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>

1 files changed, 27 insertions, 3 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0db2c1b3361e..c8870c5bd7df 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1727,10 +1727,11 @@ struct sched_class {
 	struct task_struct * (*pick_next_task)(struct rq *rq,
 					       struct task_struct *prev,
 					       struct rq_flags *rf);
-	void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf);
+	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
+	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
 	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
 
@@ -1773,7 +1774,7 @@ struct sched_class {
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	WARN_ON_ONCE(rq->curr != prev);
-	prev->sched_class->put_prev_task(rq, prev, NULL);
+	prev->sched_class->put_prev_task(rq, prev);
 }
 
 static inline void set_next_task(struct rq *rq, struct task_struct *next)
@@ -1787,8 +1788,12 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next)
 #else
 #define sched_class_highest (&dl_sched_class)
 #endif
+
+#define for_class_range(class, _from, _to) \
+	for (class = (_from); class != (_to); class = class->next)
+
 #define for_each_class(class) \
-   for (class = sched_class_highest; class; class = class->next)
+	for_class_range(class, sched_class_highest, NULL)
 
 extern const struct sched_class stop_sched_class;
 extern const struct sched_class dl_sched_class;
@@ -1796,6 +1801,25 @@ extern const struct sched_class rt_sched_class;
 extern const struct sched_class fair_sched_class;
 extern const struct sched_class idle_sched_class;
 
+static inline bool sched_stop_runnable(struct rq *rq)
+{
+	return rq->stop && task_on_rq_queued(rq->stop);
+}
+
+static inline bool sched_dl_runnable(struct rq *rq)
+{
+	return rq->dl.dl_nr_running > 0;
+}
+
+static inline bool sched_rt_runnable(struct rq *rq)
+{
+	return rq->rt.rt_queued > 0;
+}
+
+static inline bool sched_fair_runnable(struct rq *rq)
+{
+	return rq->cfs.nr_running > 0;
+}
 
 #ifdef CONFIG_SMP