netdev - Re: unexpected GRO/veth behavior

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 11 Sep 2018 08:42:42 -0700
From:   Eric Dumazet <eric.dumazet@...il.com>
To:     Paolo Abeni <pabeni@...hat.com>,
        Eric Dumazet <eric.dumazet@...il.com>, netdev@...r.kernel.org
Cc:     Toshiaki Makita <makita.toshiaki@....ntt.co.jp>
Subject: Re: unexpected GRO/veth behavior



On 09/11/2018 04:44 AM, Paolo Abeni wrote:
> On Tue, 2018-09-11 at 03:27 -0700, Eric Dumazet wrote:
>> On 09/10/2018 11:54 PM, Paolo Abeni wrote:
>>> I *think* we can hit a similar condition with a tun device in IFF_NAPI
>>> mode.
>>
>> Why ?
>>
>> tun_get_user() does not attach skb to a socket, that would be quite useless since skb
>>
> 	
> I think we can hit this code path:
> 
> tun_get_user() -> tun_alloc_skb() -> sock_alloc_send_pskb() ->
> skb_set_owner_w() 
> 
> Than later napi and GRO.
> 


No we can not.

Please look again.