* [PATCH] RFC: ARM: dts: ixp4xx: Fix interrupt-map weirdness
@ 2026-07-05 22:15 Linus Walleij
2026-07-05 22:22 ` sashiko-bot
0 siblings, 1 reply; 2+ messages in thread
From: Linus Walleij @ 2026-07-05 22:15 UTC (permalink / raw)
To: Imre Kaloz, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: linux-arm-kernel, devicetree, Linus Walleij
Building the DTBs for IXP4xx results in a few thousand lines
of this:
arch/arm/boot/dts/intel/ixp/intel-ixp42x-adi-coyote.dts:68.4-78.31:
Warning (interrupt_map): /soc/pci@c0000000:interrupt-map:
Missing property '#address-cells' in node /soc/gpio@c8004000,
using 0 as fallback
(...)
I don't understand why an *interrupt* map needs address-cells, but
I suppose I am missing something. I have not seen this before but
it started appearing.
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi b/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi
index 0adeccabd4fe..b6ef98a88c4e 100644
--- a/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi
+++ b/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi
@@ -114,6 +114,7 @@ gpio0: gpio@c8004000 {
reg = <0xc8004000 0x1000>;
gpio-controller;
#gpio-cells = <2>;
+ #address-cells = <0>;
interrupt-controller;
#interrupt-cells = <2>;
};
---
base-commit: dc59e4fea9d83f03bad6bddf3fa2e52491777482
change-id: 20260705-ixp4xx-dts-gpio-cells-ed21349de298
Best regards,
--
Linus Walleij <linusw@kernel.org>
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH] RFC: ARM: dts: ixp4xx: Fix interrupt-map weirdness
2026-07-05 22:15 [PATCH] RFC: ARM: dts: ixp4xx: Fix interrupt-map weirdness Linus Walleij
@ 2026-07-05 22:22 ` sashiko-bot
0 siblings, 0 replies; 2+ messages in thread
From: sashiko-bot @ 2026-07-05 22:22 UTC (permalink / raw)
To: Linus Walleij; +Cc: robh, conor+dt, devicetree
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] Adding `#address-cells = <0>;` to the GPIO node breaks dt-schema validation because the binding schema uses `additionalProperties: false` and does not define `#address-cells`.
--
commit 41571606070d7063df98228dc5614c488e017fdc
Author: Linus Walleij <linusw@kernel.org>
RFC: ARM: dts: ixp4xx: Fix interrupt-map weirdness
This commit adds #address-cells = <0>; to the GPIO node in the IXP4xx
device tree to fix a dtc warning related to interrupt-map.
> diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi b/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi
> index 0adeccabd4fef..b6ef98a88c4e5 100644
> --- a/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi
> +++ b/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi
> @@ -114,6 +114,7 @@ gpio0: gpio@c8004000 {
> reg = <0xc8004000 0x1000>;
> gpio-controller;
> #gpio-cells = <2>;
> + #address-cells = <0>;
[Severity: Low]
Will this cause a schema validation error during make dtbs_check?
The corresponding YAML schema for this node
(Documentation/devicetree/bindings/gpio/intel,ixp4xx-gpio.yaml) enforces
additionalProperties: false and does not define #address-cells.
Without updating the YAML binding to explicitly permit
"#address-cells": { const: 0 }, the dt-schema validation will report an
unrecognized property error.
> interrupt-controller;
> #interrupt-cells = <2>;
> };
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260706-ixp4xx-dts-gpio-cells-v1-1-98fa3ba0ad2d@kernel.org?part=1
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2026-07-05 22:22 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-05 22:15 [PATCH] RFC: ARM: dts: ixp4xx: Fix interrupt-map weirdness Linus Walleij
2026-07-05 22:22 ` sashiko-bot
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox