1 files changed, 698 insertions, 704 deletions

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 186f20c4a45..b10cd43a472 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -5,8 +5,6 @@
  *
  *		IPv4 Forwarding Information Base: semantics.
  *
- * Version:	$Id: fib_semantics.c,v 1.19 2002/01/12 07:54:56 davem Exp $
- *
  * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
  *
  *		This program is free software; you can redistribute it and/or
@@ -15,9 +13,7 @@
  *		2 of the License, or (at your option) any later version.
  */
 
-#include <linux/config.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -29,29 +25,30 @@
 #include <linux/errno.h>
 #include <linux/in.h>
 #include <linux/inet.h>
+#include <linux/inetdevice.h>
 #include <linux/netdevice.h>
 #include <linux/if_arp.h>
 #include <linux/proc_fs.h>
 #include <linux/skbuff.h>
-#include <linux/netlink.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 
+#include <net/arp.h>
 #include <net/ip.h>
 #include <net/protocol.h>
 #include <net/route.h>
 #include <net/tcp.h>
 #include <net/sock.h>
 #include <net/ip_fib.h>
-#include <net/ip_mp_alg.h>
+#include <net/netlink.h>
+#include <net/nexthop.h>
 
 #include "fib_lookup.h"
 
-#define FSprintk(a...)
-
-static DEFINE_RWLOCK(fib_info_lock);
+static DEFINE_SPINLOCK(fib_info_lock);
 static struct hlist_head *fib_info_hash;
 static struct hlist_head *fib_info_laddrhash;
-static unsigned int fib_hash_size;
+static unsigned int fib_info_hash_size;
 static unsigned int fib_info_cnt;
 
 #define DEVINDEX_HASHBITS 8
@@ -62,119 +59,199 @@ static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];
 
 static DEFINE_SPINLOCK(fib_multipath_lock);
 
-#define for_nexthops(fi) { int nhsel; const struct fib_nh * nh; \
-for (nhsel=0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++)
+#define for_nexthops(fi) {						\
+	int nhsel; const struct fib_nh *nh;				\
+	for (nhsel = 0, nh = (fi)->fib_nh;				\
+	     nhsel < (fi)->fib_nhs;					\
+	     nh++, nhsel++)
 
-#define change_nexthops(fi) { int nhsel; struct fib_nh * nh; \
-for (nhsel=0, nh = (struct fib_nh*)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++)
+#define change_nexthops(fi) {						\
+	int nhsel; struct fib_nh *nexthop_nh;				\
+	for (nhsel = 0,	nexthop_nh = (struct fib_nh *)((fi)->fib_nh);	\
+	     nhsel < (fi)->fib_nhs;					\
+	     nexthop_nh++, nhsel++)
 
 #else /* CONFIG_IP_ROUTE_MULTIPATH */
 
 /* Hope, that gcc will optimize it to get rid of dummy loop */
 
-#define for_nexthops(fi) { int nhsel=0; const struct fib_nh * nh = (fi)->fib_nh; \
-for (nhsel=0; nhsel < 1; nhsel++)
+#define for_nexthops(fi) {						\
+	int nhsel; const struct fib_nh *nh = (fi)->fib_nh;		\
+	for (nhsel = 0; nhsel < 1; nhsel++)
 
-#define change_nexthops(fi) { int nhsel=0; struct fib_nh * nh = (struct fib_nh*)((fi)->fib_nh); \
-for (nhsel=0; nhsel < 1; nhsel++)
+#define change_nexthops(fi) {						\
+	int nhsel;							\
+	struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh);	\
+	for (nhsel = 0; nhsel < 1; nhsel++)
 
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
 
 #define endfor_nexthops(fi) }
 
 
-static struct 
-{
-	int	error;
-	u8	scope;
-} fib_props[RTA_MAX + 1] = {
-        {
+const struct fib_prop fib_props[RTN_MAX + 1] = {
+	[RTN_UNSPEC] = {
 		.error	= 0,
 		.scope	= RT_SCOPE_NOWHERE,
-	},	/* RTN_UNSPEC */
-	{
+	},
+	[RTN_UNICAST] = {
 		.error	= 0,
 		.scope	= RT_SCOPE_UNIVERSE,
-	},	/* RTN_UNICAST */
-	{
+	},
+	[RTN_LOCAL] = {
 		.error	= 0,
 		.scope	= RT_SCOPE_HOST,
-	},	/* RTN_LOCAL */
-	{
+	},
+	[RTN_BROADCAST] = {
 		.error	= 0,
 		.scope	= RT_SCOPE_LINK,
-	},	/* RTN_BROADCAST */
-	{
+	},
+	[RTN_ANYCAST] = {
 		.error	= 0,
 		.scope	= RT_SCOPE_LINK,
-	},	/* RTN_ANYCAST */
-	{
+	},
+	[RTN_MULTICAST] = {
 		.error	= 0,
 		.scope	= RT_SCOPE_UNIVERSE,
-	},	/* RTN_MULTICAST */
-	{
+	},
+	[RTN_BLACKHOLE] = {
 		.error	= -EINVAL,
 		.scope	= RT_SCOPE_UNIVERSE,
-	},	/* RTN_BLACKHOLE */
-	{
+	},
+	[RTN_UNREACHABLE] = {
 		.error	= -EHOSTUNREACH,
 		.scope	= RT_SCOPE_UNIVERSE,
-	},	/* RTN_UNREACHABLE */
-	{
+	},
+	[RTN_PROHIBIT] = {
 		.error	= -EACCES,
 		.scope	= RT_SCOPE_UNIVERSE,
-	},	/* RTN_PROHIBIT */
-	{
+	},
+	[RTN_THROW] = {
 		.error	= -EAGAIN,
 		.scope	= RT_SCOPE_UNIVERSE,
-	},	/* RTN_THROW */
-	{
+	},
+	[RTN_NAT] = {
 		.error	= -EINVAL,
 		.scope	= RT_SCOPE_NOWHERE,
-	},	/* RTN_NAT */
-	{
+	},
+	[RTN_XRESOLVE] = {
 		.error	= -EINVAL,
 		.scope	= RT_SCOPE_NOWHERE,
-	},	/* RTN_XRESOLVE */
+	},
 };
 
+static void rt_fibinfo_free(struct rtable __rcu **rtp)
+{
+	struct rtable *rt = rcu_dereference_protected(*rtp, 1);
+
+	if (!rt)
+		return;
+
+	/* Not even needed : RCU_INIT_POINTER(*rtp, NULL);
+	 * because we waited an RCU grace period before calling
+	 * free_fib_info_rcu()
+	 */
+
+	dst_free(&rt->dst);
+}
+
+static void free_nh_exceptions(struct fib_nh *nh)
+{
+	struct fnhe_hash_bucket *hash = nh->nh_exceptions;
+	int i;
+
+	for (i = 0; i < FNHE_HASH_SIZE; i++) {
+		struct fib_nh_exception *fnhe;
+
+		fnhe = rcu_dereference_protected(hash[i].chain, 1);
+		while (fnhe) {
+			struct fib_nh_exception *next;
+			
+			next = rcu_dereference_protected(fnhe->fnhe_next, 1);
+
+			rt_fibinfo_free(&fnhe->fnhe_rth_input);
+			rt_fibinfo_free(&fnhe->fnhe_rth_output);
+
+			kfree(fnhe);
+
+			fnhe = next;
+		}
+	}
+	kfree(hash);
+}
+
+static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
+{
+	int cpu;
+
+	if (!rtp)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct rtable *rt;
+
+		rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1);
+		if (rt)
+			dst_free(&rt->dst);
+	}
+	free_percpu(rtp);
+}
 
 /* Release a nexthop info record */
+static void free_fib_info_rcu(struct rcu_head *head)
+{
+	struct fib_info *fi = container_of(head, struct fib_info, rcu);
+
+	change_nexthops(fi) {
+		if (nexthop_nh->nh_dev)
+			dev_put(nexthop_nh->nh_dev);
+		if (nexthop_nh->nh_exceptions)
+			free_nh_exceptions(nexthop_nh);
+		rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
+		rt_fibinfo_free(&nexthop_nh->nh_rth_input);
+	} endfor_nexthops(fi);
+
+	release_net(fi->fib_net);
+	if (fi->fib_metrics != (u32 *) dst_default_metrics)
+		kfree(fi->fib_metrics);
+	kfree(fi);
+}
 
 void free_fib_info(struct fib_info *fi)
 {
 	if (fi->fib_dead == 0) {
-		printk("Freeing alive fib_info %p\n", fi);
+		pr_warn("Freeing alive fib_info %p\n", fi);
 		return;
 	}
+	fib_info_cnt--;
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	change_nexthops(fi) {
-		if (nh->nh_dev)
-			dev_put(nh->nh_dev);
-		nh->nh_dev = NULL;
+		if (nexthop_nh->nh_tclassid)
+			fi->fib_net->ipv4.fib_num_tclassid_users--;
 	} endfor_nexthops(fi);
-	fib_info_cnt--;
-	kfree(fi);
+#endif
+	call_rcu(&fi->rcu, free_fib_info_rcu);
 }
 
 void fib_release_info(struct fib_info *fi)
 {
-	write_lock(&fib_info_lock);
+	spin_lock_bh(&fib_info_lock);
 	if (fi && --fi->fib_treeref == 0) {
 		hlist_del(&fi->fib_hash);
 		if (fi->fib_prefsrc)
 			hlist_del(&fi->fib_lhash);
 		change_nexthops(fi) {
-			if (!nh->nh_dev)
+			if (!nexthop_nh->nh_dev)
 				continue;
-			hlist_del(&nh->nh_hash);
+			hlist_del(&nexthop_nh->nh_hash);
 		} endfor_nexthops(fi)
 		fi->fib_dead = 1;
 		fib_info_put(fi);
 	}
-	write_unlock(&fib_info_lock);
+	spin_unlock_bh(&fib_info_lock);
 }
 
-static __inline__ int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
+static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
 {
 	const struct fib_nh *onh = ofi->fib_nh;
 
@@ -185,24 +262,36 @@ static __inline__ int nh_comp(const struct fib_info *fi, const struct fib_info *
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 		    nh->nh_weight != onh->nh_weight ||
 #endif
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		    nh->nh_tclassid != onh->nh_tclassid ||
 #endif
-		    ((nh->nh_flags^onh->nh_flags)&~RTNH_F_DEAD))
+		    ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_F_DEAD))
 			return -1;
 		onh++;
 	} endfor_nexthops(fi);
 	return 0;
 }
 
+static inline unsigned int fib_devindex_hashfn(unsigned int val)
+{
+	unsigned int mask = DEVINDEX_HASHSIZE - 1;
+
+	return (val ^
+		(val >> DEVINDEX_HASHBITS) ^
+		(val >> (DEVINDEX_HASHBITS * 2))) & mask;
+}
+
 static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
 {
-	unsigned int mask = (fib_hash_size - 1);
+	unsigned int mask = (fib_info_hash_size - 1);
 	unsigned int val = fi->fib_nhs;
 
-	val ^= fi->fib_protocol;
-	val ^= fi->fib_prefsrc;
+	val ^= (fi->fib_protocol << 8) | fi->fib_scope;
+	val ^= (__force u32)fi->fib_prefsrc;
 	val ^= fi->fib_priority;
+	for_nexthops(fi) {
+		val ^= fib_devindex_hashfn(nh->nh_oif);
+	} endfor_nexthops(fi)
 
 	return (val ^ (val >> 7) ^ (val >> 12)) & mask;
 }
@@ -210,22 +299,25 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
 static struct fib_info *fib_find_info(const struct fib_info *nfi)
 {
 	struct hlist_head *head;
-	struct hlist_node *node;
 	struct fib_info *fi;
 	unsigned int hash;
 
 	hash = fib_info_hashfn(nfi);
 	head = &fib_info_hash[hash];
 
-	hlist_for_each_entry(fi, node, head, fib_hash) {
+	hlist_for_each_entry(fi, head, fib_hash) {
+		if (!net_eq(fi->fib_net, nfi->fib_net))
+			continue;
 		if (fi->fib_nhs != nfi->fib_nhs)
 			continue;
 		if (nfi->fib_protocol == fi->fib_protocol &&
+		    nfi->fib_scope == fi->fib_scope &&
 		    nfi->fib_prefsrc == fi->fib_prefsrc &&
 		    nfi->fib_priority == fi->fib_priority &&
+		    nfi->fib_type == fi->fib_type &&
 		    memcmp(nfi->fib_metrics, fi->fib_metrics,
-			   sizeof(fi->fib_metrics)) == 0 &&
-		    ((nfi->fib_flags^fi->fib_flags)&~RTNH_F_DEAD) == 0 &&
+			   sizeof(u32) * RTAX_MAX) == 0 &&
+		    ((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_F_DEAD) == 0 &&
 		    (nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0))
 			return fi;
 	}
@@ -233,69 +325,87 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi)
 	return NULL;
 }
 
-static inline unsigned int fib_devindex_hashfn(unsigned int val)
-{
-	unsigned int mask = DEVINDEX_HASHSIZE - 1;
-
-	return (val ^
-		(val >> DEVINDEX_HASHBITS) ^
-		(val >> (DEVINDEX_HASHBITS * 2))) & mask;
-}
-
 /* Check, that the gateway is already configured.
-   Used only by redirect accept routine.
+ * Used only by redirect accept routine.
  */
-
-int ip_fib_check_default(u32 gw, struct net_device *dev)
+int ip_fib_check_default(__be32 gw, struct net_device *dev)
 {
 	struct hlist_head *head;
-	struct hlist_node *node;
 	struct fib_nh *nh;
 	unsigned int hash;
 
-	read_lock(&fib_info_lock);
+	spin_lock(&fib_info_lock);
 
 	hash = fib_devindex_hashfn(dev->ifindex);
 	head = &fib_info_devhash[hash];
-	hlist_for_each_entry(nh, node, head, nh_hash) {
+	hlist_for_each_entry(nh, head, nh_hash) {
 		if (nh->nh_dev == dev &&
 		    nh->nh_gw == gw &&
-		    !(nh->nh_flags&RTNH_F_DEAD)) {
-			read_unlock(&fib_info_lock);
+		    !(nh->nh_flags & RTNH_F_DEAD)) {
+			spin_unlock(&fib_info_lock);
 			return 0;
 		}
 	}
 
-	read_unlock(&fib_info_lock);
+	spin_unlock(&fib_info_lock);
 
 	return -1;
 }
 
-void rtmsg_fib(int event, u32 key, struct fib_alias *fa,
-	       int z, int tb_id,
-	       struct nlmsghdr *n, struct netlink_skb_parms *req)
+static inline size_t fib_nlmsg_size(struct fib_info *fi)
 {
-	struct sk_buff *skb;
-	u32 pid = req ? req->pid : n->nlmsg_pid;
-	int size = NLMSG_SPACE(sizeof(struct rtmsg)+256);
+	size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
+			 + nla_total_size(4) /* RTA_TABLE */
+			 + nla_total_size(4) /* RTA_DST */
+			 + nla_total_size(4) /* RTA_PRIORITY */
+			 + nla_total_size(4); /* RTA_PREFSRC */
 
-	skb = alloc_skb(size, GFP_KERNEL);
-	if (!skb)
-		return;
+	/* space for nested metrics */
+	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
+
+	if (fi->fib_nhs) {
+		/* Also handles the special case fib_nhs == 1 */
+
+		/* each nexthop is packed in an attribute */
+		size_t nhsize = nla_total_size(sizeof(struct rtnexthop));
+
+		/* may contain flow and gateway attribute */
+		nhsize += 2 * nla_total_size(4);
+
+		/* all nexthops are packed in a nested attribute */
+		payload += nla_total_size(fi->fib_nhs * nhsize);
+	}
 
-	if (fib_dump_info(skb, pid, n->nlmsg_seq, event, tb_id,
-			  fa->fa_type, fa->fa_scope, &key, z,
-			  fa->fa_tos,
-			  fa->fa_info, 0) < 0) {
+	return payload;
+}
+
+void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
+	       int dst_len, u32 tb_id, const struct nl_info *info,
+	       unsigned int nlm_flags)
+{
+	struct sk_buff *skb;
+	u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
+	int err = -ENOBUFS;
+
+	skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL);
+	if (skb == NULL)
+		goto errout;
+
+	err = fib_dump_info(skb, info->portid, seq, event, tb_id,
+			    fa->fa_type, key, dst_len,
+			    fa->fa_tos, fa->fa_info, nlm_flags);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
+		WARN_ON(err == -EMSGSIZE);
 		kfree_skb(skb);
-		return;
+		goto errout;
 	}
-	NETLINK_CB(skb).dst_group = RTNLGRP_IPV4_ROUTE;
-	if (n->nlmsg_flags&NLM_F_ECHO)
-		atomic_inc(&skb->users);
-	netlink_broadcast(rtnl, skb, pid, RTNLGRP_IPV4_ROUTE, GFP_KERNEL);
-	if (n->nlmsg_flags&NLM_F_ECHO)
-		netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT);
+	rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_IPV4_ROUTE,
+		    info->nlh, GFP_KERNEL);
+	return;
+errout:
+	if (err < 0)
+		rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
 }
 
 /* Return the first fib alias matching TOS with
@@ -316,8 +426,9 @@ struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio)
 	return NULL;
 }
 
-int fib_detect_death(struct fib_info *fi, int order,
-		     struct fib_info **last_resort, int *last_idx, int *dflt)
+static int fib_detect_death(struct fib_info *fi, int order,
+			    struct fib_info **last_resort, int *last_idx,
+			    int dflt)
 {
 	struct neighbour *n;
 	int state = NUD_NONE;
@@ -327,12 +438,12 @@ int fib_detect_death(struct fib_info *fi, int order,
 		state = n->nud_state;
 		neigh_release(n);
 	}
-	if (state==NUD_REACHABLE)
+	if (state == NUD_REACHABLE)
 		return 0;
-	if ((state&NUD_VALID) && order != *dflt)
+	if ((state & NUD_VALID) && order != dflt)
 		return 0;
-	if ((state&NUD_VALID) ||
-	    (*last_idx<0 && order > *dflt)) {
+	if ((state & NUD_VALID) ||
+	    (*last_idx < 0 && order > dflt)) {
 		*last_resort = fi;
 		*last_idx = order;
 	}
@@ -341,102 +452,103 @@ int fib_detect_death(struct fib_info *fi, int order,
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 
-static u32 fib_get_attr32(struct rtattr *attr, int attrlen, int type)
-{
-	while (RTA_OK(attr,attrlen)) {
-		if (attr->rta_type == type)
-			return *(u32*)RTA_DATA(attr);
-		attr = RTA_NEXT(attr, attrlen);
-	}
-	return 0;
-}
-
-static int
-fib_count_nexthops(struct rtattr *rta)
+static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining)
 {
 	int nhs = 0;
-	struct rtnexthop *nhp = RTA_DATA(rta);
-	int nhlen = RTA_PAYLOAD(rta);
 
-	while (nhlen >= (int)sizeof(struct rtnexthop)) {
-		if ((nhlen -= nhp->rtnh_len) < 0)
-			return 0;
+	while (rtnh_ok(rtnh, remaining)) {
 		nhs++;
-		nhp = RTNH_NEXT(nhp);
-	};
-	return nhs;
+		rtnh = rtnh_next(rtnh, &remaining);
+	}
+
+	/* leftover implies invalid nexthop configuration, discard it */
+	return remaining > 0 ? 0 : nhs;
 }
 
-static int
-fib_get_nhs(struct fib_info *fi, const struct rtattr *rta, const struct rtmsg *r)
+static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
+		       int remaining, struct fib_config *cfg)
 {
-	struct rtnexthop *nhp = RTA_DATA(rta);
-	int nhlen = RTA_PAYLOAD(rta);
-
 	change_nexthops(fi) {
-		int attrlen = nhlen - sizeof(struct rtnexthop);
-		if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0)
+		int attrlen;
+
+		if (!rtnh_ok(rtnh, remaining))
 			return -EINVAL;
-		nh->nh_flags = (r->rtm_flags&~0xFF) | nhp->rtnh_flags;
-		nh->nh_oif = nhp->rtnh_ifindex;
-		nh->nh_weight = nhp->rtnh_hops + 1;
-		if (attrlen) {
-			nh->nh_gw = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_GATEWAY);
-#ifdef CONFIG_NET_CLS_ROUTE
-			nh->nh_tclassid = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_FLOW);
+
+		nexthop_nh->nh_flags =
+			(cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
+		nexthop_nh->nh_oif = rtnh->rtnh_ifindex;
+		nexthop_nh->nh_weight = rtnh->rtnh_hops + 1;
+
+		attrlen = rtnh_attrlen(rtnh);
+		if (attrlen > 0) {
+			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+
+			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+			nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+			nla = nla_find(attrs, attrlen, RTA_FLOW);
+			nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
+			if (nexthop_nh->nh_tclassid)
+				fi->fib_net->ipv4.fib_num_tclassid_users++;
 #endif
 		}
-		nhp = RTNH_NEXT(nhp);
+
+		rtnh = rtnh_next(rtnh, &remaining);
 	} endfor_nexthops(fi);
+
 	return 0;
 }
 
 #endif
 
-int fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct kern_rta *rta,
-		 struct fib_info *fi)
+int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	struct rtnexthop *nhp;
-	int nhlen;
+	struct rtnexthop *rtnh;
+	int remaining;
 #endif
 
-	if (rta->rta_priority &&
-	    *rta->rta_priority != fi->fib_priority)
+	if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
 		return 1;
 
-	if (rta->rta_oif || rta->rta_gw) {
-		if ((!rta->rta_oif || *rta->rta_oif == fi->fib_nh->nh_oif) &&
-		    (!rta->rta_gw  || memcmp(rta->rta_gw, &fi->fib_nh->nh_gw, 4) == 0))
+	if (cfg->fc_oif || cfg->fc_gw) {
+		if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
+		    (!cfg->fc_gw  || cfg->fc_gw == fi->fib_nh->nh_gw))
 			return 0;
 		return 1;
 	}
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (rta->rta_mp == NULL)
+	if (cfg->fc_mp == NULL)
 		return 0;
-	nhp = RTA_DATA(rta->rta_mp);
-	nhlen = RTA_PAYLOAD(rta->rta_mp);
-	
+
+	rtnh = cfg->fc_mp;
+	remaining = cfg->fc_mp_len;
+
 	for_nexthops(fi) {
-		int attrlen = nhlen - sizeof(struct rtnexthop);
-		u32 gw;
+		int attrlen;
 
-		if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0)
+		if (!rtnh_ok(rtnh, remaining))
 			return -EINVAL;
-		if (nhp->rtnh_ifindex && nhp->rtnh_ifindex != nh->nh_oif)
+
+		if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->nh_oif)
 			return 1;
-		if (attrlen) {
-			gw = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_GATEWAY);
-			if (gw && gw != nh->nh_gw)
+
+		attrlen = rtnh_attrlen(rtnh);
+		if (attrlen < 0) {
+			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+
+			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+			if (nla && nla_get_be32(nla) != nh->nh_gw)
 				return 1;
-#ifdef CONFIG_NET_CLS_ROUTE
-			gw = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_FLOW);
-			if (gw && gw != nh->nh_tclassid)
+#ifdef CONFIG_IP_ROUTE_CLASSID
+			nla = nla_find(attrs, attrlen, RTA_FLOW);
+			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
 				return 1;
 #endif
 		}
-		nhp = RTNH_NEXT(nhp);
+
+		rtnh = rtnh_next(rtnh, &remaining);
 	} endfor_nexthops(fi);
 #endif
 	return 0;
@@ -444,141 +556,147 @@ int fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct kern_rta *rta,
 
 
 /*
-   Picture
-   -------
-
-   Semantics of nexthop is very messy by historical reasons.
-   We have to take into account, that:
-   a) gateway can be actually local interface address,
-      so that gatewayed route is direct.
-   b) gateway must be on-link address, possibly
-      described not by an ifaddr, but also by a direct route.
-   c) If both gateway and interface are specified, they should not
-      contradict.
-   d) If we use tunnel routes, gateway could be not on-link.
-
-   Attempt to reconcile all of these (alas, self-contradictory) conditions
-   results in pretty ugly and hairy code with obscure logic.
-
-   I chose to generalized it instead, so that the size
-   of code does not increase practically, but it becomes
-   much more general.
-   Every prefix is assigned a "scope" value: "host" is local address,
-   "link" is direct route,
-   [ ... "site" ... "interior" ... ]
-   and "universe" is true gateway route with global meaning.
-
-   Every prefix refers to a set of "nexthop"s (gw, oif),
-   where gw must have narrower scope. This recursion stops
-   when gw has LOCAL scope or if "nexthop" is declared ONLINK,
-   which means that gw is forced to be on link.
-
-   Code is still hairy, but now it is apparently logically
-   consistent and very flexible. F.e. as by-product it allows
-   to co-exists in peace independent exterior and interior
-   routing processes.
-
-   Normally it looks as following.
-
-   {universe prefix}  -> (gw, oif) [scope link]
-                          |
-			  |-> {link prefix} -> (gw, oif) [scope local]
-			                        |
-						|-> {local prefix} (terminal node)
+ * Picture
+ * -------
+ *
+ * Semantics of nexthop is very messy by historical reasons.
+ * We have to take into account, that:
+ * a) gateway can be actually local interface address,
+ *    so that gatewayed route is direct.
+ * b) gateway must be on-link address, possibly
+ *    described not by an ifaddr, but also by a direct route.
+ * c) If both gateway and interface are specified, they should not
+ *    contradict.
+ * d) If we use tunnel routes, gateway could be not on-link.
+ *
+ * Attempt to reconcile all of these (alas, self-contradictory) conditions
+ * results in pretty ugly and hairy code with obscure logic.
+ *
+ * I chose to generalized it instead, so that the size
+ * of code does not increase practically, but it becomes
+ * much more general.
+ * Every prefix is assigned a "scope" value: "host" is local address,
+ * "link" is direct route,
+ * [ ... "site" ... "interior" ... ]
+ * and "universe" is true gateway route with global meaning.
+ *
+ * Every prefix refers to a set of "nexthop"s (gw, oif),
+ * where gw must have narrower scope. This recursion stops
+ * when gw has LOCAL scope or if "nexthop" is declared ONLINK,
+ * which means that gw is forced to be on link.
+ *
+ * Code is still hairy, but now it is apparently logically
+ * consistent and very flexible. F.e. as by-product it allows
+ * to co-exists in peace independent exterior and interior
+ * routing processes.
+ *
+ * Normally it looks as following.
+ *
+ * {universe prefix}  -> (gw, oif) [scope link]
+ *		  |
+ *		  |-> {link prefix} -> (gw, oif) [scope local]
+ *					|
+ *					|-> {local prefix} (terminal node)
  */
-
-static int fib_check_nh(const struct rtmsg *r, struct fib_info *fi, struct fib_nh *nh)
+static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
+			struct fib_nh *nh)
 {
 	int err;
+	struct net *net;
+	struct net_device *dev;
 
+	net = cfg->fc_nlinfo.nl_net;
 	if (nh->nh_gw) {
 		struct fib_result res;
 
-#ifdef CONFIG_IP_ROUTE_PERVASIVE
-		if (nh->nh_flags&RTNH_F_PERVASIVE)
-			return 0;
-#endif
-		if (nh->nh_flags&RTNH_F_ONLINK) {
-			struct net_device *dev;
+		if (nh->nh_flags & RTNH_F_ONLINK) {
 
-			if (r->rtm_scope >= RT_SCOPE_LINK)
+			if (cfg->fc_scope >= RT_SCOPE_LINK)
 				return -EINVAL;
-			if (inet_addr_type(nh->nh_gw) != RTN_UNICAST)
+			if (inet_addr_type(net, nh->nh_gw) != RTN_UNICAST)
 				return -EINVAL;
-			if ((dev = __dev_get_by_index(nh->nh_oif)) == NULL)
+			dev = __dev_get_by_index(net, nh->nh_oif);
+			if (!dev)
 				return -ENODEV;
-			if (!(dev->flags&IFF_UP))
+			if (!(dev->flags & IFF_UP))
 				return -ENETDOWN;
 			nh->nh_dev = dev;
 			dev_hold(dev);
 			nh->nh_scope = RT_SCOPE_LINK;
 			return 0;
 		}
+		rcu_read_lock();
 		{
-			struct flowi fl = { .nl_u = { .ip4_u =
-						      { .daddr = nh->nh_gw,
-							.scope = r->rtm_scope + 1 } },
-					    .oif = nh->nh_oif };
+			struct flowi4 fl4 = {
+				.daddr = nh->nh_gw,
+				.flowi4_scope = cfg->fc_scope + 1,
+				.flowi4_oif = nh->nh_oif,
+				.flowi4_iif = LOOPBACK_IFINDEX,
+			};
 
 			/* It is not necessary, but requires a bit of thinking */
-			if (fl.fl4_scope < RT_SCOPE_LINK)
-				fl.fl4_scope = RT_SCOPE_LINK;
-			if ((err = fib_lookup(&fl, &res)) != 0)
+			if (fl4.flowi4_scope < RT_SCOPE_LINK)
+				fl4.flowi4_scope = RT_SCOPE_LINK;
+			err = fib_lookup(net, &fl4, &res);
+			if (err) {
+				rcu_read_unlock();
 				return err;
+			}
 		}
 		err = -EINVAL;
 		if (res.type != RTN_UNICAST && res.type != RTN_LOCAL)
 			goto out;
 		nh->nh_scope = res.scope;
 		nh->nh_oif = FIB_RES_OIF(res);
-		if ((nh->nh_dev = FIB_RES_DEV(res)) == NULL)
-			goto out;
-		dev_hold(nh->nh_dev);
-		err = -ENETDOWN;
-		if (!(nh->nh_dev->flags & IFF_UP))
+		nh->nh_dev = dev = FIB_RES_DEV(res);
+		if (!dev)
 			goto out;
-		err = 0;
-out:
-		fib_res_put(&res);
-		return err;
+		dev_hold(dev);
+		err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN;
 	} else {
 		struct in_device *in_dev;
 
-		if (nh->nh_flags&(RTNH_F_PERVASIVE|RTNH_F_ONLINK))
+		if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK))
 			return -EINVAL;
 
-		in_dev = inetdev_by_index(nh->nh_oif);
+		rcu_read_lock();
+		err = -ENODEV;
+		in_dev = inetdev_by_index(net, nh->nh_oif);
 		if (in_dev == NULL)
-			return -ENODEV;
-		if (!(in_dev->dev->flags&IFF_UP)) {
-			in_dev_put(in_dev);
-			return -ENETDOWN;
-		}
+			goto out;
+		err = -ENETDOWN;
+		if (!(in_dev->dev->flags & IFF_UP))
+			goto out;
 		nh->nh_dev = in_dev->dev;
 		dev_hold(nh->nh_dev);
 		nh->nh_scope = RT_SCOPE_HOST;
-		in_dev_put(in_dev);
+		err = 0;
 	}
-	return 0;
+out:
+	rcu_read_unlock();
+	return err;
 }
 
-static inline unsigned int fib_laddr_hashfn(u32 val)
+static inline unsigned int fib_laddr_hashfn(__be32 val)
 {
-	unsigned int mask = (fib_hash_size - 1);
+	unsigned int mask = (fib_info_hash_size - 1);
 
-	return (val ^ (val >> 7) ^ (val >> 14)) & mask;
+	return ((__force u32)val ^
+		((__force u32)val >> 7) ^
+		((__force u32)val >> 14)) & mask;
 }
 
-static struct hlist_head *fib_hash_alloc(int bytes)
+static struct hlist_head *fib_info_hash_alloc(int bytes)
 {
 	if (bytes <= PAGE_SIZE)
-		return kmalloc(bytes, GFP_KERNEL);
+		return kzalloc(bytes, GFP_KERNEL);
 	else
 		return (struct hlist_head *)
-			__get_free_pages(GFP_KERNEL, get_order(bytes));
+			__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+					 get_order(bytes));
 }
 
-static void fib_hash_free(struct hlist_head *hash, int bytes)
+static void fib_info_hash_free(struct hlist_head *hash, int bytes)
 {
 	if (!hash)
 		return;
@@ -589,25 +707,25 @@ static void fib_hash_free(struct hlist_head *hash, int bytes)
 		free_pages((unsigned long) hash, get_order(bytes));
 }
 
-static void fib_hash_move(struct hlist_head *new_info_hash,
-			  struct hlist_head *new_laddrhash,
-			  unsigned int new_size)
+static void fib_info_hash_move(struct hlist_head *new_info_hash,
+			       struct hlist_head *new_laddrhash,
+			       unsigned int new_size)
 {
 	struct hlist_head *old_info_hash, *old_laddrhash;
-	unsigned int old_size = fib_hash_size;
+	unsigned int old_size = fib_info_hash_size;
 	unsigned int i, bytes;
 
-	write_lock(&fib_info_lock);
+	spin_lock_bh(&fib_info_lock);
 	old_info_hash = fib_info_hash;
 	old_laddrhash = fib_info_laddrhash;
-	fib_hash_size = new_size;
+	fib_info_hash_size = new_size;
 
 	for (i = 0; i < old_size; i++) {
 		struct hlist_head *head = &fib_info_hash[i];
-		struct hlist_node *node, *n;
+		struct hlist_node *n;
 		struct fib_info *fi;
 
-		hlist_for_each_entry_safe(fi, node, n, head, fib_hash) {
+		hlist_for_each_entry_safe(fi, n, head, fib_hash) {
 			struct hlist_head *dest;
 			unsigned int new_hash;
 
@@ -622,10 +740,10 @@ static void fib_hash_move(struct hlist_head *new_info_hash,
 
 	for (i = 0; i < old_size; i++) {
 		struct hlist_head *lhead = &fib_info_laddrhash[i];
-		struct hlist_node *node, *n;
+		struct hlist_node *n;
 		struct fib_info *fi;
 
-		hlist_for_each_entry_safe(fi, node, n, lhead, fib_lhash) {
+		hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) {
 			struct hlist_head *ldest;
 			unsigned int new_hash;
 
@@ -638,119 +756,128 @@ static void fib_hash_move(struct hlist_head *new_info_hash,
 	}
 	fib_info_laddrhash = new_laddrhash;
 
-	write_unlock(&fib_info_lock);
+	spin_unlock_bh(&fib_info_lock);
 
 	bytes = old_size * sizeof(struct hlist_head *);
-	fib_hash_free(old_info_hash, bytes);
-	fib_hash_free(old_laddrhash, bytes);
+	fib_info_hash_free(old_info_hash, bytes);
+	fib_info_hash_free(old_laddrhash, bytes);
 }
 
-struct fib_info *
-fib_create_info(const struct rtmsg *r, struct kern_rta *rta,
-		const struct nlmsghdr *nlh, int *errp)
+__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
+{
+	nh->nh_saddr = inet_select_addr(nh->nh_dev,
+					nh->nh_gw,
+					nh->nh_parent->fib_scope);
+	nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);
+
+	return nh->nh_saddr;
+}
+
+struct fib_info *fib_create_info(struct fib_config *cfg)
 {
 	int err;
 	struct fib_info *fi = NULL;
 	struct fib_info *ofi;
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int nhs = 1;
-#else
-	const int nhs = 1;
-#endif
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
-	u32 mp_alg = IP_MP_ALG_NONE;
-#endif
+	struct net *net = cfg->fc_nlinfo.nl_net;
+
+	if (cfg->fc_type > RTN_MAX)
+		goto err_inval;
 
 	/* Fast check to catch the most weird cases */
-	if (fib_props[r->rtm_type].scope > r->rtm_scope)
+	if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
 		goto err_inval;
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (rta->rta_mp) {
-		nhs = fib_count_nexthops(rta->rta_mp);
+	if (cfg->fc_mp) {
+		nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len);
 		if (nhs == 0)
 			goto err_inval;
 	}
 #endif
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
-	if (rta->rta_mp_alg) {
-		mp_alg = *rta->rta_mp_alg;
-
-		if (mp_alg < IP_MP_ALG_NONE ||
-		    mp_alg > IP_MP_ALG_MAX)
-			goto err_inval;
-	}
-#endif
 
 	err = -ENOBUFS;
-	if (fib_info_cnt >= fib_hash_size) {
-		unsigned int new_size = fib_hash_size << 1;
+	if (fib_info_cnt >= fib_info_hash_size) {
+		unsigned int new_size = fib_info_hash_size << 1;
 		struct hlist_head *new_info_hash;
 		struct hlist_head *new_laddrhash;
 		unsigned int bytes;
 
 		if (!new_size)
-			new_size = 1;
+			new_size = 16;
 		bytes = new_size * sizeof(struct hlist_head *);
-		new_info_hash = fib_hash_alloc(bytes);
-		new_laddrhash = fib_hash_alloc(bytes);
+		new_info_hash = fib_info_hash_alloc(bytes);
+		new_laddrhash = fib_info_hash_alloc(bytes);
 		if (!new_info_hash || !new_laddrhash) {
-			fib_hash_free(new_info_hash, bytes);
-			fib_hash_free(new_laddrhash, bytes);
-		} else {
-			memset(new_info_hash, 0, bytes);
-			memset(new_laddrhash, 0, bytes);
-
-			fib_hash_move(new_info_hash, new_laddrhash, new_size);
-		}
+			fib_info_hash_free(new_info_hash, bytes);
+			fib_info_hash_free(new_laddrhash, bytes);
+		} else
+			fib_info_hash_move(new_info_hash, new_laddrhash, new_size);
 
-		if (!fib_hash_size)
+		if (!fib_info_hash_size)
 			goto failure;
 	}
 
-	fi = kmalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
+	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (fi == NULL)
 		goto failure;
 	fib_info_cnt++;
-	memset(fi, 0, sizeof(*fi)+nhs*sizeof(struct fib_nh));
+	if (cfg->fc_mx) {
+		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+		if (!fi->fib_metrics)
+			goto failure;
+	} else
+		fi->fib_metrics = (u32 *) dst_default_metrics;
 
-	fi->fib_protocol = r->rtm_protocol;
+	fi->fib_net = hold_net(net);
+	fi->fib_protocol = cfg->fc_protocol;
+	fi->fib_scope = cfg->fc_scope;
+	fi->fib_flags = cfg->fc_flags;
+	fi->fib_priority = cfg->fc_priority;
+	fi->fib_prefsrc = cfg->fc_prefsrc;
+	fi->fib_type = cfg->fc_type;
 
 	fi->fib_nhs = nhs;
 	change_nexthops(fi) {
-		nh->nh_parent = fi;
+		nexthop_nh->nh_parent = fi;
+		nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
+		if (!nexthop_nh->nh_pcpu_rth_output)
+			goto failure;
 	} endfor_nexthops(fi)
 
-	fi->fib_flags = r->rtm_flags;
-	if (rta->rta_priority)
-		fi->fib_priority = *rta->rta_priority;
-	if (rta->rta_mx) {
-		int attrlen = RTA_PAYLOAD(rta->rta_mx);
-		struct rtattr *attr = RTA_DATA(rta->rta_mx);
-
-		while (RTA_OK(attr, attrlen)) {
-			unsigned flavor = attr->rta_type;
-			if (flavor) {
-				if (flavor > RTAX_MAX)
+	if (cfg->fc_mx) {
+		struct nlattr *nla;
+		int remaining;
+
+		nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
+			int type = nla_type(nla);
+
+			if (type) {
+				u32 val;
+
+				if (type > RTAX_MAX)
 					goto err_inval;
-				fi->fib_metrics[flavor-1] = *(unsigned*)RTA_DATA(attr);
+				val = nla_get_u32(nla);
+				if (type == RTAX_ADVMSS && val > 65535 - 40)
+					val = 65535 - 40;
+				if (type == RTAX_MTU && val > 65535 - 15)
+					val = 65535 - 15;
+				fi->fib_metrics[type - 1] = val;
 			}
-			attr = RTA_NEXT(attr, attrlen);
 		}
 	}
-	if (rta->rta_prefsrc)
-		memcpy(&fi->fib_prefsrc, rta->rta_prefsrc, 4);
 
-	if (rta->rta_mp) {
+	if (cfg->fc_mp) {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-		if ((err = fib_get_nhs(fi, rta->rta_mp, r)) != 0)
+		err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg);
+		if (err != 0)
 			goto failure;
-		if (rta->rta_oif && fi->fib_nh->nh_oif != *rta->rta_oif)
+		if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif)
 			goto err_inval;
-		if (rta->rta_gw && memcmp(&fi->fib_nh->nh_gw, rta->rta_gw, 4))
+		if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw)
 			goto err_inval;
-#ifdef CONFIG_NET_CLS_ROUTE
-		if (rta->rta_flow && memcmp(&fi->fib_nh->nh_tclassid, rta->rta_flow, 4))
+#ifdef CONFIG_IP_ROUTE_CLASSID
+		if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow)
 			goto err_inval;
 #endif
 #else
@@ -758,60 +885,73 @@ fib_create_info(const struct rtmsg *r, struct kern_rta *rta,
 #endif
 	} else {
 		struct fib_nh *nh = fi->fib_nh;
-		if (rta->rta_oif)
-			nh->nh_oif = *rta->rta_oif;
-		if (rta->rta_gw)
-			memcpy(&nh->nh_gw, rta->rta_gw, 4);
-#ifdef CONFIG_NET_CLS_ROUTE
-		if (rta->rta_flow)
-			memcpy(&nh->nh_tclassid, rta->rta_flow, 4);
+
+		nh->nh_oif = cfg->fc_oif;
+		nh->nh_gw = cfg->fc_gw;
+		nh->nh_flags = cfg->fc_flags;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+		nh->nh_tclassid = cfg->fc_flow;
+		if (nh->nh_tclassid)
+			fi->fib_net->ipv4.fib_num_tclassid_users++;
 #endif
-		nh->nh_flags = r->rtm_flags;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 		nh->nh_weight = 1;
 #endif
 	}
 
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
-	fi->fib_mp_alg = mp_alg;
-#endif
-
-	if (fib_props[r->rtm_type].error) {
-		if (rta->rta_gw || rta->rta_oif || rta->rta_mp)
+	if (fib_props[cfg->fc_type].error) {
+		if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp)
 			goto err_inval;
 		goto link_it;
+	} else {
+		switch (cfg->fc_type) {
+		case RTN_UNICAST:
+		case RTN_LOCAL:
+		case RTN_BROADCAST:
+		case RTN_ANYCAST:
+		case RTN_MULTICAST:
+			break;
+		default:
+			goto err_inval;
+		}
 	}
 
-	if (r->rtm_scope > RT_SCOPE_HOST)
+	if (cfg->fc_scope > RT_SCOPE_HOST)
 		goto err_inval;
 
-	if (r->rtm_scope == RT_SCOPE_HOST) {
+	if (cfg->fc_scope == RT_SCOPE_HOST) {
 		struct fib_nh *nh = fi->fib_nh;
 
 		/* Local address is added. */
 		if (nhs != 1 || nh->nh_gw)
 			goto err_inval;
 		nh->nh_scope = RT_SCOPE_NOWHERE;
-		nh->nh_dev = dev_get_by_index(fi->fib_nh->nh_oif);
+		nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif);
 		err = -ENODEV;
 		if (nh->nh_dev == NULL)
 			goto failure;
 	} else {
 		change_nexthops(fi) {
-			if ((err = fib_check_nh(r, fi, nh)) != 0)
+			err = fib_check_nh(cfg, fi, nexthop_nh);
+			if (err != 0)
 				goto failure;
 		} endfor_nexthops(fi)
 	}
 
 	if (fi->fib_prefsrc) {
-		if (r->rtm_type != RTN_LOCAL || rta->rta_dst == NULL ||
-		    memcmp(&fi->fib_prefsrc, rta->rta_dst, 4))
-			if (inet_addr_type(fi->fib_prefsrc) != RTN_LOCAL)
+		if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
+		    fi->fib_prefsrc != cfg->fc_dst)
+			if (inet_addr_type(net, fi->fib_prefsrc) != RTN_LOCAL)
 				goto err_inval;
 	}
 
+	change_nexthops(fi) {
+		fib_info_update_nh_saddr(net, nexthop_nh);
+	} endfor_nexthops(fi)
+
 link_it:
-	if ((ofi = fib_find_info(fi)) != NULL) {
+	ofi = fib_find_info(fi);
+	if (ofi) {
 		fi->fib_dead = 1;
 		free_fib_info(fi);
 		ofi->fib_treeref++;
@@ -820,7 +960,7 @@ link_it:
 
 	fi->fib_treeref++;
 	atomic_inc(&fi->fib_clntref);
-	write_lock(&fib_info_lock);
+	spin_lock_bh(&fib_info_lock);
 	hlist_add_head(&fi->fib_hash,
 		       &fib_info_hash[fib_info_hashfn(fi)]);
 	if (fi->fib_prefsrc) {
@@ -833,417 +973,268 @@ link_it:
 		struct hlist_head *head;
 		unsigned int hash;
 
-		if (!nh->nh_dev)
+		if (!nexthop_nh->nh_dev)
 			continue;
-		hash = fib_devindex_hashfn(nh->nh_dev->ifindex);
+		hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex);
 		head = &fib_info_devhash[hash];
-		hlist_add_head(&nh->nh_hash, head);
+		hlist_add_head(&nexthop_nh->nh_hash, head);
 	} endfor_nexthops(fi)
-	write_unlock(&fib_info_lock);
+	spin_unlock_bh(&fib_info_lock);
 	return fi;
 
 err_inval:
 	err = -EINVAL;
 
 failure:
-        *errp = err;
-        if (fi) {
+	if (fi) {
 		fi->fib_dead = 1;
 		free_fib_info(fi);
 	}
-	return NULL;
-}
-
-/* Note! fib_semantic_match intentionally uses  RCU list functions. */
-int fib_semantic_match(struct list_head *head, const struct flowi *flp,
-		       struct fib_result *res, __u32 zone, __u32 mask, 
-			int prefixlen)
-{
-	struct fib_alias *fa;
-	int nh_sel = 0;
-
-	list_for_each_entry_rcu(fa, head, fa_list) {
-		int err;
 
-		if (fa->fa_tos &&
-		    fa->fa_tos != flp->fl4_tos)
-			continue;
-
-		if (fa->fa_scope < flp->fl4_scope)
-			continue;
-
-		fa->fa_state |= FA_S_ACCESSED;
-
-		err = fib_props[fa->fa_type].error;
-		if (err == 0) {
-			struct fib_info *fi = fa->fa_info;
-
-			if (fi->fib_flags & RTNH_F_DEAD)
-				continue;
-
-			switch (fa->fa_type) {
-			case RTN_UNICAST:
-			case RTN_LOCAL:
-			case RTN_BROADCAST:
-			case RTN_ANYCAST:
-			case RTN_MULTICAST:
-				for_nexthops(fi) {
-					if (nh->nh_flags&RTNH_F_DEAD)
-						continue;
-					if (!flp->oif || flp->oif == nh->nh_oif)
-						break;
-				}
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-				if (nhsel < fi->fib_nhs) {
-					nh_sel = nhsel;
-					goto out_fill_res;
-				}
-#else
-				if (nhsel < 1) {
-					goto out_fill_res;
-				}
-#endif
-				endfor_nexthops(fi);
-				continue;
-
-			default:
-				printk(KERN_DEBUG "impossible 102\n");
-				return -EINVAL;
-			};
-		}
-		return err;
-	}
-	return 1;
-
-out_fill_res:
-	res->prefixlen = prefixlen;
-	res->nh_sel = nh_sel;
-	res->type = fa->fa_type;
-	res->scope = fa->fa_scope;
-	res->fi = fa->fa_info;
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
-	res->netmask = mask;
-	res->network = zone &
-		(0xFFFFFFFF >> (32 - prefixlen));
-#endif
-	atomic_inc(&res->fi->fib_clntref);
-	return 0;
+	return ERR_PTR(err);
 }
 
-/* Find appropriate source address to this destination */
-
-u32 __fib_res_prefsrc(struct fib_result *res)
-{
-	return inet_select_addr(FIB_RES_DEV(*res), FIB_RES_GW(*res), res->scope);
-}
-
-int
-fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
-	      u8 tb_id, u8 type, u8 scope, void *dst, int dst_len, u8 tos,
-	      struct fib_info *fi, unsigned int flags)
+int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
+		  u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
+		  struct fib_info *fi, unsigned int flags)
 {
+	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
-	struct nlmsghdr  *nlh;
-	unsigned char	 *b = skb->tail;
 
-	nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*rtm), flags);
-	rtm = NLMSG_DATA(nlh);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	rtm = nlmsg_data(nlh);
 	rtm->rtm_family = AF_INET;
 	rtm->rtm_dst_len = dst_len;
 	rtm->rtm_src_len = 0;
 	rtm->rtm_tos = tos;
-	rtm->rtm_table = tb_id;
+	if (tb_id < 256)
+		rtm->rtm_table = tb_id;
+	else
+		rtm->rtm_table = RT_TABLE_COMPAT;
+	if (nla_put_u32(skb, RTA_TABLE, tb_id))
+		goto nla_put_failure;
 	rtm->rtm_type = type;
 	rtm->rtm_flags = fi->fib_flags;
-	rtm->rtm_scope = scope;
-	if (rtm->rtm_dst_len)
-		RTA_PUT(skb, RTA_DST, 4, dst);
+	rtm->rtm_scope = fi->fib_scope;
 	rtm->rtm_protocol = fi->fib_protocol;
-	if (fi->fib_priority)
-		RTA_PUT(skb, RTA_PRIORITY, 4, &fi->fib_priority);
-#ifdef CONFIG_NET_CLS_ROUTE
-	if (fi->fib_nh[0].nh_tclassid)
-		RTA_PUT(skb, RTA_FLOW, 4, &fi->fib_nh[0].nh_tclassid);
-#endif
+
+	if (rtm->rtm_dst_len &&
+	    nla_put_be32(skb, RTA_DST, dst))
+		goto nla_put_failure;
+	if (fi->fib_priority &&
+	    nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
+		goto nla_put_failure;
 	if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
-		goto rtattr_failure;
-	if (fi->fib_prefsrc)
-		RTA_PUT(skb, RTA_PREFSRC, 4, &fi->fib_prefsrc);
+		goto nla_put_failure;
+
+	if (fi->fib_prefsrc &&
+	    nla_put_be32(skb, RTA_PREFSRC, fi->fib_prefsrc))
+		goto nla_put_failure;
 	if (fi->fib_nhs == 1) {
-		if (fi->fib_nh->nh_gw)
-			RTA_PUT(skb, RTA_GATEWAY, 4, &fi->fib_nh->nh_gw);
-		if (fi->fib_nh->nh_oif)
-			RTA_PUT(skb, RTA_OIF, sizeof(int), &fi->fib_nh->nh_oif);
+		if (fi->fib_nh->nh_gw &&
+		    nla_put_be32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw))
+			goto nla_put_failure;
+		if (fi->fib_nh->nh_oif &&
+		    nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif))
+			goto nla_put_failure;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+		if (fi->fib_nh[0].nh_tclassid &&
+		    nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
+			goto nla_put_failure;
+#endif
 	}
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (fi->fib_nhs > 1) {
-		struct rtnexthop *nhp;
-		struct rtattr *mp_head;
-		if (skb_tailroom(skb) <= RTA_SPACE(0))
-			goto rtattr_failure;
-		mp_head = (struct rtattr*)skb_put(skb, RTA_SPACE(0));
+		struct rtnexthop *rtnh;
+		struct nlattr *mp;
+
+		mp = nla_nest_start(skb, RTA_MULTIPATH);
+		if (mp == NULL)
+			goto nla_put_failure;
 
 		for_nexthops(fi) {
-			if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4))
-				goto rtattr_failure;
-			nhp = (struct rtnexthop*)skb_put(skb, RTA_ALIGN(sizeof(*nhp)));
-			nhp->rtnh_flags = nh->nh_flags & 0xFF;
-			nhp->rtnh_hops = nh->nh_weight-1;
-			nhp->rtnh_ifindex = nh->nh_oif;
-			if (nh->nh_gw)
-				RTA_PUT(skb, RTA_GATEWAY, 4, &nh->nh_gw);
-			nhp->rtnh_len = skb->tail - (unsigned char*)nhp;
+			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
+			if (rtnh == NULL)
+				goto nla_put_failure;
+
+			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
+			rtnh->rtnh_hops = nh->nh_weight - 1;
+			rtnh->rtnh_ifindex = nh->nh_oif;
+
+			if (nh->nh_gw &&
+			    nla_put_be32(skb, RTA_GATEWAY, nh->nh_gw))
+				goto nla_put_failure;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+			if (nh->nh_tclassid &&
+			    nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
+				goto nla_put_failure;
+#endif
+			/* length of rtnetlink header + attributes */
+			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
 		} endfor_nexthops(fi);
-		mp_head->rta_type = RTA_MULTIPATH;
-		mp_head->rta_len = skb->tail - (u8*)mp_head;
+
+		nla_nest_end(skb, mp);
 	}
 #endif
-	nlh->nlmsg_len = skb->tail - b;
-	return skb->len;
+	return nlmsg_end(skb, nlh);
 
-nlmsg_failure:
-rtattr_failure:
-	skb_trim(skb, b - skb->data);
-	return -1;
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
 }
 
-#ifndef CONFIG_IP_NOSIOCRT
-
-int
-fib_convert_rtentry(int cmd, struct nlmsghdr *nl, struct rtmsg *rtm,
-		    struct kern_rta *rta, struct rtentry *r)
+/*
+ * Update FIB if:
+ * - local address disappeared -> we must delete all the entries
+ *   referring to it.
+ * - device went down -> we must shutdown all nexthops going via it.
+ */
+int fib_sync_down_addr(struct net *net, __be32 local)
 {
-	int    plen;
-	u32    *ptr;
-
-	memset(rtm, 0, sizeof(*rtm));
-	memset(rta, 0, sizeof(*rta));
-
-	if (r->rt_dst.sa_family != AF_INET)
-		return -EAFNOSUPPORT;
-
-	/* Check mask for validity:
-	   a) it must be contiguous.
-	   b) destination must have all host bits clear.
-	   c) if application forgot to set correct family (AF_INET),
-	      reject request unless it is absolutely clear i.e.
-	      both family and mask are zero.
-	 */
-	plen = 32;
-	ptr = &((struct sockaddr_in*)&r->rt_dst)->sin_addr.s_addr;
-	if (!(r->rt_flags&RTF_HOST)) {
-		u32 mask = ((struct sockaddr_in*)&r->rt_genmask)->sin_addr.s_addr;
-		if (r->rt_genmask.sa_family != AF_INET) {
-			if (mask || r->rt_genmask.sa_family)
-				return -EAFNOSUPPORT;
-		}
-		if (bad_mask(mask, *ptr))
-			return -EINVAL;
-		plen = inet_mask_len(mask);
-	}
-
-	nl->nlmsg_flags = NLM_F_REQUEST;
-	nl->nlmsg_pid = current->pid;
-	nl->nlmsg_seq = 0;
-	nl->nlmsg_len = NLMSG_LENGTH(sizeof(*rtm));
-	if (cmd == SIOCDELRT) {
-		nl->nlmsg_type = RTM_DELROUTE;
-		nl->nlmsg_flags = 0;
-	} else {
-		nl->nlmsg_type = RTM_NEWROUTE;
-		nl->nlmsg_flags = NLM_F_REQUEST|NLM_F_CREATE;
-		rtm->rtm_protocol = RTPROT_BOOT;
-	}
-
-	rtm->rtm_dst_len = plen;
-	rta->rta_dst = ptr;
-
-	if (r->rt_metric) {
-		*(u32*)&r->rt_pad3 = r->rt_metric - 1;
-		rta->rta_priority = (u32*)&r->rt_pad3;
-	}
-	if (r->rt_flags&RTF_REJECT) {
-		rtm->rtm_scope = RT_SCOPE_HOST;
-		rtm->rtm_type = RTN_UNREACHABLE;
-		return 0;
-	}
-	rtm->rtm_scope = RT_SCOPE_NOWHERE;
-	rtm->rtm_type = RTN_UNICAST;
-
-	if (r->rt_dev) {
-		char *colon;
-		struct net_device *dev;
-		char   devname[IFNAMSIZ];
-
-		if (copy_from_user(devname, r->rt_dev, IFNAMSIZ-1))
-			return -EFAULT;
-		devname[IFNAMSIZ-1] = 0;
-		colon = strchr(devname, ':');
-		if (colon)
-			*colon = 0;
-		dev = __dev_get_by_name(devname);
-		if (!dev)
-			return -ENODEV;
-		rta->rta_oif = &dev->ifindex;
-		if (colon) {
-			struct in_ifaddr *ifa;
-			struct in_device *in_dev = __in_dev_get_rtnl(dev);
-			if (!in_dev)
-				return -ENODEV;
-			*colon = ':';
-			for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next)
-				if (strcmp(ifa->ifa_label, devname) == 0)
-					break;
-			if (ifa == NULL)
-				return -ENODEV;
-			rta->rta_prefsrc = &ifa->ifa_local;
-		}
-	}
-
-	ptr = &((struct sockaddr_in*)&r->rt_gateway)->sin_addr.s_addr;
-	if (r->rt_gateway.sa_family == AF_INET && *ptr) {
-		rta->rta_gw = ptr;
-		if (r->rt_flags&RTF_GATEWAY && inet_addr_type(*ptr) == RTN_UNICAST)
-			rtm->rtm_scope = RT_SCOPE_UNIVERSE;
-	}
+	int ret = 0;
+	unsigned int hash = fib_laddr_hashfn(local);
+	struct hlist_head *head = &fib_info_laddrhash[hash];
+	struct fib_info *fi;
 
-	if (cmd == SIOCDELRT)
+	if (fib_info_laddrhash == NULL || local == 0)
 		return 0;
 
-	if (r->rt_flags&RTF_GATEWAY && rta->rta_gw == NULL)
-		return -EINVAL;
-
-	if (rtm->rtm_scope == RT_SCOPE_NOWHERE)
-		rtm->rtm_scope = RT_SCOPE_LINK;
-
-	if (r->rt_flags&(RTF_MTU|RTF_WINDOW|RTF_IRTT)) {
-		struct rtattr *rec;
-		struct rtattr *mx = kmalloc(RTA_LENGTH(3*RTA_LENGTH(4)), GFP_KERNEL);
-		if (mx == NULL)
-			return -ENOMEM;
-		rta->rta_mx = mx;
-		mx->rta_type = RTA_METRICS;
-		mx->rta_len  = RTA_LENGTH(0);
-		if (r->rt_flags&RTF_MTU) {
-			rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len));
-			rec->rta_type = RTAX_ADVMSS;
-			rec->rta_len = RTA_LENGTH(4);
-			mx->rta_len += RTA_LENGTH(4);
-			*(u32*)RTA_DATA(rec) = r->rt_mtu - 40;
-		}
-		if (r->rt_flags&RTF_WINDOW) {
-			rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len));
-			rec->rta_type = RTAX_WINDOW;
-			rec->rta_len = RTA_LENGTH(4);
-			mx->rta_len += RTA_LENGTH(4);
-			*(u32*)RTA_DATA(rec) = r->rt_window;
-		}
-		if (r->rt_flags&RTF_IRTT) {
-			rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len));
-			rec->rta_type = RTAX_RTT;
-			rec->rta_len = RTA_LENGTH(4);
-			mx->rta_len += RTA_LENGTH(4);
-			*(u32*)RTA_DATA(rec) = r->rt_irtt<<3;
+	hlist_for_each_entry(fi, head, fib_lhash) {
+		if (!net_eq(fi->fib_net, net))
+			continue;
+		if (fi->fib_prefsrc == local) {
+			fi->fib_flags |= RTNH_F_DEAD;
+			ret++;
 		}
 	}
-	return 0;
+	return ret;
 }
 
-#endif
-
-/*
-   Update FIB if:
-   - local address disappeared -> we must delete all the entries
-     referring to it.
-   - device went down -> we must shutdown all nexthops going via it.
- */
-
-int fib_sync_down(u32 local, struct net_device *dev, int force)
+int fib_sync_down_dev(struct net_device *dev, int force)
 {
 	int ret = 0;
 	int scope = RT_SCOPE_NOWHERE;
-	
+	struct fib_info *prev_fi = NULL;
+	unsigned int hash = fib_devindex_hashfn(dev->ifindex);
+	struct hlist_head *head = &fib_info_devhash[hash];
+	struct fib_nh *nh;
+
 	if (force)
 		scope = -1;
 
-	if (local && fib_info_laddrhash) {
-		unsigned int hash = fib_laddr_hashfn(local);
-		struct hlist_head *head = &fib_info_laddrhash[hash];
-		struct hlist_node *node;
-		struct fib_info *fi;
+	hlist_for_each_entry(nh, head, nh_hash) {
+		struct fib_info *fi = nh->nh_parent;
+		int dead;
 
-		hlist_for_each_entry(fi, node, head, fib_lhash) {
-			if (fi->fib_prefsrc == local) {
-				fi->fib_flags |= RTNH_F_DEAD;
-				ret++;
+		BUG_ON(!fi->fib_nhs);
+		if (nh->nh_dev != dev || fi == prev_fi)
+			continue;
+		prev_fi = fi;
+		dead = 0;
+		change_nexthops(fi) {
+			if (nexthop_nh->nh_flags & RTNH_F_DEAD)
+				dead++;
+			else if (nexthop_nh->nh_dev == dev &&
+				 nexthop_nh->nh_scope != scope) {
+				nexthop_nh->nh_flags |= RTNH_F_DEAD;
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+				spin_lock_bh(&fib_multipath_lock);
+				fi->fib_power -= nexthop_nh->nh_power;
+				nexthop_nh->nh_power = 0;
+				spin_unlock_bh(&fib_multipath_lock);
+#endif
+				dead++;
+			}
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+			if (force > 1 && nexthop_nh->nh_dev == dev) {
+				dead = fi->fib_nhs;
+				break;
 			}
+#endif
+		} endfor_nexthops(fi)
+		if (dead == fi->fib_nhs) {
+			fi->fib_flags |= RTNH_F_DEAD;
+			ret++;
 		}
 	}
 
-	if (dev) {
-		struct fib_info *prev_fi = NULL;
-		unsigned int hash = fib_devindex_hashfn(dev->ifindex);
-		struct hlist_head *head = &fib_info_devhash[hash];
-		struct hlist_node *node;
-		struct fib_nh *nh;
+	return ret;
+}
 
-		hlist_for_each_entry(nh, node, head, nh_hash) {
-			struct fib_info *fi = nh->nh_parent;
-			int dead;
+/* Must be invoked inside of an RCU protected region.  */
+void fib_select_default(struct fib_result *res)
+{
+	struct fib_info *fi = NULL, *last_resort = NULL;
+	struct list_head *fa_head = res->fa_head;
+	struct fib_table *tb = res->table;
+	int order = -1, last_idx = -1;
+	struct fib_alias *fa;
 
-			BUG_ON(!fi->fib_nhs);
-			if (nh->nh_dev != dev || fi == prev_fi)
-				continue;
-			prev_fi = fi;
-			dead = 0;
-			change_nexthops(fi) {
-				if (nh->nh_flags&RTNH_F_DEAD)
-					dead++;
-				else if (nh->nh_dev == dev &&
-					 nh->nh_scope != scope) {
-					nh->nh_flags |= RTNH_F_DEAD;
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-					spin_lock_bh(&fib_multipath_lock);
-					fi->fib_power -= nh->nh_power;
-					nh->nh_power = 0;
-					spin_unlock_bh(&fib_multipath_lock);
-#endif
-					dead++;
-				}
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-				if (force > 1 && nh->nh_dev == dev) {
-					dead = fi->fib_nhs;
-					break;
-				}
-#endif
-			} endfor_nexthops(fi)
-			if (dead == fi->fib_nhs) {
-				fi->fib_flags |= RTNH_F_DEAD;
-				ret++;
-			}
+	list_for_each_entry_rcu(fa, fa_head, fa_list) {
+		struct fib_info *next_fi = fa->fa_info;
+
+		if (next_fi->fib_scope != res->scope ||
+		    fa->fa_type != RTN_UNICAST)
+			continue;
+
+		if (next_fi->fib_priority > res->fi->fib_priority)
+			break;
+		if (!next_fi->fib_nh[0].nh_gw ||
+		    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
+			continue;
+
+		fib_alias_accessed(fa);
+
+		if (fi == NULL) {
+			if (next_fi != res->fi)
+				break;
+		} else if (!fib_detect_death(fi, order, &last_resort,
+					     &last_idx, tb->tb_default)) {
+			fib_result_assign(res, fi);
+			tb->tb_default = order;
+			goto out;
 		}
+		fi = next_fi;
+		order++;
 	}
 
-	return ret;
+	if (order <= 0 || fi == NULL) {
+		tb->tb_default = -1;
+		goto out;
+	}
+
+	if (!fib_detect_death(fi, order, &last_resort, &last_idx,
+				tb->tb_default)) {
+		fib_result_assign(res, fi);
+		tb->tb_default = order;
+		goto out;
+	}
+
+	if (last_idx >= 0)
+		fib_result_assign(res, last_resort);
+	tb->tb_default = last_idx;
+out:
+	return;
 }
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 
 /*
-   Dead device goes up. We wake up dead nexthops.
-   It takes sense only on multipath routes.
+ * Dead device goes up. We wake up dead nexthops.
+ * It takes sense only on multipath routes.
  */
-
 int fib_sync_up(struct net_device *dev)
 {
 	struct fib_info *prev_fi;
 	unsigned int hash;
 	struct hlist_head *head;
-	struct hlist_node *node;
 	struct fib_nh *nh;
 	int ret;
 
-	if (!(dev->flags&IFF_UP))
+	if (!(dev->flags & IFF_UP))
 		return 0;
 
 	prev_fi = NULL;
@@ -1251,7 +1242,7 @@ int fib_sync_up(struct net_device *dev)
 	head = &fib_info_devhash[hash];
 	ret = 0;
 
-	hlist_for_each_entry(nh, node, head, nh_hash) {
+	hlist_for_each_entry(nh, head, nh_hash) {
 		struct fib_info *fi = nh->nh_parent;
 		int alive;
 
@@ -1262,18 +1253,20 @@ int fib_sync_up(struct net_device *dev)
 		prev_fi = fi;
 		alive = 0;
 		change_nexthops(fi) {
-			if (!(nh->nh_flags&RTNH_F_DEAD)) {
+			if (!(nexthop_nh->nh_flags & RTNH_F_DEAD)) {
 				alive++;
 				continue;
 			}
-			if (nh->nh_dev == NULL || !(nh->nh_dev->flags&IFF_UP))
+			if (nexthop_nh->nh_dev == NULL ||
+			    !(nexthop_nh->nh_dev->flags & IFF_UP))
 				continue;
-			if (nh->nh_dev != dev || !__in_dev_get_rtnl(dev))
+			if (nexthop_nh->nh_dev != dev ||
+			    !__in_dev_get_rtnl(dev))
 				continue;
 			alive++;
 			spin_lock_bh(&fib_multipath_lock);
-			nh->nh_power = 0;
-			nh->nh_flags &= ~RTNH_F_DEAD;
+			nexthop_nh->nh_power = 0;
+			nexthop_nh->nh_flags &= ~RTNH_F_DEAD;
 			spin_unlock_bh(&fib_multipath_lock);
 		} endfor_nexthops(fi)
 
@@ -1287,11 +1280,10 @@ int fib_sync_up(struct net_device *dev)
 }
 
 /*
-   The algorithm is suboptimal, but it provides really
-   fair weighted route distribution.
+ * The algorithm is suboptimal, but it provides really
+ * fair weighted route distribution.
  */
-
-void fib_select_multipath(const struct flowi *flp, struct fib_result *res)
+void fib_select_multipath(struct fib_result *res)
 {
 	struct fib_info *fi = res->fi;
 	int w;
@@ -1300,9 +1292,9 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res)
 	if (fi->fib_power <= 0) {
 		int power = 0;
 		change_nexthops(fi) {
-			if (!(nh->nh_flags&RTNH_F_DEAD)) {
-				power += nh->nh_weight;
-				nh->nh_power = nh->nh_weight;
+			if (!(nexthop_nh->nh_flags & RTNH_F_DEAD)) {
+				power += nexthop_nh->nh_weight;
+				nexthop_nh->nh_power = nexthop_nh->nh_weight;
 			}
 		} endfor_nexthops(fi);
 		fi->fib_power = power;
@@ -1316,15 +1308,17 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res)
 
 
 	/* w should be random number [0..fi->fib_power-1],
-	   it is pretty bad approximation.
+	 * it is pretty bad approximation.
 	 */
 
 	w = jiffies % fi->fib_power;
 
 	change_nexthops(fi) {
-		if (!(nh->nh_flags&RTNH_F_DEAD) && nh->nh_power) {
-			if ((w -= nh->nh_power) <= 0) {
-				nh->nh_power--;
+		if (!(nexthop_nh->nh_flags & RTNH_F_DEAD) &&
+		    nexthop_nh->nh_power) {
+			w -= nexthop_nh->nh_power;
+			if (w <= 0) {
+				nexthop_nh->nh_power--;
 				fi->fib_power--;
 				res->nh_sel = nhsel;
 				spin_unlock_bh(&fib_multipath_lock);