bonding: fix oops during rmmod

"rmmod bonding" causes an oops ever since commit cc317ea3d9 ("bonding:
remove redundant NULL check in debugfs function").  Here are the relevant
functions being called:

bonding_exit()
  bond_destroy_debugfs()
    debugfs_remove_recursive(bonding_debug_root);
    bonding_debug_root = NULL; <--------- SET TO NULL HERE
  bond_netlink_fini()
    rtnl_link_unregister()
      __rtnl_link_unregister()
        unregister_netdevice_many_notify()
          bond_uninit()
            bond_debug_unregister()
              (commit removed check for bonding_debug_root == NULL)
              debugfs_remove()
              simple_recursive_removal()
                down_write() -> OOPS

However, reverting the bad commit does not solve the problem completely
because the original code contains a race that could cause the same
oops, although it was much less likely to be triggered unintentionally:

CPU1
  rmmod bonding
    bonding_exit()
      bond_destroy_debugfs()
        debugfs_remove_recursive(bonding_debug_root);

CPU2
  echo -bond0 > /sys/class/net/bonding_masters
    bond_uninit()
      bond_debug_unregister()
        if (!bonding_debug_root)

CPU1
        bonding_debug_root = NULL;

So do NOT revert the bad commit (since the removed checks were racy
anyway), and instead change the order of actions taken during module
removal.  The same oops can also happen if there is an error during
module init, so apply the same fix there.

Fixes: cc317ea3d9 ("bonding: remove redundant NULL check in debugfs function")
Cc: stable@vger.kernel.org
Signed-off-by: Tony Battersby <tonyb@cybernetics.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Link: https://lore.kernel.org/r/641f914f-3216-4eeb-87dd-91b78aa97773@cybernetics.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Tony Battersby 2024-05-14 15:57:29 -04:00 committed by Jakub Kicinski
parent bb48727238
commit a45835a0bb

View File

@ -6477,16 +6477,16 @@ static int __init bonding_init(void)
if (res) if (res)
goto out; goto out;
bond_create_debugfs();
res = register_pernet_subsys(&bond_net_ops); res = register_pernet_subsys(&bond_net_ops);
if (res) if (res)
goto out; goto err_net_ops;
res = bond_netlink_init(); res = bond_netlink_init();
if (res) if (res)
goto err_link; goto err_link;
bond_create_debugfs();
for (i = 0; i < max_bonds; i++) { for (i = 0; i < max_bonds; i++) {
res = bond_create(&init_net, NULL); res = bond_create(&init_net, NULL);
if (res) if (res)
@ -6501,10 +6501,11 @@ static int __init bonding_init(void)
out: out:
return res; return res;
err: err:
bond_destroy_debugfs();
bond_netlink_fini(); bond_netlink_fini();
err_link: err_link:
unregister_pernet_subsys(&bond_net_ops); unregister_pernet_subsys(&bond_net_ops);
err_net_ops:
bond_destroy_debugfs();
goto out; goto out;
} }
@ -6513,11 +6514,11 @@ static void __exit bonding_exit(void)
{ {
unregister_netdevice_notifier(&bond_netdev_notifier); unregister_netdevice_notifier(&bond_netdev_notifier);
bond_destroy_debugfs();
bond_netlink_fini(); bond_netlink_fini();
unregister_pernet_subsys(&bond_net_ops); unregister_pernet_subsys(&bond_net_ops);
bond_destroy_debugfs();
#ifdef CONFIG_NET_POLL_CONTROLLER #ifdef CONFIG_NET_POLL_CONTROLLER
/* Make sure we don't have an imbalance on our netpoll blocking */ /* Make sure we don't have an imbalance on our netpoll blocking */
WARN_ON(atomic_read(&netpoll_block_tx)); WARN_ON(atomic_read(&netpoll_block_tx));