1 files changed, 255 insertions, 299 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0302e0eb07af..6e89151693d0 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -441,14 +441,14 @@ struct fib6_info *fib6_multipath_select(const struct net *net,
 	if (!fl6->mp_hash)
 		fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
 
-	if (fl6->mp_hash <= atomic_read(&match->fib6_nh.nh_upper_bound))
+	if (fl6->mp_hash <= atomic_read(&match->fib6_nh.fib_nh_upper_bound))
 		return match;
 
 	list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
 				 fib6_siblings) {
 		int nh_upper_bound;
 
-		nh_upper_bound = atomic_read(&sibling->fib6_nh.nh_upper_bound);
+		nh_upper_bound = atomic_read(&sibling->fib6_nh.fib_nh_upper_bound);
 		if (fl6->mp_hash > nh_upper_bound)
 			continue;
 		if (rt6_score_route(sibling, oif, strict) < 0)
@@ -473,13 +473,13 @@ static inline struct fib6_info *rt6_device_match(struct net *net,
 	struct fib6_info *sprt;
 
 	if (!oif && ipv6_addr_any(saddr) &&
-	    !(rt->fib6_nh.nh_flags & RTNH_F_DEAD))
+	    !(rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD))
 		return rt;
 
 	for (sprt = rt; sprt; sprt = rcu_dereference(sprt->fib6_next)) {
-		const struct net_device *dev = sprt->fib6_nh.nh_dev;
+		const struct net_device *dev = sprt->fib6_nh.fib_nh_dev;
 
-		if (sprt->fib6_nh.nh_flags & RTNH_F_DEAD)
+		if (sprt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
 			continue;
 
 		if (oif) {
@@ -495,7 +495,7 @@ static inline struct fib6_info *rt6_device_match(struct net *net,
 	if (oif && flags & RT6_LOOKUP_F_IFACE)
 		return net->ipv6.fib6_null_entry;
 
-	return rt->fib6_nh.nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt;
+	return rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt;
 }
 
 #ifdef CONFIG_IPV6_ROUTER_PREF
@@ -533,11 +533,11 @@ static void rt6_probe(struct fib6_info *rt)
 	 * Router Reachability Probe MUST be rate-limited
 	 * to no more than one per minute.
 	 */
-	if (!rt || !(rt->fib6_flags & RTF_GATEWAY))
+	if (!rt || !rt->fib6_nh.fib_nh_has_gw)
 		return;
 
-	nh_gw = &rt->fib6_nh.nh_gw;
-	dev = rt->fib6_nh.nh_dev;
+	nh_gw = &rt->fib6_nh.fib_nh_gw6;
+	dev = rt->fib6_nh.fib_nh_dev;
 	rcu_read_lock_bh();
 	idev = __in6_dev_get(dev);
 	neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
@@ -582,7 +582,7 @@ static inline void rt6_probe(struct fib6_info *rt)
  */
 static inline int rt6_check_dev(struct fib6_info *rt, int oif)
 {
-	const struct net_device *dev = rt->fib6_nh.nh_dev;
+	const struct net_device *dev = rt->fib6_nh.fib_nh_dev;
 
 	if (!oif || dev->ifindex == oif)
 		return 2;
@@ -595,12 +595,12 @@ static inline enum rt6_nud_state rt6_check_neigh(struct fib6_info *rt)
 	struct neighbour *neigh;
 
 	if (rt->fib6_flags & RTF_NONEXTHOP ||
-	    !(rt->fib6_flags & RTF_GATEWAY))
+	    !rt->fib6_nh.fib_nh_has_gw)
 		return RT6_NUD_SUCCEED;
 
 	rcu_read_lock_bh();
-	neigh = __ipv6_neigh_lookup_noref(rt->fib6_nh.nh_dev,
-					  &rt->fib6_nh.nh_gw);
+	neigh = __ipv6_neigh_lookup_noref(rt->fib6_nh.fib_nh_dev,
+					  &rt->fib6_nh.fib_nh_gw6);
 	if (neigh) {
 		read_lock(&neigh->lock);
 		if (neigh->nud_state & NUD_VALID)
@@ -639,21 +639,6 @@ static int rt6_score_route(struct fib6_info *rt, int oif, int strict)
 	return m;
 }
 
-/* called with rc_read_lock held */
-static inline bool fib6_ignore_linkdown(const struct fib6_info *f6i)
-{
-	const struct net_device *dev = fib6_info_nh_dev(f6i);
-	bool rc = false;
-
-	if (dev) {
-		const struct inet6_dev *idev = __in6_dev_get(dev);
-
-		rc = !!idev->cnf.ignore_routes_with_linkdown;
-	}
-
-	return rc;
-}
-
 static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict,
 				   int *mpri, struct fib6_info *match,
 				   bool *do_rr)
@@ -661,11 +646,11 @@ static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict,
 	int m;
 	bool match_do_rr = false;
 
-	if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
+	if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
 		goto out;
 
-	if (fib6_ignore_linkdown(rt) &&
-	    rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
+	if (ip6_ignore_linkdown(rt->fib6_nh.fib_nh_dev) &&
+	    rt->fib6_nh.fib_nh_flags & RTNH_F_LINKDOWN &&
 	    !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
 		goto out;
 
@@ -784,7 +769,7 @@ static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn,
 
 static bool rt6_is_gw_or_nonexthop(const struct fib6_info *rt)
 {
-	return (rt->fib6_flags & (RTF_NONEXTHOP | RTF_GATEWAY));
+	return (rt->fib6_flags & RTF_NONEXTHOP) || rt->fib6_nh.fib_nh_has_gw;
 }
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
@@ -870,7 +855,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 /* called with rcu_lock held */
 static struct net_device *ip6_rt_get_dev_rcu(struct fib6_info *rt)
 {
-	struct net_device *dev = rt->fib6_nh.nh_dev;
+	struct net_device *dev = rt->fib6_nh.fib_nh_dev;
 
 	if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) {
 		/* for copies of local routes, dst->dev needs to be the
@@ -964,8 +949,8 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
 		rt->dst.input = ip6_forward;
 	}
 
-	if (ort->fib6_nh.nh_lwtstate) {
-		rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate);
+	if (ort->fib6_nh.fib_nh_lws) {
+		rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.fib_nh_lws);
 		lwtunnel_set_redirect(&rt->dst);
 	}
 
@@ -989,8 +974,11 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
 
 	rt->rt6i_dst = ort->fib6_dst;
 	rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL;
-	rt->rt6i_gateway = ort->fib6_nh.nh_gw;
 	rt->rt6i_flags = ort->fib6_flags;
+	if (ort->fib6_nh.fib_nh_has_gw) {
+		rt->rt6i_gateway = ort->fib6_nh.fib_nh_gw6;
+		rt->rt6i_flags |= RTF_GATEWAY;
+	}
 	rt6_set_from(rt, ort);
 #ifdef CONFIG_IPV6_SUBTREES
 	rt->rt6i_src = ort->fib6_src;
@@ -1015,14 +1003,13 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
 	}
 }
 
-static bool ip6_hold_safe(struct net *net, struct rt6_info **prt,
-			  bool null_fallback)
+static bool ip6_hold_safe(struct net *net, struct rt6_info **prt)
 {
 	struct rt6_info *rt = *prt;
 
 	if (dst_hold_safe(&rt->dst))
 		return true;
-	if (null_fallback) {
+	if (net) {
 		rt = net->ipv6.ip6_null_entry;
 		dst_hold(&rt->dst);
 	} else {
@@ -1036,7 +1023,7 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt,
 static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
 {
 	unsigned short flags = fib6_info_dst_flags(rt);
-	struct net_device *dev = rt->fib6_nh.nh_dev;
+	struct net_device *dev = rt->fib6_nh.fib_nh_dev;
 	struct rt6_info *nrt;
 
 	if (!fib6_info_hold_safe(rt))
@@ -1095,7 +1082,7 @@ restart:
 	/* Search through exception table */
 	rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
 	if (rt) {
-		if (ip6_hold_safe(net, &rt, true))
+		if (ip6_hold_safe(net, &rt))
 			dst_use_noref(&rt->dst, jiffies);
 	} else if (f6i == net->ipv6.fib6_null_entry) {
 		rt = net->ipv6.ip6_null_entry;
@@ -1242,7 +1229,7 @@ static struct rt6_info *rt6_get_pcpu_route(struct fib6_info *rt)
 	pcpu_rt = *p;
 
 	if (pcpu_rt)
-		ip6_hold_safe(NULL, &pcpu_rt, false);
+		ip6_hold_safe(NULL, &pcpu_rt);
 
 	return pcpu_rt;
 }
@@ -1420,7 +1407,7 @@ static unsigned int fib6_mtu(const struct fib6_info *rt)
 
 	mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
 
-	return mtu - lwtunnel_headroom(rt->fib6_nh.nh_lwtstate, mtu);
+	return mtu - lwtunnel_headroom(rt->fib6_nh.fib_nh_lws, mtu);
 }
 
 static int rt6_insert_exception(struct rt6_info *nrt,
@@ -1867,13 +1854,13 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 	/*Search through exception table */
 	rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
 	if (rt) {
-		if (ip6_hold_safe(net, &rt, true))
+		if (ip6_hold_safe(net, &rt))
 			dst_use_noref(&rt->dst, jiffies);
 
 		rcu_read_unlock();
 		return rt;
 	} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
-			    !(f6i->fib6_flags & RTF_GATEWAY))) {
+			    !f6i->fib6_nh.fib_nh_has_gw)) {
 		/* Create a RTF_CACHE clone which will not be
 		 * owned by the fib6 tree.  It is for the special case where
 		 * the daddr in the skb during the neighbor look-up is different
@@ -2437,22 +2424,22 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
 	for_each_fib6_node_rt_rcu(fn) {
-		if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
+		if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
 			continue;
 		if (fib6_check_expired(rt))
 			continue;
 		if (rt->fib6_flags & RTF_REJECT)
 			break;
-		if (!(rt->fib6_flags & RTF_GATEWAY))
+		if (!rt->fib6_nh.fib_nh_has_gw)
 			continue;
-		if (fl6->flowi6_oif != rt->fib6_nh.nh_dev->ifindex)
+		if (fl6->flowi6_oif != rt->fib6_nh.fib_nh_dev->ifindex)
 			continue;
 		/* rt_cache's gateway might be different from its 'parent'
 		 * in the case of an ip redirect.
 		 * So we keep searching in the exception table if the gateway
 		 * is different.
 		 */
-		if (!ipv6_addr_equal(&rdfl->gateway, &rt->fib6_nh.nh_gw)) {
+		if (!ipv6_addr_equal(&rdfl->gateway, &rt->fib6_nh.fib_nh_gw6)) {
 			rt_cache = rt6_find_cached_rt(rt,
 						      &fl6->daddr,
 						      &fl6->saddr);
@@ -2482,7 +2469,7 @@ restart:
 
 out:
 	if (ret)
-		ip6_hold_safe(net, &ret, true);
+		ip6_hold_safe(net, &ret);
 	else
 		ret = ip6_create_rt_rcu(rt);
 
@@ -2899,17 +2886,143 @@ out:
 	return err;
 }
 
+static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type)
+{
+	if ((flags & RTF_REJECT) ||
+	    (dev && (dev->flags & IFF_LOOPBACK) &&
+	     !(addr_type & IPV6_ADDR_LOOPBACK) &&
+	     !(flags & RTF_LOCAL)))
+		return true;
+
+	return false;
+}
+
+int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
+		 struct fib6_config *cfg, gfp_t gfp_flags,
+		 struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = NULL;
+	struct inet6_dev *idev = NULL;
+	int addr_type;
+	int err;
+
+	fib6_nh->fib_nh_family = AF_INET6;
+
+	err = -ENODEV;
+	if (cfg->fc_ifindex) {
+		dev = dev_get_by_index(net, cfg->fc_ifindex);
+		if (!dev)
+			goto out;
+		idev = in6_dev_get(dev);
+		if (!idev)
+			goto out;
+	}
+
+	if (cfg->fc_flags & RTNH_F_ONLINK) {
+		if (!dev) {
+			NL_SET_ERR_MSG(extack,
+				       "Nexthop device required for onlink");
+			goto out;
+		}
+
+		if (!(dev->flags & IFF_UP)) {
+			NL_SET_ERR_MSG(extack, "Nexthop device is not up");
+			err = -ENETDOWN;
+			goto out;
+		}
+
+		fib6_nh->fib_nh_flags |= RTNH_F_ONLINK;
+	}
+
+	fib6_nh->fib_nh_weight = 1;
+
+	/* We cannot add true routes via loopback here,
+	 * they would result in kernel looping; promote them to reject routes
+	 */
+	addr_type = ipv6_addr_type(&cfg->fc_dst);
+	if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) {
+		/* hold loopback dev/idev if we haven't done so. */
+		if (dev != net->loopback_dev) {
+			if (dev) {
+				dev_put(dev);
+				in6_dev_put(idev);
+			}
+			dev = net->loopback_dev;
+			dev_hold(dev);
+			idev = in6_dev_get(dev);
+			if (!idev) {
+				err = -ENODEV;
+				goto out;
+			}
+		}
+		goto set_dev;
+	}
+
+	if (cfg->fc_flags & RTF_GATEWAY) {
+		err = ip6_validate_gw(net, cfg, &dev, &idev, extack);
+		if (err)
+			goto out;
+
+		fib6_nh->fib_nh_gw6 = cfg->fc_gateway;
+		fib6_nh->fib_nh_has_gw = 1;
+	}
+
+	err = -ENODEV;
+	if (!dev)
+		goto out;
+
+	if (idev->cnf.disable_ipv6) {
+		NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device");
+		err = -EACCES;
+		goto out;
+	}
+
+	if (!(dev->flags & IFF_UP) && !cfg->fc_ignore_dev_down) {
+		NL_SET_ERR_MSG(extack, "Nexthop device is not up");
+		err = -ENETDOWN;
+		goto out;
+	}
+
+	if (!(cfg->fc_flags & (RTF_LOCAL | RTF_ANYCAST)) &&
+	    !netif_carrier_ok(dev))
+		fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN;
+
+	err = fib_nh_common_init(&fib6_nh->nh_common, cfg->fc_encap,
+				 cfg->fc_encap_type, cfg, gfp_flags, extack);
+	if (err)
+		goto out;
+set_dev:
+	fib6_nh->fib_nh_dev = dev;
+	fib6_nh->fib_nh_oif = dev->ifindex;
+	err = 0;
+out:
+	if (idev)
+		in6_dev_put(idev);
+
+	if (err) {
+		lwtstate_put(fib6_nh->fib_nh_lws);
+		fib6_nh->fib_nh_lws = NULL;
+		if (dev)
+			dev_put(dev);
+	}
+
+	return err;
+}
+
+void fib6_nh_release(struct fib6_nh *fib6_nh)
+{
+	fib_nh_common_release(&fib6_nh->nh_common);
+}
+
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 					      gfp_t gfp_flags,
 					      struct netlink_ext_ack *extack)
 {
 	struct net *net = cfg->fc_nlinfo.nl_net;
 	struct fib6_info *rt = NULL;
-	struct net_device *dev = NULL;
-	struct inet6_dev *idev = NULL;
 	struct fib6_table *table;
-	int addr_type;
 	int err = -EINVAL;
+	int addr_type;
 
 	/* RTF_PCPU is an internal flag; can not be set by userspace */
 	if (cfg->fc_flags & RTF_PCPU) {
@@ -2943,33 +3056,6 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		goto out;
 	}
 #endif
-	if (cfg->fc_ifindex) {
-		err = -ENODEV;
-		dev = dev_get_by_index(net, cfg->fc_ifindex);
-		if (!dev)
-			goto out;
-		idev = in6_dev_get(dev);
-		if (!idev)
-			goto out;
-	}
-
-	if (cfg->fc_metric == 0)
-		cfg->fc_metric = IP6_RT_PRIO_USER;
-
-	if (cfg->fc_flags & RTNH_F_ONLINK) {
-		if (!dev) {
-			NL_SET_ERR_MSG(extack,
-				       "Nexthop device required for onlink");
-			err = -ENODEV;
-			goto out;
-		}
-
-		if (!(dev->flags & IFF_UP)) {
-			NL_SET_ERR_MSG(extack, "Nexthop device is not up");
-			err = -ENETDOWN;
-			goto out;
-		}
-	}
 
 	err = -ENOBUFS;
 	if (cfg->fc_nlinfo.nlh &&
@@ -3013,18 +3099,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		cfg->fc_protocol = RTPROT_BOOT;
 	rt->fib6_protocol = cfg->fc_protocol;
 
-	addr_type = ipv6_addr_type(&cfg->fc_dst);
-
-	if (cfg->fc_encap) {
-		struct lwtunnel_state *lwtstate;
-
-		err = lwtunnel_build_state(cfg->fc_encap_type,
-					   cfg->fc_encap, AF_INET6, cfg,
-					   &lwtstate, extack);
-		if (err)
-			goto out;
-		rt->fib6_nh.nh_lwtstate = lwtstate_get(lwtstate);
-	}
+	rt->fib6_table = table;
+	rt->fib6_metric = cfg->fc_metric;
+	rt->fib6_type = cfg->fc_type;
+	rt->fib6_flags = cfg->fc_flags & ~RTF_GATEWAY;
 
 	ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
 	rt->fib6_dst.plen = cfg->fc_dst_len;
@@ -3035,62 +3113,20 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len);
 	rt->fib6_src.plen = cfg->fc_src_len;
 #endif
-
-	rt->fib6_metric = cfg->fc_metric;
-	rt->fib6_nh.nh_weight = 1;
-
-	rt->fib6_type = cfg->fc_type;
+	err = fib6_nh_init(net, &rt->fib6_nh, cfg, gfp_flags, extack);
+	if (err)
+		goto out;
 
 	/* We cannot add true routes via loopback here,
-	   they would result in kernel looping; promote them to reject routes
+	 * they would result in kernel looping; promote them to reject routes
 	 */
-	if ((cfg->fc_flags & RTF_REJECT) ||
-	    (dev && (dev->flags & IFF_LOOPBACK) &&
-	     !(addr_type & IPV6_ADDR_LOOPBACK) &&
-	     !(cfg->fc_flags & RTF_LOCAL))) {
-		/* hold loopback dev/idev if we haven't done so. */
-		if (dev != net->loopback_dev) {
-			if (dev) {
-				dev_put(dev);
-				in6_dev_put(idev);
-			}
-			dev = net->loopback_dev;
-			dev_hold(dev);
-			idev = in6_dev_get(dev);
-			if (!idev) {
-				err = -ENODEV;
-				goto out;
-			}
-		}
-		rt->fib6_flags = RTF_REJECT|RTF_NONEXTHOP;
-		goto install_route;
-	}
-
-	if (cfg->fc_flags & RTF_GATEWAY) {
-		err = ip6_validate_gw(net, cfg, &dev, &idev, extack);
-		if (err)
-			goto out;
-
-		rt->fib6_nh.nh_gw = cfg->fc_gateway;
-	}
-
-	err = -ENODEV;
-	if (!dev)
-		goto out;
-
-	if (idev->cnf.disable_ipv6) {
-		NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device");
-		err = -EACCES;
-		goto out;
-	}
-
-	if (!(dev->flags & IFF_UP)) {
-		NL_SET_ERR_MSG(extack, "Nexthop device is not up");
-		err = -ENETDOWN;
-		goto out;
-	}
+	addr_type = ipv6_addr_type(&cfg->fc_dst);
+	if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh.fib_nh_dev, addr_type))
+		rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP;
 
 	if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
+		struct net_device *dev = fib6_info_nh_dev(rt);
+
 		if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
 			NL_SET_ERR_MSG(extack, "Invalid source address");
 			err = -EINVAL;
@@ -3101,26 +3137,8 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	} else
 		rt->fib6_prefsrc.plen = 0;
 
-	rt->fib6_flags = cfg->fc_flags;
-
-install_route:
-	if (!(rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) &&
-	    !netif_carrier_ok(dev))
-		rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN;
-	rt->fib6_nh.nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK);
-	rt->fib6_nh.nh_dev = dev;
-	rt->fib6_table = table;
-
-	if (idev)
-		in6_dev_put(idev);
-
 	return rt;
 out:
-	if (dev)
-		dev_put(dev);
-	if (idev)
-		in6_dev_put(idev);
-
 	fib6_info_release(rt);
 	return ERR_PTR(err);
 }
@@ -3261,6 +3279,8 @@ static int ip6_route_del(struct fib6_config *cfg,
 
 	if (fn) {
 		for_each_fib6_node_rt_rcu(fn) {
+			struct fib6_nh *nh;
+
 			if (cfg->fc_flags & RTF_CACHE) {
 				int rc;
 
@@ -3275,12 +3295,14 @@ static int ip6_route_del(struct fib6_config *cfg,
 				}
 				continue;
 			}
+
+			nh = &rt->fib6_nh;
 			if (cfg->fc_ifindex &&
-			    (!rt->fib6_nh.nh_dev ||
-			     rt->fib6_nh.nh_dev->ifindex != cfg->fc_ifindex))
+			    (!nh->fib_nh_dev ||
+			     nh->fib_nh_dev->ifindex != cfg->fc_ifindex))
 				continue;
 			if (cfg->fc_flags & RTF_GATEWAY &&
-			    !ipv6_addr_equal(&cfg->fc_gateway, &rt->fib6_nh.nh_gw))
+			    !ipv6_addr_equal(&cfg->fc_gateway, &nh->fib_nh_gw6))
 				continue;
 			if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric)
 				continue;
@@ -3451,11 +3473,12 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 		goto out;
 
 	for_each_fib6_node_rt_rcu(fn) {
-		if (rt->fib6_nh.nh_dev->ifindex != ifindex)
+		if (rt->fib6_nh.fib_nh_dev->ifindex != ifindex)
 			continue;
-		if ((rt->fib6_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
+		if (!(rt->fib6_flags & RTF_ROUTEINFO) ||
+		    !rt->fib6_nh.fib_nh_has_gw)
 			continue;
-		if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr))
+		if (!ipv6_addr_equal(&rt->fib6_nh.fib_nh_gw6, gwaddr))
 			continue;
 		if (!fib6_info_hold_safe(rt))
 			continue;
@@ -3513,9 +3536,11 @@ struct fib6_info *rt6_get_dflt_router(struct net *net,
 
 	rcu_read_lock();
 	for_each_fib6_node_rt_rcu(&table->tb6_root) {
-		if (dev == rt->fib6_nh.nh_dev &&
+		struct fib6_nh *nh = &rt->fib6_nh;
+
+		if (dev == nh->fib_nh_dev &&
 		    ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
-		    ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr))
+		    ipv6_addr_equal(&nh->fib_nh_gw6, addr))
 			break;
 	}
 	if (rt && !fib6_info_hold_safe(rt))
@@ -3606,7 +3631,7 @@ static void rtmsg_to_fib6_config(struct net *net,
 		.fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ?
 			 : RT6_TABLE_MAIN,
 		.fc_ifindex = rtmsg->rtmsg_ifindex,
-		.fc_metric = rtmsg->rtmsg_metric,
+		.fc_metric = rtmsg->rtmsg_metric ? : IP6_RT_PRIO_USER,
 		.fc_expires = rtmsg->rtmsg_info,
 		.fc_dst_len = rtmsg->rtmsg_dst_len,
 		.fc_src_len = rtmsg->rtmsg_src_len,
@@ -3717,36 +3742,26 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 				     const struct in6_addr *addr,
 				     bool anycast, gfp_t gfp_flags)
 {
-	u32 tb_id;
-	struct net_device *dev = idev->dev;
-	struct fib6_info *f6i;
-
-	f6i = fib6_info_alloc(gfp_flags);
-	if (!f6i)
-		return ERR_PTR(-ENOMEM);
+	struct fib6_config cfg = {
+		.fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL,
+		.fc_ifindex = idev->dev->ifindex,
+		.fc_flags = RTF_UP | RTF_ADDRCONF | RTF_NONEXTHOP,
+		.fc_dst = *addr,
+		.fc_dst_len = 128,
+		.fc_protocol = RTPROT_KERNEL,
+		.fc_nlinfo.nl_net = net,
+		.fc_ignore_dev_down = true,
+	};
 
-	f6i->fib6_metrics = ip_fib_metrics_init(net, NULL, 0, NULL);
-	f6i->dst_nocount = true;
-	f6i->dst_host = true;
-	f6i->fib6_protocol = RTPROT_KERNEL;
-	f6i->fib6_flags = RTF_UP | RTF_NONEXTHOP;
 	if (anycast) {
-		f6i->fib6_type = RTN_ANYCAST;
-		f6i->fib6_flags |= RTF_ANYCAST;
+		cfg.fc_type = RTN_ANYCAST;
+		cfg.fc_flags |= RTF_ANYCAST;
 	} else {
-		f6i->fib6_type = RTN_LOCAL;
-		f6i->fib6_flags |= RTF_LOCAL;
+		cfg.fc_type = RTN_LOCAL;
+		cfg.fc_flags |= RTF_LOCAL;
 	}
 
-	f6i->fib6_nh.nh_gw = *addr;
-	dev_hold(dev);
-	f6i->fib6_nh.nh_dev = dev;
-	f6i->fib6_dst.addr = *addr;
-	f6i->fib6_dst.plen = 128;
-	tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
-	f6i->fib6_table = fib6_get_table(net, tb_id);
-
-	return f6i;
+	return ip6_route_info_create(&cfg, gfp_flags, NULL);
 }
 
 /* remove deleted ip from prefsrc entries */
@@ -3762,7 +3777,7 @@ static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg)
 	struct net *net = ((struct arg_dev_net_ip *)arg)->net;
 	struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
 
-	if (((void *)rt->fib6_nh.nh_dev == dev || !dev) &&
+	if (((void *)rt->fib6_nh.fib_nh_dev == dev || !dev) &&
 	    rt != net->ipv6.fib6_null_entry &&
 	    ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr)) {
 		spin_lock_bh(&rt6_exception_lock);
@@ -3784,7 +3799,7 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 	fib6_clean_all(net, fib6_remove_prefsrc, &adni);
 }
 
-#define RTF_RA_ROUTER		(RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
+#define RTF_RA_ROUTER		(RTF_ADDRCONF | RTF_DEFAULT)
 
 /* Remove routers and update dst entries when gateway turn into host. */
 static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
@@ -3792,7 +3807,8 @@ static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
 	struct in6_addr *gateway = (struct in6_addr *)arg;
 
 	if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
-	    ipv6_addr_equal(gateway, &rt->fib6_nh.nh_gw)) {
+	    rt->fib6_nh.fib_nh_has_gw &&
+	    ipv6_addr_equal(gateway, &rt->fib6_nh.fib_nh_gw6)) {
 		return -1;
 	}
 
@@ -3840,9 +3856,9 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
 
 static bool rt6_is_dead(const struct fib6_info *rt)
 {
-	if (rt->fib6_nh.nh_flags & RTNH_F_DEAD ||
-	    (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
-	     fib6_ignore_linkdown(rt)))
+	if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD ||
+	    (rt->fib6_nh.fib_nh_flags & RTNH_F_LINKDOWN &&
+	     ip6_ignore_linkdown(rt->fib6_nh.fib_nh_dev)))
 		return true;
 
 	return false;
@@ -3854,11 +3870,11 @@ static int rt6_multipath_total_weight(const struct fib6_info *rt)
 	int total = 0;
 
 	if (!rt6_is_dead(rt))
-		total += rt->fib6_nh.nh_weight;
+		total += rt->fib6_nh.fib_nh_weight;
 
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
 		if (!rt6_is_dead(iter))
-			total += iter->fib6_nh.nh_weight;
+			total += iter->fib6_nh.fib_nh_weight;
 	}
 
 	return total;
@@ -3869,11 +3885,11 @@ static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total)
 	int upper_bound = -1;
 
 	if (!rt6_is_dead(rt)) {
-		*weight += rt->fib6_nh.nh_weight;
+		*weight += rt->fib6_nh.fib_nh_weight;
 		upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31,
 						    total) - 1;
 	}
-	atomic_set(&rt->fib6_nh.nh_upper_bound, upper_bound);
+	atomic_set(&rt->fib6_nh.fib_nh_upper_bound, upper_bound);
 }
 
 static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total)
@@ -3916,8 +3932,9 @@ static int fib6_ifup(struct fib6_info *rt, void *p_arg)
 	const struct arg_netdev_event *arg = p_arg;
 	struct net *net = dev_net(arg->dev);
 
-	if (rt != net->ipv6.fib6_null_entry && rt->fib6_nh.nh_dev == arg->dev) {
-		rt->fib6_nh.nh_flags &= ~arg->nh_flags;
+	if (rt != net->ipv6.fib6_null_entry &&
+	    rt->fib6_nh.fib_nh_dev == arg->dev) {
+		rt->fib6_nh.fib_nh_flags &= ~arg->nh_flags;
 		fib6_update_sernum_upto_root(net, rt);
 		rt6_multipath_rebalance(rt);
 	}
@@ -3945,10 +3962,10 @@ static bool rt6_multipath_uses_dev(const struct fib6_info *rt,
 {
 	struct fib6_info *iter;
 
-	if (rt->fib6_nh.nh_dev == dev)
+	if (rt->fib6_nh.fib_nh_dev == dev)
 		return true;
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
-		if (iter->fib6_nh.nh_dev == dev)
+		if (iter->fib6_nh.fib_nh_dev == dev)
 			return true;
 
 	return false;
@@ -3969,12 +3986,12 @@ static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt,
 	struct fib6_info *iter;
 	unsigned int dead = 0;
 
-	if (rt->fib6_nh.nh_dev == down_dev ||
-	    rt->fib6_nh.nh_flags & RTNH_F_DEAD)
+	if (rt->fib6_nh.fib_nh_dev == down_dev ||
+	    rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
 		dead++;
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
-		if (iter->fib6_nh.nh_dev == down_dev ||
-		    iter->fib6_nh.nh_flags & RTNH_F_DEAD)
+		if (iter->fib6_nh.fib_nh_dev == down_dev ||
+		    iter->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
 			dead++;
 
 	return dead;
@@ -3986,11 +4003,11 @@ static void rt6_multipath_nh_flags_set(struct fib6_info *rt,
 {
 	struct fib6_info *iter;
 
-	if (rt->fib6_nh.nh_dev == dev)
-		rt->fib6_nh.nh_flags |= nh_flags;
+	if (rt->fib6_nh.fib_nh_dev == dev)
+		rt->fib6_nh.fib_nh_flags |= nh_flags;
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
-		if (iter->fib6_nh.nh_dev == dev)
-			iter->fib6_nh.nh_flags |= nh_flags;
+		if (iter->fib6_nh.fib_nh_dev == dev)
+			iter->fib6_nh.fib_nh_flags |= nh_flags;
 }
 
 /* called with write lock held for table with rt */
@@ -4005,12 +4022,12 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
 
 	switch (arg->event) {
 	case NETDEV_UNREGISTER:
-		return rt->fib6_nh.nh_dev == dev ? -1 : 0;
+		return rt->fib6_nh.fib_nh_dev == dev ? -1 : 0;
 	case NETDEV_DOWN:
 		if (rt->should_flush)
 			return -1;
 		if (!rt->fib6_nsiblings)
-			return rt->fib6_nh.nh_dev == dev ? -1 : 0;
+			return rt->fib6_nh.fib_nh_dev == dev ? -1 : 0;
 		if (rt6_multipath_uses_dev(rt, dev)) {
 			unsigned int count;
 
@@ -4026,10 +4043,10 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
 		}
 		return -2;
 	case NETDEV_CHANGE:
-		if (rt->fib6_nh.nh_dev != dev ||
+		if (rt->fib6_nh.fib_nh_dev != dev ||
 		    rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))
 			break;
-		rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN;
+		rt->fib6_nh.fib_nh_flags |= RTNH_F_LINKDOWN;
 		rt6_multipath_rebalance(rt);
 		break;
 	}
@@ -4085,7 +4102,7 @@ static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg)
 	   Since RFC 1981 doesn't include administrative MTU increase
 	   update PMTU increase is a MUST. (i.e. jumbo frame)
 	 */
-	if (rt->fib6_nh.nh_dev == arg->dev &&
+	if (rt->fib6_nh.fib_nh_dev == arg->dev &&
 	    !fib6_metric_locked(rt, RTAX_MTU)) {
 		u32 mtu = rt->fib6_pmtu;
 
@@ -4376,7 +4393,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			goto cleanup;
 		}
 
-		rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1;
+		rt->fib6_nh.fib_nh_weight = rtnh->rtnh_hops + 1;
 
 		err = ip6_route_info_append(info->nl_net, &rt6_nh_list,
 					    rt, &r_cfg);
@@ -4526,6 +4543,9 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		return err;
 
+	if (cfg.fc_metric == 0)
+		cfg.fc_metric = IP6_RT_PRIO_USER;
+
 	if (cfg.fc_mp)
 		return ip6_route_multipath_add(&cfg, extack);
 	else
@@ -4540,7 +4560,7 @@ static size_t rt6_nlmsg_size(struct fib6_info *rt)
 		nexthop_len = nla_total_size(0)	 /* RTA_MULTIPATH */
 			    + NLA_ALIGN(sizeof(struct rtnexthop))
 			    + nla_total_size(16) /* RTA_GATEWAY */
-			    + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate);
+			    + lwtunnel_get_encap_size(rt->fib6_nh.fib_nh_lws);
 
 		nexthop_len *= rt->fib6_nsiblings;
 	}
@@ -4558,77 +4578,10 @@ static size_t rt6_nlmsg_size(struct fib6_info *rt)
 	       + nla_total_size(sizeof(struct rta_cacheinfo))
 	       + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
 	       + nla_total_size(1) /* RTA_PREF */
-	       + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate)
+	       + lwtunnel_get_encap_size(rt->fib6_nh.fib_nh_lws)
 	       + nexthop_len;
 }
 
-static int rt6_nexthop_info(struct sk_buff *skb, struct fib6_info *rt,
-			    unsigned int *flags, bool skip_oif)
-{
-	if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
-		*flags |= RTNH_F_DEAD;
-
-	if (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN) {
-		*flags |= RTNH_F_LINKDOWN;
-
-		rcu_read_lock();
-		if (fib6_ignore_linkdown(rt))
-			*flags |= RTNH_F_DEAD;
-		rcu_read_unlock();
-	}
-
-	if (rt->fib6_flags & RTF_GATEWAY) {
-		if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->fib6_nh.nh_gw) < 0)
-			goto nla_put_failure;
-	}
-
-	*flags |= (rt->fib6_nh.nh_flags & RTNH_F_ONLINK);
-	if (rt->fib6_nh.nh_flags & RTNH_F_OFFLOAD)
-		*flags |= RTNH_F_OFFLOAD;
-
-	/* not needed for multipath encoding b/c it has a rtnexthop struct */
-	if (!skip_oif && rt->fib6_nh.nh_dev &&
-	    nla_put_u32(skb, RTA_OIF, rt->fib6_nh.nh_dev->ifindex))
-		goto nla_put_failure;
-
-	if (rt->fib6_nh.nh_lwtstate &&
-	    lwtunnel_fill_encap(skb, rt->fib6_nh.nh_lwtstate) < 0)
-		goto nla_put_failure;
-
-	return 0;
-
-nla_put_failure:
-	return -EMSGSIZE;
-}
-
-/* add multipath next hop */
-static int rt6_add_nexthop(struct sk_buff *skb, struct fib6_info *rt)
-{
-	const struct net_device *dev = rt->fib6_nh.nh_dev;
-	struct rtnexthop *rtnh;
-	unsigned int flags = 0;
-
-	rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
-	if (!rtnh)
-		goto nla_put_failure;
-
-	rtnh->rtnh_hops = rt->fib6_nh.nh_weight - 1;
-	rtnh->rtnh_ifindex = dev ? dev->ifindex : 0;
-
-	if (rt6_nexthop_info(skb, rt, &flags, true) < 0)
-		goto nla_put_failure;
-
-	rtnh->rtnh_flags = flags;
-
-	/* length of rtnetlink header + attributes */
-	rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh;
-
-	return 0;
-
-nla_put_failure:
-	return -EMSGSIZE;
-}
-
 static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			 struct fib6_info *rt, struct dst_entry *dst,
 			 struct in6_addr *dest, struct in6_addr *src,
@@ -4745,18 +4698,21 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		if (!mp)
 			goto nla_put_failure;
 
-		if (rt6_add_nexthop(skb, rt) < 0)
+		if (fib_add_nexthop(skb, &rt->fib6_nh.nh_common,
+				    rt->fib6_nh.fib_nh_weight) < 0)
 			goto nla_put_failure;
 
 		list_for_each_entry_safe(sibling, next_sibling,
 					 &rt->fib6_siblings, fib6_siblings) {
-			if (rt6_add_nexthop(skb, sibling) < 0)
+			if (fib_add_nexthop(skb, &sibling->fib6_nh.nh_common,
+					    sibling->fib6_nh.fib_nh_weight) < 0)
 				goto nla_put_failure;
 		}
 
 		nla_nest_end(skb, mp);
 	} else {
-		if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags, false) < 0)
+		if (fib_nexthop_info(skb, &rt->fib6_nh.nh_common,
+				     &rtm->rtm_flags, false) < 0)
 			goto nla_put_failure;
 	}
 
@@ -4783,7 +4739,7 @@ nla_put_failure:
 static bool fib6_info_uses_dev(const struct fib6_info *f6i,
 			       const struct net_device *dev)
 {
-	if (f6i->fib6_nh.nh_dev == dev)
+	if (f6i->fib6_nh.fib_nh_dev == dev)
 		return true;
 
 	if (f6i->fib6_nsiblings) {
@@ -4791,7 +4747,7 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i,
 
 		list_for_each_entry_safe(sibling, next_sibling,
 					 &f6i->fib6_siblings, fib6_siblings) {
-			if (sibling->fib6_nh.nh_dev == dev)
+			if (sibling->fib6_nh.fib_nh_dev == dev)
 				return true;
 		}
 	}
@@ -5076,7 +5032,7 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 		return NOTIFY_OK;
 
 	if (event == NETDEV_REGISTER) {
-		net->ipv6.fib6_null_entry->fib6_nh.nh_dev = dev;
+		net->ipv6.fib6_null_entry->fib6_nh.fib_nh_dev = dev;
 		net->ipv6.ip6_null_entry->dst.dev = dev;
 		net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -5411,7 +5367,7 @@ void __init ip6_route_init_special_entries(void)
 	/* Registering of the loopback is done before this portion of code,
 	 * the loopback reference in rt6_info will not be taken, do it
 	 * manually for init_net */
-	init_net.ipv6.fib6_null_entry->fib6_nh.nh_dev = init_net.loopback_dev;
+	init_net.ipv6.fib6_null_entry->fib6_nh.fib_nh_dev = init_net.loopback_dev;
 	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
 	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
   #ifdef CONFIG_IPV6_MULTIPLE_TABLES