[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAE4R7bALEVb1reyCzfXXi=ifv97jy14ozQuxnG6x9BWmWX10Hg@mail.gmail.com>
Date: Mon, 2 Mar 2015 09:00:58 -0800
From: Scott Feldman <sfeldma@...il.com>
To: roopa <roopa@...ulusnetworks.com>
Cc: Netdev <netdev@...r.kernel.org>,
"David S. Miller" <davem@...emloft.net>,
Jiří Pírko <jiri@...nulli.us>
Subject: Re: [PATCH net-next v2 4/4] switchdev: don't support custom ip rules,
for now
On Mon, Mar 2, 2015 at 6:36 AM, roopa <roopa@...ulusnetworks.com> wrote:
> On 3/2/15, 2:06 AM, sfeldma@...il.com wrote:
>>
>> From: Scott Feldman <sfeldma@...il.com>
>>
>> Keep switchdev FIB offload model simple for now and don't allow custom ip
>> rules.
>>
>> Signed-off-by: Scott Feldman <sfeldma@...il.com>
>
>
> I don't see a need to do this. And seems very aggressive.
> Also, note that the rules in a system can be on non-hw accelerated ports.
It is aggressive but it's the safest choice for the first pass on this
L3 offload. Without, switchdev has no way to model custom ip rules
down to hardware. Let's start with this aggressive case, and that'll
force us to work on relaxing it.
> Until rules are hw accelerated, its ok to document this limitation for hw
> accelerated routes in my opinion.
>
--
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