All of lore.kernel.org
 help / color / mirror / Atom feed
From: Eric Dumazet <edumazet@google.com>
To: Alexander H Duyck <alexander.duyck@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
	"David S . Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	netdev <netdev@vger.kernel.org>, Coco Li <lixiaoyan@google.com>
Subject: Re: [PATCH v4 net-next 02/12] ipv6: add IFLA_GSO_IPV6_MAX_SIZE
Date: Fri, 6 May 2022 14:20:43 -0700	[thread overview]
Message-ID: <CANn89iL3sjnRKQNwbqxh_jh5cZ-Cxo58FKeqhP+mF969u4oQkA@mail.gmail.com> (raw)
In-Reply-To: <e582432dbe85e743cc18d358d020711db5ddbf82.camel@gmail.com>

On Fri, May 6, 2022 at 1:48 PM Alexander H Duyck
<alexander.duyck@gmail.com> wrote:
>
> On Fri, 2022-05-06 at 08:30 -0700, Eric Dumazet wrote:
> > From: Coco Li <lixiaoyan@google.com>
> >
> > This enables ipv6/TCP stacks to build TSO packets bigger than
> > 64KB if the driver is LSOv2 compatible.
> >
> > This patch introduces new variable gso_ipv6_max_size
> > that is modifiable through ip link.
> >
> > ip link set dev eth0 gso_ipv6_max_size 185000
> >
> > User input is capped by driver limit (tso_max_size)
> >
> > Signed-off-by: Coco Li <lixiaoyan@google.com>
> > Signed-off-by: Eric Dumazet <edumazet@google.com>
>
> So I am still not a fan of adding all this extra tooling to make an
> attribute that is just being applied to one protocol. Why not just
> allow gso_max_size to extend beyond 64K and only limit it by
> tso_max_size?

Answer is easy, and documented in our paper. Please read it.

We do not want to enable BIG TCP for IPv4, this breaks user space badly.

I do not want to break tcpdump just because some people think TCP just works.

>
> Doing that would make this patch much simpler as most of the code below
> could be dropped.
>

Sure, but no thanks.

  reply	other threads:[~2022-05-06 21:20 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-06 15:30 [PATCH v4 net-next 00/12] tcp: BIG TCP implementation Eric Dumazet
2022-05-06 15:30 ` [PATCH v4 net-next 01/12] net: add IFLA_TSO_{MAX_SIZE|SEGS} attributes Eric Dumazet
2022-05-06 15:30 ` [PATCH v4 net-next 02/12] ipv6: add IFLA_GSO_IPV6_MAX_SIZE Eric Dumazet
2022-05-06 20:48   ` Alexander H Duyck
2022-05-06 21:20     ` Eric Dumazet [this message]
2022-05-06 21:37       ` Alexander Duyck
2022-05-06 21:50         ` Eric Dumazet
2022-05-06 22:16           ` Alexander Duyck
2022-05-06 22:25             ` Eric Dumazet
2022-05-06 22:26             ` Jakub Kicinski
2022-05-06 22:46               ` Alexander Duyck
2022-05-06 15:30 ` [PATCH v4 net-next 03/12] tcp_cubic: make hystart_ack_delay() aware of BIG TCP Eric Dumazet
2022-05-06 15:30 ` [PATCH v4 net-next 04/12] ipv6: add struct hop_jumbo_hdr definition Eric Dumazet
2022-05-06 15:30 ` [PATCH v4 net-next 05/12] ipv6/gso: remove temporary HBH/jumbo header Eric Dumazet
2022-05-06 15:30 ` [PATCH v4 net-next 06/12] ipv6/gro: insert " Eric Dumazet
2022-05-06 15:30 ` [PATCH v4 net-next 07/12] ipv6: add IFLA_GRO_IPV6_MAX_SIZE Eric Dumazet
2022-05-06 21:06   ` Alexander H Duyck
2022-05-06 21:22     ` Eric Dumazet
2022-05-06 22:01       ` Alexander Duyck
2022-05-06 22:08         ` Eric Dumazet
2022-05-09 18:17       ` [PATCH 0/2] Replacements for patches 2 and 7 in Big TCP series Alexander Duyck
2022-05-09 18:17         ` [PATCH 1/2] net: Allow gso_max_size to exceed 65536 Alexander Duyck
2022-05-09 18:17         ` [PATCH 2/2] net: Allow gro_max_size " Alexander Duyck
2022-05-09 18:54         ` [PATCH 0/2] Replacements for patches 2 and 7 in Big TCP series Eric Dumazet
2022-05-09 20:21           ` Alexander H Duyck
2022-05-09 20:31             ` Eric Dumazet
2022-05-09 21:05               ` Alexander Duyck
2022-05-06 15:30 ` [PATCH v4 net-next 08/12] ipv6: Add hop-by-hop header to jumbograms in ip6_output Eric Dumazet
2022-05-06 15:30 ` [PATCH v4 net-next 09/12] net: loopback: enable BIG TCP packets Eric Dumazet
2022-05-06 15:30 ` [PATCH v4 net-next 10/12] veth: " Eric Dumazet
2022-05-06 22:33   ` Jakub Kicinski
2022-05-06 15:30 ` [PATCH v4 net-next 11/12] mlx4: support " Eric Dumazet
2022-05-06 15:30 ` [PATCH v4 net-next 12/12] mlx5: " Eric Dumazet
2022-05-06 22:34   ` Jakub Kicinski
2022-05-07  0:32     ` Eric Dumazet
2022-05-07  1:54       ` Jakub Kicinski
2022-05-07  1:54         ` Jakub Kicinski
2022-05-07  2:10         ` Eric Dumazet
2022-05-07  2:37           ` Jakub Kicinski
2022-05-07  2:43             ` Eric Dumazet
2022-05-07  7:16               ` Kees Cook
2022-05-07  7:23             ` Kees Cook
2022-05-07  6:57         ` Kees Cook
2022-05-07  7:46         ` Kees Cook
2022-05-07 11:19           ` Eric Dumazet
2022-05-09  8:05             ` David Laight
2022-05-09 23:20             ` Kees Cook

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CANn89iL3sjnRKQNwbqxh_jh5cZ-Cxo58FKeqhP+mF969u4oQkA@mail.gmail.com \
    --to=edumazet@google.com \
    --cc=alexander.duyck@gmail.com \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=kuba@kernel.org \
    --cc=lixiaoyan@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.