drm/amdgpu: use scheduler load balancing for compute CS

Start to use the scheduler load balancing for userspace compute
command submissions.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -49,7 +49,8 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 			   struct amdgpu_ctx *ctx)
 {
 	struct drm_sched_rq *sdma_rqs[AMDGPU_MAX_RINGS];
-	unsigned i, j, num_sdma_rqs;
+	struct drm_sched_rq *comp_rqs[AMDGPU_MAX_RINGS];
+	unsigned i, j, num_sdma_rqs, num_comp_rqs;
 	int r;
 
 	if (priority < 0 || priority >= DRM_SCHED_PRIORITY_MAX)
@@ -82,6 +83,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 	ctx->override_priority = DRM_SCHED_PRIORITY_UNSET;
 
 	num_sdma_rqs = 0;
+	num_comp_rqs = 0;
 	for (i = 0; i < adev->num_rings; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 		struct drm_sched_rq *rq;
@@ -89,6 +91,8 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 		rq = &ring->sched.sched_rq[priority];
 		if (ring->funcs->type == AMDGPU_RING_TYPE_SDMA)
 			sdma_rqs[num_sdma_rqs++] = rq;
+		else if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE)
+			comp_rqs[num_comp_rqs++] = rq;
 	}
 
 	/* create context entity for each ring */
@@ -102,6 +106,10 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 			r = drm_sched_entity_init(&ctx->rings[i].entity,
 						  sdma_rqs, num_sdma_rqs,
 						  &ctx->guilty);
+		} else if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) {
+			r = drm_sched_entity_init(&ctx->rings[i].entity,
+						  comp_rqs, num_comp_rqs,
+						  &ctx->guilty);
 		} else {
 			struct drm_sched_rq *rq;