From: peterz@infradead.org (Peter Zijlstra)
To: linux-riscv@lists.infradead.org
Subject: [RFC PATCH] riscv/locking: Strengthen spin_lock() and spin_unlock()
Date: Tue, 6 Mar 2018 14:00:59 +0100 [thread overview]
Message-ID: <20180306130059.GE25201@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <CA+55aFyT=+8m0mmpeegP8LOVtkCYv3O2vyO-ZcQdLAR=s309jg@mail.gmail.com>
On Mon, Feb 26, 2018 at 09:00:43AM -0800, Linus Torvalds wrote:
> On Mon, Feb 26, 2018 at 8:24 AM, Will Deacon <will.deacon@arm.com> wrote:
> >
> > Strictly speaking, that's not what we've got implemented on arm64: only
> > the read part of the RmW has Acquire semantics, but there is a total
> > order on the lock/unlock operations for the lock.
>
> Hmm.
>
> I thought we had exactly that bug on some architecture with the queued
> spinlocks, and people decided it was wrong.
So ARM64 and Power have the acquire-on-load only thing, but qspinlock
has it per construction on anything that allowes reordering stores.
Given that unlock/lock are ordered, which covers about 99% of the users
out there, and fixing the issue would make things significantly slower
on the weak architectures we let it be.
But yes, its a pesky detail.
WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Will Deacon <will.deacon@arm.com>,
Luc Maranget <luc.maranget@inria.fr>,
Daniel Lustig <dlustig@nvidia.com>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Andrea Parri <parri.andrea@gmail.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Palmer Dabbelt <palmer@sifive.com>, Albert Ou <albert@sifive.com>,
Alan Stern <stern@rowland.harvard.edu>,
Boqun Feng <boqun.feng@gmail.com>,
Nicholas Piggin <npiggin@gmail.com>,
David Howells <dhowells@redhat.com>,
Jade Alglave <j.alglave@ucl.ac.uk>,
Akira Yokosawa <akiyks@gmail.com>, Ingo Molnar <mingo@kernel.org>,
linux-riscv@lists.infradead.org
Subject: Re: [RFC PATCH] riscv/locking: Strengthen spin_lock() and spin_unlock()
Date: Tue, 6 Mar 2018 14:00:59 +0100 [thread overview]
Message-ID: <20180306130059.GE25201@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <CA+55aFyT=+8m0mmpeegP8LOVtkCYv3O2vyO-ZcQdLAR=s309jg@mail.gmail.com>
On Mon, Feb 26, 2018 at 09:00:43AM -0800, Linus Torvalds wrote:
> On Mon, Feb 26, 2018 at 8:24 AM, Will Deacon <will.deacon@arm.com> wrote:
> >
> > Strictly speaking, that's not what we've got implemented on arm64: only
> > the read part of the RmW has Acquire semantics, but there is a total
> > order on the lock/unlock operations for the lock.
>
> Hmm.
>
> I thought we had exactly that bug on some architecture with the queued
> spinlocks, and people decided it was wrong.
So ARM64 and Power have the acquire-on-load only thing, but qspinlock
has it per construction on anything that allowes reordering stores.
Given that unlock/lock are ordered, which covers about 99% of the users
out there, and fixing the issue would make things significantly slower
on the weak architectures we let it be.
But yes, its a pesky detail.
next prev parent reply other threads:[~2018-03-06 13:00 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-22 12:19 [RFC PATCH] riscv/locking: Strengthen spin_lock() and spin_unlock() Andrea Parri
2018-02-22 12:19 ` Andrea Parri
2018-02-22 12:44 ` Andrea Parri
2018-02-22 12:44 ` Andrea Parri
2018-02-22 13:40 ` Peter Zijlstra
2018-02-22 13:40 ` Peter Zijlstra
2018-02-22 14:12 ` Andrea Parri
2018-02-22 14:12 ` Andrea Parri
2018-02-22 17:27 ` Daniel Lustig
2018-02-22 17:27 ` Daniel Lustig
2018-02-22 18:13 ` Paul E. McKenney
2018-02-22 18:13 ` Paul E. McKenney
2018-02-22 18:27 ` Peter Zijlstra
2018-02-22 18:27 ` Peter Zijlstra
2018-02-22 19:47 ` Daniel Lustig
2018-02-22 19:47 ` Daniel Lustig
2018-02-23 11:16 ` Andrea Parri
2018-02-23 11:16 ` Andrea Parri
2018-02-26 10:39 ` Will Deacon
2018-02-26 10:39 ` Will Deacon
2018-02-26 14:21 ` Luc Maranget
2018-02-26 14:21 ` Luc Maranget
2018-02-26 16:06 ` Linus Torvalds
2018-02-26 16:06 ` Linus Torvalds
2018-02-26 16:24 ` Will Deacon
2018-02-26 16:24 ` Will Deacon
2018-02-26 17:00 ` Linus Torvalds
2018-02-26 17:00 ` Linus Torvalds
2018-02-26 17:10 ` Will Deacon
2018-02-26 17:10 ` Will Deacon
2018-03-06 13:00 ` Peter Zijlstra [this message]
2018-03-06 13:00 ` Peter Zijlstra
2018-02-27 5:06 ` Boqun Feng
2018-02-27 5:06 ` Boqun Feng
2018-02-27 10:16 ` Boqun Feng
2018-02-27 10:16 ` Boqun Feng
2018-03-01 15:11 ` Andrea Parri
2018-03-01 15:11 ` Andrea Parri
2018-03-01 21:54 ` Palmer Dabbelt
2018-03-01 21:54 ` Palmer Dabbelt
2018-03-01 22:21 ` Daniel Lustig
2018-03-01 22:21 ` Daniel Lustig
2018-02-22 20:02 ` Paul E. McKenney
2018-02-22 20:02 ` Paul E. McKenney
2018-02-22 18:21 ` Peter Zijlstra
2018-02-22 18:21 ` Peter Zijlstra
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=20180306130059.GE25201@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=linux-riscv@lists.infradead.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.