Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
To: <intel-xe@lists.freedesktop.org>
Cc: Danilo Krummrich <dakr@redhat.com>, Luben Tuikov <ltuikov89@gmail.com>
Subject: [PATCH 06/13] drm/sched: Don't disturb the entity when in RR-mode scheduling
Date: Fri, 8 Dec 2023 15:27:16 -0500	[thread overview]
Message-ID: <20231208202723.918082-6-rodrigo.vivi@intel.com> (raw)
In-Reply-To: <20231208202723.918082-1-rodrigo.vivi@intel.com>

From: Luben Tuikov <ltuikov89@gmail.com>

Don't call drm_sched_select_entity() in drm_sched_run_job_queue().  In fact,
rename __drm_sched_run_job_queue() to just drm_sched_run_job_queue(), and let
it do just that, schedule the work item for execution.

The problem is that drm_sched_run_job_queue() calls drm_sched_select_entity()
to determine if the scheduler has an entity ready in one of its run-queues,
and in the case of the Round-Robin (RR) scheduling, the function
drm_sched_rq_select_entity_rr() does just that, selects the _next_ entity
which is ready, sets up the run-queue and completion and returns that
entity. The FIFO scheduling algorithm is unaffected.

Now, since drm_sched_run_job_work() also calls drm_sched_select_entity(), then
in the case of RR scheduling, that would result in drm_sched_select_entity()
having been called twice, which may result in skipping a ready entity if more
than one entity is ready. This commit fixes this by eliminating the call to
drm_sched_select_entity() from drm_sched_run_job_queue(), and leaves it only
in drm_sched_run_job_work().

v2: Rebased on top of Tvrtko's renames series of patches. (Luben)
    Add fixes-tag. (Tvrtko)

Signed-off-by: Luben Tuikov <ltuikov89@gmail.com>
Fixes: f7fe64ad0f22ff ("drm/sched: Split free_job into own work item")
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231107041020.10035-2-ltuikov89@gmail.com
(cherry picked from commit bc8d6a9df99038f61adf2881ad9f717abe414e06)
---
 drivers/gpu/drm/scheduler/sched_main.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 27843e37d9b7..cd0dc3f81d05 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -256,10 +256,10 @@ drm_sched_rq_select_entity_fifo(struct drm_sched_rq *rq)
 }
 
 /**
- * __drm_sched_run_job_queue - enqueue run-job work
+ * drm_sched_run_job_queue - enqueue run-job work
  * @sched: scheduler instance
  */
-static void __drm_sched_run_job_queue(struct drm_gpu_scheduler *sched)
+static void drm_sched_run_job_queue(struct drm_gpu_scheduler *sched)
 {
 	if (!READ_ONCE(sched->pause_submit))
 		queue_work(sched->submit_wq, &sched->work_run_job);
@@ -928,7 +928,7 @@ static bool drm_sched_can_queue(struct drm_gpu_scheduler *sched)
 void drm_sched_wakeup(struct drm_gpu_scheduler *sched)
 {
 	if (drm_sched_can_queue(sched))
-		__drm_sched_run_job_queue(sched);
+		drm_sched_run_job_queue(sched);
 }
 
 /**
@@ -1040,16 +1040,6 @@ drm_sched_pick_best(struct drm_gpu_scheduler **sched_list,
 }
 EXPORT_SYMBOL(drm_sched_pick_best);
 
-/**
- * drm_sched_run_job_queue - enqueue run-job work if there are ready entities
- * @sched: scheduler instance
- */
-static void drm_sched_run_job_queue(struct drm_gpu_scheduler *sched)
-{
-	if (drm_sched_select_entity(sched))
-		__drm_sched_run_job_queue(sched);
-}
-
 /**
  * drm_sched_free_job_work - worker to call free_job
  *
-- 
2.43.0


  parent reply	other threads:[~2023-12-08 20:28 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-12-08 20:27 [PATCH 01/13] drm/sched: Rename drm_sched_get_cleanup_job to be more descriptive Rodrigo Vivi
2023-12-08 20:27 ` [PATCH 02/13] drm/sched: Move free worker re-queuing out of the if block Rodrigo Vivi
2023-12-08 20:27 ` [PATCH 03/13] drm/sched: Rename drm_sched_free_job_queue to be more descriptive Rodrigo Vivi
2023-12-08 20:27 ` [PATCH 04/13] drm/sched: Rename drm_sched_run_job_queue_if_ready and clarify kerneldoc Rodrigo Vivi
2023-12-08 20:27 ` [PATCH 05/13] drm/sched: Drop suffix from drm_sched_wakeup_if_can_queue Rodrigo Vivi
2023-12-08 20:27 ` Rodrigo Vivi [this message]
2023-12-08 20:27 ` [PATCH 07/13] drm/sched: Qualify drm_sched_wakeup() by drm_sched_entity_is_ready() Rodrigo Vivi
2023-12-08 20:27 ` [PATCH 08/13] drm/sched: implement dynamic job-flow control Rodrigo Vivi
2023-12-08 20:27 ` [PATCH 09/13] drm/sched: Fix bounds limiting when given a malformed entity Rodrigo Vivi
2023-12-08 20:27 ` [PATCH 10/13] drm/sched: Rename priority MIN to LOW Rodrigo Vivi
2023-12-08 20:27 ` [PATCH 11/13] drm/sched: Reverse run-queue priority enumeration Rodrigo Vivi
2023-12-08 20:27 ` [PATCH 12/13] drm/sched: Partial revert of "Qualify drm_sched_wakeup() by drm_sched_entity_is_ready()" Rodrigo Vivi
2023-12-08 20:27 ` [PATCH 13/13] fixup! drm/xe: Introduce a new DRM driver for Intel GPUs Rodrigo Vivi
2023-12-08 22:53 ` ✓ CI.Patch_applied: success for series starting with [01/13] drm/sched: Rename drm_sched_get_cleanup_job to be more descriptive Patchwork
2023-12-08 22:53 ` ✗ CI.checkpatch: warning " Patchwork
2023-12-08 22:54 ` ✓ CI.KUnit: success " Patchwork
2023-12-08 23:02 ` ✓ CI.Build: " Patchwork
2023-12-08 23:02 ` ✓ CI.Hooks: " Patchwork
2023-12-08 23:03 ` ✓ CI.checksparse: " Patchwork
2023-12-08 23:42 ` ✗ CI.BAT: failure " Patchwork
  -- strict thread matches above, loose matches on Subject: below --
2023-12-11 19:12 [PATCH 01/13] " Rodrigo Vivi
2023-12-11 19:12 ` [PATCH 06/13] drm/sched: Don't disturb the entity when in RR-mode scheduling Rodrigo Vivi
2023-12-12  0:10 [PATCH 01/13] drm/sched: Rename drm_sched_get_cleanup_job to be more descriptive Rodrigo Vivi
2023-12-12  0:10 ` [PATCH 06/13] drm/sched: Don't disturb the entity when in RR-mode scheduling Rodrigo Vivi

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=20231208202723.918082-6-rodrigo.vivi@intel.com \
    --to=rodrigo.vivi@intel.com \
    --cc=dakr@redhat.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=ltuikov89@gmail.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