diff options
Diffstat (limited to 'arch/x86/kernel')
49 files changed, 881 insertions, 249 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 7bd3bd310106..111eb356dbea 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-y += syscall_$(BITS).o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index b44577bc9744..ec94e11807dc 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -48,9 +48,20 @@ int acpi_suspend_lowlevel(void) #ifndef CONFIG_64BIT native_store_gdt((struct desc_ptr *)&header->pmode_gdt); + /* + * We have to check that we can write back the value, and not + * just read it. At least on 90 nm Pentium M (Family 6, Model + * 13), reading an invalid MSR is not guaranteed to trap, see + * Erratum X4 in "Intel Pentium M Processor on 90 nm Process + * with 2-MB L2 Cache and IntelĀ® Processor A100 and A110 on 90 + * nm process with 512-KB L2 Cache Specification Update". + */ if (!rdmsr_safe(MSR_EFER, &header->pmode_efer_low, - &header->pmode_efer_high)) + &header->pmode_efer_high) && + !wrmsr_safe(MSR_EFER, + header->pmode_efer_low, + header->pmode_efer_high)) header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER); #endif /* !CONFIG_64BIT */ @@ -61,7 +72,10 @@ int acpi_suspend_lowlevel(void) } if (!rdmsr_safe(MSR_IA32_MISC_ENABLE, &header->pmode_misc_en_low, - &header->pmode_misc_en_high)) + &header->pmode_misc_en_high) && + !wrmsr_safe(MSR_IA32_MISC_ENABLE, + header->pmode_misc_en_low, + header->pmode_misc_en_high)) header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE); header->realmode_flags = acpi_realmode_flags; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 3048ded1b598..59554dca96ec 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -20,6 +20,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, {} }; @@ -27,6 +28,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids); static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, {} }; @@ -81,13 +83,20 @@ int amd_cache_northbridges(void) next_northbridge(misc, amd_nb_misc_ids); node_to_amd_nb(i)->link = link = next_northbridge(link, amd_nb_link_ids); - } + } + /* GART present only on Fam15h upto model 0fh */ if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || - boot_cpu_data.x86 == 0x15) + (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) amd_northbridges.flags |= AMD_NB_GART; /* + * Check for L3 cache presence. + */ + if (!cpuid_edx(0x80000006)) + return 0; + + /* * Some CPU families support L3 Cache Index Disable. There are some * limitations because of E382 and E388 on family 0x10. */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 904611bf0e5a..033eb44dc661 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1263,7 +1263,7 @@ void __cpuinit setup_local_APIC(void) unsigned int value, queued; int i, j, acked = 0; unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz; + long long max_loops = cpu_khz ? cpu_khz : 1000000; if (cpu_has_tsc) rdtscll(tsc); @@ -1360,7 +1360,7 @@ void __cpuinit setup_local_APIC(void) break; } if (queued) { - if (cpu_has_tsc) { + if (cpu_has_tsc && cpu_khz) { rdtscll(ntsc); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 794f6eb54cd3..b32dbb411a9a 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -98,7 +98,7 @@ static int __init early_get_pnodeid(void) break; case UV3_HUB_PART_NUMBER: case UV3_HUB_PART_NUMBER_X: - uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1; + uv_min_hub_revision_id += UV3_HUB_REVISION_BASE; break; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 5013a48d1aff..ae177a014180 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -508,6 +508,16 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_EXTD_APICID); } #endif + + /* F16h erratum 793, CVE-2013-6885 */ + if (c->x86 == 0x16 && c->x86_model <= 0xf) { + u64 val; + + rdmsrl(MSR_AMD64_LS_CFG, val); + if (!(val & BIT(15))) + wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15)); + } + } static const int amd_erratum_383[]; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 22018f70a671..564140155c36 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -144,6 +144,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); static int __init x86_xsave_setup(char *s) { + if (strlen(s)) + return 0; setup_clear_cpu_cap(X86_FEATURE_XSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); setup_clear_cpu_cap(X86_FEATURE_AVX); @@ -284,8 +286,13 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) raw_local_save_flags(eflags); BUG_ON(eflags & X86_EFLAGS_AC); - if (cpu_has(c, X86_FEATURE_SMAP)) + if (cpu_has(c, X86_FEATURE_SMAP)) { +#ifdef CONFIG_X86_SMAP set_in_cr4(X86_CR4_SMAP); +#else + clear_in_cr4(X86_CR4_SMAP); +#endif + } } /* @@ -1129,7 +1136,7 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| - X86_EFLAGS_IOPL|X86_EFLAGS_AC); + X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } /* diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 9b0c441c03f5..8533e69d2b89 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -154,6 +154,21 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_ERMS); } } + + /* + * Intel Quark Core DevMan_001.pdf section 6.4.11 + * "The operating system also is required to invalidate (i.e., flush) + * 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 + */ + if (c->x86 == 5 && c->x86_model == 9) { + pr_info("Disabling PGE capability bit\n"); + setup_clear_cpu_cap(X86_FEATURE_PGE); + } } #ifdef CONFIG_X86_32 @@ -387,7 +402,8 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_PEBS); } - if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush) + if (c->x86 == 6 && cpu_has_clflush && + (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR); #ifdef CONFIG_X86_64 @@ -627,7 +643,7 @@ static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) tlb_flushall_shift = 5; break; case 0x63a: /* Ivybridge */ - tlb_flushall_shift = 1; + tlb_flushall_shift = 2; break; default: tlb_flushall_shift = 6; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 8f4be53ea04b..1853659820e0 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -60,6 +60,7 @@ static struct clocksource hyperv_cs = { .rating = 400, /* use this when running on Hyperv*/ .read = read_hv_clock, .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; static void __init ms_hyperv_init_platform(void) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fa72a39e5d46..3982357de5b0 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -510,8 +510,9 @@ generic_get_free_region(unsigned long base, unsigned long size, int replace_reg) static void generic_get_mtrr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type *type) { - unsigned int mask_lo, mask_hi, base_lo, base_hi; - unsigned int tmp, hi; + u32 mask_lo, mask_hi, base_lo, base_hi; + unsigned int hi; + u64 tmp, mask; /* * get_mtrr doesn't need to update mtrr_state, also it could be called @@ -532,18 +533,18 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); /* Work out the shifted address mask: */ - tmp = mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; - mask_lo = size_or_mask | tmp; + tmp = (u64)mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; + mask = size_or_mask | tmp; /* Expand tmp with high bits to all 1s: */ - hi = fls(tmp); + hi = fls64(tmp); if (hi > 0) { - tmp |= ~((1<<(hi - 1)) - 1); + tmp |= ~((1ULL<<(hi - 1)) - 1); - if (tmp != mask_lo) { + if (tmp != mask) { printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); - mask_lo = tmp; + mask = tmp; } } @@ -551,8 +552,8 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, * This works correctly if size is a power of two, i.e. a * contiguous range: */ - *size = -mask_lo; - *base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; + *size = -mask; + *base = (u64)base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; *type = base_lo & 0xff; out_put_cpu: diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 726bf963c227..ca22b73aaa25 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -305,7 +305,8 @@ int mtrr_add_page(unsigned long base, unsigned long size, return -EINVAL; } - if (base & size_or_mask || size & size_or_mask) { + if ((base | (base + size - 1)) >> + (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) { pr_warning("mtrr: base or size exceeds the MTRR width\n"); return -EINVAL; } @@ -583,6 +584,7 @@ static struct syscore_ops mtrr_syscore_ops = { int __initdata changed_by_mtrr_cleanup; +#define SIZE_OR_MASK_BITS(n) (~((1ULL << ((n) - PAGE_SHIFT)) - 1)) /** * mtrr_bp_init - initialize mtrrs on the boot CPU * @@ -600,7 +602,7 @@ void __init mtrr_bp_init(void) if (cpu_has_mtrr) { mtrr_if = &generic_mtrr_ops; - size_or_mask = 0xff000000; /* 36 bits */ + size_or_mask = SIZE_OR_MASK_BITS(36); size_and_mask = 0x00f00000; phys_addr = 36; @@ -619,7 +621,7 @@ void __init mtrr_bp_init(void) boot_cpu_data.x86_mask == 0x4)) phys_addr = 36; - size_or_mask = ~((1ULL << (phys_addr - PAGE_SHIFT)) - 1); + size_or_mask = SIZE_OR_MASK_BITS(phys_addr); size_and_mask = ~size_or_mask & 0xfffff00000ULL; } else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR && boot_cpu_data.x86 == 6) { @@ -627,7 +629,7 @@ void __init mtrr_bp_init(void) * VIA C* family have Intel style MTRRs, * but don't support PAE */ - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; phys_addr = 32; } @@ -637,21 +639,21 @@ void __init mtrr_bp_init(void) if (cpu_has_k6_mtrr) { /* Pre-Athlon (K6) AMD CPU MTRRs */ mtrr_if = mtrr_ops[X86_VENDOR_AMD]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CENTAUR: if (cpu_has_centaur_mcr) { mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CYRIX: if (cpu_has_cyrix_arr) { mtrr_if = mtrr_ops[X86_VENDOR_CYRIX]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1025f3c99d20..123d9e2271dc 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1165,6 +1165,9 @@ static void x86_pmu_del(struct perf_event *event, int flags) for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event_list[i]) { + if (i >= cpuc->n_events - cpuc->n_added) + --cpuc->n_added; + if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, event); @@ -1249,10 +1252,20 @@ void perf_events_lapic_init(void) static int __kprobes perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { + int ret; + u64 start_clock; + u64 finish_clock; + if (!atomic_read(&active_events)) return NMI_DONE; - return x86_pmu.handle_irq(regs); + start_clock = local_clock(); + ret = x86_pmu.handle_irq(regs); + finish_clock = local_clock(); + + perf_sample_event_took(finish_clock - start_clock); + + return ret; } struct event_constraint emptyconstraint; diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index 5f0581e713c2..b46601ada813 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/ptrace.h> +#include <linux/syscore_ops.h> #include <asm/apic.h> @@ -816,6 +817,18 @@ out: return ret; } +static void ibs_eilvt_setup(void) +{ + /* + * Force LVT offset assignment for family 10h: The offsets are + * not assigned by the BIOS for this family, so the OS is + * responsible for doing it. If the OS assignment fails, fall + * back to BIOS settings and try to setup this. + */ + if (boot_cpu_data.x86 == 0x10) + force_ibs_eilvt_setup(); +} + static inline int get_ibs_lvt_offset(void) { u64 val; @@ -851,6 +864,36 @@ static void clear_APIC_ibs(void *dummy) setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1); } +#ifdef CONFIG_PM + +static int perf_ibs_suspend(void) +{ + clear_APIC_ibs(NULL); + return 0; +} + +static void perf_ibs_resume(void) +{ + ibs_eilvt_setup(); + setup_APIC_ibs(NULL); +} + +static struct syscore_ops perf_ibs_syscore_ops = { + .resume = perf_ibs_resume, + .suspend = perf_ibs_suspend, +}; + +static void perf_ibs_pm_init(void) +{ + register_syscore_ops(&perf_ibs_syscore_ops); +} + +#else + +static inline void perf_ibs_pm_init(void) { } + +#endif + static int __cpuinit perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -877,18 +920,12 @@ static __init int amd_ibs_init(void) if (!caps) return -ENODEV; /* ibs not supported by the cpu */ - /* - * Force LVT offset assignment for family 10h: The offsets are - * not assigned by the BIOS for this family, so the OS is - * responsible for doing it. If the OS assignment fails, fall - * back to BIOS settings and try to setup this. - */ - if (boot_cpu_data.x86 == 0x10) - force_ibs_eilvt_setup(); + ibs_eilvt_setup(); if (!ibs_eilvt_valid()) goto out; + perf_ibs_pm_init(); get_online_cpus(); ibs_caps = caps; /* make ibs_caps visible to other cpus: */ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index a9e22073bd56..6d6bb6f4fd43 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1199,6 +1199,15 @@ again: intel_pmu_lbr_read(); /* + * CondChgd bit 63 doesn't mean any overflow status. Ignore + * and clear the bit. + */ + if (__test_and_clear_bit(63, (unsigned long *)&status)) { + if (!status) + goto done; + } + + /* * PEBS overflow sets bit 62 in the global status register */ if (__test_and_clear_bit(62, (unsigned long *)&status)) { @@ -2163,6 +2172,9 @@ __init int intel_pmu_init(void) case 62: /* IvyBridge EP */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + /* dTLB-load-misses on IVB is different than SNB */ + hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */ + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 52441a2af538..7185af255fb5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -314,8 +314,8 @@ static struct uncore_event_desc snbep_uncore_imc_events[] = { static struct uncore_event_desc snbep_uncore_qpi_events[] = { INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), - INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"), - INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"), + INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"), { /* end: all zeroes */ }, }; @@ -2657,6 +2657,17 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); } +/* + * Using uncore_pmu_event_init pmu event_init callback + * as a detection point for uncore events. + */ +static int uncore_pmu_event_init(struct perf_event *event); + +static bool is_uncore_event(struct perf_event *event) +{ + return event->pmu->event_init == uncore_pmu_event_init; +} + static int uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp) { @@ -2671,13 +2682,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b return -EINVAL; n = box->n_events; - box->event_list[n] = leader; - n++; + + if (is_uncore_event(leader)) { + box->event_list[n] = leader; + n++; + } + if (!dogrp) return n; list_for_each_entry(event, &leader->sibling_list, group_entry) { - if (event->state <= PERF_EVENT_STATE_OFF) + if (!is_uncore_event(event) || + event->state <= PERF_EVENT_STATE_OFF) continue; if (n >= max_count) diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index b1581527a236..2fbad6b9f23c 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -52,8 +52,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) } #ifdef CONFIG_BLK_DEV_INITRD -void __init early_init_dt_setup_initrd_arch(unsigned long start, - unsigned long end) +void __init early_init_dt_setup_initrd_arch(u64 start, u64 end) { initrd_start = (unsigned long)__va(start); initrd_end = (unsigned long)__va(end); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index addb207dab92..66e274a3d968 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = { [ DEBUG_STACK-1 ] = "#DB", [ NMI_STACK-1 ] = "NMI", [ DOUBLEFAULT_STACK-1 ] = "#DF", - [ STACKFAULT_STACK-1 ] = "#SS", [ MCE_STACK-1 ] = "#MC", #if DEBUG_STKSZ > EXCEPTION_STKSZ [ N_EXCEPTION_STACKS ... diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d32abeabbda5..174da5fc5a7b 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -658,15 +658,18 @@ __init void e820_setup_gap(void) * boot_params.e820_map, others are passed via SETUP_E820_EXT node of * linked list of struct setup_data, which is parsed here. */ -void __init parse_e820_ext(struct setup_data *sdata) +void __init parse_e820_ext(u64 phys_addr, u32 data_len) { int entries; struct e820entry *extmap; + struct setup_data *sdata; + sdata = early_memremap(phys_addr, data_len); entries = sdata->len / sizeof(struct e820entry); extmap = (struct e820entry *)(sdata->data); __append_e820_map(extmap, entries); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + early_iounmap(sdata, data_len); printk(KERN_INFO "e820: extended physical RAM map:\n"); e820_print_map("extended"); } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 94ab6b90dd3f..4f7c82cdd0f5 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -196,16 +196,21 @@ static void __init ati_bugs_contd(int num, int slot, int func) static void __init intel_remapping_check(int num, int slot, int func) { u8 revision; + u16 device; + device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID); revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID); /* - * Revision 0x13 of this chipset supports irq remapping - * but has an erratum that breaks its behavior, flag it as such + * Revision <= 13 of all triggering devices id in this quirk + * have a problem draining interrupts when irq remapping is + * enabled, and should be flagged as broken. Additionally + * revision 0x22 of device id 0x3405 has this problem. */ - if (revision == 0x13) + if (revision <= 0x13) + set_irq_remapping_broken(); + else if (device == 0x3405 && revision == 0x22) set_irq_remapping_broken(); - } #define QFLAG_APPLY_ONCE 0x1 @@ -239,6 +244,8 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd }, { PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST, PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, + { PCI_VENDOR_ID_INTEL, 0x3405, PCI_CLASS_BRIDGE_HOST, + PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, { PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST, PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, {} diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 8f3e2dec1df3..5c38e2b298cd 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -434,8 +434,9 @@ sysenter_past_esp: jnz sysenter_audit sysenter_do_call: cmpl $(NR_syscalls), %eax - jae syscall_badsys + jae sysenter_badsys call *sys_call_table(,%eax,4) +sysenter_after_call: movl %eax,PT_EAX(%esp) LOCKDEP_SYS_EXIT DISABLE_INTERRUPTS(CLBR_ANY) @@ -516,6 +517,7 @@ ENTRY(system_call) jae syscall_badsys syscall_call: call *sys_call_table(,%eax,4) +syscall_after_call: movl %eax,PT_EAX(%esp) # store the return value syscall_exit: LOCKDEP_SYS_EXIT @@ -530,6 +532,7 @@ syscall_exit: restore_all: TRACE_IRQS_IRET restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS # Warning: PT_OLDSS(%esp) contains the wrong/random values if we # are returning to the kernel. @@ -540,6 +543,7 @@ restore_all_notrace: cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax CFI_REMEMBER_STATE je ldt_ss # returning to user-space with LDT SS +#endif restore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code irq_return: @@ -552,13 +556,9 @@ ENTRY(iret_exc) .previous _ASM_EXTABLE(irq_return,iret_exc) +#ifdef CONFIG_X86_ESPFIX32 CFI_RESTORE_STATE ldt_ss: - larl PT_OLDSS(%esp), %eax - jnz restore_nocheck - testl $0x00400000, %eax # returning to 32bit stack? - jnz restore_nocheck # allright, normal return - #ifdef CONFIG_PARAVIRT /* * The kernel can't run on a non-flat stack if paravirt mode @@ -600,6 +600,7 @@ ldt_ss: lss (%esp), %esp /* switch to espfix segment */ CFI_ADJUST_CFA_OFFSET -8 jmp restore_nocheck +#endif CFI_ENDPROC ENDPROC(system_call) @@ -690,8 +691,13 @@ syscall_fault: END(syscall_fault) syscall_badsys: - movl $-ENOSYS,PT_EAX(%esp) - jmp resume_userspace + movl $-ENOSYS,%eax + jmp syscall_after_call +END(syscall_badsys) + +sysenter_badsys: + movl $-ENOSYS,%eax + jmp sysenter_after_call END(syscall_badsys) CFI_ENDPROC /* @@ -707,6 +713,7 @@ END(syscall_badsys) * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. */ +#ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ @@ -716,8 +723,10 @@ END(syscall_badsys) pushl_cfi %eax lss (%esp), %esp /* switch to the normal stack segment */ CFI_ADJUST_CFA_OFFSET -8 +#endif .endm .macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax @@ -728,6 +737,7 @@ END(syscall_badsys) /* switch to normal stack */ FIXUP_ESPFIX_STACK 27: +#endif .endm /* @@ -1075,7 +1085,7 @@ ENTRY(ftrace_caller) pushl $0 /* Pass NULL as regs pointer */ movl 4*4(%esp), %eax movl 0x4(%ebp), %edx - leal function_trace_op, %ecx + movl function_trace_op, %ecx subl $MCOUNT_INSN_SIZE, %eax .globl ftrace_call @@ -1133,7 +1143,7 @@ ENTRY(ftrace_regs_caller) movl 12*4(%esp), %eax /* Load ip (1st parameter) */ subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ - leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ pushl %esp /* Save pt_regs as 4th parameter */ GLOBAL(ftrace_regs_call) @@ -1335,11 +1345,13 @@ END(debug) ENTRY(nmi) RING0_INT_FRAME ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax popl_cfi %eax je nmi_espfix_stack +#endif cmpl $ia32_sysenter_target,(%esp) je nmi_stack_fixup pushl_cfi %eax @@ -1379,6 +1391,7 @@ nmi_debug_stack_check: FIX_STACK 24, nmi_stack_correct, 1 jmp nmi_stack_correct +#ifdef CONFIG_X86_ESPFIX32 nmi_espfix_stack: /* We have a RING0_INT_FRAME here. * @@ -1400,6 +1413,7 @@ nmi_espfix_stack: lss 12+4(%esp), %esp # back to espfix stack CFI_ADJUST_CFA_OFFSET -24 jmp irq_return +#endif CFI_ENDPROC END(nmi) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 727208941030..6ed8f16fd61b 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -58,6 +58,7 @@ #include <asm/asm.h> #include <asm/context_tracking.h> #include <asm/smap.h> +#include <asm/pgtable_types.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -88,7 +89,7 @@ END(function_hook) MCOUNT_SAVE_FRAME \skip /* Load the ftrace_ops into the 3rd parameter */ - leaq function_trace_op, %rdx + movq function_trace_op(%rip), %rdx /* Load ip into the first parameter */ movq RIP(%rsp), %rdi @@ -365,7 +366,7 @@ ENDPROC(native_usergs_sysret64) /*CFI_REL_OFFSET ss,0*/ pushq_cfi %rax /* rsp */ CFI_REL_OFFSET rsp,0 - pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_BIT1) /* eflags - interrupts on */ + pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) /* eflags - interrupts on */ /*CFI_REL_OFFSET rflags,0*/ pushq_cfi $__KERNEL_CS /* cs */ /*CFI_REL_OFFSET cs,0*/ @@ -556,11 +557,14 @@ ENTRY(ret_from_fork) testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread? jz 1f - testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET - jnz int_ret_from_sys_call - - RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET - jmp ret_from_sys_call # go to the SYSRET fastpath + /* + * By the time we get here, we have no idea whether our pt_regs, + * ti flags, and ti status came from the 64-bit SYSCALL fast path, + * the slow path, or one of the ia32entry paths. + * Use int_ret_from_sys_call to return, since it can safely handle + * all of the above. + */ + jmp int_ret_from_sys_call 1: subq $REST_SKIP, %rsp # leave space for volatiles @@ -1056,32 +1060,52 @@ restore_args: irq_return: INTERRUPT_RETURN - _ASM_EXTABLE(irq_return, bad_iret) -#ifdef CONFIG_PARAVIRT ENTRY(native_iret) - iretq - _ASM_EXTABLE(native_iret, bad_iret) + /* + * Are we returning to a stack segment from the LDT? Note: in + * 64-bit mode SS:RSP on the exception stack is always valid. + */ +#ifdef CONFIG_X86_ESPFIX64 + testb $4,(SS-RIP)(%rsp) + jnz native_irq_return_ldt #endif - .section .fixup,"ax" -bad_iret: +.global native_irq_return_iret +native_irq_return_iret: /* - * The iret traps when the %cs or %ss being restored is bogus. - * We've lost the original trap vector and error code. - * #GPF is the most likely one to get for an invalid selector. - * So pretend we completed the iret and took the #GPF in user mode. - * - * We are now running with the kernel GS after exception recovery. - * But error_entry expects us to have user GS to match the user %cs, - * so swap back. + * This may fault. Non-paranoid faults on return to userspace are + * handled by fixup_bad_iret. These include #SS, #GP, and #NP. + * Double-faults due to espfix64 are handled in do_double_fault. + * Other faults here are fatal. */ - pushq $0 + iretq +#ifdef CONFIG_X86_ESPFIX64 +native_irq_return_ldt: + pushq_cfi %rax + pushq_cfi %rdi SWAPGS - jmp general_protection - - .previous + movq PER_CPU_VAR(espfix_waddr),%rdi + movq %rax,(0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp),%rax /* RIP */ + movq %rax,(1*8)(%rdi) + movq (3*8)(%rsp),%rax /* CS */ + movq %rax,(2*8)(%rdi) + movq (4*8)(%rsp),%rax /* RFLAGS */ + movq %rax,(3*8)(%rdi) + movq (6*8)(%rsp),%rax /* SS */ + movq %rax,(5*8)(%rdi) + movq (5*8)(%rsp),%rax /* RSP */ + movq %rax,(4*8)(%rdi) + andl $0xffff0000,%eax + popq_cfi %rdi + orq PER_CPU_VAR(espfix_stack),%rax + SWAPGS + movq %rax,%rsp + popq_cfi %rax + jmp native_irq_return_iret +#endif /* edi: workmask, edx: work */ retint_careful: @@ -1127,9 +1151,9 @@ ENTRY(retint_kernel) call preempt_schedule_irq jmp exit_intr #endif - CFI_ENDPROC END(common_interrupt) + /* * End of kprobes section */ @@ -1468,7 +1492,7 @@ apicinterrupt HYPERVISOR_CALLBACK_VECTOR \ paranoidzeroentry_ist debug do_debug DEBUG_STACK paranoidzeroentry_ist int3 do_int3 DEBUG_STACK -paranoiderrorentry stack_segment do_stack_segment +errorentry stack_segment do_stack_segment #ifdef CONFIG_XEN zeroentry xen_debug do_debug zeroentry xen_int3 do_int3 @@ -1578,16 +1602,15 @@ error_sti: /* * There are two places in the kernel that can potentially fault with - * usergs. Handle them here. The exception handlers after iret run with - * kernel gs again, so don't set the user space flag. B stepping K8s - * sometimes report an truncated RIP for IRET exceptions returning to - * compat mode. Check for these here too. + * usergs. Handle them here. B stepping K8s sometimes report a + * truncated RIP for IRET exceptions returning to compat mode. Check + * for these here too. */ error_kernelspace: incl %ebx - leaq irq_return(%rip),%rcx + leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) - je error_swapgs + je error_bad_iret movl %ecx,%eax /* zero extend */ cmpq %rax,RIP+8(%rsp) je bstep_iret @@ -1598,7 +1621,15 @@ error_kernelspace: bstep_iret: /* Fix truncated RIP */ movq %rcx,RIP+8(%rsp) - jmp error_swapgs + /* fall through */ + +error_bad_iret: + SWAPGS + mov %rsp,%rdi + call fixup_bad_iret + mov %rax,%rsp + decl %ebx /* Return to usergs */ + jmp error_sti CFI_ENDPROC END(error_entry) diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c new file mode 100644 index 000000000000..94d857fb1033 --- /dev/null +++ b/arch/x86/kernel/espfix_64.c @@ -0,0 +1,208 @@ +/* ----------------------------------------------------------------------- * + * + * Copyright 2014 Intel Corporation; author: H. Peter Anvin + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * ----------------------------------------------------------------------- */ + +/* + * The IRET instruction, when returning to a 16-bit segment, only + * restores the bottom 16 bits of the user space stack pointer. This + * causes some 16-bit software to break, but it also leaks kernel state + * to user space. + * + * This works around this by creating percpu "ministacks", each of which + * is mapped 2^16 times 64K apart. When we detect that the return SS is + * on the LDT, we copy the IRET frame to the ministack and use the + * relevant alias to return to userspace. The ministacks are mapped + * readonly, so if the IRET fault we promote #GP to #DF which is an IST + * vector and thus has its own stack; we then do the fixup in the #DF + * handler. + * + * This file sets up the ministacks and the related page tables. The + * actual ministack invocation is in entry_64.S. + */ + +#include <linux/init.h> +#include <linux/init_task.h> +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/gfp.h> +#include <linux/random.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/setup.h> +#include <asm/espfix.h> + +/* + * Note: we only need 6*8 = 48 bytes for the espfix stack, but round + * it up to a cache line to avoid unnecessary sharing. + */ +#define ESPFIX_STACK_SIZE (8*8UL) +#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) + +/* There is address space for how many espfix pages? */ +#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16)) + +#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) +#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS +# error "Need more than one PGD for the ESPFIX hack" +#endif + +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) + +/* This contains the *bottom* address of the espfix stack */ +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +/* Initialization mutex - should this be a spinlock? */ +static DEFINE_MUTEX(espfix_init_mutex); + +/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */ +#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE) +static void *espfix_pages[ESPFIX_MAX_PAGES]; + +static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD] + __aligned(PAGE_SIZE); + +static unsigned int page_random, slot_random; + +/* + * This returns the bottom address of the espfix stack for a specific CPU. + * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case + * we have to account for some amount of padding at the end of each page. + */ +static inline unsigned long espfix_base_addr(unsigned int cpu) +{ + unsigned long page, slot; + unsigned long addr; + + page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random; + slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE; + addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE); + addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16); + addr += ESPFIX_BASE_ADDR; + return addr; +} + +#define PTE_STRIDE (65536/PAGE_SIZE) +#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE) +#define ESPFIX_PMD_CLONES PTRS_PER_PMD +#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES)) + +#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX) + +static void init_espfix_random(void) +{ + unsigned long rand; + + /* + * This is run before the entropy pools are initialized, + * but this is hopefully better than nothing. + */ + if (!arch_get_random_long(&rand)) { + /* The constant is an arbitrary large prime */ + rdtscll(rand); + rand *= 0xc345c6b72fd16123UL; + } + + slot_random = rand % ESPFIX_STACKS_PER_PAGE; + page_random = (rand / ESPFIX_STACKS_PER_PAGE) + & (ESPFIX_PAGE_SPACE - 1); +} + +void __init init_espfix_bsp(void) +{ + pgd_t *pgd_p; + pteval_t ptemask; + + ptemask = __supported_pte_mask; + + /* Install the espfix pud into the kernel page directory */ + pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + + /* Randomize the locations */ + init_espfix_random(); + + /* The rest is the same as for any other processor */ + init_espfix_ap(); +} + +void init_espfix_ap(void) +{ + unsigned int cpu, page; + unsigned long addr; + pud_t pud, *pud_p; + pmd_t pmd, *pmd_p; + pte_t pte, *pte_p; + int n; + void *stack_page; + pteval_t ptemask; + + /* We only have to do this once... */ + if (likely(this_cpu_read(espfix_stack))) + return; /* Already initialized */ + + cpu = smp_processor_id(); + addr = espfix_base_addr(cpu); + page = cpu/ESPFIX_STACKS_PER_PAGE; + + /* Did another CPU already set this up? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (likely(stack_page)) + goto done; + + mutex_lock(&espfix_init_mutex); + + /* Did we race on the lock? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (stack_page) + goto unlock_done; + + ptemask = __supported_pte_mask; + + pud_p = &espfix_pud_page[pud_index(addr)]; + pud = *pud_p; + if (!pud_present(pud)) { + pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); + pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PUD_CLONES; n++) + set_pud(&pud_p[n], pud); + } + + pmd_p = pmd_offset(&pud, addr); + pmd = *pmd_p; + if (!pmd_present(pmd)) { + pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); + pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PMD_CLONES; n++) + set_pmd(&pmd_p[n], pmd); + } + + pte_p = pte_offset_kernel(&pmd, addr); + stack_page = (void *)__get_free_page(GFP_KERNEL); + pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); + for (n = 0; n < ESPFIX_PTE_CLONES; n++) + set_pte(&pte_p[n*PTE_STRIDE], pte); + + /* Job is done for this CPU and any CPU which shares this page */ + ACCESS_ONCE(espfix_pages[page]) = stack_page; + +unlock_done: + mutex_unlock(&espfix_init_mutex); +done: + this_cpu_write(espfix_stack, addr); + this_cpu_write(espfix_waddr, (unsigned long)stack_page + + (addr & ~PAGE_MASK)); +} diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 42a392a9fd02..1ffc32dbe450 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -77,8 +77,7 @@ within(unsigned long addr, unsigned long start, unsigned long end) return addr >= start && addr < end; } -static int -do_ftrace_mod_code(unsigned long ip, const void *new_code) +static unsigned long text_ip_addr(unsigned long ip) { /* * On x86_64, kernel text mappings are mapped read-only with @@ -91,7 +90,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code) if (within(ip, (unsigned long)_text, (unsigned long)_etext)) ip = (unsigned long)__va(__pa_symbol(ip)); - return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE); + return ip; } static const unsigned char *ftrace_nop_replace(void) @@ -123,8 +122,10 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) return -EINVAL; + ip = text_ip_addr(ip); + /* replace the text with the new text */ - if (do_ftrace_mod_code(ip, new_code)) + if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) return -EPERM; sync_core(); @@ -221,33 +222,56 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return -EINVAL; } -int ftrace_update_ftrace_func(ftrace_func_t func) +static unsigned long ftrace_update_func; + +static int update_ftrace_func(unsigned long ip, void *new) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned char old[MCOUNT_INSN_SIZE], *new; + unsigned char old[MCOUNT_INSN_SIZE]; int ret; - memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(ip, (unsigned long)func); + memcpy(old, (void *)ip, MCOUNT_INSN_SIZE); + + ftrace_update_func = ip; + /* Make sure the breakpoints see the ftrace_update_func update */ + smp_wmb(); /* See comment above by declaration of modifying_ftrace_code */ atomic_inc(&modifying_ftrace_code); ret = ftrace_modify_code(ip, old, new); + atomic_dec(&modifying_ftrace_code); + + return ret; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned char *new; + int ret; + + new = ftrace_call_replace(ip, (unsigned long)func); + ret = update_ftrace_func(ip, new); + /* Also update the regs callback function */ if (!ret) { ip = (unsigned long)(&ftrace_regs_call); - memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE); new = ftrace_call_replace(ip, (unsigned long)func); - ret = ftrace_modify_code(ip, old, new); + ret = update_ftrace_func(ip, new); } - atomic_dec(&modifying_ftrace_code); - return ret; } +static int is_ftrace_caller(unsigned long ip) +{ + if (ip == ftrace_update_func) + return 1; + + return 0; +} + /* * A breakpoint was added to the code address we are about to * modify, and this is the handle that will just skip over it. @@ -257,10 +281,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func) */ int ftrace_int3_handler(struct pt_regs *regs) { + unsigned long ip; + if (WARN_ON_ONCE(!regs)) return 0; - if (!ftrace_location(regs->ip - 1)) + ip = regs->ip - 1; + if (!ftrace_location(ip) && !is_ftrace_caller(ip)) return 0; regs->ip += MCOUNT_INSN_SIZE - 1; @@ -632,8 +659,8 @@ ftrace_modify_code(unsigned long ip, unsigned const char *old_code, ret = -EPERM; goto out; } - run_sync(); out: + run_sync(); return ret; fail_update: @@ -665,45 +692,41 @@ int __init ftrace_dyn_arch_init(void *data) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); -static int ftrace_mod_jmp(unsigned long ip, - int old_offset, int new_offset) +static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { - unsigned char code[MCOUNT_INSN_SIZE]; + static union ftrace_code_union calc; - if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; + /* Jmp not a call (ignore the .e8) */ + calc.e8 = 0xe9; + calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - if (code[0] != 0xe9 || old_offset != *(int *)(&code[1])) - return -EINVAL; + /* + * ftrace external locks synchronize the access to the static variable. + */ + return calc.code; +} - *(int *)(&code[1]) = new_offset; +static int ftrace_mod_jmp(unsigned long ip, void *func) +{ + unsigned char *new; - if (do_ftrace_mod_code(ip, &code)) - return -EPERM; + new = ftrace_jmp_replace(ip, (unsigned long)func); - return 0; + return update_ftrace_func(ip, new); } int ftrace_enable_ftrace_graph_caller(void) { unsigned long ip = (unsigned long)(&ftrace_graph_call); - int old_offset, new_offset; - old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE); - new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE); - - return ftrace_mod_jmp(ip, old_offset, new_offset); + return ftrace_mod_jmp(ip, &ftrace_graph_caller); } int ftrace_disable_ftrace_graph_caller(void) { unsigned long ip = (unsigned long)(&ftrace_graph_call); - int old_offset, new_offset; - - old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE); - new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE); - return ftrace_mod_jmp(ip, old_offset, new_offset); + return ftrace_mod_jmp(ip, &ftrace_stub); } #endif /* !CONFIG_DYNAMIC_FTRACE */ diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 73afd11799ca..df63cae573e0 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -566,6 +566,10 @@ ENDPROC(early_idt_handlers) /* This is global to keep gas from relaxing the jumps */ ENTRY(early_idt_handler) cld + + cmpl $2,(%esp) # X86_TRAP_NMI + je is_nmi # Ignore NMI + cmpl $2,%ss:early_recursion_flag je hlt_loop incl %ss:early_recursion_flag @@ -616,8 +620,9 @@ ex_entry: pop %edx pop %ecx pop %eax - addl $8,%esp /* drop vector number and error code */ decl %ss:early_recursion_flag +is_nmi: + addl $8,%esp /* drop vector number and error code */ iret ENDPROC(early_idt_handler) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 321d65ebaffe..f2a9a2aa98f3 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -343,6 +343,9 @@ early_idt_handlers: ENTRY(early_idt_handler) cld + cmpl $2,(%rsp) # X86_TRAP_NMI + je is_nmi # Ignore NMI + cmpl $2,early_recursion_flag(%rip) jz 1f incl early_recursion_flag(%rip) @@ -405,8 +408,9 @@ ENTRY(early_idt_handler) popq %rdx popq %rcx popq %rax - addq $16,%rsp # drop vector number and error code decl early_recursion_flag(%rip) +is_nmi: + addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN ENDPROC(early_idt_handler) @@ -513,7 +517,7 @@ ENTRY(phys_base) #include "../../x86/xen/xen-head.S" .section .bss, "aw", @nobits - .align L1_CACHE_BYTES + .align PAGE_SIZE ENTRY(idt_table) .skip IDT_ENTRIES * 16 diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index cb339097b9ea..b03ff1842547 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin); void __kernel_fpu_end(void) { - if (use_eager_fpu()) - math_state_restore(); - else + if (use_eager_fpu()) { + /* + * For eager fpu, most the time, tsk_used_math() is true. + * Restore the user math as we are done with the kernel usage. + * At few instances during thread exit, signal handling etc, + * tsk_used_math() is false. Those few places will take proper + * actions, so we don't need to restore the math here. + */ + if (likely(tsk_used_math(current))) + math_state_restore(); + } else { stts(); + } } EXPORT_SYMBOL(__kernel_fpu_end); @@ -116,7 +125,7 @@ static void __cpuinit mxcsr_feature_mask_init(void) if (cpu_has_fxsr) { memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); - asm volatile("fxsave %0" : : "m" (fx_scratch)); + asm volatile("fxsave %0" : "+m" (fx_scratch)); mask = fx_scratch.mxcsr_mask; if (mask == 0) mask = 0x0000ffbf; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 211bce445522..0c6c07cea3f7 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1017,6 +1017,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->flags &= ~X86_EFLAGS_IF; trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); + + /* + * jprobes use jprobe_return() which skips the normal return + * path of the function, and this messes up the accounting of the + * function graph tracer to get messed up. + * + * Pause function graph tracing while performing the jprobe function. + */ + pause_graph_tracing(); return 1; } @@ -1042,24 +1051,25 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); u8 *addr = (u8 *) (regs->ip - 1); struct jprobe *jp = container_of(p, struct jprobe, kp); + void *saved_sp = kcb->jprobe_saved_sp; if ((addr > (u8 *) jprobe_return) && (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != kcb->jprobe_saved_sp) { + if (stack_addr(regs) != saved_sp) { struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; printk(KERN_ERR "current sp %p does not match saved sp %p\n", - stack_addr(regs), kcb->jprobe_saved_sp); + stack_addr(regs), saved_sp); printk(KERN_ERR "Saved registers for jprobe %p\n", jp); show_regs(saved_regs); printk(KERN_ERR "Current registers\n"); show_regs(regs); BUG(); } + /* It's OK to start function graph tracing again */ + unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp), - kcb->jprobes_stack, - MIN_STACK_SIZE(kcb->jprobe_saved_sp)); + memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp)); preempt_enable_no_resched(); return 1; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index cd6d9a5a42f6..c4ff2a916139 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -279,7 +279,14 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; - pv_info.paravirt_enabled = 1; + + /* + * KVM isn't paravirt in the sense of paravirt_enabled. A KVM + * guest kernel works like a bare metal kernel with additional + * features, and paravirt_enabled is about features that are + * missing. + */ + pv_info.paravirt_enabled = 0; if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) pv_cpu_ops.io_delay = kvm_io_delay; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 3dd37ebd591b..41514f56c241 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -265,7 +265,6 @@ void __init kvmclock_init(void) #endif kvm_get_preset_lpj(); clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); - pv_info.paravirt_enabled = 1; pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ebc987398923..c37886d759cc 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -229,6 +229,11 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } } + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out_unlock; + } + fill_ldt(&ldt, &ldt_info); if (oldmode) ldt.avl = 0; diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index efdec7cd8e01..b516dfb411ec 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -430,7 +430,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); if (request_firmware(&fw, (const char *)fw_name, device)) { - pr_err("failed to load file %s\n", fw_name); + pr_debug("failed to load file %s\n", fw_name); goto out; } diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 3f08f34f93eb..a1da6737ba5b 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq"); DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); -DEF_NATIVE(pv_cpu_ops, iret, "iretq"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); @@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, iret); PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 872079a67e4d..f7d0672481fd 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -100,8 +100,10 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, flag |= __GFP_ZERO; again: page = NULL; - if (!(flag & GFP_ATOMIC)) + /* CMA can be used only in the context which permits sleeping */ + if (flag & __GFP_WAIT) page = dma_alloc_from_contiguous(dev, count, get_order(size)); + /* fallback */ if (!page) page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); if (!page) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 81a5f5e8f142..59b90379cb6a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -391,9 +391,9 @@ static void amd_e400_idle(void) * The switch back from broadcast mode needs to be * called with interrupts disabled. */ - local_irq_disable(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); - local_irq_enable(); + local_irq_disable(); + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); + local_irq_enable(); } else default_idle(); } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 7305f7dfc7ab..0339f5c14bf9 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -147,7 +147,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->bp = arg; childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; + childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 355ae06dbf94..7099ab1e075b 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -176,7 +176,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->bp = arg; childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; + childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; return 0; } *childregs = *current_pt_regs(); @@ -279,24 +279,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) fpu = switch_fpu_prepare(prev_p, next_p, cpu); - /* - * Reload esp0, LDT and the page table pointer: - */ + /* Reload esp0 and ss1. */ load_sp0(tss, next); - /* - * Switch DS and ES. - * This won't pick up thread selector changes, but I guess that is ok. - */ - savesegment(es, prev->es); - if (unlikely(next->es | prev->es)) - loadsegment(es, next->es); - - savesegment(ds, prev->ds); - if (unlikely(next->ds | prev->ds)) - loadsegment(ds, next->ds); - - /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). * @@ -305,41 +290,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) savesegment(fs, fsindex); savesegment(gs, gsindex); + /* + * Load TLS before restoring any segments so that segment loads + * reference the correct GDT entries. + */ load_TLS(next, cpu); /* - * Leave lazy mode, flushing any hypercalls made here. - * This must be done before restoring TLS segments so - * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up - * to date. + * Leave lazy mode, flushing any hypercalls made here. This + * must be done after loading TLS entries in the GDT but before + * loading segments that might reference them, and and it must + * be done before math_state_restore, so the TS bit is up to + * date. */ arch_end_context_switch(next_p); + /* Switch DS and ES. + * + * Reading them only returns the selectors, but writing them (if + * nonzero) loads the full descriptor from the GDT or LDT. The + * LDT for next is loaded in switch_mm, and the GDT is loaded + * above. + * + * We therefore need to write new values to the segment + * registers on every context switch unless both the new and old + * values are zero. + * + * Note that we don't need to do anything for CS and SS, as + * those are saved and restored as part of pt_regs. + */ + savesegment(es, prev->es); + if (unlikely(next->es | prev->es)) + loadsegment(es, next->es); + + savesegment(ds, prev->ds); + if (unlikely(next->ds | prev->ds)) + loadsegment(ds, next->ds); + /* * Switch FS and GS. * - * Segment register != 0 always requires a reload. Also - * reload when it has changed. When prev process used 64bit - * base always reload to avoid an information leak. + * These are even more complicated than FS and GS: 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. + * + * 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. + * + * 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. */ if (unlikely(fsindex | next->fsindex | prev->fs)) { loadsegment(fs, next->fsindex); + /* - * Check if the user used a selector != 0; if yes - * clear 64bit base, since overloaded base is always - * mapped to the Null selector + * 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; } - /* when next process has a 64bit base use it */ if (next->fs) wrmsrl(MSR_FS_BASE, next->fs); prev->fsindex = fsindex; if (unlikely(gsindex | next->gsindex | prev->gs)) { load_gs_index(next->gsindex); + + /* This works (and fails) the same way as fsindex above. */ if (gsindex) prev->gs = 0; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 29a8120e6fe8..baa61e7370b7 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1475,15 +1475,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, force_sig_info(SIGTRAP, &info, tsk); } - -#ifdef CONFIG_X86_32 -# define IS_IA32 1 -#elif defined CONFIG_IA32_EMULATION -# define IS_IA32 is_compat_task() -#else -# define IS_IA32 0 -#endif - /* * We must return the syscall number to actually look up in the table. * This can be -1L to skip running any syscall at all. @@ -1521,7 +1512,7 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (IS_IA32) + if (is_ia32_task()) audit_syscall_entry(AUDIT_ARCH_I386, regs->orig_ax, regs->bx, regs->cx, diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 04ee1e2e4c02..52dbf1e400dc 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -529,7 +529,7 @@ static void quirk_amd_nb_node(struct pci_dev *dev) return; pci_read_config_dword(nb_ht, 0x60, &val); - node = val & 7; + node = pcibus_to_node(dev->bus) | (val & 7); /* * Some hardware may return an invalid node ID, * so check it first: diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 76fa1e9a2b39..3876c04feef9 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -36,7 +36,7 @@ void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); static const struct desc_ptr no_idt = {}; -static int reboot_mode; +static enum reboot_mode reboot_mode; enum reboot_type reboot_type = BOOT_ACPI; int reboot_force; @@ -88,11 +88,11 @@ static int __init reboot_setup(char *str) switch (*str) { case 'w': - reboot_mode = 0x1234; + reboot_mode = REBOOT_WARM; break; case 'c': - reboot_mode = 0; + reboot_mode = REBOOT_COLD; break; #ifdef CONFIG_SMP @@ -447,6 +447,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), }, }, + { /* Handle problems with rebooting on the Dell PowerEdge C6100. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, + { /* Some C6100 machines were shipped with vendor being 'Dell'. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell"), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, { } }; @@ -536,6 +552,7 @@ static void native_machine_emergency_restart(void) int i; int attempt = 0; int orig_reboot_type = reboot_type; + unsigned short mode; if (reboot_emergency) emergency_vmx_disable_all(); @@ -543,7 +560,8 @@ static void native_machine_emergency_restart(void) tboot_shutdown(TB_SHUTDOWN_REBOOT); /* Tell the BIOS if we want cold or warm reboot */ - *((unsigned short *)__va(0x472)) = reboot_mode; + mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0; + *((unsigned short *)__va(0x472)) = mode; for (;;) { /* Could also try the reset bit in the Hammer NB */ @@ -585,7 +603,7 @@ static void native_machine_emergency_restart(void) case BOOT_EFI: if (efi_enabled(EFI_RUNTIME_SERVICES)) - efi.reset_system(reboot_mode ? + efi.reset_system(reboot_mode == REBOOT_WARM ? EFI_RESET_WARM : EFI_RESET_COLD, EFI_SUCCESS, 0, NULL); diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 2a26819bb6a8..80eab01c1a68 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail) void arch_remove_reservations(struct resource *avail) { - /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */ + /* + * Trim out BIOS area (high 2MB) and E820 regions. We do not remove + * the low 1MB unconditionally, as this area is needed for some ISA + * cards requiring a memory range, e.g. the i82365 PCMCIA controller. + */ if (avail->flags & IORESOURCE_MEM) { - if (avail->start < BIOS_END) - avail->start = BIOS_END; resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END); remove_e820_regions(avail); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 56f7fcfe7fa2..a3627ade4b15 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -426,25 +426,23 @@ static void __init reserve_initrd(void) static void __init parse_setup_data(void) { struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; pa_data = boot_params.hdr.setup_data; while (pa_data) { - u32 data_len, map_len; + u32 data_len, map_len, data_type; map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK), (u64)sizeof(struct setup_data)); data = early_memremap(pa_data, map_len); data_len = data->len + sizeof(struct setup_data); - if (data_len > map_len) { - early_iounmap(data, map_len); - data = early_memremap(pa_data, data_len); - map_len = data_len; - } + data_type = data->type; + pa_next = data->next; + early_iounmap(data, map_len); - switch (data->type) { + switch (data_type) { case SETUP_E820_EXT: - parse_e820_ext(data); + parse_e820_ext(pa_data, data_len); break; case SETUP_DTB: add_dtb(pa_data); @@ -452,8 +450,7 @@ static void __init parse_setup_data(void) default: break; } - pa_data = data->next; - early_iounmap(data, map_len); + pa_data = pa_next; } } @@ -911,11 +908,11 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL32", 4)) { - set_bit(EFI_BOOT, &x86_efi_facility); + set_bit(EFI_BOOT, &efi.flags); } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL64", 4)) { - set_bit(EFI_BOOT, &x86_efi_facility); - set_bit(EFI_64BIT, &x86_efi_facility); + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); } if (efi_enabled(EFI_BOOT)) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 69562992e457..66deef41512f 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -364,7 +364,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. */ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); @@ -429,7 +429,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. If provided, use a stub already in userspace. */ @@ -496,7 +496,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); if (ksig->ka.sa.sa_flags & SA_RESTORER) { @@ -677,6 +677,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * handler too. */ regs->flags &= ~X86_EFLAGS_TF; + /* + * Ensure the signal handler starts with the new fpu state. + */ + if (used_math()) + drop_init_fpu(current); } signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index bfd348e99369..87084ab90d19 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -265,6 +265,13 @@ notrace static void __cpuinit start_secondary(void *unused) check_tsc_sync_target(); /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(); +#endif + + /* * We need to hold vector_lock so there the set of online cpus * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. @@ -1277,6 +1284,9 @@ static void remove_siblinginfo(int cpu) for_each_cpu(sibling, cpu_sibling_mask(cpu)) cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) + cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); + cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(cpu_sibling_mask(cpu)); cpumask_clear(cpu_core_mask(cpu)); c->phys_proc_id = 0; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index dbded5aedb81..30277e27431a 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin, *begin = new_begin; } } else { - *begin = TASK_UNMAPPED_BASE; + *begin = current->mm->mmap_legacy_base; *end = TASK_SIZE; } } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index f7fec09e3e3a..7fc5e843f247 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -27,6 +27,58 @@ static int get_free_idx(void) return -ESRCH; } +static bool tls_desc_okay(const struct user_desc *info) +{ + /* + * For historical reasons (i.e. no one ever documented how any + * of the segmentation APIs work), user programs can and do + * assume that a struct user_desc that's all zeros except for + * entry_number means "no segment at all". This never actually + * worked. In fact, up to Linux 3.19, a struct user_desc like + * this would create a 16-bit read-write segment with base and + * limit both equal to zero. + * + * That was close enough to "no segment at all" until we + * hardened this function to disallow 16-bit TLS segments. Fix + * it up by interpreting these zeroed segments the way that they + * were almost certainly intended to be interpreted. + * + * The correct way to ask for "no segment at all" is to specify + * a user_desc that satisfies LDT_empty. To keep everything + * working, we accept both. + * + * Note that there's a similar kludge in modify_ldt -- look at + * the distinction between modes 1 and 0x11. + */ + if (LDT_empty(info) || LDT_zero(info)) + return true; + + /* + * espfix is required for 16-bit data segments, but espfix + * only works for LDT segments. + */ + if (!info->seg_32bit) + return false; + + /* Only allow data segments in the TLS array. */ + if (info->contents > 1) + return false; + + /* + * Non-present segments with DPL 3 present an interesting attack + * surface. The kernel should handle such segments correctly, + * but TLS is very difficult to protect in a sandbox, so prevent + * such segments from being created. + * + * If userspace needs to remove a TLS entry, it can still delete + * it outright. + */ + if (info->seg_not_present) + return false; + + return true; +} + static void set_tls_desc(struct task_struct *p, int idx, const struct user_desc *info, int n) { @@ -40,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx, cpu = get_cpu(); while (n-- > 0) { - if (LDT_empty(info)) + if (LDT_empty(info) || LDT_zero(info)) desc->a = desc->b = 0; else fill_ldt(desc, info); @@ -66,6 +118,9 @@ int do_set_thread_area(struct task_struct *p, int idx, if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; + if (!tls_desc_okay(&info)) + return -EINVAL; + if (idx == -1) idx = info.entry_number; @@ -192,6 +247,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, { struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; + int i; if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || @@ -205,6 +261,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, else info = infobuf; + for (i = 0; i < count / sizeof(struct user_desc); i++) + if (!tls_desc_okay(info + i)) + return -EINVAL; + set_tls_desc(target, GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)), info, count / sizeof(struct user_desc)); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 772e2a846dec..0010ed7c3ec2 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -220,33 +220,41 @@ DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS) DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) -#ifdef CONFIG_X86_32 DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) -#endif DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) #ifdef CONFIG_X86_64 /* Runs on IST stack */ -dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) -{ - enum ctx_state prev_state; - - prev_state = exception_enter(); - if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { - preempt_conditional_sti(regs); - do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); - } - exception_exit(prev_state); -} - dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) { static const char str[] = "double fault"; struct task_struct *tsk = current; +#ifdef CONFIG_X86_ESPFIX64 + extern unsigned char native_irq_return_iret[]; + + /* + * If IRET takes a non-IST fault on the espfix64 stack, then we + * end up promoting it to a doublefault. In that case, modify + * the stack to make it look like we just entered the #GP + * handler from user space, similar to bad_iret. + */ + if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY && + regs->cs == __KERNEL_CS && + regs->ip == (unsigned long)native_irq_return_iret) + { + struct pt_regs *normal_regs = task_pt_regs(current); + + /* Fake a #GP(0) from userspace. */ + memmove(&normal_regs->ip, (void *)regs->sp, 5*8); + normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */ + regs->ip = (unsigned long)general_protection; + regs->sp = (unsigned long)&normal_regs->orig_ax; + return; + } +#endif + exception_enter(); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -354,7 +362,7 @@ exit: * for scheduling or signal handling. The actual stack switch is done in * entry.S */ -asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) +asmlinkage notrace __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) { struct pt_regs *regs = eregs; /* Did already sync */ @@ -373,6 +381,35 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) *regs = *eregs; return regs; } + +struct bad_iret_stack { + void *error_entry_ret; + struct pt_regs regs; +}; + +asmlinkage __visible notrace __kprobes +struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) +{ + /* + * This is called from entry_64.S early in handling a fault + * caused by a bad iret to user mode. To handle the fault + * correctly, we want move our stack frame to task_pt_regs + * and we want to pretend that the exception came from the + * iret target. + */ + struct bad_iret_stack *new_stack = + container_of(task_pt_regs(current), + struct bad_iret_stack, regs); + + /* Copy the IRET target to the new stack. */ + memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); + + /* Copy the remainder of the stack from the current stack. */ + memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip)); + + BUG_ON(!user_mode_vm(&new_stack->regs)); + return new_stack; +} #endif /* @@ -745,7 +782,7 @@ void __init trap_init(void) set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun); set_intr_gate(X86_TRAP_TS, &invalid_TSS); set_intr_gate(X86_TRAP_NP, &segment_not_present); - set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); + set_intr_gate(X86_TRAP_SS, stack_segment); set_intr_gate(X86_TRAP_GP, &general_protection); set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug); set_intr_gate(X86_TRAP_MF, &coprocessor_error); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 098b3cfda72e..27e3a14fc917 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -380,7 +380,7 @@ static unsigned long quick_pit_calibrate(void) goto success; } } - pr_err("Fast TSC calibration failed\n"); + pr_info("Fast TSC calibration failed\n"); return 0; success: @@ -968,14 +968,17 @@ void __init tsc_init(void) x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) + if (!cpu_has_tsc) { + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; + } tsc_khz = x86_platform.calibrate_tsc(); cpu_khz = tsc_khz; if (!tsc_khz) { mark_tsc_unstable("could not calculate TSC khz"); + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 9a907a67be8f..c52c07efe970 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -125,10 +125,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, if (!show_unhandled_signals) return; - pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", - level, current->comm, task_pid_nr(current), - message, regs->ip, regs->cs, - regs->sp, regs->ax, regs->si, regs->di); + printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + level, current->comm, task_pid_nr(current), + message, regs->ip, regs->cs, + regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index ada87a329edc..92f37e7683c5 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -268,8 +268,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) return -1; - drop_init_fpu(tsk); /* trigger finit */ - return 0; } @@ -378,7 +376,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) * thread's fpu state, reconstruct fxstate from the fsave * header. Sanitize the copied state etc. */ - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; @@ -392,16 +390,20 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) */ drop_fpu(tsk); - if (__copy_from_user(xsave, buf_fx, state_size) || + if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) || __copy_from_user(&env, buf, sizeof(env))) { + fpu_finit(fpu); err = -1; } else { sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); - set_used_math(); } - if (use_eager_fpu()) + set_used_math(); + if (use_eager_fpu()) { + preempt_disable(); math_state_restore(); + preempt_enable(); + } return err; } else { |