From mboxrd@z Thu Jan  1 00:00:00 1970
From: Will Deacon <will.deacon-5wv7dgnIgG8@public.gmane.org>
Subject: Re: [PATCH V4 5/5] arm: mvebu: Added SMP support for Armada XP
Date: Tue, 20 Nov 2012 17:09:44 +0000
Message-ID: <20121120170944.GH27765@mudshark.cambridge.arm.com>
References: <1353357360-7242-1-git-send-email-gregory.clement@free-electrons.com>
 <1353357360-7242-6-git-send-email-gregory.clement@free-electrons.com>
 <20121120164058.GB27765@mudshark.cambridge.arm.com>
 <50ABB499.6090508@free-electrons.com>
 <20121120170127.GE27765@mudshark.cambridge.arm.com>
 <20121120180759.27df512f@skate>
Mime-Version: 1.0
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Return-path: <devicetree-discuss-bounces+gldd-devicetree-discuss=m.gmane.org-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org>
Content-Disposition: inline
In-Reply-To: <20121120180759.27df512f@skate>
List-Unsubscribe: <https://lists.ozlabs.org/options/devicetree-discuss>,
 <mailto:devicetree-discuss-request-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org?subject=unsubscribe>
List-Archive: <http://lists.ozlabs.org/pipermail/devicetree-discuss/>
List-Post: <mailto:devicetree-discuss-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org>
List-Help: <mailto:devicetree-discuss-request-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org?subject=help>
List-Subscribe: <https://lists.ozlabs.org/listinfo/devicetree-discuss>,
 <mailto:devicetree-discuss-request-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org?subject=subscribe>
Errors-To: devicetree-discuss-bounces+gldd-devicetree-discuss=m.gmane.org-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org
Sender: "devicetree-discuss"
 <devicetree-discuss-bounces+gldd-devicetree-discuss=m.gmane.org-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org>
To: Thomas Petazzoni <thomas.petazzoni-wi1+55ScJUtKEb57/3fJTNBPR1lH4CV8@public.gmane.org>
Cc: Lior Amsalem <alior-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>, Andrew Lunn <andrew-g2DYL2Zd6BY@public.gmane.org>, Ike Pan <ike.pan-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>, Nadav Haklai <nadavh-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>, Ian Molton <ian.molton-4yDnlxn2s6sWdaTGBSpHTA@public.gmane.org>, David Marlin <dmarlin-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>, Yehuda Yitschak <yehuday-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>, Jani Monoses <jani.monoses-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>, Russell King <linux-lFZ/pmaqli7XmaaqVzeoHQ@public.gmane.org>, Tawfik Bayouk <tawfik-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>, Dan Frazier <dann.frazier-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>, Eran Ben-Avi <benavi-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>, Leif Lindholm <Leif.Lindholm-5wv7dgnIgG8@public.gmane.org>, Sebastian Hesselbarth <sebastian.hesselbarth-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>, Jason Cooper <jason-NLaQJdtUoK4Be96aLqz0jA@public.gmane.org>, "jcm-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org" <jcm-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>, "devicetree-discuss-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org" <devicetree-discuss-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org>, "rob.herring-bsGFqQB8/DxBDgjK7y7TUQ@public.gmane.org" <rob.herring-bsGFqQB8/DxBDgjK7y7TUQ@public.gmane.org>, Ben Dooks <ben-linux-elnMNo+KYs3YtjvyW6yDsg@public.gmane.org>, Mike Turquette <mturquette-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>, "linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org" <linux-arm-kernel-IAPFreCvJWOunwaRDDq4rA@public.gmane.org>
List-Id: devicetree@vger.kernel.org

On Tue, Nov 20, 2012 at 05:07:59PM +0000, Thomas Petazzoni wrote:
> Dear Will Deacon,
> =

> On Tue, 20 Nov 2012 17:01:27 +0000, Will Deacon wrote:
> =

> > > I prefer to keep them separate, as we can use coherency without SMP.
> > > That's why I create the coherency_ll.S file instead of putting
> > > everything in this file.
> > =

> > Hmm, can you elaborate a bit more on coherency without SMP please? Do
> > these controls also affect IO coherency?
> =

> The coherency unit does coherency between CPUs, but also between the
> CPU and the devices for DMA. So for example the MV78230 is a single-core
> variant of the Armada XP, so having CONFIG_SMP for it is useless, but
> you still want the CPU to join the coherency fabric in order to provide
> coherency with I/O.
> =

> Thanks to the coherency unit, we have an almost DMA coherent
> architecture (see the HW I/O coherency patches from Gr=E9gory for
> details).

Ok, gotcha -- I didn't realise it was all controlled by the same register on
the CPU side.

Thanks for the explanation,

Will