Date: Mon, 31 Jul 2017 19:04:03 +0800
From: Boqun Feng <boqun.feng@gmail.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>,
        Paul McKenney <paulmck@linux.vnet.ibm.com>,
        linux-kernel@vger.kernel.org, Ingo Molnar <mingo@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Randy Dunlap <rdunlap@infradead.org>
Subject: Re: [RFC][PATCH v3]: documentation,atomic: Add new documents
Message-ID: <20170731110403.ou3zqsp3uviqorkz@tardis>
References: <20170609092450.jwmldgtli57ozxgq@hirez.programming.kicks-ass.net>
 <20170609154442.GB9236@arm.com>
 <20170609193604.ncw3hhgvewzc3h5u@hirez.programming.kicks-ass.net>
 <20170611135632.sl72klbeklelupej@tardis>
 <20170612144929.3wiwtbqopsfpm3qk@hirez.programming.kicks-ass.net>
 <20170726115328.2sxiitivlnlq64dk@hirez.programming.kicks-ass.net>
 <20170726124750.vktrn5zi2gmpzfru@tardis>
 <20170731090535.rjgnoewqg7mhzr55@hirez.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: multipart/signed; micalg=pgp-sha256;
        protocol="application/pgp-signature"; boundary="haur2sczzbhe6hhg"
Content-Disposition: inline
In-Reply-To: <20170731090535.rjgnoewqg7mhzr55@hirez.programming.kicks-ass.net>
User-Agent: NeoMutt/20170609 (1.8.3)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2514
Lines: 83


--haur2sczzbhe6hhg
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Mon, Jul 31, 2017 at 11:05:35AM +0200, Peter Zijlstra wrote:
> On Wed, Jul 26, 2017 at 08:47:50PM +0800, Boqun Feng wrote:
>=20
> > > +
> > > +Further, while something like:
> > > +
> > > +  smp_mb__before_atomic();
> > > +  atomic_dec(&X);
> > > +
> > > +is a 'typical' RELEASE pattern, the barrier is strictly stronger than
> > > +a RELEASE. Similarly for something like:
> > > +
> >=20
> > .. at here. Maybe you planned to put stronger ACQUIRE pattern?
>=20
> Yes, although I struggled to find a sensible one. The problem is that
> ACQUIRE is on loads and value returning atomics have an ACQUIRE variant,
> so why would you ever want to use smp_mb__after_atomic() for this.
>=20
>=20
> That is, the best I could come up with is something like:
>=20
> 	val =3D atomic_fetch_or_relaxed(1, &var);
> 	smp_mb__after_atomic();
>=20
> But in that case we should've just written:
>=20
> 	val =3D atomic_fetch_or_acquire(1, &var);
>=20

Agreed.

And besides, in memory-barriers.txt, the wording is:

 (*) smp_mb__before_atomic();
 (*) smp_mb__after_atomic();

     These are for use with atomic (such as add, subtract, increment and
     decrement) functions that don't return a value, especially when used f=
or
     reference counting.=20

So actually, using smp_mb__after_atomic() for ACQUIRE is a misuse.

>=20
> Suggestions?

As a result, I think it's better we say smp_mb__{before,after}_atomic()
are only for 1) non-value-returning RmW atomic ops, 2)
{set,clear,change}_bit and 3) internal use of atomic primitives(e.g. the
generic version of fully ordered atomics).

1) prevents people to use it for an ACQUIRE, but allows for a RELEASE.
1) & 2) makes atomic_t.txt consistent with memory-barriers.txt
3) explains our usage of those barriers internally.

Thoughts?

Regards,
Boqun

--haur2sczzbhe6hhg
Content-Type: application/pgp-signature; name="signature.asc"

-----BEGIN PGP SIGNATURE-----

iQEzBAABCAAdFiEEj5IosQTPz8XU1wRHSXnow7UH+rgFAll/Dp8ACgkQSXnow7UH
+rjiuggAj+Iv5pq2qq1ua8IFhoZb4KUSg649UQER+PwfiWLpXwcpzOPvBPG7hZ7E
Zd/JE+nGYjq+5myhD38dK3hKAk9LjHeM7Lk5eZJI55M4fA/YJGTTFBz3wCPsuiSH
xKucZp9cCc4GlM/O/u3vqqSdMjbViBmDeQGYwvwDol+cSRHCJNMtY3SvGzEHqmdC
Qa/kygKsIFkcgVj2cGXq7R7pVuwSW5cTy3EApkPkeua36vMhasZGQwS8YLQR+r03
BoQVBVGpMM/J9HqvCYKoVENCLku/2LGPCDqbGxvcNapnISGK2XP9LG09LLiElz2I
TXkdTRGmx6yvd50/M0+9FFlpyuWY8g==
=pI9p
-----END PGP SIGNATURE-----

--haur2sczzbhe6hhg--