From: Mel Gorman <mgorman@suse.de>
To: Hugh Dickins <hughd@google.com>
Cc: Pawel Sikora <pluto@agmk.net>,
Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>,
linux-mm@vger.kernel.org, jpiszcz@lucidpixels.com,
arekm@pld-linux.org, linux-kernel@vger.kernel.org
Subject: Re: kernel 3.0: BUG: soft lockup: find_get_pages+0x51/0x110
Date: Fri, 21 Oct 2011 14:44:15 +0200 [thread overview]
Message-ID: <20111021124415.GB4082@suse.de> (raw)
In-Reply-To: <20111019073036.GA3410@suse.de>
On Wed, Oct 19, 2011 at 09:30:36AM +0200, Mel Gorman wrote:
> > RIP: 0010:[<ffffffff81127b76>] [<ffffffff81127b76>]
> > migration_entry_wait+0x156/0x160
> > [<ffffffff811016a1>] handle_pte_fault+0xae1/0xaf0
> > [<ffffffff810feee2>] ? __pte_alloc+0x42/0x120
> > [<ffffffff8112c26b>] ? do_huge_pmd_anonymous_page+0xab/0x310
> > [<ffffffff81102a31>] handle_mm_fault+0x181/0x310
> > [<ffffffff81106097>] ? vma_adjust+0x537/0x570
> > [<ffffffff81424bed>] do_page_fault+0x11d/0x4e0
> > [<ffffffff81109a05>] ? do_mremap+0x2d5/0x570
> > [<ffffffff81421d5f>] page_fault+0x1f/0x30
> >
> > mremap's down_write of mmap_sem, together with i_mmap_mutex/lock,
> > and pagetable locks, were good enough before page migration (with its
> > requirement that every migration entry be found) came in; and enough
> > while migration always held mmap_sem. But not enough nowadays, when
> > there's memory hotremove and compaction: anon_vma lock is also needed,
> > to make sure a migration entry is not dodging around behind our back.
> >
>
> migration holds the anon_vma lock while it unmaps the pages and keeps holding
> it until after remove_migration_ptes is called.
I reread this today and realised I was sloppy with my writing. migration
holds the anon_vma lock while it unmaps the pages. It also holds the
anon_vma lock during remove_migration_ptes. For the migration operation,
a reference count is held on anon_vma but not the lock itself.
> There are two anon vmas
> that should exist during mremap that were created for the move. They
> should not be able to disappear while migration runs and right now,
And what is preventing them disappearing is not the lock but the
reference count.
next prev parent reply other threads:[~2011-10-21 12:44 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-10-12 18:12 Paweł Sikora
2011-10-13 23:16 ` Hugh Dickins
2011-10-13 23:30 ` Hugh Dickins
2011-10-16 16:11 ` Christoph Hellwig
2011-10-16 23:54 ` Andrea Arcangeli
2011-10-17 18:51 ` Hugh Dickins
2011-10-17 22:05 ` Andrea Arcangeli
2011-10-19 7:43 ` Mel Gorman
2011-10-19 13:39 ` Linus Torvalds
2011-10-19 19:42 ` Hugh Dickins
2011-10-20 6:30 ` Paweł Sikora
2011-10-20 6:51 ` Linus Torvalds
2011-10-21 6:54 ` Nai Xia
2011-10-21 7:35 ` Pawel Sikora
2011-10-20 12:51 ` Nai Xia
[not found] ` <CANsGZ6a6_q8+88FRV2froBsVEq7GhtKd9fRnB-0M2MD3a7tnSw@mail.gmail.com>
2011-10-21 6:22 ` Nai Xia
2011-10-21 8:07 ` Pawel Sikora
2011-10-21 9:07 ` Nai Xia
2011-10-21 21:36 ` Paweł Sikora
2011-10-22 6:21 ` Nai Xia
2011-10-22 16:42 ` Paweł Sikora
[not found] ` <CAPQyPG5HJKTo8AEy_khdJeciTgtNQepK6XLcpzvPF8PYS0V-Lw@mail.gmail.com>
2011-10-25 7:33 ` Pawel Sikora
2011-10-20 9:11 ` Nai Xia
2011-10-21 15:56 ` Mel Gorman
2011-10-21 17:21 ` Nai Xia
2011-10-21 17:41 ` Andrea Arcangeli
2011-10-21 22:50 ` Andrea Arcangeli
2011-10-22 5:52 ` Nai Xia
2011-10-31 17:14 ` Andrea Arcangeli
2011-10-31 17:27 ` [PATCH] mremap: enforce rmap src/dst vma ordering in case of vma_merge succeeding in copy_vma Andrea Arcangeli
2011-11-01 12:07 ` Mel Gorman
2011-11-01 14:35 ` Nai Xia
2011-11-04 7:31 ` Hugh Dickins
2011-11-04 14:34 ` Nai Xia
2011-11-04 15:59 ` Pawel Sikora
2011-11-05 2:21 ` Nai Xia
2011-11-04 19:16 ` Hugh Dickins
2011-11-04 20:54 ` Andrea Arcangeli
2011-11-05 0:09 ` Nai Xia
2011-11-05 2:21 ` Hugh Dickins
2011-11-05 3:07 ` Andrea Arcangeli
2011-11-05 17:06 ` Andrea Arcangeli
2011-12-08 3:24 ` David Rientjes
2011-12-08 12:42 ` Andrea Arcangeli
2011-12-09 0:08 ` Andrew Morton
2011-12-09 1:55 ` Andrea Arcangeli
2011-11-04 23:56 ` Andrea Arcangeli
2011-11-05 0:21 ` Nai Xia
2011-11-05 0:59 ` Nai Xia
2011-11-05 1:33 ` Andrea Arcangeli
2011-11-05 2:00 ` Nai Xia
2011-11-07 13:14 ` Mel Gorman
2011-11-07 15:42 ` Andrea Arcangeli
2011-11-07 16:28 ` Mel Gorman
2011-11-09 1:25 ` Andrea Arcangeli
2011-11-11 9:14 ` Nai Xia
2011-11-16 14:00 ` Andrea Arcangeli
2011-11-17 0:16 ` Hugh Dickins
2011-11-17 2:49 ` Nai Xia
2011-11-17 6:21 ` Nai Xia
2011-11-17 18:42 ` Andrea Arcangeli
2011-11-18 1:42 ` Nai Xia
2011-11-18 2:17 ` Andrea Arcangeli
2011-11-19 9:15 ` Nai Xia
2011-10-22 5:07 ` kernel 3.0: BUG: soft lockup: find_get_pages+0x51/0x110 Nai Xia
2011-10-31 16:34 ` Andrea Arcangeli
2011-10-16 22:37 ` Linus Torvalds
2011-10-17 3:02 ` Hugh Dickins
2011-10-17 3:09 ` Linus Torvalds
2011-10-18 19:17 ` Paweł Sikora
2011-10-19 7:30 ` Mel Gorman
2011-10-21 12:44 ` Mel Gorman [this message]
-- strict thread matches above, loose matches on Subject: below --
2011-08-15 16:43 Justin Piszcz
2011-08-15 18:18 ` Hugh Dickins
2011-08-15 19:02 ` Justin Piszcz
2011-08-15 19:53 ` Hugh Dickins
2011-08-21 17:59 ` Maciej Rutecki
2011-08-21 18:49 ` Justin Piszcz
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=20111021124415.GB4082@suse.de \
--to=mgorman@suse.de \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=arekm@pld-linux.org \
--cc=hughd@google.com \
--cc=jpiszcz@lucidpixels.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@vger.kernel.org \
--cc=pluto@agmk.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
Powered by JetHome