Merge branch 'netlink_multicast'

Johannes Berg says:

====================
netlink/genetlink cleanups & multicast improvements

I'm looking at using the multicast group functionality in a way that would
benefit from knowing when there are subscribers to avoid collecting the
required data when there aren't any. During this I noticed that the unbind
for multicast groups doesn't actually work - it's never called when sockets
are closed. Luckily, nobody actually uses the functionality.

While looking at the code trying to find why it's not called and where the
multicast listeners are actually removed, I found the potential cleanup in
patch 3. Patch 2 also has a cleanup for a generic netlink API in this area.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/genetlink.h

@@ -31,6 +31,9 @@ struct genl_info;
  *	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
  * @attrbuf: buffer to store parsed attributes
  * @family_list: family list
  * @mcgrps: multicast groups used by this family (private)
@@ -53,6 +56,8 @@ struct genl_family {
 	void			(*post_doit)(const struct genl_ops *ops,
 					     struct sk_buff *skb,
 					     struct genl_info *info);
+	int			(*mcast_bind)(int group);
+	void			(*mcast_unbind)(int group);
 	struct nlattr **	attrbuf;	/* private */
 	const struct genl_ops *	ops;		/* private */
 	const struct genl_multicast_group *mcgrps; /* private */
@@ -395,11 +400,11 @@ static inline int genl_set_err(struct genl_family *family, struct net *net,
 }
 
 static inline int genl_has_listeners(struct genl_family *family,
-				     struct sock *sk, unsigned int group)
+				     struct net *net, unsigned int group)
 {
 	if (WARN_ON_ONCE(group >= family->n_mcgrps))
 		return -EINVAL;
 	group = family->mcgrp_offset + group;
-	return netlink_has_listeners(sk, group);
+	return netlink_has_listeners(net->genl_sock, group);
 }
 #endif	/* __NET_GENERIC_NETLINK_H */

net/netlink/af_netlink.c

@@ -1091,8 +1091,10 @@ static void netlink_remove(struct sock *sk)
 	mutex_unlock(&nl_sk_hash_lock);
 
 	netlink_table_grab();
-	if (nlk_sk(sk)->subscriptions)
+	if (nlk_sk(sk)->subscriptions) {
 		__sk_del_bind_node(sk);
+		netlink_update_listeners(sk);
+	}
 	netlink_table_ungrab();
 }
 
@@ -1226,8 +1228,8 @@ static int netlink_release(struct socket *sock)
 
 	module_put(nlk->module);
 
-	netlink_table_grab();
 	if (netlink_is_kernel(sk)) {
+		netlink_table_grab();
 		BUG_ON(nl_table[sk->sk_protocol].registered == 0);
 		if (--nl_table[sk->sk_protocol].registered == 0) {
 			struct listeners *old;
@@ -1241,11 +1243,16 @@ static int netlink_release(struct socket *sock)
 			nl_table[sk->sk_protocol].flags = 0;
 			nl_table[sk->sk_protocol].registered = 0;
 		}
-	} else if (nlk->subscriptions) {
-		netlink_update_listeners(sk);
+		netlink_table_ungrab();
 	}
-	netlink_table_ungrab();
 
+	if (nlk->netlink_unbind) {
+		int i;
+
+		for (i = 0; i < nlk->ngroups; i++)
+			if (test_bit(i, nlk->groups))
+				nlk->netlink_unbind(i + 1);
+	}
 	kfree(nlk->groups);
 	nlk->groups = NULL;
 
@@ -1410,8 +1417,8 @@ static int netlink_realloc_groups(struct sock *sk)
 	return err;
 }
 
-static void netlink_unbind(int group, long unsigned int groups,
-			   struct netlink_sock *nlk)
+static void netlink_undo_bind(int group, long unsigned int groups,
+			      struct netlink_sock *nlk)
 {
 	int undo;
 
@@ -1461,7 +1468,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			err = nlk->netlink_bind(group);
 			if (!err)
 				continue;
-			netlink_unbind(group, groups, nlk);
+			netlink_undo_bind(group, groups, nlk);
 			return err;
 		}
 	}
@@ -1471,7 +1478,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			netlink_insert(sk, net, nladdr->nl_pid) :
 			netlink_autobind(sock);
 		if (err) {
-			netlink_unbind(nlk->ngroups, groups, nlk);
+			netlink_undo_bind(nlk->ngroups, groups, nlk);
 			return err;
 		}
 	}

net/netlink/genetlink.c

@@ -983,11 +983,70 @@ static struct genl_multicast_group genl_ctrl_groups[] = {
 	{ .name = "notify", },
 };
 
+static int genl_bind(int group)
+{
+	int i, err;
+	bool found = false;
+
+	down_read(&cb_lock);
+	for (i = 0; i < GENL_FAM_TAB_SIZE; i++) {
+		struct genl_family *f;
+
+		list_for_each_entry(f, genl_family_chain(i), family_list) {
+			if (group >= f->mcgrp_offset &&
+			    group < f->mcgrp_offset + f->n_mcgrps) {
+				int fam_grp = group - f->mcgrp_offset;
+
+				if (f->mcast_bind)
+					err = f->mcast_bind(fam_grp);
+				else
+					err = 0;
+				found = true;
+				break;
+			}
+		}
+	}
+	up_read(&cb_lock);
+
+	if (WARN_ON(!found))
+		err = 0;
+
+	return err;
+}
+
+static void genl_unbind(int group)
+{
+	int i;
+	bool found = false;
+
+	down_read(&cb_lock);
+	for (i = 0; i < GENL_FAM_TAB_SIZE; i++) {
+		struct genl_family *f;
+
+		list_for_each_entry(f, genl_family_chain(i), family_list) {
+			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(fam_grp);
+				found = true;
+				break;
+			}
+		}
+	}
+	up_read(&cb_lock);
+
+	WARN_ON(!found);
+}
+
 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 */

net/openvswitch/datapath.c

@@ -83,8 +83,7 @@ static bool ovs_must_notify(struct genl_family *family, struct genl_info *info,
 			    unsigned int group)
 {
 	return info->nlhdr->nlmsg_flags & NLM_F_ECHO ||
-	       genl_has_listeners(family, genl_info_net(info)->genl_sock,
-				  group);
+	       genl_has_listeners(family, genl_info_net(info), group);
 }
 
 static void ovs_notify(struct genl_family *family,