Commit b7e3a5d9c0d6 for kernel
commit b7e3a5d9c0d66b7fb44f63aef3bd734821afa0c8
Author: Cosmin Ratiu <cratiu@nvidia.com>
Date: Mon Mar 16 11:46:01 2026 +0200
net/mlx5: qos: Restrict RTNL area to avoid a lock cycle
A lock dependency cycle exists where:
1. mlx5_ib_roce_init -> mlx5_core_uplink_netdev_event_replay ->
mlx5_blocking_notifier_call_chain (takes notifier_rwsem) ->
mlx5e_mdev_notifier_event -> mlx5_netdev_notifier_register ->
register_netdevice_notifier_dev_net (takes rtnl)
=> notifier_rwsem -> rtnl
2. mlx5e_probe -> _mlx5e_probe ->
mlx5_core_uplink_netdev_set (takes uplink_netdev_lock) ->
mlx5_blocking_notifier_call_chain (takes notifier_rwsem)
=> uplink_netdev_lock -> notifier_rwsem
3: devlink_nl_rate_set_doit -> devlink_nl_rate_set ->
mlx5_esw_devlink_rate_leaf_tx_max_set -> esw_qos_devlink_rate_to_mbps ->
mlx5_esw_qos_max_link_speed_get (takes rtnl) ->
mlx5_esw_qos_lag_link_speed_get_locked ->
mlx5_uplink_netdev_get (takes uplink_netdev_lock)
=> rtnl -> uplink_netdev_lock
=> BOOM! (lock cycle)
Fix that by restricting the rtnl-protected section to just the necessary
part, the call to netdev_master_upper_dev_get and speed querying, so
that the last lock dependency is avoided and the cycle doesn't close.
This is safe because mlx5_uplink_netdev_get uses netdev_hold to keep the
uplink netdev alive while its master device is queried.
Use this opportunity to rename the ambiguously-named "hold_rtnl_lock"
argument to "take_rtnl" and remove the "_locked" suffix from
mlx5_esw_qos_lag_link_speed_get_locked.
Fixes: 6b4be64fd9fe ("net/mlx5e: Harden uplink netdev access against device unbind")
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260316094603.6999-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 26178d0bac92..faccc60fc93a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -1489,24 +1489,24 @@ static int esw_qos_node_enable_tc_arbitration(struct mlx5_esw_sched_node *node,
return err;
}
-static u32 mlx5_esw_qos_lag_link_speed_get_locked(struct mlx5_core_dev *mdev)
+static u32 mlx5_esw_qos_lag_link_speed_get(struct mlx5_core_dev *mdev,
+ bool take_rtnl)
{
struct ethtool_link_ksettings lksettings;
struct net_device *slave, *master;
u32 speed = SPEED_UNKNOWN;
- /* Lock ensures a stable reference to master and slave netdevice
- * while port speed of master is queried.
- */
- ASSERT_RTNL();
-
slave = mlx5_uplink_netdev_get(mdev);
if (!slave)
goto out;
+ if (take_rtnl)
+ rtnl_lock();
master = netdev_master_upper_dev_get(slave);
if (master && !__ethtool_get_link_ksettings(master, &lksettings))
speed = lksettings.base.speed;
+ if (take_rtnl)
+ rtnl_unlock();
out:
mlx5_uplink_netdev_put(mdev, slave);
@@ -1514,20 +1514,15 @@ static u32 mlx5_esw_qos_lag_link_speed_get_locked(struct mlx5_core_dev *mdev)
}
static int mlx5_esw_qos_max_link_speed_get(struct mlx5_core_dev *mdev, u32 *link_speed_max,
- bool hold_rtnl_lock, struct netlink_ext_ack *extack)
+ bool take_rtnl,
+ struct netlink_ext_ack *extack)
{
int err;
if (!mlx5_lag_is_active(mdev))
goto skip_lag;
- if (hold_rtnl_lock)
- rtnl_lock();
-
- *link_speed_max = mlx5_esw_qos_lag_link_speed_get_locked(mdev);
-
- if (hold_rtnl_lock)
- rtnl_unlock();
+ *link_speed_max = mlx5_esw_qos_lag_link_speed_get(mdev, take_rtnl);
if (*link_speed_max != (u32)SPEED_UNKNOWN)
return 0;