net: output path optimizations

1) Avoid dirtying neighbour's confirmed field.

  TCP workloads hits this cache line for each incoming ACK.
  Lets write n->confirmed only if there is a jiffie change.

2) Optimize neigh_hh_output() for the common Ethernet case, were
   hh_len is less than 16 bytes. Replace the memcpy() call
   by two inlined 64bit load/stores on x86_64.

Bench results using udpflood test, with -C option (MSG_CONFIRM flag
added to sendto(), to reproduce the n->confirmed dirtying on UDP)

24 threads doing 1.000.000 UDP sendto() on dummy device, 4 runs.

before : 2.247s, 2.235s, 2.247s, 2.318s
after  : 1.884s, 1.905s, 1.891s, 1.895s

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 9 insertions, 5 deletions

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 344d8988842a..0dab173e27da 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -334,18 +334,22 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
 }
 #endif
 
-static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb)
+static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
 {
         unsigned int seq;
         int hh_len;
 
         do {
-                int hh_alen;
-
                 seq = read_seqbegin(&hh->hh_lock);
                 hh_len = hh->hh_len;
-                hh_alen = HH_DATA_ALIGN(hh_len);
-                memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
+                if (likely(hh_len <= HH_DATA_MOD)) {
+                        /* this is inlined by gcc */
+                        memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD);
+                } else {
+                        int hh_alen = HH_DATA_ALIGN(hh_len);
+
+                        memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
+                }
         } while (read_seqretry(&hh->hh_lock, seq));
 
         skb_push(skb, hh_len);