net: Allow userns root to control ipv4

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.

Settings that merely control a single network device are allowed.
Either the network device is a logical network device where
restrictions make no difference or the network device is hardware NIC
that has been explicity moved from the initial network namespace.

In general policy and network stack state changes are allowed
while resource control is left unchanged.

Allow creating raw sockets.
Allow the SIOCSARP ioctl to control the arp cache.
Allow the SIOCSIFFLAG ioctl to allow setting network device flags.
Allow the SIOCSIFADDR ioctl to allow setting a netdevice ipv4 address.
Allow the SIOCSIFBRDADDR ioctl to allow setting a netdevice ipv4 broadcast address.
Allow the SIOCSIFDSTADDR ioctl to allow setting a netdevice ipv4 destination address.
Allow the SIOCSIFNETMASK ioctl to allow setting a netdevice ipv4 netmask.
Allow the SIOCADDRT and SIOCDELRT ioctls to allow adding and deleting ipv4 routes.

Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for
adding, changing and deleting gre tunnels.

Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for
adding, changing and deleting ipip tunnels.

Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for
adding, changing and deleting ipsec virtual tunnel interfaces.

Allow setting the MRT_INIT, MRT_DONE, MRT_ADD_VIF, MRT_DEL_VIF, MRT_ADD_MFC,
MRT_DEL_MFC, MRT_ASSERT, MRT_PIM, MRT_TABLE socket options on multicast routing
sockets.

Allow setting and receiving IPOPT_CIPSO, IP_OPT_SEC, IP_OPT_SID and
arbitrary ip options.

Allow setting IP_SEC_POLICY/IP_XFRM_POLICY ipv4 socket option.
Allow setting the IP_TRANSPARENT ipv4 socket option.
Allow setting the TCP_REPAIR socket option.
Allow setting the TCP_CONGESTION socket option.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/af_inet.c

@@ -346,7 +346,8 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	}
 
 	err = -EPERM;
-	if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
+	if (sock->type == SOCK_RAW && !kern &&
+	    !ns_capable(net->user_ns, CAP_NET_RAW))
 		goto out_rcu_unlock;
 
 	err = -EAFNOSUPPORT;

net/ipv4/arp.c

@@ -1161,7 +1161,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	switch (cmd) {
 	case SIOCDARP:
 	case SIOCSARP:
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 	case SIOCGARP:
 		err = copy_from_user(&r, arg, sizeof(struct arpreq));

net/ipv4/devinet.c

@@ -730,7 +730,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 
 	case SIOCSIFFLAGS:
 		ret = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto out;
 		break;
 	case SIOCSIFADDR:	/* Set interface address (and family) */
@@ -738,7 +738,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	case SIOCSIFDSTADDR:	/* Set the destination address */
 	case SIOCSIFNETMASK: 	/* Set the netmask for the interface */
 		ret = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto out;
 		ret = -EINVAL;
 		if (sin->sin_family != AF_INET)

net/ipv4/fib_frontend.c

@@ -488,7 +488,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	switch (cmd) {
 	case SIOCADDRT:		/* Add a route */
 	case SIOCDELRT:		/* Delete a route */
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 
 		if (copy_from_user(&rt, arg, sizeof(rt)))

net/ipv4/ip_gre.c

@@ -1064,7 +1064,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCADDTUNNEL:
 	case SIOCCHGTUNNEL:
 		err = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto done;
 
 		err = -EFAULT;
@@ -1139,7 +1139,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 
 	case SIOCDELTUNNEL:
 		err = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto done;
 
 		if (dev == ign->fb_tunnel_dev) {

net/ipv4/ip_options.c

@@ -409,7 +409,7 @@ int ip_options_compile(struct net *net,
 					optptr[2] += 8;
 					break;
 				      default:
-					if (!skb && !capable(CAP_NET_RAW)) {
+					if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) {
 						pp_ptr = optptr + 3;
 						goto error;
 					}
@@ -445,7 +445,7 @@ int ip_options_compile(struct net *net,
 				opt->router_alert = optptr - iph;
 			break;
 		      case IPOPT_CIPSO:
-			if ((!skb && !capable(CAP_NET_RAW)) || opt->cipso) {
+			if ((!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) || opt->cipso) {
 				pp_ptr = optptr;
 				goto error;
 			}
@@ -458,7 +458,7 @@ int ip_options_compile(struct net *net,
 		      case IPOPT_SEC:
 		      case IPOPT_SID:
 		      default:
-			if (!skb && !capable(CAP_NET_RAW)) {
+			if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) {
 				pp_ptr = optptr;
 				goto error;
 			}

net/ipv4/ip_sockglue.c

@@ -989,13 +989,14 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 	case IP_IPSEC_POLICY:
 	case IP_XFRM_POLICY:
 		err = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 			break;
 		err = xfrm_user_policy(sk, optname, optval, optlen);
 		break;
 
 	case IP_TRANSPARENT:
-		if (!!val && !capable(CAP_NET_RAW) && !capable(CAP_NET_ADMIN)) {
+		if (!!val && !ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			err = -EPERM;
 			break;
 		}

net/ipv4/ip_vti.c

@@ -488,7 +488,7 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCADDTUNNEL:
 	case SIOCCHGTUNNEL:
 		err = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto done;
 
 		err = -EFAULT;
@@ -553,7 +553,7 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 	case SIOCDELTUNNEL:
 		err = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto done;
 
 		if (dev == ipn->fb_tunnel_dev) {

net/ipv4/ipip.c

@@ -691,7 +691,7 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCADDTUNNEL:
 	case SIOCCHGTUNNEL:
 		err = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto done;
 
 		err = -EFAULT;
@@ -735,7 +735,7 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 
 	case SIOCDELTUNNEL:
 		err = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto done;
 
 		if (dev == ipn->fb_tunnel_dev) {

net/ipv4/ipmr.c

@@ -1213,7 +1213,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 
 	if (optname != MRT_INIT) {
 		if (sk != rcu_access_pointer(mrt->mroute_sk) &&
-		    !capable(CAP_NET_ADMIN))
+		    !ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EACCES;
 	}
 

net/ipv4/netfilter/arp_tables.c

@@ -1533,7 +1533,7 @@ static int compat_do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user,
 {
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	switch (cmd) {
@@ -1677,7 +1677,7 @@ static int compat_do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user,
 {
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	switch (cmd) {
@@ -1698,7 +1698,7 @@ static int do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned
 {
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	switch (cmd) {
@@ -1722,7 +1722,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
 {
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	switch (cmd) {

net/ipv4/netfilter/ip_tables.c

@@ -1846,7 +1846,7 @@ compat_do_ipt_set_ctl(struct sock *sk,	int cmd, void __user *user,
 {
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	switch (cmd) {
@@ -1961,7 +1961,7 @@ compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 {
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	switch (cmd) {
@@ -1983,7 +1983,7 @@ do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 {
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	switch (cmd) {
@@ -2008,7 +2008,7 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 {
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	switch (cmd) {

net/ipv4/tcp.c

@@ -2304,7 +2304,7 @@ void tcp_sock_destruct(struct sock *sk)
 
 static inline bool tcp_can_repair_sock(const struct sock *sk)
 {
-	return capable(CAP_NET_ADMIN) &&
+	return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) &&
 		((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED));
 }
 

net/ipv4/tcp_cong.c

@@ -259,7 +259,8 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 	if (!ca)
 		err = -ENOENT;
 
-	else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || capable(CAP_NET_ADMIN)))
+	else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
+		   ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)))
 		err = -EPERM;
 
 	else if (!try_module_get(ca->owner))