Merge tag 'sched-urgent-2025-09-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:
 "Fix two dl_server regressions: a race that can end up leaving the
  dl_server stuck, and a dl_server throttling bug causing lag to fair
  tasks"

* tag 'sched-urgent-2025-09-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/deadline: Fix dl_server behaviour
  sched/deadline: Fix dl_server getting stuck

Author: torvalds

include/linux/sched.h

@@ -706,7 +706,6 @@ struct sched_dl_entity {
 	unsigned int			dl_defer	  : 1;
 	unsigned int			dl_defer_armed	  : 1;
 	unsigned int			dl_defer_running  : 1;
-	unsigned int			dl_server_idle    : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -733,7 +732,6 @@ struct sched_dl_entity {
 	 * runnable task.
 	 */
 	struct rq			*rq;
-	dl_server_has_tasks_f		server_has_tasks;
 	dl_server_pick_f		server_pick_task;
 
 #ifdef CONFIG_RT_MUTEXES

kernel/sched/deadline.c

@@ -875,7 +875,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 	 */
 	if (dl_se->dl_defer && !dl_se->dl_defer_running &&
 	    dl_time_before(rq_clock(dl_se->rq), dl_se->deadline - dl_se->runtime)) {
-		if (!is_dl_boosted(dl_se) && dl_se->server_has_tasks(dl_se)) {
+		if (!is_dl_boosted(dl_se)) {
 
 			/*
 			 * Set dl_se->dl_defer_armed and dl_throttled variables to
@@ -1152,8 +1152,6 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
 /* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */
 static const u64 dl_server_min_res = 1 * NSEC_PER_MSEC;
 
-static bool dl_server_stopped(struct sched_dl_entity *dl_se);
-
 static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_dl_entity *dl_se)
 {
 	struct rq *rq = rq_of_dl_se(dl_se);
@@ -1171,12 +1169,6 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
 		if (!dl_se->dl_runtime)
 			return HRTIMER_NORESTART;
 
-		if (!dl_se->server_has_tasks(dl_se)) {
-			replenish_dl_entity(dl_se);
-			dl_server_stopped(dl_se);
-			return HRTIMER_NORESTART;
-		}
-
 		if (dl_se->dl_defer_armed) {
 			/*
 			 * First check if the server could consume runtime in background.
@@ -1579,10 +1571,8 @@ void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
 void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
 {
 	/* 0 runtime = fair server disabled */
-	if (dl_se->dl_runtime) {
-		dl_se->dl_server_idle = 0;
+	if (dl_se->dl_runtime)
 		update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
-	}
 }
 
 void dl_server_start(struct sched_dl_entity *dl_se)
@@ -1610,26 +1600,10 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
 	dl_se->dl_server_active = 0;
 }
 
-static bool dl_server_stopped(struct sched_dl_entity *dl_se)
-{
-	if (!dl_se->dl_server_active)
-		return true;
-
-	if (dl_se->dl_server_idle) {
-		dl_server_stop(dl_se);
-		return true;
-	}
-
-	dl_se->dl_server_idle = 1;
-	return false;
-}
-
 void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
-		    dl_server_has_tasks_f has_tasks,
 		    dl_server_pick_f pick_task)
 {
 	dl_se->rq = rq;
-	dl_se->server_has_tasks = has_tasks;
 	dl_se->server_pick_task = pick_task;
 }
 
@@ -2394,10 +2368,7 @@ 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) {
-			if (!dl_server_stopped(dl_se)) {
-				dl_se->dl_yielded = 1;
-				update_curr_dl_se(rq, dl_se, 0);
-			}
+			dl_server_stop(dl_se);
 			goto again;
 		}
 		rq->dl_server = dl_se;

kernel/sched/fair.c

@@ -8859,11 +8859,6 @@ static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_stru
 	return pick_next_task_fair(rq, prev, NULL);
 }
 
-static bool fair_server_has_tasks(struct sched_dl_entity *dl_se)
-{
-	return !!dl_se->rq->cfs.nr_queued;
-}
-
 static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se)
 {
 	return pick_task_fair(dl_se->rq);
@@ -8875,7 +8870,7 @@ void fair_server_init(struct rq *rq)
 
 	init_dl_entity(dl_se);
 
-	dl_server_init(dl_se, rq, fair_server_has_tasks, fair_server_pick_task);
+	dl_server_init(dl_se, rq, fair_server_pick_task);
 }
 
 /*

kernel/sched/sched.h

@@ -365,25 +365,50 @@ extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s6
  *
  *   dl_se::rq -- runqueue we belong to.
  *
- *   dl_se::server_has_tasks() -- used on bandwidth enforcement; we 'stop' the
- *                                server when it runs out of tasks to run.
- *
  *   dl_se::server_pick() -- nested pick_next_task(); we yield the period if this
  *                           returns NULL.
  *
  *   dl_server_update() -- called from update_curr_common(), propagates runtime
  *                         to the server.
  *
- *   dl_server_start()
- *   dl_server_stop()  -- start/stop the server when it has (no) tasks.
+ *   dl_server_start() -- start the server when it has tasks; it will stop
+ *			  automatically when there are no more tasks, per
+ *			  dl_se::server_pick() returning NULL.
+ *
+ *   dl_server_stop() -- (force) stop the server; use when updating
+ *                       parameters.
  *
  *   dl_server_init() -- initializes the server.
+ *
+ * When started the dl_server will (per dl_defer) schedule a timer for its
+ * zero-laxity point -- that is, unlike regular EDF tasks which run ASAP, a
+ * server will run at the very end of its period.
+ *
+ * This is done such that any runtime from the target class can be accounted
+ * against the server -- through dl_server_update() above -- such that when it
+ * becomes time to run, it might already be out of runtime and get deferred
+ * until the next period. In this case dl_server_timer() will alternate
+ * between defer and replenish but never actually enqueue the server.
+ *
+ * Only when the target class does not manage to exhaust the server's runtime
+ * (there's actualy starvation in the given period), will the dl_server get on
+ * the runqueue. Once queued it will pick tasks from the target class and run
+ * them until either its runtime is exhaused, at which point its back to
+ * dl_server_timer, or until there are no more tasks to run, at which point
+ * the dl_server stops itself.
+ *
+ * By stopping at this point the dl_server retains bandwidth, which, if a new
+ * task wakes up imminently (starting the server again), can be used --
+ * subject to CBS wakeup rules -- without having to wait for the next period.
+ *
+ * Additionally, because of the dl_defer behaviour the start/stop behaviour is
+ * naturally thottled to once per period, avoiding high context switch
+ * workloads from spamming the hrtimer program/cancel paths.
  */
 extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec);
 extern void dl_server_start(struct sched_dl_entity *dl_se);
 extern void dl_server_stop(struct sched_dl_entity *dl_se);
 extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
-		    dl_server_has_tasks_f has_tasks,
 		    dl_server_pick_f pick_task);
 extern void sched_init_dl_servers(void);