Skip to contentSkip to conversation

perf: Fix throttle logic

tip:perf/core tip-bot for Peter Zijlstra 1 participant 1 message Feb 16, 2011

lore
Share & tools
lore
#0 lore raw
Commit-ID:  4fe757dd48a9e95e1a071291f15dda5421dacb66
Gitweb:     http://git.kernel.org/tip/4fe757dd48a9e95e1a071291f15dda5421dacb66
Author:     Peter Zijlstra <[email protected]>
AuthorDate: Tue, 15 Feb 2011 22:26:07 +0100
Committer:  Ingo Molnar <[email protected]>
CommitDate: Wed, 16 Feb 2011 13:25:29 +0100

perf: Fix throttle logic

It was possible to call pmu::start() on an already running event. In particular this lead so some wreckage as the hrtimer events would re-initialize active timers.

This was due to throttled events being activated again by scheduling. Scheduling in a context would add and force start events, resulting in running events with a possible throttle status. The next tick to hit that task will then try to unthrottle the event and call ->start() on an already running event.

LKML-Reference: <new-submission>

---
 kernel/perf_event.c |   19 +++++++++++++++----
 1 files changed, 15 insertions(+), 4 deletions(-)
kernel/perf_event.c +15 -4
index 999835b..656222f 100644
@@ -782,6 +782,10 @@ retry:
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
+#define MAX_INTERRUPTS (~0ULL)
+
+static void perf_log_throttle(struct perf_event *event, int enable);
+
 static int
 event_sched_in(struct perf_event *event,
 		 struct perf_cpu_context *cpuctx,
@@ -794,6 +798,17 @@ event_sched_in(struct perf_event *event,
 
 	event->state = PERF_EVENT_STATE_ACTIVE;
 	event->oncpu = smp_processor_id();
+
+	/*
+	 * Unthrottle events, since we scheduled we might have missed several
+	 * ticks already, also for a heavily scheduling task there is little
+	 * guarantee it'll get a tick in a timely manner.
+	 */
+	if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) {
+		perf_log_throttle(event, 1);
+		event->hw.interrupts = 0;
+	}
+
 	/*
 	 * The new state must be visible before we turn it on in the hardware:
 	 */
@@ -1596,10 +1611,6 @@ void __perf_event_task_sched_in(struct task_struct *task)
 	}
 }
 
-#define MAX_INTERRUPTS (~0ULL)
-
-static void perf_log_throttle(struct perf_event *event, int enable);
-
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 {
 	u64 frequency = event->attr.sample_freq;