Merge branch 'net-Enable-nexthop-objects-with-IPv4-and-IPv6-routes'

David Ahern says:

====================
net: Enable nexthop objects with IPv4 and IPv6 routes

This is the final set of the initial nexthop object work. When I
started this idea almost 2 years ago, it took 18 seconds to inject
700k+ IPv4 routes with 1 hop and about 28 seconds for 4-paths. Some
of that time was due to inefficiencies in 'ip', but most of it was
kernel side with excessive synchronize_rcu calls in ipv4, and redundant
processing validating a nexthop spec (device, gateway, encap). Worse,
the time increased dramatically as the number of legs in the routes
increased; for example, taking over 72 seconds for 16-path routes.

After this set, with increased dirty memory limits (fib_sync_mem sysctl),
an improved ip and nexthop objects a full internet fib (743,799 routes
based on a pull in January 2019) can be pushed to the kernel in 4.3
seconds. Even better, the time to insert is "almost" constant with
increasing number of paths. The 'almost constant' time is due to
expanding the nexthop definitions when generating notifications. A
follow on patch will be sent adding a sysctl that allows an admin to
avoid the nexthop expansion and truly get constant route insert time
regardless of the number of paths in a route! (Useful once all programs
used for a deployment that care about routes understand nexthop objects).

To be clear, 'ip' is used for benchmarking for no other reason than
'ip -batch' is a trivial to use for the tests. FRR, for example, better
manages nexthops and route changes and the way those are pushed to the
kernel and thus will have less userspace processing times than 'ip -batch'.

Patches 1-10 iterate over fib6_nh with a nexthop invoke a processing
function per fib6_nh. Prior to nexthop objects, a fib6_info referenced
a single fib6_nh. Multipath routes were added as separate fib6_info for
each leg of the route and linked as siblings:

    f6i -> sibling -> sibling ... -> sibling
     |                                   |
     +--------- multipath route ---------+

With nexthop objects a single fib6_info references an external
nexthop which may have a series of fib6_nh:

     f6i ---> nexthop ---> fib6_nh
                           ...
                           fib6_nh

making IPv6 routes similar to IPv4. The side effect is that a single
fib6_info now indirectly references a series of fib6_nh so the code
needs to walk each entry and call the local, per-fib6_nh processing
function.

Patches 11 and 13 wire up use of nexthops with fib entries for IPv4
and IPv6. With these commits you can actually use nexthops with routes.

Patch 12 is an optimization for IPv4 when using nexthops in the most
predominant use case (no metrics).

Patches 14 handles replace of a nexthop config.

Patches 15-18 add update pmtu and redirect tests to use both old and
new routing.

Patches 19 and 20 add new tests for the nexthop infrastructure. The first
is single nexthop is used by multiple prefixes to communicate with remote
hosts. This is on top of the functional tests already committed. The
second verifies multipath selection.

v4
- changed return to 'goto out' in patch 9 since the rcu_read_lock is
  held (noticed by Wei)

v3
- removed found arg in patch 7 and changed rt6_nh_remove_exception_rt
  to return 1 when a match is found for an exception

v2
- changed ++i to i++ in patches 1 and 14 as noticed by DaveM
- improved commit message for patch 14 (nexthop replace)
- removed the skip_fib argument to remove_nexthop; vestige of an
  older design
====================
Reviewed-By: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip6_fib.h

@@ -49,6 +49,7 @@ struct fib6_config {
 	u16		fc_delete_all_nh : 1,
 			fc_ignore_dev_down:1,
 			__unused : 14;
+	u32		fc_nh_id;
 
 	struct in6_addr	fc_dst;
 	struct in6_addr	fc_src;

include/net/ip_fib.h

@@ -40,6 +40,7 @@ struct fib_config {
 	u32			fc_flags;
 	u32			fc_priority;
 	__be32			fc_prefsrc;
+	u32			fc_nh_id;
 	struct nlattr		*fc_mx;
 	struct rtnexthop	*fc_mp;
 	int			fc_mx_len;

include/net/nexthop.h

@@ -305,4 +305,8 @@ static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash)
 		res->nh = &nhi->fib6_nh;
 	}
 }
+
+int nexthop_for_each_fib6_nh(struct nexthop *nh,
+			     int (*cb)(struct fib6_nh *nh, void *arg),
+			     void *arg);
 #endif

net/ipv4/fib_frontend.c

@@ -671,6 +671,7 @@ const struct nla_policy rtm_ipv4_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 },
 };
 
 int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
@@ -808,6 +809,18 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			if (err < 0)
 				goto errout;
 			break;
+		case RTA_NH_ID:
+			cfg->fc_nh_id = nla_get_u32(attr);
+			break;
+		}
+	}
+
+	if (cfg->fc_nh_id) {
+		if (cfg->fc_oif || cfg->fc_gw_family ||
+		    cfg->fc_encap || cfg->fc_mp) {
+			NL_SET_ERR_MSG(extack,
+				       "Nexthop specification and nexthop id are mutually exclusive");
+			return -EINVAL;
 		}
 	}
 
@@ -834,6 +847,12 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		goto errout;
 
+	if (cfg.fc_nh_id && !nexthop_find_by_id(net, cfg.fc_nh_id)) {
+		NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+		err = -EINVAL;
+		goto errout;
+	}
+
 	tb = fib_get_table(net, cfg.fc_table);
 	if (!tb) {
 		NL_SET_ERR_MSG(extack, "FIB table does not exist");

net/ipv4/fib_semantics.c

@@ -325,14 +325,32 @@ static inline unsigned int fib_devindex_hashfn(unsigned int val)
 		(val >> (DEVINDEX_HASHBITS * 2))) & mask;
 }
 
-static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
+static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope,
+				      u32 prefsrc, u32 priority)
+{
+	unsigned int val = init_val;
+
+	val ^= (protocol << 8) | scope;
+	val ^= prefsrc;
+	val ^= priority;
+
+	return val;
+}
+
+static unsigned int fib_info_hashfn_result(unsigned int val)
 {
 	unsigned int mask = (fib_info_hash_size - 1);
-	unsigned int val = fi->fib_nhs;
 
-	val ^= (fi->fib_protocol << 8) | fi->fib_scope;
-	val ^= (__force u32)fi->fib_prefsrc;
-	val ^= fi->fib_priority;
+	return (val ^ (val >> 7) ^ (val >> 12)) & mask;
+}
+
+static inline unsigned int fib_info_hashfn(struct fib_info *fi)
+{
+	unsigned int val;
+
+	val = fib_info_hashfn_1(fi->fib_nhs, fi->fib_protocol,
+				fi->fib_scope, (__force u32)fi->fib_prefsrc,
+				fi->fib_priority);
 
 	if (fi->nh) {
 		val ^= fib_devindex_hashfn(fi->nh->id);
@@ -342,7 +360,40 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
 		} endfor_nexthops(fi)
 	}
 
-	return (val ^ (val >> 7) ^ (val >> 12)) & mask;
+	return fib_info_hashfn_result(val);
+}
+
+/* no metrics, only nexthop id */
+static struct fib_info *fib_find_info_nh(struct net *net,
+					 const struct fib_config *cfg)
+{
+	struct hlist_head *head;
+	struct fib_info *fi;
+	unsigned int hash;
+
+	hash = fib_info_hashfn_1(fib_devindex_hashfn(cfg->fc_nh_id),
+				 cfg->fc_protocol, cfg->fc_scope,
+				 (__force u32)cfg->fc_prefsrc,
+				 cfg->fc_priority);
+	hash = fib_info_hashfn_result(hash);
+	head = &fib_info_hash[hash];
+
+	hlist_for_each_entry(fi, head, fib_hash) {
+		if (!net_eq(fi->fib_net, net))
+			continue;
+		if (!fi->nh || fi->nh->id != cfg->fc_nh_id)
+			continue;
+		if (cfg->fc_protocol == fi->fib_protocol &&
+		    cfg->fc_scope == fi->fib_scope &&
+		    cfg->fc_prefsrc == fi->fib_prefsrc &&
+		    cfg->fc_priority == fi->fib_priority &&
+		    cfg->fc_type == fi->fib_type &&
+		    cfg->fc_table == fi->fib_tb_id &&
+		    !((cfg->fc_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK))
+			return fi;
+	}
+
+	return NULL;
 }
 
 static struct fib_info *fib_find_info(struct fib_info *nfi)
@@ -789,6 +840,12 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 	if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
 		return 1;
 
+	if (cfg->fc_nh_id) {
+		if (fi->nh && cfg->fc_nh_id == fi->nh->id)
+			return 0;
+		return 1;
+	}
+
 	if (cfg->fc_oif || cfg->fc_gw_family) {
 		struct fib_nh *nh = fib_info_nh(fi, 0);
 
@@ -1302,6 +1359,23 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		goto err_inval;
 	}
 
+	if (cfg->fc_nh_id) {
+		if (!cfg->fc_mx) {
+			fi = fib_find_info_nh(net, cfg);
+			if (fi) {
+				fi->fib_treeref++;
+				return fi;
+			}
+		}
+
+		nh = nexthop_find_by_id(net, cfg->fc_nh_id);
+		if (!nh) {
+			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+			goto err_inval;
+		}
+		nhs = 0;
+	}
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (cfg->fc_mp) {
 		nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len, extack);

net/ipv4/nexthop.c

@@ -517,6 +517,47 @@ struct nexthop *nexthop_select_path(struct nexthop *nh, int hash)
 }
 EXPORT_SYMBOL_GPL(nexthop_select_path);
 
+int nexthop_for_each_fib6_nh(struct nexthop *nh,
+			     int (*cb)(struct fib6_nh *nh, void *arg),
+			     void *arg)
+{
+	struct nh_info *nhi;
+	int err;
+
+	if (nh->is_group) {
+		struct nh_group *nhg;
+		int i;
+
+		nhg = rcu_dereference_rtnl(nh->nh_grp);
+		for (i = 0; i < nhg->num_nh; i++) {
+			struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+
+			nhi = rcu_dereference_rtnl(nhge->nh->nh_info);
+			err = cb(&nhi->fib6_nh, arg);
+			if (err)
+				return err;
+		}
+	} else {
+		nhi = rcu_dereference_rtnl(nh->nh_info);
+		err = cb(&nhi->fib6_nh, arg);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nexthop_for_each_fib6_nh);
+
+static int check_src_addr(const struct in6_addr *saddr,
+			  struct netlink_ext_ack *extack)
+{
+	if (!ipv6_addr_any(saddr)) {
+		NL_SET_ERR_MSG(extack, "IPv6 routes using source address can not use nexthop objects");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
 		       struct netlink_ext_ack *extack)
 {
@@ -528,10 +569,8 @@ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
 	 * routing it can not use nexthop objects. mlxsw also does not allow
 	 * fib6_src on routes.
 	 */
-	if (!ipv6_addr_any(&cfg->fc_src)) {
-		NL_SET_ERR_MSG(extack, "IPv6 routes using source address can not use nexthop objects");
+	if (cfg && check_src_addr(&cfg->fc_src, extack) < 0)
 		return -EINVAL;
-	}
 
 	if (nh->is_group) {
 		struct nh_group *nhg;
@@ -552,6 +591,25 @@ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
 }
 EXPORT_SYMBOL_GPL(fib6_check_nexthop);
 
+/* if existing nexthop has ipv6 routes linked to it, need
+ * to verify this new spec works with ipv6
+ */
+static int fib6_check_nh_list(struct nexthop *old, struct nexthop *new,
+			      struct netlink_ext_ack *extack)
+{
+	struct fib6_info *f6i;
+
+	if (list_empty(&old->f6i_list))
+		return 0;
+
+	list_for_each_entry(f6i, &old->f6i_list, nh_list) {
+		if (check_src_addr(&f6i->fib6_src.addr, extack) < 0)
+			return -EINVAL;
+	}
+
+	return fib6_check_nexthop(new, NULL, extack);
+}
+
 static int nexthop_check_scope(struct nexthop *nh, u8 scope,
 			       struct netlink_ext_ack *extack)
 {
@@ -600,6 +658,21 @@ int fib_check_nexthop(struct nexthop *nh, u8 scope,
 	return err;
 }
 
+static int fib_check_nh_list(struct nexthop *old, struct nexthop *new,
+			     struct netlink_ext_ack *extack)
+{
+	struct fib_info *fi;
+
+	list_for_each_entry(fi, &old->fi_list, nh_list) {
+		int err;
+
+		err = fib_check_nexthop(new, fi->fib_scope, extack);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
 static void nh_group_rebalance(struct nh_group *nhg)
 {
 	int total = 0;
@@ -692,6 +765,7 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
 	}
 }
 
+/* not called for nexthop replace */
 static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
 {
 	struct fib6_info *f6i, *tmp;
@@ -746,10 +820,171 @@ static void remove_nexthop(struct net *net, struct nexthop *nh,
 	nexthop_put(nh);
 }
 
+/* if any FIB entries reference this nexthop, any dst entries
+ * need to be regenerated
+ */
+static void nh_rt_cache_flush(struct net *net, struct nexthop *nh)
+{
+	struct fib6_info *f6i;
+
+	if (!list_empty(&nh->fi_list))
+		rt_cache_flush(net);
+
+	list_for_each_entry(f6i, &nh->f6i_list, nh_list)
+		ipv6_stub->fib6_update_sernum(net, f6i);
+}
+
+static int replace_nexthop_grp(struct net *net, struct nexthop *old,
+			       struct nexthop *new,
+			       struct netlink_ext_ack *extack)
+{
+	struct nh_group *oldg, *newg;
+	int i;
+
+	if (!new->is_group) {
+		NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop.");
+		return -EINVAL;
+	}
+
+	oldg = rtnl_dereference(old->nh_grp);
+	newg = rtnl_dereference(new->nh_grp);
+
+	/* update parents - used by nexthop code for cleanup */
+	for (i = 0; i < newg->num_nh; i++)
+		newg->nh_entries[i].nh_parent = old;
+
+	rcu_assign_pointer(old->nh_grp, newg);
+
+	for (i = 0; i < oldg->num_nh; i++)
+		oldg->nh_entries[i].nh_parent = new;
+
+	rcu_assign_pointer(new->nh_grp, oldg);
+
+	return 0;
+}
+
+static int replace_nexthop_single(struct net *net, struct nexthop *old,
+				  struct nexthop *new,
+				  struct netlink_ext_ack *extack)
+{
+	struct nh_info *oldi, *newi;
+
+	if (new->is_group) {
+		NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group.");
+		return -EINVAL;
+	}
+
+	oldi = rtnl_dereference(old->nh_info);
+	newi = rtnl_dereference(new->nh_info);
+
+	newi->nh_parent = old;
+	oldi->nh_parent = new;
+
+	old->protocol = new->protocol;
+	old->nh_flags = new->nh_flags;
+
+	rcu_assign_pointer(old->nh_info, newi);
+	rcu_assign_pointer(new->nh_info, oldi);
+
+	return 0;
+}
+
+static void __nexthop_replace_notify(struct net *net, struct nexthop *nh,
+				     struct nl_info *info)
+{
+	struct fib6_info *f6i;
+
+	if (!list_empty(&nh->fi_list)) {
+		struct fib_info *fi;
+
+		/* expectation is a few fib_info per nexthop and then
+		 * a lot of routes per fib_info. So mark the fib_info
+		 * and then walk the fib tables once
+		 */
+		list_for_each_entry(fi, &nh->fi_list, nh_list)
+			fi->nh_updated = true;
+
+		fib_info_notify_update(net, info);
+
+		list_for_each_entry(fi, &nh->fi_list, nh_list)
+			fi->nh_updated = false;
+	}
+
+	list_for_each_entry(f6i, &nh->f6i_list, nh_list)
+		ipv6_stub->fib6_rt_update(net, f6i, info);
+}
+
+/* send RTM_NEWROUTE with REPLACE flag set for all FIB entries
+ * linked to this nexthop and for all groups that the nexthop
+ * is a member of
+ */
+static void nexthop_replace_notify(struct net *net, struct nexthop *nh,
+				   struct nl_info *info)
+{
+	struct nh_grp_entry *nhge;
+
+	__nexthop_replace_notify(net, nh, info);
+
+	list_for_each_entry(nhge, &nh->grp_list, nh_list)
+		__nexthop_replace_notify(net, nhge->nh_parent, info);
+}
+
 static int replace_nexthop(struct net *net, struct nexthop *old,
 			   struct nexthop *new, struct netlink_ext_ack *extack)
 {
-	return -EEXIST;
+	bool new_is_reject = false;
+	struct nh_grp_entry *nhge;
+	int err;
+
+	/* check that existing FIB entries are ok with the
+	 * new nexthop definition
+	 */
+	err = fib_check_nh_list(old, new, extack);
+	if (err)
+		return err;
+
+	err = fib6_check_nh_list(old, new, extack);
+	if (err)
+		return err;
+
+	if (!new->is_group) {
+		struct nh_info *nhi = rtnl_dereference(new->nh_info);
+
+		new_is_reject = nhi->reject_nh;
+	}
+
+	list_for_each_entry(nhge, &old->grp_list, nh_list) {
+		/* if new nexthop is a blackhole, any groups using this
+		 * nexthop cannot have more than 1 path
+		 */
+		if (new_is_reject &&
+		    nexthop_num_path(nhge->nh_parent) > 1) {
+			NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be a member of a group with more than one path");
+			return -EINVAL;
+		}
+
+		err = fib_check_nh_list(nhge->nh_parent, new, extack);
+		if (err)
+			return err;
+
+		err = fib6_check_nh_list(nhge->nh_parent, new, extack);
+		if (err)
+			return err;
+	}
+
+	if (old->is_group)
+		err = replace_nexthop_grp(net, old, new, extack);
+	else
+		err = replace_nexthop_single(net, old, new, extack);
+
+	if (!err) {
+		nh_rt_cache_flush(net, old);
+
+		__remove_nexthop(net, new, NULL);
+		nexthop_put(new);
+	}
+
+	return err;
 }
 
 /* called with rtnl_lock held */
@@ -761,6 +996,7 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh,
 	bool replace = !!(cfg->nlflags & NLM_F_REPLACE);
 	bool create = !!(cfg->nlflags & NLM_F_CREATE);
 	u32 new_id = new_nh->id;
+	int replace_notify = 0;
 	int rc = -EEXIST;
 
 	pp = &root->rb_node;
@@ -780,8 +1016,10 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh,
 			pp = &next->rb_right;
 		} else if (replace) {
 			rc = replace_nexthop(net, nh, new_nh, extack);
-			if (!rc)
+			if (!rc) {
 				new_nh = nh; /* send notification with old nh */
+				replace_notify = 1;
+			}
 			goto out;
 		} else {
 			/* id already exists and not a replace */
@@ -802,6 +1040,8 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh,
 	if (!rc) {
 		nh_base_seq_inc(net);
 		nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo);
+		if (replace_notify)
+			nexthop_replace_notify(net, new_nh, &cfg->nlinfo);
 	}
 
 	return rc;

net/ipv6/ip6_fib.c

@@ -906,19 +906,42 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,
 	}
 }
 
+struct fib6_nh_pcpu_arg {
+	struct fib6_info	*from;
+	const struct fib6_table *table;
+};
+
+static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_pcpu_arg *arg = _arg;
+
+	__fib6_drop_pcpu_from(nh, arg->from, arg->table);
+	return 0;
+}
+
 static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 				const struct fib6_table *table)
 {
-	struct fib6_nh *fib6_nh;
-
 	/* Make sure rt6_make_pcpu_route() wont add other percpu routes
 	 * while we are cleaning them here.
 	 */
 	f6i->fib6_destroying = 1;
 	mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */
 
-	fib6_nh = f6i->fib6_nh;
-	__fib6_drop_pcpu_from(fib6_nh, f6i, table);
+	if (f6i->nh) {
+		struct fib6_nh_pcpu_arg arg = {
+			.from = f6i,
+			.table = table
+		};
+
+		nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from,
+					 &arg);
+	} else {
+		struct fib6_nh *fib6_nh;
+
+		fib6_nh = f6i->fib6_nh;
+		__fib6_drop_pcpu_from(fib6_nh, f6i, table);
+	}
 }
 
 static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,

net/ipv6/route.c

@@ -100,7 +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,
@@ -490,6 +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)
 {
@@ -510,8 +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;
 		}
@@ -715,6 +765,24 @@ static bool find_match(struct fib6_nh *nh, u32 fib6_flags,
 	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,
@@ -725,6 +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) {
@@ -735,8 +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;
@@ -1647,9 +1742,22 @@ static void fib6_nh_flush_exceptions(struct fib6_nh *nh, struct fib6_info *from)
 	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
@@ -1736,6 +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;
@@ -1744,6 +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);
 }
@@ -1774,9 +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();
 
@@ -1784,7 +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();
 }
@@ -1946,11 +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 */
@@ -2479,10 +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);
@@ -2589,6 +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;
@@ -2604,6 +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;
 
@@ -2628,14 +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)
@@ -3279,6 +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 &&
@@ -3510,6 +3772,30 @@ 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)
 {
@@ -3535,11 +3821,20 @@ 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;
@@ -3547,6 +3842,23 @@ 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))
@@ -3554,10 +3866,6 @@ 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();
@@ -3668,7 +3976,25 @@ 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);
@@ -4401,6 +4727,12 @@ 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);
 }
 
@@ -4433,6 +4765,7 @@ 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,
@@ -4479,6 +4812,16 @@ 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;
@@ -4813,6 +5156,12 @@ 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 {
@@ -4840,20 +5189,46 @@ 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))
@@ -4869,7 +5244,6 @@ 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;
 }
 
@@ -5070,9 +5444,27 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 	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;
 

tools/testing/selftests/net/fib_nexthop_multiprefix.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Validate cached routes in fib{6}_nh that is used by multiple prefixes.
+# Validate a different # exception is generated in h0 for each remote host.
+#
+#               h1
+#            /
+#    h0 - r1 -  h2
+#            \
+#               h3
+#
+# routing in h0 to hN is done with nexthop objects.
+
+PAUSE_ON_FAIL=no
+VERBOSE=0
+
+################################################################################
+# helpers
+
+log_test()
+{
+	local rc=$1
+	local expected=$2
+	local msg="$3"
+
+	if [ ${rc} -eq ${expected} ]; then
+		printf "TEST: %-60s  [ OK ]\n" "${msg}"
+		nsuccess=$((nsuccess+1))
+	else
+		ret=1
+		nfail=$((nfail+1))
+		printf "TEST: %-60s  [FAIL]\n" "${msg}"
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+			echo
+			echo "hit enter to continue, 'q' to quit"
+			read a
+			[ "$a" = "q" ] && exit 1
+		fi
+	fi
+
+	[ "$VERBOSE" = "1" ] && echo
+}
+
+run_cmd()
+{
+	local cmd="$*"
+	local out
+	local rc
+
+	if [ "$VERBOSE" = "1" ]; then
+		echo "COMMAND: $cmd"
+	fi
+
+	out=$(eval $cmd 2>&1)
+	rc=$?
+	if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+		echo "$out"
+	fi
+
+	[ "$VERBOSE" = "1" ] && echo
+
+	return $rc
+}
+
+################################################################################
+# config
+
+create_ns()
+{
+	local ns=${1}
+
+	ip netns del ${ns} 2>/dev/null
+
+	ip netns add ${ns}
+	ip -netns ${ns} addr add 127.0.0.1/8 dev lo
+	ip -netns ${ns} link set lo up
+
+	ip netns exec ${ns} sysctl -q -w net.ipv6.conf.all.keep_addr_on_down=1
+	case ${ns} in
+	h*)
+		ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=0
+		;;
+	r*)
+		ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
+		ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
+		;;
+	esac
+}
+
+setup()
+{
+	local ns
+	local i
+
+	#set -e
+
+	for ns in h0 r1 h1 h2 h3
+	do
+		create_ns ${ns}
+	done
+
+	#
+	# create interconnects
+	#
+
+	for i in 0 1 2 3
+	do
+		ip -netns h${i} li add eth0 type veth peer name r1h${i}
+		ip -netns h${i} li set eth0 up
+		ip -netns h${i} li set r1h${i} netns r1 name eth${i} up
+
+		ip -netns h${i}    addr add dev eth0 172.16.10${i}.1/24
+		ip -netns h${i} -6 addr add dev eth0 2001:db8:10${i}::1/64
+		ip -netns r1    addr add dev eth${i} 172.16.10${i}.254/24
+		ip -netns r1 -6 addr add dev eth${i} 2001:db8:10${i}::64/64
+	done
+
+	ip -netns h0 nexthop add id 4 via 172.16.100.254 dev eth0
+	ip -netns h0 nexthop add id 6 via 2001:db8:100::64 dev eth0
+
+	# routing from h0 to h1-h3 and back
+	for i in 1 2 3
+	do
+		ip -netns h0    ro add 172.16.10${i}.0/24 nhid 4
+		ip -netns h${i} ro add 172.16.100.0/24 via 172.16.10${i}.254
+
+		ip -netns h0    -6 ro add 2001:db8:10${i}::/64 nhid 6
+		ip -netns h${i} -6 ro add 2001:db8:100::/64 via 2001:db8:10${i}::64
+	done
+
+	if [ "$VERBOSE" = "1" ]; then
+		echo
+		echo "host 1 config"
+		ip -netns h0 li sh
+		ip -netns h0 ro sh
+		ip -netns h0 -6 ro sh
+	fi
+
+	#set +e
+}
+
+cleanup()
+{
+	for n in h1 r1 h2 h3 h4
+	do
+		ip netns del ${n} 2>/dev/null
+	done
+}
+
+change_mtu()
+{
+	local hostid=$1
+	local mtu=$2
+
+	run_cmd ip -netns h${hostid} li set eth0 mtu ${mtu}
+	run_cmd ip -netns r1 li set eth${hostid} mtu ${mtu}
+}
+
+################################################################################
+# validate exceptions
+
+validate_v4_exception()
+{
+	local i=$1
+	local mtu=$2
+	local ping_sz=$3
+	local dst="172.16.10${i}.1"
+	local h0=172.16.100.1
+	local r1=172.16.100.254
+	local rc
+
+	if [ ${ping_sz} != "0" ]; then
+		run_cmd ip netns exec h0 ping -s ${ping_sz} -c5 -w5 ${dst}
+	fi
+
+	if [ "$VERBOSE" = "1" ]; then
+		echo "Route get"
+		ip -netns h0 ro get ${dst}
+		echo "Searching for:"
+		echo "    cache .* mtu ${mtu}"
+		echo
+	fi
+
+	ip -netns h0 ro get ${dst} | \
+	grep -q "cache .* mtu ${mtu}"
+	rc=$?
+
+	log_test $rc 0 "IPv4: host 0 to host ${i}, mtu ${mtu}"
+}
+
+validate_v6_exception()
+{
+	local i=$1
+	local mtu=$2
+	local ping_sz=$3
+	local dst="2001:db8:10${i}::1"
+	local h0=2001:db8:100::1
+	local r1=2001:db8:100::64
+	local rc
+
+	if [ ${ping_sz} != "0" ]; then
+		run_cmd ip netns exec h0 ping6 -s ${ping_sz} -c5 -w5 ${dst}
+	fi
+
+	if [ "$VERBOSE" = "1" ]; then
+		echo "Route get"
+		ip -netns h0 -6 ro get ${dst}
+		echo "Searching for:"
+		echo "    ${dst} from :: via ${r1} dev eth0 src ${h0} .* mtu ${mtu}"
+		echo
+	fi
+
+	ip -netns h0 -6 ro get ${dst} | \
+	grep -q "${dst} from :: via ${r1} dev eth0 src ${h0} .* mtu ${mtu}"
+	rc=$?
+
+	log_test $rc 0 "IPv6: host 0 to host ${i}, mtu ${mtu}"
+}
+
+################################################################################
+# main
+
+while getopts :pv o
+do
+	case $o in
+		p) PAUSE_ON_FAIL=yes;;
+		v) VERBOSE=1;;
+	esac
+done
+
+cleanup
+setup
+sleep 2
+
+cpus=$(cat  /sys/devices/system/cpu/online)
+cpus="$(seq ${cpus/-/ })"
+ret=0
+for i in 1 2 3
+do
+	# generate a cached route per-cpu
+	for c in ${cpus}; do
+		run_cmd taskset -c ${c} ip netns exec h0 ping -c1 -w1 172.16.10${i}.1
+		[ $? -ne 0 ] && printf "\nERROR: ping to h${i} failed\n" && ret=1
+
+		run_cmd taskset -c ${c} ip netns exec h0 ping6 -c1 -w1 2001:db8:10${i}::1
+		[ $? -ne 0 ] && printf "\nERROR: ping6 to h${i} failed\n" && ret=1
+
+		[ $ret -ne 0 ] && break
+	done
+	[ $ret -ne 0 ] && break
+done
+
+if [ $ret -eq 0 ]; then
+	# generate different exceptions in h0 for h1, h2 and h3
+	change_mtu 1 1300
+	validate_v4_exception 1 1300 1350
+	validate_v6_exception 1 1300 1350
+	echo
+
+	change_mtu 2 1350
+	validate_v4_exception 2 1350 1400
+	validate_v6_exception 2 1350 1400
+	echo
+
+	change_mtu 3 1400
+	validate_v4_exception 3 1400 1450
+	validate_v6_exception 3 1400 1450
+	echo
+
+	validate_v4_exception 1 1300 0
+	validate_v6_exception 1 1300 0
+	echo
+
+	validate_v4_exception 2 1350 0
+	validate_v6_exception 2 1350 0
+	echo
+
+	validate_v4_exception 3 1400 0
+	validate_v6_exception 3 1400 0
+
+	# targeted deletes to trigger cleanup paths in kernel
+	ip -netns h0 ro del 172.16.102.0/24 nhid 4
+	ip -netns h0 -6 ro del 2001:db8:102::/64 nhid 6
+
+	ip -netns h0 nexthop del id 4
+	ip -netns h0 nexthop del id 6
+fi
+
+cleanup

tools/testing/selftests/net/forwarding/router_mpath_nh.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="ping_ipv4 ping_ipv6 multipath_test"
+NUM_NETIFS=8
+source lib.sh
+
+h1_create()
+{
+	vrf_create "vrf-h1"
+	ip link set dev $h1 master vrf-h1
+
+	ip link set dev vrf-h1 up
+	ip link set dev $h1 up
+
+	ip address add 192.0.2.2/24 dev $h1
+	ip address add 2001:db8:1::2/64 dev $h1
+
+	ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+	ip route add 2001:db8:2::/64 vrf vrf-h1 nexthop via 2001:db8:1::1
+}
+
+h1_destroy()
+{
+	ip route del 2001:db8:2::/64 vrf vrf-h1
+	ip route del 198.51.100.0/24 vrf vrf-h1
+
+	ip address del 2001:db8:1::2/64 dev $h1
+	ip address del 192.0.2.2/24 dev $h1
+
+	ip link set dev $h1 down
+	vrf_destroy "vrf-h1"
+}
+
+h2_create()
+{
+	vrf_create "vrf-h2"
+	ip link set dev $h2 master vrf-h2
+
+	ip link set dev vrf-h2 up
+	ip link set dev $h2 up
+
+	ip address add 198.51.100.2/24 dev $h2
+	ip address add 2001:db8:2::2/64 dev $h2
+
+	ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+	ip route add 2001:db8:1::/64 vrf vrf-h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip route del 2001:db8:1::/64 vrf vrf-h2
+	ip route del 192.0.2.0/24 vrf vrf-h2
+
+	ip address del 2001:db8:2::2/64 dev $h2
+	ip address del 198.51.100.2/24 dev $h2
+
+	ip link set dev $h2 down
+	vrf_destroy "vrf-h2"
+}
+
+router1_create()
+{
+	vrf_create "vrf-r1"
+	ip link set dev $rp11 master vrf-r1
+	ip link set dev $rp12 master vrf-r1
+	ip link set dev $rp13 master vrf-r1
+
+	ip link set dev vrf-r1 up
+	ip link set dev $rp11 up
+	ip link set dev $rp12 up
+	ip link set dev $rp13 up
+
+	ip address add 192.0.2.1/24 dev $rp11
+	ip address add 2001:db8:1::1/64 dev $rp11
+
+	ip address add 169.254.2.12/24 dev $rp12
+	ip address add fe80:2::12/64 dev $rp12
+
+	ip address add 169.254.3.13/24 dev $rp13
+	ip address add fe80:3::13/64 dev $rp13
+}
+
+router1_destroy()
+{
+	ip route del 2001:db8:2::/64 vrf vrf-r1
+	ip route del 198.51.100.0/24 vrf vrf-r1
+
+	ip address del fe80:3::13/64 dev $rp13
+	ip address del 169.254.3.13/24 dev $rp13
+
+	ip address del fe80:2::12/64 dev $rp12
+	ip address del 169.254.2.12/24 dev $rp12
+
+	ip address del 2001:db8:1::1/64 dev $rp11
+	ip address del 192.0.2.1/24 dev $rp11
+
+	ip nexthop del id 103
+	ip nexthop del id 101
+	ip nexthop del id 102
+	ip nexthop del id 106
+	ip nexthop del id 104
+	ip nexthop del id 105
+
+	ip link set dev $rp13 down
+	ip link set dev $rp12 down
+	ip link set dev $rp11 down
+
+	vrf_destroy "vrf-r1"
+}
+
+router2_create()
+{
+	vrf_create "vrf-r2"
+	ip link set dev $rp21 master vrf-r2
+	ip link set dev $rp22 master vrf-r2
+	ip link set dev $rp23 master vrf-r2
+
+	ip link set dev vrf-r2 up
+	ip link set dev $rp21 up
+	ip link set dev $rp22 up
+	ip link set dev $rp23 up
+
+	ip address add 198.51.100.1/24 dev $rp21
+	ip address add 2001:db8:2::1/64 dev $rp21
+
+	ip address add 169.254.2.22/24 dev $rp22
+	ip address add fe80:2::22/64 dev $rp22
+
+	ip address add 169.254.3.23/24 dev $rp23
+	ip address add fe80:3::23/64 dev $rp23
+}
+
+router2_destroy()
+{
+	ip route del 2001:db8:1::/64 vrf vrf-r2
+	ip route del 192.0.2.0/24 vrf vrf-r2
+
+	ip address del fe80:3::23/64 dev $rp23
+	ip address del 169.254.3.23/24 dev $rp23
+
+	ip address del fe80:2::22/64 dev $rp22
+	ip address del 169.254.2.22/24 dev $rp22
+
+	ip address del 2001:db8:2::1/64 dev $rp21
+	ip address del 198.51.100.1/24 dev $rp21
+
+	ip nexthop del id 201
+	ip nexthop del id 202
+	ip nexthop del id 204
+	ip nexthop del id 205
+
+	ip link set dev $rp23 down
+	ip link set dev $rp22 down
+	ip link set dev $rp21 down
+
+	vrf_destroy "vrf-r2"
+}
+
+routing_nh_obj()
+{
+	ip nexthop add id 101 via 169.254.2.22 dev $rp12
+	ip nexthop add id 102 via 169.254.3.23 dev $rp13
+	ip nexthop add id 103 group 101/102
+	ip route add 198.51.100.0/24 vrf vrf-r1 nhid 103
+
+	ip nexthop add id 104 via fe80:2::22 dev $rp12
+	ip nexthop add id 105 via fe80:3::23 dev $rp13
+	ip nexthop add id 106 group 104/105
+	ip route add 2001:db8:2::/64 vrf vrf-r1 nhid 106
+
+	ip nexthop add id 201 via 169.254.2.12 dev $rp22
+	ip nexthop add id 202 via 169.254.3.13 dev $rp23
+	ip nexthop add id 203 group 201/202
+	ip route add 192.0.2.0/24 vrf vrf-r2 nhid 203
+
+	ip nexthop add id 204 via fe80:2::12 dev $rp22
+	ip nexthop add id 205 via fe80:3::13 dev $rp23
+	ip nexthop add id 206 group 204/205
+	ip route add 2001:db8:1::/64 vrf vrf-r2 nhid 206
+}
+
+multipath4_test()
+{
+	local desc="$1"
+	local weight_rp12=$2
+	local weight_rp13=$3
+	local t0_rp12 t0_rp13 t1_rp12 t1_rp13
+	local packets_rp12 packets_rp13
+
+	# Transmit multiple flows from h1 to h2 and make sure they are
+	# distributed between both multipath links (rp12 and rp13)
+	# according to the configured weights.
+	sysctl_set net.ipv4.fib_multipath_hash_policy 1
+	ip nexthop replace id 103 group 101,$weight_rp12/102,$weight_rp13
+
+	t0_rp12=$(link_stats_tx_packets_get $rp12)
+	t0_rp13=$(link_stats_tx_packets_get $rp13)
+
+	ip vrf exec vrf-h1 $MZ -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
+		-d 1msec -t udp "sp=1024,dp=0-32768"
+
+	t1_rp12=$(link_stats_tx_packets_get $rp12)
+	t1_rp13=$(link_stats_tx_packets_get $rp13)
+
+	let "packets_rp12 = $t1_rp12 - $t0_rp12"
+	let "packets_rp13 = $t1_rp13 - $t0_rp13"
+	multipath_eval "$desc" $weight_rp12 $weight_rp13 $packets_rp12 $packets_rp13
+
+	# Restore settings.
+	ip nexthop replace id 103 group 101/102
+	sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+multipath6_l4_test()
+{
+	local desc="$1"
+	local weight_rp12=$2
+	local weight_rp13=$3
+	local t0_rp12 t0_rp13 t1_rp12 t1_rp13
+	local packets_rp12 packets_rp13
+
+	# Transmit multiple flows from h1 to h2 and make sure they are
+	# distributed between both multipath links (rp12 and rp13)
+	# according to the configured weights.
+	sysctl_set net.ipv6.fib_multipath_hash_policy 1
+
+	ip nexthop replace id 106 group 104,$weight_rp12/105,$weight_rp13
+
+	t0_rp12=$(link_stats_tx_packets_get $rp12)
+	t0_rp13=$(link_stats_tx_packets_get $rp13)
+
+	$MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+		-d 1msec -t udp "sp=1024,dp=0-32768"
+
+	t1_rp12=$(link_stats_tx_packets_get $rp12)
+	t1_rp13=$(link_stats_tx_packets_get $rp13)
+
+	let "packets_rp12 = $t1_rp12 - $t0_rp12"
+	let "packets_rp13 = $t1_rp13 - $t0_rp13"
+	multipath_eval "$desc" $weight_rp12 $weight_rp13 $packets_rp12 $packets_rp13
+
+	ip nexthop replace id 106 group 104/105
+
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+multipath6_test()
+{
+	local desc="$1"
+	local weight_rp12=$2
+	local weight_rp13=$3
+	local t0_rp12 t0_rp13 t1_rp12 t1_rp13
+	local packets_rp12 packets_rp13
+
+	ip nexthop replace id 106 group 104,$weight_rp12/105,$weight_rp13
+
+	t0_rp12=$(link_stats_tx_packets_get $rp12)
+	t0_rp13=$(link_stats_tx_packets_get $rp13)
+
+	# Generate 16384 echo requests, each with a random flow label.
+	for _ in $(seq 1 16384); do
+		ip vrf exec vrf-h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1
+	done
+
+	t1_rp12=$(link_stats_tx_packets_get $rp12)
+	t1_rp13=$(link_stats_tx_packets_get $rp13)
+
+	let "packets_rp12 = $t1_rp12 - $t0_rp12"
+	let "packets_rp13 = $t1_rp13 - $t0_rp13"
+	multipath_eval "$desc" $weight_rp12 $weight_rp13 $packets_rp12 $packets_rp13
+
+	ip nexthop replace id 106 group 104/105
+}
+
+multipath_test()
+{
+	log_info "Running IPv4 multipath tests"
+	multipath4_test "ECMP" 1 1
+	multipath4_test "Weighted MP 2:1" 2 1
+	multipath4_test "Weighted MP 11:45" 11 45
+
+	log_info "Running IPv6 multipath tests"
+	multipath6_test "ECMP" 1 1
+	multipath6_test "Weighted MP 2:1" 2 1
+	multipath6_test "Weighted MP 11:45" 11 45
+
+	log_info "Running IPv6 L4 hash multipath tests"
+	multipath6_l4_test "ECMP" 1 1
+	multipath6_l4_test "Weighted MP 2:1" 2 1
+	multipath6_l4_test "Weighted MP 11:45" 11 45
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp11=${NETIFS[p2]}
+
+	rp12=${NETIFS[p3]}
+	rp22=${NETIFS[p4]}
+
+	rp13=${NETIFS[p5]}
+	rp23=${NETIFS[p6]}
+
+	rp21=${NETIFS[p7]}
+	h2=${NETIFS[p8]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router1_create
+	router2_create
+	routing_nh_obj
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router2_destroy
+	router1_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 198.51.100.2
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+ip nexthop ls >/dev/null 2>&1
+if [ $? -ne 0 ]; then
+	echo "Nexthop objects not supported; skipping tests"
+	exit 0
+fi
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+routing_nh_obj
+
+tests_run
+
+exit $EXIT_STATUS

tools/testing/selftests/net/icmp_redirect.sh

@@ -331,6 +331,38 @@ run_ping()
 	run_cmd ip netns exec h1 ${ping6} -q -M want -i 0.5 -c 10 -w 2 -s ${sz} ${H1_PING_ARG} ${H2_N2_IP6}
 }
 
+replace_route_new()
+{
+	# r1 to h2 via r2 and eth0
+	run_cmd ip -netns r1 nexthop replace id 1 via ${R2_N1_IP} dev eth0
+	run_cmd ip -netns r1 nexthop replace id 2 via ${R2_LLADDR} dev eth0
+}
+
+reset_route_new()
+{
+	run_cmd ip -netns r1 nexthop flush
+	run_cmd ip -netns h1 nexthop flush
+
+	initial_route_new
+}
+
+initial_route_new()
+{
+	# r1 to h2 via r2 and eth1
+	run_cmd ip -netns r1 nexthop add id 1 via ${R2_R1_N1_IP} dev eth1
+	run_cmd ip -netns r1 ro add ${H2_N2} nhid 1
+
+	run_cmd ip -netns r1 nexthop add id 2 via ${R2_R1_N1_IP6} dev eth1
+	run_cmd ip -netns r1 -6 ro add ${H2_N2_6} nhid 2
+
+	# h1 to h2 via r1
+	run_cmd ip -netns h1 nexthop add id 1 via ${R1_N1_IP} dev br0
+	run_cmd ip -netns h1 ro add ${H1_VRF_ARG} ${H2_N2} nhid 1
+
+	run_cmd ip -netns h1 nexthop add id 2 via ${R1_LLADDR} dev br0
+	run_cmd ip -netns h1 -6 ro add ${H1_VRF_ARG} ${H2_N2_6} nhid 2
+}
+
 replace_route_legacy()
 {
 	# r1 to h2 via r2 and eth0
@@ -479,6 +511,23 @@ WITH_VRF=yes
 setup
 do_test "legacy"
 
+cleanup
+log_section "Routing with nexthop objects"
+ip nexthop ls >/dev/null 2>&1
+if [ $? -eq 0 ]; then
+	WITH_VRF=no
+	setup
+	do_test "new"
+
+	cleanup
+	log_section "Routing with nexthop objects and VRF"
+	WITH_VRF=yes
+	setup
+	do_test "new"
+else
+	echo "Nexthop objects not supported; skipping tests"
+fi
+
 printf "\nTests passed: %3d\n" ${nsuccess}
 printf "Tests failed: %3d\n"   ${nfail}
 

tools/testing/selftests/net/pmtu.sh

@@ -123,34 +123,35 @@ TRACING=0
 # Some systems don't have a ping6 binary anymore
 which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 
+#               Name                          Description                  re-run with nh
 tests="
-	pmtu_ipv4_exception		ipv4: PMTU exceptions
-	pmtu_ipv6_exception		ipv6: PMTU exceptions
-	pmtu_ipv4_vxlan4_exception	IPv4 over vxlan4: PMTU exceptions
-	pmtu_ipv6_vxlan4_exception	IPv6 over vxlan4: PMTU exceptions
-	pmtu_ipv4_vxlan6_exception	IPv4 over vxlan6: PMTU exceptions
-	pmtu_ipv6_vxlan6_exception	IPv6 over vxlan6: PMTU exceptions
-	pmtu_ipv4_geneve4_exception	IPv4 over geneve4: PMTU exceptions
-	pmtu_ipv6_geneve4_exception	IPv6 over geneve4: PMTU exceptions
-	pmtu_ipv4_geneve6_exception	IPv4 over geneve6: PMTU exceptions
-	pmtu_ipv6_geneve6_exception	IPv6 over geneve6: PMTU exceptions
-	pmtu_ipv4_fou4_exception	IPv4 over fou4: PMTU exceptions
-	pmtu_ipv6_fou4_exception	IPv6 over fou4: PMTU exceptions
-	pmtu_ipv4_fou6_exception	IPv4 over fou6: PMTU exceptions
-	pmtu_ipv6_fou6_exception	IPv6 over fou6: PMTU exceptions
-	pmtu_ipv4_gue4_exception	IPv4 over gue4: PMTU exceptions
-	pmtu_ipv6_gue4_exception	IPv6 over gue4: PMTU exceptions
-	pmtu_ipv4_gue6_exception	IPv4 over gue6: PMTU exceptions
-	pmtu_ipv6_gue6_exception	IPv6 over gue6: PMTU exceptions
-	pmtu_vti6_exception		vti6: PMTU exceptions
-	pmtu_vti4_exception		vti4: PMTU exceptions
-	pmtu_vti4_default_mtu		vti4: default MTU assignment
-	pmtu_vti6_default_mtu		vti6: default MTU assignment
-	pmtu_vti4_link_add_mtu		vti4: MTU setting on link creation
-	pmtu_vti6_link_add_mtu		vti6: MTU setting on link creation
-	pmtu_vti6_link_change_mtu	vti6: MTU changes on link changes
-	cleanup_ipv4_exception		ipv4: cleanup of cached exceptions
-	cleanup_ipv6_exception		ipv6: cleanup of cached exceptions"
+	pmtu_ipv4_exception		ipv4: PMTU exceptions			1
+	pmtu_ipv6_exception		ipv6: PMTU exceptions			1
+	pmtu_ipv4_vxlan4_exception	IPv4 over vxlan4: PMTU exceptions	1
+	pmtu_ipv6_vxlan4_exception	IPv6 over vxlan4: PMTU exceptions	1
+	pmtu_ipv4_vxlan6_exception	IPv4 over vxlan6: PMTU exceptions	1
+	pmtu_ipv6_vxlan6_exception	IPv6 over vxlan6: PMTU exceptions	1
+	pmtu_ipv4_geneve4_exception	IPv4 over geneve4: PMTU exceptions	1
+	pmtu_ipv6_geneve4_exception	IPv6 over geneve4: PMTU exceptions	1
+	pmtu_ipv4_geneve6_exception	IPv4 over geneve6: PMTU exceptions	1
+	pmtu_ipv6_geneve6_exception	IPv6 over geneve6: PMTU exceptions	1
+	pmtu_ipv4_fou4_exception	IPv4 over fou4: PMTU exceptions		1
+	pmtu_ipv6_fou4_exception	IPv6 over fou4: PMTU exceptions		1
+	pmtu_ipv4_fou6_exception	IPv4 over fou6: PMTU exceptions		1
+	pmtu_ipv6_fou6_exception	IPv6 over fou6: PMTU exceptions		1
+	pmtu_ipv4_gue4_exception	IPv4 over gue4: PMTU exceptions		1
+	pmtu_ipv6_gue4_exception	IPv6 over gue4: PMTU exceptions		1
+	pmtu_ipv4_gue6_exception	IPv4 over gue6: PMTU exceptions		1
+	pmtu_ipv6_gue6_exception	IPv6 over gue6: PMTU exceptions		1
+	pmtu_vti6_exception		vti6: PMTU exceptions			0
+	pmtu_vti4_exception		vti4: PMTU exceptions			0
+	pmtu_vti4_default_mtu		vti4: default MTU assignment		0
+	pmtu_vti6_default_mtu		vti6: default MTU assignment		0
+	pmtu_vti4_link_add_mtu		vti4: MTU setting on link creation	0
+	pmtu_vti6_link_add_mtu		vti6: MTU setting on link creation	0
+	pmtu_vti6_link_change_mtu	vti6: MTU changes on link changes	0
+	cleanup_ipv4_exception		ipv4: cleanup of cached exceptions	1
+	cleanup_ipv6_exception		ipv6: cleanup of cached exceptions	1"
 
 NS_A="ns-A"
 NS_B="ns-B"
@@ -194,6 +195,30 @@ routes="
 	B	default			${prefix6}:${b_r1}::2
 "
 
+USE_NH="no"
+#	ns	family	nh id	   destination		gateway
+nexthops="
+	A	4	41	${prefix4}.${a_r1}.2	veth_A-R1
+	A	4	42	${prefix4}.${a_r2}.2	veth_A-R2
+	B	4	41	${prefix4}.${b_r1}.2	veth_B-R1
+
+	A	6	61	${prefix6}:${a_r1}::2	veth_A-R1
+	A	6	62	${prefix6}:${a_r2}::2	veth_A-R2
+	B	6	61	${prefix6}:${b_r1}::2	veth_B-R1
+"
+
+# nexthop id correlates to id in nexthops config above
+#	ns    family	prefix			nh id
+routes_nh="
+	A	4	default			41
+	A	4	${prefix4}.${b_r2}.1	42
+	B	4	default			41
+
+	A	6	default			61
+	A	6	${prefix6}:${b_r2}::1	62
+	B	6	default			61
+"
+
 veth4_a_addr="192.168.1.1"
 veth4_b_addr="192.168.1.2"
 veth4_mask="24"
@@ -448,6 +473,50 @@ setup_xfrm6() {
 	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
 }
 
+setup_routing_old() {
+	for i in ${routes}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${addr}" = "" ]	&& addr="${i}"		&& continue
+		[ "${gw}" = "" ]	&& gw="${i}"
+
+		ns_name="$(nsname ${ns})"
+
+		ip -n ${ns_name} route add ${addr} via ${gw}
+
+		ns=""; addr=""; gw=""
+	done
+}
+
+setup_routing_new() {
+	for i in ${nexthops}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${fam}" = "" ]	&& fam="${i}"		&& continue
+		[ "${nhid}" = "" ]	&& nhid="${i}"		&& continue
+		[ "${gw}" = "" ]	&& gw="${i}"		&& continue
+		[ "${dev}" = "" ]	&& dev="${i}"
+
+		ns_name="$(nsname ${ns})"
+
+		ip -n ${ns_name} -${fam} nexthop add id ${nhid} via ${gw} dev ${dev}
+
+		ns=""; fam=""; nhid=""; gw=""; dev=""
+
+	done
+
+	for i in ${routes_nh}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${fam}" = "" ]	&& fam="${i}"		&& continue
+		[ "${addr}" = "" ]	&& addr="${i}"		&& continue
+		[ "${nhid}" = "" ]	&& nhid="${i}"
+
+		ns_name="$(nsname ${ns})"
+
+		ip -n ${ns_name} -${fam} route add ${addr} nhid ${nhid}
+
+		ns=""; fam=""; addr=""; nhid=""
+	done
+}
+
 setup_routing() {
 	for i in ${NS_R1} ${NS_R2}; do
 		ip netns exec ${i} sysctl -q net/ipv4/ip_forward=1
@@ -478,17 +547,13 @@ setup_routing() {
 		ns=""; peer=""; segment=""
 	done
 
-	for i in ${routes}; do
-		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
-		[ "${addr}" = "" ]	&& addr="${i}"		&& continue
-		[ "${gw}" = "" ]	&& gw="${i}"
-
-		ns_name="$(nsname ${ns})"
-
-		ip -n ${ns_name} route add ${addr} via ${gw}
+	if [ "$USE_NH" = "yes" ]; then
+		setup_routing_new
+	else
+		setup_routing_old
+	fi
 
-		ns=""; addr=""; gw=""
-	done
+	return 0
 }
 
 setup() {
@@ -1090,6 +1155,53 @@ test_cleanup_ipv4_exception() {
 	test_cleanup_vxlanX_exception 4
 }
 
+run_test() {
+	(
+	tname="$1"
+	tdesc="$2"
+
+	unset IFS
+
+	if [ "$VERBOSE" = "1" ]; then
+		printf "\n##########################################################################\n\n"
+	fi
+
+	eval test_${tname}
+	ret=$?
+
+	if [ $ret -eq 0 ]; then
+		printf "TEST: %-60s  [ OK ]\n" "${tdesc}"
+	elif [ $ret -eq 1 ]; then
+		printf "TEST: %-60s  [FAIL]\n" "${tdesc}"
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+			echo
+			echo "Pausing. Hit enter to continue"
+			read a
+		fi
+		err_flush
+		exit 1
+	elif [ $ret -eq 2 ]; then
+		printf "TEST: %-60s  [SKIP]\n" "${tdesc}"
+		err_flush
+	fi
+
+	return $ret
+	)
+	ret=$?
+	[ $ret -ne 0 ] && exitcode=1
+
+	return $ret
+}
+
+run_test_nh() {
+	tname="$1"
+	tdesc="$2"
+
+	USE_NH=yes
+	run_test "${tname}" "${tdesc} - nexthop objects"
+	USE_NH=no
+}
+
 usage() {
 	echo
 	echo "$0 [OPTIONS] [TEST]..."
@@ -1136,8 +1248,20 @@ trap cleanup EXIT
 # start clean
 cleanup
 
+HAVE_NH=no
+ip nexthop ls >/dev/null 2>&1
+[ $? -eq 0 ] && HAVE_NH=yes
+
+name=""
+desc=""
+rerun_nh=0
 for t in ${tests}; do
-	[ $desc -eq 0 ] && name="${t}" && desc=1 && continue || desc=0
+	[ "${name}" = "" ]	&& name="${t}"	&& continue
+	[ "${desc}" = "" ]	&& desc="${t}"	&& continue
+
+	if [ "${HAVE_NH}" = "yes" ]; then
+		rerun_nh="${t}"
+	fi
 
 	run_this=1
 	for arg do
@@ -1145,35 +1269,18 @@ for t in ${tests}; do
 		[ "${arg}" = "${name}" ] && run_this=1 && break
 		run_this=0
 	done
-	[ $run_this -eq 0 ] && continue
-
-	(
-		unset IFS
+	if [ $run_this -eq 1 ]; then
+		run_test "${name}" "${desc}"
+		# if test was skipped no need to retry with nexthop objects
+		[ $? -eq 2 ] && rerun_nh=0
 
-		if [ "$VERBOSE" = "1" ]; then
-			printf "\n##########################################################################\n\n"
+		if [ "${rerun_nh}" = "1" ]; then
+			run_test_nh "${name}" "${desc}"
 		fi
-
-		eval test_${name}
-		ret=$?
-
-		if [ $ret -eq 0 ]; then
-			printf "TEST: %-60s  [ OK ]\n" "${t}"
-		elif [ $ret -eq 1 ]; then
-			printf "TEST: %-60s  [FAIL]\n" "${t}"
-			if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
-				echo
-				echo "Pausing. Hit enter to continue"
-				read a
-			fi
-			err_flush
-			exit 1
-		elif [ $ret -eq 2 ]; then
-			printf "TEST: %-60s  [SKIP]\n" "${t}"
-			err_flush
-		fi
-	)
-	[ $? -ne 0 ] && exitcode=1
+	fi
+	name=""
+	desc=""
+	rerun_nh=0
 done
 
 exit ${exitcode}