[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240620064546.16b0019e@kernel.org>
Date: Thu, 20 Jun 2024 06:45:46 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Michael Chan <michael.chan@...adcom.com>
Cc: davem@...emloft.net, netdev@...r.kernel.org, edumazet@...gle.com,
pabeni@...hat.com, pavan.chebbi@...adcom.com,
andrew.gospodarek@...adcom.com, Ajit Khaparde <ajit.khaparde@...adcom.com>,
Somnath Kotur <somnath.kotur@...adcom.com>
Subject: Re: [PATCH net 2/3] bnxt_en: Set TSO max segs on devices with
limits
On Wed, 19 Jun 2024 23:50:42 -0700 Michael Chan wrote:
> > If we're only going to see 0 or 2047 pulling in the FW interface update
> > and depending on newer FW version isn't a great way to fix this, IMHO.
>
> This issue only affects the newest chip which just started production
> and the production FW has this updated interface.
Hm, okay, I see this only needs to go back to 6.8.
> > TCP has min MSS of 500+ bytes, so 2k segments gives us 1MB LSO at min
> > legitimate segment size, right? So this is really just a protection
> > against bugs in the TCP stack, letting MSS slide below 100.
>
> That's true for Big TCP, but what about UDP GSO? Can UDP GSO exceed
> 2k segments?
I really don't think 2k segment limit is of any practical concern.
What I have seen for UDP GSO, since its used mostly for QUIC and mostly
on edge / in CDN - the speeds are much lower, so the QUIC stacks only
use sends of 16k or so.
Anyway, the "this is only needed in 6.8" convinced me, I'll apply.
Powered by blists - more mailing lists