diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c05d05094e70..eb3a7b8bd3cb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3919,7 +3919,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		p = fair_sched_class.pick_next_task(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
-			goto restart;
+			goto again;
 
 		/* Assumes fair_sched_class->next == idle_sched_class */
 		if (unlikely(!p))
@@ -3928,19 +3928,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		return p;
 	}
 
-restart:
-	/*
-	 * Ensure that we put DL/RT tasks before the pick loop, such that they
-	 * can PULL higher prio tasks when we lower the RQ 'priority'.
-	 */
-	prev->sched_class->put_prev_task(rq, prev, rf);
-	if (!rq->nr_running)
-		newidle_balance(rq, rf);
-
+again:
 	for_each_class(class) {
-		p = class->pick_next_task(rq, NULL, NULL);
-		if (p)
+		p = class->pick_next_task(rq, prev, rf);
+		if (p) {
+			if (unlikely(p == RETRY_TASK))
+				goto again;
 			return p;
+		}
 	}
 
 	/* The idle class should always have a runnable task: */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 2dc48720f189..4ed2d10c196c 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1761,13 +1761,39 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	struct task_struct *p;
 	struct dl_rq *dl_rq;
 
-	WARN_ON_ONCE(prev || rf);
-
 	dl_rq = &rq->dl;
 
+	if (need_pull_dl_task(rq, prev)) {
+		/*
+		 * 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're
+		 * being very careful to re-start the picking loop.
+		 */
+		rq_unpin_lock(rq, rf);
+		pull_dl_task(rq);
+		rq_repin_lock(rq, rf);
+		/*
+		 * pull_dl_task() can drop (and re-acquire) rq->lock; this
+		 * means a stop task can slip in, in which case we need to
+		 * re-start task selection.
+		 */
+		if (rq->stop && task_on_rq_queued(rq->stop))
+			return RETRY_TASK;
+	}
+
+	/*
+	 * When prev is DL, we may throttle it in put_prev_task().
+	 * So, we update time before we check for dl_nr_running.
+	 */
+	if (prev->sched_class == &dl_sched_class)
+		update_curr_dl(rq);
+
 	if (unlikely(!dl_rq->dl_nr_running))
 		return NULL;
 
+	put_prev_task(rq, prev);
+
 	dl_se = pick_next_dl_entity(rq, dl_rq);
 	BUG_ON(!dl_se);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8f8692baa679..31b3e1a10bb3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6810,7 +6810,7 @@ again:
 		goto idle;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	if (!prev || prev->sched_class != &fair_sched_class)
+	if (prev->sched_class != &fair_sched_class)
 		goto simple;
 
 	/*
@@ -6887,8 +6887,8 @@ again:
 	goto done;
 simple:
 #endif
-	if (prev)
-		put_prev_task(rq, prev);
+
+	put_prev_task(rq, prev);
 
 	do {
 		se = pick_next_entity(cfs_rq, NULL);
@@ -6916,9 +6916,6 @@ done: __maybe_unused;
 	return p;
 
 idle:
-	if (!rf)
-		return NULL;
-
 	new_tasks = newidle_balance(rq, rf);
 
 	/*
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8dad5aa600ea..e397a165b408 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -390,9 +390,7 @@ pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 {
 	struct task_struct *next = rq->idle;
 
-	if (prev)
-		put_prev_task(rq, prev);
-
+	put_prev_task(rq, prev);
 	set_next_task_idle(rq, next);
 
 	return next;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index ebaa4e619684..f65653b139bc 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1554,11 +1554,38 @@ 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 (need_pull_rt_task(rq, prev)) {
+		/*
+		 * 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're
+		 * being very careful to re-start the picking loop.
+		 */
+		rq_unpin_lock(rq, rf);
+		pull_rt_task(rq);
+		rq_repin_lock(rq, rf);
+		/*
+		 * pull_rt_task() can drop (and re-acquire) rq->lock; this
+		 * means a dl or stop task can slip in, in which case we need
+		 * to re-start task selection.
+		 */
+		if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) ||
+			     rq->dl.dl_nr_running))
+			return RETRY_TASK;
+	}
+
+	/*
+	 * We may dequeue prev's rt_rq in put_prev_task().
+	 * So, we update time before rt_queued check.
+	 */
+	if (prev->sched_class == &rt_sched_class)
+		update_curr_rt(rq);
 
 	if (!rt_rq->rt_queued)
 		return NULL;
 
+	put_prev_task(rq, prev);
+
 	p = _pick_next_task_rt(rq);
 
 	set_next_task_rt(rq, p);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4f0d1668c283..e14ae174e0d1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1724,15 +1724,12 @@ struct sched_class {
 	void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
 
 	/*
-	 * Both @prev and @rf are optional and may be NULL, in which case the
-	 * caller must already have invoked put_prev_task(rq, prev, rf).
+	 * It is the responsibility of the pick_next_task() method that will
+	 * return the next task to call put_prev_task() on the @prev task or
+	 * something equivalent.
 	 *
-	 * Otherwise it is the responsibility of the pick_next_task() to call
-	 * put_prev_task() on the @prev task or something equivalent, IFF it
-	 * returns a next task.
-	 *
-	 * In that case (@rf != NULL) it may return RETRY_TASK when it finds a
-	 * higher prio class has runnable tasks.
+	 * May return RETRY_TASK when it finds a higher prio class has runnable
+	 * tasks.
 	 */
 	struct task_struct * (*pick_next_task)(struct rq *rq,
 					       struct task_struct *prev,
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 7e1cee4e65b2..8f414018d5e0 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -33,11 +33,10 @@ pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 {
 	struct task_struct *stop = rq->stop;
 
-	WARN_ON_ONCE(prev || rf);
-
 	if (!stop || !task_on_rq_queued(stop))
 		return NULL;
 
+	put_prev_task(rq, prev);
 	set_next_task_stop(rq, stop);
 
 	return stop;