drm/amdgpu: cache the fence to wait for a VMID

Beneficial when a lot of processes are waiting for VMIDs.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 13044e6..e223b0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -360,6 +360,9 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
 
 	amdgpu_debugfs_ring_fini(ring);
 
+	dma_fence_put(ring->vmid_wait);
+	ring->vmid_wait = NULL;
+
 	ring->adev->rings[ring->idx] = NULL;
 }