Re: [PATCH v1 1/1] backlight: hx8357: Convert to agnostic GPIO API

[Andy Shevchenko]

On Fri, Mar 17, 2023 at 09:53:40PM +0100, Linus Walleij wrote:
> On Fri, Mar 17, 2023 at 7:51 PM Andy Shevchenko
> <andriy.shevchenko@xxxxxxxxxxxxxxx> wrote:
> 
> > The of_gpio.h is going to be removed. In preparation of that convert
> > the driver to the agnostic API.
> >
> > Signed-off-by: Andy Shevchenko <andriy.shevchenko@xxxxxxxxxxxxxxx>
> 
> Thanks for fixing this Andy!
> 
> > -#if !IS_ENABLED(CONFIG_LCD_HX8357)
> > +#if IS_ENABLED(CONFIG_LCD_HX8357)
> >                 /*
> >                  * Himax LCD controllers used incorrectly named
> >                  * "gpios-reset" property and also specified wrong
> > @@ -452,7 +452,7 @@ static struct gpio_desc *of_find_gpio_rename(struct device_node *np,
> >                  */
> >                 const char *compatible;
> >         } gpios[] = {
> > -#if !IS_ENABLED(CONFIG_LCD_HX8357)
> > +#if IS_ENABLED(CONFIG_LCD_HX8357)
> >                 /* Himax LCD controllers used "gpios-reset" */
> >                 { "reset",      "gpios-reset",  "himax,hx8357" },
> >                 { "reset",      "gpios-reset",  "himax,hx8369" },
> 
> Eh what happened here .. it's even intuitively wrong.

I believe it had to be something  like

	#if 0 && IS_ENABLED()

to show that this change is for the future.
Currently it does something unneeded for the kernels with that option off.

> I would add
> Fixes: fbbbcd177a27 ("gpiolib: of: add quirk for locating reset lines
> with legacy bindings")

I'm not sure. But it's fine, I can add it. Just want to double confirm
you really want this Fixes tag.

> It wasn't used until now it seems so not a regression and no
> need for a separate patch.

Exactly why I'm not sure about the tag :-)

> Other than that it looks correct.
> Reviewed-by: Linus Walleij <linus.walleij@xxxxxxxxxx>

Thank you!

-- 
With Best Regards,
Andy Shevchenko