[PATCH v2 1/9] dt-bindings: arm-smmu: Allow up to 3 power-domains

[Konrad Dybcio]

On 14/11/2022 14:00, Krzysztof Kozlowski wrote:
> On 14/11/2022 12:17, Konrad Dybcio wrote:
>> On 14/11/2022 12:01, Krzysztof Kozlowski wrote:
>>> On 14/11/2022 11:42, Konrad Dybcio wrote:
>>>> Some SMMUs require that a vote is held on as much as 3 separate PDs
>>>> (hello Qualcomm). Allow it in bindings.
>>>>
>>>> Signed-off-by: Konrad Dybcio <konrad.dybcio at linaro.org>
>>>> ---
>>>> Changes since v1:
>>>> - Add minItems
>>>>
>>>>    Documentation/devicetree/bindings/iommu/arm,smmu.yaml | 3 ++-
>>>>    1 file changed, 2 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
>>>> index 9066e6df1ba1..82bc696de662 100644
>>>> --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
>>>> +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
>>>> @@ -159,7 +159,8 @@ properties:
>>>>              through the TCU's programming interface.
>>>>    
>>>>      power-domains:
>>>> -    maxItems: 1
>>>> +    minItems: 0
>>> It cannot be 0.
>>>
>>> minItems: 1
>>>
>>> Anyway you still need to restrict it per variant, as I said in previous
>>> version.
>> Hm.. I'm not entirely sure what you mean.. Should I add a list of
>> compatibles
> Yes and limit it to maxItems: 1 for "else".

I tried adding:



   - if:
       properties:
         compatible:
           contains:
             enum:
               - qcom,sm6375-smmu-500
     then:
       properties:
         power-domains:
           minItems: 3
           maxItems: 3
     else:
       properties:
         power-domains:
           maxItems: 1


Right under the nvidia reg if-else in the allOf, but dtbs_check throws 
errors like:


/home/konrad/linux/arch/arm64/boot/dts/qcom/msm8998-sony-xperia-yoshino-poplar.dtb: 
iommu at 5040000: 'power-domains' does not match any of the regexes: 
'pinctrl-[0-9]+'


Any clues as to why?


Konrad

>
>> that are allowed to have 3 power-domains and leave it as it was before
>> in the
>> 'else' case?
> Best regards,
> Krzysztof
>