linux/net/openvswitch/vport-vxlan.c
Thomas Graf 3511494ce2 vxlan: Group Policy extension
Implements supports for the Group Policy VXLAN extension [0] to provide
a lightweight and simple security label mechanism across network peers
based on VXLAN. The security context and associated metadata is mapped
to/from skb->mark. This allows further mapping to a SELinux context
using SECMARK, to implement ACLs directly with nftables, iptables, OVS,
tc, etc.

The group membership is defined by the lower 16 bits of skb->mark, the
upper 16 bits are used for flags.

SELinux allows to manage label to secure local resources. However,
distributed applications require ACLs to implemented across hosts. This
is typically achieved by matching on L2-L4 fields to identify the
original sending host and process on the receiver. On top of that,
netlabel and specifically CIPSO [1] allow to map security contexts to
universal labels.  However, netlabel and CIPSO are relatively complex.
This patch provides a lightweight alternative for overlay network
environments with a trusted underlay. No additional control protocol
is required.

           Host 1:                       Host 2:

      Group A        Group B        Group B     Group A
      +-----+   +-------------+    +-------+   +-----+
      | lxc |   | SELinux CTX |    | httpd |   | VM  |
      +--+--+   +--+----------+    +---+---+   +--+--+
	  \---+---/                     \----+---/
	      |                              |
	  +---+---+                      +---+---+
	  | vxlan |                      | vxlan |
	  +---+---+                      +---+---+
	      +------------------------------+

Backwards compatibility:
A VXLAN-GBP socket can receive standard VXLAN frames and will assign
the default group 0x0000 to such frames. A Linux VXLAN socket will
drop VXLAN-GBP  frames. The extension is therefore disabled by default
and needs to be specifically enabled:

   ip link add [...] type vxlan [...] gbp

In a mixed environment with VXLAN and VXLAN-GBP sockets, the GBP socket
must run on a separate port number.

Examples:
 iptables:
  host1# iptables -I OUTPUT -m owner --uid-owner 101 -j MARK --set-mark 0x200
  host2# iptables -I INPUT -m mark --mark 0x200 -j DROP

 OVS:
  # ovs-ofctl add-flow br0 'in_port=1,actions=load:0x200->NXM_NX_TUN_GBP_ID[],NORMAL'
  # ovs-ofctl add-flow br0 'in_port=2,tun_gbp_id=0x200,actions=drop'

[0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy
[1] http://lwn.net/Articles/204905/

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-15 01:11:41 -05:00

243 lines
6.0 KiB
C

/*
* Copyright (c) 2014 Nicira, Inc.
* Copyright (c) 2013 Cisco Systems, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <linux/rculist.h>
#include <linux/udp.h>
#include <linux/module.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/ip_tunnels.h>
#include <net/rtnetlink.h>
#include <net/route.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/vxlan.h>
#include "datapath.h"
#include "vport.h"
/**
* struct vxlan_port - Keeps track of open UDP ports
* @vs: vxlan_sock created for the port.
* @name: vport name.
*/
struct vxlan_port {
struct vxlan_sock *vs;
char name[IFNAMSIZ];
};
static struct vport_ops ovs_vxlan_vport_ops;
static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
{
return vport_priv(vport);
}
/* Called with rcu_read_lock and BH disabled. */
static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
struct vxlan_metadata *md)
{
struct ovs_tunnel_info tun_info;
struct vport *vport = vs->data;
struct iphdr *iph;
__be64 key;
/* Save outer tunnel values */
iph = ip_hdr(skb);
key = cpu_to_be64(ntohl(md->vni) >> 8);
ovs_flow_tun_info_init(&tun_info, iph,
udp_hdr(skb)->source, udp_hdr(skb)->dest,
key, TUNNEL_KEY, NULL, 0);
ovs_vport_receive(vport, skb, &tun_info);
}
static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
{
struct vxlan_port *vxlan_port = vxlan_vport(vport);
__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port)))
return -EMSGSIZE;
return 0;
}
static void vxlan_tnl_destroy(struct vport *vport)
{
struct vxlan_port *vxlan_port = vxlan_vport(vport);
vxlan_sock_release(vxlan_port->vs);
ovs_vport_deferred_free(vport);
}
static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
{
struct net *net = ovs_dp_get_net(parms->dp);
struct nlattr *options = parms->options;
struct vxlan_port *vxlan_port;
struct vxlan_sock *vs;
struct vport *vport;
struct nlattr *a;
u16 dst_port;
int err;
if (!options) {
err = -EINVAL;
goto error;
}
a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT);
if (a && nla_len(a) == sizeof(u16)) {
dst_port = nla_get_u16(a);
} else {
/* Require destination port from userspace. */
err = -EINVAL;
goto error;
}
vport = ovs_vport_alloc(sizeof(struct vxlan_port),
&ovs_vxlan_vport_ops, parms);
if (IS_ERR(vport))
return vport;
vxlan_port = vxlan_vport(vport);
strncpy(vxlan_port->name, parms->name, IFNAMSIZ);
vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, 0);
if (IS_ERR(vs)) {
ovs_vport_free(vport);
return (void *)vs;
}
vxlan_port->vs = vs;
return vport;
error:
return ERR_PTR(err);
}
static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
{
struct net *net = ovs_dp_get_net(vport->dp);
struct vxlan_port *vxlan_port = vxlan_vport(vport);
__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
const struct ovs_key_ipv4_tunnel *tun_key;
struct vxlan_metadata md = {0};
struct rtable *rt;
struct flowi4 fl;
__be16 src_port;
__be16 df;
int err;
if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
err = -EINVAL;
goto error;
}
tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
goto error;
}
df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
htons(IP_DF) : 0;
skb->ignore_df = 1;
src_port = udp_flow_src_port(net, skb, 0, 0, true);
md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8);
err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
fl.saddr, tun_key->ipv4_dst,
tun_key->ipv4_tos, tun_key->ipv4_ttl, df,
src_port, dst_port,
&md,
false);
if (err < 0)
ip_rt_put(rt);
return err;
error:
kfree_skb(skb);
return err;
}
static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
struct ovs_tunnel_info *egress_tun_info)
{
struct net *net = ovs_dp_get_net(vport->dp);
struct vxlan_port *vxlan_port = vxlan_vport(vport);
__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
__be16 src_port;
int port_min;
int port_max;
inet_get_local_port_range(net, &port_min, &port_max);
src_port = udp_flow_src_port(net, skb, 0, 0, true);
return ovs_tunnel_get_egress_info(egress_tun_info, net,
OVS_CB(skb)->egress_tun_info,
IPPROTO_UDP, skb->mark,
src_port, dst_port);
}
static const char *vxlan_get_name(const struct vport *vport)
{
struct vxlan_port *vxlan_port = vxlan_vport(vport);
return vxlan_port->name;
}
static struct vport_ops ovs_vxlan_vport_ops = {
.type = OVS_VPORT_TYPE_VXLAN,
.create = vxlan_tnl_create,
.destroy = vxlan_tnl_destroy,
.get_name = vxlan_get_name,
.get_options = vxlan_get_options,
.send = vxlan_tnl_send,
.get_egress_tun_info = vxlan_get_egress_tun_info,
.owner = THIS_MODULE,
};
static int __init ovs_vxlan_tnl_init(void)
{
return ovs_vport_ops_register(&ovs_vxlan_vport_ops);
}
static void __exit ovs_vxlan_tnl_exit(void)
{
ovs_vport_ops_unregister(&ovs_vxlan_vport_ops);
}
module_init(ovs_vxlan_tnl_init);
module_exit(ovs_vxlan_tnl_exit);
MODULE_DESCRIPTION("OVS: VXLAN switching port");
MODULE_LICENSE("GPL");
MODULE_ALIAS("vport-type-4");