[11/15,v3] gpio: Add devm_gpiod_unhinge()

This adds a function named devm_gpiod_unhinge() that removes
the resource management from a GPIO descriptor.

I am not sure if this is the best anglosaxon name for the
function, no other managed resources have an equivalent
currently, but I chose "unhinge" as the closest intuitive
thing I could imagine that fits Rusty Russell's API design
criterions "the obvious use is the correct one" and
"the name tells you how to use it".

The idea came out of a remark from Mark Brown that it should
be possible to handle over management of a resource from
devres to the regulator core, and indeed we can do that.

Cc: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>

---
ChangeLog v2->v3:
- Make sure to bail out of gpiod_unhinge() if the descritor
  passed in is NULL or an error pointer.
- Accept of devres_destroy() returns -ENOENT: if we have
  nonexclusive GPIOs, we may attempt to remove resource
  management from the same descriptor multiple times.
ChangeLog v1->v2:
- New patch to be able to hand over GPIO descriptors to
  the regulator core.
- Mark: feel free to apply this to the regulator tree with
  the regulator tree with the rest.
---
 Documentation/driver-model/devres.txt |  1 +
 drivers/gpio/gpiolib-devres.c         | 30 +++++++++++++++++++++++++++
 include/linux/gpio/consumer.h         | 10 +++++++++
 3 files changed, 41 insertions(+)

-- 
2.19.2

Hi Linus,

On 2018-12-05 13:47, Linus Walleij wrote:
> This adds a function named devm_gpiod_unhinge() that removes

> the resource management from a GPIO descriptor.

>

> I am not sure if this is the best anglosaxon name for the

> function, no other managed resources have an equivalent

> currently, but I chose "unhinge" as the closest intuitive

> thing I could imagine that fits Rusty Russell's API design

> criterions "the obvious use is the correct one" and

> "the name tells you how to use it".

>

> The idea came out of a remark from Mark Brown that it should

> be possible to handle over management of a resource from

> devres to the regulator core, and indeed we can do that.

>

> Cc: Bartosz Golaszewski <bgolaszewski@baylibre.com>

> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>

> ---

> ChangeLog v2->v3:

> - Make sure to bail out of gpiod_unhinge() if the descritor

>   passed in is NULL or an error pointer.

> - Accept of devres_destroy() returns -ENOENT: if we have

>   nonexclusive GPIOs, we may attempt to remove resource

>   management from the same descriptor multiple times.

> ChangeLog v1->v2:

> - New patch to be able to hand over GPIO descriptors to

>   the regulator core.

> - Mark: feel free to apply this to the regulator tree with

>   the regulator tree with the rest.

> ---

>  Documentation/driver-model/devres.txt |  1 +

>  drivers/gpio/gpiolib-devres.c         | 30 +++++++++++++++++++++++++++

>  include/linux/gpio/consumer.h         | 10 +++++++++

>  3 files changed, 41 insertions(+)

>

> diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt

> index 43681ca0837f..fc4cc24dfb97 100644

> --- a/Documentation/driver-model/devres.txt

> +++ b/Documentation/driver-model/devres.txt

> @@ -254,6 +254,7 @@ GPIO

>    devm_gpiod_get_index_optional()

>    devm_gpiod_get_optional()

>    devm_gpiod_put()

> +  devm_gpiod_unhinge()

>    devm_gpiochip_add_data()

>    devm_gpiochip_remove()

>    devm_gpio_request()

> diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c

> index a57e968025a8..e9a17ec4de02 100644

> --- a/drivers/gpio/gpiolib-devres.c

> +++ b/drivers/gpio/gpiolib-devres.c

> @@ -346,6 +346,36 @@ void devm_gpiod_put(struct device *dev, struct gpio_desc *desc)

>  }

>  EXPORT_SYMBOL(devm_gpiod_put);

>  

> +/**

> + * devm_gpiod_unhinge - Remove resource management from a gpio descriptor

> + * @dev:	GPIO consumer

> + * @desc:	GPIO descriptor to remove resource management from

> + *

> + * Remove resource management from a GPIO descriptor. This is needed when

> + * you want to hand over lifecycle management of a descriptor to another

> + * mechanism.

> + */

> +

> +void devm_gpiod_unhinge(struct device *dev, struct gpio_desc *desc)

> +{

> +	int ret;

> +

> +	if (IS_ERR_OR_NULL(desc))

> +		return;

> +	ret = devres_destroy(dev, devm_gpiod_release,

> +			     devm_gpiod_match, desc);


    devres_destroy(dev, devm_gpiod_release, devm_gpiod_match, &desc);

> +	/*

> +	 * If the GPIO descriptor is requested as nonexclusive, we

> +	 * may call this function several times on the same descriptor

> +	 * so it is OK if devres_destroy() returns -ENOENT.

> +	 */

> +	if (ret == -ENOENT)

> +		return;

> +	/* Anything else we should warn about */

> +	WARN_ON(ret);

> +}

> +EXPORT_SYMBOL(devm_gpiod_unhinge);

> +

>  /**

>   * devm_gpiod_put_array - Resource-managed gpiod_put_array()

>   * @dev:	GPIO consumer

> diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h

> index 348885f2f3d3..8aebcf822082 100644

> --- a/include/linux/gpio/consumer.h

> +++ b/include/linux/gpio/consumer.h

> @@ -104,6 +104,7 @@ struct gpio_descs *__must_check

>  devm_gpiod_get_array_optional(struct device *dev, const char *con_id,

>  			      enum gpiod_flags flags);

>  void devm_gpiod_put(struct device *dev, struct gpio_desc *desc);

> +void devm_gpiod_unhinge(struct device *dev, struct gpio_desc *desc);

>  void devm_gpiod_put_array(struct device *dev, struct gpio_descs *descs);

>  

>  int gpiod_get_direction(struct gpio_desc *desc);

> @@ -249,6 +250,15 @@ static inline void gpiod_put(struct gpio_desc *desc)

>  	WARN_ON(1);

>  }

>  

> +static inline void devm_gpiod_unhinge(struct device *dev,

> +				      struct gpio_desc *desc)

> +{

> +	might_sleep();

> +

> +	/* GPIO can never have been requested */

> +	WARN_ON(1);

> +}

> +

>  static inline void gpiod_put_array(struct gpio_descs *descs)

>  {

>  	might_sleep();


Best regards
-- 
Marek Szyprowski, PhD
Samsung R&D Institute Poland