1 files changed, 1090 insertions, 614 deletions

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 5022bc63863a..a5f3c8459758 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * INET		An implementation of the TCP/IP protocol suite for the LINUX
  *		operating system.  INET is implemented using the  BSD Socket
@@ -6,11 +7,6 @@
  *		IPv4 Forwarding Information Base: semantics.
  *
  * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
  */
 
 #include <linux/uaccess.h>
@@ -33,43 +29,42 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/netlink.h>
+#include <linux/hash.h>
+#include <linux/nospec.h>
 
 #include <net/arp.h>
+#include <net/inet_dscp.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/netlink.h>
+#include <net/ip6_fib.h>
 #include <net/nexthop.h>
+#include <net/netlink.h>
+#include <net/rtnh.h>
 #include <net/lwtunnel.h>
 #include <net/fib_notifier.h>
+#include <net/addrconf.h>
 
 #include "fib_lookup.h"
 
-static DEFINE_SPINLOCK(fib_info_lock);
-static struct hlist_head *fib_info_hash;
-static struct hlist_head *fib_info_laddrhash;
-static unsigned int fib_info_hash_size;
-static unsigned int fib_info_cnt;
-
-#define DEVINDEX_HASHBITS 8
-#define DEVINDEX_HASHSIZE (1U << DEVINDEX_HASHBITS)
-static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];
-
+/* for_nexthops and change_nexthops only used when nexthop object
+ * is not set in a fib_info. The logic within can reference fib_nh.
+ */
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 
 #define for_nexthops(fi) {						\
 	int nhsel; const struct fib_nh *nh;				\
 	for (nhsel = 0, nh = (fi)->fib_nh;				\
-	     nhsel < (fi)->fib_nhs;					\
+	     nhsel < fib_info_num_path((fi));				\
 	     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;					\
+	     nhsel < fib_info_num_path((fi));				\
 	     nexthop_nh++, nhsel++)
 
 #else /* CONFIG_IP_ROUTE_MULTIPATH */
@@ -157,12 +152,12 @@ static void rt_fibinfo_free(struct rtable __rcu **rtp)
 	dst_release_immediate(&rt->dst);
 }
 
-static void free_nh_exceptions(struct fib_nh *nh)
+static void free_nh_exceptions(struct fib_nh_common *nhc)
 {
 	struct fnhe_hash_bucket *hash;
 	int i;
 
-	hash = rcu_dereference_protected(nh->nh_exceptions, 1);
+	hash = rcu_dereference_protected(nhc->nhc_exceptions, 1);
 	if (!hash)
 		return;
 	for (i = 0; i < FNHE_HASH_SIZE; i++) {
@@ -204,19 +199,37 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
 	free_percpu(rtp);
 }
 
+void fib_nh_common_release(struct fib_nh_common *nhc)
+{
+	netdev_put(nhc->nhc_dev, &nhc->nhc_dev_tracker);
+	lwtstate_put(nhc->nhc_lwtstate);
+	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
+	rt_fibinfo_free(&nhc->nhc_rth_input);
+	free_nh_exceptions(nhc);
+}
+EXPORT_SYMBOL_GPL(fib_nh_common_release);
+
+void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
+{
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	if (fib_nh->nh_tclassid)
+		atomic_dec(&net->ipv4.fib_num_tclassid_users);
+#endif
+	fib_nh_common_release(&fib_nh->nh_common);
+}
+
 /* 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);
-		lwtstate_put(nexthop_nh->nh_lwtstate);
-		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);
+	if (fi->nh) {
+		nexthop_put(fi->nh);
+	} else {
+		change_nexthops(fi) {
+			fib_nh_release(fi->fib_net, nexthop_nh);
+		} endfor_nexthops(fi);
+	}
 
 	ip_fib_metrics_put(fi->fib_metrics);
 
@@ -229,104 +242,229 @@ void free_fib_info(struct fib_info *fi)
 		pr_warn("Freeing alive fib_info %p\n", fi);
 		return;
 	}
-	fib_info_cnt--;
-#ifdef CONFIG_IP_ROUTE_CLASSID
-	change_nexthops(fi) {
-		if (nexthop_nh->nh_tclassid)
-			fi->fib_net->ipv4.fib_num_tclassid_users--;
-	} endfor_nexthops(fi);
-#endif
-	call_rcu(&fi->rcu, free_fib_info_rcu);
+
+	call_rcu_hurry(&fi->rcu, free_fib_info_rcu);
 }
 EXPORT_SYMBOL_GPL(free_fib_info);
 
 void fib_release_info(struct fib_info *fi)
 {
-	spin_lock_bh(&fib_info_lock);
-	if (fi && --fi->fib_treeref == 0) {
+	ASSERT_RTNL();
+	if (fi && refcount_dec_and_test(&fi->fib_treeref)) {
 		hlist_del(&fi->fib_hash);
+		fi->fib_net->ipv4.fib_info_cnt--;
+
 		if (fi->fib_prefsrc)
 			hlist_del(&fi->fib_lhash);
-		change_nexthops(fi) {
-			if (!nexthop_nh->nh_dev)
-				continue;
-			hlist_del(&nexthop_nh->nh_hash);
-		} endfor_nexthops(fi)
-		fi->fib_dead = 1;
+		if (fi->nh) {
+			list_del(&fi->nh_list);
+		} else {
+			change_nexthops(fi) {
+				if (!nexthop_nh->fib_nh_dev)
+					continue;
+				hlist_del_rcu(&nexthop_nh->nh_hash);
+			} endfor_nexthops(fi)
+		}
+		/* Paired with READ_ONCE() from fib_table_lookup() */
+		WRITE_ONCE(fi->fib_dead, 1);
 		fib_info_put(fi);
 	}
-	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(struct fib_info *fi, struct fib_info *ofi)
 {
-	const struct fib_nh *onh = ofi->fib_nh;
+	const struct fib_nh *onh;
+
+	if (fi->nh || ofi->nh)
+		return nexthop_cmp(fi->nh, ofi->nh) ? 0 : -1;
+
+	if (ofi->fib_nhs == 0)
+		return 0;
 
 	for_nexthops(fi) {
-		if (nh->nh_oif != onh->nh_oif ||
-		    nh->nh_gw  != onh->nh_gw ||
-		    nh->nh_scope != onh->nh_scope ||
+		onh = fib_info_nh(ofi, nhsel);
+
+		if (nh->fib_nh_oif != onh->fib_nh_oif ||
+		    nh->fib_nh_gw_family != onh->fib_nh_gw_family ||
+		    nh->fib_nh_scope != onh->fib_nh_scope ||
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-		    nh->nh_weight != onh->nh_weight ||
+		    nh->fib_nh_weight != onh->fib_nh_weight ||
 #endif
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		    nh->nh_tclassid != onh->nh_tclassid ||
 #endif
-		    lwtunnel_cmp_encap(nh->nh_lwtstate, onh->nh_lwtstate) ||
-		    ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_COMPARE_MASK))
+		    lwtunnel_cmp_encap(nh->fib_nh_lws, onh->fib_nh_lws) ||
+		    ((nh->fib_nh_flags ^ onh->fib_nh_flags) & ~RTNH_COMPARE_MASK))
+			return -1;
+
+		if (nh->fib_nh_gw_family == AF_INET &&
+		    nh->fib_nh_gw4 != onh->fib_nh_gw4)
+			return -1;
+
+		if (nh->fib_nh_gw_family == AF_INET6 &&
+		    ipv6_addr_cmp(&nh->fib_nh_gw6, &onh->fib_nh_gw6))
 			return -1;
-		onh++;
 	} endfor_nexthops(fi);
 	return 0;
 }
 
-static inline unsigned int fib_devindex_hashfn(unsigned int val)
+static struct hlist_head *fib_nh_head(struct net_device *dev)
 {
-	unsigned int mask = DEVINDEX_HASHSIZE - 1;
+	return &dev->fib_nh_head;
+}
 
-	return (val ^
-		(val >> DEVINDEX_HASHBITS) ^
-		(val >> (DEVINDEX_HASHBITS * 2))) & mask;
+static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope,
+				      u32 prefsrc, u32 priority)
+{
+	unsigned int val = init_val;
+
+	val ^= (protocol << 8) | scope;
+	val ^= prefsrc;
+	val ^= priority;
+
+	return val;
 }
 
-static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
+static unsigned int fib_info_hashfn_result(const struct net *net,
+					   unsigned int val)
 {
-	unsigned int mask = (fib_info_hash_size - 1);
-	unsigned int val = fi->fib_nhs;
+	return hash_32(val ^ net_hash_mix(net), net->ipv4.fib_info_hash_bits);
+}
 
-	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)
+static struct hlist_head *fib_info_hash_bucket(struct fib_info *fi)
+{
+	struct net *net = fi->fib_net;
+	unsigned int val;
 
-	return (val ^ (val >> 7) ^ (val >> 12)) & mask;
+	val = fib_info_hashfn_1(fi->fib_nhs, fi->fib_protocol,
+				fi->fib_scope, (__force u32)fi->fib_prefsrc,
+				fi->fib_priority);
+
+	if (fi->nh) {
+		val ^= fi->nh->id;
+	} else {
+		for_nexthops(fi) {
+			val ^= nh->fib_nh_oif;
+		} endfor_nexthops(fi)
+	}
+
+	return &net->ipv4.fib_info_hash[fib_info_hashfn_result(net, val)];
+}
+
+static struct hlist_head *fib_info_laddrhash_bucket(const struct net *net,
+						    __be32 val)
+{
+	unsigned int hash_bits = net->ipv4.fib_info_hash_bits;
+	u32 slot;
+
+	slot = hash_32(net_hash_mix(net) ^ (__force u32)val, hash_bits);
+
+	return &net->ipv4.fib_info_hash[(1 << hash_bits) + slot];
+}
+
+static struct hlist_head *fib_info_hash_alloc(unsigned int hash_bits)
+{
+	/* The second half is used for prefsrc */
+	return kvcalloc((1 << hash_bits) * 2, sizeof(struct hlist_head),
+			GFP_KERNEL);
 }
 
-static struct fib_info *fib_find_info(const struct fib_info *nfi)
+static void fib_info_hash_free(struct hlist_head *head)
+{
+	kvfree(head);
+}
+
+static void fib_info_hash_grow(struct net *net)
+{
+	unsigned int old_size = 1 << net->ipv4.fib_info_hash_bits;
+	struct hlist_head *new_info_hash, *old_info_hash;
+	unsigned int i;
+
+	if (net->ipv4.fib_info_cnt < old_size)
+		return;
+
+	new_info_hash = fib_info_hash_alloc(net->ipv4.fib_info_hash_bits + 1);
+	if (!new_info_hash)
+		return;
+
+	old_info_hash = net->ipv4.fib_info_hash;
+	net->ipv4.fib_info_hash = new_info_hash;
+	net->ipv4.fib_info_hash_bits += 1;
+
+	for (i = 0; i < old_size; i++) {
+		struct hlist_head *head = &old_info_hash[i];
+		struct hlist_node *n;
+		struct fib_info *fi;
+
+		hlist_for_each_entry_safe(fi, n, head, fib_hash)
+			hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
+	}
+
+	for (i = 0; i < old_size; i++) {
+		struct hlist_head *lhead = &old_info_hash[old_size + i];
+		struct hlist_node *n;
+		struct fib_info *fi;
+
+		hlist_for_each_entry_safe(fi, n, lhead, fib_lhash)
+			hlist_add_head(&fi->fib_lhash,
+				       fib_info_laddrhash_bucket(fi->fib_net,
+								 fi->fib_prefsrc));
+	}
+
+	fib_info_hash_free(old_info_hash);
+}
+
+/* no metrics, only nexthop id */
+static struct fib_info *fib_find_info_nh(struct net *net,
+					 const struct fib_config *cfg)
 {
 	struct hlist_head *head;
 	struct fib_info *fi;
 	unsigned int hash;
 
-	hash = fib_info_hashfn(nfi);
-	head = &fib_info_hash[hash];
+	hash = fib_info_hashfn_1(cfg->fc_nh_id,
+				 cfg->fc_protocol, cfg->fc_scope,
+				 (__force u32)cfg->fc_prefsrc,
+				 cfg->fc_priority);
+	hash = fib_info_hashfn_result(net, hash);
+	head = &net->ipv4.fib_info_hash[hash];
 
 	hlist_for_each_entry(fi, head, fib_hash) {
-		if (!net_eq(fi->fib_net, nfi->fib_net))
+		if (!fi->nh || fi->nh->id != cfg->fc_nh_id)
 			continue;
+
+		if (cfg->fc_protocol == fi->fib_protocol &&
+		    cfg->fc_scope == fi->fib_scope &&
+		    cfg->fc_prefsrc == fi->fib_prefsrc &&
+		    cfg->fc_priority == fi->fib_priority &&
+		    cfg->fc_type == fi->fib_type &&
+		    cfg->fc_table == fi->fib_tb_id &&
+		    !((cfg->fc_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK))
+			return fi;
+	}
+
+	return NULL;
+}
+
+static struct fib_info *fib_find_info(struct fib_info *nfi)
+{
+	struct hlist_head *head = fib_info_hash_bucket(nfi);
+	struct fib_info *fi;
+
+	hlist_for_each_entry(fi, head, fib_hash) {
 		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 &&
+		    nfi->fib_tb_id == fi->fib_tb_id &&
 		    memcmp(nfi->fib_metrics, fi->fib_metrics,
 			   sizeof(u32) * RTAX_MAX) == 0 &&
 		    !((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK) &&
-		    (nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0))
+		    nh_comp(fi, nfi) == 0)
 			return fi;
 	}
 
@@ -334,33 +472,27 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi)
 }
 
 /* Check, that the gateway is already configured.
- * Used only by redirect accept routine.
+ * Used only by redirect accept routine, under rcu_read_lock();
  */
 int ip_fib_check_default(__be32 gw, struct net_device *dev)
 {
 	struct hlist_head *head;
 	struct fib_nh *nh;
-	unsigned int hash;
 
-	spin_lock(&fib_info_lock);
+	head = fib_nh_head(dev);
 
-	hash = fib_devindex_hashfn(dev->ifindex);
-	head = &fib_info_devhash[hash];
-	hlist_for_each_entry(nh, head, nh_hash) {
-		if (nh->nh_dev == dev &&
-		    nh->nh_gw == gw &&
-		    !(nh->nh_flags & RTNH_F_DEAD)) {
-			spin_unlock(&fib_info_lock);
+	hlist_for_each_entry_rcu(nh, head, nh_hash) {
+		DEBUG_NET_WARN_ON_ONCE(nh->fib_nh_dev != dev);
+		if (nh->fib_nh_gw4 == gw &&
+		    !(nh->fib_nh_flags & RTNH_F_DEAD)) {
 			return 0;
 		}
 	}
 
-	spin_unlock(&fib_info_lock);
-
 	return -1;
 }
 
-static inline size_t fib_nlmsg_size(struct fib_info *fi)
+size_t fib_nlmsg_size(struct fib_info *fi)
 {
 	size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
 			 + nla_total_size(4) /* RTA_TABLE */
@@ -368,34 +500,40 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi)
 			 + nla_total_size(4) /* RTA_PRIORITY */
 			 + nla_total_size(4) /* RTA_PREFSRC */
 			 + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
+	unsigned int nhs = fib_info_num_path(fi);
 
 	/* space for nested metrics */
 	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
 
-	if (fi->fib_nhs) {
+	if (fi->nh)
+		payload += nla_total_size(4); /* RTA_NH_ID */
+
+	if (nhs) {
 		size_t nh_encapsize = 0;
-		/* Also handles the special case fib_nhs == 1 */
+		/* Also handles the special case nhs == 1 */
 
 		/* each nexthop is packed in an attribute */
 		size_t nhsize = nla_total_size(sizeof(struct rtnexthop));
+		unsigned int i;
 
 		/* may contain flow and gateway attribute */
 		nhsize += 2 * nla_total_size(4);
 
 		/* grab encap info */
-		for_nexthops(fi) {
-			if (nh->nh_lwtstate) {
+		for (i = 0; i < fib_info_num_path(fi); i++) {
+			struct fib_nh_common *nhc = fib_info_nhc(fi, i);
+
+			if (nhc->nhc_lwtstate) {
 				/* RTA_ENCAP_TYPE */
 				nh_encapsize += lwtunnel_get_encap_size(
-						nh->nh_lwtstate);
+						nhc->nhc_lwtstate);
 				/* RTA_ENCAP */
 				nh_encapsize +=  nla_total_size(2);
 			}
-		} endfor_nexthops(fi);
+		}
 
 		/* all nexthops are packed in a nested attribute */
-		payload += nla_total_size((fi->fib_nhs * nhsize) +
-					  nh_encapsize);
+		payload += nla_total_size((nhs * nhsize) + nh_encapsize);
 
 	}
 
@@ -406,6 +544,7 @@ 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 fib_rt_info fri;
 	struct sk_buff *skb;
 	u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 	int err = -ENOBUFS;
@@ -414,9 +553,16 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
 	if (!skb)
 		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);
+	fri.fi = fa->fa_info;
+	fri.tb_id = tb_id;
+	fri.dst = key;
+	fri.dst_len = dst_len;
+	fri.dscp = fa->fa_dscp;
+	fri.type = fa->fa_type;
+	fri.offload = READ_ONCE(fa->offload);
+	fri.trap = READ_ONCE(fa->trap);
+	fri.offload_failed = READ_ONCE(fa->offload_failed);
+	err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -427,20 +573,27 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
 		    info->nlh, GFP_KERNEL);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
+	rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
 }
 
 static int fib_detect_death(struct fib_info *fi, int order,
 			    struct fib_info **last_resort, int *last_idx,
 			    int dflt)
 {
+	const struct fib_nh_common *nhc = fib_info_nhc(fi, 0);
 	struct neighbour *n;
 	int state = NUD_NONE;
 
-	n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].nh_gw, fi->fib_dev);
+	if (likely(nhc->nhc_gw_family == AF_INET))
+		n = neigh_lookup(&arp_tbl, &nhc->nhc_gw.ipv4, nhc->nhc_dev);
+	else if (nhc->nhc_gw_family == AF_INET6)
+		n = neigh_lookup(ipv6_stub->nd_tbl, &nhc->nhc_gw.ipv6,
+				 nhc->nhc_dev);
+	else
+		n = NULL;
+
 	if (n) {
-		state = n->nud_state;
+		state = READ_ONCE(n->nud_state);
 		neigh_release(n);
 	} else {
 		return 0;
@@ -457,6 +610,72 @@ static int fib_detect_death(struct fib_info *fi, int order,
 	return 1;
 }
 
+int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc,
+		       struct nlattr *encap, u16 encap_type,
+		       void *cfg, gfp_t gfp_flags,
+		       struct netlink_ext_ack *extack)
+{
+	int err;
+
+	nhc->nhc_pcpu_rth_output = alloc_percpu_gfp(struct rtable __rcu *,
+						    gfp_flags);
+	if (!nhc->nhc_pcpu_rth_output)
+		return -ENOMEM;
+
+	if (encap) {
+		struct lwtunnel_state *lwtstate;
+
+		err = lwtunnel_build_state(net, encap_type, encap,
+					   nhc->nhc_family, cfg, &lwtstate,
+					   extack);
+		if (err)
+			goto lwt_failure;
+
+		nhc->nhc_lwtstate = lwtstate_get(lwtstate);
+	}
+
+	return 0;
+
+lwt_failure:
+	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
+	nhc->nhc_pcpu_rth_output = NULL;
+	return err;
+}
+EXPORT_SYMBOL_GPL(fib_nh_common_init);
+
+int fib_nh_init(struct net *net, struct fib_nh *nh,
+		struct fib_config *cfg, int nh_weight,
+		struct netlink_ext_ack *extack)
+{
+	int err;
+
+	nh->fib_nh_family = AF_INET;
+
+	err = fib_nh_common_init(net, &nh->nh_common, cfg->fc_encap,
+				 cfg->fc_encap_type, cfg, GFP_KERNEL, extack);
+	if (err)
+		return err;
+
+	nh->fib_nh_oif = cfg->fc_oif;
+	nh->fib_nh_gw_family = cfg->fc_gw_family;
+	if (cfg->fc_gw_family == AF_INET)
+		nh->fib_nh_gw4 = cfg->fc_gw4;
+	else if (cfg->fc_gw_family == AF_INET6)
+		nh->fib_nh_gw6 = cfg->fc_gw6;
+
+	nh->fib_nh_flags = cfg->fc_flags;
+
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	nh->nh_tclassid = cfg->fc_flow;
+	if (nh->nh_tclassid)
+		atomic_inc(&net->ipv4.fib_num_tclassid_users);
+#endif
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+	nh->fib_nh_weight = nh_weight;
+#endif
+	return 0;
+}
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 
 static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining,
@@ -479,15 +698,34 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining,
 	return nhs;
 }
 
+static int fib_gw_from_attr(__be32 *gw, struct nlattr *nla,
+			    struct netlink_ext_ack *extack)
+{
+	if (nla_len(nla) < sizeof(*gw)) {
+		NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_GATEWAY");
+		return -EINVAL;
+	}
+
+	*gw = nla_get_in_addr(nla);
+
+	return 0;
+}
+
+/* only called when fib_nh is integrated into fib_info */
 static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 		       int remaining, struct fib_config *cfg,
 		       struct netlink_ext_ack *extack)
 {
+	struct net *net = fi->fib_net;
+	struct fib_config fib_cfg;
+	struct fib_nh *nh;
 	int ret;
 
 	change_nexthops(fi) {
 		int attrlen;
 
+		memset(&fib_cfg, 0, sizeof(fib_cfg));
+
 		if (!rtnh_ok(rtnh, remaining)) {
 			NL_SET_ERR_MSG(extack,
 				       "Invalid nexthop configuration - extra data after nexthop");
@@ -500,112 +738,145 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 			return -EINVAL;
 		}
 
-		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;
+		fib_cfg.fc_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
+		fib_cfg.fc_oif = rtnh->rtnh_ifindex;
 
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
-			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+			struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
-			nexthop_nh->nh_gw = nla ? nla_get_in_addr(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
-			nla = nla_find(attrs, attrlen, RTA_ENCAP);
+			nlav = nla_find(attrs, attrlen, RTA_VIA);
+			if (nla && nlav) {
+				NL_SET_ERR_MSG(extack,
+					       "Nexthop configuration can not contain both GATEWAY and VIA");
+				return -EINVAL;
+			}
 			if (nla) {
-				struct lwtunnel_state *lwtstate;
-				struct nlattr *nla_entype;
-
-				nla_entype = nla_find(attrs, attrlen,
-						      RTA_ENCAP_TYPE);
-				if (!nla_entype) {
-					NL_SET_BAD_ATTR(extack, nla);
-					NL_SET_ERR_MSG(extack,
-						       "Encap type is missing");
-					goto err_inval;
-				}
+				ret = fib_gw_from_attr(&fib_cfg.fc_gw4, nla,
+						       extack);
+				if (ret)
+					goto errout;
 
-				ret = lwtunnel_build_state(nla_get_u16(
-							   nla_entype),
-							   nla,  AF_INET, cfg,
-							   &lwtstate, extack);
+				if (fib_cfg.fc_gw4)
+					fib_cfg.fc_gw_family = AF_INET;
+			} else if (nlav) {
+				ret = fib_gw_from_via(&fib_cfg, nlav, extack);
 				if (ret)
 					goto errout;
-				nexthop_nh->nh_lwtstate =
-					lwtstate_get(lwtstate);
 			}
+
+			nla = nla_find(attrs, attrlen, RTA_FLOW);
+			if (nla) {
+				if (nla_len(nla) < sizeof(u32)) {
+					NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW");
+					return -EINVAL;
+				}
+				fib_cfg.fc_flow = nla_get_u32(nla);
+			}
+
+			fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
+			/* RTA_ENCAP_TYPE length checked in
+			 * lwtunnel_valid_encap_type_attr
+			 */
+			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
+			if (nla)
+				fib_cfg.fc_encap_type = nla_get_u16(nla);
 		}
 
+		ret = fib_nh_init(net, nexthop_nh, &fib_cfg,
+				  rtnh->rtnh_hops + 1, extack);
+		if (ret)
+			goto errout;
+
 		rtnh = rtnh_next(rtnh, &remaining);
 	} endfor_nexthops(fi);
 
-	return 0;
-
-err_inval:
 	ret = -EINVAL;
-
+	nh = fib_info_nh(fi, 0);
+	if (cfg->fc_oif && nh->fib_nh_oif != cfg->fc_oif) {
+		NL_SET_ERR_MSG(extack,
+			       "Nexthop device index does not match RTA_OIF");
+		goto errout;
+	}
+	if (cfg->fc_gw_family) {
+		if (cfg->fc_gw_family != nh->fib_nh_gw_family ||
+		    (cfg->fc_gw_family == AF_INET &&
+		     nh->fib_nh_gw4 != cfg->fc_gw4) ||
+		    (cfg->fc_gw_family == AF_INET6 &&
+		     ipv6_addr_cmp(&nh->fib_nh_gw6, &cfg->fc_gw6))) {
+			NL_SET_ERR_MSG(extack,
+				       "Nexthop gateway does not match RTA_GATEWAY or RTA_VIA");
+			goto errout;
+		}
+	}
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	if (cfg->fc_flow && nh->nh_tclassid != cfg->fc_flow) {
+		NL_SET_ERR_MSG(extack,
+			       "Nexthop class id does not match RTA_FLOW");
+		goto errout;
+	}
+#endif
+	ret = 0;
 errout:
 	return ret;
 }
 
+/* only called when fib_nh is integrated into fib_info */
 static void fib_rebalance(struct fib_info *fi)
 {
 	int total;
 	int w;
-	struct in_device *in_dev;
 
-	if (fi->fib_nhs < 2)
+	if (fib_info_num_path(fi) < 2)
 		return;
 
 	total = 0;
 	for_nexthops(fi) {
-		if (nh->nh_flags & RTNH_F_DEAD)
+		if (nh->fib_nh_flags & RTNH_F_DEAD)
 			continue;
 
-		in_dev = __in_dev_get_rtnl(nh->nh_dev);
-
-		if (in_dev &&
-		    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-		    nh->nh_flags & RTNH_F_LINKDOWN)
+		if (ip_ignore_linkdown(nh->fib_nh_dev) &&
+		    nh->fib_nh_flags & RTNH_F_LINKDOWN)
 			continue;
 
-		total += nh->nh_weight;
+		total += nh->fib_nh_weight;
 	} endfor_nexthops(fi);
 
 	w = 0;
 	change_nexthops(fi) {
 		int upper_bound;
 
-		in_dev = __in_dev_get_rtnl(nexthop_nh->nh_dev);
-
-		if (nexthop_nh->nh_flags & RTNH_F_DEAD) {
+		if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) {
 			upper_bound = -1;
-		} else if (in_dev &&
-			   IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-			   nexthop_nh->nh_flags & RTNH_F_LINKDOWN) {
+		} else if (ip_ignore_linkdown(nexthop_nh->fib_nh_dev) &&
+			   nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) {
 			upper_bound = -1;
 		} else {
-			w += nexthop_nh->nh_weight;
+			w += nexthop_nh->fib_nh_weight;
 			upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31,
 							    total) - 1;
 		}
 
-		atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
+		atomic_set(&nexthop_nh->fib_nh_upper_bound, upper_bound);
 	} endfor_nexthops(fi);
 }
 #else /* CONFIG_IP_ROUTE_MULTIPATH */
 
+static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
+		       int remaining, struct fib_config *cfg,
+		       struct netlink_ext_ack *extack)
+{
+	NL_SET_ERR_MSG(extack, "Multipath support not enabled in kernel");
+
+	return -EINVAL;
+}
+
 #define fib_rebalance(fi) do { } while (0)
 
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
 
-static int fib_encap_match(u16 encap_type,
+static int fib_encap_match(struct net *net, u16 encap_type,
 			   struct nlattr *encap,
 			   const struct fib_nh *nh,
 			   const struct fib_config *cfg,
@@ -617,17 +888,17 @@ static int fib_encap_match(u16 encap_type,
 	if (encap_type == LWTUNNEL_ENCAP_NONE)
 		return 0;
 
-	ret = lwtunnel_build_state(encap_type, encap, AF_INET,
+	ret = lwtunnel_build_state(net, encap_type, encap, AF_INET,
 				   cfg, &lwtstate, extack);
 	if (!ret) {
-		result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate);
+		result = lwtunnel_cmp_encap(lwtstate, nh->fib_nh_lws);
 		lwtstate_free(lwtstate);
 	}
 
 	return result;
 }
 
-int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
+int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
 		 struct netlink_ext_ack *extack)
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -638,21 +909,46 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 	if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
 		return 1;
 
-	if (cfg->fc_oif || cfg->fc_gw) {
+	if (cfg->fc_nh_id) {
+		if (fi->nh && cfg->fc_nh_id == fi->nh->id)
+			return 0;
+		return 1;
+	}
+
+	if (fi->nh) {
+		if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_mp)
+			return 1;
+		return 0;
+	}
+
+	if (cfg->fc_oif || cfg->fc_gw_family) {
+		struct fib_nh *nh;
+
+		nh = fib_info_nh(fi, 0);
 		if (cfg->fc_encap) {
-			if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap,
-					    fi->fib_nh, cfg, extack))
+			if (fib_encap_match(net, cfg->fc_encap_type,
+					    cfg->fc_encap, nh, cfg, extack))
 				return 1;
 		}
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		if (cfg->fc_flow &&
-		    cfg->fc_flow != fi->fib_nh->nh_tclassid)
+		    cfg->fc_flow != nh->nh_tclassid)
 			return 1;
 #endif
-		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;
+		if ((cfg->fc_oif && cfg->fc_oif != nh->fib_nh_oif) ||
+		    (cfg->fc_gw_family &&
+		     cfg->fc_gw_family != nh->fib_nh_gw_family))
+			return 1;
+
+		if (cfg->fc_gw_family == AF_INET &&
+		    cfg->fc_gw4 != nh->fib_nh_gw4)
+			return 1;
+
+		if (cfg->fc_gw_family == AF_INET6 &&
+		    ipv6_addr_cmp(&cfg->fc_gw6, &nh->fib_nh_gw6))
+			return 1;
+
+		return 0;
 	}
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -668,20 +964,64 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 		if (!rtnh_ok(rtnh, remaining))
 			return -EINVAL;
 
-		if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->nh_oif)
+		if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->fib_nh_oif)
 			return 1;
 
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
-			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+			struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
+			int err;
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
-			if (nla && nla_get_in_addr(nla) != nh->nh_gw)
-				return 1;
+			nlav = nla_find(attrs, attrlen, RTA_VIA);
+			if (nla && nlav) {
+				NL_SET_ERR_MSG(extack,
+					       "Nexthop configuration can not contain both GATEWAY and VIA");
+				return -EINVAL;
+			}
+
+			if (nla) {
+				__be32 gw;
+
+				err = fib_gw_from_attr(&gw, nla, extack);
+				if (err)
+					return err;
+
+				if (nh->fib_nh_gw_family != AF_INET ||
+				    gw != nh->fib_nh_gw4)
+					return 1;
+			} else if (nlav) {
+				struct fib_config cfg2;
+
+				err = fib_gw_from_via(&cfg2, nlav, extack);
+				if (err)
+					return err;
+
+				switch (nh->fib_nh_gw_family) {
+				case AF_INET:
+					if (cfg2.fc_gw_family != AF_INET ||
+					    cfg2.fc_gw4 != nh->fib_nh_gw4)
+						return 1;
+					break;
+				case AF_INET6:
+					if (cfg2.fc_gw_family != AF_INET6 ||
+					    ipv6_addr_cmp(&cfg2.fc_gw6,
+							  &nh->fib_nh_gw6))
+						return 1;
+					break;
+				}
+			}
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
-			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
-				return 1;
+			if (nla) {
+				if (nla_len(nla) < sizeof(u32)) {
+					NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW");
+					return -EINVAL;
+				}
+				if (nla_get_u32(nla) != nh->nh_tclassid)
+					return 1;
+			}
 #endif
 		}
 
@@ -708,12 +1048,13 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
 		if (type > RTAX_MAX)
 			return false;
 
+		type = array_index_nospec(type, RTAX_MAX + 1);
 		if (type == RTAX_CC_ALGO) {
 			char tmp[TCP_CA_NAME_MAX];
 			bool ecn_ca = false;
 
-			nla_strlcpy(tmp, nla, sizeof(tmp));
-			val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
+			nla_strscpy(tmp, nla, sizeof(tmp));
+			val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
 		} else {
 			if (nla_len(nla) != sizeof(u32))
 				return false;
@@ -731,6 +1072,31 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
 	return true;
 }
 
+static int fib_check_nh_v6_gw(struct net *net, struct fib_nh *nh,
+			      u32 table, struct netlink_ext_ack *extack)
+{
+	struct fib6_config cfg = {
+		.fc_table = table,
+		.fc_flags = nh->fib_nh_flags | RTF_GATEWAY,
+		.fc_ifindex = nh->fib_nh_oif,
+		.fc_gateway = nh->fib_nh_gw6,
+	};
+	struct fib6_nh fib6_nh = {};
+	int err;
+
+	err = ipv6_stub->fib6_nh_init(net, &fib6_nh, &cfg, GFP_KERNEL, extack);
+	if (!err) {
+		nh->fib_nh_dev = fib6_nh.fib_nh_dev;
+		netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker,
+			    GFP_KERNEL);
+		nh->fib_nh_oif = nh->fib_nh_dev->ifindex;
+		nh->fib_nh_scope = RT_SCOPE_LINK;
+
+		ipv6_stub->fib6_nh_release(&fib6_nh);
+	}
+
+	return err;
+}
 
 /*
  * Picture
@@ -775,223 +1141,185 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
  *					|
  *					|-> {local prefix} (terminal node)
  */
-static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
-			struct netlink_ext_ack *extack)
+static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table,
+			      u8 scope, struct netlink_ext_ack *extack)
 {
-	int err = 0;
-	struct net *net;
 	struct net_device *dev;
+	struct fib_result res;
+	int err = 0;
 
-	net = cfg->fc_nlinfo.nl_net;
-	if (nh->nh_gw) {
-		struct fib_result res;
-
-		if (nh->nh_flags & RTNH_F_ONLINK) {
-			unsigned int addr_type;
+	if (nh->fib_nh_flags & RTNH_F_ONLINK) {
+		unsigned int addr_type;
 
-			if (cfg->fc_scope >= RT_SCOPE_LINK) {
-				NL_SET_ERR_MSG(extack,
-					       "Nexthop has invalid scope");
-				return -EINVAL;
-			}
-			dev = __dev_get_by_index(net, nh->nh_oif);
-			if (!dev) {
-				NL_SET_ERR_MSG(extack, "Nexthop device required for onlink");
-				return -ENODEV;
-			}
-			if (!(dev->flags & IFF_UP)) {
-				NL_SET_ERR_MSG(extack,
-					       "Nexthop device is not up");
-				return -ENETDOWN;
-			}
-			addr_type = inet_addr_type_dev_table(net, dev, nh->nh_gw);
-			if (addr_type != RTN_UNICAST) {
-				NL_SET_ERR_MSG(extack,
-					       "Nexthop has invalid gateway");
-				return -EINVAL;
-			}
-			if (!netif_carrier_ok(dev))
-				nh->nh_flags |= RTNH_F_LINKDOWN;
-			nh->nh_dev = dev;
-			dev_hold(dev);
-			nh->nh_scope = RT_SCOPE_LINK;
-			return 0;
+		if (scope >= RT_SCOPE_LINK) {
+			NL_SET_ERR_MSG(extack, "Nexthop has invalid scope");
+			return -EINVAL;
 		}
-		rcu_read_lock();
-		{
-			struct fib_table *tbl = NULL;
-			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 (fl4.flowi4_scope < RT_SCOPE_LINK)
-				fl4.flowi4_scope = RT_SCOPE_LINK;
-
-			if (cfg->fc_table)
-				tbl = fib_get_table(net, cfg->fc_table);
-
-			if (tbl)
-				err = fib_table_lookup(tbl, &fl4, &res,
-						       FIB_LOOKUP_IGNORE_LINKSTATE |
-						       FIB_LOOKUP_NOREF);
-
-			/* on error or if no table given do full lookup. This
-			 * is needed for example when nexthops are in the local
-			 * table rather than the given table
-			 */
-			if (!tbl || err) {
-				err = fib_lookup(net, &fl4, &res,
-						 FIB_LOOKUP_IGNORE_LINKSTATE);
-			}
-
-			if (err) {
-				NL_SET_ERR_MSG(extack,
-					       "Nexthop has invalid gateway");
-				rcu_read_unlock();
-				return err;
-			}
+		dev = __dev_get_by_index(net, nh->fib_nh_oif);
+		if (!dev) {
+			NL_SET_ERR_MSG(extack, "Nexthop device required for onlink");
+			return -ENODEV;
 		}
-		err = -EINVAL;
-		if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) {
-			NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
-			goto out;
+		if (!(dev->flags & IFF_UP)) {
+			NL_SET_ERR_MSG(extack, "Nexthop device is not up");
+			return -ENETDOWN;
 		}
-		nh->nh_scope = res.scope;
-		nh->nh_oif = FIB_RES_OIF(res);
-		nh->nh_dev = dev = FIB_RES_DEV(res);
-		if (!dev) {
-			NL_SET_ERR_MSG(extack,
-				       "No egress device for nexthop gateway");
-			goto out;
+		addr_type = inet_addr_type_dev_table(net, dev, nh->fib_nh_gw4);
+		if (addr_type != RTN_UNICAST) {
+			NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
+			return -EINVAL;
 		}
-		dev_hold(dev);
 		if (!netif_carrier_ok(dev))
-			nh->nh_flags |= RTNH_F_LINKDOWN;
-		err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN;
-	} else {
-		struct in_device *in_dev;
-
-		if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) {
-			NL_SET_ERR_MSG(extack,
-				       "Invalid flags for nexthop - PERVASIVE and ONLINK can not be set");
-			return -EINVAL;
+			nh->fib_nh_flags |= RTNH_F_LINKDOWN;
+		nh->fib_nh_dev = dev;
+		netdev_hold(dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC);
+		nh->fib_nh_scope = RT_SCOPE_LINK;
+		return 0;
+	}
+	rcu_read_lock();
+	{
+		struct fib_table *tbl = NULL;
+		struct flowi4 fl4 = {
+			.daddr = nh->fib_nh_gw4,
+			.flowi4_scope = scope + 1,
+			.flowi4_oif = nh->fib_nh_oif,
+			.flowi4_iif = LOOPBACK_IFINDEX,
+		};
+
+		/* It is not necessary, but requires a bit of thinking */
+		if (fl4.flowi4_scope < RT_SCOPE_LINK)
+			fl4.flowi4_scope = RT_SCOPE_LINK;
+
+		if (table && table != RT_TABLE_MAIN)
+			tbl = fib_get_table(net, table);
+
+		if (tbl)
+			err = fib_table_lookup(tbl, &fl4, &res,
+					       FIB_LOOKUP_IGNORE_LINKSTATE |
+					       FIB_LOOKUP_NOREF);
+
+		/* on error or if no table given do full lookup. This
+		 * is needed for example when nexthops are in the local
+		 * table rather than the given table
+		 */
+		if (!tbl || err) {
+			err = fib_lookup(net, &fl4, &res,
+					 FIB_LOOKUP_IGNORE_LINKSTATE);
 		}
-		rcu_read_lock();
-		err = -ENODEV;
-		in_dev = inetdev_by_index(net, nh->nh_oif);
-		if (!in_dev)
-			goto out;
-		err = -ENETDOWN;
-		if (!(in_dev->dev->flags & IFF_UP)) {
-			NL_SET_ERR_MSG(extack, "Device for nexthop is not up");
+
+		if (err) {
+			NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
 			goto out;
 		}
-		nh->nh_dev = in_dev->dev;
-		dev_hold(nh->nh_dev);
-		nh->nh_scope = RT_SCOPE_HOST;
-		if (!netif_carrier_ok(nh->nh_dev))
-			nh->nh_flags |= RTNH_F_LINKDOWN;
-		err = 0;
 	}
+
+	err = -EINVAL;
+	if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) {
+		NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
+		goto out;
+	}
+	nh->fib_nh_scope = res.scope;
+	nh->fib_nh_oif = FIB_RES_OIF(res);
+	nh->fib_nh_dev = dev = FIB_RES_DEV(res);
+	if (!dev) {
+		NL_SET_ERR_MSG(extack,
+			       "No egress device for nexthop gateway");
+		goto out;
+	}
+	netdev_hold(dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC);
+	if (!netif_carrier_ok(dev))
+		nh->fib_nh_flags |= RTNH_F_LINKDOWN;
+	err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN;
 out:
 	rcu_read_unlock();
 	return err;
 }
 
-static inline unsigned int fib_laddr_hashfn(__be32 val)
+static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh,
+			      struct netlink_ext_ack *extack)
 {
-	unsigned int mask = (fib_info_hash_size - 1);
+	struct in_device *in_dev;
+	int err;
 
-	return ((__force u32)val ^
-		((__force u32)val >> 7) ^
-		((__force u32)val >> 14)) & mask;
-}
+	if (nh->fib_nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) {
+		NL_SET_ERR_MSG(extack,
+			       "Invalid flags for nexthop - PERVASIVE and ONLINK can not be set");
+		return -EINVAL;
+	}
 
-static struct hlist_head *fib_info_hash_alloc(int bytes)
-{
-	if (bytes <= PAGE_SIZE)
-		return kzalloc(bytes, GFP_KERNEL);
-	else
-		return (struct hlist_head *)
-			__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-					 get_order(bytes));
+	rcu_read_lock();
+
+	err = -ENODEV;
+	in_dev = inetdev_by_index(net, nh->fib_nh_oif);
+	if (!in_dev)
+		goto out;
+	err = -ENETDOWN;
+	if (!(in_dev->dev->flags & IFF_UP)) {
+		NL_SET_ERR_MSG(extack, "Device for nexthop is not up");
+		goto out;
+	}
+
+	nh->fib_nh_dev = in_dev->dev;
+	netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC);
+	nh->fib_nh_scope = RT_SCOPE_HOST;
+	if (!netif_carrier_ok(nh->fib_nh_dev))
+		nh->fib_nh_flags |= RTNH_F_LINKDOWN;
+	err = 0;
+out:
+	rcu_read_unlock();
+	return err;
 }
 
-static void fib_info_hash_free(struct hlist_head *hash, int bytes)
+int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,
+		 struct netlink_ext_ack *extack)
 {
-	if (!hash)
-		return;
+	int err;
 
-	if (bytes <= PAGE_SIZE)
-		kfree(hash);
+	if (nh->fib_nh_gw_family == AF_INET)
+		err = fib_check_nh_v4_gw(net, nh, table, scope, extack);
+	else if (nh->fib_nh_gw_family == AF_INET6)
+		err = fib_check_nh_v6_gw(net, nh, table, extack);
 	else
-		free_pages((unsigned long) hash, get_order(bytes));
+		err = fib_check_nh_nongw(net, nh, extack);
+
+	return err;
 }
 
-static void fib_info_hash_move(struct hlist_head *new_info_hash,
-			       struct hlist_head *new_laddrhash,
-			       unsigned int new_size)
+__be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc,
+				 unsigned char scope)
 {
-	struct hlist_head *old_info_hash, *old_laddrhash;
-	unsigned int old_size = fib_info_hash_size;
-	unsigned int i, bytes;
-
-	spin_lock_bh(&fib_info_lock);
-	old_info_hash = fib_info_hash;
-	old_laddrhash = fib_info_laddrhash;
-	fib_info_hash_size = new_size;
-
-	for (i = 0; i < old_size; i++) {
-		struct hlist_head *head = &fib_info_hash[i];
-		struct hlist_node *n;
-		struct fib_info *fi;
+	struct fib_nh *nh;
+	__be32 saddr;
 
-		hlist_for_each_entry_safe(fi, n, head, fib_hash) {
-			struct hlist_head *dest;
-			unsigned int new_hash;
+	if (nhc->nhc_family != AF_INET)
+		return inet_select_addr(nhc->nhc_dev, 0, scope);
 
-			new_hash = fib_info_hashfn(fi);
-			dest = &new_info_hash[new_hash];
-			hlist_add_head(&fi->fib_hash, dest);
-		}
-	}
-	fib_info_hash = new_info_hash;
+	nh = container_of(nhc, struct fib_nh, nh_common);
+	saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope);
 
-	for (i = 0; i < old_size; i++) {
-		struct hlist_head *lhead = &fib_info_laddrhash[i];
-		struct hlist_node *n;
-		struct fib_info *fi;
+	WRITE_ONCE(nh->nh_saddr, saddr);
+	WRITE_ONCE(nh->nh_saddr_genid, atomic_read(&net->ipv4.dev_addr_genid));
 
-		hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) {
-			struct hlist_head *ldest;
-			unsigned int new_hash;
+	return saddr;
+}
 
-			new_hash = fib_laddr_hashfn(fi->fib_prefsrc);
-			ldest = &new_laddrhash[new_hash];
-			hlist_add_head(&fi->fib_lhash, ldest);
-		}
-	}
-	fib_info_laddrhash = new_laddrhash;
+__be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
+{
+	struct fib_nh_common *nhc = res->nhc;
 
-	spin_unlock_bh(&fib_info_lock);
+	if (res->fi->fib_prefsrc)
+		return res->fi->fib_prefsrc;
 
-	bytes = old_size * sizeof(struct hlist_head *);
-	fib_info_hash_free(old_info_hash, bytes);
-	fib_info_hash_free(old_laddrhash, bytes);
-}
+	if (nhc->nhc_family == AF_INET) {
+		struct fib_nh *nh;
 
-__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);
+		nh = container_of(nhc, struct fib_nh, nh_common);
+		if (READ_ONCE(nh->nh_saddr_genid) ==
+		    atomic_read(&net->ipv4.dev_addr_genid))
+			return READ_ONCE(nh->nh_saddr);
+	}
 
-	return nh->nh_saddr;
+	return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope);
 }
 
 static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
@@ -1023,10 +1351,12 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 {
 	int err;
 	struct fib_info *fi = NULL;
+	struct nexthop *nh = NULL;
 	struct fib_info *ofi;
 	int nhs = 1;
 	struct net *net = cfg->fc_nlinfo.nl_net;
 
+	ASSERT_RTNL();
 	if (cfg->fc_type > RTN_MAX)
 		goto err_inval;
 
@@ -1042,6 +1372,23 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		goto err_inval;
 	}
 
+	if (cfg->fc_nh_id) {
+		if (!cfg->fc_mx) {
+			fi = fib_find_info_nh(net, cfg);
+			if (fi) {
+				refcount_inc(&fi->fib_treeref);
+				return fi;
+			}
+		}
+
+		nh = nexthop_find_by_id(net, cfg->fc_nh_id);
+		if (!nh) {
+			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+			goto err_inval;
+		}
+		nhs = 0;
+	}
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (cfg->fc_mp) {
 		nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len, extack);
@@ -1050,40 +1397,21 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	}
 #endif
 
-	err = -ENOBUFS;
-	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 = 16;
-		bytes = new_size * sizeof(struct hlist_head *);
-		new_info_hash = fib_info_hash_alloc(bytes);
-		new_laddrhash = fib_info_hash_alloc(bytes);
-		if (!new_info_hash || !new_laddrhash) {
-			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_info_hash_size)
-			goto failure;
-	}
+	fib_info_hash_grow(net);
 
-	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
-	if (!fi)
+	fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
+	if (!fi) {
+		err = -ENOBUFS;
 		goto failure;
-	fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx,
-					      cfg->fc_mx_len, extack);
-	if (unlikely(IS_ERR(fi->fib_metrics))) {
+	}
+
+	fi->fib_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack);
+	if (IS_ERR(fi->fib_metrics)) {
 		err = PTR_ERR(fi->fib_metrics);
 		kfree(fi);
 		return ERR_PTR(err);
 	}
 
-	fib_info_cnt++;
 	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
 	fi->fib_scope = cfg->fc_scope;
@@ -1094,74 +1422,31 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	fi->fib_tb_id = cfg->fc_table;
 
 	fi->fib_nhs = nhs;
-	change_nexthops(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)
-
-	if (cfg->fc_mp) {
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-		err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack);
-		if (err != 0)
-			goto failure;
-		if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) {
-			NL_SET_ERR_MSG(extack,
-				       "Nexthop device index does not match RTA_OIF");
-			goto err_inval;
-		}
-		if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) {
-			NL_SET_ERR_MSG(extack,
-				       "Nexthop gateway does not match RTA_GATEWAY");
-			goto err_inval;
-		}
-#ifdef CONFIG_IP_ROUTE_CLASSID
-		if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) {
-			NL_SET_ERR_MSG(extack,
-				       "Nexthop class id does not match RTA_FLOW");
-			goto err_inval;
+	if (nh) {
+		if (!nexthop_get(nh)) {
+			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+			err = -EINVAL;
+		} else {
+			err = 0;
+			fi->nh = nh;
 		}
-#endif
-#else
-		NL_SET_ERR_MSG(extack,
-			       "Multipath support not enabled in kernel");
-		goto err_inval;
-#endif
 	} else {
-		struct fib_nh *nh = fi->fib_nh;
-
-		if (cfg->fc_encap) {
-			struct lwtunnel_state *lwtstate;
-
-			if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) {
-				NL_SET_ERR_MSG(extack,
-					       "LWT encap type not specified");
-				goto err_inval;
-			}
-			err = lwtunnel_build_state(cfg->fc_encap_type,
-						   cfg->fc_encap, AF_INET, cfg,
-						   &lwtstate, extack);
-			if (err)
-				goto failure;
+		change_nexthops(fi) {
+			nexthop_nh->nh_parent = fi;
+		} endfor_nexthops(fi)
 
-			nh->nh_lwtstate = lwtstate_get(lwtstate);
-		}
-		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
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-		nh->nh_weight = 1;
-#endif
+		if (cfg->fc_mp)
+			err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg,
+					  extack);
+		else
+			err = fib_nh_init(net, fi->fib_nh, cfg, 1, extack);
 	}
 
+	if (err != 0)
+		goto failure;
+
 	if (fib_props[cfg->fc_type].error) {
-		if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) {
+		if (cfg->fc_gw_family || cfg->fc_oif || cfg->fc_mp) {
 			NL_SET_ERR_MSG(extack,
 				       "Gateway, device and multipath can not be specified for this route type");
 			goto err_inval;
@@ -1186,7 +1471,11 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		goto err_inval;
 	}
 
-	if (cfg->fc_scope == RT_SCOPE_HOST) {
+	if (fi->nh) {
+		err = fib_check_nexthop(fi->nh, cfg->fc_scope, extack);
+		if (err)
+			goto failure;
+	} else if (cfg->fc_scope == RT_SCOPE_HOST) {
 		struct fib_nh *nh = fi->fib_nh;
 
 		/* Local address is added. */
@@ -1195,24 +1484,28 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 				       "Route with host scope can not have multiple nexthops");
 			goto err_inval;
 		}
-		if (nh->nh_gw) {
+		if (nh->fib_nh_gw_family) {
 			NL_SET_ERR_MSG(extack,
 				       "Route with host scope can not have a gateway");
 			goto err_inval;
 		}
-		nh->nh_scope = RT_SCOPE_NOWHERE;
-		nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif);
+		nh->fib_nh_scope = RT_SCOPE_NOWHERE;
+		nh->fib_nh_dev = dev_get_by_index(net, nh->fib_nh_oif);
 		err = -ENODEV;
-		if (!nh->nh_dev)
+		if (!nh->fib_nh_dev)
 			goto failure;
+		netdev_tracker_alloc(nh->fib_nh_dev, &nh->fib_nh_dev_tracker,
+				     GFP_KERNEL);
 	} else {
 		int linkdown = 0;
 
 		change_nexthops(fi) {
-			err = fib_check_nh(cfg, nexthop_nh, extack);
+			err = fib_check_nh(cfg->fc_nlinfo.nl_net, nexthop_nh,
+					   cfg->fc_table, cfg->fc_scope,
+					   extack);
 			if (err != 0)
 				goto failure;
-			if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
+			if (nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN)
 				linkdown++;
 		} endfor_nexthops(fi)
 		if (linkdown == fi->fib_nhs)
@@ -1224,43 +1517,51 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		goto err_inval;
 	}
 
-	change_nexthops(fi) {
-		fib_info_update_nh_saddr(net, nexthop_nh);
-	} endfor_nexthops(fi)
+	if (!fi->nh) {
+		change_nexthops(fi) {
+			fib_info_update_nhc_saddr(net, &nexthop_nh->nh_common,
+						  fi->fib_scope);
+			if (nexthop_nh->fib_nh_gw_family == AF_INET6)
+				fi->fib_nh_is_v6 = true;
+		} endfor_nexthops(fi)
 
-	fib_rebalance(fi);
+		fib_rebalance(fi);
+	}
 
 link_it:
 	ofi = fib_find_info(fi);
 	if (ofi) {
+		/* fib_table_lookup() should not see @fi yet. */
 		fi->fib_dead = 1;
 		free_fib_info(fi);
-		ofi->fib_treeref++;
+		refcount_inc(&ofi->fib_treeref);
 		return ofi;
 	}
 
-	fi->fib_treeref++;
+	refcount_set(&fi->fib_treeref, 1);
 	refcount_set(&fi->fib_clntref, 1);
-	spin_lock_bh(&fib_info_lock);
-	hlist_add_head(&fi->fib_hash,
-		       &fib_info_hash[fib_info_hashfn(fi)]);
+
+	net->ipv4.fib_info_cnt++;
+	hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
+
 	if (fi->fib_prefsrc) {
 		struct hlist_head *head;
 
-		head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)];
+		head = fib_info_laddrhash_bucket(net, fi->fib_prefsrc);
 		hlist_add_head(&fi->fib_lhash, head);
 	}
-	change_nexthops(fi) {
-		struct hlist_head *head;
-		unsigned int hash;
+	if (fi->nh) {
+		list_add(&fi->nh_list, &nh->fi_list);
+	} else {
+		change_nexthops(fi) {
+			struct hlist_head *head;
 
-		if (!nexthop_nh->nh_dev)
-			continue;
-		hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex);
-		head = &fib_info_devhash[hash];
-		hlist_add_head(&nexthop_nh->nh_hash, head);
-	} endfor_nexthops(fi)
-	spin_unlock_bh(&fib_info_lock);
+			if (!nexthop_nh->fib_nh_dev)
+				continue;
+			head = fib_nh_head(nexthop_nh->fib_nh_dev);
+			hlist_add_head_rcu(&nexthop_nh->nh_hash, head);
+		} endfor_nexthops(fi)
+	}
 	return fi;
 
 err_inval:
@@ -1268,6 +1569,7 @@ err_inval:
 
 failure:
 	if (fi) {
+		/* fib_table_lookup() should not see @fi yet. */
 		fi->fib_dead = 1;
 		free_fib_info(fi);
 	}
@@ -1275,10 +1577,155 @@ failure:
 	return ERR_PTR(err);
 }
 
+int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
+		     u8 rt_family, unsigned char *flags, bool skip_oif)
+{
+	if (nhc->nhc_flags & RTNH_F_DEAD)
+		*flags |= RTNH_F_DEAD;
+
+	if (nhc->nhc_flags & RTNH_F_LINKDOWN) {
+		*flags |= RTNH_F_LINKDOWN;
+
+		rcu_read_lock();
+		switch (nhc->nhc_family) {
+		case AF_INET:
+			if (ip_ignore_linkdown(nhc->nhc_dev))
+				*flags |= RTNH_F_DEAD;
+			break;
+		case AF_INET6:
+			if (ip6_ignore_linkdown(nhc->nhc_dev))
+				*flags |= RTNH_F_DEAD;
+			break;
+		}
+		rcu_read_unlock();
+	}
+
+	switch (nhc->nhc_gw_family) {
+	case AF_INET:
+		if (nla_put_in_addr(skb, RTA_GATEWAY, nhc->nhc_gw.ipv4))
+			goto nla_put_failure;
+		break;
+	case AF_INET6:
+		/* if gateway family does not match nexthop family
+		 * gateway is encoded as RTA_VIA
+		 */
+		if (rt_family != nhc->nhc_gw_family) {
+			int alen = sizeof(struct in6_addr);
+			struct nlattr *nla;
+			struct rtvia *via;
+
+			nla = nla_reserve(skb, RTA_VIA, alen + 2);
+			if (!nla)
+				goto nla_put_failure;
+
+			via = nla_data(nla);
+			via->rtvia_family = AF_INET6;
+			memcpy(via->rtvia_addr, &nhc->nhc_gw.ipv6, alen);
+		} else if (nla_put_in6_addr(skb, RTA_GATEWAY,
+					    &nhc->nhc_gw.ipv6) < 0) {
+			goto nla_put_failure;
+		}
+		break;
+	}
+
+	*flags |= (nhc->nhc_flags &
+		   (RTNH_F_ONLINK | RTNH_F_OFFLOAD | RTNH_F_TRAP));
+
+	if (!skip_oif && nhc->nhc_dev &&
+	    nla_put_u32(skb, RTA_OIF, nhc->nhc_dev->ifindex))
+		goto nla_put_failure;
+
+	if (lwtunnel_fill_encap(skb, nhc->nhc_lwtstate,
+				RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(fib_nexthop_info);
+
+#if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6)
+int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc,
+		    int nh_weight, u8 rt_family, u32 nh_tclassid)
+{
+	const struct net_device *dev = nhc->nhc_dev;
+	struct rtnexthop *rtnh;
+	unsigned char flags = 0;
+
+	rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
+	if (!rtnh)
+		goto nla_put_failure;
+
+	rtnh->rtnh_hops = nh_weight - 1;
+	rtnh->rtnh_ifindex = dev ? dev->ifindex : 0;
+
+	if (fib_nexthop_info(skb, nhc, rt_family, &flags, true) < 0)
+		goto nla_put_failure;
+
+	rtnh->rtnh_flags = flags;
+
+	if (nh_tclassid && nla_put_u32(skb, RTA_FLOW, nh_tclassid))
+		goto nla_put_failure;
+
+	/* length of rtnetlink header + attributes */
+	rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh;
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(fib_add_nexthop);
+#endif
+
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi)
+{
+	struct nlattr *mp;
+
+	mp = nla_nest_start_noflag(skb, RTA_MULTIPATH);
+	if (!mp)
+		goto nla_put_failure;
+
+	if (unlikely(fi->nh)) {
+		if (nexthop_mpath_fill_node(skb, fi->nh, AF_INET) < 0)
+			goto nla_put_failure;
+		goto mp_end;
+	}
+
+	for_nexthops(fi) {
+		u32 nh_tclassid = 0;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+		nh_tclassid = nh->nh_tclassid;
+#endif
+		if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight,
+				    AF_INET, nh_tclassid) < 0)
+			goto nla_put_failure;
+	} endfor_nexthops(fi);
+
+mp_end:
+	nla_nest_end(skb, mp);
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+#else
+static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi)
+{
+	return 0;
+}
+#endif
+
 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)
+		  const struct fib_rt_info *fri, unsigned int flags)
 {
+	unsigned int nhs = fib_info_num_path(fri->fi);
+	struct fib_info *fi = fri->fi;
+	u32 tb_id = fri->tb_id;
 	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
 
@@ -1288,22 +1735,22 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 
 	rtm = nlmsg_data(nlh);
 	rtm->rtm_family = AF_INET;
-	rtm->rtm_dst_len = dst_len;
+	rtm->rtm_dst_len = fri->dst_len;
 	rtm->rtm_src_len = 0;
-	rtm->rtm_tos = tos;
+	rtm->rtm_tos = inet_dscp_to_dsfield(fri->dscp);
 	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_type = fri->type;
 	rtm->rtm_flags = fi->fib_flags;
 	rtm->rtm_scope = fi->fib_scope;
 	rtm->rtm_protocol = fi->fib_protocol;
 
 	if (rtm->rtm_dst_len &&
-	    nla_put_in_addr(skb, RTA_DST, dst))
+	    nla_put_in_addr(skb, RTA_DST, fri->dst))
 		goto nla_put_failure;
 	if (fi->fib_priority &&
 	    nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
@@ -1314,81 +1761,47 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	if (fi->fib_prefsrc &&
 	    nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc))
 		goto nla_put_failure;
-	if (fi->fib_nhs == 1) {
-		if (fi->fib_nh->nh_gw &&
-		    nla_put_in_addr(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;
-		if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) {
-			struct in_device *in_dev;
-
-			rcu_read_lock();
-			in_dev = __in_dev_get_rcu(fi->fib_nh->nh_dev);
-			if (in_dev &&
-			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
-				rtm->rtm_flags |= RTNH_F_DEAD;
-			rcu_read_unlock();
-		}
-		if (fi->fib_nh->nh_flags & RTNH_F_OFFLOAD)
-			rtm->rtm_flags |= RTNH_F_OFFLOAD;
-#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
-		if (fi->fib_nh->nh_lwtstate &&
-		    lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0)
-			goto nla_put_failure;
-	}
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (fi->fib_nhs > 1) {
-		struct rtnexthop *rtnh;
-		struct nlattr *mp;
 
-		mp = nla_nest_start(skb, RTA_MULTIPATH);
-		if (!mp)
+	if (fi->nh) {
+		if (nla_put_u32(skb, RTA_NH_ID, fi->nh->id))
 			goto nla_put_failure;
+		if (nexthop_is_blackhole(fi->nh))
+			rtm->rtm_type = RTN_BLACKHOLE;
+		if (!READ_ONCE(fi->fib_net->ipv4.sysctl_nexthop_compat_mode))
+			goto offload;
+	}
 
-		for_nexthops(fi) {
-			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
-			if (!rtnh)
-				goto nla_put_failure;
-
-			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
-			if (nh->nh_flags & RTNH_F_LINKDOWN) {
-				struct in_device *in_dev;
+	if (nhs == 1) {
+		const struct fib_nh_common *nhc = fib_info_nhc(fi, 0);
+		unsigned char flags = 0;
 
-				rcu_read_lock();
-				in_dev = __in_dev_get_rcu(nh->nh_dev);
-				if (in_dev &&
-				    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
-					rtnh->rtnh_flags |= RTNH_F_DEAD;
-				rcu_read_unlock();
-			}
-			rtnh->rtnh_hops = nh->nh_weight - 1;
-			rtnh->rtnh_ifindex = nh->nh_oif;
+		if (fib_nexthop_info(skb, nhc, AF_INET, &flags, false) < 0)
+			goto nla_put_failure;
 
-			if (nh->nh_gw &&
-			    nla_put_in_addr(skb, RTA_GATEWAY, nh->nh_gw))
-				goto nla_put_failure;
+		rtm->rtm_flags = flags;
 #ifdef CONFIG_IP_ROUTE_CLASSID
+		if (nhc->nhc_family == AF_INET) {
+			struct fib_nh *nh;
+
+			nh = container_of(nhc, struct fib_nh, nh_common);
 			if (nh->nh_tclassid &&
 			    nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
 				goto nla_put_failure;
+		}
 #endif
-			if (nh->nh_lwtstate &&
-			    lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0)
-				goto nla_put_failure;
+	} else {
+		if (fib_add_multipath(skb, fi) < 0)
+			goto nla_put_failure;
+	}
 
-			/* length of rtnetlink header + attributes */
-			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
-		} endfor_nexthops(fi);
+offload:
+	if (fri->offload)
+		rtm->rtm_flags |= RTM_F_OFFLOAD;
+	if (fri->trap)
+		rtm->rtm_flags |= RTM_F_TRAP;
+	if (fri->offload_failed)
+		rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED;
 
-		nla_nest_end(skb, mp);
-	}
-#endif
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -1405,51 +1818,51 @@ nla_put_failure:
  */
 int fib_sync_down_addr(struct net_device *dev, __be32 local)
 {
-	int ret = 0;
-	unsigned int hash = fib_laddr_hashfn(local);
-	struct hlist_head *head = &fib_info_laddrhash[hash];
+	int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
 	struct net *net = dev_net(dev);
-	int tb_id = l3mdev_fib_table(dev);
+	struct hlist_head *head;
 	struct fib_info *fi;
+	int ret = 0;
 
-	if (!fib_info_laddrhash || local == 0)
+	if (!local)
 		return 0;
 
+	head = fib_info_laddrhash_bucket(net, local);
 	hlist_for_each_entry(fi, head, fib_lhash) {
 		if (!net_eq(fi->fib_net, net) ||
 		    fi->fib_tb_id != tb_id)
 			continue;
 		if (fi->fib_prefsrc == local) {
 			fi->fib_flags |= RTNH_F_DEAD;
+			fi->pfsrc_removed = true;
 			ret++;
 		}
 	}
 	return ret;
 }
 
-static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
+static int call_fib_nh_notifiers(struct fib_nh *nh,
 				 enum fib_event_type event_type)
 {
-	struct in_device *in_dev = __in_dev_get_rtnl(fib_nh->nh_dev);
+	bool ignore_link_down = ip_ignore_linkdown(nh->fib_nh_dev);
 	struct fib_nh_notifier_info info = {
-		.fib_nh = fib_nh,
+		.fib_nh = nh,
 	};
 
 	switch (event_type) {
 	case FIB_EVENT_NH_ADD:
-		if (fib_nh->nh_flags & RTNH_F_DEAD)
+		if (nh->fib_nh_flags & RTNH_F_DEAD)
 			break;
-		if (IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-		    fib_nh->nh_flags & RTNH_F_LINKDOWN)
+		if (ignore_link_down && nh->fib_nh_flags & RTNH_F_LINKDOWN)
 			break;
-		return call_fib4_notifiers(dev_net(fib_nh->nh_dev), event_type,
+		return call_fib4_notifiers(dev_net(nh->fib_nh_dev), event_type,
 					   &info.info);
 	case FIB_EVENT_NH_DEL:
-		if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-		     fib_nh->nh_flags & RTNH_F_LINKDOWN) ||
-		    (fib_nh->nh_flags & RTNH_F_DEAD))
-			return call_fib4_notifiers(dev_net(fib_nh->nh_dev),
+		if ((ignore_link_down && nh->fib_nh_flags & RTNH_F_LINKDOWN) ||
+		    (nh->fib_nh_flags & RTNH_F_DEAD))
+			return call_fib4_notifiers(dev_net(nh->fib_nh_dev),
 						   event_type, &info.info);
+		break;
 	default:
 		break;
 	}
@@ -1467,12 +1880,12 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
  * - if the new MTU is greater than the PMTU, don't make any change
  * - otherwise, unlock and set PMTU
  */
-static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig)
+void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig)
 {
 	struct fnhe_hash_bucket *bucket;
 	int i;
 
-	bucket = rcu_dereference_protected(nh->nh_exceptions, 1);
+	bucket = rcu_dereference_protected(nhc->nhc_exceptions, 1);
 	if (!bucket)
 		return;
 
@@ -1497,13 +1910,12 @@ static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig)
 
 void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
 {
-	unsigned int hash = fib_devindex_hashfn(dev->ifindex);
-	struct hlist_head *head = &fib_info_devhash[hash];
+	struct hlist_head *head = fib_nh_head(dev);
 	struct fib_nh *nh;
 
 	hlist_for_each_entry(nh, head, nh_hash) {
-		if (nh->nh_dev == dev)
-			nh_update_mtu(nh, dev->mtu, orig_mtu);
+		DEBUG_NET_WARN_ON_ONCE(nh->fib_nh_dev != dev);
+		fib_nhc_update_mtu(&nh->nh_common, dev->mtu, orig_mtu);
 	}
 }
 
@@ -1512,15 +1924,16 @@ void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
  * NETDEV_DOWN        0     LINKDOWN|DEAD   Link down, not for scope host
  * NETDEV_DOWN        1     LINKDOWN|DEAD   Last address removed
  * NETDEV_UNREGISTER  1     LINKDOWN|DEAD   Device removed
+ *
+ * only used when fib_nh is built into fib_info
  */
 int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
 {
-	int ret = 0;
-	int scope = RT_SCOPE_NOWHERE;
+	struct hlist_head *head = fib_nh_head(dev);
 	struct fib_info *prev_fi = NULL;
-	unsigned int hash = fib_devindex_hashfn(dev->ifindex);
-	struct hlist_head *head = &fib_info_devhash[hash];
+	int scope = RT_SCOPE_NOWHERE;
 	struct fib_nh *nh;
+	int ret = 0;
 
 	if (force)
 		scope = -1;
@@ -1530,22 +1943,23 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
 		int dead;
 
 		BUG_ON(!fi->fib_nhs);
-		if (nh->nh_dev != dev || fi == prev_fi)
+		DEBUG_NET_WARN_ON_ONCE(nh->fib_nh_dev != dev);
+		if (fi == prev_fi)
 			continue;
 		prev_fi = fi;
 		dead = 0;
 		change_nexthops(fi) {
-			if (nexthop_nh->nh_flags & RTNH_F_DEAD)
+			if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD)
 				dead++;
-			else if (nexthop_nh->nh_dev == dev &&
-				 nexthop_nh->nh_scope != scope) {
+			else if (nexthop_nh->fib_nh_dev == dev &&
+				 nexthop_nh->fib_nh_scope != scope) {
 				switch (event) {
 				case NETDEV_DOWN:
 				case NETDEV_UNREGISTER:
-					nexthop_nh->nh_flags |= RTNH_F_DEAD;
-					/* fall through */
+					nexthop_nh->fib_nh_flags |= RTNH_F_DEAD;
+					fallthrough;
 				case NETDEV_CHANGE:
-					nexthop_nh->nh_flags |= RTNH_F_LINKDOWN;
+					nexthop_nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 					break;
 				}
 				call_fib_nh_notifiers(nexthop_nh,
@@ -1554,7 +1968,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
 			}
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 			if (event == NETDEV_UNREGISTER &&
-			    nexthop_nh->nh_dev == dev) {
+			    nexthop_nh->fib_nh_dev == dev) {
 				dead = fi->fib_nhs;
 				break;
 			}
@@ -1565,7 +1979,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
 			case NETDEV_DOWN:
 			case NETDEV_UNREGISTER:
 				fi->fib_flags |= RTNH_F_DEAD;
-				/* fall through */
+				fallthrough;
 			case NETDEV_CHANGE:
 				fi->fib_flags |= RTNH_F_LINKDOWN;
 				break;
@@ -1589,33 +2003,35 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 	int order = -1, last_idx = -1;
 	struct fib_alias *fa, *fa1 = NULL;
 	u32 last_prio = res->fi->fib_priority;
-	u8 last_tos = 0;
+	dscp_t last_dscp = 0;
 
 	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
+		struct fib_nh_common *nhc;
 
 		if (fa->fa_slen != slen)
 			continue;
-		if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
+		if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp))
 			continue;
 		if (fa->tb_id != tb->tb_id)
 			continue;
 		if (next_fi->fib_priority > last_prio &&
-		    fa->fa_tos == last_tos) {
-			if (last_tos)
+		    fa->fa_dscp == last_dscp) {
+			if (last_dscp)
 				continue;
 			break;
 		}
 		if (next_fi->fib_flags & RTNH_F_DEAD)
 			continue;
-		last_tos = fa->fa_tos;
+		last_dscp = fa->fa_dscp;
 		last_prio = next_fi->fib_priority;
 
 		if (next_fi->fib_scope != res->scope ||
 		    fa->fa_type != RTN_UNICAST)
 			continue;
-		if (!next_fi->fib_nh[0].nh_gw ||
-		    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
+
+		nhc = fib_info_nhc(next_fi, 0);
+		if (!nhc->nhc_gw_family || nhc->nhc_scope != RT_SCOPE_LINK)
 			continue;
 
 		fib_alias_accessed(fa);
@@ -1657,11 +2073,12 @@ out:
 /*
  * Dead device goes up. We wake up dead nexthops.
  * It takes sense only on multipath routes.
+ *
+ * only used when fib_nh is built into fib_info
  */
-int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
+int fib_sync_up(struct net_device *dev, unsigned char nh_flags)
 {
 	struct fib_info *prev_fi;
-	unsigned int hash;
 	struct hlist_head *head;
 	struct fib_nh *nh;
 	int ret;
@@ -1670,15 +2087,14 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
 		return 0;
 
 	if (nh_flags & RTNH_F_DEAD) {
-		unsigned int flags = dev_get_flags(dev);
+		unsigned int flags = netif_get_flags(dev);
 
 		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
 			nh_flags |= RTNH_F_LINKDOWN;
 	}
 
 	prev_fi = NULL;
-	hash = fib_devindex_hashfn(dev->ifindex);
-	head = &fib_info_devhash[hash];
+	head = fib_nh_head(dev);
 	ret = 0;
 
 	hlist_for_each_entry(nh, head, nh_hash) {
@@ -1686,24 +2102,25 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
 		int alive;
 
 		BUG_ON(!fi->fib_nhs);
-		if (nh->nh_dev != dev || fi == prev_fi)
+		DEBUG_NET_WARN_ON_ONCE(nh->fib_nh_dev != dev);
+		if (fi == prev_fi)
 			continue;
 
 		prev_fi = fi;
 		alive = 0;
 		change_nexthops(fi) {
-			if (!(nexthop_nh->nh_flags & nh_flags)) {
+			if (!(nexthop_nh->fib_nh_flags & nh_flags)) {
 				alive++;
 				continue;
 			}
-			if (!nexthop_nh->nh_dev ||
-			    !(nexthop_nh->nh_dev->flags & IFF_UP))
+			if (!nexthop_nh->fib_nh_dev ||
+			    !(nexthop_nh->fib_nh_dev->flags & IFF_UP))
 				continue;
-			if (nexthop_nh->nh_dev != dev ||
+			if (nexthop_nh->fib_nh_dev != dev ||
 			    !__in_dev_get_rtnl(dev))
 				continue;
 			alive++;
-			nexthop_nh->nh_flags &= ~nh_flags;
+			nexthop_nh->fib_nh_flags &= ~nh_flags;
 			call_fib_nh_notifiers(nexthop_nh, FIB_EVENT_NH_ADD);
 		} endfor_nexthops(fi)
 
@@ -1723,43 +2140,74 @@ static bool fib_good_nh(const struct fib_nh *nh)
 {
 	int state = NUD_REACHABLE;
 
-	if (nh->nh_scope == RT_SCOPE_LINK) {
+	if (nh->fib_nh_scope == RT_SCOPE_LINK) {
 		struct neighbour *n;
 
-		rcu_read_lock_bh();
+		rcu_read_lock();
 
-		n = __ipv4_neigh_lookup_noref(nh->nh_dev,
-					      (__force u32)nh->nh_gw);
+		if (likely(nh->fib_nh_gw_family == AF_INET))
+			n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev,
+						   (__force u32)nh->fib_nh_gw4);
+		else if (nh->fib_nh_gw_family == AF_INET6)
+			n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev,
+							   &nh->fib_nh_gw6);
+		else
+			n = NULL;
 		if (n)
-			state = n->nud_state;
+			state = READ_ONCE(n->nud_state);
 
-		rcu_read_unlock_bh();
+		rcu_read_unlock();
 	}
 
 	return !!(state & NUD_VALID);
 }
 
-void fib_select_multipath(struct fib_result *res, int hash)
+void fib_select_multipath(struct fib_result *res, int hash,
+			  const struct flowi4 *fl4)
 {
 	struct fib_info *fi = res->fi;
 	struct net *net = fi->fib_net;
-	bool first = false;
+	bool found = false;
+	bool use_neigh;
+	__be32 saddr;
 
-	for_nexthops(fi) {
-		if (net->ipv4.sysctl_fib_multipath_use_neigh) {
-			if (!fib_good_nh(nh))
-				continue;
-			if (!first) {
-				res->nh_sel = nhsel;
-				first = true;
-			}
+	if (unlikely(res->fi->nh)) {
+		nexthop_path_fib_result(res, hash);
+		return;
+	}
+
+	use_neigh = READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh);
+	saddr = fl4 ? fl4->saddr : 0;
+
+	change_nexthops(fi) {
+		int nh_upper_bound;
+
+		/* Nexthops without a carrier are assigned an upper bound of
+		 * minus one when "ignore_routes_with_linkdown" is set.
+		 */
+		nh_upper_bound = atomic_read(&nexthop_nh->fib_nh_upper_bound);
+		if (nh_upper_bound == -1 ||
+		    (use_neigh && !fib_good_nh(nexthop_nh)))
+			continue;
+
+		if (!found) {
+			res->nh_sel = nhsel;
+			res->nhc = &nexthop_nh->nh_common;
+			found = !saddr || nexthop_nh->nh_saddr == saddr;
 		}
 
-		if (hash > atomic_read(&nh->nh_upper_bound))
+		if (hash > nh_upper_bound)
 			continue;
 
-		res->nh_sel = nhsel;
-		return;
+		if (!saddr || nexthop_nh->nh_saddr == saddr) {
+			res->nh_sel = nhsel;
+			res->nhc = &nexthop_nh->nh_common;
+			return;
+		}
+
+		if (found)
+			return;
+
 	} endfor_nexthops(fi);
 }
 #endif
@@ -1767,14 +2215,14 @@ void fib_select_multipath(struct fib_result *res, int hash)
 void fib_select_path(struct net *net, struct fib_result *res,
 		     struct flowi4 *fl4, const struct sk_buff *skb)
 {
-	if (fl4->flowi4_oif && !(fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF))
+	if (fl4->flowi4_oif)
 		goto check_saddr;
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (res->fi->fib_nhs > 1) {
+	if (fib_info_num_path(res->fi) > 1) {
 		int h = fib_multipath_hash(net, fl4, skb, NULL);
 
-		fib_select_multipath(res, h);
+		fib_select_multipath(res, h, fl4);
 	}
 	else
 #endif
@@ -1784,6 +2232,34 @@ void fib_select_path(struct net *net, struct fib_result *res,
 		fib_select_default(fl4, res);
 
 check_saddr:
-	if (!fl4->saddr)
-		fl4->saddr = FIB_RES_PREFSRC(net, *res);
+	if (!fl4->saddr) {
+		struct net_device *l3mdev;
+
+		l3mdev = dev_get_by_index_rcu(net, fl4->flowi4_l3mdev);
+
+		if (!l3mdev ||
+		    l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) == l3mdev)
+			fl4->saddr = fib_result_prefsrc(net, res);
+		else
+			fl4->saddr = inet_select_addr(l3mdev, 0, RT_SCOPE_LINK);
+	}
+}
+
+int __net_init fib4_semantics_init(struct net *net)
+{
+	unsigned int hash_bits = 4;
+
+	net->ipv4.fib_info_hash = fib_info_hash_alloc(hash_bits);
+	if (!net->ipv4.fib_info_hash)
+		return -ENOMEM;
+
+	net->ipv4.fib_info_hash_bits = hash_bits;
+	net->ipv4.fib_info_cnt = 0;
+
+	return 0;
+}
+
+void __net_exit fib4_semantics_exit(struct net *net)
+{
+	fib_info_hash_free(net->ipv4.fib_info_hash);
 }