[PATCH] gpio/lynxpoint: check if the interrupt is enabled in IRQ handler

[PATCH] gpio/lynxpoint: check if the interrupt is enabled in IRQ handler

[Mika Westerberg]

Checking LP_INT_STAT is not enough in the interrupt handler because its
contents get updated regardless of whether the pin has interrupt enabled or
not. This causes the driver to loop forever for GPIOs that are pulled up.

Fix this by checking the interrupt enable bit for the pin as well.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/gpio/gpio-lynxpoint.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 2d9ca60..41b5913 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -248,14 +248,15 @@ static void lp_gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 	struct lp_gpio *lg = irq_data_get_irq_handler_data(data);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	u32 base, pin, mask;
-	unsigned long reg, pending;
+	unsigned long reg, ena, pending;
 	unsigned virq;
 
 	/* check from GPIO controller which pin triggered the interrupt */
 	for (base = 0; base < lg->chip.ngpio; base += 32) {
 		reg = lp_gpio_reg(&lg->chip, base, LP_INT_STAT);
+		ena = lp_gpio_reg(&lg->chip, base, LP_INT_ENABLE);
 
-		while ((pending = inl(reg))) {
+		while ((pending = (inl(reg) & inl(ena)))) {
 			pin = __ffs(pending);
 			mask = BIT(pin);
 			/* Clear before handling so we don't lose an edge */
-- 
1.8.4.rc3

Re: [PATCH] gpio/lynxpoint: check if the interrupt is enabled in IRQ handler

[Mathias Nyman]

On 10/01/2013 05:35 PM, Mika Westerberg wrote:
> Checking LP_INT_STAT is not enough in the interrupt handler because its
> contents get updated regardless of whether the pin has interrupt enabled or
> not. This causes the driver to loop forever for GPIOs that are pulled up.
>
> Fix this by checking the interrupt enable bit for the pin as well.
>
> Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>

Acked-by: Mathias Nyman <mathias.nyman@linux.intel.com>

Re: [PATCH] gpio/lynxpoint: check if the interrupt is enabled in IRQ handler

[Linus Walleij]

On Tue, Oct 1, 2013 at 4:35 PM, Mika Westerberg
<mika.westerberg@linux.intel.com> wrote:

> Checking LP_INT_STAT is not enough in the interrupt handler because its
> contents get updated regardless of whether the pin has interrupt enabled or
> not. This causes the driver to loop forever for GPIOs that are pulled up.
>
> Fix this by checking the interrupt enable bit for the pin as well.
>
> Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>

Patch applied for fixes with Mathias ACK.

Should this be tagged for -stable as well?

Yours,
Linus Walleij

Re: [PATCH] gpio/lynxpoint: check if the interrupt is enabled in IRQ handler

[Mika Westerberg]

On Fri, Oct 11, 2013 at 12:57:37PM +0200, Linus Walleij wrote:
> On Tue, Oct 1, 2013 at 4:35 PM, Mika Westerberg
> <mika.westerberg@linux.intel.com> wrote:
> 
> > Checking LP_INT_STAT is not enough in the interrupt handler because its
> > contents get updated regardless of whether the pin has interrupt enabled or
> > not. This causes the driver to loop forever for GPIOs that are pulled up.
> >
> > Fix this by checking the interrupt enable bit for the pin as well.
> >
> > Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
> 
> Patch applied for fixes with Mathias ACK.

Thanks!

> Should this be tagged for -stable as well?

Yes, please. I think starting from 3.9 when this driver was merged.