From mboxrd@z Thu Jan  1 00:00:00 1970
From: arnd@arndb.de (Arnd Bergmann)
Date: Tue, 04 Nov 2014 08:39:55 +0100
Subject: [PATCH v4 1/8] ARM: mediatek: Add basic support for mt8127
In-Reply-To: <1415083006.10186.85.camel@mtksdaap41>
References: <1413973797-17619-1-git-send-email-yingjoe.chen@mediatek.com>
 <CABuKBeLYMbD-dV_25FJd_NE1RgfVkgF+SoCiAx9O9jKUUAcexA@mail.gmail.com>
 <1415083006.10186.85.camel@mtksdaap41>
Message-ID: <13477264.GuOdydWub7@wuerfel>
To: linux-arm-kernel@lists.infradead.org
List-Id: linux-arm-kernel.lists.infradead.org

On Tuesday 04 November 2014 14:36:45 HC Yen wrote:
> > > +
> > > +#include <dt-bindings/interrupt-controller/irq.h>
> > > +#include <dt-bindings/interrupt-controller/arm-gic.h>
> > > +#include "skeleton64.dtsi"
> > 
> > Cortex a7 is 32 bits, right? So why do you use skeleton64.dtsi?
> 
> Cortex-A7 is 32-bit, but that doesn't mean it can only have 32-bit
> physical address.  With LPAE enabled, we can have physical address more
> than 32 bits.
> 
> The main difference between "skeleton64.dtsi" and "skeleton.dtsi" is
> "#address-cells" property set to 2.  Although there are few sources
> using "skeleton64.dtsi", some of them write "#address-cells = <2>"
> directly in order to have 64-bit address space.  ARM's TC2 reference
> platform (vexpress-v2p-ca15_a7.dts) is an example.
> 
> Some of MediaTek ARMv7 SoCs support address space larger than 4GB. It
> will be convenient to share the sources if we all use 64-bit device
> tree.

Right, in general, I'd use #address-cells=<2> for Cortex-A7/A15/A17.

	Arnd