RDMA/mlx5: Fix devlink deadlock on net namespace deletion

When a mlx5 core devlink instance is reloaded in different net namespace,
its associated IB device is deleted and recreated.

Example sequence is:
$ ip netns add foo
$ devlink dev reload pci/0000:00:08.0 netns foo
$ ip netns del foo

mlx5 IB device needs to attach and detach the netdevice to it through the
netdev notifier chain during load and unload sequence.  A below call graph
of the unload flow.

cleanup_net()
   down_read(&pernet_ops_rwsem); <- first sem acquired
     ops_pre_exit_list()
       pre_exit()
         devlink_pernet_pre_exit()
           devlink_reload()
             mlx5_devlink_reload_down()
               mlx5_unload_one()
               [...]
                 mlx5_ib_remove()
                   mlx5_ib_unbind_slave_port()
                     mlx5_remove_netdev_notifier()
                       unregister_netdevice_notifier()
                         down_write(&pernet_ops_rwsem);<- recurrsive lock

Hence, when net namespace is deleted, mlx5 reload results in deadlock.

When deadlock occurs, devlink mutex is also held. This not only deadlocks
the mlx5 device under reload, but all the processes which attempt to
access unrelated devlink devices are deadlocked.

Hence, fix this by mlx5 ib driver to register for per net netdev notifier
instead of global one, which operats on the net namespace without holding
the pernet_ops_rwsem.

Fixes: 4383cfcc ("net/mlx5: Add devlink reload")
Link: https://lore.kernel.org/r/20201026134359.23150-1-parav@nvidia.comSigned-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

drivers/infiniband/hw/mlx5/main.c

@@ -3305,7 +3305,8 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 	int err;
 
 	dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
-	err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
+	err = register_netdevice_notifier_net(mlx5_core_net(dev->mdev),
+					      &dev->port[port_num].roce.nb);
 	if (err) {
 		dev->port[port_num].roce.nb.notifier_call = NULL;
 		return err;
@@ -3317,7 +3318,8 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 {
 	if (dev->port[port_num].roce.nb.notifier_call) {
-		unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
+		unregister_netdevice_notifier_net(mlx5_core_net(dev->mdev),
+						  &dev->port[port_num].roce.nb);
 		dev->port[port_num].roce.nb.notifier_call = NULL;
 	}
 }

drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h

@@ -90,9 +90,4 @@ int mlx5_create_encryption_key(struct mlx5_core_dev *mdev,
 			       u32 key_type, u32 *p_key_id);
 void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id);
 
-static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
-{
-	return devlink_net(priv_to_devlink(dev));
-}
-
 #endif

include/linux/mlx5/driver.h

@@ -1213,4 +1213,22 @@ static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev)
 	return val.vbool;
 }
 
+/**
+ * mlx5_core_net - Provide net namespace of the mlx5_core_dev
+ * @dev: mlx5 core device
+ *
+ * mlx5_core_net() returns the net namespace of mlx5 core device.
+ * This can be called only in below described limited context.
+ * (a) When a devlink instance for mlx5_core is registered and
+ *     when devlink reload operation is disabled.
+ *     or
+ * (b) during devlink reload reload_down() and reload_up callbacks
+ *     where it is ensured that devlink instance's net namespace is
+ *     stable.
+ */
+static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+{
+	return devlink_net(priv_to_devlink(dev));
+}
+
 #endif /* MLX5_DRIVER_H */