Re: [PATCH 1/3] irqchip: qcom-pdc: Fix phantom irq when changing between rising/falling

[Maulik Shah <mkshah@codeaurora.org>]

Hi Doug,

Thanks for the patch. Looks good to me and tested.

Reviewed-by: Maulik Shah <mkshah@codeaurora.org>
Tested-by: Maulik Shah <mkshah@codeaurora.org>

Thanks,
Maulik

On 11/24/2020 5:31 AM, Douglas Anderson wrote:
> We have a problem if we use gpio-keys and configure wakeups such that
> we only want one edge to wake us up.  AKA:
>    wakeup-event-action = <EV_ACT_DEASSERTED>;
>    wakeup-source;
>
> Specifically we end up with a phantom interrupt that blocks suspend if
> the line was already high and we want wakeups on rising edges (AKA we
> want the GPIO to go low and then high again before we wake up).  The
> opposite is also problematic.
>
> Specifically, here's what's happening today:
> 1. Normally, gpio-keys configures to look for both edges.  Due to the
>     current workaround introduced in commit c3c0c2e18d94 ("pinctrl:
>     qcom: Handle broken/missing PDC dual edge IRQs on sc7180"), if the
>     line was high we'd configure for falling edges.
> 2. At suspend time, we change to look for rising edges.
> 3. After qcom_pdc_gic_set_type() runs, we get a phantom interrupt.
>
> We can solve this by just clearing the phantom interrupt.
>
> NOTE: it is possible that this could cause problems for a client with
> very specific needs, but there's not much we can do with this
> hardware.  As an example, let's say the interrupt signal is currently
> high and the client is looking for falling edges.  The client now
> changes to look for rising edges.  The client could possibly expect
> that if the line has a short pulse low (and back high) that it would
> always be detected.  Specifically no matter when the pulse happened,
> it should either have tripped the (old) falling edge trigger or the
> (new) rising edge trigger.  We will simply not trip it.  We could
> narrow down the race a bit by polling our parent before changing
> types, but no matter what we do there will still be a period of time
> where we can't tell the difference between a real transition (or more
> than one transition) and the phantom.
>
> Signed-off-by: Douglas Anderson <dianders@chromium.org>
> ---
>
>   drivers/irqchip/qcom-pdc.c | 19 ++++++++++++++++++-
>   1 file changed, 18 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/irqchip/qcom-pdc.c b/drivers/irqchip/qcom-pdc.c
> index bd39e9de6ecf..7d097164aadc 100644
> --- a/drivers/irqchip/qcom-pdc.c
> +++ b/drivers/irqchip/qcom-pdc.c
> @@ -159,6 +159,8 @@ static int qcom_pdc_gic_set_type(struct irq_data *d, unsigned int type)
>   {
>   	int pin_out = d->hwirq;
>   	enum pdc_irq_config_bits pdc_type;
> +	enum pdc_irq_config_bits old_pdc_type;
> +	int ret;
>   
>   	if (pin_out == GPIO_NO_WAKE_IRQ)
>   		return 0;
> @@ -187,9 +189,24 @@ static int qcom_pdc_gic_set_type(struct irq_data *d, unsigned int type)
>   		return -EINVAL;
>   	}
>   
> +	old_pdc_type = pdc_reg_read(IRQ_i_CFG, pin_out);
>   	pdc_reg_write(IRQ_i_CFG, pin_out, pdc_type);
>   
> -	return irq_chip_set_type_parent(d, type);
> +	ret = irq_chip_set_type_parent(d, type);
> +
> +	/*
> +	 * When we change types the PDC can give a phantom interrupt.
> +	 * Clear it.  Specifically the phantom shows up if a line is already
> +	 * high and we change to rising or if a line is already low and we
> +	 * change to falling but let's be consistent and clear it always.
> +	 *
> +	 * Doing this works because we have IRQCHIP_SET_TYPE_MASKED so the
> +	 * interrupt will be cleared before the rest of the system sees it.
> +	 */
> +	if (old_pdc_type != pdc_type)
> +		irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0);
> +
> +	return ret;
>   }
>   
>   static struct irq_chip qcom_pdc_gic_chip = {

-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, hosted by The Linux Foundation