From c10983e14e8f5d7c8dab0415e0cb7fe8d10aa9e3 Mon Sep 17 00:00:00 2001
From: Luben Tuikov <luben.tuikov@amd.com>
Date: Wed, 20 Jan 2021 15:09:59 -0500
Subject: drm/scheduler: Job timeout handler returns status (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch does not change current behaviour.

The driver's job timeout handler now returns
status indicating back to the DRM layer whether
the device (GPU) is no longer available, such as
after it's been unplugged, or whether all is
normal, i.e. current behaviour.

All drivers which make use of the
drm_sched_backend_ops' .timedout_job() callback
have been accordingly renamed and return the
would've-been default value of
DRM_GPU_SCHED_STAT_NOMINAL to restart the task's
timeout timer--this is the old behaviour, and is
preserved by this patch.

v2: Use enum as the status of a driver's job
    timeout callback method.

v3: Return scheduler/device information, rather
    than task information.

Cc: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: Andrey Grodzovsky <Andrey.Grodzovsky@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Lucas Stach <l.stach@pengutronix.de>
Cc: Russell King <linux+etnaviv@armlinux.org.uk>
Cc: Christian Gmeiner <christian.gmeiner@gmail.com>
Cc: Qiang Yu <yuq825@gmail.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Cc: Steven Price <steven.price@arm.com>
Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Cc: Eric Anholt <eric@anholt.net>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Steven Price <steven.price@arm.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/415095/
(cherry picked from commit a6a1f036c74e3d2a3a56b3140492c7c3ecb879f3)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 include/drm/gpu_scheduler.h | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

(limited to 'include/drm')

diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 975e8a67947f..ce6a383ed99f 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -206,6 +206,12 @@ static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
 	return s_job && atomic_inc_return(&s_job->karma) > threshold;
 }
 
+enum drm_gpu_sched_stat {
+	DRM_GPU_SCHED_STAT_NONE, /* Reserve 0 */
+	DRM_GPU_SCHED_STAT_NOMINAL,
+	DRM_GPU_SCHED_STAT_ENODEV,
+};
+
 /**
  * struct drm_sched_backend_ops
  *
@@ -230,10 +236,16 @@ struct drm_sched_backend_ops {
 	struct dma_fence *(*run_job)(struct drm_sched_job *sched_job);
 
 	/**
-         * @timedout_job: Called when a job has taken too long to execute,
-         * to trigger GPU recovery.
+	 * @timedout_job: Called when a job has taken too long to execute,
+	 * to trigger GPU recovery.
+	 *
+	 * Return DRM_GPU_SCHED_STAT_NOMINAL, when all is normal,
+	 * and the underlying driver has started or completed recovery.
+	 *
+	 * Return DRM_GPU_SCHED_STAT_ENODEV, if the device is no longer
+	 * available, i.e. has been unplugged.
 	 */
-	void (*timedout_job)(struct drm_sched_job *sched_job);
+	enum drm_gpu_sched_stat (*timedout_job)(struct drm_sched_job *sched_job);
 
 	/**
          * @free_job: Called once the job's finished fence has been signaled
-- 
cgit v1.2.3