net/mlx5: Disable reload while removing the device

While unregistration is in progress, user might be reloading the
interface.
This can race with unregistration in below flow which uses the
resources which are getting disabled by reload flow.

Hence, disable the devlink reloading first when removing the device.

     CPU0                                   CPU1
     ----                                   ----
local_pci_remove()                  devlink_mutex
  remove_one()                       devlink_nl_cmd_reload()
    mlx5_unregister_device()           devlink_reload()
                                       ops->reload_down()
                                         mlx5_unload_one()

Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index e94f0c4..a99fe4b 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -283,7 +283,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
                goto params_reg_err;
        mlx5_devlink_set_params_init_values(devlink);
        devlink_params_publish(devlink);
-       devlink_reload_enable(devlink);
        return 0;
 
 params_reg_err:
@@ -293,7 +292,6 @@ params_reg_err:
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
-       devlink_reload_disable(devlink);
        devlink_params_unregister(devlink, mlx5_devlink_params,
                                  ARRAY_SIZE(mlx5_devlink_params));
        devlink_unregister(devlink);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 18d6c37..2729afc 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1367,6 +1367,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
                dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
 
        pci_save_state(pdev);
+       devlink_reload_enable(devlink);
        return 0;
 
 err_load_one:
@@ -1384,6 +1385,7 @@ static void remove_one(struct pci_dev *pdev)
        struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
        struct devlink *devlink = priv_to_devlink(dev);
 
+       devlink_reload_disable(devlink);
        mlx5_crdump_disable(dev);
        mlx5_devlink_unregister(devlink);