drm/amdgpu: Protect the amdgpu_bo_list list with a mutex v2

Protect the struct amdgpu_bo_list with a mutex. This is used during command
submission in order to avoid buffer object corruption as recorded in
the link below.

v2 (chk): Keep the mutex looked for the whole CS to avoid using the
	  list from multiple CS threads at the same time.

Suggested-by: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <Alexander.Deucher@amd.com>
Cc: Andrey Grodzovsky <Andrey.Grodzovsky@amd.com>
Cc: Vitaly Prosyak <Vitaly.Prosyak@amd.com>
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2048
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Luben Tuikov <luben.tuikov@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

Author: Luben Tuikov

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

@@ -40,7 +40,7 @@ static void amdgpu_bo_list_free_rcu(struct rcu_head *rcu)
 {
 	struct amdgpu_bo_list *list = container_of(rcu, struct amdgpu_bo_list,
 						   rhead);
-
+	mutex_destroy(&list->bo_list_mutex);
 	kvfree(list);
 }
 
@@ -136,6 +136,7 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
 
 	trace_amdgpu_cs_bo_status(list->num_entries, total_size);
 
+	mutex_init(&list->bo_list_mutex);
 	*result = list;
 	return 0;
 

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

@@ -47,6 +47,10 @@ struct amdgpu_bo_list {
 	struct amdgpu_bo *oa_obj;
 	unsigned first_userptr;
 	unsigned num_entries;
+
+	/* Protect access during command submission.
+	 */
+	struct mutex bo_list_mutex;
 };
 
 int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,

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

@@ -519,6 +519,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 			return r;
 	}
 
+	mutex_lock(&p->bo_list->bo_list_mutex);
+
 	/* One for TTM and one for the CS job */
 	amdgpu_bo_list_for_each_entry(e, p->bo_list)
 		e->tv.num_shared = 2;
@@ -651,6 +653,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 			kvfree(e->user_pages);
 			e->user_pages = NULL;
 		}
+		mutex_unlock(&p->bo_list->bo_list_mutex);
 	}
 	return r;
 }
@@ -690,9 +693,11 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
 {
 	unsigned i;
 
-	if (error && backoff)
+	if (error && backoff) {
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
+		mutex_unlock(&parser->bo_list->bo_list_mutex);
+	}
 
 	for (i = 0; i < parser->num_post_deps; i++) {
 		drm_syncobj_put(parser->post_deps[i].syncobj);
@@ -832,12 +837,16 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 			continue;
 
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
-		if (r)
+		if (r) {
+			mutex_unlock(&p->bo_list->bo_list_mutex);
 			return r;
+		}
 
 		r = amdgpu_sync_fence(&p->job->sync, bo_va->last_pt_update);
-		if (r)
+		if (r) {
+			mutex_unlock(&p->bo_list->bo_list_mutex);
 			return r;
+		}
 	}
 
 	r = amdgpu_vm_handle_moved(adev, vm);
@@ -1278,6 +1287,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
 	mutex_unlock(&p->adev->notifier_lock);
+	mutex_unlock(&p->bo_list->bo_list_mutex);
 
 	return 0;