From: Andrea Arcangeli <andrea@suse.de>
To: Alexander Viro <viro@math.psu.edu>
Cc: Manfred Spraul <manfreds@colorfullife.com>,
linux-kernel@vger.rutgers.edu,
Ingo Molnar <mingo@chiara.csoma.elte.hu>,
linux-mm@kvack.org
Subject: Re: locking question: do_mmap(), do_munmap()
Date: Sun, 10 Oct 1999 19:12:58 +0200 (CEST) [thread overview]
Message-ID: <Pine.LNX.4.10.9910101900210.520-100000@alpha.random> (raw)
In-Reply-To: <Pine.GSO.4.10.9910101219370.16317-100000@weyl.math.psu.edu>
On Sun, 10 Oct 1999, Alexander Viro wrote:
>sys_swapoff(). It's a syscall. Andrea, could you show a scenario for
do_page_fault -> down() -> GFP -> swap_out() -> down() -> deadlock
To grab the mm semaphore in swap_out we could swap_out only from kswapd
doing a kind of wakeup_and_wait_kswapd() ala wakeup_bdflush(1) but it would
be slow and I don't want to run worse than in 2.2.x in UP to get some more
SMP scalability in SMP (that won't pay the cost).
The other option is to make the mmap semaphore recursive checking that GFP
is not called in the middle of a vma change. I don't like this one it sound
not robust as the spinlock way to me (see below).
What I like is to go as in 2.2.x with a proper spinlock for doing vma
reads (I am _not_ talking about the big kernel lock!).
Andrea
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://humbolt.geo.uu.nl/Linux-MM/
next prev parent reply other threads:[~1999-10-10 17:12 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <Pine.LNX.4.10.9910101713010.364-100000@alpha.random>
1999-10-10 15:52 ` Manfred Spraul
1999-10-10 16:07 ` Alexander Viro
1999-10-10 16:25 ` Alexander Viro
1999-10-10 16:45 ` Manfred Spraul
1999-10-10 17:25 ` Alexander Viro
1999-10-10 17:12 ` Andrea Arcangeli [this message]
1999-10-10 17:48 ` Alexander Viro
1999-10-10 18:42 ` Manfred Spraul
1999-10-10 19:03 ` Alexander Viro
1999-10-10 21:31 ` Manfred Spraul
1999-10-10 21:53 ` Andrea Arcangeli
1999-10-10 22:34 ` Alexander Viro
1999-10-10 23:28 ` Andrea Arcangeli
1999-10-11 15:50 ` Stephen C. Tweedie
1999-10-11 16:05 ` Alexander Viro
1999-10-11 18:02 ` Manfred Spraul
1999-10-11 19:07 ` Kanoj Sarcar
1999-10-11 22:23 ` Stephen C. Tweedie
1999-10-13 1:25 ` Kanoj Sarcar
1999-10-13 7:32 ` Manfred Spraul
1999-10-15 9:58 ` Ralf Baechle
1999-10-15 17:50 ` Kanoj Sarcar
1999-10-13 10:45 ` Stephen C. Tweedie
1999-10-11 20:15 ` Stephen C. Tweedie
1999-10-11 21:14 ` Manfred Spraul
1999-10-11 21:37 ` Alexander Viro
1999-10-11 22:13 ` Manfred Spraul
1999-10-11 22:22 ` Stephen C. Tweedie
1999-10-11 23:01 ` Alexander Viro
1999-10-12 14:06 ` [more fun] " Alexander Viro
1999-10-13 7:35 ` Manfred Spraul
1999-10-13 18:34 ` Kanoj Sarcar
1999-10-13 10:16 ` Stephen C. Tweedie
1999-10-11 20:13 ` Stephen C. Tweedie
1999-10-11 21:40 ` Alexander Viro
1999-10-11 22:20 ` Stephen C. Tweedie
1999-10-11 22:31 ` Alexander Viro
1999-10-13 10:25 ` Stephen C. Tweedie
1999-10-11 15:47 ` Stephen C. Tweedie
1999-10-11 15:43 ` Stephen C. Tweedie
1999-10-10 16:56 ` Andrea Arcangeli
1999-10-11 15:41 ` Stephen C. Tweedie
1999-10-11 15:52 ` Alexander Viro
1999-10-09 12:48 Manfred Spraul
1999-10-09 13:12 ` Alexander Viro
1999-10-09 13:17 ` Manfred Spraul
1999-10-09 13:38 ` Alexander Viro
1999-10-09 16:01 ` Andrea Arcangeli
1999-10-10 13:05 ` Manfred Spraul
1999-10-11 15:09 ` Stephen C. Tweedie
1999-10-11 15:05 ` Stephen C. Tweedie
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=Pine.LNX.4.10.9910101900210.520-100000@alpha.random \
--to=andrea@suse.de \
--cc=linux-kernel@vger.rutgers.edu \
--cc=linux-mm@kvack.org \
--cc=manfreds@colorfullife.com \
--cc=mingo@chiara.csoma.elte.hu \
--cc=viro@math.psu.edu \
/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