perf/core: Fix time on IOC_ENABLE

Vince reported that when we do IOC_ENABLE/IOC_DISABLE while the task
is SIGSTOP'ed state the timestamps go wobbly.

It turns out we indeed fail to correctly account time while in 'OFF'
state and doing IOC_ENABLE without getting scheduled in exposes the
problem.

Further thinking about this problem, it occurred to me that we can
suffer a similar fate when we migrate an uncore event between CPUs.
The perf_event_install() on the 'new' CPU will do add_event_to_ctx()
which will reset all the time stamp, resulting in a subsequent
update_event_times() to overwrite the total_time_* fields with smaller
values.

Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/events/core.c b/kernel/events/core.c
index a654b8a3586fc1f54f84f45e89d89617541bb52a..ee20d4c546b5ebc0248c084e11c483e0ef800c6f 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2217,6 +2217,33 @@ static int group_can_go_on(struct perf_event *event,
        return can_add_hw;
 }
 
+/*
+ * Complement to update_event_times(). This computes the tstamp_* values to
+ * continue 'enabled' state from @now, and effectively discards the time
+ * between the prior tstamp_stopped and now (as we were in the OFF state, or
+ * just switched (context) time base).
+ *
+ * This further assumes '@event->state == INACTIVE' (we just came from OFF) and
+ * cannot have been scheduled in yet. And going into INACTIVE state means
+ * '@event->tstamp_stopped = @now'.
+ *
+ * Thus given the rules of update_event_times():
+ *
+ *   total_time_enabled = tstamp_stopped - tstamp_enabled
+ *   total_time_running = tstamp_stopped - tstamp_running
+ *
+ * We can insert 'tstamp_stopped == now' and reverse them to compute new
+ * tstamp_* values.
+ */
+static void __perf_event_enable_time(struct perf_event *event, u64 now)
+{
+       WARN_ON_ONCE(event->state != PERF_EVENT_STATE_INACTIVE);
+
+       event->tstamp_stopped = now;
+       event->tstamp_enabled = now - event->total_time_enabled;
+       event->tstamp_running = now - event->total_time_running;
+}
+
 static void add_event_to_ctx(struct perf_event *event,
                               struct perf_event_context *ctx)
 {
@@ -2224,9 +2251,12 @@ static void add_event_to_ctx(struct perf_event *event,
 
        list_add_event(event, ctx);
        perf_group_attach(event);
-       event->tstamp_enabled = tstamp;
-       event->tstamp_running = tstamp;
-       event->tstamp_stopped = tstamp;
+       /*
+        * We can be called with event->state == STATE_OFF when we create with
+        * .disabled = 1. In that case the IOC_ENABLE will call this function.
+        */
+       if (event->state == PERF_EVENT_STATE_INACTIVE)
+               __perf_event_enable_time(event, tstamp);
 }
 
 static void ctx_sched_out(struct perf_event_context *ctx,
@@ -2471,10 +2501,11 @@ static void __perf_event_mark_enabled(struct perf_event *event)
        u64 tstamp = perf_event_time(event);
 
        event->state = PERF_EVENT_STATE_INACTIVE;
-       event->tstamp_enabled = tstamp - event->total_time_enabled;
+       __perf_event_enable_time(event, tstamp);
        list_for_each_entry(sub, &event->sibling_list, group_entry) {
+               /* XXX should not be > INACTIVE if event isn't */
                if (sub->state >= PERF_EVENT_STATE_INACTIVE)
-                       sub->tstamp_enabled = tstamp - sub->total_time_enabled;
+                       __perf_event_enable_time(sub, tstamp);
        }
 }