diff options
| author | Grazvydas Ignotas <notasas@gmail.com> | 2016-10-23 21:31:44 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2016-10-25 00:00:38 +0300 |
| commit | a053fb7e512c77f0742bceb578b10025256e1911 (patch) | |
| tree | f93b3190e71ef43e1830f41a3feb932daaa89e5d /drivers/gpu/drm/amd/scheduler | |
| parent | 9dc79965b21967caebde575f5f5d8bf1aa2c23ab (diff) | |
| download | linux-a053fb7e512c77f0742bceb578b10025256e1911.tar.xz | |
drm/amdgpu: fix sched fence slab teardown
To free fences, call_rcu() is used, which calls amd_sched_fence_free()
after a grace period. During teardown, there is no guarantee all
callbacks have finished, so sched_fence_slab may be destroyed before
all fences have been freed. If we are lucky, this results in some slab
warnings, if not, we get a crash in one of rcu threads because callback
is called after amdgpu has already been unloaded.
Fix it with a rcu_barrier().
Fixes: 189e0fb76304 ("drm/amdgpu: RCU protected amd_sched_fence_release")
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Grazvydas Ignotas <notasas@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/scheduler')
| -rw-r--r-- | drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 963a24d46a93..910b8d5b21c5 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -645,6 +645,7 @@ void amd_sched_fini(struct amd_gpu_scheduler *sched) { if (sched->thread) kthread_stop(sched->thread); + rcu_barrier(); if (atomic_dec_and_test(&sched_fence_slab_ref)) kmem_cache_destroy(sched_fence_slab); } |