[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20220614091438.3d0665d9@kernel.org>
Date: Tue, 14 Jun 2022 09:14:38 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Paolo Abeni <pabeni@...hat.com>
Cc: Lior Nahmanson <liorna@...dia.com>, edumazet@...gle.com,
davem@...emloft.net, netdev@...r.kernel.org,
Raed Salem <raeds@...dia.com>, Jiri Pirko <jiri@...dia.com>,
Ben Ben-Ishay <benishay@...dia.com>
Subject: Re: [PATCH net-next v3 2/3] net/macsec: Add MACsec skb extension Rx
Data path support
On Tue, 14 Jun 2022 15:55:13 +0200 Paolo Abeni wrote:
> The main reason I suggested to look for the a possible alternative to
> the skb extension is that the GRO stage is becoming bigger (and slower)
> with any of such addition.
>
> The 'slow_gro' protects the common use-case from any additional
> conditionals and intructions, I still have some concerns due to the
> increased code size.
>
> This is not a reject, I'm mostly looking for a 2nd opinion.
Shooting from the hip a little bit, but macsec being a tightly bound L2
upper maybe metadata dst is a workable solution for carrying the sci and
offload status between upper and lower? The range of values should be
well known and limited.
Powered by blists - more mailing lists