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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

10 files changed, 1258 insertions, 109 deletions

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 3f386eb9e7d7..895ec992b2f1 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -16,6 +16,7 @@ TEST_PROGS += altnames.sh icmp_redirect.sh ip6_gre_headroom.sh
 TEST_PROGS += route_localnet.sh
 TEST_PROGS += reuseaddr_ports_exhausted.sh
 TEST_PROGS += txtimestamp.sh
+TEST_PROGS += vrf-xfrm-tests.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/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 6560ed796ac4..dee567f7576a 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -19,8 +19,8 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-IPV4_TESTS="ipv4_fcnal ipv4_grp_fcnal ipv4_withv6_fcnal ipv4_fcnal_runtime"
-IPV6_TESTS="ipv6_fcnal ipv6_grp_fcnal ipv6_fcnal_runtime"
+IPV4_TESTS="ipv4_fcnal ipv4_grp_fcnal ipv4_withv6_fcnal ipv4_fcnal_runtime ipv4_large_grp ipv4_compat_mode ipv4_fdb_grp_fcnal ipv4_torture"
+IPV6_TESTS="ipv6_fcnal ipv6_grp_fcnal ipv6_fcnal_runtime ipv6_large_grp ipv6_compat_mode ipv6_fdb_grp_fcnal ipv6_torture"
 
 ALL_TESTS="basic ${IPV4_TESTS} ${IPV6_TESTS}"
 TESTS="${ALL_TESTS}"
@@ -146,35 +146,36 @@ setup()
 	create_ns remote
 
 	IP="ip -netns me"
+	BRIDGE="bridge -netns me"
 	set -e
 	$IP li add veth1 type veth peer name veth2
 	$IP li set veth1 up
 	$IP addr add 172.16.1.1/24 dev veth1
-	$IP -6 addr add 2001:db8:91::1/64 dev veth1
+	$IP -6 addr add 2001:db8:91::1/64 dev veth1 nodad
 
 	$IP li add veth3 type veth peer name veth4
 	$IP li set veth3 up
 	$IP addr add 172.16.2.1/24 dev veth3
-	$IP -6 addr add 2001:db8:92::1/64 dev veth3
+	$IP -6 addr add 2001:db8:92::1/64 dev veth3 nodad
 
 	$IP li set veth2 netns peer up
 	ip -netns peer addr add 172.16.1.2/24 dev veth2
-	ip -netns peer -6 addr add 2001:db8:91::2/64 dev veth2
+	ip -netns peer -6 addr add 2001:db8:91::2/64 dev veth2 nodad
 
 	$IP li set veth4 netns peer up
 	ip -netns peer addr add 172.16.2.2/24 dev veth4
-	ip -netns peer -6 addr add 2001:db8:92::2/64 dev veth4
+	ip -netns peer -6 addr add 2001:db8:92::2/64 dev veth4 nodad
 
 	ip -netns remote li add veth5 type veth peer name veth6
 	ip -netns remote li set veth5 up
 	ip -netns remote addr add dev veth5 172.16.101.1/24
-	ip -netns remote addr add dev veth5 2001:db8:101::1/64
+	ip -netns remote -6 addr add dev veth5 2001:db8:101::1/64 nodad
 	ip -netns remote ro add 172.16.0.0/22 via 172.16.101.2
 	ip -netns remote -6 ro add 2001:db8:90::/40 via 2001:db8:101::2
 
 	ip -netns remote li set veth6 netns peer up
 	ip -netns peer addr add dev veth6 172.16.101.2/24
-	ip -netns peer addr add dev veth6 2001:db8:101::2/64
+	ip -netns peer -6 addr add dev veth6 2001:db8:101::2/64 nodad
 	set +e
 }
 
@@ -248,11 +249,247 @@ check_route6()
 	local expected="$2"
 	local out
 
-	out=$($IP -6 route ls match ${pfx} 2>/dev/null)
+	out=$($IP -6 route ls match ${pfx} 2>/dev/null | sed -e 's/pref medium//')
 
 	check_output "${out}" "${expected}"
 }
 
+check_large_grp()
+{
+	local ipv=$1
+	local ecmp=$2
+	local grpnum=100
+	local nhidstart=100
+	local grpidstart=1000
+	local iter=0
+	local nhidstr=""
+	local grpidstr=""
+	local grpstr=""
+	local ipstr=""
+
+	if [ $ipv -eq 4 ]; then
+		ipstr="172.16.1."
+	else
+		ipstr="2001:db8:91::"
+	fi
+
+	#
+	# Create $grpnum groups with specified $ecmp and dump them
+	#
+
+	# create nexthops with different gateways
+	iter=2
+	while [ $iter -le $(($ecmp + 1)) ]
+	do
+		nhidstr="$(($nhidstart + $iter))"
+		run_cmd "$IP nexthop add id $nhidstr via $ipstr$iter dev veth1"
+		check_nexthop "id $nhidstr" "id $nhidstr via $ipstr$iter dev veth1 scope link"
+
+		if [ $iter -le $ecmp ]; then
+			grpstr+="$nhidstr/"
+		else
+			grpstr+="$nhidstr"
+		fi
+		((iter++))
+	done
+
+	# create duplicate large ecmp groups
+	iter=0
+	while [ $iter -le $grpnum ]
+	do
+		grpidstr="$(($grpidstart + $iter))"
+		run_cmd "$IP nexthop add id $grpidstr group $grpstr"
+		check_nexthop "id $grpidstr" "id $grpidstr group $grpstr"
+		((iter++))
+	done
+
+	# dump large groups
+	run_cmd "$IP nexthop list"
+	log_test $? 0 "Dump large (x$ecmp) ecmp groups"
+}
+
+start_ip_monitor()
+{
+	local mtype=$1
+
+	# start the monitor in the background
+	tmpfile=`mktemp /var/run/nexthoptestXXX`
+	mpid=`($IP monitor $mtype > $tmpfile & echo $!) 2>/dev/null`
+	sleep 0.2
+	echo "$mpid $tmpfile"
+}
+
+stop_ip_monitor()
+{
+	local mpid=$1
+	local tmpfile=$2
+	local el=$3
+
+	# check the monitor results
+	kill $mpid
+	lines=`wc -l $tmpfile | cut "-d " -f1`
+	test $lines -eq $el
+	rc=$?
+	rm -rf $tmpfile
+
+	return $rc
+}
+
+check_nexthop_fdb_support()
+{
+	$IP nexthop help 2>&1 | grep -q fdb
+	if [ $? -ne 0 ]; then
+		echo "SKIP: iproute2 too old, missing fdb nexthop support"
+		return $ksft_skip
+	fi
+}
+
+ipv6_fdb_grp_fcnal()
+{
+	local rc
+
+	echo
+	echo "IPv6 fdb groups functional"
+	echo "--------------------------"
+
+	check_nexthop_fdb_support
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	# create group with multiple nexthops
+	run_cmd "$IP nexthop add id 61 via 2001:db8:91::2 fdb"
+	run_cmd "$IP nexthop add id 62 via 2001:db8:91::3 fdb"
+	run_cmd "$IP nexthop add id 102 group 61/62 fdb"
+	check_nexthop "id 102" "id 102 group 61/62 fdb"
+	log_test $? 0 "Fdb Nexthop group with multiple nexthops"
+
+	## get nexthop group
+	run_cmd "$IP nexthop get id 102"
+	check_nexthop "id 102" "id 102 group 61/62 fdb"
+	log_test $? 0 "Get Fdb nexthop group by id"
+
+	# fdb nexthop group can only contain fdb nexthops
+	run_cmd "$IP nexthop add id 63 via 2001:db8:91::4"
+	run_cmd "$IP nexthop add id 64 via 2001:db8:91::5"
+	run_cmd "$IP nexthop add id 103 group 63/64 fdb"
+	log_test $? 2 "Fdb Nexthop group with non-fdb nexthops"
+
+	# Non fdb nexthop group can not contain fdb nexthops
+	run_cmd "$IP nexthop add id 65 via 2001:db8:91::5 fdb"
+	run_cmd "$IP nexthop add id 66 via 2001:db8:91::6 fdb"
+	run_cmd "$IP nexthop add id 104 group 65/66"
+	log_test $? 2 "Non-Fdb Nexthop group with fdb nexthops"
+
+	# fdb nexthop cannot have blackhole
+	run_cmd "$IP nexthop add id 67 blackhole fdb"
+	log_test $? 2 "Fdb Nexthop with blackhole"
+
+	# fdb nexthop with oif
+	run_cmd "$IP nexthop add id 68 via 2001:db8:91::7 dev veth1 fdb"
+	log_test $? 2 "Fdb Nexthop with oif"
+
+	# fdb nexthop with onlink
+	run_cmd "$IP nexthop add id 68 via 2001:db8:91::7 onlink fdb"
+	log_test $? 2 "Fdb Nexthop with onlink"
+
+	# fdb nexthop with encap
+	run_cmd "$IP nexthop add id 69 encap mpls 101 via 2001:db8:91::8 dev veth1 fdb"
+	log_test $? 2 "Fdb Nexthop with encap"
+
+	run_cmd "$IP link add name vx10 type vxlan id 1010 local 2001:db8:91::9 remote 2001:db8:91::10 dstport 4789 nolearning noudpcsum tos inherit ttl 100"
+	run_cmd "$BRIDGE fdb add 02:02:00:00:00:13 dev vx10 nhid 102 self"
+	log_test $? 0 "Fdb mac add with nexthop group"
+
+	## fdb nexthops can only reference nexthop groups and not nexthops
+	run_cmd "$BRIDGE fdb add 02:02:00:00:00:14 dev vx10 nhid 61 self"
+	log_test $? 255 "Fdb mac add with nexthop"
+
+	run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 66"
+	log_test $? 2 "Route add with fdb nexthop"
+
+	run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 103"
+	log_test $? 2 "Route add with fdb nexthop group"
+
+	run_cmd "$IP nexthop del id 102"
+	log_test $? 0 "Fdb nexthop delete"
+
+	$IP link del dev vx10
+}
+
+ipv4_fdb_grp_fcnal()
+{
+	local rc
+
+	echo
+	echo "IPv4 fdb groups functional"
+	echo "--------------------------"
+
+	check_nexthop_fdb_support
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	# create group with multiple nexthops
+	run_cmd "$IP nexthop add id 12 via 172.16.1.2 fdb"
+	run_cmd "$IP nexthop add id 13 via 172.16.1.3 fdb"
+	run_cmd "$IP nexthop add id 102 group 12/13 fdb"
+	check_nexthop "id 102" "id 102 group 12/13 fdb"
+	log_test $? 0 "Fdb Nexthop group with multiple nexthops"
+
+	# get nexthop group
+	run_cmd "$IP nexthop get id 102"
+	check_nexthop "id 102" "id 102 group 12/13 fdb"
+	log_test $? 0 "Get Fdb nexthop group by id"
+
+	# fdb nexthop group can only contain fdb nexthops
+	run_cmd "$IP nexthop add id 14 via 172.16.1.2"
+	run_cmd "$IP nexthop add id 15 via 172.16.1.3"
+	run_cmd "$IP nexthop add id 103 group 14/15 fdb"
+	log_test $? 2 "Fdb Nexthop group with non-fdb nexthops"
+
+	# Non fdb nexthop group can not contain fdb nexthops
+	run_cmd "$IP nexthop add id 16 via 172.16.1.2 fdb"
+	run_cmd "$IP nexthop add id 17 via 172.16.1.3 fdb"
+	run_cmd "$IP nexthop add id 104 group 14/15"
+	log_test $? 2 "Non-Fdb Nexthop group with fdb nexthops"
+
+	# fdb nexthop cannot have blackhole
+	run_cmd "$IP nexthop add id 18 blackhole fdb"
+	log_test $? 2 "Fdb Nexthop with blackhole"
+
+	# fdb nexthop with oif
+	run_cmd "$IP nexthop add id 16 via 172.16.1.2 dev veth1 fdb"
+	log_test $? 2 "Fdb Nexthop with oif"
+
+	# fdb nexthop with onlink
+	run_cmd "$IP nexthop add id 16 via 172.16.1.2 onlink fdb"
+	log_test $? 2 "Fdb Nexthop with onlink"
+
+	# fdb nexthop with encap
+	run_cmd "$IP nexthop add id 17 encap mpls 101 via 172.16.1.2 dev veth1 fdb"
+	log_test $? 2 "Fdb Nexthop with encap"
+
+	run_cmd "$IP link add name vx10 type vxlan id 1010 local 10.0.0.1 remote 10.0.0.2 dstport 4789 nolearning noudpcsum tos inherit ttl 100"
+	run_cmd "$BRIDGE fdb add 02:02:00:00:00:13 dev vx10 nhid 102 self"
+	log_test $? 0 "Fdb mac add with nexthop group"
+
+	# fdb nexthops can only reference nexthop groups and not nexthops
+	run_cmd "$BRIDGE fdb add 02:02:00:00:00:14 dev vx10 nhid 12 self"
+	log_test $? 255 "Fdb mac add with nexthop"
+
+	run_cmd "$IP ro add 172.16.0.0/22 nhid 15"
+	log_test $? 2 "Route add with fdb nexthop"
+
+	run_cmd "$IP ro add 172.16.0.0/22 nhid 103"
+	log_test $? 2 "Route add with fdb nexthop group"
+
+	run_cmd "$IP nexthop del id 102"
+	log_test $? 0 "Fdb nexthop delete"
+
+	$IP link del dev vx10
+}
+
 ################################################################################
 # basic operations (add, delete, replace) on nexthops and nexthop groups
 #
@@ -423,8 +660,6 @@ ipv6_fcnal_runtime()
 	echo "IPv6 functional runtime"
 	echo "-----------------------"
 
-	sleep 5
-
 	#
 	# IPv6 - the basics
 	#
@@ -481,12 +716,12 @@ ipv6_fcnal_runtime()
 	run_cmd "$IP -6 nexthop add id 85 dev veth1"
 	run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 85"
 	log_test $? 0 "IPv6 route with device only nexthop"
-	check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1 metric 1024 pref medium"
+	check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1 metric 1024"
 
 	run_cmd "$IP nexthop add id 123 group 81/85"
 	run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 123"
 	log_test $? 0 "IPv6 multipath route with nexthop mix - dev only + gw"
-	check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 123 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop dev veth1 weight 1 pref medium"
+	check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 123 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop dev veth1 weight 1"
 
 	#
 	# IPv6 route with v4 nexthop - not allowed
@@ -519,6 +754,75 @@ ipv6_fcnal_runtime()
 	# route with src address and using nexthop - not allowed
 }
 
+ipv6_large_grp()
+{
+	local ecmp=32
+
+	echo
+	echo "IPv6 large groups (x$ecmp)"
+	echo "---------------------"
+
+	check_large_grp 6 $ecmp
+
+	$IP nexthop flush >/dev/null 2>&1
+}
+
+ipv6_del_add_loop1()
+{
+	while :; do
+		$IP nexthop del id 100
+		$IP nexthop add id 100 via 2001:db8:91::2 dev veth1
+	done >/dev/null 2>&1
+}
+
+ipv6_grp_replace_loop()
+{
+	while :; do
+		$IP nexthop replace id 102 group 100/101
+	done >/dev/null 2>&1
+}
+
+ipv6_torture()
+{
+	local pid1
+	local pid2
+	local pid3
+	local pid4
+	local pid5
+
+	echo
+	echo "IPv6 runtime torture"
+	echo "--------------------"
+	if [ ! -x "$(command -v mausezahn)" ]; then
+		echo "SKIP: Could not run test; need mausezahn tool"
+		return
+	fi
+
+	run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1"
+	run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth3"
+	run_cmd "$IP nexthop add id 102 group 100/101"
+	run_cmd "$IP route add 2001:db8:101::1 nhid 102"
+	run_cmd "$IP route add 2001:db8:101::2 nhid 102"
+
+	ipv6_del_add_loop1 &
+	pid1=$!
+	ipv6_grp_replace_loop &
+	pid2=$!
+	ip netns exec me ping -f 2001:db8:101::1 >/dev/null 2>&1 &
+	pid3=$!
+	ip netns exec me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
+	pid4=$!
+	ip netns exec me mausezahn veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+	pid5=$!
+
+	sleep 300
+	kill -9 $pid1 $pid2 $pid3 $pid4 $pid5
+
+	# if we did not crash, success
+	log_test 0 0 "IPv6 torture test"
+}
+
+
 ipv4_fcnal()
 {
 	local rc
@@ -866,6 +1170,11 @@ ipv4_fcnal_runtime()
 		$IP neigh sh | grep 'dev veth1'
 	fi
 
+	run_cmd "$IP ro del 172.16.101.1/32 via inet6 ${lladdr} dev veth1"
+	run_cmd "$IP -4 ro add default via inet6 ${lladdr} dev veth1"
+	run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
+	log_test $? 0 "IPv4 default route with IPv6 gateway"
+
 	#
 	# MPLS as an example of LWT encap
 	#
@@ -880,6 +1189,241 @@ ipv4_fcnal_runtime()
 	log_test $? 0 "IPv4 route with MPLS encap, v6 gw - check"
 }
 
+ipv4_large_grp()
+{
+	local ecmp=32
+
+	echo
+	echo "IPv4 large groups (x$ecmp)"
+	echo "---------------------"
+
+	check_large_grp 4 $ecmp
+
+	$IP nexthop flush >/dev/null 2>&1
+}
+
+sysctl_nexthop_compat_mode_check()
+{
+	local sysctlname="net.ipv4.nexthop_compat_mode"
+	local lprefix=$1
+
+	IPE="ip netns exec me"
+
+	$IPE sysctl -q $sysctlname 2>&1 >/dev/null
+	if [ $? -ne 0 ]; then
+		echo "SKIP: kernel lacks nexthop compat mode sysctl control"
+		return $ksft_skip
+	fi
+
+	out=$($IPE sysctl $sysctlname 2>/dev/null)
+	log_test $? 0 "$lprefix default nexthop compat mode check"
+	check_output "${out}" "$sysctlname = 1"
+}
+
+sysctl_nexthop_compat_mode_set()
+{
+	local sysctlname="net.ipv4.nexthop_compat_mode"
+	local mode=$1
+	local lprefix=$2
+
+	IPE="ip netns exec me"
+
+	out=$($IPE sysctl -w $sysctlname=$mode)
+	log_test $? 0 "$lprefix set compat mode - $mode"
+	check_output "${out}" "net.ipv4.nexthop_compat_mode = $mode"
+}
+
+ipv6_compat_mode()
+{
+	local rc
+
+	echo
+	echo "IPv6 nexthop api compat mode test"
+	echo "--------------------------------"
+
+	sysctl_nexthop_compat_mode_check "IPv6"
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1"
+	run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1"
+	run_cmd "$IP nexthop add id 122 group 62/63"
+	ipmout=$(start_ip_monitor route)
+
+	run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 122"
+	# route add notification should contain expanded nexthops
+	stop_ip_monitor $ipmout 3
+	log_test $? 0 "IPv6 compat mode on - route add notification"
+
+	# route dump should contain expanded nexthops
+	check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 122 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop via 2001:db8:91::3 dev veth1 weight 1"
+	log_test $? 0 "IPv6 compat mode on - route dump"
+
+	# change in nexthop group should generate route notification
+	run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1"
+	ipmout=$(start_ip_monitor route)
+	run_cmd "$IP nexthop replace id 122 group 62/64"
+	stop_ip_monitor $ipmout 3
+
+	log_test $? 0 "IPv6 compat mode on - nexthop change"
+
+	# set compat mode off
+	sysctl_nexthop_compat_mode_set 0 "IPv6"
+
+	run_cmd "$IP -6 ro del 2001:db8:101::1/128 nhid 122"
+
+	run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1"
+	run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1"
+	run_cmd "$IP nexthop add id 122 group 62/63"
+	ipmout=$(start_ip_monitor route)
+
+	run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 122"
+	# route add notification should not contain expanded nexthops
+	stop_ip_monitor $ipmout 1
+	log_test $? 0 "IPv6 compat mode off - route add notification"
+
+	# route dump should not contain expanded nexthops
+	check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 122 metric 1024"
+	log_test $? 0 "IPv6 compat mode off - route dump"
+
+	# change in nexthop group should not generate route notification
+	run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1"
+	ipmout=$(start_ip_monitor route)
+	run_cmd "$IP nexthop replace id 122 group 62/64"
+	stop_ip_monitor $ipmout 0
+	log_test $? 0 "IPv6 compat mode off - nexthop change"
+
+	# nexthop delete should not generate route notification
+	ipmout=$(start_ip_monitor route)
+	run_cmd "$IP nexthop del id 122"
+	stop_ip_monitor $ipmout 0
+	log_test $? 0 "IPv6 compat mode off - nexthop delete"
+
+	# set compat mode back on
+	sysctl_nexthop_compat_mode_set 1 "IPv6"
+}
+
+ipv4_compat_mode()
+{
+	local rc
+
+	echo
+	echo "IPv4 nexthop api compat mode"
+	echo "----------------------------"
+
+	sysctl_nexthop_compat_mode_check "IPv4"
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	run_cmd "$IP nexthop add id 21 via 172.16.1.2 dev veth1"
+	run_cmd "$IP nexthop add id 22 via 172.16.1.2 dev veth1"
+	run_cmd "$IP nexthop add id 122 group 21/22"
+	ipmout=$(start_ip_monitor route)
+
+	run_cmd "$IP ro add 172.16.101.1/32 nhid 122"
+	stop_ip_monitor $ipmout 3
+
+	# route add notification should contain expanded nexthops
+	log_test $? 0 "IPv4 compat mode on - route add notification"
+
+	# route dump should contain expanded nexthops
+	check_route "172.16.101.1" "172.16.101.1 nhid 122 nexthop via 172.16.1.2 dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1"
+	log_test $? 0 "IPv4 compat mode on - route dump"
+
+	# change in nexthop group should generate route notification
+	run_cmd "$IP nexthop add id 23 via 172.16.1.3 dev veth1"
+	ipmout=$(start_ip_monitor route)
+	run_cmd "$IP nexthop replace id 122 group 21/23"
+	stop_ip_monitor $ipmout 3
+	log_test $? 0 "IPv4 compat mode on - nexthop change"
+
+	sysctl_nexthop_compat_mode_set 0 "IPv4"
+
+	# cleanup
+	run_cmd "$IP ro del 172.16.101.1/32 nhid 122"
+
+	ipmout=$(start_ip_monitor route)
+	run_cmd "$IP ro add 172.16.101.1/32 nhid 122"
+	stop_ip_monitor $ipmout 1
+	# route add notification should not contain expanded nexthops
+	log_test $? 0 "IPv4 compat mode off - route add notification"
+
+	# route dump should not contain expanded nexthops
+	check_route "172.16.101.1" "172.16.101.1 nhid 122"
+	log_test $? 0 "IPv4 compat mode off - route dump"
+
+	# change in nexthop group should not generate route notification
+	ipmout=$(start_ip_monitor route)
+	run_cmd "$IP nexthop replace id 122 group 21/22"
+	stop_ip_monitor $ipmout 0
+	log_test $? 0 "IPv4 compat mode off - nexthop change"
+
+	# nexthop delete should not generate route notification
+	ipmout=$(start_ip_monitor route)
+	run_cmd "$IP nexthop del id 122"
+	stop_ip_monitor $ipmout 0
+	log_test $? 0 "IPv4 compat mode off - nexthop delete"
+
+	sysctl_nexthop_compat_mode_set 1 "IPv4"
+}
+
+ipv4_del_add_loop1()
+{
+	while :; do
+		$IP nexthop del id 100
+		$IP nexthop add id 100 via 172.16.1.2 dev veth1
+	done >/dev/null 2>&1
+}
+
+ipv4_grp_replace_loop()
+{
+	while :; do
+		$IP nexthop replace id 102 group 100/101
+	done >/dev/null 2>&1
+}
+
+ipv4_torture()
+{
+	local pid1
+	local pid2
+	local pid3
+	local pid4
+	local pid5
+
+	echo
+	echo "IPv4 runtime torture"
+	echo "--------------------"
+	if [ ! -x "$(command -v mausezahn)" ]; then
+		echo "SKIP: Could not run test; need mausezahn tool"
+		return
+	fi
+
+	run_cmd "$IP nexthop add id 100 via 172.16.1.2 dev veth1"
+	run_cmd "$IP nexthop add id 101 via 172.16.2.2 dev veth3"
+	run_cmd "$IP nexthop add id 102 group 100/101"
+	run_cmd "$IP route add 172.16.101.1 nhid 102"
+	run_cmd "$IP route add 172.16.101.2 nhid 102"
+
+	ipv4_del_add_loop1 &
+	pid1=$!
+	ipv4_grp_replace_loop &
+	pid2=$!
+	ip netns exec me ping -f 172.16.101.1 >/dev/null 2>&1 &
+	pid3=$!
+	ip netns exec me ping -f 172.16.101.2 >/dev/null 2>&1 &
+	pid4=$!
+	ip netns exec me mausezahn veth1 -B 172.16.101.2 -A 172.16.1.1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+	pid5=$!
+
+	sleep 300
+	kill -9 $pid1 $pid2 $pid3 $pid4 $pid5
+
+	# if we did not crash, success
+	log_test 0 0 "IPv4 torture test"
+}
+
 basic()
 {
 	echo
diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
index 155d48bd4d9e..f0e6be4c09e9 100644
--- a/tools/testing/selftests/net/forwarding/devlink_lib.sh
+++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
@@ -365,7 +365,9 @@ devlink_trap_group_stats_idle_test()
 devlink_trap_exception_test()
 {
 	local trap_name=$1; shift
-	local group_name=$1; shift
+	local group_name
+
+	group_name=$(devlink_trap_group_get $trap_name)
 
 	devlink_trap_stats_idle_test $trap_name
 	check_fail $? "Trap stats idle when packets should have been trapped"
@@ -377,9 +379,11 @@ devlink_trap_exception_test()
 devlink_trap_drop_test()
 {
 	local trap_name=$1; shift
-	local group_name=$1; shift
 	local dev=$1; shift
 	local handle=$1; shift
+	local group_name
+
+	group_name=$(devlink_trap_group_get $trap_name)
 
 	# 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
@@ -390,7 +394,6 @@ devlink_trap_drop_test()
 	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"
@@ -420,6 +423,29 @@ devlink_trap_drop_cleanup()
 	tc filter del dev $dev egress protocol $proto pref $pref handle $handle flower
 }
 
+devlink_trap_stats_test()
+{
+	local test_name=$1; shift
+	local trap_name=$1; shift
+	local send_one="$@"
+	local t0_packets
+	local t1_packets
+
+	RET=0
+
+	t0_packets=$(devlink_trap_rx_packets_get $trap_name)
+
+	$send_one && sleep 1
+
+	t1_packets=$(devlink_trap_rx_packets_get $trap_name)
+
+	if [[ $t1_packets -eq $t0_packets ]]; then
+		check_err 1 "Trap stats did not increase"
+	fi
+
+	log_test "$test_name"
+}
+
 devlink_trap_policers_num_get()
 {
 	devlink -j -p trap policer show | jq '.[]["'$DEVLINK_DEV'"] | length'
diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh
index 00797597fcf5..c33bfd7ba214 100644
--- a/tools/testing/selftests/net/forwarding/mirror_lib.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh
@@ -29,11 +29,9 @@ mirror_test()
 	local pref=$1; shift
 	local expect=$1; shift
 
-	local ping_timeout=$((PING_TIMEOUT * 5))
 	local t0=$(tc_rule_stats_get $dev $pref)
-	ip vrf exec $vrf_name \
-	   ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.5 -w $ping_timeout \
-		   &> /dev/null
+	$MZ $vrf_name ${sip:+-A $sip} -B $dip -a own -b bc -q \
+	    -c 10 -d 100ms -t icmp type=8
 	sleep 0.5
 	local t1=$(tc_rule_stats_get $dev $pref)
 	local delta=$((t1 - t0))
diff --git a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
index b50081855913..55eeacf59241 100755
--- a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
+++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
@@ -20,10 +20,14 @@
 
 ALL_TESTS="
 	ping_ipv4
+	ping_ipv6
 	test_ip_dsfield
 	test_ip_dscp
 	test_ip_ecn
 	test_ip_dscp_ecn
+	test_ip6_dsfield
+	test_ip6_dscp
+	test_ip6_ecn
 "
 
 NUM_NETIFS=4
@@ -107,6 +111,11 @@ ping_ipv4()
 	ping_test $h1 192.0.2.2
 }
 
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:1::2
+}
+
 do_test_pedit_dsfield_common()
 {
 	local pedit_locus=$1; shift
@@ -123,7 +132,12 @@ do_test_pedit_dsfield_common()
 	local pkts
 	pkts=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= 10" \
 			tc_rule_handle_stats_get "dev $h2 ingress" 101)
-	check_err $? "Expected to get 10 packets, but got $pkts."
+	check_err $? "Expected to get 10 packets on test probe, but got $pkts."
+
+	pkts=$(tc_rule_handle_stats_get "$pedit_locus" 101)
+	((pkts >= 10))
+	check_err $? "Expected to get 10 packets on pedit rule, but got $pkts."
+
 	log_test "$pedit_locus pedit $pedit_action"
 }
 
@@ -228,6 +242,63 @@ test_ip_dscp_ecn()
 	do_test_ip_dscp_ecn "dev $swp2 egress"
 }
 
+do_test_ip6_dsfield()
+{
+	local locus=$1; shift
+	local dsfield
+
+	for dsfield in 0 1 2 3 128 252 253 254 255; do
+		do_test_pedit_dsfield "$locus"				\
+				  "ip6 traffic_class set $dsfield"	\
+				  ipv6 "ip_tos $dsfield"		\
+				  "-6 -A 2001:db8:1::1 -B 2001:db8:1::2"
+	done
+}
+
+test_ip6_dsfield()
+{
+	do_test_ip6_dsfield "dev $swp1 ingress"
+	do_test_ip6_dsfield "dev $swp2 egress"
+}
+
+do_test_ip6_dscp()
+{
+	local locus=$1; shift
+	local dscp
+
+	for dscp in 0 1 2 3 32 61 62 63; do
+		do_test_pedit_dsfield "$locus"				       \
+			    "ip6 traffic_class set $((dscp << 2)) retain 0xfc" \
+			    ipv6 "ip_tos $(((dscp << 2) | 1))"		       \
+			    "-6 -A 2001:db8:1::1 -B 2001:db8:1::2"
+	done
+}
+
+test_ip6_dscp()
+{
+	do_test_ip6_dscp "dev $swp1 ingress"
+	do_test_ip6_dscp "dev $swp2 egress"
+}
+
+do_test_ip6_ecn()
+{
+	local locus=$1; shift
+	local ecn
+
+	for ecn in 0 1 2 3; do
+		do_test_pedit_dsfield "$locus"				\
+				"ip6 traffic_class set $ecn retain 0x3"	\
+				ipv6 "ip_tos $((124 | $ecn))"		\
+				"-6 -A 2001:db8:1::1 -B 2001:db8:1::2"
+	done
+}
+
+test_ip6_ecn()
+{
+	do_test_ip6_ecn "dev $swp1 ingress"
+	do_test_ip6_ecn "dev $swp2 egress"
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index 813d02d1939d..d9eca227136b 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -2,7 +2,8 @@
 # SPDX-License-Identifier: GPL-2.0
 
 ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
-	mirred_egress_mirror_test gact_trap_test"
+	mirred_egress_mirror_test matchall_mirred_egress_mirror_test \
+	gact_trap_test"
 NUM_NETIFS=4
 source tc_common.sh
 source lib.sh
@@ -50,6 +51,9 @@ switch_destroy()
 mirred_egress_test()
 {
 	local action=$1
+	local protocol=$2
+	local classifier=$3
+	local classifier_args=$4
 
 	RET=0
 
@@ -62,9 +66,9 @@ mirred_egress_test()
 	tc_check_packets "dev $h2 ingress" 101 1
 	check_fail $? "Matched without redirect rule inserted"
 
-	tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
-		$tcflags dst_ip 192.0.2.2 action mirred egress $action \
-		dev $swp2
+	tc filter add dev $swp1 ingress protocol $protocol pref 1 handle 101 \
+		$classifier $tcflags $classifier_args \
+		action mirred egress $action dev $swp2
 
 	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
 		-t ip -q
@@ -72,10 +76,11 @@ mirred_egress_test()
 	tc_check_packets "dev $h2 ingress" 101 1
 	check_err $? "Did not match incoming $action packet"
 
-	tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
+	tc filter del dev $swp1 ingress protocol $protocol pref 1 handle 101 \
+		$classifier
 	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
 
-	log_test "mirred egress $action ($tcflags)"
+	log_test "mirred egress $classifier $action ($tcflags)"
 }
 
 gact_drop_and_ok_test()
@@ -187,12 +192,17 @@ cleanup()
 
 mirred_egress_redirect_test()
 {
-	mirred_egress_test "redirect"
+	mirred_egress_test "redirect" "ip" "flower" "dst_ip 192.0.2.2"
 }
 
 mirred_egress_mirror_test()
 {
-	mirred_egress_test "mirror"
+	mirred_egress_test "mirror" "ip" "flower" "dst_ip 192.0.2.2"
+}
+
+matchall_mirred_egress_mirror_test()
+{
+	mirred_egress_test "mirror" "all" "matchall" ""
 }
 
 trap cleanup EXIT
diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c
index c0c9ecb891e1..f9ed749fd8c7 100644
--- a/tools/testing/selftests/net/ip_defrag.c
+++ b/tools/testing/selftests/net/ip_defrag.c
@@ -192,9 +192,9 @@ static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen,
 	}
 
 	res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
-	if (res < 0)
+	if (res < 0 && errno != EPERM)
 		error(1, errno, "send_fragment");
-	if (res != frag_len)
+	if (res >= 0 && res != frag_len)
 		error(1, 0, "send_fragment: %d vs %d", res, frag_len);
 
 	frag_counter++;
@@ -313,9 +313,9 @@ static void send_udp_frags(int fd_raw, struct sockaddr *addr,
 			iphdr->ip_len = htons(frag_len);
 		}
 		res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
-		if (res < 0)
+		if (res < 0 && errno != EPERM)
 			error(1, errno, "sendto overlap: %d", frag_len);
-		if (res != frag_len)
+		if (res >= 0 && res != frag_len)
 			error(1, 0, "sendto overlap: %d vs %d", (int)res, frag_len);
 		frag_counter++;
 	}
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 71a62e7e35b1..77c09cd339c3 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -67,6 +67,10 @@
 #	Same as pmtu_ipv4_vxlan4, but using a generic UDP IPv4/IPv6
 #	encapsulation (GUE) over IPv4/IPv6, instead of VXLAN
 #
+# - pmtu_ipv{4,6}_ipv{4,6}_exception
+#	Same as pmtu_ipv4_vxlan4, but using a IPv4/IPv6 tunnel over IPv4/IPv6,
+#	instead of VXLAN
+#
 # - pmtu_vti4_exception
 #	Set up vti tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is not
@@ -151,6 +155,10 @@ tests="
 	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_ipv4_ipv4_exception	IPv4 over IPv4: PMTU exceptions		1
+	pmtu_ipv6_ipv4_exception	IPv6 over IPv4: PMTU exceptions		1
+	pmtu_ipv4_ipv6_exception	IPv4 over IPv6: PMTU exceptions		1
+	pmtu_ipv6_ipv6_exception	IPv6 over IPv6: 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
@@ -363,6 +371,62 @@ setup_gue66() {
 	setup_fou_or_gue 6 6 gue
 }
 
+setup_ipvX_over_ipvY() {
+	inner=${1}
+	outer=${2}
+
+	if [ "${outer}" -eq 4 ]; then
+		a_addr="${prefix4}.${a_r1}.1"
+		b_addr="${prefix4}.${b_r1}.1"
+		if [ "${inner}" -eq 4 ]; then
+			type="ipip"
+			mode="ipip"
+		else
+			type="sit"
+			mode="ip6ip"
+		fi
+	else
+		a_addr="${prefix6}:${a_r1}::1"
+		b_addr="${prefix6}:${b_r1}::1"
+		type="ip6tnl"
+		if [ "${inner}" -eq 4 ]; then
+			mode="ipip6"
+		else
+			mode="ip6ip6"
+		fi
+	fi
+
+	run_cmd ${ns_a} ip link add ip_a type ${type} local ${a_addr} remote ${b_addr} mode ${mode} || return 2
+	run_cmd ${ns_b} ip link add ip_b type ${type} local ${b_addr} remote ${a_addr} mode ${mode}
+
+	run_cmd ${ns_a} ip link set ip_a up
+	run_cmd ${ns_b} ip link set ip_b up
+
+	if [ "${inner}" = "4" ]; then
+		run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ip_a
+		run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ip_b
+	else
+		run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ip_a
+		run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ip_b
+	fi
+}
+
+setup_ip4ip4() {
+	setup_ipvX_over_ipvY 4 4
+}
+
+setup_ip6ip4() {
+	setup_ipvX_over_ipvY 6 4
+}
+
+setup_ip4ip6() {
+	setup_ipvX_over_ipvY 4 6
+}
+
+setup_ip6ip6() {
+	setup_ipvX_over_ipvY 6 6
+}
+
 setup_namespaces() {
 	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
 		ip netns add ${n} || return 1
@@ -908,6 +972,64 @@ test_pmtu_ipv6_gue6_exception() {
 	test_pmtu_ipvX_over_fouY_or_gueY 6 6 gue
 }
 
+test_pmtu_ipvX_over_ipvY_exception() {
+	inner=${1}
+	outer=${2}
+	ll_mtu=4000
+
+	setup namespaces routing ip${inner}ip${outer} || return 2
+
+	trace "${ns_a}" ip_a         "${ns_b}"  ip_b  \
+	      "${ns_a}" veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_b}" veth_B-R1    "${ns_r1}" veth_R1-B
+
+	if [ ${inner} -eq 4 ]; then
+		ping=ping
+		dst=${tunnel4_b_addr}
+	else
+		ping=${ping6}
+		dst=${tunnel6_b_addr}
+	fi
+
+	if [ ${outer} -eq 4 ]; then
+		#                      IPv4 header
+		exp_mtu=$((${ll_mtu} - 20))
+	else
+		#                      IPv6 header   Option 4
+		exp_mtu=$((${ll_mtu} - 40          - 8))
+	fi
+
+	# Create route exception by exceeding link layer MTU
+	mtu "${ns_a}"  veth_A-R1 $((${ll_mtu} + 1000))
+	mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+	mtu "${ns_b}"  veth_B-R1 ${ll_mtu}
+	mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+	mtu "${ns_a}" ip_a $((${ll_mtu} + 1000)) || return
+	mtu "${ns_b}" ip_b $((${ll_mtu} + 1000)) || return
+	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst}
+
+	# Check that exception was created
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
+	check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ip${inner}ip${outer} interface"
+}
+
+test_pmtu_ipv4_ipv4_exception() {
+	test_pmtu_ipvX_over_ipvY_exception 4 4
+}
+
+test_pmtu_ipv6_ipv4_exception() {
+	test_pmtu_ipvX_over_ipvY_exception 6 4
+}
+
+test_pmtu_ipv4_ipv6_exception() {
+	test_pmtu_ipvX_over_ipvY_exception 4 6
+}
+
+test_pmtu_ipv6_ipv6_exception() {
+	test_pmtu_ipvX_over_ipvY_exception 6 6
+}
+
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
 	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 0ea44d975b6c..c5282e62df75 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -101,6 +101,21 @@ FIXTURE(tls)
 	bool notls;
 };
 
+FIXTURE_VARIANT(tls)
+{
+	unsigned int tls_version;
+};
+
+FIXTURE_VARIANT_ADD(tls, 12)
+{
+	.tls_version = TLS_1_2_VERSION,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13)
+{
+	.tls_version = TLS_1_3_VERSION,
+};
+
 FIXTURE_SETUP(tls)
 {
 	struct tls12_crypto_info_aes_gcm_128 tls12;
@@ -112,7 +127,7 @@ FIXTURE_SETUP(tls)
 	len = sizeof(addr);
 
 	memset(&tls12, 0, sizeof(tls12));
-	tls12.info.version = TLS_1_3_VERSION;
+	tls12.info.version = variant->tls_version;
 	tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
 
 	addr.sin_family = AF_INET;
@@ -733,7 +748,7 @@ TEST_F(tls, bidir)
 		struct tls12_crypto_info_aes_gcm_128 tls12;
 
 		memset(&tls12, 0, sizeof(tls12));
-		tls12.info.version = TLS_1_3_VERSION;
+		tls12.info.version = variant->tls_version;
 		tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
 
 		ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12,
@@ -1258,78 +1273,4 @@ TEST(keysizes) {
 	close(cfd);
 }
 
-TEST(tls12) {
-	int fd, cfd;
-	bool notls;
-
-	struct tls12_crypto_info_aes_gcm_128 tls12;
-	struct sockaddr_in addr;
-	socklen_t len;
-	int sfd, ret;
-
-	notls = false;
-	len = sizeof(addr);
-
-	memset(&tls12, 0, sizeof(tls12));
-	tls12.info.version = TLS_1_2_VERSION;
-	tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
-
-	addr.sin_family = AF_INET;
-	addr.sin_addr.s_addr = htonl(INADDR_ANY);
-	addr.sin_port = 0;
-
-	fd = socket(AF_INET, SOCK_STREAM, 0);
-	sfd = socket(AF_INET, SOCK_STREAM, 0);
-
-	ret = bind(sfd, &addr, sizeof(addr));
-	ASSERT_EQ(ret, 0);
-	ret = listen(sfd, 10);
-	ASSERT_EQ(ret, 0);
-
-	ret = getsockname(sfd, &addr, &len);
-	ASSERT_EQ(ret, 0);
-
-	ret = connect(fd, &addr, sizeof(addr));
-	ASSERT_EQ(ret, 0);
-
-	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
-	if (ret != 0) {
-		notls = true;
-		printf("Failure setting TCP_ULP, testing without tls\n");
-	}
-
-	if (!notls) {
-		ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12,
-				 sizeof(tls12));
-		ASSERT_EQ(ret, 0);
-	}
-
-	cfd = accept(sfd, &addr, &len);
-	ASSERT_GE(cfd, 0);
-
-	if (!notls) {
-		ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls",
-				 sizeof("tls"));
-		ASSERT_EQ(ret, 0);
-
-		ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12,
-				 sizeof(tls12));
-		ASSERT_EQ(ret, 0);
-	}
-
-	close(sfd);
-
-	char const *test_str = "test_read";
-	int send_len = 10;
-	char buf[10];
-
-	send_len = strlen(test_str) + 1;
-	EXPECT_EQ(send(fd, test_str, send_len, 0), send_len);
-	EXPECT_NE(recv(cfd, buf, send_len, 0), -1);
-	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
-
-	close(fd);
-	close(cfd);
-}
-
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/vrf-xfrm-tests.sh b/tools/testing/selftests/net/vrf-xfrm-tests.sh
new file mode 100755
index 000000000000..184da81f554f
--- /dev/null
+++ b/tools/testing/selftests/net/vrf-xfrm-tests.sh
@@ -0,0 +1,436 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Various combinations of VRF with xfrms and qdisc.
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+PAUSE_ON_FAIL=no
+VERBOSE=0
+ret=0
+
+HOST1_4=192.168.1.1
+HOST2_4=192.168.1.2
+HOST1_6=2001:db8:1::1
+HOST2_6=2001:db8:1::2
+
+XFRM1_4=10.0.1.1
+XFRM2_4=10.0.1.2
+XFRM1_6=fc00:1000::1
+XFRM2_6=fc00:1000::2
+IF_ID=123
+
+VRF=red
+TABLE=300
+
+AUTH_1=0xd94fcfea65fddf21dc6e0d24a0253508
+AUTH_2=0xdc6e0d24a0253508d94fcfea65fddf21
+ENC_1=0xfc46c20f8048be9725930ff3fb07ac2a91f0347dffeacf62
+ENC_2=0x3fb07ac2a91f0347dffeacf62fc46c20f8048be9725930ff
+SPI_1=0x02122b77
+SPI_2=0x2b770212
+
+which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
+
+################################################################################
+#
+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
+			[ "$a" = "q" ] && exit 1
+		fi
+	fi
+}
+
+run_cmd_host1()
+{
+	local cmd="$*"
+	local out
+	local rc
+
+	if [ "$VERBOSE" = "1" ]; then
+		printf "    COMMAND: $cmd\n"
+	fi
+
+	out=$(eval ip netns exec host1 $cmd 2>&1)
+	rc=$?
+	if [ "$VERBOSE" = "1" ]; then
+		if [ -n "$out" ]; then
+			echo
+			echo "    $out"
+		fi
+		echo
+	fi
+
+	return $rc
+}
+
+################################################################################
+# create namespaces for hosts and sws
+
+create_vrf()
+{
+	local ns=$1
+	local vrf=$2
+	local table=$3
+
+	if [ -n "${ns}" ]; then
+		ns="-netns ${ns}"
+	fi
+
+	ip ${ns} link add ${vrf} type vrf table ${table}
+	ip ${ns} link set ${vrf} up
+	ip ${ns} route add vrf ${vrf} unreachable default metric 8192
+	ip ${ns} -6 route add vrf ${vrf} unreachable default metric 8192
+
+	ip ${ns} addr add 127.0.0.1/8 dev ${vrf}
+	ip ${ns} -6 addr add ::1 dev ${vrf} nodad
+
+	ip ${ns} ru del pref 0
+	ip ${ns} ru add pref 32765 from all lookup local
+	ip ${ns} -6 ru del pref 0
+	ip ${ns} -6 ru add pref 32765 from all lookup local
+}
+
+create_ns()
+{
+	local ns=$1
+	local addr=$2
+	local addr6=$3
+
+	[ -z "${addr}" ] && addr="-"
+	[ -z "${addr6}" ] && addr6="-"
+
+	ip netns add ${ns}
+
+	ip -netns ${ns} link set lo up
+	if [ "${addr}" != "-" ]; then
+		ip -netns ${ns} addr add dev lo ${addr}
+	fi
+	if [ "${addr6}" != "-" ]; then
+		ip -netns ${ns} -6 addr add dev lo ${addr6}
+	fi
+
+	ip -netns ${ns} ro add unreachable default metric 8192
+	ip -netns ${ns} -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=$8
+	local ns1arg
+	local ns2arg
+
+	if [ -n "${ns1}" ]; then
+		ns1arg="-netns ${ns1}"
+	fi
+	if [ -n "${ns2}" ]; then
+		ns2arg="-netns ${ns2}"
+	fi
+
+	ip ${ns1arg} li add ${ns1_dev} type veth peer name tmp
+	ip ${ns1arg} li set ${ns1_dev} up
+	ip ${ns1arg} li set tmp netns ${ns2} name ${ns2_dev}
+	ip ${ns2arg} li set ${ns2_dev} up
+
+	if [ "${ns1_addr}" != "-" ]; then
+		ip ${ns1arg} addr add dev ${ns1_dev} ${ns1_addr}
+		ip ${ns2arg} addr add dev ${ns2_dev} ${ns2_addr}
+	fi
+
+	if [ "${ns1_addr6}" != "-" ]; then
+		ip ${ns1arg} addr add dev ${ns1_dev} ${ns1_addr6} nodad
+		ip ${ns2arg} addr add dev ${ns2_dev} ${ns2_addr6} nodad
+	fi
+}
+
+################################################################################
+
+cleanup()
+{
+	ip netns del host1
+	ip netns del host2
+}
+
+setup()
+{
+	create_ns "host1"
+	create_ns "host2"
+
+	connect_ns "host1" eth0 ${HOST1_4}/24 ${HOST1_6}/64 \
+	           "host2" eth0 ${HOST2_4}/24 ${HOST2_6}/64
+
+	create_vrf "host1" ${VRF} ${TABLE}
+	ip -netns host1 link set dev eth0 master ${VRF}
+}
+
+cleanup_xfrm()
+{
+	for ns in host1 host2
+	do
+		for x in state policy
+		do
+			ip -netns ${ns} xfrm ${x} flush
+			ip -6 -netns ${ns} xfrm ${x} flush
+		done
+	done
+}
+
+setup_xfrm()
+{
+	local h1_4=$1
+	local h2_4=$2
+	local h1_6=$3
+	local h2_6=$4
+	local devarg="$5"
+
+	#
+	# policy
+	#
+
+	# host1 - IPv4 out
+	ip -netns host1 xfrm policy add \
+	  src ${h1_4} dst ${h2_4} ${devarg} dir out \
+	  tmpl src ${HOST1_4} dst ${HOST2_4} proto esp mode tunnel
+
+	# host2 - IPv4 in
+	ip -netns host2 xfrm policy add \
+	  src ${h1_4} dst ${h2_4} dir in \
+	  tmpl src ${HOST1_4} dst ${HOST2_4} proto esp mode tunnel
+
+	# host1 - IPv4 in
+	ip -netns host1 xfrm policy add \
+	  src ${h2_4} dst ${h1_4} ${devarg} dir in \
+	  tmpl src ${HOST2_4} dst ${HOST1_4} proto esp mode tunnel
+
+	# host2 - IPv4 out
+	ip -netns host2 xfrm policy add \
+	  src ${h2_4} dst ${h1_4} dir out \
+	  tmpl src ${HOST2_4} dst ${HOST1_4} proto esp mode tunnel
+
+
+	# host1 - IPv6 out
+	ip -6 -netns host1 xfrm policy add \
+	  src ${h1_6} dst ${h2_6} ${devarg} dir out \
+	  tmpl src ${HOST1_6} dst ${HOST2_6} proto esp mode tunnel
+
+	# host2 - IPv6 in
+	ip -6 -netns host2 xfrm policy add \
+	  src ${h1_6} dst ${h2_6} dir in \
+	  tmpl src ${HOST1_6} dst ${HOST2_6} proto esp mode tunnel
+
+	# host1 - IPv6 in
+	ip -6 -netns host1 xfrm policy add \
+	  src ${h2_6} dst ${h1_6} ${devarg} dir in \
+	  tmpl src ${HOST2_6} dst ${HOST1_6} proto esp mode tunnel
+
+	# host2 - IPv6 out
+	ip -6 -netns host2 xfrm policy add \
+	  src ${h2_6} dst ${h1_6} dir out \
+	  tmpl src ${HOST2_6} dst ${HOST1_6} proto esp mode tunnel
+
+	#
+	# state
+	#
+	ip -netns host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \
+	    proto esp spi ${SPI_1} reqid 0 mode tunnel \
+	    replay-window 4 replay-oseq 0x4 \
+	    auth-trunc 'hmac(md5)' ${AUTH_1} 96 \
+	    enc 'cbc(des3_ede)' ${ENC_1} \
+	    sel src ${h1_4} dst ${h2_4} ${devarg}
+
+	ip -netns host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \
+	    proto esp spi ${SPI_1} reqid 0 mode tunnel \
+	    replay-window 4 replay-oseq 0x4 \
+	    auth-trunc 'hmac(md5)' ${AUTH_1} 96 \
+	    enc 'cbc(des3_ede)' ${ENC_1} \
+	    sel src ${h1_4} dst ${h2_4}
+
+
+	ip -netns host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \
+	    proto esp spi ${SPI_2} reqid 0 mode tunnel \
+	    replay-window 4 replay-oseq 0x4 \
+	    auth-trunc 'hmac(md5)' ${AUTH_2} 96 \
+	    enc 'cbc(des3_ede)' ${ENC_2} \
+	    sel src ${h2_4} dst ${h1_4} ${devarg}
+
+	ip -netns host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \
+	    proto esp spi ${SPI_2} reqid 0 mode tunnel \
+	    replay-window 4 replay-oseq 0x4 \
+	    auth-trunc 'hmac(md5)' ${AUTH_2} 96 \
+	    enc 'cbc(des3_ede)' ${ENC_2} \
+	    sel src ${h2_4} dst ${h1_4}
+
+
+	ip -6 -netns host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \
+	    proto esp spi ${SPI_1} reqid 0 mode tunnel \
+	    replay-window 4 replay-oseq 0x4 \
+	    auth-trunc 'hmac(md5)' ${AUTH_1} 96 \
+	    enc 'cbc(des3_ede)' ${ENC_1} \
+	    sel src ${h1_6} dst ${h2_6} ${devarg}
+
+	ip -6 -netns host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \
+	    proto esp spi ${SPI_1} reqid 0 mode tunnel \
+	    replay-window 4 replay-oseq 0x4 \
+	    auth-trunc 'hmac(md5)' ${AUTH_1} 96 \
+	    enc 'cbc(des3_ede)' ${ENC_1} \
+	    sel src ${h1_6} dst ${h2_6}
+
+
+	ip -6 -netns host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \
+	    proto esp spi ${SPI_2} reqid 0 mode tunnel \
+	    replay-window 4 replay-oseq 0x4 \
+	    auth-trunc 'hmac(md5)' ${AUTH_2} 96 \
+	    enc 'cbc(des3_ede)' ${ENC_2} \
+	    sel src ${h2_6} dst ${h1_6} ${devarg}
+
+	ip -6 -netns host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \
+	    proto esp spi ${SPI_2} reqid 0 mode tunnel \
+	    replay-window 4 replay-oseq 0x4 \
+	    auth-trunc 'hmac(md5)' ${AUTH_2} 96 \
+	    enc 'cbc(des3_ede)' ${ENC_2} \
+	    sel src ${h2_6} dst ${h1_6}
+}
+
+cleanup_xfrm_dev()
+{
+	ip -netns host1 li del xfrm0
+	ip -netns host2 addr del ${XFRM2_4}/24 dev eth0
+	ip -netns host2 addr del ${XFRM2_6}/64 dev eth0
+}
+
+setup_xfrm_dev()
+{
+	local vrfarg="vrf ${VRF}"
+
+	ip -netns host1 li add type xfrm dev eth0 if_id ${IF_ID}
+	ip -netns host1 li set xfrm0 ${vrfarg} up
+	ip -netns host1 addr add ${XFRM1_4}/24 dev xfrm0
+	ip -netns host1 addr add ${XFRM1_6}/64 dev xfrm0
+
+	ip -netns host2 addr add ${XFRM2_4}/24 dev eth0
+	ip -netns host2 addr add ${XFRM2_6}/64 dev eth0
+
+	setup_xfrm ${XFRM1_4} ${XFRM2_4} ${XFRM1_6} ${XFRM2_6} "if_id ${IF_ID}"
+}
+
+run_tests()
+{
+	cleanup_xfrm
+
+	# no IPsec
+	run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4}
+	log_test $? 0 "IPv4 no xfrm policy"
+	run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6}
+	log_test $? 0 "IPv6 no xfrm policy"
+
+	# xfrm without VRF in sel
+	setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6}
+	run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4}
+	log_test $? 0 "IPv4 xfrm policy based on address"
+	run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6}
+	log_test $? 0 "IPv6 xfrm policy based on address"
+	cleanup_xfrm
+
+	# xfrm with VRF in sel
+	# Known failure: ipv4 resets the flow oif after the lookup. Fix is
+	# not straightforward.
+	# setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6} "dev ${VRF}"
+	# run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4}
+	# log_test $? 0 "IPv4 xfrm policy with VRF in selector"
+	run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6}
+	log_test $? 0 "IPv6 xfrm policy with VRF in selector"
+	cleanup_xfrm
+
+	# xfrm with enslaved device in sel
+	# Known failures: combined with the above, __xfrm{4,6}_selector_match
+	# needs to consider both l3mdev and enslaved device index.
+	# setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6} "dev eth0"
+	# run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4}
+	# log_test $? 0 "IPv4 xfrm policy with enslaved device in selector"
+	# run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6}
+	# log_test $? 0 "IPv6 xfrm policy with enslaved device in selector"
+	# cleanup_xfrm
+
+	# xfrm device
+	setup_xfrm_dev
+	run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${XFRM2_4}
+	log_test $? 0 "IPv4 xfrm policy with xfrm device"
+	run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${XFRM2_6}
+	log_test $? 0 "IPv6 xfrm policy with xfrm device"
+	cleanup_xfrm_dev
+}
+
+################################################################################
+# usage
+
+usage()
+{
+        cat <<EOF
+usage: ${0##*/} OPTS
+
+        -p          Pause on fail
+        -v          verbose mode (show commands and output)
+
+done
+EOF
+}
+
+################################################################################
+# main
+
+while getopts :pv o
+do
+	case $o in
+		p) PAUSE_ON_FAIL=yes;;
+		v) VERBOSE=$(($VERBOSE + 1));;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
+cleanup 2>/dev/null
+setup
+
+echo
+echo "No qdisc on VRF device"
+run_tests
+
+run_cmd_host1 tc qdisc add dev ${VRF} root netem delay 100ms
+echo
+echo "netem qdisc on VRF device"
+run_tests
+
+printf "\nTests passed: %3d\n" ${nsuccess}
+printf "Tests failed: %3d\n"   ${nfail}
+
+exit $ret