diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 98c618e..a8e3815 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -108,6 +108,7 @@ struct nbd_device {
 	struct nbd_config *config;
 	struct mutex config_lock;
 	struct gendisk *disk;
+	struct workqueue_struct *recv_workq;
 
 	struct list_head list;
 	struct task_struct *task_recv;
@@ -139,7 +140,6 @@ static struct dentry *nbd_dbg_dir;
 
 static unsigned int nbds_max = 16;
 static int max_part = 16;
-static struct workqueue_struct *recv_workqueue;
 static int part_shift;
 
 static int nbd_dev_dbg_init(struct nbd_device *nbd);
@@ -1058,7 +1058,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 		/* We take the tx_mutex in an error path in the recv_work, so we
 		 * need to queue_work outside of the tx_mutex.
 		 */
-		queue_work(recv_workqueue, &args->work);
+		queue_work(nbd->recv_workq, &args->work);
 
 		atomic_inc(&config->live_connections);
 		wake_up(&config->conn_wait);
@@ -1159,6 +1159,10 @@ static void nbd_config_put(struct nbd_device *nbd)
 		kfree(nbd->config);
 		nbd->config = NULL;
 
+		if (nbd->recv_workq)
+			destroy_workqueue(nbd->recv_workq);
+		nbd->recv_workq = NULL;
+
 		nbd->tag_set.timeout = 0;
 		nbd->disk->queue->limits.discard_granularity = 0;
 		nbd->disk->queue->limits.discard_alignment = 0;
@@ -1187,6 +1191,14 @@ static int nbd_start_device(struct nbd_device *nbd)
 		return -EINVAL;
 	}
 
+	nbd->recv_workq = alloc_workqueue("knbd%d-recv",
+					  WQ_MEM_RECLAIM | WQ_HIGHPRI |
+					  WQ_UNBOUND, 0, nbd->index);
+	if (!nbd->recv_workq) {
+		dev_err(disk_to_dev(nbd->disk), "Could not allocate knbd recv work queue.\n");
+		return -ENOMEM;
+	}
+
 	blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections);
 	nbd->task_recv = current;
 
@@ -1217,7 +1229,7 @@ static int nbd_start_device(struct nbd_device *nbd)
 		INIT_WORK(&args->work, recv_work);
 		args->nbd = nbd;
 		args->index = i;
-		queue_work(recv_workqueue, &args->work);
+		queue_work(nbd->recv_workq, &args->work);
 	}
 	nbd_size_update(nbd);
 	return error;
@@ -1237,8 +1249,10 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 	mutex_unlock(&nbd->config_lock);
 	ret = wait_event_interruptible(config->recv_wq,
 					 atomic_read(&config->recv_threads) == 0);
-	if (ret)
+	if (ret) {
 		sock_shutdown(nbd);
+		flush_workqueue(nbd->recv_workq);
+	}
 	mutex_lock(&nbd->config_lock);
 	nbd_bdev_reset(bdev);
 	/* user requested, ignore socket errors */
@@ -1899,6 +1913,12 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd)
 	nbd_disconnect(nbd);
 	nbd_clear_sock(nbd);
 	mutex_unlock(&nbd->config_lock);
+	/*
+	 * Make sure recv thread has finished, so it does not drop the last
+	 * config ref and try to destroy the workqueue from inside the work
+	 * queue.
+	 */
+	flush_workqueue(nbd->recv_workq);
 	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
 			       &nbd->config->runtime_flags))
 		nbd_config_put(nbd);
@@ -2283,20 +2303,12 @@ static int __init nbd_init(void)
 
 	if (nbds_max > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
-	recv_workqueue = alloc_workqueue("knbd-recv",
-					 WQ_MEM_RECLAIM | WQ_HIGHPRI |
-					 WQ_UNBOUND, 0);
-	if (!recv_workqueue)
-		return -ENOMEM;
 
-	if (register_blkdev(NBD_MAJOR, "nbd")) {
-		destroy_workqueue(recv_workqueue);
+	if (register_blkdev(NBD_MAJOR, "nbd"))
 		return -EIO;
-	}
 
 	if (genl_register_family(&nbd_genl_family)) {
 		unregister_blkdev(NBD_MAJOR, "nbd");
-		destroy_workqueue(recv_workqueue);
 		return -EINVAL;
 	}
 	nbd_dbg_init();
@@ -2338,7 +2350,6 @@ static void __exit nbd_cleanup(void)
 
 	idr_destroy(&nbd_index_idr);
 	genl_unregister_family(&nbd_genl_family);
-	destroy_workqueue(recv_workqueue);
 	unregister_blkdev(NBD_MAJOR, "nbd");
 }