Commit c8a85394 authored by Joel Fernandes (Google)'s avatar Joel Fernandes (Google) Committed by Peter Zijlstra
Browse files

sched/core: Fix picking of tasks for core scheduling with DL server



* Use simple CFS pick_task for DL pick_task

  DL server's pick_task calls CFS's pick_next_task_fair(), this is wrong
  because core scheduling's pick_task only calls CFS's pick_task() for
  evaluation / checking of the CFS task (comparing across CPUs), not for
  actually affirmatively picking the next task. This causes RB tree
  corruption issues in CFS that were found by syzbot.

* Make pick_task_fair clear DL server

  A DL task pick might set ->dl_server, but it is possible the task will
  never run (say the other HT has a stop task). If the CFS task is picked
  in the future directly (say without DL server), ->dl_server will be
  set. So clear it in pick_task_fair().

This fixes the KASAN issue reported by syzbot in set_next_entity().

(DL refactoring suggestions by Vineeth Pillai).

Reported-by: default avatarSuleiman Souhlal <suleiman@google.com>
Signed-off-by: default avatar"Joel Fernandes (Google)" <joel@joelfernandes.org>
Signed-off-by: default avatarDaniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: default avatarVineeth Pillai <vineeth@bitbyteword.org>
Tested-by: default avatarJuri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/b10489ab1f03d23e08e6097acea47442e7d6466f.1716811044.git.bristot@kernel.org
parent 4b26cfdd
Loading
Loading
Loading
Loading
+2 −1
Original line number Diff line number Diff line
@@ -686,7 +686,8 @@ struct sched_dl_entity {
	 */
	struct rq			*rq;
	dl_server_has_tasks_f		server_has_tasks;
	dl_server_pick_f		server_pick;
	dl_server_pick_f		server_pick_next;
	dl_server_pick_f		server_pick_task;

#ifdef CONFIG_RT_MUTEXES
	/*
+22 −5
Original line number Diff line number Diff line
@@ -1664,11 +1664,13 @@ void dl_server_stop(struct sched_dl_entity *dl_se)

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)
		    dl_server_pick_f pick_next,
		    dl_server_pick_f pick_task)
{
	dl_se->rq = rq;
	dl_se->server_has_tasks = has_tasks;
	dl_se->server_pick = pick;
	dl_se->server_pick_next = pick_next;
	dl_se->server_pick_task = pick_task;
}

void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq)
@@ -2399,7 +2401,12 @@ static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
	return __node_2_dle(left);
}

static struct task_struct *pick_task_dl(struct rq *rq)
/*
 * __pick_next_task_dl - Helper to pick the next -deadline task to run.
 * @rq: The runqueue to pick the next task from.
 * @peek: If true, just peek at the next task. Only relevant for dlserver.
 */
static struct task_struct *__pick_next_task_dl(struct rq *rq, bool peek)
{
	struct sched_dl_entity *dl_se;
	struct dl_rq *dl_rq = &rq->dl;
@@ -2413,7 +2420,10 @@ static struct task_struct *pick_task_dl(struct rq *rq)
	WARN_ON_ONCE(!dl_se);

	if (dl_server(dl_se)) {
		p = dl_se->server_pick(dl_se);
		if (IS_ENABLED(CONFIG_SMP) && peek)
			p = dl_se->server_pick_task(dl_se);
		else
			p = dl_se->server_pick_next(dl_se);
		if (!p) {
			WARN_ON_ONCE(1);
			dl_se->dl_yielded = 1;
@@ -2428,11 +2438,18 @@ static struct task_struct *pick_task_dl(struct rq *rq)
	return p;
}

#ifdef CONFIG_SMP
static struct task_struct *pick_task_dl(struct rq *rq)
{
	return __pick_next_task_dl(rq, true);
}
#endif

static struct task_struct *pick_next_task_dl(struct rq *rq)
{
	struct task_struct *p;

	p = pick_task_dl(rq);
	p = __pick_next_task_dl(rq, false);
	if (!p)
		return p;

+21 −2
Original line number Diff line number Diff line
@@ -8479,6 +8479,14 @@ static struct task_struct *pick_task_fair(struct rq *rq)
		cfs_rq = group_cfs_rq(se);
	} while (cfs_rq);

	/*
	 * This can be called from directly from CFS's ->pick_task() or indirectly
	 * from DL's ->pick_task when fair server is enabled. In the indirect case,
	 * DL will set ->dl_server just after this function is called, so its Ok to
	 * clear. In the direct case, we are picking directly so we must clear it.
	 */
	task_of(se)->dl_server = NULL;

	return task_of(se);
}
#endif
@@ -8638,7 +8646,16 @@ static bool fair_server_has_tasks(struct sched_dl_entity *dl_se)
	return !!dl_se->rq->cfs.nr_running;
}

static struct task_struct *fair_server_pick(struct sched_dl_entity *dl_se)
static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se)
{
#ifdef CONFIG_SMP
	return pick_task_fair(dl_se->rq);
#else
	return NULL;
#endif
}

static struct task_struct *fair_server_pick_next(struct sched_dl_entity *dl_se)
{
	return pick_next_task_fair(dl_se->rq, NULL, NULL);
}
@@ -8649,7 +8666,9 @@ 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);
	dl_server_init(dl_se, rq, fair_server_has_tasks, fair_server_pick_next,
		       fair_server_pick_task);

}

/*
+2 −1
Original line number Diff line number Diff line
@@ -361,7 +361,8 @@ 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);
		    dl_server_pick_f pick_next,
		    dl_server_pick_f pick_task);

extern void dl_server_update_idle_time(struct rq *rq,
		    struct task_struct *p);