vdpa/mlx5: Keep notifiers during suspend but ignore

Unregistering notifiers is a costly operation. Instead of removing
the notifiers during device suspend and adding them back at resume,
simply ignore the call when the device is suspended.

At resume time call queue_link_work() to make sure that the device state
is propagated in case there were changes.

For 1 vDPA device x 32 VQs (16 VQPs) attached to a large VM (256 GB RAM,
32 CPUs x 2 threads per core), the device suspend time is reduced from
~13 ms to ~2.5 ms.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20240816090159.1967650-9-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index fc9fb8d9ac4fa8c8e455682b03b7c77b9045a616..6d1207d7ae75cd8127f338c0340921e82ecb5d58 100644 (file)
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -2850,6 +2850,9 @@ static int event_handler(struct notifier_block *nb, unsigned long event, void *p
        struct mlx5_eqe *eqe = param;
        int ret = NOTIFY_DONE;
 
+       if (ndev->mvdev.suspended)
+               return NOTIFY_DONE;
+
        if (event == MLX5_EVENT_TYPE_PORT_CHANGE) {
                switch (eqe->sub_type) {
                case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
@@ -3595,7 +3598,6 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev)
        mlx5_vdpa_info(mvdev, "suspending device\n");
 
        down_write(&ndev->reslock);
-       unregister_link_notifier(ndev);
        err = suspend_vqs(ndev, 0, ndev->cur_num_vqs);
        mlx5_vdpa_cvq_suspend(mvdev);
        mvdev->suspended = true;
@@ -3617,7 +3619,7 @@ static int mlx5_vdpa_resume(struct vdpa_device *vdev)
        down_write(&ndev->reslock);
        mvdev->suspended = false;
        err = resume_vqs(ndev, 0, ndev->cur_num_vqs);
-       register_link_notifier(ndev);
+       queue_link_work(ndev);
        up_write(&ndev->reslock);
 
        return err;