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

3 files changed, 21 insertions, 0 deletions

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 5c19cba34dce..fab4d0ddf4ed 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -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_WANPIPE	AF_WANPIPE
 #define PF_LLC		AF_LLC
 #define PF_IB		AF_IB
+#define PF_MPLS		AF_MPLS
 #define PF_CAN		AF_CAN
 #define PF_TIPC		AF_TIPC
 #define PF_BLUETOOTH	AF_BLUETOOTH
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 36faf4990c4b..2cb9acb618e9 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -26,6 +26,7 @@
 #endif
 #include <net/netns/nftables.h>
 #include <net/netns/xfrm.h>
+#include <net/netns/mpls.h>
 #include <linux/ns_common.h>
 
 struct user_namespace;
@@ -130,6 +131,9 @@ struct net {
 #if IS_ENABLED(CONFIG_IP_VS)
 	struct netns_ipvs	*ipvs;
 #endif
+#if IS_ENABLED(CONFIG_MPLS)
+	struct netns_mpls	mpls;
+#endif
 	struct sock		*diag_nlsk;
 	atomic_t		fnhe_genid;
 };
diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h
new file mode 100644
index 000000000000..f90aaf8d4f89
--- /dev/null
+++ b/include/net/netns/mpls.h
@@ -0,0 +1,15 @@
+/*
+ * 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__ */