diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index f3778f8952da..b8c3c813ea57 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -396,14 +396,14 @@ o	Each element of the form "3/3 ..>. 0:7 ^0" represents one rcu_node
 
 The output of "cat rcu/rcu_sched/rcu_pending" looks as follows:
 
-  0!np=26111 qsp=29 rpq=5386 cbr=1 cng=570 gpc=3674 gps=577 nn=15903
-  1!np=28913 qsp=35 rpq=6097 cbr=1 cng=448 gpc=3700 gps=554 nn=18113
-  2!np=32740 qsp=37 rpq=6202 cbr=0 cng=476 gpc=4627 gps=546 nn=20889
-  3 np=23679 qsp=22 rpq=5044 cbr=1 cng=415 gpc=3403 gps=347 nn=14469
-  4!np=30714 qsp=4 rpq=5574 cbr=0 cng=528 gpc=3931 gps=639 nn=20042
-  5 np=28910 qsp=2 rpq=5246 cbr=0 cng=428 gpc=4105 gps=709 nn=18422
-  6!np=38648 qsp=5 rpq=7076 cbr=0 cng=840 gpc=4072 gps=961 nn=25699
-  7 np=37275 qsp=2 rpq=6873 cbr=0 cng=868 gpc=3416 gps=971 nn=25147
+  0!np=26111 qsp=29 rpq=5386 cbr=1 cng=570 gpc=3674 gps=577 nn=15903 ndw=0
+  1!np=28913 qsp=35 rpq=6097 cbr=1 cng=448 gpc=3700 gps=554 nn=18113 ndw=0
+  2!np=32740 qsp=37 rpq=6202 cbr=0 cng=476 gpc=4627 gps=546 nn=20889 ndw=0
+  3 np=23679 qsp=22 rpq=5044 cbr=1 cng=415 gpc=3403 gps=347 nn=14469 ndw=0
+  4!np=30714 qsp=4 rpq=5574 cbr=0 cng=528 gpc=3931 gps=639 nn=20042 ndw=0
+  5 np=28910 qsp=2 rpq=5246 cbr=0 cng=428 gpc=4105 gps=709 nn=18422 ndw=0
+  6!np=38648 qsp=5 rpq=7076 cbr=0 cng=840 gpc=4072 gps=961 nn=25699 ndw=0
+  7 np=37275 qsp=2 rpq=6873 cbr=0 cng=868 gpc=3416 gps=971 nn=25147 ndw=0
 
 The fields are as follows:
 
@@ -432,6 +432,10 @@ o	"gpc" is the number of times that an old grace period had
 o	"gps" is the number of times that a new grace period had started,
 	but this CPU was not yet aware of it.
 
+o	"ndw" is the number of times that a wakeup of an rcuo
+	callback-offload kthread had to be deferred in order to avoid
+	deadlock.
+
 o	"nn" is the number of times that this CPU needed nothing.
 
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index abef9c358d47..264f0284c0bd 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -369,6 +369,9 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
 static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 				bool user)
 {
+	struct rcu_state *rsp;
+	struct rcu_data *rdp;
+
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
 	if (!user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
@@ -380,6 +383,10 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 			  current->pid, current->comm,
 			  idle->pid, idle->comm); /* must be idle task! */
 	}
+	for_each_rcu_flavor(rsp) {
+		rdp = this_cpu_ptr(rsp->rda);
+		do_nocb_deferred_wakeup(rdp);
+	}
 	rcu_prepare_for_idle(smp_processor_id());
 	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
 	smp_mb__before_atomic_inc();  /* See above. */
@@ -1928,13 +1935,13 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
  * Adopt the RCU callbacks from the specified rcu_state structure's
  * orphanage.  The caller must hold the ->orphan_lock.
  */
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
 {
 	int i;
 	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
 
 	/* No-CBs CPUs are handled specially. */
-	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
+	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
 		return;
 
 	/* Do the accounting first. */
@@ -2013,7 +2020,7 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
 	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
-	rcu_adopt_orphan_cbs(rsp);
+	rcu_adopt_orphan_cbs(rsp, flags);
 
 	/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
 	mask = rdp->grpmask;	/* rnp->grplo is constant. */
@@ -2330,6 +2337,9 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	/* If there are callbacks ready, invoke them. */
 	if (cpu_has_callbacks_ready_to_invoke(rdp))
 		invoke_rcu_callbacks(rsp, rdp);
+
+	/* Do any needed deferred wakeups of rcuo kthreads. */
+	do_nocb_deferred_wakeup(rdp);
 }
 
 /*
@@ -2464,7 +2474,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 
 		if (cpu != -1)
 			rdp = per_cpu_ptr(rsp->rda, cpu);
-		offline = !__call_rcu_nocb(rdp, head, lazy);
+		offline = !__call_rcu_nocb(rdp, head, lazy, flags);
 		WARN_ON_ONCE(offline);
 		/* _call_rcu() is illegal on offline CPU; leak the callback. */
 		local_irq_restore(flags);
@@ -2817,6 +2827,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 		return 1;
 	}
 
+	/* Does this CPU need a deferred NOCB wakeup? */
+	if (rcu_nocb_need_deferred_wakeup(rdp)) {
+		rdp->n_rp_nocb_defer_wakeup++;
+		return 1;
+	}
+
 	/* nothing to do */
 	rdp->n_rp_need_nothing++;
 	return 0;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8e34d8674a4e..a87adfc2916b 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -317,6 +317,7 @@ struct rcu_data {
 	unsigned long n_rp_cpu_needs_gp;
 	unsigned long n_rp_gp_completed;
 	unsigned long n_rp_gp_started;
+	unsigned long n_rp_nocb_defer_wakeup;
 	unsigned long n_rp_need_nothing;
 
 	/* 6) _rcu_barrier() and OOM callbacks. */
@@ -335,6 +336,7 @@ struct rcu_data {
 	int nocb_p_count_lazy;		/*  (approximate). */
 	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
+	bool nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* 8) RCU CPU stall data. */
@@ -550,9 +552,12 @@ 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 void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy);
+			    bool lazy, unsigned long flags);
 static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-				      struct rcu_data *rdp);
+				      struct rcu_data *rdp,
+				      unsigned long flags);
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
 static void rcu_kick_nohz_cpu(int cpu);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index b023e5407111..752ffaa0d681 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2104,7 +2104,8 @@ bool rcu_is_nocb_cpu(int cpu)
 static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 				    struct rcu_head *rhp,
 				    struct rcu_head **rhtp,
-				    int rhcount, int rhcount_lazy)
+				    int rhcount, int rhcount_lazy,
+				    unsigned long flags)
 {
 	int len;
 	struct rcu_head **old_rhpp;
@@ -2125,9 +2126,16 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 	}
 	len = atomic_long_read(&rdp->nocb_q_count);
 	if (old_rhpp == &rdp->nocb_head) {
-		wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */
+		if (!irqs_disabled_flags(flags)) {
+			wake_up(&rdp->nocb_wq); /* ... if queue was empty ... */
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeEmpty"));
+		} else {
+			rdp->nocb_defer_wakeup = true;
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeEmptyIsDeferred"));
+		}
 		rdp->qlen_last_fqs_check = 0;
-		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty"));
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
 		wake_up_process(t); /* ... or if many callbacks queued. */
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
@@ -2148,12 +2156,12 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
  * "rcuo" kthread can find it.
  */
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy)
+			    bool lazy, unsigned long flags)
 {
 
 	if (!rcu_is_nocb_cpu(rdp->cpu))
 		return 0;
-	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy);
+	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags);
 	if (__is_kfree_rcu_offset((unsigned long)rhp->func))
 		trace_rcu_kfree_callback(rdp->rsp->name, rhp,
 					 (unsigned long)rhp->func,
@@ -2171,7 +2179,8 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
  * not a no-CBs CPU.
  */
 static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-						     struct rcu_data *rdp)
+						     struct rcu_data *rdp,
+						     unsigned long flags)
 {
 	long ql = rsp->qlen;
 	long qll = rsp->qlen_lazy;
@@ -2185,14 +2194,14 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 	/* First, enqueue the donelist, if any.  This preserves CB ordering. */
 	if (rsp->orphan_donelist != NULL) {
 		__call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
-					rsp->orphan_donetail, ql, qll);
+					rsp->orphan_donetail, ql, qll, flags);
 		ql = qll = 0;
 		rsp->orphan_donelist = NULL;
 		rsp->orphan_donetail = &rsp->orphan_donelist;
 	}
 	if (rsp->orphan_nxtlist != NULL) {
 		__call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
-					rsp->orphan_nxttail, ql, qll);
+					rsp->orphan_nxttail, ql, qll, flags);
 		ql = qll = 0;
 		rsp->orphan_nxtlist = NULL;
 		rsp->orphan_nxttail = &rsp->orphan_nxtlist;
@@ -2314,6 +2323,22 @@ static int rcu_nocb_kthread(void *arg)
 	return 0;
 }
 
+/* Is a deferred wakeup of rcu_nocb_kthread() required? */
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+	return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+}
+
+/* Do a deferred wakeup of rcu_nocb_kthread(). */
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+	if (!rcu_nocb_need_deferred_wakeup(rdp))
+		return;
+	ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
+	wake_up(&rdp->nocb_wq);
+	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
+}
+
 /* Initialize per-rcu_data variables for no-CBs CPUs. */
 static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
@@ -2369,13 +2394,14 @@ 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)
+			    bool lazy, unsigned long flags)
 {
 	return 0;
 }
 
 static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-						     struct rcu_data *rdp)
+						     struct rcu_data *rdp,
+						     unsigned long flags)
 {
 	return 0;
 }
@@ -2384,6 +2410,15 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 }
 
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+	return false;
+}
+
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+}
+
 static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 {
 }
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 3596797b7e46..4def475336d4 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -364,9 +364,10 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->n_rp_report_qs,
 		   rdp->n_rp_cb_ready,
 		   rdp->n_rp_cpu_needs_gp);
-	seq_printf(m, "gpc=%ld gps=%ld nn=%ld\n",
+	seq_printf(m, "gpc=%ld gps=%ld nn=%ld ndw%ld\n",
 		   rdp->n_rp_gp_completed,
 		   rdp->n_rp_gp_started,
+		   rdp->n_rp_nocb_defer_wakeup,
 		   rdp->n_rp_need_nothing);
 }