* [PATCH net-next] net: keep original skb which only needs header checking during software GSO
@ 2014-09-19 6:38 Jason Wang
2014-09-19 7:04 ` Eric Dumazet
0 siblings, 1 reply; 3+ messages in thread
From: Jason Wang @ 2014-09-19 6:38 UTC (permalink / raw)
To: davem, netdev, linux-kernel; +Cc: Jason Wang
Commit ce93718fb7cdbc064c3000ff59e4d3200bdfa744 ("net: Don't keep
around original SKB when we software segment GSO frames") frees the
original skb after software GSO even for dodgy gso skbs. This breaks
the stream throughput from untrusted sources, since only header
checking was done during software GSO instead of a true
segmentation. This patch fixes this by freeing the original gso skb
only when it was really segmented by software.
Fixes ce93718fb7cdbc064c3000ff59e4d3200bdfa744 ("net: Don't keep
around original SKB when we software segment GSO frames.")
CC: David S. Miller <davem@davemloft.net>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
net/core/dev.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index e916ba8..b7a0e1d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2694,10 +2694,12 @@ struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
struct sk_buff *segs;
segs = skb_gso_segment(skb, features);
- kfree_skb(skb);
if (IS_ERR(segs))
segs = NULL;
- skb = segs;
+ else if (segs) {
+ kfree_skb(skb);
+ skb = segs;
+ }
} else {
if (skb_needs_linearize(skb, features) &&
__skb_linearize(skb))
--
1.9.1
^ permalink raw reply related [flat|nested] 3+ messages in thread* Re: [PATCH net-next] net: keep original skb which only needs header checking during software GSO
2014-09-19 6:38 [PATCH net-next] net: keep original skb which only needs header checking during software GSO Jason Wang
@ 2014-09-19 7:04 ` Eric Dumazet
2014-09-19 7:49 ` Jason Wang
0 siblings, 1 reply; 3+ messages in thread
From: Eric Dumazet @ 2014-09-19 7:04 UTC (permalink / raw)
To: Jason Wang; +Cc: davem, netdev, linux-kernel
On Fri, 2014-09-19 at 14:38 +0800, Jason Wang wrote:
> Commit ce93718fb7cdbc064c3000ff59e4d3200bdfa744 ("net: Don't keep
> around original SKB when we software segment GSO frames") frees the
> original skb after software GSO even for dodgy gso skbs. This breaks
> the stream throughput from untrusted sources, since only header
> checking was done during software GSO instead of a true
> segmentation. This patch fixes this by freeing the original gso skb
> only when it was really segmented by software.
>
> Fixes ce93718fb7cdbc064c3000ff59e4d3200bdfa744 ("net: Don't keep
> around original SKB when we software segment GSO frames.")
>
> CC: David S. Miller <davem@davemloft.net>
> Signed-off-by: Jason Wang <jasowang@redhat.com>
> ---
> net/core/dev.c | 6 ++++--
> 1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/net/core/dev.c b/net/core/dev.c
> index e916ba8..b7a0e1d 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -2694,10 +2694,12 @@ struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
> struct sk_buff *segs;
>
> segs = skb_gso_segment(skb, features);
> - kfree_skb(skb);
> if (IS_ERR(segs))
>
> - skb = segs;
> + else if (segs) {
> + kfree_skb(skb);
> + skb = segs;
> + }
> } else {
> if (skb_needs_linearize(skb, features) &&
> __skb_linearize(skb))
Good catch !
While we are at it, could you use consume_skb() instead of kfree_skb(),
and add missing {} (CodingStyle) ?
if (IS_ERR(segs)) {
segs = NULL;
} else if (segs) {
consume_skb(skb);
skb = segs;
}
Thanks !
^ permalink raw reply [flat|nested] 3+ messages in thread* Re: [PATCH net-next] net: keep original skb which only needs header checking during software GSO
2014-09-19 7:04 ` Eric Dumazet
@ 2014-09-19 7:49 ` Jason Wang
0 siblings, 0 replies; 3+ messages in thread
From: Jason Wang @ 2014-09-19 7:49 UTC (permalink / raw)
To: Eric Dumazet; +Cc: davem, netdev, linux-kernel
On 09/19/2014 03:04 PM, Eric Dumazet wrote:
> On Fri, 2014-09-19 at 14:38 +0800, Jason Wang wrote:
>> Commit ce93718fb7cdbc064c3000ff59e4d3200bdfa744 ("net: Don't keep
>> around original SKB when we software segment GSO frames") frees the
>> original skb after software GSO even for dodgy gso skbs. This breaks
>> the stream throughput from untrusted sources, since only header
>> checking was done during software GSO instead of a true
>> segmentation. This patch fixes this by freeing the original gso skb
>> only when it was really segmented by software.
>>
>> Fixes ce93718fb7cdbc064c3000ff59e4d3200bdfa744 ("net: Don't keep
>> around original SKB when we software segment GSO frames.")
>>
>> CC: David S. Miller <davem@davemloft.net>
>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>> ---
>> net/core/dev.c | 6 ++++--
>> 1 file changed, 4 insertions(+), 2 deletions(-)
>>
>> diff --git a/net/core/dev.c b/net/core/dev.c
>> index e916ba8..b7a0e1d 100644
>> --- a/net/core/dev.c
>> +++ b/net/core/dev.c
>> @@ -2694,10 +2694,12 @@ struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
>> struct sk_buff *segs;
>>
>> segs = skb_gso_segment(skb, features);
>> - kfree_skb(skb);
>> if (IS_ERR(segs))
>>
>> - skb = segs;
>> + else if (segs) {
>> + kfree_skb(skb);
>> + skb = segs;
>> + }
>> } else {
>> if (skb_needs_linearize(skb, features) &&
>> __skb_linearize(skb))
> Good catch !
>
> While we are at it, could you use consume_skb() instead of kfree_skb(),
> and add missing {} (CodingStyle) ?
>
> if (IS_ERR(segs)) {
> segs = NULL;
> } else if (segs) {
> consume_skb(skb);
> skb = segs;
> }
>
>
> Thanks !
>
>
Yes, it's better. Will do them in V2.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2014-09-19 7:49 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-09-19 6:38 [PATCH net-next] net: keep original skb which only needs header checking during software GSO Jason Wang
2014-09-19 7:04 ` Eric Dumazet
2014-09-19 7:49 ` Jason Wang
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).