From 259254f28bb014221ab298333364002cc8f53bba Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Tue, 12 Apr 2022 01:15:36 +0300
Subject: drm/scheduler: Don't kill jobs in interrupt context
Git-commit: 9b04369b060fd4885f728b7a4ab4851ffb1abb64
Patch-mainline: v5.19-rc8
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
Alt-commit: 7d64c40a7d96190d9d06e240305389e025295916

Interrupt context can't sleep. Drivers like Panfrost and MSM are taking
mutex when job is released, and thus, that code can sleep. This results
into "BUG: scheduling while atomic" if locks are contented while job is
freed. There is no good reason for releasing scheduler's jobs in IRQ
context, hence use normal context to fix the trouble.

Cc: stable@vger.kernel.org
Fixes: 542cff7893a3 ("drm/sched: Avoid lockdep spalt on killing a processes")
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220411221536.283312-1-dmitry.osipenko@collabora.com
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/scheduler/sched_entity.c | 6 +++---
 include/drm/gpu_scheduler.h              | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 191c56064f19..6b25b2f4f5a3 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -190,7 +190,7 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 }
 EXPORT_SYMBOL(drm_sched_entity_flush);
 
-static void drm_sched_entity_kill_jobs_irq_work(struct irq_work *wrk)
+static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk)
 {
 	struct drm_sched_job *job = container_of(wrk, typeof(*job), work);
 
@@ -207,8 +207,8 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
 						 finish_cb);
 
-	init_irq_work(&job->work, drm_sched_entity_kill_jobs_irq_work);
-	irq_work_queue(&job->work);
+	INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work);
+	schedule_work(&job->work);
 }
 
 static struct dma_fence *
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 0fca8f38bee4..addb135eeea6 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -28,7 +28,7 @@
 #include <linux/dma-fence.h>
 #include <linux/completion.h>
 #include <linux/xarray.h>
-#include <linux/irq_work.h>
+#include <linux/workqueue.h>
 
 #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
 
@@ -295,7 +295,7 @@ struct drm_sched_job {
 	 */
 	union {
 		struct dma_fence_cb		finish_cb;
-		struct irq_work 		work;
+		struct work_struct 		work;
 	};
 
 	uint64_t			id;
-- 
2.38.1