Re: [PATCH 5/7] dt-bindings: HID: i2c-hid: goodix: Add mainboard-vddio-supply

[Dmitry Torokhov <dmitry.torokhov@gmail.com>]

On Mon, Feb 06, 2023 at 06:48:14PM -0800, Douglas Anderson wrote:
> The goodix i2c-hid bindings currently support two models of
> touchscreen: GT7375P and GT7986U. The datasheets of both touchscreens
> show the following things:
> * The mainboard that the touchscreen is connected to is only expected
>   to supply one voltage to the touchscreen: 3.3V.
> * The touchscreen, depending on stuffing options, can accept IO to the
>   touchscreen as either 3.3V or 1.8V. Presumably this means that the
>   touchscreen has its own way internally to make or deal with 1.8V
>   signals when it's configured for 1.8V IO.
> 
> NOTE: you've got to look very carefully at the datasheet for the
> touchscreen to see that the above bullets are true. Specifically, the
> datasheet shows a signal called VDDIO and one might think that this is
> where a mainboard would provide VDDIO to the touchscreen. Upon closer
> inspection, however, a footnote can be found that says "When VDDIO is
> left floating, the logic level is 1.8V [...]; when VDDIO is connected
> to AVDD, the logic level is AVDD.". Thus the VDDIO pin on the
> touchscreen IC is actually a selector and not a pin whre the mainboard
> would pass a reference voltage.
> 
> The fact that the touchscreen isn't supplied 1.8V by the mainboard
> means that when I originally submitted bindings for these touchscreens
> I only listed the 3.3V rail in the bindings. It can be noted that the
> original bindings and driver were added for sc7180-trogdor boards and
> these boards all use 3.3V IO via a level shifter on the mainboard.
> 
> It turns out that with sc7280-herobrine-evoker, we've got a bit of a
> strange monkey on our hands. Due to some very interesting but
> (unfortunately) set-in-stone hardware design, we are doing 1.8V IO to
> the touchscreen but we _also_ have some extra buffers on the mainboard
> that need to be powered up to make the IO lines work. After much
> pondering about this, it seems like the best way to handle this is to
> add an optional "mainboard-vddio" rail to the bindings that is used to
> power up the buffers. Specifically, the fact that the touchscreen
> datasheet documents that its IOs can be at a different voltage level
> than its main power rail means that there truly are two voltage rails
> associated with the touchscreen, even if we don't actually provide the
> IO rail to it. Thus it doesn't feel absurd for the DT node on the host
> to have a 1.8V rail to power up anything related to its 1.8V logic.
> 
> Signed-off-by: Douglas Anderson <dianders@chromium.org>

We went over this with Doug offline, and after re-reading the spec sheet
this does make sense to me.

Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>

> ---
> 
>  .../devicetree/bindings/input/goodix,gt7375p.yaml          | 7 +++++++
>  1 file changed, 7 insertions(+)
> 
> diff --git a/Documentation/devicetree/bindings/input/goodix,gt7375p.yaml b/Documentation/devicetree/bindings/input/goodix,gt7375p.yaml
> index 1c191bc5a178..ce18d7dadae2 100644
> --- a/Documentation/devicetree/bindings/input/goodix,gt7375p.yaml
> +++ b/Documentation/devicetree/bindings/input/goodix,gt7375p.yaml
> @@ -36,6 +36,13 @@ properties:
>    vdd-supply:
>      description: The 3.3V supply to the touchscreen.
>  
> +  mainboard-vddio-supply:
> +    description:
> +      The supply on the main board needed to power up IO signals going
> +      to the touchscreen. This supply need not go to the touchscreen
> +      itself as long as it allows the main board to make signals compatible
> +      with what the touchscreen is expecting for its IO rails.
> +
>  required:
>    - compatible
>    - reg
> -- 
> 2.39.1.519.gcb327c4b5f-goog
> 

-- 
Dmitry