Re: [PATCH net-next v2 3/3] ieee802154: ca8210: Switch to using gpiod API

Mon, Mar 03, 2025 at 09:00:39PM +0100, Linus Walleij kirjoitti:

On Mon, Mar 3, 2025 at 5:49 PM Andy Shevchenko
[off-list ref] wrote:

...

quoted

        reinit_completion(&priv->ca8210_is_awake);
        msleep(ms);
-       gpio_set_value(pdata->gpio_reset, 1);
+       gpiod_set_value(pdata->reset_gpio, 1);

This drives the GPIO low to assert reset, meaning it is something
that should have GPIO_ACTIVE_LOW set in the device tree,

Yeah, the pin 27 is marked as NRESET and description is pointing out to it as
active low.

and it might even have, so let's check what we can check:

git grep cascoda,ca8210
Documentation/devicetree/bindings/net/ieee802154/ca8210.txt:    -
compatible:           Should be "cascoda,ca8210"
Documentation/devicetree/bindings/net/ieee802154/ca8210.txt:
 compatible = "cascoda,ca8210";
drivers/net/ieee802154/ca8210.c:        {.compatible = "cascoda,ca8210", },

well ain't that typical, all users are out of tree. The example
in the bindings file is wrong, setting ACTIVE_HIGH. Sigh, let's
assume all those DTS files somewhere are wrong and they
didn't set GPIO_ACTIVE_LOW in them...

Maybe add a comment in the code that this is wrong and the
driver and DTS files should be fixed.

Or maybe fix in the driver and schema and add a quirk to gpiolib-of.c?

Alternatively patch Documentation/devicetree/bindings/net/ieee802154/ca8210.txt
to set GPIO_ACTIVE_LOW and fix the code to invert it both
here and when getting the GPIO, but it could cause problems
for outoftree users.

Would it? We have such quirks to fix a polarity for other drivers/devices.

Either way, this is good progress:
Reviewed-by: Linus Walleij <redacted>

Thank you!

-- 
With Best Regards,
Andy Shevchenko