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.

Change-Id: I3b6ce2465e354cd2865e1a7fe67d6e812f88b16a
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

12 files changed, 27 insertions, 24 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 770355376a9..be386d7791c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -355,7 +355,8 @@ lookup_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;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 18d9b81ecb1..67a141df282 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1171,7 +1171,7 @@ 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));
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 2f274b8a35a..d955f1592de 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -732,7 +732,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 
 	case SIOCSIFFLAGS:
 		ret = -EACCES;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto out;
 		break;
 	case SIOCSIFADDR:	/* Set interface address (and family) */
@@ -741,7 +741,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	case SIOCSIFNETMASK: 	/* Set the netmask for the interface */
 	case SIOCKILLADDR:	/* Nuke all sockets on this address */
 		ret = -EACCES;
-		if (!capable(CAP_NET_ADMIN))
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto out;
 		ret = -EINVAL;
 		if (sin->sin_family != AF_INET)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b6381bfddde..b8a662a1353 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -436,7 +436,7 @@ 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)))
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index a16509cba75..b2db059b816 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1022,7 +1022,7 @@ 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;
@@ -1097,7 +1097,7 @@ 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) {
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 52354173077..416e1daf652 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -399,7 +399,7 @@ 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;
 					}
@@ -435,7 +435,7 @@ 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;
 			}
@@ -448,7 +448,7 @@ 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;
 			}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d48a978d21a..82f6e854640 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -984,13 +984,14 @@ mc_msf_out:
 	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;
 		}
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 490132664d0..fbc73b3ff08 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -630,7 +630,7 @@ 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;
@@ -690,7 +690,7 @@ 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) {
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index b2a73a3bad5..7b2ada0695f 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1217,7 +1217,7 @@ 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;
 	}
 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 8037afe159a..fb96e0f1de8 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1543,7 +1543,7 @@ 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) {
@@ -1687,7 +1687,7 @@ 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) {
@@ -1708,7 +1708,7 @@ 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) {
@@ -1732,7 +1732,7 @@ 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) {
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index cf63e6cf282..34780598f58 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1855,7 +1855,7 @@ 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) {
@@ -1970,7 +1970,7 @@ 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) {
@@ -1992,7 +1992,7 @@ 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) {
@@ -2017,7 +2017,7 @@ 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) {
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 69251dde750..8a28a865727 100644
--- a/net/ipv4/tcp_cong.c
+++ b/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))