Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Christopher Snowhill <kode54@gmail.com>
To: intel-xe@lists.freedesktop.org
Subject: [Intel-xe] [PATCH v2 4/8] drm/xe: Use DRM_SCHED_POLICY_SINGLE_ENTITY mode
Date: Mon, 22 May 2023 20:58:04 -0700	[thread overview]
Message-ID: <20230523035808.635175-5-kode54@gmail.com> (raw)
In-Reply-To: <20230523035808.635175-1-kode54@gmail.com>

From: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>

We create 1 GPU scheduler per entity in Xe, use
DRM_SCHED_POLICY_SINGLE_ENTITY scheduling which is designed for that
paradigm.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_execlist.c   | 3 ++-
 drivers/gpu/drm/xe/xe_guc_submit.c | 3 +--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c
index 944dad79a037..46293c9bb6a8 100644
--- a/drivers/gpu/drm/xe/xe_execlist.c
+++ b/drivers/gpu/drm/xe/xe_execlist.c
@@ -339,7 +339,8 @@ static int execlist_engine_init(struct xe_engine *e)
 	err = drm_sched_init(&exl->sched, &drm_sched_ops, NULL,
 			     e->lrc[0].ring.size / MAX_JOB_SIZE_BYTES,
 			     XE_SCHED_HANG_LIMIT, XE_SCHED_JOB_TIMEOUT,
-			     NULL, NULL, e->hwe->name, DRM_SCHED_POLICY_DEFAULT,
+			     NULL, NULL, e->hwe->name,
+			     DRM_SCHED_POLICY_SINGLE_ENTITY,
 			     gt_to_xe(e->gt)->drm.dev);
 	if (err)
 		goto err_free;
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index c147b17690dd..a7a0d9f806bd 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1067,7 +1067,7 @@ static int guc_engine_init(struct xe_engine *e)
 	err = drm_sched_init(&ge->sched, &drm_sched_ops, NULL,
 			     e->lrc[0].ring.size / MAX_JOB_SIZE_BYTES,
 			     64, timeout, guc_to_gt(guc)->ordered_wq, NULL,
-			     e->name, DRM_SCHED_POLICY_DEFAULT,
+			     e->name, DRM_SCHED_POLICY_SINGLE_ENTITY,
 			     gt_to_xe(e->gt)->drm.dev);
 	if (err)
 		goto err_free;
@@ -1168,7 +1168,6 @@ static int guc_engine_set_priority(struct xe_engine *e,
 	if (!msg)
 		return -ENOMEM;
 
-	drm_sched_entity_set_priority(e->entity, priority);
 	guc_engine_add_msg(e, msg, SET_SCHED_PROPS);
 
 	return 0;
-- 
2.40.1


  parent reply	other threads:[~2023-05-23  3:58 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-23  3:58 [Intel-xe] [PATCH v2 0/8] Scheduler changes for upstreaming Christopher Snowhill
2023-05-23  3:58 ` [Intel-xe] [PATCH v2 1/8] fixup! drm/sched: Convert drm scheduler to use a work queue rather than kthread Christopher Snowhill
2023-05-23  3:58 ` [Intel-xe] [PATCH v2 2/8] drm/sched: Move schedule policy to scheduler Christopher Snowhill
2023-05-23  3:58 ` [Intel-xe] [PATCH v2 3/8] drm/sched: Add DRM_SCHED_POLICY_SINGLE_ENTITY scheduling policy Christopher Snowhill
2023-05-23  3:58 ` Christopher Snowhill [this message]
2023-05-23  3:58 ` [Intel-xe] [PATCH v2 5/8] drm/xe: Long running job update Christopher Snowhill
2023-05-23  3:58 ` [Intel-xe] [PATCH v2 6/8] drm/xe: Ensure LR engines are not persistent Christopher Snowhill
2023-05-23  3:58 ` [Intel-xe] [PATCH v2 7/8] drm/xe: Only try to lock external BOs in VM bind Christopher Snowhill
2023-05-23  3:58 ` [Intel-xe] [PATCH v2 8/8] drm/xe: VM LRU bulk move Christopher Snowhill
2023-05-23  4:00 ` [Intel-xe] ✓ CI.Patch_applied: success for Scheduler changes for upstreaming (rev2) Patchwork
2023-05-23  4:02 ` [Intel-xe] ✓ CI.KUnit: " Patchwork
2023-05-23  4:06 ` [Intel-xe] ✓ CI.Build: " Patchwork
2023-05-23  4:36 ` [Intel-xe] ○ CI.BAT: info " Patchwork
  -- strict thread matches above, loose matches on Subject: below --
2023-05-23  5:43 [Intel-xe] [PATCH v2 0/8] Scheduler changes for upstreaming Matthew Brost
2023-05-23  5:44 ` [Intel-xe] [PATCH v2 4/8] drm/xe: Use DRM_SCHED_POLICY_SINGLE_ENTITY mode Matthew Brost

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=20230523035808.635175-5-kode54@gmail.com \
    --to=kode54@gmail.com \
    --cc=intel-xe@lists.freedesktop.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