Commit 0189197f authored by Eric W. Biederman's avatar Eric W. Biederman Committed by David S. Miller

mpls: Basic routing support

This change adds a new Kconfig option MPLS_ROUTING.

The core of this change is the code to look at an mpls packet received
from another machine.  Look that packet up in a routing table and
forward the packet on.

Support of MPLS over ATM is not considered or attempted here.  This
implemntation follows RFC3032 and implements the MPLS shim header that
can pass over essentially any network.

What RFC3021 refers to as the as the Incoming Label Map (ILM) I call
net->mpls.platform_label[].  What RFC3031 refers to as the Next Label
Hop Forwarding Entry (NHLFE) I call mpls_route.  Though calling it the
label fordwarding information base (lfib) might also be valid.

Further the implemntation forwards packets as described in RFC3032.
There is no need and given the original motivation for MPLS a strong
discincentive to have a flexible label forwarding path.  In essence
the logic is the topmost label is read, looked up, removed, and
replaced by 0 or more new lables and the sent out the specified
interface to it's next hop.

Quite a few optional features are not implemented here.  Among them
are generation of ICMP errors when the TTL is exceeded or the packet
is larger than the next hop MTU (those conditions are detected and the
packets are dropped instead of generating an icmp error).  The traffic
class field is always set to 0.  The implementation focuses on IP over
MPLS and does not handle egress of other kinds of protocols.

Instead of implementing coordination with the neighbour table and
sorting out how to input next hops in a different address family (for
which there is value).  I was lazy and implemented a next hop mac
address instead.  The code is simpler and there are flavor of MPLS
such as MPLS-TP where neither an IPv4 nor an IPv6 next hop is
appropriate so a next hop by mac address would need to be implemented
at some point.

Two new definitions AF_MPLS and PF_MPLS are exposed to userspace.

Decoding the mpls header must be done by first byeswapping a 32bit bit
endian word into the local cpu endian and then bit shifting to extract
the pieces.  There is no C bit-field that can represent a wire format
mpls header on a little endian machine as the low bits of the 20bit
label wind up in the wrong half of third byte.  Therefore internally
everything is deal with in cpu native byte order except when writing
to and reading from a packet.

For management simplicity if a label is configured to forward out
an interface that is down the packet is dropped early.  Similarly
if an network interface is removed rt_dev is updated to NULL
(so no reference is preserved) and any packets for that label
are dropped.  Keeping the label entries in the kernel allows
the kernel label table to function as the definitive source
of which labels are allocated and which are not.
Signed-off-by: default avatar"Eric W. Biederman" <>
Signed-off-by: default avatarDavid S. Miller <>
parent cec9166c
......@@ -181,6 +181,7 @@ struct ucred {
#define AF_WANPIPE 25 /* Wanpipe API Sockets */
#define AF_LLC 26 /* Linux LLC */
#define AF_IB 27 /* Native InfiniBand address */
#define AF_MPLS 28 /* MPLS */
#define AF_CAN 29 /* Controller Area Network */
#define AF_TIPC 30 /* TIPC sockets */
#define AF_BLUETOOTH 31 /* Bluetooth sockets */
......@@ -226,6 +227,7 @@ struct ucred {
#define PF_LLC AF_LLC
#define PF_IB AF_IB
#define PF_CAN AF_CAN
......@@ -26,6 +26,7 @@
#include <net/netns/nftables.h>
#include <net/netns/xfrm.h>
#include <net/netns/mpls.h>
#include <linux/ns_common.h>
struct user_namespace;
......@@ -129,6 +130,9 @@ struct net {
struct netns_ipvs *ipvs;
struct netns_mpls mpls;
struct sock *diag_nlsk;
atomic_t fnhe_genid;
* mpls in net namespaces
#ifndef __NETNS_MPLS_H__
#define __NETNS_MPLS_H__
struct mpls_route;
struct netns_mpls {
size_t platform_labels;
struct mpls_route __rcu * __rcu *platform_label;
#endif /* __NETNS_MPLS_H__ */
......@@ -22,4 +22,9 @@ config NET_MPLS_GSO
that have had MPLS stack entries pushed onto them and thus
become MPLS GSO packets.
bool "MPLS: routing support"
Add support for forwarding of mpls packets.
endif # MPLS
......@@ -2,3 +2,4 @@
# Makefile for MPLS.
obj-$(CONFIG_NET_MPLS_GSO) += mpls_gso.o
obj-$(CONFIG_MPLS_ROUTING) += af_mpls.o
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/socket.h>
#include <linux/net.h>
#include <linux/module.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/mpls.h>
#include <net/ip.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/ip_fib.h>
#include <net/netevent.h>
#include <net/netns/generic.h>
#include "internal.h"
#define MAX_NEW_LABELS 2
/* This maximum ha length copied from the definition of struct neighbour */
#define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long)))
struct mpls_route { /* next hop label forwarding entry */
struct net_device *rt_dev;
struct rcu_head rt_rcu;
u32 rt_label[MAX_NEW_LABELS];
u8 rt_protocol; /* routing protocol that set this entry */
u8 rt_labels:2,
unsigned short rt_via_family;
u8 rt_via[0];
static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index)
struct mpls_route *rt = NULL;
if (index < net->mpls.platform_labels) {
struct mpls_route __rcu **platform_label =
rt = rcu_dereference(platform_label[index]);
return rt;
static bool mpls_output_possible(const struct net_device *dev)
return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev);
static unsigned int mpls_rt_header_size(const struct mpls_route *rt)
/* The size of the layer 2.5 labels to be added for this route */
return rt->rt_labels * sizeof(struct mpls_shim_hdr);
static unsigned int mpls_dev_mtu(const struct net_device *dev)
/* The amount of data the layer 2 frame can hold */
return dev->mtu;
static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
if (skb->len <= mtu)
return false;
if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
return false;
return true;
static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
struct mpls_entry_decoded dec)
/* RFC4385 and RFC5586 encode other packets in mpls such that
* they don't conflict with the ip version number, making
* decoding by examining the ip version correct in everything
* except for the strangest cases.
* The strange cases if we choose to support them will require
* manual configuration.
struct iphdr *hdr4 = ip_hdr(skb);
bool success = true;
if (hdr4->version == 4) {
skb->protocol = htons(ETH_P_IP);
htons(hdr4->ttl << 8),
htons(dec.ttl << 8));
hdr4->ttl = dec.ttl;
else if (hdr4->version == 6) {
struct ipv6hdr *hdr6 = ipv6_hdr(skb);
skb->protocol = htons(ETH_P_IPV6);
hdr6->hop_limit = dec.ttl;
/* version 0 and version 1 are used by pseudo wires */
success = false;
return success;
static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
struct net *net = dev_net(dev);
struct mpls_shim_hdr *hdr;
struct mpls_route *rt;
struct mpls_entry_decoded dec;
struct net_device *out_dev;
unsigned int hh_len;
unsigned int new_header_size;
unsigned int mtu;
int err;
/* Careful this entire function runs inside of an rcu critical section */
if (skb->pkt_type != PACKET_HOST)
goto drop;
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
goto drop;
if (!pskb_may_pull(skb, sizeof(*hdr)))
goto drop;
/* Read and decode the label */
hdr = mpls_hdr(skb);
dec = mpls_entry_decode(hdr);
/* Pop the label */
skb_pull(skb, sizeof(*hdr));
rt = mpls_route_input_rcu(net, dec.label);
if (!rt)
goto drop;
/* Find the output device */
out_dev = rt->rt_dev;
if (!mpls_output_possible(out_dev))
goto drop;
if (skb_warn_if_lro(skb))
goto drop;
/* Verify ttl is valid */
if (dec.ttl <= 2)
goto drop;
dec.ttl -= 1;
/* Verify the destination can hold the packet */
new_header_size = mpls_rt_header_size(rt);
mtu = mpls_dev_mtu(out_dev);
if (mpls_pkt_too_big(skb, mtu - new_header_size))
goto drop;
hh_len = LL_RESERVED_SPACE(out_dev);
if (!out_dev->header_ops)
hh_len = 0;
/* Ensure there is enough space for the headers in the skb */
if (skb_cow(skb, hh_len + new_header_size))
goto drop;
skb->dev = out_dev;
skb->protocol = htons(ETH_P_MPLS_UC);
if (unlikely(!new_header_size && dec.bos)) {
/* Penultimate hop popping */
if (!mpls_egress(rt, skb, dec))
goto drop;
} else {
bool bos;
int i;
skb_push(skb, new_header_size);
/* Push the new labels */
hdr = mpls_hdr(skb);
bos = dec.bos;
for (i = rt->rt_labels - 1; i >= 0; i--) {
hdr[i] = mpls_entry_encode(rt->rt_label[i], dec.ttl, 0, bos);
bos = false;
err = neigh_xmit(rt->rt_via_family, out_dev, rt->rt_via, skb);
if (err)
net_dbg_ratelimited("%s: packet transmission failed: %d\n",
__func__, err);
return 0;
return NET_RX_DROP;
static struct packet_type mpls_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_MPLS_UC),
.func = mpls_forward,
static struct mpls_route *mpls_rt_alloc(size_t alen)
struct mpls_route *rt;
rt = kzalloc(GFP_KERNEL, sizeof(*rt) + alen);
if (rt)
rt->rt_via_alen = alen;
return rt;
static void mpls_rt_free(struct mpls_route *rt)
if (rt)
kfree_rcu(rt, rt_rcu);
static void mpls_route_update(struct net *net, unsigned index,
struct net_device *dev, struct mpls_route *new,
const struct nl_info *info)
struct mpls_route *rt, *old = NULL;
rt = net->mpls.platform_label[index];
if (!dev || (rt && (rt->rt_dev == dev))) {
rcu_assign_pointer(net->mpls.platform_label[index], new);
old = rt;
/* If we removed a route free it now */
static void mpls_ifdown(struct net_device *dev)
struct net *net = dev_net(dev);
unsigned index;
for (index = 0; index < net->mpls.platform_labels; index++) {
struct mpls_route *rt = net->mpls.platform_label[index];
if (!rt)
if (rt->rt_dev != dev)
rt->rt_dev = NULL;
static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
void *ptr)
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
switch(event) {
return NOTIFY_OK;
static struct notifier_block mpls_dev_notifier = {
.notifier_call = mpls_dev_notify,
static int mpls_net_init(struct net *net)
net->mpls.platform_labels = 0;
net->mpls.platform_label = NULL;
return 0;
static void mpls_net_exit(struct net *net)
unsigned int index;
/* An rcu grace period haselapsed since there was a device in
* the network namespace (and thus the last in fqlight packet)
* left this network namespace. This is because
* unregister_netdevice_many and netdev_run_todo has completed
* for each network device that was in this network namespace.
* As such no additional rcu synchronization is necessary when
* freeing the platform_label table.
for (index = 0; index < net->mpls.platform_labels; index++) {
struct mpls_route *rt = net->mpls.platform_label[index];
rcu_assign_pointer(net->mpls.platform_label[index], NULL);
static struct pernet_operations mpls_net_ops = {
.init = mpls_net_init,
.exit = mpls_net_exit,
static int __init mpls_init(void)
int err;
BUILD_BUG_ON(sizeof(struct mpls_shim_hdr) != 4);
err = register_pernet_subsys(&mpls_net_ops);
if (err)
goto out;
err = register_netdevice_notifier(&mpls_dev_notifier);
if (err)
goto out_unregister_pernet;
err = 0;
return err;
goto out;
static void __exit mpls_exit(void)
MODULE_DESCRIPTION("MultiProtocol Label Switching");
#define LABEL_IPV4_EXPLICIT_NULL 0 /* RFC3032 */
#define LABEL_ROUTER_ALERT_LABEL 1 /* RFC3032 */
#define LABEL_IPV6_EXPLICIT_NULL 2 /* RFC3032 */
#define LABEL_IMPLICIT_NULL 3 /* RFC3032 */
#define LABEL_GAL 13 /* RFC5586 */
#define LABEL_OAM_ALERT 14 /* RFC3429 */
#define LABEL_EXTENSION 15 /* RFC7274 */
struct mpls_shim_hdr {
__be32 label_stack_entry;
struct mpls_entry_decoded {
u32 label;
u8 ttl;
u8 tc;
u8 bos;
struct sk_buff;
static inline struct mpls_shim_hdr *mpls_hdr(const struct sk_buff *skb)
return (struct mpls_shim_hdr *)skb_network_header(skb);
static inline struct mpls_shim_hdr mpls_entry_encode(u32 label, unsigned ttl, unsigned tc, bool bos)
struct mpls_shim_hdr result;
result.label_stack_entry =
cpu_to_be32((label << MPLS_LS_LABEL_SHIFT) |
(tc << MPLS_LS_TC_SHIFT) |
(bos ? (1 << MPLS_LS_S_SHIFT) : 0) |
(ttl << MPLS_LS_TTL_SHIFT));
return result;
static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr *hdr)
struct mpls_entry_decoded result;
unsigned entry = be32_to_cpu(hdr->label_stack_entry);
result.label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
result.ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; = (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT;
result.bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT;
return result;
#endif /* MPLS_INTERNAL_H */
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment