Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
To: Matthew Brost <matthew.brost@intel.com>,
	"Hellstrom, Thomas" <thomas.hellstrom@intel.com>
Cc: intel-xe@lists.freedesktop.org
Subject: Re: [PATCH 0/5] GuC Buffer Cache
Date: Sun, 13 Oct 2024 14:41:06 +0200	[thread overview]
Message-ID: <bd9acb70-b774-46b8-9f6e-40cb5205f3d9@intel.com> (raw)
In-Reply-To: <ZwnYnZQQZm5jtpWL@DUT025-TGLU.fm.intel.com>



On 12.10.2024 04:02, Matthew Brost wrote:
> On Wed, Oct 09, 2024 at 07:21:20PM +0200, Michal Wajdeczko wrote:
>> Michal Wajdeczko (5):
>>   drm/xe/guc: Introduce the GuC Buffer Cache
>>   drm/xe/kunit: Allow to replace xe_managed_bo_create_pin_map()
>>   drm/xe/kunit: Add KUnit tests for GuC Buffer Cache
>>   drm/xe/pf: Prepare GuC Buffer Cache for PF-only actions
>>   drm/xe/pf: Use GuC Buffer Cache during VFs provisioning
>>
>>  drivers/gpu/drm/xe/Makefile                 |   1 +
>>  drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c | 450 ++++++++++++++++++++
>>  drivers/gpu/drm/xe/xe_bo.c                  |   4 +
>>  drivers/gpu/drm/xe/xe_gt.c                  |   6 +
>>  drivers/gpu/drm/xe/xe_gt_sriov_pf.c         |  32 ++
>>  drivers/gpu/drm/xe/xe_gt_sriov_pf.h         |   6 +
>>  drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c  |  67 +--
>>  drivers/gpu/drm/xe/xe_gt_sriov_pf_types.h   |   4 +
>>  drivers/gpu/drm/xe/xe_guc_buf.c             | 391 +++++++++++++++++
>>  drivers/gpu/drm/xe/xe_guc_buf.h             |  48 +++
>>  drivers/gpu/drm/xe/xe_guc_buf_types.h       |  40 ++
>>  11 files changed, 1017 insertions(+), 32 deletions(-)
> 
> See my comment in patch #1, please explore if that suggestion works.

already tried but it didn't work, hence this new code

> Nearly 1000+ new lines code needs to be carefully considered if this is
> required. IMO we really want avoid bloating Xe unless this has strong
> justification.

my bad, I missed to refer to [1] where it was pointed that PF should
avoid doing any memory allocations during resume/reset and with this new
cache in patch 5/5 PF is now able to do VFs re-provisioning (which uses
H2G CTB with indirect data) without any allocations

[1]
https://lore.kernel.org/intel-xe/3e13401972fd49240f486fd7d47580e576794c78.camel@intel.com/

> 
> Matt
> 
>>  create mode 100644 drivers/gpu/drm/xe/tests/xe_guc_buf_kunit.c
>>  create mode 100644 drivers/gpu/drm/xe/xe_guc_buf.c
>>  create mode 100644 drivers/gpu/drm/xe/xe_guc_buf.h
>>  create mode 100644 drivers/gpu/drm/xe/xe_guc_buf_types.h
>>
>> -- 
>> 2.43.0
>>


      reply	other threads:[~2024-10-13 12:41 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-09 17:21 [PATCH 0/5] GuC Buffer Cache Michal Wajdeczko
2024-10-09 17:21 ` [PATCH 1/5] drm/xe/guc: Introduce the " Michal Wajdeczko
2024-10-12  1:50   ` Matthew Brost
2024-10-13 11:55     ` Michal Wajdeczko
2024-10-13 17:30       ` Matthew Brost
2024-10-14 17:32         ` Michal Wajdeczko
2024-10-14 19:55           ` Matthew Brost
2024-10-22 21:51             ` Rodrigo Vivi
2024-10-09 17:21 ` [PATCH 2/5] drm/xe/kunit: Allow to replace xe_managed_bo_create_pin_map() Michal Wajdeczko
2024-10-09 17:21 ` [PATCH 3/5] drm/xe/kunit: Add KUnit tests for GuC Buffer Cache Michal Wajdeczko
2024-10-09 17:21 ` [PATCH 4/5] drm/xe/pf: Prepare GuC Buffer Cache for PF-only actions Michal Wajdeczko
2024-10-09 17:21 ` [PATCH 5/5] drm/xe/pf: Use GuC Buffer Cache during VFs provisioning Michal Wajdeczko
2024-10-09 19:11 ` ✓ CI.Patch_applied: success for GuC Buffer Cache Patchwork
2024-10-09 19:12 ` ✗ CI.checkpatch: warning " Patchwork
2024-10-09 19:13 ` ✓ CI.KUnit: success " Patchwork
2024-10-09 19:24 ` ✓ CI.Build: " Patchwork
2024-10-09 19:27 ` ✓ CI.Hooks: " Patchwork
2024-10-09 19:28 ` ✓ CI.checksparse: " Patchwork
2024-10-09 19:56 ` ✓ CI.BAT: " Patchwork
2024-10-10  8:01 ` ✗ CI.FULL: failure " Patchwork
2024-10-10 10:12   ` Michal Wajdeczko
2024-10-12  2:02 ` [PATCH 0/5] " Matthew Brost
2024-10-13 12:41   ` Michal Wajdeczko [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=bd9acb70-b774-46b8-9f6e-40cb5205f3d9@intel.com \
    --to=michal.wajdeczko@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@intel.com \
    --cc=thomas.hellstrom@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