1 files changed, 174 insertions, 58 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 8df7f64c6db..e6fac7e3db5 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -131,7 +131,7 @@ int netlink_add_tap(struct netlink_tap *nt)
 }
 EXPORT_SYMBOL_GPL(netlink_add_tap);
 
-int __netlink_remove_tap(struct netlink_tap *nt)
+static int __netlink_remove_tap(struct netlink_tap *nt)
 {
 	bool found = false;
 	struct netlink_tap *tmp;
@@ -155,7 +155,6 @@ out:
 
 	return found ? 0 : -ENODEV;
 }
-EXPORT_SYMBOL_GPL(__netlink_remove_tap);
 
 int netlink_remove_tap(struct netlink_tap *nt)
 {
@@ -204,6 +203,8 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	if (nskb) {
 		nskb->dev = dev;
 		nskb->protocol = htons((u16) sk->sk_protocol);
+		nskb->pkt_type = netlink_is_kernel(sk) ?
+				 PACKET_KERNEL : PACKET_USER;
 
 		ret = dev_queue_xmit(nskb);
 		if (unlikely(ret > 0))
@@ -239,6 +240,13 @@ static void netlink_deliver_tap(struct sk_buff *skb)
 	rcu_read_unlock();
 }
 
+static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src,
+				       struct sk_buff *skb)
+{
+	if (!(netlink_is_kernel(dst) && netlink_is_kernel(src)))
+		netlink_deliver_tap(skb);
+}
+
 static void netlink_overrun(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -628,7 +636,7 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock,
 		while (nlk->cb_running && netlink_dump_space(nlk)) {
 			err = netlink_dump(sk);
 			if (err < 0) {
-				sk->sk_err = err;
+				sk->sk_err = -err;
 				sk->sk_error_report(sk);
 				break;
 			}
@@ -1198,7 +1206,8 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	struct module *module = NULL;
 	struct mutex *cb_mutex;
 	struct netlink_sock *nlk;
-	void (*bind)(int group);
+	int (*bind)(int group);
+	void (*unbind)(int group);
 	int err = 0;
 
 	sock->state = SS_UNCONNECTED;
@@ -1224,6 +1233,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 		err = -EPROTONOSUPPORT;
 	cb_mutex = nl_table[protocol].cb_mutex;
 	bind = nl_table[protocol].bind;
+	unbind = nl_table[protocol].unbind;
 	netlink_unlock_table();
 
 	if (err < 0)
@@ -1240,6 +1250,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	nlk = nlk_sk(sock->sk);
 	nlk->module = module;
 	nlk->netlink_bind = bind;
+	nlk->netlink_unbind = unbind;
 out:
 	return err;
 
@@ -1293,6 +1304,7 @@ static int netlink_release(struct socket *sock)
 			kfree_rcu(old, rcu);
 			nl_table[sk->sk_protocol].module = NULL;
 			nl_table[sk->sk_protocol].bind = NULL;
+			nl_table[sk->sk_protocol].unbind = NULL;
 			nl_table[sk->sk_protocol].flags = 0;
 			nl_table[sk->sk_protocol].registered = 0;
 		}
@@ -1352,7 +1364,74 @@ retry:
 	return err;
 }
 
-static inline int netlink_capable(const struct socket *sock, unsigned int flag)
+/**
+ * __netlink_ns_capable - General netlink message capability test
+ * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace.
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+			struct user_namespace *user_ns, int cap)
+{
+	return ((nsp->flags & NETLINK_SKB_DST) ||
+		file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
+		ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(__netlink_ns_capable);
+
+/**
+ * netlink_ns_capable - General netlink message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool netlink_ns_capable(const struct sk_buff *skb,
+			struct user_namespace *user_ns, int cap)
+{
+	return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_ns_capable);
+
+/**
+ * netlink_capable - Netlink global message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in all user namespaces.
+ */
+bool netlink_capable(const struct sk_buff *skb, int cap)
+{
+	return netlink_ns_capable(skb, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_capable);
+
+/**
+ * netlink_net_capable - Netlink network namespace message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap over the network namespace of
+ * the socket we received the message from.
+ */
+bool netlink_net_capable(const struct sk_buff *skb, int cap)
+{
+	return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_net_capable);
+
+static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
 {
 	return (nl_table[sock->sk->sk_protocol].flags & flag) ||
 		ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
@@ -1403,6 +1482,19 @@ static int netlink_realloc_groups(struct sock *sk)
 	return err;
 }
 
+static void netlink_unbind(int group, long unsigned int groups,
+			   struct netlink_sock *nlk)
+{
+	int undo;
+
+	if (!nlk->netlink_unbind)
+		return;
+
+	for (undo = 0; undo < group; undo++)
+		if (test_bit(group, &groups))
+			nlk->netlink_unbind(undo);
+}
+
 static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			int addr_len)
 {
@@ -1411,6 +1503,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err;
+	long unsigned int groups = nladdr->nl_groups;
 
 	if (addr_len < sizeof(struct sockaddr_nl))
 		return -EINVAL;
@@ -1419,45 +1512,53 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		return -EINVAL;
 
 	/* Only superuser is allowed to listen multicasts */
-	if (nladdr->nl_groups) {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+	if (groups) {
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)
 			return err;
 	}
 
-	if (nlk->portid) {
+	if (nlk->portid)
 		if (nladdr->nl_pid != nlk->portid)
 			return -EINVAL;
-	} else {
+
+	if (nlk->netlink_bind && groups) {
+		int group;
+
+		for (group = 0; group < nlk->ngroups; group++) {
+			if (!test_bit(group, &groups))
+				continue;
+			err = nlk->netlink_bind(group);
+			if (!err)
+				continue;
+			netlink_unbind(group, groups, nlk);
+			return err;
+		}
+	}
+
+	if (!nlk->portid) {
 		err = nladdr->nl_pid ?
 			netlink_insert(sk, net, nladdr->nl_pid) :
 			netlink_autobind(sock);
-		if (err)
+		if (err) {
+			netlink_unbind(nlk->ngroups - 1, groups, nlk);
 			return err;
+		}
 	}
 
-	if (!nladdr->nl_groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
+	if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
 		return 0;
 
 	netlink_table_grab();
 	netlink_update_subscriptions(sk, nlk->subscriptions +
-					 hweight32(nladdr->nl_groups) -
+					 hweight32(groups) -
 					 hweight32(nlk->groups[0]));
-	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups;
+	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups;
 	netlink_update_listeners(sk);
 	netlink_table_ungrab();
 
-	if (nlk->netlink_bind && nlk->groups[0]) {
-		int i;
-
-		for (i=0; i<nlk->ngroups; i++) {
-			if (test_bit(i, nlk->groups))
-				nlk->netlink_bind(i);
-		}
-	}
-
 	return 0;
 }
 
@@ -1481,8 +1582,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	if (addr->sa_family != AF_NETLINK)
 		return -EINVAL;
 
-	/* Only superuser is allowed to send multicasts */
-	if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+	if ((nladdr->nl_groups || nladdr->nl_pid) &&
+	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
 	if (!nlk->portid)
@@ -1645,7 +1746,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 	else
 #endif /* CONFIG_NETLINK_MMAP */
 		skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, len);
+	sk->sk_data_ready(sk);
 	return len;
 }
 
@@ -1697,14 +1798,10 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
 
 	ret = -ECONNREFUSED;
 	if (nlk->netlink_rcv != NULL) {
-		/* We could do a netlink_deliver_tap(skb) here as well
-		 * but since this is intended for the kernel only, we
-		 * should rather let it stay under the hood.
-		 */
-
 		ret = skb->len;
 		netlink_skb_set_owner_r(skb, sk);
 		NETLINK_CB(skb).sk = ssk;
+		netlink_deliver_tap_kernel(sk, ssk, skb);
 		nlk->netlink_rcv(skb);
 		consume_skb(skb);
 	} else {
@@ -1769,6 +1866,9 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
 	if (ring->pg_vec == NULL)
 		goto out_put;
 
+	if (ring->frame_size - NL_MMAP_HDRLEN < size)
+		goto out_put;
+
 	skb = alloc_skb_head(gfp_mask);
 	if (skb == NULL)
 		goto err1;
@@ -1778,6 +1878,7 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
 	if (ring->pg_vec == NULL)
 		goto out_free;
 
+	/* check again under lock */
 	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
 	if (maxlen < size)
 		goto out_free;
@@ -2017,7 +2118,7 @@ out:
  * netlink_set_err - report error to broadcast listeners
  * @ssk: the kernel netlink socket, as returned by netlink_kernel_create()
  * @portid: the PORTID of a process that we want to skip (if any)
- * @groups: the broadcast group that will notice the error
+ * @group: the broadcast group that will notice the error
  * @code: error code, must be negative (as usual in kernelspace)
  *
  * This function returns the number of broadcast listeners that have set the
@@ -2088,20 +2189,24 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
 	case NETLINK_DROP_MEMBERSHIP: {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)
 			return err;
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
+		if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) {
+			err = nlk->netlink_bind(val);
+			if (err)
+				return err;
+		}
 		netlink_table_grab();
 		netlink_update_socket_mc(nlk, val,
 					 optname == NETLINK_ADD_MEMBERSHIP);
 		netlink_table_ungrab();
-
-		if (nlk->netlink_bind)
-			nlk->netlink_bind(val);
+		if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind)
+			nlk->netlink_unbind(val);
 
 		err = 0;
 		break;
@@ -2214,12 +2319,13 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
-	struct sockaddr_nl *addr = msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
 	u32 dst_portid;
 	u32 dst_group;
 	struct sk_buff *skb;
 	int err;
 	struct scm_cookie scm;
+	u32 netlink_skb_flags = 0;
 
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;
@@ -2239,8 +2345,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		dst_group = ffs(addr->nl_groups);
 		err =  -EPERM;
 		if ((dst_group || dst_portid) &&
-		    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+		    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 			goto out;
+		netlink_skb_flags |= NETLINK_SKB_DST;
 	} else {
 		dst_portid = nlk->dst_portid;
 		dst_group = nlk->dst_group;
@@ -2270,6 +2377,7 @@ 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).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
 	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
@@ -2335,7 +2443,10 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	}
 #endif
 
-	msg->msg_namelen = 0;
+	/* Record the max length of recvmsg() calls for future allocations */
+	nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len);
+	nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len,
+				     16384);
 
 	copied = data_skb->len;
 	if (len < copied) {
@@ -2347,7 +2458,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	err = skb_copy_datagram_iovec(data_skb, 0, msg->msg_iov, copied);
 
 	if (msg->msg_name) {
-		struct sockaddr_nl *addr = (struct sockaddr_nl *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
 		addr->nl_family = AF_NETLINK;
 		addr->nl_pad    = 0;
 		addr->nl_pid	= NETLINK_CB(skb).portid;
@@ -2372,7 +2483,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	    atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
 		ret = netlink_dump(sk);
 		if (ret) {
-			sk->sk_err = ret;
+			sk->sk_err = -ret;
 			sk->sk_error_report(sk);
 		}
 	}
@@ -2383,7 +2494,7 @@ out:
 	return err ? : copied;
 }
 
-static void netlink_data_ready(struct sock *sk, int len)
+static void netlink_data_ready(struct sock *sk)
 {
 	BUG();
 }
@@ -2537,28 +2648,13 @@ void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group)
 		netlink_update_socket_mc(nlk_sk(sk), group, 0);
 }
 
-/**
- * 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)
-{
-	netlink_table_grab();
-	__netlink_clear_multicast_users(ksk, group);
-	netlink_table_ungrab();
-}
-
 struct nlmsghdr *
 __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags)
 {
 	struct nlmsghdr *nlh;
 	int size = nlmsg_msg_size(len);
 
-	nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size));
+	nlh = (struct nlmsghdr *)skb_put(skb, NLMSG_ALIGN(size));
 	nlh->nlmsg_type = type;
 	nlh->nlmsg_len = size;
 	nlh->nlmsg_flags = flags;
@@ -2596,7 +2692,27 @@ static int netlink_dump(struct sock *sk)
 	if (!netlink_rx_is_mmaped(sk) &&
 	    atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		goto errout_skb;
-	skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL);
+
+	/* NLMSG_GOODSIZE is small to avoid high order allocations being
+	 * required, but it makes sense to _attempt_ a 16K bytes allocation
+	 * to reduce number of system calls on dump operations, if user
+	 * ever provided a big enough buffer.
+	 */
+	if (alloc_size < nlk->max_recvmsg_len) {
+		skb = netlink_alloc_skb(sk,
+					nlk->max_recvmsg_len,
+					nlk->portid,
+					GFP_KERNEL |
+					__GFP_NOWARN |
+					__GFP_NORETRY);
+		/* available room should be exact amount to avoid MSG_TRUNC */
+		if (skb)
+			skb_reserve(skb, skb_tailroom(skb) -
+					 nlk->max_recvmsg_len);
+	}
+	if (!skb)
+		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
+					GFP_KERNEL);
 	if (!skb)
 		goto errout_skb;
 	netlink_skb_set_owner_r(skb, sk);