drm/amdgpu: Move scheduler init to after XGMI is ready

Before we initialize schedulers we must know which reset
domain are we in - for single device there iis a single
domain per device and so single wq per device. For XGMI
the reset domain spans the entire XGMI hive and so the
reset wq is per hive.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://www.spinics.net/lists/amd-gfx/msg74112.html

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -2287,6 +2287,47 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
 	return r;
 }
 
+static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
+{
+	long timeout;
+	int r, i;
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		/* No need to setup the GPU scheduler for rings that don't need it */
+		if (!ring || ring->no_scheduler)
+			continue;
+
+		switch (ring->funcs->type) {
+		case AMDGPU_RING_TYPE_GFX:
+			timeout = adev->gfx_timeout;
+			break;
+		case AMDGPU_RING_TYPE_COMPUTE:
+			timeout = adev->compute_timeout;
+			break;
+		case AMDGPU_RING_TYPE_SDMA:
+			timeout = adev->sdma_timeout;
+			break;
+		default:
+			timeout = adev->video_timeout;
+			break;
+		}
+
+		r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
+				   ring->num_hw_submission, amdgpu_job_hang_limit,
+				   timeout, adev->reset_domain.wq, ring->sched_score, ring->name);
+		if (r) {
+			DRM_ERROR("Failed to create scheduler on ring %s.\n",
+				  ring->name);
+			return r;
+		}
+	}
+
+	return 0;
+}
+
+
 /**
  * amdgpu_device_ip_init - run init for hardware IPs
  *
@@ -2419,6 +2460,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 		}
 	}
 
+	r = amdgpu_device_init_schedulers(adev);
+	if (r)
+		goto init_failed;
+
 	/* Don't init kfd if whole hive need to be reset during init */
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);

drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c

@@ -446,24 +446,18 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
  * for the requested ring.
  *
  * @ring: ring to init the fence driver on
- * @num_hw_submission: number of entries on the hardware queue
- * @sched_score: optional score atomic shared with other schedulers
  *
  * Init the fence driver for the requested ring (all asics).
  * Helper function for amdgpu_fence_driver_init().
  */
-int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
-				  unsigned num_hw_submission,
-				  atomic_t *sched_score)
+int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	long timeout;
-	int r;
 
 	if (!adev)
 		return -EINVAL;
 
-	if (!is_power_of_2(num_hw_submission))
+	if (!is_power_of_2(ring->num_hw_submission))
 		return -EINVAL;
 
 	ring->fence_drv.cpu_addr = NULL;
@@ -474,41 +468,14 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 
 	timer_setup(&ring->fence_drv.fallback_timer, amdgpu_fence_fallback, 0);
 
-	ring->fence_drv.num_fences_mask = num_hw_submission * 2 - 1;
+	ring->fence_drv.num_fences_mask = ring->num_hw_submission * 2 - 1;
 	spin_lock_init(&ring->fence_drv.lock);
-	ring->fence_drv.fences = kcalloc(num_hw_submission * 2, sizeof(void *),
+	ring->fence_drv.fences = kcalloc(ring->num_hw_submission * 2, sizeof(void *),
 					 GFP_KERNEL);
+
 	if (!ring->fence_drv.fences)
 		return -ENOMEM;
 
-	/* No need to setup the GPU scheduler for rings that don't need it */
-	if (ring->no_scheduler)
-		return 0;
-
-	switch (ring->funcs->type) {
-	case AMDGPU_RING_TYPE_GFX:
-		timeout = adev->gfx_timeout;
-		break;
-	case AMDGPU_RING_TYPE_COMPUTE:
-		timeout = adev->compute_timeout;
-		break;
-	case AMDGPU_RING_TYPE_SDMA:
-		timeout = adev->sdma_timeout;
-		break;
-	default:
-		timeout = adev->video_timeout;
-		break;
-	}
-
-	r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
-			   num_hw_submission, amdgpu_job_hang_limit,
-			   timeout, NULL, sched_score, ring->name);
-	if (r) {
-		DRM_ERROR("Failed to create scheduler on ring %s.\n",
-			  ring->name);
-		return r;
-	}
-
 	return 0;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c

@@ -191,8 +191,9 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		ring->adev = adev;
 		ring->idx = adev->num_rings++;
 		adev->rings[ring->idx] = ring;
-		r = amdgpu_fence_driver_init_ring(ring, sched_hw_submission,
-						  sched_score);
+		ring->num_hw_submission = sched_hw_submission;
+		ring->sched_score = sched_score;
+		r = amdgpu_fence_driver_init_ring(ring);
 		if (r)
 			return r;
 	}

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h

@@ -114,9 +114,7 @@ struct amdgpu_fence_driver {
 void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring);
 void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
 
-int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
-				  unsigned num_hw_submission,
-				  atomic_t *sched_score);
+int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring);
 int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 				   struct amdgpu_irq_src *irq_src,
 				   unsigned irq_type);
@@ -251,6 +249,8 @@ struct amdgpu_ring {
 	bool			has_compute_vm_bug;
 	bool			no_scheduler;
 	int			hw_prio;
+	unsigned 		num_hw_submission;
+	atomic_t		*sched_score;
 };
 
 #define amdgpu_ring_parse_cs(r, p, ib) ((r)->funcs->parse_cs((p), (ib)))