diff options
Diffstat (limited to 'arch/x86/kernel')
68 files changed, 2348 insertions, 1105 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 5369059c07a..532d2e090e6 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -69,6 +69,7 @@ obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_OPTPROBES) += kprobes-opt.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o obj-$(CONFIG_KGDB) += kgdb.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index ce664f33ea8..406ed77216d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -593,7 +593,7 @@ void __init acpi_set_irq_model_ioapic(void) #ifdef CONFIG_ACPI_HOTPLUG_CPU #include <acpi/processor.h> -static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +static void __cpuinitdata acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA int nid; diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 8c3cdded6f2..359b6899a36 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -180,6 +180,7 @@ static struct apic apic_flat = { .name = "flat", .probe = flat_probe, .acpi_madt_oem_check = flat_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = flat_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, @@ -337,6 +338,7 @@ static struct apic apic_physflat = { .name = "physical flat", .probe = physflat_probe, .acpi_madt_oem_check = physflat_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = flat_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 775b82bc655..634ae6cdd5c 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -124,6 +124,7 @@ struct apic apic_noop = { .probe = noop_probe, .acpi_madt_oem_check = NULL, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = noop_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 09d3d8c1cd9..d9ea5f331ac 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -56,6 +56,12 @@ static unsigned int read_xapic_id(void) return get_apic_id(apic_read(APIC_ID)); } +static int numachip_apic_id_valid(int apicid) +{ + /* Trust what bootloader passes in MADT */ + return 1; +} + static int numachip_apic_id_registered(void) { return physid_isset(read_xapic_id(), phys_cpu_present_map); @@ -223,10 +229,11 @@ static int __init numachip_system_init(void) } early_initcall(numachip_system_init); -static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static int __cpuinit numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { if (!strncmp(oem_id, "NUMASC", 6)) { numachip_system = 1; + setup_force_cpu_cap(X86_FEATURE_X2APIC); return 1; } @@ -238,6 +245,7 @@ static struct apic apic_numachip __refconst = { .name = "NumaConnect system", .probe = numachip_probe, .acpi_madt_oem_check = numachip_acpi_madt_oem_check, + .apic_id_valid = numachip_apic_id_valid, .apic_id_registered = numachip_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 521bead0113..0cdec7065af 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -198,6 +198,7 @@ static struct apic apic_bigsmp = { .name = "bigsmp", .probe = probe_bigsmp, .acpi_madt_oem_check = NULL, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = bigsmp_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 5d513bc47b6..e42d1d3b913 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -625,6 +625,7 @@ static struct apic __refdata apic_es7000_cluster = { .name = "es7000", .probe = probe_es7000, .acpi_madt_oem_check = es7000_acpi_madt_oem_check_cluster, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = es7000_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, @@ -690,6 +691,7 @@ static struct apic __refdata apic_es7000 = { .name = "es7000", .probe = probe_es7000, .acpi_madt_oem_check = es7000_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = es7000_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index fb072754bc1..6d10a66fc5a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3967,18 +3967,36 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi) static __init int bad_ioapic(unsigned long address) { if (nr_ioapics >= MAX_IO_APICS) { - printk(KERN_WARNING "WARNING: Max # of I/O APICs (%d) exceeded " - "(found %d), skipping\n", MAX_IO_APICS, nr_ioapics); + pr_warn("WARNING: Max # of I/O APICs (%d) exceeded (found %d), skipping\n", + MAX_IO_APICS, nr_ioapics); return 1; } if (!address) { - printk(KERN_WARNING "WARNING: Bogus (zero) I/O APIC address" - " found in table, skipping!\n"); + pr_warn("WARNING: Bogus (zero) I/O APIC address found in table, skipping!\n"); return 1; } return 0; } +static __init int bad_ioapic_register(int idx) +{ + union IO_APIC_reg_00 reg_00; + union IO_APIC_reg_01 reg_01; + union IO_APIC_reg_02 reg_02; + + reg_00.raw = io_apic_read(idx, 0); + reg_01.raw = io_apic_read(idx, 1); + reg_02.raw = io_apic_read(idx, 2); + + if (reg_00.raw == -1 && reg_01.raw == -1 && reg_02.raw == -1) { + pr_warn("I/O APIC 0x%x registers return all ones, skipping!\n", + mpc_ioapic_addr(idx)); + return 1; + } + + return 0; +} + void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) { int idx = 0; @@ -3995,6 +4013,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) ioapics[idx].mp_config.apicaddr = address; set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); + + if (bad_ioapic_register(idx)) { + clear_fixmap(FIX_IO_APIC_BASE_0 + idx); + return; + } + ioapics[idx].mp_config.apicid = io_apic_unique_id(id); ioapics[idx].mp_config.apicver = io_apic_get_version(idx); @@ -4015,10 +4039,10 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) if (gsi_cfg->gsi_end >= gsi_top) gsi_top = gsi_cfg->gsi_end + 1; - printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, " - "GSI %d-%d\n", idx, mpc_ioapic_id(idx), - mpc_ioapic_ver(idx), mpc_ioapic_addr(idx), - gsi_cfg->gsi_base, gsi_cfg->gsi_end); + pr_info("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, GSI %d-%d\n", + idx, mpc_ioapic_id(idx), + mpc_ioapic_ver(idx), mpc_ioapic_addr(idx), + gsi_cfg->gsi_base, gsi_cfg->gsi_end); nr_ioapics++; } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index c4a61ca1349..00d2422ca7c 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -478,6 +478,7 @@ static struct apic __refdata apic_numaq = { .name = "NUMAQ", .probe = probe_numaq, .acpi_madt_oem_check = NULL, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = numaq_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 0787bb3412f..ff2c1b9aac4 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -92,6 +92,7 @@ static struct apic apic_default = { .name = "default", .probe = probe_default, .acpi_madt_oem_check = NULL, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = default_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 19114423c58..fea000b27f0 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -496,6 +496,7 @@ static struct apic apic_summit = { .name = "summit", .probe = probe_summit, .acpi_madt_oem_check = summit_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = summit_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 50079587582..9193713060a 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -213,6 +213,7 @@ static struct apic apic_x2apic_cluster = { .name = "cluster x2apic", .probe = x2apic_cluster_probe, .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = x2apic_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index f5373dfde21..bcd1db6eaca 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -119,6 +119,7 @@ static struct apic apic_x2apic_phys = { .name = "physical x2apic", .probe = x2apic_phys_probe, .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = x2apic_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 79b05b88aa1..fc477142585 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -351,6 +351,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .name = "UV large system", .probe = uv_probe, .acpi_madt_oem_check = uv_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = uv_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index f76623cbe26..5d56931a15b 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1234,8 +1234,7 @@ static int suspend(int vetoable) struct apm_user *as; dpm_suspend_start(PMSG_SUSPEND); - - dpm_suspend_noirq(PMSG_SUSPEND); + dpm_suspend_end(PMSG_SUSPEND); local_irq_disable(); syscore_suspend(); @@ -1259,9 +1258,9 @@ static int suspend(int vetoable) syscore_resume(); local_irq_enable(); - dpm_resume_noirq(PMSG_RESUME); - + dpm_resume_start(PMSG_RESUME); dpm_resume_end(PMSG_RESUME); + queue_event(APM_NORMAL_RESUME, NULL); spin_lock(&user_list_lock); for (as = user_list; as != NULL; as = as->next) { @@ -1277,7 +1276,7 @@ static void standby(void) { int err; - dpm_suspend_noirq(PMSG_SUSPEND); + dpm_suspend_end(PMSG_SUSPEND); local_irq_disable(); syscore_suspend(); @@ -1291,7 +1290,7 @@ static void standby(void) syscore_resume(); local_irq_enable(); - dpm_resume_noirq(PMSG_RESUME); + dpm_resume_start(PMSG_RESUME); } static apm_event_t get_event(void) diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 25f24dccdcf..6ab6aa2fdfd 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -16,6 +16,7 @@ obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += proc.o capflags.o powerflags.o common.o obj-y += vmware.o hypervisor.o sched.o mshyperv.o obj-y += rdrand.o +obj-y += match.o obj-$(CONFIG_X86_32) += bugs.o obj-$(CONFIG_X86_64) += bugs_64.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f4773f4aae3..0a44b90602b 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -5,6 +5,7 @@ #include <linux/mm.h> #include <linux/io.h> +#include <linux/sched.h> #include <asm/processor.h> #include <asm/apic.h> #include <asm/cpu.h> @@ -456,6 +457,8 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); + if (!check_tsc_unstable()) + sched_clock_stable = 1; } #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d43cad74f16..e49477444ff 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -18,6 +18,7 @@ #include <asm/archrandom.h> #include <asm/hypervisor.h> #include <asm/processor.h> +#include <asm/debugreg.h> #include <asm/sections.h> #include <linux/topology.h> #include <linux/cpumask.h> @@ -28,6 +29,7 @@ #include <asm/apic.h> #include <asm/desc.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/mtrr.h> #include <linux/numa.h> #include <asm/asm.h> @@ -933,7 +935,7 @@ static const struct msr_range msr_range_array[] __cpuinitconst = { { 0xc0011000, 0xc001103b}, }; -static void __cpuinit print_cpu_msr(void) +static void __cpuinit __print_cpu_msr(void) { unsigned index_min, index_max; unsigned index; @@ -997,13 +999,13 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) else printk(KERN_CONT "\n"); -#ifdef CONFIG_SMP + __print_cpu_msr(); +} + +void __cpuinit print_cpu_msr(struct cpuinfo_x86 *c) +{ if (c->cpu_index < show_msr) - print_cpu_msr(); -#else - if (show_msr) - print_cpu_msr(); -#endif + __print_cpu_msr(); } static __init int setup_disablecpuid(char *arg) @@ -1044,6 +1046,8 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) = DEFINE_PER_CPU(unsigned int, irq_count) = -1; +DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); + /* * Special IST stacks which the CPU switches to when it calls * an IST-marked descriptor entry. Up to 7 stacks (hardware @@ -1111,6 +1115,7 @@ void debug_stack_reset(void) DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); +DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); #ifdef CONFIG_CC_STACKPROTECTOR DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 6b45e5e7a90..73d08ed98a6 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -326,8 +326,7 @@ static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb) l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1; } -static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, - int index) +static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) { int node; @@ -725,14 +724,16 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info); #define CPUID4_INFO_IDX(x, y) (&((per_cpu(ici_cpuid4_info, x))[y])) #ifdef CONFIG_SMP -static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) + +static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) { - struct _cpuid4_info *this_leaf, *sibling_leaf; - unsigned long num_threads_sharing; - int index_msb, i, sibling; + struct _cpuid4_info *this_leaf; + int ret, i, sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); - if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) { + ret = 0; + if (index == 3) { + ret = 1; for_each_cpu(i, cpu_llc_shared_mask(cpu)) { if (!per_cpu(ici_cpuid4_info, i)) continue; @@ -743,8 +744,35 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) set_bit(sibling, this_leaf->shared_cpu_map); } } - return; + } else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) { + ret = 1; + for_each_cpu(i, cpu_sibling_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)) { + if (!cpu_online(sibling)) + continue; + set_bit(sibling, this_leaf->shared_cpu_map); + } + } } + + return ret; +} + +static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) +{ + struct _cpuid4_info *this_leaf, *sibling_leaf; + unsigned long num_threads_sharing; + int index_msb, i; + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86_vendor == X86_VENDOR_AMD) { + if (cache_shared_amd_cpu_map_setup(cpu, index)) + return; + } + this_leaf = CPUID4_INFO_IDX(cpu, index); num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing; diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c new file mode 100644 index 00000000000..5502b289341 --- /dev/null +++ b/arch/x86/kernel/cpu/match.c @@ -0,0 +1,91 @@ +#include <asm/cpu_device_id.h> +#include <asm/processor.h> +#include <linux/cpu.h> +#include <linux/module.h> +#include <linux/slab.h> + +/** + * x86_match_cpu - match current CPU again an array of x86_cpu_ids + * @match: Pointer to array of x86_cpu_ids. Last entry terminated with + * {}. + * + * Return the entry if the current CPU matches the entries in the + * passed x86_cpu_id match table. Otherwise NULL. The match table + * contains vendor (X86_VENDOR_*), family, model and feature bits or + * respective wildcard entries. + * + * A typical table entry would be to match a specific CPU + * { X86_VENDOR_INTEL, 6, 0x12 } + * or to match a specific CPU feature + * { X86_FEATURE_MATCH(X86_FEATURE_FOOBAR) } + * + * Fields can be wildcarded with %X86_VENDOR_ANY, %X86_FAMILY_ANY, + * %X86_MODEL_ANY, %X86_FEATURE_ANY or 0 (except for vendor) + * + * Arrays used to match for this should also be declared using + * MODULE_DEVICE_TABLE(x86_cpu, ...) + * + * This always matches against the boot cpu, assuming models and features are + * consistent over all CPUs. + */ +const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) +{ + const struct x86_cpu_id *m; + struct cpuinfo_x86 *c = &boot_cpu_data; + + for (m = match; m->vendor | m->family | m->model | m->feature; m++) { + if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) + continue; + if (m->family != X86_FAMILY_ANY && c->x86 != m->family) + continue; + if (m->model != X86_MODEL_ANY && c->x86_model != m->model) + continue; + if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature)) + continue; + return m; + } + return NULL; +} +EXPORT_SYMBOL(x86_match_cpu); + +ssize_t arch_print_cpu_modalias(struct device *dev, + struct device_attribute *attr, + char *bufptr) +{ + int size = PAGE_SIZE; + int i, n; + char *buf = bufptr; + + n = snprintf(buf, size, "x86cpu:vendor:%04X:family:%04X:" + "model:%04X:feature:", + boot_cpu_data.x86_vendor, + boot_cpu_data.x86, + boot_cpu_data.x86_model); + size -= n; + buf += n; + size -= 1; + for (i = 0; i < NCAPINTS*32; i++) { + if (boot_cpu_has(i)) { + n = snprintf(buf, size, ",%04X", i); + if (n >= size) { + WARN(1, "x86 features overflow page\n"); + break; + } + size -= n; + buf += n; + } + } + *buf++ = '\n'; + return buf - bufptr; +} + +int arch_cpu_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (buf) { + arch_print_cpu_modalias(NULL, NULL, buf); + add_uevent_var(env, "MODALIAS=%s", buf); + kfree(buf); + } + return 0; +} diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 7395d5f4272..0c82091b165 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -54,7 +54,14 @@ static struct severity { #define MASK(x, y) .mask = x, .result = y #define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S) #define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR) +#define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV) #define MCACOD 0xffff +/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ +#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ +#define MCACOD_SCRUBMSK 0xfff0 +#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ +#define MCACOD_DATA 0x0134 /* Data Load */ +#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ MCESEV( NO, "Invalid", @@ -102,11 +109,24 @@ static struct severity { SER, BITCLR(MCI_STATUS_S) ), - /* AR add known MCACODs here */ MCESEV( PANIC, "Action required with lost events", SER, BITSET(MCI_STATUS_OVER|MCI_UC_SAR) ), + + /* known AR MCACODs: */ +#ifdef CONFIG_MEMORY_FAILURE + MCESEV( + KEEP, "HT thread notices Action required: data load error", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + MCGMASK(MCG_STATUS_EIPV, 0) + ), + MCESEV( + AR, "Action required: data load error", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + USER + ), +#endif MCESEV( PANIC, "Action required: unknown MCACOD", SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_SAR) @@ -115,11 +135,11 @@ static struct severity { /* known AO MCACODs: */ MCESEV( AO, "Action optional: memory scrubbing error", - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|0xfff0, MCI_UC_S|0x00c0) + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD_SCRUBMSK, MCI_UC_S|MCACOD_SCRUB) ), MCESEV( AO, "Action optional: last level cache writeback error", - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|0x017a) + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|MCACOD_L3WB) ), MCESEV( SOME, "Action optional: unknown MCACOD", diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 5a11ae2e9e9..d086a09c087 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -191,7 +191,7 @@ static void drain_mcelog_buffer(void) { unsigned int next, i, prev = 0; - next = rcu_dereference_check_mce(mcelog.next); + next = ACCESS_ONCE(mcelog.next); do { struct mce *m; @@ -540,6 +540,27 @@ static void mce_report_event(struct pt_regs *regs) irq_work_queue(&__get_cpu_var(mce_irq_work)); } +/* + * Read ADDR and MISC registers. + */ +static void mce_read_aux(struct mce *m, int i) +{ + if (m->status & MCI_STATUS_MISCV) + m->misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i)); + if (m->status & MCI_STATUS_ADDRV) { + m->addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i)); + + /* + * Mask the reported address by the reported granularity. + */ + if (mce_ser && (m->status & MCI_STATUS_MISCV)) { + u8 shift = MCI_MISC_ADDR_LSB(m->misc); + m->addr >>= shift; + m->addr <<= shift; + } + } +} + DEFINE_PER_CPU(unsigned, mce_poll_count); /* @@ -590,10 +611,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) (m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; - if (m.status & MCI_STATUS_MISCV) - m.misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i)); - if (m.status & MCI_STATUS_ADDRV) - m.addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i)); + mce_read_aux(&m, i); if (!(flags & MCP_TIMESTAMP)) m.tsc = 0; @@ -917,6 +935,49 @@ static void mce_clear_state(unsigned long *toclear) } /* + * Need to save faulting physical address associated with a process + * in the machine check handler some place where we can grab it back + * later in mce_notify_process() + */ +#define MCE_INFO_MAX 16 + +struct mce_info { + atomic_t inuse; + struct task_struct *t; + __u64 paddr; +} mce_info[MCE_INFO_MAX]; + +static void mce_save_info(__u64 addr) +{ + struct mce_info *mi; + + for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) { + if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) { + mi->t = current; + mi->paddr = addr; + return; + } + } + + mce_panic("Too many concurrent recoverable errors", NULL, NULL); +} + +static struct mce_info *mce_find_info(void) +{ + struct mce_info *mi; + + for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) + if (atomic_read(&mi->inuse) && mi->t == current) + return mi; + return NULL; +} + +static void mce_clear_info(struct mce_info *mi) +{ + atomic_set(&mi->inuse, 0); +} + +/* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. * @@ -969,7 +1030,9 @@ void do_machine_check(struct pt_regs *regs, long error_code) barrier(); /* - * When no restart IP must always kill or panic. + * When no restart IP might need to kill or panic. + * Assume the worst for now, but if we find the + * severity is MCE_AR_SEVERITY we have other options. */ if (!(m.mcgstatus & MCG_STATUS_RIPV)) kill_it = 1; @@ -1023,16 +1086,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) continue; } - /* - * Kill on action required. - */ - if (severity == MCE_AR_SEVERITY) - kill_it = 1; - - if (m.status & MCI_STATUS_MISCV) - m.misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i)); - if (m.status & MCI_STATUS_ADDRV) - m.addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i)); + mce_read_aux(&m, i); /* * Action optional error. Queue address for later processing. @@ -1052,6 +1106,9 @@ void do_machine_check(struct pt_regs *regs, long error_code) } } + /* mce_clear_state will clear *final, save locally for use later */ + m = *final; + if (!no_way_out) mce_clear_state(toclear); @@ -1063,27 +1120,22 @@ void do_machine_check(struct pt_regs *regs, long error_code) no_way_out = worst >= MCE_PANIC_SEVERITY; /* - * If we have decided that we just CAN'T continue, and the user - * has not set tolerant to an insane level, give up and die. - * - * This is mainly used in the case when the system doesn't - * support MCE broadcasting or it has been disabled. - */ - if (no_way_out && tolerant < 3) - mce_panic("Fatal machine check on current CPU", final, msg); - - /* - * If the error seems to be unrecoverable, something should be - * done. Try to kill as little as possible. If we can kill just - * one task, do that. If the user has set the tolerance very - * high, don't try to do anything at all. + * At insane "tolerant" levels we take no action. Otherwise + * we only die if we have no other choice. For less serious + * issues we try to recover, or limit damage to the current + * process. */ - - if (kill_it && tolerant < 3) - force_sig(SIGBUS, current); - - /* notify userspace ASAP */ - set_thread_flag(TIF_MCE_NOTIFY); + if (tolerant < 3) { + if (no_way_out) + mce_panic("Fatal machine check on current CPU", &m, msg); + if (worst == MCE_AR_SEVERITY) { + /* schedule action before return to userland */ + mce_save_info(m.addr); + set_thread_flag(TIF_MCE_NOTIFY); + } else if (kill_it) { + force_sig(SIGBUS, current); + } + } if (worst > 0) mce_report_event(regs); @@ -1094,34 +1146,57 @@ out: } EXPORT_SYMBOL_GPL(do_machine_check); -/* dummy to break dependency. actual code is in mm/memory-failure.c */ -void __attribute__((weak)) memory_failure(unsigned long pfn, int vector) +#ifndef CONFIG_MEMORY_FAILURE +int memory_failure(unsigned long pfn, int vector, int flags) { - printk(KERN_ERR "Action optional memory failure at %lx ignored\n", pfn); + /* mce_severity() should not hand us an ACTION_REQUIRED error */ + BUG_ON(flags & MF_ACTION_REQUIRED); + printk(KERN_ERR "Uncorrected memory error in page 0x%lx ignored\n" + "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", pfn); + + return 0; } +#endif /* - * Called after mce notification in process context. This code - * is allowed to sleep. Call the high level VM handler to process - * any corrupted pages. - * Assume that the work queue code only calls this one at a time - * per CPU. - * Note we don't disable preemption, so this code might run on the wrong - * CPU. In this case the event is picked up by the scheduled work queue. - * This is merely a fast path to expedite processing in some common - * cases. + * Called in process context that interrupted by MCE and marked with + * TIF_MCE_NOTIFY, just before returning to erroneous userland. + * This code is allowed to sleep. + * Attempt possible recovery such as calling the high level VM handler to + * process any corrupted pages, and kill/signal current process if required. + * Action required errors are handled here. */ void mce_notify_process(void) { unsigned long pfn; - mce_notify_irq(); - while (mce_ring_get(&pfn)) - memory_failure(pfn, MCE_VECTOR); + struct mce_info *mi = mce_find_info(); + + if (!mi) + mce_panic("Lost physical address for unconsumed uncorrectable error", NULL, NULL); + pfn = mi->paddr >> PAGE_SHIFT; + + clear_thread_flag(TIF_MCE_NOTIFY); + + pr_err("Uncorrected hardware memory error in user-access at %llx", + mi->paddr); + if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) { + pr_err("Memory error not recovered"); + force_sig(SIGBUS, current); + } + mce_clear_info(mi); } +/* + * Action optional processing happens here (picking up + * from the list of faulting pages that do_machine_check() + * placed into the "ring"). + */ static void mce_process_work(struct work_struct *dummy) { - mce_notify_process(); + unsigned long pfn; + + while (mce_ring_get(&pfn)) + memory_failure(pfn, MCE_VECTOR, 0); } #ifdef CONFIG_X86_MCE_INTEL @@ -1211,8 +1286,6 @@ int mce_notify_irq(void) /* Not more than two messages every minute */ static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); - clear_thread_flag(TIF_MCE_NOTIFY); - if (test_and_clear_bit(0, &mce_need_notify)) { /* wake processes polling /dev/mcelog */ wake_up_interruptible(&mce_chrdev_wait); @@ -1541,6 +1614,12 @@ static int __mce_read_apei(char __user **ubuf, size_t usize) /* Error or no more MCE record */ if (rc <= 0) { mce_apei_read_done = 1; + /* + * When ERST is disabled, mce_chrdev_read() should return + * "no record" instead of "no device." + */ + if (rc == -ENODEV) + return 0; return rc; } rc = -EFAULT; @@ -1859,7 +1938,7 @@ static struct bus_type mce_subsys = { .dev_name = "machinecheck", }; -struct device *mce_device[CONFIG_NR_CPUS]; +DEFINE_PER_CPU(struct device *, mce_device); __cpuinitdata void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); @@ -2038,7 +2117,7 @@ static __cpuinit int mce_device_create(unsigned int cpu) goto error2; } cpumask_set_cpu(cpu, mce_device_initialized); - mce_device[cpu] = dev; + per_cpu(mce_device, cpu) = dev; return 0; error2: @@ -2055,7 +2134,7 @@ error: static __cpuinit void mce_device_remove(unsigned int cpu) { - struct device *dev = mce_device[cpu]; + struct device *dev = per_cpu(mce_device, cpu); int i; if (!cpumask_test_cpu(cpu, mce_device_initialized)) @@ -2069,7 +2148,7 @@ static __cpuinit void mce_device_remove(unsigned int cpu) device_unregister(dev); cpumask_clear_cpu(cpu, mce_device_initialized); - mce_device[cpu] = NULL; + per_cpu(mce_device, cpu) = NULL; } /* Make sure there are no machine checks on offlined CPUs. */ diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 786e76a8632..99b57179f91 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -523,11 +523,12 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) { int i, err = 0; struct threshold_bank *b = NULL; - struct device *dev = mce_device[cpu]; + struct device *dev = per_cpu(mce_device, cpu); char name[32]; sprintf(name, "threshold_bank%i", bank); +#ifdef CONFIG_SMP if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ i = cpumask_first(cpu_llc_shared_mask(cpu)); @@ -553,6 +554,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out; } +#endif b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL); if (!b) { @@ -585,7 +587,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (i == cpu) continue; - dev = mce_device[i]; + dev = per_cpu(mce_device, i); if (dev) err = sysfs_create_link(&dev->kobj,b->kobj, name); if (err) @@ -665,7 +667,8 @@ static void threshold_remove_bank(unsigned int cpu, int bank) #ifdef CONFIG_SMP /* sibling symlink */ if (shared_bank[bank] && b->blocks->cpu != cpu) { - sysfs_remove_link(&mce_device[cpu]->kobj, name); + dev = per_cpu(mce_device, cpu); + sysfs_remove_link(&dev->kobj, name); per_cpu(threshold_banks, cpu)[bank] = NULL; return; @@ -677,7 +680,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) if (i == cpu) continue; - dev = mce_device[i]; + dev = per_cpu(mce_device, i); if (dev) sysfs_remove_link(&dev->kobj, name); per_cpu(threshold_banks, i)[bank] = NULL; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 5adce1040b1..fa2900c0e39 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -24,6 +24,7 @@ #include <linux/slab.h> #include <linux/cpu.h> #include <linux/bitops.h> +#include <linux/device.h> #include <asm/apic.h> #include <asm/stacktrace.h> @@ -31,6 +32,7 @@ #include <asm/compat.h> #include <asm/smp.h> #include <asm/alternative.h> +#include <asm/timer.h> #include "perf_event.h" @@ -351,6 +353,36 @@ int x86_setup_perfctr(struct perf_event *event) return 0; } +/* + * check that branch_sample_type is compatible with + * settings needed for precise_ip > 1 which implies + * using the LBR to capture ALL taken branches at the + * priv levels of the measurement + */ +static inline int precise_br_compat(struct perf_event *event) +{ + u64 m = event->attr.branch_sample_type; + u64 b = 0; + + /* must capture all branches */ + if (!(m & PERF_SAMPLE_BRANCH_ANY)) + return 0; + + m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER; + + if (!event->attr.exclude_user) + b |= PERF_SAMPLE_BRANCH_USER; + + if (!event->attr.exclude_kernel) + b |= PERF_SAMPLE_BRANCH_KERNEL; + + /* + * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86 + */ + + return m == b; +} + int x86_pmu_hw_config(struct perf_event *event) { if (event->attr.precise_ip) { @@ -367,6 +399,36 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip > precise) return -EOPNOTSUPP; + /* + * check that PEBS LBR correction does not conflict with + * whatever the user is asking with attr->branch_sample_type + */ + if (event->attr.precise_ip > 1) { + u64 *br_type = &event->attr.branch_sample_type; + + if (has_branch_stack(event)) { + if (!precise_br_compat(event)) + return -EOPNOTSUPP; + + /* branch_sample_type is compatible */ + + } else { + /* + * user did not specify branch_sample_type + * + * For PEBS fixups, we capture all + * the branches at the priv level of the + * event. + */ + *br_type = PERF_SAMPLE_BRANCH_ANY; + + if (!event->attr.exclude_user) + *br_type |= PERF_SAMPLE_BRANCH_USER; + + if (!event->attr.exclude_kernel) + *br_type |= PERF_SAMPLE_BRANCH_KERNEL; + } + } } /* @@ -424,6 +486,10 @@ static int __x86_pmu_event_init(struct perf_event *event) /* mark unused */ event->hw.extra_reg.idx = EXTRA_REG_NONE; + /* mark not used */ + event->hw.extra_reg.idx = EXTRA_REG_NONE; + event->hw.branch_reg.idx = EXTRA_REG_NONE; + return x86_pmu.hw_config(event); } @@ -577,14 +643,14 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) /* Prefer fixed purpose counters */ if (x86_pmu.num_counters_fixed) { idx = X86_PMC_IDX_FIXED; - for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_MAX) { + for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; } } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; - for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_FIXED) { + for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_FIXED) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; } @@ -1210,6 +1276,8 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) break; case CPU_STARTING: + if (x86_pmu.attr_rdpmc) + set_in_cr4(X86_CR4_PCE); if (x86_pmu.cpu_starting) x86_pmu.cpu_starting(cpu); break; @@ -1319,6 +1387,8 @@ static int __init init_hw_perf_events(void) } } + x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ + 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); @@ -1542,23 +1612,106 @@ static int x86_pmu_event_init(struct perf_event *event) return err; } +static int x86_pmu_event_idx(struct perf_event *event) +{ + int idx = event->hw.idx; + + if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) { + idx -= X86_PMC_IDX_FIXED; + idx |= 1 << 30; + } + + return idx + 1; +} + +static ssize_t get_attr_rdpmc(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc); +} + +static void change_rdpmc(void *info) +{ + bool enable = !!(unsigned long)info; + + if (enable) + set_in_cr4(X86_CR4_PCE); + else + clear_in_cr4(X86_CR4_PCE); +} + +static ssize_t set_attr_rdpmc(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val = simple_strtoul(buf, NULL, 0); + + if (!!val != !!x86_pmu.attr_rdpmc) { + x86_pmu.attr_rdpmc = !!val; + smp_call_function(change_rdpmc, (void *)val, 1); + } + + return count; +} + +static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc); + +static struct attribute *x86_pmu_attrs[] = { + &dev_attr_rdpmc.attr, + NULL, +}; + +static struct attribute_group x86_pmu_attr_group = { + .attrs = x86_pmu_attrs, +}; + +static const struct attribute_group *x86_pmu_attr_groups[] = { + &x86_pmu_attr_group, + NULL, +}; + +static void x86_pmu_flush_branch_stack(void) +{ + if (x86_pmu.flush_branch_stack) + x86_pmu.flush_branch_stack(); +} + static struct pmu pmu = { - .pmu_enable = x86_pmu_enable, - .pmu_disable = x86_pmu_disable, + .pmu_enable = x86_pmu_enable, + .pmu_disable = x86_pmu_disable, + + .attr_groups = x86_pmu_attr_groups, .event_init = x86_pmu_event_init, - .add = x86_pmu_add, - .del = x86_pmu_del, - .start = x86_pmu_start, - .stop = x86_pmu_stop, - .read = x86_pmu_read, + .add = x86_pmu_add, + .del = x86_pmu_del, + .start = x86_pmu_start, + .stop = x86_pmu_stop, + .read = x86_pmu_read, .start_txn = x86_pmu_start_txn, .cancel_txn = x86_pmu_cancel_txn, .commit_txn = x86_pmu_commit_txn, + + .event_idx = x86_pmu_event_idx, + .flush_branch_stack = x86_pmu_flush_branch_stack, }; +void perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now) +{ + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + return; + + if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) + return; + + userpg->time_mult = this_cpu_read(cyc2ns); + userpg->time_shift = CYC2NS_SCALE_FACTOR; + userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; +} + /* * callchain support */ diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 8944062f46e..8484e77c211 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -33,6 +33,7 @@ enum extra_reg_type { EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ + EXTRA_REG_LBR = 2, /* lbr_select */ EXTRA_REG_MAX /* number of entries needed */ }; @@ -130,6 +131,8 @@ struct cpu_hw_events { void *lbr_context; struct perf_branch_stack lbr_stack; struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; + struct er_account *lbr_sel; + u64 br_sel; /* * Intel host/guest exclude bits @@ -147,7 +150,9 @@ struct cpu_hw_events { /* * AMD specific bits */ - struct amd_nb *amd_nb; + struct amd_nb *amd_nb; + /* Inverted mask of bits to clear in the perf_ctr ctrl registers */ + u64 perf_ctr_virt_mask; void *kfree_on_online; }; @@ -266,6 +271,29 @@ struct x86_pmu_quirk { void (*func)(void); }; +union x86_pmu_config { + struct { + u64 event:8, + umask:8, + usr:1, + os:1, + edge:1, + pc:1, + interrupt:1, + __reserved1:1, + en:1, + inv:1, + cmask:8, + event2:4, + __reserved2:4, + go:1, + ho:1; + } bits; + u64 value; +}; + +#define X86_CONFIG(args...) ((union x86_pmu_config){.bits = {args}}).value + /* * struct x86_pmu - generic x86 pmu */ @@ -307,10 +335,19 @@ struct x86_pmu { struct x86_pmu_quirk *quirks; int perfctr_second_write; + /* + * sysfs attrs + */ + int attr_rdpmc; + + /* + * CPU Hotplug hooks + */ int (*cpu_prepare)(int cpu); void (*cpu_starting)(int cpu); void (*cpu_dying)(int cpu); void (*cpu_dead)(int cpu); + void (*flush_branch_stack)(void); /* * Intel Arch Perfmon v2+ @@ -332,6 +369,8 @@ struct x86_pmu { */ unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ int lbr_nr; /* hardware stack size */ + u64 lbr_sel_mask; /* LBR_SELECT valid bits */ + const int *lbr_sel_map; /* lbr_select mappings */ /* * Extra registers for events @@ -417,9 +456,11 @@ void x86_pmu_disable_all(void); static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, u64 enable_mask) { + u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask); + if (hwc->extra_reg.reg) wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); - wrmsrl(hwc->config_base, hwc->config | enable_mask); + wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask); } void x86_pmu_enable_all(int added); @@ -443,6 +484,15 @@ extern struct event_constraint emptyconstraint; extern struct event_constraint unconstrained; +static inline bool kernel_ip(unsigned long ip) +{ +#ifdef CONFIG_X86_32 + return ip > PAGE_OFFSET; +#else + return (long)ip < 0; +#endif +} + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); @@ -523,6 +573,10 @@ void intel_pmu_lbr_init_nhm(void); void intel_pmu_lbr_init_atom(void); +void intel_pmu_lbr_init_snb(void); + +int intel_pmu_setup_lbr_filter(struct perf_event *event); + int p4_pmu_init(void); int p6_pmu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 0397b23be8e..dd002faff7a 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -1,4 +1,5 @@ #include <linux/perf_event.h> +#include <linux/export.h> #include <linux/types.h> #include <linux/init.h> #include <linux/slab.h> @@ -138,6 +139,9 @@ static int amd_pmu_hw_config(struct perf_event *event) if (ret) return ret; + if (has_branch_stack(event)) + return -EOPNOTSUPP; + if (event->attr.exclude_host && event->attr.exclude_guest) /* * When HO == GO == 1 the hardware treats that as GO == HO == 0 @@ -357,7 +361,9 @@ static void amd_pmu_cpu_starting(int cpu) struct amd_nb *nb; int i, nb_id; - if (boot_cpu_data.x86_max_cores < 2) + cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY; + + if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15) return; nb_id = amd_get_nb_id(cpu); @@ -587,9 +593,9 @@ static __initconst const struct x86_pmu amd_pmu_f15h = { .put_event_constraints = amd_put_event_constraints, .cpu_prepare = amd_pmu_cpu_prepare, - .cpu_starting = amd_pmu_cpu_starting, .cpu_dead = amd_pmu_cpu_dead, #endif + .cpu_starting = amd_pmu_cpu_starting, }; __init int amd_pmu_init(void) @@ -621,3 +627,33 @@ __init int amd_pmu_init(void) return 0; } + +void amd_pmu_enable_virt(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + cpuc->perf_ctr_virt_mask = 0; + + /* Reload all events */ + x86_pmu_disable_all(); + x86_pmu_enable_all(0); +} +EXPORT_SYMBOL_GPL(amd_pmu_enable_virt); + +void amd_pmu_disable_virt(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + /* + * We only mask out the Host-only bit so that host-only counting works + * when SVM is disabled. If someone sets up a guest-only counter when + * SVM is disabled the Guest-only bits still gets set and the counter + * will not count anything. + */ + cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY; + + /* Reload all events */ + x86_pmu_disable_all(); + x86_pmu_enable_all(0); +} +EXPORT_SYMBOL_GPL(amd_pmu_disable_virt); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 3bd37bdf1b8..6a84e7f28f0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -385,14 +385,15 @@ static __initconst const u64 westmere_hw_cache_event_ids #define NHM_LOCAL_DRAM (1 << 14) #define NHM_NON_DRAM (1 << 15) -#define NHM_ALL_DRAM (NHM_REMOTE_DRAM|NHM_LOCAL_DRAM) +#define NHM_LOCAL (NHM_LOCAL_DRAM|NHM_REMOTE_CACHE_FWD) +#define NHM_REMOTE (NHM_REMOTE_DRAM) #define NHM_DMND_READ (NHM_DMND_DATA_RD) #define NHM_DMND_WRITE (NHM_DMND_RFO|NHM_DMND_WB) #define NHM_DMND_PREFETCH (NHM_PF_DATA_RD|NHM_PF_DATA_RFO) #define NHM_L3_HIT (NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM) -#define NHM_L3_MISS (NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD) +#define NHM_L3_MISS (NHM_NON_DRAM|NHM_LOCAL_DRAM|NHM_REMOTE_DRAM|NHM_REMOTE_CACHE_FWD) #define NHM_L3_ACCESS (NHM_L3_HIT|NHM_L3_MISS) static __initconst const u64 nehalem_hw_cache_extra_regs @@ -416,16 +417,16 @@ static __initconst const u64 nehalem_hw_cache_extra_regs }, [ C(NODE) ] = { [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_ALL_DRAM, - [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_REMOTE_DRAM, + [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_LOCAL|NHM_REMOTE, + [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_REMOTE, }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_ALL_DRAM, - [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_REMOTE_DRAM, + [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_LOCAL|NHM_REMOTE, + [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_REMOTE, }, [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_ALL_DRAM, - [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_REMOTE_DRAM, + [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_LOCAL|NHM_REMOTE, + [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_REMOTE, }, }, }; @@ -727,6 +728,19 @@ static __initconst const u64 atom_hw_cache_event_ids }, }; +static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) +{ + /* user explicitly requested branch sampling */ + if (has_branch_stack(event)) + return true; + + /* implicit branch sampling to correct PEBS skid */ + if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1) + return true; + + return false; +} + static void intel_pmu_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -881,6 +895,13 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx); cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); + /* + * must disable before any actual event + * because any event may be combined with LBR + */ + if (intel_pmu_needs_lbr_smpl(event)) + intel_pmu_lbr_disable(event); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_disable_fixed(hwc); return; @@ -935,6 +956,12 @@ static void intel_pmu_enable_event(struct perf_event *event) intel_pmu_enable_bts(hwc->config); return; } + /* + * must enabled before any actual event + * because any event may be combined with LBR + */ + if (intel_pmu_needs_lbr_smpl(event)) + intel_pmu_lbr_enable(event); if (event->attr.exclude_host) cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx); @@ -1057,6 +1084,9 @@ again: data.period = event->hw.last_period; + if (has_branch_stack(event)) + data.br_stack = &cpuc->lbr_stack; + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } @@ -1123,17 +1153,17 @@ static bool intel_try_alt_er(struct perf_event *event, int orig_idx) */ static struct event_constraint * __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc, - struct perf_event *event) + struct perf_event *event, + struct hw_perf_event_extra *reg) { struct event_constraint *c = &emptyconstraint; - struct hw_perf_event_extra *reg = &event->hw.extra_reg; struct er_account *era; unsigned long flags; int orig_idx = reg->idx; /* already allocated shared msr */ if (reg->alloc) - return &unconstrained; + return NULL; /* call x86_get_event_constraint() */ again: era = &cpuc->shared_regs->regs[reg->idx]; @@ -1156,14 +1186,10 @@ again: reg->alloc = 1; /* - * All events using extra_reg are unconstrained. - * Avoids calling x86_get_event_constraints() - * - * Must revisit if extra_reg controlling events - * ever have constraints. Worst case we go through - * the regular event constraint table. + * need to call x86_get_event_constraint() + * to check if associated event has constraints */ - c = &unconstrained; + c = NULL; } else if (intel_try_alt_er(event, orig_idx)) { raw_spin_unlock_irqrestore(&era->lock, flags); goto again; @@ -1200,11 +1226,23 @@ static struct event_constraint * intel_shared_regs_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { - struct event_constraint *c = NULL; - - if (event->hw.extra_reg.idx != EXTRA_REG_NONE) - c = __intel_shared_reg_get_constraints(cpuc, event); + struct event_constraint *c = NULL, *d; + struct hw_perf_event_extra *xreg, *breg; + xreg = &event->hw.extra_reg; + if (xreg->idx != EXTRA_REG_NONE) { + c = __intel_shared_reg_get_constraints(cpuc, event, xreg); + if (c == &emptyconstraint) + return c; + } + breg = &event->hw.branch_reg; + if (breg->idx != EXTRA_REG_NONE) { + d = __intel_shared_reg_get_constraints(cpuc, event, breg); + if (d == &emptyconstraint) { + __intel_shared_reg_put_constraints(cpuc, xreg); + c = d; + } + } return c; } @@ -1252,6 +1290,10 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, reg = &event->hw.extra_reg; if (reg->idx != EXTRA_REG_NONE) __intel_shared_reg_put_constraints(cpuc, reg); + + reg = &event->hw.branch_reg; + if (reg->idx != EXTRA_REG_NONE) + __intel_shared_reg_put_constraints(cpuc, reg); } static void intel_put_event_constraints(struct cpu_hw_events *cpuc, @@ -1287,12 +1329,19 @@ static int intel_pmu_hw_config(struct perf_event *event) * * Thereby we gain a PEBS capable cycle counter. */ - u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */ + u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16); + alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK); event->hw.config = alt_config; } + if (intel_pmu_needs_lbr_smpl(event)) { + ret = intel_pmu_setup_lbr_filter(event); + if (ret) + return ret; + } + if (event->attr.type != PERF_TYPE_RAW) return 0; @@ -1431,7 +1480,7 @@ static int intel_pmu_cpu_prepare(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); - if (!x86_pmu.extra_regs) + if (!(x86_pmu.extra_regs || x86_pmu.lbr_sel_map)) return NOTIFY_OK; cpuc->shared_regs = allocate_shared_regs(cpu); @@ -1453,22 +1502,28 @@ static void intel_pmu_cpu_starting(int cpu) */ intel_pmu_lbr_reset(); - if (!cpuc->shared_regs || (x86_pmu.er_flags & ERF_NO_HT_SHARING)) + cpuc->lbr_sel = NULL; + + if (!cpuc->shared_regs) return; - for_each_cpu(i, topology_thread_cpumask(cpu)) { - struct intel_shared_regs *pc; + if (!(x86_pmu.er_flags & ERF_NO_HT_SHARING)) { + for_each_cpu(i, topology_thread_cpumask(cpu)) { + struct intel_shared_regs *pc; - pc = per_cpu(cpu_hw_events, i).shared_regs; - if (pc && pc->core_id == core_id) { - cpuc->kfree_on_online = cpuc->shared_regs; - cpuc->shared_regs = pc; - break; + pc = per_cpu(cpu_hw_events, i).shared_regs; + if (pc && pc->core_id == core_id) { + cpuc->kfree_on_online = cpuc->shared_regs; + cpuc->shared_regs = pc; + break; + } } + cpuc->shared_regs->core_id = core_id; + cpuc->shared_regs->refcnt++; } - cpuc->shared_regs->core_id = core_id; - cpuc->shared_regs->refcnt++; + if (x86_pmu.lbr_sel_map) + cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR]; } static void intel_pmu_cpu_dying(int cpu) @@ -1486,6 +1541,18 @@ static void intel_pmu_cpu_dying(int cpu) fini_debug_store_on_cpu(cpu); } +static void intel_pmu_flush_branch_stack(void) +{ + /* + * Intel LBR does not tag entries with the + * PID of the current task, then we need to + * flush it on ctxsw + * For now, we simply reset it + */ + if (x86_pmu.lbr_nr) + intel_pmu_lbr_reset(); +} + static __initconst const struct x86_pmu intel_pmu = { .name = "Intel", .handle_irq = intel_pmu_handle_irq, @@ -1513,6 +1580,7 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .guest_get_msrs = intel_guest_get_msrs, + .flush_branch_stack = intel_pmu_flush_branch_stack, }; static __init void intel_clovertown_quirk(void) @@ -1689,9 +1757,11 @@ __init int intel_pmu_init(void) x86_pmu.extra_regs = intel_nehalem_extra_regs; /* UOPS_ISSUED.STALLED_CYCLES */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = + X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); /* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = + X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); x86_add_quirk(intel_nehalem_quirk); @@ -1726,9 +1796,11 @@ __init int intel_pmu_init(void) x86_pmu.er_flags |= ERF_HAS_RSP_1; /* UOPS_ISSUED.STALLED_CYCLES */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = + X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); /* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = + X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); pr_cont("Westmere events, "); break; @@ -1739,7 +1811,7 @@ __init int intel_pmu_init(void) memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - intel_pmu_lbr_init_nhm(); + intel_pmu_lbr_init_snb(); x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; @@ -1749,9 +1821,11 @@ __init int intel_pmu_init(void) x86_pmu.er_flags |= ERF_NO_HT_SHARING; /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = + X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); /* UOPS_DISPATCHED.THREAD,c=1,i=1 to count stall cycles*/ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x18001b1; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = + X86_CONFIG(.event=0xb1, .umask=0x01, .inv=1, .cmask=1); pr_cont("SandyBridge events, "); break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 73da6b64f5b..7f64df19e7d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -3,6 +3,7 @@ #include <linux/slab.h> #include <asm/perf_event.h> +#include <asm/insn.h> #include "perf_event.h" @@ -439,10 +440,6 @@ void intel_pmu_pebs_enable(struct perf_event *event) hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; cpuc->pebs_enabled |= 1ULL << hwc->idx; - WARN_ON_ONCE(cpuc->enabled); - - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1) - intel_pmu_lbr_enable(event); } void intel_pmu_pebs_disable(struct perf_event *event) @@ -455,9 +452,6 @@ void intel_pmu_pebs_disable(struct perf_event *event) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); hwc->config |= ARCH_PERFMON_EVENTSEL_INT; - - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1) - intel_pmu_lbr_disable(event); } void intel_pmu_pebs_enable_all(void) @@ -476,17 +470,6 @@ void intel_pmu_pebs_disable_all(void) wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } -#include <asm/insn.h> - -static inline bool kernel_ip(unsigned long ip) -{ -#ifdef CONFIG_X86_32 - return ip > PAGE_OFFSET; -#else - return (long)ip < 0; -#endif -} - static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -573,6 +556,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * both formats and we don't use the other fields in this * routine. */ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct pebs_record_core *pebs = __pebs; struct perf_sample_data data; struct pt_regs regs; @@ -603,6 +587,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event, else regs.flags &= ~PERF_EFLAGS_EXACT; + if (has_branch_stack(event)) + data.br_stack = &cpuc->lbr_stack; + if (perf_event_overflow(event, &data, ®s)) x86_pmu_stop(event, 0); } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 3fab3de3ce9..520b4265fcd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -3,6 +3,7 @@ #include <asm/perf_event.h> #include <asm/msr.h> +#include <asm/insn.h> #include "perf_event.h" @@ -14,6 +15,100 @@ enum { }; /* + * Intel LBR_SELECT bits + * Intel Vol3a, April 2011, Section 16.7 Table 16-10 + * + * Hardware branch filter (not available on all CPUs) + */ +#define LBR_KERNEL_BIT 0 /* do not capture at ring0 */ +#define LBR_USER_BIT 1 /* do not capture at ring > 0 */ +#define LBR_JCC_BIT 2 /* do not capture conditional branches */ +#define LBR_REL_CALL_BIT 3 /* do not capture relative calls */ +#define LBR_IND_CALL_BIT 4 /* do not capture indirect calls */ +#define LBR_RETURN_BIT 5 /* do not capture near returns */ +#define LBR_IND_JMP_BIT 6 /* do not capture indirect jumps */ +#define LBR_REL_JMP_BIT 7 /* do not capture relative jumps */ +#define LBR_FAR_BIT 8 /* do not capture far branches */ + +#define LBR_KERNEL (1 << LBR_KERNEL_BIT) +#define LBR_USER (1 << LBR_USER_BIT) +#define LBR_JCC (1 << LBR_JCC_BIT) +#define LBR_REL_CALL (1 << LBR_REL_CALL_BIT) +#define LBR_IND_CALL (1 << LBR_IND_CALL_BIT) +#define LBR_RETURN (1 << LBR_RETURN_BIT) +#define LBR_REL_JMP (1 << LBR_REL_JMP_BIT) +#define LBR_IND_JMP (1 << LBR_IND_JMP_BIT) +#define LBR_FAR (1 << LBR_FAR_BIT) + +#define LBR_PLM (LBR_KERNEL | LBR_USER) + +#define LBR_SEL_MASK 0x1ff /* valid bits in LBR_SELECT */ +#define LBR_NOT_SUPP -1 /* LBR filter not supported */ +#define LBR_IGN 0 /* ignored */ + +#define LBR_ANY \ + (LBR_JCC |\ + LBR_REL_CALL |\ + LBR_IND_CALL |\ + LBR_RETURN |\ + LBR_REL_JMP |\ + LBR_IND_JMP |\ + LBR_FAR) + +#define LBR_FROM_FLAG_MISPRED (1ULL << 63) + +#define for_each_branch_sample_type(x) \ + for ((x) = PERF_SAMPLE_BRANCH_USER; \ + (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1) + +/* + * x86control flow change classification + * x86control flow changes include branches, interrupts, traps, faults + */ +enum { + X86_BR_NONE = 0, /* unknown */ + + X86_BR_USER = 1 << 0, /* branch target is user */ + X86_BR_KERNEL = 1 << 1, /* branch target is kernel */ + + X86_BR_CALL = 1 << 2, /* call */ + X86_BR_RET = 1 << 3, /* return */ + X86_BR_SYSCALL = 1 << 4, /* syscall */ + X86_BR_SYSRET = 1 << 5, /* syscall return */ + X86_BR_INT = 1 << 6, /* sw interrupt */ + X86_BR_IRET = 1 << 7, /* return from interrupt */ + X86_BR_JCC = 1 << 8, /* conditional */ + X86_BR_JMP = 1 << 9, /* jump */ + X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ + X86_BR_IND_CALL = 1 << 11,/* indirect calls */ +}; + +#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) + +#define X86_BR_ANY \ + (X86_BR_CALL |\ + X86_BR_RET |\ + X86_BR_SYSCALL |\ + X86_BR_SYSRET |\ + X86_BR_INT |\ + X86_BR_IRET |\ + X86_BR_JCC |\ + X86_BR_JMP |\ + X86_BR_IRQ |\ + X86_BR_IND_CALL) + +#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) + +#define X86_BR_ANY_CALL \ + (X86_BR_CALL |\ + X86_BR_IND_CALL |\ + X86_BR_SYSCALL |\ + X86_BR_IRQ |\ + X86_BR_INT) + +static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc); + +/* * We only support LBR implementations that have FREEZE_LBRS_ON_PMI * otherwise it becomes near impossible to get a reliable stack. */ @@ -21,6 +116,10 @@ enum { static void __intel_pmu_lbr_enable(void) { u64 debugctl; + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->lbr_sel) + wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config); rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); @@ -72,17 +171,15 @@ void intel_pmu_lbr_enable(struct perf_event *event) if (!x86_pmu.lbr_nr) return; - WARN_ON_ONCE(cpuc->enabled); - /* * Reset the LBR stack if we changed task context to * avoid data leaks. */ - if (event->ctx->task && cpuc->lbr_context != event->ctx) { intel_pmu_lbr_reset(); cpuc->lbr_context = event->ctx; } + cpuc->br_sel = event->hw.branch_reg.reg; cpuc->lbr_users++; } @@ -97,8 +194,11 @@ void intel_pmu_lbr_disable(struct perf_event *event) cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); - if (cpuc->enabled && !cpuc->lbr_users) + if (cpuc->enabled && !cpuc->lbr_users) { __intel_pmu_lbr_disable(); + /* avoid stale pointer */ + cpuc->lbr_context = NULL; + } } void intel_pmu_lbr_enable_all(void) @@ -117,6 +217,9 @@ void intel_pmu_lbr_disable_all(void) __intel_pmu_lbr_disable(); } +/* + * TOS = most recently recorded branch + */ static inline u64 intel_pmu_lbr_tos(void) { u64 tos; @@ -144,15 +247,15 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr); - cpuc->lbr_entries[i].from = msr_lastbranch.from; - cpuc->lbr_entries[i].to = msr_lastbranch.to; - cpuc->lbr_entries[i].flags = 0; + cpuc->lbr_entries[i].from = msr_lastbranch.from; + cpuc->lbr_entries[i].to = msr_lastbranch.to; + cpuc->lbr_entries[i].mispred = 0; + cpuc->lbr_entries[i].predicted = 0; + cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; } -#define LBR_FROM_FLAG_MISPRED (1ULL << 63) - /* * Due to lack of segmentation in Linux the effective address (offset) * is the same as the linear address, allowing us to merge the LIP and EIP @@ -167,19 +270,22 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) for (i = 0; i < x86_pmu.lbr_nr; i++) { unsigned long lbr_idx = (tos - i) & mask; - u64 from, to, flags = 0; + u64 from, to, mis = 0, pred = 0; rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); if (lbr_format == LBR_FORMAT_EIP_FLAGS) { - flags = !!(from & LBR_FROM_FLAG_MISPRED); + mis = !!(from & LBR_FROM_FLAG_MISPRED); + pred = !mis; from = (u64)((((s64)from) << 1) >> 1); } - cpuc->lbr_entries[i].from = from; - cpuc->lbr_entries[i].to = to; - cpuc->lbr_entries[i].flags = flags; + cpuc->lbr_entries[i].from = from; + cpuc->lbr_entries[i].to = to; + cpuc->lbr_entries[i].mispred = mis; + cpuc->lbr_entries[i].predicted = pred; + cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; } @@ -195,28 +301,404 @@ void intel_pmu_lbr_read(void) intel_pmu_lbr_read_32(cpuc); else intel_pmu_lbr_read_64(cpuc); + + intel_pmu_lbr_filter(cpuc); +} + +/* + * SW filter is used: + * - in case there is no HW filter + * - in case the HW filter has errata or limitations + */ +static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) +{ + u64 br_type = event->attr.branch_sample_type; + int mask = 0; + + if (br_type & PERF_SAMPLE_BRANCH_USER) + mask |= X86_BR_USER; + + if (br_type & PERF_SAMPLE_BRANCH_KERNEL) + mask |= X86_BR_KERNEL; + + /* we ignore BRANCH_HV here */ + + if (br_type & PERF_SAMPLE_BRANCH_ANY) + mask |= X86_BR_ANY; + + if (br_type & PERF_SAMPLE_BRANCH_ANY_CALL) + mask |= X86_BR_ANY_CALL; + + if (br_type & PERF_SAMPLE_BRANCH_ANY_RETURN) + mask |= X86_BR_RET | X86_BR_IRET | X86_BR_SYSRET; + + if (br_type & PERF_SAMPLE_BRANCH_IND_CALL) + mask |= X86_BR_IND_CALL; + /* + * stash actual user request into reg, it may + * be used by fixup code for some CPU + */ + event->hw.branch_reg.reg = mask; +} + +/* + * setup the HW LBR filter + * Used only when available, may not be enough to disambiguate + * all branches, may need the help of the SW filter + */ +static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) +{ + struct hw_perf_event_extra *reg; + u64 br_type = event->attr.branch_sample_type; + u64 mask = 0, m; + u64 v; + + for_each_branch_sample_type(m) { + if (!(br_type & m)) + continue; + + v = x86_pmu.lbr_sel_map[m]; + if (v == LBR_NOT_SUPP) + return -EOPNOTSUPP; + + if (v != LBR_IGN) + mask |= v; + } + reg = &event->hw.branch_reg; + reg->idx = EXTRA_REG_LBR; + + /* LBR_SELECT operates in suppress mode so invert mask */ + reg->config = ~mask & x86_pmu.lbr_sel_mask; + + return 0; +} + +int intel_pmu_setup_lbr_filter(struct perf_event *event) +{ + int ret = 0; + + /* + * no LBR on this PMU + */ + if (!x86_pmu.lbr_nr) + return -EOPNOTSUPP; + + /* + * setup SW LBR filter + */ + intel_pmu_setup_sw_lbr_filter(event); + + /* + * setup HW LBR filter, if any + */ + if (x86_pmu.lbr_sel_map) + ret = intel_pmu_setup_hw_lbr_filter(event); + + return ret; +} + +/* + * return the type of control flow change at address "from" + * intruction is not necessarily a branch (in case of interrupt). + * + * The branch type returned also includes the priv level of the + * target of the control flow change (X86_BR_USER, X86_BR_KERNEL). + * + * If a branch type is unknown OR the instruction cannot be + * decoded (e.g., text page not present), then X86_BR_NONE is + * returned. + */ +static int branch_type(unsigned long from, unsigned long to) +{ + struct insn insn; + void *addr; + int bytes, size = MAX_INSN_SIZE; + int ret = X86_BR_NONE; + int ext, to_plm, from_plm; + u8 buf[MAX_INSN_SIZE]; + int is64 = 0; + + to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER; + from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER; + + /* + * maybe zero if lbr did not fill up after a reset by the time + * we get a PMU interrupt + */ + if (from == 0 || to == 0) + return X86_BR_NONE; + + if (from_plm == X86_BR_USER) { + /* + * can happen if measuring at the user level only + * and we interrupt in a kernel thread, e.g., idle. + */ + if (!current->mm) + return X86_BR_NONE; + + /* may fail if text not present */ + bytes = copy_from_user_nmi(buf, (void __user *)from, size); + if (bytes != size) + return X86_BR_NONE; + + addr = buf; + } else + addr = (void *)from; + + /* + * decoder needs to know the ABI especially + * on 64-bit systems running 32-bit apps + */ +#ifdef CONFIG_X86_64 + is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32); +#endif + insn_init(&insn, addr, is64); + insn_get_opcode(&insn); + + switch (insn.opcode.bytes[0]) { + case 0xf: + switch (insn.opcode.bytes[1]) { + case 0x05: /* syscall */ + case 0x34: /* sysenter */ + ret = X86_BR_SYSCALL; + break; + case 0x07: /* sysret */ + case 0x35: /* sysexit */ + ret = X86_BR_SYSRET; + break; + case 0x80 ... 0x8f: /* conditional */ + ret = X86_BR_JCC; + break; + default: + ret = X86_BR_NONE; + } + break; + case 0x70 ... 0x7f: /* conditional */ + ret = X86_BR_JCC; + break; + case 0xc2: /* near ret */ + case 0xc3: /* near ret */ + case 0xca: /* far ret */ + case 0xcb: /* far ret */ + ret = X86_BR_RET; + break; + case 0xcf: /* iret */ + ret = X86_BR_IRET; + break; + case 0xcc ... 0xce: /* int */ + ret = X86_BR_INT; + break; + case 0xe8: /* call near rel */ + case 0x9a: /* call far absolute */ + ret = X86_BR_CALL; + break; + case 0xe0 ... 0xe3: /* loop jmp */ + ret = X86_BR_JCC; + break; + case 0xe9 ... 0xeb: /* jmp */ + ret = X86_BR_JMP; + break; + case 0xff: /* call near absolute, call far absolute ind */ + insn_get_modrm(&insn); + ext = (insn.modrm.bytes[0] >> 3) & 0x7; + switch (ext) { + case 2: /* near ind call */ + case 3: /* far ind call */ + ret = X86_BR_IND_CALL; + break; + case 4: + case 5: + ret = X86_BR_JMP; + break; + } + break; + default: + ret = X86_BR_NONE; + } + /* + * interrupts, traps, faults (and thus ring transition) may + * occur on any instructions. Thus, to classify them correctly, + * we need to first look at the from and to priv levels. If they + * are different and to is in the kernel, then it indicates + * a ring transition. If the from instruction is not a ring + * transition instr (syscall, systenter, int), then it means + * it was a irq, trap or fault. + * + * we have no way of detecting kernel to kernel faults. + */ + if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL + && ret != X86_BR_SYSCALL && ret != X86_BR_INT) + ret = X86_BR_IRQ; + + /* + * branch priv level determined by target as + * is done by HW when LBR_SELECT is implemented + */ + if (ret != X86_BR_NONE) + ret |= to_plm; + + return ret; } +/* + * implement actual branch filter based on user demand. + * Hardware may not exactly satisfy that request, thus + * we need to inspect opcodes. Mismatched branches are + * discarded. Therefore, the number of branches returned + * in PERF_SAMPLE_BRANCH_STACK sample may vary. + */ +static void +intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) +{ + u64 from, to; + int br_sel = cpuc->br_sel; + int i, j, type; + bool compress = false; + + /* if sampling all branches, then nothing to filter */ + if ((br_sel & X86_BR_ALL) == X86_BR_ALL) + return; + + for (i = 0; i < cpuc->lbr_stack.nr; i++) { + + from = cpuc->lbr_entries[i].from; + to = cpuc->lbr_entries[i].to; + + type = branch_type(from, to); + + /* if type does not correspond, then discard */ + if (type == X86_BR_NONE || (br_sel & type) != type) { + cpuc->lbr_entries[i].from = 0; + compress = true; + } + } + + if (!compress) + return; + + /* remove all entries with from=0 */ + for (i = 0; i < cpuc->lbr_stack.nr; ) { + if (!cpuc->lbr_entries[i].from) { + j = i; + while (++j < cpuc->lbr_stack.nr) + cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j]; + cpuc->lbr_stack.nr--; + if (!cpuc->lbr_entries[i].from) + continue; + } + i++; + } +} + +/* + * Map interface branch filters onto LBR filters + */ +static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { + [PERF_SAMPLE_BRANCH_ANY] = LBR_ANY, + [PERF_SAMPLE_BRANCH_USER] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV] = LBR_IGN, + [PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_REL_JMP + | LBR_IND_JMP | LBR_FAR, + /* + * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches + */ + [PERF_SAMPLE_BRANCH_ANY_CALL] = + LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR, + /* + * NHM/WSM erratum: must include IND_JMP to capture IND_CALL + */ + [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP, +}; + +static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { + [PERF_SAMPLE_BRANCH_ANY] = LBR_ANY, + [PERF_SAMPLE_BRANCH_USER] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV] = LBR_IGN, + [PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_FAR, + [PERF_SAMPLE_BRANCH_ANY_CALL] = LBR_REL_CALL | LBR_IND_CALL + | LBR_FAR, + [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL, +}; + +/* core */ void intel_pmu_lbr_init_core(void) { x86_pmu.lbr_nr = 4; - x86_pmu.lbr_tos = 0x01c9; - x86_pmu.lbr_from = 0x40; - x86_pmu.lbr_to = 0x60; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_CORE_FROM; + x86_pmu.lbr_to = MSR_LBR_CORE_TO; + + /* + * SW branch filter usage: + * - compensate for lack of HW filter + */ + pr_cont("4-deep LBR, "); } +/* nehalem/westmere */ void intel_pmu_lbr_init_nhm(void) { x86_pmu.lbr_nr = 16; - x86_pmu.lbr_tos = 0x01c9; - x86_pmu.lbr_from = 0x680; - x86_pmu.lbr_to = 0x6c0; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = nhm_lbr_sel_map; + + /* + * SW branch filter usage: + * - workaround LBR_SEL errata (see above) + * - support syscall, sysret capture. + * That requires LBR_FAR but that means far + * jmp need to be filtered out + */ + pr_cont("16-deep LBR, "); +} + +/* sandy bridge */ +void intel_pmu_lbr_init_snb(void) +{ + x86_pmu.lbr_nr = 16; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = snb_lbr_sel_map; + + /* + * SW branch filter usage: + * - support syscall, sysret capture. + * That requires LBR_FAR but that means far + * jmp need to be filtered out + */ + pr_cont("16-deep LBR, "); } +/* atom */ void intel_pmu_lbr_init_atom(void) { + /* + * only models starting at stepping 10 seems + * to have an operational LBR which can freeze + * on PMU interrupt + */ + if (boot_cpu_data.x86_mask < 10) { + pr_cont("LBR disabled due to erratum"); + return; + } + x86_pmu.lbr_nr = 8; - x86_pmu.lbr_tos = 0x01c9; - x86_pmu.lbr_from = 0x40; - x86_pmu.lbr_to = 0x60; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_CORE_FROM; + x86_pmu.lbr_to = MSR_LBR_CORE_TO; + + /* + * SW branch filter usage: + * - compensate for lack of HW filter + */ + pr_cont("8-deep LBR, "); } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index c7f64e6f537..addf9e82a7f 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -40,6 +40,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_XSAVEOPT, CR_EAX, 0, 0x0000000d, 1 }, { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, + { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a, 0 }, { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a, 0 }, { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a, 0 }, diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c index 642f75a68cd..11891ca7b71 100644 --- a/arch/x86/kernel/crash_dump_32.c +++ b/arch/x86/kernel/crash_dump_32.c @@ -62,16 +62,16 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, if (!userbuf) { memcpy(buf, (vaddr + offset), csize); - kunmap_atomic(vaddr, KM_PTE0); + kunmap_atomic(vaddr); } else { if (!kdump_buf_page) { printk(KERN_WARNING "Kdump: Kdump buffer page not" " allocated\n"); - kunmap_atomic(vaddr, KM_PTE0); + kunmap_atomic(vaddr); return -EFAULT; } copy_page(kdump_buf_page, vaddr); - kunmap_atomic(vaddr, KM_PTE0); + kunmap_atomic(vaddr); if (copy_to_user(buf, (kdump_buf_page + offset), csize)) return -EFAULT; } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 52821799a70..3ae2ced4a87 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -4,6 +4,7 @@ #include <linux/bootmem.h> #include <linux/export.h> #include <linux/io.h> +#include <linux/irqdomain.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/of.h> @@ -17,64 +18,14 @@ #include <linux/initrd.h> #include <asm/hpet.h> -#include <asm/irq_controller.h> #include <asm/apic.h> #include <asm/pci_x86.h> __initdata u64 initial_dtb; char __initdata cmd_line[COMMAND_LINE_SIZE]; -static LIST_HEAD(irq_domains); -static DEFINE_RAW_SPINLOCK(big_irq_lock); int __initdata of_ioapic; -#ifdef CONFIG_X86_IO_APIC -static void add_interrupt_host(struct irq_domain *ih) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&big_irq_lock, flags); - list_add(&ih->l, &irq_domains); - raw_spin_unlock_irqrestore(&big_irq_lock, flags); -} -#endif - -static struct irq_domain *get_ih_from_node(struct device_node *controller) -{ - struct irq_domain *ih, *found = NULL; - unsigned long flags; - - raw_spin_lock_irqsave(&big_irq_lock, flags); - list_for_each_entry(ih, &irq_domains, l) { - if (ih->controller == controller) { - found = ih; - break; - } - } - raw_spin_unlock_irqrestore(&big_irq_lock, flags); - return found; -} - -unsigned int irq_create_of_mapping(struct device_node *controller, - const u32 *intspec, unsigned int intsize) -{ - struct irq_domain *ih; - u32 virq, type; - int ret; - - ih = get_ih_from_node(controller); - if (!ih) - return 0; - ret = ih->xlate(ih, intspec, intsize, &virq, &type); - if (ret) - return 0; - if (type == IRQ_TYPE_NONE) - return virq; - irq_set_irq_type(virq, type); - return virq; -} -EXPORT_SYMBOL_GPL(irq_create_of_mapping); - unsigned long pci_address_to_pio(phys_addr_t address) { /* @@ -354,36 +305,43 @@ static struct of_ioapic_type of_ioapic_type[] = }, }; -static int ioapic_xlate(struct irq_domain *id, const u32 *intspec, u32 intsize, - u32 *out_hwirq, u32 *out_type) +static int ioapic_xlate(struct irq_domain *domain, + struct device_node *controller, + const u32 *intspec, u32 intsize, + irq_hw_number_t *out_hwirq, u32 *out_type) { - struct mp_ioapic_gsi *gsi_cfg; struct io_apic_irq_attr attr; struct of_ioapic_type *it; - u32 line, idx, type; + u32 line, idx; + int rc; - if (intsize < 2) + if (WARN_ON(intsize < 2)) return -EINVAL; - line = *intspec; - idx = (u32) id->priv; - gsi_cfg = mp_ioapic_gsi_routing(idx); - *out_hwirq = line + gsi_cfg->gsi_base; - - intspec++; - type = *intspec; + line = intspec[0]; - if (type >= ARRAY_SIZE(of_ioapic_type)) + if (intspec[1] >= ARRAY_SIZE(of_ioapic_type)) return -EINVAL; - it = of_ioapic_type + type; - *out_type = it->out_type; + it = &of_ioapic_type[intspec[1]]; + idx = (u32) domain->host_data; set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity); - return io_apic_setup_irq_pin_once(*out_hwirq, cpu_to_node(0), &attr); + rc = io_apic_setup_irq_pin_once(irq_find_mapping(domain, line), + cpu_to_node(0), &attr); + if (rc) + return rc; + + *out_hwirq = line; + *out_type = it->out_type; + return 0; } +const struct irq_domain_ops ioapic_irq_domain_ops = { + .xlate = ioapic_xlate, +}; + static void __init ioapic_add_ofnode(struct device_node *np) { struct resource r; @@ -399,13 +357,14 @@ static void __init ioapic_add_ofnode(struct device_node *np) for (i = 0; i < nr_ioapics; i++) { if (r.start == mpc_ioapic_addr(i)) { struct irq_domain *id; + struct mp_ioapic_gsi *gsi_cfg; + + gsi_cfg = mp_ioapic_gsi_routing(i); - id = kzalloc(sizeof(*id), GFP_KERNEL); + id = irq_domain_add_legacy(np, 32, gsi_cfg->gsi_base, 0, + &ioapic_irq_domain_ops, + (void*)i); BUG_ON(!id); - id->controller = np; - id->xlate = ioapic_xlate; - id->priv = (void *)i; - add_interrupt_host(id); return; } } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 1aae78f775f..4025fe4f928 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -252,7 +252,8 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) unsigned short ss; unsigned long sp; #endif - printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter); + printk(KERN_DEFAULT + "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter); #ifdef CONFIG_PREEMPT printk("PREEMPT "); #endif diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index c99f9ed013d..88ec9129271 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -87,7 +87,7 @@ void show_registers(struct pt_regs *regs) int i; print_modules(); - __show_regs(regs, 0); + __show_regs(regs, !user_mode_vm(regs)); printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n", TASK_COMM_LEN, current->comm, task_pid_nr(current), diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 6d728d9284b..17107bd6e1f 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -129,7 +129,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (!stack) { if (regs) stack = (unsigned long *)regs->sp; - else if (task && task != current) + else if (task != current) stack = (unsigned long *)task->thread.sp; else stack = &dummy; @@ -269,11 +269,11 @@ void show_registers(struct pt_regs *regs) unsigned char c; u8 *ip; - printk(KERN_EMERG "Stack:\n"); + printk(KERN_DEFAULT "Stack:\n"); show_stack_log_lvl(NULL, regs, (unsigned long *)sp, - 0, KERN_EMERG); + 0, KERN_DEFAULT); - printk(KERN_EMERG "Code: "); + printk(KERN_DEFAULT "Code: "); ip = (u8 *)regs->ip - code_prologue; if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 79d97e68f04..7b784f4ef1e 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -98,12 +98,6 @@ #endif .endm -#ifdef CONFIG_VM86 -#define resume_userspace_sig check_userspace -#else -#define resume_userspace_sig resume_userspace -#endif - /* * User gs save/restore * @@ -327,10 +321,19 @@ ret_from_exception: preempt_stop(CLBR_ANY) ret_from_intr: GET_THREAD_INFO(%ebp) -check_userspace: +resume_userspace_sig: +#ifdef CONFIG_VM86 movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS movb PT_CS(%esp), %al andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax +#else + /* + * We can be coming here from a syscall done in the kernel space, + * e.g. a failed kernel_execve(). + */ + movl PT_CS(%esp), %eax + andl $SEGMENT_RPL_MASK, %eax +#endif cmpl $USER_RPL, %eax jb resume_kernel # not returning to v8086 or userspace diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 3fe8239fd8f..734ebd1d3ca 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -320,7 +320,7 @@ ENDPROC(native_usergs_sysret64) movq %rsp, %rsi leaq -RBP(%rsp),%rdi /* arg1 for handler */ - testl $3, CS(%rdi) + testl $3, CS-RBP(%rsi) je 1f SWAPGS /* @@ -330,11 +330,10 @@ ENDPROC(native_usergs_sysret64) * moving irq_enter into assembly, which would be too much work) */ 1: incl PER_CPU_VAR(irq_count) - jne 2f - mov PER_CPU_VAR(irq_stack_ptr),%rsp + cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp CFI_DEF_CFA_REGISTER rsi -2: /* Store previous stack value */ + /* Store previous stack value */ pushq %rsi CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \ 0x77 /* DW_OP_breg7 */, 0, \ @@ -813,7 +812,7 @@ ret_from_intr: /* Restore saved previous stack */ popq %rsi - CFI_DEF_CFA_REGISTER rsi + CFI_DEF_CFA rsi,SS+8-RBP /* reg/off reset after def_cfa_expr */ leaq ARGOFFSET-RBP(%rsi), %rsp CFI_DEF_CFA_REGISTER rsp CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET @@ -1530,12 +1529,20 @@ ENTRY(nmi) /* Use %rdx as out temp variable throughout */ pushq_cfi %rdx + CFI_REL_OFFSET rdx, 0 + + /* + * If %cs was not the kernel segment, then the NMI triggered in user + * space, which means it is definitely not nested. + */ + cmpl $__KERNEL_CS, 16(%rsp) + jne first_nmi /* * Check the special variable on the stack to see if NMIs are * executing. */ - cmp $1, -8(%rsp) + cmpl $1, -8(%rsp) je nested_nmi /* @@ -1547,6 +1554,7 @@ ENTRY(nmi) */ lea 6*8(%rsp), %rdx test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi + CFI_REMEMBER_STATE nested_nmi: /* @@ -1578,10 +1586,12 @@ nested_nmi: nested_nmi_out: popq_cfi %rdx + CFI_RESTORE rdx /* No need to check faults here */ INTERRUPT_RETURN + CFI_RESTORE_STATE first_nmi: /* * Because nested NMIs will use the pushed location that we @@ -1613,10 +1623,15 @@ first_nmi: * | pt_regs | * +-------------------------+ * - * The saved RIP is used to fix up the copied RIP that a nested - * NMI may zero out. The original stack frame and the temp storage + * The saved stack frame is used to fix up the copied stack frame + * that a nested NMI may change to make the interrupted NMI iret jump + * to the repeat_nmi. The original stack frame and the temp storage * is also used by nested NMIs and can not be trusted on exit. */ + /* Do not pop rdx, nested NMIs will corrupt that part of the stack */ + movq (%rsp), %rdx + CFI_RESTORE rdx + /* Set the NMI executing variable on the stack. */ pushq_cfi $1 @@ -1624,22 +1639,39 @@ first_nmi: .rept 5 pushq_cfi 6*8(%rsp) .endr + CFI_DEF_CFA_OFFSET SS+8-RIP + + /* Everything up to here is safe from nested NMIs */ + + /* + * If there was a nested NMI, the first NMI's iret will return + * here. But NMIs are still enabled and we can take another + * nested NMI. The nested NMI checks the interrupted RIP to see + * if it is between repeat_nmi and end_repeat_nmi, and if so + * it will just return, as we are about to repeat an NMI anyway. + * This makes it safe to copy to the stack frame that a nested + * NMI will update. + */ +repeat_nmi: + /* + * Update the stack variable to say we are still in NMI (the update + * is benign for the non-repeat case, where 1 was pushed just above + * to this very stack slot). + */ + movq $1, 5*8(%rsp) /* Make another copy, this one may be modified by nested NMIs */ .rept 5 pushq_cfi 4*8(%rsp) .endr - - /* Do not pop rdx, nested NMIs will corrupt it */ - movq 11*8(%rsp), %rdx + CFI_DEF_CFA_OFFSET SS+8-RIP +end_repeat_nmi: /* * Everything below this point can be preempted by a nested - * NMI if the first NMI took an exception. Repeated NMIs - * caused by an exception and nested NMI will start here, and - * can still be preempted by another NMI. + * NMI if the first NMI took an exception and reset our iret stack + * so that we repeat another NMI. */ -restart_nmi: pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 @@ -1668,26 +1700,6 @@ nmi_restore: CFI_ENDPROC END(nmi) - /* - * If an NMI hit an iret because of an exception or breakpoint, - * it can lose its NMI context, and a nested NMI may come in. - * In that case, the nested NMI will change the preempted NMI's - * stack to jump to here when it does the final iret. - */ -repeat_nmi: - INTR_FRAME - /* Update the stack variable to say we are still in NMI */ - movq $1, 5*8(%rsp) - - /* copy the saved stack back to copy stack */ - .rept 5 - pushq_cfi 4*8(%rsp) - .endr - - jmp restart_nmi - CFI_ENDPROC -end_repeat_nmi: - ENTRY(ignore_sysret) CFI_STARTPROC mov $-ENOSYS,%eax diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 739d8598f78..7734bcbb5a3 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -16,6 +16,7 @@ #include <asm/uaccess.h> #include <asm/ptrace.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/user.h> #ifdef CONFIG_X86_64 @@ -32,6 +33,86 @@ # define user32_fxsr_struct user_fxsr_struct #endif +/* + * Were we in an interrupt that interrupted kernel mode? + * + * We can do a kernel_fpu_begin/end() pair *ONLY* if that + * pair does nothing at all: the thread must not have fpu (so + * that we don't try to save the FPU state), and TS must + * be set (so that the clts/stts pair does nothing that is + * visible in the interrupted kernel thread). + */ +static inline bool interrupted_kernel_fpu_idle(void) +{ + return !__thread_has_fpu(current) && + (read_cr0() & X86_CR0_TS); +} + +/* + * Were we in user mode (or vm86 mode) when we were + * interrupted? + * + * Doing kernel_fpu_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static inline bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + return regs && user_mode_vm(regs); +} + +/* + * Can we use the FPU in kernel mode with the + * whole "kernel_fpu_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +bool irq_fpu_usable(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} +EXPORT_SYMBOL(irq_fpu_usable); + +void kernel_fpu_begin(void) +{ + struct task_struct *me = current; + + WARN_ON_ONCE(!irq_fpu_usable()); + preempt_disable(); + if (__thread_has_fpu(me)) { + __save_init_fpu(me); + __thread_clear_has_fpu(me); + /* We do 'stts()' in kernel_fpu_end() */ + } else { + percpu_write(fpu_owner_task, NULL); + clts(); + } +} +EXPORT_SYMBOL(kernel_fpu_begin); + +void kernel_fpu_end(void) +{ + stts(); + preempt_enable(); +} +EXPORT_SYMBOL(kernel_fpu_end); + +void unlazy_fpu(struct task_struct *tsk) +{ + preempt_disable(); + if (__thread_has_fpu(tsk)) { + __save_init_fpu(tsk); + __thread_fpu_end(tsk); + } else + tsk->fpu_counter = 0; + preempt_enable(); +} +EXPORT_SYMBOL(unlazy_fpu); + #ifdef CONFIG_MATH_EMULATION # define HAVE_HWFP (boot_cpu_data.hard_math) #else @@ -44,7 +125,7 @@ EXPORT_SYMBOL_GPL(xstate_size); unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32); static struct i387_fxsave_struct fx_scratch __cpuinitdata; -void __cpuinit mxcsr_feature_mask_init(void) +static void __cpuinit mxcsr_feature_mask_init(void) { unsigned long mask = 0; diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 40fc86161d9..58b7f27cb3e 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -100,13 +100,8 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) irqctx->tinfo.task = curctx->tinfo.task; irqctx->tinfo.previous_esp = current_stack_pointer; - /* - * Copy the softirq bits in preempt_count so that the - * softirq checks work in the hardirq context. - */ - irqctx->tinfo.preempt_count = - (irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) | - (curctx->tinfo.preempt_count & SOFTIRQ_MASK); + /* Copy the preempt_count so that the [soft]irq checks work. */ + irqctx->tinfo.preempt_count = curctx->tinfo.preempt_count; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -196,7 +191,7 @@ bool handle_irq(unsigned irq, struct pt_regs *regs) if (unlikely(!desc)) return false; - if (!execute_on_irq_stack(overflow, desc, irq)) { + if (user_mode_vm(regs) || !execute_on_irq_stack(overflow, desc, irq)) { if (unlikely(overflow)) print_stack_overflow(); desc->handle_irq(irq, desc); diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 313fb5cddbc..43e2b1cff0a 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -306,10 +306,10 @@ void __init native_init_IRQ(void) * us. (some of these will be overridden and become * 'special' SMP interrupts) */ - for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) { + i = FIRST_EXTERNAL_VECTOR; + for_each_clear_bit_from(i, used_vectors, NR_VECTORS) { /* IA32_SYSCALL_VECTOR could be used in trap_init already. */ - if (!test_bit(i, used_vectors)) - set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]); + set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]); } if (!acpi_ioapic && !of_ioapic) diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index faba5771aca..fdc37b3d0ce 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -67,8 +67,6 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { "ss", 4, offsetof(struct pt_regs, ss) }, { "ds", 4, offsetof(struct pt_regs, ds) }, { "es", 4, offsetof(struct pt_regs, es) }, - { "fs", 4, -1 }, - { "gs", 4, -1 }, #else { "ax", 8, offsetof(struct pt_regs, ax) }, { "bx", 8, offsetof(struct pt_regs, bx) }, @@ -90,7 +88,11 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { "flags", 4, offsetof(struct pt_regs, flags) }, { "cs", 4, offsetof(struct pt_regs, cs) }, { "ss", 4, offsetof(struct pt_regs, ss) }, + { "ds", 4, -1 }, + { "es", 4, -1 }, #endif + { "fs", 4, -1 }, + { "gs", 4, -1 }, }; int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes-common.h new file mode 100644 index 00000000000..3230b68ef29 --- /dev/null +++ b/arch/x86/kernel/kprobes-common.h @@ -0,0 +1,102 @@ +#ifndef __X86_KERNEL_KPROBES_COMMON_H +#define __X86_KERNEL_KPROBES_COMMON_H + +/* Kprobes and Optprobes common header */ + +#ifdef CONFIG_X86_64 +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax. */ \ + " subq $24, %rsp\n" \ + " pushq %rdi\n" \ + " pushq %rsi\n" \ + " pushq %rdx\n" \ + " pushq %rcx\n" \ + " pushq %rax\n" \ + " pushq %r8\n" \ + " pushq %r9\n" \ + " pushq %r10\n" \ + " pushq %r11\n" \ + " pushq %rbx\n" \ + " pushq %rbp\n" \ + " pushq %r12\n" \ + " pushq %r13\n" \ + " pushq %r14\n" \ + " pushq %r15\n" +#define RESTORE_REGS_STRING \ + " popq %r15\n" \ + " popq %r14\n" \ + " popq %r13\n" \ + " popq %r12\n" \ + " popq %rbp\n" \ + " popq %rbx\n" \ + " popq %r11\n" \ + " popq %r10\n" \ + " popq %r9\n" \ + " popq %r8\n" \ + " popq %rax\n" \ + " popq %rcx\n" \ + " popq %rdx\n" \ + " popq %rsi\n" \ + " popq %rdi\n" \ + /* Skip orig_ax, ip, cs */ \ + " addq $24, %rsp\n" +#else +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax and gs. */ \ + " subl $16, %esp\n" \ + " pushl %fs\n" \ + " pushl %es\n" \ + " pushl %ds\n" \ + " pushl %eax\n" \ + " pushl %ebp\n" \ + " pushl %edi\n" \ + " pushl %esi\n" \ + " pushl %edx\n" \ + " pushl %ecx\n" \ + " pushl %ebx\n" +#define RESTORE_REGS_STRING \ + " popl %ebx\n" \ + " popl %ecx\n" \ + " popl %edx\n" \ + " popl %esi\n" \ + " popl %edi\n" \ + " popl %ebp\n" \ + " popl %eax\n" \ + /* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\ + " addl $24, %esp\n" +#endif + +/* Ensure if the instruction can be boostable */ +extern int can_boost(kprobe_opcode_t *instruction); +/* Recover instruction if given address is probed */ +extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, + unsigned long addr); +/* + * Copy an instruction and adjust the displacement if the instruction + * uses the %rip-relative addressing mode. + */ +extern int __copy_instruction(u8 *dest, u8 *src); + +/* Generate a relative-jump/call instruction */ +extern void synthesize_reljump(void *from, void *to); +extern void synthesize_relcall(void *from, void *to); + +#ifdef CONFIG_OPTPROBES +extern int arch_init_optprobes(void); +extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); +extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr); +#else /* !CONFIG_OPTPROBES */ +static inline int arch_init_optprobes(void) +{ + return 0; +} +static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) +{ + return 0; +} +static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) +{ + return addr; +} +#endif +#endif diff --git a/arch/x86/kernel/kprobes-opt.c b/arch/x86/kernel/kprobes-opt.c new file mode 100644 index 00000000000..c5e410eed40 --- /dev/null +++ b/arch/x86/kernel/kprobes-opt.c @@ -0,0 +1,512 @@ +/* + * Kernel Probes Jump Optimization (Optprobes) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2002, 2004 + * Copyright (C) Hitachi Ltd., 2012 + */ +#include <linux/kprobes.h> +#include <linux/ptrace.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/hardirq.h> +#include <linux/preempt.h> +#include <linux/module.h> +#include <linux/kdebug.h> +#include <linux/kallsyms.h> +#include <linux/ftrace.h> + +#include <asm/cacheflush.h> +#include <asm/desc.h> +#include <asm/pgtable.h> +#include <asm/uaccess.h> +#include <asm/alternative.h> +#include <asm/insn.h> +#include <asm/debugreg.h> + +#include "kprobes-common.h" + +unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) +{ + struct optimized_kprobe *op; + struct kprobe *kp; + long offs; + int i; + + for (i = 0; i < RELATIVEJUMP_SIZE; i++) { + kp = get_kprobe((void *)addr - i); + /* This function only handles jump-optimized kprobe */ + if (kp && kprobe_optimized(kp)) { + op = container_of(kp, struct optimized_kprobe, kp); + /* If op->list is not empty, op is under optimizing */ + if (list_empty(&op->list)) + goto found; + } + } + + return addr; +found: + /* + * If the kprobe can be optimized, original bytes which can be + * overwritten by jump destination address. In this case, original + * bytes must be recovered from op->optinsn.copied_insn buffer. + */ + memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + if (addr == (unsigned long)kp->addr) { + buf[0] = kp->opcode; + memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + } else { + offs = addr - (unsigned long)kp->addr - 1; + memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs); + } + + return (unsigned long)buf; +} + +/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ +static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) +{ +#ifdef CONFIG_X86_64 + *addr++ = 0x48; + *addr++ = 0xbf; +#else + *addr++ = 0xb8; +#endif + *(unsigned long *)addr = val; +} + +static void __used __kprobes kprobes_optinsn_template_holder(void) +{ + asm volatile ( + ".global optprobe_template_entry\n" + "optprobe_template_entry:\n" +#ifdef CONFIG_X86_64 + /* We don't bother saving the ss register */ + " pushq %rsp\n" + " pushfq\n" + SAVE_REGS_STRING + " movq %rsp, %rsi\n" + ".global optprobe_template_val\n" + "optprobe_template_val:\n" + ASM_NOP5 + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call:\n" + ASM_NOP5 + /* Move flags to rsp */ + " movq 144(%rsp), %rdx\n" + " movq %rdx, 152(%rsp)\n" + RESTORE_REGS_STRING + /* Skip flags entry */ + " addq $8, %rsp\n" + " popfq\n" +#else /* CONFIG_X86_32 */ + " pushf\n" + SAVE_REGS_STRING + " movl %esp, %edx\n" + ".global optprobe_template_val\n" + "optprobe_template_val:\n" + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call:\n" + ASM_NOP5 + RESTORE_REGS_STRING + " addl $4, %esp\n" /* skip cs */ + " popf\n" +#endif + ".global optprobe_template_end\n" + "optprobe_template_end:\n"); +} + +#define TMPL_MOVE_IDX \ + ((long)&optprobe_template_val - (long)&optprobe_template_entry) +#define TMPL_CALL_IDX \ + ((long)&optprobe_template_call - (long)&optprobe_template_entry) +#define TMPL_END_IDX \ + ((long)&optprobe_template_end - (long)&optprobe_template_entry) + +#define INT3_SIZE sizeof(kprobe_opcode_t) + +/* Optimized kprobe call back function: called from optinsn */ +static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long flags; + + /* This is possible if op is under delayed unoptimizing */ + if (kprobe_disabled(&op->kp)) + return; + + local_irq_save(flags); + if (kprobe_running()) { + kprobes_inc_nmissed_count(&op->kp); + } else { + /* Save skipped registers */ +#ifdef CONFIG_X86_64 + regs->cs = __KERNEL_CS; +#else + regs->cs = __KERNEL_CS | get_kernel_rpl(); + regs->gs = 0; +#endif + regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; + regs->orig_ax = ~0UL; + + __this_cpu_write(current_kprobe, &op->kp); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + opt_pre_handler(&op->kp, regs); + __this_cpu_write(current_kprobe, NULL); + } + local_irq_restore(flags); +} + +static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) +{ + int len = 0, ret; + + while (len < RELATIVEJUMP_SIZE) { + ret = __copy_instruction(dest + len, src + len); + if (!ret || !can_boost(dest + len)) + return -EINVAL; + len += ret; + } + /* Check whether the address range is reserved */ + if (ftrace_text_reserved(src, src + len - 1) || + alternatives_text_reserved(src, src + len - 1) || + jump_label_text_reserved(src, src + len - 1)) + return -EBUSY; + + return len; +} + +/* Check whether insn is indirect jump */ +static int __kprobes insn_is_indirect_jump(struct insn *insn) +{ + return ((insn->opcode.bytes[0] == 0xff && + (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ + insn->opcode.bytes[0] == 0xea); /* Segment based jump */ +} + +/* Check whether insn jumps into specified address range */ +static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) +{ + unsigned long target = 0; + + switch (insn->opcode.bytes[0]) { + case 0xe0: /* loopne */ + case 0xe1: /* loope */ + case 0xe2: /* loop */ + case 0xe3: /* jcxz */ + case 0xe9: /* near relative jump */ + case 0xeb: /* short relative jump */ + break; + case 0x0f: + if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */ + break; + return 0; + default: + if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */ + break; + return 0; + } + target = (unsigned long)insn->next_byte + insn->immediate.value; + + return (start <= target && target <= start + len); +} + +/* Decode whole function to ensure any instructions don't jump into target */ +static int __kprobes can_optimize(unsigned long paddr) +{ + unsigned long addr, size = 0, offset = 0; + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + + /* Lookup symbol including addr */ + if (!kallsyms_lookup_size_offset(paddr, &size, &offset)) + return 0; + + /* + * Do not optimize in the entry code due to the unstable + * stack handling. + */ + if ((paddr >= (unsigned long)__entry_text_start) && + (paddr < (unsigned long)__entry_text_end)) + return 0; + + /* Check there is enough space for a relative jump. */ + if (size - offset < RELATIVEJUMP_SIZE) + return 0; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr - offset + size) { /* Decode until function end */ + if (search_exception_tables(addr)) + /* + * Since some fixup code will jumps into this function, + * we can't optimize kprobe in this function. + */ + return 0; + kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr)); + insn_get_length(&insn); + /* Another subsystem puts a breakpoint */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + return 0; + /* Recover address */ + insn.kaddr = (void *)addr; + insn.next_byte = (void *)(addr + insn.length); + /* Check any instructions don't jump into target */ + if (insn_is_indirect_jump(&insn) || + insn_jump_into_range(&insn, paddr + INT3_SIZE, + RELATIVE_ADDR_SIZE)) + return 0; + addr += insn.length; + } + + return 1; +} + +/* Check optimized_kprobe can actually be optimized. */ +int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) +{ + int i; + struct kprobe *p; + + for (i = 1; i < op->optinsn.size; i++) { + p = get_kprobe(op->kp.addr + i); + if (p && !kprobe_disabled(p)) + return -EEXIST; + } + + return 0; +} + +/* Check the addr is within the optimized instructions. */ +int __kprobes +arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr) +{ + return ((unsigned long)op->kp.addr <= addr && + (unsigned long)op->kp.addr + op->optinsn.size > addr); +} + +/* Free optimized instruction slot */ +static __kprobes +void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) +{ + if (op->optinsn.insn) { + free_optinsn_slot(op->optinsn.insn, dirty); + op->optinsn.insn = NULL; + op->optinsn.size = 0; + } +} + +void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) +{ + __arch_remove_optimized_kprobe(op, 1); +} + +/* + * Copy replacing target instructions + * Target instructions MUST be relocatable (checked inside) + * This is called when new aggr(opt)probe is allocated or reused. + */ +int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) +{ + u8 *buf; + int ret; + long rel; + + if (!can_optimize((unsigned long)op->kp.addr)) + return -EILSEQ; + + op->optinsn.insn = get_optinsn_slot(); + if (!op->optinsn.insn) + return -ENOMEM; + + /* + * Verify if the address gap is in 2GB range, because this uses + * a relative jump. + */ + rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; + if (abs(rel) > 0x7fffffff) + return -ERANGE; + + buf = (u8 *)op->optinsn.insn; + + /* Copy instructions into the out-of-line buffer */ + ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); + if (ret < 0) { + __arch_remove_optimized_kprobe(op, 0); + return ret; + } + op->optinsn.size = ret; + + /* Copy arch-dep-instance from template */ + memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); + + /* Set probe information */ + synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); + + /* Set probe function call */ + synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); + + /* Set returning jmp instruction at the tail of out-of-line buffer */ + synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, + (u8 *)op->kp.addr + op->optinsn.size); + + flush_icache_range((unsigned long) buf, + (unsigned long) buf + TMPL_END_IDX + + op->optinsn.size + RELATIVEJUMP_SIZE); + return 0; +} + +#define MAX_OPTIMIZE_PROBES 256 +static struct text_poke_param *jump_poke_params; +static struct jump_poke_buffer { + u8 buf[RELATIVEJUMP_SIZE]; +} *jump_poke_bufs; + +static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) +{ + s32 rel = (s32)((long)op->optinsn.insn - + ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + + /* Backup instructions which will be replaced by jump address */ + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, + RELATIVE_ADDR_SIZE); + + insn_buf[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&insn_buf[1]) = rel; + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Replace breakpoints (int3) with relative jumps. + * Caller must call with locking kprobe_mutex and text_mutex. + */ +void __kprobes arch_optimize_kprobes(struct list_head *oplist) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + WARN_ON(kprobe_disabled(&op->kp)); + /* Setup param */ + setup_optimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_del_init(&op->list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } + + /* + * text_poke_smp doesn't support NMI/MCE code modifying. + * However, since kprobes itself also doesn't support NMI/MCE + * code probing, it's not a problem. + */ + text_poke_smp_batch(jump_poke_params, c); +} + +static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) +{ + /* Set int3 to first byte for kprobes */ + insn_buf[0] = BREAKPOINT_INSTRUCTION; + memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Recover original instructions and breakpoints from relative jumps. + * Caller must call with locking kprobe_mutex. + */ +extern void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + /* Setup param */ + setup_unoptimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_move(&op->list, done_list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } + + /* + * text_poke_smp doesn't support NMI/MCE code modifying. + * However, since kprobes itself also doesn't support NMI/MCE + * code probing, it's not a problem. + */ + text_poke_smp_batch(jump_poke_params, c); +} + +/* Replace a relative jump with a breakpoint (int3). */ +void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) +{ + u8 buf[RELATIVEJUMP_SIZE]; + + /* Set int3 to first byte for kprobes */ + buf[0] = BREAKPOINT_INSTRUCTION; + memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); +} + +int __kprobes +setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) +{ + struct optimized_kprobe *op; + + if (p->flags & KPROBE_FLAG_OPTIMIZED) { + /* This kprobe is really able to run optimized path. */ + op = container_of(p, struct optimized_kprobe, kp); + /* Detour through copied instructions */ + regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; + if (!reenter) + reset_current_kprobe(); + preempt_enable_no_resched(); + return 1; + } + return 0; +} + +int __kprobes arch_init_optprobes(void) +{ + /* Allocate code buffer and parameter array */ + jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_bufs) + return -ENOMEM; + + jump_poke_params = kmalloc(sizeof(struct text_poke_param) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_params) { + kfree(jump_poke_bufs); + jump_poke_bufs = NULL; + return -ENOMEM; + } + + return 0; +} diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 7da647d8b64..e213fc8408d 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -30,16 +30,15 @@ * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi * <prasanna@in.ibm.com> added function-return probes. * 2005-May Rusty Lynch <rusty.lynch@intel.com> - * Added function return probes functionality + * Added function return probes functionality * 2006-Feb Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added - * kprobe-booster and kretprobe-booster for i386. + * kprobe-booster and kretprobe-booster for i386. * 2007-Dec Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster - * and kretprobe-booster for x86-64 + * and kretprobe-booster for x86-64 * 2007-Dec Masami Hiramatsu <mhiramat@redhat.com>, Arjan van de Ven - * <arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com> - * unified x86 kprobes code. + * <arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com> + * unified x86 kprobes code. */ - #include <linux/kprobes.h> #include <linux/ptrace.h> #include <linux/string.h> @@ -59,6 +58,8 @@ #include <asm/insn.h> #include <asm/debugreg.h> +#include "kprobes-common.h" + void jprobe_return_end(void); DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; @@ -108,6 +109,7 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = { doesn't switch kernel stack.*/ {NULL, NULL} /* Terminator */ }; + const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) @@ -123,11 +125,17 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) } /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ -static void __kprobes synthesize_reljump(void *from, void *to) +void __kprobes synthesize_reljump(void *from, void *to) { __synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE); } +/* Insert a call instruction at address 'from', which calls address 'to'.*/ +void __kprobes synthesize_relcall(void *from, void *to) +{ + __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); +} + /* * Skip the prefixes of the instruction. */ @@ -151,7 +159,7 @@ static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) * Returns non-zero if opcode is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ -static int __kprobes can_boost(kprobe_opcode_t *opcodes) +int __kprobes can_boost(kprobe_opcode_t *opcodes) { kprobe_opcode_t opcode; kprobe_opcode_t *orig_opcodes = opcodes; @@ -207,13 +215,15 @@ retry: } } -/* Recover the probed instruction at addr for further analysis. */ -static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) +static unsigned long +__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) { struct kprobe *kp; + kp = get_kprobe((void *)addr); + /* There is no probe, return original address */ if (!kp) - return -EINVAL; + return addr; /* * Basically, kp->ainsn.insn has an original instruction. @@ -230,14 +240,29 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) */ memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); buf[0] = kp->opcode; - return 0; + return (unsigned long)buf; +} + +/* + * Recover the probed instruction at addr for further analysis. + * Caller must lock kprobes by kprobe_mutex, or disable preemption + * for preventing to release referencing kprobes. + */ +unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) +{ + unsigned long __addr; + + __addr = __recover_optprobed_insn(buf, addr); + if (__addr != addr) + return __addr; + + return __recover_probed_insn(buf, addr); } /* Check if paddr is at an instruction boundary */ static int __kprobes can_probe(unsigned long paddr) { - int ret; - unsigned long addr, offset = 0; + unsigned long addr, __addr, offset = 0; struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; @@ -247,26 +272,24 @@ static int __kprobes can_probe(unsigned long paddr) /* Decode instructions */ addr = paddr - offset; while (addr < paddr) { - kernel_insn_init(&insn, (void *)addr); - insn_get_opcode(&insn); - /* * Check if the instruction has been modified by another * kprobe, in which case we replace the breakpoint by the * original instruction in our buffer. + * Also, jump optimization will change the breakpoint to + * relative-jump. Since the relative-jump itself is + * normally used, we just go through if there is no kprobe. */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { - ret = recover_probed_instruction(buf, addr); - if (ret) - /* - * Another debugging subsystem might insert - * this breakpoint. In that case, we can't - * recover it. - */ - return 0; - kernel_insn_init(&insn, buf); - } + __addr = recover_probed_instruction(buf, addr); + kernel_insn_init(&insn, (void *)__addr); insn_get_length(&insn); + + /* + * Another debugging subsystem might insert this breakpoint. + * In that case, we can't recover it. + */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + return 0; addr += insn.length; } @@ -299,24 +322,16 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) * If not, return null. * Only applicable to 64-bit x86. */ -static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover) +int __kprobes __copy_instruction(u8 *dest, u8 *src) { struct insn insn; - int ret; kprobe_opcode_t buf[MAX_INSN_SIZE]; - kernel_insn_init(&insn, src); - if (recover) { - insn_get_opcode(&insn); - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { - ret = recover_probed_instruction(buf, - (unsigned long)src); - if (ret) - return 0; - kernel_insn_init(&insn, buf); - } - } + kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src)); insn_get_length(&insn); + /* Another subsystem puts a breakpoint, failed to recover */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + return 0; memcpy(dest, insn.kaddr, insn.length); #ifdef CONFIG_X86_64 @@ -337,8 +352,7 @@ static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover) * extension of the original signed 32-bit displacement would * have given. */ - newdisp = (u8 *) src + (s64) insn.displacement.value - - (u8 *) dest; + newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest; BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */ disp = (u8 *) dest + insn_offset_displacement(&insn); *(s32 *) disp = (s32) newdisp; @@ -349,18 +363,20 @@ static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover) static void __kprobes arch_copy_kprobe(struct kprobe *p) { + /* Copy an instruction with recovering if other optprobe modifies it.*/ + __copy_instruction(p->ainsn.insn, p->addr); + /* - * Copy an instruction without recovering int3, because it will be - * put by another subsystem. + * __copy_instruction can modify the displacement of the instruction, + * but it doesn't affect boostable check. */ - __copy_instruction(p->ainsn.insn, p->addr, 0); - - if (can_boost(p->addr)) + if (can_boost(p->ainsn.insn)) p->ainsn.boostable = 0; else p->ainsn.boostable = -1; - p->opcode = *p->addr; + /* Also, displacement change doesn't affect the first byte */ + p->opcode = p->ainsn.insn[0]; } int __kprobes arch_prepare_kprobe(struct kprobe *p) @@ -442,8 +458,8 @@ static void __kprobes restore_btf(void) } } -void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, - struct pt_regs *regs) +void __kprobes +arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { unsigned long *sara = stack_addr(regs); @@ -453,16 +469,8 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, *sara = (unsigned long) &kretprobe_trampoline; } -#ifdef CONFIG_OPTPROBES -static int __kprobes setup_detour_execution(struct kprobe *p, - struct pt_regs *regs, - int reenter); -#else -#define setup_detour_execution(p, regs, reenter) (0) -#endif - -static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb, int reenter) +static void __kprobes +setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter) { if (setup_detour_execution(p, regs, reenter)) return; @@ -504,8 +512,8 @@ static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs, * within the handler. We save the original kprobes variables and just single * step on the instruction of the new probe without calling any user handlers. */ -static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) +static int __kprobes +reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { switch (kcb->kprobe_status) { case KPROBE_HIT_SSDONE: @@ -600,69 +608,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) return 0; } -#ifdef CONFIG_X86_64 -#define SAVE_REGS_STRING \ - /* Skip cs, ip, orig_ax. */ \ - " subq $24, %rsp\n" \ - " pushq %rdi\n" \ - " pushq %rsi\n" \ - " pushq %rdx\n" \ - " pushq %rcx\n" \ - " pushq %rax\n" \ - " pushq %r8\n" \ - " pushq %r9\n" \ - " pushq %r10\n" \ - " pushq %r11\n" \ - " pushq %rbx\n" \ - " pushq %rbp\n" \ - " pushq %r12\n" \ - " pushq %r13\n" \ - " pushq %r14\n" \ - " pushq %r15\n" -#define RESTORE_REGS_STRING \ - " popq %r15\n" \ - " popq %r14\n" \ - " popq %r13\n" \ - " popq %r12\n" \ - " popq %rbp\n" \ - " popq %rbx\n" \ - " popq %r11\n" \ - " popq %r10\n" \ - " popq %r9\n" \ - " popq %r8\n" \ - " popq %rax\n" \ - " popq %rcx\n" \ - " popq %rdx\n" \ - " popq %rsi\n" \ - " popq %rdi\n" \ - /* Skip orig_ax, ip, cs */ \ - " addq $24, %rsp\n" -#else -#define SAVE_REGS_STRING \ - /* Skip cs, ip, orig_ax and gs. */ \ - " subl $16, %esp\n" \ - " pushl %fs\n" \ - " pushl %es\n" \ - " pushl %ds\n" \ - " pushl %eax\n" \ - " pushl %ebp\n" \ - " pushl %edi\n" \ - " pushl %esi\n" \ - " pushl %edx\n" \ - " pushl %ecx\n" \ - " pushl %ebx\n" -#define RESTORE_REGS_STRING \ - " popl %ebx\n" \ - " popl %ecx\n" \ - " popl %edx\n" \ - " popl %esi\n" \ - " popl %edi\n" \ - " popl %ebp\n" \ - " popl %eax\n" \ - /* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\ - " addl $24, %esp\n" -#endif - /* * When a retprobed function returns, this code saves registers and * calls trampoline_handler() runs, which calls the kretprobe's handler. @@ -816,8 +761,8 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) * jump instruction after the copied instruction, that jumps to the next * instruction after the probepoint. */ -static void __kprobes resume_execution(struct kprobe *p, - struct pt_regs *regs, struct kprobe_ctlblk *kcb) +static void __kprobes +resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { unsigned long *tos = stack_addr(regs); unsigned long copy_ip = (unsigned long)p->ainsn.insn; @@ -996,8 +941,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) /* * Wrapper routine for handling exceptions. */ -int __kprobes kprobe_exceptions_notify(struct notifier_block *self, - unsigned long val, void *data) +int __kprobes +kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) { struct die_args *args = data; int ret = NOTIFY_DONE; @@ -1107,466 +1052,9 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } - -#ifdef CONFIG_OPTPROBES - -/* Insert a call instruction at address 'from', which calls address 'to'.*/ -static void __kprobes synthesize_relcall(void *from, void *to) -{ - __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); -} - -/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ -static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, - unsigned long val) -{ -#ifdef CONFIG_X86_64 - *addr++ = 0x48; - *addr++ = 0xbf; -#else - *addr++ = 0xb8; -#endif - *(unsigned long *)addr = val; -} - -static void __used __kprobes kprobes_optinsn_template_holder(void) -{ - asm volatile ( - ".global optprobe_template_entry\n" - "optprobe_template_entry: \n" -#ifdef CONFIG_X86_64 - /* We don't bother saving the ss register */ - " pushq %rsp\n" - " pushfq\n" - SAVE_REGS_STRING - " movq %rsp, %rsi\n" - ".global optprobe_template_val\n" - "optprobe_template_val: \n" - ASM_NOP5 - ASM_NOP5 - ".global optprobe_template_call\n" - "optprobe_template_call: \n" - ASM_NOP5 - /* Move flags to rsp */ - " movq 144(%rsp), %rdx\n" - " movq %rdx, 152(%rsp)\n" - RESTORE_REGS_STRING - /* Skip flags entry */ - " addq $8, %rsp\n" - " popfq\n" -#else /* CONFIG_X86_32 */ - " pushf\n" - SAVE_REGS_STRING - " movl %esp, %edx\n" - ".global optprobe_template_val\n" - "optprobe_template_val: \n" - ASM_NOP5 - ".global optprobe_template_call\n" - "optprobe_template_call: \n" - ASM_NOP5 - RESTORE_REGS_STRING - " addl $4, %esp\n" /* skip cs */ - " popf\n" -#endif - ".global optprobe_template_end\n" - "optprobe_template_end: \n"); -} - -#define TMPL_MOVE_IDX \ - ((long)&optprobe_template_val - (long)&optprobe_template_entry) -#define TMPL_CALL_IDX \ - ((long)&optprobe_template_call - (long)&optprobe_template_entry) -#define TMPL_END_IDX \ - ((long)&optprobe_template_end - (long)&optprobe_template_entry) - -#define INT3_SIZE sizeof(kprobe_opcode_t) - -/* Optimized kprobe call back function: called from optinsn */ -static void __kprobes optimized_callback(struct optimized_kprobe *op, - struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long flags; - - /* This is possible if op is under delayed unoptimizing */ - if (kprobe_disabled(&op->kp)) - return; - - local_irq_save(flags); - if (kprobe_running()) { - kprobes_inc_nmissed_count(&op->kp); - } else { - /* Save skipped registers */ -#ifdef CONFIG_X86_64 - regs->cs = __KERNEL_CS; -#else - regs->cs = __KERNEL_CS | get_kernel_rpl(); - regs->gs = 0; -#endif - regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; - regs->orig_ax = ~0UL; - - __this_cpu_write(current_kprobe, &op->kp); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; - opt_pre_handler(&op->kp, regs); - __this_cpu_write(current_kprobe, NULL); - } - local_irq_restore(flags); -} - -static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) -{ - int len = 0, ret; - - while (len < RELATIVEJUMP_SIZE) { - ret = __copy_instruction(dest + len, src + len, 1); - if (!ret || !can_boost(dest + len)) - return -EINVAL; - len += ret; - } - /* Check whether the address range is reserved */ - if (ftrace_text_reserved(src, src + len - 1) || - alternatives_text_reserved(src, src + len - 1) || - jump_label_text_reserved(src, src + len - 1)) - return -EBUSY; - - return len; -} - -/* Check whether insn is indirect jump */ -static int __kprobes insn_is_indirect_jump(struct insn *insn) -{ - return ((insn->opcode.bytes[0] == 0xff && - (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ - insn->opcode.bytes[0] == 0xea); /* Segment based jump */ -} - -/* Check whether insn jumps into specified address range */ -static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) -{ - unsigned long target = 0; - - switch (insn->opcode.bytes[0]) { - case 0xe0: /* loopne */ - case 0xe1: /* loope */ - case 0xe2: /* loop */ - case 0xe3: /* jcxz */ - case 0xe9: /* near relative jump */ - case 0xeb: /* short relative jump */ - break; - case 0x0f: - if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */ - break; - return 0; - default: - if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */ - break; - return 0; - } - target = (unsigned long)insn->next_byte + insn->immediate.value; - - return (start <= target && target <= start + len); -} - -/* Decode whole function to ensure any instructions don't jump into target */ -static int __kprobes can_optimize(unsigned long paddr) -{ - int ret; - unsigned long addr, size = 0, offset = 0; - struct insn insn; - kprobe_opcode_t buf[MAX_INSN_SIZE]; - - /* Lookup symbol including addr */ - if (!kallsyms_lookup_size_offset(paddr, &size, &offset)) - return 0; - - /* - * Do not optimize in the entry code due to the unstable - * stack handling. - */ - if ((paddr >= (unsigned long )__entry_text_start) && - (paddr < (unsigned long )__entry_text_end)) - return 0; - - /* Check there is enough space for a relative jump. */ - if (size - offset < RELATIVEJUMP_SIZE) - return 0; - - /* Decode instructions */ - addr = paddr - offset; - while (addr < paddr - offset + size) { /* Decode until function end */ - if (search_exception_tables(addr)) - /* - * Since some fixup code will jumps into this function, - * we can't optimize kprobe in this function. - */ - return 0; - kernel_insn_init(&insn, (void *)addr); - insn_get_opcode(&insn); - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { - ret = recover_probed_instruction(buf, addr); - if (ret) - return 0; - kernel_insn_init(&insn, buf); - } - insn_get_length(&insn); - /* Recover address */ - insn.kaddr = (void *)addr; - insn.next_byte = (void *)(addr + insn.length); - /* Check any instructions don't jump into target */ - if (insn_is_indirect_jump(&insn) || - insn_jump_into_range(&insn, paddr + INT3_SIZE, - RELATIVE_ADDR_SIZE)) - return 0; - addr += insn.length; - } - - return 1; -} - -/* Check optimized_kprobe can actually be optimized. */ -int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) -{ - int i; - struct kprobe *p; - - for (i = 1; i < op->optinsn.size; i++) { - p = get_kprobe(op->kp.addr + i); - if (p && !kprobe_disabled(p)) - return -EEXIST; - } - - return 0; -} - -/* Check the addr is within the optimized instructions. */ -int __kprobes arch_within_optimized_kprobe(struct optimized_kprobe *op, - unsigned long addr) -{ - return ((unsigned long)op->kp.addr <= addr && - (unsigned long)op->kp.addr + op->optinsn.size > addr); -} - -/* Free optimized instruction slot */ -static __kprobes -void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) -{ - if (op->optinsn.insn) { - free_optinsn_slot(op->optinsn.insn, dirty); - op->optinsn.insn = NULL; - op->optinsn.size = 0; - } -} - -void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) -{ - __arch_remove_optimized_kprobe(op, 1); -} - -/* - * Copy replacing target instructions - * Target instructions MUST be relocatable (checked inside) - */ -int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) -{ - u8 *buf; - int ret; - long rel; - - if (!can_optimize((unsigned long)op->kp.addr)) - return -EILSEQ; - - op->optinsn.insn = get_optinsn_slot(); - if (!op->optinsn.insn) - return -ENOMEM; - - /* - * Verify if the address gap is in 2GB range, because this uses - * a relative jump. - */ - rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; - if (abs(rel) > 0x7fffffff) - return -ERANGE; - - buf = (u8 *)op->optinsn.insn; - - /* Copy instructions into the out-of-line buffer */ - ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); - if (ret < 0) { - __arch_remove_optimized_kprobe(op, 0); - return ret; - } - op->optinsn.size = ret; - - /* Copy arch-dep-instance from template */ - memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); - - /* Set probe information */ - synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); - - /* Set probe function call */ - synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); - - /* Set returning jmp instruction at the tail of out-of-line buffer */ - synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, - (u8 *)op->kp.addr + op->optinsn.size); - - flush_icache_range((unsigned long) buf, - (unsigned long) buf + TMPL_END_IDX + - op->optinsn.size + RELATIVEJUMP_SIZE); - return 0; -} - -#define MAX_OPTIMIZE_PROBES 256 -static struct text_poke_param *jump_poke_params; -static struct jump_poke_buffer { - u8 buf[RELATIVEJUMP_SIZE]; -} *jump_poke_bufs; - -static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) -{ - s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); - - /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); - - insn_buf[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&insn_buf[1]) = rel; - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; -} - -/* - * Replace breakpoints (int3) with relative jumps. - * Caller must call with locking kprobe_mutex and text_mutex. - */ -void __kprobes arch_optimize_kprobes(struct list_head *oplist) -{ - struct optimized_kprobe *op, *tmp; - int c = 0; - - list_for_each_entry_safe(op, tmp, oplist, list) { - WARN_ON(kprobe_disabled(&op->kp)); - /* Setup param */ - setup_optimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); - list_del_init(&op->list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; - } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); -} - -static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) -{ - /* Set int3 to first byte for kprobes */ - insn_buf[0] = BREAKPOINT_INSTRUCTION; - memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; -} - -/* - * Recover original instructions and breakpoints from relative jumps. - * Caller must call with locking kprobe_mutex. - */ -extern void arch_unoptimize_kprobes(struct list_head *oplist, - struct list_head *done_list) -{ - struct optimized_kprobe *op, *tmp; - int c = 0; - - list_for_each_entry_safe(op, tmp, oplist, list) { - /* Setup param */ - setup_unoptimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); - list_move(&op->list, done_list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; - } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); -} - -/* Replace a relative jump with a breakpoint (int3). */ -void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) -{ - u8 buf[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - buf[0] = BREAKPOINT_INSTRUCTION; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); -} - -static int __kprobes setup_detour_execution(struct kprobe *p, - struct pt_regs *regs, - int reenter) -{ - struct optimized_kprobe *op; - - if (p->flags & KPROBE_FLAG_OPTIMIZED) { - /* This kprobe is really able to run optimized path. */ - op = container_of(p, struct optimized_kprobe, kp); - /* Detour through copied instructions */ - regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; - if (!reenter) - reset_current_kprobe(); - preempt_enable_no_resched(); - return 1; - } - return 0; -} - -static int __kprobes init_poke_params(void) -{ - /* Allocate code buffer and parameter array */ - jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_bufs) - return -ENOMEM; - - jump_poke_params = kmalloc(sizeof(struct text_poke_param) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_params) { - kfree(jump_poke_bufs); - jump_poke_bufs = NULL; - return -ENOMEM; - } - - return 0; -} -#else /* !CONFIG_OPTPROBES */ -static int __kprobes init_poke_params(void) -{ - return 0; -} -#endif - int __init arch_init_kprobes(void) { - return init_poke_params(); + return arch_init_optprobes(); } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index f0c6fd6f176..694d801bf60 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -438,9 +438,9 @@ void __init kvm_guest_init(void) static __init int activate_jump_labels(void) { if (has_steal_clock) { - jump_label_inc(¶virt_steal_enabled); + static_key_slow_inc(¶virt_steal_enabled); if (steal_acc) - jump_label_inc(¶virt_steal_rq_enabled); + static_key_slow_inc(¶virt_steal_rq_enabled); } return 0; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 44842d756b2..f8492da65bf 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -136,6 +136,15 @@ int kvm_register_clock(char *txt) return ret; } +static void kvm_save_sched_clock_state(void) +{ +} + +static void kvm_restore_sched_clock_state(void) +{ + kvm_register_clock("primary cpu clock, resume"); +} + #ifdef CONFIG_X86_LOCAL_APIC static void __cpuinit kvm_setup_secondary_clock(void) { @@ -144,8 +153,6 @@ static void __cpuinit kvm_setup_secondary_clock(void) * we shouldn't fail. */ WARN_ON(kvm_register_clock("secondary cpu clock")); - /* ok, done with our trickery, call native */ - setup_secondary_APIC_clock(); } #endif @@ -194,9 +201,11 @@ void __init kvmclock_init(void) x86_platform.get_wallclock = kvm_get_wallclock; x86_platform.set_wallclock = kvm_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC - x86_cpuinit.setup_percpu_clockev = + x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock; #endif + x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; + x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; machine_ops.shutdown = kvm_shutdown; #ifdef CONFIG_KEXEC machine_ops.crash_shutdown = kvm_crash_shutdown; diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index fe86493f3ed..73465aab28f 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -311,13 +311,33 @@ out: return state; } +/* + * AMD microcode firmware naming convention, up to family 15h they are in + * the legacy file: + * + * amd-ucode/microcode_amd.bin + * + * This legacy file is always smaller than 2K in size. + * + * Starting at family 15h they are in family specific firmware files: + * + * amd-ucode/microcode_amd_fam15h.bin + * amd-ucode/microcode_amd_fam16h.bin + * ... + * + * These might be larger than 2K. + */ static enum ucode_state request_microcode_amd(int cpu, struct device *device) { - const char *fw_name = "amd-ucode/microcode_amd.bin"; + char fw_name[36] = "amd-ucode/microcode_amd.bin"; const struct firmware *fw; enum ucode_state ret = UCODE_NFOUND; + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86 >= 0x15) + snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); - if (request_firmware(&fw, fw_name, device)) { + if (request_firmware(&fw, (const char *)fw_name, device)) { pr_err("failed to load file %s\n", fw_name); goto out; } @@ -340,7 +360,6 @@ out: static enum ucode_state request_microcode_user(int cpu, const void __user *buf, size_t size) { - pr_info("AMD microcode update via /dev/cpu/microcode not supported\n"); return UCODE_ERROR; } diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index fda91c30710..87a0f868830 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -86,6 +86,7 @@ #include <asm/microcode.h> #include <asm/processor.h> +#include <asm/cpu_device_id.h> MODULE_DESCRIPTION("Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); @@ -504,6 +505,20 @@ static struct notifier_block __refdata mc_cpu_notifier = { .notifier_call = mc_cpu_callback, }; +#ifdef MODULE +/* Autoload on Intel and AMD systems */ +static const struct x86_cpu_id microcode_id[] = { +#ifdef CONFIG_MICROCODE_INTEL + { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, }, +#endif +#ifdef CONFIG_MICROCODE_AMD + { X86_VENDOR_AMD, X86_FAMILY_ANY, X86_MODEL_ANY, }, +#endif + {} +}; +MODULE_DEVICE_TABLE(x86cpu, microcode_id); +#endif + static int __init microcode_init(void) { struct cpuinfo_x86 *c = &cpu_data(0); diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c index 0d01a8ea4e1..2c39dcd510f 100644 --- a/arch/x86/kernel/nmi_selftest.c +++ b/arch/x86/kernel/nmi_selftest.c @@ -12,6 +12,7 @@ #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/delay.h> +#include <linux/init.h> #include <asm/apic.h> #include <asm/nmi.h> @@ -20,35 +21,35 @@ #define FAILURE 1 #define TIMEOUT 2 -static int nmi_fail; +static int __initdata nmi_fail; /* check to see if NMI IPIs work on this machine */ -static DECLARE_BITMAP(nmi_ipi_mask, NR_CPUS) __read_mostly; +static DECLARE_BITMAP(nmi_ipi_mask, NR_CPUS) __initdata; -static int testcase_total; -static int testcase_successes; -static int expected_testcase_failures; -static int unexpected_testcase_failures; -static int unexpected_testcase_unknowns; +static int __initdata testcase_total; +static int __initdata testcase_successes; +static int __initdata expected_testcase_failures; +static int __initdata unexpected_testcase_failures; +static int __initdata unexpected_testcase_unknowns; -static int nmi_unk_cb(unsigned int val, struct pt_regs *regs) +static int __init nmi_unk_cb(unsigned int val, struct pt_regs *regs) { unexpected_testcase_unknowns++; return NMI_HANDLED; } -static void init_nmi_testsuite(void) +static void __init init_nmi_testsuite(void) { /* trap all the unknown NMIs we may generate */ register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk"); } -static void cleanup_nmi_testsuite(void) +static void __init cleanup_nmi_testsuite(void) { unregister_nmi_handler(NMI_UNKNOWN, "nmi_selftest_unk"); } -static int test_nmi_ipi_callback(unsigned int val, struct pt_regs *regs) +static int __init test_nmi_ipi_callback(unsigned int val, struct pt_regs *regs) { int cpu = raw_smp_processor_id(); @@ -58,7 +59,7 @@ static int test_nmi_ipi_callback(unsigned int val, struct pt_regs *regs) return NMI_DONE; } -static void test_nmi_ipi(struct cpumask *mask) +static void __init test_nmi_ipi(struct cpumask *mask) { unsigned long timeout; @@ -86,7 +87,7 @@ static void test_nmi_ipi(struct cpumask *mask) return; } -static void remote_ipi(void) +static void __init remote_ipi(void) { cpumask_copy(to_cpumask(nmi_ipi_mask), cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), to_cpumask(nmi_ipi_mask)); @@ -94,19 +95,19 @@ static void remote_ipi(void) test_nmi_ipi(to_cpumask(nmi_ipi_mask)); } -static void local_ipi(void) +static void __init local_ipi(void) { cpumask_clear(to_cpumask(nmi_ipi_mask)); cpumask_set_cpu(smp_processor_id(), to_cpumask(nmi_ipi_mask)); test_nmi_ipi(to_cpumask(nmi_ipi_mask)); } -static void reset_nmi(void) +static void __init reset_nmi(void) { nmi_fail = 0; } -static void dotest(void (*testcase_fn)(void), int expected) +static void __init dotest(void (*testcase_fn)(void), int expected) { testcase_fn(); /* @@ -131,12 +132,12 @@ static void dotest(void (*testcase_fn)(void), int expected) reset_nmi(); } -static inline void print_testname(const char *testname) +static inline void __init print_testname(const char *testname) { printk("%12s:", testname); } -void nmi_selftest(void) +void __init nmi_selftest(void) { init_nmi_testsuite(); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index d90272e6bc4..9c57c02e54f 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -26,6 +26,7 @@ #include <asm/bug.h> #include <asm/paravirt.h> +#include <asm/debugreg.h> #include <asm/desc.h> #include <asm/setup.h> #include <asm/pgtable.h> @@ -202,8 +203,8 @@ static void native_flush_tlb_single(unsigned long addr) __native_flush_tlb_single(addr); } -struct jump_label_key paravirt_steal_enabled; -struct jump_label_key paravirt_steal_rq_enabled; +struct static_key paravirt_steal_enabled; +struct static_key paravirt_steal_rq_enabled; static u64 native_steal_clock(int cpu) { diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 1c4d769e21e..28e5e06fcba 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -262,10 +262,11 @@ rootfs_initcall(pci_iommu_init); static __devinit void via_no_dac(struct pci_dev *dev) { - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) { + if (forbid_dac == 0) { dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n"); forbid_dac = 1; } } -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac); +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, + PCI_CLASS_BRIDGE_PCI, 8, via_no_dac); #endif diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 34e06e84ce3..0bc72e2069e 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -12,6 +12,7 @@ #include <linux/pci.h> #include <linux/export.h> +#include <asm/probe_roms.h> #include <asm/pci-direct.h> #include <asm/e820.h> #include <asm/mmzone.h> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 15763af7bfe..14baf78d5a1 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -21,6 +21,7 @@ #include <asm/idle.h> #include <asm/uaccess.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/debugreg.h> struct kmem_cache *task_xstate_cachep; @@ -377,8 +378,8 @@ static inline int hlt_use_halt(void) void default_idle(void) { if (hlt_use_halt()) { - trace_power_start(POWER_CSTATE, 1, smp_processor_id()); - trace_cpu_idle(1, smp_processor_id()); + 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 @@ -391,8 +392,8 @@ void default_idle(void) else local_irq_enable(); current_thread_info()->status |= TS_POLLING; - trace_power_end(smp_processor_id()); - trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); + trace_power_end_rcuidle(smp_processor_id()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else { local_irq_enable(); /* loop is done by the caller */ @@ -450,8 +451,8 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); static void mwait_idle(void) { if (!need_resched()) { - trace_power_start(POWER_CSTATE, 1, smp_processor_id()); - trace_cpu_idle(1, smp_processor_id()); + trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -461,8 +462,8 @@ static void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); - trace_power_end(smp_processor_id()); - trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); + trace_power_end_rcuidle(smp_processor_id()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else local_irq_enable(); } @@ -474,13 +475,13 @@ static void mwait_idle(void) */ static void poll_idle(void) { - trace_power_start(POWER_CSTATE, 0, smp_processor_id()); - trace_cpu_idle(0, smp_processor_id()); + trace_power_start_rcuidle(POWER_CSTATE, 0, smp_processor_id()); + trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); - trace_power_end(smp_processor_id()); - trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); + trace_power_end_rcuidle(smp_processor_id()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 485204f58cd..9d7d4842bfa 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -45,6 +45,7 @@ #include <asm/ldt.h> #include <asm/processor.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/desc.h> #ifdef CONFIG_MATH_EMULATION #include <asm/math_emu.h> @@ -119,9 +120,7 @@ void cpu_idle(void) } rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } @@ -214,6 +213,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, task_user_gs(p) = get_user_gs(regs); + p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; tsk = current; err = -ENOMEM; @@ -299,22 +299,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) *next = &next_p->thread; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); - bool preload_fpu; + fpu_switch_t fpu; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - /* - * If the task has used fpu the last 5 timeslices, just do a full - * restore of the math state immediately to avoid the trap; the - * chances of needing FPU soon are obviously high now - */ - preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5; - - __unlazy_fpu(prev_p); - - /* we're going to use this soon, after a few expensive things */ - if (preload_fpu) - prefetch(next->fpu.state); + fpu = switch_fpu_prepare(prev_p, next_p, cpu); /* * Reload esp0. @@ -354,11 +343,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) __switch_to_xtra(prev_p, next_p, tss); - /* If we're going to preload the fpu context, make sure clts - is run while we're batching the cpu state updates. */ - if (preload_fpu) - clts(); - /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -368,15 +352,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ arch_end_context_switch(next_p); - if (preload_fpu) - __math_state_restore(); - /* * Restore %gs if needed (which is common) */ if (prev->gs | next->gs) lazy_load_gs(next->gs); + switch_fpu_finish(next_p, fpu); + percpu_write(current_task, next_p); return prev_p; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9b9fe4a85c8..292da13fc5a 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -43,6 +43,7 @@ #include <asm/system.h> #include <asm/processor.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/mmu_context.h> #include <asm/prctl.h> #include <asm/desc.h> @@ -156,9 +157,7 @@ void cpu_idle(void) } tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } @@ -286,6 +285,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, set_tsk_thread_flag(p, TIF_FORK); + p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); @@ -341,6 +341,7 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, loadsegment(es, _ds); loadsegment(ds, _ds); load_gs_index(0); + current->thread.usersp = new_sp; regs->ip = new_ip; regs->sp = new_sp; percpu_write(old_rsp, new_sp); @@ -386,18 +387,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); unsigned fsindex, gsindex; - bool preload_fpu; + fpu_switch_t fpu; - /* - * If the task has used fpu the last 5 timeslices, just do a full - * restore of the math state immediately to avoid the trap; the - * chances of needing FPU soon are obviously high now - */ - preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5; - - /* we're going to use this soon, after a few expensive things */ - if (preload_fpu) - prefetch(next->fpu.state); + fpu = switch_fpu_prepare(prev_p, next_p, cpu); /* * Reload esp0, LDT and the page table pointer: @@ -427,13 +419,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) load_TLS(next, cpu); - /* Must be after DS reload */ - __unlazy_fpu(prev_p); - - /* Make sure cpu is ready for new context */ - if (preload_fpu) - clts(); - /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -474,6 +459,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) wrmsrl(MSR_KERNEL_GS_BASE, next->gs); prev->gsindex = gsindex; + switch_fpu_finish(next_p, fpu); + /* * Switch the PDA and FPU contexts. */ @@ -492,13 +479,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); - /* - * Preload the FPU context, now that we've determined that the - * task is likely to be using it. - */ - if (preload_fpu) - __math_state_restore(); - return prev_p; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 50267386b76..78f05e438be 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -27,6 +27,7 @@ #include <asm/system.h> #include <asm/processor.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/debugreg.h> #include <asm/ldt.h> #include <asm/desc.h> diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 37a458b521a..d840e69a853 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -39,6 +39,14 @@ static int reboot_mode; enum reboot_type reboot_type = BOOT_ACPI; int reboot_force; +/* This variable is used privately to keep track of whether or not + * reboot_type is still set to its default value (i.e., reboot= hasn't + * been set on the command line). This is needed so that we can + * suppress DMI scanning for reboot quirks. Without it, it's + * impossible to override a faulty reboot quirk without recompiling. + */ +static int reboot_default = 1; + #if defined(CONFIG_X86_32) && defined(CONFIG_SMP) static int reboot_cpu = -1; #endif @@ -67,6 +75,12 @@ bool port_cf9_safe = false; static int __init reboot_setup(char *str) { for (;;) { + /* Having anything passed on the command line via + * reboot= will cause us to disable DMI checking + * below. + */ + reboot_default = 0; + switch (*str) { case 'w': reboot_mode = 0x1234; @@ -295,14 +309,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P4S800"), }, }, - { /* Handle problems with rebooting on VersaLogic Menlow boards */ - .callback = set_bios_reboot, - .ident = "VersaLogic Menlow based board", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"), - DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"), - }, - }, { /* Handle reboot issue on Acer Aspire one */ .callback = set_kbd_reboot, .ident = "Acer Aspire One A110", @@ -316,7 +322,12 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { static int __init reboot_init(void) { - dmi_check_system(reboot_dmi_table); + /* Only do the DMI check if reboot_type hasn't been overridden + * on the command line + */ + if (reboot_default) { + dmi_check_system(reboot_dmi_table); + } return 0; } core_initcall(reboot_init); @@ -465,7 +476,12 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = { static int __init pci_reboot_init(void) { - dmi_check_system(pci_reboot_dmi_table); + /* Only do the DMI check if reboot_type hasn't been overridden + * on the command line + */ + if (reboot_default) { + dmi_check_system(pci_reboot_dmi_table); + } return 0; } core_initcall(pci_reboot_init); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d7d5099fe87..88638883176 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -749,10 +749,16 @@ void __init setup_arch(char **cmdline_p) #endif #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, - EFI_LOADER_SIGNATURE, 4)) { + "EL32", 4)) { efi_enabled = 1; - efi_memblock_x86_reserve_range(); + efi_64bit = false; + } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, + "EL64", 4)) { + efi_enabled = 1; + efi_64bit = true; } + if (efi_enabled && efi_memblock_x86_reserve_range()) + efi_enabled = 0; #endif x86_init.oem.arch_setup(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 46a01bdc27e..25edcfc9ba5 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -24,6 +24,7 @@ #include <asm/processor.h> #include <asm/ucontext.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/vdso.h> #include <asm/mce.h> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 66d250c00d1..5104a2b685c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -255,6 +255,7 @@ notrace static void __cpuinit start_secondary(void *unused) * most necessary things. */ cpu_init(); + x86_cpuinit.early_percpu_clock_init(); preempt_disable(); smp_callin(); @@ -291,19 +292,6 @@ notrace static void __cpuinit start_secondary(void *unused) per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; x86_platform.nmi_init(); - /* - * Wait until the cpu which brought this one up marked it - * online before enabling interrupts. If we don't do that then - * we can end up waking up the softirq thread before this cpu - * reached the active state, which makes the scheduler unhappy - * and schedule the softirq thread on the wrong cpu. This is - * only observable with forced threaded interrupts, but in - * theory it could also happen w/o them. It's just way harder - * to achieve. - */ - while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) - cpu_relax(); - /* enable local interrupts */ local_irq_enable(); @@ -740,8 +728,6 @@ do_rest: * the targeted processor. */ - printk(KERN_DEBUG "smpboot cpu %d: start_ip = %lx\n", cpu, start_ip); - atomic_set(&init_deasserted, 0); if (get_uv_system_type() != UV_NON_UNIQUE_APIC) { @@ -791,9 +777,10 @@ do_rest: schedule(); } - if (cpumask_test_cpu(cpu, cpu_callin_mask)) + if (cpumask_test_cpu(cpu, cpu_callin_mask)) { + print_cpu_msr(&cpu_data(cpu)); pr_debug("CPU%d: has booted.\n", cpu); - else { + } else { boot_error = 1; if (*(volatile u32 *)TRAMPOLINE_SYM(trampoline_status) == 0xA5A5A5A5) @@ -847,7 +834,7 @@ int __cpuinit native_cpu_up(unsigned int cpu) if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid || !physid_isset(apicid, phys_cpu_present_map) || - (!x2apic_mode && apicid >= 255)) { + !apic->apic_id_valid(apicid)) { printk(KERN_ERR "%s: bad cpu %d\n", __func__, cpu); return -EINVAL; } diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 051489082d5..ef59642ff1b 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -195,7 +195,7 @@ 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; + unsigned long addr = addr0, start_addr; /* requested length too big for entire address space */ if (len > TASK_SIZE) @@ -223,25 +223,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, mm->free_area_cache = mm->mmap_base; } +try_again: /* either no address requested or can't fit in requested address hole */ - addr = mm->free_area_cache; - - /* make sure it can fit in the remaining address space */ - if (addr > len) { - unsigned long tmp_addr = align_addr(addr - len, filp, - ALIGN_TOPDOWN); - - vma = find_vma(mm, tmp_addr); - if (!vma || tmp_addr + len <= vma->vm_start) - /* remember the address as a hint for next time */ - return mm->free_area_cache = tmp_addr; - } - - if (mm->mmap_base < len) - goto bottomup; + start_addr = addr = mm->free_area_cache; - addr = mm->mmap_base-len; + if (addr < len) + goto fail; + addr -= len; do { addr = align_addr(addr, filp, ALIGN_TOPDOWN); @@ -263,6 +252,17 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, 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; + } + bottomup: /* * A failed mmap() very likely causes application failure, diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index dd5fbf4101f..c6eba2b4267 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -57,9 +57,6 @@ EXPORT_SYMBOL(profile_pc); */ static irqreturn_t timer_interrupt(int irq, void *dev_id) { - /* Keep nmi watchdog up to date */ - inc_irq_stat(irq0_irqs); - global_clock_event->event_handler(global_clock_event); /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 482ec3af206..ec61d4c1b93 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -54,6 +54,7 @@ #include <asm/traps.h> #include <asm/desc.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/mce.h> #include <asm/mach_traps.h> @@ -571,41 +572,18 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void) } /* - * __math_state_restore assumes that cr0.TS is already clear and the - * fpu state is all ready for use. Used during context switch. - */ -void __math_state_restore(void) -{ - struct thread_info *thread = current_thread_info(); - struct task_struct *tsk = thread->task; - - /* - * Paranoid restore. send a SIGSEGV if we fail to restore the state. - */ - if (unlikely(restore_fpu_checking(tsk))) { - stts(); - force_sig(SIGSEGV, tsk); - return; - } - - thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */ - tsk->fpu_counter++; -} - -/* * 'math_state_restore()' saves the current math information in the * old math state array, and gets the new ones from the current task * * Careful.. There are problems with IBM-designed IRQ13 behaviour. * Don't touch unless you *really* know how it works. * - * Must be called with kernel preemption disabled (in this case, - * local interrupts are disabled at the call-site in entry.S). + * Must be called with kernel preemption disabled (eg with local + * local interrupts as in the case of do_device_not_available). */ -asmlinkage void math_state_restore(void) +void math_state_restore(void) { - struct thread_info *thread = current_thread_info(); - struct task_struct *tsk = thread->task; + struct task_struct *tsk = current; if (!tsk_used_math(tsk)) { local_irq_enable(); @@ -622,9 +600,17 @@ asmlinkage void math_state_restore(void) local_irq_disable(); } - clts(); /* Allow maths ops (or we recurse) */ + __thread_fpu_begin(tsk); + /* + * Paranoid restore. send a SIGSEGV if we fail to restore the state. + */ + if (unlikely(restore_fpu_checking(tsk))) { + __thread_fpu_end(tsk); + force_sig(SIGSEGV, tsk); + return; + } - __math_state_restore(); + tsk->fpu_counter++; } EXPORT_SYMBOL_GPL(math_state_restore); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index a62c201c97e..899a03f2d18 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -620,7 +620,8 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) if (cpu_khz) { *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; - *offset = ns_now - (tsc_now * *scale >> CYC2NS_SCALE_FACTOR); + *offset = ns_now - mult_frac(tsc_now, *scale, + (1UL << CYC2NS_SCALE_FACTOR)); } sched_clock_idle_wakeup_event(0); @@ -629,7 +630,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) static unsigned long long cyc2ns_suspend; -void save_sched_clock_state(void) +void tsc_save_sched_clock_state(void) { if (!sched_clock_stable) return; @@ -645,7 +646,7 @@ void save_sched_clock_state(void) * that sched_clock() continues from the point where it was left off during * suspend. */ -void restore_sched_clock_state(void) +void tsc_restore_sched_clock_state(void) { unsigned long long offset; unsigned long flags; diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 9eba29b46cb..fc25e60a588 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -42,7 +42,7 @@ static __cpuinitdata int nr_warps; /* * TSC-warp measurement loop running on both CPUs: */ -static __cpuinit void check_tsc_warp(void) +static __cpuinit void check_tsc_warp(unsigned int timeout) { cycles_t start, now, prev, end; int i; @@ -51,9 +51,9 @@ static __cpuinit void check_tsc_warp(void) start = get_cycles(); rdtsc_barrier(); /* - * The measurement runs for 20 msecs: + * The measurement runs for 'timeout' msecs: */ - end = start + tsc_khz * 20ULL; + end = start + (cycles_t) tsc_khz * timeout; now = start; for (i = 0; ; i++) { @@ -99,6 +99,25 @@ static __cpuinit void check_tsc_warp(void) } /* + * If the target CPU coming online doesn't have any of its core-siblings + * online, a timeout of 20msec will be used for the TSC-warp measurement + * loop. Otherwise a smaller timeout of 2msec will be used, as we have some + * information about this socket already (and this information grows as we + * have more and more logical-siblings in that socket). + * + * Ideally we should be able to skip the TSC sync check on the other + * core-siblings, if the first logical CPU in a socket passed the sync test. + * But as the TSC is per-logical CPU and can potentially be modified wrongly + * by the bios, TSC sync test for smaller duration should be able + * to catch such errors. Also this will catch the condition where all the + * cores in the socket doesn't get reset at the same time. + */ +static inline unsigned int loop_timeout(int cpu) +{ + return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20; +} + +/* * Source CPU calls into this - it waits for the freshly booted * target CPU to arrive and then starts the measurement: */ @@ -135,7 +154,7 @@ void __cpuinit check_tsc_sync_source(int cpu) */ atomic_inc(&start_count); - check_tsc_warp(); + check_tsc_warp(loop_timeout(cpu)); while (atomic_read(&stop_count) != cpus-1) cpu_relax(); @@ -183,7 +202,7 @@ void __cpuinit check_tsc_sync_target(void) while (atomic_read(&start_count) != cpus) cpu_relax(); - check_tsc_warp(); + check_tsc_warp(loop_timeout(smp_processor_id())); /* * Ok, we are done: diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index b466cab5ba1..328cb37bb82 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -172,6 +172,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) spinlock_t *ptl; int i; + down_write(&mm->mmap_sem); pgd = pgd_offset(mm, 0xA0000); if (pgd_none_or_clear_bad(pgd)) goto out; @@ -190,6 +191,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) } pte_unmap_unlock(pte, ptl); out: + up_write(&mm->mmap_sem); flush_tlb(); } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 947a06ccc67..e9f265fd79a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -91,6 +91,7 @@ struct x86_init_ops x86_init __initdata = { }; struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { + .early_percpu_clock_init = x86_init_noop, .setup_percpu_clockev = setup_secondary_APIC_clock, .fixup_cpu_id = x86_default_fixup_cpu_id, }; @@ -107,7 +108,9 @@ struct x86_platform_ops x86_platform = { .is_untracked_pat_range = is_ISA_range, .nmi_init = default_nmi_init, .get_nmi_reason = default_get_nmi_reason, - .i8042_detect = default_i8042_detect + .i8042_detect = default_i8042_detect, + .save_sched_clock_state = tsc_save_sched_clock_state, + .restore_sched_clock_state = tsc_restore_sched_clock_state, }; EXPORT_SYMBOL_GPL(x86_platform); diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index a3911343976..e62728e30b0 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -6,6 +6,7 @@ #include <linux/bootmem.h> #include <linux/compat.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #ifdef CONFIG_IA32_EMULATION #include <asm/sigcontext32.h> #endif @@ -47,7 +48,7 @@ void __sanitize_i387_state(struct task_struct *tsk) if (!fx) return; - BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU); + BUG_ON(__thread_has_fpu(tsk)); xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv; @@ -168,7 +169,7 @@ int save_i387_xstate(void __user *buf) if (!used_math()) return 0; - if (task_thread_info(tsk)->status & TS_USEDFPU) { + if (user_has_fpu()) { if (use_xsave()) err = xsave_user(buf); else @@ -176,8 +177,7 @@ int save_i387_xstate(void __user *buf) if (err) return err; - task_thread_info(tsk)->status &= ~TS_USEDFPU; - stts(); + user_fpu_end(); } else { sanitize_i387_state(tsk); if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave, @@ -292,10 +292,7 @@ int restore_i387_xstate(void __user *buf) return err; } - if (!(task_thread_info(current)->status & TS_USEDFPU)) { - clts(); - task_thread_info(current)->status |= TS_USEDFPU; - } + user_fpu_begin(); if (use_xsave()) err = restore_user_xstate(buf); else |