From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Graf Subject: Re: [PATCH v1 1/6] net: Generalize udp based tunnel offload Date: Wed, 9 Dec 2015 23:25:44 +0100 Message-ID: <20151209222544.GF11201@pox.localdomain> References: <20151209125857.GA9900@pox.localdomain> <20151209173842.GA18097@ast-mbp.thefacebook.com> <20151209220339.GD11201@pox.localdomain> <20151209.172128.2004885848439372720.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: alexei.starovoitov@gmail.com, jhs@mojatatu.com, john.fastabend@gmail.com, tom@herbertland.com, hannes@stressinduktion.org, linville@tuxdriver.com, jesse@kernel.org, anjali.singhai@intel.com, netdev@vger.kernel.org, kiran.patil@intel.com To: David Miller Return-path: Received: from mail-wm0-f41.google.com ([74.125.82.41]:33774 "EHLO mail-wm0-f41.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752788AbbLIWZq (ORCPT ); Wed, 9 Dec 2015 17:25:46 -0500 Received: by mail-wm0-f41.google.com with SMTP id c201so6589999wme.0 for ; Wed, 09 Dec 2015 14:25:46 -0800 (PST) Content-Disposition: inline In-Reply-To: <20151209.172128.2004885848439372720.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On 12/09/15 at 05:21pm, David Miller wrote: > It is clearly the most appropriate middle layer representation. > > The fact that BPF could be generated from any P4 program, yet the > reverse is not true, tells me everything I need to know. > > I'm sorry if you have either a mental or a time invenstment in P4, but > I really don't see it as really suitable for this. I don't. I like the approach and the effect it has on a currently very vendor secrets oriented environment. I won't drag this further. I'm perfectly fine if BPF is suitable for a wide range of hardware models.