Merge branch 'mlxsw-add-support-for-nexthop-objects'

Ido Schimmel says:

====================
mlxsw: Add support for nexthop objects

This patch set adds support for nexthop objects in mlxsw. Nexthop
objects are treated as another front-end for programming nexthops, in
addition to the existing IPv4 and IPv6 front-ends.

Patch #1 registers a listener to the nexthop notification chain and
parses the nexthop information into the existing mlxsw data structures
that are already used by the IPv4 and IPv6 front-ends. Blackhole
nexthops are currently rejected. Support will be added in a follow-up
patch set.

Patch #2 extends mlxsw to resolve its internal nexthop objects from the
nexthop identifier encoded in the FIB info of the notified routes.

Patch #3 finally removes the limitation of rejecting routes that use
nexthop objects.

Patch #4 adds a selftest.

Patches #5-#8 add generic forwarding selftests that can be used with
veth pairs or physical loopbacks.
====================

Link: https://lore.kernel.org/r/20201119130848.407918-1-idosch@idosch.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 716 insertions, 1 deletions

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index f4031002d5e9..5de47d72f8c9 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -29,6 +29,10 @@ ALL_TESTS="
 	bridge_extern_learn_test
 	neigh_offload_test
 	nexthop_offload_test
+	nexthop_obj_invalid_test
+	nexthop_obj_offload_test
+	nexthop_obj_group_offload_test
+	nexthop_obj_route_offload_test
 	devlink_reload_test
 "
 NUM_NETIFS=2
@@ -674,6 +678,191 @@ nexthop_offload_test()
 	sysctl_restore net.ipv6.conf.$swp2.keep_addr_on_down
 }
 
+nexthop_obj_invalid_test()
+{
+	# Test that invalid nexthop object configurations are rejected
+	RET=0
+
+	simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+	simple_if_init $swp2 192.0.2.2/24 2001:db8:1::2/64
+	setup_wait
+
+	ip nexthop add id 1 via 192.0.2.3 fdb
+	check_fail $? "managed to configure an FDB nexthop when should not"
+
+	ip nexthop add id 1 encap mpls 200/300 via 192.0.2.3 dev $swp1
+	check_fail $? "managed to configure a nexthop with MPLS encap when should not"
+
+	ip nexthop add id 1 blackhole
+	check_fail $? "managed to configure a blackhole nexthop when should not"
+
+	ip nexthop add id 1 dev $swp1
+	ip nexthop add id 2 dev $swp1
+	ip nexthop add id 10 group 1/2
+	check_fail $? "managed to configure a nexthop group with device-only nexthops when should not"
+
+	log_test "nexthop objects - invalid configurations"
+
+	ip nexthop del id 2
+	ip nexthop del id 1
+
+	simple_if_fini $swp2 192.0.2.2/24 2001:db8:1::2/64
+	simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+nexthop_obj_offload_test()
+{
+	# Test offload indication of nexthop objects
+	RET=0
+
+	simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+	simple_if_init $swp2
+	setup_wait
+
+	ip nexthop add id 1 via 192.0.2.2 dev $swp1
+	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop show id 1
+	check_err $? "nexthop not marked as offloaded when should"
+
+	ip neigh replace 192.0.2.2 nud failed dev $swp1
+	busywait "$TIMEOUT" not wait_for_offload \
+		ip nexthop show id 1
+	check_err $? "nexthop marked as offloaded after setting neigh to failed state"
+
+	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop show id 1
+	check_err $? "nexthop not marked as offloaded after neigh replace"
+
+	ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+	busywait "$TIMEOUT" not wait_for_offload \
+		ip nexthop show id 1
+	check_err $? "nexthop marked as offloaded after replacing to use an invalid address"
+
+	ip nexthop replace id 1 via 192.0.2.2 dev $swp1
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop show id 1
+	check_err $? "nexthop not marked as offloaded after replacing to use a valid address"
+
+	log_test "nexthop objects offload indication"
+
+	ip neigh del 192.0.2.2 dev $swp1
+	ip nexthop del id 1
+
+	simple_if_fini $swp2
+	simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+nexthop_obj_group_offload_test()
+{
+	# Test offload indication of nexthop group objects
+	RET=0
+
+	simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+	simple_if_init $swp2
+	setup_wait
+
+	ip nexthop add id 1 via 192.0.2.2 dev $swp1
+	ip nexthop add id 2 via 2001:db8:1::2 dev $swp1
+	ip nexthop add id 10 group 1/2
+	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+	ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop show id 1
+	check_err $? "IPv4 nexthop not marked as offloaded when should"
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop show id 2
+	check_err $? "IPv6 nexthop not marked as offloaded when should"
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop show id 10
+	check_err $? "nexthop group not marked as offloaded when should"
+
+	# Invalidate nexthop id 1
+	ip neigh replace 192.0.2.2 nud failed dev $swp1
+	busywait "$TIMEOUT" not wait_for_offload \
+		ip nexthop show id 10
+	check_fail $? "nexthop group not marked as offloaded with one valid nexthop"
+
+	# Invalidate nexthop id 2
+	ip neigh replace 2001:db8:1::2 nud failed dev $swp1
+	busywait "$TIMEOUT" not wait_for_offload \
+		ip nexthop show id 10
+	check_err $? "nexthop group marked as offloaded when should not"
+
+	# Revalidate nexthop id 1
+	ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop show id 10
+	check_err $? "nexthop group not marked as offloaded after revalidating nexthop"
+
+	log_test "nexthop group objects offload indication"
+
+	ip neigh del 2001:db8:1::2 dev $swp1
+	ip neigh del 192.0.2.3 dev $swp1
+	ip neigh del 192.0.2.2 dev $swp1
+	ip nexthop del id 10
+	ip nexthop del id 2
+	ip nexthop del id 1
+
+	simple_if_fini $swp2
+	simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+nexthop_obj_route_offload_test()
+{
+	# Test offload indication of routes using nexthop objects
+	RET=0
+
+	simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+	simple_if_init $swp2
+	setup_wait
+
+	ip nexthop add id 1 via 192.0.2.2 dev $swp1
+	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+
+	ip route replace 198.51.100.0/24 nhid 1
+	busywait "$TIMEOUT" wait_for_offload \
+		ip route show 198.51.100.0/24
+	check_err $? "route not marked as offloaded when using valid nexthop"
+
+	ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+	busywait "$TIMEOUT" wait_for_offload \
+		ip route show 198.51.100.0/24
+	check_err $? "route not marked as offloaded after replacing valid nexthop with a valid one"
+
+	ip nexthop replace id 1 via 192.0.2.4 dev $swp1
+	busywait "$TIMEOUT" not wait_for_offload \
+		ip route show 198.51.100.0/24
+	check_err $? "route marked as offloaded after replacing valid nexthop with an invalid one"
+
+	ip nexthop replace id 1 via 192.0.2.2 dev $swp1
+	busywait "$TIMEOUT" wait_for_offload \
+		ip route show 198.51.100.0/24
+	check_err $? "route not marked as offloaded after replacing invalid nexthop with a valid one"
+
+	log_test "routes using nexthop objects offload indication"
+
+	ip route del 198.51.100.0/24
+	ip neigh del 192.0.2.3 dev $swp1
+	ip neigh del 192.0.2.2 dev $swp1
+	ip nexthop del id 1
+
+	simple_if_fini $swp2
+	simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
 devlink_reload_test()
 {
 	# Test that after executing all the above configuration tests, a
diff --git a/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh b/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh
new file mode 100755
index 000000000000..d03aa2cab9fd
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh
@@ -0,0 +1,356 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test traffic distribution when a wECMP route forwards traffic to two GRE
+# tunnels.
+#
+# +-------------------------+
+# | H1                      |
+# |               $h1 +     |
+# |      192.0.2.1/28 |     |
+# |  2001:db8:1::1/64 |     |
+# +-------------------|-----+
+#                     |
+# +-------------------|------------------------+
+# | SW1               |                        |
+# |              $ol1 +                        |
+# |      192.0.2.2/28                          |
+# |  2001:db8:1::2/64                          |
+# |                                            |
+# |  + g1a (gre)          + g1b (gre)          |
+# |    loc=192.0.2.65       loc=192.0.2.81     |
+# |    rem=192.0.2.66 --.   rem=192.0.2.82 --. |
+# |    tos=inherit      |   tos=inherit      | |
+# |  .------------------'                    | |
+# |  |                    .------------------' |
+# |  v                    v                    |
+# |  + $ul1.111 (vlan)    + $ul1.222 (vlan)    |
+# |  | 192.0.2.129/28     | 192.0.2.145/28     |
+# |   \                  /                     |
+# |    \________________/                      |
+# |            |                               |
+# |            + $ul1                          |
+# +------------|-------------------------------+
+#              |
+# +------------|-------------------------------+
+# | SW2        + $ul2                          |
+# |     _______|________                       |
+# |    /                \                      |
+# |   /                  \                     |
+# |  + $ul2.111 (vlan)    + $ul2.222 (vlan)    |
+# |  ^ 192.0.2.130/28     ^ 192.0.2.146/28     |
+# |  |                    |                    |
+# |  |                    '------------------. |
+# |  '------------------.                    | |
+# |  + g2a (gre)        | + g2b (gre)        | |
+# |    loc=192.0.2.66   |   loc=192.0.2.82   | |
+# |    rem=192.0.2.65 --'   rem=192.0.2.81 --' |
+# |    tos=inherit          tos=inherit        |
+# |                                            |
+# |              $ol2 +                        |
+# |     192.0.2.17/28 |                        |
+# |  2001:db8:2::1/64 |                        |
+# +-------------------|------------------------+
+#                     |
+# +-------------------|-----+
+# | H2                |     |
+# |               $h2 +     |
+# |     192.0.2.18/28       |
+# |  2001:db8:2::2/64       |
+# +-------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	multipath_ipv4
+	multipath_ipv6
+	multipath_ipv6_l4
+"
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+	ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
+	ip route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+	ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+sw1_create()
+{
+	simple_if_init $ol1 192.0.2.2/28 2001:db8:1::2/64
+	__simple_if_init $ul1 v$ol1
+	vlan_create $ul1 111 v$ol1 192.0.2.129/28
+	vlan_create $ul1 222 v$ol1 192.0.2.145/28
+
+	tunnel_create g1a gre 192.0.2.65 192.0.2.66 tos inherit dev v$ol1
+	__simple_if_init g1a v$ol1 192.0.2.65/32
+	ip route add vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+
+	tunnel_create g1b gre 192.0.2.81 192.0.2.82 tos inherit dev v$ol1
+	__simple_if_init g1b v$ol1 192.0.2.81/32
+	ip route add vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+
+	ip -6 nexthop add id 101 dev g1a
+	ip -6 nexthop add id 102 dev g1b
+	ip nexthop add id 103 group 101/102
+
+	ip route add vrf v$ol1 192.0.2.16/28 nhid 103
+	ip route add vrf v$ol1 2001:db8:2::/64 nhid 103
+}
+
+sw1_destroy()
+{
+	ip route del vrf v$ol1 2001:db8:2::/64
+	ip route del vrf v$ol1 192.0.2.16/28
+
+	ip nexthop del id 103
+	ip -6 nexthop del id 102
+	ip -6 nexthop del id 101
+
+	ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+	__simple_if_fini g1b 192.0.2.81/32
+	tunnel_destroy g1b
+
+	ip route del vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+	__simple_if_fini g1a 192.0.2.65/32
+	tunnel_destroy g1a
+
+	vlan_destroy $ul1 222
+	vlan_destroy $ul1 111
+	__simple_if_fini $ul1
+	simple_if_fini $ol1 192.0.2.2/28 2001:db8:1::2/64
+}
+
+sw2_create()
+{
+	simple_if_init $ol2 192.0.2.17/28 2001:db8:2::1/64
+	__simple_if_init $ul2 v$ol2
+	vlan_create $ul2 111 v$ol2 192.0.2.130/28
+	vlan_create $ul2 222 v$ol2 192.0.2.146/28
+
+	tunnel_create g2a gre 192.0.2.66 192.0.2.65 tos inherit dev v$ol2
+	__simple_if_init g2a v$ol2 192.0.2.66/32
+	ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+
+	tunnel_create g2b gre 192.0.2.82 192.0.2.81 tos inherit dev v$ol2
+	__simple_if_init g2b v$ol2 192.0.2.82/32
+	ip route add vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+
+	ip -6 nexthop add id 201 dev g2a
+	ip -6 nexthop add id 202 dev g2b
+	ip nexthop add id 203 group 201/202
+
+	ip route add vrf v$ol2 192.0.2.0/28 nhid 203
+	ip route add vrf v$ol2 2001:db8:1::/64 nhid 203
+
+	tc qdisc add dev $ul2 clsact
+	tc filter add dev $ul2 ingress pref 111 prot 802.1Q \
+	   flower vlan_id 111 action pass
+	tc filter add dev $ul2 ingress pref 222 prot 802.1Q \
+	   flower vlan_id 222 action pass
+}
+
+sw2_destroy()
+{
+	tc qdisc del dev $ul2 clsact
+
+	ip route del vrf v$ol2 2001:db8:1::/64
+	ip route del vrf v$ol2 192.0.2.0/28
+
+	ip nexthop del id 203
+	ip -6 nexthop del id 202
+	ip -6 nexthop del id 201
+
+	ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+	__simple_if_fini g2b 192.0.2.82/32
+	tunnel_destroy g2b
+
+	ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+	__simple_if_fini g2a 192.0.2.66/32
+	tunnel_destroy g2a
+
+	vlan_destroy $ul2 222
+	vlan_destroy $ul2 111
+	__simple_if_fini $ul2
+	simple_if_fini $ol2 192.0.2.17/28 2001:db8:2::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.18/28 2001:db8:2::2/64
+	ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
+	ip route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+	ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
+	simple_if_fini $h2 192.0.2.18/28 2001:db8:2::2/64
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	vrf_prepare
+	h1_create
+	sw1_create
+	sw2_create
+	h2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	h2_destroy
+	sw2_destroy
+	sw1_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+multipath4_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv4.fib_multipath_hash_policy 1
+	ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+	local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	ip vrf exec v$h1 \
+	   $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \
+	       -d 1msec -t udp "sp=1024,dp=0-32768"
+
+	local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip nexthop replace id 103 group 101/102
+	sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+multipath6_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv6.fib_multipath_hash_policy 0
+	ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+	local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	# Generate 16384 echo requests, each with a random flow label.
+	for ((i=0; i < 16384; ++i)); do
+		ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null
+	done
+
+	local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip nexthop replace id 103 group 101/102
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+multipath6_l4_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv6.fib_multipath_hash_policy 1
+	ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+	local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	ip vrf exec v$h1 \
+		$MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \
+		-d 1msec -t udp "sp=1024,dp=0-32768"
+
+	local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip nexthop replace id 103 group 101/102
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.18
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+multipath_ipv4()
+{
+	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
+}
+
+multipath_ipv6()
+{
+	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
+}
+
+multipath_ipv6_l4()
+{
+	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
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
index cf3d26c233e8..e8c2573d5232 100755
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
@@ -280,6 +280,17 @@ multipath_test()
 	multipath4_test "Weighted MP 2:1" 2 1
 	multipath4_test "Weighted MP 11:45" 11 45
 
+	log_info "Running IPv4 multipath tests with IPv6 link-local nexthops"
+	ip nexthop replace id 101 via fe80:2::22 dev $rp12
+	ip nexthop replace id 102 via fe80:3::23 dev $rp13
+
+	multipath4_test "ECMP" 1 1
+	multipath4_test "Weighted MP 2:1" 2 1
+	multipath4_test "Weighted MP 11:45" 11 45
+
+	ip nexthop replace id 102 via 169.254.3.23 dev $rp13
+	ip nexthop replace id 101 via 169.254.2.22 dev $rp12
+
 	log_info "Running IPv6 multipath tests"
 	multipath6_test "ECMP" 1 1
 	multipath6_test "Weighted MP 2:1" 2 1
@@ -312,7 +323,6 @@ setup_prepare()
 
 	router1_create
 	router2_create
-	routing_nh_obj
 
 	forwarding_enable
 }
diff --git a/tools/testing/selftests/net/forwarding/router_nh.sh b/tools/testing/selftests/net/forwarding/router_nh.sh
new file mode 100755
index 000000000000..f3a53738bdcc
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_nh.sh
@@ -0,0 +1,160 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+"
+
+NUM_NETIFS=4
+source lib.sh
+source tc_common.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"
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	ip link set dev $rp2 up
+
+	tc qdisc add dev $rp2 clsact
+
+	ip address add 192.0.2.1/24 dev $rp1
+	ip address add 2001:db8:1::1/64 dev $rp1
+
+	ip address add 198.51.100.1/24 dev $rp2
+	ip address add 2001:db8:2::1/64 dev $rp2
+}
+
+router_destroy()
+{
+	ip address del 2001:db8:2::1/64 dev $rp2
+	ip address del 198.51.100.1/24 dev $rp2
+
+	ip address del 2001:db8:1::1/64 dev $rp1
+	ip address del 192.0.2.1/24 dev $rp1
+
+	tc qdisc del dev $rp2 clsact
+
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
+}
+
+routing_nh_obj()
+{
+	# Create the nexthops as AF_INET6, so that IPv4 and IPv6 routes could
+	# use them.
+	ip -6 nexthop add id 101 dev $rp1
+	ip -6 nexthop add id 102 dev $rp2
+
+	ip route replace 192.0.2.0/24 nhid 101
+	ip route replace 2001:db8:1::/64 nhid 101
+	ip route replace 198.51.100.0/24 nhid 102
+	ip route replace 2001:db8:2::/64 nhid 102
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp1mac=$(mac_get $rp1)
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_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
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+routing_nh_obj
+
+tests_run
+
+exit $EXIT_STATUS