diff --git a/kernel/padata.c b/kernel/padata.c
index 282b489a2..0d7ec5fd5 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -33,6 +33,8 @@
 
 #define MAX_OBJ_NUM 1000
 
+static void padata_free_pd(struct parallel_data *pd);
+
 static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
 {
 	int cpu, target_cpu;
@@ -300,6 +302,7 @@ static void padata_serial_worker(struct work_struct *serial_work)
 	struct padata_serial_queue *squeue;
 	struct parallel_data *pd;
 	LIST_HEAD(local_list);
+	int cnt;
 
 	local_bh_disable();
 	squeue = container_of(serial_work, struct padata_serial_queue, work);
@@ -309,6 +312,8 @@ static void padata_serial_worker(struct work_struct *serial_work)
 	list_replace_init(&squeue->serial.list, &local_list);
 	spin_unlock(&squeue->serial.lock);
 
+	cnt = 0;
+
 	while (!list_empty(&local_list)) {
 		struct padata_priv *padata;
 
@@ -318,9 +323,12 @@ static void padata_serial_worker(struct work_struct *serial_work)
 		list_del_init(&padata->list);
 
 		padata->serial(padata);
-		atomic_dec(&pd->refcnt);
+		cnt++;
 	}
 	local_bh_enable();
+
+	if (atomic_sub_and_test(cnt, &pd->refcnt))
+		padata_free_pd(pd);
 }
 
 /**
@@ -443,7 +451,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
 	setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd);
 	atomic_set(&pd->seq_nr, -1);
 	atomic_set(&pd->reorder_objects, 0);
-	atomic_set(&pd->refcnt, 0);
+	atomic_set(&pd->refcnt, 1);
 	pd->pinst = pinst;
 	spin_lock_init(&pd->lock);
 
@@ -468,31 +476,6 @@ static void padata_free_pd(struct parallel_data *pd)
 	kfree(pd);
 }
 
-/* Flush all objects out of the padata queues. */
-static void padata_flush_queues(struct parallel_data *pd)
-{
-	int cpu;
-	struct padata_parallel_queue *pqueue;
-	struct padata_serial_queue *squeue;
-
-	for_each_cpu(cpu, pd->cpumask.pcpu) {
-		pqueue = per_cpu_ptr(pd->pqueue, cpu);
-		flush_work(&pqueue->work);
-	}
-
-	del_timer_sync(&pd->timer);
-
-	if (atomic_read(&pd->reorder_objects))
-		padata_reorder(pd);
-
-	for_each_cpu(cpu, pd->cpumask.cbcpu) {
-		squeue = per_cpu_ptr(pd->squeue, cpu);
-		flush_work(&squeue->work);
-	}
-
-	BUG_ON(atomic_read(&pd->refcnt) != 0);
-}
-
 static void __padata_start(struct padata_instance *pinst)
 {
 	pinst->flags |= PADATA_INIT;
@@ -506,10 +489,6 @@ static void __padata_stop(struct padata_instance *pinst)
 	pinst->flags &= ~PADATA_INIT;
 
 	synchronize_rcu();
-
-	get_online_cpus();
-	padata_flush_queues(pinst->pd);
-	put_online_cpus();
 }
 
 /* Replace the internal control structure with a new one. */
@@ -530,8 +509,8 @@ static void padata_replace(struct padata_instance *pinst,
 	if (!cpumask_equal(pd_old->cpumask.cbcpu, pd_new->cpumask.cbcpu))
 		notification_mask |= PADATA_CPU_SERIAL;
 
-	padata_flush_queues(pd_old);
-	padata_free_pd(pd_old);
+	if (atomic_dec_and_test(&pd_old->refcnt))
+		padata_free_pd(pd_old);
 
 	if (notification_mask)
 		blocking_notifier_call_chain(&pinst->cpumask_change_notifier,