Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Dong, Zhanjun" <zhanjun.dong@intel.com>
To: Kenneth Graunke <kenneth@whitecape.org>,
	<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 10:27:46 -0400	[thread overview]
Message-ID: <495d642b-22bb-42eb-9534-d81f59465d15@intel.com> (raw)
In-Reply-To: <6142361.lOV4Wx5bFT@imeretto>

Woo, so nice to hear the issue is fixed by your patch!

Then I will hold on this patch and wait for your patch get merged.
Let me know if there's somepart I can help.

Thanks Kenneth. Cheers!

Regards,
Zhanjun Dong


On 2025-03-20 6:23 a.m., Kenneth Graunke wrote:
> 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 14:27 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
2025-03-20 14:27     ` Dong, Zhanjun [this message]

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=495d642b-22bb-42eb-9534-d81f59465d15@intel.com \
    --to=zhanjun.dong@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=john.c.harrison@intel.com \
    --cc=julia.filipchuk@intel.com \
    --cc=kenneth@whitecape.org \
    /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