From: Peter Zijlstra <peterz@infradead.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Waiman Long <waiman.long@hp.com>,
Mikulas Patocka <mpatocka@redhat.com>,
"James E.J. Bottomley" <jejb@parisc-linux.org>,
Helge Deller <deller@gmx.de>,
John David Anglin <dave.anglin@bell.net>,
Parisc List <linux-parisc@vger.kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Paul McKenney <paulmck@linux.vnet.ibm.com>,
"Vinod, Chegu" <chegu_vinod@hp.com>,
Thomas Gleixner <tglx@linutronix.de>,
Rik van Riel <riel@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
Davidlohr Bueso <davidlohr@hp.com>, Peter Anvin <hpa@zytor.com>,
Andi Kleen <andi@firstfloor.org>,
"Chandramouleeswaran, Aswin" <aswin@hp.com>,
"Norton, Scott J" <scott.norton@hp.com>,
Jason Low <jason.low2@hp.com>
Subject: Re: [PATCH v2] introduce atomic_pointer to fix a race condition in cancelable mcs spinlocks
Date: Tue, 3 Jun 2014 09:54:33 +0200 [thread overview]
Message-ID: <20140603075433.GI11096@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <CA+55aFwJwVf_MbcwNNWg-KrLdoOaV2xse2jzvBZTJHJgC_Htvg@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1093 bytes --]
On Mon, Jun 02, 2014 at 01:22:10PM -0700, Linus Torvalds wrote:
> On Mon, Jun 2, 2014 at 1:05 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> >
> > So the question is, do you prefer subtly broken code or hard compile
> > fails? Me, I go for the compile fail.
>
> The thing is, parisc has a perfectly fine "cmpxchg" implementation in
> practice, and ACCESS_ONCE() and friends work fine too for reading.
>
> What the "use a spinlock" approach cannot generally do is:
>
> - ACCESS_ONCE() to _write_ things doesn't work well. You really
> should use "atomic_set()".
>
> - you may not necessarily be able to mix partial updates (ie
> differently sized updates to the same thing) depending on just how the
> spinlock hashing works
>
> but both of those are really rare issues and don't affect normal code.
Agreed on the second, although that would be fairly easy to fix by
masking out the lower few bits in the pointer address before hashing.
The first, you're probably, right, but seeing how its a completely
silent fail atm I'm not at all comfortable with it.
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
next prev parent reply other threads:[~2014-06-03 7:54 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-01 17:53 [PATCH] fix a race condition in cancelable mcs spinlocks Mikulas Patocka
2014-06-01 19:20 ` Peter Zijlstra
2014-06-01 20:46 ` John David Anglin
2014-06-01 21:30 ` Peter Zijlstra
2014-06-01 21:46 ` Paul E. McKenney
2014-06-02 9:19 ` Mikulas Patocka
2014-06-02 13:24 ` Paul E. McKenney
2014-06-02 15:57 ` Mikulas Patocka
2014-06-02 16:39 ` Paul E. McKenney
2014-06-02 19:56 ` James Bottomley
2014-06-03 7:56 ` Peter Zijlstra
2014-06-04 12:53 ` Mikulas Patocka
2014-06-02 13:58 ` Mikulas Patocka
2014-06-02 14:02 ` Mikulas Patocka
2014-06-02 15:39 ` John David Anglin
2014-06-02 10:34 ` Mikulas Patocka
2014-06-02 14:14 ` Waiman Long
2014-06-02 15:27 ` Jason Low
2014-06-02 16:00 ` [PATCH v2] introduce atomic_pointer to " Mikulas Patocka
2014-06-02 16:25 ` Peter Zijlstra
2014-06-02 16:30 ` Peter Zijlstra
2014-06-02 16:46 ` Paul E. McKenney
2014-06-02 17:33 ` Waiman Long
2014-06-02 20:05 ` Peter Zijlstra
2014-06-02 20:22 ` Linus Torvalds
2014-06-02 21:02 ` Paul E. McKenney
2014-06-02 21:12 ` Linus Torvalds
2014-06-02 22:08 ` Paul E. McKenney
2014-06-02 22:44 ` Eric Dumazet
2014-06-02 23:17 ` Paul E. McKenney
2014-06-02 23:53 ` Eric Dumazet
2014-06-03 0:28 ` Paul E. McKenney
2014-06-02 22:55 ` Linus Torvalds
2014-06-03 16:48 ` Paul E. McKenney
2014-06-03 7:54 ` Peter Zijlstra [this message]
2014-06-02 20:24 ` James Bottomley
2014-06-02 16:43 ` Paul E. McKenney
2014-06-02 17:14 ` James Bottomley
2014-06-02 17:29 ` Waiman Long
2014-06-02 17:09 ` Linus Torvalds
2014-06-02 17:12 ` Davidlohr Bueso
2014-06-02 17:42 ` Waiman Long
2014-06-02 20:46 ` Mikulas Patocka
2014-06-02 20:53 ` Linus Torvalds
2014-06-02 21:12 ` Mikulas Patocka
2014-06-03 7:36 ` Peter Zijlstra
2014-06-03 11:14 ` Mikulas Patocka
2014-06-03 13:24 ` Peter Zijlstra
2014-06-03 14:18 ` Mikulas Patocka
2014-06-03 14:07 ` Paul E. McKenney
2014-06-03 15:09 ` Peter Zijlstra
2014-06-03 15:56 ` Paul E. McKenney
2014-06-03 7:20 ` Peter Zijlstra
2014-06-02 21:03 ` Paul E. McKenney
2014-06-06 15:06 ` Peter Zijlstra
2014-06-06 15:15 ` Paul E. McKenney
2014-06-06 15:42 ` Davidlohr Bueso
2014-06-02 16:50 ` Jason Low
2014-06-02 17:03 ` Paul E. McKenney
2014-06-02 17:25 ` Waiman Long
2014-06-02 17:38 ` H. Peter Anvin
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=20140603075433.GI11096@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=aswin@hp.com \
--cc=chegu_vinod@hp.com \
--cc=dave.anglin@bell.net \
--cc=davidlohr@hp.com \
--cc=deller@gmx.de \
--cc=hpa@zytor.com \
--cc=jason.low2@hp.com \
--cc=jejb@parisc-linux.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-parisc@vger.kernel.org \
--cc=mpatocka@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=riel@redhat.com \
--cc=scott.norton@hp.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=waiman.long@hp.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