perf, x86: Catch spurious interrupts after disabling counters

Some cpus still deliver spurious interrupts after disabling a
counter. This caused 'undelivered NMI' messages. This patch
fixes this. Introduced by:

  4177c42: perf, x86: Try to handle unknown nmis with an enabled PMU

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Robert Richter <robert.richter@amd.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: gorcunov@gmail.com <gorcunov@gmail.com>
Cc: fweisbec@gmail.com <fweisbec@gmail.com>
Cc: ying.huang@intel.com <ying.huang@intel.com>
Cc: ming.m.lin@intel.com <ming.m.lin@intel.com>
Cc: yinghai@kernel.org <yinghai@kernel.org>
Cc: andi@firstfloor.org <andi@firstfloor.org>
Cc: eranian@google.com <eranian@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20100915162034.GO13563@erda.amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3efdf28..03a5b03 100644 (file)
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -102,6 +102,7 @@ struct cpu_hw_events {
         */
        struct perf_event       *events[X86_PMC_IDX_MAX]; /* in counter order */
        unsigned long           active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+       unsigned long           running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
        int                     enabled;
 
        int                     n_events;
@@ -1010,6 +1011,7 @@ static int x86_pmu_start(struct perf_event *event)
        x86_perf_event_set_period(event);
        cpuc->events[idx] = event;
        __set_bit(idx, cpuc->active_mask);
+       __set_bit(idx, cpuc->running);
        x86_pmu.enable(event);
        perf_event_update_userpage(event);
 
@@ -1141,8 +1143,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
        cpuc = &__get_cpu_var(cpu_hw_events);
 
        for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-               if (!test_bit(idx, cpuc->active_mask))
+               if (!test_bit(idx, cpuc->active_mask)) {
+                       /*
+                        * Though we deactivated the counter some cpus
+                        * might still deliver spurious interrupts still
+                        * in flight. Catch them:
+                        */
+                       if (__test_and_clear_bit(idx, cpuc->running))
+                               handled++;
                        continue;
+               }
 
                event = cpuc->events[idx];
                hwc = &event->hw;