[PATCH v4 1/8] ARM: mediatek: Add basic support for mt8127

[Matthias Brugger]

2014-11-04 8:39 GMT+01:00 Arnd Bergmann <arnd at arndb.de>:
> 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.

Alright, thanks for clarification. So we should use skeleton64.dtsi
for mt6589 as well, right?

>
>         Arnd



-- 
motzblog.wordpress.com