Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: sashiko-bot@kernel.org
To: "Daniel Charles" <daniel.charles@intel.com>
Cc: intel-xe@lists.freedesktop.org
Subject: Re: [PATCH] drm/xe/xe3p: Force non-compressible memory reads to 256B overfetches
Date: Tue, 29 Sep 2026 20:20:03 +0000	[thread overview]
Message-ID: <20260929202004.43DF51F000FF@smtp.kernel.org> (raw)
In-Reply-To: <20260929200839.843116-1-daniel.charles@intel.com>

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] drm/xe: missing media GT tuning for NONCOMPMEMRD256BOVRFETCHEN
--

commit 0d0918701116e6b353267a1af32ce09421b27bbd
Author: Daniel Charles <daniel.charles@intel.com>

drm/xe/xe3p: Force non-compressible memory reads to 256B overfetches

This commit adds a tuning entry to set bit 14 (NONCOMPMEMRD256BOVRFETCHEN)
of L3SQCREG2 for Xe3p and later platforms to force non-compressible memory
reads to 256B overfetches.

> diff --git a/drivers/gpu/drm/xe/xe_tuning.c b/drivers/gpu/drm/xe/xe_tuning.c
> index bcec40ca2d35f..a9bd3f8969a54 100644
> --- a/drivers/gpu/drm/xe/xe_tuning.c
> +++ b/drivers/gpu/drm/xe/xe_tuning.c

[ ... ]

> @@ -100,6 +100,10 @@ VISIBLE_IF_KUNIT const struct xe_rtp_table_sr gt_tunings = XE_RTP_TABLE_SR(
>  	  XE_RTP_ACTIONS(FIELD_SET(GAMSTLB_CTRL, BANK_HASH_MODE,
>  				   BANK_HASH_4KB_MODE))
>  	},
> +	{ XE_RTP_NAME("Tuning: Force All Non-Compressible Memory Reads to be 256B Overfetches"),
> +	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3510, XE_RTP_END_VERSION_UNDEFINED)),
> +	  XE_RTP_ACTIONS(SET(L3SQCREG2, NONCOMPMEMRD256BOVRFETCHEN))
> +	},

[Severity: Medium]
Should this tuning also be applied to the standalone Media GT?

Since this rule uses GRAPHICS_VERSION_RANGE(), it evaluates to false for
standalone Media GTs when checked in xe_rtp_match_graphics_version_range().
Xe3p platforms feature a standalone Media GT with its own L3 cache controlled
by XE2LPM_L3SQCREG2.

Previous overfetch tunings for the same cache (such as
COMPMEMRD256BOVRFETCHEN) provided a companion rule using MEDIA_VERSION_RANGE.

Is there a similar configuration needed here to optimize non-compressible
memory reads for the Media GT L3 cache?

>  );
>  EXPORT_SYMBOL_IF_KUNIT(gt_tunings);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260929200839.843116-1-daniel.charles@intel.com?part=1

  reply	other threads:[~2026-09-29 20:20 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-29 20:08 [PATCH] drm/xe/xe3p: Force non-compressible memory reads to 256B overfetches Daniel Charles
2026-09-29 20:20 ` sashiko-bot [this message]
2026-09-29 20:51 ` ✓ CI.KUnit: success for drm/xe/xe3p: Force non-compressible memory reads to 256B overfetches (rev2) Patchwork
2026-09-29 20:55 ` [PATCH] drm/xe/xe3p: Force non-compressible memory reads to 256B overfetches Matt Roper
2026-09-29 22:44 ` ✓ Xe.CI.BAT: success for drm/xe/xe3p: Force non-compressible memory reads to 256B overfetches (rev2) Patchwork
2026-09-30  3:55 ` ✓ Xe.CI.FULL: " Patchwork
     [not found] <20260923210802.297468-1-daniel.charles@intel.com>
     [not found] ` <677c0fa4-b9a2-4fa7-8e57-04b235d5e5b3@intel.com>
     [not found]   ` <20260924150422.GG730887@mdroper-desk1.amr.corp.intel.com>
     [not found]     ` <731a8c07-333f-43a4-90d6-8f2fd86a498a@intel.com>
2026-09-29 19:58       ` [PATCH] drm/xe/xe3p: Force non-compressible memory reads to 256B overfetches Matt Roper

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=20260929202004.43DF51F000FF@smtp.kernel.org \
    --to=sashiko-bot@kernel.org \
    --cc=daniel.charles@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=sashiko-reviews@lists.linux.dev \
    /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