[RFC PATCH v2 5/5] sched/fair: Simplify ancestor enqueue loops

[Michal Koutný]

When a task is enqueued or cfs_rq is unthrottled we have work to do from
the cfs_rq in question possibly up to root. The important nodes on the
path are throttled cfs_rqs or cfs_rqs already enqueud to their parent.

Instead of multiple (interrupted) loops make all work in a single loop
and decide what all needs to be done inside it. This undoes parts of
commit 39f23ce07b93 ("sched/fair: Fix unthrottle_cfs_rq() for
leaf_cfs_rq list") but it should not bring any functional changes.

Note some PELT stats update code is duplicated both in enqueue_entity
and the ancestor loop (update_load_avg, se_update_runnable,
update_cfs_group). It'd be nice to factor these out, however, the later
parts of enqueue_entity rely on the updates, so stick with the current
repetition.

Signed-off-by: Michal Koutný <mkoutny@xxxxxxxx>
---
 kernel/sched/fair.c | 57 +++++++++++++++++----------------------------
 1 file changed, 21 insertions(+), 36 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9978485334ec..79f183336fa8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4883,6 +4883,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long task_delta, idle_task_delta;
+	int enqueue = 1;
 
 	cfs_rq->throttled = 0;
 
@@ -4911,29 +4912,21 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	task_delta = cfs_rq->h_nr_running;
 	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
-		if (se->on_rq)
-			break;
 		cfs_rq = cfs_rq_of(se);
-		enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
-
-		cfs_rq->h_nr_running += task_delta;
-		cfs_rq->idle_h_nr_running += idle_task_delta;
 
-		/* end evaluation on encountering a throttled cfs_rq */
-		if (cfs_rq_throttled(cfs_rq))
-			goto unthrottle_throttle;
-	}
-
-	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
-
-		update_load_avg(cfs_rq, se, UPDATE_TG);
-		se_update_runnable(se);
+		if (se->on_rq)
+			enqueue = 0;
+		if (enqueue)
+			enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+		else {
+			update_load_avg(cfs_rq, se, UPDATE_TG);
+			se_update_runnable(se);
+			/* XXX: no update_cfs_group(se); */
+		}
 
 		cfs_rq->h_nr_running += task_delta;
 		cfs_rq->idle_h_nr_running += idle_task_delta;
 
-
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
 			goto unthrottle_throttle;
@@ -5537,6 +5530,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_entity *se = &p->se;
 	int idle_h_nr_running = task_has_idle_policy(p);
 	int task_new = !(flags & ENQUEUE_WAKEUP);
+	int enqueue = 1;
 
 	/*
 	 * The code below (indirectly) updates schedutil which looks at
@@ -5555,27 +5549,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
 
 	for_each_sched_entity(se) {
-		if (se->on_rq)
-			break;
 		cfs_rq = cfs_rq_of(se);
-		enqueue_entity(cfs_rq, se, flags);
 
-		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);
-
-		update_load_avg(cfs_rq, se, UPDATE_TG);
-		se_update_runnable(se);
-		update_cfs_group(se);
+		if (se->on_rq)
+			enqueue = 0;
+		if (enqueue) {
+			enqueue_entity(cfs_rq, se, flags);
+			flags = ENQUEUE_WAKEUP;
+		} else {
+			update_load_avg(cfs_rq, se, UPDATE_TG);
+			se_update_runnable(se);
+			update_cfs_group(se);
+		}
 
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
-- 
2.32.0