[PATCH] sched/fair: combine detach into dequeue when migrating task

[PATCH] sched/fair: combine detach into dequeue when migrating task

[Chengming Zhou]

When we are migrating task out of the CPU, we can combine detach
into dequeue_entity() to save the independent detach_entity_cfs_rq()
in migrate_task_rq_fair().

This optimization is like combining DO_ATTACH in the enqueue_entity()
when migrating task to the CPU.

So we don't have to traverse the CFS tree twice to do these load
detach and propagation.

Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
---
 kernel/sched/fair.c | 33 ++++++++++++++++++++++-----------
 1 file changed, 22 insertions(+), 11 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e0cd4052e32f..1db7c97a5fe6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3896,6 +3896,7 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 #define UPDATE_TG	0x1
 #define SKIP_AGE_LOAD	0x2
 #define DO_ATTACH	0x4
+#define DO_DETACH	0x8
 
 /* Update task and its cfs_rq load average */
 static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
@@ -3913,7 +3914,14 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	decayed  = update_cfs_rq_load_avg(now, cfs_rq);
 	decayed |= propagate_entity_load_avg(se);
 
-	if (!se->avg.last_update_time && (flags & DO_ATTACH)) {
+	if (flags & DO_DETACH) {
+		/*
+		 * DO_DETACH means we're here from dequeue_entity()
+		 * and we are migrating task out of the CPU.
+		 */
+		detach_entity_load_avg(cfs_rq, se);
+		update_tg_load_avg(cfs_rq);
+	} else if (!se->avg.last_update_time && (flags & DO_ATTACH)) {
 
 		/*
 		 * DO_ATTACH means we're here from enqueue_entity().
@@ -4426,6 +4434,14 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
+	int action = UPDATE_TG;
+
+	/*
+	 * If we are migrating task from the CPU, detach load_avg when dequeue.
+	 */
+	if (entity_is_task(se) && task_of(se)->on_rq == TASK_ON_RQ_MIGRATING)
+		action |= DO_DETACH;
+
 	/*
 	 * Update run-time statistics of the 'current'.
 	 */
@@ -4440,7 +4456,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 *   - For group entity, update its weight to reflect the new share
 	 *     of its group cfs_rq.
 	 */
-	update_load_avg(cfs_rq, se, UPDATE_TG);
+	update_load_avg(cfs_rq, se, action);
 	se_update_runnable(se);
 
 	update_stats_dequeue_fair(cfs_rq, se, flags);
@@ -6940,15 +6956,10 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 		se->vruntime -= min_vruntime;
 	}
 
-	if (p->on_rq == TASK_ON_RQ_MIGRATING) {
-		/*
-		 * In case of TASK_ON_RQ_MIGRATING we in fact hold the 'old'
-		 * rq->lock and can modify state directly.
-		 */
-		lockdep_assert_rq_held(task_rq(p));
-		detach_entity_cfs_rq(&p->se);
-
-	} else {
+	/*
+	 * In case of TASK_ON_RQ_MIGRATING we already detach in dequeue_entity.
+	 */
+	if (p->on_rq != TASK_ON_RQ_MIGRATING) {
 		/*
 		 * We are supposed to update the task to "current" time, then
 		 * its up to date and ready to go to new CPU/cfs_rq. But we
-- 
2.36.1