path: root/net/ipv4/fib_frontend.c

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		IPv4 Forwarding Information Base: FIB frontend.
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 */

#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/skbuff.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/slab.h>

#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/ip_fib.h>
#include <net/rtnetlink.h>
#include <net/xfrm.h>
#include <net/l3mdev.h>
#include <net/lwtunnel.h>
#include <trace/events/fib.h>

#ifndef CONFIG_IP_MULTIPLE_TABLES

static int __net_init fib4_rules_init(struct net *net)
{
	struct fib_table *local_table, *main_table;

	main_table  = fib_trie_table(RT_TABLE_MAIN, NULL);
	if (!main_table)
		return -ENOMEM;

	local_table = fib_trie_table(RT_TABLE_LOCAL, main_table);
	if (!local_table)
		goto fail;

	hlist_add_head_rcu(&local_table->tb_hlist,
				&net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]);
	hlist_add_head_rcu(&main_table->tb_hlist,
				&net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]);
	return 0;

fail:
	fib_free_table(main_table);
	return -ENOMEM;
}

static bool fib4_has_custom_rules(struct net *net)
{
	return false;
}
#else

struct fib_table *fib_new_table(struct net *net, u32 id)
{
	struct fib_table *tb, *alias = NULL;
	unsigned int h;

	if (id == 0)
		id = RT_TABLE_MAIN;
	tb = fib_get_table(net, id);
	if (tb)
		return tb;

	if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules)
		alias = fib_new_table(net, RT_TABLE_MAIN);

	tb = fib_trie_table(id, alias);
	if (!tb)
		return NULL;

	switch (id) {
	case RT_TABLE_MAIN:
		rcu_assign_pointer(net->ipv4.fib_main, tb);
		break;
	case RT_TABLE_DEFAULT:
		rcu_assign_pointer(net->ipv4.fib_default, tb);
		break;
	default:
		break;
	}

	h = id & (FIB_TABLE_HASHSZ - 1);
	hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]);
	return tb;
}
EXPORT_SYMBOL_GPL(fib_new_table);

/* caller must hold either rtnl or rcu read lock */
struct fib_table *fib_get_table(struct net *net, u32 id)
{
	struct fib_table *tb;
	struct hlist_head *head;
	unsigned int h;

	if (id == 0)
		id = RT_TABLE_MAIN;
	h = id & (FIB_TABLE_HASHSZ - 1);

	head = &net->ipv4.fib_table_hash[h];
	hlist_for_each_entry_rcu(tb, head, tb_hlist) {
		if (tb->tb_id == id)
			return tb;
	}
	return NULL;
}

static bool fib4_has_custom_rules(struct net *net)
{
	return net->ipv4.fib_has_custom_rules;
}
#endif /* CONFIG_IP_MULTIPLE_TABLES */

static void fib_replace_table(struct net *net, struct fib_table *old,
			      struct fib_table *new)
{
#ifdef CONFIG_IP_MULTIPLE_TABLES
	switch (new->tb_id) {
	case RT_TABLE_MAIN:
		rcu_assign_pointer(net->ipv4.fib_main, new);
		break;
	case RT_TABLE_DEFAULT:
		rcu_assign_pointer(net->ipv4.fib_default, new);
		break;
	default:
		break;
	}

#endif
	/* replace the old table in the hlist */
	hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist);
}

int fib_unmerge(struct net *net)
{
	struct fib_table *old, *new, *main_table;

	/* attempt to fetch local table if it has been allocated */
	old = fib_get_table(net, RT_TABLE_LOCAL);
	if (!old)
		return 0;

	new = fib_trie_unmerge(old);
	if (!new)
		return -ENOMEM;

	/* table is already unmerged */
	if (new == old)
		return 0;

	/* replace merged table with clean table */
	fib_replace_table(net, old, new);
	fib_free_table(old);

	/* attempt to fetch main table if it has been allocated */
	main_table = fib_get_table(net, RT_TABLE_MAIN);
	if (!main_table)
		return 0;

	/* flush local entries from main table */
	fib_table_flush_external(main_table);

	return 0;
}

static void fib_flush(struct net *net)
{
	int flushed = 0;
	unsigned int h;

	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
		struct hlist_head *head = &net->ipv4.fib_table_hash[h];
		struct hlist_node *tmp;
		struct fib_table *tb;

		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist)
			flushed += fib_table_flush(net, tb, false);
	}

	if (flushed)
		rt_cache_flush(net);
}

/*
 * Find address type as if only "dev" was present in the system. If
 * on_dev is NULL then all interfaces are taken into consideration.
 */
static inline unsigned int __inet_dev_addr_type(struct net *net,
						const struct net_device *dev,
						__be32 addr, u32 tb_id)
{
	struct flowi4		fl4 = { .daddr = addr };
	struct fib_result	res;
	unsigned int ret = RTN_BROADCAST;
	struct fib_table *table;

	if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr))
		return RTN_BROADCAST;
	if (ipv4_is_multicast(addr))
		return RTN_MULTICAST;

	rcu_read_lock();

	table = fib_get_table(net, tb_id);
	if (table) {
		ret = RTN_UNICAST;
		if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) {
			if (!dev || dev == res.fi->fib_dev)
				ret = res.type;
		}
	}

	rcu_read_unlock();
	return ret;
}

unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id)
{
	return __inet_dev_addr_type(net, NULL, addr, tb_id);
}
EXPORT_SYMBOL(inet_addr_type_table);

unsigned int inet_addr_type(struct net *net, __be32 addr)
{
	return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL);
}
EXPORT_SYMBOL(inet_addr_type);

unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
				__be32 addr)
{
	u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;

	return __inet_dev_addr_type(net, dev, addr, rt_table);
}
EXPORT_SYMBOL(inet_dev_addr_type);

/* inet_addr_type with dev == NULL but using the table from a dev
 * if one is associated
 */
unsigned int inet_addr_type_dev_table(struct net *net,
				      const struct net_device *dev,
				      __be32 addr)
{
	u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;

	return __inet_dev_addr_type(net, NULL, addr, rt_table);
}
EXPORT_SYMBOL(inet_addr_type_dev_table);

__be32 fib_compute_spec_dst(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct in_device *in_dev;
	struct fib_result res;
	struct rtable *rt;
	struct net *net;
	int scope;

	rt = skb_rtable(skb);
	if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) ==
	    RTCF_LOCAL)
		return ip_hdr(skb)->daddr;

	in_dev = __in_dev_get_rcu(dev);

	net = dev_net(dev);

	scope = RT_SCOPE_UNIVERSE;
	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
		bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev);
		struct flowi4 fl4 = {
			.flowi4_iif = LOOPBACK_IFINDEX,
			.flowi4_oif = l3mdev_master_ifind