Merge branch 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (28 commits)
  perf session: Fix infinite loop in __perf_session__process_events
  perf evsel: Support perf_evsel__open(cpus > 1 && threads > 1)
  perf sched: Use PTHREAD_STACK_MIN to avoid pthread_attr_setstacksize() fail
  perf tools: Emit clearer message for sys_perf_event_open ENOENT return
  perf stat: better error message for unsupported events
  perf sched: Fix allocation result check
  perf, x86: P4 PMU - Fix unflagged overflows handling
  dynamic debug: Fix build issue with older gcc
  tracing: Fix TRACE_EVENT power tracepoint creation
  tracing: Fix preempt count leak
  tracepoint: Add __rcu annotation
  tracing: remove duplicate null-pointer check in skb tracepoint
  tracing/trivial: Add missing comma in TRACE_EVENT comment
  tracing: Include module.h in define_trace.h
  x86: Save rbp in pt_regs on irq entry
  x86, dumpstack: Fix unused variable warning
  x86, NMI: Clean-up default_do_nmi()
  x86, NMI: Allow NMI reason io port (0x61) to be processed on any CPU
  x86, NMI: Remove DIE_NMI_IPI
  x86, NMI: Add priorities to handlers
  ...

3 files changed, 19 insertions, 17 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index e7dbde7bfedb..a77971979564 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -25,6 +25,7 @@
 #include <linux/gfp.h>
 #include <asm/mce.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 /* Update fake mce registers on current CPU. */
 static void inject_mce(struct mce *m)
@@ -83,7 +84,7 @@ static int mce_raise_notify(struct notifier_block *self,
         struct die_args *args = (struct die_args *)data;
         int cpu = smp_processor_id();
         struct mce *m = &__get_cpu_var(injectm);
-        if (val != DIE_NMI_IPI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
+        if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
                 return NOTIFY_DONE;
         cpumask_clear_cpu(cpu, mce_inject_cpumask);
         if (m->inject_flags & MCJ_EXCEPTION)
@@ -95,7 +96,7 @@ static int mce_raise_notify(struct notifier_block *self,
 
 static struct notifier_block mce_raise_nb = {
         .notifier_call = mce_raise_notify,
-        .priority = 1000,
+        .priority = NMI_LOCAL_NORMAL_PRIOR,
 };
 
 /* Inject mce on current CPU */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 04921017abe0..9d977a2ea693 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1267,7 +1267,6 @@ perf_event_nmi_handler(struct notifier_block *self,
 
         switch (cmd) {
         case DIE_NMI:
-        case DIE_NMI_IPI:
                 break;
         case DIE_NMIUNKNOWN:
                 this_nmi = percpu_read(irq_stat.__nmi_count);
@@ -1317,7 +1316,7 @@ perf_event_nmi_handler(struct notifier_block *self,
 static __read_mostly struct notifier_block perf_event_nmi_notifier = {
         .notifier_call          = perf_event_nmi_handler,
         .next                   = NULL,
-        .priority               = 1
+        .priority               = NMI_LOCAL_LOW_PRIOR,
 };
 
 static struct event_constraint unconstrained;
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 81400b93e694..e56b9bfbabd1 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -753,19 +753,21 @@ out:
 
 static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 {
-        int overflow = 0;
-        u32 low, high;
+        u64 v;
 
-        rdmsr(hwc->config_base + hwc->idx, low, high);
-
-        /* we need to check high bit for unflagged overflows */
-        if ((low & P4_CCCR_OVF) || !(high & (1 << 31))) {
-                overflow = 1;
-                (void)checking_wrmsrl(hwc->config_base + hwc->idx,
-                        ((u64)low) & ~P4_CCCR_OVF);
+        /* an official way for overflow indication */
+        rdmsrl(hwc->config_base + hwc->idx, v);
+        if (v & P4_CCCR_OVF) {
+                wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF);
+                return 1;
         }
 
-        return overflow;
+        /* it might be unflagged overflow */
+        rdmsrl(hwc->event_base + hwc->idx, v);
+        if (!(v & ARCH_P4_CNTRVAL_MASK))
+                return 1;
+
+        return 0;
 }
 
 static void p4_pmu_disable_pebs(void)
@@ -1152,9 +1154,9 @@ static __initconst const struct x86_pmu p4_pmu = {
          */
         .num_counters           = ARCH_P4_MAX_CCCR,
         .apic                   = 1,
-        .cntval_bits            = 40,
-        .cntval_mask            = (1ULL << 40) - 1,
-        .max_period             = (1ULL << 39) - 1,
+        .cntval_bits            = ARCH_P4_CNTRVAL_BITS,
+        .cntval_mask            = ARCH_P4_CNTRVAL_MASK,
+        .max_period             = (1ULL << (ARCH_P4_CNTRVAL_BITS - 1)) - 1,
         .hw_config              = p4_hw_config,
         .schedule_events        = p4_pmu_schedule_events,
         /*