uart", "amlogic,meson-ao-uart", "amlogic,meson-uart"; + compatible = "amlogic,meson6-uart", "amlogic,meson-ao-uart"; reg = <0x4c0 0x18>; interrupts = <GIC_SPI 90 IRQ_TYPE_EDGE_RISING>; status = "disabled"; diff --git a/arch/arm/boot/dts/meson8.dtsi b/arch/arm/boot/dts/meson8.dtsi index f80ddc98d3a2..9997a5d0333a 100644 --- a/arch/arm/boot/dts/meson8.dtsi +++ b/arch/arm/boot/dts/meson8.dtsi @@ -736,27 +736,27 @@ }; &uart_AO { - compatible = "amlogic,meson8-uart", "amlogic,meson-uart"; - clocks = <&clkc CLKID_CLK81>, <&xtal>, <&clkc CLKID_CLK81>; - clock-names = "baud", "xtal", "pclk"; + compatible = "amlogic,meson8-uart", "amlogic,meson-ao-uart"; + clocks = <&xtal>, <&clkc CLKID_CLK81>, <&clkc CLKID_CLK81>; + clock-names = "xtal", "pclk", "baud"; }; &uart_A { - compatible = "amlogic,meson8-uart", "amlogic,meson-uart"; - clocks = <&clkc CLKID_CLK81>, <&xtal>, <&clkc CLKID_UART0>; - clock-names = "baud", "xtal", "pclk"; + compatible = "amlogic,meson8-uart"; + clocks = <&xtal>, <&clkc CLKID_UART0>, <&clkc CLKID_CLK81>; + clock-names = "xtal", "pclk", "baud"; }; &uart_B { - compatible = "amlogic,meson8-uart", "amlogic,meson-uart"; - clocks = <&clkc CLKID_CLK81>, <&xtal>, <&clkc CLKID_UART1>; - clock-names = "baud", "xtal", "pclk"; + compatible = "amlogic,meson8-uart"; + clocks = <&xtal>, <&clkc CLKID_UART0>, <&clkc CLKID_CLK81>; + clock-names = "xtal", "pclk", "baud"; }; &uart_C { - compatible = "amlogic,meson8-uart", "amlogic,meson-uart"; - clocks = <&clkc CLKID_CLK81>, <&xtal>, <&clkc CLKID_UART2>; - clock-names = "baud", "xtal", "pclk"; + compatible = "amlogic,meson8-uart"; + clocks = <&xtal>, <&clkc CLKID_UART0>, <&clkc CLKID_CLK81>; + clock-names = "xtal", "pclk", "baud"; }; &usb0 { diff --git a/arch/arm/boot/dts/meson8b.dtsi b/arch/arm/boot/dts/meson8b.dtsi index b49b7cbaed4e..94f1c03decce 100644 --- a/arch/arm/boot/dts/meson8b.dtsi +++ b/arch/arm/boot/dts/meson8b.dtsi @@ -724,27 +724,27 @@ }; &uart_AO { - compatible = "amlogic,meson8b-uart", "amlogic,meson-uart"; - clocks = <&clkc CLKID_CLK81>, <&xtal>, <&clkc CLKID_CLK81>; - clock-names = "baud", "xtal", "pclk"; + compatible = "amlogic,meson8b-uart", "amlogic,meson-ao-uart"; + clocks = <&xtal>, <&clkc CLKID_CLK81>, <&clkc CLKID_CLK81>; + clock-names = "xtal", "pclk", "baud"; }; &uart_A { - compatible = "amlogic,meson8b-uart", "amlogic,meson-uart"; - clocks = <&clkc CLKID_CLK81>, <&xtal>, <&clkc CLKID_UART0>; - clock-names = "baud", "xtal", "pclk"; + compatible = "amlogic,meson8b-uart"; + clocks = <&xtal>, <&clkc CLKID_UART0>, <&clkc CLKID_CLK81>; + clock-names = "xtal", "pclk", "baud"; }; &uart_B { - compatible = "amlogic,meson8b-uart", "amlogic,meson-uart"; - clocks = <&clkc CLKID_CLK81>, <&xtal>, <&clkc CLKID_UART1>; - clock-names = "baud", "xtal", "pclk"; + compatible = "amlogic,meson8b-uart"; + clocks = <&xtal>, <&clkc CLKID_UART0>, <&clkc CLKID_CLK81>; + clock-names = "xtal", "pclk", "baud"; }; &uart_C { - compatible = "amlogic,meson8b-uart", "amlogic,meson-uart"; - clocks = <&clkc CLKID_CLK81>, <&xtal>, <&clkc CLKID_UART2>; - clock-names = "baud", "xtal", "pclk"; + compatible = "amlogic,meson8b-uart"; + clocks = <&xtal>, <&clkc CLKID_UART0>, <&clkc CLKID_CLK81>; + clock-names = "xtal", "pclk", "baud"; }; &usb0 { diff --git a/arch/arm/boot/dts/omap3-beagle-ab4.dts b/arch/arm/boot/dts/omap3-beagle-ab4.dts new file mode 100644 index 000000000000..990ff2d84686 --- /dev/null +++ b/arch/arm/boot/dts/omap3-beagle-ab4.dts @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0-only +/dts-v1/; + +#include "omap3-beagle.dts" + +/ { + model = "TI OMAP3 BeagleBoard A to B4"; + compatible = "ti,omap3-beagle-ab4", "ti,omap3-beagle", "ti,omap3430", "ti,omap3"; +}; + +/* + * Workaround for capacitor C70 issue, see "Boards revision A and < B5" + * section at https://elinux.org/BeagleBoard_Community + */ + +/* Unusable as clocksource because of unreliable oscillator */ +&counter32k { + status = "disabled"; +}; + +/* Unusable as clockevent because of unreliable oscillator, allow to idle */ +&timer1_target { + /delete-property/ti,no-reset-on-init; + /delete-property/ti,no-idle; + timer@0 { + /delete-property/ti,timer-alwon; + }; +}; + +/* Preferred always-on timer for clocksource */ +&timer12_target { + ti,no-reset-on-init; + ti,no-idle; + timer@0 { + /* Always clocked by secure_32k_fck */ + }; +}; + +/* Preferred timer for clockevent */ +&timer2_target { + ti,no-reset-on-init; + ti,no-idle; + timer@0 { + assigned-clocks = <&gpt2_fck>; + assigned-clock-parents = <&sys_ck>; + }; +}; diff --git a/arch/arm/boot/dts/omap3-beagle.dts b/arch/arm/boot/dts/omap3-beagle.dts index f9f34b8458e9..0548b391334f 100644 --- a/arch/arm/boot/dts/omap3-beagle.dts +++ b/arch/arm/boot/dts/omap3-beagle.dts @@ -304,39 +304,6 @@ phys = <0 &hsusb2_phy>; }; -/* Unusable as clocksource because of unreliable oscillator */ -&counter32k { - status = "disabled"; -}; - -/* Unusable as clockevent because if unreliable oscillator, allow to idle */ -&timer1_target { - /delete-property/ti,no-reset-on-init; - /delete-property/ti,no-idle; - timer@0 { - /delete-property/ti,timer-alwon; - }; -}; - -/* Preferred always-on timer for clocksource */ -&timer12_target { - ti,no-reset-on-init; - ti,no-idle; - timer@0 { - /* Always clocked by secure_32k_fck */ - }; -}; - -/* Preferred timer for clockevent */ -&timer2_target { - ti,no-reset-on-init; - ti,no-idle; - timer@0 { - assigned-clocks = <&gpt2_fck>; - assigned-clock-parents = <&sys_ck>; - }; -}; - &twl_gpio { ti,use-leds; /* pullups: BIT(1) */ diff --git a/arch/arm/boot/dts/omap3-devkit8000-common.dtsi b/arch/arm/boot/dts/omap3-devkit8000-common.dtsi index 5e55198e4576..54cd37336be7 100644 --- a/arch/arm/boot/dts/omap3-devkit8000-common.dtsi +++ b/arch/arm/boot/dts/omap3-devkit8000-common.dtsi @@ -158,6 +158,24 @@ status = "disabled"; }; +/* Unusable as clockevent because if unreliable oscillator, allow to idle */ +&timer1_target { + /delete-property/ti,no-reset-on-init; + /delete-property/ti,no-idle; + timer@0 { + /delete-property/ti,timer-alwon; + }; +}; + +/* Preferred timer for clockevent */ +&timer12_target { + ti,no-reset-on-init; + ti,no-idle; + timer@0 { + /* Always clocked by secure_32k_fck */ + }; +}; + &twl_gpio { ti,use-leds; /* diff --git a/arch/arm/boot/dts/omap3-devkit8000.dts b/arch/arm/boot/dts/omap3-devkit8000.dts index c2995a280729..162d0726b008 100644 --- a/arch/arm/boot/dts/omap3-devkit8000.dts +++ b/arch/arm/boot/dts/omap3-devkit8000.dts @@ -14,36 +14,3 @@ display2 = &tv0; }; }; - -/* Unusable as clocksource because of unreliable oscillator */ -&counter32k { - status = "disabled"; -}; - -/* Unusable as clockevent because if unreliable oscillator, allow to idle */ -&timer1_target { - /delete-property/ti,no-reset-on-init; - /delete-property/ti,no-idle; - timer@0 { - /delete-property/ti,timer-alwon; - }; -}; - -/* Preferred always-on timer for clocksource */ -&timer12_target { - ti,no-reset-on-init; - ti,no-idle; - timer@0 { - /* Always clocked by secure_32k_fck */ - }; -}; - -/* Preferred timer for clockevent */ -&timer2_target { - ti,no-reset-on-init; - ti,no-idle; - timer@0 { - assigned-clocks = <&gpt2_fck>; - assigned-clock-parents = <&sys_ck>; - }; -}; diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi index 8eed9e3a92e9..5868eb512f69 100644 --- a/arch/arm/boot/dts/rk322x.dtsi +++ b/arch/arm/boot/dts/rk322x.dtsi @@ -718,8 +718,8 @@ interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>; assigned-clocks = <&cru SCLK_HDMI_PHY>; assigned-clock-parents = <&hdmi_phy>; - clocks = <&cru SCLK_HDMI_HDCP>, <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_CEC>; - clock-names = "isfr", "iahb", "cec"; + clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_HDCP>, <&cru SCLK_HDMI_CEC>; + clock-names = "iahb", "isfr", "cec"; pinctrl-names = "default"; pinctrl-0 = <&hdmii2c_xfer &hdmi_hpd &hdmi_cec>; resets = <&cru SRST_HDMI_P>; diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index aaaa61875701..45a9d9b908d2 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -971,7 +971,7 @@ status = "disabled"; }; - crypto: cypto-controller@ff8a0000 { + crypto: crypto@ff8a0000 { compatible = "rockchip,rk3288-crypto"; reg = <0x0 0xff8a0000 0x0 0x4000>; interrupts = <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/spear320-hmi.dts b/arch/arm/boot/dts/spear320-hmi.dts index 367ba48aac3e..b587e4ec11e5 100644 --- a/arch/arm/boot/dts/spear320-hmi.dts +++ b/arch/arm/boot/dts/spear320-hmi.dts @@ -235,7 +235,6 @@ #address-cells = <1>; #size-cells = <0>; reg = <0x41>; - irq-over-gpio; irq-gpios = <&gpiopinctrl 29 0x4>; id = <0>; blocks = <0x5>; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts b/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts index 580ca497f312..f8c5899fbdba 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts @@ -185,10 +185,6 @@ cap-sd-highspeed; cap-mmc-highspeed; /* All direction control is used */ - st,sig-dir-cmd; - st,sig-dir-dat0; - st,sig-dir-dat2; - st,sig-dir-dat31; st,sig-pin-fbclk; full-pwr-cycle; vmmc-supply = <&ab8500_ldo_aux3_reg>; diff --git a/arch/arm/boot/dts/tegra124-nyan-big.dts b/arch/arm/boot/dts/tegra124-nyan-big.dts index 1d2aac2cb6d0..fdc1d64dfff9 100644 --- a/arch/arm/boot/dts/tegra124-nyan-big.dts +++ b/arch/arm/boot/dts/tegra124-nyan-big.dts @@ -13,12 +13,15 @@ "google,nyan-big-rev1", "google,nyan-big-rev0", "google,nyan-big", "google,nyan", "nvidia,tegra124"; - panel: panel { - compatible = "auo,b133xtn01"; - - power-supply = <&vdd_3v3_panel>; - backlight = <&backlight>; - ddc-i2c-bus = <&dpaux>; + host1x@50000000 { + dpaux@545c0000 { + aux-bus { + panel: panel { + compatible = "auo,b133xtn01"; + backlight = <&backlight>; + }; + }; + }; }; mmc@700b0400 { /* SD Card on this bus */ diff --git a/arch/arm/boot/dts/tegra124-nyan-blaze.dts b/arch/arm/boot/dts/tegra124-nyan-blaze.dts index 677babde6460..abdf4456826f 100644 --- a/arch/arm/boot/dts/tegra124-nyan-blaze.dts +++ b/arch/arm/boot/dts/tegra124-nyan-blaze.dts @@ -15,12 +15,15 @@ "google,nyan-blaze-rev0", "google,nyan-blaze", "google,nyan", "nvidia,tegra124"; - panel: panel { - compatible = "samsung,ltn140at29-301"; - - power-supply = <&vdd_3v3_panel>; - backlight = <&backlight>; - ddc-i2c-bus = <&dpaux>; + host1x@50000000 { + dpaux@545c0000 { + aux-bus { + panel: panel { + compatible = "samsung,ltn140at29-301"; + backlight = <&backlight>; + }; + }; + }; }; sound { diff --git a/arch/arm/boot/dts/tegra124-venice2.dts b/arch/arm/boot/dts/tegra124-venice2.dts index 232c90604df9..6a9592ceb5f2 100644 --- a/arch/arm/boot/dts/tegra124-venice2.dts +++ b/arch/arm/boot/dts/tegra124-venice2.dts @@ -48,6 +48,13 @@ dpaux@545c0000 { vdd-supply = <&vdd_3v3_panel>; status = "okay"; + + aux-bus { + panel: panel { + compatible = "lg,lp129qe"; + backlight = <&backlight>; + }; + }; }; }; @@ -1080,13 +1087,6 @@ }; }; - panel: panel { - compatible = "lg,lp129qe"; - power-supply = <&vdd_3v3_panel>; - backlight = <&backlight>; - ddc-i2c-bus = <&dpaux>; - }; - vdd_mux: regulator-mux { compatible = "regulator-fixed"; regulator-name = "+VDD_MUX"; diff --git a/arch/arm/crypto/blake2s-shash.c b/arch/arm/crypto/blake2s-shash.c index 17c1c3bfe2f5..763c73beea2d 100644 --- a/arch/arm/crypto/blake2s-shash.c +++ b/arch/arm/crypto/blake2s-shash.c @@ -13,12 +13,12 @@ static int crypto_blake2s_update_arm(struct shash_desc *desc, const u8 *in, unsigned int inlen) { - return crypto_blake2s_update(desc, in, inlen, blake2s_compress); + return crypto_blake2s_update(desc, in, inlen, false); } static int crypto_blake2s_final_arm(struct shash_desc *desc, u8 *out) { - return crypto_blake2s_final(desc, out, blake2s_compress); + return crypto_blake2s_final(desc, out, false); } #define BLAKE2S_ALG(name, driver_name, digest_size) \ diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 7d23d4bb2168..aee73ef5b3dc 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -107,6 +107,16 @@ .endm #endif +#if __LINUX_ARM_ARCH__ < 7 + .macro dsb, args + mcr p15, 0, r0, c7, c10, 4 + .endm + + .macro isb, args + mcr p15, 0, r0, c7, c5, 4 + .endm +#endif + .macro asm_trace_hardirqs_off, save=1 #if defined(CONFIG_TRACE_IRQFLAGS) .if \save @@ -288,6 +298,7 @@ */ #define ALT_UP(instr...) \ .pushsection ".alt.smp.init", "a" ;\ + .align 2 ;\ .long 9998b - . ;\ 9997: instr ;\ .if . - 9997b == 2 ;\ @@ -299,6 +310,7 @@ .popsection #define ALT_UP_B(label) \ .pushsection ".alt.smp.init", "a" ;\ + .align 2 ;\ .long 9998b - . ;\ W(b) . + (label - 9998b) ;\ .popsection diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index 6af68edfa53a..bdc35c0e8dfb 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -96,6 +96,7 @@ unsigned long __get_wchan(struct task_struct *p); #define __ALT_SMP_ASM(smp, up) \ "9998: " smp "\n" \ " .pushsection \".alt.smp.init\", \"a\"\n" \ + " .align 2\n" \ " .long 9998b - .\n" \ " " up "\n" \ " .popsection\n" diff --git a/arch/arm/include/asm/spectre.h b/arch/arm/include/asm/spectre.h new file mode 100644 index 000000000000..d1fa5607d3aa --- /dev/null +++ b/arch/arm/include/asm/spectre.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_SPECTRE_H +#define __ASM_SPECTRE_H + +enum { + SPECTRE_UNAFFECTED, + SPECTRE_MITIGATED, + SPECTRE_VULNERABLE, +}; + +enum { + __SPECTRE_V2_METHOD_BPIALL, + __SPECTRE_V2_METHOD_ICIALLU, + __SPECTRE_V2_METHOD_SMC, + __SPECTRE_V2_METHOD_HVC, + __SPECTRE_V2_METHOD_LOOP8, +}; + +enum { + SPECTRE_V2_METHOD_BPIALL = BIT(__SPECTRE_V2_METHOD_BPIALL), + SPECTRE_V2_METHOD_ICIALLU = BIT(__SPECTRE_V2_METHOD_ICIALLU), + SPECTRE_V2_METHOD_SMC = BIT(__SPECTRE_V2_METHOD_SMC), + SPECTRE_V2_METHOD_HVC = BIT(__SPECTRE_V2_METHOD_HVC), + SPECTRE_V2_METHOD_LOOP8 = BIT(__SPECTRE_V2_METHOD_LOOP8), +}; + +void spectre_v2_update_state(unsigned int state, unsigned int methods); + +int spectre_bhb_update_vectors(unsigned int method); + +#endif diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 36fbc3329252..32dbfd81f42a 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -11,6 +11,7 @@ #include <linux/string.h> #include <asm/memory.h> #include <asm/domain.h> +#include <asm/unaligned.h> #include <asm/unified.h> #include <asm/compiler.h> @@ -497,7 +498,10 @@ do { \ } \ default: __err = __get_user_bad(); break; \ } \ - *(type *)(dst) = __val; \ + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) \ + put_unaligned(__val, (type *)(dst)); \ + else \ + *(type *)(dst) = __val; /* aligned by caller */ \ if (__err) \ goto err_label; \ } while (0) @@ -507,7 +511,9 @@ do { \ const type *__pk_ptr = (dst); \ unsigned long __dst = (unsigned long)__pk_ptr; \ int __err = 0; \ - type __val = *(type *)src; \ + type __val = IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) \ + ? get_unaligned((type *)(src)) \ + : *(type *)(src); /* aligned by caller */ \ switch (sizeof(type)) { \ case 1: __put_user_asm_byte(__val, __dst, __err, ""); break; \ case 2: __put_user_asm_half(__val, __dst, __err, ""); break; \ diff --git a/arch/arm/include/asm/vmlinux.lds.h b/arch/arm/include/asm/vmlinux.lds.h index 4a91428c324d..fad45c884e98 100644 --- a/arch/arm/include/asm/vmlinux.lds.h +++ b/arch/arm/include/asm/vmlinux.lds.h @@ -26,6 +26,19 @@ #define ARM_MMU_DISCARD(x) x #endif +/* + * ld.lld does not support NOCROSSREFS: + * https://github.com/ClangBuiltLinux/linux/issues/1609 + */ +#ifdef CONFIG_LD_IS_LLD +#define NOCROSSREFS +#endif + +/* Set start/end symbol names to the LMA for the section */ +#define ARM_LMA(sym, section) \ + sym##_start = LOADADDR(section); \ + sym##_end = LOADADDR(section) + SIZEOF(section) + #define PROC_INFO \ . = ALIGN(4); \ __proc_info_begin = .; \ @@ -110,19 +123,31 @@ * only thing that matters is their relative offsets */ #define ARM_VECTORS \ - __vectors_start = .; \ - .vectors 0xffff0000 : AT(__vectors_start) { \ - *(.vectors) \ + __vectors_lma = .; \ + OVERLAY 0xffff0000 : NOCROSSREFS AT(__vectors_lma) { \ + .vectors { \ + *(.vectors) \ + } \ + .vectors.bhb.loop8 { \ + *(.vectors.bhb.loop8) \ + } \ + .vectors.bhb.bpiall { \ + *(.vectors.bhb.bpiall) \ + } \ } \ - . = __vectors_start + SIZEOF(.vectors); \ - __vectors_end = .; \ + ARM_LMA(__vectors, .vectors); \ + ARM_LMA(__vectors_bhb_loop8, .vectors.bhb.loop8); \ + ARM_LMA(__vectors_bhb_bpiall, .vectors.bhb.bpiall); \ + . = __vectors_lma + SIZEOF(.vectors) + \ + SIZEOF(.vectors.bhb.loop8) + \ + SIZEOF(.vectors.bhb.bpiall); \ \ - __stubs_start = .; \ - .stubs ADDR(.vectors) + 0x1000 : AT(__stubs_start) { \ + __stubs_lma = .; \ + .stubs ADDR(.vectors) + 0x1000 : AT(__stubs_lma) { \ *(.stubs) \ } \ - . = __stubs_start + SIZEOF(.stubs); \ - __stubs_end = .; \ + ARM_LMA(__stubs, .stubs); \ + . = __stubs_lma + SIZEOF(.stubs); \ \ PROVIDE(vector_fiq_offset = vector_fiq - ADDR(.vectors)); diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index ae295a3bcfef..6ef3b535b7bf 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -106,4 +106,6 @@ endif obj-$(CONFIG_HAVE_ARM_SMCCC) += smccc-call.o +obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += spectre.o + extra-y := $(head-y) vmlinux.lds diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 5cd057859fe9..676703cbfe4b 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -1002,12 +1002,11 @@ vector_\name: sub lr, lr, #\correction .endif - @ - @ Save r0, lr_<exception> (parent PC) and spsr_<exception> - @ (parent CPSR) - @ + @ Save r0, lr_<exception> (parent PC) stmia sp, {r0, lr} @ save r0, lr - mrs lr, spsr + + @ Save spsr_<exception> (parent CPSR) +2: mrs lr, spsr str lr, [sp, #8] @ save spsr @ @@ -1028,6 +1027,44 @@ vector_\name: movs pc, lr @ branch to handler in SVC mode ENDPROC(vector_\name) +#ifdef CONFIG_HARDEN_BRANCH_HISTORY + .subsection 1 + .align 5 +vector_bhb_loop8_\name: + .if \correction + sub lr, lr, #\correction + .endif + + @ Save r0, lr_<exception> (parent PC) + stmia sp, {r0, lr} + + @ bhb workaround + mov r0, #8 +1: b . + 4 + subs r0, r0, #1 + bne 1b + dsb + isb + b 2b +ENDPROC(vector_bhb_loop8_\name) + +vector_bhb_bpiall_\name: + .if \correction + sub lr, lr, #\correction + .endif + + @ Save r0, lr_<exception> (parent PC) + stmia sp, {r0, lr} + + @ bhb workaround + mcr p15, 0, r0, c7, c5, 6 @ BPIALL + @ isb not needed due to "movs pc, lr" in the vector stub + @ which gives a "context synchronisation". + b 2b +ENDPROC(vector_bhb_bpiall_\name) + .previous +#endif + .align 2 @ handler addresses follow this label 1: @@ -1036,6 +1073,10 @@ ENDPROC(vector_\name) .section .stubs, "ax", %progbits @ This must be the first word .word vector_swi +#ifdef CONFIG_HARDEN_BRANCH_HISTORY + .word vector_bhb_loop8_swi + .word vector_bhb_bpiall_swi +#endif vector_rst: ARM( swi SYS_ERROR0 ) @@ -1150,8 +1191,10 @@ vector_addrexcptn: * FIQ "NMI" handler *----------------------------------------------------------------------------- * Handle a FIQ using the SVC stack allowing FIQ act like NMI on x86 - * systems. + * systems. This must be the last vector stub, so lets place it in its own + * subsection. */ + .subsection 2 vector_stub fiq, FIQ_MODE, 4 .long __fiq_usr @ 0 (USR_26 / USR_32) @@ -1184,6 +1227,30 @@ vector_addrexcptn: W(b) vector_irq W(b) vector_fiq +#ifdef CONFIG_HARDEN_BRANCH_HISTORY + .section .vectors.bhb.loop8, "ax", %progbits +.L__vectors_bhb_loop8_start: + W(b) vector_rst + W(b) vector_bhb_loop8_und + W(ldr) pc, .L__vectors_bhb_loop8_start + 0x1004 + W(b) vector_bhb_loop8_pabt + W(b) vector_bhb_loop8_dabt + W(b) vector_addrexcptn + W(b) vector_bhb_loop8_irq + W(b) vector_bhb_loop8_fiq + + .section .vectors.bhb.bpiall, "ax", %progbits +.L__vectors_bhb_bpiall_start: + W(b) vector_rst + W(b) vector_bhb_bpiall_und + W(ldr) pc, .L__vectors_bhb_bpiall_start + 0x1008 + W(b) vector_bhb_bpiall_pabt + W(b) vector_bhb_bpiall_dabt + W(b) vector_addrexcptn + W(b) vector_bhb_bpiall_irq + W(b) vector_bhb_bpiall_fiq +#endif + .data .align 2 diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index ac86c34682bb..dbc1913ee30b 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -154,12 +154,36 @@ ENDPROC(ret_from_fork) */ .align 5 +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +ENTRY(vector_bhb_loop8_swi) + sub sp, sp, #PT_REGS_SIZE + stmia sp, {r0 - r12} + mov r8, #8 +1: b 2f +2: subs r8, r8, #1 + bne 1b + dsb + isb + b 3f +ENDPROC(vector_bhb_loop8_swi) + + .align 5 +ENTRY(vector_bhb_bpiall_swi) + sub sp, sp, #PT_REGS_SIZE + stmia sp, {r0 - r12} + mcr p15, 0, r8, c7, c5, 6 @ BPIALL + isb + b 3f +ENDPROC(vector_bhb_bpiall_swi) +#endif + .align 5 ENTRY(vector_swi) #ifdef CONFIG_CPU_V7M v7m_exception_entry #else sub sp, sp, #PT_REGS_SIZE stmia sp, {r0 - r12} @ Calling r0 - r12 +3: ARM( add r8, sp, #S_PC ) ARM( stmdb r8, {sp, lr}^ ) @ Calling sp, lr THUMB( mov r8, sp ) diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c index 7bd30c0a4280..22f937e6f3ff 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -154,22 +154,38 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr) return 0; } -static struct undef_hook kgdb_brkpt_hook = { +static struct undef_hook kgdb_brkpt_arm_hook = { .instr_mask = 0xffffffff, .instr_val = KGDB_BREAKINST, - .cpsr_mask = MODE_MASK, + .cpsr_mask = PSR_T_BIT | MODE_MASK, .cpsr_val = SVC_MODE, .fn = kgdb_brk_fn }; -static struct undef_hook kgdb_compiled_brkpt_hook = { +static struct undef_hook kgdb_brkpt_thumb_hook = { + .instr_mask = 0xffff, + .instr_val = KGDB_BREAKINST & 0xffff, + .cpsr_mask = PSR_T_BIT | MODE_MASK, + .cpsr_val = PSR_T_BIT | SVC_MODE, + .fn = kgdb_brk_fn +}; + +static struct undef_hook kgdb_compiled_brkpt_arm_hook = { .instr_mask = 0xffffffff, .instr_val = KGDB_COMPILED_BREAK, - .cpsr_mask = MODE_MASK, + .cpsr_mask = PSR_T_BIT | MODE_MASK, .cpsr_val = SVC_MODE, .fn = kgdb_compiled_brk_fn }; +static struct undef_hook kgdb_compiled_brkpt_thumb_hook = { + .instr_mask = 0xffff, + .instr_val = KGDB_COMPILED_BREAK & 0xffff, + .cpsr_mask = PSR_T_BIT | MODE_MASK, + .cpsr_val = PSR_T_BIT | SVC_MODE, + .fn = kgdb_compiled_brk_fn +}; + static int __kgdb_notify(struct die_args *args, unsigned long cmd) { struct pt_regs *regs = args->regs; @@ -210,8 +226,10 @@ int kgdb_arch_init(void) if (ret != 0) return ret; - register_undef_hook(&kgdb_brkpt_hook); - register_undef_hook(&kgdb_compiled_brkpt_hook); + register_undef_hook(&kgdb_brkpt_arm_hook); + register_undef_hook(&kgdb_brkpt_thumb_hook); + register_undef_hook(&kgdb_compiled_brkpt_arm_hook); + register_undef_hook(&kgdb_compiled_brkpt_thumb_hook); return 0; } @@ -224,8 +242,10 @@ int kgdb_arch_init(void) */ void kgdb_arch_exit(void) { - unregister_undef_hook(&kgdb_brkpt_hook); - unregister_undef_hook(&kgdb_compiled_brkpt_hook); + unregister_undef_hook(&kgdb_brkpt_arm_hook); + unregister_undef_hook(&kgdb_brkpt_thumb_hook); + unregister_undef_hook(&kgdb_compiled_brkpt_arm_hook); + unregister_undef_hook(&kgdb_compiled_brkpt_thumb_hook); unregister_die_notifier(&kgdb_notifier); } diff --git a/arch/arm/kernel/spectre.c b/arch/arm/kernel/spectre.c new file mode 100644 index 000000000000..0dcefc36fb7a --- /dev/null +++ b/arch/arm/kernel/spectre.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/bpf.h> +#include <linux/cpu.h> +#include <linux/device.h> + +#include <asm/spectre.h> + +static bool _unprivileged_ebpf_enabled(void) +{ +#ifdef CONFIG_BPF_SYSCALL + return !sysctl_unprivileged_bpf_disabled; +#else + return false; +#endif +} + +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); +} + +static unsigned int spectre_v2_state; +static unsigned int spectre_v2_methods; + +void spectre_v2_update_state(unsigned int state, unsigned int method) +{ + if (state > spectre_v2_state) + spectre_v2_state = state; + spectre_v2_methods |= method; +} + +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, + char *buf) +{ + const char *method; + + if (spectre_v2_state == SPECTRE_UNAFFECTED) + return sprintf(buf, "%s\n", "Not affected"); + + if (spectre_v2_state != SPECTRE_MITIGATED) + return sprintf(buf, "%s\n", "Vulnerable"); + + if (_unprivileged_ebpf_enabled()) + return sprintf(buf, "Vulnerable: Unprivileged eBPF enabled\n"); + + switch (spectre_v2_methods) { + case SPECTRE_V2_METHOD_BPIALL: + method = "Branch predictor hardening"; + break; + + case SPECTRE_V2_METHOD_ICIALLU: + method = "I-cache invalidation"; + break; + + case SPECTRE_V2_METHOD_SMC: + case SPECTRE_V2_METHOD_HVC: + method = "Firmware call"; + break; + + case SPECTRE_V2_METHOD_LOOP8: + method = "History overwrite"; + break; + + default: + method = "Multiple mitigations"; + break; + } + + return sprintf(buf, "Mitigation: %s\n", method); +} diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index da04ed85855a..cae4a748811f 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -30,6 +30,7 @@ #include <linux/atomic.h> #include <asm/cacheflush.h> #include <asm/exception.h> +#include <asm/spectre.h> #include <asm/unistd.h> #include <asm/traps.h> #include <asm/ptrace.h> @@ -789,10 +790,59 @@ static inline void __init kuser_init(void *vectors) } #endif +#ifndef CONFIG_CPU_V7M +static void copy_from_lma(void *vma, void *lma_start, void *lma_end) +{ + memcpy(vma, lma_start, lma_end - lma_start); +} + +static void flush_vectors(void *vma, size_t offset, size_t size) +{ + unsigned long start = (unsigned long)vma + offset; + unsigned long end = start + size; + + flush_icache_range(start, end); +} + +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +int spectre_bhb_update_vectors(unsigned int method) +{ + extern char __vectors_bhb_bpiall_start[], __vectors_bhb_bpiall_end[]; + extern char __vectors_bhb_loop8_start[], __vectors_bhb_loop8_end[]; + void *vec_start, *vec_end; + + if (system_state >= SYSTEM_FREEING_INITMEM) { + pr_err("CPU%u: Spectre BHB workaround too late - system vulnerable\n", + smp_processor_id()); + return SPECTRE_VULNERABLE; + } + + switch (method) { + case SPECTRE_V2_METHOD_LOOP8: + vec_start = __vectors_bhb_loop8_start; + vec_end = __vectors_bhb_loop8_end; + break; + + case SPECTRE_V2_METHOD_BPIALL: + vec_start = __vectors_bhb_bpiall_start; + vec_end = __vectors_bhb_bpiall_end; + break; + + default: + pr_err("CPU%u: unknown Spectre BHB state %d\n", + smp_processor_id(), method); + return SPECTRE_VULNERABLE; + } + + copy_from_lma(vectors_page, vec_start, vec_end); + flush_vectors(vectors_page, 0, vec_end - vec_start); + + return SPECTRE_MITIGATED; +} +#endif + void __init early_trap_init(void *vectors_base) { -#ifndef CONFIG_CPU_V7M - unsigned long vectors = (unsigned long)vectors_base; extern char __stubs_start[], __stubs_end[]; extern char __vectors_start[], __vectors_end[]; unsigned i; @@ -813,17 +863,20 @@ void __init early_trap_init(void *vectors_base) * into the vector page, mapped at 0xffff0000, and ensure these * are visible to the instruction stream. */ - memcpy((void *)vectors, __vectors_start, __vectors_end - __vectors_start); - memcpy((void *)vectors + 0x1000, __stubs_start, __stubs_end - __stubs_start); + copy_from_lma(vectors_base, __vectors_start, __vectors_end); + copy_from_lma(vectors_base + 0x1000, __stubs_start, __stubs_end); kuser_init(vectors_base); - flush_icache_range(vectors, vectors + PAGE_SIZE * 2); + flush_vectors(vectors_base, 0, PAGE_SIZE * 2); +} #else /* ifndef CONFIG_CPU_V7M */ +void __init early_trap_init(void *vectors_base) +{ /* * on V7-M there is no need to copy the vector table to a dedicated * memory area. The address is configurable and so a table in the kernel * image can be used. */ -#endif } +#endif diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c index 6daaa645ae5d..21413a9b7b6c 100644 --- a/arch/arm/mach-omap2/display.c +++ b/arch/arm/mach-omap2/display.c @@ -263,9 +263,9 @@ static int __init omapdss_init_of(void) } r = of_platform_populate(node, NULL, NULL, &pdev->dev); + put_device(&pdev->dev); if (r) { pr_err("Unable to populate DSS submodule devices\n"); - put_device(&pdev->dev); return r; } diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index ccb0e3732c0d..31d1a21f6041 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -752,8 +752,10 @@ static int __init _init_clkctrl_providers(void) for_each_matching_node(np, ti_clkctrl_match_table) { ret = _setup_clkctrl_provider(np); - if (ret) + if (ret) { + of_node_put(np); break; + } } return ret; diff --git a/arch/arm/mach-socfpga/Kconfig b/arch/arm/mach-socfpga/Kconfig index 43ddec677c0b..594edf9bbea4 100644 --- a/arch/arm/mach-socfpga/Kconfig +++ b/arch/arm/mach-socfpga/Kconfig @@ -2,6 +2,7 @@ menuconfig ARCH_INTEL_SOCFPGA bool "Altera SOCFPGA family" depends on ARCH_MULTI_V7 + select ARCH_HAS_RESET_CONTROLLER select ARCH_SUPPORTS_BIG_ENDIAN select ARM_AMBA select ARM_GIC @@ -18,6 +19,7 @@ menuconfig ARCH_INTEL_SOCFPGA select PL310_ERRATA_727915 select PL310_ERRATA_753970 if PL310 select PL310_ERRATA_769419 + select RESET_CONTROLLER if ARCH_INTEL_SOCFPGA config SOCFPGA_SUSPEND diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 58afba346729..9724c16e9076 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -830,6 +830,7 @@ config CPU_BPREDICT_DISABLE config CPU_SPECTRE bool + select GENERIC_CPU_VULNERABILITIES config HARDEN_BRANCH_PREDICTOR bool "Harden the branch predictor against aliasing attacks" if EXPERT @@ -850,6 +851,16 @@ config HARDEN_BRANCH_PREDICTOR If unsure, say Y. +config HARDEN_BRANCH_HISTORY + bool "Harden Spectre style attacks against branch history" if EXPERT + depends on CPU_SPECTRE + default y + help + Speculation attacks against some high-performance processors can + make use of branch history to influence future speculation. When + taking an exception, a sequence of branches overwrites the branch + history, or branch history is invalidated. + config TLS_REG_EMUL bool select NEED_KUSER_HELPERS diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 274e4f73fd33..5e2be37a198e 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -212,12 +212,14 @@ early_param("ecc", early_ecc); static int __init early_cachepolicy(char *p) { pr_warn("cachepolicy kernel parameter not supported without cp15\n"); + return 0; } early_param("cachepolicy", early_cachepolicy); static int __init noalign_setup(char *__unused) { pr_warn("noalign kernel parameter not supported without cp15\n"); + return 1; } __setup("noalign", noalign_setup); diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 114c05ab4dd9..c226feab2457 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -6,8 +6,35 @@ #include <asm/cp15.h> #include <asm/cputype.h> #include <asm/proc-fns.h> +#include <asm/spectre.h> #include <asm/system_misc.h> +#ifdef CONFIG_ARM_PSCI +static int __maybe_unused spectre_v2_get_cpu_fw_mitigation_state(void) +{ + struct arm_smccc_res res; + + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_1, &res); + + switch ((int)res.a0) { + case SMCCC_RET_SUCCESS: + return SPECTRE_MITIGATED; + + case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED: + return SPECTRE_UNAFFECTED; + + default: + return SPECTRE_VULNERABLE; + } +} +#else +static int __maybe_unused spectre_v2_get_cpu_fw_mitigation_state(void) +{ + return SPECTRE_VULNERABLE; +} +#endif + #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR DEFINE_PER_CPU(harden_branch_predictor_fn_t, harden_branch_predictor_fn); @@ -36,13 +63,60 @@ static void __maybe_unused call_hvc_arch_workaround_1(void) arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); } -static void cpu_v7_spectre_init(void) +static unsigned int spectre_v2_install_workaround(unsigned int method) { const char *spectre_v2_method = NULL; int cpu = smp_processor_id(); if (per_cpu(harden_branch_predictor_fn, cpu)) - return; + return SPECTRE_MITIGATED; + + switch (method) { + case SPECTRE_V2_METHOD_BPIALL: + per_cpu(harden_branch_predictor_fn, cpu) = + harden_branch_predictor_bpiall; + spectre_v2_method = "BPIALL"; + break; + + case SPECTRE_V2_METHOD_ICIALLU: + per_cpu(harden_branch_predictor_fn, cpu) = + harden_branch_predictor_iciallu; + spectre_v2_method = "ICIALLU"; + break; + + case SPECTRE_V2_METHOD_HVC: + per_cpu(harden_branch_predictor_fn, cpu) = + call_hvc_arch_workaround_1; + cpu_do_switch_mm = cpu_v7_hvc_switch_mm; + spectre_v2_method = "hypervisor"; + break; + + case SPECTRE_V2_METHOD_SMC: + per_cpu(harden_branch_predictor_fn, cpu) = + call_smc_arch_workaround_1; + cpu_do_switch_mm = cpu_v7_smc_switch_mm; + spectre_v2_method = "firmware"; + break; + } + + if (spectre_v2_method) + pr_info("CPU%u: Spectre v2: using %s workaround\n", + smp_processor_id(), spectre_v2_method); + + return SPECTRE_MITIGATED; +} +#else +static unsigned int spectre_v2_install_workaround(unsigned int method) +{ + pr_info("CPU%u: Spectre V2: workarounds disabled by configuration\n"); + + return SPECTRE_VULNERABLE; +} +#endif + +static void cpu_v7_spectre_v2_init(void) +{ + unsigned int state, method = 0; switch (read_cpuid_part()) { case ARM_CPU_PART_CORTEX_A8: @@ -51,69 +125,133 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A17: case ARM_CPU_PART_CORTEX_A73: case ARM_CPU_PART_CORTEX_A75: - per_cpu(harden_branch_predictor_fn, cpu) = - harden_branch_predictor_bpiall; - spectre_v2_method = "BPIALL"; + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_BPIALL; break; case ARM_CPU_PART_CORTEX_A15: case ARM_CPU_PART_BRAHMA_B15: - per_cpu(harden_branch_predictor_fn, cpu) = - harden_branch_predictor_iciallu; - spectre_v2_method = "ICIALLU"; + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_ICIALLU; break; -#ifdef CONFIG_ARM_PSCI case ARM_CPU_PART_BRAHMA_B53: /* Requires no workaround */ + state = SPECTRE_UNAFFECTED; break; + default: /* Other ARM CPUs require no workaround */ - if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) + if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) { + state = SPECTRE_UNAFFECTED; break; + } + fallthrough; - /* Cortex A57/A72 require firmware workaround */ - case ARM_CPU_PART_CORTEX_A57: - case ARM_CPU_PART_CORTEX_A72: { - struct arm_smccc_res res; - arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if ((int)res.a0 != 0) - return; + /* Cortex A57/A72 require firmware workaround */ + case ARM_CPU_PART_CORTEX_A57: + case ARM_CPU_PART_CORTEX_A72: + state = spectre_v2_get_cpu_fw_mitigation_state(); + if (state != SPECTRE_MITIGATED) + break; switch (arm_smccc_1_1_get_conduit()) { case SMCCC_CONDUIT_HVC: - per_cpu(harden_branch_predictor_fn, cpu) = - call_hvc_arch_workaround_1; - cpu_do_switch_mm = cpu_v7_hvc_switch_mm; - spectre_v2_method = "hypervisor"; + method = SPECTRE_V2_METHOD_HVC; break; case SMCCC_CONDUIT_SMC: - per_cpu(harden_branch_predictor_fn, cpu) = - call_smc_arch_workaround_1; - cpu_do_switch_mm = cpu_v7_smc_switch_mm; - spectre_v2_method = "firmware"; + method = SPECTRE_V2_METHOD_SMC; break; default: + state = SPECTRE_VULNERABLE; break; } } -#endif + + if (state == SPECTRE_MITIGATED) + state = spectre_v2_install_workaround(method); + + spectre_v2_update_state(state, method); +} + +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +static int spectre_bhb_method; + +static const char *spectre_bhb_method_name(int method) +{ + switch (method) { + case SPECTRE_V2_METHOD_LOOP8: + return "loop"; + + case SPECTRE_V2_METHOD_BPIALL: + return "BPIALL"; + + default: + return "unknown"; } +} - if (spectre_v2_method) - pr_info("CPU%u: Spectre v2: using %s workaround\n", - smp_processor_id(), spectre_v2_method); +static int spectre_bhb_install_workaround(int method) +{ + if (spectre_bhb_method != method) { + if (spectre_bhb_method) { + pr_err("CPU%u: Spectre BHB: method disagreement, system vulnerable\n", + smp_processor_id()); + + return SPECTRE_VULNERABLE; + } + + if (spectre_bhb_update_vectors(method) == SPECTRE_VULNERABLE) + return SPECTRE_VULNERABLE; + + spectre_bhb_method = method; + } + + pr_info("CPU%u: Spectre BHB: using %s workaround\n", + smp_processor_id(), spectre_bhb_method_name(method)); + + return SPECTRE_MITIGATED; } #else -static void cpu_v7_spectre_init(void) +static int spectre_bhb_install_workaround(int method) { + return SPECTRE_VULNERABLE; } #endif +static void cpu_v7_spectre_bhb_init(void) +{ + unsigned int state, method = 0; + + switch (read_cpuid_part()) { + case ARM_CPU_PART_CORTEX_A15: + case ARM_CPU_PART_BRAHMA_B15: + case ARM_CPU_PART_CORTEX_A57: + case ARM_CPU_PART_CORTEX_A72: + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_LOOP8; + break; + + case ARM_CPU_PART_CORTEX_A73: + case ARM_CPU_PART_CORTEX_A75: + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_BPIALL; + break; + + default: + state = SPECTRE_UNAFFECTED; + break; + } + + if (state == SPECTRE_MITIGATED) + state = spectre_bhb_install_workaround(method); + + spectre_v2_update_state(state, method); +} + static __maybe_unused bool cpu_v7_check_auxcr_set(bool *warned, u32 mask, const char *msg) { @@ -142,16 +280,17 @@ static bool check_spectre_auxcr(bool *warned, u32 bit) void cpu_v7_ca8_ibe(void) { if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(6))) - cpu_v7_spectre_init(); + cpu_v7_spectre_v2_init(); } void cpu_v7_ca15_ibe(void) { if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(0))) - cpu_v7_spectre_init(); + cpu_v7_spectre_v2_init(); } void cpu_v7_bugs_init(void) { - cpu_v7_spectre_init(); + cpu_v7_spectre_v2_init(); + cpu_v7_spectre_bhb_init(); } diff --git a/arch/arm/probes/kprobes/Makefile b/arch/arm/probes/kprobes/Makefile index 14db56f49f0a..6159010dac4a 100644 --- a/arch/arm/probes/kprobes/Makefile +++ b/arch/arm/probes/kprobes/Makefile @@ -1,4 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +KASAN_SANITIZE_actions-common.o := n +KASAN_SANITIZE_actions-arm.o := n +KASAN_SANITIZE_actions-thumb.o := n obj-$(CONFIG_KPROBES) += core.o actions-common.o checkers-common.o obj-$(CONFIG_ARM_KPROBES_TEST) += test-kprobes.o test-kprobes-objs := test-core.o diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6978140edfa4..c842878f8133 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -670,15 +670,42 @@ config ARM64_ERRATUM_1508412 config ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE bool +config ARM64_ERRATUM_2051678 + bool "Cortex-A510: 2051678: disable Hardware Update of the page table dirty bit" + default y + help + This options adds the workaround for ARM Cortex-A510 erratum ARM64_ERRATUM_2051678. + Affected Coretex-A510 might not respect the ordering rules for + hardware update of the page table's dirty bit. The workaround + is to not enable the feature on affected CPUs. + + If unsure, say Y. + +config ARM64_ERRATUM_2077057 + bool "Cortex-A510: 2077057: workaround software-step corrupting SPSR_EL2" + help + This option adds the workaround for ARM Cortex-A510 erratum 2077057. + Affected Cortex-A510 may corrupt SPSR_EL2 when the a step exception is + expected, but a Pointer Authentication trap is taken instead. The + erratum causes SPSR_EL1 to be copied to SPSR_EL2, which could allow + EL1 to cause a return to EL2 with a guest controlled ELR_EL2. + + This can only happen when EL2 is stepping EL1. + + When these conditions occur, the SPSR_EL2 value is unchanged from the + previous guest entry, and can be restored from the in-memory copy. + + If unsure, say Y. + config ARM64_ERRATUM_2119858 - bool "Cortex-A710: 2119858: workaround TRBE overwriting trace data in FILL mode" + bool "Cortex-A710/X2: 2119858: workaround TRBE overwriting trace data in FILL mode" default y depends on CORESIGHT_TRBE select ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE help - This option adds the workaround for ARM Cortex-A710 erratum 2119858. + This option adds the workaround for ARM Cortex-A710/X2 erratum 2119858. - Affected Cortex-A710 cores could overwrite up to 3 cache lines of trace + Affected Cortex-A710/X2 cores could overwrite up to 3 cache lines of trace data at the base of the buffer (pointed to by TRBASER_EL1) in FILL mode in the event of a WRAP event. @@ -761,14 +788,14 @@ config ARM64_ERRATUM_2253138 If unsure, say Y. config ARM64_ERRATUM_2224489 - bool "Cortex-A710: 2224489: workaround TRBE writing to address out-of-range" + bool "Cortex-A710/X2: 2224489: workaround TRBE writing to address out-of-range" depends on CORESIGHT_TRBE default y select ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE help - This option adds the workaround for ARM Cortex-A710 erratum 2224489. + This option adds the workaround for ARM Cortex-A710/X2 erratum 2224489. - Affected Cortex-A710 cores might write to an out-of-range address, not reserved + Affected Cortex-A710/X2 cores might write to an out-of-range address, not reserved for TRBE. Under some conditions, the TRBE might generate a write to the next virtually addressed page following the last page of the TRBE address space (i.e., the TRBLIMITR_EL1.LIMIT), instead of wrapping around to the base. @@ -778,6 +805,65 @@ config ARM64_ERRATUM_2224489 If unsure, say Y. +config ARM64_ERRATUM_2064142 + bool "Cortex-A510: 2064142: workaround TRBE register writes while disabled" + depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in + default y + help + This option adds the workaround for ARM Cortex-A510 erratum 2064142. + + Affected Cortex-A510 core might fail to write into system registers after the + TRBE has been disabled. Under some conditions after the TRBE has been disabled + writes into TRBE registers TRBLIMITR_EL1, TRBPTR_EL1, TRBBASER_EL1, TRBSR_EL1, + and TRBTRG_EL1 will be ignored and will not be effected. + + Work around this in the driver by executing TSB CSYNC and DSB after collection + is stopped and before performing a system register write to one of the affected + registers. + + If unsure, say Y. + +config ARM64_ERRATUM_2038923 + bool "Cortex-A510: 2038923: workaround TRBE corruption with enable" + depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in + default y + help + This option adds the workaround for ARM Cortex-A510 erratum 2038923. + + Affected Cortex-A510 core might cause an inconsistent view on whether trace is + prohibited within the CPU. As a result, the trace buffer or trace buffer state + might be corrupted. This happens after TRBE buffer has been enabled by setting + TRBLIMITR_EL1.E, followed by just a single context synchronization event before + execution changes from a context, in which trace is prohibited to one where it + isn't, or vice versa. In these mentioned conditions, the view of whether trace + is prohibited is inconsistent between parts of the CPU, and the trace buffer or + the trace buffer state might be corrupted. + + Work around this in the driver by preventing an inconsistent view of whether the + trace is prohibited or not based on TRBLIMITR_EL1.E by immediately following a + change to TRBLIMITR_EL1.E with at least one ISB instruction before an ERET, or + two ISB instructions if no ERET is to take place. + + If unsure, say Y. + +config ARM64_ERRATUM_1902691 + bool "Cortex-A510: 1902691: workaround TRBE trace corruption" + depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in + default y + help + This option adds the workaround for ARM Cortex-A510 erratum 1902691. + + Affected Cortex-A510 core might cause trace data corruption, when being written + into the memory. Effectively TRBE is broken and hence cannot be used to capture + trace data. + + Work around this problem in the driver by just preventing TRBE initialization on + affected cpus. The firmware must have disabled the access to TRBE for the kernel + on such implementations. This will cover the kernel for any firmware that doesn't + do this already. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y @@ -1166,9 +1252,6 @@ config HW_PERF_EVENTS def_bool y depends on ARM_PMU -config ARCH_HAS_FILTER_PGPROT - def_bool y - # Supported by clang >= 7.0 config CC_HAVE_SHADOW_CALL_STACK def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18) @@ -1297,6 +1380,15 @@ config UNMAP_KERNEL_AT_EL0 If unsure, say Y. +config MITIGATE_SPECTRE_BRANCH_HISTORY + bool "Mitigate Spectre style attacks against branch history" if EXPERT + default y + help + Speculation attacks against some high-performance processors can + make use of branch history to influence future speculation. + When taking an exception from user-space, a sequence of branches + or a firmware call overwrites the branch history. + config RODATA_FULL_DEFAULT_ENABLED bool "Apply r/o permissions of VM areas also to their linear aliases" default y diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 7d5d58800170..21697449d762 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -309,9 +309,6 @@ config ARCH_VISCONTI help This enables support for Toshiba Visconti SoCs Family. -config ARCH_VULCAN - def_bool n - config ARCH_XGENE bool "AppliedMicro X-Gene SOC Family" help diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index 517519e6e87f..f84d4b489e0b 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -107,6 +107,12 @@ no-map; }; + /* 32 MiB reserved for ARM Trusted Firmware (BL32) */ + secmon_reserved_bl32: secmon@5300000 { + reg = <0x0 0x05300000 0x0 0x2000000>; + no-map; + }; + linux,cma { compatible = "shared-dma-pool"; reusable; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts index d8838dde0f0f..4fb31c2ba31c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts +++ b/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts @@ -157,14 +157,6 @@ regulator-always-on; }; - reserved-memory { - /* TEE Reserved Memory */ - bl32_reserved: bl32@5000000 { - reg = <0x0 0x05300000 0x0 0x2000000>; - no-map; - }; - }; - sdio_pwrseq: sdio-pwrseq { compatible = "mmc-pwrseq-simple"; reset-gpios = <&gpio GPIOX_6 GPIO_ACTIVE_LOW>; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dtsi index 3e968b244191..fd3fa82e4c33 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dtsi @@ -17,7 +17,7 @@ rtc1 = &vrtc; }; - dioo2133: audio-amplifier-0 { + dio2133: audio-amplifier-0 { compatible = "simple-audio-amplifier"; enable-gpios = <&gpio_ao GPIOAO_2 GPIO_ACTIVE_HIGH>; VCC-supply = <&vcc_5v>; @@ -219,7 +219,7 @@ audio-widgets = "Line", "Lineout"; audio-aux-devs = <&tdmout_b>, <&tdmout_c>, <&tdmin_a>, <&tdmin_b>, <&tdmin_c>, <&tdmin_lb>, - <&dioo2133>; + <&dio2133>; audio-routing = "TDMOUT_B IN 0", "FRDDR_A OUT 1", "TDMOUT_B IN 1", "FRDDR_B OUT 1", "TDMOUT_B IN 2", "FRDDR_C OUT 1", diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 6b457b2c30a4..aa14ea017a61 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -49,6 +49,12 @@ no-map; }; + /* 32 MiB reserved for ARM Trusted Firmware (BL32) */ + secmon_reserved_bl32: secmon@5300000 { + reg = <0x0 0x05300000 0x0 0x2000000>; + no-map; + }; + linux,cma { compatible = "shared-dma-pool"; reusable; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts index 212c6aa5a3b8..5751c48620ed 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts @@ -123,7 +123,7 @@ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; - enable-gpio = <&gpio GPIOE_2 GPIO_ACTIVE_HIGH>; + enable-gpio = <&gpio_ao GPIOE_2 GPIO_ACTIVE_HIGH>; enable-active-high; regulator-always-on; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi index 0bd1e98a0eef..ddb1b345397f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi @@ -48,7 +48,7 @@ regulator-max-microvolt = <3300000>; vin-supply = <&vcc_5v>; - enable-gpio = <&gpio GPIOE_2 GPIO_ACTIVE_HIGH>; + enable-gpio = <&gpio_ao GPIOE_2 GPIO_OPEN_DRAIN>; enable-active-high; regulator-always-on; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts index 427475846fc7..a5d79f2f7c19 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts @@ -203,14 +203,6 @@ regulator-always-on; }; - reserved-memory { - /* TEE Reserved Memory */ - bl32_reserved: bl32@5000000 { - reg = <0x0 0x05300000 0x0 0x2000000>; - no-map; - }; - }; - sdio_pwrseq: sdio-pwrseq { compatible = "mmc-pwrseq-simple"; reset-gpios = <&gpio GPIOX_6 GPIO_ACTIVE_LOW>; diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 6288e104a089..a2635b14da30 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -543,8 +543,7 @@ <0x02000000 0x00 0x50000000 0x00 0x50000000 0x0 0x08000000>, <0x42000000 0x40 0x00000000 0x40 0x00000000 0x1 0x00000000>; /* Standard AXI Translation entries as programmed by EDK2 */ - dma-ranges = <0x02000000 0x0 0x2c1c0000 0x0 0x2c1c0000 0x0 0x00040000>, - <0x02000000 0x0 0x80000000 0x0 0x80000000 0x0 0x80000000>, + dma-ranges = <0x02000000 0x0 0x80000000 0x0 0x80000000 0x0 0x80000000>, <0x43000000 0x8 0x00000000 0x8 0x00000000 0x2 0x00000000>; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 7>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts index d74e738e4070..c03f4e183389 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts @@ -157,6 +157,10 @@ }; }; +&ftm_alarm0 { + status = "okay"; +}; + &gpio1 { gpio-line-names = "", "", "", "", "", "", "", "", diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index f77f90ed416f..0c7a72c51a31 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -707,7 +707,6 @@ clocks = <&clk IMX8MM_CLK_VPU_DEC_ROOT>; assigned-clocks = <&clk IMX8MM_CLK_VPU_BUS>; assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_800M>; - resets = <&src IMX8MQ_RESET_VPU_RESET>; }; pgc_vpu_g1: power-domain@7 { diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi index f3e3418f7edc..2d4a472af6a9 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi @@ -1115,8 +1115,8 @@ status = "okay"; ports { - port@1 { - reg = <1>; + port@0 { + reg = <0>; mipi1_sensor_ep: endpoint { remote-endpoint = <&camera1_ep>; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 2df2510d0118..e92ebb6147e6 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -554,7 +554,7 @@ assigned-clock-rates = <0>, <0>, <0>, <594000000>; status = "disabled"; - port@0 { + port { lcdif_mipi_dsi: endpoint { remote-endpoint = <&mipi_dsi_lcdif_in>; }; @@ -1151,8 +1151,8 @@ #address-cells = <1>; #size-cells = <0>; - port@0 { - reg = <0>; + port@1 { + reg = <1>; csi1_mipi_ep: endpoint { remote-endpoint = <&csi1_ep>; @@ -1203,8 +1203,8 @@ #address-cells = <1>; #size-cells = <0>; - port@0 { - reg = <0>; + port@1 { + reg = <1>; csi2_mipi_ep: endpoint { remote-endpoint = <&csi2_ep>; diff --git a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi index a987ff7156bd..09f7364dd1d0 100644 --- a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi @@ -132,7 +132,7 @@ scmi_sensor: protocol@15 { reg = <0x15>; - #thermal-sensor-cells = <0>; + #thermal-sensor-cells = <1>; }; }; }; diff --git a/arch/arm64/boot/dts/freescale/mba8mx.dtsi b/arch/arm64/boot/dts/freescale/mba8mx.dtsi index f27e3c8de916..ce6d5bdba0a8 100644 --- a/arch/arm64/boot/dts/freescale/mba8mx.dtsi +++ b/arch/arm64/boot/dts/freescale/mba8mx.dtsi @@ -91,7 +91,7 @@ sound { compatible = "fsl,imx-audio-tlv320aic32x4"; - model = "tqm-tlv320aic32"; + model = "imx-audio-tlv320aic32x4"; ssi-controller = <&sai3>; audio-codec = <&tlv320aic3x04>; }; diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi index 0dd2d2ee765a..f4270cf18996 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi +++ b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi @@ -502,7 +502,7 @@ }; usb0: usb@ffb00000 { - compatible = "snps,dwc2"; + compatible = "intel,socfpga-agilex-hsotg", "snps,dwc2"; reg = <0xffb00000 0x40000>; interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy0>; @@ -515,7 +515,7 @@ }; usb1: usb@ffb40000 { - compatible = "snps,dwc2"; + compatible = "intel,socfpga-agilex-hsotg", "snps,dwc2"; reg = <0xffb40000 0x40000>; interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy0>; diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi index f972704dfe7a..56dfbb2e2fa6 100644 --- a/arch/arm64/boot/dts/rockchip/px30.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30.dtsi @@ -711,7 +711,7 @@ clock-names = "pclk", "timer"; }; - dmac: dmac@ff240000 { + dmac: dma-controller@ff240000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x0 0xff240000 0x0 0x4000>; interrupts = <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 39db0b85b4da..b822533dc7f1 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -489,7 +489,7 @@ status = "disabled"; }; - dmac: dmac@ff1f0000 { + dmac: dma-controller@ff1f0000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x0 0xff1f0000 0x0 0x4000>; interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi index 45a5ae5d2027..162f08bca0d4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi @@ -286,7 +286,7 @@ sound: sound { compatible = "rockchip,rk3399-gru-sound"; - rockchip,cpu = <&i2s0 &i2s2>; + rockchip,cpu = <&i2s0 &spdif>; }; }; @@ -437,10 +437,6 @@ ap_i2c_audio: &i2c8 { status = "okay"; }; -&i2s2 { - status = "okay"; -}; - &io_domains { status = "okay"; @@ -537,6 +533,17 @@ ap_i2c_audio: &i2c8 { vqmmc-supply = <&ppvar_sd_card_io>; }; +&spdif { + status = "okay"; + + /* + * SPDIF is routed internally to DP; we either don't use these pins, or + * mux them to something else. + */ + /delete-property/ pinctrl-0; + /delete-property/ pinctrl-names; +}; + &spi1 { status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts index 292bb7e80cf3..3ae5d727e367 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts @@ -232,6 +232,7 @@ &usbdrd_dwc3_0 { dr_mode = "otg"; + extcon = <&extcon_usb3>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index fb67db4619ea..08fa00364b42 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -25,6 +25,13 @@ }; }; + extcon_usb3: extcon-usb3 { + compatible = "linux,extcon-usb-gpio"; + id-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&usb3_id>; + }; + clkin_gmac: external-gmac-clock { compatible = "fixed-clock"; clock-frequency = <125000000>; @@ -422,9 +429,22 @@ <4 RK_PA3 RK_FUNC_GPIO &pcfg_pull_none>; }; }; + + usb3 { + usb3_id: usb3-id { + rockchip,pins = + <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; }; &sdhci { + /* + * Signal integrity isn't great at 200MHz but 100MHz has proven stable + * enough. + */ + max-frequency = <100000000>; + bus-width = <8>; mmc-hs400-1_8v; mmc-hs400-enhanced-strobe; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index d3cdf6f42a30..080457a68e3c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1881,10 +1881,10 @@ interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH 0>; clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_SFR>, - <&cru PLL_VPLL>, + <&cru SCLK_HDMI_CEC>, <&cru PCLK_VIO_GRF>, - <&cru SCLK_HDMI_CEC>; - clock-names = "iahb", "isfr", "vpll", "grf", "cec"; + <&cru PLL_VPLL>; + clock-names = "iahb", "isfr", "cec", "grf", "vpll"; power-domains = <&power RK3399_PD_HDCP>; reg-io-width = <4>; rockchip,grf = <&grf>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts index 166399b7f13f..d9eb92d59099 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts @@ -285,8 +285,6 @@ vcc_ddr: DCDC_REG3 { regulator-always-on; regulator-boot-on; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1100000>; regulator-initial-mode = <0x2>; regulator-name = "vcc_ddr"; regulator-state-mem { diff --git a/arch/arm64/boot/dts/rockchip/rk3568.dtsi b/arch/arm64/boot/dts/rockchip/rk3568.dtsi index 2fd313a295f8..d91df1cde736 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3568.dtsi @@ -32,13 +32,11 @@ clocks = <&cru SCLK_GMAC0>, <&cru SCLK_GMAC0_RX_TX>, <&cru SCLK_GMAC0_RX_TX>, <&cru CLK_MAC0_REFOUT>, <&cru ACLK_GMAC0>, <&cru PCLK_GMAC0>, - <&cru SCLK_GMAC0_RX_TX>, <&cru CLK_GMAC0_PTP_REF>, - <&cru PCLK_XPCS>; + <&cru SCLK_GMAC0_RX_TX>, <&cru CLK_GMAC0_PTP_REF>; clock-names = "stmmaceth", "mac_clk_rx", "mac_clk_tx", "clk_mac_refout", "aclk_mac", "pclk_mac", - "clk_mac_speed", "ptp_ref", - "pclk_xpcs"; + "clk_mac_speed", "ptp_ref"; resets = <&cru SRST_A_GMAC0>; reset-names = "stmmaceth"; rockchip,grf = <&grf>; diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi index a68033a23975..8ccce54ee8e7 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi @@ -651,7 +651,7 @@ status = "disabled"; }; - dmac0: dmac@fe530000 { + dmac0: dma-controller@fe530000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x0 0xfe530000 0x0 0x4000>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>, @@ -662,7 +662,7 @@ #dma-cells = <1>; }; - dmac1: dmac@fe550000 { + dmac1: dma-controller@fe550000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x0 0xfe550000 0x0 0x4000>; interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts index a5a24f9f46c5..b210cc07c539 100644 --- a/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts @@ -15,8 +15,18 @@ model = "Texas Instruments J721S2 EVM"; chosen { - stdout-path = "serial10:115200n8"; - bootargs = "console=ttyS10,115200n8 earlycon=ns16550a,mmio32,2880000"; + stdout-path = "serial2:115200n8"; + bootargs = "console=ttyS2,115200n8 earlycon=ns16550a,mmio32,2880000"; + }; + + aliases { + serial1 = &mcu_uart0; + serial2 = &main_uart8; + mmc0 = &main_sdhci0; + mmc1 = &main_sdhci1; + can0 = &main_mcan16; + can1 = &mcu_mcan0; + can2 = &mcu_mcan1; }; evm_12v0: fixedregulator-evm12v0 { diff --git a/arch/arm64/boot/dts/ti/k3-j721s2.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2.dtsi index 80d3cae03e88..fe5234c40f6c 100644 --- a/arch/arm64/boot/dts/ti/k3-j721s2.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721s2.dtsi @@ -21,28 +21,6 @@ #address-cells = <2>; #size-cells = <2>; - aliases { - serial0 = &wkup_uart0; - serial1 = &mcu_uart0; - serial2 = &main_uart0; - serial3 = &main_uart1; - serial4 = &main_uart2; - serial5 = &main_uart3; - serial6 = &main_uart4; - serial7 = &main_uart5; - serial8 = &main_uart6; - serial9 = &main_uart7; - serial10 = &main_uart8; - serial11 = &main_uart9; - mmc0 = &main_sdhci0; - mmc1 = &main_sdhci1; - can0 = &main_mcan16; - can1 = &mcu_mcan0; - can2 = &mcu_mcan1; - can3 = &main_mcan3; - can4 = &main_mcan5; - }; - chosen { }; cpus { diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index e8bd0af0141c..6ebdc0f834a7 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -109,6 +109,13 @@ .endm /* + * Clear Branch History instruction + */ + .macro clearbhb + hint #22 + .endm + +/* * Speculation barrier */ .macro sb @@ -850,4 +857,50 @@ alternative_endif #endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */ + .macro __mitigate_spectre_bhb_loop tmp +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb spectre_bhb_patch_loop_iter + mov \tmp, #32 // Patched to correct the immediate +alternative_cb_end +.Lspectre_bhb_loop\@: + b . + 4 + subs \tmp, \tmp, #1 + b.ne .Lspectre_bhb_loop\@ + sb +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + .macro mitigate_spectre_bhb_loop tmp +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb spectre_bhb_patch_loop_mitigation_enable + b .L_spectre_bhb_loop_done\@ // Patched to NOP +alternative_cb_end + __mitigate_spectre_bhb_loop \tmp +.L_spectre_bhb_loop_done\@: +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + /* Save/restores x0-x3 to the stack */ + .macro __mitigate_spectre_bhb_fw +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + stp x0, x1, [sp, #-16]! + stp x2, x3, [sp, #-16]! + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_3 +alternative_cb smccc_patch_fw_mitigation_conduit + nop // Patched to SMC/HVC #0 +alternative_cb_end + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + .macro mitigate_spectre_bhb_clear_insn +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb spectre_bhb_patch_clearbhb + /* Patched to NOP when not supported */ + clearbhb + isb +alternative_cb_end +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index ef6be92b1921..a77b5f49b3a6 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -637,6 +637,35 @@ static inline bool cpu_supports_mixed_endian_el0(void) return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1)); } + +static inline bool supports_csv2p3(int scope) +{ + u64 pfr0; + u8 csv2_val; + + if (scope == SCOPE_LOCAL_CPU) + pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1); + else + pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + + csv2_val = cpuid_feature_extract_unsigned_field(pfr0, + ID_AA64PFR0_CSV2_SHIFT); + return csv2_val == 3; +} + +static inline bool supports_clearbhb(int scope) +{ + u64 isar2; + + if (scope == SCOPE_LOCAL_CPU) + isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); + else + isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); + + return cpuid_feature_extract_unsigned_field(isar2, + ID_AA64ISAR2_CLEARBHB_SHIFT); +} + const struct cpumask *system_32bit_el0_cpumask(void); DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0); diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 19b8441aa8f2..bfbf0c4c7c5e 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -73,8 +73,14 @@ #define ARM_CPU_PART_CORTEX_A76 0xD0B #define ARM_CPU_PART_NEOVERSE_N1 0xD0C #define ARM_CPU_PART_CORTEX_A77 0xD0D +#define ARM_CPU_PART_NEOVERSE_V1 0xD40 +#define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_X1 0xD44 +#define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 +#define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 +#define ARM_CPU_PART_CORTEX_A78C 0xD4B #define APM_CPU_PART_POTENZA 0x000 @@ -115,8 +121,14 @@ #define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76) #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1) #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) +#define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) +#define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) +#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) +#define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) +#define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 3198acb2aad8..7f3c87f7a0ce 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -106,7 +106,7 @@ msr_s SYS_ICC_SRE_EL2, x0 isb // Make sure SRE is now set mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, - tbz x0, #0, 1f // and check that it sticks + tbz x0, #0, .Lskip_gicv3_\@ // and check that it sticks msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults .Lskip_gicv3_\@: .endm diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index 4335800201c9..daff882883f9 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -62,9 +62,11 @@ enum fixed_addresses { #endif /* CONFIG_ACPI_APEI_GHES */ #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 + FIX_ENTRY_TRAMP_TEXT3, + FIX_ENTRY_TRAMP_TEXT2, + FIX_ENTRY_TRAMP_TEXT1, FIX_ENTRY_TRAMP_DATA, - FIX_ENTRY_TRAMP_TEXT, -#define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT)) +#define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT1)) #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ __end_of_permanent_fixed_addresses, diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 6b776c8667b2..b02f0c328c8e 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -65,6 +65,7 @@ enum aarch64_insn_hint_cr_op { AARCH64_INSN_HINT_PSB = 0x11 << 5, AARCH64_INSN_HINT_TSB = 0x12 << 5, AARCH64_INSN_HINT_CSDB = 0x14 << 5, + AARCH64_INSN_HINT_CLEARBHB = 0x16 << 5, AARCH64_INSN_HINT_BTI = 0x20 << 5, AARCH64_INSN_HINT_BTIC = 0x22 << 5, diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 5bc01e62c08a..031e3a2537fc 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -714,6 +714,11 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr(); } +static inline bool kvm_system_needs_idmapped_vectors(void) +{ + return cpus_have_const_cap(ARM64_SPECTRE_V3A); +} + void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu); static inline void kvm_arch_hardware_unsetup(void) {} diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h index e4704a403237..a857bcacf0fe 100644 --- a/arch/arm64/include/asm/mte-kasan.h +++ b/arch/arm64/include/asm/mte-kasan.h @@ -5,6 +5,7 @@ #ifndef __ASM_MTE_KASAN_H #define __ASM_MTE_KASAN_H +#include <asm/compiler.h> #include <asm/mte-def.h> #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 7032f04c8ac6..b1e1b74d993c 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -92,7 +92,7 @@ extern bool arm64_use_ng_mappings; #define __P001 PAGE_READONLY #define __P010 PAGE_READONLY #define __P011 PAGE_READONLY -#define __P100 PAGE_EXECONLY +#define __P100 PAGE_READONLY_EXEC /* PAGE_EXECONLY if Enhanced PAN */ #define __P101 PAGE_READONLY_EXEC #define __P110 PAGE_READONLY_EXEC #define __P111 PAGE_READONLY_EXEC @@ -101,7 +101,7 @@ extern bool arm64_use_ng_mappings; #define __S001 PAGE_READONLY #define __S010 PAGE_SHARED #define __S011 PAGE_SHARED -#define __S100 PAGE_EXECONLY +#define __S100 PAGE_READONLY_EXEC /* PAGE_EXECONLY if Enhanced PAN */ #define __S101 PAGE_READONLY_EXEC #define __S110 PAGE_SHARED_EXEC #define __S111 PAGE_SHARED_EXEC diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index c4ba047a82d2..94e147e5456c 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1017,17 +1017,6 @@ static inline bool arch_wants_old_prefaulted_pte(void) } #define arch_wants_old_prefaulted_pte arch_wants_old_prefaulted_pte -static inline pgprot_t arch_filter_pgprot(pgprot_t prot) -{ - if (cpus_have_const_cap(ARM64_HAS_EPAN)) - return prot; - - if (pgprot_val(prot) != pgprot_val(PAGE_EXECONLY)) - return prot; - - return PAGE_READONLY_EXEC; -} - static inline bool pud_sect_supported(void) { return PAGE_SIZE == SZ_4K; diff --git a/arch/arm64/include/asm/rwonce.h b/arch/arm64/include/asm/rwonce.h index 1bce62fa908a..56f7b1d4d54b 100644 --- a/arch/arm64/include/asm/rwonce.h +++ b/arch/arm64/include/asm/rwonce.h @@ -5,7 +5,7 @@ #ifndef __ASM_RWONCE_H #define __ASM_RWONCE_H -#ifdef CONFIG_LTO +#if defined(CONFIG_LTO) && !defined(__ASSEMBLY__) #include <linux/compiler_types.h> #include <asm/alternative-macros.h> @@ -66,7 +66,7 @@ }) #endif /* !BUILD_VDSO */ -#endif /* CONFIG_LTO */ +#endif /* CONFIG_LTO && !__ASSEMBLY__ */ #include <asm-generic/rwonce.h> diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h index 152cb35bf9df..40971ac1303f 100644 --- a/arch/arm64/include/asm/sections.h +++ b/arch/arm64/include/asm/sections.h @@ -23,4 +23,9 @@ extern char __mmuoff_data_start[], __mmuoff_data_end[]; extern char __entry_tramp_text_start[], __entry_tramp_text_end[]; extern char __relocate_new_kernel_start[], __relocate_new_kernel_end[]; +static inline size_t entry_tramp_text_size(void) +{ + return __entry_tramp_text_end - __entry_tramp_text_start; +} + #endif /* __ASM_SECTIONS_H */ diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h index f62ca39da6c5..86e0cc9b9c68 100644 --- a/arch/arm64/include/asm/spectre.h +++ b/arch/arm64/include/asm/spectre.h @@ -93,5 +93,9 @@ void spectre_v4_enable_task_mitigation(struct task_struct *tsk); enum mitigation_state arm64_get_meltdown_state(void); +enum mitigation_state arm64_get_spectre_bhb_state(void); +bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope); +u8 spectre_bhb_loop_affected(int scope); +void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused); #endif /* __ASSEMBLY__ */ #endif /* __ASM_SPECTRE_H */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 898bee0004ae..932d45b17877 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -773,6 +773,7 @@ #define ID_AA64ISAR1_GPI_IMP_DEF 0x1 /* id_aa64isar2 */ +#define ID_AA64ISAR2_CLEARBHB_SHIFT 28 #define ID_AA64ISAR2_RPRES_SHIFT 4 #define ID_AA64ISAR2_WFXT_SHIFT 0 @@ -904,6 +905,7 @@ #endif /* id_aa64mmfr1 */ +#define ID_AA64MMFR1_ECBHB_SHIFT 60 #define ID_AA64MMFR1_AFP_SHIFT 44 #define ID_AA64MMFR1_ETS_SHIFT 36 #define ID_AA64MMFR1_TWED_SHIFT 32 diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h new file mode 100644 index 000000000000..f64613a96d53 --- /dev/null +++ b/arch/arm64/include/asm/vectors.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 ARM Ltd. + */ +#ifndef __ASM_VECTORS_H +#define __ASM_VECTORS_H + +#include <linux/bug.h> +#include <linux/percpu.h> + +#include <asm/fixmap.h> + +extern char vectors[]; +extern char tramp_vectors[]; +extern char __bp_harden_el1_vectors[]; + +/* + * Note: the order of this enum corresponds to two arrays in entry.S: + * tramp_vecs and __bp_harden_el1_vectors. By default the canonical + * 'full fat' vectors are used directly. + */ +enum arm64_bp_harden_el1_vectors { +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + /* + * Perform the BHB loop mitigation, before branching to the canonical + * vectors. + */ + EL1_VECTOR_BHB_LOOP, + + /* + * Make the SMC call for firmware mitigation, before branching to the + * canonical vectors. + */ + EL1_VECTOR_BHB_FW, + + /* + * Use the ClearBHB instruction, before branching to the canonical + * vectors. + */ + EL1_VECTOR_BHB_CLEAR_INSN, +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + + /* + * Remap the kernel before branching to the canonical vectors. + */ + EL1_VECTOR_KPTI, +}; + +#ifndef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +#define EL1_VECTOR_BHB_LOOP -1 +#define EL1_VECTOR_BHB_FW -1 +#define EL1_VECTOR_BHB_CLEAR_INSN -1 +#endif /* !CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + +/* The vectors to use on return from EL0. e.g. to remap the kernel */ +DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector); + +#ifndef CONFIG_UNMAP_KERNEL_AT_EL0 +#define TRAMP_VALIAS 0 +#endif + +static inline const char * +arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot) +{ + if (arm64_kernel_unmapped_at_el0()) + return (char *)TRAMP_VALIAS + SZ_2K * slot; + + WARN_ON_ONCE(slot == EL1_VECTOR_KPTI); + + return __bp_harden_el1_vectors + SZ_2K * slot; +} + +#endif /* __ASM_VECTORS_H */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index b3edde68bc3e..323e251ed37b 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -281,6 +281,11 @@ struct kvm_arm_copy_mte_tags { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 KVM_REG_ARM_FW_REG(3) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED 2 + /* SVE registers */ #define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 9e1c1aef9ebd..a401180e8d66 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -347,6 +347,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { #endif #ifdef CONFIG_ARM64_ERRATUM_2119858 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_RANGE(MIDR_CORTEX_X2, 0, 0, 2, 0), #endif {}, }; @@ -371,6 +372,7 @@ static struct midr_range trbe_write_out_of_range_cpus[] = { #endif #ifdef CONFIG_ARM64_ERRATUM_2224489 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_RANGE(MIDR_CORTEX_X2, 0, 0, 2, 0), #endif {}, }; @@ -500,6 +502,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .matches = has_spectre_v4, .cpu_enable = spectre_v4_enable_mitigation, }, + { + .desc = "Spectre-BHB", + .capability = ARM64_SPECTRE_BHB, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = is_spectre_bhb_affected, + .cpu_enable = spectre_bhb_enable_mitigation, + }, #ifdef CONFIG_ARM64_ERRATUM_1418040 { .desc = "ARM erratum 1418040", @@ -598,6 +607,41 @@ const struct arm64_cpu_capabilities arm64_errata[] = { CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2077057 + { + .desc = "ARM erratum 2077057", + .capability = ARM64_WORKAROUND_2077057, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2), + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_2064142 + { + .desc = "ARM erratum 2064142", + .capability = ARM64_WORKAROUND_2064142, + + /* Cortex-A510 r0p0 - r0p2 */ + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2) + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_2038923 + { + .desc = "ARM erratum 2038923", + .capability = ARM64_WORKAROUND_2038923, + + /* Cortex-A510 r0p0 - r0p2 */ + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2) + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_1902691 + { + .desc = "ARM erratum 1902691", + .capability = ARM64_WORKAROUND_1902691, + + /* Cortex-A510 r0p0 - r0p1 */ + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 1) + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index a46ab3b1c4d5..d33687673f6b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -73,6 +73,8 @@ #include <linux/mm.h> #include <linux/cpu.h> #include <linux/kasan.h> +#include <linux/percpu.h> + #include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/cpu_ops.h> @@ -85,6 +87,7 @@ #include <asm/smp.h> #include <asm/sysreg.h> #include <asm/traps.h> +#include <asm/vectors.h> #include <asm/virt.h> /* Kernel representation of AT_HWCAP and AT_HWCAP2 */ @@ -110,6 +113,8 @@ DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE); bool arm64_use_ng_mappings = false; EXPORT_SYMBOL(arm64_use_ng_mappings); +DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors; + /* * Permit PER_LINUX32 and execve() of 32-bit binaries even if not all CPUs * support it? @@ -226,6 +231,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_CLEARBHB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_RPRES_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -1590,6 +1596,12 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) int cpu = smp_processor_id(); + if (__this_cpu_read(this_cpu_vector) == vectors) { + const char *v = arm64_get_bp_hardening_vector(EL1_VECTOR_KPTI); + + __this_cpu_write(this_cpu_vector, v); + } + /* * We don't need to rewrite the page-tables if either we've done * it already or we have KASLR enabled and therefore have not @@ -1646,6 +1658,9 @@ static bool cpu_has_broken_dbm(void) /* Kryo4xx Silver (rdpe => r1p0) */ MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe), #endif +#ifdef CONFIG_ARM64_ERRATUM_2051678 + MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2), +#endif {}, }; diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 772ec2ecf488..4a3a653df07e 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -37,18 +37,21 @@ .macro kernel_ventry, el:req, ht:req, regsize:req, label:req .align 7 -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 +.Lventry_start\@: .if \el == 0 -alternative_if ARM64_UNMAP_KERNEL_AT_EL0 + /* + * This must be the first instruction of the EL0 vector entries. It is + * skipped by the trampoline vectors, to trigger the cleanup. + */ + b .Lskip_tramp_vectors_cleanup\@ .if \regsize == 64 mrs x30, tpidrro_el0 msr tpidrro_el0, xzr .else mov x30, xzr .endif -alternative_else_nop_endif +.Lskip_tramp_vectors_cleanup\@: .endif -#endif sub sp, sp, #PT_REGS_SIZE #ifdef CONFIG_VMAP_STACK @@ -95,11 +98,15 @@ alternative_else_nop_endif mrs x0, tpidrro_el0 #endif b el\el\ht\()_\regsize\()_\label +.org .Lventry_start\@ + 128 // Did we overflow the ventry slot? .endm - .macro tramp_alias, dst, sym + .macro tramp_alias, dst, sym, tmp mov_q \dst, TRAMP_VALIAS - add \dst, \dst, #(\sym - .entry.tramp.text) + adr_l \tmp, \sym + add \dst, \dst, \tmp + adr_l \tmp, .entry.tramp.text + sub \dst, \dst, \tmp .endm /* @@ -116,7 +123,7 @@ alternative_cb_end tbnz \tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@ mov w0, #ARM_SMCCC_ARCH_WORKAROUND_2 mov w1, #\state -alternative_cb spectre_v4_patch_fw_mitigation_conduit +alternative_cb smccc_patch_fw_mitigation_conduit nop // Patched to SMC/HVC #0 alternative_cb_end .L__asm_ssbd_skip\@: @@ -413,21 +420,26 @@ alternative_else_nop_endif ldp x24, x25, [sp, #16 * 12] ldp x26, x27, [sp, #16 * 13] ldp x28, x29, [sp, #16 * 14] - ldr lr, [sp, #S_LR] - add sp, sp, #PT_REGS_SIZE // restore sp .if \el == 0 -alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 +alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 + ldr lr, [sp, #S_LR] + add sp, sp, #PT_REGS_SIZE // restore sp + eret +alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 bne 4f - msr far_el1, x30 - tramp_alias x30, tramp_exit_native + msr far_el1, x29 + tramp_alias x30, tramp_exit_native, x29 br x30 4: - tramp_alias x30, tramp_exit_compat + tramp_alias x30, tramp_exit_compat, x29 br x30 #endif .else + ldr lr, [sp, #S_LR] + add sp, sp, #PT_REGS_SIZE // restore sp + /* Ensure any device/NC reads complete */ alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412 @@ -594,12 +606,6 @@ SYM_CODE_END(ret_to_user) .popsection // .entry.text -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -/* - * Exception vectors trampoline. - */ - .pushsection ".entry.tramp.text", "ax" - // Move from tramp_pg_dir to swapper_pg_dir .macro tramp_map_kernel, tmp mrs \tmp, ttbr1_el1 @@ -633,12 +639,47 @@ alternative_else_nop_endif */ .endm - .macro tramp_ventry, regsize = 64 + .macro tramp_data_page dst + adr_l \dst, .entry.tramp.text + sub \dst, \dst, PAGE_SIZE + .endm + + .macro tramp_data_read_var dst, var +#ifdef CONFIG_RANDOMIZE_BASE + tramp_data_page \dst + add \dst, \dst, #:lo12:__entry_tramp_data_\var + ldr \dst, [\dst] +#else + ldr \dst, =\var +#endif + .endm + +#define BHB_MITIGATION_NONE 0 +#define BHB_MITIGATION_LOOP 1 +#define BHB_MITIGATION_FW 2 +#define BHB_MITIGATION_INSN 3 + + .macro tramp_ventry, vector_start, regsize, kpti, bhb .align 7 1: .if \regsize == 64 msr tpidrro_el0, x30 // Restored in kernel_ventry .endif + + .if \bhb == BHB_MITIGATION_LOOP + /* + * This sequence must appear before the first indirect branch. i.e. the + * ret out of tramp_ventry. It appears here because x30 is free. + */ + __mitigate_spectre_bhb_loop x30 + .endif // \bhb == BHB_MITIGATION_LOOP + + .if \bhb == BHB_MITIGATION_INSN + clearbhb + isb + .endif // \bhb == BHB_MITIGATION_INSN + + .if \kpti == 1 /* * Defend against branch aliasing attacks by pushing a dummy * entry onto the return stack and using a RET instruction to @@ -648,46 +689,75 @@ alternative_else_nop_endif b . 2: tramp_map_kernel x30 -#ifdef CONFIG_RANDOMIZE_BASE - adr x30, tramp_vectors + PAGE_SIZE alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003 - ldr x30, [x30] -#else - ldr x30, =vectors -#endif + tramp_data_read_var x30, vectors alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM - prfm plil1strm, [x30, #(1b - tramp_vectors)] + prfm plil1strm, [x30, #(1b - \vector_start)] alternative_else_nop_endif + msr vbar_el1, x30 - add x30, x30, #(1b - tramp_vectors) isb + .else + ldr x30, =vectors + .endif // \kpti == 1 + + .if \bhb == BHB_MITIGATION_FW + /* + * The firmware sequence must appear before the first indirect branch. + * i.e. the ret out of tramp_ventry. But it also needs the stack to be + * mapped to save/restore the registers the SMC clobbers. + */ + __mitigate_spectre_bhb_fw + .endif // \bhb == BHB_MITIGATION_FW + + add x30, x30, #(1b - \vector_start + 4) ret +.org 1b + 128 // Did we overflow the ventry slot? .endm .macro tramp_exit, regsize = 64 - adr x30, tramp_vectors + tramp_data_read_var x30, this_cpu_vector + get_this_cpu_offset x29 + ldr x30, [x30, x29] + msr vbar_el1, x30 - tramp_unmap_kernel x30 + ldr lr, [sp, #S_LR] + tramp_unmap_kernel x29 .if \regsize == 64 - mrs x30, far_el1 + mrs x29, far_el1 .endif + add sp, sp, #PT_REGS_SIZE // restore sp eret sb .endm - .align 11 -SYM_CODE_START_NOALIGN(tramp_vectors) + .macro generate_tramp_vector, kpti, bhb +.Lvector_start\@: .space 0x400 - tramp_ventry - tramp_ventry - tramp_ventry - tramp_ventry + .rept 4 + tramp_ventry .Lvector_start\@, 64, \kpti, \bhb + .endr + .rept 4 + tramp_ventry .Lvector_start\@, 32, \kpti, \bhb + .endr + .endm - tramp_ventry 32 - tramp_ventry 32 - tramp_ventry 32 - tramp_ventry 32 +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 +/* + * Exception vectors trampoline. + * The order must match __bp_harden_el1_vectors and the + * arm64_bp_harden_el1_vectors enum. + */ + .pushsection ".entry.tramp.text", "ax" + .align 11 +SYM_CODE_START_NOALIGN(tramp_vectors) +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_LOOP + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_FW + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_INSN +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_NONE SYM_CODE_END(tramp_vectors) SYM_CODE_START(tramp_exit_native) @@ -704,13 +774,57 @@ SYM_CODE_END(tramp_exit_compat) .pushsection ".rodata", "a" .align PAGE_SHIFT SYM_DATA_START(__entry_tramp_data_start) +__entry_tramp_data_vectors: .quad vectors +#ifdef CONFIG_ARM_SDE_INTERFACE +__entry_tramp_data___sdei_asm_handler: + .quad __sdei_asm_handler +#endif /* CONFIG_ARM_SDE_INTERFACE */ +__entry_tramp_data_this_cpu_vector: + .quad this_cpu_vector SYM_DATA_END(__entry_tramp_data_start) .popsection // .rodata #endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ /* + * Exception vectors for spectre mitigations on entry from EL1 when + * kpti is not in use. + */ + .macro generate_el1_vector, bhb +.Lvector_start\@: + kernel_ventry 1, t, 64, sync // Synchronous EL1t + kernel_ventry 1, t, 64, irq // IRQ EL1t + kernel_ventry 1, t, 64, fiq // FIQ EL1h + kernel_ventry 1, t, 64, error // Error EL1t + + kernel_ventry 1, h, 64, sync // Synchronous EL1h + kernel_ventry 1, h, 64, irq // IRQ EL1h + kernel_ventry 1, h, 64, fiq // FIQ EL1h + kernel_ventry 1, h, 64, error // Error EL1h + + .rept 4 + tramp_ventry .Lvector_start\@, 64, 0, \bhb + .endr + .rept 4 + tramp_ventry .Lvector_start\@, 32, 0, \bhb + .endr + .endm + +/* The order must match tramp_vecs and the arm64_bp_harden_el1_vectors enum. */ + .pushsection ".entry.text", "ax" + .align 11 +SYM_CODE_START(__bp_harden_el1_vectors) +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + generate_el1_vector bhb=BHB_MITIGATION_LOOP + generate_el1_vector bhb=BHB_MITIGATION_FW + generate_el1_vector bhb=BHB_MITIGATION_INSN +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ +SYM_CODE_END(__bp_harden_el1_vectors) + .popsection + + +/* * Register switch for AArch64. The callee-saved registers need to be saved * and restored. On entry: * x0 = previous task_struct (must be preserved across the switch) @@ -835,14 +949,7 @@ SYM_CODE_START(__sdei_asm_entry_trampoline) * Remember whether to unmap the kernel on exit. */ 1: str x4, [x1, #(SDEI_EVENT_INTREGS + S_SDEI_TTBR1)] - -#ifdef CONFIG_RANDOMIZE_BASE - adr x4, tramp_vectors + PAGE_SIZE - add x4, x4, #:lo12:__sdei_asm_trampoline_next_handler - ldr x4, [x4] -#else - ldr x4, =__sdei_asm_handler -#endif + tramp_data_read_var x4, __sdei_asm_handler br x4 SYM_CODE_END(__sdei_asm_entry_trampoline) NOKPROBE(__sdei_asm_entry_trampoline) @@ -865,13 +972,6 @@ SYM_CODE_END(__sdei_asm_exit_trampoline) NOKPROBE(__sdei_asm_exit_trampoline) .ltorg .popsection // .entry.tramp.text -#ifdef CONFIG_RANDOMIZE_BASE -.pushsection ".rodata", "a" -SYM_DATA_START(__sdei_asm_trampoline_next_handler) - .quad __sdei_asm_handler -SYM_DATA_END(__sdei_asm_trampoline_next_handler) -.popsection // .rodata -#endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ /* @@ -981,7 +1081,7 @@ alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 - tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline + tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline, tmp=x3 br x5 #endif SYM_CODE_END(__sdei_asm_handler) diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 7eaf1f7c4168..55a1ced8eb77 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -66,6 +66,10 @@ KVM_NVHE_ALIAS(kvm_patch_vector_branch); KVM_NVHE_ALIAS(kvm_update_va_mask); KVM_NVHE_ALIAS(kvm_get_kimage_voffset); KVM_NVHE_ALIAS(kvm_compute_final_ctr_el0); +KVM_NVHE_ALIAS(spectre_bhb_patch_loop_iter); +KVM_NVHE_ALIAS(spectre_bhb_patch_loop_mitigation_enable); +KVM_NVHE_ALIAS(spectre_bhb_patch_wa3); +KVM_NVHE_ALIAS(spectre_bhb_patch_clearbhb); /* Global kernel state accessed by nVHE hyp code. */ KVM_NVHE_ALIAS(kvm_vgic_global_state); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 902e4084c477..6d45c63c6454 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -18,15 +18,18 @@ */ #include <linux/arm-smccc.h> +#include <linux/bpf.h> #include <linux/cpu.h> #include <linux/device.h> #include <linux/nospec.h> #include <linux/prctl.h> #include <linux/sched/task_stack.h> +#include <asm/debug-monitors.h> #include <asm/insn.h> #include <asm/spectre.h> #include <asm/traps.h> +#include <asm/vectors.h> #include <asm/virt.h> /* @@ -96,14 +99,51 @@ static bool spectre_v2_mitigations_off(void) return ret; } +static const char *get_bhb_affected_string(enum mitigation_state bhb_state) +{ + switch (bhb_state) { + case SPECTRE_UNAFFECTED: + return ""; + default: + case SPECTRE_VULNERABLE: + return ", but not BHB"; + case SPECTRE_MITIGATED: + return ", BHB"; + } +} + +static bool _unprivileged_ebpf_enabled(void) +{ +#ifdef CONFIG_BPF_SYSCALL + return !sysctl_unprivileged_bpf_disabled; +#else + return false; +#endif +} + ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { + enum mitigation_state bhb_state = arm64_get_spectre_bhb_state(); + const char *bhb_str = get_bhb_affected_string(bhb_state); + const char *v2_str = "Branch predictor hardening"; + switch (spectre_v2_state) { case SPECTRE_UNAFFECTED: - return sprintf(buf, "Not affected\n"); + if (bhb_state == SPECTRE_UNAFFECTED) + return sprintf(buf, "Not affected\n"); + + /* + * Platforms affected by Spectre-BHB can't report + * "Not affected" for Spectre-v2. + */ + v2_str = "CSV2"; + fallthrough; case SPECTRE_MITIGATED: - return sprintf(buf, "Mitigation: Branch predictor hardening\n"); + if (bhb_state == SPECTRE_MITIGATED && _unprivileged_ebpf_enabled()) + return sprintf(buf, "Vulnerable: Unprivileged eBPF enabled\n"); + + return sprintf(buf, "Mitigation: %s%s\n", v2_str, bhb_str); case SPECTRE_VULNERABLE: fallthrough; default: @@ -554,9 +594,9 @@ void __init spectre_v4_patch_fw_mitigation_enable(struct alt_instr *alt, * Patch a NOP in the Spectre-v4 mitigation code with an SMC/HVC instruction * to call into firmware to adjust the mitigation state. */ -void __init spectre_v4_patch_fw_mitigation_conduit(struct alt_instr *alt, - __le32 *origptr, - __le32 *updptr, int nr_inst) +void __init smccc_patch_fw_mitigation_conduit(struct alt_instr *alt, + __le32 *origptr, + __le32 *updptr, int nr_inst) { u32 insn; @@ -770,3 +810,344 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) return -ENODEV; } } + +/* + * Spectre BHB. + * + * A CPU is either: + * - Mitigated by a branchy loop a CPU specific number of times, and listed + * in our "loop mitigated list". + * - Mitigated in software by the firmware Spectre v2 call. + * - Has the ClearBHB instruction to perform the mitigation. + * - Has the 'Exception Clears Branch History Buffer' (ECBHB) feature, so no + * software mitigation in the vectors is needed. + * - Has CSV2.3, so is unaffected. + */ +static enum mitigation_state spectre_bhb_state; + +enum mitigation_state arm64_get_spectre_bhb_state(void) +{ + return spectre_bhb_state; +} + +enum bhb_mitigation_bits { + BHB_LOOP, + BHB_FW, + BHB_HW, + BHB_INSN, +}; +static unsigned long system_bhb_mitigations; + +/* + * This must be called with SCOPE_LOCAL_CPU for each type of CPU, before any + * SCOPE_SYSTEM call will give the right answer. + */ +u8 spectre_bhb_loop_affected(int scope) +{ + u8 k = 0; + static u8 max_bhb_k; + + if (scope == SCOPE_LOCAL_CPU) { + static const struct midr_range spectre_bhb_k32_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), + {}, + }; + static const struct midr_range spectre_bhb_k24_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A76), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A77), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), + {}, + }; + static const struct midr_range spectre_bhb_k8_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), + {}, + }; + + if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k32_list)) + k = 32; + else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list)) + k = 24; + else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list)) + k = 8; + + max_bhb_k = max(max_bhb_k, k); + } else { + k = max_bhb_k; + } + + return k; +} + +static enum mitigation_state spectre_bhb_get_cpu_fw_mitigation_state(void) +{ + int ret; + struct arm_smccc_res res; + + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_3, &res); + + ret = res.a0; + switch (ret) { + case SMCCC_RET_SUCCESS: + return SPECTRE_MITIGATED; + case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED: + return SPECTRE_UNAFFECTED; + default: + fallthrough; + case SMCCC_RET_NOT_SUPPORTED: + return SPECTRE_VULNERABLE; + } +} + +static bool is_spectre_bhb_fw_affected(int scope) +{ + static bool system_affected; + enum mitigation_state fw_state; + bool has_smccc = arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_NONE; + static const struct midr_range spectre_bhb_firmware_mitigated_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A75), + {}, + }; + bool cpu_in_list = is_midr_in_range_list(read_cpuid_id(), + spectre_bhb_firmware_mitigated_list); + + if (scope != SCOPE_LOCAL_CPU) + return system_affected; + + fw_state = spectre_bhb_get_cpu_fw_mitigation_state(); + if (cpu_in_list || (has_smccc && fw_state == SPECTRE_MITIGATED)) { + system_affected = true; + return true; + } + + return false; +} + +static bool supports_ecbhb(int scope) +{ + u64 mmfr1; + + if (scope == SCOPE_LOCAL_CPU) + mmfr1 = read_sysreg_s(SYS_ID_AA64MMFR1_EL1); + else + mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); + + return cpuid_feature_extract_unsigned_field(mmfr1, + ID_AA64MMFR1_ECBHB_SHIFT); +} + +bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, + int scope) +{ + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + + if (supports_csv2p3(scope)) + return false; + + if (supports_clearbhb(scope)) + return true; + + if (spectre_bhb_loop_affected(scope)) + return true; + + if (is_spectre_bhb_fw_affected(scope)) + return true; + + return false; +} + +static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) +{ + const char *v = arm64_get_bp_hardening_vector(slot); + + if (slot < 0) + return; + + __this_cpu_write(this_cpu_vector, v); + + /* + * When KPTI is in use, the vectors are switched when exiting to + * user-space. + */ + if (arm64_kernel_unmapped_at_el0()) + return; + + write_sysreg(v, vbar_el1); + isb(); +} + +void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) +{ + bp_hardening_cb_t cpu_cb; + enum mitigation_state fw_state, state = SPECTRE_VULNERABLE; + struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data); + + if (!is_spectre_bhb_affected(entry, SCOPE_LOCAL_CPU)) + return; + + if (arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) { + /* No point mitigating Spectre-BHB alone. */ + } else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) { + pr_info_once("spectre-bhb mitigation disabled by compile time option\n"); + } else if (cpu_mitigations_off()) { + pr_info_once("spectre-bhb mitigation disabled by command line option\n"); + } else if (supports_ecbhb(SCOPE_LOCAL_CPU)) { + state = SPECTRE_MITIGATED; + set_bit(BHB_HW, &system_bhb_mitigations); + } else if (supports_clearbhb(SCOPE_LOCAL_CPU)) { + /* + * Ensure KVM uses the indirect vector which will have ClearBHB + * added. + */ + if (!data->slot) + data->slot = HYP_VECTOR_INDIRECT; + + this_cpu_set_vectors(EL1_VECTOR_BHB_CLEAR_INSN); + state = SPECTRE_MITIGATED; + set_bit(BHB_INSN, &system_bhb_mitigations); + } else if (spectre_bhb_loop_affected(SCOPE_LOCAL_CPU)) { + /* + * Ensure KVM uses the indirect vector which will have the + * branchy-loop added. A57/A72-r0 will already have selected + * the spectre-indirect vector, which is sufficient for BHB + * too. + */ + if (!data->slot) + data->slot = HYP_VECTOR_INDIRECT; + + this_cpu_set_vectors(EL1_VECTOR_BHB_LOOP); + state = SPECTRE_MITIGATED; + set_bit(BHB_LOOP, &system_bhb_mitigations); + } else if (is_spectre_bhb_fw_affected(SCOPE_LOCAL_CPU)) { + fw_state = spectre_bhb_get_cpu_fw_mitigation_state(); + if (fw_state == SPECTRE_MITIGATED) { + /* + * Ensure KVM uses one of the spectre bp_hardening + * vectors. The indirect vector doesn't include the EL3 + * call, so needs upgrading to + * HYP_VECTOR_SPECTRE_INDIRECT. + */ + if (!data->slot || data->slot == HYP_VECTOR_INDIRECT) + data->slot += 1; + + this_cpu_set_vectors(EL1_VECTOR_BHB_FW); + + /* + * The WA3 call in the vectors supersedes the WA1 call + * made during context-switch. Uninstall any firmware + * bp_hardening callback. + */ + cpu_cb = spectre_v2_get_sw_mitigation_cb(); + if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb) + __this_cpu_write(bp_hardening_data.fn, NULL); + + state = SPECTRE_MITIGATED; + set_bit(BHB_FW, &system_bhb_mitigations); + } + } + + update_mitigation_state(&spectre_bhb_state, state); +} + +/* Patched to NOP when enabled */ +void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt, + __le32 *origptr, + __le32 *updptr, int nr_inst) +{ + BUG_ON(nr_inst != 1); + + if (test_bit(BHB_LOOP, &system_bhb_mitigations)) + *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); +} + +/* Patched to NOP when enabled */ +void noinstr spectre_bhb_patch_fw_mitigation_enabled(struct alt_instr *alt, + __le32 *origptr, + __le32 *updptr, int nr_inst) +{ + BUG_ON(nr_inst != 1); + + if (test_bit(BHB_FW, &system_bhb_mitigations)) + *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); +} + +/* Patched to correct the immediate */ +void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + u8 rd; + u32 insn; + u16 loop_count = spectre_bhb_loop_affected(SCOPE_SYSTEM); + + BUG_ON(nr_inst != 1); /* MOV -> MOV */ + + if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) + return; + + insn = le32_to_cpu(*origptr); + rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn); + insn = aarch64_insn_gen_movewide(rd, loop_count, 0, + AARCH64_INSN_VARIANT_64BIT, + AARCH64_INSN_MOVEWIDE_ZERO); + *updptr++ = cpu_to_le32(insn); +} + +/* Patched to mov WA3 when supported */ +void noinstr spectre_bhb_patch_wa3(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + u8 rd; + u32 insn; + + BUG_ON(nr_inst != 1); /* MOV -> MOV */ + + if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) || + !test_bit(BHB_FW, &system_bhb_mitigations)) + return; + + insn = le32_to_cpu(*origptr); + rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn); + + insn = aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_ORR, + AARCH64_INSN_VARIANT_32BIT, + AARCH64_INSN_REG_ZR, rd, + ARM_SMCCC_ARCH_WORKAROUND_3); + if (WARN_ON_ONCE(insn == AARCH64_BREAK_FAULT)) + return; + + *updptr++ = cpu_to_le32(insn); +} + +/* Patched to NOP when not supported */ +void __init spectre_bhb_patch_clearbhb(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + BUG_ON(nr_inst != 2); + + if (test_bit(BHB_INSN, &system_bhb_mitigations)) + return; + + *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); + *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); +} + +#ifdef CONFIG_BPF_SYSCALL +#define EBPF_WARN "Unprivileged eBPF is enabled, data leaks possible via Spectre v2 BHB attacks!\n" +void unpriv_ebpf_notify(int new_state) +{ + if (spectre_v2_state == SPECTRE_VULNERABLE || + spectre_bhb_state != SPECTRE_MITIGATED) + return; + + if (!new_state) + pr_err("WARNING: %s", EBPF_WARN); +} +#endif diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 0fb58fed54cb..e4103e085681 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -33,8 +33,8 @@ */ -static void start_backtrace(struct stackframe *frame, unsigned long fp, - unsigned long pc) +static notrace void start_backtrace(struct stackframe *frame, unsigned long fp, + unsigned long pc) { frame->fp = fp; frame->pc = pc; @@ -55,6 +55,7 @@ static void start_backtrace(struct stackframe *frame, unsigned long fp, frame->prev_fp = 0; frame->prev_type = STACK_TYPE_UNKNOWN; } +NOKPROBE_SYMBOL(start_backtrace); /* * Unwind from one frame record (A) to the next frame record (B). diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 60813497a381..172452f79e46 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -29,8 +29,11 @@ ldflags-y := -shared -soname=linux-vdso.so.1 --hash-style=sysv \ ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO +# -Wmissing-prototypes and -Wmissing-declarations are removed from +# the CFLAGS of vgettimeofday.c to make possible to build the +# kernel with CONFIG_WERROR enabled. CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) \ - $(CC_FLAGS_LTO) + $(CC_FLAGS_LTO) -Wmissing-prototypes -Wmissing-declarations KASAN_SANITIZE := n KCSAN_SANITIZE := n UBSAN_SANITIZE := n diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 50bab186c49b..edaf0faf766f 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -341,7 +341,7 @@ ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1)) <= SZ_4K, "Hibernate exit text too big or misaligned") #endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) == PAGE_SIZE, +ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE, "Entry trampoline text too big") #endif #ifdef CONFIG_KVM diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index a4a0063df456..4dca6ffd03d4 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -797,6 +797,24 @@ static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret) xfer_to_guest_mode_work_pending(); } +/* + * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while + * the vCPU is running. + * + * This must be noinstr as instrumentation may make use of RCU, and this is not + * safe during the EQS. + */ +static int noinstr kvm_arm_vcpu_enter_exit(struct kvm_vcpu *vcpu) +{ + int ret; + + guest_state_enter_irqoff(); + ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu); + guest_state_exit_irqoff(); + + return ret; +} + /** * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code * @vcpu: The VCPU pointer @@ -881,9 +899,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * Enter the guest */ trace_kvm_entry(*vcpu_pc(vcpu)); - guest_enter_irqoff(); + guest_timing_enter_irqoff(); - ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu); + ret = kvm_arm_vcpu_enter_exit(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; vcpu->stat.exits++; @@ -918,26 +936,23 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_arch_vcpu_ctxsync_fp(vcpu); /* - * We may have taken a host interrupt in HYP mode (ie - * while executing the guest). This interrupt is still - * pending, as we haven't serviced it yet! + * We must ensure that any pending interrupts are taken before + * we exit guest timing so that timer ticks are accounted as + * guest time. Transiently unmask interrupts so that any + * pending interrupts are taken. * - * We're now back in SVC mode, with interrupts - * disabled. Enabling the interrupts now will have - * the effect of taking the interrupt again, in SVC - * mode this time. + * Per ARM DDI 0487G.b section D1.13.4, an ISB (or other + * context synchronization event) is necessary to ensure that + * pending interrupts are taken. */ local_irq_enable(); + isb(); + local_irq_disable(); + + guest_timing_exit_irqoff(); + + local_irq_enable(); - /* - * We do local_irq_enable() before calling guest_exit() so - * that if a timer interrupt hits while running the guest we - * account that tick as being spent in the guest. We enable - * preemption after calling guest_exit() so that if we get - * preempted we make sure ticks after that is not counted as - * guest time. - */ - guest_exit(); trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); /* Exit types that need handling before we can be preempted */ @@ -1476,10 +1491,7 @@ static int kvm_init_vector_slots(void) base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs)); kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT); - if (!cpus_have_const_cap(ARM64_SPECTRE_V3A)) - return 0; - - if (!has_vhe()) { + if (kvm_system_needs_idmapped_vectors() && !has_vhe()) { err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs), __BP_HARDEN_HYP_VECS_SZ, &base); if (err) diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index fd2dd26caf91..e3140abd2e2e 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -228,6 +228,14 @@ int handle_exit(struct kvm_vcpu *vcpu, int exception_index) { struct kvm_run *run = vcpu->run; + if (ARM_SERROR_PENDING(exception_index)) { + /* + * The SError is handled by handle_exit_early(). If the guest + * survives it will re-execute the original instruction. + */ + return 1; + } + exception_index = ARM_EXCEPTION_CODE(exception_index); switch (exception_index) { diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index 0418399e0a20..c5d009715402 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -38,7 +38,10 @@ static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, u64 val) { - write_sysreg_el1(val, SYS_SPSR); + if (has_vhe()) + write_sysreg_el1(val, SYS_SPSR); + else + __vcpu_sys_reg(vcpu, SPSR_EL1) = val; } static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index b6b6801d96d5..7839d075729b 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -62,6 +62,10 @@ el1_sync: // Guest trapped into EL2 /* ARM_SMCCC_ARCH_WORKAROUND_2 handling */ eor w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_1 ^ \ ARM_SMCCC_ARCH_WORKAROUND_2) + cbz w1, wa_epilogue + + eor w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_2 ^ \ + ARM_SMCCC_ARCH_WORKAROUND_3) cbnz w1, el1_trap wa_epilogue: @@ -192,7 +196,10 @@ SYM_CODE_END(__kvm_hyp_vector) sub sp, sp, #(8 * 4) stp x2, x3, [sp, #(8 * 0)] stp x0, x1, [sp, #(8 * 2)] + alternative_cb spectre_bhb_patch_wa3 + /* Patched to mov WA3 when supported */ mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1 + alternative_cb_end smc #0 ldp x2, x3, [sp, #(8 * 0)] add sp, sp, #(8 * 2) @@ -205,6 +212,8 @@ SYM_CODE_END(__kvm_hyp_vector) spectrev2_smccc_wa1_smc .else stp x0, x1, [sp, #-16]! + mitigate_spectre_bhb_loop x0 + mitigate_spectre_bhb_clear_insn .endif .if \indirect != 0 alternative_cb kvm_patch_vector_branch diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 58e14f8ead23..701cfb964905 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -402,6 +402,24 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } +static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + /* + * Check for the conditions of Cortex-A510's #2077057. When these occur + * SPSR_EL2 can't be trusted, but isn't needed either as it is + * unchanged from the value in vcpu_gp_regs(vcpu)->pstate. + * Are we single-stepping the guest, and took a PAC exception from the + * active-not-pending state? + */ + if (cpus_have_final_cap(ARM64_WORKAROUND_2077057) && + vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && + *vcpu_cpsr(vcpu) & DBG_SPSR_SS && + ESR_ELx_EC(read_sysreg_el2(SYS_ESR)) == ESR_ELx_EC_PAC) + write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR); + + vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR); +} + /* * Return true when we were able to fixup the guest exit and should return to * the guest, false when we should restore the host state and return to the @@ -413,7 +431,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) * Save PSTATE early so that we can evaluate the vcpu mode * early on. */ - vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR); + synchronize_vcpu_pstate(vcpu, exit_code); /* * Check whether we want to repaint the state one way or @@ -424,7 +442,8 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); - if (ARM_SERROR_PENDING(*exit_code)) { + if (ARM_SERROR_PENDING(*exit_code) && + ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) { u8 esr_ec = kvm_vcpu_trap_get_class(vcpu); /* diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c index 526a7d6fa86f..cdbe8e246418 100644 --- a/arch/arm64/kvm/hyp/nvhe/mm.c +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -148,8 +148,10 @@ int hyp_map_vectors(void) phys_addr_t phys; void *bp_base; - if (!cpus_have_const_cap(ARM64_SPECTRE_V3A)) + if (!kvm_system_needs_idmapped_vectors()) { + __hyp_bp_vect_base = __bp_harden_hyp_vecs; return 0; + } phys = __hyp_pa(__bp_harden_hyp_vecs); bp_base = (void *)__pkvm_create_private_mapping(phys, diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 844a6f003fd5..2cb3867eb7c2 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -983,13 +983,9 @@ static int stage2_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, */ stage2_put_pte(ptep, mmu, addr, level, mm_ops); - if (need_flush) { - kvm_pte_t *pte_follow = kvm_pte_follow(pte, mm_ops); - - dcache_clean_inval_poc((unsigned long)pte_follow, - (unsigned long)pte_follow + - kvm_granule_size(level)); - } + if (need_flush && mm_ops->dcache_clean_inval_poc) + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(pte, mm_ops), + kvm_granule_size(level)); if (childp) mm_ops->put_page(childp); @@ -1151,15 +1147,13 @@ static int stage2_flush_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, struct kvm_pgtable *pgt = arg; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; kvm_pte_t pte = *ptep; - kvm_pte_t *pte_follow; if (!kvm_pte_valid(pte) || !stage2_pte_cacheable(pgt, pte)) return 0; - pte_follow = kvm_pte_follow(pte, mm_ops); - dcache_clean_inval_poc((unsigned long)pte_follow, - (unsigned long)pte_follow + - kvm_granule_size(level)); + if (mm_ops->dcache_clean_inval_poc) + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(pte, mm_ops), + kvm_granule_size(level)); return 0; } diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 20db2f281cf2..4fb419f7b8b6 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -983,6 +983,9 @@ static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT; /* IDbits */ val |= ((vtr >> 23) & 7) << ICC_CTLR_EL1_ID_BITS_SHIFT; + /* SEIS */ + if (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) + val |= BIT(ICC_CTLR_EL1_SEIS_SHIFT); /* A3V */ val |= ((vtr >> 21) & 1) << ICC_CTLR_EL1_A3V_SHIFT; /* EOImode */ diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 11d053fdd604..54af47005e45 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -10,6 +10,7 @@ #include <linux/kvm_host.h> #include <linux/types.h> #include <linux/jump_label.h> +#include <linux/percpu.h> #include <uapi/linux/psci.h> #include <kvm/arm_psci.h> @@ -24,6 +25,8 @@ #include <asm/fpsimd.h> #include <asm/debug-monitors.h> #include <asm/processor.h> +#include <asm/thread_info.h> +#include <asm/vectors.h> /* VHE specific context */ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); @@ -67,7 +70,7 @@ NOKPROBE_SYMBOL(__activate_traps); static void __deactivate_traps(struct kvm_vcpu *vcpu) { - extern char vectors[]; /* kernel exception vectors */ + const char *host_vectors = vectors; ___deactivate_traps(vcpu); @@ -81,7 +84,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); - write_sysreg(vectors, vbar_el1); + + if (!arm64_kernel_unmapped_at_el0()) + host_vectors = __this_cpu_read(this_cpu_vector); + write_sysreg(host_vectors, vbar_el1); } NOKPROBE_SYMBOL(__deactivate_traps); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 30da78f72b3b..202b8c455724 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -107,6 +107,18 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) break; } break; + case ARM_SMCCC_ARCH_WORKAROUND_3: + switch (arm64_get_spectre_bhb_state()) { + case SPECTRE_VULNERABLE: + break; + case SPECTRE_MITIGATED: + val[0] = SMCCC_RET_SUCCESS; + break; + case SPECTRE_UNAFFECTED: + val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED; + break; + } + break; case ARM_SMCCC_HV_PV_TIME_FEATURES: val[0] = SMCCC_RET_SUCCESS; break; diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 3eae32876897..5918095c90a5 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -46,8 +46,7 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) * specification (ARM DEN 0022A). This means all suspend states * for KVM will preserve the register state. */ - kvm_vcpu_halt(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); + kvm_vcpu_wfi(vcpu); return PSCI_RET_SUCCESS; } @@ -406,7 +405,7 @@ int kvm_psci_call(struct kvm_vcpu *vcpu) int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) { - return 3; /* PSCI version and two workaround registers */ + return 4; /* PSCI version and three workaround registers */ } int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) @@ -420,6 +419,9 @@ int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, uindices++)) return -EFAULT; + if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, uindices++)) + return -EFAULT; + return 0; } @@ -459,6 +461,17 @@ static int get_kernel_wa_level(u64 regid) case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; } + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: + switch (arm64_get_spectre_bhb_state()) { + case SPECTRE_VULNERABLE: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; + case SPECTRE_MITIGATED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL; + case SPECTRE_UNAFFECTED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED; + } + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; } return -EINVAL; @@ -475,6 +488,7 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK; break; default: @@ -520,6 +534,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: if (val & ~KVM_REG_FEATURE_LEVEL_MASK) return -EINVAL; diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index 7068da080799..49837d3a3ef5 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -248,6 +248,8 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, IRQCHIP_STATE_PENDING, &val); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + } else if (vgic_irq_is_mapped_level(irq)) { + val = vgic_get_phys_line_level(irq); } else { val = irq_is_pending(irq); } diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index a33d4366b326..b549af8b1dc2 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -609,6 +609,18 @@ static int __init early_gicv4_enable(char *buf) } early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); +static const struct midr_range broken_seis[] = { + MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM), + MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM), + {}, +}; + +static bool vgic_v3_broken_seis(void) +{ + return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) && + is_midr_in_range_list(read_cpuid_id(), broken_seis)); +} + /** * vgic_v3_probe - probe for a VGICv3 compatible interrupt controller * @info: pointer to the GIC description @@ -676,9 +688,10 @@ int vgic_v3_probe(const struct gic_kvm_info *info) group1_trap = true; } - if (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) { - kvm_info("GICv3 with locally generated SEI\n"); + if (vgic_v3_broken_seis()) { + kvm_info("GICv3 with broken locally generated SEI\n"); + kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_SEIS_MASK; group0_trap = true; group1_trap = true; if (ich_vtr_el2 & ICH_VTR_TDS_MASK) diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c index c0181e60cc98..489455309695 100644 --- a/arch/arm64/mm/extable.c +++ b/arch/arm64/mm/extable.c @@ -40,8 +40,8 @@ static bool ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex, struct pt_regs *regs) { - int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->type); - int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->type); + int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data); + int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data); unsigned long data, addr, offset; addr = pt_regs_read_reg(regs, reg_addr); diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index a38f54cd638c..77ada00280d9 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -7,8 +7,10 @@ #include <linux/io.h> #include <linux/memblock.h> +#include <linux/mm.h> #include <linux/types.h> +#include <asm/cpufeature.h> #include <asm/page.h> /* @@ -38,3 +40,18 @@ int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) { return !(((pfn << PAGE_SHIFT) + size) & ~PHYS_MASK); } + +static int __init adjust_protection_map(void) +{ + /* + * With Enhanced PAN we can honour the execute-only permissions as + * there is no PAN override with such mappings. + */ + if (cpus_have_const_cap(ARM64_HAS_EPAN)) { + protection_map[VM_EXEC] = PAGE_EXECONLY; + protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY; + } + + return 0; +} +arch_initcall(adjust_protection_map); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index acfae9b41cc8..49abbf43bf35 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -617,6 +617,8 @@ early_param("rodata", parse_rodata); #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 static int __init map_entry_trampoline(void) { + int i; + pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC; phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start); @@ -625,11 +627,15 @@ static int __init map_entry_trampoline(void) /* Map only the text into the trampoline page table */ memset(tramp_pg_dir, 0, PGD_SIZE); - __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE, - prot, __pgd_pgtable_alloc, 0); + __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, + entry_tramp_text_size(), prot, + __pgd_pgtable_alloc, NO_BLOCK_MAPPINGS); /* Map both the text and data into the kernel page table */ - __set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot); + for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++) + __set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i, + pa_start + i * PAGE_SIZE, prot); + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { extern char __entry_tramp_data_start[]; diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 870c39537dd0..cea7533cb304 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -44,6 +44,7 @@ MTE_ASYMM SPECTRE_V2 SPECTRE_V3A SPECTRE_V4 +SPECTRE_BHB SSBS SVE UNMAP_KERNEL_AT_EL0 @@ -55,6 +56,10 @@ WORKAROUND_1418040 WORKAROUND_1463225 WORKAROUND_1508412 WORKAROUND_1542419 +WORKAROUND_1902691 +WORKAROUND_2038923 +WORKAROUND_2064142 +WORKAROUND_2077057 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE WORKAROUND_TRBE_WRITE_OUT_OF_RANGE diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 703952819e10..a7e01573abd8 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -318,7 +318,7 @@ config ARCH_PROC_KCORE_TEXT depends on PROC_KCORE config IA64_MCA_RECOVERY - tristate "MCA recovery from errors other than TLB." + bool "MCA recovery from errors other than TLB." config IA64_PALINFO tristate "/proc/pal support" diff --git a/arch/ia64/pci/fixup.c b/arch/ia64/pci/fixup.c index acb55a41260d..2bcdd7d3a1ad 100644 --- a/arch/ia64/pci/fixup.c +++ b/arch/ia64/pci/fixup.c @@ -76,5 +76,5 @@ static void pci_fixup_video(struct pci_dev *pdev) } } } -DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, - PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 3e336b3dbb10..ab6e3dc0bc1d 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -83,6 +83,8 @@ label = "HDMI OUT"; type = "a"; + ddc-en-gpios = <&gpa 25 GPIO_ACTIVE_HIGH>; + port { hdmi_con: endpoint { remote-endpoint = <&dw_hdmi_out>; @@ -114,17 +116,6 @@ gpio = <&gpf 14 GPIO_ACTIVE_LOW>; enable-active-high; }; - - hdmi_power: fixedregulator@3 { - compatible = "regulator-fixed"; - - regulator-name = "hdmi_power"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - - gpio = <&gpa 25 0>; - enable-active-high; - }; }; &ext { @@ -576,8 +567,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pins_hdmi_ddc>; - hdmi-5v-supply = <&hdmi_power>; - ports { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/mips/cavium-octeon/octeon-memcpy.S b/arch/mips/cavium-octeon/octeon-memcpy.S index 0a515cde1c18..25860fba6218 100644 --- a/arch/mips/cavium-octeon/octeon-memcpy.S +++ b/arch/mips/cavium-octeon/octeon-memcpy.S @@ -74,7 +74,7 @@ #define EXC(inst_reg,addr,handler) \ 9: inst_reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous /* diff --git a/arch/mips/include/asm/asm.h b/arch/mips/include/asm/asm.h index 6ffdd4b5e1d0..336ac9b65235 100644 --- a/arch/mips/include/asm/asm.h +++ b/arch/mips/include/asm/asm.h @@ -285,7 +285,7 @@ symbol = value #define PTR_SCALESHIFT 2 -#define PTR .word +#define PTR_WD .word #define PTRSIZE 4 #define PTRLOG 2 #endif @@ -310,7 +310,7 @@ symbol = value #define PTR_SCALESHIFT 3 -#define PTR .dword +#define PTR_WD .dword #define PTRSIZE 8 #define PTRLOG 3 #endif diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h index b463f2aa5a61..db497a8167da 100644 --- a/arch/mips/include/asm/ftrace.h +++ b/arch/mips/include/asm/ftrace.h @@ -32,7 +32,7 @@ do { \ ".previous\n" \ \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR) "\t1b, 3b\n\t" \ + STR(PTR_WD) "\t1b, 3b\n\t" \ ".previous\n" \ \ : [tmp_dst] "=&r" (dst), [tmp_err] "=r" (error)\ @@ -54,7 +54,7 @@ do { \ ".previous\n" \ \ ".section\t__ex_table,\"a\"\n\t"\ - STR(PTR) "\t1b, 3b\n\t" \ + STR(PTR_WD) "\t1b, 3b\n\t" \ ".previous\n" \ \ : [tmp_err] "=r" (error) \ diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h index af3788589ee6..431a1c9d53fc 100644 --- a/arch/mips/include/asm/r4kcache.h +++ b/arch/mips/include/asm/r4kcache.h @@ -119,7 +119,7 @@ static inline void flush_scache_line(unsigned long addr) " j 2b \n" \ " .previous \n" \ " .section __ex_table,\"a\" \n" \ - " "STR(PTR)" 1b, 3b \n" \ + " "STR(PTR_WD)" 1b, 3b \n" \ " .previous" \ : "+r" (__err) \ : "i" (op), "r" (addr), "i" (-EFAULT)); \ @@ -142,7 +142,7 @@ static inline void flush_scache_line(unsigned long addr) " j 2b \n" \ " .previous \n" \ " .section __ex_table,\"a\" \n" \ - " "STR(PTR)" 1b, 3b \n" \ + " "STR(PTR_WD)" 1b, 3b \n" \ " .previous" \ : "+r" (__err) \ : "i" (op), "r" (addr), "i" (-EFAULT)); \ diff --git a/arch/mips/include/asm/unaligned-emul.h b/arch/mips/include/asm/unaligned-emul.h index 2022b18944b9..9af0f4d3d288 100644 --- a/arch/mips/include/asm/unaligned-emul.h +++ b/arch/mips/include/asm/unaligned-emul.h @@ -20,8 +20,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -41,8 +41,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -74,10 +74,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -102,8 +102,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -125,8 +125,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -145,8 +145,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -178,10 +178,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -223,14 +223,14 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ - STR(PTR)"\t5b, 11b\n\t" \ - STR(PTR)"\t6b, 11b\n\t" \ - STR(PTR)"\t7b, 11b\n\t" \ - STR(PTR)"\t8b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t5b, 11b\n\t" \ + STR(PTR_WD)"\t6b, 11b\n\t" \ + STR(PTR_WD)"\t7b, 11b\n\t" \ + STR(PTR_WD)"\t8b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -255,8 +255,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT));\ @@ -276,8 +276,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); \ @@ -296,8 +296,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); \ @@ -325,10 +325,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT) \ @@ -365,14 +365,14 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ - STR(PTR)"\t5b, 11b\n\t" \ - STR(PTR)"\t6b, 11b\n\t" \ - STR(PTR)"\t7b, 11b\n\t" \ - STR(PTR)"\t8b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t5b, 11b\n\t" \ + STR(PTR_WD)"\t6b, 11b\n\t" \ + STR(PTR_WD)"\t7b, 11b\n\t" \ + STR(PTR_WD)"\t8b, 11b\n\t" \ ".previous" \ : "=&r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT) \ @@ -398,8 +398,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -419,8 +419,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -452,10 +452,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -481,8 +481,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -504,8 +504,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -524,8 +524,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -557,10 +557,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -602,14 +602,14 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ - STR(PTR)"\t5b, 11b\n\t" \ - STR(PTR)"\t6b, 11b\n\t" \ - STR(PTR)"\t7b, 11b\n\t" \ - STR(PTR)"\t8b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t5b, 11b\n\t" \ + STR(PTR_WD)"\t6b, 11b\n\t" \ + STR(PTR_WD)"\t7b, 11b\n\t" \ + STR(PTR_WD)"\t8b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -632,8 +632,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT));\ @@ -653,8 +653,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); \ @@ -673,8 +673,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); \ @@ -703,10 +703,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT) \ @@ -743,14 +743,14 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ - STR(PTR)"\t5b, 11b\n\t" \ - STR(PTR)"\t6b, 11b\n\t" \ - STR(PTR)"\t7b, 11b\n\t" \ - STR(PTR)"\t8b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t5b, 11b\n\t" \ + STR(PTR_WD)"\t6b, 11b\n\t" \ + STR(PTR_WD)"\t7b, 11b\n\t" \ + STR(PTR_WD)"\t8b, 11b\n\t" \ ".previous" \ : "=&r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT) \ diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c index a39ec755e4c2..750fe569862b 100644 --- a/arch/mips/kernel/mips-r2-to-r6-emul.c +++ b/arch/mips/kernel/mips-r2-to-r6-emul.c @@ -1258,10 +1258,10 @@ fpu_emul: " j 10b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1333,10 +1333,10 @@ fpu_emul: " j 10b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1404,10 +1404,10 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1474,10 +1474,10 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1589,14 +1589,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" - STR(PTR) " 5b,8b\n" - STR(PTR) " 6b,8b\n" - STR(PTR) " 7b,8b\n" - STR(PTR) " 0b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" + STR(PTR_WD) " 5b,8b\n" + STR(PTR_WD) " 6b,8b\n" + STR(PTR_WD) " 7b,8b\n" + STR(PTR_WD) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1708,14 +1708,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" - STR(PTR) " 5b,8b\n" - STR(PTR) " 6b,8b\n" - STR(PTR) " 7b,8b\n" - STR(PTR) " 0b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" + STR(PTR_WD) " 5b,8b\n" + STR(PTR_WD) " 6b,8b\n" + STR(PTR_WD) " 7b,8b\n" + STR(PTR_WD) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1827,14 +1827,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" - STR(PTR) " 5b,8b\n" - STR(PTR) " 6b,8b\n" - STR(PTR) " 7b,8b\n" - STR(PTR) " 0b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" + STR(PTR_WD) " 5b,8b\n" + STR(PTR_WD) " 6b,8b\n" + STR(PTR_WD) " 7b,8b\n" + STR(PTR_WD) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1945,14 +1945,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" - STR(PTR) " 5b,8b\n" - STR(PTR) " 6b,8b\n" - STR(PTR) " 7b,8b\n" - STR(PTR) " 0b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" + STR(PTR_WD) " 5b,8b\n" + STR(PTR_WD) " 6b,8b\n" + STR(PTR_WD) " 7b,8b\n" + STR(PTR_WD) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -2007,7 +2007,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - STR(PTR) " 1b,3b\n" + STR(PTR_WD) " 1b,3b\n" ".previous\n" : "=&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV) @@ -2065,7 +2065,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - STR(PTR) " 1b,3b\n" + STR(PTR_WD) " 1b,3b\n" ".previous\n" : "+&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV)); @@ -2126,7 +2126,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - STR(PTR) " 1b,3b\n" + STR(PTR_WD) " 1b,3b\n" ".previous\n" : "=&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV) @@ -2189,7 +2189,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - STR(PTR) " 1b,3b\n" + STR(PTR_WD) " 1b,3b\n" ".previous\n" : "+&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV)); diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S index cbf6db98cfb3..2748c55820c2 100644 --- a/arch/mips/kernel/r2300_fpu.S +++ b/arch/mips/kernel/r2300_fpu.S @@ -23,14 +23,14 @@ #define EX(a,b) \ 9: a,##b; \ .section __ex_table,"a"; \ - PTR 9b,fault; \ + PTR_WD 9b,fault; \ .previous #define EX2(a,b) \ 9: a,##b; \ .section __ex_table,"a"; \ - PTR 9b,fault; \ - PTR 9b+4,fault; \ + PTR_WD 9b,fault; \ + PTR_WD 9b+4,fault; \ .previous .set mips1 diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index b91e91106475..2e687c60bc4f 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -31,7 +31,7 @@ .ex\@: \insn \reg, \src .set pop .section __ex_table,"a" - PTR .ex\@, fault + PTR_WD .ex\@, fault .previous .endm diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S index f3c908abdbb8..cfde14b48fd8 100644 --- a/arch/mips/kernel/relocate_kernel.S +++ b/arch/mips/kernel/relocate_kernel.S @@ -147,10 +147,10 @@ LEAF(kexec_smp_wait) kexec_args: EXPORT(kexec_args) -arg0: PTR 0x0 -arg1: PTR 0x0 -arg2: PTR 0x0 -arg3: PTR 0x0 +arg0: PTR_WD 0x0 +arg1: PTR_WD 0x0 +arg2: PTR_WD 0x0 +arg3: PTR_WD 0x0 .size kexec_args,PTRSIZE*4 #ifdef CONFIG_SMP @@ -161,10 +161,10 @@ arg3: PTR 0x0 */ secondary_kexec_args: EXPORT(secondary_kexec_args) -s_arg0: PTR 0x0 -s_arg1: PTR 0x0 -s_arg2: PTR 0x0 -s_arg3: PTR 0x0 +s_arg0: PTR_WD 0x0 +s_arg1: PTR_WD 0x0 +s_arg2: PTR_WD 0x0 +s_arg3: PTR_WD 0x0 .size secondary_kexec_args,PTRSIZE*4 kexec_flag: LONG 0x1 @@ -173,17 +173,17 @@ kexec_flag: kexec_start_address: EXPORT(kexec_start_address) - PTR 0x0 + PTR_WD 0x0 .size kexec_start_address, PTRSIZE kexec_indirection_page: EXPORT(kexec_indirection_page) - PTR 0 + PTR_WD 0 .size kexec_indirection_page, PTRSIZE relocate_new_kernel_end: relocate_new_kernel_size: EXPORT(relocate_new_kernel_size) - PTR relocate_new_kernel_end - relocate_new_kernel + PTR_WD relocate_new_kernel_end - relocate_new_kernel .size relocate_new_kernel_size, PTRSIZE diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index b1b2e106f711..9bfce5f75f60 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -72,10 +72,10 @@ loads_done: .set pop .section __ex_table,"a" - PTR load_a4, bad_stack_a4 - PTR load_a5, bad_stack_a5 - PTR load_a6, bad_stack_a6 - PTR load_a7, bad_stack_a7 + PTR_WD load_a4, bad_stack_a4 + PTR_WD load_a5, bad_stack_a5 + PTR_WD load_a6, bad_stack_a6 + PTR_WD load_a7, bad_stack_a7 .previous lw t0, TI_FLAGS($28) # syscall tracing enabled? @@ -216,7 +216,7 @@ einval: li v0, -ENOSYS #endif /* CONFIG_MIPS_MT_FPAFF */ #define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) -#define __SYSCALL(nr, entry) PTR entry +#define __SYSCALL(nr, entry) PTR_WD entry .align 2 .type sys_call_table, @object EXPORT(sys_call_table) diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index f650c55a17dc..97456b2ca7dc 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -101,7 +101,7 @@ not_n32_scall: END(handle_sysn32) -#define __SYSCALL(nr, entry) PTR entry +#define __SYSCALL(nr, entry) PTR_WD entry .type sysn32_call_table, @object EXPORT(sysn32_call_table) #include <asm/syscall_table_n32.h> diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S index 5d7bfc65e4d0..5f6ed4b4c399 100644 --- a/arch/mips/kernel/scall64-n64.S +++ b/arch/mips/kernel/scall64-n64.S @@ -109,7 +109,7 @@ illegal_syscall: j n64_syscall_exit END(handle_sys64) -#define __SYSCALL(nr, entry) PTR entry +#define __SYSCALL(nr, entry) PTR_WD entry .align 3 .type sys_call_table, @object EXPORT(sys_call_table) diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index cedc8bd88804..d3c2616cba22 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -73,10 +73,10 @@ load_a7: lw a7, 28(t0) # argument #8 from usp loads_done: .section __ex_table,"a" - PTR load_a4, bad_stack_a4 - PTR load_a5, bad_stack_a5 - PTR load_a6, bad_stack_a6 - PTR load_a7, bad_stack_a7 + PTR_WD load_a4, bad_stack_a4 + PTR_WD load_a5, bad_stack_a5 + PTR_WD load_a6, bad_stack_a6 + PTR_WD load_a7, bad_stack_a7 .previous li t1, _TIF_WORK_SYSCALL_ENTRY @@ -214,7 +214,7 @@ einval: li v0, -ENOSYS END(sys32_syscall) #define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat) -#define __SYSCALL(nr, entry) PTR entry +#define __SYSCALL(nr, entry) PTR_WD entry .align 3 .type sys32_call_table,@object EXPORT(sys32_call_table) diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index f979adfd4fc2..ef73ba1e0ec1 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -803,7 +803,7 @@ early_param("coherentio", setcoherentio); static int __init setnocoherentio(char *str) { - dma_default_coherent = true; + dma_default_coherent = false; pr_info("Software DMA cache coherency (command line)\n"); return 0; } diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index d542fb7af3ba..1986d1309410 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -351,6 +351,9 @@ asmlinkage void start_secondary(void) cpu = smp_processor_id(); cpu_data[cpu].udelay_val = loops_per_jiffy; + set_cpu_sibling_map(cpu); + set_cpu_core_map(cpu); + cpumask_set_cpu(cpu, &cpu_coherent_mask); notify_cpu_starting(cpu); @@ -362,9 +365,6 @@ asmlinkage void start_secondary(void) /* The CPU is running and counters synchronised, now mark it online */ set_cpu_online(cpu, true); - set_cpu_sibling_map(cpu); - set_cpu_core_map(cpu); - calculate_cpu_foreign_map(); /* diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 5512cd586e6e..ae93a607ddf7 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -122,8 +122,8 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) " j 3b \n" " .previous \n" " .section __ex_table,\"a\" \n" - " "STR(PTR)" 1b, 4b \n" - " "STR(PTR)" 2b, 4b \n" + " "STR(PTR_WD)" 1b, 4b \n" + " "STR(PTR_WD)" 2b, 4b \n" " .previous \n" " .set pop \n" : [old] "=&r" (old), @@ -152,8 +152,8 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) " j 3b \n" " .previous \n" " .section __ex_table,\"a\" \n" - " "STR(PTR)" 1b, 5b \n" - " "STR(PTR)" 2b, 5b \n" + " "STR(PTR_WD)" 1b, 5b \n" + " "STR(PTR_WD)" 2b, 5b \n" " .previous \n" " .set pop \n" : [old] "=&r" (old), diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index e59cb6246f76..a25e0b73ee70 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -414,6 +414,24 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, return -ENOIOCTLCMD; } +/* + * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while + * the vCPU is running. + * + * This must be noinstr as instrumentation may make use of RCU, and this is not + * safe during the EQS. + */ +static int noinstr kvm_mips_vcpu_enter_exit(struct kvm_vcpu *vcpu) +{ + int ret; + + guest_state_enter_irqoff(); + ret = kvm_mips_callbacks->vcpu_run(vcpu); + guest_state_exit_irqoff(); + + return ret; +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { int r = -EINTR; @@ -434,7 +452,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) lose_fpu(1); local_irq_disable(); - guest_enter_irqoff(); + guest_timing_enter_irqoff(); trace_kvm_enter(vcpu); /* @@ -445,10 +463,23 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); - r = kvm_mips_callbacks->vcpu_run(vcpu); + r = kvm_mips_vcpu_enter_exit(vcpu); + + /* + * We must ensure that any pending interrupts are taken before + * we exit guest timing so that timer ticks are accounted as + * guest time. Transiently unmask interrupts so that any + * pending interrupts are taken. + * + * TODO: is there a barrier which ensures that pending interrupts are + * recognised? Currently this just hopes that the CPU takes any pending + * interrupts between the enable and disable. + */ + local_irq_enable(); + local_irq_disable(); trace_kvm_out(vcpu); - guest_exit_irqoff(); + guest_timing_exit_irqoff(); local_irq_enable(); out: @@ -1168,7 +1199,7 @@ static void kvm_mips_set_c0_status(void) /* * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV) */ -int kvm_mips_handle_exit(struct kvm_vcpu *vcpu) +static int __kvm_mips_handle_exit(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; u32 cause = vcpu->arch.host_cp0_cause; @@ -1357,6 +1388,17 @@ int kvm_mips_handle_exit(struct kvm_vcpu *vcpu) return ret; } +int noinstr kvm_mips_handle_exit(struct kvm_vcpu *vcpu) +{ + int ret; + + guest_state_exit_irqoff(); + ret = __kvm_mips_handle_exit(vcpu); + guest_state_enter_irqoff(); + + return ret; +} + /* Enable FPU for guest and restore context */ void kvm_own_fpu(struct kvm_vcpu *vcpu) { diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c index 4adca5abbc72..c706f5890a05 100644 --- a/arch/mips/kvm/vz.c +++ b/arch/mips/kvm/vz.c @@ -458,8 +458,8 @@ void kvm_vz_acquire_htimer(struct kvm_vcpu *vcpu) /** * _kvm_vz_save_htimer() - Switch to software emulation of guest timer. * @vcpu: Virtual CPU. - * @compare: Pointer to write compare value to. - * @cause: Pointer to write cause value to. + * @out_compare: Pointer to write compare value to. + * @out_cause: Pointer to write cause value to. * * Save VZ guest timer state and switch to software emulation of guest CP0 * timer. The hard timer must already be in use, so preemption should be @@ -1541,11 +1541,14 @@ static int kvm_trap_vz_handle_guest_exit(struct kvm_vcpu *vcpu) } /** - * kvm_trap_vz_handle_cop_unusuable() - Guest used unusable coprocessor. + * kvm_trap_vz_handle_cop_unusable() - Guest used unusable coprocessor. * @vcpu: Virtual CPU context. * * Handle when the guest attempts to use a coprocessor which hasn't been allowed * by the root context. + * + * Return: value indicating whether to resume the host or the guest + * (RESUME_HOST or RESUME_GUEST) */ static int kvm_trap_vz_handle_cop_unusable(struct kvm_vcpu *vcpu) { @@ -1592,6 +1595,9 @@ static int kvm_trap_vz_handle_cop_unusable(struct kvm_vcpu *vcpu) * * Handle when the guest attempts to use MSA when it is disabled in the root * context. + * + * Return: value indicating whether to resume the host or the guest + * (RESUME_HOST or RESUME_GUEST) */ static int kvm_trap_vz_handle_msa_disabled(struct kvm_vcpu *vcpu) { diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S index a46db0807195..7767137c3e49 100644 --- a/arch/mips/lib/csum_partial.S +++ b/arch/mips/lib/csum_partial.S @@ -347,7 +347,7 @@ EXPORT_SYMBOL(csum_partial) .if \mode == LEGACY_MODE; \ 9: insn reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, .L_exc; \ + PTR_WD 9b, .L_exc; \ .previous; \ /* This is enabled in EVA mode */ \ .else; \ @@ -356,7 +356,7 @@ EXPORT_SYMBOL(csum_partial) ((\to == USEROP) && (type == ST_INSN)); \ 9: __BUILD_EVA_INSN(insn##e, reg, addr); \ .section __ex_table,"a"; \ - PTR 9b, .L_exc; \ + PTR_WD 9b, .L_exc; \ .previous; \ .else; \ /* EVA without exception */ \ diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S index 277c32296636..18a43f2e29c8 100644 --- a/arch/mips/lib/memcpy.S +++ b/arch/mips/lib/memcpy.S @@ -116,7 +116,7 @@ .if \mode == LEGACY_MODE; \ 9: insn reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous; \ /* This is assembled in EVA mode */ \ .else; \ @@ -125,7 +125,7 @@ ((\to == USEROP) && (type == ST_INSN)); \ 9: __BUILD_EVA_INSN(insn##e, reg, addr); \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous; \ .else; \ /* \ diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S index b0baa3c79fad..0b342bae9a98 100644 --- a/arch/mips/lib/memset.S +++ b/arch/mips/lib/memset.S @@ -52,7 +52,7 @@ 9: ___BUILD_EVA_INSN(insn, reg, addr); \ .endif; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous .macro f_fill64 dst, offset, val, fixup, mode diff --git a/arch/mips/lib/strncpy_user.S b/arch/mips/lib/strncpy_user.S index 556acf684d7b..13aaa9927ad1 100644 --- a/arch/mips/lib/strncpy_user.S +++ b/arch/mips/lib/strncpy_user.S @@ -15,7 +15,7 @@ #define EX(insn,reg,addr,handler) \ 9: insn reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous /* @@ -59,7 +59,7 @@ LEAF(__strncpy_from_user_asm) jr ra .section __ex_table,"a" - PTR 1b, .Lfault + PTR_WD 1b, .Lfault .previous EXPORT_SYMBOL(__strncpy_from_user_asm) diff --git a/arch/mips/lib/strnlen_user.S b/arch/mips/lib/strnlen_user.S index 92b63f20ec05..6de31b616f9c 100644 --- a/arch/mips/lib/strnlen_user.S +++ b/arch/mips/lib/strnlen_user.S @@ -14,7 +14,7 @@ #define EX(insn,reg,addr,handler) \ 9: insn reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous /* diff --git a/arch/mips/loongson64/vbios_quirk.c b/arch/mips/loongson64/vbios_quirk.c index 9a29e94d3db1..3115d4de982c 100644 --- a/arch/mips/loongson64/vbios_quirk.c +++ b/arch/mips/loongson64/vbios_quirk.c @@ -3,7 +3,7 @@ #include <linux/pci.h> #include <loongson.h> -static void pci_fixup_radeon(struct pci_dev *pdev) +static void pci_fixup_video(struct pci_dev *pdev) { struct resource *res = &pdev->resource[PCI_ROM_RESOURCE]; @@ -22,8 +22,7 @@ static void pci_fixup_radeon(struct pci_dev *pdev) res->flags = IORESOURCE_MEM | IORESOURCE_ROM_SHADOW | IORESOURCE_PCI_FIXED; - dev_info(&pdev->dev, "BAR %d: assigned %pR for Radeon ROM\n", - PCI_ROM_RESOURCE, res); + dev_info(&pdev->dev, "Video device with shadowed ROM at %pR\n", res); } -DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_ATI, 0x9615, - PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_radeon); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_ATI, 0x9615, + PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); diff --git a/arch/mips/ralink/mt7621.c b/arch/mips/ralink/mt7621.c index d6efffd4dd20..fb0565bc34fd 100644 --- a/arch/mips/ralink/mt7621.c +++ b/arch/mips/ralink/mt7621.c @@ -22,7 +22,9 @@ #include "common.h" -static void *detect_magic __initdata = detect_memory_region; +#define MT7621_MEM_TEST_PATTERN 0xaa5555aa + +static u32 detect_magic __initdata; int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) { @@ -58,24 +60,32 @@ phys_addr_t mips_cpc_default_phys_base(void) panic("Cannot detect cpc address"); } +static bool __init mt7621_addr_wraparound_test(phys_addr_t size) +{ + void *dm = (void *)KSEG1ADDR(&detect_magic); + + if (CPHYSADDR(dm + size) >= MT7621_LOWMEM_MAX_SIZE) + return true; + __raw_writel(MT7621_MEM_TEST_PATTERN, dm); + if (__raw_readl(dm) != __raw_readl(dm + size)) + return false; + __raw_writel(~MT7621_MEM_TEST_PATTERN, dm); + return __raw_readl(dm) == __raw_readl(dm + size); +} + static void __init mt7621_memory_detect(void) { - void *dm = &detect_magic; phys_addr_t size; - for (size = 32 * SZ_1M; size < 256 * SZ_1M; size <<= 1) { - if (!__builtin_memcmp(dm, dm + size, sizeof(detect_magic))) - break; + for (size = 32 * SZ_1M; size <= 256 * SZ_1M; size <<= 1) { + if (mt7621_addr_wraparound_test(size)) { + memblock_add(MT7621_LOWMEM_BASE, size); + return; + } } - if ((size == 256 * SZ_1M) && - (CPHYSADDR(dm + size) < MT7621_LOWMEM_MAX_SIZE) && - __builtin_memcmp(dm, dm + size, sizeof(detect_magic))) { - memblock_add(MT7621_LOWMEM_BASE, MT7621_LOWMEM_MAX_SIZE); - memblock_add(MT7621_HIGHMEM_BASE, MT7621_HIGHMEM_SIZE); - } else { - memblock_add(MT7621_LOWMEM_BASE, size); - } + memblock_add(MT7621_LOWMEM_BASE, MT7621_LOWMEM_MAX_SIZE); + memblock_add(MT7621_HIGHMEM_BASE, MT7621_HIGHMEM_SIZE); } void __init ralink_of_remap(void) diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h index 0ec9cfc5131f..56ffd260c669 100644 --- a/arch/parisc/include/asm/bitops.h +++ b/arch/parisc/include/asm/bitops.h @@ -12,6 +12,14 @@ #include <asm/barrier.h> #include <linux/atomic.h> +/* compiler build environment sanity checks: */ +#if !defined(CONFIG_64BIT) && defined(__LP64__) +#error "Please use 'ARCH=parisc' to build the 32-bit kernel." +#endif +#if defined(CONFIG_64BIT) && !defined(__LP64__) +#error "Please use 'ARCH=parisc64' to build the 64-bit kernel." +#endif + /* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion * on use of volatile and __*_bit() (set/clear/change): * *_bit() want use of volatile. diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index ebf8a845b017..123d5f16cd9d 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -89,8 +89,8 @@ struct exception_table_entry { __asm__("1: " ldx " 0(" sr "%2),%0\n" \ "9:\n" \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ - : "=r"(__gu_val), "=r"(__gu_err) \ - : "r"(ptr), "1"(__gu_err)); \ + : "=r"(__gu_val), "+r"(__gu_err) \ + : "r"(ptr)); \ \ (val) = (__force __typeof__(*(ptr))) __gu_val; \ } @@ -123,8 +123,8 @@ struct exception_table_entry { "9:\n" \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ - : "=&r"(__gu_tmp.l), "=r"(__gu_err) \ - : "r"(ptr), "1"(__gu_err)); \ + : "=&r"(__gu_tmp.l), "+r"(__gu_err) \ + : "r"(ptr)); \ \ (val) = __gu_tmp.t; \ } @@ -135,13 +135,12 @@ struct exception_table_entry { #define __put_user_internal(sr, x, ptr) \ ({ \ ASM_EXCEPTIONTABLE_VAR(__pu_err); \ - __typeof__(*(ptr)) __x = (__typeof__(*(ptr)))(x); \ \ switch (sizeof(*(ptr))) { \ - case 1: __put_user_asm(sr, "stb", __x, ptr); break; \ - case 2: __put_user_asm(sr, "sth", __x, ptr); break; \ - case 4: __put_user_asm(sr, "stw", __x, ptr); break; \ - case 8: STD_USER(sr, __x, ptr); break; \ + case 1: __put_user_asm(sr, "stb", x, ptr); break; \ + case 2: __put_user_asm(sr, "sth", x, ptr); break; \ + case 4: __put_user_asm(sr, "stw", x, ptr); break; \ + case 8: STD_USER(sr, x, ptr); break; \ default: BUILD_BUG(); \ } \ \ @@ -150,7 +149,9 @@ struct exception_table_entry { #define __put_user(x, ptr) \ ({ \ - __put_user_internal("%%sr3,", x, ptr); \ + __typeof__(&*(ptr)) __ptr = ptr; \ + __typeof__(*(__ptr)) __x = (__typeof__(*(__ptr)))(x); \ + __put_user_internal("%%sr3,", __x, __ptr); \ }) #define __put_kernel_nofault(dst, src, type, err_label) \ @@ -180,8 +181,8 @@ struct exception_table_entry { "1: " stx " %2,0(" sr "%1)\n" \ "9:\n" \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ - : "=r"(__pu_err) \ - : "r"(ptr), "r"(x), "0"(__pu_err)) + : "+r"(__pu_err) \ + : "r"(ptr), "r"(x)) #if !defined(CONFIG_64BIT) @@ -193,8 +194,8 @@ struct exception_table_entry { "9:\n" \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ - : "=r"(__pu_err) \ - : "r"(ptr), "r"(__val), "0"(__pu_err)); \ + : "+r"(__pu_err) \ + : "r"(ptr), "r"(__val)); \ } while (0) #endif /* !defined(CONFIG_64BIT) */ diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index 237d20dd5622..286cec4d86d7 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -340,7 +340,7 @@ static int emulate_stw(struct pt_regs *regs, int frreg, int flop) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r22", "r1", FIXUP_BRANCH_CLOBBER ); - return 0; + return ret; } static int emulate_std(struct pt_regs *regs, int frreg, int flop) { @@ -397,7 +397,7 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) __asm__ __volatile__ ( " mtsp %4, %%sr1\n" " zdep %2, 29, 2, %%r19\n" -" dep %%r0, 31, 2, %2\n" +" dep %%r0, 31, 2, %3\n" " mtsar %%r19\n" " zvdepi -2, 32, %%r19\n" "1: ldw 0(%%sr1,%3),%%r20\n" @@ -409,7 +409,7 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) " andcm %%r21, %%r19, %%r21\n" " or %1, %%r20, %1\n" " or %2, %%r21, %2\n" -"3: stw %1,0(%%sr1,%1)\n" +"3: stw %1,0(%%sr1,%3)\n" "4: stw %%r1,4(%%sr1,%3)\n" "5: stw %2,8(%%sr1,%3)\n" " copy %%r0, %0\n" @@ -596,7 +596,6 @@ void handle_unaligned(struct pt_regs *regs) ret = ERR_NOTHANDLED; /* "undefined", but lets kill them. */ break; } -#ifdef CONFIG_PA20 switch (regs->iir & OPCODE2_MASK) { case OPCODE_FLDD_L: @@ -607,22 +606,23 @@ void handle_unaligned(struct pt_regs *regs) flop=1; ret = emulate_std(regs, R2(regs->iir),1); break; +#ifdef CONFIG_PA20 case OPCODE_LDD_L: ret = emulate_ldd(regs, R2(regs->iir),0); break; case OPCODE_STD_L: ret = emulate_std(regs, R2(regs->iir),0); break; - } #endif + } switch (regs->iir & OPCODE3_MASK) { case OPCODE_FLDW_L: flop=1; - ret = emulate_ldw(regs, R2(regs->iir),0); + ret = emulate_ldw(regs, R2(regs->iir), 1); break; case OPCODE_LDW_M: - ret = emulate_ldw(regs, R2(regs->iir),1); + ret = emulate_ldw(regs, R2(regs->iir), 0); break; case OPCODE_FSTW_L: diff --git a/arch/parisc/lib/iomap.c b/arch/parisc/lib/iomap.c index 367f6397bda7..860385058085 100644 --- a/arch/parisc/lib/iomap.c +++ b/arch/parisc/lib/iomap.c @@ -346,6 +346,16 @@ u64 ioread64be(const void __iomem *addr) return *((u64 *)addr); } +u64 ioread64_lo_hi(const void __iomem *addr) +{ + u32 low, high; + + low = ioread32(addr); + high = ioread32(addr + sizeof(u32)); + + return low + ((u64)high << 32); +} + u64 ioread64_hi_lo(const void __iomem *addr) { u32 low, high; @@ -419,6 +429,12 @@ void iowrite64be(u64 datum, void __iomem *addr) } } +void iowrite64_lo_hi(u64 val, void __iomem *addr) +{ + iowrite32(val, addr); + iowrite32(val >> 32, addr + sizeof(u32)); +} + void iowrite64_hi_lo(u64 val, void __iomem *addr) { iowrite32(val >> 32, addr + sizeof(u32)); @@ -530,6 +546,7 @@ EXPORT_SYMBOL(ioread32); EXPORT_SYMBOL(ioread32be); EXPORT_SYMBOL(ioread64); EXPORT_SYMBOL(ioread64be); +EXPORT_SYMBOL(ioread64_lo_hi); EXPORT_SYMBOL(ioread64_hi_lo); EXPORT_SYMBOL(iowrite8); EXPORT_SYMBOL(iowrite16); @@ -538,6 +555,7 @@ EXPORT_SYMBOL(iowrite32); EXPORT_SYMBOL(iowrite32be); EXPORT_SYMBOL(iowrite64); EXPORT_SYMBOL(iowrite64be); +EXPORT_SYMBOL(iowrite64_lo_hi); EXPORT_SYMBOL(iowrite64_hi_lo); EXPORT_SYMBOL(ioread8_rep); EXPORT_SYMBOL(ioread16_rep); diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 1ae31db9988f..1dc2e88e7b04 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -337,9 +337,9 @@ static void __init setup_bootmem(void) static bool kernel_set_to_readonly; -static void __init map_pages(unsigned long start_vaddr, - unsigned long start_paddr, unsigned long size, - pgprot_t pgprot, int force) +static void __ref map_pages(unsigned long start_vaddr, + unsigned long start_paddr, unsigned long size, + pgprot_t pgprot, int force) { pmd_t *pmd; pte_t *pg_table; @@ -449,7 +449,7 @@ void __init set_kernel_text_rw(int enable_read_write) flush_tlb_all(); } -void __ref free_initmem(void) +void free_initmem(void) { unsigned long init_begin = (unsigned long)__init_begin; unsigned long init_end = (unsigned long)__init_end; @@ -463,7 +463,6 @@ void __ref free_initmem(void) /* The init text pages are marked R-X. We have to * flush the icache and mark them RW- * - * This is tricky, because map_pages is in the init section. * Do a dummy remap of the data section first (the data * section is already PAGE_KERNEL) to pull in the TLB entries * for map_kernel */ diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h index 7be27862329f..78c6a5fde1d6 100644 --- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h @@ -223,6 +223,8 @@ static __always_inline void update_user_segments(u32 val) update_user_segment(15, val); } +int __init find_free_bat(void); +unsigned int bat_block_size(unsigned long base, unsigned long top); #endif /* !__ASSEMBLY__ */ /* We happily ignore the smaller BATs on 601, we don't actually use diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 609c80f67194..f8b94f78403f 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -178,6 +178,7 @@ static inline bool pte_user(pte_t pte) #ifndef __ASSEMBLY__ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index ba5b1becf518..006cbec70ffe 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -202,7 +202,6 @@ static inline struct subpage_prot_table *mm_ctx_subpage_prot(mm_context_t *ctx) /* * The current system page and segment sizes */ -extern int mmu_linear_psize; extern int mmu_virtual_psize; extern int mmu_vmalloc_psize; extern int mmu_io_psize; @@ -213,6 +212,7 @@ extern int mmu_io_psize; #define mmu_virtual_psize MMU_PAGE_4K #endif #endif +extern int mmu_linear_psize; extern int mmu_vmemmap_psize; /* MMU initialization */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 33e073d6b0c4..875730d5af40 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1082,6 +1082,8 @@ static inline int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t p return hash__map_kernel_page(ea, pa, prot); } +void unmap_kernel_page(unsigned long va); + static inline int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys) diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 947b5b9c4424..a832aeafe560 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -111,8 +111,10 @@ static inline void __set_fixmap(enum fixed_addresses idx, BUILD_BUG_ON(idx >= __end_of_fixed_addresses); else if (WARN_ON(idx >= __end_of_fixed_addresses)) return; - - map_kernel_page(__fix_to_virt(idx), phys, flags); + if (pgprot_val(flags)) + map_kernel_page(__fix_to_virt(idx), phys, flags); + else + unmap_kernel_page(__fix_to_virt(idx)); } #define __early_set_fixmap __set_fixmap diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index a58fb4aa6c81..674e5aaafcbd 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -473,7 +473,7 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs) return !(regs->msr & MSR_EE); } -static inline bool should_hard_irq_enable(void) +static __always_inline bool should_hard_irq_enable(void) { return false; } diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h index 7a90000f8d15..f83866a19e87 100644 --- a/arch/powerpc/include/asm/kexec_ranges.h +++ b/arch/powerpc/include/asm/kexec_ranges.h @@ -9,7 +9,7 @@ struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges); int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size); int add_tce_mem_ranges(struct crash_mem **mem_ranges); int add_initrd_mem_range(struct crash_mem **mem_ranges); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU int add_htab_mem_range(struct crash_mem **mem_ranges); #else static inline int add_htab_mem_range(struct crash_mem **mem_ranges) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index fe07558173ef..827038a33064 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -39,7 +39,6 @@ struct kvm_nested_guest { pgd_t *shadow_pgtable; /* our page table for this guest */ u64 l1_gr_to_hr; /* L1's addr of part'n-scoped table */ u64 process_table; /* process table entry for this guest */ - u64 hfscr; /* HFSCR that the L1 requested for this nested guest */ long refcnt; /* number of pointers to this struct */ struct mutex tlb_lock; /* serialize page faults and tlbies */ struct kvm_nested_guest *next; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index a770443cd6e0..d9bf60bf0816 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -818,6 +818,7 @@ struct kvm_vcpu_arch { /* For support of nested guests */ struct kvm_nested_guest *nested; + u64 nested_hfscr; /* HFSCR that the L1 requested for the nested guest */ u32 nested_vcpu_id; gpa_t nested_io_gpr; #endif diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index b67742e2a9b2..d959c2a73fbf 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -64,6 +64,7 @@ extern int icache_44x_need_flush; #ifndef __ASSEMBLY__ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index a3313e853e5e..2816d158280a 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -308,6 +308,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define __swp_entry_to_pte(x) __pte((x).val) int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); extern int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index efad07081cc0..9675303b724e 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -500,6 +500,7 @@ #define PPC_RAW_LDX(r, base, b) (0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_LHZ(r, base, i) (0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LHBRX(r, base, b) (0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LWBRX(r, base, b) (0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_LDBRX(r, base, b) (0x7c000428 | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_STWCX(s, a, b) (0x7c00012d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_CMPWI(a, i) (0x2c000000 | ___PPC_RA(a) | IMM_L(i)) diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index 52d05b465e3e..25fc8ad9a27a 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -90,7 +90,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long val, mask = -1UL; unsigned int n = 6; - if (is_32bit_task()) + if (is_tsk_32bit_task(task)) mask = 0xffffffff; while (n--) { @@ -105,7 +105,7 @@ static inline void syscall_get_arguments(struct task_struct *task, static inline int syscall_get_arch(struct task_struct *task) { - if (is_32bit_task()) + if (is_tsk_32bit_task(task)) return AUDIT_ARCH_PPC; else if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) return AUDIT_ARCH_PPC64LE; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 5725029aaa29..d6e649b3c70b 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -168,8 +168,10 @@ static inline bool test_thread_local_flags(unsigned int flags) #ifdef CONFIG_COMPAT #define is_32bit_task() (test_thread_flag(TIF_32BIT)) +#define is_tsk_32bit_task(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT)) #else #define is_32bit_task() (IS_ENABLED(CONFIG_PPC32)) +#define is_tsk_32bit_task(tsk) (IS_ENABLED(CONFIG_PPC32)) #endif #if defined(CONFIG_PPC64) diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index fa84744d6b24..b876ef8c70a7 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -421,14 +421,14 @@ InstructionTLBMiss: */ /* Get PTE (linux-style) and check access */ mfspr r3,SPRN_IMISS -#ifdef CONFIG_MODULES +#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 #endif mfspr r2, SPRN_SDR1 li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER rlwinm r2, r2, 28, 0xfffff000 -#ifdef CONFIG_MODULES +#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index 92088f848266..7bab2d7de372 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -30,6 +30,7 @@ COMPAT_SYS_CALL_TABLE: .ifc \srr,srr mfspr r11,SPRN_SRR0 ld r12,_NIP(r1) + clrrdi r11,r11,2 clrrdi r12,r12,2 100: tdne r11,r12 EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) @@ -40,6 +41,7 @@ COMPAT_SYS_CALL_TABLE: .else mfspr r11,SPRN_HSRR0 ld r12,_NIP(r1) + clrrdi r11,r11,2 clrrdi r12,r12,2 100: tdne r11,r12 EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 62361cc7281c..cd0b8b71ecdd 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -649,8 +649,9 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) __this_cpu_inc(irq_stat.timer_irqs_event); } else { now = *next_tb - now; - if (now <= decrementer_max) - set_dec_or_work(now); + if (now > decrementer_max) + now = decrementer_max; + set_dec_or_work(now); __this_cpu_inc(irq_stat.timer_irqs_others); } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index d1817cd9a691..84c89f08ae9a 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1816,7 +1816,6 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) { - struct kvm_nested_guest *nested = vcpu->arch.nested; int r; int srcu_idx; @@ -1922,7 +1921,7 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) * it into a HEAI. */ if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) || - (nested->hfscr & (1UL << cause))) { + (vcpu->arch.nested_hfscr & (1UL << cause))) { vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST; /* diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 8f8daaeeb3b7..9d373f8963ee 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -363,7 +363,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* set L1 state to L2 state */ vcpu->arch.nested = l2; vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token; - l2->hfscr = l2_hv.hfscr; + vcpu->arch.nested_hfscr = l2_hv.hfscr; vcpu->arch.regs = l2_regs; /* Guest must always run with ME enabled, HV disabled. */ diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index a94b0cd0bdc5..bd3734d5be89 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -3264,12 +3264,14 @@ void emulate_update_regs(struct pt_regs *regs, struct instruction_op *op) case BARRIER_EIEIO: eieio(); break; +#ifdef CONFIG_PPC64 case BARRIER_LWSYNC: asm volatile("lwsync" : : : "memory"); break; case BARRIER_PTESYNC: asm volatile("ptesync" : : : "memory"); break; +#endif } break; diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 94045b265b6b..203735caf691 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -76,7 +76,7 @@ unsigned long p_block_mapped(phys_addr_t pa) return 0; } -static int __init find_free_bat(void) +int __init find_free_bat(void) { int b; int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; @@ -100,7 +100,7 @@ static int __init find_free_bat(void) * - block size has to be a power of two. This is calculated by finding the * highest bit set to 1. */ -static unsigned int block_size(unsigned long base, unsigned long top) +unsigned int bat_block_size(unsigned long base, unsigned long top) { unsigned int max_size = SZ_256M; unsigned int base_shift = (ffs(base) - 1) & 31; @@ -145,7 +145,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to int idx; while ((idx = find_free_bat()) != -1 && base != top) { - unsigned int size = block_size(base, top); + unsigned int size = bat_block_size(base, top); if (size < 128 << 10) break; @@ -201,12 +201,12 @@ void mmu_mark_initmem_nx(void) unsigned long size; for (i = 0; i < nb - 1 && base < top;) { - size = block_size(base, top); + size = bat_block_size(base, top); setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT); base += size; } if (base < top) { - size = block_size(base, top); + size = bat_block_size(base, top); if ((top - base) > size) { size <<= 1; if (strict_kernel_rwx_enabled() && base + size > border) diff --git a/arch/powerpc/mm/kasan/book3s_32.c b/arch/powerpc/mm/kasan/book3s_32.c index 35b287b0a8da..450a67ef0bbe 100644 --- a/arch/powerpc/mm/kasan/book3s_32.c +++ b/arch/powerpc/mm/kasan/book3s_32.c @@ -10,48 +10,51 @@ int __init kasan_init_region(void *start, size_t size) { unsigned long k_start = (unsigned long)kasan_mem_to_shadow(start); unsigned long k_end = (unsigned long)kasan_mem_to_shadow(start + size); - unsigned long k_cur = k_start; - int k_size = k_end - k_start; - int k_size_base = 1 << (ffs(k_size) - 1); + unsigned long k_nobat = k_start; + unsigned long k_cur; + phys_addr_t phys; int ret; - void *block; - block = memblock_alloc(k_size, k_size_base); - - if (block && k_size_base >= SZ_128K && k_start == ALIGN(k_start, k_size_base)) { - int shift = ffs(k_size - k_size_base); - int k_size_more = shift ? 1 << (shift - 1) : 0; - - setbat(-1, k_start, __pa(block), k_size_base, PAGE_KERNEL); - if (k_size_more >= SZ_128K) - setbat(-1, k_start + k_size_base, __pa(block) + k_size_base, - k_size_more, PAGE_KERNEL); - if (v_block_mapped(k_start)) - k_cur = k_start + k_size_base; - if (v_block_mapped(k_start + k_size_base)) - k_cur = k_start + k_size_base + k_size_more; - - update_bats(); + while (k_nobat < k_end) { + unsigned int k_size = bat_block_size(k_nobat, k_end); + int idx = find_free_bat(); + + if (idx == -1) + break; + if (k_size < SZ_128K) + break; + phys = memblock_phys_alloc_range(k_size, k_size, 0, + MEMBLOCK_ALLOC_ANYWHERE); + if (!phys) + break; + + setbat(idx, k_nobat, phys, k_size, PAGE_KERNEL); + k_nobat += k_size; } + if (k_nobat != k_start) + update_bats(); - if (!block) - block = memblock_alloc(k_size, PAGE_SIZE); - if (!block) - return -ENOMEM; + if (k_nobat < k_end) { + phys = memblock_phys_alloc_range(k_end - k_nobat, PAGE_SIZE, 0, + MEMBLOCK_ALLOC_ANYWHERE); + if (!phys) + return -ENOMEM; + } ret = kasan_init_shadow_page_tables(k_start, k_end); if (ret) return ret; - kasan_update_early_region(k_start, k_cur, __pte(0)); + kasan_update_early_region(k_start, k_nobat, __pte(0)); - for (; k_cur < k_end; k_cur += PAGE_SIZE) { + for (k_cur = k_nobat; k_cur < k_end; k_cur += PAGE_SIZE) { pmd_t *pmd = pmd_off_k(k_cur); - void *va = block + k_cur - k_start; - pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL); + pte_t pte = pfn_pte(PHYS_PFN(phys + k_cur - k_nobat), PAGE_KERNEL); __set_pte_at(&init_mm, k_cur, pte_offset_kernel(pmd, k_cur), pte, 0); } flush_tlb_kernel_range(k_start, k_end); + memset(kasan_mem_to_shadow(start), 0, k_end - k_start); + return 0; } diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index abb3198bd277..6ec5a7dd7913 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -206,6 +206,15 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, __set_pte_at(mm, addr, ptep, pte, 0); } +void unmap_kernel_page(unsigned long va) +{ + pmd_t *pmdp = pmd_off_k(va); + pte_t *ptep = pte_offset_kernel(pmdp, va); + + pte_clear(&init_mm, va, ptep); + flush_tlb_kernel_range(va, va + PAGE_SIZE); +} + /* * This is called when relaxing access to a PTE. It's also called in the page * fault path when we don't hit any of the major fault cases, ie, a minor diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index d6ffdd0f2309..56dd1f4e3e44 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -23,15 +23,15 @@ static void bpf_jit_fill_ill_insns(void *area, unsigned int size) memset32(area, BREAKPOINT_INSTRUCTION, size / 4); } -/* Fix the branch target addresses for subprog calls */ -static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image, - struct codegen_context *ctx, u32 *addrs) +/* Fix updated addresses (for subprog calls, ldimm64, et al) during extra pass */ +static int bpf_jit_fixup_addresses(struct bpf_prog *fp, u32 *image, + struct codegen_context *ctx, u32 *addrs) { const struct bpf_insn *insn = fp->insnsi; bool func_addr_fixed; u64 func_addr; u32 tmp_idx; - int i, ret; + int i, j, ret; for (i = 0; i < fp->len; i++) { /* @@ -66,6 +66,23 @@ static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image, * of the JITed sequence remains unchanged. */ ctx->idx = tmp_idx; + } else if (insn[i].code == (BPF_LD | BPF_IMM | BPF_DW)) { + tmp_idx = ctx->idx; + ctx->idx = addrs[i] / 4; +#ifdef CONFIG_PPC32 + PPC_LI32(ctx->b2p[insn[i].dst_reg] - 1, (u32)insn[i + 1].imm); + PPC_LI32(ctx->b2p[insn[i].dst_reg], (u32)insn[i].imm); + for (j = ctx->idx - addrs[i] / 4; j < 4; j++) + EMIT(PPC_RAW_NOP()); +#else + func_addr = ((u64)(u32)insn[i].imm) | (((u64)(u32)insn[i + 1].imm) << 32); + PPC_LI64(b2p[insn[i].dst_reg], func_addr); + /* overwrite rest with nops */ + for (j = ctx->idx - addrs[i] / 4; j < 5; j++) + EMIT(PPC_RAW_NOP()); +#endif + ctx->idx = tmp_idx; + i++; } } @@ -200,13 +217,13 @@ skip_init_ctx: /* * Do not touch the prologue and epilogue as they will remain * unchanged. Only fix the branch target address for subprog - * calls in the body. + * calls in the body, and ldimm64 instructions. * * This does not change the offsets and lengths of the subprog * call instruction sequences and hence, the size of the JITed * image as well. */ - bpf_jit_fixup_subprog_calls(fp, code_base, &cgctx, addrs); + bpf_jit_fixup_addresses(fp, code_base, &cgctx, addrs); /* There is no need to perform the usual passes. */ goto skip_codegen_passes; diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index faaebd446cad..cf8dd8aea386 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -191,6 +191,9 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun if (image && rel < 0x2000000 && rel >= -0x2000000) { PPC_BL_ABS(func); + EMIT(PPC_RAW_NOP()); + EMIT(PPC_RAW_NOP()); + EMIT(PPC_RAW_NOP()); } else { /* Load function address into r0 */ EMIT(PPC_RAW_LIS(_R0, IMM_H(func))); @@ -290,6 +293,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * bool func_addr_fixed; u64 func_addr; u32 true_cond; + u32 tmp_idx; + int j; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -905,8 +910,12 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * * 16 byte instruction that uses two 'struct bpf_insn' */ case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */ + tmp_idx = ctx->idx; PPC_LI32(dst_reg_h, (u32)insn[i + 1].imm); PPC_LI32(dst_reg, (u32)insn[i].imm); + /* padding to allow full 4 instructions for later patching */ + for (j = ctx->idx - tmp_idx; j < 4; j++) + EMIT(PPC_RAW_NOP()); /* Adjust for two bpf instructions */ addrs[++i] = ctx->idx * 4; break; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 9eae8d8ed340..e1e8c934308a 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -319,6 +319,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * u64 imm64; u32 true_cond; u32 tmp_idx; + int j; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -633,17 +634,21 @@ bpf_alu32_trunc: EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1])); break; case 64: - /* - * Way easier and faster(?) to store the value - * into stack and then use ldbrx - * - * ctx->seen will be reliable in pass2, but - * the instructions generated will remain the - * same across all passes - */ + /* Store the value to stack and then use byte-reverse loads */ PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx)); EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx))); - EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); + } else { + EMIT(PPC_RAW_LWBRX(dst_reg, 0, b2p[TMP_REG_1])); + if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) + EMIT(PPC_RAW_SLDI(dst_reg, dst_reg, 32)); + EMIT(PPC_RAW_LI(b2p[TMP_REG_2], 4)); + EMIT(PPC_RAW_LWBRX(b2p[TMP_REG_2], b2p[TMP_REG_2], b2p[TMP_REG_1])); + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + EMIT(PPC_RAW_SLDI(b2p[TMP_REG_2], b2p[TMP_REG_2], 32)); + EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_2])); + } break; } break; @@ -848,9 +853,13 @@ emit_clear: case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */ imm64 = ((u64)(u32) insn[i].imm) | (((u64)(u32) insn[i+1].imm) << 32); + tmp_idx = ctx->idx; + PPC_LI64(dst_reg, imm64); + /* padding to allow full 5 instructions for later patching */ + for (j = ctx->idx - tmp_idx; j < 5; j++) + EMIT(PPC_RAW_NOP()); /* Adjust for two bpf instructions */ addrs[++i] = ctx->idx * 4; - PPC_LI64(dst_reg, imm64); break; /* diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index a684901b6965..b5b42cf0a703 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -776,6 +776,34 @@ static void pmao_restore_workaround(bool ebb) mtspr(SPRN_PMC6, pmcs[5]); } +/* + * If the perf subsystem wants performance monitor interrupts as soon as + * possible (e.g., to sample the instruction address and stack chain), + * this should return true. The IRQ masking code can then enable MSR[EE] + * in some places (e.g., interrupt handlers) that allows PMI interrupts + * through to improve accuracy of profiles, at the cost of some performance. + * + * The PMU counters can be enabled by other means (e.g., sysfs raw SPR + * access), but in that case there is no need for prompt PMI handling. + * + * This currently returns true if any perf counter is being used. It + * could possibly return false if only events are being counted rather than + * samples being taken, but for now this is good enough. + */ +bool power_pmu_wants_prompt_pmi(void) +{ + struct cpu_hw_events *cpuhw; + + /* + * This could simply test local_paca->pmcregs_in_use if that were not + * under ifdef KVM. + */ + if (!ppmu) + return false; + + cpuhw = this_cpu_ptr(&cpu_hw_events); + return cpuhw->n_events; +} #endif /* CONFIG_PPC64 */ static void perf_event_interrupt(struct pt_regs *regs); @@ -1327,9 +1355,20 @@ static void power_pmu_disable(struct pmu *pmu) * Otherwise provide a warning if there is PMI pending, but * no counter is found overflown. */ - if (any_pmc_overflown(cpuhw)) - clear_pmi_irq_pending(); - else + if (any_pmc_overflown(cpuhw)) { + /* + * Since power_pmu_disable runs under local_irq_save, it + * could happen that code hits a PMC overflow without PMI + * pending in paca. Hence only clear PMI pending if it was + * set. + * + * If a PMI is pending, then MSR[EE] must be disabled (because + * the masked PMI handler disabling EE). So it is safe to + * call clear_pmi_irq_pending(). + */ + if (pmi_irq_pending()) + clear_pmi_irq_pending(); + } else WARN_ON(pmi_irq_pending()); val = mmcra = cpuhw->mmcr.mmcra; @@ -2438,36 +2477,6 @@ static void perf_event_interrupt(struct pt_regs *regs) perf_sample_event_took(sched_clock() - start_clock); } -/* - * If the perf subsystem wants performance monitor interrupts as soon as - * possible (e.g., to sample the instruction address and stack chain), - * this should return true. The IRQ masking code can then enable MSR[EE] - * in some places (e.g., interrupt handlers) that allows PMI interrupts - * though to improve accuracy of profiles, at the cost of some performance. - * - * The PMU counters can be enabled by other means (e.g., sysfs raw SPR - * access), but in that case there is no need for prompt PMI handling. - * - * This currently returns true if any perf counter is being used. It - * could possibly return false if only events are being counted rather than - * samples being taken, but for now this is good enough. - */ -bool power_pmu_wants_prompt_pmi(void) -{ - struct cpu_hw_events *cpuhw; - - /* - * This could simply test local_paca->pmcregs_in_use if that were not - * under ifdef KVM. - */ - - if (!ppmu) - return false; - - cpuhw = this_cpu_ptr(&cpu_hw_events); - return cpuhw->n_events; -} - static int power_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 8a107ed18b0d..7d81102cffd4 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -50,6 +50,12 @@ riscv-march-$(CONFIG_ARCH_RV32I) := rv32ima riscv-march-$(CONFIG_ARCH_RV64I) := rv64ima riscv-march-$(CONFIG_FPU) := $(riscv-march-y)fd riscv-march-$(CONFIG_RISCV_ISA_C) := $(riscv-march-y)c + +# Newer binutils versions default to ISA spec version 20191213 which moves some +# instructions from the I extension to the Zicsr and Zifencei extensions. +toolchain-need-zicsr-zifencei := $(call cc-option-yn, -march=$(riscv-march-y)_zicsr_zifencei) +riscv-march-$(toolchain-need-zicsr-zifencei) := $(riscv-march-y)_zicsr_zifencei + KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y)) KBUILD_AFLAGS += -march=$(riscv-march-y) diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi index 56f57118c633..44d338514761 100644 --- a/arch/riscv/boot/dts/canaan/k210.dtsi +++ b/arch/riscv/boot/dts/canaan/k210.dtsi @@ -113,7 +113,8 @@ compatible = "canaan,k210-plic", "sifive,plic-1.0.0"; reg = <0xC000000 0x4000000>; interrupt-controller; - interrupts-extended = <&cpu0_intc 11>, <&cpu1_intc 11>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>; riscv,ndev = <65>; }; diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig index 2a82a3b2992b..af64b95e88cc 100644 --- a/arch/riscv/configs/nommu_k210_sdcard_defconfig +++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig @@ -23,7 +23,7 @@ CONFIG_SLOB=y CONFIG_SOC_CANAAN=y CONFIG_SMP=y CONFIG_NR_CPUS=2 -CONFIG_CMDLINE="earlycon console=ttySIF0 rootdelay=2 root=/dev/mmcblk0p1 ro" +CONFIG_CMDLINE="earlycon console=ttySIF0 root=/dev/mmcblk0p1 rootwait ro" CONFIG_CMDLINE_FORCE=y # CONFIG_SECCOMP is not set # CONFIG_STACKPROTECTOR is not set diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 160e3a1e8f8b..004372f8da54 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -119,7 +119,7 @@ extern phys_addr_t phys_ram_base; ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) #define is_linear_mapping(x) \ - ((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < kernel_map.virt_addr)) + ((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < PAGE_OFFSET + KERN_VIRT_SIZE)) #define linear_mapping_pa_to_va(x) ((void *)((unsigned long)(x) + kernel_map.va_pa_offset)) #define kernel_mapping_pa_to_va(y) ({ \ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 7e949f25c933..e3549e50de95 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -13,6 +13,7 @@ #ifndef CONFIG_MMU #define KERNEL_LINK_ADDR PAGE_OFFSET +#define KERN_VIRT_SIZE (UL(-1)) #else #define ADDRESS_SPACE_END (UL(-1)) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 612556faa527..ffc87e76b1dd 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -51,6 +51,8 @@ obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o +obj-$(CONFIG_TRACE_IRQFLAGS) += trace_irq.o + obj-$(CONFIG_RISCV_BASE_PMU) += perf_event.o obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c index be7f05b542bb..f7a832e3a1d1 100644 --- a/arch/riscv/kernel/cpu-hotplug.c +++ b/arch/riscv/kernel/cpu-hotplug.c @@ -12,6 +12,7 @@ #include <linux/sched/hotplug.h> #include <asm/irq.h> #include <asm/cpu_ops.h> +#include <asm/numa.h> #include <asm/sbi.h> bool cpu_has_hotplug(unsigned int cpu) @@ -40,6 +41,7 @@ int __cpu_disable(void) return ret; remove_cpu_topology(cpu); + numa_remove_cpu(cpu); set_cpu_online(cpu, false); irq_migrate_all_off_this_cpu(); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index ed29e9c8f660..d6a46ed0bf05 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -108,7 +108,7 @@ _save_context: .option pop #ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_off + call __trace_hardirqs_off #endif #ifdef CONFIG_CONTEXT_TRACKING @@ -143,7 +143,7 @@ skip_context_tracking: li t0, EXC_BREAKPOINT beq s4, t0, 1f #ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_on + call __trace_hardirqs_on #endif csrs CSR_STATUS, SR_IE @@ -234,7 +234,7 @@ ret_from_exception: REG_L s0, PT_STATUS(sp) csrc CSR_STATUS, SR_IE #ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_off + call __trace_hardirqs_off #endif #ifdef CONFIG_RISCV_M_MODE /* the MPP value is too large to be used as an immediate arg for addi */ @@ -270,10 +270,10 @@ restore_all: REG_L s1, PT_STATUS(sp) andi t0, s1, SR_PIE beqz t0, 1f - call trace_hardirqs_on + call __trace_hardirqs_on j 2f 1: - call trace_hardirqs_off + call __trace_hardirqs_off 2: #endif REG_L a0, PT_STATUS(sp) diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 2363b43312fc..ec07f991866a 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -22,14 +22,13 @@ add \reg, \reg, t0 .endm .macro XIP_FIXUP_FLASH_OFFSET reg - la t1, __data_loc - li t0, XIP_OFFSET_MASK - and t1, t1, t0 - li t1, XIP_OFFSET - sub t0, t0, t1 - sub \reg, \reg, t0 + la t0, __data_loc + REG_L t1, _xip_phys_offset + sub \reg, \reg, t1 + add \reg, \reg, t0 .endm _xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET +_xip_phys_offset: .dword CONFIG_XIP_PHYS_ADDR + XIP_OFFSET #else .macro XIP_FIXUP_OFFSET reg .endm diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index f72527fcb347..775d3322b422 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -5,6 +5,7 @@ * Copyright (c) 2020 Western Digital Corporation or its affiliates. */ +#include <linux/bits.h> #include <linux/init.h> #include <linux/pm.h> #include <linux/reboot.h> @@ -85,7 +86,7 @@ static unsigned long __sbi_v01_cpumask_to_hartmask(const struct cpumask *cpu_mas pr_warn("Unable to send any request to hartid > BITS_PER_LONG for SBI v0.1\n"); break; } - hmask |= 1 << hartid; + hmask |= BIT(hartid); } return hmask; @@ -160,7 +161,7 @@ static int __sbi_send_ipi_v01(const struct cpumask *cpu_mask) { unsigned long hart_mask; - if (!cpu_mask) + if (!cpu_mask || cpumask_empty(cpu_mask)) cpu_mask = cpu_online_mask; hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask); @@ -176,7 +177,7 @@ static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask, int result = 0; unsigned long hart_mask; - if (!cpu_mask) + if (!cpu_mask || cpumask_empty(cpu_mask)) cpu_mask = cpu_online_mask; hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask); @@ -249,26 +250,37 @@ static void __sbi_set_timer_v02(uint64_t stime_value) static int __sbi_send_ipi_v02(const struct cpumask *cpu_mask) { - unsigned long hartid, cpuid, hmask = 0, hbase = 0; + unsigned long hartid, cpuid, hmask = 0, hbase = 0, htop = 0; struct sbiret ret = {0}; int result; - if (!cpu_mask) + if (!cpu_mask || cpumask_empty(cpu_mask)) cpu_mask = cpu_online_mask; for_each_cpu(cpuid, cpu_mask) { hartid = cpuid_to_hartid_map(cpuid); - if (hmask && ((hbase + BITS_PER_LONG) <= hartid)) { - ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI, - hmask, hbase, 0, 0, 0, 0); - if (ret.error) - goto ecall_failed; - hmask = 0; - hbase = 0; + if (hmask) { + if (hartid + BITS_PER_LONG <= htop || + hbase + BITS_PER_LONG <= hartid) { + ret = sbi_ecall(SBI_EXT_IPI, + SBI_EXT_IPI_SEND_IPI, hmask, + hbase, 0, 0, 0, 0); + if (ret.error) + goto ecall_failed; + hmask = 0; + } else if (hartid < hbase) { + /* shift the mask to fit lower hartid */ + hmask <<= hbase - hartid; + hbase = hartid; + } } - if (!hmask) + if (!hmask) { hbase = hartid; - hmask |= 1UL << (hartid - hbase); + htop = hartid; + } else if (hartid > htop) { + htop = hartid; + } + hmask |= BIT(hartid - hbase); } if (hmask) { @@ -344,25 +356,35 @@ static int __sbi_rfence_v02(int fid, const struct cpumask *cpu_mask, unsigned long start, unsigned long size, unsigned long arg4, unsigned long arg5) { - unsigned long hartid, cpuid, hmask = 0, hbase = 0; + unsigned long hartid, cpuid, hmask = 0, hbase = 0, htop = 0; int result; - if (!cpu_mask) + if (!cpu_mask || cpumask_empty(cpu_mask)) cpu_mask = cpu_online_mask; for_each_cpu(cpuid, cpu_mask) { hartid = cpuid_to_hartid_map(cpuid); - if (hmask && ((hbase + BITS_PER_LONG) <= hartid)) { - result = __sbi_rfence_v02_call(fid, hmask, hbase, - start, size, arg4, arg5); - if (result) - return result; - hmask = 0; - hbase = 0; + if (hmask) { + if (hartid + BITS_PER_LONG <= htop || + hbase + BITS_PER_LONG <= hartid) { + result = __sbi_rfence_v02_call(fid, hmask, + hbase, start, size, arg4, arg5); + if (result) + return result; + hmask = 0; + } else if (hartid < hbase) { + /* shift the mask to fit lower hartid */ + hmask <<= hbase - hartid; + hbase = hartid; + } } - if (!hmask) + if (!hmask) { hbase = hartid; - hmask |= 1UL << (hartid - hbase); + htop = hartid; + } else if (hartid > htop) { + htop = hartid; + } + hmask |= BIT(hartid - hbase); } if (hmask) { diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 201ee206fb57..14d2b53ec322 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -22,15 +22,16 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg) { unsigned long fp, sp, pc; + int level = 0; if (regs) { fp = frame_pointer(regs); sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - fp = (unsigned long)__builtin_frame_address(1); - sp = (unsigned long)__builtin_frame_address(0); - pc = (unsigned long)__builtin_return_address(0); + fp = (unsigned long)__builtin_frame_address(0); + sp = sp_in_global; + pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ fp = task->thread.s[0]; @@ -42,7 +43,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, unsigned long low, high; struct stackframe *frame; - if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) + if (unlikely(!__kernel_text_address(pc) || (level++ >= 1 && !fn(arg, pc)))) break; /* Validate frame pointer */ diff --git a/arch/riscv/kernel/trace_irq.c b/arch/riscv/kernel/trace_irq.c new file mode 100644 index 000000000000..095ac976d7da --- /dev/null +++ b/arch/riscv/kernel/trace_irq.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 Changbin Du <changbin.du@gmail.com> + */ + +#include <linux/irqflags.h> +#include <linux/kprobes.h> +#include "trace_irq.h" + +/* + * trace_hardirqs_on/off require the caller to setup frame pointer properly. + * Otherwise, CALLER_ADDR1 might trigger an pagging exception in kernel. + * Here we add one extra level so they can be safely called by low + * level entry code which $fp is used for other purpose. + */ + +void __trace_hardirqs_on(void) +{ + trace_hardirqs_on(); +} +NOKPROBE_SYMBOL(__trace_hardirqs_on); + +void __trace_hardirqs_off(void) +{ + trace_hardirqs_off(); +} +NOKPROBE_SYMBOL(__trace_hardirqs_off); diff --git a/arch/riscv/kernel/trace_irq.h b/arch/riscv/kernel/trace_irq.h new file mode 100644 index 000000000000..99fe67377e5e --- /dev/null +++ b/arch/riscv/kernel/trace_irq.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Changbin Du <changbin.du@gmail.com> + */ +#ifndef __TRACE_IRQ_H +#define __TRACE_IRQ_H + +void __trace_hardirqs_on(void); +void __trace_hardirqs_off(void); + +#endif /* __TRACE_IRQ_H */ diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 0c5239e05721..624166004e36 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -90,6 +90,7 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *cntx; + struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr; /* Mark this VCPU never ran */ vcpu->arch.ran_atleast_once = false; @@ -106,6 +107,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) cntx->hstatus |= HSTATUS_SPVP; cntx->hstatus |= HSTATUS_SPV; + /* By default, make CY, TM, and IR counters accessible in VU mode */ + reset_csr->scounteren = 0x7; + /* Setup VCPU timer */ kvm_riscv_vcpu_timer_init(vcpu); @@ -699,6 +703,20 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu) csr_write(CSR_HVIP, csr->hvip); } +/* + * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while + * the vCPU is running. + * + * This must be noinstr as instrumentation may make use of RCU, and this is not + * safe during the EQS. + */ +static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu) +{ + guest_state_enter_irqoff(); + __kvm_riscv_switch_to(&vcpu->arch); + guest_state_exit_irqoff(); +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { int ret; @@ -790,9 +808,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) continue; } - guest_enter_irqoff(); + guest_timing_enter_irqoff(); - __kvm_riscv_switch_to(&vcpu->arch); + kvm_riscv_vcpu_enter_exit(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; vcpu->stat.exits++; @@ -812,25 +830,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_sync_interrupts(vcpu); /* - * We may have taken a host interrupt in VS/VU-mode (i.e. - * while executing the guest). This interrupt is still - * pending, as we haven't serviced it yet! + * We must ensure that any pending interrupts are taken before + * we exit guest timing so that timer ticks are accounted as + * guest time. Transiently unmask interrupts so that any + * pending interrupts are taken. * - * We're now back in HS-mode with interrupts disabled - * so enabling the interrupts now will have the effect - * of taking the interrupt again, in HS-mode this time. + * There's no barrier which ensures that pending interrupts are + * recognised, so we just hope that the CPU takes any pending + * interrupts between the enable and disable. */ local_irq_enable(); + local_irq_disable(); - /* - * We do local_irq_enable() before calling guest_exit() so - * that if a timer interrupt hits while running the guest - * we account that tick as being spent in the guest. We - * enable preemption after calling guest_exit() so that if - * we get preempted we make sure ticks after that is not - * counted as guest time. - */ - guest_exit(); + guest_timing_exit_irqoff(); + + local_irq_enable(); preempt_enable(); diff --git a/arch/riscv/kvm/vcpu_sbi_base.c b/arch/riscv/kvm/vcpu_sbi_base.c index 4ecf377f483b..48f431091cdb 100644 --- a/arch/riscv/kvm/vcpu_sbi_base.c +++ b/arch/riscv/kvm/vcpu_sbi_base.c @@ -9,6 +9,7 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> +#include <linux/version.h> #include <asm/csr.h> #include <asm/sbi.h> #include <asm/kvm_vcpu_timer.h> @@ -32,7 +33,7 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, *out_val = KVM_SBI_IMPID; break; case SBI_EXT_BASE_GET_IMP_VERSION: - *out_val = 0; + *out_val = LINUX_VERSION_CODE; break; case SBI_EXT_BASE_PROBE_EXT: if ((cp->a0 >= SBI_EXT_EXPERIMENTAL_START && diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index 7ebaef10ea1b..ac7a25298a04 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -24,6 +24,9 @@ obj-$(CONFIG_KASAN) += kasan_init.o ifdef CONFIG_KASAN KASAN_SANITIZE_kasan_init.o := n KASAN_SANITIZE_init.o := n +ifdef CONFIG_DEBUG_VIRTUAL +KASAN_SANITIZE_physaddr.o := n +endif endif obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c index 05978f78579f..35484d830fd6 100644 --- a/arch/riscv/mm/extable.c +++ b/arch/riscv/mm/extable.c @@ -33,7 +33,7 @@ static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset, if (unlikely(offset > MAX_REG_OFFSET)) return; - if (!offset) + if (offset) *(unsigned long *)((unsigned long)regs + offset) = val; } @@ -43,8 +43,8 @@ static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex, int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data); int reg_zero = FIELD_GET(EX_DATA_REG_ZERO, ex->data); - regs_set_gpr(regs, reg_err, -EFAULT); - regs_set_gpr(regs, reg_zero, 0); + regs_set_gpr(regs, reg_err * sizeof(unsigned long), -EFAULT); + regs_set_gpr(regs, reg_zero * sizeof(unsigned long), 0); regs->epc = get_ex_fixup(ex); return true; diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index cf4d018b7d66..0d588032d6e6 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -125,7 +125,6 @@ void __init mem_init(void) else swiotlb_force = SWIOTLB_NO_FORCE; #endif - high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); memblock_free_all(); print_vm_layout(); @@ -195,6 +194,7 @@ static void __init setup_bootmem(void) min_low_pfn = PFN_UP(phys_ram_base); max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end); + high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); @@ -232,6 +232,7 @@ static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAG #ifdef CONFIG_XIP_KERNEL #define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops)) +#define riscv_pfn_base (*(unsigned long *)XIP_FIXUP(&riscv_pfn_base)) #define trampoline_pg_dir ((pgd_t *)XIP_FIXUP(trampoline_pg_dir)) #define fixmap_pte ((pte_t *)XIP_FIXUP(fixmap_pte)) #define early_pg_dir ((pgd_t *)XIP_FIXUP(early_pg_dir)) @@ -522,6 +523,7 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size) } #ifdef CONFIG_XIP_KERNEL +#define phys_ram_base (*(phys_addr_t *)XIP_FIXUP(&phys_ram_base)) extern char _xiprom[], _exiprom[], __data_loc; /* called from head.S with MMU off */ diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index f61f7ca6fe0f..cd1a145257b7 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -113,8 +113,11 @@ static void __init kasan_populate_pud(pgd_t *pgd, base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd))); } else { base_pud = (pud_t *)pgd_page_vaddr(*pgd); - if (base_pud == lm_alias(kasan_early_shadow_pud)) + if (base_pud == lm_alias(kasan_early_shadow_pud)) { base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); + memcpy(base_pud, (void *)kasan_early_shadow_pud, + sizeof(pud_t) * PTRS_PER_PUD); + } } pudp = base_pud + pud_index(vaddr); @@ -202,8 +205,7 @@ asmlinkage void __init kasan_early_init(void) for (i = 0; i < PTRS_PER_PTE; ++i) set_pte(kasan_early_shadow_pte + i, - mk_pte(virt_to_page(kasan_early_shadow_page), - PAGE_KERNEL)); + pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL)); for (i = 0; i < PTRS_PER_PMD; ++i) set_pmd(kasan_early_shadow_pmd + i, diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c index e7fd0c253c7b..19cf25a74ee2 100644 --- a/arch/riscv/mm/physaddr.c +++ b/arch/riscv/mm/physaddr.c @@ -8,12 +8,10 @@ phys_addr_t __virt_to_phys(unsigned long x) { - phys_addr_t y = x - PAGE_OFFSET; - /* * Boundary checking aginst the kernel linear mapping space. */ - WARN(y >= KERN_VIRT_SIZE, + WARN(!is_linear_mapping(x) && !is_kernel_mapping(x), "virt_to_phys used for non-linear address: %pK (%pS)\n", (void *)x, (void *)x); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 9750f92380f5..be9f39fd06df 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -945,6 +945,9 @@ config S390_GUEST endmenu +config S390_MODULES_SANITY_TEST_HELPERS + def_bool n + menu "Selftests" config S390_UNWIND_SELFTEST @@ -971,4 +974,16 @@ config S390_KPROBES_SANITY_TEST Say N if you are unsure. +config S390_MODULES_SANITY_TEST + def_tristate n + depends on KUNIT + default KUNIT_ALL_TESTS + prompt "Enable s390 specific modules tests" + select S390_MODULES_SANITY_TEST_HELPERS + help + This option enables an s390 specific modules test. This option is + not useful for distributions or general kernels, but only for + kernel developers working on architecture code. + + Say N if you are unsure. endmenu diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 7fe8975b49ec..498bed9b261b 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -63,6 +63,7 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m +CONFIG_S390_MODULES_SANITY_TEST=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_STATIC_KEYS_SELFTEST=y @@ -96,7 +97,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_FRONTSWAP=y CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y CONFIG_CMA_SYSFS=y @@ -109,6 +109,7 @@ CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y CONFIG_PERCPU_STATS=y CONFIG_GUP_TEST=y +CONFIG_ANON_VMA_NAME=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -116,7 +117,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_NET_SWITCHDEV=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y @@ -185,7 +185,6 @@ CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y CONFIG_NFT_CT=m -CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m @@ -391,6 +390,7 @@ CONFIG_OPENVSWITCH=m CONFIG_VSOCKETS=m CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m +CONFIG_NET_SWITCHDEV=y CONFIG_CGROUP_NET_PRIO=y CONFIG_NET_PKTGEN=m CONFIG_PCI=y @@ -400,6 +400,7 @@ CONFIG_PCI_IOV=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_SAFE=y CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m @@ -501,6 +502,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set +# CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set @@ -511,7 +513,6 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y -CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set @@ -542,6 +543,7 @@ CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_TEHUTI is not set # CONFIG_NET_VENDOR_TI is not set +# CONFIG_NET_VENDOR_VERTEXCOM is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_NET_VENDOR_XILINX is not set @@ -592,6 +594,7 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m +# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -756,9 +759,6 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_STATS=y -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m @@ -774,6 +774,8 @@ CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_CRC32_SELFTEST=y CONFIG_CRC4=m CONFIG_CRC7=m @@ -807,7 +809,6 @@ CONFIG_SLUB_DEBUG_ON=y CONFIG_SLUB_STATS=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_VM=y -CONFIG_DEBUG_VM_VMACACHE=y CONFIG_DEBUG_VM_PGFLAGS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m @@ -819,12 +820,11 @@ CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y CONFIG_TEST_LOCKUP=m -CONFIG_DEBUG_TIMEKEEPING=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y -CONFIG_DEBUG_LOCKDEP=y CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LOCKING_API_SELFTESTS=y +CONFIG_DEBUG_IRQFLAGS=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y CONFIG_BUG_ON_DATA_CORRUPTION=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 466780c465f5..61e36b999f67 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -61,6 +61,7 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m +CONFIG_S390_MODULES_SANITY_TEST=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y # CONFIG_GCC_PLUGINS is not set @@ -91,7 +92,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_FRONTSWAP=y CONFIG_CMA_SYSFS=y CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y @@ -101,6 +101,7 @@ CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y CONFIG_PERCPU_STATS=y +CONFIG_ANON_VMA_NAME=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -108,7 +109,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_NET_SWITCHDEV=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y @@ -177,7 +177,6 @@ CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y CONFIG_NFT_CT=m -CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m @@ -382,6 +381,7 @@ CONFIG_OPENVSWITCH=m CONFIG_VSOCKETS=m CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m +CONFIG_NET_SWITCHDEV=y CONFIG_CGROUP_NET_PRIO=y CONFIG_NET_PKTGEN=m CONFIG_PCI=y @@ -391,6 +391,7 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_UEVENT_HELPER=y CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_SAFE=y CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m @@ -492,6 +493,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set +# CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set @@ -502,7 +504,6 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y -CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set @@ -533,6 +534,7 @@ CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_TEHUTI is not set # CONFIG_NET_VENDOR_TI is not set +# CONFIG_NET_VENDOR_VERTEXCOM is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_NET_VENDOR_XILINX is not set @@ -582,6 +584,7 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m +# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -743,9 +746,6 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_STATS=y -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m @@ -762,6 +762,8 @@ CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index eed3b9acfa71..c55c668dc3c7 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -1,6 +1,7 @@ # CONFIG_SWAP is not set CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_BPF_SYSCALL=y # CONFIG_CPU_ISOLATION is not set # CONFIG_UTS_NS is not set # CONFIG_TIME_NS is not set @@ -34,6 +35,7 @@ CONFIG_NET=y # CONFIG_PCPU_DEV_REFCNT is not set # CONFIG_ETHTOOL_NETLINK is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_SAFE=y CONFIG_BLK_DEV_RAM=y # CONFIG_DCSSBLK is not set # CONFIG_DASD is not set @@ -58,6 +60,7 @@ CONFIG_ZFCP=y # CONFIG_HID is not set # CONFIG_VIRTIO_MENU is not set # CONFIG_VHOST_MENU is not set +# CONFIG_SURFACE_PLATFORMS is not set # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index 33f973ff9744..e8f15dbb89d0 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -20,6 +20,7 @@ static char local_guest[] = " "; static char all_guests[] = "* "; +static char *all_groups = all_guests; static char *guest_query; struct diag2fc_data { @@ -62,10 +63,11 @@ static int diag2fc(int size, char* query, void *addr) memcpy(parm_list.userid, query, NAME_LEN); ASCEBC(parm_list.userid, NAME_LEN); - parm_list.addr = (unsigned long) addr ; + memcpy(parm_list.aci_grp, all_groups, NAME_LEN); + ASCEBC(parm_list.aci_grp, NAME_LEN); + parm_list.addr = (unsigned long)addr; parm_list.size = size; parm_list.fmt = 0x02; - memset(parm_list.aci_grp, 0x40, NAME_LEN); rc = -1; diag_stat_inc(DIAG_STAT_X2FC); diff --git a/arch/s390/include/asm/extable.h b/arch/s390/include/asm/extable.h index 16dc57dd90b3..8511f0e59290 100644 --- a/arch/s390/include/asm/extable.h +++ b/arch/s390/include/asm/extable.h @@ -69,8 +69,13 @@ static inline void swap_ex_entry_fixup(struct exception_table_entry *a, { a->fixup = b->fixup + delta; b->fixup = tmp.fixup - delta; - a->handler = b->handler + delta; - b->handler = tmp.handler - delta; + a->handler = b->handler; + if (a->handler) + a->handler += delta; + b->handler = tmp.handler; + if (b->handler) + b->handler -= delta; } +#define swap_ex_entry_fixup swap_ex_entry_fixup #endif diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 267f70f4393f..6f80ec9c04be 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -47,15 +47,17 @@ struct ftrace_regs { static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) { - return &fregs->regs; + struct pt_regs *regs = &fregs->regs; + + if (test_pt_regs_flag(regs, PIF_FTRACE_FULL_REGS)) + return regs; + return NULL; } static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *fregs, unsigned long ip) { - struct pt_regs *regs = arch_ftrace_get_regs(fregs); - - regs->psw.addr = ip; + fregs->regs.psw.addr = ip; } /* diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 4ffa8e7f0ed3..ddb70fb13fbc 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -15,11 +15,13 @@ #define PIF_EXECVE_PGSTE_RESTART 1 /* restart execve for PGSTE binaries */ #define PIF_SYSCALL_RET_SET 2 /* return value was set via ptrace */ #define PIF_GUEST_FAULT 3 /* indicates program check in sie64a */ +#define PIF_FTRACE_FULL_REGS 4 /* all register contents valid (ftrace) */ #define _PIF_SYSCALL BIT(PIF_SYSCALL) #define _PIF_EXECVE_PGSTE_RESTART BIT(PIF_EXECVE_PGSTE_RESTART) #define _PIF_SYSCALL_RET_SET BIT(PIF_SYSCALL_RET_SET) #define _PIF_GUEST_FAULT BIT(PIF_GUEST_FAULT) +#define _PIF_FTRACE_FULL_REGS BIT(PIF_FTRACE_FULL_REGS) #ifndef __ASSEMBLY__ diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 147cb3534ce4..d74e26b48604 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -47,8 +47,6 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n); int __put_user_bad(void) __attribute__((noreturn)); int __get_user_bad(void) __attribute__((noreturn)); -#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES - union oac { unsigned int val; struct { @@ -71,6 +69,8 @@ union oac { }; }; +#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES + #define __put_get_user_asm(to, from, size, oac_spec) \ ({ \ int __rc; \ diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 21d62d8b6b9a..89c0870d5679 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -159,9 +159,38 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) return 0; } +static struct ftrace_hotpatch_trampoline *ftrace_get_trampoline(struct dyn_ftrace *rec) +{ + struct ftrace_hotpatch_trampoline *trampoline; + struct ftrace_insn insn; + s64 disp; + u16 opc; + + if (copy_from_kernel_nofault(&insn, (void *)rec->ip, sizeof(insn))) + return ERR_PTR(-EFAULT); + disp = (s64)insn.disp * 2; + trampoline = (void *)(rec->ip + disp); + if (get_kernel_nofault(opc, &trampoline->brasl_opc)) + return ERR_PTR(-EFAULT); + if (opc != 0xc015) + return ERR_PTR(-EINVAL); + return trampoline; +} + int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { + struct ftrace_hotpatch_trampoline *trampoline; + u64 old; + + trampoline = ftrace_get_trampoline(rec); + if (IS_ERR(trampoline)) + return PTR_ERR(trampoline); + if (get_kernel_nofault(old, &trampoline->interceptor)) + return -EFAULT; + if (old != old_addr) + return -EINVAL; + s390_kernel_write(&trampoline->interceptor, &addr, sizeof(addr)); return 0; } @@ -188,6 +217,12 @@ static void brcl_enable(void *brcl) int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { + struct ftrace_hotpatch_trampoline *trampoline; + + trampoline = ftrace_get_trampoline(rec); + if (IS_ERR(trampoline)) + return PTR_ERR(trampoline); + s390_kernel_write(&trampoline->interceptor, &addr, sizeof(addr)); brcl_enable((void *)rec->ip); return 0; } @@ -291,7 +326,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, regs = ftrace_get_regs(fregs); p = get_kprobe((kprobe_opcode_t *)ip); - if (unlikely(!p) || kprobe_disabled(p)) + if (!regs || unlikely(!p) || kprobe_disabled(p)) goto out; if (kprobe_running()) { diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 39bcc0e39a10..a24177dcd12a 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -27,6 +27,7 @@ ENDPROC(ftrace_stub) #define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS) #define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW) #define STACK_PTREGS_ORIG_GPR2 (STACK_PTREGS + __PT_ORIG_GPR2) +#define STACK_PTREGS_FLAGS (STACK_PTREGS + __PT_FLAGS) #ifdef __PACK_STACK /* allocate just enough for r14, r15 and backchain */ #define TRACED_FUNC_FRAME_SIZE 24 @@ -57,6 +58,14 @@ ENDPROC(ftrace_stub) .if \allregs == 1 stg %r14,(STACK_PTREGS_PSW)(%r15) stosm (STACK_PTREGS_PSW)(%r15),0 +#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES + mvghi STACK_PTREGS_FLAGS(%r15),_PIF_FTRACE_FULL_REGS +#else + lghi %r14,_PIF_FTRACE_FULL_REGS + stg %r14,STACK_PTREGS_FLAGS(%r15) +#endif + .else + xc STACK_PTREGS_FLAGS(8,%r15),STACK_PTREGS_FLAGS(%r15) .endif lg %r14,(__SF_GPRS+8*8)(%r1) # restore original return address diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index d52d85367bf7..b032e556eeb7 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -33,7 +33,7 @@ #define DEBUGP(fmt , ...) #endif -#define PLT_ENTRY_SIZE 20 +#define PLT_ENTRY_SIZE 22 void *module_alloc(unsigned long size) { @@ -341,27 +341,26 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PLTOFF32: /* 32 bit offset from GOT to PLT. */ case R_390_PLTOFF64: /* 16 bit offset from GOT to PLT. */ if (info->plt_initialized == 0) { - unsigned int insn[5]; - unsigned int *ip = me->core_layout.base + - me->arch.plt_offset + - info->plt_offset; - - insn[0] = 0x0d10e310; /* basr 1,0 */ - insn[1] = 0x100a0004; /* lg 1,10(1) */ + unsigned char insn[PLT_ENTRY_SIZE]; + char *plt_base; + char *ip; + + plt_base = me->core_layout.base + me->arch.plt_offset; + ip = plt_base + info->plt_offset; + *(int *)insn = 0x0d10e310; /* basr 1,0 */ + *(int *)&insn[4] = 0x100c0004; /* lg 1,12(1) */ if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable) { - unsigned int *ij; - ij = me->core_layout.base + - me->arch.plt_offset + - me->arch.plt_size - PLT_ENTRY_SIZE; - insn[2] = 0xa7f40000 + /* j __jump_r1 */ - (unsigned int)(u16) - (((unsigned long) ij - 8 - - (unsigned long) ip) / 2); + char *jump_r1; + + jump_r1 = plt_base + me->arch.plt_size - + PLT_ENTRY_SIZE; + /* brcl 0xf,__jump_r1 */ + *(short *)&insn[8] = 0xc0f4; + *(int *)&insn[10] = (jump_r1 - (ip + 8)) / 2; } else { - insn[2] = 0x07f10000; /* br %r1 */ + *(int *)&insn[8] = 0x07f10000; /* br %r1 */ } - insn[3] = (unsigned int) (val >> 32); - insn[4] = (unsigned int) val; + *(long *)&insn[14] = val; write(ip, insn, sizeof(insn)); info->plt_initialized = 1; diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 0c9e894913dc..651a51914e34 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -264,7 +264,14 @@ static int notrace s390_validate_registers(union mci mci, int umode) /* Validate vector registers */ union ctlreg0 cr0; - if (!mci.vr) { + /* + * The vector validity must only be checked if not running a + * KVM guest. For KVM guests the machine check is forwarded by + * KVM and it is the responsibility of the guest to take + * appropriate actions. The host vector or FPU values have been + * saved by KVM and will be restored by KVM. + */ + if (!mci.vr && !test_cpu_flag(CIF_MCCK_GUEST)) { /* * Vector registers can't be restored. If the kernel * currently uses vector registers the system is @@ -307,11 +314,21 @@ static int notrace s390_validate_registers(union mci mci, int umode) if (cr2.gse) { if (!mci.gs) { /* - * Guarded storage register can't be restored and - * the current processes uses guarded storage. - * It has to be terminated. + * 2 cases: + * - machine check in kernel or userspace + * - machine check while running SIE (KVM guest) + * For kernel or userspace the userspace values of + * guarded storage control can not be recreated, the + * process must be terminated. + * For SIE the guest values of guarded storage can not + * be recreated. This is either due to a bug or due to + * GS being disabled in the guest. The guest will be + * notified by KVM code and the guests machine check + * handling must take care of this. The host values + * are saved by KVM and are not affected. */ - kill_task = 1; + if (!test_cpu_flag(CIF_MCCK_GUEST)) + kill_task = 1; } else { load_gs_cb((struct gs_cb *)mcesa->guarded_storage_save_area); } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index f2c25d113e7b..05327be3a982 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -800,6 +800,8 @@ static void __init check_initrd(void) static void __init reserve_kernel(void) { memblock_reserve(0, STARTUP_NORMAL_OFFSET); + memblock_reserve(OLDMEM_BASE, sizeof(unsigned long)); + memblock_reserve(OLDMEM_SIZE, sizeof(unsigned long)); memblock_reserve(__amode31_base, __eamode31 - __samode31); memblock_reserve(__pa(sclp_early_sccb), EXT_SCCB_READ_SCP); memblock_reserve(__pa(_stext), _end - _stext); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 577f1ead6a51..2296b1ff1e02 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4667,6 +4667,8 @@ static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu, return -EINVAL; if (mop->size + mop->sida_offset > sida_size(vcpu->arch.sie_block)) return -E2BIG; + if (!kvm_s390_pv_cpu_is_protected(vcpu)) + return -EINVAL; switch (mop->op) { case KVM_S390_MEMOP_SIDA_READ: diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index 707cd4622c13..69feb8ed3312 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -17,4 +17,7 @@ KASAN_SANITIZE_uaccess.o := n obj-$(CONFIG_S390_UNWIND_SELFTEST) += test_unwind.o CFLAGS_test_unwind.o += -fno-optimize-sibling-calls +obj-$(CONFIG_S390_MODULES_SANITY_TEST) += test_modules.o +obj-$(CONFIG_S390_MODULES_SANITY_TEST_HELPERS) += test_modules_helpers.o + lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/s390/lib/test_modules.c b/arch/s390/lib/test_modules.c new file mode 100644 index 000000000000..9894009fc1f2 --- /dev/null +++ b/arch/s390/lib/test_modules.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <kunit/test.h> +#include <linux/module.h> + +#include "test_modules.h" + +/* + * Test that modules with many relocations are loaded properly. + */ +static void test_modules_many_vmlinux_relocs(struct kunit *test) +{ + int result = 0; + +#define CALL_RETURN(i) result += test_modules_return_ ## i() + REPEAT_10000(CALL_RETURN); + KUNIT_ASSERT_EQ(test, result, 49995000); +} + +static struct kunit_case modules_testcases[] = { + KUNIT_CASE(test_modules_many_vmlinux_relocs), + {} +}; + +static struct kunit_suite modules_test_suite = { + .name = "modules_test_s390", + .test_cases = modules_testcases, +}; + +kunit_test_suites(&modules_test_suite); + +MODULE_LICENSE("GPL"); diff --git a/arch/s390/lib/test_modules.h b/arch/s390/lib/test_modules.h new file mode 100644 index 000000000000..6371fcf17684 --- /dev/null +++ b/arch/s390/lib/test_modules.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef TEST_MODULES_H +#define TEST_MODULES_H + +#define __REPEAT_10000_3(f, x) \ + f(x ## 0); \ + f(x ## 1); \ + f(x ## 2); \ + f(x ## 3); \ + f(x ## 4); \ + f(x ## 5); \ + f(x ## 6); \ + f(x ## 7); \ + f(x ## 8); \ + f(x ## 9) +#define __REPEAT_10000_2(f, x) \ + __REPEAT_10000_3(f, x ## 0); \ + __REPEAT_10000_3(f, x ## 1); \ + __REPEAT_10000_3(f, x ## 2); \ + __REPEAT_10000_3(f, x ## 3); \ + __REPEAT_10000_3(f, x ## 4); \ + __REPEAT_10000_3(f, x ## 5); \ + __REPEAT_10000_3(f, x ## 6); \ + __REPEAT_10000_3(f, x ## 7); \ + __REPEAT_10000_3(f, x ## 8); \ + __REPEAT_10000_3(f, x ## 9) +#define __REPEAT_10000_1(f, x) \ + __REPEAT_10000_2(f, x ## 0); \ + __REPEAT_10000_2(f, x ## 1); \ + __REPEAT_10000_2(f, x ## 2); \ + __REPEAT_10000_2(f, x ## 3); \ + __REPEAT_10000_2(f, x ## 4); \ + __REPEAT_10000_2(f, x ## 5); \ + __REPEAT_10000_2(f, x ## 6); \ + __REPEAT_10000_2(f, x ## 7); \ + __REPEAT_10000_2(f, x ## 8); \ + __REPEAT_10000_2(f, x ## 9) +#define REPEAT_10000(f) \ + __REPEAT_10000_1(f, 0); \ + __REPEAT_10000_1(f, 1); \ + __REPEAT_10000_1(f, 2); \ + __REPEAT_10000_1(f, 3); \ + __REPEAT_10000_1(f, 4); \ + __REPEAT_10000_1(f, 5); \ + __REPEAT_10000_1(f, 6); \ + __REPEAT_10000_1(f, 7); \ + __REPEAT_10000_1(f, 8); \ + __REPEAT_10000_1(f, 9) + +#define DECLARE_RETURN(i) int test_modules_return_ ## i(void) +REPEAT_10000(DECLARE_RETURN); + +#endif diff --git a/arch/s390/lib/test_modules_helpers.c b/arch/s390/lib/test_modules_helpers.c new file mode 100644 index 000000000000..1670349a03eb --- /dev/null +++ b/arch/s390/lib/test_modules_helpers.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/export.h> + +#include "test_modules.h" + +#define DEFINE_RETURN(i) \ + int test_modules_return_ ## i(void) \ + { \ + return 1 ## i - 10000; \ + } \ + EXPORT_SYMBOL_GPL(test_modules_return_ ## i) +REPEAT_10000(DEFINE_RETURN); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ebe8fc76949a..9f5bd41bf660 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -186,6 +186,7 @@ config X86 select HAVE_CONTEXT_TRACKING_OFFSTACK if HAVE_CONTEXT_TRACKING select HAVE_C_RECORDMCOUNT select HAVE_OBJTOOL_MCOUNT if STACK_VALIDATION + select HAVE_BUILDTIME_MCOUNT_SORT select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE diff --git a/arch/x86/crypto/blake2s-shash.c b/arch/x86/crypto/blake2s-shash.c index f9e2fecdb761..59ae28abe35c 100644 --- a/arch/x86/crypto/blake2s-shash.c +++ b/arch/x86/crypto/blake2s-shash.c @@ -18,12 +18,12 @@ static int crypto_blake2s_update_x86(struct shash_desc *desc, const u8 *in, unsigned int inlen) { - return crypto_blake2s_update(desc, in, inlen, blake2s_compress); + return crypto_blake2s_update(desc, in, inlen, false); } static int crypto_blake2s_final_x86(struct shash_desc *desc, u8 *out) { - return crypto_blake2s_final(desc, out, blake2s_compress); + return crypto_blake2s_final(desc, out, false); } #define BLAKE2S_ALG(name, driver_name, digest_size) \ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index fd9f908debe5..a3c7ca876aeb 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4703,6 +4703,19 @@ static __initconst const struct x86_pmu intel_pmu = { .lbr_read = intel_pmu_lbr_read_64, .lbr_save = intel_pmu_lbr_save, .lbr_restore = intel_pmu_lbr_restore, + + /* + * SMM has access to all 4 rings and while traditionally SMM code only + * ran in CPL0, 2021-era firmware is starting to make use of CPL3 in SMM. + * + * Since the EVENTSEL.{USR,OS} CPL filtering makes no distinction + * between SMM or not, this results in what should be pure userspace + * counters including SMM data. + * + * This is a clear privilege issue, therefore globally disable + * counting SMM by default. + */ + .attr_freeze_on_smi = 1, }; static __init void intel_clovertown_quirk(void) @@ -6236,6 +6249,19 @@ __init int intel_pmu_init(void) pmu->num_counters = x86_pmu.num_counters; pmu->num_counters_fixed = x86_pmu.num_counters_fixed; } + + /* + * Quirk: For some Alder Lake machine, when all E-cores are disabled in + * a BIOS, the leaf 0xA will enumerate all counters of P-cores. However, + * the X86_FEATURE_HYBRID_CPU is still set. The above codes will + * mistakenly add extra counters for P-cores. Correct the number of + * counters here. + */ + if ((pmu->num_counters > 8) || (pmu->num_counters_fixed > 4)) { + pmu->num_counters = x86_pmu.num_counters; + pmu->num_counters_fixed = x86_pmu.num_counters_fixed; + } + pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters); pmu->unconstrained = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1, @@ -6340,6 +6366,8 @@ __init int intel_pmu_init(void) } if (x86_pmu.lbr_nr) { + intel_pmu_lbr_init(); + pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr); /* only support branch_stack snapshot for perfmon >= v2 */ diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 8043213b75a5..669c2be14784 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -8,14 +8,6 @@ #include "../perf_event.h" -static const enum { - LBR_EIP_FLAGS = 1, - LBR_TSX = 2, -} lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = { - [LBR_FORMAT_EIP_FLAGS] = LBR_EIP_FLAGS, - [LBR_FORMAT_EIP_FLAGS2] = LBR_EIP_FLAGS | LBR_TSX, -}; - /* * Intel LBR_SELECT bits * Intel Vol3a, April 2011, Section 16.7 Table 16-10 @@ -243,7 +235,7 @@ void intel_pmu_lbr_reset_64(void) for (i = 0; i < x86_pmu.lbr_nr; i++) { wrmsrl(x86_pmu.lbr_from + i, 0); wrmsrl(x86_pmu.lbr_to + i, 0); - if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + if (x86_pmu.lbr_has_info) wrmsrl(x86_pmu.lbr_info + i, 0); } } @@ -305,11 +297,10 @@ enum { */ static inline bool lbr_from_signext_quirk_needed(void) { - int lbr_format = x86_pmu.intel_cap.lbr_format; bool tsx_support = boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM); - return !tsx_support && (lbr_desc[lbr_format] & LBR_TSX); + return !tsx_support && x86_pmu.lbr_has_tsx; } static DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key); @@ -427,12 +418,12 @@ rdlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info) void intel_pmu_lbr_restore(void *ctx) { - bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx = ctx; - int i; - unsigned lbr_idx, mask; + bool need_info = x86_pmu.lbr_has_info; u64 tos = task_ctx->tos; + unsigned lbr_idx, mask; + int i; mask = x86_pmu.lbr_nr - 1; for (i = 0; i < task_ctx->valid_lbrs; i++) { @@ -444,7 +435,7 @@ void intel_pmu_lbr_restore(void *ctx) lbr_idx = (tos - i) & mask; wrlbr_from(lbr_idx, 0); wrlbr_to(lbr_idx, 0); - if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + if (need_info) wrlbr_info(lbr_idx, 0); } @@ -519,9 +510,9 @@ static void __intel_pmu_lbr_restore(void *ctx) void intel_pmu_lbr_save(void *ctx) { - bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx = ctx; + bool need_info = x86_pmu.lbr_has_info; unsigned lbr_idx, mask; u64 tos; int i; @@ -816,7 +807,6 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { bool need_info = false, call_stack = false; unsigned long mask = x86_pmu.lbr_nr - 1; - int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); int i; int out = 0; @@ -831,9 +821,7 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) for (i = 0; i < num; i++) { unsigned long lbr_idx = (tos - i) & mask; u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0; - int skip = 0; u16 cycles = 0; - int lbr_flags = lbr_desc[lbr_format]; from = rdlbr_from(lbr_idx, NULL); to = rdlbr_to(lbr_idx, NULL); @@ -845,37 +833,39 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) if (call_stack && !from) break; - if (lbr_format == LBR_FORMAT_INFO && need_info) { - u64 info; - - info = rdlbr_info(lbr_idx, NULL); - mis = !!(info & LBR_INFO_MISPRED); - pred = !mis; - in_tx = !!(info & LBR_INFO_IN_TX); - abort = !!(info & LBR_INFO_ABORT); - cycles = (info & LBR_INFO_CYCLES); - } - - if (lbr_format == LBR_FORMAT_TIME) { - mis = !!(from & LBR_FROM_FLAG_MISPRED); - pred = !mis; - skip = 1; - cycles = ((to >> 48) & LBR_INFO_CYCLES); - - to = (u64)((((s64)to) << 16) >> 16); - } - - if (lbr_flags & LBR_EIP_FLAGS) { - mis = !!(from & LBR_FROM_FLAG_MISPRED); - pred = !mis; - skip = 1; - } - if (lbr_flags & LBR_TSX) { - in_tx = !!(from & LBR_FROM_FLAG_IN_TX); - abort = !!(from & LBR_FROM_FLAG_ABORT); - skip = 3; + if (x86_pmu.lbr_has_info) { + if (need_info) { + u64 info; + + info = rdlbr_info(lbr_idx, NULL); + mis = !!(info & LBR_INFO_MISPRED); + pred = !mis; + cycles = (info & LBR_INFO_CYCLES); + if (x86_pmu.lbr_has_tsx) { + in_tx = !!(info & LBR_INFO_IN_TX); + abort = !!(info & LBR_INFO_ABORT); + } + } + } else { + int skip = 0; + + if (x86_pmu.lbr_from_flags) { + mis = !!(from & LBR_FROM_FLAG_MISPRED); + pred = !mis; + skip = 1; + } + if (x86_pmu.lbr_has_tsx) { + in_tx = !!(from & LBR_FROM_FLAG_IN_TX); + abort = !!(from & LBR_FROM_FLAG_ABORT); + skip = 3; + } + from = (u64)((((s64)from) << skip) >> skip); + + if (x86_pmu.lbr_to_cycles) { + cycles = ((to >> 48) & LBR_INFO_CYCLES); + to = (u64)((((s64)to) << 16) >> 16); + } } - from = (u64)((((s64)from) << skip) >> skip); /* * Some CPUs report duplicated abort records, @@ -903,37 +893,40 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) cpuc->lbr_stack.hw_idx = tos; } +static DEFINE_STATIC_KEY_FALSE(x86_lbr_mispred); +static DEFINE_STATIC_KEY_FALSE(x86_lbr_cycles); +static DEFINE_STATIC_KEY_FALSE(x86_lbr_type); + static __always_inline int get_lbr_br_type(u64 info) { - if (!static_cpu_has(X86_FEATURE_ARCH_LBR) || !x86_pmu.lbr_br_type) - return 0; + int type = 0; - return (info & LBR_INFO_BR_TYPE) >> LBR_INFO_BR_TYPE_OFFSET; + if (static_branch_likely(&x86_lbr_type)) + type = (info & LBR_INFO_BR_TYPE) >> LBR_INFO_BR_TYPE_OFFSET; + + return type; } static __always_inline bool get_lbr_mispred(u64 info) { - if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred) - return 0; + bool mispred = 0; - return !!(info & LBR_INFO_MISPRED); -} + if (static_branch_likely(&x86_lbr_mispred)) + mispred = !!(info & LBR_INFO_MISPRED); -static __always_inline bool get_lbr_predicted(u64 info) -{ - if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred) - return 0; - - return !(info & LBR_INFO_MISPRED); + return mispred; } static __always_inline u16 get_lbr_cycles(u64 info) { + u16 cycles = info & LBR_INFO_CYCLES; + if (static_cpu_has(X86_FEATURE_ARCH_LBR) && - !(x86_pmu.lbr_timed_lbr && info & LBR_INFO_CYC_CNT_VALID)) - return 0; + (!static_branch_likely(&x86_lbr_cycles) || + !(info & LBR_INFO_CYC_CNT_VALID))) + cycles = 0; - return info & LBR_INFO_CYCLES; + return cycles; } static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, @@ -961,7 +954,7 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, e->from = from; e->to = to; e->mispred = get_lbr_mispred(info); - e->predicted = get_lbr_predicted(info); + e->predicted = !e->mispred; e->in_tx = !!(info & LBR_INFO_IN_TX); e->abort = !!(info & LBR_INFO_ABORT); e->cycles = get_lbr_cycles(info); @@ -1120,7 +1113,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) && (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) && - (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)) + x86_pmu.lbr_has_info) reg->config |= LBR_NO_INFO; return 0; @@ -1706,6 +1699,38 @@ void intel_pmu_lbr_init_knl(void) x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS; } +void intel_pmu_lbr_init(void) +{ + switch (x86_pmu.intel_cap.lbr_format) { + case LBR_FORMAT_EIP_FLAGS2: + x86_pmu.lbr_has_tsx = 1; + fallthrough; + case LBR_FORMAT_EIP_FLAGS: + x86_pmu.lbr_from_flags = 1; + break; + + case LBR_FORMAT_INFO: + x86_pmu.lbr_has_tsx = 1; + fallthrough; + case LBR_FORMAT_INFO2: + x86_pmu.lbr_has_info = 1; + break; + + case LBR_FORMAT_TIME: + x86_pmu.lbr_from_flags = 1; + x86_pmu.lbr_to_cycles = 1; + break; + } + + if (x86_pmu.lbr_has_info) { + /* + * Only used in combination with baseline pebs. + */ + static_branch_enable(&x86_lbr_mispred); + static_branch_enable(&x86_lbr_cycles); + } +} + /* * LBR state size is variable based on the max number of registers. * This calculates the expected state size, which should match @@ -1726,6 +1751,9 @@ static bool is_arch_lbr_xsave_available(void) * Check the LBR state with the corresponding software structure. * Disable LBR XSAVES support if the size doesn't match. */ + if (xfeature_size(XFEATURE_LBR) == 0) + return false; + if (WARN_ON(xfeature_size(XFEATURE_LBR) != get_lbr_state_size())) return false; @@ -1765,6 +1793,12 @@ void __init intel_pmu_arch_lbr_init(void) x86_pmu.lbr_br_type = ecx.split.lbr_br_type; x86_pmu.lbr_nr = lbr_nr; + if (x86_pmu.lbr_mispred) + static_branch_enable(&x86_lbr_mispred); + if (x86_pmu.lbr_timed_lbr) + static_branch_enable(&x86_lbr_cycles); + if (x86_pmu.lbr_br_type) + static_branch_enable(&x86_lbr_type); arch_lbr_xsave = is_arch_lbr_xsave_available(); if (arch_lbr_xsave) { diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 7f406c14715f..2d33bba9a144 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -897,8 +897,9 @@ static void pt_handle_status(struct pt *pt) * means we are already losing data; need to let the decoder * know. */ - if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries) || - buf->output_off == pt_buffer_region_size(buf)) { + if (!buf->single && + (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries) || + buf->output_off == pt_buffer_region_size(buf))) { perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_TRUNCATED); advance++; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index f1ba6ab2e97e..e497da9bf427 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1762,7 +1762,7 @@ static const struct intel_uncore_init_fun rkl_uncore_init __initconst = { static const struct intel_uncore_init_fun adl_uncore_init __initconst = { .cpu_init = adl_uncore_cpu_init, - .mmio_init = tgl_uncore_mmio_init, + .mmio_init = adl_uncore_mmio_init, }; static const struct intel_uncore_init_fun icx_uncore_init __initconst = { diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index b9687980aab6..2adeaf4de4df 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -584,10 +584,11 @@ void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); void skl_uncore_cpu_init(void); void icl_uncore_cpu_init(void); -void adl_uncore_cpu_init(void); void tgl_uncore_cpu_init(void); +void adl_uncore_cpu_init(void); void tgl_uncore_mmio_init(void); void tgl_l_uncore_mmio_init(void); +void adl_uncore_mmio_init(void); int snb_pci2phy_map_init(int devid); /* uncore_snbep.c */ diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c index 3049c646fa20..6ddadb482f68 100644 --- a/arch/x86/events/intel/uncore_discovery.c +++ b/arch/x86/events/intel/uncore_discovery.c @@ -494,8 +494,8 @@ void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box) writel(0, box->io_addr); } -static void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box, - struct perf_event *event) +void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box, + struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h index 6d735611c281..cfaf558bdb6b 100644 --- a/arch/x86/events/intel/uncore_discovery.h +++ b/arch/x86/events/intel/uncore_discovery.h @@ -139,6 +139,8 @@ void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box); void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box); void intel_generic_uncore_mmio_disable_event(struct intel_uncore_box *box, struct perf_event *event); +void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box, + struct perf_event *event); void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box); void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box); diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 0f63706cdadf..f698a55bde81 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Nehalem/SandBridge/Haswell/Broadwell/Skylake uncore support */ #include "uncore.h" +#include "uncore_discovery.h" /* Uncore IMC PCI IDs */ #define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100 @@ -64,6 +65,20 @@ #define PCI_DEVICE_ID_INTEL_RKL_2_IMC 0x4c53 #define PCI_DEVICE_ID_INTEL_ADL_1_IMC 0x4660 #define PCI_DEVICE_ID_INTEL_ADL_2_IMC 0x4641 +#define PCI_DEVICE_ID_INTEL_ADL_3_IMC 0x4601 +#define PCI_DEVICE_ID_INTEL_ADL_4_IMC 0x4602 +#define PCI_DEVICE_ID_INTEL_ADL_5_IMC 0x4609 +#define PCI_DEVICE_ID_INTEL_ADL_6_IMC 0x460a +#define PCI_DEVICE_ID_INTEL_ADL_7_IMC 0x4621 +#define PCI_DEVICE_ID_INTEL_ADL_8_IMC 0x4623 +#define PCI_DEVICE_ID_INTEL_ADL_9_IMC 0x4629 +#define PCI_DEVICE_ID_INTEL_ADL_10_IMC 0x4637 +#define PCI_DEVICE_ID_INTEL_ADL_11_IMC 0x463b +#define PCI_DEVICE_ID_INTEL_ADL_12_IMC 0x4648 +#define PCI_DEVICE_ID_INTEL_ADL_13_IMC 0x4649 +#define PCI_DEVICE_ID_INTEL_ADL_14_IMC 0x4650 +#define PCI_DEVICE_ID_INTEL_ADL_15_IMC 0x4668 +#define PCI_DEVICE_ID_INTEL_ADL_16_IMC 0x4670 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -155,6 +170,7 @@ DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(chmask, chmask, "config:8-11"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); @@ -1334,6 +1350,62 @@ static const struct pci_device_id tgl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_2_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_4_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_5_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_6_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_7_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_8_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_9_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_10_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_11_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_12_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_13_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_14_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_15_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ } }; @@ -1390,7 +1462,8 @@ static struct pci_dev *tgl_uncore_get_mc_dev(void) #define TGL_UNCORE_MMIO_IMC_MEM_OFFSET 0x10000 #define TGL_UNCORE_PCI_IMC_MAP_SIZE 0xe000 -static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +static void __uncore_imc_init_box(struct intel_uncore_box *box, + unsigned int base_offset) { struct pci_dev *pdev = tgl_uncore_get_mc_dev(); struct intel_uncore_pmu *pmu = box->pmu; @@ -1417,11 +1490,17 @@ static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) addr |= ((resource_size_t)mch_bar << 32); #endif + addr += base_offset; box->io_addr = ioremap(addr, type->mmio_map_size); if (!box->io_addr) pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name); } +static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +{ + __uncore_imc_init_box(box, 0); +} + static struct intel_uncore_ops tgl_uncore_imc_freerunning_ops = { .init_box = tgl_uncore_imc_freerunning_init_box, .exit_box = uncore_mmio_exit_box, @@ -1469,3 +1548,136 @@ void tgl_uncore_mmio_init(void) } /* end of Tiger Lake MMIO uncore support */ + +/* Alder Lake MMIO uncore support */ +#define ADL_UNCORE_IMC_BASE 0xd900 +#define ADL_UNCORE_IMC_MAP_SIZE 0x200 +#define ADL_UNCORE_IMC_CTR 0xe8 +#define ADL_UNCORE_IMC_CTRL 0xd0 +#define ADL_UNCORE_IMC_GLOBAL_CTL 0xc0 +#define ADL_UNCORE_IMC_BOX_CTL 0xc4 +#define ADL_UNCORE_IMC_FREERUNNING_BASE 0xd800 +#define ADL_UNCORE_IMC_FREERUNNING_MAP_SIZE 0x100 + +#define ADL_UNCORE_IMC_CTL_FRZ (1 << 0) +#define ADL_UNCORE_IMC_CTL_RST_CTRL (1 << 1) +#define ADL_UNCORE_IMC_CTL_RST_CTRS (1 << 2) +#define ADL_UNCORE_IMC_CTL_INT (ADL_UNCORE_IMC_CTL_RST_CTRL | \ + ADL_UNCORE_IMC_CTL_RST_CTRS) + +static void adl_uncore_imc_init_box(struct intel_uncore_box *box) +{ + __uncore_imc_init_box(box, ADL_UNCORE_IMC_BASE); + + /* The global control in MC1 can control both MCs. */ + if (box->io_addr && (box->pmu->pmu_idx == 1)) + writel(ADL_UNCORE_IMC_CTL_INT, box->io_addr + ADL_UNCORE_IMC_GLOBAL_CTL); +} + +static void adl_uncore_mmio_disable_box(struct intel_uncore_box *box) +{ + if (!box->io_addr) + return; + + writel(ADL_UNCORE_IMC_CTL_FRZ, box->io_addr + uncore_mmio_box_ctl(box)); +} + +static void adl_uncore_mmio_enable_box(struct intel_uncore_box *box) +{ + if (!box->io_addr) + return; + + writel(0, box->io_addr + uncore_mmio_box_ctl(box)); +} + +static struct intel_uncore_ops adl_uncore_mmio_ops = { + .init_box = adl_uncore_imc_init_box, + .exit_box = uncore_mmio_exit_box, + .disable_box = adl_uncore_mmio_disable_box, + .enable_box = adl_uncore_mmio_enable_box, + .disable_event = intel_generic_uncore_mmio_disable_event, + .enable_event = intel_generic_uncore_mmio_enable_event, + .read_counter = uncore_mmio_read_counter, +}; + +#define ADL_UNC_CTL_CHMASK_MASK 0x00000f00 +#define ADL_UNC_IMC_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + ADL_UNC_CTL_CHMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET) + +static struct attribute *adl_uncore_imc_formats_attr[] = { + &format_attr_event.attr, + &format_attr_chmask.attr, + &format_attr_edge.attr, + NULL, +}; + +static const struct attribute_group adl_uncore_imc_format_group = { + .name = "format", + .attrs = adl_uncore_imc_formats_attr, +}; + +static struct intel_uncore_type adl_uncore_imc = { + .name = "imc", + .num_counters = 5, + .num_boxes = 2, + .perf_ctr_bits = 64, + .perf_ctr = ADL_UNCORE_IMC_CTR, + .event_ctl = ADL_UNCORE_IMC_CTRL, + .event_mask = ADL_UNC_IMC_EVENT_MASK, + .box_ctl = ADL_UNCORE_IMC_BOX_CTL, + .mmio_offset = 0, + .mmio_map_size = ADL_UNCORE_IMC_MAP_SIZE, + .ops = &adl_uncore_mmio_ops, + .format_group = &adl_uncore_imc_format_group, +}; + +enum perf_adl_uncore_imc_freerunning_types { + ADL_MMIO_UNCORE_IMC_DATA_TOTAL, + ADL_MMIO_UNCORE_IMC_DATA_READ, + ADL_MMIO_UNCORE_IMC_DATA_WRITE, + ADL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX +}; + +static struct freerunning_counters adl_uncore_imc_freerunning[] = { + [ADL_MMIO_UNCORE_IMC_DATA_TOTAL] = { 0x40, 0x0, 0x0, 1, 64 }, + [ADL_MMIO_UNCORE_IMC_DATA_READ] = { 0x58, 0x0, 0x0, 1, 64 }, + [ADL_MMIO_UNCORE_IMC_DATA_WRITE] = { 0xA0, 0x0, 0x0, 1, 64 }, +}; + +static void adl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +{ + __uncore_imc_init_box(box, ADL_UNCORE_IMC_FREERUNNING_BASE); +} + +static struct intel_uncore_ops adl_uncore_imc_freerunning_ops = { + .init_box = adl_uncore_imc_freerunning_init_box, + .exit_box = uncore_mmio_exit_box, + .read_counter = uncore_mmio_read_counter, + .hw_config = uncore_freerunning_hw_config, +}; + +static struct intel_uncore_type adl_uncore_imc_free_running = { + .name = "imc_free_running", + .num_counters = 3, + .num_boxes = 2, + .num_freerunning_types = ADL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX, + .mmio_map_size = ADL_UNCORE_IMC_FREERUNNING_MAP_SIZE, + .freerunning = adl_uncore_imc_freerunning, + .ops = &adl_uncore_imc_freerunning_ops, + .event_descs = tgl_uncore_imc_events, + .format_group = &tgl_uncore_imc_format_group, +}; + +static struct intel_uncore_type *adl_mmio_uncores[] = { + &adl_uncore_imc, + &adl_uncore_imc_free_running, + NULL +}; + +void adl_uncore_mmio_init(void) +{ + uncore_mmio_uncores = adl_mmio_uncores; +} + +/* end of Alder Lake MMIO uncore support */ diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 3660f698fb2a..ed869443efb2 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -5482,7 +5482,7 @@ static struct intel_uncore_type icx_uncore_imc = { .fixed_ctr_bits = 48, .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, - .event_descs = hswep_uncore_imc_events, + .event_descs = snr_uncore_imc_events, .perf_ctr = SNR_IMC_MMIO_PMON_CTR0, .event_ctl = SNR_IMC_MMIO_PMON_CTL0, .event_mask = SNBEP_PMON_RAW_EVENT_MASK, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 9d376e528dfc..150261d929b9 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -215,7 +215,8 @@ enum { LBR_FORMAT_EIP_FLAGS2 = 0x04, LBR_FORMAT_INFO = 0x05, LBR_FORMAT_TIME = 0x06, - LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_TIME, + LBR_FORMAT_INFO2 = 0x07, + LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_INFO2, }; enum { @@ -840,6 +841,11 @@ struct x86_pmu { bool lbr_double_abort; /* duplicated lbr aborts */ bool lbr_pt_coexist; /* (LBR|BTS) may coexist with PT */ + unsigned int lbr_has_info:1; + unsigned int lbr_has_tsx:1; + unsigned int lbr_from_flags:1; + unsigned int lbr_to_cycles:1; + /* * Intel Architectural LBR CPUID Enumeration */ @@ -1392,6 +1398,8 @@ void intel_pmu_lbr_init_skl(void); void intel_pmu_lbr_init_knl(void); +void intel_pmu_lbr_init(void); + void intel_pmu_arch_lbr_init(void); void intel_pmu_pebs_data_source_nhm(void); diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 85feafacc445..77e3a47af5ad 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -536,11 +536,14 @@ static struct perf_msr intel_rapl_spr_msrs[] = { * - perf_msr_probe(PERF_RAPL_MAX) * - want to use same event codes across both architectures */ -static struct perf_msr amd_rapl_msrs[PERF_RAPL_MAX] = { - [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr }, +static struct perf_msr amd_rapl_msrs[] = { + [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, 0, false, 0 }, + [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, 0, false, 0 }, + [PERF_RAPL_PP1] = { 0, &rapl_events_gpu_group, 0, false, 0 }, + [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, 0, false, 0 }, }; - static int rapl_cpu_offline(unsigned int cpu) { struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 84b87538a15d..bab883c0b6fe 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -22,7 +22,7 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE -#define _BUG_FLAGS(ins, flags) \ +#define _BUG_FLAGS(ins, flags, extra) \ do { \ asm_inline volatile("1:\t" ins "\n" \ ".pushsection __bug_table,\"aw\"\n" \ @@ -31,7 +31,8 @@ do { \ "\t.word %c1" "\t# bug_entry::line\n" \ "\t.word %c2" "\t# bug_entry::flags\n" \ "\t.org 2b+%c3\n" \ - ".popsection" \ + ".popsection\n" \ + extra \ : : "i" (__FILE__), "i" (__LINE__), \ "i" (flags), \ "i" (sizeof(struct bug_entry))); \ @@ -39,14 +40,15 @@ do { \ #else /* !CONFIG_DEBUG_BUGVERBOSE */ -#define _BUG_FLAGS(ins, flags) \ +#define _BUG_FLAGS(ins, flags, extra) \ do { \ asm_inline volatile("1:\t" ins "\n" \ ".pushsection __bug_table,\"aw\"\n" \ "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ "\t.word %c0" "\t# bug_entry::flags\n" \ "\t.org 2b+%c1\n" \ - ".popsection" \ + ".popsection\n" \ + extra \ : : "i" (flags), \ "i" (sizeof(struct bug_entry))); \ } while (0) @@ -55,7 +57,7 @@ do { \ #else -#define _BUG_FLAGS(ins, flags) asm volatile(ins) +#define _BUG_FLAGS(ins, flags, extra) asm volatile(ins) #endif /* CONFIG_GENERIC_BUG */ @@ -63,8 +65,8 @@ do { \ #define BUG() \ do { \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, 0); \ - unreachable(); \ + _BUG_FLAGS(ASM_UD2, 0, ""); \ + __builtin_unreachable(); \ } while (0) /* @@ -75,9 +77,9 @@ do { \ */ #define __WARN_FLAGS(flags) \ do { \ + __auto_type f = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags)); \ - annotate_reachable(); \ + _BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6db4e2932b3d..65d147974f8d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -204,7 +204,7 @@ /* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 631d5040b31e..d39e0de06be2 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -82,7 +82,7 @@ KVM_X86_OP_NULL(guest_apic_has_interrupt) KVM_X86_OP(load_eoi_exitmap) KVM_X86_OP(set_virtual_apic_mode) KVM_X86_OP_NULL(set_apic_access_page_addr) -KVM_X86_OP(deliver_posted_interrupt) +KVM_X86_OP(deliver_interrupt) KVM_X86_OP_NULL(sync_pir_to_irr) KVM_X86_OP(set_tss_addr) KVM_X86_OP(set_identity_map_addr) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1384517d7709..ec9830d2aabf 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -703,7 +703,6 @@ struct kvm_vcpu_arch { struct fpu_guest guest_fpu; u64 xcr0; - u64 guest_supported_xcr0; struct kvm_pio_request pio; void *pio_data; @@ -1410,7 +1409,8 @@ struct kvm_x86_ops { void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu); - int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); + void (*deliver_interrupt)(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); @@ -1483,7 +1483,8 @@ struct kvm_x86_ops { int (*get_msr_feature)(struct kvm_msr_entry *entry); - bool (*can_emulate_instruction)(struct kvm_vcpu *vcpu, void *insn, int insn_len); + bool (*can_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu); @@ -1496,6 +1497,7 @@ struct kvm_x86_ops { }; struct kvm_x86_nested_ops { + void (*leave_nested)(struct kvm_vcpu *vcpu); int (*check_events)(struct kvm_vcpu *vcpu); bool (*hv_timer_pending)(struct kvm_vcpu *vcpu); void (*triple_fault)(struct kvm_vcpu *vcpu); @@ -1861,7 +1863,6 @@ int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); -void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3faf0f97edb1..a4a39c3e0f19 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -476,6 +476,7 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index cc74dc584836..acbaeaf83b61 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -84,7 +84,7 @@ #ifdef CONFIG_RETPOLINE ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(jmp __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE #else jmp *%\reg #endif @@ -94,7 +94,7 @@ #ifdef CONFIG_RETPOLINE ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \ __stringify(call __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_LFENCE #else call *%\reg #endif @@ -146,7 +146,7 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ - X86_FEATURE_RETPOLINE_AMD) + X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "r" (addr) @@ -176,7 +176,7 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ - X86_FEATURE_RETPOLINE_AMD) + X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif @@ -188,9 +188,11 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, - SPECTRE_V2_RETPOLINE_GENERIC, - SPECTRE_V2_RETPOLINE_AMD, - SPECTRE_V2_IBRS_ENHANCED, + SPECTRE_V2_RETPOLINE, + SPECTRE_V2_LFENCE, + SPECTRE_V2_EIBRS, + SPECTRE_V2_EIBRS_RETPOLINE, + SPECTRE_V2_EIBRS_LFENCE, }; /* The indirect branch speculation control variants */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index b00dbc5fac2b..bb2fb78523ce 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -220,6 +220,42 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_NESTED_CTL_SEV_ENABLE BIT(1) #define SVM_NESTED_CTL_SEV_ES_ENABLE BIT(2) + +/* AVIC */ +#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) +#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 +#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) + +#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) +#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) +#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) +#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) +#define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFF) + +#define AVIC_DOORBELL_PHYSICAL_ID_MASK (0xFF) + +#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 +#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 +#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF + +enum avic_ipi_failure_cause { + AVIC_IPI_FAILURE_INVALID_INT_TYPE, + AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, + AVIC_IPI_FAILURE_INVALID_TARGET, + AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, +}; + + +/* + * 0xff is broadcast, so the max index allowed for physical APIC ID + * table is 0xfe. APIC IDs above 0xff are reserved. + */ +#define AVIC_MAX_PHYSICAL_ID_COUNT 0xff + +#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) +#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL + + struct vmcb_seg { u16 selector; u16 attrib; diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h index a9630104f1c4..78e667a31d6c 100644 --- a/arch/x86/include/asm/xen/cpuid.h +++ b/arch/x86/include/asm/xen/cpuid.h @@ -100,6 +100,13 @@ /* Memory mapped from other domains has valid IOMMU entries */ #define XEN_HVM_CPUID_IOMMU_MAPPINGS (1u << 2) #define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3) /* vcpu id is present in EBX */ +#define XEN_HVM_CPUID_DOMID_PRESENT (1u << 4) /* domid is present in ECX */ +/* + * Bits 55:49 from the IO-APIC RTE and bits 11:5 from the MSI address can be + * used to store high bits for the Destination ID. This expands the Destination + * ID field from 8 to 15 bits, allowing to target APIC IDs up 32768. + */ +#define XEN_HVM_CPUID_EXT_DEST_ID (1u << 5) /* * Leaf 6 (0x40000x05) diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 1bf2ad34188a..16f548a661cf 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -43,20 +43,6 @@ static inline uint32_t xen_cpuid_base(void) return hypervisor_cpuid_base("XenVMMXenVMM", 2); } -#ifdef CONFIG_XEN -extern bool __init xen_hvm_need_lapic(void); - -static inline bool __init xen_x2apic_para_available(void) -{ - return xen_hvm_need_lapic(); -} -#else -static inline bool __init xen_x2apic_para_available(void) -{ - return (xen_cpuid_base() != 0); -} -#endif - struct pci_dev; #ifdef CONFIG_XEN_PV_DOM0 diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 2da3316bb559..bf6e96011dfe 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -452,6 +452,9 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 +/* attributes for system fd (group 0) */ +#define KVM_X86_XCOMP_GUEST_SUPP 0 + struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5007c3ffe96f..b4470eabf151 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -389,7 +389,7 @@ static int emit_indirect(int op, int reg, u8 *bytes) * * CALL *%\reg * - * It also tries to inline spectre_v2=retpoline,amd when size permits. + * It also tries to inline spectre_v2=retpoline,lfence when size permits. */ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) { @@ -407,7 +407,7 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) BUG_ON(reg == 4); if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) && - !cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) + !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) return -1; op = insn->opcode.bytes[0]; @@ -438,9 +438,9 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) } /* - * For RETPOLINE_AMD: prepend the indirect CALL/JMP with an LFENCE. + * For RETPOLINE_LFENCE: prepend the indirect CALL/JMP with an LFENCE. */ - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) { + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { bytes[i++] = 0x0f; bytes[i++] = 0xae; bytes[i++] = 0xe8; /* LFENCE */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1c1f218a701d..6296e1ebed1d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -16,6 +16,7 @@ #include <linux/prctl.h> #include <linux/sched/smt.h> #include <linux/pgtable.h> +#include <linux/bpf.h> #include <asm/spec-ctrl.h> #include <asm/cmdline.h> @@ -650,6 +651,32 @@ static inline const char *spectre_v2_module_string(void) static inline const char *spectre_v2_module_string(void) { return ""; } #endif +#define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n" +#define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n" +#define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n" + +#ifdef CONFIG_BPF_SYSCALL +void unpriv_ebpf_notify(int new_state) +{ + if (new_state) + return; + + /* Unprivileged eBPF is enabled */ + + switch (spectre_v2_enabled) { + case SPECTRE_V2_EIBRS: + pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); + break; + case SPECTRE_V2_EIBRS_LFENCE: + if (sched_smt_active()) + pr_err(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); + break; + default: + break; + } +} +#endif + static inline bool match_option(const char *arg, int arglen, const char *opt) { int len = strlen(opt); @@ -664,7 +691,10 @@ enum spectre_v2_mitigation_cmd { SPECTRE_V2_CMD_FORCE, SPECTRE_V2_CMD_RETPOLINE, SPECTRE_V2_CMD_RETPOLINE_GENERIC, - SPECTRE_V2_CMD_RETPOLINE_AMD, + SPECTRE_V2_CMD_RETPOLINE_LFENCE, + SPECTRE_V2_CMD_EIBRS, + SPECTRE_V2_CMD_EIBRS_RETPOLINE, + SPECTRE_V2_CMD_EIBRS_LFENCE, }; enum spectre_v2_user_cmd { @@ -737,6 +767,13 @@ spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd) return SPECTRE_V2_USER_CMD_AUTO; } +static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) +{ + return (mode == SPECTRE_V2_EIBRS || + mode == SPECTRE_V2_EIBRS_RETPOLINE || + mode == SPECTRE_V2_EIBRS_LFENCE); +} + static void __init spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) { @@ -804,7 +841,7 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return; /* @@ -824,9 +861,11 @@ set_mode: static const char * const spectre_v2_strings[] = { [SPECTRE_V2_NONE] = "Vulnerable", - [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", - [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", - [SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS", + [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines", + [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE", + [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", + [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", + [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", }; static const struct { @@ -837,8 +876,12 @@ static const struct { { "off", SPECTRE_V2_CMD_NONE, false }, { "on", SPECTRE_V2_CMD_FORCE, true }, { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, - { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false }, + { "retpoline,lfence", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false }, { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "eibrs", SPECTRE_V2_CMD_EIBRS, false }, + { "eibrs,lfence", SPECTRE_V2_CMD_EIBRS_LFENCE, false }, + { "eibrs,retpoline", SPECTRE_V2_CMD_EIBRS_RETPOLINE, false }, { "auto", SPECTRE_V2_CMD_AUTO, false }, }; @@ -875,10 +918,30 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if ((cmd == SPECTRE_V2_CMD_RETPOLINE || - cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || - cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + cmd == SPECTRE_V2_CMD_RETPOLINE_LFENCE || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC || + cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || + cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && !IS_ENABLED(CONFIG_RETPOLINE)) { - pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if ((cmd == SPECTRE_V2_CMD_EIBRS || + cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || + cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { + pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if ((cmd == SPECTRE_V2_CMD_RETPOLINE_LFENCE || + cmd == SPECTRE_V2_CMD_EIBRS_LFENCE) && + !boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { + pr_err("%s selected, but CPU doesn't have a serializing LFENCE. Switching to AUTO select\n", + mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -887,6 +950,16 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return cmd; } +static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) +{ + if (!IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("Kernel not compiled with retpoline; no mitigation available!"); + return SPECTRE_V2_NONE; + } + + return SPECTRE_V2_RETPOLINE; +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -907,49 +980,64 @@ static void __init spectre_v2_select_mitigation(void) case SPECTRE_V2_CMD_FORCE: case SPECTRE_V2_CMD_AUTO: if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { - mode = SPECTRE_V2_IBRS_ENHANCED; - /* Force it so VMEXIT will restore correctly */ - x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); - goto specv2_set_mode; + mode = SPECTRE_V2_EIBRS; + break; } - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_auto; + + mode = spectre_v2_select_retpoline(); break; - case SPECTRE_V2_CMD_RETPOLINE_AMD: - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_amd; + + case SPECTRE_V2_CMD_RETPOLINE_LFENCE: + pr_err(SPECTRE_V2_LFENCE_MSG); + mode = SPECTRE_V2_LFENCE; break; + case SPECTRE_V2_CMD_RETPOLINE_GENERIC: - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_generic; + mode = SPECTRE_V2_RETPOLINE; break; + case SPECTRE_V2_CMD_RETPOLINE: - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_auto; + mode = spectre_v2_select_retpoline(); + break; + + case SPECTRE_V2_CMD_EIBRS: + mode = SPECTRE_V2_EIBRS; + break; + + case SPECTRE_V2_CMD_EIBRS_LFENCE: + mode = SPECTRE_V2_EIBRS_LFENCE; + break; + + case SPECTRE_V2_CMD_EIBRS_RETPOLINE: + mode = SPECTRE_V2_EIBRS_RETPOLINE; break; } - pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!"); - return; -retpoline_auto: - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { - retpoline_amd: - if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { - pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); - goto retpoline_generic; - } - mode = SPECTRE_V2_RETPOLINE_AMD; - setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); - setup_force_cpu_cap(X86_FEATURE_RETPOLINE); - } else { - retpoline_generic: - mode = SPECTRE_V2_RETPOLINE_GENERIC; + if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) + pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); + + if (spectre_v2_in_eibrs_mode(mode)) { + /* Force it so VMEXIT will restore correctly */ + x86_spec_ctrl_base |= SPEC_CTRL_IBRS; + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + } + + switch (mode) { + case SPECTRE_V2_NONE: + case SPECTRE_V2_EIBRS: + break; + + case SPECTRE_V2_LFENCE: + case SPECTRE_V2_EIBRS_LFENCE: + setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE); + fallthrough; + + case SPECTRE_V2_RETPOLINE: + case SPECTRE_V2_EIBRS_RETPOLINE: setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + break; } -specv2_set_mode: spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -975,7 +1063,7 @@ specv2_set_mode: * the CPU supports Enhanced IBRS, kernel might un-intentionally not * enable IBRS around firmware calls. */ - if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) { + if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_eibrs_mode(mode)) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } @@ -1045,6 +1133,10 @@ void cpu_bugs_smt_update(void) { mutex_lock(&spec_ctrl_mutex); + if (sched_smt_active() && unprivileged_ebpf_enabled() && + spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) + pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: break; @@ -1684,7 +1776,7 @@ static ssize_t tsx_async_abort_show_state(char *buf) static char *stibp_state(void) { - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return ""; switch (spectre_v2_user_stibp) { @@ -1714,6 +1806,27 @@ static char *ibpb_state(void) return ""; } +static ssize_t spectre_v2_show_state(char *buf) +{ + if (spectre_v2_enabled == SPECTRE_V2_LFENCE) + return sprintf(buf, "Vulnerable: LFENCE\n"); + + if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) + return sprintf(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); + + if (sched_smt_active() && unprivileged_ebpf_enabled() && + spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) + return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); + + return sprintf(buf, "%s%s%s%s%s%s\n", + spectre_v2_strings[spectre_v2_enabled], + ibpb_state(), + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + stibp_state(), + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + spectre_v2_module_string()); +} + static ssize_t srbds_show_state(char *buf) { return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); @@ -1739,12 +1852,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: - return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", - spectre_v2_module_string()); + return spectre_v2_show_state(buf); case X86_BUG_SPEC_STORE_BYPASS: return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index a1e2f41796dc..9f4b508886dd 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -423,7 +423,7 @@ static void threshold_restart_bank(void *_tr) u32 hi, lo; /* sysfs write might race against an offline operation */ - if (this_cpu_read(threshold_banks)) + if (!this_cpu_read(threshold_banks) && !tr->set_lvt_off) return; rdmsr(tr->b->address, lo, hi); diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index bb9a46a804bf..baafbb37be67 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -486,6 +486,7 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ICELAKE_X: + case INTEL_FAM6_ICELAKE_D: case INTEL_FAM6_SAPPHIRERAPIDS_X: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 001808e3901c..48afe96ae0f0 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -410,6 +410,8 @@ void sgx_encl_release(struct kref *ref) } kfree(entry); + /* Invoke scheduler to prevent soft lockups. */ + cond_resched(); } xa_destroy(&encl->page_array); diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 4b41efc9e367..8e4bc6453d26 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -344,10 +344,8 @@ static void sgx_reclaim_pages(void) { struct sgx_epc_page *chunk[SGX_NR_TO_SCAN]; struct sgx_backing backing[SGX_NR_TO_SCAN]; - struct sgx_epc_section *section; struct sgx_encl_page *encl_page; struct sgx_epc_page *epc_page; - struct sgx_numa_node *node; pgoff_t page_index; int cnt = 0; int ret; @@ -418,13 +416,7 @@ skip: kref_put(&encl_page->encl->refcount, sgx_encl_release); epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED; - section = &sgx_epc_sections[epc_page->section]; - node = section->node; - - spin_lock(&node->lock); - list_add_tail(&epc_page->list, &node->free_page_list); - spin_unlock(&node->lock); - atomic_long_inc(&sgx_nr_free_pages); + sgx_free_epc_page(epc_page); } } diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 437d7c930c0b..75ffaef8c299 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -91,11 +91,9 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, const void *kbuf, const void __user *ubuf) { struct fpu *fpu = &target->thread.fpu; - struct user32_fxsr_struct newstate; + struct fxregs_state newstate; int ret; - BUILD_BUG_ON(sizeof(newstate) != sizeof(struct fxregs_state)); - if (!cpu_feature_enabled(X86_FEATURE_FXSR)) return -ENODEV; @@ -116,9 +114,10 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, /* Copy the state */ memcpy(&fpu->fpstate->regs.fxsave, &newstate, sizeof(newstate)); - /* Clear xmm8..15 */ + /* Clear xmm8..15 for 32-bit callers */ BUILD_BUG_ON(sizeof(fpu->__fpstate.regs.fxsave.xmm_space) != 16 * 16); - memset(&fpu->fpstate->regs.fxsave.xmm_space[8], 0, 8 * 16); + if (in_ia32_syscall()) + memset(&fpu->fpstate->regs.fxsave.xmm_space[8*4], 0, 8 * 16); /* Mark FP and SSE as in use when XSAVE is enabled */ if (use_xsave()) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 02b3ddaf4f75..7c7824ae7862 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1558,7 +1558,10 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; - newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; + + if (!guest_fpu) + newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; + newfps->xfd = curfps->xfd & ~xfeatures; /* Do the final updates within the locked region */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a438217cbfac..d77481ecb0d5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -462,19 +462,24 @@ static bool pv_tlb_flush_supported(void) { return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) && + !boot_cpu_has(X86_FEATURE_MWAIT) && + (num_possible_cpus() != 1)); } static bool pv_ipi_supported(void) { - return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI); + return (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI) && + (num_possible_cpus() != 1)); } static bool pv_sched_yield_supported(void) { return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) && + !boot_cpu_has(X86_FEATURE_MWAIT) && + (num_possible_cpus() != 1)); } #define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG) @@ -619,7 +624,7 @@ static void kvm_smp_send_call_func_ipi(const struct cpumask *mask) /* Make sure other vCPUs get a chance to run if they need to. */ for_each_cpu(cpu, mask) { - if (vcpu_is_preempted(cpu)) { + if (!idle_cpu(cpu) && vcpu_is_preempted(cpu)) { kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu)); break; } diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index a35cbf9107af..c5caa7311bd8 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -239,6 +239,9 @@ static void __init kvmclock_init_mem(void) static int __init kvm_setup_vsyscall_timeinfo(void) { + if (!kvm_para_available() || !kvmclock) + return 0; + kvmclock_init_mem(); #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 6d2244c94799..8d2f2f995539 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1224,7 +1224,7 @@ static struct user_regset x86_64_regsets[] __ro_after_init = { }, [REGSET_FP] = { .core_note_type = NT_PRFPREG, - .n = sizeof(struct user_i387_struct) / sizeof(long), + .n = sizeof(struct fxregs_state) / sizeof(long), .size = sizeof(long), .align = sizeof(long), .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set }, @@ -1271,7 +1271,7 @@ static struct user_regset x86_32_regsets[] __ro_after_init = { }, [REGSET_XFP] = { .core_note_type = NT_PRXFPREG, - .n = sizeof(struct user32_fxsr_struct) / sizeof(u32), + .n = sizeof(struct fxregs_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set }, diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 9ae64f9af956..9b9fb7882c20 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/dmi.h> #include <linux/ioport.h> #include <asm/e820/api.h> @@ -24,31 +23,11 @@ static void resource_clip(struct resource *res, resource_size_t start, res->start = end + 1; } -/* - * Some BIOS-es contain a bug where they add addresses which map to - * system RAM in the PCI host bridge window returned by the ACPI _CRS - * method, see commit 4dc2287c1805 ("x86: avoid E820 regions when - * allocating address space"). To avoid this Linux by default excludes - * E820 reservations when allocating addresses since 2010. - * In 2019 some systems have shown-up with E820 reservations which cover - * the entire _CRS returned PCI host bridge window, causing all attempts - * to assign memory to PCI BARs to fail if Linux uses E820 reservations. - * - * Ideally Linux would fully stop using E820 reservations, but then - * the old systems this was added for will regress. - * Instead keep the old behavior for old systems, while ignoring the - * E820 reservations for any systems from now on. - */ static void remove_e820_regions(struct resource *avail) { - int i, year = dmi_get_bios_year(); + int i; struct e820_entry *entry; - if (year >= 2018) - return; - - pr_info_once("PCI: Removing E820 reservations from host bridge windows\n"); - for (i = 0; i < e820_table->nr_entries; i++) { entry = &e820_table->entries[i]; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 3902c28fb6cb..b8f8d268d058 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -133,6 +133,7 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 orig = &vcpu->arch.cpuid_entries[i]; if (e2[i].function != orig->function || e2[i].index != orig->index || + e2[i].flags != orig->flags || e2[i].eax != orig->eax || e2[i].ebx != orig->ebx || e2[i].ecx != orig->ecx || e2[i].edx != orig->edx) return -EINVAL; @@ -196,10 +197,26 @@ void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) vcpu->arch.pv_cpuid.features = best->eax; } +/* + * Calculate guest's supported XCR0 taking into account guest CPUID data and + * supported_xcr0 (comprised of host configuration and KVM_SUPPORTED_XCR0). + */ +static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent) +{ + struct kvm_cpuid_entry2 *best; + + best = cpuid_entry2_find(entries, nent, 0xd, 0); + if (!best) + return 0; + + return (best->eax | ((u64)best->edx << 32)) & supported_xcr0; +} + static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, int nent) { struct kvm_cpuid_entry2 *best; + u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(entries, nent); best = cpuid_entry2_find(entries, nent, 1, 0); if (best) { @@ -238,6 +255,21 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT); } + + /* + * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate + * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's + * requested XCR0 value. The enclave's XFRM must be a subset of XCRO + * at the time of EENTER, thus adjust the allowed XFRM by the guest's + * supported XCR0. Similar to XCR0 handling, FP and SSE are forced to + * '1' even on CPUs that don't support XSAVE. + */ + best = cpuid_entry2_find(entries, nent, 0x12, 0x1); + if (best) { + best->ecx &= guest_supported_xcr0 & 0xffffffff; + best->edx &= guest_supported_xcr0 >> 32; + best->ecx |= XFEATURE_MASK_FPSSE; + } } void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) @@ -250,6 +282,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; + u64 guest_supported_xcr0; best = kvm_find_cpuid_entry(vcpu, 1, 0); if (best && apic) { @@ -261,27 +294,10 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - best = kvm_find_cpuid_entry(vcpu, 0xD, 0); - if (!best) - vcpu->arch.guest_supported_xcr0 = 0; - else - vcpu->arch.guest_supported_xcr0 = - (best->eax | ((u64)best->edx << 32)) & supported_xcr0; + guest_supported_xcr0 = + cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - /* - * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate - * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's - * requested XCR0 value. The enclave's XFRM must be a subset of XCRO - * at the time of EENTER, thus adjust the allowed XFRM by the guest's - * supported XCR0. Similar to XCR0 handling, FP and SSE are forced to - * '1' even on CPUs that don't support XSAVE. - */ - best = kvm_find_cpuid_entry(vcpu, 0x12, 0x1); - if (best) { - best->ecx &= vcpu->arch.guest_supported_xcr0 & 0xffffffff; - best->edx &= vcpu->arch.guest_supported_xcr0 >> 32; - best->ecx |= XFEATURE_MASK_FPSSE; - } + vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0; kvm_update_pv_runtime(vcpu); @@ -346,8 +362,14 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, * KVM_SET_CPUID{,2} again. To support this legacy behavior, check * whether the supplied CPUID data is equal to what's already set. */ - if (vcpu->arch.last_vmentry_cpu != -1) - return kvm_cpuid_check_equal(vcpu, e2, nent); + if (vcpu->arch.last_vmentry_cpu != -1) { + r = kvm_cpuid_check_equal(vcpu, e2, nent); + if (r) + return r; + + kvfree(e2); + return 0; + } r = kvm_check_cpuid(vcpu, e2, nent); if (r) @@ -535,12 +557,13 @@ void kvm_set_cpu_caps(void) ); kvm_cpu_cap_mask(CPUID_7_0_EBX, - F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | - F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | 0 /*MPX*/ | F(RDSEED) | - F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | - F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | - F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/ - ); + F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | + F(FDP_EXCPTN_ONLY) | F(SMEP) | F(BMI2) | F(ERMS) | F(INVPCID) | + F(RTM) | F(ZERO_FCS_FDS) | 0 /*MPX*/ | F(AVX512F) | + F(AVX512DQ) | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512IFMA) | + F(CLFLUSHOPT) | F(CLWB) | 0 /*INTEL_PT*/ | F(AVX512PF) | + F(AVX512ER) | F(AVX512CD) | F(SHA_NI) | F(AVX512BW) | + F(AVX512VL)); kvm_cpu_cap_mask(CPUID_7_ECX, F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) | @@ -887,13 +910,14 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) } break; case 0xd: { - u64 guest_perm = xstate_get_guest_group_perm(); + u64 permitted_xcr0 = supported_xcr0 & xstate_get_guest_group_perm(); + u64 permitted_xss = supported_xss; - entry->eax &= supported_xcr0 & guest_perm; - entry->ebx = xstate_required_size(supported_xcr0, false); + entry->eax &= permitted_xcr0; + entry->ebx = xstate_required_size(permitted_xcr0, false); entry->ecx = entry->ebx; - entry->edx &= (supported_xcr0 & guest_perm) >> 32; - if (!supported_xcr0) + entry->edx &= permitted_xcr0 >> 32; + if (!permitted_xcr0) break; entry = do_host_cpuid(array, function, 1); @@ -902,20 +926,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) cpuid_entry_override(entry, CPUID_D_1_EAX); if (entry->eax & (F(XSAVES)|F(XSAVEC))) - entry->ebx = xstate_required_size(supported_xcr0 | supported_xss, + entry->ebx = xstate_required_size(permitted_xcr0 | permitted_xss, true); else { - WARN_ON_ONCE(supported_xss != 0); + WARN_ON_ONCE(permitted_xss != 0); entry->ebx = 0; } - entry->ecx &= supported_xss; - entry->edx &= supported_xss >> 32; + entry->ecx &= permitted_xss; + entry->edx &= permitted_xss >> 32; for (i = 2; i < 64; ++i) { bool s_state; - if (supported_xcr0 & BIT_ULL(i)) + if (permitted_xcr0 & BIT_ULL(i)) s_state = false; - else if (supported_xss & BIT_ULL(i)) + else if (permitted_xss & BIT_ULL(i)) s_state = true; else continue; @@ -929,7 +953,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * invalid sub-leafs. Only valid sub-leafs should * reach this point, and they should have a non-zero * save state size. Furthermore, check whether the - * processor agrees with supported_xcr0/supported_xss + * processor agrees with permitted_xcr0/permitted_xss * on whether this is an XCR0- or IA32_XSS-managed area. */ if (WARN_ON_ONCE(!entry->eax || (entry->ecx & 0x1) != s_state)) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index baca9fa37a91..9322e6340a74 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1096,14 +1096,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic->regs + APIC_TMR); } - if (static_call(kvm_x86_deliver_posted_interrupt)(vcpu, vector)) { - kvm_lapic_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_vcpu_kick(vcpu); - } else { - trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, - trig_mode, vector); - } + static_call(kvm_x86_deliver_interrupt)(apic, delivery_mode, + trig_mode, vector); break; case APIC_DM_REMRD: @@ -2312,7 +2306,12 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) apic->irr_pending = true; apic->isr_count = 1; } else { - apic->irr_pending = (apic_search_irr(apic) != -1); + /* + * Don't clear irr_pending, searching the IRR can race with + * updates from the CPU as APICv is still active from hardware's + * perspective. The flag will be cleared as appropriate when + * KVM injects the interrupt. + */ apic->isr_count = count_vectors(apic->regs + APIC_ISR); } } @@ -2629,7 +2628,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) kvm_apic_set_version(vcpu); apic_update_ppr(apic); - hrtimer_cancel(&apic->lapic_timer.timer); + cancel_apic_timer(apic); apic->lapic_timer.expired_tscdeadline = 0; apic_update_lvtt(apic); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 593093b52395..5628d0ba637e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3565,7 +3565,7 @@ set_root_pgd: out_unlock: write_unlock(&vcpu->kvm->mmu_lock); - return 0; + return r; } static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) @@ -3889,12 +3889,23 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) walk_shadow_page_lockless_end(vcpu); } +static u32 alloc_apf_token(struct kvm_vcpu *vcpu) +{ + /* make sure the token value is not 0 */ + u32 id = vcpu->arch.apf.id; + + if (id << 12 == 0) + vcpu->arch.apf.id = 1; + + return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; +} + static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, gfn_t gfn) { struct kvm_arch_async_pf arch; - arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; + arch.token = alloc_apf_token(vcpu); arch.gfn = gfn; arch.direct_map = vcpu->arch.mmu->direct_map; arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index f614f95acc6b..b1a02993782b 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -95,7 +95,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event, } static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, - unsigned config, bool exclude_user, + u64 config, bool exclude_user, bool exclude_kernel, bool intr, bool in_tx, bool in_tx_cp) { @@ -181,7 +181,8 @@ static int cmp_u64(const void *a, const void *b) void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) { - unsigned config, type = PERF_TYPE_RAW; + u64 config; + u32 type = PERF_TYPE_RAW; struct kvm *kvm = pmc->vcpu->kvm; struct kvm_pmu_event_filter *filter; bool allow_event = true; @@ -220,7 +221,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) } if (type == PERF_TYPE_RAW) - config = eventsel & X86_RAW_EVENT_MASK; + config = eventsel & AMD64_RAW_EVENT_MASK; if (pmc->current_config == eventsel && pmc_resume_counter(pmc)) return; diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 90364d02f22a..fb3e20791338 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -27,20 +27,6 @@ #include "irq.h" #include "svm.h" -#define SVM_AVIC_DOORBELL 0xc001011b - -#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) - -/* - * 0xff is broadcast, so the max index allowed for physical APIC ID - * table is 0xfe. APIC IDs above 0xff are reserved. - */ -#define AVIC_MAX_PHYSICAL_ID_COUNT 255 - -#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 -#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 -#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF - /* AVIC GATAG is encoded using VM and VCPU IDs */ #define AVIC_VCPU_ID_BITS 8 #define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) @@ -73,12 +59,6 @@ struct amd_svm_iommu_ir { void *data; /* Storing pointer to struct amd_ir_data */ }; -enum avic_ipi_failure_cause { - AVIC_IPI_FAILURE_INVALID_INT_TYPE, - AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, - AVIC_IPI_FAILURE_INVALID_TARGET, - AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, -}; /* Note: * This function is called from IOMMU driver to notify @@ -289,6 +269,22 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } +void avic_ring_doorbell(struct kvm_vcpu *vcpu) +{ + /* + * Note, the vCPU could get migrated to a different pCPU at any point, + * which could result in signalling the wrong/previous pCPU. But if + * that happens the vCPU is guaranteed to do a VMRUN (after being + * migrated) and thus will process pending interrupts, i.e. a doorbell + * is not needed (and the spurious one is harmless). + */ + int cpu = READ_ONCE(vcpu->cpu); + + if (cpu != get_cpu()) + wrmsrl(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); + put_cpu(); +} + static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh) { @@ -304,8 +300,13 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, kvm_for_each_vcpu(i, vcpu, kvm) { if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK, GET_APIC_DEST_FIELD(icrh), - icrl & APIC_DEST_MASK)) - kvm_vcpu_wake_up(vcpu); + icrl & APIC_DEST_MASK)) { + vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); + } } } @@ -345,8 +346,6 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh); break; case AVIC_IPI_FAILURE_INVALID_TARGET: - WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n", - index, vcpu->vcpu_id, icrh, icrl); break; case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); @@ -669,52 +668,6 @@ void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) -{ - if (!vcpu->arch.apicv_active) - return -1; - - kvm_lapic_set_irr(vec, vcpu->arch.apic); - - /* - * Pairs with the smp_mb_*() after setting vcpu->guest_mode in - * vcpu_enter_guest() to ensure the write to the vIRR is ordered before - * the read of guest_mode, which guarantees that either VMRUN will see - * and process the new vIRR entry, or that the below code will signal - * the doorbell if the vCPU is already running in the guest. - */ - smp_mb__after_atomic(); - - /* - * Signal the doorbell to tell hardware to inject the IRQ if the vCPU - * is in the guest. If the vCPU is not in the guest, hardware will - * automatically process AVIC interrupts at VMRUN. - */ - if (vcpu->mode == IN_GUEST_MODE) { - int cpu = READ_ONCE(vcpu->cpu); - - /* - * Note, the vCPU could get migrated to a different pCPU at any - * point, which could result in signalling the wrong/previous - * pCPU. But if that happens the vCPU is guaranteed to do a - * VMRUN (after being migrated) and thus will process pending - * interrupts, i.e. a doorbell is not needed (and the spurious - * one is harmless). - */ - if (cpu != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); - put_cpu(); - } else { - /* - * Wake the vCPU if it was blocking. KVM will then detect the - * pending IRQ when checking if the vCPU has a wake event. - */ - kvm_vcpu_wake_up(vcpu); - } - - return 0; -} - bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { return false; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index cf206855ebf0..39d280e7e80e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -983,9 +983,9 @@ void svm_free_nested(struct vcpu_svm *svm) /* * Forcibly leave nested mode in order to be able to reset the VCPU later on. */ -void svm_leave_nested(struct vcpu_svm *svm) +void svm_leave_nested(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu = &svm->vcpu; + struct vcpu_svm *svm = to_svm(vcpu); if (is_guest_mode(vcpu)) { svm->nested.nested_run_pending = 0; @@ -1411,7 +1411,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) { - svm_leave_nested(svm); + svm_leave_nested(vcpu); svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); return 0; } @@ -1457,18 +1457,6 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, !__nested_vmcb_check_save(vcpu, &save_cached)) goto out_free; - /* - * While the nested guest CR3 is already checked and set by - * KVM_SET_SREGS, it was set when nested state was yet loaded, - * thus MMU might not be initialized correctly. - * Set it again to fix this. - */ - - ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, - nested_npt_enabled(svm), false); - if (WARN_ON_ONCE(ret)) - goto out_free; - /* * All checks done, we can enter guest mode. Userspace provides @@ -1478,7 +1466,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, */ if (is_guest_mode(vcpu)) - svm_leave_nested(svm); + svm_leave_nested(vcpu); else svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; @@ -1494,6 +1482,20 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm_switch_vmcb(svm, &svm->nested.vmcb02); nested_vmcb02_prepare_control(svm); + + /* + * While the nested guest CR3 is already checked and set by + * KVM_SET_SREGS, it was set when nested state was yet loaded, + * thus MMU might not be initialized correctly. + * Set it again to fix this. + */ + + ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, + nested_npt_enabled(svm), false); + if (WARN_ON_ONCE(ret)) + goto out_free; + + kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); ret = 0; out_free: @@ -1532,6 +1534,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) } struct kvm_x86_nested_ops svm_nested_ops = { + .leave_nested = svm_leave_nested, .check_events = svm_check_nested_events, .triple_fault = nested_svm_triple_fault, .get_nested_state_pages = svm_get_nested_state_pages, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 6a22798eaaee..17b53457d866 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2100,8 +2100,13 @@ void __init sev_hardware_setup(void) if (!sev_enabled || !npt_enabled) goto out; - /* Does the CPU support SEV? */ - if (!boot_cpu_has(X86_FEATURE_SEV)) + /* + * SEV must obviously be supported in hardware. Sanity check that the + * CPU supports decode assists, which is mandatory for SEV guests to + * support instruction emulation. + */ + if (!boot_cpu_has(X86_FEATURE_SEV) || + WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS))) goto out; /* Retrieve SEV CPUID information */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2c99b18d76c0..fd3a00c892c7 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -290,7 +290,7 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) if ((old_efer & EFER_SVME) != (efer & EFER_SVME)) { if (!(efer & EFER_SVME)) { - svm_leave_nested(svm); + svm_leave_nested(vcpu); svm_set_gif(svm, true); /* #GP intercept is still needed for vmware backdoor */ if (!enable_vmware_backdoor) @@ -312,7 +312,11 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) return ret; } - if (svm_gp_erratum_intercept) + /* + * Never intercept #GP for SEV guests, KVM can't + * decrypt guest memory to workaround the erratum. + */ + if (svm_gp_erratum_intercept && !sev_guest(vcpu->kvm)) set_exception_intercept(svm, GP_VECTOR); } } @@ -1010,9 +1014,10 @@ static void init_vmcb(struct kvm_vcpu *vcpu) * Guest access to VMware backdoor ports could legitimately * trigger #GP because of TSS I/O permission bitmap. * We intercept those #GP and allow access to them anyway - * as VMware does. + * as VMware does. Don't intercept #GP for SEV guests as KVM can't + * decrypt guest memory to decode the faulting instruction. */ - if (enable_vmware_backdoor) + if (enable_vmware_backdoor && !sev_guest(vcpu->kvm)) set_exception_intercept(svm, GP_VECTOR); svm_set_intercept(svm, INTERCEPT_INTR); @@ -1580,6 +1585,7 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); u64 hcr0 = cr0; + bool old_paging = is_paging(vcpu); #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) { @@ -1596,8 +1602,11 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) #endif vcpu->arch.cr0 = cr0; - if (!npt_enabled) + if (!npt_enabled) { hcr0 |= X86_CR0_PG | X86_CR0_WP; + if (old_paging != is_paging(vcpu)) + svm_set_cr4(vcpu, kvm_read_cr4(vcpu)); + } /* * re-enable caching here because the QEMU bios @@ -1641,8 +1650,12 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) svm_flush_tlb(vcpu); vcpu->arch.cr4 = cr4; - if (!npt_enabled) + if (!npt_enabled) { cr4 |= X86_CR4_PAE; + + if (!is_paging(vcpu)) + cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE); + } cr4 |= host_cr4_mce; to_svm(vcpu)->vmcb->save.cr4 = cr4; vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); @@ -2091,10 +2104,6 @@ static int gp_interception(struct kvm_vcpu *vcpu) if (error_code) goto reinject; - /* All SVM instructions expect page aligned RAX */ - if (svm->vmcb->save.rax & ~PAGE_MASK) - goto reinject; - /* Decode the instruction for usage later */ if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK) goto reinject; @@ -2112,8 +2121,13 @@ static int gp_interception(struct kvm_vcpu *vcpu) if (!is_guest_mode(vcpu)) return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP | EMULTYPE_NO_DECODE); - } else + } else { + /* All SVM instructions expect page aligned RAX */ + if (svm->vmcb->save.rax & ~PAGE_MASK) + goto reinject; + return emulate_svm_instr(vcpu, opcode); + } reinject: kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); @@ -2679,8 +2693,23 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) u64 data = msr->data; switch (ecx) { case MSR_AMD64_TSC_RATIO: - if (!msr->host_initiated && !svm->tsc_scaling_enabled) - return 1; + + if (!svm->tsc_scaling_enabled) { + + if (!msr->host_initiated) + return 1; + /* + * In case TSC scaling is not enabled, always + * leave this MSR at the default value. + * + * Due to bug in qemu 6.2.0, it would try to set + * this msr to 0 if tsc scaling is not enabled. + * Ignore this value as well. + */ + if (data != 0 && data != svm->tsc_ratio_msr) + return 1; + break; + } if (data & TSC_RATIO_RSVD) return 1; @@ -3285,6 +3314,55 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; } +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vector) +{ + /* + * vcpu->arch.apicv_active must be read after vcpu->mode. + * Pairs with smp_store_release in vcpu_enter_guest. + */ + bool in_guest_mode = (smp_load_acquire(&vcpu->mode) == IN_GUEST_MODE); + + if (!READ_ONCE(vcpu->arch.apicv_active)) { + /* Process the interrupt via inject_pending_event */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + return; + } + + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector); + if (in_guest_mode) { + /* + * Signal the doorbell to tell hardware to inject the IRQ. If + * the vCPU exits the guest before the doorbell chimes, hardware + * will automatically process AVIC interrupts at the next VMRUN. + */ + avic_ring_doorbell(vcpu); + } else { + /* + * Wake the vCPU if it was blocking. KVM will then detect the + * pending IRQ when checking if the vCPU has a wake event. + */ + kvm_vcpu_wake_up(vcpu); + } +} + +static void svm_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + kvm_lapic_set_irr(vector, apic); + + /* + * Pairs with the smp_mb_*() after setting vcpu->guest_mode in + * vcpu_enter_guest() to ensure the write to the vIRR is ordered before + * the read of guest_mode. This guarantees that either VMRUN will see + * and process the new vIRR entry, or that svm_complete_interrupt_delivery + * will signal the doorbell if the CPU has already entered the guest. + */ + smp_mb__after_atomic(); + svm_complete_interrupt_delivery(apic->vcpu, delivery_mode, trig_mode, vector); +} + static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3332,11 +3410,13 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_nmi_blocked(vcpu)) + return 0; + /* An NMI must not be injected into L2 if it's supposed to VM-Exit. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) return -EBUSY; - - return !svm_nmi_blocked(vcpu); + return 1; } static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) @@ -3388,9 +3468,13 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { struct vcpu_svm *svm = to_svm(vcpu); + if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_interrupt_blocked(vcpu)) + return 0; + /* * An IRQ must not be injected into L2 if it's supposed to VM-Exit, * e.g. if the IRQ arrived asynchronously after checking nested events. @@ -3398,7 +3482,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(svm)) return -EBUSY; - return !svm_interrupt_blocked(vcpu); + return 1; } static void svm_enable_irq_window(struct kvm_vcpu *vcpu) @@ -3609,7 +3693,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); unsigned long vmcb_pa = svm->current_vmcb->pa; - kvm_guest_enter_irqoff(); + guest_state_enter_irqoff(); if (sev_es_guest(vcpu->kvm)) { __svm_sev_es_vcpu_run(vmcb_pa); @@ -3629,7 +3713,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) vmload(__sme_page_pa(sd->save_area)); } - kvm_guest_exit_irqoff(); + guest_state_exit_irqoff(); } static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) @@ -4129,11 +4213,14 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_smi_blocked(vcpu)) + return 0; + /* An SMI must not be injected into L2 if it's supposed to VM-Exit. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_smi(svm)) return -EBUSY; - return !svm_smi_blocked(vcpu); + return 1; } static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) @@ -4227,11 +4314,18 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) * Enter the nested guest now */ + vmcb_mark_all_dirty(svm->vmcb01.ptr); + vmcb12 = map.hva; nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); + if (ret) + goto unmap_save; + + svm->nested.nested_run_pending = 1; + unmap_save: kvm_vcpu_unmap(vcpu, &map_save, true); unmap_map: @@ -4252,79 +4346,140 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) } } -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len) +static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { bool smep, smap, is_user; unsigned long cr4; + u64 error_code; + + /* Emulation is always possible when KVM has access to all guest state. */ + if (!sev_guest(vcpu->kvm)) + return true; + + /* #UD and #GP should never be intercepted for SEV guests. */ + WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD | + EMULTYPE_TRAP_UD_FORCED | + EMULTYPE_VMWARE_GP)); /* - * When the guest is an SEV-ES guest, emulation is not possible. + * Emulation is impossible for SEV-ES guests as KVM doesn't have access + * to guest register state. */ if (sev_es_guest(vcpu->kvm)) return false; /* + * Emulation is possible if the instruction is already decoded, e.g. + * when completing I/O after returning from userspace. + */ + if (emul_type & EMULTYPE_NO_DECODE) + return true; + + /* + * Emulation is possible for SEV guests if and only if a prefilled + * buffer containing the bytes of the intercepted instruction is + * available. SEV guest memory is encrypted with a guest specific key + * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and + * decode garbage. + * + * Inject #UD if KVM reached this point without an instruction buffer. + * In practice, this path should never be hit by a well-behaved guest, + * e.g. KVM doesn't intercept #UD or #GP for SEV guests, but this path + * is still theoretically reachable, e.g. via unaccelerated fault-like + * AVIC access, and needs to be handled by KVM to avoid putting the + * guest into an infinite loop. Injecting #UD is somewhat arbitrary, + * but its the least awful option given lack of insight into the guest. + */ + if (unlikely(!insn)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return false; + } + + /* + * Emulate for SEV guests if the insn buffer is not empty. The buffer + * will be empty if the DecodeAssist microcode cannot fetch bytes for + * the faulting instruction because the code fetch itself faulted, e.g. + * the guest attempted to fetch from emulated MMIO or a guest page + * table used to translate CS:RIP resides in emulated MMIO. + */ + if (likely(insn_len)) + return true; + + /* * Detect and workaround Errata 1096 Fam_17h_00_0Fh. * * Errata: - * When CPU raise #NPF on guest data access and vCPU CR4.SMAP=1, it is - * possible that CPU microcode implementing DecodeAssist will fail - * to read bytes of instruction which caused #NPF. In this case, - * GuestIntrBytes field of the VMCB on a VMEXIT will incorrectly - * return 0 instead of the correct guest instruction bytes. - * - * This happens because CPU microcode reading instruction bytes - * uses a special opcode which attempts to read data using CPL=0 - * privileges. The microcode reads CS:RIP and if it hits a SMAP - * fault, it gives up and returns no instruction bytes. + * When CPU raises #NPF on guest data access and vCPU CR4.SMAP=1, it is + * possible that CPU microcode implementing DecodeAssist will fail to + * read guest memory at CS:RIP and vmcb.GuestIntrBytes will incorrectly + * be '0'. This happens because microcode reads CS:RIP using a _data_ + * loap uop with CPL=0 privileges. If the load hits a SMAP #PF, ucode + * gives up and does not fill the instruction bytes buffer. * - * Detection: - * We reach here in case CPU supports DecodeAssist, raised #NPF and - * returned 0 in GuestIntrBytes field of the VMCB. - * First, errata can only be triggered in case vCPU CR4.SMAP=1. - * Second, if vCPU CR4.SMEP=1, errata could only be triggered - * in case vCPU CPL==3 (Because otherwise guest would have triggered - * a SMEP fault instead of #NPF). - * Otherwise, vCPU CR4.SMEP=0, errata could be triggered by any vCPU CPL. - * As most guests enable SMAP if they have also enabled SMEP, use above - * logic in order to attempt minimize false-positive of detecting errata - * while still preserving all cases semantic correctness. + * As above, KVM reaches this point iff the VM is an SEV guest, the CPU + * supports DecodeAssist, a #NPF was raised, KVM's page fault handler + * triggered emulation (e.g. for MMIO), and the CPU returned 0 in the + * GuestIntrBytes field of the VMCB. * - * Workaround: - * To determine what instruction the guest was executing, the hypervisor - * will have to decode the instruction at the instruction pointer. + * This does _not_ mean that the erratum has been encountered, as the + * DecodeAssist will also fail if the load for CS:RIP hits a legitimate + * #PF, e.g. if the guest attempt to execute from emulated MMIO and + * encountered a reserved/not-present #PF. * - * In non SEV guest, hypervisor will be able to read the guest - * memory to decode the instruction pointer when insn_len is zero - * so we return true to indicate that decoding is possible. + * To hit the erratum, the following conditions must be true: + * 1. CR4.SMAP=1 (obviously). + * 2. CR4.SMEP=0 || CPL=3. If SMEP=1 and CPL<3, the erratum cannot + * have been hit as the guest would have encountered a SMEP + * violation #PF, not a #NPF. + * 3. The #NPF is not due to a code fetch, in which case failure to + * retrieve the instruction bytes is legitimate (see abvoe). * - * But in the SEV guest, the guest memory is encrypted with the - * guest specific key and hypervisor will not be able to decode the - * instruction pointer so we will not able to workaround it. Lets - * print the error and request to kill the guest. - */ - if (likely(!insn || insn_len)) - return true; - - /* - * If RIP is invalid, go ahead with emulation which will cause an - * internal error exit. + * In addition, don't apply the erratum workaround if the #NPF occurred + * while translating guest page tables (see below). */ - if (!kvm_vcpu_gfn_to_memslot(vcpu, kvm_rip_read(vcpu) >> PAGE_SHIFT)) - return true; + error_code = to_svm(vcpu)->vmcb->control.exit_info_1; + if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK)) + goto resume_guest; cr4 = kvm_read_cr4(vcpu); smep = cr4 & X86_CR4_SMEP; smap = cr4 & X86_CR4_SMAP; is_user = svm_get_cpl(vcpu) == 3; if (smap && (!smep || is_user)) { - if (!sev_guest(vcpu->kvm)) - return true; - pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n"); - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + + /* + * If the fault occurred in userspace, arbitrarily inject #GP + * to avoid killing the guest and to hopefully avoid confusing + * the guest kernel too much, e.g. injecting #PF would not be + * coherent with respect to the guest's page tables. Request + * triple fault if the fault occurred in the kernel as there's + * no fault that KVM can inject without confusing the guest. + * In practice, the triple fault is moot as no sane SEV kernel + * will execute from user memory while also running with SMAP=1. + */ + if (is_user) + kvm_inject_gp(vcpu, 0); + else + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); } +resume_guest: + /* + * If the erratum was not hit, simply resume the guest and let it fault + * again. While awful, e.g. the vCPU may get stuck in an infinite loop + * if the fault is at CPL=0, it's the lesser of all evils. Exiting to + * userspace will kill the guest, and letting the emulator read garbage + * will yield random behavior and potentially corrupt the guest. + * + * Simply resuming the guest is technically not a violation of the SEV + * architecture. AMD's APM states that all code fetches and page table + * accesses for SEV guest are encrypted, regardless of the C-Bit. The + * APM also states that encrypted accesses to MMIO are "ignored", but + * doesn't explicitly define "ignored", i.e. doing nothing and letting + * the guest spin is technically "ignoring" the access. + */ return false; } @@ -4478,7 +4633,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .pmu_ops = &amd_pmu_ops, .nested_ops = &svm_nested_ops, - .deliver_posted_interrupt = svm_deliver_avic_intr, + .deliver_interrupt = svm_deliver_interrupt, .dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt, .update_pi_irte = svm_update_pi_irte, .setup_mce = svm_setup_mce, @@ -4555,6 +4710,7 @@ static __init void svm_set_cpu_caps(void) /* CPUID 0x80000001 and 0x8000000A (SVM features) */ if (nested) { kvm_cpu_cap_set(X86_FEATURE_SVM); + kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN); if (nrips) kvm_cpu_cap_set(X86_FEATURE_NRIPS); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 47ef8f4a9358..fa98d6844728 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -304,11 +304,6 @@ static inline void vmcb_mark_all_clean(struct vmcb *vmcb) & ~VMCB_ALWAYS_DIRTY_MASK; } -static inline bool vmcb_is_clean(struct vmcb *vmcb, int bit) -{ - return (vmcb->control.clean & (1 << bit)); -} - static inline void vmcb_mark_dirty(struct vmcb *vmcb, int bit) { vmcb->control.clean &= ~(1 << bit); @@ -494,6 +489,8 @@ void svm_set_gif(struct vcpu_svm *svm, bool value); int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code); void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, int read, int write); +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vec); /* nested.c */ @@ -525,7 +522,7 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun); -void svm_leave_nested(struct vcpu_svm *svm); +void svm_leave_nested(struct kvm_vcpu *vcpu); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); int nested_svm_vmrun(struct kvm_vcpu *vcpu); @@ -561,17 +558,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ -#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) -#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 -#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) - -#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) -#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) -#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) -#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) - -#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL - int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); @@ -588,12 +574,12 @@ bool svm_check_apicv_inhibit_reasons(ulong bit); void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); -int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec); bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu); int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void avic_vcpu_blocking(struct kvm_vcpu *vcpu); void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); +void avic_ring_doorbell(struct kvm_vcpu *vcpu); /* sev.c */ diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index c53b8bf8d013..489ca56212c6 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -46,6 +46,9 @@ static inline void svm_hv_init_vmcb(struct vmcb *vmcb) if (npt_enabled && ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) hve->hv_enlightenments_control.enlightened_npt_tlb = 1; + + if (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP) + hve->hv_enlightenments_control.msr_bitmap = 1; } static inline void svm_hv_hardware_setup(void) @@ -83,14 +86,7 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments( struct hv_enlightenments *hve = (struct hv_enlightenments *)vmcb->control.reserved_sw; - /* - * vmcb can be NULL if called during early vcpu init. - * And its okay not to mark vmcb dirty during vcpu init - * as we mark it dirty unconditionally towards end of vcpu - * init phase. - */ - if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && - hve->hv_enlightenments_control.msr_bitmap) + if (hve->hv_enlightenments_control.msr_bitmap) vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); } diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 959b59d13b5a..3f430e218375 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -54,7 +54,6 @@ struct nested_vmx_msrs { struct vmcs_config { int size; - int order; u32 basic_cap; u32 revision_id; u32 pin_based_exec_ctrl; diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index ba6f99f584ac..87e3dc10edf4 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -12,8 +12,6 @@ DEFINE_STATIC_KEY_FALSE(enable_evmcs); -#if IS_ENABLED(CONFIG_HYPERV) - #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ {EVMCS1_OFFSET(name), clean_field} @@ -296,6 +294,7 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { }; const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); +#if IS_ENABLED(CONFIG_HYPERV) __init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) { vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL; @@ -362,6 +361,7 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) case MSR_IA32_VMX_PROCBASED_CTLS2: ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; break; + case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_PINBASED_CTLS: ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; break; diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index 16731d2cf231..8d70f9aea94b 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -59,12 +59,12 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); SECONDARY_EXEC_SHADOW_VMCS | \ SECONDARY_EXEC_TSC_SCALING | \ SECONDARY_EXEC_PAUSE_LOOP_EXITING) -#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) +#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) #define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) #define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING) -#if IS_ENABLED(CONFIG_HYPERV) - struct evmcs_field { u16 offset; u16 clean_field; @@ -73,26 +73,56 @@ struct evmcs_field { extern const struct evmcs_field vmcs_field_to_evmcs_1[]; extern const unsigned int nr_evmcs_1_fields; -static __always_inline int get_evmcs_offset(unsigned long field, - u16 *clean_field) +static __always_inline int evmcs_field_offset(unsigned long field, + u16 *clean_field) { unsigned int index = ROL16(field, 6); const struct evmcs_field *evmcs_field; - if (unlikely(index >= nr_evmcs_1_fields)) { - WARN_ONCE(1, "KVM: accessing unsupported EVMCS field %lx\n", - field); + if (unlikely(index >= nr_evmcs_1_fields)) return -ENOENT; - } evmcs_field = &vmcs_field_to_evmcs_1[index]; + /* + * Use offset=0 to detect holes in eVMCS. This offset belongs to + * 'revision_id' but this field has no encoding and is supposed to + * be accessed directly. + */ + if (unlikely(!evmcs_field->offset)) + return -ENOENT; + if (clean_field) *clean_field = evmcs_field->clean_field; return evmcs_field->offset; } +static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, + unsigned long field, u16 offset) +{ + /* + * vmcs12_read_any() doesn't care whether the supplied structure + * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes + * the exact offset of the required field, use it for convenience + * here. + */ + return vmcs12_read_any((void *)evmcs, field, offset); +} + +#if IS_ENABLED(CONFIG_HYPERV) + +static __always_inline int get_evmcs_offset(unsigned long field, + u16 *clean_field) +{ + int offset = evmcs_field_offset(field, clean_field); + + WARN_ONCE(offset < 0, "KVM: accessing unsupported EVMCS field %lx\n", + field); + + return offset; +} + static __always_inline void evmcs_write64(unsigned long field, u64 value) { u16 clean_field; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f235f77cbc03..dc822a1d403d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -7,6 +7,7 @@ #include <asm/mmu_context.h> #include "cpuid.h" +#include "evmcs.h" #include "hyperv.h" #include "mmu.h" #include "nested.h" @@ -245,8 +246,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, src = &prev->host_state; dest = &vmx->loaded_vmcs->host_state; - vmx_set_vmcs_host_state(dest, src->cr3, src->fs_sel, src->gs_sel, - src->fs_base, src->gs_base); + vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base); dest->ldt_sel = src->ldt_sel; #ifdef CONFIG_X86_64 dest->ds_sel = src->ds_sel; @@ -3055,7 +3055,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr4; + unsigned long cr3, cr4; bool vm_fail; if (!nested_early_check) @@ -3078,6 +3078,12 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) */ vmcs_writel(GUEST_RFLAGS, 0); + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { + vmcs_writel(HOST_CR3, cr3); + vmx->loaded_vmcs->host_state.cr3 = cr3; + } + cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); @@ -4851,18 +4857,20 @@ static struct vmcs *alloc_shadow_vmcs(struct kvm_vcpu *vcpu) struct loaded_vmcs *loaded_vmcs = vmx->loaded_vmcs; /* - * We should allocate a shadow vmcs for vmcs01 only when L1 - * executes VMXON and free it when L1 executes VMXOFF. - * As it is invalid to execute VMXON twice, we shouldn't reach - * here when vmcs01 already have an allocated shadow vmcs. + * KVM allocates a shadow VMCS only when L1 executes VMXON and frees it + * when L1 executes VMXOFF or the vCPU is forced out of nested + * operation. VMXON faults if the CPU is already post-VMXON, so it + * should be impossible to already have an allocated shadow VMCS. KVM + * doesn't support virtualization of VMCS shadowing, so vmcs01 should + * always be the loaded VMCS. */ - WARN_ON(loaded_vmcs == &vmx->vmcs01 && loaded_vmcs->shadow_vmcs); + if (WARN_ON(loaded_vmcs != &vmx->vmcs01 || loaded_vmcs->shadow_vmcs)) + return loaded_vmcs->shadow_vmcs; + + loaded_vmcs->shadow_vmcs = alloc_vmcs(true); + if (loaded_vmcs->shadow_vmcs) + vmcs_clear(loaded_vmcs->shadow_vmcs); - if (!loaded_vmcs->shadow_vmcs) { - loaded_vmcs->shadow_vmcs = alloc_vmcs(true); - if (loaded_vmcs->shadow_vmcs) - vmcs_clear(loaded_vmcs->shadow_vmcs); - } return loaded_vmcs->shadow_vmcs; } @@ -5099,27 +5107,49 @@ static int handle_vmread(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - /* - * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, - * any VMREAD sets the ALU flags for VMfailInvalid. - */ - if (vmx->nested.current_vmptr == INVALID_GPA || - (is_guest_mode(vcpu) && - get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA)) - return nested_vmx_failInvalid(vcpu); - /* Decode instruction info and find the field to read */ field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); - offset = vmcs_field_to_offset(field); - if (offset < 0) - return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); + if (!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + /* + * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, + * any VMREAD sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == INVALID_GPA || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA)) + return nested_vmx_failInvalid(vcpu); - if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) - copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); + offset = get_vmcs12_field_offset(field); + if (offset < 0) + return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); + + if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) + copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - /* Read the field, zero-extended to a u64 value */ - value = vmcs12_read_any(vmcs12, field, offset); + /* Read the field, zero-extended to a u64 value */ + value = vmcs12_read_any(vmcs12, field, offset); + } else { + /* + * Hyper-V TLFS (as of 6.0b) explicitly states, that while an + * enlightened VMCS is active VMREAD/VMWRITE instructions are + * unsupported. Unfortunately, certain versions of Windows 11 + * don't comply with this requirement which is not enforced in + * genuine Hyper-V. Allow VMREAD from an enlightened VMCS as a + * workaround, as misbehaving guests will panic on VM-Fail. + * Note, enlightened VMCS is incompatible with shadow VMCS so + * all VMREADs from L2 should go to L1. + */ + if (WARN_ON_ONCE(is_guest_mode(vcpu))) + return nested_vmx_failInvalid(vcpu); + + offset = evmcs_field_offset(field, NULL); + if (offset < 0) + return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); + + /* Read the field, zero-extended to a u64 value */ + value = evmcs_read_any(vmx->nested.hv_evmcs, field, offset); + } /* * Now copy part of this value to register or memory, as requested. @@ -5214,7 +5244,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); - offset = vmcs_field_to_offset(field); + offset = get_vmcs12_field_offset(field); if (offset < 0) return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); @@ -6462,7 +6492,7 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void) max_idx = 0; for (i = 0; i < nr_vmcs12_fields; i++) { /* The vmcs12 table is very, very sparsely populated. */ - if (!vmcs_field_to_offset_table[i]) + if (!vmcs12_field_offsets[i]) continue; idx = vmcs_field_index(VMCS12_IDX_TO_ENC(i)); @@ -6771,6 +6801,7 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) } struct kvm_x86_nested_ops vmx_nested_ops = { + .leave_nested = vmx_leave_nested, .check_events = vmx_check_nested_events, .hv_timer_pending = nested_vmx_preemption_timer_pending, .triple_fault = nested_vmx_triple_fault, diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index cab6ba7a5005..2251b60920f8 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -8,7 +8,7 @@ FIELD(number, name), \ [ROL16(number##_HIGH, 6)] = VMCS12_OFFSET(name) + sizeof(u32) -const unsigned short vmcs_field_to_offset_table[] = { +const unsigned short vmcs12_field_offsets[] = { FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id), FIELD(POSTED_INTR_NV, posted_intr_nv), FIELD(GUEST_ES_SELECTOR, guest_es_selector), @@ -151,4 +151,4 @@ const unsigned short vmcs_field_to_offset_table[] = { FIELD(HOST_RSP, host_rsp), FIELD(HOST_RIP, host_rip), }; -const unsigned int nr_vmcs12_fields = ARRAY_SIZE(vmcs_field_to_offset_table); +const unsigned int nr_vmcs12_fields = ARRAY_SIZE(vmcs12_field_offsets); diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 2a45f026ee11..746129ddd5ae 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -361,10 +361,10 @@ static inline void vmx_check_vmcs12_offsets(void) CHECK_OFFSET(guest_pml_index, 996); } -extern const unsigned short vmcs_field_to_offset_table[]; +extern const unsigned short vmcs12_field_offsets[]; extern const unsigned int nr_vmcs12_fields; -static inline short vmcs_field_to_offset(unsigned long field) +static inline short get_vmcs12_field_offset(unsigned long field) { unsigned short offset; unsigned int index; @@ -377,7 +377,7 @@ static inline short vmcs_field_to_offset(unsigned long field) return -ENOENT; index = array_index_nospec(index, nr_vmcs12_fields); - offset = vmcs_field_to_offset_table[index]; + offset = vmcs12_field_offsets[index]; if (offset == 0) return -ENOENT; return offset; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4ac676066d60..b730d799c26e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1080,14 +1080,9 @@ static void pt_guest_exit(struct vcpu_vmx *vmx) wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } -void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3, - u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base) +void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base) { - if (unlikely(cr3 != host->cr3)) { - vmcs_writel(HOST_CR3, cr3); - host->cr3 = cr3; - } if (unlikely(fs_sel != host->fs_sel)) { if (!(fs_sel & 7)) vmcs_write16(HOST_FS_SELECTOR, fs_sel); @@ -1182,9 +1177,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) gs_base = segment_base(gs_sel); #endif - vmx_set_vmcs_host_state(host_state, __get_current_cr3_fast(), - fs_sel, gs_sel, fs_base, gs_base); - + vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); vmx->guest_state_loaded = true; } @@ -1487,11 +1480,12 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len) +static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does - * not point tthe failing instruction, and even if it did, the code + * not point at the failing instruction, and even if it did, the code * stream is inaccessible. Inject #UD instead of exiting to userspace * so that guest userspace can't DoS the guest simply by triggering * emulation (enclaves are CPL3 only). @@ -2603,7 +2597,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, return -EIO; vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->order = get_order(vmcs_conf->size); vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; vmcs_conf->revision_id = vmx_msr_low; @@ -2628,7 +2621,7 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) struct page *pages; struct vmcs *vmcs; - pages = __alloc_pages_node(node, flags, vmcs_config.order); + pages = __alloc_pages_node(node, flags, 0); if (!pages) return NULL; vmcs = page_address(pages); @@ -2647,7 +2640,7 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) void free_vmcs(struct vmcs *vmcs) { - free_pages((unsigned long)vmcs, vmcs_config.order); + free_page((unsigned long)vmcs); } /* @@ -4041,6 +4034,21 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) return 0; } +static void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + struct kvm_vcpu *vcpu = apic->vcpu; + + if (vmx_deliver_posted_interrupt(vcpu, vector)) { + kvm_lapic_set_irr(vector, apic); + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + } else { + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector); + } +} + /* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest. @@ -4094,10 +4102,14 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) vmcs_write32(HOST_IA32_SYSENTER_CS, low32); /* - * If 32-bit syscall is enabled, vmx_vcpu_load_vcms rewrites - * HOST_IA32_SYSENTER_ESP. + * SYSENTER is used for 32-bit system calls on either 32-bit or + * 64-bit kernels. It is always zero If neither is allowed, otherwise + * vmx_vcpu_load_vmcs loads it with the per-CPU entry stack (and may + * have already done so!). */ - vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); + if (!IS_ENABLED(CONFIG_IA32_EMULATION) && !IS_ENABLED(CONFIG_X86_32)) + vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); + rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ @@ -4901,8 +4913,33 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) dr6 = vmx_get_exit_qual(vcpu); if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { + /* + * If the #DB was due to ICEBP, a.k.a. INT1, skip the + * instruction. ICEBP generates a trap-like #DB, but + * despite its interception control being tied to #DB, + * is an instruction intercept, i.e. the VM-Exit occurs + * on the ICEBP itself. Note, skipping ICEBP also + * clears STI and MOVSS blocking. + * + * For all other #DBs, set vmcs.PENDING_DBG_EXCEPTIONS.BS + * if single-step is enabled in RFLAGS and STI or MOVSS + * blocking is active, as the CPU doesn't set the bit + * on VM-Exit due to #DB interception. VM-Entry has a + * consistency check that a single-step #DB is pending + * in this scenario as the previous instruction cannot + * have toggled RFLAGS.TF 0=>1 (because STI and POP/MOV + * don't modify RFLAGS), therefore the one instruction + * delay when activating single-step breakpoints must + * have already expired. Note, the CPU sets/clears BS + * as appropriate for all other VM-Exits types. + */ if (is_icebp(intr_info)) WARN_ON(!skip_emulated_instruction(vcpu)); + else if ((vmx_get_rflags(vcpu) & X86_EFLAGS_TF) && + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS))) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, + vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS) | DR6_BS); kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); return 1; @@ -5397,7 +5434,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; - if (!vmx_can_emulate_instruction(vcpu, NULL, 0)) + if (!vmx_can_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) return 1; /* @@ -6725,7 +6762,7 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - kvm_guest_enter_irqoff(); + guest_state_enter_irqoff(); /* L1D Flush includes CPU buffer clear to mitigate MDS */ if (static_branch_unlikely(&vmx_l1d_should_flush)) @@ -6741,13 +6778,13 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vcpu->arch.cr2 = native_read_cr2(); - kvm_guest_exit_irqoff(); + guest_state_exit_irqoff(); } static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr4; + unsigned long cr3, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -6790,6 +6827,19 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); vcpu->arch.regs_dirty = 0; + /* + * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately + * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time + * it switches back to the current->mm, which can occur in KVM context + * when switching to a temporary mm to patch kernel code, e.g. if KVM + * toggles a static key while handling a VM-Exit. + */ + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { + vmcs_writel(HOST_CR3, cr3); + vmx->loaded_vmcs->host_state.cr3 = cr3; + } + cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); @@ -7615,6 +7665,7 @@ static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) if (ret) return ret; + vmx->nested.nested_run_pending = 1; vmx->nested.smm.guest_mode = false; } return 0; @@ -7739,7 +7790,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .hwapic_isr_update = vmx_hwapic_isr_update, .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_posted_interrupt = vmx_deliver_posted_interrupt, + .deliver_interrupt = vmx_deliver_interrupt, .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, .set_tss_addr = vmx_set_tss_addr, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7f2c82e7f38f..9c6bfcd84008 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -374,9 +374,8 @@ int allocate_vpid(void); void free_vpid(int vpid); void vmx_set_constant_host_state(struct vcpu_vmx *vmx); void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); -void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3, - u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base); +void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); bool vmx_emulation_required(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9e43d756312f..eb4029660bd9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -90,6 +90,8 @@ u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P; EXPORT_SYMBOL_GPL(kvm_mce_cap_supported); +#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) + #define emul_to_vcpu(ctxt) \ ((struct kvm_vcpu *)(ctxt)->vcpu) @@ -982,6 +984,18 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); +static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.guest_fpu.fpstate->user_xfeatures; +} + +#ifdef CONFIG_X86_64 +static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) +{ + return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC; +} +#endif + static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0 = xcr; @@ -1001,7 +1015,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ - valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; + valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; @@ -2349,10 +2363,12 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) return tsc; } +#ifdef CONFIG_X86_64 static inline int gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } +#endif static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { @@ -3535,6 +3551,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~supported_xss) return 1; vcpu->arch.ia32_xss = data; + kvm_update_cpuid_runtime(vcpu); break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) @@ -3703,8 +3720,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; - if (data & ~(XFEATURE_MASK_USER_DYNAMIC & - vcpu->arch.guest_supported_xcr0)) + if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data); @@ -3714,8 +3730,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; - if (data & ~(XFEATURE_MASK_USER_DYNAMIC & - vcpu->arch.guest_supported_xcr0)) + if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; vcpu->arch.guest_fpu.xfd_err = data; @@ -4229,6 +4244,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: + case KVM_CAP_SYS_ATTRIBUTES: + case KVM_CAP_ENABLE_CAP: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -4331,7 +4348,49 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; } return r; +} + +static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr) +{ + void __user *uaddr = (void __user*)(unsigned long)attr->addr; + if ((u64)(unsigned long)uaddr != attr->addr) + return ERR_PTR_USR(-EFAULT); + return uaddr; +} + +static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) +{ + u64 __user *uaddr = kvm_get_attr_addr(attr); + + if (attr->group) + return -ENXIO; + + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + if (put_user(supported_xcr0, uaddr)) + return -EFAULT; + return 0; + default: + return -ENXIO; + break; + } +} + +static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr) +{ + if (attr->group) + return -ENXIO; + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + return 0; + default: + return -ENXIO; + } } long kvm_arch_dev_ioctl(struct file *filp, @@ -4422,6 +4481,22 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; + case KVM_GET_DEVICE_ATTR: { + struct kvm_device_attr attr; + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_x86_dev_get_attr(&attr); + break; + } + case KVM_HAS_DEVICE_ATTR: { + struct kvm_device_attr attr; + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_x86_dev_has_attr(&attr); + break; + } default: r = -EINVAL; break; @@ -4860,8 +4935,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { - if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) + if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { + kvm_x86_ops.nested_ops->leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); + } vcpu->arch.smi_pending = events->smi.pending; @@ -5022,11 +5099,11 @@ static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr; + u64 __user *uaddr = kvm_get_attr_addr(attr); int r; - if ((u64)(unsigned long)uaddr != attr->addr) - return -EFAULT; + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: @@ -5045,12 +5122,12 @@ static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr; + u64 __user *uaddr = kvm_get_attr_addr(attr); struct kvm *kvm = vcpu->kvm; int r; - if ((u64)(unsigned long)uaddr != attr->addr) - return -EFAULT; + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: { @@ -6810,6 +6887,13 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); +static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) +{ + return static_call(kvm_x86_can_emulate_instruction)(vcpu, emul_type, + insn, insn_len); +} + int handle_ud(struct kvm_vcpu *vcpu) { static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; @@ -6817,7 +6901,7 @@ int handle_ud(struct kvm_vcpu *vcpu) char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; - if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, NULL, 0))) + if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) return 1; if (force_emulation_prefix && @@ -8193,7 +8277,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool writeback = true; bool write_fault_to_spt; - if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, insn, insn_len))) + if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) return 1; vcpu->arch.l1tf_flush_l1d = true; @@ -8871,6 +8955,13 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; + /* + * When tsc is in permanent catchup mode guests won't be able to use + * pvclock_read_retry loop to get consistent view of pvclock + */ + if (vcpu->arch.tsc_always_catchup) + return -KVM_EOPNOTSUPP; + if (!kvm_get_walltime_and_clockread(&ts, &cycle)) return -KVM_EOPNOTSUPP; @@ -9089,6 +9180,7 @@ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) likely(!pic_in_kernel(vcpu->kvm)); } +/* Called within kvm->srcu read side. */ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; @@ -9097,16 +9189,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); - /* - * The call to kvm_ready_for_interrupt_injection() may end up in - * kvm_xen_has_interrupt() which may require the srcu lock to be - * held, to protect against changes in the vcpu_info address. - */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; @@ -9706,7 +9791,7 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); } -void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) +static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) return; @@ -9724,6 +9809,7 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); /* + * Called within kvm->srcu read side. * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. @@ -9912,7 +9998,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * result in virtual interrupt delivery. */ local_irq_disable(); - vcpu->mode = IN_GUEST_MODE; + + /* Store vcpu->apicv_active before vcpu->mode. */ + smp_store_release(&vcpu->mode, IN_GUEST_MODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -9972,6 +10060,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(0, 7); } + guest_timing_enter_irqoff(); + for (;;) { /* * Assert that vCPU vs. VM APICv state is consistent. An APICv @@ -10056,7 +10146,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * of accounting via context tracking, but the loss of accuracy is * acceptable for all known use cases. */ - vtime_account_guest_exit(); + guest_timing_exit_irqoff(); if (lapic_in_kernel(vcpu)) { s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta; @@ -10098,6 +10188,7 @@ out: return r; } +/* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { bool hv_timer; @@ -10157,12 +10248,12 @@ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) !vcpu->arch.apf.halted); } +/* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; struct kvm *kvm = vcpu->kvm; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); vcpu->arch.l1tf_flush_l1d = true; for (;;) { @@ -10190,14 +10281,12 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (__xfer_to_guest_mode_work_pending()) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); r = xfer_to_guest_mode_handle_work(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (r) return r; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); } } - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - return r; } @@ -10303,6 +10392,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; + struct kvm *kvm = vcpu->kvm; int r; vcpu_load(vcpu); @@ -10310,6 +10400,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; @@ -10320,7 +10411,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * use before KVM has ever run the vCPU. */ WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); + + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (kvm_apic_accept_events(vcpu) < 0) { r = 0; goto out; @@ -10380,8 +10475,9 @@ out: if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); - kvm_sigset_deactivate(vcpu); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); return r; } @@ -11209,7 +11305,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.msr_misc_features_enables = 0; - vcpu->arch.xcr0 = XFEATURE_MASK_FP; + __kvm_set_xcr(vcpu, 0, XFEATURE_MASK_FP); + __kvm_set_msr(vcpu, MSR_IA32_XSS, 0, true); } /* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */ @@ -11226,8 +11323,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1, 0); kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600); - vcpu->arch.ia32_xss = 0; - static_call(kvm_x86_vcpu_reset)(vcpu, init_event); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); @@ -11571,8 +11666,6 @@ void kvm_arch_sync_events(struct kvm *kvm) kvm_free_pit(kvm); } -#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) - /** * __x86_set_memory_region: Setup KVM internal memory slot * diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 635b75f9e145..767ec7f99516 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -10,51 +10,6 @@ void kvm_spurious_fault(void); -static __always_inline void kvm_guest_enter_irqoff(void) -{ - /* - * VMENTER enables interrupts (host state), but the kernel state is - * interrupts disabled when this is invoked. Also tell RCU about - * it. This is the same logic as for exit_to_user_mode(). - * - * This ensures that e.g. latency analysis on the host observes - * guest mode as interrupt enabled. - * - * guest_enter_irqoff() informs context tracking about the - * transition to guest mode and if enabled adjusts RCU state - * accordingly. - */ - instrumentation_begin(); - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); - instrumentation_end(); - - guest_enter_irqoff(); - lockdep_hardirqs_on(CALLER_ADDR0); -} - -static __always_inline void kvm_guest_exit_irqoff(void) -{ - /* - * VMEXIT disables interrupts (host state), but tracing and lockdep - * have them in state 'on' as recorded before entering guest mode. - * Same as enter_from_user_mode(). - * - * context_tracking_guest_exit() restores host context and reinstates - * RCU if enabled and required. - * - * This needs to be done immediately after VM-Exit, before any code - * that might contain tracepoints or call out to the greater world, - * e.g. before x86_spec_ctrl_restore_host(). - */ - lockdep_hardirqs_off(CALLER_ADDR0); - context_tracking_guest_exit(); - - instrumentation_begin(); - trace_hardirqs_off_finish(); - instrumentation_end(); -} - #define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check) \ ({ \ bool failed = (consistency_check); \ diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 0e3f7d6e9fd7..74be1fda58e3 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -133,32 +133,57 @@ static void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) { struct kvm_vcpu_xen *vx = &v->arch.xen; + struct gfn_to_hva_cache *ghc = &vx->runstate_cache; + struct kvm_memslots *slots = kvm_memslots(v->kvm); + bool atomic = (state == RUNSTATE_runnable); uint64_t state_entry_time; - unsigned int offset; + int __user *user_state; + uint64_t __user *user_times; kvm_xen_update_runstate(v, state); if (!vx->runstate_set) return; - BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + if (unlikely(slots->generation != ghc->generation || kvm_is_error_hva(ghc->hva)) && + kvm_gfn_to_hva_cache_init(v->kvm, ghc, ghc->gpa, ghc->len)) + return; + + /* We made sure it fits in a single page */ + BUG_ON(!ghc->memslot); + + if (atomic) + pagefault_disable(); - offset = offsetof(struct compat_vcpu_runstate_info, state_entry_time); -#ifdef CONFIG_X86_64 /* - * The only difference is alignment of uint64_t in 32-bit. - * So the first field 'state' is accessed directly using - * offsetof() (where its offset happens to be zero), while the - * remaining fields which are all uint64_t, start at 'offset' - * which we tweak here by adding 4. + * The only difference between 32-bit and 64-bit versions of the + * runstate struct us the alignment of uint64_t in 32-bit, which + * means that the 64-bit version has an additional 4 bytes of + * padding after the first field 'state'. + * + * So we use 'int __user *user_state' to point to the state field, + * and 'uint64_t __user *user_times' for runstate_entry_time. So + * the actual array of time[] in each state starts at user_times[1]. */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != 0); + BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state) != 0); + user_state = (int __user *)ghc->hva; + + BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + + user_times = (uint64_t __user *)(ghc->hva + + offsetof(struct compat_vcpu_runstate_info, + state_entry_time)); +#ifdef CONFIG_X86_64 BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4); BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) != offsetof(struct compat_vcpu_runstate_info, time) + 4); if (v->kvm->arch.xen.long_mode) - offset = offsetof(struct vcpu_runstate_info, state_entry_time); + user_times = (uint64_t __user *)(ghc->hva + + offsetof(struct vcpu_runstate_info, + state_entry_time)); #endif /* * First write the updated state_entry_time at the appropriate @@ -172,10 +197,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) != sizeof(state_entry_time)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &state_entry_time, offset, - sizeof(state_entry_time))) - return; + if (__put_user(state_entry_time, user_times)) + goto out; smp_wmb(); /* @@ -189,11 +212,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) != sizeof(vx->current_runstate)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &vx->current_runstate, - offsetof(struct vcpu_runstate_info, state), - sizeof(vx->current_runstate))) - return; + if (__put_user(vx->current_runstate, user_state)) + goto out; /* * Write the actual runstate times immediately after the @@ -208,24 +228,23 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != sizeof(vx->runstate_times)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &vx->runstate_times[0], - offset + sizeof(u64), - sizeof(vx->runstate_times))) - return; - + if (__copy_to_user(user_times + 1, vx->runstate_times, sizeof(vx->runstate_times))) + goto out; smp_wmb(); /* * Finally, clear the XEN_RUNSTATE_UPDATE bit in the guest's * runstate_entry_time field. */ - state_entry_time &= ~XEN_RUNSTATE_UPDATE; - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &state_entry_time, offset, - sizeof(state_entry_time))) - return; + __put_user(state_entry_time, user_times); + smp_wmb(); + + out: + mark_page_dirty_in_slot(v->kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + + if (atomic) + pagefault_enable(); } int __kvm_xen_has_interrupt(struct kvm_vcpu *v) @@ -316,10 +335,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) "\tnotq %0\n" "\t" LOCK_PREFIX "andq %0, %2\n" "2:\n" - "\t.section .fixup,\"ax\"\n" - "3:\tjmp\t2b\n" - "\t.previous\n" - _ASM_EXTABLE_UA(1b, 3b) + _ASM_EXTABLE_UA(1b, 2b) : "=r" (evtchn_pending_sel), "+m" (vi->evtchn_pending_sel), "+m" (v->arch.xen.evtchn_pending_sel) @@ -335,10 +351,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) "\tnotl %0\n" "\t" LOCK_PREFIX "andl %0, %2\n" "2:\n" - "\t.section .fixup,\"ax\"\n" - "3:\tjmp\t2b\n" - "\t.previous\n" - _ASM_EXTABLE_UA(1b, 3b) + _ASM_EXTABLE_UA(1b, 2b) : "=r" (evtchn_pending_sel32), "+m" (vi->evtchn_pending_sel), "+m" (v->arch.xen.evtchn_pending_sel) @@ -449,6 +462,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache, data->u.gpa, @@ -466,6 +485,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct pvclock_vcpu_time_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache, data->u.gpa, @@ -487,6 +512,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_runstate_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.runstate_cache, data->u.gpa, diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 89b3fb244e15..afbdda539b80 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -34,7 +34,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE .endm diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 2b1e266ff95c..0ecb140864b2 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -394,7 +394,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) u8 *prog = *pprog; #ifdef CONFIG_RETPOLINE - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) { + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 2edd86649468..615a76d70019 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -353,8 +353,8 @@ static void pci_fixup_video(struct pci_dev *pdev) } } } -DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, - PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); static const struct dmi_system_id msi_k8t_dmi_table[] = { diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 42300941ec29..517a9d8d8f94 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -9,6 +9,7 @@ #include <xen/events.h> #include <xen/interface/memory.h> +#include <asm/apic.h> #include <asm/cpu.h> #include <asm/smp.h> #include <asm/io_apic.h> @@ -184,8 +185,7 @@ static int xen_cpu_dead_hvm(unsigned int cpu) if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock)) xen_teardown_timer(cpu); - - return 0; + return 0; } static bool no_vector_callback __initdata; @@ -242,15 +242,14 @@ static __init int xen_parse_no_vector_callback(char *arg) } early_param("xen_no_vector_callback", xen_parse_no_vector_callback); -bool __init xen_hvm_need_lapic(void) +static __init bool xen_x2apic_available(void) { - if (xen_pv_domain()) - return false; - if (!xen_hvm_domain()) - return false; - if (xen_feature(XENFEAT_hvm_pirqs) && xen_have_vector_callback) - return false; - return true; + return x2apic_supported(); +} + +static bool __init msi_ext_dest_id(void) +{ + return cpuid_eax(xen_cpuid_base() + 4) & XEN_HVM_CPUID_EXT_DEST_ID; } static __init void xen_hvm_guest_late_init(void) @@ -312,9 +311,10 @@ struct hypervisor_x86 x86_hyper_xen_hvm __initdata = { .detect = xen_platform_hvm, .type = X86_HYPER_XEN_HVM, .init.init_platform = xen_hvm_guest_init, - .init.x2apic_available = xen_x2apic_para_available, + .init.x2apic_available = xen_x2apic_available, .init.init_mem_mapping = xen_hvm_init_mem_mapping, .init.guest_late_init = xen_hvm_guest_late_init, + .init.msi_ext_dest_id = msi_ext_dest_id, .runtime.pin_vcpu = xen_pin_vcpu, .ignore_nopv = true, }; diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 5004feb16783..d47c3d176ae4 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1341,10 +1341,6 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_acpi_sleep_register(); - /* Avoid searching for BIOS MP tables */ - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.get_smp_config = x86_init_uint_noop; - xen_boot_params_init_edd(); #ifdef CONFIG_ACPI diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 6a8f3b53ab83..4a6019238ee7 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -148,28 +148,12 @@ int xen_smp_intr_init_pv(unsigned int cpu) return rc; } -static void __init xen_fill_possible_map(void) -{ - int i, rc; - - if (xen_initial_domain()) - return; - - for (i = 0; i < nr_cpu_ids; i++) { - rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL); - if (rc >= 0) { - num_processors++; - set_cpu_possible(i, true); - } - } -} - -static void __init xen_filter_cpu_maps(void) +static void __init _get_smp_config(unsigned int early) { int i, rc; unsigned int subtract = 0; - if (!xen_initial_domain()) + if (early) return; num_processors = 0; @@ -210,7 +194,6 @@ static void __init xen_pv_smp_prepare_boot_cpu(void) * sure the old memory can be recycled. */ make_lowmem_page_readwrite(xen_initial_gdt); - xen_filter_cpu_maps(); xen_setup_vcpu_info_placement(); /* @@ -476,5 +459,8 @@ static const struct smp_ops xen_smp_ops __initconst = { void __init xen_smp_init(void) { smp_ops = xen_smp_ops; - xen_fill_possible_map(); + + /* Avoid searching for BIOS MP tables */ + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.get_smp_config = _get_smp_config; } diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c index 31b1e3477cb6..14ea32e734d5 100644 --- a/arch/x86/xen/vga.c +++ b/arch/x86/xen/vga.c @@ -57,6 +57,14 @@ void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size; screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos; + if (size >= offsetof(struct dom0_vga_console_info, + u.vesa_lfb.ext_lfb_base) + + sizeof(info->u.vesa_lfb.ext_lfb_base) + && info->u.vesa_lfb.ext_lfb_base) { + screen_info->ext_lfb_base = info->u.vesa_lfb.ext_lfb_base; + screen_info->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + } + if (info->video_type == XEN_VGATYPE_EFI_LFB) { screen_info->orig_video_isVGA = VIDEO_TYPE_EFI; break; @@ -66,14 +74,6 @@ void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) u.vesa_lfb.mode_attrs) + sizeof(info->u.vesa_lfb.mode_attrs)) screen_info->vesa_attributes = info->u.vesa_lfb.mode_attrs; - - if (size >= offsetof(struct dom0_vga_console_info, - u.vesa_lfb.ext_lfb_base) - + sizeof(info->u.vesa_lfb.ext_lfb_base) - && info->u.vesa_lfb.ext_lfb_base) { - screen_info->ext_lfb_base = info->u.vesa_lfb.ext_lfb_base; - screen_info->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; - } break; } } |