Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1391659

Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good.

From Ben Hutchings <ben@decadent.org.uk>
Newsgroups linux.kernel
Subject Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good.
Date 2016-04-30 21:30 +0200
Message-ID <rtIKu-4Aw-15@gated-at.bofh.it> (permalink)
References (2 earlier) <rsC4r-5HB-39@gated-at.bofh.it> <rsHGN-1Zc-1@gated-at.bofh.it> <rsHQu-23g-1@gated-at.bofh.it> <rsRwv-1zl-65@gated-at.bofh.it> <rsUum-3Xq-33@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

[Multipart message — attachments visible in raw view] - view raw

On Thu, 2016-04-28 at 06:45 -0700, Ben Greear wrote:
> 
> On 04/28/2016 03:29 AM, Sabrina Dubroca wrote:
[...]
> > Your use case is invalid, it just happened to work because of a
> > bug.  If you want the stack to fill checksums so that you want capture
> > and reinject packets, you have to disable checksum offloading (or
> > compute the checksum yourself in userspace).
> Disabling checksum offloading or computing in user-space (and then
> recomputing in veth to verify the checksum?) is a huge performance loss.
> 
> Maybe we could add a socket option to enable Cong's patch on a per-socket
> basis?  That way my use-case can still work and you can have this new
> behaviour by default?

It does sound like a useful option to have.  If there are other
applications that depend on veth's checksum-fixing behaviour and are
being distributed in binary form, then a per-device option might be
necessary so users can keep those applications working before they're
updated.

Ben.

-- 
Ben Hutchings
Tomorrow will be cancelled due to lack of interest.

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats  packets with bad checksums as good. Sabrina Dubroca <sd@queasysnail.net> - 2016-04-28 12:40 +0200
  Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Ben Greear <greearb@candelatech.com> - 2016-04-28 15:50 +0200
    Re: [PATCH 3.2 085/115] veth: don’t modify  ip_summed; doing so treats packets with bad checksums as good. Ben Hutchings <ben@decadent.org.uk> - 2016-04-30 21:30 +0200
  Re: [PATCH 3.2 085/115] veth: don’t modify  ip_summed; doing so treats packets with bad checksums as good. Ben Hutchings <ben@decadent.org.uk> - 2016-04-30 21:30 +0200
    Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Ben Greear <greearb@candelatech.com> - 2016-04-30 21:50 +0200
      Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Tom Herbert <tom@herbertland.com> - 2016-04-30 22:00 +0200
        Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Ben Greear <greearb@candelatech.com> - 2016-04-30 23:00 +0200
          Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Vijay Pandurangan <vijayp@vijayp.ca> - 2016-04-30 23:20 +0200
            Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Ben Greear <greearb@candelatech.com> - 2016-04-30 23:40 +0200
              Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Vijay Pandurangan <vijayp@vijayp.ca> - 2016-04-30 23:40 +0200
                Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Ben Greear <greearb@candelatech.com> - 2016-05-01 00:00 +0200
                Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Vijay Pandurangan <vijayp@vijayp.ca> - 2016-05-01 00:10 +0200
                Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Ben Greear <greearb@candelatech.com> - 2016-05-01 00:50 +0200
                Re: [PATCH 3.2 085/115] veth: don???t modify ip_summed; doing so  treats packets with bad checksums as good. Willy Tarreau <w@1wt.eu> - 2016-05-01 07:40 +0200
          Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Tom Herbert <tom@herbertland.com> - 2016-05-01 00:50 +0200
  Re: [PATCH 3.2 085/115] veth: don’t modify ip_summed; doing so treats packets with bad checksums as good. Vijay Pandurangan <vijayp@vijayp.ca> - 2016-04-30 22:20 +0200

csiph-web