r8169: add support for Byte Queue Limits

This patch is basically a resubmit of 1e91887 ("r8169: add support
for Byte Queue Limits") which was reverted later. The problems causing
the revert seem to have been fixed in the meantime.
Only change to the original patch is that the call to
netdev_reset_queue was moved to rtl8169_tx_clear.

The Tested-by refers to a system using the RTL8168evl chip version.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/realtek/r8169.c

@@ -5851,6 +5851,7 @@ static void rtl8169_tx_clear(struct rtl8169_private *tp)
 {
 	rtl8169_tx_clear_range(tp, tp->dirty_tx, NUM_TX_DESC);
 	tp->cur_tx = tp->dirty_tx = 0;
+	netdev_reset_queue(tp->dev);
 }
 
 static void rtl_reset_work(struct rtl8169_private *tp)
@@ -6153,6 +6154,8 @@ 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 */
@@ -6251,7 +6254,7 @@ static void rtl8169_pcierr_interrupt(struct net_device *dev)
 
 static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 {
-	unsigned int dirty_tx, tx_left;
+	unsigned int dirty_tx, tx_left, bytes_compl = 0, pkts_compl = 0;
 
 	dirty_tx = tp->dirty_tx;
 	smp_rmb();
@@ -6275,10 +6278,8 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 		rtl8169_unmap_tx_skb(tp_to_dev(tp), tx_skb,
 				     tp->TxDescArray + entry);
 		if (status & LastFrag) {
-			u64_stats_update_begin(&tp->tx_stats.syncp);
-			tp->tx_stats.packets++;
-			tp->tx_stats.bytes += tx_skb->skb->len;
-			u64_stats_update_end(&tp->tx_stats.syncp);
+			pkts_compl++;
+			bytes_compl += tx_skb->skb->len;
 			dev_consume_skb_any(tx_skb->skb);
 			tx_skb->skb = NULL;
 		}
@@ -6287,6 +6288,13 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 	}
 
 	if (tp->dirty_tx != dirty_tx) {
+		netdev_completed_queue(dev, pkts_compl, bytes_compl);
+
+		u64_stats_update_begin(&tp->tx_stats.syncp);
+		tp->tx_stats.packets += pkts_compl;
+		tp->tx_stats.bytes += bytes_compl;
+		u64_stats_update_end(&tp->tx_stats.syncp);
+
 		tp->dirty_tx = dirty_tx;
 		/* Sync with rtl8169_start_xmit:
 		 * - publish dirty_tx ring index (write barrier)