[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <51bc118ff452c42fef489818422f278ab79e6dd4.camel@redhat.com>
Date: Thu, 12 May 2022 11:02:19 +0200
From: Paolo Abeni <pabeni@...hat.com>
To: Saeed Mahameed <saeedm@...dia.com>,
Eric Dumazet <eric.dumazet@...il.com>
Cc: "David S . Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>,
netdev <netdev@...r.kernel.org>,
Alexander Duyck <alexanderduyck@...com>,
Coco Li <lixiaoyan@...gle.com>,
Eric Dumazet <edumazet@...gle.com>,
Tariq Toukan <tariqt@...dia.com>,
Leon Romanovsky <leon@...nel.org>
Subject: Re: [PATCH v6 net-next 13/13] mlx5: support BIG TCP packets
On Thu, 2022-05-12 at 01:40 -0700, Saeed Mahameed wrote:
> On 09 May 20:32, Eric Dumazet wrote:
> > From: Coco Li <lixiaoyan@...gle.com>
> >
> > mlx5 supports LSOv2.
> >
> > IPv6 gro/tcp stacks insert a temporary Hop-by-Hop header
> > with JUMBO TLV for big packets.
> >
> > We need to ignore/skip this HBH header when populating TX descriptor.
> >
>
> Sorry i didn't go through all the documentations or previous discussions,
> please bare with me, so why not clear HBH just before calling the
> driver xmit ndo ?
I guess this way is more efficient: the driver copies IP hdr and TCP
hdr directly in the correct/final location into the tx descriptor,
otherwise the caller would have to memmove L2/L3 just before the driver
copies them again.
>
> Or if HBH has to stick,
My understanding is that this is not the case.
Cheers,
Paolo
Powered by blists - more mailing lists