X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv4%2Froute.c;h=28205e5bfa9b703a30baed0afe83c24575080574;hb=0975ecba3b670df7c488a5e0e6fe9f1f370a8ad8;hp=1b70ffd1261580008dc499ef1b286ff7ee8edd53;hpb=bb72845e699d3c84e5f861b51db686107a51dea5;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 1b70ffd..28205e5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -5,8 +5,6 @@
  *
  *		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, <waltje@uWalt.NL.Mugnet.ORG>
  *		Alan Cox, <gw4pts@gw4pts.ampr.org>
@@ -117,31 +115,24 @@
 
 #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 int ip_rt_flush_expected;
-static unsigned long rt_deadline;
-
-#define RTprint(a...)	printk(KERN_DEBUG a)
-
-static struct timer_list rt_flush_timer;
+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 ip_rt_secret_interval __read_mostly	= 10 * 60 * HZ;
+static int rt_chain_length_max __read_mostly	= 20;
+
 static void rt_worker_func(struct work_struct *work);
 static DECLARE_DELAYED_WORK(expires_work, rt_worker_func);
-static struct timer_list rt_secret_timer;
 
 /*
  *	Interface to generic destination cache.
@@ -154,12 +145,13 @@ static void		 ipv4_dst_ifdown(struct dst_entry *dst,
 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 int rt_garbage_collect(struct dst_ops *ops);
+static void rt_emergency_hash_rebuild(struct net *net);
 
 
 static struct dst_ops ipv4_dst_ops = {
 	.family =		AF_INET,
-	.protocol =		__constant_htons(ETH_P_IP),
+	.protocol =		cpu_to_be16(ETH_P_IP),
 	.gc =			rt_garbage_collect,
 	.check =		ipv4_dst_check,
 	.destroy =		ipv4_dst_destroy,
@@ -167,8 +159,8 @@ static struct dst_ops ipv4_dst_ops = {
 	.negative_advice =	ipv4_negative_advice,
 	.link_failure =		ipv4_link_failure,
 	.update_pmtu =		ip_rt_update_pmtu,
-	.local_out =		ip_local_out,
-	.entry_size =		sizeof(struct rtable),
+	.local_out =		__ip_local_out,
+	.entries =		ATOMIC_INIT(0),
 };
 
 #define ECN_OR_COST(class)	TC_PRIO_##class
@@ -210,6 +202,7 @@ const __u8 ip_tos2prio[16] = {
 struct rt_hash_bucket {
 	struct rtable	*chain;
 };
+
 #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
 	defined(CONFIG_PROVE_LOCKING)
 /*
@@ -256,63 +249,87 @@ static inline void rt_hash_lock_init(void)
 }
 #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 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) \
 	(__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)
+static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
+		int genid)
 {
-	return (jhash_2words(daddr, saddr, rt_hash_rnd)
-		& rt_hash_mask);
+	return jhash_3words((__force u32)(__be32)(daddr),
+			    (__force u32)(__be32)(saddr),
+			    idx, genid)
+		& rt_hash_mask;
 }
 
-#define rt_hash(daddr, saddr, idx) \
-	rt_hash_code((__force u32)(__be32)(daddr),\
-		     (__force u32)(__be32)(saddr) ^ ((idx) << 5))
+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 rtable *r = NULL;
 	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 = rt_hash_table[st->bucket].chain;
-		if (r)
-			break;
+		r = rcu_dereference(rt_hash_table[st->bucket].chain);
+		while (r) {
+			if (dev_net(r->u.dst.dev) == seq_file_net(seq) &&
+			    r->rt_genid == st->genid)
+				return r;
+			r = rcu_dereference(r->u.dst.rt_next);
+		}
 		rcu_read_unlock_bh();
 	}
-	return rcu_dereference(r);
+	return r;
 }
 
-static struct rtable *rt_cache_get_next(struct seq_file *seq, struct rtable *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;
+		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(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->u.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);
@@ -325,12 +342,16 @@ static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
 
 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;
+	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 = NULL;
+	struct rtable *r;
 
 	if (v == SEQ_START_TOKEN)
 		r = rt_cache_get_first(seq);
@@ -355,10 +376,10 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 			   "HHUptod\tSpecDst");
 	else {
 		struct rtable *r = v;
-		char temp[256];
+		int len;
 
-		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",
+		seq_printf(seq, "%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%n",
 			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),
@@ -372,8 +393,9 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 			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);
+			r->rt_spec_dst, &len);
+
+		seq_printf(seq, "%*s\n", 127 - len, "");
 	}
 	return 0;
 }
@@ -387,7 +409,7 @@ static const struct seq_operations rt_cache_seq_ops = {
 
 static int rt_cache_seq_open(struct inode *inode, struct file *file)
 {
-	return seq_open_private(file, &rt_cache_seq_ops,
+	return seq_open_net(inode, file, &rt_cache_seq_ops,
 			sizeof(struct rt_cache_iter_state));
 }
 
@@ -396,7 +418,7 @@ static const struct file_operations rt_cache_seq_fops = {
 	.open	 = rt_cache_seq_open,
 	.read	 = seq_read,
 	.llseek	 = seq_lseek,
-	.release = seq_release_private,
+	.release = seq_release_net,
 };
 
 
@@ -407,7 +429,7 @@ static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos)
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
 
-	for (cpu = *pos-1; cpu < NR_CPUS; ++cpu) {
+	for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) {
 		if (!cpu_possible(cpu))
 			continue;
 		*pos = cpu+1;
@@ -420,7 +442,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	int cpu;
 
-	for (cpu = *pos; cpu < NR_CPUS; ++cpu) {
+	for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) {
 		if (!cpu_possible(cpu))
 			continue;
 		*pos = cpu+1;
@@ -530,7 +552,7 @@ static int ip_rt_acct_read(char *buffer, char **start, off_t offset,
 }
 #endif
 
-static __init int ip_rt_proc_init(struct net *net)
+static int __net_init ip_rt_do_proc_init(struct net *net)
 {
 	struct proc_dir_entry *pde;
 
@@ -539,12 +561,11 @@ static __init int ip_rt_proc_init(struct net *net)
 	if (!pde)
 		goto err1;
 
-	pde = create_proc_entry("rt_cache", S_IRUGO, net->proc_net_stat);
+	pde = proc_create("rt_cache", S_IRUGO,
+			  net->proc_net_stat, &rt_cpu_seq_fops);
 	if (!pde)
 		goto err2;
 
-	pde->proc_fops = &rt_cpu_seq_fops;
-
 #ifdef CONFIG_NET_CLS_ROUTE
 	pde = create_proc_read_entry("rt_acct", 0, net->proc_net,
 			ip_rt_acct_read, NULL);
@@ -562,25 +583,43 @@ err2:
 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);
+	remove_proc_entry("rt_acct", net->proc_net);
+}
+
+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(struct net *net)
+static inline int ip_rt_proc_init(void)
 {
 	return 0;
 }
 #endif /* CONFIG_PROC_FS */
 
-static __inline__ void rt_free(struct rtable *rt)
+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)
+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)
+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 */
@@ -588,7 +627,7 @@ static __inline__ int rt_fast_clean(struct rtable *rth)
 		rth->fl.iif && rth->u.dst.rt_next;
 }
 
-static __inline__ int rt_valuable(struct rtable *rth)
+static inline int rt_valuable(struct rtable *rth)
 {
 	return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
 		rth->u.dst.expires;
@@ -637,6 +676,20 @@ static inline u32 rt_score(struct rtable *rt)
 	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 ^ fl2->nl_u.ip4_u.daddr) |
+		(fl1->nl_u.ip4_u.saddr ^ 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 ^ fl2->nl_u.ip4_u.daddr) |
@@ -648,6 +701,16 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
 		(fl1->iif ^ fl2->iif)) == 0;
 }
 
+static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
+{
+	return dev_net(rt1->u.dst.dev) == dev_net(rt2->u.dst.dev);
+}
+
+static inline int rt_is_expired(struct rtable *rth)
+{
+	return rth->rt_genid != rt_genid(dev_net(rth->u.dst.dev));
+}
+
 /*
  * Perform a full scan of hash table and free all entries.
  * Can be called by a softirq or a process.
@@ -657,6 +720,7 @@ 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())
@@ -666,22 +730,63 @@ static void rt_do_flush(int process_context)
 			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->u.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->u.dst.rt_next;
+			if (!rt_is_expired(p)) {
+				prev = &p->u.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; rth = next) {
+		for (; rth != tail; rth = next) {
 			next = rth->u.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)
+
 static void rt_check_expire(void)
 {
 	static unsigned int rover;
 	unsigned int i = rover, goal;
-	struct rtable *rth, **rthp;
+	struct rtable *rth, *aux, **rthp;
+	unsigned long samples = 0;
+	unsigned long sum = 0, sum2 = 0;
 	u64 mult;
 
 	mult = ((u64)ip_rt_gc_interval) << rt_hash_log;
@@ -692,6 +797,7 @@ static void rt_check_expire(void)
 		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;
@@ -699,112 +805,128 @@ static void rt_check_expire(void)
 		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->u.dst.rt_next);
+			if (rt_is_expired(rth)) {
+				*rthp = rth->u.dst.rt_next;
+				rt_free(rth);
+				continue;
+			}
 			if (rth->u.dst.expires) {
 				/* Entry is expired even if it is in use */
 				if (time_before_eq(jiffies, rth->u.dst.expires)) {
+nofree:
 					tmo >>= 1;
 					rthp = &rth->u.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
+					 */
+					for (aux = rt_hash_table[i].chain;;) {
+						if (aux == rth) {
+							length += ONE;
+							break;
+						}
+						if (compare_hash_inputs(&aux->fl, &rth->fl))
+							break;
+						aux = aux->u.dst.rt_next;
+					}
 					continue;
 				}
-			} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
-				tmo >>= 1;
-				rthp = &rth->u.dst.rt_next;
-				continue;
-			}
+			} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
+				goto nofree;
 
 			/* Cleanup aged off entries. */
 			*rthp = rth->u.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.
- * If a whole flush was scheduled, it is done.
- * Else, we call rt_check_expire() to scan part of the hash table
+ * we call rt_check_expire() to scan part of the hash table
  */
 static void rt_worker_func(struct work_struct *work)
 {
-	if (ip_rt_flush_expected) {
-		ip_rt_flush_expected = 0;
-		rt_do_flush(1);
-	} else
-		rt_check_expire();
+	rt_check_expire();
 	schedule_delayed_work(&expires_work, ip_rt_gc_interval);
 }
 
-/* This can run from both BH and non-BH contexts, the latter
- * in the case of a forced flush event.
+/*
+ * 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_run_flush(unsigned long process_context)
+static void rt_cache_invalidate(struct net *net)
 {
-	rt_deadline = 0;
+	unsigned char shuffle;
 
-	get_random_bytes(&rt_hash_rnd, 4);
-
-	rt_do_flush(process_context);
+	get_random_bytes(&shuffle, sizeof(shuffle));
+	atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
 }
 
-static DEFINE_SPINLOCK(rt_flush_lock);
-
-void rt_cache_flush(int delay)
+/*
+ * 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)
 {
-	unsigned long now = jiffies;
-	int user_mode = !in_softirq();
-
-	if (delay < 0)
-		delay = ip_rt_min_delay;
-
-	spin_lock_bh(&rt_flush_lock);
-
-	if (del_timer(&rt_flush_timer) && delay > 0 && rt_deadline) {
-		long tmo = (long)(rt_deadline - now);
-
-		/* If flush timer is already running
-		   and flush request is not immediate (delay > 0):
-
-		   if deadline is not achieved, prolongate timer to "delay",
-		   otherwise fire it at deadline time.
-		 */
-
-		if (user_mode && tmo < ip_rt_max_delay-ip_rt_min_delay)
-			tmo = 0;
+	rt_cache_invalidate(net);
+	if (delay >= 0)
+		rt_do_flush(!in_softirq());
+}
 
-		if (delay > tmo)
-			delay = tmo;
-	}
+/*
+ * We change rt_genid and let gc do the cleanup
+ */
+static void rt_secret_rebuild(unsigned long __net)
+{
+	struct net *net = (struct net *)__net;
+	rt_cache_invalidate(net);
+	mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
+}
 
-	if (delay <= 0) {
-		spin_unlock_bh(&rt_flush_lock);
-		rt_run_flush(user_mode);
-		return;
+static void rt_secret_rebuild_oneshot(struct net *net)
+{
+	del_timer_sync(&net->ipv4.rt_secret_timer);
+	rt_cache_invalidate(net);
+	if (ip_rt_secret_interval) {
+		net->ipv4.rt_secret_timer.expires += ip_rt_secret_interval;
+		add_timer(&net->ipv4.rt_secret_timer);
 	}
-
-	if (rt_deadline == 0)
-		rt_deadline = now + ip_rt_max_delay;
-
-	mod_timer(&rt_flush_timer, now+delay);
-	spin_unlock_bh(&rt_flush_lock);
 }
 
-/*
- * We change rt_hash_rnd and ask next rt_worker_func() invocation
- * to perform a flush in process context
- */
-static void rt_secret_rebuild(unsigned long dummy)
+static void rt_emergency_hash_rebuild(struct net *net)
 {
-	get_random_bytes(&rt_hash_rnd, 4);
-	ip_rt_flush_expected = 1;
-	cancel_delayed_work(&expires_work);
-	schedule_delayed_work(&expires_work, HZ/10);
-	mod_timer(&rt_secret_timer, jiffies + ip_rt_secret_interval);
+	if (net_ratelimit()) {
+		printk(KERN_WARNING "Route hash chain too long!\n");
+		printk(KERN_WARNING "Adjust your secret_interval!\n");
+	}
+
+	rt_secret_rebuild_oneshot(net);
 }
 
 /*
@@ -820,7 +942,7 @@ static void rt_secret_rebuild(unsigned long dummy)
    and when load increases it reduces to limit cache size.
  */
 
-static int rt_garbage_collect(void)
+static int rt_garbage_collect(struct dst_ops *ops)
 {
 	static unsigned long expire = RT_GC_TIMEOUT;
 	static unsigned long last_gc;
@@ -851,14 +973,14 @@ static int rt_garbage_collect(void)
 			equilibrium = ipv4_dst_ops.gc_thresh;
 		goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
 		if (goal > 0) {
-			equilibrium += min_t(unsigned int, goal / 2, rt_hash_mask + 1);
+			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 / 2, rt_hash_mask + 1);
+		goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1);
 		equilibrium = atomic_read(&ipv4_dst_ops.entries) - goal;
 	}
 
@@ -880,7 +1002,8 @@ static int rt_garbage_collect(void)
 			rthp = &rt_hash_table[k].chain;
 			spin_lock_bh(rt_hash_lock_addr(k));
 			while ((rth = *rthp) != NULL) {
-				if (!rt_may_expire(rth, tmo, expire)) {
+				if (!rt_is_expired(rth) &&
+					!rt_may_expire(rth, tmo, expire)) {
 					tmo >>= 1;
 					rthp = &rth->u.dst.rt_next;
 					continue;
@@ -957,11 +1080,21 @@ restart:
 	candp = NULL;
 	now = jiffies;
 
+	if (!rt_caching(dev_net(rt->u.dst.dev))) {
+		rt_drop(rt);
+		return 0;
+	}
+
 	rthp = &rt_hash_table[hash].chain;
 
 	spin_lock_bh(rt_hash_lock_addr(hash));
 	while ((rth = *rthp) != NULL) {
-		if (compare_keys(&rth->fl, &rt->fl)) {
+		if (rt_is_expired(rth)) {
+			*rthp = rth->u.dst.rt_next;
+			rt_free(rth);
+			continue;
+		}
+		if (compare_keys(&rth->fl, &rt->fl) && compare_netns(rth, rt)) {
 			/* Put it first */
 			*rthp = rth->u.dst.rt_next;
 			/*
@@ -1011,6 +1144,16 @@ restart:
 			*candp = cand->u.dst.rt_next;
 			rt_free(cand);
 		}
+	} else {
+		if (chain_length > rt_chain_length_max) {
+			struct net *net = dev_net(rt->u.dst.dev);
+			int num = ++net->ipv4.current_rt_cache_rebuild_count;
+			if (!rt_caching(dev_net(rt->u.dst.dev))) {
+				printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n",
+					rt->u.dst.dev->name, num);
+			}
+			rt_emergency_hash_rebuild(dev_net(rt->u.dst.dev));
+		}
 	}
 
 	/* Try to bind route to arp only if it is output
@@ -1035,7 +1178,7 @@ restart:
 				int saved_int = ip_rt_gc_min_interval;
 				ip_rt_gc_elasticity	= 1;
 				ip_rt_gc_min_interval	= 0;
-				rt_garbage_collect();
+				rt_garbage_collect(&ipv4_dst_ops);
 				ip_rt_gc_min_interval	= saved_int;
 				ip_rt_gc_elasticity	= saved_elasticity;
 				goto restart;
@@ -1049,17 +1192,23 @@ restart:
 	}
 
 	rt->u.dst.rt_next = rt_hash_table[hash].chain;
+
 #if RT_CACHE_DEBUG >= 2
 	if (rt->u.dst.rt_next) {
 		struct rtable *trt;
-		printk(KERN_DEBUG "rt_cache @%02x: %u.%u.%u.%u", hash,
-		       NIPQUAD(rt->rt_dst));
+		printk(KERN_DEBUG "rt_cache @%02x: %pI4", hash, &rt->rt_dst);
 		for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next)
-			printk(" . %u.%u.%u.%u", NIPQUAD(trt->rt_dst));
+			printk(" . %pI4", &trt->rt_dst);
 		printk("\n");
 	}
 #endif
-	rt_hash_table[hash].chain = rt;
+	/*
+	 * 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));
 	*rp = rt;
 	return 0;
@@ -1126,17 +1275,19 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
 
 static void rt_del(unsigned hash, struct rtable *rt)
 {
-	struct rtable **rthp;
+	struct rtable **rthp, *aux;
 
+	rthp = &rt_hash_table[hash].chain;
 	spin_lock_bh(rt_hash_lock_addr(hash));
 	ip_rt_put(rt);
-	for (rthp = &rt_hash_table[hash].chain; *rthp;
-	     rthp = &(*rthp)->u.dst.rt_next)
-		if (*rthp == rt) {
-			*rthp = rt->u.dst.rt_next;
-			rt_free(rt);
-			break;
+	while ((aux = *rthp) != NULL) {
+		if (aux == rt || rt_is_expired(aux)) {
+			*rthp = aux->u.dst.rt_next;
+			rt_free(aux);
+			continue;
 		}
+		rthp = &aux->u.dst.rt_next;
+	}
 	spin_unlock_bh(rt_hash_lock_addr(hash));
 }
 
@@ -1149,12 +1300,18 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 	__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)
-	    || MULTICAST(new_gw) || BADCLASS(new_gw) || ZERONET(new_gw))
+	    || 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)) {
@@ -1163,13 +1320,14 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 		if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev))
 			goto reject_redirect;
 	} else {
-		if (inet_addr_type(new_gw) != RTN_UNICAST)
+		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]);
+			unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],
+						rt_genid(net));
 
 			rthp=&rt_hash_table[hash].chain;
 
@@ -1180,7 +1338,9 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 				if (rth->fl.fl4_dst != daddr ||
 				    rth->fl.fl4_src != skeys[i] ||
 				    rth->fl.oif != ikeys[k] ||
-				    rth->fl.iif != 0) {
+				    rth->fl.iif != 0 ||
+				    rt_is_expired(rth) ||
+				    !net_eq(dev_net(rth->u.dst.dev), net)) {
 					rthp = &rth->u.dst.rt_next;
 					continue;
 				}
@@ -1204,7 +1364,6 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 
 				/* Copy all the information. */
 				*rt = *rth;
-				INIT_RCU_HEAD(&rt->u.dst.rcu_head);
 				rt->u.dst.__use		= 1;
 				atomic_set(&rt->u.dst.__refcnt, 1);
 				rt->u.dst.child		= NULL;
@@ -1217,8 +1376,10 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 				rt->u.dst.path		= &rt->u.dst;
 				rt->u.dst.neighbour	= NULL;
 				rt->u.dst.hh		= NULL;
+#ifdef CONFIG_XFRM
 				rt->u.dst.xfrm		= NULL;
-
+#endif
+				rt->rt_genid		= rt_genid(net);
 				rt->rt_flags		|= RTCF_REDIRECTED;
 
 				/* Gateway is different ... */
@@ -1261,18 +1422,17 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 reject_redirect:
 #ifdef CONFIG_IP_ROUTE_VERBOSE
 	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
-		printk(KERN_INFO "Redirect from %u.%u.%u.%u on %s about "
-			"%u.%u.%u.%u ignored.\n"
-			"  Advised path = %u.%u.%u.%u -> %u.%u.%u.%u\n",
-		       NIPQUAD(old_gw), dev->name, NIPQUAD(new_gw),
-		       NIPQUAD(saddr), NIPQUAD(daddr));
+		printk(KERN_INFO "Redirect from %pI4 on %s about %pI4 ignored.\n"
+			"  Advised path = %pI4 -> %pI4\n",
+		       &old_gw, dev->name, &new_gw,
+		       &saddr, &daddr);
 #endif
 	in_dev_put(in_dev);
 }
 
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 {
-	struct rtable *rt = (struct rtable*)dst;
+	struct rtable *rt = (struct rtable *)dst;
 	struct dst_entry *ret = dst;
 
 	if (rt) {
@@ -1282,11 +1442,11 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 		} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
 			   rt->u.dst.expires) {
 			unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
-						rt->fl.oif);
+						rt->fl.oif,
+						rt_genid(dev_net(dst->dev)));
 #if RT_CACHE_DEBUG >= 1
-			printk(KERN_DEBUG "ipv4_negative_advice: redirect to "
-					  "%u.%u.%u.%u/%02x dropped\n",
-				NIPQUAD(rt->rt_dst), rt->fl.fl4_tos);
+			printk(KERN_DEBUG "ipv4_negative_advice: redirect to %pI4/%02x dropped\n",
+				&rt->rt_dst, rt->fl.fl4_tos);
 #endif
 			rt_del(hash, rt);
 			ret = NULL;
@@ -1313,7 +1473,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 
 void ip_rt_send_redirect(struct sk_buff *skb)
 {
-	struct rtable *rt = (struct rtable*)skb->dst;
+	struct rtable *rt = skb->rtable;
 	struct in_device *in_dev = in_dev_get(rt->u.dst.dev);
 
 	if (!in_dev)
@@ -1350,10 +1510,9 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 		if (IN_DEV_LOG_MARTIANS(in_dev) &&
 		    rt->u.dst.rate_tokens == ip_rt_redirect_number &&
 		    net_ratelimit())
-			printk(KERN_WARNING "host %u.%u.%u.%u/if%d ignores "
-				"redirects for %u.%u.%u.%u to %u.%u.%u.%u.\n",
-				NIPQUAD(rt->rt_src), rt->rt_iif,
-				NIPQUAD(rt->rt_dst), NIPQUAD(rt->rt_gateway));
+			printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n",
+				&rt->rt_src, rt->rt_iif,
+				&rt->rt_dst, &rt->rt_gateway);
 #endif
 	}
 out:
@@ -1362,7 +1521,7 @@ out:
 
 static int ip_error(struct sk_buff *skb)
 {
-	struct rtable *rt = (struct rtable*)skb->dst;
+	struct rtable *rt = skb->rtable;
 	unsigned long now;
 	int code;
 
@@ -1375,7 +1534,8 @@ static int ip_error(struct sk_buff *skb)
 			break;
 		case ENETUNREACH:
 			code = ICMP_NET_UNREACH;
-			IP_INC_STATS_BH(IPSTATS_MIB_INNOROUTES);
+			IP_INC_STATS_BH(dev_net(rt->u.dst.dev),
+					IPSTATS_MIB_INNOROUTES);
 			break;
 		case EACCES:
 			code = ICMP_PKT_FILTERED;
@@ -1404,7 +1564,7 @@ out:	kfree_skb(skb);
 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)
+static inline unsigned short guess_mtu(unsigned short old_mtu)
 {
 	int i;
 
@@ -1414,11 +1574,14 @@ static __inline__ unsigned short guess_mtu(unsigned short old_mtu)
 	return 68;
 }
 
-unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu)
+unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph,
+				 unsigned short new_mtu,
+				 struct net_device *dev)
 {
-	int i;
+	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;
@@ -1426,32 +1589,39 @@ unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu)
 	if (ipv4_config.no_pmtu_disc)
 		return 0;
 
-	for (i = 0; i < 2; i++) {
-		unsigned hash = rt_hash(daddr, skeys[i], 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->u.dst.rt_next)) {
-			if (rth->fl.fl4_dst == daddr &&
-			    rth->fl.fl4_src == skeys[i] &&
-			    rth->rt_dst  == daddr &&
-			    rth->rt_src  == iph->saddr &&
-			    rth->fl.iif == 0 &&
-			    !(dst_metric_locked(&rth->u.dst, RTAX_MTU))) {
+			rcu_read_lock();
+			for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
+			     rth = rcu_dereference(rth->u.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->u.dst, RTAX_MTU) ||
+				    !net_eq(dev_net(rth->u.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 >= rth->u.dst.metrics[RTAX_MTU-1] &&
+					    old_mtu >= dst_mtu(&rth->u.dst) &&
 					    old_mtu >= 68 + (iph->ihl << 2))
 						old_mtu -= iph->ihl << 2;
 
 					mtu = guess_mtu(old_mtu);
 				}
-				if (mtu <= rth->u.dst.metrics[RTAX_MTU-1]) {
-					if (mtu < rth->u.dst.metrics[RTAX_MTU-1]) {
+				if (mtu <= dst_mtu(&rth->u.dst)) {
+					if (mtu < dst_mtu(&rth->u.dst)) {
 						dst_confirm(&rth->u.dst);
 						if (mtu < ip_rt_min_pmtu) {
 							mtu = ip_rt_min_pmtu;
@@ -1465,15 +1635,15 @@ unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu)
 					est_mtu = mtu;
 				}
 			}
+			rcu_read_unlock();
 		}
-		rcu_read_unlock();
 	}
 	return est_mtu ? : new_mtu;
 }
 
 static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 {
-	if (dst->metrics[RTAX_MTU-1] > mtu && mtu >= 68 &&
+	if (dst_mtu(dst) > mtu && mtu >= 68 &&
 	    !(dst_metric_locked(dst, RTAX_MTU))) {
 		if (mtu < ip_rt_min_pmtu) {
 			mtu = ip_rt_min_pmtu;
@@ -1512,9 +1682,9 @@ static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 {
 	struct rtable *rt = (struct rtable *) dst;
 	struct in_device *idev = rt->idev;
-	if (dev != dev->nd_net->loopback_dev && idev && idev->dev == dev) {
+	if (dev != dev_net(dev)->loopback_dev && idev && idev->dev == dev) {
 		struct in_device *loopback_idev =
-			in_dev_get(dev->nd_net->loopback_dev);
+			in_dev_get(dev_net(dev)->loopback_dev);
 		if (loopback_idev) {
 			rt->idev = loopback_idev;
 			in_dev_put(idev);
@@ -1528,15 +1698,15 @@ static void ipv4_link_failure(struct sk_buff *skb)
 
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
 
-	rt = (struct rtable *) skb->dst;
+	rt = skb->rtable;
 	if (rt)
 		dst_set_expires(&rt->u.dst, 0);
 }
 
 static int ip_rt_bug(struct sk_buff *skb)
 {
-	printk(KERN_DEBUG "ip_rt_bug: %u.%u.%u.%u -> %u.%u.%u.%u, %s\n",
-		NIPQUAD(ip_hdr(skb)->saddr), NIPQUAD(ip_hdr(skb)->daddr),
+	printk(KERN_DEBUG "ip_rt_bug: %pI4 -> %pI4, %s\n",
+		&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
 		skb->dev ? skb->dev->name : "?");
 	kfree_skb(skb);
 	return 0;
@@ -1558,7 +1728,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt)
 
 	if (rt->fl.iif == 0)
 		src = rt->rt_src;
-	else if (fib_lookup(&rt->fl, &res) == 0) {
+	else if (fib_lookup(dev_net(rt->u.dst.dev), &rt->fl, &res) == 0) {
 		src = FIB_RES_PREFSRC(res);
 		fib_res_put(&res);
 	} else
@@ -1589,7 +1759,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 		       sizeof(rt->u.dst.metrics));
 		if (fi->fib_mtu == 0) {
 			rt->u.dst.metrics[RTAX_MTU-1] = rt->u.dst.dev->mtu;
-			if (rt->u.dst.metrics[RTAX_LOCK-1] & (1 << RTAX_MTU) &&
+			if (dst_metric_locked(&rt->u.dst, RTAX_MTU) &&
 			    rt->rt_gateway != rt->rt_dst &&
 			    rt->u.dst.dev->mtu > 576)
 				rt->u.dst.metrics[RTAX_MTU-1] = 576;
@@ -1600,14 +1770,14 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 	} else
 		rt->u.dst.metrics[RTAX_MTU-1]= rt->u.dst.dev->mtu;
 
-	if (rt->u.dst.metrics[RTAX_HOPLIMIT-1] == 0)
+	if (dst_metric(&rt->u.dst, RTAX_HOPLIMIT) == 0)
 		rt->u.dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl;
-	if (rt->u.dst.metrics[RTAX_MTU-1] > IP_MAX_MTU)
+	if (dst_mtu(&rt->u.dst) > IP_MAX_MTU)
 		rt->u.dst.metrics[RTAX_MTU-1] = IP_MAX_MTU;
-	if (rt->u.dst.metrics[RTAX_ADVMSS-1] == 0)
+	if (dst_metric(&rt->u.dst, RTAX_ADVMSS) == 0)
 		rt->u.dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->u.dst.dev->mtu - 40,
 				       ip_rt_min_advmss);
-	if (rt->u.dst.metrics[RTAX_ADVMSS-1] > 65535 - 40)
+	if (dst_metric(&rt->u.dst, RTAX_ADVMSS) > 65535 - 40)
 		rt->u.dst.metrics[RTAX_ADVMSS-1] = 65535 - 40;
 
 #ifdef CONFIG_NET_CLS_ROUTE
@@ -1633,12 +1803,12 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (in_dev == NULL)
 		return -EINVAL;
 
-	if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr) ||
-	    skb->protocol != htons(ETH_P_IP))
+	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
+	    ipv4_is_loopback(saddr) || skb->protocol != htons(ETH_P_IP))
 		goto e_inval;
 
-	if (ZERONET(saddr)) {
-		if (!LOCAL_MCAST(daddr))
+	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 if (fib_validate_source(saddr, 0, tos, 0,
@@ -1672,22 +1842,23 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	rth->fl.oif	= 0;
 	rth->rt_gateway	= daddr;
 	rth->rt_spec_dst= spec_dst;
-	rth->rt_type	= RTN_MULTICAST;
+	rth->rt_genid	= rt_genid(dev_net(dev));
 	rth->rt_flags	= RTCF_MULTICAST;
+	rth->rt_type	= RTN_MULTICAST;
 	if (our) {
 		rth->u.dst.input= ip_local_deliver;
 		rth->rt_flags |= RTCF_LOCAL;
 	}
 
 #ifdef CONFIG_IP_MROUTE
-	if (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
+	if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev))
 		rth->u.dst.input = ip_mr_input;
 #endif
 	RT_CACHE_STAT_INC(in_slow_mc);
 
 	in_dev_put(in_dev);
-	hash = rt_hash(daddr, saddr, dev->ifindex);
-	return rt_intern_hash(hash, rth, (struct rtable**) &skb->dst);
+	hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
+	return rt_intern_hash(hash, rth, &skb->rtable);
 
 e_nobufs:
 	in_dev_put(in_dev);
@@ -1712,9 +1883,8 @@ static void ip_handle_martian_source(struct net_device *dev,
 		 *	RFC1812 recommendation, if source is martian,
 		 *	the only hint is MAC header.
 		 */
-		printk(KERN_WARNING "martian source %u.%u.%u.%u from "
-			"%u.%u.%u.%u, on dev %s\n",
-			NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
+		printk(KERN_WARNING "martian source %pI4 from %pI4, on dev %s\n",
+			&daddr, &saddr, dev->name);
 		if (dev->hard_header_len && skb_mac_header_was_set(skb)) {
 			int i;
 			const unsigned char *p = skb_mac_header(skb);
@@ -1730,11 +1900,11 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
-static inline int __mkroute_input(struct sk_buff *skb,
-				  struct fib_result* res,
-				  struct in_device *in_dev,
-				  __be32 daddr, __be32 saddr, u32 tos,
-				  struct rtable **result)
+static int __mkroute_input(struct sk_buff *skb,
+			   struct fib_result *res,
+			   struct in_device *in_dev,
+			   __be32 daddr, __be32 saddr, u32 tos,
+			   struct rtable **result)
 {
 
 	struct rtable *rth;
@@ -1767,7 +1937,7 @@ static inline int __mkroute_input(struct sk_buff *skb,
 	if (err)
 		flags |= RTCF_DIRECTSRC;
 
-	if (out_dev == in_dev && err && !(flags & (RTCF_NAT | RTCF_MASQ)) &&
+	if (out_dev == in_dev && err &&
 	    (IN_DEV_SHARED_MEDIA(out_dev) ||
 	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
 		flags |= RTCF_DOREDIRECT;
@@ -1776,7 +1946,7 @@ static inline int __mkroute_input(struct sk_buff *skb,
 		/* Not IP (i.e. ARP). Do not create route, if it is
 		 * invalid for proxy arp. DNAT routes are always valid.
 		 */
-		if (out_dev == in_dev && !(flags & RTCF_DNAT)) {
+		if (out_dev == in_dev) {
 			err = -EINVAL;
 			goto cleanup;
 		}
@@ -1812,6 +1982,7 @@ static inline int __mkroute_input(struct sk_buff *skb,
 
 	rth->u.dst.input = ip_forward;
 	rth->u.dst.output = ip_output;
+	rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev));
 
 	rt_set_nexthop(rth, res, itag);
 
@@ -1825,11 +1996,11 @@ static inline int __mkroute_input(struct sk_buff *skb,
 	return err;
 }
 
-static inline int ip_mkroute_input(struct sk_buff *skb,
-				   struct fib_result* res,
-				   const struct flowi *fl,
-				   struct in_device *in_dev,
-				   __be32 daddr, __be32 saddr, u32 tos)
+static int ip_mkroute_input(struct sk_buff *skb,
+			    struct fib_result *res,
+			    const struct flowi *fl,
+			    struct in_device *in_dev,
+			    __be32 daddr, __be32 saddr, u32 tos)
 {
 	struct rtable* rth = NULL;
 	int err;
@@ -1846,8 +2017,9 @@ static inline int ip_mkroute_input(struct sk_buff *skb,
 		return err;
 
 	/* put it into the cache */
-	hash = rt_hash(daddr, saddr, fl->iif);
-	return rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
+	hash = rt_hash(daddr, saddr, fl->iif,
+		       rt_genid(dev_net(rth->u.dst.dev)));
+	return rt_intern_hash(hash, rth, &skb->rtable);
 }
 
 /*
@@ -1880,6 +2052,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	__be32		spec_dst;
 	int		err = -EINVAL;
 	int		free_res = 0;
+	struct net    * net = dev_net(dev);
 
 	/* IP on this device is disabled. */
 
@@ -1890,7 +2063,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	   by fib_lookup.
 	 */
 
-	if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr))
+	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
+	    ipv4_is_loopback(saddr))
 		goto martian_source;
 
 	if (daddr == htonl(0xFFFFFFFF) || (saddr == 0 && daddr == 0))
@@ -1899,16 +2073,17 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	/* Accept zero addresses only to limited broadcast;
 	 * I even do not know to fix it or not. Waiting for complains :-)
 	 */
-	if (ZERONET(saddr))
+	if (ipv4_is_zeronet(saddr))
 		goto martian_source;
 
-	if (BADCLASS(daddr) || ZERONET(daddr) || LOOPBACK(daddr))
+	if (ipv4_is_lbcast(daddr) || ipv4_is_zeronet(daddr) ||
+	    ipv4_is_loopback(daddr))
 		goto martian_destination;
 
 	/*
 	 *	Now we are ready to route packet.
 	 */
-	if ((err = fib_lookup(&fl, &res)) != 0) {
+	if ((err = fib_lookup(net, &fl, &res)) != 0) {
 		if (!IN_DEV_FORWARD(in_dev))
 			goto e_hostunreach;
 		goto no_route;
@@ -1923,7 +2098,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (res.type == RTN_LOCAL) {
 		int result;
 		result = fib_validate_source(saddr, daddr, tos,
-					     init_net.loopback_dev->ifindex,
+					     net->loopback_dev->ifindex,
 					     dev, &spec_dst, &itag);
 		if (result < 0)
 			goto martian_source;
@@ -1949,7 +2124,7 @@ brd_input:
 	if (skb->protocol != htons(ETH_P_IP))
 		goto e_inval;
 
-	if (ZERONET(saddr))
+	if (ipv4_is_zeronet(saddr))
 		spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
 	else {
 		err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
@@ -1969,6 +2144,7 @@ local_input:
 		goto e_nobufs;
 
 	rth->u.dst.output= ip_rt_bug;
+	rth->rt_genid = rt_genid(net);
 
 	atomic_set(&rth->u.dst.__refcnt, 1);
 	rth->u.dst.flags= DST_HOST;
@@ -1985,7 +2161,7 @@ local_input:
 #endif
 	rth->rt_iif	=
 	rth->fl.iif	= dev->ifindex;
-	rth->u.dst.dev	= init_net.loopback_dev;
+	rth->u.dst.dev	= net->loopback_dev;
 	dev_hold(rth->u.dst.dev);
 	rth->idev	= in_dev_get(rth->u.dst.dev);
 	rth->rt_gateway	= daddr;
@@ -1998,8 +2174,8 @@ local_input:
 		rth->rt_flags 	&= ~RTCF_LOCAL;
 	}
 	rth->rt_type	= res.type;
-	hash = rt_hash(daddr, saddr, fl.iif);
-	err = rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
+	hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
+	err = rt_intern_hash(hash, rth, &skb->rtable);
 	goto done;
 
 no_route:
@@ -2017,9 +2193,8 @@ martian_destination:
 	RT_CACHE_STAT_INC(in_martian_dst);
 #ifdef CONFIG_IP_ROUTE_VERBOSE
 	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
-		printk(KERN_WARNING "martian destination %u.%u.%u.%u from "
-			"%u.%u.%u.%u, dev %s\n",
-			NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
+		printk(KERN_WARNING "martian destination %pI4 from %pI4, dev %s\n",
+			&daddr, &saddr, dev->name);
 #endif
 
 e_hostunreach:
@@ -2045,29 +2220,38 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	struct rtable * rth;
 	unsigned	hash;
 	int iif = dev->ifindex;
+	struct net *net;
+
+	net = dev_net(dev);
+
+	if (!rt_caching(net))
+		goto skip_cache;
 
 	tos &= IPTOS_RT_MASK;
-	hash = rt_hash(daddr, saddr, iif);
+	hash = rt_hash(daddr, saddr, iif, rt_genid(net));
 
 	rcu_read_lock();
 	for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
 	     rth = rcu_dereference(rth->u.dst.rt_next)) {
-		if (rth->fl.fl4_dst == daddr &&
-		    rth->fl.fl4_src == saddr &&
-		    rth->fl.iif == iif &&
-		    rth->fl.oif == 0 &&
+		if (((rth->fl.fl4_dst ^ daddr) |
+		     (rth->fl.fl4_src ^ saddr) |
+		     (rth->fl.iif ^ iif) |
+		     rth->fl.oif |
+		     (rth->fl.fl4_tos ^ tos)) == 0 &&
 		    rth->fl.mark == skb->mark &&
-		    rth->fl.fl4_tos == tos) {
+		    net_eq(dev_net(rth->u.dst.dev), net) &&
+		    !rt_is_expired(rth)) {
 			dst_use(&rth->u.dst, jiffies);
 			RT_CACHE_STAT_INC(in_hit);
 			rcu_read_unlock();
-			skb->dst = (struct dst_entry*)rth;
+			skb->rtable = rth;
 			return 0;
 		}
 		RT_CACHE_STAT_INC(in_hlist_search);
 	}
 	rcu_read_unlock();
 
+skip_cache:
 	/* Multicast recognition logic is moved from route cache to here.
 	   The problem was that too many Ethernet cards have broken/missing
 	   hardware multicast filters :-( As result the host on multicasting
@@ -2079,7 +2263,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	   Note, that multicast routers are not affected, because
 	   route cache entry is created eventually.
 	 */
-	if (MULTICAST(daddr)) {
+	if (ipv4_is_multicast(daddr)) {
 		struct in_device *in_dev;
 
 		rcu_read_lock();
@@ -2088,7 +2272,8 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 				ip_hdr(skb)->protocol);
 			if (our
 #ifdef CONFIG_IP_MROUTE
-			    || (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
+			    || (!ipv4_is_local_multicast(daddr) &&
+				IN_DEV_MFORWARD(in_dev))
 #endif
 			    ) {
 				rcu_read_unlock();
@@ -2102,26 +2287,26 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	return ip_route_input_slow(skb, daddr, saddr, tos, dev);
 }
 
-static inline int __mkroute_output(struct rtable **result,
-				   struct fib_result* res,
-				   const struct flowi *fl,
-				   const struct flowi *oldflp,
-				   struct net_device *dev_out,
-				   unsigned flags)
+static int __mkroute_output(struct rtable **result,
+			    struct fib_result *res,
+			    const struct flowi *fl,
+			    const struct flowi *oldflp,
+			    struct net_device *dev_out,
+			    unsigned flags)
 {
 	struct rtable *rth;
 	struct in_device *in_dev;
 	u32 tos = RT_FL_TOS(oldflp);
 	int err = 0;
 
-	if (LOOPBACK(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK))
+	if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK))
 		return -EINVAL;
 
 	if (fl->fl4_dst == htonl(0xFFFFFFFF))
 		res->type = RTN_BROADCAST;
-	else if (MULTICAST(fl->fl4_dst))
+	else if (ipv4_is_multicast(fl->fl4_dst))
 		res->type = RTN_MULTICAST;
-	else if (BADCLASS(fl->fl4_dst) || ZERONET(fl->fl4_dst))
+	else if (ipv4_is_lbcast(fl->fl4_dst) || ipv4_is_zeronet(fl->fl4_dst))
 		return -EINVAL;
 
 	if (dev_out->flags & IFF_LOOPBACK)
@@ -2184,6 +2369,7 @@ static inline int __mkroute_output(struct rtable **result,
 	rth->rt_spec_dst= fl->fl4_src;
 
 	rth->u.dst.output=ip_output;
+	rth->rt_genid = rt_genid(dev_net(dev_out));
 
 	RT_CACHE_STAT_INC(out_slow_tot);
 
@@ -2201,7 +2387,7 @@ static inline int __mkroute_output(struct rtable **result,
 #ifdef CONFIG_IP_MROUTE
 		if (res->type == RTN_MULTICAST) {
 			if (IN_DEV_MFORWARD(in_dev) &&
-			    !LOCAL_MCAST(oldflp->fl4_dst)) {
+			    !ipv4_is_local_multicast(oldflp->fl4_dst)) {
 				rth->u.dst.input = ip_mr_input;
 				rth->u.dst.output = ip_mc_output;
 			}
@@ -2221,18 +2407,19 @@ static inline int __mkroute_output(struct rtable **result,
 	return err;
 }
 
-static inline int ip_mkroute_output(struct rtable **rp,
-				    struct fib_result* res,
-				    const struct flowi *fl,
-				    const struct flowi *oldflp,
-				    struct net_device *dev_out,
-				    unsigned flags)
+static int ip_mkroute_output(struct rtable **rp,
+			     struct fib_result *res,
+			     const struct flowi *fl,
+			     const struct flowi *oldflp,
+			     struct net_device *dev_out,
+			     unsigned flags)
 {
 	struct rtable *rth = NULL;
 	int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags);
 	unsigned hash;
 	if (err == 0) {
-		hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif);
+		hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif,
+			       rt_genid(dev_net(dev_out)));
 		err = rt_intern_hash(hash, rth, rp);
 	}
 
@@ -2243,7 +2430,8 @@ static inline int ip_mkroute_output(struct rtable **rp,
  * Major route resolver routine.
  */
 
-static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp)
+static int ip_route_output_slow(struct net *net, struct rtable **rp,
+				const struct flowi *oldflp)
 {
 	u32 tos	= RT_FL_TOS(oldflp);
 	struct flowi fl = { .nl_u = { .ip4_u =
@@ -2255,7 +2443,7 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp)
 						  RT_SCOPE_UNIVERSE),
 				      } },
 			    .mark = oldflp->mark,
-			    .iif = init_net.loopback_dev->ifindex,
+			    .iif = net->loopback_dev->ifindex,
 			    .oif = oldflp->oif };
 	struct fib_result res;
 	unsigned flags = 0;
@@ -2271,26 +2459,27 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp)
 
 	if (oldflp->fl4_src) {
 		err = -EINVAL;
-		if (MULTICAST(oldflp->fl4_src) ||
-		    BADCLASS(oldflp->fl4_src) ||
-		    ZERONET(oldflp->fl4_src))
-			goto out;
-
-		/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
-		dev_out = ip_dev_find(oldflp->fl4_src);
-		if (dev_out == NULL)
+		if (ipv4_is_multicast(oldflp->fl4_src) ||
+		    ipv4_is_lbcast(oldflp->fl4_src) ||
+		    ipv4_is_zeronet(oldflp->fl4_src))
 			goto out;
 
 		/* I removed check for oif == dev_out->oif here.
 		   It was wrong for two reasons:
-		   1. ip_dev_find(saddr) can return wrong iface, if saddr is
-		      assigned to multiple interfaces.
+		   1. ip_dev_find(net, saddr) can return wrong iface, if saddr
+		      is assigned to multiple interfaces.
 		   2. Moreover, we are allowed to send packets with saddr
 		      of another iface. --ANK
 		 */
 
 		if (oldflp->oif == 0
-		    && (MULTICAST(oldflp->fl4_dst) || oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
+		    && (ipv4_is_multicast(oldflp->fl4_dst) ||
+			oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
+			/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
+			dev_out = ip_dev_find(net, oldflp->fl4_src);
+			if (dev_out == NULL)
+				goto out;
+
 			/* Special hack: user can direct multicasts
 			   and limited broadcast via necessary interface
 			   without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
@@ -2309,14 +2498,20 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp)
 			fl.oif = dev_out->ifindex;
 			goto make_route;
 		}
-		if (dev_out)
+
+		if (!(oldflp->flags & FLOWI_FLAG_ANYSRC)) {
+			/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
+			dev_out = ip_dev_find(net, oldflp->fl4_src);
+			if (dev_out == NULL)
+				goto out;
 			dev_put(dev_out);
-		dev_out = NULL;
+			dev_out = NULL;
+		}
 	}
 
 
 	if (oldflp->oif) {
-		dev_out = dev_get_by_index(&init_net, oldflp->oif);
+		dev_out = dev_get_by_index(net, oldflp->oif);
 		err = -ENODEV;
 		if (dev_out == NULL)
 			goto out;
@@ -2327,14 +2522,15 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp)
 			goto out;	/* Wrong error code */
 		}
 
-		if (LOCAL_MCAST(oldflp->fl4_dst) || oldflp->fl4_dst == htonl(0xFFFFFFFF)) {
+		if (ipv4_is_local_multicast(oldflp->fl4_dst) ||
+		    oldflp->fl4_dst == htonl(0xFFFFFFFF)) {
 			if (!fl.fl4_src)
 				fl.fl4_src = inet_select_addr(dev_out, 0,
 							      RT_SCOPE_LINK);
 			goto make_route;
 		}
 		if (!fl.fl4_src) {
-			if (MULTICAST(oldflp->fl4_dst))
+			if (ipv4_is_multicast(oldflp->fl4_dst))
 				fl.fl4_src = inet_select_addr(dev_out, 0,
 							      fl.fl4_scope);
 			else if (!oldflp->fl4_dst)
@@ -2349,15 +2545,15 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp)
 			fl.fl4_dst = fl.fl4_src = htonl(INADDR_LOOPBACK);
 		if (dev_out)
 			dev_put(dev_out);
-		dev_out = init_net.loopback_dev;
+		dev_out = net->loopback_dev;
 		dev_hold(dev_out);
-		fl.oif = init_net.loopback_dev->ifindex;
+		fl.oif = net->loopback_dev->ifindex;
 		res.type = RTN_LOCAL;
 		flags |= RTCF_LOCAL;
 		goto make_route;
 	}
 
-	if (fib_lookup(&fl, &res)) {
+	if (fib_lookup(net, &fl, &res)) {
 		res.fi = NULL;
 		if (oldflp->oif) {
 			/* Apparently, routing tables are wrong. Assume,
@@ -2396,7 +2592,7 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp)
 			fl.fl4_src = fl.fl4_dst;
 		if (dev_out)
 			dev_put(dev_out);
-		dev_out = init_net.loopback_dev;
+		dev_out = net->loopback_dev;
 		dev_hold(dev_out);
 		fl.oif = dev_out->ifindex;
 		if (res.fi)
@@ -2412,7 +2608,7 @@ static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp)
 	else
 #endif
 	if (!res.prefixlen && res.type == RTN_UNICAST && !fl.oif)
-		fib_select_default(&fl, &res);
+		fib_select_default(net, &fl, &res);
 
 	if (!fl.fl4_src)
 		fl.fl4_src = FIB_RES_PREFSRC(res);
@@ -2435,12 +2631,16 @@ make_route:
 out:	return err;
 }
 
-int __ip_route_output_key(struct rtable **rp, const struct flowi *flp)
+int __ip_route_output_key(struct net *net, struct rtable **rp,
+			  const struct flowi *flp)
 {
 	unsigned hash;
 	struct rtable *rth;
 
-	hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif);
+	if (!rt_caching(net))
+		goto slow_output;
+
+	hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net));
 
 	rcu_read_lock_bh();
 	for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
@@ -2451,7 +2651,9 @@ int __ip_route_output_key(struct rtable **rp, const struct flowi *flp)
 		    rth->fl.oif == flp->oif &&
 		    rth->fl.mark == flp->mark &&
 		    !((rth->fl.fl4_tos ^ flp->fl4_tos) &
-			    (IPTOS_RT_MASK | RTO_ONLINK))) {
+			    (IPTOS_RT_MASK | RTO_ONLINK)) &&
+		    net_eq(dev_net(rth->u.dst.dev), net) &&
+		    !rt_is_expired(rth)) {
 			dst_use(&rth->u.dst, jiffies);
 			RT_CACHE_STAT_INC(out_hit);
 			rcu_read_unlock_bh();
@@ -2462,7 +2664,8 @@ int __ip_route_output_key(struct rtable **rp, const struct flowi *flp)
 	}
 	rcu_read_unlock_bh();
 
-	return ip_route_output_slow(rp, flp);
+slow_output:
+	return ip_route_output_slow(net, rp, flp);
 }
 
 EXPORT_SYMBOL_GPL(__ip_route_output_key);
@@ -2473,15 +2676,15 @@ static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
 
 static struct dst_ops ipv4_dst_blackhole_ops = {
 	.family			=	AF_INET,
-	.protocol		=	__constant_htons(ETH_P_IP),
+	.protocol		=	cpu_to_be16(ETH_P_IP),
 	.destroy		=	ipv4_dst_destroy,
 	.check			=	ipv4_dst_check,
 	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
-	.entry_size		=	sizeof(struct rtable),
+	.entries		=	ATOMIC_INIT(0),
 };
 
 
-static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp, struct sock *sk)
+static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi *flp)
 {
 	struct rtable *ort = *rp;
 	struct rtable *rt = (struct rtable *)
@@ -2505,6 +2708,7 @@ static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp, struct sock
 		rt->idev = ort->idev;
 		if (rt->idev)
 			in_dev_hold(rt->idev);
+		rt->rt_genid = rt_genid(net);
 		rt->rt_flags = ort->rt_flags;
 		rt->rt_type = ort->rt_type;
 		rt->rt_dst = ort->rt_dst;
@@ -2524,11 +2728,12 @@ static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp, struct sock
 	return (rt ? 0 : -ENOMEM);
 }
 
-int ip_route_output_flow(struct rtable **rp, struct flowi *flp, struct sock *sk, int flags)
+int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
+			 struct sock *sk, int flags)
 {
 	int err;
 
-	if ((err = __ip_route_output_key(rp, flp)) != 0)
+	if ((err = __ip_route_output_key(net, rp, flp)) != 0)
 		return err;
 
 	if (flp->proto) {
@@ -2536,10 +2741,10 @@ int ip_route_output_flow(struct rtable **rp, struct flowi *flp, struct sock *sk,
 			flp->fl4_src = (*rp)->rt_src;
 		if (!flp->fl4_dst)
 			flp->fl4_dst = (*rp)->rt_dst;
-		err = __xfrm_lookup((struct dst_entry **)rp, flp, sk,
+		err = __xfrm_lookup(net, (struct dst_entry **)rp, flp, sk,
 				    flags ? XFRM_LOOKUP_WAIT : 0);
 		if (err == -EREMOTE)
-			err = ipv4_dst_blackhole(rp, flp, sk);
+			err = ipv4_dst_blackhole(net, rp, flp);
 
 		return err;
 	}
@@ -2549,15 +2754,16 @@ int ip_route_output_flow(struct rtable **rp, struct flowi *flp, struct sock *sk,
 
 EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
-int ip_route_output_key(struct rtable **rp, struct flowi *flp)
+int ip_route_output_key(struct net *net, struct rtable **rp, struct flowi *flp)
 {
-	return ip_route_output_flow(rp, flp, NULL, 0);
+	return ip_route_output_flow(net, rp, flp, NULL, 0);
 }
 
-static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
+static int rt_fill_info(struct net *net,
+			struct sk_buff *skb, u32 pid, u32 seq, int event,
 			int nowait, unsigned int flags)
 {
-	struct rtable *rt = (struct rtable*)skb->dst;
+	struct rtable *rt = skb->rtable;
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
 	long expires;
@@ -2618,9 +2824,9 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 #ifdef CONFIG_IP_MROUTE
 		__be32 dst = rt->rt_dst;
 
-		if (MULTICAST(dst) && !LOCAL_MCAST(dst) &&
-		    IPV4_DEVCONF_ALL(MC_FORWARDING)) {
-			int err = ipmr_get_route(skb, r, nowait);
+		if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
+		    IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
+			int err = ipmr_get_route(net, skb, r, nowait);
 			if (err <= 0) {
 				if (!nowait) {
 					if (err == 0)
@@ -2650,7 +2856,7 @@ nla_put_failure:
 
 static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
 {
-	struct net *net = in_skb->sk->sk_net;
+	struct net *net = sock_net(in_skb->sk);
 	struct rtmsg *rtm;
 	struct nlattr *tb[RTA_MAX+1];
 	struct rtable *rt = NULL;
@@ -2660,9 +2866,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 	int err;
 	struct sk_buff *skb;
 
-	if (net != &init_net)
-		return -EINVAL;
-
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
 	if (err < 0)
 		goto errout;
@@ -2692,7 +2895,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 	if (iif) {
 		struct net_device *dev;
 
-		dev = __dev_get_by_index(&init_net, iif);
+		dev = __dev_get_by_index(net, iif);
 		if (dev == NULL) {
 			err = -ENODEV;
 			goto errout_free;
@@ -2704,7 +2907,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 		err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
 		local_bh_enable();
 
-		rt = (struct rtable*) skb->dst;
+		rt = skb->rtable;
 		if (err == 0 && rt->u.dst.error)
 			err = -rt->u.dst.error;
 	} else {
@@ -2718,22 +2921,22 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 			},
 			.oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
 		};
-		err = ip_route_output_key(&rt, &fl);
+		err = ip_route_output_key(net, &rt, &fl);
 	}
 
 	if (err)
 		goto errout_free;
 
-	skb->dst = &rt->u.dst;
+	skb->rtable = rt;
 	if (rtm->rtm_flags & RTM_F_NOTIFY)
 		rt->rt_flags |= RTCF_NOTIFY;
 
-	err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
-				RTM_NEWROUTE, 0, 0);
+	err = rt_fill_info(net, skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
+			   RTM_NEWROUTE, 0, 0);
 	if (err <= 0)
 		goto errout_free;
 
-	err = rtnl_unicast(skb, &init_net, NETLINK_CB(in_skb).pid);
+	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
 errout:
 	return err;
 
@@ -2747,19 +2950,26 @@ int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
 	struct rtable *rt;
 	int h, s_h;
 	int idx, s_idx;
+	struct net *net;
+
+	net = sock_net(skb->sk);
 
 	s_h = cb->args[0];
 	if (s_h < 0)
 		s_h = 0;
 	s_idx = idx = cb->args[1];
-	for (h = s_h; h <= rt_hash_mask; h++) {
+	for (h = s_h; h <= rt_hash_mask; h++, s_idx = 0) {
+		if (!rt_hash_table[h].chain)
+			continue;
 		rcu_read_lock_bh();
 		for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt;
 		     rt = rcu_dereference(rt->u.dst.rt_next), idx++) {
-			if (idx < s_idx)
+			if (!net_eq(dev_net(rt->u.dst.dev), net) || idx < s_idx)
+				continue;
+			if (rt_is_expired(rt))
 				continue;
 			skb->dst = dst_clone(&rt->u.dst);
-			if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid,
+			if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid,
 					 cb->nlh->nlmsg_seq, RTM_NEWROUTE,
 					 1, NLM_F_MULTI) <= 0) {
 				dst_release(xchg(&skb->dst, NULL));
@@ -2769,7 +2979,6 @@ int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
 			dst_release(xchg(&skb->dst, NULL));
 		}
 		rcu_read_unlock_bh();
-		s_idx = 0;
 	}
 
 done:
@@ -2780,19 +2989,25 @@ done:
 
 void ip_rt_multicast_event(struct in_device *in_dev)
 {
-	rt_cache_flush(0);
+	rt_cache_flush(dev_net(in_dev->dev), 0);
 }
 
 #ifdef CONFIG_SYSCTL
-static int flush_delay;
-
-static int ipv4_sysctl_rtcache_flush(ctl_table *ctl, int write,
+static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
 					struct file *filp, void __user *buffer,
 					size_t *lenp, loff_t *ppos)
 {
 	if (write) {
-		proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
-		rt_cache_flush(flush_delay);
+		int flush_delay;
+		ctl_table ctl;
+		struct net *net;
+
+		memcpy(&ctl, __ctl, sizeof(ctl));
+		ctl.data = &flush_delay;
+		proc_dointvec(&ctl, write, filp, buffer, lenp, ppos);
+
+		net = (struct net *)__ctl->extra1;
+		rt_cache_flush(net, flush_delay);
 		return 0;
 	}
 
@@ -2800,57 +3015,89 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *ctl, int write,
 }
 
 static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table,
-						int __user *name,
-						int nlen,
 						void __user *oldval,
 						size_t __user *oldlenp,
 						void __user *newval,
 						size_t newlen)
 {
 	int delay;
+	struct net *net;
 	if (newlen != sizeof(int))
 		return -EINVAL;
 	if (get_user(delay, (int __user *)newval))
 		return -EFAULT;
-	rt_cache_flush(delay);
+	net = (struct net *)table->extra1;
+	rt_cache_flush(net, delay);
 	return 0;
 }
 
-ctl_table ipv4_route_table[] = {
-	{
-		.ctl_name 	= NET_IPV4_ROUTE_FLUSH,
-		.procname	= "flush",
-		.data		= &flush_delay,
-		.maxlen		= sizeof(int),
-		.mode		= 0200,
-		.proc_handler	= &ipv4_sysctl_rtcache_flush,
-		.strategy	= &ipv4_sysctl_rtcache_flush_strategy,
-	},
-	{
-		.ctl_name	= NET_IPV4_ROUTE_MIN_DELAY,
-		.procname	= "min_delay",
-		.data		= &ip_rt_min_delay,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_jiffies,
-		.strategy	= &sysctl_jiffies,
-	},
-	{
-		.ctl_name	= NET_IPV4_ROUTE_MAX_DELAY,
-		.procname	= "max_delay",
-		.data		= &ip_rt_max_delay,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_jiffies,
-		.strategy	= &sysctl_jiffies,
-	},
+static void rt_secret_reschedule(int old)
+{
+	struct net *net;
+	int new = ip_rt_secret_interval;
+	int diff = new - old;
+
+	if (!diff)
+		return;
+
+	rtnl_lock();
+	for_each_net(net) {
+		int deleted = del_timer_sync(&net->ipv4.rt_secret_timer);
+
+		if (!new)
+			continue;
+
+		if (deleted) {
+			long time = net->ipv4.rt_secret_timer.expires - jiffies;
+
+			if (time <= 0 || (time += diff) <= 0)
+				time = 0;
+
+			net->ipv4.rt_secret_timer.expires = time;
+		} else
+			net->ipv4.rt_secret_timer.expires = new;
+
+		net->ipv4.rt_secret_timer.expires += jiffies;
+		add_timer(&net->ipv4.rt_secret_timer);
+	}
+	rtnl_unlock();
+}
+
+static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write,
+					  struct file *filp,
+					  void __user *buffer, size_t *lenp,
+					  loff_t *ppos)
+{
+	int old = ip_rt_secret_interval;
+	int ret = proc_dointvec_jiffies(ctl, write, filp, buffer, lenp, ppos);
+
+	rt_secret_reschedule(old);
+
+	return ret;
+}
+
+static int ipv4_sysctl_rt_secret_interval_strategy(ctl_table *table,
+						   void __user *oldval,
+						   size_t __user *oldlenp,
+						   void __user *newval,
+						   size_t newlen)
+{
+	int old = ip_rt_secret_interval;
+	int ret = sysctl_jiffies(table, oldval, oldlenp, newval, newlen);
+
+	rt_secret_reschedule(old);
+
+	return ret;
+}
+
+static ctl_table ipv4_route_table[] = {
 	{
 		.ctl_name	= NET_IPV4_ROUTE_GC_THRESH,
 		.procname	= "gc_thresh",
 		.data		= &ipv4_dst_ops.gc_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_MAX_SIZE,
@@ -2858,7 +3105,7 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_max_size,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		/*  Deprecated. Use gc_min_interval_ms */
@@ -2868,8 +3115,8 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_gc_min_interval,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_jiffies,
-		.strategy	= &sysctl_jiffies,
+		.proc_handler	= proc_dointvec_jiffies,
+		.strategy	= sysctl_jiffies,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS,
@@ -2877,8 +3124,8 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_gc_min_interval,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_ms_jiffies,
-		.strategy	= &sysctl_ms_jiffies,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+		.strategy	= sysctl_ms_jiffies,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_GC_TIMEOUT,
@@ -2886,8 +3133,8 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_gc_timeout,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_jiffies,
-		.strategy	= &sysctl_jiffies,
+		.proc_handler	= proc_dointvec_jiffies,
+		.strategy	= sysctl_jiffies,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_GC_INTERVAL,
@@ -2895,8 +3142,8 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_gc_interval,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_jiffies,
-		.strategy	= &sysctl_jiffies,
+		.proc_handler	= proc_dointvec_jiffies,
+		.strategy	= sysctl_jiffies,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_REDIRECT_LOAD,
@@ -2904,7 +3151,7 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_redirect_load,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_REDIRECT_NUMBER,
@@ -2912,7 +3159,7 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_redirect_number,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_REDIRECT_SILENCE,
@@ -2920,7 +3167,7 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_redirect_silence,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_ERROR_COST,
@@ -2928,7 +3175,7 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_error_cost,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_ERROR_BURST,
@@ -2936,7 +3183,7 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_error_burst,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_GC_ELASTICITY,
@@ -2944,7 +3191,7 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_gc_elasticity,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_MTU_EXPIRES,
@@ -2952,8 +3199,8 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_mtu_expires,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_jiffies,
-		.strategy	= &sysctl_jiffies,
+		.proc_handler	= proc_dointvec_jiffies,
+		.strategy	= sysctl_jiffies,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_MIN_PMTU,
@@ -2961,7 +3208,7 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_min_pmtu,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_MIN_ADVMSS,
@@ -2969,7 +3216,7 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_min_advmss,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.ctl_name	= NET_IPV4_ROUTE_SECRET_INTERVAL,
@@ -2977,13 +3224,120 @@ ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_secret_interval,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_jiffies,
-		.strategy	= &sysctl_jiffies,
+		.proc_handler	= ipv4_sysctl_rt_secret_interval,
+		.strategy	= ipv4_sysctl_rt_secret_interval_strategy,
 	},
 	{ .ctl_name = 0 }
 };
+
+static struct ctl_table empty[1];
+
+static struct ctl_table ipv4_skeleton[] =
+{
+	{ .procname = "route", .ctl_name = NET_IPV4_ROUTE,
+	  .mode = 0555, .child = ipv4_route_table},
+	{ .procname = "neigh", .ctl_name = NET_IPV4_NEIGH,
+	  .mode = 0555, .child = empty},
+	{ }
+};
+
+static __net_initdata struct ctl_path ipv4_path[] = {
+	{ .procname = "net", .ctl_name = CTL_NET, },
+	{ .procname = "ipv4", .ctl_name = NET_IPV4, },
+	{ },
+};
+
+static struct ctl_table ipv4_route_flush_table[] = {
+	{
+		.ctl_name 	= NET_IPV4_ROUTE_FLUSH,
+		.procname	= "flush",
+		.maxlen		= sizeof(int),
+		.mode		= 0200,
+		.proc_handler	= ipv4_sysctl_rtcache_flush,
+		.strategy	= ipv4_sysctl_rtcache_flush_strategy,
+	},
+	{ .ctl_name = 0 },
+};
+
+static __net_initdata struct ctl_path ipv4_route_path[] = {
+	{ .procname = "net", .ctl_name = CTL_NET, },
+	{ .procname = "ipv4", .ctl_name = NET_IPV4, },
+	{ .procname = "route", .ctl_name = NET_IPV4_ROUTE, },
+	{ },
+};
+
+static __net_init int sysctl_route_net_init(struct net *net)
+{
+	struct ctl_table *tbl;
+
+	tbl = ipv4_route_flush_table;
+	if (net != &init_net) {
+		tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL);
+		if (tbl == NULL)
+			goto err_dup;
+	}
+	tbl[0].extra1 = net;
+
+	net->ipv4.route_hdr =
+		register_net_sysctl_table(net, ipv4_route_path, tbl);
+	if (net->ipv4.route_hdr == NULL)
+		goto err_reg;
+	return 0;
+
+err_reg:
+	if (tbl != ipv4_route_flush_table)
+		kfree(tbl);
+err_dup:
+	return -ENOMEM;
+}
+
+static __net_exit void sysctl_route_net_exit(struct net *net)
+{
+	struct ctl_table *tbl;
+
+	tbl = net->ipv4.route_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->ipv4.route_hdr);
+	BUG_ON(tbl == ipv4_route_flush_table);
+	kfree(tbl);
+}
+
+static __net_initdata struct pernet_operations sysctl_route_ops = {
+	.init = sysctl_route_net_init,
+	.exit = sysctl_route_net_exit,
+};
 #endif
 
+
+static __net_init int rt_secret_timer_init(struct net *net)
+{
+	atomic_set(&net->ipv4.rt_genid,
+			(int) ((num_physpages ^ (num_physpages>>8)) ^
+			(jiffies ^ (jiffies >> 7))));
+
+	net->ipv4.rt_secret_timer.function = rt_secret_rebuild;
+	net->ipv4.rt_secret_timer.data = (unsigned long)net;
+	init_timer_deferrable(&net->ipv4.rt_secret_timer);
+
+	if (ip_rt_secret_interval) {
+		net->ipv4.rt_secret_timer.expires =
+			jiffies + net_random() % ip_rt_secret_interval +
+			ip_rt_secret_interval;
+		add_timer(&net->ipv4.rt_secret_timer);
+	}
+	return 0;
+}
+
+static __net_exit void rt_secret_timer_exit(struct net *net)
+{
+	del_timer_sync(&net->ipv4.rt_secret_timer);
+}
+
+static __net_initdata struct pernet_operations rt_secret_timer_ops = {
+	.init = rt_secret_timer_init,
+	.exit = rt_secret_timer_exit,
+};
+
+
 #ifdef CONFIG_NET_CLS_ROUTE
 struct ip_rt_acct *ip_rt_acct __read_mostly;
 #endif /* CONFIG_NET_CLS_ROUTE */
@@ -3002,11 +3356,8 @@ int __init ip_rt_init(void)
 {
 	int rc = 0;
 
-	rt_hash_rnd = (int) ((num_physpages ^ (num_physpages>>8)) ^
-			     (jiffies ^ (jiffies >> 7)));
-
 #ifdef CONFIG_NET_CLS_ROUTE
-	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct));
+	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
 		panic("IP: failed to allocate ip_rt_acct\n");
 #endif
@@ -3026,7 +3377,7 @@ int __init ip_rt_init(void)
 					0,
 					&rt_hash_log,
 					&rt_hash_mask,
-					0);
+					rhash_entries ? 0 : 512 * 1024);
 	memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
 	rt_hash_lock_init();
 
@@ -3036,20 +3387,16 @@ int __init ip_rt_init(void)
 	devinet_init();
 	ip_fib_init();
 
-	setup_timer(&rt_flush_timer, rt_run_flush, 0);
-	setup_timer(&rt_secret_timer, rt_secret_rebuild, 0);
-
 	/* All the timers, started at system startup tend
 	   to synchronize. Perturb it a bit.
 	 */
 	schedule_delayed_work(&expires_work,
 		net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
 
-	rt_secret_timer.expires = jiffies + net_random() % ip_rt_secret_interval +
-		ip_rt_secret_interval;
-	add_timer(&rt_secret_timer);
+	if (register_pernet_subsys(&rt_secret_timer_ops))
+		printk(KERN_ERR "Unable to setup rt_secret_timer\n");
 
-	if (ip_rt_proc_init(&init_net))
+	if (ip_rt_proc_init())
 		printk(KERN_ERR "Unable to create route proc files\n");
 #ifdef CONFIG_XFRM
 	xfrm_init();
@@ -3057,9 +3404,23 @@ int __init ip_rt_init(void)
 #endif
 	rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL);
 
+#ifdef CONFIG_SYSCTL
+	register_pernet_subsys(&sysctl_route_ops);
+#endif
 	return rc;
 }
 
+#ifdef CONFIG_SYSCTL
+/*
+ * We really need to sanitize the damn ipv4 init order, then all
+ * this nonsense will go away.
+ */
+void __init ip_static_sysctl_init(void)
+{
+	register_sysctl_paths(ipv4_path, ipv4_skeleton);
+}
+#endif
+
 EXPORT_SYMBOL(__ip_select_ident);
 EXPORT_SYMBOL(ip_route_input);
 EXPORT_SYMBOL(ip_route_output_key);