Merge branch 'sched/urgent'

Sync with urgent bits as a base for further work.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>

5 files changed, 57 insertions, 14 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5fbec67d48b2..2167d38f4d65 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1343,7 +1343,7 @@ bool sched_can_stop_tick(struct rq *rq)
 	if (scx_enabled() && !scx_can_stop_tick(rq))
 		return false;
 
-	if (rq->cfs.nr_running > 1)
+	if (rq->cfs.h_nr_running > 1)
 		return false;
 
 	/*
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index a48b2a701ec2..a1be00a988bf 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -845,6 +845,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread));
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running);
+	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_delayed", cfs_rq->h_nr_delayed);
 	SEQ_printf(m, "  .%-30s: %d\n", "idle_nr_running",
 			cfs_rq->idle_nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "idle_h_nr_running",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d5127d9beaea..1f73cb408b29 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5463,9 +5463,33 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 
-static inline void finish_delayed_dequeue_entity(struct sched_entity *se)
+static void set_delayed(struct sched_entity *se)
+{
+	se->sched_delayed = 1;
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+		cfs_rq->h_nr_delayed++;
+		if (cfs_rq_throttled(cfs_rq))
+			break;
+	}
+}
+
+static void clear_delayed(struct sched_entity *se)
 {
 	se->sched_delayed = 0;
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+		cfs_rq->h_nr_delayed--;
+		if (cfs_rq_throttled(cfs_rq))
+			break;
+	}
+}
+
+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;
 }
@@ -5476,6 +5500,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	bool sleep = flags & DEQUEUE_SLEEP;
 
 	update_curr(cfs_rq);
+	clear_buddies(cfs_rq, se);
 
 	if (flags & DEQUEUE_DELAYED) {
 		SCHED_WARN_ON(!se->sched_delayed);
@@ -5492,10 +5517,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 		if (sched_feat(DELAY_DEQUEUE) && delay &&
 		    !entity_eligible(cfs_rq, se)) {
-			if (cfs_rq->next == se)
-				cfs_rq->next = NULL;
 			update_load_avg(cfs_rq, se, 0);
-			se->sched_delayed = 1;
+			set_delayed(se);
 			return false;
 		}
 	}
@@ -5518,8 +5541,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	update_stats_dequeue_fair(cfs_rq, se, flags);
 
-	clear_buddies(cfs_rq, se);
-
 	update_entity_lag(cfs_rq, se);
 	if (sched_feat(PLACE_REL_DEADLINE) && !sleep) {
 		se->deadline -= se->vruntime;
@@ -5909,7 +5930,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
-	long task_delta, idle_task_delta, dequeue = 1;
+	long task_delta, idle_task_delta, delayed_delta, dequeue = 1;
 	long rq_h_nr_running = rq->cfs.h_nr_running;
 
 	raw_spin_lock(&cfs_b->lock);
@@ -5942,6 +5963,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 	task_delta = cfs_rq->h_nr_running;
 	idle_task_delta = cfs_rq->idle_h_nr_running;
+	delayed_delta = cfs_rq->h_nr_delayed;
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 		int flags;
@@ -5965,6 +5987,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
+		qcfs_rq->h_nr_delayed -= delayed_delta;
 
 		if (qcfs_rq->load.weight) {
 			/* Avoid re-evaluating load for this entity: */
@@ -5987,6 +6010,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
+		qcfs_rq->h_nr_delayed -= delayed_delta;
 	}
 
 	/* At this point se is NULL and we are at root level*/
@@ -6012,7 +6036,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
-	long task_delta, idle_task_delta;
+	long task_delta, idle_task_delta, delayed_delta;
 	long rq_h_nr_running = rq->cfs.h_nr_running;
 
 	se = cfs_rq->tg->se[cpu_of(rq)];
@@ -6048,6 +6072,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 
 	task_delta = cfs_rq->h_nr_running;
 	idle_task_delta = cfs_rq->idle_h_nr_running;
+	delayed_delta = cfs_rq->h_nr_delayed;
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 
@@ -6065,6 +6090,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 
 		qcfs_rq->h_nr_running += task_delta;
 		qcfs_rq->idle_h_nr_running += idle_task_delta;
+		qcfs_rq->h_nr_delayed += delayed_delta;
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(qcfs_rq))
@@ -6082,6 +6108,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 
 		qcfs_rq->h_nr_running += task_delta;
 		qcfs_rq->idle_h_nr_running += idle_task_delta;
+		qcfs_rq->h_nr_delayed += delayed_delta;
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(qcfs_rq))
@@ -6930,7 +6957,7 @@ requeue_delayed_entity(struct sched_entity *se)
 	}
 
 	update_load_avg(cfs_rq, se, 0);
-	se->sched_delayed = 0;
+	clear_delayed(se);
 }
 
 /*
@@ -6944,6 +6971,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 	int idle_h_nr_running = task_has_idle_policy(p);
+	int h_nr_delayed = 0;
 	int task_new = !(flags & ENQUEUE_WAKEUP);
 	int rq_h_nr_running = rq->cfs.h_nr_running;
 	u64 slice = 0;
@@ -6970,6 +6998,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (p->in_iowait)
 		cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
 
+	if (task_new)
+		h_nr_delayed = !!se->sched_delayed;
+
 	for_each_sched_entity(se) {
 		if (se->on_rq) {
 			if (se->sched_delayed)
@@ -6992,6 +7023,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
+		cfs_rq->h_nr_delayed += h_nr_delayed;
 
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = 1;
@@ -7015,6 +7047,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
+		cfs_rq->h_nr_delayed += h_nr_delayed;
 
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = 1;
@@ -7077,6 +7110,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 	struct task_struct *p = NULL;
 	int idle_h_nr_running = 0;
 	int h_nr_running = 0;
+	int h_nr_delayed = 0;
 	struct cfs_rq *cfs_rq;
 	u64 slice = 0;
 
@@ -7084,6 +7118,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		p = task_of(se);
 		h_nr_running = 1;
 		idle_h_nr_running = task_has_idle_policy(p);
+		if (!task_sleep && !task_delayed)
+			h_nr_delayed = !!se->sched_delayed;
 	} else {
 		cfs_rq = group_cfs_rq(se);
 		slice = cfs_rq_min_slice(cfs_rq);
@@ -7101,6 +7137,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 
 		cfs_rq->h_nr_running -= h_nr_running;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+		cfs_rq->h_nr_delayed -= h_nr_delayed;
 
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = h_nr_running;
@@ -7139,6 +7176,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 
 		cfs_rq->h_nr_running -= h_nr_running;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+		cfs_rq->h_nr_delayed -= h_nr_delayed;
 
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = h_nr_running;
@@ -8767,7 +8805,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	if (unlikely(throttled_hierarchy(cfs_rq_of(pse))))
 		return;
 
-	if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) {
+	if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK) && !pse->sched_delayed) {
 		set_next_buddy(pse);
 	}
 
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index fc07382361a8..fee75cc2c47b 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -321,7 +321,7 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq)
 {
 	if (___update_load_sum(now, &cfs_rq->avg,
 				scale_load_down(cfs_rq->load.weight),
-				cfs_rq->h_nr_running,
+				cfs_rq->h_nr_running - cfs_rq->h_nr_delayed,
 				cfs_rq->curr != NULL)) {
 
 		___update_load_avg(&cfs_rq->avg, 1);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 5eb2d5b9722f..99d19c605e4f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -649,6 +649,7 @@ struct cfs_rq {
 	unsigned int		h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */
 	unsigned int		idle_nr_running;   /* SCHED_IDLE */
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
+	unsigned int		h_nr_delayed;
 
 	s64			avg_vruntime;
 	u64			avg_load;
@@ -898,8 +899,11 @@ struct dl_rq {
 
 static inline void se_update_runnable(struct sched_entity *se)
 {
-	if (!entity_is_task(se))
-		se->runnable_weight = se->my_q->h_nr_running;
+	if (!entity_is_task(se)) {
+		struct cfs_rq *cfs_rq = se->my_q;
+
+		se->runnable_weight = cfs_rq->h_nr_running - cfs_rq->h_nr_delayed;
+	}
 }
 
 static inline long se_runnable(struct sched_entity *se)