[PATCH 0/2] Improvement for pca953x drivers

[PATCH 0/2] Improvement for pca953x drivers

[Gregory CLEMENT]

Hi Linus,

those two patches are the begining of the improvement work we have
spoken about earlier. I started with the two patches you sent.

I've just made a small fix to make it build on the 2nd patch so I keep
your autorship and signed-off.

For the second one, it didn't build too, but I made a more substantial
change on it by moving the setting of the irq to the map function. So
for this one, I took the authorship and remove your signed-off to not
make you responsible of my possible bug! :)

I've compiled and run it, but as I don't have support for the pca905
interrupt on my board, I can't say it didn't break anything. Maybe
this time again Maxime will be willing to test it.

For the remaining improvement related to the PWA and MMP #ifdef, I
hope to be able to work on it this week-end.

Regards

Gregory CLEMENT (1):
  gpio: pca953x: use simple irqdomain

Linus Walleij (1):
  gpio: pca953x: use managed resources

 drivers/gpio/gpio-pca953x.c |   97 ++++++++++++++++---------------------------
 1 file changed, 36 insertions(+), 61 deletions(-)

-- 
1.7.9.5

[PATCH 1/2] gpio: pca953x: use simple irqdomain

[Gregory CLEMENT]

This switches the legacy irqdomain to the simple one, which will
auto-allocate descriptors, and also make sure that we use
irq_create_mapping() in the to_irq function. Also use the map function
of irq_domain_ops to setup the irq configuration on demand and no more
statically during the initialization of the driver.

Based on a initial patch from Linus Walleij <linus.walleij@linaro.org>

Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
---
 drivers/gpio/gpio-pca953x.c |   65 +++++++++++++++++++------------------------
 1 file changed, 28 insertions(+), 37 deletions(-)

diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 3a68aed..1dc9906 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -89,7 +89,6 @@ struct pca953x_chip {
 	u8 irq_stat[MAX_BANK];
 	u8 irq_trig_raise[MAX_BANK];
 	u8 irq_trig_fall[MAX_BANK];
-	int	 irq_base;
 	struct irq_domain *domain;
 #endif
 
@@ -372,7 +371,7 @@ static int pca953x_gpio_to_irq(struct gpio_chip *gc, unsigned off)
 	struct pca953x_chip *chip;
 
 	chip = container_of(gc, struct pca953x_chip, gpio_chip);
-	return chip->irq_base + off;
+	return irq_create_mapping(chip->domain, off);
 }
 
 static void pca953x_irq_mask(struct irq_data *d)
@@ -520,6 +519,27 @@ static irqreturn_t pca953x_irq_handler(int irq, void *devid)
 	return IRQ_HANDLED;
 }
 
+static int pca953x_gpio_irq_map(struct irq_domain *d, unsigned int irq,
+		       irq_hw_number_t hwirq)
+{
+	irq_clear_status_flags(irq, IRQ_NOREQUEST);
+	irq_set_chip_data(irq, d->host_data);
+	irq_set_chip(irq, &pca953x_irq_chip);
+	irq_set_nested_thread(irq, true);
+#ifdef CONFIG_ARM
+	set_irq_flags(irq, IRQF_VALID);
+#else
+	irq_set_noprobe(irq);
+#endif
+
+	return 0;
+}
+
+static const struct irq_domain_ops pca953x_irq_simple_ops = {
+	.map = pca953x_gpio_irq_map,
+	.xlate = irq_domain_xlate_twocell,
+};
+
 static int pca953x_irq_setup(struct pca953x_chip *chip,
 			     const struct i2c_device_id *id,
 			     int irq_base)
@@ -529,7 +549,6 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 
 	if (irq_base != -1
 			&& (id->driver_data & PCA_INT)) {
-		int lvl;
 
 		switch (chip->chip_type) {
 		case PCA953X_TYPE:
@@ -552,34 +571,13 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 			chip->irq_stat[i] &= chip->reg_direction[i];
 		mutex_init(&chip->irq_lock);
 
-		chip->irq_base = irq_alloc_descs(-1, irq_base, chip->gpio_chip.ngpio, -1);
-		if (chip->irq_base < 0)
-			goto out_failed;
-
-		chip->domain = irq_domain_add_legacy(client->dev.of_node,
+		chip->domain = irq_domain_add_simple(client->dev.of_node,
 						chip->gpio_chip.ngpio,
-						chip->irq_base,
-						0,
-						&irq_domain_simple_ops,
+						irq_base,
+						&pca953x_irq_simple_ops,
 						NULL);
-		if (!chip->domain) {
-			ret = -ENODEV;
-			goto out_irqdesc_free;
-		}
-
-		for (lvl = 0; lvl < chip->gpio_chip.ngpio; lvl++) {
-			int irq = lvl + chip->irq_base;
-
-			irq_clear_status_flags(irq, IRQ_NOREQUEST);
-			irq_set_chip_data(irq, chip);
-			irq_set_chip(irq, &pca953x_irq_chip);
-			irq_set_nested_thread(irq, true);
-#ifdef CONFIG_ARM
-			set_irq_flags(irq, IRQF_VALID);
-#else
-			irq_set_noprobe(irq);
-#endif
-		}
+		if (!chip->domain)
+			return -ENODEV;
 
 		ret = request_threaded_irq(client->irq,
 					   NULL,
@@ -589,25 +587,18 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 		if (ret) {
 			dev_err(&client->dev, "failed to request irq %d\n",
 				client->irq);
-			goto out_irqdesc_free;
+			return ret;
 		}
 
 		chip->gpio_chip.to_irq = pca953x_gpio_to_irq;
 	}
 
 	return 0;
-
-out_irqdesc_free:
-	irq_free_descs(chip->irq_base, chip->gpio_chip.ngpio);
-out_failed:
-	chip->irq_base = -1;
-	return ret;
 }
 
 static void pca953x_irq_teardown(struct pca953x_chip *chip)
 {
 	if (chip->irq_base != -1) {
-		irq_free_descs(chip->irq_base, chip->gpio_chip.ngpio);
 		free_irq(chip->client->irq, chip);
 	}
 }
-- 
1.7.9.5

Re: [PATCH 1/2] gpio: pca953x: use simple irqdomain

[Linus Walleij]

On Fri, Jan 25, 2013 at 5:59 PM, Gregory CLEMENT
<gregory.clement@free-electrons.com> wrote:

> This switches the legacy irqdomain to the simple one, which will
> auto-allocate descriptors, and also make sure that we use
> irq_create_mapping() in the to_irq function. Also use the map function
> of irq_domain_ops to setup the irq configuration on demand and no more
> statically during the initialization of the driver.
>
> Based on a initial patch from Linus Walleij <linus.walleij@linaro.org>
>
> Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>

Patch applied!

Thanks,
Linus Walleij

[PATCH 2/2] gpio: pca953x: use managed resources

[Gregory CLEMENT]

From: Linus Walleij <linus.walleij@linaro.org>

Using the devm_* managed resources the pca driver can be simplified
and cut down on boilerplate code.

[gcl: fixed a inccorect reference to a removed label, "goto fail_out"
became "return ret"]

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
---
 drivers/gpio/gpio-pca953x.c |   32 ++++++++------------------------
 1 file changed, 8 insertions(+), 24 deletions(-)

diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 1dc9906..2405946 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -560,7 +560,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 		}
 		ret = pca953x_read_regs(chip, offset, chip->irq_stat);
 		if (ret)
-			goto out_failed;
+			return ret;
 
 		/*
 		 * There is no way to know which GPIO line generated the
@@ -579,7 +579,8 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 		if (!chip->domain)
 			return -ENODEV;
 
-		ret = request_threaded_irq(client->irq,
+		ret = devm_request_threaded_irq(&client->dev,
+					client->irq,
 					   NULL,
 					   pca953x_irq_handler,
 					   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
@@ -596,12 +597,6 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 	return 0;
 }
 
-static void pca953x_irq_teardown(struct pca953x_chip *chip)
-{
-	if (chip->irq_base != -1) {
-		free_irq(chip->client->irq, chip);
-	}
-}
 #else /* CONFIG_GPIO_PCA953X_IRQ */
 static int pca953x_irq_setup(struct pca953x_chip *chip,
 			     const struct i2c_device_id *id,
@@ -614,10 +609,6 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 
 	return 0;
 }
-
-static void pca953x_irq_teardown(struct pca953x_chip *chip)
-{
-}
 #endif
 
 /*
@@ -736,7 +727,8 @@ static int pca953x_probe(struct i2c_client *client,
 	int ret;
 	u32 invert = 0;
 
-	chip = kzalloc(sizeof(struct pca953x_chip), GFP_KERNEL);
+	chip = devm_kzalloc(&client->dev,
+			sizeof(struct pca953x_chip), GFP_KERNEL);
 	if (chip == NULL)
 		return -ENOMEM;
 
@@ -771,15 +763,15 @@ static int pca953x_probe(struct i2c_client *client,
 	else
 		ret = device_pca957x_init(chip, invert);
 	if (ret)
-		goto out_failed;
+		return ret;
 
 	ret = pca953x_irq_setup(chip, id, irq_base);
 	if (ret)
-		goto out_failed;
+		return ret;
 
 	ret = gpiochip_add(&chip->gpio_chip);
 	if (ret)
-		goto out_failed_irq;
+		return ret;
 
 	if (pdata && pdata->setup) {
 		ret = pdata->setup(client, chip->gpio_chip.base,
@@ -790,12 +782,6 @@ static int pca953x_probe(struct i2c_client *client,
 
 	i2c_set_clientdata(client, chip);
 	return 0;
-
-out_failed_irq:
-	pca953x_irq_teardown(chip);
-out_failed:
-	kfree(chip);
-	return ret;
 }
 
 static int pca953x_remove(struct i2c_client *client)
@@ -821,8 +807,6 @@ static int pca953x_remove(struct i2c_client *client)
 		return ret;
 	}
 
-	pca953x_irq_teardown(chip);
-	kfree(chip);
 	return 0;
 }
 
-- 
1.7.9.5

Re: [PATCH 2/2] gpio: pca953x: use managed resources

[Linus Walleij]

On Fri, Jan 25, 2013 at 5:59 PM, Gregory CLEMENT
<gregory.clement@free-electrons.com> wrote:

> From: Linus Walleij <linus.walleij@linaro.org>
>
> Using the devm_* managed resources the pca driver can be simplified
> and cut down on boilerplate code.
>
> [gcl: fixed a inccorect reference to a removed label, "goto fail_out"
> became "return ret"]

Oh now "gcl" means both Grant C. Likely and Gregory CLement :-)

> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
> Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>

Patch applied, thanks!

Yours,
Linus Walleij

Re: [PATCH 2/2] gpio: pca953x: use managed resources

[Russell King - ARM Linux]

On Mon, Jan 28, 2013 at 11:17:48AM +0100, Linus Walleij wrote:
> On Fri, Jan 25, 2013 at 5:59 PM, Gregory CLEMENT
> <gregory.clement@free-electrons.com> wrote:
> 
> > From: Linus Walleij <linus.walleij@linaro.org>
> >
> > Using the devm_* managed resources the pca driver can be simplified
> > and cut down on boilerplate code.
> >
> > [gcl: fixed a inccorect reference to a removed label, "goto fail_out"
> > became "return ret"]
> 
> Oh now "gcl" means both Grant C. Likely and Gregory CLement :-)

I'd say gcl means Grant C. Likely.  gc would be Gregory Clement.
Initials. :)  Using anything else results in yet more many namespace
clashes.

Maybe we should switch to a numeric namespace instead? :)

Re: [PATCH 0/2] Improvement for pca953x drivers

[Linus Walleij]

On Fri, Jan 25, 2013 at 5:59 PM, Gregory CLEMENT
<gregory.clement@free-electrons.com> wrote:

> those two patches are the begining of the improvement work we have
> spoken about earlier. I started with the two patches you sent.

Thanks for doing this!! :-)

> I've just made a small fix to make it build on the 2nd patch so I keep
> your autorship and signed-off.

OK I don't care about authorship & such stuff, the important thing
to me is that the code works and looks nice and maintainable.

> I've compiled and run it, but as I don't have support for the pca905
> interrupt on my board, I can't say it didn't break anything. Maybe
> this time again Maxime will be willing to test it.

I will apply the patches and then Maxime can shout if it breaks :-)

> For the remaining improvement related to the PWA and MMP #ifdef, I
> hope to be able to work on it this week-end.

Excellent, thanks!

Yours,
Linus Walleij