From: Eric Dumazet <eric.dumazet@gmail.com>
To: Bhaskar Dutta <bhaskie@gmail.com>
Cc: Stephen Hemminger <shemminger@vyatta.com>,
Ben Hutchings <bhutchings@solarflare.com>,
netdev@vger.kernel.org
Subject: Re: TCP-MD5 checksum failure on x86_64 SMP
Date: Wed, 05 May 2010 20:53:18 +0200 [thread overview]
Message-ID: <1273085598.2367.233.camel@edumazet-laptop> (raw)
In-Reply-To: <g2p571fb4001005051103w67e1b9ddn3e8f7feb84d0559@mail.gmail.com>
Le mercredi 05 mai 2010 à 23:33 +0530, Bhaskar Dutta a écrit :
> Hi,
>
> TSO, GSO and SG are already turned off.
> rx/tx checksumming is on, but that shouldn't matter, right?
>
> # ethtool -k eth0
> Offload parameters for eth0:
> rx-checksumming: on
> tx-checksumming: on
> scatter-gather: off
> tcp segmentation offload: off
> udp fragmentation offload: off
> generic segmentation offload: off
>
> The bad packets are very small in size, most have no data at all (<300 bytes).
>
> After adding some logs to kernel 2.6.31-12, it seems that
> tcp_v4_md5_hash_skb (function that calculates the md5 hash) is
> (might?) getting corrupt.
>
> The tcp4_pseudohdr (bp = &hp->md5_blk.ip4) structure's saddr, daddr
> and len fields get modified to different values towards the end of the
> tcp_v4_md5_hash_skb function whenever there is a checksum error.
>
> The tcp4_pseudohdr (bp) is within the tcp_md5sig_pool (hp), which is
> filled up by tcp_get_md5sig_pool (which calls per_cpu_ptr).
>
> Using a local copy of the tcp4_pseudohdr in the same function
> tcp_v4_md5_hash_skb (copied all fields from the original
> tcp4_pseudohdr within the tcp_md5sig_pool) and calculating the md5
> checksum with the local tcp4_pseudohdr seems to solve the issue
> (don't see bad packets for a hours in load tests, and without the
> change I can see them instantaneously in the load tests).
>
> I am still unable to figure out how this is happening. Please let me
> know if you have any pointers.
I am not familiar with this code, but I suspect same per_cpu data can be
used at both time by a sender (process context) and by a receiver
(softirq context).
To trigger this, you need at least two active md5 sockets.
tcp_get_md5sig_pool() should probably disable bh to make sure current
cpu wont be preempted by softirq processing
Something like :
diff --git a/include/net/tcp.h b/include/net/tcp.h
index fb5c66b..e232123 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1221,12 +1221,15 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
struct tcp_md5sig_pool *ret = __tcp_get_md5sig_pool(cpu);
if (!ret)
put_cpu();
+ else
+ local_bh_disable();
return ret;
}
static inline void tcp_put_md5sig_pool(void)
{
__tcp_put_md5sig_pool();
+ local_bh_enable();
put_cpu();
}
next prev parent reply other threads:[~2010-05-05 18:53 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <i2h571fb4001005031027y4a58c4dtfd28ddcdc08d8401@mail.gmail.com>
2010-05-04 3:30 ` TCP-MD5 checksum failure on x86_64 SMP Bhaskar Dutta
2010-05-04 11:32 ` Ben Hutchings
2010-05-04 14:28 ` Bhaskar Dutta
2010-05-04 16:12 ` Stephen Hemminger
2010-05-04 17:08 ` Bhaskar Dutta
2010-05-04 17:13 ` Stephen Hemminger
2010-05-05 18:03 ` Bhaskar Dutta
2010-05-05 18:53 ` Eric Dumazet [this message]
2010-05-06 11:55 ` Bhaskar Dutta
2010-05-06 12:06 ` Eric Dumazet
2010-05-07 5:04 ` David Miller
2010-05-07 5:32 ` Eric Dumazet
2010-05-07 17:14 ` Stephen Hemminger
2010-05-07 17:21 ` Eric Dumazet
2010-05-07 17:36 ` Stephen Hemminger
2010-05-07 21:40 ` Eric Dumazet
2010-05-10 14:55 ` Bijay Singh
2010-05-10 15:18 ` Eric Dumazet
2010-05-10 17:27 ` Bijay Singh
2010-05-11 4:08 ` Bijay Singh
2010-05-11 6:27 ` Eric Dumazet
2010-05-11 8:23 ` Bijay Singh
2010-05-11 20:50 ` Eric Dumazet
2010-05-12 3:20 ` Eric Dumazet
2010-05-12 22:22 ` Stephen Hemminger
2010-05-12 22:24 ` David Miller
2010-05-16 19:53 ` Eric Dumazet
2010-05-16 20:48 ` Eric Dumazet
2010-05-17 3:49 ` Bijay Singh
2010-05-17 5:03 ` Eric Dumazet
2010-05-17 17:22 ` Stephen Hemminger
2010-05-17 20:42 ` Stephen Hemminger
2010-05-17 21:04 ` [PATCH] tcp: tcp_synack_options() fix Eric Dumazet
2010-05-18 5:35 ` David Miller
2010-05-16 7:30 ` TCP-MD5 checksum failure on x86_64 SMP David Miller
2010-05-07 8:46 ` Lars Eggert
2010-05-07 8:55 ` Eric Dumazet
2010-05-07 9:12 ` David Miller
2010-05-07 5:39 ` Eric Dumazet
2010-05-07 8:00 ` Eric Dumazet
2010-05-07 8:59 ` Bhaskar Dutta
2010-05-07 9:37 ` Eric Dumazet
2010-05-07 10:50 ` Bhaskar Dutta
2010-05-07 15:18 ` Eric Dumazet
2010-05-07 15:44 ` Eric Dumazet
2010-05-07 21:18 ` Eric Dumazet
2010-05-16 7:37 ` David Miller
2010-05-16 7:35 ` David Miller
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=1273085598.2367.233.camel@edumazet-laptop \
--to=eric.dumazet@gmail.com \
--cc=bhaskie@gmail.com \
--cc=bhutchings@solarflare.com \
--cc=netdev@vger.kernel.org \
--cc=shemminger@vyatta.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox