diff mbox series

of: property: Add device link support for interrupts

Message ID 20201218210750.3455872-1-saravanak@google.com
State New
Headers show
Series of: property: Add device link support for interrupts | expand

Commit Message

Saravana Kannan Dec. 18, 2020, 9:07 p.m. UTC
Add support for creating device links out of interrupts property.

Cc: Marc Zyngier <maz@kernel.org>
Cc: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Saravana Kannan <saravanak@google.com>
---
Rob/Greg,

This might need to go into driver-core to avoid conflict
due to fw_devlink refactor series that merged there.

Thanks,
Saravana


 drivers/of/property.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

Comments

Marc Zyngier Dec. 21, 2020, 9:30 a.m. UTC | #1
On 2020-12-18 21:07, Saravana Kannan wrote:
> Add support for creating device links out of interrupts property.

> 

> Cc: Marc Zyngier <maz@kernel.org>

> Cc: Kevin Hilman <khilman@baylibre.com>

> Signed-off-by: Saravana Kannan <saravanak@google.com>

> ---

> Rob/Greg,

> 

> This might need to go into driver-core to avoid conflict

> due to fw_devlink refactor series that merged there.

> 

> Thanks,

> Saravana

> 

> 

>  drivers/of/property.c | 17 +++++++++++++++++

>  1 file changed, 17 insertions(+)

> 

> diff --git a/drivers/of/property.c b/drivers/of/property.c

> index 5f9eed79a8aa..e56a5eae0a0b 100644

> --- a/drivers/of/property.c

> +++ b/drivers/of/property.c

> @@ -1271,6 +1271,22 @@ static struct device_node

> *parse_iommu_maps(struct device_node *np,

>  	return of_parse_phandle(np, prop_name, (index * 4) + 1);

>  }

> 

> +static struct device_node *parse_interrupts(struct device_node *np,

> +					    const char *prop_name, int index)

> +{

> +	struct device_node *sup;

> +

> +	if (strcmp(prop_name, "interrupts") || index)

> +		return NULL;

> +

> +	of_node_get(np);

> +	while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> +		np = of_get_next_parent(np);

> +	of_node_put(np);

> +

> +	return sup;

> +}

> +

>  static const struct supplier_bindings of_supplier_bindings[] = {

>  	{ .parse_prop = parse_clocks, },

>  	{ .parse_prop = parse_interconnects, },

> @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> of_supplier_bindings[] = {

>  	{ .parse_prop = parse_pinctrl6, },

>  	{ .parse_prop = parse_pinctrl7, },

>  	{ .parse_prop = parse_pinctrl8, },

> +	{ .parse_prop = parse_interrupts, },

>  	{ .parse_prop = parse_regulators, },

>  	{ .parse_prop = parse_gpio, },

>  	{ .parse_prop = parse_gpios, },


You don't really describe what this is for so I'm only guessing
from the context. If you want to follow the interrupt hierarchy,
"interrupt-parent" isn't enough. You also need to track
things like interrupt-map, or anything that carries a phandle
to an interrupt controller.

Thanks,

         M.
-- 
Jazz is not dead. It just smells funny...
Rob Herring (Arm) Dec. 31, 2020, 9:12 p.m. UTC | #2
On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:
> On 2020-12-18 21:07, Saravana Kannan wrote:

> > Add support for creating device links out of interrupts property.

> > 

> > Cc: Marc Zyngier <maz@kernel.org>

> > Cc: Kevin Hilman <khilman@baylibre.com>

> > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > ---

> > Rob/Greg,

> > 

> > This might need to go into driver-core to avoid conflict

> > due to fw_devlink refactor series that merged there.

> > 

> > Thanks,

> > Saravana

> > 

> > 

> >  drivers/of/property.c | 17 +++++++++++++++++

> >  1 file changed, 17 insertions(+)

> > 

> > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > --- a/drivers/of/property.c

> > +++ b/drivers/of/property.c

> > @@ -1271,6 +1271,22 @@ static struct device_node

> > *parse_iommu_maps(struct device_node *np,

> >  	return of_parse_phandle(np, prop_name, (index * 4) + 1);

> >  }

> > 

> > +static struct device_node *parse_interrupts(struct device_node *np,

> > +					    const char *prop_name, int index)

> > +{

> > +	struct device_node *sup;

> > +

> > +	if (strcmp(prop_name, "interrupts") || index)

> > +		return NULL;

> > +

> > +	of_node_get(np);

> > +	while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > +		np = of_get_next_parent(np);

> > +	of_node_put(np);

> > +

> > +	return sup;

> > +}

> > +

> >  static const struct supplier_bindings of_supplier_bindings[] = {

> >  	{ .parse_prop = parse_clocks, },

> >  	{ .parse_prop = parse_interconnects, },

> > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > of_supplier_bindings[] = {

> >  	{ .parse_prop = parse_pinctrl6, },

> >  	{ .parse_prop = parse_pinctrl7, },

> >  	{ .parse_prop = parse_pinctrl8, },

> > +	{ .parse_prop = parse_interrupts, },

> >  	{ .parse_prop = parse_regulators, },

> >  	{ .parse_prop = parse_gpio, },

> >  	{ .parse_prop = parse_gpios, },

> 

> You don't really describe what this is for so I'm only guessing

> from the context. If you want to follow the interrupt hierarchy,

> "interrupt-parent" isn't enough. You also need to track

> things like interrupt-map, or anything that carries a phandle

> to an interrupt controller.


We don't need to follow the hierarchy, we just need the immediate 
dependencies. But you are right that 'interrupt-map' also needs to be 
tracked.

I also noticed that we define 'interrupt-parent' as a dependency to 
parse, but that's wrong. The dependency is where 'interrupts' appears 
and where 'interrupt-parent' appears is irrelevant.

Rob
Marc Zyngier Jan. 2, 2021, 11:36 a.m. UTC | #3
On Thu, 31 Dec 2020 21:12:40 +0000,
Rob Herring <robh@kernel.org> wrote:
> 

> On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > Add support for creating device links out of interrupts property.

> > > 

> > > Cc: Marc Zyngier <maz@kernel.org>

> > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > ---

> > > Rob/Greg,

> > > 

> > > This might need to go into driver-core to avoid conflict

> > > due to fw_devlink refactor series that merged there.

> > > 

> > > Thanks,

> > > Saravana

> > > 

> > > 

> > >  drivers/of/property.c | 17 +++++++++++++++++

> > >  1 file changed, 17 insertions(+)

> > > 

> > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > --- a/drivers/of/property.c

> > > +++ b/drivers/of/property.c

> > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > *parse_iommu_maps(struct device_node *np,

> > >  	return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > >  }

> > > 

> > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > +					    const char *prop_name, int index)

> > > +{

> > > +	struct device_node *sup;

> > > +

> > > +	if (strcmp(prop_name, "interrupts") || index)

> > > +		return NULL;

> > > +

> > > +	of_node_get(np);

> > > +	while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > +		np = of_get_next_parent(np);

> > > +	of_node_put(np);

> > > +

> > > +	return sup;

> > > +}

> > > +

> > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > >  	{ .parse_prop = parse_clocks, },

> > >  	{ .parse_prop = parse_interconnects, },

> > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > of_supplier_bindings[] = {

> > >  	{ .parse_prop = parse_pinctrl6, },

> > >  	{ .parse_prop = parse_pinctrl7, },

> > >  	{ .parse_prop = parse_pinctrl8, },

> > > +	{ .parse_prop = parse_interrupts, },

> > >  	{ .parse_prop = parse_regulators, },

> > >  	{ .parse_prop = parse_gpio, },

> > >  	{ .parse_prop = parse_gpios, },

> > 

> > You don't really describe what this is for so I'm only guessing

> > from the context. If you want to follow the interrupt hierarchy,

> > "interrupt-parent" isn't enough. You also need to track

> > things like interrupt-map, or anything that carries a phandle

> > to an interrupt controller.

> 

> We don't need to follow the hierarchy, we just need the immediate 

> dependencies.


Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.

> But you are right that 'interrupt-map' also needs to be tracked.


And 'interrupts-extended', while we're at it.

>

> I also noticed that we define 'interrupt-parent' as a dependency to 

> parse, but that's wrong. The dependency is where 'interrupts' appears 

> and where 'interrupt-parent' appears is irrelevant.


Agreed. Though you need the object the dependency is on, I guess, if
you want to be able to have the dependency edge between the device and
the interrupt controller. But since the commit message doesn't say
much about what this is trying to achieve, I'm only guessing the
purpose of this patch.

	M.

-- 
Without deviation from the norm, progress is not possible.
Saravana Kannan Jan. 6, 2021, 6:52 p.m. UTC | #4
On Sat, Jan 2, 2021 at 3:37 AM Marc Zyngier <maz@kernel.org> wrote:
>

> On Thu, 31 Dec 2020 21:12:40 +0000,

> Rob Herring <robh@kernel.org> wrote:

> >

> > On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > > Add support for creating device links out of interrupts property.

> > > >

> > > > Cc: Marc Zyngier <maz@kernel.org>

> > > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > > ---

> > > > Rob/Greg,

> > > >

> > > > This might need to go into driver-core to avoid conflict

> > > > due to fw_devlink refactor series that merged there.

> > > >

> > > > Thanks,

> > > > Saravana

> > > >

> > > >

> > > >  drivers/of/property.c | 17 +++++++++++++++++

> > > >  1 file changed, 17 insertions(+)

> > > >

> > > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > > --- a/drivers/of/property.c

> > > > +++ b/drivers/of/property.c

> > > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > > *parse_iommu_maps(struct device_node *np,

> > > >   return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > > >  }

> > > >

> > > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > > +                                     const char *prop_name, int index)

> > > > +{

> > > > + struct device_node *sup;

> > > > +

> > > > + if (strcmp(prop_name, "interrupts") || index)

> > > > +         return NULL;

> > > > +

> > > > + of_node_get(np);

> > > > + while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > > +         np = of_get_next_parent(np);

> > > > + of_node_put(np);

> > > > +

> > > > + return sup;

> > > > +}

> > > > +

> > > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > > >   { .parse_prop = parse_clocks, },

> > > >   { .parse_prop = parse_interconnects, },

> > > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > > of_supplier_bindings[] = {

> > > >   { .parse_prop = parse_pinctrl6, },

> > > >   { .parse_prop = parse_pinctrl7, },

> > > >   { .parse_prop = parse_pinctrl8, },

> > > > + { .parse_prop = parse_interrupts, },

> > > >   { .parse_prop = parse_regulators, },

> > > >   { .parse_prop = parse_gpio, },

> > > >   { .parse_prop = parse_gpios, },

> > >

> > > You don't really describe what this is for so I'm only guessing

> > > from the context. If you want to follow the interrupt hierarchy,

> > > "interrupt-parent" isn't enough. You also need to track

> > > things like interrupt-map, or anything that carries a phandle

> > > to an interrupt controller.

> >

> > We don't need to follow the hierarchy, we just need the immediate

> > dependencies.

>

> Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.


Thanks Rob for explaining it.

Marc, I wasn't sure if Rob would be okay with including of_irq.h here.
Also, I'm trying to keep of/property.c independent of the framework
code for now. The long term goal is to see if I can move out most of
this into the frameworks. But I want to do that after I sort of some
of the larger problems (like getting fw_devlink=on to work on all
devices  first). Let me know if you have a strong preference for right
now, if not, I'd rather keep property.c independent for now.

I wasn't aware of interrupt-map until a few weeks ago and didn't know
it carried phandles. I can add support for that too. There's no reason
for all of them to go in one patch though.

>

> > But you are right that 'interrupt-map' also needs to be tracked.

>

> And 'interrupts-extended', while we're at it.


This is already handled.

> >

> > I also noticed that we define 'interrupt-parent' as a dependency to

> > parse, but that's wrong. The dependency is where 'interrupts' appears

> > and where 'interrupt-parent' appears is irrelevant.


No, the interrupt-parent parsing is correct and it's needed for
interrupt controllers to probe in the right order. But
interrupt-parent is also needs to be looked at for parsing
"interrupts".

-Saravana

> Agreed. Though you need the object the dependency is on, I guess, if

> you want to be able to have the dependency edge between the device and

> the interrupt controller. But since the commit message doesn't say

> much about what this is trying to achieve, I'm only guessing the

> purpose of this patch.

>

>         M.

>

> --

> Without deviation from the norm, progress is not possible.
Saravana Kannan Jan. 7, 2021, 1:25 a.m. UTC | #5
On Wed, Jan 6, 2021 at 10:52 AM Saravana Kannan <saravanak@google.com> wrote:
>

> On Sat, Jan 2, 2021 at 3:37 AM Marc Zyngier <maz@kernel.org> wrote:

> >

> > On Thu, 31 Dec 2020 21:12:40 +0000,

> > Rob Herring <robh@kernel.org> wrote:

> > >

> > > On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > > > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > > > Add support for creating device links out of interrupts property.

> > > > >

> > > > > Cc: Marc Zyngier <maz@kernel.org>

> > > > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > > > ---

> > > > > Rob/Greg,

> > > > >

> > > > > This might need to go into driver-core to avoid conflict

> > > > > due to fw_devlink refactor series that merged there.

> > > > >

> > > > > Thanks,

> > > > > Saravana

> > > > >

> > > > >

> > > > >  drivers/of/property.c | 17 +++++++++++++++++

> > > > >  1 file changed, 17 insertions(+)

> > > > >

> > > > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > > > --- a/drivers/of/property.c

> > > > > +++ b/drivers/of/property.c

> > > > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > > > *parse_iommu_maps(struct device_node *np,

> > > > >   return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > > > >  }

> > > > >

> > > > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > > > +                                     const char *prop_name, int index)

> > > > > +{

> > > > > + struct device_node *sup;

> > > > > +

> > > > > + if (strcmp(prop_name, "interrupts") || index)

> > > > > +         return NULL;

> > > > > +

> > > > > + of_node_get(np);

> > > > > + while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > > > +         np = of_get_next_parent(np);

> > > > > + of_node_put(np);

> > > > > +

> > > > > + return sup;

> > > > > +}

> > > > > +

> > > > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > > > >   { .parse_prop = parse_clocks, },

> > > > >   { .parse_prop = parse_interconnects, },

> > > > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > > > of_supplier_bindings[] = {

> > > > >   { .parse_prop = parse_pinctrl6, },

> > > > >   { .parse_prop = parse_pinctrl7, },

> > > > >   { .parse_prop = parse_pinctrl8, },

> > > > > + { .parse_prop = parse_interrupts, },

> > > > >   { .parse_prop = parse_regulators, },

> > > > >   { .parse_prop = parse_gpio, },

> > > > >   { .parse_prop = parse_gpios, },

> > > >

> > > > You don't really describe what this is for so I'm only guessing

> > > > from the context. If you want to follow the interrupt hierarchy,

> > > > "interrupt-parent" isn't enough. You also need to track

> > > > things like interrupt-map, or anything that carries a phandle

> > > > to an interrupt controller.

> > >

> > > We don't need to follow the hierarchy, we just need the immediate

> > > dependencies.

> >

> > Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.

>

> Thanks Rob for explaining it.

>

> Marc, I wasn't sure if Rob would be okay with including of_irq.h here.

> Also, I'm trying to keep of/property.c independent of the framework

> code for now. The long term goal is to see if I can move out most of

> this into the frameworks. But I want to do that after I sort of some

> of the larger problems (like getting fw_devlink=on to work on all

> devices  first). Let me know if you have a strong preference for right

> now, if not, I'd rather keep property.c independent for now.

>

> I wasn't aware of interrupt-map until a few weeks ago and didn't know

> it carried phandles. I can add support for that too. There's no reason

> for all of them to go in one patch though.


Hmm... I looked at
Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
and it has no documentation for interrupt-map. There's a bunch of
references to it in device specific DT binding documentation but I
don't want to rely on those for correctness.

Marc, can you explain the interrupt-map format here or add
documentation for it please?

-Saravana
Rob Herring (Arm) Jan. 7, 2021, 4:47 p.m. UTC | #6
On Wed, Jan 6, 2021 at 6:26 PM Saravana Kannan <saravanak@google.com> wrote:
>

> On Wed, Jan 6, 2021 at 10:52 AM Saravana Kannan <saravanak@google.com> wrote:

> >

> > On Sat, Jan 2, 2021 at 3:37 AM Marc Zyngier <maz@kernel.org> wrote:

> > >

> > > On Thu, 31 Dec 2020 21:12:40 +0000,

> > > Rob Herring <robh@kernel.org> wrote:

> > > >

> > > > On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > > > > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > > > > Add support for creating device links out of interrupts property.

> > > > > >

> > > > > > Cc: Marc Zyngier <maz@kernel.org>

> > > > > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > > > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > > > > ---

> > > > > > Rob/Greg,

> > > > > >

> > > > > > This might need to go into driver-core to avoid conflict

> > > > > > due to fw_devlink refactor series that merged there.

> > > > > >

> > > > > > Thanks,

> > > > > > Saravana

> > > > > >

> > > > > >

> > > > > >  drivers/of/property.c | 17 +++++++++++++++++

> > > > > >  1 file changed, 17 insertions(+)

> > > > > >

> > > > > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > > > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > > > > --- a/drivers/of/property.c

> > > > > > +++ b/drivers/of/property.c

> > > > > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > > > > *parse_iommu_maps(struct device_node *np,

> > > > > >   return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > > > > >  }

> > > > > >

> > > > > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > > > > +                                     const char *prop_name, int index)

> > > > > > +{

> > > > > > + struct device_node *sup;

> > > > > > +

> > > > > > + if (strcmp(prop_name, "interrupts") || index)

> > > > > > +         return NULL;

> > > > > > +

> > > > > > + of_node_get(np);

> > > > > > + while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > > > > +         np = of_get_next_parent(np);

> > > > > > + of_node_put(np);

> > > > > > +

> > > > > > + return sup;

> > > > > > +}

> > > > > > +

> > > > > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > > > > >   { .parse_prop = parse_clocks, },

> > > > > >   { .parse_prop = parse_interconnects, },

> > > > > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > > > > of_supplier_bindings[] = {

> > > > > >   { .parse_prop = parse_pinctrl6, },

> > > > > >   { .parse_prop = parse_pinctrl7, },

> > > > > >   { .parse_prop = parse_pinctrl8, },

> > > > > > + { .parse_prop = parse_interrupts, },

> > > > > >   { .parse_prop = parse_regulators, },

> > > > > >   { .parse_prop = parse_gpio, },

> > > > > >   { .parse_prop = parse_gpios, },

> > > > >

> > > > > You don't really describe what this is for so I'm only guessing

> > > > > from the context. If you want to follow the interrupt hierarchy,

> > > > > "interrupt-parent" isn't enough. You also need to track

> > > > > things like interrupt-map, or anything that carries a phandle

> > > > > to an interrupt controller.

> > > >

> > > > We don't need to follow the hierarchy, we just need the immediate

> > > > dependencies.

> > >

> > > Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.

> >

> > Thanks Rob for explaining it.

> >

> > Marc, I wasn't sure if Rob would be okay with including of_irq.h here.

> > Also, I'm trying to keep of/property.c independent of the framework

> > code for now. The long term goal is to see if I can move out most of

> > this into the frameworks. But I want to do that after I sort of some

> > of the larger problems (like getting fw_devlink=on to work on all

> > devices  first). Let me know if you have a strong preference for right

> > now, if not, I'd rather keep property.c independent for now.

> >

> > I wasn't aware of interrupt-map until a few weeks ago and didn't know

> > it carried phandles. I can add support for that too. There's no reason

> > for all of them to go in one patch though.

>

> Hmm... I looked at

> Documentation/devicetree/bindings/interrupt-controller/interrupts.txt

> and it has no documentation for interrupt-map. There's a bunch of

> references to it in device specific DT binding documentation but I

> don't want to rely on those for correctness.


See the DT spec and there's also details on elinux.org. It's only
existed since the 1990s.

Rob
Saravana Kannan Jan. 7, 2021, 5:08 p.m. UTC | #7
On Thu, Jan 7, 2021 at 8:48 AM Rob Herring <robh@kernel.org> wrote:
>

> On Wed, Jan 6, 2021 at 6:26 PM Saravana Kannan <saravanak@google.com> wrote:

> >

> > On Wed, Jan 6, 2021 at 10:52 AM Saravana Kannan <saravanak@google.com> wrote:

> > >

> > > On Sat, Jan 2, 2021 at 3:37 AM Marc Zyngier <maz@kernel.org> wrote:

> > > >

> > > > On Thu, 31 Dec 2020 21:12:40 +0000,

> > > > Rob Herring <robh@kernel.org> wrote:

> > > > >

> > > > > On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > > > > > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > > > > > Add support for creating device links out of interrupts property.

> > > > > > >

> > > > > > > Cc: Marc Zyngier <maz@kernel.org>

> > > > > > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > > > > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > > > > > ---

> > > > > > > Rob/Greg,

> > > > > > >

> > > > > > > This might need to go into driver-core to avoid conflict

> > > > > > > due to fw_devlink refactor series that merged there.

> > > > > > >

> > > > > > > Thanks,

> > > > > > > Saravana

> > > > > > >

> > > > > > >

> > > > > > >  drivers/of/property.c | 17 +++++++++++++++++

> > > > > > >  1 file changed, 17 insertions(+)

> > > > > > >

> > > > > > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > > > > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > > > > > --- a/drivers/of/property.c

> > > > > > > +++ b/drivers/of/property.c

> > > > > > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > > > > > *parse_iommu_maps(struct device_node *np,

> > > > > > >   return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > > > > > >  }

> > > > > > >

> > > > > > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > > > > > +                                     const char *prop_name, int index)

> > > > > > > +{

> > > > > > > + struct device_node *sup;

> > > > > > > +

> > > > > > > + if (strcmp(prop_name, "interrupts") || index)

> > > > > > > +         return NULL;

> > > > > > > +

> > > > > > > + of_node_get(np);

> > > > > > > + while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > > > > > +         np = of_get_next_parent(np);

> > > > > > > + of_node_put(np);

> > > > > > > +

> > > > > > > + return sup;

> > > > > > > +}

> > > > > > > +

> > > > > > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > > > > > >   { .parse_prop = parse_clocks, },

> > > > > > >   { .parse_prop = parse_interconnects, },

> > > > > > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > > > > > of_supplier_bindings[] = {

> > > > > > >   { .parse_prop = parse_pinctrl6, },

> > > > > > >   { .parse_prop = parse_pinctrl7, },

> > > > > > >   { .parse_prop = parse_pinctrl8, },

> > > > > > > + { .parse_prop = parse_interrupts, },

> > > > > > >   { .parse_prop = parse_regulators, },

> > > > > > >   { .parse_prop = parse_gpio, },

> > > > > > >   { .parse_prop = parse_gpios, },

> > > > > >

> > > > > > You don't really describe what this is for so I'm only guessing

> > > > > > from the context. If you want to follow the interrupt hierarchy,

> > > > > > "interrupt-parent" isn't enough. You also need to track

> > > > > > things like interrupt-map, or anything that carries a phandle

> > > > > > to an interrupt controller.

> > > > >

> > > > > We don't need to follow the hierarchy, we just need the immediate

> > > > > dependencies.

> > > >

> > > > Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.

> > >

> > > Thanks Rob for explaining it.

> > >

> > > Marc, I wasn't sure if Rob would be okay with including of_irq.h here.

> > > Also, I'm trying to keep of/property.c independent of the framework

> > > code for now. The long term goal is to see if I can move out most of

> > > this into the frameworks. But I want to do that after I sort of some

> > > of the larger problems (like getting fw_devlink=on to work on all

> > > devices  first). Let me know if you have a strong preference for right

> > > now, if not, I'd rather keep property.c independent for now.

> > >

> > > I wasn't aware of interrupt-map until a few weeks ago and didn't know

> > > it carried phandles. I can add support for that too. There's no reason

> > > for all of them to go in one patch though.

> >

> > Hmm... I looked at

> > Documentation/devicetree/bindings/interrupt-controller/interrupts.txt

> > and it has no documentation for interrupt-map. There's a bunch of

> > references to it in device specific DT binding documentation but I

> > don't want to rely on those for correctness.

>

> See the DT spec and there's also details on elinux.org. It's only

> existed since the 1990s.


Thanks :) Will try to find it there.

-Saravana
Marc Zyngier Jan. 7, 2021, 5:17 p.m. UTC | #8
On 2021-01-07 17:08, Saravana Kannan wrote:
> On Thu, Jan 7, 2021 at 8:48 AM Rob Herring <robh@kernel.org> wrote:

>> 

>> On Wed, Jan 6, 2021 at 6:26 PM Saravana Kannan <saravanak@google.com> 

>> wrote:

>> >

>> > On Wed, Jan 6, 2021 at 10:52 AM Saravana Kannan <saravanak@google.com> wrote:


[...]

>> > > I wasn't aware of interrupt-map until a few weeks ago and didn't know

>> > > it carried phandles. I can add support for that too. There's no reason

>> > > for all of them to go in one patch though.

>> >

>> > Hmm... I looked at

>> > Documentation/devicetree/bindings/interrupt-controller/interrupts.txt

>> > and it has no documentation for interrupt-map. There's a bunch of

>> > references to it in device specific DT binding documentation but I

>> > don't want to rely on those for correctness.

>> 

>> See the DT spec and there's also details on elinux.org. It's only

>> existed since the 1990s.

> 

> Thanks :) Will try to find it there.


My document of reference is [1]. Although interrupt-map appears
there in the context of PCI, it is in no way specific to a specific
bus.

HTH,

         M.

[1] https://www.openbios.org/data/docs/rec.intmap.d09.pdf
-- 
Jazz is not dead. It just smells funny...
Rob Herring (Arm) Jan. 7, 2021, 6:39 p.m. UTC | #9
On Wed, Jan 6, 2021 at 11:53 AM Saravana Kannan <saravanak@google.com> wrote:
>

> On Sat, Jan 2, 2021 at 3:37 AM Marc Zyngier <maz@kernel.org> wrote:

> >

> > On Thu, 31 Dec 2020 21:12:40 +0000,

> > Rob Herring <robh@kernel.org> wrote:

> > >

> > > On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > > > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > > > Add support for creating device links out of interrupts property.

> > > > >

> > > > > Cc: Marc Zyngier <maz@kernel.org>

> > > > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > > > ---

> > > > > Rob/Greg,

> > > > >

> > > > > This might need to go into driver-core to avoid conflict

> > > > > due to fw_devlink refactor series that merged there.

> > > > >

> > > > > Thanks,

> > > > > Saravana

> > > > >

> > > > >

> > > > >  drivers/of/property.c | 17 +++++++++++++++++

> > > > >  1 file changed, 17 insertions(+)

> > > > >

> > > > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > > > --- a/drivers/of/property.c

> > > > > +++ b/drivers/of/property.c

> > > > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > > > *parse_iommu_maps(struct device_node *np,

> > > > >   return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > > > >  }

> > > > >

> > > > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > > > +                                     const char *prop_name, int index)

> > > > > +{

> > > > > + struct device_node *sup;

> > > > > +

> > > > > + if (strcmp(prop_name, "interrupts") || index)

> > > > > +         return NULL;

> > > > > +

> > > > > + of_node_get(np);

> > > > > + while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > > > +         np = of_get_next_parent(np);

> > > > > + of_node_put(np);

> > > > > +

> > > > > + return sup;

> > > > > +}

> > > > > +

> > > > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > > > >   { .parse_prop = parse_clocks, },

> > > > >   { .parse_prop = parse_interconnects, },

> > > > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > > > of_supplier_bindings[] = {

> > > > >   { .parse_prop = parse_pinctrl6, },

> > > > >   { .parse_prop = parse_pinctrl7, },

> > > > >   { .parse_prop = parse_pinctrl8, },

> > > > > + { .parse_prop = parse_interrupts, },

> > > > >   { .parse_prop = parse_regulators, },

> > > > >   { .parse_prop = parse_gpio, },

> > > > >   { .parse_prop = parse_gpios, },

> > > >

> > > > You don't really describe what this is for so I'm only guessing

> > > > from the context. If you want to follow the interrupt hierarchy,

> > > > "interrupt-parent" isn't enough. You also need to track

> > > > things like interrupt-map, or anything that carries a phandle

> > > > to an interrupt controller.

> > >

> > > We don't need to follow the hierarchy, we just need the immediate

> > > dependencies.

> >

> > Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.

>

> Thanks Rob for explaining it.

>

> Marc, I wasn't sure if Rob would be okay with including of_irq.h here.

> Also, I'm trying to keep of/property.c independent of the framework

> code for now. The long term goal is to see if I can move out most of

> this into the frameworks. But I want to do that after I sort of some

> of the larger problems (like getting fw_devlink=on to work on all

> devices  first). Let me know if you have a strong preference for right

> now, if not, I'd rather keep property.c independent for now.

>

> I wasn't aware of interrupt-map until a few weeks ago and didn't know

> it carried phandles. I can add support for that too. There's no reason

> for all of them to go in one patch though.

>

> >

> > > But you are right that 'interrupt-map' also needs to be tracked.

> >

> > And 'interrupts-extended', while we're at it.

>

> This is already handled.

>

> > >

> > > I also noticed that we define 'interrupt-parent' as a dependency to

> > > parse, but that's wrong. The dependency is where 'interrupts' appears

> > > and where 'interrupt-parent' appears is irrelevant.

>

> No, the interrupt-parent parsing is correct and it's needed for

> interrupt controllers to probe in the right order. But

> interrupt-parent is also needs to be looked at for parsing

> "interrupts".


If you parse 'interrupts' for interrupt controllers (which in turn
will use 'interrupt-parent'), then you aren't going to need to track
'interrupt-parent' by itself.

To look at it another way, 'interrupt-parent' can appear in any
ancestor node. Which node the dts author arbitrarily decided to put it
in does not matter at all. It could be at the DT root or duplicated in
every single node with 'interrupts'. Those are logically the same. The
node(s) with the dependency are the ones with 'interrupts'.

Rob
Saravana Kannan Jan. 7, 2021, 7:09 p.m. UTC | #10
On Thu, Jan 7, 2021 at 10:39 AM Rob Herring <robh@kernel.org> wrote:
>

> On Wed, Jan 6, 2021 at 11:53 AM Saravana Kannan <saravanak@google.com> wrote:

> >

> > On Sat, Jan 2, 2021 at 3:37 AM Marc Zyngier <maz@kernel.org> wrote:

> > >

> > > On Thu, 31 Dec 2020 21:12:40 +0000,

> > > Rob Herring <robh@kernel.org> wrote:

> > > >

> > > > On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > > > > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > > > > Add support for creating device links out of interrupts property.

> > > > > >

> > > > > > Cc: Marc Zyngier <maz@kernel.org>

> > > > > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > > > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > > > > ---

> > > > > > Rob/Greg,

> > > > > >

> > > > > > This might need to go into driver-core to avoid conflict

> > > > > > due to fw_devlink refactor series that merged there.

> > > > > >

> > > > > > Thanks,

> > > > > > Saravana

> > > > > >

> > > > > >

> > > > > >  drivers/of/property.c | 17 +++++++++++++++++

> > > > > >  1 file changed, 17 insertions(+)

> > > > > >

> > > > > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > > > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > > > > --- a/drivers/of/property.c

> > > > > > +++ b/drivers/of/property.c

> > > > > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > > > > *parse_iommu_maps(struct device_node *np,

> > > > > >   return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > > > > >  }

> > > > > >

> > > > > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > > > > +                                     const char *prop_name, int index)

> > > > > > +{

> > > > > > + struct device_node *sup;

> > > > > > +

> > > > > > + if (strcmp(prop_name, "interrupts") || index)

> > > > > > +         return NULL;

> > > > > > +

> > > > > > + of_node_get(np);

> > > > > > + while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > > > > +         np = of_get_next_parent(np);

> > > > > > + of_node_put(np);

> > > > > > +

> > > > > > + return sup;

> > > > > > +}

> > > > > > +

> > > > > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > > > > >   { .parse_prop = parse_clocks, },

> > > > > >   { .parse_prop = parse_interconnects, },

> > > > > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > > > > of_supplier_bindings[] = {

> > > > > >   { .parse_prop = parse_pinctrl6, },

> > > > > >   { .parse_prop = parse_pinctrl7, },

> > > > > >   { .parse_prop = parse_pinctrl8, },

> > > > > > + { .parse_prop = parse_interrupts, },

> > > > > >   { .parse_prop = parse_regulators, },

> > > > > >   { .parse_prop = parse_gpio, },

> > > > > >   { .parse_prop = parse_gpios, },

> > > > >

> > > > > You don't really describe what this is for so I'm only guessing

> > > > > from the context. If you want to follow the interrupt hierarchy,

> > > > > "interrupt-parent" isn't enough. You also need to track

> > > > > things like interrupt-map, or anything that carries a phandle

> > > > > to an interrupt controller.

> > > >

> > > > We don't need to follow the hierarchy, we just need the immediate

> > > > dependencies.

> > >

> > > Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.

> >

> > Thanks Rob for explaining it.

> >

> > Marc, I wasn't sure if Rob would be okay with including of_irq.h here.

> > Also, I'm trying to keep of/property.c independent of the framework

> > code for now. The long term goal is to see if I can move out most of

> > this into the frameworks. But I want to do that after I sort of some

> > of the larger problems (like getting fw_devlink=on to work on all

> > devices  first). Let me know if you have a strong preference for right

> > now, if not, I'd rather keep property.c independent for now.

> >

> > I wasn't aware of interrupt-map until a few weeks ago and didn't know

> > it carried phandles. I can add support for that too. There's no reason

> > for all of them to go in one patch though.

> >

> > >

> > > > But you are right that 'interrupt-map' also needs to be tracked.

> > >

> > > And 'interrupts-extended', while we're at it.

> >

> > This is already handled.

> >

> > > >

> > > > I also noticed that we define 'interrupt-parent' as a dependency to

> > > > parse, but that's wrong. The dependency is where 'interrupts' appears

> > > > and where 'interrupt-parent' appears is irrelevant.

> >

> > No, the interrupt-parent parsing is correct and it's needed for

> > interrupt controllers to probe in the right order. But

> > interrupt-parent is also needs to be looked at for parsing

> > "interrupts".

>

> If you parse 'interrupts' for interrupt controllers (which in turn

> will use 'interrupt-parent'), then you aren't going to need to track

> 'interrupt-parent' by itself.


Do all interrupt controllers (that are not the root interrupt
controller) need to have "interrupts" property? If yes, then yeah,
that makes sense. But I vaguely remember that this wasn't the case for
some DT I saw.

Ah, here's one I found.
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/arm/boot/dts/mt2701.dtsi#n209

-Saravana
Rob Herring (Arm) Jan. 7, 2021, 7:33 p.m. UTC | #11
On Thu, Jan 7, 2021 at 12:09 PM Saravana Kannan <saravanak@google.com> wrote:
>

> On Thu, Jan 7, 2021 at 10:39 AM Rob Herring <robh@kernel.org> wrote:

> >

> > On Wed, Jan 6, 2021 at 11:53 AM Saravana Kannan <saravanak@google.com> wrote:

> > >

> > > On Sat, Jan 2, 2021 at 3:37 AM Marc Zyngier <maz@kernel.org> wrote:

> > > >

> > > > On Thu, 31 Dec 2020 21:12:40 +0000,

> > > > Rob Herring <robh@kernel.org> wrote:

> > > > >

> > > > > On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > > > > > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > > > > > Add support for creating device links out of interrupts property.

> > > > > > >

> > > > > > > Cc: Marc Zyngier <maz@kernel.org>

> > > > > > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > > > > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > > > > > ---

> > > > > > > Rob/Greg,

> > > > > > >

> > > > > > > This might need to go into driver-core to avoid conflict

> > > > > > > due to fw_devlink refactor series that merged there.

> > > > > > >

> > > > > > > Thanks,

> > > > > > > Saravana

> > > > > > >

> > > > > > >

> > > > > > >  drivers/of/property.c | 17 +++++++++++++++++

> > > > > > >  1 file changed, 17 insertions(+)

> > > > > > >

> > > > > > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > > > > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > > > > > --- a/drivers/of/property.c

> > > > > > > +++ b/drivers/of/property.c

> > > > > > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > > > > > *parse_iommu_maps(struct device_node *np,

> > > > > > >   return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > > > > > >  }

> > > > > > >

> > > > > > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > > > > > +                                     const char *prop_name, int index)

> > > > > > > +{

> > > > > > > + struct device_node *sup;

> > > > > > > +

> > > > > > > + if (strcmp(prop_name, "interrupts") || index)

> > > > > > > +         return NULL;

> > > > > > > +

> > > > > > > + of_node_get(np);

> > > > > > > + while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > > > > > +         np = of_get_next_parent(np);

> > > > > > > + of_node_put(np);

> > > > > > > +

> > > > > > > + return sup;

> > > > > > > +}

> > > > > > > +

> > > > > > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > > > > > >   { .parse_prop = parse_clocks, },

> > > > > > >   { .parse_prop = parse_interconnects, },

> > > > > > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > > > > > of_supplier_bindings[] = {

> > > > > > >   { .parse_prop = parse_pinctrl6, },

> > > > > > >   { .parse_prop = parse_pinctrl7, },

> > > > > > >   { .parse_prop = parse_pinctrl8, },

> > > > > > > + { .parse_prop = parse_interrupts, },

> > > > > > >   { .parse_prop = parse_regulators, },

> > > > > > >   { .parse_prop = parse_gpio, },

> > > > > > >   { .parse_prop = parse_gpios, },

> > > > > >

> > > > > > You don't really describe what this is for so I'm only guessing

> > > > > > from the context. If you want to follow the interrupt hierarchy,

> > > > > > "interrupt-parent" isn't enough. You also need to track

> > > > > > things like interrupt-map, or anything that carries a phandle

> > > > > > to an interrupt controller.

> > > > >

> > > > > We don't need to follow the hierarchy, we just need the immediate

> > > > > dependencies.

> > > >

> > > > Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.

> > >

> > > Thanks Rob for explaining it.

> > >

> > > Marc, I wasn't sure if Rob would be okay with including of_irq.h here.

> > > Also, I'm trying to keep of/property.c independent of the framework

> > > code for now. The long term goal is to see if I can move out most of

> > > this into the frameworks. But I want to do that after I sort of some

> > > of the larger problems (like getting fw_devlink=on to work on all

> > > devices  first). Let me know if you have a strong preference for right

> > > now, if not, I'd rather keep property.c independent for now.

> > >

> > > I wasn't aware of interrupt-map until a few weeks ago and didn't know

> > > it carried phandles. I can add support for that too. There's no reason

> > > for all of them to go in one patch though.

> > >

> > > >

> > > > > But you are right that 'interrupt-map' also needs to be tracked.

> > > >

> > > > And 'interrupts-extended', while we're at it.

> > >

> > > This is already handled.

> > >

> > > > >

> > > > > I also noticed that we define 'interrupt-parent' as a dependency to

> > > > > parse, but that's wrong. The dependency is where 'interrupts' appears

> > > > > and where 'interrupt-parent' appears is irrelevant.

> > >

> > > No, the interrupt-parent parsing is correct and it's needed for

> > > interrupt controllers to probe in the right order. But

> > > interrupt-parent is also needs to be looked at for parsing

> > > "interrupts".

> >

> > If you parse 'interrupts' for interrupt controllers (which in turn

> > will use 'interrupt-parent'), then you aren't going to need to track

> > 'interrupt-parent' by itself.

>

> Do all interrupt controllers (that are not the root interrupt

> controller) need to have "interrupts" property? If yes, then yeah,

> that makes sense. But I vaguely remember that this wasn't the case for

> some DT I saw.


There are some cases of stacked controllers where it's implicit.

>

> Ah, here's one I found.

> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/arm/boot/dts/mt2701.dtsi#n209


Right, so this is one of several cases of custom interrupt mapping
properties (mediatek,ext-irq-range). Really, 'interrupts' or
'interrupt-map' should have been used here, but 'interrupt-map'
doesn't really scale well if you have large ranges of interrupts.

To handle the dependency with just 'interrupt-parent', you need to
find nodes that are themselves an 'interrupt-parent' and then find
their 'interrupt-parent'.

Rob
Saravana Kannan Jan. 7, 2021, 11:13 p.m. UTC | #12
On Thu, Jan 7, 2021 at 11:33 AM Rob Herring <robh@kernel.org> wrote:
>

> On Thu, Jan 7, 2021 at 12:09 PM Saravana Kannan <saravanak@google.com> wrote:

> >

> > On Thu, Jan 7, 2021 at 10:39 AM Rob Herring <robh@kernel.org> wrote:

> > >

> > > On Wed, Jan 6, 2021 at 11:53 AM Saravana Kannan <saravanak@google.com> wrote:

> > > >

> > > > On Sat, Jan 2, 2021 at 3:37 AM Marc Zyngier <maz@kernel.org> wrote:

> > > > >

> > > > > On Thu, 31 Dec 2020 21:12:40 +0000,

> > > > > Rob Herring <robh@kernel.org> wrote:

> > > > > >

> > > > > > On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > > > > > > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > > > > > > Add support for creating device links out of interrupts property.

> > > > > > > >

> > > > > > > > Cc: Marc Zyngier <maz@kernel.org>

> > > > > > > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > > > > > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > > > > > > ---

> > > > > > > > Rob/Greg,

> > > > > > > >

> > > > > > > > This might need to go into driver-core to avoid conflict

> > > > > > > > due to fw_devlink refactor series that merged there.

> > > > > > > >

> > > > > > > > Thanks,

> > > > > > > > Saravana

> > > > > > > >

> > > > > > > >

> > > > > > > >  drivers/of/property.c | 17 +++++++++++++++++

> > > > > > > >  1 file changed, 17 insertions(+)

> > > > > > > >

> > > > > > > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > > > > > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > > > > > > --- a/drivers/of/property.c

> > > > > > > > +++ b/drivers/of/property.c

> > > > > > > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > > > > > > *parse_iommu_maps(struct device_node *np,

> > > > > > > >   return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > > > > > > >  }

> > > > > > > >

> > > > > > > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > > > > > > +                                     const char *prop_name, int index)

> > > > > > > > +{

> > > > > > > > + struct device_node *sup;

> > > > > > > > +

> > > > > > > > + if (strcmp(prop_name, "interrupts") || index)

> > > > > > > > +         return NULL;

> > > > > > > > +

> > > > > > > > + of_node_get(np);

> > > > > > > > + while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > > > > > > +         np = of_get_next_parent(np);

> > > > > > > > + of_node_put(np);

> > > > > > > > +

> > > > > > > > + return sup;

> > > > > > > > +}

> > > > > > > > +

> > > > > > > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > > > > > > >   { .parse_prop = parse_clocks, },

> > > > > > > >   { .parse_prop = parse_interconnects, },

> > > > > > > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > > > > > > of_supplier_bindings[] = {

> > > > > > > >   { .parse_prop = parse_pinctrl6, },

> > > > > > > >   { .parse_prop = parse_pinctrl7, },

> > > > > > > >   { .parse_prop = parse_pinctrl8, },

> > > > > > > > + { .parse_prop = parse_interrupts, },

> > > > > > > >   { .parse_prop = parse_regulators, },

> > > > > > > >   { .parse_prop = parse_gpio, },

> > > > > > > >   { .parse_prop = parse_gpios, },

> > > > > > >

> > > > > > > You don't really describe what this is for so I'm only guessing

> > > > > > > from the context. If you want to follow the interrupt hierarchy,

> > > > > > > "interrupt-parent" isn't enough. You also need to track

> > > > > > > things like interrupt-map, or anything that carries a phandle

> > > > > > > to an interrupt controller.

> > > > > >

> > > > > > We don't need to follow the hierarchy, we just need the immediate

> > > > > > dependencies.

> > > > >

> > > > > Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.

> > > >

> > > > Thanks Rob for explaining it.

> > > >

> > > > Marc, I wasn't sure if Rob would be okay with including of_irq.h here.

> > > > Also, I'm trying to keep of/property.c independent of the framework

> > > > code for now. The long term goal is to see if I can move out most of

> > > > this into the frameworks. But I want to do that after I sort of some

> > > > of the larger problems (like getting fw_devlink=on to work on all

> > > > devices  first). Let me know if you have a strong preference for right

> > > > now, if not, I'd rather keep property.c independent for now.

> > > >

> > > > I wasn't aware of interrupt-map until a few weeks ago and didn't know

> > > > it carried phandles. I can add support for that too. There's no reason

> > > > for all of them to go in one patch though.

> > > >

> > > > >

> > > > > > But you are right that 'interrupt-map' also needs to be tracked.

> > > > >

> > > > > And 'interrupts-extended', while we're at it.

> > > >

> > > > This is already handled.

> > > >

> > > > > >

> > > > > > I also noticed that we define 'interrupt-parent' as a dependency to

> > > > > > parse, but that's wrong. The dependency is where 'interrupts' appears

> > > > > > and where 'interrupt-parent' appears is irrelevant.

> > > >

> > > > No, the interrupt-parent parsing is correct and it's needed for

> > > > interrupt controllers to probe in the right order. But

> > > > interrupt-parent is also needs to be looked at for parsing

> > > > "interrupts".

> > >

> > > If you parse 'interrupts' for interrupt controllers (which in turn

> > > will use 'interrupt-parent'), then you aren't going to need to track

> > > 'interrupt-parent' by itself.

> >

> > Do all interrupt controllers (that are not the root interrupt

> > controller) need to have "interrupts" property? If yes, then yeah,

> > that makes sense. But I vaguely remember that this wasn't the case for

> > some DT I saw.

>

> There are some cases of stacked controllers where it's implicit.


In that case, I think it's good to track interrupt-parent explicitly.
Doesn't really hurt anything. We already protect for stuff like making
sure a parent doesn't depend on its child, etc.

> >

> > Ah, here's one I found.

> > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/arm/boot/dts/mt2701.dtsi#n209

>

> Right, so this is one of several cases of custom interrupt mapping

> properties (mediatek,ext-irq-range). Really, 'interrupts' or

> 'interrupt-map' should have been used here, but 'interrupt-map'

> doesn't really scale well if you have large ranges of interrupts.

>

> To handle the dependency with just 'interrupt-parent', you need to

> find nodes that are themselves an 'interrupt-parent' and then find

> their 'interrupt-parent'.


Not sure I understand this.

On a side note, if I'm adding device links between a device and the
"interrupt-parent" it's pointing to, at worst, I'm having it depend on
an interrupt controller its child devices would depend on. This
combined with the fact that "weird" links like "parent depending on
child", "non-device node having interrupt-parent", etc are already
ignored, seems safe to leave in "interrupt-parent" to catch these
cases where interrupt controllers don't specify "interrupts" or
"interrupt-map"? I don't mind removing it, but maybe we can wait till
we get fw_devlink=on and then remove it to see if anything breaks? If
nothing breaks, we can remove explicit interrupt-parent parsing?

Going back to interrupt-map, I understand the syntax now. I'm trying
to see if I can break up of_irq_parse_raw() into smaller pieces and
reuse (call into) some of that code. While doing that I see that when
"address-cells" isn't present, the "addrsize" is initialized to 2 [1]
but when "address-cells" isn't present, the "newaddrsize" is
initialized to 0 [1]. Why is the default value of #address-cells two
different numbers?

Thanks,
Saravana

[1] - https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/of/irq.c#n141
[2] - https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/of/irq.c#n226
Rob Herring (Arm) Jan. 8, 2021, 3:35 a.m. UTC | #13
On Thu, Jan 7, 2021 at 4:13 PM Saravana Kannan <saravanak@google.com> wrote:
>

> On Thu, Jan 7, 2021 at 11:33 AM Rob Herring <robh@kernel.org> wrote:

> >

> > On Thu, Jan 7, 2021 at 12:09 PM Saravana Kannan <saravanak@google.com> wrote:

> > >

> > > On Thu, Jan 7, 2021 at 10:39 AM Rob Herring <robh@kernel.org> wrote:

> > > >

> > > > On Wed, Jan 6, 2021 at 11:53 AM Saravana Kannan <saravanak@google.com> wrote:

> > > > >

> > > > > On Sat, Jan 2, 2021 at 3:37 AM Marc Zyngier <maz@kernel.org> wrote:

> > > > > >

> > > > > > On Thu, 31 Dec 2020 21:12:40 +0000,

> > > > > > Rob Herring <robh@kernel.org> wrote:

> > > > > > >

> > > > > > > On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > > > > > > > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > > > > > > > Add support for creating device links out of interrupts property.

> > > > > > > > >

> > > > > > > > > Cc: Marc Zyngier <maz@kernel.org>

> > > > > > > > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > > > > > > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > > > > > > > ---

> > > > > > > > > Rob/Greg,

> > > > > > > > >

> > > > > > > > > This might need to go into driver-core to avoid conflict

> > > > > > > > > due to fw_devlink refactor series that merged there.

> > > > > > > > >

> > > > > > > > > Thanks,

> > > > > > > > > Saravana

> > > > > > > > >

> > > > > > > > >

> > > > > > > > >  drivers/of/property.c | 17 +++++++++++++++++

> > > > > > > > >  1 file changed, 17 insertions(+)

> > > > > > > > >

> > > > > > > > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > > > > > > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > > > > > > > --- a/drivers/of/property.c

> > > > > > > > > +++ b/drivers/of/property.c

> > > > > > > > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > > > > > > > *parse_iommu_maps(struct device_node *np,

> > > > > > > > >   return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > > > > > > > >  }

> > > > > > > > >

> > > > > > > > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > > > > > > > +                                     const char *prop_name, int index)

> > > > > > > > > +{

> > > > > > > > > + struct device_node *sup;

> > > > > > > > > +

> > > > > > > > > + if (strcmp(prop_name, "interrupts") || index)

> > > > > > > > > +         return NULL;

> > > > > > > > > +

> > > > > > > > > + of_node_get(np);

> > > > > > > > > + while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > > > > > > > +         np = of_get_next_parent(np);

> > > > > > > > > + of_node_put(np);

> > > > > > > > > +

> > > > > > > > > + return sup;

> > > > > > > > > +}

> > > > > > > > > +

> > > > > > > > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > > > > > > > >   { .parse_prop = parse_clocks, },

> > > > > > > > >   { .parse_prop = parse_interconnects, },

> > > > > > > > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > > > > > > > of_supplier_bindings[] = {

> > > > > > > > >   { .parse_prop = parse_pinctrl6, },

> > > > > > > > >   { .parse_prop = parse_pinctrl7, },

> > > > > > > > >   { .parse_prop = parse_pinctrl8, },

> > > > > > > > > + { .parse_prop = parse_interrupts, },

> > > > > > > > >   { .parse_prop = parse_regulators, },

> > > > > > > > >   { .parse_prop = parse_gpio, },

> > > > > > > > >   { .parse_prop = parse_gpios, },

> > > > > > > >

> > > > > > > > You don't really describe what this is for so I'm only guessing

> > > > > > > > from the context. If you want to follow the interrupt hierarchy,

> > > > > > > > "interrupt-parent" isn't enough. You also need to track

> > > > > > > > things like interrupt-map, or anything that carries a phandle

> > > > > > > > to an interrupt controller.

> > > > > > >

> > > > > > > We don't need to follow the hierarchy, we just need the immediate

> > > > > > > dependencies.

> > > > > >

> > > > > > Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.

> > > > >

> > > > > Thanks Rob for explaining it.

> > > > >

> > > > > Marc, I wasn't sure if Rob would be okay with including of_irq.h here.

> > > > > Also, I'm trying to keep of/property.c independent of the framework

> > > > > code for now. The long term goal is to see if I can move out most of

> > > > > this into the frameworks. But I want to do that after I sort of some

> > > > > of the larger problems (like getting fw_devlink=on to work on all

> > > > > devices  first). Let me know if you have a strong preference for right

> > > > > now, if not, I'd rather keep property.c independent for now.

> > > > >

> > > > > I wasn't aware of interrupt-map until a few weeks ago and didn't know

> > > > > it carried phandles. I can add support for that too. There's no reason

> > > > > for all of them to go in one patch though.

> > > > >

> > > > > >

> > > > > > > But you are right that 'interrupt-map' also needs to be tracked.

> > > > > >

> > > > > > And 'interrupts-extended', while we're at it.

> > > > >

> > > > > This is already handled.

> > > > >

> > > > > > >

> > > > > > > I also noticed that we define 'interrupt-parent' as a dependency to

> > > > > > > parse, but that's wrong. The dependency is where 'interrupts' appears

> > > > > > > and where 'interrupt-parent' appears is irrelevant.

> > > > >

> > > > > No, the interrupt-parent parsing is correct and it's needed for

> > > > > interrupt controllers to probe in the right order. But

> > > > > interrupt-parent is also needs to be looked at for parsing

> > > > > "interrupts".

> > > >

> > > > If you parse 'interrupts' for interrupt controllers (which in turn

> > > > will use 'interrupt-parent'), then you aren't going to need to track

> > > > 'interrupt-parent' by itself.

> > >

> > > Do all interrupt controllers (that are not the root interrupt

> > > controller) need to have "interrupts" property? If yes, then yeah,

> > > that makes sense. But I vaguely remember that this wasn't the case for

> > > some DT I saw.

> >

> > There are some cases of stacked controllers where it's implicit.

>

> In that case, I think it's good to track interrupt-parent explicitly.

> Doesn't really hurt anything. We already protect for stuff like making

> sure a parent doesn't depend on its child, etc.


Given the interrupt controller is probably always going to be there,
it probably doesn't really matter. But the dependency is wrong.

Does this work:

bus {
  interrupt-parent = <&root_int>;

  root_int: interrupt-controller {
  };

  device {
    interrupts = <1>;
  };
};

The only dependency here should be /bus/device -> root_int.

> > >

> > > Ah, here's one I found.

> > > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/arm/boot/dts/mt2701.dtsi#n209

> >

> > Right, so this is one of several cases of custom interrupt mapping

> > properties (mediatek,ext-irq-range). Really, 'interrupts' or

> > 'interrupt-map' should have been used here, but 'interrupt-map'

> > doesn't really scale well if you have large ranges of interrupts.

> >

> > To handle the dependency with just 'interrupt-parent', you need to

> > find nodes that are themselves an 'interrupt-parent' and then find

> > their 'interrupt-parent'.

>

> Not sure I understand this.

>

> On a side note, if I'm adding device links between a device and the

> "interrupt-parent" it's pointing to, at worst, I'm having it depend on

> an interrupt controller its child devices would depend on. This

> combined with the fact that "weird" links like "parent depending on

> child",


The above would be this case if you treat root_int as a dependency of
bus. It's not, but I guess that plus the child dependency on parent
makes interrupt dependencies mostly work.

> "non-device node having interrupt-parent",


Yes, that's probably 95% of interrupt-parent cases. It's either at the
root or bus node.

> etc are already

> ignored, seems safe to leave in "interrupt-parent" to catch these

> cases where interrupt controllers don't specify "interrupts" or

> "interrupt-map"? I don't mind removing it, but maybe we can wait till

> we get fw_devlink=on and then remove it to see if anything breaks? If

> nothing breaks, we can remove explicit interrupt-parent parsing?


Okay, as long as we're breaking platforms once potentially.

> Going back to interrupt-map, I understand the syntax now. I'm trying

> to see if I can break up of_irq_parse_raw() into smaller pieces and

> reuse (call into) some of that code. While doing that I see that when

> "address-cells" isn't present, the "addrsize" is initialized to 2 [1]

> but when "address-cells" isn't present, the "newaddrsize" is

> initialized to 0 [1]. Why is the default value of #address-cells two

> different numbers?


It's some ancient code that needs to handle quirks of ancient systems.

The first one is the #address-cells for the device's bus. The second
is #address-cells in the interrupt-controller/map. It's complicated
because interrupt hierarchies used to follow the bus hierarchies.
Generally in modern systems #address-cells used for interrupt-map
purposes (the 2nd case) will always be 0.

Note that there's generic nexus code to support gpio-map. It works
similarly though without the address-cells part. Any refactoring
should take that into account.

Rob
Saravana Kannan Jan. 8, 2021, 4:34 a.m. UTC | #14
On Thu, Jan 7, 2021 at 7:36 PM Rob Herring <robh@kernel.org> wrote:
>

> On Thu, Jan 7, 2021 at 4:13 PM Saravana Kannan <saravanak@google.com> wrote:

> >

> > On Thu, Jan 7, 2021 at 11:33 AM Rob Herring <robh@kernel.org> wrote:

> > >

> > > On Thu, Jan 7, 2021 at 12:09 PM Saravana Kannan <saravanak@google.com> wrote:

> > > >

> > > > On Thu, Jan 7, 2021 at 10:39 AM Rob Herring <robh@kernel.org> wrote:

> > > > >

> > > > > On Wed, Jan 6, 2021 at 11:53 AM Saravana Kannan <saravanak@google.com> wrote:

> > > > > >

> > > > > > On Sat, Jan 2, 2021 at 3:37 AM Marc Zyngier <maz@kernel.org> wrote:

> > > > > > >

> > > > > > > On Thu, 31 Dec 2020 21:12:40 +0000,

> > > > > > > Rob Herring <robh@kernel.org> wrote:

> > > > > > > >

> > > > > > > > On Mon, Dec 21, 2020 at 09:30:45AM +0000, Marc Zyngier wrote:

> > > > > > > > > On 2020-12-18 21:07, Saravana Kannan wrote:

> > > > > > > > > > Add support for creating device links out of interrupts property.

> > > > > > > > > >

> > > > > > > > > > Cc: Marc Zyngier <maz@kernel.org>

> > > > > > > > > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > > > > > > > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> > > > > > > > > > ---

> > > > > > > > > > Rob/Greg,

> > > > > > > > > >

> > > > > > > > > > This might need to go into driver-core to avoid conflict

> > > > > > > > > > due to fw_devlink refactor series that merged there.

> > > > > > > > > >

> > > > > > > > > > Thanks,

> > > > > > > > > > Saravana

> > > > > > > > > >

> > > > > > > > > >

> > > > > > > > > >  drivers/of/property.c | 17 +++++++++++++++++

> > > > > > > > > >  1 file changed, 17 insertions(+)

> > > > > > > > > >

> > > > > > > > > > diff --git a/drivers/of/property.c b/drivers/of/property.c

> > > > > > > > > > index 5f9eed79a8aa..e56a5eae0a0b 100644

> > > > > > > > > > --- a/drivers/of/property.c

> > > > > > > > > > +++ b/drivers/of/property.c

> > > > > > > > > > @@ -1271,6 +1271,22 @@ static struct device_node

> > > > > > > > > > *parse_iommu_maps(struct device_node *np,

> > > > > > > > > >   return of_parse_phandle(np, prop_name, (index * 4) + 1);

> > > > > > > > > >  }

> > > > > > > > > >

> > > > > > > > > > +static struct device_node *parse_interrupts(struct device_node *np,

> > > > > > > > > > +                                     const char *prop_name, int index)

> > > > > > > > > > +{

> > > > > > > > > > + struct device_node *sup;

> > > > > > > > > > +

> > > > > > > > > > + if (strcmp(prop_name, "interrupts") || index)

> > > > > > > > > > +         return NULL;

> > > > > > > > > > +

> > > > > > > > > > + of_node_get(np);

> > > > > > > > > > + while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))

> > > > > > > > > > +         np = of_get_next_parent(np);

> > > > > > > > > > + of_node_put(np);

> > > > > > > > > > +

> > > > > > > > > > + return sup;

> > > > > > > > > > +}

> > > > > > > > > > +

> > > > > > > > > >  static const struct supplier_bindings of_supplier_bindings[] = {

> > > > > > > > > >   { .parse_prop = parse_clocks, },

> > > > > > > > > >   { .parse_prop = parse_interconnects, },

> > > > > > > > > > @@ -1296,6 +1312,7 @@ static const struct supplier_bindings

> > > > > > > > > > of_supplier_bindings[] = {

> > > > > > > > > >   { .parse_prop = parse_pinctrl6, },

> > > > > > > > > >   { .parse_prop = parse_pinctrl7, },

> > > > > > > > > >   { .parse_prop = parse_pinctrl8, },

> > > > > > > > > > + { .parse_prop = parse_interrupts, },

> > > > > > > > > >   { .parse_prop = parse_regulators, },

> > > > > > > > > >   { .parse_prop = parse_gpio, },

> > > > > > > > > >   { .parse_prop = parse_gpios, },

> > > > > > > > >

> > > > > > > > > You don't really describe what this is for so I'm only guessing

> > > > > > > > > from the context. If you want to follow the interrupt hierarchy,

> > > > > > > > > "interrupt-parent" isn't enough. You also need to track

> > > > > > > > > things like interrupt-map, or anything that carries a phandle

> > > > > > > > > to an interrupt controller.

> > > > > > > >

> > > > > > > > We don't need to follow the hierarchy, we just need the immediate

> > > > > > > > dependencies.

> > > > > > >

> > > > > > > Indeed. I also wonder why this isn't just a irq_find_parent() call, TBH.

> > > > > >

> > > > > > Thanks Rob for explaining it.

> > > > > >

> > > > > > Marc, I wasn't sure if Rob would be okay with including of_irq.h here.

> > > > > > Also, I'm trying to keep of/property.c independent of the framework

> > > > > > code for now. The long term goal is to see if I can move out most of

> > > > > > this into the frameworks. But I want to do that after I sort of some

> > > > > > of the larger problems (like getting fw_devlink=on to work on all

> > > > > > devices  first). Let me know if you have a strong preference for right

> > > > > > now, if not, I'd rather keep property.c independent for now.

> > > > > >

> > > > > > I wasn't aware of interrupt-map until a few weeks ago and didn't know

> > > > > > it carried phandles. I can add support for that too. There's no reason

> > > > > > for all of them to go in one patch though.

> > > > > >

> > > > > > >

> > > > > > > > But you are right that 'interrupt-map' also needs to be tracked.

> > > > > > >

> > > > > > > And 'interrupts-extended', while we're at it.

> > > > > >

> > > > > > This is already handled.

> > > > > >

> > > > > > > >

> > > > > > > > I also noticed that we define 'interrupt-parent' as a dependency to

> > > > > > > > parse, but that's wrong. The dependency is where 'interrupts' appears

> > > > > > > > and where 'interrupt-parent' appears is irrelevant.

> > > > > >

> > > > > > No, the interrupt-parent parsing is correct and it's needed for

> > > > > > interrupt controllers to probe in the right order. But

> > > > > > interrupt-parent is also needs to be looked at for parsing

> > > > > > "interrupts".

> > > > >

> > > > > If you parse 'interrupts' for interrupt controllers (which in turn

> > > > > will use 'interrupt-parent'), then you aren't going to need to track

> > > > > 'interrupt-parent' by itself.

> > > >

> > > > Do all interrupt controllers (that are not the root interrupt

> > > > controller) need to have "interrupts" property? If yes, then yeah,

> > > > that makes sense. But I vaguely remember that this wasn't the case for

> > > > some DT I saw.

> > >

> > > There are some cases of stacked controllers where it's implicit.

> >

> > In that case, I think it's good to track interrupt-parent explicitly.

> > Doesn't really hurt anything. We already protect for stuff like making

> > sure a parent doesn't depend on its child, etc.

>

> Given the interrupt controller is probably always going to be there,

> it probably doesn't really matter. But the dependency is wrong.

>

> Does this work:

>

> bus {

>   interrupt-parent = <&root_int>;

>

>   root_int: interrupt-controller {

>   };

>

>   device {

>     interrupts = <1>;

>   };

> };

>

> The only dependency here should be /bus/device -> root_int.


Right, and that's the only one that'll get created because a parent
(bus) can't depend on a child (root_int). There are other similar
things that'll effectively make the interrupt-parent handling harmless
and also cover the few odd cases like the one I pointed out.

> > > >

> > > > Ah, here's one I found.

> > > > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/arm/boot/dts/mt2701.dtsi#n209

> > >

> > > Right, so this is one of several cases of custom interrupt mapping

> > > properties (mediatek,ext-irq-range). Really, 'interrupts' or

> > > 'interrupt-map' should have been used here, but 'interrupt-map'

> > > doesn't really scale well if you have large ranges of interrupts.

> > >

> > > To handle the dependency with just 'interrupt-parent', you need to

> > > find nodes that are themselves an 'interrupt-parent' and then find

> > > their 'interrupt-parent'.

> >

> > Not sure I understand this.

> >

> > On a side note, if I'm adding device links between a device and the

> > "interrupt-parent" it's pointing to, at worst, I'm having it depend on

> > an interrupt controller its child devices would depend on. This

> > combined with the fact that "weird" links like "parent depending on

> > child",

>

> The above would be this case if you treat root_int as a dependency of

> bus. It's not, but I guess that plus the child dependency on parent

> makes interrupt dependencies mostly work.

>

> > "non-device node having interrupt-parent",

>

> Yes, that's probably 95% of interrupt-parent cases. It's either at the

> root or bus node.

>

> > etc are already

> > ignored, seems safe to leave in "interrupt-parent" to catch these

> > cases where interrupt controllers don't specify "interrupts" or

> > "interrupt-map"? I don't mind removing it, but maybe we can wait till

> > we get fw_devlink=on and then remove it to see if anything breaks? If

> > nothing breaks, we can remove explicit interrupt-parent parsing?

>

> Okay, as long as we're breaking platforms once potentially.


I'm not sure if the sentence needs a negative somewhere in there, but
I believe we are in agreement.

> > Going back to interrupt-map, I understand the syntax now. I'm trying

> > to see if I can break up of_irq_parse_raw() into smaller pieces and

> > reuse (call into) some of that code. While doing that I see that when

> > "address-cells" isn't present, the "addrsize" is initialized to 2 [1]

> > but when "address-cells" isn't present, the "newaddrsize" is

> > initialized to 0 [1]. Why is the default value of #address-cells two

> > different numbers?

>

> It's some ancient code that needs to handle quirks of ancient systems.

>

> The first one is the #address-cells for the device's bus. The second

> is #address-cells in the interrupt-controller/map. It's complicated

> because interrupt hierarchies used to follow the bus hierarchies.

> Generally in modern systems #address-cells used for interrupt-map

> purposes (the 2nd case) will always be 0.

>

> Note that there's generic nexus code to support gpio-map. It works

> similarly though without the address-cells part. Any refactoring

> should take that into account.


Ok, thanks for the info. I'll refactor out the common code and try to
use that to implement interrupt-map support.

-Saravana
Geert Uytterhoeven Jan. 20, 2021, 9:53 a.m. UTC | #15
Hi Saravana,

On Fri, Dec 18, 2020 at 10:11 PM Saravana Kannan <saravanak@google.com> wrote:
> Add support for creating device links out of interrupts property.

>

> Cc: Marc Zyngier <maz@kernel.org>

> Cc: Kevin Hilman <khilman@baylibre.com>

> Signed-off-by: Saravana Kannan <saravanak@google.com>


Thanks for your patch!

This does not seem to add all links.  I see links being created to the
secondary interrupt controller (e61c0000 "renesas,irqc"), but not to
the primary interrupt controller (GIC)

Which is good, as the GIC driver is not a platform_driver, and thus
creating links would break everything ;-)

BTW, I'd _love_ the GIC driver to be a platform_driver, as the GIC is
part of a power/and or clock domain on Renesas SoCs...

Gr{oetje,eeting}s,

                        Geert

-- 
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds
Marc Zyngier Jan. 20, 2021, 10:04 a.m. UTC | #16
On 2021-01-20 09:53, Geert Uytterhoeven wrote:
> Hi Saravana,

> 

> On Fri, Dec 18, 2020 at 10:11 PM Saravana Kannan <saravanak@google.com> 

> wrote:

>> Add support for creating device links out of interrupts property.

>> 

>> Cc: Marc Zyngier <maz@kernel.org>

>> Cc: Kevin Hilman <khilman@baylibre.com>

>> Signed-off-by: Saravana Kannan <saravanak@google.com>

> 

> Thanks for your patch!

> 

> This does not seem to add all links.  I see links being created to the

> secondary interrupt controller (e61c0000 "renesas,irqc"), but not to

> the primary interrupt controller (GIC)

> 

> Which is good, as the GIC driver is not a platform_driver, and thus

> creating links would break everything ;-)

> 

> BTW, I'd _love_ the GIC driver to be a platform_driver, as the GIC is

> part of a power/and or clock domain on Renesas SoCs...


The trouble is that we need the GIC much earlier than the device model
is available, because the timer needs to be available super early.
This isn't specific to the GIC, by the way, but also to all root
interrupt controllers that end-up controlling the per-CPU interrupts.

If you try to relax this constraint, you'll end up observing some of the
very weird dependencies between sysfs, sched, and the device model (I 
went
there a few years back, wasted a week on it, did a reset --hard on the 
branch,
and swore never to look at this again! ;-)

But for a start, I'd like the ITS code to be turned into a platform 
driver,
as this would potentially allow for the various domains to be 
instantiated
dynamically. One day.

         M.
-- 
Jazz is not dead. It just smells funny...
Geert Uytterhoeven Jan. 20, 2021, 2:28 p.m. UTC | #17
Hi Saravana,

On Wed, Jan 20, 2021 at 10:53 AM Geert Uytterhoeven
<geert@linux-m68k.org> wrote:
> On Fri, Dec 18, 2020 at 10:11 PM Saravana Kannan <saravanak@google.com> wrote:

> > Add support for creating device links out of interrupts property.

> >

> > Cc: Marc Zyngier <maz@kernel.org>

> > Cc: Kevin Hilman <khilman@baylibre.com>

> > Signed-off-by: Saravana Kannan <saravanak@google.com>

>

> Thanks for your patch!

>

> This does not seem to add all links.  I see links being created to the

> secondary interrupt controller (e61c0000 "renesas,irqc"), but not to

> the primary interrupt controller (GIC)

>

> Which is good, as the GIC driver is not a platform_driver, and thus

> creating links would break everything ;-)


of_link_to_phandle() ignores device nodes where OF_POPULATED
is set, and of_irq_init() sets that flag.  Hence the GIC is ignored.

Gr{oetje,eeting}s,

                        Geert

-- 
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds
Saravana Kannan Jan. 20, 2021, 5:15 p.m. UTC | #18
On Wed, Jan 20, 2021 at 6:28 AM Geert Uytterhoeven <geert@linux-m68k.org> wrote:
>

> Hi Saravana,

>

> On Wed, Jan 20, 2021 at 10:53 AM Geert Uytterhoeven

> <geert@linux-m68k.org> wrote:

> > On Fri, Dec 18, 2020 at 10:11 PM Saravana Kannan <saravanak@google.com> wrote:

> > > Add support for creating device links out of interrupts property.

> > >

> > > Cc: Marc Zyngier <maz@kernel.org>

> > > Cc: Kevin Hilman <khilman@baylibre.com>

> > > Signed-off-by: Saravana Kannan <saravanak@google.com>

> >

> > Thanks for your patch!

> >

> > This does not seem to add all links.  I see links being created to the

> > secondary interrupt controller (e61c0000 "renesas,irqc"), but not to

> > the primary interrupt controller (GIC)

> >

> > Which is good, as the GIC driver is not a platform_driver, and thus

> > creating links would break everything ;-)

>

> of_link_to_phandle() ignores device nodes where OF_POPULATED

> is set, and of_irq_init() sets that flag.  Hence the GIC is ignored.


Geert,

Yes, I know :)  I wrote it that way for GIC and some of the early
devices that can't use the driver core. And as Marc said in the other
email, it looks like GIC is going to be stuck as a non-device for a
while. But this patch and others that'll follow are all set up for
allowing non-root interrupt controllers to be implemented as platform
devices (or <anybus> device).

-Saravana
diff mbox series

Patch

diff --git a/drivers/of/property.c b/drivers/of/property.c
index 5f9eed79a8aa..e56a5eae0a0b 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1271,6 +1271,22 @@  static struct device_node *parse_iommu_maps(struct device_node *np,
 	return of_parse_phandle(np, prop_name, (index * 4) + 1);
 }
 
+static struct device_node *parse_interrupts(struct device_node *np,
+					    const char *prop_name, int index)
+{
+	struct device_node *sup;
+
+	if (strcmp(prop_name, "interrupts") || index)
+		return NULL;
+
+	of_node_get(np);
+	while (np && !(sup = of_parse_phandle(np, "interrupt-parent", 0)))
+		np = of_get_next_parent(np);
+	of_node_put(np);
+
+	return sup;
+}
+
 static const struct supplier_bindings of_supplier_bindings[] = {
 	{ .parse_prop = parse_clocks, },
 	{ .parse_prop = parse_interconnects, },
@@ -1296,6 +1312,7 @@  static const struct supplier_bindings of_supplier_bindings[] = {
 	{ .parse_prop = parse_pinctrl6, },
 	{ .parse_prop = parse_pinctrl7, },
 	{ .parse_prop = parse_pinctrl8, },
+	{ .parse_prop = parse_interrupts, },
 	{ .parse_prop = parse_regulators, },
 	{ .parse_prop = parse_gpio, },
 	{ .parse_prop = parse_gpios, },