4 files changed, 252 insertions, 196 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index ef5f77b44ec7..2702673f0f23 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -61,6 +61,7 @@
 #include <linux/rhashtable.h>
 #include <asm/cacheflush.h>
 #include <linux/hash.h>
+#include <linux/genetlink.h>
 
 #include <net/net_namespace.h>
 #include <net/sock.h>
@@ -97,12 +98,12 @@ static int netlink_dump(struct sock *sk);
 static void netlink_skb_destructor(struct sk_buff *skb);
 
 /* nl_table locking explained:
- * Lookup and traversal are protected with nl_sk_hash_lock or nl_table_lock
- * combined with an RCU read-side lock. Insertion and removal are protected
- * with nl_sk_hash_lock while using RCU list modification primitives and may
- * run in parallel to nl_table_lock protected lookups. Destruction of the
- * Netlink socket may only occur *after* nl_table_lock has been acquired
- * either during or after the socket has been removed from the list.
+ * Lookup and traversal are protected with an RCU read-side lock. Insertion
+ * and removal are protected with per bucket lock while using RCU list
+ * modification primitives and may run in parallel to RCU protected lookups.
+ * Destruction of the Netlink socket may only occur *after* nl_table_lock has
+ * been acquired * either during or after the socket has been removed from
+ * the list and after an RCU grace period.
  */
 DEFINE_RWLOCK(nl_table_lock);
 EXPORT_SYMBOL_GPL(nl_table_lock);
@@ -110,19 +111,6 @@ static atomic_t nl_table_users = ATOMIC_INIT(0);
 
 #define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock));
 
-/* Protects netlink socket hash table mutations */
-DEFINE_MUTEX(nl_sk_hash_lock);
-EXPORT_SYMBOL_GPL(nl_sk_hash_lock);
-
-#ifdef CONFIG_PROVE_LOCKING
-static int lockdep_nl_sk_hash_is_held(void *parent)
-{
-	if (debug_locks)
-		return lockdep_is_held(&nl_sk_hash_lock) || lockdep_is_held(&nl_table_lock);
-	return 1;
-}
-#endif
-
 static ATOMIC_NOTIFIER_HEAD(netlink_chain);
 
 static DEFINE_SPINLOCK(netlink_tap_lock);
@@ -525,14 +513,14 @@ out:
 	return err;
 }
 
-static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr)
+static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len)
 {
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
 	struct page *p_start, *p_end;
 
 	/* First page is flushed through netlink_{get,set}_status */
 	p_start = pgvec_to_page(hdr + PAGE_SIZE);
-	p_end   = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + hdr->nm_len - 1);
+	p_end   = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1);
 	while (p_start <= p_end) {
 		flush_dcache_page(p_start);
 		p_start++;
@@ -550,9 +538,9 @@ static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr)
 static void netlink_set_status(struct nl_mmap_hdr *hdr,
 			       enum nl_mmap_status status)
 {
+	smp_mb();
 	hdr->nm_status = status;
 	flush_dcache_page(pgvec_to_page(hdr));
-	smp_wmb();
 }
 
 static struct nl_mmap_hdr *
@@ -707,31 +695,23 @@ static void netlink_ring_setup_skb(struct sk_buff *skb, struct sock *sk,
 
 static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 				u32 dst_portid, u32 dst_group,
-				struct sock_iocb *siocb)
+				struct scm_cookie *scm)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ring *ring;
 	struct nl_mmap_hdr *hdr;
 	struct sk_buff *skb;
 	unsigned int maxlen;
-	bool excl = true;
 	int err = 0, len = 0;
 
-	/* Netlink messages are validated by the receiver before processing.
-	 * In order to avoid userspace changing the contents of the message
-	 * after validation, the socket and the ring may only be used by a
-	 * single process, otherwise we fall back to copying.
-	 */
-	if (atomic_long_read(&sk->sk_socket->file->f_count) > 1 ||
-	    atomic_read(&nlk->mapped) > 1)
-		excl = false;
-
 	mutex_lock(&nlk->pg_vec_lock);
 
 	ring   = &nlk->tx_ring;
 	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
 
 	do {
+		unsigned int nm_len;
+
 		hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID);
 		if (hdr == NULL) {
 			if (!(msg->msg_flags & MSG_DONTWAIT) &&
@@ -739,41 +719,29 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 				schedule();
 			continue;
 		}
-		if (hdr->nm_len > maxlen) {
+
+		nm_len = ACCESS_ONCE(hdr->nm_len);
+		if (nm_len > maxlen) {
 			err = -EINVAL;
 			goto out;
 		}
 
-		netlink_frame_flush_dcache(hdr);
+		netlink_frame_flush_dcache(hdr, nm_len);
 
-		if (likely(dst_portid == 0 && dst_group == 0 && excl)) {
-			skb = alloc_skb_head(GFP_KERNEL);
-			if (skb == NULL) {
-				err = -ENOBUFS;
-				goto out;
-			}
-			sock_hold(sk);
-			netlink_ring_setup_skb(skb, sk, ring, hdr);
-			NETLINK_CB(skb).flags |= NETLINK_SKB_TX;
-			__skb_put(skb, hdr->nm_len);
-			netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED);
-			atomic_inc(&ring->pending);
-		} else {
-			skb = alloc_skb(hdr->nm_len, GFP_KERNEL);
-			if (skb == NULL) {
-				err = -ENOBUFS;
-				goto out;
-			}
-			__skb_put(skb, hdr->nm_len);
-			memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, hdr->nm_len);
-			netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
+		skb = alloc_skb(nm_len, GFP_KERNEL);
+		if (skb == NULL) {
+			err = -ENOBUFS;
+			goto out;
 		}
+		__skb_put(skb, nm_len);
+		memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len);
+		netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
 
 		netlink_increment_head(ring);
 
 		NETLINK_CB(skb).portid	  = nlk->portid;
 		NETLINK_CB(skb).dst_group = dst_group;
-		NETLINK_CB(skb).creds	  = siocb->scm->creds;
+		NETLINK_CB(skb).creds	  = scm->creds;
 
 		err = security_netlink_send(sk, skb);
 		if (err) {
@@ -813,7 +781,7 @@ static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb)
 	hdr->nm_pid	= NETLINK_CB(skb).creds.pid;
 	hdr->nm_uid	= from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid);
 	hdr->nm_gid	= from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid);
-	netlink_frame_flush_dcache(hdr);
+	netlink_frame_flush_dcache(hdr, hdr->nm_len);
 	netlink_set_status(hdr, NL_MMAP_STATUS_VALID);
 
 	NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED;
@@ -852,7 +820,7 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 #define netlink_tx_is_mmaped(sk)	false
 #define netlink_mmap			sock_no_mmap
 #define netlink_poll			datagram_poll
-#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, siocb)	0
+#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, scm)	0
 #endif /* CONFIG_NETLINK_MMAP */
 
 static void netlink_skb_destructor(struct sk_buff *skb)
@@ -1022,26 +990,33 @@ static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid,
 		.net = net,
 		.portid = portid,
 	};
-	u32 hash;
-
-	hash = rhashtable_hashfn(&table->hash, &portid, sizeof(portid));
 
-	return rhashtable_lookup_compare(&table->hash, hash,
+	return rhashtable_lookup_compare(&table->hash, &portid,
 					 &netlink_compare, &arg);
 }
 
+static bool __netlink_insert(struct netlink_table *table, struct sock *sk)
+{
+	struct netlink_compare_arg arg = {
+		.net = sock_net(sk),
+		.portid = nlk_sk(sk)->portid,
+	};
+
+	return rhashtable_lookup_compare_insert(&table->hash,
+						&nlk_sk(sk)->node,
+						&netlink_compare, &arg);
+}
+
 static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid)
 {
 	struct netlink_table *table = &nl_table[protocol];
 	struct sock *sk;
 
-	read_lock(&nl_table_lock);
 	rcu_read_lock();
 	sk = __netlink_lookup(table, portid, net);
 	if (sk)
 		sock_hold(sk);
 	rcu_read_unlock();
-	read_unlock(&nl_table_lock);
 
 	return sk;
 }
@@ -1072,29 +1047,33 @@ netlink_update_listeners(struct sock *sk)
 	 * makes sure updates are visible before bind or setsockopt return. */
 }
 
-static int netlink_insert(struct sock *sk, struct net *net, u32 portid)
+static int netlink_insert(struct sock *sk, u32 portid)
 {
 	struct netlink_table *table = &nl_table[sk->sk_protocol];
-	int err = -EADDRINUSE;
+	int err;
 
-	mutex_lock(&nl_sk_hash_lock);
-	if (__netlink_lookup(table, portid, net))
-		goto err;
+	lock_sock(sk);
 
 	err = -EBUSY;
 	if (nlk_sk(sk)->portid)
 		goto err;
 
 	err = -ENOMEM;
-	if (BITS_PER_LONG > 32 && unlikely(table->hash.nelems >= UINT_MAX))
+	if (BITS_PER_LONG > 32 &&
+	    unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX))
 		goto err;
 
 	nlk_sk(sk)->portid = portid;
 	sock_hold(sk);
-	rhashtable_insert(&table->hash, &nlk_sk(sk)->node);
+
 	err = 0;
+	if (!__netlink_insert(table, sk)) {
+		err = -EADDRINUSE;
+		sock_put(sk);
+	}
+
 err:
-	mutex_unlock(&nl_sk_hash_lock);
+	release_sock(sk);
 	return err;
 }
 
@@ -1102,17 +1081,19 @@ static void netlink_remove(struct sock *sk)
 {
 	struct netlink_table *table;
 
-	mutex_lock(&nl_sk_hash_lock);
 	table = &nl_table[sk->sk_protocol];
 	if (rhashtable_remove(&table->hash, &nlk_sk(sk)->node)) {
 		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
 		__sock_put(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);
+	}
+	if (sk->sk_protocol == NETLINK_GENERIC)
+		atomic_inc(&genl_sk_destructing_cnt);
 	netlink_table_ungrab();
 }
 
@@ -1159,8 +1140,8 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	struct module *module = NULL;
 	struct mutex *cb_mutex;
 	struct netlink_sock *nlk;
-	int (*bind)(int group);
-	void (*unbind)(int group);
+	int (*bind)(struct net *net, int group);
+	void (*unbind)(struct net *net, int group);
 	int err = 0;
 
 	sock->state = SS_UNCONNECTED;
@@ -1212,6 +1193,13 @@ out_module:
 	goto out;
 }
 
+static void deferred_put_nlk_sk(struct rcu_head *head)
+{
+	struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
+
+	sock_put(&nlk->sk);
+}
+
 static int netlink_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
@@ -1229,6 +1217,20 @@ static int netlink_release(struct socket *sock)
 	 * will be purged.
 	 */
 
+	/* must not acquire netlink_table_lock in any way again before unbind
+	 * and notifying genetlink is done as otherwise it might deadlock
+	 */
+	if (nlk->netlink_unbind) {
+		int i;
+
+		for (i = 0; i < nlk->ngroups; i++)
+			if (test_bit(i, nlk->groups))
+				nlk->netlink_unbind(sock_net(sk), i + 1);
+	}
+	if (sk->sk_protocol == NETLINK_GENERIC &&
+	    atomic_dec_return(&genl_sk_destructing_cnt) == 0)
+		wake_up(&genl_sk_destructing_waitq);
+
 	sock->sk = NULL;
 	wake_up_interruptible_all(&nlk->wait);
 
@@ -1246,8 +1248,8 @@ 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;
@@ -1261,10 +1263,8 @@ 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();
 
 	kfree(nlk->groups);
 	nlk->groups = NULL;
@@ -1272,7 +1272,7 @@ static int netlink_release(struct socket *sock)
 	local_bh_disable();
 	sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
 	local_bh_enable();
-	sock_put(sk);
+	call_rcu(&nlk->rcu, deferred_put_nlk_sk);
 	return 0;
 }
 
@@ -1287,7 +1287,6 @@ static int netlink_autobind(struct socket *sock)
 
 retry:
 	cond_resched();
-	netlink_table_grab();
 	rcu_read_lock();
 	if (__netlink_lookup(table, portid, net)) {
 		/* Bind collision, search negative portid values. */
@@ -1295,13 +1294,11 @@ retry:
 		if (rover > -4097)
 			rover = -4097;
 		rcu_read_unlock();
-		netlink_table_ungrab();
 		goto retry;
 	}
 	rcu_read_unlock();
-	netlink_table_ungrab();
 
-	err = netlink_insert(sk, net, portid);
+	err = netlink_insert(sk, portid);
 	if (err == -EADDRINUSE)
 		goto retry;
 
@@ -1430,9 +1427,10 @@ 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 sock *sk)
 {
+	struct netlink_sock *nlk = nlk_sk(sk);
 	int undo;
 
 	if (!nlk->netlink_unbind)
@@ -1440,7 +1438,7 @@ static void netlink_unbind(int group, long unsigned int groups,
 
 	for (undo = 0; undo < group; undo++)
 		if (test_bit(undo, &groups))
-			nlk->netlink_unbind(undo);
+			nlk->netlink_unbind(sock_net(sk), undo + 1);
 }
 
 static int netlink_bind(struct socket *sock, struct sockaddr *addr,
@@ -1478,20 +1476,20 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		for (group = 0; group < nlk->ngroups; group++) {
 			if (!test_bit(group, &groups))
 				continue;
-			err = nlk->netlink_bind(group);
+			err = nlk->netlink_bind(net, group + 1);
 			if (!err)
 				continue;
-			netlink_unbind(group, groups, nlk);
+			netlink_undo_bind(group, groups, sk);
 			return err;
 		}
 	}
 
 	if (!nlk->portid) {
 		err = nladdr->nl_pid ?
-			netlink_insert(sk, net, nladdr->nl_pid) :
+			netlink_insert(sk, nladdr->nl_pid) :
 			netlink_autobind(sock);
 		if (err) {
-			netlink_unbind(nlk->ngroups, groups, nlk);
+			netlink_undo_bind(nlk->ngroups, groups, sk);
 			return err;
 		}
 	}
@@ -2142,7 +2140,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
 		if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) {
-			err = nlk->netlink_bind(val);
+			err = nlk->netlink_bind(sock_net(sk), val);
 			if (err)
 				return err;
 		}
@@ -2151,7 +2149,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 					 optname == NETLINK_ADD_MEMBERSHIP);
 		netlink_table_ungrab();
 		if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind)
-			nlk->netlink_unbind(val);
+			nlk->netlink_unbind(sock_net(sk), val);
 
 		err = 0;
 		break;
@@ -2261,7 +2259,6 @@ static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			   struct msghdr *msg, size_t len)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
@@ -2275,10 +2272,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;
 
-	if (NULL == siocb->scm)
-		siocb->scm = &scm;
-
-	err = scm_send(sock, msg, siocb->scm, true);
+	err = scm_send(sock, msg, &scm, true);
 	if (err < 0)
 		return err;
 
@@ -2304,10 +2298,15 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			goto out;
 	}
 
+	/* It's a really convoluted way for userland to ask for mmaped
+	 * sendmsg(), but that's what we've got...
+	 */
 	if (netlink_tx_is_mmaped(sk) &&
+	    msg->msg_iter.type == ITER_IOVEC &&
+	    msg->msg_iter.nr_segs == 1 &&
 	    msg->msg_iter.iov->iov_base == NULL) {
 		err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
-					   siocb);
+					   &scm);
 		goto out;
 	}
 
@@ -2321,7 +2320,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 
 	NETLINK_CB(skb).portid	= nlk->portid;
 	NETLINK_CB(skb).dst_group = dst_group;
-	NETLINK_CB(skb).creds	= siocb->scm->creds;
+	NETLINK_CB(skb).creds	= scm.creds;
 	NETLINK_CB(skb).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
@@ -2343,7 +2342,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags&MSG_DONTWAIT);
 
 out:
-	scm_destroy(siocb->scm);
+	scm_destroy(&scm);
 	return err;
 }
 
@@ -2351,7 +2350,6 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 			   struct msghdr *msg, size_t len,
 			   int flags)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -2414,11 +2412,8 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	if (nlk->flags & NETLINK_RECV_PKTINFO)
 		netlink_cmsg_recv_pktinfo(msg, skb);
 
-	if (NULL == siocb->scm) {
-		memset(&scm, 0, sizeof(scm));
-		siocb->scm = &scm;
-	}
-	siocb->scm->creds = *NETLINK_CREDS(skb);
+	memset(&scm, 0, sizeof(scm));
+	scm.creds = *NETLINK_CREDS(skb);
 	if (flags & MSG_TRUNC)
 		copied = data_skb->len;
 
@@ -2433,7 +2428,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 		}
 	}
 
-	scm_recv(sock, msg, siocb->scm, flags);
+	scm_recv(sock, msg, &scm, flags);
 out:
 	netlink_rcv_wake(sk);
 	return err ? : copied;
@@ -2494,7 +2489,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 	if (cfg && cfg->input)
 		nlk_sk(sk)->netlink_rcv = cfg->input;
 
-	if (netlink_insert(sk, net, 0))
+	if (netlink_insert(sk, 0))
 		goto out_sock_release;
 
 	nlk = nlk_sk(sk);
@@ -2896,97 +2891,97 @@ EXPORT_SYMBOL(nlmsg_notify);
 #ifdef CONFIG_PROC_FS
 struct nl_seq_iter {
 	struct seq_net_private p;
+	struct rhashtable_iter hti;
 	int link;
-	int hash_idx;
 };
 
-static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos)
+static int netlink_walk_start(struct nl_seq_iter *iter)
 {
-	struct nl_seq_iter *iter = seq->private;
-	int i, j;
-	struct netlink_sock *nlk;
-	struct sock *s;
-	loff_t off = 0;
-
-	for (i = 0; i < MAX_LINKS; i++) {
-		struct rhashtable *ht = &nl_table[i].hash;
-		const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
-
-		for (j = 0; j < tbl->size; j++) {
-			rht_for_each_entry_rcu(nlk, tbl->buckets[j], node) {
-				s = (struct sock *)nlk;
+	int err;
 
-				if (sock_net(s) != seq_file_net(seq))
-					continue;
-				if (off == pos) {
-					iter->link = i;
-					iter->hash_idx = j;
-					return s;
-				}
-				++off;
-			}
-		}
+	err = rhashtable_walk_init(&nl_table[iter->link].hash, &iter->hti);
+	if (err) {
+		iter->link = MAX_LINKS;
+		return err;
 	}
-	return NULL;
+
+	err = rhashtable_walk_start(&iter->hti);
+	return err == -EAGAIN ? 0 : err;
 }
 
-static void *netlink_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(nl_table_lock) __acquires(RCU)
+static void netlink_walk_stop(struct nl_seq_iter *iter)
 {
-	read_lock(&nl_table_lock);
-	rcu_read_lock();
-	return *pos ? netlink_seq_socket_idx(seq, *pos - 1) : SEQ_START_TOKEN;
+	rhashtable_walk_stop(&iter->hti);
+	rhashtable_walk_exit(&iter->hti);
 }
 
-static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+static void *__netlink_seq_next(struct seq_file *seq)
 {
-	struct rhashtable *ht;
+	struct nl_seq_iter *iter = seq->private;
 	struct netlink_sock *nlk;
-	struct nl_seq_iter *iter;
-	struct net *net;
-	int i, j;
 
-	++*pos;
+	do {
+		for (;;) {
+			int err;
 
-	if (v == SEQ_START_TOKEN)
-		return netlink_seq_socket_idx(seq, 0);
+			nlk = rhashtable_walk_next(&iter->hti);
 
-	net = seq_file_net(seq);
-	iter = seq->private;
-	nlk = v;
+			if (IS_ERR(nlk)) {
+				if (PTR_ERR(nlk) == -EAGAIN)
+					continue;
 
-	i = iter->link;
-	ht = &nl_table[i].hash;
-	rht_for_each_entry(nlk, nlk->node.next, ht, node)
-		if (net_eq(sock_net((struct sock *)nlk), net))
-			return nlk;
+				return nlk;
+			}
 
-	j = iter->hash_idx + 1;
+			if (nlk)
+				break;
 
-	do {
-		const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
-
-		for (; j < tbl->size; j++) {
-			rht_for_each_entry(nlk, tbl->buckets[j], ht, node) {
-				if (net_eq(sock_net((struct sock *)nlk), net)) {
-					iter->link = i;
-					iter->hash_idx = j;
-					return nlk;
-				}
-			}
+			netlink_walk_stop(iter);
+			if (++iter->link >= MAX_LINKS)
+				return NULL;
+
+			err = netlink_walk_start(iter);
+			if (err)
+				return ERR_PTR(err);
 		}
+	} while (sock_net(&nlk->sk) != seq_file_net(seq));
 
-		j = 0;
-	} while (++i < MAX_LINKS);
+	return nlk;
+}
 
-	return NULL;
+static void *netlink_seq_start(struct seq_file *seq, loff_t *posp)
+{
+	struct nl_seq_iter *iter = seq->private;
+	void *obj = SEQ_START_TOKEN;
+	loff_t pos;
+	int err;
+
+	iter->link = 0;
+
+	err = netlink_walk_start(iter);
+	if (err)
+		return ERR_PTR(err);
+
+	for (pos = *posp; pos && obj && !IS_ERR(obj); pos--)
+		obj = __netlink_seq_next(seq);
+
+	return obj;
+}
+
+static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	++*pos;
+	return __netlink_seq_next(seq);
 }
 
 static void netlink_seq_stop(struct seq_file *seq, void *v)
-	__releases(RCU) __releases(nl_table_lock)
 {
-	rcu_read_unlock();
-	read_unlock(&nl_table_lock);
+	struct nl_seq_iter *iter = seq->private;
+
+	if (iter->link >= MAX_LINKS)
+		return;
+
+	netlink_walk_stop(iter);
 }
 
 
@@ -3133,9 +3128,6 @@ static int __init netlink_proto_init(void)
 		.max_shift = 16, /* 64K */
 		.grow_decision = rht_grow_above_75,
 		.shrink_decision = rht_shrink_below_30,
-#ifdef CONFIG_PROVE_LOCKING
-		.mutex_is_held = lockdep_nl_sk_hash_is_held,
-#endif
 	};
 
 	if (err != 0)
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index b20a1731759b..89008405d6b4 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -2,6 +2,7 @@
 #define _AF_NETLINK_H
 
 #include <linux/rhashtable.h>
+#include <linux/atomic.h>
 #include <net/sock.h>
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
@@ -39,8 +40,8 @@ struct netlink_sock {
 	struct mutex		*cb_mutex;
 	struct mutex		cb_def_mutex;
 	void			(*netlink_rcv)(struct sk_buff *skb);
-	int			(*netlink_bind)(int group);
-	void			(*netlink_unbind)(int group);
+	int			(*netlink_bind)(struct net *net, int group);
+	void			(*netlink_unbind)(struct net *net, int group);
 	struct module		*module;
 #ifdef CONFIG_NETLINK_MMAP
 	struct mutex		pg_vec_lock;
@@ -50,6 +51,7 @@ struct netlink_sock {
 #endif /* CONFIG_NETLINK_MMAP */
 
 	struct rhash_head	node;
+	struct rcu_head		rcu;
 };
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)
@@ -65,14 +67,13 @@ struct netlink_table {
 	unsigned int		groups;
 	struct mutex		*cb_mutex;
 	struct module		*module;
-	int			(*bind)(int group);
-	void			(*unbind)(int group);
+	int			(*bind)(struct net *net, int group);
+	void			(*unbind)(struct net *net, int group);
 	bool			(*compare)(struct net *net, struct sock *sock);
 	int			registered;
 };
 
 extern struct netlink_table *nl_table;
 extern rwlock_t nl_table_lock;
-extern struct mutex nl_sk_hash_lock;
 
 #endif
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index de8c74a3c061..3ee63a3cff30 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -91,7 +91,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 	    sk_diag_put_rings_cfg(sk, skb))
 		goto out_nlmsg_trim;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_nlmsg_trim:
 	nlmsg_cancel(skb, nlh);
@@ -103,7 +104,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 {
 	struct netlink_table *tbl = &nl_table[protocol];
 	struct rhashtable *ht = &tbl->hash;
-	const struct bucket_table *htbl = rht_dereference(ht->tbl, ht);
+	const struct bucket_table *htbl = rht_dereference_rcu(ht->tbl, ht);
 	struct net *net = sock_net(skb->sk);
 	struct netlink_diag_req *req;
 	struct netlink_sock *nlsk;
@@ -113,7 +114,9 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	req = nlmsg_data(cb->nlh);
 
 	for (i = 0; i < htbl->size; i++) {
-		rht_for_each_entry(nlsk, htbl->buckets[i], ht, node) {
+		struct rhash_head *pos;
+
+		rht_for_each_entry_rcu(nlsk, pos, htbl, i, node) {
 			sk = (struct sock *)nlsk;
 
 			if (!net_eq(sock_net(sk), net))
@@ -170,7 +173,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 	req = nlmsg_data(cb->nlh);
 
-	mutex_lock(&nl_sk_hash_lock);
+	rcu_read_lock();
 	read_lock(&nl_table_lock);
 
 	if (req->sdiag_protocol == NDIAG_PROTO_ALL) {
@@ -184,7 +187,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	} else {
 		if (req->sdiag_protocol >= MAX_LINKS) {
 			read_unlock(&nl_table_lock);
-			mutex_unlock(&nl_sk_hash_lock);
+			rcu_read_unlock();
 			return -ENOENT;
 		}
 
@@ -192,7 +195,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 
 	read_unlock(&nl_table_lock);
-	mutex_unlock(&nl_sk_hash_lock);
+	rcu_read_unlock();
 
 	return skb->len;
 }
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 76393f2f4b22..2ed5f964772e 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -23,6 +23,9 @@
 static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */
 static DECLARE_RWSEM(cb_lock);
 
+atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0);
+DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq);
+
 void genl_lock(void)
 {
 	mutex_lock(&genl_mutex);
@@ -435,15 +438,18 @@ int genl_unregister_family(struct genl_family *family)
 
 	genl_lock_all();
 
-	genl_unregister_mc_groups(family);
-
 	list_for_each_entry(rc, genl_family_chain(family->id), family_list) {
 		if (family->id != rc->id || strcmp(rc->name, family->name))
 			continue;
 
+		genl_unregister_mc_groups(family);
+
 		list_del(&rc->family_list);
 		family->n_ops = 0;
-		genl_unlock_all();
+		up_write(&cb_lock);
+		wait_event(genl_sk_destructing_waitq,
+			   atomic_read(&genl_sk_destructing_cnt) == 0);
+		genl_unlock();
 
 		kfree(family->attrbuf);
 		genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0);
@@ -756,7 +762,8 @@ static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq,
 		nla_nest_end(skb, nla_grps);
 	}
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -796,7 +803,8 @@ static int ctrl_fill_mcgrp_info(struct genl_family *family,
 	nla_nest_end(skb, nest);
 	nla_nest_end(skb, nla_grps);
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -983,11 +991,63 @@ static struct genl_multicast_group genl_ctrl_groups[] = {
 	{ .name = "notify", },
 };
 
+static int genl_bind(struct net *net, int group)
+{
+	int i, err = -ENOENT;
+
+	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->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)
+{
+	int i;
+
+	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(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 */