sched: Throttle entities exceeding their allowed bandwidth

With the machinery in place to throttle and unthrottle entities, as well as
handle their participation (or lack there of) we can now enable throttling.

There are 2 points that we must check whether it's time to set throttled state:
 put_prev_entity() and enqueue_entity().

- put_prev_entity() is the typical throttle path, we reach it by exceeding our
  allocated run-time within update_curr()->account_cfs_rq_runtime() and going
  through a reschedule.

- enqueue_entity() covers the case of a wake-up into an already throttled
  group.  In this case we know the group cannot be on_rq and can throttle
  immediately.  Checks are added at time of put_prev_entity() and
  enqueue_entity()
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110721184758.091415417@google.comSigned-off-by: Ingo Molnar <mingo@elte.hu>

kernel/sched_fair.c

@@ -970,6 +970,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 	se->vruntime = vruntime;
 }
 
+static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
+
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -999,8 +1001,10 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
 
-	if (cfs_rq->nr_running == 1)
+	if (cfs_rq->nr_running == 1) {
 		list_add_leaf_cfs_rq(cfs_rq);
+		check_enqueue_throttle(cfs_rq);
+	}
 }
 
 static void __clear_buddies_last(struct sched_entity *se)
@@ -1202,6 +1206,8 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 	return se;
 }
 
+static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
+
 static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 {
 	/*
@@ -1211,6 +1217,9 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	if (prev->on_rq)
 		update_curr(cfs_rq);
 
+	/* throttle cfs_rqs exceeding runtime */
+	check_cfs_rq_runtime(cfs_rq);
+
 	check_spread(cfs_rq, prev);
 	if (prev->on_rq) {
 		update_stats_wait_start(cfs_rq, prev);
@@ -1464,7 +1473,7 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 	return 0;
 }
 
-static __used void throttle_cfs_rq(struct cfs_rq *cfs_rq)
+static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
@@ -1657,9 +1666,48 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 
 	return idle;
 }
+
+/*
+ * When a group wakes up we want to make sure that its quota is not already
+ * expired/exceeded, otherwise it may be allowed to steal additional ticks of
+ * runtime as update_curr() throttling can not not trigger until it's on-rq.
+ */
+static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
+{
+	/* an active group must be handled by the update_curr()->put() path */
+	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
+		return;
+
+	/* ensure the group is not already throttled */
+	if (cfs_rq_throttled(cfs_rq))
+		return;
+
+	/* update runtime allocation */
+	account_cfs_rq_runtime(cfs_rq, 0);
+	if (cfs_rq->runtime_remaining <= 0)
+		throttle_cfs_rq(cfs_rq);
+}
+
+/* conditionally throttle active cfs_rq's from put_prev_entity() */
+static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+{
+	if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0))
+		return;
+
+	/*
+	 * it's possible for a throttled entity to be forced into a running
+	 * state (e.g. set_curr_task), in this case we're finished.
+	 */
+	if (cfs_rq_throttled(cfs_rq))
+		return;
+
+	throttle_cfs_rq(cfs_rq);
+}
 #else
 static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
 				     unsigned long delta_exec) {}
+static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
+static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
 
 static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
 {