3 files changed, 377 insertions, 45 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 1f15821c8da4..5681ce3aebca 100644
--- a/net/netlink/af_netlink.c
+++ b/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)
-			mask |= nlk_sk(sk)->groups[i];
+		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)
@@ -591,11 +605,9 @@ 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);
-			if (err)
-				return err;
-		}
+		err = netlink_realloc_groups(sk);
+		if (err)
+			return err;
 	}
 
 	if (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);
@@ -1007,18 +1027,36 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 	read_unlock(&nl_table_lock);
 }
 
+/* must be called with netlink table grabbed */
+static void netlink_update_socket_mc(struct netlink_sock *nlk,
+				     unsigned int group,
+				     int is_new)
+{
+	int old, new = !!is_new, subscriptions;
+
+	old = test_bit(group - 1, nlk->groups);
+	subscriptions = nlk->subscriptions - old + new;
+	if (new)
+		__set_bit(group - 1, nlk->groups);
+	else
+		__clear_bit(group - 1, nlk->groups);
+	netlink_update_subscriptions(&nlk->sk, subscriptions);
+	netlink_update_listeners(&nlk->sk);
+}
+
 static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			      char __user *optval, int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
-	int val = 0, err;
+	unsigned int val = 0;
+	int err;
 
 	if (level != SOL_NETLINK)
 		return -ENOPROTOOPT;
 
 	if (optlen >= sizeof(int) &&
-	    get_user(val, (int __user *)optval))
+	    get_user(val, (unsigned int __user *)optval))
 		return -EFAULT;
 
 	switch (optname) {
@@ -1031,27 +1069,16 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
 	case NETLINK_DROP_MEMBERSHIP: {
-		unsigned int subscriptions;
-		int old, new = optname == NETLINK_ADD_MEMBERSHIP ? 1 : 0;
-
 		if (!netlink_capable(sock, NL_NONROOT_RECV))
 			return -EPERM;
-		if (nlk->groups == NULL) {
-			err = netlink_alloc_groups(sk);
-			if (err)
-				return err;
-		}
+		err = netlink_realloc_groups(sk);
+		if (err)
+			return err;
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
 		netlink_table_grab();
-		old = test_bit(val - 1, nlk->groups);
-		subscriptions = nlk->subscriptions - old + new;
-		if (new)
-			__set_bit(val - 1, nlk->groups);
-		else
-			__clear_bit(val - 1, nlk->groups);
-		netlink_update_subscriptions(sk, subscriptions);
-		netlink_update_listeners(sk);
+		netlink_update_socket_mc(nlk, val,
+					 optname == NETLINK_ADD_MEMBERSHIP);
 		netlink_table_ungrab();
 		err = 0;
 		break;
@@ -1327,6 +1354,71 @@ 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. Also note that it does
+ * not implicitly call netlink_clear_multicast_users() when the
+ * number of groups is reduced.
+ *
+ * @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);
+
+/**
+ * netlink_clear_multicast_users - kick off multicast listeners
+ *
+ * This function removes all listeners from the given group.
+ * @ksk: The kernel netlink socket, as returned by
+ *	netlink_kernel_create().
+ * @group: The multicast group to clear.
+ */
+void netlink_clear_multicast_users(struct sock *ksk, unsigned int group)
+{
+	struct sock *sk;
+	struct hlist_node *node;
+	struct netlink_table *tbl = &nl_table[ksk->sk_protocol];
+
+	netlink_table_grab();
+
+	sk_for_each_bound(sk, node, &tbl->mc_list)
+		netlink_update_socket_mc(nlk_sk(sk), group, 0);
+
+	netlink_table_ungrab();
+}
+EXPORT_SYMBOL(netlink_clear_multicast_users);
+
 void netlink_set_nonroot(int protocol, unsigned int flags)
 {
 	if ((unsigned int)protocol < MAX_LINKS)
@@ -1713,7 +1805,7 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static struct seq_operations netlink_seq_ops = {
+static const struct seq_operations netlink_seq_ops = {
 	.start  = netlink_seq_start,
 	.next   = netlink_seq_next,
 	.stop   = netlink_seq_stop,
diff --git a/net/netlink/attr.c b/net/netlink/attr.c
index c591212793ee..e4d7bed99c2e 100644
--- a/net/netlink/attr.c
+++ b/net/netlink/attr.c
@@ -72,6 +72,17 @@ static int validate_nla(struct nlattr *nla, int maxtype,
 			return -ERANGE;
 		break;
 
+	case NLA_NESTED_COMPAT:
+		if (attrlen < pt->len)
+			return -ERANGE;
+		if (attrlen < NLA_ALIGN(pt->len))
+			break;
+		if (attrlen < NLA_ALIGN(pt->len) + NLA_HDRLEN)
+			return -ERANGE;
+		nla = nla_data(nla) + NLA_ALIGN(pt->len);
+		if (attrlen < NLA_ALIGN(pt->len) + NLA_HDRLEN + nla_len(nla))
+			return -ERANGE;
+		break;
 	default:
 		if (pt->len)
 			minlen = pt->len;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index b9ab62f938d0..8c11ca4a2121 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -3,6 +3,7 @@
  *
  * 		Authors:	Jamal Hadi Salim
  * 				Thomas Graf <tgraf@suug.ch>
+ *				Johannes Berg <johannes@sipsolutions.net>
  */
 
 #include <linux/module.h>
@@ -13,6 +14,7 @@
 #include <linux/string.h>
 #include <linux/skbuff.h>
 #include <linux/mutex.h>
+#include <linux/bitmap.h>
 #include <net/sock.h>
 #include <net/genetlink.h>
 
@@ -42,6 +44,16 @@ static void genl_unlock(void)
 #define GENL_FAM_TAB_MASK	(GENL_FAM_TAB_SIZE - 1)
 
 static struct list_head family_ht[GENL_FAM_TAB_SIZE];
+/*
+ * Bitmap of multicast groups that are currently in use.
+ *
+ * To avoid an allocation at boot of just one unsigned long,
+ * declare it global instead.
+ * Bit 0 is marked as already used since group 0 is invalid.
+ */
+static unsigned long mc_group_start = 0x1;
+static unsigned long *mc_groups = &mc_group_start;
+static unsigned long mc_groups_longs = 1;
 
 static int genl_ctrl_event(int event, void *data);
 
@@ -116,6 +128,122 @@ static inline u16 genl_generate_id(void)
 	return id_gen_idx;
 }
 
+static struct genl_multicast_group notify_grp;
+
+/**
+ * genl_register_mc_group - register a multicast group
+ *
+ * Registers the specified multicast group and notifies userspace
+ * about the new group.
+ *
+ * Returns 0 on success or a negative error code.
+ *
+ * @family: The generic netlink family the group shall be registered for.
+ * @grp: The group to register, must have a name.
+ */
+int genl_register_mc_group(struct genl_family *family,
+			   struct genl_multicast_group *grp)
+{
+	int id;
+	unsigned long *new_groups;
+	int err;
+
+	BUG_ON(grp->name[0] == '\0');
+
+	genl_lock();
+
+	/* special-case our own group */
+	if (grp == &notify_grp)
+		id = GENL_ID_CTRL;
+	else
+		id = find_first_zero_bit(mc_groups,
+					 mc_groups_longs * BITS_PER_LONG);
+
+
+	if (id >= mc_groups_longs * BITS_PER_LONG) {
+		size_t nlen = (mc_groups_longs + 1) * sizeof(unsigned long);
+
+		if (mc_groups == &mc_group_start) {
+			new_groups = kzalloc(nlen, GFP_KERNEL);
+			if (!new_groups) {
+				err = -ENOMEM;
+				goto out;
+			}
+			mc_groups = new_groups;
+			*mc_groups = mc_group_start;
+		} else {
+			new_groups = krealloc(mc_groups, nlen, GFP_KERNEL);
+			if (!new_groups) {
+				err = -ENOMEM;
+				goto out;
+			}
+			mc_groups = new_groups;
+			mc_groups[mc_groups_longs] = 0;
+		}
+		mc_groups_longs++;
+	}
+
+	err = netlink_change_ngroups(genl_sock,
+				     mc_groups_longs * BITS_PER_LONG);
+	if (err)
+		goto out;
+
+	grp->id = id;
+	set_bit(id, mc_groups);
+	list_add_tail(&grp->list, &family->mcast_groups);
+	grp->family = family;
+
+	genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, grp);
+ out:
+	genl_unlock();
+	return err;
+}
+EXPORT_SYMBOL(genl_register_mc_group);
+
+static void __genl_unregister_mc_group(struct genl_family *family,
+				       struct genl_multicast_group *grp)
+{
+	BUG_ON(grp->family != family);
+	netlink_clear_multicast_users(genl_sock, grp->id);
+	clear_bit(grp->id, mc_groups);
+	list_del(&grp->list);
+	genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, grp);
+	grp->id = 0;
+	grp->family = NULL;
+}
+
+/**
+ * genl_unregister_mc_group - unregister a multicast group
+ *
+ * Unregisters the specified multicast group and notifies userspace
+ * about it. All current listeners on the group are removed.
+ *
+ * Note: It is not necessary to unregister all multicast groups before
+ *       unregistering the family, unregistering the family will cause
+ *       all assigned multicast groups to be unregistered automatically.
+ *
+ * @family: Generic netlink family the group belongs to.
+ * @grp: The group to unregister, must have been registered successfully
+ *	 previously.
+ */
+void genl_unregister_mc_group(struct genl_family *family,
+			      struct genl_multicast_group *grp)
+{
+	genl_lock();
+	__genl_unregister_mc_group(family, grp);
+	genl_unlock();
+}
+
+static void genl_unregister_mc_groups(struct genl_family *family)
+{
+	struct genl_multicast_group *grp, *tmp;
+
+	genl_lock();
+	list_for_each_entry_safe(grp, tmp, &family->mcast_groups, list)
+		__genl_unregister_mc_group(family, grp);
+	genl_unlock();
+}
+
 /**
  * genl_register_ops - register generic netlink operations
  * @family: generic netlink family
@@ -216,6 +344,7 @@ int genl_register_family(struct genl_family *family)
 		goto errout;
 
 	INIT_LIST_HEAD(&family->ops_list);
+	INIT_LIST_HEAD(&family->mcast_groups);
 
 	genl_lock();
 
@@ -275,6 +404,8 @@ int genl_unregister_family(struct genl_family *family)
 {
 	struct genl_family *rc;
 
+	genl_unregister_mc_groups(family);
+
 	genl_lock();
 
 	list_for_each_entry(rc, genl_family_chain(family->id), family_list) {
@@ -410,6 +541,67 @@ static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq,
 		nla_nest_end(skb, nla_ops);
 	}
 
+	if (!list_empty(&family->mcast_groups)) {
+		struct genl_multicast_group *grp;
+		struct nlattr *nla_grps;
+		int idx = 1;
+
+		nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
+		if (nla_grps == NULL)
+			goto nla_put_failure;
+
+		list_for_each_entry(grp, &family->mcast_groups, list) {
+			struct nlattr *nest;
+
+			nest = nla_nest_start(skb, idx++);
+			if (nest == NULL)
+				goto nla_put_failure;
+
+			NLA_PUT_U32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id);
+			NLA_PUT_STRING(skb, CTRL_ATTR_MCAST_GRP_NAME,
+				       grp->name);
+
+			nla_nest_end(skb, nest);
+		}
+		nla_nest_end(skb, nla_grps);
+	}
+
+	return genlmsg_end(skb, hdr);
+
+nla_put_failure:
+	return genlmsg_cancel(skb, hdr);
+}
+
+static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid,
+				u32 seq, u32 flags, struct sk_buff *skb,
+				u8 cmd)
+{
+	void *hdr;
+	struct nlattr *nla_grps;
+	struct nlattr *nest;
+
+	hdr = genlmsg_put(skb, pid, seq, &genl_ctrl, flags, cmd);
+	if (hdr == NULL)
+		return -1;
+
+	NLA_PUT_STRING(skb, CTRL_ATTR_FAMILY_NAME, grp->family->name);
+	NLA_PUT_U16(skb, CTRL_ATTR_FAMILY_ID, grp->family->id);
+
+	nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
+	if (nla_grps == NULL)
+		goto nla_put_failure;
+
+	nest = nla_nest_start(skb, 1);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	NLA_PUT_U32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id);
+	NLA_PUT_STRING(skb, CTRL_ATTR_MCAST_GRP_NAME,
+		       grp->name);
+
+	nla_nest_end(skb, nest);
+	nla_nest_end(skb, nla_grps);
+
 	return genlmsg_end(skb, hdr);
 
 nla_put_failure:
@@ -453,8 +645,8 @@ errout:
 	return skb->len;
 }
 
-static struct sk_buff *ctrl_build_msg(struct genl_family *family, u32 pid,
-				      int seq, u8 cmd)
+static struct sk_buff *ctrl_build_family_msg(struct genl_family *family,
+					     u32 pid, int seq, u8 cmd)
 {
 	struct sk_buff *skb;
 	int err;
@@ -472,6 +664,25 @@ static struct sk_buff *ctrl_build_msg(struct genl_family *family, u32 pid,
 	return skb;
 }
 
+static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_multicast_group *grp,
+					    u32 pid, int seq, u8 cmd)
+{
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (skb == NULL)
+		return ERR_PTR(-ENOBUFS);
+
+	err = ctrl_fill_mcgrp_info(grp, pid, seq, 0, skb, cmd);
+	if (err < 0) {
+		nlmsg_free(skb);
+		return ERR_PTR(err);
+	}
+
+	return skb;
+}
+
 static const struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] = {
 	[CTRL_ATTR_FAMILY_ID]	= { .type = NLA_U16 },
 	[CTRL_ATTR_FAMILY_NAME]	= { .type = NLA_NUL_STRING,
@@ -501,8 +712,8 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info)
 		goto errout;
 	}
 
-	msg = ctrl_build_msg(res, info->snd_pid, info->snd_seq,
-			     CTRL_CMD_NEWFAMILY);
+	msg = ctrl_build_family_msg(res, info->snd_pid, info->snd_seq,
+				    CTRL_CMD_NEWFAMILY);
 	if (IS_ERR(msg)) {
 		err = PTR_ERR(msg);
 		goto errout;
@@ -523,7 +734,15 @@ static int genl_ctrl_event(int event, void *data)
 	switch (event) {
 	case CTRL_CMD_NEWFAMILY:
 	case CTRL_CMD_DELFAMILY:
-		msg = ctrl_build_msg(data, 0, 0, event);
+		msg = ctrl_build_family_msg(data, 0, 0, event);
+		if (IS_ERR(msg))
+			return PTR_ERR(msg);
+
+		genlmsg_multicast(msg, 0, GENL_ID_CTRL, GFP_KERNEL);
+		break;
+	case CTRL_CMD_NEWMCAST_GRP:
+	case CTRL_CMD_DELMCAST_GRP:
+		msg = ctrl_build_mcgrp_msg(data, 0, 0, event);
 		if (IS_ERR(msg))
 			return PTR_ERR(msg);
 
@@ -541,6 +760,10 @@ static struct genl_ops genl_ctrl_ops = {
 	.policy		= ctrl_policy,
 };
 
+static struct genl_multicast_group notify_grp = {
+	.name		= "notify",
+};
+
 static int __init genl_init(void)
 {
 	int i, err;
@@ -557,11 +780,17 @@ static int __init genl_init(void)
 		goto errout_register;
 
 	netlink_set_nonroot(NETLINK_GENERIC, NL_NONROOT_RECV);
-	genl_sock = netlink_kernel_create(NETLINK_GENERIC, GENL_MAX_ID,
-					  genl_rcv, NULL, THIS_MODULE);
+
+	/* we'll bump the group number right afterwards */
+	genl_sock = netlink_kernel_create(NETLINK_GENERIC, 0, genl_rcv,
+					  NULL, THIS_MODULE);
 	if (genl_sock == NULL)
 		panic("GENL: Cannot initialize generic netlink\n");
 
+	err = genl_register_mc_group(&genl_ctrl, &notify_grp);
+	if (err < 0)
+		goto errout_register;
+
 	return 0;
 
 errout_register: