diff options
Diffstat (limited to 'arch/x86/kernel')
62 files changed, 930 insertions, 668 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index a5408b965c9d..9b0a34e2cd79 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -36,6 +36,8 @@ obj-y += tsc.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o +obj-$(CONFIG_PREEMPT) += preempt.o + obj-y += process.o obj-y += i387.o xsave.o obj-y += ptrace.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 40c76604199f..6c0b43bd024b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -189,24 +189,31 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) return 0; } -static void acpi_register_lapic(int id, u8 enabled) +/** + * acpi_register_lapic - register a local apic and generates a logic cpu number + * @id: local apic id to register + * @enabled: this cpu is enabled or not + * + * Returns the logic cpu number which maps to the local apic + */ +static int acpi_register_lapic(int id, u8 enabled) { unsigned int ver = 0; if (id >= MAX_LOCAL_APIC) { printk(KERN_INFO PREFIX "skipped apicid that is too big\n"); - return; + return -EINVAL; } if (!enabled) { ++disabled_cpus; - return; + return -EINVAL; } if (boot_cpu_physical_apicid != -1U) ver = apic_version[boot_cpu_physical_apicid]; - generic_processor_info(id, ver); + return generic_processor_info(id, ver); } static int __init @@ -614,84 +621,27 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) #endif } -static int _acpi_map_lsapic(acpi_handle handle, int *pcpu) +static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; - struct acpi_madt_local_apic *lapic; - cpumask_var_t tmp_map, new_map; - u8 physid; int cpu; - int retval = -ENOMEM; - - if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) - return -EINVAL; - - if (!buffer.length || !buffer.pointer) - return -EINVAL; - - obj = buffer.pointer; - if (obj->type != ACPI_TYPE_BUFFER || - obj->buffer.length < sizeof(*lapic)) { - kfree(buffer.pointer); - return -EINVAL; - } - lapic = (struct acpi_madt_local_apic *)obj->buffer.pointer; - - if (lapic->header.type != ACPI_MADT_TYPE_LOCAL_APIC || - !(lapic->lapic_flags & ACPI_MADT_ENABLED)) { - kfree(buffer.pointer); - return -EINVAL; - } - - physid = lapic->id; - - kfree(buffer.pointer); - buffer.length = ACPI_ALLOCATE_BUFFER; - buffer.pointer = NULL; - lapic = NULL; - - if (!alloc_cpumask_var(&tmp_map, GFP_KERNEL)) - goto out; - - if (!alloc_cpumask_var(&new_map, GFP_KERNEL)) - goto free_tmp_map; - - cpumask_copy(tmp_map, cpu_present_mask); - acpi_register_lapic(physid, ACPI_MADT_ENABLED); - - /* - * If acpi_register_lapic successfully generates a new logical cpu - * number, then the following will get us exactly what was mapped - */ - cpumask_andnot(new_map, cpu_present_mask, tmp_map); - if (cpumask_empty(new_map)) { - printk ("Unable to map lapic to logical cpu number\n"); - retval = -EINVAL; - goto free_new_map; + cpu = acpi_register_lapic(physid, ACPI_MADT_ENABLED); + if (cpu < 0) { + pr_info(PREFIX "Unable to map lapic to logical cpu number\n"); + return cpu; } acpi_processor_set_pdc(handle); - - cpu = cpumask_first(new_map); acpi_map_cpu2node(handle, cpu, physid); *pcpu = cpu; - retval = 0; - -free_new_map: - free_cpumask_var(new_map); -free_tmp_map: - free_cpumask_var(tmp_map); -out: - return retval; + return 0; } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_lsapic(acpi_handle handle, int *pcpu) +int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - return _acpi_map_lsapic(handle, pcpu); + return _acpi_map_lsapic(handle, physid, pcpu); } EXPORT_SYMBOL(acpi_map_lsapic); @@ -745,7 +695,7 @@ static int __init acpi_parse_sbf(struct acpi_table_header *table) #ifdef CONFIG_HPET_TIMER #include <asm/hpet.h> -static struct __initdata resource *hpet_res; +static struct resource *hpet_res __initdata; static int __init acpi_parse_hpet(struct acpi_table_header *table) { diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 33120100ff5e..3a2ae4c88948 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -26,6 +26,17 @@ static char temp_stack[4096]; #endif /** + * x86_acpi_enter_sleep_state - enter sleep state + * @state: Sleep state to enter. + * + * Wrapper around acpi_enter_sleep_state() to be called by assmebly. + */ +acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state) +{ + return acpi_enter_sleep_state(state); +} + +/** * x86_acpi_suspend_lowlevel - save kernel state * * Create an identity mapped page table and copy the wakeup routine to diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index c9c2c982d5e4..65c7b606b606 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -17,3 +17,5 @@ extern void wakeup_long64(void); extern void do_suspend_lowlevel(void); extern int x86_acpi_suspend_lowlevel(void); + +acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index d1daa66ab162..665c6b7d2ea9 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -73,7 +73,7 @@ ENTRY(do_suspend_lowlevel) call save_processor_state call save_registers pushl $3 - call acpi_enter_sleep_state + call x86_acpi_enter_sleep_state addl $4, %esp # In case of S3 failure, we'll emerge here. Jump diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 8ea5164cbd04..ae693b51ed8e 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -73,7 +73,7 @@ ENTRY(do_suspend_lowlevel) addq $8, %rsp movl $3, %edi xorl %eax, %eax - call acpi_enter_sleep_state + call x86_acpi_enter_sleep_state /* in case something went wrong, restore the machine status and go on */ jmp resume_point diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 15e8563e5c24..df94598ad05a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -402,17 +402,6 @@ void alternatives_enable_smp(void) { struct smp_alt_module *mod; -#ifdef CONFIG_LOCKDEP - /* - * Older binutils section handling bug prevented - * alternatives-replacement from working reliably. - * - * If this still occurs then you should see a hang - * or crash shortly after this line: - */ - pr_info("lockdep: fixing up alternatives\n"); -#endif - /* Why bother if there are no other CPUs? */ BUG_ON(num_possible_cpus() == 1); diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index c9876efecafb..af5b08ab3b71 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -40,7 +40,7 @@ #include <asm/fixmap.h> #include <asm/apb_timer.h> -#include <asm/mrst.h> +#include <asm/intel-mid.h> #include <asm/time.h> #define APBT_CLOCKEVENT_RATING 110 @@ -157,13 +157,13 @@ static int __init apbt_clockevent_register(void) adev->num = smp_processor_id(); adev->timer = dw_apb_clockevent_init(smp_processor_id(), "apbt0", - mrst_timer_options == MRST_TIMER_LAPIC_APBT ? + intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ? APBT_CLOCKEVENT_RATING - 100 : APBT_CLOCKEVENT_RATING, adev_virt_addr(adev), 0, apbt_freq); /* Firmware does EOI handling for us. */ adev->timer->eoi = NULL; - if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { + if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT) { global_clock_event = &adev->timer->ced; printk(KERN_DEBUG "%s clockevent registered as global\n", global_clock_event->name); @@ -253,7 +253,7 @@ static int apbt_cpuhp_notify(struct notifier_block *n, static __init int apbt_late_init(void) { - if (mrst_timer_options == MRST_TIMER_LAPIC_APBT || + if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT || !apb_timer_block_enabled) return 0; /* This notifier should be called after workqueue is ready */ @@ -340,7 +340,7 @@ void __init apbt_time_init(void) } #ifdef CONFIG_SMP /* kernel cmdline disable apb timer, so we will use lapic timers */ - if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { + if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT) { printk(KERN_INFO "apbt: disabled per cpu timer\n"); return; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a7eb82d9b012..ed165d657380 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2107,7 +2107,7 @@ void disconnect_bsp_APIC(int virt_wire_setup) apic_write(APIC_LVT1, value); } -void generic_processor_info(int apicid, int version) +int generic_processor_info(int apicid, int version) { int cpu, max = nr_cpu_ids; bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid, @@ -2127,7 +2127,7 @@ void generic_processor_info(int apicid, int version) " Processor %d/0x%x ignored.\n", max, thiscpu, apicid); disabled_cpus++; - return; + return -ENODEV; } if (num_processors >= nr_cpu_ids) { @@ -2138,7 +2138,7 @@ void generic_processor_info(int apicid, int version) " Processor %d/0x%x ignored.\n", max, thiscpu, apicid); disabled_cpus++; - return; + return -EINVAL; } num_processors++; @@ -2183,6 +2183,8 @@ void generic_processor_info(int apicid, int version) #endif set_cpu_possible(cpu, true); set_cpu_present(cpu, true); + + return cpu; } int hard_smp_processor_id(void) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1191ac1c9d25..ad0dc0428baf 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -39,12 +39,6 @@ #include <asm/x86_init.h> #include <asm/nmi.h> -/* BMC sets a bit this MMR non-zero before sending an NMI */ -#define UVH_NMI_MMR UVH_SCRATCH5 -#define UVH_NMI_MMR_CLEAR (UVH_NMI_MMR + 8) -#define UV_NMI_PENDING_MASK (1UL << 63) -DEFINE_PER_CPU(unsigned long, cpu_last_nmi_count); - DEFINE_PER_CPU(int, x2apic_extra_bits); #define PR_DEVEL(fmt, args...) pr_devel("%s: " fmt, __func__, args) @@ -58,7 +52,6 @@ int uv_min_hub_revision_id; EXPORT_SYMBOL_GPL(uv_min_hub_revision_id); unsigned int uv_apicid_hibits; EXPORT_SYMBOL_GPL(uv_apicid_hibits); -static DEFINE_SPINLOCK(uv_nmi_lock); static struct apic apic_x2apic_uv_x; @@ -113,7 +106,7 @@ static int __init early_get_pnodeid(void) break; case UV3_HUB_PART_NUMBER: case UV3_HUB_PART_NUMBER_X: - uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1; + uv_min_hub_revision_id += UV3_HUB_REVISION_BASE; break; } @@ -847,68 +840,6 @@ void uv_cpu_init(void) set_x2apic_extra_bits(uv_hub_info->pnode); } -/* - * When NMI is received, print a stack trace. - */ -int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) -{ - unsigned long real_uv_nmi; - int bid; - - /* - * Each blade has an MMR that indicates when an NMI has been sent - * to cpus on the blade. If an NMI is detected, atomically - * clear the MMR and update a per-blade NMI count used to - * cause each cpu on the blade to notice a new NMI. - */ - bid = uv_numa_blade_id(); - real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK); - - if (unlikely(real_uv_nmi)) { - spin_lock(&uv_blade_info[bid].nmi_lock); - real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK); - if (real_uv_nmi) { - uv_blade_info[bid].nmi_count++; - uv_write_local_mmr(UVH_NMI_MMR_CLEAR, UV_NMI_PENDING_MASK); - } - spin_unlock(&uv_blade_info[bid].nmi_lock); - } - - if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count)) - return NMI_DONE; - - __get_cpu_var(cpu_last_nmi_count) = uv_blade_info[bid].nmi_count; - - /* - * Use a lock so only one cpu prints at a time. - * This prevents intermixed output. - */ - spin_lock(&uv_nmi_lock); - pr_info("UV NMI stack dump cpu %u:\n", smp_processor_id()); - dump_stack(); - spin_unlock(&uv_nmi_lock); - - return NMI_HANDLED; -} - -void uv_register_nmi_notifier(void) -{ - if (register_nmi_handler(NMI_UNKNOWN, uv_handle_nmi, 0, "uv")) - printk(KERN_WARNING "UV NMI handler failed to register\n"); -} - -void uv_nmi_init(void) -{ - unsigned int value; - - /* - * Unmask NMI on all cpus - */ - value = apic_read(APIC_LVT1) | APIC_DM_NMI; - value &= ~APIC_LVT_MASKED; - apic_write(APIC_LVT1, value); -} - void __init uv_system_init(void) { union uvh_rh_gam_config_mmr_u m_n_config; @@ -1046,6 +977,7 @@ void __init uv_system_init(void) map_mmr_high(max_pnode); map_mmioh_high(min_pnode, max_pnode); + uv_nmi_setup(); uv_cpu_init(); uv_scir_register_cpu_notifier(); uv_register_nmi_notifier(); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 28610822fb3c..9f6b9341950f 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -32,7 +32,6 @@ void common(void) { OFFSET(TI_flags, thread_info, flags); OFFSET(TI_status, thread_info, status); OFFSET(TI_addr_limit, thread_info, addr_limit); - OFFSET(TI_preempt_count, thread_info, preempt_count); BLANK(); OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 903a264af981..3daece79a142 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -823,8 +823,8 @@ static const struct cpu_dev amd_cpu_dev = { .c_vendor = "AMD", .c_ident = { "AuthenticAMD" }, #ifdef CONFIG_X86_32 - .c_models = { - { .vendor = X86_VENDOR_AMD, .family = 4, .model_names = + .legacy_models = { + { .family = 4, .model_names = { [3] = "486 DX/2", [7] = "486 DX/2-WB", @@ -835,7 +835,7 @@ static const struct cpu_dev amd_cpu_dev = { } }, }, - .c_size_cache = amd_size_cache, + .legacy_cache_size = amd_size_cache, #endif .c_early_init = early_init_amd, .c_detect_tlb = cpu_detect_tlb_amd, diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index fbf6c3bc2400..8d5652dc99dd 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -468,10 +468,10 @@ static void init_centaur(struct cpuinfo_x86 *c) #endif } +#ifdef CONFIG_X86_32 static unsigned int centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) { -#ifdef CONFIG_X86_32 /* VIA C3 CPUs (670-68F) need further shifting. */ if ((c->x86 == 6) && ((c->x86_model == 7) || (c->x86_model == 8))) size >>= 8; @@ -484,16 +484,18 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) if ((c->x86 == 6) && (c->x86_model == 9) && (c->x86_mask == 1) && (size == 65)) size -= 1; -#endif return size; } +#endif static const struct cpu_dev centaur_cpu_dev = { .c_vendor = "Centaur", .c_ident = { "CentaurHauls" }, .c_early_init = early_init_centaur, .c_init = init_centaur, - .c_size_cache = centaur_size_cache, +#ifdef CONFIG_X86_32 + .legacy_cache_size = centaur_size_cache, +#endif .c_x86_vendor = X86_VENDOR_CENTAUR, }; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 2793d1f095a2..6abc172b8258 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -346,7 +346,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) /* Look up CPU names by table lookup. */ static const char *table_lookup_model(struct cpuinfo_x86 *c) { - const struct cpu_model_info *info; +#ifdef CONFIG_X86_32 + const struct legacy_cpu_model_info *info; if (c->x86_model >= 16) return NULL; /* Range check */ @@ -354,13 +355,14 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c) if (!this_cpu) return NULL; - info = this_cpu->c_models; + info = this_cpu->legacy_models; - while (info && info->family) { + while (info->family) { if (info->family == c->x86) return info->model_names[c->x86_model]; info++; } +#endif return NULL; /* Not found */ } @@ -450,8 +452,8 @@ void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff); #else /* do processor-specific cache resizing */ - if (this_cpu->c_size_cache) - l2size = this_cpu->c_size_cache(c, l2size); + if (this_cpu->legacy_cache_size) + l2size = this_cpu->legacy_cache_size(c, l2size); /* Allow user to override all this if necessary. */ if (cachesize_override != -1) @@ -1095,6 +1097,9 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) = DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; +DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; +EXPORT_PER_CPU_SYMBOL(__preempt_count); + DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); /* @@ -1169,6 +1174,8 @@ void debug_stack_reset(void) DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); +DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; +EXPORT_PER_CPU_SYMBOL(__preempt_count); DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); #ifdef CONFIG_CC_STACKPROTECTOR diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 4041c24ae7db..c37dc37e8317 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -1,12 +1,6 @@ #ifndef ARCH_X86_CPU_H #define ARCH_X86_CPU_H -struct cpu_model_info { - int vendor; - int family; - const char *model_names[16]; -}; - /* attempt to consolidate cpu attributes */ struct cpu_dev { const char *c_vendor; @@ -14,15 +8,23 @@ struct cpu_dev { /* some have two possibilities for cpuid string */ const char *c_ident[2]; - struct cpu_model_info c_models[4]; - void (*c_early_init)(struct cpuinfo_x86 *); void (*c_bsp_init)(struct cpuinfo_x86 *); void (*c_init)(struct cpuinfo_x86 *); void (*c_identify)(struct cpuinfo_x86 *); void (*c_detect_tlb)(struct cpuinfo_x86 *); - unsigned int (*c_size_cache)(struct cpuinfo_x86 *, unsigned int); int c_x86_vendor; +#ifdef CONFIG_X86_32 + /* Optional vendor specific routine to obtain the cache size. */ + unsigned int (*legacy_cache_size)(struct cpuinfo_x86 *, + unsigned int); + + /* Family/stepping-based lookup table for model names. */ + struct legacy_cpu_model_info { + int family; + const char *model_names[16]; + } legacy_models[5]; +#endif }; struct _tlb_table { diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index ec7299566f79..dc1ec0dff939 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -665,8 +665,8 @@ static const struct cpu_dev intel_cpu_dev = { .c_vendor = "Intel", .c_ident = { "GenuineIntel" }, #ifdef CONFIG_X86_32 - .c_models = { - { .vendor = X86_VENDOR_INTEL, .family = 4, .model_names = + .legacy_models = { + { .family = 4, .model_names = { [0] = "486 DX-25/33", [1] = "486 DX-50", @@ -679,7 +679,7 @@ static const struct cpu_dev intel_cpu_dev = { [9] = "486 DX/4-WB" } }, - { .vendor = X86_VENDOR_INTEL, .family = 5, .model_names = + { .family = 5, .model_names = { [0] = "Pentium 60/66 A-step", [1] = "Pentium 60/66", @@ -690,7 +690,7 @@ static const struct cpu_dev intel_cpu_dev = { [8] = "Mobile Pentium MMX" } }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model_names = + { .family = 6, .model_names = { [0] = "Pentium Pro A-step", [1] = "Pentium Pro", @@ -704,7 +704,7 @@ static const struct cpu_dev intel_cpu_dev = { [11] = "Pentium III (Tualatin)", } }, - { .vendor = X86_VENDOR_INTEL, .family = 15, .model_names = + { .family = 15, .model_names = { [0] = "Pentium 4 (Unknown)", [1] = "Pentium 4 (Willamette)", @@ -714,7 +714,7 @@ static const struct cpu_dev intel_cpu_dev = { } }, }, - .c_size_cache = intel_size_cache, + .legacy_cache_size = intel_size_cache, #endif .c_detect_tlb = intel_detect_tlb, .c_early_init = early_init_intel, diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index cd8b166a1735..de8b60a53f69 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -42,8 +42,7 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err) struct mce m; /* Only corrected MC is reported */ - if (!corrected || !(mem_err->validation_bits & - CPER_MEM_VALID_PHYSICAL_ADDRESS)) + if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA)) return; mce_setup(&m); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 71a39f3621ba..9f7ca266864a 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -15,6 +15,7 @@ #include <linux/clocksource.h> #include <linux/module.h> #include <linux/hardirq.h> +#include <linux/efi.h> #include <linux/interrupt.h> #include <asm/processor.h> #include <asm/hypervisor.h> @@ -23,6 +24,8 @@ #include <asm/desc.h> #include <asm/idle.h> #include <asm/irq_regs.h> +#include <asm/i8259.h> +#include <asm/apic.h> struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); @@ -76,6 +79,30 @@ static void __init ms_hyperv_init_platform(void) printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n", ms_hyperv.features, ms_hyperv.hints); +#ifdef CONFIG_X86_LOCAL_APIC + if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) { + /* + * Get the APIC frequency. + */ + u64 hv_lapic_frequency; + + rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency); + hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ); + lapic_timer_frequency = hv_lapic_frequency; + printk(KERN_INFO "HyperV: LAPIC Timer Frequency: %#x\n", + lapic_timer_frequency); + + /* + * On Hyper-V, when we are booting off an EFI firmware stack, + * we do not have many legacy devices including PIC, PIT etc. + */ + if (efi_enabled(EFI_BOOT)) { + printk(KERN_INFO "HyperV: Using null_legacy_pic\n"); + legacy_pic = &null_legacy_pic; + } + } +#endif + if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 8355c84b9729..8e132931614d 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1276,16 +1276,16 @@ void perf_events_lapic_init(void) static int __kprobes perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { - int ret; u64 start_clock; u64 finish_clock; + int ret; if (!atomic_read(&active_events)) return NMI_DONE; - start_clock = local_clock(); + start_clock = sched_clock(); ret = x86_pmu.handle_irq(regs); - finish_clock = local_clock(); + finish_clock = sched_clock(); perf_sample_event_took(finish_clock - start_clock); @@ -1506,7 +1506,7 @@ static int __init init_hw_perf_events(void) err = amd_pmu_init(); break; default: - return 0; + err = -ENOTSUPP; } if (err != 0) { pr_cont("no PMU driver, software events only.\n"); @@ -1883,26 +1883,21 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { - userpg->cap_usr_time = 0; - userpg->cap_usr_time_zero = 0; - userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc; + userpg->cap_user_time = 0; + userpg->cap_user_time_zero = 0; + userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + if (!sched_clock_stable) return; - if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) - return; - - userpg->cap_usr_time = 1; + userpg->cap_user_time = 1; userpg->time_mult = this_cpu_read(cyc2ns); userpg->time_shift = CYC2NS_SCALE_FACTOR; userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; - if (sched_clock_stable && !check_tsc_disabled()) { - userpg->cap_usr_time_zero = 1; - userpg->time_zero = this_cpu_read(cyc2ns_offset); - } + userpg->cap_user_time_zero = 1; + userpg->time_zero = this_cpu_read(cyc2ns_offset); } /* @@ -1994,7 +1989,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) frame.return_address = 0; bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); - if (bytes != sizeof(frame)) + if (bytes != 0) break; if (!valid_user_frame(fp, sizeof(frame))) @@ -2046,7 +2041,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) frame.return_address = 0; bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); - if (bytes != sizeof(frame)) + if (bytes != 0) break; if (!valid_user_frame(fp, sizeof(frame))) diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index cc16faae0538..fd00bb29425d 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -164,6 +164,11 @@ struct cpu_hw_events { struct perf_guest_switch_msr guest_switch_msrs[X86_PMC_IDX_MAX]; /* + * Intel checkpoint mask + */ + u64 intel_cp_status; + + /* * manage shared (per-core, per-cpu) registers * used on Intel NHM/WSM/SNB */ @@ -440,6 +445,7 @@ struct x86_pmu { int lbr_nr; /* hardware stack size */ u64 lbr_sel_mask; /* LBR_SELECT valid bits */ const int *lbr_sel_map; /* lbr_select mappings */ + bool lbr_double_abort; /* duplicated lbr aborts */ /* * Extra registers for events diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index c62d88396ad5..0fa4f242f050 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -190,9 +190,9 @@ static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; -EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); -EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); -EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); +EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); +EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); struct attribute *nhm_events_attrs[] = { EVENT_PTR(mem_ld_nhm), @@ -899,8 +899,8 @@ static __initconst const u64 atom_hw_cache_event_ids static struct extra_reg intel_slm_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ - INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffff, RSP_0), - INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffff, RSP_1), + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffffull, RSP_1), EVENT_EXTRA_END }; @@ -1184,6 +1184,11 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc) wrmsrl(hwc->config_base, ctrl_val); } +static inline bool event_is_checkpointed(struct perf_event *event) +{ + return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0; +} + static void intel_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -1197,6 +1202,7 @@ 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); + cpuc->intel_cp_status &= ~(1ull << hwc->idx); /* * must disable before any actual event @@ -1271,6 +1277,9 @@ static void intel_pmu_enable_event(struct perf_event *event) if (event->attr.exclude_guest) cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx); + if (unlikely(event_is_checkpointed(event))) + cpuc->intel_cp_status |= (1ull << hwc->idx); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_enable_fixed(hwc); return; @@ -1289,6 +1298,17 @@ static void intel_pmu_enable_event(struct perf_event *event) int intel_pmu_save_and_restart(struct perf_event *event) { x86_perf_event_update(event); + /* + * For a checkpointed counter always reset back to 0. This + * avoids a situation where the counter overflows, aborts the + * transaction and is then set back to shortly before the + * overflow, and overflows and aborts again. + */ + if (unlikely(event_is_checkpointed(event))) { + /* No race with NMIs because the counter should not be armed */ + wrmsrl(event->hw.event_base, 0); + local64_set(&event->hw.prev_count, 0); + } return x86_perf_event_set_period(event); } @@ -1372,6 +1392,13 @@ again: x86_pmu.drain_pebs(regs); } + /* + * Checkpointed counters can lead to 'spurious' PMIs because the + * rollback caused by the PMI will have cleared the overflow status + * bit. Therefore always force probe these counters. + */ + status |= cpuc->intel_cp_status; + for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { struct perf_event *event = cpuc->events[bit]; @@ -1837,6 +1864,20 @@ static int hsw_hw_config(struct perf_event *event) event->attr.precise_ip > 0)) return -EOPNOTSUPP; + if (event_is_checkpointed(event)) { + /* + * Sampling of checkpointed events can cause situations where + * the CPU constantly aborts because of a overflow, which is + * then checkpointed back and ignored. Forbid checkpointing + * for sampling. + * + * But still allow a long sampling period, so that perf stat + * from KVM works. + */ + if (event->attr.sample_period > 0 && + event->attr.sample_period < 0x7fffffff) + return -EOPNOTSUPP; + } return 0; } @@ -2182,10 +2223,36 @@ static __init void intel_nehalem_quirk(void) } } -EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3"); -EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82") +EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82") + +/* Haswell special events */ +EVENT_ATTR_STR(tx-start, tx_start, "event=0xc9,umask=0x1"); +EVENT_ATTR_STR(tx-commit, tx_commit, "event=0xc9,umask=0x2"); +EVENT_ATTR_STR(tx-abort, tx_abort, "event=0xc9,umask=0x4"); +EVENT_ATTR_STR(tx-capacity, tx_capacity, "event=0x54,umask=0x2"); +EVENT_ATTR_STR(tx-conflict, tx_conflict, "event=0x54,umask=0x1"); +EVENT_ATTR_STR(el-start, el_start, "event=0xc8,umask=0x1"); +EVENT_ATTR_STR(el-commit, el_commit, "event=0xc8,umask=0x2"); +EVENT_ATTR_STR(el-abort, el_abort, "event=0xc8,umask=0x4"); +EVENT_ATTR_STR(el-capacity, el_capacity, "event=0x54,umask=0x2"); +EVENT_ATTR_STR(el-conflict, el_conflict, "event=0x54,umask=0x1"); +EVENT_ATTR_STR(cycles-t, cycles_t, "event=0x3c,in_tx=1"); +EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1"); static struct attribute *hsw_events_attrs[] = { + EVENT_PTR(tx_start), + EVENT_PTR(tx_commit), + EVENT_PTR(tx_abort), + EVENT_PTR(tx_capacity), + EVENT_PTR(tx_conflict), + EVENT_PTR(el_start), + EVENT_PTR(el_commit), + EVENT_PTR(el_abort), + EVENT_PTR(el_capacity), + EVENT_PTR(el_conflict), + EVENT_PTR(cycles_t), + EVENT_PTR(cycles_ct), EVENT_PTR(mem_ld_hsw), EVENT_PTR(mem_st_hsw), NULL @@ -2325,6 +2392,7 @@ __init int intel_pmu_init(void) break; case 55: /* Atom 22nm "Silvermont" */ + case 77: /* Avoton "Silvermont" */ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, @@ -2451,6 +2519,7 @@ __init int intel_pmu_init(void) x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.lbr_double_abort = true; pr_cont("Haswell 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 63438aad177f..ae96cfa5eddd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -12,6 +12,7 @@ #define BTS_BUFFER_SIZE (PAGE_SIZE << 4) #define PEBS_BUFFER_SIZE PAGE_SIZE +#define PEBS_FIXUP_SIZE PAGE_SIZE /* * pebs_record_32 for p4 and core not supported @@ -182,18 +183,32 @@ struct pebs_record_nhm { * Same as pebs_record_nhm, with two additional fields. */ struct pebs_record_hsw { - struct pebs_record_nhm nhm; - /* - * Real IP of the event. In the Intel documentation this - * is called eventingrip. - */ - u64 real_ip; - /* - * TSX tuning information field: abort cycles and abort flags. - */ - u64 tsx_tuning; + u64 flags, ip; + u64 ax, bx, cx, dx; + u64 si, di, bp, sp; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; + u64 status, dla, dse, lat; + u64 real_ip, tsx_tuning; +}; + +union hsw_tsx_tuning { + struct { + u32 cycles_last_block : 32, + hle_abort : 1, + rtm_abort : 1, + instruction_abort : 1, + non_instruction_abort : 1, + retry : 1, + data_conflict : 1, + capacity_writes : 1, + capacity_reads : 1; + }; + u64 value; }; +#define PEBS_HSW_TSX_FLAGS 0xff00000000ULL + void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -214,12 +229,14 @@ void fini_debug_store_on_cpu(int cpu) wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0); } +static DEFINE_PER_CPU(void *, insn_buffer); + static int alloc_pebs_buffer(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; int node = cpu_to_node(cpu); int max, thresh = 1; /* always use a single PEBS record */ - void *buffer; + void *buffer, *ibuffer; if (!x86_pmu.pebs) return 0; @@ -228,6 +245,19 @@ static int alloc_pebs_buffer(int cpu) if (unlikely(!buffer)) return -ENOMEM; + /* + * HSW+ already provides us the eventing ip; no need to allocate this + * buffer then. + */ + if (x86_pmu.intel_cap.pebs_format < 2) { + ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node); + if (!ibuffer) { + kfree(buffer); + return -ENOMEM; + } + per_cpu(insn_buffer, cpu) = ibuffer; + } + max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size; ds->pebs_buffer_base = (u64)(unsigned long)buffer; @@ -248,6 +278,9 @@ static void release_pebs_buffer(int cpu) if (!ds || !x86_pmu.pebs) return; + kfree(per_cpu(insn_buffer, cpu)); + per_cpu(insn_buffer, cpu) = NULL; + kfree((void *)(unsigned long)ds->pebs_buffer_base); ds->pebs_buffer_base = 0; } @@ -584,6 +617,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */ EVENT_CONSTRAINT_END }; @@ -714,6 +748,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) unsigned long old_to, to = cpuc->lbr_entries[0].to; unsigned long ip = regs->ip; int is_64bit = 0; + void *kaddr; /* * We don't need to fixup if the PEBS assist is fault like @@ -737,7 +772,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) * unsigned math, either ip is before the start (impossible) or * the basic block is larger than 1 page (sanity) */ - if ((ip - to) > PAGE_SIZE) + if ((ip - to) > PEBS_FIXUP_SIZE) return 0; /* @@ -748,29 +783,33 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 1; } + if (!kernel_ip(ip)) { + int size, bytes; + u8 *buf = this_cpu_read(insn_buffer); + + size = ip - to; /* Must fit our buffer, see above */ + bytes = copy_from_user_nmi(buf, (void __user *)to, size); + if (bytes != 0) + return 0; + + kaddr = buf; + } else { + kaddr = (void *)to; + } + do { struct insn insn; - u8 buf[MAX_INSN_SIZE]; - void *kaddr; old_to = to; - if (!kernel_ip(ip)) { - int bytes, size = MAX_INSN_SIZE; - - bytes = copy_from_user_nmi(buf, (void __user *)to, size); - if (bytes != size) - return 0; - - kaddr = buf; - } else - kaddr = (void *)to; #ifdef CONFIG_X86_64 is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32); #endif insn_init(&insn, kaddr, is_64bit); insn_get_length(&insn); + to += insn.length; + kaddr += insn.length; } while (to < ip); if (to == ip) { @@ -785,16 +824,34 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 0; } +static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs) +{ + if (pebs->tsx_tuning) { + union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning }; + return tsx.cycles_last_block; + } + return 0; +} + +static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) +{ + u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32; + + /* For RTM XABORTs also log the abort code from AX */ + if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1)) + txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT; + return txn; +} + static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *__pebs) { /* - * We cast to pebs_record_nhm to get the load latency data - * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used + * We cast to the biggest pebs_record but are careful not to + * unconditionally access the 'extra' entries. */ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct pebs_record_nhm *pebs = __pebs; - struct pebs_record_hsw *pebs_hsw = __pebs; + struct pebs_record_hsw *pebs = __pebs; struct perf_sample_data data; struct pt_regs regs; u64 sample_type; @@ -853,7 +910,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, regs.sp = pebs->sp; if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { - regs.ip = pebs_hsw->real_ip; + regs.ip = pebs->real_ip; regs.flags |= PERF_EFLAGS_EXACT; } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) regs.flags |= PERF_EFLAGS_EXACT; @@ -861,9 +918,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event, regs.flags &= ~PERF_EFLAGS_EXACT; if ((event->attr.sample_type & PERF_SAMPLE_ADDR) && - x86_pmu.intel_cap.pebs_format >= 1) + x86_pmu.intel_cap.pebs_format >= 1) data.addr = pebs->dla; + if (x86_pmu.intel_cap.pebs_format >= 2) { + /* Only set the TSX weight when no memory weight. */ + if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll) + data.weight = intel_hsw_weight(pebs); + + if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION) + data.txn = intel_hsw_transaction(pebs); + } + if (has_branch_stack(event)) data.br_stack = &cpuc->lbr_stack; @@ -912,17 +978,34 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) __intel_pmu_pebs_event(event, iregs, at); } -static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at, - void *top) +static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct debug_store *ds = cpuc->ds; struct perf_event *event = NULL; + void *at, *top; u64 status = 0; int bit; + if (!x86_pmu.pebs_active) + return; + + at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; + ds->pebs_index = ds->pebs_buffer_base; + if (unlikely(at > top)) + return; + + /* + * Should not happen, we program the threshold at 1 and do not + * set a reset value. + */ + WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size, + "Unexpected number of pebs records %ld\n", + (long)(top - at) / x86_pmu.pebs_record_size); + for (; at < top; at += x86_pmu.pebs_record_size) { struct pebs_record_nhm *p = at; @@ -950,61 +1033,6 @@ static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at, } } -static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct debug_store *ds = cpuc->ds; - struct pebs_record_nhm *at, *top; - int n; - - if (!x86_pmu.pebs_active) - return; - - at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; - top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; - - ds->pebs_index = ds->pebs_buffer_base; - - n = top - at; - if (n <= 0) - return; - - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > x86_pmu.max_pebs_events, - "Unexpected number of pebs records %d\n", n); - - return __intel_pmu_drain_pebs_nhm(iregs, at, top); -} - -static void intel_pmu_drain_pebs_hsw(struct pt_regs *iregs) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct debug_store *ds = cpuc->ds; - struct pebs_record_hsw *at, *top; - int n; - - if (!x86_pmu.pebs_active) - return; - - at = (struct pebs_record_hsw *)(unsigned long)ds->pebs_buffer_base; - top = (struct pebs_record_hsw *)(unsigned long)ds->pebs_index; - - n = top - at; - if (n <= 0) - return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > x86_pmu.max_pebs_events, - "Unexpected number of pebs records %d\n", n); - - return __intel_pmu_drain_pebs_nhm(iregs, at, top); -} - /* * BTS, PEBS probe and setup */ @@ -1039,7 +1067,7 @@ void intel_ds_init(void) case 2: pr_cont("PEBS fmt2%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_hsw); - x86_pmu.drain_pebs = intel_pmu_drain_pebs_hsw; + x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; break; default: diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index d5be06a5005e..d82d155aca8c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -284,6 +284,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); int i; + int out = 0; for (i = 0; i < x86_pmu.lbr_nr; i++) { unsigned long lbr_idx = (tos - i) & mask; @@ -306,15 +307,27 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) } from = (u64)((((s64)from) << skip) >> skip); - 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].in_tx = in_tx; - cpuc->lbr_entries[i].abort = abort; - cpuc->lbr_entries[i].reserved = 0; + /* + * Some CPUs report duplicated abort records, + * with the second entry not having an abort bit set. + * Skip them here. This loop runs backwards, + * so we need to undo the previous record. + * If the abort just happened outside the window + * the extra entry cannot be removed. + */ + if (abort && x86_pmu.lbr_double_abort && out > 0) + out--; + + cpuc->lbr_entries[out].from = from; + cpuc->lbr_entries[out].to = to; + cpuc->lbr_entries[out].mispred = mis; + cpuc->lbr_entries[out].predicted = pred; + cpuc->lbr_entries[out].in_tx = in_tx; + cpuc->lbr_entries[out].abort = abort; + cpuc->lbr_entries[out].reserved = 0; + out++; } - cpuc->lbr_stack.nr = i; + cpuc->lbr_stack.nr = out; } void intel_pmu_lbr_read(void) @@ -478,7 +491,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) /* may fail if text not present */ bytes = copy_from_user_nmi(buf, (void __user *)from, size); - if (bytes != size) + if (bytes != 0) return X86_BR_NONE; addr = buf; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 8ed44589b0e4..29c248799ced 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -997,6 +997,20 @@ static int snbep_pci2phy_map_init(int devid) } } + if (!err) { + /* + * For PCI bus with no UBOX device, find the next bus + * that has UBOX device and use its mapping. + */ + i = -1; + for (bus = 255; bus >= 0; bus--) { + if (pcibus_to_physid[bus] >= 0) + i = pcibus_to_physid[bus]; + else + pcibus_to_physid[bus] = i; + } + } + if (ubox_dev) pci_dev_put(ubox_dev); @@ -1099,6 +1113,24 @@ static struct attribute *ivt_uncore_qpi_formats_attr[] = { &format_attr_umask.attr, &format_attr_edge.attr, &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, NULL, }; @@ -1312,17 +1344,83 @@ static struct intel_uncore_type ivt_uncore_imc = { IVT_UNCORE_PCI_COMMON_INIT(), }; +/* registers in IRP boxes are not properly aligned */ +static unsigned ivt_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4}; +static unsigned ivt_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0}; + +static void ivt_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], + hwc->config | SNBEP_PMON_CTL_EN); +} + +static void ivt_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], hwc->config); +} + +static u64 ivt_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count = 0; + + pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx], (u32 *)&count); + pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1); + + return count; +} + +static struct intel_uncore_ops ivt_uncore_irp_ops = { + .init_box = ivt_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = ivt_uncore_irp_disable_event, + .enable_event = ivt_uncore_irp_enable_event, + .read_counter = ivt_uncore_irp_read_counter, +}; + +static struct intel_uncore_type ivt_uncore_irp = { + .name = "irp", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_mask = IVT_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &ivt_uncore_irp_ops, + .format_group = &ivt_uncore_format_group, +}; + +static struct intel_uncore_ops ivt_uncore_qpi_ops = { + .init_box = ivt_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_qpi_enable_event, + .read_counter = snbep_uncore_pci_read_counter, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + static struct intel_uncore_type ivt_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 3, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .ops = &ivt_uncore_pci_ops, - .format_group = &ivt_uncore_qpi_format_group, + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &ivt_uncore_qpi_ops, + .format_group = &ivt_uncore_qpi_format_group, }; static struct intel_uncore_type ivt_uncore_r2pcie = { @@ -1346,6 +1444,7 @@ static struct intel_uncore_type ivt_uncore_r3qpi = { enum { IVT_PCI_UNCORE_HA, IVT_PCI_UNCORE_IMC, + IVT_PCI_UNCORE_IRP, IVT_PCI_UNCORE_QPI, IVT_PCI_UNCORE_R2PCIE, IVT_PCI_UNCORE_R3QPI, @@ -1354,6 +1453,7 @@ enum { static struct intel_uncore_type *ivt_pci_uncores[] = { [IVT_PCI_UNCORE_HA] = &ivt_uncore_ha, [IVT_PCI_UNCORE_IMC] = &ivt_uncore_imc, + [IVT_PCI_UNCORE_IRP] = &ivt_uncore_irp, [IVT_PCI_UNCORE_QPI] = &ivt_uncore_qpi, [IVT_PCI_UNCORE_R2PCIE] = &ivt_uncore_r2pcie, [IVT_PCI_UNCORE_R3QPI] = &ivt_uncore_r3qpi, @@ -1401,6 +1501,10 @@ static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7), }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39), + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IRP, 0), + }, { /* QPI0 Port 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0), @@ -1429,6 +1533,16 @@ static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2), }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, { /* end: all zeroes */ } }; @@ -2706,14 +2820,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box) box->hrtimer.function = uncore_pmu_hrtimer; } -struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu) +static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node) { struct intel_uncore_box *box; int i, size; size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg); - box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); + box = kzalloc_node(size, GFP_KERNEL, node); if (!box) return NULL; @@ -3031,7 +3145,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu, struct intel_uncore_box *fake_box; int ret = -EINVAL, n; - fake_box = uncore_alloc_box(pmu->type, smp_processor_id()); + fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE); if (!fake_box) return -ENOMEM; @@ -3294,7 +3408,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id } type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; - box = uncore_alloc_box(type, 0); + box = uncore_alloc_box(type, NUMA_NO_NODE); if (!box) return -ENOMEM; @@ -3499,7 +3613,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id) if (pmu->func_id < 0) pmu->func_id = j; - box = uncore_alloc_box(type, cpu); + box = uncore_alloc_box(type, cpu_to_node(cpu)); if (!box) return -ENOMEM; diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index aee6317b902f..06fe3ed8b851 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -11,15 +11,12 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, unsigned int cpu) { #ifdef CONFIG_SMP - if (c->x86_max_cores * smp_num_siblings > 1) { - seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", - cpumask_weight(cpu_core_mask(cpu))); - seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); - seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); - seq_printf(m, "apicid\t\t: %d\n", c->apicid); - seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid); - } + seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); + seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu))); + seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); + seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); + seq_printf(m, "apicid\t\t: %d\n", c->apicid); + seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid); #endif } diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c index 202759a14121..75c5ad5d35cc 100644 --- a/arch/x86/kernel/cpu/umc.c +++ b/arch/x86/kernel/cpu/umc.c @@ -11,8 +11,8 @@ static const struct cpu_dev umc_cpu_dev = { .c_vendor = "UMC", .c_ident = { "UMC UMC UMC" }, - .c_models = { - { .vendor = X86_VENDOR_UMC, .family = 4, .model_names = + .legacy_models = { + { .family = 4, .model_names = { [1] = "U5D", [2] = "U5S", diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index e0e0841eef45..18677a90d6a3 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -127,12 +127,12 @@ void native_machine_crash_shutdown(struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); - lapic_shutdown(); #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); disable_IO_APIC(); #endif + lapic_shutdown(); #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 376dc7873447..d35078ea1446 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -20,22 +20,13 @@ #include <asm/hpet.h> #include <asm/apic.h> #include <asm/pci_x86.h> +#include <asm/setup.h> __initdata u64 initial_dtb; char __initdata cmd_line[COMMAND_LINE_SIZE]; int __initdata of_ioapic; -unsigned long pci_address_to_pio(phys_addr_t address) -{ - /* - * The ioport address can be directly used by inX / outX - */ - BUG_ON(address >= (1 << 16)); - return (unsigned long)address; -} -EXPORT_SYMBOL_GPL(pci_address_to_pio); - void __init early_init_dt_scan_chosen_arch(unsigned long node) { BUG(); @@ -51,15 +42,6 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)); } -#ifdef CONFIG_BLK_DEV_INITRD -void __init early_init_dt_setup_initrd_arch(u64 start, u64 end) -{ - initrd_start = (unsigned long)__va(start); - initrd_end = (unsigned long)__va(end); - initrd_below_start_ok = 1; -} -#endif - void __init add_dtb(u64 data) { initial_dtb = data + offsetof(struct setup_data, data); @@ -105,7 +87,6 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) static int x86_of_pci_irq_enable(struct pci_dev *dev) { - struct of_irq oirq; u32 virq; int ret; u8 pin; @@ -116,12 +97,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev) if (!pin) return 0; - ret = of_irq_map_pci(dev, &oirq); - if (ret) - return ret; - - virq = irq_create_of_mapping(oirq.controller, oirq.specifier, - oirq.size); + virq = of_irq_parse_and_map_pci(dev, 0, 0); if (virq == 0) return -EINVAL; dev->irq = virq; @@ -230,7 +206,7 @@ static void __init dtb_apic_setup(void) static void __init x86_flattree_get_config(void) { u32 size, map_len; - void *new_dtb; + struct boot_param_header *dt; if (!initial_dtb) return; @@ -238,24 +214,17 @@ static void __init x86_flattree_get_config(void) map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)sizeof(struct boot_param_header)); - initial_boot_params = early_memremap(initial_dtb, map_len); - size = be32_to_cpu(initial_boot_params->totalsize); + dt = early_memremap(initial_dtb, map_len); + size = be32_to_cpu(dt->totalsize); if (map_len < size) { - early_iounmap(initial_boot_params, map_len); - initial_boot_params = early_memremap(initial_dtb, size); + early_iounmap(dt, map_len); + dt = early_memremap(initial_dtb, size); map_len = size; } - new_dtb = alloc_bootmem(size); - memcpy(new_dtb, initial_boot_params, size); - early_iounmap(initial_boot_params, map_len); - - initial_boot_params = new_dtb; - - /* root level address cells */ - of_scan_flat_dt(early_init_dt_scan_root, NULL); - - unflatten_device_tree(); + initial_boot_params = dt; + unflatten_and_copy_device_tree(); + early_iounmap(dt, map_len); } #else static inline void x86_flattree_get_config(void) { } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index deb6421c9e69..d9c12d3022a7 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -25,12 +25,17 @@ unsigned int code_bytes = 64; int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE; static int die_counter; -void printk_address(unsigned long address, int reliable) +static void printk_stack_address(unsigned long address, int reliable) { pr_cont(" [<%p>] %s%pB\n", (void *)address, reliable ? "" : "? ", (void *)address); } +void printk_address(unsigned long address) +{ + pr_cont(" [<%p>] %pS\n", (void *)address, (void *)address); +} + #ifdef CONFIG_FUNCTION_GRAPH_TRACER static void print_ftrace_graph_addr(unsigned long addr, void *data, @@ -151,7 +156,7 @@ static void print_trace_address(void *data, unsigned long addr, int reliable) { touch_nmi_watchdog(); printk(data); - printk_address(addr, reliable); + printk_stack_address(addr, reliable); } static const struct stacktrace_ops print_trace_ops = { @@ -281,7 +286,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) #else /* Executive summary in case the oops scrolled away */ printk(KERN_ALERT "RIP "); - printk_address(regs->ip, 1); + printk_address(regs->ip); printk(" RSP <%016lx>\n", regs->sp); #endif return 0; diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index b3cd3ebae077..96f958d8cd45 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -313,6 +313,16 @@ static size_t __init gen6_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } +static inline size_t gen8_stolen_size(int num, int slot, int func) +{ + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); + gmch_ctrl >>= BDW_GMCH_GMS_SHIFT; + gmch_ctrl &= BDW_GMCH_GMS_MASK; + return gmch_ctrl << 25; /* 32 MB units */ +} + typedef size_t (*stolen_size_fn)(int num, int slot, int func); static struct pci_device_id intel_stolen_ids[] __initdata = { @@ -336,6 +346,8 @@ static struct pci_device_id intel_stolen_ids[] __initdata = { INTEL_IVB_D_IDS(gen6_stolen_size), INTEL_HSW_D_IDS(gen6_stolen_size), INTEL_HSW_M_IDS(gen6_stolen_size), + INTEL_BDW_M_IDS(gen8_stolen_size), + INTEL_BDW_D_IDS(gen8_stolen_size) }; static void __init intel_graphics_stolen(int num, int slot, int func) diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index d15f575a861b..01d1c187c9f9 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -14,9 +14,11 @@ #include <xen/hvc-console.h> #include <asm/pci-direct.h> #include <asm/fixmap.h> -#include <asm/mrst.h> +#include <asm/intel-mid.h> #include <asm/pgtable.h> #include <linux/usb/ehci_def.h> +#include <linux/efi.h> +#include <asm/efi.h> /* Simple VGA output */ #define VGABASE (__ISA_IO_base + 0xb8000) @@ -234,6 +236,11 @@ static int __init setup_early_printk(char *buf) early_console_register(&early_hsu_console, keep); } #endif +#ifdef CONFIG_EARLY_PRINTK_EFI + if (!strncmp(buf, "efi", 3)) + early_console_register(&early_efi_console, keep); +#endif + buf++; } return 0; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index f0dcb0ceb6a2..51e2988c5728 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -362,12 +362,9 @@ END(ret_from_exception) #ifdef CONFIG_PREEMPT ENTRY(resume_kernel) DISABLE_INTERRUPTS(CLBR_ANY) - cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ? - jnz restore_all need_resched: - movl TI_flags(%ebp), %ecx # need_resched set ? - testb $_TIF_NEED_RESCHED, %cl - jz restore_all + cmpl $0,PER_CPU_VAR(__preempt_count) + jnz restore_all testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? jz restore_all call preempt_schedule_irq @@ -1247,6 +1244,16 @@ return_to_handler: */ .pushsection .kprobes.text, "ax" +#ifdef CONFIG_TRACING +ENTRY(trace_page_fault) + RING0_EC_FRAME + ASM_CLAC + pushl_cfi $trace_do_page_fault + jmp error_code + CFI_ENDPROC +END(trace_page_fault) +#endif + ENTRY(page_fault) RING0_EC_FRAME ASM_CLAC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 1b69951a81e2..e21b0785a85b 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -487,21 +487,6 @@ ENDPROC(native_usergs_sysret64) TRACE_IRQS_OFF .endm -ENTRY(save_rest) - PARTIAL_FRAME 1 (REST_SKIP+8) - movq 5*8+16(%rsp), %r11 /* save return address */ - movq_cfi rbx, RBX+16 - movq_cfi rbp, RBP+16 - movq_cfi r12, R12+16 - movq_cfi r13, R13+16 - movq_cfi r14, R14+16 - movq_cfi r15, R15+16 - movq %r11, 8(%rsp) /* return address */ - FIXUP_TOP_OF_STACK %r11, 16 - ret - CFI_ENDPROC -END(save_rest) - /* save complete stack frame */ .pushsection .kprobes.text, "ax" ENTRY(save_paranoid) @@ -1118,10 +1103,8 @@ retint_signal: /* Returning to kernel space. Check if we need preemption */ /* rcx: threadinfo. interrupts off. */ ENTRY(retint_kernel) - cmpl $0,TI_preempt_count(%rcx) + cmpl $0,PER_CPU_VAR(__preempt_count) jnz retint_restore_args - bt $TIF_NEED_RESCHED,TI_flags(%rcx) - jnc retint_restore_args bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ jnc retint_restore_args call preempt_schedule_irq @@ -1295,6 +1278,17 @@ ENTRY(\sym) END(\sym) .endm +#ifdef CONFIG_TRACING +.macro trace_errorentry sym do_sym +errorentry trace(\sym) trace(\do_sym) +errorentry \sym \do_sym +.endm +#else +.macro trace_errorentry sym do_sym +errorentry \sym \do_sym +.endm +#endif + /* error code is on the stack already */ .macro paranoiderrorentry sym do_sym ENTRY(\sym) @@ -1357,7 +1351,7 @@ bad_gs: .previous /* Call softirq on interrupt stack. Interrupts are off. */ -ENTRY(call_softirq) +ENTRY(do_softirq_own_stack) CFI_STARTPROC pushq_cfi %rbp CFI_REL_OFFSET rbp,0 @@ -1374,7 +1368,7 @@ ENTRY(call_softirq) decl PER_CPU_VAR(irq_count) ret CFI_ENDPROC -END(call_softirq) +END(do_softirq_own_stack) #ifdef CONFIG_XEN zeroentry xen_hypervisor_callback xen_do_hypervisor_callback @@ -1497,7 +1491,7 @@ zeroentry xen_int3 do_int3 errorentry xen_stack_segment do_stack_segment #endif errorentry general_protection do_general_protection -errorentry page_fault do_page_fault +trace_errorentry page_fault do_page_fault #ifdef CONFIG_KVM_GUEST errorentry async_page_fault do_async_page_fault #endif diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 06f87bece92a..c61a14a4a310 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -35,8 +35,8 @@ asmlinkage void __init i386_start_kernel(void) /* Call the subarch specific early setup function */ switch (boot_params.hdr.hardware_subarch) { - case X86_SUBARCH_MRST: - x86_mrst_early_setup(); + case X86_SUBARCH_INTEL_MID: + x86_intel_mid_early_setup(); break; case X86_SUBARCH_CE4100: x86_ce4100_early_setup(); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 1be8e43b669e..85126ccbdf6b 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -162,7 +162,7 @@ asmlinkage void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, &early_idt_handlers[i]); + set_intr_gate(i, early_idt_handlers[i]); load_idt((const struct desc_ptr *)&idt_descr); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 0fa69127209a..05fd74f537d6 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -37,3 +37,10 @@ EXPORT_SYMBOL(strstr); EXPORT_SYMBOL(csum_partial); EXPORT_SYMBOL(empty_zero_page); + +#ifdef CONFIG_PREEMPT +EXPORT_SYMBOL(___preempt_schedule); +#ifdef CONFIG_CONTEXT_TRACKING +EXPORT_SYMBOL(___preempt_schedule_context); +#endif +#endif diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 5d576ab34403..e8368c6dd2a2 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -100,7 +100,7 @@ void unlazy_fpu(struct task_struct *tsk) __save_init_fpu(tsk); __thread_fpu_end(tsk); } else - tsk->fpu_counter = 0; + tsk->thread.fpu_counter = 0; preempt_enable(); } EXPORT_SYMBOL(unlazy_fpu); diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 9a5c460404dc..2e977b5d61dd 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -312,8 +312,7 @@ static void init_8259A(int auto_eoi) */ outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */ - /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 on x86-64, - to 0x20-0x27 on i386 */ + /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */ outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR); /* 8259A-1 (the master) has a slave on IR2 */ diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 4186755f1d7c..d7fcbedc9c43 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -100,9 +100,6 @@ 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 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); @@ -131,7 +128,6 @@ void irq_ctx_init(int cpu) THREAD_SIZE_ORDER)); memset(&irqctx->tinfo, 0, sizeof(struct thread_info)); irqctx->tinfo.cpu = cpu; - irqctx->tinfo.preempt_count = HARDIRQ_OFFSET; irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); per_cpu(hardirq_ctx, cpu) = irqctx; @@ -149,35 +145,21 @@ void irq_ctx_init(int cpu) cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu)); } -asmlinkage void do_softirq(void) +void do_softirq_own_stack(void) { - unsigned long flags; struct thread_info *curctx; union irq_ctx *irqctx; u32 *isp; - if (in_interrupt()) - return; - - local_irq_save(flags); - - if (local_softirq_pending()) { - curctx = current_thread_info(); - irqctx = __this_cpu_read(softirq_ctx); - irqctx->tinfo.task = curctx->task; - irqctx->tinfo.previous_esp = current_stack_pointer; - - /* build the stack frame on the softirq stack */ - isp = (u32 *) ((char *)irqctx + sizeof(*irqctx)); + curctx = current_thread_info(); + irqctx = __this_cpu_read(softirq_ctx); + irqctx->tinfo.task = curctx->task; + irqctx->tinfo.previous_esp = current_stack_pointer; - call_on_stack(__do_softirq, isp); - /* - * Shouldn't happen, we returned above if in_interrupt(): - */ - WARN_ON_ONCE(softirq_count()); - } + /* build the stack frame on the softirq stack */ + isp = (u32 *) ((char *)irqctx + sizeof(*irqctx)); - local_irq_restore(flags); + call_on_stack(__do_softirq, isp); } bool handle_irq(unsigned irq, struct pt_regs *regs) diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index d04d3ecded62..4d1c746892eb 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -87,24 +87,3 @@ bool handle_irq(unsigned irq, struct pt_regs *regs) generic_handle_irq_desc(irq, desc); return true; } - - -extern void call_softirq(void); - -asmlinkage void do_softirq(void) -{ - __u32 pending; - unsigned long flags; - - if (in_interrupt()) - return; - - local_irq_save(flags); - pending = local_softirq_pending(); - /* Switch to interrupt stack */ - if (pending) { - call_softirq(); - WARN_ON_ONCE(softirq_count()); - } - local_irq_restore(flags); -} diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index ee11b7dfbfbb..26d5a55a2736 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -42,15 +42,27 @@ static void __jump_label_transform(struct jump_entry *entry, int init) { union jump_code_union code; + const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; if (type == JUMP_LABEL_ENABLE) { - /* - * We are enabling this jump label. If it is not a nop - * then something must have gone wrong. - */ - if (unlikely(memcmp((void *)entry->code, ideal_nop, 5) != 0)) - bug_at((void *)entry->code, __LINE__); + if (init) { + /* + * Jump label is enabled for the first time. + * So we expect a default_nop... + */ + if (unlikely(memcmp((void *)entry->code, default_nop, 5) + != 0)) + bug_at((void *)entry->code, __LINE__); + } else { + /* + * ...otherwise expect an ideal_nop. Otherwise + * something went horribly wrong. + */ + if (unlikely(memcmp((void *)entry->code, ideal_nop, 5) + != 0)) + bug_at((void *)entry->code, __LINE__); + } code.jump = 0xe9; code.offset = entry->target - @@ -63,7 +75,6 @@ static void __jump_label_transform(struct jump_entry *entry, * are converting the default nop to the ideal nop. */ if (init) { - const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; if (unlikely(memcmp((void *)entry->code, default_nop, 5) != 0)) bug_at((void *)entry->code, __LINE__); } else { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 697b93af02dd..6dd802c6d780 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -464,7 +464,7 @@ static struct notifier_block kvm_cpu_notifier = { static void __init kvm_apf_trap_init(void) { - set_intr_gate(14, &async_page_fault); + set_intr_gate(14, async_page_fault); } void __init kvm_guest_init(void) @@ -609,7 +609,7 @@ static struct dentry *d_kvm_debug; struct dentry *kvm_init_debugfs(void) { - d_kvm_debug = debugfs_create_dir("kvm", NULL); + d_kvm_debug = debugfs_create_dir("kvm-guest", NULL); if (!d_kvm_debug) printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n"); @@ -775,11 +775,22 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; - printk(KERN_INFO "KVM setup paravirtual spinlock\n"); + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); + pv_lock_ops.unlock_kick = kvm_unlock_kick; +} + +static __init int kvm_spinlock_init_jump(void) +{ + if (!kvm_para_available()) + return 0; + if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) + return 0; static_key_slow_inc(¶virt_ticketlocks_enabled); + printk(KERN_INFO "KVM setup paravirtual spinlock\n"); - pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); - pv_lock_ops.unlock_kick = kvm_unlock_kick; + return 0; } +early_initcall(kvm_spinlock_init_jump); + #endif /* CONFIG_PARAVIRT_SPINLOCKS */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1570e0741344..e6041094ff26 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -139,6 +139,7 @@ bool kvm_check_and_clear_guest_paused(void) src = &hv_clock[cpu].pvti; if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) { src->flags &= ~PVCLOCK_GUEST_STOPPED; + pvclock_touch_watchdogs(); ret = true; } diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 7123b5df479d..c3d4cc972eca 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -216,6 +216,7 @@ int apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { c->microcode = rev; + uci->cpu_sig.rev = rev; return 0; } @@ -430,7 +431,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); if (request_firmware(&fw, (const char *)fw_name, device)) { - pr_err("failed to load file %s\n", fw_name); + pr_debug("failed to load file %s\n", fw_name); goto out; } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 216a4d754b0c..18be189368bb 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -49,7 +49,7 @@ void *module_alloc(unsigned long size) return NULL; return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, - -1, __builtin_return_address(0)); + NUMA_NO_NODE, __builtin_return_address(0)); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 88458faea2f8..05266b5aae22 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -46,7 +46,7 @@ static struct class *msr_class; static loff_t msr_seek(struct file *file, loff_t offset, int orig) { loff_t ret; - struct inode *inode = file->f_mapping->host; + struct inode *inode = file_inode(file); mutex_lock(&inode->i_mutex); switch (orig) { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index ba77ebc2c353..6fcb49ce50a1 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -113,10 +113,10 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 u64 before, delta, whole_msecs; int remainder_ns, decimal_msecs, thishandled; - before = local_clock(); + before = sched_clock(); thishandled = a->handler(type, regs); handled += thishandled; - delta = local_clock() - before; + delta = sched_clock() - before; trace_nmi_handler(a->handler, (int)delta, thishandled); if (delta < nmi_longest_ns) diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S new file mode 100644 index 000000000000..ca7f0d58a87d --- /dev/null +++ b/arch/x86/kernel/preempt.S @@ -0,0 +1,25 @@ + +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/asm.h> +#include <asm/calling.h> + +ENTRY(___preempt_schedule) + CFI_STARTPROC + SAVE_ALL + call preempt_schedule + RESTORE_ALL + ret + CFI_ENDPROC + +#ifdef CONFIG_CONTEXT_TRACKING + +ENTRY(___preempt_schedule_context) + CFI_STARTPROC + SAVE_ALL + call preempt_schedule_context + RESTORE_ALL + ret + CFI_ENDPROC + +#endif diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index c83516be1052..3fb8d95ab8b5 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -391,9 +391,9 @@ static void amd_e400_idle(void) * The switch back from broadcast mode needs to be * called with interrupts disabled. */ - local_irq_disable(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); - local_irq_enable(); + local_irq_disable(); + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); + local_irq_enable(); } else default_idle(); } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 884f98f69354..6f1236c29c4b 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -153,7 +153,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; - p->fpu_counter = 0; + p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); return 0; @@ -166,7 +166,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.ip = (unsigned long) ret_from_fork; task_user_gs(p) = get_user_gs(current_pt_regs()); - p->fpu_counter = 0; + p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; tsk = current; err = -ENOMEM; @@ -292,6 +292,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) set_iopl_mask(next->iopl); /* + * If it were not for PREEMPT_ACTIVE we could guarantee that the + * preempt_count of all tasks was equal here and this would not be + * needed. + */ + task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count); + this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count); + + /* * Now maybe handle debug registers and/or IO bitmaps */ if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV || diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index bb1dc51bab05..9c0280f93d05 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -63,7 +63,7 @@ void __show_regs(struct pt_regs *regs, int all) unsigned int ds, cs, es; printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); - printk_address(regs->ip, 1); + printk_address(regs->ip); printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->sp, regs->flags); printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n", @@ -163,7 +163,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.usersp = me->thread.usersp; set_tsk_thread_flag(p, TIF_FORK); - p->fpu_counter = 0; + p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); @@ -363,6 +363,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) this_cpu_write(old_rsp, next->usersp); this_cpu_write(current_task, next_p); + /* + * If it were not for PREEMPT_ACTIVE we could guarantee that the + * preempt_count of all tasks was equal here and this would not be + * needed. + */ + task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count); + this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count); + this_cpu_write(kernel_stack, (unsigned long)task_stack_page(next_p) + THREAD_SIZE - KERNEL_STACK_OFFSET); diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index a16bae3f83b3..2f355d229a58 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -43,6 +43,14 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) return pv_tsc_khz; } +void pvclock_touch_watchdogs(void) +{ + touch_softlockup_watchdog_sync(); + clocksource_touch_watchdog(); + rcu_cpu_stall_reset(); + reset_hung_task_detector(); +} + static atomic64_t last_value = ATOMIC64_INIT(0); void pvclock_resume(void) @@ -74,6 +82,11 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) version = __pvclock_read_cycles(src, &ret, &flags); } while ((src->version & 1) || version != src->version); + if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { + src->flags &= ~PVCLOCK_GUEST_STOPPED; + pvclock_touch_watchdogs(); + } + if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) && (flags & PVCLOCK_TSC_STABLE_BIT)) return ret; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 563ed91e6faa..da3c599584a3 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -61,7 +61,7 @@ static int __init set_bios_reboot(const struct dmi_system_id *d) if (reboot_type != BOOT_BIOS) { reboot_type = BOOT_BIOS; pr_info("%s series board detected. Selecting %s-method for reboots.\n", - "BIOS", d->ident); + d->ident, "BIOS"); } return 0; } @@ -117,7 +117,7 @@ static int __init set_pci_reboot(const struct dmi_system_id *d) if (reboot_type != BOOT_CF9) { reboot_type = BOOT_CF9; pr_info("%s series board detected. Selecting %s-method for reboots.\n", - "PCI", d->ident); + d->ident, "PCI"); } return 0; } @@ -127,7 +127,7 @@ static int __init set_kbd_reboot(const struct dmi_system_id *d) if (reboot_type != BOOT_KBD) { reboot_type = BOOT_KBD; pr_info("%s series board detected. Selecting %s-method for reboot.\n", - "KBD", d->ident); + d->ident, "KBD"); } return 0; } @@ -136,228 +136,256 @@ static int __init set_kbd_reboot(const struct dmi_system_id *d) * This is a single dmi_table handling all reboot quirks. */ static struct dmi_system_id __initdata reboot_dmi_table[] = { - { /* Handle problems with rebooting on Dell E520's */ - .callback = set_bios_reboot, - .ident = "Dell E520", + + /* Acer */ + { /* Handle reboot issue on Acer Aspire one */ + .callback = set_kbd_reboot, + .ident = "Acer Aspire One A110", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Dell DM061"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"), }, }, - { /* Handle problems with rebooting on Dell 1300's */ - .callback = set_bios_reboot, - .ident = "Dell PowerEdge 1300", + + /* Apple */ + { /* Handle problems with rebooting on Apple MacBook5 */ + .callback = set_pci_reboot, + .ident = "Apple MacBook5", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 1300/"), + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"), }, }, - { /* Handle problems with rebooting on Dell 300's */ - .callback = set_bios_reboot, - .ident = "Dell PowerEdge 300", + { /* Handle problems with rebooting on Apple MacBookPro5 */ + .callback = set_pci_reboot, + .ident = "Apple MacBookPro5", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 300/"), + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro5"), }, }, - { /* Handle problems with rebooting on Dell Optiplex 745's SFF */ - .callback = set_bios_reboot, - .ident = "Dell OptiPlex 745", + { /* Handle problems with rebooting on Apple Macmini3,1 */ + .callback = set_pci_reboot, + .ident = "Apple Macmini3,1", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Macmini3,1"), }, }, - { /* Handle problems with rebooting on Dell Optiplex 745's DFF */ + { /* Handle problems with rebooting on the iMac9,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac9,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), + }, + }, + + /* ASUS */ + { /* Handle problems with rebooting on ASUS P4S800 */ .callback = set_bios_reboot, - .ident = "Dell OptiPlex 745", + .ident = "ASUS P4S800", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), - DMI_MATCH(DMI_BOARD_NAME, "0MM599"), + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "P4S800"), }, }, - { /* Handle problems with rebooting on Dell Optiplex 745 with 0KW626 */ + + /* Dell */ + { /* Handle problems with rebooting on Dell DXP061 */ .callback = set_bios_reboot, - .ident = "Dell OptiPlex 745", + .ident = "Dell DXP061", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), - DMI_MATCH(DMI_BOARD_NAME, "0KW626"), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"), }, }, - { /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */ + { /* Handle problems with rebooting on Dell E520's */ .callback = set_bios_reboot, - .ident = "Dell OptiPlex 330", + .ident = "Dell E520", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"), - DMI_MATCH(DMI_BOARD_NAME, "0KP561"), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell DM061"), }, }, - { /* Handle problems with rebooting on Dell Optiplex 360 with 0T656F */ - .callback = set_bios_reboot, - .ident = "Dell OptiPlex 360", + { /* Handle problems with rebooting on the Latitude E5410. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E5410", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 360"), - DMI_MATCH(DMI_BOARD_NAME, "0T656F"), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5410"), }, }, - { /* Handle problems with rebooting on Dell OptiPlex 760 with 0G919G */ - .callback = set_bios_reboot, - .ident = "Dell OptiPlex 760", + { /* Handle problems with rebooting on the Latitude E5420. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E5420", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 760"), - DMI_MATCH(DMI_BOARD_NAME, "0G919G"), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5420"), }, }, - { /* Handle problems with rebooting on Dell 2400's */ - .callback = set_bios_reboot, - .ident = "Dell PowerEdge 2400", + { /* Handle problems with rebooting on the Latitude E6320. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6320", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2400"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"), }, }, - { /* Handle problems with rebooting on Dell T5400's */ - .callback = set_bios_reboot, - .ident = "Dell Precision T5400", + { /* Handle problems with rebooting on the Latitude E6420. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6420", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T5400"), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"), }, }, - { /* Handle problems with rebooting on Dell T7400's */ + { /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */ .callback = set_bios_reboot, - .ident = "Dell Precision T7400", + .ident = "Dell OptiPlex 330", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T7400"), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"), + DMI_MATCH(DMI_BOARD_NAME, "0KP561"), }, }, - { /* Handle problems with rebooting on HP laptops */ + { /* Handle problems with rebooting on Dell Optiplex 360 with 0T656F */ .callback = set_bios_reboot, - .ident = "HP Compaq Laptop", + .ident = "Dell OptiPlex 360", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 360"), + DMI_MATCH(DMI_BOARD_NAME, "0T656F"), }, }, - { /* Handle problems with rebooting on Dell XPS710 */ + { /* Handle problems with rebooting on Dell Optiplex 745's SFF */ .callback = set_bios_reboot, - .ident = "Dell XPS710", + .ident = "Dell OptiPlex 745", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), }, }, - { /* Handle problems with rebooting on Dell DXP061 */ + { /* Handle problems with rebooting on Dell Optiplex 745's DFF */ .callback = set_bios_reboot, - .ident = "Dell DXP061", + .ident = "Dell OptiPlex 745", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), + DMI_MATCH(DMI_BOARD_NAME, "0MM599"), }, }, - { /* Handle problems with rebooting on Sony VGN-Z540N */ + { /* Handle problems with rebooting on Dell Optiplex 745 with 0KW626 */ .callback = set_bios_reboot, - .ident = "Sony VGN-Z540N", + .ident = "Dell OptiPlex 745", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), + DMI_MATCH(DMI_BOARD_NAME, "0KW626"), }, }, - { /* Handle problems with rebooting on ASUS P4S800 */ + { /* Handle problems with rebooting on Dell OptiPlex 760 with 0G919G */ .callback = set_bios_reboot, - .ident = "ASUS P4S800", + .ident = "Dell OptiPlex 760", .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), - DMI_MATCH(DMI_BOARD_NAME, "P4S800"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 760"), + DMI_MATCH(DMI_BOARD_NAME, "0G919G"), }, }, - - { /* Handle reboot issue on Acer Aspire one */ - .callback = set_kbd_reboot, - .ident = "Acer Aspire One A110", + { /* Handle problems with rebooting on the OptiPlex 990. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 990", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), }, }, - { /* Handle problems with rebooting on Apple MacBook5 */ - .callback = set_pci_reboot, - .ident = "Apple MacBook5", + { /* Handle problems with rebooting on Dell 300's */ + .callback = set_bios_reboot, + .ident = "Dell PowerEdge 300", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 300/"), }, }, - { /* Handle problems with rebooting on Apple MacBookPro5 */ - .callback = set_pci_reboot, - .ident = "Apple MacBookPro5", + { /* Handle problems with rebooting on Dell 1300's */ + .callback = set_bios_reboot, + .ident = "Dell PowerEdge 1300", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro5"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 1300/"), }, }, - { /* Handle problems with rebooting on Apple Macmini3,1 */ - .callback = set_pci_reboot, - .ident = "Apple Macmini3,1", + { /* Handle problems with rebooting on Dell 2400's */ + .callback = set_bios_reboot, + .ident = "Dell PowerEdge 2400", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Macmini3,1"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2400"), }, }, - { /* Handle problems with rebooting on the iMac9,1. */ + { /* Handle problems with rebooting on the Dell PowerEdge C6100. */ .callback = set_pci_reboot, - .ident = "Apple iMac9,1", + .ident = "Dell PowerEdge C6100", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell"), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), }, }, - { /* Handle problems with rebooting on the Latitude E6320. */ + { /* Handle problems with rebooting on the Precision M6600. */ .callback = set_pci_reboot, - .ident = "Dell Latitude E6320", + .ident = "Dell Precision M6600", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), }, }, - { /* Handle problems with rebooting on the Latitude E5420. */ - .callback = set_pci_reboot, - .ident = "Dell Latitude E5420", + { /* Handle problems with rebooting on Dell T5400's */ + .callback = set_bios_reboot, + .ident = "Dell Precision T5400", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5420"), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T5400"), }, }, - { /* Handle problems with rebooting on the Latitude E6420. */ - .callback = set_pci_reboot, - .ident = "Dell Latitude E6420", + { /* Handle problems with rebooting on Dell T7400's */ + .callback = set_bios_reboot, + .ident = "Dell Precision T7400", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T7400"), }, }, - { /* Handle problems with rebooting on the OptiPlex 990. */ - .callback = set_pci_reboot, - .ident = "Dell OptiPlex 990", + { /* Handle problems with rebooting on Dell XPS710 */ + .callback = set_bios_reboot, + .ident = "Dell XPS710", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"), }, }, - { /* Handle problems with rebooting on the Precision M6600. */ - .callback = set_pci_reboot, - .ident = "Dell OptiPlex 990", + + /* Hewlett-Packard */ + { /* Handle problems with rebooting on HP laptops */ + .callback = set_bios_reboot, + .ident = "HP Compaq Laptop", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"), + }, + }, + + /* Sony */ + { /* Handle problems with rebooting on Sony VGN-Z540N */ + .callback = set_bios_reboot, + .ident = "Sony VGN-Z540N", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"), }, }, + { } }; @@ -511,10 +539,13 @@ static void native_machine_emergency_restart(void) case BOOT_CF9_COND: if (port_cf9_safe) { - u8 cf9 = inb(0xcf9) & ~6; + u8 reboot_code = reboot_mode == REBOOT_WARM ? + 0x06 : 0x0E; + u8 cf9 = inb(0xcf9) & ~reboot_code; outb(cf9|2, 0xcf9); /* Request hard reset */ udelay(50); - outb(cf9|6, 0xcf9); /* Actually do the reset */ + /* Actually do the reset */ + outb(cf9|reboot_code, 0xcf9); udelay(50); } reboot_type = BOOT_KBD; @@ -526,6 +557,10 @@ static void native_machine_emergency_restart(void) void native_machine_shutdown(void) { /* Stop the cpus and apics */ +#ifdef CONFIG_X86_IO_APIC + disable_IO_APIC(); +#endif + #ifdef CONFIG_SMP /* * Stop all of the others. Also disable the local irq to @@ -538,10 +573,6 @@ void native_machine_shutdown(void) lapic_shutdown(); -#ifdef CONFIG_X86_IO_APIC - disable_IO_APIC(); -#endif - #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 0aa29394ed6f..ca9622a25e95 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -12,7 +12,7 @@ #include <asm/vsyscall.h> #include <asm/x86_init.h> #include <asm/time.h> -#include <asm/mrst.h> +#include <asm/intel-mid.h> #include <asm/rtc.h> #ifdef CONFIG_X86_32 @@ -189,9 +189,17 @@ static __init int add_rtc_cmos(void) return 0; /* Intel MID platforms don't have ioport rtc */ - if (mrst_identify_cpu()) + if (intel_mid_identify_cpu()) return -ENODEV; +#ifdef CONFIG_ACPI + if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) { + /* This warning can likely go away again in a year or two. */ + pr_info("ACPI: not registering RTC platform device\n"); + return -ENODEV; + } +#endif + platform_device_register(&rtc_device); dev_info(&rtc_device.dev, "registered platform RTC device (no PNP device found)\n"); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f0de6294b955..cb233bc9dee3 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -993,6 +993,7 @@ void __init setup_arch(char **cmdline_p) efi_init(); dmi_scan_machine(); + dmi_memdev_walk(); dmi_set_dump_stack_arch_desc(); /* @@ -1120,8 +1121,6 @@ void __init setup_arch(char **cmdline_p) acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start); #endif - reserve_crashkernel(); - vsmp_init(); io_delay_init(); @@ -1134,6 +1133,13 @@ void __init setup_arch(char **cmdline_p) early_acpi_boot_init(); initmem_init(); + + /* + * Reserve memory for crash kernel after SRAT is parsed so that it + * won't consume hotpluggable memory. + */ + reserve_crashkernel(); + memblock_find_dma_reserve(); #ifdef CONFIG_KVM_GUEST diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index aecc98a93d1b..85dc05a3aa02 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -73,36 +73,14 @@ #include <asm/setup.h> #include <asm/uv/uv.h> #include <linux/mc146818rtc.h> - #include <asm/smpboot_hooks.h> #include <asm/i8259.h> - #include <asm/realmode.h> +#include <asm/misc.h> /* State of each CPU */ DEFINE_PER_CPU(int, cpu_state) = { 0 }; -#ifdef CONFIG_HOTPLUG_CPU -/* - * We need this for trampoline_base protection from concurrent accesses when - * off- and onlining cores wildly. - */ -static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex); - -void cpu_hotplug_driver_lock(void) -{ - mutex_lock(&x86_cpu_hotplug_driver_mutex); -} - -void cpu_hotplug_driver_unlock(void) -{ - mutex_unlock(&x86_cpu_hotplug_driver_mutex); -} - -ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; } -ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; } -#endif - /* Number of siblings per CPU package */ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); @@ -648,21 +626,46 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) return (send_status | accept_status); } +void smp_announce(void) +{ + int num_nodes = num_online_nodes(); + + printk(KERN_INFO "x86: Booted up %d node%s, %d CPUs\n", + num_nodes, (num_nodes > 1 ? "s" : ""), num_online_cpus()); +} + /* reduce the number of lines printed when booting a large cpu count system */ static void announce_cpu(int cpu, int apicid) { static int current_node = -1; int node = early_cpu_to_node(cpu); + static int width, node_width; + + if (!width) + width = num_digits(num_possible_cpus()) + 1; /* + '#' sign */ + + if (!node_width) + node_width = num_digits(num_possible_nodes()) + 1; /* + '#' */ + + if (cpu == 1) + printk(KERN_INFO "x86: Booting SMP configuration:\n"); if (system_state == SYSTEM_BOOTING) { if (node != current_node) { if (current_node > (-1)) - pr_cont(" OK\n"); + pr_cont("\n"); current_node = node; - pr_info("Booting Node %3d, Processors ", node); + + printk(KERN_INFO ".... node %*s#%d, CPUs: ", + node_width - num_digits(node), " ", node); } - pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " OK\n" : ""); - return; + + /* Add padding for the BSP */ + if (cpu == 1) + pr_cont("%*s", width + 1, " "); + + pr_cont("%*s#%d", width - num_digits(cpu), " ", cpu); + } else pr_info("Booting Node %d Processor %d APIC 0x%x\n", node, cpu, apicid); diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 22513e96b012..86179d409893 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -72,14 +72,14 @@ __init int create_simplefb(const struct screen_info *si, * the part that is occupied by the framebuffer */ len = mode->height * mode->stride; len = PAGE_ALIGN(len); - if (len > si->lfb_size << 16) { + if (len > (u64)si->lfb_size << 16) { printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); return -EINVAL; } /* setup IORESOURCE_MEM as framebuffer memory */ memset(&res, 0, sizeof(res)); - res.flags = IORESOURCE_MEM; + res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; res.name = simplefb_resname; res.start = si->lfb_base; res.end = si->lfb_base + len - 1; diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 6e60b5fe2244..649b010da00b 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -65,29 +65,32 @@ int __ref _debug_hotplug_cpu(int cpu, int action) if (!cpu_is_hotpluggable(cpu)) return -EINVAL; - cpu_hotplug_driver_lock(); + lock_device_hotplug(); switch (action) { case 0: ret = cpu_down(cpu); if (!ret) { pr_info("CPU %u is now offline\n", cpu); + dev->offline = true; kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } else pr_debug("Can't offline CPU%d.\n", cpu); break; case 1: ret = cpu_up(cpu); - if (!ret) + if (!ret) { + dev->offline = false; kobject_uevent(&dev->kobj, KOBJ_ONLINE); - else + } else { pr_debug("Can't online CPU%d.\n", cpu); + } break; default: ret = -EINVAL; } - cpu_hotplug_driver_unlock(); + unlock_device_hotplug(); return ret; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 8c8093b146ca..b857ed890b4c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -88,7 +88,7 @@ static inline void conditional_sti(struct pt_regs *regs) static inline void preempt_conditional_sti(struct pt_regs *regs) { - inc_preempt_count(); + preempt_count_inc(); if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } @@ -103,7 +103,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) local_irq_disable(); - dec_preempt_count(); + preempt_count_dec(); } static int __kprobes @@ -653,7 +653,7 @@ void math_state_restore(void) return; } - tsk->fpu_counter++; + tsk->thread.fpu_counter++; } EXPORT_SYMBOL_GPL(math_state_restore); @@ -713,7 +713,7 @@ void __init early_trap_init(void) /* int3 can be called from all */ set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); #ifdef CONFIG_X86_32 - set_intr_gate(X86_TRAP_PF, &page_fault); + set_intr_gate(X86_TRAP_PF, page_fault); #endif load_idt(&idt_descr); } @@ -721,7 +721,7 @@ void __init early_trap_init(void) void __init early_trap_pf_init(void) { #ifdef CONFIG_X86_64 - set_intr_gate(X86_TRAP_PF, &page_fault); + set_intr_gate(X86_TRAP_PF, page_fault); #endif } @@ -737,30 +737,30 @@ void __init trap_init(void) early_iounmap(p, 4); #endif - set_intr_gate(X86_TRAP_DE, ÷_error); + set_intr_gate(X86_TRAP_DE, divide_error); set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK); /* int4 can be called from all */ set_system_intr_gate(X86_TRAP_OF, &overflow); - set_intr_gate(X86_TRAP_BR, &bounds); - set_intr_gate(X86_TRAP_UD, &invalid_op); - set_intr_gate(X86_TRAP_NM, &device_not_available); + set_intr_gate(X86_TRAP_BR, bounds); + set_intr_gate(X86_TRAP_UD, invalid_op); + set_intr_gate(X86_TRAP_NM, device_not_available); #ifdef CONFIG_X86_32 set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS); #else set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK); #endif - set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun); - set_intr_gate(X86_TRAP_TS, &invalid_TSS); - set_intr_gate(X86_TRAP_NP, &segment_not_present); + set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); + set_intr_gate(X86_TRAP_TS, invalid_TSS); + set_intr_gate(X86_TRAP_NP, segment_not_present); set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); - set_intr_gate(X86_TRAP_GP, &general_protection); - set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug); - set_intr_gate(X86_TRAP_MF, &coprocessor_error); - set_intr_gate(X86_TRAP_AC, &alignment_check); + set_intr_gate(X86_TRAP_GP, general_protection); + set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); + set_intr_gate(X86_TRAP_MF, coprocessor_error); + set_intr_gate(X86_TRAP_AC, alignment_check); #ifdef CONFIG_X86_MCE set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK); #endif - set_intr_gate(X86_TRAP_XF, &simd_coprocessor_error); + set_intr_gate(X86_TRAP_XF, simd_coprocessor_error); /* Reserve all the builtin and the syscall vector: */ for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 10c4f3006afd..da6b35a98260 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -199,6 +199,15 @@ SECTIONS __x86_cpu_dev_end = .; } +#ifdef CONFIG_X86_INTEL_MID + .x86_intel_mid_dev.init : AT(ADDR(.x86_intel_mid_dev.init) - \ + LOAD_OFFSET) { + __x86_intel_mid_dev_start = .; + *(.x86_intel_mid_dev.init) + __x86_intel_mid_dev_end = .; + } +#endif + /* * start address and size of operations which during runtime * can be patched with virtualization friendly instructions or diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index b014d9414d08..040681928e9d 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -66,3 +66,10 @@ EXPORT_SYMBOL(empty_zero_page); #ifndef CONFIG_PARAVIRT EXPORT_SYMBOL(native_load_gs_index); #endif + +#ifdef CONFIG_PREEMPT +EXPORT_SYMBOL(___preempt_schedule); +#ifdef CONFIG_CONTEXT_TRACKING +EXPORT_SYMBOL(___preempt_schedule_context); +#endif +#endif diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 8ce0072cd700..021783b1f46a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -116,6 +116,8 @@ struct x86_msi_ops x86_msi = { .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, .setup_hpet_msi = default_setup_hpet_msi, + .msi_mask_irq = default_msi_mask_irq, + .msix_mask_irq = default_msix_mask_irq, }; /* MSI arch specific hooks */ @@ -138,6 +140,14 @@ void arch_restore_msi_irqs(struct pci_dev *dev, int irq) { x86_msi.restore_msi_irqs(dev, irq); } +u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +{ + return x86_msi.msi_mask_irq(desc, mask, flag); +} +u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag) +{ + return x86_msi.msix_mask_irq(desc, flag); +} #endif struct x86_io_apic_ops x86_io_apic_ops = { |
