diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt index 54944c71b819..2a4ee6302122 100644 --- a/Documentation/x86/pat.txt +++ b/Documentation/x86/pat.txt @@ -196,3 +196,35 @@ Another, more verbose way of getting PAT related debug messages is with "debugpat" boot parameter. With this parameter, various debug messages are printed to dmesg log. +PAT Initialization +------------------ + +The following table describes how PAT is initialized under various +configurations. The PAT MSR must be updated by Linux in order to support WC +and WT attributes. Otherwise, the PAT MSR has the value programmed in it +by the firmware. Note, Xen enables WC attribute in the PAT MSR for guests. + + MTRR PAT Call Sequence PAT State PAT MSR + ========================================================= + E E MTRR -> PAT init Enabled OS + E D MTRR -> PAT init Disabled - + D E MTRR -> PAT disable Disabled BIOS + D D MTRR -> PAT disable Disabled - + - np/E PAT -> PAT disable Disabled BIOS + - np/D PAT -> PAT disable Disabled - + E !P/E MTRR -> PAT init Disabled BIOS + D !P/E MTRR -> PAT disable Disabled BIOS + !M !P/E MTRR stub -> PAT disable Disabled BIOS + + Legend + ------------------------------------------------ + E Feature enabled in CPU + D Feature disabled/unsupported in CPU + np "nopat" boot option specified + !P CONFIG_X86_PAT option unset + !M CONFIG_MTRR option unset + Enabled PAT state set to enabled + Disabled PAT state set to disabled + OS PAT initializes PAT MSR with OS setting + BIOS PAT keeps PAT MSR with BIOS setting + diff --git a/arch/ia64/include/asm/iommu.h b/arch/ia64/include/asm/iommu.h index 105c93b00b1b..1d1212901ae7 100644 --- a/arch/ia64/include/asm/iommu.h +++ b/arch/ia64/include/asm/iommu.h @@ -1,7 +1,6 @@ #ifndef _ASM_IA64_IOMMU_H #define _ASM_IA64_IOMMU_H 1 -#define cpu_has_x2apic 0 /* 10 seconds */ #define DMAR_OPERATION_TIMEOUT (((cycles_t) local_cpu_data->itc_freq)*10) diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 064c7e2bd7c8..5b7fa1471007 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1477,7 +1477,7 @@ static int __init aesni_init(void) } aesni_ctr_enc_tfm = aesni_ctr_enc; #ifdef CONFIG_AS_AVX - if (cpu_has_avx) { + if (boot_cpu_has(X86_FEATURE_AVX)) { /* optimize performance of ctr mode encryption transform */ aesni_ctr_enc_tfm = aesni_ctr_enc_avx_tfm; pr_info("AES CTR mode by8 optimization enabled\n"); diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index d84456924563..60907c139c4e 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -562,7 +562,10 @@ static int __init camellia_aesni_init(void) { const char *feature_name; - if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { + if (!boot_cpu_has(X86_FEATURE_AVX) || + !boot_cpu_has(X86_FEATURE_AVX2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE)) { pr_info("AVX2 or AES-NI instructions are not detected.\n"); return -ENODEV; } diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 93d8f295784e..d96429da88eb 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -554,7 +554,9 @@ static int __init camellia_aesni_init(void) { const char *feature_name; - if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { + if (!boot_cpu_has(X86_FEATURE_AVX) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE)) { pr_info("AVX or AES-NI instructions are not detected.\n"); return -ENODEV; } diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c index 8baaff5af0b5..2d5c2e0bd939 100644 --- a/arch/x86/crypto/chacha20_glue.c +++ b/arch/x86/crypto/chacha20_glue.c @@ -129,7 +129,8 @@ static int __init chacha20_simd_mod_init(void) return -ENODEV; #ifdef CONFIG_AS_AVX2 - chacha20_use_avx2 = cpu_has_avx && cpu_has_avx2 && + chacha20_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) && + boot_cpu_has(X86_FEATURE_AVX2) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); #endif return crypto_register_alg(&alg); diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 4264a3d59589..e32142bc071d 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -179,11 +179,12 @@ static struct shash_alg alg = { static int __init poly1305_simd_mod_init(void) { - if (!cpu_has_xmm2) + if (!boot_cpu_has(X86_FEATURE_XMM2)) return -ENODEV; #ifdef CONFIG_AS_AVX2 - poly1305_use_avx2 = cpu_has_avx && cpu_has_avx2 && + poly1305_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) && + boot_cpu_has(X86_FEATURE_AVX2) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); alg.descsize = sizeof(struct poly1305_simd_desc_ctx); if (poly1305_use_avx2) diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index 6d198342e2de..870f6d812a2d 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -538,7 +538,7 @@ static int __init init(void) { const char *feature_name; - if (!cpu_has_avx2 || !cpu_has_osxsave) { + if (!boot_cpu_has(X86_FEATURE_AVX2) || !boot_cpu_has(X86_FEATURE_OSXSAVE)) { pr_info("AVX2 instructions are not detected.\n"); return -ENODEV; } diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c index 8943407e8917..644f97ab8cac 100644 --- a/arch/x86/crypto/serpent_sse2_glue.c +++ b/arch/x86/crypto/serpent_sse2_glue.c @@ -600,7 +600,7 @@ static struct crypto_alg serpent_algs[10] = { { static int __init serpent_sse2_init(void) { - if (!cpu_has_xmm2) { + if (!boot_cpu_has(X86_FEATURE_XMM2)) { printk(KERN_INFO "SSE2 instructions are not detected.\n"); return -ENODEV; } diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index dd14616b7739..1024e378a358 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -166,7 +166,7 @@ static struct shash_alg sha1_avx_alg = { static bool avx_usable(void) { if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { - if (cpu_has_avx) + if (boot_cpu_has(X86_FEATURE_AVX)) pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 5f4d6086dc59..3ae0f43ebd37 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -201,7 +201,7 @@ static struct shash_alg sha256_avx_algs[] = { { static bool avx_usable(void) { if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { - if (cpu_has_avx) + if (boot_cpu_has(X86_FEATURE_AVX)) pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 34e5083d6f36..0b17c83d027d 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -151,7 +151,7 @@ asmlinkage void sha512_transform_avx(u64 *digest, const char *data, static bool avx_usable(void) { if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { - if (cpu_has_avx) + if (boot_cpu_has(X86_FEATURE_AVX)) pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index e79d93d44ecd..ec138e538c44 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -191,7 +191,7 @@ long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, long syscall_trace_enter(struct pt_regs *regs) { - u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; + u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch); if (phase1_result == 0) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 10868aa734dc..983e5d3a0d27 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -207,10 +207,7 @@ ENTRY(ret_from_fork) pushl %eax call schedule_tail - GET_THREAD_INFO(%ebp) popl %eax - pushl $0x0202 # Reset kernel eflags - popfl /* When we fork, we trace the syscall return in the child, too. */ movl %esp, %eax @@ -221,10 +218,7 @@ END(ret_from_fork) ENTRY(ret_from_kernel_thread) pushl %eax call schedule_tail - GET_THREAD_INFO(%ebp) popl %eax - pushl $0x0202 # Reset kernel eflags - popfl movl PT_EBP(%esp), %eax call *PT_EBX(%esp) movl $0, PT_EAX(%esp) @@ -251,7 +245,6 @@ ENDPROC(ret_from_kernel_thread) ret_from_exception: preempt_stop(CLBR_ANY) ret_from_intr: - GET_THREAD_INFO(%ebp) #ifdef CONFIG_VM86 movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS movb PT_CS(%esp), %al diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 858b555e274b..9ee0da1807ed 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -372,9 +372,6 @@ END(ptregs_\func) ENTRY(ret_from_fork) LOCK ; btr $TIF_FORK, TI_flags(%r8) - pushq $0x0002 - popfq /* reset kernel eflags */ - call schedule_tail /* rdi: 'prev' task parameter */ testb $3, CS(%rsp) /* from kernel_thread? */ @@ -781,19 +778,25 @@ ENTRY(native_load_gs_index) pushfq DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) SWAPGS -gs_change: +.Lgs_change: movl %edi, %gs -2: mfence /* workaround */ +2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE SWAPGS popfq ret END(native_load_gs_index) - _ASM_EXTABLE(gs_change, bad_gs) + _ASM_EXTABLE(.Lgs_change, bad_gs) .section .fixup, "ax" /* running with kernelgs */ bad_gs: SWAPGS /* switch back to user gs */ +.macro ZAP_GS + /* This can't be a string because the preprocessor needs to see it. */ + movl $__USER_DS, %eax + movl %eax, %gs +.endm + ALTERNATIVE "", "ZAP_GS", X86_BUG_NULL_SEG xorl %eax, %eax movl %eax, %gs jmp 2b @@ -1019,13 +1022,13 @@ ENTRY(error_entry) movl %ecx, %eax /* zero extend */ cmpq %rax, RIP+8(%rsp) je .Lbstep_iret - cmpq $gs_change, RIP+8(%rsp) + cmpq $.Lgs_change, RIP+8(%rsp) jne .Lerror_entry_done /* - * hack: gs_change can fail with user gsbase. If this happens, fix up + * hack: .Lgs_change can fail with user gsbase. If this happens, fix up * gsbase and proceed. We'll fix up the exception and land in - * gs_change's error handler with kernel gsbase. + * .Lgs_change's error handler with kernel gsbase. */ jmp .Lerror_entry_from_usermode_swapgs diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 847f2f0c31e5..e1721dafbcb1 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -72,24 +72,23 @@ ENTRY(entry_SYSENTER_compat) pushfq /* pt_regs->flags (except IF = 0) */ orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */ pushq $__USER32_CS /* pt_regs->cs */ - xorq %r8,%r8 - pushq %r8 /* pt_regs->ip = 0 (placeholder) */ + pushq $0 /* pt_regs->ip = 0 (placeholder) */ pushq %rax /* pt_regs->orig_ax */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 = 0 */ - pushq %r8 /* pt_regs->r9 = 0 */ - pushq %r8 /* pt_regs->r10 = 0 */ - pushq %r8 /* pt_regs->r11 = 0 */ + pushq $0 /* pt_regs->r8 = 0 */ + pushq $0 /* pt_regs->r9 = 0 */ + pushq $0 /* pt_regs->r10 = 0 */ + pushq $0 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ - pushq %r8 /* pt_regs->r12 = 0 */ - pushq %r8 /* pt_regs->r13 = 0 */ - pushq %r8 /* pt_regs->r14 = 0 */ - pushq %r8 /* pt_regs->r15 = 0 */ + pushq $0 /* pt_regs->r12 = 0 */ + pushq $0 /* pt_regs->r13 = 0 */ + pushq $0 /* pt_regs->r14 = 0 */ + pushq $0 /* pt_regs->r15 = 0 */ cld /* @@ -205,17 +204,16 @@ ENTRY(entry_SYSCALL_compat) pushq %rdx /* pt_regs->dx */ pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ - xorq %r8,%r8 - pushq %r8 /* pt_regs->r8 = 0 */ - pushq %r8 /* pt_regs->r9 = 0 */ - pushq %r8 /* pt_regs->r10 = 0 */ - pushq %r8 /* pt_regs->r11 = 0 */ + pushq $0 /* pt_regs->r8 = 0 */ + pushq $0 /* pt_regs->r9 = 0 */ + pushq $0 /* pt_regs->r10 = 0 */ + pushq $0 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ - pushq %r8 /* pt_regs->r12 = 0 */ - pushq %r8 /* pt_regs->r13 = 0 */ - pushq %r8 /* pt_regs->r14 = 0 */ - pushq %r8 /* pt_regs->r15 = 0 */ + pushq $0 /* pt_regs->r12 = 0 */ + pushq $0 /* pt_regs->r13 = 0 */ + pushq $0 /* pt_regs->r14 = 0 */ + pushq $0 /* pt_regs->r15 = 0 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -316,11 +314,10 @@ ENTRY(entry_INT80_compat) pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ - xorq %r8,%r8 - pushq %r8 /* pt_regs->r8 = 0 */ - pushq %r8 /* pt_regs->r9 = 0 */ - pushq %r8 /* pt_regs->r10 = 0 */ - pushq %r8 /* pt_regs->r11 = 0 */ + pushq $0 /* pt_regs->r8 = 0 */ + pushq $0 /* pt_regs->r9 = 0 */ + pushq $0 /* pt_regs->r10 = 0 */ + pushq $0 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ pushq %rbp /* pt_regs->rbp */ pushq %r12 /* pt_regs->r12 */ diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index cac6d17ce5db..555263e385c9 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -374,3 +374,5 @@ 543 x32 io_setup compat_sys_io_setup 544 x32 io_submit compat_sys_io_submit 545 x32 execveat compat_sys_execveat/ptregs +534 x32 preadv2 compat_sys_preadv2 +535 x32 pwritev2 compat_sys_pwritev2 diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 03c3eb77bfce..2f02d23a05ef 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -13,7 +13,6 @@ #include #include -#include #include #include #include @@ -28,16 +27,6 @@ extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts); extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); extern time_t __vdso_time(time_t *t); -#ifdef CONFIG_HPET_TIMER -extern u8 hpet_page - __attribute__((visibility("hidden"))); - -static notrace cycle_t vread_hpet(void) -{ - return *(const volatile u32 *)(&hpet_page + HPET_COUNTER); -} -#endif - #ifdef CONFIG_PARAVIRT_CLOCK extern u8 pvclock_page __attribute__((visibility("hidden"))); @@ -195,10 +184,6 @@ notrace static inline u64 vgetsns(int *mode) if (gtod->vclock_mode == VCLOCK_TSC) cycles = vread_tsc(); -#ifdef CONFIG_HPET_TIMER - else if (gtod->vclock_mode == VCLOCK_HPET) - cycles = vread_hpet(); -#endif #ifdef CONFIG_PARAVIRT_CLOCK else if (gtod->vclock_mode == VCLOCK_PVCLOCK) cycles = vread_pvclock(mode); diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index 4158acc17df0..a708aa90b507 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -25,7 +25,7 @@ SECTIONS * segment. */ - vvar_start = . - 3 * PAGE_SIZE; + vvar_start = . - 2 * PAGE_SIZE; vvar_page = vvar_start; /* Place all vvars at the offsets in asm/vvar.h. */ @@ -35,8 +35,7 @@ SECTIONS #undef __VVAR_KERNEL_LDS #undef EMIT_VVAR - hpet_page = vvar_start + PAGE_SIZE; - pvclock_page = vvar_start + 2 * PAGE_SIZE; + pvclock_page = vvar_start + PAGE_SIZE; . = SIZEOF_HEADERS; diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 10f704584922..b3cf81333a54 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include @@ -129,16 +128,6 @@ static int vvar_fault(const struct vm_special_mapping *sm, if (sym_offset == image->sym_vvar_page) { ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, __pa_symbol(&__vvar_page) >> PAGE_SHIFT); - } else if (sym_offset == image->sym_hpet_page) { -#ifdef CONFIG_HPET_TIMER - if (hpet_address && vclock_was_used(VCLOCK_HPET)) { - ret = vm_insert_pfn_prot( - vma, - (unsigned long)vmf->virtual_address, - hpet_address >> PAGE_SHIFT, - pgprot_noncached(PAGE_READONLY)); - } -#endif } else if (sym_offset == image->sym_pvclock_page) { struct pvclock_vsyscall_time_info *pvti = pvclock_pvti_cpu0_va(); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index b7080bef9137..73a75aa5a66d 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1524,7 +1524,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) static void __init pmu_check_apic(void) { - if (cpu_has_apic) + if (boot_cpu_has(X86_FEATURE_APIC)) return; x86_pmu.apic = 0; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 17734a6ef474..16c178916412 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1400,7 +1400,7 @@ static int __init intel_uncore_init(void) if (!id) return -ENODEV; - if (cpu_has_hypervisor) + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) return -ENODEV; max_packages = topology_max_packages(); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 0552884da18d..2f29f4e407c3 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -357,7 +357,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, put_user_ex(ptr_to_compat(&frame->uc), &frame->puc); /* Create the ucontext. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); else put_user_ex(0, &frame->uc.uc_flags); diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 99afb665a004..e77a6443104f 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -1,11 +1,12 @@ #ifndef _ASM_X86_ALTERNATIVE_H #define _ASM_X86_ALTERNATIVE_H +#ifndef __ASSEMBLY__ + #include #include #include #include -#include /* * Alternative inline assembly for SMP. @@ -233,36 +234,6 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr -struct paravirt_patch_site; -#ifdef CONFIG_PARAVIRT -void apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end); -#else -static inline void apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end) -{} -#define __parainstructions NULL -#define __parainstructions_end NULL -#endif - -extern void *text_poke_early(void *addr, const void *opcode, size_t len); - -/* - * Clear and restore the kernel write-protection flag on the local CPU. - * Allows the kernel to edit read-only pages. - * Side-effect: any interrupt handler running between save and restore will have - * the ability to write to read-only pages. - * - * Warning: - * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and - * no thread can be preempted in the instructions being modified (no iret to an - * invalid instruction possible) or if the instructions are changed from a - * consistent state to another consistent state atomically. - * On the local CPU you need to be protected again NMI or MCE handlers seeing an - * inconsistent instruction while you patch. - */ -extern void *text_poke(void *addr, const void *opcode, size_t len); -extern int poke_int3_handler(struct pt_regs *regs); -extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); +#endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 98f25bbafac4..bc27611fa58f 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -239,10 +239,10 @@ extern void __init check_x2apic(void); extern void x2apic_setup(void); static inline int x2apic_enabled(void) { - return cpu_has_x2apic && apic_is_x2apic_enabled(); + return boot_cpu_has(X86_FEATURE_X2APIC) && apic_is_x2apic_enabled(); } -#define x2apic_supported() (cpu_has_x2apic) +#define x2apic_supported() (boot_cpu_has(X86_FEATURE_X2APIC)) #else /* !CONFIG_X86_X2APIC */ static inline void check_x2apic(void) { } static inline void x2apic_setup(void) { } diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h index d194266acb28..eae33c7170c8 100644 --- a/arch/x86/include/asm/clocksource.h +++ b/arch/x86/include/asm/clocksource.h @@ -3,11 +3,10 @@ #ifndef _ASM_X86_CLOCKSOURCE_H #define _ASM_X86_CLOCKSOURCE_H -#define VCLOCK_NONE 0 /* No vDSO clock available. */ -#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ -#define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */ -#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */ -#define VCLOCK_MAX 3 +#define VCLOCK_NONE 0 /* No vDSO clock available. */ +#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ +#define VCLOCK_PVCLOCK 2 /* vDSO should use vread_pvclock. */ +#define VCLOCK_MAX 2 struct arch_clocksource_data { int vclock_mode; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index ebb102e1bbc7..5a3b2c119ed0 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -307,7 +307,7 @@ static inline void __user *arch_compat_alloc_user_space(long len) return (void __user *)round_down(sp - len, 16); } -static inline bool is_x32_task(void) +static inline bool in_x32_syscall(void) { #ifdef CONFIG_X86_X32_ABI if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT) @@ -318,7 +318,7 @@ static inline bool is_x32_task(void) static inline bool in_compat_syscall(void) { - return is_ia32_task() || is_x32_task(); + return in_ia32_syscall() || in_x32_syscall(); } #define in_compat_syscall in_compat_syscall /* override the generic impl */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 53ac9bbf2064..25ebb54905e0 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -119,31 +119,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) -#define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU) -#define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE) -#define cpu_has_tsc boot_cpu_has(X86_FEATURE_TSC) -#define cpu_has_pge boot_cpu_has(X86_FEATURE_PGE) -#define cpu_has_apic boot_cpu_has(X86_FEATURE_APIC) -#define cpu_has_fxsr boot_cpu_has(X86_FEATURE_FXSR) -#define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM) -#define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2) -#define cpu_has_aes boot_cpu_has(X86_FEATURE_AES) -#define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX) -#define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2) -#define cpu_has_clflush boot_cpu_has(X86_FEATURE_CLFLUSH) -#define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES) -#define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON) -#define cpu_has_pat boot_cpu_has(X86_FEATURE_PAT) -#define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) -#define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) -#define cpu_has_xsaves boot_cpu_has(X86_FEATURE_XSAVES) -#define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) -#define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) -/* - * Do not add any more of those clumsy macros - use static_cpu_has() for - * fast paths and boot_cpu_has() otherwise! - */ - #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS) /* * Static testing of CPU features. Used the same as boot_cpu_has(). diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 0aee9dd1976e..4a413485f9eb 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -301,6 +301,9 @@ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ + #ifdef CONFIG_X86_32 /* diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 15340e36ddcb..fea7724141a0 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -176,7 +176,7 @@ static inline void elf_common_init(struct thread_struct *t, regs->si = regs->di = regs->bp = 0; regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0; regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; - t->fs = t->gs = 0; + t->fsbase = t->gsbase = 0; t->fsindex = t->gsindex = 0; t->ds = t->es = ds; } @@ -226,8 +226,8 @@ do { \ (pr_reg)[18] = (regs)->flags; \ (pr_reg)[19] = (regs)->sp; \ (pr_reg)[20] = (regs)->ss; \ - (pr_reg)[21] = current->thread.fs; \ - (pr_reg)[22] = current->thread.gs; \ + (pr_reg)[21] = current->thread.fsbase; \ + (pr_reg)[22] = current->thread.gsbase; \ asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v; \ asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v; \ asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v; \ diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index e6a8613fbfb0..3a106165e03a 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -4,7 +4,7 @@ #include #include -#define hugepages_supported() cpu_has_pse +#define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE) static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index d0afb05c84fc..f70604125286 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -5,7 +5,7 @@ static inline bool arch_irq_work_has_interrupt(void) { - return cpu_has_apic; + return boot_cpu_has(X86_FEATURE_APIC); } #endif /* _ASM_IRQ_WORK_H */ diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index 332f98c9111f..22a8537eb780 100644 --- a/arch/x86/include/asm/kgdb.h +++ b/arch/x86/include/asm/kgdb.h @@ -6,6 +6,8 @@ * Copyright (C) 2008 Wind River Systems, Inc. */ +#include + /* * BUFMAX defines the maximum number of characters in inbound/outbound * buffers at least NUMREGBYTES*2 are needed for register packets diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 79327e9483a3..0ccb26dda126 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -8,40 +8,6 @@ #ifdef CONFIG_X86_32 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0))) - -/* - * Make sure the compiler doesn't do anything stupid with the - * arguments on the stack - they are owned by the *caller*, not - * the callee. This just fools gcc into not spilling into them, - * and keeps it from doing tailcall recursion and/or using the - * stack slots for temporaries, since they are live and "used" - * all the way to the end of the function. - * - * NOTE! On x86-64, all the arguments are in registers, so this - * only matters on a 32-bit kernel. - */ -#define asmlinkage_protect(n, ret, args...) \ - __asmlinkage_protect##n(ret, ##args) -#define __asmlinkage_protect_n(ret, args...) \ - __asm__ __volatile__ ("" : "=r" (ret) : "0" (ret), ##args) -#define __asmlinkage_protect0(ret) \ - __asmlinkage_protect_n(ret) -#define __asmlinkage_protect1(ret, arg1) \ - __asmlinkage_protect_n(ret, "m" (arg1)) -#define __asmlinkage_protect2(ret, arg1, arg2) \ - __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2)) -#define __asmlinkage_protect3(ret, arg1, arg2, arg3) \ - __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3)) -#define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \ - __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ - "m" (arg4)) -#define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \ - __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ - "m" (arg4), "m" (arg5)) -#define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \ - __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ - "m" (arg4), "m" (arg5), "m" (arg6)) - #endif /* CONFIG_X86_32 */ #ifdef __ASSEMBLY__ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 7a79ee2778b3..7dc1d8fef7fd 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -84,7 +84,10 @@ static inline unsigned long long native_read_msr(unsigned int msr) { DECLARE_ARGS(val, low, high); - asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr)); + asm volatile("1: rdmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe) + : EAX_EDX_RET(val, low, high) : "c" (msr)); if (msr_tracepoint_active(__tracepoint_read_msr)) do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); @@ -98,7 +101,10 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, asm volatile("2: rdmsr ; xor %[err],%[err]\n" "1:\n\t" ".section .fixup,\"ax\"\n\t" - "3: mov %[fault],%[err] ; jmp 1b\n\t" + "3: mov %[fault],%[err]\n\t" + "xorl %%eax, %%eax\n\t" + "xorl %%edx, %%edx\n\t" + "jmp 1b\n\t" ".previous\n\t" _ASM_EXTABLE(2b, 3b) : [err] "=r" (*err), EAX_EDX_RET(val, low, high) @@ -108,10 +114,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, return EAX_EDX_VAL(val, low, high); } -static inline void native_write_msr(unsigned int msr, - unsigned low, unsigned high) +/* Can be uninlined because referenced by paravirt */ +notrace static inline void native_write_msr(unsigned int msr, + unsigned low, unsigned high) { - asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory"); + asm volatile("1: wrmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe) + : : "c" (msr), "a"(low), "d" (high) : "memory"); if (msr_tracepoint_active(__tracepoint_read_msr)) do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index b94f6f64e23d..dbff1456d215 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -24,6 +24,7 @@ #define _ASM_X86_MTRR_H #include +#include /* @@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) { } +static inline void mtrr_bp_init(void) +{ + pat_disable("MTRRs disabled, skipping PAT initialization too."); +} #define mtrr_ap_init() do {} while (0) -#define mtrr_bp_init() do {} while (0) #define set_mtrr_aps_delayed_init() do {} while (0) #define mtrr_aps_init() do {} while (0) #define mtrr_bp_restore() do {} while (0) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 601f1b8f9961..3c731413f1de 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -130,21 +130,31 @@ static inline void wbinvd(void) #define get_kernel_rpl() (pv_info.kernel_rpl) -static inline u64 paravirt_read_msr(unsigned msr, int *err) +static inline u64 paravirt_read_msr(unsigned msr) { - return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err); + return PVOP_CALL1(u64, pv_cpu_ops.read_msr, msr); } -static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high) +static inline void paravirt_write_msr(unsigned msr, + unsigned low, unsigned high) { - return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high); + return PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high); +} + +static inline u64 paravirt_read_msr_safe(unsigned msr, int *err) +{ + return PVOP_CALL2(u64, pv_cpu_ops.read_msr_safe, msr, err); +} + +static inline int paravirt_write_msr_safe(unsigned msr, + unsigned low, unsigned high) +{ + return PVOP_CALL3(int, pv_cpu_ops.write_msr_safe, msr, low, high); } -/* These should all do BUG_ON(_err), but our headers are too tangled. */ #define rdmsr(msr, val1, val2) \ do { \ - int _err; \ - u64 _l = paravirt_read_msr(msr, &_err); \ + u64 _l = paravirt_read_msr(msr); \ val1 = (u32)_l; \ val2 = _l >> 32; \ } while (0) @@ -156,8 +166,7 @@ do { \ #define rdmsrl(msr, val) \ do { \ - int _err; \ - val = paravirt_read_msr(msr, &_err); \ + val = paravirt_read_msr(msr); \ } while (0) static inline void wrmsrl(unsigned msr, u64 val) @@ -165,23 +174,23 @@ static inline void wrmsrl(unsigned msr, u64 val) wrmsr(msr, (u32)val, (u32)(val>>32)); } -#define wrmsr_safe(msr, a, b) paravirt_write_msr(msr, a, b) +#define wrmsr_safe(msr, a, b) paravirt_write_msr_safe(msr, a, b) /* rdmsr with exception handling */ -#define rdmsr_safe(msr, a, b) \ -({ \ - int _err; \ - u64 _l = paravirt_read_msr(msr, &_err); \ - (*a) = (u32)_l; \ - (*b) = _l >> 32; \ - _err; \ +#define rdmsr_safe(msr, a, b) \ +({ \ + int _err; \ + u64 _l = paravirt_read_msr_safe(msr, &_err); \ + (*a) = (u32)_l; \ + (*b) = _l >> 32; \ + _err; \ }) static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) { int err; - *p = paravirt_read_msr(msr, &err); + *p = paravirt_read_msr_safe(msr, &err); return err; } diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index e8c2326478c8..b4a23eafa1b9 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -155,10 +155,16 @@ struct pv_cpu_ops { void (*cpuid)(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx); - /* MSR, PMC and TSR operations. - err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */ - u64 (*read_msr)(unsigned int msr, int *err); - int (*write_msr)(unsigned int msr, unsigned low, unsigned high); + /* Unsafe MSR operations. These will warn or panic on failure. */ + u64 (*read_msr)(unsigned int msr); + void (*write_msr)(unsigned int msr, unsigned low, unsigned high); + + /* + * Safe MSR operations. + * read sets err to 0 or -EIO. write returns 0 or -EIO. + */ + u64 (*read_msr_safe)(unsigned int msr, int *err); + int (*write_msr_safe)(unsigned int msr, unsigned low, unsigned high); u64 (*read_pmc)(int counter); diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index ca6c228d5e62..0b1ff4c1c14e 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -5,8 +5,8 @@ #include bool pat_enabled(void); +void pat_disable(const char *reason); extern void pat_init(void); -void pat_init_cache_modes(u64); extern int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 97f3242e133c..f86491a7bc9d 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -183,7 +183,7 @@ static inline int pmd_trans_huge(pmd_t pmd) static inline int has_transparent_hugepage(void) { - return cpu_has_pse; + return boot_cpu_has(X86_FEATURE_PSE); } #ifdef __HAVE_ARCH_PTE_DEVMAP diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 9264476f3d57..9251aa962721 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -388,9 +388,16 @@ struct thread_struct { unsigned long ip; #endif #ifdef CONFIG_X86_64 - unsigned long fs; + unsigned long fsbase; + unsigned long gsbase; +#else + /* + * XXX: this could presumably be unsigned short. Alternatively, + * 32-bit kernels could be taught to use fsindex instead. + */ + unsigned long fs; + unsigned long gs; #endif - unsigned long gs; /* Save middle states of ptrace breakpoints */ struct perf_event *ptrace_bps[HBP_NUM]; diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 7d5a1929d76b..1549caa098f0 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -2,6 +2,7 @@ #define _ASM_X86_SEGMENT_H #include +#include /* * Constructor for a conventional segment GDT (or LDT) entry. @@ -207,13 +208,6 @@ #define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) #define __PER_CPU_SEG (GDT_ENTRY_PER_CPU*8 + 3) -/* TLS indexes for 64-bit - hardcoded in arch_prctl(): */ -#define FS_TLS 0 -#define GS_TLS 1 - -#define GS_TLS_SEL ((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3) -#define FS_TLS_SEL ((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3) - #endif #ifndef CONFIG_PARAVIRT @@ -249,10 +243,13 @@ extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDL #endif /* - * Load a segment. Fall back on loading the zero - * segment if something goes wrong.. + * Load a segment. Fall back on loading the zero segment if something goes + * wrong. This variant assumes that loading zero fully clears the segment. + * This is always the case on Intel CPUs and, even on 64-bit AMD CPUs, any + * failure to fully clear the cached descriptor is only observable for + * FS and GS. */ -#define loadsegment(seg, value) \ +#define __loadsegment_simple(seg, value) \ do { \ unsigned short __val = (value); \ \ @@ -269,6 +266,38 @@ do { \ : "+r" (__val) : : "memory"); \ } while (0) +#define __loadsegment_ss(value) __loadsegment_simple(ss, (value)) +#define __loadsegment_ds(value) __loadsegment_simple(ds, (value)) +#define __loadsegment_es(value) __loadsegment_simple(es, (value)) + +#ifdef CONFIG_X86_32 + +/* + * On 32-bit systems, the hidden parts of FS and GS are unobservable if + * the selector is NULL, so there's no funny business here. + */ +#define __loadsegment_fs(value) __loadsegment_simple(fs, (value)) +#define __loadsegment_gs(value) __loadsegment_simple(gs, (value)) + +#else + +static inline void __loadsegment_fs(unsigned short value) +{ + asm volatile(" \n" + "1: movw %0, %%fs \n" + "2: \n" + + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_clear_fs) + + : : "rm" (value) : "memory"); +} + +/* __loadsegment_gs is intentionally undefined. Use load_gs_index instead. */ + +#endif + +#define loadsegment(seg, value) __loadsegment_ ## seg (value) + /* * Save a segment register away: */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 11af24e09c8a..ac1d5da14734 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -6,6 +6,7 @@ #define COMMAND_LINE_SIZE 2048 #include +#include #ifdef __i386__ diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 751bf4b7bf11..8f321a1b03a1 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -39,8 +39,7 @@ do { \ */ \ unsigned long ebx, ecx, edx, esi, edi; \ \ - asm volatile("pushfl\n\t" /* save flags */ \ - "pushl %%ebp\n\t" /* save EBP */ \ + asm volatile("pushl %%ebp\n\t" /* save EBP */ \ "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ @@ -49,7 +48,6 @@ do { \ "jmp __switch_to\n" /* regparm call */ \ "1:\t" \ "popl %%ebp\n\t" /* restore EBP */ \ - "popfl\n" /* restore flags */ \ \ /* output parameters */ \ : [prev_sp] "=m" (prev->thread.sp), \ diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h new file mode 100644 index 000000000000..90395063383c --- /dev/null +++ b/arch/x86/include/asm/text-patching.h @@ -0,0 +1,40 @@ +#ifndef _ASM_X86_TEXT_PATCHING_H +#define _ASM_X86_TEXT_PATCHING_H + +#include +#include +#include + +struct paravirt_patch_site; +#ifdef CONFIG_PARAVIRT +void apply_paravirt(struct paravirt_patch_site *start, + struct paravirt_patch_site *end); +#else +static inline void apply_paravirt(struct paravirt_patch_site *start, + struct paravirt_patch_site *end) +{} +#define __parainstructions NULL +#define __parainstructions_end NULL +#endif + +extern void *text_poke_early(void *addr, const void *opcode, size_t len); + +/* + * Clear and restore the kernel write-protection flag on the local CPU. + * Allows the kernel to edit read-only pages. + * Side-effect: any interrupt handler running between save and restore will have + * the ability to write to read-only pages. + * + * Warning: + * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and + * no thread can be preempted in the instructions being modified (no iret to an + * invalid instruction possible) or if the instructions are changed from a + * consistent state to another consistent state atomically. + * On the local CPU you need to be protected again NMI or MCE handlers seeing an + * inconsistent instruction while you patch. + */ +extern void *text_poke(void *addr, const void *opcode, size_t len); +extern int poke_int3_handler(struct pt_regs *regs); +extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); + +#endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index ffae84df8a93..30c133ac05cd 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -255,7 +255,7 @@ static inline bool test_and_clear_restore_sigmask(void) return true; } -static inline bool is_ia32_task(void) +static inline bool in_ia32_syscall(void) { #ifdef CONFIG_X86_32 return true; diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 1fde8d580a5b..4e5be94e079a 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -181,7 +181,7 @@ static inline void __native_flush_tlb_single(unsigned long addr) static inline void __flush_tlb_all(void) { - if (cpu_has_pge) + if (static_cpu_has(X86_FEATURE_PGE)) __flush_tlb_global(); else __flush_tlb(); diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 174c4212780a..7428697c5b8d 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -22,7 +22,7 @@ extern void disable_TSC(void); static inline cycles_t get_cycles(void) { #ifndef CONFIG_X86_TSC - if (!cpu_has_tsc) + if (!boot_cpu_has(X86_FEATURE_TSC)) return 0; #endif diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 2e7513d1f1f4..12f9653bde8d 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -118,7 +118,7 @@ struct exception_table_entry { extern int fixup_exception(struct pt_regs *regs, int trapnr); extern bool ex_has_fault_handler(unsigned long ip); -extern int early_fixup_exception(unsigned long *ip); +extern void early_fixup_exception(struct pt_regs *regs, int trapnr); /* * These are the main single-value transfer routines. They automatically diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index c54beb44c4c1..635eac543922 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -550,7 +550,7 @@ static struct xor_block_template xor_block_pIII_sse = { #define XOR_TRY_TEMPLATES \ do { \ AVX_XOR_SPEED; \ - if (cpu_has_xmm) { \ + if (boot_cpu_has(X86_FEATURE_XMM)) { \ xor_speed(&xor_block_pIII_sse); \ xor_speed(&xor_block_sse_pf64); \ } else if (boot_cpu_has(X86_FEATURE_MMX)) { \ diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h index 7c0a517ec751..22a7b1870a31 100644 --- a/arch/x86/include/asm/xor_avx.h +++ b/arch/x86/include/asm/xor_avx.h @@ -167,12 +167,12 @@ static struct xor_block_template xor_block_avx = { #define AVX_XOR_SPEED \ do { \ - if (cpu_has_avx && cpu_has_osxsave) \ + if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE)) \ xor_speed(&xor_block_avx); \ } while (0) #define AVX_SELECT(FASTEST) \ - (cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST) + (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE) ? &xor_block_avx : FASTEST) #else diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 8c2f1ef6ca23..2522e564269e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -136,7 +136,7 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) { struct acpi_table_madt *madt = NULL; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -EINVAL; madt = (struct acpi_table_madt *)table; @@ -951,7 +951,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) { int count; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; /* @@ -979,7 +979,7 @@ static int __init acpi_parse_madt_lapic_entries(void) int ret; struct acpi_subtable_proc madt_proc[2]; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; /* @@ -1125,7 +1125,7 @@ static int __init acpi_parse_madt_ioapic_entries(void) if (acpi_disabled || acpi_noirq) return -ENODEV; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; /* diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 25f909362b7a..5cb272a7a5a3 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d356987a04e9..60078a67d7e3 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -607,7 +607,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev) long tapic = apic_read(APIC_TMCCT); unsigned long pm = acpi_pm_read_early(); - if (cpu_has_tsc) + if (boot_cpu_has(X86_FEATURE_TSC)) tsc = rdtsc(); switch (lapic_cal_loops++) { @@ -668,7 +668,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) *delta = (long)res; /* Correct the tsc counter value */ - if (cpu_has_tsc) { + if (boot_cpu_has(X86_FEATURE_TSC)) { res = (((u64)(*deltatsc)) * pm_100ms); do_div(res, deltapm); apic_printk(APIC_VERBOSE, "TSC delta adjusted to " @@ -760,7 +760,7 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "..... calibration result: %u\n", lapic_timer_frequency); - if (cpu_has_tsc) { + if (boot_cpu_has(X86_FEATURE_TSC)) { apic_printk(APIC_VERBOSE, "..... CPU clock speed is " "%ld.%04ld MHz.\n", (deltatsc / LAPIC_CAL_LOOPS) / (1000000 / HZ), @@ -1085,7 +1085,7 @@ void lapic_shutdown(void) { unsigned long flags; - if (!cpu_has_apic && !apic_from_smp_config()) + if (!boot_cpu_has(X86_FEATURE_APIC) && !apic_from_smp_config()) return; local_irq_save(flags); @@ -1134,7 +1134,7 @@ void __init init_bsp_APIC(void) * Don't do the setup now if we have a SMP BIOS as the * through-I/O-APIC virtual wire mode might be active. */ - if (smp_found_config || !cpu_has_apic) + if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC)) return; /* @@ -1227,7 +1227,7 @@ void setup_local_APIC(void) unsigned long long tsc = 0, ntsc; long long max_loops = cpu_khz ? cpu_khz : 1000000; - if (cpu_has_tsc) + if (boot_cpu_has(X86_FEATURE_TSC)) tsc = rdtsc(); if (disable_apic) { @@ -1311,7 +1311,7 @@ void setup_local_APIC(void) break; } if (queued) { - if (cpu_has_tsc && cpu_khz) { + if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { ntsc = rdtsc(); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else @@ -1445,7 +1445,7 @@ static void __x2apic_disable(void) { u64 msr; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return; rdmsrl(MSR_IA32_APICBASE, msr); @@ -1561,7 +1561,7 @@ void __init check_x2apic(void) pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n"); x2apic_mode = 1; x2apic_state = X2APIC_ON; - } else if (!cpu_has_x2apic) { + } else if (!boot_cpu_has(X86_FEATURE_X2APIC)) { x2apic_state = X2APIC_DISABLED; } } @@ -1632,7 +1632,7 @@ void __init enable_IR_x2apic(void) */ static int __init detect_init_APIC(void) { - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { pr_info("No local APIC present\n"); return -1; } @@ -1711,14 +1711,14 @@ static int __init detect_init_APIC(void) goto no_apic; case X86_VENDOR_INTEL: if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 || - (boot_cpu_data.x86 == 5 && cpu_has_apic)) + (boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC))) break; goto no_apic; default: goto no_apic; } - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { /* * Over-ride BIOS and try to enable the local APIC only if * "lapic" specified. @@ -2233,19 +2233,19 @@ int __init APIC_init_uniprocessor(void) return -1; } #ifdef CONFIG_X86_64 - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { disable_apic = 1; pr_info("Apic disabled by BIOS\n"); return -1; } #else - if (!smp_found_config && !cpu_has_apic) + if (!smp_found_config && !boot_cpu_has(X86_FEATURE_APIC)) return -1; /* * Complain if the BIOS pretends there is one. */ - if (!cpu_has_apic && + if (!boot_cpu_has(X86_FEATURE_APIC) && APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) { pr_err("BIOS bug, local APIC 0x%x not detected!...\n", boot_cpu_physical_apicid); @@ -2426,7 +2426,7 @@ static void apic_pm_activate(void) static int __init init_lapic_sysfs(void) { /* XXX: remove suspend/resume procs if !apic_pm_state.active? */ - if (cpu_has_apic) + if (boot_cpu_has(X86_FEATURE_APIC)) register_syscore_ops(&lapic_syscore_ops); return 0; diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 331a7a07c48f..13d19ed58514 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -100,13 +100,13 @@ static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask, static u32 noop_apic_read(u32 reg) { - WARN_ON_ONCE((cpu_has_apic && !disable_apic)); + WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); return 0; } static void noop_apic_write(u32 reg, u32 v) { - WARN_ON_ONCE(cpu_has_apic && !disable_apic); + WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); } struct apic apic_noop = { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index fdb0fbfb1197..84e33ff5a6d5 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1454,7 +1454,7 @@ void native_disable_io_apic(void) ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry); } - if (cpu_has_apic || apic_from_smp_config()) + if (boot_cpu_has(X86_FEATURE_APIC) || apic_from_smp_config()) disconnect_bsp_APIC(ioapic_i8259.pin != -1); } diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 28bde88b0085..2a0f225afebd 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -230,7 +230,7 @@ int safe_smp_processor_id(void) { int apicid, cpuid; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return 0; apicid = hard_smp_processor_id(); diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index ef495511f019..a5e400afc563 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -944,7 +944,7 @@ static int __init print_ICs(void) print_PIC(); /* don't print out if apic is not there */ - if (!cpu_has_apic && !apic_from_smp_config()) + if (!boot_cpu_has(X86_FEATURE_APIC) && !apic_from_smp_config()) return 0; print_local_APICs(show_lapic); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7b76eb67a9b3..c343a54bed39 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -565,14 +565,17 @@ static void early_init_amd(struct cpuinfo_x86 *c) * can safely set X86_FEATURE_EXTD_APICID unconditionally for families * after 16h. */ - if (cpu_has_apic && c->x86 > 0x16) { - set_cpu_cap(c, X86_FEATURE_EXTD_APICID); - } else if (cpu_has_apic && c->x86 >= 0xf) { - /* check CPU config space for extended APIC ID */ - unsigned int val; - val = read_pci_config(0, 24, 0, 0x68); - if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18))) + if (boot_cpu_has(X86_FEATURE_APIC)) { + if (c->x86 > 0x16) set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + else if (c->x86 >= 0xf) { + /* check CPU config space for extended APIC ID */ + unsigned int val; + + val = read_pci_config(0, 24, 0, 0x68); + if ((val >> 17 & 0x3) == 0x3) + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + } } #endif @@ -628,6 +631,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c) */ msr_set_bit(MSR_K7_HWCR, 6); #endif + set_cpu_bug(c, X86_BUG_SWAPGS_FENCE); } static void init_amd_gh(struct cpuinfo_x86 *c) @@ -746,7 +750,7 @@ static void init_amd(struct cpuinfo_x86 *c) if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); - if (cpu_has_xmm2) { + if (cpu_has(c, X86_FEATURE_XMM2)) { /* MFENCE stops RDTSC speculation */ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index dbc6f066e231..6ef6ed9ccca6 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -430,7 +430,7 @@ void load_percpu_segment(int cpu) #ifdef CONFIG_X86_32 loadsegment(fs, __KERNEL_PERCPU); #else - loadsegment(gs, 0); + __loadsegment_simple(gs, 0); wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu)); #endif load_stack_canary_segment(); @@ -866,30 +866,34 @@ static void detect_nopl(struct cpuinfo_x86 *c) #else set_cpu_cap(c, X86_FEATURE_NOPL); #endif +} +static void detect_null_seg_behavior(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_X86_64 /* - * ESPFIX is a strange bug. All real CPUs have it. Paravirt - * systems that run Linux at CPL > 0 may or may not have the - * issue, but, even if they have the issue, there's absolutely - * nothing we can do about it because we can't use the real IRET - * instruction. + * Empirically, writing zero to a segment selector on AMD does + * not clear the base, whereas writing zero to a segment + * selector on Intel does clear the base. Intel's behavior + * allows slightly faster context switches in the common case + * where GS is unused by the prev and next threads. * - * NB: For the time being, only 32-bit kernels support - * X86_BUG_ESPFIX as such. 64-bit kernels directly choose - * whether to apply espfix using paravirt hooks. If any - * non-paravirt system ever shows up that does *not* have the - * ESPFIX issue, we can change this. + * Since neither vendor documents this anywhere that I can see, + * detect it directly instead of hardcoding the choice by + * vendor. + * + * I've designated AMD's behavior as the "bug" because it's + * counterintuitive and less friendly. */ -#ifdef CONFIG_X86_32 -#ifdef CONFIG_PARAVIRT - do { - extern void native_iret(void); - if (pv_cpu_ops.iret == native_iret) - set_cpu_bug(c, X86_BUG_ESPFIX); - } while (0); -#else - set_cpu_bug(c, X86_BUG_ESPFIX); -#endif + + unsigned long old_base, tmp; + rdmsrl(MSR_FS_BASE, old_base); + wrmsrl(MSR_FS_BASE, 1); + loadsegment(fs, 0); + rdmsrl(MSR_FS_BASE, tmp); + if (tmp != 0) + set_cpu_bug(c, X86_BUG_NULL_SEG); + wrmsrl(MSR_FS_BASE, old_base); #endif } @@ -925,6 +929,33 @@ static void generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ detect_nopl(c); + + detect_null_seg_behavior(c); + + /* + * ESPFIX is a strange bug. All real CPUs have it. Paravirt + * systems that run Linux at CPL > 0 may or may not have the + * issue, but, even if they have the issue, there's absolutely + * nothing we can do about it because we can't use the real IRET + * instruction. + * + * NB: For the time being, only 32-bit kernels support + * X86_BUG_ESPFIX as such. 64-bit kernels directly choose + * whether to apply espfix using paravirt hooks. If any + * non-paravirt system ever shows up that does *not* have the + * ESPFIX issue, we can change this. + */ +#ifdef CONFIG_X86_32 +# ifdef CONFIG_PARAVIRT + do { + extern void native_iret(void); + if (pv_cpu_ops.iret == native_iret) + set_cpu_bug(c, X86_BUG_ESPFIX); + } while (0); +# else + set_cpu_bug(c, X86_BUG_ESPFIX); +# endif +#endif } static void x86_init_cache_qos(struct cpuinfo_x86 *c) @@ -1080,12 +1111,12 @@ void enable_sep_cpu(void) struct tss_struct *tss; int cpu; + if (!boot_cpu_has(X86_FEATURE_SEP)) + return; + cpu = get_cpu(); tss = &per_cpu(cpu_tss, cpu); - if (!boot_cpu_has(X86_FEATURE_SEP)) - goto out; - /* * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field -- * see the big comment in struct x86_hw_tss's definition. @@ -1100,7 +1131,6 @@ void enable_sep_cpu(void) wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); -out: put_cpu(); } #endif @@ -1532,7 +1562,7 @@ void cpu_init(void) pr_info("Initializing CPU#%d\n", cpu); if (cpu_feature_enabled(X86_FEATURE_VME) || - cpu_has_tsc || + boot_cpu_has(X86_FEATURE_TSC) || boot_cpu_has(X86_FEATURE_DE)) cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 6adef9cac23e..bd9dcd6b712d 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -333,7 +333,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) switch (dir0_lsn) { case 0xd: /* either a 486SLC or DLC w/o DEVID */ dir0_msn = 0; - p = Cx486_name[(cpu_has_fpu ? 1 : 0)]; + p = Cx486_name[!!boot_cpu_has(X86_FEATURE_FPU)]; break; case 0xe: /* a 486S A step */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index e4393bfc7f0d..b18f4706e607 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -152,9 +152,9 @@ static void early_init_intel(struct cpuinfo_x86 *c) * the TLB when any changes are made to any of the page table entries. * The operating system must reload CR3 to cause the TLB to be flushed" * - * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should - * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE - * to be modified + * As a result, boot_cpu_has(X86_FEATURE_PGE) in arch/x86/include/asm/tlbflush.h + * should be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified. */ if (c->x86 == 5 && c->x86_model == 9) { pr_info("Disabling PGE capability bit\n"); @@ -281,7 +281,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * integrated APIC (see 11AP erratum in "Pentium Processor * Specification Update"). */ - if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 && + if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 && (c->x86_mask < 0x6 || c->x86_mask == 0xb)) set_cpu_bug(c, X86_BUG_11AP); @@ -456,7 +456,7 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON); } - if (cpu_has_xmm2) + if (cpu_has(c, X86_FEATURE_XMM2)) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); if (boot_cpu_has(X86_FEATURE_DS)) { @@ -468,7 +468,7 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_PEBS); } - if (c->x86 == 6 && cpu_has_clflush && + if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_CLFLUSH) && (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR); diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 1e8bb6c94f14..1defb8ea882c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -84,7 +84,7 @@ static int cmci_supported(int *banks) */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; - if (!cpu_has_apic || lapic_get_maxlvt() < 6) + if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) return 0; rdmsrl(MSR_IA32_MCG_CAP, cap); *banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff); diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index ac780cad3b86..6b9dc4d18ccc 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -450,7 +450,7 @@ asmlinkage __visible void smp_trace_thermal_interrupt(struct pt_regs *regs) /* Thermal monitoring depends on APIC, ACPI and clock modulation */ static int intel_thermal_supported(struct cpuinfo_x86 *c) { - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return 0; if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC)) return 0; diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index f8c81ba0b465..b1086f79e57e 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -137,7 +137,7 @@ static void prepare_set(void) u32 cr0; /* Save value of CR4 and clear Page Global Enable (bit 7) */ - if (cpu_has_pge) { + if (boot_cpu_has(X86_FEATURE_PGE)) { cr4 = __read_cr4(); __write_cr4(cr4 & ~X86_CR4_PGE); } @@ -170,7 +170,7 @@ static void post_set(void) write_cr0(read_cr0() & ~X86_CR0_CD); /* Restore value of CR4 */ - if (cpu_has_pge) + if (boot_cpu_has(X86_FEATURE_PGE)) __write_cr4(cr4); } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 19f57360dfd2..16e37a2581ac 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -444,11 +444,24 @@ static void __init print_mtrr_state(void) pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } +/* PAT setup for BP. We need to go through sync steps here */ +void __init mtrr_bp_pat_init(void) +{ + unsigned long flags; + + local_irq_save(flags); + prepare_set(); + + pat_init(); + + post_set(); + local_irq_restore(flags); +} + /* Grab all of the MTRR state for this CPU into *state */ bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; - unsigned long flags; unsigned lo, dummy; unsigned int i; @@ -481,15 +494,6 @@ bool __init get_mtrr_state(void) mtrr_state_set = 1; - /* PAT setup for BP. We need to go through sync steps here */ - local_irq_save(flags); - prepare_set(); - - pat_init(); - - post_set(); - local_irq_restore(flags); - return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } @@ -741,7 +745,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) wbinvd(); /* Save value of CR4 and clear Page Global Enable (bit 7) */ - if (cpu_has_pge) { + if (boot_cpu_has(X86_FEATURE_PGE)) { cr4 = __read_cr4(); __write_cr4(cr4 & ~X86_CR4_PGE); } @@ -771,7 +775,7 @@ static void post_set(void) __releases(set_atomicity_lock) write_cr0(read_cr0() & ~X86_CR0_CD); /* Restore value of CR4 */ - if (cpu_has_pge) + if (boot_cpu_has(X86_FEATURE_PGE)) __write_cr4(cr4); raw_spin_unlock(&set_atomicity_lock); } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 10f8d4796240..7d393ecdeee6 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -752,6 +752,9 @@ void __init mtrr_bp_init(void) /* BIOS may override */ __mtrr_enabled = get_mtrr_state(); + if (mtrr_enabled()) + mtrr_bp_pat_init(); + if (mtrr_cleanup(phys_addr)) { changed_by_mtrr_cleanup = 1; mtrr_if->set_all(); @@ -759,8 +762,16 @@ void __init mtrr_bp_init(void) } } - if (!mtrr_enabled()) + if (!mtrr_enabled()) { pr_info("MTRR: Disabled\n"); + + /* + * PAT initialization relies on MTRR's rendezvous handler. + * Skip PAT init until the handler can initialize both + * features independently. + */ + pat_disable("MTRRs disabled, skipping PAT initialization too."); + } } void mtrr_ap_init(void) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 951884dcc433..6c7ced07d16d 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); bool get_mtrr_state(void); +void mtrr_bp_pat_init(void); extern void set_mtrr_ops(const struct mtrr_ops *ops); diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 364e58346897..8cac429b6a1d 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -94,7 +94,7 @@ static void __init vmware_platform_setup(void) */ static uint32_t __init vmware_platform(void) { - if (cpu_has_hypervisor) { + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { unsigned int eax; unsigned int hyper_vendor_id[3]; diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 1f4acd68b98b..3fe45f84ced4 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -151,7 +151,7 @@ static void __init dtb_lapic_setup(void) return; /* Did the boot loader setup the local APIC ? */ - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { if (apic_force_enable(r.start)) return; } diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index dd9ca9b60ff3..aad34aafc0e0 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -21,11 +21,15 @@ static double __initdata y = 3145727.0; * We should really only care about bugs here * anyway. Not features. */ -static void __init check_fpu(void) +void __init fpu__init_check_bugs(void) { u32 cr0_saved; s32 fdiv_bug; + /* kernel_fpu_begin/end() relies on patched alternative instructions. */ + if (!boot_cpu_has(X86_FEATURE_FPU)) + return; + /* We might have CR0::TS set already, clear it: */ cr0_saved = read_cr0(); write_cr0(cr0_saved & ~X86_CR0_TS); @@ -59,13 +63,3 @@ static void __init check_fpu(void) pr_warn("Hmm, FPU with FDIV bug\n"); } } - -void __init fpu__init_check_bugs(void) -{ - /* - * kernel_fpu_begin/end() in check_fpu() relies on the patched - * alternative instructions. - */ - if (cpu_has_fpu) - check_fpu(); -} diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 8e37cc8a539a..97027545a72d 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -217,14 +217,14 @@ static inline void fpstate_init_fstate(struct fregs_state *fp) void fpstate_init(union fpregs_state *state) { - if (!cpu_has_fpu) { + if (!static_cpu_has(X86_FEATURE_FPU)) { fpstate_init_soft(&state->soft); return; } memset(state, 0, xstate_size); - if (cpu_has_fxsr) + if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else fpstate_init_fstate(&state->fsave); @@ -237,7 +237,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) dst_fpu->fpregs_active = 0; dst_fpu->last_cpu = -1; - if (!src_fpu->fpstate_active || !cpu_has_fpu) + if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); @@ -506,33 +506,6 @@ void fpu__clear(struct fpu *fpu) * x87 math exception handling: */ -static inline unsigned short get_fpu_cwd(struct fpu *fpu) -{ - if (cpu_has_fxsr) { - return fpu->state.fxsave.cwd; - } else { - return (unsigned short)fpu->state.fsave.cwd; - } -} - -static inline unsigned short get_fpu_swd(struct fpu *fpu) -{ - if (cpu_has_fxsr) { - return fpu->state.fxsave.swd; - } else { - return (unsigned short)fpu->state.fsave.swd; - } -} - -static inline unsigned short get_fpu_mxcsr(struct fpu *fpu) -{ - if (cpu_has_xmm) { - return fpu->state.fxsave.mxcsr; - } else { - return MXCSR_DEFAULT; - } -} - int fpu__exception_code(struct fpu *fpu, int trap_nr) { int err; @@ -547,10 +520,15 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr) * so if this combination doesn't produce any single exception, * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception + * fully reproduce the context of the exception. */ - cwd = get_fpu_cwd(fpu); - swd = get_fpu_swd(fpu); + if (boot_cpu_has(X86_FEATURE_FXSR)) { + cwd = fpu->state.fxsave.cwd; + swd = fpu->state.fxsave.swd; + } else { + cwd = (unsigned short)fpu->state.fsave.cwd; + swd = (unsigned short)fpu->state.fsave.swd; + } err = swd & ~cwd; } else { @@ -560,7 +538,11 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr) * unmasked exception was caught we must mask the exception mask bits * at 0x1f80, and then use these to mask the exception bits at 0x3f. */ - unsigned short mxcsr = get_fpu_mxcsr(fpu); + unsigned short mxcsr = MXCSR_DEFAULT; + + if (boot_cpu_has(X86_FEATURE_XMM)) + mxcsr = fpu->state.fxsave.mxcsr; + err = ~(mxcsr >> 7) & mxcsr; } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 54c86fffbf9f..aacfd7a82cec 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -29,22 +29,22 @@ static void fpu__init_cpu_generic(void) unsigned long cr0; unsigned long cr4_mask = 0; - if (cpu_has_fxsr) + if (boot_cpu_has(X86_FEATURE_FXSR)) cr4_mask |= X86_CR4_OSFXSR; - if (cpu_has_xmm) + if (boot_cpu_has(X86_FEATURE_XMM)) cr4_mask |= X86_CR4_OSXMMEXCPT; if (cr4_mask) cr4_set_bits(cr4_mask); cr0 = read_cr0(); cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ - if (!cpu_has_fpu) + if (!boot_cpu_has(X86_FEATURE_FPU)) cr0 |= X86_CR0_EM; write_cr0(cr0); /* Flush out any pending x87 state: */ #ifdef CONFIG_MATH_EMULATION - if (!cpu_has_fpu) + if (!boot_cpu_has(X86_FEATURE_FPU)) fpstate_init_soft(¤t->thread.fpu.state.soft); else #endif @@ -89,7 +89,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) } #ifndef CONFIG_MATH_EMULATION - if (!cpu_has_fpu) { + if (!boot_cpu_has(X86_FEATURE_FPU)) { pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n"); for (;;) asm volatile("hlt"); @@ -106,7 +106,7 @@ static void __init fpu__init_system_mxcsr(void) { unsigned int mask = 0; - if (cpu_has_fxsr) { + if (boot_cpu_has(X86_FEATURE_FXSR)) { /* Static because GCC does not get 16-byte stack alignment right: */ static struct fxregs_state fxregs __initdata; @@ -212,7 +212,7 @@ static void __init fpu__init_system_xstate_size_legacy(void) * fpu__init_system_xstate(). */ - if (!cpu_has_fpu) { + if (!boot_cpu_has(X86_FEATURE_FPU)) { /* * Disable xsave as we do not support it if i387 * emulation is enabled. @@ -221,7 +221,7 @@ static void __init fpu__init_system_xstate_size_legacy(void) setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); xstate_size = sizeof(struct swregs_state); } else { - if (cpu_has_fxsr) + if (boot_cpu_has(X86_FEATURE_FXSR)) xstate_size = sizeof(struct fxregs_state); else xstate_size = sizeof(struct fregs_state); diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 8bd1c003942a..81422dfb152b 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -21,7 +21,10 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r { struct fpu *target_fpu = &target->thread.fpu; - return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0; + if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active) + return regset->n; + else + return 0; } int xfpregs_get(struct task_struct *target, const struct user_regset *regset, @@ -30,7 +33,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, { struct fpu *fpu = &target->thread.fpu; - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; fpu__activate_fpstate_read(fpu); @@ -47,7 +50,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; int ret; - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; fpu__activate_fpstate_write(fpu); @@ -65,7 +68,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, * update the header bits in the xsave header, indicating the * presence of FP and SSE state. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; return ret; @@ -79,7 +82,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, struct xregs_state *xsave; int ret; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -ENODEV; fpu__activate_fpstate_read(fpu); @@ -108,7 +111,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, struct xregs_state *xsave; int ret; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -ENODEV; fpu__activate_fpstate_write(fpu); @@ -275,10 +278,10 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, fpu__activate_fpstate_read(fpu); - if (!static_cpu_has(X86_FEATURE_FPU)) + if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &fpu->state.fsave, 0, -1); @@ -306,10 +309,10 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, fpu__activate_fpstate_write(fpu); fpstate_sanitize_xstate(fpu); - if (!static_cpu_has(X86_FEATURE_FPU)) + if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpu->state.fsave, 0, -1); @@ -325,7 +328,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, * update the header bit in the xsave header, indicating the * presence of FP. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP; return ret; } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index b48ef35b28d4..4ea2a59483c7 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -190,7 +190,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu) */ void fpu__init_cpu_xstate(void) { - if (!cpu_has_xsave || !xfeatures_mask) + if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask) return; cr4_set_bits(X86_CR4_OSXSAVE); @@ -280,7 +280,7 @@ static void __init setup_xstate_comp(void) xstate_comp_offsets[0] = 0; xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space); - if (!cpu_has_xsaves) { + if (!boot_cpu_has(X86_FEATURE_XSAVES)) { for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { if (xfeature_enabled(i)) { xstate_comp_offsets[i] = xstate_offsets[i]; @@ -316,13 +316,13 @@ static void __init setup_init_fpu_buf(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return; setup_xstate_features(); print_xstate_features(); - if (cpu_has_xsaves) { + if (boot_cpu_has(X86_FEATURE_XSAVES)) { init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask; init_fpstate.xsave.header.xfeatures = xfeatures_mask; } @@ -417,7 +417,7 @@ static int xfeature_size(int xfeature_nr) */ static int using_compacted_format(void) { - return cpu_has_xsaves; + return boot_cpu_has(X86_FEATURE_XSAVES); } static void __xstate_dump_leaves(void) @@ -549,7 +549,7 @@ static unsigned int __init calculate_xstate_size(void) unsigned int eax, ebx, ecx, edx; unsigned int calculated_xstate_size; - if (!cpu_has_xsaves) { + if (!boot_cpu_has(X86_FEATURE_XSAVES)) { /* * - CPUID function 0DH, sub-function 0: * EBX enumerates the size (in bytes) required by @@ -630,7 +630,7 @@ void __init fpu__init_system_xstate(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - if (!cpu_has_xsave) { + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { pr_info("x86/fpu: Legacy x87 FPU detected.\n"); return; } @@ -667,7 +667,7 @@ void __init fpu__init_system_xstate(void) pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", xfeatures_mask, xstate_size, - cpu_has_xsaves ? "compacted" : "standard"); + boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard"); } /* @@ -678,7 +678,7 @@ void fpu__resume_cpu(void) /* * Restore XCR0 on xsave capable CPUs: */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index af1112980dd4..6f8902b0d151 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -555,62 +555,53 @@ early_idt_handler_common: */ cld - cmpl $2,(%esp) # X86_TRAP_NMI - je .Lis_nmi # Ignore NMI - - cmpl $2,%ss:early_recursion_flag - je hlt_loop incl %ss:early_recursion_flag - push %eax # 16(%esp) - push %ecx # 12(%esp) - push %edx # 8(%esp) - push %ds # 4(%esp) - push %es # 0(%esp) - movl $(__KERNEL_DS),%eax - movl %eax,%ds - movl %eax,%es + /* The vector number is in pt_regs->gs */ - cmpl $(__KERNEL_CS),32(%esp) - jne 10f + cld + pushl %fs /* pt_regs->fs */ + movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %es /* pt_regs->es */ + movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %ds /* pt_regs->ds */ + movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %eax /* pt_regs->ax */ + pushl %ebp /* pt_regs->bp */ + pushl %edi /* pt_regs->di */ + pushl %esi /* pt_regs->si */ + pushl %edx /* pt_regs->dx */ + pushl %ecx /* pt_regs->cx */ + pushl %ebx /* pt_regs->bx */ - leal 28(%esp),%eax # Pointer to %eip - call early_fixup_exception - andl %eax,%eax - jnz ex_entry /* found an exception entry */ + /* Fix up DS and ES */ + movl $(__KERNEL_DS), %ecx + movl %ecx, %ds + movl %ecx, %es -10: -#ifdef CONFIG_PRINTK - xorl %eax,%eax - movw %ax,2(%esp) /* clean up the segment values on some cpus */ - movw %ax,6(%esp) - movw %ax,34(%esp) - leal 40(%esp),%eax - pushl %eax /* %esp before the exception */ - pushl %ebx - pushl %ebp - pushl %esi - pushl %edi - movl %cr2,%eax - pushl %eax - pushl (20+6*4)(%esp) /* trapno */ - pushl $fault_msg - call printk -#endif - call dump_stack -hlt_loop: - hlt - jmp hlt_loop + /* Load the vector number into EDX */ + movl PT_GS(%esp), %edx -ex_entry: - pop %es - pop %ds - pop %edx - pop %ecx - pop %eax - decl %ss:early_recursion_flag -.Lis_nmi: - addl $8,%esp /* drop vector number and error code */ + /* Load GS into pt_regs->gs and clear high bits */ + movw %gs, PT_GS(%esp) + movw $0, PT_GS+2(%esp) + + movl %esp, %eax /* args are pt_regs (EAX), trapnr (EDX) */ + call early_fixup_exception + + popl %ebx /* pt_regs->bx */ + popl %ecx /* pt_regs->cx */ + popl %edx /* pt_regs->dx */ + popl %esi /* pt_regs->si */ + popl %edi /* pt_regs->di */ + popl %ebp /* pt_regs->bp */ + popl %eax /* pt_regs->ax */ + popl %ds /* pt_regs->ds */ + popl %es /* pt_regs->es */ + popl %fs /* pt_regs->fs */ + popl %gs /* pt_regs->gs */ + decl %ss:early_recursion_flag + addl $4, %esp /* pop pt_regs->orig_ax */ iret ENDPROC(early_idt_handler_common) @@ -647,10 +638,14 @@ ignore_int: popl %eax #endif iret + +hlt_loop: + hlt + jmp hlt_loop ENDPROC(ignore_int) __INITDATA .align 4 -early_recursion_flag: +GLOBAL(early_recursion_flag) .long 0 __REFDATA @@ -715,19 +710,6 @@ __INITRODATA int_msg: .asciz "Unknown interrupt or fault at: %p %p %p\n" -fault_msg: -/* fault info: */ - .ascii "BUG: Int %d: CR2 %p\n" -/* regs pushed in early_idt_handler: */ - .ascii " EDI %p ESI %p EBP %p EBX %p\n" - .ascii " ESP %p ES %p DS %p\n" - .ascii " EDX %p ECX %p EAX %p\n" -/* fault frame: */ - .ascii " vec %p err %p EIP %p CS %p flg %p\n" - .ascii "Stack: %p %p %p %p %p %p %p %p\n" - .ascii " %p %p %p %p %p %p %p %p\n" - .asciz " %p %p %p %p %p %p %p %p\n" - #include "../../x86/xen/xen-head.S" /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 22fbf9df61bb..5df831ef1442 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -20,6 +20,7 @@ #include #include #include +#include "../entry/calling.h" #ifdef CONFIG_PARAVIRT #include @@ -64,6 +65,14 @@ startup_64: * tables and then reload them. */ + /* + * Setup stack for verify_cpu(). "-8" because stack_start is defined + * this way, see below. Our best guess is a NULL ptr for stack + * termination heuristics and we don't want to break anything which + * might depend on it (kgdb, ...). + */ + leaq (__end_init_task - 8)(%rip), %rsp + /* Sanitize CPU configuration */ call verify_cpu @@ -350,90 +359,48 @@ early_idt_handler_common: */ cld - cmpl $2,(%rsp) # X86_TRAP_NMI - je .Lis_nmi # Ignore NMI - - cmpl $2,early_recursion_flag(%rip) - jz 1f incl early_recursion_flag(%rip) - pushq %rax # 64(%rsp) - pushq %rcx # 56(%rsp) - pushq %rdx # 48(%rsp) - pushq %rsi # 40(%rsp) - pushq %rdi # 32(%rsp) - pushq %r8 # 24(%rsp) - pushq %r9 # 16(%rsp) - pushq %r10 # 8(%rsp) - pushq %r11 # 0(%rsp) + /* The vector number is currently in the pt_regs->di slot. */ + pushq %rsi /* pt_regs->si */ + movq 8(%rsp), %rsi /* RSI = vector number */ + movq %rdi, 8(%rsp) /* pt_regs->di = RDI */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq %rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + pushq %r9 /* pt_regs->r9 */ + pushq %r10 /* pt_regs->r10 */ + pushq %r11 /* pt_regs->r11 */ + pushq %rbx /* pt_regs->bx */ + pushq %rbp /* pt_regs->bp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ - cmpl $__KERNEL_CS,96(%rsp) - jne 11f - - cmpl $14,72(%rsp) # Page fault? + cmpq $14,%rsi /* Page fault? */ jnz 10f - GET_CR2_INTO(%rdi) # can clobber any volatile register if pv + GET_CR2_INTO(%rdi) /* Can clobber any volatile register if pv */ call early_make_pgtable andl %eax,%eax - jz 20f # All good + jz 20f /* All good */ 10: - leaq 88(%rsp),%rdi # Pointer to %rip + movq %rsp,%rdi /* RDI = pt_regs; RSI is already trapnr */ call early_fixup_exception - andl %eax,%eax - jnz 20f # Found an exception entry -11: -#ifdef CONFIG_EARLY_PRINTK - GET_CR2_INTO(%r9) # can clobber any volatile register if pv - movl 80(%rsp),%r8d # error code - movl 72(%rsp),%esi # vector number - movl 96(%rsp),%edx # %cs - movq 88(%rsp),%rcx # %rip - xorl %eax,%eax - leaq early_idt_msg(%rip),%rdi - call early_printk - cmpl $2,early_recursion_flag(%rip) - jz 1f - call dump_stack -#ifdef CONFIG_KALLSYMS - leaq early_idt_ripmsg(%rip),%rdi - movq 40(%rsp),%rsi # %rip again - call __print_symbol -#endif -#endif /* EARLY_PRINTK */ -1: hlt - jmp 1b - -20: # Exception table entry found or page table generated - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rdi - popq %rsi - popq %rdx - popq %rcx - popq %rax +20: decl early_recursion_flag(%rip) -.Lis_nmi: - addq $16,%rsp # drop vector number and error code - INTERRUPT_RETURN + jmp restore_regs_and_iret ENDPROC(early_idt_handler_common) __INITDATA .balign 4 -early_recursion_flag: +GLOBAL(early_recursion_flag) .long 0 -#ifdef CONFIG_EARLY_PRINTK -early_idt_msg: - .asciz "PANIC: early exception %02lx rip %lx:%lx error %lx cr2 %lx\n" -early_idt_ripmsg: - .asciz "RIP %s\n" -#endif /* CONFIG_EARLY_PRINTK */ - #define NEXT_PAGE(name) \ .balign PAGE_SIZE; \ GLOBAL(name) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index a1f0e4a5c47e..7282c2e3858e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -773,7 +773,6 @@ static struct clocksource clocksource_hpet = { .mask = HPET_MASK, .flags = CLOCK_SOURCE_IS_CONTINUOUS, .resume = hpet_resume_counter, - .archdata = { .vclock_mode = VCLOCK_HPET }, }; static int hpet_clocksource_register(void) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index e565e0e4d216..fc25f698d792 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -13,6 +13,7 @@ #include #include #include +#include #ifdef HAVE_JUMP_LABEL diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 2da6ee9ae69b..04cde527d728 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -45,6 +45,7 @@ #include #include +#include #include #include #include diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index ae703acb85c1..38cf7a741250 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -51,6 +51,7 @@ #include #include +#include #include #include #include diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 7b3b9d15c47a..4425f593f0ec 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -29,6 +29,7 @@ #include #include +#include #include #include #include diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 807950860fb7..dc1207e2f193 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -522,7 +522,7 @@ static noinline uint32_t __kvm_cpuid_base(void) if (boot_cpu_data.cpuid_level < 0) return 0; /* So we don't blow up on old processors */ - if (cpu_has_hypervisor) + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); return 0; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 005c03e93fc5..477ae806c2fa 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -31,6 +31,7 @@ #include #include +#include #include #include #include diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index f08ac28b8136..f9583917c7c4 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -339,8 +339,10 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .write_cr8 = native_write_cr8, #endif .wbinvd = native_wbinvd, - .read_msr = native_read_msr_safe, - .write_msr = native_write_msr_safe, + .read_msr = native_read_msr, + .write_msr = native_write_msr, + .read_msr_safe = native_read_msr_safe, + .write_msr_safe = native_write_msr_safe, .read_pmc = native_read_pmc, .load_tr_desc = native_load_tr_desc, .set_ldt = native_set_ldt, diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6cbab31ac23a..6b16c36f0939 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -136,25 +136,6 @@ void release_thread(struct task_struct *dead_task) } } -static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr) -{ - struct user_desc ud = { - .base_addr = addr, - .limit = 0xfffff, - .seg_32bit = 1, - .limit_in_pages = 1, - .useable = 1, - }; - struct desc_struct *desc = t->thread.tls_array; - desc += tls; - fill_ldt(desc, &ud); -} - -static inline u32 read_32bit_tls(struct task_struct *t, int tls) -{ - return get_desc_base(&t->thread.tls_array[tls]); -} - int copy_thread_tls(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct *p, unsigned long tls) { @@ -169,9 +150,9 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); - p->thread.gs = p->thread.gsindex ? 0 : me->thread.gs; + p->thread.gsbase = p->thread.gsindex ? 0 : me->thread.gsbase; savesegment(fs, p->thread.fsindex); - p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs; + p->thread.fsbase = p->thread.fsindex ? 0 : me->thread.fsbase; savesegment(es, p->thread.es); savesegment(ds, p->thread.ds); memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); @@ -210,7 +191,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, */ if (clone_flags & CLONE_SETTLS) { #ifdef CONFIG_IA32_EMULATION - if (is_ia32_task()) + if (in_ia32_syscall()) err = do_set_thread_area(p, -1, (struct user_desc __user *)tls, 0); else @@ -282,7 +263,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); - unsigned fsindex, gsindex; + unsigned prev_fsindex, prev_gsindex; fpu_switch_t fpu_switch; fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); @@ -292,8 +273,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * * (e.g. xen_load_tls()) */ - savesegment(fs, fsindex); - savesegment(gs, gsindex); + savesegment(fs, prev_fsindex); + savesegment(gs, prev_gsindex); /* * Load TLS before restoring any segments so that segment loads @@ -336,66 +317,104 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Switch FS and GS. * * These are even more complicated than DS and ES: they have - * 64-bit bases are that controlled by arch_prctl. Those bases - * only differ from the values in the GDT or LDT if the selector - * is 0. + * 64-bit bases are that controlled by arch_prctl. The bases + * don't necessarily match the selectors, as user code can do + * any number of things to cause them to be inconsistent. * - * Loading the segment register resets the hidden base part of - * the register to 0 or the value from the GDT / LDT. If the - * next base address zero, writing 0 to the segment register is - * much faster than using wrmsr to explicitly zero the base. + * We don't promise to preserve the bases if the selectors are + * nonzero. We also don't promise to preserve the base if the + * selector is zero and the base doesn't match whatever was + * most recently passed to ARCH_SET_FS/GS. (If/when the + * FSGSBASE instructions are enabled, we'll need to offer + * stronger guarantees.) * - * The thread_struct.fs and thread_struct.gs values are 0 - * if the fs and gs bases respectively are not overridden - * from the values implied by fsindex and gsindex. They - * are nonzero, and store the nonzero base addresses, if - * the bases are overridden. - * - * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should - * be impossible. - * - * Therefore we need to reload the segment registers if either - * the old or new selector is nonzero, and we need to override - * the base address if next thread expects it to be overridden. - * - * This code is unnecessarily slow in the case where the old and - * new indexes are zero and the new base is nonzero -- it will - * unnecessarily write 0 to the selector before writing the new - * base address. - * - * Note: This all depends on arch_prctl being the only way that - * user code can override the segment base. Once wrfsbase and - * wrgsbase are enabled, most of this code will need to change. + * As an invariant, + * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is + * impossible. */ - if (unlikely(fsindex | next->fsindex | prev->fs)) { + if (next->fsindex) { + /* Loading a nonzero value into FS sets the index and base. */ loadsegment(fs, next->fsindex); - - /* - * If user code wrote a nonzero value to FS, then it also - * cleared the overridden base address. - * - * XXX: if user code wrote 0 to FS and cleared the base - * address itself, we won't notice and we'll incorrectly - * restore the prior base address next time we reschdule - * the process. - */ - if (fsindex) - prev->fs = 0; + } else { + if (next->fsbase) { + /* Next index is zero but next base is nonzero. */ + if (prev_fsindex) + loadsegment(fs, 0); + wrmsrl(MSR_FS_BASE, next->fsbase); + } else { + /* Next base and index are both zero. */ + if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { + /* + * We don't know the previous base and can't + * find out without RDMSR. Forcibly clear it. + */ + loadsegment(fs, __USER_DS); + loadsegment(fs, 0); + } else { + /* + * If the previous index is zero and ARCH_SET_FS + * didn't change the base, then the base is + * also zero and we don't need to do anything. + */ + if (prev->fsbase || prev_fsindex) + loadsegment(fs, 0); + } + } } - if (next->fs) - wrmsrl(MSR_FS_BASE, next->fs); - prev->fsindex = fsindex; + /* + * Save the old state and preserve the invariant. + * NB: if prev_fsindex == 0, then we can't reliably learn the base + * without RDMSR because Intel user code can zero it without telling + * us and AMD user code can program any 32-bit value without telling + * us. + */ + if (prev_fsindex) + prev->fsbase = 0; + prev->fsindex = prev_fsindex; - if (unlikely(gsindex | next->gsindex | prev->gs)) { + if (next->gsindex) { + /* Loading a nonzero value into GS sets the index and base. */ load_gs_index(next->gsindex); - - /* This works (and fails) the same way as fsindex above. */ - if (gsindex) - prev->gs = 0; + } else { + if (next->gsbase) { + /* Next index is zero but next base is nonzero. */ + if (prev_gsindex) + load_gs_index(0); + wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase); + } else { + /* Next base and index are both zero. */ + if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { + /* + * We don't know the previous base and can't + * find out without RDMSR. Forcibly clear it. + * + * This contains a pointless SWAPGS pair. + * Fixing it would involve an explicit check + * for Xen or a new pvop. + */ + load_gs_index(__USER_DS); + load_gs_index(0); + } else { + /* + * If the previous index is zero and ARCH_SET_GS + * didn't change the base, then the base is + * also zero and we don't need to do anything. + */ + if (prev->gsbase || prev_gsindex) + load_gs_index(0); + } + } } - if (next->gs) - wrmsrl(MSR_KERNEL_GS_BASE, next->gs); - prev->gsindex = gsindex; + /* + * Save the old state and preserve the invariant. + * NB: if prev_gsindex == 0, then we can't reliably learn the base + * without RDMSR because Intel user code can zero it without telling + * us and AMD user code can program any 32-bit value without telling + * us. + */ + if (prev_gsindex) + prev->gsbase = 0; + prev->gsindex = prev_gsindex; switch_fpu_finish(next_fpu, fpu_switch); @@ -516,23 +535,11 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) if (addr >= TASK_SIZE_OF(task)) return -EPERM; cpu = get_cpu(); - /* handle small bases via the GDT because that's faster to - switch. */ - if (addr <= 0xffffffff) { - set_32bit_tls(task, GS_TLS, addr); - if (doit) { - load_TLS(&task->thread, cpu); - load_gs_index(GS_TLS_SEL); - } - task->thread.gsindex = GS_TLS_SEL; - task->thread.gs = 0; - } else { - task->thread.gsindex = 0; - task->thread.gs = addr; - if (doit) { - load_gs_index(0); - ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); - } + task->thread.gsindex = 0; + task->thread.gsbase = addr; + if (doit) { + load_gs_index(0); + ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); } put_cpu(); break; @@ -542,52 +549,30 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) if (addr >= TASK_SIZE_OF(task)) return -EPERM; cpu = get_cpu(); - /* handle small bases via the GDT because that's faster to - switch. */ - if (addr <= 0xffffffff) { - set_32bit_tls(task, FS_TLS, addr); - if (doit) { - load_TLS(&task->thread, cpu); - loadsegment(fs, FS_TLS_SEL); - } - task->thread.fsindex = FS_TLS_SEL; - task->thread.fs = 0; - } else { - task->thread.fsindex = 0; - task->thread.fs = addr; - if (doit) { - /* set the selector to 0 to not confuse - __switch_to */ - loadsegment(fs, 0); - ret = wrmsrl_safe(MSR_FS_BASE, addr); - } + task->thread.fsindex = 0; + task->thread.fsbase = addr; + if (doit) { + /* set the selector to 0 to not confuse __switch_to */ + loadsegment(fs, 0); + ret = wrmsrl_safe(MSR_FS_BASE, addr); } put_cpu(); break; case ARCH_GET_FS: { unsigned long base; - if (task->thread.fsindex == FS_TLS_SEL) - base = read_32bit_tls(task, FS_TLS); - else if (doit) + if (doit) rdmsrl(MSR_FS_BASE, base); else - base = task->thread.fs; + base = task->thread.fsbase; ret = put_user(base, (unsigned long __user *)addr); break; } case ARCH_GET_GS: { unsigned long base; - unsigned gsindex; - if (task->thread.gsindex == GS_TLS_SEL) - base = read_32bit_tls(task, GS_TLS); - else if (doit) { - savesegment(gs, gsindex); - if (gsindex) - rdmsrl(MSR_KERNEL_GS_BASE, base); - else - base = task->thread.gs; - } else - base = task->thread.gs; + if (doit) + rdmsrl(MSR_KERNEL_GS_BASE, base); + else + base = task->thread.gsbase; ret = put_user(base, (unsigned long __user *)addr); break; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 32e9d9cbb884..e60ef918f53d 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -303,29 +303,11 @@ static int set_segment_reg(struct task_struct *task, switch (offset) { case offsetof(struct user_regs_struct,fs): - /* - * If this is setting fs as for normal 64-bit use but - * setting fs_base has implicitly changed it, leave it. - */ - if ((value == FS_TLS_SEL && task->thread.fsindex == 0 && - task->thread.fs != 0) || - (value == 0 && task->thread.fsindex == FS_TLS_SEL && - task->thread.fs == 0)) - break; task->thread.fsindex = value; if (task == current) loadsegment(fs, task->thread.fsindex); break; case offsetof(struct user_regs_struct,gs): - /* - * If this is setting gs as for normal 64-bit use but - * setting gs_base has implicitly changed it, leave it. - */ - if ((value == GS_TLS_SEL && task->thread.gsindex == 0 && - task->thread.gs != 0) || - (value == 0 && task->thread.gsindex == GS_TLS_SEL && - task->thread.gs == 0)) - break; task->thread.gsindex = value; if (task == current) load_gs_index(task->thread.gsindex); @@ -417,7 +399,7 @@ static int putreg(struct task_struct *child, * to set either thread.fs or thread.fsindex and the * corresponding GDT slot. */ - if (child->thread.fs != value) + if (child->thread.fsbase != value) return do_arch_prctl(child, ARCH_SET_FS, value); return 0; case offsetof(struct user_regs_struct,gs_base): @@ -426,7 +408,7 @@ static int putreg(struct task_struct *child, */ if (value >= TASK_SIZE_OF(child)) return -EIO; - if (child->thread.gs != value) + if (child->thread.gsbase != value) return do_arch_prctl(child, ARCH_SET_GS, value); return 0; #endif @@ -453,31 +435,17 @@ static unsigned long getreg(struct task_struct *task, unsigned long offset) #ifdef CONFIG_X86_64 case offsetof(struct user_regs_struct, fs_base): { /* - * do_arch_prctl may have used a GDT slot instead of - * the MSR. To userland, it appears the same either - * way, except the %fs segment selector might not be 0. + * XXX: This will not behave as expected if called on + * current or if fsindex != 0. */ - unsigned int seg = task->thread.fsindex; - if (task->thread.fs != 0) - return task->thread.fs; - if (task == current) - asm("movl %%fs,%0" : "=r" (seg)); - if (seg != FS_TLS_SEL) - return 0; - return get_desc_base(&task->thread.tls_array[FS_TLS]); + return task->thread.fsbase; } case offsetof(struct user_regs_struct, gs_base): { /* - * Exactly the same here as the %fs handling above. + * XXX: This will not behave as expected if called on + * current or if fsindex != 0. */ - unsigned int seg = task->thread.gsindex; - if (task->thread.gs != 0) - return task->thread.gs; - if (task == current) - asm("movl %%gs,%0" : "=r" (seg)); - if (seg != GS_TLS_SEL) - return 0; - return get_desc_base(&task->thread.tls_array[GS_TLS]); + return task->thread.gsbase; } #endif } @@ -1266,7 +1234,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { #ifdef CONFIG_X86_X32_ABI - if (!is_ia32_task()) + if (!in_ia32_syscall()) return x32_arch_ptrace(child, request, caddr, cdata); #endif #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 3e84ef16f657..22cc2f9f8aec 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -390,7 +390,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, put_user_ex(&frame->uc, &frame->puc); /* Create the ucontext. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); else put_user_ex(0, &frame->uc.uc_flags); @@ -441,7 +441,7 @@ static unsigned long frame_uc_flags(struct pt_regs *regs) { unsigned long flags; - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS; else flags = UC_SIGCONTEXT_SS; @@ -761,7 +761,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { #ifdef CONFIG_X86_64 - if (is_ia32_task()) + if (in_ia32_syscall()) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0e4329ed91ef..fafe8b923cac 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1236,7 +1236,7 @@ static int __init smp_sanity_check(unsigned max_cpus) * If we couldn't find a local APIC, then get out of here now! */ if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) && - !cpu_has_apic) { + !boot_cpu_has(X86_FEATURE_APIC)) { if (!disable_apic) { pr_err("BIOS bug, local APIC #%d not detected!...\n", boot_cpu_physical_apicid); diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index ab40954e113e..f386bad0984e 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -40,7 +40,7 @@ static inline void flush_tce(void* tceaddr) { /* a single tce can't cross a cache line */ - if (cpu_has_clflush) + if (boot_cpu_has(X86_FEATURE_CLFLUSH)) clflush(tceaddr); else wbinvd(); diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 7fc5e843f247..9692a5e9fdab 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -114,6 +114,7 @@ int do_set_thread_area(struct task_struct *p, int idx, int can_allocate) { struct user_desc info; + unsigned short __maybe_unused sel, modified_sel; if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; @@ -141,6 +142,47 @@ int do_set_thread_area(struct task_struct *p, int idx, set_tls_desc(p, idx, &info, 1); + /* + * If DS, ES, FS, or GS points to the modified segment, forcibly + * refresh it. Only needed on x86_64 because x86_32 reloads them + * on return to user mode. + */ + modified_sel = (idx << 3) | 3; + + if (p == current) { +#ifdef CONFIG_X86_64 + savesegment(ds, sel); + if (sel == modified_sel) + loadsegment(ds, sel); + + savesegment(es, sel); + if (sel == modified_sel) + loadsegment(es, sel); + + savesegment(fs, sel); + if (sel == modified_sel) + loadsegment(fs, sel); + + savesegment(gs, sel); + if (sel == modified_sel) + load_gs_index(sel); +#endif + +#ifdef CONFIG_X86_32_LAZY_GS + savesegment(gs, sel); + if (sel == modified_sel) + loadsegment(gs, sel); +#endif + } else { +#ifdef CONFIG_X86_64 + if (p->thread.fsindex == modified_sel) + p->thread.fsbase = info.base_addr; + + if (p->thread.gsindex == modified_sel) + p->thread.gsbase = info.base_addr; +#endif + } + return 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 06cbe25861f1..d1590486204a 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c9c4c7ce3eb2..38ba6de56ede 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -36,7 +36,7 @@ static int __read_mostly tsc_unstable; /* native_sched_clock() is called before tsc_init(), so we must start with the TSC soft disabled to prevent - erroneous rdtsc usage on !cpu_has_tsc processors */ + erroneous rdtsc usage on !boot_cpu_has(X86_FEATURE_TSC) processors */ static int __read_mostly tsc_disabled = -1; static DEFINE_STATIC_KEY_FALSE(__use_tsc); @@ -834,15 +834,15 @@ int recalibrate_cpu_khz(void) #ifndef CONFIG_SMP unsigned long cpu_khz_old = cpu_khz; - if (cpu_has_tsc) { - tsc_khz = x86_platform.calibrate_tsc(); - cpu_khz = tsc_khz; - cpu_data(0).loops_per_jiffy = - cpufreq_scale(cpu_data(0).loops_per_jiffy, - cpu_khz_old, cpu_khz); - return 0; - } else + if (!boot_cpu_has(X86_FEATURE_TSC)) return -ENODEV; + + tsc_khz = x86_platform.calibrate_tsc(); + cpu_khz = tsc_khz; + cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy, + cpu_khz_old, cpu_khz); + + return 0; #else return -ENODEV; #endif @@ -922,9 +922,6 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, struct cpufreq_freqs *freq = data; unsigned long *lpj; - if (cpu_has(&cpu_data(freq->cpu), X86_FEATURE_CONSTANT_TSC)) - return 0; - lpj = &boot_cpu_data.loops_per_jiffy; #ifdef CONFIG_SMP if (!(freq->flags & CPUFREQ_CONST_LOOPS)) @@ -954,9 +951,9 @@ static struct notifier_block time_cpufreq_notifier_block = { .notifier_call = time_cpufreq_notifier }; -static int __init cpufreq_tsc(void) +static int __init cpufreq_register_tsc_scaling(void) { - if (!cpu_has_tsc) + if (!boot_cpu_has(X86_FEATURE_TSC)) return 0; if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; @@ -965,7 +962,7 @@ static int __init cpufreq_tsc(void) return 0; } -core_initcall(cpufreq_tsc); +core_initcall(cpufreq_register_tsc_scaling); #endif /* CONFIG_CPU_FREQ */ @@ -1081,7 +1078,7 @@ static void __init check_system_tsc_reliable(void) */ int unsynchronized_tsc(void) { - if (!cpu_has_tsc || tsc_unstable) + if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_unstable) return 1; #ifdef CONFIG_SMP @@ -1205,7 +1202,7 @@ out: static int __init init_tsc_clocksource(void) { - if (!cpu_has_tsc || tsc_disabled > 0 || !tsc_khz) + if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz) return 0; if (tsc_clocksource_reliable) @@ -1242,7 +1239,7 @@ void __init tsc_init(void) u64 lpj; int cpu; - if (!cpu_has_tsc) { + if (!boot_cpu_has(X86_FEATURE_TSC)) { setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index bd074151bfd6..6c1ff31d99ff 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -516,7 +516,7 @@ struct uprobe_xol_ops { static inline int sizeof_long(void) { - return is_ia32_task() ? 4 : 8; + return in_ia32_syscall() ? 4 : 8; } static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index bbbaa802d13e..769af907f824 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -75,7 +75,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) return 0; /* Update OSXSAVE bit */ - if (cpu_has_xsave && best->function == 0x1) { + if (boot_cpu_has(X86_FEATURE_XSAVE) && best->function == 0x1) { best->ecx &= ~F(OSXSAVE); if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) best->ecx |= F(OSXSAVE); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b6f50e8b0a39..38c0c32926c9 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3844,7 +3844,8 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, context->shadow_root_level, false, - cpu_has_gbpages, true, true); + boot_cpu_has(X86_FEATURE_GBPAGES), + true, true); else __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, boot_cpu_data.x86_phys_bits, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 31346a3f20a5..fafd720ce10a 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1254,7 +1254,7 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) kvm_load_ldt(svm->host.ldt); #ifdef CONFIG_X86_64 loadsegment(fs, svm->host.fs); - wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); + wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gsbase); load_gs_index(svm->host.gs); #else #ifdef CONFIG_X86_32_LAZY_GS diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 2f1ea2f61e1f..b72743c5668d 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -809,8 +809,7 @@ TRACE_EVENT(kvm_write_tsc_offset, #define host_clocks \ {VCLOCK_NONE, "none"}, \ - {VCLOCK_TSC, "tsc"}, \ - {VCLOCK_HPET, "hpet"} \ + {VCLOCK_TSC, "tsc"} \ TRACE_EVENT(kvm_update_master_clock, TP_PROTO(bool use_master_clock, unsigned int host_clock, bool offset_matched), diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 133679d520af..cb47fe3da292 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3390,7 +3390,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) } } - if (cpu_has_xsaves) + if (boot_cpu_has(X86_FEATURE_XSAVES)) rdmsrl(MSR_IA32_XSS, host_xss); return 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9b7798c7b210..12f33e662382 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2611,7 +2611,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_MAX_MCE_BANKS; break; case KVM_CAP_XCRS: - r = cpu_has_xsave; + r = boot_cpu_has(X86_FEATURE_XSAVE); break; case KVM_CAP_TSC_CONTROL: r = kvm_has_tsc_control; @@ -3094,7 +3094,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) /* Set XSTATE_BV and possibly XCOMP_BV. */ xsave->header.xfeatures = xstate_bv; - if (cpu_has_xsaves) + if (boot_cpu_has(X86_FEATURE_XSAVES)) xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; /* @@ -3121,7 +3121,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { - if (cpu_has_xsave) { + if (boot_cpu_has(X86_FEATURE_XSAVE)) { memset(guest_xsave, 0, sizeof(struct kvm_xsave)); fill_xsave((u8 *) guest_xsave->region, vcpu); } else { @@ -3139,7 +3139,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, u64 xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; - if (cpu_has_xsave) { + if (boot_cpu_has(X86_FEATURE_XSAVE)) { /* * Here we allow setting states that are not present in * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility @@ -3160,7 +3160,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, struct kvm_xcrs *guest_xcrs) { - if (!cpu_has_xsave) { + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { guest_xcrs->nr_xcrs = 0; return; } @@ -3176,7 +3176,7 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, { int i, r = 0; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -EINVAL; if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags) @@ -5865,7 +5865,7 @@ int kvm_arch_init(void *opaque) perf_register_guest_info_callbacks(&kvm_guest_cbs); - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_lapic_init(); @@ -7293,7 +7293,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) static void fx_init(struct kvm_vcpu *vcpu) { fpstate_init(&vcpu->arch.guest_fpu.state); - if (cpu_has_xsaves) + if (boot_cpu_has(X86_FEATURE_XSAVES)) vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 91d93b95bd86..b559d9238781 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -612,7 +612,7 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from, { stac(); #ifdef CONFIG_X86_INTEL_USERCOPY - if (n > 64 && cpu_has_xmm2) + if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_zeroing_intel_nocache(to, from, n); else __copy_user_zeroing(to, from, n); @@ -629,7 +629,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr { stac(); #ifdef CONFIG_X86_INTEL_USERCOPY - if (n > 64 && cpu_has_xmm2) + if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_intel_nocache(to, from, n); else __copy_user(to, from, n); diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 82447b3fba38..4bb53b89f3c5 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -1,5 +1,6 @@ #include #include +#include typedef bool (*ex_handler_t)(const struct exception_table_entry *, struct pt_regs *, int); @@ -42,6 +43,43 @@ bool ex_handler_ext(const struct exception_table_entry *fixup, } EXPORT_SYMBOL(ex_handler_ext); +bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + WARN_ONCE(1, "unchecked MSR access error: RDMSR from 0x%x\n", + (unsigned int)regs->cx); + + /* Pretend that the read succeeded and returned 0. */ + regs->ip = ex_fixup_addr(fixup); + regs->ax = 0; + regs->dx = 0; + return true; +} +EXPORT_SYMBOL(ex_handler_rdmsr_unsafe); + +bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + WARN_ONCE(1, "unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x)\n", + (unsigned int)regs->cx, + (unsigned int)regs->dx, (unsigned int)regs->ax); + + /* Pretend that the write succeeded. */ + regs->ip = ex_fixup_addr(fixup); + return true; +} +EXPORT_SYMBOL(ex_handler_wrmsr_unsafe); + +bool ex_handler_clear_fs(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + if (static_cpu_has(X86_BUG_NULL_SEG)) + asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS)); + asm volatile ("mov %0, %%fs" : : "rm" (0)); + return ex_handler_default(fixup, regs, trapnr); +} +EXPORT_SYMBOL(ex_handler_clear_fs); + bool ex_has_fault_handler(unsigned long ip) { const struct exception_table_entry *e; @@ -82,24 +120,46 @@ int fixup_exception(struct pt_regs *regs, int trapnr) return handler(e, regs, trapnr); } +extern unsigned int early_recursion_flag; + /* Restricted version used during very early boot */ -int __init early_fixup_exception(unsigned long *ip) +void __init early_fixup_exception(struct pt_regs *regs, int trapnr) { - const struct exception_table_entry *e; - unsigned long new_ip; - ex_handler_t handler; + /* Ignore early NMIs. */ + if (trapnr == X86_TRAP_NMI) + return; - e = search_exception_tables(*ip); - if (!e) - return 0; + if (early_recursion_flag > 2) + goto halt_loop; - new_ip = ex_fixup_addr(e); - handler = ex_fixup_handler(e); + if (regs->cs != __KERNEL_CS) + goto fail; - /* special handling not supported during early boot */ - if (handler != ex_handler_default) - return 0; + /* + * The full exception fixup machinery is available as soon as + * the early IDT is loaded. This means that it is the + * responsibility of extable users to either function correctly + * when handlers are invoked early or to simply avoid causing + * exceptions before they're ready to handle them. + * + * This is better than filtering which handlers can be used, + * because refusing to call a handler here is guaranteed to + * result in a hard-to-debug panic. + * + * Keep in mind that not all vectors actually get here. Early + * fage faults, for example, are special. + */ + if (fixup_exception(regs, trapnr)) + return; - *ip = new_ip; - return 1; +fail: + early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n", + (unsigned)trapnr, (unsigned long)regs->cs, regs->ip, + regs->orig_ax, read_cr2()); + + show_regs(regs); + +halt_loop: + while (true) + halt(); } diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 740d7ac03a55..14a95054d4e0 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -162,7 +162,7 @@ static __init int setup_hugepagesz(char *opt) unsigned long ps = memparse(opt, &opt); if (ps == PMD_SIZE) { hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); - } else if (ps == PUD_SIZE && cpu_has_gbpages) { + } else if (ps == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES)) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); } else { printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n", @@ -177,7 +177,7 @@ __setup("hugepagesz=", setup_hugepagesz); static __init int gigantic_pages_init(void) { /* With compaction or CMA we can allocate gigantic pages at runtime */ - if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT)) + if (boot_cpu_has(X86_FEATURE_GBPAGES) && !size_to_hstate(1UL << PUD_SHIFT)) hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); return 0; } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 9d56f271d519..372aad2b3291 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -157,23 +157,23 @@ static void __init probe_page_size_mask(void) * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ - if (cpu_has_pse && !debug_pagealloc_enabled()) + if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled()) page_size_mask |= 1 << PG_LEVEL_2M; #endif /* Enable PSE if available */ - if (cpu_has_pse) + if (boot_cpu_has(X86_FEATURE_PSE)) cr4_set_bits_and_update_boot(X86_CR4_PSE); /* Enable PGE if available */ - if (cpu_has_pge) { + if (boot_cpu_has(X86_FEATURE_PGE)) { cr4_set_bits_and_update_boot(X86_CR4_PGE); __supported_pte_mask |= _PAGE_GLOBAL; } else __supported_pte_mask &= ~_PAGE_GLOBAL; /* Enable 1 GB linear kernel mappings if available: */ - if (direct_gbpages && cpu_has_gbpages) { + if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) { printk(KERN_INFO "Using GB pages for direct mapping\n"); page_size_mask |= 1 << PG_LEVEL_1G; } else { diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index bd7a9b9e2e14..85af914e3d27 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -284,7 +284,7 @@ kernel_physical_mapping_init(unsigned long start, */ mapping_iter = 1; - if (!cpu_has_pse) + if (!boot_cpu_has(X86_FEATURE_PSE)) use_pse = 0; repeat: diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 214afda97911..89d97477c1d9 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1295,7 +1295,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) struct vmem_altmap *altmap = to_vmem_altmap(start); int err; - if (cpu_has_pse) + if (boot_cpu_has(X86_FEATURE_PSE)) err = vmemmap_populate_hugepages(start, end, node, altmap); else if (altmap) { pr_err_once("%s: no cpu support for altmap allocations\n", @@ -1338,7 +1338,7 @@ void register_page_bootmem_memmap(unsigned long section_nr, } get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO); - if (!cpu_has_pse) { + if (!boot_cpu_has(X86_FEATURE_PSE)) { next = (addr + PAGE_SIZE) & PAGE_MASK; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 0d8d53d1f5cc..f0894910bdd7 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -378,7 +378,7 @@ EXPORT_SYMBOL(iounmap); int __init arch_ioremap_pud_supported(void) { #ifdef CONFIG_X86_64 - return cpu_has_gbpages; + return boot_cpu_has(X86_FEATURE_GBPAGES); #else return 0; #endif @@ -386,7 +386,7 @@ int __init arch_ioremap_pud_supported(void) int __init arch_ioremap_pmd_supported(void) { - return cpu_has_pse; + return boot_cpu_has(X86_FEATURE_PSE); } /* diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a1f0e1d0ddc2..7a1f7bbf4105 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -1055,7 +1055,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, /* * Map everything starting from the Gb boundary, possibly with 1G pages */ - while (cpu_has_gbpages && end - start >= PUD_SIZE) { + while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) { set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE | massage_pgprot(pud_pgprot))); @@ -1466,7 +1466,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, * error case we fall back to cpa_flush_all (which uses * WBINVD): */ - if (!ret && cpu_has_clflush) { + if (!ret && boot_cpu_has(X86_FEATURE_CLFLUSH)) { if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { cpa_flush_array(addr, numpages, cache, cpa.flags, pages); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index faec01e7a17d..fb0604f11eec 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -40,11 +40,22 @@ static bool boot_cpu_done; static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT); +static void init_cache_modes(void); -static inline void pat_disable(const char *reason) +void pat_disable(const char *reason) { + if (!__pat_enabled) + return; + + if (boot_cpu_done) { + WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n"); + return; + } + __pat_enabled = 0; pr_info("x86/PAT: %s\n", reason); + + init_cache_modes(); } static int __init nopat(char *str) @@ -181,7 +192,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) * configuration. * Using lower indices is preferred, so we start with highest index. */ -void pat_init_cache_modes(u64 pat) +static void __init_cache_modes(u64 pat) { enum page_cache_mode cache; char pat_msg[33]; @@ -202,14 +213,11 @@ static void pat_bsp_init(u64 pat) { u64 tmp_pat; - if (!cpu_has_pat) { + if (!boot_cpu_has(X86_FEATURE_PAT)) { pat_disable("PAT not supported by CPU."); return; } - if (!pat_enabled()) - goto done; - rdmsrl(MSR_IA32_CR_PAT, tmp_pat); if (!tmp_pat) { pat_disable("PAT MSR is 0, disabled."); @@ -218,16 +226,12 @@ static void pat_bsp_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); -done: - pat_init_cache_modes(pat); + __init_cache_modes(pat); } static void pat_ap_init(u64 pat) { - if (!pat_enabled()) - return; - - if (!cpu_has_pat) { + if (!boot_cpu_has(X86_FEATURE_PAT)) { /* * If this happens we are on a secondary CPU, but switched to * PAT on the boot CPU. We have no way to undo PAT. @@ -238,18 +242,32 @@ static void pat_ap_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); } -void pat_init(void) +static void init_cache_modes(void) { - u64 pat; - struct cpuinfo_x86 *c = &boot_cpu_data; + u64 pat = 0; + static int init_cm_done; - if (!pat_enabled()) { + if (init_cm_done) + return; + + if (boot_cpu_has(X86_FEATURE_PAT)) { + /* + * CPU supports PAT. Set PAT table to be consistent with + * PAT MSR. This case supports "nopat" boot option, and + * virtual machine environments which support PAT without + * MTRRs. In specific, Xen has unique setup to PAT MSR. + * + * If PAT MSR returns 0, it is considered invalid and emulates + * as No PAT. + */ + rdmsrl(MSR_IA32_CR_PAT, pat); + } + + if (!pat) { /* * No PAT. Emulate the PAT table that corresponds to the two - * cache bits, PWT (Write Through) and PCD (Cache Disable). This - * setup is the same as the BIOS default setup when the system - * has PAT but the "nopat" boot option has been specified. This - * emulated PAT table is used when MSR_IA32_CR_PAT returns 0. + * cache bits, PWT (Write Through) and PCD (Cache Disable). + * This setup is also the same as the BIOS default setup. * * PTE encoding: * @@ -266,10 +284,36 @@ void pat_init(void) */ pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); + } - } else if ((c->x86_vendor == X86_VENDOR_INTEL) && - (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || - ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { + __init_cache_modes(pat); + + init_cm_done = 1; +} + +/** + * pat_init - Initialize PAT MSR and PAT table + * + * This function initializes PAT MSR and PAT table with an OS-defined value + * to enable additional cache attributes, WC and WT. + * + * This function must be called on all CPUs using the specific sequence of + * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this + * procedure for PAT. + */ +void pat_init(void) +{ + u64 pat; + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (!pat_enabled()) { + init_cache_modes(); + return; + } + + if ((c->x86_vendor == X86_VENDOR_INTEL) && + (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || + ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { /* * PAT support with the lower four entries. Intel Pentium 2, * 3, M, and 4 are affected by PAT errata, which makes the @@ -734,25 +778,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, if (file->f_flags & O_DSYNC) pcm = _PAGE_CACHE_MODE_UC_MINUS; -#ifdef CONFIG_X86_32 - /* - * On the PPro and successors, the MTRRs are used to set - * memory types for physical addresses outside main memory, - * so blindly setting UC or PWT on those pages is wrong. - * For Pentiums and earlier, the surround logic should disable - * caching for the high addresses through the KEN pin, but - * we maintain the tradition of paranoia in this code. - */ - if (!pat_enabled() && - !(boot_cpu_has(X86_FEATURE_MTRR) || - boot_cpu_has(X86_FEATURE_K6_MTRR) || - boot_cpu_has(X86_FEATURE_CYRIX_ARR) || - boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) && - (pfn << PAGE_SHIFT) >= __pa(high_memory)) { - pcm = _PAGE_CACHE_MODE_UC; - } -#endif - *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | cachemode2protval(pcm)); return 1; diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 0e07e0968c3a..28c04123b6dd 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -636,7 +636,7 @@ static int __init ppro_init(char **cpu_type) __u8 cpu_model = boot_cpu_data.x86_model; struct op_x86_model_spec *spec = &op_ppro_spec; /* default */ - if (force_cpu_type == arch_perfmon && cpu_has_arch_perfmon) + if (force_cpu_type == arch_perfmon && boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) return 0; /* @@ -700,7 +700,7 @@ int __init op_nmi_init(struct oprofile_operations *ops) char *cpu_type = NULL; int ret = 0; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; if (force_cpu_type == timer) @@ -761,7 +761,7 @@ int __init op_nmi_init(struct oprofile_operations *ops) if (cpu_type) break; - if (!cpu_has_arch_perfmon) + if (!boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) return -ENODEV; /* use arch perfmon as fallback */ diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index d90528ea5412..350f7096baac 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -75,7 +75,7 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model, u64 val; int i; - if (cpu_has_arch_perfmon) { + if (boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) { union cpuid10_eax eax; eax.full = cpuid_eax(0xa); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index beac4dfdade6..4bd08b0fc8ea 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -445,7 +445,7 @@ void __init xen_msi_init(void) uint32_t eax = cpuid_eax(xen_cpuid_base() + 4); if (((eax & XEN_HVM_CPUID_X2APIC_VIRT) && x2apic_mode) || - ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && cpu_has_apic)) + ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && boot_cpu_has(X86_FEATURE_APIC))) return; } diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 291226b952a9..9f14bd34581d 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -106,7 +106,7 @@ static int resume_physical_mapping_init(pgd_t *pgd_base) * normal page tables. * NOTE: We can mark everything as executable here */ - if (cpu_has_pse) { + if (boot_cpu_has(X86_FEATURE_PSE)) { set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE_EXEC)); pfn += PTRS_PER_PTE; } else { diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 880862c7d9dd..6ab672233ac9 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -75,7 +75,6 @@ #include #include #include -#include #include #ifdef CONFIG_ACPI @@ -1093,6 +1092,26 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) return ret; } +static u64 xen_read_msr(unsigned int msr) +{ + /* + * This will silently swallow a #GP from RDMSR. It may be worth + * changing that. + */ + int err; + + return xen_read_msr_safe(msr, &err); +} + +static void xen_write_msr(unsigned int msr, unsigned low, unsigned high) +{ + /* + * This will silently swallow a #GP from WRMSR. It may be worth + * changing that. + */ + xen_write_msr_safe(msr, low, high); +} + void xen_setup_shared_info(void) { if (!xen_feature(XENFEAT_auto_translated_physmap)) { @@ -1223,8 +1242,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .wbinvd = native_wbinvd, - .read_msr = xen_read_msr_safe, - .write_msr = xen_write_msr_safe, + .read_msr = xen_read_msr, + .write_msr = xen_write_msr, + + .read_msr_safe = xen_read_msr_safe, + .write_msr_safe = xen_write_msr_safe, .read_pmc = xen_read_pmc, @@ -1469,10 +1491,10 @@ static void xen_pvh_set_cr_flags(int cpu) * For BSP, PSE PGE are set in probe_page_size_mask(), for APs * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu(). */ - if (cpu_has_pse) + if (boot_cpu_has(X86_FEATURE_PSE)) cr4_set_bits_and_update_boot(X86_CR4_PSE); - if (cpu_has_pge) + if (boot_cpu_has(X86_FEATURE_PGE)) cr4_set_bits_and_update_boot(X86_CR4_PGE); } @@ -1511,7 +1533,6 @@ asmlinkage __visible void __init xen_start_kernel(void) { struct physdev_set_iopl set_iopl; unsigned long initrd_start = 0; - u64 pat; int rc; if (!xen_start_info) @@ -1618,13 +1639,6 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_start_info->nr_pages); xen_reserve_special_pages(); - /* - * Modify the cache mode translation tables to match Xen's PAT - * configuration. - */ - rdmsrl(MSR_IA32_CR_PAT, pat); - pat_init_cache_modes(pat); - /* keep using Xen gdt for now; no urgent need to change it */ #ifdef CONFIG_X86_32 diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index 0f6b229afcb9..247bfa8eaddb 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -945,7 +945,7 @@ static int __init longhaul_init(void) } #endif #ifdef CONFIG_X86_IO_APIC - if (cpu_has_apic) { + if (boot_cpu_has(X86_FEATURE_APIC)) { printk(KERN_ERR PFX "APIC detected. Longhaul is currently " "broken in this configuration.\n"); return -ENODEV; diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index 6743ff7dccfa..059f7c39c582 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -72,7 +72,7 @@ drm_clflush_pages(struct page *pages[], unsigned long num_pages) { #if defined(CONFIG_X86) - if (cpu_has_clflush) { + if (static_cpu_has(X86_FEATURE_CLFLUSH)) { drm_cache_flush_clflush(pages, num_pages); return; } @@ -105,7 +105,7 @@ void drm_clflush_sg(struct sg_table *st) { #if defined(CONFIG_X86) - if (cpu_has_clflush) { + if (static_cpu_has(X86_FEATURE_CLFLUSH)) { struct sg_page_iter sg_iter; mb(); @@ -129,7 +129,7 @@ void drm_clflush_virt_range(void *addr, unsigned long length) { #if defined(CONFIG_X86) - if (cpu_has_clflush) { + if (static_cpu_has(X86_FEATURE_CLFLUSH)) { const int size = boot_cpu_data.x86_clflush_size; void *end = addr + length; addr = (void *)(((unsigned long)addr) & -size); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index dabc08987b5e..f2cb9a9539ee 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1732,7 +1732,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, if (args->flags & ~(I915_MMAP_WC)) return -EINVAL; - if (args->flags & I915_MMAP_WC && !cpu_has_pat) + if (args->flags & I915_MMAP_WC && !boot_cpu_has(X86_FEATURE_PAT)) return -ENODEV; obj = drm_gem_object_lookup(dev, file, args->handle); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 1328bc5021b4..b845f468dd74 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -488,7 +488,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, ret = relocate_entry_cpu(obj, reloc, target_offset); else if (obj->map_and_fenceable) ret = relocate_entry_gtt(obj, reloc, target_offset); - else if (cpu_has_clflush) + else if (static_cpu_has(X86_FEATURE_CLFLUSH)) ret = relocate_entry_clflush(obj, reloc, target_offset); else { WARN_ONCE(1, "Impossible case in relocation handling\n"); diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c index 6f8b084e13d0..3d8ff09eba57 100644 --- a/drivers/input/joystick/analog.c +++ b/drivers/input/joystick/analog.c @@ -143,9 +143,9 @@ struct analog_port { #include -#define GET_TIME(x) do { if (cpu_has_tsc) x = (unsigned int)rdtsc(); else x = get_time_pit(); } while (0) -#define DELTA(x,y) (cpu_has_tsc ? ((y) - (x)) : ((x) - (y) + ((x) < (y) ? PIT_TICK_RATE / HZ : 0))) -#define TIME_NAME (cpu_has_tsc?"TSC":"PIT") +#define GET_TIME(x) do { if (boot_cpu_has(X86_FEATURE_TSC)) x = (unsigned int)rdtsc(); else x = get_time_pit(); } while (0) +#define DELTA(x,y) (boot_cpu_has(X86_FEATURE_TSC) ? ((y) - (x)) : ((x) - (y) + ((x) < (y) ? PIT_TICK_RATE / HZ : 0))) +#define TIME_NAME (boot_cpu_has(X86_FEATURE_TSC)?"TSC":"PIT") static unsigned int get_time_pit(void) { unsigned long flags; diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 8adaaeae3268..49721b4e1975 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -36,7 +36,7 @@ static void irq_remapping_disable_io_apic(void) * As this gets called during crash dump, keep this simple for * now. */ - if (cpu_has_apic || apic_from_smp_config()) + if (boot_cpu_has(X86_FEATURE_APIC) || apic_from_smp_config()) disconnect_bsp_APIC(0); } diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c index adc162c7040d..6e9042e3d2a9 100644 --- a/drivers/lguest/x86/core.c +++ b/drivers/lguest/x86/core.c @@ -603,7 +603,7 @@ void __init lguest_arch_host_init(void) * doing this. */ get_online_cpus(); - if (cpu_has_pge) { /* We have a broader idea of "global". */ + if (boot_cpu_has(X86_FEATURE_PGE)) { /* We have a broader idea of "global". */ /* Remember that this was originally set (for cleanup). */ cpu_had_pge = 1; /* diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 72c9f1f352b4..7c7830722ea2 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -635,10 +635,10 @@ static int receive(struct net_device *dev, int cnt) #ifdef __i386__ #include -#define GETTICK(x) \ -({ \ - if (cpu_has_tsc) \ - x = (unsigned int)rdtsc(); \ +#define GETTICK(x) \ +({ \ + if (boot_cpu_has(X86_FEATURE_TSC)) \ + x = (unsigned int)rdtsc(); \ }) #else /* __i386__ */ #define GETTICK(x) diff --git a/drivers/staging/unisys/visorbus/visorchipset.c b/drivers/staging/unisys/visorbus/visorchipset.c index 5fbda7b218c7..9cf4f8463c4e 100644 --- a/drivers/staging/unisys/visorbus/visorchipset.c +++ b/drivers/staging/unisys/visorbus/visorchipset.c @@ -2425,7 +2425,7 @@ static __init uint32_t visorutil_spar_detect(void) { unsigned int eax, ebx, ecx, edx; - if (cpu_has_hypervisor) { + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { /* check the ID */ cpuid(UNISYS_SPAR_LEAF_ID, &eax, &ebx, &ecx, &edx); return (ebx == UNISYS_SPAR_ID_EBX) && diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 339125bb4d2c..6a67ab94b553 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -245,7 +245,9 @@ #define INIT_TASK_DATA(align) \ . = ALIGN(align); \ - *(.data..init_task) + VMLINUX_SYMBOL(__start_init_task) = .; \ + *(.data..init_task) \ + VMLINUX_SYMBOL(__end_init_task) = .; /* * Read only Data diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index b47ebd170690..c73425de3cfe 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -9,6 +9,7 @@ TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_sysc TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer +TARGETS_C_64BIT_ONLY := fsgsbase TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY) diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c new file mode 100644 index 000000000000..5b2b4b3c634c --- /dev/null +++ b/tools/testing/selftests/x86/fsgsbase.c @@ -0,0 +1,398 @@ +/* + * fsgsbase.c, an fsgsbase test + * Copyright (c) 2014-2016 Andy Lutomirski + * GPL v2 + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifndef __x86_64__ +# error This test is 64-bit only +#endif + +static volatile sig_atomic_t want_segv; +static volatile unsigned long segv_addr; + +static int nerrs; + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void sigsegv(int sig, siginfo_t *si, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + if (!want_segv) { + clearhandler(SIGSEGV); + return; /* Crash cleanly. */ + } + + want_segv = false; + segv_addr = (unsigned long)si->si_addr; + + ctx->uc_mcontext.gregs[REG_RIP] += 4; /* Skip the faulting mov */ + +} + +enum which_base { FS, GS }; + +static unsigned long read_base(enum which_base which) +{ + unsigned long offset; + /* + * Unless we have FSGSBASE, there's no direct way to do this from + * user mode. We can get at it indirectly using signals, though. + */ + + want_segv = true; + + offset = 0; + if (which == FS) { + /* Use a constant-length instruction here. */ + asm volatile ("mov %%fs:(%%rcx), %%rax" : : "c" (offset) : "rax"); + } else { + asm volatile ("mov %%gs:(%%rcx), %%rax" : : "c" (offset) : "rax"); + } + if (!want_segv) + return segv_addr + offset; + + /* + * If that didn't segfault, try the other end of the address space. + * Unless we get really unlucky and run into the vsyscall page, this + * is guaranteed to segfault. + */ + + offset = (ULONG_MAX >> 1) + 1; + if (which == FS) { + asm volatile ("mov %%fs:(%%rcx), %%rax" + : : "c" (offset) : "rax"); + } else { + asm volatile ("mov %%gs:(%%rcx), %%rax" + : : "c" (offset) : "rax"); + } + if (!want_segv) + return segv_addr + offset; + + abort(); +} + +static void check_gs_value(unsigned long value) +{ + unsigned long base; + unsigned short sel; + + printf("[RUN]\tARCH_SET_GS to 0x%lx\n", value); + if (syscall(SYS_arch_prctl, ARCH_SET_GS, value) != 0) + err(1, "ARCH_SET_GS"); + + asm volatile ("mov %%gs, %0" : "=rm" (sel)); + base = read_base(GS); + if (base == value) { + printf("[OK]\tGSBASE was set as expected (selector 0x%hx)\n", + sel); + } else { + nerrs++; + printf("[FAIL]\tGSBASE was not as expected: got 0x%lx (selector 0x%hx)\n", + base, sel); + } + + if (syscall(SYS_arch_prctl, ARCH_GET_GS, &base) != 0) + err(1, "ARCH_GET_GS"); + if (base == value) { + printf("[OK]\tARCH_GET_GS worked as expected (selector 0x%hx)\n", + sel); + } else { + nerrs++; + printf("[FAIL]\tARCH_GET_GS was not as expected: got 0x%lx (selector 0x%hx)\n", + base, sel); + } +} + +static void mov_0_gs(unsigned long initial_base, bool schedule) +{ + unsigned long base, arch_base; + + printf("[RUN]\tARCH_SET_GS to 0x%lx then mov 0 to %%gs%s\n", initial_base, schedule ? " and schedule " : ""); + if (syscall(SYS_arch_prctl, ARCH_SET_GS, initial_base) != 0) + err(1, "ARCH_SET_GS"); + + if (schedule) + usleep(10); + + asm volatile ("mov %0, %%gs" : : "rm" (0)); + base = read_base(GS); + if (syscall(SYS_arch_prctl, ARCH_GET_GS, &arch_base) != 0) + err(1, "ARCH_GET_GS"); + if (base == arch_base) { + printf("[OK]\tGSBASE is 0x%lx\n", base); + } else { + nerrs++; + printf("[FAIL]\tGSBASE changed to 0x%lx but kernel reports 0x%lx\n", base, arch_base); + } +} + +static volatile unsigned long remote_base; +static volatile bool remote_hard_zero; +static volatile unsigned int ftx; + +/* + * ARCH_SET_FS/GS(0) may or may not program a selector of zero. HARD_ZERO + * means to force the selector to zero to improve test coverage. + */ +#define HARD_ZERO 0xa1fa5f343cb85fa4 + +static void do_remote_base() +{ + unsigned long to_set = remote_base; + bool hard_zero = false; + if (to_set == HARD_ZERO) { + to_set = 0; + hard_zero = true; + } + + if (syscall(SYS_arch_prctl, ARCH_SET_GS, to_set) != 0) + err(1, "ARCH_SET_GS"); + + if (hard_zero) + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0)); + + unsigned short sel; + asm volatile ("mov %%gs, %0" : "=rm" (sel)); + printf("\tother thread: ARCH_SET_GS(0x%lx)%s -- sel is 0x%hx\n", + to_set, hard_zero ? " and clear gs" : "", sel); +} + +void do_unexpected_base(void) +{ + /* + * The goal here is to try to arrange for GS == 0, GSBASE != + * 0, and for the the kernel the think that GSBASE == 0. + * + * To make the test as reliable as possible, this uses + * explicit descriptorss. (This is not the only way. This + * could use ARCH_SET_GS with a low, nonzero base, but the + * relevant side effect of ARCH_SET_GS could change.) + */ + + /* Step 1: tell the kernel that we have GSBASE == 0. */ + if (syscall(SYS_arch_prctl, ARCH_SET_GS, 0) != 0) + err(1, "ARCH_SET_GS"); + + /* Step 2: change GSBASE without telling the kernel. */ + struct user_desc desc = { + .entry_number = 0, + .base_addr = 0xBAADF00D, + .limit = 0xfffff, + .seg_32bit = 1, + .contents = 0, /* Data, grow-up */ + .read_exec_only = 0, + .limit_in_pages = 1, + .seg_not_present = 0, + .useable = 0 + }; + if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) == 0) { + printf("\tother thread: using LDT slot 0\n"); + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0x7)); + } else { + /* No modify_ldt for us (configured out, perhaps) */ + + struct user_desc *low_desc = mmap( + NULL, sizeof(desc), + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0); + memcpy(low_desc, &desc, sizeof(desc)); + + low_desc->entry_number = -1; + + /* 32-bit set_thread_area */ + long ret; + asm volatile ("int $0x80" + : "=a" (ret) : "a" (243), "b" (low_desc) + : "flags"); + memcpy(&desc, low_desc, sizeof(desc)); + munmap(low_desc, sizeof(desc)); + + if (ret != 0) { + printf("[NOTE]\tcould not create a segment -- test won't do anything\n"); + return; + } + printf("\tother thread: using GDT slot %d\n", desc.entry_number); + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)((desc.entry_number << 3) | 0x3))); + } + + /* + * Step 3: set the selector back to zero. On AMD chips, this will + * preserve GSBASE. + */ + + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0)); +} + +static void *threadproc(void *ctx) +{ + while (1) { + while (ftx == 0) + syscall(SYS_futex, &ftx, FUTEX_WAIT, 0, NULL, NULL, 0); + if (ftx == 3) + return NULL; + + if (ftx == 1) + do_remote_base(); + else if (ftx == 2) + do_unexpected_base(); + else + errx(1, "helper thread got bad command"); + + ftx = 0; + syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); + } +} + +static void set_gs_and_switch_to(unsigned long local, unsigned long remote) +{ + unsigned long base; + + bool hard_zero = false; + if (local == HARD_ZERO) { + hard_zero = true; + local = 0; + } + + printf("[RUN]\tARCH_SET_GS(0x%lx)%s, then schedule to 0x%lx\n", + local, hard_zero ? " and clear gs" : "", remote); + if (syscall(SYS_arch_prctl, ARCH_SET_GS, local) != 0) + err(1, "ARCH_SET_GS"); + if (hard_zero) + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0)); + + if (read_base(GS) != local) { + nerrs++; + printf("[FAIL]\tGSBASE wasn't set as expected\n"); + } + + remote_base = remote; + ftx = 1; + syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); + while (ftx != 0) + syscall(SYS_futex, &ftx, FUTEX_WAIT, 1, NULL, NULL, 0); + + base = read_base(GS); + if (base == local) { + printf("[OK]\tGSBASE remained 0x%lx\n", local); + } else { + nerrs++; + printf("[FAIL]\tGSBASE changed to 0x%lx\n", base); + } +} + +static void test_unexpected_base(void) +{ + unsigned long base; + + printf("[RUN]\tARCH_SET_GS(0), clear gs, then manipulate GSBASE in a different thread\n"); + if (syscall(SYS_arch_prctl, ARCH_SET_GS, 0) != 0) + err(1, "ARCH_SET_GS"); + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0)); + + ftx = 2; + syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); + while (ftx != 0) + syscall(SYS_futex, &ftx, FUTEX_WAIT, 1, NULL, NULL, 0); + + base = read_base(GS); + if (base == 0) { + printf("[OK]\tGSBASE remained 0\n"); + } else { + nerrs++; + printf("[FAIL]\tGSBASE changed to 0x%lx\n", base); + } +} + +int main() +{ + pthread_t thread; + + sethandler(SIGSEGV, sigsegv, 0); + + check_gs_value(0); + check_gs_value(1); + check_gs_value(0x200000000); + check_gs_value(0); + check_gs_value(0x200000000); + check_gs_value(1); + + for (int sched = 0; sched < 2; sched++) { + mov_0_gs(0, !!sched); + mov_0_gs(1, !!sched); + mov_0_gs(0x200000000, !!sched); + } + + /* Set up for multithreading. */ + + cpu_set_t cpuset; + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) + err(1, "sched_setaffinity to CPU 0"); /* should never fail */ + + if (pthread_create(&thread, 0, threadproc, 0) != 0) + err(1, "pthread_create"); + + static unsigned long bases_with_hard_zero[] = { + 0, HARD_ZERO, 1, 0x200000000, + }; + + for (int local = 0; local < 4; local++) { + for (int remote = 0; remote < 4; remote++) { + set_gs_and_switch_to(bases_with_hard_zero[local], + bases_with_hard_zero[remote]); + } + } + + test_unexpected_base(); + + ftx = 3; /* Kill the thread. */ + syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); + + if (pthread_join(thread, NULL) != 0) + err(1, "pthread_join"); + + return nerrs == 0 ? 0 : 1; +} diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c index 31a3035cd4eb..4af47079cf04 100644 --- a/tools/testing/selftests/x86/ldt_gdt.c +++ b/tools/testing/selftests/x86/ldt_gdt.c @@ -21,6 +21,9 @@ #include #include #include +#include +#include +#include #define AR_ACCESSED (1<<8) @@ -44,6 +47,12 @@ static int nerrs; +/* Points to an array of 1024 ints, each holding its own index. */ +static const unsigned int *counter_page; +static struct user_desc *low_user_desc; +static struct user_desc *low_user_desc_clear; /* Use to delete GDT entry */ +static int gdt_entry_num; + static void check_invalid_segment(uint16_t index, int ldt) { uint32_t has_limit = 0, has_ar = 0, limit, ar; @@ -561,16 +570,257 @@ static void do_exec_test(void) } } +static void setup_counter_page(void) +{ + unsigned int *page = mmap(NULL, 4096, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_32BIT, -1, 0); + if (page == MAP_FAILED) + err(1, "mmap"); + + for (int i = 0; i < 1024; i++) + page[i] = i; + counter_page = page; +} + +static int invoke_set_thread_area(void) +{ + int ret; + asm volatile ("int $0x80" + : "=a" (ret), "+m" (low_user_desc) : + "a" (243), "b" (low_user_desc) + : "flags"); + return ret; +} + +static void setup_low_user_desc(void) +{ + low_user_desc = mmap(NULL, 2 * sizeof(struct user_desc), + PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_32BIT, -1, 0); + if (low_user_desc == MAP_FAILED) + err(1, "mmap"); + + low_user_desc->entry_number = -1; + low_user_desc->base_addr = (unsigned long)&counter_page[1]; + low_user_desc->limit = 0xfffff; + low_user_desc->seg_32bit = 1; + low_user_desc->contents = 0; /* Data, grow-up*/ + low_user_desc->read_exec_only = 0; + low_user_desc->limit_in_pages = 1; + low_user_desc->seg_not_present = 0; + low_user_desc->useable = 0; + + if (invoke_set_thread_area() == 0) { + gdt_entry_num = low_user_desc->entry_number; + printf("[NOTE]\tset_thread_area is available; will use GDT index %d\n", gdt_entry_num); + } else { + printf("[NOTE]\tset_thread_area is unavailable\n"); + } + + low_user_desc_clear = low_user_desc + 1; + low_user_desc_clear->entry_number = gdt_entry_num; + low_user_desc_clear->read_exec_only = 1; + low_user_desc_clear->seg_not_present = 1; +} + +static void test_gdt_invalidation(void) +{ + if (!gdt_entry_num) + return; /* 64-bit only system -- we can't use set_thread_area */ + + unsigned short prev_sel; + unsigned short sel; + unsigned int eax; + const char *result; +#ifdef __x86_64__ + unsigned long saved_base; + unsigned long new_base; +#endif + + /* Test DS */ + invoke_set_thread_area(); + eax = 243; + sel = (gdt_entry_num << 3) | 3; + asm volatile ("movw %%ds, %[prev_sel]\n\t" + "movw %[sel], %%ds\n\t" +#ifdef __i386__ + "pushl %%ebx\n\t" +#endif + "movl %[arg1], %%ebx\n\t" + "int $0x80\n\t" /* Should invalidate ds */ +#ifdef __i386__ + "popl %%ebx\n\t" +#endif + "movw %%ds, %[sel]\n\t" + "movw %[prev_sel], %%ds" + : [prev_sel] "=&r" (prev_sel), [sel] "+r" (sel), + "+a" (eax) + : "m" (low_user_desc_clear), + [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) + : "flags"); + + if (sel != 0) { + result = "FAIL"; + nerrs++; + } else { + result = "OK"; + } + printf("[%s]\tInvalidate DS with set_thread_area: new DS = 0x%hx\n", + result, sel); + + /* Test ES */ + invoke_set_thread_area(); + eax = 243; + sel = (gdt_entry_num << 3) | 3; + asm volatile ("movw %%es, %[prev_sel]\n\t" + "movw %[sel], %%es\n\t" +#ifdef __i386__ + "pushl %%ebx\n\t" +#endif + "movl %[arg1], %%ebx\n\t" + "int $0x80\n\t" /* Should invalidate es */ +#ifdef __i386__ + "popl %%ebx\n\t" +#endif + "movw %%es, %[sel]\n\t" + "movw %[prev_sel], %%es" + : [prev_sel] "=&r" (prev_sel), [sel] "+r" (sel), + "+a" (eax) + : "m" (low_user_desc_clear), + [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) + : "flags"); + + if (sel != 0) { + result = "FAIL"; + nerrs++; + } else { + result = "OK"; + } + printf("[%s]\tInvalidate ES with set_thread_area: new ES = 0x%hx\n", + result, sel); + + /* Test FS */ + invoke_set_thread_area(); + eax = 243; + sel = (gdt_entry_num << 3) | 3; +#ifdef __x86_64__ + syscall(SYS_arch_prctl, ARCH_GET_FS, &saved_base); +#endif + asm volatile ("movw %%fs, %[prev_sel]\n\t" + "movw %[sel], %%fs\n\t" +#ifdef __i386__ + "pushl %%ebx\n\t" +#endif + "movl %[arg1], %%ebx\n\t" + "int $0x80\n\t" /* Should invalidate fs */ +#ifdef __i386__ + "popl %%ebx\n\t" +#endif + "movw %%fs, %[sel]\n\t" + : [prev_sel] "=&r" (prev_sel), [sel] "+r" (sel), + "+a" (eax) + : "m" (low_user_desc_clear), + [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) + : "flags"); + +#ifdef __x86_64__ + syscall(SYS_arch_prctl, ARCH_GET_FS, &new_base); +#endif + + /* Restore FS/BASE for glibc */ + asm volatile ("movw %[prev_sel], %%fs" : : [prev_sel] "rm" (prev_sel)); +#ifdef __x86_64__ + if (saved_base) + syscall(SYS_arch_prctl, ARCH_SET_FS, saved_base); +#endif + + if (sel != 0) { + result = "FAIL"; + nerrs++; + } else { + result = "OK"; + } + printf("[%s]\tInvalidate FS with set_thread_area: new FS = 0x%hx\n", + result, sel); + +#ifdef __x86_64__ + if (sel == 0 && new_base != 0) { + nerrs++; + printf("[FAIL]\tNew FSBASE was 0x%lx\n", new_base); + } else { + printf("[OK]\tNew FSBASE was zero\n"); + } +#endif + + /* Test GS */ + invoke_set_thread_area(); + eax = 243; + sel = (gdt_entry_num << 3) | 3; +#ifdef __x86_64__ + syscall(SYS_arch_prctl, ARCH_GET_GS, &saved_base); +#endif + asm volatile ("movw %%gs, %[prev_sel]\n\t" + "movw %[sel], %%gs\n\t" +#ifdef __i386__ + "pushl %%ebx\n\t" +#endif + "movl %[arg1], %%ebx\n\t" + "int $0x80\n\t" /* Should invalidate gs */ +#ifdef __i386__ + "popl %%ebx\n\t" +#endif + "movw %%gs, %[sel]\n\t" + : [prev_sel] "=&r" (prev_sel), [sel] "+r" (sel), + "+a" (eax) + : "m" (low_user_desc_clear), + [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) + : "flags"); + +#ifdef __x86_64__ + syscall(SYS_arch_prctl, ARCH_GET_GS, &new_base); +#endif + + /* Restore GS/BASE for glibc */ + asm volatile ("movw %[prev_sel], %%gs" : : [prev_sel] "rm" (prev_sel)); +#ifdef __x86_64__ + if (saved_base) + syscall(SYS_arch_prctl, ARCH_SET_GS, saved_base); +#endif + + if (sel != 0) { + result = "FAIL"; + nerrs++; + } else { + result = "OK"; + } + printf("[%s]\tInvalidate GS with set_thread_area: new GS = 0x%hx\n", + result, sel); + +#ifdef __x86_64__ + if (sel == 0 && new_base != 0) { + nerrs++; + printf("[FAIL]\tNew GSBASE was 0x%lx\n", new_base); + } else { + printf("[OK]\tNew GSBASE was zero\n"); + } +#endif +} + int main(int argc, char **argv) { if (argc == 1 && !strcmp(argv[0], "ldt_gdt_test_exec")) return finish_exec_test(); + setup_counter_page(); + setup_low_user_desc(); + do_simple_tests(); do_multicpu_tests(); do_exec_test(); + test_gdt_invalidation(); + return nerrs ? 1 : 0; }