From: 'Christoph Hellwig' <hch@infradead.org>
To: Sean Noonan <Sean.Noonan@twosigma.com>
Cc: 'Michel Lespinasse' <walken@google.com>,
'Christoph Hellwig' <hch@infradead.org>,
"'linux-kernel@vger.kernel.org'" <linux-kernel@vger.kernel.org>,
Martin Bligh <Martin.Bligh@twosigma.com>,
Trammell Hudson <Trammell.Hudson@twosigma.com>,
Christos Zoulas <Christos.Zoulas@twosigma.com>,
"'linux-xfs@oss.sgi.com'" <linux-xfs@oss.sgi.com>,
Stephen Degler <Stephen.Degler@twosigma.com>,
"'linux-mm@kvack.org'" <linux-mm@kvack.org>
Subject: Re: XFS memory allocation deadlock in 2.6.38
Date: Tue, 29 Mar 2011 15:24:34 -0400 [thread overview]
Message-ID: <20110329192434.GA10536@infradead.org> (raw)
In-Reply-To: <081DDE43F61F3D43929A181B477DCA95639B5359@MSXAOA6.twosigma.com>
Can you check if the brute force patch below helps? If it does I
still need to refine it a bit, but it could be that we are doing
an allocation under an xfs lock that could recurse back into the
filesystem. We have a per-process flag to disable that for normal
kmalloc allocation, but we lost it for vmalloc in the commit you
bisected the regression to.
Index: xfs/fs/xfs/linux-2.6/kmem.h
===================================================================
--- xfs.orig/fs/xfs/linux-2.6/kmem.h 2011-03-29 21:16:58.039224236 +0200
+++ xfs/fs/xfs/linux-2.6/kmem.h 2011-03-29 21:17:08.368223598 +0200
@@ -63,7 +63,7 @@ static inline void *kmem_zalloc_large(si
{
void *ptr;
- ptr = vmalloc(size);
+ ptr = __vmalloc(size, GFP_NOFS | __GFP_HIGHMEM, PAGE_KERNEL);
if (ptr)
memset(ptr, 0, size);
return ptr;
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-03-29 19:24 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <081DDE43F61F3D43929A181B477DCA95639B52FD@MSXAOA6.twosigma.com>
[not found] ` <081DDE43F61F3D43929A181B477DCA95639B5327@MSXAOA6.twosigma.com>
2011-03-24 17:43 ` XFS memory allocation deadlock in 2.6.38 Christoph Hellwig
2011-03-24 23:45 ` Michel Lespinasse
2011-03-28 14:58 ` Sean Noonan
2011-03-28 21:06 ` Michel Lespinasse
2011-03-28 21:34 ` Sean Noonan
2011-03-29 0:25 ` Michel Lespinasse
2011-03-29 1:51 ` Dave Chinner
2011-03-29 2:49 ` Sean Noonan
2011-03-29 19:05 ` Sean Noonan
2011-03-29 19:24 ` 'Christoph Hellwig' [this message]
2011-03-29 19:39 ` Johannes Weiner
2011-03-29 19:43 ` 'Christoph Hellwig'
2011-03-29 19:46 ` Sean Noonan
2011-03-29 20:02 ` 'Christoph Hellwig'
2011-03-29 20:23 ` Sean Noonan
2011-03-29 22:42 ` Dave Chinner
2011-03-29 22:45 ` Sean Noonan
2011-03-30 9:23 ` 'Christoph Hellwig'
2011-03-29 19:54 ` Sean Noonan
2011-03-30 0:09 ` Dave Chinner
2011-03-30 1:32 ` Sean Noonan
2011-03-30 1:44 ` Dave Chinner
2011-03-30 1:52 ` Sean Noonan
2011-03-30 9:30 ` 'Christoph Hellwig'
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=20110329192434.GA10536@infradead.org \
--to=hch@infradead.org \
--cc=Christos.Zoulas@twosigma.com \
--cc=Martin.Bligh@twosigma.com \
--cc=Sean.Noonan@twosigma.com \
--cc=Stephen.Degler@twosigma.com \
--cc=Trammell.Hudson@twosigma.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@oss.sgi.com \
--cc=walken@google.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;
as well as URLs for NNTP newsgroup(s).