[tip: sched/core] sched/fair: Avoid re-setting virtual deadline on 'migrations'

[tip-bot2 for Peter Zijlstra]

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

Commit-ID:     82e9d0456e06cebe2c89f3c73cdbc9e3805e9437
Gitweb:        https://git.kernel.org/tip/82e9d0456e06cebe2c89f3c73cdbc9e3805e9437
Author:        Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate:    Fri, 31 May 2024 15:49:40 +02:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Sat, 17 Aug 2024 11:06:45 +02:00

sched/fair: Avoid re-setting virtual deadline on 'migrations'

During OSPM24 Youssef noted that migrations are re-setting the virtual
deadline. Notably everything that does a dequeue-enqueue, like setting
nice, changing preferred numa-node, and a myriad of other random crap,
will cause this to happen.

This shouldn't be. Preserve the relative virtual deadline across such
dequeue/enqueue cycles.

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/20240727105030.625119246@xxxxxxxxxxxxx
---
 include/linux/sched.h   |  6 ++++--
 kernel/sched/fair.c     | 23 ++++++++++++++++++-----
 kernel/sched/features.h |  4 ++++
 3 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8a3a389..d25e1cf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -544,8 +544,10 @@ struct sched_entity {
 	u64				min_vruntime;
 
 	struct list_head		group_node;
-	unsigned int			on_rq;
-	unsigned int			sched_delayed;
+	unsigned char			on_rq;
+	unsigned char			sched_delayed;
+	unsigned char			rel_deadline;
+					/* hole */
 
 	u64				exec_start;
 	u64				sum_exec_runtime;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0eb1bbf..fef0e1f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5270,6 +5270,12 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	se->vruntime = vruntime - lag;
 
+	if (sched_feat(PLACE_REL_DEADLINE) && se->rel_deadline) {
+		se->deadline += se->vruntime;
+		se->rel_deadline = 0;
+		return;
+	}
+
 	/*
 	 * When joining the competition; the existing tasks will be,
 	 * on average, halfway through their slice, as such start tasks
@@ -5382,23 +5388,24 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 static bool
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
+	bool sleep = flags & DEQUEUE_SLEEP;
+
 	update_curr(cfs_rq);
 
 	if (flags & DEQUEUE_DELAYED) {
 		SCHED_WARN_ON(!se->sched_delayed);
 	} else {
-		bool sleep = flags & DEQUEUE_SLEEP;
-
+		bool delay = sleep;
 		/*
 		 * DELAY_DEQUEUE relies on spurious wakeups, special task
 		 * states must not suffer spurious wakeups, excempt them.
 		 */
 		if (flags & DEQUEUE_SPECIAL)
-			sleep = false;
+			delay = false;
 
-		SCHED_WARN_ON(sleep && se->sched_delayed);
+		SCHED_WARN_ON(delay && se->sched_delayed);
 
-		if (sched_feat(DELAY_DEQUEUE) && sleep &&
+		if (sched_feat(DELAY_DEQUEUE) && delay &&
 		    !entity_eligible(cfs_rq, se)) {
 			if (cfs_rq->next == se)
 				cfs_rq->next = NULL;
@@ -5429,6 +5436,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	clear_buddies(cfs_rq, se);
 
 	update_entity_lag(cfs_rq, se);
+	if (sched_feat(PLACE_REL_DEADLINE) && !sleep) {
+		se->deadline -= se->vruntime;
+		se->rel_deadline = 1;
+	}
+
 	if (se != cfs_rq->curr)
 		__dequeue_entity(cfs_rq, se);
 	se->on_rq = 0;
@@ -12992,6 +13004,7 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 	if (p->se.sched_delayed) {
 		dequeue_task(rq, p, DEQUEUE_NOCLOCK | DEQUEUE_SLEEP);
 		p->se.sched_delayed = 0;
+		p->se.rel_deadline = 0;
 		if (sched_feat(DELAY_ZERO) && p->se.vlag > 0)
 			p->se.vlag = 0;
 	}
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 7fdeb55..caa4d72 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -10,6 +10,10 @@ SCHED_FEAT(PLACE_LAG, true)
  */
 SCHED_FEAT(PLACE_DEADLINE_INITIAL, true)
 /*
+ * Preserve relative virtual deadline on 'migration'.
+ */
+SCHED_FEAT(PLACE_REL_DEADLINE, true)
+/*
  * Inhibit (wakeup) preemption until the current task has either matched the
  * 0-lag point or until is has exhausted it's slice.
  */