diff options
Diffstat (limited to 'arch/x86/kernel')
57 files changed, 1302 insertions, 797 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 91ce48f..34e923a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -9,7 +9,6 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities CFLAGS_REMOVE_tsc.o = -pg -CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg CFLAGS_REMOVE_pvclock.o = -pg CFLAGS_REMOVE_kvmclock.o = -pg @@ -62,6 +61,7 @@ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o +obj-$(CONFIG_X86_TSC) += trace_clock.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4b23aa1..cfc755d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -573,6 +573,12 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) return irq; } +EXPORT_SYMBOL_GPL(acpi_register_gsi); + +void acpi_unregister_gsi(u32 gsi) +{ +} +EXPORT_SYMBOL_GPL(acpi_unregister_gsi); void __init acpi_set_irq_model_pic(void) { @@ -1699,3 +1705,9 @@ int __acpi_release_global_lock(unsigned int *lock) } while (unlikely (val != old)); return old & 0x1; } + +void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) +{ + e820_add_region(addr, size, E820_ACPI); + update_e820(); +} diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 11676cf..d5e0d71 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -101,6 +101,8 @@ static int __init acpi_sleep_setup(char *str) #endif if (strncmp(str, "nonvs", 5) == 0) acpi_nvs_nosave(); + if (strncmp(str, "nonvs_s3", 8) == 0) + acpi_nvs_nosave_s3(); if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); str = strchr(str, ','); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b17416e..b994cc8 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -90,21 +90,6 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid); */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID); -/* - * Knob to control our willingness to enable the local APIC. - * - * +1=force-enable - */ -static int force_enable_local_apic __initdata; -/* - * APIC command line parameters - */ -static int __init parse_lapic(char *arg) -{ - force_enable_local_apic = 1; - return 0; -} -early_param("lapic", parse_lapic); /* Local APIC was disabled by the BIOS and enabled by the kernel */ static int enabled_via_apicbase; @@ -133,6 +118,25 @@ static inline void imcr_apic_to_pic(void) } #endif +/* + * Knob to control our willingness to enable the local APIC. + * + * +1=force-enable + */ +static int force_enable_local_apic __initdata; +/* + * APIC command line parameters + */ +static int __init parse_lapic(char *arg) +{ + if (config_enabled(CONFIG_X86_32) && !arg) + force_enable_local_apic = 1; + else if (!strncmp(arg, "notscdeadline", 13)) + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); + return 0; +} +early_param("lapic", parse_lapic); + #ifdef CONFIG_X86_64 static int apic_calibrate_pmtmr __initdata; static __init int setup_apicpmtimer(char *s) @@ -315,6 +319,7 @@ int lapic_get_maxlvt(void) /* Clock divisor */ #define APIC_DIVISOR 16 +#define TSC_DIVISOR 32 /* * This function sets up the local APIC timer, with a timeout of @@ -333,6 +338,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) lvtt_value = LOCAL_TIMER_VECTOR; if (!oneshot) lvtt_value |= APIC_LVT_TIMER_PERIODIC; + else if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + lvtt_value |= APIC_LVT_TIMER_TSCDEADLINE; + if (!lapic_is_integrated()) lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV); @@ -341,6 +349,11 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) apic_write(APIC_LVTT, lvtt_value); + if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) { + printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); + return; + } + /* * Divide PICLK by 16 */ @@ -453,6 +466,16 @@ static int lapic_next_event(unsigned long delta, return 0; } +static int lapic_next_deadline(unsigned long delta, + struct clock_event_device *evt) +{ + u64 tsc; + + rdtscll(tsc); + wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR)); + return 0; +} + /* * Setup the lapic timer in periodic or oneshot mode */ @@ -533,7 +556,15 @@ static void __cpuinit setup_APIC_timer(void) memcpy(levt, &lapic_clockevent, sizeof(*levt)); levt->cpumask = cpumask_of(smp_processor_id()); - clockevents_register_device(levt); + if (this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) { + levt->features &= ~(CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_DUMMY); + levt->set_next_event = lapic_next_deadline; + clockevents_config_and_register(levt, + (tsc_khz / TSC_DIVISOR) * 1000, + 0xF, ~0UL); + } else + clockevents_register_device(levt); } /* @@ -661,7 +692,9 @@ static int __init calibrate_APIC_clock(void) * in the clockevent structure and return. */ - if (lapic_timer_frequency) { + if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) { + return 0; + } else if (lapic_timer_frequency) { apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n", lapic_timer_frequency); lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR, @@ -674,6 +707,9 @@ static int __init calibrate_APIC_clock(void) return 0; } + apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" + "calibrating APIC timer ...\n"); + local_irq_disable(); /* Replace the global interrupt handler */ @@ -811,9 +847,6 @@ void __init setup_boot_APIC_clock(void) return; } - apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" - "calibrating APIC timer ...\n"); - if (calibrate_APIC_clock()) { /* No broadcast on UP ! */ if (num_possible_cpus() > 1) diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index a65829a..9c2aa89 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -22,6 +22,7 @@ #include <linux/hardirq.h> #include <linux/delay.h> +#include <asm/numachip/numachip.h> #include <asm/numachip/numachip_csr.h> #include <asm/smp.h> #include <asm/apic.h> @@ -179,6 +180,7 @@ static int __init numachip_system_init(void) return 0; x86_cpuinit.fixup_cpu_id = fixup_cpu_id; + x86_init.pci.arch_init = pci_numachip_init; map_csrs(); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 1817fa9..b739d39 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -234,11 +234,11 @@ int __init arch_early_irq_init(void) zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node); /* * For legacy IRQ's, start with assigning irq0 to irq15 to - * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0. + * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's. */ if (i < legacy_pic->nr_legacy_irqs) { cfg[i].vector = IRQ0_VECTOR + i; - cpumask_set_cpu(0, cfg[i].domain); + cpumask_setall(cfg[i].domain); } } @@ -1141,7 +1141,8 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) * allocation for the members that are not used anymore. */ cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); - cfg->move_in_progress = 1; + cfg->move_in_progress = + cpumask_intersects(cfg->old_domain, cpu_online_mask); cpumask_and(cfg->domain, cfg->domain, tmp_mask); break; } @@ -1172,8 +1173,9 @@ next: current_vector = vector; current_offset = offset; if (cfg->vector) { - cfg->move_in_progress = 1; cpumask_copy(cfg->old_domain, cfg->domain); + cfg->move_in_progress = + cpumask_intersects(cfg->old_domain, cpu_online_mask); } for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) per_cpu(vector_irq, new_cpu)[vector] = irq; @@ -1241,12 +1243,6 @@ void __setup_vector_irq(int cpu) cfg = irq_get_chip_data(irq); if (!cfg) continue; - /* - * If it is a legacy IRQ handled by the legacy PIC, this cpu - * will be part of the irq_cfg's domain. - */ - if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq)) - cpumask_set_cpu(cpu, cfg->domain); if (!cpumask_test_cpu(cpu, cfg->domain)) continue; @@ -1356,16 +1352,6 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, if (!IO_APIC_IRQ(irq)) return; - /* - * For legacy irqs, cfg->domain starts with cpu 0. Now that IO-APIC - * can handle this irq and the apic driver is finialized at this point, - * update the cfg->domain. - */ - if (irq < legacy_pic->nr_legacy_irqs && - cpumask_equal(cfg->domain, cpumask_of(0))) - apic->vector_allocation_domain(0, cfg->domain, - apic->target_cpus()); - if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; @@ -2199,9 +2185,11 @@ static int ioapic_retrigger_irq(struct irq_data *data) { struct irq_cfg *cfg = data->chip_data; unsigned long flags; + int cpu; raw_spin_lock_irqsave(&vector_lock, flags); - apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector); + cpu = cpumask_first_and(cfg->domain, cpu_online_mask); + apic->send_IPI_mask(cpumask_of(cpu), cfg->vector); raw_spin_unlock_irqrestore(&vector_lock, flags); return 1; @@ -3317,8 +3305,9 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id) int ret; if (irq_remapping_enabled) { - if (!setup_hpet_msi_remapped(irq, id)) - return -1; + ret = setup_hpet_msi_remapped(irq, id); + if (ret) + return ret; } ret = msi_compose_msg(NULL, irq, &msg, id); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 913f94f..eafb084 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -303,7 +303,7 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c) int cpu = smp_processor_id(); /* get information required for multi-node processors */ - if (cpu_has(c, X86_FEATURE_TOPOEXT)) { + if (cpu_has_topoext) { u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); @@ -630,6 +630,20 @@ static void __cpuinit 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)) { + u64 val; + + if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) { + val |= 0x1E; + wrmsrl_safe(0xc0011021, val); + } + } + cpu_detect_cache_sizes(c); /* Multi core CPU? */ @@ -642,12 +656,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) detect_ht(c); #endif - if (c->extended_cpuid_level >= 0x80000006) { - if (cpuid_edx(0x80000006) & 0xf000) - num_cache_leaves = 4; - else - num_cache_leaves = 3; - } + init_amd_cacheinfo(c); if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); @@ -736,9 +745,6 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) { - if (!cpu_has_invlpg) - return; - tlb_flushall_shift = 5; if (c->x86 <= 0x11) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d0e910d..92dfec9 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -107,53 +107,17 @@ static void __init check_hlt(void) } /* - * Most 386 processors have a bug where a POPAD can lock the - * machine even from user space. - */ - -static void __init check_popad(void) -{ -#ifndef CONFIG_X86_POPAD_OK - int res, inp = (int) &res; - - pr_info("Checking for popad bug... "); - __asm__ __volatile__( - "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx " - : "=&a" (res) - : "d" (inp) - : "ecx", "edi"); - /* - * If this fails, it means that any user program may lock the - * CPU hard. Too bad. - */ - if (res != 12345678) - pr_cont("Buggy\n"); - else - pr_cont("OK\n"); -#endif -} - -/* * Check whether we are able to run this kernel safely on SMP. * - * - In order to run on a i386, we need to be compiled for i386 - * (for due to lack of "invlpg" and working WP on a i386) + * - i386 is no longer supported. * - In order to run on anything without a TSC, we need to be * compiled for a i486. */ static void __init check_config(void) { -/* - * We'd better not be a i386 if we're configured to use some - * i486+ only features! (WP works in supervisor mode and the - * new "invlpg" and "bswap" instructions) - */ -#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || \ - defined(CONFIG_X86_BSWAP) - if (boot_cpu_data.x86 == 3) + if (boot_cpu_data.x86 < 4) panic("Kernel requires i486+ for 'invlpg' and other features"); -#endif } @@ -166,7 +130,6 @@ void __init check_bugs(void) #endif check_config(); check_hlt(); - check_popad(); init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 7505f7b..9c3ab43 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1173,15 +1173,6 @@ DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); #endif -/* Make sure %fs and %gs are initialized properly in idle threads */ -struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs) -{ - memset(regs, 0, sizeof(struct pt_regs)); - regs->fs = __KERNEL_PERCPU; - regs->gs = __KERNEL_STACK_CANARY; - - return regs; -} #endif /* CONFIG_X86_64 */ /* @@ -1237,7 +1228,7 @@ void __cpuinit cpu_init(void) oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA - if (cpu != 0 && this_cpu_read(numa_node) == 0 && + if (this_cpu_read(numa_node) == 0 && early_cpu_to_node(cpu) != NUMA_NO_NODE) set_numa_node(early_cpu_to_node(cpu)); #endif @@ -1269,8 +1260,7 @@ void __cpuinit cpu_init(void) barrier(); x86_configure_nx(); - if (cpu != 0) - enable_x2apic(); + enable_x2apic(); /* * set up and load the per-CPU TSS diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 3b547cc..a24c462 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -611,10 +611,6 @@ static void __cpuinit intel_tlb_lookup(const unsigned char desc) static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) { - if (!cpu_has_invlpg) { - tlb_flushall_shift = -1; - return; - } switch ((c->x86 << 8) + c->x86_model) { case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 93c5451..fe9edec 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -538,7 +538,11 @@ __cpuinit cpuid4_cache_lookup_regs(int index, unsigned edx; if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - amd_cpuid4(index, &eax, &ebx, &ecx); + if (cpu_has_topoext) + cpuid_count(0x8000001d, index, &eax.full, + &ebx.full, &ecx.full, &edx); + else + amd_cpuid4(index, &eax, &ebx, &ecx); amd_init_l3_cache(this_leaf, index); } else { cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx); @@ -557,21 +561,39 @@ __cpuinit cpuid4_cache_lookup_regs(int index, return 0; } -static int __cpuinit find_num_cache_leaves(void) +static int __cpuinit find_num_cache_leaves(struct cpuinfo_x86 *c) { - unsigned int eax, ebx, ecx, edx; + unsigned int eax, ebx, ecx, edx, op; union _cpuid4_leaf_eax cache_eax; int i = -1; + if (c->x86_vendor == X86_VENDOR_AMD) + op = 0x8000001d; + else + op = 4; + do { ++i; - /* Do cpuid(4) loop to find out num_cache_leaves */ - cpuid_count(4, i, &eax, &ebx, &ecx, &edx); + /* Do cpuid(op) loop to find out num_cache_leaves */ + cpuid_count(op, i, &eax, &ebx, &ecx, &edx); cache_eax.full = eax; } while (cache_eax.split.type != CACHE_TYPE_NULL); return i; } +void __cpuinit init_amd_cacheinfo(struct cpuinfo_x86 *c) +{ + + if (cpu_has_topoext) { + num_cache_leaves = find_num_cache_leaves(c); + } else if (c->extended_cpuid_level >= 0x80000006) { + if (cpuid_edx(0x80000006) & 0xf000) + num_cache_leaves = 4; + else + num_cache_leaves = 3; + } +} + unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) { /* Cache sizes */ @@ -588,7 +610,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) if (is_initialized == 0) { /* Init num_cache_leaves from boot CPU */ - num_cache_leaves = find_num_cache_leaves(); + num_cache_leaves = find_num_cache_leaves(c); is_initialized++; } @@ -728,37 +750,50 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info); static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) { struct _cpuid4_info *this_leaf; - int ret, i, sibling; - struct cpuinfo_x86 *c = &cpu_data(cpu); + int i, sibling; - ret = 0; - if (index == 3) { - ret = 1; - for_each_cpu(i, cpu_llc_shared_mask(cpu)) { + if (cpu_has_topoext) { + unsigned int apicid, nshared, first, last; + + if (!per_cpu(ici_cpuid4_info, cpu)) + return 0; + + this_leaf = CPUID4_INFO_IDX(cpu, index); + nshared = this_leaf->base.eax.split.num_threads_sharing + 1; + apicid = cpu_data(cpu).apicid; + first = apicid - (apicid % nshared); + last = first + nshared - 1; + + for_each_online_cpu(i) { + apicid = cpu_data(i).apicid; + if ((apicid < first) || (apicid > last)) + continue; if (!per_cpu(ici_cpuid4_info, i)) continue; this_leaf = CPUID4_INFO_IDX(i, index); - for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { - if (!cpu_online(sibling)) + + for_each_online_cpu(sibling) { + apicid = cpu_data(sibling).apicid; + if ((apicid < first) || (apicid > last)) continue; set_bit(sibling, this_leaf->shared_cpu_map); } } - } else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) { - ret = 1; - for_each_cpu(i, cpu_sibling_mask(cpu)) { + } else if (index == 3) { + for_each_cpu(i, cpu_llc_shared_mask(cpu)) { if (!per_cpu(ici_cpuid4_info, i)) continue; this_leaf = CPUID4_INFO_IDX(i, index); - for_each_cpu(sibling, cpu_sibling_mask(cpu)) { + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { if (!cpu_online(sibling)) continue; set_bit(sibling, this_leaf->shared_cpu_map); } } - } + } else + return 0; - return ret; + return 1; } static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 6a05c1d..5b7d4fa 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -24,8 +24,6 @@ struct mce_bank { int mce_severity(struct mce *a, int tolerant, char **msg); struct dentry *mce_get_debugfs_dir(void); -extern int mce_ser; - extern struct mce_bank *mce_banks; #ifdef CONFIG_X86_MCE_INTEL diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 1301762..beb1f16 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -193,9 +193,9 @@ int mce_severity(struct mce *m, int tolerant, char **msg) continue; if ((m->mcgstatus & s->mcgmask) != s->mcgres) continue; - if (s->ser == SER_REQUIRED && !mce_ser) + if (s->ser == SER_REQUIRED && !mca_cfg.ser) continue; - if (s->ser == NO_SER && mce_ser) + if (s->ser == NO_SER && mca_cfg.ser) continue; if (s->context && ctx != s->context) continue; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 46cbf86..80dbda8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -58,34 +58,26 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define CREATE_TRACE_POINTS #include <trace/events/mce.h> -int mce_disabled __read_mostly; - #define SPINUNIT 100 /* 100ns */ atomic_t mce_entry; DEFINE_PER_CPU(unsigned, mce_exception_count); -/* - * Tolerant levels: - * 0: always panic on uncorrected errors, log corrected errors - * 1: panic or SIGBUS on uncorrected errors, log corrected errors - * 2: SIGBUS or log uncorrected errors (if possible), log corrected errors - * 3: never panic or SIGBUS, log all errors (for testing only) - */ -static int tolerant __read_mostly = 1; -static int banks __read_mostly; -static int rip_msr __read_mostly; -static int mce_bootlog __read_mostly = -1; -static int monarch_timeout __read_mostly = -1; -static int mce_panic_timeout __read_mostly; -static int mce_dont_log_ce __read_mostly; -int mce_cmci_disabled __read_mostly; -int mce_ignore_ce __read_mostly; -int mce_ser __read_mostly; -int mce_bios_cmci_threshold __read_mostly; - -struct mce_bank *mce_banks __read_mostly; +struct mce_bank *mce_banks __read_mostly; + +struct mca_config mca_cfg __read_mostly = { + .bootlog = -1, + /* + * Tolerant levels: + * 0: always panic on uncorrected errors, log corrected errors + * 1: panic or SIGBUS on uncorrected errors, log corrected errors + * 2: SIGBUS or log uncorrected errors (if possible), log corr. errors + * 3: never panic or SIGBUS, log all errors (for testing only) + */ + .tolerant = 1, + .monarch_timeout = -1 +}; /* User mode helper program triggered by machine check event */ static unsigned long mce_need_notify; @@ -302,7 +294,7 @@ static void wait_for_panic(void) while (timeout-- > 0) udelay(1); if (panic_timeout == 0) - panic_timeout = mce_panic_timeout; + panic_timeout = mca_cfg.panic_timeout; panic("Panicing machine check CPU died"); } @@ -360,7 +352,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp) pr_emerg(HW_ERR "Machine check: %s\n", exp); if (!fake_panic) { if (panic_timeout == 0) - panic_timeout = mce_panic_timeout; + panic_timeout = mca_cfg.panic_timeout; panic(msg); } else pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); @@ -372,7 +364,7 @@ static int msr_to_offset(u32 msr) { unsigned bank = __this_cpu_read(injectm.bank); - if (msr == rip_msr) + if (msr == mca_cfg.rip_msr) return offsetof(struct mce, ip); if (msr == MSR_IA32_MCx_STATUS(bank)) return offsetof(struct mce, status); @@ -451,8 +443,8 @@ static inline void mce_gather_info(struct mce *m, struct pt_regs *regs) m->cs |= 3; } /* Use accurate RIP reporting if available. */ - if (rip_msr) - m->ip = mce_rdmsrl(rip_msr); + if (mca_cfg.rip_msr) + m->ip = mce_rdmsrl(mca_cfg.rip_msr); } } @@ -513,7 +505,7 @@ static int mce_ring_add(unsigned long pfn) int mce_available(struct cpuinfo_x86 *c) { - if (mce_disabled) + if (mca_cfg.disabled) return 0; return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA); } @@ -565,7 +557,7 @@ static void mce_read_aux(struct mce *m, int i) /* * Mask the reported address by the reported granularity. */ - if (mce_ser && (m->status & MCI_STATUS_MISCV)) { + if (mca_cfg.ser && (m->status & MCI_STATUS_MISCV)) { u8 shift = MCI_MISC_ADDR_LSB(m->misc); m->addr >>= shift; m->addr <<= shift; @@ -599,7 +591,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_gather_info(&m, NULL); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) continue; @@ -620,7 +612,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * TBD do the same check for MCI_STATUS_EN here? */ if (!(flags & MCP_UC) && - (m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC))) + (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; mce_read_aux(&m, i); @@ -631,7 +623,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) mce_log(&m); /* @@ -658,14 +650,14 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, { int i, ret = 0; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); if (m->status & MCI_STATUS_VAL) { __set_bit(i, validp); if (quirk_no_way_out) quirk_no_way_out(i, m, regs); } - if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY) + if (mce_severity(m, mca_cfg.tolerant, msg) >= MCE_PANIC_SEVERITY) ret = 1; } return ret; @@ -696,11 +688,11 @@ static int mce_timed_out(u64 *t) rmb(); if (atomic_read(&mce_paniced)) wait_for_panic(); - if (!monarch_timeout) + if (!mca_cfg.monarch_timeout) goto out; if ((s64)*t < SPINUNIT) { /* CHECKME: Make panic default for 1 too? */ - if (tolerant < 1) + if (mca_cfg.tolerant < 1) mce_panic("Timeout synchronizing machine check over CPUs", NULL, NULL); cpu_missing = 1; @@ -750,7 +742,8 @@ static void mce_reign(void) * Grade the severity of the errors of all the CPUs. */ for_each_possible_cpu(cpu) { - int severity = mce_severity(&per_cpu(mces_seen, cpu), tolerant, + int severity = mce_severity(&per_cpu(mces_seen, cpu), + mca_cfg.tolerant, &nmsg); if (severity > global_worst) { msg = nmsg; @@ -764,7 +757,7 @@ static void mce_reign(void) * This dumps all the mces in the log buffer and stops the * other CPUs. */ - if (m && global_worst >= MCE_PANIC_SEVERITY && tolerant < 3) + if (m && global_worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) mce_panic("Fatal Machine check", m, msg); /* @@ -777,7 +770,7 @@ static void mce_reign(void) * No machine check event found. Must be some external * source or one CPU is hung. Panic. */ - if (global_worst <= MCE_KEEP_SEVERITY && tolerant < 3) + if (global_worst <= MCE_KEEP_SEVERITY && mca_cfg.tolerant < 3) mce_panic("Machine check from unknown source", NULL, NULL); /* @@ -801,7 +794,7 @@ static int mce_start(int *no_way_out) { int order; int cpus = num_online_cpus(); - u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC; + u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC; if (!timeout) return -1; @@ -865,7 +858,7 @@ static int mce_start(int *no_way_out) static int mce_end(int order) { int ret = -1; - u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC; + u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC; if (!timeout) goto reset; @@ -946,7 +939,7 @@ static void mce_clear_state(unsigned long *toclear) { int i; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { if (test_bit(i, toclear)) mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0); } @@ -1011,6 +1004,7 @@ static void mce_clear_info(struct mce_info *mi) */ void do_machine_check(struct pt_regs *regs, long error_code) { + struct mca_config *cfg = &mca_cfg; struct mce m, *final; int i; int worst = 0; @@ -1022,7 +1016,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) int order; /* * If no_way_out gets set, there is no safe way to recover from this - * MCE. If tolerant is cranked up, we'll try anyway. + * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. */ int no_way_out = 0; /* @@ -1038,7 +1032,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) this_cpu_inc(mce_exception_count); - if (!banks) + if (!cfg->banks) goto out; mce_gather_info(&m, regs); @@ -1065,7 +1059,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * because the first one to see it will clear it. */ order = mce_start(&no_way_out); - for (i = 0; i < banks; i++) { + for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); if (!test_bit(i, valid_banks)) continue; @@ -1084,7 +1078,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * Non uncorrected or non signaled errors are handled by * machine_check_poll. Leave them alone, unless this panics. */ - if (!(m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC)) && + if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && !no_way_out) continue; @@ -1093,7 +1087,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) */ add_taint(TAINT_MACHINE_CHECK); - severity = mce_severity(&m, tolerant, NULL); + severity = mce_severity(&m, cfg->tolerant, NULL); /* * When machine check was for corrected handler don't touch, @@ -1117,7 +1111,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * When the ring overflows we just ignore the AO error. * RED-PEN add some logging mechanism when * usable_address or mce_add_ring fails. - * RED-PEN don't ignore overflow for tolerant == 0 + * RED-PEN don't ignore overflow for mca_cfg.tolerant == 0 */ if (severity == MCE_AO_SEVERITY && mce_usable_address(&m)) mce_ring_add(m.addr >> PAGE_SHIFT); @@ -1149,7 +1143,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * issues we try to recover, or limit damage to the current * process. */ - if (tolerant < 3) { + if (cfg->tolerant < 3) { if (no_way_out) mce_panic("Fatal machine check on current CPU", &m, msg); if (worst == MCE_AR_SEVERITY) { @@ -1377,11 +1371,13 @@ EXPORT_SYMBOL_GPL(mce_notify_irq); static int __cpuinit __mcheck_cpu_mce_banks_init(void) { int i; + u8 num_banks = mca_cfg.banks; - mce_banks = kzalloc(banks * sizeof(struct mce_bank), GFP_KERNEL); + mce_banks = kzalloc(num_banks * sizeof(struct mce_bank), GFP_KERNEL); if (!mce_banks) return -ENOMEM; - for (i = 0; i < banks; i++) { + + for (i = 0; i < num_banks; i++) { struct mce_bank *b = &mce_banks[i]; b->ctl = -1ULL; @@ -1401,7 +1397,7 @@ static int __cpuinit __mcheck_cpu_cap_init(void) rdmsrl(MSR_IA32_MCG_CAP, cap); b = cap & MCG_BANKCNT_MASK; - if (!banks) + if (!mca_cfg.banks) pr_info("CPU supports %d MCE banks\n", b); if (b > MAX_NR_BANKS) { @@ -1411,8 +1407,9 @@ static int __cpuinit __mcheck_cpu_cap_init(void) } /* Don't support asymmetric configurations today */ - WARN_ON(banks != 0 && b != banks); - banks = b; + WARN_ON(mca_cfg.banks != 0 && b != mca_cfg.banks); + mca_cfg.banks = b; + if (!mce_banks) { int err = __mcheck_cpu_mce_banks_init(); @@ -1422,25 +1419,29 @@ static int __cpuinit __mcheck_cpu_cap_init(void) /* Use accurate RIP reporting if available. */ if ((cap & MCG_EXT_P) && MCG_EXT_CNT(cap) >= 9) - rip_msr = MSR_IA32_MCG_EIP; + mca_cfg.rip_msr = MSR_IA32_MCG_EIP; if (cap & MCG_SER_P) - mce_ser = 1; + mca_cfg.ser = true; return 0; } static void __mcheck_cpu_init_generic(void) { + enum mcp_flags m_fl = 0; mce_banks_t all_banks; u64 cap; int i; + if (!mca_cfg.bootlog) + m_fl = MCP_DONTLOG; + /* * Log the machine checks left over from the previous reset. */ bitmap_fill(all_banks, MAX_NR_BANKS); - machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks); + machine_check_poll(MCP_UC | m_fl, &all_banks); set_in_cr4(X86_CR4_MCE); @@ -1448,7 +1449,7 @@ static void __mcheck_cpu_init_generic(void) if (cap & MCG_CTL_P) wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (!b->init) @@ -1489,6 +1490,8 @@ static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) /* Add per CPU specific workarounds here */ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { + struct mca_config *cfg = &mca_cfg; + if (c->x86_vendor == X86_VENDOR_UNKNOWN) { pr_info("unknown CPU type - not enabling MCE support\n"); return -EOPNOTSUPP; @@ -1496,7 +1499,7 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) /* This should be disabled by the BIOS, but isn't always */ if (c->x86_vendor == X86_VENDOR_AMD) { - if (c->x86 == 15 && banks > 4) { + if (c->x86 == 15 && cfg->banks > 4) { /* * disable GART TBL walk error reporting, which * trips off incorrectly with the IOMMU & 3ware @@ -1504,18 +1507,18 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ clear_bit(10, (unsigned long *)&mce_banks[4].ctl); } - if (c->x86 <= 17 && mce_bootlog < 0) { + if (c->x86 <= 17 && cfg->bootlog < 0) { /* * Lots of broken BIOS around that don't clear them * by default and leave crap in there. Don't log: */ - mce_bootlog = 0; + cfg->bootlog = 0; } /* * Various K7s with broken bank 0 around. Always disable * by default. */ - if (c->x86 == 6 && banks > 0) + if (c->x86 == 6 && cfg->banks > 0) mce_banks[0].ctl = 0; /* @@ -1566,7 +1569,7 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) * valid event later, merely don't write CTL0. */ - if (c->x86 == 6 && c->x86_model < 0x1A && banks > 0) + if (c->x86 == 6 && c->x86_model < 0x1A && cfg->banks > 0) mce_banks[0].init = 0; /* @@ -1574,23 +1577,23 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) * synchronization with a one second timeout. */ if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) && - monarch_timeout < 0) - monarch_timeout = USEC_PER_SEC; + cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; /* * There are also broken BIOSes on some Pentium M and * earlier systems: */ - if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0) - mce_bootlog = 0; + if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0) + cfg->bootlog = 0; if (c->x86 == 6 && c->x86_model == 45) quirk_no_way_out = quirk_sandybridge_ifu; } - if (monarch_timeout < 0) - monarch_timeout = 0; - if (mce_bootlog != 0) - mce_panic_timeout = 30; + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = 0; + if (cfg->bootlog != 0) + cfg->panic_timeout = 30; return 0; } @@ -1635,7 +1638,7 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t) __this_cpu_write(mce_next_interval, iv); - if (mce_ignore_ce || !iv) + if (mca_cfg.ignore_ce || !iv) return; t->expires = round_jiffies(jiffies + iv); @@ -1668,7 +1671,7 @@ void (*machine_check_vector)(struct pt_regs *, long error_code) = */ void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c) { - if (mce_disabled) + if (mca_cfg.disabled) return; if (__mcheck_cpu_ancient_init(c)) @@ -1678,7 +1681,7 @@ void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c) return; if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) { - mce_disabled = 1; + mca_cfg.disabled = true; return; } @@ -1951,6 +1954,8 @@ static struct miscdevice mce_chrdev_device = { */ static int __init mcheck_enable(char *str) { + struct mca_config *cfg = &mca_cfg; + if (*str == 0) { enable_p5_mce(); return 1; @@ -1958,22 +1963,22 @@ static int __init mcheck_enable(char *str) if (*str == '=') str++; if (!strcmp(str, "off")) - mce_disabled = 1; + cfg->disabled = true; else if (!strcmp(str, "no_cmci")) - mce_cmci_disabled = 1; + cfg->cmci_disabled = true; else if (!strcmp(str, "dont_log_ce")) - mce_dont_log_ce = 1; + cfg->dont_log_ce = true; else if (!strcmp(str, "ignore_ce")) - mce_ignore_ce = 1; + cfg->ignore_ce = true; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) - mce_bootlog = (str[0] == 'b'); + cfg->bootlog = (str[0] == 'b'); else if (!strcmp(str, "bios_cmci_threshold")) - mce_bios_cmci_threshold = 1; + cfg->bios_cmci_threshold = true; else if (isdigit(str[0])) { - get_option(&str, &tolerant); + get_option(&str, &(cfg->tolerant)); if (*str == ',') { ++str; - get_option(&str, &monarch_timeout); + get_option(&str, &(cfg->monarch_timeout)); } } else { pr_info("mce argument %s ignored. Please use /sys\n", str); @@ -2002,7 +2007,7 @@ static int mce_disable_error_reporting(void) { int i; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (b->init) @@ -2142,15 +2147,15 @@ static ssize_t set_ignore_ce(struct device *s, if (strict_strtoull(buf, 0, &new) < 0) return -EINVAL; - if (mce_ignore_ce ^ !!new) { + if (mca_cfg.ignore_ce ^ !!new) { if (new) { /* disable ce features */ mce_timer_delete_all(); on_each_cpu(mce_disable_cmci, NULL, 1); - mce_ignore_ce = 1; + mca_cfg.ignore_ce = true; } else { /* enable ce features */ - mce_ignore_ce = 0; + mca_cfg.ignore_ce = false; on_each_cpu(mce_enable_ce, (void *)1, 1); } } @@ -2166,14 +2171,14 @@ static ssize_t set_cmci_disabled(struct device *s, if (strict_strtoull(buf, 0, &new) < 0) return -EINVAL; - if (mce_cmci_disabled ^ !!new) { + if (mca_cfg.cmci_disabled ^ !!new) { if (new) { /* disable cmci */ on_each_cpu(mce_disable_cmci, NULL, 1); - mce_cmci_disabled = 1; + mca_cfg.cmci_disabled = true; } else { /* enable cmci */ - mce_cmci_disabled = 0; + mca_cfg.cmci_disabled = false; on_each_cpu(mce_enable_ce, NULL, 1); } } @@ -2190,9 +2195,9 @@ static ssize_t store_int_with_restart(struct device *s, } static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger); -static DEVICE_INT_ATTR(tolerant, 0644, tolerant); -static DEVICE_INT_ATTR(monarch_timeout, 0644, monarch_timeout); -static DEVICE_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce); +static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant); +static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout); +static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); static struct dev_ext_attribute dev_attr_check_interval = { __ATTR(check_interval, 0644, device_show_int, store_int_with_restart), @@ -2200,13 +2205,13 @@ static struct dev_ext_attribute dev_attr_check_interval = { }; static struct dev_ext_attribute dev_attr_ignore_ce = { - __ATTR(ignore_ce, 0644, device_show_int, set_ignore_ce), - &mce_ignore_ce + __ATTR(ignore_ce, 0644, device_show_bool, set_ignore_ce), + &mca_cfg.ignore_ce }; static struct dev_ext_attribute dev_attr_cmci_disabled = { - __ATTR(cmci_disabled, 0644, device_show_int, set_cmci_disabled), - &mce_cmci_disabled + __ATTR(cmci_disabled, 0644, device_show_bool, set_cmci_disabled), + &mca_cfg.cmci_disabled }; static struct device_attribute *mce_device_attrs[] = { @@ -2253,7 +2258,7 @@ static __cpuinit int mce_device_create(unsigned int cpu) if (err) goto error; } - for (j = 0; j < banks; j++) { + for (j = 0; j < mca_cfg.banks; j++) { err = device_create_file(dev, &mce_banks[j].attr); if (err) goto error2; @@ -2285,7 +2290,7 @@ static __cpuinit void mce_device_remove(unsigned int cpu) for (i = 0; mce_device_attrs[i]; i++) device_remove_file(dev, mce_device_attrs[i]); - for (i = 0; i < banks; i++) + for (i = 0; i < mca_cfg.banks; i++) device_remove_file(dev, &mce_banks[i].attr); device_unregister(dev); @@ -2304,7 +2309,7 @@ static void __cpuinit mce_disable_cpu(void *h) if (!(action & CPU_TASKS_FROZEN)) cmci_clear(); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (b->init) @@ -2322,7 +2327,7 @@ static void __cpuinit mce_reenable_cpu(void *h) if (!(action & CPU_TASKS_FROZEN)) cmci_reenable(); - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (b->init) @@ -2375,7 +2380,7 @@ static __init void mce_init_banks(void) { int i; - for (i = 0; i < banks; i++) { + for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; struct device_attribute *a = &b->attr; @@ -2426,7 +2431,7 @@ device_initcall_sync(mcheck_init_device); */ static int __init mcheck_disable(char *str) { - mce_disabled = 1; + mca_cfg.disabled = true; return 1; } __setup("nomce", mcheck_disable); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 698b6ec..1ac581f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -6,7 +6,7 @@ * * Written by Jacob Shin - AMD, Inc. * - * Support: borislav.petkov@amd.com + * Maintained by: Borislav Petkov <bp@alien8.de> * * April 2006 * - added support for AMD Family 0x10 processors diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 5f88abf..402c454 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -53,7 +53,7 @@ static int cmci_supported(int *banks) { u64 cap; - if (mce_cmci_disabled || mce_ignore_ce) + if (mca_cfg.cmci_disabled || mca_cfg.ignore_ce) return 0; /* @@ -200,7 +200,7 @@ static void cmci_discover(int banks) continue; } - if (!mce_bios_cmci_threshold) { + if (!mca_cfg.bios_cmci_threshold) { val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; val |= CMCI_THRESHOLD; } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { @@ -227,7 +227,7 @@ static void cmci_discover(int banks) * set the thresholds properly or does not work with * this boot option. Note down now and report later. */ - if (mce_bios_cmci_threshold && bios_zero_thresh && + if (mca_cfg.bios_cmci_threshold && bios_zero_thresh && (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) bios_wrong_thresh = 1; } else { @@ -235,7 +235,7 @@ static void cmci_discover(int banks) } } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); - if (mce_bios_cmci_threshold && bios_wrong_thresh) { + if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) { pr_info_once( "bios_cmci_threshold: Some banks do not have valid thresholds set\n"); pr_info_once( @@ -285,34 +285,39 @@ void cmci_clear(void) raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } +static long cmci_rediscover_work_func(void *arg) +{ + int banks; + + /* Recheck banks in case CPUs don't all have the same */ + if (cmci_supported(&banks)) + cmci_discover(banks); + + return 0; +} + /* * After a CPU went down cycle through all the others and rediscover * Must run in process context. */ void cmci_rediscover(int dying) { - int banks; - int cpu; - cpumask_var_t old; + int cpu, banks; if (!cmci_supported(&banks)) return; - if (!alloc_cpumask_var(&old, GFP_KERNEL)) - return; - cpumask_copy(old, ¤t->cpus_allowed); for_each_online_cpu(cpu) { if (cpu == dying) continue; - if (set_cpus_allowed_ptr(current, cpumask_of(cpu))) + + if (cpu == smp_processor_id()) { + cmci_rediscover_work_func(NULL); continue; - /* Recheck banks in case CPUs don't all have the same */ - if (cmci_supported(&banks)) - cmci_discover(banks); - } + } - set_cpus_allowed_ptr(current, old); - free_cpumask_var(old); + work_on_cpu(cpu, cmci_rediscover_work_func, NULL); + } } /* diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 6b96110..726bf96 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -606,7 +606,7 @@ void __init mtrr_bp_init(void) /* * This is an AMD specific MSR, but we assume(hope?) that - * Intel will implement it to when they extend the address + * Intel will implement it too when they extend the address * bus of the Xeon. */ if (cpuid_eax(0x80000000) >= 0x80000008) { @@ -695,11 +695,16 @@ void mtrr_ap_init(void) } /** - * Save current fixed-range MTRR state of the BSP + * Save current fixed-range MTRR state of the first cpu in cpu_online_mask. */ void mtrr_save_state(void) { - smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1); + int first_cpu; + + get_online_cpus(); + first_cpu = cpumask_first(cpu_online_mask); + smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); + put_online_cpus(); } void set_mtrr_aps_delayed_init(void) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4a3374e..6774c17 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -340,9 +340,6 @@ int x86_setup_perfctr(struct perf_event *event) /* BTS is currently only allowed for user-mode. */ if (!attr->exclude_kernel) return -EOPNOTSUPP; - - if (!attr->exclude_guest) - return -EOPNOTSUPP; } hwc->config |= config; @@ -385,9 +382,6 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip) { int precise = 0; - if (!event->attr.exclude_guest) - return -EOPNOTSUPP; - /* Support for constant skid */ if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { precise++; @@ -1316,6 +1310,121 @@ static struct attribute_group x86_pmu_format_group = { .attrs = NULL, }; +struct perf_pmu_events_attr { + struct device_attribute attr; + u64 id; +}; + +/* + * Remove all undefined events (x86_pmu.event_map(id) == 0) + * out of events_attr attributes. + */ +static void __init filter_events(struct attribute **attrs) +{ + int i, j; + + for (i = 0; attrs[i]; i++) { + if (x86_pmu.event_map(i)) + continue; + + for (j = i; attrs[j]; j++) + attrs[j] = attrs[j + 1]; + + /* Check the shifted attr. */ + i--; + } +} + +static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr = \ + container_of(attr, struct perf_pmu_events_attr, attr); + + u64 config = x86_pmu.event_map(pmu_attr->id); + return x86_pmu.events_sysfs_show(page, config); +} + +#define EVENT_VAR(_id) event_attr_##_id +#define EVENT_PTR(_id) &event_attr_##_id.attr.attr + +#define EVENT_ATTR(_name, _id) \ +static struct perf_pmu_events_attr EVENT_VAR(_id) = { \ + .attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \ + .id = PERF_COUNT_HW_##_id, \ +}; + +EVENT_ATTR(cpu-cycles, CPU_CYCLES ); +EVENT_ATTR(instructions, INSTRUCTIONS ); +EVENT_ATTR(cache-references, CACHE_REFERENCES ); +EVENT_ATTR(cache-misses, CACHE_MISSES ); +EVENT_ATTR(branch-instructions, BRANCH_INSTRUCTIONS ); +EVENT_ATTR(branch-misses, BRANCH_MISSES ); +EVENT_ATTR(bus-cycles, BUS_CYCLES ); +EVENT_ATTR(stalled-cycles-frontend, STALLED_CYCLES_FRONTEND ); +EVENT_ATTR(stalled-cycles-backend, STALLED_CYCLES_BACKEND ); +EVENT_ATTR(ref-cycles, REF_CPU_CYCLES ); + +static struct attribute *empty_attrs; + +static struct attribute *events_attr[] = { + EVENT_PTR(CPU_CYCLES), + EVENT_PTR(INSTRUCTIONS), + EVENT_PTR(CACHE_REFERENCES), + EVENT_PTR(CACHE_MISSES), + EVENT_PTR(BRANCH_INSTRUCTIONS), + EVENT_PTR(BRANCH_MISSES), + EVENT_PTR(BUS_CYCLES), + EVENT_PTR(STALLED_CYCLES_FRONTEND), + EVENT_PTR(STALLED_CYCLES_BACKEND), + EVENT_PTR(REF_CPU_CYCLES), + NULL, +}; + +static struct attribute_group x86_pmu_events_group = { + .name = "events", + .attrs = events_attr, +}; + +ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) +{ + u64 umask = (config & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; + u64 cmask = (config & ARCH_PERFMON_EVENTSEL_CMASK) >> 24; + bool edge = (config & ARCH_PERFMON_EVENTSEL_EDGE); + bool pc = (config & ARCH_PERFMON_EVENTSEL_PIN_CONTROL); + bool any = (config & ARCH_PERFMON_EVENTSEL_ANY); + bool inv = (config & ARCH_PERFMON_EVENTSEL_INV); + ssize_t ret; + + /* + * We have whole page size to spend and just little data + * to write, so we can safely use sprintf. + */ + ret = sprintf(page, "event=0x%02llx", event); + + if (umask) + ret += sprintf(page + ret, ",umask=0x%02llx", umask); + + if (edge) + ret += sprintf(page + ret, ",edge"); + + if (pc) + ret += sprintf(page + ret, ",pc"); + + if (any) + ret += sprintf(page + ret, ",any"); + + if (inv) + ret += sprintf(page + ret, ",inv"); + + if (cmask) + ret += sprintf(page + ret, ",cmask=0x%02llx", cmask); + + ret += sprintf(page + ret, "\n"); + + return ret; +} + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -1362,6 +1471,11 @@ static int __init init_hw_perf_events(void) x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; + if (!x86_pmu.events_sysfs_show) + x86_pmu_events_group.attrs = &empty_attrs; + else + filter_events(x86_pmu_events_group.attrs); + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); @@ -1651,6 +1765,7 @@ static struct attribute_group x86_pmu_attr_group = { static const struct attribute_group *x86_pmu_attr_groups[] = { &x86_pmu_attr_group, &x86_pmu_format_group, + &x86_pmu_events_group, NULL, }; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 271d257..115c1ea 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -354,6 +354,8 @@ struct x86_pmu { int attr_rdpmc; struct attribute **format_attrs; + ssize_t (*events_sysfs_show)(char *page, u64 config); + /* * CPU Hotplug hooks */ @@ -536,6 +538,9 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } +ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event); +ssize_t intel_event_sysfs_show(char *page, u64 config); + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 4528ae7..c93bc4e 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -568,6 +568,14 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev } } +static ssize_t amd_event_sysfs_show(char *page, u64 config) +{ + u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) | + (config & AMD64_EVENTSEL_EVENT) >> 24; + + return x86_event_sysfs_show(page, config, event); +} + static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = x86_pmu_handle_irq, @@ -591,6 +599,7 @@ static __initconst const struct x86_pmu amd_pmu = { .put_event_constraints = amd_put_event_constraints, .format_attrs = amd_format_attr, + .events_sysfs_show = amd_event_sysfs_show, .cpu_prepare = amd_pmu_cpu_prepare, .cpu_starting = amd_pmu_cpu_starting, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 324bb52..93b9e11 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1603,6 +1603,13 @@ static struct attribute *intel_arch_formats_attr[] = { NULL, }; +ssize_t intel_event_sysfs_show(char *page, u64 config) +{ + u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT); + + return x86_event_sysfs_show(page, config, event); +} + static __initconst const struct x86_pmu core_pmu = { .name = "core", .handle_irq = x86_pmu_handle_irq, @@ -1628,6 +1635,7 @@ static __initconst const struct x86_pmu core_pmu = { .event_constraints = intel_core_event_constraints, .guest_get_msrs = core_guest_get_msrs, .format_attrs = intel_arch_formats_attr, + .events_sysfs_show = intel_event_sysfs_show, }; struct intel_shared_regs *allocate_shared_regs(int cpu) @@ -1766,6 +1774,7 @@ static __initconst const struct x86_pmu intel_pmu = { .pebs_aliases = intel_pebs_aliases_core2, .format_attrs = intel_arch3_formats_attr, + .events_sysfs_show = intel_event_sysfs_show, .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 3cf3d97..b43200d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2500,7 +2500,7 @@ static bool pcidrv_registered; /* * add a pci uncore device */ -static int __devinit uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) +static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) { struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; @@ -2571,8 +2571,8 @@ static void uncore_pci_remove(struct pci_dev *pdev) kfree(box); } -static int __devinit uncore_pci_probe(struct pci_dev *pdev, - const struct pci_device_id *id) +static int uncore_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) { struct intel_uncore_type *type; diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 7d0270b..f2af39f 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -227,6 +227,8 @@ static __initconst const struct x86_pmu p6_pmu = { .event_constraints = p6_event_constraints, .format_attrs = intel_p6_formats_attr, + .events_sysfs_show = intel_event_sysfs_show, + }; __init int p6_pmu_init(void) diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index fbd8955..3286a92 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -26,11 +26,6 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, #ifdef CONFIG_X86_32 static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) { - /* - * We use exception 16 if we have hardware math and we've either seen - * it or the CPU claims it is internal - */ - int fpu_exception = c->hard_math && (ignore_fpu_irq || cpu_has_fpu); seq_printf(m, "fdiv_bug\t: %s\n" "hlt_bug\t\t: %s\n" @@ -45,7 +40,7 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) c->f00f_bug ? "yes" : "no", c->coma_bug ? "yes" : "no", c->hard_math ? "yes" : "no", - fpu_exception ? "yes" : "no", + c->hard_math ? "yes" : "no", c->cpuid_level, c->wp_works_ok ? "yes" : "no"); } diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 13ad899..74467fe 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -16,6 +16,7 @@ #include <linux/delay.h> #include <linux/elf.h> #include <linux/elfcore.h> +#include <linux/module.h> #include <asm/processor.h> #include <asm/hardirq.h> @@ -30,6 +31,27 @@ int in_crash_kexec; +/* + * This is used to VMCLEAR all VMCSs loaded on the + * processor. And when loading kvm_intel module, the + * callback function pointer will be assigned. + * + * protected by rcu. + */ +crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL; +EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss); + +static inline void cpu_crash_vmclear_loaded_vmcss(void) +{ + crash_vmclear_fn *do_vmclear_operation = NULL; + + rcu_read_lock(); + do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss); + if (do_vmclear_operation) + do_vmclear_operation(); + rcu_read_unlock(); +} + #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) @@ -46,6 +68,11 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) #endif crash_save_cpu(regs, cpu); + /* + * VMCLEAR VMCSs loaded on all cpus if needed. + */ + cpu_crash_vmclear_loaded_vmcss(); + /* Disable VMX or SVM if needed. * * We need to disable virtualization on all CPUs. @@ -88,6 +115,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs) kdump_nmi_shootdown_cpus(); + /* + * VMCLEAR VMCSs loaded on this cpu if needed. + */ + cpu_crash_vmclear_loaded_vmcss(); + /* Booting kdump kernel with VMX or SVM enabled won't work, * because (among other limitations) we can't disable paging * with the virt flags. diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 88b725a..6ed91d9 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -739,30 +739,11 @@ ENTRY(ptregs_##name) ; \ ENDPROC(ptregs_##name) PTREGSCALL1(iopl) -PTREGSCALL0(fork) -PTREGSCALL0(vfork) -PTREGSCALL2(sigaltstack) PTREGSCALL0(sigreturn) PTREGSCALL0(rt_sigreturn) PTREGSCALL2(vm86) PTREGSCALL1(vm86old) -/* Clone is an oddball. The 4th arg is in %edi */ -ENTRY(ptregs_clone) - CFI_STARTPROC - leal 4(%esp),%eax - pushl_cfi %eax - pushl_cfi PT_EDI(%eax) - movl PT_EDX(%eax),%ecx - movl PT_ECX(%eax),%edx - movl PT_EBX(%eax),%eax - call sys_clone - addl $8,%esp - CFI_ADJUST_CFA_OFFSET -8 - ret - CFI_ENDPROC -ENDPROC(ptregs_clone) - .macro FIXUP_ESPFIX_STACK /* * Switch back for ESPFIX stack to the normal zerobased stack @@ -1084,7 +1065,6 @@ ENTRY(xen_failsafe_callback) lea 16(%esp),%esp CFI_ADJUST_CFA_OFFSET -16 jz 5f - addl $16,%esp jmp iret_exc 5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index b51b2c7..07a7a04 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -56,7 +56,7 @@ #include <asm/ftrace.h> #include <asm/percpu.h> #include <asm/asm.h> -#include <asm/rcu.h> +#include <asm/context_tracking.h> #include <asm/smap.h> #include <linux/err.h> @@ -845,10 +845,25 @@ ENTRY(\label) END(\label) .endm - PTREGSCALL stub_clone, sys_clone, %r8 - PTREGSCALL stub_fork, sys_fork, %rdi - PTREGSCALL stub_vfork, sys_vfork, %rdi - PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx + .macro FORK_LIKE func +ENTRY(stub_\func) + CFI_STARTPROC + popq %r11 /* save return address */ + PARTIAL_FRAME 0 + SAVE_REST + pushq %r11 /* put it back on stack */ + FIXUP_TOP_OF_STACK %r11, 8 + DEFAULT_FRAME 0 8 /* offset 8: return address */ + call sys_\func + RESTORE_TOP_OF_STACK %r11, 8 + ret $REST_SKIP /* pop extended registers */ + CFI_ENDPROC +END(stub_\func) + .endm + + FORK_LIKE clone + FORK_LIKE fork + FORK_LIKE vfork PTREGSCALL stub_iopl, sys_iopl, %rsi ENTRY(ptregscall_common) @@ -897,8 +912,6 @@ ENTRY(stub_rt_sigreturn) END(stub_rt_sigreturn) #ifdef CONFIG_X86_X32_ABI - PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx - ENTRY(stub_x32_rt_sigreturn) CFI_STARTPROC addq $8, %rsp @@ -995,8 +1008,8 @@ END(interrupt) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: - ASM_CLAC XCPT_FRAME + ASM_CLAC addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ interrupt do_IRQ /* 0(%rsp): old_rsp-ARGOFFSET */ @@ -1135,8 +1148,8 @@ END(common_interrupt) */ .macro apicinterrupt num sym do_sym ENTRY(\sym) - ASM_CLAC INTR_FRAME + ASM_CLAC pushq_cfi $~(\num) .Lcommon_\sym: interrupt \do_sym @@ -1190,8 +1203,8 @@ apicinterrupt IRQ_WORK_VECTOR \ */ .macro zeroentry sym do_sym ENTRY(\sym) - ASM_CLAC INTR_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp @@ -1208,8 +1221,8 @@ END(\sym) .macro paranoidzeroentry sym do_sym ENTRY(\sym) - ASM_CLAC INTR_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp @@ -1227,8 +1240,8 @@ END(\sym) #define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) .macro paranoidzeroentry_ist sym do_sym ist ENTRY(\sym) - ASM_CLAC INTR_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp @@ -1247,8 +1260,8 @@ END(\sym) .macro errorentry sym do_sym ENTRY(\sym) - ASM_CLAC XCPT_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 @@ -1266,8 +1279,8 @@ END(\sym) /* error code is on the stack already */ .macro paranoiderrorentry sym do_sym ENTRY(\sym) - ASM_CLAC XCPT_FRAME + ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 @@ -1699,9 +1712,10 @@ nested_nmi: 1: /* Set up the interrupted NMIs stack to jump to repeat_nmi */ - leaq -6*8(%rsp), %rdx + leaq -1*8(%rsp), %rdx movq %rdx, %rsp - CFI_ADJUST_CFA_OFFSET 6*8 + CFI_ADJUST_CFA_OFFSET 1*8 + leaq -10*8(%rsp), %rdx pushq_cfi $__KERNEL_DS pushq_cfi %rdx pushfq_cfi @@ -1709,8 +1723,8 @@ nested_nmi: pushq_cfi $repeat_nmi /* Put stack back */ - addq $(11*8), %rsp - CFI_ADJUST_CFA_OFFSET -11*8 + addq $(6*8), %rsp + CFI_ADJUST_CFA_OFFSET -6*8 nested_nmi_out: popq_cfi %rdx @@ -1736,18 +1750,18 @@ first_nmi: * +-------------------------+ * | NMI executing variable | * +-------------------------+ - * | Saved SS | - * | Saved Return RSP | - * | Saved RFLAGS | - * | Saved CS | - * | Saved RIP | - * +-------------------------+ * | copied SS | * | copied Return RSP | * | copied RFLAGS | * | copied CS | * | copied RIP | * +-------------------------+ + * | Saved SS | + * | Saved Return RSP | + * | Saved RFLAGS | + * | Saved CS | + * | Saved RIP | + * +-------------------------+ * | pt_regs | * +-------------------------+ * @@ -1763,9 +1777,14 @@ first_nmi: /* Set the NMI executing variable on the stack. */ pushq_cfi $1 + /* + * Leave room for the "copied" frame + */ + subq $(5*8), %rsp + /* Copy the stack frame to the Saved frame */ .rept 5 - pushq_cfi 6*8(%rsp) + pushq_cfi 11*8(%rsp) .endr CFI_DEF_CFA_OFFSET SS+8-RIP @@ -1786,12 +1805,15 @@ repeat_nmi: * is benign for the non-repeat case, where 1 was pushed just above * to this very stack slot). */ - movq $1, 5*8(%rsp) + movq $1, 10*8(%rsp) /* Make another copy, this one may be modified by nested NMIs */ + addq $(10*8), %rsp + CFI_ADJUST_CFA_OFFSET -10*8 .rept 5 - pushq_cfi 4*8(%rsp) + pushq_cfi -6*8(%rsp) .endr + subq $(5*8), %rsp CFI_DEF_CFA_OFFSET SS+8-RIP end_repeat_nmi: @@ -1842,8 +1864,12 @@ nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: RESTORE_ALL 8 + + /* Pop the extra iret frame */ + addq $(5*8), %rsp + /* Clear the NMI executing stack variable */ - movq $0, 10*8(%rsp) + movq $0, 5*8(%rsp) jmp irq_return CFI_ENDPROC END(nmi) diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index c18f59d..6773c91 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -18,6 +18,7 @@ #include <asm/io_apic.h> #include <asm/bios_ebda.h> #include <asm/tlbflush.h> +#include <asm/bootparam_utils.h> static void __init i386_default_early_setup(void) { @@ -30,6 +31,8 @@ static void __init i386_default_early_setup(void) void __init i386_start_kernel(void) { + sanitize_boot_params(&boot_params); + memblock_reserve(__pa_symbol(&_text), __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 037df57..849fc9e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -25,6 +25,7 @@ #include <asm/kdebug.h> #include <asm/e820.h> #include <asm/bios_ebda.h> +#include <asm/bootparam_utils.h> static void __init zap_identity_mappings(void) { @@ -46,6 +47,7 @@ static void __init copy_bootdata(char *real_mode_data) char * command_line; memcpy(&boot_params, real_mode_data, sizeof boot_params); + sanitize_boot_params(&boot_params); if (boot_params.hdr.cmd_line_ptr) { command_line = __va(boot_params.hdr.cmd_line_ptr); memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 957a47a..8e7f655 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -266,6 +266,19 @@ num_subarch_entries = (. - subarch_entries) / 4 jmp default_entry #endif /* CONFIG_PARAVIRT */ +#ifdef CONFIG_HOTPLUG_CPU +/* + * Boot CPU0 entry point. It's called from play_dead(). Everything has been set + * up already except stack. We just set up stack here. Then call + * start_secondary(). + */ +ENTRY(start_cpu0) + movl stack_start, %ecx + movl %ecx, %esp + jmp *(initial_code) +ENDPROC(start_cpu0) +#endif + /* * Non-boot CPU entry point; entered from trampoline.S * We can't lgdt here, because lgdt itself uses a data segment, but @@ -292,8 +305,8 @@ default_entry: * be using the global pages. * * NOTE! If we are on a 486 we may have no cr4 at all! - * Specifically, cr4 exists if and only if CPUID exists, - * which in turn exists if and only if EFLAGS.ID exists. + * Specifically, cr4 exists if and only if CPUID exists + * and has flags other than the FPU flag set. */ movl $X86_EFLAGS_ID,%ecx pushl %ecx @@ -308,6 +321,11 @@ default_entry: testl %ecx,%eax jz 6f # No ID flag = no CPUID = no CR4 + movl $1,%eax + cpuid + andl $~1,%edx # Ignore CPUID.FPU + jz 6f # No flags or only CPUID.FPU = no CR4 + movl pa(mmu_cr4_features),%eax movl %eax,%cr4 diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 94bf9cc..980053c 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -252,6 +252,22 @@ ENTRY(secondary_startup_64) pushq %rax # target address in negative space lretq +#ifdef CONFIG_HOTPLUG_CPU +/* + * Boot CPU0 entry point. It's called from play_dead(). Everything has been set + * up already except stack. We just set up stack here. Then call + * start_secondary(). + */ +ENTRY(start_cpu0) + movq stack_start(%rip),%rsp + movq initial_code(%rip),%rax + pushq $0 # fake return address to stop unwinder + pushq $__KERNEL_CS # set correct cs + pushq %rax # target address in negative space + lretq +ENDPROC(start_cpu0) +#endif + /* SMP bootup changes these two */ __REFDATA .align 8 diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 1460a5d..e28670f 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -434,7 +434,7 @@ void hpet_msi_unmask(struct irq_data *data) /* unmask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); - cfg |= HPET_TN_FSB; + cfg |= HPET_TN_ENABLE | HPET_TN_FSB; hpet_writel(cfg, HPET_Tn_CFG(hdev->num)); } @@ -445,7 +445,7 @@ void hpet_msi_mask(struct irq_data *data) /* mask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); - cfg &= ~HPET_TN_FSB; + cfg &= ~(HPET_TN_ENABLE | HPET_TN_FSB); hpet_writel(cfg, HPET_Tn_CFG(hdev->num)); } diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 675a050..245a71d 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -175,7 +175,11 @@ void __cpuinit fpu_init(void) cr0 |= X86_CR0_EM; write_cr0(cr0); - if (!smp_processor_id()) + /* + * init_thread_xstate is only called once to avoid overriding + * xstate_size during boot time or during CPU hotplug. + */ + if (xstate_size == 0) init_thread_xstate(); mxcsr_feature_mask_init(); diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 6e03b0d..7dc4e45 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -42,39 +42,6 @@ * (these are usually mapped into the 0x30-0xff vector range) */ -#ifdef CONFIG_X86_32 -/* - * Note that on a 486, we don't want to do a SIGFPE on an irq13 - * as the irq is unreliable, and exception 16 works correctly - * (ie as explained in the intel literature). On a 386, you - * can't use exception 16 due to bad IBM design, so we have to - * rely on the less exact irq13. - * - * Careful.. Not only is IRQ13 unreliable, but it is also - * leads to races. IBM designers who came up with it should - * be shot. - */ - -static irqreturn_t math_error_irq(int cpl, void *dev_id) -{ - outb(0, 0xF0); - if (ignore_fpu_irq || !boot_cpu_data.hard_math) - return IRQ_NONE; - math_error(get_irq_regs(), 0, X86_TRAP_MF); - return IRQ_HANDLED; -} - -/* - * New motherboards sometimes make IRQ 13 be a PCI interrupt, - * so allow interrupt sharing. - */ -static struct irqaction fpu_irq = { - .handler = math_error_irq, - .name = "fpu", - .flags = IRQF_NO_THREAD, -}; -#endif - /* * IRQ2 is cascade interrupt to second interrupt controller */ @@ -242,13 +209,6 @@ void __init native_init_IRQ(void) setup_irq(2, &irq2); #ifdef CONFIG_X86_32 - /* - * External FPU? Set up irq13 if so, for - * original braindamaged IBM FERR coupling. - */ - if (boot_cpu_data.hard_math && !cpu_has_fpu) - setup_irq(FPU_IRQ, &fpu_irq); - irq_ctx_init(smp_processor_id()); #endif } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 4180a87..9c2bd8b 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -42,6 +42,8 @@ #include <asm/apic.h> #include <asm/apicdef.h> #include <asm/hypervisor.h> +#include <asm/kvm_guest.h> +#include <asm/context_tracking.h> static int kvmapf = 1; @@ -62,6 +64,15 @@ static int parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); +static int kvmclock_vsyscall = 1; +static int parse_no_kvmclock_vsyscall(char *arg) +{ + kvmclock_vsyscall = 0; + return 0; +} + +early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); + static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64); static int has_steal_clock = 0; @@ -110,11 +121,8 @@ void kvm_async_pf_task_wait(u32 token) struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; struct kvm_task_sleep_node n, *e; DEFINE_WAIT(wait); - int cpu, idle; - cpu = get_cpu(); - idle = idle_cpu(cpu); - put_cpu(); + rcu_irq_enter(); spin_lock(&b->lock); e = _find_apf_task(b, token); @@ -123,12 +131,14 @@ void kvm_async_pf_task_wait(u32 token) hlist_del(&e->link); kfree(e); spin_unlock(&b->lock); + + rcu_irq_exit(); return; } n.token = token; n.cpu = smp_processor_id(); - n.halted = idle || preempt_count() > 1; + n.halted = is_idle_task(current) || preempt_count() > 1; init_waitqueue_head(&n.wq); hlist_add_head(&n.link, &b->list); spin_unlock(&b->lock); @@ -147,13 +157,16 @@ void kvm_async_pf_task_wait(u32 token) /* * We cannot reschedule. So halt. */ + rcu_irq_exit(); native_safe_halt(); + rcu_irq_enter(); local_irq_disable(); } } if (!n.halted) finish_wait(&n.wq, &wait); + rcu_irq_exit(); return; } EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait); @@ -247,10 +260,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ - rcu_irq_enter(); + exception_enter(regs); exit_idle(); kvm_async_pf_task_wait((u32)read_cr2()); - rcu_irq_exit(); + exception_exit(regs); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); @@ -471,6 +484,9 @@ void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) apic_set_eoi_write(kvm_guest_apic_eoi_write); + if (kvmclock_vsyscall) + kvm_setup_vsyscall_timeinfo(); + #ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; register_cpu_notifier(&kvm_cpu_notifier); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index f1b42b3..220a360 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -23,6 +23,7 @@ #include <asm/apic.h> #include <linux/percpu.h> #include <linux/hardirq.h> +#include <linux/memblock.h> #include <asm/x86_init.h> #include <asm/reboot.h> @@ -39,7 +40,7 @@ static int parse_no_kvmclock(char *arg) early_param("no-kvmclock", parse_no_kvmclock); /* The hypervisor will put information about time periodically here */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock); +static struct pvclock_vsyscall_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; /* @@ -52,15 +53,20 @@ static unsigned long kvm_get_wallclock(void) struct pvclock_vcpu_time_info *vcpu_time; struct timespec ts; int low, high; + int cpu; low = (int)__pa_symbol(&wall_clock); high = ((u64)__pa_symbol(&wall_clock) >> 32); native_write_msr(msr_kvm_wall_clock, low, high); - vcpu_time = &get_cpu_var(hv_clock); + preempt_disable(); + cpu = smp_processor_id(); + + vcpu_time = &hv_clock[cpu].pvti; pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); - put_cpu_var(hv_clock); + + preempt_enable(); return ts.tv_sec; } @@ -74,9 +80,11 @@ static cycle_t kvm_clock_read(void) { struct pvclock_vcpu_time_info *src; cycle_t ret; + int cpu; preempt_disable_notrace(); - src = &__get_cpu_var(hv_clock); + cpu = smp_processor_id(); + src = &hv_clock[cpu].pvti; ret = pvclock_clocksource_read(src); preempt_enable_notrace(); return ret; @@ -99,8 +107,15 @@ static cycle_t kvm_clock_get_cycles(struct clocksource *cs) static unsigned long kvm_get_tsc_khz(void) { struct pvclock_vcpu_time_info *src; - src = &per_cpu(hv_clock, 0); - return pvclock_tsc_khz(src); + int cpu; + unsigned long tsc_khz; + + preempt_disable(); + cpu = smp_processor_id(); + src = &hv_clock[cpu].pvti; + tsc_khz = pvclock_tsc_khz(src); + preempt_enable(); + return tsc_khz; } static void kvm_get_preset_lpj(void) @@ -119,10 +134,14 @@ bool kvm_check_and_clear_guest_paused(void) { bool ret = false; struct pvclock_vcpu_time_info *src; + int cpu = smp_processor_id(); - src = &__get_cpu_var(hv_clock); + if (!hv_clock) + return ret; + + src = &hv_clock[cpu].pvti; if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) { - __this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED); + src->flags &= ~PVCLOCK_GUEST_STOPPED; ret = true; } @@ -141,9 +160,10 @@ int kvm_register_clock(char *txt) { int cpu = smp_processor_id(); int low, high, ret; + struct pvclock_vcpu_time_info *src = &hv_clock[cpu].pvti; - low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1; - high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32); + low = (int)__pa(src) | 1; + high = ((u64)__pa(src) >> 32); ret = native_write_msr_safe(msr_kvm_system_time, low, high); printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n", cpu, high, low, txt); @@ -197,6 +217,8 @@ static void kvm_shutdown(void) void __init kvmclock_init(void) { + unsigned long mem; + if (!kvm_para_available()) return; @@ -209,8 +231,18 @@ void __init kvmclock_init(void) printk(KERN_INFO "kvm-clock: Using msrs %x and %x", msr_kvm_system_time, msr_kvm_wall_clock); - if (kvm_register_clock("boot clock")) + mem = memblock_alloc(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS, + PAGE_SIZE); + if (!mem) + return; + hv_clock = __va(mem); + + if (kvm_register_clock("boot clock")) { + hv_clock = NULL; + memblock_free(mem, + sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); return; + } pv_time_ops.sched_clock = kvm_clock_read; x86_platform.calibrate_tsc = kvm_get_tsc_khz; x86_platform.get_wallclock = kvm_get_wallclock; @@ -233,3 +265,37 @@ void __init kvmclock_init(void) if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); } + +int __init kvm_setup_vsyscall_timeinfo(void) +{ +#ifdef CONFIG_X86_64 + int cpu; + int ret; + u8 flags; + struct pvclock_vcpu_time_info *vcpu_time; + unsigned int size; + + size = sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS; + + preempt_disable(); + cpu = smp_processor_id(); + + vcpu_time = &hv_clock[cpu].pvti; + flags = pvclock_read_flags(vcpu_time); + + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) { + preempt_enable(); + return 1; + } + + if ((ret = pvclock_init_vsyscall(hv_clock, size))) { + preempt_enable(); + return ret; + } + + preempt_enable(); + + kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; +#endif + return 0; +} diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 7720ff5..efdec7c 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -8,8 +8,8 @@ * Tigran Aivazian <tigran@aivazian.fsnet.co.uk> * * Maintainers: - * Andreas Herrmann <andreas.herrmann3@amd.com> - * Borislav Petkov <borislav.petkov@amd.com> + * Andreas Herrmann <herrmann.der.user@googlemail.com> + * Borislav Petkov <bp@alien8.de> * * This driver allows to upgrade microcode on F10h AMD * CPUs and later. @@ -190,6 +190,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size, #define F1XH_MPB_MAX_SIZE 2048 #define F14H_MPB_MAX_SIZE 1824 #define F15H_MPB_MAX_SIZE 4096 +#define F16H_MPB_MAX_SIZE 3458 switch (c->x86) { case 0x14: @@ -198,6 +199,9 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size, case 0x15: max_size = F15H_MPB_MAX_SIZE; break; + case 0x16: + max_size = F16H_MPB_MAX_SIZE; + break; default: max_size = F1XH_MPB_MAX_SIZE; break; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index de2b7ad..0f5dec5 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -265,7 +265,7 @@ rootfs_initcall(pci_iommu_init); #ifdef CONFIG_PCI /* Many VIA bridges seem to corrupt data for DAC. Disable it here */ -static __devinit void via_no_dac(struct pci_dev *dev) +static void via_no_dac(struct pci_dev *dev) { if (forbid_dac == 0) { dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n"); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b644e1c..2ed787f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -262,36 +262,6 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, propagate_user_return_notify(prev_p, next_p); } -int sys_fork(struct pt_regs *regs) -{ - return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - -/* - * This is trivial, and on the face of it looks like it - * could equally well be done in user mode. - * - * Not so, for quite unobvious reasons - register pressure. - * In user mode vfork() cannot have a stack frame, and if - * done by calling the "clone()" system call directly, you - * do not have enough call-clobbered registers to hold all - * the information you need. - */ -int sys_vfork(struct pt_regs *regs) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, - NULL, NULL); -} - -long -sys_clone(unsigned long clone_flags, unsigned long newsp, - void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) -{ - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); -} - /* * Idle related variables and functions */ @@ -306,11 +276,6 @@ void (*pm_idle)(void); EXPORT_SYMBOL(pm_idle); #endif -static inline int hlt_use_halt(void) -{ - return 1; -} - #ifndef CONFIG_SMP static inline void play_dead(void) { @@ -410,28 +375,22 @@ void cpu_idle(void) */ void default_idle(void) { - if (hlt_use_halt()) { - trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); - trace_cpu_idle_rcuidle(1, smp_processor_id()); - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); + trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle_rcuidle(1, smp_processor_id()); + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we + * test NEED_RESCHED: + */ + smp_mb(); - if (!need_resched()) - safe_halt(); /* enables interrupts racelessly */ - else - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; - trace_power_end_rcuidle(smp_processor_id()); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); - } else { + if (!need_resched()) + safe_halt(); /* enables interrupts racelessly */ + else local_irq_enable(); - /* loop is done by the caller */ - cpu_relax(); - } + current_thread_info()->status |= TS_POLLING; + trace_power_end_rcuidle(smp_processor_id()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(default_idle); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 44e0bff..b5a8905 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -128,8 +128,7 @@ void release_thread(struct task_struct *dead_task) } int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, - struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { struct pt_regs *childregs = task_pt_regs(p); struct task_struct *tsk; @@ -138,7 +137,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.sp0 = (unsigned long) (childregs+1); - if (unlikely(!regs)) { + if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); p->thread.ip = (unsigned long) ret_from_kernel_thread; @@ -156,12 +155,13 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); return 0; } - *childregs = *regs; + *childregs = *current_pt_regs(); childregs->ax = 0; - childregs->sp = sp; + if (sp) + childregs->sp = sp; p->thread.ip = (unsigned long) ret_from_fork; - task_user_gs(p) = get_user_gs(regs); + task_user_gs(p) = get_user_gs(current_pt_regs()); p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 16c6365..6e68a61 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -146,8 +146,7 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls) } int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, - struct task_struct *p, struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { int err; struct pt_regs *childregs; @@ -169,7 +168,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, savesegment(ds, p->thread.ds); memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); - if (unlikely(!regs)) { + if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); childregs->sp = (unsigned long)childregs; @@ -181,10 +180,11 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; return 0; } - *childregs = *regs; + *childregs = *current_pt_regs(); childregs->ax = 0; - childregs->sp = sp; + if (sp) + childregs->sp = sp; err = -ENOMEM; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index b00b33a..b629bbe 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -22,6 +22,8 @@ #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> #include <linux/rcupdate.h> +#include <linux/module.h> +#include <linux/context_tracking.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -166,6 +168,35 @@ static inline bool invalid_selector(u16 value) #define FLAG_MASK FLAG_MASK_32 +/* + * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode + * when it traps. The previous stack will be directly underneath the saved + * registers, and 'sp/ss' won't even have been saved. Thus the '®s->sp'. + * + * Now, if the stack is empty, '®s->sp' is out of range. In this + * case we try to take the previous stack. To always return a non-null + * stack pointer we fall back to regs as stack if no previous stack + * exists. + * + * This is valid only for kernel mode traps. + */ +unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ + unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1); + unsigned long sp = (unsigned long)®s->sp; + struct thread_info *tinfo; + + if (context == (sp & ~(THREAD_SIZE - 1))) + return sp; + + tinfo = (struct thread_info *)context; + if (tinfo->previous_esp) + return tinfo->previous_esp; + + return (unsigned long)regs; +} +EXPORT_SYMBOL_GPL(kernel_stack_pointer); + static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno) { BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0); @@ -1461,7 +1492,7 @@ long syscall_trace_enter(struct pt_regs *regs) { long ret = 0; - rcu_user_exit(); + user_exit(); /* * If we stepped into a sysenter/syscall insn, it trapped in @@ -1511,6 +1542,13 @@ void syscall_trace_leave(struct pt_regs *regs) { bool step; + /* + * We may come here right after calling schedule_user() + * or do_notify_resume(), in which case we can be in RCU + * user mode. + */ + user_exit(); + audit_syscall_exit(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) @@ -1527,5 +1565,5 @@ void syscall_trace_leave(struct pt_regs *regs) if (step || test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, step); - rcu_user_enter(); + user_enter(); } diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 42eb330..85c3959 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -17,23 +17,13 @@ #include <linux/kernel.h> #include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/sched.h> +#include <linux/gfp.h> +#include <linux/bootmem.h> +#include <asm/fixmap.h> #include <asm/pvclock.h> -/* - * These are perodically updated - * xen: magic shared_info page - * kvm: gpa registered via msr - * and then copied here. - */ -struct pvclock_shadow_time { - u64 tsc_timestamp; /* TSC at last update of time vals. */ - u64 system_timestamp; /* Time, in nanosecs, since boot. */ - u32 tsc_to_nsec_mul; - int tsc_shift; - u32 version; - u8 flags; -}; - static u8 valid_flags __read_mostly = 0; void pvclock_set_flags(u8 flags) @@ -41,34 +31,6 @@ void pvclock_set_flags(u8 flags) valid_flags = flags; } -static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow) -{ - u64 delta = native_read_tsc() - shadow->tsc_timestamp; - return pvclock_scale_delta(delta, shadow->tsc_to_nsec_mul, - shadow->tsc_shift); -} - -/* - * Reads a consistent set of time-base values from hypervisor, - * into a shadow data area. - */ -static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst, - struct pvclock_vcpu_time_info *src) -{ - do { - dst->version = src->version; - rmb(); /* fetch version before data */ - dst->tsc_timestamp = src->tsc_timestamp; - dst->system_timestamp = src->system_time; - dst->tsc_to_nsec_mul = src->tsc_to_system_mul; - dst->tsc_shift = src->tsc_shift; - dst->flags = src->flags; - rmb(); /* test version after fetching data */ - } while ((src->version & 1) || (dst->version != src->version)); - - return dst->version; -} - unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) { u64 pv_tsc_khz = 1000000ULL << 32; @@ -88,23 +50,32 @@ void pvclock_resume(void) atomic64_set(&last_value, 0); } +u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) +{ + unsigned version; + cycle_t ret; + u8 flags; + + do { + version = __pvclock_read_cycles(src, &ret, &flags); + } while ((src->version & 1) || version != src->version); + + return flags & valid_flags; +} + cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { - struct pvclock_shadow_time shadow; unsigned version; - cycle_t ret, offset; + cycle_t ret; u64 last; + u8 flags; do { - version = pvclock_get_time_values(&shadow, src); - barrier(); - offset = pvclock_get_nsec_offset(&shadow); - ret = shadow.system_timestamp + offset; - barrier(); - } while (version != src->version); + version = __pvclock_read_cycles(src, &ret, &flags); + } while ((src->version & 1) || version != src->version); if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) && - (shadow.flags & PVCLOCK_TSC_STABLE_BIT)) + (flags & PVCLOCK_TSC_STABLE_BIT)) return ret; /* @@ -156,3 +127,71 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } + +static struct pvclock_vsyscall_time_info *pvclock_vdso_info; + +static struct pvclock_vsyscall_time_info * +pvclock_get_vsyscall_user_time_info(int cpu) +{ + if (!pvclock_vdso_info) { + BUG(); + return NULL; + } + + return &pvclock_vdso_info[cpu]; +} + +struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) +{ + return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; +} + +#ifdef CONFIG_X86_64 +static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, + void *v) +{ + struct task_migration_notifier *mn = v; + struct pvclock_vsyscall_time_info *pvti; + + pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); + + /* this is NULL when pvclock vsyscall is not initialized */ + if (unlikely(pvti == NULL)) + return NOTIFY_DONE; + + pvti->migrate_count++; + + return NOTIFY_DONE; +} + +static struct notifier_block pvclock_migrate = { + .notifier_call = pvclock_task_migrate, +}; + +/* + * Initialize the generic pvclock vsyscall state. This will allocate + * a/some page(s) for the per-vcpu pvclock information, set up a + * fixmap mapping for the page(s) + */ + +int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, + int size) +{ + int idx; + + WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); + + pvclock_vdso_info = i; + + for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { + __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, + __pa_symbol(i) + (idx*PAGE_SIZE), + PAGE_KERNEL_VVAR); + } + + + register_task_migration_notifier(&pvclock_migrate); + + return 0; +} +#endif diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 1b27de5..26ee48a 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -8,7 +8,7 @@ #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI) -static void __devinit quirk_intel_irqbalance(struct pci_dev *dev) +static void quirk_intel_irqbalance(struct pci_dev *dev) { u8 config; u16 word; @@ -512,7 +512,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, #if defined(CONFIG_PCI) && defined(CONFIG_NUMA) /* Set correct numa_node information for AMD NB functions */ -static void __devinit quirk_amd_nb_node(struct pci_dev *dev) +static void quirk_amd_nb_node(struct pci_dev *dev) { struct pci_dev *nb_ht; unsigned int devfn; diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 4929c1b..801602b 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -195,12 +195,6 @@ void read_persistent_clock(struct timespec *ts) ts->tv_nsec = 0; } -unsigned long long native_read_tsc(void) -{ - return __native_read_tsc(); -} -EXPORT_SYMBOL(native_read_tsc); - static struct resource rtc_resources[] = { [0] = { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 6d29d1f..2681937 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -142,11 +142,7 @@ int default_check_phys_apicid_present(int phys_apicid) } #endif -#ifndef CONFIG_DEBUG_BOOT_PARAMS -struct boot_params __initdata boot_params; -#else struct boot_params boot_params; -#endif /* * Machine setup.. @@ -605,6 +601,83 @@ static __init void reserve_ibft_region(void) static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; +static bool __init snb_gfx_workaround_needed(void) +{ +#ifdef CONFIG_PCI + int i; + u16 vendor, devid; + static const __initconst u16 snb_ids[] = { + 0x0102, + 0x0112, + 0x0122, + 0x0106, + 0x0116, + 0x0126, + 0x010a, + }; + + /* Assume no if something weird is going on with PCI */ + if (!early_pci_allowed()) + return false; + + vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID); + if (vendor != 0x8086) + return false; + + devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID); + for (i = 0; i < ARRAY_SIZE(snb_ids); i++) + if (devid == snb_ids[i]) + return true; +#endif + + return false; +} + +/* + * Sandy Bridge graphics has trouble with certain ranges, exclude + * them from allocation. + */ +static void __init trim_snb_memory(void) +{ + static const __initconst unsigned long bad_pages[] = { + 0x20050000, + 0x20110000, + 0x20130000, + 0x20138000, + 0x40004000, + }; + int i; + + if (!snb_gfx_workaround_needed()) + return; + + printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n"); + + /* + * Reserve all memory below the 1 MB mark that has not + * already been reserved. + */ + memblock_reserve(0, 1<<20); + + for (i = 0; i < ARRAY_SIZE(bad_pages); i++) { + if (memblock_reserve(bad_pages[i], PAGE_SIZE)) + printk(KERN_WARNING "failed to reserve 0x%08lx\n", + bad_pages[i]); + } +} + +/* + * Here we put platform-specific memory range workarounds, i.e. + * memory known to be corrupt or otherwise in need to be reserved on + * specific platforms. + * + * If this gets used more widely it could use a real dispatch mechanism. + */ +static void __init trim_platform_memory_ranges(void) +{ + trim_snb_memory(); +} + static void __init trim_bios_range(void) { /* @@ -625,6 +698,7 @@ static void __init trim_bios_range(void) * take them out. */ e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } @@ -919,6 +993,8 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); + trim_platform_memory_ranges(); + init_mem_mapping(); memblock.current_limit = get_max_mapped(); @@ -937,6 +1013,10 @@ void __init setup_arch(char **cmdline_p) reserve_initrd(); +#if defined(CONFIG_ACPI) && defined(CONFIG_BLK_DEV_INITRD) + acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start); +#endif + reserve_crashkernel(); vsmp_init(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 70b27ee..d6bf1f3 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -22,6 +22,7 @@ #include <linux/uaccess.h> #include <linux/user-return-notifier.h> #include <linux/uprobes.h> +#include <linux/context_tracking.h> #include <asm/processor.h> #include <asm/ucontext.h> @@ -363,10 +364,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - put_user_ex(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= __save_altstack(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. */ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); @@ -413,7 +411,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, struct rt_sigframe __user *frame; void __user *fp = NULL; int err = 0; - struct task_struct *me = current; frame = get_sigframe(ka, regs, sizeof(struct rt_sigframe), &fp); @@ -432,10 +429,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - put_user_ex(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - put_user_ex(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - put_user_ex(me->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= __save_altstack(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. If provided, use a stub already in userspace. */ @@ -502,10 +496,7 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - put_user_ex(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); if (ka->sa.sa_flags & SA_RESTORER) { @@ -602,13 +593,6 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, } #endif /* CONFIG_X86_32 */ -long -sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, - struct pt_regs *regs) -{ - return do_sigaltstack(uss, uoss, regs->sp); -} - /* * Do a signal return; undo the signal stack. */ @@ -658,7 +642,7 @@ long sys_rt_sigreturn(struct pt_regs *regs) if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) goto badframe; - if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT) + if (restore_altstack(&frame->uc.uc_stack)) goto badframe; return ax; @@ -816,7 +800,7 @@ static void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { - rcu_user_exit(); + user_exit(); #ifdef CONFIG_X86_MCE /* notify userspace of pending MCEs */ @@ -838,7 +822,7 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) fire_user_return_notifiers(); - rcu_user_enter(); + user_enter(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) @@ -864,7 +848,6 @@ asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) struct rt_sigframe_x32 __user *frame; sigset_t set; unsigned long ax; - struct pt_regs tregs; frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); @@ -878,8 +861,7 @@ asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) goto badframe; - tregs = *regs; - if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT) + if (compat_restore_altstack(&frame->uc.uc_stack)) goto badframe; return ax; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c80a33b..ed0fe38 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -68,6 +68,8 @@ #include <asm/mwait.h> #include <asm/apic.h> #include <asm/io_apic.h> +#include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/setup.h> #include <asm/uv/uv.h> #include <linux/mc146818rtc.h> @@ -125,8 +127,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_info); atomic_t init_deasserted; /* - * Report back to the Boot Processor. - * Running on AP. + * Report back to the Boot Processor during boot time or to the caller processor + * during CPU online. */ static void __cpuinit smp_callin(void) { @@ -138,15 +140,17 @@ static void __cpuinit smp_callin(void) * we may get here before an INIT-deassert IPI reaches * our local APIC. We have to wait for the IPI or we'll * lock up on an APIC access. + * + * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI. */ - if (apic->wait_for_init_deassert) + cpuid = smp_processor_id(); + if (apic->wait_for_init_deassert && cpuid != 0) apic->wait_for_init_deassert(&init_deasserted); /* * (This works even if the APIC is not enabled.) */ phys_id = read_apic_id(); - cpuid = smp_processor_id(); if (cpumask_test_cpu(cpuid, cpu_callin_mask)) { panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__, phys_id, cpuid); @@ -228,6 +232,8 @@ static void __cpuinit smp_callin(void) cpumask_set_cpu(cpuid, cpu_callin_mask); } +static int cpu0_logical_apicid; +static int enable_start_cpu0; /* * Activate a secondary processor. */ @@ -243,6 +249,8 @@ notrace static void __cpuinit start_secondary(void *unused) preempt_disable(); smp_callin(); + enable_start_cpu0 = 0; + #ifdef CONFIG_X86_32 /* switch away from the initial page table */ load_cr3(swapper_pg_dir); @@ -279,19 +287,30 @@ notrace static void __cpuinit start_secondary(void *unused) cpu_idle(); } +void __init smp_store_boot_cpu_info(void) +{ + int id = 0; /* CPU 0 */ + struct cpuinfo_x86 *c = &cpu_data(id); + + *c = boot_cpu_data; + c->cpu_index = id; +} + /* * The bootstrap kernel entry code has set these up. Save them for * a given CPU */ - void __cpuinit smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); *c = boot_cpu_data; c->cpu_index = id; - if (id != 0) - identify_secondary_cpu(c); + /* + * During boot time, CPU0 has this setup already. Save the info when + * bringing up AP or offlined CPU0. + */ + identify_secondary_cpu(c); } static bool __cpuinit @@ -313,7 +332,7 @@ do { \ static bool __cpuinit match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (cpu_has(c, X86_FEATURE_TOPOEXT)) { + if (cpu_has_topoext) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && @@ -481,7 +500,7 @@ void __inquire_remote_apic(int apicid) * won't ... remember to clear down the APIC, etc later. */ int __cpuinit -wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip) +wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) { unsigned long send_status, accept_status = 0; int maxlvt; @@ -489,7 +508,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip) /* Target chip */ /* Boot on the stack */ /* Kick the second */ - apic_icr_write(APIC_DM_NMI | apic->dest_logical, logical_apicid); + apic_icr_write(APIC_DM_NMI | apic->dest_logical, apicid); pr_debug("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); @@ -649,6 +668,63 @@ static void __cpuinit announce_cpu(int cpu, int apicid) node, cpu, apicid); } +static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs) +{ + int cpu; + + cpu = smp_processor_id(); + if (cpu == 0 && !cpu_online(cpu) && enable_start_cpu0) + return NMI_HANDLED; + + return NMI_DONE; +} + +/* + * Wake up AP by INIT, INIT, STARTUP sequence. + * + * Instead of waiting for STARTUP after INITs, BSP will execute the BIOS + * boot-strap code which is not a desired behavior for waking up BSP. To + * void the boot-strap code, wake up CPU0 by NMI instead. + * + * This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined + * (i.e. physically hot removed and then hot added), NMI won't wake it up. + * We'll change this code in the future to wake up hard offlined CPU0 if + * real platform and request are available. + */ +static int __cpuinit +wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, + int *cpu0_nmi_registered) +{ + int id; + int boot_error; + + /* + * Wake up AP by INIT, INIT, STARTUP sequence. + */ + if (cpu) + return wakeup_secondary_cpu_via_init(apicid, start_ip); + + /* + * Wake up BSP by nmi. + * + * Register a NMI handler to help wake up CPU0. + */ + boot_error = register_nmi_handler(NMI_LOCAL, + wakeup_cpu0_nmi, 0, "wake_cpu0"); + + if (!boot_error) { + enable_start_cpu0 = 1; + *cpu0_nmi_registered = 1; + if (apic->dest_logical == APIC_DEST_LOGICAL) + id = cpu0_logical_apicid; + else + id = apicid; + boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip); + } + + return boot_error; +} + /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. @@ -664,6 +740,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long boot_error = 0; int timeout; + int cpu0_nmi_registered = 0; /* Just in case we booted with a single CPU. */ alternatives_enable_smp(); @@ -711,13 +788,16 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) } /* - * Kick the secondary CPU. Use the method in the APIC driver - * if it's defined - or use an INIT boot APIC message otherwise: + * Wake up a CPU in difference cases: + * - Use the method in the APIC driver if it's defined + * Otherwise, + * - Use an INIT boot APIC message for APs or NMI for BSP. */ if (apic->wakeup_secondary_cpu) boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); else - boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip); + boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, + &cpu0_nmi_registered); if (!boot_error) { /* @@ -782,6 +862,13 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) */ smpboot_restore_warm_reset_vector(); } + /* + * Clean up the nmi handler. Do this after the callin and callout sync + * to avoid impact of possible long unregister time. + */ + if (cpu0_nmi_registered) + unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); + return boot_error; } @@ -795,7 +882,7 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle) pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu); - if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid || + if (apicid == BAD_APICID || !physid_isset(apicid, phys_cpu_present_map) || !apic->apic_id_valid(apicid)) { pr_err("%s: bad cpu %d\n", __func__, cpu); @@ -818,6 +905,9 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle) per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; + /* the FPU context is blank, nobody can own it */ + __cpu_disable_lazy_restore(cpu); + err = do_boot_cpu(apicid, cpu, tidle); if (err) { pr_debug("do_boot_cpu failed %d\n", err); @@ -990,7 +1080,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) /* * Setup boot CPU information */ - smp_store_cpu_info(0); /* Final full version of the data */ + smp_store_boot_cpu_info(); /* Final full version of the data */ cpumask_copy(cpu_callin_mask, cpumask_of(0)); mb(); @@ -1026,6 +1116,11 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) */ setup_local_APIC(); + if (x2apic_mode) + cpu0_logical_apicid = apic_read(APIC_LDR); + else + cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + /* * Enable IO APIC before setting up error vector */ @@ -1214,19 +1309,6 @@ void cpu_disable_common(void) int native_cpu_disable(void) { - int cpu = smp_processor_id(); - - /* - * Perhaps use cpufreq to drop frequency, but that could go - * into generic code. - * - * We won't take down the boot processor on i386 due to some - * interrupts only being able to be serviced by the BSP. - * Especially so if we're not using an IOAPIC -zwane - */ - if (cpu == 0) - return -EBUSY; - clear_local_APIC(); cpu_disable_common(); @@ -1266,6 +1348,14 @@ void play_dead_common(void) local_irq_disable(); } +static bool wakeup_cpu0(void) +{ + if (smp_processor_id() == 0 && enable_start_cpu0) + return true; + + return false; +} + /* * We need to flush the caches before going to sleep, lest we have * dirty data in our caches when we come back up. @@ -1329,6 +1419,11 @@ static inline void mwait_play_dead(void) __monitor(mwait_ptr, 0, 0); mb(); __mwait(eax, 0); + /* + * If NMI wants to wake up CPU0, start CPU0. + */ + if (wakeup_cpu0()) + start_cpu0(); } } @@ -1339,6 +1434,11 @@ static inline void hlt_play_dead(void) while (1) { native_halt(); + /* + * If NMI wants to wake up CPU0, start CPU0. + */ + if (wakeup_cpu0()) + start_cpu0(); } } diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index cd3b243..9b4d51d 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -165,10 +165,11 @@ void set_task_blockstep(struct task_struct *task, bool on) * Ensure irq/preemption can't change debugctl in between. * Note also that both TIF_BLOCKSTEP and debugctl should * be changed atomically wrt preemption. - * FIXME: this means that set/clear TIF_BLOCKSTEP is simply - * wrong if task != current, SIGKILL can wakeup the stopped - * tracee and set/clear can play with the running task, this - * can confuse the next __switch_to_xtra(). + * + * NOTE: this means that set/clear TIF_BLOCKSTEP is only safe if + * task is current or it can't be running, otherwise we can race + * with __switch_to_xtra(). We rely on ptrace_freeze_traced() but + * PTRACE_KILL is not safe. */ local_irq_disable(); debugctl = get_debugctlmsr(); diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index b4d3c39..97ef74b 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -21,37 +21,23 @@ /* * Align a virtual address to avoid aliasing in the I$ on AMD F15h. - * - * @flags denotes the allocation direction - bottomup or topdown - - * or vDSO; see call sites below. */ -unsigned long align_addr(unsigned long addr, struct file *filp, - enum align_flags flags) +static unsigned long get_align_mask(void) { - unsigned long tmp_addr; - /* handle 32- and 64-bit case with a single conditional */ if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32()))) - return addr; + return 0; if (!(current->flags & PF_RANDOMIZE)) - return addr; - - if (!((flags & ALIGN_VDSO) || filp)) - return addr; - - tmp_addr = addr; - - /* - * We need an address which is <= than the original - * one only when in topdown direction. - */ - if (!(flags & ALIGN_TOPDOWN)) - tmp_addr += va_align.mask; + return 0; - tmp_addr &= ~va_align.mask; + return va_align.mask; +} - return tmp_addr; +unsigned long align_vdso_addr(unsigned long addr) +{ + unsigned long align_mask = get_align_mask(); + return (addr + align_mask) & ~align_mask; } static int __init control_va_addr_alignment(char *str) @@ -126,7 +112,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - unsigned long start_addr; + struct vm_unmapped_area_info info; unsigned long begin, end; if (flags & MAP_FIXED) @@ -144,50 +130,16 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, (!vma || addr + len <= vma->vm_start)) return addr; } - if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32)) - && len <= mm->cached_hole_size) { - mm->cached_hole_size = 0; - mm->free_area_cache = begin; - } - addr = mm->free_area_cache; - if (addr < begin) - addr = begin; - start_addr = addr; - -full_search: - - addr = align_addr(addr, filp, 0); - - for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { - /* At this point: (!vma || addr < vma->vm_end). */ - if (end - len < addr) { - /* - * Start a new search - just in case we missed - * some holes. - */ - if (start_addr != begin) { - start_addr = addr = begin; - mm->cached_hole_size = 0; - goto full_search; - } - return -ENOMEM; - } - if (!vma || addr + len <= vma->vm_start) { - /* - * Remember the place where we stopped the search: - */ - mm->free_area_cache = addr + len; - return addr; - } - if (addr + mm->cached_hole_size < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - addr = vma->vm_end; - addr = align_addr(addr, filp, 0); - } + info.flags = 0; + info.length = len; + info.low_limit = begin; + info.high_limit = end; + info.align_mask = filp ? get_align_mask() : 0; + info.align_offset = pgoff << PAGE_SHIFT; + return vm_unmapped_area(&info); } - unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, @@ -195,7 +147,8 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; - unsigned long addr = addr0, start_addr; + unsigned long addr = addr0; + struct vm_unmapped_area_info info; /* requested length too big for entire address space */ if (len > TASK_SIZE) @@ -217,51 +170,16 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; } - /* check if free_area_cache is useful for us */ - if (len <= mm->cached_hole_size) { - mm->cached_hole_size = 0; - mm->free_area_cache = mm->mmap_base; - } - -try_again: - /* either no address requested or can't fit in requested address hole */ - start_addr = addr = mm->free_area_cache; - - if (addr < len) - goto fail; - - addr -= len; - do { - addr = align_addr(addr, filp, ALIGN_TOPDOWN); - - /* - * Lookup failure means no vma is above this address, - * else if new region fits below vma->vm_start, - * return with success: - */ - vma = find_vma(mm, addr); - if (!vma || addr+len <= vma->vm_start) - /* remember the address as a hint for next time */ - return mm->free_area_cache = addr; - - /* remember the largest hole we saw so far */ - if (addr + mm->cached_hole_size < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - - /* try just below the current vma->vm_start */ - addr = vma->vm_start-len; - } while (len < vma->vm_start); - -fail: - /* - * if hint left us with no space for the requested - * mapping then try again: - */ - if (start_addr != mm->mmap_base) { - mm->free_area_cache = mm->mmap_base; - mm->cached_hole_size = 0; - goto try_again; - } + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.low_limit = PAGE_SIZE; + info.high_limit = mm->mmap_base; + info.align_mask = filp ? get_align_mask() : 0; + info.align_offset = pgoff << PAGE_SHIFT; + addr = vm_unmapped_area(&info); + if (!(addr & ~PAGE_MASK)) + return addr; + VM_BUG_ON(addr != -ENOMEM); bottomup: /* @@ -270,14 +188,5 @@ bottomup: * can happen with large stack limits and large mmap() * allocations. */ - mm->cached_hole_size = ~0UL; - mm->free_area_cache = TASK_UNMAPPED_BASE; - addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags); - /* - * Restore the topdown base: - */ - mm->free_area_cache = mm->mmap_base; - mm->cached_hole_size = ~0UL; - - return addr; + return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); } diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 76ee977..6e60b5f 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -30,23 +30,110 @@ #include <linux/mmzone.h> #include <linux/init.h> #include <linux/smp.h> +#include <linux/irq.h> #include <asm/cpu.h> static DEFINE_PER_CPU(struct x86_cpu, cpu_devices); #ifdef CONFIG_HOTPLUG_CPU + +#ifdef CONFIG_BOOTPARAM_HOTPLUG_CPU0 +static int cpu0_hotpluggable = 1; +#else +static int cpu0_hotpluggable; +static int __init enable_cpu0_hotplug(char *str) +{ + cpu0_hotpluggable = 1; + return 1; +} + +__setup("cpu0_hotplug", enable_cpu0_hotplug); +#endif + +#ifdef CONFIG_DEBUG_HOTPLUG_CPU0 +/* + * This function offlines a CPU as early as possible and allows userspace to + * boot up without the CPU. The CPU can be onlined back by user after boot. + * + * This is only called for debugging CPU offline/online feature. + */ +int __ref _debug_hotplug_cpu(int cpu, int action) +{ + struct device *dev = get_cpu_device(cpu); + int ret; + + if (!cpu_is_hotpluggable(cpu)) + return -EINVAL; + + cpu_hotplug_driver_lock(); + + switch (action) { + case 0: + ret = cpu_down(cpu); + if (!ret) { + pr_info("CPU %u is now offline\n", cpu); + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); + } else + pr_debug("Can't offline CPU%d.\n", cpu); + break; + case 1: + ret = cpu_up(cpu); + if (!ret) + kobject_uevent(&dev->kobj, KOBJ_ONLINE); + else + pr_debug("Can't online CPU%d.\n", cpu); + break; + default: + ret = -EINVAL; + } + + cpu_hotplug_driver_unlock(); + + return ret; +} + +static int __init debug_hotplug_cpu(void) +{ + _debug_hotplug_cpu(0, 0); + return 0; +} + +late_initcall_sync(debug_hotplug_cpu); +#endif /* CONFIG_DEBUG_HOTPLUG_CPU0 */ + int __ref arch_register_cpu(int num) { + struct cpuinfo_x86 *c = &cpu_data(num); + + /* + * Currently CPU0 is only hotpluggable on Intel platforms. Other + * vendors can add hotplug support later. + */ + if (c->x86_vendor != X86_VENDOR_INTEL) + cpu0_hotpluggable = 0; + /* - * CPU0 cannot be offlined due to several - * restrictions and assumptions in kernel. This basically - * doesn't add a control file, one cannot attempt to offline - * BSP. + * Two known BSP/CPU0 dependencies: Resume from suspend/hibernate + * depends on BSP. PIC interrupts depend on BSP. * - * Also certain PCI quirks require not to enable hotplug control - * for all CPU's. + * If the BSP depencies are under control, one can tell kernel to + * enable BSP hotplug. This basically adds a control file and + * one can attempt to offline BSP. */ - if (num) + if (num == 0 && cpu0_hotpluggable) { + unsigned int irq; + /* + * We won't take down the boot processor on i386 if some + * interrupts only are able to be serviced by the BSP in PIC. + */ + for_each_active_irq(irq) { + if (!IO_APIC_IRQ(irq) && irq_has_action(irq)) { + cpu0_hotpluggable = 0; + break; + } + } + } + if (num || cpu0_hotpluggable) per_cpu(cpu_devices, num).cpu.hotpluggable = 1; return register_cpu(&per_cpu(cpu_devices, num).cpu, num); diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c new file mode 100644 index 0000000..25b9937 --- /dev/null +++ b/arch/x86/kernel/trace_clock.c @@ -0,0 +1,21 @@ +/* + * X86 trace clocks + */ +#include <asm/trace_clock.h> +#include <asm/barrier.h> +#include <asm/msr.h> + +/* + * trace_clock_x86_tsc(): A clock that is just the cycle counter. + * + * Unlike the other clocks, this is not in nanoseconds. + */ +u64 notrace trace_clock_x86_tsc(void) +{ + u64 ret; + + rdtsc_barrier(); + rdtscll(ret); + + return ret; +} diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 8276dc6..ecffca1 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -55,7 +55,7 @@ #include <asm/i387.h> #include <asm/fpu-internal.h> #include <asm/mce.h> -#include <asm/rcu.h> +#include <asm/context_tracking.h> #include <asm/mach_traps.h> @@ -69,9 +69,6 @@ asmlinkage int system_call(void); -/* Do we ignore FPU interrupts ? */ -char ignore_fpu_irq; - /* * The IDT has to be page-aligned to simplify the Pentium * F0 0F bug workaround. @@ -564,9 +561,6 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) { -#ifdef CONFIG_X86_32 - ignore_fpu_irq = 1; -#endif exception_enter(regs); math_error(regs, error_code, X86_TRAP_MF); exception_exit(regs); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cfa5d4f..06ccb50 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -77,6 +77,12 @@ unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); #endif +unsigned long long native_read_tsc(void) +{ + return __native_read_tsc(); +} +EXPORT_SYMBOL(native_read_tsc); + int check_tsc_unstable(void) { return tsc_unstable; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index aafa555..c71025b 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -478,6 +478,11 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) regs->ip = current->utask->xol_vaddr; pre_xol_rip_insn(auprobe, regs, autask); + autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); + regs->flags |= X86_EFLAGS_TF; + if (test_tsk_thread_flag(current, TIF_BLOCKSTEP)) + set_task_blockstep(current, false); + return 0; } @@ -603,6 +608,16 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) if (auprobe->fixups & UPROBE_FIX_CALL) result = adjust_ret_addr(regs->sp, correction); + /* + * arch_uprobe_pre_xol() doesn't save the state of TIF_BLOCKSTEP + * so we can get an extra SIGTRAP if we do not clear TF. We need + * to examine the opcode to make it right. + */ + if (utask->autask.saved_tf) + send_sig(SIGTRAP, current, 0); + else if (!(auprobe->fixups & UPROBE_FIX_SETF)) + regs->flags &= ~X86_EFLAGS_TF; + return result; } @@ -647,6 +662,10 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) current->thread.trap_nr = utask->autask.saved_trap_nr; handle_riprel_post_xol(auprobe, regs, NULL); instruction_pointer_set(regs, utask->vaddr); + + /* clear TF if it was set by us in arch_uprobe_pre_xol() */ + if (!utask->autask.saved_tf) + regs->flags &= ~X86_EFLAGS_TF; } /* @@ -676,38 +695,3 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) send_sig(SIGTRAP, current, 0); return ret; } - -void arch_uprobe_enable_step(struct arch_uprobe *auprobe) -{ - struct task_struct *task = current; - struct arch_uprobe_task *autask = &task->utask->autask; - struct pt_regs *regs = task_pt_regs(task); - - autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); - - regs->flags |= X86_EFLAGS_TF; - if (test_tsk_thread_flag(task, TIF_BLOCKSTEP)) - set_task_blockstep(task, false); -} - -void arch_uprobe_disable_step(struct arch_uprobe *auprobe) -{ - struct task_struct *task = current; - struct arch_uprobe_task *autask = &task->utask->autask; - bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED); - struct pt_regs *regs = task_pt_regs(task); - /* - * The state of TIF_BLOCKSTEP was not saved so we can get an extra - * SIGTRAP if we do not clear TF. We need to examine the opcode to - * make it right. - */ - if (unlikely(trapped)) { - if (!autask->saved_tf) - regs->flags &= ~X86_EFLAGS_TF; - } else { - if (autask->saved_tf) - send_sig(SIGTRAP, task, 0); - else if (!(auprobe->fixups & UPROBE_FIX_SETF)) - regs->flags &= ~X86_EFLAGS_TF; - } -} diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 5c9687b..1dfe69c 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -182,7 +182,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); - split_huge_page_pmd(mm, pmd); + split_huge_page_pmd_mm(mm, 0xA0000, pmd); if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 3a3e8c9..9a907a6 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -145,19 +145,6 @@ static int addr_to_vsyscall_nr(unsigned long addr) return nr; } -#ifdef CONFIG_SECCOMP -static int vsyscall_seccomp(struct task_struct *tsk, int syscall_nr) -{ - if (!seccomp_mode(&tsk->seccomp)) - return 0; - task_pt_regs(tsk)->orig_ax = syscall_nr; - task_pt_regs(tsk)->ax = syscall_nr; - return __secure_computing(syscall_nr); -} -#else -#define vsyscall_seccomp(_tsk, _nr) 0 -#endif - static bool write_ok_or_segv(unsigned long ptr, size_t size) { /* @@ -190,10 +177,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) { struct task_struct *tsk; unsigned long caller; - int vsyscall_nr; + int vsyscall_nr, syscall_nr, tmp; int prev_sig_on_uaccess_error; long ret; - int skip; /* * No point in checking CS -- the only way to get here is a user mode @@ -225,56 +211,84 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) } tsk = current; - /* - * With a real vsyscall, page faults cause SIGSEGV. We want to - * preserve that behavior to make writing exploits harder. - */ - prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error; - current_thread_info()->sig_on_uaccess_error = 1; /* + * Check for access_ok violations and find the syscall nr. + * * NULL is a valid user pointer (in the access_ok sense) on 32-bit and * 64-bit, so we don't need to special-case it here. For all the * vsyscalls, NULL means "don't write anything" not "write it at * address 0". */ - ret = -EFAULT; - skip = 0; switch (vsyscall_nr) { case 0: - skip = vsyscall_seccomp(tsk, __NR_gettimeofday); - if (skip) - break; - if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) || - !write_ok_or_segv(regs->si, sizeof(struct timezone))) - break; + !write_ok_or_segv(regs->si, sizeof(struct timezone))) { + ret = -EFAULT; + goto check_fault; + } + + syscall_nr = __NR_gettimeofday; + break; + + case 1: + if (!write_ok_or_segv(regs->di, sizeof(time_t))) { + ret = -EFAULT; + goto check_fault; + } + + syscall_nr = __NR_time; + break; + + case 2: + if (!write_ok_or_segv(regs->di, sizeof(unsigned)) || + !write_ok_or_segv(regs->si, sizeof(unsigned))) { + ret = -EFAULT; + goto check_fault; + } + + syscall_nr = __NR_getcpu; + break; + } + + /* + * Handle seccomp. regs->ip must be the original value. + * See seccomp_send_sigsys and Documentation/prctl/seccomp_filter.txt. + * + * We could optimize the seccomp disabled case, but performance + * here doesn't matter. + */ + regs->orig_ax = syscall_nr; + regs->ax = -ENOSYS; + tmp = secure_computing(syscall_nr); + if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { + warn_bad_vsyscall(KERN_DEBUG, regs, + "seccomp tried to change syscall nr or ip"); + do_exit(SIGSYS); + } + if (tmp) + goto do_ret; /* skip requested */ + /* + * With a real vsyscall, page faults cause SIGSEGV. We want to + * preserve that behavior to make writing exploits harder. + */ + prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error; + current_thread_info()->sig_on_uaccess_error = 1; + + ret = -EFAULT; + switch (vsyscall_nr) { + case 0: ret = sys_gettimeofday( (struct timeval __user *)regs->di, (struct timezone __user *)regs->si); break; case 1: - skip = vsyscall_seccomp(tsk, __NR_time); - if (skip) - break; - - if (!write_ok_or_segv(regs->di, sizeof(time_t))) - break; - ret = sys_time((time_t __user *)regs->di); break; case 2: - skip = vsyscall_seccomp(tsk, __NR_getcpu); - if (skip) - break; - - if (!write_ok_or_segv(regs->di, sizeof(unsigned)) || - !write_ok_or_segv(regs->si, sizeof(unsigned))) - break; - ret = sys_getcpu((unsigned __user *)regs->di, (unsigned __user *)regs->si, NULL); @@ -283,12 +297,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error; - if (skip) { - if ((long)regs->ax <= 0L) /* seccomp errno emulation */ - goto do_ret; - goto done; /* seccomp trace/trap */ - } - +check_fault: if (ret == -EFAULT) { /* Bad news -- userspace fed a bad pointer to a vsyscall. */ warn_bad_vsyscall(KERN_INFO, regs, @@ -311,7 +320,6 @@ do_ret: /* Emulate a ret instruction. */ regs->ip = caller; regs->sp += 8; -done: return true; sigsegv: |
