From: Sasha Levin <sashal@kernel.org>
To: Julia Lawall <julia.lawall@inria.fr>
Cc: workflows@vger.kernel.org, ksummit@lists.linux.dev,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
Jonathan Corbet <corbet@lwn.net>,
Shuah Khan <skhan@linuxfoundation.org>,
Randy Dunlap <rdunlap@infradead.org>,
Mark Brown <broonie@kernel.org>, Theodore Ts'o <tytso@mit.edu>,
Laurent Pinchart <laurent.pinchart@ideasonboard.com>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Leon Romanovsky <leon@kernel.org>,
Konstantin Ryabitsev <konstantin@linuxfoundation.org>,
Thorsten Leemhuis <linux@leemhuis.info>,
"Michael S. Tsirkin" <mst@redhat.com>,
Kees Cook <kees@kernel.org>,
Geert Uytterhoeven <geert@linux-m68k.org>,
Dan Carpenter <error27@gmail.com>,
Miguel Ojeda <ojeda@kernel.org>
Subject: Re: [PATCH v3 6/7] agents: add a skill to find other instances of a fixed bug
Date: Fri, 16 Oct 2026 14:09:37 -0400 [thread overview]
Message-ID: <atJoYRBujlGx0xTV@laps> (raw)
In-Reply-To: <957f530-7954-3e2c-9975-d369af37270@inria.fr>
On Fri, Oct 16, 2026 at 02:00:15PM -0400, Julia Lawall wrote:
>
>
>On Fri, 16 Oct 2026, Sasha Levin wrote:
>
>> A bug fixed in one place often exists elsewhere, in copied code, sibling
>> drivers, or other users of the same interface, and reviewers routinely
>> ask whether that was checked. Left alone, agents tend to audit the whole
>> tree by reading it. Add a skill that states the defect as a rule,
>> searches for it through shared interfaces, copied code, the introducing
>> series and earlier fixes, and verifies each candidate before reporting
>> it.
>>
>> When Coccinelle is available, the skill searches with a semantic patch:
>> it looks for an existing one under scripts/coccinelle/, checks that the
>> rule marks the fixed site in the code before the fix, runs it over the
>> whole tree with coccicheck, and checks which code spatch could not
>> parse. These steps live in references/coccinelle.md, which the agent
>> reads only when it uses Coccinelle.
>
>Could I get some feedback from this? I would be interested to know about
>code that it can't parse. Maybe AI could write a semantic patch and try
>it?
Right, this is exactly what the skill currently says:
+2. Otherwise, write a semantic patch outside the repository. Match only what
+ the defect needs, not names or statements specific to the fixed site. Mark
[...]
I'd expect the agent to have information in the transcript about this, or are
you looking for something different?
--
Thanks,
Sasha
next prev parent reply other threads:[~2026-10-16 18:09 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-16 15:28 [PATCH v3 0/7] agents: add skills for Fixes tags, stable tags, similar bugs, and commit messages Sasha Levin
2026-10-16 15:28 ` [PATCH v3 1/7] agents: add infrastructure for agent resources Sasha Levin
2026-10-16 16:02 ` Bradley Morgan
2026-10-16 15:28 ` [PATCH v3 2/7] docs: submitting-patches: say which commit a Fixes tag names Sasha Levin
2026-10-16 16:03 ` Bradley Morgan
2026-10-16 15:28 ` [PATCH v3 3/7] docs: stable-kernel-rules: drop rules the stable trees do not apply Sasha Levin
2026-10-16 15:59 ` Greg Kroah-Hartman
2026-10-16 16:01 ` Bradley Morgan
2026-10-16 15:28 ` [PATCH v3 4/7] agents: add a skill to determine Fixes tags Sasha Levin
2026-10-16 16:04 ` Bradley Morgan
2026-10-16 15:28 ` [PATCH v3 5/7] agents: add a skill to determine stable tags Sasha Levin
2026-10-16 16:04 ` Bradley Morgan
2026-10-16 15:28 ` [PATCH v3 6/7] agents: add a skill to find other instances of a fixed bug Sasha Levin
2026-10-16 16:05 ` Bradley Morgan
2026-10-16 18:00 ` Julia Lawall
2026-10-16 18:09 ` Sasha Levin [this message]
2026-10-16 18:17 ` Julia Lawall
2026-10-16 18:32 ` Sasha Levin
2026-10-16 15:28 ` [PATCH v3 7/7] agents: add a skill to write commit messages Sasha Levin
2026-10-16 16:05 ` Bradley Morgan
2026-10-16 16:00 ` [PATCH v3 0/7] agents: add skills for Fixes tags, stable tags, similar bugs, and " Miguel Ojeda
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=atJoYRBujlGx0xTV@laps \
--to=sashal@kernel.org \
--cc=broonie@kernel.org \
--cc=corbet@lwn.net \
--cc=error27@gmail.com \
--cc=geert@linux-m68k.org \
--cc=gregkh@linuxfoundation.org \
--cc=julia.lawall@inria.fr \
--cc=kees@kernel.org \
--cc=konstantin@linuxfoundation.org \
--cc=ksummit@lists.linux.dev \
--cc=laurent.pinchart@ideasonboard.com \
--cc=leon@kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@leemhuis.info \
--cc=mst@redhat.com \
--cc=ojeda@kernel.org \
--cc=rdunlap@infradead.org \
--cc=skhan@linuxfoundation.org \
--cc=tytso@mit.edu \
--cc=workflows@vger.kernel.org \
/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