net: Allow userns root to control llc, netfilter, netlink, packet, and xfrm

Allow an unpriviled user who has created a user namespace, and then
created a network namespace to effectively use the new network
namespace, by reducing capable(CAP_NET_ADMIN) and
capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns,
CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls.

Allow creation of af_key sockets.
Allow creation of llc sockets.
Allow creation of af_packet sockets.

Allow sending xfrm netlink control messages.

Allow binding to netlink multicast groups.
Allow sending to netlink multicast groups.
Allow adding and dropping netlink multicast groups.
Allow sending to all netlink multicast groups and port ids.

Allow reading the netfilter SO_IP_SET socket option.
Allow sending netfilter netlink messages.
Allow setting and getting ip_vs netfilter socket options.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/key/af_key.c

@@ -141,7 +141,7 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol,
 	struct sock *sk;
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 	if (sock->type != SOCK_RAW)
 		return -ESOCKTNOSUPPORT;

net/llc/af_llc.c

@@ -160,7 +160,7 @@ static int llc_ui_create(struct net *net, struct socket *sock, int protocol,
 	struct sock *sk;
 	int rc = -ESOCKTNOSUPPORT;
 
-	if (!capable(CAP_NET_RAW))
+	if (!ns_capable(net->user_ns, CAP_NET_RAW))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))

net/netfilter/ipset/ip_set_core.c

@@ -1643,7 +1643,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 	void *data;
 	int copylen = *len, ret = 0;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 	if (optval != SO_IP_SET)
 		return -EBADF;

net/netfilter/ipvs/ip_vs_ctl.c

@@ -2339,7 +2339,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 	struct ip_vs_dest_user_kern udest;
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_SET_MAX)
@@ -2632,7 +2632,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	BUG_ON(!net);
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_GET_MAX)

net/netfilter/nfnetlink.c

@@ -138,7 +138,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	const struct nfnetlink_subsystem *ss;
 	int type, err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	/* All the messages must at least contain nfgenmsg */

net/netlink/af_netlink.c

@@ -612,7 +612,7 @@ retry:
 static inline int netlink_capable(const struct socket *sock, unsigned int flag)
 {
 	return (nl_table[sock->sk->sk_protocol].flags & flag) ||
-	       capable(CAP_NET_ADMIN);
+		ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
 }
 
 static void

net/packet/af_packet.c

@@ -2504,7 +2504,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	__be16 proto = (__force __be16)protocol; /* weird, but documented */
 	int err;
 
-	if (!capable(CAP_NET_RAW))
+	if (!ns_capable(net->user_ns, CAP_NET_RAW))
 		return -EPERM;
 	if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW &&
 	    sock->type != SOCK_PACKET)

net/xfrm/xfrm_user.c

@@ -2349,7 +2349,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	link = &xfrm_dispatch[type];
 
 	/* All operations require privileges, even GET */
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||