diff options
Diffstat (limited to 'arch/x86/kernel')
28 files changed, 513 insertions, 350 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 86281ffb96d..a531f6564ed 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -74,10 +74,6 @@ int acpi_fix_pin2_polarity __initdata; static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; #endif -#ifndef __HAVE_ARCH_CMPXCHG -#warning ACPI uses CMPXCHG, i486 and later hardware -#endif - /* -------------------------------------------------------------------------- Boot-time Configuration -------------------------------------------------------------------------- */ diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index c3fcb5de508..6a1e71bde32 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -33,31 +33,41 @@ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; /* "in progress" flag of arch_trigger_all_cpu_backtrace */ static unsigned long backtrace_flag; -void arch_trigger_all_cpu_backtrace(void) +void arch_trigger_all_cpu_backtrace(bool include_self) { int i; + int cpu = get_cpu(); - if (test_and_set_bit(0, &backtrace_flag)) + if (test_and_set_bit(0, &backtrace_flag)) { /* * If there is already a trigger_all_cpu_backtrace() in progress * (backtrace_flag == 1), don't output double cpu dump infos. */ + put_cpu(); return; + } cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); + if (!include_self) + cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); - printk(KERN_INFO "sending NMI to all CPUs:\n"); - apic->send_IPI_all(NMI_VECTOR); + if (!cpumask_empty(to_cpumask(backtrace_mask))) { + pr_info("sending NMI to %s CPUs:\n", + (include_self ? "all" : "other")); + apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR); + } /* Wait for up to 10 seconds for all CPUs to do the backtrace */ for (i = 0; i < 10 * 1000; i++) { if (cpumask_empty(to_cpumask(backtrace_mask))) break; mdelay(1); + touch_softlockup_watchdog(); } clear_bit(0, &backtrace_flag); smp_mb__after_atomic(); + put_cpu(); } static int diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index f3a1f04ed4c..58487445141 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -841,7 +841,6 @@ static int apm_do_idle(void) u32 eax; u8 ret = 0; int idled = 0; - int polling; int err = 0; if (!need_resched()) { diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ce8b8ff0e0e..bc360d3df60 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -8,6 +8,7 @@ #include <asm/processor.h> #include <asm/apic.h> #include <asm/cpu.h> +#include <asm/smp.h> #include <asm/pci-direct.h> #ifdef CONFIG_X86_64 @@ -50,7 +51,6 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) return wrmsr_safe_regs(gprs); } -#ifdef CONFIG_X86_32 /* * B step AMD K6 before B 9730xxxx have hardware bugs that can cause * misexecution of code under Linux. Owners of such processors should @@ -70,6 +70,7 @@ __asm__(".globl vide\n\t.align 4\nvide: ret"); static void init_amd_k5(struct cpuinfo_x86 *c) { +#ifdef CONFIG_X86_32 /* * General Systems BIOSen alias the cpu frequency registers * of the Elan at 0x000df000. Unfortuantly, one of the Linux @@ -83,11 +84,12 @@ static void init_amd_k5(struct cpuinfo_x86 *c) if (inl(CBAR) & CBAR_ENB) outl(0 | CBAR_KEY, CBAR); } +#endif } - static void init_amd_k6(struct cpuinfo_x86 *c) { +#ifdef CONFIG_X86_32 u32 l, h; int mbytes = get_num_physpages() >> (20-PAGE_SHIFT); @@ -176,10 +178,44 @@ static void init_amd_k6(struct cpuinfo_x86 *c) /* placeholder for any needed mods */ return; } +#endif } -static void amd_k7_smp_check(struct cpuinfo_x86 *c) +static void init_amd_k7(struct cpuinfo_x86 *c) { +#ifdef CONFIG_X86_32 + u32 l, h; + + /* + * Bit 15 of Athlon specific MSR 15, needs to be 0 + * to enable SSE on Palomino/Morgan/Barton CPU's. + * If the BIOS didn't enable it already, enable it here. + */ + if (c->x86_model >= 6 && c->x86_model <= 10) { + if (!cpu_has(c, X86_FEATURE_XMM)) { + printk(KERN_INFO "Enabling disabled K7/SSE Support.\n"); + msr_clear_bit(MSR_K7_HWCR, 15); + set_cpu_cap(c, X86_FEATURE_XMM); + } + } + + /* + * It's been determined by AMD that Athlons since model 8 stepping 1 + * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx + * As per AMD technical note 27212 0.2 + */ + if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { + rdmsr(MSR_K7_CLK_CTL, l, h); + if ((l & 0xfff00000) != 0x20000000) { + printk(KERN_INFO + "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", + l, ((l & 0x000fffff)|0x20000000)); + wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h); + } + } + + set_cpu_cap(c, X86_FEATURE_K7); + /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) return; @@ -207,7 +243,7 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c) if (((c->x86_model == 6) && (c->x86_mask >= 2)) || ((c->x86_model == 7) && (c->x86_mask >= 1)) || (c->x86_model > 7)) - if (cpu_has_mp) + if (cpu_has(c, X86_FEATURE_MP)) return; /* If we get here, not a certified SMP capable AMD system. */ @@ -219,45 +255,8 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c) WARN_ONCE(1, "WARNING: This combination of AMD" " processors is not suitable for SMP.\n"); add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE); -} - -static void init_amd_k7(struct cpuinfo_x86 *c) -{ - u32 l, h; - - /* - * Bit 15 of Athlon specific MSR 15, needs to be 0 - * to enable SSE on Palomino/Morgan/Barton CPU's. - * If the BIOS didn't enable it already, enable it here. - */ - if (c->x86_model >= 6 && c->x86_model <= 10) { - if (!cpu_has(c, X86_FEATURE_XMM)) { - printk(KERN_INFO "Enabling disabled K7/SSE Support.\n"); - msr_clear_bit(MSR_K7_HWCR, 15); - set_cpu_cap(c, X86_FEATURE_XMM); - } - } - - /* - * It's been determined by AMD that Athlons since model 8 stepping 1 - * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx - * As per AMD technical note 27212 0.2 - */ - if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { - rdmsr(MSR_K7_CLK_CTL, l, h); - if ((l & 0xfff00000) != 0x20000000) { - printk(KERN_INFO - "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", - l, ((l & 0x000fffff)|0x20000000)); - wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h); - } - } - - set_cpu_cap(c, X86_FEATURE_K7); - - amd_k7_smp_check(c); -} #endif +} #ifdef CONFIG_NUMA /* @@ -446,6 +445,26 @@ static void early_init_amd_mc(struct cpuinfo_x86 *c) static void bsp_init_amd(struct cpuinfo_x86 *c) { + +#ifdef CONFIG_X86_64 + if (c->x86 >= 0xf) { + unsigned long long tseg; + + /* + * Split up direct mapping around the TSEG SMM area. + * Don't do it for gbpages because there seems very little + * benefit in doing so. + */ + if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { + unsigned long pfn = tseg >> PAGE_SHIFT; + + printk(KERN_DEBUG "tseg: %010llx\n", tseg); + if (pfn_range_is_mapped(pfn, pfn + 1)) + set_memory_4k((unsigned long)__va(tseg), 1); + } + } +#endif + if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { if (c->x86 > 0x10 || @@ -515,101 +534,74 @@ static const int amd_erratum_383[]; static const int amd_erratum_400[]; static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); -static void init_amd(struct cpuinfo_x86 *c) +static void init_amd_k8(struct cpuinfo_x86 *c) { - u32 dummy; - unsigned long long value; - -#ifdef CONFIG_SMP - /* - * Disable TLB flush filter by setting HWCR.FFDIS on K8 - * bit 6 of msr C001_0015 - * - * Errata 63 for SH-B3 steppings - * Errata 122 for all steppings (F+ have it disabled by default) - */ - if (c->x86 == 0xf) - msr_set_bit(MSR_K7_HWCR, 6); -#endif + u32 level; + u64 value; - early_init_amd(c); + /* On C+ stepping K8 rep microcode works well for copy/memset */ + level = cpuid_eax(1); + if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58) + set_cpu_cap(c, X86_FEATURE_REP_GOOD); /* - * Bit 31 in normal CPUID used for nonstandard 3DNow ID; - * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway + * Some BIOSes incorrectly force this feature, but only K8 revision D + * (model = 0x14) and later actually support it. + * (AMD Erratum #110, docId: 25759). */ - clear_cpu_cap(c, 0*32+31); - -#ifdef CONFIG_X86_64 - /* On C+ stepping K8 rep microcode works well for copy/memset */ - if (c->x86 == 0xf) { - u32 level; - - level = cpuid_eax(1); - if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58) - set_cpu_cap(c, X86_FEATURE_REP_GOOD); - - /* - * Some BIOSes incorrectly force this feature, but only K8 - * revision D (model = 0x14) and later actually support it. - * (AMD Erratum #110, docId: 25759). - */ - if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) { - clear_cpu_cap(c, X86_FEATURE_LAHF_LM); - if (!rdmsrl_amd_safe(0xc001100d, &value)) { - value &= ~(1ULL << 32); - wrmsrl_amd_safe(0xc001100d, value); - } + if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) { + clear_cpu_cap(c, X86_FEATURE_LAHF_LM); + if (!rdmsrl_amd_safe(0xc001100d, &value)) { + value &= ~BIT_64(32); + wrmsrl_amd_safe(0xc001100d, value); } - } - if (c->x86 >= 0x10) - set_cpu_cap(c, X86_FEATURE_REP_GOOD); - /* get apicid instead of initial apic id from cpuid */ - c->apicid = hard_smp_processor_id(); -#else + if (!c->x86_model_id[0]) + strcpy(c->x86_model_id, "Hammer"); +} + +static void init_amd_gh(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_X86_64 + /* do this for boot cpu */ + if (c == &boot_cpu_data) + check_enable_amd_mmconf_dmi(); + + fam10h_check_enable_mmcfg(); +#endif /* - * FIXME: We should handle the K5 here. Set up the write - * range and also turn on MSR 83 bits 4 and 31 (write alloc, - * no bus pipeline) + * Disable GART TLB Walk Errors on Fam10h. We do this here because this + * is always needed when GART is enabled, even in a kernel which has no + * MCE support built in. BIOS should disable GartTlbWlk Errors already. + * If it doesn't, we do it here as suggested by the BKDG. + * + * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012 */ + msr_set_bit(MSR_AMD64_MCx_MASK(4), 10); - switch (c->x86) { - case 4: - init_amd_k5(c); - break; - case 5: - init_amd_k6(c); - break; - case 6: /* An Athlon/Duron */ - init_amd_k7(c); - break; - } + /* + * On family 10h BIOS may not have properly enabled WC+ support, causing + * it to be converted to CD memtype. This may result in performance + * degradation for certain nested-paging guests. Prevent this conversion + * by clearing bit 24 in MSR_AMD64_BU_CFG2. + * + * NOTE: we want to use the _safe accessors so as not to #GP kvm + * guests on older kvm hosts. + */ + msr_clear_bit(MSR_AMD64_BU_CFG2, 24); - /* K6s reports MCEs but don't actually have all the MSRs */ - if (c->x86 < 6) - clear_cpu_cap(c, X86_FEATURE_MCE); -#endif + if (cpu_has_amd_erratum(c, amd_erratum_383)) + set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); +} - /* Enable workaround for FXSAVE leak */ - if (c->x86 >= 6) - set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK); - - if (!c->x86_model_id[0]) { - switch (c->x86) { - case 0xf: - /* Should distinguish Models here, but this is only - a fallback anyways. */ - strcpy(c->x86_model_id, "Hammer"); - break; - } - } +static void init_amd_bd(struct cpuinfo_x86 *c) +{ + u64 value; /* re-enable TopologyExtensions if switched off by BIOS */ - if ((c->x86 == 0x15) && - (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) && + if ((c->x86_model >= 0x10) && (c->x86_model <= 0x1f) && !cpu_has(c, X86_FEATURE_TOPOEXT)) { if (msr_set_bit(0xc0011005, 54) > 0) { @@ -625,14 +617,60 @@ static void init_amd(struct cpuinfo_x86 *c) * The way access filter has a performance penalty on some workloads. * Disable it on the affected CPUs. */ - if ((c->x86 == 0x15) && - (c->x86_model >= 0x02) && (c->x86_model < 0x20)) { - + if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) { if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) { value |= 0x1E; wrmsrl_safe(0xc0011021, value); } } +} + +static void init_amd(struct cpuinfo_x86 *c) +{ + u32 dummy; + +#ifdef CONFIG_SMP + /* + * Disable TLB flush filter by setting HWCR.FFDIS on K8 + * bit 6 of msr C001_0015 + * + * Errata 63 for SH-B3 steppings + * Errata 122 for all steppings (F+ have it disabled by default) + */ + if (c->x86 == 0xf) + msr_set_bit(MSR_K7_HWCR, 6); +#endif + + early_init_amd(c); + + /* + * Bit 31 in normal CPUID used for nonstandard 3DNow ID; + * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway + */ + clear_cpu_cap(c, 0*32+31); + + if (c->x86 >= 0x10) + set_cpu_cap(c, X86_FEATURE_REP_GOOD); + + /* get apicid instead of initial apic id from cpuid */ + c->apicid = hard_smp_processor_id(); + + /* K6s reports MCEs but don't actually have all the MSRs */ + if (c->x86 < 6) + clear_cpu_cap(c, X86_FEATURE_MCE); + + switch (c->x86) { + case 4: init_amd_k5(c); break; + case 5: init_amd_k6(c); break; + case 6: init_amd_k7(c); break; + case 0xf: init_amd_k8(c); break; + case 0x10: init_amd_gh(c); break; + case 0x15: init_amd_bd(c); break; + } + + /* Enable workaround for FXSAVE leak */ + if (c->x86 >= 6) + set_cpu_bug(c, X86_BUG_FXSAVE_LEAK); cpu_detect_cache_sizes(c); @@ -656,33 +694,6 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); } -#ifdef CONFIG_X86_64 - if (c->x86 == 0x10) { - /* do this for boot cpu */ - if (c == &boot_cpu_data) - check_enable_amd_mmconf_dmi(); - - fam10h_check_enable_mmcfg(); - } - - if (c == &boot_cpu_data && c->x86 >= 0xf) { - unsigned long long tseg; - - /* - * Split up direct mapping around the TSEG SMM area. - * Don't do it for gbpages because there seems very little - * benefit in doing so. - */ - if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { - unsigned long pfn = tseg >> PAGE_SHIFT; - - printk(KERN_DEBUG "tseg: %010llx\n", tseg); - if (pfn_range_is_mapped(pfn, pfn + 1)) - set_memory_4k((unsigned long)__va(tseg), 1); - } - } -#endif - /* * Family 0x12 and above processors have APIC timer * running in deep C states. @@ -690,34 +701,6 @@ static void init_amd(struct cpuinfo_x86 *c) if (c->x86 > 0x11) set_cpu_cap(c, X86_FEATURE_ARAT); - if (c->x86 == 0x10) { - /* - * Disable GART TLB Walk Errors on Fam10h. We do this here - * because this is always needed when GART is enabled, even in a - * kernel which has no MCE support built in. - * BIOS should disable GartTlbWlk Errors already. If - * it doesn't, do it here as suggested by the BKDG. - * - * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012 - */ - msr_set_bit(MSR_AMD64_MCx_MASK(4), 10); - - /* - * On family 10h BIOS may not have properly enabled WC+ support, - * causing it to be converted to CD memtype. This may result in - * performance degradation for certain nested-paging guests. - * Prevent this conversion by clearing bit 24 in - * MSR_AMD64_BU_CFG2. - * - * NOTE: we want to use the _safe accessors so as not to #GP kvm - * guests on older kvm hosts. - */ - msr_clear_bit(MSR_AMD64_BU_CFG2, 24); - - if (cpu_has_amd_erratum(c, amd_erratum_383)) - set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); - } - if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_APIC_C1E); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ef1b93f18ed..188a8c5cc09 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -634,6 +634,15 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[9] = ebx; } + /* Extended state features: level 0x0000000d */ + if (c->cpuid_level >= 0x0000000d) { + u32 eax, ebx, ecx, edx; + + cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx); + + c->x86_capability[10] = eax; + } + /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); c->extended_cpuid_level = xlvl; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index a80029035bf..9483ee5b399 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -253,7 +253,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) */ if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 && (c->x86_mask < 0x6 || c->x86_mask == 0xb)) - set_cpu_cap(c, X86_FEATURE_11AP); + set_cpu_bug(c, X86_BUG_11AP); #ifdef CONFIG_X86_INTEL_USERCOPY @@ -370,6 +370,17 @@ static void init_intel(struct cpuinfo_x86 *c) */ detect_extended_topology(c); + if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) { + /* + * let's use the legacy cpuid vector 0x1 and 0x4 for topology + * detection. + */ + c->x86_max_cores = intel_num_cpu_cores(c); +#ifdef CONFIG_X86_32 + detect_ht(c); +#endif + } + l2 = init_intel_cacheinfo(c); if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); @@ -391,7 +402,7 @@ static void init_intel(struct cpuinfo_x86 *c) 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); + set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR); #ifdef CONFIG_X86_64 if (c->x86 == 15) @@ -438,17 +449,6 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_P3); #endif - if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) { - /* - * let's use the legacy cpuid vector 0x1 and 0x4 for topology - * detection. - */ - c->x86_max_cores = intel_num_cpu_cores(c); -#ifdef CONFIG_X86_32 - detect_ht(c); -#endif - } - /* Work around errata */ srat_detect_node(c); diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index a952e9c85b6..9c8f7394c61 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -730,6 +730,18 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) #endif } +#ifdef CONFIG_X86_HT + /* + * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in + * turns means that the only possibility is SMT (as indicated in + * cpuid1). Since cpuid2 doesn't specify shared caches, and we know + * that SMT shares all caches, we can unconditionally set cpu_llc_id to + * c->phys_proc_id. + */ + if (per_cpu(cpu_llc_id, cpu) == BAD_APICID) + per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; +#endif + c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d)); return l2; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index bb92f38153b..9a79c8dbd8e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -2451,6 +2451,12 @@ static __init int mcheck_init_device(void) for_each_online_cpu(i) { err = mce_device_create(i); if (err) { + /* + * Register notifier anyway (and do not unreg it) so + * that we don't leave undeleted timers, see notifier + * callback above. + */ + __register_hotcpu_notifier(&mce_cpu_notifier); cpu_notifier_register_done(); goto err_device_create; } @@ -2471,10 +2477,6 @@ static __init int mcheck_init_device(void) err_register: unregister_syscore_ops(&mce_syscore_ops); - cpu_notifier_register_begin(); - __unregister_hotcpu_notifier(&mce_cpu_notifier); - cpu_notifier_register_done(); - err_device_create: /* * We didn't keep track of which devices were created above, but diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index 2bf61650549..e2b22df964c 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -1,23 +1,25 @@ #!/bin/sh # -# Generate the x86_cap_flags[] array from include/asm/cpufeature.h +# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeature.h # IN=$1 OUT=$2 -TABS="$(printf '\t\t\t\t\t')" -trap 'rm "$OUT"' EXIT +function dump_array() +{ + ARRAY=$1 + SIZE=$2 + PFX=$3 + POSTFIX=$4 -( - echo "#ifndef _ASM_X86_CPUFEATURE_H" - echo "#include <asm/cpufeature.h>" - echo "#endif" - echo "" - echo "const char * const x86_cap_flags[NCAPINTS*32] = {" + PFX_SZ=$(echo $PFX | wc -c) + TABS="$(printf '\t\t\t\t\t')" + + echo "const char * const $ARRAY[$SIZE] = {" - # Iterate through any input lines starting with #define X86_FEATURE_ - sed -n -e 's/\t/ /g' -e 's/^ *# *define *X86_FEATURE_//p' $IN | + # Iterate through any input lines starting with #define $PFX + sed -n -e 's/\t/ /g' -e "s/^ *# *define *$PFX//p" $IN | while read i do # Name is everything up to the first whitespace @@ -31,11 +33,32 @@ trap 'rm "$OUT"' EXIT # Name is uppercase, VALUE is all lowercase VALUE="$(echo "$VALUE" | tr A-Z a-z)" - TABCOUNT=$(( ( 5*8 - 14 - $(echo "$NAME" | wc -c) ) / 8 )) - printf "\t[%s]%.*s = %s,\n" \ - "X86_FEATURE_$NAME" "$TABCOUNT" "$TABS" "$VALUE" + if [ -n "$POSTFIX" ]; then + T=$(( $PFX_SZ + $(echo $POSTFIX | wc -c) + 2 )) + TABS="$(printf '\t\t\t\t\t\t')" + TABCOUNT=$(( ( 6*8 - ($T + 1) - $(echo "$NAME" | wc -c) ) / 8 )) + printf "\t[%s - %s]%.*s = %s,\n" "$PFX$NAME" "$POSTFIX" "$TABCOUNT" "$TABS" "$VALUE" + else + TABCOUNT=$(( ( 5*8 - ($PFX_SZ + 1) - $(echo "$NAME" | wc -c) ) / 8 )) + printf "\t[%s]%.*s = %s,\n" "$PFX$NAME" "$TABCOUNT" "$TABS" "$VALUE" + fi done echo "};" +} + +trap 'rm "$OUT"' EXIT + +( + echo "#ifndef _ASM_X86_CPUFEATURE_H" + echo "#include <asm/cpufeature.h>" + echo "#endif" + echo "" + + dump_array "x86_cap_flags" "NCAPINTS*32" "X86_FEATURE_" "" + echo "" + + dump_array "x86_bug_flags" "NBUGINTS*32" "X86_BUG_" "NCAPINTS*32" + ) > $OUT trap - EXIT diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2bdfbff8a4f..2879ecdaac4 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; + /* Check if the extra msrs can be safely accessed*/ + if (!er->extra_msr_access) + return -ENXIO; reg->idx = er->idx; reg->config = event->attr.config1; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 3b2f9bdd974..8ade93111e0 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -295,14 +295,16 @@ struct extra_reg { u64 config_mask; u64 valid_mask; int idx; /* per_xxx->regs[] reg index */ + bool extra_msr_access; }; #define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ - .event = (e), \ - .msr = (ms), \ - .config_mask = (m), \ - .valid_mask = (vm), \ - .idx = EXTRA_REG_##i, \ + .event = (e), \ + .msr = (ms), \ + .config_mask = (m), \ + .valid_mask = (vm), \ + .idx = EXTRA_REG_##i, \ + .extra_msr_access = true, \ } #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c index 3bbdf4cd38b..30790d798e6 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -294,31 +294,41 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) cpu_to_node(cpu)); } -static void amd_uncore_cpu_up_prepare(unsigned int cpu) +static int amd_uncore_cpu_up_prepare(unsigned int cpu) { - struct amd_uncore *uncore; + struct amd_uncore *uncore_nb = NULL, *uncore_l2; if (amd_uncore_nb) { - uncore = amd_uncore_alloc(cpu); - uncore->cpu = cpu; - uncore->num_counters = NUM_COUNTERS_NB; - uncore->rdpmc_base = RDPMC_BASE_NB; - uncore->msr_base = MSR_F15H_NB_PERF_CTL; - uncore->active_mask = &amd_nb_active_mask; - uncore->pmu = &amd_nb_pmu; - *per_cpu_ptr(amd_uncore_nb, cpu) = uncore; + uncore_nb = amd_uncore_alloc(cpu); + if (!uncore_nb) + goto fail; + uncore_nb->cpu = cpu; + uncore_nb->num_counters = NUM_COUNTERS_NB; + uncore_nb->rdpmc_base = RDPMC_BASE_NB; + uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL; + uncore_nb->active_mask = &amd_nb_active_mask; + uncore_nb->pmu = &amd_nb_pmu; + *per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb; } if (amd_uncore_l2) { - uncore = amd_uncore_alloc(cpu); - uncore->cpu = cpu; - uncore->num_counters = NUM_COUNTERS_L2; - uncore->rdpmc_base = RDPMC_BASE_L2; - uncore->msr_base = MSR_F16H_L2I_PERF_CTL; - uncore->active_mask = &amd_l2_active_mask; - uncore->pmu = &amd_l2_pmu; - *per_cpu_ptr(amd_uncore_l2, cpu) = uncore; + uncore_l2 = amd_uncore_alloc(cpu); + if (!uncore_l2) + goto fail; + uncore_l2->cpu = cpu; + uncore_l2->num_counters = NUM_COUNTERS_L2; + uncore_l2->rdpmc_base = RDPMC_BASE_L2; + uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL; + uncore_l2->active_mask = &amd_l2_active_mask; + uncore_l2->pmu = &amd_l2_pmu; + *per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2; } + + return 0; + +fail: + kfree(uncore_nb); + return -ENOMEM; } static struct amd_uncore * @@ -441,7 +451,7 @@ static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores) if (!--uncore->refcnt) kfree(uncore); - *per_cpu_ptr(amd_uncore_nb, cpu) = NULL; + *per_cpu_ptr(uncores, cpu) = NULL; } static void amd_uncore_cpu_dead(unsigned int cpu) @@ -461,7 +471,8 @@ amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action, switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - amd_uncore_cpu_up_prepare(cpu); + if (amd_uncore_cpu_up_prepare(cpu)) + return notifier_from_errno(-ENOMEM); break; case CPU_STARTING: @@ -501,20 +512,33 @@ static void __init init_cpu_already_online(void *dummy) amd_uncore_cpu_online(cpu); } +static void cleanup_cpu_online(void *dummy) +{ + unsigned int cpu = smp_processor_id(); + + amd_uncore_cpu_dead(cpu); +} + static int __init amd_uncore_init(void) { - unsigned int cpu; + unsigned int cpu, cpu2; int ret = -ENODEV; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) - return -ENODEV; + goto fail_nodev; if (!cpu_has_topoext) - return -ENODEV; + goto fail_nodev; if (cpu_has_perfctr_nb) { amd_uncore_nb = alloc_percpu(struct amd_uncore *); - perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1); + if (!amd_uncore_nb) { + ret = -ENOMEM; + goto fail_nb; + } + ret = perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1); + if (ret) + goto fail_nb; printk(KERN_INFO "perf: AMD NB counters detected\n"); ret = 0; @@ -522,20 +546,28 @@ static int __init amd_uncore_init(void) if (cpu_has_perfctr_l2) { amd_uncore_l2 = alloc_percpu(struct amd_uncore *); - perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1); + if (!amd_uncore_l2) { + ret = -ENOMEM; + goto fail_l2; + } + ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1); + if (ret) + goto fail_l2; printk(KERN_INFO "perf: AMD L2I counters detected\n"); ret = 0; } if (ret) - return -ENODEV; + goto fail_nodev; cpu_notifier_register_begin(); /* init cpus already online before registering for hotplug notifier */ for_each_online_cpu(cpu) { - amd_uncore_cpu_up_prepare(cpu); + ret = amd_uncore_cpu_up_prepare(cpu); + if (ret) + goto fail_online; smp_call_function_single(cpu, init_cpu_already_online, NULL, 1); } @@ -543,5 +575,30 @@ static int __init amd_uncore_init(void) cpu_notifier_register_done(); return 0; + + +fail_online: + for_each_online_cpu(cpu2) { + if (cpu2 == cpu) + break; + smp_call_function_single(cpu, cleanup_cpu_online, NULL, 1); + } + cpu_notifier_register_done(); + + /* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */ + amd_uncore_nb = amd_uncore_l2 = NULL; + if (cpu_has_perfctr_l2) + perf_pmu_unregister(&amd_l2_pmu); +fail_l2: + if (cpu_has_perfctr_nb) + perf_pmu_unregister(&amd_nb_pmu); + if (amd_uncore_l2) + free_percpu(amd_uncore_l2); +fail_nb: + if (amd_uncore_nb) + free_percpu(amd_uncore_nb); + +fail_nodev: + return ret; } device_initcall(amd_uncore_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index adb02aa62af..2502d0d9d24 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1382,6 +1382,15 @@ 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)) { @@ -2173,6 +2182,41 @@ static void intel_snb_check_microcode(void) } } +/* + * Under certain circumstances, access certain MSR may cause #GP. + * The function tests if the input MSR can be safely accessed. + */ +static bool check_msr(unsigned long msr, u64 mask) +{ + u64 val_old, val_new, val_tmp; + + /* + * Read the current value, change it and read it back to see if it + * matches, this is needed to detect certain hardware emulators + * (qemu/kvm) that don't trap on the MSR access and always return 0s. + */ + if (rdmsrl_safe(msr, &val_old)) + return false; + + /* + * Only change the bits which can be updated by wrmsrl. + */ + val_tmp = val_old ^ mask; + if (wrmsrl_safe(msr, val_tmp) || + rdmsrl_safe(msr, &val_new)) + return false; + + if (val_new != val_tmp) + return false; + + /* Here it's sure that the MSR can be safely accessed. + * Restore the old value and return. + */ + wrmsrl(msr, val_old); + + return true; +} + static __init void intel_sandybridge_quirk(void) { x86_pmu.check_microcode = intel_snb_check_microcode; @@ -2262,7 +2306,8 @@ __init int intel_pmu_init(void) union cpuid10_ebx ebx; struct event_constraint *c; unsigned int unused; - int version; + struct extra_reg *er; + int version, i; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { switch (boot_cpu_data.x86) { @@ -2465,6 +2510,9 @@ __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)); @@ -2565,6 +2613,34 @@ __init int intel_pmu_init(void) } } + /* + * Access LBR MSR may cause #GP under certain circumstances. + * E.g. KVM doesn't support LBR MSR + * Check all LBT MSR here. + * Disable LBR access if any LBR MSRs can not be accessed. + */ + if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL)) + x86_pmu.lbr_nr = 0; + for (i = 0; i < x86_pmu.lbr_nr; i++) { + if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) && + check_msr(x86_pmu.lbr_to + i, 0xffffUL))) + x86_pmu.lbr_nr = 0; + } + + /* + * Access extra MSR may cause #GP under certain circumstances. + * E.g. KVM doesn't support offcore event + * Check all extra_regs here. + */ + if (x86_pmu.extra_regs) { + for (er = x86_pmu.extra_regs; er->msr; er++) { + er->extra_msr_access = check_msr(er->msr, 0x1ffUL); + /* Disable LBR select mapping */ + if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access) + x86_pmu.lbr_sel_map = NULL; + } + } + /* Support full width counters using alternative MSR range */ if (x86_pmu.intel_cap.full_width_write) { x86_pmu.max_period = x86_pmu.cntval_mask; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 980970cb744..696ade311de 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -311,9 +311,11 @@ static int alloc_bts_buffer(int cpu) if (!x86_pmu.bts) return 0; - buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node); - if (unlikely(!buffer)) + buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node); + if (unlikely(!buffer)) { + WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__); return -ENOMEM; + } max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE; thresh = max / 16; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 65bbbea38b9..cfc6f9dfcd9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -550,16 +550,16 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa), SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2), SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2), SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2), SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2), SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8), SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa), SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2), SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2), SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2), @@ -1222,6 +1222,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, SNBEP_CBO_PMON_CTL_TID_EN, 0x1), SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), @@ -1245,7 +1246,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10), SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), @@ -2946,10 +2947,7 @@ again: * extra registers. If we failed to take an extra * register, try the alternative. */ - if (idx % 2) - idx--; - else - idx++; + idx ^= 1; if (idx != reg1->idx % 6) { if (idx == 2) config1 >>= 8; diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 06fe3ed8b85..5433658e598 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -97,6 +97,14 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has(c, i) && x86_cap_flags[i] != NULL) seq_printf(m, " %s", x86_cap_flags[i]); + seq_printf(m, "\nbugs\t\t:"); + for (i = 0; i < 32*NBUGINTS; i++) { + unsigned int bug_bit = 32*NCAPINTS + i; + + if (cpu_has_bug(c, bug_bit) && x86_bug_flags[i]) + seq_printf(m, " %s", x86_bug_flags[i]); + } + seq_printf(m, "\nbogomips\t: %lu.%02lu\n", c->loops_per_jiffy/(500000/HZ), (c->loops_per_jiffy/(5000/HZ)) % 100); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index b6f794aa169..4a8013d5594 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -38,7 +38,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_XSAVEOPT, CR_EAX, 0, 0x0000000d, 1 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 }, diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index f0da82b8e63..47c410d99f5 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -423,8 +423,9 @@ 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) @@ -501,6 +502,7 @@ 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 @@ -674,8 +676,13 @@ 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 @@ -1052,9 +1059,6 @@ ENTRY(mcount) END(mcount) ENTRY(ftrace_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - pushl %eax pushl %ecx pushl %edx @@ -1086,8 +1090,6 @@ END(ftrace_caller) ENTRY(ftrace_regs_caller) pushf /* push flags before compare (in cs location) */ - cmpl $0, function_trace_stop - jne ftrace_restore_flags /* * i386 does not save SS and ESP when coming from kernel. @@ -1146,7 +1148,6 @@ GLOBAL(ftrace_regs_call) popf /* Pop flags at end (no addl to corrupt flags) */ jmp ftrace_ret -ftrace_restore_flags: popf jmp ftrace_stub #else /* ! CONFIG_DYNAMIC_FTRACE */ @@ -1155,9 +1156,6 @@ ENTRY(mcount) cmpl $__PAGE_OFFSET, %esp jb ftrace_stub /* Paging not enabled yet? */ - cmpl $0, function_trace_stop - jne ftrace_stub - cmpl $ftrace_stub, ftrace_trace_function jnz trace #ifdef CONFIG_FUNCTION_GRAPH_TRACER diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index b25ca969edd..2fac1343a90 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -207,7 +207,6 @@ ENDPROC(native_usergs_sysret64) */ .macro XCPT_FRAME start=1 offset=0 INTR_FRAME \start, RIP+\offset-ORIG_RAX - /*CFI_REL_OFFSET orig_rax, ORIG_RAX-ORIG_RAX*/ .endm /* @@ -287,21 +286,21 @@ ENDPROC(native_usergs_sysret64) ENTRY(save_paranoid) XCPT_FRAME 1 RDI+8 cld - movq_cfi rdi, RDI+8 - movq_cfi rsi, RSI+8 + movq %rdi, RDI+8(%rsp) + movq %rsi, RSI+8(%rsp) movq_cfi rdx, RDX+8 movq_cfi rcx, RCX+8 movq_cfi rax, RAX+8 - movq_cfi r8, R8+8 - movq_cfi r9, R9+8 - movq_cfi r10, R10+8 - movq_cfi r11, R11+8 + movq %r8, R8+8(%rsp) + movq %r9, R9+8(%rsp) + movq %r10, R10+8(%rsp) + movq %r11, R11+8(%rsp) movq_cfi rbx, RBX+8 - movq_cfi rbp, RBP+8 - movq_cfi r12, R12+8 - movq_cfi r13, R13+8 - movq_cfi r14, R14+8 - movq_cfi r15, R15+8 + movq %rbp, RBP+8(%rsp) + movq %r12, R12+8(%rsp) + movq %r13, R13+8(%rsp) + movq %r14, R14+8(%rsp) + movq %r15, R15+8(%rsp) movl $1,%ebx movl $MSR_GS_BASE,%ecx rdmsr @@ -830,27 +829,24 @@ restore_args: RESTORE_ARGS 1,8,1 irq_return: + INTERRUPT_RETURN + +ENTRY(native_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 irq_return_ldt + jnz native_irq_return_ldt #endif -irq_return_iret: - INTERRUPT_RETURN - _ASM_EXTABLE(irq_return_iret, bad_iret) - -#ifdef CONFIG_PARAVIRT -ENTRY(native_iret) +native_irq_return_iret: iretq - _ASM_EXTABLE(native_iret, bad_iret) -#endif + _ASM_EXTABLE(native_irq_return_iret, bad_iret) #ifdef CONFIG_X86_ESPFIX64 -irq_return_ldt: +native_irq_return_ldt: pushq_cfi %rax pushq_cfi %rdi SWAPGS @@ -872,7 +868,7 @@ irq_return_ldt: SWAPGS movq %rax,%rsp popq_cfi %rax - jmp irq_return_iret + jmp native_irq_return_iret #endif .section .fixup,"ax" @@ -956,13 +952,8 @@ __do_double_fault: cmpl $__KERNEL_CS,CS(%rdi) jne do_double_fault movq RIP(%rdi),%rax - cmpq $irq_return_iret,%rax -#ifdef CONFIG_PARAVIRT - je 1f - cmpq $native_iret,%rax -#endif + cmpq $native_irq_return_iret,%rax jne do_double_fault /* This shouldn't happen... */ -1: movq PER_CPU_VAR(kernel_stack),%rax subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */ movq %rax,RSP(%rdi) @@ -1395,21 +1386,21 @@ ENTRY(error_entry) CFI_ADJUST_CFA_OFFSET 15*8 /* oldrax contains error code */ cld - movq_cfi rdi, RDI+8 - movq_cfi rsi, RSI+8 - movq_cfi rdx, RDX+8 - movq_cfi rcx, RCX+8 - movq_cfi rax, RAX+8 - movq_cfi r8, R8+8 - movq_cfi r9, R9+8 - movq_cfi r10, R10+8 - movq_cfi r11, R11+8 + movq %rdi, RDI+8(%rsp) + movq %rsi, RSI+8(%rsp) + movq %rdx, RDX+8(%rsp) + movq %rcx, RCX+8(%rsp) + movq %rax, RAX+8(%rsp) + movq %r8, R8+8(%rsp) + movq %r9, R9+8(%rsp) + movq %r10, R10+8(%rsp) + movq %r11, R11+8(%rsp) movq_cfi rbx, RBX+8 - movq_cfi rbp, RBP+8 - movq_cfi r12, R12+8 - movq_cfi r13, R13+8 - movq_cfi r14, R14+8 - movq_cfi r15, R15+8 + movq %rbp, RBP+8(%rsp) + movq %r12, R12+8(%rsp) + movq %r13, R13+8(%rsp) + movq %r14, R14+8(%rsp) + movq %r15, R15+8(%rsp) xorl %ebx,%ebx testl $3,CS+8(%rsp) je error_kernelspace @@ -1427,8 +1418,9 @@ error_sti: * compat mode. Check for these here too. */ error_kernelspace: + CFI_REL_OFFSET rcx, RCX+8 incl %ebx - leaq irq_return_iret(%rip),%rcx + leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) je error_swapgs movl %ecx,%eax /* zero extend */ diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 6afbb16e9b7..94d857fb103 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -175,7 +175,7 @@ void init_espfix_ap(void) if (!pud_present(pud)) { pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); - paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); + paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PUD_CLONES; n++) set_pud(&pud_p[n], pud); } @@ -185,7 +185,7 @@ void init_espfix_ap(void) if (!pmd_present(pmd)) { pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); - paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT); + paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PMD_CLONES; n++) set_pmd(&pmd_p[n], pmd); } @@ -193,7 +193,6 @@ void init_espfix_ap(void) pte_p = pte_offset_kernel(&pmd, addr); stack_page = (void *)__get_free_page(GFP_KERNEL); pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); - paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index cbc4a91b131..3386dc9aa33 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -703,6 +703,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, unsigned long return_hooker = (unsigned long) &return_to_handler; + if (unlikely(ftrace_graph_is_dead())) + return; + if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 7596df66490..67e6d19ef1b 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -574,6 +574,9 @@ int kprobe_int3_handler(struct pt_regs *regs) struct kprobe *p; struct kprobe_ctlblk *kcb; + if (user_mode_vm(regs)) + return 0; + addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t)); /* * We don't want to be preempted for the entire diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index c050a015316..c73aecf10d3 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -46,10 +46,6 @@ END(function_hook) .endm ENTRY(ftrace_caller) - /* Check if tracing was disabled (quick check) */ - cmpl $0, function_trace_stop - jne ftrace_stub - ftrace_caller_setup /* regs go into 4th parameter (but make it NULL) */ movq $0, %rcx @@ -73,10 +69,6 @@ ENTRY(ftrace_regs_caller) /* Save the current flags before compare (in SS location)*/ pushfq - /* Check if tracing was disabled (quick check) */ - cmpl $0, function_trace_stop - jne ftrace_restore_flags - /* skip=8 to skip flags saved in SS */ ftrace_caller_setup 8 @@ -131,7 +123,7 @@ GLOBAL(ftrace_regs_call) popfq jmp ftrace_return -ftrace_restore_flags: + popfq jmp ftrace_stub @@ -141,9 +133,6 @@ END(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ ENTRY(function_hook) - cmpl $0, function_trace_stop - jne ftrace_stub - cmpq $ftrace_stub, ftrace_trace_function jnz trace diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 3f08f34f93e..a1da6737ba5 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/resource.c b/arch/x86/kernel/resource.c index 2a26819bb6a..80eab01c1a6 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/signal.c b/arch/x86/kernel/signal.c index a0da58db43a..2851d63c120 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -363,7 +363,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, /* Set up to return from userspace. */ restorer = current->mm->context.vdso + - selected_vdso32->sym___kernel_sigreturn; + selected_vdso32->sym___kernel_rt_sigreturn; if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; put_user_ex(restorer, &frame->pretcode); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c6eb418c562..0d0e922fafc 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -343,6 +343,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) if (poke_int3_handler(regs)) return; + prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) @@ -351,9 +352,8 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) #ifdef CONFIG_KPROBES if (kprobe_int3_handler(regs)) - return; + goto exit; #endif - prev_state = exception_enter(); if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) @@ -433,6 +433,8 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) unsigned long dr6; int si_code; + prev_state = exception_enter(); + get_debugreg(dr6, 6); /* Filter out all the reserved bits which are preset to 1 */ @@ -465,7 +467,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) if (kprobe_debug_handler(regs)) goto exit; #endif - prev_state = exception_enter(); if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code, SIGTRAP) == NOTIFY_STOP) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 57e5ce126d5..56b0c338061 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -234,9 +234,6 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) return ns; } -/* XXX surely we already have this someplace in the kernel?! */ -#define DIV_ROUND(n, d) (((n) + ((d) / 2)) / (d)) - static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) { unsigned long long tsc_now, ns_now; @@ -259,7 +256,9 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) * time function is continuous; see the comment near struct * cyc2ns_data. */ - data->cyc2ns_mul = DIV_ROUND(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, cpu_khz); + data->cyc2ns_mul = + DIV_ROUND_CLOSEST(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, + cpu_khz); data->cyc2ns_shift = CYC2NS_SCALE_FACTOR; data->cyc2ns_offset = ns_now - mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); @@ -920,9 +919,9 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); if (!(freq->flags & CPUFREQ_CONST_LOOPS)) mark_tsc_unstable("cpufreq changes"); - } - set_cyc2ns_scale(tsc_khz, freq->cpu); + set_cyc2ns_scale(tsc_khz, freq->cpu); + } return 0; } |