genetlink: remove genl_bind

A potential deadlock can occur during registering or unregistering a
new generic netlink family between the main nl_table_lock and the
cb_lock where each thread wants the lock held by the other, as
demonstrated below.

1) Thread 1 is performing a netlink_bind() operation on a socket. As part
of this call, it will call netlink_lock_table(), incrementing the
nl_table_users count to 1.
2) Thread 2 is registering (or unregistering) a genl_family via the
genl_(un)register_family() API. The cb_lock semaphore will be taken for
writing.
3) Thread 1 will call genl_bind() as part of the bind operation to handle
subscribing to GENL multicast groups at the request of the user. It will
attempt to take the cb_lock semaphore for reading, but it will fail and
be scheduled away, waiting for Thread 2 to finish the write.
4) Thread 2 will call netlink_table_grab() during the (un)registration
call. However, as Thread 1 has incremented nl_table_users, it will not
be able to proceed, and both threads will be stuck waiting for the
other.

genl_bind() is a noop, unless a genl_family implements the mcast_bind()
function to handle setting up family-specific multicast operations. Since
no one in-tree uses this functionality as Cong pointed out, simply removing
the genl_bind() function will remove the possibility for deadlock, as there
is no attempt by Thread 1 above to take the cb_lock semaphore.

Fixes: c380d9a7afff ("genetlink: pass multicast bind/unbind to families")
Suggested-by: Cong Wang <[e-mail]>
Acked-by: Johannes Berg <[e-mail]>
Reported-by: kernel test robot <[e-mail]>
Signed-off-by: Sean Tranchetti <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

include/net/genetlink.h

···
  *	do additional, common, filtering and return an error
  * @post_doit: called after an operation's doit callback, it may
  *	undo operations done by pre_doit, for example release locks
- * @mcast_bind: a socket bound to the given multicast group (which
- *	is given as the offset into the groups array)
- * @mcast_unbind: a socket was unbound from the given multicast group.
- *	Note that unbind() will not be called symmetrically if the
- *	generic netlink family is removed while there are still open
- *	sockets.
  * @mcgrps: multicast groups used by this family
  * @n_mcgrps: number of multicast groups
  * @mcgrp_offset: starting number of multicast group IDs in this family
···
 	void			(*post_doit)(const struct genl_ops *ops,
 					     struct sk_buff *skb,
 					     struct genl_info *info);
-	int			(*mcast_bind)(struct net *net, int group);
-	void			(*mcast_unbind)(struct net *net, int group);
 	const struct genl_ops *	ops;
 	const struct genl_multicast_group *mcgrps;
 	unsigned int		n_ops;

net/netlink/genetlink.c

···
 	.netnsok = true,
 };
 
-static int genl_bind(struct net *net, int group)
-{
-	struct genl_family *f;
-	int err = -ENOENT;
-	unsigned int id;
-
-	down_read(&cb_lock);
-
-	idr_for_each_entry(&genl_fam_idr, f, id) {
-		if (group >= f->mcgrp_offset &&
-		    group < f->mcgrp_offset + f->n_mcgrps) {
-			int fam_grp = group - f->mcgrp_offset;
-
-			if (!f->netnsok && net != &init_net)
-				err = -ENOENT;
-			else if (f->mcast_bind)
-				err = f->mcast_bind(net, fam_grp);
-			else
-				err = 0;
-			break;
-		}
-	}
-	up_read(&cb_lock);
-
-	return err;
-}
-
-static void genl_unbind(struct net *net, int group)
-{
-	struct genl_family *f;
-	unsigned int id;
-
-	down_read(&cb_lock);
-
-	idr_for_each_entry(&genl_fam_idr, f, id) {
-		if (group >= f->mcgrp_offset &&
-		    group < f->mcgrp_offset + f->n_mcgrps) {
-			int fam_grp = group - f->mcgrp_offset;
-
-			if (f->mcast_unbind)
-				f->mcast_unbind(net, fam_grp);
-			break;
-		}
-	}
-	up_read(&cb_lock);
-}
-
 static int __net_init genl_pernet_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
-		.bind		= genl_bind,
-		.unbind		= genl_unbind,
 	};
 
 	/* we'll bump the group number right afterwards */