[PATCH] docs: dt: maintainer: Add Devicetree and OF maintainer profile document

[PATCH] docs: dt: maintainer: Add Devicetree and OF maintainer profile document

[Krzysztof Kozlowski]

Document how Devicetree and Open Firmware maintainers handle their
subsystem, especially focusing on two caveats:

Devicetree subsystem handles patches with a minor difference comparing
to other subsystems: while DT maintainers pick up OF code, they only
provide review of DT bindings without applying these.

All three DT bindings maintainers rely currently on Patchwork and due to
enormous amount of emails per day, regardless how much DT maintainers
try, they cannot read all the emails.

Cc: Rob Herring <robh@kernel.org>
Cc: Conor Dooley <conor+dt@kernel.org>
Cc: Saravana Kannan <saravanak@kernel.org>
Cc: devicetree@vger.kernel.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>

---

I expect patch to be picked up by Rob, after review.
---
 .../process/maintainer-devicetree.rst         | 70 +++++++++++++++++++
 MAINTAINERS                                   |  2 +
 2 files changed, 72 insertions(+)
 create mode 100644 Documentation/process/maintainer-devicetree.rst

diff --git a/Documentation/process/maintainer-devicetree.rst b/Documentation/process/maintainer-devicetree.rst
new file mode 100644
index 000000000000..331701bb2282
--- /dev/null
+++ b/Documentation/process/maintainer-devicetree.rst
@@ -0,0 +1,70 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================================
+Devicetree and Open Firmware Subsystem
+======================================
+
+Other Process Documents
+-----------------------
+
+Please see the documents in Documentation/devicetree/bindings/ for information
+on how to write proper Devicetree bindings and how to submit patches.
+
+Patch Review and Handling
+-------------------------
+
+Patches handled by Devicetree maintainers are processed differently depending
+on the patch type:
+
+1. Core OF driver code, e.g. drivers/of/:
+   patches are reviewed and applied by DT maintainers.
+
+2. Devicetree bindings:
+   patches are reviewed by DT maintainers but, except in certain cases, should
+   be applied by subsystem maintainers.  See also *For kernel maintainers* in
+   Documentation/devicetree/bindings/submitting-patches.rst.
+   
+3. DTS and drivers:
+   DT maintainers might provide comments, but review is generally not expected.
+
+Pachwork
+~~~~~~~~
+
+Devicetree maintainers review patches using Patchwork, so the current status of
+a patch can be checked there. For typical driver submissions, Patchwork
+receives the entire patch set, but only a few patches are usually Devicetree
+bindings that are reviewed by DT maintainers.
+
+Explanation of Patchwork statutes:
+
+ - **New**: Not yet processed by the automation toolset.
+ - **Needs ACK**: Waiting for review by DT maintainers.
+ - **Handled Elsewhere**: Non-DT patch; not being reviewed here.
+ - **RFC**: Patch was likely ignored because it was an incomplete RFC.
+ - **Changes Requested**: Patch was reviewed and DT maintainers expect changes.
+ - **Accepted**: Patch was reviewed and applied by DT maintainers to their tree.
+ - **Not Applicable**: Patch was reviewed and is likely in good shape, with a
+   *Reviewed-by* or *Acked-by* tag provided, but DT maintainers expect someone
+   else to apply it.
+
+Patch Re-review and Pinging
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Due to the high volume of email traffic, Devicetree maintainers do not read
+every email they receive and instead rely on Patchwork during the review
+process. They also often skip patches that have already been reviewed.
+
+As a result, maintainers might miss:
+
+1. Questions about already reviewed patches.
+2. Pings, for example when a patch has been reviewed by DT maintainers but has
+   not been picked up by subsystem maintainers.
+
+Such cases can be addressed by:
+
+1. Pinging DT maintainers on the IRC channel.
+2. Dropping the DT maintainer’s *Acked-by* or *Reviewed-by* tag when sending a new
+   version of the patch set, together with an explanation in the patch
+   changelog describing why the tag was removed and what is expected from DT
+   maintainers.
+
diff --git a/MAINTAINERS b/MAINTAINERS
index f877e5aaf2c7..c4929de50ab7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20050,6 +20050,7 @@ S:	Maintained
 Q:	http://patchwork.kernel.org/project/devicetree/list/
 W:	http://www.devicetree.org/
 C:	irc://irc.libera.chat/devicetree
+P:	Documentation/process/maintainer-devicetree.rst
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
 F:	Documentation/ABI/testing/sysfs-firmware-ofw
 F:	drivers/of/
@@ -20070,6 +20071,7 @@ M:	Conor Dooley <conor+dt@kernel.org>
 L:	devicetree@vger.kernel.org
 S:	Maintained
 Q:	http://patchwork.kernel.org/project/devicetree/list/
+P:	Documentation/process/maintainer-devicetree.rst
 C:	irc://irc.libera.chat/devicetree
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
 F:	Documentation/devicetree/
-- 
2.51.0

Re: [PATCH] docs: dt: maintainer: Add Devicetree and OF maintainer profile document

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Low] Typos in the new documentation file: 'Pachwork' instead of 'Patchwork' in the section header, and 'statutes' instead of 'statuses' in the text.
- [Low] Incorrect tag ordering in the MAINTAINERS file.
--

commit 51df2774f45c1a37759547f78fcc2881a87cc94a
Author: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>

docs: dt: maintainer: Add Devicetree and OF maintainer profile document

Document how Devicetree and Open Firmware maintainers handle their
subsystem, focusing on how bindings are reviewed, applied, and the heavy
reliance on Patchwork.

> diff --git a/Documentation/process/maintainer-devicetree.rst b/Documentation/process/maintainer-devicetree.rst
> new file mode 100644
> index 0000000000000..b983c5f1d851b
> --- /dev/null
> +++ b/Documentation/process/maintainer-devicetree.rst
[ ... ]
> +3. DTS and drivers:
> +   DT maintainers might provide comments, but review is generally not expected.
> +
> +Pachwork
> +~~~~~~~~

This isn't a bug, but there is a typo in the section header.

If Pachwork is changed to Patchwork, should the underline also be extended to
9 characters to avoid a Sphinx build warning for the title underline being
too short?

> +
> +Devicetree maintainers review patches using Patchwork, so the current status of
> +a patch can be checked there. For typical driver submissions, Patchwork
> +receives the entire patch set, but only a few patches are usually Devicetree
> +bindings that are reviewed by DT maintainers.
> +
> +Explanation of Patchwork statutes:

This isn't a bug, but should this be statuses instead of statutes?

> +
> + - **New**: Not yet processed by the automation toolset.
> + - **Needs ACK**: Waiting for review by DT maintainers.
[ ... ]
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 2fb1c75afd163..c0ef1ee78ffcc 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
[ ... ]
> @@ -19962,6 +19963,7 @@ M:	Conor Dooley <conor+dt@kernel.org>
>  L:	devicetree@vger.kernel.org
>  S:	Maintained
>  Q:	http://patchwork.kernel.org/project/devicetree/list/
> +P:	Documentation/process/maintainer-devicetree.rst
>  C:	irc://irc.libera.chat/devicetree

This isn't a bug, but is this the correct tag ordering?

The preferred order defined at the top of the MAINTAINERS file specifies that
the chat (C:) tag should precede the subsystem profile (P:) tag.

>  T:	git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
>  F:	Documentation/devicetree/

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260518091942.29822-2-krzysztof.kozlowski@oss.qualcomm.com?part=1

Re: [PATCH] docs: dt: maintainer: Add Devicetree and OF maintainer profile document

[Krzysztof Kozlowski]

On 18/05/2026 11:27, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [Low] Typos in the new documentation file: 'Pachwork' instead of 'Patchwork' in the section header, and 'statutes' instead of 'statuses' in the text.
> - [Low] Incorrect tag ordering in the MAINTAINERS file.
> --

Ack both, I sent v2.

Best regards,
Krzysztof