Merge tag 'sched_urgent_for_v6.13_rc3-p2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Borislav Petkov:

 - Prevent incorrect dequeueing of the deadline dlserver helper task and
   fix its time accounting

 - Properly track the CFS runqueue runnable stats

 - Check the total number of all queued tasks in a sched fair's runqueue
   hierarchy before deciding to stop the tick

 - Fix the scheduling of the task that got woken last (NEXT_BUDDY) by
   preventing those from being delayed

* tag 'sched_urgent_for_v6.13_rc3-p2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/dlserver: Fix dlserver time accounting
  sched/dlserver: Fix dlserver double enqueue
  sched/eevdf: More PELT vs DELAYED_DEQUEUE
  sched/fair: Fix sched_can_stop_tick() for fair tasks
  sched/fair: Fix NEXT_BUDDY

Author: torvalds

include/linux/sched.h

@@ -656,6 +656,12 @@ struct sched_dl_entity {
 	 * @dl_defer_armed tells if the deferrable server is waiting
 	 * for the replenishment timer to activate it.
 	 *
+	 * @dl_server_active tells if the dlserver is active(started).
+	 * dlserver is started on first cfs enqueue on an idle runqueue
+	 * and is stopped when a dequeue results in 0 cfs tasks on the
+	 * runqueue. In other words, dlserver is active only when cpu's
+	 * runqueue has atleast one cfs task.
+	 *
 	 * @dl_defer_running tells if the deferrable server is actually
 	 * running, skipping the defer phase.
 	 */
@@ -664,6 +670,7 @@ struct sched_dl_entity {
 	unsigned int			dl_non_contending : 1;
 	unsigned int			dl_overrun	  : 1;
 	unsigned int			dl_server         : 1;
+	unsigned int			dl_server_active  : 1;
 	unsigned int			dl_defer	  : 1;
 	unsigned int			dl_defer_armed	  : 1;
 	unsigned int			dl_defer_running  : 1;

kernel/sched/core.c

@@ -1341,7 +1341,7 @@ 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;
 
 	/*

kernel/sched/deadline.c

@@ -1647,6 +1647,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
 	if (!dl_se->dl_runtime)
 		return;
 
+	dl_se->dl_server_active = 1;
 	enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
 	if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
 		resched_curr(dl_se->rq);
@@ -1661,6 +1662,7 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
 	hrtimer_try_to_cancel(&dl_se->dl_timer);
 	dl_se->dl_defer_armed = 0;
 	dl_se->dl_throttled = 0;
+	dl_se->dl_server_active = 0;
 }
 
 void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
@@ -2421,8 +2423,10 @@ static struct task_struct *__pick_task_dl(struct rq *rq)
 	if (dl_server(dl_se)) {
 		p = dl_se->server_pick_task(dl_se);
 		if (!p) {
-			dl_se->dl_yielded = 1;
-			update_curr_dl_se(rq, dl_se, 0);
+			if (dl_server_active(dl_se)) {
+				dl_se->dl_yielded = 1;
+				update_curr_dl_se(rq, dl_se, 0);
+			}
 			goto again;
 		}
 		rq->dl_server = dl_se;

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",

kernel/sched/fair.c

@@ -1159,8 +1159,6 @@ static inline void update_curr_task(struct task_struct *p, s64 delta_exec)
 	trace_sched_stat_runtime(p, delta_exec);
 	account_group_exec_runtime(p, delta_exec);
 	cgroup_account_cputime(p, delta_exec);
-	if (p->dl_server)
-		dl_server_update(p->dl_server, delta_exec);
 }
 
 static inline bool did_preempt_short(struct cfs_rq *cfs_rq, struct sched_entity *curr)
@@ -1237,11 +1235,16 @@ static void update_curr(struct cfs_rq *cfs_rq)
 		update_curr_task(p, delta_exec);
 
 		/*
-		 * Any fair task that runs outside of fair_server should
-		 * account against fair_server such that it can account for
-		 * this time and possibly avoid running this period.
+		 * If the fair_server is active, we need to account for the
+		 * fair_server time whether or not the task is running on
+		 * behalf of fair_server or not:
+		 *  - If the task is running on behalf of fair_server, we need
+		 *    to limit its time based on the assigned runtime.
+		 *  - Fair task that runs outside of fair_server should account
+		 *    against fair_server such that it can account for this time
+		 *    and possibly avoid running this period.
 		 */
-		if (p->dl_server != &rq->fair_server)
+		if (dl_server_active(&rq->fair_server))
 			dl_server_update(&rq->fair_server, delta_exec);
 	}
 
@@ -5471,9 +5474,33 @@ 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;
 }
@@ -5484,6 +5511,7 @@ 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);
@@ -5500,10 +5528,8 @@ 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;
 		}
 	}
@@ -5526,8 +5552,6 @@ 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;
@@ -5917,7 +5941,7 @@ 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);
@@ -5950,6 +5974,7 @@ 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;
@@ -5973,6 +5998,7 @@ 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: */
@@ -5995,6 +6021,7 @@ 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*/
@@ -6020,7 +6047,7 @@ 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)];
@@ -6056,6 +6083,7 @@ 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);
 
@@ -6073,6 +6101,7 @@ 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))
@@ -6090,6 +6119,7 @@ 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))
@@ -6943,7 +6973,7 @@ requeue_delayed_entity(struct sched_entity *se)
 	}
 
 	update_load_avg(cfs_rq, se, 0);
-	se->sched_delayed = 0;
+	clear_delayed(se);
 }
 
 /*
@@ -6957,6 +6987,7 @@ 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;
@@ -6983,6 +7014,9 @@ 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)
@@ -7005,6 +7039,7 @@ 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;
@@ -7028,6 +7063,7 @@ 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;
@@ -7090,13 +7126,16 @@ 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;
 
 	if (entity_is_task(se)) {
 		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);
@@ -7114,6 +7153,7 @@ 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;
@@ -7152,6 +7192,7 @@ 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;
@@ -8780,7 +8821,7 @@ 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);
 	}
 

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);

kernel/sched/sched.h

@@ -398,6 +398,11 @@ extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq
 extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
 		    u64 runtime, u64 period, bool init);
 
+static inline bool dl_server_active(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_server_active;
+}
+
 #ifdef CONFIG_CGROUP_SCHED
 
 extern struct list_head task_groups;
@@ -649,6 +654,7 @@ 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 +904,11 @@ 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)