Merge branch 'r8169-revert-two-commits-due-to-a-regression'

Heiner Kallweit says:

====================
r8169: revert two commits due to a regression

Sander reported a regression (kernel panic, see[1]), therefore let's
revert these commits. Removal of the barriers doesn't seem to
contribute to the issue, the patch just overlaps with the problematic
one and only reverting both patches was tested.

[1] https://marc.info/?t=154965066400001&r=1&w=2

v2:
- improve commit message
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/realtek/r8169.c

@@ -1286,11 +1286,13 @@ static u16 rtl_get_events(struct rtl8169_private *tp)
 static void rtl_ack_events(struct rtl8169_private *tp, u16 bits)
 {
 	RTL_W16(tp, IntrStatus, bits);
+	mmiowb();
 }
 
 static void rtl_irq_disable(struct rtl8169_private *tp)
 {
 	RTL_W16(tp, IntrMask, 0);
+	mmiowb();
 }
 
 #define RTL_EVENT_NAPI_RX	(RxOK | RxErr)
@@ -6072,7 +6074,6 @@ 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))) {
@@ -6114,6 +6115,8 @@ 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 */
@@ -6126,14 +6129,16 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	tp->cur_tx += frags + 1;
 
-	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);
 
-	if (unlikely(stop_queue)) {
+	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();
+		netif_stop_queue(dev);
 		/* Sync with rtl_tx:
 		 * - publish queue status and cur_tx ring index (write barrier)
 		 * - refresh dirty_tx ring index (read barrier).
@@ -6483,7 +6488,9 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
 
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
+
 		rtl_irq_enable(tp);
+		mmiowb();
 	}
 
 	return work_done;