Skip to contentSkip to conversation

dt-bindings: pinctrl: cypress,cy8c95x0: Add reset pin

PATCH In review Naresh Solanki 4 participants 5 messages Jul 14, 2023 – Jul 20, 2023

Subsystems (4)
lore
Share & tools
lore
#0 lore raw

PATCH v3 1/2 dt-bindings: pinctrl: cypress,cy8c95x0: Add reset pin

From: Patrick Rudolph <[email protected]>

This patch adds support for an optional reset pin.

The reset pin is used to bring the chip into a known state and has an internal pull-down, allowing it to be left floating if not needed.

---
Changes in V3:
- Update reset-gpios description.
Changes in V2:
- Update subject
- Update reset-gpios description.

---
 .../devicetree/bindings/pinctrl/cypress,cy8c95x0.yaml         | 4 ++++
 1 file changed, 4 insertions(+)
Documentation/devicetree/bindings/pinctrl/cypress,cy8c95x0.yaml +4 -0
index 222d57541b65..7f30ec2f1e54 100644
@@ -51,6 +51,10 @@ properties:
     description:
       Optional power supply.
 
+  reset-gpios:
+    description: GPIO connected to the XRES pin
+    maxItems: 1
+
 patternProperties:
   '-pins$':
     type: object

base-commit: 3bc551a3007a751a53bfba5b37fa16157f4fb861

Signature · 1 line
2.41.0
#1 lore raw

PATCH v3 2/2 pinctrl: cy8c95x0: Add reset support

From: Patrick Rudolph <[email protected]>

This patch adds support for an optional "reset" GPIO pin in the cy8c95x0 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.

---
Changes in V2:
- None

---
 drivers/pinctrl/pinctrl-cy8c95x0.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
drivers/pinctrl/pinctrl-cy8c95x0.c +15 -0
index 2ecc96691c55..58ca6fac7849 100644
@@ -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);
Signature · 1 line
2.41.0
#2 lore raw

Re: [PATCH v3 2/2] pinctrl: cy8c95x0: Add reset support

Fri, Jul 14, 2023 at 10:19:01AM +0200, Naresh Solanki kirjoitti:

Quoted 3 lines

From: Patrick Rudolph <[email protected]>

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.

Quoted 10 lines

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.

...

drivers/pinctrl/pinctrl-cy8c95x0.c static int cy8c95x0_probe(struct i2c_client *client) · line 1388

Quoted 2 lines
drivers/pinctrl/pinctrl-cy8c95x0.c +2 -0
+	/* 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

drivers/pinctrl/pinctrl-cy8c95x0.c static int cy8c95x0_probe(struct i2c_client *client) · line 1390

Quoted 2 lines
drivers/pinctrl/pinctrl-cy8c95x0.c +2 -0
+	if (IS_ERR(chip->gpio_reset)) {
+		ret = dev_err_probe(chip->dev, PTR_ERR(chip->gpio_reset),

chip->dev

Why inconsistent?

drivers/pinctrl/pinctrl-cy8c95x0.c static int cy8c95x0_probe(struct i2c_client *client) · line 1392

Quoted 2 lines
drivers/pinctrl/pinctrl-cy8c95x0.c +2 -0
+				    "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.

drivers/pinctrl/pinctrl-cy8c95x0.c static int cy8c95x0_probe(struct i2c_client *client) · line 1396

Quoted 5 lines
drivers/pinctrl/pinctrl-cy8c95x0.c +4 -0
+	} 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.

drivers/pinctrl/pinctrl-cy8c95x0.c static int cy8c95x0_probe(struct i2c_client *client) · line 1398

Quoted 1 line
drivers/pinctrl/pinctrl-cy8c95x0.c +1 -0
+		gpiod_set_consumer_name(chip->gpio_reset, "CY8C95X0 RESET");

This can be done uncoditionally before toggling the reset.

drivers/pinctrl/pinctrl-cy8c95x0.c static int cy8c95x0_probe(struct i2c_client *client) · line 1399

Quoted 1 line
drivers/pinctrl/pinctrl-cy8c95x0.c +1 -0
+	}

...

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

Signature · 2 lines
With Best Regards,
Andy Shevchenko
Reviewed-by on v3 1/2
#3 lore raw
In reply to Naresh Solanki
Quoted 10 lines · Naresh Solanki

From: Patrick Rudolph <[email protected]>

This patch adds support for an optional reset pin.

The reset pin is used to bring the chip into a known state and has an internal pull-down, allowing it to be left floating if not needed.

---

Best regards,
Krzysztof