diff options
Diffstat (limited to 'arch')
195 files changed, 3051 insertions, 1128 deletions
diff --git a/arch/alpha/kernel/pci_impl.h b/arch/alpha/kernel/pci_impl.h index 2b0ac429f5eb..412bb3c24f36 100644 --- a/arch/alpha/kernel/pci_impl.h +++ b/arch/alpha/kernel/pci_impl.h @@ -143,7 +143,8 @@ struct pci_iommu_arena }; #if defined(CONFIG_ALPHA_SRM) && \ - (defined(CONFIG_ALPHA_CIA) || defined(CONFIG_ALPHA_LCA)) + (defined(CONFIG_ALPHA_CIA) || defined(CONFIG_ALPHA_LCA) || \ + defined(CONFIG_ALPHA_AVANTI)) # define NEED_SRM_SAVE_RESTORE #else # undef NEED_SRM_SAVE_RESTORE diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index b483156698d5..60c17b9bf04d 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -265,12 +265,13 @@ copy_thread(unsigned long clone_flags, unsigned long usp, application calling fork. */ if (clone_flags & CLONE_SETTLS) childti->pcb.unique = regs->r20; + else + regs->r20 = 0; /* OSF/1 has some strange fork() semantics. */ childti->pcb.usp = usp ?: rdusp(); *childregs = *regs; childregs->r0 = 0; childregs->r19 = 0; childregs->r20 = 1; /* OSF/1 has some strange fork() semantics. */ - regs->r20 = 0; stack = ((struct switch_stack *) regs) - 1; *childstack = *stack; childstack->r26 = (unsigned long) ret_from_fork; diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 74aceead06e9..32ba92cdf5f6 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -158,11 +158,16 @@ void show_stack(struct task_struct *task, unsigned long *sp) for(i=0; i < kstack_depth_to_print; i++) { if (((long) stack & (THREAD_SIZE-1)) == 0) break; - if (i && ((i % 4) == 0)) - printk("\n "); - printk("%016lx ", *stack++); + if ((i % 4) == 0) { + if (i) + pr_cont("\n"); + printk(" "); + } else { + pr_cont(" "); + } + pr_cont("%016lx", *stack++); } - printk("\n"); + pr_cont("\n"); dik_show_trace(sp); } diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index a20a71d9d22e..c9c9a47446e8 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -926,7 +926,8 @@ 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>, @@ -940,7 +941,8 @@ 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/arm-realview-eb-mp.dtsi b/arch/arm/boot/dts/arm-realview-eb-mp.dtsi index 7b8d90b7aeea..29b636fce23f 100644 --- a/arch/arm/boot/dts/arm-realview-eb-mp.dtsi +++ b/arch/arm/boot/dts/arm-realview-eb-mp.dtsi @@ -150,11 +150,6 @@ interrupts = <0 8 IRQ_TYPE_LEVEL_HIGH>; }; -&charlcd { - interrupt-parent = <&intc>; - interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; -}; - &serial0 { interrupt-parent = <&intc>; interrupts = <0 4 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi index 7c9e0fae9bb9..65e0db1d3bd7 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/exynos5410.dtsi b/arch/arm/boot/dts/exynos5410.dtsi index 137f48464f8b..bb59fee072c0 100644 --- a/arch/arm/boot/dts/exynos5410.dtsi +++ b/arch/arm/boot/dts/exynos5410.dtsi @@ -274,7 +274,6 @@ &rtc { clocks = <&clock CLK_RTC>; clock-names = "rtc"; - interrupt-parent = <&pmu_system_controller>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts index cf2f5240e176..27cc913ca0f5 100644 --- a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts +++ b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts @@ -53,7 +53,8 @@ }; pinctrl: pin-controller@10000 { - pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header>; + pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header + &pmx_gpio_header_gpo>; pinctrl-names = "default"; pmx_uart0: pmx-uart0 { @@ -85,11 +86,16 @@ * ground. */ pmx_gpio_header: pmx-gpio-header { - marvell,pins = "mpp17", "mpp7", "mpp29", "mpp28", + marvell,pins = "mpp17", "mpp29", "mpp28", "mpp35", "mpp34", "mpp40"; marvell,function = "gpio"; }; + pmx_gpio_header_gpo: pxm-gpio-header-gpo { + marvell,pins = "mpp7"; + marvell,function = "gpo"; + }; + pmx_gpio_init: pmx-init { marvell,pins = "mpp38"; marvell,function = "gpio"; 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..4f2c5ec75714 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -37,7 +37,7 @@ }; &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 +121,7 @@ &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 +132,8 @@ 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 +157,6 @@ 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 +226,12 @@ 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/lpc3250-ea3250.dts b/arch/arm/boot/dts/lpc3250-ea3250.dts index 52b3ed10283a..e2bc731079be 100644 --- a/arch/arm/boot/dts/lpc3250-ea3250.dts +++ b/arch/arm/boot/dts/lpc3250-ea3250.dts @@ -156,8 +156,8 @@ uda1380: uda1380@18 { compatible = "nxp,uda1380"; reg = <0x18>; - power-gpio = <&gpio 0x59 0>; - reset-gpio = <&gpio 0x51 0>; + power-gpio = <&gpio 3 10 0>; + reset-gpio = <&gpio 3 2 0>; dac-clk = "wspll"; }; diff --git a/arch/arm/boot/dts/lpc3250-phy3250.dts b/arch/arm/boot/dts/lpc3250-phy3250.dts index fd95e2b10357..b7bd3a110a8d 100644 --- a/arch/arm/boot/dts/lpc3250-phy3250.dts +++ b/arch/arm/boot/dts/lpc3250-phy3250.dts @@ -81,8 +81,8 @@ uda1380: uda1380@18 { compatible = "nxp,uda1380"; reg = <0x18>; - power-gpio = <&gpio 0x59 0>; - reset-gpio = <&gpio 0x51 0>; + power-gpio = <&gpio 3 10 0>; + reset-gpio = <&gpio 3 2 0>; dac-clk = "wspll"; }; diff --git a/arch/arm/boot/dts/mt2701.dtsi b/arch/arm/boot/dts/mt2701.dtsi index 77c6b931dc24..23fe0497f708 100644 --- a/arch/arm/boot/dts/mt2701.dtsi +++ b/arch/arm/boot/dts/mt2701.dtsi @@ -197,12 +197,14 @@ compatible = "mediatek,mt2701-hifsys", "syscon"; reg = <0 0x1a000000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; ethsys: syscon@1b000000 { compatible = "mediatek,mt2701-ethsys", "syscon"; reg = <0 0x1b000000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; bdpsys: syscon@1c000000 { diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index 9c289ddab3df..4d6584f15b17 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -352,7 +352,7 @@ 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"; }; @@ -859,14 +859,12 @@ usbhsohci: ohci@4a064800 { compatible = "ti,ohci-omap3"; reg = <0x4a064800 0x400>; - interrupt-parent = <&gic>; interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>; }; 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/s5pv210.dtsi b/arch/arm/boot/dts/s5pv210.dtsi index a853918be43f..0c10ba517cd0 100644 --- a/arch/arm/boot/dts/s5pv210.dtsi +++ b/arch/arm/boot/dts/s5pv210.dtsi @@ -463,6 +463,7 @@ compatible = "samsung,exynos4210-ohci"; reg = <0xec300000 0x100>; interrupts = <23>; + interrupt-parent = <&vic1>; clocks = <&clocks CLK_USB_HOST>; clock-names = "usbhost"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/spear1310-evb.dts b/arch/arm/boot/dts/spear1310-evb.dts index 84101e4eebbf..0f5f379323a8 100644 --- a/arch/arm/boot/dts/spear1310-evb.dts +++ b/arch/arm/boot/dts/spear1310-evb.dts @@ -349,7 +349,7 @@ spi0: spi@e0100000 { status = "okay"; num-cs = <3>; - cs-gpios = <&gpio1 7 0>, <&spics 0>, <&spics 1>; + cs-gpios = <&gpio1 7 0>, <&spics 0 0>, <&spics 1 0>; stmpe610@0 { compatible = "st,stmpe610"; diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi index df2232d767ed..6361cbfcbe5e 100644 --- a/arch/arm/boot/dts/spear1340.dtsi +++ b/arch/arm/boot/dts/spear1340.dtsi @@ -141,8 +141,8 @@ reg = <0xb4100000 0x1000>; interrupts = <0 105 0x4>; status = "disabled"; - dmas = <&dwdma0 0x600 0 0 1>, /* 0xC << 11 */ - <&dwdma0 0x680 0 1 0>; /* 0xD << 7 */ + dmas = <&dwdma0 12 0 1>, + <&dwdma0 13 1 0>; dma-names = "tx", "rx"; }; diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi index 449acf0d8272..9564337c1815 100644 --- a/arch/arm/boot/dts/spear13xx.dtsi +++ b/arch/arm/boot/dts/spear13xx.dtsi @@ -100,7 +100,7 @@ reg = <0xb2800000 0x1000>; interrupts = <0 29 0x4>; status = "disabled"; - dmas = <&dwdma0 0 0 0 0>; + dmas = <&dwdma0 0 0 0>; dma-names = "data"; }; @@ -288,8 +288,8 @@ #size-cells = <0>; interrupts = <0 31 0x4>; status = "disabled"; - dmas = <&dwdma0 0x2000 0 0 0>, /* 0x4 << 11 */ - <&dwdma0 0x0280 0 0 0>; /* 0x5 << 7 */ + dmas = <&dwdma0 4 0 0>, + <&dwdma0 5 0 0>; dma-names = "tx", "rx"; }; diff --git a/arch/arm/boot/dts/spear600.dtsi b/arch/arm/boot/dts/spear600.dtsi index 9f60a7b6a42b..bd379034993c 100644 --- a/arch/arm/boot/dts/spear600.dtsi +++ b/arch/arm/boot/dts/spear600.dtsi @@ -194,6 +194,7 @@ rtc@fc900000 { compatible = "st,spear600-rtc"; reg = <0xfc900000 0x1000>; + interrupt-parent = <&vic0>; interrupts = <10>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index adb1c0998b81..1077ceebb2d6 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -749,6 +749,7 @@ reg = <0x10120000 0x1000>; interrupt-names = "combined"; interrupts = <14>; + interrupt-parent = <&vica>; clocks = <&clcdclk>, <&hclkclcd>; clock-names = "clcdclk", "apb_pclk"; status = "disabled"; diff --git a/arch/arm/boot/dts/stih407.dtsi b/arch/arm/boot/dts/stih407.dtsi index 291ffacbd2e0..fe043d313ccd 100644 --- a/arch/arm/boot/dts/stih407.dtsi +++ b/arch/arm/boot/dts/stih407.dtsi @@ -8,6 +8,7 @@ */ #include "stih407-clock.dtsi" #include "stih407-family.dtsi" +#include <dt-bindings/gpio/gpio.h> / { soc { sti-display-subsystem { @@ -122,7 +123,7 @@ <&clk_s_d2_quadfs 0>, <&clk_s_d2_quadfs 1>; - hdmi,hpd-gpio = <&pio5 3>; + hdmi,hpd-gpio = <&pio5 3 GPIO_ACTIVE_LOW>; reset-names = "hdmi"; resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>; ddc = <&hdmiddc>; diff --git a/arch/arm/boot/dts/stih410.dtsi b/arch/arm/boot/dts/stih410.dtsi index 4d329b2908be..3c118fc2bf61 100644 --- a/arch/arm/boot/dts/stih410.dtsi +++ b/arch/arm/boot/dts/stih410.dtsi @@ -9,6 +9,7 @@ #include "stih410-clock.dtsi" #include "stih407-family.dtsi" #include "stih410-pinctrl.dtsi" +#include <dt-bindings/gpio/gpio.h> / { aliases { bdisp0 = &bdisp0; @@ -213,7 +214,7 @@ <&clk_s_d2_quadfs 0>, <&clk_s_d2_quadfs 1>; - hdmi,hpd-gpio = <&pio5 3>; + hdmi,hpd-gpio = <&pio5 3 GPIO_ACTIVE_LOW>; reset-names = "hdmi"; resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>; ddc = <&hdmiddc>; diff --git a/arch/arm/common/bL_switcher_dummy_if.c b/arch/arm/common/bL_switcher_dummy_if.c index 6053f64c3752..94133e33943c 100644 --- a/arch/arm/common/bL_switcher_dummy_if.c +++ b/arch/arm/common/bL_switcher_dummy_if.c @@ -57,3 +57,7 @@ static struct miscdevice bL_switcher_device = { &bL_switcher_fops }; module_misc_device(bL_switcher_device); + +MODULE_AUTHOR("Nicolas Pitre <nico@linaro.org>"); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("big.LITTLE switcher dummy user interface"); diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index 714da336ec86..5d49b60841e3 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -11,6 +11,7 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 CONFIG_AEABI=y CONFIG_HIGHMEM=y +CONFIG_CMA=y CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_CPU_FREQ=y @@ -35,6 +36,7 @@ CONFIG_CAN_SUN4I=y # CONFIG_WIRELESS is not set CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y +CONFIG_DMA_CMA=y CONFIG_BLK_DEV_SD=y CONFIG_ATA=y CONFIG_AHCI_SUNXI=y diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 19b5f5c1c0ff..c38bfbeec306 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -1165,6 +1165,7 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self, cpu_hyp_reset(); return NOTIFY_OK; + case CPU_PM_ENTER_FAILED: case CPU_PM_EXIT: if (__this_cpu_read(kvm_arm_hardware_enabled)) /* The hardware was enabled before suspend. */ diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index 42f5daf715d0..4e57ebca6e69 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -38,7 +38,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_psci_call(vcpu); if (ret < 0) { - kvm_inject_undefined(vcpu); + vcpu_set_reg(vcpu, 0, ~0UL); return 1; } @@ -47,7 +47,16 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) { - kvm_inject_undefined(vcpu); + /* + * "If an SMC instruction executed at Non-secure EL1 is + * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a + * Trap exception, not a Secure Monitor Call exception [...]" + * + * We need to advance the PC after the trap, as it would + * otherwise return to the same address... + */ + vcpu_set_reg(vcpu, 0, ~0UL); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); return 1; } diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index b6e715fd3c90..dac7ceb1a677 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -112,7 +112,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) } trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, - data); + &data); data = vcpu_data_host_to_guest(vcpu, data, len); vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data); } @@ -182,14 +182,14 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt), len); - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, &data); kvm_mmio_write_buf(data_buf, len, data); ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len, data_buf); } else { trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, - fault_ipa, 0); + fault_ipa, NULL); ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len, data_buf); diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 2206e0e00934..2a35c1963f6d 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1284,7 +1284,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } - if (is_vm_hugetlb_page(vma) && !logging_active) { + if (vma_kernel_pagesize(vma) && !logging_active) { hugetlb = true; gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT; } else { diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c index 5ac122e88f67..9ff92050053c 100644 --- a/arch/arm/mach-omap2/omap-secure.c +++ b/arch/arm/mach-omap2/omap-secure.c @@ -73,6 +73,25 @@ phys_addr_t omap_secure_ram_mempool_base(void) return omap_secure_memblock_base; } +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; +} + /** * 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/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 d44e0e2f1106..3836958074ac 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) @@ -554,7 +549,7 @@ 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/prm33xx.c b/arch/arm/mach-omap2/prm33xx.c index dcb5001d77da..973bcd754e1c 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 1b9f0520dea9..3e0d802c59da 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/arm/mach-pxa/tosa-bt.c b/arch/arm/mach-pxa/tosa-bt.c index 107f37210fb9..83606087edc7 100644 --- a/arch/arm/mach-pxa/tosa-bt.c +++ b/arch/arm/mach-pxa/tosa-bt.c @@ -132,3 +132,7 @@ static struct platform_driver tosa_bt_driver = { }, }; module_platform_driver(tosa_bt_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Dmitry Baryshkov"); +MODULE_DESCRIPTION("Bluetooth built-in chip control"); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index cf57a7799a0f..7769c2e27788 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1007,7 +1007,7 @@ source "fs/Kconfig.binfmt" config COMPAT bool "Kernel support for 32-bit EL0" depends on ARM64_4K_PAGES || EXPERT - select COMPAT_BINFMT_ELF + select COMPAT_BINFMT_ELF if BINFMT_ELF select HAVE_UID16 select OLD_SIGSUSPEND3 select COMPAT_OLD_SIGACTION diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 101794f5ce10..08a4497f70a6 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -2,9 +2,11 @@ menu "Platform selection" config ARCH_SUNXI bool "Allwinner sunxi 64-bit SoC Family" + select ARCH_HAS_RESET_CONTROLLER select GENERIC_IRQ_CHIP select PINCTRL select PINCTRL_SUN50I_A64 + select RESET_CONTROLLER help This enables support for Allwinner sunxi based SoCs like the A64. diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi index 6c03c1702bb3..b307d6b6357e 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi @@ -73,6 +73,7 @@ reg = <0x000>; enable-method = "psci"; cpu-idle-states = <&CPU_SLEEP_0>; + #cooling-cells = <2>; }; cpu1: cpu@1 { @@ -89,6 +90,7 @@ reg = <0x100>; enable-method = "psci"; cpu-idle-states = <&CPU_SLEEP_0>; + #cooling-cells = <2>; }; cpu3: cpu@101 { diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index 466ca5705c99..08b88f6791be 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -796,6 +796,7 @@ "dsi_phy_regulator"; #clock-cells = <1>; + #phy-cells = <0>; clocks = <&gcc GCC_MDSS_AHB_CLK>; clock-names = "iface_clk"; @@ -906,8 +907,8 @@ #address-cells = <1>; #size-cells = <0>; - qcom,ipc-1 = <&apcs 0 13>; - qcom,ipc-6 = <&apcs 0 19>; + qcom,ipc-1 = <&apcs 8 13>; + qcom,ipc-3 = <&apcs 8 19>; apps_smsm: apps@0 { reg = <0>; diff --git a/arch/arm64/crypto/crc32-arm64.c b/arch/arm64/crypto/crc32-arm64.c index 6a37c3c6b11d..3ec568afd1d3 100644 --- a/arch/arm64/crypto/crc32-arm64.c +++ b/arch/arm64/crypto/crc32-arm64.c @@ -232,6 +232,7 @@ static struct shash_alg crc32_alg = { .cra_name = "crc32", .cra_driver_name = "crc32-arm64-hw", .cra_priority = 300, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .cra_blocksize = CHKSUM_BLOCK_SIZE, .cra_alignmask = 0, .cra_ctxsize = sizeof(struct chksum_ctx), @@ -253,6 +254,7 @@ static struct shash_alg crc32c_alg = { .cra_name = "crc32c", .cra_driver_name = "crc32c-arm64-hw", .cra_priority = 300, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .cra_blocksize = CHKSUM_BLOCK_SIZE, .cra_alignmask = 0, .cra_ctxsize = sizeof(struct chksum_ctx), diff --git a/arch/arm64/include/asm/bug.h b/arch/arm64/include/asm/bug.h index 561190d15881..0bfe1df12b19 100644 --- a/arch/arm64/include/asm/bug.h +++ b/arch/arm64/include/asm/bug.h @@ -20,9 +20,6 @@ #include <asm/brk-imm.h> -#ifdef CONFIG_GENERIC_BUG -#define HAVE_ARCH_BUG - #ifdef CONFIG_DEBUG_BUGVERBOSE #define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line) #define __BUGVERBOSE_LOCATION(file, line) \ @@ -36,28 +33,36 @@ #define _BUGVERBOSE_LOCATION(file, line) #endif -#define _BUG_FLAGS(flags) __BUG_FLAGS(flags) +#ifdef CONFIG_GENERIC_BUG -#define __BUG_FLAGS(flags) asm volatile ( \ +#define __BUG_ENTRY(flags) \ ".pushsection __bug_table,\"a\"\n\t" \ ".align 2\n\t" \ "0: .long 1f - 0b\n\t" \ _BUGVERBOSE_LOCATION(__FILE__, __LINE__) \ ".short " #flags "\n\t" \ ".popsection\n" \ - \ - "1: brk %[imm]" \ - :: [imm] "i" (BUG_BRK_IMM) \ -) + "1: " +#else +#define __BUG_ENTRY(flags) "" +#endif + +#define __BUG_FLAGS(flags) \ + asm volatile ( \ + __BUG_ENTRY(flags) \ + "brk %[imm]" :: [imm] "i" (BUG_BRK_IMM) \ + ); -#define BUG() do { \ - _BUG_FLAGS(0); \ - unreachable(); \ + +#define BUG() do { \ + __BUG_FLAGS(0); \ + unreachable(); \ } while (0) -#define __WARN_TAINT(taint) _BUG_FLAGS(BUGFLAG_TAINT(taint)) +#define __WARN_TAINT(taint) \ + __BUG_FLAGS(BUGFLAG_TAINT(taint)) -#endif /* ! CONFIG_GENERIC_BUG */ +#define HAVE_ARCH_BUG #include <asm-generic/bug.h> diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 85baadab02d3..2e6e9e99977b 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -44,7 +44,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_psci_call(vcpu); if (ret < 0) { - kvm_inject_undefined(vcpu); + vcpu_set_reg(vcpu, 0, ~0UL); return 1; } @@ -53,7 +53,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) { - kvm_inject_undefined(vcpu); + vcpu_set_reg(vcpu, 0, ~0UL); return 1; } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 05615a3fdc6f..d5cc6d73c2c4 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -479,7 +479,7 @@ void __init paging_init(void) * To do this we need to go via a temporary pgd. */ cpu_replace_ttbr1(__va(pgd_phys)); - memcpy(swapper_pg_dir, pgd, PAGE_SIZE); + memcpy(swapper_pg_dir, pgd, PGD_SIZE); cpu_replace_ttbr1(swapper_pg_dir); pgd_clear_fixmap(); diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds index d2c8abf1c8c4..e958abe0f51e 100644 --- a/arch/m68k/kernel/vmlinux-nommu.lds +++ b/arch/m68k/kernel/vmlinux-nommu.lds @@ -44,6 +44,8 @@ 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 5b5ce1e4d1ed..1656ae8a145d 100644 --- a/arch/m68k/kernel/vmlinux-std.lds +++ b/arch/m68k/kernel/vmlinux-std.lds @@ -15,6 +15,8 @@ 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 fe5ea1974b16..07b9818b3176 100644 --- a/arch/m68k/kernel/vmlinux-sun3.lds +++ b/arch/m68k/kernel/vmlinux-sun3.lds @@ -15,6 +15,8 @@ SECTIONS .text : { HEAD_TEXT TEXT_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT SCHED_TEXT CPUIDLE_TEXT LOCK_TEXT diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 5e844f68e847..2d2fd79ced9d 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -112,12 +112,12 @@ config MIPS_GENERIC select SYS_SUPPORTS_MULTITHREADING select SYS_SUPPORTS_RELOCATABLE select SYS_SUPPORTS_SMARTMIPS - select USB_EHCI_BIG_ENDIAN_DESC if BIG_ENDIAN - select USB_EHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN - select USB_OHCI_BIG_ENDIAN_DESC if BIG_ENDIAN - select USB_OHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN - select USB_UHCI_BIG_ENDIAN_DESC if BIG_ENDIAN - select USB_UHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN + select USB_EHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN + select USB_EHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN + select USB_OHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN + select USB_OHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN + select USB_UHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN + select USB_UHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN select USE_OF help Select this to build a kernel which aims to support multiple boards, diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c index 3446b6fb3acb..9da4e2292fc7 100644 --- a/arch/mips/ar7/platform.c +++ b/arch/mips/ar7/platform.c @@ -576,7 +576,7 @@ static int __init ar7_register_uarts(void) uart_port.type = PORT_AR7; uart_port.uartclk = clk_get_rate(bus_clk) / 2; uart_port.iotype = UPIO_MEM32; - uart_port.flags = UPF_FIXED_TYPE; + uart_port.flags = UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF; uart_port.regshift = 2; uart_port.line = 0; diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index c558bce989cd..6e716a5f1173 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -683,6 +683,18 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) struct task_struct *t; int max_users; + /* If nothing to change, return right away, successfully. */ + if (value == mips_get_process_fp_mode(task)) + return 0; + + /* Only accept a mode change if 64-bit FP enabled for o32. */ + if (!IS_ENABLED(CONFIG_MIPS_O32_FP64_SUPPORT)) + return -EOPNOTSUPP; + + /* And only for o32 tasks. */ + if (IS_ENABLED(CONFIG_64BIT) && !test_thread_flag(TIF_32BIT_REGS)) + return -EOPNOTSUPP; + /* Check the value is valid */ if (value & ~known_bits) return -EOPNOTSUPP; diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 11890e6e4093..0c8ae2cc6380 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -439,63 +439,160 @@ static int gpr64_set(struct task_struct *target, #endif /* CONFIG_64BIT */ +/* + * Copy the floating-point context to the supplied NT_PRFPREG buffer, + * !CONFIG_CPU_HAS_MSA variant. FP context's general register slots + * correspond 1:1 to buffer slots. Only general registers are copied. + */ +static int fpr_get_fpa(struct task_struct *target, + unsigned int *pos, unsigned int *count, + void **kbuf, void __user **ubuf) +{ + return user_regset_copyout(pos, count, kbuf, ubuf, + &target->thread.fpu, + 0, NUM_FPU_REGS * sizeof(elf_fpreg_t)); +} + +/* + * Copy the floating-point context to the supplied NT_PRFPREG buffer, + * CONFIG_CPU_HAS_MSA variant. Only lower 64 bits of FP context's + * general register slots are copied to buffer slots. Only general + * registers are copied. + */ +static int fpr_get_msa(struct task_struct *target, + unsigned int *pos, unsigned int *count, + void **kbuf, void __user **ubuf) +{ + unsigned int i; + u64 fpr_val; + int err; + + BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t)); + for (i = 0; i < NUM_FPU_REGS; i++) { + fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0); + err = user_regset_copyout(pos, count, kbuf, ubuf, + &fpr_val, i * sizeof(elf_fpreg_t), + (i + 1) * sizeof(elf_fpreg_t)); + if (err) + return err; + } + + return 0; +} + +/* + * Copy the floating-point context to the supplied NT_PRFPREG buffer. + * Choose the appropriate helper for general registers, and then copy + * the FCSR register separately. + */ static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - unsigned i; + const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t); int err; - u64 fpr_val; - /* XXX fcr31 */ + if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t)) + err = fpr_get_fpa(target, &pos, &count, &kbuf, &ubuf); + else + err = fpr_get_msa(target, &pos, &count, &kbuf, &ubuf); + if (err) + return err; - if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t)) - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu, - 0, sizeof(elf_fpregset_t)); + err = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.fpu.fcr31, + fcr31_pos, fcr31_pos + sizeof(u32)); - for (i = 0; i < NUM_FPU_REGS; i++) { - fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0); - err = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &fpr_val, i * sizeof(elf_fpreg_t), - (i + 1) * sizeof(elf_fpreg_t)); + return err; +} + +/* + * Copy the supplied NT_PRFPREG buffer to the floating-point context, + * !CONFIG_CPU_HAS_MSA variant. Buffer slots correspond 1:1 to FP + * context's general register slots. Only general registers are copied. + */ +static int fpr_set_fpa(struct task_struct *target, + unsigned int *pos, unsigned int *count, + const void **kbuf, const void __user **ubuf) +{ + return user_regset_copyin(pos, count, kbuf, ubuf, + &target->thread.fpu, + 0, NUM_FPU_REGS * sizeof(elf_fpreg_t)); +} + +/* + * Copy the supplied NT_PRFPREG buffer to the floating-point context, + * CONFIG_CPU_HAS_MSA variant. Buffer slots are copied to lower 64 + * bits only of FP context's general register slots. Only general + * registers are copied. + */ +static int fpr_set_msa(struct task_struct *target, + unsigned int *pos, unsigned int *count, + const void **kbuf, const void __user **ubuf) +{ + unsigned int i; + u64 fpr_val; + int err; + + BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t)); + for (i = 0; i < NUM_FPU_REGS && *count > 0; i++) { + err = user_regset_copyin(pos, count, kbuf, ubuf, + &fpr_val, i * sizeof(elf_fpreg_t), + (i + 1) * sizeof(elf_fpreg_t)); if (err) return err; + set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val); } return 0; } +/* + * Copy the supplied NT_PRFPREG buffer to the floating-point context. + * Choose the appropriate helper for general registers, and then copy + * the FCSR register separately. + * + * We optimize for the case where `count % sizeof(elf_fpreg_t) == 0', + * which is supposed to have been guaranteed by the kernel before + * calling us, e.g. in `ptrace_regset'. We enforce that requirement, + * so that we can safely avoid preinitializing temporaries for + * partial register writes. + */ static int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - unsigned i; + const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t); + u32 fcr31; int err; - u64 fpr_val; - /* XXX fcr31 */ + BUG_ON(count % sizeof(elf_fpreg_t)); + + if (pos + count > sizeof(elf_fpregset_t)) + return -EIO; init_fp_ctx(target); - if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t)) - return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu, - 0, sizeof(elf_fpregset_t)); + if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t)) + err = fpr_set_fpa(target, &pos, &count, &kbuf, &ubuf); + else + err = fpr_set_msa(target, &pos, &count, &kbuf, &ubuf); + if (err) + return err; - BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t)); - for (i = 0; i < NUM_FPU_REGS && count >= sizeof(elf_fpreg_t); i++) { + if (count > 0) { err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &fpr_val, i * sizeof(elf_fpreg_t), - (i + 1) * sizeof(elf_fpreg_t)); + &fcr31, + fcr31_pos, fcr31_pos + sizeof(u32)); if (err) return err; - set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val); + + ptrace_setfcr31(target, fcr31); } - return 0; + return err; } enum mips_regset { diff --git a/arch/mn10300/mm/misalignment.c b/arch/mn10300/mm/misalignment.c index b9920b1edd5a..70cef54dc40f 100644 --- a/arch/mn10300/mm/misalignment.c +++ b/arch/mn10300/mm/misalignment.c @@ -437,7 +437,7 @@ transfer_failed: info.si_signo = SIGSEGV; info.si_errno = 0; - info.si_code = 0; + info.si_code = SEGV_MAPERR; info.si_addr = (void *) regs->pc; force_sig_info(SIGSEGV, &info, current); return; diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index 3d3f6062f49c..605a284922fb 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -302,12 +302,12 @@ asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address) siginfo_t info; if (user_mode(regs)) { - /* Send a SIGSEGV */ - info.si_signo = SIGSEGV; + /* Send a SIGBUS */ + info.si_signo = SIGBUS; info.si_errno = 0; - /* info.si_code has been set above */ - info.si_addr = (void *)address; - force_sig_info(SIGSEGV, &info, current); + info.si_code = BUS_ADRALN; + info.si_addr = (void __user *)address; + force_sig_info(SIGBUS, &info, current); } else { printk("KERNEL: Unaligned Access 0x%.8lx\n", address); show_registers(regs); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6eda5abbd719..0a6bb48854e3 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -128,6 +128,7 @@ config PPC select ARCH_HAS_GCOV_PROFILE_ALL select GENERIC_SMP_IDLE_THREAD select GENERIC_CMOS_UPDATE + select GENERIC_CPU_VULNERABILITIES if PPC_BOOK3S_64 select GENERIC_TIME_VSYSCALL_OLD select GENERIC_CLOCKEVENTS select GENERIC_CLOCKEVENTS_BROADCAST if SMP diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c index f058e0c3e4d4..fd1d6c83f0c0 100644 --- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c +++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c @@ -141,6 +141,7 @@ static struct shash_alg alg = { .cra_name = "crc32c", .cra_driver_name = "crc32c-vpmsum", .cra_priority = 200, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .cra_blocksize = CHKSUM_BLOCK_SIZE, .cra_ctxsize = sizeof(u32), .cra_module = THIS_MODULE, diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h index a703452d67b6..555e22d5e07f 100644 --- a/arch/powerpc/include/asm/exception-64e.h +++ b/arch/powerpc/include/asm/exception-64e.h @@ -209,5 +209,11 @@ exc_##label##_book3e: ori r3,r3,vector_offset@l; \ mtspr SPRN_IVOR##vector_number,r3; +#define RFI_TO_KERNEL \ + rfi + +#define RFI_TO_USER \ + rfi + #endif /* _ASM_POWERPC_EXCEPTION_64E_H */ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 9a3eee661297..903e76a9f158 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -51,6 +51,59 @@ #define EX_PPR 88 /* SMT thread status register (priority) */ #define EX_CTR 96 +/* + * Macros for annotating the expected destination of (h)rfid + * + * The nop instructions allow us to insert one or more instructions to flush the + * L1-D cache when returning to userspace or a guest. + */ +#define RFI_FLUSH_SLOT \ + RFI_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop + +#define RFI_TO_KERNEL \ + rfid + +#define RFI_TO_USER \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define RFI_TO_USER_OR_KERNEL \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define RFI_TO_GUEST \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define HRFI_TO_KERNEL \ + hrfid + +#define HRFI_TO_USER \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_USER_OR_KERNEL \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_GUEST \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_UNKNOWN \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + #ifdef CONFIG_RELOCATABLE #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) \ mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ @@ -189,7 +242,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mtspr SPRN_##h##SRR0,r12; \ mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ mtspr SPRN_##h##SRR1,r10; \ - h##rfid; \ + h##RFI_TO_KERNEL; \ b . /* prevent speculative execution */ #define EXCEPTION_PROLOG_PSERIES_1(label, h) \ __EXCEPTION_PROLOG_PSERIES_1(label, h) diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index ddf54f5bbdd1..7b332342071c 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -189,4 +189,19 @@ void apply_feature_fixups(void); void setup_feature_keys(void); #endif +#define RFI_FLUSH_FIXUP_SECTION \ +951: \ + .pushsection __rfi_flush_fixup,"a"; \ + .align 2; \ +952: \ + FTR_ENTRY_OFFSET 951b-952b; \ + .popsection; + + +#ifndef __ASSEMBLY__ + +extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; + +#endif + #endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 708edebcf147..dc0996b9d75d 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -240,6 +240,7 @@ #define H_GET_HCA_INFO 0x1B8 #define H_GET_PERF_COUNT 0x1BC #define H_MANAGE_TRACE 0x1C0 +#define H_GET_CPU_CHARACTERISTICS 0x1C8 #define H_FREE_LOGICAL_LAN_BUFFER 0x1D4 #define H_QUERY_INT_STATE 0x1E4 #define H_POLL_PENDING 0x1D8 @@ -306,7 +307,19 @@ #define H_SET_MODE_RESOURCE_ADDR_TRANS_MODE 3 #define H_SET_MODE_RESOURCE_LE 4 +/* H_GET_CPU_CHARACTERISTICS return values */ +#define H_CPU_CHAR_SPEC_BAR_ORI31 (1ull << 63) // IBM bit 0 +#define H_CPU_CHAR_BCCTRL_SERIALISED (1ull << 62) // IBM bit 1 +#define H_CPU_CHAR_L1D_FLUSH_ORI30 (1ull << 61) // IBM bit 2 +#define H_CPU_CHAR_L1D_FLUSH_TRIG2 (1ull << 60) // IBM bit 3 +#define H_CPU_CHAR_L1D_THREAD_PRIV (1ull << 59) // IBM bit 4 + +#define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0 +#define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1 +#define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2 + #ifndef __ASSEMBLY__ +#include <linux/types.h> /** * plpar_hcall_norets: - Make a pseries hypervisor call with no return arguments @@ -433,6 +446,11 @@ static inline unsigned long cmo_get_page_size(void) } #endif /* CONFIG_PPC_PSERIES */ +struct h_cpu_char_result { + u64 character; + u64 behaviour; +}; + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HVCALL_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 6a6792bb39fb..c75ee2d886fc 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -205,6 +205,15 @@ struct paca_struct { struct sibling_subcore_state *sibling_subcore_state; #endif #endif +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * rfi fallback flush must be in its own cacheline to prevent + * other paca data leaking into the L1d + */ + u64 exrfi[13] __aligned(0x80); + void *rfi_flush_fallback_area; + u64 l1d_flush_size; +#endif }; #ifdef CONFIG_PPC_BOOK3S diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 1b394247afc2..4e53b8570d1f 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -340,4 +340,18 @@ static inline long plapr_set_watchpoint0(unsigned long dawr0, unsigned long dawr return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR, dawr0, dawrx0); } +static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + rc = plpar_hcall(H_GET_CPU_CHARACTERISTICS, retbuf); + if (rc == H_SUCCESS) { + p->character = retbuf[0]; + p->behaviour = retbuf[1]; + } + + return rc; +} + #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 654d64c9f3ac..6825a67cc3db 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -38,6 +38,19 @@ static inline void pseries_big_endian_exceptions(void) {} static inline void pseries_little_endian_exceptions(void) {} #endif /* CONFIG_PPC_PSERIES */ +void rfi_flush_enable(bool enable); + +/* These are bit flags */ +enum l1d_flush_type { + L1D_FLUSH_NONE = 0x1, + L1D_FLUSH_FALLBACK = 0x2, + L1D_FLUSH_ORI = 0x4, + L1D_FLUSH_MTTRIG = 0x8, +}; + +void __init setup_rfi_flush(enum l1d_flush_type, bool enable); +void do_rfi_flush_fixups(enum l1d_flush_type types); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_SETUP_H */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index c833d88c423d..14fbbd9035ca 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -240,6 +240,9 @@ int main(void) #ifdef CONFIG_PPC_BOOK3S_64 DEFINE(PACAMCEMERGSP, offsetof(struct paca_struct, mc_emergency_sp)); DEFINE(PACA_IN_MCE, offsetof(struct paca_struct, in_mce)); + DEFINE(PACA_RFI_FLUSH_FALLBACK_AREA, offsetof(struct paca_struct, rfi_flush_fallback_area)); + DEFINE(PACA_EXRFI, offsetof(struct paca_struct, exrfi)); + DEFINE(PACA_L1D_FLUSH_SIZE, offsetof(struct paca_struct, l1d_flush_size)); #endif DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index caa659671599..2dc52e6d2af4 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -39,6 +39,11 @@ #include <asm/tm.h> #include <asm/ppc-opcode.h> #include <asm/export.h> +#ifdef CONFIG_PPC_BOOK3S +#include <asm/exception-64s.h> +#else +#include <asm/exception-64e.h> +#endif /* * System calls. @@ -251,13 +256,23 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r13,GPR13(r1) /* only restore r13 if returning to usermode */ + ld r2,GPR2(r1) + ld r1,GPR1(r1) + mtlr r4 + mtcr r5 + mtspr SPRN_SRR0,r7 + mtspr SPRN_SRR1,r8 + RFI_TO_USER + b . /* prevent speculative execution */ + + /* exit to kernel */ 1: ld r2,GPR2(r1) ld r1,GPR1(r1) mtlr r4 mtcr r5 mtspr SPRN_SRR0,r7 mtspr SPRN_SRR1,r8 - RFI + RFI_TO_KERNEL b . /* prevent speculative execution */ syscall_error: @@ -386,8 +401,7 @@ tabort_syscall: mtmsrd r10, 1 mtspr SPRN_SRR0, r11 mtspr SPRN_SRR1, r12 - - rfid + RFI_TO_USER b . /* prevent speculative execution */ #endif @@ -859,7 +873,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ACCOUNT_CPU_USER_EXIT(r13, r2, r4) REST_GPR(13, r1) -1: + mtspr SPRN_SRR1,r3 ld r2,_CCR(r1) @@ -872,8 +886,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r3,GPR3(r1) ld r4,GPR4(r1) ld r1,GPR1(r1) + RFI_TO_USER + b . /* prevent speculative execution */ - rfid +1: mtspr SPRN_SRR1,r3 + + ld r2,_CCR(r1) + mtcrf 0xFF,r2 + ld r2,_NIP(r1) + mtspr SPRN_SRR0,r2 + + ld r0,GPR0(r1) + ld r2,GPR2(r1) + ld r3,GPR3(r1) + ld r4,GPR4(r1) + ld r1,GPR1(r1) + RFI_TO_KERNEL b . /* prevent speculative execution */ #endif /* CONFIG_PPC_BOOK3E */ @@ -1049,7 +1077,7 @@ _GLOBAL(enter_rtas) mtspr SPRN_SRR0,r5 mtspr SPRN_SRR1,r6 - rfid + RFI_TO_KERNEL b . /* prevent speculative execution */ rtas_return_loc: @@ -1074,7 +1102,7 @@ rtas_return_loc: mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 - rfid + RFI_TO_KERNEL b . /* prevent speculative execution */ .align 3 @@ -1145,7 +1173,7 @@ _GLOBAL(enter_prom) LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE) andc r11,r11,r12 mtsrr1 r11 - rfid + RFI_TO_KERNEL #endif /* CONFIG_PPC_BOOK3E */ 1: /* Return from OF */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index fd68e19b9ef7..7614d1dd2c0b 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -244,7 +244,7 @@ BEGIN_FTR_SECTION LOAD_HANDLER(r12, machine_check_handle_early) 1: mtspr SPRN_SRR0,r12 mtspr SPRN_SRR1,r11 - rfid + RFI_TO_KERNEL b . /* prevent speculative execution */ 2: /* Stack overflow. Stay on emergency stack and panic. @@ -280,7 +280,7 @@ machine_check_pSeries_0: mtspr SPRN_SRR0,r12 mfspr r12,SPRN_SRR1 mtspr SPRN_SRR1,r10 - rfid + RFI_TO_KERNEL b . /* prevent speculative execution */ TRAMP_KVM_SKIP(PACA_EXMC, 0x200) @@ -446,7 +446,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early) li r3,MSR_ME andc r10,r10,r3 /* Turn off MSR_ME */ mtspr SPRN_SRR1,r10 - rfid + RFI_TO_KERNEL b . 2: /* @@ -464,7 +464,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early) */ bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP - rfid + RFI_TO_USER_OR_KERNEL 9: /* Deliver the machine check to host kernel in V mode. */ MACHINE_CHECK_HANDLER_WINDUP @@ -655,6 +655,8 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) andi. r10,r12,MSR_RI /* check for unrecoverable exception */ beq- 2f + andi. r10,r12,MSR_PR /* check for user mode (PR != 0) */ + bne 1f /* All done -- return from exception. */ @@ -671,7 +673,24 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) ld r11,PACA_EXSLB+EX_R11(r13) ld r12,PACA_EXSLB+EX_R12(r13) ld r13,PACA_EXSLB+EX_R13(r13) - rfid + RFI_TO_KERNEL + b . /* prevent speculative execution */ + +1: +.machine push +.machine "power4" + mtcrf 0x80,r9 + mtcrf 0x02,r9 /* I/D indication is in cr6 */ + mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ +.machine pop + + RESTORE_PPR_PACA(PACA_EXSLB, r9) + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + ld r11,PACA_EXSLB+EX_R11(r13) + ld r12,PACA_EXSLB+EX_R12(r13) + ld r13,PACA_EXSLB+EX_R13(r13) + RFI_TO_USER b . /* prevent speculative execution */ 2: mfspr r11,SPRN_SRR0 @@ -679,7 +698,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 - rfid + RFI_TO_KERNEL b . 8: mfspr r11,SPRN_SRR0 @@ -687,7 +706,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 - rfid + RFI_TO_KERNEL b . EXC_COMMON_BEGIN(unrecov_slb) @@ -874,7 +893,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ mtspr SPRN_SRR0,r10 ; \ ld r10,PACAKMSR(r13) ; \ mtspr SPRN_SRR1,r10 ; \ - rfid ; \ + RFI_TO_KERNEL ; \ b . ; /* prevent speculative execution */ #define SYSCALL_PSERIES_3 \ @@ -882,7 +901,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ 1: mfspr r12,SPRN_SRR1 ; \ xori r12,r12,MSR_LE ; \ mtspr SPRN_SRR1,r12 ; \ - rfid ; /* return to userspace */ \ + RFI_TO_USER ; /* return to userspace */ \ b . ; /* prevent speculative execution */ #if defined(CONFIG_RELOCATABLE) @@ -1257,7 +1276,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) ld r11,PACA_EXGEN+EX_R11(r13) ld r12,PACA_EXGEN+EX_R12(r13) ld r13,PACA_EXGEN+EX_R13(r13) - HRFID + HRFI_TO_UNKNOWN b . #endif @@ -1331,7 +1350,7 @@ masked_##_H##interrupt: \ ld r10,PACA_EXGEN+EX_R10(r13); \ ld r11,PACA_EXGEN+EX_R11(r13); \ GET_SCRATCH0(r13); \ - ##_H##rfid; \ + ##_H##RFI_TO_KERNEL; \ b . /* @@ -1353,7 +1372,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_interrupt) addi r13, r13, 4 mtspr SPRN_SRR0, r13 GET_SCRATCH0(r13) - rfid + RFI_TO_KERNEL b . TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt) @@ -1365,7 +1384,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt) addi r13, r13, 4 mtspr SPRN_HSRR0, r13 GET_SCRATCH0(r13) - hrfid + HRFI_TO_KERNEL b . #endif @@ -1576,6 +1595,88 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) bl kernel_bad_stack b 1b + .globl rfi_flush_fallback +rfi_flush_fallback: + SET_SCRATCH0(r13); + GET_PACA(r13); + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) + ld r11,PACA_L1D_FLUSH_SIZE(r13) + srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ + mtctr r11 + DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + + /* order ld/st prior to dcbt stop all streams with flushing */ + sync + + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ +1: + ld r11,(0x80 + 8)*0(r10) + ld r11,(0x80 + 8)*1(r10) + ld r11,(0x80 + 8)*2(r10) + ld r11,(0x80 + 8)*3(r10) + ld r11,(0x80 + 8)*4(r10) + ld r11,(0x80 + 8)*5(r10) + ld r11,(0x80 + 8)*6(r10) + ld r11,(0x80 + 8)*7(r10) + addi r10,r10,0x80*8 + bdnz 1b + + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + GET_SCRATCH0(r13); + rfid + + .globl hrfi_flush_fallback +hrfi_flush_fallback: + SET_SCRATCH0(r13); + GET_PACA(r13); + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) + ld r11,PACA_L1D_FLUSH_SIZE(r13) + srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ + mtctr r11 + DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + + /* order ld/st prior to dcbt stop all streams with flushing */ + sync + + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ +1: + ld r11,(0x80 + 8)*0(r10) + ld r11,(0x80 + 8)*1(r10) + ld r11,(0x80 + 8)*2(r10) + ld r11,(0x80 + 8)*3(r10) + ld r11,(0x80 + 8)*4(r10) + ld r11,(0x80 + 8)*5(r10) + ld r11,(0x80 + 8)*6(r10) + ld r11,(0x80 + 8)*7(r10) + addi r10,r10,0x80*8 + bdnz 1b + + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + GET_SCRATCH0(r13); + hrfid + /* * Called from arch_local_irq_enable when an interrupt needs * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index b350ac5e3111..d92c95333435 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -9,6 +9,7 @@ */ #include <linux/threads.h> +#include <asm/exception-64s.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/cputable.h> @@ -178,7 +179,7 @@ _GLOBAL(pnv_powersave_common) mtmsrd r6, 1 /* clear RI before setting SRR0/1 */ mtspr SPRN_SRR0, r5 mtspr SPRN_SRR1, r7 - rfid + RFI_TO_KERNEL .globl pnv_enter_arch207_idle_mode pnv_enter_arch207_idle_mode: @@ -668,7 +669,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) mtcr r6 mtspr SPRN_SRR1,r4 mtspr SPRN_SRR0,r5 - rfid + RFI_TO_KERNEL /* * R3 here contains the value that will be returned to the caller @@ -689,4 +690,4 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) mtcr r6 mtspr SPRN_SRR1,r4 mtspr SPRN_SRR0,r5 - rfid + RFI_TO_KERNEL diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index a12be60181bf..5243501d95ef 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -37,6 +37,7 @@ #include <linux/memblock.h> #include <linux/memory.h> #include <linux/nmi.h> +#include <linux/debugfs.h> #include <asm/io.h> #include <asm/kdump.h> @@ -678,4 +679,131 @@ static int __init disable_hardlockup_detector(void) return 0; } early_initcall(disable_hardlockup_detector); + +#ifdef CONFIG_PPC_BOOK3S_64 +static enum l1d_flush_type enabled_flush_types; +static void *l1d_flush_fallback_area; +static bool no_rfi_flush; +bool rfi_flush; + +static int __init handle_no_rfi_flush(char *p) +{ + pr_info("rfi-flush: disabled on command line."); + no_rfi_flush = true; + return 0; +} +early_param("no_rfi_flush", handle_no_rfi_flush); + +/* + * The RFI flush is not KPTI, but because users will see doco that says to use + * nopti we hijack that option here to also disable the RFI flush. + */ +static int __init handle_no_pti(char *p) +{ + pr_info("rfi-flush: disabling due to 'nopti' on command line.\n"); + handle_no_rfi_flush(NULL); + return 0; +} +early_param("nopti", handle_no_pti); + +static void do_nothing(void *unused) +{ + /* + * We don't need to do the flush explicitly, just enter+exit kernel is + * sufficient, the RFI exit handlers will do the right thing. + */ +} + +void rfi_flush_enable(bool enable) +{ + if (rfi_flush == enable) + return; + + if (enable) { + do_rfi_flush_fixups(enabled_flush_types); + on_each_cpu(do_nothing, NULL, 1); + } else + do_rfi_flush_fixups(L1D_FLUSH_NONE); + + rfi_flush = enable; +} + +static void init_fallback_flush(void) +{ + u64 l1d_size, limit; + int cpu; + + l1d_size = ppc64_caches.dsize; + limit = min(safe_stack_limit(), ppc64_rma_size); + + /* + * Align to L1d size, and size it at 2x L1d size, to catch possible + * hardware prefetch runoff. We don't have a recipe for load patterns to + * reliably avoid the prefetcher. + */ + l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit)); + memset(l1d_flush_fallback_area, 0, l1d_size * 2); + + for_each_possible_cpu(cpu) { + paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area; + paca[cpu].l1d_flush_size = l1d_size; + } +} + +void __init setup_rfi_flush(enum l1d_flush_type types, bool enable) +{ + if (types & L1D_FLUSH_FALLBACK) { + pr_info("rfi-flush: Using fallback displacement flush\n"); + init_fallback_flush(); + } + + if (types & L1D_FLUSH_ORI) + pr_info("rfi-flush: Using ori type flush\n"); + + if (types & L1D_FLUSH_MTTRIG) + pr_info("rfi-flush: Using mttrig type flush\n"); + + enabled_flush_types = types; + + if (!no_rfi_flush) + rfi_flush_enable(enable); +} + +#ifdef CONFIG_DEBUG_FS +static int rfi_flush_set(void *data, u64 val) +{ + if (val == 1) + rfi_flush_enable(true); + else if (val == 0) + rfi_flush_enable(false); + else + return -EINVAL; + + return 0; +} + +static int rfi_flush_get(void *data, u64 *val) +{ + *val = rfi_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); + +static __init int rfi_flush_debugfs_init(void) +{ + debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + return 0; +} +device_initcall(rfi_flush_debugfs_init); +#endif + +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (rfi_flush) + return sprintf(buf, "Mitigation: RFI Flush\n"); + + return sprintf(buf, "Vulnerable\n"); +} +#endif /* CONFIG_PPC_BOOK3S_64 */ #endif diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 7394b770ae1f..b61fb7902018 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -132,6 +132,15 @@ SECTIONS /* Read-only data */ RODATA +#ifdef CONFIG_PPC64 + . = ALIGN(8); + __rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) { + __start___rfi_flush_fixup = .; + *(__rfi_flush_fixup) + __stop___rfi_flush_fixup = .; + } +#endif + EXCEPTION_TABLE(0) NOTES :kernel :notes diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 0447a22a4df6..55fbc0c78721 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -65,7 +65,7 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline) mtmsrd r0,1 /* clear RI in MSR */ mtsrr0 r5 mtsrr1 r6 - RFI + RFI_TO_KERNEL kvmppc_call_hv_entry: ld r4, HSTATE_KVM_VCPU(r13) @@ -171,7 +171,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtsrr0 r8 mtsrr1 r7 beq cr1, 13f /* machine check */ - RFI + RFI_TO_KERNEL /* On POWER7, we have external interrupts set to use HSRR0/1 */ 11: mtspr SPRN_HSRR0, r8 @@ -1018,8 +1018,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r0, VCPU_GPR(R0)(r4) ld r4, VCPU_GPR(R4)(r4) - - hrfid + HRFI_TO_GUEST b . secondary_too_late: diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 42a4b237df5f..34a5adeff084 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -46,6 +46,9 @@ #define FUNC(name) name +#define RFI_TO_KERNEL RFI +#define RFI_TO_GUEST RFI + .macro INTERRUPT_TRAMPOLINE intno .global kvmppc_trampoline_\intno @@ -141,7 +144,7 @@ kvmppc_handler_skip_ins: GET_SCRATCH0(r13) /* And get back into the code */ - RFI + RFI_TO_KERNEL #endif /* @@ -164,6 +167,6 @@ _GLOBAL_TOC(kvmppc_entry_trampoline) ori r5, r5, MSR_EE mtsrr0 r7 mtsrr1 r6 - RFI + RFI_TO_KERNEL #include "book3s_segment.S" diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index ca8f174289bb..7c982956d709 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -156,7 +156,7 @@ no_dcbz32_on: PPC_LL r9, SVCPU_R9(r3) PPC_LL r3, (SVCPU_R3)(r3) - RFI + RFI_TO_GUEST kvmppc_handler_trampoline_enter_end: @@ -389,5 +389,5 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) cmpwi r12, BOOK3S_INTERRUPT_DOORBELL beqa BOOK3S_INTERRUPT_DOORBELL - RFI + RFI_TO_KERNEL kvmppc_handler_trampoline_exit_end: diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 043415f0bdb1..e86bfa111f3c 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -23,6 +23,7 @@ #include <asm/sections.h> #include <asm/setup.h> #include <asm/firmware.h> +#include <asm/setup.h> struct fixup_entry { unsigned long mask; @@ -115,6 +116,47 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end) } } +#ifdef CONFIG_PPC_BOOK3S_64 +void do_rfi_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[3], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___rfi_flush_fixup), + end = PTRRELOC(&__stop___rfi_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + + if (types & L1D_FLUSH_FALLBACK) + /* b .+16 to fallback flush */ + instrs[0] = 0x48000010; + + i = 0; + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction(dest, instrs[0]); + patch_instruction(dest + 1, instrs[1]); + patch_instruction(dest + 2, instrs[2]); + } + + printk(KERN_DEBUG "rfi-flush: patched %d locations\n", i); +} +#endif /* CONFIG_PPC_BOOK3S_64 */ + void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) { long *start, *end; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 083f92746951..bf949623de90 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1381,7 +1381,7 @@ 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; @@ -1389,7 +1389,7 @@ 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/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index b33faa0015cc..6f8b4c19373a 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -35,13 +35,63 @@ #include <asm/opal.h> #include <asm/kexec.h> #include <asm/smp.h> +#include <asm/tm.h> +#include <asm/setup.h> #include "powernv.h" +static void pnv_setup_rfi_flush(void) +{ + struct device_node *np, *fw_features; + enum l1d_flush_type type; + int enable; + + /* Default to fallback in case fw-features are not available */ + type = L1D_FLUSH_FALLBACK; + enable = 1; + + np = of_find_node_by_name(NULL, "ibm,opal"); + fw_features = of_get_child_by_name(np, "fw-features"); + of_node_put(np); + + if (fw_features) { + np = of_get_child_by_name(fw_features, "inst-l1d-flush-trig2"); + if (np && of_property_read_bool(np, "enabled")) + type = L1D_FLUSH_MTTRIG; + + of_node_put(np); + + np = of_get_child_by_name(fw_features, "inst-l1d-flush-ori30,30,0"); + if (np && of_property_read_bool(np, "enabled")) + type = L1D_FLUSH_ORI; + + of_node_put(np); + + /* Enable unless firmware says NOT to */ + enable = 2; + np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-hv-1-to-0"); + if (np && of_property_read_bool(np, "disabled")) + enable--; + + of_node_put(np); + + np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-pr-0-to-1"); + if (np && of_property_read_bool(np, "disabled")) + enable--; + + of_node_put(np); + of_node_put(fw_features); + } + + setup_rfi_flush(type, enable > 0); +} + static void __init pnv_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); + pnv_setup_rfi_flush(); + /* Initialize SMP */ pnv_smp_init(); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 97aa3f332f24..1845fc611912 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -450,6 +450,39 @@ static void __init find_and_init_phbs(void) of_pci_check_probe_only(); } +static void pseries_setup_rfi_flush(void) +{ + struct h_cpu_char_result result; + enum l1d_flush_type types; + bool enable; + long rc; + + /* Enable by default */ + enable = true; + + rc = plpar_get_cpu_characteristics(&result); + if (rc == H_SUCCESS) { + types = L1D_FLUSH_NONE; + + if (result.character & H_CPU_CHAR_L1D_FLUSH_TRIG2) + types |= L1D_FLUSH_MTTRIG; + if (result.character & H_CPU_CHAR_L1D_FLUSH_ORI30) + types |= L1D_FLUSH_ORI; + + /* Use fallback if nothing set in hcall */ + if (types == L1D_FLUSH_NONE) + types = L1D_FLUSH_FALLBACK; + + if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR)) + enable = false; + } else { + /* Default to fallback if case hcall is not available */ + types = L1D_FLUSH_FALLBACK; + } + + setup_rfi_flush(types, enable); +} + static void __init pSeries_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); @@ -467,6 +500,8 @@ static void __init pSeries_setup_arch(void) fwnmi_init(); + pseries_setup_rfi_flush(); + /* By default, only probe PCI (can be overridden by rtas_pci) */ pci_add_flags(PCI_PROBE_ONLY); diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c index 992e630c227b..6f4985f357c6 100644 --- a/arch/s390/crypto/crc32-vx.c +++ b/arch/s390/crypto/crc32-vx.c @@ -238,6 +238,7 @@ static struct shash_alg crc32_vx_algs[] = { .cra_name = "crc32", .cra_driver_name = "crc32-vx", .cra_priority = 200, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .cra_blocksize = CRC32_BLOCK_SIZE, .cra_ctxsize = sizeof(struct crc_ctx), .cra_module = THIS_MODULE, @@ -258,6 +259,7 @@ static struct shash_alg crc32_vx_algs[] = { .cra_name = "crc32be", .cra_driver_name = "crc32be-vx", .cra_priority = 200, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .cra_blocksize = CRC32_BLOCK_SIZE, .cra_ctxsize = sizeof(struct crc_ctx), .cra_module = THIS_MODULE, @@ -278,6 +280,7 @@ static struct shash_alg crc32_vx_algs[] = { .cra_name = "crc32c", .cra_driver_name = "crc32c-vx", .cra_priority = 200, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .cra_blocksize = CRC32_BLOCK_SIZE, .cra_ctxsize = sizeof(struct crc_ctx), .cra_module = THIS_MODULE, diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index f06a9a0063f1..d0724a924184 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -110,7 +110,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setregid16, u16, rgid, u16, egid) COMPAT_SYSCALL_DEFINE1(s390_setgid16, u16, gid) { - return sys_setgid((gid_t)gid); + return sys_setgid(low2highgid(gid)); } COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid) @@ -120,7 +120,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid) COMPAT_SYSCALL_DEFINE1(s390_setuid16, u16, uid) { - return sys_setuid((uid_t)uid); + return sys_setuid(low2highuid(uid)); } COMPAT_SYSCALL_DEFINE3(s390_setresuid16, u16, ruid, u16, euid, u16, suid) @@ -173,12 +173,12 @@ COMPAT_SYSCALL_DEFINE3(s390_getresgid16, u16 __user *, rgidp, COMPAT_SYSCALL_DEFINE1(s390_setfsuid16, u16, uid) { - return sys_setfsuid((uid_t)uid); + return sys_setfsuid(low2highuid(uid)); } COMPAT_SYSCALL_DEFINE1(s390_setfsgid16, u16, gid) { - return sys_setfsgid((gid_t)gid); + return sys_setfsgid(low2highgid(gid)); } static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info) diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index ff639342a8be..c5b997757988 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -607,7 +607,8 @@ asmlinkage void do_divide_error(unsigned long r4) break; } - force_sig_info(SIGFPE, &info, current); + info.si_signo = SIGFPE; + force_sig_info(info.si_signo, &info, current); } #endif diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c index d1064e46efe8..8aa664638c3c 100644 --- a/arch/sparc/crypto/crc32c_glue.c +++ b/arch/sparc/crypto/crc32c_glue.c @@ -133,6 +133,7 @@ static struct shash_alg alg = { .cra_name = "crc32c", .cra_driver_name = "crc32c-sparc64", .cra_priority = SPARC_CR_OPCODE_PRIORITY, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .cra_blocksize = CHKSUM_BLOCK_SIZE, .cra_ctxsize = sizeof(u32), .cra_alignmask = 7, diff --git a/arch/um/Makefile b/arch/um/Makefile index 0ca46ededfc7..9c150ccb35d2 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -117,7 +117,7 @@ archheaders: archprepare: include/generated/user_constants.h LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static -LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib +LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib $(call cc-option, -no-pie) CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \ $(call cc-option, -fno-stack-protector,) \ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index da8156fd3d58..a4ac7bab15f7 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -64,6 +64,7 @@ config X86 select GENERIC_CLOCKEVENTS_MIN_ADJUST select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE + select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP select GENERIC_FIND_FIRST_BIT select GENERIC_IOMAP @@ -407,6 +408,19 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH +config RETPOLINE + bool "Avoid speculative indirect branches in kernel" + default y + ---help--- + Compile kernel with the retpoline compiler options to guard against + kernel-to-user data leaks by avoiding speculative indirect + branches. Requires a compiler with -mindirect-branch=thunk-extern + support for full protection. The kernel may run slower. + + Without compiler support, at least indirect branches in assembler + code are eliminated. Since this includes the syscall entry path, + it is not entirely pointless. + if X86_32 config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" @@ -1043,7 +1057,7 @@ config X86_MCE_THRESHOLD def_bool y config X86_MCE_INJECT - depends on X86_MCE + depends on X86_MCE && X86_LOCAL_APIC tristate "Machine check injector support" ---help--- Provide support for injecting machine checks for testing purposes. diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 67eec55093a5..4386440fe463 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -352,6 +352,7 @@ config X86_DEBUG_FPU config PUNIT_ATOM_DEBUG tristate "ATOM Punit debug driver" + depends on PCI select DEBUG_FS select IOSF_MBI ---help--- diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 2d449337a360..cd22cb8ebd42 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -182,6 +182,14 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) +# Avoid indirect branches in kernel to deal with Spectre +ifdef CONFIG_RETPOLINE + RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) + ifneq ($(RETPOLINE_CFLAGS),) + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE + endif +endif + archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 12ea8f8384f4..3b7156f46bc1 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -73,12 +73,13 @@ UBSAN_SANITIZE := n $(obj)/bzImage: asflags-y := $(SVGA_MODE) quiet_cmd_image = BUILD $@ +silent_redirect_image = >/dev/null cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \ - $(obj)/zoffset.h $@ + $(obj)/zoffset.h $@ $($(quiet)redirect_image) $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) - @echo 'Kernel: $@ is ready' ' (#'`cat .version`')' + @$(kecho) 'Kernel: $@ is ready' ' (#'`cat .version`')' OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 383a6f84a060..fa8801b35e51 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -32,6 +32,7 @@ #include <linux/linkage.h> #include <asm/inst.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> /* * The following macros are used to move an (un)aligned 16 byte value to/from @@ -2734,7 +2735,7 @@ ENTRY(aesni_xts_crypt8) pxor INC, STATE4 movdqu IV, 0x30(OUTP) - call *%r11 + CALL_NOSPEC %r11 movdqu 0x00(OUTP), INC pxor INC, STATE1 @@ -2779,7 +2780,7 @@ ENTRY(aesni_xts_crypt8) _aesni_gf128mul_x_ble() movups IV, (IVP) - call *%r11 + CALL_NOSPEC %r11 movdqu 0x40(OUTP), INC pxor INC, STATE1 diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index aa8b0672f87a..d9ae404f08c9 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -906,7 +906,7 @@ static int helper_rfc4106_encrypt(struct aead_request *req) if (sg_is_last(req->src) && req->src->offset + req->src->length <= PAGE_SIZE && - sg_is_last(req->dst) && ++ sg_is_last(req->dst) && req->dst->length && req->dst->offset + req->dst->length <= PAGE_SIZE) { one_entry_in_sg = 1; scatterwalk_start(&src_sg_walk, req->src); diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index aa9e8bd163f6..77ff4de2224d 100644 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -17,6 +17,7 @@ #include <linux/linkage.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> #define CAMELLIA_TABLE_BYTE_LEN 272 @@ -1224,7 +1225,7 @@ camellia_xts_crypt_16way: vpxor 14 * 16(%rax), %xmm15, %xmm14; vpxor 15 * 16(%rax), %xmm15, %xmm15; - call *%r9; + CALL_NOSPEC %r9; addq $(16 * 16), %rsp; diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index 16186c18656d..7384342fbb41 100644 --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -12,6 +12,7 @@ #include <linux/linkage.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> #define CAMELLIA_TABLE_BYTE_LEN 272 @@ -1337,7 +1338,7 @@ camellia_xts_crypt_32way: vpxor 14 * 32(%rax), %ymm15, %ymm14; vpxor 15 * 32(%rax), %ymm15, %ymm15; - call *%r9; + CALL_NOSPEC %r9; addq $(16 * 32), %rsp; diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c index 27226df3f7d8..c8d9cdacbf10 100644 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ b/arch/x86/crypto/crc32-pclmul_glue.c @@ -162,6 +162,7 @@ static struct shash_alg alg = { .cra_name = "crc32", .cra_driver_name = "crc32-pclmul", .cra_priority = 200, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .cra_blocksize = CHKSUM_BLOCK_SIZE, .cra_ctxsize = sizeof(u32), .cra_module = THIS_MODULE, diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 0857b1a1de3b..60a391b8c4a2 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -239,6 +239,7 @@ static struct shash_alg alg = { .cra_name = "crc32c", .cra_driver_name = "crc32c-intel", .cra_priority = 200, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .cra_blocksize = CHKSUM_BLOCK_SIZE, .cra_ctxsize = sizeof(u32), .cra_module = THIS_MODULE, diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index dc05f010ca9b..174fd4146043 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -45,6 +45,7 @@ #include <asm/inst.h> #include <linux/linkage.h> +#include <asm/nospec-branch.h> ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction @@ -172,7 +173,7 @@ continue_block: movzxw (bufp, %rax, 2), len lea crc_array(%rip), bufp lea (bufp, len, 1), bufp - jmp *bufp + JMP_NOSPEC bufp ################################################################ ## 2a) PROCESS FULL BLOCKS: diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index e32142bc071d..28c372003e44 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -164,7 +164,6 @@ static struct shash_alg alg = { .init = poly1305_simd_init, .update = poly1305_simd_update, .final = crypto_poly1305_final, - .setkey = crypto_poly1305_setkey, .descsize = sizeof(struct poly1305_simd_desc_ctx), .base = { .cra_name = "poly1305", diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c index 36870b26067a..d08805032f01 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c @@ -57,10 +57,12 @@ void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state) { unsigned int j; - state->lens[0] = 0; - state->lens[1] = 1; - state->lens[2] = 2; - state->lens[3] = 3; + /* initially all lanes are unused */ + state->lens[0] = 0xFFFFFFFF00000000; + state->lens[1] = 0xFFFFFFFF00000001; + state->lens[2] = 0xFFFFFFFF00000002; + state->lens[3] = 0xFFFFFFFF00000003; + state->unused_lanes = 0xFF03020100; for (j = 0; j < 4; j++) state->ldata[j].job_in_lane = NULL; diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S index 1c3b7ceb36d2..e7273a606a07 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S @@ -55,29 +55,31 @@ #define RAB1bl %bl #define RAB2bl %cl +#define CD0 0x0(%rsp) +#define CD1 0x8(%rsp) +#define CD2 0x10(%rsp) + +# used only before/after all rounds #define RCD0 %r8 #define RCD1 %r9 #define RCD2 %r10 -#define RCD0d %r8d -#define RCD1d %r9d -#define RCD2d %r10d - -#define RX0 %rbp -#define RX1 %r11 -#define RX2 %r12 +# used only during rounds +#define RX0 %r8 +#define RX1 %r9 +#define RX2 %r10 -#define RX0d %ebp -#define RX1d %r11d -#define RX2d %r12d +#define RX0d %r8d +#define RX1d %r9d +#define RX2d %r10d -#define RY0 %r13 -#define RY1 %r14 -#define RY2 %r15 +#define RY0 %r11 +#define RY1 %r12 +#define RY2 %r13 -#define RY0d %r13d -#define RY1d %r14d -#define RY2d %r15d +#define RY0d %r11d +#define RY1d %r12d +#define RY2d %r13d #define RT0 %rdx #define RT1 %rsi @@ -85,6 +87,8 @@ #define RT0d %edx #define RT1d %esi +#define RT1bl %sil + #define do16bit_ror(rot, op1, op2, T0, T1, tmp1, tmp2, ab, dst) \ movzbl ab ## bl, tmp2 ## d; \ movzbl ab ## bh, tmp1 ## d; \ @@ -92,6 +96,11 @@ op1##l T0(CTX, tmp2, 4), dst ## d; \ op2##l T1(CTX, tmp1, 4), dst ## d; +#define swap_ab_with_cd(ab, cd, tmp) \ + movq cd, tmp; \ + movq ab, cd; \ + movq tmp, ab; + /* * Combined G1 & G2 function. Reordered with help of rotates to have moves * at begining. @@ -110,15 +119,15 @@ /* G1,2 && G2,2 */ \ do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 0, x ## 0); \ do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 0, y ## 0); \ - xchgq cd ## 0, ab ## 0; \ + swap_ab_with_cd(ab ## 0, cd ## 0, RT0); \ \ do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 1, x ## 1); \ do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 1, y ## 1); \ - xchgq cd ## 1, ab ## 1; \ + swap_ab_with_cd(ab ## 1, cd ## 1, RT0); \ \ do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 2, x ## 2); \ do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 2, y ## 2); \ - xchgq cd ## 2, ab ## 2; + swap_ab_with_cd(ab ## 2, cd ## 2, RT0); #define enc_round_end(ab, x, y, n) \ addl y ## d, x ## d; \ @@ -168,6 +177,16 @@ decrypt_round3(ba, dc, (n*2)+1); \ decrypt_round3(ba, dc, (n*2)); +#define push_cd() \ + pushq RCD2; \ + pushq RCD1; \ + pushq RCD0; + +#define pop_cd() \ + popq RCD0; \ + popq RCD1; \ + popq RCD2; + #define inpack3(in, n, xy, m) \ movq 4*(n)(in), xy ## 0; \ xorq w+4*m(CTX), xy ## 0; \ @@ -223,11 +242,8 @@ ENTRY(__twofish_enc_blk_3way) * %rdx: src, RIO * %rcx: bool, if true: xor output */ - pushq %r15; - pushq %r14; pushq %r13; pushq %r12; - pushq %rbp; pushq %rbx; pushq %rcx; /* bool xor */ @@ -235,40 +251,36 @@ ENTRY(__twofish_enc_blk_3way) inpack_enc3(); - encrypt_cycle3(RAB, RCD, 0); - encrypt_cycle3(RAB, RCD, 1); - encrypt_cycle3(RAB, RCD, 2); - encrypt_cycle3(RAB, RCD, 3); - encrypt_cycle3(RAB, RCD, 4); - encrypt_cycle3(RAB, RCD, 5); - encrypt_cycle3(RAB, RCD, 6); - encrypt_cycle3(RAB, RCD, 7); + push_cd(); + encrypt_cycle3(RAB, CD, 0); + encrypt_cycle3(RAB, CD, 1); + encrypt_cycle3(RAB, CD, 2); + encrypt_cycle3(RAB, CD, 3); + encrypt_cycle3(RAB, CD, 4); + encrypt_cycle3(RAB, CD, 5); + encrypt_cycle3(RAB, CD, 6); + encrypt_cycle3(RAB, CD, 7); + pop_cd(); popq RIO; /* dst */ - popq %rbp; /* bool xor */ + popq RT1; /* bool xor */ - testb %bpl, %bpl; + testb RT1bl, RT1bl; jnz .L__enc_xor3; outunpack_enc3(mov); popq %rbx; - popq %rbp; popq %r12; popq %r13; - popq %r14; - popq %r15; ret; .L__enc_xor3: outunpack_enc3(xor); popq %rbx; - popq %rbp; popq %r12; popq %r13; - popq %r14; - popq %r15; ret; ENDPROC(__twofish_enc_blk_3way) @@ -278,35 +290,31 @@ ENTRY(twofish_dec_blk_3way) * %rsi: dst * %rdx: src, RIO */ - pushq %r15; - pushq %r14; pushq %r13; pushq %r12; - pushq %rbp; pushq %rbx; pushq %rsi; /* dst */ inpack_dec3(); - decrypt_cycle3(RAB, RCD, 7); - decrypt_cycle3(RAB, RCD, 6); - decrypt_cycle3(RAB, RCD, 5); - decrypt_cycle3(RAB, RCD, 4); - decrypt_cycle3(RAB, RCD, 3); - decrypt_cycle3(RAB, RCD, 2); - decrypt_cycle3(RAB, RCD, 1); - decrypt_cycle3(RAB, RCD, 0); + push_cd(); + decrypt_cycle3(RAB, CD, 7); + decrypt_cycle3(RAB, CD, 6); + decrypt_cycle3(RAB, CD, 5); + decrypt_cycle3(RAB, CD, 4); + decrypt_cycle3(RAB, CD, 3); + decrypt_cycle3(RAB, CD, 2); + decrypt_cycle3(RAB, CD, 1); + decrypt_cycle3(RAB, CD, 0); + pop_cd(); popq RIO; /* dst */ outunpack_dec3(); popq %rbx; - popq %rbp; popq %r12; popq %r13; - popq %r14; - popq %r15; ret; ENDPROC(twofish_dec_blk_3way) diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index bdd9cc59d20f..b0cd306dc527 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -20,6 +20,7 @@ #include <linux/export.h> #include <linux/context_tracking.h> #include <linux/user-return-notifier.h> +#include <linux/nospec.h> #include <linux/uprobes.h> #include <asm/desc.h> @@ -201,7 +202,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) * special case only applies after poking regs and before the * very next return to user mode. */ - current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED); + ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif user_enter_irqoff(); @@ -277,7 +278,8 @@ __visible void do_syscall_64(struct pt_regs *regs) * regs->orig_ax, which changes the behavior of some syscalls. */ if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) { - regs->ax = sys_call_table[nr & __SYSCALL_MASK]( + nr = array_index_nospec(nr & __SYSCALL_MASK, NR_syscalls); + regs->ax = sys_call_table[nr]( regs->di, regs->si, regs->dx, regs->r10, regs->r8, regs->r9); } @@ -299,7 +301,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) unsigned int nr = (unsigned int)regs->orig_ax; #ifdef CONFIG_IA32_EMULATION - current->thread.status |= TS_COMPAT; + ti->status |= TS_COMPAT; #endif if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { @@ -313,6 +315,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) } if (likely(nr < IA32_NR_syscalls)) { + nr = array_index_nospec(nr, IA32_NR_syscalls); /* * It's possible that a 32-bit syscall implementation * takes a 64-bit parameter but nonetheless assumes that diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index edba8606b99a..f5434b4670c1 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -45,6 +45,7 @@ #include <asm/asm.h> #include <asm/smap.h> #include <asm/export.h> +#include <asm/nospec-branch.h> .section .entry.text, "ax" @@ -228,6 +229,18 @@ ENTRY(__switch_to_asm) movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset #endif +#ifdef CONFIG_RETPOLINE + /* + * When switching from a shallower to a deeper call stack + * the RSB may either underflow or use entries populated + * with userspace addresses. On CPUs where those concerns + * exist, overwrite the RSB with entries which capture + * speculative execution to prevent attack. + */ + /* Clobbers %ebx */ + FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW +#endif + /* restore callee-saved registers */ popl %esi popl %edi @@ -260,7 +273,7 @@ ENTRY(ret_from_fork) /* kernel thread */ 1: movl %edi, %eax - call *%ebx + CALL_NOSPEC %ebx /* * A kernel thread is allowed to return here after successfully * calling do_execve(). Exit to userspace to complete the execve() @@ -984,7 +997,8 @@ trace: movl 0x4(%ebp), %edx subl $MCOUNT_INSN_SIZE, %eax - call *ftrace_trace_function + movl ftrace_trace_function, %ecx + CALL_NOSPEC %ecx popl %edx popl %ecx @@ -1020,7 +1034,7 @@ return_to_handler: movl %eax, %ecx popl %edx popl %eax - jmp *%ecx + JMP_NOSPEC %ecx #endif #ifdef CONFIG_TRACING @@ -1062,7 +1076,7 @@ error_code: movl %ecx, %es TRACE_IRQS_OFF movl %esp, %eax # pt_regs pointer - call *%edi + CALL_NOSPEC %edi jmp ret_from_exception END(page_fault) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index af4e58132d91..db5009ce065a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -37,6 +37,7 @@ #include <asm/pgtable_types.h> #include <asm/export.h> #include <asm/kaiser.h> +#include <asm/nospec-branch.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -176,91 +177,17 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) pushq %r9 /* pt_regs->r9 */ pushq %r10 /* pt_regs->r10 */ pushq %r11 /* pt_regs->r11 */ - sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ - /* - * If we need to do entry work or if we guess we'll need to do - * exit work, go straight to the slow path. - */ - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz entry_SYSCALL64_slow_path - -entry_SYSCALL_64_fastpath: - /* - * Easy case: enable interrupts and issue the syscall. If the syscall - * needs pt_regs, we'll call a stub that disables interrupts again - * and jumps to the slow path. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) -#if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax -#else - andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax -#endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10, %rcx - - /* - * This call instruction is handled specially in stub_ptregs_64. - * It might end up jumping to the slow path. If it jumps, RAX - * and all argument registers are clobbered. - */ - call *sys_call_table(, %rax, 8) -.Lentry_SYSCALL_64_after_fastpath_call: - - movq %rax, RAX(%rsp) -1: - - /* - * If we get here, then we know that pt_regs is clean for SYSRET64. - * If we see that no exit work is required (which we are required - * to check with IRQs off), then we can go straight to SYSRET64. - */ - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz 1f - - LOCKDEP_SYS_EXIT - TRACE_IRQS_ON /* user mode is traced as IRQs on */ - movq RIP(%rsp), %rcx - movq EFLAGS(%rsp), %r11 - RESTORE_C_REGS_EXCEPT_RCX_R11 - /* - * This opens a window where we have a user CR3, but are - * running in the kernel. This makes using the CS - * register useless for telling whether or not we need to - * switch CR3 in NMIs. Normal interrupts are OK because - * they are off here. - */ - SWITCH_USER_CR3 - movq RSP(%rsp), %rsp - USERGS_SYSRET64 - -1: - /* - * The fast path looked good when we started, but something changed - * along the way and we need to switch to the slow path. Calling - * raise(3) will trigger this, for example. IRQs are off. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_EXTRA_REGS - movq %rsp, %rdi - call syscall_return_slowpath /* returns with IRQs disabled */ - jmp return_from_SYSCALL_64 - -entry_SYSCALL64_slow_path: /* IRQs are off. */ - SAVE_EXTRA_REGS movq %rsp, %rdi call do_syscall_64 /* returns with IRQs disabled */ -return_from_SYSCALL_64: RESTORE_EXTRA_REGS TRACE_IRQS_IRETQ /* we're about to change IF */ @@ -333,6 +260,7 @@ return_from_SYSCALL_64: syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ RESTORE_C_REGS_EXCEPT_RCX_R11 + /* * This opens a window where we have a user CR3, but are * running in the kernel. This makes using the CS @@ -357,45 +285,6 @@ opportunistic_sysret_failed: jmp restore_c_regs_and_iret END(entry_SYSCALL_64) -ENTRY(stub_ptregs_64) - /* - * Syscalls marked as needing ptregs land here. - * If we are on the fast path, we need to save the extra regs, - * which we achieve by trying again on the slow path. If we are on - * the slow path, the extra regs are already saved. - * - * RAX stores a pointer to the C function implementing the syscall. - * IRQs are on. - */ - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) - jne 1f - - /* - * Called from fast path -- disable IRQs again, pop return address - * and jump to slow path - */ - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - popq %rax - jmp entry_SYSCALL64_slow_path - -1: - jmp *%rax /* Called from C */ -END(stub_ptregs_64) - -.macro ptregs_stub func -ENTRY(ptregs_\func) - leaq \func(%rip), %rax - jmp stub_ptregs_64 -END(ptregs_\func) -.endm - -/* Instantiate ptregs_stub for each ptregs-using syscall */ -#define __SYSCALL_64_QUAL_(sym) -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym -#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym) -#include <asm/syscalls_64.h> - /* * %rdi: prev task * %rsi: next task @@ -421,6 +310,18 @@ ENTRY(__switch_to_asm) movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset #endif +#ifdef CONFIG_RETPOLINE + /* + * When switching from a shallower to a deeper call stack + * the RSB may either underflow or use entries populated + * with userspace addresses. On CPUs where those concerns + * exist, overwrite the RSB with entries which capture + * speculative execution to prevent attack. + */ + /* Clobbers %rbx */ + FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW +#endif + /* restore callee-saved registers */ popq %r15 popq %r14 @@ -457,7 +358,7 @@ ENTRY(ret_from_fork) 1: /* kernel thread */ movq %r12, %rdi - call *%rbx + CALL_NOSPEC %rbx /* * A kernel thread is allowed to return here after successfully * calling do_execve(). Exit to userspace to complete the execve() @@ -1047,7 +948,7 @@ idtentry async_page_fault do_async_page_fault has_error_code=1 #endif #ifdef CONFIG_X86_MCE -idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) +idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index d76a97653980..92c55738d543 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -83,15 +83,25 @@ ENTRY(entry_SYSENTER_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorq %r12, %r12 /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorq %r13, %r13 /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorq %r14, %r14 /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorq %r15, %r15 /* nospec r15 */ cld /* @@ -209,15 +219,25 @@ ENTRY(entry_SYSCALL_compat) pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorq %r12, %r12 /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorq %r13, %r13 /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorq %r14, %r14 /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorq %r15, %r15 /* nospec r15 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -320,15 +340,25 @@ ENTRY(entry_INT80_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15 */ cld /* diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 9dbc5abb6162..6705edda4ac3 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -6,14 +6,11 @@ #include <asm/asm-offsets.h> #include <asm/syscall.h> -#define __SYSCALL_64_QUAL_(sym) sym -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym - -#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include <asm/syscalls_64.h> #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym), +#define __SYSCALL_64(nr, sym, qual) [nr] = sym, extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 6bb7e92c6d50..0174290b2857 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -46,6 +46,7 @@ static enum { EMULATE, NATIVE, NONE } vsyscall_mode = #else EMULATE; #endif +unsigned long vsyscall_pgprot = __PAGE_KERNEL_VSYSCALL; static int __init vsyscall_setup(char *str) { @@ -336,11 +337,11 @@ void __init map_vsyscall(void) extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); + if (vsyscall_mode != NATIVE) + vsyscall_pgprot = __PAGE_KERNEL_VVAR; if (vsyscall_mode != NONE) __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, - vsyscall_mode == NATIVE - ? PAGE_KERNEL_VSYSCALL - : PAGE_KERNEL_VVAR); + __pgprot(vsyscall_pgprot)); BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c index 9842270ed2f2..21a4e4127f43 100644 --- a/arch/x86/events/amd/power.c +++ b/arch/x86/events/amd/power.c @@ -277,7 +277,7 @@ static int __init amd_power_pmu_init(void) int ret; if (!x86_match_cpu(cpu_match)) - return 0; + return -ENODEV; if (!boot_cpu_has(X86_FEATURE_ACC_POWER)) return -ENODEV; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 9604b2574d6c..f73796db8758 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -190,8 +190,8 @@ static void release_pmc_hardware(void) {} static bool check_hw_exists(void) { - u64 val, val_fail, val_new= ~0; - int i, reg, reg_fail, ret = 0; + u64 val, val_fail = -1, val_new= ~0; + int i, reg, reg_fail = -1, ret = 0; int bios_fail = 0; int reg_safe = -1; diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 982c9e31daca..21298c173b0e 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -22,6 +22,7 @@ #include <linux/debugfs.h> #include <linux/device.h> #include <linux/coredump.h> +#include <linux/kaiser.h> #include <asm-generic/sizes.h> #include <asm/perf_event.h> @@ -77,6 +78,23 @@ static size_t buf_size(struct page *page) return 1 << (PAGE_SHIFT + page_private(page)); } +static void bts_buffer_free_aux(void *data) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + struct bts_buffer *buf = data; + int nbuf; + + for (nbuf = 0; nbuf < buf->nr_bufs; nbuf++) { + struct page *page = buf->buf[nbuf].page; + void *kaddr = page_address(page); + size_t page_size = buf_size(page); + + kaiser_remove_mapping((unsigned long)kaddr, page_size); + } +#endif + kfree(data); +} + static void * bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite) { @@ -113,29 +131,33 @@ bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite) buf->real_size = size - size % BTS_RECORD_SIZE; for (pg = 0, nbuf = 0, offset = 0, pad = 0; nbuf < buf->nr_bufs; nbuf++) { - unsigned int __nr_pages; + void *kaddr = pages[pg]; + size_t page_size; + + page = virt_to_page(kaddr); + page_size = buf_size(page); + + if (kaiser_add_mapping((unsigned long)kaddr, + page_size, __PAGE_KERNEL) < 0) { + buf->nr_bufs = nbuf; + bts_buffer_free_aux(buf); + return NULL; + } - page = virt_to_page(pages[pg]); - __nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1; buf->buf[nbuf].page = page; buf->buf[nbuf].offset = offset; buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0); - buf->buf[nbuf].size = buf_size(page) - buf->buf[nbuf].displacement; + buf->buf[nbuf].size = page_size - buf->buf[nbuf].displacement; pad = buf->buf[nbuf].size % BTS_RECORD_SIZE; buf->buf[nbuf].size -= pad; - pg += __nr_pages; - offset += __nr_pages << PAGE_SHIFT; + pg += page_size >> PAGE_SHIFT; + offset += page_size; } return buf; } -static void bts_buffer_free_aux(void *data) -{ - kfree(data); -} - static unsigned long bts_buffer_offset(struct bts_buffer *buf, unsigned int idx) { return buf->buf[idx].offset + buf->buf[idx].displacement; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index f0f197f459b5..0bd0c1cc3228 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3363,7 +3363,7 @@ static int intel_snb_pebs_broken(int cpu) break; case INTEL_FAM6_SANDYBRIDGE_X: - switch (cpu_data(cpu).x86_mask) { + switch (cpu_data(cpu).x86_stepping) { case 6: rev = 0x618; break; case 7: rev = 0x70c; break; } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index f924629836a8..5d103a87e984 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1131,7 +1131,7 @@ void __init intel_pmu_lbr_init_atom(void) * on PMU interrupt */ if (boot_cpu_data.x86_model == 28 - && boot_cpu_data.x86_mask < 10) { + && boot_cpu_data.x86_stepping < 10) { pr_cont("LBR disabled due to erratum"); return; } diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c index 1f5c47ab4c65..c5e441baccc7 100644 --- a/arch/x86/events/intel/p6.c +++ b/arch/x86/events/intel/p6.c @@ -233,7 +233,7 @@ static __initconst const struct x86_pmu p6_pmu = { static __init void p6_pmu_rdpmc_quirk(void) { - if (boot_cpu_data.x86_mask < 9) { + if (boot_cpu_data.x86_stepping < 9) { /* * PPro erratum 26; fixed in stepping 9 and above. */ diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 5391b0ae7cc3..d32bab65de70 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -92,7 +92,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) if (boot_cpu_data.x86 == 0x0F && boot_cpu_data.x86_vendor == X86_VENDOR_AMD && boot_cpu_data.x86_model <= 0x05 && - boot_cpu_data.x86_mask < 0x0A) + boot_cpu_data.x86_stepping < 0x0A) return 1; else if (amd_e400_c1e_detected) return 1; diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index d4aea31eec03..deca9b9c7923 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -139,7 +139,7 @@ static inline int alternatives_text_reserved(void *start, void *end) ".popsection\n" \ ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(newinstr, feature, 1) \ - ".popsection" + ".popsection\n" #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\ OLDINSTR_2(oldinstr, 1, 2) \ @@ -150,7 +150,7 @@ static inline int alternatives_text_reserved(void *start, void *end) ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \ ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ - ".popsection" + ".popsection\n" /* * Alternative instructions for different CPU types or capabilities. diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 44b8762fa0c7..166654218329 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -10,7 +10,34 @@ #include <asm/pgtable.h> #include <asm/special_insns.h> #include <asm/preempt.h> +#include <asm/asm.h> #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); #endif + +#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_X86_32 +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void); +#else +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void); +INDIRECT_THUNK(8) +INDIRECT_THUNK(9) +INDIRECT_THUNK(10) +INDIRECT_THUNK(11) +INDIRECT_THUNK(12) +INDIRECT_THUNK(13) +INDIRECT_THUNK(14) +INDIRECT_THUNK(15) +#endif +INDIRECT_THUNK(ax) +INDIRECT_THUNK(bx) +INDIRECT_THUNK(cx) +INDIRECT_THUNK(dx) +INDIRECT_THUNK(si) +INDIRECT_THUNK(di) +INDIRECT_THUNK(bp) +asmlinkage void __fill_rsb(void); +asmlinkage void __clear_rsb(void); + +#endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 7acb51c49fec..7bb29a416b77 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -11,10 +11,12 @@ # define __ASM_FORM_COMMA(x) " " #x "," #endif -#ifdef CONFIG_X86_32 +#ifndef __x86_64__ +/* 32 bit */ # define __ASM_SEL(a,b) __ASM_FORM(a) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a) #else +/* 64 bit */ # define __ASM_SEL(a,b) __ASM_FORM(b) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b) #endif @@ -125,4 +127,15 @@ /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif +#ifndef __ASSEMBLY__ +/* + * This output constraint should be used for any inline asm which has a "call" + * instruction. Otherwise the asm may be inserted before the frame pointer + * gets set up by the containing function. If you forget to do this, objtool + * may print a "call without frame pointer save/setup" warning. + */ +register unsigned long current_stack_pointer asm(_ASM_SP); +#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) +#endif + #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index bfb28caf97b1..78d1c6a3d221 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -23,6 +23,34 @@ #define wmb() asm volatile("sfence" ::: "memory") #endif +/** + * array_index_mask_nospec() - generate a mask that is ~0UL when the + * bounds check succeeds and 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * Returns: + * 0 - (index < size) + */ +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + unsigned long mask; + + asm ("cmp %1,%2; sbb %0,%0;" + :"=r" (mask) + :"g"(size),"r" (index) + :"cc"); + return mask; +} + +/* Override the default implementation from linux/nospec.h. */ +#define array_index_mask_nospec array_index_mask_nospec + +/* Prevent speculative execution past this barrier. */ +#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \ + "lfence", X86_FEATURE_LFENCE_RDTSC) + #ifdef CONFIG_X86_PPRO_FENCE #define dma_rmb() rmb() #else diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 1d2b69fc0ceb..8c101579f535 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -28,6 +28,7 @@ enum cpuid_leafs CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_8000_0007_EBX, + CPUID_7_EDX, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -78,8 +79,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + BUILD_BUG_ON_ZERO(NCAPINTS != 19)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -100,8 +102,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + BUILD_BUG_ON_ZERO(NCAPINTS != 19)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ @@ -135,6 +138,8 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; 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 454a37adb823..8eb23f5cf7f4 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -12,7 +12,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 18 /* N 32-bit words worth of info */ +#define NCAPINTS 19 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -194,13 +194,16 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ -#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ + +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */ #define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */ +#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ + /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ #define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ @@ -232,6 +235,7 @@ #define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ #define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ @@ -256,6 +260,9 @@ /* 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_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -291,6 +298,13 @@ #define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ #define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ + /* * BUG word(s) */ @@ -316,5 +330,8 @@ #define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ +#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ +#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ +#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 21c5ac15657b..1f8cca459c6c 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -59,6 +59,7 @@ #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) #define DISABLED_MASK17 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define DISABLED_MASK18 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 34a46dc076d3..75b748a1deb8 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -12,6 +12,7 @@ */ #define INTEL_FAM6_CORE_YONAH 0x0E + #define INTEL_FAM6_CORE2_MEROM 0x0F #define INTEL_FAM6_CORE2_MEROM_L 0x16 #define INTEL_FAM6_CORE2_PENRYN 0x17 @@ -21,6 +22,7 @@ #define INTEL_FAM6_NEHALEM_G 0x1F /* Auburndale / Havendale */ #define INTEL_FAM6_NEHALEM_EP 0x1A #define INTEL_FAM6_NEHALEM_EX 0x2E + #define INTEL_FAM6_WESTMERE 0x25 #define INTEL_FAM6_WESTMERE_EP 0x2C #define INTEL_FAM6_WESTMERE_EX 0x2F @@ -36,9 +38,9 @@ #define INTEL_FAM6_HASWELL_GT3E 0x46 #define INTEL_FAM6_BROADWELL_CORE 0x3D -#define INTEL_FAM6_BROADWELL_XEON_D 0x56 #define INTEL_FAM6_BROADWELL_GT3E 0x47 #define INTEL_FAM6_BROADWELL_X 0x4F +#define INTEL_FAM6_BROADWELL_XEON_D 0x56 #define INTEL_FAM6_SKYLAKE_MOBILE 0x4E #define INTEL_FAM6_SKYLAKE_DESKTOP 0x5E @@ -57,9 +59,10 @@ #define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ #define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ #define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ -#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Annidale */ +#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C #define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ +#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A /* Xeon Phi */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index cbd1d44da2d3..20cfeeb681c6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1113,7 +1113,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, static inline int emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type) { - return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0); + return x86_emulate_instruction(vcpu, 0, + emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0); } void kvm_enable_efer_bits(u64); diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 15eb75484cc0..98ccbd1dbb01 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -59,7 +59,6 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, extern int __apply_microcode_amd(struct microcode_amd *mc_amd); extern int apply_microcode_amd(int cpu); -extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size); #define PATCH_MAX_SIZE PAGE_SIZE diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index b601ddac5719..c768bc1550a1 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -37,6 +37,13 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) /* Intel MSRs. Some also available on other CPUs */ +#define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ +#define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ +#define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */ + +#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ +#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ + #define MSR_IA32_PERFCTR0 0x000000c1 #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd @@ -50,6 +57,11 @@ #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) #define MSR_MTRRcap 0x000000fe + +#define MSR_IA32_ARCH_CAPABILITIES 0x0000010a +#define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */ +#define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */ + #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e @@ -330,6 +342,9 @@ #define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c +#define MSR_F10H_DECFG 0xc0011029 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT) /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index b5fee97813cd..ed35b915b5c9 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -188,8 +188,7 @@ static __always_inline unsigned long long rdtsc_ordered(void) * that some other imaginary CPU is updating continuously with a * time stamp. */ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); + barrier_nospec(); return rdtsc(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h new file mode 100644 index 000000000000..76b058533e47 --- /dev/null +++ b/arch/x86/include/asm/nospec-branch.h @@ -0,0 +1,180 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_X86_NOSPEC_BRANCH_H_ +#define _ASM_X86_NOSPEC_BRANCH_H_ + +#include <asm/alternative.h> +#include <asm/alternative-asm.h> +#include <asm/cpufeatures.h> +#include <asm/msr-index.h> + +#ifdef __ASSEMBLY__ + +/* + * This should be used immediately before a retpoline alternative. It tells + * objtool where the retpolines are so that it can make sense of the control + * flow by just reading the original instruction(s) and ignoring the + * alternatives. + */ +.macro ANNOTATE_NOSPEC_ALTERNATIVE + .Lannotate_\@: + .pushsection .discard.nospec + .long .Lannotate_\@ - . + .popsection +.endm + +/* + * These are the bare retpoline primitives for indirect jmp and call. + * Do not use these directly; they only exist to make the ALTERNATIVE + * invocation below less ugly. + */ +.macro RETPOLINE_JMP reg:req + call .Ldo_rop_\@ +.Lspec_trap_\@: + pause + lfence + jmp .Lspec_trap_\@ +.Ldo_rop_\@: + mov \reg, (%_ASM_SP) + ret +.endm + +/* + * This is a wrapper around RETPOLINE_JMP so the called function in reg + * returns to the instruction after the macro. + */ +.macro RETPOLINE_CALL reg:req + jmp .Ldo_call_\@ +.Ldo_retpoline_jmp_\@: + RETPOLINE_JMP \reg +.Ldo_call_\@: + call .Ldo_retpoline_jmp_\@ +.endm + +/* + * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple + * indirect jmp/call which may be susceptible to the Spectre variant 2 + * attack. + */ +.macro JMP_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE_2 __stringify(jmp *\reg), \ + __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \ + __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD +#else + jmp *\reg +#endif +.endm + +.macro CALL_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE_2 __stringify(call *\reg), \ + __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\ + __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD +#else + call *\reg +#endif +.endm + +/* This clobbers the BX register */ +.macro FILL_RETURN_BUFFER nr:req ftr:req +#ifdef CONFIG_RETPOLINE + ALTERNATIVE "", "call __clear_rsb", \ftr +#endif +.endm + +#else /* __ASSEMBLY__ */ + +#define ANNOTATE_NOSPEC_ALTERNATIVE \ + "999:\n\t" \ + ".pushsection .discard.nospec\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" + +#if defined(CONFIG_X86_64) && defined(RETPOLINE) + +/* + * Since the inline asm uses the %V modifier which is only in newer GCC, + * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE. + */ +# define CALL_NOSPEC \ + ANNOTATE_NOSPEC_ALTERNATIVE \ + ALTERNATIVE( \ + "call *%[thunk_target]\n", \ + "call __x86_indirect_thunk_%V[thunk_target]\n", \ + X86_FEATURE_RETPOLINE) +# define THUNK_TARGET(addr) [thunk_target] "r" (addr) + +#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE) +/* + * For i386 we use the original ret-equivalent retpoline, because + * otherwise we'll run out of registers. We don't care about CET + * here, anyway. + */ +# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \ + " jmp 904f;\n" \ + " .align 16\n" \ + "901: call 903f;\n" \ + "902: pause;\n" \ + " lfence;\n" \ + " jmp 902b;\n" \ + " .align 16\n" \ + "903: addl $4, %%esp;\n" \ + " pushl %[thunk_target];\n" \ + " ret;\n" \ + " .align 16\n" \ + "904: call 901b;\n", \ + X86_FEATURE_RETPOLINE) + +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#else /* No retpoline for C / inline asm */ +# define CALL_NOSPEC "call *%[thunk_target]\n" +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif + +/* The Spectre V2 mitigation variants */ +enum spectre_v2_mitigation { + SPECTRE_V2_NONE, + SPECTRE_V2_RETPOLINE_MINIMAL, + SPECTRE_V2_RETPOLINE_MINIMAL_AMD, + SPECTRE_V2_RETPOLINE_GENERIC, + SPECTRE_V2_RETPOLINE_AMD, + SPECTRE_V2_IBRS, +}; + +extern char __indirect_thunk_start[]; +extern char __indirect_thunk_end[]; + +/* + * On VMEXIT we must ensure that no RSB predictions learned in the guest + * can be followed in the host, by overwriting the RSB completely. Both + * retpoline and IBRS mitigations for Spectre v2 need this; only on future + * CPUs with IBRS_ALL *might* it be avoided. + */ +static inline void vmexit_fill_RSB(void) +{ +#ifdef CONFIG_RETPOLINE + alternative_input("", + "call __fill_rsb", + X86_FEATURE_RETPOLINE, + ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory")); +#endif +} + +static inline void indirect_branch_prediction_barrier(void) +{ + asm volatile(ALTERNATIVE("", + "movl %[msr], %%ecx\n\t" + "movl %[val], %%eax\n\t" + "movl $0, %%edx\n\t" + "wrmsr", + X86_FEATURE_USE_IBPB) + : : [msr] "i" (MSR_IA32_PRED_CMD), + [val] "i" (PRED_CMD_IBPB) + : "eax", "ecx", "edx", "memory"); +} + +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 2536f90cd30c..5af0401ccff2 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -20,9 +20,15 @@ #ifdef CONFIG_PAGE_TABLE_ISOLATION extern int kaiser_enabled; +/* + * Instead of one PGD, we acquire two PGDs. Being order-1, it is + * both 8k in size and 8k-aligned. That lets us just flip bit 12 + * in a pointer to swap between the two 4k halves. + */ #else #define kaiser_enabled 0 #endif +#define PGD_ALLOCATION_ORDER kaiser_enabled void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); void ptdump_walk_pgd_level_checkwx(void); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 8cb52ee3ade6..ec15ca2b32d0 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -88,7 +88,7 @@ struct cpuinfo_x86 { __u8 x86; /* CPU family */ __u8 x86_vendor; /* CPU vendor */ __u8 x86_model; - __u8 x86_mask; + __u8 x86_stepping; #ifdef CONFIG_X86_32 char wp_works_ok; /* It doesn't on 386's */ @@ -113,7 +113,7 @@ struct cpuinfo_x86 { char x86_vendor_id[16]; char x86_model_id[64]; /* in KB - valid for CPUS which support this call: */ - int x86_cache_size; + unsigned int x86_cache_size; int x86_cache_alignment; /* In bytes */ /* Cache QoS architectural values: */ int x86_cache_max_rmid; /* max index */ @@ -156,8 +156,8 @@ 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 __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); @@ -391,8 +391,6 @@ struct thread_struct { unsigned short gsindex; #endif - u32 status; /* thread synchronous flags */ - #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; @@ -596,7 +594,7 @@ static inline void sync_core(void) { int tmp; -#ifdef CONFIG_M486 +#ifdef CONFIG_X86_32 /* * Do a CPUID if available, otherwise do a jump. The jump * can conveniently enough be the jump around CPUID. diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index fac9a5c0abe9..6847d85400a8 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -100,6 +100,7 @@ #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 0 #define REQUIRED_MASK17 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define REQUIRED_MASK18 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index e3c95e8e61c5..03eedc21246d 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task, * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ - if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. @@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index ad6f5eb07a95..89978b9c667a 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -54,6 +54,7 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level flags */ + u32 status; /* thread synchronous flags */ }; #define INIT_THREAD_INFO(tsk) \ @@ -152,17 +153,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__ -static inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; -#ifdef CONFIG_X86_64 - asm("mov %%rsp,%0" : "=g" (sp)); -#else - asm("mov %%esp,%0" : "=g" (sp)); -#endif - return sp; -} - /* * Walks up the stack frames to make sure that the specified object is * entirely contained by a single stack frame. @@ -224,7 +214,7 @@ static inline int arch_within_stack_frames(const void * const stack, #define in_ia32_syscall() true #else #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ - current->thread.status & TS_COMPAT) + current_thread_info()->status & TS_COMPAT) #endif /* diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 01fd0a7f48cd..688315b7a922 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -92,6 +92,7 @@ dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long); #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *, long); #endif +dotraplinkage void do_mce(struct pt_regs *, long); static inline int get_si_code(unsigned long condition) { diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index dead0f3921f3..a8d85a687cf4 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -123,6 +123,11 @@ extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() +#define __uaccess_begin_nospec() \ +({ \ + stac(); \ + barrier_nospec(); \ +}) /* * This is a type: either unsigned long, if the argument fits into @@ -432,7 +437,7 @@ do { \ ({ \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ @@ -474,6 +479,10 @@ struct __large_struct { unsigned long buf[100]; }; __uaccess_begin(); \ barrier(); +#define uaccess_try_nospec do { \ + current->thread.uaccess_err = 0; \ + __uaccess_begin_nospec(); \ + #define uaccess_catch(err) \ __uaccess_end(); \ (err) |= (current->thread.uaccess_err ? -EFAULT : 0); \ @@ -538,7 +547,7 @@ struct __large_struct { unsigned long buf[100]; }; * get_user_ex(...); * } get_user_catch(err) */ -#define get_user_try uaccess_try +#define get_user_try uaccess_try_nospec #define get_user_catch(err) uaccess_catch(err) #define get_user_ex(x, ptr) do { \ @@ -573,7 +582,7 @@ extern void __cmpxchg_wrong_size(void) __typeof__(ptr) __uval = (uval); \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ switch (size) { \ case 1: \ { \ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 7d3bdd1ed697..d6d245088dd5 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -102,17 +102,17 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u8 *)to, from, 1, ret, 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u16 *)to, from, 2, ret, 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u32 *)to, from, 4, ret, 4); __uaccess_end(); return ret; @@ -130,17 +130,17 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to, switch (n) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u8 *)to, from, 1, ret, 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u16 *)to, from, 2, ret, 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u32 *)to, from, 4, ret, 4); __uaccess_end(); return ret; diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 673059a109fe..6e5cc08134ba 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -59,31 +59,31 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size) return copy_user_generic(dst, (__force void *)src, size); switch (size) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u8 *)dst, (u8 __user *)src, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u16 *)dst, (u16 __user *)src, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u32 *)dst, (u32 __user *)src, ret, "l", "k", "=r", 4); __uaccess_end(); return ret; case 8: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 8); __uaccess_end(); return ret; case 10: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 10); if (likely(!ret)) @@ -93,7 +93,7 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size) __uaccess_end(); return ret; case 16: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 16); if (likely(!ret)) diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index a002b07a7099..6899cf187ba2 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -399,10 +399,11 @@ enum vmcs_field { #define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 2) #define VMX_NR_VPIDS (1 << 16) +#define VMX_VPID_EXTENT_INDIVIDUAL_ADDR 0 #define VMX_VPID_EXTENT_SINGLE_CONTEXT 1 #define VMX_VPID_EXTENT_ALL_CONTEXT 2 +#define VMX_VPID_EXTENT_SINGLE_NON_GLOBAL 3 -#define VMX_EPT_EXTENT_INDIVIDUAL_ADDR 0 #define VMX_EPT_EXTENT_CONTEXT 1 #define VMX_EPT_EXTENT_GLOBAL 2 #define VMX_EPT_EXTENT_SHIFT 24 @@ -419,8 +420,10 @@ enum vmcs_field { #define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) #define VMX_VPID_INVVPID_BIT (1ull << 0) /* (32 - 32) */ +#define VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT (1ull << 8) /* (40 - 32) */ #define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT (1ull << 9) /* (41 - 32) */ #define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT (1ull << 10) /* (42 - 32) */ +#define VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT (1ull << 11) /* (43 - 32) */ #define VMX_EPT_DEFAULT_GAW 3 #define VMX_EPT_MAX_GAW 0x4 diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 4865e10dbb55..62210da19a92 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -21,5 +21,6 @@ static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) } static inline bool vsyscall_enabled(void) { return false; } #endif +extern unsigned long vsyscall_pgprot; #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 8b678af866f7..ccdc23d89b60 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -44,6 +44,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/smap.h> +#include <asm/nospec-branch.h> #include <xen/interface/xen.h> #include <xen/interface/sched.h> @@ -216,9 +217,9 @@ privcmd_call(unsigned call, __HYPERCALL_5ARG(a1, a2, a3, a4, a5); stac(); - asm volatile("call *%[call]" + asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM - : [call] "a" (&hypercall_page[call]) + : [thunk_target] "a" (&hypercall_page[call]) : __HYPERCALL_CLOBBER5); clac(); diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 11cc600f4df0..0a1e8a67cc99 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -335,13 +335,12 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e #ifdef CONFIG_X86_IO_APIC #define MP_ISA_BUS 0 +static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, + u8 trigger, u32 gsi); + static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) { - int ioapic; - int pin; - struct mpc_intsrc mp_irq; - /* * Check bus_irq boundary. */ @@ -351,14 +350,6 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, } /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return; - pin = mp_find_ioapic_pin(ioapic, gsi); - - /* * TBD: This check is for faulty timer entries, where the override * erroneously sets the trigger to level, resulting in a HUGE * increase of timer interrupts! @@ -366,16 +357,8 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, if ((bus_irq == 0) && (trigger == 3)) trigger = 1; - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; - mp_irq.irqflag = (trigger << 2) | polarity; - mp_irq.srcbus = MP_ISA_BUS; - mp_irq.srcbusirq = bus_irq; /* IRQ */ - mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */ - mp_irq.dstirq = pin; /* INTIN# */ - - mp_save_irq(&mp_irq); - + if (mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi) < 0) + return; /* * Reset default identity mapping if gsi is also an legacy IRQ, * otherwise there will be more than one entry with the same GSI @@ -422,6 +405,34 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, return 0; } +static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, + u8 trigger, u32 gsi) +{ + struct mpc_intsrc mp_irq; + int ioapic, pin; + + /* Convert 'gsi' to 'ioapic.pin'(INTIN#) */ + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) { + pr_warn("Failed to find ioapic for gsi : %u\n", gsi); + return ioapic; + } + + pin = mp_find_ioapic_pin(ioapic, gsi); + + mp_irq.type = MP_INTSRC; + mp_irq.irqtype = mp_INT; + mp_irq.irqflag = (trigger << 2) | polarity; + mp_irq.srcbus = MP_ISA_BUS; + mp_irq.srcbusirq = bus_irq; + mp_irq.dstapic = mpc_ioapic_id(ioapic); + mp_irq.dstirq = pin; + + mp_save_irq(&mp_irq); + + return 0; +} + static int __init acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) { @@ -466,7 +477,11 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK) polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; - mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + if (bus_irq < NR_IRQS_LEGACY) + mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + else + mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5cb272a7a5a3..03b6e5c6cf23 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -46,17 +46,6 @@ static int __init setup_noreplace_smp(char *str) } __setup("noreplace-smp", setup_noreplace_smp); -#ifdef CONFIG_PARAVIRT -static int __initdata_or_module noreplace_paravirt = 0; - -static int __init setup_noreplace_paravirt(char *str) -{ - noreplace_paravirt = 1; - return 1; -} -__setup("noreplace-paravirt", setup_noreplace_paravirt); -#endif - #define DPRINTK(fmt, args...) \ do { \ if (debug_alternative) \ @@ -340,9 +329,12 @@ done: static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr) { unsigned long flags; + int i; - if (instr[0] != 0x90) - return; + for (i = 0; i < a->padlen; i++) { + if (instr[i] != 0x90) + return; + } local_irq_save(flags); add_nops(instr + (a->instrlen - a->padlen), a->padlen); @@ -585,9 +577,6 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start, struct paravirt_patch_site *p; char insnbuf[MAX_PATCH_LEN]; - if (noreplace_paravirt) - return; - for (p = start; p < end; p++) { unsigned int used; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 4fdf6230d93c..8462e2d4ed94 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -105,7 +105,7 @@ int amd_cache_northbridges(void) if (boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model >= 0x8 && (boot_cpu_data.x86_model > 0x9 || - boot_cpu_data.x86_mask >= 0x1)) + boot_cpu_data.x86_stepping >= 0x1)) amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE; if (boot_cpu_data.x86 == 0x15) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index f3557a1eb562..b5229abd1629 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -361,14 +361,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irq_data->chip_data = data; irq_data->hwirq = virq + i; err = assign_irq_vector_policy(virq + i, node, data, info); - if (err) + if (err) { + irq_data->chip_data = NULL; + free_apic_chip_data(data); goto error; + } } return 0; error: - x86_vector_free_irqs(domain, virq, i + 1); + x86_vector_free_irqs(domain, virq, i); return err; } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 880aa093268d..36ebb6de1a03 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -20,7 +20,7 @@ void foo(void) OFFSET(CPUINFO_x86, cpuinfo_x86, x86); OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); - OFFSET(CPUINFO_x86_mask, cpuinfo_x86, x86_mask); + OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping); OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level); OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability); OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 4a8697f7d4ef..33b63670bf09 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -20,13 +20,11 @@ obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += common.o obj-y += rdrand.o obj-y += match.o +obj-y += bugs.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o -obj-$(CONFIG_X86_32) += bugs.o -obj-$(CONFIG_X86_64) += bugs_64.o - obj-$(CONFIG_CPU_SUP_INTEL) += intel.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2b4cf04239b6..c375bc672f82 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -118,7 +118,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if (c->x86_model == 6 && c->x86_mask == 1) { + if (c->x86_model == 6 && c->x86_stepping == 1) { const int K6_BUG_LOOP = 1000000; int n; void (*f_vide)(void); @@ -147,7 +147,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) /* K6 with old style WHCR */ if (c->x86_model < 8 || - (c->x86_model == 8 && c->x86_mask < 8)) { + (c->x86_model == 8 && c->x86_stepping < 8)) { /* We can only write allocate on the low 508Mb */ if (mbytes > 508) mbytes = 508; @@ -166,7 +166,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if ((c->x86_model == 8 && c->x86_mask > 7) || + if ((c->x86_model == 8 && c->x86_stepping > 7) || c->x86_model == 9 || c->x86_model == 13) { /* The more serious chips .. */ @@ -219,7 +219,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx * As per AMD technical note 27212 0.2 */ - if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { + if ((c->x86_model == 8 && c->x86_stepping >= 1) || (c->x86_model > 8)) { rdmsr(MSR_K7_CLK_CTL, l, h); if ((l & 0xfff00000) != 0x20000000) { pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", @@ -239,12 +239,12 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * but they are not certified as MP capable. */ /* Athlon 660/661 is valid. */ - if ((c->x86_model == 6) && ((c->x86_mask == 0) || - (c->x86_mask == 1))) + if ((c->x86_model == 6) && ((c->x86_stepping == 0) || + (c->x86_stepping == 1))) return; /* Duron 670 is valid */ - if ((c->x86_model == 7) && (c->x86_mask == 0)) + if ((c->x86_model == 7) && (c->x86_stepping == 0)) return; /* @@ -254,8 +254,8 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for * more. */ - if (((c->x86_model == 6) && (c->x86_mask >= 2)) || - ((c->x86_model == 7) && (c->x86_mask >= 1)) || + if (((c->x86_model == 6) && (c->x86_stepping >= 2)) || + ((c->x86_model == 7) && (c->x86_stepping >= 1)) || (c->x86_model > 7)) if (cpu_has(c, X86_FEATURE_MP)) return; @@ -569,7 +569,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) /* Set MTRR capability flag if appropriate */ if (c->x86 == 5) if (c->x86_model == 13 || c->x86_model == 9 || - (c->x86_model == 8 && c->x86_mask >= 8)) + (c->x86_model == 8 && c->x86_stepping >= 8)) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) @@ -782,8 +782,32 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K8); if (cpu_has(c, X86_FEATURE_XMM2)) { - /* MFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + unsigned long long val; + int ret; + + /* + * A serializing LFENCE has less overhead than MFENCE, so + * use it for execution serialization. On families which + * don't have that MSR, LFENCE is already serializing. + * msr_set_bit() uses the safe accessors, too, even if the MSR + * is not present. + */ + msr_set_bit(MSR_F10H_DECFG, + MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + + /* + * Verify that the MSR write was successful (could be running + * under a hypervisor) and only then assume that LFENCE is + * serializing. + */ + ret = rdmsrl_safe(MSR_F10H_DECFG, &val); + if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); + } else { + /* MFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + } } /* @@ -810,11 +834,11 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) /* AMD errata T13 (order #21922) */ if ((c->x86 == 6)) { /* Duron Rev A0 */ - if (c->x86_model == 3 && c->x86_mask == 0) + if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; /* Tbird rev A1/A2 */ if (c->x86_model == 4 && - (c->x86_mask == 0 || c->x86_mask == 1)) + (c->x86_stepping == 0 || c->x86_stepping == 1)) size = 256; } return size; @@ -951,7 +975,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) } /* OSVW unavailable or ID unknown, match family-model-stepping range */ - ms = (cpu->x86_model << 4) | cpu->x86_mask; + ms = (cpu->x86_model << 4) | cpu->x86_stepping; while ((range = *erratum++)) if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && (ms >= AMD_MODEL_RANGE_START(range)) && diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0b6124315441..baddc9ed3454 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -9,6 +9,11 @@ */ #include <linux/init.h> #include <linux/utsname.h> +#include <linux/cpu.h> +#include <linux/module.h> + +#include <asm/nospec-branch.h> +#include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> @@ -16,23 +21,25 @@ #include <asm/msr.h> #include <asm/paravirt.h> #include <asm/alternative.h> +#include <asm/pgtable.h> +#include <asm/cacheflush.h> +#include <asm/intel-family.h> + +static void __init spectre_v2_select_mitigation(void); void __init check_bugs(void) { -#ifdef CONFIG_X86_32 - /* - * Regardless of whether PCID is enumerated, the SDM says - * that it can't be enabled in 32-bit mode. - */ - setup_clear_cpu_cap(X86_FEATURE_PCID); -#endif - identify_boot_cpu(); -#ifndef CONFIG_SMP - pr_info("CPU: "); - print_cpu_info(&boot_cpu_data); -#endif + if (!IS_ENABLED(CONFIG_SMP)) { + pr_info("CPU: "); + print_cpu_info(&boot_cpu_data); + } + + /* Select the proper spectre mitigation before patching alternatives */ + spectre_v2_select_mitigation(); + +#ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. * @@ -48,4 +55,278 @@ void __init check_bugs(void) alternative_instructions(); fpu__init_check_bugs(); +#else /* CONFIG_X86_64 */ + alternative_instructions(); + + /* + * Make sure the first 2MB area is not mapped by huge pages + * There are typically fixed size MTRRs in there and overlapping + * MTRRs into large pages causes slow downs. + * + * Right now we don't do that with gbpages because there seems + * very little benefit for that case. + */ + if (!direct_gbpages) + set_memory_4k((unsigned long)__va(0), 1); +#endif +} + +/* The kernel command line selection */ +enum spectre_v2_mitigation_cmd { + SPECTRE_V2_CMD_NONE, + SPECTRE_V2_CMD_AUTO, + SPECTRE_V2_CMD_FORCE, + SPECTRE_V2_CMD_RETPOLINE, + SPECTRE_V2_CMD_RETPOLINE_GENERIC, + SPECTRE_V2_CMD_RETPOLINE_AMD, +}; + +static const char *spectre_v2_strings[] = { + [SPECTRE_V2_NONE] = "Vulnerable", + [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline", + [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", + [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", + [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", +}; + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt + +static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; + +#ifdef RETPOLINE +static bool spectre_v2_bad_module; + +bool retpoline_module_ok(bool has_retpoline) +{ + if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) + return true; + + pr_err("System may be vulnerable to spectre v2\n"); + spectre_v2_bad_module = true; + return false; +} + +static inline const char *spectre_v2_module_string(void) +{ + return spectre_v2_bad_module ? " - vulnerable module loaded" : ""; +} +#else +static inline const char *spectre_v2_module_string(void) { return ""; } +#endif + +static void __init spec2_print_if_insecure(const char *reason) +{ + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s selected on command line.\n", reason); +} + +static void __init spec2_print_if_secure(const char *reason) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s selected on command line.\n", reason); +} + +static inline bool retp_compiler(void) +{ + return __is_defined(RETPOLINE); +} + +static inline bool match_option(const char *arg, int arglen, const char *opt) +{ + int len = strlen(opt); + + return len == arglen && !strncmp(arg, opt, len); +} + +static const struct { + const char *option; + enum spectre_v2_mitigation_cmd cmd; + bool secure; +} mitigation_options[] = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, +}; + +static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) +{ + char arg[20]; + int ret, i; + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; + + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_NONE; + else { + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); + if (ret < 0) + return SPECTRE_V2_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", arg); + return SPECTRE_V2_CMD_AUTO; + } + } + + if ((cmd == SPECTRE_V2_CMD_RETPOLINE || + cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + !IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); + return SPECTRE_V2_CMD_AUTO; + } + + if (mitigation_options[i].secure) + spec2_print_if_secure(mitigation_options[i].option); + else + spec2_print_if_insecure(mitigation_options[i].option); + + return cmd; +} + +/* Check for Skylake-like CPUs (for RSB handling) */ +static bool __init is_skylake_era(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + boot_cpu_data.x86 == 6) { + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + return true; + } + } + return false; +} + +static void __init spectre_v2_select_mitigation(void) +{ + enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); + enum spectre_v2_mitigation mode = SPECTRE_V2_NONE; + + /* + * If the CPU is not affected and the command line mode is NONE or AUTO + * then nothing to do. + */ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) && + (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO)) + return; + + switch (cmd) { + case SPECTRE_V2_CMD_NONE: + return; + + case SPECTRE_V2_CMD_FORCE: + case SPECTRE_V2_CMD_AUTO: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; + case SPECTRE_V2_CMD_RETPOLINE_AMD: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_amd; + break; + case SPECTRE_V2_CMD_RETPOLINE_GENERIC: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_generic; + break; + case SPECTRE_V2_CMD_RETPOLINE: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; + } + pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!"); + return; + +retpoline_auto: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + retpoline_amd: + if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { + pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); + goto retpoline_generic; + } + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : + SPECTRE_V2_RETPOLINE_MINIMAL_AMD; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } else { + retpoline_generic: + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC : + SPECTRE_V2_RETPOLINE_MINIMAL; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } + + spectre_v2_enabled = mode; + pr_info("%s\n", spectre_v2_strings[mode]); + + /* + * If neither SMEP nor PTI are available, there is a risk of + * hitting userspace addresses in the RSB after a context switch + * from a shallow call stack to a deeper one. To prevent this fill + * the entire RSB, even when using IBRS. + * + * Skylake era CPUs have a separate issue with *underflow* of the + * RSB, when they will predict 'ret' targets from the generic BTB. + * The proper mitigation for this is IBRS. If IBRS is not supported + * or deactivated in favour of retpolines the RSB fill on context + * switch is required. + */ + if ((!boot_cpu_has(X86_FEATURE_KAISER) && + !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { + setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); + pr_info("Spectre v2 mitigation: Filling RSB on context switch\n"); + } + + /* Initialize Indirect Branch Prediction Barrier if supported */ + if (boot_cpu_has(X86_FEATURE_IBPB)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); + } } + +#undef pr_fmt + +#ifdef CONFIG_SYSFS +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + return sprintf(buf, "Not affected\n"); + if (boot_cpu_has(X86_FEATURE_KAISER)) + return sprintf(buf, "Mitigation: PTI\n"); + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) + return sprintf(buf, "Not affected\n"); + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); +} + +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + return sprintf(buf, "Not affected\n"); + + return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + spectre_v2_module_string()); +} +#endif diff --git a/arch/x86/kernel/cpu/bugs_64.c b/arch/x86/kernel/cpu/bugs_64.c deleted file mode 100644 index a972ac4c7e7d..000000000000 --- a/arch/x86/kernel/cpu/bugs_64.c +++ /dev/null @@ -1,33 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * Copyright (C) 2000 SuSE - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <asm/alternative.h> -#include <asm/bugs.h> -#include <asm/processor.h> -#include <asm/mtrr.h> -#include <asm/cacheflush.h> - -void __init check_bugs(void) -{ - identify_boot_cpu(); -#if !defined(CONFIG_SMP) - pr_info("CPU: "); - print_cpu_info(&boot_cpu_data); -#endif - alternative_instructions(); - - /* - * Make sure the first 2MB area is not mapped by huge pages - * There are typically fixed size MTRRs in there and overlapping - * MTRRs into large pages causes slow downs. - * - * Right now we don't do that with gbpages because there seems - * very little benefit for that case. - */ - if (!direct_gbpages) - set_memory_4k((unsigned long)__va(0), 1); -} diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 1661d8ec9280..4d2f61f92fed 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -134,7 +134,7 @@ static void init_centaur(struct cpuinfo_x86 *c) clear_cpu_cap(c, X86_FEATURE_TSC); break; case 8: - switch (c->x86_mask) { + switch (c->x86_stepping) { default: name = "2"; break; @@ -209,7 +209,7 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) * - Note, it seems this may only be in engineering samples. */ if ((c->x86 == 6) && (c->x86_model == 9) && - (c->x86_mask == 1) && (size == 65)) + (c->x86_stepping == 1) && (size == 65)) size -= 1; return size; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 918e44772b04..301bbd1f2373 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -44,6 +44,8 @@ #include <asm/pat.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #ifdef CONFIG_X86_LOCAL_APIC #include <asm/uv/uv.h> @@ -480,8 +482,8 @@ 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) { @@ -697,7 +699,7 @@ void cpu_detect(struct cpuinfo_x86 *c) cpuid(0x00000001, &tfms, &misc, &junk, &cap0); c->x86 = x86_family(tfms); c->x86_model = x86_model(tfms); - c->x86_mask = x86_stepping(tfms); + c->x86_stepping = x86_stepping(tfms); if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; @@ -706,6 +708,36 @@ void cpu_detect(struct cpuinfo_x86 *c) } } +static void apply_forced_caps(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < NCAPINTS + NBUGINTS; i++) { + c->x86_capability[i] &= ~cpu_caps_cleared[i]; + c->x86_capability[i] |= cpu_caps_set[i]; + } +} + +static void init_speculation_control(struct cpuinfo_x86 *c) +{ + /* + * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, + * and they also have a different bit for STIBP support. Also, + * a hypervisor might have set the individual AMD bits even on + * Intel CPUs, for finer-grained selection of what's available. + * + * We use the AMD bits in 0x8000_0008 EBX as the generic hardware + * features, which are visible in /proc/cpuinfo and used by the + * kernel. So set those accordingly from the Intel bits. + */ + if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_IBPB); + } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) + set_cpu_cap(c, X86_FEATURE_STIBP); +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -727,6 +759,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); c->x86_capability[CPUID_7_0_EBX] = ebx; c->x86_capability[CPUID_7_ECX] = ecx; + c->x86_capability[CPUID_7_EDX] = edx; } /* Extended state features: level 0x0000000d */ @@ -799,6 +832,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + init_speculation_control(c); } static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -827,6 +861,41 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } +static const __initconst struct x86_cpu_id cpu_no_speculation[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_CENTAUR, 5 }, + { X86_VENDOR_INTEL, 5 }, + { X86_VENDOR_NSC, 5 }, + { X86_VENDOR_ANY, 4 }, + {} +}; + +static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { + { X86_VENDOR_AMD }, + {} +}; + +static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = 0; + + if (x86_match_cpu(cpu_no_meltdown)) + return false; + + if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + /* Rogue Data Cache Load? No! */ + if (ia32_cap & ARCH_CAP_RDCL_NO) + return false; + + return true; +} + /* * Do minimum CPU detection early. * Fields really needed: vendor, cpuid_level, family, model, mask, @@ -872,7 +941,23 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) } setup_force_cpu_cap(X86_FEATURE_ALWAYS); + + if (!x86_match_cpu(cpu_no_speculation)) { + if (cpu_vulnerable_to_meltdown(c)) + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + } + fpu__init_system(c); + +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif } void __init early_cpu_init(void) @@ -1059,9 +1144,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) int i; c->loops_per_jiffy = loops_per_jiffy; - c->x86_cache_size = -1; + c->x86_cache_size = 0; c->x86_vendor = X86_VENDOR_UNKNOWN; - c->x86_model = c->x86_mask = 0; /* So far unknown... */ + c->x86_model = c->x86_stepping = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; @@ -1086,10 +1171,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_identify(c); /* Clear/Set all flags overridden by options, after probe */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + apply_forced_caps(c); #ifdef CONFIG_X86_64 c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); @@ -1151,10 +1233,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) * Clear/Set all flags overridden by options, need do it * before following smp all cpus cap AND. */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + apply_forced_caps(c); /* * On SMP, boot_cpu_data holds the common feature set between @@ -1312,8 +1391,8 @@ void print_cpu_info(struct cpuinfo_x86 *c) pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model); - if (c->x86_mask || c->cpuid_level >= 0) - pr_cont(", stepping: 0x%x)\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + pr_cont(", stepping: 0x%x)\n", c->x86_stepping); else pr_cont(")\n"); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index bd9dcd6b712d..455d8ada9b9a 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -212,7 +212,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* common case step number/rev -- exceptions handled below */ c->x86_model = (dir1 >> 4) + 1; - c->x86_mask = dir1 & 0xf; + c->x86_stepping = dir1 & 0xf; /* Now cook; the original recipe is by Channing Corn, from Cyrix. * We do the same thing for each generation: we work out diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fcd484d2bb03..6ed206bd9071 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -61,6 +61,56 @@ void check_mpx_erratum(struct cpuinfo_x86 *c) } } +/* + * Early microcode releases for the Spectre v2 mitigation were broken. + * Information taken from; + * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf + * - https://kb.vmware.com/s/article/52345 + * - Microcode revisions observed in the wild + * - Release note from 20180108 microcode release + */ +struct sku_microcode { + u8 model; + u8 stepping; + u32 microcode; +}; +static const struct sku_microcode spectre_bad_microcodes[] = { + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 }, + { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, + { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, + { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, + { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, + { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 }, + { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 }, + { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 }, + { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 }, + { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 }, + { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, + { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, + { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, + /* Observed in the wild */ + { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, + { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, +}; + +static bool bad_spectre_microcode(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { + if (c->x86_model == spectre_bad_microcodes[i].model && + c->x86_stepping == spectre_bad_microcodes[i].stepping) + return (c->microcode <= spectre_bad_microcodes[i].microcode); + } + return false; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -87,6 +137,19 @@ static void early_init_intel(struct cpuinfo_x86 *c) rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode); } + /* Now if any of them are set, check the blacklist and clear the lot */ + if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || + cpu_has(c, X86_FEATURE_INTEL_STIBP) || + cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || + cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) { + pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n"); + setup_clear_cpu_cap(X86_FEATURE_IBRS); + setup_clear_cpu_cap(X86_FEATURE_IBPB); + setup_clear_cpu_cap(X86_FEATURE_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + } + /* * Atom erratum AAE44/AAF40/AAG38/AAH41: * @@ -95,7 +158,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * need the microcode to have already been loaded... so if it is * not, recommend a BIOS update and disable large pages. */ - if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 && + if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 && c->microcode < 0x20e) { pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n"); clear_cpu_cap(c, X86_FEATURE_PSE); @@ -111,7 +174,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* CPUID workaround for 0F33/0F34 CPU */ if (c->x86 == 0xF && c->x86_model == 0x3 - && (c->x86_mask == 0x3 || c->x86_mask == 0x4)) + && (c->x86_stepping == 0x3 || c->x86_stepping == 0x4)) c->x86_phys_bits = 36; /* @@ -226,7 +289,7 @@ int ppro_with_ram_bug(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask < 8) { + boot_cpu_data.x86_stepping < 8) { pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n"); return 1; } @@ -243,7 +306,7 @@ static void intel_smp_check(struct cpuinfo_x86 *c) * Mask B, Pentium, but not Pentium MMX */ if (c->x86 == 5 && - c->x86_mask >= 1 && c->x86_mask <= 4 && + c->x86_stepping >= 1 && c->x86_stepping <= 4 && c->x86_model <= 3) { /* * Remember we have B step Pentia with bugs @@ -286,7 +349,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until * model 3 mask 3 */ - if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633) + if ((c->x86<<8 | c->x86_model<<4 | c->x86_stepping) < 0x633) clear_cpu_cap(c, X86_FEATURE_SEP); /* @@ -304,7 +367,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * P4 Xeon erratum 037 workaround. * Hardware prefetcher may cause stale data to be loaded into the cache. */ - if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) { + if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_stepping == 1)) { if (msr_set_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) > 0) { pr_info("CPU: C0 stepping P4 Xeon detected.\n"); @@ -319,7 +382,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * Specification Update"). */ if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 && - (c->x86_mask < 0x6 || c->x86_mask == 0xb)) + (c->x86_stepping < 0x6 || c->x86_stepping == 0xb)) set_cpu_bug(c, X86_BUG_11AP); @@ -538,7 +601,7 @@ static void init_intel(struct cpuinfo_x86 *c) case 6: if (l2 == 128) p = "Celeron (Mendocino)"; - else if (c->x86_mask == 0 || c->x86_mask == 5) + else if (c->x86_stepping == 0 || c->x86_stepping == 5) p = "Celeron-A"; break; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index de6626c18e42..be6337156502 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -934,6 +934,8 @@ static int __populate_cache_leaves(unsigned int cpu) ci_leaf_init(this_leaf++, &id4_regs); __cache_cpumap_setup(cpu, idx, &id4_regs); } + this_cpu_ci->cpu_map_populated = true; + return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 517619ea6498..99165b206df3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -152,7 +152,6 @@ static void raise_mce(struct mce *m) if (context == MCJ_CTX_RANDOM) return; -#ifdef CONFIG_X86_LOCAL_APIC if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) { unsigned long start; int cpu; @@ -192,9 +191,7 @@ static void raise_mce(struct mce *m) raise_local(); put_cpu(); put_online_cpus(); - } else -#endif - { + } else { preempt_disable(); raise_local(); preempt_enable(); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8ca5f8ad008e..fe5cd6ea1f0e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1754,6 +1754,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code) void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check; +dotraplinkage void do_mce(struct pt_regs *regs, long error_code) +{ + machine_check_vector(regs, error_code); +} + /* * Called for each booted CPU to set up machine checks. * Must be called with preempt off: diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index b74bb29db6b9..732bb03fcf91 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -135,6 +135,9 @@ static size_t compute_container_size(u8 *data, u32 total_size) return size; } +static enum ucode_state +load_microcode_amd(bool save, u8 family, const u8 *data, size_t size); + /* * Early load occurs before we can vmalloc(). So we look for the microcode * patch container file in initrd, traverse equivalent cpu table, look for a @@ -451,7 +454,7 @@ int __init save_microcode_in_initrd_amd(void) eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); - ret = load_microcode_amd(smp_processor_id(), eax, container, container_size); + ret = load_microcode_amd(true, eax, container, container_size); if (ret != UCODE_OK) retval = -EINVAL; @@ -864,7 +867,8 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, return UCODE_OK; } -enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size) +static enum ucode_state +load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) { enum ucode_state ret; @@ -878,8 +882,8 @@ enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t s #ifdef CONFIG_X86_32 /* save BSP's matching patch for early load */ - if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) { - struct ucode_patch *p = find_patch(cpu); + if (save) { + struct ucode_patch *p = find_patch(0); if (p) { memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), @@ -911,11 +915,12 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, { char fw_name[36] = "amd-ucode/microcode_amd.bin"; struct cpuinfo_x86 *c = &cpu_data(cpu); + bool bsp = c->cpu_index == boot_cpu_data.cpu_index; enum ucode_state ret = UCODE_NFOUND; const struct firmware *fw; /* reload ucode container only on the boot cpu */ - if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index) + if (!refresh_fw || !bsp) return UCODE_OK; if (c->x86 >= 0x15) @@ -932,7 +937,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, goto fw_release; } - ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size); + ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size); fw_release: release_firmware(fw); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 5ce5155f0695..0afaf00b029b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -43,7 +43,7 @@ #define MICROCODE_VERSION "2.01" static struct microcode_ops *microcode_ops; -static bool dis_ucode_ldr; +static bool dis_ucode_ldr = true; /* * Synchronization. @@ -73,6 +73,7 @@ struct cpu_info_ctx { static bool __init check_loader_disabled_bsp(void) { static const char *__dis_opt_str = "dis_ucode_ldr"; + u32 a, b, c, d; #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); @@ -85,8 +86,20 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (cmdline_find_option_bool(cmdline, option)) - *res = true; + a = 1; + c = 0; + native_cpuid(&a, &b, &c, &d); + + /* + * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not + * completely accurate as xen pv guests don't see that CPUID bit set but + * that's good enough as they don't land on the BSP path anyway. + */ + if (c & BIT(31)) + return *res; + + if (cmdline_find_option_bool(cmdline, option) <= 0) + *res = false; return *res; } @@ -114,9 +127,7 @@ void __init load_ucode_bsp(void) { int vendor; unsigned int family; - - if (check_loader_disabled_bsp()) - return; + bool intel = true; if (!have_cpuid_p()) return; @@ -126,16 +137,27 @@ void __init load_ucode_bsp(void) switch (vendor) { case X86_VENDOR_INTEL: - if (family >= 6) - load_ucode_intel_bsp(); + if (family < 6) + return; break; + case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(family); + if (family < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(family); } static bool check_loader_disabled_ap(void) @@ -154,9 +176,6 @@ void load_ucode_ap(void) if (check_loader_disabled_ap()) return; - if (!have_cpuid_p()) - return; - vendor = x86_cpuid_vendor(); family = x86_cpuid_family(); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 13dbcc0f9d03..4bcd30c87531 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -40,6 +40,9 @@ #include <asm/setup.h> #include <asm/msr.h> +/* last level cache size per core */ +static int llc_size_per_core; + /* * Temporary microcode blobs pointers storage. We note here during early load * the pointers to microcode blobs we've got from whatever storage (detached @@ -1051,8 +1054,19 @@ static bool is_blacklisted(unsigned int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); - if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) { - pr_err_once("late loading on model 79 is disabled.\n"); + /* + * Late loading on model 79 with microcode revision less than 0x0b000021 + * and LLC size per core bigger than 2.5MB may result in a system hang. + * This behavior is documented in item BDF90, #334165 (Intel Xeon + * Processor E7-8800/4800 v4 Product Family). + */ + if (c->x86 == 6 && + c->x86_model == INTEL_FAM6_BROADWELL_X && + c->x86_stepping == 0x01 && + llc_size_per_core > 2621440 && + c->microcode < 0x0b000021) { + pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); + pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); return true; } @@ -1071,7 +1085,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, return UCODE_NFOUND; sprintf(name, "intel-ucode/%02x-%02x-%02x", - c->x86, c->x86_model, c->x86_mask); + c->x86, c->x86_model, c->x86_stepping); if (request_firmware_direct(&firmware, name, device)) { pr_debug("data file %s load failed\n", name); @@ -1116,6 +1130,15 @@ static struct microcode_ops microcode_intel_ops = { .microcode_fini_cpu = microcode_fini_cpu, }; +static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) +{ + u64 llc_size = c->x86_cache_size * 1024ULL; + + do_div(llc_size, c->x86_max_cores); + + return (int)llc_size; +} + struct microcode_ops * __init init_intel_microcode(void) { struct cpuinfo_x86 *c = &boot_cpu_data; @@ -1126,6 +1149,8 @@ struct microcode_ops * __init init_intel_microcode(void) return NULL; } + llc_size_per_core = calc_llc_size_per_core(c); + return µcode_intel_ops; } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fdc55215d44d..e12ee86906c6 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -859,7 +859,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, */ if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask <= 7) { + boot_cpu_data.x86_stepping <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 24e87e74990d..fae740c22657 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -699,8 +699,8 @@ void __init mtrr_bp_init(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 0xF && boot_cpu_data.x86_model == 0x3 && - (boot_cpu_data.x86_mask == 0x3 || - boot_cpu_data.x86_mask == 0x4)) + (boot_cpu_data.x86_stepping == 0x3 || + boot_cpu_data.x86_stepping == 0x4)) phys_addr = 36; size_or_mask = SIZE_OR_MASK_BITS(phys_addr); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 18ca99f2798b..c4f772d3f35c 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -70,8 +70,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) c->x86_model, c->x86_model_id[0] ? c->x86_model_id : "unknown"); - if (c->x86_mask || c->cpuid_level >= 0) - seq_printf(m, "stepping\t: %d\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + seq_printf(m, "stepping\t: %d\n", c->x86_stepping); else seq_puts(m, "stepping\t: unknown\n"); if (c->microcode) @@ -87,8 +87,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) } /* Cache size */ - if (c->x86_cache_size >= 0) - seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); + if (c->x86_cache_size) + seq_printf(m, "cache size\t: %u KB\n", c->x86_cache_size); show_cpuinfo_core(m, c, cpu); show_cpuinfo_misc(m, c); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 1db8dc490b66..afbb52532791 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,9 +31,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit cpuid_bits[] = { - { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, - { X86_FEATURE_AVX512_4VNNIW, CR_EDX, 2, 0x00000007, 0 }, - { X86_FEATURE_AVX512_4FMAPS, CR_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 2dabea46f039..82155d0cc310 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -35,7 +35,7 @@ #define X86 new_cpu_data+CPUINFO_x86 #define X86_VENDOR new_cpu_data+CPUINFO_x86_vendor #define X86_MODEL new_cpu_data+CPUINFO_x86_model -#define X86_MASK new_cpu_data+CPUINFO_x86_mask +#define X86_STEPPING new_cpu_data+CPUINFO_x86_stepping #define X86_HARD_MATH new_cpu_data+CPUINFO_hard_math #define X86_CPUID new_cpu_data+CPUINFO_cpuid_level #define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability @@ -441,7 +441,7 @@ enable_paging: shrb $4,%al movb %al,X86_MODEL andb $0x0f,%cl # mask mask revision - movb %cl,X86_MASK + movb %cl,X86_STEPPING movl %edx,X86_CAPABILITY is486: diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 1f38d9a4d9de..2763573ee1d2 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -19,6 +19,7 @@ #include <linux/mm.h> #include <asm/apic.h> +#include <asm/nospec-branch.h> #ifdef CONFIG_DEBUG_STACKOVERFLOW @@ -54,17 +55,17 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack); static void call_on_stack(void *func, void *stack) { asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=b" (stack) : "0" (stack), - "D"(func) + [thunk_target] "D"(func) : "memory", "cc", "edx", "ecx", "eax"); } static inline void *current_stack(void) { - return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); } static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) @@ -88,17 +89,17 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) /* Save the next esp at the bottom of the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=a" (arg1), "=b" (isp) : "0" (desc), "1" (isp), - "D" (desc->handle_irq) + [thunk_target] "D" (desc->handle_irq) : "memory", "cc", "ecx"); return 1; } @@ -139,7 +140,7 @@ void do_softirq_own_stack(void) /* Push the previous esp onto the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 4d74f7386a61..dc20da1c78f0 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -37,6 +37,7 @@ #include <asm/alternative.h> #include <asm/insn.h> #include <asm/debugreg.h> +#include <asm/nospec-branch.h> #include "common.h" @@ -192,7 +193,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src) } /* Check whether insn is indirect jump */ -static int insn_is_indirect_jump(struct insn *insn) +static int __insn_is_indirect_jump(struct insn *insn) { return ((insn->opcode.bytes[0] == 0xff && (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ @@ -226,6 +227,26 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) return (start <= target && target <= start + len); } +static int insn_is_indirect_jump(struct insn *insn) +{ + int ret = __insn_is_indirect_jump(insn); + +#ifdef CONFIG_RETPOLINE + /* + * Jump to x86_indirect_thunk_* is treated as an indirect jump. + * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with + * older gcc may use indirect jump. So we add this check instead of + * replace indirect-jump check. + */ + if (!ret) + ret = insn_jump_into_range(insn, + (unsigned long)__indirect_thunk_start, + (unsigned long)__indirect_thunk_end - + (unsigned long)__indirect_thunk_start); +#endif + return ret; +} + /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index 7b0d3da52fb4..287ec3bc141f 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -8,7 +8,7 @@ #include <asm/ptrace.h> #include <asm/ftrace.h> #include <asm/export.h> - +#include <asm/nospec-branch.h> .code64 .section .entry.text, "ax" @@ -290,8 +290,9 @@ trace: * ip and parent ip are used and the list function is called when * function tracing is enabled. */ - call *ftrace_trace_function + movq ftrace_trace_function, %r8 + CALL_NOSPEC %r8 restore_mcount_regs jmp fgraph_trace @@ -334,5 +335,5 @@ GLOBAL(return_to_handler) movq 8(%rsp), %rdx movq (%rsp), %rax addq $24, %rsp - jmp *%rdi + JMP_NOSPEC %rdi #endif diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 0f8d20497383..d0fb941330c6 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -406,7 +406,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) processor.apicver = mpc_default_type > 4 ? 0x10 : 0x01; processor.cpuflag = CPU_ENABLED; processor.cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; + (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_stepping; processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX]; processor.reserved[0] = 0; processor.reserved[1] = 0; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 0887d2ae3797..dffe81d3c261 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -538,7 +538,7 @@ void set_personality_ia32(bool x32) current->personality &= ~READ_IMPLIES_EXEC; /* in_compat_syscall() uses the presence of the x32 syscall bit flag to determine compat status */ - current->thread.status &= ~TS_COMPAT; + current_thread_info()->status &= ~TS_COMPAT; } else { set_thread_flag(TIF_IA32); clear_thread_flag(TIF_X32); @@ -546,7 +546,7 @@ void set_personality_ia32(bool x32) current->mm->context.ia32_compat = TIF_IA32; current->personality |= force_personality32; /* Prepare the first "return" to user space */ - current->thread.status |= TS_COMPAT; + current_thread_info()->status |= TS_COMPAT; } } EXPORT_SYMBOL_GPL(set_personality_ia32); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 0e63c0267f99..e497d374412a 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -934,7 +934,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) */ regs->orig_ax = value; if (syscall_get_nr(child, regs) >= 0) - child->thread.status |= TS_I386_REGS_POKED; + child->thread_info.status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 763af1d0de64..b1a5d252d482 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -785,7 +785,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * than the tracee. */ #ifdef CONFIG_IA32_EMULATION - if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 8402907825b0..21454e254a4c 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -134,6 +134,16 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn, return -1; set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot)); pte_unmap(pte); + + /* + * PTI poisons low addresses in the kernel page tables in the + * name of making them unusable for userspace. To execute + * code at such a low address, the poison must be cleared. + * + * Note: 'pgd' actually gets set in pud_alloc(). + */ + pgd->pgd &= ~_PAGE_NX; + return 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index bd4e3d4d3625..322f433fbc76 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -153,7 +153,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) * from double_fault. */ BUG_ON((unsigned long)(current_top_of_stack() - - current_stack_pointer()) >= THREAD_SIZE); + current_stack_pointer) >= THREAD_SIZE); preempt_enable_no_resched(); } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 44bf5cf417d3..d07a9390023e 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -693,7 +693,6 @@ unsigned long native_calibrate_tsc(void) case INTEL_FAM6_KABYLAKE_DESKTOP: crystal_khz = 24000; /* 24.0 MHz */ break; - case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ATOM_DENVERTON: crystal_khz = 25000; /* 25.0 MHz */ break; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 4b3012888ada..8a1d63591399 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -160,11 +160,12 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) static void mark_screen_rdonly(struct mm_struct *mm) { + struct vm_area_struct *vma; + spinlock_t *ptl; pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - spinlock_t *ptl; int i; down_write(&mm->mmap_sem); @@ -177,7 +178,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pmd = pmd_offset(pud, 0xA0000); if (pmd_trans_huge(*pmd)) { - struct vm_area_struct *vma = find_vma(mm, 0xA0000); + vma = find_vma(mm, 0xA0000); split_huge_pmd(vma, pmd, 0xA0000); } if (pmd_none_or_clear_bad(pmd)) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index dbf67f64d5ec..c7194e97c3d4 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -105,6 +105,13 @@ SECTIONS SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) + +#ifdef CONFIG_RETPOLINE + __indirect_thunk_start = .; + *(.text.__x86.indirect_thunk) + __indirect_thunk_end = .; +#endif + /* End of text section */ _etext = .; } :text = 0x9090 diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index ab8e32f7b9a8..9150e09773cb 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -22,7 +22,8 @@ config KVM depends on HAVE_KVM depends on HIGH_RES_TIMERS # for TASKSTATS/TASK_DELAY_ACCT: - depends on NET + depends on NET && MULTIUSER + depends on X86_LOCAL_APIC select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 91af75e37306..93f924de06cf 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -355,6 +355,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + /* cpuid 0x80000008.ebx */ + const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(IBPB) | F(IBRS); + /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | @@ -376,6 +380,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = F(PKU) | 0 /*OSPKE*/; + /* cpuid 7.0.edx*/ + const u32 kvm_cpuid_7_0_edx_x86_features = + F(SPEC_CTRL) | F(ARCH_CAPABILITIES); + /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -458,12 +466,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); + entry->edx &= kvm_cpuid_7_0_edx_x86_features; + cpuid_mask(&entry->edx, CPUID_7_EDX); } else { entry->ebx = 0; entry->ecx = 0; + entry->edx = 0; } entry->eax = 0; - entry->edx = 0; break; } case 9: @@ -607,7 +617,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (!g_phys_as) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); - entry->ebx = entry->edx = 0; + entry->edx = 0; + /* IBRS and IBPB aren't necessarily present in hardware cpuid */ + if (boot_cpu_has(X86_FEATURE_IBPB)) + entry->ebx |= F(IBPB); + if (boot_cpu_has(X86_FEATURE_IBRS)) + entry->ebx |= F(IBRS); + entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); break; } case 0x80000019: diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 9368fecca3ee..d1beb7156704 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -160,6 +160,37 @@ static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu) return best && (best->edx & bit(X86_FEATURE_RDTSCP)); } +static inline bool guest_cpuid_has_ibpb(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best && (best->ebx & bit(X86_FEATURE_IBPB))) + return true; + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); +} + +static inline bool guest_cpuid_has_ibrs(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best && (best->ebx & bit(X86_FEATURE_IBRS))) + return true; + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); +} + +static inline bool guest_cpuid_has_arch_capabilities(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->edx & bit(X86_FEATURE_ARCH_CAPABILITIES)); +} + + /* * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3 */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c8f8dd8ca0a1..c8d573822e60 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -25,6 +25,7 @@ #include <asm/kvm_emulate.h> #include <linux/stringify.h> #include <asm/debugreg.h> +#include <asm/nospec-branch.h> #include "x86.h" #include "tss.h" @@ -1012,8 +1013,8 @@ static __always_inline u8 test_cc(unsigned int condition, unsigned long flags) void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf); flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; - asm("push %[flags]; popf; call *%[fastop]" - : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags)); + asm("push %[flags]; popf; " CALL_NOSPEC + : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags)); return rc; } @@ -4990,6 +4991,8 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) bool op_prefix = false; bool has_seg_override = false; struct opcode opcode; + u16 dummy; + struct desc_struct desc; ctxt->memop.type = OP_NONE; ctxt->memopp = NULL; @@ -5008,6 +5011,11 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) switch (mode) { case X86EMUL_MODE_REAL: case X86EMUL_MODE_VM86: + def_op_bytes = def_ad_bytes = 2; + ctxt->ops->get_segment(ctxt, &dummy, &desc, NULL, VCPU_SREG_CS); + if (desc.d) + def_op_bytes = def_ad_bytes = 4; + break; case X86EMUL_MODE_PROT16: def_op_bytes = def_ad_bytes = 2; break; @@ -5299,15 +5307,14 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { - register void *__sp asm(_ASM_SP); ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; if (!(ctxt->d & ByteOp)) fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; - asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" + asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop), "+r"(__sp) + [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 6e219e5c07d2..5f810bb80802 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -257,8 +257,7 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) index == RTC_GSI) { if (kvm_apic_match_dest(vcpu, NULL, 0, e->fields.dest_id, e->fields.dest_mode) || - (e->fields.trig_mode == IOAPIC_EDGE_TRIG && - kvm_apic_pending_eoi(vcpu, e->fields.vector))) + kvm_apic_pending_eoi(vcpu, e->fields.vector)) __set_bit(e->fields.vector, ioapic_handled_vectors); } @@ -279,6 +278,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) { unsigned index; bool mask_before, mask_after; + int old_remote_irr, old_delivery_status; union kvm_ioapic_redirect_entry *e; switch (ioapic->ioregsel) { @@ -301,14 +301,28 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) return; e = &ioapic->redirtbl[index]; mask_before = e->fields.mask; + /* Preserve read-only fields */ + old_remote_irr = e->fields.remote_irr; + old_delivery_status = e->fields.delivery_status; if (ioapic->ioregsel & 1) { e->bits &= 0xffffffff; e->bits |= (u64) val << 32; } else { e->bits &= ~0xffffffffULL; e->bits |= (u32) val; - e->fields.remote_irr = 0; } + e->fields.remote_irr = old_remote_irr; + e->fields.delivery_status = old_delivery_status; + + /* + * Some OSes (Linux, Xen) assume that Remote IRR bit will + * be cleared by IOAPIC hardware when the entry is configured + * as edge-triggered. This behavior is used to simulate an + * explicit EOI on IOAPICs that don't have the EOI register. + */ + if (e->fields.trig_mode == IOAPIC_EDGE_TRIG) + e->fields.remote_irr = 0; + mask_after = e->fields.mask; if (mask_before != mask_after) kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 0a324e120942..a16c06604a56 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4640,7 +4640,7 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); /* The caller should hold mmu-lock before calling this function. */ -static bool +static __always_inline bool slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) @@ -4670,7 +4670,7 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, return flush; } -static bool +static __always_inline bool slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, bool lock_flush_tlb) @@ -4681,7 +4681,7 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -4689,7 +4689,7 @@ slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -4697,7 +4697,7 @@ slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 8148d8ca7930..be644afab1bb 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -44,6 +44,7 @@ #include <asm/debugreg.h> #include <asm/kvm_para.h> #include <asm/irq_remapping.h> +#include <asm/nospec-branch.h> #include <asm/virtext.h> #include "trace.h" @@ -182,6 +183,8 @@ struct vcpu_svm { u64 gs_base; } host; + u64 spec_ctrl; + u32 *msrpm; ulong nmi_iret_rip; @@ -247,6 +250,8 @@ static const struct svm_direct_access_msrs { { .index = MSR_CSTAR, .always = true }, { .index = MSR_SYSCALL_MASK, .always = true }, #endif + { .index = MSR_IA32_SPEC_CTRL, .always = false }, + { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -509,6 +514,7 @@ struct svm_cpu_data { struct kvm_ldttss_desc *tss_desc; struct page *save_area; + struct vmcb *current_vmcb; }; static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); @@ -860,6 +866,25 @@ static bool valid_msr_intercept(u32 index) return false; } +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr) +{ + u8 bit_write; + unsigned long tmp; + u32 offset; + u32 *msrpm; + + msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm: + to_svm(vcpu)->msrpm; + + offset = svm_msrpm_offset(msr); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + return !!test_bit(bit_write, &tmp); +} + static void set_msr_interception(u32 *msrpm, unsigned msr, int read, int write) { @@ -1534,6 +1559,8 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; + svm->spec_ctrl = 0; + if (!init_event) { svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; @@ -1643,11 +1670,17 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); + /* + * The vmcb page can be recycled, causing a false negative in + * svm_vcpu_load(). So do a full IBPB now. + */ + indirect_branch_prediction_barrier(); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int i; if (unlikely(cpu != vcpu->cpu)) { @@ -1676,6 +1709,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (static_cpu_has(X86_FEATURE_RDTSCP)) wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + if (sd->current_vmcb != svm->vmcb) { + sd->current_vmcb = svm->vmcb; + indirect_branch_prediction_barrier(); + } avic_vcpu_load(vcpu, cpu); } @@ -3507,6 +3544,13 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_VM_CR: msr_info->data = svm->nested.vm_cr_msr; break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + msr_info->data = svm->spec_ctrl; + break; case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; @@ -3598,6 +3642,49 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr); break; + case MSR_IA32_SPEC_CTRL: + if (!msr->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + svm->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_svm_vmrun_msrpm. + * We update the L1 MSR bit as well since it will end up + * touching the MSR anyway now. + */ + set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); + break; + case MSR_IA32_PRED_CMD: + if (!msr->host_initiated && + !guest_cpuid_has_ibpb(vcpu)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + if (is_guest_mode(vcpu)) + break; + set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); + break; case MSR_STAR: svm->vmcb->save.star = data; break; @@ -4825,6 +4912,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) local_irq_enable(); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + asm volatile ( "push %%" _ASM_BP "; \n\t" "mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t" @@ -4869,6 +4965,25 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) "mov %%r14, %c[r14](%[svm]) \n\t" "mov %%r15, %c[r15](%[svm]) \n\t" #endif + /* + * Clear host registers marked as clobbered to prevent + * speculative use. + */ + "xor %%" _ASM_BX ", %%" _ASM_BX " \n\t" + "xor %%" _ASM_CX ", %%" _ASM_CX " \n\t" + "xor %%" _ASM_DX ", %%" _ASM_DX " \n\t" + "xor %%" _ASM_SI ", %%" _ASM_SI " \n\t" + "xor %%" _ASM_DI ", %%" _ASM_DI " \n\t" +#ifdef CONFIG_X86_64 + "xor %%r8, %%r8 \n\t" + "xor %%r9, %%r9 \n\t" + "xor %%r10, %%r10 \n\t" + "xor %%r11, %%r11 \n\t" + "xor %%r12, %%r12 \n\t" + "xor %%r13, %%r13 \n\t" + "xor %%r14, %%r14 \n\t" + "xor %%r15, %%r15 \n\t" +#endif "pop %%" _ASM_BP : : [svm]"a"(svm), @@ -4898,6 +5013,30 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + #ifdef CONFIG_X86_64 wrmsrl(MSR_GS_BASE, svm->host.gs_base); #else diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 263e56059fd5..c51aaac953b4 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <linux/tboot.h> #include <linux/hrtimer.h> +#include <linux/nospec.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -48,6 +49,7 @@ #include <asm/kexec.h> #include <asm/apic.h> #include <asm/irq_remapping.h> +#include <asm/nospec-branch.h> #include "trace.h" #include "pmu.h" @@ -108,6 +110,14 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define MSR_TYPE_R 1 +#define MSR_TYPE_W 2 +#define MSR_TYPE_RW 3 + +#define MSR_BITMAP_MODE_X2APIC 1 +#define MSR_BITMAP_MODE_X2APIC_APICV 2 +#define MSR_BITMAP_MODE_LM 4 + #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL /* Guest_tsc -> host_tsc conversion requires 64-bit division. */ @@ -132,6 +142,12 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5 +#define VMX_VPID_EXTENT_SUPPORTED_MASK \ + (VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT | \ + VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT | \ + VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT | \ + VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT) + /* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * ple_gap: upper bound on the amount of time between two successive @@ -172,7 +188,6 @@ module_param(ple_window_max, int, S_IRUGO); extern const ulong vmx_return; #define NR_AUTOLOAD_MSRS 8 -#define VMCS02_POOL_SIZE 1 struct vmcs { u32 revision_id; @@ -190,6 +205,7 @@ struct loaded_vmcs { struct vmcs *shadow_vmcs; int cpu; int launched; + unsigned long *msr_bitmap; struct list_head loaded_vmcss_on_cpu_link; }; @@ -206,7 +222,7 @@ struct shared_msr_entry { * stored in guest memory specified by VMPTRLD, but is opaque to the guest, * which must access it using VMREAD/VMWRITE/VMCLEAR instructions. * More than one of these structures may exist, if L1 runs multiple L2 guests. - * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the + * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the * underlying hardware which will be used to run L2. * This structure is packed to ensure that its layout is identical across * machines (necessary for live migration). @@ -385,13 +401,6 @@ struct __packed vmcs12 { */ #define VMCS12_SIZE 0x1000 -/* Used to remember the last vmcs02 used for some recently used vmcs12s */ -struct vmcs02_list { - struct list_head list; - gpa_t vmptr; - struct loaded_vmcs vmcs02; -}; - /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -418,15 +427,15 @@ struct nested_vmx { */ bool sync_shadow_vmcs; - /* vmcs02_list cache of VMCSs recently used to run L2 guests */ - struct list_head vmcs02_pool; - int vmcs02_num; bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + + struct loaded_vmcs vmcs02; + /* - * Guest pages referred to in vmcs02 with host-physical pointers, so - * we must keep them pinned while L2 runs. + * Guest pages referred to in the vmcs02 with host-physical + * pointers, so we must keep them pinned while L2 runs. */ struct page *apic_access_page; struct page *virtual_apic_page; @@ -435,8 +444,6 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; - unsigned long *msr_bitmap; - struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -537,6 +544,7 @@ struct vcpu_vmx { unsigned long host_rsp; u8 fail; bool nmi_known_unmasked; + u8 msr_bitmap_mode; u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -548,6 +556,10 @@ struct vcpu_vmx { u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif + + u64 arch_capabilities; + u64 spec_ctrl; + u32 vm_entry_controls_shadow; u32 vm_exit_controls_shadow; /* @@ -855,13 +867,18 @@ static const unsigned short vmcs_field_to_offset_table[] = { static inline short vmcs_field_to_offset(unsigned long field) { - BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); + const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table); + unsigned short offset; - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) || - vmcs_field_to_offset_table[field] == 0) + BUILD_BUG_ON(size > SHRT_MAX); + if (field >= size) return -ENOENT; - return vmcs_field_to_offset_table[field]; + field = array_index_nospec(field, size); + offset = vmcs_field_to_offset_table[field]; + if (offset == 0) + return -ENOENT; + return offset; } static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) @@ -903,6 +920,9 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static int alloc_identity_pagetable(struct kvm *kvm); +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -922,12 +942,6 @@ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); static unsigned long *vmx_io_bitmap_a; static unsigned long *vmx_io_bitmap_b; -static unsigned long *vmx_msr_bitmap_legacy; -static unsigned long *vmx_msr_bitmap_longmode; -static unsigned long *vmx_msr_bitmap_legacy_x2apic; -static unsigned long *vmx_msr_bitmap_longmode_x2apic; -static unsigned long *vmx_msr_bitmap_legacy_x2apic_apicv_inactive; -static unsigned long *vmx_msr_bitmap_longmode_x2apic_apicv_inactive; static unsigned long *vmx_vmread_bitmap; static unsigned long *vmx_vmwrite_bitmap; @@ -1844,6 +1858,52 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(EXCEPTION_BITMAP, eb); } +/* + * Check if MSR is intercepted for currently loaded MSR bitmap. + */ +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + +/* + * Check if MSR is intercepted for L01 MSR bitmap. + */ +static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -2253,6 +2313,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); + indirect_branch_prediction_barrier(); } if (!already_loaded) { @@ -2521,36 +2582,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) vmx->guest_msrs[from] = tmp; } -static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) -{ - unsigned long *msr_bitmap; - - if (is_guest_mode(vcpu)) - msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; - else if (cpu_has_secondary_exec_ctrls() && - (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic; - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv_inactive; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv_inactive; - } - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode; - else - msr_bitmap = vmx_msr_bitmap_legacy; - } - - vmcs_write64(MSR_BITMAP, __pa(msr_bitmap)); -} - /* * Set up the vmcs to automatically save and restore system * msrs. Don't touch the 64-bit msrs if the guest is in legacy @@ -2591,7 +2622,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx->save_nmsrs = save_nmsrs; if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(&vmx->vcpu); + vmx_update_msr_bitmap(&vmx->vcpu); } /* @@ -2814,8 +2845,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) */ if (enable_vpid) vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | - VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT | - VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; + VMX_VPID_EXTENT_SUPPORTED_MASK; else vmx->nested.nested_vmx_vpid_caps = 0; @@ -2980,6 +3010,19 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: msr_info->data = guest_read_tsc(vcpu); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + msr_info->data = to_vmx(vcpu)->spec_ctrl; + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has_arch_capabilities(vcpu)) + return 1; + msr_info->data = to_vmx(vcpu)->arch_capabilities; + break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -3084,6 +3127,68 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + vmx->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. We update the vmcs01 here for L1 as well + * since it will end up touching the MSR anyway now. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_RW); + break; + case MSR_IA32_PRED_CMD: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibpb(vcpu)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, + MSR_TYPE_W); + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vmx->arch_capabilities = data; + break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -3523,11 +3628,6 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) return vmcs; } -static struct vmcs *alloc_vmcs(void) -{ - return alloc_vmcs_cpu(raw_smp_processor_id()); -} - static void free_vmcs(struct vmcs *vmcs) { free_pages((unsigned long)vmcs, vmcs_config.order); @@ -3543,9 +3643,38 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) loaded_vmcs_clear(loaded_vmcs); free_vmcs(loaded_vmcs->vmcs); loaded_vmcs->vmcs = NULL; + if (loaded_vmcs->msr_bitmap) + free_page((unsigned long)loaded_vmcs->msr_bitmap); WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } +static struct vmcs *alloc_vmcs(void) +{ + return alloc_vmcs_cpu(raw_smp_processor_id()); +} + +static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) +{ + loaded_vmcs->vmcs = alloc_vmcs(); + if (!loaded_vmcs->vmcs) + return -ENOMEM; + + loaded_vmcs->shadow_vmcs = NULL; + loaded_vmcs_init(loaded_vmcs); + + if (cpu_has_vmx_msr_bitmap()) { + loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!loaded_vmcs->msr_bitmap) + goto out_vmcs; + memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); + } + return 0; + +out_vmcs: + free_loaded_vmcs(loaded_vmcs); + return -ENOMEM; +} + static void free_kvm_area(void) { int cpu; @@ -4552,10 +4681,8 @@ static void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -4589,8 +4716,8 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, } } -static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) +static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -4624,6 +4751,15 @@ static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, } } +static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type, bool value) +{ + if (value) + vmx_enable_intercept_for_msr(msr_bitmap, msr, type); + else + vmx_disable_intercept_for_msr(msr_bitmap, msr, type); +} + /* * If a msr is allowed by L0, we should check whether it is allowed by L1. * The corresponding bit will be cleared unless both of L0 and L1 allow it. @@ -4670,58 +4806,68 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only) +static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) { - if (!longmode_only) - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, - msr, MSR_TYPE_R | MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, - msr, MSR_TYPE_R | MSR_TYPE_W); -} + u8 mode = 0; -static void vmx_enable_intercept_msr_read_x2apic(u32 msr, bool apicv_active) -{ - if (apicv_active) { - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_R); - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_R); - } else { - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - msr, MSR_TYPE_R); - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - msr, MSR_TYPE_R); + if (cpu_has_secondary_exec_ctrls() && + (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { + mode |= MSR_BITMAP_MODE_X2APIC; + if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) + mode |= MSR_BITMAP_MODE_X2APIC_APICV; } + + if (is_long_mode(vcpu)) + mode |= MSR_BITMAP_MODE_LM; + + return mode; } -static void vmx_disable_intercept_msr_read_x2apic(u32 msr, bool apicv_active) +#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) + +static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, + u8 mode) { - if (apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_R); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_R); - } else { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - msr, MSR_TYPE_R); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - msr, MSR_TYPE_R); + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } + + if (mode & MSR_BITMAP_MODE_X2APIC) { + /* + * TPR reads and writes can be virtualized even if virtual interrupt + * delivery is not in use. + */ + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW); + if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { + vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); + } } } -static void vmx_disable_intercept_msr_write_x2apic(u32 msr, bool apicv_active) +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) { - if (apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_W); - } else { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - msr, MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - msr, MSR_TYPE_W); - } + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + u8 mode = vmx_msr_bitmap_mode(vcpu); + u8 changed = mode ^ vmx->msr_bitmap_mode; + + if (!changed) + return; + + vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW, + !(mode & MSR_BITMAP_MODE_LM)); + + if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) + vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); + + vmx->msr_bitmap_mode = mode; } static bool vmx_get_enable_apicv(void) @@ -4729,30 +4875,45 @@ static bool vmx_get_enable_apicv(void) return enable_apicv; } -static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) +static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + gfn_t gfn; + + /* + * Don't need to mark the APIC access page dirty; it is never + * written to by the CPU during APIC virtualization. + */ + + if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { + gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } + + if (nested_cpu_has_posted_intr(vmcs12)) { + gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } +} + + +static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; void *vapic_page; u16 status; - if (vmx->nested.pi_desc && - vmx->nested.pi_pending) { - vmx->nested.pi_pending = false; - if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return 0; - - max_irr = find_last_bit( - (unsigned long *)vmx->nested.pi_desc->pir, 256); + if (!vmx->nested.pi_desc || !vmx->nested.pi_pending) + return; - if (max_irr == 256) - return 0; + vmx->nested.pi_pending = false; + if (!pi_test_and_clear_on(vmx->nested.pi_desc)) + return; + max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); + if (max_irr != 256) { vapic_page = kmap(vmx->nested.virtual_apic_page); - if (!vapic_page) { - WARN_ON(1); - return -ENOMEM; - } __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -4763,7 +4924,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_INTR_STATUS, status); } } - return 0; + + nested_mark_vmcs12_pages_dirty(vcpu); } static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) @@ -4810,14 +4972,15 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { - /* the PIR and ON have been set by L1. */ - kvm_vcpu_trigger_posted_interrupt(vcpu); /* * If a posted intr is not recognized by hardware, * we will accomplish it in the next vmentry. */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); + /* the PIR and ON have been set by L1. */ + if (!kvm_vcpu_trigger_posted_interrupt(vcpu)) + kvm_vcpu_kick(vcpu); return 0; } return -1; @@ -4950,7 +5113,7 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) } if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static u32 vmx_exec_control(struct vcpu_vmx *vmx) @@ -5039,7 +5202,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); } if (cpu_has_vmx_msr_bitmap()) - vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy)); + vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ @@ -5113,6 +5276,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities); vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl); @@ -5141,6 +5306,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u64 cr0; vmx->rmode.vm86_active = 0; + vmx->spec_ctrl = 0; vmx->soft_vnmi_blocked = 0; @@ -5185,7 +5351,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write64(GUEST_IA32_DEBUGCTL, 0); } - vmcs_writel(GUEST_RFLAGS, 0x02); + kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0xfff0); vmcs_writel(GUEST_GDTR_BASE, 0); @@ -6248,7 +6414,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (test_bit(KVM_REQ_EVENT, &vcpu->requests)) return 1; - err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE); + err = emulate_instruction(vcpu, 0); if (err == EMULATE_USER_EXIT) { ++vcpu->stat.mmio_exits; @@ -6370,7 +6536,7 @@ static void wakeup_handler(void) static __init int hardware_setup(void) { - int r = -ENOMEM, i, msr; + int r = -ENOMEM, i; rdmsrl_safe(MSR_EFER, &host_efer); @@ -6385,41 +6551,13 @@ static __init int hardware_setup(void) if (!vmx_io_bitmap_b) goto out; - vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy) - goto out1; - - vmx_msr_bitmap_legacy_x2apic = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy_x2apic) - goto out2; - - vmx_msr_bitmap_legacy_x2apic_apicv_inactive = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy_x2apic_apicv_inactive) - goto out3; - - vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode) - goto out4; - - vmx_msr_bitmap_longmode_x2apic = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode_x2apic) - goto out5; - - vmx_msr_bitmap_longmode_x2apic_apicv_inactive = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode_x2apic_apicv_inactive) - goto out6; - vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmread_bitmap) - goto out7; + goto out1; vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmwrite_bitmap) - goto out8; + goto out2; memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); @@ -6428,12 +6566,9 @@ static __init int hardware_setup(void) memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; - goto out9; + goto out3; } if (boot_cpu_has(X86_FEATURE_NX)) @@ -6490,47 +6625,8 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); - vmx_disable_intercept_for_msr(MSR_GS_BASE, false); - vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - - memcpy(vmx_msr_bitmap_legacy_x2apic, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic, - vmx_msr_bitmap_longmode, PAGE_SIZE); - memcpy(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - vmx_msr_bitmap_longmode, PAGE_SIZE); - set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - /* - * enable_apicv && kvm_vcpu_apicv_active() - */ - for (msr = 0x800; msr <= 0x8ff; msr++) - vmx_disable_intercept_msr_read_x2apic(msr, true); - - /* TMCCT */ - vmx_enable_intercept_msr_read_x2apic(0x839, true); - /* TPR */ - vmx_disable_intercept_msr_write_x2apic(0x808, true); - /* EOI */ - vmx_disable_intercept_msr_write_x2apic(0x80b, true); - /* SELF-IPI */ - vmx_disable_intercept_msr_write_x2apic(0x83f, true); - - /* - * (enable_apicv && !kvm_vcpu_apicv_active()) || - * !enable_apicv - */ - /* TPR */ - vmx_disable_intercept_msr_read_x2apic(0x808, false); - vmx_disable_intercept_msr_write_x2apic(0x808, false); - if (enable_ept) { kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, @@ -6576,22 +6672,10 @@ static __init int hardware_setup(void) return alloc_kvm_area(); -out9: - free_page((unsigned long)vmx_vmwrite_bitmap); -out8: - free_page((unsigned long)vmx_vmread_bitmap); -out7: - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive); -out6: - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); -out5: - free_page((unsigned long)vmx_msr_bitmap_longmode); -out4: - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive); out3: - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); + free_page((unsigned long)vmx_vmwrite_bitmap); out2: - free_page((unsigned long)vmx_msr_bitmap_legacy); + free_page((unsigned long)vmx_vmread_bitmap); out1: free_page((unsigned long)vmx_io_bitmap_b); out: @@ -6602,12 +6686,6 @@ out: static __exit void hardware_unsetup(void) { - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive); - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive); - free_page((unsigned long)vmx_msr_bitmap_legacy); - free_page((unsigned long)vmx_msr_bitmap_longmode); free_page((unsigned long)vmx_io_bitmap_b); free_page((unsigned long)vmx_io_bitmap_a); free_page((unsigned long)vmx_vmwrite_bitmap); @@ -6655,94 +6733,6 @@ static int handle_monitor(struct kvm_vcpu *vcpu) } /* - * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12. - * We could reuse a single VMCS for all the L2 guests, but we also want the - * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this - * allows keeping them loaded on the processor, and in the future will allow - * optimizations where prepare_vmcs02 doesn't need to set all the fields on - * every entry if they never change. - * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE - * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first. - * - * The following functions allocate and free a vmcs02 in this pool. - */ - -/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */ -static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmx->nested.current_vmptr) { - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) { - /* Recycle the least recently used VMCS. */ - item = list_last_entry(&vmx->nested.vmcs02_pool, - struct vmcs02_list, list); - item->vmptr = vmx->nested.current_vmptr; - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - /* Create a new VMCS */ - item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL); - if (!item) - return NULL; - item->vmcs02.vmcs = alloc_vmcs(); - item->vmcs02.shadow_vmcs = NULL; - if (!item->vmcs02.vmcs) { - kfree(item); - return NULL; - } - loaded_vmcs_init(&item->vmcs02); - item->vmptr = vmx->nested.current_vmptr; - list_add(&(item->list), &(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num++; - return &item->vmcs02; -} - -/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */ -static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmptr) { - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - return; - } -} - -/* - * Free all VMCSs saved for this vcpu, except the one pointed by - * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs - * must be &vmx->vmcs01. - */ -static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item, *n; - - WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01); - list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) { - /* - * Something will leak if the above WARN triggers. Better than - * a use-after-free. - */ - if (vmx->loaded_vmcs == &item->vmcs02) - continue; - - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - } -} - -/* * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(), * set the success or error code of an emulated VMX instruction, as specified * by Vol 2B, VMX Instruction Reference, "Conventions". @@ -7016,6 +7006,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu) struct vmcs *shadow_vmcs; const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + int r; /* The Intel VMX Instruction Reference lists a bunch of bits that * are prerequisite to running VMXON, most notably cr4.VMXE must be @@ -7055,12 +7046,9 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (cpu_has_vmx_msr_bitmap()) { - vmx->nested.msr_bitmap = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx->nested.msr_bitmap) - goto out_msr_bitmap; - } + r = alloc_loaded_vmcs(&vmx->nested.vmcs02); + if (r < 0) + goto out_vmcs02; vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) @@ -7077,9 +7065,6 @@ static int handle_vmon(struct kvm_vcpu *vcpu) vmx->vmcs01.shadow_vmcs = shadow_vmcs; } - INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num = 0; - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; @@ -7094,9 +7079,9 @@ out_shadow_vmcs: kfree(vmx->nested.cached_vmcs12); out_cached_vmcs12: - free_page((unsigned long)vmx->nested.msr_bitmap); + free_loaded_vmcs(&vmx->nested.vmcs02); -out_msr_bitmap: +out_vmcs02: return -ENOMEM; } @@ -7172,17 +7157,13 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.vmxon = false; free_vpid(vmx->nested.vpid02); nested_release_vmcs12(vmx); - if (vmx->nested.msr_bitmap) { - free_page((unsigned long)vmx->nested.msr_bitmap); - vmx->nested.msr_bitmap = NULL; - } if (enable_shadow_vmcs) { vmcs_clear(vmx->vmcs01.shadow_vmcs); free_vmcs(vmx->vmcs01.shadow_vmcs); vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); - /* Unpin physical memory we referred to in current vmcs02 */ + /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { nested_release_page(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; @@ -7198,7 +7179,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.pi_desc = NULL; } - nested_free_all_saved_vmcss(vmx); + free_loaded_vmcs(&vmx->nested.vmcs02); } /* Emulate the VMXOFF instruction */ @@ -7232,8 +7213,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - nested_free_vmcs02(vmx, vmptr); - skip_emulated_instruction(vcpu); nested_vmx_succeed(vcpu); return 1; @@ -7711,7 +7690,8 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf); - types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7; + types = (vmx->nested.nested_vmx_vpid_caps & + VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8; if (type >= 32 || !(types & (1 << type))) { nested_vmx_failValid(vcpu, @@ -7733,21 +7713,27 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) } switch (type) { + case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: case VMX_VPID_EXTENT_SINGLE_CONTEXT: - /* - * Old versions of KVM use the single-context version so we - * have to support it; just treat it the same as all-context. - */ + case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL: + if (!vpid) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); + return 1; + } + break; case VMX_VPID_EXTENT_ALL_CONTEXT: - __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); - nested_vmx_succeed(vcpu); break; default: - /* Trap individual address invalidation invvpid calls */ - BUG_ON(1); - break; + WARN_ON_ONCE(1); + skip_emulated_instruction(vcpu); + return 1; } + __vmx_flush_tlb(vcpu, vmx->nested.vpid02); + nested_vmx_succeed(vcpu); + skip_emulated_instruction(vcpu); return 1; } @@ -8020,6 +8006,19 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) vmcs_read32(VM_EXIT_INTR_ERROR_CODE), KVM_ISA_VMX); + /* + * The host physical addresses of some pages of guest memory + * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC + * Page). The CPU may write to these pages via their host + * physical address while L2 is running, bypassing any + * address-translation-based dirty tracking (e.g. EPT write + * protection). + * + * Mark them dirty on every exit from L2 to prevent them from + * getting out of sync with dirty tracking. + */ + nested_mark_vmcs12_pages_dirty(vcpu); + if (vmx->nested.nested_run_pending) return false; @@ -8511,7 +8510,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) @@ -8667,14 +8666,14 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) #endif "pushf\n\t" __ASM_SIZE(push) " $%c[cs]\n\t" - "call *%[entry]\n\t" + CALL_NOSPEC : #ifdef CONFIG_X86_64 [sp]"=&r"(tmp), #endif "+r"(__sp) : - [entry]"r"(entry), + THUNK_TARGET(entry), [ss]"i"(__KERNEL_DS), [cs]"i"(__KERNEL_CS) ); @@ -8900,6 +8899,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_arm_hv_timer(vcpu); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -8948,6 +8956,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) /* Save guest registers, load host registers, keep flags */ "mov %0, %c[wordsize](%%" _ASM_SP ") \n\t" "pop %0 \n\t" + "setbe %c[fail](%0)\n\t" "mov %%" _ASM_AX ", %c[rax](%0) \n\t" "mov %%" _ASM_BX ", %c[rbx](%0) \n\t" __ASM_SIZE(pop) " %c[rcx](%0) \n\t" @@ -8964,12 +8973,23 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) "mov %%r13, %c[r13](%0) \n\t" "mov %%r14, %c[r14](%0) \n\t" "mov %%r15, %c[r15](%0) \n\t" + "xor %%r8d, %%r8d \n\t" + "xor %%r9d, %%r9d \n\t" + "xor %%r10d, %%r10d \n\t" + "xor %%r11d, %%r11d \n\t" + "xor %%r12d, %%r12d \n\t" + "xor %%r13d, %%r13d \n\t" + "xor %%r14d, %%r14d \n\t" + "xor %%r15d, %%r15d \n\t" #endif "mov %%cr2, %%" _ASM_AX " \n\t" "mov %%" _ASM_AX ", %c[cr2](%0) \n\t" + "xor %%eax, %%eax \n\t" + "xor %%ebx, %%ebx \n\t" + "xor %%esi, %%esi \n\t" + "xor %%edi, %%edi \n\t" "pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t" - "setbe %c[fail](%0) \n\t" ".pushsection .rodata \n\t" ".global vmx_return \n\t" "vmx_return: " _ASM_PTR " 2b \n\t" @@ -9006,6 +9026,30 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (debugctlmsr) update_debugctlmsr(debugctlmsr); @@ -9116,6 +9160,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + unsigned long *msr_bitmap; int cpu; if (!vmx) @@ -9148,17 +9193,24 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx->guest_msrs) goto free_pml; - vmx->loaded_vmcs = &vmx->vmcs01; - vmx->loaded_vmcs->vmcs = alloc_vmcs(); - vmx->loaded_vmcs->shadow_vmcs = NULL; - if (!vmx->loaded_vmcs->vmcs) - goto free_msrs; if (!vmm_exclusive) kvm_cpu_vmxon(__pa(per_cpu(vmxarea, raw_smp_processor_id()))); - loaded_vmcs_init(vmx->loaded_vmcs); + err = alloc_loaded_vmcs(&vmx->vmcs01); if (!vmm_exclusive) kvm_cpu_vmxoff(); + if (err < 0) + goto free_msrs; + + msr_bitmap = vmx->vmcs01.msr_bitmap; + vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); + vmx->msr_bitmap_mode = 0; + vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); vmx->vcpu.cpu = cpu; @@ -9552,21 +9604,31 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, int msr; struct page *page; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; + /* + * pred_cmd & spec_ctrl are trying to verify two things: + * + * 1. L0 gave a permission to L1 to actually passthrough the MSR. This + * ensures that we do not accidentally generate an L02 MSR bitmap + * from the L12 MSR bitmap that is too permissive. + * 2. That L1 or L2s have actually used the MSR. This avoids + * unnecessarily merging of the bitmap if the MSR is unused. This + * works properly because we only update the L01 MSR bitmap lazily. + * So even if L0 should pass L1 these MSRs, the L01 bitmap is only + * updated to reflect this when L1 (or its L2s) actually write to + * the MSR. + */ + bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); - /* This shortcut is ok because we support only x2APIC MSRs so far. */ - if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) + if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && + !pred_cmd && !spec_ctrl) return false; page = nested_get_page(vcpu, vmcs12->msr_bitmap); if (!page) return false; msr_bitmap_l1 = (unsigned long *)kmap(page); - if (!msr_bitmap_l1) { - nested_release_page_clean(page); - WARN_ON(1); - return false; - } memset(msr_bitmap_l0, 0xff, PAGE_SIZE); @@ -9593,6 +9655,19 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, MSR_TYPE_W); } } + + if (spec_ctrl) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_R | MSR_TYPE_W); + + if (pred_cmd) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, + MSR_TYPE_W); + kunmap(page); nested_release_page_clean(page); @@ -10072,6 +10147,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); + if (cpu_has_vmx_msr_bitmap()) + vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); + if (enable_vpid) { /* * There is no direct mapping between vpid02 and vpid12, the @@ -10167,7 +10245,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); int cpu; - struct loaded_vmcs *vmcs02; bool ia32e; u32 msr_entry_idx; @@ -10307,17 +10384,13 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * the nested entry. */ - vmcs02 = nested_get_current_vmcs02(vmx); - if (!vmcs02) - return -ENOMEM; - enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); cpu = get_cpu(); - vmx->loaded_vmcs = vmcs02; + vmx->loaded_vmcs = &vmx->nested.vmcs02; vmx_vcpu_put(vcpu); vmx_vcpu_load(vcpu, cpu); vcpu->cpu = cpu; @@ -10469,7 +10542,8 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - return vmx_complete_nested_posted_interrupt(vcpu); + vmx_complete_nested_posted_interrupt(vcpu); + return 0; } static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) @@ -10780,7 +10854,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs_write64(GUEST_IA32_DEBUGCTL, 0); if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) @@ -10831,10 +10905,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vm_exit_controls_reset_shadow(vmx); vmx_segment_cache_clear(vmx); - /* if no vmcs02 cache requested, remove the one we used */ - if (VMCS02_POOL_SIZE == 0) - nested_free_vmcs02(vmx, vmx->nested.current_vmptr); - load_vmcs12_host_state(vcpu, vmcs12); /* Update any VMCS fields that might have changed while L2 ran */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 73304b1a03cc..4b19ec1da22d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -975,6 +975,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES }; static unsigned num_msrs_to_save; @@ -1751,10 +1752,13 @@ static u64 __get_kvmclock_ns(struct kvm *kvm) /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); - kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, - &hv_clock.tsc_shift, - &hv_clock.tsc_to_system_mul); - ret = __pvclock_read_cycles(&hv_clock, rdtsc()); + if (__this_cpu_read(cpu_tsc_khz)) { + kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, + &hv_clock.tsc_shift, + &hv_clock.tsc_to_system_mul); + ret = __pvclock_read_cycles(&hv_clock, rdtsc()); + } else + ret = ktime_get_boot_ns() + ka->kvmclock_offset; put_cpu(); @@ -2843,6 +2847,12 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); vcpu->arch.last_host_tsc = rdtsc(); + /* + * If userspace has set any breakpoints or watchpoints, dr6 is restored + * on every vmexit, but if not, we might have a stale dr6 from the + * guest. do_debug expects dr6 to be cleared after it runs, do the same. + */ + set_debugreg(0, 6); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, @@ -4264,7 +4274,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) addr, n, v)) && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v)) break; - trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v); + trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, v); handled += n; addr += n; len -= n; @@ -4517,7 +4527,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) { if (vcpu->mmio_read_completed) { trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, - vcpu->mmio_fragments[0].gpa, *(u64 *)val); + vcpu->mmio_fragments[0].gpa, val); vcpu->mmio_read_completed = 0; return 1; } @@ -4539,14 +4549,14 @@ static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val) { - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, val); return vcpu_mmio_write(vcpu, gpa, bytes, val); } static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { - trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, NULL); return X86EMUL_IO_NEEDED; } @@ -5308,7 +5318,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu) vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; - r = EMULATE_FAIL; + r = EMULATE_USER_EXIT; } kvm_queue_exception(vcpu, UD_VECTOR); @@ -8417,6 +8427,13 @@ static int apf_put_user(struct kvm_vcpu *vcpu, u32 val) sizeof(val)); } +static int apf_get_user(struct kvm_vcpu *vcpu, u32 *val) +{ + + return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, val, + sizeof(u32)); +} + void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { @@ -8443,6 +8460,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { struct x86_exception fault; + u32 val; if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ @@ -8450,14 +8468,24 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, kvm_del_async_pf_gfn(vcpu, work->arch.gfn); trace_kvm_async_pf_ready(work->arch.token, work->gva); - if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) && - !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { - fault.vector = PF_VECTOR; - fault.error_code_valid = true; - fault.error_code = 0; - fault.nested_page_fault = false; - fault.address = work->arch.token; - kvm_inject_page_fault(vcpu, &fault); + if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED && + !apf_get_user(vcpu, &val)) { + if (val == KVM_PV_REASON_PAGE_NOT_PRESENT && + vcpu->arch.exception.pending && + vcpu->arch.exception.nr == PF_VECTOR && + !apf_put_user(vcpu, 0)) { + vcpu->arch.exception.pending = false; + vcpu->arch.exception.nr = 0; + vcpu->arch.exception.has_error_code = false; + vcpu->arch.exception.error_code = 0; + } else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { + fault.vector = PF_VECTOR; + fault.error_code_valid = true; + fault.error_code = 0; + fault.nested_page_fault = false; + fault.address = work->arch.token; + kvm_inject_page_fault(vcpu, &fault); + } } vcpu->arch.apf.halted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 34a74131a12c..4ad7c4dd311c 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -25,6 +25,8 @@ lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o +lib-$(CONFIG_RETPOLINE) += retpoline.o +OBJECT_FILES_NON_STANDARD_retpoline.o :=y obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 4d34bb548b41..46e71a74e612 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -29,7 +29,8 @@ #include <asm/errno.h> #include <asm/asm.h> #include <asm/export.h> - +#include <asm/nospec-branch.h> + /* * computes a partial checksum, e.g. for TCP/UDP fragments */ @@ -156,7 +157,7 @@ ENTRY(csum_partial) negl %ebx lea 45f(%ebx,%ebx,2), %ebx testl %esi, %esi - jmp *%ebx + JMP_NOSPEC %ebx # Handle 2-byte-aligned regions 20: addw (%esi), %ax @@ -439,7 +440,7 @@ ENTRY(csum_partial_copy_generic) andl $-32,%edx lea 3f(%ebx,%ebx), %ebx testl %esi, %esi - jmp *%ebx + JMP_NOSPEC %ebx 1: addl $64,%esi addl $64,%edi SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl) diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c index d6f848d1211d..2dd1fe13a37b 100644 --- a/arch/x86/lib/cpu.c +++ b/arch/x86/lib/cpu.c @@ -18,7 +18,7 @@ unsigned int x86_model(unsigned int sig) { unsigned int fam, model; - fam = x86_family(sig); + fam = x86_family(sig); model = (sig >> 4) & 0xf; diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 073d1f1a620b..9758524ee99f 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -93,6 +93,13 @@ static void delay_mwaitx(unsigned long __loops) { u64 start, end, delay, loops = __loops; + /* + * Timer value of 0 causes MWAITX to wait indefinitely, unless there + * is a store on the memory monitored by MONITORX. + */ + if (loops == 0) + return; + start = rdtsc_ordered(); for (;;) { diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 37b62d412148..b12b214713a6 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -39,6 +39,8 @@ ENTRY(__get_user_1) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 1: movzbl (%_ASM_AX),%edx xor %eax,%eax @@ -53,6 +55,8 @@ ENTRY(__get_user_2) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 2: movzwl -1(%_ASM_AX),%edx xor %eax,%eax @@ -67,6 +71,8 @@ ENTRY(__get_user_4) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 3: movl -3(%_ASM_AX),%edx xor %eax,%eax @@ -82,6 +88,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movq -7(%_ASM_AX),%rdx xor %eax,%eax @@ -93,6 +101,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user_8 + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movl -7(%_ASM_AX),%edx 5: movl -3(%_ASM_AX),%ecx diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S new file mode 100644 index 000000000000..480edc3a5e03 --- /dev/null +++ b/arch/x86/lib/retpoline.S @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/stringify.h> +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/cpufeatures.h> +#include <asm/alternative-asm.h> +#include <asm/export.h> +#include <asm/nospec-branch.h> +#include <asm/bitsperlong.h> + +.macro THUNK reg + .section .text.__x86.indirect_thunk + +ENTRY(__x86_indirect_thunk_\reg) + CFI_STARTPROC + JMP_NOSPEC %\reg + CFI_ENDPROC +ENDPROC(__x86_indirect_thunk_\reg) +.endm + +/* + * Despite being an assembler file we can't just use .irp here + * because __KSYM_DEPS__ only uses the C preprocessor and would + * only see one instance of "__x86_indirect_thunk_\reg" rather + * than one per register with the correct names. So we do it + * the simple and nasty way... + */ +#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym) +#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg) +#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg) + +GENERATE_THUNK(_ASM_AX) +GENERATE_THUNK(_ASM_BX) +GENERATE_THUNK(_ASM_CX) +GENERATE_THUNK(_ASM_DX) +GENERATE_THUNK(_ASM_SI) +GENERATE_THUNK(_ASM_DI) +GENERATE_THUNK(_ASM_BP) +#ifdef CONFIG_64BIT +GENERATE_THUNK(r8) +GENERATE_THUNK(r9) +GENERATE_THUNK(r10) +GENERATE_THUNK(r11) +GENERATE_THUNK(r12) +GENERATE_THUNK(r13) +GENERATE_THUNK(r14) +GENERATE_THUNK(r15) +#endif + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * Google experimented with loop-unrolling and this turned out to be + * the optimal version - two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +.macro STUFF_RSB nr:req sp:req + mov $(\nr / 2), %_ASM_BX + .align 16 +771: + call 772f +773: /* speculation trap */ + pause + lfence + jmp 773b + .align 16 +772: + call 774f +775: /* speculation trap */ + pause + lfence + jmp 775b + .align 16 +774: + dec %_ASM_BX + jnz 771b + add $((BITS_PER_LONG/8) * \nr), \sp +.endm + +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +ENTRY(__fill_rsb) + STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP + ret +END(__fill_rsb) +EXPORT_SYMBOL_GPL(__fill_rsb) + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ + +ENTRY(__clear_rsb) + STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP + ret +END(__clear_rsb) +EXPORT_SYMBOL_GPL(__clear_rsb) diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 3bc7baf2a711..5c06dbffc52f 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -570,12 +570,12 @@ do { \ unsigned long __copy_to_user_ll(void __user *to, const void *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel(to, from, n); - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_to_user_ll); @@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache); unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_intel_nocache(to, from, n); @@ -636,7 +636,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr #else __copy_user(to, from, n); #endif - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); diff --git a/arch/x86/math-emu/Makefile b/arch/x86/math-emu/Makefile index 9b0c63b60302..1b2dac174321 100644 --- a/arch/x86/math-emu/Makefile +++ b/arch/x86/math-emu/Makefile @@ -5,8 +5,8 @@ #DEBUG = -DDEBUGGING DEBUG = PARANOID = -DPARANOID -EXTRA_CFLAGS := $(PARANOID) $(DEBUG) -fno-builtin $(MATH_EMULATION) -EXTRA_AFLAGS := $(PARANOID) +ccflags-y += $(PARANOID) $(DEBUG) -fno-builtin $(MATH_EMULATION) +asflags-y += $(PARANOID) # From 'C' language sources: C_OBJS =fpu_entry.o errors.o \ diff --git a/arch/x86/math-emu/reg_compare.c b/arch/x86/math-emu/reg_compare.c index b77360fdbf4a..19b33b50adfa 100644 --- a/arch/x86/math-emu/reg_compare.c +++ b/arch/x86/math-emu/reg_compare.c @@ -168,7 +168,7 @@ static int compare(FPU_REG const *b, int tagb) /* This function requires that st(0) is not empty */ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag) { - int f = 0, c; + int f, c; c = compare(loaded_data, loaded_tag); @@ -189,12 +189,12 @@ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag) case COMP_No_Comp: f = SW_C3 | SW_C2 | SW_C0; break; -#ifdef PARANOID default: +#ifdef PARANOID EXCEPTION(EX_INTERNAL | 0x121); +#endif /* PARANOID */ f = SW_C3 | SW_C2 | SW_C0; break; -#endif /* PARANOID */ } setcc(f); if (c & COMP_Denormal) { @@ -205,7 +205,7 @@ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag) static int compare_st_st(int nr) { - int f = 0, c; + int f, c; FPU_REG *st_ptr; if (!NOT_EMPTY(0) || !NOT_EMPTY(nr)) { @@ -235,12 +235,12 @@ static int compare_st_st(int nr) case COMP_No_Comp: f = SW_C3 | SW_C2 | SW_C0; break; -#ifdef PARANOID default: +#ifdef PARANOID EXCEPTION(EX_INTERNAL | 0x122); +#endif /* PARANOID */ f = SW_C3 | SW_C2 | SW_C0; break; -#endif /* PARANOID */ } setcc(f); if (c & COMP_Denormal) { @@ -283,12 +283,12 @@ static int compare_i_st_st(int nr) case COMP_No_Comp: f = X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF; break; -#ifdef PARANOID default: +#ifdef PARANOID EXCEPTION(EX_INTERNAL | 0x122); +#endif /* PARANOID */ f = 0; break; -#endif /* PARANOID */ } FPU_EFLAGS = (FPU_EFLAGS & ~(X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF)) | f; if (c & COMP_Denormal) { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8b5ff88aa4f8..74dea7f14c20 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -191,14 +191,15 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ -static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) +static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info, + u32 *pkey) { /* This is effectively an #ifdef */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return; /* Fault not from Protection Keys: nothing to do */ - if (si_code != SEGV_PKUERR) + if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV)) return; /* * force_sig_info_fault() is called from a number of @@ -237,7 +238,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, lsb = PAGE_SHIFT; info.si_addr_lsb = lsb; - fill_sig_info_pkey(si_code, &info, pkey); + fill_sig_info_pkey(si_signo, si_code, &info, pkey); force_sig_info(si_signo, &info, tsk); } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 7aaa2635862d..ecae9ac216fa 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -347,11 +347,11 @@ void iounmap(volatile void __iomem *addr) (void __force *)addr < phys_to_virt(ISA_END_ADDRESS)) 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/kaiser.c b/arch/x86/mm/kaiser.c index 8f8e5e03d083..ec678aafa3f8 100644 --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -197,6 +197,8 @@ static int kaiser_add_user_map(const void *__start_addr, unsigned long size, * requires that not to be #defined to 0): so mask it off here. */ flags &= ~_PAGE_GLOBAL; + if (!(__supported_pte_mask & _PAGE_NX)) + flags &= ~_PAGE_NX; for (; address < end_addr; address += PAGE_SIZE) { target_address = get_pa_from_mapping(address); @@ -342,7 +344,7 @@ void __init kaiser_init(void) if (vsyscall_enabled()) kaiser_add_user_map_early((void *)VSYSCALL_ADDR, PAGE_SIZE, - __PAGE_KERNEL_VSYSCALL); + vsyscall_pgprot); for_each_possible_cpu(cpu) { void *percpu_vaddr = __per_cpu_user_mapped_start + diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index afc47f5c9531..cadb82be5f36 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -434,17 +434,18 @@ 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; @@ -453,7 +454,7 @@ 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); } @@ -527,19 +528,20 @@ 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/mm/pgtable.c b/arch/x86/mm/pgtable.c index 5aaec8effc5f..209b9465e97a 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -345,13 +345,6 @@ static inline void _pgd_free(pgd_t *pgd) } #else -/* - * Instead of one pgd, Kaiser acquires two pgds. Being order-1, it is - * both 8k in size and 8k-aligned. That lets us just flip bit 12 - * in a pointer to swap between the two 4k halves. - */ -#define PGD_ALLOCATION_ORDER kaiser_enabled - static inline pgd_t *_pgd_alloc(void) { return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 41205de487e7..578973ade71b 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -110,7 +110,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mapped in the new pgd, we'll double-fault. Forcibly * map it. */ - unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); + unsigned int stack_pgd_index = pgd_index(current_stack_pointer); pgd_t *pgd = next->pgd + stack_pgd_index; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 15f743615923..7840331d3056 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -278,10 +278,10 @@ static void emit_bpf_tail_call(u8 **pprog) /* if (index >= array->map.max_entries) * goto out; */ - EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ + EMIT2(0x89, 0xD2); /* mov edx, edx */ + EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); - EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ -#define OFFSET1 47 /* number of bytes to jump */ +#define OFFSET1 43 /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; @@ -290,21 +290,20 @@ static void emit_bpf_tail_call(u8 **pprog) */ EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 36 +#define OFFSET2 32 EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ /* prog = array->ptrs[index]; */ - EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ + EMIT4_off32(0x48, 0x8B, 0x84, 0xD6, /* mov rax, [rsi + rdx * 8 + offsetof(...)] */ offsetof(struct bpf_array, ptrs)); - EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */ /* if (prog == NULL) * goto out; */ - EMIT4(0x48, 0x83, 0xF8, 0x00); /* cmp rax, 0 */ + EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ #define OFFSET3 10 EMIT2(X86_JE, OFFSET3); /* je out */ label3 = cnt; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 2f25a363068c..dcb2d9d185a2 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -142,7 +142,7 @@ int __init efi_alloc_page_tables(void) return 0; gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO; - efi_pgd = (pgd_t *)__get_free_page(gfp_mask); + efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER); if (!efi_pgd) return -ENOMEM; diff --git a/arch/xtensa/include/asm/futex.h b/arch/xtensa/include/asm/futex.h index b39531babec0..72bfc1cbc2b5 100644 --- a/arch/xtensa/include/asm/futex.h +++ b/arch/xtensa/include/asm/futex.h @@ -109,7 +109,6 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { int ret = 0; - u32 prev; if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; @@ -120,26 +119,24 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, __asm__ __volatile__ ( " # futex_atomic_cmpxchg_inatomic\n" - "1: l32i %1, %3, 0\n" - " mov %0, %5\n" - " wsr %1, scompare1\n" - "2: s32c1i %0, %3, 0\n" - "3:\n" + " wsr %5, scompare1\n" + "1: s32c1i %1, %4, 0\n" + " s32i %1, %6, 0\n" + "2:\n" " .section .fixup,\"ax\"\n" " .align 4\n" - "4: .long 3b\n" - "5: l32r %1, 4b\n" - " movi %0, %6\n" + "3: .long 2b\n" + "4: l32r %1, 3b\n" + " movi %0, %7\n" " jx %1\n" " .previous\n" " .section __ex_table,\"a\"\n" - " .long 1b,5b,2b,5b\n" + " .long 1b,4b\n" " .previous\n" - : "+r" (ret), "=&r" (prev), "+m" (*uaddr) - : "r" (uaddr), "r" (oldval), "r" (newval), "I" (-EFAULT) + : "+r" (ret), "+r" (newval), "+m" (*uaddr), "+m" (*uval) + : "r" (uaddr), "r" (oldval), "r" (uval), "I" (-EFAULT) : "memory"); - *uval = prev; return ret; } |