When there are one task with sched-delayed and one task
which is descheduling, Using nr-running to determine
CPU idle may be incorrect.
For example:
task-A is sched_delayed, task-B is descheduling:
1. before schedule():
   rq-nr-running=2, task-A->on_rq=1; task-B->on_rq=1;
2. after block_task(B):
   rq-nr-running=1, task-A->on_rq=1; task-B->on_rq=0;
3. after pick_next_task(), because the task-A would be dequeued:
   rq-nr-running=0, task-A->on_rq=0; task-B->on_rq=0;

In ttwu_queue_cond, it hope the nr-running to be 0 after
the step 2, however, now the nr-running is not 0.
So sub the nr-delayed-task when checking the rq-nr-running.

Fixes: 152e11f6df29 ("sched/fair: Implement delayed dequeue")
Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
---
 kernel/sched/core.c  | 2 +-
 kernel/sched/fair.c  | 5 -----
 kernel/sched/sched.h | 5 +++++
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 67189907214d..6569f220c2fb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3963,7 +3963,7 @@ static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 	 * p->on_cpu can be whatever, we've done the dequeue, so
 	 * the wakee has been accounted out of ->nr_running.
 	 */
-	if (!cpu_rq(cpu)->nr_running)
+	if (!(cpu_rq(cpu)->nr_running - cfs_h_nr_delayed(cpu_rq(cpu))))
 		return true;
 
 	return false;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8797f6872155..29ee1ce17036 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7181,11 +7181,6 @@ static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	return true;
 }
 
-static inline unsigned int cfs_h_nr_delayed(struct rq *rq)
-{
-	return (rq->cfs.h_nr_queued - rq->cfs.h_nr_runnable);
-}
-
 #ifdef CONFIG_SMP
 
 /* Working cpumask for: sched_balance_rq(), sched_balance_newidle(). */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c8512a9fb022..3996b0c5c332 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3609,6 +3609,11 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
 }
 #endif
 
+static inline unsigned int cfs_h_nr_delayed(struct rq *rq)
+{
+	return (rq->cfs.h_nr_queued - rq->cfs.h_nr_runnable);
+}
+
 extern void swake_up_all_locked(struct swait_queue_head *q);
 extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
 
-- 
2.25.1