ipv6: ip6mr: support multiple tables

This patch adds support for multiple independant multicast routing instances,
named "tables".

Userspace multicast routing daemons can bind to a specific table instance by
issuing a setsockopt call using a new option MRT6_TABLE. The table number is
stored in the raw socket data and affects all following ip6mr setsockopt(),
getsockopt() and ioctl() calls. By default, a single table (RT6_TABLE_DFLT)
is created with a default routing rule pointing to it. Newly created pim6reg
devices have the table number appended ("pim6regX"), with the exception of
devices created in the default table, which are named just "pim6reg" for
compatibility reasons.

Packets are directed to a specific table instance using routing rules,
similar to how regular routing rules work. Currently iif, oif and mark
are supported as keys, source and destination addresses could be supported
additionally.

Example usage:

- bind pimd/xorp/... to a specific table:

uint32_t table = 123;
setsockopt(fd, SOL_IPV6, MRT6_TABLE, &table, sizeof(table));

- create routing rules directing packets to the new table:

# ip -6 mrule add iif eth0 lookup 123
# ip -6 mrule add oif eth0 lookup 123
Signed-off-by: Patrick McHardy <kaber@trash.net>

include/linux/ipv6.h

@@ -383,6 +383,7 @@ struct raw6_sock {
 	__u32			checksum;	/* perform checksum */
 	__u32			offset;		/* checksum offset  */
 	struct icmp6_filter	filter;
+	__u32			ip6mr_table;
 	/* ipv6_pinfo has to be the last member of raw6_sock, see inet6_sk_generic */
 	struct ipv6_pinfo	inet6;
 };

include/linux/mroute6.h

@@ -25,6 +25,7 @@
 #define MRT6_VERSION	(MRT6_BASE+6)	/* Get the kernel multicast version	*/
 #define MRT6_ASSERT	(MRT6_BASE+7)	/* Activate PIM assert mode		*/
 #define MRT6_PIM	(MRT6_BASE+8)	/* enable PIM code			*/
+#define MRT6_TABLE	(MRT6_BASE+9)	/* Specify mroute table ID		*/
 
 #define SIOCGETMIFCNT_IN6	SIOCPROTOPRIVATE	/* IP protocol privates */
 #define SIOCGETSGCNT_IN6	(SIOCPROTOPRIVATE+1)
@@ -229,11 +230,17 @@ extern int ip6mr_get_route(struct net *net, struct sk_buff *skb,
 			   struct rtmsg *rtm, int nowait);
 
 #ifdef CONFIG_IPV6_MROUTE
-extern struct sock *mroute6_socket(struct net *net);
+extern struct sock *mroute6_socket(struct net *net, struct sk_buff *skb);
 extern int ip6mr_sk_done(struct sock *sk);
 #else
-static inline struct sock *mroute6_socket(struct net *net) { return NULL; }
-static inline int ip6mr_sk_done(struct sock *sk) { return 0; }
+static inline struct sock *mroute6_socket(struct net *net, struct sk_buff *skb)
+{
+	return NULL;
+}
+static inline int ip6mr_sk_done(struct sock *sk)
+{
+	return 0;
+}
 #endif
 #endif
 

include/linux/rtnetlink.h

@@ -11,7 +11,8 @@
  * families, values above 128 may be used arbitrarily.
  */
 #define RTNL_FAMILY_IPMR		128
-#define RTNL_FAMILY_MAX			128
+#define RTNL_FAMILY_IP6MR		129
+#define RTNL_FAMILY_MAX			129
 
 /****
  *		Routing/neighbour discovery messages.

include/net/netns/ipv6.h

@@ -59,7 +59,12 @@ struct netns_ipv6 {
 	struct sock             *tcp_sk;
 	struct sock             *igmp_sk;
 #ifdef CONFIG_IPV6_MROUTE
+#ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
 	struct mr6_table	*mrt6;
+#else
+	struct list_head	mr6_tables;
+	struct fib_rules_ops	*mr6_rules_ops;
+#endif
 #endif
 };
 #endif

net/ipv6/Kconfig

@@ -229,6 +229,20 @@ config IPV6_MROUTE
 	  Experimental support for IPv6 multicast forwarding.
 	  If unsure, say N.
 
+config IPV6_MROUTE_MULTIPLE_TABLES
+	bool "IPv6: multicast policy routing"
+	depends on IPV6_MROUTE
+	select FIB_RULES
+	help
+	  Normally, a multicast router runs a userspace daemon and decides
+	  what to do with a multicast packet based on the source and
+	  destination addresses. If you say Y here, the multicast router
+	  will also be able to take interfaces and packet marks into
+	  account and run multiple instances of userspace daemons
+	  simultaneously, each one handling a single table.
+
+	  If unsure, say N.
+
 config IPV6_PIMSM_V2
 	bool "IPv6: PIM-SM version 2 support (EXPERIMENTAL)"
 	depends on IPV6_MROUTE

net/ipv6/ip6_output.c

@@ -108,7 +108,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
 		if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
-		    ((mroute6_socket(dev_net(dev)) &&
+		    ((mroute6_socket(dev_net(dev), skb) &&
 		     !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
 		     ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
 					 &ipv6_hdr(skb)->saddr))) {