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, 3 deletions

diff --git a/include/net/ipip.h b/include/net/ipip.h
index 87acf8f3a155..0159221a8509 100644
--- a/include/net/ipip.h
+++ b/include/net/ipip.h
@@ -42,9 +42,9 @@ struct ip_tunnel_prl_entry
         ip_select_ident(iph, &rt->u.dst, NULL);                         \
                                                                         \
         err = ip_local_out(skb);                                        \
-        if (net_xmit_eval(err) == 0) {                                  \
-                stats->tx_bytes += pkt_len;                             \
-                stats->tx_packets++;                                    \
+        if (likely(net_xmit_eval(err) == 0)) {                          \
+                txq->tx_bytes += pkt_len;                               \
+                txq->tx_packets++;                                      \
         } else {                                                        \
                 stats->tx_errors++;                                     \
                 stats->tx_aborted_errors++;                             \