tunnels: Optimize tx path

We currently dirty a cache line to update tunnel device stats
(tx_packets/tx_bytes). We better use the txq->tx_bytes/tx_packets
counters that already are present in cpu cache, in the cache
line shared with txq->_xmit_lock

This patch extends IPTUNNEL_XMIT() macro to use txq pointer
provided by the caller.

Also &tunnel->dev->stats can be replaced by &dev->stats

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 3 insertions, 2 deletions

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 41ada9904d31..89ff9d5b1500 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -662,7 +662,8 @@ drop_nolock:
 static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 {
         struct ip_tunnel *tunnel = netdev_priv(dev);
-        struct net_device_stats *stats = &tunnel->dev->stats;
+        struct net_device_stats *stats = &dev->stats;
+        struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
         struct iphdr  *old_iph = ip_hdr(skb);
         struct iphdr  *tiph;
         u8     tos;
@@ -810,7 +811,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
                 struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
                 if (!new_skb) {
                         ip_rt_put(rt);
-                        stats->tx_dropped++;
+                        txq->tx_dropped++;
                         dev_kfree_skb(skb);
                         return NETDEV_TX_OK;
                 }