From 9d32177f4da380e8581a4226736b4cf67ddf0121 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Mon, 12 Dec 2016 17:52:45 +1000 Subject: ttm: wait for bo fence to signal before unmapping vmas TTM was changed a while back to allow for pipelining of buffer moves, and part of this was the removal of waiting for a BO to idle before calling move(), placing the responsibility on the driver to do this if required. That's all well and good, except, we make use of move_notify() to handle mapping/unmapping from the GPU VMM as move() isn't called on all paths. This commit adds a wait before unmapping from a VMM in move_notify(), to prevent GPU page faults where a buffer is still being accessed. Signed-off-by: Ben Skeggs --- drm/nouveau/nouveau_bo.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drm') diff --git a/drm/nouveau/nouveau_bo.c b/drm/nouveau/nouveau_bo.c index e0c000768..dd07ca140 100644 --- a/drm/nouveau/nouveau_bo.c +++ b/drm/nouveau/nouveau_bo.c @@ -1209,6 +1209,7 @@ nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, struct ttm_mem_reg *new_mem) nvbo->page_shift != vma->vm->mmu->lpg_shift)) { nvkm_vm_map(vma, new_mem->mm_node); } else { + WARN_ON(ttm_bo_wait(bo, false, false)); nvkm_vm_unmap(vma); } } -- cgit v1.2.1