diff mbox series

[RFC,net-next,11/20] net/ipv6: Add fib6_null_entry

Message ID 20180225194730.30063-12-dsahern@gmail.com
State RFC, archived
Delegated to: David Miller
Headers show
Series net/ipv6: Separate data structures for FIB and data path | expand

Commit Message

David Ahern Feb. 25, 2018, 7:47 p.m. UTC 
ip6_null_entry will stay a dst based return for lookups that fail to
match an entry.

Add a new fib6_null_entry which constitutes the root node and leafs
for fibs.

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/net/netns/ipv6.h |  3 ++-
 net/ipv6/ip6_fib.c       | 26 ++++++++++----------
 net/ipv6/route.c         | 62 +++++++++++++++++++++++++++++++++---------------
 3 files changed, 58 insertions(+), 33 deletions(-)
diff mbox series

Patch

diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 987cc4569cb8..c6ee8d21bfda 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -59,7 +59,8 @@  struct netns_ipv6 {
 #endif
 	struct xt_table		*ip6table_nat;
 #endif
-	struct rt6_info         *ip6_null_entry;
+	struct rt6_info         *fib6_null_entry;
+	struct rt6_info		*ip6_null_entry;
 	struct rt6_statistics   *rt6_stats;
 	struct timer_list       ip6_fib_timer;
 	struct hlist_head       *fib_table_hash;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7bc23b048189..5b03f7e8d850 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -231,7 +231,7 @@  static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 	if (table) {
 		table->tb6_id = id;
 		rcu_assign_pointer(table->tb6_root.leaf,
-				   net->ipv6.ip6_null_entry);
+				   net->ipv6.fib6_null_entry);
 		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 		inet_peer_base_init(&table->tb6_peers);
 	}
@@ -368,7 +368,7 @@  struct fib6_dump_arg {
 
 static void fib6_rt_dump(struct rt6_info *rt, struct fib6_dump_arg *arg)
 {
-	if (rt == arg->net->ipv6.ip6_null_entry)
+	if (rt == arg->net->ipv6.fib6_null_entry)
 		return;
 	call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt);
 }
@@ -639,7 +639,7 @@  static struct fib6_node *fib6_add_1(struct net *net,
 			/* remove null_entry in the root node */
 			} else if (fn->fn_flags & RTN_TL_ROOT &&
 				   rcu_access_pointer(fn->leaf) ==
-				   net->ipv6.ip6_null_entry) {
+				   net->ipv6.fib6_null_entry) {
 				RCU_INIT_POINTER(fn->leaf, NULL);
 			}
 
@@ -1143,9 +1143,9 @@  int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			if (!sfn)
 				goto failure;
 
-			atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
+			atomic_inc(&info->nl_net->ipv6.fib6_null_entry->rt6i_ref);
 			rcu_assign_pointer(sfn->leaf,
-					   info->nl_net->ipv6.ip6_null_entry);
+					   info->nl_net->ipv6.fib6_null_entry);
 			sfn->fn_flags = RTN_ROOT;
 
 			/* Now add the first leaf node to new subtree */
@@ -1184,7 +1184,7 @@  int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			if (fn->fn_flags & RTN_TL_ROOT) {
 				/* put back null_entry for root node */
 				rcu_assign_pointer(fn->leaf,
-					    info->nl_net->ipv6.ip6_null_entry);
+					    info->nl_net->ipv6.fib6_null_entry);
 			} else {
 				atomic_inc(&rt->rt6i_ref);
 				rcu_assign_pointer(fn->leaf, rt);
@@ -1223,7 +1223,7 @@  int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 				if (!pn_leaf) {
 					WARN_ON(!pn_leaf);
 					pn_leaf =
-					    info->nl_net->ipv6.ip6_null_entry;
+					    info->nl_net->ipv6.fib6_null_entry;
 				}
 #endif
 				atomic_inc(&pn_leaf->rt6i_ref);
@@ -1466,7 +1466,7 @@  static struct rt6_info *fib6_find_prefix(struct net *net,
 	struct fib6_node *child_left, *child_right;
 
 	if (fn->fn_flags & RTN_ROOT)
-		return net->ipv6.ip6_null_entry;
+		return net->ipv6.fib6_null_entry;
 
 	while (fn) {
 		child_left = rcu_dereference_protected(fn->left,
@@ -1503,7 +1503,7 @@  static struct fib6_node *fib6_repair_tree(struct net *net,
 
 	/* Set fn->leaf to null_entry for root node. */
 	if (fn->fn_flags & RTN_TL_ROOT) {
-		rcu_assign_pointer(fn->leaf, net->ipv6.ip6_null_entry);
+		rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry);
 		return fn;
 	}
 
@@ -1548,7 +1548,7 @@  static struct fib6_node *fib6_repair_tree(struct net *net,
 #if RT6_DEBUG >= 2
 			if (!new_fn_leaf) {
 				WARN_ON(!new_fn_leaf);
-				new_fn_leaf = net->ipv6.ip6_null_entry;
+				new_fn_leaf = net->ipv6.fib6_null_entry;
 			}
 #endif
 			atomic_inc(&new_fn_leaf->rt6i_ref);
@@ -1698,7 +1698,7 @@  int fib6_del(struct rt6_info *rt, struct nl_info *info)
 		return -ENOENT;
 	}
 #endif
-	if (!fn || rt == net->ipv6.ip6_null_entry)
+	if (!fn || rt == net->ipv6.fib6_null_entry)
 		return -ENOENT;
 
 	WARN_ON(!(fn->fn_flags & RTN_RTINFO));
@@ -2059,7 +2059,7 @@  static int __net_init fib6_net_init(struct net *net)
 
 	net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
 	rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf,
-			   net->ipv6.ip6_null_entry);
+			   net->ipv6.fib6_null_entry);
 	net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
 		RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 	inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers);
@@ -2071,7 +2071,7 @@  static int __net_init fib6_net_init(struct net *net)
 		goto out_fib6_main_tbl;
 	net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
 	rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf,
-			   net->ipv6.ip6_null_entry);
+			   net->ipv6.fib6_null_entry);
 	net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
 		RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 	inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b6206ec947e6..31832b170a9f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -276,6 +276,15 @@  static const u32 ip6_template_metrics[RTAX_MAX] = {
 	[RTAX_HOPLIMIT - 1] = 0,
 };
 
+static const struct rt6_info fib6_null_entry_template = {
+	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
+	.rt6i_protocol  = RTPROT_KERNEL,
+	.rt6i_metric	= ~(u32)0,
+	.rt6i_ref	= ATOMIC_INIT(1),
+	.fib6_type	= RTN_UNREACHABLE,
+	.fib6_metrics	= (struct dst_metrics *)&dst_default_metrics,
+};
+
 static const struct rt6_info ip6_null_entry_template = {
 	.dst = {
 		.__refcnt	= ATOMIC_INIT(1),
@@ -520,10 +529,10 @@  static inline struct rt6_info *rt6_device_match(struct net *net,
 			return local;
 
 		if (flags & RT6_LOOKUP_F_IFACE)
-			return net->ipv6.ip6_null_entry;
+			return net->ipv6.fib6_null_entry;
 	}
 
-	return rt->fib6_nh.nh_flags & RTNH_F_DEAD ? net->ipv6.ip6_null_entry : rt;
+	return rt->fib6_nh.nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt;
 }
 
 #ifdef CONFIG_IPV6_ROUTER_PREF
@@ -756,8 +765,8 @@  static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
 	bool do_rr = false;
 	int key_plen;
 
-	if (!leaf || leaf == net->ipv6.ip6_null_entry)
-		return net->ipv6.ip6_null_entry;
+	if (!leaf || leaf == net->ipv6.fib6_null_entry)
+		return net->ipv6.fib6_null_entry;
 
 	rt0 = rcu_dereference(fn->rr_ptr);
 	if (!rt0)
@@ -774,7 +783,7 @@  static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
 		key_plen = rt0->rt6i_src.plen;
 #endif
 	if (fn->fn_bit != key_plen)
-		return net->ipv6.ip6_null_entry;
+		return net->ipv6.fib6_null_entry;
 
 	match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict,
 			     &do_rr);
@@ -795,7 +804,7 @@  static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
 		}
 	}
 
-	return match ? match : net->ipv6.ip6_null_entry;
+	return match ? match : net->ipv6.fib6_null_entry;
 }
 
 static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt)
@@ -1056,7 +1065,7 @@  static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 restart:
 	rt = rcu_dereference(fn->leaf);
 	if (!rt) {
-		rt = net->ipv6.ip6_null_entry;
+		rt = net->ipv6.fib6_null_entry;
 	} else {
 		rt = rt6_device_match(net, rt, &fl6->saddr,
 				      fl6->flowi6_oif, flags);
@@ -1064,7 +1073,7 @@  static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 			rt = rt6_multipath_select(rt, fl6,
 						  fl6->flowi6_oif, flags);
 	}
-	if (rt == net->ipv6.ip6_null_entry) {
+	if (rt == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
 			goto restart;
@@ -1787,7 +1796,7 @@  struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 	rt = rt6_select(net, fn, oif, strict);
 	if (rt->rt6i_nsiblings)
 		rt = rt6_multipath_select(rt, fl6, oif, strict);
-	if (rt == net->ipv6.ip6_null_entry) {
+	if (rt == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
 			goto redo_rt6_select;
@@ -1804,7 +1813,8 @@  struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 	if (rt_cache)
 		rt = rt_cache;
 
-	if (rt == net->ipv6.ip6_null_entry) {
+	if (rt == net->ipv6.fib6_null_entry) {
+		rt = net->ipv6.ip6_null_entry;
 		rcu_read_unlock();
 		dst_hold(&rt->dst);
 		trace_fib6_table_lookup(net, rt, table, fl6);
@@ -2295,13 +2305,13 @@  static struct rt6_info *__ip6_route_redirect(struct net *net,
 	}
 
 	if (!rt)
-		rt = net->ipv6.ip6_null_entry;
+		rt = net->ipv6.fib6_null_entry;
 	else if (rt->rt6i_flags & RTF_REJECT) {
 		rt = net->ipv6.ip6_null_entry;
 		goto out;
 	}
 
-	if (rt == net->ipv6.ip6_null_entry) {
+	if (rt == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
 			goto restart;
@@ -2906,7 +2916,7 @@  static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
 	struct fib6_table *table;
 	int err;
 
-	if (rt == net->ipv6.ip6_null_entry) {
+	if (rt == net->ipv6.fib6_null_entry) {
 		err = -ENOENT;
 		goto out;
 	}
@@ -2936,7 +2946,7 @@  static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
 	struct fib6_table *table;
 	int err = -ENOENT;
 
-	if (rt == net->ipv6.ip6_null_entry)
+	if (rt == net->ipv6.fib6_null_entry)
 		goto out_put;
 	table = rt->rt6i_table;
 	spin_lock_bh(&table->tb6_lock);
@@ -3488,7 +3498,7 @@  static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
 	struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
 
 	if (((void *)rt->fib6_nh.nh_dev == dev || !dev) &&
-	    rt != net->ipv6.ip6_null_entry &&
+	    rt != net->ipv6.fib6_null_entry &&
 	    ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
 		spin_lock_bh(&rt6_exception_lock);
 		/* remove prefsrc entry */
@@ -3643,7 +3653,7 @@  static int fib6_ifup(struct rt6_info *rt, void *p_arg)
 	const struct arg_netdev_event *arg = p_arg;
 	struct net *net = dev_net(arg->dev);
 
-	if (rt != net->ipv6.ip6_null_entry && rt->fib6_nh.nh_dev == arg->dev) {
+	if (rt != net->ipv6.fib6_null_entry && rt->fib6_nh.nh_dev == arg->dev) {
 		rt->fib6_nh.nh_flags &= ~arg->nh_flags;
 		fib6_update_sernum_upto_root(net, rt);
 		rt6_multipath_rebalance(rt);
@@ -3727,7 +3737,7 @@  static int fib6_ifdown(struct rt6_info *rt, void *p_arg)
 	const struct net_device *dev = arg->dev;
 	struct net *net = dev_net(dev);
 
-	if (rt == net->ipv6.ip6_null_entry)
+	if (rt == net->ipv6.fib6_null_entry)
 		return 0;
 
 	switch (arg->event) {
@@ -4485,7 +4495,7 @@  int rt6_dump_route(struct rt6_info *rt, void *p_arg)
 	struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
 	struct net *net = arg->net;
 
-	if (rt == net->ipv6.ip6_null_entry)
+	if (rt == net->ipv6.fib6_null_entry)
 		return 0;
 
 	if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) {
@@ -4674,6 +4684,8 @@  static int ip6_route_dev_notify(struct notifier_block *this,
 		return NOTIFY_OK;
 
 	if (event == NETDEV_REGISTER) {
+		net->ipv6.fib6_null_entry->fib6_nh.nh_dev = dev;
+		net->ipv6.fib6_null_entry->rt6i_idev = in6_dev_get(dev);
 		net->ipv6.ip6_null_entry->dst.dev = dev;
 		net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -4687,6 +4699,7 @@  static int ip6_route_dev_notify(struct notifier_block *this,
 		/* NETDEV_UNREGISTER could be fired for multiple times by
 		 * netdev_wait_allrefs(). Make sure we only call this once.
 		 */
+		in6_dev_put_clear(&net->ipv6.fib6_null_entry->rt6i_idev);
 		in6_dev_put_clear(&net->ipv6.ip6_null_entry->rt6i_idev);
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 		in6_dev_put_clear(&net->ipv6.ip6_prohibit_entry->rt6i_idev);
@@ -4870,11 +4883,17 @@  static int __net_init ip6_route_net_init(struct net *net)
 	if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0)
 		goto out_ip6_dst_ops;
 
+	net->ipv6.fib6_null_entry = kmemdup(&fib6_null_entry_template,
+					    sizeof(*net->ipv6.fib6_null_entry),
+					    GFP_KERNEL);
+	if (!net->ipv6.fib6_null_entry)
+		goto out_ip6_dst_entries;
+
 	net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
 					   sizeof(*net->ipv6.ip6_null_entry),
 					   GFP_KERNEL);
 	if (!net->ipv6.ip6_null_entry)
-		goto out_ip6_dst_entries;
+		goto out_fib6_null_entry;
 	net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
 	dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
 			 ip6_template_metrics, true);
@@ -4921,6 +4940,8 @@  static int __net_init ip6_route_net_init(struct net *net)
 out_ip6_null_entry:
 	kfree(net->ipv6.ip6_null_entry);
 #endif
+out_fib6_null_entry:
+	kfree(net->ipv6.fib6_null_entry);
 out_ip6_dst_entries:
 	dst_entries_destroy(&net->ipv6.ip6_dst_ops);
 out_ip6_dst_ops:
@@ -4929,6 +4950,7 @@  static int __net_init ip6_route_net_init(struct net *net)
 
 static void __net_exit ip6_route_net_exit(struct net *net)
 {
+	kfree(net->ipv6.fib6_null_entry);
 	kfree(net->ipv6.ip6_null_entry);
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 	kfree(net->ipv6.ip6_prohibit_entry);
@@ -5002,6 +5024,8 @@  void __init ip6_route_init_special_entries(void)
 	/* Registering of the loopback is done before this portion of code,
 	 * the loopback reference in rt6_info will not be taken, do it
 	 * manually for init_net */
+	init_net.ipv6.fib6_null_entry->fib6_nh.nh_dev = init_net.loopback_dev;
+	init_net.ipv6.fib6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
 	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
 	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
   #ifdef CONFIG_IPV6_MULTIPLE_TABLES