drm/amdgpu: disable bulk moves for now
authorChristian König <ckoenig.leichtzumerken@gmail.com>
Wed, 20 Feb 2019 14:16:06 +0000 (15:16 +0100)
committerAlex Deucher <alexander.deucher@amd.com>
Wed, 20 Feb 2019 22:13:27 +0000 (17:13 -0500)
The changes to fix those are two invasive for backporting.

Just disable the feature in 4.20 and 5.0.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Cc: <stable@vger.kernel.org> [4.20+]
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

index 7c108e687683489fa5d247a1d42177bb225bdb99..698bcb8ce61d54ea0064227674405a099fc39582 100644 (file)
@@ -638,12 +638,14 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
        struct ttm_bo_global *glob = adev->mman.bdev.glob;
        struct amdgpu_vm_bo_base *bo_base;
 
+#if 0
        if (vm->bulk_moveable) {
                spin_lock(&glob->lru_lock);
                ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move);
                spin_unlock(&glob->lru_lock);
                return;
        }
+#endif
 
        memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move));