From: Zach Brown <zach.brown@oracle.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Jens Axboe <jens.axboe@oracle.com>,
linux-kernel@vger.kernel.org, akpm@linux-foundation.org,
linux-aio@kvack.org, Trond Myklebust <trond.myklebust@fys.uio.no>,
Chris Mason <chris.mason@oracle.com>
Subject: Re: dio_get_page() lockdep complaints
Date: Fri, 09 Nov 2007 09:30:20 -0800 [thread overview]
Message-ID: <4734992C.7000408@oracle.com> (raw)
In-Reply-To: <1194627742.6289.175.camel@twins>
So, reiserfs and NFS are nesting i_mutex inside the mmap_sem.
>> [<b038c6e5>] mutex_lock+0x1c/0x1f
>> [<b01b17e9>] reiserfs_file_release+0x54/0x447
>> [<b016afe7>] __fput+0x53/0x101
>> [<b016b0ee>] fput+0x19/0x1c
>> [<b015bcd5>] remove_vma+0x3b/0x4d
>> [<b015c659>] do_munmap+0x17f/0x1cf
> [<ffffffff802686a1>] _mutex_lock+0x28/0x34
> [<ffffffff883e71d0>] nfs_revalidate_mapping+0x6d/0xac [nfs]
> [<ffffffff883e4b51>] nfs_file_mmap+0x5c/0x74 [nfs]
> [<ffffffff8020df7e>] do_mmap_pgoff+0x51a/0x817
> [<ffffffff80225d19>] sys_mmap+0x90/0x119
I think i_mutex is fundamentally nested outside of the mmap_sem because
of faulting in the buffered write path. I think these warnings could be
reproduced with a careful test app which tries buffered writes from an
address which will fault.
DIO just tripped it up because it *always* performs get_user_pages() on
the memory.
So reiser and NFS need to be fixed. No?
(reiser is grabbing i_mutex from any final fput? brave!)
- z
next prev parent reply other threads:[~2007-11-09 17:30 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-19 7:38 dio_get_page() lockdep complaints Jens Axboe
2007-04-19 8:01 ` Andrew Morton
2007-04-19 8:01 ` Jens Axboe
2007-04-19 8:25 ` Andrew Morton
2007-04-19 8:34 ` Jens Axboe
2007-04-19 12:43 ` Vladimir V. Saveliev
2007-04-19 12:49 ` Jens Axboe
2007-04-19 12:52 ` Jens Axboe
2007-04-19 13:53 ` Roland Dreier
2007-04-19 14:20 ` Jens Axboe
2007-04-19 14:15 ` Jens Axboe
2007-04-19 14:55 ` Vladimir V. Saveliev
2007-04-19 14:57 ` Vladimir V. Saveliev
2007-04-19 16:42 ` Andrew Morton
2007-04-19 14:36 ` Chris Mason
2007-11-09 17:02 ` Peter Zijlstra
2007-11-09 17:30 ` Zach Brown [this message]
2007-11-09 17:45 ` Trond Myklebust
2007-11-09 17:48 ` Zach Brown
2007-11-09 18:01 ` Chris Mason
2007-11-09 18:35 ` Zach Brown
2007-11-09 18:53 ` Chris Mason
2007-11-09 18:57 ` Chris Mason
2007-11-09 19:16 ` Zach Brown
2007-11-09 19:35 ` Chris Mason
2007-11-11 19:49 ` Peter Zijlstra
2007-11-12 8:45 ` Martin Schwidefsky
2007-11-12 9:27 ` Peter Zijlstra
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=4734992C.7000408@oracle.com \
--to=zach.brown@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=chris.mason@oracle.com \
--cc=jens.axboe@oracle.com \
--cc=linux-aio@kvack.org \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=trond.myklebust@fys.uio.no \
/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