| Message ID | 20230714081902.2621771-2-Naresh.Solanki@9elements.com |
|---|---|
| State | New |
| Headers | show |
| Series | [v3,1/2] dt-bindings: pinctrl: cypress,cy8c95x0: Add reset pin | expand |
Fri, Jul 14, 2023 at 10:19:01AM +0200, Naresh Solanki kirjoitti: > From: Patrick Rudolph <patrick.rudolph@9elements.com> > > This patch adds support for an optional "reset" GPIO pin in the cy8c95x0 Find "This patch" in the Submitting Patches documentation and modify this accordingly. > pinctrl driver. On probe, the reset pin is pulled low to bring chip out > of reset. The reset pin has an internal pull-down and can be left > floating if not required. > > The datasheet doesn't mention any timing related to the reset pin. > > Based on empirical tests, it was found that the chip requires a > delay of 250 milliseconds before accepting I2C transfers after driving > the reset pin low. Therefore, a delay of 250ms is added before > proceeding with I2C transfers. ... > + /* bring the chip out of reset if reset pin is provided */ > + chip->gpio_reset = devm_gpiod_get_optional(&client->dev, "reset", GPIOD_OUT_HIGH); &client->dev > + if (IS_ERR(chip->gpio_reset)) { > + ret = dev_err_probe(chip->dev, PTR_ERR(chip->gpio_reset), chip->dev Why inconsistent? > + "Failed to get GPIO 'reset'\n"); > + goto err_exit; I haven't looked at the context, but this seems like a smoke, we usually don't have such in devm-enabled drivers. > + } else if (chip->gpio_reset) { > + usleep_range(1000, 2000); > + gpiod_set_value_cansleep(chip->gpio_reset, 0); > + usleep_range(250000, 300000); This is incorrect use of usleep_range(). Please, read documentation Documentation/timers/timers-howto.rst on the topic. The fix can be switching to fsleep() in both branches. > + gpiod_set_consumer_name(chip->gpio_reset, "CY8C95X0 RESET"); This can be done uncoditionally before toggling the reset. > + } ... This change wasn't Cc'ed to me, however I was contributing a lot into this driver. I would recommend to use my "smart" script [1] to send patches. It has some heuristics which works well in 98% of the cases for me. [1]: https://github.com/andy-shev/home-bin-tools/blob/master/ge2maintainer.sh
diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c index 2ecc96691c55..58ca6fac7849 100644 --- a/drivers/pinctrl/pinctrl-cy8c95x0.c +++ b/drivers/pinctrl/pinctrl-cy8c95x0.c @@ -164,6 +164,7 @@ struct cy8c95x0_pinctrl { struct pinctrl_desc pinctrl_desc; char name[32]; unsigned int tpin; + struct gpio_desc *gpio_reset; }; static const struct pinctrl_pin_desc cy8c9560_pins[] = { @@ -1383,6 +1384,20 @@ static int cy8c95x0_probe(struct i2c_client *client) chip->regulator = reg; } + /* bring the chip out of reset if reset pin is provided */ + chip->gpio_reset = devm_gpiod_get_optional(&client->dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(chip->gpio_reset)) { + ret = dev_err_probe(chip->dev, PTR_ERR(chip->gpio_reset), + "Failed to get GPIO 'reset'\n"); + goto err_exit; + } else if (chip->gpio_reset) { + usleep_range(1000, 2000); + gpiod_set_value_cansleep(chip->gpio_reset, 0); + usleep_range(250000, 300000); + + gpiod_set_consumer_name(chip->gpio_reset, "CY8C95X0 RESET"); + } + chip->regmap = devm_regmap_init_i2c(client, &cy8c95x0_i2c_regmap); if (IS_ERR(chip->regmap)) { ret = PTR_ERR(chip->regmap);