From: Eric Dumazet
Date: Sun, 01 Nov 2015 15:36:55 -0800
> From: Eric Dumazet
>
> skb_set_owner_w() is called from various places that assume
> skb->sk always point to a full blown socket (as it changes
> sk->sk_wmem_alloc)
>
> We'd like to attach skb to request sockets, and in the future
> to
From: Eric Dumazet
Date: Mon, 02 Nov 2015 12:09:25 -0800
> On Mon, 2015-11-02 at 20:05 +, Haiyang Zhang wrote:
>
>> Thanks for the fix!
>> For some driver, like ours, this condition may not be "unlikely".
>> So could you remove the "unlikely"?
>
> No, I wont remove the unlikely.
>
> Look,
On Mon, 2015-11-02 at 20:05 +, Haiyang Zhang wrote:
> Thanks for the fix!
> For some driver, like ours, this condition may not be "unlikely".
> So could you remove the "unlikely"?
No, I wont remove the unlikely.
Look, your main issue is about reallocating skbs, because of excessive
dev->need
> -Original Message-
> From: Eric Dumazet [mailto:eric.duma...@gmail.com]
> Sent: Sunday, November 1, 2015 6:37 PM
> To: David Miller
> Cc: Haiyang Zhang ; eduma...@google.com;
> netdev@vger.kernel.org; KY Srinivasan
> Subject: [PATCH v2 net-next] net: make s
From: Eric Dumazet
skb_set_owner_w() is called from various places that assume
skb->sk always point to a full blown socket (as it changes
sk->sk_wmem_alloc)
We'd like to attach skb to request sockets, and in the future
to timewait sockets as well. For these kind of pseudo sockets,
we need to tak
