The async page flip completion drops the old FB reference before
decrementing its BO usecnt. If that was the last reference, the BO is
already freed or recycled into the BO cache when vc4_bo_dec_usecnt()
runs, leading to a use-after-free or a refcount underflow. For example,
while running glmark2-es2-drm in the Raspberry Pi 3, the following
warning appears:

[  459.078834] ------------[ cut here ]------------
[  459.078855] refcount_t: underflow; use-after-free.
[  459.078952] WARNING: lib/refcount.c:96 at refcount_dec_not_one+0xa0/0xa8, 
CPU#0: swapper/0/0
<snip>
[  459.079316] Call trace:
[  459.079323]  refcount_dec_not_one+0xa0/0xa8 (P)
[  459.079335]  vc4_bo_dec_usecnt+0x30/0x118 [vc4]
[  459.079371]  vc4_async_page_flip_complete_with_cleanup+0xa0/0xc4 [vc4]
[  459.079395]  dma_fence_signal_timestamp_locked+0xb0/0x12c
[  459.079408]  dma_fence_signal+0x3c/0x6c
[  459.079416]  vc4_irq_render_job_done+0x24/0xbc [vc4]
[  459.079440]  vc4_irq+0x120/0x138 [vc4]

This could happen when userspace removes the old FB and closes its GEM
handle while the flip is still pending.

Decrement the BO usecnt before releasing the old FB reference. Do this
by unifying the two fence callbacks and only decrementing the BO usecnt
in VC4_GEN_4.

Cc: [email protected]
Fixes: 4d12c36fb73b ("drm/vc4: crtc: Move the BO handling out of common 
page-flip callback")
Signed-off-by: Maíra Canal <[email protected]>
---
 drivers/gpu/drm/vc4/vc4_crtc.c | 62 +++++++++++++++---------------------------
 1 file changed, 22 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index f42cd5353230..c558b527c7e6 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -895,6 +895,7 @@ vc4_async_page_flip_complete(struct vc4_async_flip_state 
*flip_state)
 {
        struct drm_crtc *crtc = flip_state->crtc;
        struct drm_device *dev = crtc->dev;
+       struct vc4_dev *vc4 = to_vc4_dev(dev);
        struct drm_plane *plane = crtc->primary;
 
        vc4_plane_async_set_fb(plane, flip_state->fb);
@@ -909,39 +910,27 @@ vc4_async_page_flip_complete(struct vc4_async_flip_state 
*flip_state)
        drm_crtc_vblank_put(crtc);
        drm_framebuffer_put(flip_state->fb);
 
-       if (flip_state->old_fb)
-               drm_framebuffer_put(flip_state->old_fb);
-
-       kfree(flip_state);
-}
-
-static void vc4_async_page_flip_complete_with_cleanup(struct dma_fence *fence,
-                                                     struct dma_fence_cb *cb)
-{
-       struct vc4_async_flip_state *flip_state =
-               container_of(cb, struct vc4_async_flip_state, cb);
-       struct vc4_bo *bo = NULL;
-
        if (flip_state->old_fb) {
-               struct drm_gem_dma_object *dma_bo =
-                       drm_fb_dma_get_gem_obj(flip_state->old_fb, 0);
-               bo = to_vc4_bo(&dma_bo->base);
+               /*
+                * Decrement the BO usecnt in order to keep the inc/dec
+                * calls balanced when the planes are updated through
+                * the async update path.
+                *
+                * FIXME: we should move to generic async-page-flip when
+                * it's available, so that we can get rid of this
+                * hand-made cleanup_fb() logic.
+                */
+               if (vc4->gen == VC4_GEN_4) {
+                       struct drm_gem_dma_object *dma_bo =
+                               drm_fb_dma_get_gem_obj(flip_state->old_fb, 0);
+
+                       vc4_bo_dec_usecnt(to_vc4_bo(&dma_bo->base));
+               }
+
+               drm_framebuffer_put(flip_state->old_fb);
        }
 
-       vc4_async_page_flip_complete(flip_state);
-       dma_fence_put(fence);
-
-       /*
-        * Decrement the BO usecnt in order to keep the inc/dec
-        * calls balanced when the planes are updated through
-        * the async update path.
-        *
-        * FIXME: we should move to generic async-page-flip when
-        * it's available, so that we can get rid of this
-        * hand-made cleanup_fb() logic.
-        */
-       if (bo)
-               vc4_bo_dec_usecnt(bo);
+       kfree(flip_state);
 }
 
 static void vc4_async_page_flip_fence_complete(struct dma_fence *fence,
@@ -959,30 +948,23 @@ static int vc4_async_set_fence_cb(struct drm_device *dev,
 {
        struct drm_framebuffer *fb = flip_state->fb;
        struct drm_gem_dma_object *dma_bo = drm_fb_dma_get_gem_obj(fb, 0);
-       dma_fence_func_t async_page_flip_complete_function;
-       struct vc4_dev *vc4 = to_vc4_dev(dev);
        struct dma_fence *fence;
        int ret;
 
-       if (vc4->gen == VC4_GEN_4)
-               async_page_flip_complete_function = 
vc4_async_page_flip_complete_with_cleanup;
-       else
-               async_page_flip_complete_function = 
vc4_async_page_flip_fence_complete;
-
        ret = dma_resv_get_singleton(dma_bo->base.resv, DMA_RESV_USAGE_READ, 
&fence);
        if (ret)
                return ret;
 
        /* If there's no fence, complete the page flip immediately */
        if (!fence) {
-               async_page_flip_complete_function(fence, &flip_state->cb);
+               vc4_async_page_flip_fence_complete(fence, &flip_state->cb);
                return 0;
        }
 
        /* If the fence has already been completed, complete the page flip */
        if (dma_fence_add_callback(fence, &flip_state->cb,
-                                  async_page_flip_complete_function))
-               async_page_flip_complete_function(fence, &flip_state->cb);
+                                  vc4_async_page_flip_fence_complete))
+               vc4_async_page_flip_fence_complete(fence, &flip_state->cb);
 
        return 0;
 }

-- 
2.56.0

Reply via email to