Merge commit 'ee919658' into thread-next-iface

5 files changed, 143 insertions, 48 deletions

diff --git a/doc/bird.sgml b/doc/bird.sgml
index b9ccf9f7..9a3cb996 100644
--- a/doc/bird.sgml
+++ b/doc/bird.sgml
@@ -1954,6 +1954,7 @@ protocol babel [<name>] {
 		check link <switch>;
 		next hop ipv4 <address>;
 		next hop ipv6 <address>;
+		extended next hop <switch>;
 		authentication none|mac [permissive];
 		password "&lt;text&gt;";
 		password "&lt;text&gt;" {
@@ -2058,6 +2059,11 @@ protocol babel [<name>] {
       source for Babel packets will be used. In normal operation, it should not
       be necessary to set this option.
 
+      <tag><label id="babel-extended-next-hop">extended next hop <m/switch/</tag>
+      If enabled, BIRD will accept and emit IPv4 routes with an IPv6 next
+      hop when IPv4 addresses are absent from the interface as described in
+      <rfc id="9229">. Default: yes.
+
       <tag><label id="babel-authentication">authentication none|mac [permissive]</tag>
       Selects authentication method to be used. <cf/none/ means that packets
       are not authenticated at all, <cf/mac/ means MAC authentication is
diff --git a/proto/babel/babel.c b/proto/babel/babel.c
index 83a87d8f..cf625819 100644
--- a/proto/babel/babel.c
+++ b/proto/babel/babel.c
@@ -1002,8 +1002,18 @@ babel_send_update_(struct babel_iface *ifa, btime changed, struct fib *rtable)
     msg.update.router_id = e->router_id;
     net_copy(&msg.update.net, e->n.addr);
 
-    msg.update.next_hop = ((e->n.addr->type == NET_IP4) ?
-			   ifa->next_hop_ip4 : ifa->next_hop_ip6);
+    if (e->n.addr->type == NET_IP4)
+    {
+      /* Always prefer IPv4 nexthop if set */
+      if (ipa_nonzero(ifa->next_hop_ip4))
+        msg.update.next_hop = ifa->next_hop_ip4;
+
+      /* Only send IPv6 nexthop if enabled */
+      else if (ifa->cf->ext_next_hop)
+        msg.update.next_hop = ifa->next_hop_ip6;
+    }
+    else
+      msg.update.next_hop = ifa->next_hop_ip6;
 
     /* Do not send route if next hop is unknown, e.g. no configured IPv4 address */
     if (ipa_zero(msg.update.next_hop))
@@ -1262,6 +1272,13 @@ babel_handle_update(union babel_msg *m, struct babel_iface *ifa)
     return;
   }
 
+  /* Reject IPv4 via IPv6 routes if disabled */
+  if ((msg->net.type == NET_IP4) && ipa_is_ip6(msg->next_hop) && !ifa->cf->ext_next_hop)
+  {
+    DBG("Babel: Ignoring disabled IPv4 via IPv6 route.\n");
+    return;
+  }
+
   /* Retraction */
   if (msg->metric == BABEL_INFINITY)
   {
@@ -1548,7 +1565,8 @@ babel_auth_check_pc(struct babel_iface *ifa, struct babel_msg_auth *msg)
     n->auth_index_len = msg->index_len;
     memcpy(n->auth_index, msg->index, msg->index_len);
 
-    n->auth_pc = msg->pc;
+    n->auth_pc_unicast = msg->pc;
+    n->auth_pc_multicast = msg->pc;
     n->auth_passed = 1;
 
     return 1;
@@ -1567,16 +1585,30 @@ babel_auth_check_pc(struct babel_iface *ifa, struct babel_msg_auth *msg)
     return 0;
   }
 
-  /* (6) Index matches; only accept if PC is greater than last */
-  if (n->auth_pc >= msg->pc)
+  /*
+   * (6) Index matches; only accept if PC is greater than last. We keep separate
+   * counters for unicast and multicast because multicast packets can be delayed
+   * significantly on wireless networks (enough to be received out of order).
+   * Separate counters are safe because the packet destination address is part
+   * of the MAC pseudo-header (so unicast packets can't be replayed as multicast
+   * and vice versa).
+   */
+  u32 auth_pc = msg->unicast ? n->auth_pc_unicast : n->auth_pc_multicast;
+  if (auth_pc >= msg->pc)
   {
     LOG_PKT_AUTH("Authentication failed for %I on %s - "
-		 "lower packet counter (rcv %u, old %u)",
-                 msg->sender, ifa->ifname, msg->pc, n->auth_pc);
+		 "lower %s packet counter (rcv %u, old %u)",
+                 msg->sender, ifa->ifname,
+		 msg->unicast ? "unicast" : "multicast",
+		 msg->pc, auth_pc);
     return 0;
   }
 
-  n->auth_pc = msg->pc;
+  if (msg->unicast)
+    n->auth_pc_unicast = msg->pc;
+  else
+    n->auth_pc_multicast = msg->pc;
+
   n->auth_passed = 1;
 
   return 1;
@@ -1728,7 +1760,7 @@ babel_iface_update_addr4(struct babel_iface *ifa)
   ip_addr addr4 = ifa->iface->addr4 ? ifa->iface->addr4->ip : IPA_NONE;
   ifa->next_hop_ip4 = ipa_nonzero(ifa->cf->next_hop_ip4) ? ifa->cf->next_hop_ip4 : addr4;
 
-  if (ipa_zero(ifa->next_hop_ip4) && p->ip4_channel)
+  if (ipa_zero(ifa->next_hop_ip4) && p->ip4_channel && !ifa->cf->ext_next_hop)
     log(L_WARN "%s: Missing IPv4 next hop address for %s", p->p.name, ifa->ifname);
 
   if (ifa->up)
@@ -1805,8 +1837,8 @@ babel_add_iface(struct babel_proto *p, struct iface *new, struct babel_iface_con
   ifa->next_hop_ip4 = ipa_nonzero(ic->next_hop_ip4) ? ic->next_hop_ip4 : addr4;
   ifa->next_hop_ip6 = ipa_nonzero(ic->next_hop_ip6) ? ic->next_hop_ip6 : ifa->addr;
 
-  if (ipa_zero(ifa->next_hop_ip4) && p->ip4_channel)
-    log(L_WARN "%s: Missing IPv4 next hop address for %s", p->p.name, new->name);
+  if (ipa_zero(ifa->next_hop_ip4) && p->ip4_channel && !ic->ext_next_hop)
+    log(L_WARN "%s: Missing IPv4 next hop address for %s", p->p.name, ifa->ifname);
 
   init_list(&ifa->neigh_list);
   ifa->hello_seqno = 1;
@@ -1929,7 +1961,7 @@ babel_reconfigure_iface(struct babel_proto *p, struct babel_iface *ifa, struct b
   if ((new->auth_type != BABEL_AUTH_NONE) && (new->auth_type != old->auth_type))
     babel_auth_reset_index(ifa);
 
-  if (ipa_zero(ifa->next_hop_ip4) && p->ip4_channel)
+  if (ipa_zero(ifa->next_hop_ip4) && p->ip4_channel && !new->ext_next_hop)
     log(L_WARN "%s: Missing IPv4 next hop address for %s", p->p.name, ifa->ifname);
 
   if (ifa->next_hello > (current_time() + new->hello_interval))
diff --git a/proto/babel/babel.h b/proto/babel/babel.h
index 9014ace2..562abac2 100644
--- a/proto/babel/babel.h
+++ b/proto/babel/babel.h
@@ -110,6 +110,7 @@ enum babel_ae_type {
   BABEL_AE_IP4			= 1,
   BABEL_AE_IP6			= 2,
   BABEL_AE_IP6_LL		= 3,
+  BABEL_AE_IP4_VIA_IP6		= 4,
   BABEL_AE_MAX
 };
 
@@ -143,8 +144,9 @@ struct babel_iface_config {
 
   ip_addr next_hop_ip4;
   ip_addr next_hop_ip6;
+  u8 ext_next_hop;			/* Enable IPv4 via IPv6 */
 
-  u8 auth_type;			/* Authentication type (BABEL_AUTH_*) */
+  u8 auth_type;				/* Authentication type (BABEL_AUTH_*) */
   u8 auth_permissive;			/* Don't drop packets failing auth check */
   uint mac_num_keys;			/* Number of configured HMAC keys */
   uint mac_total_len;			/* Total digest length for all configured keys */
@@ -223,7 +225,8 @@ struct babel_neighbor {
   u16 next_hello_seqno;
   uint last_hello_int;
 
-  u32 auth_pc;
+  u32 auth_pc_unicast;
+  u32 auth_pc_multicast;
   u8 auth_passed;
   u8 auth_index_len;
   u8 auth_index[BABEL_AUTH_INDEX_LEN];
@@ -401,6 +404,7 @@ struct babel_msg_auth {
   u8 challenge_seen;
   u8 challenge_len;
   u8 challenge[BABEL_AUTH_MAX_NONCE_LEN];
+  u8 unicast;
 };
 
 static inline int babel_sadr_enabled(struct babel_proto *p)
diff --git a/proto/babel/config.Y b/proto/babel/config.Y
index a4350eed..6d1ad7d0 100644
--- a/proto/babel/config.Y
+++ b/proto/babel/config.Y
@@ -25,7 +25,8 @@ CF_DECLS
 CF_KEYWORDS(BABEL, INTERFACE, METRIC, RXCOST, HELLO, UPDATE, INTERVAL, PORT,
 	TYPE, WIRED, WIRELESS, RX, TX, BUFFER, PRIORITY, LENGTH, CHECK, LINK,
 	NEXT, HOP, IPV4, IPV6, SHOW, INTERFACES, NEIGHBORS,
-	ENTRIES, RANDOMIZE, ROUTER, ID, AUTHENTICATION, NONE, MAC, PERMISSIVE)
+	ENTRIES, RANDOMIZE, ROUTER, ID, AUTHENTICATION, NONE, MAC, PERMISSIVE,
+	EXTENDED)
 
 CF_GRAMMAR
 
@@ -67,6 +68,7 @@ babel_iface_start:
   BABEL_IFACE->tx_tos = IP_PREC_INTERNET_CONTROL;
   BABEL_IFACE->tx_priority = sk_priority_control;
   BABEL_IFACE->check_link = 1;
+  BABEL_IFACE->ext_next_hop = 1;
 };
 
 
@@ -143,6 +145,7 @@ babel_iface_item:
  | CHECK LINK bool { BABEL_IFACE->check_link = $3; }
  | NEXT HOP IPV4 ipa { BABEL_IFACE->next_hop_ip4 = $4; if (!ipa_is_ip4($4)) cf_error("Must be an IPv4 address"); }
  | NEXT HOP IPV6 ipa { BABEL_IFACE->next_hop_ip6 = $4; if (!ipa_is_ip6($4)) cf_error("Must be an IPv6 address"); }
+ | EXTENDED NEXT HOP bool { BABEL_IFACE->ext_next_hop = $4; }
  | AUTHENTICATION NONE { BABEL_IFACE->auth_type = BABEL_AUTH_NONE; }
  | AUTHENTICATION MAC { BABEL_IFACE->auth_type = BABEL_AUTH_MAC; BABEL_IFACE->auth_permissive = 0; }
  | AUTHENTICATION MAC PERMISSIVE { BABEL_IFACE->auth_type = BABEL_AUTH_MAC; BABEL_IFACE->auth_permissive = 1; }
diff --git a/proto/babel/packets.c b/proto/babel/packets.c
index f13bb5ba..d26ee5c6 100644
--- a/proto/babel/packets.c
+++ b/proto/babel/packets.c
@@ -166,10 +166,12 @@ struct babel_parse_state {
   ip_addr next_hop_ip6;
   u64 router_id;		/* Router ID used in subsequent updates */
   u8 def_ip6_prefix[16];	/* Implicit IPv6 prefix in network order */
-  u8 def_ip4_prefix[4];		/* Implicit IPv4 prefix in network order */
+  u8 def_ip4_prefix[4];		/* Implicit IPv4 prefix (AE 1) in network order */
+  u8 def_ip4_via_ip6_prefix[4];	/* Implicit IPv4 prefix (AE 4) in network order */
   u8 router_id_seen;		/* router_id field is valid */
   u8 def_ip6_prefix_seen;	/* def_ip6_prefix is valid */
   u8 def_ip4_prefix_seen;	/* def_ip4_prefix is valid */
+  u8 def_ip4_via_ip6_prefix_seen; /* def_ip4_via_ip6_prefix is valid */
   u8 current_tlv_endpos;	/* End of self-terminating TLVs (offset from start) */
   u8 sadr_enabled;
   u8 is_unicast;
@@ -515,9 +517,6 @@ babel_read_ihu(struct babel_tlv *hdr, union babel_msg *m,
   msg->addr = IPA_NONE;
   msg->sender = state->saddr;
 
-  if (msg->ae >= BABEL_AE_MAX)
-    return PARSE_IGNORE;
-
   /*
    * We only actually read link-local IPs. In every other case, the addr field
    * will be 0 but validation will succeed. The handler takes care of these
@@ -526,17 +525,20 @@ babel_read_ihu(struct babel_tlv *hdr, union babel_msg *m,
    */
   switch (msg->ae)
   {
+  case BABEL_AE_WILDCARD:
+    return PARSE_SUCCESS;
+
   case BABEL_AE_IP4:
     if (TLV_OPT_LENGTH(tlv) < 4)
       return PARSE_ERROR;
     state->current_tlv_endpos += 4;
-    break;
+    return PARSE_SUCCESS;
 
   case BABEL_AE_IP6:
     if (TLV_OPT_LENGTH(tlv) < 16)
       return PARSE_ERROR;
     state->current_tlv_endpos += 16;
-    break;
+    return PARSE_SUCCESS;
 
   case BABEL_AE_IP6_LL:
     if (TLV_OPT_LENGTH(tlv) < 8)
@@ -544,10 +546,17 @@ babel_read_ihu(struct babel_tlv *hdr, union babel_msg *m,
 
     msg->addr = ipa_from_ip6(get_ip6_ll(&tlv->addr));
     state->current_tlv_endpos += 8;
-    break;
+    return PARSE_SUCCESS;
+
+  /* RFC 9229 2.4 - IHU TLV MUST NOT carry the AE 4 (IPv4-via-IPv6) */
+  case BABEL_AE_IP4_VIA_IP6:
+    return PARSE_ERROR;
+
+  default:
+    return PARSE_IGNORE;
   }
 
-  return PARSE_SUCCESS;
+  return PARSE_IGNORE;
 }
 
 static uint
@@ -640,6 +649,10 @@ babel_read_next_hop(struct babel_tlv *hdr, union babel_msg *m UNUSED,
     state->current_tlv_endpos += 8;
     return PARSE_IGNORE;
 
+  /* RFC 9229 2.4 - Next Hop TLV MUST NOT carry the AE 4 (IPv4-via-IPv6) */
+  case BABEL_AE_IP4_VIA_IP6:
+    return PARSE_ERROR;
+
   default:
     return PARSE_IGNORE;
   }
@@ -692,6 +705,42 @@ babel_write_next_hop(struct babel_tlv *hdr, ip_addr addr,
   return 0;
 }
 
+/* This is called directly from babel_read_update() to handle
+   both BABEL_AE_IP4 and BABEL_AE_IP4_VIA_IP6 encodings */
+static int
+babel_read_ip4_prefix(struct babel_tlv_update *tlv, struct babel_msg_update *msg,
+		     u8 *def_prefix, u8 *def_prefix_seen, ip_addr next_hop, int len)
+{
+    if (tlv->plen > IP4_MAX_PREFIX_LENGTH)
+      return PARSE_ERROR;
+
+    /* Cannot omit data if there is no saved prefix */
+    if (tlv->omitted && !*def_prefix_seen)
+      return PARSE_ERROR;
+
+    /* Update must have next hop, unless it is retraction */
+    if (ipa_zero(next_hop) && msg->metric != BABEL_INFINITY)
+      return PARSE_ERROR;
+
+    /* Merge saved prefix and received prefix parts */
+    u8 buf[4] = {};
+    memcpy(buf, def_prefix, tlv->omitted);
+    memcpy(buf + tlv->omitted, tlv->addr, len);
+
+    ip4_addr prefix4 = get_ip4(buf);
+    net_fill_ip4(&msg->net, prefix4, tlv->plen);
+
+    if (tlv->flags & BABEL_UF_DEF_PREFIX)
+    {
+      put_ip4(def_prefix, prefix4);
+      *def_prefix_seen = 1;
+    }
+
+    msg->next_hop = next_hop;
+
+    return PARSE_SUCCESS;
+}
+
 static int
 babel_read_update(struct babel_tlv *hdr, union babel_msg *m,
                   struct babel_parse_state *state)
@@ -706,11 +755,11 @@ babel_read_update(struct babel_tlv *hdr, union babel_msg *m,
 
   /* Length of received prefix data without omitted part */
   int len = BYTES(tlv->plen) - (int) tlv->omitted;
-  u8 buf[16] = {};
 
   if ((len < 0) || ((uint) len > TLV_OPT_LENGTH(tlv)))
     return PARSE_ERROR;
 
+  int rc;
   switch (tlv->ae)
   {
   case BABEL_AE_WILDCARD:
@@ -724,31 +773,20 @@ babel_read_update(struct babel_tlv *hdr, union babel_msg *m,
     break;
 
   case BABEL_AE_IP4:
-    if (tlv->plen > IP4_MAX_PREFIX_LENGTH)
-      return PARSE_ERROR;
-
-    /* Cannot omit data if there is no saved prefix */
-    if (tlv->omitted && !state->def_ip4_prefix_seen)
-      return PARSE_ERROR;
-
-    /* Update must have next hop, unless it is retraction */
-    if (ipa_zero(state->next_hop_ip4) && (msg->metric != BABEL_INFINITY))
-      return PARSE_IGNORE;
-
-    /* Merge saved prefix and received prefix parts */
-    memcpy(buf, state->def_ip4_prefix, tlv->omitted);
-    memcpy(buf + tlv->omitted, tlv->addr, len);
+    rc = babel_read_ip4_prefix(tlv, msg, state->def_ip4_prefix,
+			       &state->def_ip4_prefix_seen,
+			       state->next_hop_ip4, len);
+    if (rc != PARSE_SUCCESS)
+      return rc;
 
-    ip4_addr prefix4 = get_ip4(buf);
-    net_fill_ip4(&msg->net, prefix4, tlv->plen);
-
-    if (tlv->flags & BABEL_UF_DEF_PREFIX)
-    {
-      put_ip4(state->def_ip4_prefix, prefix4);
-      state->def_ip4_prefix_seen = 1;
-    }
+    break;
 
-    msg->next_hop = state->next_hop_ip4;
+  case BABEL_AE_IP4_VIA_IP6:
+    rc = babel_read_ip4_prefix(tlv, msg, state->def_ip4_via_ip6_prefix,
+			       &state->def_ip4_via_ip6_prefix_seen,
+			       state->next_hop_ip6, len);
+    if (rc != PARSE_SUCCESS)
+      return rc;
 
     break;
 
@@ -761,6 +799,7 @@ babel_read_update(struct babel_tlv *hdr, union babel_msg *m,
       return PARSE_ERROR;
 
     /* Merge saved prefix and received prefix parts */
+    u8 buf[16] = {};
     memcpy(buf, state->def_ip6_prefix, tlv->omitted);
     memcpy(buf + tlv->omitted, tlv->addr, len);
 
@@ -863,7 +902,7 @@ babel_write_update(struct babel_tlv *hdr, union babel_msg *m,
   }
   else if (msg->net.type == NET_IP4)
   {
-    tlv->ae = BABEL_AE_IP4;
+    tlv->ae = ipa_is_ip4(msg->next_hop) ? BABEL_AE_IP4 : BABEL_AE_IP4_VIA_IP6;
     tlv->plen = net4_pxlen(&msg->net);
     put_ip4_px(tlv->addr, &msg->net);
   }
@@ -931,7 +970,12 @@ babel_read_route_request(struct babel_tlv *hdr, union babel_msg *m,
     msg->full = 1;
     return PARSE_SUCCESS;
 
+  /*
+   * RFC 9229 2.3 - When receiving requests, AE 1 (IPv4) and AE 4
+   * (IPv4-via-IPv6) MUST be treated in the same manner.
+   */
   case BABEL_AE_IP4:
+  case BABEL_AE_IP4_VIA_IP6:
     if (tlv->plen > IP4_MAX_PREFIX_LENGTH)
       return PARSE_ERROR;
 
@@ -1032,7 +1076,12 @@ babel_read_seqno_request(struct babel_tlv *hdr, union babel_msg *m,
   case BABEL_AE_WILDCARD:
     return PARSE_ERROR;
 
+  /*
+   * RFC 9229 2.3 - When receiving requests, AE 1 (IPv4) and AE 4
+   * (IPv4-via-IPv6) MUST be treated in the same manner.
+   */
   case BABEL_AE_IP4:
+  case BABEL_AE_IP4_VIA_IP6:
     if (tlv->plen > IP4_MAX_PREFIX_LENGTH)
       return PARSE_ERROR;
 
@@ -1655,6 +1704,7 @@ babel_read_pc(struct babel_tlv *hdr, union babel_msg *m UNUSED,
   state->auth.pc_seen = 1;
   state->auth.index_len = index_len;
   state->auth.index = tlv->index;
+  state->auth.unicast = state->is_unicast;
   state->current_tlv_endpos += index_len;
 
   return PARSE_SUCCESS;