From: Rusty Russell <rusty@rustcorp.com.au>
To: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: William Lee Irwin III <wli@holomorphy.com>,
"Van Maren, Kevin" <kevin.vanmaren@unisys.com>,
linux-ia64@linuxia64.org,
Linux Kernel List <linux-kernel@vger.kernel.org>,
rusty@rustcorp.com.au, dhowells@redhat.com, mingo@elte.hu,
torvalds@transmeta.com
Subject: Re: [Linux-ia64] reader-writer livelock problem
Date: Sat, 09 Nov 2002 13:48:17 +1100 [thread overview]
Message-ID: <20021109041543.EBE8A2C29F@lists.samba.org> (raw)
In-Reply-To: Your message of "08 Nov 2002 09:38:25 -0800." <1036777105.13021.13.camel@ixodes.goop.org>
In message <1036777105.13021.13.camel@ixodes.goop.org> you write:
> On Fri, 2002-11-08 at 09:25, Linus Torvalds wrote:
> > There's another reason for not doing it that way: allowing readers to keep
> > interrupts on even in the presense of interrupt uses of readers.
> >
> > If you do the "pending writes stop readers" approach, you get
> >
> > cpu1 cpu2
> >
> > read_lock() - get
> >
> > write_lock_irq() - pending
> >
> > irq happens
> > - read_lock() - deadlock
> >
> > and that means that you need to make readers protect against interrupts
> > even if the interrupts only read themselves.
>
> Even without interrupts that would be a bug. It isn't ever safe to
> attempt to retake a read lock if you already hold it, because you may
> deadlock with a pending writer. Fair multi-reader locks aren't
> recursive locks.
That's the point. This is explicitly guaranteed with the current
locks, and you are allowed to recurse on them. The netfilter code
explicitly uses this to retake the net brlock, since it gets called
from different paths.
Implement "read_lock_yield" or "wrlock_t" but don't break existing
semantics until 2.7 *please*!
Rusty.
--
Anyone who quotes me in their sig is an idiot. -- Rusty Russell.
next prev parent reply other threads:[~2002-11-09 4:09 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <3FAD1088D4556046AEC48D80B47B478C0101F4E7@usslc-exch-4.slc.unisys.com>
2002-11-08 3:51 ` [Linux-ia64] reader-writer livelock problem William Lee Irwin III
2002-11-08 17:13 ` Jeremy Fitzhardinge
2002-11-08 17:25 ` Linus Torvalds
2002-11-08 17:28 ` Linus Torvalds
2002-11-08 17:38 ` Jeremy Fitzhardinge
2002-11-08 17:43 ` David Howells
2002-11-08 17:57 ` Linus Torvalds
2002-11-09 2:48 ` Rusty Russell [this message]
2002-11-09 4:36 ` William Lee Irwin III
[not found] ` <3DCFDAE9.6D359448@email.mot.com>
2002-11-11 19:22 ` David Mosberger
2002-11-12 1:39 ` your mail Rik van Riel
2002-11-08 17:34 ` [Linux-ia64] reader-writer livelock problem David Howells
2002-11-08 17:54 ` David Howells
2002-11-08 17:55 ` Stephen Hemminger
2002-11-08 17:41 Van Maren, Kevin
2002-11-08 17:52 ` Matthew Wilcox
2002-11-08 18:05 Van Maren, Kevin
2002-11-08 19:19 ` Matthew Wilcox
2002-11-08 19:26 ` David Mosberger
2002-11-08 20:17 Van Maren, Kevin
2002-11-08 20:39 ` Matthew Wilcox
2002-11-08 20:24 Van Maren, Kevin
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=20021109041543.EBE8A2C29F@lists.samba.org \
--to=rusty@rustcorp.com.au \
--cc=dhowells@redhat.com \
--cc=jeremy@goop.org \
--cc=kevin.vanmaren@unisys.com \
--cc=linux-ia64@linuxia64.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=torvalds@transmeta.com \
--cc=wli@holomorphy.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).