From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jiri Pirko Subject: Re: [PATCH net-next 0/8] nfp: offload LAG for tc flower egress Date: Wed, 30 May 2018 22:29:54 +0200 Message-ID: <20180530202954.GF2010@nanopsycho> References: <20180524022255.18548-1-jakub.kicinski@netronome.com> <20180525064809.GG2295@nanopsycho> <20180525194728.7aa4a116@cakuba> <20180529220947.GC2367@nanopsycho> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Jakub Kicinski , David Miller , Linux Netdev List , oss-drivers@netronome.com, Jay Vosburgh , Veaceslav Falico , Andy Gospodarek To: John Hurley Return-path: Received: from mail-pg0-f68.google.com ([74.125.83.68]:43474 "EHLO mail-pg0-f68.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932169AbeE3UaW (ORCPT ); Wed, 30 May 2018 16:30:22 -0400 Received: by mail-pg0-f68.google.com with SMTP id p8-v6so8639778pgq.10 for ; Wed, 30 May 2018 13:30:22 -0700 (PDT) Content-Disposition: inline In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: Wed, May 30, 2018 at 11:26:23AM CEST, john.hurley@netronome.com wrote: >On Tue, May 29, 2018 at 11:09 PM, Jiri Pirko wrote: >> Tue, May 29, 2018 at 04:08:48PM CEST, john.hurley@netronome.com wrote: >>>On Sat, May 26, 2018 at 3:47 AM, Jakub Kicinski >>> wrote: >>>> On Fri, 25 May 2018 08:48:09 +0200, Jiri Pirko wrote: >>>>> Thu, May 24, 2018 at 04:22:47AM CEST, jakub.kicinski@netronome.com wrote: >>>>> >Hi! >>>>> > >>>>> >This series from John adds bond offload to the nfp driver. Patch 5 >>>>> >exposes the hash type for NETDEV_LAG_TX_TYPE_HASH to make sure nfp >>>>> >hashing matches that of the software LAG. This may be unnecessarily >>>>> >conservative, let's see what LAG maintainers think :) >>>>> >>>>> So you need to restrict offload to only certain hash algo? In mlxsw, we >>>>> just ignore the lag setting and do some hw default hashing. Would not be >>>>> enough? Note that there's a good reason for it, as you see, in team, the >>>>> hashing is done in a BPF function and could be totally arbitrary. >>>>> Your patchset effectively disables team offload for nfp. >>>> >>>> My understanding is that the project requirements only called for L3/L4 >>>> hash algorithm offload, hence the temptation to err on the side of >>>> caution and not offload all the bond configurations. John can provide >>>> more details. Not being able to offload team is unfortunate indeed. >>> >>>Hi Jiri, >>>Yes, as Jakub mentions, we restrict ourselves to L3/L4 hash algorithm >>>as this is currently what is supported in fw. >> >> In mlxsw, a default l3/l4 is used always, no matter what the >> bonding/team sets. It is not correct, but it works with team as well. >> Perhaps we can have NETDEV_LAG_HASH_UNKNOWN to indicate to the driver to >> do some default? That would make the "team" offload functional. >> > >yes, I would agree with that. >Thanks Okay, would you please adjust your driver? I will teka care of mlxsw bits. Thanks! > >>>Hopefully this will change as fw features are expanded. >>>I understand the issue this presents with offloading team. >>>Perhaps resorting to a default hw hash for team is acceptable. >>>John