* [net PATCH] ipv6: Do not treat a GSO_TCPV4 request from UDP tunnel over IPv6 as invalid
@ 2014-11-22 3:37 Alexander Duyck
2014-11-23 19:18 ` David Miller
0 siblings, 1 reply; 2+ messages in thread
From: Alexander Duyck @ 2014-11-22 3:37 UTC (permalink / raw)
To: netdev; +Cc: davem
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@redhat.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 |
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [net PATCH] ipv6: Do not treat a GSO_TCPV4 request from UDP tunnel over IPv6 as invalid
2014-11-22 3:37 [net PATCH] ipv6: Do not treat a GSO_TCPV4 request from UDP tunnel over IPv6 as invalid Alexander Duyck
@ 2014-11-23 19:18 ` David Miller
0 siblings, 0 replies; 2+ messages in thread
From: David Miller @ 2014-11-23 19:18 UTC (permalink / raw)
To: alexander.h.duyck; +Cc: netdev
From: Alexander Duyck <alexander.h.duyck@redhat.com>
Date: Fri, 21 Nov 2014 19:37:09 -0800
> 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@redhat.com>
Applied, thank you.
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2014-11-23 19:18 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-11-22 3:37 [net PATCH] ipv6: Do not treat a GSO_TCPV4 request from UDP tunnel over IPv6 as invalid Alexander Duyck
2014-11-23 19:18 ` David Miller
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).