net: stmmac: Re-work the queue selection for TSO packets

[ Upstream commit 4993e5b37e8bcb55ac90f76eb6d2432647273747 ]

Ben Hutchings says:
	"This is the wrong place to change the queue mapping.
	stmmac_xmit() is called with a specific TX queue locked,
	and accessing a different TX queue results in a data race
	for all of that queue's state.

	I think this commit should be reverted upstream and in all
	stable branches.  Instead, the driver should implement the
	ndo_select_queue operation and override the queue mapping there."

Fixes: c5acdbee22a1 ("net: stmmac: Send TSO packets always from Queue 0")
Suggested-by: NBen Hutchings <ben@decadent.org.uk>
Signed-off-by: NJose Abreu <joabreu@synopsys.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -3036,18 +3036,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Manage oversized TCP frames for GMAC4 device */
 	if (skb_is_gso(skb) && priv->tso) {
-		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
-			/*
-			 * There is no way to determine the number of TSO
-			 * capable Queues. Let's use always the Queue 0
-			 * because if TSO is supported then at least this
-			 * one will be capable.
-			 */
-			skb_set_queue_mapping(skb, 0);
-
+		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))
 			return stmmac_tso_xmit(skb, dev);
 	}
-	}
 
 	if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) {
 		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) {
@@ -3855,6 +3846,23 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	}
 }
 
+static u16 stmmac_select_queue(struct net_device *dev, struct sk_buff *skb,
+			       struct net_device *sb_dev,
+			       select_queue_fallback_t fallback)
+{
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+		/*
+		 * There is no way to determine the number of TSO
+		 * capable Queues. Let's use always the Queue 0
+		 * because if TSO is supported then at least this
+		 * one will be capable.
+		 */
+		return 0;
+	}
+
+	return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
+}
+
 static int stmmac_set_mac_address(struct net_device *ndev, void *addr)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
@@ -4097,6 +4105,7 @@ static const struct net_device_ops stmmac_netdev_ops = {
 	.ndo_tx_timeout = stmmac_tx_timeout,
 	.ndo_do_ioctl = stmmac_ioctl,
 	.ndo_setup_tc = stmmac_setup_tc,
+	.ndo_select_queue = stmmac_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = stmmac_poll_controller,
 #endif