[tip: sched/core] sched/fair: Prevent negative lag increase during delayed dequeue

[tip-bot2 for Vincent Guittot]

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     059258b0d424510202b6f2796279dbdbf0c6a83d
Gitweb:        https://git.kernel.org/tip/059258b0d424510202b6f2796279dbdbf0c6a83d
Author:        Vincent Guittot <vincent.guittot@xxxxxxxxxx>
AuthorDate:    Tue, 31 Mar 2026 18:23:52 +02:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Fri, 03 Apr 2026 14:23:41 +02:00

sched/fair: Prevent negative lag increase during delayed dequeue

Delayed dequeue feature aims to reduce the negative lag of a dequeued
task while sleeping but it can happens that newly enqueued tasks will
move backward the avg vruntime and increase its negative lag.
When the delayed dequeued task wakes up, it has more neg lag compared
to being dequeued immediately or to other tasks that have been
dequeued just before theses new enqueues.

Ensure that the negative lag of a delayed dequeued task doesn't
increase during its delayed dequeued phase while waiting for its neg
lag to diseappear. Similarly, we remove any positive lag that the
delayed dequeued task could have gain during thsi period.

Short slice tasks are particularly impacted in overloaded system.

Test on snapdragon rb5:

hackbench -T -p -l 16000000 -g 2 1> /dev/null &
cyclictest -t 1 -i 2777 -D 333 --policy=fair --mlock  -h 20000 -q

The scheduling latency of cyclictest is:

                       tip/sched/core  tip/sched/core    +this patch
cyclictest slice  (ms) (default)2.8             8               8
hackbench slice   (ms) (default)2.8            20              20
Total Samples          |   115632          119733          119806
Average           (us) |      364              64(-82%)        61(- 5%)
Median (P50)      (us) |       60              56(- 7%)        56(  0%)
90th Percentile   (us) |     1166              62(-95%)        62(  0%)
99th Percentile   (us) |     4192              73(-98%)        72(- 1%)
99.9th Percentile (us) |     8528            2707(-68%)      1300(-52%)
Maximum           (us) |    17735           14273(-20%)     13525(- 5%)

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://patch.msgid.link/20260331162352.551501-1-vincent.guittot@xxxxxxxxxx
---
 kernel/sched/fair.c | 56 ++++++++++++++++++++++++++------------------
 1 file changed, 34 insertions(+), 22 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 41293d5..597ce5b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -840,11 +840,33 @@ static s64 entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 avrunt
 	return clamp(vlag, -limit, limit);
 }
 
-static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
+/*
+ * Delayed dequeue aims to reduce the negative lag of a dequeued task. While
+ * updating the lag of an entity, check that negative lag didn't increase
+ * during the delayed dequeue period which would be unfair.
+ * Similarly, check that the entity didn't gain positive lag when DELAY_ZERO
+ * is set.
+ *
+ * Return true if the lag has been adjusted.
+ */
+static __always_inline
+bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	s64 vlag = entity_lag(cfs_rq, se, avg_vruntime(cfs_rq));
+	bool ret;
+
 	WARN_ON_ONCE(!se->on_rq);
 
-	se->vlag = entity_lag(cfs_rq, se, avg_vruntime(cfs_rq));
+	if (se->sched_delayed) {
+		/* previous vlag < 0 otherwise se would not be delayed */
+		vlag = max(vlag, se->vlag);
+		if (sched_feat(DELAY_ZERO))
+			vlag = min(vlag, 0);
+	}
+	ret = (vlag == se->vlag);
+	se->vlag = vlag;
+
+	return ret;
 }
 
 /*
@@ -5564,13 +5586,6 @@ static void clear_delayed(struct sched_entity *se)
 	}
 }
 
-static inline void finish_delayed_dequeue_entity(struct sched_entity *se)
-{
-	clear_delayed(se);
-	if (sched_feat(DELAY_ZERO) && se->vlag > 0)
-		se->vlag = 0;
-}
-
 static bool
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -5596,6 +5611,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		if (sched_feat(DELAY_DEQUEUE) && delay &&
 		    !entity_eligible(cfs_rq, se)) {
 			update_load_avg(cfs_rq, se, 0);
+			update_entity_lag(cfs_rq, se);
 			set_delayed(se);
 			return false;
 		}
@@ -5635,7 +5651,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_cfs_group(se);
 
 	if (flags & DEQUEUE_DELAYED)
-		finish_delayed_dequeue_entity(se);
+		clear_delayed(se);
 
 	if (cfs_rq->nr_queued == 0) {
 		update_idle_cfs_rq_clock_pelt(cfs_rq);
@@ -7084,18 +7100,14 @@ requeue_delayed_entity(struct sched_entity *se)
 	WARN_ON_ONCE(!se->sched_delayed);
 	WARN_ON_ONCE(!se->on_rq);
 
-	if (sched_feat(DELAY_ZERO)) {
-		update_entity_lag(cfs_rq, se);
-		if (se->vlag > 0) {
-			cfs_rq->nr_queued--;
-			if (se != cfs_rq->curr)
-				__dequeue_entity(cfs_rq, se);
-			se->vlag = 0;
-			place_entity(cfs_rq, se, 0);
-			if (se != cfs_rq->curr)
-				__enqueue_entity(cfs_rq, se);
-			cfs_rq->nr_queued++;
-		}
+	if (update_entity_lag(cfs_rq, se)) {
+		cfs_rq->nr_queued--;
+		if (se != cfs_rq->curr)
+			__dequeue_entity(cfs_rq, se);
+		place_entity(cfs_rq, se, 0);
+		if (se != cfs_rq->curr)
+			__enqueue_entity(cfs_rq, se);
+		cfs_rq->nr_queued++;
 	}
 
 	update_load_avg(cfs_rq, se, 0);