[PATCH 3/4] perf: Add child_count

[Peter Zijlstra]

Only child counters adding back their values into the parent counter
are responsible for cross-cpu updates to event->count.

So if we pull that out into a new child_count variable, we get an
event->count that is only modified locally.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
LKML-Reference: <new-submission>
---
 include/linux/perf_event.h |    1 +
 kernel/perf_event.c        |    4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

Index: linux-2.6/include/linux/perf_event.h
===================================================================
--- linux-2.6.orig/include/linux/perf_event.h
+++ linux-2.6/include/linux/perf_event.h
@@ -648,6 +648,7 @@ struct perf_event {
 
 	enum perf_event_active_state	state;
 	atomic64_t			count;
+	atomic64_t			child_count;
 
 	/*
 	 * These are the total time in nanoseconds that the event
Index: linux-2.6/kernel/perf_event.c
===================================================================
--- linux-2.6.orig/kernel/perf_event.c
+++ linux-2.6/kernel/perf_event.c
@@ -1703,7 +1703,7 @@ static void __perf_event_read(void *info
 
 static inline u64 perf_event_count(struct perf_event *event)
 {
-	return atomic64_read(&event->count);
+	return atomic64_read(&event->count) + atomic64_read(&event->child_count);
 }
 
 static u64 perf_event_read(struct perf_event *event)
@@ -5282,7 +5282,7 @@ static void sync_child_event(struct perf
 	/*
 	 * Add back the child's count to the parent's count:
 	 */
-	atomic64_add(child_val, &parent_event->count);
+	atomic64_add(child_val, &parent_event->child_count);
 	atomic64_add(child_event->total_time_enabled,
 		     &parent_event->child_total_time_enabled);
 	atomic64_add(child_event->total_time_running,


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/