[tip: sched/core] sched/fair: Implement DELAY_ZERO

[tip-bot2 for Peter Zijlstra]

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

Commit-ID:     54a58a78779169f9c92a51facf6de7ce94962328
Gitweb:        https://git.kernel.org/tip/54a58a78779169f9c92a51facf6de7ce94962328
Author:        Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate:    Thu, 23 May 2024 12:26:06 +02:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Sat, 17 Aug 2024 11:06:44 +02:00

sched/fair: Implement DELAY_ZERO

'Extend' DELAY_DEQUEUE by noting that since we wanted to dequeued them
at the 0-lag point, truncate lag (eg. don't let them earn positive
lag).

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Valentin Schneider <vschneid@xxxxxxxxxx>
Tested-by: Valentin Schneider <vschneid@xxxxxxxxxx>
Link: https://lkml.kernel.org/r/20240727105030.403750550@xxxxxxxxxxxxx
---
 kernel/sched/fair.c     | 20 ++++++++++++++++++--
 kernel/sched/features.h |  3 +++
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index da5065a..1a59339 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5447,8 +5447,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
 		update_min_vruntime(cfs_rq);
 
-	if (flags & DEQUEUE_DELAYED)
+	if (flags & DEQUEUE_DELAYED) {
 		se->sched_delayed = 0;
+		if (sched_feat(DELAY_ZERO) && se->vlag > 0)
+			se->vlag = 0;
+	}
 
 	if (cfs_rq->nr_running == 0)
 		update_idle_cfs_rq_clock_pelt(cfs_rq);
@@ -5527,7 +5530,6 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
 		dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
 		SCHED_WARN_ON(se->sched_delayed);
 		SCHED_WARN_ON(se->on_rq);
-
 		return NULL;
 	}
 	return se;
@@ -6825,6 +6827,20 @@ requeue_delayed_entity(struct sched_entity *se)
 	SCHED_WARN_ON(!se->sched_delayed);
 	SCHED_WARN_ON(!se->on_rq);
 
+	if (sched_feat(DELAY_ZERO)) {
+		update_entity_lag(cfs_rq, se);
+		if (se->vlag > 0) {
+			cfs_rq->nr_running--;
+			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_running++;
+		}
+	}
+
 	se->sched_delayed = 0;
 }
 
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 1feaa7b..7fdeb55 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -34,8 +34,11 @@ SCHED_FEAT(CACHE_HOT_BUDDY, true)
  * By delaying the dequeue for non-eligible tasks, they remain in the
  * competition and can burn off their negative lag. When they get selected
  * they'll have positive lag by definition.
+ *
+ * DELAY_ZERO clips the lag on dequeue (or wakeup) to 0.
  */
 SCHED_FEAT(DELAY_DEQUEUE, true)
+SCHED_FEAT(DELAY_ZERO, true)
 
 /*
  * Allow wakeup-time preemption of the current task: