1 files changed, 35 insertions, 15 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 663043c8f0f5..52a5e4fdc95b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -50,7 +50,8 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
 	bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
 	p->uf_entry.priority = 0;
 	p->uf_entry.tv.bo = &bo->tbo;
-	p->uf_entry.tv.shared = true;
+	/* One for TTM and one for the CS job */
+	p->uf_entry.tv.num_shared = 2;
 	p->uf_entry.user_pages = NULL;
 
 	drm_gem_object_put_unlocked(gobj);
@@ -124,14 +125,14 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
 		goto free_chunk;
 	}
 
+	mutex_lock(&p->ctx->lock);
+
 	/* skip guilty context job */
 	if (atomic_read(&p->ctx->guilty) == 1) {
 		ret = -ECANCELED;
 		goto free_chunk;
 	}
 
-	mutex_lock(&p->ctx->lock);
-
 	/* get chunks */
 	chunk_array_user = u64_to_user_ptr(cs->in.chunks);
 	if (copy_from_user(chunk_array, chunk_array_user,
@@ -213,6 +214,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
 		case AMDGPU_CHUNK_ID_DEPENDENCIES:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
+		case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES:
 			break;
 
 		default:
@@ -598,6 +600,10 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 			return r;
 	}
 
+	/* One for TTM and one for the CS job */
+	amdgpu_bo_list_for_each_entry(e, p->bo_list)
+		e->tv.num_shared = 2;
+
 	amdgpu_bo_list_get_list(p->bo_list, &p->validated);
 	if (p->bo_list->first_userptr != p->bo_list->num_entries)
 		p->mn = amdgpu_mn_get(p->adev, AMDGPU_MN_TYPE_GFX);
@@ -717,8 +723,14 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	gws = p->bo_list->gws_obj;
 	oa = p->bo_list->oa_obj;
 
-	amdgpu_bo_list_for_each_entry(e, p->bo_list)
-		e->bo_va = amdgpu_vm_bo_find(vm, ttm_to_amdgpu_bo(e->tv.bo));
+	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
+		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
+
+		/* Make sure we use the exclusive slot for shared BOs */
+		if (bo->prime_shared_count)
+			e->tv.num_shared = 0;
+		e->bo_va = amdgpu_vm_bo_find(vm, bo);
+	}
 
 	if (gds) {
 		p->job->gds_base = amdgpu_bo_gpu_offset(gds) >> PAGE_SHIFT;
@@ -955,10 +967,6 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = reservation_object_reserve_shared(vm->root.base.bo->tbo.resv);
-	if (r)
-		return r;
-
 	p->job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.base.bo);
 
 	if (amdgpu_vm_debug) {
@@ -1083,6 +1091,15 @@ static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
 
 		fence = amdgpu_ctx_get_fence(ctx, entity,
 					     deps[i].handle);
+
+		if (chunk->chunk_id == AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES) {
+			struct drm_sched_fence *s_fence = to_drm_sched_fence(fence);
+			struct dma_fence *old = fence;
+
+			fence = dma_fence_get(&s_fence->scheduled);
+			dma_fence_put(old);
+		}
+
 		if (IS_ERR(fence)) {
 			r = PTR_ERR(fence);
 			amdgpu_ctx_put(ctx);
@@ -1104,7 +1121,7 @@ static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
 {
 	int r;
 	struct dma_fence *fence;
-	r = drm_syncobj_find_fence(p->filp, handle, 0, &fence);
+	r = drm_syncobj_find_fence(p->filp, handle, 0, 0, &fence);
 	if (r)
 		return r;
 
@@ -1170,7 +1187,8 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 
 		chunk = &p->chunks[i];
 
-		if (chunk->chunk_id == AMDGPU_CHUNK_ID_DEPENDENCIES) {
+		if (chunk->chunk_id == AMDGPU_CHUNK_ID_DEPENDENCIES ||
+		    chunk->chunk_id == AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES) {
 			r = amdgpu_cs_process_fence_dep(p, chunk);
 			if (r)
 				return r;
@@ -1193,7 +1211,7 @@ static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
 	int i;
 
 	for (i = 0; i < p->num_post_dep_syncobjs; ++i)
-		drm_syncobj_replace_fence(p->post_dep_syncobjs[i], 0, p->fence);
+		drm_syncobj_replace_fence(p->post_dep_syncobjs[i], p->fence);
 }
 
 static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
@@ -1260,8 +1278,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	return 0;
 
 error_abort:
-	dma_fence_put(&job->base.s_fence->finished);
-	job->base.s_fence = NULL;
+	drm_sched_job_cleanup(&job->base);
 	amdgpu_mn_unlock(p->mn);
 
 error_unlock:
@@ -1285,7 +1302,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	r = amdgpu_cs_parser_init(&parser, data);
 	if (r) {
-		DRM_ERROR("Failed to initialize parser !\n");
+		DRM_ERROR("Failed to initialize parser %d!\n", r);
 		goto out;
 	}
 
@@ -1422,6 +1439,9 @@ int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data,
 	if (IS_ERR(fence))
 		return PTR_ERR(fence);
 
+	if (!fence)
+		fence = dma_fence_get_stub();
+
 	switch (info->in.what) {
 	case AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ:
 		r = drm_syncobj_create(&syncobj, 0, fence);