[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CALx6S35V47scFFQab7ZsQyh6CktS17w4hSKZSVAnOB0Ppa7brg@mail.gmail.com>
Date: Fri, 29 Jan 2016 15:00:34 -0800
From: Tom Herbert <tom@...bertland.com>
To: Sowmini Varadhan <sowmini.varadhan@...cle.com>
Cc: Eric Dumazet <eric.dumazet@...il.com>,
Michael Dalton <mwdalton@...gle.com>,
Linux Kernel Network Developers <netdev@...r.kernel.org>
Subject: Re: [RFC] Kernel unaligned access at __skb_flow_dissect
On Fri, Jan 29, 2016 at 1:09 PM, Sowmini Varadhan
<sowmini.varadhan@...cle.com> wrote:
> On (01/29/16 13:00), Tom Herbert wrote:
>> Doesn't every IP/VXLAN packet contains unaligned headers? Why don't
>> those create alignment issues (like when stack looks at addresses)?
>
> They do.
>
> http://comments.gmane.org/gmane.linux.network/370672
>
> some of it was fixed in https://lkml.org/lkml/2015/7/20/63.
> There's still some NET_IP_ALIGN missing. IIRC, I was seeing
> this for mldv3, but the fix has to be done carefully, by
> someone who knows how to fully regression test it.
>
> I dont know if other tunneling methods manage to get the
> NET_IP_ALIGN correct in every case.
>
> Also, while sparc complains about unaligned access
> in most cases, some sins may pass under the radar, and other
> platforms dont even generate traps, so it's easy to not know
> that there's a problem, a lot of the time.
>
The sparc documentation is pretty clear
http://docs.oracle.com/cd/E19253-01/816-4854/hwovr-2/index.html, seems
like unaligned accesses are not allowed in the architecture.
Tom
> --Sowmini
>
Powered by blists - more mailing lists