Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Francois Dugast <francois.dugast@intel.com>
To: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: <intel-xe@lists.freedesktop.org>, <lucas.demarchi@intel.com>,
	<matthew.brost@intel.com>, <thomas.hellstrom@linux.intel.com>,
	<matthew.auld@intel.com>, <anshuman.gupta@intel.com>
Subject: Re: [PATCH 0/7] Unlock deeper package-C states (PC-10) and D3Cold
Date: Thu, 9 May 2024 12:21:50 +0200	[thread overview]
Message-ID: <ZjyjvmL8BgiAsEi1@fdugast-desk> (raw)
In-Reply-To: <20240503191309.7022-1-rodrigo.vivi@intel.com>

Hi Rodrigo,

On Fri, May 03, 2024 at 03:13:02PM -0400, Rodrigo Vivi wrote:
> For integrated graphics, this series mean the unlock of
> deeper package-C states. With this, on MTL I'm glad to
> see PC-10 even with display enabled (with eDP PSR).
> 
> On my DG2 I'm gladly getting the big saves of D3Cold when
> display is off/idle. And everything working niftly on
> the desktop environment.

This is really great. I just tested the latest version of
this series on ADL-P and confirm the device now suspends
in an idle desktop session, whereas previously this was
prevented by held references (power/runtime_usage > 0).
Besides, no other issue so far so feel free to add to
the whole series:

Tested-by: Francois Dugast <francois.dugast@intel.com>

Thanks,
Francois

> 
> But in order to achieve that, we need to relax the runtime
> PM protection around VMs and exec_queue, as explained on
> each individual patch touching them.
> 
> Please let me know your thoughts, specially around those
> relaxation cases.
> 
> Thanks,
> Rodrigo.
> 
> Rodrigo Vivi (7):
>   drm/xe: Fix xe_pm_runtime_get_if_active return
>   drm/xe: Fix xe_pm_runtime_get_if_in_use documentation
>   drm/xe: Relax runtime pm protection during execution
>   drm/xe: Relax runtime pm protection around VM
>   drm/xe: Prepare display for D3Cold
>   drm/xe: Stop checking for power_lost on D3Cold
>   drm/xe: Enable D3Cold on 'low' VRAM utilization
> 
>  drivers/gpu/drm/xe/display/xe_display.c | 10 ++++---
>  drivers/gpu/drm/xe/display/xe_display.h |  8 ++---
>  drivers/gpu/drm/xe/xe_bo.c              | 17 ++++++++++-
>  drivers/gpu/drm/xe/xe_device_types.h    |  3 --
>  drivers/gpu/drm/xe/xe_exec_queue.c      | 14 ---------
>  drivers/gpu/drm/xe/xe_guc.c             | 27 -----------------
>  drivers/gpu/drm/xe/xe_guc.h             |  1 -
>  drivers/gpu/drm/xe/xe_guc_submit.c      |  3 ++
>  drivers/gpu/drm/xe/xe_pm.c              | 40 +++++++++++++------------
>  drivers/gpu/drm/xe/xe_pm.h              |  9 ++----
>  drivers/gpu/drm/xe/xe_sched_job.c       | 10 ++-----
>  drivers/gpu/drm/xe/xe_vm.c              |  6 ++--
>  12 files changed, 58 insertions(+), 90 deletions(-)
> 
> -- 
> 2.44.0
> 

      parent reply	other threads:[~2024-05-09 10:22 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-03 19:13 [PATCH 0/7] Unlock deeper package-C states (PC-10) and D3Cold Rodrigo Vivi
2024-05-03 19:13 ` [PATCH 1/7] drm/xe: Fix xe_pm_runtime_get_if_active return Rodrigo Vivi
2024-05-06 11:47   ` Thomas Hellström
2024-05-06 13:15     ` Francois Dugast
2024-05-06 13:23       ` Thomas Hellström
2024-05-03 19:13 ` [PATCH 2/7] drm/xe: Fix xe_pm_runtime_get_if_in_use documentation Rodrigo Vivi
2024-05-06 11:49   ` Thomas Hellström
2024-05-03 19:13 ` [PATCH 3/7] drm/xe: Relax runtime pm protection during execution Rodrigo Vivi
2024-05-06 11:57   ` Thomas Hellström
2024-05-03 19:13 ` [PATCH 4/7] drm/xe: Relax runtime pm protection around VM Rodrigo Vivi
2024-05-06 12:30   ` Thomas Hellström
2024-05-06 14:23     ` Rodrigo Vivi
2024-05-07 18:19       ` Matthew Brost
2024-05-09 11:48   ` Gupta, Anshuman
2024-05-09 19:41     ` Rodrigo Vivi
2024-05-03 19:13 ` [PATCH 5/7] drm/xe: Prepare display for D3Cold Rodrigo Vivi
2024-05-03 19:13 ` [PATCH 6/7] drm/xe: Stop checking for power_lost on D3Cold Rodrigo Vivi
2024-05-07 10:35   ` Gupta, Anshuman
2024-05-03 19:13 ` [PATCH 7/7] drm/xe: Enable D3Cold on 'low' VRAM utilization Rodrigo Vivi
2024-05-09 11:51   ` Gupta, Anshuman
2024-05-03 20:34 ` ✓ CI.Patch_applied: success for Unlock deeper package-C states (PC-10) and D3Cold Patchwork
2024-05-03 20:34 ` ✓ CI.checkpatch: " Patchwork
2024-05-03 20:35 ` ✓ CI.KUnit: " Patchwork
2024-05-03 20:47 ` ✓ CI.Build: " Patchwork
2024-05-03 20:49 ` ✓ CI.Hooks: " Patchwork
2024-05-03 20:51 ` ✓ CI.checksparse: " Patchwork
2024-05-03 21:31 ` ✓ CI.BAT: " Patchwork
2024-05-04  0:18 ` ✗ CI.FULL: failure " Patchwork
2024-05-06 19:09   ` Rodrigo Vivi
2024-05-09 10:21 ` Francois Dugast [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=ZjyjvmL8BgiAsEi1@fdugast-desk \
    --to=francois.dugast@intel.com \
    --cc=anshuman.gupta@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=lucas.demarchi@intel.com \
    --cc=matthew.auld@intel.com \
    --cc=matthew.brost@intel.com \
    --cc=rodrigo.vivi@intel.com \
    --cc=thomas.hellstrom@linux.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