[PATCH 1/3] dt-bindings: add document of mediatek efuse driver

Srinivas Kandagatla srinivas.kandagatla at linaro.org
Mon Oct 26 03:55:20 PDT 2015



On 26/10/15 10:23, Sascha Hauer wrote:
> On Mon, Oct 26, 2015 at 09:56:14AM +0000, Srinivas Kandagatla wrote:
>>
>>
>> On 16/10/15 09:39, andrew-ct.chen at mediatek.com wrote:
>>> From: Andrew-CT Chen <andrew-ct.chen at mediatek.com>
>>>
>>> Add Mediatek MT8173 EFUSE Devicetree binding file
>>>
>>> Signed-off-by: Andrew-CT Chen <andrew-ct.chen at mediatek.com>
>>
>> Looks good to me, minor comment below.
>>
>> Will queue this for v4.5 once v4.4-rc1 is released.
>>
>>
>>> ---
>>>   .../devicetree/bindings/nvmem/mtk-efuse.txt        | 36 ++++++++++++++++++++++
>>>   1 file changed, 36 insertions(+)
>>>   create mode 100644 Documentation/devicetree/bindings/nvmem/mtk-efuse.txt
>>>
>>> diff --git a/Documentation/devicetree/bindings/nvmem/mtk-efuse.txt b/Documentation/devicetree/bindings/nvmem/mtk-efuse.txt
>>> new file mode 100644
>>> index 0000000..92edc3d
>>> --- /dev/null
>>> +++ b/Documentation/devicetree/bindings/nvmem/mtk-efuse.txt
>>> @@ -0,0 +1,36 @@
>>> += Mediatek MTK-EFUSE device tree bindings =
>>> +
>>> +This binding is intended to represent MTK-EFUSE which is found in most Mediatek SOCs.
>>> +
>>> +Required properties:
>>> +- compatible: should be "mediatek,mt8173-efuse" or "mediatek,mt8135-efuse"
>>
>> Can we make the compatible more generic for mediatek socs? Like
>> "mediatek,efuse"  Or are they different in each SOC?
>
> While we can add an additional "mediatek,efuse" compatible we should
> always add the most specific compatible first. Otherwise we cannot
> differentiate between SoCs later without changing the device tree.
Yes, that’s correct.

AFAIK, Ideally the driver should have more generic compatible string 
unless there is any SOC specific thing, and DT can still use the order 
of specific, generic compatible strings. If not we would end up adding 
compatible strings into the driver for every new SOC.

--srini

>
> Sascha
>



More information about the linux-arm-kernel mailing list