linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Herbert Xu <herbert@gondor.apana.org.au>
To: Andrew Morton <akpm@osdl.org>
Cc: Reuben Farrelly <reuben-lkml@reub.net>,
	linux-kernel@vger.kernel.org, netdev@vger.kernel.org
Subject: Re: 2.6.18-rc1-mm2
Date: Sat, 15 Jul 2006 10:04:58 +1000	[thread overview]
Message-ID: <20060715000458.GB9334@gondor.apana.org.au> (raw)
In-Reply-To: <20060714000551.649ca455.akpm@osdl.org>

On Fri, Jul 14, 2006 at 12:05:51AM -0700, Andrew Morton wrote:
>
> > Call Trace:
> >   [<ffffffff8026963e>] show_trace+0xae/0x265
> >   [<ffffffff8026980a>] dump_stack+0x15/0x1b
> >   [<ffffffff8043ba7b>] skb_checksum_help+0x61/0x126
> >   [<ffffffff8802f35f>] :iptable_nat:ip_nat_fn+0x5f/0x1d2

This is tell you that there is a bug in ip_nat_fn in that it completes
the partial checksum even for TSO packets which will cause them to go
out with bogus checksums.

The warning also indicates that the system has detected this and has
worked around it by recomputing the partial checksum after NAT.

The warning is here so someone can fix NAT to not trash the partial
checksum.  It would also tell us if anyone else breaks checksums in
this way.

I've already made the warning appear only once per-boot so I'd really
like to keep it in until

1) NAT is fixed.
2) We're reasonably sure there's nothing else doing this.

Prior to this change your TSO packets would've gone out with corrupted
checksums silently.  Essentially TSO would only slow your machine down
since every transmission it makes has to be retransmitted as non-TSO.

Cheers,
-- 
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

  reply	other threads:[~2006-07-15  0:05 UTC|newest]

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-07-14  5:48 2.6.18-rc1-mm2 Andrew Morton
2006-07-14  6:55 ` 2.6.18-rc1-mm2 Reuben Farrelly
2006-07-14  7:05   ` 2.6.18-rc1-mm2 Andrew Morton
2006-07-15  0:04     ` Herbert Xu [this message]
     [not found]       ` <20060714172010.fcc50c0a.akpm@osdl.org>
     [not found]         ` <20060715002623.GE9334@gondor.apana.org.au>
     [not found]           ` <20060714173517.cdd58097.akpm@osdl.org>
2006-07-15  1:06             ` 2.6.18-rc1-mm2 Herbert Xu
2006-07-15  5:40               ` 2.6.18-rc1-mm2 David Miller
2006-07-15  6:04                 ` 2.6.18-rc1-mm2 Dave Jones
2006-07-16  1:19                   ` 2.6.18-rc1-mm2 David Miller
2006-07-15 10:32                 ` 2.6.18-rc1-mm2 Herbert Xu
2006-07-15 10:34                   ` 2.6.18-rc1-mm2 Herbert Xu
2006-07-14  7:33   ` 2.6.18-rc1-mm2 David Miller
2006-07-14  7:00 ` 2.6.18-rc1-mm2 Reuben Farrelly
2006-07-14  8:39 ` [patch -mm] s390: kprobes compile fix Heiko Carstens
2006-07-14 11:30 ` 2.6.18-rc1-mm2 Reuben Farrelly
2006-07-14 15:00   ` 2.6.18-rc1-mm2 Andrew Morton
2006-07-14 11:36 ` 2.6.18-rc1-mm2 Rafael J. Wysocki
2006-07-14 18:00   ` 2.6.18-rc1-mm2 Andrew Morton
2006-07-14 18:36     ` 2.6.18-rc1-mm2 Michal Piotrowski
2006-07-14 20:27       ` 2.6.18-rc1-mm2 Rafael J. Wysocki
2006-07-14 12:23 ` 2.6.18-rc1-mm2 Michal Piotrowski
2006-07-14 12:36 ` 2.6.18-rc1-mm2 Lexington Luthor
2006-07-14 16:30   ` [PATCH] fixed add_bind_files() definition Yoichi Yuasa
2006-07-14 15:48 ` 2.6.18-rc1-mm2 Dave Hansen
2006-07-18 21:49   ` 2.6.18-rc1-mm2 Haavard Skinnemoen
2006-07-14 16:30 ` 2.6.18-rc1-mm2 (bttv: NULL pointer derefernce) Dominik Karall
2006-08-02 16:00   ` 2.6.18-rc1-mm2 and 2.6.18-rc3 " Dominik Karall
2006-08-02 16:49     ` Andrew Morton
2006-08-02 16:57       ` Linus Torvalds
2006-08-02 18:02         ` Mauro Carvalho Chehab
2006-08-02 17:08     ` Bret Towe
2006-07-14 17:57 ` 2.6.18-rc1-mm2 Cédric Augonnet
2006-07-14 18:18   ` 2.6.18-rc1-mm2 Andrew Morton
2006-07-14 18:50     ` 2.6.18-rc1-mm2 Cédric Augonnet
2006-07-14 18:48 ` 2.6.18-rc1-mm2: drivers/char/*synclink* compile errors Adrian Bunk
2006-07-14 21:31   ` David Miller
2006-07-14 19:08 ` 2.6.18-rc1-mm2: drivers/scsi/NCR53C9x.c compile error Adrian Bunk
2006-07-20 10:17   ` 2.6.18-rc1-mm2: drivers/fc4/fc.c " Adrian Bunk
2006-07-15  0:35 ` [-mm patch] remove net/core/skbuff.c:skb_queue_lock_key Adrian Bunk
2006-07-15  5:35   ` Arjan van de Ven
2006-07-15  0:35 ` [-mm patch] drivers/char/pc8736x_gpio.c: unexport a static struct Adrian Bunk
2006-07-15 14:50   ` Chris Boot
2006-07-15  0:35 ` [RFC: -mm patch] drivers/char/scx200_gpio.c: make code static Adrian Bunk
2006-07-15 14:49   ` Chris Boot
2006-07-15 15:37     ` Adrian Bunk
2006-07-15 17:10       ` Chris Boot
2006-07-15 23:49   ` Jim Cromie
2006-07-15  0:35 ` [-mm patch] drivers/crypto/padlock-sha.c: make 2 functions static Adrian Bunk
2006-07-15  0:39   ` Herbert Xu
2006-07-15  0:35 ` [RFC: -mm patch] drivers/usb/core/driver.c: " Adrian Bunk
2006-07-15 12:50   ` [linux-usb-devel] " Alan Stern
2006-07-15  0:36 ` [RFC: -mm patch] fs/dlm/lock.c: unexport dlm_lvb_operations Adrian Bunk
2006-07-19 23:27   ` Steven Whitehouse
2006-07-15  0:37 ` [-mm patch] drivers/char/pc8736x_gpio.c: remove unused static functions Adrian Bunk
2006-07-18 16:07   ` Jim Cromie
2006-07-30 16:49   ` Jim Cromie
2006-07-22  9:49 ` [patch] mdacon: fix __init section warnings Frederik Deweerdt
2006-07-23  0:55 ` 2.6.18-rc1-mm2 Reuben Farrelly
2006-07-24 17:21   ` [patch] inotify: fix deadlock found by lockdep Arjan van de Ven
2006-07-24 19:14     ` Ingo Molnar
2006-07-24 22:08     ` Robert Love

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=20060715000458.GB9334@gondor.apana.org.au \
    --to=herbert@gondor.apana.org.au \
    --cc=akpm@osdl.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=reuben-lkml@reub.net \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).