1 files changed, 580 insertions, 67 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fada5a13bcb2..c4d285fe0adc 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *	Linux INET6 implementation
  *	FIB front-end.
  *
  *	Authors:
  *	Pedro Roque		<roque@di.fc.ul.pt>
- *
- *	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.
  */
 
 /*	Changes:
@@ -104,7 +100,7 @@ static void		rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,
 			   int strict);
-static size_t rt6_nlmsg_size(struct fib6_info *rt);
+static size_t rt6_nlmsg_size(struct fib6_info *f6i);
 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,
@@ -432,15 +428,21 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 	struct fib6_info *sibling, *next_sibling;
 	struct fib6_info *match = res->f6i;
 
-	if (!match->fib6_nsiblings || have_oif_match)
+	if ((!match->fib6_nsiblings && !match->nh) || have_oif_match)
 		goto out;
 
 	/* We might have already computed the hash for ICMPv6 errors. In such
 	 * case it will always be non-zero. Otherwise now is the time to do it.
 	 */
-	if (!fl6->mp_hash)
+	if (!fl6->mp_hash &&
+	    (!match->nh || nexthop_is_multipath(match->nh)))
 		fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
 
+	if (unlikely(match->nh)) {
+		nexthop_path_fib6_result(res, fl6->mp_hash);
+		return;
+	}
+
 	if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
 		goto out;
 
@@ -488,6 +490,45 @@ static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh,
 	return false;
 }
 
+struct fib6_nh_dm_arg {
+	struct net		*net;
+	const struct in6_addr	*saddr;
+	int			oif;
+	int			flags;
+	struct fib6_nh		*nh;
+};
+
+static int __rt6_nh_dev_match(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_dm_arg *arg = _arg;
+
+	arg->nh = nh;
+	return __rt6_device_match(arg->net, nh, arg->saddr, arg->oif,
+				  arg->flags);
+}
+
+/* returns fib6_nh from nexthop or NULL */
+static struct fib6_nh *rt6_nh_dev_match(struct net *net, struct nexthop *nh,
+					struct fib6_result *res,
+					const struct in6_addr *saddr,
+					int oif, int flags)
+{
+	struct fib6_nh_dm_arg arg = {
+		.net   = net,
+		.saddr = saddr,
+		.oif   = oif,
+		.flags = flags,
+	};
+
+	if (nexthop_is_blackhole(nh))
+		return NULL;
+
+	if (nexthop_for_each_fib6_nh(nh, __rt6_nh_dev_match, &arg))
+		return arg.nh;
+
+	return NULL;
+}
+
 static void rt6_device_match(struct net *net, struct fib6_result *res,
 			     const struct in6_addr *saddr, int oif, int flags)
 {
@@ -496,14 +537,31 @@ static void rt6_device_match(struct net *net, struct fib6_result *res,
 	struct fib6_nh *nh;
 
 	if (!oif && ipv6_addr_any(saddr)) {
-		nh = f6i->fib6_nh;
+		if (unlikely(f6i->nh)) {
+			nh = nexthop_fib6_nh(f6i->nh);
+			if (nexthop_is_blackhole(f6i->nh))
+				goto out_blackhole;
+		} else {
+			nh = f6i->fib6_nh;
+		}
 		if (!(nh->fib_nh_flags & RTNH_F_DEAD))
 			goto out;
 	}
 
 	for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) {
-		nh = spf6i->fib6_nh;
-		if (__rt6_device_match(net, nh, saddr, oif, flags)) {
+		bool matched = false;
+
+		if (unlikely(spf6i->nh)) {
+			nh = rt6_nh_dev_match(net, spf6i->nh, res, saddr,
+					      oif, flags);
+			if (nh)
+				matched = true;
+		} else {
+			nh = spf6i->fib6_nh;
+			if (__rt6_device_match(net, nh, saddr, oif, flags))
+				matched = true;
+		}
+		if (matched) {
 			res->f6i = spf6i;
 			goto out;
 		}
@@ -515,7 +573,14 @@ static void rt6_device_match(struct net *net, struct fib6_result *res,
 		goto out;
 	}
 
-	nh = f6i->fib6_nh;
+	if (unlikely(f6i->nh)) {
+		nh = nexthop_fib6_nh(f6i->nh);
+		if (nexthop_is_blackhole(f6i->nh))
+			goto out_blackhole;
+	} else {
+		nh = f6i->fib6_nh;
+	}
+
 	if (nh->fib_nh_flags & RTNH_F_DEAD) {
 		res->f6i = net->ipv6.fib6_null_entry;
 		nh = res->f6i->fib6_nh;
@@ -524,6 +589,12 @@ out:
 	res->nh = nh;
 	res->fib6_type = res->f6i->fib6_type;
 	res->fib6_flags = res->f6i->fib6_flags;
+	return;
+
+out_blackhole:
+	res->fib6_flags |= RTF_REJECT;
+	res->fib6_type = RTN_BLACKHOLE;
+	res->nh = nh;
 }
 
 #ifdef CONFIG_IPV6_ROUTER_PREF
@@ -694,6 +765,24 @@ out:
 	return rc;
 }
 
+struct fib6_nh_frl_arg {
+	u32		flags;
+	int		oif;
+	int		strict;
+	int		*mpri;
+	bool		*do_rr;
+	struct fib6_nh	*nh;
+};
+
+static int rt6_nh_find_match(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_frl_arg *arg = _arg;
+
+	arg->nh = nh;
+	return find_match(nh, arg->flags, arg->oif, arg->strict,
+			  arg->mpri, arg->do_rr);
+}
+
 static void __find_rr_leaf(struct fib6_info *f6i_start,
 			   struct fib6_info *nomatch, u32 metric,
 			   struct fib6_result *res, struct fib6_info **cont,
@@ -704,6 +793,7 @@ static void __find_rr_leaf(struct fib6_info *f6i_start,
 	for (f6i = f6i_start;
 	     f6i && f6i != nomatch;
 	     f6i = rcu_dereference(f6i->fib6_next)) {
+		bool matched = false;
 		struct fib6_nh *nh;
 
 		if (cont && f6i->fib6_metric != metric) {
@@ -714,8 +804,34 @@ static void __find_rr_leaf(struct fib6_info *f6i_start,
 		if (fib6_check_expired(f6i))
 			continue;
 
-		nh = f6i->fib6_nh;
-		if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) {
+		if (unlikely(f6i->nh)) {
+			struct fib6_nh_frl_arg arg = {
+				.flags  = f6i->fib6_flags,
+				.oif    = oif,
+				.strict = strict,
+				.mpri   = mpri,
+				.do_rr  = do_rr
+			};
+
+			if (nexthop_is_blackhole(f6i->nh)) {
+				res->fib6_flags = RTF_REJECT;
+				res->fib6_type = RTN_BLACKHOLE;
+				res->f6i = f6i;
+				res->nh = nexthop_fib6_nh(f6i->nh);
+				return;
+			}
+			if (nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match,
+						     &arg)) {
+				matched = true;
+				nh = arg.nh;
+			}
+		} else {
+			nh = f6i->fib6_nh;
+			if (find_match(nh, f6i->fib6_flags, oif, strict,
+				       mpri, do_rr))
+				matched = true;
+		}
+		if (matched) {
 			res->f6i = f6i;
 			res->nh = nh;
 			res->fib6_flags = f6i->fib6_flags;
@@ -1117,6 +1233,8 @@ restart:
 		rt = net->ipv6.ip6_null_entry;
 		dst_hold(&rt->dst);
 		goto out;
+	} else if (res.fib6_flags & RTF_REJECT) {
+		goto do_create;
 	}
 
 	fib6_select_path(net, &res, fl6, fl6->flowi6_oif,
@@ -1128,6 +1246,7 @@ restart:
 		if (ip6_hold_safe(net, &rt))
 			dst_use_noref(&rt->dst, jiffies);
 	} else {
+do_create:
 		rt = ip6_create_rt_rcu(&res);
 	}
 
@@ -1268,10 +1387,9 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
 /* It should be called with rcu_read_lock() acquired */
 static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 {
-	struct rt6_info *pcpu_rt, **p;
+	struct rt6_info *pcpu_rt;
 
-	p = this_cpu_ptr(res->nh->rt6i_pcpu);
-	pcpu_rt = *p;
+	pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu);
 
 	if (pcpu_rt)
 		ip6_hold_safe(NULL, &pcpu_rt);
@@ -1624,9 +1742,22 @@ out:
 	spin_unlock_bh(&rt6_exception_lock);
 }
 
+static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg)
+{
+	struct fib6_info *f6i = arg;
+
+	fib6_nh_flush_exceptions(nh, f6i);
+
+	return 0;
+}
+
 void rt6_flush_exceptions(struct fib6_info *f6i)
 {
-	fib6_nh_flush_exceptions(f6i->fib6_nh, f6i);
+	if (f6i->nh)
+		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions,
+					 f6i);
+	else
+		fib6_nh_flush_exceptions(f6i->fib6_nh, f6i);
 }
 
 /* Find cached rt in the hash table inside passed in rt
@@ -1713,6 +1844,23 @@ static int fib6_nh_remove_exception(const struct fib6_nh *nh, int plen,
 	return err;
 }
 
+struct fib6_nh_excptn_arg {
+	struct rt6_info	*rt;
+	int		plen;
+};
+
+static int rt6_nh_remove_exception_rt(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_excptn_arg *arg = _arg;
+	int err;
+
+	err = fib6_nh_remove_exception(nh, arg->plen, arg->rt);
+	if (err == 0)
+		return 1;
+
+	return 0;
+}
+
 static int rt6_remove_exception_rt(struct rt6_info *rt)
 {
 	struct fib6_info *from;
@@ -1721,6 +1869,20 @@ static int rt6_remove_exception_rt(struct rt6_info *rt)
 	if (!from || !(rt->rt6i_flags & RTF_CACHE))
 		return -EINVAL;
 
+	if (from->nh) {
+		struct fib6_nh_excptn_arg arg = {
+			.rt = rt,
+			.plen = from->fib6_src.plen
+		};
+		int rc;
+
+		/* rc = 1 means an entry was found */
+		rc = nexthop_for_each_fib6_nh(from->nh,
+					      rt6_nh_remove_exception_rt,
+					      &arg);
+		return rc ? 0 : -ENOENT;
+	}
+
 	return fib6_nh_remove_exception(from->fib6_nh,
 					from->fib6_src.plen, rt);
 }
@@ -1751,9 +1913,33 @@ static void fib6_nh_update_exception(const struct fib6_nh *nh, int plen,
 		rt6_ex->stamp = jiffies;
 }
 
+struct fib6_nh_match_arg {
+	const struct net_device *dev;
+	const struct in6_addr	*gw;
+	struct fib6_nh		*match;
+};
+
+/* determine if fib6_nh has given device and gateway */
+static int fib6_nh_find_match(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_match_arg *arg = _arg;
+
+	if (arg->dev != nh->fib_nh_dev ||
+	    (arg->gw && !nh->fib_nh_gw_family) ||
+	    (!arg->gw && nh->fib_nh_gw_family) ||
+	    (arg->gw && !ipv6_addr_equal(arg->gw, &nh->fib_nh_gw6)))
+		return 0;
+
+	arg->match = nh;
+
+	/* found a match, break the loop */
+	return 1;
+}
+
 static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
 {
 	struct fib6_info *from;
+	struct fib6_nh *fib6_nh;
 
 	rcu_read_lock();
 
@@ -1761,7 +1947,21 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
 	if (!from || !(rt->rt6i_flags & RTF_CACHE))
 		goto unlock;
 
-	fib6_nh_update_exception(from->fib6_nh, from->fib6_src.plen, rt);
+	if (from->nh) {
+		struct fib6_nh_match_arg arg = {
+			.dev = rt->dst.dev,
+			.gw = &rt->rt6i_gateway,
+		};
+
+		nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg);
+
+		if (!arg.match)
+			return;
+		fib6_nh = arg.match;
+	} else {
+		fib6_nh = from->fib6_nh;
+	}
+	fib6_nh_update_exception(fib6_nh, from->fib6_src.plen, rt);
 unlock:
 	rcu_read_unlock();
 }
@@ -1923,11 +2123,34 @@ static void fib6_nh_age_exceptions(const struct fib6_nh *nh,
 	rcu_read_unlock_bh();
 }
 
+struct fib6_nh_age_excptn_arg {
+	struct fib6_gc_args	*gc_args;
+	unsigned long		now;
+};
+
+static int rt6_nh_age_exceptions(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_age_excptn_arg *arg = _arg;
+
+	fib6_nh_age_exceptions(nh, arg->gc_args, arg->now);
+	return 0;
+}
+
 void rt6_age_exceptions(struct fib6_info *f6i,
 			struct fib6_gc_args *gc_args,
 			unsigned long now)
 {
-	fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now);
+	if (f6i->nh) {
+		struct fib6_nh_age_excptn_arg arg = {
+			.gc_args = gc_args,
+			.now = now
+		};
+
+		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_age_exceptions,
+					 &arg);
+	} else {
+		fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now);
+	}
 }
 
 /* must be called with rcu lock held */
@@ -2456,10 +2679,31 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 			rcu_read_unlock();
 			return;
 		}
-		res.nh = res.f6i->fib6_nh;
 		res.fib6_flags = res.f6i->fib6_flags;
 		res.fib6_type = res.f6i->fib6_type;
 
+		if (res.f6i->nh) {
+			struct fib6_nh_match_arg arg = {
+				.dev = dst->dev,
+				.gw = &rt6->rt6i_gateway,
+			};
+
+			nexthop_for_each_fib6_nh(res.f6i->nh,
+						 fib6_nh_find_match, &arg);
+
+			/* fib6_info uses a nexthop that does not have fib6_nh
+			 * using the dst->dev + gw. Should be impossible.
+			 */
+			if (!arg.match) {
+				rcu_read_unlock();
+				return;
+			}
+
+			res.nh = arg.match;
+		} else {
+			res.nh = res.f6i->fib6_nh;
+		}
+
 		nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr);
 		if (nrt6) {
 			rt6_do_update_pmtu(nrt6, mtu);
@@ -2566,6 +2810,21 @@ static bool ip6_redirect_nh_match(const struct fib6_result *res,
 	return true;
 }
 
+struct fib6_nh_rd_arg {
+	struct fib6_result	*res;
+	struct flowi6		*fl6;
+	const struct in6_addr	*gw;
+	struct rt6_info		**ret;
+};
+
+static int fib6_nh_redirect_match(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_rd_arg *arg = _arg;
+
+	arg->res->nh = nh;
+	return ip6_redirect_nh_match(arg->res, arg->fl6, arg->gw, arg->ret);
+}
+
 /* Handle redirects */
 struct ip6rd_flowi {
 	struct flowi6 fl6;
@@ -2581,6 +2840,12 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
 	struct rt6_info *ret = NULL;
 	struct fib6_result res = {};
+	struct fib6_nh_rd_arg arg = {
+		.res = &res,
+		.fl6 = fl6,
+		.gw  = &rdfl->gateway,
+		.ret = &ret
+	};
 	struct fib6_info *rt;
 	struct fib6_node *fn;
 
@@ -2605,14 +2870,24 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 restart:
 	for_each_fib6_node_rt_rcu(fn) {
 		res.f6i = rt;
-		res.nh = rt->fib6_nh;
-
 		if (fib6_check_expired(rt))
 			continue;
 		if (rt->fib6_flags & RTF_REJECT)
 			break;
-		if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway, &ret))
-			goto out;
+		if (unlikely(rt->nh)) {
+			if (nexthop_is_blackhole(rt->nh))
+				continue;
+			/* on match, res->nh is filled in and potentially ret */
+			if (nexthop_for_each_fib6_nh(rt->nh,
+						     fib6_nh_redirect_match,
+						     &arg))
+				goto out;
+		} else {
+			res.nh = rt->fib6_nh;
+			if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway,
+						  &ret))
+				goto out;
+		}
 	}
 
 	if (!rt)
@@ -3114,7 +3389,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 				goto out;
 			}
 		}
-		goto set_dev;
+		goto pcpu_alloc;
 	}
 
 	if (cfg->fc_flags & RTF_GATEWAY) {
@@ -3146,17 +3421,18 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 	    !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;
+
+pcpu_alloc:
 	fib6_nh->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
 	if (!fib6_nh->rt6i_pcpu) {
 		err = -ENOMEM;
 		goto out;
 	}
 
-	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;
@@ -3217,7 +3493,9 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 {
 	struct net *net = cfg->fc_nlinfo.nl_net;
 	struct fib6_info *rt = NULL;
+	struct nexthop *nh = NULL;
 	struct fib6_table *table;
+	struct fib6_nh *fib6_nh;
 	int err = -EINVAL;
 	int addr_type;
 
@@ -3253,6 +3531,16 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		goto out;
 	}
 #endif
+	if (cfg->fc_nh_id) {
+		nh = nexthop_find_by_id(net, cfg->fc_nh_id);
+		if (!nh) {
+			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+			goto out;
+		}
+		err = fib6_check_nexthop(nh, cfg, extack);
+		if (err)
+			goto out;
+	}
 
 	err = -ENOBUFS;
 	if (cfg->fc_nlinfo.nlh &&
@@ -3270,7 +3558,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		goto out;
 
 	err = -ENOMEM;
-	rt = fib6_info_alloc(gfp_flags, true);
+	rt = fib6_info_alloc(gfp_flags, !nh);
 	if (!rt)
 		goto out;
 
@@ -3310,19 +3598,35 @@ 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
-	err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack);
-	if (err)
-		goto out;
+	if (nh) {
+		if (!nexthop_get(nh)) {
+			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+			goto out;
+		}
+		if (rt->fib6_src.plen) {
+			NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+			goto out;
+		}
+		rt->nh = nh;
+		fib6_nh = nexthop_fib6_nh(rt->nh);
+	} else {
+		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
-	 */
-	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;
+		fib6_nh = rt->fib6_nh;
+
+		/* 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, 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);
+		struct net_device *dev = fib6_nh->fib_nh_dev;
 
 		if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
 			NL_SET_ERR_MSG(extack, "Invalid source address");
@@ -3414,6 +3718,12 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg)
 				info->skip_notify = 1;
 		}
 
+		info->skip_notify_kernel = 1;
+		call_fib6_multipath_entry_notifiers(net,
+						    FIB_EVENT_ENTRY_DEL,
+						    rt,
+						    rt->fib6_nsiblings,
+						    NULL);
 		list_for_each_entry_safe(sibling, next_sibling,
 					 &rt->fib6_siblings,
 					 fib6_siblings) {
@@ -3468,6 +3778,30 @@ static int ip6_del_cached_rt(struct fib6_config *cfg, struct fib6_info *rt,
 	return 0;
 }
 
+struct fib6_nh_del_cached_rt_arg {
+	struct fib6_config *cfg;
+	struct fib6_info *f6i;
+};
+
+static int fib6_nh_del_cached_rt(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_del_cached_rt_arg *arg = _arg;
+	int rc;
+
+	rc = ip6_del_cached_rt(arg->cfg, arg->f6i, nh);
+	return rc != -ESRCH ? rc : 0;
+}
+
+static int ip6_del_cached_rt_nh(struct fib6_config *cfg, struct fib6_info *f6i)
+{
+	struct fib6_nh_del_cached_rt_arg arg = {
+		.cfg = cfg,
+		.f6i = f6i
+	};
+
+	return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_del_cached_rt, &arg);
+}
+
 static int ip6_route_del(struct fib6_config *cfg,
 			 struct netlink_ext_ack *extack)
 {
@@ -3493,11 +3827,20 @@ static int ip6_route_del(struct fib6_config *cfg,
 		for_each_fib6_node_rt_rcu(fn) {
 			struct fib6_nh *nh;
 
-			nh = rt->fib6_nh;
-			if (cfg->fc_flags & RTF_CACHE) {
-				int rc;
+			if (rt->nh && rt->nh->id != cfg->fc_nh_id)
+				continue;
 
-				rc = ip6_del_cached_rt(cfg, rt, nh);
+			if (cfg->fc_flags & RTF_CACHE) {
+				int rc = 0;
+
+				if (rt->nh) {
+					rc = ip6_del_cached_rt_nh(cfg, rt);
+				} else if (cfg->fc_nh_id) {
+					continue;
+				} else {
+					nh = rt->fib6_nh;
+					rc = ip6_del_cached_rt(cfg, rt, nh);
+				}
 				if (rc != -ESRCH) {
 					rcu_read_unlock();
 					return rc;
@@ -3505,6 +3848,23 @@ static int ip6_route_del(struct fib6_config *cfg,
 				continue;
 			}
 
+			if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric)
+				continue;
+			if (cfg->fc_protocol &&
+			    cfg->fc_protocol != rt->fib6_protocol)
+				continue;
+
+			if (rt->nh) {
+				if (!fib6_info_hold_safe(rt))
+					continue;
+				rcu_read_unlock();
+
+				return __ip6_del_rt(rt, &cfg->fc_nlinfo);
+			}
+			if (cfg->fc_nh_id)
+				continue;
+
+			nh = rt->fib6_nh;
 			if (cfg->fc_ifindex &&
 			    (!nh->fib_nh_dev ||
 			     nh->fib_nh_dev->ifindex != cfg->fc_ifindex))
@@ -3512,10 +3872,6 @@ static int ip6_route_del(struct fib6_config *cfg,
 			if (cfg->fc_flags & RTF_GATEWAY &&
 			    !ipv6_addr_equal(&cfg->fc_gateway, &nh->fib_nh_gw6))
 				continue;
-			if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric)
-				continue;
-			if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol)
-				continue;
 			if (!fib6_info_hold_safe(rt))
 				continue;
 			rcu_read_unlock();
@@ -3626,7 +3982,25 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	if (!res.f6i)
 		goto out;
 
-	res.nh = res.f6i->fib6_nh;
+	if (res.f6i->nh) {
+		struct fib6_nh_match_arg arg = {
+			.dev = dst->dev,
+			.gw = &rt->rt6i_gateway,
+		};
+
+		nexthop_for_each_fib6_nh(res.f6i->nh,
+					 fib6_nh_find_match, &arg);
+
+		/* fib6_info uses a nexthop that does not have fib6_nh
+		 * using the dst->dev. Should be impossible
+		 */
+		if (!arg.match)
+			goto out;
+		res.nh = arg.match;
+	} else {
+		res.nh = res.f6i->fib6_nh;
+	}
+
 	res.fib6_flags = res.f6i->fib6_flags;
 	res.fib6_type = res.f6i->fib6_type;
 	nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL);
@@ -3678,6 +4052,9 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 		goto out;
 
 	for_each_fib6_node_rt_rcu(fn) {
+		/* these routes do not use nexthops */
+		if (rt->nh)
+			continue;
 		if (rt->fib6_nh->fib_nh_dev->ifindex != ifindex)
 			continue;
 		if (!(rt->fib6_flags & RTF_ROUTEINFO) ||
@@ -3741,8 +4118,13 @@ struct fib6_info *rt6_get_dflt_router(struct net *net,
 
 	rcu_read_lock();
 	for_each_fib6_node_rt_rcu(&table->tb6_root) {
-		struct fib6_nh *nh = rt->fib6_nh;
+		struct fib6_nh *nh;
+
+		/* RA routes do not use nexthops */
+		if (rt->nh)
+			continue;
 
+		nh = rt->fib6_nh;
 		if (dev == nh->fib_nh_dev &&
 		    ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
 		    ipv6_addr_equal(&nh->fib_nh_gw6, addr))
@@ -3993,7 +4375,8 @@ 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->fib_nh_dev == dev || !dev) &&
+	if (!rt->nh &&
+	    ((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);
@@ -4021,8 +4404,13 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
 {
 	struct in6_addr *gateway = (struct in6_addr *)arg;
-	struct fib6_nh *nh = rt->fib6_nh;
+	struct fib6_nh *nh;
 
+	/* RA routes do not use nexthops */
+	if (rt->nh)
+		return 0;
+
+	nh = rt->fib6_nh;
 	if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
 	    nh->fib_nh_gw_family && ipv6_addr_equal(gateway, &nh->fib_nh_gw6))
 		return -1;
@@ -4069,6 +4457,7 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
 	return NULL;
 }
 
+/* only called for fib entries with builtin fib6_nh */
 static bool rt6_is_dead(const struct fib6_info *rt)
 {
 	if (rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD ||
@@ -4147,7 +4536,7 @@ 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 &&
+	if (rt != net->ipv6.fib6_null_entry && !rt->nh &&
 	    rt->fib6_nh->fib_nh_dev == arg->dev) {
 		rt->fib6_nh->fib_nh_flags &= ~arg->nh_flags;
 		fib6_update_sernum_upto_root(net, rt);
@@ -4172,6 +4561,7 @@ void rt6_sync_up(struct net_device *dev, unsigned char nh_flags)
 	fib6_clean_all(dev_net(dev), fib6_ifup, &arg);
 }
 
+/* only called for fib entries with inline fib6_nh */
 static bool rt6_multipath_uses_dev(const struct fib6_info *rt,
 				   const struct net_device *dev)
 {
@@ -4232,7 +4622,7 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
 	const struct net_device *dev = arg->dev;
 	struct net *net = dev_net(dev);
 
-	if (rt == net->ipv6.fib6_null_entry)
+	if (rt == net->ipv6.fib6_null_entry || rt->nh)
 		return 0;
 
 	switch (arg->event) {
@@ -4343,6 +4733,12 @@ static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg)
 		return 0;
 
 	arg->f6i = f6i;
+	if (f6i->nh) {
+		/* fib6_nh_mtu_change only returns 0, so this is safe */
+		return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_mtu_change,
+						arg);
+	}
+
 	return fib6_nh_mtu_change(f6i->fib6_nh, arg);
 }
 
@@ -4375,6 +4771,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_IP_PROTO]		= { .type = NLA_U8 },
 	[RTA_SPORT]		= { .type = NLA_U16 },
 	[RTA_DPORT]		= { .type = NLA_U16 },
+	[RTA_NH_ID]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -4421,6 +4818,16 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	cfg->fc_flags |= (rtm->rtm_flags & RTNH_F_ONLINK);
 
+	if (tb[RTA_NH_ID]) {
+		if (tb[RTA_GATEWAY]   || tb[RTA_OIF] ||
+		    tb[RTA_MULTIPATH] || tb[RTA_ENCAP]) {
+			NL_SET_ERR_MSG(extack,
+				       "Nexthop specification and nexthop id are mutually exclusive");
+			goto errout;
+		}
+		cfg->fc_nh_id = nla_get_u32(tb[RTA_NH_ID]);
+	}
+
 	if (tb[RTA_GATEWAY]) {
 		cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]);
 		cfg->fc_flags |= RTF_GATEWAY;
@@ -4564,6 +4971,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 {
 	struct fib6_info *rt_notif = NULL, *rt_last = NULL;
 	struct nl_info *info = &cfg->fc_nlinfo;
+	enum fib_event_type event_type;
 	struct fib6_config r_cfg;
 	struct rtnexthop *rtnh;
 	struct fib6_info *rt;
@@ -4641,6 +5049,11 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 	 */
 	info->skip_notify = 1;
 
+	/* For add and replace, send one notification with all nexthops. For
+	 * append, send one notification with all appended nexthops.
+	 */
+	info->skip_notify_kernel = 1;
+
 	err_nh = NULL;
 	list_for_each_entry(nh, &rt6_nh_list, next) {
 		err = __ip6_ins_rt(nh->fib6_info, info, extack);
@@ -4677,6 +5090,15 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		nhn++;
 	}
 
+	event_type = replace ? FIB_EVENT_ENTRY_REPLACE : FIB_EVENT_ENTRY_ADD;
+	err = call_fib6_multipath_entry_notifiers(info->nl_net, event_type,
+						  rt_notif, nhn - 1, extack);
+	if (err) {
+		/* Delete all the siblings that were just added */
+		err_nh = NULL;
+		goto add_errout;
+	}
+
 	/* success ... tell user about new route */
 	ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags);
 	goto cleanup;
@@ -4755,6 +5177,12 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		return err;
 
+	if (cfg.fc_nh_id &&
+	    !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id)) {
+		NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+		return -EINVAL;
+	}
+
 	if (cfg.fc_mp)
 		return ip6_route_multipath_del(&cfg, extack);
 	else {
@@ -4782,17 +5210,46 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return ip6_route_add(&cfg, GFP_KERNEL, extack);
 }
 
-static size_t rt6_nlmsg_size(struct fib6_info *rt)
+/* add the overhead of this fib6_nh to nexthop_len */
+static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg)
+{
+	int *nexthop_len = arg;
+
+	*nexthop_len += nla_total_size(0)	 /* RTA_MULTIPATH */
+		     + NLA_ALIGN(sizeof(struct rtnexthop))
+		     + nla_total_size(16); /* RTA_GATEWAY */
+
+	if (nh->fib_nh_lws) {
+		/* RTA_ENCAP_TYPE */
+		*nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
+		/* RTA_ENCAP */
+		*nexthop_len += nla_total_size(2);
+	}
+
+	return 0;
+}
+
+static size_t rt6_nlmsg_size(struct fib6_info *f6i)
 {
-	int nexthop_len = 0;
+	int nexthop_len;
+
+	if (f6i->nh) {
+		nexthop_len = nla_total_size(4); /* RTA_NH_ID */
+		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
+					 &nexthop_len);
+	} else {
+		struct fib6_nh *nh = f6i->fib6_nh;
 
-	if (rt->fib6_nsiblings) {
-		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->fib_nh_lws);
+		nexthop_len = 0;
+		if (f6i->fib6_nsiblings) {
+			nexthop_len = nla_total_size(0)	 /* RTA_MULTIPATH */
+				    + NLA_ALIGN(sizeof(struct rtnexthop))
+				    + nla_total_size(16) /* RTA_GATEWAY */
+				    + lwtunnel_get_encap_size(nh->fib_nh_lws);
 
-		nexthop_len *= rt->fib6_nsiblings;
+			nexthop_len *= f6i->fib6_nsiblings;
+		}
+		nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
 	}
 
 	return NLMSG_ALIGN(sizeof(struct rtmsg))
@@ -4808,10 +5265,38 @@ 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->fib_nh_lws)
 	       + nexthop_len;
 }
 
+static int rt6_fill_node_nexthop(struct sk_buff *skb, struct nexthop *nh,
+				 unsigned char *flags)
+{
+	if (nexthop_is_multipath(nh)) {
+		struct nlattr *mp;
+
+		mp = nla_nest_start(skb, RTA_MULTIPATH);
+		if (!mp)
+			goto nla_put_failure;
+
+		if (nexthop_mpath_fill_node(skb, nh))
+			goto nla_put_failure;
+
+		nla_nest_end(skb, mp);
+	} else {
+		struct fib6_nh *fib6_nh;
+
+		fib6_nh = nexthop_fib6_nh(nh);
+		if (fib_nexthop_info(skb, &fib6_nh->nh_common,
+				     flags, false) < 0)
+			goto nla_put_failure;
+	}
+
+	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,
@@ -4821,6 +5306,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
 	struct rt6key *rt6_dst, *rt6_src;
 	u32 *pmetrics, table, rt6_flags;
+	unsigned char nh_flags = 0;
 	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
 	long expires = 0;
@@ -4940,9 +5426,18 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		}
 
 		nla_nest_end(skb, mp);
-	} else {
-		unsigned char nh_flags = 0;
+	} else if (rt->nh) {
+		if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id))
+			goto nla_put_failure;
 
+		if (nexthop_is_blackhole(rt->nh))
+			rtm->rtm_type = RTN_BLACKHOLE;
+
+		if (rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0)
+			goto nla_put_failure;
+
+		rtm->rtm_flags |= nh_flags;
+	} else {
 		if (fib_nexthop_info(skb, &rt->fib6_nh->nh_common,
 				     &nh_flags, false) < 0)
 			goto nla_put_failure;
@@ -4970,9 +5465,27 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int fib6_info_nh_uses_dev(struct fib6_nh *nh, void *arg)
+{
+	const struct net_device *dev = arg;
+
+	if (nh->fib_nh_dev == dev)
+		return 1;
+
+	return 0;
+}
+
 static bool fib6_info_uses_dev(const struct fib6_info *f6i,
 			       const struct net_device *dev)
 {
+	if (f6i->nh) {
+		struct net_device *_dev = (struct net_device *)dev;
+
+		return !!nexthop_for_each_fib6_nh(f6i->nh,
+						  fib6_info_nh_uses_dev,
+						  _dev);
+	}
+
 	if (f6i->fib6_nh->fib_nh_dev == dev)
 		return true;