add basic mpls support to iproute

- Pull in the uapi mpls.h
- Update rtnetlink.h to include the mpls rtnetlink notification multicast group.
- Define AF_MPLS in utils.h if it is not defined from elsewhere
  as is done with AF_DECnet

The address syntax for multiple mpls labels is a complete invention.
When I looked there seemed to be no wide spread convention for talking
about an mpls label stack in text for.  Sometimes people did:
"{ Label1, Label2, Label3 }", sometimes people would do:
"[ label3, label2, label1 ]", and most of the time label
stacks were not explicitly shown at all.

The syntax I wound up using, so it would not have spaces and so it
would visually distinct from other kinds of addresses is.

label1/label2/label3 Where label1 is the label at the top of the label
stack and label3 is the label at the bottom on the label stack.

When there is a single label this matches what seems to be convention
with other tools.  Just print out the numeric value of the mpls label.

The netlink protocol for labels uses the on the wire format for a
label stack. The ttl and traffic class are expected to be 0.  Using
the on the wire format is common and what happens with other address
types. BGP when passing label stacks also uses this technique with the
exception that the ttl byte is not included making each label in a BGP
label stack 3 bytes instead of 4.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

Makefile

@@ -26,6 +26,9 @@ ADDLIB+=dnet_ntop.o dnet_pton.o
 #options for ipx
 ADDLIB+=ipx_ntop.o ipx_pton.o
 
+#options for mpls
+ADDLIB+=mpls_ntop.o mpls_pton.o
+
 CC = gcc
 HOSTCC = gcc
 DEFINES += -D_GNU_SOURCE

include/linux/mpls.h

+#ifndef _MPLS_H
+#define _MPLS_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/* Reference: RFC 5462, RFC 3032
+ *
+ *  0                   1                   2                   3
+ *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                Label                  | TC  |S|       TTL     |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ *	Label:  Label Value, 20 bits
+ *	TC:     Traffic Class field, 3 bits
+ *	S:      Bottom of Stack, 1 bit
+ *	TTL:    Time to Live, 8 bits
+ */
+
+struct mpls_label {
+	__be32 entry;
+};
+
+#define MPLS_LS_LABEL_MASK      0xFFFFF000
+#define MPLS_LS_LABEL_SHIFT     12
+#define MPLS_LS_TC_MASK         0x00000E00
+#define MPLS_LS_TC_SHIFT        9
+#define MPLS_LS_S_MASK          0x00000100
+#define MPLS_LS_S_SHIFT         8
+#define MPLS_LS_TTL_MASK        0x000000FF
+#define MPLS_LS_TTL_SHIFT       0
+
+#endif /* _MPLS_H */

include/utils.h

@@ -78,6 +78,13 @@ struct ipx_addr {
 	u_int8_t  ipx_node[IPX_NODE_LEN];
 };
 
+#ifndef AF_MPLS
+# define AF_MPLS 28
+#endif
+
+/* Maximum number of labels the mpls helpers support */
+#define MPLS_MAX_LABELS 8
+
 extern __u32 get_addr32(const char *name);
 extern int get_addr_1(inet_prefix *dst, const char *arg, int family);
 extern int get_prefix_1(inet_prefix *dst, char *arg, int family);
@@ -126,6 +133,9 @@ int dnet_pton(int af, const char *src, void *addr);
 const char *ipx_ntop(int af, const void *addr, char *str, size_t len);
 int ipx_pton(int af, const char *src, void *addr);
 
+const char *mpls_ntop(int af, const void *addr, char *str, size_t len);
+int mpls_pton(int af, const char *src, void *addr);
+
 extern int __iproute2_hz_internal;
 extern int __get_hz(void);
 

ip/ip.c

@@ -52,7 +52,7 @@ static void usage(void)
 "                   netns | l2tp | fou | tcp_metrics | token | netconf }\n"
 "       OPTIONS := { -V[ersion] | -s[tatistics] | -d[etails] | -r[esolve] |\n"
 "                    -h[uman-readable] | -iec |\n"
-"                    -f[amily] { inet | inet6 | ipx | dnet | bridge | link } |\n"
+"                    -f[amily] { inet | inet6 | ipx | dnet | mpls | bridge | link } |\n"
 "                    -4 | -6 | -I | -D | -B | -0 |\n"
 "                    -l[oops] { maximum-addr-flush-attempts } |\n"
 "                    -o[neline] | -t[imestamp] | -ts[hort] | -b[atch] [filename] |\n"
@@ -206,6 +206,8 @@ int main(int argc, char **argv)
 			preferred_family = AF_IPX;
 		} else if (strcmp(opt, "-D") == 0) {
 			preferred_family = AF_DECnet;
+		} else if (strcmp(opt, "-M") == 0) {
+			preferred_family = AF_MPLS;
 		} else if (strcmp(opt, "-B") == 0) {
 			preferred_family = AF_BRIDGE;
 		} else if (matches(opt, "-human") == 0 ||

ip/ipmonitor.c

@@ -158,6 +158,7 @@ int do_ipmonitor(int argc, char **argv)
 	groups |= nl_mgrp(RTNLGRP_IPV6_IFADDR);
 	groups |= nl_mgrp(RTNLGRP_IPV4_ROUTE);
 	groups |= nl_mgrp(RTNLGRP_IPV6_ROUTE);
+	groups |= nl_mgrp(RTNLGRP_MPLS_ROUTE);
 	groups |= nl_mgrp(RTNLGRP_IPV4_MROUTE);
 	groups |= nl_mgrp(RTNLGRP_IPV6_MROUTE);
 	groups |= nl_mgrp(RTNLGRP_IPV6_PREFIX);
@@ -235,6 +236,8 @@ int do_ipmonitor(int argc, char **argv)
 			groups |= nl_mgrp(RTNLGRP_IPV4_ROUTE);
 		if (!preferred_family || preferred_family == AF_INET6)
 			groups |= nl_mgrp(RTNLGRP_IPV6_ROUTE);
+		if (!preferred_family || preferred_family == AF_MPLS)
+			groups |= nl_mgrp(RTNLGRP_MPLS_ROUTE);
 	}
 	if (lmroute) {
 		if (!preferred_family || preferred_family == AF_INET)

ip/iproute.c

@@ -76,7 +76,7 @@ static void usage(void)
 	fprintf(stderr, "             [ scope SCOPE ] [ metric METRIC ]\n");
 	fprintf(stderr, "INFO_SPEC := NH OPTIONS FLAGS [ nexthop NH ]...\n");
 	fprintf(stderr, "NH := [ via [ FAMILY ] ADDRESS ] [ dev STRING ] [ weight NUMBER ] NHFLAGS\n");
-	fprintf(stderr, "FAMILY := [ inet | inet6 | ipx | dnet | bridge | link ]");
+	fprintf(stderr, "FAMILY := [ inet | inet6 | ipx | dnet | mpls | bridge | link ]");
 	fprintf(stderr, "OPTIONS := FLAGS [ mtu NUMBER ] [ advmss NUMBER ] [ as [ to ] ADDRESS ]\n");
 	fprintf(stderr, "           [ rtt TIME ] [ rttvar TIME ] [ reordering NUMBER ]\n");
 	fprintf(stderr, "           [ window NUMBER] [ cwnd NUMBER ] [ initcwnd NUMBER ]\n");

lib/mpls_ntop.c

+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <netinet/in.h>
+#include <linux/mpls.h>
+
+#include "utils.h"
+
+static const char *mpls_ntop1(const struct mpls_label *addr, char *buf, size_t buflen)
+{
+	size_t destlen = buflen;
+	char *dest = buf;
+	int count;
+
+	for (count = 0; count < MPLS_MAX_LABELS; count++) {
+		uint32_t entry = ntohl(addr[count].entry);
+		uint32_t label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
+		int len = snprintf(dest, destlen, "%u", label);
+
+		/* Is this the end? */
+		if (entry & MPLS_LS_S_MASK)
+			return buf;
+
+
+		dest += len;
+		destlen -= len;
+		if (destlen) {
+			*dest = '/';
+			dest++;
+			destlen--;
+		}
+	}
+	errno = -E2BIG;
+	return NULL;
+}
+
+const char *mpls_ntop(int af, const void *addr, char *buf, size_t buflen)
+{
+	switch(af) {
+	case AF_MPLS:
+		errno = 0;
+		return mpls_ntop1((struct mpls_label *)addr, buf, buflen);
+	default:
+		errno = EAFNOSUPPORT;
+	}
+
+	return NULL;
+}

lib/mpls_pton.c

+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <netinet/in.h>
+#include <linux/mpls.h>
+
+#include "utils.h"
+
+
+static int mpls_pton1(const char *name, struct mpls_label *addr)
+{
+	char *endp;
+	unsigned count;
+
+	for (count = 0; count < MPLS_MAX_LABELS; count++) {
+		unsigned long label;
+
+		label = strtoul(name, &endp, 0);
+		/* Fail when the label value is out or range */
+		if (label >= (1 << 20))
+			return 0;
+
+		if (endp == name) /* no digits */
+			return 0;
+
+		addr->entry = htonl(label << MPLS_LS_LABEL_SHIFT);
+		if (*endp == '\0') {
+			addr->entry |= htonl(1 << MPLS_LS_S_SHIFT);
+			return 1;
+		}
+
+		/* Bad character in the address */
+		if (*endp != '/')
+			return 0;
+
+		name = endp + 1;
+		addr += 1;
+	}
+	/* The address was too long */
+	return 0;
+}
+
+int mpls_pton(int af, const char *src, void *addr)
+{
+	int err;
+
+	switch(af) {
+	case AF_MPLS:
+		errno = 0;
+		err = mpls_pton1(src, (struct mpls_label *)addr);
+		break;
+	default:
+		errno = EAFNOSUPPORT;
+		err = -1;
+	}
+
+	return err;
+}

lib/utils.c

@@ -26,6 +26,7 @@
 #include <linux/pkt_sched.h>
 #include <linux/param.h>
 #include <linux/if_arp.h>
+#include <linux/mpls.h>
 #include <time.h>
 #include <sys/time.h>
 #include <errno.h>
@@ -390,7 +391,7 @@ int get_addr_1(inet_prefix *addr, const char *name, int family)
 	if (strcmp(name, "default") == 0 ||
 	    strcmp(name, "all") == 0 ||
 	    strcmp(name, "any") == 0) {
-		if (family == AF_DECnet)
+		if ((family == AF_DECnet) || (family == AF_MPLS))
 			return -1;
 		addr->family = family;
 		addr->bytelen = (family == AF_INET6 ? 16 : 4);
@@ -432,6 +433,23 @@ int get_addr_1(inet_prefix *addr, const char *name, int family)
 		return 0;
 	}
 
+	if (family == AF_MPLS) {
+		int i;
+		addr->family = AF_MPLS;
+		if (mpls_pton(AF_MPLS, name, addr->data) <= 0)
+			return -1;
+		addr->bytelen = 4;
+		addr->bitlen = 20;
+		/* How many bytes do I need? */
+		for (i = 0; i < 8; i++) {
+			if (ntohl(addr->data[i]) & MPLS_LS_S_MASK) {
+				addr->bytelen = (i + 1)*4;
+				break;
+			}
+		}
+		return 0;
+	}
+
 	addr->family = AF_INET;
 	if (family != AF_UNSPEC && family != AF_INET)
 		return -1;
@@ -455,6 +473,8 @@ int af_bit_len(int af)
 		return 16;
 	case AF_IPX:
 		return 80;
+	case AF_MPLS:
+		return 20;
 	}
 
 	return 0;
@@ -476,7 +496,7 @@ int get_prefix_1(inet_prefix *dst, char *arg, int family)
 	if (strcmp(arg, "default") == 0 ||
 	    strcmp(arg, "any") == 0 ||
 	    strcmp(arg, "all") == 0) {
-		if (family == AF_DECnet)
+		if ((family == AF_DECnet) || (family = AF_MPLS))
 			return -1;
 		dst->family = family;
 		dst->bytelen = 0;
@@ -651,6 +671,8 @@ const char *rt_addr_n2a(int af, int len, const void *addr, char *buf, int buflen
 	case AF_INET:
 	case AF_INET6:
 		return inet_ntop(af, addr, buf, buflen);
+	case AF_MPLS:
+		return mpls_ntop(af, addr, buf, buflen);
 	case AF_IPX:
 		return ipx_ntop(af, addr, buf, buflen);
 	case AF_DECnet:
@@ -679,6 +701,8 @@ int read_family(const char *name)
 		family = AF_PACKET;
 	else if (strcmp(name, "ipx") == 0)
 		family = AF_IPX;
+	else if (strcmp(name, "mpls") == 0)
+		family = AF_MPLS;
 	else if (strcmp(name, "bridge") == 0)
 		family = AF_BRIDGE;
 	return family;
@@ -696,6 +720,8 @@ const char *family_name(int family)
 		return "link";
 	if (family == AF_IPX)
 		return "ipx";
+	if (family == AF_MPLS)
+		return "mpls";
 	if (family == AF_BRIDGE)
 		return "bridge";
 	return "???";

man/man8/ip-route.8.in

@@ -90,7 +90,7 @@ replace " } "
 
 .ti -8
 .IR FAMILY " := [ "
-.BR inet " | " inet6 " | " ipx " | " dnet " | " bridge " | " link " ]"
+.BR inet " | " inet6 " | " ipx " | " dnet " | " mpls " | " bridge " | " link " ]"
 
 .ti -8
 .IR OPTIONS " := " FLAGS " [ "

man/man8/ip.8

@@ -73,7 +73,7 @@ Zero (0) means loop until all addresses are removed.
 .TP
 .BR "\-f" , " \-family " <FAMILY>
 Specifies the protocol family to use. The protocol family identifier can be one of
-.BR "inet" , " inet6" , " bridge" , " ipx" , " dnet"
+.BR "inet" , " inet6" , " bridge" , " ipx" , " dnet" , " mpls"
 or
 .BR link .
 If this option is not present,
@@ -114,6 +114,11 @@ shortcut for
 shortcut for
 .BR "\-family ipx" .
 
+.TP
+.B \-M
+shortcut for
+.BR "\-family mpls" .
+
 .TP
 .B \-0
 shortcut for