1 files changed, 100 insertions, 58 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 19909d0786a2..69d67c300b80 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -76,20 +76,21 @@ struct listeners {
 };
 
 /* state bits */
-#define NETLINK_CONGESTED	0x0
+#define NETLINK_S_CONGESTED		0x0
 
 /* flags */
-#define NETLINK_KERNEL_SOCKET	0x1
-#define NETLINK_RECV_PKTINFO	0x2
-#define NETLINK_BROADCAST_SEND_ERROR	0x4
-#define NETLINK_RECV_NO_ENOBUFS	0x8
+#define NETLINK_F_KERNEL_SOCKET		0x1
+#define NETLINK_F_RECV_PKTINFO		0x2
+#define NETLINK_F_BROADCAST_SEND_ERROR	0x4
+#define NETLINK_F_RECV_NO_ENOBUFS	0x8
+#define NETLINK_F_LISTEN_ALL_NSID	0x10
 
 static inline int netlink_is_kernel(struct sock *sk)
 {
-	return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET;
+	return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET;
 }
 
-struct netlink_table *nl_table;
+struct netlink_table *nl_table __read_mostly;
 EXPORT_SYMBOL_GPL(nl_table);
 
 static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
@@ -256,8 +257,9 @@ static void netlink_overrun(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
-	if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) {
-		if (!test_and_set_bit(NETLINK_CONGESTED, &nlk_sk(sk)->state)) {
+	if (!(nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)) {
+		if (!test_and_set_bit(NETLINK_S_CONGESTED,
+				      &nlk_sk(sk)->state)) {
 			sk->sk_err = ENOBUFS;
 			sk->sk_error_report(sk);
 		}
@@ -270,8 +272,8 @@ static void netlink_rcv_wake(struct sock *sk)
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (skb_queue_empty(&sk->sk_receive_queue))
-		clear_bit(NETLINK_CONGESTED, &nlk->state);
-	if (!test_bit(NETLINK_CONGESTED, &nlk->state))
+		clear_bit(NETLINK_S_CONGESTED, &nlk->state);
+	if (!test_bit(NETLINK_S_CONGESTED, &nlk->state))
 		wake_up_interruptible(&nlk->wait);
 }
 
@@ -1081,6 +1083,7 @@ static int netlink_insert(struct sock *sk, u32 portid)
 	if (err) {
 		if (err == -EEXIST)
 			err = -EADDRINUSE;
+		nlk_sk(sk)->portid = 0;
 		sock_put(sk);
 	}
 
@@ -1117,14 +1120,15 @@ static struct proto netlink_proto = {
 };
 
 static int __netlink_create(struct net *net, struct socket *sock,
-			    struct mutex *cb_mutex, int protocol)
+			    struct mutex *cb_mutex, int protocol,
+			    int kern)
 {
 	struct sock *sk;
 	struct netlink_sock *nlk;
 
 	sock->ops = &netlink_ops;
 
-	sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto);
+	sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern);
 	if (!sk)
 		return -ENOMEM;
 
@@ -1186,7 +1190,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	if (err < 0)
 		goto out;
 
-	err = __netlink_create(net, sock, cb_mutex, protocol);
+	err = __netlink_create(net, sock, cb_mutex, protocol, kern);
 	if (err < 0)
 		goto out_module;
 
@@ -1296,20 +1300,24 @@ static int netlink_autobind(struct socket *sock)
 	struct netlink_table *table = &nl_table[sk->sk_protocol];
 	s32 portid = task_tgid_vnr(current);
 	int err;
-	static s32 rover = -4097;
+	s32 rover = -4096;
+	bool ok;
 
 retry:
 	cond_resched();
 	rcu_read_lock();
-	if (__netlink_lookup(table, portid, net)) {
+	ok = !__netlink_lookup(table, portid, net);
+	rcu_read_unlock();
+	if (!ok) {
 		/* Bind collision, search negative portid values. */
-		portid = rover--;
-		if (rover > -4097)
+		if (rover == -4096)
+			/* rover will be in range [S32_MIN, -4097] */
+			rover = S32_MIN + prandom_u32_max(-4096 - S32_MIN);
+		else if (rover >= -4096)
 			rover = -4097;
-		rcu_read_unlock();
+		portid = rover--;
 		goto retry;
 	}
-	rcu_read_unlock();
 
 	err = netlink_insert(sk, portid);
 	if (err == -EADDRINUSE)
@@ -1629,13 +1637,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
 	if (data == NULL)
 		return NULL;
 
-	skb = build_skb(data, size);
+	skb = __build_skb(data, size);
 	if (skb == NULL)
 		vfree(data);
-	else {
-		skb->head_frag = 0;
+	else
 		skb->destructor = netlink_skb_destructor;
-	}
 
 	return skb;
 }
@@ -1658,7 +1664,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 	nlk = nlk_sk(sk);
 
 	if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
-	     test_bit(NETLINK_CONGESTED, &nlk->state)) &&
+	     test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
 	    !netlink_skb_is_mmaped(skb)) {
 		DECLARE_WAITQUEUE(wait, current);
 		if (!*timeo) {
@@ -1673,7 +1679,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 		add_wait_queue(&nlk->wait, &wait);
 
 		if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
-		     test_bit(NETLINK_CONGESTED, &nlk->state)) &&
+		     test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
 		    !sock_flag(sk, SOCK_DEAD))
 			*timeo = schedule_timeout(*timeo);
 
@@ -1897,7 +1903,7 @@ static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
-	    !test_bit(NETLINK_CONGESTED, &nlk->state)) {
+	    !test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
 		netlink_skb_set_owner_r(skb, sk);
 		__netlink_sendskb(sk, skb);
 		return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
@@ -1933,8 +1939,17 @@ static void do_one_broadcast(struct sock *sk,
 	    !test_bit(p->group - 1, nlk->groups))
 		return;
 
-	if (!net_eq(sock_net(sk), p->net))
-		return;
+	if (!net_eq(sock_net(sk), p->net)) {
+		if (!(nlk->flags & NETLINK_F_LISTEN_ALL_NSID))
+			return;
+
+		if (!peernet_has_id(sock_net(sk), p->net))
+			return;
+
+		if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns,
+				     CAP_NET_BROADCAST))
+			return;
+	}
 
 	if (p->failure) {
 		netlink_overrun(sk);
@@ -1958,23 +1973,33 @@ static void do_one_broadcast(struct sock *sk,
 		netlink_overrun(sk);
 		/* Clone failed. Notify ALL listeners. */
 		p->failure = 1;
-		if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR)
+		if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
 			p->delivery_failure = 1;
-	} else if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) {
+		goto out;
+	}
+	if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) {
 		kfree_skb(p->skb2);
 		p->skb2 = NULL;
-	} else if (sk_filter(sk, p->skb2)) {
+		goto out;
+	}
+	if (sk_filter(sk, p->skb2)) {
 		kfree_skb(p->skb2);
 		p->skb2 = NULL;
-	} else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) {
+		goto out;
+	}
+	NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net);
+	NETLINK_CB(p->skb2).nsid_is_set = true;
+	val = netlink_broadcast_deliver(sk, p->skb2);
+	if (val < 0) {
 		netlink_overrun(sk);
-		if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR)
+		if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
 			p->delivery_failure = 1;
 	} else {
 		p->congested |= val;
 		p->delivered = 1;
 		p->skb2 = NULL;
 	}
+out:
 	sock_put(sk);
 }
 
@@ -2059,7 +2084,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p)
 	    !test_bit(p->group - 1, nlk->groups))
 		goto out;
 
-	if (p->code == ENOBUFS && nlk->flags & NETLINK_RECV_NO_ENOBUFS) {
+	if (p->code == ENOBUFS && nlk->flags & NETLINK_F_RECV_NO_ENOBUFS) {
 		ret = 1;
 		goto out;
 	}
@@ -2078,7 +2103,7 @@ out:
  * @code: error code, must be negative (as usual in kernelspace)
  *
  * This function returns the number of broadcast listeners that have set the
- * NETLINK_RECV_NO_ENOBUFS socket option.
+ * NETLINK_NO_ENOBUFS socket option.
  */
 int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code)
 {
@@ -2138,9 +2163,9 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 	switch (optname) {
 	case NETLINK_PKTINFO:
 		if (val)
-			nlk->flags |= NETLINK_RECV_PKTINFO;
+			nlk->flags |= NETLINK_F_RECV_PKTINFO;
 		else
-			nlk->flags &= ~NETLINK_RECV_PKTINFO;
+			nlk->flags &= ~NETLINK_F_RECV_PKTINFO;
 		err = 0;
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
@@ -2169,18 +2194,18 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 	}
 	case NETLINK_BROADCAST_ERROR:
 		if (val)
-			nlk->flags |= NETLINK_BROADCAST_SEND_ERROR;
+			nlk->flags |= NETLINK_F_BROADCAST_SEND_ERROR;
 		else
-			nlk->flags &= ~NETLINK_BROADCAST_SEND_ERROR;
+			nlk->flags &= ~NETLINK_F_BROADCAST_SEND_ERROR;
 		err = 0;
 		break;
 	case NETLINK_NO_ENOBUFS:
 		if (val) {
-			nlk->flags |= NETLINK_RECV_NO_ENOBUFS;
-			clear_bit(NETLINK_CONGESTED, &nlk->state);
+			nlk->flags |= NETLINK_F_RECV_NO_ENOBUFS;
+			clear_bit(NETLINK_S_CONGESTED, &nlk->state);
 			wake_up_interruptible(&nlk->wait);
 		} else {
-			nlk->flags &= ~NETLINK_RECV_NO_ENOBUFS;
+			nlk->flags &= ~NETLINK_F_RECV_NO_ENOBUFS;
 		}
 		err = 0;
 		break;
@@ -2203,6 +2228,16 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		break;
 	}
 #endif /* CONFIG_NETLINK_MMAP */
+	case NETLINK_LISTEN_ALL_NSID:
+		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST))
+			return -EPERM;
+
+		if (val)
+			nlk->flags |= NETLINK_F_LISTEN_ALL_NSID;
+		else
+			nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -2229,7 +2264,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		if (len < sizeof(int))
 			return -EINVAL;
 		len = sizeof(int);
-		val = nlk->flags & NETLINK_RECV_PKTINFO ? 1 : 0;
+		val = nlk->flags & NETLINK_F_RECV_PKTINFO ? 1 : 0;
 		if (put_user(len, optlen) ||
 		    put_user(val, optval))
 			return -EFAULT;
@@ -2239,7 +2274,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		if (len < sizeof(int))
 			return -EINVAL;
 		len = sizeof(int);
-		val = nlk->flags & NETLINK_BROADCAST_SEND_ERROR ? 1 : 0;
+		val = nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR ? 1 : 0;
 		if (put_user(len, optlen) ||
 		    put_user(val, optval))
 			return -EFAULT;
@@ -2249,7 +2284,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		if (len < sizeof(int))
 			return -EINVAL;
 		len = sizeof(int);
-		val = nlk->flags & NETLINK_RECV_NO_ENOBUFS ? 1 : 0;
+		val = nlk->flags & NETLINK_F_RECV_NO_ENOBUFS ? 1 : 0;
 		if (put_user(len, optlen) ||
 		    put_user(val, optval))
 			return -EFAULT;
@@ -2269,6 +2304,16 @@ static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info);
 }
 
+static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg,
+					 struct sk_buff *skb)
+{
+	if (!NETLINK_CB(skb).nsid_is_set)
+		return;
+
+	put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int),
+		 &NETLINK_CB(skb).nsid);
+}
+
 static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
@@ -2420,8 +2465,10 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		msg->msg_namelen = sizeof(*addr);
 	}
 
-	if (nlk->flags & NETLINK_RECV_PKTINFO)
+	if (nlk->flags & NETLINK_F_RECV_PKTINFO)
 		netlink_cmsg_recv_pktinfo(msg, skb);
+	if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID)
+		netlink_cmsg_listen_all_nsid(sk, msg, skb);
 
 	memset(&scm, 0, sizeof(scm));
 	scm.creds = *NETLINK_CREDS(skb);
@@ -2475,17 +2522,10 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 	if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock))
 		return NULL;
 
-	/*
-	 * We have to just have a reference on the net from sk, but don't
-	 * get_net it. Besides, we cannot get and then put the net here.
-	 * So we create one inside init_net and the move it to net.
-	 */
-
-	if (__netlink_create(&init_net, sock, cb_mutex, unit) < 0)
+	if (__netlink_create(net, sock, cb_mutex, unit, 1) < 0)
 		goto out_sock_release_nosk;
 
 	sk = sock->sk;
-	sk_change_net(sk, net);
 
 	if (!cfg || cfg->groups < 32)
 		groups = 32;
@@ -2504,7 +2544,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 		goto out_sock_release;
 
 	nlk = nlk_sk(sk);
-	nlk->flags |= NETLINK_KERNEL_SOCKET;
+	nlk->flags |= NETLINK_F_KERNEL_SOCKET;
 
 	netlink_table_grab();
 	if (!nl_table[unit].registered) {
@@ -2541,7 +2581,10 @@ EXPORT_SYMBOL(__netlink_kernel_create);
 void
 netlink_kernel_release(struct sock *sk)
 {
-	sk_release_kernel(sk);
+	if (sk == NULL || sk->sk_socket == NULL)
+		return;
+
+	sock_release(sk->sk_socket);
 }
 EXPORT_SYMBOL(netlink_kernel_release);
 
@@ -3141,7 +3184,6 @@ static const struct rhashtable_params netlink_rhashtable_params = {
 	.key_len = netlink_compare_arg_len,
 	.obj_hashfn = netlink_hash,
 	.obj_cmpfn = netlink_compare,
-	.max_size = 65536,
 	.automatic_shrinking = true,
 };