diff options
Diffstat (limited to 'arch/x86')
76 files changed, 610 insertions, 268 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/Makefile b/arch/x86/Makefile index f0a6ea22429d..a08e82856563 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -258,11 +258,6 @@ archscripts: scripts_basic archheaders: $(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all -archprepare: -ifeq ($(CONFIG_KEXEC_FILE),y) - $(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c -endif - ### # Kernel objects @@ -327,7 +322,6 @@ archclean: $(Q)rm -rf $(objtree)/arch/x86_64 $(Q)$(MAKE) $(clean)=$(boot) $(Q)$(MAKE) $(clean)=arch/x86/tools - $(Q)$(MAKE) $(clean)=arch/x86/purgatory define archhelp echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)' diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index fa42f895fdde..169c2feda14a 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -106,9 +106,13 @@ define cmd_check_data_rel done endef +# We need to run two commands under "if_changed", so merge them into a +# single invocation. +quiet_cmd_check-and-link-vmlinux = LD $@ + cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld) + $(obj)/vmlinux: $(vmlinux-objs-y) FORCE - $(call if_changed,check_data_rel) - $(call if_changed,ld) + $(call if_changed,check-and-link-vmlinux) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index a8a8642d2b0b..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, 0, 0, - &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/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 8c5107545251..9e2157371491 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,3 +1,4 @@ +#include <asm/e820/types.h> #include <asm/processor.h> #include "pgtable.h" #include "../string.h" @@ -34,10 +35,62 @@ unsigned long *trampoline_32bit __section(.data); extern struct boot_params *boot_params; int cmdline_find_option_bool(const char *option); +static unsigned long find_trampoline_placement(void) +{ + unsigned long bios_start, ebda_start; + unsigned long trampoline_start; + struct boot_e820_entry *entry; + int i; + + /* + * Find a suitable spot for the trampoline. + * This code is based on reserve_bios_regions(). + */ + + ebda_start = *(unsigned short *)0x40e << 4; + bios_start = *(unsigned short *)0x413 << 10; + + if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) + bios_start = BIOS_START_MAX; + + if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) + bios_start = ebda_start; + + bios_start = round_down(bios_start, PAGE_SIZE); + + /* Find the first usable memory region under bios_start. */ + for (i = boot_params->e820_entries - 1; i >= 0; i--) { + entry = &boot_params->e820_table[i]; + + /* Skip all entries above bios_start. */ + if (bios_start <= entry->addr) + continue; + + /* Skip non-RAM entries. */ + if (entry->type != E820_TYPE_RAM) + continue; + + /* Adjust bios_start to the end of the entry if needed. */ + if (bios_start > entry->addr + entry->size) + bios_start = entry->addr + entry->size; + + /* Keep bios_start page-aligned. */ + bios_start = round_down(bios_start, PAGE_SIZE); + + /* Skip the entry if it's too small. */ + if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr) + continue; + + break; + } + + /* Place the trampoline just below the end of low memory */ + return bios_start - TRAMPOLINE_32BIT_SIZE; +} + struct paging_config paging_prepare(void *rmode) { struct paging_config paging_config = {}; - unsigned long bios_start, ebda_start; /* Initialize boot_params. Required for cmdline_find_option_bool(). */ boot_params = rmode; @@ -61,23 +114,7 @@ struct paging_config paging_prepare(void *rmode) paging_config.l5_required = 1; } - /* - * Find a suitable spot for the trampoline. - * This code is based on reserve_bios_regions(). - */ - - ebda_start = *(unsigned short *)0x40e << 4; - bios_start = *(unsigned short *)0x413 << 10; - - if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) - bios_start = BIOS_START_MAX; - - if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) - bios_start = ebda_start; - - /* Place the trampoline just below the end of low memory, aligned to 4k */ - paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE; - paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE); + paging_config.trampoline_start = find_trampoline_placement(); trampoline_32bit = (unsigned long *)paging_config.trampoline_start; 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/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index 5de7c0d46edf..acd11b3bf639 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis128_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis128_aesni_alg, 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/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c index 876e4866e633..2071c3d1ae07 100644 --- a/arch/x86/crypto/aegis128l-aesni-glue.c +++ b/arch/x86/crypto/aegis128l-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128l_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis128l_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis128l_aesni_alg, 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/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c index 2b5dd3af8f4d..b5f2a8fd5a71 100644 --- a/arch/x86/crypto/aegis256-aesni-glue.c +++ b/arch/x86/crypto/aegis256-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis256_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis256_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis256_aesni_alg, 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-avx2-glue.c b/arch/x86/crypto/morus1280-avx2-glue.c index f111f36d26dc..6634907d6ccd 100644 --- a/arch/x86/crypto/morus1280-avx2-glue.c +++ b/arch/x86/crypto/morus1280-avx2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_avx2_final(void *state, void *tag_xor, MORUS1280_DECLARE_ALGS(avx2, "morus1280-avx2", 400); -static const struct x86_cpu_id avx2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AVX2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, avx2_cpu_id); - static int __init crypto_morus1280_avx2_module_init(void) { - if (!x86_match_cpu(avx2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_AVX2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus1280_avx2_algs, 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/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c index 839270aa713c..95cf857d2cbb 100644 --- a/arch/x86/crypto/morus1280-sse2-glue.c +++ b/arch/x86/crypto/morus1280-sse2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_sse2_final(void *state, void *tag_xor, MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350); -static const struct x86_cpu_id sse2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id); - static int __init crypto_morus1280_sse2_module_init(void) { - if (!x86_match_cpu(sse2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus1280_sse2_algs, 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/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c index 26b47e2db8d2..615fb7bc9a32 100644 --- a/arch/x86/crypto/morus640-sse2-glue.c +++ b/arch/x86/crypto/morus640-sse2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus640_sse2_final(void *state, void *tag_xor, MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400); -static const struct x86_cpu_id sse2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id); - static int __init crypto_morus640_sse2_module_init(void) { - if (!x86_match_cpu(sse2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus640_sse2_algs, diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 92190879b228..3b2490b81918 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -164,7 +164,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) if (cached_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); - rseq_handle_notify_resume(regs); + rseq_handle_notify_resume(NULL, regs); } if (cached_flags & _TIF_USER_RETURN_NOTIFY) 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.S b/arch/x86/entry/entry_64.S index 73a522d53b53..8ae7ffda8f98 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -981,7 +981,7 @@ ENTRY(\sym) call \do_sym - jmp error_exit /* %ebx: no swapgs flag */ + jmp error_exit .endif END(\sym) .endm @@ -1222,7 +1222,6 @@ END(paranoid_exit) /* * Save all registers in pt_regs, and switch GS if needed. - * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) UNWIND_HINT_FUNC @@ -1269,7 +1268,6 @@ ENTRY(error_entry) * for these here too. */ .Lerror_kernelspace: - incl %ebx leaq native_irq_return_iret(%rip), %rcx cmpq %rcx, RIP+8(%rsp) je .Lerror_bad_iret @@ -1303,28 +1301,20 @@ ENTRY(error_entry) /* * Pretend that the exception came from user mode: set up pt_regs - * as if we faulted immediately after IRET and clear EBX so that - * error_exit knows that we will be returning to user mode. + * as if we faulted immediately after IRET. */ mov %rsp, %rdi call fixup_bad_iret mov %rax, %rsp - decl %ebx jmp .Lerror_entry_from_usermode_after_swapgs END(error_entry) - -/* - * On entry, EBX is a "return to kernel mode" flag: - * 1: already in kernel mode, don't need SWAPGS - * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode - */ ENTRY(error_exit) UNWIND_HINT_REGS DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - testl %ebx, %ebx - jnz retint_kernel + testb $3, CS(%rsp) + jz retint_kernel jmp retint_user END(error_exit) 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/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index c9e1e0bef3c3..e17ab885b1e9 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -28,7 +28,7 @@ #define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff) #define UNCORE_PCI_DEV_IDX(data) (data & 0xff) #define UNCORE_EXTRA_PCI_DEV 0xff -#define UNCORE_EXTRA_PCI_DEV_MAX 3 +#define UNCORE_EXTRA_PCI_DEV_MAX 4 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 87dc0263a2e1..51d7c117e3c7 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void) enum { SNBEP_PCI_QPI_PORT0_FILTER, SNBEP_PCI_QPI_PORT1_FILTER, + BDX_PCI_QPI_PORT2_FILTER, HSWEP_PCI_PCU_3, }; @@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { }, { /* QPI Port 0 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), }, { /* QPI Port 1 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), }, { /* QPI Port 2 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + BDX_PCI_QPI_PORT2_FILTER), }, { /* PCU.3 (for Capability registers) */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0), 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/barrier.h b/arch/x86/include/asm/barrier.h index 042b5e892ed1..14de0432d288 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -38,7 +38,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, { unsigned long mask; - asm ("cmp %1,%2; sbb %0,%0;" + asm volatile ("cmp %1,%2; sbb %0,%0;" :"=r" (mask) :"g"(size),"r" (index) :"cc"); 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/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 9ef5ee03d2d7..159622ee0674 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -43,7 +43,7 @@ asm (".pushsection .text;" "push %rdx;" "mov $0x1,%eax;" "xor %edx,%edx;" - "lock cmpxchg %dl,(%rdi);" + LOCK_PREFIX "cmpxchg %dl,(%rdi);" "cmp $0x1,%al;" "jne .slowpath;" "pop %rdx;" 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/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 425e6b8b9547..6aa8499e1f62 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -114,6 +114,7 @@ #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f #define VMX_MISC_SAVE_EFER_LMA 0x00000020 #define VMX_MISC_ACTIVITY_HLT 0x00000040 +#define VMX_MISC_ZERO_LEN_INS 0x40000000 /* VMFUNC functions */ #define VMX_VMFUNC_EPTP_SWITCHING 0x00000001 @@ -351,11 +352,13 @@ enum vmcs_field { #define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK #define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ +#define INTR_TYPE_RESERVED (1 << 8) /* reserved */ #define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ #define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ #define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ #define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */ #define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ +#define INTR_TYPE_OTHER_EVENT (7 << 8) /* other event */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ #define GUEST_INTR_STATE_STI 0x00000001 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/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2aabd4cb0e3f..adbda5847b14 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -573,6 +573,9 @@ static u32 skx_deadline_rev(void) case 0x04: return 0x02000014; } + if (boot_cpu_data.x86_stepping > 4) + return 0; + return ~0U; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index efaf2d4f9c3c..d492752f79e1 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -26,6 +26,7 @@ #include <linux/delay.h> #include <linux/crash_dump.h> #include <linux/reboot.h> +#include <linux/memory.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> @@ -392,6 +393,51 @@ extern int uv_hub_info_version(void) } EXPORT_SYMBOL(uv_hub_info_version); +/* Default UV memory block size is 2GB */ +static unsigned long mem_block_size = (2UL << 30); + +/* Kernel parameter to specify UV mem block size */ +static int parse_mem_block_size(char *ptr) +{ + unsigned long size = memparse(ptr, NULL); + + /* Size will be rounded down by set_block_size() below */ + mem_block_size = size; + return 0; +} +early_param("uv_memblksize", parse_mem_block_size); + +static __init int adj_blksize(u32 lgre) +{ + unsigned long base = (unsigned long)lgre << UV_GAM_RANGE_SHFT; + unsigned long size; + + for (size = mem_block_size; size > MIN_MEMORY_BLOCK_SIZE; size >>= 1) + if (IS_ALIGNED(base, size)) + break; + + if (size >= mem_block_size) + return 0; + + mem_block_size = size; + return 1; +} + +static __init void set_block_size(void) +{ + unsigned int order = ffs(mem_block_size); + + if (order) { + /* adjust for ffs return of 1..64 */ + set_memory_block_size_order(order - 1); + pr_info("UV: mem_block_size set to 0x%lx\n", mem_block_size); + } else { + /* bad or zero value, default to 1UL << 31 (2GB) */ + pr_err("UV: mem_block_size error with 0x%lx\n", mem_block_size); + set_memory_block_size_order(31); + } +} + /* Build GAM range lookup table: */ static __init void build_uv_gr_table(void) { @@ -1180,23 +1226,30 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) << UV_GAM_RANGE_SHFT); int order = 0; char suffix[] = " KMGTPE"; + int flag = ' '; while (size > 9999 && order < sizeof(suffix)) { size /= 1024; order++; } + /* adjust max block size to current range start */ + if (gre->type == 1 || gre->type == 2) + if (adj_blksize(lgre)) + flag = '*'; + if (!index) { pr_info("UV: GAM Range Table...\n"); - pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); + pr_info("UV: # %20s %14s %6s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx%c %5lu%c %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, - size, suffix[order], + flag, size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); + /* update to next range start */ lgre = gre->limit; if (sock_min > gre->sockid) sock_min = gre->sockid; @@ -1427,6 +1480,7 @@ static void __init uv_system_init_hub(void) build_socket_tables(); build_uv_gr_table(); + set_block_size(); uv_init_hub_info(&hub_info); uv_possible_blades = num_possible_nodes(); if (!_node_to_pnode) 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 cd0fda1fff6d..5c0ea39311fe 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -27,6 +27,7 @@ #include <asm/pgtable.h> #include <asm/set_memory.h> #include <asm/intel-family.h> +#include <asm/hypervisor.h> static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); @@ -154,7 +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) { @@ -532,9 +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); @@ -664,6 +667,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr if (boot_cpu_has(X86_FEATURE_PTI)) return sprintf(buf, "Mitigation: PTI\n"); + if (hypervisor_is_type(X86_HYPER_XEN_PV)) + return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); + break; case X86_BUG_SPECTRE_V1: diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 38354c66df81..0c5fcbd998cf 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -671,7 +671,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) num_sharing_cache = ((eax >> 14) & 0xfff) + 1; if (num_sharing_cache) { - int bits = get_count_order(num_sharing_cache) - 1; + int bits = get_count_order(num_sharing_cache); per_cpu(cpu_llc_id, cpu) = c->apicid >> bits; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0df7151cfef4..eb4cb3efd20e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1,3 +1,6 @@ +/* cpu_feature_enabled() cannot be used this early */ +#define USE_EARLY_PGTABLE_L5 + #include <linux/bootmem.h> #include <linux/linkage.h> #include <linux/bitops.h> diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 5bbd06f38ff6..f34d89c01edc 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -160,6 +160,11 @@ static struct severity { SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), USER ), + MCESEV( + PANIC, "Data load in unrecoverable area of kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + KERNEL + ), #endif MCESEV( PANIC, "Action required: unknown MCACOD", diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index e4cf6ff1c2e1..8c50754c09c1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -772,23 +772,25 @@ EXPORT_SYMBOL_GPL(machine_check_poll); static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, struct pt_regs *regs) { - int i, ret = 0; char *tmp; + int i; for (i = 0; i < mca_cfg.banks; i++) { m->status = mce_rdmsrl(msr_ops.status(i)); - if (m->status & MCI_STATUS_VAL) { - __set_bit(i, validp); - if (quirk_no_way_out) - quirk_no_way_out(i, m, regs); - } + if (!(m->status & MCI_STATUS_VAL)) + continue; + + __set_bit(i, validp); + if (quirk_no_way_out) + quirk_no_way_out(i, m, regs); if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + mce_read_aux(m, i); *msg = tmp; - ret = 1; + return 1; } } - return ret; + return 0; } /* @@ -1205,13 +1207,18 @@ void do_machine_check(struct pt_regs *regs, long error_code) lmce = m.mcgstatus & MCG_STATUS_LMCES; /* + * Local machine check may already know that we have to panic. + * Broadcast machine check begins rendezvous in mce_start() * Go through all banks in exclusion of the other CPUs. This way we * don't report duplicated events on shared banks because the first one - * to see it will clear it. If this is a Local MCE, then no need to - * perform rendezvous. + * to see it will clear it. */ - if (!lmce) + if (lmce) { + if (no_way_out) + mce_panic("Fatal local machine check", &m, msg); + } else { order = mce_start(&no_way_out); + } for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); @@ -1287,12 +1294,17 @@ void do_machine_check(struct pt_regs *regs, long error_code) no_way_out = worst >= MCE_PANIC_SEVERITY; } else { /* - * Local MCE skipped calling mce_reign() - * If we found a fatal error, we need to panic here. + * If there was a fatal machine check we should have + * already called mce_panic earlier in this function. + * Since we re-read the banks, we might have found + * something new. Check again to see if we found a + * fatal error. We call "mce_severity()" again to + * make sure we have the right "msg". */ - if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) - mce_panic("Machine check from unknown source", - NULL, NULL); + if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) { + mce_severity(&m, cfg->tolerant, &msg, true); + mce_panic("Local fatal machine check!", &m, msg); + } } /* @@ -2153,9 +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/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 1c2cfa0644aa..97ccf4c3b45b 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -190,8 +190,11 @@ static void save_microcode_patch(void *data, unsigned int size) p = memdup_patch(data, size); if (!p) pr_err("Error allocating buffer %p\n", data); - else + else { list_replace(&iter->plist, &p->plist); + kfree(iter->data); + kfree(iter); + } } } 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/head64.c b/arch/x86/kernel/head64.c index a21d6ace648e..8047379e575a 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -44,7 +44,7 @@ static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); #ifdef CONFIG_X86_5LEVEL -unsigned int __pgtable_l5_enabled __initdata; +unsigned int __pgtable_l5_enabled __ro_after_init; unsigned int pgdir_shift __ro_after_init = 39; EXPORT_SYMBOL(pgdir_shift); unsigned int ptrs_per_p4d __ro_after_init = 1; 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/quirks.c b/arch/x86/kernel/quirks.c index 697a4ce04308..736348ead421 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -645,12 +645,19 @@ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev) /* Skylake */ static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev) { - u32 capid0; + u32 capid0, capid5; pci_read_config_dword(pdev, 0x84, &capid0); + pci_read_config_dword(pdev, 0x98, &capid5); - if ((capid0 & 0xc0) == 0xc0) + /* + * CAPID0{7:6} indicate whether this is an advanced RAS SKU + * CAPID5{8:5} indicate that various NVDIMM usage modes are + * enabled, so memory machine check recovery is also enabled. + */ + if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0)) static_branch_inc(&mcsafe_key); + } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ras_cap); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 445ca11ff863..92a3b312a53c 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -692,7 +692,7 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) * Increment event counter and perform fixup for the pre-signal * frame. */ - rseq_signal_deliver(regs); + rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ if (is_ia32_frame(ksig)) { 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/kernel/traps.c b/arch/x86/kernel/traps.c index a535dd64de63..e6db475164ed 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -835,16 +835,18 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" : "simd exception"; - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP) - return; cond_local_irq_enable(regs); if (!user_mode(regs)) { - if (!fixup_exception(regs, trapnr)) { - task->thread.error_code = error_code; - task->thread.trap_nr = trapnr; + if (fixup_exception(regs, trapnr)) + return; + + task->thread.error_code = error_code; + task->thread.trap_nr = trapnr; + + if (notify_die(DIE_TRAP, str, regs, error_code, + trapnr, SIGFPE) != NOTIFY_STOP) die(str, regs, error_code); - } return; } diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 58d8d800875d..deb576b23b7c 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -293,7 +293,7 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64); /* has the side-effect of processing the entire instruction */ insn_get_length(insn); - if (WARN_ON_ONCE(!insn_complete(insn))) + if (!insn_complete(insn)) return -ENOEXEC; if (is_prefix_bad(insn)) 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/mmu.c b/arch/x86/kvm/mmu.c index d594690d8b95..6b8f11521c41 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -890,7 +890,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - page = (void *)__get_free_page(GFP_KERNEL); + page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT); if (!page) return -ENOMEM; cache->objects[cache->nobjs++] = page; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 559a12b6184d..5d8e317c2b04 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1705,6 +1705,17 @@ static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu) MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; } +static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.msrs.misc_low & VMX_MISC_ZERO_LEN_INS; +} + +static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.msrs.procbased_ctls_high & + CPU_BASED_MONITOR_TRAP_FLAG; +} + static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit) { return vmcs12->cpu_based_vm_exec_control & bit; @@ -2560,6 +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; @@ -2575,12 +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); @@ -2600,10 +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 @@ -4311,11 +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; @@ -4385,7 +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; } @@ -4553,6 +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; @@ -7858,6 +7893,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + vmx->nested.vpid02 = allocate_vpid(); + vmx->nested.vmxon = true; return 0; @@ -8445,21 +8482,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) /* Emulate the VMPTRST instruction */ static int handle_vmptrst(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - gva_t vmcs_gva; + unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION); + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr; struct x86_exception e; + gva_t gva; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, true, &vmcs_gva)) + if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva)) return 1; /* *_system ok, nested_vmx_check_permission has verified cpl=0 */ - if (kvm_write_guest_virt_system(vcpu, vmcs_gva, - (void *)&to_vmx(vcpu)->nested.current_vmptr, - sizeof(u64), &e)) { + if (kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr, + sizeof(gpa_t), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } @@ -10335,11 +10371,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto free_vmcs; } - if (nested) { + if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, kvm_vcpu_apicv_active(&vmx->vcpu)); - vmx->nested.vpid02 = allocate_vpid(); - } vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; @@ -10356,7 +10390,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return &vmx->vcpu; free_vmcs: - free_vpid(vmx->nested.vpid02); free_loaded_vmcs(vmx->loaded_vmcs); free_msrs: kfree(vmx->guest_msrs); @@ -11620,6 +11653,62 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) !nested_cr3_valid(vcpu, vmcs12->host_cr3)) return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD; + /* + * From the Intel SDM, volume 3: + * Fields relevant to VM-entry event injection must be set properly. + * These fields are the VM-entry interruption-information field, the + * VM-entry exception error code, and the VM-entry instruction length. + */ + if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) { + u32 intr_info = vmcs12->vm_entry_intr_info_field; + u8 vector = intr_info & INTR_INFO_VECTOR_MASK; + u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK; + bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK; + bool should_have_error_code; + bool urg = nested_cpu_has2(vmcs12, + SECONDARY_EXEC_UNRESTRICTED_GUEST); + bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE; + + /* VM-entry interruption-info field: interruption type */ + if (intr_type == INTR_TYPE_RESERVED || + (intr_type == INTR_TYPE_OTHER_EVENT && + !nested_cpu_supports_monitor_trap_flag(vcpu))) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: vector */ + if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) || + (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) || + (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: deliver error code */ + should_have_error_code = + intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode && + x86_exception_has_error_code(vector); + if (has_error_code != should_have_error_code) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry exception error code */ + if (has_error_code && + vmcs12->vm_entry_exception_error_code & GENMASK(31, 15)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: reserved bits */ + if (intr_info & INTR_INFO_RESVD_BITS_MASK) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry instruction length */ + switch (intr_type) { + case INTR_TYPE_SOFT_EXCEPTION: + case INTR_TYPE_SOFT_INTR: + case INTR_TYPE_PRIV_SW_EXCEPTION: + if ((vmcs12->vm_entry_instruction_len > 15) || + (vmcs12->vm_entry_instruction_len == 0 && + !nested_cpu_has_zero_length_injection(vcpu))) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + } + } + return 0; } @@ -11686,7 +11775,6 @@ 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; @@ -11708,10 +11796,10 @@ 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/kvm/x86.h b/arch/x86/kvm/x86.h index 331993c49dae..257f27620bc2 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -110,6 +110,15 @@ static inline bool is_la57_mode(struct kvm_vcpu *vcpu) #endif } +static inline bool x86_exception_has_error_code(unsigned int vector) +{ + static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) | + BIT(NP_VECTOR) | BIT(SS_VECTOR) | BIT(GP_VECTOR) | + BIT(PF_VECTOR) | BIT(AC_VECTOR); + + return (1U << vector) & exception_has_error_code; +} + static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) { return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; 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/mm/init_64.c b/arch/x86/mm/init_64.c index 045f492d5f68..a688617c727e 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1350,16 +1350,28 @@ int kern_addr_valid(unsigned long addr) /* Amount of ram needed to start using large blocks */ #define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30) +/* Adjustable memory block size */ +static unsigned long set_memory_block_size; +int __init set_memory_block_size_order(unsigned int order) +{ + unsigned long size = 1UL << order; + + if (size > MEM_SIZE_FOR_LARGE_BLOCK || size < MIN_MEMORY_BLOCK_SIZE) + return -EINVAL; + + set_memory_block_size = size; + return 0; +} + static unsigned long probe_memory_block_size(void) { unsigned long boot_mem_end = max_pfn << PAGE_SHIFT; unsigned long bz; - /* If this is UV system, always set 2G block size */ - if (is_uv_system()) { - bz = MAX_BLOCK_SIZE; + /* If memory block size has been set, then use it */ + bz = set_memory_block_size; + if (bz) goto done; - } /* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */ if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) { diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 55799873ebe5..8f6cc71e0848 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1441,8 +1441,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth) /* sub esp,STACK_SIZE */ EMIT2_off32(0x81, 0xEC, STACK_SIZE); - /* sub ebp,SCRATCH_SIZE+4+12*/ - EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16); + /* sub ebp,SCRATCH_SIZE+12*/ + EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 12); /* xor ebx,ebx */ EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX)); @@ -1475,8 +1475,8 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) /* mov edx,dword ptr [ebp+off]*/ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1])); - /* add ebp,SCRATCH_SIZE+4+12*/ - EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16); + /* add ebp,SCRATCH_SIZE+12*/ + EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 12); /* mov ebx,dword ptr [ebp-12]*/ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index e01f7ceb9e7a..5f2eb3231607 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); @@ -417,7 +417,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va) if (!(md->attribute & EFI_MEMORY_WB)) flags |= _PAGE_PCD; - if (sev_active()) + if (sev_active() && md->type != EFI_MEMORY_MAPPED_IO) flags |= _PAGE_ENC; pfn = md->phys_addr >> PAGE_SHIFT; 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/um/mem_32.c b/arch/x86/um/mem_32.c index 744afdc18cf3..56c44d865f7b 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -16,7 +16,7 @@ static int __init gate_vma_init(void) if (!FIXADDR_USER_START) return 0; - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c9081c6671f0..3b5318505c69 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -65,6 +65,13 @@ __read_mostly int xen_have_vector_callback; EXPORT_SYMBOL_GPL(xen_have_vector_callback); /* + * NB: needs to live in .data because it's used by xen_prepare_pvh which runs + * before clearing the bss. + */ +uint32_t xen_start_flags __attribute__((section(".data"))) = 0; +EXPORT_SYMBOL(xen_start_flags); + +/* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. */ diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 357969a3697c..439a94bf89ad 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1203,15 +1203,24 @@ asmlinkage __visible void __init xen_start_kernel(void) return; xen_domain_type = XEN_PV_DOMAIN; + xen_start_flags = xen_start_info->flags; 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; @@ -1224,10 +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 @@ -1248,20 +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/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index aa1c6a6831a9..c85d1a88f476 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -97,6 +97,7 @@ void __init xen_prepare_pvh(void) } xen_pvh = 1; + xen_start_flags = pvh_start_info.flags; msr = cpuid_ebx(xen_cpuid_base() + 2); pfn = __pa(hypercall_page); 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; } diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 2e20ae2fa2d6..e3b18ad49889 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -32,6 +32,7 @@ #include <xen/interface/vcpu.h> #include <xen/interface/xenpmu.h> +#include <asm/spec-ctrl.h> #include <asm/xen/interface.h> #include <asm/xen/hypercall.h> @@ -70,6 +71,8 @@ static void cpu_bringup(void) cpu_data(cpu).x86_max_cores = 1; set_cpu_sibling_map(cpu); + speculative_store_bypass_ht_init(); + xen_setup_cpu_clockevents(); notify_cpu_starting(cpu); @@ -250,6 +253,8 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus) } set_cpu_sibling_map(0); + speculative_store_bypass_ht_init(); + xen_pmu_init(0); if (xen_smp_intr_init(0) || xen_smp_intr_init_pv(0)) |