From: olof@austin.ibm.com (Olof Johansson)
To: David Howells <dhowells@redhat.com>
Cc: Linus Torvalds <torvalds@osdl.org>,
Jamie Lokier <jamie@shareable.org>, Andrew Morton <akpm@osdl.org>,
linux-kernel@vger.kernel.org, rusty@rustcorp.com.au
Subject: Re: [PATCH/RFC] Futex mmap_sem deadlock
Date: Wed, 23 Feb 2005 10:22:26 -0600 [thread overview]
Message-ID: <20050223162225.GB10256@austin.ibm.com> (raw)
In-Reply-To: <5316.1109158748@redhat.com>
On Wed, Feb 23, 2005 at 11:39:08AM +0000, David Howells wrote:
> Alternately, you could just have do_page_fault() do:
>
> while (!down_read_trylock(¤t->mm->mmap_sem))
> continue;
>
> However, note that this can suffer from starvation due to a never ending flow
> of mixed write-locks and read-locks on other CPUs. Unlikely, true, but not
> impossible.
How can this help?
The semaphore is held for reading by the thread that faulted in
futex_wait() -> get_user(), so no writers will be let through. Until the
writer has been let through, the down_read_trylock will never succeed
either. No forward progress can be made even with the above loop.
-Olof
next prev parent reply other threads:[~2005-02-23 16:26 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-02-22 19:06 Olof Johansson
2005-02-22 19:36 ` Linus Torvalds
2005-02-22 21:16 ` Benjamin Herrenschmidt
2005-02-22 21:19 ` Benjamin Herrenschmidt
2005-02-22 21:31 ` Linus Torvalds
2005-02-22 21:42 ` Benjamin Herrenschmidt
2005-02-22 22:10 ` Linus Torvalds
2005-02-22 22:24 ` Benjamin Herrenschmidt
2005-02-22 23:08 ` Greg KH
2005-02-22 19:55 ` Andrew Morton
2005-02-22 21:07 ` Jamie Lokier
2005-02-22 21:19 ` Olof Johansson
2005-02-22 22:09 ` Jamie Lokier
2005-02-22 21:19 ` Chris Friesen
2005-02-22 21:27 ` Jamie Lokier
2005-02-22 21:30 ` Linus Torvalds
2005-02-22 22:34 ` Jamie Lokier
2005-02-22 22:42 ` Olof Johansson
2005-02-22 23:20 ` Andrew Morton
2005-02-22 23:23 ` Olof Johansson
2005-02-23 14:49 ` Joe Korty
2005-02-23 15:54 ` Linus Torvalds
2005-02-23 17:10 ` Olof Johansson
2005-02-23 17:37 ` Arjan van de Ven
2005-02-23 18:22 ` Jamie Lokier
2005-02-23 18:34 ` Linus Torvalds
2005-02-23 18:49 ` Jamie Lokier
2005-02-23 19:12 ` Olof Johansson
2005-02-23 22:00 ` Linus Torvalds
2005-02-24 0:00 ` Jamie Lokier
2005-02-23 18:37 ` Olof Johansson
2005-02-22 21:40 ` Andrew Morton
2005-02-22 21:59 ` Linus Torvalds
2005-02-23 11:39 ` David Howells
2005-02-23 16:22 ` Olof Johansson [this message]
2005-02-23 18:44 ` David Howells
2005-02-23 11:42 ` David Howells
2005-02-23 11:24 ` David Howells
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=20050223162225.GB10256@austin.ibm.com \
--to=olof@austin.ibm.com \
--cc=akpm@osdl.org \
--cc=dhowells@redhat.com \
--cc=jamie@shareable.org \
--cc=linux-kernel@vger.kernel.org \
--cc=rusty@rustcorp.com.au \
--cc=torvalds@osdl.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®