[IPV6]: Multiple Routing Tables

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>
Signed-off-by: David S. Miller <davem@davemloft.net>

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 fib6_node *root,
 						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);
 

include/net/ip6_route.h

@@ -58,7 +58,8 @@ extern int			ipv6_route_ioctl(unsigned int cmd, void __user *arg);
 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,

net/ipv6/Kconfig

@@ -136,3 +136,9 @@ 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.
+

net/ipv6/addrconf.c

@@ -1525,7 +1525,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
 	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 net_device *dev)
 	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_device *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)

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(struct rt6_info *rt)
 		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 *root,
 	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)