diff options
Diffstat (limited to 'arch')
63 files changed, 1037 insertions, 343 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 2e2dc0975ab4..a541ce263865 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1303,4 +1303,28 @@ source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" +config FUNCTION_ALIGNMENT_4B + bool + +config FUNCTION_ALIGNMENT_8B + bool + +config FUNCTION_ALIGNMENT_16B + bool + +config FUNCTION_ALIGNMENT_32B + bool + +config FUNCTION_ALIGNMENT_64B + bool + +config FUNCTION_ALIGNMENT + int + default 64 if FUNCTION_ALIGNMENT_64B + default 32 if FUNCTION_ALIGNMENT_32B + default 16 if FUNCTION_ALIGNMENT_16B + default 8 if FUNCTION_ALIGNMENT_8B + default 4 if FUNCTION_ALIGNMENT_4B + default 0 + endmenu diff --git a/arch/arm/boot/dts/mmp2-brownstone.dts b/arch/arm/boot/dts/mmp2-brownstone.dts index 04f1ae1382e7..bc64348b8218 100644 --- a/arch/arm/boot/dts/mmp2-brownstone.dts +++ b/arch/arm/boot/dts/mmp2-brownstone.dts @@ -28,7 +28,7 @@ &twsi1 { status = "okay"; pmic: max8925@3c { - compatible = "maxium,max8925"; + compatible = "maxim,max8925"; reg = <0x3c>; interrupts = <1>; interrupt-parent = <&intcmux4>; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index a9d36ac6cb90..a88798b80921 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -911,6 +911,8 @@ ap_spi_fp: &spi10 { vddrf-supply = <&pp1300_l2c>; vddch0-supply = <&pp3300_l10c>; max-speed = <3200000>; + + qcom,local-bd-address-broken; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 3cbe83e6fb9a..26f02cc70dc5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -728,11 +728,20 @@ status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; + hdmi_in_vop: endpoint { remote-endpoint = <&vop_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 9e33f0e6ed50..e98966899f53 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1801,6 +1801,7 @@ hdmi: hdmi@ff940000 { compatible = "rockchip,rk3399-dw-hdmi"; reg = <0x0 0xff940000 0x0 0x20000>; + reg-io-width = <4>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH 0>; clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_SFR>, @@ -1809,13 +1810,16 @@ <&cru PLL_VPLL>; clock-names = "iahb", "isfr", "cec", "grf", "vpll"; power-domains = <&power RK3399_PD_HDCP>; - reg-io-width = <4>; rockchip,grf = <&grf>; #sound-dai-cells = <0>; status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; #address-cells = <1>; #size-cells = <0>; @@ -1828,6 +1832,10 @@ remote-endpoint = <&vopl_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 027783829584..87e782eec925 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -13,6 +13,18 @@ #define KVM_PGTABLE_MAX_LEVELS 4U +/* + * The largest supported block sizes for KVM (no 52-bit PA support): + * - 4K (level 1): 1GB + * - 16K (level 2): 32MB + * - 64K (level 2): 512MB + */ +#ifdef CONFIG_ARM64_4K_PAGES +#define KVM_PGTABLE_MIN_BLOCK_LEVEL 1U +#else +#define KVM_PGTABLE_MIN_BLOCK_LEVEL 2U +#endif + static inline u64 kvm_get_parange(u64 mmfr0) { u64 parange = cpuid_feature_extract_unsigned_field(mmfr0, @@ -58,11 +70,7 @@ static inline u64 kvm_granule_size(u32 level) static inline bool kvm_level_supports_block_mapping(u32 level) { - /* - * Reject invalid block mappings and don't bother with 4TB mappings for - * 52-bit PAs. - */ - return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1)); + return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL; } /** diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h index fe341a6578c3..c8dca8ae359c 100644 --- a/arch/arm64/include/asm/stage2_pgtable.h +++ b/arch/arm64/include/asm/stage2_pgtable.h @@ -11,13 +11,6 @@ #include <linux/pgtable.h> /* - * PGDIR_SHIFT determines the size a top-level page table entry can map - * and depends on the number of levels in the page table. Compute the - * PGDIR_SHIFT for a given number of levels. - */ -#define pt_levels_pgdir_shift(lvls) ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls)) - -/* * The hardware supports concatenation of up to 16 tables at stage2 entry * level and we use the feature whenever possible, which means we resolve 4 * additional bits of address at the entry level. @@ -30,11 +23,6 @@ #define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4) #define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr) -/* stage2_pgdir_shift() is the size mapped by top-level stage2 entry for the VM */ -#define stage2_pgdir_shift(kvm) pt_levels_pgdir_shift(kvm_stage2_levels(kvm)) -#define stage2_pgdir_size(kvm) (1ULL << stage2_pgdir_shift(kvm)) -#define stage2_pgdir_mask(kvm) ~(stage2_pgdir_size(kvm) - 1) - /* * kvm_mmmu_cache_min_pages() is the number of pages required to install * a stage-2 translation. We pre-allocate the entry level page table at @@ -42,12 +30,4 @@ */ #define kvm_mmu_cache_min_pages(kvm) (kvm_stage2_levels(kvm) - 1) -static inline phys_addr_t -stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) -{ - phys_addr_t boundary = (addr + stage2_pgdir_size(kvm)) & stage2_pgdir_mask(kvm); - - return (boundary - 1 < end - 1) ? boundary : end; -} - #endif /* __ARM64_S2_PGTABLE_H_ */ diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 38a8095744a0..db667b4ad103 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -31,6 +31,13 @@ static phys_addr_t hyp_idmap_vector; static unsigned long io_map_base; +static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL); + phys_addr_t boundary = ALIGN_DOWN(addr + size, size); + + return (boundary - 1 < end - 1) ? boundary : end; +} /* * Release kvm_mmu_lock periodically if the memory region is large. Otherwise, @@ -52,7 +59,7 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr, if (!pgt) return -EINVAL; - next = stage2_pgd_addr_end(kvm, addr, end); + next = stage2_range_addr_end(addr, end); ret = fn(pgt, addr, next - addr); if (ret) break; diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 57465bff1fe4..df7f349c8d4f 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -64,6 +64,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG ELF_DETAILS + .hexagon.attributes 0 : { *(.hexagon.attributes) } DISCARDS } diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 89869aff8ca2..8902d1517894 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -63,6 +63,7 @@ config IA64 select PCI_MSI_ARCH_FALLBACKS if PCI_MSI select SET_FS select ZONE_DMA32 + select FUNCTION_ALIGNMENT_32B default y help The Itanium Processor Family is Intel's 64-bit successor to diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index 7e548c654a29..43cde968da88 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -23,7 +23,7 @@ KBUILD_AFLAGS_KERNEL := -mconstant-gp EXTRA := cflags-y := -pipe $(EXTRA) -ffixed-r13 -mfixed-range=f12-f15,f32-f127 \ - -falign-functions=32 -frename-registers -fno-optimize-sibling-calls + -frename-registers -fno-optimize-sibling-calls KBUILD_CFLAGS_KERNEL := -mconstant-gp GAS_STATUS = $(shell $(srctree)/arch/ia64/scripts/check-gas "$(CC)" "$(OBJDUMP)") diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index a82b2caaa560..b3edbb33b621 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -74,10 +74,10 @@ 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); + mmap_write_lock(&init_mm); + error = walk_page_range_novma(&init_mm, va, va + size, + &set_nocache_walk_ops, NULL, NULL); + mmap_write_unlock(&init_mm); if (error) return ERR_PTR(error); @@ -88,11 +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); + mmap_write_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); + WARN_ON(walk_page_range_novma(&init_mm, va, va + size, + &clear_nocache_walk_ops, NULL, NULL)); + mmap_write_unlock(&init_mm); } void arch_sync_dma_for_device(phys_addr_t addr, size_t size, diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index fd8c1ebd2747..12b9236effbc 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -79,26 +79,28 @@ * version takes two arguments: a src and destination register. * However, the source and destination registers can not be * the same register. + * + * We use add,l to avoid clobbering the C/B bits in the PSW. */ .macro tophys grvirt, grphys - ldil L%(__PAGE_OFFSET), \grphys - sub \grvirt, \grphys, \grphys + ldil L%(-__PAGE_OFFSET), \grphys + addl \grvirt, \grphys, \grphys .endm - + .macro tovirt grphys, grvirt ldil L%(__PAGE_OFFSET), \grvirt - add \grphys, \grvirt, \grvirt + addl \grphys, \grvirt, \grvirt .endm .macro tophys_r1 gr - ldil L%(__PAGE_OFFSET), %r1 - sub \gr, %r1, \gr + ldil L%(-__PAGE_OFFSET), %r1 + addl \gr, %r1, \gr .endm - + .macro tovirt_r1 gr ldil L%(__PAGE_OFFSET), %r1 - add \gr, %r1, \gr + addl \gr, %r1, \gr .endm .macro delay value diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h index 3c43baca7b39..2aceebcd695c 100644 --- a/arch/parisc/include/asm/checksum.h +++ b/arch/parisc/include/asm/checksum.h @@ -40,7 +40,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) " addc %0, %5, %0\n" " addc %0, %3, %0\n" "1: ldws,ma 4(%1), %3\n" -" addib,< 0, %2, 1b\n" +" addib,> -1, %2, 1b\n" " addc %0, %3, %0\n" "\n" " extru %0, 31, 16, %4\n" @@ -126,6 +126,7 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, ** Try to keep 4 registers with "live" values ahead of the ALU. */ +" depdi 0, 31, 32, %0\n"/* clear upper half of incoming checksum */ " ldd,ma 8(%1), %4\n" /* get 1st saddr word */ " ldd,ma 8(%2), %5\n" /* get 1st daddr word */ " add %4, %0, %0\n" @@ -137,8 +138,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " add,dc %3, %0, %0\n" /* fold in proto+len | carry bit */ " extrd,u %0, 31, 32, %4\n"/* copy upper half down */ " depdi 0, 31, 32, %0\n"/* clear upper half */ -" add %4, %0, %0\n" /* fold into 32-bits */ -" addc 0, %0, %0\n" /* add carry */ +" add,dc %4, %0, %0\n" /* fold into 32-bits, plus carry */ +" addc 0, %0, %0\n" /* add final carry */ #else @@ -163,7 +164,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " ldw,ma 4(%2), %7\n" /* 4th daddr */ " addc %6, %0, %0\n" " addc %7, %0, %0\n" -" addc %3, %0, %0\n" /* fold in proto+len, catch carry */ +" addc %3, %0, %0\n" /* fold in proto+len */ +" addc 0, %0, %0\n" /* add carry */ #endif : "=r" (sum), "=r" (saddr), "=r" (daddr), "=r" (len), diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h index a21f529c43d9..8359c06d92d9 100644 --- a/arch/powerpc/include/asm/reg_fsl_emb.h +++ b/arch/powerpc/include/asm/reg_fsl_emb.h @@ -12,9 +12,16 @@ #ifndef __ASSEMBLY__ /* Performance Monitor Registers */ #define mfpmr(rn) ({unsigned int rval; \ - asm volatile("mfpmr %0," __stringify(rn) \ + asm volatile(".machine push; " \ + ".machine e300; " \ + "mfpmr %0," __stringify(rn) ";" \ + ".machine pop; " \ : "=r" (rval)); rval;}) -#define mtpmr(rn, v) asm volatile("mtpmr " __stringify(rn) ",%0" : : "r" (v)) +#define mtpmr(rn, v) asm volatile(".machine push; " \ + ".machine e300; " \ + "mtpmr " __stringify(rn) ",%0; " \ + ".machine pop; " \ + : : "r" (v)) #endif /* __ASSEMBLY__ */ /* Freescale Book E Performance Monitor APU Registers */ diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 6448de85f738..2a4f3d09a08e 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -67,6 +67,6 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o -CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec) +CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec) obj-$(CONFIG_PPC64) += $(obj64-y) diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index d4d628af21a4..0a38801c52aa 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -467,7 +467,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n) #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ if (unlikely(__kr_err)) \ @@ -476,7 +476,7 @@ do { \ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ if (unlikely(__kr_err)) \ diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index bda3bc294718..1dea5b26f77e 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -24,8 +24,6 @@ #include <asm/switch_to.h> #include <asm/thread_info.h> -register unsigned long gp_in_global __asm__("gp"); - #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include <linux/stackprotector.h> unsigned long __stack_chk_guard __read_mostly; @@ -130,7 +128,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* Kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - childregs->gp = gp_in_global; /* Supervisor/Machine, irqs on: */ childregs->status = SR_PP | SR_PIE; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index d530eb4dc413..74ef903f94e7 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -685,6 +685,7 @@ ENDPROC(stack_overflow) .Lthis_cpu: .short 0 .Lstosm_tmp: .byte 0 .section .rodata, "a" + .balign 8 #define SYSCALL(esame,emu) .quad __s390x_ ## esame .globl sys_call_table sys_call_table: diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 060fff95a305..fbf25e926f67 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -274,7 +274,7 @@ static int __init setup_nmi_watchdog(char *str) if (!strncmp(str, "panic", 5)) panic_on_timeout = 1; - return 0; + return 1; } __setup("nmi_watchdog=", setup_nmi_watchdog); diff --git a/arch/sparc/vdso/vma.c b/arch/sparc/vdso/vma.c index cc19e09b0fa1..b073153c711a 100644 --- a/arch/sparc/vdso/vma.c +++ b/arch/sparc/vdso/vma.c @@ -449,9 +449,8 @@ static __init int vdso_setup(char *s) unsigned long val; err = kstrtoul(s, 10, &val); - if (err) - return err; - vdso_enabled = val; - return 0; + if (!err) + vdso_enabled = val; + return 1; } __setup("vdso=", vdso_setup); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2f89fa4d4fe1..1f2e53b8650b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -267,6 +267,8 @@ config X86 select HAVE_ARCH_KCSAN if X86_64 select X86_FEATURE_NAMES if PROC_FS select PROC_PID_ARCH_STATUS if PROC_FS + select FUNCTION_ALIGNMENT_16B if X86_64 || X86_ALIGNMENT_16 + select FUNCTION_ALIGNMENT_4B imply IMA_SECURE_AND_OR_TRUSTED_BOOT if EFI config INSTRUCTION_DECODER @@ -2498,6 +2500,42 @@ config GDS_FORCE_MITIGATION If in doubt, say N. +config MITIGATION_RFDS + bool "RFDS Mitigation" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for Register File Data Sampling (RFDS) by default. + RFDS is a hardware vulnerability which affects Intel Atom CPUs. It + allows unprivileged speculative access to stale data previously + stored in floating point, vector and integer registers. + See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst> + +choice + prompt "Clear branch history" + depends on CPU_SUP_INTEL + default SPECTRE_BHI_ON + help + Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks + where the branch history buffer is poisoned to speculatively steer + indirect branches. + See <file:Documentation/admin-guide/hw-vuln/spectre.rst> + +config SPECTRE_BHI_ON + bool "on" + help + Equivalent to setting spectre_bhi=on command line parameter. +config SPECTRE_BHI_OFF + bool "off" + help + Equivalent to setting spectre_bhi=off command line parameter. +config SPECTRE_BHI_AUTO + bool "auto" + help + Equivalent to setting spectre_bhi=auto command line parameter. + +endchoice + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index c3d427c817c7..e189a16ae40a 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -38,6 +38,14 @@ #include "pgtable.h" /* + * Fix alignment at 16 bytes. Following CONFIG_FUNCTION_ALIGNMENT will result + * in assembly errors due to trying to move .org backward due to the excessive + * alignment. + */ +#undef __ALIGN +#define __ALIGN .balign 16, 0x90 + +/* * Locally defined symbols should be marked hidden: */ .hidden _bss diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 6c2826417b33..e160f502d1dc 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -47,7 +47,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr) if (likely(unr < NR_syscalls)) { unr = array_index_nospec(unr, NR_syscalls); - regs->ax = sys_call_table[unr](regs); + regs->ax = x64_sys_call(regs, unr); return true; } return false; @@ -64,7 +64,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr) if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) { xnr = array_index_nospec(xnr, X32_NR_syscalls); - regs->ax = x32_sys_call_table[xnr](regs); + regs->ax = x32_sys_call(regs, xnr); return true; } return false; @@ -109,7 +109,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) if (likely(unr < IA32_NR_syscalls)) { unr = array_index_nospec(unr, IA32_NR_syscalls); - regs->ax = ia32_sys_call_table[unr](regs); + regs->ax = ia32_sys_call(regs, unr); } else if (nr != -1) { regs->ax = __ia32_sys_ni_syscall(regs); } diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index bfb7bcb362bc..09e99d13fc0b 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -6,6 +6,9 @@ #include <linux/linkage.h> #include <asm/export.h> #include <asm/msr-index.h> +#include <asm/unwind_hints.h> +#include <asm/segment.h> +#include <asm/cache.h> .pushsection .noinstr.text, "ax" @@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb) EXPORT_SYMBOL_GPL(entry_ibpb); .popsection + +/* + * Define the VERW operand that is disguised as entry code so that + * it can be referenced with KPTI enabled. This ensure VERW can be + * used late in exit-to-user path after page tables are switched. + */ +.pushsection .entry.text, "ax" + +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_START_NOALIGN(mds_verw_sel) + UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR + .word __KERNEL_DS +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_END(mds_verw_sel); +/* For KVM */ +EXPORT_SYMBOL_GPL(mds_verw_sel); + +.popsection + diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index e309e7156038..ee5def1060c8 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -912,6 +912,7 @@ SYM_FUNC_START(entry_SYSENTER_32) BUG_IF_WRONG_CR3 no_user_check=1 popfl popl %eax + CLEAR_CPU_BUFFERS /* * Return back to the vDSO, which will pop ecx and edx. @@ -981,6 +982,7 @@ restore_all_switch_stack: /* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code + CLEAR_CPU_BUFFERS .Lirq_return: /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -1173,6 +1175,7 @@ SYM_CODE_START(asm_exc_nmi) /* Not on SYSENTER stack. */ call exc_nmi + CLEAR_CPU_BUFFERS jmp .Lnmi_return .Lnmi_from_sysenter_stack: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 9f1333a9ee41..10d6888713d8 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -114,6 +114,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) /* clobbers %rax, make sure it is after saving the syscall nr */ IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY call do_syscall_64 /* returns with IRQs disabled */ @@ -219,6 +220,7 @@ syscall_return_via_sysret: popq %rdi popq %rsp swapgs + CLEAR_CPU_BUFFERS sysretq SYM_CODE_END(entry_SYSCALL_64) @@ -637,6 +639,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) /* Restore RDI. */ popq %rdi SWAPGS + CLEAR_CPU_BUFFERS INTERRUPT_RETURN @@ -743,6 +746,8 @@ native_irq_return_ldt: */ popq %rax /* Restore user RAX */ + CLEAR_CPU_BUFFERS + /* * RSP now points to an ordinary IRET frame, except that the page * is read-only and RSP[31:16] are preloaded with the userspace @@ -1466,6 +1471,12 @@ nmi_restore: movq $0, 5*8(%rsp) /* clear "NMI executing" */ /* + * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like + * NMI in kernel after user state is restored. For an unprivileged user + * these conditions are hard to meet. + */ + + /* * iretq reads the "iret" frame and exits the NMI stack in a * single instruction. We are returning to kernel mode, so this * cannot result in a fault. Similarly, we don't need to worry @@ -1482,6 +1493,7 @@ SYM_CODE_END(asm_exc_nmi) SYM_CODE_START(ignore_sysret) UNWIND_HINT_EMPTY mov $-ENOSYS, %eax + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(ignore_sysret) #endif @@ -1499,3 +1511,63 @@ SYM_CODE_START(rewind_stack_and_make_dead) call make_task_dead SYM_CODE_END(rewind_stack_and_make_dead) .popsection + +/* + * This sequence executes branches in order to remove user branch information + * from the branch history tracker in the Branch Predictor, therefore removing + * user influence on subsequent BTB lookups. + * + * It should be used on parts prior to Alder Lake. Newer parts should use the + * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being + * virtualized on newer hardware the VMM should protect against BHI attacks by + * setting BHI_DIS_S for the guests. + * + * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging + * and not clearing the branch history. The call tree looks like: + * + * call 1 + * call 2 + * call 2 + * call 2 + * call 2 + * call 2 + * ret + * ret + * ret + * ret + * ret + * ret + * + * This means that the stack is non-constant and ORC can't unwind it with %rsp + * alone. Therefore we unconditionally set up the frame pointer, which allows + * ORC to unwind properly. + * + * The alignment is for performance and not for safety, and may be safely + * refactored in the future if needed. + */ +SYM_FUNC_START(clear_bhb_loop) + push %rbp + mov %rsp, %rbp + movl $5, %ecx + ANNOTATE_INTRA_FUNCTION_CALL + call 1f + jmp 5f + .align 64, 0xcc + ANNOTATE_INTRA_FUNCTION_CALL +1: call 2f + RET + .align 64, 0xcc +2: movl $5, %eax +3: jmp 4f + nop +4: sub $1, %eax + jnz 3b + sub $1, %ecx + jnz 1b + RET +5: lfence + pop %rbp + RET +SYM_FUNC_END(clear_bhb_loop) +EXPORT_SYMBOL_GPL(clear_bhb_loop) +STACK_FRAME_NON_STANDARD(clear_bhb_loop) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 4d637a965efb..d03f0cfbcb1e 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY /* * SYSENTER doesn't filter flags, so we need to clear NT and AC @@ -259,6 +260,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY movq %rsp, %rdi call do_fast_syscall_32 @@ -319,6 +321,7 @@ sysret32_from_system_call: xorl %r9d, %r9d xorl %r10d, %r10d swapgs + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(entry_SYSCALL_compat) @@ -421,6 +424,7 @@ SYM_CODE_START(entry_INT80_compat) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY movq %rsp, %rdi call do_int80_syscall_32 diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 8cfc9bc73e7f..c2235bae17ef 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -18,8 +18,25 @@ #include <asm/syscalls_32.h> #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ +#ifdef CONFIG_X86_32 #define __SYSCALL(nr, sym) __ia32_##sym, - -__visible const sys_call_ptr_t ia32_sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include <asm/syscalls_32.h> }; +#undef __SYSCALL +#endif + +#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs); + +long ia32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_32.h> + default: return __ia32_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index be120eec1fc9..33b3f09e6f15 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -11,8 +11,23 @@ #include <asm/syscalls_64.h> #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ #define __SYSCALL(nr, sym) __x64_##sym, - -asmlinkage const sys_call_ptr_t sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include <asm/syscalls_64.h> }; +#undef __SYSCALL + +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); + +long x64_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_64.h> + default: return __x64_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index bdd0e03a1265..03de4a932131 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -11,8 +11,12 @@ #include <asm/syscalls_x32.h> #undef __SYSCALL -#define __SYSCALL(nr, sym) __x64_##sym, +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); -asmlinkage const sys_call_ptr_t x32_sys_call_table[] = { -#include <asm/syscalls_x32.h> +long x32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_x32.h> + default: return __x64_sys_ni_syscall(regs); + } }; diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 8f80de627c60..5cdccea45554 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -12,6 +12,7 @@ #include <asm/special_insns.h> #include <asm/preempt.h> #include <asm/asm.h> +#include <asm/nospec-branch.h> #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 6dd47c9ec788..fbcfec4dc4cc 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -6,11 +6,13 @@ # define __ASM_FORM(x, ...) x,## __VA_ARGS__ # define __ASM_FORM_RAW(x, ...) x,## __VA_ARGS__ # define __ASM_FORM_COMMA(x, ...) x,## __VA_ARGS__, +# define __ASM_REGPFX % #else #include <linux/stringify.h> # define __ASM_FORM(x, ...) " " __stringify(x,##__VA_ARGS__) " " # define __ASM_FORM_RAW(x, ...) __stringify(x,##__VA_ARGS__) # define __ASM_FORM_COMMA(x, ...) " " __stringify(x,##__VA_ARGS__) "," +# define __ASM_REGPFX %% #endif #define _ASM_BYTES(x, ...) __ASM_FORM(.byte x,##__VA_ARGS__ ;) @@ -49,6 +51,9 @@ #define _ASM_SI __ASM_REG(si) #define _ASM_DI __ASM_REG(di) +/* Adds a (%rip) suffix on 64 bits only; for immediate memory references */ +#define _ASM_RIP(x) __ASM_SEL_RAW(x, x (__ASM_REGPFX rip)) + #ifndef __x86_64__ /* 32 bit */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index cc3f62f5d551..955ca6b13e35 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -33,6 +33,8 @@ enum cpuid_leafs CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, + CPUID_LNX_5, + NR_CPUID_WORDS, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -93,8 +95,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -118,8 +121,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index d6089072ee41..18817817ea81 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -302,7 +302,7 @@ #define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ #define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ - +#define X86_FEATURE_CLEAR_CPU_BUF (11*32+18) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ @@ -416,11 +416,23 @@ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ #define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ /* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc and Linux defined features. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ + +/* * BUG word(s) */ #define X86_BUG(x) (NCAPINTS*32 + (x)) @@ -466,4 +478,6 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 99a12012c66e..b05d815ceaaa 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -109,6 +109,7 @@ #define DISABLED_MASK18 0 #define DISABLED_MASK19 0 #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index a12fdf01dc26..f27d6cecd803 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static __always_inline void arch_exit_to_user_mode(void) { - mds_user_clear_cpu_buffers(); amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 5000cf59bdf5..04a333c334ae 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -11,12 +11,14 @@ #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0))) #endif /* CONFIG_X86_32 */ -#ifdef __ASSEMBLY__ - -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16) -#define __ALIGN .p2align 4, 0x90 +#define __ALIGN .balign CONFIG_FUNCTION_ALIGNMENT, 0x90; #define __ALIGN_STR __stringify(__ALIGN) -#endif + +#define ASM_FUNC_ALIGN __ALIGN_STR +#define __FUNC_ALIGN __ALIGN +#define SYM_F_ALIGN __FUNC_ALIGN + +#ifdef __ASSEMBLY__ #if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define RET jmp __x86_return_thunk diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 5672ccb80eb1..15939a71dca7 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -30,6 +30,7 @@ #define _EFER_SVME 12 /* Enable virtualization */ #define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */ #define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ +#define _EFER_AUTOIBRS 21 /* Enable Automatic IBRS */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) @@ -38,6 +39,7 @@ #define EFER_SVME (1<<_EFER_SVME) #define EFER_LMSLE (1<<_EFER_LMSLE) #define EFER_FFXSR (1<<_EFER_FFXSR) +#define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) /* Intel MSRs. Some also available on other CPUs */ @@ -53,10 +55,13 @@ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */ +#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT) /* A mask for bits which the kernel toggles when controlling mitigations */ #define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ - | SPEC_CTRL_RRSBA_DIS_S) + | SPEC_CTRL_RRSBA_DIS_S \ + | SPEC_CTRL_BHI_DIS_S) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -153,6 +158,10 @@ * are restricted to targets in * kernel. */ +#define ARCH_CAP_BHI_NO BIT(20) /* + * CPU is not affected by Branch + * History Injection. + */ #define ARCH_CAP_PBRSB_NO BIT(24) /* * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. @@ -166,6 +175,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f3f6c28e5818..ed582fa98cb2 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -155,11 +155,20 @@ .Lskip_rsb_\@: .endm +/* + * The CALL to srso_alias_untrain_ret() must be patched in directly at + * the spot where untraining must be done, ie., srso_alias_untrain_ret() + * must be the target of a CALL instruction instead of indirectly + * jumping to a wrapper which then calls it. Therefore, this macro is + * called outside of __UNTRAIN_RET below, for the time being, before the + * kernel can support nested alternatives with arbitrary nesting. + */ +.macro CALL_UNTRAIN_RET #ifdef CONFIG_CPU_UNRET_ENTRY -#define CALL_UNTRAIN_RET "call entry_untrain_ret" -#else -#define CALL_UNTRAIN_RET "" + ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ + "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif +.endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the @@ -176,12 +185,37 @@ #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ defined(CONFIG_CPU_SRSO) ANNOTATE_UNRET_END - ALTERNATIVE_2 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_ENTRY_IBPB + CALL_UNTRAIN_RET + ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif .endm +/* + * Macro to execute VERW instruction that mitigate transient data sampling + * attacks such as MDS. On affected systems a microcode update overloaded VERW + * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. + * + * Note: Only the memory operand variant of VERW clears the CPU buffers. + */ +.macro CLEAR_CPU_BUFFERS + ALTERNATIVE "jmp .Lskip_verw_\@", "", X86_FEATURE_CLEAR_CPU_BUF + verw _ASM_RIP(mds_verw_sel) +.Lskip_verw_\@: +.endm + +#ifdef CONFIG_X86_64 +.macro CLEAR_BRANCH_HISTORY + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP +.endm + +.macro CLEAR_BRANCH_HISTORY_VMEXIT + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT +.endm +#else +#define CLEAR_BRANCH_HISTORY +#define CLEAR_BRANCH_HISTORY_VMEXIT +#endif + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ @@ -207,6 +241,10 @@ extern void srso_alias_untrain_ret(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); +#ifdef CONFIG_X86_64 +extern void clear_bhb_loop(void); +#endif + extern void (*x86_return_thunk)(void); #ifdef CONFIG_RETPOLINE @@ -357,13 +395,14 @@ 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); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); +extern u16 mds_verw_sel; + #include <asm/segment.h> /** @@ -390,17 +429,6 @@ static __always_inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability - * - * Clear CPU buffers if the corresponding static key is enabled - */ -static __always_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 diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 9bf60a8b9e9c..1fbe53583e95 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -103,6 +103,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index a800abb1a992..d8416b3bf832 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -12,11 +12,6 @@ /* image of the saved processor state */ struct saved_context { - /* - * On x86_32, all segment registers except gs are saved at kernel - * entry in pt_regs. - */ - u16 gs; unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; struct saved_msrs saved_msrs; @@ -27,6 +22,11 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + /* + * On x86_32, all segment registers except gs are saved at kernel + * entry in pt_regs. + */ + u16 gs; bool misc_enable_saved; } __attribute__((packed)); diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index f7e2d82d24fb..825528bf0daf 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,19 +16,17 @@ #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> +/* This is used purely for kernel/trace/trace_syscalls.c */ typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; -#if defined(CONFIG_X86_32) -#define ia32_sys_call_table sys_call_table -#else /* * These may not exist, but still put the prototypes in so we * can use IS_ENABLED(). */ -extern const sys_call_ptr_t ia32_sys_call_table[]; -extern const sys_call_ptr_t x32_sys_call_table[]; -#endif +extern long ia32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x64_sys_call(const struct pt_regs *, unsigned int nr); /* * Only the low 32 bits of orig_ax are meaningful, so we return int. diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index c6015b407461..7281ce64e99d 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -181,6 +181,37 @@ void int3_emulate_ret(struct pt_regs *regs) unsigned long ip = int3_emulate_pop(regs); int3_emulate_jmp(regs, ip); } + +static __always_inline +void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned long disp) +{ + static const unsigned long jcc_mask[6] = { + [0] = X86_EFLAGS_OF, + [1] = X86_EFLAGS_CF, + [2] = X86_EFLAGS_ZF, + [3] = X86_EFLAGS_CF | X86_EFLAGS_ZF, + [4] = X86_EFLAGS_SF, + [5] = X86_EFLAGS_PF, + }; + + bool invert = cc & 1; + bool match; + + if (cc < 0xc) { + match = regs->flags & jcc_mask[cc >> 1]; + } else { + match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ + ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); + if (cc >= 0xe) + match = match || (regs->flags & X86_EFLAGS_ZF); + } + + if ((match && !invert) || (!match && invert)) + ip += disp; + + int3_emulate_jmp(regs, ip); +} + #endif /* !CONFIG_UML_X86 */ #endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index e5536edbae57..5614e6d219b7 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -351,6 +351,12 @@ next: kasan_enable_current(); } +static inline bool is_jcc32(struct insn *insn) +{ + /* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */ + return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80; +} + #if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION) /* @@ -1201,6 +1207,11 @@ void text_poke_sync(void) on_each_cpu(do_sync_core, NULL, 1); } +/* + * NOTE: crazy scheme to allow patching Jcc.d32 but not increase the size of + * this thing. When len == 6 everything is prefixed with 0x0f and we map + * opcode to Jcc.d8, using len to distinguish. + */ struct text_poke_loc { /* addr := _stext + rel_addr */ s32 rel_addr; @@ -1322,6 +1333,10 @@ noinstr int poke_int3_handler(struct pt_regs *regs) int3_emulate_jmp(regs, (long)ip + tp->disp); break; + case 0x70 ... 0x7f: /* Jcc */ + int3_emulate_jcc(regs, tp->opcode & 0xf, (long)ip, tp->disp); + break; + default: BUG(); } @@ -1395,16 +1410,26 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries * Second step: update all but the first byte of the patched range. */ for (do_sync = 0, i = 0; i < nr_entries; i++) { - u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, }; + u8 old[POKE_MAX_OPCODE_SIZE+1] = { tp[i].old, }; + u8 _new[POKE_MAX_OPCODE_SIZE+1]; + const u8 *new = tp[i].text; int len = tp[i].len; if (len - INT3_INSN_SIZE > 0) { memcpy(old + INT3_INSN_SIZE, text_poke_addr(&tp[i]) + INT3_INSN_SIZE, len - INT3_INSN_SIZE); + + if (len == 6) { + _new[0] = 0x0f; + memcpy(_new + 1, new, 5); + new = _new; + } + text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE, - (const char *)tp[i].text + INT3_INSN_SIZE, + new + INT3_INSN_SIZE, len - INT3_INSN_SIZE); + do_sync++; } @@ -1432,8 +1457,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries * The old instruction is recorded so that the event can be * processed forwards or backwards. */ - perf_event_text_poke(text_poke_addr(&tp[i]), old, len, - tp[i].text, len); + perf_event_text_poke(text_poke_addr(&tp[i]), old, len, new, len); } if (do_sync) { @@ -1450,10 +1474,15 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries * replacing opcode. */ for (do_sync = 0, i = 0; i < nr_entries; i++) { - if (tp[i].text[0] == INT3_INSN_OPCODE) + u8 byte = tp[i].text[0]; + + if (tp[i].len == 6) + byte = 0x0f; + + if (byte == INT3_INSN_OPCODE) continue; - text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE); + text_poke(text_poke_addr(&tp[i]), &byte, INT3_INSN_SIZE); do_sync++; } @@ -1471,9 +1500,11 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, const void *opcode, size_t len, const void *emulate) { struct insn insn; - int ret, i; + int ret, i = 0; - memcpy((void *)tp->text, opcode, len); + if (len == 6) + i = 1; + memcpy((void *)tp->text, opcode+i, len-i); if (!emulate) emulate = opcode; @@ -1484,6 +1515,13 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, tp->len = len; tp->opcode = insn.opcode.bytes[0]; + if (is_jcc32(&insn)) { + /* + * Map Jcc.d32 onto Jcc.d8 and use len to distinguish. + */ + tp->opcode = insn.opcode.bytes[1] - 0x10; + } + switch (tp->opcode) { case RET_INSN_OPCODE: case JMP32_INSN_OPCODE: @@ -1500,7 +1538,6 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, BUG_ON(len != insn.length); }; - switch (tp->opcode) { case INT3_INSN_OPCODE: case RET_INSN_OPCODE: @@ -1509,6 +1546,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, case CALL_INSN_OPCODE: case JMP32_INSN_OPCODE: case JMP8_INSN_OPCODE: + case 0x70 ... 0x7f: /* Jcc */ tp->disp = insn.immediate.value; break; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index dba7fe7ecea9..9fb890574f36 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1021,11 +1021,11 @@ static bool cpu_has_zenbleed_microcode(void) u32 good_rev = 0; switch (boot_cpu_data.x86_model) { - case 0x30 ... 0x3f: good_rev = 0x0830107a; break; - case 0x60 ... 0x67: good_rev = 0x0860010b; break; - case 0x68 ... 0x6f: good_rev = 0x08608105; break; - case 0x70 ... 0x7f: good_rev = 0x08701032; break; - case 0xa0 ... 0xaf: good_rev = 0x08a00008; break; + case 0x30 ... 0x3f: good_rev = 0x0830107b; break; + case 0x60 ... 0x67: good_rev = 0x0860010c; break; + case 0x68 ... 0x6f: good_rev = 0x08608107; break; + case 0x70 ... 0x7f: good_rev = 0x08701033; break; + case 0xa0 ... 0xaf: good_rev = 0x08a00009; break; default: return false; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d1ba55ea46a7..50fdd6ca3b78 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -110,9 +110,6 @@ 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); @@ -258,7 +255,7 @@ static void __init mds_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV; - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) @@ -362,7 +359,7 @@ static void __init taa_select_mitigation(void) * For guests that can't determine whether the correct microcode is * present on host, enable the mitigation for UCODE_NEEDED as well. */ - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -430,7 +427,14 @@ static void __init mmio_select_mitigation(void) */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + + /* + * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based + * mitigations, disable KVM-only mitigation in that case. + */ + if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) + static_branch_disable(&mmio_stale_data_clear); else static_branch_enable(&mmio_stale_data_clear); @@ -483,6 +487,57 @@ static int __init mmio_stale_data_parse_cmdline(char *str) early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "Register File Data Sampling: " fmt + +enum rfds_mitigations { + RFDS_MITIGATION_OFF, + RFDS_MITIGATION_VERW, + RFDS_MITIGATION_UCODE_NEEDED, +}; + +/* Default mitigation for Register File Data Sampling */ +static enum rfds_mitigations rfds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF; + +static const char * const rfds_strings[] = { + [RFDS_MITIGATION_OFF] = "Vulnerable", + [RFDS_MITIGATION_VERW] = "Mitigation: Clear Register File", + [RFDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", +}; + +static void __init rfds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) { + rfds_mitigation = RFDS_MITIGATION_OFF; + return; + } + if (rfds_mitigation == RFDS_MITIGATION_OFF) + return; + + if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR) + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + else + rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; +} + +static __init int rfds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + return 0; + + if (!strcmp(str, "off")) + rfds_mitigation = RFDS_MITIGATION_OFF; + else if (!strcmp(str, "on")) + rfds_mitigation = RFDS_MITIGATION_VERW; + + return 0; +} +early_param("reg_file_data_sampling", rfds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "" fmt static void __init md_clear_update_mitigation(void) @@ -490,12 +545,12 @@ static void __init md_clear_update_mitigation(void) if (cpu_mitigations_off()) return; - if (!static_key_enabled(&mds_user_clear)) + if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out; /* - * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data - * mitigation, if necessary. + * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO + * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { @@ -507,11 +562,19 @@ static void __init md_clear_update_mitigation(void) taa_mitigation = TAA_MITIGATION_VERW; taa_select_mitigation(); } - if (mmio_mitigation == MMIO_MITIGATION_OFF && - boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { + /* + * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear + * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state. + */ + if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { mmio_mitigation = MMIO_MITIGATION_VERW; mmio_select_mitigation(); } + if (rfds_mitigation == RFDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_RFDS)) { + rfds_mitigation = RFDS_MITIGATION_VERW; + rfds_select_mitigation(); + } out: if (boot_cpu_has_bug(X86_BUG_MDS)) pr_info("MDS: %s\n", mds_strings[mds_mitigation]); @@ -521,6 +584,8 @@ out: pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) pr_info("MMIO Stale Data: Unknown: No mitigations\n"); + if (boot_cpu_has_bug(X86_BUG_RFDS)) + pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]); } static void __init md_clear_select_mitigation(void) @@ -528,11 +593,12 @@ static void __init md_clear_select_mitigation(void) mds_select_mitigation(); taa_select_mitigation(); mmio_select_mitigation(); + rfds_select_mitigation(); /* - * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update - * and print their mitigation after MDS, TAA and MMIO Stale Data - * mitigation selection is done. + * As these mitigations are inter-related and rely on VERW instruction + * to clear the microarchitural buffers, update and print their status + * after mitigation selection is done for each of these vulnerabilities. */ md_clear_update_mitigation(); } @@ -1288,19 +1354,21 @@ spectre_v2_user_select_mitigation(void) } /* - * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP + * If no STIBP, Intel enhanced IBRS is enabled, or SMT impossible, STIBP * is not required. * - * Enhanced IBRS also protects against cross-thread branch target + * Intel's Enhanced IBRS also protects against cross-thread branch target * injection in user-mode as the IBRS bit remains always set which * implicitly enables cross-thread protections. However, in legacy IBRS * mode, the IBRS bit is set only on kernel entry and cleared on return - * to userspace. This disables the implicit cross-thread protection, - * so allow for STIBP to be selected in that case. + * to userspace. AMD Automatic IBRS also does not protect userspace. + * These modes therefore disable the implicit cross-thread protection, + * so allow for STIBP to be selected in those cases. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS))) return; /* @@ -1330,9 +1398,9 @@ static const char * const spectre_v2_strings[] = { [SPECTRE_V2_NONE] = "Vulnerable", [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines", [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE", - [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", - [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", - [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", + [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced / Automatic IBRS", + [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced / Automatic IBRS + LFENCE", + [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced / Automatic IBRS + Retpolines", [SPECTRE_V2_IBRS] = "Mitigation: IBRS", }; @@ -1401,7 +1469,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { - pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n", + pr_err("%s selected but CPU doesn't have Enhanced or Automatic IBRS. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -1516,6 +1584,79 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_ dump_stack(); } +/* + * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by + * branch history in userspace. Not needed if BHI_NO is set. + */ +static bool __init spec_ctrl_bhi_dis(void) +{ + if (!boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW); + + return true; +} + +enum bhi_mitigations { + BHI_MITIGATION_OFF, + BHI_MITIGATION_ON, + BHI_MITIGATION_AUTO, +}; + +static enum bhi_mitigations bhi_mitigation __ro_after_init = + IS_ENABLED(CONFIG_SPECTRE_BHI_ON) ? BHI_MITIGATION_ON : + IS_ENABLED(CONFIG_SPECTRE_BHI_OFF) ? BHI_MITIGATION_OFF : + BHI_MITIGATION_AUTO; + +static int __init spectre_bhi_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + bhi_mitigation = BHI_MITIGATION_OFF; + else if (!strcmp(str, "on")) + bhi_mitigation = BHI_MITIGATION_ON; + else if (!strcmp(str, "auto")) + bhi_mitigation = BHI_MITIGATION_AUTO; + else + pr_err("Ignoring unknown spectre_bhi option (%s)", str); + + return 0; +} +early_param("spectre_bhi", spectre_bhi_parse_cmdline); + +static void __init bhi_select_mitigation(void) +{ + if (bhi_mitigation == BHI_MITIGATION_OFF) + return; + + /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */ + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) && + !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA)) + return; + + if (spec_ctrl_bhi_dis()) + return; + + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* Mitigate KVM by default */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); + pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n"); + + if (bhi_mitigation == BHI_MITIGATION_AUTO) + return; + + /* Mitigate syscalls when the mitigation is forced =on */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); + pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n"); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1586,8 +1727,12 @@ static void __init spectre_v2_select_mitigation(void) pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); if (spectre_v2_in_ibrs_mode(mode)) { - x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - update_spec_ctrl(x86_spec_ctrl_base); + if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) { + msr_set_bit(MSR_EFER, _EFER_AUTOIBRS); + } else { + x86_spec_ctrl_base |= SPEC_CTRL_IBRS; + update_spec_ctrl(x86_spec_ctrl_base); + } } switch (mode) { @@ -1622,6 +1767,9 @@ static void __init spectre_v2_select_mitigation(void) mode == SPECTRE_V2_RETPOLINE) spec_ctrl_disable_kernel_rrsba(); + if (boot_cpu_has(X86_BUG_BHI)) + bhi_select_mitigation(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -1671,8 +1819,8 @@ static void __init spectre_v2_select_mitigation(void) /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS * and Enhanced IBRS protect firmware too, so enable IBRS around - * firmware calls only when IBRS / Enhanced IBRS aren't otherwise - * enabled. + * firmware calls only when IBRS / Enhanced / Automatic IBRS aren't + * otherwise enabled. * * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because * the user might select retpoline on the kernel command line and if @@ -2502,74 +2650,74 @@ static const char * const l1tf_vmx_states[] = { static ssize_t l1tf_show_state(char *buf) { if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) - return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && sched_smt_active())) { - return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, - l1tf_vmx_states[l1tf_vmx_mitigation]); + return sysfs_emit(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation]); } - return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, - l1tf_vmx_states[l1tf_vmx_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t itlb_multihit_show_state(char *buf) { if (!boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || !boot_cpu_has(X86_FEATURE_VMX)) - return sprintf(buf, "KVM: Mitigation: VMX unsupported\n"); + return sysfs_emit(buf, "KVM: Mitigation: VMX unsupported\n"); else if (!(cr4_read_shadow() & X86_CR4_VMXE)) - return sprintf(buf, "KVM: Mitigation: VMX disabled\n"); + return sysfs_emit(buf, "KVM: Mitigation: VMX disabled\n"); else if (itlb_multihit_kvm_mitigation) - return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + return sysfs_emit(buf, "KVM: Mitigation: Split huge pages\n"); else - return sprintf(buf, "KVM: Vulnerable\n"); + return sysfs_emit(buf, "KVM: Vulnerable\n"); } #else static ssize_t l1tf_show_state(char *buf) { - return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); } static ssize_t itlb_multihit_show_state(char *buf) { - return sprintf(buf, "Processor vulnerable\n"); + return sysfs_emit(buf, "Processor vulnerable\n"); } #endif static ssize_t mds_show_state(char *buf) { if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - return sprintf(buf, "%s; SMT Host state unknown\n", - mds_strings[mds_mitigation]); + return sysfs_emit(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 sysfs_emit(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"); + return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t tsx_async_abort_show_state(char *buf) { if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || (taa_mitigation == TAA_MITIGATION_OFF)) - return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + return sysfs_emit(buf, "%s\n", taa_strings[taa_mitigation]); if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - return sprintf(buf, "%s; SMT Host state unknown\n", - taa_strings[taa_mitigation]); + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); } - return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t mmio_stale_data_show_state(char *buf) @@ -2589,22 +2737,28 @@ static ssize_t mmio_stale_data_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t rfds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); +} + static char *stibp_state(void) { - if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS)) return ""; switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: - return ", STIBP: disabled"; + return "; STIBP: disabled"; case SPECTRE_V2_USER_STRICT: - return ", STIBP: forced"; + return "; STIBP: forced"; case SPECTRE_V2_USER_STRICT_PREFERRED: - return ", STIBP: always-on"; + return "; STIBP: always-on"; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: if (static_key_enabled(&switch_to_cond_stibp)) - return ", STIBP: conditional"; + return "; STIBP: conditional"; } return ""; } @@ -2613,10 +2767,10 @@ static char *ibpb_state(void) { if (boot_cpu_has(X86_FEATURE_IBPB)) { if (static_key_enabled(&switch_mm_always_ibpb)) - return ", IBPB: always-on"; + return "; IBPB: always-on"; if (static_key_enabled(&switch_mm_cond_ibpb)) - return ", IBPB: conditional"; - return ", IBPB: disabled"; + return "; IBPB: conditional"; + return "; IBPB: disabled"; } return ""; } @@ -2626,58 +2780,76 @@ static char *pbrsb_eibrs_state(void) if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || boot_cpu_has(X86_FEATURE_RSB_VMEXIT)) - return ", PBRSB-eIBRS: SW sequence"; + return "; PBRSB-eIBRS: SW sequence"; else - return ", PBRSB-eIBRS: Vulnerable"; + return "; PBRSB-eIBRS: Vulnerable"; } else { - return ", PBRSB-eIBRS: Not affected"; + return "; PBRSB-eIBRS: Not affected"; } } +static const char * const spectre_bhi_state(void) +{ + if (!boot_cpu_has_bug(X86_BUG_BHI)) + return "; BHI: Not affected"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) + return "; BHI: BHI_DIS_S"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) + return "; BHI: SW loop, KVM: SW loop"; + else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA)) + return "; BHI: Retpoline"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT)) + return "; BHI: Syscall hardening, KVM: SW loop"; + + return "; BHI: Vulnerable (Syscall hardening enabled)"; +} + static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) - return sprintf(buf, "Vulnerable: LFENCE\n"); + return sysfs_emit(buf, "Vulnerable: LFENCE\n"); if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) - return sprintf(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); + return sysfs_emit(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); if (sched_smt_active() && unprivileged_ebpf_enabled() && spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) - return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); + return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sprintf(buf, "%s%s%s%s%s%s%s\n", - spectre_v2_strings[spectre_v2_enabled], - ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", - pbrsb_eibrs_state(), - spectre_v2_module_string()); + return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n", + spectre_v2_strings[spectre_v2_enabled], + ibpb_state(), + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "", + stibp_state(), + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "", + pbrsb_eibrs_state(), + spectre_bhi_state(), + /* this should always be at the end */ + spectre_v2_module_string()); } static ssize_t srbds_show_state(char *buf) { - return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); + return sysfs_emit(buf, "%s\n", srbds_strings[srbds_mitigation]); } static ssize_t retbleed_show_state(char *buf) { if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET || retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && - boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) - return sprintf(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return sysfs_emit(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); - return sprintf(buf, "%s; SMT %s\n", - retbleed_strings[retbleed_mitigation], - !sched_smt_active() ? "disabled" : - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? - "enabled with STIBP protection" : "vulnerable"); + return sysfs_emit(buf, "%s; SMT %s\n", retbleed_strings[retbleed_mitigation], + !sched_smt_active() ? "disabled" : + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? + "enabled with STIBP protection" : "vulnerable"); } - return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); + return sysfs_emit(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } static ssize_t gds_show_state(char *buf) @@ -2699,26 +2871,26 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr char *buf, unsigned int bug) { if (!boot_cpu_has_bug(bug)) - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); switch (bug) { case X86_BUG_CPU_MELTDOWN: if (boot_cpu_has(X86_FEATURE_PTI)) - return sprintf(buf, "Mitigation: PTI\n"); + return sysfs_emit(buf, "Mitigation: PTI\n"); if (hypervisor_is_type(X86_HYPER_XEN_PV)) - return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); + return sysfs_emit(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); break; case X86_BUG_SPECTRE_V1: - return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); + return sysfs_emit(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: return spectre_v2_show_state(buf); case X86_BUG_SPEC_STORE_BYPASS: - return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + return sysfs_emit(buf, "%s\n", ssb_strings[ssb_mode]); case X86_BUG_L1TF: if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) @@ -2750,11 +2922,14 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_SRSO: return srso_show_state(buf); + case X86_BUG_RFDS: + return rfds_show_state(buf); + default: break; } - return sprintf(buf, "Vulnerable\n"); + return sysfs_emit(buf, "Vulnerable\n"); } ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) @@ -2824,4 +2999,9 @@ ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribut { return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); } + +ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 01c4f8f45b83..664562389665 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1036,6 +1036,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SPECTRE_V2 BIT(8) #define NO_MMIO BIT(9) #define NO_EIBRS_PBRSB BIT(10) +#define NO_BHI BIT(11) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1096,18 +1097,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), {} }; @@ -1138,6 +1139,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define SRSO BIT(5) /* CPU is affected by GDS */ #define GDS BIT(6) +/* CPU is affected by Register File Data Sampling */ +#define RFDS BIT(7) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1165,9 +1168,18 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_N, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), @@ -1201,6 +1213,24 @@ static bool arch_cap_mmio_immune(u64 ia32_cap) ia32_cap & ARCH_CAP_SBDR_SSDP_NO); } +static bool __init vulnerable_to_rfds(u64 ia32_cap) +{ + /* The "immunity" bit trumps everything else: */ + if (ia32_cap & ARCH_CAP_RFDS_NO) + return false; + + /* + * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to + * indicate that mitigation is needed because guest is running on a + * vulnerable hardware or may migrate to such hardware: + */ + if (ia32_cap & ARCH_CAP_RFDS_CLEAR) + return true; + + /* Only consult the blacklist when there is no enumeration: */ + return cpu_matches(cpu_vuln_blacklist, RFDS); +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -1223,8 +1253,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); - if (ia32_cap & ARCH_CAP_IBRS_ALL) + /* + * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature + * flag and protect from vendor-specific bugs via the whitelist. + */ + if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); + if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && + !(ia32_cap & ARCH_CAP_PBRSB_NO)) + setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); + } if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { @@ -1286,11 +1324,6 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_RETBLEED); } - if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) && - !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && - !(ia32_cap & ARCH_CAP_PBRSB_NO)) - setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); - if (cpu_matches(cpu_vuln_blacklist, SMT_RSB)) setup_force_cpu_bug(X86_BUG_SMT_RSB); @@ -1309,6 +1342,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SRSO); } + if (vulnerable_to_rfds(ia32_cap)) + setup_force_cpu_bug(X86_BUG_RFDS); + + /* When virtualized, eIBRS could be hidden, assume vulnerable */ + if (!(ia32_cap & ARCH_CAP_BHI_NO) && + !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || + boot_cpu_has(X86_FEATURE_HYPERVISOR))) + setup_force_cpu_bug(X86_BUG_BHI); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index eb48729e220e..30d822c2e5c0 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2382,12 +2382,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return -EINVAL; b = &per_cpu(mce_banks_array, s->id)[bank]; - if (!b->init) return -ENODEV; b->ctl = new; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); return size; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 06bfef1c4175..0f5211087810 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, + { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 052ea7425c4d..893f040b97b7 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -463,50 +463,26 @@ static void kprobe_emulate_call(struct kprobe *p, struct pt_regs *regs) } NOKPROBE_SYMBOL(kprobe_emulate_call); -static nokprobe_inline -void __kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs, bool cond) +static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs) { unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; - if (cond) - ip += p->ainsn.rel32; + ip += p->ainsn.rel32; int3_emulate_jmp(regs, ip); } - -static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs) -{ - __kprobe_emulate_jmp(p, regs, true); -} NOKPROBE_SYMBOL(kprobe_emulate_jmp); -static const unsigned long jcc_mask[6] = { - [0] = X86_EFLAGS_OF, - [1] = X86_EFLAGS_CF, - [2] = X86_EFLAGS_ZF, - [3] = X86_EFLAGS_CF | X86_EFLAGS_ZF, - [4] = X86_EFLAGS_SF, - [5] = X86_EFLAGS_PF, -}; - static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs) { - bool invert = p->ainsn.jcc.type & 1; - bool match; + unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; - if (p->ainsn.jcc.type < 0xc) { - match = regs->flags & jcc_mask[p->ainsn.jcc.type >> 1]; - } else { - match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ - ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); - if (p->ainsn.jcc.type >= 0xe) - match = match || (regs->flags & X86_EFLAGS_ZF); - } - __kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert)); + int3_emulate_jcc(regs, p->ainsn.jcc.type, ip, p->ainsn.rel32); } NOKPROBE_SYMBOL(kprobe_emulate_jcc); static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs) { + unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; bool match; if (p->ainsn.loop.type != 3) { /* LOOP* */ @@ -534,7 +510,9 @@ static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs) else if (p->ainsn.loop.type == 1) /* LOOPE */ match = match && (regs->flags & X86_EFLAGS_ZF); - __kprobe_emulate_jmp(p, regs, match); + if (match) + ip += p->ainsn.rel32; + int3_emulate_jmp(regs, ip); } NOKPROBE_SYMBOL(kprobe_emulate_loop); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4bce802d25fb..b892fe7035db 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -519,9 +519,6 @@ 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(); } #if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index e25050c7ff1e..0e0221271e72 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -9,6 +9,7 @@ enum insn_type { NOP = 1, /* site cond-call */ JMP = 2, /* tramp / site tail-call */ RET = 3, /* tramp / site cond-tail-call */ + JCC = 4, }; /* @@ -25,12 +26,40 @@ static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; +static u8 __is_Jcc(u8 *insn) /* Jcc.d32 */ +{ + u8 ret = 0; + + if (insn[0] == 0x0f) { + u8 tmp = insn[1]; + if ((tmp & 0xf0) == 0x80) + ret = tmp; + } + + return ret; +} + +extern void __static_call_return(void); + +asm (".global __static_call_return\n\t" + ".type __static_call_return, @function\n\t" + ASM_FUNC_ALIGN "\n\t" + "__static_call_return:\n\t" + ANNOTATE_NOENDBR + ANNOTATE_RETPOLINE_SAFE + "ret; int3\n\t" + ".size __static_call_return, . - __static_call_return \n\t"); + static void __ref __static_call_transform(void *insn, enum insn_type type, void *func, bool modinit) { const void *emulate = NULL; int size = CALL_INSN_SIZE; const void *code; + u8 op, buf[6]; + + if ((type == JMP || type == RET) && (op = __is_Jcc(insn))) + type = JCC; switch (type) { case CALL: @@ -56,6 +85,20 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, else code = &retinsn; break; + + case JCC: + if (!func) { + func = __static_call_return; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + func = x86_return_thunk; + } + + buf[0] = 0x0f; + __text_gen_insn(buf+1, op, insn+1, func, 5); + code = buf; + size = 6; + + break; } if (memcmp(insn, code, size) == 0) @@ -67,13 +110,14 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, text_poke_bp(insn, code, size, emulate); } -static void __static_call_validate(void *insn, bool tail) +static void __static_call_validate(u8 *insn, bool tail) { - u8 opcode = *(u8 *)insn; + u8 opcode = insn[0]; if (tail) { if (opcode == JMP32_INSN_OPCODE || - opcode == RET_INSN_OPCODE) + opcode == RET_INSN_OPCODE || + __is_Jcc(insn)) return; } else { if (opcode == CALL_INSN_OPCODE || diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b939b94d931f..537e826205ce 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -355,9 +355,9 @@ static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf) } static __always_inline -void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask) +void kvm_cpu_cap_init_kvm_defined(enum kvm_only_cpuid_leafs leaf, u32 mask) { - /* Use kvm_cpu_cap_mask for non-scattered leafs. */ + /* Use kvm_cpu_cap_mask for leafs that aren't KVM-only. */ BUILD_BUG_ON(leaf < NCAPINTS); kvm_cpu_caps[leaf] = mask; @@ -367,7 +367,7 @@ void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask) static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) { - /* Use kvm_cpu_cap_init_scattered for scattered leafs. */ + /* Use kvm_cpu_cap_init_kvm_defined for KVM-only leafs. */ BUILD_BUG_ON(leaf >= NCAPINTS); kvm_cpu_caps[leaf] &= mask; @@ -469,11 +469,16 @@ void kvm_set_cpu_caps(void) F(AVX_VNNI) | F(AVX512_BF16) ); + kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, + F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) | + F(BHI_CTRL) | F(MCDT_NO) + ); + kvm_cpu_cap_mask(CPUID_D_1_EAX, F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) ); - kvm_cpu_cap_init_scattered(CPUID_12_EAX, + kvm_cpu_cap_init_kvm_defined(CPUID_12_EAX, SF(SGX1) | SF(SGX2) ); @@ -710,13 +715,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; /* function 7 has additional index. */ case 7: - entry->eax = min(entry->eax, 1u); + max_idx = entry->eax = min(entry->eax, 2u); cpuid_entry_override(entry, CPUID_7_0_EBX); cpuid_entry_override(entry, CPUID_7_ECX); cpuid_entry_override(entry, CPUID_7_EDX); - /* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */ - if (entry->eax == 1) { + /* KVM only supports up to 0x7.2, capped above via min(). */ + if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; @@ -726,6 +731,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ecx = 0; entry->edx = 0; } + if (max_idx >= 2) { + entry = do_host_cpuid(array, function, 2); + if (!entry) + goto out; + + cpuid_entry_override(entry, CPUID_7_2_EDX); + entry->ecx = 0; + entry->ebx = 0; + entry->eax = 0; + } break; case 0xa: { /* Architectural Performance Monitoring */ struct x86_pmu_capability cap; diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 7eeade35a425..e43909d6504a 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -7,23 +7,44 @@ #include <asm/cpufeatures.h> /* - * Hardware-defined CPUID leafs that are scattered in the kernel, but need to - * be directly used by KVM. Note, these word values conflict with the kernel's - * "bug" caps, but KVM doesn't use those. + * Hardware-defined CPUID leafs that are either scattered by the kernel or are + * unknown to the kernel, but need to be directly used by KVM. Note, these + * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. */ enum kvm_only_cpuid_leafs { CPUID_12_EAX = NCAPINTS, + CPUID_7_2_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, }; +/* + * Define a KVM-only feature flag. + * + * For features that are scattered by cpufeatures.h, __feature_translate() also + * needs to be updated to translate the kernel-defined feature into the + * KVM-defined feature. + * + * For features that are 100% KVM-only, i.e. not defined by cpufeatures.h, + * forego the intermediate KVM_X86_FEATURE and directly define X86_FEATURE_* so + * that X86_FEATURE_* can be used in KVM. No __feature_translate() handling is + * needed in this case. + */ #define KVM_X86_FEATURE(w, f) ((w)*32 + (f)) /* Intel-defined SGX sub-features, CPUID level 0x12 (EAX). */ #define KVM_X86_FEATURE_SGX1 KVM_X86_FEATURE(CPUID_12_EAX, 0) #define KVM_X86_FEATURE_SGX2 KVM_X86_FEATURE(CPUID_12_EAX, 1) +/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */ +#define X86_FEATURE_INTEL_PSFD KVM_X86_FEATURE(CPUID_7_2_EDX, 0) +#define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) +#define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) +#define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) +#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) + struct cpuid_reg { u32 function; u32 index; @@ -49,6 +70,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX}, [CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX}, [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, + [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, }; /* @@ -61,10 +83,12 @@ static const struct cpuid_reg reverse_cpuid[] = { */ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { + BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS); BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_5); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); } @@ -75,12 +99,17 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) */ static __always_inline u32 __feature_translate(int x86_feature) { - if (x86_feature == X86_FEATURE_SGX1) - return KVM_X86_FEATURE_SGX1; - else if (x86_feature == X86_FEATURE_SGX2) - return KVM_X86_FEATURE_SGX2; - - return x86_feature; +#define KVM_X86_TRANSLATE_FEATURE(f) \ + case X86_FEATURE_##f: return KVM_X86_FEATURE_##f + + switch (x86_feature) { + KVM_X86_TRANSLATE_FEATURE(SGX1); + KVM_X86_TRANSLATE_FEATURE(SGX2); + KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); + default: + return x86_feature; + } } static __always_inline u32 __feature_leaf(int x86_feature) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 93d73b55ae3e..0f3d29f83c58 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1662,20 +1662,22 @@ int svm_register_enc_region(struct kvm *kvm, goto e_free; } - region->uaddr = range->addr; - region->size = range->size; - - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are * flushed to ensure that guest data gets written into memory with - * correct C-bit. + * correct C-bit. Note, this must be done before dropping kvm->lock, + * as region and its array of pages can be freed by a different task + * once kvm->lock is released. */ sev_clflush_pages(region->pages, region->npages); + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + return ret; e_free: diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index edc3f16cc189..6a9bfdfbb6e5 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,7 +2,10 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H -#define VMX_RUN_VMRESUME (1 << 0) -#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) +#define VMX_RUN_VMRESUME_SHIFT 0 +#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 + +#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT) #endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 982138bebb70..ef61bd6d071f 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -77,7 +77,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - testb $VMX_RUN_VMRESUME, %bl + bt $VMX_RUN_VMRESUME_SHIFT, %bx /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -99,8 +99,11 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Check EFLAGS.ZF from 'testb' above */ - jz .Lvmlaunch + /* Clobbers EFLAGS.ZF */ + CLEAR_CPU_BUFFERS + + /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ + jnc .Lvmlaunch /* * After a successful VMRESUME/VMLAUNCH, control flow "magically" @@ -210,6 +213,8 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) call vmx_spec_ctrl_restore_host + CLEAR_BRANCH_HISTORY_VMEXIT + /* Put return value in AX */ mov %_ASM_BX, %_ASM_AX diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 89744ee06101..bedbd077e50e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -398,7 +398,8 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && + vmx_fb_clear_ctrl_available; /* * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS @@ -6747,11 +6748,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, { kvm_guest_enter_irqoff(); - /* L1D Flush includes CPU buffer clear to mitigate MDS */ + /* + * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW + * mitigation for MDS is done late in VMentry and is still + * executed in spite of L1D Flush. This is because an extra VERW + * should not matter much after the big hammer L1D Flush. + */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index aa6f700f8c5f..57a1484e257f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1498,7 +1498,8 @@ static unsigned int num_msr_based_features; ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1535,6 +1536,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + data |= ARCH_CAP_RFDS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -7105,7 +7108,17 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, } if (r < 0) - goto emul_write; + return X86EMUL_UNHANDLEABLE; + + /* + * Mark the page dirty _before_ checking whether or not the CMPXCHG was + * successful, as the old value is written back on failure. Note, for + * live migration, this is unnecessarily conservative as CMPXCHG writes + * back the original value and the access is atomic, but KVM's ABI is + * that all writes are dirty logged, regardless of the value written. + */ + kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa)); + if (r) return X86EMUL_CMPXCHG_FAILED; diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 6f5321b36dbb..019096b66eff 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -108,6 +108,7 @@ SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ret int3 SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) #endif SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) @@ -249,9 +250,7 @@ SYM_CODE_START(srso_return_thunk) SYM_CODE_END(srso_return_thunk) SYM_FUNC_START(entry_untrain_ret) - ALTERNATIVE_2 "jmp retbleed_untrain_ret", \ - "jmp srso_untrain_ret", X86_FEATURE_SRSO, \ - "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS + ALTERNATIVE "jmp retbleed_untrain_ret", "jmp srso_untrain_ret", X86_FEATURE_SRSO SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index f50cc210a981..968d7005f4a7 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, for (; addr < end; addr = next) { pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; - bool use_gbpage; next = (addr & PUD_MASK) + PUD_SIZE; if (next > end) next = end; - /* if this is already a gbpage, this portion is already mapped */ - if (pud_large(*pud)) - continue; - - /* Is using a gbpage allowed? */ - use_gbpage = info->direct_gbpages; - - /* Don't use gbpage if it maps more than the requested region. */ - /* at the begining: */ - use_gbpage &= ((addr & ~PUD_MASK) == 0); - /* ... or at the end: */ - use_gbpage &= ((next & ~PUD_MASK) == 0); - - /* Never overwrite existing mappings */ - use_gbpage &= !pud_present(*pud); - - if (use_gbpage) { + if (info->direct_gbpages) { pud_t pudval; + if (pud_present(*pud)) + continue; + + addr &= PUD_MASK; pudval = __pud((addr - info->offset) | info->page_flag); set_pud(pud, pudval); continue; diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index d5ef64ddd35e..f6466022954b 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -989,6 +989,38 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, + pgprot_t *pgprot) +{ + unsigned long prot; + + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); + + /* + * We need the starting PFN and cachemode used for track_pfn_remap() + * that covered the whole VMA. For most mappings, we can obtain that + * information from the page tables. For COW mappings, we might now + * suddenly have anon folios mapped and follow_phys() will fail. + * + * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to + * detect the PFN. If we need the cachemode as well, we're out of luck + * for now and have to fail fork(). + */ + if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (pgprot) + *pgprot = __pgprot(prot); + return 0; + } + if (is_cow_mapping(vma->vm_flags)) { + if (pgprot) + return -EINVAL; + *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; + return 0; + } + WARN_ON_ONCE(1); + return -EINVAL; +} + /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). @@ -999,20 +1031,13 @@ static void free_pfn_range(u64 paddr, unsigned long size) int track_pfn_copy(struct vm_area_struct *vma) { resource_size_t paddr; - unsigned long prot; unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (vma->vm_flags & VM_PAT) { - /* - * reserve the whole chunk covered by vma. We need the - * starting address and protection from pte. - */ - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, &pgprot)) return -EINVAL; - } - pgprot = __pgprot(prot); + /* reserve the whole chunk covered by vma. */ return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } @@ -1087,7 +1112,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size) { resource_size_t paddr; - unsigned long prot; if (vma && !(vma->vm_flags & VM_PAT)) return; @@ -1095,11 +1119,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, /* free the chunk starting from pfn or the whole chunk */ paddr = (resource_size_t)pfn << PAGE_SHIFT; if (!paddr && !size) { - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, NULL)) return; - } - size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); |