[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20141122033603.22361.28896.stgit@ahduyck-server>
Date: Fri, 21 Nov 2014 19:37:09 -0800
From: Alexander Duyck <alexander.h.duyck@...hat.com>
To: netdev@...r.kernel.org
Cc: davem@...emloft.net
Subject: [net PATCH] ipv6: Do not treat a GSO_TCPV4 request from UDP tunnel
over IPv6 as invalid
This patch adds SKB_GSO_TCPV4 to the list of supported GSO types handled by
the IPv6 GSO offloads. Without this change VXLAN tunnels running over IPv6
do not currently handle IPv4 TCP TSO requests correctly and end up handing
the non-segmented frame off to the device.
Below is the before and after for a simple netperf TCP_STREAM test between
two endpoints tunneling IPv4 over a VXLAN tunnel running on IPv6 on top of
a 1Gb/s network adapter.
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
87380 16384 16384 10.29 0.88 Before
87380 16384 16384 10.03 895.69 After
Signed-off-by: Alexander Duyck <alexander.h.duyck@...hat.com>
---
net/ipv6/ip6_offload.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index a071563..01e12d0 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -69,7 +69,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
int nhoff;
if (unlikely(skb_shinfo(skb)->gso_type &
- ~(SKB_GSO_UDP |
+ ~(SKB_GSO_TCPV4 |
+ SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists