diff mbox series

[v1,1/3] gpiolib: acpi: Respect bias settings for GpioInt() resource

Message ID 20201014133154.30610-1-andriy.shevchenko@linux.intel.com
State New
Headers show
Series [v1,1/3] gpiolib: acpi: Respect bias settings for GpioInt() resource | expand

Commit Message

Andy Shevchenko Oct. 14, 2020, 1:31 p.m. UTC
In some cases the GpioInt() resource is coming with bias settings
which may affect system functioning. Respect bias settings for
GpioInt() resource by calling acpi_gpio_update_gpiod_*flags() API
in acpi_dev_gpio_irq_get().

While at it, refactor to configure flags first and, only when succeeded,
map the IRQ descriptor.

Reported-by: Jamie McClymont <jamie@kwiius.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---

This one highly depends on Intel pin control driver changes (for now [1], but
might be more), so it's probably not supposed to be backported (at least right
now).

[1]: https://lore.kernel.org/linux-gpio/20201014104638.84043-1-andriy.shevchenko@linux.intel.com/T/

 drivers/gpio/gpiolib-acpi.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

Comments

Mika Westerberg Oct. 21, 2020, 9:58 a.m. UTC | #1
On Wed, Oct 14, 2020 at 04:31:52PM +0300, Andy Shevchenko wrote:
> In some cases the GpioInt() resource is coming with bias settings
> which may affect system functioning. Respect bias settings for
> GpioInt() resource by calling acpi_gpio_update_gpiod_*flags() API
> in acpi_dev_gpio_irq_get().
> 
> While at it, refactor to configure flags first and, only when succeeded,
> map the IRQ descriptor.
> 
> Reported-by: Jamie McClymont <jamie@kwiius.com>
> Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
> ---
> 
> This one highly depends on Intel pin control driver changes (for now [1], but
> might be more), so it's probably not supposed to be backported (at least right
> now).
> 
> [1]: https://lore.kernel.org/linux-gpio/20201014104638.84043-1-andriy.shevchenko@linux.intel.com/T/
> 
>  drivers/gpio/gpiolib-acpi.c | 12 ++++++++----
>  1 file changed, 8 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
> index 834a12f3219e..52b961673f16 100644
> --- a/drivers/gpio/gpiolib-acpi.c
> +++ b/drivers/gpio/gpiolib-acpi.c
> @@ -942,21 +942,25 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
>  
>  		if (info.gpioint && idx++ == index) {
>  			unsigned long lflags = GPIO_LOOKUP_FLAGS_DEFAULT;
> +			enum gpiod_flags dflags = info.flags;
>  			char label[32];
>  			int irq;
>  
>  			if (IS_ERR(desc))
>  				return PTR_ERR(desc);
>  
> -			irq = gpiod_to_irq(desc);
> -			if (irq < 0)
> -				return irq;
> +			acpi_gpio_update_gpiod_flags(&dflags, &info);
> +			acpi_gpio_update_gpiod_lookup_flags(&lflags, &info);
>  
>  			snprintf(label, sizeof(label), "GpioInt() %d", index);
> -			ret = gpiod_configure_flags(desc, label, lflags, info.flags);
> +			ret = gpiod_configure_flags(desc, label, lflags, dflags);
>  			if (ret < 0)
>  				return ret;
>  
> +			irq = gpiod_to_irq(desc);
> +			if (irq < 0)
> +				return irq;

Should the above be undone if the conversion here fails?

In any case looks good so,

Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Andy Shevchenko Oct. 21, 2020, 4:38 p.m. UTC | #2
On Wed, Oct 21, 2020 at 12:58:54PM +0300, Mika Westerberg wrote:
> On Wed, Oct 14, 2020 at 04:31:52PM +0300, Andy Shevchenko wrote:
> > In some cases the GpioInt() resource is coming with bias settings
> > which may affect system functioning. Respect bias settings for
> > GpioInt() resource by calling acpi_gpio_update_gpiod_*flags() API
> > in acpi_dev_gpio_irq_get().
> > 
> > While at it, refactor to configure flags first and, only when succeeded,
> > map the IRQ descriptor.

...

> > -			irq = gpiod_to_irq(desc);
> > -			if (irq < 0)
> > -				return irq;
> > +			acpi_gpio_update_gpiod_flags(&dflags, &info);
> > +			acpi_gpio_update_gpiod_lookup_flags(&lflags, &info);
> >  
> >  			snprintf(label, sizeof(label), "GpioInt() %d", index);
> > -			ret = gpiod_configure_flags(desc, label, lflags, info.flags);
> > +			ret = gpiod_configure_flags(desc, label, lflags, dflags);
> >  			if (ret < 0)
> >  				return ret;
> >  
> > +			irq = gpiod_to_irq(desc);
> > +			if (irq < 0)
> > +				return irq;
> 
> Should the above be undone if the conversion here fails?

But wouldn't it be not good if we changed direction, for example, and then
change it back? (IRQ requires input, which is safer, right?)

This makes me think what gpiod_to_irq() may do for physical state of the pin.
On the brief search it seems there is no side effect on the pin with that
function, so, perhaps the original order has that in mind to not shuffle with
line if mapping can't be established. But if setting flags fail, we may got
into the state which is not equal to the initial one, right?

So, in either case I see no good way to roll back the physical pin state
changes. But I can return ordering of the calls in next version.

What do you think?

> In any case looks good so,
> 
> Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>

Thanks!
Mika Westerberg Oct. 22, 2020, 6:51 a.m. UTC | #3
On Wed, Oct 21, 2020 at 07:38:44PM +0300, Andy Shevchenko wrote:
> On Wed, Oct 21, 2020 at 12:58:54PM +0300, Mika Westerberg wrote:
> > On Wed, Oct 14, 2020 at 04:31:52PM +0300, Andy Shevchenko wrote:
> > > In some cases the GpioInt() resource is coming with bias settings
> > > which may affect system functioning. Respect bias settings for
> > > GpioInt() resource by calling acpi_gpio_update_gpiod_*flags() API
> > > in acpi_dev_gpio_irq_get().
> > > 
> > > While at it, refactor to configure flags first and, only when succeeded,
> > > map the IRQ descriptor.
> 
> ...
> 
> > > -			irq = gpiod_to_irq(desc);
> > > -			if (irq < 0)
> > > -				return irq;
> > > +			acpi_gpio_update_gpiod_flags(&dflags, &info);
> > > +			acpi_gpio_update_gpiod_lookup_flags(&lflags, &info);
> > >  
> > >  			snprintf(label, sizeof(label), "GpioInt() %d", index);
> > > -			ret = gpiod_configure_flags(desc, label, lflags, info.flags);
> > > +			ret = gpiod_configure_flags(desc, label, lflags, dflags);
> > >  			if (ret < 0)
> > >  				return ret;
> > >  
> > > +			irq = gpiod_to_irq(desc);
> > > +			if (irq < 0)
> > > +				return irq;
> > 
> > Should the above be undone if the conversion here fails?
> 
> But wouldn't it be not good if we changed direction, for example, and then
> change it back? (IRQ requires input, which is safer, right?)
> 
> This makes me think what gpiod_to_irq() may do for physical state of the pin.
> On the brief search it seems there is no side effect on the pin with that
> function, so, perhaps the original order has that in mind to not shuffle with
> line if mapping can't be established. But if setting flags fail, we may got
> into the state which is not equal to the initial one, right?
> 
> So, in either case I see no good way to roll back the physical pin state
> changes. But I can return ordering of the calls in next version.
> 
> What do you think?

If there is no good way rolling back to the previous state then I think
this ordering is as good as the original, so up to you :-)
Hans de Goede Oct. 22, 2020, 9:05 a.m. UTC | #4
Hi,

On 10/21/20 6:38 PM, Andy Shevchenko wrote:
> On Wed, Oct 21, 2020 at 12:58:54PM +0300, Mika Westerberg wrote:

>> On Wed, Oct 14, 2020 at 04:31:52PM +0300, Andy Shevchenko wrote:

>>> In some cases the GpioInt() resource is coming with bias settings

>>> which may affect system functioning. Respect bias settings for

>>> GpioInt() resource by calling acpi_gpio_update_gpiod_*flags() API

>>> in acpi_dev_gpio_irq_get().

>>>

>>> While at it, refactor to configure flags first and, only when succeeded,

>>> map the IRQ descriptor.

> 

> ...

> 

>>> -			irq = gpiod_to_irq(desc);

>>> -			if (irq < 0)

>>> -				return irq;

>>> +			acpi_gpio_update_gpiod_flags(&dflags, &info);

>>> +			acpi_gpio_update_gpiod_lookup_flags(&lflags, &info);

>>>  

>>>  			snprintf(label, sizeof(label), "GpioInt() %d", index);

>>> -			ret = gpiod_configure_flags(desc, label, lflags, info.flags);

>>> +			ret = gpiod_configure_flags(desc, label, lflags, dflags);

>>>  			if (ret < 0)

>>>  				return ret;

>>>  

>>> +			irq = gpiod_to_irq(desc);

>>> +			if (irq < 0)

>>> +				return irq;

>>

>> Should the above be undone if the conversion here fails?

> 

> But wouldn't it be not good if we changed direction, for example, and then

> change it back? (IRQ requires input, which is safer, right?)

> 

> This makes me think what gpiod_to_irq() may do for physical state of the pin.

> On the brief search it seems there is no side effect on the pin with that

> function, so, perhaps the original order has that in mind to not shuffle with

> line if mapping can't be established. But if setting flags fail, we may got

> into the state which is not equal to the initial one, right?

> 

> So, in either case I see no good way to roll back the physical pin state

> changes. But I can return ordering of the calls in next version.

> 

> What do you think?


I think it would be good to do a new version where you keep the original
ordering.

Also if you decide to keep the ordering change, that really should be
in a separate commit and not squashed into this one, so that e.g. a bisect
can determine the difference between the ordering change or the flags
changes causing any issues.

Regards,

Hans
Andy Shevchenko Oct. 22, 2020, 10:43 a.m. UTC | #5
On Thu, Oct 22, 2020 at 12:32 PM Hans de Goede <hdegoede@redhat.com> wrote:
> On 10/21/20 6:38 PM, Andy Shevchenko wrote:
> > On Wed, Oct 21, 2020 at 12:58:54PM +0300, Mika Westerberg wrote:
> >> On Wed, Oct 14, 2020 at 04:31:52PM +0300, Andy Shevchenko wrote:
> >>> In some cases the GpioInt() resource is coming with bias settings
> >>> which may affect system functioning. Respect bias settings for
> >>> GpioInt() resource by calling acpi_gpio_update_gpiod_*flags() API
> >>> in acpi_dev_gpio_irq_get().
> >>>
> >>> While at it, refactor to configure flags first and, only when succeeded,
> >>> map the IRQ descriptor.
> >
> > ...
> >
> >>> -                   irq = gpiod_to_irq(desc);
> >>> -                   if (irq < 0)
> >>> -                           return irq;
> >>> +                   acpi_gpio_update_gpiod_flags(&dflags, &info);
> >>> +                   acpi_gpio_update_gpiod_lookup_flags(&lflags, &info);
> >>>
> >>>                     snprintf(label, sizeof(label), "GpioInt() %d", index);
> >>> -                   ret = gpiod_configure_flags(desc, label, lflags, info.flags);
> >>> +                   ret = gpiod_configure_flags(desc, label, lflags, dflags);
> >>>                     if (ret < 0)
> >>>                             return ret;
> >>>
> >>> +                   irq = gpiod_to_irq(desc);
> >>> +                   if (irq < 0)
> >>> +                           return irq;
> >>
> >> Should the above be undone if the conversion here fails?
> >
> > But wouldn't it be not good if we changed direction, for example, and then
> > change it back? (IRQ requires input, which is safer, right?)
> >
> > This makes me think what gpiod_to_irq() may do for physical state of the pin.
> > On the brief search it seems there is no side effect on the pin with that
> > function, so, perhaps the original order has that in mind to not shuffle with
> > line if mapping can't be established. But if setting flags fail, we may got
> > into the state which is not equal to the initial one, right?
> >
> > So, in either case I see no good way to roll back the physical pin state
> > changes. But I can return ordering of the calls in next version.
> >
> > What do you think?
>
> I think it would be good to do a new version where you keep the original
> ordering.
>
> Also if you decide to keep the ordering change, that really should be
> in a separate commit and not squashed into this one, so that e.g. a bisect
> can determine the difference between the ordering change or the flags
> changes causing any issues.

Ack. Thanks Hans, Mika for your comments! I'll revert that piece of
change. I dunno what I had in mind when I did it in the first place...
diff mbox series

Patch

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 834a12f3219e..52b961673f16 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -942,21 +942,25 @@  int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
 
 		if (info.gpioint && idx++ == index) {
 			unsigned long lflags = GPIO_LOOKUP_FLAGS_DEFAULT;
+			enum gpiod_flags dflags = info.flags;
 			char label[32];
 			int irq;
 
 			if (IS_ERR(desc))
 				return PTR_ERR(desc);
 
-			irq = gpiod_to_irq(desc);
-			if (irq < 0)
-				return irq;
+			acpi_gpio_update_gpiod_flags(&dflags, &info);
+			acpi_gpio_update_gpiod_lookup_flags(&lflags, &info);
 
 			snprintf(label, sizeof(label), "GpioInt() %d", index);
-			ret = gpiod_configure_flags(desc, label, lflags, info.flags);
+			ret = gpiod_configure_flags(desc, label, lflags, dflags);
 			if (ret < 0)
 				return ret;
 
+			irq = gpiod_to_irq(desc);
+			if (irq < 0)
+				return irq;
+
 			irq_flags = acpi_dev_get_irq_type(info.triggering,
 							  info.polarity);