Re: [PATCH V2] regulator: core: add support for configuring turn-on time through constraints

[Stephen Warren <swarren@wwwdotorg.org>]

On 09/11/2013 11:46 AM, Laxman Dewangan wrote:
> On Wednesday 11 September 2013 10:47 PM, Stephen Warren wrote:
>> On 09/11/2013 06:58 AM, Laxman Dewangan wrote:
>>> The Turn-on time of the regulator depends on the regulator device's
>>> electrical characteristics. Sometimes regulator turn-on time also
>>> depends on the capacitive load on the given platform and it can be
>>> more than the datasheet value.
>>>
>>> The driver provides the enable-time as per datasheet.
>>>
>>> Add support for configure the enable ramp time through regulator
>>> constraints so that regulator core can take this value for enable
>>> time for that regulator.
>>> diff --git
>>> a/Documentation/devicetree/bindings/regulator/regulator.txt
>>> b/Documentation/devicetree/bindings/regulator/regulator.txt
>>>   - regulator-ramp-delay: ramp delay for regulator(in uV/uS)
>>>     For hardwares which support disabling ramp rate, it should be
>>> explicitly
>>>     intialised to zero (regulator-ramp-delay = <0>) for disabling
>>> ramp delay.
>>> +- regulator-enable-ramp-delay: Turn-on time for regulator(in uSec).
>>> This is
>>> +  the time time taken to reach within some proportion of the target
>>> voltage
>>> +  from off state.
>> This is still a bit unclear. What proportion of the target voltage?
>> There's no mention that this describes the delay due to the
>> board/environment rather than the delay due to the internal operation of
>> the regulator itself. How about:
>>
>> - regulator-enable-ramp-delay: The time taken, in uSec, for the supply
>> rail to reach the target voltage, plus/minus whatever tolerance the
>> board design requires, once the regulator output itself has ramped up.
>> This value is in addition to whatever built-in ramp time is inherent in
>> the regulator's own internal design or configuration. This property
>> describes the additional ramp time required due to board design issues
>> such as trace capacitance and load on the supply.
>>
>> That's text repeats "additional" a bit, but I think describes the
>> situation correctly?
> 
> I wanted to provide the absolute delay rather than additional delay on
> top of inherit delay from device.

I suppose that either is fine from a DT perspective. But, the regulator
drivers already know their internal delay, so presumably driver code
will have to take the value from DT, and subtract out whatever delay the
driver already embodies, in order to calculate the extra delay required?
Or, if this property is set, does the driver-specified delay just get
ignored?