r8169: improve rtl_tx

We can simplify the for() condition and eliminate variable tx_left.
The change also considers that tp->cur_tx may be incremented by a
racing rtl8169_start_xmit().
In addition replace the write to tp->dirty_tx and the following
smp_mb() with an equivalent call to smp_store_mb(). This implicitly
adds a WRITE_ONCE() to the write.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/c2e19e5e-3d3f-d663-af32-13c3374f5def@gmail.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/realtek/r8169_main.c

@@ -4362,11 +4362,11 @@ static void rtl8169_pcierr_interrupt(struct net_device *dev)
 static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
 		   int budget)
 {
-	unsigned int dirty_tx, tx_left, bytes_compl = 0, pkts_compl = 0;
+	unsigned int dirty_tx, bytes_compl = 0, pkts_compl = 0;
 
 	dirty_tx = tp->dirty_tx;
 
-	for (tx_left = READ_ONCE(tp->cur_tx) - dirty_tx; tx_left; tx_left--) {
+	while (READ_ONCE(tp->cur_tx) != dirty_tx) {
 		unsigned int entry = dirty_tx % NUM_TX_DESC;
 		struct sk_buff *skb = tp->tx_skb[entry].skb;
 		u32 status;
@@ -4389,7 +4389,6 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
 		netdev_completed_queue(dev, pkts_compl, bytes_compl);
 		dev_sw_netstats_tx_add(dev, pkts_compl, bytes_compl);
 
-		tp->dirty_tx = dirty_tx;
 		/* Sync with rtl8169_start_xmit:
 		 * - publish dirty_tx ring index (write barrier)
 		 * - refresh cur_tx ring index and queue status (read barrier)
@@ -4397,7 +4396,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
 		 * a racing xmit thread can only have a right view of the
 		 * ring status.
 		 */
-		smp_mb();
+		smp_store_mb(tp->dirty_tx, dirty_tx);
 		if (netif_queue_stopped(dev) &&
 		    rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) {
 			netif_wake_queue(dev);