diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index aa7cade1b9f3..79c7fe978b17 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2084,7 +2084,8 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq_rcu_node(rnp);
-		WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+		if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+			dump_blkd_tasks(rnp, 10);
 		WARN_ON_ONCE(rnp->qsmask);
 		WRITE_ONCE(rnp->completed, rsp->gpnum);
 		rdp = this_cpu_ptr(rsp->rda);
@@ -2294,6 +2295,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			return;
 		}
+		rnp->completedqs = rnp->gpnum;
 		mask = rnp->grpmask;
 		if (rnp->parent == NULL) {
 
@@ -3930,6 +3932,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 						   &rcu_fqs_class[i], fqs[i]);
 			rnp->gpnum = rsp->gpnum;
 			rnp->completed = rsp->completed;
+			rnp->completedqs = rsp->completed;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
 			rnp->grplo = j * cpustride;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 78e051dffc5b..7365ac53fdd9 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -87,6 +87,7 @@ struct rcu_node {
 	unsigned long completed; /* Last GP completed for this node. */
 				/*  This will either be equal to or one */
 				/*  behind the root rcu_node's gpnum. */
+	unsigned long completedqs; /* All QSes done for this node. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
 				/*  order for current grace period to proceed.*/
 				/*  In leaf rcu_node, each bit corresponds to */
@@ -453,6 +454,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 static void rcu_preempt_check_callbacks(void);
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
 static void __init __rcu_init_preempt(void);
+static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
 static void invoke_rcu_callbacks_kthread(void);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 7fd12039e512..17b67ecf7dff 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -260,8 +260,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * ->exp_tasks pointers, respectively, to reference the newly
 	 * blocked tasks.
 	 */
-	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD))
+	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) {
 		rnp->gp_tasks = &t->rcu_node_entry;
+		WARN_ON_ONCE(rnp->completedqs == rnp->gpnum);
+	}
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
 		rnp->exp_tasks = &t->rcu_node_entry;
 	WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) !=
@@ -535,6 +537,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 		WARN_ON_ONCE(rnp != t->rcu_blocked_node);
 		WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
+		WARN_ON_ONCE(rnp->completedqs == rnp->gpnum &&
+			     (!empty_norm || rnp->qsmask));
 		empty_exp = sync_rcu_preempt_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
 		np = rcu_next_node_entry(t, rnp);
@@ -697,7 +701,8 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 	struct task_struct *t;
 
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
-	WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+	if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+		dump_blkd_tasks(rnp, 10);
 	if (rcu_preempt_has_tasks(rnp)) {
 		rnp->gp_tasks = rnp->blkd_tasks.next;
 		t = container_of(rnp->gp_tasks, struct task_struct,
@@ -841,6 +846,27 @@ void exit_rcu(void)
 	__rcu_read_unlock();
 }
 
+/*
+ * Dump the blocked-tasks state, but limit the list dump to the
+ * specified number of elements.
+ */
+static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
+{
+	int i;
+	struct list_head *lhp;
+
+	lockdep_assert_held(&rnp->lock);
+	pr_info("%s: grp: %d-%d level: %d ->qamask %#lx ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p &->blkd_tasks: %p offset: %u\n", __func__, rnp->grplo, rnp->grphi, rnp->level, rnp->qsmask, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks, &rnp->blkd_tasks, (unsigned int)offsetof(typeof(*rnp), blkd_tasks));
+	pr_cont("\t->blkd_tasks");
+	i = 0;
+	list_for_each(lhp, &rnp->blkd_tasks) {
+		pr_cont(" %p", lhp);
+		if (++i >= 10)
+			break;
+	}
+	pr_cont("\n");
+}
+
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
 static struct rcu_state *const rcu_state_p = &rcu_sched_state;
@@ -949,6 +975,14 @@ void exit_rcu(void)
 {
 }
 
+/*
+ * Dump the guaranteed-empty blocked-tasks state.  Trust but verify.
+ */
+static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
+{
+	WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks));
+}
+
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_BOOST