Re: [PATCH 03/12] sched: Fold sched_class::switch{ing,ed}_{to,from}() into the change pattern

[Peter Zijlstra <peterz@infradead.org>]

On Thu, Oct 09, 2025 at 03:54:08PM +0200, Peter Zijlstra wrote:
> On Thu, Oct 09, 2025 at 03:30:02PM +0200, Dietmar Eggemann wrote:
> > On 06.10.25 12:44, Peter Zijlstra wrote:
> > > Add {DE,EN}QUEUE_CLASS and fold the sched_class::switch* methods into
> > > the change pattern. This completes and makes the pattern more
> > > symmetric.
> > > 
> > > This changes the order of callbacks slightly:
> > > 
> > > 				|
> > > 				|  switching_from()
> > >   dequeue_task();		|  dequeue_task()
> > >   put_prev_task();		|  put_prev_task()
> > > 				|  switched_from()
> > > 				|
> > >   ... change task ...		|  ... change task ...
> > > 				|
> > >   switching_to();		|  switching_to()
> > >   enqueue_task();		|  enqueue_task()
> > >   set_next_task();		|  set_next_task()
> > >   prev_class->switched_from()	|
> > >   switched_to()			|  switched_to()
> > > 				|
> > > 
> > > Notably, it moves the switched_from() callback right after the
> > > dequeue/put. Existing implementations don't appear to be affected by
> > > this change in location -- specifically the task isn't enqueued on the
> > > class in question in either location.
> > > 
> > > Make (CLASS)^(SAVE|MOVE), because there is nothing to save-restore
> > > when changing scheduling classes.
> > 
> > This one causes a DL bw related warning when I run a simple 1 DL task
> > rt-app workload:
> 
> > Not sure yet how this is related to switched_from_dl() being now called earlier?
> 
> Ooh, I might see a problem. task_non_contending() uses dl_task(), which
> uses p->prio. The move above means it is now called using the 'old'
> prio, whereas it used to run with the 'new' prio.
> 
> Let me see if I can figure out something for this.

Does this help? /me goes find rt-app.

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 615411a0a881..fe2272c812b2 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -405,7 +405,7 @@ static void __dl_clear_params(struct sched_dl_entity *dl_se);
  * up, and checks if the task is still in the "ACTIVE non contending"
  * state or not (in the second case, it updates running_bw).
  */
-static void task_non_contending(struct sched_dl_entity *dl_se)
+static void task_non_contending(struct sched_dl_entity *dl_se, bool dl_task)
 {
 	struct hrtimer *timer = &dl_se->inactive_timer;
 	struct rq *rq = rq_of_dl_se(dl_se);
@@ -444,10 +444,10 @@ static void task_non_contending(struct sched_dl_entity *dl_se)
 		} else {
 			struct task_struct *p = dl_task_of(dl_se);
 
-			if (dl_task(p))
+			if (dl_task)
 				sub_running_bw(dl_se, dl_rq);
 
-			if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
+			if (!dl_task || READ_ONCE(p->__state) == TASK_DEAD) {
 				struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
 
 				if (READ_ONCE(p->__state) == TASK_DEAD)
@@ -2045,7 +2045,7 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 	 * or "inactive")
 	 */
 	if (flags & DEQUEUE_SLEEP)
-		task_non_contending(dl_se);
+		task_non_contending(dl_se, true);
 }
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -2970,7 +2970,7 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	 * will reset the task parameters.
 	 */
 	if (task_on_rq_queued(p) && p->dl.dl_runtime)
-		task_non_contending(&p->dl);
+		task_non_contending(&p->dl, false);
 
 	/*
 	 * In case a task is setscheduled out from SCHED_DEADLINE we need to