[PATCH/RFC 05/15] dt-bindings: display: bridge: thc63lvd1024: Document dual-link operation

[Laurent Pinchart]

Hi Jacopo,

On Sat, Mar 09, 2019 at 12:23:08PM +0100, Jacopo Mondi wrote:
> On Fri, Mar 08, 2019 at 07:57:39PM +0200, Laurent Pinchart wrote:
> > On Fri, Mar 08, 2019 at 05:49:25PM +0100, Jacopo Mondi wrote:
> >> On Thu, Mar 07, 2019 at 01:23:35AM +0200, Laurent Pinchart wrote:
> >>> The THC63LVD1024 LVDS decoder can operate in two modes, single-link or
> >>> dual-link. In dual-link mode both input ports are used to carry even-
> >>> and odd-numbered pixels separately. Document this in the DT bindings,
> >>> along with the related rules governing port and usage.
> >>>
> >>> Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas at ideasonboard.com>
> >>> ---
> >>>  .../bindings/display/bridge/thine,thc63lvd1024.txt         | 7 +++++++
> >>>  1 file changed, 7 insertions(+)
> >>>
> >>> diff --git a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
> >>> index 37f0c04d5a28..4ff6eb9bbc19 100644
> >>> --- a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
> >>> +++ b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
> >>> @@ -28,6 +28,13 @@ Optional video port nodes:
> >>>  - port at 1: Second LVDS input port
> >>>  - port at 3: Second digital CMOS/TTL parallel output
> >>>
> >>> +The device can operate in single-link mode or dual-link mode. In single-link
> >>> +mode, all pixels are received on port at 0, and port at 1 shall not contain any
> >>> +endpoint. In dual-link mode, even-numbered pixels are received on port at 0 and
> >>> +odd-numbered pixels on port at 1, and both port at 0 and port at 1 shall contain
> >>> +endpoints.
> >>
> >> You know, I'm not sure this is helpful, as if we have to go and
> >> describe what the chip supports, a paragraph for dual ouput mode would
> >> be required as well. The bindings already document that the chip
> >> supports single/dual input/output modes, maybe you can just add rules
> >> that prescribes how to populate the endpoints, for both input and
> >> output modes?
> >
> > That's what I was trying to do :-) How else would you like to see it
> > described ?
> 
> I wonder if it won't be enough to expand the Optional endpoint
> properties description as in:
> 
>  - port at 1: Second LVDS input port, to be used for dual-input mode
>  - port at 3: Second digital CMOS/TTL parallel output, to be used for
>    dual-output mode.

I think it's useful to explain the constraints regarding presence (or
absence) of endpoints for ports 0 and 1 depending on which mode the
device operates under, not just what the ports are used for.

> If you prefer providing more context, it's fine what you had, just
> keep in mind there's also dual-output mode and not just the dual-input
> one.

Absolutely. The reason why I haven't expanded the bindings to document
dual-output mode is that I have no way to test it, and I don't think
untested bindings (meaning without a testable end-to-end implementation)
are a good idea.

> Up to you, feel free to add my
> Reviewed-by: Jacopo Mondi <jacopo+renesas at jmondi.org>
> if relevant.
> 
> >>> +
> >>> +
> >>
> >> You can drop this empty line.
> >>
> >>>  Example:
> >>>  --------
> >>>

-- 
Regards,

Laurent Pinchart