From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 23 May 2024 09:57:43 +0000 (+0200)
Subject: sched/fair: Implement ENQUEUE_DELAYED
X-Git-Tag: v6.12-rc1~120^2~30
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=781773e3b68031bd001c0c18aa72e8470c225ebd;p=thirdparty%2Flinux.git

sched/fair: Implement ENQUEUE_DELAYED

Doing a wakeup on a delayed dequeue task is about as simple as it
sounds -- remove the delayed mark and enjoy the fact it was actually
still on the runqueue.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Tested-by: Valentin Schneider <vschneid@redhat.com>
Link: https://lkml.kernel.org/r/20240727105029.888107381@infradead.org
---

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a4f1f79ac90c1..25b14dffeb37b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5289,6 +5289,9 @@ static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq);
 
 static inline bool cfs_bandwidth_used(void);
 
+static void
+requeue_delayed_entity(struct sched_entity *se);
+
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -5922,8 +5925,10 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 
-		if (se->on_rq)
+		if (se->on_rq) {
+			SCHED_WARN_ON(se->sched_delayed);
 			break;
+		}
 		enqueue_entity(qcfs_rq, se, ENQUEUE_WAKEUP);
 
 		if (cfs_rq_is_idle(group_cfs_rq(se)))
@@ -6773,6 +6778,22 @@ static int sched_idle_cpu(int cpu)
 }
 #endif
 
+static void
+requeue_delayed_entity(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+	/*
+	 * se->sched_delayed should imply: se->on_rq == 1.
+	 * Because a delayed entity is one that is still on
+	 * the runqueue competing until elegibility.
+	 */
+	SCHED_WARN_ON(!se->sched_delayed);
+	SCHED_WARN_ON(!se->on_rq);
+
+	se->sched_delayed = 0;
+}
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -6787,6 +6808,11 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	int task_new = !(flags & ENQUEUE_WAKEUP);
 	int rq_h_nr_running = rq->cfs.h_nr_running;
 
+	if (flags & ENQUEUE_DELAYED) {
+		requeue_delayed_entity(se);
+		return;
+	}
+
 	/*
 	 * The code below (indirectly) updates schedutil which looks at
 	 * the cfs_rq utilization to select a frequency.
@@ -6804,8 +6830,11 @@ 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)
+		if (se->on_rq) {
+			if (se->sched_delayed)
+				requeue_delayed_entity(se);
 			break;
+		}
 		cfs_rq = cfs_rq_of(se);
 		enqueue_entity(cfs_rq, se, flags);