[PATCH 2/5] [IPV6]: Multiple Routing Tables

[Thomas Graf <tgraf@suug.ch>]

[-- Attachment #1: ip6_mrt --]
[-- Type: text/plain, Size: 28525 bytes --]

Adds the framework to support multiple IPv6 routing tables.
Currently all automatically generated routes are put into the
same table. This could be changed at a later point after
considering the produced locking overhead.

Signed-off-by: Thomas Graf <tgraf@suug.ch>

Index: net-2.6.19/include/net/ip6_fib.h
===================================================================
--- net-2.6.19.orig/include/net/ip6_fib.h
+++ net-2.6.19/include/net/ip6_fib.h
@@ -51,6 +51,8 @@ struct rt6key
 	int		plen;
 };
 
+struct fib6_table;
+
 struct rt6_info
 {
 	union {
@@ -71,6 +73,7 @@ struct rt6_info
 	u32				rt6i_flags;
 	u32				rt6i_metric;
 	atomic_t			rt6i_ref;
+	struct fib6_table		*rt6i_table;
 
 	struct rt6key			rt6i_dst;
 	struct rt6key			rt6i_src;
@@ -143,12 +146,43 @@ struct rt6_statistics {
 
 typedef void			(*f_pnode)(struct fib6_node *fn, void *);
 
-extern struct fib6_node		ip6_routing_table;
+struct fib6_table {
+	struct hlist_node	tb6_hlist;
+	u32			tb6_id;
+	rwlock_t		tb6_lock;
+	struct fib6_node	tb6_root;
+};
+
+#define RT6_TABLE_UNSPEC	RT_TABLE_UNSPEC
+#define RT6_TABLE_MAIN		RT_TABLE_MAIN
+#define RT6_TABLE_LOCAL		RT6_TABLE_MAIN
+#define RT6_TABLE_DFLT		RT6_TABLE_MAIN
+#define RT6_TABLE_INFO		RT6_TABLE_MAIN
+#define RT6_TABLE_PREFIX	RT6_TABLE_MAIN
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+#define FIB6_TABLE_MIN		1
+#define FIB6_TABLE_MAX		RT_TABLE_MAX
+#else
+#define FIB6_TABLE_MIN		RT_TABLE_MAIN
+#define FIB6_TABLE_MAX		FIB6_TABLE_MIN
+#endif
+
+#define RT6_F_STRICT		1
+#define RT6_F_HAS_SADDR		2
+
+typedef struct rt6_info *(*pol_lookup_t)(struct fib6_table *,
+					 struct flowi *, int);
 
 /*
  *	exported functions
  */
 
+extern struct fib6_table *	fib6_get_table(u32 id);
+extern struct fib6_table *	fib6_new_table(u32 id);
+extern struct dst_entry *	fib6_rule_lookup(struct flowi *fl, int flags,
+						 pol_lookup_t lookup);
+
 extern struct fib6_node		*fib6_lookup(struct fib6_node *root,
 					     struct in6_addr *daddr,
 					     struct in6_addr *saddr);
@@ -161,6 +195,9 @@ extern void			fib6_clean_tree(struct fib
 						int (*func)(struct rt6_info *, void *arg),
 						int prune, void *arg);
 
+extern void			fib6_clean_all(int (*func)(struct rt6_info *, void *arg),
+					       int prune, void *arg);
+
 extern int			fib6_walk(struct fib6_walker_t *w);
 extern int			fib6_walk_continue(struct fib6_walker_t *w);
 
Index: net-2.6.19/net/ipv6/ip6_fib.c
===================================================================
--- net-2.6.19.orig/net/ipv6/ip6_fib.c
+++ net-2.6.19/net/ipv6/ip6_fib.c
@@ -26,6 +26,7 @@
 #include <linux/netdevice.h>
 #include <linux/in6.h>
 #include <linux/init.h>
+#include <linux/list.h>
 
 #ifdef 	CONFIG_PROC_FS
 #include <linux/proc_fs.h>
@@ -147,6 +148,126 @@ static __inline__ void rt6_release(struc
 		dst_free(&rt->u.dst);
 }
 
+static struct fib6_table fib6_main_tbl = {
+	.tb6_id		= RT6_TABLE_MAIN,
+	.tb6_lock	= RW_LOCK_UNLOCKED,
+	.tb6_root	= {
+		.leaf		= &ip6_null_entry,
+		.fn_flags	= RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
+	},
+};
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+
+#define FIB_TABLE_HASHSZ 256
+static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];
+
+static struct fib6_table *fib6_alloc_table(u32 id)
+{
+	struct fib6_table *table;
+
+	table = kzalloc(sizeof(*table), GFP_ATOMIC);
+	if (table != NULL) {
+		table->tb6_id = id;
+		table->tb6_lock = RW_LOCK_UNLOCKED;
+		table->tb6_root.leaf = &ip6_null_entry;
+		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+	}
+
+	return table;
+}
+
+static void fib6_link_table(struct fib6_table *tb)
+{
+	unsigned int h;
+
+	h = tb->tb6_id & (FIB_TABLE_HASHSZ - 1);
+
+	/*
+	 * No protection necessary, this is the only list mutatation
+	 * operation, tables never disappear once they exist.
+	 */
+	hlist_add_head_rcu(&tb->tb6_hlist, &fib_table_hash[h]);
+}
+
+struct fib6_table *fib6_new_table(u32 id)
+{
+	struct fib6_table *tb;
+
+	if (id == 0)
+		id = RT6_TABLE_MAIN;
+	tb = fib6_get_table(id);
+	if (tb)
+		return tb;
+
+	tb = fib6_alloc_table(id);
+	if (tb != NULL)
+		fib6_link_table(tb);
+
+	return tb;
+}
+
+struct fib6_table *fib6_get_table(u32 id)
+{
+	struct fib6_table *tb;
+	struct hlist_node *node;
+	unsigned int h;
+
+	if (id == 0)
+		id = RT6_TABLE_MAIN;
+	h = id & (FIB_TABLE_HASHSZ - 1);
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tb, node, &fib_table_hash[h], tb6_hlist) {
+		if (tb->tb6_id == id) {
+			rcu_read_unlock();
+			return tb;
+		}
+	}
+	rcu_read_unlock();
+
+	return NULL;
+}
+
+struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
+				   pol_lookup_t lookup)
+{
+	/*
+	 * TODO: Add rule lookup
+	 */
+	struct fib6_table *table = fib6_get_table(RT6_TABLE_MAIN);
+
+	return (struct dst_entry *) lookup(table, fl, flags);
+}
+
+static void __init fib6_tables_init(void)
+{
+	fib6_link_table(&fib6_main_tbl);
+}
+
+#else
+
+struct fib6_table *fib6_new_table(u32 id)
+{
+	return fib6_get_table(id);
+}
+
+struct fib6_table *fib6_get_table(u32 id)
+{
+	return &fib6_main_tbl;
+}
+
+struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
+				   pol_lookup_t lookup)
+{
+	return (struct dst_entry *) lookup(&fib6_main_tbl, fl, flags);
+}
+
+static void __init fib6_tables_init(void)
+{
+}
+
+#endif
+
 
 /*
  *	Routing Table
@@ -1064,6 +1185,22 @@ void fib6_clean_tree(struct fib6_node *r
 	fib6_walk(&c.w);
 }
 
+void fib6_clean_all(int (*func)(struct rt6_info *, void *arg),
+		    int prune, void *arg)
+{
+	int i;
+	struct fib6_table *table;
+
+	for (i = FIB6_TABLE_MIN; i <= FIB6_TABLE_MAX; i++) {
+		table = fib6_get_table(i);
+		if (table != NULL) {
+			write_lock_bh(&table->tb6_lock);
+			fib6_clean_tree(&table->tb6_root, func, prune, arg);
+			write_unlock_bh(&table->tb6_lock);
+		}
+	}
+}
+
 static int fib6_prune_clone(struct rt6_info *rt, void *arg)
 {
 	if (rt->rt6i_flags & RTF_CACHE) {
@@ -1142,11 +1279,8 @@ void fib6_run_gc(unsigned long dummy)
 	}
 	gc_args.more = 0;
 
-
-	write_lock_bh(&rt6_lock);
 	ndisc_dst_gc(&gc_args.more);
-	fib6_clean_tree(&ip6_routing_table, fib6_age, 0, NULL);
-	write_unlock_bh(&rt6_lock);
+	fib6_clean_all(fib6_age, 0, NULL);
 
 	if (gc_args.more)
 		mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval);
@@ -1165,6 +1299,8 @@ void __init fib6_init(void)
 					   NULL, NULL);
 	if (!fib6_node_kmem)
 		panic("cannot create fib6_nodes cache");
+
+	fib6_tables_init();
 }
 
 void fib6_gc_cleanup(void)
Index: net-2.6.19/net/ipv6/route.c
===================================================================
--- net-2.6.19.orig/net/ipv6/route.c
+++ net-2.6.19/net/ipv6/route.c
@@ -139,16 +139,6 @@ struct rt6_info ip6_null_entry = {
 	.rt6i_ref	= ATOMIC_INIT(1),
 };
 
-struct fib6_node ip6_routing_table = {
-	.leaf		= &ip6_null_entry,
-	.fn_flags	= RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
-};
-
-/* Protects all the ip6 fib */
-
-DEFINE_RWLOCK(rt6_lock);
-
-
 /* allocate dst with ip6_dst_ops */
 static __inline__ struct rt6_info *ip6_dst_alloc(void)
 {
@@ -187,8 +177,14 @@ static __inline__ int rt6_check_expired(
 		time_after(jiffies, rt->rt6i_expires));
 }
 
+static inline int rt6_need_strict(struct in6_addr *daddr)
+{
+	return (ipv6_addr_type(daddr) &
+		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
+}
+
 /*
- *	Route lookup. Any rt6_lock is implied.
+ *	Route lookup. Any table->tb6_lock is implied.
  */
 
 static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt,
@@ -440,27 +436,66 @@ int rt6_route_rcv(struct net_device *dev
 }
 #endif
 
-struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr,
-			    int oif, int strict)
+#define BACKTRACK() \
+if (rt == &ip6_null_entry && flags & RT6_F_STRICT) { \
+	while ((fn = fn->parent) != NULL) { \
+		if (fn->fn_flags & RTN_TL_ROOT) { \
+			dst_hold(&rt->u.dst); \
+			goto out; \
+		} \
+		if (fn->fn_flags & RTN_RTINFO) \
+			goto restart; \
+	} \
+}
+
+static struct rt6_info *ip6_pol_route_lookup(struct fib6_table *table,
+					     struct flowi *fl, int flags)
 {
 	struct fib6_node *fn;
 	struct rt6_info *rt;
 
-	read_lock_bh(&rt6_lock);
-	fn = fib6_lookup(&ip6_routing_table, daddr, saddr);
-	rt = rt6_device_match(fn->leaf, oif, strict);
+	read_lock_bh(&table->tb6_lock);
+	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
+restart:
+	rt = fn->leaf;
+	rt = rt6_device_match(rt, fl->oif, flags & RT6_F_STRICT);
+	BACKTRACK();
 	dst_hold(&rt->u.dst);
-	rt->u.dst.__use++;
-	read_unlock_bh(&rt6_lock);
+out:
+	read_unlock_bh(&table->tb6_lock);
 
 	rt->u.dst.lastuse = jiffies;
-	if (rt->u.dst.error == 0)
-		return rt;
-	dst_release(&rt->u.dst);
+	rt->u.dst.__use++;
+
+	return rt;
+
+}
+
+struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr,
+			    int oif, int strict)
+{
+	struct flowi fl = {
+		.oif = oif,
+		.nl_u = {
+			.ip6_u = {
+				.daddr = *daddr,
+				/* TODO: saddr */
+			},
+		},
+	};
+	struct dst_entry *dst;
+	int flags = strict ? RT6_F_STRICT : 0;
+
+	dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup);
+	if (dst->error == 0)
+		return (struct rt6_info *) dst;
+
+	dst_release(dst);
+
 	return NULL;
 }
 
-/* ip6_ins_rt is called with FREE rt6_lock.
+/* ip6_ins_rt is called with FREE table->tb6_lock.
    It takes new route entry, the addition fails by any reason the
    route is freed. In any case, if caller does not hold it, it may
    be destroyed.
@@ -470,10 +505,12 @@ int ip6_ins_rt(struct rt6_info *rt, stru
 		void *_rtattr, struct netlink_skb_parms *req)
 {
 	int err;
+	struct fib6_table *table;
 
-	write_lock_bh(&rt6_lock);
-	err = fib6_add(&ip6_routing_table, rt, nlh, _rtattr, req);
-	write_unlock_bh(&rt6_lock);
+	table = rt->rt6i_table;
+	write_lock_bh(&table->tb6_lock);
+	err = fib6_add(&table->tb6_root, rt, nlh, _rtattr, req);
+	write_unlock_bh(&table->tb6_lock);
 
 	return err;
 }
@@ -531,51 +568,40 @@ static struct rt6_info *rt6_alloc_clone(
 	return rt;
 }
 
-#define BACKTRACK() \
-if (rt == &ip6_null_entry) { \
-       while ((fn = fn->parent) != NULL) { \
-		if (fn->fn_flags & RTN_ROOT) { \
-			goto out; \
-		} \
-		if (fn->fn_flags & RTN_RTINFO) \
-			goto restart; \
-	} \
-}
-
-
-void ip6_route_input(struct sk_buff *skb)
+struct rt6_info *ip6_pol_route_input(struct fib6_table *table, struct flowi *fl,
+				     int flags)
 {
 	struct fib6_node *fn;
 	struct rt6_info *rt, *nrt;
-	int strict;
+	int strict = 0;
 	int attempts = 3;
 	int err;
 	int reachable = RT6_SELECT_F_REACHABLE;
 
-	strict = ipv6_addr_type(&skb->nh.ipv6h->daddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0;
+	if (flags & RT6_F_STRICT)
+		strict = RT6_SELECT_F_IFACE;
 
 relookup:
-	read_lock_bh(&rt6_lock);
+	read_lock_bh(&table->tb6_lock);
 
 restart_2:
-	fn = fib6_lookup(&ip6_routing_table, &skb->nh.ipv6h->daddr,
-			 &skb->nh.ipv6h->saddr);
+	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
 
 restart:
-	rt = rt6_select(&fn->leaf, skb->dev->ifindex, strict | reachable);
+	rt = rt6_select(&fn->leaf, fl->iif, strict | reachable);
 	BACKTRACK();
 	if (rt == &ip6_null_entry ||
 	    rt->rt6i_flags & RTF_CACHE)
 		goto out;
 
 	dst_hold(&rt->u.dst);
-	read_unlock_bh(&rt6_lock);
+	read_unlock_bh(&table->tb6_lock);
 
 	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
-		nrt = rt6_alloc_cow(rt, &skb->nh.ipv6h->daddr, &skb->nh.ipv6h->saddr);
+		nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
 	else {
 #if CLONE_OFFLINK_ROUTE
-		nrt = rt6_alloc_clone(rt, &skb->nh.ipv6h->daddr);
+		nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
 #else
 		goto out2;
 #endif
@@ -586,7 +612,7 @@ restart:
 
 	dst_hold(&rt->u.dst);
 	if (nrt) {
-		err = ip6_ins_rt(nrt, NULL, NULL, &NETLINK_CB(skb));
+		err = ip6_ins_rt(nrt, NULL, NULL, NULL);
 		if (!err)
 			goto out2;
 	}
@@ -595,7 +621,7 @@ restart:
 		goto out2;
 
 	/*
-	 * Race condition! In the gap, when rt6_lock was
+	 * Race condition! In the gap, when table->tb6_lock was
 	 * released someone could insert this route.  Relookup.
 	 */
 	dst_release(&rt->u.dst);
@@ -607,30 +633,54 @@ out:
 		goto restart_2;
 	}
 	dst_hold(&rt->u.dst);
-	read_unlock_bh(&rt6_lock);
+	read_unlock_bh(&table->tb6_lock);
 out2:
 	rt->u.dst.lastuse = jiffies;
 	rt->u.dst.__use++;
-	skb->dst = (struct dst_entry *) rt;
-	return;
+
+	return rt;
 }
 
-struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl)
+void ip6_route_input(struct sk_buff *skb)
+{
+	struct ipv6hdr *iph = skb->nh.ipv6h;
+	struct flowi fl = {
+		.iif = skb->dev->ifindex,
+		.nl_u = {
+			.ip6_u = {
+				.daddr = iph->daddr,
+				.saddr = iph->saddr,
+				.flowlabel = (* (u32 *) iph)&IPV6_FLOWINFO_MASK,
+			},
+		},
+		.proto = iph->nexthdr,
+	};
+	int flags = 0;
+
+	if (rt6_need_strict(&iph->daddr))
+		flags |= RT6_F_STRICT;
+
+	skb->dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_input);
+}
+
+static struct rt6_info *ip6_pol_route_output(struct fib6_table *table,
+					     struct flowi *fl, int flags)
 {
 	struct fib6_node *fn;
 	struct rt6_info *rt, *nrt;
-	int strict;
+	int strict = 0;
 	int attempts = 3;
 	int err;
 	int reachable = RT6_SELECT_F_REACHABLE;
 
-	strict = ipv6_addr_type(&fl->fl6_dst) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0;
+	if (flags & RT6_F_STRICT)
+		strict = RT6_SELECT_F_IFACE;
 
 relookup:
-	read_lock_bh(&rt6_lock);
+	read_lock_bh(&table->tb6_lock);
 
 restart_2:
-	fn = fib6_lookup(&ip6_routing_table, &fl->fl6_dst, &fl->fl6_src);
+	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
 
 restart:
 	rt = rt6_select(&fn->leaf, fl->oif, strict | reachable);
@@ -640,7 +690,7 @@ restart:
 		goto out;
 
 	dst_hold(&rt->u.dst);
-	read_unlock_bh(&rt6_lock);
+	read_unlock_bh(&table->tb6_lock);
 
 	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
 		nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
@@ -666,7 +716,7 @@ restart:
 		goto out2;
 
 	/*
-	 * Race condition! In the gap, when rt6_lock was
+	 * Race condition! In the gap, when table->tb6_lock was
 	 * released someone could insert this route.  Relookup.
 	 */
 	dst_release(&rt->u.dst);
@@ -678,11 +728,21 @@ out:
 		goto restart_2;
 	}
 	dst_hold(&rt->u.dst);
-	read_unlock_bh(&rt6_lock);
+	read_unlock_bh(&table->tb6_lock);
 out2:
 	rt->u.dst.lastuse = jiffies;
 	rt->u.dst.__use++;
-	return &rt->u.dst;
+	return rt;
+}
+
+struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl)
+{
+	int flags = 0;
+
+	if (rt6_need_strict(&fl->fl6_dst))
+		flags |= RT6_F_STRICT;
+
+	return fib6_rule_lookup(fl, flags, ip6_pol_route_output);
 }
 
 
@@ -904,7 +964,8 @@ int ipv6_get_hoplimit(struct net_device 
  */
 
 int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, 
-		void *_rtattr, struct netlink_skb_parms *req)
+		  void *_rtattr, struct netlink_skb_parms *req,
+		  u32 table_id)
 {
 	int err;
 	struct rtmsg *r;
@@ -912,6 +973,7 @@ int ip6_route_add(struct in6_rtmsg *rtms
 	struct rt6_info *rt = NULL;
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
+	struct fib6_table *table;
 	int addr_type;
 
 	rta = (struct rtattr **) _rtattr;
@@ -935,6 +997,12 @@ int ip6_route_add(struct in6_rtmsg *rtms
 	if (rtmsg->rtmsg_metric == 0)
 		rtmsg->rtmsg_metric = IP6_RT_PRIO_USER;
 
+	table = fib6_new_table(table_id);
+	if (table == NULL) {
+		err = -ENOBUFS;
+		goto out;
+	}
+
 	rt = ip6_dst_alloc();
 
 	if (rt == NULL) {
@@ -1091,6 +1159,7 @@ install_route:
 		rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
 	rt->u.dst.dev = dev;
 	rt->rt6i_idev = idev;
+	rt->rt6i_table = table;
 	return ip6_ins_rt(rt, nlh, _rtattr, req);
 
 out:
@@ -1106,26 +1175,35 @@ out:
 int ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req)
 {
 	int err;
+	struct fib6_table *table;
 
-	write_lock_bh(&rt6_lock);
+	table = rt->rt6i_table;
+	write_lock_bh(&table->tb6_lock);
 
 	err = fib6_del(rt, nlh, _rtattr, req);
 	dst_release(&rt->u.dst);
 
-	write_unlock_bh(&rt6_lock);
+	write_unlock_bh(&table->tb6_lock);
 
 	return err;
 }
 
-static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req)
+static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh,
+			 void *_rtattr, struct netlink_skb_parms *req,
+			 u32 table_id)
 {
+	struct fib6_table *table;
 	struct fib6_node *fn;
 	struct rt6_info *rt;
 	int err = -ESRCH;
 
-	read_lock_bh(&rt6_lock);
+	table = fib6_get_table(table_id);
+	if (table == NULL)
+		return err;
 
-	fn = fib6_locate(&ip6_routing_table,
+	read_lock_bh(&table->tb6_lock);
+
+	fn = fib6_locate(&table->tb6_root,
 			 &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len,
 			 &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len);
 	
@@ -1142,12 +1220,12 @@ static int ip6_route_del(struct in6_rtms
 			    rtmsg->rtmsg_metric != rt->rt6i_metric)
 				continue;
 			dst_hold(&rt->u.dst);
-			read_unlock_bh(&rt6_lock);
+			read_unlock_bh(&table->tb6_lock);
 
 			return ip6_del_rt(rt, nlh, _rtattr, req);
 		}
 	}
-	read_unlock_bh(&rt6_lock);
+	read_unlock_bh(&table->tb6_lock);
 
 	return err;
 }
@@ -1159,8 +1237,13 @@ void rt6_redirect(struct in6_addr *dest,
 		  struct neighbour *neigh, u8 *lladdr, int on_link)
 {
 	struct rt6_info *rt, *nrt = NULL;
-	int strict;
 	struct fib6_node *fn;
+	struct fib6_table *table;
+
+	/* TODO: Very lazy, might need to check all tables */
+	table = fib6_get_table(RT6_TABLE_MAIN);
+	if (table == NULL)
+		return;
 
 	/*
 	 * Get the "current" route for this destination and
@@ -1172,10 +1255,9 @@ void rt6_redirect(struct in6_addr *dest,
 	 * is a bit fuzzy and one might need to check all possible
 	 * routes.
 	 */
-	strict = ipv6_addr_type(dest) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL);
 
-	read_lock_bh(&rt6_lock);
-	fn = fib6_lookup(&ip6_routing_table, dest, NULL);
+	read_lock_bh(&table->tb6_lock);
+	fn = fib6_lookup(&table->tb6_root, dest, NULL);
 restart:
 	for (rt = fn->leaf; rt; rt = rt->u.next) {
 		/*
@@ -1198,7 +1280,7 @@ restart:
 	}
 	if (rt)
 		dst_hold(&rt->u.dst);
-	else if (strict) {
+	else if (rt6_need_strict(dest)) {
 		while ((fn = fn->parent) != NULL) {
 			if (fn->fn_flags & RTN_ROOT)
 				break;
@@ -1206,7 +1288,7 @@ restart:
 				goto restart;
 		}
 	}
-	read_unlock_bh(&rt6_lock);
+	read_unlock_bh(&table->tb6_lock);
 
 	if (!rt) {
 		if (net_ratelimit())
@@ -1377,6 +1459,7 @@ static struct rt6_info * ip6_rt_copy(str
 #ifdef CONFIG_IPV6_SUBTREES
 		memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
 #endif
+		rt->rt6i_table = ort->rt6i_table;
 	}
 	return rt;
 }
@@ -1387,9 +1470,14 @@ static struct rt6_info *rt6_get_route_in
 {
 	struct fib6_node *fn;
 	struct rt6_info *rt = NULL;
+	struct fib6_table *table;
 
-	write_lock_bh(&rt6_lock);
-	fn = fib6_locate(&ip6_routing_table, prefix ,prefixlen, NULL, 0);
+	table = fib6_get_table(RT6_TABLE_INFO);
+	if (table == NULL)
+		return NULL;
+
+	write_lock_bh(&table->tb6_lock);
+	fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0);
 	if (!fn)
 		goto out;
 
@@ -1404,7 +1492,7 @@ static struct rt6_info *rt6_get_route_in
 		break;
 	}
 out:
-	write_unlock_bh(&rt6_lock);
+	write_unlock_bh(&table->tb6_lock);
 	return rt;
 }
 
@@ -1426,7 +1514,7 @@ static struct rt6_info *rt6_add_route_in
 		rtmsg.rtmsg_flags |= RTF_DEFAULT;
 	rtmsg.rtmsg_ifindex = ifindex;
 
-	ip6_route_add(&rtmsg, NULL, NULL, NULL);
+	ip6_route_add(&rtmsg, NULL, NULL, NULL, RT6_TABLE_INFO);
 
 	return rt6_get_route_info(prefix, prefixlen, gwaddr, ifindex);
 }
@@ -1435,12 +1523,14 @@ static struct rt6_info *rt6_add_route_in
 struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev)
 {	
 	struct rt6_info *rt;
-	struct fib6_node *fn;
+	struct fib6_table *table;
 
-	fn = &ip6_routing_table;
+	table = fib6_get_table(RT6_TABLE_DFLT);
+	if (table == NULL)
+		return NULL;
 
-	write_lock_bh(&rt6_lock);
-	for (rt = fn->leaf; rt; rt=rt->u.next) {
+	write_lock_bh(&table->tb6_lock);
+	for (rt = table->tb6_root.leaf; rt; rt=rt->u.next) {
 		if (dev == rt->rt6i_dev &&
 		    ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
 		    ipv6_addr_equal(&rt->rt6i_gateway, addr))
@@ -1448,7 +1538,7 @@ struct rt6_info *rt6_get_dflt_router(str
 	}
 	if (rt)
 		dst_hold(&rt->u.dst);
-	write_unlock_bh(&rt6_lock);
+	write_unlock_bh(&table->tb6_lock);
 	return rt;
 }
 
@@ -1467,28 +1557,31 @@ struct rt6_info *rt6_add_dflt_router(str
 
 	rtmsg.rtmsg_ifindex = dev->ifindex;
 
-	ip6_route_add(&rtmsg, NULL, NULL, NULL);
+	ip6_route_add(&rtmsg, NULL, NULL, NULL, RT6_TABLE_DFLT);
 	return rt6_get_dflt_router(gwaddr, dev);
 }
 
 void rt6_purge_dflt_routers(void)
 {
 	struct rt6_info *rt;
+	struct fib6_table *table;
+
+	/* NOTE: Keep consistent with rt6_get_dflt_router */
+	table = fib6_get_table(RT6_TABLE_DFLT);
+	if (table == NULL)
+		return;
 
 restart:
-	read_lock_bh(&rt6_lock);
-	for (rt = ip6_routing_table.leaf; rt; rt = rt->u.next) {
+	read_lock_bh(&table->tb6_lock);
+	for (rt = table->tb6_root.leaf; rt; rt = rt->u.next) {
 		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) {
 			dst_hold(&rt->u.dst);
-
-			read_unlock_bh(&rt6_lock);
-
+			read_unlock_bh(&table->tb6_lock);
 			ip6_del_rt(rt, NULL, NULL, NULL);
-
 			goto restart;
 		}
 	}
-	read_unlock_bh(&rt6_lock);
+	read_unlock_bh(&table->tb6_lock);
 }
 
 int ipv6_route_ioctl(unsigned int cmd, void __user *arg)
@@ -1509,10 +1602,12 @@ int ipv6_route_ioctl(unsigned int cmd, v
 		rtnl_lock();
 		switch (cmd) {
 		case SIOCADDRT:
-			err = ip6_route_add(&rtmsg, NULL, NULL, NULL);
+			err = ip6_route_add(&rtmsg, NULL, NULL, NULL,
+					    RT6_TABLE_MAIN);
 			break;
 		case SIOCDELRT:
-			err = ip6_route_del(&rtmsg, NULL, NULL, NULL);
+			err = ip6_route_del(&rtmsg, NULL, NULL, NULL,
+					    RT6_TABLE_MAIN);
 			break;
 		default:
 			err = -EINVAL;
@@ -1582,6 +1677,7 @@ struct rt6_info *addrconf_dst_alloc(stru
 
 	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
 	rt->rt6i_dst.plen = 128;
+	rt->rt6i_table = fib6_get_table(RT6_TABLE_LOCAL);
 
 	atomic_set(&rt->u.dst.__refcnt, 1);
 
@@ -1600,9 +1696,7 @@ static int fib6_ifdown(struct rt6_info *
 
 void rt6_ifdown(struct net_device *dev)
 {
-	write_lock_bh(&rt6_lock);
-	fib6_clean_tree(&ip6_routing_table, fib6_ifdown, 0, dev);
-	write_unlock_bh(&rt6_lock);
+	fib6_clean_all(fib6_ifdown, 0, dev);
 }
 
 struct rt6_mtu_change_arg
@@ -1652,13 +1746,12 @@ static int rt6_mtu_change_route(struct r
 
 void rt6_mtu_change(struct net_device *dev, unsigned mtu)
 {
-	struct rt6_mtu_change_arg arg;
+	struct rt6_mtu_change_arg arg = {
+		.dev = dev,
+		.mtu = mtu,
+	};
 
-	arg.dev = dev;
-	arg.mtu = mtu;
-	read_lock_bh(&rt6_lock);
-	fib6_clean_tree(&ip6_routing_table, rt6_mtu_change_route, 0, &arg);
-	read_unlock_bh(&rt6_lock);
+	fib6_clean_all(rt6_mtu_change_route, 0, &arg);
 }
 
 static int inet6_rtm_to_rtmsg(struct rtmsg *r, struct rtattr **rta,
@@ -1708,7 +1801,7 @@ int inet6_rtm_delroute(struct sk_buff *s
 
 	if (inet6_rtm_to_rtmsg(r, arg, &rtmsg))
 		return -EINVAL;
-	return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb));
+	return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb), r->rtm_table);
 }
 
 int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
@@ -1718,7 +1811,7 @@ int inet6_rtm_newroute(struct sk_buff *s
 
 	if (inet6_rtm_to_rtmsg(r, arg, &rtmsg))
 		return -EINVAL;
-	return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb));
+	return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb), r->rtm_table);
 }
 
 struct rt6_rtnl_dump_arg
@@ -1750,6 +1843,10 @@ static int rt6_fill_node(struct sk_buff 
 	rtm->rtm_dst_len = rt->rt6i_dst.plen;
 	rtm->rtm_src_len = rt->rt6i_src.plen;
 	rtm->rtm_tos = 0;
+	if (rt->rt6i_table)
+		rtm->rtm_table = rt->rt6i_table->tb6_id;
+	else
+		rtm->rtm_table = RT6_TABLE_UNSPEC;
 	rtm->rtm_table = RT_TABLE_MAIN;
 	if (rt->rt6i_flags&RTF_REJECT)
 		rtm->rtm_type = RTN_UNREACHABLE;
@@ -1857,7 +1954,6 @@ static void fib6_dump_end(struct netlink
 
 	if (w) {
 		cb->args[0] = 0;
-		fib6_walker_unlink(w);
 		kfree(w);
 	}
 	cb->done = (void*)cb->args[1];
@@ -1872,13 +1968,20 @@ static int fib6_dump_done(struct netlink
 
 int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct fib6_table *table;
 	struct rt6_rtnl_dump_arg arg;
 	struct fib6_walker_t *w;
-	int res;
+	int i, res = 0;
 
 	arg.skb = skb;
 	arg.cb = cb;
 
+	/*
+	 * cb->args[0] = pointer to walker structure
+	 * cb->args[1] = saved cb->done() pointer
+	 * cb->args[2] = current table being dumped
+	 */
+
 	w = (void*)cb->args[0];
 	if (w == NULL) {
 		/* New dump:
@@ -1894,24 +1997,48 @@ int inet6_dump_fib(struct sk_buff *skb, 
 		w = kzalloc(sizeof(*w), GFP_ATOMIC);
 		if (w == NULL)
 			return -ENOMEM;
-		RT6_TRACE("dump<%p", w);
-		w->root = &ip6_routing_table;
 		w->func = fib6_dump_node;
 		w->args = &arg;
 		cb->args[0] = (long)w;
-		read_lock_bh(&rt6_lock);
-		res = fib6_walk(w);
-		read_unlock_bh(&rt6_lock);
+		cb->args[2] = FIB6_TABLE_MIN;
 	} else {
 		w->args = &arg;
-		read_lock_bh(&rt6_lock);
-		res = fib6_walk_continue(w);
-		read_unlock_bh(&rt6_lock);
-	}
-#if RT6_DEBUG >= 3
-	if (res <= 0 && skb->len == 0)
-		RT6_TRACE("%p>dump end\n", w);
-#endif
+		i = cb->args[2];
+		if (i > FIB6_TABLE_MAX)
+			goto end;
+
+		table = fib6_get_table(i);
+		if (table != NULL) {
+			read_lock_bh(&table->tb6_lock);
+			w->root = &table->tb6_root;
+			res = fib6_walk_continue(w);
+			read_unlock_bh(&table->tb6_lock);
+			if (res != 0) {
+				if (res < 0)
+					fib6_walker_unlink(w);
+				goto end;
+			}
+		}
+
+		fib6_walker_unlink(w);
+		cb->args[2] = ++i;
+	}
+
+	for (i = cb->args[2]; i <= FIB6_TABLE_MAX; i++) {
+		table = fib6_get_table(i);
+		if (table == NULL)
+			continue;
+
+		read_lock_bh(&table->tb6_lock);
+		w->root = &table->tb6_root;
+		res = fib6_walk(w);
+		read_unlock_bh(&table->tb6_lock);
+		if (res)
+			break;
+	}
+end:
+	cb->args[2] = i;
+
 	res = res < 0 ? res : skb->len;
 	/* res < 0 is an error. (really, impossible)
 	   res == 0 means that dump is complete, but skb still can contain data.
@@ -2091,16 +2218,13 @@ static int rt6_info_route(struct rt6_inf
 
 static int rt6_proc_info(char *buffer, char **start, off_t offset, int length)
 {
-	struct rt6_proc_arg arg;
-	arg.buffer = buffer;
-	arg.offset = offset;
-	arg.length = length;
-	arg.skip = 0;
-	arg.len = 0;
-
-	read_lock_bh(&rt6_lock);
-	fib6_clean_tree(&ip6_routing_table, rt6_info_route, 0, &arg);
-	read_unlock_bh(&rt6_lock);
+	struct rt6_proc_arg arg = {
+		.buffer = buffer,
+		.offset = offset,
+		.length = length,
+	};
+
+	fib6_clean_all(rt6_info_route, 0, &arg);
 
 	*start = buffer;
 	if (offset)
Index: net-2.6.19/net/ipv6/Kconfig
===================================================================
--- net-2.6.19.orig/net/ipv6/Kconfig
+++ net-2.6.19/net/ipv6/Kconfig
@@ -135,3 +135,9 @@ config IPV6_TUNNEL
 
 	  If unsure, say N.
 
+config IPV6_MULTIPLE_TABLES
+	bool "IPv6: Multiple Routing Tables"
+	depends on IPV6 && EXPERIMENTAL
+	---help---
+	  Support multiple routing tables.
+
Index: net-2.6.19/include/net/ip6_route.h
===================================================================
--- net-2.6.19.orig/include/net/ip6_route.h
+++ net-2.6.19/include/net/ip6_route.h
@@ -58,7 +58,8 @@ extern int			ipv6_route_ioctl(unsigned i
 extern int			ip6_route_add(struct in6_rtmsg *rtmsg,
 					      struct nlmsghdr *,
 					      void *rtattr,
-					      struct netlink_skb_parms *req);
+					      struct netlink_skb_parms *req,
+					      u32 table_id);
 extern int			ip6_ins_rt(struct rt6_info *,
 					   struct nlmsghdr *,
 					   void *rtattr,
Index: net-2.6.19/net/ipv6/addrconf.c
===================================================================
--- net-2.6.19.orig/net/ipv6/addrconf.c
+++ net-2.6.19/net/ipv6/addrconf.c
@@ -1525,7 +1525,7 @@ addrconf_prefix_route(struct in6_addr *p
 	if (dev->type == ARPHRD_SIT && (dev->flags&IFF_POINTOPOINT))
 		rtmsg.rtmsg_flags |= RTF_NONEXTHOP;
 
-	ip6_route_add(&rtmsg, NULL, NULL, NULL);
+	ip6_route_add(&rtmsg, NULL, NULL, NULL, RT6_TABLE_PREFIX);
 }
 
 /* Create "default" multicast route to the interface */
@@ -1542,7 +1542,7 @@ static void addrconf_add_mroute(struct n
 	rtmsg.rtmsg_ifindex = dev->ifindex;
 	rtmsg.rtmsg_flags = RTF_UP;
 	rtmsg.rtmsg_type = RTMSG_NEWROUTE;
-	ip6_route_add(&rtmsg, NULL, NULL, NULL);
+	ip6_route_add(&rtmsg, NULL, NULL, NULL, RT6_TABLE_LOCAL);
 }
 
 static void sit_route_add(struct net_device *dev)
@@ -1559,7 +1559,7 @@ static void sit_route_add(struct net_dev
 	rtmsg.rtmsg_flags	= RTF_UP|RTF_NONEXTHOP;
 	rtmsg.rtmsg_ifindex	= dev->ifindex;
 
-	ip6_route_add(&rtmsg, NULL, NULL, NULL);
+	ip6_route_add(&rtmsg, NULL, NULL, NULL, RT6_TABLE_MAIN);
 }
 
 static void addrconf_add_lroute(struct net_device *dev)