Messages in this thread Patch in this message | | | From | Mika Westerberg <> | Subject | [PATCH] gpio/lynxpoint: check if the interrupt is enabled in IRQ handler | Date | Tue, 1 Oct 2013 17:35:43 +0300 |
| |
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
| |