Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Kenneth Graunke <kenneth@whitecape.org>
To: Zhanjun Dong <zhanjun.dong@intel.com>,
	intel-xe@lists.freedesktop.org,
	John Harrison <john.c.harrison@intel.com>
Cc: Julia Filipchuk <julia.filipchuk@intel.com>
Subject: Re: [PATCH v2] drm/xe/guc: Disable lite restore for MTL
Date: Thu, 20 Mar 2025 03:23:02 -0700	[thread overview]
Message-ID: <6142361.lOV4Wx5bFT@imeretto> (raw)
In-Reply-To: <76f06baa-59b2-4d6a-87e5-a89a2d94904b@intel.com>

On Wednesday, March 19, 2025 1:20:40 PM Pacific Daylight Time John Harrison 
wrote:
> On 3/19/2025 10:28 AM, Zhanjun Dong wrote:
> > Lite restore for MTL is not POR for Xe, then disable it for MTL.
> 
> The point is that it is causing unexplained problems. And it is Xe as a
> whole that is not POR on MTL, not just lite restore. Hence no priority
> to investigate what is going wrong and how to fix it properly.
> 
> You should also reference the upstream bug that this is in response to.
> I think the tag is 'Closes:'?

Better yet, I managed to track down the missing invalidation.  I've just sent 
a patch to intel-xe@fd.o titled "drm/xe: Invalidate L3 read-only cachelines 
for geometry streams too" [1] which fixes the underlying issue and makes 
Firefox render correctly on Meteorlake with lite restore still enabled.  And 
probably fixes other bugs.

Assuming that patch is acceptable, I don't think we'll need to disable lite 
restore.  Which is certainly preferable!

--Ken

[1] https://lists.freedesktop.org/archives/intel-xe/2025-March/073997.html



  reply	other threads:[~2025-03-20 10:26 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-19 17:28 [PATCH v2] drm/xe/guc: Disable lite restore for MTL Zhanjun Dong
2025-03-19 17:33 ` ✓ CI.Patch_applied: success for drm/xe/guc: Disable lite restore for MTL (rev2) Patchwork
2025-03-19 17:33 ` ✓ CI.checkpatch: " Patchwork
2025-03-19 17:34 ` ✓ CI.KUnit: " Patchwork
2025-03-19 17:51 ` ✓ CI.Build: " Patchwork
2025-03-19 17:53 ` ✓ CI.Hooks: " Patchwork
2025-03-19 17:54 ` ✓ CI.checksparse: " Patchwork
2025-03-19 18:15 ` ✓ Xe.CI.BAT: " Patchwork
2025-03-19 19:15 ` ✗ Xe.CI.Full: failure " Patchwork
2025-03-19 20:20 ` [PATCH v2] drm/xe/guc: Disable lite restore for MTL John Harrison
2025-03-20 10:23   ` Kenneth Graunke [this message]
2025-03-20 14:27     ` Dong, Zhanjun

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=6142361.lOV4Wx5bFT@imeretto \
    --to=kenneth@whitecape.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=john.c.harrison@intel.com \
    --cc=julia.filipchuk@intel.com \
    --cc=zhanjun.dong@intel.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