Commit d3dbdc9f authored by Moshe Shemesh's avatar Moshe Shemesh Committed by Jakub Kicinski
Browse files

net/mlx5: Lock mlx5 devlink health recovery callback 



Change devlink instance locks in mlx5 driver to have devlink health
recovery callback locked, while keeping all driver paths which lead to
devl_ API functions called by the driver locked.

Signed-off-by: default avatarMoshe Shemesh <moshe@nvidia.com>
Reviewed-by: default avatarJiri Pirko <jiri@nvidia.com>
Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 60d7ceea

drivers/net/ethernet/mellanox/mlx5/core/health.c

+11 −1
Original line number Diff line number Diff line
@@ -622,8 +622,14 @@ mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter, 
			       struct netlink_ext_ack *extack)

{

	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);

	struct devlink *devlink = priv_to_devlink(dev);

	int ret;



	return mlx5_health_try_recover(dev);

	devl_lock(devlink);

	ret = mlx5_health_try_recover(dev);

	devl_unlock(devlink);



	return ret;

}



static int
@@ -666,16 +672,20 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) 
	struct mlx5_fw_reporter_ctx fw_reporter_ctx;

	struct mlx5_core_health *health;

	struct mlx5_core_dev *dev;

	struct devlink *devlink;

	struct mlx5_priv *priv;



	health = container_of(work, struct mlx5_core_health, fatal_report_work);

	priv = container_of(health, struct mlx5_priv, health);

	dev = container_of(priv, struct mlx5_core_dev, priv);

	devlink = priv_to_devlink(dev);



	enter_error_state(dev, false);

	if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) {

		devl_lock(devlink);

		if (mlx5_health_try_recover(dev))

			mlx5_core_err(dev, "health recovery failed\n");

		devl_unlock(devlink);

		return;

	}

	fw_reporter_ctx.err_synd = health->synd;

drivers/net/ethernet/mellanox/mlx5/core/main.c

+2 −2
Original line number Diff line number Diff line
@@ -1932,7 +1932,7 @@ MODULE_DEVICE_TABLE(pci, mlx5_core_pci_table); 
void mlx5_disable_device(struct mlx5_core_dev *dev)

{

	mlx5_error_sw_reset(dev);

	mlx5_unload_one(dev);

	mlx5_unload_one_devl_locked(dev);

}



int mlx5_recover_device(struct mlx5_core_dev *dev)
@@ -1943,7 +1943,7 @@ int mlx5_recover_device(struct mlx5_core_dev *dev) 
			return -EIO;

	}



	return mlx5_load_one(dev, true);

	return mlx5_load_one_devl_locked(dev, true);

}



static struct pci_driver mlx5_core_driver = {