diff options
Diffstat (limited to 'arch')
104 files changed, 1112 insertions, 345 deletions
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 87b23b7fb781..aefcf7a4e17a 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -8,6 +8,7 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_BLK_DEV_RAM=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 30e090625916..a72bbda2f7aa 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -106,6 +106,7 @@ ENTRY(stext) ; r2 = pointer to uboot provided cmdline or external DTB in mem ; These are handled later in handle_uboot_args() st r0, [@uboot_tag] + st r1, [@uboot_magic] st r2, [@uboot_arg] ; setup "current" tsk and optionally cache it in dedicated r25 diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 7b2340996cf8..7b3a7b3b380c 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -36,6 +36,7 @@ unsigned int intr_to_DE_cnt; /* Part of U-boot ABI: see head.S */ int __initdata uboot_tag; +int __initdata uboot_magic; char __initdata *uboot_arg; const struct machine_desc *machine_desc; @@ -497,6 +498,8 @@ static inline bool uboot_arg_invalid(unsigned long addr) #define UBOOT_TAG_NONE 0 #define UBOOT_TAG_CMDLINE 1 #define UBOOT_TAG_DTB 2 +/* We always pass 0 as magic from U-boot */ +#define UBOOT_MAGIC_VALUE 0 void __init handle_uboot_args(void) { @@ -511,6 +514,11 @@ void __init handle_uboot_args(void) goto ignore_uboot_args; } + if (uboot_magic != UBOOT_MAGIC_VALUE) { + pr_warn(IGNORE_ARGS "non zero uboot magic\n"); + goto ignore_uboot_args; + } + if (uboot_tag != UBOOT_TAG_NONE && uboot_arg_invalid((unsigned long)uboot_arg)) { pr_warn(IGNORE_ARGS "invalid uboot arg: '%px'\n", uboot_arg); diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S index f230bb7092fd..b3373f5c88e0 100644 --- a/arch/arc/lib/memset-archs.S +++ b/arch/arc/lib/memset-archs.S @@ -30,10 +30,10 @@ #else -.macro PREALLOC_INSTR +.macro PREALLOC_INSTR reg, off .endm -.macro PREFETCHW_INSTR +.macro PREFETCHW_INSTR reg, off .endm #endif diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 26524b75970a..3b353af9c48d 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -69,7 +69,7 @@ config ARM select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL - select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL + select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG select HAVE_FUNCTION_TRACER if !XIP_KERNEL select HAVE_GCC_PLUGINS select HAVE_GENERIC_DMA_COHERENT @@ -593,6 +593,7 @@ config ARCH_DAVINCI select HAVE_IDE select PM_GENERIC_DOMAINS if PM select PM_GENERIC_DOMAINS_OF if PM && OF + select REGMAP_MMIO select RESET_CONTROLLER select USE_OF select ZONE_DMA diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 6d6e0330930b..e388af4594a6 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -47,8 +47,8 @@ config DEBUG_WX choice prompt "Choose kernel unwinder" - default UNWINDER_ARM if AEABI && !FUNCTION_GRAPH_TRACER - default UNWINDER_FRAME_POINTER if !AEABI || FUNCTION_GRAPH_TRACER + default UNWINDER_ARM if AEABI + default UNWINDER_FRAME_POINTER if !AEABI help This determines which method will be used for unwinding kernel stack traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack, @@ -65,7 +65,7 @@ config UNWINDER_FRAME_POINTER config UNWINDER_ARM bool "ARM EABI stack unwinder" - depends on AEABI + depends on AEABI && !FUNCTION_GRAPH_TRACER select ARM_UNWIND help This option enables stack unwinding support in the kernel diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 6c7ccb428c07..7135820f76d4 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1438,7 +1438,21 @@ ENTRY(efi_stub_entry) @ Preserve return value of efi_entry() in r4 mov r4, r0 - bl cache_clean_flush + + @ our cache maintenance code relies on CP15 barrier instructions + @ but since we arrived here with the MMU and caches configured + @ by UEFI, we must check that the CP15BEN bit is set in SCTLR. + @ Note that this bit is RAO/WI on v6 and earlier, so the ISB in + @ the enable path will be executed on v7+ only. + mrc p15, 0, r1, c1, c0, 0 @ read SCTLR + tst r1, #(1 << 5) @ CP15BEN bit set? + bne 0f + orr r1, r1, #(1 << 5) @ CP15 barrier instructions + mcr p15, 0, r1, c1, c0, 0 @ write SCTLR + ARM( .inst 0xf57ff06f @ v7+ isb ) + THUMB( isb ) + +0: bl cache_clean_flush bl cache_off @ Set parameters for booting zImage according to boot protocol diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index 7b818d9d2eab..8396faa9ac28 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -1763,7 +1763,7 @@ reg = <0xcc000 0x4>; reg-names = "rev"; /* Domains (P, C): per_pwrdm, l4ls_clkdm */ - clocks = <&l4ls_clkctrl AM3_D_CAN0_CLKCTRL 0>; + clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN0_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; @@ -1786,7 +1786,7 @@ reg = <0xd0000 0x4>; reg-names = "rev"; /* Domains (P, C): per_pwrdm, l4ls_clkdm */ - clocks = <&l4ls_clkctrl AM3_D_CAN1_CLKCTRL 0>; + clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN1_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts index 5641d162dfdb..28e7513ce617 100644 --- a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts +++ b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts @@ -93,7 +93,7 @@ }; &hdmi { - hpd-gpios = <&gpio 46 GPIO_ACTIVE_LOW>; + hpd-gpios = <&gpio 46 GPIO_ACTIVE_HIGH>; }; &pwm { diff --git a/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi b/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi index 1d1b4bd0670f..a4217f564a53 100644 --- a/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi +++ b/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi @@ -264,7 +264,7 @@ pinctrl-2 = <&pinctrl_usdhc3_200mhz>; vmcc-supply = <®_sd3_vmmc>; cd-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; - bus-witdh = <4>; + bus-width = <4>; no-1-8-v; status = "okay"; }; @@ -275,7 +275,7 @@ pinctrl-1 = <&pinctrl_usdhc4_100mhz>; pinctrl-2 = <&pinctrl_usdhc4_200mhz>; vmcc-supply = <®_sd4_vmmc>; - bus-witdh = <8>; + bus-width = <8>; no-1-8-v; non-removable; status = "okay"; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi index 1b50b01e9bac..65d03c5d409b 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi @@ -90,6 +90,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; phy-mode = "rgmii"; + phy-reset-duration = <10>; /* in msecs */ phy-reset-gpios = <&gpio3 23 GPIO_ACTIVE_LOW>; phy-supply = <&vdd_eth_io_reg>; status = "disabled"; diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index 09868dcee34b..df0c5456c94f 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -1282,27 +1282,27 @@ gpu_opp_table: gpu-opp-table { compatible = "operating-points-v2"; - opp@100000000 { + opp-100000000 { opp-hz = /bits/ 64 <100000000>; opp-microvolt = <950000>; }; - opp@200000000 { + opp-200000000 { opp-hz = /bits/ 64 <200000000>; opp-microvolt = <950000>; }; - opp@300000000 { + opp-300000000 { opp-hz = /bits/ 64 <300000000>; opp-microvolt = <1000000>; }; - opp@400000000 { + opp-400000000 { opp-hz = /bits/ 64 <400000000>; opp-microvolt = <1100000>; }; - opp@500000000 { + opp-500000000 { opp-hz = /bits/ 64 <500000000>; opp-microvolt = <1200000>; }; - opp@600000000 { + opp-600000000 { opp-hz = /bits/ 64 <600000000>; opp-microvolt = <1250000>; }; diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 3a875fc1b63c..cee06509f00a 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -381,6 +381,17 @@ static inline int kvm_read_guest_lock(struct kvm *kvm, return ret; } +static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, + const void *data, unsigned long len) +{ + int srcu_idx = srcu_read_lock(&kvm->srcu); + int ret = kvm_write_guest(kvm, gpa, data, len); + + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return ret; +} + static inline void *kvm_get_hyp_vector(void) { switch(read_cpuid_part()) { diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h index de2089501b8b..9e11dce55e06 100644 --- a/arch/arm/include/asm/stage2_pgtable.h +++ b/arch/arm/include/asm/stage2_pgtable.h @@ -75,6 +75,8 @@ static inline bool kvm_stage2_has_pud(struct kvm *kvm) #define S2_PMD_MASK PMD_MASK #define S2_PMD_SIZE PMD_SIZE +#define S2_PUD_MASK PUD_MASK +#define S2_PUD_SIZE PUD_SIZE static inline bool kvm_stage2_has_pmd(struct kvm *kvm) { diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index ec29de250076..cab89479d15e 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -133,9 +133,9 @@ __secondary_data: */ .text __after_proc_init: -#ifdef CONFIG_ARM_MPU M_CLASS(movw r12, #:lower16:BASEADDR_V7M_SCB) M_CLASS(movt r12, #:upper16:BASEADDR_V7M_SCB) +#ifdef CONFIG_ARM_MPU M_CLASS(ldr r3, [r12, 0x50]) AR_CLASS(mrc p15, 0, r3, c0, c1, 4) @ Read ID_MMFR0 and r3, r3, #(MMFR0_PMSA) @ PMSA field diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c index a50dc00d79a2..d0a05a3bdb96 100644 --- a/arch/arm/kernel/patch.c +++ b/arch/arm/kernel/patch.c @@ -16,7 +16,7 @@ struct patch { unsigned int insn; }; -static DEFINE_SPINLOCK(patch_lock); +static DEFINE_RAW_SPINLOCK(patch_lock); static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) __acquires(&patch_lock) @@ -33,7 +33,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) return addr; if (flags) - spin_lock_irqsave(&patch_lock, *flags); + raw_spin_lock_irqsave(&patch_lock, *flags); else __acquire(&patch_lock); @@ -48,7 +48,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags) clear_fixmap(fixmap); if (flags) - spin_unlock_irqrestore(&patch_lock, *flags); + raw_spin_unlock_irqrestore(&patch_lock, *flags); else __release(&patch_lock); } diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 51e808adb00c..2a757dcaa1a5 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -591,13 +591,13 @@ static int __init at91_pm_backup_init(void) np = of_find_compatible_node(NULL, NULL, "atmel,sama5d2-securam"); if (!np) - goto securam_fail; + goto securam_fail_no_ref_dev; pdev = of_find_device_by_node(np); of_node_put(np); if (!pdev) { pr_warn("%s: failed to find securam device!\n", __func__); - goto securam_fail; + goto securam_fail_no_ref_dev; } sram_pool = gen_pool_get(&pdev->dev, NULL); @@ -620,6 +620,8 @@ static int __init at91_pm_backup_init(void) return 0; securam_fail: + put_device(&pdev->dev); +securam_fail_no_ref_dev: iounmap(pm_data.sfrbu); pm_data.sfrbu = NULL; return ret; diff --git a/arch/arm/mach-imx/mach-imx51.c b/arch/arm/mach-imx/mach-imx51.c index c7169c2f94c4..08c7892866c2 100644 --- a/arch/arm/mach-imx/mach-imx51.c +++ b/arch/arm/mach-imx/mach-imx51.c @@ -59,6 +59,7 @@ static void __init imx51_m4if_setup(void) return; m4if_base = of_iomap(np, 0); + of_node_put(np); if (!m4if_base) { pr_err("Unable to map M4IF registers\n"); return; diff --git a/arch/arm/mach-iop13xx/setup.c b/arch/arm/mach-iop13xx/setup.c index 53c316f7301e..fe4932fda01d 100644 --- a/arch/arm/mach-iop13xx/setup.c +++ b/arch/arm/mach-iop13xx/setup.c @@ -300,7 +300,7 @@ static struct resource iop13xx_adma_2_resources[] = { } }; -static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(64); +static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(32); static struct iop_adma_platform_data iop13xx_adma_0_data = { .hw_id = 0, .pool_size = PAGE_SIZE, @@ -324,7 +324,7 @@ static struct platform_device iop13xx_adma_0_channel = { .resource = iop13xx_adma_0_resources, .dev = { .dma_mask = &iop13xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop13xx_adma_0_data, }, }; @@ -336,7 +336,7 @@ static struct platform_device iop13xx_adma_1_channel = { .resource = iop13xx_adma_1_resources, .dev = { .dma_mask = &iop13xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop13xx_adma_1_data, }, }; @@ -348,7 +348,7 @@ static struct platform_device iop13xx_adma_2_channel = { .resource = iop13xx_adma_2_resources, .dev = { .dma_mask = &iop13xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop13xx_adma_2_data, }, }; diff --git a/arch/arm/mach-iop13xx/tpmi.c b/arch/arm/mach-iop13xx/tpmi.c index db511ec2b1df..116feb6b261e 100644 --- a/arch/arm/mach-iop13xx/tpmi.c +++ b/arch/arm/mach-iop13xx/tpmi.c @@ -152,7 +152,7 @@ static struct resource iop13xx_tpmi_3_resources[] = { } }; -u64 iop13xx_tpmi_mask = DMA_BIT_MASK(64); +u64 iop13xx_tpmi_mask = DMA_BIT_MASK(32); static struct platform_device iop13xx_tpmi_0_device = { .name = "iop-tpmi", .id = 0, @@ -160,7 +160,7 @@ static struct platform_device iop13xx_tpmi_0_device = { .resource = iop13xx_tpmi_0_resources, .dev = { .dma_mask = &iop13xx_tpmi_mask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -171,7 +171,7 @@ static struct platform_device iop13xx_tpmi_1_device = { .resource = iop13xx_tpmi_1_resources, .dev = { .dma_mask = &iop13xx_tpmi_mask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -182,7 +182,7 @@ static struct platform_device iop13xx_tpmi_2_device = { .resource = iop13xx_tpmi_2_resources, .dev = { .dma_mask = &iop13xx_tpmi_mask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -193,7 +193,7 @@ static struct platform_device iop13xx_tpmi_3_device = { .resource = iop13xx_tpmi_3_resources, .dev = { .dma_mask = &iop13xx_tpmi_mask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c index 1444b4b4bd9f..439e143cad7b 100644 --- a/arch/arm/mach-omap2/display.c +++ b/arch/arm/mach-omap2/display.c @@ -250,8 +250,10 @@ static int __init omapdss_init_of(void) if (!node) return 0; - if (!of_device_is_available(node)) + if (!of_device_is_available(node)) { + of_node_put(node); return 0; + } pdev = of_find_device_by_node(node); diff --git a/arch/arm/plat-iop/adma.c b/arch/arm/plat-iop/adma.c index a4d1f8de3b5b..d9612221e484 100644 --- a/arch/arm/plat-iop/adma.c +++ b/arch/arm/plat-iop/adma.c @@ -143,7 +143,7 @@ struct platform_device iop3xx_dma_0_channel = { .resource = iop3xx_dma_0_resources, .dev = { .dma_mask = &iop3xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop3xx_dma_0_data, }, }; @@ -155,7 +155,7 @@ struct platform_device iop3xx_dma_1_channel = { .resource = iop3xx_dma_1_resources, .dev = { .dma_mask = &iop3xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop3xx_dma_1_data, }, }; @@ -167,7 +167,7 @@ struct platform_device iop3xx_aau_channel = { .resource = iop3xx_aau_resources, .dev = { .dma_mask = &iop3xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop3xx_aau_data, }, }; diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index a2399fd66e97..1e970873439c 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -622,7 +622,7 @@ static struct platform_device orion_xor0_shared = { .resource = orion_xor0_shared_resources, .dev = { .dma_mask = &orion_xor_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = &orion_xor0_pdata, }, }; @@ -683,7 +683,7 @@ static struct platform_device orion_xor1_shared = { .resource = orion_xor1_shared_resources, .dev = { .dma_mask = &orion_xor_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = &orion_xor1_pdata, }, }; diff --git a/arch/arm64/boot/dts/renesas/r8a77990.dtsi b/arch/arm64/boot/dts/renesas/r8a77990.dtsi index b2f606e286ce..327d12097643 100644 --- a/arch/arm64/boot/dts/renesas/r8a77990.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77990.dtsi @@ -2,7 +2,7 @@ /* * Device Tree Source for the R-Car E3 (R8A77990) SoC * - * Copyright (C) 2018 Renesas Electronics Corp. + * Copyright (C) 2018-2019 Renesas Electronics Corp. */ #include <dt-bindings/clock/r8a77990-cpg-mssr.h> @@ -1040,9 +1040,8 @@ <&cpg CPG_CORE R8A77990_CLK_S3D1C>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; - dmas = <&dmac1 0x5b>, <&dmac1 0x5a>, - <&dmac2 0x5b>, <&dmac2 0x5a>; - dma-names = "tx", "rx", "tx", "rx"; + dmas = <&dmac0 0x5b>, <&dmac0 0x5a>; + dma-names = "tx", "rx"; power-domains = <&sysc R8A77990_PD_ALWAYS_ON>; resets = <&cpg 202>; status = "disabled"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts index 99d0d9912950..a91f87df662e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts @@ -107,8 +107,8 @@ snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; - tx_delay = <0x25>; - rx_delay = <0x11>; + tx_delay = <0x24>; + rx_delay = <0x18>; status = "okay"; }; diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index e1d95f08f8e1..6fb2214333a2 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -23,26 +23,34 @@ #include <asm/errno.h> +#define FUTEX_MAX_LOOPS 128 /* What's the largest number you can think of? */ + #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg) \ do { \ + unsigned int loops = FUTEX_MAX_LOOPS; \ + \ uaccess_enable(); \ asm volatile( \ " prfm pstl1strm, %2\n" \ "1: ldxr %w1, %2\n" \ insn "\n" \ "2: stlxr %w0, %w3, %2\n" \ -" cbnz %w0, 1b\n" \ -" dmb ish\n" \ +" cbz %w0, 3f\n" \ +" sub %w4, %w4, %w0\n" \ +" cbnz %w4, 1b\n" \ +" mov %w0, %w7\n" \ "3:\n" \ +" dmb ish\n" \ " .pushsection .fixup,\"ax\"\n" \ " .align 2\n" \ -"4: mov %w0, %w5\n" \ +"4: mov %w0, %w6\n" \ " b 3b\n" \ " .popsection\n" \ _ASM_EXTABLE(1b, 4b) \ _ASM_EXTABLE(2b, 4b) \ - : "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp) \ - : "r" (oparg), "Ir" (-EFAULT) \ + : "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp), \ + "+r" (loops) \ + : "r" (oparg), "Ir" (-EFAULT), "Ir" (-EAGAIN) \ : "memory"); \ uaccess_disable(); \ } while (0) @@ -50,30 +58,30 @@ do { \ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) { - int oldval, ret, tmp; + int oldval = 0, ret, tmp; u32 __user *uaddr = __uaccess_mask_ptr(_uaddr); pagefault_disable(); switch (op) { case FUTEX_OP_SET: - __futex_atomic_op("mov %w3, %w4", + __futex_atomic_op("mov %w3, %w5", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_ADD: - __futex_atomic_op("add %w3, %w1, %w4", + __futex_atomic_op("add %w3, %w1, %w5", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_OR: - __futex_atomic_op("orr %w3, %w1, %w4", + __futex_atomic_op("orr %w3, %w1, %w5", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_ANDN: - __futex_atomic_op("and %w3, %w1, %w4", + __futex_atomic_op("and %w3, %w1, %w5", ret, oldval, uaddr, tmp, ~oparg); break; case FUTEX_OP_XOR: - __futex_atomic_op("eor %w3, %w1, %w4", + __futex_atomic_op("eor %w3, %w1, %w5", ret, oldval, uaddr, tmp, oparg); break; default: @@ -93,6 +101,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr, u32 oldval, u32 newval) { int ret = 0; + unsigned int loops = FUTEX_MAX_LOOPS; u32 val, tmp; u32 __user *uaddr; @@ -104,20 +113,24 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr, asm volatile("// futex_atomic_cmpxchg_inatomic\n" " prfm pstl1strm, %2\n" "1: ldxr %w1, %2\n" -" sub %w3, %w1, %w4\n" -" cbnz %w3, 3f\n" -"2: stlxr %w3, %w5, %2\n" -" cbnz %w3, 1b\n" -" dmb ish\n" +" sub %w3, %w1, %w5\n" +" cbnz %w3, 4f\n" +"2: stlxr %w3, %w6, %2\n" +" cbz %w3, 3f\n" +" sub %w4, %w4, %w3\n" +" cbnz %w4, 1b\n" +" mov %w0, %w8\n" "3:\n" +" dmb ish\n" +"4:\n" " .pushsection .fixup,\"ax\"\n" -"4: mov %w0, %w6\n" -" b 3b\n" +"5: mov %w0, %w7\n" +" b 4b\n" " .popsection\n" - _ASM_EXTABLE(1b, 4b) - _ASM_EXTABLE(2b, 4b) - : "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp) - : "r" (oldval), "r" (newval), "Ir" (-EFAULT) + _ASM_EXTABLE(1b, 5b) + _ASM_EXTABLE(2b, 5b) + : "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops) + : "r" (oldval), "r" (newval), "Ir" (-EFAULT), "Ir" (-EAGAIN) : "memory"); uaccess_disable(); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 8af4b1befa42..c246effd1b67 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -444,6 +444,17 @@ static inline int kvm_read_guest_lock(struct kvm *kvm, return ret; } +static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, + const void *data, unsigned long len) +{ + int srcu_idx = srcu_read_lock(&kvm->srcu); + int ret = kvm_write_guest(kvm, gpa, data, len); + + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return ret; +} + #ifdef CONFIG_KVM_INDIRECT_VECTORS /* * EL2 vectors can be mapped and rerouted in a number of ways, diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 07b298120182..65a51331088e 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -103,10 +103,15 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * to be revisited if support for multiple ftrace entry points * is added in the future, but for now, the pr_err() below * deals with a theoretical issue only. + * + * Note that PLTs are place relative, and plt_entries_equal() + * checks whether they point to the same target. Here, we need + * to check if the actual opcodes are in fact identical, + * regardless of the offset in memory so use memcmp() instead. */ trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline); - if (!plt_entries_equal(mod->arch.ftrace_trampoline, - &trampoline)) { + if (memcmp(mod->arch.ftrace_trampoline, &trampoline, + sizeof(trampoline))) { if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) { pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); return -EINVAL; diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index 5ba4465e44f0..ea94cf8f9dc6 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -94,6 +94,9 @@ static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info) unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr); unsigned long high = low + SDEI_STACK_SIZE; + if (!low) + return false; + if (sp < low || sp >= high) return false; @@ -111,6 +114,9 @@ static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info) unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr); unsigned long high = low + SDEI_STACK_SIZE; + if (!low) + return false; + if (sp < low || sp >= high) return false; diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index f16a5f8ff2b4..e2a0500cd7a2 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -123,6 +123,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) int ret = -EINVAL; bool loaded; + /* Reset PMU outside of the non-preemptible section */ + kvm_pmu_vcpu_reset(vcpu); + preempt_disable(); loaded = (vcpu->cpu != -1); if (loaded) @@ -170,9 +173,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.reset_state.reset = false; } - /* Reset PMU */ - kvm_pmu_vcpu_reset(vcpu); - /* Default workaround setup is enabled (if supported) */ if (kvm_arm_have_ssbd() == KVM_SSBD_KERNEL) vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 7205a9085b4d..c9411774555d 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -406,7 +406,7 @@ void __init arm64_memblock_init(void) * Otherwise, this is a no-op */ u64 base = phys_initrd_start & PAGE_MASK; - u64 size = PAGE_ALIGN(phys_initrd_size); + u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base; /* * We can only add back the initrd memory if we don't end up diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 9728abcb18fa..c04ae685003f 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -211,12 +211,6 @@ const char *get_system_type(void) return ath79_sys_type; } -int get_c0_perfcount_int(void) -{ - return ATH79_MISC_IRQ(5); -} -EXPORT_SYMBOL_GPL(get_c0_perfcount_int); - unsigned int get_c0_compare_int(void) { return CP0_LEGACY_COMPARE_IRQ; diff --git a/arch/mips/bcm47xx/workarounds.c b/arch/mips/bcm47xx/workarounds.c index 46eddbec8d9f..0ab95dd431b3 100644 --- a/arch/mips/bcm47xx/workarounds.c +++ b/arch/mips/bcm47xx/workarounds.c @@ -24,6 +24,7 @@ void __init bcm47xx_workarounds(void) case BCM47XX_BOARD_NETGEAR_WNR3500L: bcm47xx_workarounds_enable_usb_power(12); break; + case BCM47XX_BOARD_NETGEAR_WNDR3400V2: case BCM47XX_BOARD_NETGEAR_WNDR3400_V3: bcm47xx_workarounds_enable_usb_power(21); break; diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c index 149100e1bc7c..90f37626100f 100644 --- a/arch/mips/kernel/kgdb.c +++ b/arch/mips/kernel/kgdb.c @@ -33,6 +33,7 @@ #include <asm/processor.h> #include <asm/sigcontext.h> #include <linux/uaccess.h> +#include <asm/irq_regs.h> static struct hard_trap_info { unsigned char tt; /* Trap type code for MIPS R3xxx and R4xxx */ @@ -214,7 +215,7 @@ void kgdb_call_nmi_hook(void *ignored) old_fs = get_fs(); set_fs(get_ds()); - kgdb_nmicallback(raw_smp_processor_id(), NULL); + kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs()); set_fs(old_fs); } diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index f158c5894a9a..feb2653490df 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -125,7 +125,7 @@ trace_a_syscall: subu t1, v0, __NR_O32_Linux move a1, v0 bnez t1, 1f /* __NR_syscall at offset 0 */ - lw a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ + ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ .set pop 1: jal syscall_trace_enter diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index cfdd08897a06..e2b0c5f15c7b 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -260,6 +260,7 @@ CONFIG_UDF_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_PROC_KCORE=y +CONFIG_HUGETLBFS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_NLS=y diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 9c1173283b96..6c6211a82b9a 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -81,6 +81,9 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), pgtable_gfp_flags(mm, GFP_KERNEL)); + if (unlikely(!pgd)) + return pgd; + /* * Don't scan the PGD for pointers, it contains references to PUDs but * those references are not full pointers and so can't be recognised by diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index eb2a33d5df26..e382bd6ede84 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -41,7 +41,7 @@ #if defined(CONFIG_PPC_BOOK3E_64) #define MSR_64BIT MSR_CM -#define MSR_ (MSR_ME | MSR_CE) +#define MSR_ (MSR_ME | MSR_RI | MSR_CE) #define MSR_KERNEL (MSR_ | MSR_64BIT) #define MSR_USER32 (MSR_ | MSR_PR | MSR_EE) #define MSR_USER64 (MSR_USER32 | MSR_64BIT) diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 7f5ac2e8581b..36178000a2f2 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -170,6 +170,9 @@ core_idle_lock_held: bne- core_idle_lock_held blr +/* Reuse an unused pt_regs slot for IAMR */ +#define PNV_POWERSAVE_IAMR _DAR + /* * Pass requested state in r3: * r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8 @@ -200,6 +203,12 @@ pnv_powersave_common: /* Continue saving state */ SAVE_GPR(2, r1) SAVE_NVGPRS(r1) + +BEGIN_FTR_SECTION + mfspr r5, SPRN_IAMR + std r5, PNV_POWERSAVE_IAMR(r1) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + mfcr r5 std r5,_CCR(r1) std r1,PACAR1(r13) @@ -924,6 +933,17 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) REST_NVGPRS(r1) REST_GPR(2, r1) + +BEGIN_FTR_SECTION + /* IAMR was saved in pnv_powersave_common() */ + ld r5, PNV_POWERSAVE_IAMR(r1) + mtspr SPRN_IAMR, r5 + /* + * We don't need an isync here because the upcoming mtmsrd is + * execution synchronizing. + */ +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + ld r4,PACAKMSR(r13) ld r5,_LINK(r1) ld r6,_CCR(r1) diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 683b5b3805bd..cd381e2291df 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -22,6 +22,7 @@ #include <linux/kvm_host.h> #include <linux/init.h> #include <linux/export.h> +#include <linux/kmemleak.h> #include <linux/kvm_para.h> #include <linux/slab.h> #include <linux/of.h> @@ -712,6 +713,12 @@ static void kvm_use_magic_page(void) static __init void kvm_free_tmp(void) { + /* + * Inform kmemleak about the hole in the .bss section since the + * corresponding pages will be unmapped with DEBUG_PAGEALLOC=y. + */ + kmemleak_free_part(&kvm_tmp[kvm_tmp_index], + ARRAY_SIZE(kvm_tmp) - kvm_tmp_index); free_reserved_area(&kvm_tmp[kvm_tmp_index], &kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL); } diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index b33bafb8fcea..70568ccbd9fd 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -57,7 +57,7 @@ void setup_barrier_nospec(void) enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR); - if (!no_nospec) + if (!no_nospec && !cpu_mitigations_off()) enable_barrier_nospec(enable); } @@ -116,7 +116,7 @@ static int __init handle_nospectre_v2(char *p) early_param("nospectre_v2", handle_nospectre_v2); void setup_spectre_v2(void) { - if (no_spectrev2) + if (no_spectrev2 || cpu_mitigations_off()) do_btb_flush_fixups(); else btb_flush_enabled = true; @@ -300,7 +300,7 @@ void setup_stf_barrier(void) stf_enabled_flush_types = type; - if (!no_stf_barrier) + if (!no_stf_barrier && !cpu_mitigations_off()) stf_barrier_enable(enable); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 236c1151a3a7..c7ec27ba8926 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -958,7 +958,7 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable) enabled_flush_types = types; - if (!no_rfi_flush) + if (!no_rfi_flush && !cpu_mitigations_off()) rfi_flush_enable(enable); } diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 1e0bc5955a40..afd516b572f8 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -98,7 +98,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) * can be used, r7 contains NSEC_PER_SEC. */ - lwz r5,WTOM_CLOCK_SEC(r9) + lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9) lwz r6,WTOM_CLOCK_NSEC(r9) /* We now have our offset in r5,r6. We create a fake dependency diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 06898c13901d..aec91dbcdc0b 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -32,6 +32,7 @@ #include <linux/export.h> #include <linux/hugetlb.h> #include <linux/sched/mm.h> +#include <linux/security.h> #include <asm/mman.h> #include <asm/mmu.h> #include <asm/copro.h> @@ -377,6 +378,7 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); unsigned long addr, found, prev; struct vm_unmapped_area_info info; + unsigned long min_addr = max(PAGE_SIZE, mmap_min_addr); info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; @@ -393,7 +395,7 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, if (high_limit > DEFAULT_MAP_WINDOW) addr += mm->context.slb_addr_limit - DEFAULT_MAP_WINDOW; - while (addr > PAGE_SIZE) { + while (addr > min_addr) { info.high_limit = addr; if (!slice_scan_available(addr - 1, available, 0, &addr)) continue; @@ -405,8 +407,8 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, * Check if we need to reduce the range, or if we can * extend it to cover the previous available slice. */ - if (addr < PAGE_SIZE) - addr = PAGE_SIZE; + if (addr < min_addr) + addr = min_addr; else if (slice_scan_available(addr - 1, available, 0, &prev)) { addr = prev; goto prev_slice; @@ -528,7 +530,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, addr = _ALIGN_UP(addr, page_size); slice_dbg(" aligned addr=%lx\n", addr); /* Ignore hint if it's too large or overlaps a VMA */ - if (addr > high_limit - len || + if (addr > high_limit - len || addr < mmap_min_addr || !slice_area_is_free(mm, addr, len)) addr = 0; } diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 8c7464c3f27f..2782188a5ba1 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -318,7 +318,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK config PPC_RADIX_MMU bool "Radix MMU Support" - depends on PPC_BOOK3S_64 + depends on PPC_BOOK3S_64 && HUGETLB_PAGE select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA default y help diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 637b896894fc..aa82df30e38a 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -301,7 +301,7 @@ do { \ " .balign 4\n" \ "4:\n" \ " li %0, %6\n" \ - " jump 2b, %1\n" \ + " jump 3b, %1\n" \ " .previous\n" \ " .section __ex_table,\"a\"\n" \ " .balign " RISCV_SZPTR "\n" \ diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c index 4cb771ba13fa..5d316fe40480 100644 --- a/arch/s390/boot/mem_detect.c +++ b/arch/s390/boot/mem_detect.c @@ -25,7 +25,7 @@ static void *mem_detect_alloc_extended(void) { unsigned long offset = ALIGN(mem_safe_offset(), sizeof(u64)); - if (IS_ENABLED(BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE && + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE && INITRD_START < offset + ENTRIES_EXTENDED_MAX) offset = ALIGN(INITRD_START + INITRD_SIZE, sizeof(u64)); diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 7d22a474a040..f74639a05f0f 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -252,11 +252,14 @@ do { \ /* * Cache aliasing on the latest machines calls for a mapping granularity - * of 512KB. For 64-bit processes use a 512KB alignment and a randomization - * of up to 1GB. For 31-bit processes the virtual address space is limited, - * use no alignment and limit the randomization to 8MB. + * of 512KB for the anonymous mapping base. For 64-bit processes use a + * 512KB alignment and a randomization of up to 1GB. For 31-bit processes + * the virtual address space is limited, use no alignment and limit the + * randomization to 8MB. + * For the additional randomization of the program break use 32MB for + * 64-bit and 8MB for 31-bit. */ -#define BRK_RND_MASK (is_compat_task() ? 0x7ffUL : 0x3ffffUL) +#define BRK_RND_MASK (is_compat_task() ? 0x7ffUL : 0x1fffUL) #define MMAP_RND_MASK (is_compat_task() ? 0x7ffUL : 0x3ff80UL) #define MMAP_ALIGN_MASK (is_compat_task() ? 0 : 0x7fUL) #define STACK_RND_MASK MMAP_RND_MASK diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c index bdddaae96559..649135cbedd5 100644 --- a/arch/s390/kernel/nospec-branch.c +++ b/arch/s390/kernel/nospec-branch.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> #include <linux/device.h> +#include <linux/cpu.h> #include <asm/nospec-branch.h> static int __init nobp_setup_early(char *str) @@ -58,7 +59,7 @@ early_param("nospectre_v2", nospectre_v2_setup_early); void __init nospec_auto_detect(void) { - if (test_facility(156)) { + if (test_facility(156) || cpu_mitigations_off()) { /* * The machine supports etokens. * Disable expolines and disable nobp. diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c index 958f46da3a79..d91065e81a4e 100644 --- a/arch/sh/boards/of-generic.c +++ b/arch/sh/boards/of-generic.c @@ -164,10 +164,10 @@ static struct sh_machine_vector __initmv sh_of_generic_mv = { struct sh_clk_ops; -void __init arch_init_clk_ops(struct sh_clk_ops **ops, int idx) +void __init __weak arch_init_clk_ops(struct sh_clk_ops **ops, int idx) { } -void __init plat_irq_setup(void) +void __init __weak plat_irq_setup(void) { } diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 9c5a67d1b9c1..c0c7291d4ccf 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -217,6 +217,15 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre ifdef CONFIG_RETPOLINE KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) + # Additionally, avoid generating expensive indirect jumps which + # are subject to retpolines for small number of switch cases. + # clang turns off jump table generation by default when under + # retpoline builds, however, gcc does not for x86. This has + # only been fixed starting from gcc stable version 8.4.0 and + # onwards, but not for older ones. See gcc bug #86952. + ifndef CONFIG_CC_IS_CLANG + KBUILD_CFLAGS += $(call cc-option,-fno-jump-tables) + endif endif archscripts: scripts_basic diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S index 3b6e70d085da..8457cdd47f75 100644 --- a/arch/x86/crypto/poly1305-avx2-x86_64.S +++ b/arch/x86/crypto/poly1305-avx2-x86_64.S @@ -323,6 +323,12 @@ ENTRY(poly1305_4block_avx2) vpaddq t2,t1,t1 vmovq t1x,d4 + # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> + # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small + # amount. Careful: we must not assume the carry bits 'd0 >> 26', + # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit + # integers. It's true in a single-block implementation, but not here. + # d1 += d0 >> 26 mov d0,%rax shr $26,%rax @@ -361,16 +367,16 @@ ENTRY(poly1305_4block_avx2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S index c88c670cb5fc..5851c7418fb7 100644 --- a/arch/x86/crypto/poly1305-sse2-x86_64.S +++ b/arch/x86/crypto/poly1305-sse2-x86_64.S @@ -253,16 +253,16 @@ ENTRY(poly1305_block_sse2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx @@ -520,6 +520,12 @@ ENTRY(poly1305_2block_sse2) paddq t2,t1 movq t1,d4 + # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> + # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small + # amount. Careful: we must not assume the carry bits 'd0 >> 26', + # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit + # integers. It's true in a single-block implementation, but not here. + # d1 += d0 >> 26 mov d0,%rax shr $26,%rax @@ -558,16 +564,16 @@ ENTRY(poly1305_2block_sse2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 7bc105f47d21..19f650d729f5 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -31,6 +31,7 @@ #include <asm/vdso.h> #include <linux/uaccess.h> #include <asm/cpufeature.h> +#include <asm/nospec-branch.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -212,6 +213,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) #endif user_enter_irqoff(); + + mds_user_clear_cpu_buffers(); } #define SYSCALL_EXIT_WORK_FLAGS \ diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 0ecfac84ba91..f15441b07dad 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -116,23 +116,144 @@ static __initconst const u64 amd_hw_cache_event_ids }, }; +static __initconst const u64 amd_hw_cache_event_ids_f17h + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { +[C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */ + [C(RESULT_MISS)] = 0xc860, /* L2$ access from DC Miss */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */ + [C(RESULT_MISS)] = 0, + }, +}, +[C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches */ + [C(RESULT_MISS)] = 0x0081, /* Instruction cache misses */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, +}, +[C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, +}, +[C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */ + [C(RESULT_MISS)] = 0xf045, /* L2 DTLB misses (PT walks) */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, +}, +[C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */ + [C(RESULT_MISS)] = 0xff85, /* L1 ITLB misses, L2 misses */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, +}, +[C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr. */ + [C(RESULT_MISS)] = 0x00c3, /* Retired Mispredicted BI */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, +}, +[C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, +}, +}; + /* - * AMD Performance Monitor K7 and later. + * AMD Performance Monitor K7 and later, up to and including Family 16h: */ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = { - [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, - [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, + [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ +}; + +/* + * AMD Performance Monitor Family 17h and later: + */ +static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187, }; static u64 amd_pmu_event_map(int hw_event) { + if (boot_cpu_data.x86 >= 0x17) + return amd_f17h_perfmon_event_map[hw_event]; + return amd_perfmon_event_map[hw_event]; } @@ -848,9 +969,10 @@ __init int amd_pmu_init(void) x86_pmu.amd_nb_constraints = 0; } - /* Events are common for all AMDs */ - memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, - sizeof(hw_cache_event_ids)); + if (boot_cpu_data.x86 >= 0x17) + memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids)); + else + memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids)); return 0; } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2480feb07df3..71fb8b7b2954 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3130,7 +3130,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event) flags &= ~PERF_SAMPLE_TIME; if (!event->attr.exclude_kernel) flags &= ~PERF_SAMPLE_REGS_USER; - if (event->attr.sample_regs_user & ~PEBS_REGS) + if (event->attr.sample_regs_user & ~PEBS_GP_REGS) flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR); return flags; } @@ -3184,7 +3184,7 @@ static int intel_pmu_hw_config(struct perf_event *event) return ret; if (event->attr.precise_ip) { - if (!event->attr.freq) { + if (!(event->attr.freq || event->attr.wakeup_events)) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; if (!(event->attr.sample_type & ~intel_pmu_large_pebs_flags(event))) @@ -3563,6 +3563,12 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = NULL; + if (x86_pmu.flags & PMU_FL_TFA) { + WARN_ON_ONCE(cpuc->tfa_shadow); + cpuc->tfa_shadow = ~0ULL; + intel_set_tfa(cpuc, false); + } + if (x86_pmu.version > 1) flip_smm_bit(&x86_pmu.attr_freeze_on_smi); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index d2e780705c5a..56194c571299 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -76,15 +76,15 @@ * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 - * Available model: HSW ULT,CNL + * Available model: HSW ULT,KBL,CNL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 - * Available model: HSW ULT,CNL + * Available model: HSW ULT,KBL,CNL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT,GLM,CNL + * Available model: HSW ULT,KBL,GLM,CNL * Scope: Package (physical package) * */ @@ -572,8 +572,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, hswult_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, hswult_cstates), X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates), diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index acd72e669c04..b68ab65454ff 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -96,25 +96,25 @@ struct amd_nb { PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \ PERF_SAMPLE_PERIOD) -#define PEBS_REGS \ - (PERF_REG_X86_AX | \ - PERF_REG_X86_BX | \ - PERF_REG_X86_CX | \ - PERF_REG_X86_DX | \ - PERF_REG_X86_DI | \ - PERF_REG_X86_SI | \ - PERF_REG_X86_SP | \ - PERF_REG_X86_BP | \ - PERF_REG_X86_IP | \ - PERF_REG_X86_FLAGS | \ - PERF_REG_X86_R8 | \ - PERF_REG_X86_R9 | \ - PERF_REG_X86_R10 | \ - PERF_REG_X86_R11 | \ - PERF_REG_X86_R12 | \ - PERF_REG_X86_R13 | \ - PERF_REG_X86_R14 | \ - PERF_REG_X86_R15) +#define PEBS_GP_REGS \ + ((1ULL << PERF_REG_X86_AX) | \ + (1ULL << PERF_REG_X86_BX) | \ + (1ULL << PERF_REG_X86_CX) | \ + (1ULL << PERF_REG_X86_DX) | \ + (1ULL << PERF_REG_X86_DI) | \ + (1ULL << PERF_REG_X86_SI) | \ + (1ULL << PERF_REG_X86_SP) | \ + (1ULL << PERF_REG_X86_BP) | \ + (1ULL << PERF_REG_X86_IP) | \ + (1ULL << PERF_REG_X86_FLAGS) | \ + (1ULL << PERF_REG_X86_R8) | \ + (1ULL << PERF_REG_X86_R9) | \ + (1ULL << PERF_REG_X86_R10) | \ + (1ULL << PERF_REG_X86_R11) | \ + (1ULL << PERF_REG_X86_R12) | \ + (1ULL << PERF_REG_X86_R13) | \ + (1ULL << PERF_REG_X86_R14) | \ + (1ULL << PERF_REG_X86_R15)) /* * Per register state. diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index d3f42b6bbdac..8a9cff1f129d 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -102,9 +102,13 @@ static int hv_cpu_init(unsigned int cpu) u64 msr_vp_index; struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; void **input_arg; + struct page *pg; input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - *input_arg = page_address(alloc_page(GFP_KERNEL)); + pg = alloc_page(GFP_KERNEL); + if (unlikely(!pg)) + return -ENOMEM; + *input_arg = page_address(pg); hv_get_vp_index(msr_vp_index); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 981ff9479648..75f27ee2c263 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -344,6 +344,7 @@ /* 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_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ @@ -382,5 +383,7 @@ #define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ #define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ +#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ +#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 058e40fed167..8a0e56e1dcc9 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -6,6 +6,8 @@ #ifndef __ASSEMBLY__ +#include <asm/nospec-branch.h> + /* Provide __cpuidle; we can't safely include <linux/cpu.h> */ #define __cpuidle __attribute__((__section__(".cpuidle.text"))) @@ -54,11 +56,13 @@ static inline void native_irq_enable(void) static inline __cpuidle void native_safe_halt(void) { + mds_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static inline __cpuidle void native_halt(void) { + mds_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 71d763ad2637..9f2d890733a9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1198,6 +1198,8 @@ struct kvm_x86_ops { int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu); + + bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu); }; struct kvm_arch_async_pf { diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ca5bc0eacb95..20f7da552e90 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_MSR_INDEX_H #define _ASM_X86_MSR_INDEX_H +#include <linux/bits.h> + /* * CPU model specific register (MSR) numbers. * @@ -40,14 +42,14 @@ /* 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_IBRS BIT(0) /* Indirect Branch Restricted Speculation */ #define SPEC_CTRL_STIBP_SHIFT 1 /* Single Thread Indirect Branch Predictor (STIBP) bit */ -#define SPEC_CTRL_STIBP (1 << SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ +#define SPEC_CTRL_STIBP BIT(SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ #define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ -#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ +#define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ -#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f @@ -69,20 +71,25 @@ #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 ARCH_CAP_SKIP_VMENTRY_L1DFLUSH (1 << 3) /* Skip L1D flush on vmentry */ -#define ARCH_CAP_SSB_NO (1 << 4) /* - * Not susceptible to Speculative Store Bypass - * attack, so no Speculative Store Bypass - * control required. - */ +#define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */ +#define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */ +#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH BIT(3) /* Skip L1D flush on vmentry */ +#define ARCH_CAP_SSB_NO BIT(4) /* + * Not susceptible to Speculative Store Bypass + * attack, so no Speculative Store Bypass + * control required. + */ +#define ARCH_CAP_MDS_NO BIT(5) /* + * Not susceptible to + * Microarchitectural Data + * Sampling (MDS) vulnerabilities. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b -#define L1D_FLUSH (1 << 0) /* - * Writeback and invalidate the - * L1 data cache. - */ +#define L1D_FLUSH BIT(0) /* + * Writeback and invalidate the + * L1 data cache. + */ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 39a2fb29378a..eb0f80ce8524 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -6,6 +6,7 @@ #include <linux/sched/idle.h> #include <asm/cpufeature.h> +#include <asm/nospec-branch.h> #define MWAIT_SUBSTATE_MASK 0xf #define MWAIT_CSTATE_MASK 0xf @@ -40,6 +41,8 @@ static inline void __monitorx(const void *eax, unsigned long ecx, static inline void __mwait(unsigned long eax, unsigned long ecx) { + mds_idle_clear_cpu_buffers(); + /* "mwait %eax, %ecx;" */ asm volatile(".byte 0x0f, 0x01, 0xc9;" :: "a" (eax), "c" (ecx)); @@ -74,6 +77,8 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) static inline void __mwaitx(unsigned long eax, unsigned long ebx, unsigned long ecx) { + /* No MDS buffer clear as this is AMD/HYGON only */ + /* "mwaitx %eax, %ebx, %ecx;" */ asm volatile(".byte 0x0f, 0x01, 0xfb;" :: "a" (eax), "b" (ebx), "c" (ecx)); @@ -81,6 +86,8 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx, static inline void __sti_mwait(unsigned long eax, unsigned long ecx) { + mds_idle_clear_cpu_buffers(); + trace_hardirqs_on(); /* "mwait %eax, %ecx;" */ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index dad12b767ba0..4e970390110f 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -318,6 +318,56 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); +DECLARE_STATIC_KEY_FALSE(mds_user_clear); +DECLARE_STATIC_KEY_FALSE(mds_idle_clear); + +#include <asm/segment.h> + +/** + * mds_clear_cpu_buffers - Mitigation for MDS vulnerability + * + * This uses the otherwise unused and obsolete VERW instruction in + * combination with microcode which triggers a CPU buffer flush when the + * instruction is executed. + */ +static inline void mds_clear_cpu_buffers(void) +{ + static const u16 ds = __KERNEL_DS; + + /* + * Has to be the memory-operand variant because only that + * guarantees the CPU buffer flush functionality according to + * documentation. The register-operand variant does not. + * Works with any segment selector, but a valid writable + * data segment is the fastest variant. + * + * "cc" clobber is required because VERW modifies ZF. + */ + asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); +} + +/** + * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability + * + * Clear CPU buffers if the corresponding static key is enabled + */ +static inline void mds_user_clear_cpu_buffers(void) +{ + if (static_branch_likely(&mds_user_clear)) + mds_clear_cpu_buffers(); +} + +/** + * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability + * + * Clear CPU buffers if the corresponding static key is enabled + */ +static inline void mds_idle_clear_cpu_buffers(void) +{ + if (static_branch_likely(&mds_idle_clear)) + mds_clear_cpu_buffers(); +} + #endif /* __ASSEMBLY__ */ /* diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 33051436c864..aca1ef8cc79f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -992,4 +992,10 @@ enum l1tf_mitigations { extern enum l1tf_mitigations l1tf_mitigation; +enum mds_mitigations { + MDS_MITIGATION_OFF, + MDS_MITIGATION_FULL, + MDS_MITIGATION_VMWERV, +}; + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index dabfcf7c3941..7a0e64ccd6ff 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -381,6 +381,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index f0b0c90dd398..d213ec5c3766 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -146,6 +146,7 @@ #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 +#define VMX_ABORT_VMCS_CORRUPTED 3 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 #endif /* _UAPIVMX_H */ diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 58176b56354e..294ed4392a0e 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -14,6 +14,7 @@ #define pr_fmt(fmt) "AGP: " fmt #include <linux/kernel.h> +#include <linux/kcore.h> #include <linux/types.h> #include <linux/init.h> #include <linux/memblock.h> @@ -57,7 +58,7 @@ int fallback_aper_force __initdata; int fix_aperture __initdata = 1; -#ifdef CONFIG_PROC_VMCORE +#if defined(CONFIG_PROC_VMCORE) || defined(CONFIG_PROC_KCORE) /* * If the first kernel maps the aperture over e820 RAM, the kdump kernel will * use the same range because it will remain configured in the northbridge. @@ -66,20 +67,25 @@ int fix_aperture __initdata = 1; */ static unsigned long aperture_pfn_start, aperture_page_count; -static int gart_oldmem_pfn_is_ram(unsigned long pfn) +static int gart_mem_pfn_is_ram(unsigned long pfn) { return likely((pfn < aperture_pfn_start) || (pfn >= aperture_pfn_start + aperture_page_count)); } -static void exclude_from_vmcore(u64 aper_base, u32 aper_order) +static void __init exclude_from_core(u64 aper_base, u32 aper_order) { aperture_pfn_start = aper_base >> PAGE_SHIFT; aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT; - WARN_ON(register_oldmem_pfn_is_ram(&gart_oldmem_pfn_is_ram)); +#ifdef CONFIG_PROC_VMCORE + WARN_ON(register_oldmem_pfn_is_ram(&gart_mem_pfn_is_ram)); +#endif +#ifdef CONFIG_PROC_KCORE + WARN_ON(register_mem_pfn_is_ram(&gart_mem_pfn_is_ram)); +#endif } #else -static void exclude_from_vmcore(u64 aper_base, u32 aper_order) +static void exclude_from_core(u64 aper_base, u32 aper_order) { } #endif @@ -474,7 +480,7 @@ out: * may have allocated the range over its e820 RAM * and fixed up the northbridge */ - exclude_from_vmcore(last_aper_base, last_aper_order); + exclude_from_core(last_aper_base, last_aper_order); return 1; } @@ -520,7 +526,7 @@ out: * overlap with the first kernel's memory. We can't access the * range through vmcore even though it should be part of the dump. */ - exclude_from_vmcore(aper_alloc, aper_order); + exclude_from_core(aper_alloc, aper_order); /* Fix up the north bridges */ for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 01874d54f4fd..1b2ce0c6c4da 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -37,6 +37,7 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); +static void __init mds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -63,6 +64,13 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); +/* Control MDS CPU buffer clear before returning to user space */ +DEFINE_STATIC_KEY_FALSE(mds_user_clear); +EXPORT_SYMBOL_GPL(mds_user_clear); +/* Control MDS CPU buffer clear before idling (halt, mwait) */ +DEFINE_STATIC_KEY_FALSE(mds_idle_clear); +EXPORT_SYMBOL_GPL(mds_idle_clear); + void __init check_bugs(void) { identify_boot_cpu(); @@ -101,6 +109,10 @@ void __init check_bugs(void) l1tf_select_mitigation(); + mds_select_mitigation(); + + arch_smt_update(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -207,6 +219,61 @@ static void x86_amd_ssb_disable(void) } #undef pr_fmt +#define pr_fmt(fmt) "MDS: " fmt + +/* Default mitigation for MDS-affected CPUs */ +static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL; +static bool mds_nosmt __ro_after_init = false; + +static const char * const mds_strings[] = { + [MDS_MITIGATION_OFF] = "Vulnerable", + [MDS_MITIGATION_FULL] = "Mitigation: Clear CPU buffers", + [MDS_MITIGATION_VMWERV] = "Vulnerable: Clear CPU buffers attempted, no microcode", +}; + +static void __init mds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) { + mds_mitigation = MDS_MITIGATION_OFF; + return; + } + + if (mds_mitigation == MDS_MITIGATION_FULL) { + if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) + mds_mitigation = MDS_MITIGATION_VMWERV; + + static_branch_enable(&mds_user_clear); + + if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && + (mds_nosmt || cpu_mitigations_auto_nosmt())) + cpu_smt_disable(false); + } + + pr_info("%s\n", mds_strings[mds_mitigation]); +} + +static int __init mds_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + mds_mitigation = MDS_MITIGATION_OFF; + else if (!strcmp(str, "full")) + mds_mitigation = MDS_MITIGATION_FULL; + else if (!strcmp(str, "full,nosmt")) { + mds_mitigation = MDS_MITIGATION_FULL; + mds_nosmt = true; + } + + return 0; +} +early_param("mds", mds_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = @@ -275,7 +342,7 @@ static const struct { const char *option; enum spectre_v2_user_cmd cmd; bool secure; -} v2_user_options[] __initdata = { +} v2_user_options[] __initconst = { { "auto", SPECTRE_V2_USER_CMD_AUTO, false }, { "off", SPECTRE_V2_USER_CMD_NONE, false }, { "on", SPECTRE_V2_USER_CMD_FORCE, true }, @@ -419,7 +486,7 @@ static const struct { const char *option; enum spectre_v2_mitigation_cmd cmd; bool secure; -} mitigation_options[] __initdata = { +} mitigation_options[] __initconst = { { "off", SPECTRE_V2_CMD_NONE, false }, { "on", SPECTRE_V2_CMD_FORCE, true }, { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, @@ -440,7 +507,8 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) char arg[20]; int ret, i; - if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") || + cpu_mitigations_off()) return SPECTRE_V2_CMD_NONE; ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); @@ -574,9 +642,6 @@ specv2_set_mode: /* Set up IBPB and STIBP depending on the general spectre V2 command */ spectre_v2_user_select_mitigation(cmd); - - /* Enable STIBP if appropriate */ - arch_smt_update(); } static void update_stibp_msr(void * __unused) @@ -610,6 +675,31 @@ static void update_indir_branch_cond(void) static_branch_disable(&switch_to_cond_stibp); } +#undef pr_fmt +#define pr_fmt(fmt) fmt + +/* Update the static key controlling the MDS CPU buffer clear in idle */ +static void update_mds_branch_idle(void) +{ + /* + * Enable the idle clearing if SMT is active on CPUs which are + * affected only by MSBDS and not any other MDS variant. + * + * The other variants cannot be mitigated when SMT is enabled, so + * clearing the buffers on idle just to prevent the Store Buffer + * repartitioning leak would be a window dressing exercise. + */ + if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY)) + return; + + if (sched_smt_active()) + static_branch_enable(&mds_idle_clear); + else + static_branch_disable(&mds_idle_clear); +} + +#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" + void arch_smt_update(void) { /* Enhanced IBRS implies STIBP. No update required. */ @@ -631,6 +721,17 @@ void arch_smt_update(void) break; } + switch (mds_mitigation) { + case MDS_MITIGATION_FULL: + case MDS_MITIGATION_VMWERV: + if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY)) + pr_warn_once(MDS_MSG_SMT); + update_mds_branch_idle(); + break; + case MDS_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -658,7 +759,7 @@ static const char * const ssb_strings[] = { static const struct { const char *option; enum ssb_mitigation_cmd cmd; -} ssb_mitigation_options[] __initdata = { +} ssb_mitigation_options[] __initconst = { { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ @@ -672,7 +773,8 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) char arg[20]; int ret, i; - if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) { + if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") || + cpu_mitigations_off()) { return SPEC_STORE_BYPASS_CMD_NONE; } else { ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", @@ -996,6 +1098,11 @@ static void __init l1tf_select_mitigation(void) if (!boot_cpu_has_bug(X86_BUG_L1TF)) return; + if (cpu_mitigations_off()) + l1tf_mitigation = L1TF_MITIGATION_OFF; + else if (cpu_mitigations_auto_nosmt()) + l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT; + override_cache_bits(&boot_cpu_data); switch (l1tf_mitigation) { @@ -1024,7 +1131,7 @@ static void __init l1tf_select_mitigation(void) pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n", half_pa); pr_info("However, doing so will make a part of your RAM unusable.\n"); - pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n"); + pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html might help you decide.\n"); return; } @@ -1057,6 +1164,7 @@ static int __init l1tf_cmdline(char *str) early_param("l1tf", l1tf_cmdline); #undef pr_fmt +#define pr_fmt(fmt) fmt #ifdef CONFIG_SYSFS @@ -1095,6 +1203,23 @@ static ssize_t l1tf_show_state(char *buf) } #endif +static ssize_t mds_show_state(char *buf) +{ + if (!hypervisor_is_type(X86_HYPER_NATIVE)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + mds_strings[mds_mitigation]); + } + + if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) { + return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : + sched_smt_active() ? "mitigated" : "disabled")); + } + + return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) @@ -1161,6 +1286,10 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) return l1tf_show_state(buf); break; + + case X86_BUG_MDS: + return mds_show_state(buf); + default: break; } @@ -1192,4 +1321,9 @@ ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *b { return cpu_show_common(dev, attr, buf, X86_BUG_L1TF); } + +ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_MDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cb28e98a0659..132a63dc5a76 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -948,61 +948,77 @@ 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_SALTWELL, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL_TABLET, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_BONNELL_MID, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL_MID, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_BONNELL, X86_FEATURE_ANY }, - { X86_VENDOR_CENTAUR, 5 }, - { X86_VENDOR_INTEL, 5 }, - { X86_VENDOR_NSC, 5 }, - { X86_VENDOR_ANY, 4 }, +#define NO_SPECULATION BIT(0) +#define NO_MELTDOWN BIT(1) +#define NO_SSB BIT(2) +#define NO_L1TF BIT(3) +#define NO_MDS BIT(4) +#define MSBDS_ONLY BIT(5) + +#define VULNWL(_vendor, _family, _model, _whitelist) \ + { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } + +#define VULNWL_INTEL(model, whitelist) \ + VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist) + +#define VULNWL_AMD(family, whitelist) \ + VULNWL(AMD, family, X86_MODEL_ANY, whitelist) + +#define VULNWL_HYGON(family, whitelist) \ + VULNWL(HYGON, family, X86_MODEL_ANY, whitelist) + +static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { + VULNWL(ANY, 4, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(CENTAUR, 5, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(INTEL, 5, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), + + /* Intel Family 6 */ + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION), + VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION), + VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION), + VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), + VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION), + + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY), + + VULNWL_INTEL(CORE_YONAH, NO_SSB), + + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY), + + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF), + VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF), + + /* AMD Family 0xf - 0x12 */ + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + + /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS), {} }; -static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { - { X86_VENDOR_AMD }, - { X86_VENDOR_HYGON }, - {} -}; - -/* Only list CPUs which speculate but are non susceptible to SSB */ -static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_X }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_MID }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, - { X86_VENDOR_AMD, 0x12, }, - { X86_VENDOR_AMD, 0x11, }, - { X86_VENDOR_AMD, 0x10, }, - { X86_VENDOR_AMD, 0xf, }, - {} -}; +static bool __init cpu_matches(unsigned long which) +{ + const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist); -static const __initconst struct x86_cpu_id cpu_no_l1tf[] = { - /* in addition to cpu_no_speculation */ - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_X }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_MID }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT_MID }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_X }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_PLUS }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, - {} -}; + return m && !!(m->driver_data & which); +} static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; - if (x86_match_cpu(cpu_no_speculation)) + if (cpu_matches(NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); @@ -1011,15 +1027,20 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); - if (!x86_match_cpu(cpu_no_spec_store_bypass) && - !(ia32_cap & ARCH_CAP_SSB_NO) && + if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); if (ia32_cap & ARCH_CAP_IBRS_ALL) setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); - if (x86_match_cpu(cpu_no_meltdown)) + if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { + setup_force_cpu_bug(X86_BUG_MDS); + if (cpu_matches(MSBDS_ONLY)) + setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); + } + + if (cpu_matches(NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ @@ -1028,7 +1049,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - if (x86_match_cpu(cpu_no_l1tf)) + if (cpu_matches(NO_L1TF)) return; setup_force_cpu_bug(X86_BUG_L1TF); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index d12226f60168..1d9b8aaea06c 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -124,7 +124,7 @@ static void set_cx86_reorder(void) setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ /* Load/Store Serialize to mem access disable (=reorder it) */ - setCx86_old(CX86_PCR0, getCx86_old(CX86_PCR0) & ~0x80); + setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80); /* set load/store serialize from 1GB to 4GB */ ccr3 |= 0xe0; setCx86(CX86_CCR3, ccr3); @@ -135,11 +135,11 @@ static void set_cx86_memwb(void) pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n"); /* CCR2 bit 2: unlock NW bit */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04); /* set 'Not Write-through' */ write_cr0(read_cr0() | X86_CR0_NW); /* CCR2 bit 2: lock NW bit and set WT1 */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x14); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14); } /* @@ -153,14 +153,14 @@ static void geode_configure(void) local_irq_save(flags); /* Suspend on halt power saving and enable #SUSP pin */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x88); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88); ccr3 = getCx86(CX86_CCR3); setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ /* FPU fast, DTE cache, Mem bypass */ - setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x38); + setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38); setCx86(CX86_CCR3, ccr3); /* disable MAPEN */ set_cx86_memwb(); @@ -296,7 +296,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* GXm supports extended cpuid levels 'ala' AMD */ if (c->cpuid_level == 2) { /* Enable cxMMX extensions (GX1 Datasheet 54) */ - setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7) | 1); + setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1); /* * GXm : 0x30 ... 0x5f GXm datasheet 51 @@ -319,7 +319,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) if (dir1 > 7) { dir0_msn++; /* M II */ /* Enable MMX extensions (App note 108) */ - setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1); + setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1); } else { /* A 6x86MX - it has the bug. */ set_cpu_bug(c, X86_BUG_COMA); diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index dc3e26e905a3..65201e180fe0 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -165,6 +165,11 @@ static struct severity { SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), KERNEL ), + MCESEV( + PANIC, "Instruction fetch error in kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), + KERNEL + ), #endif MCESEV( PANIC, "Action required: unknown MCACOD", diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dfd3aca82c61..fb32925a2e62 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -905,6 +905,8 @@ int __init hpet_enable(void) return 0; hpet_set_mapping(); + if (!hpet_virt_address) + return 0; /* * Read the period and check for a sane value: diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 34a5c1715148..2882fe1d2a78 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -357,6 +357,7 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, #endif default: WARN_ON_ONCE(1); + return -EINVAL; } /* diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 4ba75afba527..f4b954ff5b89 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) unsigned long *sara = stack_addr(regs); ri->ret_addr = (kprobe_opcode_t *) *sara; + ri->fp = sara; /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; @@ -748,26 +749,48 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); +static struct kprobe kretprobe_kprobe = { + .addr = (void *)kretprobe_trampoline, +}; + /* * Called from kretprobe_trampoline */ static __used void *trampoline_handler(struct pt_regs *regs) { + struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; kprobe_opcode_t *correct_ret_addr = NULL; + void *frame_pointer; + bool skipped = false; + + preempt_disable(); + + /* + * Set a dummy kprobe for avoiding kretprobe recursion. + * Since kretprobe never run in kprobe handler, kprobe must not + * be running at this point. + */ + kcb = get_kprobe_ctlblk(); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; + /* On x86-64, we use pt_regs->sp for return address holder. */ + frame_pointer = ®s->sp; #else regs->cs = __KERNEL_CS | get_kernel_rpl(); regs->gs = 0; + /* On x86-32, we use pt_regs->flags for return address holder. */ + frame_pointer = ®s->flags; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; @@ -789,8 +812,25 @@ static __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + /* + * Return probes must be pushed on this hash list correct + * order (same as return order) so that it can be poped + * correctly. However, if we find it is pushed it incorrect + * order, this means we find a function which should not be + * probed, because the wrong order entry is pushed on the + * path of processing other kretprobe itself. + */ + if (ri->fp != frame_pointer) { + if (!skipped) + pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); + skipped = true; + continue; + } orig_ret_address = (unsigned long)ri->ret_addr; + if (skipped) + pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", + ri->rp->kp.addr); if (orig_ret_address != trampoline_address) /* @@ -808,14 +848,15 @@ static __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + if (ri->fp != frame_pointer) + continue; orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { __this_cpu_write(current_kprobe, &ri->rp->kp); - get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, NULL); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); } recycle_rp_inst(ri, &empty_rp); @@ -831,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 3482460d984d..1bfe5c6e6cfe 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -598,8 +598,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) mpf_base = base; mpf_found = true; - pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n", - base, base + sizeof(*mpf) - 1, mpf); + pr_info("found SMP MP-table at [mem %#010lx-%#010lx]\n", + base, base + sizeof(*mpf) - 1); memblock_reserve(base, sizeof(*mpf)); if (mpf->physptr) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 18bc9b51ac9b..086cf1d1d71d 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -34,6 +34,7 @@ #include <asm/x86_init.h> #include <asm/reboot.h> #include <asm/cache.h> +#include <asm/nospec-branch.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -533,6 +534,9 @@ nmi_restart: write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) goto nmi_restart; + + if (user_mode(regs)) + mds_user_clear_cpu_buffers(); } NOKPROBE_SYMBOL(do_nmi); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 90ae0ca51083..9db049f06f2f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -414,6 +414,8 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, u64 msr = x86_spec_ctrl_base; bool updmsr = false; + lockdep_assert_irqs_disabled(); + /* * If TIF_SSBD is different, select the proper mitigation * method. Note that if SSBD mitigation is disabled or permanentely @@ -465,10 +467,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) void speculation_ctrl_update(unsigned long tif) { + unsigned long flags; + /* Forced update. Make sure all relevant TIF flags are different */ - preempt_disable(); + local_irq_save(flags); __speculation_ctrl_update(~tif, tif); - preempt_enable(); + local_irq_restore(flags); } /* Called from seccomp/prctl update */ diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 725624b6c0c0..8fd3cedd9acc 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -81,6 +81,19 @@ static int __init set_bios_reboot(const struct dmi_system_id *d) return 0; } +/* + * Some machines don't handle the default ACPI reboot method and + * require the EFI reboot method: + */ +static int __init set_efi_reboot(const struct dmi_system_id *d) +{ + if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) { + reboot_type = BOOT_EFI; + pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident); + } + return 0; +} + void __noreturn machine_real_restart(unsigned int type) { local_irq_disable(); @@ -166,6 +179,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"), }, }, + { /* Handle reboot issue on Acer TravelMate X514-51T */ + .callback = set_efi_reboot, + .ident = "Acer TravelMate X514-51T", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"), + }, + }, /* Apple */ { /* Handle problems with rebooting on Apple MacBook5 */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 9b7c4ca8f0a7..85fe1870f873 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -58,6 +58,7 @@ #include <asm/alternative.h> #include <asm/fpu/xstate.h> #include <asm/trace/mpx.h> +#include <asm/nospec-branch.h> #include <asm/mpx.h> #include <asm/vm86.h> #include <asm/umip.h> @@ -366,6 +367,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) regs->ip = (unsigned long)general_protection; regs->sp = (unsigned long)&gpregs->orig_ax; + /* + * This situation can be triggered by userspace via + * modify_ldt(2) and the return does not take the regular + * user space exit, so a CPU buffer clear is required when + * MDS mitigation is enabled. + */ + mds_user_clear_cpu_buffers(); return; } #endif diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index ee3b5c7d662e..c45214c44e61 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -362,7 +362,7 @@ SECTIONS .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; *(.bss..page_aligned) - *(.bss) + *(BSS_MAIN) BSS_DECRYPTED . = ALIGN(PAGE_SIZE); __bss_stop = .; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c07958b59f50..39501e7afdb4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -410,7 +410,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | - F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP); + F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | + F(MD_CLEAR); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c338984c850d..81be2165821f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2575,15 +2575,13 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU * supports long mode. */ - cr4 = ctxt->ops->get_cr(ctxt, 4); if (emulator_has_longmode(ctxt)) { struct desc_struct cs_desc; /* Zero CR4.PCIDE before CR0.PG. */ - if (cr4 & X86_CR4_PCIDE) { + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PCIDE) ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); - cr4 &= ~X86_CR4_PCIDE; - } /* A 32-bit code segment is required to clear EFER.LMA. */ memset(&cs_desc, 0, sizeof(cs_desc)); @@ -2597,13 +2595,16 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) if (cr0 & X86_CR0_PE) ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); - /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */ - if (cr4 & X86_CR4_PAE) - ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); + if (emulator_has_longmode(ctxt)) { + /* Clear CR4.PAE before clearing EFER.LME. */ + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PAE) + ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); - /* And finally go back to 32-bit mode. */ - efer = 0; - ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + /* And finally go back to 32-bit mode. */ + efer = 0; + ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + } smbase = ctxt->ops->get_smbase(ctxt); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 89d20ed1d2e8..371c669696d7 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -526,7 +526,9 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, new_config.enable = 0; stimer->config.as_uint64 = new_config.as_uint64; - stimer_mark_pending(stimer, false); + if (stimer->config.enable) + stimer_mark_pending(stimer, false); + return 0; } @@ -542,7 +544,10 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, stimer->config.enable = 0; else if (stimer->config.auto_enable) stimer->config.enable = 1; - stimer_mark_pending(stimer, false); + + if (stimer->config.enable) + stimer_mark_pending(stimer, false); + return 0; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4b6c2da7265c..235687f3388f 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -70,7 +70,6 @@ #define APIC_BROADCAST 0xFF #define X2APIC_BROADCAST 0xFFFFFFFFul -static bool lapic_timer_advance_adjust_done = false; #define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 @@ -138,6 +137,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, if (offset <= max_apic_id) { u8 cluster_size = min(max_apic_id - offset + 1, 16U); + offset = array_index_nospec(offset, map->max_apic_id + 1); *cluster = &map->phys_map[offset]; *mask = dest_id & (0xffff >> (16 - cluster_size)); } else { @@ -900,7 +900,8 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm, if (irq->dest_id > map->max_apic_id) { *bitmap = 0; } else { - *dst = &map->phys_map[irq->dest_id]; + u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1); + *dst = &map->phys_map[dest_id]; *bitmap = 1; } return true; @@ -1479,14 +1480,32 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) return false; } +static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles) +{ + u64 timer_advance_ns = vcpu->arch.apic->lapic_timer.timer_advance_ns; + + /* + * If the guest TSC is running at a different ratio than the host, then + * convert the delay to nanoseconds to achieve an accurate delay. Note + * that __delay() uses delay_tsc whenever the hardware has TSC, thus + * always for VMX enabled hardware. + */ + if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) { + __delay(min(guest_cycles, + nsec_to_cycles(vcpu, timer_advance_ns))); + } else { + u64 delay_ns = guest_cycles * 1000000ULL; + do_div(delay_ns, vcpu->arch.virtual_tsc_khz); + ndelay(min_t(u32, delay_ns, timer_advance_ns)); + } +} + void wait_lapic_expire(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; + u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns; u64 guest_tsc, tsc_deadline, ns; - if (!lapic_in_kernel(vcpu)) - return; - if (apic->lapic_timer.expired_tscdeadline == 0) return; @@ -1498,33 +1517,37 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); - /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ if (guest_tsc < tsc_deadline) - __delay(min(tsc_deadline - guest_tsc, - nsec_to_cycles(vcpu, lapic_timer_advance_ns))); + __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - if (!lapic_timer_advance_adjust_done) { + if (!apic->lapic_timer.timer_advance_adjust_done) { /* too early */ if (guest_tsc < tsc_deadline) { ns = (tsc_deadline - guest_tsc) * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - lapic_timer_advance_ns -= min((unsigned int)ns, - lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns -= min((u32)ns, + timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); } else { /* too late */ ns = (guest_tsc - tsc_deadline) * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - lapic_timer_advance_ns += min((unsigned int)ns, - lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns += min((u32)ns, + timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); } if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE) - lapic_timer_advance_adjust_done = true; + apic->lapic_timer.timer_advance_adjust_done = true; + if (unlikely(timer_advance_ns > 5000)) { + timer_advance_ns = 0; + apic->lapic_timer.timer_advance_adjust_done = true; + } + apic->lapic_timer.timer_advance_ns = timer_advance_ns; } } static void start_sw_tscdeadline(struct kvm_lapic *apic) { - u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; + struct kvm_timer *ktimer = &apic->lapic_timer; + u64 guest_tsc, tscdeadline = ktimer->tscdeadline; u64 ns = 0; ktime_t expire; struct kvm_vcpu *vcpu = apic->vcpu; @@ -1539,13 +1562,15 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) now = ktime_get(); guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); - if (likely(tscdeadline > guest_tsc)) { - ns = (tscdeadline - guest_tsc) * 1000000ULL; - do_div(ns, this_tsc_khz); + + ns = (tscdeadline - guest_tsc) * 1000000ULL; + do_div(ns, this_tsc_khz); + + if (likely(tscdeadline > guest_tsc) && + likely(ns > apic->lapic_timer.timer_advance_ns)) { expire = ktime_add_ns(now, ns); - expire = ktime_sub_ns(expire, lapic_timer_advance_ns); - hrtimer_start(&apic->lapic_timer.timer, - expire, HRTIMER_MODE_ABS_PINNED); + expire = ktime_sub_ns(expire, ktimer->timer_advance_ns); + hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_PINNED); } else apic_timer_expired(apic); @@ -2252,7 +2277,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } -int kvm_create_lapic(struct kvm_vcpu *vcpu) +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) { struct kvm_lapic *apic; @@ -2276,6 +2301,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); apic->lapic_timer.timer.function = apic_timer_fn; + if (timer_advance_ns == -1) { + apic->lapic_timer.timer_advance_ns = 1000; + apic->lapic_timer.timer_advance_adjust_done = false; + } else { + apic->lapic_timer.timer_advance_ns = timer_advance_ns; + apic->lapic_timer.timer_advance_adjust_done = true; + } + /* * APIC is created enabled. This will prevent kvm_lapic_set_base from diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index ff6ef9c3d760..d6d049ba3045 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -31,8 +31,10 @@ struct kvm_timer { u32 timer_mode_mask; u64 tscdeadline; u64 expired_tscdeadline; + u32 timer_advance_ns; atomic_t pending; /* accumulated triggered timers */ bool hv_timer_in_use; + bool timer_advance_adjust_done; }; struct kvm_lapic { @@ -62,7 +64,7 @@ struct kvm_lapic { struct dest_map; -int kvm_create_lapic(struct kvm_vcpu *vcpu); +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns); void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 9ab33cab9486..77dbb57412cc 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4915,11 +4915,15 @@ static union kvm_mmu_role kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, bool execonly) { - union kvm_mmu_role role; + union kvm_mmu_role role = {0}; + union kvm_mmu_page_role root_base = vcpu->arch.root_mmu.mmu_role.base; - /* Base role is inherited from root_mmu */ - role.base.word = vcpu->arch.root_mmu.mmu_role.base.word; - role.ext = kvm_calc_mmu_role_ext(vcpu); + /* Legacy paging and SMM flags are inherited from root_mmu */ + role.base.smm = root_base.smm; + role.base.nxe = root_base.nxe; + role.base.cr0_wp = root_base.cr0_wp; + role.base.smep_andnot_wp = root_base.smep_andnot_wp; + role.base.smap_andnot_wp = root_base.smap_andnot_wp; role.base.level = PT64_ROOT_4LEVEL; role.base.direct = false; @@ -4927,6 +4931,7 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, role.base.guest_mode = true; role.base.access = ACC_ALL; + role.ext = kvm_calc_mmu_role_ext(vcpu); role.ext.execonly = execonly; return role; @@ -5390,10 +5395,12 @@ emulate: * This can happen if a guest gets a page-fault on data access but the HW * table walker is not able to read the instruction page (e.g instruction * page is not present in memory). In those cases we simply restart the - * guest. + * guest, with the exception of AMD Erratum 1096 which is unrecoverable. */ - if (unlikely(insn && !insn_len)) - return 1; + if (unlikely(insn && !insn_len)) { + if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu)) + return 1; + } er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a9b8e38d78ad..2a07e43ee666 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2687,6 +2687,7 @@ static int npf_interception(struct vcpu_svm *svm) static int db_interception(struct vcpu_svm *svm) { struct kvm_run *kvm_run = svm->vcpu.run; + struct kvm_vcpu *vcpu = &svm->vcpu; if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && @@ -2697,6 +2698,8 @@ static int db_interception(struct vcpu_svm *svm) if (svm->nmi_singlestep) { disable_nmi_singlestep(svm); + /* Make sure we check for pending NMIs upon entry */ + kvm_make_request(KVM_REQ_EVENT, vcpu); } if (svm->vcpu.guest_debug & @@ -4512,14 +4515,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) kvm_lapic_reg_write(apic, APIC_ICR, icrl); break; case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: { + int i; + struct kvm_vcpu *vcpu; + struct kvm *kvm = svm->vcpu.kvm; struct kvm_lapic *apic = svm->vcpu.arch.apic; /* - * Update ICR high and low, then emulate sending IPI, - * which is handled when writing APIC_ICR. + * At this point, we expect that the AVIC HW has already + * set the appropriate IRR bits on the valid target + * vcpus. So, we just need to kick the appropriate vcpu. */ - kvm_lapic_reg_write(apic, APIC_ICR2, icrh); - kvm_lapic_reg_write(apic, APIC_ICR, icrl); + kvm_for_each_vcpu(i, vcpu, kvm) { + bool m = kvm_apic_match_dest(vcpu, apic, + icrl & KVM_APIC_SHORT_MASK, + GET_APIC_DEST_FIELD(icrh), + icrl & KVM_APIC_DEST_MASK); + + if (m && !avic_vcpu_is_running(vcpu)) + kvm_vcpu_wake_up(vcpu); + } break; } case AVIC_IPI_FAILURE_INVALID_TARGET: @@ -5620,6 +5634,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); + kvm_load_guest_xcr0(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -5765,6 +5780,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(&svm->vcpu); + kvm_put_guest_xcr0(vcpu); stgi(); /* Any pending NMI will happen here */ @@ -6799,7 +6815,8 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) struct page **src_p, **dst_p; struct kvm_sev_dbg debug; unsigned long n; - int ret, size; + unsigned int size; + int ret; if (!sev_guest(kvm)) return -ENOTTY; @@ -6807,6 +6824,11 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) return -EFAULT; + if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr) + return -EINVAL; + if (!debug.dst_uaddr) + return -EINVAL; + vaddr = debug.src_uaddr; size = debug.len; vaddr_end = vaddr + size; @@ -6857,8 +6879,8 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) dst_vaddr, len, &argp->error); - sev_unpin_memory(kvm, src_p, 1); - sev_unpin_memory(kvm, dst_p, 1); + sev_unpin_memory(kvm, src_p, n); + sev_unpin_memory(kvm, dst_p, n); if (ret) goto err; @@ -7098,6 +7120,36 @@ static int nested_enable_evmcs(struct kvm_vcpu *vcpu, return -ENODEV; } +static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) +{ + bool is_user, smap; + + is_user = svm_get_cpl(vcpu) == 3; + smap = !kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); + + /* + * Detect and workaround Errata 1096 Fam_17h_00_0Fh + * + * In non SEV guest, hypervisor will be able to read the guest + * memory to decode the instruction pointer when insn_len is zero + * so we return true to indicate that decoding is possible. + * + * But in the SEV guest, the guest memory is encrypted with the + * guest specific key and hypervisor will not be able to decode the + * instruction pointer so we will not able to workaround it. Lets + * print the error and request to kill the guest. + */ + if (is_user && smap) { + if (!sev_guest(vcpu->kvm)) + return true; + + pr_err_ratelimited("KVM: Guest triggered AMD Erratum 1096\n"); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + } + + return false; +} + static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -7231,6 +7283,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .nested_enable_evmcs = nested_enable_evmcs, .nested_get_evmcs_version = nested_get_evmcs_version, + + .need_emulation_on_page_fault = svm_need_emulation_on_page_fault, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 6432d08c7de7..4d47a2631d1f 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -438,13 +438,13 @@ TRACE_EVENT(kvm_apic_ipi, ); TRACE_EVENT(kvm_apic_accept_irq, - TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec), + TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec), TP_ARGS(apicid, dm, tm, vec), TP_STRUCT__entry( __field( __u32, apicid ) __field( __u16, dm ) - __field( __u8, tm ) + __field( __u16, tm ) __field( __u8, vec ) ), diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f90b3a948291..2a16bd887729 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2793,7 +2793,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) [fail]"i"(offsetof(struct vcpu_vmx, fail)), [host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)), [wordsize]"i"(sizeof(ulong)) - : "rax", "cc", "memory" + : "cc", "memory" ); preempt_enable(); @@ -3790,8 +3790,18 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW)); nested_ept_uninit_mmu_context(vcpu); - vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + + /* + * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3 + * points to shadow pages! Fortunately we only get here after a WARN_ON + * if EPT is disabled, so a VMabort is perfectly fine. + */ + if (enable_ept) { + vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + } else { + nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED); + } /* * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs @@ -5407,7 +5417,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return ret; /* Empty 'VMXON' state is permitted */ - if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12)) + if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) return 0; if (kvm_state->vmx.vmcs_pa != -1ull) { @@ -5451,7 +5461,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmcs12->vmcs_link_pointer != -1ull) { struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); - if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12)) + if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12)) return -EINVAL; if (copy_from_user(shadow_vmcs12, @@ -5739,6 +5749,14 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) { int i; + /* + * Without EPT it is not possible to restore L1's CR3 and PDPTR on + * VMfail, because they are not available in vmcs01. Just always + * use hardware checks. + */ + if (!enable_ept) + nested_early_check = 1; + if (!cpu_has_vmx_shadow_vmcs()) enable_shadow_vmcs = 0; if (enable_shadow_vmcs) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a0a770816429..df6e325b288b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6356,8 +6356,11 @@ static void __vmx_vcpu_run(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) evmcs_rsp = static_branch_unlikely(&enable_evmcs) ? (unsigned long)¤t_evmcs->host_rsp : 0; + /* L1D Flush includes CPU buffer clear to mitigate MDS */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); + else if (static_branch_unlikely(&mds_user_clear)) + mds_clear_cpu_buffers(); asm( /* Store host registers */ @@ -6465,7 +6468,7 @@ static void __vmx_vcpu_run(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) "xor %%edi, %%edi \n\t" "xor %%ebp, %%ebp \n\t" "pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t" - : ASM_CALL_CONSTRAINT + : ASM_CALL_CONSTRAINT, "=S"((int){0}) : "c"(vmx), "d"((unsigned long)HOST_RSP), "S"(evmcs_rsp), [launched]"i"(offsetof(struct vcpu_vmx, __launched)), [fail]"i"(offsetof(struct vcpu_vmx, fail)), @@ -6548,6 +6551,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); + kvm_load_guest_xcr0(vcpu); + if (static_cpu_has(X86_FEATURE_PKU) && kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && vcpu->arch.pkru != vmx->host_pkru) @@ -6635,6 +6640,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vmx->host_pkru); } + kvm_put_guest_xcr0(vcpu); + vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; @@ -6793,8 +6800,8 @@ free_partial_vcpu: return ERR_PTR(err); } -#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n" -#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n" +#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" +#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" static int vmx_vm_init(struct kvm *kvm) { @@ -7129,6 +7136,7 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) { struct vcpu_vmx *vmx; u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; + struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer; if (kvm_mwait_in_guest(vcpu->kvm)) return -EOPNOTSUPP; @@ -7137,7 +7145,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) tscl = rdtsc(); guest_tscl = kvm_read_l1_tsc(vcpu, tscl); delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; - lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns); + lapic_timer_advance_cycles = nsec_to_cycles(vcpu, + ktimer->timer_advance_ns); if (delta_tsc > lapic_timer_advance_cycles) delta_tsc -= lapic_timer_advance_cycles; @@ -7522,6 +7531,11 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } +static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) +{ + return 0; +} + static __init int hardware_setup(void) { unsigned long host_bndcfgs; @@ -7824,6 +7838,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .set_nested_state = NULL, .get_vmcs12_pages = NULL, .nested_enable_evmcs = NULL, + .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, }; static void vmx_cleanup_l1d_flush(void) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 1abae731c3e4..b26cb680ba38 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -444,7 +444,8 @@ static inline u32 vmx_vmentry_ctrl(void) { u32 vmentry_ctrl = vmcs_config.vmentry_ctrl; if (pt_mode == PT_MODE_SYSTEM) - vmentry_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); + vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | + VM_ENTRY_LOAD_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ return vmentry_ctrl & ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER); @@ -454,9 +455,10 @@ static inline u32 vmx_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; if (pt_mode == PT_MODE_SYSTEM) - vmexit_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); + vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | + VM_EXIT_CLEAR_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ - return vmcs_config.vmexit_ctrl & + return vmexit_ctrl & ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7ee802a92bc8..3eeb7183fc09 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -136,10 +136,14 @@ EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio); static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); -/* lapic timer advance (tscdeadline mode only) in nanoseconds */ -unsigned int __read_mostly lapic_timer_advance_ns = 1000; +/* + * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables + * adaptive tuning starting from default advancment of 1000ns. '0' disables + * advancement entirely. Any other value is used as-is and disables adaptive + * tuning, i.e. allows priveleged userspace to set an exact advancement time. + */ +static int __read_mostly lapic_timer_advance_ns = -1; module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); -EXPORT_SYMBOL_GPL(lapic_timer_advance_ns); static bool __read_mostly vector_hashing = true; module_param(vector_hashing, bool, S_IRUGO); @@ -800,7 +804,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_GPL(kvm_lmsw); -static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) { if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && !vcpu->guest_xcr0_loaded) { @@ -810,8 +814,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 1; } } +EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); -static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) { if (vcpu->guest_xcr0_loaded) { if (vcpu->arch.xcr0 != host_xcr0) @@ -819,6 +824,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 0; } } +EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -1125,7 +1131,7 @@ 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, + MSR_IA32_SPEC_CTRL, MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, @@ -1158,6 +1164,7 @@ static u32 emulated_msrs[] = { MSR_IA32_TSC_ADJUST, MSR_IA32_TSCDEADLINE, + MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, @@ -6533,6 +6540,12 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); +static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pio.count = 0; + return 1; +} + static int complete_fast_pio_out(struct kvm_vcpu *vcpu) { vcpu->arch.pio.count = 0; @@ -6549,12 +6562,23 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, size, port, &val, 1); + if (ret) + return ret; - if (!ret) { + /* + * Workaround userspace that relies on old KVM behavior of %rip being + * incremented prior to exiting to userspace to handle "OUT 0x7e". + */ + if (port == 0x7e && + kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) { + vcpu->arch.complete_userspace_io = + complete_fast_pio_out_port_0x7e; + kvm_skip_emulated_instruction(vcpu); + } else { vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_out; } - return ret; + return 0; } static int complete_fast_pio_in(struct kvm_vcpu *vcpu) @@ -7856,15 +7880,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - kvm_load_guest_xcr0(vcpu); - if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_x86_ops->request_immediate_exit(vcpu); } trace_kvm_entry(vcpu->vcpu_id); - if (lapic_timer_advance_ns) + if (lapic_in_kernel(vcpu) && + vcpu->arch.apic->lapic_timer.timer_advance_ns) wait_lapic_expire(vcpu); guest_enter_irqoff(); @@ -7910,8 +7933,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_put_guest_xcr0(vcpu); - kvm_before_interrupt(vcpu); kvm_x86_ops->handle_external_intr(vcpu); kvm_after_interrupt(vcpu); @@ -9054,7 +9075,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_pio_data; if (irqchip_in_kernel(vcpu->kvm)) { - r = kvm_create_lapic(vcpu); + r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); if (r < 0) goto fail_mmu_destroy; } else diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 20ede17202bf..b457160dc7ba 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -294,8 +294,6 @@ extern u64 kvm_supported_xcr0(void); extern unsigned int min_timer_period_us; -extern unsigned int lapic_timer_advance_ns; - extern bool enable_vmware_backdoor; extern struct static_key kvm_no_apic_vcpu; @@ -347,4 +345,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) __this_cpu_write(current_vcpu, NULL); } +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index e3cdc85ce5b6..84304626b1cb 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -259,7 +259,8 @@ static void note_wx(struct pg_state *st) #endif /* Account the WX pages */ st->wx_pages += npages; - WARN_ONCE(1, "x86/mm: Found insecure W+X mapping at address %pS\n", + WARN_ONCE(__supported_pte_mask & _PAGE_NX, + "x86/mm: Found insecure W+X mapping at address %pS\n", (void *)st->start_address); } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index f905a2371080..8dacdb96899e 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -5,6 +5,7 @@ #include <linux/memblock.h> #include <linux/swapfile.h> #include <linux/swapops.h> +#include <linux/kmemleak.h> #include <asm/set_memory.h> #include <asm/e820/api.h> @@ -766,6 +767,11 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end) if (debug_pagealloc_enabled()) { pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n", begin, end - 1); + /* + * Inform kmemleak about the hole in the memory since the + * corresponding pages will be unmapped. + */ + kmemleak_free_part((void *)begin, end - begin); set_memory_np(begin, (end - begin) >> PAGE_SHIFT); } else { /* diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 5378d10f1d31..3b76fe954978 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -825,7 +825,7 @@ void __init __early_set_fixmap(enum fixed_addresses idx, pte = early_ioremap_pte(addr); /* Sanitize 'prot' against any unsupported bits: */ - pgprot_val(flags) &= __default_kernel_pte_mask; + pgprot_val(flags) &= __supported_pte_mask; if (pgprot_val(flags)) set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 3f452ffed7e9..d669c5e797e0 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -94,7 +94,7 @@ void __init kernel_randomize_memory(void) if (!kaslr_memory_enabled()) return; - kaslr_regions[0].size_tb = 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT); + kaslr_regions[0].size_tb = 1 << (MAX_PHYSMEM_BITS - TB_SHIFT); kaslr_regions[1].size_tb = VMALLOC_SIZE_TB; /* diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index db3165714521..dc726e07d8ba 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -230,7 +230,7 @@ bool mmap_address_hint_valid(unsigned long addr, unsigned long len) /* Can we access it for direct reading/writing? Must be RAM: */ int valid_phys_addr_range(phys_addr_t addr, size_t count) { - return addr + count <= __pa(high_memory); + return addr + count - 1 <= __pa(high_memory - 1); } /* Can we access it through mmap? Must be a valid physical address: */ diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 4fee5c3003ed..5890f09bfc19 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -35,6 +35,7 @@ #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/uaccess.h> +#include <linux/cpu.h> #include <asm/cpufeature.h> #include <asm/hypervisor.h> @@ -115,7 +116,8 @@ void __init pti_check_boottime_disable(void) } } - if (cmdline_find_option_bool(boot_command_line, "nopti")) { + if (cmdline_find_option_bool(boot_command_line, "nopti") || + cpu_mitigations_off()) { pti_mode = PTI_FORCE_OFF; pti_print_if_insecure("disabled on command line."); return; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 999d6d8f0bef..9a49335e717a 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -731,7 +731,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, { int cpu; - struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = { + struct flush_tlb_info info = { .mm = mm, .stride_shift = stride_shift, .freed_tables = freed_tables, diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index d10105825d57..47d097946872 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -20,8 +20,6 @@ void __init set_real_mode_mem(phys_addr_t mem, size_t size) void *base = __va(mem); real_mode_header = (struct real_mode_header *) base; - printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", - base, (unsigned long long)mem, size); } void __init reserve_real_mode(void) diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index f7dd895b2353..0c14018d1c26 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -187,15 +187,18 @@ struct thread_struct { /* Clearing a0 terminates the backtrace. */ #define start_thread(regs, new_pc, new_sp) \ - memset(regs, 0, sizeof(*regs)); \ - regs->pc = new_pc; \ - regs->ps = USER_PS_VALUE; \ - regs->areg[1] = new_sp; \ - regs->areg[0] = 0; \ - regs->wmask = 1; \ - regs->depc = 0; \ - regs->windowbase = 0; \ - regs->windowstart = 1; + do { \ + memset((regs), 0, sizeof(*(regs))); \ + (regs)->pc = (new_pc); \ + (regs)->ps = USER_PS_VALUE; \ + (regs)->areg[1] = (new_sp); \ + (regs)->areg[0] = 0; \ + (regs)->wmask = 1; \ + (regs)->depc = 0; \ + (regs)->windowbase = 0; \ + (regs)->windowstart = 1; \ + (regs)->syscall = NO_SYSCALL; \ + } while (0) /* Forward declaration */ struct task_struct; |