diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e41dd4131f7a141976e771653e3169f2955f6f33..8e8c6ec1d30f01292bf2634ebf76ebddb83597c6 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1614,7 +1614,6 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 	int needmore;
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
-	rcu_nocb_gp_cleanup(rsp, rnp);
 	rnp->need_future_gp[c & 0x1] = 0;
 	needmore = rnp->need_future_gp[(c + 1) & 0x1];
 	trace_rcu_future_gp(rnp, rdp, c,
@@ -2010,6 +2009,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	int nocb = 0;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
+	wait_queue_head_t *sq;
 
 	WRITE_ONCE(rsp->gp_activity, jiffies);
 	raw_spin_lock_irq_rcu_node(rnp);
@@ -2046,7 +2046,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 			needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
 		/* smp_mb() provided by prior unlock-lock pair. */
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
+		sq = rcu_nocb_gp_get(rnp);
 		raw_spin_unlock_irq(&rnp->lock);
+		rcu_nocb_gp_cleanup(sq);
 		cond_resched_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 		rcu_gp_slow(rsp, gp_cleanup_delay);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 83360b4f4352786b0129d5ac64046102d73933db..10dedfbef09d8362e437fdb264a1d67111886056 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -621,7 +621,8 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static void increment_cpu_stall_ticks(void);
 static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
 static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
-static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
+static wait_queue_head_t *rcu_nocb_gp_get(struct rcu_node *rnp);
+static void rcu_nocb_gp_cleanup(wait_queue_head_t *sq);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 			    bool lazy, unsigned long flags);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 9467a8b7e756173bc9a94cc5b9828066a9f50e16..631aff61abe93f7ee59a82ce9ec6b6b094e6879b 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1811,9 +1811,9 @@ early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
  * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended
  * grace period.
  */
-static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+static void rcu_nocb_gp_cleanup(wait_queue_head_t *sq)
 {
-	wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]);
+	wake_up_all(sq);
 }
 
 /*
@@ -1829,6 +1829,11 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
 	rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq;
 }
 
+static wait_queue_head_t *rcu_nocb_gp_get(struct rcu_node *rnp)
+{
+	return &rnp->nocb_gp_wq[rnp->completed & 0x1];
+}
+
 static void rcu_init_one_nocb(struct rcu_node *rnp)
 {
 	init_waitqueue_head(&rnp->nocb_gp_wq[0]);
@@ -2502,7 +2507,7 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
 	return false;
 }
 
-static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+static void rcu_nocb_gp_cleanup(wait_queue_head_t *sq)
 {
 }
 
@@ -2510,6 +2515,11 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
 {
 }
 
+static wait_queue_head_t *rcu_nocb_gp_get(struct rcu_node *rnp)
+{
+	return NULL;
+}
+
 static void rcu_init_one_nocb(struct rcu_node *rnp)
 {
 }