Devicetree
 help / color / mirror / Atom feed
From: sashiko-bot@kernel.org
To: "Tapio Reijonen" <tapio.reijonen@vaisala.com>
Cc: devicetree@vger.kernel.org, robh@kernel.org, conor+dt@kernel.org
Subject: Re: [PATCH v3 2/3] dt-bindings: serial: maxim,max310x: describe per-channel rs485 subnodes
Date: Mon, 15 Jun 2026 10:38:16 +0000	[thread overview]
Message-ID: <20260615103817.43D2E1F000E9@smtp.kernel.org> (raw)
In-Reply-To: <20260615-b4-max310x-rs485-dt-v3-2-7e79f064bdd7@vaisala.com>

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] Schema backward compatibility break for legacy multi-channel device trees by removing $refs to serial/rs485 schemas at the chip level.
--

commit d832a7d0f42d71a0c331f81efe607eabea305da1
Author: Tapio Reijonen <tapio.reijonen@vaisala.com>

dt-bindings: serial: maxim,max310x: describe per-channel rs485 subnodes

This commit splits the binding for the MAX310x UART family, introducing
per-channel child nodes for multi-channel parts while keeping single-channel
parts as serial nodes. It removes the top-level serial and RS-485 references
and conditionally maps them based on the compatible string.

> diff --git a/Documentation/devicetree/bindings/serial/maxim,max310x.yaml b/Documentation/devicetree/bindings/serial/maxim,max310x.yaml
> index 889eeaca64a02..e598dda4d13f5 100644
> --- a/Documentation/devicetree/bindings/serial/maxim,max310x.yaml
> +++ b/Documentation/devicetree/bindings/serial/maxim,max310x.yaml
[ ... ]
> @@ -49,8 +56,55 @@ required:
>  
>  allOf:
>    - $ref: /schemas/spi/spi-peripheral-props.yaml#
> -  - $ref: /schemas/serial/serial.yaml#
> -  - $ref: /schemas/serial/rs485.yaml#
> +
> +  - if:
> +      properties:
> +        compatible:
> +          contains:
> +            enum:
> +              - maxim,max3107
> +              - maxim,max3108
> +    then:
> +      allOf:
> +        - $ref: /schemas/serial/serial.yaml#
> +        - $ref: /schemas/serial/rs485.yaml#
> +
> +  - if:
> +      properties:
> +        compatible:
> +          contains:
> +            enum:
> +              - maxim,max3109
> +              - maxim,max14830
> +    then:
> +      properties:

[Severity: Medium]
The commit message notes that existing users are unaffected because the driver
still reads chip-level RS-485 for single-channel and legacy device trees.

However, does this change break schema validation for legacy multi-channel
device trees?

By removing the top-level references to serial.yaml and rs485.yaml for
multi-channel parts, and because the binding uses unevaluatedProperties: false
at the top level, any legacy multi-channel device trees that still declare
serial or RS-485 properties at the chip level will now trigger unevaluated
property validation errors during dtbs_check.

Could we retain the top-level references for multi-channel parts, perhaps with
a deprecation note, to preserve ABI backward compatibility for existing device
trees?

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260615-b4-max310x-rs485-dt-v3-0-7e79f064bdd7@vaisala.com?part=2

  reply	other threads:[~2026-06-15 10:38 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-15 10:27 [PATCH v3 0/3] serial: max310x: honour per-channel DT RS485 properties Tapio Reijonen
2026-06-15 10:27 ` [PATCH v3 1/3] serial: max310x: register GPIO controller before adding UART ports Tapio Reijonen
2026-06-15 10:43   ` sashiko-bot
2026-06-15 10:27 ` [PATCH v3 2/3] dt-bindings: serial: maxim,max310x: describe per-channel rs485 subnodes Tapio Reijonen
2026-06-15 10:38   ` sashiko-bot [this message]
2026-06-15 10:27 ` [PATCH v3 3/3] serial: max310x: honour rs485 properties from per-channel DT subnode Tapio Reijonen
2026-06-15 10:39   ` sashiko-bot

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260615103817.43D2E1F000E9@smtp.kernel.org \
    --to=sashiko-bot@kernel.org \
    --cc=conor+dt@kernel.org \
    --cc=devicetree@vger.kernel.org \
    --cc=robh@kernel.org \
    --cc=sashiko-reviews@lists.linux.dev \
    --cc=tapio.reijonen@vaisala.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox