diff options
Diffstat (limited to 'arch')
269 files changed, 1671 insertions, 905 deletions
diff --git a/arch/alpha/include/uapi/asm/Kbuild b/arch/alpha/include/uapi/asm/Kbuild index b15bf6bc0e94..14a2e9af97e9 100644 --- a/arch/alpha/include/uapi/asm/Kbuild +++ b/arch/alpha/include/uapi/asm/Kbuild @@ -1,2 +1,4 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm + +generic-y += bpf_perf_event.h diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild index fa6d0ff4ff89..170b5db64afe 100644 --- a/arch/arc/include/uapi/asm/Kbuild +++ b/arch/arc/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 1b81c4e75772..d37f95025807 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -630,6 +630,7 @@ reg-names = "phy"; status = "disabled"; ti,ctrl_mod = <&usb_ctrl_mod>; + #phy-cells = <0>; }; usb0: usb@47401000 { @@ -678,6 +679,7 @@ reg-names = "phy"; status = "disabled"; ti,ctrl_mod = <&usb_ctrl_mod>; + #phy-cells = <0>; }; usb1: usb@47401800 { diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index e5b061469bf8..4714a59fd86d 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -927,7 +927,8 @@ reg = <0x48038000 0x2000>, <0x46000000 0x400000>; reg-names = "mpu", "dat"; - interrupts = <80>, <81>; + interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "tx", "rx"; status = "disabled"; dmas = <&edma 8 2>, @@ -941,7 +942,8 @@ reg = <0x4803C000 0x2000>, <0x46400000 0x400000>; reg-names = "mpu", "dat"; - interrupts = <82>, <83>; + interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "tx", "rx"; status = "disabled"; dmas = <&edma 10 2>, diff --git a/arch/arm/boot/dts/am437x-cm-t43.dts b/arch/arm/boot/dts/am437x-cm-t43.dts index 9e92d480576b..3b9a94c274a7 100644 --- a/arch/arm/boot/dts/am437x-cm-t43.dts +++ b/arch/arm/boot/dts/am437x-cm-t43.dts @@ -301,8 +301,8 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&spi0_pins>; - dmas = <&edma 16 - &edma 17>; + dmas = <&edma 16 0 + &edma 17 0>; dma-names = "tx0", "rx0"; flash: w25q64cvzpig@0 { diff --git a/arch/arm/boot/dts/armada-385-db-ap.dts b/arch/arm/boot/dts/armada-385-db-ap.dts index 25d2d720dc0e..678aa023335d 100644 --- a/arch/arm/boot/dts/armada-385-db-ap.dts +++ b/arch/arm/boot/dts/armada-385-db-ap.dts @@ -236,6 +236,7 @@ usb3_phy: usb3_phy { compatible = "usb-nop-xceiv"; vcc-supply = <®_xhci0_vbus>; + #phy-cells = <0>; }; reg_xhci0_vbus: xhci0-vbus { diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi index e1f355ffc8f7..434dc9aaa5e4 100644 --- a/arch/arm/boot/dts/armada-385-linksys.dtsi +++ b/arch/arm/boot/dts/armada-385-linksys.dtsi @@ -66,6 +66,7 @@ usb3_1_phy: usb3_1-phy { compatible = "usb-nop-xceiv"; vcc-supply = <&usb3_1_vbus>; + #phy-cells = <0>; }; usb3_1_vbus: usb3_1-vbus { diff --git a/arch/arm/boot/dts/armada-385-synology-ds116.dts b/arch/arm/boot/dts/armada-385-synology-ds116.dts index 36ad571e76f3..0a3552ebda3b 100644 --- a/arch/arm/boot/dts/armada-385-synology-ds116.dts +++ b/arch/arm/boot/dts/armada-385-synology-ds116.dts @@ -191,11 +191,13 @@ usb3_0_phy: usb3_0_phy { compatible = "usb-nop-xceiv"; vcc-supply = <®_usb3_0_vbus>; + #phy-cells = <0>; }; usb3_1_phy: usb3_1_phy { compatible = "usb-nop-xceiv"; vcc-supply = <®_usb3_1_vbus>; + #phy-cells = <0>; }; reg_usb3_0_vbus: usb3-vbus0 { diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts index f503955dbd3b..51b4ee6df130 100644 --- a/arch/arm/boot/dts/armada-388-gp.dts +++ b/arch/arm/boot/dts/armada-388-gp.dts @@ -276,11 +276,13 @@ usb2_1_phy: usb2_1_phy { compatible = "usb-nop-xceiv"; vcc-supply = <®_usb2_1_vbus>; + #phy-cells = <0>; }; usb3_phy: usb3_phy { compatible = "usb-nop-xceiv"; vcc-supply = <®_usb3_vbus>; + #phy-cells = <0>; }; reg_usb3_vbus: usb3-vbus { diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi index 528b9e3bc1da..dcc55aa84583 100644 --- a/arch/arm/boot/dts/bcm-nsp.dtsi +++ b/arch/arm/boot/dts/bcm-nsp.dtsi @@ -85,7 +85,7 @@ timer@20200 { compatible = "arm,cortex-a9-global-timer"; reg = <0x20200 0x100>; - interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>; clocks = <&periph_clk>; }; @@ -93,7 +93,7 @@ compatible = "arm,cortex-a9-twd-timer"; reg = <0x20600 0x20>; interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | - IRQ_TYPE_LEVEL_HIGH)>; + IRQ_TYPE_EDGE_RISING)>; clocks = <&periph_clk>; }; diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index 013431e3d7c3..dcde93c85c2d 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -639,5 +639,6 @@ usbphy: phy { compatible = "usb-nop-xceiv"; + #phy-cells = <0>; }; }; diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts index 3bc50849d013..b8bde13de90a 100644 --- a/arch/arm/boot/dts/bcm958623hr.dts +++ b/arch/arm/boot/dts/bcm958623hr.dts @@ -141,10 +141,6 @@ status = "okay"; }; -&sata { - status = "okay"; -}; - &qspi { bspi-sel = <0>; flash: m25p80@0 { diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts index d94d14b3c745..6a44b8021702 100644 --- a/arch/arm/boot/dts/bcm958625hr.dts +++ b/arch/arm/boot/dts/bcm958625hr.dts @@ -177,10 +177,6 @@ status = "okay"; }; -&sata { - status = "okay"; -}; - &srab { compatible = "brcm,bcm58625-srab", "brcm,nsp-srab"; status = "okay"; diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi index 9708157f5daf..681f5487406e 100644 --- a/arch/arm/boot/dts/dm814x.dtsi +++ b/arch/arm/boot/dts/dm814x.dtsi @@ -75,6 +75,7 @@ reg = <0x47401300 0x100>; reg-names = "phy"; ti,ctrl_mod = <&usb_ctrl_mod>; + #phy-cells = <0>; }; usb0: usb@47401000 { @@ -385,6 +386,7 @@ reg = <0x1b00 0x100>; reg-names = "phy"; ti,ctrl_mod = <&usb_ctrl_mod>; + #phy-cells = <0>; }; }; diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi index 589a67c5f796..84f17f7abb71 100644 --- a/arch/arm/boot/dts/imx53.dtsi +++ b/arch/arm/boot/dts/imx53.dtsi @@ -433,15 +433,6 @@ clock-names = "ipg", "per"; }; - srtc: srtc@53fa4000 { - compatible = "fsl,imx53-rtc", "fsl,imx25-rtc"; - reg = <0x53fa4000 0x4000>; - interrupts = <24>; - interrupt-parent = <&tzic>; - clocks = <&clks IMX5_CLK_SRTC_GATE>; - clock-names = "ipg"; - }; - iomuxc: iomuxc@53fa8000 { compatible = "fsl,imx53-iomuxc"; reg = <0x53fa8000 0x4000>; diff --git a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts index 38faa90007d7..2fa5eb4bd402 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts @@ -72,7 +72,8 @@ }; &gpmc { - ranges = <1 0 0x08000000 0x1000000>; /* CS1: 16MB for LAN9221 */ + ranges = <0 0 0x30000000 0x1000000 /* CS0: 16MB for NAND */ + 1 0 0x2c000000 0x1000000>; /* CS1: 16MB for LAN9221 */ ethernet@gpmc { pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index 26cce4d18405..29cb804d10cc 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -33,11 +33,12 @@ hsusb2_phy: hsusb2_phy { compatible = "usb-nop-xceiv"; reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>; /* gpio_4 */ + #phy-cells = <0>; }; }; &gpmc { - ranges = <0 0 0x00000000 0x1000000>; /* CS0: 16MB for NAND */ + ranges = <0 0 0x30000000 0x1000000>; /* CS0: 16MB for NAND */ nand@0,0 { compatible = "ti,omap2-nand"; @@ -121,7 +122,7 @@ &mmc3 { interrupts-extended = <&intc 94 &omap3_pmx_core2 0x46>; - pinctrl-0 = <&mmc3_pins>; + pinctrl-0 = <&mmc3_pins &wl127x_gpio>; pinctrl-names = "default"; vmmc-supply = <&wl12xx_vmmc>; non-removable; @@ -132,8 +133,8 @@ wlcore: wlcore@2 { compatible = "ti,wl1273"; reg = <2>; - interrupt-parent = <&gpio5>; - interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */ + interrupt-parent = <&gpio1>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; /* gpio 2 */ ref-clock-frequency = <26000000>; }; }; @@ -157,8 +158,6 @@ OMAP3_CORE1_IOPAD(0x2166, PIN_INPUT_PULLUP | MUX_MODE3) /* sdmmc2_dat5.sdmmc3_dat1 */ OMAP3_CORE1_IOPAD(0x2168, PIN_INPUT_PULLUP | MUX_MODE3) /* sdmmc2_dat6.sdmmc3_dat2 */ OMAP3_CORE1_IOPAD(0x216a, PIN_INPUT_PULLUP | MUX_MODE3) /* sdmmc2_dat6.sdmmc3_dat3 */ - OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT_PULLUP | MUX_MODE4) /* mcbsp4_clkx.gpio_152 */ - OMAP3_CORE1_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4) /* sys_boot1.gpio_3 */ OMAP3_CORE1_IOPAD(0x21d0, PIN_INPUT_PULLUP | MUX_MODE3) /* mcspi1_cs1.sdmmc3_cmd */ OMAP3_CORE1_IOPAD(0x21d2, PIN_INPUT_PULLUP | MUX_MODE3) /* mcspi1_cs2.sdmmc_clk */ >; @@ -228,6 +227,12 @@ OMAP3_WKUP_IOPAD(0x2a0e, PIN_OUTPUT | MUX_MODE4) /* sys_boot2.gpio_4 */ >; }; + wl127x_gpio: pinmux_wl127x_gpio_pin { + pinctrl-single,pins = < + OMAP3_WKUP_IOPAD(0x2a0c, PIN_INPUT | MUX_MODE4) /* sys_boot0.gpio_2 */ + OMAP3_WKUP_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4) /* sys_boot1.gpio_3 */ + >; + }; }; &omap3_pmx_core2 { diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi index 4926133077b3..0d9faf1a51ea 100644 --- a/arch/arm/boot/dts/meson.dtsi +++ b/arch/arm/boot/dts/meson.dtsi @@ -85,15 +85,6 @@ reg = <0x7c00 0x200>; }; - gpio_intc: interrupt-controller@9880 { - compatible = "amlogic,meson-gpio-intc"; - reg = <0xc1109880 0x10>; - interrupt-controller; - #interrupt-cells = <2>; - amlogic,channel-interrupts = <64 65 66 67 68 69 70 71>; - status = "disabled"; - }; - hwrng: rng@8100 { compatible = "amlogic,meson-rng"; reg = <0x8100 0x8>; @@ -191,6 +182,15 @@ status = "disabled"; }; + gpio_intc: interrupt-controller@9880 { + compatible = "amlogic,meson-gpio-intc"; + reg = <0x9880 0x10>; + interrupt-controller; + #interrupt-cells = <2>; + amlogic,channel-interrupts = <64 65 66 67 68 69 70 71>; + status = "disabled"; + }; + wdt: watchdog@9900 { compatible = "amlogic,meson6-wdt"; reg = <0x9900 0x8>; diff --git a/arch/arm/boot/dts/nspire.dtsi b/arch/arm/boot/dts/nspire.dtsi index ec2283b1a638..1a5ae4cd107f 100644 --- a/arch/arm/boot/dts/nspire.dtsi +++ b/arch/arm/boot/dts/nspire.dtsi @@ -56,6 +56,7 @@ usb_phy: usb_phy { compatible = "usb-nop-xceiv"; + #phy-cells = <0>; }; vbus_reg: vbus_reg { diff --git a/arch/arm/boot/dts/omap3-beagle-xm.dts b/arch/arm/boot/dts/omap3-beagle-xm.dts index 683b96a8f73e..0349fcc9dc26 100644 --- a/arch/arm/boot/dts/omap3-beagle-xm.dts +++ b/arch/arm/boot/dts/omap3-beagle-xm.dts @@ -90,6 +90,7 @@ compatible = "usb-nop-xceiv"; reset-gpios = <&gpio5 19 GPIO_ACTIVE_LOW>; /* gpio_147 */ vcc-supply = <&hsusb2_power>; + #phy-cells = <0>; }; tfp410: encoder0 { diff --git a/arch/arm/boot/dts/omap3-beagle.dts b/arch/arm/boot/dts/omap3-beagle.dts index 4d2eaf843fa9..3ca8991a6c3e 100644 --- a/arch/arm/boot/dts/omap3-beagle.dts +++ b/arch/arm/boot/dts/omap3-beagle.dts @@ -64,6 +64,7 @@ compatible = "usb-nop-xceiv"; reset-gpios = <&gpio5 19 GPIO_ACTIVE_LOW>; /* gpio_147 */ vcc-supply = <&hsusb2_power>; + #phy-cells = <0>; }; sound { diff --git a/arch/arm/boot/dts/omap3-cm-t3x.dtsi b/arch/arm/boot/dts/omap3-cm-t3x.dtsi index 31d5ebf38892..ab6003fe5a43 100644 --- a/arch/arm/boot/dts/omap3-cm-t3x.dtsi +++ b/arch/arm/boot/dts/omap3-cm-t3x.dtsi @@ -43,12 +43,14 @@ hsusb1_phy: hsusb1_phy { compatible = "usb-nop-xceiv"; vcc-supply = <&hsusb1_power>; + #phy-cells = <0>; }; /* HS USB Host PHY on PORT 2 */ hsusb2_phy: hsusb2_phy { compatible = "usb-nop-xceiv"; vcc-supply = <&hsusb2_power>; + #phy-cells = <0>; }; ads7846reg: ads7846-reg { diff --git a/arch/arm/boot/dts/omap3-evm-common.dtsi b/arch/arm/boot/dts/omap3-evm-common.dtsi index dbc3f030a16c..ee64191e41ca 100644 --- a/arch/arm/boot/dts/omap3-evm-common.dtsi +++ b/arch/arm/boot/dts/omap3-evm-common.dtsi @@ -29,6 +29,7 @@ compatible = "usb-nop-xceiv"; reset-gpios = <&gpio1 21 GPIO_ACTIVE_LOW>; /* gpio_21 */ vcc-supply = <&hsusb2_power>; + #phy-cells = <0>; }; leds { diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index 4504908c23fe..3dc56fb156b7 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -120,6 +120,7 @@ hsusb2_phy: hsusb2_phy { compatible = "usb-nop-xceiv"; reset-gpios = <&gpio6 14 GPIO_ACTIVE_LOW>; + #phy-cells = <0>; }; tv0: connector { diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi index 667f96245729..ecbec23af49f 100644 --- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi +++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi @@ -58,6 +58,7 @@ compatible = "usb-nop-xceiv"; reset-gpios = <&gpio1 24 GPIO_ACTIVE_LOW>; /* gpio_24 */ vcc-supply = <&hsusb1_power>; + #phy-cells = <0>; }; tfp410: encoder { diff --git a/arch/arm/boot/dts/omap3-igep0030-common.dtsi b/arch/arm/boot/dts/omap3-igep0030-common.dtsi index e94d9427450c..443f71707437 100644 --- a/arch/arm/boot/dts/omap3-igep0030-common.dtsi +++ b/arch/arm/boot/dts/omap3-igep0030-common.dtsi @@ -37,6 +37,7 @@ hsusb2_phy: hsusb2_phy { compatible = "usb-nop-xceiv"; reset-gpios = <&gpio2 22 GPIO_ACTIVE_LOW>; /* gpio_54 */ + #phy-cells = <0>; }; }; diff --git a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi index 343a36d8031d..7ada1e93e166 100644 --- a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi +++ b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi @@ -51,6 +51,7 @@ hsusb1_phy: hsusb1_phy { compatible = "usb-nop-xceiv"; vcc-supply = <®_vcc3>; + #phy-cells = <0>; }; }; diff --git a/arch/arm/boot/dts/omap3-overo-base.dtsi b/arch/arm/boot/dts/omap3-overo-base.dtsi index f25e158e7163..ac141fcd1742 100644 --- a/arch/arm/boot/dts/omap3-overo-base.dtsi +++ b/arch/arm/boot/dts/omap3-overo-base.dtsi @@ -51,6 +51,7 @@ compatible = "usb-nop-xceiv"; reset-gpios = <&gpio6 23 GPIO_ACTIVE_LOW>; /* gpio_183 */ vcc-supply = <&hsusb2_power>; + #phy-cells = <0>; }; /* Regulator to trigger the nPoweron signal of the Wifi module */ diff --git a/arch/arm/boot/dts/omap3-pandora-common.dtsi b/arch/arm/boot/dts/omap3-pandora-common.dtsi index 53e007abdc71..cd53dc6c0051 100644 --- a/arch/arm/boot/dts/omap3-pandora-common.dtsi +++ b/arch/arm/boot/dts/omap3-pandora-common.dtsi @@ -205,6 +205,7 @@ compatible = "usb-nop-xceiv"; reset-gpios = <&gpio1 16 GPIO_ACTIVE_LOW>; /* GPIO_16 */ vcc-supply = <&vaux2>; + #phy-cells = <0>; }; /* HS USB Host VBUS supply diff --git a/arch/arm/boot/dts/omap3-tao3530.dtsi b/arch/arm/boot/dts/omap3-tao3530.dtsi index 9a601d15247b..6f5bd027b717 100644 --- a/arch/arm/boot/dts/omap3-tao3530.dtsi +++ b/arch/arm/boot/dts/omap3-tao3530.dtsi @@ -46,6 +46,7 @@ compatible = "usb-nop-xceiv"; reset-gpios = <&gpio6 2 GPIO_ACTIVE_LOW>; /* gpio_162 */ vcc-supply = <&hsusb2_power>; + #phy-cells = <0>; }; sound { diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi index 90b5c7148feb..bb33935df7b0 100644 --- a/arch/arm/boot/dts/omap3.dtsi +++ b/arch/arm/boot/dts/omap3.dtsi @@ -715,6 +715,7 @@ compatible = "ti,ohci-omap3"; reg = <0x48064400 0x400>; interrupts = <76>; + remote-wakeup-connected; }; usbhsehci: ehci@48064800 { diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index 8b93d37310f2..24a463f8641f 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -73,6 +73,7 @@ /* HS USB Host PHY on PORT 1 */ hsusb1_phy: hsusb1_phy { compatible = "usb-nop-xceiv"; + #phy-cells = <0>; }; /* LCD regulator from sw5 source */ diff --git a/arch/arm/boot/dts/omap4-duovero.dtsi b/arch/arm/boot/dts/omap4-duovero.dtsi index 6e6810c258eb..eb123b24c8e3 100644 --- a/arch/arm/boot/dts/omap4-duovero.dtsi +++ b/arch/arm/boot/dts/omap4-duovero.dtsi @@ -43,6 +43,7 @@ hsusb1_phy: hsusb1_phy { compatible = "usb-nop-xceiv"; reset-gpios = <&gpio2 30 GPIO_ACTIVE_LOW>; /* gpio_62 */ + #phy-cells = <0>; pinctrl-names = "default"; pinctrl-0 = <&hsusb1phy_pins>; diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi index 22c1eee9b07a..5501d1b4e6cd 100644 --- a/arch/arm/boot/dts/omap4-panda-common.dtsi +++ b/arch/arm/boot/dts/omap4-panda-common.dtsi @@ -89,6 +89,7 @@ hsusb1_phy: hsusb1_phy { compatible = "usb-nop-xceiv"; reset-gpios = <&gpio2 30 GPIO_ACTIVE_LOW>; /* gpio_62 */ + #phy-cells = <0>; vcc-supply = <&hsusb1_power>; clocks = <&auxclk3_ck>; clock-names = "main_clk"; diff --git a/arch/arm/boot/dts/omap4-var-som-om44.dtsi b/arch/arm/boot/dts/omap4-var-som-om44.dtsi index 6500bfc8d130..10fce28ceb5b 100644 --- a/arch/arm/boot/dts/omap4-var-som-om44.dtsi +++ b/arch/arm/boot/dts/omap4-var-som-om44.dtsi @@ -44,6 +44,7 @@ reset-gpios = <&gpio6 17 GPIO_ACTIVE_LOW>; /* gpio 177 */ vcc-supply = <&vbat>; + #phy-cells = <0>; clocks = <&auxclk3_ck>; clock-names = "main_clk"; diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index 1dc5a76b3c71..cc1a07a3620f 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -398,7 +398,7 @@ elm: elm@48078000 { compatible = "ti,am3352-elm"; reg = <0x48078000 0x2000>; - interrupts = <4>; + interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>; ti,hwmods = "elm"; status = "disabled"; }; @@ -1081,14 +1081,13 @@ usbhsohci: ohci@4a064800 { compatible = "ti,ohci-omap3"; reg = <0x4a064800 0x400>; - interrupt-parent = <&gic>; interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>; + remote-wakeup-connected; }; usbhsehci: ehci@4a064c00 { compatible = "ti,ehci-omap"; reg = <0x4a064c00 0x400>; - interrupt-parent = <&gic>; interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>; }; }; diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 575ecffb0e9e..1b20838bb9a4 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -73,12 +73,14 @@ clocks = <&auxclk1_ck>; clock-names = "main_clk"; clock-frequency = <19200000>; + #phy-cells = <0>; }; /* HS USB Host PHY on PORT 3 */ hsusb3_phy: hsusb3_phy { compatible = "usb-nop-xceiv"; reset-gpios = <&gpio3 15 GPIO_ACTIVE_LOW>; /* gpio3_79 ETH_NRESET */ + #phy-cells = <0>; }; tpd12s015: encoder { diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts index 5b172a04b6f1..5e21fb430a65 100644 --- a/arch/arm/boot/dts/omap5-cm-t54.dts +++ b/arch/arm/boot/dts/omap5-cm-t54.dts @@ -63,12 +63,14 @@ hsusb2_phy: hsusb2_phy { compatible = "usb-nop-xceiv"; reset-gpios = <&gpio3 12 GPIO_ACTIVE_LOW>; /* gpio3_76 HUB_RESET */ + #phy-cells = <0>; }; /* HS USB Host PHY on PORT 3 */ hsusb3_phy: hsusb3_phy { compatible = "usb-nop-xceiv"; reset-gpios = <&gpio3 19 GPIO_ACTIVE_LOW>; /* gpio3_83 ETH_RESET */ + #phy-cells = <0>; }; leds { diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index 4cd0005e462f..51a7fb3d7b9a 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -940,6 +940,7 @@ compatible = "ti,ohci-omap3"; reg = <0x4a064800 0x400>; interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>; + remote-wakeup-connected; }; usbhsehci: ehci@4a064c00 { diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi index 2f017fee4009..62baabd757b6 100644 --- a/arch/arm/boot/dts/r8a7790.dtsi +++ b/arch/arm/boot/dts/r8a7790.dtsi @@ -1201,6 +1201,7 @@ clock-names = "extal", "usb_extal"; #clock-cells = <2>; #power-domain-cells = <0>; + #reset-cells = <1>; }; prr: chipid@ff000044 { diff --git a/arch/arm/boot/dts/r8a7792.dtsi b/arch/arm/boot/dts/r8a7792.dtsi index 131f65b0426e..3d080e07374c 100644 --- a/arch/arm/boot/dts/r8a7792.dtsi +++ b/arch/arm/boot/dts/r8a7792.dtsi @@ -829,6 +829,7 @@ clock-names = "extal"; #clock-cells = <2>; #power-domain-cells = <0>; + #reset-cells = <1>; }; }; diff --git a/arch/arm/boot/dts/r8a7793.dtsi b/arch/arm/boot/dts/r8a7793.dtsi index 58eae569b4e0..0cd1035de1a4 100644 --- a/arch/arm/boot/dts/r8a7793.dtsi +++ b/arch/arm/boot/dts/r8a7793.dtsi @@ -1088,6 +1088,7 @@ clock-names = "extal", "usb_extal"; #clock-cells = <2>; #power-domain-cells = <0>; + #reset-cells = <1>; }; rst: reset-controller@e6160000 { diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi index 905e50c9b524..5643976c1356 100644 --- a/arch/arm/boot/dts/r8a7794.dtsi +++ b/arch/arm/boot/dts/r8a7794.dtsi @@ -1099,6 +1099,7 @@ clock-names = "extal", "usb_extal"; #clock-cells = <2>; #power-domain-cells = <0>; + #reset-cells = <1>; }; rst: reset-controller@e6160000 { diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts index 02a6227c717c..4b8edc8982cf 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts @@ -121,7 +121,7 @@ switch0port10: port@10 { reg = <10>; label = "dsa"; - phy-mode = "xgmii"; + phy-mode = "xaui"; link = <&switch1port10>; }; }; @@ -208,7 +208,7 @@ switch1port10: port@10 { reg = <10>; label = "dsa"; - phy-mode = "xgmii"; + phy-mode = "xaui"; link = <&switch0port10>; }; }; @@ -359,7 +359,7 @@ }; &i2c1 { - at24mac602@0 { + at24mac602@50 { compatible = "atmel,24c02"; reg = <0x50>; read-only; diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index c8781450905b..3ab8b3781bfe 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -161,8 +161,7 @@ #else #define VTTBR_X (5 - KVM_T0SZ) #endif -#define VTTBR_BADDR_SHIFT (VTTBR_X - 1) -#define VTTBR_BADDR_MASK (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) +#define VTTBR_BADDR_MASK (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_X) #define VTTBR_VMID_SHIFT _AC(48, ULL) #define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT) diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 242151ea6908..a9f7d3f47134 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -285,6 +285,11 @@ static inline void kvm_arm_init_debug(void) {} static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {} +static inline bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, + struct kvm_run *run) +{ + return false; +} int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild index 4d53de308ee0..4d1cc1847edf 100644 --- a/arch/arm/include/uapi/asm/Kbuild +++ b/arch/arm/include/uapi/asm/Kbuild @@ -7,6 +7,7 @@ generated-y += unistd-oabi.h generated-y += unistd-eabi.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += ioctl.h generic-y += ipcbuf.h diff --git a/arch/arm/mach-meson/platsmp.c b/arch/arm/mach-meson/platsmp.c index 2555f9056a33..cad7ee8f0d6b 100644 --- a/arch/arm/mach-meson/platsmp.c +++ b/arch/arm/mach-meson/platsmp.c @@ -102,7 +102,7 @@ static void __init meson_smp_prepare_cpus(const char *scu_compatible, scu_base = of_iomap(node, 0); if (!scu_base) { - pr_err("Couln't map SCU registers\n"); + pr_err("Couldn't map SCU registers\n"); return; } diff --git a/arch/arm/mach-omap2/cm_common.c b/arch/arm/mach-omap2/cm_common.c index d555791cf349..83c6fa74cc31 100644 --- a/arch/arm/mach-omap2/cm_common.c +++ b/arch/arm/mach-omap2/cm_common.c @@ -68,14 +68,17 @@ void __init omap2_set_globals_cm(void __iomem *cm, void __iomem *cm2) int cm_split_idlest_reg(struct clk_omap_reg *idlest_reg, s16 *prcm_inst, u8 *idlest_reg_id) { + int ret; if (!cm_ll_data->split_idlest_reg) { WARN_ONCE(1, "cm: %s: no low-level function defined\n", __func__); return -EINVAL; } - return cm_ll_data->split_idlest_reg(idlest_reg, prcm_inst, + ret = cm_ll_data->split_idlest_reg(idlest_reg, prcm_inst, idlest_reg_id); + *prcm_inst -= cm_base.offset; + return ret; } /** @@ -337,6 +340,7 @@ int __init omap2_cm_base_init(void) if (mem) { mem->pa = res.start + data->offset; mem->va = data->mem + data->offset; + mem->offset = data->offset; } data->np = np; diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c index 5ac122e88f67..fa7f308c9027 100644 --- a/arch/arm/mach-omap2/omap-secure.c +++ b/arch/arm/mach-omap2/omap-secure.c @@ -73,6 +73,27 @@ phys_addr_t omap_secure_ram_mempool_base(void) return omap_secure_memblock_base; } +#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM) +u32 omap3_save_secure_ram(void __iomem *addr, int size) +{ + u32 ret; + u32 param[5]; + + if (size != OMAP3_SAVE_SECURE_RAM_SZ) + return OMAP3_SAVE_SECURE_RAM_SZ; + + param[0] = 4; /* Number of arguments */ + param[1] = __pa(addr); /* Physical address for saving */ + param[2] = 0; + param[3] = 1; + param[4] = 1; + + ret = save_secure_ram_context(__pa(param)); + + return ret; +} +#endif + /** * rx51_secure_dispatcher: Routine to dispatch secure PPA API calls * @idx: The PPA API index diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h index bae263fba640..c509cde71f93 100644 --- a/arch/arm/mach-omap2/omap-secure.h +++ b/arch/arm/mach-omap2/omap-secure.h @@ -31,6 +31,8 @@ /* Maximum Secure memory storage size */ #define OMAP_SECURE_RAM_STORAGE (88 * SZ_1K) +#define OMAP3_SAVE_SECURE_RAM_SZ 0x803F + /* Secure low power HAL API index */ #define OMAP4_HAL_SAVESECURERAM_INDEX 0x1a #define OMAP4_HAL_SAVEHW_INDEX 0x1b @@ -65,6 +67,8 @@ extern u32 omap_smc2(u32 id, u32 falg, u32 pargs); extern u32 omap_smc3(u32 id, u32 process, u32 flag, u32 pargs); extern phys_addr_t omap_secure_ram_mempool_base(void); extern int omap_secure_ram_reserve_memblock(void); +extern u32 save_secure_ram_context(u32 args_pa); +extern u32 omap3_save_secure_ram(void __iomem *save_regs, int size); extern u32 rx51_secure_dispatcher(u32 idx, u32 process, u32 flag, u32 nargs, u32 arg1, u32 arg2, u32 arg3, u32 arg4); diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index d45cbfdb4be6..f0388058b7da 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -391,10 +391,8 @@ omap_device_copy_resources(struct omap_hwmod *oh, const char *name; int error, irq = 0; - if (!oh || !oh->od || !oh->od->pdev) { - error = -EINVAL; - goto error; - } + if (!oh || !oh->od || !oh->od->pdev) + return -EINVAL; np = oh->od->pdev->dev.of_node; if (!np) { @@ -516,8 +514,10 @@ struct platform_device __init *omap_device_build(const char *pdev_name, goto odbs_exit1; od = omap_device_alloc(pdev, &oh, 1); - if (IS_ERR(od)) + if (IS_ERR(od)) { + ret = PTR_ERR(od); goto odbs_exit1; + } ret = platform_device_add_data(pdev, pdata, pdata_len); if (ret) diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c index d2106ae4410a..52c9d585b44d 100644 --- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c @@ -1646,6 +1646,7 @@ static struct omap_hwmod omap3xxx_mmc3_hwmod = { .main_clk = "mmchs3_fck", .prcm = { .omap2 = { + .module_offs = CORE_MOD, .prcm_reg_id = 1, .module_bit = OMAP3430_EN_MMC3_SHIFT, .idlest_reg_id = 1, diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h index b668719b9b25..8e30772cfe32 100644 --- a/arch/arm/mach-omap2/pm.h +++ b/arch/arm/mach-omap2/pm.h @@ -81,10 +81,6 @@ extern unsigned int omap3_do_wfi_sz; /* ... and its pointer from SRAM after copy */ extern void (*omap3_do_wfi_sram)(void); -/* save_secure_ram_context function pointer and size, for copy to SRAM */ -extern int save_secure_ram_context(u32 *addr); -extern unsigned int save_secure_ram_context_sz; - extern void omap3_save_scratchpad_contents(void); #define PM_RTA_ERRATUM_i608 (1 << 0) diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 841ba19d64a6..36c55547137c 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -48,6 +48,7 @@ #include "prm3xxx.h" #include "pm.h" #include "sdrc.h" +#include "omap-secure.h" #include "sram.h" #include "control.h" #include "vc.h" @@ -66,7 +67,6 @@ struct power_state { static LIST_HEAD(pwrst_list); -static int (*_omap_save_secure_sram)(u32 *addr); void (*omap3_do_wfi_sram)(void); static struct powerdomain *mpu_pwrdm, *neon_pwrdm; @@ -121,8 +121,8 @@ static void omap3_save_secure_ram_context(void) * will hang the system. */ pwrdm_set_next_pwrst(mpu_pwrdm, PWRDM_POWER_ON); - ret = _omap_save_secure_sram((u32 *)(unsigned long) - __pa(omap3_secure_ram_storage)); + ret = omap3_save_secure_ram(omap3_secure_ram_storage, + OMAP3_SAVE_SECURE_RAM_SZ); pwrdm_set_next_pwrst(mpu_pwrdm, mpu_next_state); /* Following is for error tracking, it should not happen */ if (ret) { @@ -434,15 +434,10 @@ static int __init pwrdms_setup(struct powerdomain *pwrdm, void *unused) * * The minimum set of functions is pushed to SRAM for execution: * - omap3_do_wfi for erratum i581 WA, - * - save_secure_ram_context for security extensions. */ void omap_push_sram_idle(void) { omap3_do_wfi_sram = omap_sram_push(omap3_do_wfi, omap3_do_wfi_sz); - - if (omap_type() != OMAP2_DEVICE_TYPE_GP) - _omap_save_secure_sram = omap_sram_push(save_secure_ram_context, - save_secure_ram_context_sz); } static void __init pm_errata_configure(void) @@ -553,7 +548,7 @@ int __init omap3_pm_init(void) clkdm_add_wkdep(neon_clkdm, mpu_clkdm); if (omap_type() != OMAP2_DEVICE_TYPE_GP) { omap3_secure_ram_storage = - kmalloc(0x803F, GFP_KERNEL); + kmalloc(OMAP3_SAVE_SECURE_RAM_SZ, GFP_KERNEL); if (!omap3_secure_ram_storage) pr_err("Memory allocation failed when allocating for secure sram context\n"); diff --git a/arch/arm/mach-omap2/prcm-common.h b/arch/arm/mach-omap2/prcm-common.h index 0592b23902c6..0977da0dab76 100644 --- a/arch/arm/mach-omap2/prcm-common.h +++ b/arch/arm/mach-omap2/prcm-common.h @@ -528,6 +528,7 @@ struct omap_prcm_irq_setup { struct omap_domain_base { u32 pa; void __iomem *va; + s16 offset; }; /** diff --git a/arch/arm/mach-omap2/prm33xx.c b/arch/arm/mach-omap2/prm33xx.c index d2c5bcabdbeb..ebaf80d72a10 100644 --- a/arch/arm/mach-omap2/prm33xx.c +++ b/arch/arm/mach-omap2/prm33xx.c @@ -176,17 +176,6 @@ static int am33xx_pwrdm_read_pwrst(struct powerdomain *pwrdm) return v; } -static int am33xx_pwrdm_read_prev_pwrst(struct powerdomain *pwrdm) -{ - u32 v; - - v = am33xx_prm_read_reg(pwrdm->prcm_offs, pwrdm->pwrstst_offs); - v &= AM33XX_LASTPOWERSTATEENTERED_MASK; - v >>= AM33XX_LASTPOWERSTATEENTERED_SHIFT; - - return v; -} - static int am33xx_pwrdm_set_lowpwrstchange(struct powerdomain *pwrdm) { am33xx_prm_rmw_reg_bits(AM33XX_LOWPOWERSTATECHANGE_MASK, @@ -357,7 +346,6 @@ struct pwrdm_ops am33xx_pwrdm_operations = { .pwrdm_set_next_pwrst = am33xx_pwrdm_set_next_pwrst, .pwrdm_read_next_pwrst = am33xx_pwrdm_read_next_pwrst, .pwrdm_read_pwrst = am33xx_pwrdm_read_pwrst, - .pwrdm_read_prev_pwrst = am33xx_pwrdm_read_prev_pwrst, .pwrdm_set_logic_retst = am33xx_pwrdm_set_logic_retst, .pwrdm_read_logic_pwrst = am33xx_pwrdm_read_logic_pwrst, .pwrdm_read_logic_retst = am33xx_pwrdm_read_logic_retst, diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index fa5fd24f524c..22daf4efed68 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -93,20 +93,13 @@ ENTRY(enable_omap3630_toggle_l2_on_restore) ENDPROC(enable_omap3630_toggle_l2_on_restore) /* - * Function to call rom code to save secure ram context. This gets - * relocated to SRAM, so it can be all in .data section. Otherwise - * we need to initialize api_params separately. + * Function to call rom code to save secure ram context. + * + * r0 = physical address of the parameters */ - .data - .align 3 ENTRY(save_secure_ram_context) stmfd sp!, {r4 - r11, lr} @ save registers on stack - adr r3, api_params @ r3 points to parameters - str r0, [r3,#0x4] @ r0 has sdram address - ldr r12, high_mask - and r3, r3, r12 - ldr r12, sram_phy_addr_mask - orr r3, r3, r12 + mov r3, r0 @ physical address of parameters mov r0, #25 @ set service ID for PPA mov r12, r0 @ copy secure service ID in r12 mov r1, #0 @ set task id for ROM code in r1 @@ -120,18 +113,7 @@ ENTRY(save_secure_ram_context) nop nop ldmfd sp!, {r4 - r11, pc} - .align -sram_phy_addr_mask: - .word SRAM_BASE_P -high_mask: - .word 0xffff -api_params: - .word 0x4, 0x0, 0x0, 0x1, 0x1 ENDPROC(save_secure_ram_context) -ENTRY(save_secure_ram_context_sz) - .word . - save_secure_ram_context - - .text /* * ====================== diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a93339f5178f..c9a7e9e1414f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -557,7 +557,6 @@ config QCOM_QDF2400_ERRATUM_0065 If unsure, say Y. - config SOCIONEXT_SYNQUACER_PREITS bool "Socionext Synquacer: Workaround for GICv3 pre-ITS" default y @@ -576,6 +575,17 @@ config HISILICON_ERRATUM_161600802 a 128kB offset to be applied to the target address in this commands. If unsure, say Y. + +config QCOM_FALKOR_ERRATUM_E1041 + bool "Falkor E1041: Speculative instruction fetches might cause errant memory access" + default y + help + Falkor CPU may speculatively fetch instructions from an improper + memory location when MMU translation is changed from SCTLR_ELn[M]=1 + to SCTLR_ELn[M]=0. Prefix an ISB instruction to fix the problem. + + If unsure, say Y. + endmenu diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile index d7c22d51bc50..4aa50b9b26bc 100644 --- a/arch/arm64/boot/dts/Makefile +++ b/arch/arm64/boot/dts/Makefile @@ -12,6 +12,7 @@ subdir-y += cavium subdir-y += exynos subdir-y += freescale subdir-y += hisilicon +subdir-y += lg subdir-y += marvell subdir-y += mediatek subdir-y += nvidia @@ -22,5 +23,4 @@ subdir-y += rockchip subdir-y += socionext subdir-y += sprd subdir-y += xilinx -subdir-y += lg subdir-y += zte diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index ead895a4e9a5..1fb8b9d6cb4e 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -753,12 +753,12 @@ &uart_B { clocks = <&xtal>, <&clkc CLKID_UART1>, <&xtal>; - clock-names = "xtal", "core", "baud"; + clock-names = "xtal", "pclk", "baud"; }; &uart_C { clocks = <&xtal>, <&clkc CLKID_UART2>, <&xtal>; - clock-names = "xtal", "core", "baud"; + clock-names = "xtal", "pclk", "baud"; }; &vpu { diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 8ed981f59e5a..6524b89e7115 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -688,7 +688,7 @@ &uart_A { clocks = <&xtal>, <&clkc CLKID_UART0>, <&xtal>; - clock-names = "xtal", "core", "baud"; + clock-names = "xtal", "pclk", "baud"; }; &uart_AO { @@ -703,12 +703,12 @@ &uart_B { clocks = <&xtal>, <&clkc CLKID_UART1>, <&xtal>; - clock-names = "xtal", "core", "baud"; + clock-names = "xtal", "pclk", "baud"; }; &uart_C { clocks = <&xtal>, <&clkc CLKID_UART2>, <&xtal>; - clock-names = "xtal", "core", "baud"; + clock-names = "xtal", "pclk", "baud"; }; &vpu { diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts index dd7193acc7df..6bdefb26b329 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts +++ b/arch/arm64/boot/dts/socionext/uniphier-ld11-ref.dts @@ -40,7 +40,6 @@ }; ðsc { - interrupt-parent = <&gpio>; interrupts = <0 8>; }; diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts index d99e3731358c..254d6795c67e 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts +++ b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts @@ -40,7 +40,6 @@ }; ðsc { - interrupt-parent = <&gpio>; interrupts = <0 8>; }; diff --git a/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts index 864feeb35180..f9f06fcfb94a 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts +++ b/arch/arm64/boot/dts/socionext/uniphier-pxs3-ref.dts @@ -38,8 +38,7 @@ }; ðsc { - interrupt-parent = <&gpio>; - interrupts = <0 8>; + interrupts = <4 8>; }; &serial0 { diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index aef72d886677..8b168280976f 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -512,4 +512,14 @@ alternative_else_nop_endif #endif .endm +/** + * Errata workaround prior to disable MMU. Insert an ISB immediately prior + * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0. + */ + .macro pre_disable_mmu_workaround +#ifdef CONFIG_QCOM_FALKOR_ERRATUM_E1041 + isb +#endif + .endm + #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index ac67cfc2585a..060e3a4008ab 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -60,6 +60,9 @@ enum ftr_type { #define FTR_VISIBLE true /* Feature visible to the user space */ #define FTR_HIDDEN false /* Feature is hidden from the user */ +#define FTR_VISIBLE_IF_IS_ENABLED(config) \ + (IS_ENABLED(config) ? FTR_VISIBLE : FTR_HIDDEN) + struct arm64_ftr_bits { bool sign; /* Value is signed ? */ bool visible; diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 235e77d98261..cbf08d7cbf30 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -91,6 +91,7 @@ #define BRCM_CPU_PART_VULCAN 0x516 #define QCOM_CPU_PART_FALKOR_V1 0x800 +#define QCOM_CPU_PART_FALKOR 0xC00 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) @@ -99,6 +100,7 @@ #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) +#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 650344d01124..c4cd5081d78b 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -132,11 +132,9 @@ static inline void efi_set_pgd(struct mm_struct *mm) * Defer the switch to the current thread's TTBR0_EL1 * until uaccess_enable(). Restore the current * thread's saved ttbr0 corresponding to its active_mm - * (if different from init_mm). */ cpu_set_reserved_ttbr0(); - if (current->active_mm != &init_mm) - update_saved_ttbr0(current, current->active_mm); + update_saved_ttbr0(current, current->active_mm); } } } diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 7f069ff37f06..715d395ef45b 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -170,8 +170,7 @@ #define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS) #define VTTBR_X (VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA) -#define VTTBR_BADDR_SHIFT (VTTBR_X - 1) -#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) +#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X) #define VTTBR_VMID_SHIFT (UL(48)) #define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 674912d7a571..ea6cb5b24258 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -370,6 +370,7 @@ void kvm_arm_init_debug(void); void kvm_arm_setup_debug(struct kvm_vcpu *vcpu); void kvm_arm_clear_debug(struct kvm_vcpu *vcpu); void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu); +bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 3257895a9b5e..9d155fa9a507 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -156,29 +156,21 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu); #define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 0; }) -/* - * This is called when "tsk" is about to enter lazy TLB mode. - * - * mm: describes the currently active mm context - * tsk: task which is entering lazy tlb - * cpu: cpu number which is entering lazy tlb - * - * tsk->mm will be NULL - */ -static inline void -enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ -} - #ifdef CONFIG_ARM64_SW_TTBR0_PAN static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) { - if (system_uses_ttbr0_pan()) { - BUG_ON(mm->pgd == swapper_pg_dir); - task_thread_info(tsk)->ttbr0 = - virt_to_phys(mm->pgd) | ASID(mm) << 48; - } + u64 ttbr; + + if (!system_uses_ttbr0_pan()) + return; + + if (mm == &init_mm) + ttbr = __pa_symbol(empty_zero_page); + else + ttbr = virt_to_phys(mm->pgd) | ASID(mm) << 48; + + task_thread_info(tsk)->ttbr0 = ttbr; } #else static inline void update_saved_ttbr0(struct task_struct *tsk, @@ -187,6 +179,16 @@ static inline void update_saved_ttbr0(struct task_struct *tsk, } #endif +static inline void +enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ + /* + * We don't actually care about the ttbr0 mapping, so point it at the + * zero page. + */ + update_saved_ttbr0(tsk, &init_mm); +} + static inline void __switch_mm(struct mm_struct *next) { unsigned int cpu = smp_processor_id(); @@ -214,11 +216,9 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, * Update the saved TTBR0_EL1 of the scheduled-in task as the previous * value may have not been initialised yet (activate_mm caller) or the * ASID has changed since the last run (following the context switch - * of another thread of the same process). Avoid setting the reserved - * TTBR0_EL1 to swapper_pg_dir (init_mm; e.g. via idle_task_exit). + * of another thread of the same process). */ - if (next != &init_mm) - update_saved_ttbr0(tsk, next); + update_saved_ttbr0(tsk, next); } #define deactivate_mm(tsk,mm) do { } while (0) diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h index 8d5cbec17d80..f9ccc36d3dc3 100644 --- a/arch/arm64/include/asm/perf_event.h +++ b/arch/arm64/include/asm/perf_event.h @@ -18,6 +18,7 @@ #define __ASM_PERF_EVENT_H #include <asm/stack_pointer.h> +#include <asm/ptrace.h> #define ARMV8_PMU_MAX_COUNTERS 32 #define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1) @@ -79,6 +80,7 @@ struct pt_regs; extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) +#define perf_arch_bpf_user_pt_regs(regs) ®s->user_regs #endif #define perf_arch_fetch_caller_regs(regs, __ip) { \ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 149d05fb9421..bdcc7f1c9d06 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -42,6 +42,8 @@ #include <asm/cmpxchg.h> #include <asm/fixmap.h> #include <linux/mmdebug.h> +#include <linux/mm_types.h> +#include <linux/sched.h> extern void __pte_error(const char *file, int line, unsigned long val); extern void __pmd_error(const char *file, int line, unsigned long val); @@ -149,12 +151,20 @@ static inline pte_t pte_mkwrite(pte_t pte) static inline pte_t pte_mkclean(pte_t pte) { - return clear_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + + return pte; } static inline pte_t pte_mkdirty(pte_t pte) { - return set_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); + + if (pte_write(pte)) + pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); + + return pte; } static inline pte_t pte_mkold(pte_t pte) @@ -207,9 +217,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte) } } -struct mm_struct; -struct vm_area_struct; - extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); /* @@ -238,7 +245,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, * hardware updates of the pte (ptep_set_access_flags safely changes * valid ptes without going through an invalid entry). */ - if (pte_valid(*ptep) && pte_valid(pte)) { + if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) && + (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) { VM_WARN_ONCE(!pte_young(pte), "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(*ptep), pte_val(pte)); @@ -641,28 +649,23 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * ptep_set_wrprotect - mark read-only while preserving the hardware update of - * the Access Flag. + * ptep_set_wrprotect - mark read-only while trasferring potential hardware + * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. */ #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t old_pte, pte; - /* - * ptep_set_wrprotect() is only called on CoW mappings which are - * private (!VM_SHARED) with the pte either read-only (!PTE_WRITE && - * PTE_RDONLY) or writable and software-dirty (PTE_WRITE && - * !PTE_RDONLY && PTE_DIRTY); see is_cow_mapping() and - * protection_map[]. There is no race with the hardware update of the - * dirty state: clearing of PTE_RDONLY when PTE_WRITE (a.k.a. PTE_DBM) - * is set. - */ - VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(*ptep), - "%s: potential race with hardware DBM", __func__); pte = READ_ONCE(*ptep); do { old_pte = pte; + /* + * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY + * clear), set the PTE_DIRTY bit. + */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); diff --git a/arch/arm64/include/uapi/asm/bpf_perf_event.h b/arch/arm64/include/uapi/asm/bpf_perf_event.h new file mode 100644 index 000000000000..b551b741653d --- /dev/null +++ b/arch/arm64/include/uapi/asm/bpf_perf_event.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ +#define _UAPI__ASM_BPF_PERF_EVENT_H__ + +#include <asm/ptrace.h> + +typedef struct user_pt_regs bpf_user_pt_regs_t; + +#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */ diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 65f42d257414..2a752cb2a0f3 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -37,6 +37,7 @@ ENTRY(__cpu_soft_restart) mrs x12, sctlr_el1 ldr x13, =SCTLR_ELx_FLAGS bic x12, x12, x13 + pre_disable_mmu_workaround msr sctlr_el1, x12 isb diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index c5ba0097887f..a73a5928f09b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -145,7 +145,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S index 4e6ad355bd05..6b9736c3fb56 100644 --- a/arch/arm64/kernel/efi-entry.S +++ b/arch/arm64/kernel/efi-entry.S @@ -96,6 +96,7 @@ ENTRY(entry) mrs x0, sctlr_el2 bic x0, x0, #1 << 0 // clear SCTLR.M bic x0, x0, #1 << 2 // clear SCTLR.C + pre_disable_mmu_workaround msr sctlr_el2, x0 isb b 2f @@ -103,6 +104,7 @@ ENTRY(entry) mrs x0, sctlr_el1 bic x0, x0, #1 << 0 // clear SCTLR.M bic x0, x0, #1 << 2 // clear SCTLR.C + pre_disable_mmu_workaround msr sctlr_el1, x0 isb 2: diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 5084e699447a..fae81f7964b4 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -114,7 +114,12 @@ * returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so * whatever is in the FPSIMD registers is not saved to memory, but discarded. */ -static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state); +struct fpsimd_last_state_struct { + struct fpsimd_state *st; + bool sve_in_use; +}; + +static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); /* Default VL for tasks that don't set it explicitly: */ static int sve_default_vl = -1; @@ -905,7 +910,7 @@ void fpsimd_thread_switch(struct task_struct *next) */ struct fpsimd_state *st = &next->thread.fpsimd_state; - if (__this_cpu_read(fpsimd_last_state) == st + if (__this_cpu_read(fpsimd_last_state.st) == st && st->cpu == smp_processor_id()) clear_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE); else @@ -992,6 +997,21 @@ void fpsimd_signal_preserve_current_state(void) } /* + * Associate current's FPSIMD context with this cpu + * Preemption must be disabled when calling this function. + */ +static void fpsimd_bind_to_cpu(void) +{ + struct fpsimd_last_state_struct *last = + this_cpu_ptr(&fpsimd_last_state); + struct fpsimd_state *st = ¤t->thread.fpsimd_state; + + last->st = st; + last->sve_in_use = test_thread_flag(TIF_SVE); + st->cpu = smp_processor_id(); +} + +/* * Load the userland FPSIMD state of 'current' from memory, but only if the * FPSIMD state already held in the registers is /not/ the most recent FPSIMD * state of 'current' @@ -1004,11 +1024,8 @@ void fpsimd_restore_current_state(void) local_bh_disable(); if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { - struct fpsimd_state *st = ¤t->thread.fpsimd_state; - task_fpsimd_load(); - __this_cpu_write(fpsimd_last_state, st); - st->cpu = smp_processor_id(); + fpsimd_bind_to_cpu(); } local_bh_enable(); @@ -1026,18 +1043,14 @@ void fpsimd_update_current_state(struct fpsimd_state *state) local_bh_disable(); - current->thread.fpsimd_state = *state; + current->thread.fpsimd_state.user_fpsimd = state->user_fpsimd; if (system_supports_sve() && test_thread_flag(TIF_SVE)) fpsimd_to_sve(current); task_fpsimd_load(); - if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { - struct fpsimd_state *st = ¤t->thread.fpsimd_state; - - __this_cpu_write(fpsimd_last_state, st); - st->cpu = smp_processor_id(); - } + if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) + fpsimd_bind_to_cpu(); local_bh_enable(); } @@ -1052,7 +1065,7 @@ void fpsimd_flush_task_state(struct task_struct *t) static inline void fpsimd_flush_cpu_state(void) { - __this_cpu_write(fpsimd_last_state, NULL); + __this_cpu_write(fpsimd_last_state.st, NULL); } /* @@ -1065,14 +1078,10 @@ static inline void fpsimd_flush_cpu_state(void) #ifdef CONFIG_ARM64_SVE void sve_flush_cpu_state(void) { - struct fpsimd_state *const fpstate = __this_cpu_read(fpsimd_last_state); - struct task_struct *tsk; - - if (!fpstate) - return; + struct fpsimd_last_state_struct const *last = + this_cpu_ptr(&fpsimd_last_state); - tsk = container_of(fpstate, struct task_struct, thread.fpsimd_state); - if (test_tsk_thread_flag(tsk, TIF_SVE)) + if (last->st && last->sve_in_use) fpsimd_flush_cpu_state(); } #endif /* CONFIG_ARM64_SVE */ @@ -1267,7 +1276,7 @@ static inline void fpsimd_pm_init(void) { } #ifdef CONFIG_HOTPLUG_CPU static int fpsimd_cpu_dead(unsigned int cpu) { - per_cpu(fpsimd_last_state, cpu) = NULL; + per_cpu(fpsimd_last_state.st, cpu) = NULL; return 0; } diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 67e86a0f57ac..e3cb9fbf96b6 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -750,6 +750,7 @@ __primary_switch: * to take into account by discarding the current kernel mapping and * creating a new one. */ + pre_disable_mmu_workaround msr sctlr_el1, x20 // disable the MMU isb bl __create_page_tables // recreate kernel mapping diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 749f81779420..74bb56f656ef 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -28,6 +28,7 @@ #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/smp.h> +#include <linux/uaccess.h> #include <asm/compat.h> #include <asm/current.h> @@ -36,7 +37,6 @@ #include <asm/traps.h> #include <asm/cputype.h> #include <asm/system_misc.h> -#include <asm/uaccess.h> /* Breakpoint currently in use for each BRP. */ static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index b2adcce7bc18..6b7dcf4310ac 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -314,6 +314,15 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, clear_tsk_thread_flag(p, TIF_SVE); p->thread.sve_state = NULL; + /* + * In case p was allocated the same task_struct pointer as some + * other recently-exited task, make sure p is disassociated from + * any cpu that may have run that now-exited task recently. + * Otherwise we could erroneously skip reloading the FPSIMD + * registers for p. + */ + fpsimd_flush_task_state(p); + if (likely(!(p->flags & PF_KTHREAD))) { *childregs = *current_pt_regs(); childregs->regs[0] = 0; diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index ce704a4aeadd..f407e422a720 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -45,6 +45,7 @@ ENTRY(arm64_relocate_new_kernel) mrs x0, sctlr_el2 ldr x1, =SCTLR_ELx_FLAGS bic x0, x0, x1 + pre_disable_mmu_workaround msr sctlr_el2, x0 isb 1: diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index dbadfaf850a7..fa63b28c65e0 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -221,3 +221,24 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) } } } + + +/* + * After successfully emulating an instruction, we might want to + * return to user space with a KVM_EXIT_DEBUG. We can only do this + * once the emulation is complete, though, so for userspace emulations + * we have to wait until we have re-entered KVM before calling this + * helper. + * + * Return true (and set exit_reason) to return to userspace or false + * if no further action is required. + */ +bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + run->exit_reason = KVM_EXIT_DEBUG; + run->debug.arch.hsr = ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT; + return true; + } + return false; +} diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index b71247995469..304203fa9e33 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -28,6 +28,7 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/kvm_psci.h> +#include <asm/debug-monitors.h> #define CREATE_TRACE_POINTS #include "trace.h" @@ -187,14 +188,46 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) } /* + * We may be single-stepping an emulated instruction. If the emulation + * has been completed in the kernel, we can return to userspace with a + * KVM_EXIT_DEBUG, otherwise userspace needs to complete its + * emulation first. + */ +static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + int handled; + + /* + * See ARM ARM B1.14.1: "Hyp traps on instructions + * that fail their condition code check" + */ + if (!kvm_condition_valid(vcpu)) { + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + handled = 1; + } else { + exit_handle_fn exit_handler; + + exit_handler = kvm_get_exit_handler(vcpu); + handled = exit_handler(vcpu, run); + } + + /* + * kvm_arm_handle_step_debug() sets the exit_reason on the kvm_run + * structure if we need to return to userspace. + */ + if (handled > 0 && kvm_arm_handle_step_debug(vcpu, run)) + handled = 0; + + return handled; +} + +/* * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on * proper exit to userspace. */ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, int exception_index) { - exit_handle_fn exit_handler; - if (ARM_SERROR_PENDING(exception_index)) { u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu)); @@ -220,20 +253,14 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, return 1; case ARM_EXCEPTION_EL1_SERROR: kvm_inject_vabt(vcpu); - return 1; - case ARM_EXCEPTION_TRAP: - /* - * See ARM ARM B1.14.1: "Hyp traps on instructions - * that fail their condition code check" - */ - if (!kvm_condition_valid(vcpu)) { - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + /* We may still need to return for single-step */ + if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS) + && kvm_arm_handle_step_debug(vcpu, run)) + return 0; + else return 1; - } - - exit_handler = kvm_get_exit_handler(vcpu); - - return exit_handler(vcpu, run); + case ARM_EXCEPTION_TRAP: + return handle_trap_exceptions(vcpu, run); case ARM_EXCEPTION_HYP_GONE: /* * EL2 has been reset to the hyp-stub. This happens when a guest diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index 3f9615582377..870828c364c5 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -151,6 +151,7 @@ reset: mrs x5, sctlr_el2 ldr x6, =SCTLR_ELx_FLAGS bic x5, x5, x6 // Clear SCTL_M and etc + pre_disable_mmu_workaround msr sctlr_el2, x5 isb diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 525c01f48867..f7c651f3a8c0 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -22,6 +22,7 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/fpsimd.h> +#include <asm/debug-monitors.h> static bool __hyp_text __fpsimd_enabled_nvhe(void) { @@ -269,7 +270,11 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) return true; } -static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu) +/* Skip an instruction which has been emulated. Returns true if + * execution can continue or false if we need to exit hyp mode because + * single-step was in effect. + */ +static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(elr); @@ -282,6 +287,14 @@ static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu) } write_sysreg_el2(*vcpu_pc(vcpu), elr); + + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + vcpu->arch.fault.esr_el2 = + (ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT) | 0x22; + return false; + } else { + return true; + } } int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu) @@ -342,13 +355,21 @@ again: int ret = __vgic_v2_perform_cpuif_access(vcpu); if (ret == 1) { - __skip_instr(vcpu); - goto again; + if (__skip_instr(vcpu)) + goto again; + else + exit_code = ARM_EXCEPTION_TRAP; } if (ret == -1) { - /* Promote an illegal access to an SError */ - __skip_instr(vcpu); + /* Promote an illegal access to an + * SError. If we would be returning + * due to single-step clear the SS + * bit so handle_exit knows what to + * do after dealing with the error. + */ + if (!__skip_instr(vcpu)) + *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; exit_code = ARM_EXCEPTION_EL1_SERROR; } @@ -363,8 +384,10 @@ again: int ret = __vgic_v3_perform_cpuif_access(vcpu); if (ret == 1) { - __skip_instr(vcpu); - goto again; + if (__skip_instr(vcpu)) + goto again; + else + exit_code = ARM_EXCEPTION_TRAP; } /* 0 falls through to be handled out of EL2 */ diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index ca74a2aace42..7b60d62ac593 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -389,7 +389,7 @@ void ptdump_check_wx(void) .check_wx = true, }; - walk_pgd(&st, &init_mm, 0); + walk_pgd(&st, &init_mm, VA_START); note_page(&st, 0, 0, 0); if (st.wx_pages || st.uxn_pages) pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n", diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 22168cd0dde7..9b7f89df49db 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -574,7 +574,6 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) { struct siginfo info; const struct fault_info *inf; - int ret = 0; inf = esr_to_fault_info(esr); pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n", @@ -589,7 +588,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) if (interrupts_enabled(regs)) nmi_enter(); - ret = ghes_notify_sea(); + ghes_notify_sea(); if (interrupts_enabled(regs)) nmi_exit(); @@ -604,7 +603,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) info.si_addr = (void __user *)addr; arm64_notify_die("", regs, &info, esr); - return ret; + return 0; } static const struct fault_info fault_info[] = { diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 5960bef0170d..00e7b900ca41 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -476,6 +476,8 @@ void __init arm64_memblock_init(void) reserve_elfcorehdr(); + high_memory = __va(memblock_end_of_DRAM() - 1) + 1; + dma_contiguous_reserve(arm64_dma_phys_limit); memblock_allow_resize(); @@ -502,7 +504,6 @@ void __init bootmem_init(void) sparse_init(); zone_sizes_init(min, max); - high_memory = __va((max << PAGE_SHIFT) - 1) + 1; memblock_dump_all(); } diff --git a/arch/blackfin/include/uapi/asm/Kbuild b/arch/blackfin/include/uapi/asm/Kbuild index aa624b4ab655..2240b38c2915 100644 --- a/arch/blackfin/include/uapi/asm/Kbuild +++ b/arch/blackfin/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += ioctl.h generic-y += ipcbuf.h diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild index 67ee896a76a7..26644e15d854 100644 --- a/arch/c6x/include/uapi/asm/Kbuild +++ b/arch/c6x/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/cris/include/uapi/asm/Kbuild b/arch/cris/include/uapi/asm/Kbuild index 3687b54bb18e..3470c6e9c7b9 100644 --- a/arch/cris/include/uapi/asm/Kbuild +++ b/arch/cris/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/frv/include/uapi/asm/Kbuild b/arch/frv/include/uapi/asm/Kbuild index b15bf6bc0e94..14a2e9af97e9 100644 --- a/arch/frv/include/uapi/asm/Kbuild +++ b/arch/frv/include/uapi/asm/Kbuild @@ -1,2 +1,4 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm + +generic-y += bpf_perf_event.h diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild index 187aed820e71..2f65f78792cb 100644 --- a/arch/h8300/include/uapi/asm/Kbuild +++ b/arch/h8300/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild index cb5df3aad3a8..41a176dbb53e 100644 --- a/arch/hexagon/include/uapi/asm/Kbuild +++ b/arch/hexagon/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/ia64/include/uapi/asm/Kbuild b/arch/ia64/include/uapi/asm/Kbuild index 13a97aa2285f..f5c6967a93bb 100644 --- a/arch/ia64/include/uapi/asm/Kbuild +++ b/arch/ia64/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += kvm_para.h diff --git a/arch/m32r/include/uapi/asm/Kbuild b/arch/m32r/include/uapi/asm/Kbuild index 1c44d3b3eba0..451bf6071c6e 100644 --- a/arch/m32r/include/uapi/asm/Kbuild +++ b/arch/m32r/include/uapi/asm/Kbuild @@ -1,5 +1,6 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += kvm_para.h generic-y += siginfo.h diff --git a/arch/m68k/configs/stmark2_defconfig b/arch/m68k/configs/stmark2_defconfig index 55e55dbc2fb6..3d07b1de7eb0 100644 --- a/arch/m68k/configs/stmark2_defconfig +++ b/arch/m68k/configs/stmark2_defconfig @@ -5,7 +5,6 @@ CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_NAMESPACES=y CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../uClinux-dist/romfs" # CONFIG_RD_BZIP2 is not set # CONFIG_RD_LZMA is not set # CONFIG_RD_XZ is not set diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild index 3717b64a620d..c2e26a44c482 100644 --- a/arch/m68k/include/uapi/asm/Kbuild +++ b/arch/m68k/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += ioctl.h generic-y += ipcbuf.h diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds index 3aa571a513b5..cf6edda38971 100644 --- a/arch/m68k/kernel/vmlinux-nommu.lds +++ b/arch/m68k/kernel/vmlinux-nommu.lds @@ -45,6 +45,8 @@ SECTIONS { .text : { HEAD_TEXT TEXT_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT SCHED_TEXT CPUIDLE_TEXT LOCK_TEXT diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds index 89172b8974b9..625a5785804f 100644 --- a/arch/m68k/kernel/vmlinux-std.lds +++ b/arch/m68k/kernel/vmlinux-std.lds @@ -16,6 +16,8 @@ SECTIONS .text : { HEAD_TEXT TEXT_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT SCHED_TEXT CPUIDLE_TEXT LOCK_TEXT diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds index 293990efc917..9868270b0984 100644 --- a/arch/m68k/kernel/vmlinux-sun3.lds +++ b/arch/m68k/kernel/vmlinux-sun3.lds @@ -16,6 +16,8 @@ SECTIONS .text : { HEAD_TEXT TEXT_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT SCHED_TEXT CPUIDLE_TEXT LOCK_TEXT diff --git a/arch/metag/include/uapi/asm/Kbuild b/arch/metag/include/uapi/asm/Kbuild index 6ac763d9a3e3..f9eaf07d29f8 100644 --- a/arch/metag/include/uapi/asm/Kbuild +++ b/arch/metag/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index 06609ca36115..2c6a6bffea32 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 7c8aab23bce8..b1f66699677d 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -16,7 +16,6 @@ generic-y += qrwlock.h generic-y += qspinlock.h generic-y += sections.h generic-y += segment.h -generic-y += serial.h generic-y += trace_clock.h generic-y += unaligned.h generic-y += user.h diff --git a/arch/mips/include/asm/serial.h b/arch/mips/include/asm/serial.h new file mode 100644 index 000000000000..1d830c6666c2 --- /dev/null +++ b/arch/mips/include/asm/serial.h @@ -0,0 +1,22 @@ +/* + * Copyright (C) 2017 MIPS Tech, LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ +#ifndef __ASM__SERIAL_H +#define __ASM__SERIAL_H + +#ifdef CONFIG_MIPS_GENERIC +/* + * Generic kernels cannot know a correct value for all platforms at + * compile time. Set it to 0 to prevent 8250_early using it + */ +#define BASE_BAUD 0 +#else +#include <asm-generic/serial.h> +#endif + +#endif /* __ASM__SERIAL_H */ diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild index a0266feba9e6..7a4becd8963a 100644 --- a/arch/mips/include/uapi/asm/Kbuild +++ b/arch/mips/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += ipcbuf.h diff --git a/arch/mn10300/include/uapi/asm/Kbuild b/arch/mn10300/include/uapi/asm/Kbuild index c94ee54210bc..81271d3af47c 100644 --- a/arch/mn10300/include/uapi/asm/Kbuild +++ b/arch/mn10300/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += siginfo.h diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild index ffca24da7647..13a3d77b4d7b 100644 --- a/arch/nios2/include/uapi/asm/Kbuild +++ b/arch/nios2/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild index 62286dbeb904..130c16ccba0a 100644 --- a/arch/openrisc/include/uapi/asm/Kbuild +++ b/arch/openrisc/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c index 9345b44b86f0..f57118e1f6b4 100644 --- a/arch/parisc/boot/compressed/misc.c +++ b/arch/parisc/boot/compressed/misc.c @@ -123,8 +123,8 @@ int puts(const char *s) while ((nuline = strchr(s, '\n')) != NULL) { if (nuline != s) pdc_iodc_print(s, nuline - s); - pdc_iodc_print("\r\n", 2); - s = nuline + 1; + pdc_iodc_print("\r\n", 2); + s = nuline + 1; } if (*s != '\0') pdc_iodc_print(s, strlen(s)); diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h index c980a02a52bc..598c8d60fa5e 100644 --- a/arch/parisc/include/asm/thread_info.h +++ b/arch/parisc/include/asm/thread_info.h @@ -35,7 +35,12 @@ struct thread_info { /* thread information allocation */ +#ifdef CONFIG_IRQSTACKS +#define THREAD_SIZE_ORDER 2 /* PA-RISC requires at least 16k stack */ +#else #define THREAD_SIZE_ORDER 3 /* PA-RISC requires at least 32k stack */ +#endif + /* Be sure to hunt all references to this down when you change the size of * the kernel stack */ #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) diff --git a/arch/parisc/include/uapi/asm/Kbuild b/arch/parisc/include/uapi/asm/Kbuild index 196d2a4efb31..286ef5a5904b 100644 --- a/arch/parisc/include/uapi/asm/Kbuild +++ b/arch/parisc/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h +generic-y += bpf_perf_event.h generic-y += kvm_para.h generic-y += param.h generic-y += poll.h diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index a4fd296c958e..f3cecf5117cf 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -878,9 +878,6 @@ ENTRY_CFI(syscall_exit_rfi) STREG %r19,PT_SR7(%r16) intr_return: - /* NOTE: Need to enable interrupts incase we schedule. */ - ssm PSW_SM_I, %r0 - /* check for reschedule */ mfctl %cr30,%r1 LDREG TI_FLAGS(%r1),%r19 /* sched.h: TIF_NEED_RESCHED */ @@ -907,6 +904,11 @@ intr_check_sig: LDREG PT_IASQ1(%r16), %r20 cmpib,COND(=),n 0,%r20,intr_restore /* backward */ + /* NOTE: We need to enable interrupts if we have to deliver + * signals. We used to do this earlier but it caused kernel + * stack overflows. */ + ssm PSW_SM_I, %r0 + copy %r0, %r25 /* long in_syscall = 0 */ #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ @@ -958,6 +960,10 @@ intr_do_resched: cmpib,COND(=) 0, %r20, intr_do_preempt nop + /* NOTE: We need to enable interrupts if we schedule. We used + * to do this earlier but it caused kernel stack overflows. */ + ssm PSW_SM_I, %r0 + #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ #endif diff --git a/arch/parisc/kernel/hpmc.S b/arch/parisc/kernel/hpmc.S index e3a8e5e4d5de..8d072c44f300 100644 --- a/arch/parisc/kernel/hpmc.S +++ b/arch/parisc/kernel/hpmc.S @@ -305,6 +305,7 @@ ENDPROC_CFI(os_hpmc) __INITRODATA + .align 4 .export os_hpmc_size os_hpmc_size: .word .os_hpmc_end-.os_hpmc diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index 5a657986ebbf..143f90e2f9f3 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -15,7 +15,6 @@ #include <linux/slab.h> #include <linux/kallsyms.h> #include <linux/sort.h> -#include <linux/sched.h> #include <linux/uaccess.h> #include <asm/assembly.h> diff --git a/arch/parisc/lib/delay.c b/arch/parisc/lib/delay.c index 7eab4bb8abe6..66e506520505 100644 --- a/arch/parisc/lib/delay.c +++ b/arch/parisc/lib/delay.c @@ -16,9 +16,7 @@ #include <linux/preempt.h> #include <linux/init.h> -#include <asm/processor.h> #include <asm/delay.h> - #include <asm/special_insns.h> /* for mfctl() */ #include <asm/processor.h> /* for boot_cpu_data */ diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 73b92017b6d7..cd2fc1cc1cc7 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -76,6 +76,7 @@ struct machdep_calls { void __noreturn (*restart)(char *cmd); void __noreturn (*halt)(void); + void (*panic)(char *str); void (*cpu_die)(void); long (*time_init)(void); /* Optional, may be NULL */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 257d23dbf55d..cf00ec26303a 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -24,6 +24,7 @@ extern void reloc_got2(unsigned long); void check_for_initrd(void); void initmem_init(void); +void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild index 0d960ef78a9a..1a6ed5919ffd 100644 --- a/arch/powerpc/include/uapi/asm/Kbuild +++ b/arch/powerpc/include/uapi/asm/Kbuild @@ -1,6 +1,7 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += param.h generic-y += poll.h generic-y += resource.h diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 610955fe8b81..679bbe714e85 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -102,6 +102,7 @@ _GLOBAL(__setup_cpu_power9) li r0,0 mtspr SPRN_PSSCR,r0 mtspr SPRN_LPID,r0 + mtspr SPRN_PID,r0 mfspr r3,SPRN_LPCR LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC) or r3, r3, r4 @@ -126,6 +127,7 @@ _GLOBAL(__restore_cpu_power9) li r0,0 mtspr SPRN_PSSCR,r0 mtspr SPRN_LPID,r0 + mtspr SPRN_PID,r0 mfspr r3,SPRN_LPCR LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC) or r3, r3, r4 diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 04ea5c04fd24..3c2c2688918f 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -1462,25 +1462,6 @@ static void fadump_init_files(void) return; } -static int fadump_panic_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - /* - * If firmware-assisted dump has been registered then trigger - * firmware-assisted dump and let firmware handle everything - * else. If this returns, then fadump was not registered, so - * go through the rest of the panic path. - */ - crash_fadump(NULL, ptr); - - return NOTIFY_DONE; -} - -static struct notifier_block fadump_panic_block = { - .notifier_call = fadump_panic_event, - .priority = INT_MIN /* may not return; must be done last */ -}; - /* * Prepare for firmware-assisted dump. */ @@ -1513,9 +1494,6 @@ int __init setup_fadump(void) init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start); fadump_init_files(); - atomic_notifier_chain_register(&panic_notifier_list, - &fadump_panic_block); - return 1; } subsys_initcall(setup_fadump); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 2075322cd225..9d213542a48b 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -704,6 +704,30 @@ int check_legacy_ioport(unsigned long base_port) } EXPORT_SYMBOL(check_legacy_ioport); +static int ppc_panic_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + /* + * If firmware-assisted dump has been registered then trigger + * firmware-assisted dump and let firmware handle everything else. + */ + crash_fadump(NULL, ptr); + ppc_md.panic(ptr); /* May not return */ + return NOTIFY_DONE; +} + +static struct notifier_block ppc_panic_block = { + .notifier_call = ppc_panic_event, + .priority = INT_MIN /* may not return; must be done last */ +}; + +void __init setup_panic(void) +{ + if (!ppc_md.panic) + return; + atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); +} + #ifdef CONFIG_CHECK_CACHE_COHERENCY /* * For platforms that have configurable cache-coherency. This function @@ -848,6 +872,9 @@ void __init setup_arch(char **cmdline_p) /* Probe the machine type, establish ppc_md. */ probe_machine(); + /* Setup panic notifier if requested by the platform. */ + setup_panic(); + /* * Configure ppc_md.power_save (ppc32 only, 64-bit machines do * it from their respective probe() function. diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 9e3da168d54c..153812966365 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1415,7 +1415,7 @@ static int collect_events(struct perf_event *group, int max_count, int n = 0; struct perf_event *event; - if (!is_software_event(group)) { + if (group->pmu->task_ctx_nr == perf_hw_context) { if (n >= max_count) return -1; ctrs[n] = group; @@ -1423,7 +1423,7 @@ static int collect_events(struct perf_event *group, int max_count, events[n++] = group->hw.config; } list_for_each_entry(event, &group->sibling_list, group_entry) { - if (!is_software_event(event) && + if (event->pmu->task_ctx_nr == perf_hw_context && event->state != PERF_EVENT_STATE_OFF) { if (n >= max_count) return -1; diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 9dabea6e1443..6244bc849469 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -104,6 +104,20 @@ static void __noreturn ps3_halt(void) ps3_sys_manager_halt(); /* never returns */ } +static void ps3_panic(char *str) +{ + DBG("%s:%d %s\n", __func__, __LINE__, str); + + smp_send_stop(); + printk("\n"); + printk(" System does not reboot automatically.\n"); + printk(" Please press POWER button.\n"); + printk("\n"); + + while(1) + lv1_pause(1); +} + #if defined(CONFIG_FB_PS3) || defined(CONFIG_FB_PS3_MODULE) || \ defined(CONFIG_PS3_FLASH) || defined(CONFIG_PS3_FLASH_MODULE) static void __init prealloc(struct ps3_prealloc *p) @@ -255,6 +269,7 @@ define_machine(ps3) { .probe = ps3_probe, .setup_arch = ps3_setup_arch, .init_IRQ = ps3_init_IRQ, + .panic = ps3_panic, .get_boot_time = ps3_get_boot_time, .set_dabr = ps3_set_dabr, .calibrate_decr = ps3_calibrate_decr, diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 5f1beb8367ac..a8531e012658 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -726,6 +726,7 @@ define_machine(pseries) { .pcibios_fixup = pSeries_final_fixup, .restart = rtas_restart, .halt = rtas_halt, + .panic = rtas_os_term, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, .set_rtc_time = rtas_set_rtc_time, diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 1b2d8cb49abb..cab24f549e7c 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1590,7 +1590,7 @@ static void print_bug_trap(struct pt_regs *regs) printf("kernel BUG at %s:%u!\n", bug->file, bug->line); #else - printf("kernel BUG at %p!\n", (void *)bug->bug_addr); + printf("kernel BUG at %px!\n", (void *)bug->bug_addr); #endif #endif /* CONFIG_BUG */ } @@ -2329,7 +2329,7 @@ static void dump_one_paca(int cpu) p = &paca[cpu]; - printf("paca for cpu 0x%x @ %p:\n", cpu, p); + printf("paca for cpu 0x%x @ %px:\n", cpu, p); printf(" %-*s = %s\n", 20, "possible", cpu_possible(cpu) ? "yes" : "no"); printf(" %-*s = %s\n", 20, "present", cpu_present(cpu) ? "yes" : "no"); @@ -2945,7 +2945,7 @@ static void show_task(struct task_struct *tsk) (tsk->exit_state & EXIT_DEAD) ? 'E' : (tsk->state & TASK_INTERRUPTIBLE) ? 'S' : '?'; - printf("%p %016lx %6d %6d %c %2d %s\n", tsk, + printf("%px %016lx %6d %6d %c %2d %s\n", tsk, tsk->thread.ksp, tsk->pid, tsk->parent->pid, state, task_thread_info(tsk)->cpu, @@ -2988,7 +2988,7 @@ static void show_pte(unsigned long addr) if (setjmp(bus_error_jmp) != 0) { catch_memory_errors = 0; - printf("*** Error dumping pte for task %p\n", tsk); + printf("*** Error dumping pte for task %px\n", tsk); return; } @@ -3074,7 +3074,7 @@ static void show_tasks(void) if (setjmp(bus_error_jmp) != 0) { catch_memory_errors = 0; - printf("*** Error dumping task %p\n", tsk); + printf("*** Error dumping task %px\n", tsk); return; } diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index 773c4e039cd7..c0319cbf1eec 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -38,6 +38,25 @@ #define smp_rmb() RISCV_FENCE(r,r) #define smp_wmb() RISCV_FENCE(w,w) +/* + * This is a very specific barrier: it's currently only used in two places in + * the kernel, both in the scheduler. See include/linux/spinlock.h for the two + * orderings it guarantees, but the "critical section is RCsc" guarantee + * mandates a barrier on RISC-V. The sequence looks like: + * + * lr.aq lock + * sc lock <= LOCKED + * smp_mb__after_spinlock() + * // critical section + * lr lock + * sc.rl lock <= UNLOCKED + * + * The AQ/RL pair provides a RCpc critical section, but there's not really any + * way we can take advantage of that here because the ordering is only enforced + * on that one lock. Thus, we're just doing a full fence. + */ +#define smp_mb__after_spinlock() RISCV_FENCE(rw,rw) + #include <asm-generic/barrier.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/include/uapi/asm/Kbuild b/arch/riscv/include/uapi/asm/Kbuild index 5ded96b06352..7e91f4850475 100644 --- a/arch/riscv/include/uapi/asm/Kbuild +++ b/arch/riscv/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += setup.h generic-y += unistd.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 8fbb6749910d..cb7b0c63014e 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -38,10 +38,6 @@ #include <asm/tlbflush.h> #include <asm/thread_info.h> -#ifdef CONFIG_HVC_RISCV_SBI -#include <asm/hvc_riscv_sbi.h> -#endif - #ifdef CONFIG_DUMMY_CONSOLE struct screen_info screen_info = { .orig_video_lines = 30, @@ -212,13 +208,6 @@ static void __init setup_bootmem(void) void __init setup_arch(char **cmdline_p) { -#if defined(CONFIG_HVC_RISCV_SBI) - if (likely(early_console == NULL)) { - early_console = &riscv_sbi_early_console_dev; - register_console(early_console); - } -#endif - #ifdef CONFIG_CMDLINE_BOOL #ifdef CONFIG_CMDLINE_OVERRIDE strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index a2ae936a093e..79c78668258e 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -70,7 +70,7 @@ SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end, bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0; /* Check the reserved flags. */ - if (unlikely(flags & !SYS_RISCV_FLUSH_ICACHE_ALL)) + if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL)) return -EINVAL; flush_icache_mm(mm, local); diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild index eae2c64cf69d..9fdff3fe1a42 100644 --- a/arch/s390/Kbuild +++ b/arch/s390/Kbuild @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-y += kernel/ obj-y += mm/ obj-$(CONFIG_KVM) += kvm/ diff --git a/arch/s390/appldata/Makefile b/arch/s390/appldata/Makefile index 99f1cf071304..b06def4a4f2f 100644 --- a/arch/s390/appldata/Makefile +++ b/arch/s390/appldata/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the Linux - z/VM Monitor Stream. # diff --git a/arch/s390/boot/compressed/vmlinux.scr b/arch/s390/boot/compressed/vmlinux.scr index f02382ae5c48..42a242597f34 100644 --- a/arch/s390/boot/compressed/vmlinux.scr +++ b/arch/s390/boot/compressed/vmlinux.scr @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ SECTIONS { .rodata.compressed : { diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index c7de53d8da75..a00c17f761c1 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Cryptographic API. * @@ -16,12 +17,6 @@ * Copyright (c) Alan Smithee. * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk> * Copyright (c) Jean-Francois Dive <jef@linuxbe.org> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation; either version 2 of the License, or (at your option) - * any later version. - * */ #include <crypto/internal/hash.h> #include <linux/init.h> diff --git a/arch/s390/hypfs/Makefile b/arch/s390/hypfs/Makefile index 2ee25ba252d6..06f601509ce9 100644 --- a/arch/s390/hypfs/Makefile +++ b/arch/s390/hypfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the linux hypfs filesystem routines. # diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 41c211a4d8b1..048450869328 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 generic-y += asm-offsets.h generic-y += cacheflush.h generic-y += clkdev.h diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h index a72002056b54..c2cf7bcdef9b 100644 --- a/arch/s390/include/asm/alternative.h +++ b/arch/s390/include/asm/alternative.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_S390_ALTERNATIVE_H #define _ASM_S390_ALTERNATIVE_H diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index c02f4aba88a6..cfce6835b109 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Adjunct processor (AP) interfaces * * Copyright IBM Corp. 2017 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): Tony Krowiak <akrowia@linux.vnet.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> * Harald Freudenberger <freude@de.ibm.com> diff --git a/arch/s390/include/asm/bugs.h b/arch/s390/include/asm/bugs.h index 0f5bd894f4dc..aa42a179be33 100644 --- a/arch/s390/include/asm/bugs.h +++ b/arch/s390/include/asm/bugs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * S390 version * Copyright IBM Corp. 1999 diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h index d6c9d1e0dc2d..b9c0e361748b 100644 --- a/arch/s390/include/asm/perf_event.h +++ b/arch/s390/include/asm/perf_event.h @@ -40,6 +40,7 @@ struct pt_regs; extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) +#define perf_arch_bpf_user_pt_regs(regs) ®s->user_regs /* Perf pt_regs extension for sample-data-entry indicators */ struct perf_sf_sde_regs { diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 57d7bc92e0b8..0a6b0286c32e 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1264,12 +1264,6 @@ static inline pud_t pud_mkwrite(pud_t pud) return pud; } -#define pud_write pud_write -static inline int pud_write(pud_t pud) -{ - return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0; -} - static inline pud_t pud_mkclean(pud_t pud) { if (pud_large(pud)) { diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index a3788dafc0e1..6f70d81c40f2 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -74,9 +74,14 @@ enum { */ struct pt_regs { - unsigned long args[1]; - psw_t psw; - unsigned long gprs[NUM_GPRS]; + union { + user_pt_regs user_regs; + struct { + unsigned long args[1]; + psw_t psw; + unsigned long gprs[NUM_GPRS]; + }; + }; unsigned long orig_gpr2; unsigned int int_code; unsigned int int_parm; diff --git a/arch/s390/include/asm/segment.h b/arch/s390/include/asm/segment.h index 8bfce3475b1c..97a0582b8d0f 100644 --- a/arch/s390/include/asm/segment.h +++ b/arch/s390/include/asm/segment.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_SEGMENT_H #define _ASM_SEGMENT_H diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h index ec7b476c1ac5..c61b2cc1a8a8 100644 --- a/arch/s390/include/asm/switch_to.h +++ b/arch/s390/include/asm/switch_to.h @@ -30,21 +30,20 @@ static inline void restore_access_regs(unsigned int *acrs) asm volatile("lam 0,15,%0" : : "Q" (*(acrstype *)acrs)); } -#define switch_to(prev,next,last) do { \ - if (prev->mm) { \ - save_fpu_regs(); \ - save_access_regs(&prev->thread.acrs[0]); \ - save_ri_cb(prev->thread.ri_cb); \ - save_gs_cb(prev->thread.gs_cb); \ - } \ +#define switch_to(prev, next, last) do { \ + /* save_fpu_regs() sets the CIF_FPU flag, which enforces \ + * a restore of the floating point / vector registers as \ + * soon as the next task returns to user space \ + */ \ + save_fpu_regs(); \ + save_access_regs(&prev->thread.acrs[0]); \ + save_ri_cb(prev->thread.ri_cb); \ + save_gs_cb(prev->thread.gs_cb); \ update_cr_regs(next); \ - if (next->mm) { \ - set_cpu_flag(CIF_FPU); \ - restore_access_regs(&next->thread.acrs[0]); \ - restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); \ - restore_gs_cb(next->thread.gs_cb); \ - } \ - prev = __switch_to(prev,next); \ + restore_access_regs(&next->thread.acrs[0]); \ + restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); \ + restore_gs_cb(next->thread.gs_cb); \ + prev = __switch_to(prev, next); \ } while (0) #endif /* __ASM_SWITCH_TO_H */ diff --git a/arch/s390/include/asm/vga.h b/arch/s390/include/asm/vga.h index d375526c261f..605dc46bac5e 100644 --- a/arch/s390/include/asm/vga.h +++ b/arch/s390/include/asm/vga.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_S390_VGA_H #define _ASM_S390_VGA_H diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild index 098f28778a13..92b7c9b3e641 100644 --- a/arch/s390/include/uapi/asm/Kbuild +++ b/arch/s390/include/uapi/asm/Kbuild @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm diff --git a/arch/s390/include/uapi/asm/bpf_perf_event.h b/arch/s390/include/uapi/asm/bpf_perf_event.h new file mode 100644 index 000000000000..cefe7c7cd4f6 --- /dev/null +++ b/arch/s390/include/uapi/asm/bpf_perf_event.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ +#define _UAPI__ASM_BPF_PERF_EVENT_H__ + +#include <asm/ptrace.h> + +typedef user_pt_regs bpf_user_pt_regs_t; + +#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */ diff --git a/arch/s390/include/uapi/asm/perf_regs.h b/arch/s390/include/uapi/asm/perf_regs.h index 7c8564f98205..d17dd9e5d516 100644 --- a/arch/s390/include/uapi/asm/perf_regs.h +++ b/arch/s390/include/uapi/asm/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_S390_PERF_REGS_H #define _ASM_S390_PERF_REGS_H diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h index 0d23c8ff2900..543dd70e12c8 100644 --- a/arch/s390/include/uapi/asm/ptrace.h +++ b/arch/s390/include/uapi/asm/ptrace.h @@ -162,7 +162,7 @@ #define GPR_SIZE 8 #define CR_SIZE 8 -#define STACK_FRAME_OVERHEAD 160 /* size of minimum stack frame */ +#define STACK_FRAME_OVERHEAD 160 /* size of minimum stack frame */ #endif /* __s390x__ */ @@ -179,17 +179,16 @@ #define ACR_SIZE 4 -#define PTRACE_OLDSETOPTIONS 21 +#define PTRACE_OLDSETOPTIONS 21 #ifndef __ASSEMBLY__ #include <linux/stddef.h> #include <linux/types.h> -typedef union -{ - float f; - double d; - __u64 ui; +typedef union { + float f; + double d; + __u64 ui; struct { __u32 hi; @@ -197,23 +196,21 @@ typedef union } fp; } freg_t; -typedef struct -{ - __u32 fpc; +typedef struct { + __u32 fpc; __u32 pad; - freg_t fprs[NUM_FPRS]; + freg_t fprs[NUM_FPRS]; } s390_fp_regs; -#define FPC_EXCEPTION_MASK 0xF8000000 -#define FPC_FLAGS_MASK 0x00F80000 -#define FPC_DXC_MASK 0x0000FF00 -#define FPC_RM_MASK 0x00000003 +#define FPC_EXCEPTION_MASK 0xF8000000 +#define FPC_FLAGS_MASK 0x00F80000 +#define FPC_DXC_MASK 0x0000FF00 +#define FPC_RM_MASK 0x00000003 /* this typedef defines how a Program Status Word looks like */ -typedef struct -{ - unsigned long mask; - unsigned long addr; +typedef struct { + unsigned long mask; + unsigned long addr; } __attribute__ ((aligned(8))) psw_t; #ifndef __s390x__ @@ -282,8 +279,7 @@ typedef struct /* * The s390_regs structure is used to define the elf_gregset_t. */ -typedef struct -{ +typedef struct { psw_t psw; unsigned long gprs[NUM_GPRS]; unsigned int acrs[NUM_ACRS]; @@ -291,24 +287,32 @@ typedef struct } s390_regs; /* + * The user_pt_regs structure exports the beginning of + * the in-kernel pt_regs structure to user space. + */ +typedef struct { + unsigned long args[1]; + psw_t psw; + unsigned long gprs[NUM_GPRS]; +} user_pt_regs; + +/* * Now for the user space program event recording (trace) definitions. * The following structures are used only for the ptrace interface, don't * touch or even look at it if you don't want to modify the user-space * ptrace interface. In particular stay away from it for in-kernel PER. */ -typedef struct -{ +typedef struct { unsigned long cr[NUM_CR_WORDS]; } per_cr_words; #define PER_EM_MASK 0xE8000000UL -typedef struct -{ +typedef struct { #ifdef __s390x__ - unsigned : 32; + unsigned : 32; #endif /* __s390x__ */ - unsigned em_branching : 1; + unsigned em_branching : 1; unsigned em_instruction_fetch : 1; /* * Switching on storage alteration automatically fixes @@ -317,44 +321,41 @@ typedef struct unsigned em_storage_alteration : 1; unsigned em_gpr_alt_unused : 1; unsigned em_store_real_address : 1; - unsigned : 3; + unsigned : 3; unsigned branch_addr_ctl : 1; - unsigned : 1; + unsigned : 1; unsigned storage_alt_space_ctl : 1; - unsigned : 21; + unsigned : 21; unsigned long starting_addr; unsigned long ending_addr; } per_cr_bits; -typedef struct -{ +typedef struct { unsigned short perc_atmid; unsigned long address; unsigned char access_id; } per_lowcore_words; -typedef struct -{ - unsigned perc_branching : 1; +typedef struct { + unsigned perc_branching : 1; unsigned perc_instruction_fetch : 1; unsigned perc_storage_alteration : 1; - unsigned perc_gpr_alt_unused : 1; + unsigned perc_gpr_alt_unused : 1; unsigned perc_store_real_address : 1; - unsigned : 3; - unsigned atmid_psw_bit_31 : 1; - unsigned atmid_validity_bit : 1; - unsigned atmid_psw_bit_32 : 1; - unsigned atmid_psw_bit_5 : 1; - unsigned atmid_psw_bit_16 : 1; - unsigned atmid_psw_bit_17 : 1; - unsigned si : 2; + unsigned : 3; + unsigned atmid_psw_bit_31 : 1; + unsigned atmid_validity_bit : 1; + unsigned atmid_psw_bit_32 : 1; + unsigned atmid_psw_bit_5 : 1; + unsigned atmid_psw_bit_16 : 1; + unsigned atmid_psw_bit_17 : 1; + unsigned si : 2; unsigned long address; - unsigned : 4; - unsigned access_id : 4; + unsigned : 4; + unsigned access_id : 4; } per_lowcore_bits; -typedef struct -{ +typedef struct { union { per_cr_words words; per_cr_bits bits; @@ -364,9 +365,9 @@ typedef struct * the kernel always sets them to zero. To enable single * stepping use ptrace(PTRACE_SINGLESTEP) instead. */ - unsigned single_step : 1; + unsigned single_step : 1; unsigned instruction_fetch : 1; - unsigned : 30; + unsigned : 30; /* * These addresses are copied into cr10 & cr11 if single * stepping is switched off @@ -376,11 +377,10 @@ typedef struct union { per_lowcore_words words; per_lowcore_bits bits; - } lowcore; + } lowcore; } per_struct; -typedef struct -{ +typedef struct { unsigned int len; unsigned long kernel_addr; unsigned long process_addr; @@ -390,12 +390,12 @@ typedef struct * S/390 specific non posix ptrace requests. I chose unusual values so * they are unlikely to clash with future ptrace definitions. */ -#define PTRACE_PEEKUSR_AREA 0x5000 -#define PTRACE_POKEUSR_AREA 0x5001 +#define PTRACE_PEEKUSR_AREA 0x5000 +#define PTRACE_POKEUSR_AREA 0x5001 #define PTRACE_PEEKTEXT_AREA 0x5002 #define PTRACE_PEEKDATA_AREA 0x5003 #define PTRACE_POKETEXT_AREA 0x5004 -#define PTRACE_POKEDATA_AREA 0x5005 +#define PTRACE_POKEDATA_AREA 0x5005 #define PTRACE_GET_LAST_BREAK 0x5006 #define PTRACE_PEEK_SYSTEM_CALL 0x5007 #define PTRACE_POKE_SYSTEM_CALL 0x5008 @@ -413,21 +413,19 @@ typedef struct * PT_PROT definition is loosely based on hppa bsd definition in * gdb/hppab-nat.c */ -#define PTRACE_PROT 21 +#define PTRACE_PROT 21 -typedef enum -{ +typedef enum { ptprot_set_access_watchpoint, ptprot_set_write_watchpoint, ptprot_disable_watchpoint } ptprot_flags; -typedef struct -{ +typedef struct { unsigned long lowaddr; unsigned long hiaddr; ptprot_flags prot; -} ptprot_area; +} ptprot_area; /* Sequence of bytes for breakpoint illegal instruction. */ #define S390_BREAKPOINT {0x0,0x1} @@ -439,8 +437,7 @@ typedef struct * The user_regs_struct defines the way the user registers are * store on the stack for signal handling. */ -struct user_regs_struct -{ +struct user_regs_struct { psw_t psw; unsigned long gprs[NUM_GPRS]; unsigned int acrs[NUM_ACRS]; diff --git a/arch/s390/include/uapi/asm/sthyi.h b/arch/s390/include/uapi/asm/sthyi.h index ec113db4eb7e..b1b022316983 100644 --- a/arch/s390/include/uapi/asm/sthyi.h +++ b/arch/s390/include/uapi/asm/sthyi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_STHYI_H #define _UAPI_ASM_STHYI_H diff --git a/arch/s390/include/uapi/asm/virtio-ccw.h b/arch/s390/include/uapi/asm/virtio-ccw.h index 3a77833c74dc..2b605f7e8483 100644 --- a/arch/s390/include/uapi/asm/virtio-ccw.h +++ b/arch/s390/include/uapi/asm/virtio-ccw.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * Definitions for virtio-ccw devices. * diff --git a/arch/s390/include/uapi/asm/vmcp.h b/arch/s390/include/uapi/asm/vmcp.h index 4caf71714a55..aeaaa030030e 100644 --- a/arch/s390/include/uapi/asm/vmcp.h +++ b/arch/s390/include/uapi/asm/vmcp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright IBM Corp. 2004, 2005 * Interface implementation for communication with the z/VM control program diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c index 315986a06cf5..574e77622c04 100644 --- a/arch/s390/kernel/alternative.c +++ b/arch/s390/kernel/alternative.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> #include <asm/alternative.h> #include <asm/facility.h> diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index f04db3779b34..59eea9c65d3e 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -263,6 +263,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplis return retval; } + groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c index f8603ebed669..54e2d634b849 100644 --- a/arch/s390/kernel/perf_regs.c +++ b/arch/s390/kernel/perf_regs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/perf_event.h> #include <linux/perf_regs.h> #include <linux/kernel.h> diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 308a7b63348b..f7fc63385553 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -370,10 +370,10 @@ SYSCALL(sys_recvmmsg,compat_sys_recvmmsg) SYSCALL(sys_sendmmsg,compat_sys_sendmmsg) SYSCALL(sys_socket,sys_socket) SYSCALL(sys_socketpair,compat_sys_socketpair) /* 360 */ -SYSCALL(sys_bind,sys_bind) -SYSCALL(sys_connect,sys_connect) +SYSCALL(sys_bind,compat_sys_bind) +SYSCALL(sys_connect,compat_sys_connect) SYSCALL(sys_listen,sys_listen) -SYSCALL(sys_accept4,sys_accept4) +SYSCALL(sys_accept4,compat_sys_accept4) SYSCALL(sys_getsockopt,compat_sys_getsockopt) /* 365 */ SYSCALL(sys_setsockopt,compat_sys_setsockopt) SYSCALL(sys_getsockname,compat_sys_getsockname) diff --git a/arch/s390/kernel/vdso64/note.S b/arch/s390/kernel/vdso64/note.S index 79a071e4357e..db19d0680a0a 100644 --- a/arch/s390/kernel/vdso64/note.S +++ b/arch/s390/kernel/vdso64/note.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. * Here we can supply some information useful to userland. diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 6048b1c6e580..05ee90a5ea08 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -1,10 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 # Makefile for kernel virtual machines on s390 # # Copyright IBM Corp. 2008 -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License (version 2 only) -# as published by the Free Software Foundation. KVM := ../../../virt/kvm common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index d93a2c0474bf..89aa114a2cba 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * handling diagnose instructions * * Copyright IBM Corp. 2008, 2011 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> */ diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index bec42b852246..f4c51756c462 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * access guest memory * * Copyright IBM Corp. 2008, 2014 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): Carsten Otte <cotte@de.ibm.com> */ diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index bcbd86621d01..b5f3e82006d0 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kvm guest debug support * * Copyright IBM Corp. 2014 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): David Hildenbrand <dahi@linux.vnet.ibm.com> */ #include <linux/kvm_host.h> diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 8fe034beb623..9c7d70715862 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * in-kernel handling for sie intercepts * * Copyright IBM Corp. 2008, 2014 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index fa557372d600..024ad8bcc516 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * handling kvm guest interrupts * * Copyright IBM Corp. 2008, 2015 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): Carsten Otte <cotte@de.ibm.com> */ diff --git a/arch/s390/kvm/irq.h b/arch/s390/kvm/irq.h index d98e4159643d..484608c71dd0 100644 --- a/arch/s390/kvm/irq.h +++ b/arch/s390/kvm/irq.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * s390 irqchip routines * * Copyright IBM Corp. 2014 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com> */ #ifndef __KVM_IRQ_H diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 9614aea5839b..ec8b68e97d3c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * hosting zSeries kernel virtual machines + * hosting IBM Z kernel virtual machines (s390x) * - * Copyright IBM Corp. 2008, 2009 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. + * Copyright IBM Corp. 2008, 2017 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -3808,6 +3805,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; break; } + /* do not use irq_state.flags, it will break old QEMUs */ r = kvm_s390_set_irq_state(vcpu, (void __user *) irq_state.buf, irq_state.len); @@ -3823,6 +3821,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; break; } + /* do not use irq_state.flags, it will break old QEMUs */ r = kvm_s390_get_irq_state(vcpu, (__u8 __user *) irq_state.buf, irq_state.len); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 10d65dfbc306..5e46ba429bcb 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * definition for kvm on s390 * * Copyright IBM Corp. 2008, 2009 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> * Christian Ehrhardt <ehrhardt@de.ibm.com> diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index c954ac49eee4..572496c688cc 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * handling privileged instructions * * Copyright IBM Corp. 2008, 2013 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> */ @@ -235,8 +232,6 @@ static int try_handle_skey(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation"); return -EAGAIN; } - if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); return 0; } @@ -247,6 +242,9 @@ static int handle_iske(struct kvm_vcpu *vcpu) int reg1, reg2; int rc; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + rc = try_handle_skey(vcpu); if (rc) return rc != -EAGAIN ? rc : 0; @@ -276,6 +274,9 @@ static int handle_rrbe(struct kvm_vcpu *vcpu) int reg1, reg2; int rc; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + rc = try_handle_skey(vcpu); if (rc) return rc != -EAGAIN ? rc : 0; @@ -311,6 +312,9 @@ static int handle_sske(struct kvm_vcpu *vcpu) int reg1, reg2; int rc; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + rc = try_handle_skey(vcpu); if (rc) return rc != -EAGAIN ? rc : 0; diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 9d592ef4104b..c1f5cde2c878 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * handling interprocessor communication * * Copyright IBM Corp. 2008, 2013 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> * Christian Ehrhardt <ehrhardt@de.ibm.com> diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index a311938b63b3..5d6ae0326d9e 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kvm nested virtualization support for s390x * * Copyright IBM Corp. 2016 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): David Hildenbrand <dahi@linux.vnet.ibm.com> */ #include <linux/vmalloc.h> diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 434a9564917b..cb364153c43c 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -83,8 +83,6 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end) /* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */ VM_BUG_ON(mm->context.asce_limit < _REGION2_SIZE); - if (end >= TASK_SIZE_MAX) - return -ENOMEM; rc = 0; notify = 0; while (mm->context.asce_limit < end) { diff --git a/arch/s390/net/Makefile b/arch/s390/net/Makefile index 90568c33ddb0..e0d5f245e42b 100644 --- a/arch/s390/net/Makefile +++ b/arch/s390/net/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Arch-specific network modules # diff --git a/arch/s390/numa/Makefile b/arch/s390/numa/Makefile index f94ecaffa71b..66c2dff74895 100644 --- a/arch/s390/numa/Makefile +++ b/arch/s390/numa/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-y += numa.o obj-y += toptree.o obj-$(CONFIG_NUMA_EMU) += mode_emu.o diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index 805d8b29193a..22d0871291ee 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the s390 PCI subsystem. # diff --git a/arch/s390/tools/gen_opcode_table.c b/arch/s390/tools/gen_opcode_table.c index 01d4c5a4bfe9..357d42681cef 100644 --- a/arch/s390/tools/gen_opcode_table.c +++ b/arch/s390/tools/gen_opcode_table.c @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Generate opcode table initializers for the in-kernel disassembler. * diff --git a/arch/score/include/uapi/asm/Kbuild b/arch/score/include/uapi/asm/Kbuild index c94ee54210bc..81271d3af47c 100644 --- a/arch/score/include/uapi/asm/Kbuild +++ b/arch/score/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += siginfo.h diff --git a/arch/sh/include/uapi/asm/Kbuild b/arch/sh/include/uapi/asm/Kbuild index e28531333efa..ba4d39cb321d 100644 --- a/arch/sh/include/uapi/asm/Kbuild +++ b/arch/sh/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild index 2178c78c7c1a..4680ba246b55 100644 --- a/arch/sparc/include/uapi/asm/Kbuild +++ b/arch/sparc/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += types.h diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index be3136f142a9..a8103a84b4ac 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -113,7 +113,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->pc, (void *)regs->u_regs[UREG_I7], diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 815c03d7a765..41363f46797b 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -154,7 +154,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->tpc, (void *)regs->u_regs[UREG_I7], diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index 33c0f8bb0f33..5335ba3c850e 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -75,7 +75,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, if (!(pmd_val(pmd) & _PAGE_VALID)) return 0; - if (!pmd_access_permitted(pmd, write)) + if (write && !pmd_write(pmd)) return 0; refs = 0; @@ -114,7 +114,7 @@ static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr, if (!(pud_val(pud) & _PAGE_VALID)) return 0; - if (!pud_access_permitted(pud, write)) + if (write && !pud_write(pud)) return 0; refs = 0; diff --git a/arch/tile/include/uapi/asm/Kbuild b/arch/tile/include/uapi/asm/Kbuild index 5711de0a1b5e..cc439612bcd5 100644 --- a/arch/tile/include/uapi/asm/Kbuild +++ b/arch/tile/include/uapi/asm/Kbuild @@ -1,6 +1,7 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index 50a32c33d729..73c57f614c9e 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -1,4 +1,5 @@ generic-y += barrier.h +generic-y += bpf_perf_event.h generic-y += bug.h generic-y += clkdev.h generic-y += current.h diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 4e6fcb32620f..428644175956 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -150,7 +150,7 @@ static void show_segv_info(struct uml_pt_regs *regs) if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi), (void *)UPT_IP(regs), (void *)UPT_SP(regs), diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild index 759a71411169..8611ef980554 100644 --- a/arch/unicore32/include/uapi/asm/Kbuild +++ b/arch/unicore32/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 6293a8768a91..672441c008c7 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -400,6 +400,7 @@ config UNWINDER_FRAME_POINTER config UNWINDER_GUESS bool "Guess unwinder" depends on EXPERT + depends on !STACKDEPOT ---help--- This option enables the "guess" unwinder for unwinding kernel stack traces. It scans the stack and reports every kernel text address it diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 1e9c322e973a..f25e1530e064 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -80,6 +80,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o vmlinux-objs-y += $(obj)/mem_encrypt.o + vmlinux-objs-y += $(obj)/pgtable_64.o endif $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 20919b4f3133..fc313e29fe2c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -305,10 +305,18 @@ ENTRY(startup_64) leaq boot_stack_end(%rbx), %rsp #ifdef CONFIG_X86_5LEVEL - /* Check if 5-level paging has already enabled */ - movq %cr4, %rax - testl $X86_CR4_LA57, %eax - jnz lvl5 + /* + * Check if we need to enable 5-level paging. + * RSI holds real mode data and need to be preserved across + * a function call. + */ + pushq %rsi + call l5_paging_required + popq %rsi + + /* If l5_paging_required() returned zero, we're done here. */ + cmpq $0, %rax + je lvl5 /* * At this point we are in long mode with 4-level paging enabled, diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index b50c42455e25..98761a1576ce 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -169,6 +169,16 @@ void __puthex(unsigned long value) } } +static bool l5_supported(void) +{ + /* Check if leaf 7 is supported. */ + if (native_cpuid_eax(0) < 7) + return 0; + + /* Check if la57 is supported. */ + return native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)); +} + #if CONFIG_X86_NEED_RELOCS static void handle_relocations(void *output, unsigned long output_len, unsigned long virt_addr) @@ -362,6 +372,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, console_init(); debug_putstr("early console in extract_kernel\n"); + if (IS_ENABLED(CONFIG_X86_5LEVEL) && !l5_supported()) { + error("This linux kernel as configured requires 5-level paging\n" + "This CPU does not support the required 'cr4.la57' feature\n" + "Unable to boot - please use a kernel appropriate for your CPU\n"); + } + free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c new file mode 100644 index 000000000000..b4469a37e9a1 --- /dev/null +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -0,0 +1,28 @@ +#include <asm/processor.h> + +/* + * __force_order is used by special_insns.h asm code to force instruction + * serialization. + * + * It is not referenced from the code, but GCC < 5 with -fPIE would fail + * due to an undefined symbol. Define it to make these ancient GCCs work. + */ +unsigned long __force_order; + +int l5_paging_required(void) +{ + /* Check if leaf 7 is supported. */ + + if (native_cpuid_eax(0) < 7) + return 0; + + /* Check if la57 is supported. */ + if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) + return 0; + + /* Check if 5-level paging has already been enabled. */ + if (native_read_cr4() & X86_CR4_LA57) + return 0; + + return 1; +} diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh index 49f4970f693b..c9e8499fbfe7 100644 --- a/arch/x86/boot/genimage.sh +++ b/arch/x86/boot/genimage.sh @@ -44,9 +44,9 @@ FDINITRD=$6 # Make sure the files actually exist verify "$FBZIMAGE" -verify "$MTOOLSRC" genbzdisk() { + verify "$MTOOLSRC" mformat a: syslinux $FIMAGE echo "$KCMDLINE" | mcopy - a:syslinux.cfg @@ -57,6 +57,7 @@ genbzdisk() { } genfdimage144() { + verify "$MTOOLSRC" dd if=/dev/zero of=$FIMAGE bs=1024 count=1440 2> /dev/null mformat v: syslinux $FIMAGE @@ -68,6 +69,7 @@ genfdimage144() { } genfdimage288() { + verify "$MTOOLSRC" dd if=/dev/zero of=$FIMAGE bs=1024 count=2880 2> /dev/null mformat w: syslinux $FIMAGE diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c index 399a29d067d6..cb91a64a99e7 100644 --- a/arch/x86/crypto/salsa20_glue.c +++ b/arch/x86/crypto/salsa20_glue.c @@ -59,13 +59,6 @@ static int encrypt(struct blkcipher_desc *desc, salsa20_ivsetup(ctx, walk.iv); - if (likely(walk.nbytes == nbytes)) - { - salsa20_encrypt_bytes(ctx, walk.src.virt.addr, - walk.dst.virt.addr, nbytes); - return blkcipher_walk_done(desc, &walk, 0); - } - while (walk.nbytes >= 64) { salsa20_encrypt_bytes(ctx, walk.src.virt.addr, walk.dst.virt.addr, diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 4838037f97f6..bd8b57a5c874 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -941,7 +941,8 @@ ENTRY(debug) movl %esp, %eax # pt_regs pointer /* Are we currently on the SYSENTER stack? */ - PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx) + movl PER_CPU_VAR(cpu_entry_area), %ecx + addl $CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ cmpl $SIZEOF_SYSENTER_stack, %ecx jb .Ldebug_from_sysenter_stack @@ -984,7 +985,8 @@ ENTRY(nmi) movl %esp, %eax # pt_regs pointer /* Are we currently on the SYSENTER stack? */ - PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx) + movl PER_CPU_VAR(cpu_entry_area), %ecx + addl $CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ cmpl $SIZEOF_SYSENTER_stack, %ecx jb .Lnmi_from_sysenter_stack diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f81d50d7ceac..423885bee398 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -140,6 +140,64 @@ END(native_usergs_sysret64) * with them due to bugs in both AMD and Intel CPUs. */ + .pushsection .entry_trampoline, "ax" + +/* + * The code in here gets remapped into cpu_entry_area's trampoline. This means + * that the assembler and linker have the wrong idea as to where this code + * lives (and, in fact, it's mapped more than once, so it's not even at a + * fixed address). So we can't reference any symbols outside the entry + * trampoline and expect it to work. + * + * Instead, we carefully abuse %rip-relative addressing. + * _entry_trampoline(%rip) refers to the start of the remapped) entry + * trampoline. We can thus find cpu_entry_area with this macro: + */ + +#define CPU_ENTRY_AREA \ + _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip) + +/* The top word of the SYSENTER stack is hot and is usable as scratch space. */ +#define RSP_SCRATCH CPU_ENTRY_AREA_SYSENTER_stack + \ + SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA + +ENTRY(entry_SYSCALL_64_trampoline) + UNWIND_HINT_EMPTY + swapgs + + /* Stash the user RSP. */ + movq %rsp, RSP_SCRATCH + + /* Load the top of the task stack into RSP */ + movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp + + /* Start building the simulated IRET frame. */ + pushq $__USER_DS /* pt_regs->ss */ + pushq RSP_SCRATCH /* pt_regs->sp */ + pushq %r11 /* pt_regs->flags */ + pushq $__USER_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ + + /* + * x86 lacks a near absolute jump, and we can't jump to the real + * entry text with a relative jump. We could push the target + * address and then use retq, but this destroys the pipeline on + * many CPUs (wasting over 20 cycles on Sandy Bridge). Instead, + * spill RDI and restore it in a second-stage trampoline. + */ + pushq %rdi + movq $entry_SYSCALL_64_stage2, %rdi + jmp *%rdi +END(entry_SYSCALL_64_trampoline) + + .popsection + +ENTRY(entry_SYSCALL_64_stage2) + UNWIND_HINT_EMPTY + popq %rdi + jmp entry_SYSCALL_64_after_hwframe +END(entry_SYSCALL_64_stage2) + ENTRY(entry_SYSCALL_64) UNWIND_HINT_EMPTY /* @@ -330,8 +388,24 @@ syscall_return_via_sysret: popq %rsi /* skip rcx */ popq %rdx popq %rsi + + /* + * Now all regs are restored except RSP and RDI. + * Save old stack pointer and switch to trampoline stack. + */ + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + + pushq RSP-RDI(%rdi) /* RSP */ + pushq (%rdi) /* RDI */ + + /* + * We are on the trampoline stack. All regs except RDI are live. + * We can do future final exit work right here. + */ + popq %rdi - movq RSP-ORIG_RAX(%rsp), %rsp + popq %rsp USERGS_SYSRET64 END(entry_SYSCALL_64) @@ -466,12 +540,13 @@ END(irq_entries_start) .macro DEBUG_ENTRY_ASSERT_IRQS_OFF #ifdef CONFIG_DEBUG_ENTRY - pushfq - testl $X86_EFLAGS_IF, (%rsp) + pushq %rax + SAVE_FLAGS(CLBR_RAX) + testl $X86_EFLAGS_IF, %eax jz .Lokay_\@ ud2 .Lokay_\@: - addq $8, %rsp + popq %rax #endif .endm @@ -563,6 +638,13 @@ END(irq_entries_start) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func cld + + testb $3, CS-ORIG_RAX(%rsp) + jz 1f + SWAPGS + call switch_to_thread_stack +1: + ALLOC_PT_GPREGS_ON_STACK SAVE_C_REGS SAVE_EXTRA_REGS @@ -572,12 +654,8 @@ END(irq_entries_start) jz 1f /* - * IRQ from user mode. Switch to kernel gsbase and inform context - * tracking that we're in kernel mode. - */ - SWAPGS - - /* + * IRQ from user mode. + * * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode * (which can take locks). Since TRACE_IRQS_OFF idempotent, @@ -630,10 +708,41 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) ud2 1: #endif - SWAPGS POP_EXTRA_REGS - POP_C_REGS - addq $8, %rsp /* skip regs->orig_ax */ + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + + /* + * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. + * Save old stack pointer and switch to trampoline stack. + */ + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + + /* Copy the IRET frame to the trampoline stack. */ + pushq 6*8(%rdi) /* SS */ + pushq 5*8(%rdi) /* RSP */ + pushq 4*8(%rdi) /* EFLAGS */ + pushq 3*8(%rdi) /* CS */ + pushq 2*8(%rdi) /* RIP */ + + /* Push user RDI on the trampoline stack. */ + pushq (%rdi) + + /* + * We are on the trampoline stack. All regs except RDI are live. + * We can do future final exit work right here. + */ + + /* Restore RDI. */ + popq %rdi + SWAPGS INTERRUPT_RETURN @@ -829,7 +938,33 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt /* * Exception entry points. */ -#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8) +#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) + +/* + * Switch to the thread stack. This is called with the IRET frame and + * orig_ax on the stack. (That is, RDI..R12 are not on the stack and + * space has not been allocated for them.) + */ +ENTRY(switch_to_thread_stack) + UNWIND_HINT_FUNC + + pushq %rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI + + pushq 7*8(%rdi) /* regs->ss */ + pushq 6*8(%rdi) /* regs->rsp */ + pushq 5*8(%rdi) /* regs->eflags */ + pushq 4*8(%rdi) /* regs->cs */ + pushq 3*8(%rdi) /* regs->ip */ + pushq 2*8(%rdi) /* regs->orig_ax */ + pushq 8(%rdi) /* return address */ + UNWIND_HINT_FUNC + + movq (%rdi), %rdi + ret +END(switch_to_thread_stack) .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) @@ -848,11 +983,12 @@ ENTRY(\sym) ALLOC_PT_GPREGS_ON_STACK - .if \paranoid - .if \paranoid == 1 + .if \paranoid < 2 testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ - jnz 1f + jnz .Lfrom_usermode_switch_stack_\@ .endif + + .if \paranoid call paranoid_entry .else call error_entry @@ -894,20 +1030,15 @@ ENTRY(\sym) jmp error_exit .endif - .if \paranoid == 1 + .if \paranoid < 2 /* - * Paranoid entry from userspace. Switch stacks and treat it + * Entry from userspace. Switch stacks and treat it * as a normal entry. This means that paranoid handlers * run in real process context if user_mode(regs). */ -1: +.Lfrom_usermode_switch_stack_\@: call error_entry - - movq %rsp, %rdi /* pt_regs pointer */ - call sync_regs - movq %rax, %rsp /* switch stack */ - movq %rsp, %rdi /* pt_regs pointer */ .if \has_error_code @@ -1170,6 +1301,14 @@ ENTRY(error_entry) SWAPGS .Lerror_entry_from_usermode_after_swapgs: + /* Put us onto the real thread stack. */ + popq %r12 /* save return addr in %12 */ + movq %rsp, %rdi /* arg0 = pt_regs pointer */ + call sync_regs + movq %rax, %rsp /* switch stack */ + ENCODE_FRAME_POINTER + pushq %r12 + /* * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 568e130d932c..95ad40eb7eff 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -48,7 +48,7 @@ */ ENTRY(entry_SYSENTER_compat) /* Interrupts are off on entry. */ - SWAPGS_UNSAFE_STACK + SWAPGS movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* @@ -306,8 +306,11 @@ ENTRY(entry_INT80_compat) */ movl %eax, %eax - /* Construct struct pt_regs on stack (iret frame is already on stack) */ pushq %rax /* pt_regs->orig_ax */ + + /* switch to thread stack expects orig_ax to be pushed */ + call switch_to_thread_stack + pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 11b13c4b43d5..f19856d95c60 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -324,5 +324,5 @@ notrace time_t __vdso_time(time_t *t) *t = result; return result; } -int time(time_t *t) +time_t time(time_t *t) __attribute__((weak, alias("__vdso_time"))); diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index bf6a76202a77..ea9a7dde62e5 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -135,6 +135,8 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) +#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) + #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS) /* * Static testing of CPU features. Used the same as boot_cpu_has(). diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index c0b0e9e8aa66..800104c8a3ed 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -266,6 +266,7 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ +#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 4011cb03ef08..aab4fe9f49f8 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -60,17 +60,10 @@ static inline struct desc_struct *get_current_gdt_rw(void) return this_cpu_ptr(&gdt_page)->gdt; } -/* Get the fixmap index for a specific processor */ -static inline unsigned int get_cpu_gdt_ro_index(int cpu) -{ - return FIX_GDT_REMAP_BEGIN + cpu; -} - /* Provide the fixmap address of the remapped GDT */ static inline struct desc_struct *get_cpu_gdt_ro(int cpu) { - unsigned int idx = get_cpu_gdt_ro_index(cpu); - return (struct desc_struct *)__fix_to_virt(idx); + return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt; } /* Provide the current read-only GDT */ @@ -185,7 +178,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr, #endif } -static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr) +static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr) { struct desc_struct *d = get_cpu_gdt_rw(cpu); tss_desc tss; diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index b0c505fe9a95..94fc4fa14127 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -44,6 +44,45 @@ extern unsigned long __FIXADDR_TOP; PAGE_SIZE) #endif +/* + * cpu_entry_area is a percpu region in the fixmap that contains things + * needed by the CPU and early entry/exit code. Real types aren't used + * for all fields here to avoid circular header dependencies. + * + * Every field is a virtual alias of some other allocated backing store. + * There is no direct allocation of a struct cpu_entry_area. + */ +struct cpu_entry_area { + char gdt[PAGE_SIZE]; + + /* + * The GDT is just below SYSENTER_stack and thus serves (on x86_64) as + * a a read-only guard page. + */ + struct SYSENTER_stack_page SYSENTER_stack_page; + + /* + * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because + * we need task switches to work, and task switches write to the TSS. + */ + struct tss_struct tss; + + char entry_trampoline[PAGE_SIZE]; + +#ifdef CONFIG_X86_64 + /* + * Exception stacks used for IST entries. + * + * In the future, this should have a separate slot for each stack + * with guard pages between them. + */ + char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]; +#endif +}; + +#define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE) + +extern void setup_cpu_entry_areas(void); /* * Here we define all the compile-time 'special' virtual @@ -101,8 +140,8 @@ enum fixed_addresses { FIX_LNW_VRTC, #endif /* Fixmap entries to remap the GDTs, one per processor. */ - FIX_GDT_REMAP_BEGIN, - FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, + FIX_CPU_ENTRY_AREA_TOP, + FIX_CPU_ENTRY_AREA_BOTTOM = FIX_CPU_ENTRY_AREA_TOP + (CPU_ENTRY_AREA_PAGES * NR_CPUS) - 1, #ifdef CONFIG_ACPI_APEI_GHES /* Used for GHES mapping from assorted contexts */ @@ -191,5 +230,30 @@ void __init *early_memremap_decrypted_wp(resource_size_t phys_addr, void __early_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags); +static inline unsigned int __get_cpu_entry_area_page_index(int cpu, int page) +{ + BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0); + + return FIX_CPU_ENTRY_AREA_BOTTOM - cpu*CPU_ENTRY_AREA_PAGES - page; +} + +#define __get_cpu_entry_area_offset_index(cpu, offset) ({ \ + BUILD_BUG_ON(offset % PAGE_SIZE != 0); \ + __get_cpu_entry_area_page_index(cpu, offset / PAGE_SIZE); \ + }) + +#define get_cpu_entry_area_index(cpu, field) \ + __get_cpu_entry_area_offset_index((cpu), offsetof(struct cpu_entry_area, field)) + +static inline struct cpu_entry_area *get_cpu_entry_area(int cpu) +{ + return (struct cpu_entry_area *)__fix_to_virt(__get_cpu_entry_area_page_index(cpu, 0)); +} + +static inline struct SYSENTER_stack *cpu_SYSENTER_stack(int cpu) +{ + return &get_cpu_entry_area(cpu)->SYSENTER_stack_page.stack; +} + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_FIXMAP_H */ diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 1b0a5abcd8ae..96aa6b9884dc 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -20,16 +20,7 @@ #ifndef _ASM_X86_HYPERVISOR_H #define _ASM_X86_HYPERVISOR_H -#ifdef CONFIG_HYPERVISOR_GUEST - -#include <asm/kvm_para.h> -#include <asm/x86_init.h> -#include <asm/xen/hypervisor.h> - -/* - * x86 hypervisor information - */ - +/* x86 hypervisor types */ enum x86_hypervisor_type { X86_HYPER_NATIVE = 0, X86_HYPER_VMWARE, @@ -39,6 +30,12 @@ enum x86_hypervisor_type { X86_HYPER_KVM, }; +#ifdef CONFIG_HYPERVISOR_GUEST + +#include <asm/kvm_para.h> +#include <asm/x86_init.h> +#include <asm/xen/hypervisor.h> + struct hypervisor_x86 { /* Hypervisor name */ const char *name; @@ -58,7 +55,15 @@ struct hypervisor_x86 { extern enum x86_hypervisor_type x86_hyper_type; extern void init_hypervisor_platform(void); +static inline bool hypervisor_is_type(enum x86_hypervisor_type type) +{ + return x86_hyper_type == type; +} #else static inline void init_hypervisor_platform(void) { } +static inline bool hypervisor_is_type(enum x86_hypervisor_type type) +{ + return type == X86_HYPER_NATIVE; +} #endif /* CONFIG_HYPERVISOR_GUEST */ #endif /* _ASM_X86_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index c8ef23f2c28f..89f08955fff7 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -142,6 +142,9 @@ static inline notrace unsigned long arch_local_irq_save(void) swapgs; \ sysretl +#ifdef CONFIG_DEBUG_ENTRY +#define SAVE_FLAGS(x) pushfq; popq %rax +#endif #else #define INTERRUPT_RETURN iret #define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index f86a8caa561e..395c9631e000 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_stack_regs(struct pt_regs *regs); extern void __show_regs(struct pt_regs *regs, int all); +extern void show_iret_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/include/asm/kmemcheck.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 034caa1a084e..b24b1c8b3979 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -214,8 +214,6 @@ struct x86_emulate_ops { void (*halt)(struct x86_emulate_ctxt *ctxt); void (*wbinvd)(struct x86_emulate_ctxt *ctxt); int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt); - void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */ - void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */ int (*intercept)(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 977de5fb968b..516798431328 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -536,7 +536,20 @@ struct kvm_vcpu_arch { struct kvm_mmu_memory_cache mmu_page_cache; struct kvm_mmu_memory_cache mmu_page_header_cache; + /* + * QEMU userspace and the guest each have their own FPU state. + * In vcpu_run, we switch between the user and guest FPU contexts. + * While running a VCPU, the VCPU thread will have the guest FPU + * context. + * + * Note that while the PKRU state lives inside the fpu registers, + * it is switched out separately at VMENTER and VMEXIT time. The + * "guest_fpu" state here contains the guest FPU context, with the + * host PRKU bits. + */ + struct fpu user_fpu; struct fpu guest_fpu; + u64 xcr0; u64 guest_supported_xcr0; u32 guest_xstate_size; @@ -1435,4 +1448,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define put_smstate(type, buf, offset, val) \ *(type *)((buf) + (offset) - 0x7e00) = val +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 283efcaac8af..892df375b615 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -927,6 +927,15 @@ extern void default_banner(void); PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64)) + +#ifdef CONFIG_DEBUG_ENTRY +#define SAVE_FLAGS(clobbers) \ + PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \ + PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \ + PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) +#endif + #endif /* CONFIG_X86_32 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index cc16fa882e3e..1f2434ee9f80 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -163,9 +163,9 @@ enum cpuid_regs_idx { extern struct cpuinfo_x86 boot_cpu_data; extern struct cpuinfo_x86 new_cpu_data; -extern struct tss_struct doublefault_tss; -extern __u32 cpu_caps_cleared[NCAPINTS]; -extern __u32 cpu_caps_set[NCAPINTS]; +extern struct x86_hw_tss doublefault_tss; +extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS]; #ifdef CONFIG_SMP DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); @@ -253,6 +253,11 @@ static inline void load_cr3(pgd_t *pgdir) write_cr3(__sme_pa(pgdir)); } +/* + * Note that while the legacy 'TSS' name comes from 'Task State Segment', + * on modern x86 CPUs the TSS also holds information important to 64-bit mode, + * unrelated to the task-switch mechanism: + */ #ifdef CONFIG_X86_32 /* This is the TSS defined by the hardware. */ struct x86_hw_tss { @@ -305,7 +310,13 @@ struct x86_hw_tss { struct x86_hw_tss { u32 reserved1; u64 sp0; + + /* + * We store cpu_current_top_of_stack in sp1 so it's always accessible. + * Linux does not use ring 1, so sp1 is not otherwise needed. + */ u64 sp1; + u64 sp2; u64 reserved2; u64 ist[7]; @@ -323,12 +334,22 @@ struct x86_hw_tss { #define IO_BITMAP_BITS 65536 #define IO_BITMAP_BYTES (IO_BITMAP_BITS/8) #define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) -#define IO_BITMAP_OFFSET offsetof(struct tss_struct, io_bitmap) +#define IO_BITMAP_OFFSET (offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss)) #define INVALID_IO_BITMAP_OFFSET 0x8000 +struct SYSENTER_stack { + unsigned long words[64]; +}; + +struct SYSENTER_stack_page { + struct SYSENTER_stack stack; +} __aligned(PAGE_SIZE); + struct tss_struct { /* - * The hardware state: + * The fixed hardware portion. This must not cross a page boundary + * at risk of violating the SDM's advice and potentially triggering + * errata. */ struct x86_hw_tss x86_tss; @@ -339,18 +360,9 @@ struct tss_struct { * be within the limit. */ unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; +} __aligned(PAGE_SIZE); -#ifdef CONFIG_X86_32 - /* - * Space for the temporary SYSENTER stack. - */ - unsigned long SYSENTER_stack_canary; - unsigned long SYSENTER_stack[64]; -#endif - -} ____cacheline_aligned; - -DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); +DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw); /* * sizeof(unsigned long) coming from an extra "long" at the end @@ -364,6 +376,9 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); +#else +/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */ +#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1 #endif /* @@ -523,7 +538,7 @@ static inline void native_set_iopl_mask(unsigned mask) static inline void native_load_sp0(unsigned long sp0) { - this_cpu_write(cpu_tss.x86_tss.sp0, sp0); + this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } static inline void native_swapgs(void) @@ -535,12 +550,12 @@ static inline void native_swapgs(void) static inline unsigned long current_top_of_stack(void) { -#ifdef CONFIG_X86_64 - return this_cpu_read_stable(cpu_tss.x86_tss.sp0); -#else - /* sp0 on x86_32 is special in and around vm86 mode. */ + /* + * We can't read directly from tss.sp0: sp0 on x86_32 is special in + * and around vm86 mode and sp0 on x86_64 is special because of the + * entry trampoline. + */ return this_cpu_read_stable(cpu_current_top_of_stack); -#endif } static inline bool on_thread_stack(void) diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index b20f9d623f9c..8f09012b92e7 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -236,11 +236,23 @@ */ #define EARLY_IDT_HANDLER_SIZE 9 +/* + * xen_early_idt_handler_array is for Xen pv guests: for each entry in + * early_idt_handler_array it contains a prequel in the form of + * pop %rcx; pop %r11; jmp early_idt_handler_array[i]; summing up to + * max 8 bytes. + */ +#define XEN_EARLY_IDT_HANDLER_SIZE 8 + #ifndef __ASSEMBLY__ extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE]; extern void early_ignore_irq(void); +#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) +extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE]; +#endif + /* * Load a segment. Fall back on loading the zero segment if something goes * wrong. This variant assumes that loading zero fully clears the segment. diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 8da111b3c342..f8062bfd43a0 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -16,6 +16,7 @@ enum stack_type { STACK_TYPE_TASK, STACK_TYPE_IRQ, STACK_TYPE_SOFTIRQ, + STACK_TYPE_SYSENTER, STACK_TYPE_EXCEPTION, STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, }; @@ -28,6 +29,8 @@ struct stack_info { bool in_task_stack(unsigned long *stack, struct task_struct *task, struct stack_info *info); +bool in_sysenter_stack(unsigned long *stack, struct stack_info *info); + int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask); diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 982c325dad33..8be6afb58471 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -12,7 +12,13 @@ /* image of the saved processor state */ struct saved_context { - u16 es, fs, gs, ss; + /* + * On x86_32, all segment registers, with the possible exception of + * gs, are saved at kernel entry in pt_regs. + */ +#ifdef CONFIG_X86_32_LAZY_GS + u16 gs; +#endif unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; bool misc_enable_saved; diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 7306e911faee..a7af9f53c0cb 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -20,8 +20,20 @@ */ struct saved_context { struct pt_regs regs; - u16 ds, es, fs, gs, ss; - unsigned long gs_base, gs_kernel_base, fs_base; + + /* + * User CS and SS are saved in current_pt_regs(). The rest of the + * segment selectors need to be saved and restored here. + */ + u16 ds, es, fs, gs; + + /* + * Usermode FSBASE and GSBASE may not match the fs and gs selectors, + * so we save them separately. We save the kernelmode GSBASE to + * restore percpu access after resume. + */ + unsigned long kernelmode_gs_base, usermode_gs_base, fs_base; + unsigned long cr0, cr2, cr3, cr4, cr8; u64 misc_enable; bool misc_enable_saved; @@ -30,8 +42,7 @@ struct saved_context { u16 gdt_pad; /* Unused */ struct desc_ptr gdt_desc; u16 idt_pad; - u16 idt_limit; - unsigned long idt_base; + struct desc_ptr idt; u16 ldt; u16 tss; unsigned long tr; diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 8c6bd6863db9..9b6df68d8fd1 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -79,10 +79,10 @@ do { \ static inline void refresh_sysenter_cs(struct thread_struct *thread) { /* Only happens when SEP is enabled, no need to test "SEP"arately: */ - if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs)) + if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs)) return; - this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs); + this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs); wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); } #endif @@ -90,10 +90,12 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread) /* This is used when switching tasks or entering/exiting vm86 mode. */ static inline void update_sp0(struct task_struct *task) { + /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */ #ifdef CONFIG_X86_32 load_sp0(task->thread.sp0); #else - load_sp0(task_top_of_stack(task)); + if (static_cpu_has(X86_FEATURE_XENPV)) + load_sp0(task_top_of_stack(task)); #endif } diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 70f425947dc5..00223333821a 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -207,7 +207,7 @@ static inline int arch_within_stack_frames(const void * const stack, #else /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_64 -# define cpu_current_top_of_stack (cpu_tss + TSS_sp0) +# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1) #endif #endif diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 509046cfa5ce..877b5c1a1b12 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -173,40 +173,43 @@ static inline void cr4_init_shadow(void) this_cpu_write(cpu_tlbstate.cr4, __read_cr4()); } +static inline void __cr4_set(unsigned long cr4) +{ + lockdep_assert_irqs_disabled(); + this_cpu_write(cpu_tlbstate.cr4, cr4); + __write_cr4(cr4); +} + /* Set in this cpu's CR4. */ static inline void cr4_set_bits(unsigned long mask) { - unsigned long cr4; + unsigned long cr4, flags; + local_irq_save(flags); cr4 = this_cpu_read(cpu_tlbstate.cr4); - if ((cr4 | mask) != cr4) { - cr4 |= mask; - this_cpu_write(cpu_tlbstate.cr4, cr4); - __write_cr4(cr4); - } + if ((cr4 | mask) != cr4) + __cr4_set(cr4 | mask); + local_irq_restore(flags); } /* Clear in this cpu's CR4. */ static inline void cr4_clear_bits(unsigned long mask) { - unsigned long cr4; + unsigned long cr4, flags; + local_irq_save(flags); cr4 = this_cpu_read(cpu_tlbstate.cr4); - if ((cr4 & ~mask) != cr4) { - cr4 &= ~mask; - this_cpu_write(cpu_tlbstate.cr4, cr4); - __write_cr4(cr4); - } + if ((cr4 & ~mask) != cr4) + __cr4_set(cr4 & ~mask); + local_irq_restore(flags); } -static inline void cr4_toggle_bits(unsigned long mask) +static inline void cr4_toggle_bits_irqsoff(unsigned long mask) { unsigned long cr4; cr4 = this_cpu_read(cpu_tlbstate.cr4); - cr4 ^= mask; - this_cpu_write(cpu_tlbstate.cr4, cr4); - __write_cr4(cr4); + __cr4_set(cr4 ^ mask); } /* Read the CR4 shadow. */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 1fadd310ff68..31051f35cbb7 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -75,7 +75,6 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long); dotraplinkage void do_stack_segment(struct pt_regs *, long); #ifdef CONFIG_X86_64 dotraplinkage void do_double_fault(struct pt_regs *, long); -asmlinkage struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index e9cc6fe1fc6f..c1688c2d0a12 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -7,6 +7,9 @@ #include <asm/ptrace.h> #include <asm/stacktrace.h> +#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip)) +#define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET) + struct unwind_state { struct stack_info stack_info; unsigned long stack_mask; @@ -52,6 +55,10 @@ void unwind_start(struct unwind_state *state, struct task_struct *task, } #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) +/* + * WARNING: The entire pt_regs may not be safe to dereference. In some cases, + * only the iret frame registers are accessible. Use with caution! + */ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) { if (unwind_done(state)) diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild index da1489cb64dc..1e901e421f2d 100644 --- a/arch/x86/include/uapi/asm/Kbuild +++ b/arch/x86/include/uapi/asm/Kbuild @@ -1,6 +1,7 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generated-y += unistd_32.h generated-y += unistd_64.h generated-y += unistd_x32.h diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 6a823a25eaff..750449152b04 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -542,8 +542,8 @@ error: } #ifdef CONFIG_GENERIC_IRQ_DEBUGFS -void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d, - struct irq_data *irqd, int ind) +static void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d, + struct irq_data *irqd, int ind) { unsigned int cpu, vector, prev_cpu, prev_vector; struct apic_chip_data *apicd; diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 8ea78275480d..cd360a5e0dca 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -93,4 +93,10 @@ void common(void) { BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); + + /* Layout info for cpu_entry_area */ + OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss); + OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline); + OFFSET(CPU_ENTRY_AREA_SYSENTER_stack, cpu_entry_area, SYSENTER_stack_page); + DEFINE(SIZEOF_SYSENTER_stack, sizeof(struct SYSENTER_stack)); } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index dedf428b20b6..7d20d9c0b3d6 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -47,13 +47,8 @@ void foo(void) BLANK(); /* Offset from the sysenter stack to tss.sp0 */ - DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) - - offsetofend(struct tss_struct, SYSENTER_stack)); - - /* Offset from cpu_tss to SYSENTER_stack */ - OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack); - /* Size of SYSENTER_stack */ - DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack)); + DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) - + offsetofend(struct cpu_entry_area, SYSENTER_stack_page.stack)); #ifdef CONFIG_CC_STACKPROTECTOR BLANK(); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 630212fa9b9d..bf51e51d808d 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -23,6 +23,9 @@ int main(void) #ifdef CONFIG_PARAVIRT OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); +#ifdef CONFIG_DEBUG_ENTRY + OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl); +#endif BLANK(); #endif @@ -63,6 +66,7 @@ int main(void) OFFSET(TSS_ist, tss_struct, x86_tss.ist); OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); + OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); BLANK(); #ifdef CONFIG_CC_STACKPROTECTOR diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index d58184b7cd44..bcb75dc97d44 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -804,8 +804,11 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x17: init_amd_zn(c); break; } - /* Enable workaround for FXSAVE leak */ - if (c->x86 >= 6) + /* + * Enable workaround for FXSAVE leak on CPUs + * without a XSaveErPtr feature + */ + if ((c->x86 >= 6) && (!cpu_has(c, X86_FEATURE_XSAVEERPTR))) set_cpu_bug(c, X86_BUG_FXSAVE_LEAK); cpu_detect_cache_sizes(c); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index fa998ca8aa5a..7416da3ec4df 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -476,8 +476,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c) return NULL; /* Not found */ } -__u32 cpu_caps_cleared[NCAPINTS]; -__u32 cpu_caps_set[NCAPINTS]; +__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +__u32 cpu_caps_set[NCAPINTS + NBUGINTS]; void load_percpu_segment(int cpu) { @@ -490,27 +490,116 @@ void load_percpu_segment(int cpu) load_stack_canary_segment(); } -/* Setup the fixmap mapping only once per-processor */ -static inline void setup_fixmap_gdt(int cpu) +#ifdef CONFIG_X86_32 +/* The 32-bit entry code needs to find cpu_entry_area. */ +DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); +#endif + +#ifdef CONFIG_X86_64 +/* + * Special IST stacks which the CPU switches to when it calls + * an IST-marked descriptor entry. Up to 7 stacks (hardware + * limit), all of them are 4K, except the debug stack which + * is 8K. + */ +static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, + [DEBUG_STACK - 1] = DEBUG_STKSZ +}; + +static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks + [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); +#endif + +static DEFINE_PER_CPU_PAGE_ALIGNED(struct SYSENTER_stack_page, + SYSENTER_stack_storage); + +static void __init +set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot) +{ + for ( ; pages; pages--, idx--, ptr += PAGE_SIZE) + __set_fixmap(idx, per_cpu_ptr_to_phys(ptr), prot); +} + +/* Setup the fixmap mappings only once per-processor */ +static void __init setup_cpu_entry_area(int cpu) { #ifdef CONFIG_X86_64 - /* On 64-bit systems, we use a read-only fixmap GDT. */ - pgprot_t prot = PAGE_KERNEL_RO; + extern char _entry_trampoline[]; + + /* On 64-bit systems, we use a read-only fixmap GDT and TSS. */ + pgprot_t gdt_prot = PAGE_KERNEL_RO; + pgprot_t tss_prot = PAGE_KERNEL_RO; #else /* * On native 32-bit systems, the GDT cannot be read-only because * our double fault handler uses a task gate, and entering through - * a task gate needs to change an available TSS to busy. If the GDT - * is read-only, that will triple fault. + * a task gate needs to change an available TSS to busy. If the + * GDT is read-only, that will triple fault. The TSS cannot be + * read-only because the CPU writes to it on task switches. * - * On Xen PV, the GDT must be read-only because the hypervisor requires - * it. + * On Xen PV, the GDT must be read-only because the hypervisor + * requires it. */ - pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ? + pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ? PAGE_KERNEL_RO : PAGE_KERNEL; + pgprot_t tss_prot = PAGE_KERNEL; #endif - __set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot); + __set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot); + set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, SYSENTER_stack_page), + per_cpu_ptr(&SYSENTER_stack_storage, cpu), 1, + PAGE_KERNEL); + + /* + * The Intel SDM says (Volume 3, 7.2.1): + * + * Avoid placing a page boundary in the part of the TSS that the + * processor reads during a task switch (the first 104 bytes). The + * processor may not correctly perform address translations if a + * boundary occurs in this area. During a task switch, the processor + * reads and writes into the first 104 bytes of each TSS (using + * contiguous physical addresses beginning with the physical address + * of the first byte of the TSS). So, after TSS access begins, if + * part of the 104 bytes is not physically contiguous, the processor + * will access incorrect information without generating a page-fault + * exception. + * + * There are also a lot of errata involving the TSS spanning a page + * boundary. Assert that we're not doing that. + */ + BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^ + offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK); + BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0); + set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, tss), + &per_cpu(cpu_tss_rw, cpu), + sizeof(struct tss_struct) / PAGE_SIZE, + tss_prot); + +#ifdef CONFIG_X86_32 + per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu); +#endif + +#ifdef CONFIG_X86_64 + BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0); + BUILD_BUG_ON(sizeof(exception_stacks) != + sizeof(((struct cpu_entry_area *)0)->exception_stacks)); + set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, exception_stacks), + &per_cpu(exception_stacks, cpu), + sizeof(exception_stacks) / PAGE_SIZE, + PAGE_KERNEL); + + __set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline), + __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX); +#endif +} + +void __init setup_cpu_entry_areas(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + setup_cpu_entry_area(cpu); } /* Load the original GDT from the per-cpu structure */ @@ -747,7 +836,7 @@ static void apply_forced_caps(struct cpuinfo_x86 *c) { int i; - for (i = 0; i < NCAPINTS; i++) { + for (i = 0; i < NCAPINTS + NBUGINTS; i++) { c->x86_capability[i] &= ~cpu_caps_cleared[i]; c->x86_capability[i] |= cpu_caps_set[i]; } @@ -1250,7 +1339,7 @@ void enable_sep_cpu(void) return; cpu = get_cpu(); - tss = &per_cpu(cpu_tss, cpu); + tss = &per_cpu(cpu_tss_rw, cpu); /* * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field -- @@ -1259,11 +1348,7 @@ void enable_sep_cpu(void) tss->x86_tss.ss1 = __KERNEL_CS; wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0); - - wrmsr(MSR_IA32_SYSENTER_ESP, - (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack), - 0); - + wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1), 0); wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); put_cpu(); @@ -1357,25 +1442,19 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -/* - * Special IST stacks which the CPU switches to when it calls - * an IST-marked descriptor entry. Up to 7 stacks (hardware - * limit), all of them are 4K, except the debug stack which - * is 8K. - */ -static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { - [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, - [DEBUG_STACK - 1] = DEBUG_STKSZ -}; - -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks - [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); - /* May not be marked __init: used by software suspend */ void syscall_init(void) { + extern char _entry_trampoline[]; + extern char entry_SYSCALL_64_trampoline[]; + + int cpu = smp_processor_id(); + unsigned long SYSCALL64_entry_trampoline = + (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline + + (entry_SYSCALL_64_trampoline - _entry_trampoline); + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); - wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); + wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline); #ifdef CONFIG_IA32_EMULATION wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); @@ -1386,7 +1465,7 @@ void syscall_init(void) * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); @@ -1530,7 +1609,7 @@ void cpu_init(void) if (cpu) load_ucode_ap(); - t = &per_cpu(cpu_tss, cpu); + t = &per_cpu(cpu_tss_rw, cpu); oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA @@ -1569,7 +1648,7 @@ void cpu_init(void) * set up and load the per-CPU TSS */ if (!oist->ist[0]) { - char *estacks = per_cpu(exception_stacks, cpu); + char *estacks = get_cpu_entry_area(cpu)->exception_stacks; for (v = 0; v < N_EXCEPTION_STACKS; v++) { estacks += exception_stack_sizes[v]; @@ -1580,7 +1659,7 @@ void cpu_init(void) } } - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; /* * <= is required because the CPU will access up to @@ -1596,11 +1675,12 @@ void cpu_init(void) enter_lazy_tlb(&init_mm, me); /* - * Initialize the TSS. Don't bother initializing sp0, as the initial - * task never enters user mode. + * Initialize the TSS. sp0 points to the entry trampoline stack + * regardless of what task is running. */ - set_tss_desc(cpu, t); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); + load_sp0((unsigned long)(cpu_SYSENTER_stack(cpu) + 1)); load_mm_ldt(&init_mm); @@ -1612,7 +1692,6 @@ void cpu_init(void) if (is_uv_system()) uv_cpu_init(); - setup_fixmap_gdt(cpu); load_fixmap_gdt(cpu); } @@ -1622,7 +1701,7 @@ void cpu_init(void) { int cpu = smp_processor_id(); struct task_struct *curr = current; - struct tss_struct *t = &per_cpu(cpu_tss, cpu); + struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu); wait_for_master_cpu(cpu); @@ -1657,12 +1736,12 @@ void cpu_init(void) * Initialize the TSS. Don't bother initializing sp0, as the initial * task never enters user mode. */ - set_tss_desc(cpu, t); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); load_mm_ldt(&init_mm); - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; #ifdef CONFIG_DOUBLEFAULT /* Set up doublefault TSS pointer in the GDT */ @@ -1674,7 +1753,6 @@ void cpu_init(void) fpu__init_cpu(); - setup_fixmap_gdt(cpu); load_fixmap_gdt(cpu); } #endif diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index c6daec4bdba5..330b8462d426 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -470,6 +470,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, #define F14H_MPB_MAX_SIZE 1824 #define F15H_MPB_MAX_SIZE 4096 #define F16H_MPB_MAX_SIZE 3458 +#define F17H_MPB_MAX_SIZE 3200 switch (family) { case 0x14: @@ -481,6 +482,9 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, case 0x16: max_size = F16H_MPB_MAX_SIZE; break; + case 0x17: + max_size = F17H_MPB_MAX_SIZE; + break; default: max_size = F1XH_MPB_MAX_SIZE; break; diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c index 0e662c55ae90..0b8cedb20d6d 100644 --- a/arch/x86/kernel/doublefault.c +++ b/arch/x86/kernel/doublefault.c @@ -50,25 +50,23 @@ static void doublefault_fn(void) cpu_relax(); } -struct tss_struct doublefault_tss __cacheline_aligned = { - .x86_tss = { - .sp0 = STACK_START, - .ss0 = __KERNEL_DS, - .ldt = 0, - .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, - - .ip = (unsigned long) doublefault_fn, - /* 0x2 bit is always set */ - .flags = X86_EFLAGS_SF | 0x2, - .sp = STACK_START, - .es = __USER_DS, - .cs = __KERNEL_CS, - .ss = __KERNEL_DS, - .ds = __USER_DS, - .fs = __KERNEL_PERCPU, - - .__cr3 = __pa_nodebug(swapper_pg_dir), - } +struct x86_hw_tss doublefault_tss __cacheline_aligned = { + .sp0 = STACK_START, + .ss0 = __KERNEL_DS, + .ldt = 0, + .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, + + .ip = (unsigned long) doublefault_fn, + /* 0x2 bit is always set */ + .flags = X86_EFLAGS_SF | 0x2, + .sp = STACK_START, + .es = __USER_DS, + .cs = __KERNEL_CS, + .ss = __KERNEL_DS, + .ds = __USER_DS, + .fs = __KERNEL_PERCPU, + + .__cr3 = __pa_nodebug(swapper_pg_dir), }; /* dummy for do_double_fault() call */ diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f13b4c00a5de..bbd6d986e2d0 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -43,6 +43,24 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task, return true; } +bool in_sysenter_stack(unsigned long *stack, struct stack_info *info) +{ + struct SYSENTER_stack *ss = cpu_SYSENTER_stack(smp_processor_id()); + + void *begin = ss; + void *end = ss + 1; + + if ((void *)stack < begin || (void *)stack >= end) + return false; + + info->type = STACK_TYPE_SYSENTER; + info->begin = begin; + info->end = end; + info->next_sp = NULL; + + return true; +} + static void printk_stack_address(unsigned long address, int reliable, char *log_lvl) { @@ -50,6 +68,28 @@ static void printk_stack_address(unsigned long address, int reliable, printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address); } +void show_iret_regs(struct pt_regs *regs) +{ + printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip); + printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss, + regs->sp, regs->flags); +} + +static void show_regs_safe(struct stack_info *info, struct pt_regs *regs) +{ + if (on_stack(info, regs, sizeof(*regs))) + __show_regs(regs, 0); + else if (on_stack(info, (void *)regs + IRET_FRAME_OFFSET, + IRET_FRAME_SIZE)) { + /* + * When an interrupt or exception occurs in entry code, the + * full pt_regs might not have been saved yet. In that case + * just print the iret frame. + */ + show_iret_regs(regs); + } +} + void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, char *log_lvl) { @@ -71,31 +111,35 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * - task stack * - interrupt stack * - HW exception stacks (double fault, nmi, debug, mce) + * - SYSENTER stack * - * x86-32 can have up to three stacks: + * x86-32 can have up to four stacks: * - task stack * - softirq stack * - hardirq stack + * - SYSENTER stack */ for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { const char *stack_name; - /* - * If we overflowed the task stack into a guard page, jump back - * to the bottom of the usable stack. - */ - if (task_stack_page(task) - (void *)stack < PAGE_SIZE) - stack = task_stack_page(task); - - if (get_stack_info(stack, task, &stack_info, &visit_mask)) - break; + if (get_stack_info(stack, task, &stack_info, &visit_mask)) { + /* + * We weren't on a valid stack. It's possible that + * we overflowed a valid stack into a guard page. + * See if the next page up is valid so that we can + * generate some kind of backtrace if this happens. + */ + stack = (unsigned long *)PAGE_ALIGN((unsigned long)stack); + if (get_stack_info(stack, task, &stack_info, &visit_mask)) + break; + } stack_name = stack_type_name(stack_info.type); if (stack_name) printk("%s <%s>\n", log_lvl, stack_name); - if (regs && on_stack(&stack_info, regs, sizeof(*regs))) - __show_regs(regs, 0); + if (regs) + show_regs_safe(&stack_info, regs); /* * Scan the stack, printing any text addresses we find. At the @@ -119,7 +163,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, /* * Don't print regs->ip again if it was already printed - * by __show_regs() below. + * by show_regs_safe() below. */ if (regs && stack == ®s->ip) goto next; @@ -155,8 +199,8 @@ next: /* if the frame has entry regs, print them */ regs = unwind_get_entry_regs(&state); - if (regs && on_stack(&stack_info, regs, sizeof(*regs))) - __show_regs(regs, 0); + if (regs) + show_regs_safe(&stack_info, regs); } if (stack_name) diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index daefae83a3aa..5ff13a6b3680 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -26,6 +26,9 @@ const char *stack_type_name(enum stack_type type) if (type == STACK_TYPE_SOFTIRQ) return "SOFTIRQ"; + if (type == STACK_TYPE_SYSENTER) + return "SYSENTER"; + return NULL; } @@ -93,6 +96,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, if (task != current) goto unknown; + if (in_sysenter_stack(stack, info)) + goto recursion_check; + if (in_hardirq_stack(stack, info)) goto recursion_check; diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 88ce2ffdb110..abc828f8c297 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -37,6 +37,9 @@ const char *stack_type_name(enum stack_type type) if (type == STACK_TYPE_IRQ) return "IRQ"; + if (type == STACK_TYPE_SYSENTER) + return "SYSENTER"; + if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST) return exception_stack_names[type - STACK_TYPE_EXCEPTION]; @@ -115,6 +118,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, if (in_irq_stack(stack, info)) goto recursion_check; + if (in_sysenter_stack(stack, info)) + goto recursion_check; + goto unknown; recursion_check: diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 3feb648781c4..2f723301eb58 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -67,7 +67,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) * because the ->io_bitmap_max value must match the bitmap * contents: */ - tss = &per_cpu(cpu_tss, get_cpu()); + tss = &per_cpu(cpu_tss_rw, get_cpu()); if (turn_on) bitmap_clear(t->io_bitmap_ptr, from, num); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 49cfd9fe7589..68e1867cca80 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -219,18 +219,6 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) /* high bit used in ret_from_ code */ unsigned vector = ~regs->orig_ax; - /* - * NB: Unlike exception entries, IRQ entries do not reliably - * handle context tracking in the low-level entry code. This is - * because syscall entries execute briefly with IRQs on before - * updating context tracking state, so we can take an IRQ from - * kernel mode with CONTEXT_USER. The low-level entry code only - * updates the context if we came from user mode, so we won't - * switch to CONTEXT_KERNEL. We'll fix that once the syscall - * code is cleaned up enough that we can cleanly defer enabling - * IRQs. - */ - entering_irq(); /* entering_irq() tells RCU that we're not quiescent. Check it. */ diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 020efbf5786b..d86e344f5b3d 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -57,10 +57,10 @@ static inline void stack_overflow_check(struct pt_regs *regs) if (regs->sp >= estack_top && regs->sp <= estack_bottom) return; - WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n", + WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n", current->comm, curbase, regs->sp, irq_stack_top, irq_stack_bottom, - estack_top, estack_bottom); + estack_top, estack_bottom, (void *)regs->ip); if (sysctl_panic_on_stackoverflow) panic("low stack detected by irq handler - check messages\n"); diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index ac0be8283325..9edadabf04f6 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -10,7 +10,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); -DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); @@ -60,7 +59,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); - PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); #if defined(CONFIG_PARAVIRT_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 97fb3e5737f5..aed9d94bd46f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -47,7 +47,7 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { +__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss_rw) = { .x86_tss = { /* * .sp0 is only used when entering ring 0 from a lower @@ -56,6 +56,16 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { * Poison it. */ .sp0 = (1UL << (BITS_PER_LONG-1)) + 1, + +#ifdef CONFIG_X86_64 + /* + * .sp1 is cpu_current_top_of_stack. The init task never + * runs user code, but cpu_current_top_of_stack should still + * be well defined before the first context switch. + */ + .sp1 = TOP_OF_INIT_STACK, +#endif + #ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, .ss1 = __KERNEL_CS, @@ -71,11 +81,8 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { */ .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, #endif -#ifdef CONFIG_X86_32 - .SYSENTER_stack_canary = STACK_END_MAGIC, -#endif }; -EXPORT_PER_CPU_SYMBOL(cpu_tss); +EXPORT_PER_CPU_SYMBOL(cpu_tss_rw); DEFINE_PER_CPU(bool, __tss_limit_invalid); EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid); @@ -104,7 +111,7 @@ void exit_thread(struct task_struct *tsk) struct fpu *fpu = &t->fpu; if (bp) { - struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu()); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu()); t->io_bitmap_ptr = NULL; clear_thread_flag(TIF_IO_BITMAP); @@ -299,7 +306,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, } if ((tifp ^ tifn) & _TIF_NOTSC) - cr4_toggle_bits(X86_CR4_TSD); + cr4_toggle_bits_irqsoff(X86_CR4_TSD); if ((tifp ^ tifn) & _TIF_NOCPUID) set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 45bf0c5f93e1..5224c6099184 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -234,7 +234,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index eeeb34f85c25..c75466232016 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -69,9 +69,8 @@ void __show_regs(struct pt_regs *regs, int all) unsigned int fsindex, gsindex; unsigned int ds, cs, es; - printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip); - printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss, - regs->sp, regs->flags); + show_iret_regs(regs); + if (regs->orig_ax != -1) pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax); else @@ -88,6 +87,9 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); + if (!all) + return; + asm("movl %%ds,%0" : "=r" (ds)); asm("movl %%cs,%0" : "=r" (cs)); asm("movl %%es,%0" : "=r" (es)); @@ -98,9 +100,6 @@ void __show_regs(struct pt_regs *regs, int all) rdmsrl(MSR_GS_BASE, gs); rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); - if (!all) - return; - cr0 = read_cr0(); cr2 = read_cr2(); cr3 = __read_cr3(); @@ -400,7 +399,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && this_cpu_read(irq_count) != -1); @@ -462,6 +461,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Switch the PDA and FPU contexts. */ this_cpu_write(current_task, next_p); + this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p)); /* Reload sp0. */ update_sp0(next_p); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 3d01df7d7cf6..35cb20994e32 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -106,7 +106,7 @@ EXPORT_SYMBOL(__max_logical_packages); static unsigned int logical_packages __read_mostly; /* Maximum number of SMT threads on any online core */ -int __max_smt_threads __read_mostly; +int __read_mostly __max_smt_threads = 1; /* Flag to indicate if a complete sched domain rebuild is required */ bool x86_topology_update; @@ -237,7 +237,7 @@ static void notrace start_secondary(void *unused) load_cr3(swapper_pg_dir); __flush_tlb_all(); #endif - + load_current_idt(); cpu_init(); x86_cpuinit.early_percpu_clock_init(); preempt_disable(); @@ -1304,7 +1304,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus) * Today neither Intel nor AMD support heterogenous systems so * extrapolate the boot cpu's data to all packages. */ - ncpus = cpu_data(0).booted_cores * smp_num_siblings; + ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); pr_info("Max logical packages: %u\n", __max_logical_packages); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 989514c94a55..e98f8b66a460 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -348,9 +348,15 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) /* * If IRET takes a non-IST fault on the espfix64 stack, then we - * end up promoting it to a doublefault. In that case, modify - * the stack to make it look like we just entered the #GP - * handler from user space, similar to bad_iret. + * end up promoting it to a doublefault. In that case, take + * advantage of the fact that we're not using the normal (TSS.sp0) + * stack right now. We can write a fake #GP(0) frame at TSS.sp0 + * and then modify our own IRET frame so that, when we return, + * we land directly at the #GP(0) vector with the stack already + * set up according to its expectations. + * + * The net result is that our #GP handler will think that we + * entered from usermode with the bad user context. * * No need for ist_enter here because we don't use RCU. */ @@ -358,13 +364,26 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) regs->cs == __KERNEL_CS && regs->ip == (unsigned long)native_irq_return_iret) { - struct pt_regs *normal_regs = task_pt_regs(current); + struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; - /* Fake a #GP(0) from userspace. */ - memmove(&normal_regs->ip, (void *)regs->sp, 5*8); - normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */ + /* + * regs->sp points to the failing IRET frame on the + * ESPFIX64 stack. Copy it to the entry stack. This fills + * in gpregs->ss through gpregs->ip. + * + */ + memmove(&gpregs->ip, (void *)regs->sp, 5*8); + gpregs->orig_ax = 0; /* Missing (lost) #GP error code */ + + /* + * Adjust our frame so that we return straight to the #GP + * vector with the expected RSP value. This is safe because + * we won't enable interupts or schedule before we invoke + * general_protection, so nothing will clobber the stack + * frame we just set up. + */ regs->ip = (unsigned long)general_protection; - regs->sp = (unsigned long)&normal_regs->orig_ax; + regs->sp = (unsigned long)&gpregs->orig_ax; return; } @@ -389,7 +408,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) * * Processors update CR2 whenever a page fault is detected. If a * second page fault occurs while an earlier page fault is being - * deliv- ered, the faulting linear address of the second fault will + * delivered, the faulting linear address of the second fault will * overwrite the contents of CR2 (replacing the previous * address). These updates to CR2 occur even if the page fault * results in a double fault or occurs during the delivery of a @@ -605,14 +624,15 @@ NOKPROBE_SYMBOL(do_int3); #ifdef CONFIG_X86_64 /* - * Help handler running on IST stack to switch off the IST stack if the - * interrupted code was in user mode. The actual stack switch is done in - * entry_64.S + * Help handler running on a per-cpu (IST or entry trampoline) stack + * to switch to the normal thread stack if the interrupted code was in + * user mode. The actual stack switch is done in entry_64.S */ asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs) { - struct pt_regs *regs = task_pt_regs(current); - *regs = *eregs; + struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1; + if (regs != eregs) + *regs = *eregs; return regs; } NOKPROBE_SYMBOL(sync_regs); @@ -628,13 +648,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) /* * This is called from entry_64.S early in handling a fault * caused by a bad iret to user mode. To handle the fault - * correctly, we want move our stack frame to task_pt_regs - * and we want to pretend that the exception came from the - * iret target. + * correctly, we want to move our stack frame to where it would + * be had we entered directly on the entry stack (rather than + * just below the IRET frame) and we want to pretend that the + * exception came from the IRET target. */ struct bad_iret_stack *new_stack = - container_of(task_pt_regs(current), - struct bad_iret_stack, regs); + (struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the new stack. */ memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); @@ -795,14 +815,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: -#if defined(CONFIG_X86_32) - /* - * This is the most likely code path that involves non-trivial use - * of the SYSENTER stack. Check that we haven't overrun it. - */ - WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC, - "Overran or corrupted SYSENTER stack\n"); -#endif ist_exit(regs); } NOKPROBE_SYMBOL(do_debug); @@ -929,6 +941,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) void __init trap_init(void) { + /* Init cpu_entry_area before IST entries are set up */ + setup_cpu_entry_areas(); + idt_setup_traps(); /* diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index a3f973b2c97a..be86a865087a 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -253,22 +253,15 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) return NULL; } -static bool stack_access_ok(struct unwind_state *state, unsigned long addr, +static bool stack_access_ok(struct unwind_state *state, unsigned long _addr, size_t len) { struct stack_info *info = &state->stack_info; + void *addr = (void *)_addr; - /* - * If the address isn't on the current stack, switch to the next one. - * - * We may have to traverse multiple stacks to deal with the possibility - * that info->next_sp could point to an empty stack and the address - * could be on a subsequent stack. - */ - while (!on_stack(info, (void *)addr, len)) - if (get_stack_info(info->next_sp, state->task, info, - &state->stack_mask)) - return false; + if (!on_stack(info, addr, len) && + (get_stack_info(addr, state->task, info, &state->stack_mask))) + return false; return true; } @@ -283,42 +276,32 @@ static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, return true; } -#define REGS_SIZE (sizeof(struct pt_regs)) -#define SP_OFFSET (offsetof(struct pt_regs, sp)) -#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip)) -#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip)) - static bool deref_stack_regs(struct unwind_state *state, unsigned long addr, - unsigned long *ip, unsigned long *sp, bool full) + unsigned long *ip, unsigned long *sp) { - size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE; - size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET; - struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE); - - if (IS_ENABLED(CONFIG_X86_64)) { - if (!stack_access_ok(state, addr, regs_size)) - return false; + struct pt_regs *regs = (struct pt_regs *)addr; - *ip = regs->ip; - *sp = regs->sp; + /* x86-32 support will be more complicated due to the ®s->sp hack */ + BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_32)); - return true; - } - - if (!stack_access_ok(state, addr, sp_offset)) + if (!stack_access_ok(state, addr, sizeof(struct pt_regs))) return false; *ip = regs->ip; + *sp = regs->sp; + return true; +} - if (user_mode(regs)) { - if (!stack_access_ok(state, addr + sp_offset, - REGS_SIZE - SP_OFFSET)) - return false; +static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr, + unsigned long *ip, unsigned long *sp) +{ + struct pt_regs *regs = (void *)addr - IRET_FRAME_OFFSET; - *sp = regs->sp; - } else - *sp = (unsigned long)®s->sp; + if (!stack_access_ok(state, addr, IRET_FRAME_SIZE)) + return false; + *ip = regs->ip; + *sp = regs->sp; return true; } @@ -327,7 +310,6 @@ bool unwind_next_frame(struct unwind_state *state) unsigned long ip_p, sp, orig_ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; - struct pt_regs *ptregs; bool indirect = false; if (unwind_done(state)) @@ -435,7 +417,7 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_TYPE_REGS: - if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) { + if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; @@ -447,20 +429,14 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_TYPE_REGS_IRET: - if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) { + if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference iret registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; } - ptregs = container_of((void *)sp, struct pt_regs, ip); - if ((unsigned long)ptregs >= prev_sp && - on_stack(&state->stack_info, ptregs, REGS_SIZE)) { - state->regs = ptregs; - state->full_regs = false; - } else - state->regs = NULL; - + state->regs = (void *)sp - IRET_FRAME_OFFSET; + state->full_regs = false; state->signal = true; break; @@ -553,8 +529,18 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, } if (get_stack_info((unsigned long *)state->sp, state->task, - &state->stack_info, &state->stack_mask)) - return; + &state->stack_info, &state->stack_mask)) { + /* + * We weren't on a valid stack. It's possible that + * we overflowed a valid stack into a guard page. + * See if the next page up is valid so that we can + * generate some kind of backtrace if this happens. + */ + void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp); + if (get_stack_info(next_page, state->task, &state->stack_info, + &state->stack_mask)) + return; + } /* * The caller can provide the address of the first frame directly diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index a4009fb9be87..d2a8b5a24a44 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -107,6 +107,15 @@ SECTIONS SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) + +#ifdef CONFIG_X86_64 + . = ALIGN(PAGE_SIZE); + _entry_trampoline = .; + *(.entry_trampoline) + . = ALIGN(PAGE_SIZE); + ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); +#endif + /* End of text section */ _etext = .; } :text = 0x9090 diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index e7d04d0c8008..abe74f779f9d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1046,7 +1046,6 @@ static void fetch_register_operand(struct operand *op) static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) { - ctxt->ops->get_fpu(ctxt); switch (reg) { case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; @@ -1068,13 +1067,11 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) #endif default: BUG(); } - ctxt->ops->put_fpu(ctxt); } static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) { - ctxt->ops->get_fpu(ctxt); switch (reg) { case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; @@ -1096,12 +1093,10 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, #endif default: BUG(); } - ctxt->ops->put_fpu(ctxt); } static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) { - ctxt->ops->get_fpu(ctxt); switch (reg) { case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; @@ -1113,12 +1108,10 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; default: BUG(); } - ctxt->ops->put_fpu(ctxt); } static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) { - ctxt->ops->get_fpu(ctxt); switch (reg) { case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; @@ -1130,7 +1123,6 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; default: BUG(); } - ctxt->ops->put_fpu(ctxt); } static int em_fninit(struct x86_emulate_ctxt *ctxt) @@ -1138,9 +1130,7 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); - ctxt->ops->get_fpu(ctxt); asm volatile("fninit"); - ctxt->ops->put_fpu(ctxt); return X86EMUL_CONTINUE; } @@ -1151,9 +1141,7 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); - ctxt->ops->get_fpu(ctxt); asm volatile("fnstcw %0": "+m"(fcw)); - ctxt->ops->put_fpu(ctxt); ctxt->dst.val = fcw; @@ -1167,9 +1155,7 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); - ctxt->ops->get_fpu(ctxt); asm volatile("fnstsw %0": "+m"(fsw)); - ctxt->ops->put_fpu(ctxt); ctxt->dst.val = fsw; @@ -4001,12 +3987,8 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - ctxt->ops->get_fpu(ctxt); - rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); - ctxt->ops->put_fpu(ctxt); - if (rc != X86EMUL_CONTINUE) return rc; @@ -4049,8 +4031,6 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - ctxt->ops->get_fpu(ctxt); - if (size < __fxstate_size(16)) { rc = fxregs_fixup(&fx_state, size); if (rc != X86EMUL_CONTINUE) @@ -4066,8 +4046,6 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); out: - ctxt->ops->put_fpu(ctxt); - return rc; } @@ -5317,9 +5295,7 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) { int rc; - ctxt->ops->get_fpu(ctxt); rc = asm_safe("fwait"); - ctxt->ops->put_fpu(ctxt); if (unlikely(rc != X86EMUL_CONTINUE)) return emulate_exception(ctxt, MF_VECTOR, 0, false); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4704aaf6d19e..023afa0c8887 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2302,7 +2302,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) * processors. See 22.2.4. */ vmcs_writel(HOST_TR_BASE, - (unsigned long)this_cpu_ptr(&cpu_tss)); + (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ /* @@ -6751,16 +6751,10 @@ static __init int hardware_setup(void) goto out; } - vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL); memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); - /* - * Allow direct access to the PC debug port (it is often used for I/O - * delays, but the vmexits simply slow things down). - */ memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE); - clear_bit(0x80, vmx_io_bitmap_a); memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index eee8e7faf1af..faf843c9b916 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2937,7 +2937,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) srcu_read_unlock(&vcpu->kvm->srcu, idx); pagefault_enable(); kvm_x86_ops->vcpu_put(vcpu); - kvm_put_guest_fpu(vcpu); vcpu->arch.last_host_tsc = rdtsc(); } @@ -5252,17 +5251,6 @@ static void emulator_halt(struct x86_emulate_ctxt *ctxt) emul_to_vcpu(ctxt)->arch.halt_request = 1; } -static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt) -{ - preempt_disable(); - kvm_load_guest_fpu(emul_to_vcpu(ctxt)); -} - -static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt) -{ - preempt_enable(); -} - static int emulator_intercept(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage) @@ -5340,8 +5328,6 @@ static const struct x86_emulate_ops emulate_ops = { .halt = emulator_halt, .wbinvd = emulator_wbinvd, .fix_hypercall = emulator_fix_hypercall, - .get_fpu = emulator_get_fpu, - .put_fpu = emulator_put_fpu, .intercept = emulator_intercept, .get_cpuid = emulator_get_cpuid, .set_nmi_mask = emulator_set_nmi_mask, @@ -6778,6 +6764,20 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu) kvm_x86_ops->tlb_flush(vcpu); } +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end) +{ + unsigned long apic_address; + + /* + * The physical address of apic access page is stored in the VMCS. + * Update it when it becomes invalid. + */ + apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); + if (start <= apic_address && apic_address < end) + kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); +} + void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { struct page *page = NULL; @@ -6952,7 +6952,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); kvm_x86_ops->prepare_guest_switch(vcpu); - kvm_load_guest_fpu(vcpu); /* * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt @@ -7297,12 +7296,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } } + kvm_load_guest_fpu(vcpu); + if (unlikely(vcpu->arch.complete_userspace_io)) { int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io; vcpu->arch.complete_userspace_io = NULL; r = cui(vcpu); if (r <= 0) - goto out; + goto out_fpu; } else WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); @@ -7311,6 +7312,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) else r = vcpu_run(vcpu); +out_fpu: + kvm_put_guest_fpu(vcpu); out: post_kvm_run_save(vcpu); kvm_sigset_deactivate(vcpu); @@ -7704,32 +7707,25 @@ static void fx_init(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= X86_CR0_ET; } +/* Swap (qemu) user FPU context for the guest FPU context. */ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { - if (vcpu->guest_fpu_loaded) - return; - - /* - * Restore all possible states in the guest, - * and assume host would use all available bits. - * Guest xcr0 would be loaded later. - */ - vcpu->guest_fpu_loaded = 1; - __kernel_fpu_begin(); + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); /* PKRU is separately restored in kvm_x86_ops->run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, ~XFEATURE_MASK_PKRU); + preempt_enable(); trace_kvm_fpu(1); } +/* When vcpu_run ends, restore user space FPU context. */ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { - if (!vcpu->guest_fpu_loaded) - return; - - vcpu->guest_fpu_loaded = 0; + preempt_disable(); copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); - __kernel_fpu_end(); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); + preempt_enable(); ++vcpu->stat.fpu_reload; trace_kvm_fpu(0); } @@ -7846,7 +7842,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) * To avoid have the INIT path from kvm_apic_has_events() that be * called with loaded FPU and does not let userspace fix the state. */ - kvm_put_guest_fpu(vcpu); + if (init_event) + kvm_put_guest_fpu(vcpu); mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu.state.xsave, XFEATURE_MASK_BNDREGS); if (mpx_state_buffer) @@ -7855,6 +7852,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) XFEATURE_MASK_BNDCSR); if (mpx_state_buffer) memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr)); + if (init_event) + kvm_load_guest_fpu(vcpu); } if (!init_event) { diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 553f8fd23cc4..4846eff7e4c8 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -107,10 +107,10 @@ static void delay_mwaitx(unsigned long __loops) delay = min_t(u64, MWAITX_MAX_LOOPS, loops); /* - * Use cpu_tss as a cacheline-aligned, seldomly + * Use cpu_tss_rw as a cacheline-aligned, seldomly * accessed per-cpu variable as the monitor target. */ - __monitorx(raw_cpu_ptr(&cpu_tss), 0, 0); + __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); /* * AMD, like Intel, supports the EAX hint and EAX=0xf diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index c4d55919fac1..e0b85930dd77 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1) fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1) fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1) fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1) -ff: +ff: UD0 EndTable Table: 3-byte opcode 1 (0x0f 0x38) @@ -717,7 +717,7 @@ AVXcode: 2 7e: vpermt2d/q Vx,Hx,Wx (66),(ev) 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) -81: INVPID Gy,Mdq (66) +81: INVVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) 83: vpmultishiftqb Vx,Hx,Wx (66),(ev) 88: vexpandps/d Vpd,Wpd (66),(ev) @@ -970,6 +970,15 @@ GrpTable: Grp9 EndTable GrpTable: Grp10 +# all are UD1 +0: UD1 +1: UD1 +2: UD1 +3: UD1 +4: UD1 +5: UD1 +6: UD1 +7: UD1 EndTable # Grp11A and Grp11B are expressed as Grp11 in Intel SDM diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 3321b446b66c..9fe656c42aa5 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -1,6 +1,7 @@ #include <linux/extable.h> #include <linux/uaccess.h> #include <linux/sched/debug.h> +#include <xen/xen.h> #include <asm/fpu/internal.h> #include <asm/traps.h> @@ -82,7 +83,7 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup, return true; } -EXPORT_SYMBOL_GPL(ex_handler_refcount); +EXPORT_SYMBOL(ex_handler_refcount); /* * Handler for when we fail to restore a task's FPU state. We should never get @@ -212,8 +213,9 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) * Old CPUs leave the high bits of CS on the stack * undefined. I'm not sure which CPUs do this, but at least * the 486 DX works this way. + * Xen pv domains are not using the default __KERNEL_CS. */ - if (regs->cs != __KERNEL_CS) + if (!xen_pv_domain() && regs->cs != __KERNEL_CS) goto fail; /* diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 78ca9a8ee454..06fe3d51d385 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -701,7 +701,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, else printk(KERN_CONT "paging request"); - printk(KERN_CONT " at %p\n", (void *) address); + printk(KERN_CONT " at %px\n", (void *) address); printk(KERN_ALERT "IP: %pS\n", (void *)regs->ip); dump_pagetable(address); @@ -860,7 +860,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p sp %p error %lx", + printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 6e4573b1da34..c45b6ec5357b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -404,11 +404,11 @@ void iounmap(volatile void __iomem *addr) return; } + mmiotrace_iounmap(addr); + addr = (volatile void __iomem *) (PAGE_MASK & (unsigned long __force)addr); - mmiotrace_iounmap(addr); - /* Use the vm area unlocked, assuming the caller ensures there isn't another iounmap for the same address in parallel. Reuse of the virtual address is prevented by diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 99dfed6dfef8..9ec70d780f1f 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -277,6 +277,7 @@ void __init kasan_early_init(void) void __init kasan_init(void) { int i; + void *shadow_cpu_entry_begin, *shadow_cpu_entry_end; #ifdef CONFIG_KASAN_INLINE register_die_notifier(&kasan_die_notifier); @@ -329,8 +330,23 @@ void __init kasan_init(void) (unsigned long)kasan_mem_to_shadow(_end), early_pfn_to_nid(__pa(_stext))); + shadow_cpu_entry_begin = (void *)__fix_to_virt(FIX_CPU_ENTRY_AREA_BOTTOM); + shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin); + shadow_cpu_entry_begin = (void *)round_down((unsigned long)shadow_cpu_entry_begin, + PAGE_SIZE); + + shadow_cpu_entry_end = (void *)(__fix_to_virt(FIX_CPU_ENTRY_AREA_TOP) + PAGE_SIZE); + shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end); + shadow_cpu_entry_end = (void *)round_up((unsigned long)shadow_cpu_entry_end, + PAGE_SIZE); + kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), - (void *)KASAN_SHADOW_END); + shadow_cpu_entry_begin); + + kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin, + (unsigned long)shadow_cpu_entry_end, 0); + + kasan_populate_zero_shadow(shadow_cpu_entry_end, (void *)KASAN_SHADOW_END); load_cr3(init_top_pgt); __flush_tlb_all(); diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/error.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/error.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/opcode.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/opcode.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/pte.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/pte.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/selftest.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/selftest.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/shadow.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index c21c2ed04612..58477ec3d66d 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -435,17 +435,18 @@ int register_kmmio_probe(struct kmmio_probe *p) unsigned long flags; int ret = 0; unsigned long size = 0; + unsigned long addr = p->addr & PAGE_MASK; const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); unsigned int l; pte_t *pte; spin_lock_irqsave(&kmmio_lock, flags); - if (get_kmmio_probe(p->addr)) { + if (get_kmmio_probe(addr)) { ret = -EEXIST; goto out; } - pte = lookup_address(p->addr, &l); + pte = lookup_address(addr, &l); if (!pte) { ret = -EINVAL; goto out; @@ -454,7 +455,7 @@ int register_kmmio_probe(struct kmmio_probe *p) kmmio_count++; list_add_rcu(&p->list, &kmmio_probes); while (size < size_lim) { - if (add_kmmio_fault_page(p->addr + size)) + if (add_kmmio_fault_page(addr + size)) pr_err("Unable to set page fault.\n"); size += page_level_size(l); } @@ -528,19 +529,20 @@ void unregister_kmmio_probe(struct kmmio_probe *p) { unsigned long flags; unsigned long size = 0; + unsigned long addr = p->addr & PAGE_MASK; const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); struct kmmio_fault_page *release_list = NULL; struct kmmio_delayed_release *drelease; unsigned int l; pte_t *pte; - pte = lookup_address(p->addr, &l); + pte = lookup_address(addr, &l); if (!pte) return; spin_lock_irqsave(&kmmio_lock, flags); while (size < size_lim) { - release_kmmio_fault_page(p->addr + size, &release_list); + release_kmmio_fault_page(addr + size, &release_list); size += page_level_size(l); } list_del_rcu(&p->list); diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c index bb461cfd01ab..526536c81ddc 100644 --- a/arch/x86/pci/broadcom_bus.c +++ b/arch/x86/pci/broadcom_bus.c @@ -97,7 +97,7 @@ static int __init broadcom_postcore_init(void) * We should get host bridge information from ACPI unless the BIOS * doesn't support it. */ - if (acpi_os_get_root_pointer()) + if (!acpi_disabled && acpi_os_get_root_pointer()) return 0; #endif diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 1e996df687a3..e663d6bf1328 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -665,6 +665,16 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) unsigned i; u32 base, limit, high; struct resource *res, *conflict; + struct pci_dev *other; + + /* Check that we are the only device of that type */ + other = pci_get_device(dev->vendor, dev->device, NULL); + if (other != dev || + (other = pci_get_device(dev->vendor, dev->device, other))) { + /* This is a multi-socket system, don't touch it for now */ + pci_dev_put(other); + return; + } for (i = 0; i < 8; i++) { pci_read_config_dword(dev, AMD_141b_MMIO_BASE(i), &base); @@ -696,8 +706,13 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) res->end = 0xfd00000000ull - 1; /* Just grab the free area behind system memory for this */ - while ((conflict = request_resource_conflict(&iomem_resource, res))) + while ((conflict = request_resource_conflict(&iomem_resource, res))) { + if (conflict->end >= res->end) { + kfree(res); + return; + } res->start = conflict->end + 1; + } dev_info(&dev->dev, "adding root bus resource %pR\n", res); @@ -714,10 +729,10 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) pci_bus_add_resource(dev->bus, res, 0); } -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); #endif diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index c34bd8233f7c..5f64f30873e2 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -905,7 +905,7 @@ static inline void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master) /* * UV NMI handler */ -int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) +static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) { struct uv_hub_nmi_s *hub_nmi = uv_hub_nmi; int cpu = smp_processor_id(); @@ -1013,7 +1013,7 @@ void uv_nmi_init(void) } /* Setup HUB NMI info */ -void __init uv_nmi_setup_common(bool hubbed) +static void __init uv_nmi_setup_common(bool hubbed) { int size = sizeof(void *) * (1 << NODES_SHIFT); int cpu; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 84fcfde53f8f..a7d966964c6f 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -82,12 +82,8 @@ static void __save_processor_state(struct saved_context *ctxt) /* * descriptor tables */ -#ifdef CONFIG_X86_32 store_idt(&ctxt->idt); -#else -/* CONFIG_X86_64 */ - store_idt((struct desc_ptr *)&ctxt->idt_limit); -#endif + /* * We save it here, but restore it only in the hibernate case. * For ACPI S3 resume, this is loaded via 'early_gdt_desc' in 64-bit @@ -103,22 +99,18 @@ static void __save_processor_state(struct saved_context *ctxt) /* * segment registers */ -#ifdef CONFIG_X86_32 - savesegment(es, ctxt->es); - savesegment(fs, ctxt->fs); +#ifdef CONFIG_X86_32_LAZY_GS savesegment(gs, ctxt->gs); - savesegment(ss, ctxt->ss); -#else -/* CONFIG_X86_64 */ - asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds)); - asm volatile ("movw %%es, %0" : "=m" (ctxt->es)); - asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs)); - asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs)); - asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss)); +#endif +#ifdef CONFIG_X86_64 + savesegment(gs, ctxt->gs); + savesegment(fs, ctxt->fs); + savesegment(ds, ctxt->ds); + savesegment(es, ctxt->es); rdmsrl(MSR_FS_BASE, ctxt->fs_base); - rdmsrl(MSR_GS_BASE, ctxt->gs_base); - rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base); + rdmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base); + rdmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base); mtrr_save_fixed_ranges(NULL); rdmsrl(MSR_EFER, ctxt->efer); @@ -160,17 +152,19 @@ static void do_fpu_end(void) static void fix_processor_context(void) { int cpu = smp_processor_id(); - struct tss_struct *t = &per_cpu(cpu_tss, cpu); #ifdef CONFIG_X86_64 struct desc_struct *desc = get_cpu_gdt_rw(cpu); tss_desc tss; #endif - set_tss_desc(cpu, t); /* - * This just modifies memory; should not be - * necessary. But... This is necessary, because - * 386 hardware has concept of busy TSS or some - * similar stupidity. - */ + + /* + * We need to reload TR, which requires that we change the + * GDT entry to indicate "available" first. + * + * XXX: This could probably all be replaced by a call to + * force_reload_TR(). + */ + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); #ifdef CONFIG_X86_64 memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc)); @@ -178,6 +172,9 @@ static void fix_processor_context(void) write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS); syscall_init(); /* This sets MSR_*STAR and related */ +#else + if (boot_cpu_has(X86_FEATURE_SEP)) + enable_sep_cpu(); #endif load_TR_desc(); /* This does ltr */ load_mm_ldt(current->active_mm); /* This does lldt */ @@ -190,9 +187,12 @@ static void fix_processor_context(void) } /** - * __restore_processor_state - restore the contents of CPU registers saved - * by __save_processor_state() - * @ctxt - structure to load the registers contents from + * __restore_processor_state - restore the contents of CPU registers saved + * by __save_processor_state() + * @ctxt - structure to load the registers contents from + * + * The asm code that gets us here will have restored a usable GDT, although + * it will be pointing to the wrong alias. */ static void notrace __restore_processor_state(struct saved_context *ctxt) { @@ -215,46 +215,52 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) write_cr2(ctxt->cr2); write_cr0(ctxt->cr0); + /* Restore the IDT. */ + load_idt(&ctxt->idt); + /* - * now restore the descriptor tables to their proper values - * ltr is done i fix_processor_context(). + * Just in case the asm code got us here with the SS, DS, or ES + * out of sync with the GDT, update them. */ -#ifdef CONFIG_X86_32 - load_idt(&ctxt->idt); + loadsegment(ss, __KERNEL_DS); + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); + + /* + * Restore percpu access. Percpu access can happen in exception + * handlers or in complicated helpers like load_gs_index(). + */ +#ifdef CONFIG_X86_64 + wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base); #else -/* CONFIG_X86_64 */ - load_idt((const struct desc_ptr *)&ctxt->idt_limit); + loadsegment(fs, __KERNEL_PERCPU); + loadsegment(gs, __KERNEL_STACK_CANARY); #endif + /* Restore the TSS, RO GDT, LDT, and usermode-relevant MSRs. */ + fix_processor_context(); + /* - * segment registers + * Now that we have descriptor tables fully restored and working + * exception handling, restore the usermode segments. */ -#ifdef CONFIG_X86_32 +#ifdef CONFIG_X86_64 + loadsegment(ds, ctxt->es); loadsegment(es, ctxt->es); loadsegment(fs, ctxt->fs); - loadsegment(gs, ctxt->gs); - loadsegment(ss, ctxt->ss); + load_gs_index(ctxt->gs); /* - * sysenter MSRs + * Restore FSBASE and GSBASE after restoring the selectors, since + * restoring the selectors clobbers the bases. Keep in mind + * that MSR_KERNEL_GS_BASE is horribly misnamed. */ - if (boot_cpu_has(X86_FEATURE_SEP)) - enable_sep_cpu(); -#else -/* CONFIG_X86_64 */ - asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds)); - asm volatile ("movw %0, %%es" :: "r" (ctxt->es)); - asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs)); - load_gs_index(ctxt->gs); - asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss)); - wrmsrl(MSR_FS_BASE, ctxt->fs_base); - wrmsrl(MSR_GS_BASE, ctxt->gs_base); - wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base); + wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base); +#elif defined(CONFIG_X86_32_LAZY_GS) + loadsegment(gs, ctxt->gs); #endif - fix_processor_context(); - do_fpu_end(); tsc_verify_tsc_adjust(true); x86_platform.restore_sched_clock_state(); diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 6b830d4cb4c8..de58533d3664 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -57,7 +57,7 @@ static u32 xen_apic_read(u32 reg) return 0; if (reg == APIC_LVR) - return 0x10; + return 0x14; #ifdef CONFIG_X86_32 if (reg == APIC_LDR) return SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 5b2b3f3f6531..7beeee1443b3 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -622,7 +622,7 @@ static struct trap_array_entry trap_array[] = { { simd_coprocessor_error, xen_simd_coprocessor_error, false }, }; -static bool get_trap_addr(void **addr, unsigned int ist) +static bool __ref get_trap_addr(void **addr, unsigned int ist) { unsigned int nr; bool ist_okay = false; @@ -644,6 +644,14 @@ static bool get_trap_addr(void **addr, unsigned int ist) } } + if (nr == ARRAY_SIZE(trap_array) && + *addr >= (void *)early_idt_handler_array[0] && + *addr < (void *)early_idt_handler_array[NUM_EXCEPTION_VECTORS]) { + nr = (*addr - (void *)early_idt_handler_array[0]) / + EARLY_IDT_HANDLER_SIZE; + *addr = (void *)xen_early_idt_handler_array[nr]; + } + if (WARN_ON(ist != 0 && !ist_okay)) return false; @@ -818,7 +826,7 @@ static void xen_load_sp0(unsigned long sp0) mcs = xen_mc_entry(0); MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0); xen_mc_issue(PARAVIRT_LAZY_CPU); - this_cpu_write(cpu_tss.x86_tss.sp0, sp0); + this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } void xen_set_iopl_mask(unsigned mask) @@ -1262,6 +1270,21 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_setup_gdt(0); xen_init_irq_ops(); + + /* Let's presume PV guests always boot on vCPU with id 0. */ + per_cpu(xen_vcpu_id, 0) = 0; + + /* + * Setup xen_vcpu early because idt_setup_early_handler needs it for + * local_irq_disable(), irqs_disabled(). + * + * Don't do the full vcpu_info placement stuff until we have + * the cpu_possible_mask and a non-dummy shared_info. + */ + xen_vcpu_info_reset(0); + + idt_setup_early_handler(); + xen_init_capabilities(); #ifdef CONFIG_X86_LOCAL_APIC @@ -1295,18 +1318,6 @@ asmlinkage __visible void __init xen_start_kernel(void) */ acpi_numa = -1; #endif - /* Let's presume PV guests always boot on vCPU with id 0. */ - per_cpu(xen_vcpu_id, 0) = 0; - - /* - * Setup xen_vcpu early because start_kernel needs it for - * local_irq_disable(), irqs_disabled(). - * - * Don't do the full vcpu_info placement stuff until we have - * the cpu_possible_mask and a non-dummy shared_info. - */ - xen_vcpu_info_reset(0); - WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv)); local_irq_disable(); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index fc048ec686e7..6cf801ca1142 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2272,7 +2272,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #endif case FIX_TEXT_POKE0: case FIX_TEXT_POKE1: - case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END: + case FIX_CPU_ENTRY_AREA_TOP ... FIX_CPU_ENTRY_AREA_BOTTOM: /* All local page mappings */ pte = pfn_pte(phys, prot); break; diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 8a10c9a9e2b5..417b339e5c8e 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -15,6 +15,7 @@ #include <xen/interface/xen.h> +#include <linux/init.h> #include <linux/linkage.h> .macro xen_pv_trap name @@ -54,6 +55,19 @@ xen_pv_trap entry_INT80_compat #endif xen_pv_trap hypervisor_callback + __INIT +ENTRY(xen_early_idt_handler_array) + i = 0 + .rept NUM_EXCEPTION_VECTORS + pop %rcx + pop %r11 + jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE + i = i + 1 + .fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc + .endr +END(xen_early_idt_handler_array) + __FINIT + hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* * Xen64 iret frame: diff --git a/arch/xtensa/include/uapi/asm/Kbuild b/arch/xtensa/include/uapi/asm/Kbuild index a5bcdfb890f1..837d4dd76785 100644 --- a/arch/xtensa/include/uapi/asm/Kbuild +++ b/arch/xtensa/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h |
