From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Mon, 24 Feb 2020 09:52:14 +0000
Subject: sched/fair: Reorder enqueue/dequeue_task_fair path
Patch-mainline: v5.7-rc1
Git-commit: 6d4d22468dae3d8757af9f8b81b848a76ef4409d
References: bsc#1179093

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

[mkoutny: Adjusted for missing idle_h_nr_running member]
Acked-by: Michal Koutný <mkoutny@suse.com>
---
 kernel/sched/fair.c |   38 ++++++++++++++++++--------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5352,30 +5352,29 @@ enqueue_task_fair(struct rq *rq, struct
 		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++;
 
+		/* 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++;
 
+		/* 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++;
 	}
 
+enqueue_throttle:
 	if (!se)
 		add_nr_running(rq, 1);
 
@@ -5416,16 +5415,12 @@ static void dequeue_task_fair(struct rq
 		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--;
 
+		/* 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: */
@@ -5443,15 +5438,18 @@ static void dequeue_task_fair(struct rq
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		cfs_rq->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--;
 	}
 
+dequeue_throttle:
 	if (!se)
 		sub_nr_running(rq, 1);