diff options
Diffstat (limited to 'arch/x86')
78 files changed, 1574 insertions, 616 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 00fcf81f2c56..f2ee6a8ffe65 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -28,6 +28,8 @@ config X86_64 select ARCH_USE_CMPXCHG_LOCKREF select HAVE_ARCH_SOFT_DIRTY select MODULES_USE_ELF_RELA + select NEED_DMA_MAP_STATE + select SWIOTLB select X86_DEV_DMA_OPS select ARCH_HAS_SYSCALL_WRAPPER @@ -52,6 +54,7 @@ config X86 select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER + select ARCH_HAS_FILTER_PGPROT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 @@ -133,7 +136,6 @@ config X86 select HAVE_C_RECORDMCOUNT select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_STACKOVERFLOW - select HAVE_DMA_API_DEBUG select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS @@ -183,6 +185,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER select IRQ_FORCED_THREADING + select NEED_SG_DMA_LENGTH select PCI_LOCKLESS_CONFIG select PERF_EVENTS select RTC_LIB @@ -235,13 +238,6 @@ config ARCH_MMAP_RND_COMPAT_BITS_MAX config SBUS bool -config NEED_DMA_MAP_STATE - def_bool y - depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB - -config NEED_SG_DMA_LENGTH - def_bool y - config GENERIC_ISA_DMA def_bool y depends on ISA_DMA_API @@ -273,6 +269,9 @@ config ARCH_HAS_CPU_RELAX config ARCH_HAS_CACHE_LINE_SIZE def_bool y +config ARCH_HAS_FILTER_PGPROT + def_bool y + config HAVE_SETUP_PER_CPU_AREA def_bool y @@ -871,6 +870,7 @@ config DMI config GART_IOMMU bool "Old AMD GART IOMMU support" + select IOMMU_HELPER select SWIOTLB depends on X86_64 && PCI && AMD_NB ---help--- @@ -892,6 +892,7 @@ config GART_IOMMU config CALGARY_IOMMU bool "IBM Calgary IOMMU support" + select IOMMU_HELPER select SWIOTLB depends on X86_64 && PCI ---help--- @@ -919,20 +920,6 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT Calgary anyway, pass 'iommu=calgary' on the kernel command line. If unsure, say Y. -# need this always selected by IOMMU for the VIA workaround -config SWIOTLB - def_bool y if X86_64 - ---help--- - Support for software bounce buffers used on x86-64 systems - which don't have a hardware IOMMU. Using this PCI devices - which can only access 32-bits of memory can be used on systems - with more than 3 GB of memory. - If unsure, say Y. - -config IOMMU_HELPER - def_bool y - depends on CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU - config MAXSMP bool "Enable Maximum number of SMP Processors and NUMA Nodes" depends on X86_64 && SMP && DEBUG_KERNEL @@ -1454,6 +1441,7 @@ config HIGHMEM config X86_PAE bool "PAE (Physical Address Extension) Support" depends on X86_32 && !HIGHMEM4G + select PHYS_ADDR_T_64BIT select SWIOTLB ---help--- PAE is required for NX support, and furthermore enables @@ -1481,14 +1469,6 @@ config X86_5LEVEL Say N if unsure. -config ARCH_PHYS_ADDR_T_64BIT - def_bool y - depends on X86_64 || X86_PAE - -config ARCH_DMA_ADDR_T_64BIT - def_bool y - depends on X86_64 || HIGHMEM64G - config X86_DIRECT_GBPAGES def_bool y depends on X86_64 && !DEBUG_PAGEALLOC diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 47d3efff6805..09f36c0d9d4f 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -163,7 +163,8 @@ __setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom) if (status != EFI_SUCCESS) goto free_struct; - memcpy(rom->romdata, pci->romimage, pci->romsize); + memcpy(rom->romdata, (void *)(unsigned long)pci->romimage, + pci->romsize); return status; free_struct: @@ -269,7 +270,8 @@ __setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom) if (status != EFI_SUCCESS) goto free_struct; - memcpy(rom->romdata, pci->romimage, pci->romsize); + memcpy(rom->romdata, (void *)(unsigned long)pci->romimage, + pci->romsize); return status; free_struct: diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index fca012baba19..8169e8b7a4dc 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -306,6 +306,25 @@ ENTRY(startup_64) leaq boot_stack_end(%rbx), %rsp /* + * paging_prepare() and cleanup_trampoline() below can have GOT + * references. Adjust the table with address we are running at. + * + * Zero RAX for adjust_got: the GOT was not adjusted before; + * there's no adjustment to undo. + */ + xorq %rax, %rax + + /* + * Calculate the address the binary is loaded at and use it as + * a GOT adjustment. + */ + call 1f +1: popq %rdi + subq $1b, %rdi + + call adjust_got + + /* * At this point we are in long mode with 4-level paging enabled, * but we might want to enable 5-level paging or vice versa. * @@ -370,10 +389,14 @@ trampoline_return: /* * cleanup_trampoline() would restore trampoline memory. * + * RDI is address of the page table to use instead of page table + * in trampoline memory (if required). + * * RSI holds real mode data and needs to be preserved across * this function call. */ pushq %rsi + leaq top_pgtable(%rbx), %rdi call cleanup_trampoline popq %rsi @@ -381,6 +404,21 @@ trampoline_return: pushq $0 popfq + /* + * Previously we've adjusted the GOT with address the binary was + * loaded at. Now we need to re-adjust for relocation address. + * + * Calculate the address the binary is loaded at, so that we can + * undo the previous GOT adjustment. + */ + call 1f +1: popq %rax + subq $1b, %rax + + /* The new adjustment is the relocation address */ + movq %rbx, %rdi + call adjust_got + /* * Copy the compressed kernel to the end of our buffer * where decompression in place becomes safe. @@ -482,19 +520,6 @@ relocated: rep stosq /* - * Adjust our own GOT - */ - leaq _got(%rip), %rdx - leaq _egot(%rip), %rcx -1: - cmpq %rcx, %rdx - jae 2f - addq %rbx, (%rdx) - addq $8, %rdx - jmp 1b -2: - -/* * Do the extraction, and jump to the new kernel.. */ pushq %rsi /* Save the real mode argument */ @@ -512,6 +537,27 @@ relocated: */ jmp *%rax +/* + * Adjust the global offset table + * + * RAX is the previous adjustment of the table to undo (use 0 if it's the + * first time we touch GOT). + * RDI is the new adjustment to apply. + */ +adjust_got: + /* Walk through the GOT adding the address to the entries */ + leaq _got(%rip), %rdx + leaq _egot(%rip), %rcx +1: + cmpq %rcx, %rdx + jae 2f + subq %rax, (%rdx) /* Undo previous adjustment */ + addq %rdi, (%rdx) /* Apply the new adjustment */ + addq $8, %rdx + jmp 1b +2: + ret + .code32 /* * This is the 32-bit trampoline that will be copied over to low memory. @@ -649,3 +695,10 @@ boot_stack_end: .balign 4096 pgtable: .fill BOOT_PGT_SIZE, 1, 0 + +/* + * The page table is going to be used instead of page table in the trampoline + * memory. + */ +top_pgtable: + .fill PAGE_SIZE, 1, 0 diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 32af1cbcd903..a362fa0b849c 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -23,14 +23,6 @@ struct paging_config { static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; /* - * The page table is going to be used instead of page table in the trampoline - * memory. - * - * It must not be in BSS as BSS is cleared after cleanup_trampoline(). - */ -static char top_pgtable[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data); - -/* * Trampoline address will be printed by extract_kernel() for debugging * purposes. * @@ -134,7 +126,7 @@ out: return paging_config; } -void cleanup_trampoline(void) +void cleanup_trampoline(void *pgtable) { void *trampoline_pgtable; @@ -145,8 +137,8 @@ void cleanup_trampoline(void) * if it's there. */ if ((void *)__native_read_cr3() == trampoline_pgtable) { - memcpy(top_pgtable, trampoline_pgtable, PAGE_SIZE); - native_write_cr3((unsigned long)top_pgtable); + memcpy(pgtable, trampoline_pgtable, PAGE_SIZE); + native_write_cr3((unsigned long)pgtable); } /* Restore trampoline memory */ diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 9af927e59d49..9de7f1e1dede 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -84,13 +84,13 @@ ENTRY(entry_SYSENTER_compat) pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ - pushq $0 /* pt_regs->r8 = 0 */ + pushq %r8 /* pt_regs->r8 */ xorl %r8d, %r8d /* nospec r8 */ - pushq $0 /* pt_regs->r9 = 0 */ + pushq %r9 /* pt_regs->r9 */ xorl %r9d, %r9d /* nospec r9 */ - pushq $0 /* pt_regs->r10 = 0 */ + pushq %r10 /* pt_regs->r10 */ xorl %r10d, %r10d /* nospec r10 */ - pushq $0 /* pt_regs->r11 = 0 */ + pushq %r11 /* pt_regs->r11 */ xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ diff --git a/arch/x86/entry/vdso/vdso32/vdso-fakesections.c b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c deleted file mode 100644 index 541468e25265..000000000000 --- a/arch/x86/entry/vdso/vdso32/vdso-fakesections.c +++ /dev/null @@ -1 +0,0 @@ -#include "../vdso-fakesections.c" diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index a6006e7bb729..45b2b1c93d04 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -27,6 +27,7 @@ #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/device.h> +#include <linux/nospec.h> #include <asm/apic.h> #include <asm/stacktrace.h> @@ -304,17 +305,20 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) config = attr->config; - cache_type = (config >> 0) & 0xff; + cache_type = (config >> 0) & 0xff; if (cache_type >= PERF_COUNT_HW_CACHE_MAX) return -EINVAL; + cache_type = array_index_nospec(cache_type, PERF_COUNT_HW_CACHE_MAX); cache_op = (config >> 8) & 0xff; if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) return -EINVAL; + cache_op = array_index_nospec(cache_op, PERF_COUNT_HW_CACHE_OP_MAX); cache_result = (config >> 16) & 0xff; if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) return -EINVAL; + cache_result = array_index_nospec(cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX); val = hw_cache_event_ids[cache_type][cache_op][cache_result]; @@ -421,6 +425,8 @@ int x86_setup_perfctr(struct perf_event *event) if (attr->config >= x86_pmu.max_events) return -EINVAL; + attr->config = array_index_nospec((unsigned long)attr->config, x86_pmu.max_events); + /* * The generic map: */ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 607bf565a90c..707b2a96e516 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3339,7 +3339,8 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = NULL; - flip_smm_bit(&x86_pmu.attr_freeze_on_smi); + if (x86_pmu.version > 1) + flip_smm_bit(&x86_pmu.attr_freeze_on_smi); if (!cpuc->shared_regs) return; @@ -3502,6 +3503,8 @@ static __initconst const struct x86_pmu core_pmu = { .cpu_dying = intel_pmu_cpu_dying, }; +static struct attribute *intel_pmu_attrs[]; + static __initconst const struct x86_pmu intel_pmu = { .name = "Intel", .handle_irq = intel_pmu_handle_irq, @@ -3533,6 +3536,8 @@ static __initconst const struct x86_pmu intel_pmu = { .format_attrs = intel_arch3_formats_attr, .events_sysfs_show = intel_event_sysfs_show, + .attrs = intel_pmu_attrs, + .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, @@ -3911,8 +3916,6 @@ __init int intel_pmu_init(void) x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters); - - x86_pmu.attrs = intel_pmu_attrs; /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events, when not running in a hypervisor: diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 9aca448bb8e6..9f8084f18d58 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -92,6 +92,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/perf_event.h> +#include <linux/nospec.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include "../perf_event.h" @@ -302,6 +303,7 @@ static int cstate_pmu_event_init(struct perf_event *event) } else if (event->pmu == &cstate_pkg_pmu) { if (cfg >= PERF_CSTATE_PKG_EVENT_MAX) return -EINVAL; + cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX); if (!pkg_msr[cfg].attr) return -EINVAL; event->hw.event_base = pkg_msr[cfg].msr; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index c98b943e58b4..77076a102e34 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3028,10 +3028,27 @@ static struct intel_uncore_type bdx_uncore_cbox = { .format_group = &hswep_uncore_cbox_format_group, }; +static struct intel_uncore_type bdx_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_S0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_SBOX_MSR_OFFSET, + .ops = &hswep_uncore_sbox_msr_ops, + .format_group = &hswep_uncore_sbox_format_group, +}; + +#define BDX_MSR_UNCORE_SBOX 3 + static struct intel_uncore_type *bdx_msr_uncores[] = { &bdx_uncore_ubox, &bdx_uncore_cbox, &hswep_uncore_pcu, + &bdx_uncore_sbox, NULL, }; @@ -3043,10 +3060,25 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = { void bdx_uncore_cpu_init(void) { + int pkg = topology_phys_to_logical_pkg(0); + if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; uncore_msr_uncores = bdx_msr_uncores; + /* BDX-DE doesn't have SBOX */ + if (boot_cpu_data.x86_model == 86) { + uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; + /* Detect systems with no SBOXes */ + } else if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) { + struct pci_dev *pdev; + u32 capid4; + + pdev = uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]; + pci_read_config_dword(pdev, 0x94, &capid4); + if (((capid4 >> 6) & 0x3) == 0) + bdx_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; + } hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints; } @@ -3264,6 +3296,11 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), }, + { /* PCU.3 (for Capability registers) */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + HSWEP_PCI_PCU_3), + }, { /* end: all zeroes */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index e7edf19e64c2..b4771a6ddbc1 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/perf_event.h> +#include <linux/nospec.h> #include <asm/intel-family.h> enum perf_msr_id { @@ -158,9 +159,6 @@ static int msr_event_init(struct perf_event *event) if (event->attr.type != event->pmu->type) return -ENOENT; - if (cfg >= PERF_MSR_EVENT_MAX) - return -EINVAL; - /* unsupported modes and filters */ if (event->attr.exclude_user || event->attr.exclude_kernel || @@ -171,6 +169,11 @@ static int msr_event_init(struct perf_event *event) event->attr.sample_period) /* no sampling */ return -EINVAL; + if (cfg >= PERF_MSR_EVENT_MAX) + return -EINVAL; + + cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX); + if (!msr[cfg].attr) return -EINVAL; diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 386a6900e206..219faaec51df 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -136,7 +136,6 @@ #endif #ifndef __ASSEMBLY__ -#ifndef __BPF__ /* * This output constraint should be used for any inline asm which has a "call" * instruction. Otherwise the asm may be inserted before the frame pointer @@ -146,6 +145,5 @@ register unsigned long current_stack_pointer asm(_ASM_SP); #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) #endif -#endif #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index b27da9602a6d..aced6c9290d6 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -140,6 +140,20 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) +#if defined(__clang__) && !defined(CC_HAVE_ASM_GOTO) + +/* + * Workaround for the sake of BPF compilation which utilizes kernel + * headers, but clang does not support ASM GOTO and fails the build. + */ +#ifndef __BPF_TRACING__ +#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments" +#endif + +#define static_cpu_has(bit) boot_cpu_has(bit) + +#else + /* * Static testing of CPU features. Used the same as boot_cpu_has(). * These will statically patch the target code for additional @@ -195,6 +209,7 @@ t_no: boot_cpu_has(bit) : \ _static_cpu_has(bit) \ ) +#endif #define cpu_has_bug(c, bit) cpu_has(c, (bit)) #define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index d554c11e01ff..fb00a2fca990 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -198,7 +198,6 @@ #define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ #define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ - #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ @@ -207,13 +206,19 @@ #define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ - +#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ +#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ - #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ +#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ +#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */ +#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -274,9 +279,10 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ -#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ -#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ -#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ +#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ +#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -320,6 +326,7 @@ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ +#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ @@ -333,6 +340,7 @@ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ /* * BUG word(s) @@ -362,5 +370,6 @@ #define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ #define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ #define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ +#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 89ce4bfd241f..ce4d176b3d13 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -30,10 +30,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) return dma_ops; } -int arch_dma_supported(struct device *dev, u64 mask); -#define arch_dma_supported arch_dma_supported - -bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp); +bool arch_dma_alloc_attrs(struct device **dev); #define arch_dma_alloc_attrs arch_dma_alloc_attrs #endif diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 09ad88572746..cc8f8fcf9b4a 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -46,7 +46,21 @@ int ftrace_int3_handler(struct pt_regs *regs); #endif /* CONFIG_FUNCTION_TRACER */ -#if !defined(__ASSEMBLY__) && !defined(COMPILE_OFFSETS) +#ifndef __ASSEMBLY__ + +#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME +static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) +{ + /* + * Compare the symbol name with the system call name. Skip the + * "__x64_sys", "__ia32_sys" or simple "sys" prefix. + */ + return !strcmp(sym + 3, name + 3) || + (!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) || + (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)); +} + +#ifndef COMPILE_OFFSETS #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_IA32_EMULATION) #include <asm/compat.h> @@ -67,6 +81,7 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) return false; } #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */ -#endif /* !__ASSEMBLY__ && !COMPILE_OFFSETS */ +#endif /* !COMPILE_OFFSETS */ +#endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_FTRACE_H */ diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index b3e32b010ab1..c2c01f84df75 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +#define POP_SS_OPCODE 0x1f +#define MOV_SREG_OPCODE 0x8e + +/* + * Intel SDM Vol.3A 6.8.3 states; + * "Any single-step trap that would be delivered following the MOV to SS + * instruction or POP to SS instruction (because EFLAGS.TF is 1) is + * suppressed." + * This function returns true if @insn is MOV SS or POP SS. On these + * instructions, single stepping is suppressed. + */ +static inline int insn_masking_exception(struct insn *insn) +{ + return insn->opcode.bytes[0] == POP_SS_OPCODE || + (insn->opcode.bytes[0] == MOV_SREG_OPCODE && + X86_MODRM_REG(insn->modrm.bytes[0]) == 2); +} + #endif /* _ASM_X86_INSN_H */ diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 404c5fdff859..548d90bbf919 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -34,11 +34,6 @@ * (0x80 is the syscall vector, 0x30-0x3f are for ISA) */ #define FIRST_EXTERNAL_VECTOR 0x20 -/* - * We start allocating at 0x21 to spread out vectors evenly between - * priority levels. (0x80 is the syscall vector) - */ -#define VECTOR_OFFSET_START 1 /* * Reserve the lowest usable vector (and hence lowest priority) 0x20 for @@ -119,8 +114,6 @@ #define FIRST_SYSTEM_VECTOR NR_VECTORS #endif -#define FPU_IRQ 13 - /* * Size the maximum number of interrupts. * diff --git a/arch/x86/include/asm/jailhouse_para.h b/arch/x86/include/asm/jailhouse_para.h index b885a961a150..a34897aef2c2 100644 --- a/arch/x86/include/asm/jailhouse_para.h +++ b/arch/x86/include/asm/jailhouse_para.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL2.0 */ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Jailhouse paravirt detection diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 949c977bc4c9..f4b2588865e9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -924,7 +924,7 @@ struct kvm_x86_ops { int (*hardware_setup)(void); /* __init */ void (*hardware_unsetup)(void); /* __exit */ bool (*cpu_has_accelerated_tpr)(void); - bool (*cpu_has_high_real_mode_segbase)(void); + bool (*has_emulated_msr)(int index); void (*cpuid_update)(struct kvm_vcpu *vcpu); struct kvm *(*vm_alloc)(void); @@ -1013,6 +1013,7 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); + u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 57e3785d0d26..cf9911b5a53c 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -193,7 +193,7 @@ static inline int init_new_context(struct task_struct *tsk, #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { - /* pkey 0 is the default and always allocated */ + /* pkey 0 is the default and allocated implicitly */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 53d5b1b9255e..fda2114197b3 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -42,6 +42,8 @@ #define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ #define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ #define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */ +#define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ +#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ @@ -68,6 +70,11 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */ +#define ARCH_CAP_SSB_NO (1 << 4) /* + * Not susceptible to Speculative Store Bypass + * attack, so no Speculative Store Bypass + * control required. + */ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e @@ -340,6 +347,8 @@ #define MSR_AMD64_SEV_ENABLED_BIT 0 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f928ad9b143f..8b38df98548e 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -217,6 +217,14 @@ enum spectre_v2_mitigation { SPECTRE_V2_IBRS, }; +/* The Speculative Store Bypass disable variants */ +enum ssb_mitigation { + SPEC_STORE_BYPASS_NONE, + SPEC_STORE_BYPASS_DISABLE, + SPEC_STORE_BYPASS_PRCTL, + SPEC_STORE_BYPASS_SECCOMP, +}; + extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; @@ -241,22 +249,27 @@ static inline void vmexit_fill_RSB(void) #endif } -#define alternative_msr_write(_msr, _val, _feature) \ - asm volatile(ALTERNATIVE("", \ - "movl %[msr], %%ecx\n\t" \ - "movl %[val], %%eax\n\t" \ - "movl $0, %%edx\n\t" \ - "wrmsr", \ - _feature) \ - : : [msr] "i" (_msr), [val] "i" (_val) \ - : "eax", "ecx", "edx", "memory") +static __always_inline +void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) +{ + asm volatile(ALTERNATIVE("", "wrmsr", %c[feature]) + : : "c" (msr), + "a" ((u32)val), + "d" ((u32)(val >> 32)), + [feature] "i" (feature) + : "memory"); +} static inline void indirect_branch_prediction_barrier(void) { - alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, - X86_FEATURE_USE_IBPB); + u64 val = PRED_CMD_IBPB; + + alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); } +/* The Intel SPEC CTRL MSR base value cache */ +extern u64 x86_spec_ctrl_base; + /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. @@ -265,14 +278,18 @@ static inline void indirect_branch_prediction_barrier(void) */ #define firmware_restrict_branch_speculation_start() \ do { \ + u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS; \ + \ preempt_disable(); \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ X86_FEATURE_USE_IBRS_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ do { \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \ + u64 val = x86_spec_ctrl_base; \ + \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index d32175e30259..662963681ea6 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -117,9 +117,6 @@ void native_restore_msi_irqs(struct pci_dev *dev); #define native_setup_msi_irqs NULL #define native_teardown_msi_irq NULL #endif - -#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) - #endif /* __KERNEL__ */ #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5f49b4ff0c24..f1633de5a675 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -601,6 +601,11 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) +static inline pgprot_t arch_filter_pgprot(pgprot_t prot) +{ + return canon_pgprot(prot); +} + static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, enum page_cache_mode pcm, enum page_cache_mode new_pcm) diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index d5c21a382475..adb47552e6bb 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -105,14 +105,14 @@ extern unsigned int ptrs_per_p4d; #define LDT_PGD_ENTRY (pgtable_l5_enabled ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4) #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) -#define __VMALLOC_BASE_L4 0xffffc90000000000 -#define __VMALLOC_BASE_L5 0xffa0000000000000 +#define __VMALLOC_BASE_L4 0xffffc90000000000UL +#define __VMALLOC_BASE_L5 0xffa0000000000000UL #define VMALLOC_SIZE_TB_L4 32UL #define VMALLOC_SIZE_TB_L5 12800UL -#define __VMEMMAP_BASE_L4 0xffffea0000000000 -#define __VMEMMAP_BASE_L5 0xffd4000000000000 +#define __VMEMMAP_BASE_L4 0xffffea0000000000UL +#define __VMEMMAP_BASE_L5 0xffd4000000000000UL #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT # define VMALLOC_START vmalloc_base diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index a0ba1ffda0df..851c04b7a092 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H +#define ARCH_DEFAULT_PKEY 0 + #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, @@ -15,7 +17,7 @@ extern int __execute_only_pkey(struct mm_struct *mm); static inline int execute_only_pkey(struct mm_struct *mm) { if (!boot_cpu_has(X86_FEATURE_OSPKE)) - return 0; + return ARCH_DEFAULT_PKEY; return __execute_only_pkey(mm); } @@ -49,13 +51,21 @@ bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { /* * "Allocated" pkeys are those that have been returned - * from pkey_alloc(). pkey 0 is special, and never - * returned from pkey_alloc(). + * from pkey_alloc() or pkey 0 which is allocated + * implicitly when the mm is created. */ - if (pkey <= 0) + if (pkey < 0) return false; if (pkey >= arch_max_pkey()) return false; + /* + * The exec-only pkey is set in the allocation map, but + * is not available to any of the user interfaces like + * mprotect_pkey(). + */ + if (pkey == mm->context.execute_only_pkey) + return false; + return mm_pkey_allocation_map(mm) & (1U << pkey); } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 4fa4206029e3..21a114914ba4 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -749,13 +749,11 @@ enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT, extern void enable_sep_cpu(void); extern int sysenter_setup(void); -extern void early_trap_init(void); void early_trap_pf_init(void); /* Defined in head.S */ extern struct desc_ptr early_gdt_descr; -extern void cpu_set_gdt(int); extern void switch_to_new_gdt(int); extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h new file mode 100644 index 000000000000..ae7c2c5cd7f0 --- /dev/null +++ b/arch/x86/include/asm/spec-ctrl.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SPECCTRL_H_ +#define _ASM_X86_SPECCTRL_H_ + +#include <linux/thread_info.h> +#include <asm/nospec-branch.h> + +/* + * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR + * the guest has, while on VMEXIT we restore the host view. This + * would be easier if SPEC_CTRL were architecturally maskable or + * shadowable for guests but this is not (currently) the case. + * Takes the guest view of SPEC_CTRL MSR as a parameter and also + * the guest's version of VIRT_SPEC_CTRL, if emulated. + */ +extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool guest); + +/** + * x86_spec_ctrl_set_guest - Set speculation control registers for the guest + * @guest_spec_ctrl: The guest content of MSR_SPEC_CTRL + * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL + * (may get translated to MSR_AMD64_LS_CFG bits) + * + * Avoids writing to the MSR if the content/bits are the same + */ +static inline +void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) +{ + x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, true); +} + +/** + * x86_spec_ctrl_restore_host - Restore host speculation control registers + * @guest_spec_ctrl: The guest content of MSR_SPEC_CTRL + * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL + * (may get translated to MSR_AMD64_LS_CFG bits) + * + * Avoids writing to the MSR if the content/bits are the same + */ +static inline +void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) +{ + x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, false); +} + +/* AMD specific Speculative Store Bypass MSR data */ +extern u64 x86_amd_ls_cfg_base; +extern u64 x86_amd_ls_cfg_ssbd_mask; + +static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn) +{ + BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT); + return (tifn & _TIF_SSBD) >> (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); +} + +static inline unsigned long ssbd_spec_ctrl_to_tif(u64 spec_ctrl) +{ + BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT); + return (spec_ctrl & SPEC_CTRL_SSBD) << (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); +} + +static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn) +{ + return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL; +} + +#ifdef CONFIG_SMP +extern void speculative_store_bypass_ht_init(void); +#else +static inline void speculative_store_bypass_ht_init(void) { } +#endif + +extern void speculative_store_bypass_update(unsigned long tif); + +static inline void speculative_store_bypass_update_current(void) +{ + speculative_store_bypass_update(current_thread_info()->flags); +} + +#endif diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index a5d9521bb2cb..2ff2a30a264f 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -79,6 +79,7 @@ struct thread_info { #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/ +#define TIF_SSBD 5 /* Reduced data speculation */ #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ @@ -105,6 +106,7 @@ struct thread_info { #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_SSBD (1 << TIF_SSBD) #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) @@ -144,7 +146,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP) + (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP|_TIF_SSBD) #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 4c851ebb3ceb..0ede697c3961 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -29,7 +29,7 @@ #define KVM_FEATURE_PV_TLB_FLUSH 9 #define KVM_FEATURE_ASYNC_PF_VMEXIT 10 -#define KVM_HINTS_DEDICATED 0 +#define KVM_HINTS_REALTIME 0 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. diff --git a/arch/x86/include/uapi/asm/msgbuf.h b/arch/x86/include/uapi/asm/msgbuf.h index 809134c644a6..90ab9a795b49 100644 --- a/arch/x86/include/uapi/asm/msgbuf.h +++ b/arch/x86/include/uapi/asm/msgbuf.h @@ -1 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_X64_MSGBUF_H +#define __ASM_X64_MSGBUF_H + +#if !defined(__x86_64__) || !defined(__ILP32__) #include <asm-generic/msgbuf.h> +#else +/* + * The msqid64_ds structure for x86 architecture with x32 ABI. + * + * On x86-32 and x86-64 we can just use the generic definition, but + * x32 uses the same binary layout as x86_64, which is differnet + * from other 32-bit architectures. + */ + +struct msqid64_ds { + struct ipc64_perm msg_perm; + __kernel_time_t msg_stime; /* last msgsnd time */ + __kernel_time_t msg_rtime; /* last msgrcv time */ + __kernel_time_t msg_ctime; /* last change time */ + __kernel_ulong_t msg_cbytes; /* current number of bytes on queue */ + __kernel_ulong_t msg_qnum; /* number of messages in queue */ + __kernel_ulong_t msg_qbytes; /* max number of bytes on queue */ + __kernel_pid_t msg_lspid; /* pid of last msgsnd */ + __kernel_pid_t msg_lrpid; /* last receive pid */ + __kernel_ulong_t __unused4; + __kernel_ulong_t __unused5; +}; + +#endif + +#endif /* __ASM_GENERIC_MSGBUF_H */ diff --git a/arch/x86/include/uapi/asm/shmbuf.h b/arch/x86/include/uapi/asm/shmbuf.h index 83c05fc2de38..644421f3823b 100644 --- a/arch/x86/include/uapi/asm/shmbuf.h +++ b/arch/x86/include/uapi/asm/shmbuf.h @@ -1 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_X86_SHMBUF_H +#define __ASM_X86_SHMBUF_H + +#if !defined(__x86_64__) || !defined(__ILP32__) #include <asm-generic/shmbuf.h> +#else +/* + * The shmid64_ds structure for x86 architecture with x32 ABI. + * + * On x86-32 and x86-64 we can just use the generic definition, but + * x32 uses the same binary layout as x86_64, which is differnet + * from other 32-bit architectures. + */ + +struct shmid64_ds { + struct ipc64_perm shm_perm; /* operation perms */ + size_t shm_segsz; /* size of segment (bytes) */ + __kernel_time_t shm_atime; /* last attach time */ + __kernel_time_t shm_dtime; /* last detach time */ + __kernel_time_t shm_ctime; /* last change time */ + __kernel_pid_t shm_cpid; /* pid of creator */ + __kernel_pid_t shm_lpid; /* pid of last operator */ + __kernel_ulong_t shm_nattch; /* no. of current attaches */ + __kernel_ulong_t __unused4; + __kernel_ulong_t __unused5; +}; + +struct shminfo64 { + __kernel_ulong_t shmmax; + __kernel_ulong_t shmmin; + __kernel_ulong_t shmmni; + __kernel_ulong_t shmseg; + __kernel_ulong_t shmall; + __kernel_ulong_t __unused1; + __kernel_ulong_t __unused2; + __kernel_ulong_t __unused3; + __kernel_ulong_t __unused4; +}; + +#endif + +#endif /* __ASM_X86_SHMBUF_H */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index dde444f932c1..3b20607d581b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -215,6 +215,10 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) apic_id = processor->local_apic_id; enabled = processor->lapic_flags & ACPI_MADT_ENABLED; + /* Ignore invalid ID */ + if (apic_id == 0xffffffff) + return 0; + /* * We need to register disabled CPU as well to permit * counting disabled CPUs. This allows us to size diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index c88e0b127810..b481b95bd8f6 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -14,8 +14,11 @@ #include <asm/amd_nb.h> #define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 +#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -24,6 +27,7 @@ static u32 *flush_words; static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, {} }; @@ -39,6 +43,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, {} }; @@ -51,6 +56,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 8b04234e010b..7685444a106b 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -116,6 +116,7 @@ static void init_x2apic_ldr(void) goto update; } cmsk = cluster_hotplug_mask; + cmsk->clusterid = cluster; cluster_hotplug_mask = NULL; update: this_cpu_write(cluster_masks, cmsk); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index dfcbe6924eaf..cadeafabf167 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1715,19 +1715,6 @@ static int proc_apm_show(struct seq_file *m, void *v) return 0; } -static int proc_apm_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_apm_show, NULL); -} - -static const struct file_operations apm_file_ops = { - .owner = THIS_MODULE, - .open = proc_apm_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int apm(void *unused) { unsigned short bx; @@ -2360,7 +2347,7 @@ static int __init apm_init(void) set_desc_base(&gdt[APM_DS >> 3], (unsigned long)__va((unsigned long)apm_info.bios.dseg << 4)); - proc_create("apm", 0, NULL, &apm_file_ops); + proc_create_single("apm", 0, NULL, proc_apm_show); kapmd_task = kthread_create(apm, NULL, "kapmd"); if (IS_ERR(kapmd_task)) { diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 12bc0a1139da..1b18be3f35a8 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -10,6 +10,7 @@ #include <asm/processor.h> #include <asm/apic.h> #include <asm/cpu.h> +#include <asm/spec-ctrl.h> #include <asm/smp.h> #include <asm/pci-direct.h> #include <asm/delay.h> @@ -554,6 +555,26 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) rdmsrl(MSR_FAM10H_NODE_ID, value); nodes_per_socket = ((value >> 3) & 7) + 1; } + + if (c->x86 >= 0x15 && c->x86 <= 0x17) { + unsigned int bit; + + switch (c->x86) { + case 0x15: bit = 54; break; + case 0x16: bit = 33; break; + case 0x17: bit = 10; break; + default: return; + } + /* + * Try to cache the base value so further operations can + * avoid RMW. If that faults, do not enable SSBD. + */ + if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) { + setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD); + setup_force_cpu_cap(X86_FEATURE_SSBD); + x86_amd_ls_cfg_ssbd_mask = 1ULL << bit; + } + } } static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) @@ -791,6 +812,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c) static void init_amd_zn(struct cpuinfo_x86 *c) { + set_cpu_cap(c, X86_FEATURE_ZEN); /* * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects * all up to and including B1. diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bfca937bdcc3..7416fc206b4a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -12,8 +12,10 @@ #include <linux/utsname.h> #include <linux/cpu.h> #include <linux/module.h> +#include <linux/nospec.h> +#include <linux/prctl.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> @@ -27,6 +29,27 @@ #include <asm/intel-family.h> static void __init spectre_v2_select_mitigation(void); +static void __init ssb_select_mitigation(void); + +/* + * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any + * writes to SPEC_CTRL contain whatever reserved bits have been set. + */ +u64 __ro_after_init x86_spec_ctrl_base; +EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); + +/* + * The vendor and possibly platform specific bits which can be modified in + * x86_spec_ctrl_base. + */ +static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; + +/* + * AMD specific MSR info for Speculative Store Bypass control. + * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu(). + */ +u64 __ro_after_init x86_amd_ls_cfg_base; +u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask; void __init check_bugs(void) { @@ -37,9 +60,27 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); } + /* + * Read the SPEC_CTRL MSR to account for reserved bits which may + * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD + * init code as it is not enumerated and depends on the family. + */ + if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + /* Allow STIBP in MSR_SPEC_CTRL if supported */ + if (boot_cpu_has(X86_FEATURE_STIBP)) + x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; + /* Select the proper spectre mitigation before patching alternatives */ spectre_v2_select_mitigation(); + /* + * Select proper mitigation for any exposure to the Speculative Store + * Bypass vulnerability. + */ + ssb_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -93,7 +134,76 @@ static const char *spectre_v2_strings[] = { #undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt -static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = + SPECTRE_V2_NONE; + +void +x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) +{ + u64 msrval, guestval, hostval = x86_spec_ctrl_base; + struct thread_info *ti = current_thread_info(); + + /* Is MSR_SPEC_CTRL implemented ? */ + if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) { + /* + * Restrict guest_spec_ctrl to supported values. Clear the + * modifiable bits in the host base value and or the + * modifiable bits from the guest value. + */ + guestval = hostval & ~x86_spec_ctrl_mask; + guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; + + /* SSBD controlled in MSR_SPEC_CTRL */ + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) + hostval |= ssbd_tif_to_spec_ctrl(ti->flags); + + if (hostval != guestval) { + msrval = setguest ? guestval : hostval; + wrmsrl(MSR_IA32_SPEC_CTRL, msrval); + } + } + + /* + * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update + * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported. + */ + if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) && + !static_cpu_has(X86_FEATURE_VIRT_SSBD)) + return; + + /* + * If the host has SSBD mitigation enabled, force it in the host's + * virtual MSR value. If its not permanently enabled, evaluate + * current's TIF_SSBD thread flag. + */ + if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE)) + hostval = SPEC_CTRL_SSBD; + else + hostval = ssbd_tif_to_spec_ctrl(ti->flags); + + /* Sanitize the guest value */ + guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD; + + if (hostval != guestval) { + unsigned long tif; + + tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) : + ssbd_spec_ctrl_to_tif(hostval); + + speculative_store_bypass_update(tif); + } +} +EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl); + +static void x86_amd_ssb_disable(void) +{ + u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask; + + if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) + wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD); + else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + wrmsrl(MSR_AMD64_LS_CFG, msrval); +} #ifdef RETPOLINE static bool spectre_v2_bad_module; @@ -312,32 +422,289 @@ retpoline_auto: } #undef pr_fmt +#define pr_fmt(fmt) "Speculative Store Bypass: " fmt + +static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE; + +/* The kernel command line selection */ +enum ssb_mitigation_cmd { + SPEC_STORE_BYPASS_CMD_NONE, + SPEC_STORE_BYPASS_CMD_AUTO, + SPEC_STORE_BYPASS_CMD_ON, + SPEC_STORE_BYPASS_CMD_PRCTL, + SPEC_STORE_BYPASS_CMD_SECCOMP, +}; + +static const char *ssb_strings[] = { + [SPEC_STORE_BYPASS_NONE] = "Vulnerable", + [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled", + [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl", + [SPEC_STORE_BYPASS_SECCOMP] = "Mitigation: Speculative Store Bypass disabled via prctl and seccomp", +}; + +static const struct { + const char *option; + enum ssb_mitigation_cmd cmd; +} ssb_mitigation_options[] = { + { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ + { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ + { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ + { "prctl", SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */ + { "seccomp", SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */ +}; + +static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) +{ + enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO; + char arg[20]; + int ret, i; + + if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) { + return SPEC_STORE_BYPASS_CMD_NONE; + } else { + ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", + arg, sizeof(arg)); + if (ret < 0) + return SPEC_STORE_BYPASS_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) { + if (!match_option(arg, ret, ssb_mitigation_options[i].option)) + continue; + + cmd = ssb_mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(ssb_mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", arg); + return SPEC_STORE_BYPASS_CMD_AUTO; + } + } + + return cmd; +} + +static enum ssb_mitigation __init __ssb_select_mitigation(void) +{ + enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE; + enum ssb_mitigation_cmd cmd; + + if (!boot_cpu_has(X86_FEATURE_SSBD)) + return mode; + + cmd = ssb_parse_cmdline(); + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) && + (cmd == SPEC_STORE_BYPASS_CMD_NONE || + cmd == SPEC_STORE_BYPASS_CMD_AUTO)) + return mode; + + switch (cmd) { + case SPEC_STORE_BYPASS_CMD_AUTO: + case SPEC_STORE_BYPASS_CMD_SECCOMP: + /* + * Choose prctl+seccomp as the default mode if seccomp is + * enabled. + */ + if (IS_ENABLED(CONFIG_SECCOMP)) + mode = SPEC_STORE_BYPASS_SECCOMP; + else + mode = SPEC_STORE_BYPASS_PRCTL; + break; + case SPEC_STORE_BYPASS_CMD_ON: + mode = SPEC_STORE_BYPASS_DISABLE; + break; + case SPEC_STORE_BYPASS_CMD_PRCTL: + mode = SPEC_STORE_BYPASS_PRCTL; + break; + case SPEC_STORE_BYPASS_CMD_NONE: + break; + } + + /* + * We have three CPU feature flags that are in play here: + * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. + * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass + * - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation + */ + if (mode == SPEC_STORE_BYPASS_DISABLE) { + setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE); + /* + * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses + * a completely different MSR and bit dependent on family. + */ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + x86_spec_ctrl_base |= SPEC_CTRL_SSBD; + x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + break; + case X86_VENDOR_AMD: + x86_amd_ssb_disable(); + break; + } + } + + return mode; +} + +static void ssb_select_mitigation(void) +{ + ssb_mode = __ssb_select_mitigation(); + + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + pr_info("%s\n", ssb_strings[ssb_mode]); +} + +#undef pr_fmt +#define pr_fmt(fmt) "Speculation prctl: " fmt + +static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + bool update; + + if (ssb_mode != SPEC_STORE_BYPASS_PRCTL && + ssb_mode != SPEC_STORE_BYPASS_SECCOMP) + return -ENXIO; + + switch (ctrl) { + case PR_SPEC_ENABLE: + /* If speculation is force disabled, enable is not allowed */ + if (task_spec_ssb_force_disable(task)) + return -EPERM; + task_clear_spec_ssb_disable(task); + update = test_and_clear_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_DISABLE: + task_set_spec_ssb_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_FORCE_DISABLE: + task_set_spec_ssb_disable(task); + task_set_spec_ssb_force_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + break; + default: + return -ERANGE; + } + + /* + * If being set on non-current task, delay setting the CPU + * mitigation until it is next scheduled. + */ + if (task == current && update) + speculative_store_bypass_update_current(); + + return 0; +} + +int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, + unsigned long ctrl) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssb_prctl_set(task, ctrl); + default: + return -ENODEV; + } +} + +#ifdef CONFIG_SECCOMP +void arch_seccomp_spec_mitigate(struct task_struct *task) +{ + if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) + ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); +} +#endif + +static int ssb_prctl_get(struct task_struct *task) +{ + switch (ssb_mode) { + case SPEC_STORE_BYPASS_DISABLE: + return PR_SPEC_DISABLE; + case SPEC_STORE_BYPASS_SECCOMP: + case SPEC_STORE_BYPASS_PRCTL: + if (task_spec_ssb_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ssb_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + default: + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + return PR_SPEC_ENABLE; + return PR_SPEC_NOT_AFFECTED; + } +} + +int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssb_prctl_get(task); + default: + return -ENODEV; + } +} + +void x86_spec_ctrl_setup_ap(void) +{ + if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) + x86_amd_ssb_disable(); +} #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) + +static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, + char *buf, unsigned int bug) { - if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + if (!boot_cpu_has_bug(bug)) return sprintf(buf, "Not affected\n"); - if (boot_cpu_has(X86_FEATURE_PTI)) - return sprintf(buf, "Mitigation: PTI\n"); + + switch (bug) { + case X86_BUG_CPU_MELTDOWN: + if (boot_cpu_has(X86_FEATURE_PTI)) + return sprintf(buf, "Mitigation: PTI\n"); + + break; + + case X86_BUG_SPECTRE_V1: + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + + case X86_BUG_SPECTRE_V2: + return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + spectre_v2_module_string()); + + case X86_BUG_SPEC_STORE_BYPASS: + return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + + default: + break; + } + return sprintf(buf, "Vulnerable\n"); } +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN); +} + ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { - if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) - return sprintf(buf, "Not affected\n"); - return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1); } ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { - if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - return sprintf(buf, "Not affected\n"); + return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2); +} - return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - spectre_v2_module_string()); +ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS); } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8a5b185735e1..38276f58d3bf 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -757,17 +757,32 @@ static void init_speculation_control(struct cpuinfo_x86 *c) * and they also have a different bit for STIBP support. Also, * a hypervisor might have set the individual AMD bits even on * Intel CPUs, for finer-grained selection of what's available. - * - * We use the AMD bits in 0x8000_0008 EBX as the generic hardware - * features, which are visible in /proc/cpuinfo and used by the - * kernel. So set those accordingly from the Intel bits. */ if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { set_cpu_cap(c, X86_FEATURE_IBRS); set_cpu_cap(c, X86_FEATURE_IBPB); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) set_cpu_cap(c, X86_FEATURE_STIBP); + + if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) || + cpu_has(c, X86_FEATURE_VIRT_SSBD)) + set_cpu_cap(c, X86_FEATURE_SSBD); + + if (cpu_has(c, X86_FEATURE_AMD_IBRS)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + } + + if (cpu_has(c, X86_FEATURE_AMD_IBPB)) + set_cpu_cap(c, X86_FEATURE_IBPB); + + if (cpu_has(c, X86_FEATURE_AMD_STIBP)) { + set_cpu_cap(c, X86_FEATURE_STIBP); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + } } void get_cpu_cap(struct cpuinfo_x86 *c) @@ -848,6 +863,11 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_power = edx; } + if (c->extended_cpuid_level >= 0x80000008) { + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); + c->x86_capability[CPUID_8000_0008_EBX] = ebx; + } + if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); @@ -871,7 +891,6 @@ static void get_cpu_address_sizes(struct cpuinfo_x86 *c) c->x86_virt_bits = (eax >> 8) & 0xff; c->x86_phys_bits = eax & 0xff; - c->x86_capability[CPUID_8000_0008_EBX] = ebx; } #ifdef CONFIG_X86_32 else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) @@ -923,21 +942,47 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { {} }; -static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +/* Only list CPUs which speculate but are non susceptible to SSB */ +static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, + { X86_VENDOR_AMD, 0x12, }, + { X86_VENDOR_AMD, 0x11, }, + { X86_VENDOR_AMD, 0x10, }, + { X86_VENDOR_AMD, 0xf, }, + {} +}; + +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; - if (x86_match_cpu(cpu_no_meltdown)) - return false; + if (x86_match_cpu(cpu_no_speculation)) + return; + + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + if (!x86_match_cpu(cpu_no_spec_store_bypass) && + !(ia32_cap & ARCH_CAP_SSB_NO)) + setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); + + if (x86_match_cpu(cpu_no_meltdown)) + return; + /* Rogue Data Cache Load? No! */ if (ia32_cap & ARCH_CAP_RDCL_NO) - return false; + return; - return true; + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); } /* @@ -988,12 +1033,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); - if (!x86_match_cpu(cpu_no_speculation)) { - if (cpu_vulnerable_to_meltdown(c)) - setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - } + cpu_set_bug_bits(c); fpu__init_system(c); @@ -1355,6 +1395,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) #endif mtrr_ap_init(); validate_apic_and_package_id(c); + x86_spec_ctrl_setup_ap(); } static __init int setup_noclflush(char *arg) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index e806b11a99af..37672d299e35 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -50,4 +50,6 @@ extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +extern void x86_spec_ctrl_setup_ap(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b9693b80fc21..577e7f7ae273 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -188,7 +188,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_IBPB); setup_clear_cpu_cap(X86_FEATURE_STIBP); setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_MSR_SPEC_CTRL); setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SSBD); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL_SSBD); } /* @@ -835,6 +838,9 @@ static const struct _tlb_table intel_tlb_table[] = { { 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" }, { 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" }, { 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" }, + { 0x6b, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 8-way associative" }, + { 0x6c, TLB_DATA_2M_4M, 128, " TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" }, + { 0x6d, TLB_DATA_1G, 16, " TLB_DATA 1 GByte pages, fully associative" }, { 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" }, { 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" }, { 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" }, diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index f7666eef4a87..c8e038800591 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -94,6 +94,11 @@ static struct smca_bank_name smca_names[] = { [SMCA_SMU] = { "smu", "System Management Unit" }, }; +static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init = +{ + [0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 } +}; + const char *smca_get_name(enum smca_bank_types t) { if (t >= N_SMCA_BANK_TYPES) @@ -443,20 +448,26 @@ static u32 smca_get_block_address(unsigned int cpu, unsigned int bank, if (!block) return MSR_AMD64_SMCA_MCx_MISC(bank); + /* Check our cache first: */ + if (smca_bank_addrs[bank][block] != -1) + return smca_bank_addrs[bank][block]; + /* * For SMCA enabled processors, BLKPTR field of the first MISC register * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4). */ if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) - return addr; + goto out; if (!(low & MCI_CONFIG_MCAX)) - return addr; + goto out; if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && (low & MASK_BLKPTR_LO)) - return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); + addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); +out: + smca_bank_addrs[bank][block] = addr; return addr; } @@ -468,18 +479,6 @@ static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 hi if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS)) return addr; - /* Get address from already initialized block. */ - if (per_cpu(threshold_banks, cpu)) { - struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank]; - - if (bankp && bankp->blocks) { - struct threshold_block *blockp = &bankp->blocks[block]; - - if (blockp) - return blockp->address; - } - } - if (mce_flags.smca) return smca_get_block_address(cpu, bank, block); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 10c4fc2c91f8..77e201301528 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -564,14 +564,12 @@ static int __reload_late(void *info) apply_microcode_local(&err); spin_unlock(&update_lock); + /* siblings return UCODE_OK because their engine got updated already */ if (err > UCODE_NFOUND) { pr_warn("Error reloading microcode on CPU %d\n", cpu); - return -1; - /* siblings return UCODE_OK because their engine got updated already */ + ret = -1; } else if (err == UCODE_UPDATED || err == UCODE_OK) { ret = 1; - } else { - return ret; } /* diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 32b8e5724f96..1c2cfa0644aa 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -485,7 +485,6 @@ static void show_saved_mc(void) */ static void save_mc_for_early(u8 *mc, unsigned int size) { -#ifdef CONFIG_HOTPLUG_CPU /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); @@ -495,7 +494,6 @@ static void save_mc_for_early(u8 *mc, unsigned int size) show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); -#endif } static bool load_builtin_intel_microcode(struct cpio_data *cp) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 0c408f8c4ed4..2d29e47c056e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -104,6 +104,12 @@ static bool __head check_la57_support(unsigned long physaddr) } #endif +/* Code in __startup_64() can be relocated during execution, but the compiler + * doesn't have to generate PC-relative relocations when accessing globals from + * that function. Clang actually does not generate them, which leads to + * boot-time crashes. To work around this problem, every global pointer must + * be adjusted using fixup_pointer(). + */ unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { @@ -113,6 +119,7 @@ unsigned long __head __startup_64(unsigned long physaddr, p4dval_t *p4d; pudval_t *pud; pmdval_t *pmd, pmd_entry; + pteval_t *mask_ptr; bool la57; int i; unsigned int *next_pgt_ptr; @@ -196,7 +203,8 @@ unsigned long __head __startup_64(unsigned long physaddr, pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; /* Filter out unsupported __PAGE_KERNEL_* bits: */ - pmd_entry &= __supported_pte_mask; + mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr); + pmd_entry &= *mask_ptr; pmd_entry += sme_get_me_mask(); pmd_entry += physaddr; diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index fa183a131edc..a15fe0e92cf9 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL2.0 +// SPDX-License-Identifier: GPL-2.0 /* * Jailhouse paravirt_ops implementation * diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 3182908b7e6c..7326078eaa7a 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -398,11 +398,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel, * little bit simple */ efi_map_sz = efi_get_runtime_map_size(); - efi_map_sz = ALIGN(efi_map_sz, 16); params_cmdline_sz = sizeof(struct boot_params) + cmdline_len + MAX_ELFCOREHDR_STR_LEN; params_cmdline_sz = ALIGN(params_cmdline_sz, 16); - kbuf.bufsz = params_cmdline_sz + efi_map_sz + + kbuf.bufsz = params_cmdline_sz + ALIGN(efi_map_sz, 16) + sizeof(struct setup_data) + sizeof(struct efi_setup_data); @@ -410,7 +409,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, if (!params) return ERR_PTR(-ENOMEM); efi_map_offset = params_cmdline_sz; - efi_setup_data_offset = efi_map_offset + efi_map_sz; + efi_setup_data_offset = efi_map_offset + ALIGN(efi_map_sz, 16); /* Copy setup header onto bootparams. Documentation/x86/boot.txt */ setup_header_size = 0x0202 + kernel[0x0201] - setup_hdr_offset; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 0715f827607c..6f4d42377fe5 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -370,6 +370,10 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION) return 0; + /* We should not singlestep on the exception masking instructions */ + if (insn_masking_exception(insn)) + return 0; + #ifdef CONFIG_X86_64 /* Only x86_64 has RIP relative instructions */ if (insn_rip_relative(insn)) { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 7867417cfaff..5b2300b818af 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -457,7 +457,7 @@ static void __init sev_map_percpu_data(void) static void __init kvm_smp_prepare_cpus(unsigned int max_cpus) { native_smp_prepare_cpus(max_cpus); - if (kvm_para_has_hint(KVM_HINTS_DEDICATED)) + if (kvm_para_has_hint(KVM_HINTS_REALTIME)) static_branch_disable(&virt_spin_lock_key); } @@ -553,7 +553,7 @@ static void __init kvm_guest_init(void) } if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_DEDICATED) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; @@ -649,7 +649,7 @@ static __init int kvm_setup_pv_tlb_flush(void) int cpu; if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_DEDICATED) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { for_each_possible_cpu(cpu) { zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), @@ -745,7 +745,7 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; - if (kvm_para_has_hint(KVM_HINTS_DEDICATED)) + if (kvm_para_has_hint(KVM_HINTS_REALTIME)) return; __pv_init_lock_hash(); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index d41d896481b8..c9b14020f4dd 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -166,7 +166,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) */ pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL); /* Filter out unsuppored __PAGE_KERNEL* bits: */ - pgprot_val(pte_prot) |= __supported_pte_mask; + pgprot_val(pte_prot) &= __supported_pte_mask; pte = pfn_pte(pfn, pte_prot); set_pte_at(mm, va, ptep, pte); pte_unmap_unlock(ptep, ptl); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 60cdec6628b0..d1ab07ec8c9a 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -57,12 +57,17 @@ static void load_segments(void) static void machine_kexec_free_page_tables(struct kimage *image) { free_page((unsigned long)image->arch.pgd); + image->arch.pgd = NULL; #ifdef CONFIG_X86_PAE free_page((unsigned long)image->arch.pmd0); + image->arch.pmd0 = NULL; free_page((unsigned long)image->arch.pmd1); + image->arch.pmd1 = NULL; #endif free_page((unsigned long)image->arch.pte0); + image->arch.pte0 = NULL; free_page((unsigned long)image->arch.pte1); + image->arch.pte1 = NULL; } static int machine_kexec_alloc_page_tables(struct kimage *image) @@ -79,7 +84,6 @@ static int machine_kexec_alloc_page_tables(struct kimage *image) !image->arch.pmd0 || !image->arch.pmd1 || #endif !image->arch.pte0 || !image->arch.pte1) { - machine_kexec_free_page_tables(image); return -ENOMEM; } return 0; diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index a5e55d832d0a..6010449ca6d2 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -39,9 +39,13 @@ const struct kexec_file_ops * const kexec_file_loaders[] = { static void free_transition_pgtable(struct kimage *image) { free_page((unsigned long)image->arch.p4d); + image->arch.p4d = NULL; free_page((unsigned long)image->arch.pud); + image->arch.pud = NULL; free_page((unsigned long)image->arch.pmd); + image->arch.pmd = NULL; free_page((unsigned long)image->arch.pte); + image->arch.pte = NULL; } static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) @@ -91,7 +95,6 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC)); return 0; err: - free_transition_pgtable(image); return result; } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 77625b60a510..ab5d9dd668d2 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -15,13 +15,11 @@ #include <asm/x86_init.h> #include <asm/iommu_table.h> -static int forbid_dac __read_mostly; +static bool disable_dac_quirk __read_mostly; const struct dma_map_ops *dma_ops = &dma_direct_ops; EXPORT_SYMBOL(dma_ops); -static int iommu_sac_force __read_mostly; - #ifdef CONFIG_IOMMU_DEBUG int panic_on_overflow __read_mostly = 1; int force_iommu __read_mostly = 1; @@ -55,9 +53,6 @@ struct device x86_dma_fallback_dev = { }; EXPORT_SYMBOL(x86_dma_fallback_dev); -/* Number of entries preallocated for DMA-API debugging */ -#define PREALLOC_DMA_DEBUG_ENTRIES 65536 - void __init pci_iommu_alloc(void) { struct iommu_table_entry *p; @@ -76,7 +71,7 @@ void __init pci_iommu_alloc(void) } } -bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp) +bool arch_dma_alloc_attrs(struct device **dev) { if (!*dev) *dev = &x86_dma_fallback_dev; @@ -125,13 +120,13 @@ static __init int iommu_setup(char *p) if (!strncmp(p, "nomerge", 7)) iommu_merge = 0; if (!strncmp(p, "forcesac", 8)) - iommu_sac_force = 1; + pr_warn("forcesac option ignored.\n"); if (!strncmp(p, "allowdac", 8)) - forbid_dac = 0; + pr_warn("allowdac option ignored.\n"); if (!strncmp(p, "nodac", 5)) - forbid_dac = 1; + pr_warn("nodac option ignored.\n"); if (!strncmp(p, "usedac", 6)) { - forbid_dac = -1; + disable_dac_quirk = true; return 1; } #ifdef CONFIG_SWIOTLB @@ -156,40 +151,9 @@ static __init int iommu_setup(char *p) } early_param("iommu", iommu_setup); -int arch_dma_supported(struct device *dev, u64 mask) -{ -#ifdef CONFIG_PCI - if (mask > 0xffffffff && forbid_dac > 0) { - dev_info(dev, "PCI: Disallowing DAC for device\n"); - return 0; - } -#endif - - /* Tell the device to use SAC when IOMMU force is on. This - allows the driver to use cheaper accesses in some cases. - - Problem with this is that if we overflow the IOMMU area and - return DAC as fallback address the device may not handle it - correctly. - - As a special case some controllers have a 39bit address - mode that is as efficient as 32bit (aic79xx). Don't force - SAC for these. Assume all masks <= 40 bits are of this - type. Normally this doesn't make any difference, but gives - more gentle handling of IOMMU overflow. */ - if (iommu_sac_force && (mask >= DMA_BIT_MASK(40))) { - dev_info(dev, "Force SAC with mask %Lx\n", mask); - return 0; - } - - return 1; -} -EXPORT_SYMBOL(arch_dma_supported); - static int __init pci_iommu_init(void) { struct iommu_table_entry *p; - dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); #ifdef CONFIG_PCI dma_debug_add_bus(&pci_bus_type); @@ -209,11 +173,17 @@ rootfs_initcall(pci_iommu_init); #ifdef CONFIG_PCI /* Many VIA bridges seem to corrupt data for DAC. Disable it here */ +static int via_no_dac_cb(struct pci_dev *pdev, void *data) +{ + pdev->dev.dma_32bit_limit = true; + return 0; +} + static void via_no_dac(struct pci_dev *dev) { - if (forbid_dac == 0) { + if (!disable_dac_quirk) { dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n"); - forbid_dac = 1; + pci_walk_bus(dev->subordinate, via_no_dac_cb, NULL); } } DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c deleted file mode 100644 index ac7ea3a8242f..000000000000 --- a/arch/x86/kernel/pci-nommu.c +++ /dev/null @@ -1,90 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Fallback functions when the main IOMMU code is not compiled in. This - code is roughly equivalent to i386. */ -#include <linux/dma-direct.h> -#include <linux/scatterlist.h> -#include <linux/string.h> -#include <linux/gfp.h> -#include <linux/pci.h> -#include <linux/mm.h> - -#include <asm/processor.h> -#include <asm/iommu.h> -#include <asm/dma.h> - -#define NOMMU_MAPPING_ERROR 0 - -static int -check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) -{ - if (hwdev && !dma_capable(hwdev, bus, size)) { - if (*hwdev->dma_mask >= DMA_BIT_MASK(32)) - printk(KERN_ERR - "nommu_%s: overflow %Lx+%zu of device mask %Lx\n", - name, (long long)bus, size, - (long long)*hwdev->dma_mask); - return 0; - } - return 1; -} - -static dma_addr_t nommu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset; - WARN_ON(size == 0); - if (!check_addr("map_single", dev, bus, size)) - return NOMMU_MAPPING_ERROR; - return bus; -} - -/* Map a set of buffers described by scatterlist in streaming - * mode for DMA. This is the scatter-gather version of the - * above pci_map_single interface. Here the scatter gather list - * elements are each tagged with the appropriate dma address - * and length. They are obtained via sg_dma_{address,length}(SG). - * - * NOTE: An implementation may be able to use a smaller number of - * DMA address/length pairs than there are SG table elements. - * (for example via virtual mapping capabilities) - * The routine returns the number of addr/length pairs actually - * used, at most nents. - * - * Device ownership issues as mentioned above for pci_map_single are - * the same here. - */ -static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *s; - int i; - - WARN_ON(nents == 0 || sg[0].length == 0); - - for_each_sg(sg, s, nents, i) { - BUG_ON(!sg_page(s)); - s->dma_address = sg_phys(s); - if (!check_addr("map_sg", hwdev, s->dma_address, s->length)) - return 0; - s->dma_length = s->length; - } - return nents; -} - -static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return dma_addr == NOMMU_MAPPING_ERROR; -} - -const struct dma_map_ops nommu_dma_ops = { - .alloc = dma_generic_alloc_coherent, - .free = dma_generic_free_coherent, - .map_sg = nommu_map_sg, - .map_page = nommu_map_page, - .is_phys = 1, - .mapping_error = nommu_mapping_error, - .dma_supported = x86_dma_supported, -}; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 03408b942adb..30ca2d1a9231 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -38,6 +38,7 @@ #include <asm/switch_to.h> #include <asm/desc.h> #include <asm/prctl.h> +#include <asm/spec-ctrl.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -278,6 +279,148 @@ static inline void switch_to_bitmap(struct tss_struct *tss, } } +#ifdef CONFIG_SMP + +struct ssb_state { + struct ssb_state *shared_state; + raw_spinlock_t lock; + unsigned int disable_state; + unsigned long local_state; +}; + +#define LSTATE_SSB 0 + +static DEFINE_PER_CPU(struct ssb_state, ssb_state); + +void speculative_store_bypass_ht_init(void) +{ + struct ssb_state *st = this_cpu_ptr(&ssb_state); + unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; + + st->local_state = 0; + + /* + * Shared state setup happens once on the first bringup + * of the CPU. It's not destroyed on CPU hotunplug. + */ + if (st->shared_state) + return; + + raw_spin_lock_init(&st->lock); + + /* + * Go over HT siblings and check whether one of them has set up the + * shared state pointer already. + */ + for_each_cpu(cpu, topology_sibling_cpumask(this_cpu)) { + if (cpu == this_cpu) + continue; + + if (!per_cpu(ssb_state, cpu).shared_state) + continue; + + /* Link it to the state of the sibling: */ + st->shared_state = per_cpu(ssb_state, cpu).shared_state; + return; + } + + /* + * First HT sibling to come up on the core. Link shared state of + * the first HT sibling to itself. The siblings on the same core + * which come up later will see the shared state pointer and link + * themself to the state of this CPU. + */ + st->shared_state = st; +} + +/* + * Logic is: First HT sibling enables SSBD for both siblings in the core + * and last sibling to disable it, disables it for the whole core. This how + * MSR_SPEC_CTRL works in "hardware": + * + * CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL + */ +static __always_inline void amd_set_core_ssb_state(unsigned long tifn) +{ + struct ssb_state *st = this_cpu_ptr(&ssb_state); + u64 msr = x86_amd_ls_cfg_base; + + if (!static_cpu_has(X86_FEATURE_ZEN)) { + msr |= ssbd_tif_to_amd_ls_cfg(tifn); + wrmsrl(MSR_AMD64_LS_CFG, msr); + return; + } + + if (tifn & _TIF_SSBD) { + /* + * Since this can race with prctl(), block reentry on the + * same CPU. + */ + if (__test_and_set_bit(LSTATE_SSB, &st->local_state)) + return; + + msr |= x86_amd_ls_cfg_ssbd_mask; + + raw_spin_lock(&st->shared_state->lock); + /* First sibling enables SSBD: */ + if (!st->shared_state->disable_state) + wrmsrl(MSR_AMD64_LS_CFG, msr); + st->shared_state->disable_state++; + raw_spin_unlock(&st->shared_state->lock); + } else { + if (!__test_and_clear_bit(LSTATE_SSB, &st->local_state)) + return; + + raw_spin_lock(&st->shared_state->lock); + st->shared_state->disable_state--; + if (!st->shared_state->disable_state) + wrmsrl(MSR_AMD64_LS_CFG, msr); + raw_spin_unlock(&st->shared_state->lock); + } +} +#else +static __always_inline void amd_set_core_ssb_state(unsigned long tifn) +{ + u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn); + + wrmsrl(MSR_AMD64_LS_CFG, msr); +} +#endif + +static __always_inline void amd_set_ssb_virt_state(unsigned long tifn) +{ + /* + * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL, + * so ssbd_tif_to_spec_ctrl() just works. + */ + wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn)); +} + +static __always_inline void intel_set_ssb_state(unsigned long tifn) +{ + u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn); + + wrmsrl(MSR_IA32_SPEC_CTRL, msr); +} + +static __always_inline void __speculative_store_bypass_update(unsigned long tifn) +{ + if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) + amd_set_ssb_virt_state(tifn); + else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + amd_set_core_ssb_state(tifn); + else + intel_set_ssb_state(tifn); +} + +void speculative_store_bypass_update(unsigned long tif) +{ + preempt_disable(); + __speculative_store_bypass_update(tif); + preempt_enable(); +} + void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss) { @@ -309,6 +452,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, if ((tifp ^ tifn) & _TIF_NOCPUID) set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); + + if ((tifp ^ tifn) & _TIF_SSBD) + __speculative_store_bypass_update(tifn); } /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 4b100fe0f508..12bb445fb98d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -542,6 +542,7 @@ void set_personality_64bit(void) clear_thread_flag(TIF_X32); /* Pretend that this comes from a 64bit execve */ task_pt_regs(current)->orig_ax = __NR_execve; + current_thread_info()->status &= ~TS_COMPAT; /* Ensure the corresponding mm is not marked. */ if (current->mm) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 6285697b6e56..5c623dfe39d1 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -50,6 +50,7 @@ #include <linux/init_ohci1394_dma.h> #include <linux/kvm_para.h> #include <linux/dma-contiguous.h> +#include <xen/xen.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -534,6 +535,11 @@ static void __init reserve_crashkernel(void) high = true; } + if (xen_pv_domain()) { + pr_info("Ignoring crashkernel for a Xen PV domain\n"); + return; + } + /* 0 means: find the address automatically */ if (crash_base <= 0) { /* diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ff99e2b6fc54..9dd324ae4832 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -77,6 +77,9 @@ #include <asm/i8259.h> #include <asm/misc.h> #include <asm/qspinlock.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> +#include <asm/spec-ctrl.h> /* Number of siblings per CPU package */ int smp_num_siblings = 1; @@ -242,6 +245,8 @@ static void notrace start_secondary(void *unused) */ check_tsc_sync_target(); + speculative_store_bypass_ht_init(); + /* * Lock vector_lock, set CPU online and bring the vector * allocator online. Online must be set with vector_lock held @@ -390,15 +395,47 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } +/* + * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs. + * + * These are Intel CPUs that enumerate an LLC that is shared by + * multiple NUMA nodes. The LLC on these systems is shared for + * off-package data access but private to the NUMA node (half + * of the package) for on-package access. + * + * CPUID (the source of the information about the LLC) can only + * enumerate the cache as being shared *or* unshared, but not + * this particular configuration. The CPU in this case enumerates + * the cache to be shared across the entire package (spanning both + * NUMA nodes). + */ + +static const struct x86_cpu_id snc_cpu[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X }, + {} +}; + static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; - if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) - return topology_sane(c, o, "llc"); + /* Do not match if we do not have a valid APICID for cpu: */ + if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID) + return false; - return false; + /* Do not match if LLC id does not match: */ + if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2)) + return false; + + /* + * Allow the SNC topology without warning. Return of false + * means 'c' does not share the LLC of 'o'. This will be + * reflected to userspace. + */ + if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu)) + return false; + + return topology_sane(c, o, "llc"); } /* @@ -456,7 +493,8 @@ static struct sched_domain_topology_level x86_topology[] = { /* * Set if a package/die has multiple NUMA nodes inside. - * AMD Magny-Cours and Intel Cluster-on-Die have this. + * AMD Magny-Cours, Intel Cluster-on-Die, and Intel + * Sub-NUMA Clustering have this. */ static bool x86_has_numa_in_package; @@ -1257,6 +1295,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_mtrr_aps_delayed_init(); smp_quirk_init_udelay(); + + speculative_store_bypass_ht_init(); } void arch_enable_nonboot_cpus_begin(void) @@ -1536,6 +1576,8 @@ static inline void mwait_play_dead(void) void *mwait_ptr; int i; + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + return; if (!this_cpu_has(X86_FEATURE_MWAIT)) return; if (!this_cpu_has(X86_FEATURE_CLFLUSH)) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index ef32297ff17e..74392d9d51e0 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -317,7 +317,7 @@ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2) hpet2 -= hpet1; tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD)); do_div(tmp, 1000000); - do_div(deltatsc, tmp); + deltatsc = div64_u64(deltatsc, tmp); return (unsigned long) deltatsc; } @@ -1067,6 +1067,7 @@ static struct clocksource clocksource_tsc_early = { .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, + .list = LIST_HEAD_INIT(clocksource_tsc_early.list), }; /* @@ -1086,6 +1087,7 @@ static struct clocksource clocksource_tsc = { .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, + .list = LIST_HEAD_INIT(clocksource_tsc.list), }; void mark_tsc_unstable(char *reason) @@ -1098,13 +1100,9 @@ void mark_tsc_unstable(char *reason) clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to %s\n", reason); - /* Change only the rating, when not registered */ - if (clocksource_tsc.mult) { - clocksource_mark_unstable(&clocksource_tsc); - } else { - clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; - clocksource_tsc.rating = 0; - } + + clocksource_mark_unstable(&clocksource_tsc_early); + clocksource_mark_unstable(&clocksource_tsc); } EXPORT_SYMBOL_GPL(mark_tsc_unstable); @@ -1244,7 +1242,7 @@ static void tsc_refine_calibration_work(struct work_struct *work) /* Don't bother refining TSC on unstable systems */ if (tsc_unstable) - return; + goto unreg; /* * Since the work is started early in boot, we may be @@ -1297,11 +1295,12 @@ static void tsc_refine_calibration_work(struct work_struct *work) out: if (tsc_unstable) - return; + goto unreg; if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); +unreg: clocksource_unregister(&clocksource_tsc_early); } @@ -1311,8 +1310,8 @@ static int __init init_tsc_clocksource(void) if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz) return 0; - if (check_tsc_unstable()) - return 0; + if (tsc_unstable) + goto unreg; if (tsc_clocksource_reliable) clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; @@ -1328,6 +1327,7 @@ static int __init init_tsc_clocksource(void) if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); +unreg: clocksource_unregister(&clocksource_tsc_early); return 0; } diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 85c7ef23d99f..c84bb5396958 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -299,6 +299,10 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool if (is_prefix_bad(insn)) return -ENOTSUPP; + /* We should not singlestep on the exception masking instructions */ + if (insn_masking_exception(insn)) + return -ENOTSUPP; + if (x86_64) good_insns = good_insns_64; else diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 82055b90a8b3..92bf2f2e7cdd 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -379,7 +379,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = - F(IBPB) | F(IBRS); + F(AMD_IBPB) | F(AMD_IBRS) | F(VIRT_SSBD); /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = @@ -408,7 +408,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | - F(ARCH_CAPABILITIES); + F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -495,6 +495,11 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; cpuid_mask(&entry->edx, CPUID_7_EDX); + /* + * We emulate ARCH_CAPABILITIES in software even + * if the host doesn't support it. + */ + entry->edx |= F(ARCH_CAPABILITIES); } else { entry->ebx = 0; entry->ecx = 0; @@ -647,13 +652,20 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; - /* IBRS and IBPB aren't necessarily present in hardware cpuid */ - if (boot_cpu_has(X86_FEATURE_IBPB)) - entry->ebx |= F(IBPB); - if (boot_cpu_has(X86_FEATURE_IBRS)) - entry->ebx |= F(IBRS); + /* + * IBRS, IBPB and VIRT_SSBD aren't necessarily present in + * hardware cpuid + */ + if (boot_cpu_has(X86_FEATURE_AMD_IBPB)) + entry->ebx |= F(AMD_IBPB); + if (boot_cpu_has(X86_FEATURE_AMD_IBRS)) + entry->ebx |= F(AMD_IBRS); + if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) + entry->ebx |= F(VIRT_SSBD); entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + entry->ebx |= F(VIRT_SSBD); break; } case 0x80000019: diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 98618e397342..46ff64da44ca 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1260,12 +1260,16 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) } } -static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu) +static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result) { - struct kvm_run *run = vcpu->run; + kvm_hv_hypercall_set_result(vcpu, result); + ++vcpu->stat.hypercalls; + return kvm_skip_emulated_instruction(vcpu); +} - kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result); - return 1; +static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu) +{ + return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result); } static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) @@ -1296,8 +1300,10 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) if (param & ~KVM_HYPERV_CONN_ID_MASK) return HV_STATUS_INVALID_HYPERCALL_INPUT; - /* conn_to_evt is protected by vcpu->kvm->srcu */ + /* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */ + rcu_read_lock(); eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param); + rcu_read_unlock(); if (!eventfd) return HV_STATUS_INVALID_PORT_ID; @@ -1348,7 +1354,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) /* Hypercall continuation is not supported yet */ if (rep_cnt || rep_idx) { ret = HV_STATUS_INVALID_HYPERCALL_CODE; - goto set_result; + goto out; } switch (code) { @@ -1379,9 +1385,8 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) break; } -set_result: - kvm_hv_hypercall_set_result(vcpu, ret); - return 1; +out: + return kvm_hv_hypercall_complete(vcpu, ret); } void kvm_hv_init_vm(struct kvm *kvm) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 70dcb5548022..3773c4625114 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1463,23 +1463,6 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) local_irq_restore(flags); } -static void start_sw_period(struct kvm_lapic *apic) -{ - if (!apic->lapic_timer.period) - return; - - if (apic_lvtt_oneshot(apic) && - ktime_after(ktime_get(), - apic->lapic_timer.target_expiration)) { - apic_timer_expired(apic); - return; - } - - hrtimer_start(&apic->lapic_timer.timer, - apic->lapic_timer.target_expiration, - HRTIMER_MODE_ABS_PINNED); -} - static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor) { ktime_t now, remaining; @@ -1539,11 +1522,43 @@ static bool set_target_expiration(struct kvm_lapic *apic) static void advance_periodic_target_expiration(struct kvm_lapic *apic) { - apic->lapic_timer.tscdeadline += - nsec_to_cycles(apic->vcpu, apic->lapic_timer.period); + ktime_t now = ktime_get(); + u64 tscl = rdtsc(); + ktime_t delta; + + /* + * Synchronize both deadlines to the same time source or + * differences in the periods (caused by differences in the + * underlying clocks or numerical approximation errors) will + * cause the two to drift apart over time as the errors + * accumulate. + */ apic->lapic_timer.target_expiration = ktime_add_ns(apic->lapic_timer.target_expiration, apic->lapic_timer.period); + delta = ktime_sub(apic->lapic_timer.target_expiration, now); + apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) + + nsec_to_cycles(apic->vcpu, delta); +} + +static void start_sw_period(struct kvm_lapic *apic) +{ + if (!apic->lapic_timer.period) + return; + + if (ktime_after(ktime_get(), + apic->lapic_timer.target_expiration)) { + apic_timer_expired(apic); + + if (apic_lvtt_oneshot(apic)) + return; + + advance_periodic_target_expiration(apic); + } + + hrtimer_start(&apic->lapic_timer.timer, + apic->lapic_timer.target_expiration, + HRTIMER_MODE_ABS_PINNED); } bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b58787daf9f8..26110c202b19 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -49,7 +49,7 @@ #include <asm/debugreg.h> #include <asm/kvm_para.h> #include <asm/irq_remapping.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/virtext.h> #include "trace.h" @@ -213,6 +213,12 @@ struct vcpu_svm { } host; u64 spec_ctrl; + /* + * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be + * translated into the appropriate L2_CFG bits on the host to + * perform speculative control. + */ + u64 virt_spec_ctrl; u32 *msrpm; @@ -1423,12 +1429,23 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } +static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (is_guest_mode(vcpu)) + return svm->nested.hsave->control.tsc_offset; + + return vcpu->arch.tsc_offset; +} + static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vcpu_svm *svm = to_svm(vcpu); u64 g_tsc_offset = 0; if (is_guest_mode(vcpu)) { + /* Write L1's TSC offset. */ g_tsc_offset = svm->vmcb->control.tsc_offset - svm->nested.hsave->control.tsc_offset; svm->nested.hsave->control.tsc_offset = offset; @@ -2049,6 +2066,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.microcode_version = 0x01000065; svm->spec_ctrl = 0; + svm->virt_spec_ctrl = 0; if (!init_event) { svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | @@ -3322,6 +3340,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) /* Restore the original control entries */ copy_vmcb_control_area(vmcb, hsave); + svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset; kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); @@ -3482,10 +3501,12 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, /* We don't want to see VMMCALLs from a nested guest */ clr_intercept(svm, INTERCEPT_VMMCALL); + svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset; + svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset; + svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext; svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; svm->vmcb->control.int_state = nested_vmcb->control.int_state; - svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; @@ -4035,12 +4056,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) struct vcpu_svm *svm = to_svm(vcpu); switch (msr_info->index) { - case MSR_IA32_TSC: { - msr_info->data = svm->vmcb->control.tsc_offset + - kvm_scale_tsc(vcpu, rdtsc()); - - break; - } case MSR_STAR: msr_info->data = svm->vmcb->save.star; break; @@ -4100,11 +4115,18 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS)) return 1; msr_info->data = svm->spec_ctrl; break; + case MSR_AMD64_VIRT_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + return 1; + + msr_info->data = svm->virt_spec_ctrl; + break; case MSR_F15H_IC_CFG: { int family, model; @@ -4193,12 +4215,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->vmcb->save.g_pat = data; mark_dirty(svm->vmcb, VMCB_NPT); break; - case MSR_IA32_TSC: - kvm_write_tsc(vcpu, msr); - break; case MSR_IA32_SPEC_CTRL: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS)) return 1; /* The STIBP bit doesn't fault even if it's not advertised */ @@ -4225,7 +4244,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_PRED_CMD: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBPB)) + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) return 1; if (data & ~PRED_CMD_IBPB) @@ -4239,6 +4258,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); break; + case MSR_AMD64_VIRT_SPEC_CTRL: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + return 1; + + if (data & ~SPEC_CTRL_SSBD) + return 1; + + svm->virt_spec_ctrl = data; + break; case MSR_STAR: svm->vmcb->save.star = data; break; @@ -5265,9 +5294,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, } if (!ret && svm) { - trace_kvm_pi_irte_update(svm->vcpu.vcpu_id, - host_irq, e->gsi, - vcpu_info.vector, + trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id, + e->gsi, vcpu_info.vector, vcpu_info.pi_desc_addr, set); } @@ -5553,8 +5581,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * is no need to worry about the conditional branch over the wrmsr * being speculatively taken. */ - if (svm->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl); asm volatile ( "push %%" _ASM_BP "; \n\t" @@ -5648,6 +5675,18 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + +#ifdef CONFIG_X86_64 + wrmsrl(MSR_GS_BASE, svm->host.gs_base); +#else + loadsegment(fs, svm->host.fs); +#ifndef CONFIG_X86_32_LAZY_GS + loadsegment(gs, svm->host.gs); +#endif +#endif + /* * We do not use IBRS in the kernel. If this vCPU has used the * SPEC_CTRL MSR it may have left it on; save the value and @@ -5666,20 +5705,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - if (svm->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); - - /* Eliminate branch target predictions from guest mode */ - vmexit_fill_RSB(); - -#ifdef CONFIG_X86_64 - wrmsrl(MSR_GS_BASE, svm->host.gs_base); -#else - loadsegment(fs, svm->host.fs); -#ifndef CONFIG_X86_32_LAZY_GS - loadsegment(gs, svm->host.gs); -#endif -#endif + x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl); reload_tss(vcpu); @@ -5782,7 +5808,7 @@ static bool svm_cpu_has_accelerated_tpr(void) return false; } -static bool svm_has_high_real_mode_segbase(void) +static bool svm_has_emulated_msr(int index) { return true; } @@ -7008,7 +7034,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, .cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr, - .cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase, + .has_emulated_msr = svm_has_emulated_msr, .vcpu_create = svm_create_vcpu, .vcpu_free = svm_free_vcpu, @@ -7102,6 +7128,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .has_wbinvd_exit = svm_has_wbinvd_exit, + .read_l1_tsc_offset = svm_read_l1_tsc_offset, .write_tsc_offset = svm_write_tsc_offset, .set_tdp_cr3 = set_tdp_cr3, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index aafcc9881e88..40aa29204baf 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -51,7 +51,7 @@ #include <asm/apic.h> #include <asm/irq_remapping.h> #include <asm/mmu_context.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/mshyperv.h> #include "trace.h" @@ -1494,6 +1494,12 @@ static inline bool cpu_has_vmx_vmfunc(void) SECONDARY_EXEC_ENABLE_VMFUNC; } +static bool vmx_umip_emulated(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_DESC; +} + static inline bool report_flexpriority(void) { return flexpriority_enabled; @@ -2880,18 +2886,15 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx_update_msr_bitmap(&vmx->vcpu); } -/* - * reads and returns guest's timestamp counter "register" - * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset - * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3 - */ -static u64 guest_read_tsc(struct kvm_vcpu *vcpu) +static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) { - u64 host_tsc, tsc_offset; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - host_tsc = rdtsc(); - tsc_offset = vmcs_read64(TSC_OFFSET); - return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset; + if (is_guest_mode(vcpu) && + (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)) + return vcpu->arch.tsc_offset - vmcs12->tsc_offset; + + return vcpu->arch.tsc_offset; } /* @@ -3524,12 +3527,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_info); - case MSR_IA32_TSC: - msr_info->data = guest_read_tsc(vcpu); - break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; @@ -3646,17 +3645,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vmcs_write64(GUEST_BNDCFGS, data); break; - case MSR_IA32_TSC: - kvm_write_tsc(vcpu, msr_info); - break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) return 1; vmx->spec_ctrl = data; @@ -3682,7 +3677,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; @@ -4553,12 +4547,6 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa); } -static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu) -{ - if (enable_ept) - vmx_flush_tlb(vcpu, true); -} - static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; @@ -4776,14 +4764,16 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) else hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON; - if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) { - vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_DESC); - hw_cr4 &= ~X86_CR4_UMIP; - } else if (!is_guest_mode(vcpu) || - !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) - vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) { + if (cr4 & X86_CR4_UMIP) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); + hw_cr4 &= ~X86_CR4_UMIP; + } else if (!is_guest_mode(vcpu) || + !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_DESC); + } if (cr4 & X86_CR4_VMXE) { /* @@ -9287,7 +9277,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } else { sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); @@ -9315,7 +9305,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) !nested_cpu_has2(get_vmcs12(&vmx->vcpu), SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { vmcs_write64(APIC_ACCESS_ADDR, hpa); - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } } @@ -9495,9 +9485,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) } STACK_FRAME_NON_STANDARD(vmx_handle_external_intr); -static bool vmx_has_high_real_mode_segbase(void) +static bool vmx_has_emulated_msr(int index) { - return enable_unrestricted_guest || emulate_invalid_guest_state; + switch (index) { + case MSR_IA32_SMBASE: + /* + * We cannot do SMM unless we can run the guest in big + * real mode. + */ + return enable_unrestricted_guest || emulate_invalid_guest_state; + case MSR_AMD64_VIRT_SPEC_CTRL: + /* This is AMD only. */ + return false; + default: + return true; + } } static bool vmx_mpx_supported(void) @@ -9512,12 +9514,6 @@ static bool vmx_xsaves_supported(void) SECONDARY_EXEC_XSAVES; } -static bool vmx_umip_emulated(void) -{ - return vmcs_config.cpu_based_2nd_exec_ctrl & - SECONDARY_EXEC_DESC; -} - static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -9735,8 +9731,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * is no need to worry about the conditional branch over the wrmsr * being speculatively taken. */ - if (vmx->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0); vmx->__launched = vmx->loaded_vmcs->launched; @@ -9884,8 +9879,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - if (vmx->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); + x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -10608,6 +10602,16 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, return true; } +static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) && + !page_address_valid(vcpu, vmcs12->apic_access_addr)) + return -EINVAL; + else + return 0; +} + static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -11176,11 +11180,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); } - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) - vmcs_write64(TSC_OFFSET, - vcpu->arch.tsc_offset + vmcs12->tsc_offset); - else - vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); @@ -11222,7 +11223,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } } else if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } /* @@ -11299,6 +11300,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_apic_access_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; @@ -11420,6 +11424,7 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); u32 msr_entry_idx; u32 exit_qual; + int r; enter_guest_mode(vcpu); @@ -11429,26 +11434,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); vmx_segment_cache_clear(vmx); - if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) { - leave_guest_mode(vcpu); - vmx_switch_vmcs(vcpu, &vmx->vmcs01); - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, exit_qual); - return 1; - } + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + vcpu->arch.tsc_offset += vmcs12->tsc_offset; + + r = EXIT_REASON_INVALID_STATE; + if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) + goto fail; nested_get_vmcs12_pages(vcpu, vmcs12); + r = EXIT_REASON_MSR_LOAD_FAIL; msr_entry_idx = nested_vmx_load_msr(vcpu, vmcs12->vm_entry_msr_load_addr, vmcs12->vm_entry_msr_load_count); - if (msr_entry_idx) { - leave_guest_mode(vcpu); - vmx_switch_vmcs(vcpu, &vmx->vmcs01); - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx); - return 1; - } + if (msr_entry_idx) + goto fail; /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point @@ -11457,6 +11457,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) * the success flag) when L2 exits (see nested_vmx_vmexit()). */ return 0; + +fail: + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + vcpu->arch.tsc_offset -= vmcs12->tsc_offset; + leave_guest_mode(vcpu); + vmx_switch_vmcs(vcpu, &vmx->vmcs01); + nested_vmx_entry_failure(vcpu, vmcs12, r, exit_qual); + return 1; } /* @@ -12028,6 +12036,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, leave_guest_mode(vcpu); + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + vcpu->arch.tsc_offset -= vmcs12->tsc_offset; + if (likely(!vmx->fail)) { if (exit_reason == -1) sync_vmcs12(vcpu, vmcs12); @@ -12065,7 +12076,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, } else if (!nested_cpu_has_ept(vmcs12) && nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } /* This is needed for same reason as it was needed in prepare_vmcs02 */ @@ -12224,10 +12235,16 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift, static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 tscl = rdtsc(); - u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl); - u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; + struct vcpu_vmx *vmx; + u64 tscl, guest_tscl, delta_tsc; + + if (kvm_mwait_in_guest(vcpu->kvm)) + return -EOPNOTSUPP; + + vmx = to_vmx(vcpu); + tscl = rdtsc(); + guest_tscl = kvm_read_l1_tsc(vcpu, tscl); + delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; /* Convert to host delta tsc if tsc scaling is enabled */ if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && @@ -12533,7 +12550,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); vcpu_info.vector = irq.vector; - trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi, + trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi, vcpu_info.vector, vcpu_info.pi_desc_addr, set); if (set) @@ -12622,7 +12639,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .hardware_enable = hardware_enable, .hardware_disable = hardware_disable, .cpu_has_accelerated_tpr = report_flexpriority, - .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase, + .has_emulated_msr = vmx_has_emulated_msr, .vm_init = vmx_vm_init, .vm_alloc = vmx_vm_alloc, @@ -12712,6 +12729,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, + .read_l1_tsc_offset = vmx_read_l1_tsc_offset, .write_tsc_offset = vmx_write_tsc_offset, .set_tdp_cr3 = vmx_set_cr3, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b2ff74b12ec4..71e7cda6d014 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -114,7 +114,7 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); static bool __read_mostly report_ignored_msrs = true; module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR); -unsigned int min_timer_period_us = 500; +unsigned int min_timer_period_us = 200; module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); static bool __read_mostly kvmclock_periodic_sync = true; @@ -843,7 +843,10 @@ EXPORT_SYMBOL_GPL(kvm_set_cr4); int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { #ifdef CONFIG_X86_64 - cr3 &= ~CR3_PCID_INVD; + bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); + + if (pcid_enabled) + cr3 &= ~CR3_PCID_INVD; #endif if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) { @@ -1058,6 +1061,7 @@ static u32 emulated_msrs[] = { MSR_SMI_COUNT, MSR_PLATFORM_INFO, MSR_MISC_FEATURES_ENABLES, + MSR_AMD64_VIRT_SPEC_CTRL, }; static unsigned num_emulated_msrs; @@ -1490,7 +1494,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) { - u64 curr_offset = vcpu->arch.tsc_offset; + u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; } @@ -1532,7 +1536,9 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc); + u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + + return tsc_offset + kvm_scale_tsc(vcpu, host_tsc); } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); @@ -2362,6 +2368,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.smbase = data; break; + case MSR_IA32_TSC: + kvm_write_tsc(vcpu, msr_info); + break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) return 1; @@ -2605,6 +2614,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_UCODE_REV: msr_info->data = vcpu->arch.microcode_version; break; + case MSR_IA32_TSC: + msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; + break; case MSR_MTRRcap: case 0x200 ... 0x2ff: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); @@ -2819,7 +2831,8 @@ out: static inline bool kvm_can_mwait_in_guest(void) { return boot_cpu_has(X86_FEATURE_MWAIT) && - !boot_cpu_has_bug(X86_BUG_MONITOR); + !boot_cpu_has_bug(X86_BUG_MONITOR) && + boot_cpu_has(X86_FEATURE_ARAT); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) @@ -2894,7 +2907,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * fringe case that is not enabled except via specific settings * of the module parameters. */ - r = kvm_x86_ops->cpu_has_high_real_mode_segbase(); + r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE); break; case KVM_CAP_VAPIC: r = !kvm_x86_ops->cpu_has_accelerated_tpr(); @@ -4594,14 +4607,8 @@ static void kvm_init_msr_list(void) num_msrs_to_save = j; for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { - switch (emulated_msrs[i]) { - case MSR_IA32_SMBASE: - if (!kvm_x86_ops->cpu_has_high_real_mode_segbase()) - continue; - break; - default: - break; - } + if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i])) + continue; if (j < i) emulated_msrs[j] = emulated_msrs[i]; @@ -6662,9 +6669,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; - int op_64_bit, r; - - r = kvm_skip_emulated_instruction(vcpu); + int op_64_bit; if (kvm_hv_hypercall_enabled(vcpu->kvm)) return kvm_hv_hypercall(vcpu); @@ -6712,8 +6717,9 @@ out: if (!op_64_bit) ret = (u32)ret; kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + ++vcpu->stat.hypercalls; - return r; + return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); @@ -7970,6 +7976,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct msr_data apic_base_msr; int mmu_reset_needed = 0; + int cpuid_update_needed = 0; int pending_vec, max_bits, idx; struct desc_ptr dt; int ret = -EINVAL; @@ -8008,8 +8015,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) vcpu->arch.cr0 = sregs->cr0; mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; + cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) & + (X86_CR4_OSXSAVE | X86_CR4_PKE)); kvm_x86_ops->set_cr4(vcpu, sregs->cr4); - if (sregs->cr4 & (X86_CR4_OSXSAVE | X86_CR4_PKE)) + if (cpuid_update_needed) kvm_update_cpuid(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 7d35ce672989..c9492f764902 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -302,13 +302,6 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) __rem; \ }) -#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) -#define KVM_X86_DISABLE_EXITS_HTL (1 << 1) -#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) -#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \ - KVM_X86_DISABLE_EXITS_HTL | \ - KVM_X86_DISABLE_EXITS_PAUSE) - static inline bool kvm_mwait_in_guest(struct kvm *kvm) { return kvm->arch.mwait_in_guest; diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 62a7e9f65dec..cc7ff5957194 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -18,6 +18,7 @@ #include <linux/init.h> #include <linux/sched.h> #include <linux/seq_file.h> +#include <linux/highmem.h> #include <asm/pgtable.h> @@ -334,16 +335,16 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, pgprotval_t eff_in, unsigned long P) { int i; - pte_t *start; + pte_t *pte; pgprotval_t prot, eff; - start = (pte_t *)pmd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PTE; i++) { - prot = pte_flags(*start); - eff = effective_prot(eff_in, prot); st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); + pte = pte_offset_map(&addr, st->current_address); + prot = pte_flags(*pte); + eff = effective_prot(eff_in, prot); note_page(m, st, __pgprot(prot), eff, 5); - start++; + pte_unmap(pte); } } #ifdef CONFIG_KASAN diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 0f3d50f4c48c..3bded76e8d5c 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -93,6 +93,18 @@ void arch_report_meminfo(struct seq_file *m) static inline void split_page_count(int level) { } #endif +static inline int +within(unsigned long addr, unsigned long start, unsigned long end) +{ + return addr >= start && addr < end; +} + +static inline int +within_inclusive(unsigned long addr, unsigned long start, unsigned long end) +{ + return addr >= start && addr <= end; +} + #ifdef CONFIG_X86_64 static inline unsigned long highmap_start_pfn(void) @@ -106,20 +118,25 @@ static inline unsigned long highmap_end_pfn(void) return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT; } -#endif - -static inline int -within(unsigned long addr, unsigned long start, unsigned long end) +static bool __cpa_pfn_in_highmap(unsigned long pfn) { - return addr >= start && addr < end; + /* + * Kernel text has an alias mapping at a high address, known + * here as "highmap". + */ + return within_inclusive(pfn, highmap_start_pfn(), highmap_end_pfn()); } -static inline int -within_inclusive(unsigned long addr, unsigned long start, unsigned long end) +#else + +static bool __cpa_pfn_in_highmap(unsigned long pfn) { - return addr >= start && addr <= end; + /* There is no highmap on 32-bit */ + return false; } +#endif + /* * Flushing functions */ @@ -172,7 +189,7 @@ static void __cpa_flush_all(void *arg) static void cpa_flush_all(unsigned long cache) { - BUG_ON(irqs_disabled()); + BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); on_each_cpu(__cpa_flush_all, (void *) cache, 1); } @@ -236,7 +253,7 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache, unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */ #endif - BUG_ON(irqs_disabled()); + BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1); @@ -1183,6 +1200,10 @@ static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr, cpa->numpages = 1; cpa->pfn = __pa(vaddr) >> PAGE_SHIFT; return 0; + + } else if (__cpa_pfn_in_highmap(cpa->pfn)) { + /* Faults in the highmap are OK, so do not warn: */ + return -EFAULT; } else { WARN(1, KERN_WARNING "CPA: called for zero pte. " "vaddr = %lx cpa->vaddr = %lx\n", vaddr, @@ -1335,8 +1356,7 @@ static int cpa_process_alias(struct cpa_data *cpa) * to touch the high mapped kernel as well: */ if (!within(vaddr, (unsigned long)_text, _brk_end) && - within_inclusive(cpa->pfn, highmap_start_pfn(), - highmap_end_pfn())) { + __cpa_pfn_in_highmap(cpa->pfn)) { unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base; alias_cpa = *cpa; diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index d7bc0eea20a5..6e98e0a7c923 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -94,26 +94,27 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey */ if (pkey != -1) return pkey; - /* - * Look for a protection-key-drive execute-only mapping - * which is now being given permissions that are not - * execute-only. Move it back to the default pkey. - */ - if (vma_is_pkey_exec_only(vma) && - (prot & (PROT_READ|PROT_WRITE))) { - return 0; - } + /* * The mapping is execute-only. Go try to get the * execute-only protection key. If we fail to do that, * fall through as if we do not have execute-only - * support. + * support in this mm. */ if (prot == PROT_EXEC) { pkey = execute_only_pkey(vma->vm_mm); if (pkey > 0) return pkey; + } else if (vma_is_pkey_exec_only(vma)) { + /* + * Protections are *not* PROT_EXEC, but the mapping + * is using the exec-only pkey. This mapping was + * PROT_EXEC and will no longer be. Move back to + * the default pkey. + */ + return ARCH_DEFAULT_PKEY; } + /* * This is a vanilla, non-pkey mprotect (or we failed to * setup execute-only), inherit the pkey from the VMA we diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index f1fd52f449e0..4d418e705878 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -421,6 +421,16 @@ static inline bool pti_kernel_image_global_ok(void) if (boot_cpu_has(X86_FEATURE_K8)) return false; + /* + * RANDSTRUCT derives its hardening benefits from the + * attacker's lack of knowledge about the layout of kernel + * data structures. Keep the kernel image non-global in + * cases where RANDSTRUCT is in use to help keep the layout a + * secret. + */ + if (IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT)) + return false; + return true; } @@ -430,12 +440,24 @@ static inline bool pti_kernel_image_global_ok(void) */ void pti_clone_kernel_text(void) { + /* + * rodata is part of the kernel image and is normally + * readable on the filesystem or on the web. But, do not + * clone the areas past rodata, they might contain secrets. + */ unsigned long start = PFN_ALIGN(_text); - unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE); + unsigned long end = (unsigned long)__end_rodata_hpage_align; if (!pti_kernel_image_global_ok()) return; + pr_debug("mapping partial kernel image into user address space\n"); + + /* + * Note that this will undo _some_ of the work that + * pti_set_kernel_image_nonglobal() did to clear the + * global bit. + */ pti_clone_pmds(start, end, _PAGE_RW); } @@ -458,8 +480,6 @@ void pti_set_kernel_image_nonglobal(void) if (pti_kernel_image_global_ok()) return; - pr_debug("set kernel image non-global\n"); - set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT); } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index b725154182cc..263c8453815e 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1027,7 +1027,17 @@ emit_cond_jmp: /* convert BPF opcode to x86 */ break; case BPF_JMP | BPF_JA: - jmp_offset = addrs[i + insn->off] - addrs[i]; + if (insn->off == -1) + /* -1 jmp instructions will always jump + * backwards two bytes. Explicitly handling + * this case avoids wasting too many passes + * when there are long sequences of replaced + * dead code. + */ + jmp_offset = -2; + else + jmp_offset = addrs[i + insn->off] - addrs[i]; + if (!jmp_offset) /* optimize out nop jumps */ break; @@ -1226,6 +1236,7 @@ skip_init_addrs: for (pass = 0; pass < 20 || image; pass++) { proglen = do_jit(prog, addrs, image, oldproglen, &ctx); if (proglen <= 0) { +out_image: image = NULL; if (header) bpf_jit_binary_free(header); @@ -1236,8 +1247,7 @@ skip_init_addrs: if (proglen != oldproglen) { pr_err("bpf_jit: proglen=%d != oldproglen=%d\n", proglen, oldproglen); - prog = orig_prog; - goto out_addrs; + goto out_image; } break; } @@ -1273,7 +1283,7 @@ skip_init_addrs: prog = orig_prog; } - if (!prog->is_func || extra_pass) { + if (!image || !prog->is_func || extra_pass) { out_addrs: kfree(addrs); kfree(jit_data); diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 48b14b534897..ccf4a49bb065 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -98,7 +98,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd) set_pgd(pgd + pgd_index(restore_jump_address), new_pgd); } else { /* No p4d for 4-level paging: point the pgd to the pud page table */ - pgd_t new_pgd = __pgd(__pa(p4d) | pgprot_val(pgtable_prot)); + pgd_t new_pgd = __pgd(__pa(pud) | pgprot_val(pgtable_prot)); set_pgd(pgd + pgd_index(restore_jump_address), new_pgd); } diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 826898701045..19c1ff542387 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -65,6 +65,19 @@ static void __init xen_hvm_init_mem_mapping(void) { early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE); HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn)); + + /* + * The virtual address of the shared_info page has changed, so + * the vcpu_info pointer for VCPU 0 is now stale. + * + * The prepare_boot_cpu callback will re-initialize it via + * xen_vcpu_setup, but we can't rely on that to be called for + * old Xen versions (xen_have_vector_callback == 0). + * + * It is, in any case, bad to have a stale vcpu_info pointer + * so reset it now. + */ + xen_vcpu_info_reset(0); } static void __init init_hvm_pv_info(void) diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index c36d23aa6c35..357969a3697c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -421,45 +421,33 @@ static void xen_load_gdt(const struct desc_ptr *dtr) { unsigned long va = dtr->address; unsigned int size = dtr->size + 1; - unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE); - unsigned long frames[pages]; - int f; - - /* - * A GDT can be up to 64k in size, which corresponds to 8192 - * 8-byte entries, or 16 4k pages.. - */ + unsigned long pfn, mfn; + int level; + pte_t *ptep; + void *virt; - BUG_ON(size > 65536); + /* @size should be at most GDT_SIZE which is smaller than PAGE_SIZE. */ + BUG_ON(size > PAGE_SIZE); BUG_ON(va & ~PAGE_MASK); - for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) { - int level; - pte_t *ptep; - unsigned long pfn, mfn; - void *virt; - - /* - * The GDT is per-cpu and is in the percpu data area. - * That can be virtually mapped, so we need to do a - * page-walk to get the underlying MFN for the - * hypercall. The page can also be in the kernel's - * linear range, so we need to RO that mapping too. - */ - ptep = lookup_address(va, &level); - BUG_ON(ptep == NULL); - - pfn = pte_pfn(*ptep); - mfn = pfn_to_mfn(pfn); - virt = __va(PFN_PHYS(pfn)); + /* + * The GDT is per-cpu and is in the percpu data area. + * That can be virtually mapped, so we need to do a + * page-walk to get the underlying MFN for the + * hypercall. The page can also be in the kernel's + * linear range, so we need to RO that mapping too. + */ + ptep = lookup_address(va, &level); + BUG_ON(ptep == NULL); - frames[f] = mfn; + pfn = pte_pfn(*ptep); + mfn = pfn_to_mfn(pfn); + virt = __va(PFN_PHYS(pfn)); - make_lowmem_page_readonly((void *)va); - make_lowmem_page_readonly(virt); - } + make_lowmem_page_readonly((void *)va); + make_lowmem_page_readonly(virt); - if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct))) + if (HYPERVISOR_set_gdt(&mfn, size / sizeof(struct desc_struct))) BUG(); } @@ -470,34 +458,22 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr) { unsigned long va = dtr->address; unsigned int size = dtr->size + 1; - unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE); - unsigned long frames[pages]; - int f; - - /* - * A GDT can be up to 64k in size, which corresponds to 8192 - * 8-byte entries, or 16 4k pages.. - */ + unsigned long pfn, mfn; + pte_t pte; - BUG_ON(size > 65536); + /* @size should be at most GDT_SIZE which is smaller than PAGE_SIZE. */ + BUG_ON(size > PAGE_SIZE); BUG_ON(va & ~PAGE_MASK); - for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) { - pte_t pte; - unsigned long pfn, mfn; + pfn = virt_to_pfn(va); + mfn = pfn_to_mfn(pfn); - pfn = virt_to_pfn(va); - mfn = pfn_to_mfn(pfn); + pte = pfn_pte(pfn, PAGE_KERNEL_RO); - pte = pfn_pte(pfn, PAGE_KERNEL_RO); - - if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0)) - BUG(); - - frames[f] = mfn; - } + if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0)) + BUG(); - if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct))) + if (HYPERVISOR_set_gdt(&mfn, size / sizeof(struct desc_struct))) BUG(); } diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index d33e7dbe3129..2d76106788a3 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -42,13 +42,11 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr) } EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine); -static void xen_flush_tlb_all(void) +static noinline void xen_flush_tlb_all(void) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_all(0); - preempt_disable(); mcs = xen_mc_entry(sizeof(*op)); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 486c0a34d00b..2c30cabfda90 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1310,13 +1310,11 @@ unsigned long xen_read_cr2_direct(void) return this_cpu_read(xen_vcpu_info.arch.cr2); } -static void xen_flush_tlb(void) +static noinline void xen_flush_tlb(void) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb(0); - preempt_disable(); mcs = xen_mc_entry(sizeof(*op)); |
