/*
   * 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.
   *

   * Authors:	Ross Biro

   *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
   *		Alan Cox, <gw4pts@gw4pts.ampr.org>
   *		Linus Torvalds, <Linus.Torvalds@helsinki.fi>
   *		Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
   *
   * Fixes:
   *		Alan Cox	:	Verify area fixes.
   *		Alan Cox	:	cli() protects routing changes
   *		Rui Oliveira	:	ICMP routing table updates
   *		(rco@di.uminho.pt)	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 <linux/slab.h>

  #include <net/dst.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_max_size;

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

  static int rt_chain_length_max __read_mostly	= 20;

  static struct delayed_work expires_work;
  static unsigned long expires_ljiffies;

  
  /*
   *	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(struct dst_ops *ops);

  
  
  static struct dst_ops ipv4_dst_ops = {
  	.family =		AF_INET,

  	.protocol =		cpu_to_be16(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,

  	.local_out =		__ip_local_out,

  	.entries =		ATOMIC_INIT(0),

  };
  
  #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)]

  
  static __init void rt_hash_lock_init(void)
  {
  	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
  ");
  
  	for (i = 0; i < RT_HASH_LOCK_SZ; i++)
  		spin_lock_init(&rt_hash_locks[i]);
  }

  #else
  # define rt_hash_lock_addr(slot) NULL

  
  static inline void rt_hash_lock_init(void)
  {
  }

  #endif

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

  static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);

  #define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)

  static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,

  				   int genid)

  {

  	return jhash_3words((__force u32)daddr, (__force u32)saddr,

  			    idx, genid)

  		& rt_hash_mask;

  }

  static inline int rt_genid(struct net *net)
  {
  	return atomic_read(&net->ipv4.rt_genid);
  }

  #ifdef CONFIG_PROC_FS
  struct rt_cache_iter_state {

  	struct seq_net_private p;

  	int bucket;

  	int genid;

  };

  static struct rtable *rt_cache_get_first(struct seq_file *seq)

  {

  	struct rt_cache_iter_state *st = seq->private;

  	struct rtable *r = NULL;

  
  	for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {

  		if (!rt_hash_table[st->bucket].chain)
  			continue;

  		rcu_read_lock_bh();

  		r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);

  		while (r) {

  			if (dev_net(r->dst.dev) == seq_file_net(seq) &&

  			    r->rt_genid == st->genid)

  				return r;

  			r = rcu_dereference_bh(r->dst.rt_next);

  		}

  		rcu_read_unlock_bh();
  	}

  	return 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->dst.rt_next;

  	while (!r) {
  		rcu_read_unlock_bh();

  		do {
  			if (--st->bucket < 0)
  				return NULL;
  		} while (!rt_hash_table[st->bucket].chain);

  		rcu_read_lock_bh();
  		r = rt_hash_table[st->bucket].chain;
  	}

  	return rcu_dereference_bh(r);

  }

  static struct rtable *rt_cache_get_next(struct seq_file *seq,

  					struct rtable *r)
  {

  	struct rt_cache_iter_state *st = seq->private;
  	while ((r = __rt_cache_get_next(seq, r)) != NULL) {

  		if (dev_net(r->dst.dev) != seq_file_net(seq))

  			continue;

  		if (r->rt_genid == st->genid)
  			break;
  	}
  	return 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)
  {

  	struct rt_cache_iter_state *st = seq->private;

  	if (*pos)

  		return rt_cache_get_idx(seq, *pos - 1);

  	st->genid = rt_genid(seq_file_net(seq));

  	return SEQ_START_TOKEN;

  }
  
  static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
  {

  	struct rtable *r;

  
  	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
  ",
  			   "Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t"
  			   "Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t"
  			   "HHUptod\tSpecDst");
  	else {
  		struct rtable *r = v;

  		int len;

  		seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
  			      "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",

  			r->dst.dev ? r->dst.dev->name : "*",

  			(__force u32)r->rt_dst,
  			(__force u32)r->rt_gateway,

  			r->rt_flags, atomic_read(&r->dst.__refcnt),
  			r->dst.__use, 0, (__force u32)r->rt_src,
  			(dst_metric(&r->dst, RTAX_ADVMSS) ?
  			     (int)dst_metric(&r->dst, RTAX_ADVMSS) + 40 : 0),
  			dst_metric(&r->dst, RTAX_WINDOW),
  			(int)((dst_metric(&r->dst, RTAX_RTT) >> 3) +
  			      dst_metric(&r->dst, RTAX_RTTVAR)),

  			r->fl.fl4_tos,

  			r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1,
  			r->dst.hh ? (r->dst.hh->hh_output ==

  				       dev_queue_xmit) : 0,

  			r->rt_spec_dst, &len);
  
  		seq_printf(seq, "%*s
  ", 127 - len, "");

  	}
  	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_net(inode, 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_net,

  };
  
  
  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_cpu_ids; ++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_cpu_ids; ++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
  ");

  		return 0;
  	}

  	seq_printf(seq,"%08x  %08x %08x %08x %08x %08x %08x %08x "
  		   " %08x %08x %08x %08x %08x %08x %08x %08x %08x 
  ",
  		   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,
  };

  #ifdef CONFIG_NET_CLS_ROUTE

  static int rt_acct_proc_show(struct seq_file *m, void *v)

  {

  	struct ip_rt_acct *dst, *src;
  	unsigned int i, j;
  
  	dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL);
  	if (!dst)
  		return -ENOMEM;
  
  	for_each_possible_cpu(i) {
  		src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i);
  		for (j = 0; j < 256; j++) {
  			dst[j].o_bytes   += src[j].o_bytes;
  			dst[j].o_packets += src[j].o_packets;
  			dst[j].i_bytes   += src[j].i_bytes;
  			dst[j].i_packets += src[j].i_packets;
  		}

  	}

  	seq_write(m, dst, 256 * sizeof(struct ip_rt_acct));
  	kfree(dst);
  	return 0;
  }

  static int rt_acct_proc_open(struct inode *inode, struct file *file)
  {
  	return single_open(file, rt_acct_proc_show, NULL);

  }

  
  static const struct file_operations rt_acct_proc_fops = {
  	.owner		= THIS_MODULE,
  	.open		= rt_acct_proc_open,
  	.read		= seq_read,
  	.llseek		= seq_lseek,
  	.release	= single_release,
  };

  #endif

  static int __net_init ip_rt_do_proc_init(struct net *net)

  {
  	struct proc_dir_entry *pde;
  
  	pde = proc_net_fops_create(net, "rt_cache", S_IRUGO,
  			&rt_cache_seq_fops);
  	if (!pde)
  		goto err1;

  	pde = proc_create("rt_cache", S_IRUGO,
  			  net->proc_net_stat, &rt_cpu_seq_fops);

  	if (!pde)
  		goto err2;

  #ifdef CONFIG_NET_CLS_ROUTE

  	pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);

  	if (!pde)
  		goto err3;
  #endif
  	return 0;
  
  #ifdef CONFIG_NET_CLS_ROUTE
  err3:
  	remove_proc_entry("rt_cache", net->proc_net_stat);
  #endif
  err2:
  	remove_proc_entry("rt_cache", net->proc_net);
  err1:
  	return -ENOMEM;
  }

  
  static void __net_exit ip_rt_do_proc_exit(struct net *net)
  {
  	remove_proc_entry("rt_cache", net->proc_net_stat);
  	remove_proc_entry("rt_cache", net->proc_net);

  #ifdef CONFIG_NET_CLS_ROUTE

  	remove_proc_entry("rt_acct", net->proc_net);

  #endif

  }
  
  static struct pernet_operations ip_rt_proc_ops __net_initdata =  {
  	.init = ip_rt_do_proc_init,
  	.exit = ip_rt_do_proc_exit,
  };
  
  static int __init ip_rt_proc_init(void)
  {
  	return register_pernet_subsys(&ip_rt_proc_ops);
  }

  #else

  static inline int ip_rt_proc_init(void)

  {
  	return 0;
  }

  #endif /* CONFIG_PROC_FS */

  static inline void rt_free(struct rtable *rt)

  {

  	call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);

  }

  static inline void rt_drop(struct rtable *rt)

  {

  	ip_rt_put(rt);

  	call_rcu_bh(&rt->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->dst.rt_next;

  }

  static inline int rt_valuable(struct rtable *rth)

  {
  	return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||

  		rth->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->dst.__refcnt))

  		goto out;
  
  	ret = 1;

  	if (rth->dst.expires &&
  	    time_after_eq(jiffies, rth->dst.expires))

  		goto out;

  	age = jiffies - rth->dst.lastuse;

  	ret = 0;
  	if ((age <= tmo1 && !rt_fast_clean(rth)) ||
  	    (age <= tmo2 && rt_valuable(rth)))
  		goto out;
  	ret = 1;
  out:	return ret;
  }
  
  /* Bits of score are:
   * 31: very valuable
   * 30: not quite useless
   * 29..0: usage counter
   */
  static inline u32 rt_score(struct rtable *rt)
  {

  	u32 score = jiffies - rt->dst.lastuse;

  
  	score = ~score & ~(3<<30);
  
  	if (rt_valuable(rt))
  		score |= (1<<31);
  
  	if (!rt->fl.iif ||
  	    !(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL)))
  		score |= (1<<30);
  
  	return score;
  }

  static inline bool rt_caching(const struct net *net)
  {
  	return net->ipv4.current_rt_cache_rebuild_count <=
  		net->ipv4.sysctl_rt_cache_rebuild_count;
  }
  
  static inline bool compare_hash_inputs(const struct flowi *fl1,
  					const struct flowi *fl2)
  {

  	return ((((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
  		((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |

  		(fl1->iif ^ fl2->iif)) == 0);
  }

  static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
  {

  	return (((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
  		((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |

  		(fl1->mark ^ fl2->mark) |

  		(*(u16 *)&fl1->nl_u.ip4_u.tos ^ *(u16 *)&fl2->nl_u.ip4_u.tos) |

  		(fl1->oif ^ fl2->oif) |
  		(fl1->iif ^ fl2->iif)) == 0;

  }

  static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
  {

  	return net_eq(dev_net(rt1->dst.dev), dev_net(rt2->dst.dev));

  }

  static inline int rt_is_expired(struct rtable *rth)
  {

  	return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));

  }

  /*
   * Perform a full scan of hash table and free all entries.
   * Can be called by a softirq or a process.
   * In the later case, we want to be reschedule if necessary
   */
  static void rt_do_flush(int process_context)
  {
  	unsigned int i;
  	struct rtable *rth, *next;

  	struct rtable * tail;

  
  	for (i = 0; i <= rt_hash_mask; i++) {
  		if (process_context && need_resched())
  			cond_resched();
  		rth = rt_hash_table[i].chain;
  		if (!rth)
  			continue;
  
  		spin_lock_bh(rt_hash_lock_addr(i));

  #ifdef CONFIG_NET_NS
  		{
  		struct rtable ** prev, * p;
  
  		rth = rt_hash_table[i].chain;
  
  		/* defer releasing the head of the list after spin_unlock */

  		for (tail = rth; tail; tail = tail->dst.rt_next)

  			if (!rt_is_expired(tail))
  				break;
  		if (rth != tail)
  			rt_hash_table[i].chain = tail;
  
  		/* call rt_free on entries after the tail requiring flush */
  		prev = &rt_hash_table[i].chain;
  		for (p = *prev; p; p = next) {

  			next = p->dst.rt_next;

  			if (!rt_is_expired(p)) {

  				prev = &p->dst.rt_next;

  			} else {
  				*prev = next;
  				rt_free(p);
  			}
  		}
  		}
  #else

  		rth = rt_hash_table[i].chain;
  		rt_hash_table[i].chain = NULL;

  		tail = NULL;
  #endif

  		spin_unlock_bh(rt_hash_lock_addr(i));

  		for (; rth != tail; rth = next) {

  			next = rth->dst.rt_next;

  			rt_free(rth);
  		}
  	}
  }

  /*
   * While freeing expired entries, we compute average chain length
   * and standard deviation, using fixed-point arithmetic.
   * This to have an estimation of rt_chain_length_max
   *  rt_chain_length_max = max(elasticity, AVG + 4*SD)
   * We use 3 bits for frational part, and 29 (or 61) for magnitude.
   */
  
  #define FRACT_BITS 3
  #define ONE (1UL << FRACT_BITS)

  /*
   * Given a hash chain and an item in this hash chain,
   * find if a previous entry has the same hash_inputs
   * (but differs on tos, mark or oif)
   * Returns 0 if an alias is found.
   * Returns ONE if rth has no alias before itself.
   */
  static int has_noalias(const struct rtable *head, const struct rtable *rth)
  {
  	const struct rtable *aux = head;
  
  	while (aux != rth) {
  		if (compare_hash_inputs(&aux->fl, &rth->fl))
  			return 0;

  		aux = aux->dst.rt_next;

  	}
  	return ONE;
  }

  static void rt_check_expire(void)

  {

  	static unsigned int rover;
  	unsigned int i = rover, goal;

  	struct rtable *rth, **rthp;

  	unsigned long samples = 0;

  	unsigned long sum = 0, sum2 = 0;

  	unsigned long delta;

  	u64 mult;

  	delta = jiffies - expires_ljiffies;
  	expires_ljiffies = jiffies;
  	mult = ((u64)delta) << rt_hash_log;

  	if (ip_rt_gc_timeout > 1)
  		do_div(mult, ip_rt_gc_timeout);
  	goal = (unsigned int)mult;

  	if (goal > rt_hash_mask)
  		goal = rt_hash_mask + 1;

  	for (; goal > 0; goal--) {

  		unsigned long tmo = ip_rt_gc_timeout;

  		unsigned long length;

  
  		i = (i + 1) & rt_hash_mask;
  		rthp = &rt_hash_table[i].chain;

  		if (need_resched())
  			cond_resched();

  		samples++;

  		if (*rthp == NULL)

  			continue;

  		length = 0;

  		spin_lock_bh(rt_hash_lock_addr(i));

  		while ((rth = *rthp) != NULL) {

  			prefetch(rth->dst.rt_next);

  			if (rt_is_expired(rth)) {

  				*rthp = rth->dst.rt_next;

  				rt_free(rth);
  				continue;
  			}

  			if (rth->dst.expires) {

  				/* Entry is expired even if it is in use */

  				if (time_before_eq(jiffies, rth->dst.expires)) {

  nofree:

  					tmo >>= 1;

  					rthp = &rth->dst.rt_next;

  					/*

  					 * We only count entries on

  					 * a chain with equal hash inputs once
  					 * so that entries for different QOS
  					 * levels, and other non-hash input
  					 * attributes don't unfairly skew
  					 * the length computation
  					 */

  					length += has_noalias(rt_hash_table[i].chain, rth);

  					continue;
  				}

  			} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
  				goto nofree;

  
  			/* Cleanup aged off entries. */

  			*rthp = rth->dst.rt_next;

  			rt_free(rth);

  		}

  		spin_unlock_bh(rt_hash_lock_addr(i));

  		sum += length;
  		sum2 += length*length;
  	}
  	if (samples) {
  		unsigned long avg = sum / samples;
  		unsigned long sd = int_sqrt(sum2 / samples - avg*avg);
  		rt_chain_length_max = max_t(unsigned long,
  					ip_rt_gc_elasticity,
  					(avg + 4*sd) >> FRACT_BITS);

  	}
  	rover = i;

  }
  
  /*
   * rt_worker_func() is run in process context.

   * we call rt_check_expire() to scan part of the hash table

   */
  static void rt_worker_func(struct work_struct *work)
  {

  	rt_check_expire();

  	schedule_delayed_work(&expires_work, ip_rt_gc_interval);

  }

  /*
   * Pertubation of rt_genid by a small quantity [1..256]
   * Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
   * many times (2^24) without giving recent rt_genid.
   * Jenkins hash is strong enough that litle changes of rt_genid are OK.

   */

  static void rt_cache_invalidate(struct net *net)

  {

  	unsigned char shuffle;

  	get_random_bytes(&shuffle, sizeof(shuffle));

  	atomic_add(shuffle + 1U, &net->ipv4.rt_genid);

  }

  /*
   * delay < 0  : invalidate cache (fast : entries will be deleted later)
   * delay >= 0 : invalidate & flush cache (can be long)
   */

  void rt_cache_flush(struct net *net, int delay)

  {

  	rt_cache_invalidate(net);

  	if (delay >= 0)
  		rt_do_flush(!in_softirq());

  }

  /* Flush previous cache invalidated entries from the cache */
  void rt_cache_flush_batch(void)
  {
  	rt_do_flush(!in_softirq());
  }

  static void rt_emergency_hash_rebuild(struct net *net)
  {

  	if (net_ratelimit())

  		printk(KERN_WARNING "Route hash chain too long!
  ");

  	rt_cache_invalidate(net);

  }

  /*
     Short description of GC goals.
  
     We want to build algorithm, which will keep routing cache
     at some equilibrium point, when number of aged off entries
     is kept approximately equal to newly generated ones.
  
     Current expiration strength is variable "expire".
     We try to adjust it dynamically, so that if networking
     is idle expires is large enough to keep enough of warm entries,
     and when load increases it reduces to limit cache size.
   */

  static int rt_garbage_collect(struct dst_ops *ops)

  {
  	static unsigned long expire = RT_GC_TIMEOUT;
  	static unsigned long last_gc;
  	static int rover;
  	static int equilibrium;
  	struct rtable *rth, **rthp;
  	unsigned long now = jiffies;
  	int goal;
  
  	/*
  	 * Garbage collection is pretty expensive,
  	 * do not make it too frequently.
  	 */
  
  	RT_CACHE_STAT_INC(gc_total);
  
  	if (now - last_gc < ip_rt_gc_min_interval &&
  	    atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size) {
  		RT_CACHE_STAT_INC(gc_ignored);
  		goto out;
  	}
  
  	/* Calculate number of entries, which we want to expire now. */
  	goal = atomic_read(&ipv4_dst_ops.entries) -
  		(ip_rt_gc_elasticity << rt_hash_log);
  	if (goal <= 0) {
  		if (equilibrium < ipv4_dst_ops.gc_thresh)
  			equilibrium = ipv4_dst_ops.gc_thresh;
  		goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
  		if (goal > 0) {

  			equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1);

  			goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
  		}
  	} else {
  		/* We are in dangerous area. Try to reduce cache really
  		 * aggressively.
  		 */

  		goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1);

  		equilibrium = atomic_read(&ipv4_dst_ops.entries) - goal;
  	}
  
  	if (now - last_gc >= ip_rt_gc_min_interval)
  		last_gc = now;
  
  	if (goal <= 0) {
  		equilibrium += goal;
  		goto work_done;
  	}
  
  	do {
  		int i, k;
  
  		for (i = rt_hash_mask, k = rover; i >= 0; i--) {
  			unsigned long tmo = expire;
  
  			k = (k + 1) & rt_hash_mask;
  			rthp = &rt_hash_table[k].chain;

  			spin_lock_bh(rt_hash_lock_addr(k));

  			while ((rth = *rthp) != NULL) {

  				if (!rt_is_expired(rth) &&

  					!rt_may_expire(rth, tmo, expire)) {

  					tmo >>= 1;

  					rthp = &rth->dst.rt_next;

  					continue;
  				}

  				*rthp = rth->dst.rt_next;

  				rt_free(rth);
  				goal--;

  			}

  			spin_unlock_bh(rt_hash_lock_addr(k));

  			if (goal <= 0)
  				break;
  		}
  		rover = k;
  
  		if (goal <= 0)
  			goto work_done;
  
  		/* Goal is not achieved. We stop process if:
  
  		   - if expire reduced to zero. Otherwise, expire is halfed.
  		   - if table is not full.
  		   - if we are called from interrupt.
  		   - jiffies check is just fallback/debug loop breaker.
  		     We will not spin here for long time in any case.
  		 */
  
  		RT_CACHE_STAT_INC(gc_goal_miss);
  
  		if (expire == 0)
  			break;
  
  		expire >>= 1;
  #if RT_CACHE_DEBUG >= 2
  		printk(KERN_DEBUG "expire>> %u %d %d %d
  ", expire,
  				atomic_read(&ipv4_dst_ops.entries), goal, i);
  #endif
  
  		if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
  			goto out;
  	} while (!in_softirq() && time_before_eq(jiffies, now));
  
  	if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
  		goto out;
  	if (net_ratelimit())
  		printk(KERN_WARNING "dst cache overflow
  ");
  	RT_CACHE_STAT_INC(gc_dst_overflow);
  	return 1;
  
  work_done:
  	expire += ip_rt_gc_min_interval;
  	if (expire > ip_rt_gc_timeout ||
  	    atomic_read(&ipv4_dst_ops.entries) < ipv4_dst_ops.gc_thresh)
  		expire = ip_rt_gc_timeout;
  #if RT_CACHE_DEBUG >= 2
  	printk(KERN_DEBUG "expire++ %u %d %d %d
  ", expire,
  			atomic_read(&ipv4_dst_ops.entries), goal, rover);
  #endif
  out:	return 0;
  }

  /*
   * Returns number of entries in a hash chain that have different hash_inputs
   */
  static int slow_chain_length(const struct rtable *head)
  {
  	int length = 0;
  	const struct rtable *rth = head;
  
  	while (rth) {
  		length += has_noalias(head, rth);

  		rth = rth->dst.rt_next;

  	}
  	return length >> FRACT_BITS;
  }

  static int rt_intern_hash(unsigned hash, struct rtable *rt,

  			  struct rtable **rp, struct sk_buff *skb, int ifindex)

  {
  	struct rtable	*rth, **rthp;
  	unsigned long	now;
  	struct rtable *cand, **candp;
  	u32 		min_score;
  	int		chain_length;
  	int attempts = !in_softirq();
  
  restart:
  	chain_length = 0;
  	min_score = ~(u32)0;
  	cand = NULL;
  	candp = NULL;
  	now = jiffies;

  	if (!rt_caching(dev_net(rt->dst.dev))) {

  		/*
  		 * If we're not caching, just tell the caller we
  		 * were successful and don't touch the route.  The
  		 * caller hold the sole reference to the cache entry, and
  		 * it will be released when the caller is done with it.
  		 * If we drop it here, the callers have no way to resolve routes
  		 * when we're not caching.  Instead, just point *rp at rt, so
  		 * the caller gets a single use out of the route

  		 * Note that we do rt_free on this new route entry, so that
  		 * once its refcount hits zero, we are still able to reap it
  		 * (Thanks Alexey)
  		 * Note also the rt_free uses call_rcu.  We don't actually
  		 * need rcu protection here, this is just our path to get
  		 * on the route gc list.

  		 */

  
  		if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {

  			int err = arp_bind_neighbour(&rt->dst);

  			if (err) {
  				if (net_ratelimit())
  					printk(KERN_WARNING
  					    "Neighbour table failure & not caching routes.
  ");
  				rt_drop(rt);
  				return err;
  			}
  		}
  
  		rt_free(rt);
  		goto skip_hashing;

  	}

  	rthp = &rt_hash_table[hash].chain;

  	spin_lock_bh(rt_hash_lock_addr(hash));

  	while ((rth = *rthp) != NULL) {

  		if (rt_is_expired(rth)) {

  			*rthp = rth->dst.rt_next;

  			rt_free(rth);
  			continue;
  		}

  		if (compare_keys(&rth->fl, &rt->fl) && compare_netns(rth, rt)) {

  			/* Put it first */

  			*rthp = rth->dst.rt_next;

  			/*
  			 * Since lookup is lockfree, the deletion
  			 * must be visible to another weakly ordered CPU before
  			 * the insertion at the start of the hash chain.
  			 */

  			rcu_assign_pointer(rth->dst.rt_next,

  					   rt_hash_table[hash].chain);
  			/*
  			 * Since lookup is lockfree, the update writes
  			 * must be ordered for consistency on SMP.
  			 */
  			rcu_assign_pointer(rt_hash_table[hash].chain, rth);

  			dst_use(&rth->dst, now);

  			spin_unlock_bh(rt_hash_lock_addr(hash));

  
  			rt_drop(rt);

  			if (rp)
  				*rp = rth;
  			else

  				skb_dst_set(skb, &rth->dst);

  			return 0;
  		}

  		if (!atomic_read(&rth->dst.__refcnt)) {

  			u32 score = rt_score(rth);
  
  			if (score <= min_score) {
  				cand = rth;
  				candp = rthp;
  				min_score = score;
  			}
  		}
  
  		chain_length++;

  		rthp = &rth->dst.rt_next;

  	}
  
  	if (cand) {
  		/* ip_rt_gc_elasticity used to be average length of chain
  		 * length, when exceeded gc becomes really aggressive.
  		 *
  		 * The second limit is less certain. At the moment it allows
  		 * only 2 entries per bucket. We will see.
  		 */
  		if (chain_length > ip_rt_gc_elasticity) {

  			*candp = cand->dst.rt_next;

  			rt_free(cand);
  		}

  	} else {

  		if (chain_length > rt_chain_length_max &&
  		    slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) {

  			struct net *net = dev_net(rt->dst.dev);

  			int num = ++net->ipv4.current_rt_cache_rebuild_count;

  			if (!rt_caching(net)) {

  				printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled
  ",

  					rt->dst.dev->name, num);

  			}

  			rt_emergency_hash_rebuild(net);

  			spin_unlock_bh(rt_hash_lock_addr(hash));
  
  			hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
  					ifindex, rt_genid(net));
  			goto restart;

  		}

  	}
  
  	/* Try to bind route to arp only if it is output
  	   route or unicast forwarding path.
  	 */
  	if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {

  		int err = arp_bind_neighbour(&rt->dst);

  		if (err) {

  			spin_unlock_bh(rt_hash_lock_addr(hash));

  
  			if (err != -ENOBUFS) {
  				rt_drop(rt);
  				return err;
  			}
  
  			/* Neighbour tables are full and nothing
  			   can be released. Try to shrink route cache,
  			   it is most likely it holds some neighbour records.
  			 */
  			if (attempts-- > 0) {
  				int saved_elasticity = ip_rt_gc_elasticity;
  				int saved_int = ip_rt_gc_min_interval;
  				ip_rt_gc_elasticity	= 1;
  				ip_rt_gc_min_interval	= 0;

  				rt_garbage_collect(&ipv4_dst_ops);

  				ip_rt_gc_min_interval	= saved_int;
  				ip_rt_gc_elasticity	= saved_elasticity;
  				goto restart;
  			}
  
  			if (net_ratelimit())
  				printk(KERN_WARNING "Neighbour table overflow.
  ");
  			rt_drop(rt);
  			return -ENOBUFS;
  		}
  	}

  	rt->dst.rt_next = rt_hash_table[hash].chain;

  #if RT_CACHE_DEBUG >= 2

  	if (rt->dst.rt_next) {

  		struct rtable *trt;

  		printk(KERN_DEBUG "rt_cache @%02x: %pI4",
  		       hash, &rt->rt_dst);

  		for (trt = rt->dst.rt_next; trt; trt = trt->dst.rt_next)

  			printk(" . %pI4", &trt->rt_dst);

  		printk("
  ");
  	}
  #endif

  	/*
  	 * Since lookup is lockfree, we must make sure
  	 * previous writes to rt are comitted to memory
  	 * before making rt visible to other CPUS.
  	 */

  	rcu_assign_pointer(rt_hash_table[hash].chain, rt);

  	spin_unlock_bh(rt_hash_lock_addr(hash));

  skip_hashing:

  	if (rp)
  		*rp = rt;
  	else

  		skb_dst_set(skb, &rt->dst);

  	return 0;
  }
  
  void rt_bind_peer(struct rtable *rt, int create)
  {
  	static DEFINE_SPINLOCK(rt_peer_lock);
  	struct inet_peer *peer;
  
  	peer = inet_getpeer(rt->rt_dst, create);
  
  	spin_lock_bh(&rt_peer_lock);
  	if (rt->peer == NULL) {
  		rt->peer = peer;
  		peer = NULL;
  	}
  	spin_unlock_bh(&rt_peer_lock);
  	if (peer)
  		inet_putpeer(peer);
  }
  
  /*
   * Peer allocation may fail only in serious out-of-memory conditions.  However
   * we still can generate some output.
   * Random ID selection looks a bit dangerous because we have no chances to
   * select ID being unique in a reasonable period of time.
   * But broken packet identifier may be better than no packet at all.
   */
  static void ip_select_fb_ident(struct iphdr *iph)
  {
  	static DEFINE_SPINLOCK(ip_fb_id_lock);
  	static u32 ip_fallback_id;
  	u32 salt;
  
  	spin_lock_bh(&ip_fb_id_lock);

  	salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);

  	iph->id = htons(salt & 0xFFFF);
  	ip_fallback_id = salt;
  	spin_unlock_bh(&ip_fb_id_lock);
  }
  
  void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
  {
  	struct rtable *rt = (struct rtable *) dst;
  
  	if (rt) {
  		if (rt->peer == NULL)
  			rt_bind_peer(rt, 1);
  
  		/* If peer is attached to destination, it is never detached,
  		   so that we need not to grab a lock to dereference it.
  		 */
  		if (rt->peer) {
  			iph->id = htons(inet_getid(rt->peer, more));
  			return;
  		}
  	} else

  		printk(KERN_DEBUG "rt_bind_peer(0) @%p
  ",

  		       __builtin_return_address(0));

  
  	ip_select_fb_ident(iph);
  }

  EXPORT_SYMBOL(__ip_select_ident);

  
  static void rt_del(unsigned hash, struct rtable *rt)
  {

  	struct rtable **rthp, *aux;

  	rthp = &rt_hash_table[hash].chain;

  	spin_lock_bh(rt_hash_lock_addr(hash));

  	ip_rt_put(rt);

  	while ((aux = *rthp) != NULL) {

  		if (aux == rt || rt_is_expired(aux)) {

  			*rthp = aux->dst.rt_next;

  			rt_free(aux);
  			continue;

  		}

  		rthp = &aux->dst.rt_next;

  	}

  	spin_unlock_bh(rt_hash_lock_addr(hash));

  }

  /* called in rcu_read_lock() section */

  void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
  		    __be32 saddr, struct net_device *dev)

  {
  	int i, k;

  	struct in_device *in_dev = __in_dev_get_rcu(dev);

  	struct rtable *rth, **rthp;

  	__be32  skeys[2] = { saddr, 0 };

  	int  ikeys[2] = { dev->ifindex, 0 };

  	struct netevent_redirect netevent;

  	struct net *net;

  	if (!in_dev)
  		return;

  	net = dev_net(dev);

  	if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) ||
  	    ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) ||
  	    ipv4_is_zeronet(new_gw))

  		goto reject_redirect;

  	if (!rt_caching(net))
  		goto reject_redirect;

  	if (!IN_DEV_SHARED_MEDIA(in_dev)) {
  		if (!inet_addr_onlink(in_dev, new_gw, old_gw))
  			goto reject_redirect;
  		if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev))
  			goto reject_redirect;
  	} else {

  		if (inet_addr_type(net, new_gw) != RTN_UNICAST)

  			goto reject_redirect;
  	}
  
  	for (i = 0; i < 2; i++) {
  		for (k = 0; k < 2; k++) {

  			unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],

  						rt_genid(net));

  
  			rthp=&rt_hash_table[hash].chain;

  			while ((rth = rcu_dereference(*rthp)) != NULL) {
  				struct rtable *rt;
  
  				if (rth->fl.fl4_dst != daddr ||
  				    rth->fl.fl4_src != skeys[i] ||

  				    rth->fl.oif != ikeys[k] ||

  				    rth->fl.iif != 0 ||

  				    rt_is_expired(rth) ||

  				    !net_eq(dev_net(rth->dst.dev), net)) {
  					rthp = &rth->dst.rt_next;

  					continue;
  				}
  
  				if (rth->rt_dst != daddr ||
  				    rth->rt_src != saddr ||

  				    rth->dst.error ||

  				    rth->rt_gateway != old_gw ||

  				    rth->dst.dev != dev)

  					break;

  				dst_hold(&rth->dst);

  
  				rt = dst_alloc(&ipv4_dst_ops);
  				if (rt == NULL) {
  					ip_rt_put(rth);

  					return;
  				}
  
  				/* Copy all the information. */
  				*rt = *rth;

  				rt->dst.__use		= 1;
  				atomic_set(&rt->dst.__refcnt, 1);
  				rt->dst.child		= NULL;
  				if (rt->dst.dev)
  					dev_hold(rt->dst.dev);

  				if (rt->idev)
  					in_dev_hold(rt->idev);

  				rt->dst.obsolete	= -1;
  				rt->dst.lastuse	= jiffies;
  				rt->dst.path		= &rt->dst;
  				rt->dst.neighbour	= NULL;
  				rt->dst.hh		= NULL;

  #ifdef CONFIG_XFRM

  				rt->dst.xfrm		= NULL;

  #endif

  				rt->rt_genid		= rt_genid(net);

  				rt->rt_flags		|= RTCF_REDIRECTED;
  
  				/* Gateway is different ... */
  				rt->rt_gateway		= new_gw;
  
  				/* Redirect received -> path was valid */

  				dst_confirm(&rth->dst);

  
  				if (rt->peer)
  					atomic_inc(&rt->peer->refcnt);

  				if (arp_bind_neighbour(&rt->dst) ||
  				    !(rt->dst.neighbour->nud_state &

  					    NUD_VALID)) {

  					if (rt->dst.neighbour)
  						neigh_event_send(rt->dst.neighbour, NULL);

  					ip_rt_put(rth);
  					rt_drop(rt);
  					goto do_next;
  				}

  				netevent.old = &rth->dst;
  				netevent.new = &rt->dst;

  				call_netevent_notifiers(NETEVENT_REDIRECT,
  							&netevent);

  
  				rt_del(hash, rth);

  				if (!rt_intern_hash(hash, rt, &rt, NULL, rt->fl.oif))

  					ip_rt_put(rt);
  				goto do_next;
  			}

  		do_next:
  			;
  		}
  	}

  	return;
  
  reject_redirect:
  #ifdef CONFIG_IP_ROUTE_VERBOSE
  	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())

  		printk(KERN_INFO "Redirect from %pI4 on %s about %pI4 ignored.
  "
  			"  Advised path = %pI4 -> %pI4
  ",
  		       &old_gw, dev->name, &new_gw,
  		       &saddr, &daddr);

  #endif

  	;

  }
  
  static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
  {

  	struct rtable *rt = (struct rtable *)dst;

  	struct dst_entry *ret = dst;
  
  	if (rt) {

  		if (dst->obsolete > 0) {

  			ip_rt_put(rt);
  			ret = NULL;
  		} else if ((rt->rt_flags & RTCF_REDIRECTED) ||

  			   (rt->dst.expires &&
  			    time_after_eq(jiffies, rt->dst.expires))) {

  			unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,

  						rt->fl.oif,

  						rt_genid(dev_net(dst->dev)));

  #if RT_CACHE_DEBUG >= 1

  			printk(KERN_DEBUG "ipv4_negative_advice: redirect to %pI4/%02x dropped
  ",
  				&rt->rt_dst, rt->fl.fl4_tos);

  #endif
  			rt_del(hash, rt);
  			ret = NULL;
  		}
  	}
  	return ret;
  }
  
  /*
   * Algorithm:
   *	1. The first ip_rt_redirect_number redirects are sent
   *	   with exponential backoff, then we stop sending them at all,
   *	   assuming that the host ignores our redirects.
   *	2. If we did not see packets requiring redirects
   *	   during ip_rt_redirect_silence, we assume that the host
   *	   forgot redirected route and start to send redirects again.
   *
   * This algorithm is much cheaper and more intelligent than dumb load limiting
   * in icmp.c.
   *
   * NOTE. Do not forget to inhibit load limiting for redirects (redundant)
   * and "frag. need" (breaks PMTU discovery) in icmp.c.
   */
  
  void ip_rt_send_redirect(struct sk_buff *skb)
  {

  	struct rtable *rt = skb_rtable(skb);

  	struct in_device *in_dev;
  	int log_martians;

  	rcu_read_lock();

  	in_dev = __in_dev_get_rcu(rt->dst.dev);

  	if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) {
  		rcu_read_unlock();

  		return;

  	}
  	log_martians = IN_DEV_LOG_MARTIANS(in_dev);
  	rcu_read_unlock();

  
  	/* No redirected packets during ip_rt_redirect_silence;
  	 * reset the algorithm.
  	 */

  	if (time_after(jiffies, rt->dst.rate_last + ip_rt_redirect_silence))
  		rt->dst.rate_tokens = 0;

  
  	/* Too many ignored redirects; do not send anything

  	 * set dst.rate_last to the last seen redirected packet.

  	 */

  	if (rt->dst.rate_tokens >= ip_rt_redirect_number) {
  		rt->dst.rate_last = jiffies;

  		return;

  	}
  
  	/* Check for load limit; set rate_last to the latest sent
  	 * redirect.
  	 */

  	if (rt->dst.rate_tokens == 0 ||

  	    time_after(jiffies,

  		       (rt->dst.rate_last +
  			(ip_rt_redirect_load << rt->dst.rate_tokens)))) {

  		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);

  		rt->dst.rate_last = jiffies;
  		++rt->dst.rate_tokens;

  #ifdef CONFIG_IP_ROUTE_VERBOSE

  		if (log_martians &&

  		    rt->dst.rate_tokens == ip_rt_redirect_number &&

  		    net_ratelimit())

  			printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.
  ",
  				&rt->rt_src, rt->rt_iif,
  				&rt->rt_dst, &rt->rt_gateway);

  #endif
  	}

  }
  
  static int ip_error(struct sk_buff *skb)
  {

  	struct rtable *rt = skb_rtable(skb);

  	unsigned long now;
  	int code;

  	switch (rt->dst.error) {

  		case EINVAL:
  		default:
  			goto out;
  		case EHOSTUNREACH:
  			code = ICMP_HOST_UNREACH;
  			break;
  		case ENETUNREACH:
  			code = ICMP_NET_UNREACH;

  			IP_INC_STATS_BH(dev_net(rt->dst.dev),

  					IPSTATS_MIB_INNOROUTES);

  			break;
  		case EACCES:
  			code = ICMP_PKT_FILTERED;
  			break;
  	}
  
  	now = jiffies;

  	rt->dst.rate_tokens += now - rt->dst.rate_last;
  	if (rt->dst.rate_tokens > ip_rt_error_burst)
  		rt->dst.rate_tokens = ip_rt_error_burst;
  	rt->dst.rate_last = now;
  	if (rt->dst.rate_tokens >= ip_rt_error_cost) {
  		rt->dst.rate_tokens -= ip_rt_error_cost;

  		icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
  	}
  
  out:	kfree_skb(skb);
  	return 0;

  }

  
  /*
   *	The last two values are not from the RFC but
   *	are needed for AMPRnet AX.25 paths.
   */

  static const unsigned short mtu_plateau[] =

  {32000, 17914, 8166, 4352, 2002, 1492, 576, 296, 216, 128 };

  static inline unsigned short guess_mtu(unsigned short old_mtu)

  {
  	int i;

  	for (i = 0; i < ARRAY_SIZE(mtu_plateau); i++)
  		if (old_mtu > mtu_plateau[i])
  			return mtu_plateau[i];
  	return 68;
  }

  unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph,

  				 unsigned short new_mtu,
  				 struct net_device *dev)

  {

  	int i, k;

  	unsigned short old_mtu = ntohs(iph->tot_len);
  	struct rtable *rth;

  	int  ikeys[2] = { dev->ifindex, 0 };

  	__be32  skeys[2] = { iph->saddr, 0, };
  	__be32  daddr = iph->daddr;

  	unsigned short est_mtu = 0;

  	for (k = 0; k < 2; k++) {
  		for (i = 0; i < 2; i++) {

  			unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],

  						rt_genid(net));

  
  			rcu_read_lock();
  			for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;

  			     rth = rcu_dereference(rth->dst.rt_next)) {

  				unsigned short mtu = new_mtu;

  				if (rth->fl.fl4_dst != daddr ||
  				    rth->fl.fl4_src != skeys[i] ||
  				    rth->rt_dst != daddr ||
  				    rth->rt_src != iph->saddr ||
  				    rth->fl.oif != ikeys[k] ||
  				    rth->fl.iif != 0 ||

  				    dst_metric_locked(&rth->dst, RTAX_MTU) ||
  				    !net_eq(dev_net(rth->dst.dev), net) ||

  				    rt_is_expired(rth))

  					continue;

  				if (new_mtu < 68 || new_mtu >= old_mtu) {
  
  					/* BSD 4.2 compatibility hack :-( */
  					if (mtu == 0 &&

  					    old_mtu >= dst_mtu(&rth->dst) &&

  					    old_mtu >= 68 + (iph->ihl << 2))
  						old_mtu -= iph->ihl << 2;
  
  					mtu = guess_mtu(old_mtu);
  				}

  				if (mtu <= dst_mtu(&rth->dst)) {
  					if (mtu < dst_mtu(&rth->dst)) {
  						dst_confirm(&rth->dst);

  						if (mtu < ip_rt_min_pmtu) {
  							mtu = ip_rt_min_pmtu;

  							rth->dst.metrics[RTAX_LOCK-1] |=

  								(1 << RTAX_MTU);
  						}

  						rth->dst.metrics[RTAX_MTU-1] = mtu;
  						dst_set_expires(&rth->dst,

  							ip_rt_mtu_expires);
  					}
  					est_mtu = mtu;
  				}
  			}

  			rcu_read_unlock();

  		}

  	}
  	return est_mtu ? : new_mtu;
  }
  
  static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
  {

  	if (dst_mtu(dst) > mtu && mtu >= 68 &&

  	    !(dst_metric_locked(dst, RTAX_MTU))) {
  		if (mtu < ip_rt_min_pmtu) {
  			mtu = ip_rt_min_pmtu;
  			dst->metrics[RTAX_LOCK-1] |= (1 << RTAX_MTU);
  		}
  		dst->metrics[RTAX_MTU-1] = mtu;
  		dst_set_expires(dst, ip_rt_mtu_expires);

  		call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);

  	}
  }
  
  static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
  {

  	if (rt_is_expired((struct rtable *)dst))
  		return NULL;
  	return dst;

  }
  
  static void ipv4_dst_destroy(struct dst_entry *dst)
  {
  	struct rtable *rt = (struct rtable *) dst;
  	struct inet_peer *peer = rt->peer;
  	struct in_device *idev = rt->idev;
  
  	if (peer) {
  		rt->peer = NULL;
  		inet_putpeer(peer);
  	}
  
  	if (idev) {
  		rt->idev = NULL;
  		in_dev_put(idev);
  	}
  }
  
  static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
  			    int how)
  {
  	struct rtable *rt = (struct rtable *) dst;
  	struct in_device *idev = rt->idev;

  	if (dev != dev_net(dev)->loopback_dev && idev && idev->dev == dev) {

  		struct in_device *loopback_idev =

  			in_dev_get(dev_net(dev)->loopback_dev);

  		if (loopback_idev) {
  			rt->idev = loopback_idev;
  			in_dev_put(idev);
  		}
  	}
  }
  
  static void ipv4_link_failure(struct sk_buff *skb)
  {
  	struct rtable *rt;
  
  	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);

  	rt = skb_rtable(skb);

  	if (rt)

  		dst_set_expires(&rt->dst, 0);

  }
  
  static int ip_rt_bug(struct sk_buff *skb)
  {

  	printk(KERN_DEBUG "ip_rt_bug: %pI4 -> %pI4, %s
  ",
  		&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,

  		skb->dev ? skb->dev->name : "?");
  	kfree_skb(skb);
  	return 0;
  }
  
  /*
     We do not cache source address of outgoing interface,
     because it is used only by IP RR, TS and SRR options,
     so that it out of fast path.
  
     BTW remember: "addr" is allowed to be not aligned
     in IP options!
   */
  
  void ip_rt_get_source(u8 *addr, struct rtable *rt)
  {

  	__be32 src;

  	struct fib_result res;
  
  	if (rt->fl.iif == 0)
  		src = rt->rt_src;

  	else if (fib_lookup(dev_net(rt->dst.dev), &rt->fl, &res) == 0) {

  		src = FIB_RES_PREFSRC(res);
  		fib_res_put(&res);
  	} else

  		src = inet_select_addr(rt->dst.dev, rt->rt_gateway,

  					RT_SCOPE_UNIVERSE);
  	memcpy(addr, &src, 4);
  }
  
  #ifdef CONFIG_NET_CLS_ROUTE
  static void set_class_tag(struct rtable *rt, u32 tag)
  {

  	if (!(rt->dst.tclassid & 0xFFFF))
  		rt->dst.tclassid |= tag & 0xFFFF;
  	if (!(rt->dst.tclassid & 0xFFFF0000))
  		rt->dst.tclassid |= tag & 0xFFFF0000;

  }
  #endif
  
  static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
  {
  	struct fib_info *fi = res->fi;
  
  	if (fi) {
  		if (FIB_RES_GW(*res) &&
  		    FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
  			rt->rt_gateway = FIB_RES_GW(*res);

  		memcpy(rt->dst.metrics, fi->fib_metrics,
  		       sizeof(rt->dst.metrics));

  		if (fi->fib_mtu == 0) {

  			rt->dst.metrics[RTAX_MTU-1] = rt->dst.dev->mtu;
  			if (dst_metric_locked(&rt->dst, RTAX_MTU) &&

  			    rt->rt_gateway != rt->rt_dst &&

  			    rt->dst.dev->mtu > 576)
  				rt->dst.metrics[RTAX_MTU-1] = 576;

  		}
  #ifdef CONFIG_NET_CLS_ROUTE

  		rt->dst.tclassid = FIB_RES_NH(*res).nh_tclassid;

  #endif
  	} else

  		rt->dst.metrics[RTAX_MTU-1]= rt->dst.dev->mtu;
  
  	if (dst_metric(&rt->dst, RTAX_HOPLIMIT) == 0)
  		rt->dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl;
  	if (dst_mtu(&rt->dst) > IP_MAX_MTU)
  		rt->dst.metrics[RTAX_MTU-1] = IP_MAX_MTU;
  	if (dst_metric(&rt->dst, RTAX_ADVMSS) == 0)
  		rt->dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->dst.dev->mtu - 40,

  				       ip_rt_min_advmss);

  	if (dst_metric(&rt->dst, RTAX_ADVMSS) > 65535 - 40)
  		rt->dst.metrics[RTAX_ADVMSS-1] = 65535 - 40;

  
  #ifdef CONFIG_NET_CLS_ROUTE
  #ifdef CONFIG_IP_MULTIPLE_TABLES
  	set_class_tag(rt, fib_rules_tclass(res));
  #endif
  	set_class_tag(rt, itag);
  #endif

  	rt->rt_type = res->type;

  }

  /* called in rcu_read_lock() section */

  static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,

  				u8 tos, struct net_device *dev, int our)
  {

  	unsigned int hash;

  	struct rtable *rth;

  	__be32 spec_dst;

  	struct in_device *in_dev = __in_dev_get_rcu(dev);

  	u32 itag = 0;

  	int err;

  
  	/* Primary sanity checks. */
  
  	if (in_dev == NULL)
  		return -EINVAL;

  	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||

  	    ipv4_is_loopback(saddr) || skb->protocol != htons(ETH_P_IP))

  		goto e_inval;

  	if (ipv4_is_zeronet(saddr)) {
  		if (!ipv4_is_local_multicast(daddr))

  			goto e_inval;
  		spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);

  	} else {
  		err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
  					  &itag, 0);
  		if (err < 0)
  			goto e_err;
  	}

  	rth = dst_alloc(&ipv4_dst_ops);
  	if (!rth)
  		goto e_nobufs;

  	rth->dst.output = ip_rt_bug;
  	rth->dst.obsolete = -1;

  	atomic_set(&rth->dst.__refcnt, 1);
  	rth->dst.flags= DST_HOST;

  	if (IN_DEV_CONF_GET(in_dev, NOPOLICY))

  		rth->dst.flags |= DST_NOPOLICY;

  	rth->fl.fl4_dst	= daddr;
  	rth->rt_dst	= daddr;
  	rth->fl.fl4_tos	= tos;

  	rth->fl.mark    = skb->mark;

  	rth->fl.fl4_src	= saddr;
  	rth->rt_src	= saddr;
  #ifdef CONFIG_NET_CLS_ROUTE

  	rth->dst.tclassid = itag;

  #endif
  	rth->rt_iif	=
  	rth->fl.iif	= dev->ifindex;

  	rth->dst.dev	= init_net.loopback_dev;
  	dev_hold(rth->dst.dev);
  	rth->idev	= in_dev_get(rth->dst.dev);

  	rth->fl.oif	= 0;
  	rth->rt_gateway	= daddr;
  	rth->rt_spec_dst= spec_dst;

  	rth->rt_genid	= rt_genid(dev_net(dev));

  	rth->rt_flags	= RTCF_MULTICAST;

  	rth->rt_type	= RTN_MULTICAST;

  	if (our) {

  		rth->dst.input= ip_local_deliver;

  		rth->rt_flags |= RTCF_LOCAL;
  	}
  
  #ifdef CONFIG_IP_MROUTE

  	if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev))

  		rth->dst.input = ip_mr_input;

  #endif
  	RT_CACHE_STAT_INC(in_slow_mc);

  	hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));