[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAJZOPZLZNEvao9PxtX78sfpg_4GVamgxNMNU52QQ1aFqAxQDZA@mail.gmail.com>
Date: Mon, 6 Jan 2014 18:38:25 +0200
From: Or Gerlitz <or.gerlitz@...il.com>
To: Tom Herbert <therbert@...gle.com>
Cc: Or Gerlitz <ogerlitz@...lanox.com>, Jerry Chu <hkchu@...gle.com>,
Eric Dumazet <edumazet@...gle.com>,
Herbert Xu <herbert@...dor.apana.org.au>,
Linux Netdev List <netdev@...r.kernel.org>,
David Miller <davem@...emloft.net>,
Yan Burman <yanb@...lanox.com>,
Shlomo Pongratz <shlomop@...lanox.com>
Subject: Re: [PATCH V1 net-next 2/2] net: Add UDP GRO support for vxlan traffic
On Mon, Jan 6, 2014 at 3:32 PM, Or Gerlitz <or.gerlitz@...il.com> wrote:
> As the GUE RFC states, with UDP encapsulation, the encap protocol is
> actually derived from the UDP destination port. With that assumption
> at hand, we can have the udp gro code to export callbacks for upper
> uncapsulation protocol to install a gro handler which has the
> following trivial strucure:
>
> key = <PORT> data = <gro receive/complete callbacks>
> which plugs nicely into the general framework of the gro stack. The
> udp gro receive code would act as follows
> -- if there's no gro handler set for the packet udp dest port, flush
> - do the normal loop to find match on the packet dest/src udp ports
> - call the protocol (e.g VXLAN) gro receive callback
> This would avoid dealing with sockets etc and be very efficient, makes sense?
Or in short -- the destination udp port takes a similar role to the
ethertype for gro l3 handlers or the ip protocol for gro l4 handlers
and we enable encapsulating protocols to plug into the existing
offload_callbacks framework, simple.
--
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