lkml.org 
[lkml]   [2010]   [Aug]   [24]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[58/91] net: Fix napi_gro_frags vs netpoll path
2.6.34-stable review patch.  If anyone has any objections, please let us know.

------------------

From: Jarek Poplawski <jarkao2@gmail.com>

[ Upstream commit ce9e76c8450fc248d3e1fc16ef05e6eb50c02fa5 ]

The netpoll_rx_on() check in __napi_gro_receive() skips part of the
"common" GRO_NORMAL path, especially "pull:" in dev_gro_receive(),
where at least eth header should be copied for entirely paged skbs.

Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
net/core/dev.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2666,7 +2666,7 @@ enum gro_result dev_gro_receive(struct n
int mac_len;
enum gro_result ret;

- if (!(skb->dev->features & NETIF_F_GRO))
+ if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
goto normal;

if (skb_is_gso(skb) || skb_has_frags(skb))
@@ -2753,9 +2753,6 @@ __napi_gro_receive(struct napi_struct *n
{
struct sk_buff *p;

- if (netpoll_rx_on(skb))
- return GRO_NORMAL;
-
for (p = napi->gro_list; p; p = p->next) {
NAPI_GRO_CB(p)->same_flow =
(p->dev == skb->dev) &&



\
 
 \ /
  Last update: 2010-08-25 01:37    [from the cache]
©2003-2011 Jasper Spaans