[B][SRU][PATCH 2/5] sched/fair: Reorder enqueue/dequeue_task_fair path

[po-hsu.lin at canonical.com]

From: Vincent Guittot <vincent.guittot at linaro.org>

Buglink: https://bugs.launchpad.net/bugs/1931325

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 at linaro.org>
Signed-off-by: Mel Gorman <mgorman at techsingularity.net>
Signed-off-by: Ingo Molnar <mingo at kernel.org>
Reviewed-by: "Dietmar Eggemann <dietmar.eggemann at arm.com>"
Acked-by: Peter Zijlstra <a.p.zijlstra at chello.nl>
Cc: Juri Lelli <juri.lelli at redhat.com>
Cc: Valentin Schneider <valentin.schneider at arm.com>
Cc: Phil Auld <pauld at redhat.com>
Cc: Hillf Danton <hdanton at sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-5-mgorman@techsingularity.net
(backported commit 6d4d22468dae3d8757af9f8b81b848a76ef4409d)
[PHLin: backported without changes for SCHED_IDLE tasks count tracking 43e9f7f231e40e]
Signed-off-by: Po-Hsu Lin <po-hsu.lin at canonical.com>
---
 kernel/sched/fair.c | 38 ++++++++++++++++++--------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7e2bd3d..773a3bb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5310,30 +5310,29 @@ 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++;
 
+		/* 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);
 
@@ -5374,16 +5373,12 @@ 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--;
 
+		/* 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: */
@@ -5401,15 +5396,18 @@ 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--;
 
+		/* 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);
 
-- 
2.7.4