From 38fc4856ad98f230bc91da0421dec69e4aee40f8 Mon Sep 17 00:00:00 2001 From: Samuel Pitoiset Date: Thu, 9 Feb 2017 11:33:36 +0100 Subject: [PATCH] drm/amdgpu: fix a potential deadlock in amdgpu_bo_create_restricted() MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit When ttm_bo_init() fails, the reservation mutex should be unlocked. In debug build, the kernel reported "possible recursive locking detected" in this codepath. For debugging purposes, I also added a "WARN_ON(ww_mutex_is_locked())" when ttm_bo_init() fails and the mutex was locked as expected. This should fix (random) GPU hangs. The easy way to reproduce the issue is to change the "Super Sampling" option from 1.0 to 2.0 in Hitman. It will create a huge buffer, evict a bunch of buffers (around ~5k) and deadlock. This regression has been introduced pretty recently. v2: only release the mutex if resv is NULL Fixes: 12a852219583 ("drm/amdgpu: improve AMDGPU_GEM_CREATE_VRAM_CLEARED handling (v2)") Reviewed-by: Christian König Signed-off-by: Samuel Pitoiset Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index da3a53a..993c003 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -405,8 +405,11 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev, &bo->placement, page_align, !kernel, NULL, acc_size, sg, resv ? resv : &bo->tbo.ttm_resv, &amdgpu_ttm_bo_destroy); - if (unlikely(r != 0)) + if (unlikely(r != 0)) { + if (!resv) + ww_mutex_unlock(&bo->tbo.resv->lock); return r; + } bo->tbo.priority = ilog2(bo->tbo.num_pages); if (kernel) -- 2.7.4