It is possible to unbind the uplink ETH driver while the E-Switch is
in switchdev mode. This leads to netdevice reference counting issues[1],
as the driver removal path was not designed to clean up from this state.
During uplink ETH driver removal (_mlx5e_remove), the code now waits for
any concurrent E-Switch mode transition to finish. It then removes the
REPs auxiliary device, if exists. This ensures a graceful cleanup.
[1]
unregister_netdevice: waiting for eth2 to become free. Usage count = 2
ref_tracker: netdev@
00000000c912e04b has 1/1 users at
ib_device_set_netdev+0x130/0x270 [ib_core]
mlx5_ib_vport_rep_load+0xf4/0x3e0 [mlx5_ib]
mlx5_esw_offloads_rep_load+0xc7/0xe0 [mlx5_core]
esw_offloads_enable+0x583/0x900 [mlx5_core]
mlx5_eswitch_enable_locked+0x1b2/0x290 [mlx5_core]
mlx5_devlink_eswitch_mode_set+0x107/0x3e0 [mlx5_core]
devlink_nl_eswitch_set_doit+0x60/0xd0
genl_family_rcv_msg_doit+0xe0/0x130
genl_rcv_msg+0x183/0x290
netlink_rcv_skb+0x4b/0xf0
genl_rcv+0x24/0x40
netlink_unicast+0x255/0x380
netlink_sendmsg+0x1f3/0x420
__sock_sendmsg+0x38/0x60
__sys_sendto+0x119/0x180
__x64_sys_sendto+0x20/0x30
Fixes: 7a9fb35e8c3a ("net/mlx5e: Do not reload ethernet ports when changing eswitch mode")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/1769411695-18820-2-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
return plen && flen && flen == plen &&
!memcmp(fsystem_guid, psystem_guid, flen);
}
+
+void mlx5_core_reps_aux_devs_remove(struct mlx5_core_dev *dev)
+{
+ struct mlx5_priv *priv = &dev->priv;
+
+ if (priv->adev[MLX5_INTERFACE_PROTOCOL_ETH])
+ device_lock_assert(&priv->adev[MLX5_INTERFACE_PROTOCOL_ETH]->adev.dev);
+ else
+ mlx5_core_err(dev, "ETH driver already removed\n");
+ if (priv->adev[MLX5_INTERFACE_PROTOCOL_IB_REP])
+ del_adev(&priv->adev[MLX5_INTERFACE_PROTOCOL_IB_REP]->adev);
+ if (priv->adev[MLX5_INTERFACE_PROTOCOL_ETH_REP])
+ del_adev(&priv->adev[MLX5_INTERFACE_PROTOCOL_ETH_REP]->adev);
+}
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5_core_dev *mdev = edev->mdev;
+ mlx5_eswitch_safe_aux_devs_remove(mdev);
mlx5_core_uplink_netdev_set(mdev, NULL);
if (priv->profile)
int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev,
u16 vport_num);
bool mlx5_esw_host_functions_enabled(const struct mlx5_core_dev *dev);
+void mlx5_eswitch_safe_aux_devs_remove(struct mlx5_core_dev *dev);
#else /* CONFIG_MLX5_ESWITCH */
/* eswitch API stubs */
static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
return false;
}
+static inline void
+mlx5_eswitch_safe_aux_devs_remove(struct mlx5_core_dev *dev) {}
+
#endif /* CONFIG_MLX5_ESWITCH */
#endif /* __MLX5_ESWITCH_H__ */
return true;
}
+#define MLX5_ESW_HOLD_TIMEOUT_MS 7000
+#define MLX5_ESW_HOLD_RETRY_DELAY_MS 500
+
+void mlx5_eswitch_safe_aux_devs_remove(struct mlx5_core_dev *dev)
+{
+ unsigned long timeout;
+ bool hold_esw = true;
+
+ /* Wait for any concurrent eswitch mode transition to complete. */
+ if (!mlx5_esw_hold(dev)) {
+ timeout = jiffies + msecs_to_jiffies(MLX5_ESW_HOLD_TIMEOUT_MS);
+ while (!mlx5_esw_hold(dev)) {
+ if (!time_before(jiffies, timeout)) {
+ hold_esw = false;
+ break;
+ }
+ msleep(MLX5_ESW_HOLD_RETRY_DELAY_MS);
+ }
+ }
+ if (hold_esw) {
+ if (mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS)
+ mlx5_core_reps_aux_devs_remove(dev);
+ mlx5_esw_release(dev);
+ }
+}
+
int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
struct netlink_ext_ack *extack)
{
void mlx5_unregister_device(struct mlx5_core_dev *dev);
void mlx5_dev_set_lightweight(struct mlx5_core_dev *dev);
bool mlx5_dev_is_lightweight(struct mlx5_core_dev *dev);
+void mlx5_core_reps_aux_devs_remove(struct mlx5_core_dev *dev);
void mlx5_fw_reporters_create(struct mlx5_core_dev *dev);
int mlx5_query_mtpps(struct mlx5_core_dev *dev, u32 *mtpps, u32 mtpps_size);