From: Trond Myklebust <trond.myklebust@fys.uio.no>
To: kuznet@ms2.inr.ac.ru
Cc: linux-kernel@vger.kernel.org
Subject: Re: more tcpdumpinfo for nfs3 problem: aix-server --- linux 2.4.15pre5 client
Date: Tue, 20 Nov 2001 20:39:23 +0100 [thread overview]
Message-ID: <15354.45419.978323.438540@charged.uio.no> (raw)
In-Reply-To: <200111201742.UAA03009@ms2.inr.ac.ru>
In-Reply-To: <shsn11i31g2.fsf@charged.uio.no> <200111201742.UAA03009@ms2.inr.ac.ru>
>>>>> " " == kuznet <kuznet@ms2.inr.ac.ru> writes:
> Hello!
>> I forgot to add: The socket fasync lists use spinlocking in the
>> same was as RPC does, with sock_fasync() setting
>> write_lock_bh(&sk->callback_lock), and sock_def_write_space()
>> doing read_lock(&sk->callback_lock).
>>
>> So that would deadlock with the QDIO driver in the exact same
>> manner as the RPC stuff (albeit probably a lot less
>> frequently).
> Please, elaborate. I do not see any way.
Processor 1 Processor 2
(Call QDIO bottom half code)
spin_lock(&QDIO_lock);
write_lock_bh(&sk->callback_lock)
dev_kfree_skb_any()
-> kfree_skb()
<QDIO hard interrupt>
-> write_space()
->spin_lock(&QDIO_lock)
(spins...)
->read_lock(&sk->callback_lock);
(spins)
Deadlock - in exactly the same way as with the xprt code...
Cheers,
Trond
next prev parent reply other threads:[~2001-11-20 19:39 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <15349.39320.876188.274548@charged.uio.no>
2001-11-15 21:29 ` nfs problem: hp-server --- linux 2.4.13 client, ooops Birger Lammering
2001-11-15 23:58 ` Trond Myklebust
2001-11-16 11:45 ` nfs problem: hp|aix-server --- linux 2.4.15pre5 client Trond Myklebust
2001-11-16 12:01 ` Miquel van Smoorenburg
2001-11-16 12:24 ` Trond Myklebust
2001-11-16 11:24 ` Birger Lammering
2001-11-16 13:19 ` nfs problem: aix-server " Birger Lammering
2001-11-19 10:20 ` IPV4 socket layer, was: " Birger Lammering
2001-11-19 11:16 ` Alan Cox
2001-11-19 18:22 ` more tcpdumpinfo for nfs3 " Trond Myklebust
2001-11-19 18:49 ` kuznet
2001-11-19 18:55 ` Trond Myklebust
2001-11-19 19:09 ` kuznet
2001-11-19 19:29 ` Trond Myklebust
2001-11-19 19:52 ` kuznet
2001-11-19 20:38 ` Trond Myklebust
2001-11-19 21:17 ` Trond Myklebust
2001-11-20 17:42 ` kuznet
2001-11-20 19:39 ` Trond Myklebust [this message]
2001-11-20 19:45 ` kuznet
2001-11-20 20:29 ` Trond Myklebust
2001-11-21 10:07 ` Trond Myklebust
2001-11-21 17:05 ` kuznet
2001-11-20 20:05 ` Trond Myklebust
2001-11-20 20:18 ` David S. Miller
2001-11-20 20:28 ` more tcpdumpinfo for nfs3 problem: aix-server --- linux kuznet
2001-11-20 17:41 ` more tcpdumpinfo for nfs3 problem: aix-server --- linux 2.4.15pre5 client kuznet
2001-11-19 16:37 ` Birger Lammering
2001-11-20 9:26 ` Birger Lammering
2001-11-21 19:09 Manfred Spraul
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=15354.45419.978323.438540@charged.uio.no \
--to=trond.myklebust@fys.uio.no \
--cc=kuznet@ms2.inr.ac.ru \
--cc=linux-kernel@vger.kernel.org \
/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
all inboxes | Powered by JetHome®