gro: Avoid copying headers of unmerged packets

Unfortunately simplicity isn't always the best.  The fraginfo
interface turned out to be suboptimal.  The problem was quite
obvious.  For every packet, we have to copy the headers from
the frags structure into skb->head, even though for 99% of the
packets this part is immediately thrown away after the merge.

LRO didn't have this problem because it directly read the headers
from the frags structure.

This patch attempts to address this by creating an interface
that allows GRO to access the headers in the first frag without
having to copy it.  Because all drivers that use frags place the
headers in the first frag this optimisation should be enough.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 21 insertions, 11 deletions

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c802bc1658a8..bd91eadcbe3f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -799,24 +799,34 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
         int proto;
         __wsum csum;
 
-        if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
+        iph = skb_gro_header(skb, sizeof(*iph));
+        if (unlikely(!iph))
                 goto out;
 
-        iph = ipv6_hdr(skb);
-        __skb_pull(skb, sizeof(*iph));
+        skb_gro_pull(skb, sizeof(*iph));
+        skb_set_transport_header(skb, skb_gro_offset(skb));
 
-        flush += ntohs(iph->payload_len) != skb->len;
+        flush += ntohs(iph->payload_len) != skb_gro_len(skb);
 
         rcu_read_lock();
-        proto = ipv6_gso_pull_exthdrs(skb, iph->nexthdr);
-        iph = ipv6_hdr(skb);
-        IPV6_GRO_CB(skb)->proto = proto;
+        proto = iph->nexthdr;
         ops = rcu_dereference(inet6_protos[proto]);
-        if (!ops || !ops->gro_receive)
-                goto out_unlock;
+        if (!ops || !ops->gro_receive) {
+                __pskb_pull(skb, skb_gro_offset(skb));
+                proto = ipv6_gso_pull_exthdrs(skb, proto);
+                skb_gro_pull(skb, -skb_transport_offset(skb));
+                skb_reset_transport_header(skb);
+                __skb_push(skb, skb_gro_offset(skb));
+
+                if (!ops || !ops->gro_receive)
+                        goto out_unlock;
+
+                iph = ipv6_hdr(skb);
+        }
+
+        IPV6_GRO_CB(skb)->proto = proto;
 
         flush--;
-        skb_reset_transport_header(skb);
         nlen = skb_network_header_len(skb);
 
         for (p = *head; p; p = p->next) {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e5b85d45bee8..00f1269e11e9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -948,7 +948,7 @@ struct sk_buff **tcp6_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 
         switch (skb->ip_summed) {
         case CHECKSUM_COMPLETE:
-                if (!tcp_v6_check(skb->len, &iph->saddr, &iph->daddr,
+                if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr,
                                   skb->csum)) {
                         skb->ip_summed = CHECKSUM_UNNECESSARY;
                         break;