sched/deadline: Initialize dl_servers after SMP

dl-servers are currently initialized too early at boot when CPUs are not
fully up (only boot CPU is). This results in miscalculation of per
runqueue DEADLINE variables like extra_bw (which needs a stable CPU
count).

Move initialization of dl-servers later on after SMP has been
initialized and CPUs are all online, so that CPU count is stable and
DEADLINE variables can be computed correctly.

Fixes: d741f29 ("sched/fair: Fair server interface")
Reported-by: Marcel Ziswiler <marcel.ziswiler@codethink.co.uk>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Tested-by: Marcel Ziswiler <marcel.ziswiler@codethink.co.uk> # nuc & rock5b
Link: https://lore.kernel.org/r/20250627115118.438797-2-juri.lelli@redhat.com

Author: jlelli

kernel/sched/core.c

@@ -8371,6 +8371,8 @@ void __init sched_init_smp(void)
 	init_sched_rt_class();
 	init_sched_dl_class();
 
+	sched_init_dl_servers();
+
 	sched_smp_initialized = true;
 }
 

kernel/sched/deadline.c

@@ -761,6 +761,8 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
+	update_rq_clock(rq);
+
 	WARN_ON(is_dl_boosted(dl_se));
 	WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
 
@@ -1585,23 +1587,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
 {
 	struct rq *rq = dl_se->rq;
 
-	/*
-	 * XXX: the apply do not work fine at the init phase for the
-	 * fair server because things are not yet set. We need to improve
-	 * this before getting generic.
-	 */
-	if (!dl_server(dl_se)) {
-		u64 runtime =  50 * NSEC_PER_MSEC;
-		u64 period = 1000 * NSEC_PER_MSEC;
-
-		dl_server_apply_params(dl_se, runtime, period, 1);
-
-		dl_se->dl_server = 1;
-		dl_se->dl_defer = 1;
-		setup_new_dl_entity(dl_se);
-	}
-
-	if (!dl_se->dl_runtime || dl_se->dl_server_active)
+	if (!dl_server(dl_se) || dl_se->dl_server_active)
 		return;
 
 	dl_se->dl_server_active = 1;
@@ -1612,7 +1598,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
 
 void dl_server_stop(struct sched_dl_entity *dl_se)
 {
-	if (!dl_se->dl_runtime)
+	if (!dl_server(dl_se) || !dl_server_active(dl_se))
 		return;
 
 	dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
@@ -1645,6 +1631,32 @@ void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 	dl_se->server_pick_task = pick_task;
 }
 
+void sched_init_dl_servers(void)
+{
+	int cpu;
+	struct rq *rq;
+	struct sched_dl_entity *dl_se;
+
+	for_each_online_cpu(cpu) {
+		u64 runtime =  50 * NSEC_PER_MSEC;
+		u64 period = 1000 * NSEC_PER_MSEC;
+
+		rq = cpu_rq(cpu);
+
+		guard(rq_lock_irq)(rq);
+
+		dl_se = &rq->fair_server;
+
+		WARN_ON(dl_server(dl_se));
+
+		dl_server_apply_params(dl_se, runtime, period, 1);
+
+		dl_se->dl_server = 1;
+		dl_se->dl_defer = 1;
+		setup_new_dl_entity(dl_se);
+	}
+}
+
 void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq)
 {
 	u64 new_bw = dl_se->dl_bw;

kernel/sched/sched.h

@@ -385,6 +385,7 @@ 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);
 
 extern void dl_server_update_idle_time(struct rq *rq,
 		    struct task_struct *p);