diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 12811f18c134..3624e67aef72 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6069,6 +6069,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	struct device *d = tp_to_dev(tp);
 	dma_addr_t mapping;
 	u32 opts[2], len;
+	bool stop_queue;
 	int frags;
 
 	if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) {
@@ -6110,8 +6111,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	txd->opts2 = cpu_to_le32(opts[1]);
 
-	netdev_sent_queue(dev, skb->len);
-
 	skb_tx_timestamp(skb);
 
 	/* Force memory writes to complete before releasing descriptor */
@@ -6124,16 +6123,16 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	tp->cur_tx += frags + 1;
 
-	RTL_W8(tp, TxPoll, NPQ);
-
-	mmiowb();
-
-	if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) {
-		/* Avoid wrongly optimistic queue wake-up: rtl_tx thread must
-		 * not miss a ring update when it notices a stopped queue.
-		 */
-		smp_wmb();
+	stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS);
+	if (unlikely(stop_queue))
 		netif_stop_queue(dev);
+
+	if (__netdev_sent_queue(dev, skb->len, skb->xmit_more)) {
+		RTL_W8(tp, TxPoll, NPQ);
+		mmiowb();
+	}
+
+	if (unlikely(stop_queue)) {
 		/* Sync with rtl_tx:
 		 * - publish queue status and cur_tx ring index (write barrier)
 		 * - refresh dirty_tx ring index (read barrier).
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1eeb019d85a3..9b00043effa3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3226,6 +3226,14 @@ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes)
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes);
 }
 
+static inline bool __netdev_sent_queue(struct net_device *dev,
+				       unsigned int bytes,
+				       bool xmit_more)
+{
+	return __netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes,
+				      xmit_more);
+}
+
 static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
 					     unsigned int pkts, unsigned int bytes)
 {