1 files changed, 628 insertions, 100 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index df5be3d5d3e5..be5e65c97652 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,
@@ -494,6 +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)
 {
@@ -514,8 +549,19 @@ static void rt6_device_match(struct net *net, struct fib6_result *res,
 	}
 
 	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;
 		}
@@ -719,6 +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,
@@ -729,6 +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) {
@@ -739,8 +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;
@@ -1300,9 +1391,6 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 
 	pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu);
 
-	if (pcpu_rt)
-		ip6_hold_safe(NULL, &pcpu_rt);
-
 	return pcpu_rt;
 }
 
@@ -1312,12 +1400,9 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
 	struct rt6_info *pcpu_rt, *prev, **p;
 
 	pcpu_rt = ip6_rt_pcpu_alloc(res);
-	if (!pcpu_rt) {
-		dst_hold(&net->ipv6.ip6_null_entry->dst);
-		return net->ipv6.ip6_null_entry;
-	}
+	if (!pcpu_rt)
+		return NULL;
 
-	dst_hold(&pcpu_rt->dst);
 	p = this_cpu_ptr(res->nh->rt6i_pcpu);
 	prev = cmpxchg(p, NULL, pcpu_rt);
 	BUG_ON(prev);
@@ -1651,9 +1736,22 @@ 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
@@ -1740,6 +1838,23 @@ 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;
@@ -1748,6 +1863,20 @@ 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);
 }
@@ -1778,9 +1907,33 @@ 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();
 
@@ -1788,7 +1941,21 @@ 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();
 }
@@ -1950,11 +2117,34 @@ 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 */
@@ -1993,9 +2183,12 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 			       const struct sk_buff *skb, int flags)
 {
 	struct fib6_result res = {};
-	struct rt6_info *rt;
+	struct rt6_info *rt = NULL;
 	int strict = 0;
 
+	WARN_ON_ONCE((flags & RT6_LOOKUP_F_DST_NOREF) &&
+		     !rcu_read_lock_held());
+
 	strict |= flags & RT6_LOOKUP_F_IFACE;
 	strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
 	if (net->ipv6.devconf_all->forwarding == 0)
@@ -2004,23 +2197,15 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 	rcu_read_lock();
 
 	fib6_table_lookup(net, table, oif, fl6, &res, strict);
-	if (res.f6i == net->ipv6.fib6_null_entry) {
-		rt = net->ipv6.ip6_null_entry;
-		rcu_read_unlock();
-		dst_hold(&rt->dst);
-		return rt;
-	}
+	if (res.f6i == net->ipv6.fib6_null_entry)
+		goto out;
 
 	fib6_select_path(net, &res, fl6, oif, false, skb, strict);
 
 	/*Search through exception table */
 	rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr);
 	if (rt) {
-		if (ip6_hold_safe(net, &rt))
-			dst_use_noref(&rt->dst, jiffies);
-
-		rcu_read_unlock();
-		return rt;
+		goto out;
 	} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
 			    !res.nh->fib_nh_gw_family)) {
 		/* Create a RTF_CACHE clone which will not be
@@ -2028,40 +2213,38 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		 * the daddr in the skb during the neighbor look-up is different
 		 * from the fl6->daddr used to look-up route here.
 		 */
-		struct rt6_info *uncached_rt;
+		rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL);
 
-		uncached_rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL);
-
-		rcu_read_unlock();
-
-		if (uncached_rt) {
-			/* Uncached_rt's refcnt is taken during ip6_rt_cache_alloc()
-			 * No need for another dst_hold()
+		if (rt) {
+			/* 1 refcnt is taken during ip6_rt_cache_alloc().
+			 * As rt6_uncached_list_add() does not consume refcnt,
+			 * this refcnt is always returned to the caller even
+			 * if caller sets RT6_LOOKUP_F_DST_NOREF flag.
 			 */
-			rt6_uncached_list_add(uncached_rt);
+			rt6_uncached_list_add(rt);
 			atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache);
-		} else {
-			uncached_rt = net->ipv6.ip6_null_entry;
-			dst_hold(&uncached_rt->dst);
-		}
+			rcu_read_unlock();
 
-		return uncached_rt;
+			return rt;
+		}
 	} else {
 		/* Get a percpu copy */
-
-		struct rt6_info *pcpu_rt;
-
 		local_bh_disable();
-		pcpu_rt = rt6_get_pcpu_route(&res);
+		rt = rt6_get_pcpu_route(&res);
 
-		if (!pcpu_rt)
-			pcpu_rt = rt6_make_pcpu_route(net, &res);
+		if (!rt)
+			rt = rt6_make_pcpu_route(net, &res);
 
 		local_bh_enable();
-		rcu_read_unlock();
-
-		return pcpu_rt;
 	}
+out:
+	if (!rt)
+		rt = net->ipv6.ip6_null_entry;
+	if (!(flags & RT6_LOOKUP_F_DST_NOREF))
+		ip6_hold_safe(net, &rt);
+	rcu_read_unlock();
+
+	return rt;
 }
 EXPORT_SYMBOL_GPL(ip6_pol_route);
 
@@ -2192,11 +2375,12 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 	return mhash >> 1;
 }
 
+/* Called with rcu held */
 void ip6_route_input(struct sk_buff *skb)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct net *net = dev_net(skb->dev);
-	int flags = RT6_LOOKUP_F_HAS_SADDR;
+	int flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_DST_NOREF;
 	struct ip_tunnel_info *tun_info;
 	struct flowi6 fl6 = {
 		.flowi6_iif = skb->dev->ifindex,
@@ -2218,8 +2402,8 @@ void ip6_route_input(struct sk_buff *skb)
 	if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6))
 		fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys);
 	skb_dst_drop(skb);
-	skb_dst_set(skb,
-		    ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags));
+	skb_dst_set_noref(skb, ip6_route_input_lookup(net, skb->dev,
+						      &fl6, skb, flags));
 }
 
 static struct rt6_info *ip6_pol_route_output(struct net *net,
@@ -2231,8 +2415,9 @@ static struct rt6_info *ip6_pol_route_output(struct net *net,
 	return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags);
 }
 
-struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
-					 struct flowi6 *fl6, int flags)
+struct dst_entry *ip6_route_output_flags_noref(struct net *net,
+					       const struct sock *sk,
+					       struct flowi6 *fl6, int flags)
 {
 	bool any_src;
 
@@ -2240,6 +2425,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 	    (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) {
 		struct dst_entry *dst;
 
+		/* This function does not take refcnt on the dst */
 		dst = l3mdev_link_scope_lookup(net, fl6);
 		if (dst)
 			return dst;
@@ -2247,6 +2433,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 
 	fl6->flowi6_iif = LOOPBACK_IFINDEX;
 
+	flags |= RT6_LOOKUP_F_DST_NOREF;
 	any_src = ipv6_addr_any(&fl6->saddr);
 	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) ||
 	    (fl6->flowi6_oif && any_src))
@@ -2259,6 +2446,28 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 
 	return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output);
 }
+EXPORT_SYMBOL_GPL(ip6_route_output_flags_noref);
+
+struct dst_entry *ip6_route_output_flags(struct net *net,
+					 const struct sock *sk,
+					 struct flowi6 *fl6,
+					 int flags)
+{
+        struct dst_entry *dst;
+        struct rt6_info *rt6;
+
+        rcu_read_lock();
+        dst = ip6_route_output_flags_noref(net, sk, fl6, flags);
+        rt6 = (struct rt6_info *)dst;
+        /* For dst cached in uncached_list, refcnt is already taken. */
+        if (list_empty(&rt6->rt6i_uncached) && !dst_hold_safe(dst)) {
+                dst = &net->ipv6.ip6_null_entry->dst;
+                dst_hold(dst);
+        }
+        rcu_read_unlock();
+
+        return dst;
+}
 EXPORT_SYMBOL_GPL(ip6_route_output_flags);
 
 struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
@@ -2483,10 +2692,31 @@ 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);
@@ -2593,6 +2823,21 @@ 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;
@@ -2608,6 +2853,12 @@ 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;
 
@@ -2632,14 +2883,24 @@ 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)
@@ -3283,6 +3544,16 @@ 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 &&
@@ -3328,7 +3599,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 
 	rt->fib6_table = table;
 	rt->fib6_metric = cfg->fc_metric;
-	rt->fib6_type = cfg->fc_type;
+	rt->fib6_type = cfg->fc_type ? : RTN_UNICAST;
 	rt->fib6_flags = cfg->fc_flags & ~RTF_GATEWAY;
 
 	ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
@@ -3346,7 +3617,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 			goto out;
 		}
 		if (rt->fib6_src.plen) {
-			NL_SET_ERR_MSG(extack, "Nexthops can not be used wtih source routing");
+			NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
 			goto out;
 		}
 		rt->nh = nh;
@@ -3460,6 +3731,12 @@ 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) {
@@ -3514,6 +3791,30 @@ 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)
 {
@@ -3539,11 +3840,21 @@ 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 && cfg->fc_nh_id &&
+			    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;
@@ -3551,6 +3862,23 @@ 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))
@@ -3558,10 +3886,6 @@ 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();
@@ -3672,7 +3996,25 @@ 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);
@@ -4405,6 +4747,12 @@ 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);
 }
 
@@ -4437,6 +4785,7 @@ 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,
@@ -4483,6 +4832,16 @@ 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;
@@ -4626,6 +4985,7 @@ 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;
@@ -4697,12 +5057,23 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
+	if (list_empty(&rt6_nh_list)) {
+		NL_SET_ERR_MSG(extack,
+			       "Invalid nexthop configuration - no valid nexthops");
+		return -EINVAL;
+	}
+
 	/* for add and replace send one notification with all nexthops.
 	 * Skip the notification in fib6_add_rt2node and send one with
 	 * the full route when done
 	 */
 	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);
@@ -4739,6 +5110,15 @@ 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;
@@ -4817,6 +5197,12 @@ 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 {
@@ -4844,20 +5230,46 @@ 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 = 0;
+	int *nexthop_len = arg;
 
-	if (rt->nh)
-		nexthop_len += nla_total_size(4); /* RTA_NH_ID */
+	*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);
+	}
 
-	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);
+	return 0;
+}
 
-		nexthop_len *= rt->fib6_nsiblings;
+static size_t rt6_nlmsg_size(struct fib6_info *f6i)
+{
+	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;
+
+		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 *= f6i->fib6_nsiblings;
+		}
+		nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
 	}
 
 	return NLMSG_ALIGN(sizeof(struct rtmsg))
@@ -4873,7 +5285,6 @@ 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;
 }
 
@@ -5074,9 +5485,27 @@ 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;
 
@@ -5093,33 +5522,129 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i,
 	return false;
 }
 
-int rt6_dump_route(struct fib6_info *rt, void *p_arg)
+struct fib6_nh_exception_dump_walker {
+	struct rt6_rtnl_dump_arg *dump;
+	struct fib6_info *rt;
+	unsigned int flags;
+	unsigned int skip;
+	unsigned int count;
+};
+
+static int rt6_nh_dump_exceptions(struct fib6_nh *nh, void *arg)
+{
+	struct fib6_nh_exception_dump_walker *w = arg;
+	struct rt6_rtnl_dump_arg *dump = w->dump;
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	int i, err;
+
+	bucket = fib6_nh_get_excptn_bucket(nh, NULL);
+	if (!bucket)
+		return 0;
+
+	for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+		hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+			if (w->skip) {
+				w->skip--;
+				continue;
+			}
+
+			/* Expiration of entries doesn't bump sernum, insertion
+			 * does. Removal is triggered by insertion, so we can
+			 * rely on the fact that if entries change between two
+			 * partial dumps, this node is scanned again completely,
+			 * see rt6_insert_exception() and fib6_dump_table().
+			 *
+			 * Count expired entries we go through as handled
+			 * entries that we'll skip next time, in case of partial
+			 * node dump. Otherwise, if entries expire meanwhile,
+			 * we'll skip the wrong amount.
+			 */
+			if (rt6_check_expired(rt6_ex->rt6i)) {
+				w->count++;
+				continue;
+			}
+
+			err = rt6_fill_node(dump->net, dump->skb, w->rt,
+					    &rt6_ex->rt6i->dst, NULL, NULL, 0,
+					    RTM_NEWROUTE,
+					    NETLINK_CB(dump->cb->skb).portid,
+					    dump->cb->nlh->nlmsg_seq, w->flags);
+			if (err)
+				return err;
+
+			w->count++;
+		}
+		bucket++;
+	}
+
+	return 0;
+}
+
+/* Return -1 if done with node, number of handled routes on partial dump */
+int rt6_dump_route(struct fib6_info *rt, void *p_arg, unsigned int skip)
 {
 	struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
 	struct fib_dump_filter *filter = &arg->filter;
 	unsigned int flags = NLM_F_MULTI;
 	struct net *net = arg->net;
+	int count = 0;
 
 	if (rt == net->ipv6.fib6_null_entry)
-		return 0;
+		return -1;
 
 	if ((filter->flags & RTM_F_PREFIX) &&
 	    !(rt->fib6_flags & RTF_PREFIX_RT)) {
 		/* success since this is not a prefix route */
-		return 1;
+		return -1;
 	}
-	if (filter->filter_set) {
-		if ((filter->rt_type && rt->fib6_type != filter->rt_type) ||
-		    (filter->dev && !fib6_info_uses_dev(rt, filter->dev)) ||
-		    (filter->protocol && rt->fib6_protocol != filter->protocol)) {
-			return 1;
-		}
+	if (filter->filter_set &&
+	    ((filter->rt_type  && rt->fib6_type != filter->rt_type) ||
+	     (filter->dev      && !fib6_info_uses_dev(rt, filter->dev)) ||
+	     (filter->protocol && rt->fib6_protocol != filter->protocol))) {
+		return -1;
+	}
+
+	if (filter->filter_set ||
+	    !filter->dump_routes || !filter->dump_exceptions) {
 		flags |= NLM_F_DUMP_FILTERED;
 	}
 
-	return rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0,
-			     RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid,
-			     arg->cb->nlh->nlmsg_seq, flags);
+	if (filter->dump_routes) {
+		if (skip) {
+			skip--;
+		} else {
+			if (rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL,
+					  0, RTM_NEWROUTE,
+					  NETLINK_CB(arg->cb->skb).portid,
+					  arg->cb->nlh->nlmsg_seq, flags)) {
+				return 0;
+			}
+			count++;
+		}
+	}
+
+	if (filter->dump_exceptions) {
+		struct fib6_nh_exception_dump_walker w = { .dump = arg,
+							   .rt = rt,
+							   .flags = flags,
+							   .skip = skip,
+							   .count = 0 };
+		int err;
+
+		if (rt->nh) {
+			err = nexthop_for_each_fib6_nh(rt->nh,
+						       rt6_nh_dump_exceptions,
+						       &w);
+		} else {
+			err = rt6_nh_dump_exceptions(rt->fib6_nh, &w);
+		}
+
+		if (err)
+			return count += w.count;
+	}
+
+	return -1;
 }
 
 static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
@@ -5614,6 +6139,7 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
 	dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
 			 ip6_template_metrics, true);
+	INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->rt6i_uncached);
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 	net->ipv6.fib6_has_custom_rules = false;
@@ -5625,6 +6151,7 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops;
 	dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst,
 			 ip6_template_metrics, true);
+	INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->rt6i_uncached);
 
 	net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
 					       sizeof(*net->ipv6.ip6_blk_hole_entry),
@@ -5634,6 +6161,7 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops;
 	dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
 			 ip6_template_metrics, true);
+	INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->rt6i_uncached);
 #endif
 
 	net->ipv6.sysctl.flush_delay = 0;