[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20171201002311.28098-2-lyude@redhat.com>
Date: Thu, 30 Nov 2017 19:23:03 -0500
From: Lyude Paul <lyude@...hat.com>
To: stable@...r.kernel.org
Cc: Christian König <christian.koenig@....com>,
David Airlie <airlied@...ux.ie>,
Alex Deucher <alexander.deucher@....com>,
Sinclair Yeh <syeh@...are.com>,
Nicolai Hähnle <nicolai.haehnle@....com>,
Chunming Zhou <david1.zhou@....com>,
Michel Dänzer <michel.daenzer@....com>,
Peter Zijlstra <peterz@...radead.org>,
dri-devel@...ts.freedesktop.org, linux-kernel@...r.kernel.org
Subject: [PATCH 1/4] drm/ttm: fix ttm_bo_cleanup_refs_or_queue once more
From: Christian König <christian.koenig@....com>
With shared reservation objects __ttm_bo_reserve() can easily fail even on
destroyed BOs. This prevents correct handling when we need to individualize
the reservation object.
Fix this by individualizing the object before even trying to reserve it.
commit 378e2d5b504fe0231c557751e58b80fcf717cc20 upstream
Signed-off-by: Christian König <christian.koenig@....com>
Acked-by: Chunming Zhou <david1.zhou@....com>
Signed-off-by: Alex Deucher <alexander.deucher@....com>
Signed-off-by: Lyude Paul <lyude@...hat.com>
---
drivers/gpu/drm/ttm/ttm_bo.c | 32 +++++++++++++++++---------------
1 file changed, 17 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 180ce6296416..bee77d31895b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -440,28 +440,29 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
struct ttm_bo_global *glob = bo->glob;
int ret;
+ ret = ttm_bo_individualize_resv(bo);
+ if (ret) {
+ /* Last resort, if we fail to allocate memory for the
+ * fences block for the BO to become idle
+ */
+ reservation_object_wait_timeout_rcu(bo->resv, true, false,
+ 30 * HZ);
+ spin_lock(&glob->lru_lock);
+ goto error;
+ }
+
spin_lock(&glob->lru_lock);
ret = __ttm_bo_reserve(bo, false, true, NULL);
-
if (!ret) {
- if (!ttm_bo_wait(bo, false, true)) {
+ if (reservation_object_test_signaled_rcu(&bo->ttm_resv, true)) {
ttm_bo_del_from_lru(bo);
spin_unlock(&glob->lru_lock);
+ if (bo->resv != &bo->ttm_resv)
+ reservation_object_unlock(&bo->ttm_resv);
ttm_bo_cleanup_memtype_use(bo);
-
return;
}
- ret = ttm_bo_individualize_resv(bo);
- if (ret) {
- /* Last resort, if we fail to allocate memory for the
- * fences block for the BO to become idle and free it.
- */
- spin_unlock(&glob->lru_lock);
- ttm_bo_wait(bo, true, true);
- ttm_bo_cleanup_memtype_use(bo);
- return;
- }
ttm_bo_flush_all_fences(bo);
/*
@@ -474,11 +475,12 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
ttm_bo_add_to_lru(bo);
}
- if (bo->resv != &bo->ttm_resv)
- reservation_object_unlock(&bo->ttm_resv);
__ttm_bo_unreserve(bo);
}
+ if (bo->resv != &bo->ttm_resv)
+ reservation_object_unlock(&bo->ttm_resv);
+error:
kref_get(&bo->list_kref);
list_add_tail(&bo->ddestroy, &bdev->ddestroy);
spin_unlock(&glob->lru_lock);
--
2.14.3
Powered by blists - more mailing lists