1 files changed, 172 insertions, 86 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index bf6e76643..a77498548 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -76,17 +76,18 @@ 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 __read_mostly;
@@ -157,7 +158,7 @@ static int __netlink_remove_tap(struct netlink_tap *nt)
 out:
 	spin_unlock(&netlink_tap_lock);
 
-	if (found && nt->module)
+	if (found)
 		module_put(nt->module);
 
 	return found ? 0 : -ENODEV;
@@ -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);
 }
 
@@ -355,25 +357,52 @@ err1:
 	return NULL;
 }
 
+
+static void
+__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
+		   unsigned int order)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+	struct sk_buff_head *queue;
+	struct netlink_ring *ring;
+
+	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
+	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
+
+	spin_lock_bh(&queue->lock);
+
+	ring->frame_max		= req->nm_frame_nr - 1;
+	ring->head		= 0;
+	ring->frame_size	= req->nm_frame_size;
+	ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
+
+	swap(ring->pg_vec_len, req->nm_block_nr);
+	swap(ring->pg_vec_order, order);
+	swap(ring->pg_vec, pg_vec);
+
+	__skb_queue_purge(queue);
+	spin_unlock_bh(&queue->lock);
+
+	WARN_ON(atomic_read(&nlk->mapped));
+
+	if (pg_vec)
+		free_pg_vec(pg_vec, order, req->nm_block_nr);
+}
+
 static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
-			    bool closing, bool tx_ring)
+			    bool tx_ring)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ring *ring;
-	struct sk_buff_head *queue;
 	void **pg_vec = NULL;
 	unsigned int order = 0;
-	int err;
 
 	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
 
-	if (!closing) {
-		if (atomic_read(&nlk->mapped))
-			return -EBUSY;
-		if (atomic_read(&ring->pending))
-			return -EBUSY;
-	}
+	if (atomic_read(&nlk->mapped))
+		return -EBUSY;
+	if (atomic_read(&ring->pending))
+		return -EBUSY;
 
 	if (req->nm_block_nr) {
 		if (ring->pg_vec != NULL)
@@ -405,31 +434,19 @@ static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
 			return -EINVAL;
 	}
 
-	err = -EBUSY;
 	mutex_lock(&nlk->pg_vec_lock);
-	if (closing || atomic_read(&nlk->mapped) == 0) {
-		err = 0;
-		spin_lock_bh(&queue->lock);
-
-		ring->frame_max		= req->nm_frame_nr - 1;
-		ring->head		= 0;
-		ring->frame_size	= req->nm_frame_size;
-		ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
-
-		swap(ring->pg_vec_len, req->nm_block_nr);
-		swap(ring->pg_vec_order, order);
-		swap(ring->pg_vec, pg_vec);
-
-		__skb_queue_purge(queue);
-		spin_unlock_bh(&queue->lock);
-
-		WARN_ON(atomic_read(&nlk->mapped));
+	if (atomic_read(&nlk->mapped) == 0) {
+		__netlink_set_ring(sk, req, tx_ring, pg_vec, order);
+		mutex_unlock(&nlk->pg_vec_lock);
+		return 0;
 	}
+
 	mutex_unlock(&nlk->pg_vec_lock);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->nm_block_nr);
-	return err;
+
+	return -EBUSY;
 }
 
 static void netlink_mm_open(struct vm_area_struct *vma)
@@ -898,10 +915,10 @@ static void netlink_sock_destruct(struct sock *sk)
 
 		memset(&req, 0, sizeof(req));
 		if (nlk->rx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, false);
+			__netlink_set_ring(sk, &req, false, NULL, 0);
 		memset(&req, 0, sizeof(req));
 		if (nlk->tx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, true);
+			__netlink_set_ring(sk, &req, true, NULL, 0);
 	}
 #endif /* CONFIG_NETLINK_MMAP */
 
@@ -1079,6 +1096,11 @@ static int netlink_insert(struct sock *sk, u32 portid)
 
 	err = __netlink_insert(table, sk);
 	if (err) {
+		/* In case the hashtable backend returns with -EBUSY
+		 * from here, it must not escape to the caller.
+		 */
+		if (unlikely(err == -EBUSY))
+			err = -EOVERFLOW;
 		if (err == -EEXIST)
 			err = -EADDRINUSE;
 		nlk_sk(sk)->portid = 0;
@@ -1118,14 +1140,15 @@ 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;
 
@@ -1187,7 +1210,7 @@ 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;
 
@@ -1297,20 +1320,24 @@ 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)
@@ -1657,7 +1684,7 @@ 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) {
@@ -1672,7 +1699,7 @@ 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);
 
@@ -1896,7 +1923,7 @@ 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);
@@ -1932,8 +1959,17 @@ 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);
@@ -1957,23 +1993,33 @@ 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);
 }
 
@@ -2058,7 +2104,7 @@ 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;
 	}
@@ -2077,7 +2123,7 @@ 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)
 {
@@ -2137,9 +2183,9 @@ 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:
@@ -2168,18 +2214,18 @@ 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;
@@ -2197,11 +2243,21 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			return -EINVAL;
 		if (copy_from_user(&req, optval, sizeof(req)))
 			return -EFAULT;
-		err = netlink_set_ring(sk, &req, false,
+		err = netlink_set_ring(sk, &req,
 				       optname == NETLINK_TX_RING);
 		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;
 	}
@@ -2228,7 +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_PKTINFO ? 1 : 0;
+		val = nlk->flags & NETLINK_F_RECV_PKTINFO ? 1 : 0;
 		if (put_user(len, optlen) ||
 		    put_user(val, optval))
 			return -EFAULT;
@@ -2238,7 +2294,7 @@ 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;
@@ -2248,12 +2304,34 @@ 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;
 		err = 0;
 		break;
+	case NETLINK_LIST_MEMBERSHIPS: {
+		int pos, idx, shift;
+
+		err = 0;
+		netlink_table_grab();
+		for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) {
+			if (len - pos < sizeof(u32))
+				break;
+
+			idx = pos / sizeof(unsigned long);
+			shift = (pos % sizeof(unsigned long)) * 8;
+			if (put_user((u32)(nlk->groups[idx] >> shift),
+				     (u32 __user *)(optval + pos))) {
+				err = -EFAULT;
+				break;
+			}
+		}
+		if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen))
+			err = -EFAULT;
+		netlink_table_ungrab();
+		break;
+	}
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -2268,6 +2346,16 @@ 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;
@@ -2313,7 +2401,7 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	 * sendmsg(), but that's what we've got...
 	 */
 	if (netlink_tx_is_mmaped(sk) &&
-	    msg->msg_iter.type == ITER_IOVEC &&
+	    iter_is_iovec(&msg->msg_iter) &&
 	    msg->msg_iter.nr_segs == 1 &&
 	    msg->msg_iter.iov->iov_base == NULL) {
 		err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
@@ -2419,8 +2507,10 @@ 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);
@@ -2474,17 +2564,10 @@ __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;
@@ -2503,7 +2586,7 @@ __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) {
@@ -2540,7 +2623,10 @@ 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);