diff options
Diffstat (limited to 'arch')
79 files changed, 465 insertions, 441 deletions
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi index da6d70f09ef1..3175266ede64 100644 --- a/arch/arm/boot/dts/bcm-nsp.dtsi +++ b/arch/arm/boot/dts/bcm-nsp.dtsi @@ -200,7 +200,7 @@ status = "disabled"; }; - dma@20000 { + dma: dma@20000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x20000 0x1000>; interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>, @@ -215,6 +215,8 @@ clocks = <&iprocslow>; clock-names = "apb_pclk"; #dma-cells = <1>; + dma-coherent; + status = "disabled"; }; sdio: sdhci@21000 { @@ -257,10 +259,10 @@ status = "disabled"; }; - mailbox: mailbox@25000 { + mailbox: mailbox@25c00 { compatible = "brcm,iproc-fa2-mbox"; - reg = <0x25000 0x445>; - interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>; + reg = <0x25c00 0x400>; + interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>; #mbox-cells = <1>; brcm,rx-status-len = <32>; brcm,use-bcm-hdr; diff --git a/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts b/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts index 334325390aed..29bbecd36f65 100644 --- a/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts +++ b/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts @@ -17,6 +17,7 @@ }; memory { + device_type = "memory"; reg = <0x00000000 0x08000000 0x88000000 0x18000000>; }; diff --git a/arch/arm/boot/dts/bcm958522er.dts b/arch/arm/boot/dts/bcm958522er.dts index 8c388eb8a08f..7be4c4e628e0 100644 --- a/arch/arm/boot/dts/bcm958522er.dts +++ b/arch/arm/boot/dts/bcm958522er.dts @@ -58,6 +58,10 @@ /* USB 3 support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958525er.dts b/arch/arm/boot/dts/bcm958525er.dts index c339771bb22e..e58ed7e95346 100644 --- a/arch/arm/boot/dts/bcm958525er.dts +++ b/arch/arm/boot/dts/bcm958525er.dts @@ -58,6 +58,10 @@ /* USB 3 support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958525xmc.dts b/arch/arm/boot/dts/bcm958525xmc.dts index 1c72ec8288de..716da62f5788 100644 --- a/arch/arm/boot/dts/bcm958525xmc.dts +++ b/arch/arm/boot/dts/bcm958525xmc.dts @@ -58,6 +58,10 @@ /* XHCI support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958622hr.dts b/arch/arm/boot/dts/bcm958622hr.dts index 96a021cebd97..a49c2fd21f4a 100644 --- a/arch/arm/boot/dts/bcm958622hr.dts +++ b/arch/arm/boot/dts/bcm958622hr.dts @@ -58,6 +58,10 @@ /* USB 3 and SLIC support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts index b2c7f21d471e..dd6dff6452b8 100644 --- a/arch/arm/boot/dts/bcm958623hr.dts +++ b/arch/arm/boot/dts/bcm958623hr.dts @@ -58,6 +58,10 @@ /* USB 3 and SLIC support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts index 536fb24f38bb..a71371b4065e 100644 --- a/arch/arm/boot/dts/bcm958625hr.dts +++ b/arch/arm/boot/dts/bcm958625hr.dts @@ -69,6 +69,10 @@ status = "okay"; }; +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958625k.dts b/arch/arm/boot/dts/bcm958625k.dts index 3fcca12d83c2..7b84b54436ed 100644 --- a/arch/arm/boot/dts/bcm958625k.dts +++ b/arch/arm/boot/dts/bcm958625k.dts @@ -48,6 +48,10 @@ }; }; +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi index f05e91841202..53a25fba34f6 100644 --- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi +++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi @@ -232,13 +232,6 @@ status = "okay"; }; -&wdog1 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_wdog>; - fsl,ext-reset-output; - status = "okay"; -}; - &iomuxc { pinctrl-0 = <&pinctrl_reset_out &pinctrl_gpio>; @@ -409,10 +402,4 @@ MX6UL_PAD_NAND_DATA03__USDHC2_DATA3 0x170f9 >; }; - - pinctrl_wdog: wdoggrp { - fsl,pins = < - MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY 0x30b0 - >; - }; }; diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi index a17af4d9bfdf..61ba21a605a8 100644 --- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi +++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi @@ -57,6 +57,13 @@ status = "okay"; }; +&wdog1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_wdog>; + fsl,ext-reset-output; + status = "okay"; +}; + &iomuxc { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reset_out>; @@ -106,4 +113,10 @@ MX6UL_PAD_SNVS_TAMPER9__GPIO5_IO09 0x1b0b0 >; }; + + pinctrl_wdog: wdoggrp { + fsl,pins = < + MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY 0x18b0 + >; + }; }; diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi index e6308fb76183..a88ee5294d35 100644 --- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi +++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi @@ -100,79 +100,6 @@ }; }; - mcc { - compatible = "arm,vexpress,config-bus"; - arm,vexpress,config-bridge = <&v2m_sysreg>; - - oscclk0 { - /* MCC static memory clock */ - compatible = "arm,vexpress-osc"; - arm,vexpress-sysreg,func = <1 0>; - freq-range = <25000000 60000000>; - #clock-cells = <0>; - clock-output-names = "v2m:oscclk0"; - }; - - v2m_oscclk1: oscclk1 { - /* CLCD clock */ - compatible = "arm,vexpress-osc"; - arm,vexpress-sysreg,func = <1 1>; - freq-range = <23750000 65000000>; - #clock-cells = <0>; - clock-output-names = "v2m:oscclk1"; - }; - - v2m_oscclk2: oscclk2 { - /* IO FPGA peripheral clock */ - compatible = "arm,vexpress-osc"; - arm,vexpress-sysreg,func = <1 2>; - freq-range = <24000000 24000000>; - #clock-cells = <0>; - clock-output-names = "v2m:oscclk2"; - }; - - volt-vio { - /* Logic level voltage */ - compatible = "arm,vexpress-volt"; - arm,vexpress-sysreg,func = <2 0>; - regulator-name = "VIO"; - regulator-always-on; - label = "VIO"; - }; - - temp-mcc { - /* MCC internal operating temperature */ - compatible = "arm,vexpress-temp"; - arm,vexpress-sysreg,func = <4 0>; - label = "MCC"; - }; - - reset { - compatible = "arm,vexpress-reset"; - arm,vexpress-sysreg,func = <5 0>; - }; - - muxfpga { - compatible = "arm,vexpress-muxfpga"; - arm,vexpress-sysreg,func = <7 0>; - }; - - shutdown { - compatible = "arm,vexpress-shutdown"; - arm,vexpress-sysreg,func = <8 0>; - }; - - reboot { - compatible = "arm,vexpress-reboot"; - arm,vexpress-sysreg,func = <9 0>; - }; - - dvimode { - compatible = "arm,vexpress-dvimode"; - arm,vexpress-sysreg,func = <11 0>; - }; - }; - bus@8000000 { motherboard-bus { model = "V2M-P1"; @@ -435,6 +362,79 @@ }; }; }; + + mcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + oscclk0 { + /* MCC static memory clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <25000000 60000000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk0"; + }; + + v2m_oscclk1: oscclk1 { + /* CLCD clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <23750000 65000000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk1"; + }; + + v2m_oscclk2: oscclk2 { + /* IO FPGA peripheral clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <24000000 24000000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk2"; + }; + + volt-vio { + /* Logic level voltage */ + compatible = "arm,vexpress-volt"; + arm,vexpress-sysreg,func = <2 0>; + regulator-name = "VIO"; + regulator-always-on; + label = "VIO"; + }; + + temp-mcc { + /* MCC internal operating temperature */ + compatible = "arm,vexpress-temp"; + arm,vexpress-sysreg,func = <4 0>; + label = "MCC"; + }; + + reset { + compatible = "arm,vexpress-reset"; + arm,vexpress-sysreg,func = <5 0>; + }; + + muxfpga { + compatible = "arm,vexpress-muxfpga"; + arm,vexpress-sysreg,func = <7 0>; + }; + + shutdown { + compatible = "arm,vexpress-shutdown"; + arm,vexpress-sysreg,func = <8 0>; + }; + + reboot { + compatible = "arm,vexpress-reboot"; + arm,vexpress-sysreg,func = <9 0>; + }; + + dvimode { + compatible = "arm,vexpress-dvimode"; + arm,vexpress-sysreg,func = <11 0>; + }; + }; }; }; }; diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 84dc0ba822f5..5dcf3c6011b7 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -87,4 +87,11 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, return dram_base + SZ_512M; } +struct efi_arm_entry_state { + u32 cpsr_before_ebs; + u32 sctlr_before_ebs; + u32 cpsr_after_ebs; + u32 sctlr_after_ebs; +}; + #endif /* _ASM_ARM_EFI_H */ diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig index 6aa938b949db..1df0ee01ee02 100644 --- a/arch/arm/mach-bcm/Kconfig +++ b/arch/arm/mach-bcm/Kconfig @@ -53,6 +53,7 @@ config ARCH_BCM_NSP select ARM_ERRATA_754322 select ARM_ERRATA_775420 select ARM_ERRATA_764369 if SMP + select ARM_TIMER_SP804 select THERMAL select THERMAL_OF help diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c index f057df813f83..e9962b48e30c 100644 --- a/arch/arm/mach-imx/pm-imx5.c +++ b/arch/arm/mach-imx/pm-imx5.c @@ -295,14 +295,14 @@ static int __init imx_suspend_alloc_ocram( if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; - goto put_node; + goto put_device; } ocram_base = gen_pool_alloc(ocram_pool, size); if (!ocram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } phys = gen_pool_virt_to_phys(ocram_pool, ocram_base); @@ -312,6 +312,8 @@ static int __init imx_suspend_alloc_ocram( if (virt_out) *virt_out = virt; +put_device: + put_device(&pdev->dev); put_node: of_node_put(node); diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c index dd34dff13762..40c74b4c4d73 100644 --- a/arch/arm/mach-imx/pm-imx6.c +++ b/arch/arm/mach-imx/pm-imx6.c @@ -493,14 +493,14 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; - goto put_node; + goto put_device; } ocram_base = gen_pool_alloc(ocram_pool, MX6Q_SUSPEND_OCRAM_SIZE); if (!ocram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base); @@ -523,7 +523,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) ret = imx6_pm_get_base(&pm_info->mmdc_base, socdata->mmdc_compat); if (ret) { pr_warn("%s: failed to get mmdc base %d!\n", __func__, ret); - goto put_node; + goto put_device; } ret = imx6_pm_get_base(&pm_info->src_base, socdata->src_compat); @@ -570,7 +570,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) &imx6_suspend, MX6Q_SUSPEND_OCRAM_SIZE - sizeof(*pm_info)); - goto put_node; + goto put_device; pl310_cache_map_failed: iounmap(pm_info->gpc_base.vbase); @@ -580,6 +580,8 @@ iomuxc_map_failed: iounmap(pm_info->src_base.vbase); src_map_failed: iounmap(pm_info->mmdc_base.vbase); +put_device: + put_device(&pdev->dev); put_node: of_node_put(node); diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c index dcb98937fcf5..ffecbf29646f 100644 --- a/arch/arm/mach-sti/board-dt.c +++ b/arch/arm/mach-sti/board-dt.c @@ -20,14 +20,6 @@ static const char *const stih41x_dt_match[] __initconst = { NULL }; -static void sti_l2_write_sec(unsigned long val, unsigned reg) -{ - /* - * We can't write to secure registers as we are in non-secure - * mode, until we have some SMI service available. - */ -} - DT_MACHINE_START(STM, "STi SoC with Flattened Device Tree") .dt_compat = stih41x_dt_match, .l2c_aux_val = L2C_AUX_CTRL_SHARED_OVERRIDE | @@ -36,5 +28,4 @@ DT_MACHINE_START(STM, "STi SoC with Flattened Device Tree") L2C_AUX_CTRL_WAY_SIZE(4), .l2c_aux_mask = 0xc0000fff, .smp = smp_ops(sti_smp_ops), - .l2c_write_sec = sti_l2_write_sec, MACHINE_END diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a4a094bedcb2..66dc41fd49f2 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1518,9 +1518,9 @@ config ARM64_PTR_AUTH default y depends on !KVM || ARM64_VHE depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC - # GCC 9.1 and later inserts a .note.gnu.property section note for PAC + # Modern compilers insert a .note.gnu.property section note for PAC # which is only understood by binutils starting with version 2.33.1. - depends on !CC_IS_GCC || GCC_VERSION < 90100 || LD_VERSION >= 233010000 + depends on LD_IS_LLD || LD_VERSION >= 233010000 || (CC_IS_GCC && GCC_VERSION < 90100) depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi index fb0137a8611c..94911b1707ef 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi @@ -136,7 +136,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; @@ -144,7 +144,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts index e5ec8322796d..0f1d7f8aeac4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts @@ -208,7 +208,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; @@ -216,7 +216,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index d07e0e6a00cc..a1e5483dbbbe 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -113,7 +113,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; @@ -121,7 +121,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h index 81fefd2a1d02..ba89a9af820a 100644 --- a/arch/arm64/include/asm/linkage.h +++ b/arch/arm64/include/asm/linkage.h @@ -12,7 +12,6 @@ * instead. */ #define BTI_C hint 34 ; -#define BTI_J hint 36 ; /* * When using in-kernel BTI we need to ensure that PCS-conformant assembly @@ -43,11 +42,6 @@ SYM_START(name, SYM_L_WEAK, SYM_A_NONE) \ BTI_C -#define SYM_INNER_LABEL(name, linkage) \ - .type name SYM_T_NONE ASM_NL \ - SYM_ENTRY(name, linkage, SYM_A_NONE) \ - BTI_J - #endif /* diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 68140fdd89d6..8444df000181 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -19,6 +19,9 @@ typedef struct { atomic64_t id; +#ifdef CONFIG_COMPAT + void *sigpage; +#endif void *vdso; unsigned long flags; } mm_context_t; diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 151f28521f1e..a561cbb91d4d 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -29,9 +29,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ sys_compat.o -ifneq ($(CONFIG_COMPAT_VDSO), y) obj-$(CONFIG_COMPAT) += sigreturn32.o -endif obj-$(CONFIG_KUSER_HELPERS) += kuser32.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o obj-$(CONFIG_MODULES) += module.o diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index ad06d6802d2e..cf50c53e9357 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -460,6 +460,8 @@ static const struct midr_range arm64_ssb_cpus[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), {}, }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 4ae41670c2e6..9f63053a63a9 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1290,6 +1290,8 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } }; char const *str = "kpti command line option"; diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 0bbac612146e..666b225aeb3a 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) return 0; /* - * Compat (i.e. 32 bit) mode: - * - PC has been set in the pt_regs struct in kernel_entry, - * - Handle SP and LR here. + * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but + * we're stuck with it for ABI compatability reasons. + * + * For a 32-bit consumer inspecting a 32-bit task, then it will look at + * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h). + * These correspond directly to a prefix of the registers saved in our + * 'struct pt_regs', with the exception of the PC, so we copy that down + * (x15 corresponds to SP_hyp in the architecture). + * + * So far, so good. + * + * The oddity arises when a 64-bit consumer looks at a 32-bit task and + * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return + * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and + * PC registers would normally live. The initial idea was to allow a + * 64-bit unwinder to unwind a 32-bit task and, although it's not clear + * how well that works in practice, somebody might be relying on it. + * + * At the time we make a sample, we don't know whether the consumer is + * 32-bit or 64-bit, so we have to cater for both possibilities. */ if (compat_user_mode(regs)) { if ((u32)idx == PERF_REG_ARM64_SP) return regs->compat_sp; if ((u32)idx == PERF_REG_ARM64_LR) return regs->compat_lr; + if (idx == 15) + return regs->pc; } if ((u32)idx == PERF_REG_ARM64_SP) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index d1c95dcf1d78..cbe49cd117cf 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -120,15 +120,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) void *alloc_insn_page(void) { - void *page; - - page = vmalloc_exec(PAGE_SIZE); - if (page) { - set_memory_ro((unsigned long)page, 1); - set_vm_flush_reset_perms(page); - } - - return page; + return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __func__); } /* arm kprobe: install breakpoint in text */ diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 82feca6f7052..2f507f565c48 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -342,38 +342,13 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka, retcode = ptr_to_compat(ka->sa.sa_restorer); } else { /* Set up sigreturn pointer */ -#ifdef CONFIG_COMPAT_VDSO - void *vdso_base = current->mm->context.vdso; - void *vdso_trampoline; - - if (ka->sa.sa_flags & SA_SIGINFO) { - if (thumb) { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_rt_sigreturn_thumb); - } else { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_rt_sigreturn_arm); - } - } else { - if (thumb) { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_sigreturn_thumb); - } else { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_sigreturn_arm); - } - } - - retcode = ptr_to_compat(vdso_trampoline) + thumb; -#else unsigned int idx = thumb << 1; if (ka->sa.sa_flags & SA_SIGINFO) idx += 3; - retcode = (unsigned long)current->mm->context.vdso + + retcode = (unsigned long)current->mm->context.sigpage + (idx << 2) + thumb; -#endif } regs->regs[0] = usig; diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 4e016574bd91..e546df0efefb 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -191,15 +191,12 @@ enum aarch32_map { #ifdef CONFIG_COMPAT_VDSO AA32_MAP_VVAR, AA32_MAP_VDSO, -#else - AA32_MAP_SIGPAGE #endif + AA32_MAP_SIGPAGE }; static struct page *aarch32_vectors_page __ro_after_init; -#ifndef CONFIG_COMPAT_VDSO static struct page *aarch32_sig_page __ro_after_init; -#endif static struct vm_special_mapping aarch32_vdso_maps[] = { [AA32_MAP_VECTORS] = { @@ -214,12 +211,11 @@ static struct vm_special_mapping aarch32_vdso_maps[] = { .name = "[vdso]", .mremap = aarch32_vdso_mremap, }, -#else +#endif /* CONFIG_COMPAT_VDSO */ [AA32_MAP_SIGPAGE] = { .name = "[sigpage]", /* ABI */ .pages = &aarch32_sig_page, }, -#endif /* CONFIG_COMPAT_VDSO */ }; static int aarch32_alloc_kuser_vdso_page(void) @@ -242,27 +238,11 @@ static int aarch32_alloc_kuser_vdso_page(void) return 0; } -#ifdef CONFIG_COMPAT_VDSO -static int __aarch32_alloc_vdso_pages(void) -{ - int ret; - - vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR]; - vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO]; - - ret = __vdso_init(VDSO_ABI_AA32); - if (ret) - return ret; - - return aarch32_alloc_kuser_vdso_page(); -} -#else -static int __aarch32_alloc_vdso_pages(void) +static int aarch32_alloc_sigpage(void) { extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[]; int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start; unsigned long sigpage; - int ret; sigpage = get_zeroed_page(GFP_ATOMIC); if (!sigpage) @@ -271,18 +251,34 @@ static int __aarch32_alloc_vdso_pages(void) memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz); aarch32_sig_page = virt_to_page(sigpage); flush_dcache_page(aarch32_sig_page); + return 0; +} - ret = aarch32_alloc_kuser_vdso_page(); - if (ret) - free_page(sigpage); +#ifdef CONFIG_COMPAT_VDSO +static int __aarch32_alloc_vdso_pages(void) +{ + vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR]; + vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO]; - return ret; + return __vdso_init(VDSO_ABI_AA32); } #endif /* CONFIG_COMPAT_VDSO */ static int __init aarch32_alloc_vdso_pages(void) { - return __aarch32_alloc_vdso_pages(); + int ret; + +#ifdef CONFIG_COMPAT_VDSO + ret = __aarch32_alloc_vdso_pages(); + if (ret) + return ret; +#endif + + ret = aarch32_alloc_sigpage(); + if (ret) + return ret; + + return aarch32_alloc_kuser_vdso_page(); } arch_initcall(aarch32_alloc_vdso_pages); @@ -305,7 +301,6 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm) return PTR_ERR_OR_ZERO(ret); } -#ifndef CONFIG_COMPAT_VDSO static int aarch32_sigreturn_setup(struct mm_struct *mm) { unsigned long addr; @@ -328,12 +323,11 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm) if (IS_ERR(ret)) goto out; - mm->context.vdso = (void *)addr; + mm->context.sigpage = (void *)addr; out: return PTR_ERR_OR_ZERO(ret); } -#endif /* !CONFIG_COMPAT_VDSO */ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { @@ -352,10 +346,11 @@ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) mm, bprm, uses_interp); -#else - ret = aarch32_sigreturn_setup(mm); + if (ret) + goto out; #endif /* CONFIG_COMPAT_VDSO */ + ret = aarch32_sigreturn_setup(mm); out: mmap_write_unlock(mm); return ret; diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 556d424c6f52..45d5cfe46429 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -23,13 +23,14 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti # potential future proofing if we end up with internal calls to the exported # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so # preparation in build-time C")). -ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ - -Bsymbolic --eh-frame-hdr --build-id -n $(btildflags-y) -T +ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ + -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id -n \ + $(btildflags-y) -T ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 ccflags-y += -DDISABLE_BRANCH_PROFILING -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) KBUILD_CFLAGS += $(DISABLE_LTO) KASAN_SANITIZE := n UBSAN_SANITIZE := n diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S index 620a3ef837b7..0e18729abc3b 100644 --- a/arch/arm64/kernel/vdso/sigreturn.S +++ b/arch/arm64/kernel/vdso/sigreturn.S @@ -18,29 +18,40 @@ .text +/* + * NOTE!!! You may notice that all of the .cfi directives in this file have + * been commented out. This is because they have been shown to trigger segfaults + * in libgcc when unwinding out of a SIGCANCEL handler to invoke pthread + * cleanup handlers during the thread cancellation dance. By omitting the + * directives, we trigger an arm64-specific fallback path in the unwinder which + * recognises the signal frame and restores many of the registers directly from + * the sigcontext. Re-enabling the cfi directives here therefore needs to be + * much more comprehensive to reduce the risk of further regressions. + */ + /* Ensure that the mysterious NOP can be associated with a function. */ - .cfi_startproc +// .cfi_startproc /* - * .cfi_signal_frame causes the corresponding Frame Description Entry in the - * .eh_frame section to be annotated as a signal frame. This allows DWARF - * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo(), which permits - * unwinding out of the signal trampoline without the need for the mysterious - * NOP. + * .cfi_signal_frame causes the corresponding Frame Description Entry (FDE) in + * the .eh_frame section to be annotated as a signal frame. This allows DWARF + * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo() and identify + * the next frame using the unmodified return address instead of subtracting 1, + * which may yield the wrong FDE. */ - .cfi_signal_frame +// .cfi_signal_frame /* * Tell the unwinder where to locate the frame record linking back to the - * interrupted context. We don't provide unwind info for registers other - * than the frame pointer and the link register here; in practice, this - * is sufficient for unwinding in C/C++ based runtimes and the values in - * the sigcontext may have been modified by this point anyway. Debuggers + * interrupted context. We don't provide unwind info for registers other than + * the frame pointer and the link register here; in practice, this is likely to + * be insufficient for unwinding in C/C++ based runtimes, especially without a + * means to restore the stack pointer. Thankfully, unwinders and debuggers * already have baked-in strategies for attempting to unwind out of signals. */ - .cfi_def_cfa x29, 0 - .cfi_offset x29, 0 * 8 - .cfi_offset x30, 1 * 8 +// .cfi_def_cfa x29, 0 +// .cfi_offset x29, 0 * 8 +// .cfi_offset x30, 1 * 8 /* * This mysterious NOP is required for some unwinders (e.g. libc++) that @@ -51,16 +62,19 @@ nop // Mysterious NOP /* - * GDB relies on being able to identify the sigreturn instruction sequence to - * unwind from signal handlers. We cannot, therefore, use SYM_FUNC_START() - * here, as it will emit a BTI C instruction and break the unwinder. Thankfully, - * this function is only ever called from a RET and so omitting the landing pad - * is perfectly fine. + * GDB, libgcc and libunwind rely on being able to identify the sigreturn + * instruction sequence to unwind from signal handlers. We cannot, therefore, + * use SYM_FUNC_START() here, as it will emit a BTI C instruction and break the + * unwinder. Thankfully, this function is only ever called from a RET and so + * omitting the landing pad is perfectly fine. */ SYM_CODE_START(__kernel_rt_sigreturn) +// PLEASE DO NOT MODIFY mov x8, #__NR_rt_sigreturn +// PLEASE DO NOT MODIFY svc #0 - .cfi_endproc +// PLEASE DO NOT MODIFY +// .cfi_endproc SYM_CODE_END(__kernel_rt_sigreturn) emit_aarch64_feature_1_and diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 7ea1e827e505..d88148bef6b0 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -140,7 +140,6 @@ hostprogs := $(munge) c-obj-vdso := note.o c-obj-vdso-gettimeofday := vgettimeofday.o -asm-obj-vdso := sigreturn.o ifneq ($(c-gettimeofday-y),) VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y) diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S deleted file mode 100644 index b0091064c3d6..000000000000 --- a/arch/arm64/kernel/vdso32/sigreturn.S +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This file provides both A32 and T32 versions, in accordance with the - * arm sigreturn code. - * - * Please read the comments in arch/arm64/kernel/vdso/sigreturn.S to - * understand some of the craziness in here. - * - * Copyright (C) 2018 ARM Limited - */ - -#include <linux/linkage.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> - - .text - - .arm - .fnstart - .save {r0-r15} - .pad #COMPAT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_sigreturn_arm) - mov r7, #__NR_compat_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_sigreturn_arm) - - .fnstart - .save {r0-r15} - .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_rt_sigreturn_arm) - mov r7, #__NR_compat_rt_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_rt_sigreturn_arm) - - .thumb - .fnstart - .save {r0-r15} - .pad #COMPAT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_sigreturn_thumb) - mov r7, #__NR_compat_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_sigreturn_thumb) - - .fnstart - .save {r0-r15} - .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_rt_sigreturn_thumb) - mov r7, #__NR_compat_rt_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_rt_sigreturn_thumb) diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S index a3944927eaeb..337d03522048 100644 --- a/arch/arm64/kernel/vdso32/vdso.lds.S +++ b/arch/arm64/kernel/vdso32/vdso.lds.S @@ -64,19 +64,7 @@ VERSION __vdso_clock_gettime; __vdso_gettimeofday; __vdso_clock_getres; - __kernel_sigreturn_arm; - __kernel_sigreturn_thumb; - __kernel_rt_sigreturn_arm; - __kernel_rt_sigreturn_thumb; __vdso_clock_gettime64; local: *; }; } - -/* - * Make the sigreturn code visible to the kernel. - */ -VDSO_compat_sigreturn_arm = __kernel_sigreturn_arm; -VDSO_compat_sigreturn_thumb = __kernel_sigreturn_thumb; -VDSO_compat_rt_sigreturn_arm = __kernel_rt_sigreturn_arm; -VDSO_compat_rt_sigreturn_thumb = __kernel_rt_sigreturn_thumb; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 521bd5891e84..666d3350b4ac 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -67,8 +67,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("vz_ghfc", vz_ghfc_exits), VCPU_STAT("vz_gpa", vz_gpa_exits), VCPU_STAT("vz_resvd", vz_resvd_exits), +#ifdef CONFIG_CPU_LOONGSON64 VCPU_STAT("vz_cpucfg", vz_cpucfg_exits), #endif +#endif VCPU_STAT("halt_successful_poll", halt_successful_poll), VCPU_STAT("halt_attempted_poll", halt_attempted_poll), VCPU_STAT("halt_poll_invalid", halt_poll_invalid), diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index c152a68811dd..345727638d52 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -74,8 +74,11 @@ void *arch_dma_set_uncached(void *cpu_addr, size_t size) * We need to iterate through the pages, clearing the dcache for * them and setting the cache-inhibit bit. */ + mmap_read_lock(&init_mm); error = walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops, NULL); + mmap_read_unlock(&init_mm); + if (error) return ERR_PTR(error); return cpu_addr; @@ -85,9 +88,11 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size) { unsigned long va = (unsigned long)cpu_addr; + mmap_read_lock(&init_mm); /* walk_page_range shouldn't be able to fail here */ WARN_ON(walk_page_range(&init_mm, va, va + size, &clear_nocache_walk_ops, NULL)); + mmap_read_unlock(&init_mm); } void arch_sync_dma_for_device(phys_addr_t addr, size_t size, diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index e738ea652192..6a73714759ba 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -40,7 +40,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, /* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */ if (kvmhv_on_pseries()) return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr, - __pa(to), __pa(from), n); + (to != NULL) ? __pa(to): 0, + (from != NULL) ? __pa(from): 0, n); quadrant = 1; if (!pid) diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index 4a75f2d9bf0e..bce0e5349978 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -14,6 +14,7 @@ #include <linux/memblock.h> #include <linux/libfdt.h> #include <linux/crash_core.h> +#include <asm/cacheflush.h> #include <asm/pgalloc.h> #include <asm/prom.h> #include <asm/kdump.h> diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 38ba55b0eb9d..e4c7c2c8a02f 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -17,7 +17,7 @@ vdso-syms += flush_icache obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o ifneq ($(c-gettimeofday-y),) - CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) + CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) endif # Build rules @@ -27,6 +27,9 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) obj-y += vdso.o vdso-syms.o CPPFLAGS_vdso.lds += -P -C -U$(ARCH) +# Disable -pg to prevent insert call site +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os + # Disable gcov profiling for VDSO code GCOV_PROFILE := n diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c index d264943e2e47..cc0d80699c31 100644 --- a/arch/riscv/kernel/vdso/vgettimeofday.c +++ b/arch/riscv/kernel/vdso/vgettimeofday.c @@ -9,16 +9,22 @@ #include <linux/time.h> #include <linux/types.h> +extern +int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts); int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) { return __cvdso_clock_gettime(clock, ts); } +extern +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { return __cvdso_gettimeofday(tv, tz); } +extern +int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res); int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res) { return __cvdso_clock_getres(clock_id, res); diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 636446003a06..263075a1af36 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -198,9 +198,10 @@ static debug_entry_t ***debug_areas_alloc(int pages_per_area, int nr_areas) if (!areas) goto fail_malloc_areas; for (i = 0; i < nr_areas; i++) { + /* GFP_NOWARN to avoid user triggerable WARN, we handle fails */ areas[i] = kmalloc_array(pages_per_area, sizeof(debug_entry_t *), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!areas[i]) goto fail_malloc_areas2; for (j = 0; j < pages_per_area; j++) { diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index cd241ee66eff..078277231858 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -170,6 +170,8 @@ static noinline __init void setup_lowcore_early(void) psw_t psw; psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA; + if (IS_ENABLED(CONFIG_KASAN)) + psw.mask |= PSW_MASK_DAT; psw.addr = (unsigned long) s390_base_ext_handler; S390_lowcore.external_new_psw = psw; psw.addr = (unsigned long) s390_base_pgm_handler; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 496f74d98473..969b35b177dd 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -378,9 +378,9 @@ ENTRY(system_call) stmg %r8,%r15,__LC_SAVE_AREA_SYNC BPOFF lg %r12,__LC_CURRENT - lghi %r13,__TASK_thread lghi %r14,_PIF_SYSCALL .Lsysc_per: + lghi %r13,__TASK_thread lg %r15,__LC_KERNEL_STACK la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6a0cc524882d..883da0abf779 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -67,7 +67,7 @@ config X86 select ARCH_HAS_FILTER_PGPROT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL - select ARCH_HAS_KCOV if X86_64 + select ARCH_HAS_KCOV if X86_64 && STACK_VALIDATION select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index e821a7d7d5c4..97d37f0a34f5 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -213,7 +213,6 @@ SYM_FUNC_START(startup_32) * We place all of the values on our mini stack so lret can * used to perform that far jump. */ - pushl $__KERNEL_CS leal startup_64(%ebp), %eax #ifdef CONFIG_EFI_MIXED movl efi32_boot_args(%ebp), %edi @@ -224,11 +223,20 @@ SYM_FUNC_START(startup_32) movl efi32_boot_args+8(%ebp), %edx // saved bootparams pointer cmpl $0, %edx jnz 1f + /* + * efi_pe_entry uses MS calling convention, which requires 32 bytes of + * shadow space on the stack even if all arguments are passed in + * registers. We also need an additional 8 bytes for the space that + * would be occupied by the return address, and this also results in + * the correct stack alignment for entry. + */ + subl $40, %esp leal efi_pe_entry(%ebp), %eax movl %edi, %ecx // MS calling convention movl %esi, %edx 1: #endif + pushl $__KERNEL_CS pushl %eax /* Enter paged protected Mode, activating Long Mode */ @@ -784,6 +792,7 @@ SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) SYM_DATA_START_LOCAL(boot_stack) .fill BOOT_STACK_SIZE, 1, 0 + .balign 16 SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end) /* diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index 12c42eba77ec..9933c0e8e97a 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y += core.o probe.o -obj-$(PERF_EVENTS_INTEL_RAPL) += rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += rapl.o obj-y += amd/ obj-$(CONFIG_X86_LOCAL_APIC) += msr.o obj-$(CONFIG_CPU_SUP_INTEL) += intel/ diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index a54c6a401581..2bdc72e6890e 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -375,7 +375,9 @@ void __init hyperv_init(void) guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); - hv_hypercall_pg = vmalloc_exec(PAGE_SIZE); + hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, + VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __func__); if (hv_hypercall_pg == NULL) { wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); goto remove_cpuhp_state; diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 35460fef39b8..0367efdc5b7a 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -201,12 +201,8 @@ arch_test_and_change_bit(long nr, volatile unsigned long *addr) return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } -static __no_kcsan_or_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) +static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) { - /* - * Because this is a plain access, we need to disable KCSAN here to - * avoid double instrumentation via instrumented bitops. - */ return ((1UL << (nr & (BITS_PER_LONG-1))) & (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index fb34ff641e0a..028189575560 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -75,6 +75,12 @@ do { \ unreachable(); \ } while (0) +/* + * This instrumentation_begin() is strictly speaking incorrect; but it + * suppresses the complaints from WARN()s in noinstr code. If such a WARN() + * were to trigger, we'd rather wreck the machine in an attempt to get the + * message out than not know about it. + */ #define __WARN_FLAGS(flags) \ do { \ instrumentation_begin(); \ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index dd17c2da1af5..da78ccbd493b 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip) return false; } #endif +#ifdef CONFIG_IA32_FEAT_CTL +void init_ia32_feat_ctl(struct cpuinfo_x86 *c); +#else +static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {} +#endif #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index 6722ffcef2e6..3afa990d756b 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -11,5 +11,23 @@ extern cpumask_var_t cpu_sibling_setup_mask; extern void setup_cpu_local_masks(void); +/* + * NMI and MCE exceptions need cpu_is_offline() _really_ early, + * provide an arch_ special for them to avoid instrumentation. + */ +#if NR_CPUS > 1 +static __always_inline bool arch_cpu_online(int cpu) +{ + return arch_test_bit(cpu, cpumask_bits(cpu_online_mask)); +} +#else +static __always_inline bool arch_cpu_online(int cpu) +{ + return cpu == 0; +} +#endif + +#define arch_cpu_is_offline(cpu) unlikely(!arch_cpu_online(cpu)) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_CPUMASK_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f8998e97457f..be5363b21540 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -943,7 +943,7 @@ struct kvm_arch { atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map *apic_map; - bool apic_map_dirty; + atomic_t apic_map_dirty; bool apic_access_page_done; unsigned long apicv_inhibit_reasons; @@ -1220,7 +1220,7 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); - int (*write_log_dirty)(struct kvm_vcpu *vcpu); + int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 73d997aa2966..e039a933aca3 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -25,8 +25,6 @@ #define TPAUSE_C01_STATE 1 #define TPAUSE_C02_STATE 0 -u32 get_umwait_control_msr(void); - static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) { diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 2da1f95b88d7..816b31c68550 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -194,6 +194,7 @@ enum page_cache_mode { #define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0) #define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC) #define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_ROX (__PP| 0| 0|___A| 0|___D| 0|___G) #define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) #define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G) #define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G) @@ -219,6 +220,7 @@ enum page_cache_mode { #define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC) #define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC) #define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0) +#define PAGE_KERNEL_ROX __pgprot_mask(__PAGE_KERNEL_ROX | _ENC) #define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC) #define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 42cd333616c4..03b7c4ca425a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -370,7 +370,7 @@ struct x86_hw_tss { #define IO_BITMAP_OFFSET_INVALID (__KERNEL_TSS_LIMIT + 1) struct entry_stack { - unsigned long words[64]; + char stack[PAGE_SIZE]; }; struct entry_stack_page { diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 426792565d86..c5cf336e5077 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -3,6 +3,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/e820/api.h> #include <asm/mtrr.h> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 043d93cdcaad..95c090a45b4b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -347,6 +347,9 @@ out: cr4_clear_bits(X86_CR4_UMIP); } +/* These bits should not change their value after CPU init is finished. */ +static const unsigned long cr4_pinned_mask = + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE; static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning); static unsigned long cr4_pinned_bits __ro_after_init; @@ -371,20 +374,20 @@ EXPORT_SYMBOL(native_write_cr0); void native_write_cr4(unsigned long val) { - unsigned long bits_missing = 0; + unsigned long bits_changed = 0; set_register: asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits)); if (static_branch_likely(&cr_pinning)) { - if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) { - bits_missing = ~val & cr4_pinned_bits; - val |= bits_missing; + if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) { + bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits; + val = (val & ~cr4_pinned_mask) | cr4_pinned_bits; goto set_register; } - /* Warn after we've set the missing bits. */ - WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n", - bits_missing); + /* Warn after we've corrected the changed bits. */ + WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n", + bits_changed); } } #if IS_MODULE(CONFIG_LKDTM) @@ -419,7 +422,7 @@ void cr4_init(void) if (boot_cpu_has(X86_FEATURE_PCID)) cr4 |= X86_CR4_PCIDE; if (static_branch_likely(&cr_pinning)) - cr4 |= cr4_pinned_bits; + cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits; __write_cr4(cr4); @@ -434,10 +437,7 @@ void cr4_init(void) */ static void __init setup_cr_pinning(void) { - unsigned long mask; - - mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP); - cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask; + cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask; static_key_enable(&cr_pinning.key); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index fb538fccd24c..9d033693519a 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -81,8 +81,4 @@ extern void update_srbds_msr(void); extern u64 x86_read_arch_cap_msr(void); -#ifdef CONFIG_IA32_FEAT_CTL -void init_ia32_feat_ctl(struct cpuinfo_x86 *c); -#endif - #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index ce9120c4f740..fbe89a92ff36 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1083,7 +1083,7 @@ static noinstr bool mce_check_crashing_cpu(void) { unsigned int cpu = smp_processor_id(); - if (cpu_is_offline(cpu) || + if (arch_cpu_is_offline(cpu) || (crashing_cpu != -1 && crashing_cpu != cpu)) { u64 mcgstatus; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 12f967c6b603..6a9df71c1b9e 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -981,10 +981,10 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx; - if (c->x86_vendor == X86_VENDOR_INTEL) - c->x86_cache_mbm_width_offset = eax & 0xff; - else - c->x86_cache_mbm_width_offset = -1; + c->x86_cache_mbm_width_offset = eax & 0xff; + + if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset) + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; } } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index f20a47d120b1..5ffa32256b3b 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -37,6 +37,7 @@ #define MBA_IS_LINEAR 0x4 #define MBA_MAX_MBPS U32_MAX #define MAX_MBA_BW_AMD 0x800 +#define MBM_CNTR_WIDTH_OFFSET_AMD 20 #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 23b4b61319d3..3f844f14fc0a 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1117,6 +1117,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) { _r_cdp = NULL; + _d_cdp = NULL; ret = -EINVAL; } diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c index 300e3fd5ade3..ec8064c0ae03 100644 --- a/arch/x86/kernel/cpu/umwait.c +++ b/arch/x86/kernel/cpu/umwait.c @@ -18,12 +18,6 @@ */ static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE); -u32 get_umwait_control_msr(void) -{ - return umwait_control_cached; -} -EXPORT_SYMBOL_GPL(get_umwait_control_msr); - /* * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by * hardware or BIOS before kernel boot. diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index df1358ba622b..05fa4ef63490 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -2,6 +2,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include "cpu.h" diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 2de365f15684..d7c5e44b26f7 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -478,7 +478,7 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7); DEFINE_IDTENTRY_RAW(exc_nmi) { - if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id())) + if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) return; if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index f9727b96961f..f58679e487f6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -84,17 +84,16 @@ static inline void cond_local_irq_disable(struct pt_regs *regs) local_irq_disable(); } -int is_valid_bugaddr(unsigned long addr) +__always_inline int is_valid_bugaddr(unsigned long addr) { - unsigned short ud; - if (addr < TASK_SIZE_MAX) return 0; - if (get_kernel_nofault(ud, (unsigned short *)addr)) - return 0; - - return ud == INSN_UD0 || ud == INSN_UD2; + /* + * We got #UD, if the text isn't readable we'd have gotten + * a different exception. + */ + return *(unsigned short *)addr == INSN_UD2; } static nokprobe_inline int @@ -216,40 +215,45 @@ static inline void handle_invalid_op(struct pt_regs *regs) ILL_ILLOPN, error_get_trap_addr(regs)); } -DEFINE_IDTENTRY_RAW(exc_invalid_op) +static noinstr bool handle_bug(struct pt_regs *regs) { - bool rcu_exit; + bool handled = false; + + if (!is_valid_bugaddr(regs->ip)) + return handled; /* - * Handle BUG/WARN like NMIs instead of like normal idtentries: - * if we bugged/warned in a bad RCU context, for example, the last - * thing we want is to BUG/WARN again in the idtentry code, ad - * infinitum. + * All lies, just get the WARN/BUG out. */ - if (!user_mode(regs) && is_valid_bugaddr(regs->ip)) { - enum bug_trap_type type; + instrumentation_begin(); + /* + * Since we're emulating a CALL with exceptions, restore the interrupt + * state to what it was at the exception site. + */ + if (regs->flags & X86_EFLAGS_IF) + raw_local_irq_enable(); + if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { + regs->ip += LEN_UD2; + handled = true; + } + if (regs->flags & X86_EFLAGS_IF) + raw_local_irq_disable(); + instrumentation_end(); - nmi_enter(); - instrumentation_begin(); - trace_hardirqs_off_finish(); - type = report_bug(regs->ip, regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); - instrumentation_end(); - nmi_exit(); + return handled; +} - if (type == BUG_TRAP_TYPE_WARN) { - /* Skip the ud2. */ - regs->ip += LEN_UD2; - return; - } +DEFINE_IDTENTRY_RAW(exc_invalid_op) +{ + bool rcu_exit; - /* - * Else, if this was a BUG and report_bug returns or if this - * was just a normal #UD, we want to continue onward and - * crash. - */ - } + /* + * We use UD2 as a short encoding for 'CALL __WARN', as such + * handle it before exception entry to avoid recursive WARN + * in case exception entry is the one triggering WARNs. + */ + if (!user_mode(regs) && handle_bug(regs)) + return; rcu_exit = idtentry_enter_cond_rcu(regs); instrumentation_begin(); @@ -691,13 +695,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) (struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the temporary storage. */ - memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); + __memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); /* Copy the remainder of the stack from the current stack. */ - memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); + __memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); /* Update the entry stack */ - memcpy(new_stack, &tmp, sizeof(tmp)); + __memcpy(new_stack, &tmp, sizeof(tmp)); BUG_ON(!user_mode(&new_stack->regs)); return new_stack; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 34a7e0533dad..5bf72fc86a8e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -169,6 +169,18 @@ static void kvm_apic_map_free(struct rcu_head *rcu) kvfree(map); } +/* + * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock. + * + * DIRTY -> UPDATE_IN_PROGRESS and UPDATE_IN_PROGRESS -> CLEAN happen with + * apic_map_lock_held. + */ +enum { + CLEAN, + UPDATE_IN_PROGRESS, + DIRTY +}; + void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; @@ -176,17 +188,17 @@ void kvm_recalculate_apic_map(struct kvm *kvm) int i; u32 max_id = 255; /* enough space for any xAPIC ID */ - if (!kvm->arch.apic_map_dirty) { - /* - * Read kvm->arch.apic_map_dirty before - * kvm->arch.apic_map - */ - smp_rmb(); + /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ + if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN) return; - } mutex_lock(&kvm->arch.apic_map_lock); - if (!kvm->arch.apic_map_dirty) { + /* + * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map + * (if clean) or the APIC registers (if dirty). + */ + if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty, + DIRTY, UPDATE_IN_PROGRESS) == CLEAN) { /* Someone else has updated the map. */ mutex_unlock(&kvm->arch.apic_map_lock); return; @@ -256,11 +268,11 @@ out: lockdep_is_held(&kvm->arch.apic_map_lock)); rcu_assign_pointer(kvm->arch.apic_map, new); /* - * Write kvm->arch.apic_map before - * clearing apic->apic_map_dirty + * Write kvm->arch.apic_map before clearing apic->apic_map_dirty. + * If another update has come in, leave it DIRTY. */ - smp_wmb(); - kvm->arch.apic_map_dirty = false; + atomic_cmpxchg_release(&kvm->arch.apic_map_dirty, + UPDATE_IN_PROGRESS, CLEAN); mutex_unlock(&kvm->arch.apic_map_lock); if (old) @@ -282,20 +294,20 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) else static_key_slow_inc(&apic_sw_disabled.key); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) { kvm_lapic_set_reg(apic, APIC_ID, id << 24); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) { kvm_lapic_set_reg(apic, APIC_LDR, id); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) @@ -311,7 +323,7 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) kvm_lapic_set_reg(apic, APIC_ID, id); kvm_lapic_set_reg(apic, APIC_LDR, ldr); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) @@ -1976,7 +1988,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_DFR: if (!apic_x2apic_mode(apic)) { kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } else ret = 1; break; @@ -2232,7 +2244,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) static_key_slow_dec_deferred(&apic_hw_disabled); } else { static_key_slow_inc(&apic_hw_disabled.key); - vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } } @@ -2273,7 +2285,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) if (!apic) return; - vcpu->kvm->arch.apic_map_dirty = false; /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); @@ -2567,6 +2578,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 0ad06bfe2c2c..444bb9c54548 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -222,7 +222,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index fdd05c233308..76817d13c86e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1745,10 +1745,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, * Emulate arch specific page modification logging for the * nested hypervisor */ -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu) +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa) { if (kvm_x86_ops.write_log_dirty) - return kvm_x86_ops.write_log_dirty(vcpu); + return kvm_x86_ops.write_log_dirty(vcpu, l2_gpa); return 0; } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index a6d484ea110b..bd70ece1ef8b 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -235,7 +235,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte) static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, struct guest_walker *walker, - int write_fault) + gpa_t addr, int write_fault) { unsigned level, index; pt_element_t pte, orig_pte; @@ -260,7 +260,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, !(pte & PT_GUEST_DIRTY_MASK)) { trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); #if PTTYPE == PTTYPE_EPT - if (kvm_arch_write_log_dirty(vcpu)) + if (kvm_arch_write_log_dirty(vcpu, addr)) return -EINVAL; #endif pte |= PT_GUEST_DIRTY_MASK; @@ -360,7 +360,6 @@ retry_walk: ++walker->level; do { - gfn_t real_gfn; unsigned long host_addr; pt_access = pte_access; @@ -375,7 +374,7 @@ retry_walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), + real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), nested_access, &walker->fault); @@ -389,12 +388,10 @@ retry_walk: * information to fix the exit_qualification or exit_info_1 * fields. */ - if (unlikely(real_gfn == UNMAPPED_GVA)) + if (unlikely(real_gpa == UNMAPPED_GVA)) return 0; - real_gfn = gpa_to_gfn(real_gfn); - - host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn, + host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa), &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; @@ -457,7 +454,8 @@ retry_walk: (PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT); if (unlikely(!accessed_dirty)) { - ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault); + ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, + addr, write_fault); if (unlikely(ret < 0)) goto error; else if (ret) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8ccfa4197d9c..c0da4dd78ac5 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3344,7 +3344,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); -static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) +static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) { fastpath_t exit_fastpath; struct vcpu_svm *svm = to_svm(vcpu); diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 5c0ff80b85c0..7a3675fddec2 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -72,11 +72,24 @@ struct loaded_vmcs { struct vmcs_controls_shadow controls_shadow; }; +static inline bool is_intr_type(u32 intr_info, u32 type) +{ + const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK; + + return (intr_info & mask) == (INTR_INFO_VALID_MASK | type); +} + +static inline bool is_intr_type_n(u32 intr_info, u32 type, u8 vector) +{ + const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK | + INTR_INFO_VECTOR_MASK; + + return (intr_info & mask) == (INTR_INFO_VALID_MASK | type | vector); +} + static inline bool is_exception_n(u32 intr_info, u8 vector) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK); + return is_intr_type_n(intr_info, INTR_TYPE_HARD_EXCEPTION, vector); } static inline bool is_debug(u32 intr_info) @@ -106,28 +119,23 @@ static inline bool is_gp_fault(u32 intr_info) static inline bool is_machine_check(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK); + return is_exception_n(intr_info, MC_VECTOR); } /* Undocumented: icebp/int1 */ static inline bool is_icebp(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) - == (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK); + return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION); } static inline bool is_nmi(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) - == (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK); + return is_intr_type(intr_info, INTR_TYPE_NMI_INTR); } static inline bool is_external_intr(u32 intr_info) { - return (intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) - == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR); + return is_intr_type(intr_info, INTR_TYPE_EXT_INTR); } enum vmcs_field_width { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 36c771728c8c..cb22f33bf1d8 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6606,23 +6606,6 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx) -{ - u32 host_umwait_control; - - if (!vmx_has_waitpkg(vmx)) - return; - - host_umwait_control = get_umwait_control_msr(); - - if (vmx->msr_ia32_umwait_control != host_umwait_control) - add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL, - vmx->msr_ia32_umwait_control, - host_umwait_control, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL); -} - static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6728,9 +6711,7 @@ reenter_guest: pt_guest_enter(vmx); - if (vcpu_to_pmu(vcpu)->version) - atomic_switch_perf_msrs(vmx); - atomic_switch_umwait_control_msr(vmx); + atomic_switch_perf_msrs(vmx); if (enable_preemption_timer) vmx_update_hv_timer(vcpu); @@ -7501,11 +7482,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm) kvm_flush_pml_buffers(kvm); } -static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) +static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) { struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); - gpa_t gpa, dst; + gpa_t dst; if (is_guest_mode(vcpu)) { WARN_ON_ONCE(vmx->nested.pml_full); @@ -7524,7 +7505,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) return 1; } - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull; + gpa &= ~0xFFFull; dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index; if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 8a83b5edc820..639798e4a6ca 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -288,8 +288,6 @@ struct vcpu_vmx { u64 current_tsc_ratio; - u32 host_pkru; - unsigned long host_debugctlmsr; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 00c88c2f34e4..3b92db412335 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2856,7 +2856,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSCDEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); @@ -3196,7 +3196,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_APICBASE: msr_info->data = kvm_get_apic_base(vcpu); break; - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); case MSR_IA32_TSCDEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); @@ -4603,7 +4603,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; user_tsc_khz = (u32)arg; - if (user_tsc_khz >= kvm_max_guest_tsc_khz) + if (kvm_has_tsc_control && + user_tsc_khz >= kvm_max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 56b243b14c3a..bbcc05bcefad 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -8,6 +8,8 @@ #include <asm/alternative-asm.h> #include <asm/export.h> +.pushsection .noinstr.text, "ax" + /* * We build a jump to memcpy_orig by default which gets NOPped out on * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which @@ -184,6 +186,8 @@ SYM_FUNC_START_LOCAL(memcpy_orig) retq SYM_FUNC_END(memcpy_orig) +.popsection + #ifndef CONFIG_UML MCSAFE_TEST_CTL diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index fff28c6f73a2..b0dfac3d3df7 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size) asm volatile( " testq %[size8],%[size8]\n" " jz 4f\n" + " .align 16\n" "0: movq $0,(%[dst])\n" " addq $8,%[dst]\n" " decl %%ecx ; jnz 0b\n" diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 7c65102debaf..db1378c6ff26 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -193,6 +193,8 @@ static void fix_processor_context(void) */ static void notrace __restore_processor_state(struct saved_context *ctxt) { + struct cpuinfo_x86 *c; + if (ctxt->misc_enable_saved) wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable); /* @@ -263,6 +265,10 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) mtrr_bp_restore(); perf_restore_debug_store(); msr_restore_context(ctxt); + + c = &cpu_data(smp_processor_id()); + if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL)) + init_ia32_feat_ctl(c); } /* Needed by apm.c */ |