public inbox for drm-ai-reviews@public-inbox.freedesktop.org
 help / color / mirror / Atom feed
From: Claude Code Review Bot <claude-review@example.com>
To: dri-devel-reviews@example.com
Subject: Claude review: drm/xe: Do not blindly copy system CCS pages when shrinking
Date: Tue, 05 May 2026 10:06:13 +1000	[thread overview]
Message-ID: <review-overall-20260430190923.2141506-1-matthew.brost@intel.com> (raw)
In-Reply-To: <20260430190923.2141506-1-matthew.brost@intel.com>

Overall Series Review

Subject: drm/xe: Do not blindly copy system CCS pages when shrinking
Author: Matthew Brost <matthew.brost@intel.com>
Patches: 1
Reviewed: 2026-05-05T10:06:13.444811

---

This is a single-patch optimization for the Xe driver's memory shrinker path on integrated (non-DGFX) GPUs. It avoids CCS (Compression Control Surface) page copies during BO shrinking when the BO has never been bound with a compressed PAT index. The commit message cites a ~6.5:1 ratio of eligible-but-unused CCS BOs and roughly 50% reduction in CCS copies — a meaningful optimization for memory pressure scenarios.

The approach is fundamentally sound: add a one-way `ccs_used` flag that transitions false-to-true when a VMA with a compressed PAT binds the BO, and skip the `xe_migrate_copy` in the move path when CCS was never used. However, there are a few issues worth addressing around locking documentation, error-path interaction, and the correctness of skipping the copy entirely (stub fence) versus just skipping the CCS portion.

---

---
Generated by Claude Code Patch Reviewer

  reply	other threads:[~2026-05-05  0:06 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-30 19:09 [PATCH] drm/xe: Do not blindly copy system CCS pages when shrinking Matthew Brost
2026-05-05  0:06 ` Claude Code Review Bot [this message]
2026-05-05  0:06 ` Claude review: " Claude Code Review Bot
  -- strict thread matches above, loose matches on Subject: below --
2026-05-01  1:19 [PATCH v2] " Matthew Brost
2026-05-04 23:41 ` Claude review: " Claude Code Review Bot
2026-05-04 23:41 ` 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-20260430190923.2141506-1-matthew.brost@intel.com \
    --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