[RFC PATCH v2 4/7] sched/fair: Take care of group/affinity/sched_class change for throttled task

[Aaron Lu]

On task group change, for tasks whose on_rq equals to TASK_ON_RQ_QUEUED,
core will dequeue it and then requeued it.

The throttled task is still considered as queued by core because p->on_rq
is still set so core will dequeue it, but since the task is already
dequeued on throttle in fair, handle this case properly.

Affinity and sched class change is similar.

Signed-off-by: Aaron Lu <ziqianlu@xxxxxxxxxxxxx>
---
 kernel/sched/fair.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4152088fc0546..76b8a5ffcbdd2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5882,6 +5882,20 @@ void init_cfs_throttle_work(struct task_struct *p)
 	INIT_LIST_HEAD(&p->throttle_node);
 }
 
+static void dequeue_throttled_task(struct task_struct *p, int flags)
+{
+	/*
+	 * Task is throttled and someone wants to dequeue it again:
+	 * it must be sched/core when core needs to do things like
+	 * task affinity change, task group change, task sched class
+	 * change etc.
+	 */
+	WARN_ON_ONCE(p->se.on_rq);
+	WARN_ON_ONCE(flags & DEQUEUE_SLEEP);
+
+	list_del_init(&p->throttle_node);
+}
+
 static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags);
 static int tg_unthrottle_up(struct task_group *tg, void *data)
 {
@@ -6716,6 +6730,7 @@ static inline void sync_throttle(struct task_group *tg, int cpu) {}
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 static void task_throttle_setup_work(struct task_struct *p) {}
 static bool task_is_throttled(struct task_struct *p) { return false; }
+static void dequeue_throttled_task(struct task_struct *p, int flags) {}
 
 static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
 {
@@ -7146,6 +7161,11 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
  */
 static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
+	if (unlikely(task_is_throttled(p))) {
+		dequeue_throttled_task(p, flags);
+		return true;
+	}
+
 	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & DEQUEUE_SAVE))))
 		util_est_dequeue(&rq->cfs, p);
 
-- 
2.39.5