[NETLINK]: allocate group bitmaps dynamically

Allow changing the number of groups for a netlink family
after it has been created, use RCU to protect the listeners
bitmap keeping netlink_has_listeners() lock-free.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Acked-by: Patrick McHardy <kaber@trash.net>
Acked-by: Jamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netlink.h

@@ -161,6 +161,7 @@ extern struct sock *netlink_kernel_create(int unit, unsigned int groups,
 					  void (*input)(struct sock *sk, int len),
 					  struct mutex *cb_mutex,
 					  struct module *module);
+extern int netlink_change_ngroups(struct sock *sk, unsigned int groups);
 extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
 extern int netlink_has_listeners(struct sock *sk, unsigned int group);
 extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock);

net/netlink/af_netlink.c

@@ -62,6 +62,7 @@
 #include <net/netlink.h>
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
+#define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
 
 struct netlink_sock {
 	/* struct sock has to be the first member of netlink_sock */
@@ -314,10 +315,12 @@ netlink_update_listeners(struct sock *sk)
 	unsigned long mask;
 	unsigned int i;
 
-	for (i = 0; i < NLGRPSZ(tbl->groups)/sizeof(unsigned long); i++) {
+	for (i = 0; i < NLGRPLONGS(tbl->groups); i++) {
 		mask = 0;
-		sk_for_each_bound(sk, node, &tbl->mc_list)
+		sk_for_each_bound(sk, node, &tbl->mc_list) {
+			if (i < NLGRPLONGS(nlk_sk(sk)->ngroups))
 				mask |= nlk_sk(sk)->groups[i];
+		}
 		tbl->listeners[i] = mask;
 	}
 	/* this function is only called with the netlink table "grabbed", which
@@ -555,26 +558,37 @@ netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions)
 	nlk->subscriptions = subscriptions;
 }
 
-static int netlink_alloc_groups(struct sock *sk)
+static int netlink_realloc_groups(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	unsigned int groups;
+	unsigned long *new_groups;
 	int err = 0;
 
-	netlink_lock_table();
+	netlink_table_grab();
+
 	groups = nl_table[sk->sk_protocol].groups;
-	if (!nl_table[sk->sk_protocol].registered)
+	if (!nl_table[sk->sk_protocol].registered) {
 		err = -ENOENT;
-	netlink_unlock_table();
+		goto out_unlock;
+	}
 
-	if (err)
-		return err;
+	if (nlk->ngroups >= groups)
+		goto out_unlock;
 
-	nlk->groups = kzalloc(NLGRPSZ(groups), GFP_KERNEL);
-	if (nlk->groups == NULL)
-		return -ENOMEM;
+	new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC);
+	if (new_groups == NULL) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+	memset((char*)new_groups + NLGRPSZ(nlk->ngroups), 0,
+	       NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups));
+
+	nlk->groups = new_groups;
 	nlk->ngroups = groups;
-	return 0;
+ out_unlock:
+	netlink_table_ungrab();
+	return err;
 }
 
 static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
@@ -591,12 +605,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len
 	if (nladdr->nl_groups) {
 		if (!netlink_capable(sock, NL_NONROOT_RECV))
 			return -EPERM;
-		if (nlk->groups == NULL) {
-			err = netlink_alloc_groups(sk);
+		err = netlink_realloc_groups(sk);
 		if (err)
 			return err;
 	}
-	}
 
 	if (nlk->pid) {
 		if (nladdr->nl_pid != nlk->pid)
@@ -839,10 +851,18 @@ retry:
 int netlink_has_listeners(struct sock *sk, unsigned int group)
 {
 	int res = 0;
+	unsigned long *listeners;
 
 	BUG_ON(!(nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET));
+
+	rcu_read_lock();
+	listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners);
+
 	if (group - 1 < nl_table[sk->sk_protocol].groups)
-		res = test_bit(group - 1, nl_table[sk->sk_protocol].listeners);
+		res = test_bit(group - 1, listeners);
+
+	rcu_read_unlock();
+
 	return res;
 }
 EXPORT_SYMBOL_GPL(netlink_has_listeners);
@@ -1037,11 +1057,9 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 
 		if (!netlink_capable(sock, NL_NONROOT_RECV))
 			return -EPERM;
-		if (nlk->groups == NULL) {
-			err = netlink_alloc_groups(sk);
+		err = netlink_realloc_groups(sk);
 		if (err)
 			return err;
-		}
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
 		netlink_table_grab();
@@ -1328,6 +1346,46 @@ out_sock_release:
 	return NULL;
 }
 
+/**
+ * netlink_change_ngroups - change number of multicast groups
+ *
+ * This changes the number of multicast groups that are available
+ * on a certain netlink family. Note that it is not possible to
+ * change the number of groups to below 32.
+ *
+ * @sk: The kernel netlink socket, as returned by netlink_kernel_create().
+ * @groups: The new number of groups.
+ */
+int netlink_change_ngroups(struct sock *sk, unsigned int groups)
+{
+	unsigned long *listeners, *old = NULL;
+	struct netlink_table *tbl = &nl_table[sk->sk_protocol];
+	int err = 0;
+
+	if (groups < 32)
+		groups = 32;
+
+	netlink_table_grab();
+	if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) {
+		listeners = kzalloc(NLGRPSZ(groups), GFP_ATOMIC);
+		if (!listeners) {
+			err = -ENOMEM;
+			goto out_ungrab;
+		}
+		old = tbl->listeners;
+		memcpy(listeners, old, NLGRPSZ(tbl->groups));
+		rcu_assign_pointer(tbl->listeners, listeners);
+	}
+	tbl->groups = groups;
+
+ out_ungrab:
+	netlink_table_ungrab();
+	synchronize_rcu();
+	kfree(old);
+	return err;
+}
+EXPORT_SYMBOL(netlink_change_ngroups);
+
 void netlink_set_nonroot(int protocol, unsigned int flags)
 {
 	if ((unsigned int)protocol < MAX_LINKS)