diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f732642e3e09..1d7bc87007cd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -290,6 +290,10 @@ static void sched_core_assert_empty(void)
 static void __sched_core_enable(void)
 {
 	static_branch_enable(&__sched_core_enabled);
+	/*
+	 * Ensure raw_spin_rq_*lock*() have completed before flipping.
+	 */
+	synchronize_rcu();
 	__sched_core_flip(true);
 	sched_core_assert_empty();
 }
@@ -449,16 +453,23 @@ void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
 {
 	raw_spinlock_t *lock;

+	/* Matches synchronize_sched() in __sched_core_enabled() */
+	preempt_disable();
 	if (sched_core_disabled()) {
 		raw_spin_lock_nested(&rq->__lock, subclass);
+		/* preempt-count *MUST* be > 1 */
+		preempt_enable_no_resched();
 		return;
 	}

 	for (;;) {
 		lock = __rq_lockp(rq);
 		raw_spin_lock_nested(lock, subclass);
-		if (likely(lock == __rq_lockp(rq)))
+		if (likely(lock == __rq_lockp(rq))) {
+			/* preempt-count *MUST* be > 1 */
+			preempt_enable_no_resched();
 			return;
+		}
 		raw_spin_unlock(lock);
 	}
 }
@@ -468,14 +479,21 @@ bool raw_spin_rq_trylock(struct rq *rq)
 	raw_spinlock_t *lock;
 	bool ret;

-	if (sched_core_disabled())
-		return raw_spin_trylock(&rq->__lock);
+	/* Matches synchronize_sched() in __sched_core_enabled() */
+	preempt_disable();
+	if (sched_core_disabled()) {
+		ret = raw_spin_trylock(&rq->__lock);
+		preempt_enable();
+		return ret;
+	}

 	for (;;) {
 		lock = __rq_lockp(rq);
 		ret = raw_spin_trylock(lock);
-		if (!ret || (likely(lock == __rq_lockp(rq))))
+		if (!ret || (likely(lock == __rq_lockp(rq)))) {
+			preempt_enable();
 			return ret;
+		}
 		raw_spin_unlock(lock);
 	}
 }
@@ -493,14 +511,17 @@ void double_rq_lock(struct rq *rq1, struct rq *rq2)
 {
 	lockdep_assert_irqs_disabled();

-	if (rq1->cpu > rq2->cpu)
-		swap(rq1, rq2);
-
-	raw_spin_rq_lock(rq1);
-	if (__rq_lockp(rq1) == __rq_lockp(rq2))
-		return;
-
-	raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
+	if (__rq_lockp(rq1) == __rq_lockp(rq2)) {
+		raw_spin_rq_lock(rq1);
+	} else {
+		if (__rq_lockp(rq1) < __rq_lockp(rq2)) {
+			raw_spin_rq_lock(rq1);
+			raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
+		} else {
+			raw_spin_rq_lock(rq2);
+			raw_spin_rq_lock_nested(rq1, SINGLE_DEPTH_NESTING);
+		}
+	}
 }
 #endif