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 <dtatu...@nvidia.com>
Reviewed-by: Tariq Toukan <tar...@nvidia.com>
---
drivers/vdpa/mlx5/net/mlx5_vnet.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c
b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 87d355aba380..af96e49697d0 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -2934,6 +2934,9 @@ 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:
@@ -3679,7 +3682,6 @@ 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;
@@ -3701,7 +3703,7 @@ 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;
--
2.45.2
