sched/fair: Reorder enqueue/dequeue_task_fair path

The walk through the cgroup hierarchy during the enqueue/dequeue of a task
is split in 2 distinct parts for throttled cfs_rq without any added value
but making code less readable.

Change the code ordering such that everything related to a cfs_rq
(throttled or not) will be done in the same loop.

In addition, the same steps ordering is used when updating a cfs_rq:

 - update_load_avg
 - update_cfs_group
 - update *h_nr_running

This reordering enables the use of h_nr_running in PELT algorithm.

No functional and performance changes are expected and have been noticed
during tests.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: "Dietmar Eggemann <dietmar.eggemann@arm.com>"
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-5-mgorman@techsingularity.net

kernel/sched/fair.c

@@ -5260,32 +5260,31 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cfs_rq = cfs_rq_of(se);
 		enqueue_entity(cfs_rq, se, flags);
 
-		/*
-		 * end evaluation on encountering a throttled cfs_rq
-		 *
-		 * note: in the case of encountering a throttled cfs_rq we will
-		 * post the final h_nr_running increment below.
-		 */
-		if (cfs_rq_throttled(cfs_rq))
-			break;
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto enqueue_throttle;
+
 		flags = ENQUEUE_WAKEUP;
 	}
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		cfs_rq->h_nr_running++;
-		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			break;
+			goto enqueue_throttle;
 
 		update_load_avg(cfs_rq, se, UPDATE_TG);
 		update_cfs_group(se);
+
+		cfs_rq->h_nr_running++;
+		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 	}
 
+enqueue_throttle:
 	if (!se) {
 		add_nr_running(rq, 1);
 		/*
@@ -5346,17 +5345,13 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, flags);
 
-		/*
-		 * end evaluation on encountering a throttled cfs_rq
-		 *
-		 * note: in the case of encountering a throttled cfs_rq we will
-		 * post the final h_nr_running decrement below.
-		*/
-		if (cfs_rq_throttled(cfs_rq))
-			break;
 		cfs_rq->h_nr_running--;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto dequeue_throttle;
+
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
 			/* Avoid re-evaluating load for this entity: */
@@ -5374,16 +5369,19 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		cfs_rq->h_nr_running--;
-		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			break;
+			goto dequeue_throttle;
 
 		update_load_avg(cfs_rq, se, UPDATE_TG);
 		update_cfs_group(se);
+
+		cfs_rq->h_nr_running--;
+		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 	}
 
+dequeue_throttle:
 	if (!se)
 		sub_nr_running(rq, 1);