drm/ttm: Schedule delayed_delete worker closer

Try to allocate system memory on the NUMA node the device is closest to
and try to run delayed_delete workers on a CPU of this node as well.

To optimize the memory clearing operation when a TTM BO gets freed by
the delayed_delete worker, scheduling it closer to a NUMA node where the
memory was initially allocated helps avoid the cases where the worker
gets randomly scheduled on the CPU cores that are across interconnect
boundaries such as xGMI, PCIe etc.

This change helps USWC GTT allocations on NUMA systems (dGPU) and AMD
APU platforms such as GFXIP9.4.3.

Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231111130856.1168304-1-rajneesh.bhardwaj@amd.com
Signed-off-by: Christian König <christian.koenig@amd.com>

drivers/gpu/drm/ttm/ttm_bo.c

@@ -370,7 +370,13 @@ static void ttm_bo_release(struct kref *kref)
 			spin_unlock(&bo->bdev->lru_lock);
 
 			INIT_WORK(&bo->delayed_delete, ttm_bo_delayed_delete);
-			queue_work(bdev->wq, &bo->delayed_delete);
+
+			/* Schedule the worker on the closest NUMA node. This
+			 * improves performance since system memory might be
+			 * cleared on free and that is best done on a CPU core
+			 * close to it.
+			 */
+			queue_work_node(bdev->pool.nid, bdev->wq, &bo->delayed_delete);
 			return;
 		}
 

drivers/gpu/drm/ttm/ttm_device.c

@@ -204,7 +204,8 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 	if (ret)
 		return ret;
 
-	bdev->wq = alloc_workqueue("ttm", WQ_MEM_RECLAIM | WQ_HIGHPRI, 16);
+	bdev->wq = alloc_workqueue("ttm",
+				   WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 16);
 	if (!bdev->wq) {
 		ttm_global_release();
 		return -ENOMEM;
@@ -213,7 +214,8 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
 	bdev->funcs = funcs;
 
 	ttm_sys_man_init(bdev);
-	ttm_pool_init(&bdev->pool, dev, NUMA_NO_NODE, use_dma_alloc, use_dma32);
+
+	ttm_pool_init(&bdev->pool, dev, dev_to_node(dev), use_dma_alloc, use_dma32);
 
 	bdev->vma_manager = vma_manager;
 	spin_lock_init(&bdev->lru_lock);