X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fnetlink%2Faf_netlink.c;h=98e313e5e59440f0ed2b8283532cea179d267238;hb=6ce59b460201c2281c2b6b3ead0b67ab21726268;hp=276131fe56dddb140afcfaf15e46bd6ead0263fa;hpb=6db5fc5d536560e31978c6911b1f5662e42083ac;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 276131f..98e313e 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -8,7 +8,7 @@
  *		modify it under the terms of the GNU General Public License
  *		as published by the Free Software Foundation; either version
  *		2 of the License, or (at your option) any later version.
- * 
+ *
  * Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith
  *                               added netlink_proto_exit
  * Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <acme@conectiva.com.br>
@@ -45,7 +45,6 @@
 #include <linux/rtnetlink.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/notifier.h>
 #include <linux/security.h>
 #include <linux/jhash.h>
@@ -56,12 +55,15 @@
 #include <linux/types.h>
 #include <linux/audit.h>
 #include <linux/selinux.h>
+#include <linux/mutex.h>
 
+#include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/scm.h>
 #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 */
@@ -76,8 +78,9 @@ struct netlink_sock {
 	unsigned long		state;
 	wait_queue_head_t	wait;
 	struct netlink_callback	*cb;
-	spinlock_t		cb_lock;
-	void			(*data_ready)(struct sock *sk, int bytes);
+	struct mutex		*cb_mutex;
+	struct mutex		cb_def_mutex;
+	void			(*netlink_rcv)(struct sk_buff *skb);
 	struct module		*module;
 };
 
@@ -86,7 +89,12 @@ struct netlink_sock {
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)
 {
-	return (struct netlink_sock *)sk;
+	return container_of(sk, struct netlink_sock, sk);
+}
+
+static inline int netlink_is_kernel(struct sock *sk)
+{
+	return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET;
 }
 
 struct nl_pid_hash {
@@ -108,6 +116,7 @@ struct netlink_table {
 	unsigned long *listeners;
 	unsigned int nl_nonroot;
 	unsigned int groups;
+	struct mutex *cb_mutex;
 	struct module *module;
 	int registered;
 };
@@ -136,6 +145,14 @@ static struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid)
 
 static void netlink_sock_destruct(struct sock *sk)
 {
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	if (nlk->cb) {
+		if (nlk->cb->done)
+			nlk->cb->done(nlk->cb);
+		netlink_destroy_callback(nlk->cb);
+	}
+
 	skb_queue_purge(&sk->sk_receive_queue);
 
 	if (!sock_flag(sk, SOCK_DEAD)) {
@@ -144,7 +161,6 @@ static void netlink_sock_destruct(struct sock *sk)
 	}
 	BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc));
 	BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
-	BUG_TRAP(!nlk_sk(sk)->cb);
 	BUG_TRAP(!nlk_sk(sk)->groups);
 }
 
@@ -199,7 +215,7 @@ netlink_unlock_table(void)
 		wake_up(&nl_table_wait);
 }
 
-static __inline__ struct sock *netlink_lookup(int protocol, u32 pid)
+static __inline__ struct sock *netlink_lookup(struct net *net, int protocol, u32 pid)
 {
 	struct nl_pid_hash *hash = &nl_table[protocol].hash;
 	struct hlist_head *head;
@@ -209,7 +225,7 @@ static __inline__ struct sock *netlink_lookup(int protocol, u32 pid)
 	read_lock(&nl_table_lock);
 	head = nl_pid_hashfn(hash, pid);
 	sk_for_each(sk, node, head) {
-		if (nlk_sk(sk)->pid == pid) {
+		if ((sk->sk_net == net) && (nlk_sk(sk)->pid == pid)) {
 			sock_hold(sk);
 			goto found;
 		}
@@ -304,17 +320,19 @@ 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
 	 * makes sure updates are visible before bind or setsockopt return. */
 }
 
-static int netlink_insert(struct sock *sk, u32 pid)
+static int netlink_insert(struct sock *sk, struct net *net, u32 pid)
 {
 	struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash;
 	struct hlist_head *head;
@@ -327,7 +345,7 @@ static int netlink_insert(struct sock *sk, u32 pid)
 	head = nl_pid_hashfn(hash, pid);
 	len = 0;
 	sk_for_each(osk, node, head) {
-		if (nlk_sk(osk)->pid == pid)
+		if ((osk->sk_net == net) && (nlk_sk(osk)->pid == pid))
 			break;
 		len++;
 	}
@@ -370,21 +388,27 @@ static struct proto netlink_proto = {
 	.obj_size = sizeof(struct netlink_sock),
 };
 
-static int __netlink_create(struct socket *sock, int protocol)
+static int __netlink_create(struct net *net, struct socket *sock,
+			    struct mutex *cb_mutex, int protocol)
 {
 	struct sock *sk;
 	struct netlink_sock *nlk;
 
 	sock->ops = &netlink_ops;
 
-	sk = sk_alloc(PF_NETLINK, GFP_KERNEL, &netlink_proto, 1);
+	sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, 1);
 	if (!sk)
 		return -ENOMEM;
 
 	sock_init_data(sock, sk);
 
 	nlk = nlk_sk(sk);
-	spin_lock_init(&nlk->cb_lock);
+	if (cb_mutex)
+		nlk->cb_mutex = cb_mutex;
+	else {
+		nlk->cb_mutex = &nlk->cb_def_mutex;
+		mutex_init(nlk->cb_mutex);
+	}
 	init_waitqueue_head(&nlk->wait);
 
 	sk->sk_destruct = netlink_sock_destruct;
@@ -392,11 +416,11 @@ static int __netlink_create(struct socket *sock, int protocol)
 	return 0;
 }
 
-static int netlink_create(struct socket *sock, int protocol)
+static int netlink_create(struct net *net, struct socket *sock, int protocol)
 {
 	struct module *module = NULL;
+	struct mutex *cb_mutex;
 	struct netlink_sock *nlk;
-	unsigned int groups;
 	int err = 0;
 
 	sock->state = SS_UNCONNECTED;
@@ -418,10 +442,10 @@ static int netlink_create(struct socket *sock, int protocol)
 	if (nl_table[protocol].registered &&
 	    try_module_get(nl_table[protocol].module))
 		module = nl_table[protocol].module;
-	groups = nl_table[protocol].groups;
+	cb_mutex = nl_table[protocol].cb_mutex;
 	netlink_unlock_table();
 
-	if ((err = __netlink_create(sock, protocol)) < 0)
+	if ((err = __netlink_create(net, sock, cb_mutex, protocol)) < 0)
 		goto out_module;
 
 	nlk = nlk_sk(sock->sk);
@@ -443,21 +467,14 @@ static int netlink_release(struct socket *sock)
 		return 0;
 
 	netlink_remove(sk);
+	sock_orphan(sk);
 	nlk = nlk_sk(sk);
 
-	spin_lock(&nlk->cb_lock);
-	if (nlk->cb) {
-		if (nlk->cb->done)
-			nlk->cb->done(nlk->cb);
-		netlink_destroy_callback(nlk->cb);
-		nlk->cb = NULL;
-	}
-	spin_unlock(&nlk->cb_lock);
-
-	/* OK. Socket is unlinked, and, therefore,
-	   no new packets will arrive */
+	/*
+	 * OK. Socket is unlinked, any packets that arrive now
+	 * will be purged.
+	 */
 
-	sock_orphan(sk);
 	sock->sk = NULL;
 	wake_up_interruptible_all(&nlk->wait);
 
@@ -465,18 +482,18 @@ static int netlink_release(struct socket *sock)
 
 	if (nlk->pid && !nlk->subscriptions) {
 		struct netlink_notify n = {
+						.net = sk->sk_net,
 						.protocol = sk->sk_protocol,
 						.pid = nlk->pid,
 					  };
 		atomic_notifier_call_chain(&netlink_chain,
 				NETLINK_URELEASE, &n);
-	}	
+	}
 
-	if (nlk->module)
-		module_put(nlk->module);
+	module_put(nlk->module);
 
 	netlink_table_grab();
-	if (nlk->flags & NETLINK_KERNEL_SOCKET) {
+	if (netlink_is_kernel(sk)) {
 		kfree(nl_table[sk->sk_protocol].listeners);
 		nl_table[sk->sk_protocol].module = NULL;
 		nl_table[sk->sk_protocol].registered = 0;
@@ -494,6 +511,7 @@ static int netlink_release(struct socket *sock)
 static int netlink_autobind(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
+	struct net *net = sk->sk_net;
 	struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash;
 	struct hlist_head *head;
 	struct sock *osk;
@@ -507,6 +525,8 @@ retry:
 	netlink_table_grab();
 	head = nl_pid_hashfn(hash, pid);
 	sk_for_each(osk, node, head) {
+		if ((osk->sk_net != net))
+			continue;
 		if (nlk_sk(osk)->pid == pid) {
 			/* Bind collision, search negative pid values. */
 			pid = rover--;
@@ -518,7 +538,7 @@ retry:
 	}
 	netlink_table_ungrab();
 
-	err = netlink_insert(sk, pid);
+	err = netlink_insert(sk, net, pid);
 	if (err == -EADDRINUSE)
 		goto retry;
 
@@ -529,11 +549,11 @@ retry:
 	return err;
 }
 
-static inline int netlink_capable(struct socket *sock, unsigned int flag) 
-{ 
+static inline int netlink_capable(struct socket *sock, unsigned int flag)
+{
 	return (nl_table[sock->sk->sk_protocol].nl_nonroot & flag) ||
 	       capable(CAP_NET_ADMIN);
-} 
+}
 
 static void
 netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions)
@@ -547,35 +567,47 @@ 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)
 {
 	struct sock *sk = sock->sk;
+	struct net *net = sk->sk_net;
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err;
-	
+
 	if (nladdr->nl_family != AF_NETLINK)
 		return -EINVAL;
 
@@ -583,11 +615,9 @@ 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) {
@@ -595,7 +625,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len
 			return -EINVAL;
 	} else {
 		err = nladdr->nl_pid ?
-			netlink_insert(sk, nladdr->nl_pid) :
+			netlink_insert(sk, net, nladdr->nl_pid) :
 			netlink_autobind(sock);
 		if (err)
 			return err;
@@ -606,9 +636,9 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len
 
 	netlink_table_grab();
 	netlink_update_subscriptions(sk, nlk->subscriptions +
-	                                 hweight32(nladdr->nl_groups) -
-	                                 hweight32(nlk->groups[0]));
-	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups; 
+					 hweight32(nladdr->nl_groups) -
+					 hweight32(nlk->groups[0]));
+	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups;
 	netlink_update_listeners(sk);
 	netlink_table_ungrab();
 
@@ -653,7 +683,7 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, int *addr
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct sockaddr_nl *nladdr=(struct sockaddr_nl *)addr;
-	
+
 	nladdr->nl_family = AF_NETLINK;
 	nladdr->nl_pad = 0;
 	*addr_len = sizeof(*nladdr);
@@ -678,19 +708,17 @@ static void netlink_overrun(struct sock *sk)
 
 static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid)
 {
-	int protocol = ssk->sk_protocol;
 	struct sock *sock;
 	struct netlink_sock *nlk;
 
-	sock = netlink_lookup(protocol, pid);
+	sock = netlink_lookup(ssk->sk_net, ssk->sk_protocol, pid);
 	if (!sock)
 		return ERR_PTR(-ECONNREFUSED);
 
 	/* Don't bother queuing skb if kernel socket has no input function */
 	nlk = nlk_sk(sock);
-	if ((nlk->pid == 0 && !nlk->data_ready) ||
-	    (sock->sk_state == NETLINK_CONNECTED &&
-	     nlk->dst_pid != nlk_sk(ssk)->pid)) {
+	if (sock->sk_state == NETLINK_CONNECTED &&
+	    nlk->dst_pid != nlk_sk(ssk)->pid) {
 		sock_put(sock);
 		return ERR_PTR(-ECONNREFUSED);
 	}
@@ -734,7 +762,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock,
 	    test_bit(0, &nlk->state)) {
 		DECLARE_WAITQUEUE(wait, current);
 		if (!timeo) {
-			if (!ssk || nlk_sk(ssk)->pid == 0)
+			if (!ssk || netlink_is_kernel(ssk))
 				netlink_overrun(sk);
 			sock_put(sk);
 			kfree_skb(skb);
@@ -763,7 +791,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock,
 	return 0;
 }
 
-int netlink_sendskb(struct sock *sk, struct sk_buff *skb, int protocol)
+int netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 {
 	int len = skb->len;
 
@@ -804,7 +832,34 @@ static inline struct sk_buff *netlink_trim(struct sk_buff *skb,
 	return skb;
 }
 
-int netlink_unicast(struct sock *ssk, struct sk_buff *skb, u32 pid, int nonblock)
+static inline void netlink_rcv_wake(struct sock *sk)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	if (skb_queue_empty(&sk->sk_receive_queue))
+		clear_bit(0, &nlk->state);
+	if (!test_bit(0, &nlk->state))
+		wake_up_interruptible(&nlk->wait);
+}
+
+static inline int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb)
+{
+	int ret;
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	ret = -ECONNREFUSED;
+	if (nlk->netlink_rcv != NULL) {
+		ret = skb->len;
+		skb_set_owner_r(skb, sk);
+		nlk->netlink_rcv(skb);
+	}
+	kfree_skb(skb);
+	sock_put(sk);
+	return ret;
+}
+
+int netlink_unicast(struct sock *ssk, struct sk_buff *skb,
+		    u32 pid, int nonblock)
 {
 	struct sock *sk;
 	int err;
@@ -819,22 +874,33 @@ retry:
 		kfree_skb(skb);
 		return PTR_ERR(sk);
 	}
+	if (netlink_is_kernel(sk))
+		return netlink_unicast_kernel(sk, skb);
+
 	err = netlink_attachskb(sk, skb, nonblock, timeo, ssk);
 	if (err == 1)
 		goto retry;
 	if (err)
 		return err;
 
-	return netlink_sendskb(sk, skb, ssk->sk_protocol);
+	return netlink_sendskb(sk, skb);
 }
 
 int netlink_has_listeners(struct sock *sk, unsigned int group)
 {
 	int res = 0;
+	unsigned long *listeners;
+
+	BUG_ON(!netlink_is_kernel(sk));
+
+	rcu_read_lock();
+	listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners);
 
-	BUG_ON(!(nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET));
 	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);
@@ -855,6 +921,7 @@ static __inline__ int netlink_broadcast_deliver(struct sock *sk, struct sk_buff
 
 struct netlink_broadcast_data {
 	struct sock *exclude_sk;
+	struct net *net;
 	u32 pid;
 	u32 group;
 	int failure;
@@ -877,6 +944,9 @@ static inline int do_one_broadcast(struct sock *sk,
 	    !test_bit(p->group - 1, nlk->groups))
 		goto out;
 
+	if ((sk->sk_net != p->net))
+		goto out;
+
 	if (p->failure) {
 		netlink_overrun(sk);
 		goto out;
@@ -915,6 +985,7 @@ out:
 int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
 		      u32 group, gfp_t allocation)
 {
+	struct net *net = ssk->sk_net;
 	struct netlink_broadcast_data info;
 	struct hlist_node *node;
 	struct sock *sk;
@@ -922,6 +993,7 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
 	skb = netlink_trim(skb, allocation);
 
 	info.exclude_sk = ssk;
+	info.net = net;
 	info.pid = pid;
 	info.group = group;
 	info.failure = 0;
@@ -970,6 +1042,9 @@ static inline int do_one_set_err(struct sock *sk,
 	if (sk == p->exclude_sk)
 		goto out;
 
+	if (sk->sk_net != p->exclude_sk->sk_net)
+		goto out;
+
 	if (nlk->pid == p->pid || p->group - 1 >= nlk->ngroups ||
 	    !test_bit(p->group - 1, nlk->groups))
 		goto out;
@@ -999,18 +1074,36 @@ 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)
+			      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) {
@@ -1023,27 +1116,16 @@ 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;
@@ -1055,7 +1137,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 }
 
 static int netlink_getsockopt(struct socket *sock, int level, int optname,
-                              char __user *optval, int __user *optlen)
+			      char __user *optval, int __user *optlen)
 {
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -1094,16 +1176,6 @@ static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info);
 }
 
-static inline void netlink_rcv_wake(struct sock *sk)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (skb_queue_empty(&sk->sk_receive_queue))
-		clear_bit(0, &nlk->state);
-	if (!test_bit(0, &nlk->state))
-		wake_up_interruptible(&nlk->wait);
-}
-
 static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			   struct msghdr *msg, size_t len)
 {
@@ -1216,7 +1288,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 		copied = len;
 	}
 
-	skb->h.raw = skb->data;
+	skb_reset_transport_header(skb);
 	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
 
 	if (msg->msg_name) {
@@ -1236,13 +1308,14 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 		siocb->scm = &scm;
 	}
 	siocb->scm->creds = *NETLINK_CREDS(skb);
+	if (flags & MSG_TRUNC)
+		copied = skb->len;
 	skb_free_datagram(sk, skb);
 
 	if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2)
 		netlink_dump(sk);
 
 	scm_recv(sock, msg, siocb->scm, flags);
-
 out:
 	netlink_rcv_wake(sk);
 	return err ? : copied;
@@ -1250,23 +1323,19 @@ out:
 
 static void netlink_data_ready(struct sock *sk, int len)
 {
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (nlk->data_ready)
-		nlk->data_ready(sk, len);
-	netlink_rcv_wake(sk);
+	BUG();
 }
 
 /*
- *	We export these functions to other modules. They provide a 
+ *	We export these functions to other modules. They provide a
  *	complete set of kernel non-blocking support for message
  *	queueing.
  */
 
 struct sock *
-netlink_kernel_create(int unit, unsigned int groups,
-                      void (*input)(struct sock *sk, int len),
-                      struct module *module)
+netlink_kernel_create(struct net *net, int unit, unsigned int groups,
+		      void (*input)(struct sk_buff *skb),
+		      struct mutex *cb_mutex, struct module *module)
 {
 	struct socket *sock;
 	struct sock *sk;
@@ -1281,7 +1350,7 @@ netlink_kernel_create(int unit, unsigned int groups,
 	if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock))
 		return NULL;
 
-	if (__netlink_create(sock, unit) < 0)
+	if (__netlink_create(net, sock, cb_mutex, unit) < 0)
 		goto out_sock_release;
 
 	if (groups < 32)
@@ -1294,19 +1363,24 @@ netlink_kernel_create(int unit, unsigned int groups,
 	sk = sock->sk;
 	sk->sk_data_ready = netlink_data_ready;
 	if (input)
-		nlk_sk(sk)->data_ready = input;
+		nlk_sk(sk)->netlink_rcv = input;
 
-	if (netlink_insert(sk, 0))
+	if (netlink_insert(sk, net, 0))
 		goto out_sock_release;
 
 	nlk = nlk_sk(sk);
 	nlk->flags |= NETLINK_KERNEL_SOCKET;
 
 	netlink_table_grab();
-	nl_table[unit].groups = groups;
-	nl_table[unit].listeners = listeners;
-	nl_table[unit].module = module;
-	nl_table[unit].registered = 1;
+	if (!nl_table[unit].registered) {
+		nl_table[unit].groups = groups;
+		nl_table[unit].listeners = listeners;
+		nl_table[unit].cb_mutex = cb_mutex;
+		nl_table[unit].module = module;
+		nl_table[unit].registered = 1;
+	} else {
+		kfree(listeners);
+	}
 	netlink_table_ungrab();
 
 	return sk;
@@ -1317,11 +1391,76 @@ 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) 
+{
+	if ((unsigned int)protocol < MAX_LINKS)
 		nl_table[protocol].nl_nonroot = flags;
-} 
+}
 
 static void netlink_destroy_callback(struct netlink_callback *cb)
 {
@@ -1342,12 +1481,12 @@ static int netlink_dump(struct sock *sk)
 	struct sk_buff *skb;
 	struct nlmsghdr *nlh;
 	int len, err = -ENOBUFS;
-	
+
 	skb = sock_rmalloc(sk, NLMSG_GOODSIZE, 0, GFP_KERNEL);
 	if (!skb)
 		goto errout;
 
-	spin_lock(&nlk->cb_lock);
+	mutex_lock(nlk->cb_mutex);
 
 	cb = nlk->cb;
 	if (cb == NULL) {
@@ -1358,7 +1497,7 @@ static int netlink_dump(struct sock *sk)
 	len = cb->dump(skb, cb);
 
 	if (len > 0) {
-		spin_unlock(&nlk->cb_lock);
+		mutex_unlock(nlk->cb_mutex);
 		skb_queue_tail(&sk->sk_receive_queue, skb);
 		sk->sk_data_ready(sk, len);
 		return 0;
@@ -1376,13 +1515,13 @@ static int netlink_dump(struct sock *sk)
 	if (cb->done)
 		cb->done(cb);
 	nlk->cb = NULL;
-	spin_unlock(&nlk->cb_lock);
+	mutex_unlock(nlk->cb_mutex);
 
 	netlink_destroy_callback(cb);
 	return 0;
 
 errout_skb:
-	spin_unlock(&nlk->cb_lock);
+	mutex_unlock(nlk->cb_mutex);
 	kfree_skb(skb);
 errout:
 	return err;
@@ -1407,22 +1546,22 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	atomic_inc(&skb->users);
 	cb->skb = skb;
 
-	sk = netlink_lookup(ssk->sk_protocol, NETLINK_CB(skb).pid);
+	sk = netlink_lookup(ssk->sk_net, ssk->sk_protocol, NETLINK_CB(skb).pid);
 	if (sk == NULL) {
 		netlink_destroy_callback(cb);
 		return -ECONNREFUSED;
 	}
 	nlk = nlk_sk(sk);
 	/* A dump is in progress... */
-	spin_lock(&nlk->cb_lock);
+	mutex_lock(nlk->cb_mutex);
 	if (nlk->cb) {
-		spin_unlock(&nlk->cb_lock);
+		mutex_unlock(nlk->cb_mutex);
 		netlink_destroy_callback(cb);
 		sock_put(sk);
 		return -EBUSY;
 	}
 	nlk->cb = cb;
-	spin_unlock(&nlk->cb_lock);
+	mutex_unlock(nlk->cb_mutex);
 
 	netlink_dump(sk);
 	sock_put(sk);
@@ -1444,7 +1583,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
 	if (!skb) {
 		struct sock *sk;
 
-		sk = netlink_lookup(in_skb->sk->sk_protocol,
+		sk = netlink_lookup(in_skb->sk->sk_net,
+				    in_skb->sk->sk_protocol,
 				    NETLINK_CB(in_skb).pid);
 		if (sk) {
 			sk->sk_err = ENOBUFS;
@@ -1462,90 +1602,41 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
 	netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT);
 }
 
-static int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
-						     struct nlmsghdr *, int *))
+int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
+						     struct nlmsghdr *))
 {
 	struct nlmsghdr *nlh;
 	int err;
 
 	while (skb->len >= nlmsg_total_size(0)) {
-		nlh = (struct nlmsghdr *) skb->data;
+		int msglen;
+
+		nlh = nlmsg_hdr(skb);
+		err = 0;
 
 		if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len)
 			return 0;
 
-		if (cb(skb, nlh, &err) < 0) {
-			/* Not an error, but we have to interrupt processing
-			 * here. Note: that in this case we do not pull
-			 * message from skb, it will be processed later.
-			 */
-			if (err == 0)
-				return -1;
-			netlink_ack(skb, nlh, err);
-		} else if (nlh->nlmsg_flags & NLM_F_ACK)
-			netlink_ack(skb, nlh, 0);
-
-		netlink_queue_skip(nlh, skb);
-	}
+		/* Only requests are handled by the kernel */
+		if (!(nlh->nlmsg_flags & NLM_F_REQUEST))
+			goto skip;
 
-	return 0;
-}
+		/* Skip control messages */
+		if (nlh->nlmsg_type < NLMSG_MIN_TYPE)
+			goto skip;
 
-/**
- * nelink_run_queue - Process netlink receive queue.
- * @sk: Netlink socket containing the queue
- * @qlen: Place to store queue length upon entry
- * @cb: Callback function invoked for each netlink message found
- *
- * Processes as much as there was in the queue upon entry and invokes
- * a callback function for each netlink message found. The callback
- * function may refuse a message by returning a negative error code
- * but setting the error pointer to 0 in which case this function
- * returns with a qlen != 0.
- *
- * qlen must be initialized to 0 before the initial entry, afterwards
- * the function may be called repeatedly until qlen reaches 0.
- */
-void netlink_run_queue(struct sock *sk, unsigned int *qlen,
-		       int (*cb)(struct sk_buff *, struct nlmsghdr *, int *))
-{
-	struct sk_buff *skb;
-
-	if (!*qlen || *qlen > skb_queue_len(&sk->sk_receive_queue))
-		*qlen = skb_queue_len(&sk->sk_receive_queue);
-
-	for (; *qlen; (*qlen)--) {
-		skb = skb_dequeue(&sk->sk_receive_queue);
-		if (netlink_rcv_skb(skb, cb)) {
-			if (skb->len)
-				skb_queue_head(&sk->sk_receive_queue, skb);
-			else {
-				kfree_skb(skb);
-				(*qlen)--;
-			}
-			break;
-		}
+		err = cb(skb, nlh);
+skip:
+		if (nlh->nlmsg_flags & NLM_F_ACK || err)
+			netlink_ack(skb, nlh, err);
 
-		kfree_skb(skb);
+	        msglen = NLMSG_ALIGN(nlh->nlmsg_len);
+		if (msglen > skb->len)
+			msglen = skb->len;
+		skb_pull(skb, msglen);
 	}
-}
-
-/**
- * netlink_queue_skip - Skip netlink message while processing queue.
- * @nlh: Netlink message to be skipped
- * @skb: Socket buffer containing the netlink messages.
- *
- * Pulls the given netlink message off the socket buffer so the next
- * call to netlink_queue_run() will not reconsider the message.
- */
-void netlink_queue_skip(struct nlmsghdr *nlh, struct sk_buff *skb)
-{
-	int msglen = NLMSG_ALIGN(nlh->nlmsg_len);
 
-	if (msglen > skb->len)
-		msglen = skb->len;
-
-	skb_pull(skb, msglen);
+	return 0;
 }
 
 /**
@@ -1582,6 +1673,7 @@ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 pid,
 
 #ifdef CONFIG_PROC_FS
 struct nl_seq_iter {
+	struct net *net;
 	int link;
 	int hash_idx;
 };
@@ -1599,6 +1691,8 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos)
 
 		for (j = 0; j <= hash->mask; j++) {
 			sk_for_each(s, node, &hash->table[j]) {
+				if (iter->net != s->sk_net)
+					continue;
 				if (off == pos) {
 					iter->link = i;
 					iter->hash_idx = j;
@@ -1627,12 +1721,15 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 	if (v == SEQ_START_TOKEN)
 		return netlink_seq_socket_idx(seq, 0);
-		
-	s = sk_next(v);
+
+	iter = seq->private;
+	s = v;
+	do {
+		s = sk_next(s);
+	} while (s && (iter->net != s->sk_net));
 	if (s)
 		return s;
 
-	iter = seq->private;
 	i = iter->link;
 	j = iter->hash_idx + 1;
 
@@ -1641,6 +1738,8 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 		for (; j <= hash->mask; j++) {
 			s = sk_head(&hash->table[j]);
+			while (s && (iter->net != s->sk_net))
+				s = sk_next(s);
 			if (s) {
 				iter->link = i;
 				iter->hash_idx = j;
@@ -1685,7 +1784,7 @@ 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,
@@ -1695,31 +1794,35 @@ static struct seq_operations netlink_seq_ops = {
 
 static int netlink_seq_open(struct inode *inode, struct file *file)
 {
-	struct seq_file *seq;
 	struct nl_seq_iter *iter;
-	int err;
 
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+	iter = __seq_open_private(file, &netlink_seq_ops, sizeof(*iter));
 	if (!iter)
 		return -ENOMEM;
 
-	err = seq_open(file, &netlink_seq_ops);
-	if (err) {
-		kfree(iter);
-		return err;
+	iter->net = get_proc_net(inode);
+	if (!iter->net) {
+		seq_release_private(inode, file);
+		return -ENXIO;
 	}
 
-	seq = file->private_data;
-	seq->private = iter;
 	return 0;
 }
 
-static struct file_operations netlink_seq_fops = {
+static int netlink_seq_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct nl_seq_iter *iter = seq->private;
+	put_net(iter->net);
+	return seq_release_private(inode, file);
+}
+
+static const struct file_operations netlink_seq_fops = {
 	.owner		= THIS_MODULE,
 	.open		= netlink_seq_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= netlink_seq_release,
 };
 
 #endif
@@ -1733,7 +1836,7 @@ int netlink_unregister_notifier(struct notifier_block *nb)
 {
 	return atomic_notifier_chain_unregister(&netlink_chain, nb);
 }
-                
+
 static const struct proto_ops netlink_ops = {
 	.family =	PF_NETLINK,
 	.owner =	THIS_MODULE,
@@ -1761,11 +1864,32 @@ static struct net_proto_family netlink_family_ops = {
 	.owner	= THIS_MODULE,	/* for consistency 8) */
 };
 
+static int __net_init netlink_net_init(struct net *net)
+{
+#ifdef CONFIG_PROC_FS
+	if (!proc_net_fops_create(net, "netlink", 0, &netlink_seq_fops))
+		return -ENOMEM;
+#endif
+	return 0;
+}
+
+static void __net_exit netlink_net_exit(struct net *net)
+{
+#ifdef CONFIG_PROC_FS
+	proc_net_remove(net, "netlink");
+#endif
+}
+
+static struct pernet_operations __net_initdata netlink_net_ops = {
+	.init = netlink_net_init,
+	.exit = netlink_net_exit,
+};
+
 static int __init netlink_proto_init(void)
 {
 	struct sk_buff *dummy_skb;
 	int i;
-	unsigned long max;
+	unsigned long limit;
 	unsigned int order;
 	int err = proto_register(&netlink_proto, 0);
 
@@ -1779,13 +1903,13 @@ static int __init netlink_proto_init(void)
 		goto panic;
 
 	if (num_physpages >= (128 * 1024))
-		max = num_physpages >> (21 - PAGE_SHIFT);
+		limit = num_physpages >> (21 - PAGE_SHIFT);
 	else
-		max = num_physpages >> (23 - PAGE_SHIFT);
+		limit = num_physpages >> (23 - PAGE_SHIFT);
 
-	order = get_bitmask_order(max) - 1 + PAGE_SHIFT;
-	max = (1UL << order) / sizeof(struct hlist_head);
-	order = get_bitmask_order(max > UINT_MAX ? UINT_MAX : max) - 1;
+	order = get_bitmask_order(limit) - 1 + PAGE_SHIFT;
+	limit = (1UL << order) / sizeof(struct hlist_head);
+	order = get_bitmask_order(min(limit, (unsigned long)UINT_MAX)) - 1;
 
 	for (i = 0; i < MAX_LINKS; i++) {
 		struct nl_pid_hash *hash = &nl_table[i].hash;
@@ -1806,10 +1930,8 @@ static int __init netlink_proto_init(void)
 	}
 
 	sock_register(&netlink_family_ops);
-#ifdef CONFIG_PROC_FS
-	proc_net_fops_create("netlink", 0, &netlink_seq_fops);
-#endif
-	/* The netlink device handler may be needed early. */ 
+	register_pernet_subsys(&netlink_net_ops);
+	/* The netlink device handler may be needed early. */
 	rtnetlink_init();
 out:
 	return err;
@@ -1820,13 +1942,11 @@ panic:
 core_initcall(netlink_proto_init);
 
 EXPORT_SYMBOL(netlink_ack);
-EXPORT_SYMBOL(netlink_run_queue);
-EXPORT_SYMBOL(netlink_queue_skip);
+EXPORT_SYMBOL(netlink_rcv_skb);
 EXPORT_SYMBOL(netlink_broadcast);
 EXPORT_SYMBOL(netlink_dump_start);
 EXPORT_SYMBOL(netlink_kernel_create);
 EXPORT_SYMBOL(netlink_register_notifier);
-EXPORT_SYMBOL(netlink_set_err);
 EXPORT_SYMBOL(netlink_set_nonroot);
 EXPORT_SYMBOL(netlink_unicast);
 EXPORT_SYMBOL(netlink_unregister_notifier);