diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0b72e816b8d0126f0a3e72c1f3a2496fc3545030..7f5d4be220345b0899d38ced692f2458b9278ce7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2817,6 +2817,19 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
 	return false;
 }
 
+static bool __flush_work(struct work_struct *work)
+{
+	struct wq_barrier barr;
+
+	if (start_flush_work(work, &barr)) {
+		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+		return true;
+	} else {
+		return false;
+	}
+}
+
 /**
  * flush_work - wait for a work to finish executing the last queueing instance
  * @work: the work to flush
@@ -2830,18 +2843,10 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
  */
 bool flush_work(struct work_struct *work)
 {
-	struct wq_barrier barr;
-
 	lock_map_acquire(&work->lockdep_map);
 	lock_map_release(&work->lockdep_map);
 
-	if (start_flush_work(work, &barr)) {
-		wait_for_completion(&barr.done);
-		destroy_work_on_stack(&barr.work);
-		return true;
-	} else {
-		return false;
-	}
+	return __flush_work(work);
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
@@ -3411,6 +3416,12 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to,
 {
 	to->nice = from->nice;
 	cpumask_copy(to->cpumask, from->cpumask);
+	/*
+	 * Unlike hash and equality test, this function doesn't ignore
+	 * ->no_numa as it is used for both pool and wq attrs.  Instead,
+	 * get_unbound_pool() explicitly clears ->no_numa after copying.
+	 */
+	to->no_numa = from->no_numa;
 }
 
 /* hash value of the content of @attr */
@@ -3578,6 +3589,12 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
 	lockdep_set_subclass(&pool->lock, 1);	/* see put_pwq() */
 	copy_workqueue_attrs(pool->attrs, attrs);
 
+	/*
+	 * no_numa isn't a worker_pool attribute, always clear it.  See
+	 * 'struct workqueue_attrs' comments for detail.
+	 */
+	pool->attrs->no_numa = false;
+
 	/* if cpumask is contained inside a NUMA node, we belong to that node */
 	if (wq_numa_enabled) {
 		for_each_node(node) {
@@ -4756,7 +4773,14 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
 
 	INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
 	schedule_work_on(cpu, &wfc.work);
-	flush_work(&wfc.work);
+
+	/*
+	 * The work item is on-stack and can't lead to deadlock through
+	 * flushing.  Use __flush_work() to avoid spurious lockdep warnings
+	 * when work_on_cpu()s are nested.
+	 */
+	__flush_work(&wfc.work);
+
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);