route.c

linux 内核源代码

/*
 *	Linux INET6 implementation
 *	FIB front-end.
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>
 *
 *	$Id: route.c,v 1.56 2001/10/31 21:55:55 davem Exp $
 *
 *	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.
 */

/*	Changes:
 *
 *	YOSHIFUJI Hideaki @USAGI
 *		reworked default router selection.
 *		- respect outgoing interface
 *		- select from (probably) reachable routers (i.e.
 *		routers in REACHABLE, STALE, DELAY or PROBE states).
 *		- always select the same router if it is (probably)
 *		reachable.  otherwise, round-robin the list.
 *	Ville Nuorvala
 *		Fixed routing subtrees.
 */

#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/times.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/route.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/init.h>
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/tcp.h>
#include <linux/rtnetlink.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/netevent.h>
#include <net/netlink.h>

#include <asm/uaccess.h>

#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

/* Set to 3 to get tracing. */
#define RT6_DEBUG 2

#if RT6_DEBUG >= 3
#define RDBG(x) printk x
#define RT6_TRACE(x...) printk(KERN_DEBUG x)
#else
#define RDBG(x)
#define RT6_TRACE(x...) do { ; } while (0)
#endif

#define CLONE_OFFLINK_ROUTE 0

static int ip6_rt_max_size = 4096;
static int ip6_rt_gc_min_interval = HZ / 2;
static int ip6_rt_gc_timeout = 60*HZ;
int ip6_rt_gc_interval = 30*HZ;
static int ip6_rt_gc_elasticity = 9;
static int ip6_rt_mtu_expires = 10*60*HZ;
static int ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;

static struct rt6_info * ip6_rt_copy(struct rt6_info *ort);
static struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void		ip6_dst_destroy(struct dst_entry *);
static void		ip6_dst_ifdown(struct dst_entry *,
				       struct net_device *dev, int how);
static int		 ip6_dst_gc(void);

static int		ip6_pkt_discard(struct sk_buff *skb);
static int		ip6_pkt_discard_out(struct sk_buff *skb);
static void		ip6_link_failure(struct sk_buff *skb);
static void		ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu);

#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex,
					   unsigned pref);
static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex);
#endif

static struct dst_ops ip6_dst_ops = {
	.family			=	AF_INET6,
	.protocol		=	__constant_htons(ETH_P_IPV6),
	.gc			=	ip6_dst_gc,
	.gc_thresh		=	1024,
	.check			=	ip6_dst_check,
	.destroy		=	ip6_dst_destroy,
	.ifdown			=	ip6_dst_ifdown,
	.negative_advice	=	ip6_negative_advice,
	.link_failure		=	ip6_link_failure,
	.update_pmtu		=	ip6_rt_update_pmtu,
	.entry_size		=	sizeof(struct rt6_info),
};

static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}

static struct dst_ops ip6_dst_blackhole_ops = {
	.family			=	AF_INET6,
	.protocol		=	__constant_htons(ETH_P_IPV6),
	.destroy		=	ip6_dst_destroy,
	.check			=	ip6_dst_check,
	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
	.entry_size		=	sizeof(struct rt6_info),
};

struct rt6_info ip6_null_entry = {
	.u = {
		.dst = {
			.__refcnt	= ATOMIC_INIT(1),
			.__use		= 1,
			.obsolete	= -1,
			.error		= -ENETUNREACH,
			.metrics	= { [RTAX_HOPLIMIT - 1] = 255, },
			.input		= ip6_pkt_discard,
			.output		= ip6_pkt_discard_out,
			.ops		= &ip6_dst_ops,
			.path		= (struct dst_entry*)&ip6_null_entry,
		}
	},
	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
	.rt6i_metric	= ~(u32) 0,
	.rt6i_ref	= ATOMIC_INIT(1),
};

#ifdef CONFIG_IPV6_MULTIPLE_TABLES

static int ip6_pkt_prohibit(struct sk_buff *skb);
static int ip6_pkt_prohibit_out(struct sk_buff *skb);
static int ip6_pkt_blk_hole(struct sk_buff *skb);

struct rt6_info ip6_prohibit_entry = {
	.u = {
		.dst = {
			.__refcnt	= ATOMIC_INIT(1),
			.__use		= 1,
			.obsolete	= -1,
			.error		= -EACCES,
			.metrics	= { [RTAX_HOPLIMIT - 1] = 255, },
			.input		= ip6_pkt_prohibit,
			.output		= ip6_pkt_prohibit_out,
			.ops		= &ip6_dst_ops,
			.path		= (struct dst_entry*)&ip6_prohibit_entry,
		}
	},
	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
	.rt6i_metric	= ~(u32) 0,
	.rt6i_ref	= ATOMIC_INIT(1),
};

struct rt6_info ip6_blk_hole_entry = {
	.u = {
		.dst = {
			.__refcnt	= ATOMIC_INIT(1),
			.__use		= 1,
			.obsolete	= -1,
			.error		= -EINVAL,
			.metrics	= { [RTAX_HOPLIMIT - 1] = 255, },
			.input		= ip6_pkt_blk_hole,
			.output		= ip6_pkt_blk_hole,
			.ops		= &ip6_dst_ops,
			.path		= (struct dst_entry*)&ip6_blk_hole_entry,
		}
	},
	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
	.rt6i_metric	= ~(u32) 0,
	.rt6i_ref	= ATOMIC_INIT(1),
};

#endif

/* allocate dst with ip6_dst_ops */
static __inline__ struct rt6_info *ip6_dst_alloc(void)
{
	return (struct rt6_info *)dst_alloc(&ip6_dst_ops);
}

static void ip6_dst_destroy(struct dst_entry *dst)
{
	struct rt6_info *rt = (struct rt6_info *)dst;
	struct inet6_dev *idev = rt->rt6i_idev;

	if (idev != NULL) {
		rt->rt6i_idev = NULL;
		in6_dev_put(idev);
	}
}

static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
			   int how)
{
	struct rt6_info *rt = (struct rt6_info *)dst;
	struct inet6_dev *idev = rt->rt6i_idev;

	if (dev != init_net.loopback_dev && idev != NULL && idev->dev == dev) {
		struct inet6_dev *loopback_idev = in6_dev_get(init_net.loopback_dev);
		if (loopback_idev != NULL) {
			rt->rt6i_idev = loopback_idev;
			in6_dev_put(idev);
		}
	}
}

static __inline__ int rt6_check_expired(const struct rt6_info *rt)
{
	return (rt->rt6i_flags & RTF_EXPIRES &&
		time_after(jiffies, rt->rt6i_expires));
}

static inline int rt6_need_strict(struct in6_addr *daddr)
{
	return (ipv6_addr_type(daddr) &
		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
}

/*
 *	Route lookup. Any table->tb6_lock is implied.
 */

static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt,
						    int oif,
						    int strict)
{
	struct rt6_info *local = NULL;
	struct rt6_info *sprt;

	if (oif) {
		for (sprt = rt; sprt; sprt = sprt->u.dst.rt6_next) {
			struct net_device *dev = sprt->rt6i_dev;
			if (dev->ifindex == oif)
				return sprt;
			if (dev->flags & IFF_LOOPBACK) {
				if (sprt->rt6i_idev == NULL ||
				    sprt->rt6i_idev->dev->ifindex != oif) {
					if (strict && oif)
						continue;
					if (local && (!oif ||
						      local->rt6i_idev->dev->ifindex == oif))
						continue;
				}
				local = sprt;
			}
		}

		if (local)
			return local;

		if (strict)
			return &ip6_null_entry;
	}
	return rt;
}

#ifdef CONFIG_IPV6_ROUTER_PREF
static void rt6_probe(struct rt6_info *rt)
{
	struct neighbour *neigh = rt ? rt->rt6i_nexthop : NULL;
	/*
	 * Okay, this does not seem to be appropriate
	 * for now, however, we need to check if it
	 * is really so; aka Router Reachability Probing.
	 *
	 * Router Reachability Probe MUST be rate-limited
	 * to no more than one per minute.
	 */
	if (!neigh || (neigh->nud_state & NUD_VALID))
		return;
	read_lock_bh(&neigh->lock);
	if (!(neigh->nud_state & NUD_VALID) &&
	    time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
		struct in6_addr mcaddr;
		struct in6_addr *target;

		neigh->updated = jiffies;
		read_unlock_bh(&neigh->lock);

		target = (struct in6_addr *)&neigh->primary_key;
		addrconf_addr_solict_mult(target, &mcaddr);
		ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL);
	} else
		read_unlock_bh(&neigh->lock);
}
#else
static inline void rt6_probe(struct rt6_info *rt)
{
	return;
}
#endif

/*
 * Default Router Selection (RFC 2461 6.3.6)
 */
static inline int rt6_check_dev(struct rt6_info *rt, int oif)
{
	struct net_device *dev = rt->rt6i_dev;
	if (!oif || dev->ifindex == oif)
		return 2;
	if ((dev->flags & IFF_LOOPBACK) &&
	    rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif)
		return 1;
	return 0;
}

static inline int rt6_check_neigh(struct rt6_info *rt)
{
	struct neighbour *neigh = rt->rt6i_nexthop;
	int m;
	if (rt->rt6i_flags & RTF_NONEXTHOP ||
	    !(rt->rt6i_flags & RTF_GATEWAY))
		m = 1;
	else if (neigh) {
		read_lock_bh(&neigh->lock);
		if (neigh->nud_state & NUD_VALID)
			m = 2;
#ifdef CONFIG_IPV6_ROUTER_PREF
		else if (neigh->nud_state & NUD_FAILED)
			m = 0;
#endif
		else
			m = 1;
		read_unlock_bh(&neigh->lock);
	} else
		m = 0;
	return m;
}

static int rt6_score_route(struct rt6_info *rt, int oif,
			   int strict)
{
	int m, n;

	m = rt6_check_dev(rt, oif);
	if (!m && (strict & RT6_LOOKUP_F_IFACE))
		return -1;
#ifdef CONFIG_IPV6_ROUTER_PREF
	m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2;
#endif
	n = rt6_check_neigh(rt);
	if (!n && (strict & RT6_LOOKUP_F_REACHABLE))
		return -1;
	return m;
}

static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
				   int *mpri, struct rt6_info *match)
{
	int m;

	if (rt6_check_expired(rt))
		goto out;

	m = rt6_score_route(rt, oif, strict);
	if (m < 0)
		goto out;

	if (m > *mpri) {
		if (strict & RT6_LOOKUP_F_REACHABLE)
			rt6_probe(match);
		*mpri = m;
		match = rt;
	} else if (strict & RT6_LOOKUP_F_REACHABLE) {
		rt6_probe(rt);
	}

out:
	return match;
}

static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
				     struct rt6_info *rr_head,
				     u32 metric, int oif, int strict)
{
	struct rt6_info *rt, *match;
	int mpri = -1;

	match = NULL;
	for (rt = rr_head; rt && rt->rt6i_metric == metric;
	     rt = rt->u.dst.rt6_next)
		match = find_match(rt, oif, strict, &mpri, match);
	for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
	     rt = rt->u.dst.rt6_next)
		match = find_match(rt, oif, strict, &mpri, match);

	return match;
}

static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
{
	struct rt6_info *match, *rt0;

	RT6_TRACE("%s(fn->leaf=%p, oif=%d)\n",
		  __FUNCTION__, fn->leaf, oif);

	rt0 = fn->rr_ptr;
	if (!rt0)
		fn->rr_ptr = rt0 = fn->leaf;

	match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict);

	if (!match &&
	    (strict & RT6_LOOKUP_F_REACHABLE)) {
		struct rt6_info *next = rt0->u.dst.rt6_next;

		/* no entries matched; do round-robin */
		if (!next || next->rt6i_metric != rt0->rt6i_metric)
			next = fn->leaf;

		if (next != rt0)
			fn->rr_ptr = next;
	}

	RT6_TRACE("%s() => %p\n",
		  __FUNCTION__, match);

	return (match ? match : &ip6_null_entry);
}

#ifdef CONFIG_IPV6_ROUTE_INFO
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
		  struct in6_addr *gwaddr)
{
	struct route_info *rinfo = (struct route_info *) opt;
	struct in6_addr prefix_buf, *prefix;
	unsigned int pref;
	u32 lifetime;
	struct rt6_info *rt;

	if (len < sizeof(struct route_info)) {
		return -EINVAL;
	}

	/* Sanity check for prefix_len and length */
	if (rinfo->length > 3) {
		return -EINVAL;
	} else if (rinfo->prefix_len > 128) {
		return -EINVAL;
	} else if (rinfo->prefix_len > 64) {
		if (rinfo->length < 2) {
			return -EINVAL;
		}
	} else if (rinfo->prefix_len > 0) {
		if (rinfo->length < 1) {
			return -EINVAL;
		}
	}

	pref = rinfo->route_pref;
	if (pref == ICMPV6_ROUTER_PREF_INVALID)
		pref = ICMPV6_ROUTER_PREF_MEDIUM;

	lifetime = ntohl(rinfo->lifetime);
	if (lifetime == 0xffffffff) {
		/* infinity */
	} else if (lifetime > 0x7fffffff/HZ) {
		/* Avoid arithmetic overflow */
		lifetime = 0x7fffffff/HZ - 1;
	}

	if (rinfo->length == 3)
		prefix = (struct in6_addr *)rinfo->prefix;
	else {
		/* this function is safe */
		ipv6_addr_prefix(&prefix_buf,
				 (struct in6_addr *)rinfo->prefix,
				 rinfo->prefix_len);
		prefix = &prefix_buf;
	}

	rt = rt6_get_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex);

	if (rt && !lifetime) {
		ip6_del_rt(rt);
		rt = NULL;
	}

	if (!rt && lifetime)
		rt = rt6_add_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
					pref);
	else if (rt)
		rt->rt6i_flags = RTF_ROUTEINFO |
				 (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);

	if (rt) {
		if (lifetime == 0xffffffff) {
			rt->rt6i_flags &= ~RTF_EXPIRES;
		} else {
			rt->rt6i_expires = jiffies + HZ * lifetime;
			rt->rt6i_flags |= RTF_EXPIRES;
		}
		dst_release(&rt->u.dst);
	}
	return 0;
}
#endif

#define BACKTRACK(saddr) \
do { \
	if (rt == &ip6_null_entry) { \
		struct fib6_node *pn; \
		while (1) { \
			if (fn->fn_flags & RTN_TL_ROOT) \
				goto out; \
			pn = fn->parent; \
			if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) \
				fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); \
			else \
				fn = pn; \
			if (fn->fn_flags & RTN_RTINFO) \
				goto restart; \
		} \
	} \
} while(0)

static struct rt6_info *ip6_pol_route_lookup(struct fib6_table *table,
					     struct flowi *fl, int flags)
{
	struct fib6_node *fn;
	struct rt6_info *rt;

	read_lock_bh(&table->tb6_lock);
	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
	rt = fn->leaf;
	rt = rt6_device_match(rt, fl->oif, flags);
	BACKTRACK(&fl->fl6_src);
out:
	dst_use(&rt->u.dst, jiffies);
	read_unlock_bh(&table->tb6_lock);
	return rt;

}

struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr,
			    int oif, int strict)
{
	struct flowi fl = {
		.oif = oif,
		.nl_u = {
			.ip6_u = {
				.daddr = *daddr,
			},
		},
	};
	struct dst_entry *dst;
	int flags = strict ? RT6_LOOKUP_F_IFACE : 0;

	if (saddr) {
		memcpy(&fl.fl6_src, saddr, sizeof(*saddr));
		flags |= RT6_LOOKUP_F_HAS_SADDR;
	}

	dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup);
	if (dst->error == 0)
		return (struct rt6_info *) dst;

	dst_release(dst);

	return NULL;
}

EXPORT_SYMBOL(rt6_lookup);

/* ip6_ins_rt is called with FREE table->tb6_lock.
   It takes new route entry, the addition fails by any reason the
   route is freed. In any case, if caller does not hold it, it may
   be destroyed.
 */

static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info)
{
	int err;
	struct fib6_table *table;

	table = rt->rt6i_table;
	write_lock_bh(&table->tb6_lock);
	err = fib6_add(&table->tb6_root, rt, info);
	write_unlock_bh(&table->tb6_lock);

	return err;
}

int ip6_ins_rt(struct rt6_info *rt)
{
	return __ip6_ins_rt(rt, NULL);
}

static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr,
				      struct in6_addr *saddr)
{
	struct rt6_info *rt;

	/*
	 *	Clone the route.
	 */

	rt = ip6_rt_copy(ort);

	if (rt) {
		if (!(rt->rt6i_flags&RTF_GATEWAY)) {
			if (rt->rt6i_dst.plen != 128 &&
			    ipv6_addr_equal(&rt->rt6i_dst.addr, daddr))