8 files changed, 105 insertions, 28 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 224392d8fe8c..5e975298fa81 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -530,7 +530,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
                 err = -ENOMEM;
                 goto out;
         }
-        if (!alloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
+        if (!zalloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
                 kfree(b);
                 err = -ENOMEM;
                 goto out;
@@ -543,7 +543,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
         cpumask_setall(b->cpus);
 #else
-        cpumask_copy(b->cpus, c->llc_shared_map);
+        cpumask_set_cpu(cpu, b->cpus);
 #endif
 
         per_cpu(threshold_banks, cpu)[bank] = b;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index c2a8b26d4fea..d9368eeda309 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -202,10 +202,11 @@ static int therm_throt_process(bool new_event, int event, int level)
 
 #ifdef CONFIG_SYSFS
 /* Add/Remove thermal_throttle interface for CPU device: */
-static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
+static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
+                                unsigned int cpu)
 {
         int err;
-        struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+        struct cpuinfo_x86 *c = &cpu_data(cpu);
 
         err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group);
         if (err)
@@ -251,7 +252,7 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb,
         case CPU_UP_PREPARE:
         case CPU_UP_PREPARE_FROZEN:
                 mutex_lock(&therm_cpu_lock);
-                err = thermal_throttle_add_dev(sys_dev);
+                err = thermal_throttle_add_dev(sys_dev, cpu);
                 mutex_unlock(&therm_cpu_lock);
                 WARN_ON(err);
                 break;
@@ -287,7 +288,7 @@ static __init int thermal_throttle_init_device(void)
 #endif
         /* connect live CPUs to sysfs */
         for_each_online_cpu(cpu) {
-                err = thermal_throttle_add_dev(get_cpu_sysdev(cpu));
+                err = thermal_throttle_add_dev(get_cpu_sysdev(cpu), cpu);
                 WARN_ON(err);
         }
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index f2da20fda02d..3efdf2870a35 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1154,7 +1154,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
                 /*
                  * event overflow
                  */
-                handled         = 1;
+                handled++;
                 data.period     = event->hw.last_period;
 
                 if (!x86_perf_event_set_period(event))
@@ -1200,12 +1200,20 @@ void perf_events_lapic_init(void)
         apic_write(APIC_LVTPC, APIC_DM_NMI);
 }
 
+struct pmu_nmi_state {
+        unsigned int    marked;
+        int             handled;
+};
+
+static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi);
+
 static int __kprobes
 perf_event_nmi_handler(struct notifier_block *self,
                          unsigned long cmd, void *__args)
 {
         struct die_args *args = __args;
-        struct pt_regs *regs;
+        unsigned int this_nmi;
+        int handled;
 
         if (!atomic_read(&active_events))
                 return NOTIFY_DONE;
@@ -1214,22 +1222,47 @@ perf_event_nmi_handler(struct notifier_block *self,
         case DIE_NMI:
         case DIE_NMI_IPI:
                 break;
-
+        case DIE_NMIUNKNOWN:
+                this_nmi = percpu_read(irq_stat.__nmi_count);
+                if (this_nmi != __get_cpu_var(pmu_nmi).marked)
+                        /* let the kernel handle the unknown nmi */
+                        return NOTIFY_DONE;
+                /*
+                 * This one is a PMU back-to-back nmi. Two events
+                 * trigger 'simultaneously' raising two back-to-back
+                 * NMIs. If the first NMI handles both, the latter
+                 * will be empty and daze the CPU. So, we drop it to
+                 * avoid false-positive 'unknown nmi' messages.
+                 */
+                return NOTIFY_STOP;
         default:
                 return NOTIFY_DONE;
         }
 
-        regs = args->regs;
-
         apic_write(APIC_LVTPC, APIC_DM_NMI);
-        /*
-         * Can't rely on the handled return value to say it was our NMI, two
-         * events could trigger 'simultaneously' raising two back-to-back NMIs.
-         *
-         * If the first NMI handles both, the latter will be empty and daze
-         * the CPU.
-         */
-        x86_pmu.handle_irq(regs);
+
+        handled = x86_pmu.handle_irq(args->regs);
+        if (!handled)
+                return NOTIFY_DONE;
+
+        this_nmi = percpu_read(irq_stat.__nmi_count);
+        if ((handled > 1) ||
+                /* the next nmi could be a back-to-back nmi */
+            ((__get_cpu_var(pmu_nmi).marked == this_nmi) &&
+             (__get_cpu_var(pmu_nmi).handled > 1))) {
+                /*
+                 * We could have two subsequent back-to-back nmis: The
+                 * first handles more than one counter, the 2nd
+                 * handles only one counter and the 3rd handles no
+                 * counter.
+                 *
+                 * This is the 2nd nmi because the previous was
+                 * handling more than one counter. We will mark the
+                 * next (3rd) and then drop it if unhandled.
+                 */
+                __get_cpu_var(pmu_nmi).marked   = this_nmi + 1;
+                __get_cpu_var(pmu_nmi).handled  = handled;
+        }
 
         return NOTIFY_STOP;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index d8d86d014008..ee05c90012d2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -712,7 +712,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
         struct perf_sample_data data;
         struct cpu_hw_events *cpuc;
         int bit, loops;
-        u64 ack, status;
+        u64 status;
+        int handled = 0;
 
         perf_sample_data_init(&data, 0);
 
@@ -728,6 +729,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
         loops = 0;
 again:
+        intel_pmu_ack_status(status);
         if (++loops > 100) {
                 WARN_ONCE(1, "perfevents: irq loop stuck!\n");
                 perf_event_print_debug();
@@ -736,19 +738,22 @@ again:
         }
 
         inc_irq_stat(apic_perf_irqs);
-        ack = status;
 
         intel_pmu_lbr_read();
 
         /*
          * PEBS overflow sets bit 62 in the global status register
          */
-        if (__test_and_clear_bit(62, (unsigned long *)&status))
+        if (__test_and_clear_bit(62, (unsigned long *)&status)) {
+                handled++;
                 x86_pmu.drain_pebs(regs);
+        }
 
         for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
                 struct perf_event *event = cpuc->events[bit];
 
+                handled++;
+
                 if (!test_bit(bit, cpuc->active_mask))
                         continue;
 
@@ -761,8 +766,6 @@ again:
                         x86_pmu_stop(event);
         }
 
-        intel_pmu_ack_status(ack);
-
         /*
          * Repeat if there is more work to be done:
          */
@@ -772,7 +775,7 @@ again:
 
 done:
         intel_pmu_enable_all(0);
-        return 1;
+        return handled;
 }
 
 static struct event_constraint *
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index febb12cea795..b560db3305be 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -497,6 +497,8 @@ static int p4_hw_config(struct perf_event *event)
                 event->hw.config |= event->attr.config &
                         (p4_config_pack_escr(P4_ESCR_MASK_HT) |
                          p4_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED));
+
+                event->hw.config &= ~P4_CCCR_FORCE_OVF;
         }
 
         rc = x86_setup_perfctr(event);
@@ -690,7 +692,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
                 inc_irq_stat(apic_perf_irqs);
         }
 
-        return handled > 0;
+        return handled;
 }
 
 /*
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 1f11f5ce668f..a46cb3522c0c 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -40,6 +40,7 @@
 
 static unsigned int             mxcsr_feature_mask __read_mostly = 0xffffffffu;
 unsigned int xstate_size;
+EXPORT_SYMBOL_GPL(xstate_size);
 unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32);
 static struct i387_fxsave_struct fx_scratch __cpuinitdata;
 
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index a874495b3673..e2a595257390 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -45,8 +45,7 @@ void __init setup_trampoline_page_table(void)
         /* Copy kernel address range */
         clone_pgd_range(trampoline_pg_dir + KERNEL_PGD_BOUNDARY,
                         swapper_pg_dir + KERNEL_PGD_BOUNDARY,
-                        min_t(unsigned long, KERNEL_PGD_PTRS,
-                              KERNEL_PGD_BOUNDARY));
+                        KERNEL_PGD_PTRS);
 
         /* Initialize low mappings */
         clone_pgd_range(trampoline_pg_dir,
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ce8e50239332..d632934cb638 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -626,6 +626,44 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
         local_irq_restore(flags);
 }
 
+static unsigned long long cyc2ns_suspend;
+
+void save_sched_clock_state(void)
+{
+        if (!sched_clock_stable)
+                return;
+
+        cyc2ns_suspend = sched_clock();
+}
+
+/*
+ * Even on processors with invariant TSC, TSC gets reset in some the
+ * ACPI system sleep states. And in some systems BIOS seem to reinit TSC to
+ * arbitrary value (still sync'd across cpu's) during resume from such sleep
+ * states. To cope up with this, recompute the cyc2ns_offset for each cpu so
+ * that sched_clock() continues from the point where it was left off during
+ * suspend.
+ */
+void restore_sched_clock_state(void)
+{
+        unsigned long long offset;
+        unsigned long flags;
+        int cpu;
+
+        if (!sched_clock_stable)
+                return;
+
+        local_irq_save(flags);
+
+        get_cpu_var(cyc2ns_offset) = 0;
+        offset = cyc2ns_suspend - sched_clock();
+
+        for_each_possible_cpu(cpu)
+                per_cpu(cyc2ns_offset, cpu) = offset;
+
+        local_irq_restore(flags);
+}
+
 #ifdef CONFIG_CPU_FREQ
 
 /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency