Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Wed, 11 Jul 2018 13:36:14 -0400 (EDT)
From:   Alan Stern <stern@rowland.harvard.edu>
To:     David Laight <David.Laight@ACULAB.COM>
cc:     "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
        LKMM Maintainers -- Akira Yokosawa <akiyks@gmail.com>,
        Andrea Parri <andrea.parri@amarulasolutions.com>,
        Boqun Feng <boqun.feng@gmail.com>,
        Daniel Lustig <dlustig@nvidia.com>,
        David Howells <dhowells@redhat.com>,
        Jade Alglave <j.alglave@ucl.ac.uk>,
        Luc Maranget <luc.maranget@inria.fr>,
        Nicholas Piggin <npiggin@gmail.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Will Deacon <will.deacon@arm.com>,
        Kernel development list <linux-kernel@vger.kernel.org>
Subject: RE: [PATCH v3] tools/memory-model: Add extra ordering for locks and
 remove it for ordinary release/acquire
In-Reply-To: <3344e7aeb09644758860ac343bd757a1@AcuMS.aculab.com>
Message-ID: <Pine.LNX.4.44L0.1807111333030.1436-100000@iolanthe.rowland.org>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, 11 Jul 2018, David Laight wrote:

> > From: Alan Stern
> > Sent: 10 July 2018 19:18
> > More than one kernel developer has expressed the opinion that the LKMM
> > should enforce ordering of writes by locking. In other words, given
> > the following code:
> >
> > WRITE_ONCE(x, 1);
> > spin_unlock(&s):
> > spin_lock(&s);
> > WRITE_ONCE(y, 1);
> >
> > the stores to x and y should be propagated in order to all other CPUs,
> > even though those other CPUs might not access the lock s. In terms of
> > the memory model, this means expanding the cumul-fence relation.
> 
> The usual 'elephant in the room' is Alpha.
> I don't claim to understand the alpha memory model but it wouldn't
> surprise me if the above is impossible to implement on alpha.

It's not impossible, since Alpha does have a full memory barrier 
instruction (and the implementation uses it).

Alan