Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

10 files changed, 993 insertions, 12 deletions

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 0bd6b23c97ef..a8e04d665b69 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -10,7 +10,7 @@ TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
 TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh
 TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh
-TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh
+TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh traceroute.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
diff --git a/tools/testing/selftests/net/altnames.sh b/tools/testing/selftests/net/altnames.sh
new file mode 100755
index 000000000000..4254ddc3f70b
--- /dev/null
+++ b/tools/testing/selftests/net/altnames.sh
@@ -0,0 +1,75 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/forwarding
+
+ALL_TESTS="altnames_test"
+NUM_NETIFS=0
+source $lib_dir/lib.sh
+
+DUMMY_DEV=dummytest
+SHORT_NAME=shortname
+LONG_NAME=someveryveryveryveryveryverylongname
+
+altnames_test()
+{
+	RET=0
+	local output
+	local name
+
+	ip link property add $DUMMY_DEV altname $SHORT_NAME
+	check_err $? "Failed to add short alternative name"
+
+	output=$(ip -j -p link show $SHORT_NAME)
+	check_err $? "Failed to do link show with short alternative name"
+
+	name=$(echo $output | jq -e -r ".[0].altnames[0]")
+	check_err $? "Failed to get short alternative name from link show JSON"
+
+	[ "$name" == "$SHORT_NAME" ]
+	check_err $? "Got unexpected short alternative name from link show JSON"
+
+	ip -j -p link show $DUMMY_DEV &>/dev/null
+	check_err $? "Failed to do link show with original name"
+
+	ip link property add $DUMMY_DEV altname $LONG_NAME
+	check_err $? "Failed to add long alternative name"
+
+	output=$(ip -j -p link show $LONG_NAME)
+	check_err $? "Failed to do link show with long alternative name"
+
+	name=$(echo $output | jq -e -r ".[0].altnames[1]")
+	check_err $? "Failed to get long alternative name from link show JSON"
+
+	[ "$name" == "$LONG_NAME" ]
+	check_err $? "Got unexpected long alternative name from link show JSON"
+
+	ip link property del $DUMMY_DEV altname $SHORT_NAME
+	check_err $? "Failed to add short alternative name"
+
+	ip -j -p link show $SHORT_NAME &>/dev/null
+	check_fail $? "Unexpected success while trying to do link show with deleted short alternative name"
+
+	# long name is left there on purpose to be removed alongside the device
+
+	log_test "altnames test"
+}
+
+setup_prepare()
+{
+	ip link add name $DUMMY_DEV type dummy
+}
+
+cleanup()
+{
+	pre_cleanup
+	ip link del name $DUMMY_DEV
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 76c1897e6352..6dd403103800 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -9,7 +9,7 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter"
+TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
@@ -1500,6 +1500,55 @@ ipv4_route_metrics_test()
 	route_cleanup
 }
 
+ipv4_del_addr_test()
+{
+	echo
+	echo "IPv4 delete address route tests"
+
+	setup
+
+	set -e
+	$IP li add dummy1 type dummy
+	$IP li set dummy1 up
+	$IP li add dummy2 type dummy
+	$IP li set dummy2 up
+	$IP li add red type vrf table 1111
+	$IP li set red up
+	$IP ro add vrf red unreachable default
+	$IP li set dummy2 vrf red
+
+	$IP addr add dev dummy1 172.16.104.1/24
+	$IP addr add dev dummy1 172.16.104.11/24
+	$IP addr add dev dummy2 172.16.104.1/24
+	$IP addr add dev dummy2 172.16.104.11/24
+	$IP route add 172.16.105.0/24 via 172.16.104.2 src 172.16.104.11
+	$IP route add vrf red 172.16.105.0/24 via 172.16.104.2 src 172.16.104.11
+	set +e
+
+	# removing address from device in vrf should only remove route from vrf table
+	$IP addr del dev dummy2 172.16.104.11/24
+	$IP ro ls vrf red | grep -q 172.16.105.0/24
+	log_test $? 1 "Route removed from VRF when source address deleted"
+
+	$IP ro ls | grep -q 172.16.105.0/24
+	log_test $? 0 "Route in default VRF not removed"
+
+	$IP addr add dev dummy2 172.16.104.11/24
+	$IP route add vrf red 172.16.105.0/24 via 172.16.104.2 src 172.16.104.11
+
+	$IP addr del dev dummy1 172.16.104.11/24
+	$IP ro ls | grep -q 172.16.105.0/24
+	log_test $? 1 "Route removed in default VRF when source address deleted"
+
+	$IP ro ls vrf red | grep -q 172.16.105.0/24
+	log_test $? 0 "Route in VRF is not removed by address delete"
+
+	$IP li del dummy1
+	$IP li del dummy2
+	cleanup
+}
+
+
 ipv4_route_v6_gw_test()
 {
 	local rc
@@ -1633,6 +1682,7 @@ do
 	ipv4_route_test|ipv4_rt)	ipv4_route_test;;
 	ipv6_addr_metric)		ipv6_addr_metric_test;;
 	ipv4_addr_metric)		ipv4_addr_metric_test;;
+	ipv4_del_addr)			ipv4_del_addr_test;;
 	ipv6_route_metrics)		ipv6_route_metrics_test;;
 	ipv4_route_metrics)		ipv4_route_metrics_test;;
 	ipv4_route_v6_gw)		ipv4_route_v6_gw_test;;
diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
index 13d03a6d85ba..40b076983239 100644
--- a/tools/testing/selftests/net/forwarding/devlink_lib.sh
+++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
@@ -355,3 +355,58 @@ devlink_trap_group_stats_idle_test()
 		return 1
 	fi
 }
+
+devlink_trap_exception_test()
+{
+	local trap_name=$1; shift
+	local group_name=$1; shift
+
+	devlink_trap_stats_idle_test $trap_name
+	check_fail $? "Trap stats idle when packets should have been trapped"
+
+	devlink_trap_group_stats_idle_test $group_name
+	check_fail $? "Trap group idle when packets should have been trapped"
+}
+
+devlink_trap_drop_test()
+{
+	local trap_name=$1; shift
+	local group_name=$1; shift
+	local dev=$1; shift
+
+	# This is the common part of all the tests. It checks that stats are
+	# initially idle, then non-idle after changing the trap action and
+	# finally idle again. It also makes sure the packets are dropped and
+	# never forwarded.
+	devlink_trap_stats_idle_test $trap_name
+	check_err $? "Trap stats not idle with initial drop action"
+	devlink_trap_group_stats_idle_test $group_name
+	check_err $? "Trap group stats not idle with initial drop action"
+
+
+	devlink_trap_action_set $trap_name "trap"
+	devlink_trap_stats_idle_test $trap_name
+	check_fail $? "Trap stats idle after setting action to trap"
+	devlink_trap_group_stats_idle_test $group_name
+	check_fail $? "Trap group stats idle after setting action to trap"
+
+	devlink_trap_action_set $trap_name "drop"
+
+	devlink_trap_stats_idle_test $trap_name
+	check_err $? "Trap stats not idle after setting action to drop"
+	devlink_trap_group_stats_idle_test $group_name
+	check_err $? "Trap group stats not idle after setting action to drop"
+
+	tc_check_packets "dev $dev egress" 101 0
+	check_err $? "Packets were not dropped"
+}
+
+devlink_trap_drop_cleanup()
+{
+	local mz_pid=$1; shift
+	local dev=$1; shift
+	local proto=$1; shift
+
+	kill $mz_pid && wait $mz_pid &> /dev/null
+	tc filter del dev $dev egress protocol $proto pref 1 handle 101 flower
+}
diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh
new file mode 100755
index 000000000000..eb8e2a23bbb4
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ethtool.sh
@@ -0,0 +1,318 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	same_speeds_autoneg_off
+	different_speeds_autoneg_off
+	combination_of_neg_on_and_off
+	advertise_subset_of_speeds
+	check_highest_speed_is_chosen
+	different_speeds_autoneg_on
+"
+NUM_NETIFS=2
+source lib.sh
+source ethtool_lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/24
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 192.0.2.1/24
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/24
+}
+
+h2_destroy()
+{
+	simple_if_fini $h2 192.0.2.2/24
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	h1_create
+	h2_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	h2_destroy
+	h1_destroy
+}
+
+different_speeds_get()
+{
+	local dev1=$1; shift
+	local dev2=$1; shift
+	local with_mode=$1; shift
+	local adver=$1; shift
+
+	local -a speeds_arr
+
+	speeds_arr=($(common_speeds_get $dev1 $dev2 $with_mode $adver))
+	if [[ ${#speeds_arr[@]} < 2 ]]; then
+		check_err 1 "cannot check different speeds. There are not enough speeds"
+	fi
+
+	echo ${speeds_arr[0]} ${speeds_arr[1]}
+}
+
+same_speeds_autoneg_off()
+{
+	# Check that when each of the reported speeds is forced, the links come
+	# up and are operational.
+	local -a speeds_arr=($(common_speeds_get $h1 $h2 0 0))
+
+	for speed in "${speeds_arr[@]}"; do
+		RET=0
+		ethtool_set $h1 speed $speed autoneg off
+		ethtool_set $h2 speed $speed autoneg off
+
+		setup_wait_dev_with_timeout $h1
+		setup_wait_dev_with_timeout $h2
+		ping_do $h1 192.0.2.2
+		check_err $? "speed $speed autoneg off"
+		log_test "force of same speed autoneg off"
+		log_info "speed = $speed"
+	done
+
+	ethtool -s $h2 autoneg on
+	ethtool -s $h1 autoneg on
+}
+
+different_speeds_autoneg_off()
+{
+	# Test that when we force different speeds, links are not up and ping
+	# fails.
+	RET=0
+
+	local -a speeds_arr=($(different_speeds_get $h1 $h2 0 0))
+	local speed1=${speeds_arr[0]}
+	local speed2=${speeds_arr[1]}
+
+	ethtool_set $h1 speed $speed1 autoneg off
+	ethtool_set $h2 speed $speed2 autoneg off
+
+	setup_wait_dev_with_timeout $h1
+	setup_wait_dev_with_timeout $h2
+	ping_do $h1 192.0.2.2
+	check_fail $? "ping with different speeds"
+
+	log_test "force of different speeds autoneg off"
+
+	ethtool -s $h2 autoneg on
+	ethtool -s $h1 autoneg on
+}
+
+combination_of_neg_on_and_off()
+{
+	# Test that when one device is forced to a speed supported by both
+	# endpoints and the other device is configured to autoneg on, the links
+	# are up and ping passes.
+	local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1))
+
+	for speed in "${speeds_arr[@]}"; do
+		RET=0
+		ethtool_set $h1 speed $speed autoneg off
+
+		setup_wait_dev_with_timeout $h1
+		setup_wait_dev_with_timeout $h2
+		ping_do $h1 192.0.2.2
+		check_err $? "h1-speed=$speed autoneg off, h2 autoneg on"
+		log_test "one side with autoneg off and another with autoneg on"
+		log_info "force speed = $speed"
+	done
+
+	ethtool -s $h1 autoneg on
+}
+
+hex_speed_value_get()
+{
+	local speed=$1; shift
+
+	local shift_size=${speed_values[$speed]}
+	speed=$((0x1 << $"shift_size"))
+	printf "%#x" "$speed"
+}
+
+subset_of_common_speeds_get()
+{
+	local dev1=$1; shift
+	local dev2=$1; shift
+	local adver=$1; shift
+
+	local -a speeds_arr=($(common_speeds_get $dev1 $dev2 0 $adver))
+	local speed_to_advertise=0
+	local speed_to_remove=${speeds_arr[0]}
+	speed_to_remove+='base'
+
+	local -a speeds_mode_arr=($(common_speeds_get $dev1 $dev2 1 $adver))
+
+	for speed in ${speeds_mode_arr[@]}; do
+		if [[ $speed != $speed_to_remove* ]]; then
+			speed=$(hex_speed_value_get $speed)
+			speed_to_advertise=$(($speed_to_advertise | \
+						$speed))
+		fi
+
+	done
+
+	# Convert to hex.
+	printf "%#x" "$speed_to_advertise"
+}
+
+speed_to_advertise_get()
+{
+	# The function returns the hex number that is composed by OR-ing all
+	# the modes corresponding to the provided speed.
+	local speed_without_mode=$1; shift
+	local supported_speeds=("$@"); shift
+	local speed_to_advertise=0
+
+	speed_without_mode+='base'
+
+	for speed in ${supported_speeds[@]}; do
+		if [[ $speed == $speed_without_mode* ]]; then
+			speed=$(hex_speed_value_get $speed)
+			speed_to_advertise=$(($speed_to_advertise | \
+						$speed))
+		fi
+
+	done
+
+	# Convert to hex.
+	printf "%#x" "$speed_to_advertise"
+}
+
+advertise_subset_of_speeds()
+{
+	# Test that when one device advertises a subset of speeds and another
+	# advertises a specific speed (but all modes of this speed), the links
+	# are up and ping passes.
+	RET=0
+
+	local speed_1_to_advertise=$(subset_of_common_speeds_get $h1 $h2 1)
+	ethtool_set $h1 advertise $speed_1_to_advertise
+
+	if [ $RET != 0 ]; then
+		log_test "advertise subset of speeds"
+		return
+	fi
+
+	local -a speeds_arr_without_mode=($(common_speeds_get $h1 $h2 0 1))
+	# Check only speeds that h1 advertised. Remove the first speed.
+	unset speeds_arr_without_mode[0]
+	local -a speeds_arr_with_mode=($(common_speeds_get $h1 $h2 1 1))
+
+	for speed_value in ${speeds_arr_without_mode[@]}; do
+		RET=0
+		local speed_2_to_advertise=$(speed_to_advertise_get $speed_value \
+			"${speeds_arr_with_mode[@]}")
+		ethtool_set $h2 advertise $speed_2_to_advertise
+
+		setup_wait_dev_with_timeout $h1
+		setup_wait_dev_with_timeout $h2
+		ping_do $h1 192.0.2.2
+		check_err $? "h1=$speed_1_to_advertise, h2=$speed_2_to_advertise ($speed_value)"
+
+		log_test "advertise subset of speeds"
+		log_info "h1=$speed_1_to_advertise, h2=$speed_2_to_advertise"
+	done
+
+	ethtool -s $h2 autoneg on
+	ethtool -s $h1 autoneg on
+}
+
+check_highest_speed_is_chosen()
+{
+	# Test that when one device advertises a subset of speeds, the other
+	# chooses the highest speed. This test checks configuration without
+	# traffic.
+	RET=0
+
+	local max_speed
+	local chosen_speed
+	local speed_to_advertise=$(subset_of_common_speeds_get $h1 $h2 1)
+
+	ethtool_set $h1 advertise $speed_to_advertise
+
+	if [ $RET != 0 ]; then
+		log_test "check highest speed"
+		return
+	fi
+
+	local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1))
+	# Remove the first speed, h1 does not advertise this speed.
+	unset speeds_arr[0]
+
+	max_speed=${speeds_arr[0]}
+	for current in ${speeds_arr[@]}; do
+		if [[ $current -gt $max_speed ]]; then
+			max_speed=$current
+		fi
+	done
+
+	setup_wait_dev_with_timeout $h1
+	setup_wait_dev_with_timeout $h2
+	chosen_speed=$(ethtool $h1 | grep 'Speed:')
+	chosen_speed=${chosen_speed%"Mb/s"*}
+	chosen_speed=${chosen_speed#*"Speed: "}
+	((chosen_speed == max_speed))
+	check_err $? "h1 advertise $speed_to_advertise, h2 sync to speed $chosen_speed"
+
+	log_test "check highest speed"
+
+	ethtool -s $h2 autoneg on
+	ethtool -s $h1 autoneg on
+}
+
+different_speeds_autoneg_on()
+{
+	# Test that when we configure links to advertise different speeds,
+	# links are not up and ping fails.
+	RET=0
+
+	local -a speeds=($(different_speeds_get $h1 $h2 1 1))
+	local speed1=${speeds[0]}
+	local speed2=${speeds[1]}
+
+	speed1=$(hex_speed_value_get $speed1)
+	speed2=$(hex_speed_value_get $speed2)
+
+	ethtool_set $h1 advertise $speed1
+	ethtool_set $h2 advertise $speed2
+
+	if (($RET)); then
+		setup_wait_dev_with_timeout $h1
+		setup_wait_dev_with_timeout $h2
+		ping_do $h1 192.0.2.2
+		check_fail $? "ping with different speeds autoneg on"
+	fi
+
+	log_test "advertise different speeds autoneg on"
+
+	ethtool -s $h2 autoneg on
+	ethtool -s $h1 autoneg on
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+declare -gA speed_values
+eval "speed_values=($(speeds_arr_get))"
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/ethtool_lib.sh b/tools/testing/selftests/net/forwarding/ethtool_lib.sh
new file mode 100755
index 000000000000..925d229a59d8
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ethtool_lib.sh
@@ -0,0 +1,69 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+speeds_arr_get()
+{
+	cmd='/ETHTOOL_LINK_MODE_[^[:space:]]*_BIT[[:space:]]+=[[:space:]]+/ \
+		{sub(/,$/, "") \
+		sub(/ETHTOOL_LINK_MODE_/,"") \
+		sub(/_BIT/,"") \
+		sub(/_Full/,"/Full") \
+		sub(/_Half/,"/Half");\
+		print "["$1"]="$3}'
+
+	awk "${cmd}" /usr/include/linux/ethtool.h
+}
+
+ethtool_set()
+{
+	local cmd="$@"
+	local out=$(ethtool -s $cmd 2>&1 | wc -l)
+
+	check_err $out "error in configuration. $cmd"
+}
+
+dev_speeds_get()
+{
+	local dev=$1; shift
+	local with_mode=$1; shift
+	local adver=$1; shift
+	local speeds_str
+
+	if (($adver)); then
+		mode="Advertised link modes"
+	else
+		mode="Supported link modes"
+	fi
+
+	speeds_str=$(ethtool "$dev" | \
+		# Snip everything before the link modes section.
+		sed -n '/'"$mode"':/,$p' | \
+		# Quit processing the rest at the start of the next section.
+		# When checking, skip the header of this section (hence the 2,).
+		sed -n '2,${/^[\t][^ \t]/q};p' | \
+		# Drop the section header of the current section.
+		cut -d':' -f2)
+
+	local -a speeds_arr=($speeds_str)
+	if [[ $with_mode -eq 0 ]]; then
+		for ((i=0; i<${#speeds_arr[@]}; i++)); do
+			speeds_arr[$i]=${speeds_arr[$i]%base*}
+		done
+	fi
+	echo ${speeds_arr[@]}
+}
+
+common_speeds_get()
+{
+	dev1=$1; shift
+	dev2=$1; shift
+	with_mode=$1; shift
+	adver=$1; shift
+
+	local -a dev1_speeds=($(dev_speeds_get $dev1 $with_mode $adver))
+	local -a dev2_speeds=($(dev_speeds_get $dev2 $with_mode $adver))
+
+	comm -12 \
+		<(printf '%s\n' "${dev1_speeds[@]}" | sort -u) \
+		<(printf '%s\n' "${dev2_speeds[@]}" | sort -u)
+}
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 85c587a03c8a..1f64e7348f69 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -18,6 +18,8 @@ NETIF_CREATE=${NETIF_CREATE:=yes}
 MCD=${MCD:=smcrouted}
 MC_CLI=${MC_CLI:=smcroutectl}
 PING_TIMEOUT=${PING_TIMEOUT:=5}
+WAIT_TIMEOUT=${WAIT_TIMEOUT:=20}
+INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600}
 
 relative_path="${BASH_SOURCE%/*}"
 if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
@@ -226,24 +228,45 @@ log_info()
 setup_wait_dev()
 {
 	local dev=$1; shift
+	local wait_time=${1:-$WAIT_TIME}; shift
 
-	while true; do
+	setup_wait_dev_with_timeout "$dev" $INTERFACE_TIMEOUT $wait_time
+
+	if (($?)); then
+		check_err 1
+		log_test setup_wait_dev ": Interface $dev does not come up."
+		exit 1
+	fi
+}
+
+setup_wait_dev_with_timeout()
+{
+	local dev=$1; shift
+	local max_iterations=${1:-$WAIT_TIMEOUT}; shift
+	local wait_time=${1:-$WAIT_TIME}; shift
+	local i
+
+	for ((i = 1; i <= $max_iterations; ++i)); do
 		ip link show dev $dev up \
 			| grep 'state UP' &> /dev/null
 		if [[ $? -ne 0 ]]; then
 			sleep 1
 		else
-			break
+			sleep $wait_time
+			return 0
 		fi
 	done
+
+	return 1
 }
 
 setup_wait()
 {
 	local num_netifs=${1:-$NUM_NETIFS}
+	local i
 
 	for ((i = 1; i <= num_netifs; ++i)); do
-		setup_wait_dev ${NETIFS[p$i]}
+		setup_wait_dev ${NETIFS[p$i]} 0
 	done
 
 	# Make sure links are ready.
@@ -254,6 +277,7 @@ cmd_jq()
 {
 	local cmd=$1
 	local jq_exp=$2
+	local jq_opts=$3
 	local ret
 	local output
 
@@ -263,7 +287,11 @@ cmd_jq()
 	if [[ $ret -ne 0 ]]; then
 		return $ret
 	fi
-	output=$(echo $output | jq -r "$jq_exp")
+	output=$(echo $output | jq -r $jq_opts "$jq_exp")
+	ret=$?
+	if [[ $ret -ne 0 ]]; then
+		return $ret
+	fi
 	echo $output
 	# return success only in case of non-empty output
 	[ ! -z "$output" ]
diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh
index 315e934358d4..d93589bd4d1d 100644
--- a/tools/testing/selftests/net/forwarding/tc_common.sh
+++ b/tools/testing/selftests/net/forwarding/tc_common.sh
@@ -14,3 +14,14 @@ tc_check_packets()
 	              select(.options.actions[0].stats.packets == $count)" \
 	       &> /dev/null
 }
+
+tc_check_packets_hitting()
+{
+	local id=$1
+	local handle=$2
+
+	cmd_jq "tc -j -s filter show $id" \
+	       ".[] | select(.options.handle == $handle) | \
+		      select(.options.actions[0].stats.packets > 0)" \
+	       &> /dev/null
+}
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 33035d1b3f6d..35505b31e5cc 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -82,7 +82,9 @@ static int zflg; /* zero copy option. (MSG_ZEROCOPY for sender, mmap() for recei
 static int xflg; /* hash received data (simple xor) (-h option) */
 static int keepflag; /* -k option: receiver shall keep all received file in memory (no munmap() calls) */
 
-static int chunk_size  = 512*1024;
+static size_t chunk_size  = 512*1024;
+
+static size_t map_align;
 
 unsigned long htotal;
 
@@ -118,6 +120,9 @@ void hash_zone(void *zone, unsigned int length)
 	htotal = temp;
 }
 
+#define ALIGN_UP(x, align_to)	(((x) + ((align_to)-1)) & ~((align_to)-1))
+#define ALIGN_PTR_UP(p, ptr_align_to)	((typeof(p))ALIGN_UP((unsigned long)(p), ptr_align_to))
+
 void *child_thread(void *arg)
 {
 	unsigned long total_mmap = 0, total = 0;
@@ -126,6 +131,7 @@ void *child_thread(void *arg)
 	int flags = MAP_SHARED;
 	struct timeval t0, t1;
 	char *buffer = NULL;
+	void *raddr = NULL;
 	void *addr = NULL;
 	double throughput;
 	struct rusage ru;
@@ -142,9 +148,13 @@ void *child_thread(void *arg)
 		goto error;
 	}
 	if (zflg) {
-		addr = mmap(NULL, chunk_size, PROT_READ, flags, fd, 0);
-		if (addr == (void *)-1)
+		raddr = mmap(NULL, chunk_size + map_align, PROT_READ, flags, fd, 0);
+		if (raddr == (void *)-1) {
+			perror("mmap");
 			zflg = 0;
+		} else {
+			addr = ALIGN_PTR_UP(raddr, map_align);
+		}
 	}
 	while (1) {
 		struct pollfd pfd = { .fd = fd, .events = POLLIN, };
@@ -222,7 +232,7 @@ error:
 	free(buffer);
 	close(fd);
 	if (zflg)
-		munmap(addr, chunk_size);
+		munmap(raddr, chunk_size + map_align);
 	pthread_exit(0);
 }
 
@@ -270,6 +280,11 @@ static void setup_sockaddr(int domain, const char *str_addr,
 
 static void do_accept(int fdlisten)
 {
+	pthread_attr_t attr;
+
+	pthread_attr_init(&attr);
+	pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED);
+
 	if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT,
 		       &chunk_size, sizeof(chunk_size)) == -1) {
 		perror("setsockopt SO_RCVLOWAT");
@@ -288,7 +303,7 @@ static void do_accept(int fdlisten)
 			perror("accept");
 			continue;
 		}
-		res = pthread_create(&th, NULL, child_thread,
+		res = pthread_create(&th, &attr, child_thread,
 				     (void *)(unsigned long)fd);
 		if (res) {
 			errno = res;
@@ -298,6 +313,30 @@ static void do_accept(int fdlisten)
 	}
 }
 
+/* Each thread should reserve a big enough vma to avoid
+ * spinlock collisions in ptl locks.
+ * This size is 2MB on x86_64, and is exported in /proc/meminfo.
+ */
+static unsigned long default_huge_page_size(void)
+{
+	FILE *f = fopen("/proc/meminfo", "r");
+	unsigned long hps = 0;
+	size_t linelen = 0;
+	char *line = NULL;
+
+	if (!f)
+		return 0;
+	while (getline(&line, &linelen, f) > 0) {
+		if (sscanf(line, "Hugepagesize:       %lu kB", &hps) == 1) {
+			hps <<= 10;
+			break;
+		}
+	}
+	free(line);
+	fclose(f);
+	return hps;
+}
+
 int main(int argc, char *argv[])
 {
 	struct sockaddr_storage listenaddr, addr;
@@ -309,7 +348,7 @@ int main(int argc, char *argv[])
 	int sflg = 0;
 	int mss = 0;
 
-	while ((c = getopt(argc, argv, "46p:svr:w:H:zxkP:M:")) != -1) {
+	while ((c = getopt(argc, argv, "46p:svr:w:H:zxkP:M:C:a:")) != -1) {
 		switch (c) {
 		case '4':
 			cfg_family = PF_INET;
@@ -349,10 +388,24 @@ int main(int argc, char *argv[])
 		case 'P':
 			max_pacing_rate = atoi(optarg) ;
 			break;
+		case 'C':
+			chunk_size = atol(optarg);
+			break;
+		case 'a':
+			map_align = atol(optarg);
+			break;
 		default:
 			exit(1);
 		}
 	}
+	if (!map_align) {
+		map_align = default_huge_page_size();
+		/* if really /proc/meminfo is not helping,
+		 * we use the default x86_64 hugepagesize.
+		 */
+		if (!map_align)
+			map_align = 2*1024*1024;
+	}
 	if (sflg) {
 		int fdlisten = socket(cfg_family, SOCK_STREAM, 0);
 
diff --git a/tools/testing/selftests/net/traceroute.sh b/tools/testing/selftests/net/traceroute.sh
new file mode 100755
index 000000000000..de9ca97abc30
--- /dev/null
+++ b/tools/testing/selftests/net/traceroute.sh
@@ -0,0 +1,322 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run traceroute/traceroute6 tests
+#
+
+VERBOSE=0
+PAUSE_ON_FAIL=no
+
+################################################################################
+#
+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
+}
+
+run_cmd()
+{
+	local ns
+	local cmd
+	local out
+	local rc
+
+	ns="$1"
+	shift
+	cmd="$*"
+
+	if [ "$VERBOSE" = "1" ]; then
+		printf "    COMMAND: $cmd\n"
+	fi
+
+	out=$(eval ip netns exec ${ns} ${cmd} 2>&1)
+	rc=$?
+	if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+		echo "    $out"
+	fi
+
+	[ "$VERBOSE" = "1" ] && echo
+
+	return $rc
+}
+
+################################################################################
+# create namespaces and interconnects
+
+create_ns()
+{
+	local ns=$1
+	local addr=$2
+	local addr6=$3
+
+	[ -z "${addr}" ] && addr="-"
+	[ -z "${addr6}" ] && addr6="-"
+
+	ip netns add ${ns}
+
+	ip netns exec ${ns} ip link set lo up
+	if [ "${addr}" != "-" ]; then
+		ip netns exec ${ns} ip addr add dev lo ${addr}
+	fi
+	if [ "${addr6}" != "-" ]; then
+		ip netns exec ${ns} ip -6 addr add dev lo ${addr6}
+	fi
+
+	ip netns exec ${ns} ip ro add unreachable default metric 8192
+	ip netns exec ${ns} ip -6 ro add unreachable default metric 8192
+
+	ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1
+	ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1
+	ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1
+	ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.accept_dad=0
+}
+
+# create veth pair to connect namespaces and apply addresses.
+connect_ns()
+{
+	local ns1=$1
+	local ns1_dev=$2
+	local ns1_addr=$3
+	local ns1_addr6=$4
+	local ns2=$5
+	local ns2_dev=$6
+	local ns2_addr=$7
+	local ns2_addr6=$8
+
+	ip netns exec ${ns1} ip li add ${ns1_dev} type veth peer name tmp
+	ip netns exec ${ns1} ip li set ${ns1_dev} up
+	ip netns exec ${ns1} ip li set tmp netns ${ns2} name ${ns2_dev}
+	ip netns exec ${ns2} ip li set ${ns2_dev} up
+
+	if [ "${ns1_addr}" != "-" ]; then
+		ip netns exec ${ns1} ip addr add dev ${ns1_dev} ${ns1_addr}
+	fi
+
+	if [ "${ns2_addr}" != "-" ]; then
+		ip netns exec ${ns2} ip addr add dev ${ns2_dev} ${ns2_addr}
+	fi
+
+	if [ "${ns1_addr6}" != "-" ]; then
+		ip netns exec ${ns1} ip addr add dev ${ns1_dev} ${ns1_addr6}
+	fi
+
+	if [ "${ns2_addr6}" != "-" ]; then
+		ip netns exec ${ns2} ip addr add dev ${ns2_dev} ${ns2_addr6}
+	fi
+}
+
+################################################################################
+# traceroute6 test
+#
+# Verify that in this scenario
+#
+#        ------------------------ N2
+#         |                    |
+#       ------              ------  N3  ----
+#       | R1 |              | R2 |------|H2|
+#       ------              ------      ----
+#         |                    |
+#        ------------------------ N1
+#                  |
+#                 ----
+#                 |H1|
+#                 ----
+#
+# where H1's default route goes through R1 and R1's default route goes
+# through R2 over N2, traceroute6 from H1 to H2 reports R2's address
+# on N2 and not N1.
+#
+# Addresses are assigned as follows:
+#
+# N1: 2000:101::/64
+# N2: 2000:102::/64
+# N3: 2000:103::/64
+#
+# R1's host part of address: 1
+# R2's host part of address: 2
+# H1's host part of address: 3
+# H2's host part of address: 4
+#
+# For example:
+# the IPv6 address of R1's interface on N2 is 2000:102::1/64
+
+cleanup_traceroute6()
+{
+	local ns
+
+	for ns in host-1 host-2 router-1 router-2
+	do
+		ip netns del ${ns} 2>/dev/null
+	done
+}
+
+setup_traceroute6()
+{
+	brdev=br0
+
+	# start clean
+	cleanup_traceroute6
+
+	set -e
+	create_ns host-1
+	create_ns host-2
+	create_ns router-1
+	create_ns router-2
+
+	# Setup N3
+	connect_ns router-2 eth3 - 2000:103::2/64 host-2 eth3 - 2000:103::4/64
+	ip netns exec host-2 ip route add default via 2000:103::2
+
+	# Setup N2
+	connect_ns router-1 eth2 - 2000:102::1/64 router-2 eth2 - 2000:102::2/64
+	ip netns exec router-1 ip route add default via 2000:102::2
+
+	# Setup N1. host-1 and router-2 connect to a bridge in router-1.
+	ip netns exec router-1 ip link add name ${brdev} type bridge
+	ip netns exec router-1 ip link set ${brdev} up
+	ip netns exec router-1 ip addr add 2000:101::1/64 dev ${brdev}
+
+	connect_ns host-1 eth0 - 2000:101::3/64 router-1 eth0 - -
+	ip netns exec router-1 ip link set dev eth0 master ${brdev}
+	ip netns exec host-1 ip route add default via 2000:101::1
+
+	connect_ns router-2 eth1 - 2000:101::2/64 router-1 eth1 - -
+	ip netns exec router-1 ip link set dev eth1 master ${brdev}
+
+	# Prime the network
+	ip netns exec host-1 ping6 -c5 2000:103::4 >/dev/null 2>&1
+
+	set +e
+}
+
+run_traceroute6()
+{
+	if [ ! -x "$(command -v traceroute6)" ]; then
+		echo "SKIP: Could not run IPV6 test without traceroute6"
+		return
+	fi
+
+	setup_traceroute6
+
+	# traceroute6 host-2 from host-1 (expects 2000:102::2)
+	run_cmd host-1 "traceroute6 2000:103::4 | grep -q 2000:102::2"
+	log_test $? 0 "IPV6 traceroute"
+
+	cleanup_traceroute6
+}
+
+################################################################################
+# traceroute test
+#
+# Verify that traceroute from H1 to H2 shows 1.0.1.1 in this scenario
+#
+#                    1.0.3.1/24
+# ---- 1.0.1.3/24    1.0.1.1/24 ---- 1.0.2.1/24    1.0.2.4/24 ----
+# |H1|--------------------------|R1|--------------------------|H2|
+# ----            N1            ----            N2            ----
+#
+# where net.ipv4.icmp_errors_use_inbound_ifaddr is set on R1 and
+# 1.0.3.1/24 and 1.0.1.1/24 are respectively R1's primary and secondary
+# address on N1.
+#
+
+cleanup_traceroute()
+{
+	local ns
+
+	for ns in host-1 host-2 router
+	do
+		ip netns del ${ns} 2>/dev/null
+	done
+}
+
+setup_traceroute()
+{
+	# start clean
+	cleanup_traceroute
+
+	set -e
+	create_ns host-1
+	create_ns host-2
+	create_ns router
+
+	connect_ns host-1 eth0 1.0.1.3/24 - \
+	           router eth1 1.0.3.1/24 -
+	ip netns exec host-1 ip route add default via 1.0.1.1
+
+	ip netns exec router ip addr add 1.0.1.1/24 dev eth1
+	ip netns exec router sysctl -qw \
+				net.ipv4.icmp_errors_use_inbound_ifaddr=1
+
+	connect_ns host-2 eth0 1.0.2.4/24 - \
+	           router eth2 1.0.2.1/24 -
+	ip netns exec host-2 ip route add default via 1.0.2.1
+
+	# Prime the network
+	ip netns exec host-1 ping -c5 1.0.2.4 >/dev/null 2>&1
+
+	set +e
+}
+
+run_traceroute()
+{
+	if [ ! -x "$(command -v traceroute)" ]; then
+		echo "SKIP: Could not run IPV4 test without traceroute"
+		return
+	fi
+
+	setup_traceroute
+
+	# traceroute host-2 from host-1 (expects 1.0.1.1). Takes a while.
+	run_cmd host-1 "traceroute 1.0.2.4 | grep -q 1.0.1.1"
+	log_test $? 0 "IPV4 traceroute"
+
+	cleanup_traceroute
+}
+
+################################################################################
+# Run tests
+
+run_tests()
+{
+	run_traceroute6
+	run_traceroute
+}
+
+################################################################################
+# main
+
+declare -i nfail=0
+declare -i nsuccess=0
+
+while getopts :pv o
+do
+	case $o in
+		p) PAUSE_ON_FAIL=yes;;
+		v) VERBOSE=$(($VERBOSE + 1));;
+		*) exit 1;;
+	esac
+done
+
+run_tests
+
+printf "\nTests passed: %3d\n" ${nsuccess}
+printf "Tests failed: %3d\n"   ${nfail}