diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 48e5c03df1dd..257e9ae34414 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -95,9 +95,9 @@ static inline void __rcu_read_lock(void)
 
 static inline void __rcu_read_unlock(void)
 {
-	preempt_enable();
 	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
 		rcu_read_unlock_strict();
+	preempt_enable();
 }
 
 static inline int rcu_preempt_depth(void)
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3600152b858e..9573408a9800 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -833,8 +833,17 @@ void rcu_read_unlock_strict(void)
 {
 	struct rcu_data *rdp;
 
-	if (irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
+	if (irqs_disabled() || in_atomic_preempt_off() || !rcu_state.gp_kthread)
 		return;
+
+	/*
+	 * rcu_report_qs_rdp() can only be invoked with a stable rdp and
+	 * from the local CPU.
+	 *
+	 * The in_atomic_preempt_off() check ensures that we come here holding
+	 * the last preempt_count (which will get dropped once we return to
+	 * __rcu_read_unlock().
+	 */
 	rdp = this_cpu_ptr(&rcu_data);
 	rdp->cpu_no_qs.b.norm = false;
 	rcu_report_qs_rdp(rdp);