Merge branch 'drm-next-4.21' of git://people.freedesktop.org/~agd5f/linux into drm-next

New features for 4.21:
amdgpu:
- Support for SDMA paging queue on vega
- Put compute EOP buffers into vram for better performance
- Share more code with amdkfd
- Support for scanout with DCC on gfx9
- Initial kerneldoc for DC
- Updated SMU firmware support for gfx8 chips
- Rework CSA handling for eventual support for preemption
- XGMI PSP support
- Clean up RLC handling
- Enable GPU reset by default on VI, SOC15 dGPUs
- Ring and IB test cleanups

amdkfd:
- Share more code with amdgpu

ttm:
- Move global init out of the drivers

scheduler:
- Track if schedulers are ready for work
- Timeout/fault handling changes to facilitate GPU recovery

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181114165113.3751-1-alexander.deucher@amd.com

1 files changed, 32 insertions, 1 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 44fe587aaef9..18ebbb05762e 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -196,6 +196,19 @@ static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched)
 		schedule_delayed_work(&sched->work_tdr, sched->timeout);
 }
 
+/**
+ * drm_sched_fault - immediately start timeout handler
+ *
+ * @sched: scheduler where the timeout handling should be started.
+ *
+ * Start timeout handling immediately when the driver detects a hardware fault.
+ */
+void drm_sched_fault(struct drm_gpu_scheduler *sched)
+{
+	mod_delayed_work(system_wq, &sched->work_tdr, 0);
+}
+EXPORT_SYMBOL(drm_sched_fault);
+
 /* job_finish is called after hw fence signaled
  */
 static void drm_sched_job_finish(struct work_struct *work)
@@ -220,7 +233,6 @@ static void drm_sched_job_finish(struct work_struct *work)
 	drm_sched_start_timeout(sched);
 	spin_unlock(&sched->job_list_lock);
 
-	dma_fence_put(&s_job->s_fence->finished);
 	sched->ops->free_job(s_job);
 }
 
@@ -283,6 +295,7 @@ static void drm_sched_job_timedout(struct work_struct *work)
 already_signaled:
 		;
 	}
+	drm_sched_start_timeout(sched);
 	spin_unlock(&sched->job_list_lock);
 }
 
@@ -406,6 +419,9 @@ int drm_sched_job_init(struct drm_sched_job *job,
 	struct drm_gpu_scheduler *sched;
 
 	drm_sched_entity_select_rq(entity);
+	if (!entity->rq)
+		return -ENOENT;
+
 	sched = entity->rq->sched;
 
 	job->sched = sched;
@@ -424,6 +440,18 @@ int drm_sched_job_init(struct drm_sched_job *job,
 EXPORT_SYMBOL(drm_sched_job_init);
 
 /**
+ * drm_sched_job_cleanup - clean up scheduler job resources
+ *
+ * @job: scheduler job to clean up
+ */
+void drm_sched_job_cleanup(struct drm_sched_job *job)
+{
+	dma_fence_put(&job->s_fence->finished);
+	job->s_fence = NULL;
+}
+EXPORT_SYMBOL(drm_sched_job_cleanup);
+
+/**
  * drm_sched_ready - is the scheduler ready
  *
  * @sched: scheduler instance
@@ -619,6 +647,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		return PTR_ERR(sched->thread);
 	}
 
+	sched->ready = true;
 	return 0;
 }
 EXPORT_SYMBOL(drm_sched_init);
@@ -634,5 +663,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 {
 	if (sched->thread)
 		kthread_stop(sched->thread);
+
+	sched->ready = false;
 }
 EXPORT_SYMBOL(drm_sched_fini);