diff options
Diffstat (limited to 'arch/x86')
41 files changed, 262 insertions, 121 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f1dbb4ee19d7..887d3a7bb646 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -63,7 +63,7 @@ config X86 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 - select ARCH_HAS_UACCESS_MCSAFE if X86_64 + select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE select ARCH_HAS_SET_MEMORY select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index e57665b4ba1c..e98522ea6f09 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -114,18 +114,12 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) struct pci_setup_rom *rom = NULL; efi_status_t status; unsigned long size; - uint64_t attributes, romsize; + uint64_t romsize; void *romimage; - status = efi_call_proto(efi_pci_io_protocol, attributes, pci, - EfiPciIoAttributeOperationGet, 0ULL, - &attributes); - if (status != EFI_SUCCESS) - return status; - /* - * Some firmware images contain EFI function pointers at the place where the - * romimage and romsize fields are supposed to be. Typically the EFI + * Some firmware images contain EFI function pointers at the place where + * the romimage and romsize fields are supposed to be. Typically the EFI * code is mapped at high addresses, translating to an unrealistically * large romsize. The UEFI spec limits the size of option ROMs to 16 * MiB so we reject any ROMs over 16 MiB in size to catch this. diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S index 9254e0b6cc06..717bf0776421 100644 --- a/arch/x86/crypto/aegis128-aesni-asm.S +++ b/arch/x86/crypto/aegis128-aesni-asm.S @@ -535,6 +535,7 @@ ENTRY(crypto_aegis128_aesni_enc_tail) movdqu STATE3, 0x40(STATEP) FRAME_END + ret ENDPROC(crypto_aegis128_aesni_enc_tail) .macro decrypt_block a s0 s1 s2 s3 s4 i diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S index 9263c344f2c7..4eda2b8db9e1 100644 --- a/arch/x86/crypto/aegis128l-aesni-asm.S +++ b/arch/x86/crypto/aegis128l-aesni-asm.S @@ -645,6 +645,7 @@ ENTRY(crypto_aegis128l_aesni_enc_tail) state_store0 FRAME_END + ret ENDPROC(crypto_aegis128l_aesni_enc_tail) /* diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S index 1d977d515bf9..32aae8397268 100644 --- a/arch/x86/crypto/aegis256-aesni-asm.S +++ b/arch/x86/crypto/aegis256-aesni-asm.S @@ -543,6 +543,7 @@ ENTRY(crypto_aegis256_aesni_enc_tail) state_store0 FRAME_END + ret ENDPROC(crypto_aegis256_aesni_enc_tail) /* diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S index 37d422e77931..07653d4582a6 100644 --- a/arch/x86/crypto/morus1280-avx2-asm.S +++ b/arch/x86/crypto/morus1280-avx2-asm.S @@ -453,6 +453,7 @@ ENTRY(crypto_morus1280_avx2_enc_tail) vmovdqu STATE4, (4 * 32)(%rdi) FRAME_END + ret ENDPROC(crypto_morus1280_avx2_enc_tail) /* diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S index 1fe637c7be9d..bd1aa1b60869 100644 --- a/arch/x86/crypto/morus1280-sse2-asm.S +++ b/arch/x86/crypto/morus1280-sse2-asm.S @@ -652,6 +652,7 @@ ENTRY(crypto_morus1280_sse2_enc_tail) movdqu STATE4_HI, (9 * 16)(%rdi) FRAME_END + ret ENDPROC(crypto_morus1280_sse2_enc_tail) /* diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S index 71c72a0a0862..efa02816d921 100644 --- a/arch/x86/crypto/morus640-sse2-asm.S +++ b/arch/x86/crypto/morus640-sse2-asm.S @@ -437,6 +437,7 @@ ENTRY(crypto_morus640_sse2_enc_tail) movdqu STATE4, (4 * 16)(%rdi) FRAME_END + ret ENDPROC(crypto_morus640_sse2_enc_tail) /* diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 2582881d19ce..c371bfee137a 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -477,7 +477,7 @@ ENTRY(entry_SYSENTER_32) * whereas POPF does not.) */ addl $PT_EFLAGS-PT_DS, %esp /* point esp at pt_regs->flags */ - btr $X86_EFLAGS_IF_BIT, (%esp) + btrl $X86_EFLAGS_IF_BIT, (%esp) popfl /* diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 9de7f1e1dede..7d0df78db727 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 %r8 /* pt_regs->r8 */ + pushq $0 /* pt_regs->r8 = 0 */ xorl %r8d, %r8d /* nospec r8 */ - pushq %r9 /* pt_regs->r9 */ + pushq $0 /* pt_regs->r9 = 0 */ xorl %r9d, %r9d /* nospec r9 */ - pushq %r10 /* pt_regs->r10 */ + pushq $0 /* pt_regs->r10 = 0 */ xorl %r10d, %r10d /* nospec r10 */ - pushq %r11 /* pt_regs->r11 */ + pushq $0 /* pt_regs->r11 = 0 */ xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ @@ -374,13 +374,13 @@ ENTRY(entry_INT80_compat) pushq %rcx /* pt_regs->cx */ xorl %ecx, %ecx /* nospec 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/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 4b98101209a1..d50bb4dc0650 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -579,7 +579,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) { struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); struct perf_event *event = pcpu->event; - struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event *hwc; struct perf_sample_data data; struct perf_raw_record raw; struct pt_regs regs; @@ -602,6 +602,10 @@ fail: return 0; } + if (WARN_ON_ONCE(!event)) + goto fail; + + hwc = &event->hw; msr = hwc->config_base; buf = ibs_data.regs; rdmsrl(msr, *buf); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 707b2a96e516..86f0c15dcc2d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2997,6 +2997,9 @@ static int intel_pmu_hw_config(struct perf_event *event) } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); + + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY; } if (needs_branch_stack(event)) { diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8a10a045b57b..8dbba77e0518 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -408,9 +408,11 @@ static int alloc_bts_buffer(int cpu) ds->bts_buffer_base = (unsigned long) cea; ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL); ds->bts_index = ds->bts_buffer_base; - max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE); - ds->bts_absolute_maximum = ds->bts_buffer_base + max; - ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16); + max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE; + ds->bts_absolute_maximum = ds->bts_buffer_base + + max * BTS_RECORD_SIZE; + ds->bts_interrupt_threshold = ds->bts_absolute_maximum - + (max / 16) * BTS_RECORD_SIZE; return 0; } @@ -1184,16 +1186,20 @@ static void setup_pebs_sample_data(struct perf_event *event, } /* + * We must however always use iregs for the unwinder to stay sane; the + * record BP,SP,IP can point into thin air when the record is from a + * previous PMI context or an (I)RET happend between the record and + * PMI. + */ + if (sample_type & PERF_SAMPLE_CALLCHAIN) + data->callchain = perf_callchain(event, iregs); + + /* * We use the interrupt regs as a base because the PEBS record does not * contain a full regs set, specifically it seems to lack segment * descriptors, which get used by things like user_mode(). * * In the simple case fix up only the IP for PERF_SAMPLE_IP. - * - * We must however always use BP,SP from iregs for the unwinder to stay - * sane; the record BP,SP can point into thin air when the record is - * from a previous PMI context or an (I)RET happend between the record - * and PMI. */ *regs = *iregs; @@ -1212,15 +1218,8 @@ static void setup_pebs_sample_data(struct perf_event *event, regs->si = pebs->si; regs->di = pebs->di; - /* - * Per the above; only set BP,SP if we don't need callchains. - * - * XXX: does this make sense? - */ - if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) { - regs->bp = pebs->bp; - regs->sp = pebs->sp; - } + regs->bp = pebs->bp; + regs->sp = pebs->sp; #ifndef CONFIG_X86_32 regs->r8 = pebs->r8; diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index f68855499391..402338365651 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -114,6 +114,8 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); } + if (nr_bank < 0) + goto ipi_mask_ex_done; if (!nr_bank) ipi_arg->vp_set.format = HV_GENERIC_SET_ALL; @@ -158,6 +160,9 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector) for_each_cpu(cur_cpu, mask) { vcpu = hv_cpu_number_to_vp_number(cur_cpu); + if (vcpu == VP_INVAL) + goto ipi_mask_done; + /* * This particular version of the IPI hypercall can * only target upto 64 CPUs. diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 4c431e1c1eff..1ff420217298 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -265,7 +265,7 @@ void __init hyperv_init(void) { u64 guest_id, required_msrs; union hv_x64_msr_hypercall_contents hypercall_msr; - int cpuhp; + int cpuhp, i; if (x86_hyper_type != X86_HYPER_MS_HYPERV) return; @@ -293,6 +293,9 @@ void __init hyperv_init(void) if (!hv_vp_index) return; + for (i = 0; i < num_possible_cpus(); i++) + hv_vp_index[i] = VP_INVAL; + hv_vp_assist_page = kcalloc(num_possible_cpus(), sizeof(*hv_vp_assist_page), GFP_KERNEL); if (!hv_vp_assist_page) { diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index c356098b6fb9..4d4015ddcf26 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -7,8 +7,6 @@ #ifndef _ASM_X86_MACH_DEFAULT_APM_H #define _ASM_X86_MACH_DEFAULT_APM_H -#include <asm/nospec-branch.h> - #ifdef APM_ZERO_SEGS # define APM_DO_ZERO_SEGS \ "pushl %%ds\n\t" \ @@ -34,7 +32,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ - firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -47,7 +44,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, "=S" (*esi) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); - firmware_restrict_branch_speculation_end(); } static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, @@ -60,7 +56,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ - firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -73,7 +68,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, "=S" (si) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); - firmware_restrict_branch_speculation_end(); return error; } diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 219faaec51df..990770f9e76b 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -46,6 +46,65 @@ #define _ASM_SI __ASM_REG(si) #define _ASM_DI __ASM_REG(di) +#ifndef __x86_64__ +/* 32 bit */ + +#define _ASM_ARG1 _ASM_AX +#define _ASM_ARG2 _ASM_DX +#define _ASM_ARG3 _ASM_CX + +#define _ASM_ARG1L eax +#define _ASM_ARG2L edx +#define _ASM_ARG3L ecx + +#define _ASM_ARG1W ax +#define _ASM_ARG2W dx +#define _ASM_ARG3W cx + +#define _ASM_ARG1B al +#define _ASM_ARG2B dl +#define _ASM_ARG3B cl + +#else +/* 64 bit */ + +#define _ASM_ARG1 _ASM_DI +#define _ASM_ARG2 _ASM_SI +#define _ASM_ARG3 _ASM_DX +#define _ASM_ARG4 _ASM_CX +#define _ASM_ARG5 r8 +#define _ASM_ARG6 r9 + +#define _ASM_ARG1Q rdi +#define _ASM_ARG2Q rsi +#define _ASM_ARG3Q rdx +#define _ASM_ARG4Q rcx +#define _ASM_ARG5Q r8 +#define _ASM_ARG6Q r9 + +#define _ASM_ARG1L edi +#define _ASM_ARG2L esi +#define _ASM_ARG3L edx +#define _ASM_ARG4L ecx +#define _ASM_ARG5L r8d +#define _ASM_ARG6L r9d + +#define _ASM_ARG1W di +#define _ASM_ARG2W si +#define _ASM_ARG3W dx +#define _ASM_ARG4W cx +#define _ASM_ARG5W r8w +#define _ASM_ARG6W r9w + +#define _ASM_ARG1B dil +#define _ASM_ARG2B sil +#define _ASM_ARG3B dl +#define _ASM_ARG4B cl +#define _ASM_ARG5B r8b +#define _ASM_ARG6B r9b + +#endif + /* * Macros to generate condition code outputs from inline assembly, * The output operand must be type "bool". diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 89f08955fff7..c4fc17220df9 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -13,7 +13,7 @@ * Interrupt control: */ -static inline unsigned long native_save_fl(void) +extern inline unsigned long native_save_fl(void) { unsigned long flags; diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 3cd14311edfa..5a7375ed5f7c 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -9,6 +9,8 @@ #include <asm/hyperv-tlfs.h> #include <asm/nospec-branch.h> +#define VP_INVAL U32_MAX + struct ms_hyperv_info { u32 features; u32 misc_features; @@ -20,7 +22,6 @@ struct ms_hyperv_info { extern struct ms_hyperv_info ms_hyperv; - /* * Generate the guest ID. */ @@ -281,6 +282,8 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, */ for_each_cpu(cpu, cpus) { vcpu = hv_cpu_number_to_vp_number(cpu); + if (vcpu == VP_INVAL) + return -1; vcpu_bank = vcpu / 64; vcpu_offset = vcpu % 64; __set_bit(vcpu_offset, (unsigned long *) diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index ada6410fd2ec..fbd578daa66e 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -184,6 +184,9 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) { + if (!pgtable_l5_enabled()) + return; + BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); free_page((unsigned long)p4d); } diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 99ecde23c3ec..5715647fc4fe 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -898,7 +898,7 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd) #define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd)) /* to find an entry in a page-table-directory. */ -static __always_inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { if (!pgtable_l5_enabled()) return (p4d_t *)pgd; diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 0fdcd21dadbd..3c5385f9a88f 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -216,7 +216,7 @@ static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) } #endif -static __always_inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) +static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; @@ -230,7 +230,7 @@ static __always_inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) *p4dp = native_make_p4d(native_pgd_val(pgd)); } -static __always_inline void native_p4d_clear(p4d_t *p4d) +static inline void native_p4d_clear(p4d_t *p4d) { native_set_p4d(p4d, native_make_p4d(0)); } diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 62acb613114b..a9d637bc301d 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -52,7 +52,12 @@ copy_to_user_mcsafe(void *to, const void *from, unsigned len) unsigned long ret; __uaccess_begin(); - ret = memcpy_mcsafe(to, from, len); + /* + * Note, __memcpy_mcsafe() is explicitly used since it can + * handle exceptions / faults. memcpy_mcsafe() may fall back to + * memcpy() which lacks this handling. + */ + ret = __memcpy_mcsafe(to, from, len); __uaccess_end(); return ret; } diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 02d6f5cf4e70..8824d01c0c35 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -61,6 +61,7 @@ obj-y += alternative.o i8253.o hw_breakpoint.o obj-y += tsc.o tsc_msr.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o +obj-y += irqflags.o obj-y += process.o obj-y += fpu/ diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 5d0de79fdab0..ec00d1ff5098 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -240,6 +240,7 @@ #include <asm/olpc.h> #include <asm/paravirt.h> #include <asm/reboot.h> +#include <asm/nospec-branch.h> #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT) extern int (*console_blank_hook)(int); @@ -614,11 +615,13 @@ static long __apm_bios_call(void *_call) gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); + firmware_restrict_branch_speculation_start(); APM_DO_SAVE_SEGS; apm_bios_call_asm(call->func, call->ebx, call->ecx, &call->eax, &call->ebx, &call->ecx, &call->edx, &call->esi); APM_DO_RESTORE_SEGS; + firmware_restrict_branch_speculation_end(); apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); @@ -690,10 +693,12 @@ static long __apm_bios_call_simple(void *_call) gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); + firmware_restrict_branch_speculation_start(); APM_DO_SAVE_SEGS; error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx, &call->eax); APM_DO_RESTORE_SEGS; + firmware_restrict_branch_speculation_end(); apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 082d7875cef8..38915fbfae73 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -543,7 +543,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) nodes_per_socket = ((value >> 3) & 7) + 1; } - if (c->x86 >= 0x15 && c->x86 <= 0x17) { + if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && + !boot_cpu_has(X86_FEATURE_VIRT_SSBD) && + c->x86 >= 0x15 && c->x86 <= 0x17) { unsigned int bit; switch (c->x86) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 404df26b7de8..5c0ea39311fe 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -155,7 +155,8 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; /* SSBD controlled in MSR_SPEC_CTRL */ - if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) hostval |= ssbd_tif_to_spec_ctrl(ti->flags); if (hostval != guestval) { @@ -533,9 +534,10 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may * use a completely different MSR and bit dependent on family. */ - if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) && + !static_cpu_has(X86_FEATURE_AMD_SSBD)) { x86_amd_ssb_disable(); - else { + } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index c102ad51025e..8c50754c09c1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -2165,9 +2165,6 @@ static ssize_t store_int_with_restart(struct device *s, if (check_interval == old_check_interval) return ret; - if (check_interval < 1) - check_interval = 1; - mutex_lock(&mce_sysfs_mutex); mce_restart(); mutex_unlock(&mce_sysfs_mutex); diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 4021d3859499..40eee6cc4124 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -106,7 +106,8 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) memset(line, 0, LINE_SIZE); - length = strncpy_from_user(line, buf, LINE_SIZE - 1); + len = min_t(size_t, len, LINE_SIZE - 1); + length = strncpy_from_user(line, buf, len); if (length < 0) return length; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d1f25c831447..c88c23c658c1 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1248,6 +1248,7 @@ void __init e820__memblock_setup(void) { int i; u64 end; + u64 addr = 0; /* * The bootstrap memblock region count maximum is 128 entries @@ -1264,13 +1265,21 @@ void __init e820__memblock_setup(void) struct e820_entry *entry = &e820_table->entries[i]; end = entry->addr + entry->size; + if (addr < entry->addr) + memblock_reserve(addr, entry->addr - addr); + addr = end; if (end != (resource_size_t)end) continue; + /* + * all !E820_TYPE_RAM ranges (including gap ranges) are put + * into memblock.reserved to make sure that struct pages in + * such regions are not left uninitialized after bootup. + */ if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN) - continue; - - memblock_add(entry->addr, entry->size); + memblock_reserve(entry->addr, entry->size); + else + memblock_add(entry->addr, entry->size); } /* Throw away partial pages: */ diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S new file mode 100644 index 000000000000..ddeeaac8adda --- /dev/null +++ b/arch/x86/kernel/irqflags.S @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <asm/asm.h> +#include <asm/export.h> +#include <linux/linkage.h> + +/* + * unsigned long native_save_fl(void) + */ +ENTRY(native_save_fl) + pushf + pop %_ASM_AX + ret +ENDPROC(native_save_fl) +EXPORT_SYMBOL(native_save_fl) + +/* + * void native_restore_fl(unsigned long flags) + * %eax/%rdi: flags + */ +ENTRY(native_restore_fl) + push %_ASM_ARG1 + popf + ret +ENDPROC(native_restore_fl) +EXPORT_SYMBOL(native_restore_fl) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index bf8d1eb7fca3..3b8e7c13c614 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -138,6 +138,7 @@ static unsigned long kvm_get_tsc_khz(void) src = &hv_clock[cpu].pvti; tsc_khz = pvclock_tsc_khz(src); put_cpu(); + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); return tsc_khz; } @@ -319,6 +320,8 @@ void __init kvmclock_init(void) printk(KERN_INFO "kvm-clock: Using msrs %x and %x", msr_kvm_system_time, msr_kvm_wall_clock); + pvclock_set_pvti_cpu0_va(hv_clock); + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); @@ -366,14 +369,11 @@ int __init kvm_setup_vsyscall_timeinfo(void) vcpu_time = &hv_clock[cpu].pvti; flags = pvclock_read_flags(vcpu_time); - if (!(flags & PVCLOCK_TSC_STABLE_BIT)) { - put_cpu(); - return 1; - } - - pvclock_set_pvti_cpu0_va(hv_clock); put_cpu(); + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) + return 1; + kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; #endif return 0; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c2f7d1d2a5c3..db9656e13ea0 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -221,6 +221,11 @@ static void notrace start_secondary(void *unused) #ifdef CONFIG_X86_32 /* switch away from the initial page table */ load_cr3(swapper_pg_dir); + /* + * Initialize the CR4 shadow before doing anything that could + * try to read it. + */ + cr4_init_shadow(); __flush_tlb_all(); #endif load_current_idt(); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 92fd433c50b9..1bbec387d289 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -85,7 +85,7 @@ config KVM_AMD_SEV def_bool y bool "AMD Secure Encrypted Virtualization (SEV) support" depends on KVM_AMD && X86_64 - depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP + depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) ---help--- Provides support for launching Encrypted VMs on AMD processors. diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1689f433f3a0..e30da9a2430c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2571,6 +2571,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); + unsigned long fs_base, kernel_gs_base; #endif int i; @@ -2586,12 +2587,20 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel; #ifdef CONFIG_X86_64 - save_fsgs_for_kvm(); - vmx->host_state.fs_sel = current->thread.fsindex; - vmx->host_state.gs_sel = current->thread.gsindex; -#else - savesegment(fs, vmx->host_state.fs_sel); - savesegment(gs, vmx->host_state.gs_sel); + if (likely(is_64bit_mm(current->mm))) { + save_fsgs_for_kvm(); + vmx->host_state.fs_sel = current->thread.fsindex; + vmx->host_state.gs_sel = current->thread.gsindex; + fs_base = current->thread.fsbase; + kernel_gs_base = current->thread.gsbase; + } else { +#endif + savesegment(fs, vmx->host_state.fs_sel); + savesegment(gs, vmx->host_state.gs_sel); +#ifdef CONFIG_X86_64 + fs_base = read_msr(MSR_FS_BASE); + kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); + } #endif if (!(vmx->host_state.fs_sel & 7)) { vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel); @@ -2611,10 +2620,10 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) savesegment(ds, vmx->host_state.ds_sel); savesegment(es, vmx->host_state.es_sel); - vmcs_writel(HOST_FS_BASE, current->thread.fsbase); + vmcs_writel(HOST_FS_BASE, fs_base); vmcs_writel(HOST_GS_BASE, cpu_kernelmode_gs_base(cpu)); - vmx->msr_host_kernel_gs_base = current->thread.gsbase; + vmx->msr_host_kernel_gs_base = kernel_gs_base; if (is_long_mode(&vmx->vcpu)) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else @@ -4322,11 +4331,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) vmcs_conf->order = get_order(vmcs_conf->size); vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; - /* KVM supports Enlightened VMCS v1 only */ - if (static_branch_unlikely(&enable_evmcs)) - vmcs_conf->revision_id = KVM_EVMCS_VERSION; - else - vmcs_conf->revision_id = vmx_msr_low; + vmcs_conf->revision_id = vmx_msr_low; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; @@ -4396,7 +4401,13 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) return NULL; vmcs = page_address(pages); memset(vmcs, 0, vmcs_config.size); - vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */ + + /* KVM supports Enlightened VMCS v1 only */ + if (static_branch_unlikely(&enable_evmcs)) + vmcs->revision_id = KVM_EVMCS_VERSION; + else + vmcs->revision_id = vmcs_config.revision_id; + return vmcs; } @@ -4564,6 +4575,19 @@ static __init int alloc_kvm_area(void) return -ENOMEM; } + /* + * When eVMCS is enabled, alloc_vmcs_cpu() sets + * vmcs->revision_id to KVM_EVMCS_VERSION instead of + * revision_id reported by MSR_IA32_VMX_BASIC. + * + * However, even though not explictly documented by + * TLFS, VMXArea passed as VMXON argument should + * still be marked with revision_id reported by + * physical CPU. + */ + if (static_branch_unlikely(&enable_evmcs)) + vmcs->revision_id = vmcs_config.revision_id; + per_cpu(vmxarea, cpu) = vmcs; } return 0; @@ -11753,7 +11777,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u32 msr_entry_idx; u32 exit_qual; int r; @@ -11775,10 +11798,10 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu) 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) + exit_qual = nested_vmx_load_msr(vcpu, + vmcs12->vm_entry_msr_load_addr, + vmcs12->vm_entry_msr_load_count); + if (exit_qual) goto fail; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0046aa70205a..2b812b3c5088 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1097,6 +1097,7 @@ static u32 msr_based_features[] = { MSR_F10H_DECFG, MSR_IA32_UCODE_REV, + MSR_IA32_ARCH_CAPABILITIES, }; static unsigned int num_msr_based_features; @@ -1105,7 +1106,8 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { case MSR_IA32_UCODE_REV: - rdmsrl(msr->index, msr->data); + case MSR_IA32_ARCH_CAPABILITIES: + rdmsrl_safe(msr->index, &msr->data); break; default: if (kvm_x86_ops->get_msr_feature(msr)) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9a84a0d08727..2aafa6ab6103 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -641,11 +641,6 @@ static int is_f00f_bug(struct pt_regs *regs, unsigned long address) return 0; } -static const char nx_warning[] = KERN_CRIT -"kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n"; -static const char smep_warning[] = KERN_CRIT -"unable to execute userspace code (SMEP?) (uid: %d)\n"; - static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address) @@ -664,20 +659,18 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, pte = lookup_address_in_pgd(pgd, address, &level); if (pte && pte_present(*pte) && !pte_exec(*pte)) - printk(nx_warning, from_kuid(&init_user_ns, current_uid())); + pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", + from_kuid(&init_user_ns, current_uid())); if (pte && pte_present(*pte) && pte_exec(*pte) && (pgd_flags(*pgd) & _PAGE_USER) && (__read_cr4() & X86_CR4_SMEP)) - printk(smep_warning, from_kuid(&init_user_ns, current_uid())); + pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n", + from_kuid(&init_user_ns, current_uid())); } - printk(KERN_ALERT "BUG: unable to handle kernel "); - if (address < PAGE_SIZE) - printk(KERN_CONT "NULL pointer dereference"); - else - printk(KERN_CONT "paging request"); - - printk(KERN_CONT " at %px\n", (void *) address); + pr_alert("BUG: unable to handle kernel %s at %px\n", + address < PAGE_SIZE ? "NULL pointer dereference" : "paging request", + (void *)address); dump_pagetable(address); } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index e01f7ceb9e7a..77873ce700ae 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -166,14 +166,14 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd) pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE); set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]); - if (!(pgd_val(*pgd) & _PAGE_PRESENT)) + if (!pgd_present(*pgd)) continue; for (i = 0; i < PTRS_PER_P4D; i++) { p4d = p4d_offset(pgd, pgd_idx * PGDIR_SIZE + i * P4D_SIZE); - if (!(p4d_val(*p4d) & _PAGE_PRESENT)) + if (!p4d_present(*p4d)) continue; pud = (pud_t *)p4d_page_vaddr(*p4d); diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 2e9ee023e6bc..81a8e33115ad 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -6,7 +6,7 @@ purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string targets += $(purgatory-y) PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) -$(obj)/sha256.o: $(srctree)/lib/sha256.c +$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE $(call if_changed_rule,cc_o_c) LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 8d4e2e1ae60b..439a94bf89ad 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1207,12 +1207,20 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_setup_features(); - xen_setup_machphys_mapping(); - /* Install Xen paravirt ops */ pv_info = xen_info; pv_init_ops.patch = paravirt_patch_default; pv_cpu_ops = xen_cpu_ops; + xen_init_irq_ops(); + + /* + * Setup xen_vcpu early because it is needed for + * local_irq_disable(), irqs_disabled(), e.g. in printk(). + * + * Don't do the full vcpu_info placement stuff until we have + * the cpu_possible_mask and a non-dummy shared_info. + */ + xen_vcpu_info_reset(0); x86_platform.get_nmi_reason = xen_get_nmi_reason; @@ -1225,10 +1233,12 @@ asmlinkage __visible void __init xen_start_kernel(void) * Set up some pagetable state before starting to set any ptes. */ + xen_setup_machphys_mapping(); xen_init_mmu_ops(); /* Prevent unwanted bits from being set in PTEs. */ __supported_pte_mask &= ~_PAGE_GLOBAL; + __default_kernel_pte_mask &= ~_PAGE_GLOBAL; /* * Prevent page tables from being allocated in highmem, even @@ -1249,20 +1259,9 @@ asmlinkage __visible void __init xen_start_kernel(void) get_cpu_cap(&boot_cpu_data); x86_configure_nx(); - xen_init_irq_ops(); - /* Let's presume PV guests always boot on vCPU with id 0. */ per_cpu(xen_vcpu_id, 0) = 0; - /* - * Setup xen_vcpu early because idt_setup_early_handler needs it for - * local_irq_disable(), irqs_disabled(). - * - * Don't do the full vcpu_info placement stuff until we have - * the cpu_possible_mask and a non-dummy shared_info. - */ - xen_vcpu_info_reset(0); - idt_setup_early_handler(); xen_init_capabilities(); diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 74179852e46c..7515a19fd324 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -128,8 +128,6 @@ static const struct pv_irq_ops xen_irq_ops __initconst = { void __init xen_init_irq_ops(void) { - /* For PVH we use default pv_irq_ops settings. */ - if (!xen_feature(XENFEAT_hvm_callback_vector)) - pv_irq_ops = xen_irq_ops; + pv_irq_ops = xen_irq_ops; x86_init.irqs.intr_init = xen_init_IRQ; } |