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>
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d5e5a05..4f5f220 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -346,7 +346,8 @@
}
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 4780045..ce6fbdf 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1161,7 +1161,7 @@
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 4170935..259622a 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -730,7 +730,7 @@
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 @@
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)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index bce4541..784716a 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -488,7 +488,7 @@
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 127f2a1..a85ae2f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1064,7 +1064,7 @@
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 @@
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 1dc01f9..f6289bf 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -409,7 +409,7 @@
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 @@
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 @@
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 14bbfcf..3c9d208 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -989,13 +989,14 @@
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/ip_vti.c b/net/ipv4/ip_vti.c
index f4a825d..c3a4233 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -488,7 +488,7 @@
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 @@
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/ipip.c b/net/ipv4/ipip.c
index c26c171..191fc24 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -691,7 +691,7 @@
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 @@
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 6168c4d..adf3d34 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1213,7 +1213,7 @@
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 97e61ea..3ea4127 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1533,7 +1533,7 @@
{
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 @@
{
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 @@
{
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 @@
{
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 170b1fd..17c5e06 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1846,7 +1846,7 @@
{
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 @@
{
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 @@
{
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 @@
{
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.c b/net/ipv4/tcp.c
index 4aefa0b..e6eace1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2304,7 +2304,7 @@
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));
}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 1432cdb..baf2861 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -259,7 +259,8 @@
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))
