perf_counter: fix NMI race in task clock

We should not be updating ctx->time from NMI context, work around that.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090408130408.681326666@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 863703b3158f8682bafdfe2d4618c4310cb63b4d..84a39081344c85e6d2e7cc4228878d3c61ae8232 100644 (file)
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -319,8 +319,6 @@ static void __perf_counter_disable(void *info)
 
        spin_lock_irqsave(&ctx->lock, flags);
 
-       update_context_time(ctx);
-
        /*
         * If the counter is on, turn it off.
         * If it is in error state, leave it in error state.
@@ -2335,13 +2333,11 @@ static const struct hw_perf_counter_ops perf_ops_cpu_clock = {
  * Software counter: task time clock
  */
 
-static void task_clock_perf_counter_update(struct perf_counter *counter)
+static void task_clock_perf_counter_update(struct perf_counter *counter, u64 now)
 {
-       u64 prev, now;
+       u64 prev;
        s64 delta;
 
-       now = counter->ctx->time;
-
        prev = atomic64_xchg(&counter->hw.prev_count, now);
        delta = now - prev;
        atomic64_add(delta, &counter->count);
@@ -2369,13 +2365,24 @@ static int task_clock_perf_counter_enable(struct perf_counter *counter)
 static void task_clock_perf_counter_disable(struct perf_counter *counter)
 {
        hrtimer_cancel(&counter->hw.hrtimer);
-       task_clock_perf_counter_update(counter);
+       task_clock_perf_counter_update(counter, counter->ctx->time);
+
 }
 
 static void task_clock_perf_counter_read(struct perf_counter *counter)
 {
-       update_context_time(counter->ctx);
-       task_clock_perf_counter_update(counter);
+       u64 time;
+
+       if (!in_nmi()) {
+               update_context_time(counter->ctx);
+               time = counter->ctx->time;
+       } else {
+               u64 now = perf_clock();
+               u64 delta = now - counter->ctx->timestamp;
+               time = counter->ctx->time + delta;
+       }
+
+       task_clock_perf_counter_update(counter, time);
 }
 
 static const struct hw_perf_counter_ops perf_ops_task_clock = {