[NETNS][IPV6] ip6_fib - make it per network namespace

The fib table for ipv6 are moved to the network namespace structure.
All references to them are made relatively to the network namespace.

All external calls to the ip6_fib functions taking the network
namespace parameter are made using the init_net variable, so the
ip6_fib engine is ready for the namespaces but the callers not yet.
Signed-off-by: Daniel Lezcano <dlezcano@fr.ibm.com>
Signed-off-by: Benjamin Thery <benjamin.thery@bull.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip6_fib.h

@@ -181,10 +181,11 @@ typedef struct rt6_info *(*pol_lookup_t)(struct fib6_table *,
  *	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_table        *fib6_get_table(struct net *net, u32 id);
+extern struct fib6_table        *fib6_new_table(struct net *net, u32 id);
+extern struct dst_entry         *fib6_rule_lookup(struct net *net,
+						  struct flowi *fl, int flags,
+						  pol_lookup_t lookup);
 
 extern struct fib6_node		*fib6_lookup(struct fib6_node *root,
 					     struct in6_addr *daddr,

include/net/netns/ipv6.h

@@ -35,6 +35,11 @@ struct netns_ipv6 {
 	struct xt_table		*ip6table_filter;
 	struct xt_table		*ip6table_mangle;
 	struct xt_table		*ip6table_raw;
+#endif
+	struct hlist_head       *fib_table_hash;
+	struct fib6_table       *fib6_main_tbl;
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+	struct fib6_table       *fib6_local_tbl;
 #endif
 	struct sock		**icmp_sk;
 };

net/ipv6/fib6_rules.c

@@ -31,8 +31,8 @@ struct fib6_rule
 
 static struct fib_rules_ops fib6_rules_ops;
 
-struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
-				   pol_lookup_t lookup)
+struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
+				   int flags, pol_lookup_t lookup)
 {
 	struct fib_lookup_arg arg = {
 		.lookup_ptr = lookup,
@@ -71,7 +71,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 		goto discard_pkt;
 	}
 
-	table = fib6_get_table(rule->table);
+	table = fib6_get_table(&init_net, rule->table);
 	if (table)
 		rt = lookup(table, flp, flags);
 
@@ -151,7 +151,7 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 		if (rule->table == RT6_TABLE_UNSPEC)
 			goto errout;
 
-		if (fib6_new_table(rule->table) == NULL) {
+		if (fib6_new_table(&init_net, rule->table) == NULL) {
 			err = -ENOBUFS;
 			goto errout;
 		}

net/ipv6/ip6_fib.c

@@ -166,16 +166,13 @@ static __inline__ void rt6_release(struct rt6_info *rt)
 		dst_free(&rt->u.dst);
 }
 
-static struct fib6_table *fib6_main_tbl;
-
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 #define FIB_TABLE_HASHSZ 256
 #else
 #define FIB_TABLE_HASHSZ 1
 #endif
-static struct hlist_head *fib_table_hash;
 
-static void fib6_link_table(struct fib6_table *tb)
+static void fib6_link_table(struct net *net, struct fib6_table *tb)
 {
 	unsigned int h;
 
@@ -191,13 +188,11 @@ static void fib6_link_table(struct fib6_table *tb)
 	 * 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]);
+	hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]);
 }
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 
-static struct fib6_table *fib6_local_tbl;
-
 static struct fib6_table *fib6_alloc_table(u32 id)
 {
 	struct fib6_table *table;
@@ -212,26 +207,27 @@ static struct fib6_table *fib6_alloc_table(u32 id)
 	return table;
 }
 
-struct fib6_table *fib6_new_table(u32 id)
+struct fib6_table *fib6_new_table(struct net *net, u32 id)
 {
 	struct fib6_table *tb;
 
 	if (id == 0)
 		id = RT6_TABLE_MAIN;
-	tb = fib6_get_table(id);
+	tb = fib6_get_table(net, id);
 	if (tb)
 		return tb;
 
 	tb = fib6_alloc_table(id);
 	if (tb != NULL)
-		fib6_link_table(tb);
+		fib6_link_table(net, tb);
 
 	return tb;
 }
 
-struct fib6_table *fib6_get_table(u32 id)
+struct fib6_table *fib6_get_table(struct net *net, u32 id)
 {
 	struct fib6_table *tb;
+	struct hlist_head *head;
 	struct hlist_node *node;
 	unsigned int h;
 
@@ -239,7 +235,8 @@ struct fib6_table *fib6_get_table(u32 id)
 		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) {
+	head = &net->ipv6.fib_table_hash[h];
+	hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) {
 		if (tb->tb6_id == id) {
 			rcu_read_unlock();
 			return tb;
@@ -250,33 +247,32 @@ struct fib6_table *fib6_get_table(u32 id)
 	return NULL;
 }
 
-static void __init fib6_tables_init(void)
+static void fib6_tables_init(struct net *net)
 {
-	fib6_link_table(fib6_main_tbl);
-	fib6_link_table(fib6_local_tbl);
+	fib6_link_table(net, net->ipv6.fib6_main_tbl);
+	fib6_link_table(net, net->ipv6.fib6_local_tbl);
 }
-
 #else
 
-struct fib6_table *fib6_new_table(u32 id)
+struct fib6_table *fib6_new_table(struct net *net, u32 id)
 {
-	return fib6_get_table(id);
+	return fib6_get_table(net, id);
 }
 
-struct fib6_table *fib6_get_table(u32 id)
+struct fib6_table *fib6_get_table(struct net *net, u32 id)
 {
-	return fib6_main_tbl;
+	  return net->ipv6.fib6_main_tbl;
 }
 
-struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
-				   pol_lookup_t lookup)
+struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
+				   int flags, pol_lookup_t lookup)
 {
-	return (struct dst_entry *) lookup(fib6_main_tbl, fl, flags);
+	return (struct dst_entry *) lookup(net->ipv6.fib6_main_tbl, fl, flags);
 }
 
-static void __init fib6_tables_init(void)
+static void fib6_tables_init(struct net *net)
 {
-	fib6_link_table(fib6_main_tbl);
+	fib6_link_table(net, net->ipv6.fib6_main_tbl);
 }
 
 #endif
@@ -357,11 +353,9 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	struct fib6_walker_t *w;
 	struct fib6_table *tb;
 	struct hlist_node *node;
+	struct hlist_head *head;
 	int res = 0;
 
-	if (net != &init_net)
-		return 0;
-
 	s_h = cb->args[0];
 	s_e = cb->args[1];
 
@@ -390,7 +384,8 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 
 	for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
 		e = 0;
-		hlist_for_each_entry(tb, node, &fib_table_hash[h], tb6_hlist) {
+		head = &net->ipv6.fib_table_hash[h];
+		hlist_for_each_entry(tb, node, head, tb6_hlist) {
 			if (e < s_e)
 				goto next;
 			res = fib6_dump_table(tb, skb, cb);
@@ -1360,12 +1355,13 @@ void fib6_clean_all(int (*func)(struct rt6_info *, void *arg),
 {
 	struct fib6_table *table;
 	struct hlist_node *node;
+	struct hlist_head *head;
 	unsigned int h;
 
 	rcu_read_lock();
 	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
-		hlist_for_each_entry_rcu(table, node, &fib_table_hash[h],
-					 tb6_hlist) {
+		head = &init_net.ipv6.fib_table_hash[h];
+		hlist_for_each_entry_rcu(table, node, head, tb6_hlist) {
 			write_lock_bh(&table->tb6_lock);
 			fib6_clean_tree(&table->tb6_root, func, prune, arg);
 			write_unlock_bh(&table->tb6_lock);
@@ -1466,55 +1462,88 @@ void fib6_run_gc(unsigned long dummy)
 	spin_unlock_bh(&fib6_gc_lock);
 }
 
-int __init fib6_init(void)
+static int fib6_net_init(struct net *net)
 {
-	int ret = -ENOMEM;
-	fib6_node_kmem = kmem_cache_create("fib6_nodes",
-					   sizeof(struct fib6_node),
-					   0, SLAB_HWCACHE_ALIGN,
-					   NULL);
-	if (!fib6_node_kmem)
-		goto out;
+	int ret;
 
-	fib_table_hash = kzalloc(sizeof(*fib_table_hash)*FIB_TABLE_HASHSZ,
-				 GFP_KERNEL);
-	if (!fib_table_hash)
-		goto out_kmem_cache_create;
+	ret = -ENOMEM;
+	net->ipv6.fib_table_hash =
+		kzalloc(sizeof(*net->ipv6.fib_table_hash)*FIB_TABLE_HASHSZ,
+			GFP_KERNEL);
+	if (!net->ipv6.fib_table_hash)
+		goto out;
 
-	fib6_main_tbl = kzalloc(sizeof(*fib6_main_tbl), GFP_KERNEL);
-	if (!fib6_main_tbl)
+	net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl),
+					  GFP_KERNEL);
+	if (!net->ipv6.fib6_main_tbl)
 		goto out_fib_table_hash;
 
-	fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
-	fib6_main_tbl->tb6_root.leaf = &ip6_null_entry;
-	fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+	net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
+	net->ipv6.fib6_main_tbl->tb6_root.leaf = &ip6_null_entry;
+	net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
+		RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	fib6_local_tbl = kzalloc(sizeof(*fib6_local_tbl), GFP_KERNEL);
-	if (!fib6_local_tbl)
+	net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl),
+					   GFP_KERNEL);
+	if (!net->ipv6.fib6_local_tbl)
 		goto out_fib6_main_tbl;
-
-	fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
-	fib6_local_tbl->tb6_root.leaf = &ip6_null_entry;
-	fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+	net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
+	net->ipv6.fib6_local_tbl->tb6_root.leaf = &ip6_null_entry;
+	net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
+		RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 #endif
+	fib6_tables_init(net);
 
-	fib6_tables_init();
-
-	ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib);
-	if (ret)
-		goto out_fib6_local_tbl;
+	ret = 0;
 out:
 	return ret;
 
-out_fib6_local_tbl:
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	kfree(fib6_local_tbl);
 out_fib6_main_tbl:
+	kfree(net->ipv6.fib6_main_tbl);
 #endif
-	kfree(fib6_main_tbl);
 out_fib_table_hash:
-	kfree(fib_table_hash);
+	kfree(net->ipv6.fib_table_hash);
+	goto out;
+ }
+
+static void fib6_net_exit(struct net *net)
+{
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+	kfree(net->ipv6.fib6_local_tbl);
+#endif
+	kfree(net->ipv6.fib6_main_tbl);
+	kfree(net->ipv6.fib_table_hash);
+}
+
+static struct pernet_operations fib6_net_ops = {
+	.init = fib6_net_init,
+	.exit = fib6_net_exit,
+};
+
+int __init fib6_init(void)
+{
+	int ret = -ENOMEM;
+	fib6_node_kmem = kmem_cache_create("fib6_nodes",
+					   sizeof(struct fib6_node),
+					   0, SLAB_HWCACHE_ALIGN,
+					   NULL);
+	if (!fib6_node_kmem)
+		goto out;
+
+	ret = register_pernet_subsys(&fib6_net_ops);
+	if (ret)
+		goto out_kmem_cache_create;
+
+	ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib);
+	if (ret)
+		goto out_unregister_subsys;
+out:
+	return ret;
+
+out_unregister_subsys:
+	unregister_pernet_subsys(&fib6_net_ops);
 out_kmem_cache_create:
 	kmem_cache_destroy(fib6_node_kmem);
 	goto out;
@@ -1523,10 +1552,6 @@ out_kmem_cache_create:
 void fib6_gc_cleanup(void)
 {
 	del_timer(&ip6_fib_timer);
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	kfree(fib6_local_tbl);
-#endif
-	kfree(fib6_main_tbl);
-	kfree(fib_table_hash);
+	unregister_pernet_subsys(&fib6_net_ops);
 	kmem_cache_destroy(fib6_node_kmem);
 }

net/ipv6/route.c

@@ -571,7 +571,7 @@ struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr,
 		flags |= RT6_LOOKUP_F_HAS_SADDR;
 	}
 
-	dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup);
+	dst = fib6_rule_lookup(&init_net, &fl, flags, ip6_pol_route_lookup);
 	if (dst->error == 0)
 		return (struct rt6_info *) dst;
 
@@ -758,7 +758,7 @@ void ip6_route_input(struct sk_buff *skb)
 	if (rt6_need_strict(&iph->daddr))
 		flags |= RT6_LOOKUP_F_IFACE;
 
-	skb->dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_input);
+	skb->dst = fib6_rule_lookup(&init_net, &fl, flags, ip6_pol_route_input);
 }
 
 static struct rt6_info *ip6_pol_route_output(struct fib6_table *table,
@@ -777,7 +777,7 @@ struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl)
 	if (!ipv6_addr_any(&fl->fl6_src))
 		flags |= RT6_LOOKUP_F_HAS_SADDR;
 
-	return fib6_rule_lookup(fl, flags, ip6_pol_route_output);
+	return fib6_rule_lookup(&init_net, fl, flags, ip6_pol_route_output);
 }
 
 EXPORT_SYMBOL(ip6_route_output);
@@ -1069,7 +1069,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	if (cfg->fc_metric == 0)
 		cfg->fc_metric = IP6_RT_PRIO_USER;
 
-	table = fib6_new_table(cfg->fc_table);
+	table = fib6_new_table(&init_net, cfg->fc_table);
 	if (table == NULL) {
 		err = -ENOBUFS;
 		goto out;
@@ -1275,7 +1275,7 @@ static int ip6_route_del(struct fib6_config *cfg)
 	struct rt6_info *rt;
 	int err = -ESRCH;
 
-	table = fib6_get_table(cfg->fc_table);
+	table = fib6_get_table(&init_net, cfg->fc_table);
 	if (table == NULL)
 		return err;
 
@@ -1390,7 +1390,9 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
 	if (rt6_need_strict(dest))
 		flags |= RT6_LOOKUP_F_IFACE;
 
-	return (struct rt6_info *)fib6_rule_lookup((struct flowi *)&rdfl, flags, __ip6_route_redirect);
+	return (struct rt6_info *)fib6_rule_lookup(&init_net,
+						   (struct flowi *)&rdfl,
+						   flags, __ip6_route_redirect);
 }
 
 void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
@@ -1589,7 +1591,7 @@ static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixle
 	struct rt6_info *rt = NULL;
 	struct fib6_table *table;
 
-	table = fib6_get_table(RT6_TABLE_INFO);
+	table = fib6_get_table(&init_net, RT6_TABLE_INFO);
 	if (table == NULL)
 		return NULL;
 
@@ -1644,7 +1646,7 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d
 	struct rt6_info *rt;
 	struct fib6_table *table;
 
-	table = fib6_get_table(RT6_TABLE_DFLT);
+	table = fib6_get_table(&init_net, RT6_TABLE_DFLT);
 	if (table == NULL)
 		return NULL;
 
@@ -1688,7 +1690,7 @@ void rt6_purge_dflt_routers(void)
 	struct fib6_table *table;
 
 	/* NOTE: Keep consistent with rt6_get_dflt_router */
-	table = fib6_get_table(RT6_TABLE_DFLT);
+	table = fib6_get_table(&init_net, RT6_TABLE_DFLT);
 	if (table == NULL)
 		return;
 
@@ -1851,7 +1853,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 
 	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
 	rt->rt6i_dst.plen = 128;
-	rt->rt6i_table = fib6_get_table(RT6_TABLE_LOCAL);
+	rt->rt6i_table = fib6_get_table(&init_net, RT6_TABLE_LOCAL);
 
 	atomic_set(&rt->u.dst.__refcnt, 1);