From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id C9BBAE95A98 for ; Tue, 30 Dec 2025 20:48:14 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 1EDD96B0088; Tue, 30 Dec 2025 15:48:14 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 19B126B0089; Tue, 30 Dec 2025 15:48:14 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 0C5106B008A; Tue, 30 Dec 2025 15:48:14 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0016.hostedemail.com [216.40.44.16]) by kanga.kvack.org (Postfix) with ESMTP id F00A66B0088 for ; Tue, 30 Dec 2025 15:48:13 -0500 (EST) Received: from smtpin05.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay03.hostedemail.com (Postfix) with ESMTP id 9038AB7E55 for ; Tue, 30 Dec 2025 20:48:13 +0000 (UTC) X-FDA: 84277324866.05.EC4C5CD Received: from out-184.mta0.migadu.com (out-184.mta0.migadu.com [91.218.175.184]) by imf19.hostedemail.com (Postfix) with ESMTP id A81D51A0018 for ; Tue, 30 Dec 2025 20:48:11 +0000 (UTC) Authentication-Results: imf19.hostedemail.com; dkim=pass header.d=linux.dev header.s=key1 header.b=Wub7OS+L; dmarc=pass (policy=none) header.from=linux.dev; spf=pass (imf19.hostedemail.com: domain of roman.gushchin@linux.dev designates 91.218.175.184 as permitted sender) smtp.mailfrom=roman.gushchin@linux.dev ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1767127692; a=rsa-sha256; cv=none; b=M8OSwdnUhjadCePe9W13+KHKiJlnlos5ke/xgje5BV0LEWZhoNfyk6kd5lCoiZXWAvKMoM c4xyKwBCjfT4A0o3L985fY+htJcaFZ9rPDBOKptPnR4kVq8eUkHbW2wih2PB5yUn4O3qtE 7Bvly3ynRbd8uTKNF7vrFgxY+YNnTkw= ARC-Authentication-Results: i=1; imf19.hostedemail.com; dkim=pass header.d=linux.dev header.s=key1 header.b=Wub7OS+L; dmarc=pass (policy=none) header.from=linux.dev; spf=pass (imf19.hostedemail.com: domain of roman.gushchin@linux.dev designates 91.218.175.184 as permitted sender) smtp.mailfrom=roman.gushchin@linux.dev ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1767127692; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=UVuULU9DWzbX35aYTs+GdWerbt0qAG31AAAaM0plU/A=; b=wt1b5VKaECZFYUjMG7nMgNyq/8zaVQ5w/zy/83DiMsWRruawI8yqnKhexTf7t2LSAhPghu Qgp+fZ21WOunEFwnJlXtczDYB6xTelDKpzUXrclGWPLxU2eBRS3hlW7Z+FpZmnQctLiLoG 9mK9+8BL0ZUouH60KbWhE9IqTfmlZ3o= X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1767127689; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: in-reply-to:in-reply-to:references:references; bh=UVuULU9DWzbX35aYTs+GdWerbt0qAG31AAAaM0plU/A=; b=Wub7OS+L16NbJTJN4pl2A/cialO1q+2ltjN+k35LpGDOQBzBCQXojN0OAFrER0w8ETJ7lW 1FCtFaQlRsMZzpL0etDfrf+cr+AGLIeSwHdeihmiQkt0JaZiGfAfGZB1fhI+feDT7CepUs 3HJ/XszdHWrhdNwDQRkaEX46ErWO+cw= From: Roman Gushchin To: Shakeel Butt Cc: Qi Zheng , hannes@cmpxchg.org, hughd@google.com, mhocko@suse.com, muchun.song@linux.dev, david@kernel.org, lorenzo.stoakes@oracle.com, ziy@nvidia.com, harry.yoo@oracle.com, imran.f.khan@oracle.com, kamalesh.babulal@oracle.com, axelrasmussen@google.com, yuanchu@google.com, weixugc@google.com, chenridong@huaweicloud.com, mkoutny@suse.com, akpm@linux-foundation.org, hamzamahfooz@linux.microsoft.com, apais@linux.microsoft.com, lance.yang@linux.dev, linux-mm@kvack.org, linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, Qi Zheng Subject: Re: [PATCH v2 00/28] Eliminate Dying Memory Cgroup In-Reply-To: <6o2gnpjd7z7hxl2lu2lyevawtkcas6xar6z4zip4zc3unq27cf@k4bhpnfclnkj> (Shakeel Butt's message of "Tue, 30 Dec 2025 10:36:52 -0800") References: <7ia4ldikrbsj.fsf@castle.c.googlers.com> <423puqc6tesx7y6l4oqmslbby2rfjenfnw5pn5mgi63aq74jwj@jwgorel2uj3m> <87ecoc7gnp.fsf@linux.dev> <6o2gnpjd7z7hxl2lu2lyevawtkcas6xar6z4zip4zc3unq27cf@k4bhpnfclnkj> Date: Tue, 30 Dec 2025 20:47:58 +0000 Message-ID: <7ia4wm23y9vl.fsf@castle.c.googlers.com> MIME-Version: 1.0 Content-Type: text/plain X-Migadu-Flow: FLOW_OUT X-Rspamd-Server: rspam08 X-Rspamd-Queue-Id: A81D51A0018 X-Stat-Signature: 5je5tsdzbme8cbnwpw69e6o3joigmodf X-Rspam-User: X-HE-Tag: 1767127691-36098 X-HE-Meta: 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 okesNNjY Rl5RUneGGI2GmqpZ+bk8yU+jR7SHJyEyREnK7tGd2YYclP6RjhwneIUxskW/BmW12mnQhdaZNhBzBZKbfmDw9/uE8Vcz2SYrIPh9Md2JMorhAiqvZ1G5w6367tcd9HCFjIPITDm+OOY+teN7daXvG2eBZgQ== X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: Shakeel Butt writes: > On Mon, Dec 29, 2025 at 08:11:22PM -0800, Roman Gushchin wrote: >> Shakeel Butt writes: >> >> > On Tue, Dec 30, 2025 at 01:36:12AM +0000, Roman Gushchin wrote: >> >> Qi Zheng writes: >> >> >> >> Hey! >> >> >> >> I ran this patchset through AI review and it found few regression (which >> >> can of course be false positives). When you'll have time, can you, >> >> please, take a look and comment on which are real and which are not? >> >> >> >> Thank you! >> > >> > Hi Roman, this is really good. I assume this is Gemini model. I see BPF >> > and networking folks have automated the AI review process which is >> > really good. I think MM should also adopt that model. Are you looking >> > into automating MM review bot? >> >> Yes, absolutely. We're working on it, hopefully in January/February we >> can have something reasonably solid. > > Can you share a bit more about the plan? Are you working more on the > infra side of things or also iterating on the prompts? (I assume you are > using Chris Mason's review prompts) Mostly on the infra side. I want to look closer into mm and cgroups patches, but I need a bit more data and infra to do this. As of now we're building some basic infra to run it on scale. > On the infra side, one thing I would love to have is to get early > feedback/review on my patches before posting on the list. Will it be > possible to support such a scenario? Absolutely. You can do it already using a local setup, assuming you have an access to some decent LLM. In my experience, a standard entry-level pro subscription which is like $20/month these days is good enough to review a number of patchsets per day. This works well for reviewing personal patches and/or some targeted upstream reviews (like this one), but for covering entire subsystems we need more infra and more token budgets (and this is what we're building). Btw, I mastered a pre-configured environment which saves time on setting things up: https://github.com/rgushchin/kengp . I've been testing it with Gemini CLI, but it should work with other similar tools with some minimal changes (and I'd love to accept patches adding this support). Actually I think there will be several rounds of ai-reviews: 1) Developers can review their patches while working on the code and before sending anything upstream 2) AI bots can send feedback to proposed patchset, as it works for bpf currently 3) Maintainers and/or ci systems will run ai reviews to ensure the quality of changes (e.g. eventually we can re-review mm-next nightly to make sure it's not creating new regressions with other changes in linux-next). > On the prompt side, what kind of experiments are you doing to reduce the > false positives? I wonder if we can comeup with some recommendations > which help maintainers to describe relevant prompts for their sub-area > and be helpful for AI reviews. I like Chris's approach here: let's look into specific examples of false positives and missed bugs and tailor our prompt systems to handle these cases correctly. The smarter LLMs are, the fewer tricks we really need, so it's better to keep prompts minimal. We don't really need to write AI-specific long texts about subsystems, but sometimes codify some non-obvious design principles and limitations. > On the automation side, I assume we will start with some manual process. > I definitely see back-and-forth to improve prompts for MM and someone > needs to manually review the results generated by AI and may have to > update prompts for better results. Also we can start with opt-in > approach i.e. someone adds a tag to the subject for AI to review the > series. Yeah, there are some things to figure out on how to make sure we're not creating a lot of noise and not repeating the same feedback if it's not useful. Thanks!