fib_frontend.c

linux 内核源代码

/*
 * 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.
 *
 * Version:	$Id: fib_frontend.c,v 1.26 2001/10/31 21:55:54 davem Exp $
 *
 * Authors:	Alexey Kuznetsov, <[e-mail]>
 *
 *		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 <asm/uaccess.h>
#include <asm/system.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/init.h>
#include <linux/list.h>

#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/icmp.h>
#include <net/arp.h>
#include <net/ip_fib.h>
#include <net/rtnetlink.h>

#define FFprint(a...) printk(KERN_DEBUG a)

static struct sock *fibnl;

#ifndef CONFIG_IP_MULTIPLE_TABLES

struct fib_table *ip_fib_local_table;
struct fib_table *ip_fib_main_table;

#define FIB_TABLE_HASHSZ 1
static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];

static void __init fib4_rules_init(void)
{
	ip_fib_local_table = fib_hash_init(RT_TABLE_LOCAL);
	hlist_add_head_rcu(&ip_fib_local_table->tb_hlist, &fib_table_hash[0]);
	ip_fib_main_table  = fib_hash_init(RT_TABLE_MAIN);
	hlist_add_head_rcu(&ip_fib_main_table->tb_hlist, &fib_table_hash[0]);
}
#else

#define FIB_TABLE_HASHSZ 256
static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];

struct fib_table *fib_new_table(u32 id)
{
	struct fib_table *tb;
	unsigned int h;

	if (id == 0)
		id = RT_TABLE_MAIN;
	tb = fib_get_table(id);
	if (tb)
		return tb;
	tb = fib_hash_init(id);
	if (!tb)
		return NULL;
	h = id & (FIB_TABLE_HASHSZ - 1);
	hlist_add_head_rcu(&tb->tb_hlist, &fib_table_hash[h]);
	return tb;
}

struct fib_table *fib_get_table(u32 id)
{
	struct fib_table *tb;
	struct hlist_node *node;
	unsigned int h;

	if (id == 0)
		id = RT_TABLE_MAIN;
	h = id & (FIB_TABLE_HASHSZ - 1);
	rcu_read_lock();
	hlist_for_each_entry_rcu(tb, node, &fib_table_hash[h], tb_hlist) {
		if (tb->tb_id == id) {
			rcu_read_unlock();
			return tb;
		}
	}
	rcu_read_unlock();
	return NULL;
}
#endif /* CONFIG_IP_MULTIPLE_TABLES */

static void fib_flush(void)
{
	int flushed = 0;
	struct fib_table *tb;
	struct hlist_node *node;
	unsigned int h;

	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
		hlist_for_each_entry(tb, node, &fib_table_hash[h], tb_hlist)
			flushed += tb->tb_flush(tb);
	}

	if (flushed)
		rt_cache_flush(-1);
}

/*
 *	Find the first device with a given source address.
 */

struct net_device * ip_dev_find(__be32 addr)
{
	struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
	struct fib_result res;
	struct net_device *dev = NULL;
	struct fib_table *local_table;

#ifdef CONFIG_IP_MULTIPLE_TABLES
	res.r = NULL;
#endif

	local_table = fib_get_table(RT_TABLE_LOCAL);
	if (!local_table || local_table->tb_lookup(local_table, &fl, &res))
		return NULL;
	if (res.type != RTN_LOCAL)
		goto out;
	dev = FIB_RES_DEV(res);

	if (dev)
		dev_hold(dev);
out:
	fib_res_put(&res);
	return dev;
}

unsigned inet_addr_type(__be32 addr)
{
	struct flowi		fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
	struct fib_result	res;
	unsigned ret = RTN_BROADCAST;
	struct fib_table *local_table;

	if (ZERONET(addr) || BADCLASS(addr))
		return RTN_BROADCAST;
	if (MULTICAST(addr))
		return RTN_MULTICAST;

#ifdef CONFIG_IP_MULTIPLE_TABLES
	res.r = NULL;
#endif

	local_table = fib_get_table(RT_TABLE_LOCAL);
	if (local_table) {
		ret = RTN_UNICAST;
		if (!local_table->tb_lookup(local_table, &fl, &res)) {
			ret = res.type;
			fib_res_put(&res);
		}
	}
	return ret;
}

/* Given (packet source, input interface) and optional (dst, oif, tos):
   - (main) check, that source is valid i.e. not broadcast or our local
     address.
   - figure out what "logical" interface this packet arrived
     and calculate "specific destination" address.
   - check, that packet arrived from expected physical interface.
 */

int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
			struct net_device *dev, __be32 *spec_dst, u32 *itag)
{
	struct in_device *in_dev;
	struct flowi fl = { .nl_u = { .ip4_u =
				      { .daddr = src,
					.saddr = dst,
					.tos = tos } },
			    .iif = oif };
	struct fib_result res;
	int no_addr, rpf;
	int ret;

	no_addr = rpf = 0;
	rcu_read_lock();
	in_dev = __in_dev_get_rcu(dev);
	if (in_dev) {
		no_addr = in_dev->ifa_list == NULL;
		rpf = IN_DEV_RPFILTER(in_dev);
	}
	rcu_read_unlock();

	if (in_dev == NULL)
		goto e_inval;

	if (fib_lookup(&fl, &res))
		goto last_resort;
	if (res.type != RTN_UNICAST)
		goto e_inval_res;
	*spec_dst = FIB_RES_PREFSRC(res);
	fib_combine_itag(itag, &res);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (FIB_RES_DEV(res) == dev || res.fi->fib_nhs > 1)
#else
	if (FIB_RES_DEV(res) == dev)
#endif
	{
		ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
		fib_res_put(&res);
		return ret;
	}
	fib_res_put(&res);
	if (no_addr)
		goto last_resort;
	if (rpf)
		goto e_inval;
	fl.oif = dev->ifindex;

	ret = 0;
	if (fib_lookup(&fl, &res) == 0) {
		if (res.type == RTN_UNICAST) {
			*spec_dst = FIB_RES_PREFSRC(res);
			ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
		}
		fib_res_put(&res);
	}
	return ret;

last_resort:
	if (rpf)
		goto e_inval;
	*spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
	*itag = 0;
	return 0;

e_inval_res:
	fib_res_put(&res);
e_inval:
	return -EINVAL;
}

static inline __be32 sk_extract_addr(struct sockaddr *addr)
{
	return ((struct sockaddr_in *) addr)->sin_addr.s_addr;
}

static int put_rtax(struct nlattr *mx, int len, int type, u32 value)
{
	struct nlattr *nla;

	nla = (struct nlattr *) ((char *) mx + len);
	nla->nla_type = type;
	nla->nla_len = nla_attr_size(4);
	*(u32 *) nla_data(nla) = value;

	return len + nla_total_size(4);
}

static int rtentry_to_fib_config(int cmd, struct rtentry *rt,
				 struct fib_config *cfg)
{
	__be32 addr;
	int plen;

	memset(cfg, 0, sizeof(*cfg));

	if (rt->rt_dst.sa_family != AF_INET)
		return -EAFNOSUPPORT;

	/*
	 * Check mask for validity:
	 * a) it must be contiguous.
	 * b) destination must have all host bits clear.
	 * c) if application forgot to set correct family (AF_INET),
	 *    reject request unless it is absolutely clear i.e.
	 *    both family and mask are zero.
	 */
	plen = 32;
	addr = sk_extract_addr(&rt->rt_dst);
	if (!(rt->rt_flags & RTF_HOST)) {
		__be32 mask = sk_extract_addr(&rt->rt_genmask);

		if (rt->rt_genmask.sa_family != AF_INET) {
			if (mask || rt->rt_genmask.sa_family)
				return -EAFNOSUPPORT;
		}

		if (bad_mask(mask, addr))
			return -EINVAL;

		plen = inet_mask_len(mask);
	}

	cfg->fc_dst_len = plen;
	cfg->fc_dst = addr;

	if (cmd != SIOCDELRT) {
		cfg->fc_nlflags = NLM_F_CREATE;
		cfg->fc_protocol = RTPROT_BOOT;
	}

	if (rt->rt_metric)
		cfg->fc_priority = rt->rt_metric - 1;

	if (rt->rt_flags & RTF_REJECT) {
		cfg->fc_scope = RT_SCOPE_HOST;
		cfg->fc_type = RTN_UNREACHABLE;
		return 0;
	}

	cfg->fc_scope = RT_SCOPE_NOWHERE;
	cfg->fc_type = RTN_UNICAST;

	if (rt->rt_dev) {
		char *colon;
		struct net_device *dev;
		char devname[IFNAMSIZ];

		if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1))
			return -EFAULT;

		devname[IFNAMSIZ-1] = 0;
		colon = strchr(devname, ':');
		if (colon)
			*colon = 0;
		dev = __dev_get_by_name(&init_net, devname);
		if (!dev)
			return -ENODEV;
		cfg->fc_oif = dev->ifindex;
		if (colon) {
			struct in_ifaddr *ifa;
			struct in_device *in_dev = __in_dev_get_rtnl(dev);
			if (!in_dev)
				return -ENODEV;
			*colon = ':';
			for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next)
				if (strcmp(ifa->ifa_label, devname) == 0)
					break;
			if (ifa == NULL)
				return -ENODEV;
			cfg->fc_prefsrc = ifa->ifa_local;
		}
	}

	addr = sk_extract_addr(&rt->rt_gateway);
	if (rt->rt_gateway.sa_family == AF_INET && addr) {
		cfg->fc_gw = addr;
		if (rt->rt_flags & RTF_GATEWAY &&
		    inet_addr_type(addr) == RTN_UNICAST)
			cfg->fc_scope = RT_SCOPE_UNIVERSE;
	}

	if (cmd == SIOCDELRT)
		return 0;

	if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw)
		return -EINVAL;

	if (cfg->fc_scope == RT_SCOPE_NOWHERE)
		cfg->fc_scope = RT_SCOPE_LINK;

	if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) {
		struct nlattr *mx;
		int len = 0;

		mx = kzalloc(3 * nla_total_size(4), GFP_KERNEL);
		if (mx == NULL)
			return -ENOMEM;

		if (rt->rt_flags & RTF_MTU)
			len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40);

		if (rt->rt_flags & RTF_WINDOW)
			len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window);

		if (rt->rt_flags & RTF_IRTT)
			len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3);

		cfg->fc_mx = mx;
		cfg->fc_mx_len = len;
	}

	return 0;
}

/*
 *	Handle IP routing ioctl calls. These are used to manipulate the routing tables
 */

int ip_rt_ioctl(unsigned int cmd, void __user *arg)
{
	struct fib_config cfg;
	struct rtentry rt;
	int err;

	switch (cmd) {
	case SIOCADDRT:		/* Add a route */
	case SIOCDELRT:		/* Delete a route */
		if (!capable(CAP_NET_ADMIN))
			return -EPERM;

		if (copy_from_user(&rt, arg, sizeof(rt)))
			return -EFAULT;

		rtnl_lock();
		err = rtentry_to_fib_config(cmd, &rt, &cfg);
		if (err == 0) {
			struct fib_table *tb;

			if (cmd == SIOCDELRT) {
				tb = fib_get_table(cfg.fc_table);
				if (tb)
					err = tb->tb_delete(tb, &cfg);
				else
					err = -ESRCH;
			} else {
				tb = fib_new_table(cfg.fc_table);
				if (tb)
					err = tb->tb_insert(tb, &cfg);
				else
					err = -ENOBUFS;
			}

			/* allocated by rtentry_to_fib_config() */
			kfree(cfg.fc_mx);
		}
		rtnl_unlock();
		return err;
	}
	return -EINVAL;
}

const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = {
	[RTA_DST]		= { .type = NLA_U32 },
	[RTA_SRC]		= { .type = NLA_U32 },
	[RTA_IIF]		= { .type = NLA_U32 },
	[RTA_OIF]		= { .type = NLA_U32 },
	[RTA_GATEWAY]		= { .type = NLA_U32 },
	[RTA_PRIORITY]		= { .type = NLA_U32 },
	[RTA_PREFSRC]		= { .type = NLA_U32 },
	[RTA_METRICS]		= { .type = NLA_NESTED },
	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
	[RTA_PROTOINFO]		= { .type = NLA_U32 },
	[RTA_FLOW]		= { .type = NLA_U32 },