From: Claude Code Review Bot <claude-review@example.com>
To: dri-devel-reviews@example.com
Subject: Claude review: cgroup/dmem,drm/ttm: Improve protection in contended cases
Date: Fri, 27 Feb 2026 13:36:27 +1000 [thread overview]
Message-ID: <review-overall-20260225-dmemcg-aggressive-protect-v4-0-de847ab35184@gmx.de> (raw)
In-Reply-To: <20260225-dmemcg-aggressive-protect-v4-0-de847ab35184@gmx.de>
Overall Series Review
Subject: cgroup/dmem,drm/ttm: Improve protection in contended cases
Author: Natalie Vock <natalie.vock@gmx.de>
Patches: 13
Reviewed: 2026-02-27T13:36:27.560367
---
This is a well-structured v4 series from Natalie Vock that addresses a real and important problem: when VRAM is scarce, cgroup-protected allocations can end up in GTT because unprotected applications filled VRAM first, and TTM backs off to GTT before ever attempting eviction. The series correctly fixes this by making TTM more aggressive about evicting unprotected buffers when the allocating cgroup is within its min/low protection limits.
The series decomposes nicely into:
- **Patches 1-2**: cgroup/dmem infrastructure (protection queries, common ancestor)
- **Patch 3**: TTM refactoring to prepare for the behavioral changes
- **Patch 4**: Decoupling cgroup charge from resource allocation (correctness fix)
- **Patches 5-6**: The actual behavioral improvements (aggressive eviction + correct protection semantics)
The overall design is sound. The min vs low priority hierarchy is correctly implemented: below-min triggers full eviction (even low-protected buffers), while below-low only evicts genuinely unprotected buffers. Patch 6's common-ancestor approach correctly handles recursive protection semantics for sibling cgroup competition.
The v4 changes in response to Tvrtko's review (splitting charge decoupling, errno handling, documentation) are well-incorporated.
**Minor issues**: a doc typo in patch 2, a commit message typo in patch 4, and a comment style nit in patch 5. Nothing blocking.
---
---
Generated by Claude Code Patch Reviewer
next prev parent reply other threads:[~2026-02-27 3:36 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-25 12:10 [PATCH v4 0/6] cgroup/dmem,drm/ttm: Improve protection in contended cases Natalie Vock
2026-02-25 12:10 ` [PATCH v4 1/6] cgroup/dmem: Add queries for protection values Natalie Vock
2026-02-27 3:36 ` Claude review: " Claude Code Review Bot
2026-02-25 12:10 ` [PATCH v4 2/6] cgroup/dmem: Add dmem_cgroup_common_ancestor helper Natalie Vock
2026-02-25 17:16 ` Tejun Heo
2026-02-27 3:36 ` Claude review: " Claude Code Review Bot
2026-02-25 12:10 ` [PATCH v4 3/6] drm/ttm: Extract code for attempting allocation in a place Natalie Vock
2026-02-25 15:18 ` Tvrtko Ursulin
2026-02-25 15:27 ` Tvrtko Ursulin
2026-02-26 8:56 ` Tvrtko Ursulin
2026-02-27 3:36 ` Claude review: " Claude Code Review Bot
2026-02-25 12:10 ` [PATCH v4 4/6] drm/ttm: Split cgroup charge and resource allocation Natalie Vock
2026-02-25 15:33 ` Tvrtko Ursulin
2026-02-25 16:01 ` Tvrtko Ursulin
2026-02-27 3:36 ` Claude review: " Claude Code Review Bot
2026-02-25 12:10 ` [PATCH v4 5/6] drm/ttm: Be more aggressive when allocating below protection limit Natalie Vock
2026-02-27 3:36 ` Claude review: " Claude Code Review Bot
2026-02-25 12:10 ` [PATCH v4 6/6] drm/ttm: Use common ancestor of evictor and evictee as limit pool Natalie Vock
2026-02-27 3:36 ` Claude review: " Claude Code Review Bot
2026-02-27 3:36 ` Claude Code Review Bot [this message]
-- strict thread matches above, loose matches on Subject: below --
2026-03-02 12:37 [PATCH v5 0/6] cgroup/dmem,drm/ttm: Improve protection in contended cases Natalie Vock
2026-03-03 3:29 ` Claude review: " Claude Code Review Bot
2026-03-13 11:39 [PATCH v6 0/6] " Natalie Vock
2026-03-13 21:10 ` Claude review: " Claude Code Review 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=review-overall-20260225-dmemcg-aggressive-protect-v4-0-de847ab35184@gmx.de \
--to=claude-review@example.com \
--cc=dri-devel-reviews@example.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