From bad2770e6c88f8020c769267145447faa28f26f7 Mon Sep 17 00:00:00 2001
From: Monk Liu <Monk.Liu@amd.com>
Date: Wed, 1 Sep 2021 08:46:46 +0800
Subject: drm/sched: fix the bug of time out calculation(v4)
Git-commit: bcf26654a38f8e55ecac4635dac2e72c161d0063
Patch-mainline: v5.16-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

issue:
in cleanup_job the cancle_delayed_work will cancel a TO timer
even the its corresponding job is still running.

fix:
do not cancel the timer in cleanup_job, instead do the cancelling
only when the heading job is signaled, and if there is a "next" job
we start_timeout again.

v2:
further cleanup the logic, and do the TDR timer cancelling if the signaled job
is the last one in its scheduler.

v3:
change the issue description
remove the cancel_delayed_work in the begining of the cleanup_job
recover the implement of drm_sched_job_begin.

v4:
remove the kthread_should_park() checking in cleanup_job routine,
we should cleanup the signaled job asap

TODO:
1)introduce pause/resume scheduler in job_timeout to serial the handling
of scheduler and job_timeout.
2)drop the bad job's del and insert in scheduler due to above serialization
(no race issue anymore with the serialization)

Tested-by: jingwen <jingwen.chen@@amd.com>
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1630457207-13107-1-git-send-email-Monk.Liu@amd.com
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/scheduler/sched_main.c | 26 +++++++++-----------------
 1 file changed, 9 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 6987d412a946..042c16b5d54a 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -827,15 +827,6 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 {
 	struct drm_sched_job *job, *next;
 
-	/*
-	 * Don't destroy jobs while the timeout worker is running  OR thread
-	 * is being parked and hence assumed to not touch pending_list
-	 */
-	if ((sched->timeout != MAX_SCHEDULE_TIMEOUT &&
-	    !cancel_delayed_work(&sched->work_tdr)) ||
-	    kthread_should_park())
-		return NULL;
-
 	spin_lock(&sched->job_list_lock);
 
 	job = list_first_entry_or_null(&sched->pending_list,
@@ -844,17 +835,21 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
 		/* remove job from pending_list */
 		list_del_init(&job->list);
+
+		/* cancel this job's TO timer */
+		cancel_delayed_work(&sched->work_tdr);
 		/* make the scheduled timestamp more accurate */
 		next = list_first_entry_or_null(&sched->pending_list,
 						typeof(*next), list);
-		if (next)
+
+		if (next) {
 			next->s_fence->scheduled.timestamp =
 				job->s_fence->finished.timestamp;
-
+			/* start TO timer for next job */
+			drm_sched_start_timeout(sched);
+		}
 	} else {
 		job = NULL;
-		/* queue timeout for next job */
-		drm_sched_start_timeout(sched);
 	}
 
 	spin_unlock(&sched->job_list_lock);
@@ -942,11 +937,8 @@ static int drm_sched_main(void *param)
 					  (entity = drm_sched_select_entity(sched))) ||
 					 kthread_should_stop());
 
-		if (cleanup_job) {
+		if (cleanup_job)
 			sched->ops->free_job(cleanup_job);
-			/* queue timeout for next job */
-			drm_sched_start_timeout(sched);
-		}
 
 		if (!entity)
 			continue;
-- 
2.38.1