netdev - Re: Bogus frames transmitted with r8169 & fragmentation & large mtu

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]

Message-ID: <1329365963.2469.8.camel@edumazet-laptop>
Date:	Thu, 16 Feb 2012 05:19:23 +0100
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	Nick Bowler <nbowler@...iptictech.com>
Cc:	Francois Romieu <romieu@...zoreil.com>, netdev@...r.kernel.org,
	Realtek linux nic maintainers <nic_swsd@...ltek.com>
Subject: Re: Bogus frames transmitted with r8169 & fragmentation & large mtu

Le mercredi 15 février 2012 à 18:34 -0500, Nick Bowler a écrit :
> On 2012-02-15 23:41 +0100, Francois Romieu wrote:
> > Nick Bowler <nbowler@...iptictech.com> :
> > [...]
> > > Let me know if you need any more info,
> > 
> > Please send the XID line from the r8169 driver for this device.
> 
> This one?
> 
>   [   10.344571] r8169 0000:02:00.0: eth0: RTL8168d/8111d at 0xf8064000, bc:ae:c5:27:19:6f, XID 083000c0 IRQ 41
> 
> > Did you enable some offload feature (see 'ethtool -k') ?
> 
> Not beyond the defaults as far as I know.  Here's the ethtool -k output:
> 
>   Offload parameters for p10p1:
>   rx-checksumming: on
>   tx-checksumming: off
>   scatter-gather: off
>   tcp-segmentation-offload: off
>   udp-fragmentation-offload: off
>   generic-segmentation-offload: off
>   generic-receive-offload: on
>   large-receive-offload: off
>   rx-vlan-offload: on
>   tx-vlan-offload: on
>   ntuple-filters: off
>   receive-hashing: off
> 
> Thanks,

1) Are you using SLUB, SLAB, or SLOB ?

2) Problem with MTU=9000 is that frames span several 4K pages.

Maybe some versions of r8169 hardware have problems with that ...

3) We could check in xmit handler if the frames are correct before
sending them.  (Adding a trace of ICMP frames, and check if the payload
is all 0x42 filler or not) 



--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html