sched: Fix pick_next_task() vs 'change' pattern race
Commit 67692435c411 ("sched: Rework pick_next_task() slow-path")
inadvertly introduced a race because it changed a previously
unexplored dependency between dropping the rq->lock and
sched_class::put_prev_task().
The comments about dropping rq->lock, in for example
newidle_balance(), only mentions the task being current and ->on_cpu
being set. But when we look at the 'change' pattern (in for example
sched_setnuma()):
queued = task_on_rq_queued(p); /* p->on_rq == TASK_ON_RQ_QUEUED */
running = task_current(rq, p); /* rq->curr == p */
if (queued)
dequeue_task(...);
if (running)
put_prev_task(...);
/* change task properties */
if (queued)
enqueue_task(...);
if (running)
set_next_task(...);
It becomes obvious that if we do this after put_prev_task() has
already been called on @p, things go sideways. This is exactly what
the commit in question allows to happen when it does:
prev->sched_class->put_prev_task(rq, prev, rf);
if (!rq->nr_running)
newidle_balance(rq, rf);
The newidle_balance() call will drop rq->lock after we've called
put_prev_task() and that allows the above 'change' pattern to
interleave and mess up the state.
Furthermore, it turns out we lost the RT-pull when we put the last DL
task.
Fix both problems by extracting the balancing from put_prev_task() and
doing a multi-class balance() pass before put_prev_task().
Fixes: 67692435c411 ("sched: Rework pick_next_task() slow-path")
Reported-by: Quentin Perret <qperret@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Quentin Perret <qperret@google.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index ebaa4e6..9b8adc0 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1469,6 +1469,22 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
resched_curr(rq);
}
+static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+{
+ if (!on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
+ /*
+ * This is OK, because current is on_cpu, which avoids it being
+ * picked for load-balance and preemption/IRQs are still
+ * disabled avoiding further scheduler activity on it and we've
+ * not yet started the picking loop.
+ */
+ rq_unpin_lock(rq, rf);
+ pull_rt_task(rq);
+ rq_repin_lock(rq, rf);
+ }
+
+ return sched_stop_runnable(rq) || sched_dl_runnable(rq) || sched_rt_runnable(rq);
+}
#endif /* CONFIG_SMP */
/*
@@ -1552,21 +1568,18 @@ static struct task_struct *
pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *p;
- struct rt_rq *rt_rq = &rq->rt;
WARN_ON_ONCE(prev || rf);
- if (!rt_rq->rt_queued)
+ if (!sched_rt_runnable(rq))
return NULL;
p = _pick_next_task_rt(rq);
-
set_next_task_rt(rq, p);
-
return p;
}
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
{
update_curr_rt(rq);
@@ -1578,18 +1591,6 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_fla
*/
if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
-
- if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
- /*
- * This is OK, because current is on_cpu, which avoids it being
- * picked for load-balance and preemption/IRQs are still
- * disabled avoiding further scheduler activity on it and we've
- * not yet started the picking loop.
- */
- rq_unpin_lock(rq, rf);
- pull_rt_task(rq);
- rq_repin_lock(rq, rf);
- }
}
#ifdef CONFIG_SMP
@@ -2366,8 +2367,8 @@ const struct sched_class rt_sched_class = {
.set_next_task = set_next_task_rt,
#ifdef CONFIG_SMP
+ .balance = balance_rt,
.select_task_rq = select_task_rq_rt,
-
.set_cpus_allowed = set_cpus_allowed_common,
.rq_online = rq_online_rt,
.rq_offline = rq_offline_rt,
