[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20110211063753.GA29940@gondor.apana.org.au>
Date: Fri, 11 Feb 2011 17:37:53 +1100
From: Herbert Xu <herbert@...dor.apana.org.au>
To: David Miller <davem@...emloft.net>
Cc: netdev@...r.kernel.org, netfilter-devel@...r.kernel.org
Subject: Re: GRO/GSO hiding PMTU?
On Thu, Feb 10, 2011 at 10:22:16PM -0800, David Miller wrote:
>
> I gave it a shot but it isn't easy. We can figure out the length of
> the IP headers just fine, but the rest of the value we need to add
> to the MSS (the TCP header length) is transport specific which kind
> of implies a transport dependent gso proto op of some sort.
That's pretty much where I gave up :)
> Or we just hack it, admit that only TCP creates GSO packets, and
> directly check for TCP protcol and then inspect the TCP header
> length :-)
Sure we can do that for now.
What I wanted to do if I ever get enough time to work on this is
to record the transport header length in a gso_hlen field so we
can fix this properly.
We currently have a useless gso_segs field that only has one or
two users that don't even need it. We could easily get rid of it
and use that space for gso_hlen instead.
The gso_hlen field only needs to be filled in at the few spots
that generate GSO packets, i.e.,
1) TCP
2) Virt backends like tun.c
3) GRO
Cheers,
--
Email: Herbert Xu <herbert@...dor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
--
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
Powered by blists - more mailing lists