diff options
| author | Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> | 2023-11-11 08:08:56 -0500 |
|---|---|---|
| committer | Christian König <christian.koenig@amd.com> | 2023-11-27 10:58:36 +0100 |
| commit | b0a7ce53d494c94dfacb5a877fc0668f2a688652 (patch) | |
| tree | 78c44755b876d2a89ce539cdaa14701973070d87 | |
| parent | 38f922a563aac3148ac73e73689805917f034cb5 (diff) | |
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>
| -rw-r--r-- | drivers/gpu/drm/ttm/ttm_bo.c | 8 | ||||
| -rw-r--r-- | drivers/gpu/drm/ttm/ttm_device.c | 6 |
2 files changed, 11 insertions, 3 deletions
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index e58b7e249816..edf10618fe2b 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/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; } diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index d48b39132b32..f5187b384ae9 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/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); |