summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorHerbert Xu <herbert@gondor.apana.org.au>2009-04-14 15:11:06 -0700
committerDavid S. Miller <davem@davemloft.net>2009-04-14 15:11:06 -0700
commitfc59f9a3bf8096a1f68a8b78ada7a0e0ab9236b2 (patch)
treed713e3270eafb70bb6af27dd2bbdc84b1a2c8c79 /net
parentce8632ba6b3ed0bf2efa98672e2808de34250389 (diff)
downloadlinux-3.10-fc59f9a3bf8096a1f68a8b78ada7a0e0ab9236b2.tar.gz
linux-3.10-fc59f9a3bf8096a1f68a8b78ada7a0e0ab9236b2.tar.bz2
linux-3.10-fc59f9a3bf8096a1f68a8b78ada7a0e0ab9236b2.zip
gro: Restore correct value to gso_size
Since everybody has been focusing on baremetal GRO performance no one noticed when I added a bug that zapped gso_size for all GRO packets. This only gets picked up when you forward the skb out of an interface. Thanks to Mark Wagner for noticing this bug when testing kvm. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/core/dev.c5
1 files changed, 3 insertions, 2 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index ea8eb2214b0..343883f65ea 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2328,8 +2328,10 @@ static int napi_gro_complete(struct sk_buff *skb)
struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
int err = -ENOENT;
- if (NAPI_GRO_CB(skb)->count == 1)
+ if (NAPI_GRO_CB(skb)->count == 1) {
+ skb_shinfo(skb)->gso_size = 0;
goto out;
+ }
rcu_read_lock();
list_for_each_entry_rcu(ptype, head, list) {
@@ -2348,7 +2350,6 @@ static int napi_gro_complete(struct sk_buff *skb)
}
out:
- skb_shinfo(skb)->gso_size = 0;
return netif_receive_skb(skb);
}