diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -2514,7 +2514,7 @@ static inline u32 rtl8169_tso_csum(struct sk_buff *skb, struct net_device *dev)
 static int rtl8169_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-	unsigned int frags, entry = tp->cur_tx % NUM_TX_DESC;
+	unsigned int frags, cur_tx, entry = tp->cur_tx % NUM_TX_DESC;
 	struct TxDesc *txd = tp->TxDescArray + entry;
 	void __iomem *ioaddr = tp->mmio_addr;
 	dma_addr_t mapping;
@@ -2567,13 +2567,17 @@ static int rtl8169_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	dev->trans_start = jiffies;
 
+	cur_tx = tp->cur_tx;
+
 	tp->cur_tx += frags + 1;
 
-	smp_wmb();
+	mmiowb();
 
-	RTL_W8(TxPoll, NPQ);	/* set polling bit */
+	smp_mb();
 
-	if (TX_BUFFS_AVAIL(tp) < MAX_SKB_FRAGS) {
+	if (cur_tx == tp->dirty_tx)
+		RTL_W8(TxPoll, NPQ);
+	else if (TX_BUFFS_AVAIL(tp) < MAX_SKB_FRAGS) {
 		netif_stop_queue(dev);
 		smp_rmb();
 		if (TX_BUFFS_AVAIL(tp) >= MAX_SKB_FRAGS)
@@ -2677,10 +2681,18 @@ static void rtl8169_tx_interrupt(struct net_device *dev,
 
 	if (tp->dirty_tx != dirty_tx) {
 		tp->dirty_tx = dirty_tx;
-		smp_wmb();
-		if (netif_queue_stopped(dev) &&
-		    (TX_BUFFS_AVAIL(tp) >= MAX_SKB_FRAGS)) {
-			netif_wake_queue(dev);
+		smp_mb();
+		if (unlikely(netif_queue_stopped(dev))) {
+			netif_tx_lock(dev);
+		    	if (TX_BUFFS_AVAIL(tp) >= MAX_SKB_FRAGS)
+				netif_wake_queue(dev);
+			if (dirty_tx != tp->cur_tx)
+				RTL_W8(TxPoll, NPQ);
+			netif_tx_unlock(dev);
+		} else if (dirty_tx != tp->cur_tx) {
+			netif_tx_lock(dev);
+			RTL_W8(TxPoll, NPQ);
+			netif_tx_unlock(dev);
 		}
 	}
 }