perf_events: Fix time tracking for events with pid != -1 and cpu != -1

Per-thread events with a cpu filter, i.e., cpu != -1, were not
reporting correct timings when the thread never ran on the
monitored cpu. The time enabled was reported as a negative
value.

This patch fixes the problem by updating tstamp_stopped,
tstamp_running in event_sched_out() for events with filters and
which are marked as INACTIVE.

The function group_sched_out() is modified to systematically
call into event_sched_out() to avoid duplicating the timing
adjustment code twice.

With the patch, I now get:

$ task_cpu -i -e unhalted_core_cycles,unhalted_core_cycles
noploop 2 noploop for 2 seconds
CPU0 0		   unhalted_core_cycles (ena=1,991,136,594, run=0)
CPU0 0		   unhalted_core_cycles (ena=1,991,136,594, run=0)

CPU1 0		   unhalted_core_cycles (ena=1,991,136,594, run=0)
CPU1 0		   unhalted_core_cycles (ena=1,991,136,594, run=0)

CPU2 0		   unhalted_core_cycles (ena=1,991,136,594, run=0)
CPU2 0		   unhalted_core_cycles (ena=1,991,136,594, run=0)

CPU3 4,747,990,931 unhalted_core_cycles (ena=1,991,136,594, run=1,991,136,594)
CPU3 4,747,990,931 unhalted_core_cycles (ena=1,991,136,594, run=1,991,136,594)
Signed-off-by: NStephane Eranian <eranian@gmail.com>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Cc: davem@davemloft.net
Cc: fweisbec@gmail.com
Cc: perfmon2-devel@lists.sf.net
Cc: eranian@google.com
LKML-Reference: <4c76802d.aae9d80a.115d.70fe@mx.google.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

kernel/perf_event.c

@@ -402,11 +402,31 @@ static void perf_group_detach(struct perf_event *event)
 	}
 }
 
+static inline int
+event_filter_match(struct perf_event *event)
+{
+	return event->cpu == -1 || event->cpu == smp_processor_id();
+}
+
 static void
 event_sched_out(struct perf_event *event,
 		  struct perf_cpu_context *cpuctx,
 		  struct perf_event_context *ctx)
 {
+	u64 delta;
+	/*
+	 * An event which could not be activated because of
+	 * filter mismatch still needs to have its timings
+	 * maintained, otherwise bogus information is return
+	 * via read() for time_enabled, time_running:
+	 */
+	if (event->state == PERF_EVENT_STATE_INACTIVE
+	    && !event_filter_match(event)) {
+		delta = ctx->time - event->tstamp_stopped;
+		event->tstamp_running += delta;
+		event->tstamp_stopped = ctx->time;
+	}
+
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
 		return;
 
@@ -432,9 +452,7 @@ group_sched_out(struct perf_event *group_event,
 		struct perf_event_context *ctx)
 {
 	struct perf_event *event;
-
-	if (group_event->state != PERF_EVENT_STATE_ACTIVE)
-		return;
+	int state = group_event->state;
 
 	event_sched_out(group_event, cpuctx, ctx);
 
@@ -444,7 +462,7 @@ group_sched_out(struct perf_event *group_event,
 	list_for_each_entry(event, &group_event->sibling_list, group_entry)
 		event_sched_out(event, cpuctx, ctx);
 
-	if (group_event->attr.exclusive)
+	if (state == PERF_EVENT_STATE_ACTIVE && group_event->attr.exclusive)
 		cpuctx->exclusive = 0;
 }