route.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.
 *
 *		ROUTE - implementation of the IP router.
 *
 * Version:	$Id: route.c,v 1.103 2002/01/12 07:44:09 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[e-mail]>
 *		Alan Cox, <[e-mail]>
 *		Linus Torvalds, <[e-mail]>
 *		Alexey Kuznetsov, <[e-mail]>
 *
 * Fixes:
 *		Alan Cox	:	Verify area fixes.
 *		Alan Cox	:	cli() protects routing changes
 *		Rui Oliveira	:	ICMP routing table updates
 *		([e-mail])	Routing table insertion and update
 *		Linus Torvalds	:	Rewrote bits to be sensible
 *		Alan Cox	:	Added BSD route gw semantics
 *		Alan Cox	:	Super /proc >4K
 *		Alan Cox	:	MTU in route table
 *		Alan Cox	: 	MSS actually. Also added the window
 *					clamper.
 *		Sam Lantinga	:	Fixed route matching in rt_del()
 *		Alan Cox	:	Routing cache support.
 *		Alan Cox	:	Removed compatibility cruft.
 *		Alan Cox	:	RTF_REJECT support.
 *		Alan Cox	:	TCP irtt support.
 *		Jonathan Naylor	:	Added Metric support.
 *	Miquel van Smoorenburg	:	BSD API fixes.
 *	Miquel van Smoorenburg	:	Metrics.
 *		Alan Cox	:	Use __u32 properly
 *		Alan Cox	:	Aligned routing errors more closely with BSD
 *					our system is still very different.
 *		Alan Cox	:	Faster /proc handling
 *	Alexey Kuznetsov	:	Massive rework to support tree based routing,
 *					routing caches and better behaviour.
 *
 *		Olaf Erb	:	irtt wasn't being copied right.
 *		Bjorn Ekwall	:	Kerneld route support.
 *		Alan Cox	:	Multicast fixed (I hope)
 * 		Pavel Krauz	:	Limited broadcast fixed
 *		Mike McLagan	:	Routing by source
 *	Alexey Kuznetsov	:	End of old history. Split to fib.c and
 *					route.c and rewritten from scratch.
 *		Andi Kleen	:	Load-limit warning messages.
 *	Vitaly E. Lavrov	:	Transparent proxy revived after year coma.
 *	Vitaly E. Lavrov	:	Race condition in ip_route_input_slow.
 *	Tobias Ringstrom	:	Uninitialized res.type in ip_route_output_slow.
 *	Vladimir V. Ivanov	:	IP rule info (flowid) is really useful.
 *		Marc Boucher	:	routing by fwmark
 *	Robert Olsson		:	Added rt_cache statistics
 *	Arnaldo C. Melo		:	Convert proc stuff to seq_file
 *	Eric Dumazet		:	hashed spinlocks and rt_check_expire() fixes.
 * 	Ilia Sotnikov		:	Ignore TOS on PMTUD and Redirect
 * 	Ilia Sotnikov		:	Removed TOS from hash calculations
 *
 *		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/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/bootmem.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/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
#include <linux/workqueue.h>
#include <linux/skbuff.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/pkt_sched.h>
#include <linux/mroute.h>
#include <linux/netfilter_ipv4.h>
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/rcupdate.h>
#include <linux/times.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/inetpeer.h>
#include <net/sock.h>
#include <net/ip_fib.h>
#include <net/arp.h>
#include <net/tcp.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/netevent.h>
#include <net/rtnetlink.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

#define RT_FL_TOS(oldflp) \
    ((u32)(oldflp->fl4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))

#define IP_MAX_MTU	0xFFF0

#define RT_GC_TIMEOUT (300*HZ)

static int ip_rt_min_delay		= 2 * HZ;
static int ip_rt_max_delay		= 10 * HZ;
static int ip_rt_max_size;
static int ip_rt_gc_timeout		= RT_GC_TIMEOUT;
static int ip_rt_gc_interval		= 60 * HZ;
static int ip_rt_gc_min_interval	= HZ / 2;
static int ip_rt_redirect_number	= 9;
static int ip_rt_redirect_load		= HZ / 50;
static int ip_rt_redirect_silence	= ((HZ / 50) << (9 + 1));
static int ip_rt_error_cost		= HZ;
static int ip_rt_error_burst		= 5 * HZ;
static int ip_rt_gc_elasticity		= 8;
static int ip_rt_mtu_expires		= 10 * 60 * HZ;
static int ip_rt_min_pmtu		= 512 + 20 + 20;
static int ip_rt_min_advmss		= 256;
static int ip_rt_secret_interval	= 10 * 60 * HZ;
static unsigned long rt_deadline;

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

static struct timer_list rt_flush_timer;
static void rt_check_expire(struct work_struct *work);
static DECLARE_DELAYED_WORK(expires_work, rt_check_expire);
static struct timer_list rt_secret_timer;

/*
 *	Interface to generic destination cache.
 */

static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
static void		 ipv4_dst_destroy(struct dst_entry *dst);
static void		 ipv4_dst_ifdown(struct dst_entry *dst,
					 struct net_device *dev, int how);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void		 ipv4_link_failure(struct sk_buff *skb);
static void		 ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
static int rt_garbage_collect(void);


static struct dst_ops ipv4_dst_ops = {
	.family =		AF_INET,
	.protocol =		__constant_htons(ETH_P_IP),
	.gc =			rt_garbage_collect,
	.check =		ipv4_dst_check,
	.destroy =		ipv4_dst_destroy,
	.ifdown =		ipv4_dst_ifdown,
	.negative_advice =	ipv4_negative_advice,
	.link_failure =		ipv4_link_failure,
	.update_pmtu =		ip_rt_update_pmtu,
	.entry_size =		sizeof(struct rtable),
};

#define ECN_OR_COST(class)	TC_PRIO_##class

const __u8 ip_tos2prio[16] = {
	TC_PRIO_BESTEFFORT,
	ECN_OR_COST(FILLER),
	TC_PRIO_BESTEFFORT,
	ECN_OR_COST(BESTEFFORT),
	TC_PRIO_BULK,
	ECN_OR_COST(BULK),
	TC_PRIO_BULK,
	ECN_OR_COST(BULK),
	TC_PRIO_INTERACTIVE,
	ECN_OR_COST(INTERACTIVE),
	TC_PRIO_INTERACTIVE,
	ECN_OR_COST(INTERACTIVE),
	TC_PRIO_INTERACTIVE_BULK,
	ECN_OR_COST(INTERACTIVE_BULK),
	TC_PRIO_INTERACTIVE_BULK,
	ECN_OR_COST(INTERACTIVE_BULK)
};


/*
 * Route cache.
 */

/* The locking scheme is rather straight forward:
 *
 * 1) Read-Copy Update protects the buckets of the central route hash.
 * 2) Only writers remove entries, and they hold the lock
 *    as they look at rtable reference counts.
 * 3) Only readers acquire references to rtable entries,
 *    they do so with atomic increments and with the
 *    lock held.
 */

struct rt_hash_bucket {
	struct rtable	*chain;
};
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
	defined(CONFIG_PROVE_LOCKING)
/*
 * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
 * The size of this table is a power of two and depends on the number of CPUS.
 * (on lockdep we have a quite big spinlock_t, so keep the size down there)
 */
#ifdef CONFIG_LOCKDEP
# define RT_HASH_LOCK_SZ	256
#else
# if NR_CPUS >= 32
#  define RT_HASH_LOCK_SZ	4096
# elif NR_CPUS >= 16
#  define RT_HASH_LOCK_SZ	2048
# elif NR_CPUS >= 8
#  define RT_HASH_LOCK_SZ	1024
# elif NR_CPUS >= 4
#  define RT_HASH_LOCK_SZ	512
# else
#  define RT_HASH_LOCK_SZ	256
# endif
#endif

static spinlock_t	*rt_hash_locks;
# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)]
# define rt_hash_lock_init()	{ \
		int i; \
		rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ, GFP_KERNEL); \
		if (!rt_hash_locks) panic("IP: failed to allocate rt_hash_locks\n"); \
		for (i = 0; i < RT_HASH_LOCK_SZ; i++) \
			spin_lock_init(&rt_hash_locks[i]); \
		}
#else
# define rt_hash_lock_addr(slot) NULL
# define rt_hash_lock_init()
#endif

static struct rt_hash_bucket 	*rt_hash_table;
static unsigned			rt_hash_mask;
static unsigned int		rt_hash_log;
static unsigned int		rt_hash_rnd;

static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
#define RT_CACHE_STAT_INC(field) \
	(__raw_get_cpu_var(rt_cache_stat).field++)

static int rt_intern_hash(unsigned hash, struct rtable *rth,
				struct rtable **res);

static unsigned int rt_hash_code(u32 daddr, u32 saddr)
{
	return (jhash_2words(daddr, saddr, rt_hash_rnd)
		& rt_hash_mask);
}

#define rt_hash(daddr, saddr, idx) \
	rt_hash_code((__force u32)(__be32)(daddr),\
		     (__force u32)(__be32)(saddr) ^ ((idx) << 5))

#ifdef CONFIG_PROC_FS
struct rt_cache_iter_state {
	int bucket;
};

static struct rtable *rt_cache_get_first(struct seq_file *seq)
{
	struct rtable *r = NULL;
	struct rt_cache_iter_state *st = seq->private;

	for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {
		rcu_read_lock_bh();
		r = rt_hash_table[st->bucket].chain;
		if (r)
			break;
		rcu_read_unlock_bh();
	}
	return rcu_dereference(r);
}

static struct rtable *rt_cache_get_next(struct seq_file *seq, struct rtable *r)
{
	struct rt_cache_iter_state *st = seq->private;

	r = r->u.dst.rt_next;
	while (!r) {
		rcu_read_unlock_bh();
		if (--st->bucket < 0)
			break;
		rcu_read_lock_bh();
		r = rt_hash_table[st->bucket].chain;
	}
	return rcu_dereference(r);
}

static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
{
	struct rtable *r = rt_cache_get_first(seq);

	if (r)
		while (pos && (r = rt_cache_get_next(seq, r)))
			--pos;
	return pos ? NULL : r;
}

static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
	return *pos ? rt_cache_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}

static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct rtable *r = NULL;

	if (v == SEQ_START_TOKEN)
		r = rt_cache_get_first(seq);
	else
		r = rt_cache_get_next(seq, v);
	++*pos;
	return r;
}

static void rt_cache_seq_stop(struct seq_file *seq, void *v)
{
	if (v && v != SEQ_START_TOKEN)
		rcu_read_unlock_bh();
}

static int rt_cache_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_printf(seq, "%-127s\n",
			   "Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t"
			   "Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t"
			   "HHUptod\tSpecDst");
	else {
		struct rtable *r = v;
		char temp[256];

		sprintf(temp, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t"
			      "%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X",
			r->u.dst.dev ? r->u.dst.dev->name : "*",
			(unsigned long)r->rt_dst, (unsigned long)r->rt_gateway,
			r->rt_flags, atomic_read(&r->u.dst.__refcnt),
			r->u.dst.__use, 0, (unsigned long)r->rt_src,
			(dst_metric(&r->u.dst, RTAX_ADVMSS) ?
			     (int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0),
			dst_metric(&r->u.dst, RTAX_WINDOW),
			(int)((dst_metric(&r->u.dst, RTAX_RTT) >> 3) +
			      dst_metric(&r->u.dst, RTAX_RTTVAR)),
			r->fl.fl4_tos,
			r->u.dst.hh ? atomic_read(&r->u.dst.hh->hh_refcnt) : -1,
			r->u.dst.hh ? (r->u.dst.hh->hh_output ==
				       dev_queue_xmit) : 0,
			r->rt_spec_dst);
		seq_printf(seq, "%-127s\n", temp);
	}
	return 0;
}

static const struct seq_operations rt_cache_seq_ops = {
	.start  = rt_cache_seq_start,
	.next   = rt_cache_seq_next,
	.stop   = rt_cache_seq_stop,
	.show   = rt_cache_seq_show,
};

static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
	return seq_open_private(file, &rt_cache_seq_ops,
			sizeof(struct rt_cache_iter_state));
}

static const struct file_operations rt_cache_seq_fops = {
	.owner	 = THIS_MODULE,
	.open	 = rt_cache_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release_private,
};


static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos)
{
	int cpu;

	if (*pos == 0)
		return SEQ_START_TOKEN;

	for (cpu = *pos-1; cpu < NR_CPUS; ++cpu) {
		if (!cpu_possible(cpu))
			continue;
		*pos = cpu+1;
		return &per_cpu(rt_cache_stat, cpu);
	}
	return NULL;
}

static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	int cpu;

	for (cpu = *pos; cpu < NR_CPUS; ++cpu) {
		if (!cpu_possible(cpu))
			continue;
		*pos = cpu+1;
		return &per_cpu(rt_cache_stat, cpu);
	}
	return NULL;

}

static void rt_cpu_seq_stop(struct seq_file *seq, void *v)
{

}

static int rt_cpu_seq_show(struct seq_file *seq, void *v)
{
	struct rt_cache_stat *st = v;

	if (v == SEQ_START_TOKEN) {
		seq_printf(seq, "entries  in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src  out_hit out_slow_tot out_slow_mc  gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n");
		return 0;
	}

	seq_printf(seq,"%08x  %08x %08x %08x %08x %08x %08x %08x "
		   " %08x %08x %08x %08x %08x %08x %08x %08x %08x \n",
		   atomic_read(&ipv4_dst_ops.entries),
		   st->in_hit,
		   st->in_slow_tot,
		   st->in_slow_mc,
		   st->in_no_route,
		   st->in_brd,
		   st->in_martian_dst,
		   st->in_martian_src,

		   st->out_hit,
		   st->out_slow_tot,
		   st->out_slow_mc,

		   st->gc_total,
		   st->gc_ignored,
		   st->gc_goal_miss,
		   st->gc_dst_overflow,
		   st->in_hlist_search,
		   st->out_hlist_search
		);
	return 0;
}

static const struct seq_operations rt_cpu_seq_ops = {
	.start  = rt_cpu_seq_start,
	.next   = rt_cpu_seq_next,
	.stop   = rt_cpu_seq_stop,
	.show   = rt_cpu_seq_show,
};


static int rt_cpu_seq_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &rt_cpu_seq_ops);
}

static const struct file_operations rt_cpu_seq_fops = {
	.owner	 = THIS_MODULE,
	.open	 = rt_cpu_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release,
};

#endif /* CONFIG_PROC_FS */

static __inline__ void rt_free(struct rtable *rt)
{
	call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
}

static __inline__ void rt_drop(struct rtable *rt)
{
	ip_rt_put(rt);
	call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
}

static __inline__ int rt_fast_clean(struct rtable *rth)
{
	/* Kill broadcast/multicast entries very aggresively, if they
	   collide in hash table with more useful entries */
	return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) &&
		rth->fl.iif && rth->u.dst.rt_next;
}

static __inline__ int rt_valuable(struct rtable *rth)
{
	return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
		rth->u.dst.expires;
}

static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
{
	unsigned long age;
	int ret = 0;

	if (atomic_read(&rth->u.dst.__refcnt))
		goto out;

	ret = 1;
	if (rth->u.dst.expires &&
	    time_after_eq(jiffies, rth->u.dst.expires))
		goto out;