Re: [RFC PATCH 5/6] extcon-gpio: Describe devicetree bindings

[Mark Rutland <mark.rutland@arm.com>]

On Fri, Aug 30, 2013 at 05:29:37AM +0100, Guenter Roeck wrote:
> Signed-off-by: Guenter Roeck <linux@roeck-us.net>
> ---
>  .../devicetree/bindings/extcon/extcon-gpio         |   23 ++++++++++++++++++++
>  1 file changed, 23 insertions(+)
>  create mode 100644 Documentation/devicetree/bindings/extcon/extcon-gpio
> 
> diff --git a/Documentation/devicetree/bindings/extcon/extcon-gpio b/Documentation/devicetree/bindings/extcon/extcon-gpio
> new file mode 100644
> index 0000000..091ddc6
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/extcon/extcon-gpio
> @@ -0,0 +1,23 @@
> +Device-Tree bindings for extcon/extcon-gpio driver

Bindings shouldn't refer to Linux-specifics like particular drivers.
What class of hardware are you actually trying to describe?

> +
> +Required properties:
> +	- compatible = "gpio-connector";
> +	- presence-detect-gpios - presence detect gpio pin
> +
> +Optional properties:
> +	- debounce-interval - debounce interval in milli-seconds
> +	- state-on - on (connected) state
> +	- state-off - off (disconnected) state
> +	  Depending on the type of connector or cable, states may
> +	  for example be reported as "connected"/"disconnected"
> +	  or "inserted"/"removed".

I don't understand what the state-* properties describe. Do these
provide semantic information to drivers? What is the full set of valid
values?

> +
> +Example node:
> +
> +	some-connector {
> +		compatible = "gpio-connector";
> +		presence-detect-gpios = <&gpio1 7 1>;
> +		debounce-interval = <1>;
> +		state-on = "connected";
> +		state-on = "disconnected";
> +	};

I'm not sure how much value this adds to bindings over describing the
gpios directly. This seems to add a layer of indirection because of
Linux internals.

Thanks,
Mark.