Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Ingo writes:
  "scheduler fixes:

   Two fixes: a CFS-throttling bug fix, and an interactivity fix."

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Fix the min_vruntime update logic in dequeue_entity()
  sched/fair: Fix throttle_list starvation with low CFS quota

2 files changed, 22 insertions, 4 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7fc4a371bdd2..908c9cdae2f0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4001,7 +4001,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * put back on, and if we advance min_vruntime, we'll be placed back
 	 * further than we started -- ie. we'll be penalized.
 	 */
-	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE)
+	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
 		update_min_vruntime(cfs_rq);
 }
 
@@ -4476,9 +4476,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 	/*
 	 * Add to the _head_ of the list, so that an already-started
-	 * distribute_cfs_runtime will not see us
+	 * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is
+	 * not running add to the tail so that later runqueues don't get starved.
 	 */
-	list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+	if (cfs_b->distribute_running)
+		list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+	else
+		list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
 
 	/*
 	 * If we're the first throttled task, make sure the bandwidth
@@ -4622,14 +4626,16 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	 * in us over-using our runtime if it is all used during this loop, but
 	 * only by limited amounts in that extreme case.
 	 */
-	while (throttled && cfs_b->runtime > 0) {
+	while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) {
 		runtime = cfs_b->runtime;
+		cfs_b->distribute_running = 1;
 		raw_spin_unlock(&cfs_b->lock);
 		/* we can't nest cfs_b->lock while distributing bandwidth */
 		runtime = distribute_cfs_runtime(cfs_b, runtime,
 						 runtime_expires);
 		raw_spin_lock(&cfs_b->lock);
 
+		cfs_b->distribute_running = 0;
 		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
 
 		cfs_b->runtime -= min(runtime, cfs_b->runtime);
@@ -4740,6 +4746,11 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 
 	/* confirm we're still not at a refresh boundary */
 	raw_spin_lock(&cfs_b->lock);
+	if (cfs_b->distribute_running) {
+		raw_spin_unlock(&cfs_b->lock);
+		return;
+	}
+
 	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
 		raw_spin_unlock(&cfs_b->lock);
 		return;
@@ -4749,6 +4760,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 		runtime = cfs_b->runtime;
 
 	expires = cfs_b->runtime_expires;
+	if (runtime)
+		cfs_b->distribute_running = 1;
+
 	raw_spin_unlock(&cfs_b->lock);
 
 	if (!runtime)
@@ -4759,6 +4773,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 	raw_spin_lock(&cfs_b->lock);
 	if (expires == cfs_b->runtime_expires)
 		cfs_b->runtime -= min(runtime, cfs_b->runtime);
+	cfs_b->distribute_running = 0;
 	raw_spin_unlock(&cfs_b->lock);
 }
 
@@ -4867,6 +4882,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	cfs_b->period_timer.function = sched_cfs_period_timer;
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
+	cfs_b->distribute_running = 0;
 }
 
 static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 455fa330de04..9683f458aec7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -346,6 +346,8 @@ struct cfs_bandwidth {
 	int			nr_periods;
 	int			nr_throttled;
 	u64			throttled_time;
+
+	bool                    distribute_running;
 #endif
 };