Re: [PATCH v2 12/12] sched: Remove sched_class::balance()

From: Peter Zijlstra

Date: Wed Nov 11 2026 - 08:18:25 EST


On Wed, Nov 11, 2026 at 01:18:42AM -1000, Tejun Heo wrote:
> Hello,
>
> On Sat, Nov 07, 2026 at 12:59:25PM +0100, Peter Zijlstra wrote:
> > static struct task_struct *pick_task_rt(struct rq *rq, struct rq_flags *rf)
> > {
> > - struct task_struct *p;
> > + rq_modified_begin(rq, &rt_sched_class);
> > + balance_rt(rq, rf);
> > + if (rq_modified_above(rq, &rt_sched_class))
> > + return RETRY_TASK;
>
> This exposes an underlying problem on the DL side. rq->next_class is
> raised only by wakeup_preempt(), but dl_server_start(), dl_task_timer()
> and dl_server_timer() enqueue a DL entity and open-code resched_curr()
> without going through it. prev_balance() ran before any class was
> picked, so it didn't matter. Now, pick_task_dl() has already returned
> NULL when balance_rt() drops the lock, and rq_modified_above() is the
> only thing which can notice a DL entity queued in the meantime:
>
> CPU0 RT task blocks, pick_task_dl() returns NULL
> pick_task_rt(), balance_rt() drops the rq lock
> CPU1 wakes a fair task onto CPU0, dl_server_start()
> CPU0 relocks, rq_modified_above() is false
> picks an RT task with the fair server queued

A very nice catch, but I'm not entirely convinced it wasn't a problem
before.

Similar argument could be made for FAIR vs EXT, and picking a FAIR task
while an EXT server is pickable.

> resched_curr() doesn't help as __schedule() clears it on prev after the
> pick. I can trigger this with NO_RT_PUSH_IPI and a delay added in the
> lock drop. With RT_PUSH_IPI, pull_rt_task() doesn't drop the lock.
>
> Maybe the DL sites should raise rq->next_class where they enqueue and
> resched, so that they behave the same as regular wakeups?

Yes, something like that. I think the below captures all enqueues,
irrespective of rescheds. I'll add it as fix at the start of the series.

(although maybe I'll massage this a little more and create a helper,
doing the same thing over and over like this is daft)

Thanks!

---
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -715,8 +715,7 @@ static struct rq *dl_task_offline_migrat
return later_rq;
}

-static void
-enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags);
+static bool enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags);
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags);
static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags);
@@ -1184,7 +1183,8 @@ static enum hrtimer_restart dl_server_ti
dl_se->dl_defer_running = 1;
}

- enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
+ if (enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH))
+ rq->next_class = &dl_sched_class;

if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &dl_se->rq->curr->dl))
resched_curr(rq);
@@ -1520,7 +1520,8 @@ static void update_curr_dl_se(struct rq
replenish_dl_new_period(dl_se, rq);
start_dl_timer(dl_se);
} else {
- enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
+ if (enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH))
+ rq->next_class = &dl_sched_class;
}
} else {
enqueue_task_dl(rq, dl_task_of(dl_se), ENQUEUE_REPLENISH);
@@ -1812,7 +1813,8 @@ void dl_server_start(struct sched_dl_ent

trace_sched_dl_server_start_tp(dl_se, cpu_of(rq), dl_get_type(dl_se, rq));
dl_se->dl_server_active = 1;
- enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
+ if (enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP))
+ rq->next_class = &dl_sched_class;
if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
resched_curr(dl_se->rq);
}
@@ -2379,7 +2381,7 @@ static void __dequeue_dl_entity(struct s
dec_dl_tasks(dl_se, dl_rq);
}

-static void
+static bool
enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
{
WARN_ON_ONCE(on_dl_rq(dl_se));
@@ -2418,7 +2420,7 @@ enqueue_dl_entity(struct sched_dl_entity
if (flags & ENQUEUE_WAKEUP)
task_contending(dl_se, flags);

- return;
+ return false;
}

/*
@@ -2442,7 +2444,7 @@ enqueue_dl_entity(struct sched_dl_entity
* deferred task and still got to wait, don't enqueue.
*/
if (dl_se->dl_throttled && start_dl_timer(dl_se))
- return;
+ return false;

/*
* We're about to enqueue, make sure we're not ->dl_throttled!
@@ -2457,6 +2459,7 @@ enqueue_dl_entity(struct sched_dl_entity
}

__enqueue_dl_entity(dl_se);
+ return true;
}

static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags)
@@ -2534,7 +2537,8 @@ static void enqueue_task_dl(struct rq *r
if (task_on_rq_migrating(p))
flags |= ENQUEUE_MIGRATING;

- enqueue_dl_entity(dl_se, flags);
+ if (enqueue_dl_entity(dl_se, flags))
+ rq->next_class = &dl_sched_class;

if (dl_server(dl_se))
return;