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

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

39 files changed, 6296 insertions, 64 deletions

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index c612d6e38c62..128e548aa377 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -1,9 +1,14 @@
 msg_zerocopy
 socket
 psock_fanout
+psock_snd
 psock_tpacket
 reuseport_bpf
 reuseport_bpf_cpu
 reuseport_bpf_numa
 reuseport_dualstack
 reuseaddr_conflict
+tcp_mmap
+udpgso
+udpgso_bench_rx
+udpgso_bench_tx
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 3ff81a478dbe..663e11e85727 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,13 +5,18 @@ CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
 CFLAGS += -I../../../../usr/include/
 
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
-TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh
+TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh
+TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
+TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
+TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
 
 include ../lib.mk
 
 $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma
+$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread
+$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
new file mode 100755
index 000000000000..d4cfb6a7a086
--- /dev/null
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -0,0 +1,248 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test is for checking IPv4 and IPv6 FIB rules API
+
+ret=0
+
+PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+IP="ip -netns testns"
+
+RTABLE=100
+GW_IP4=192.51.100.2
+SRC_IP=192.51.100.3
+GW_IP6=2001:db8:1::2
+SRC_IP6=2001:db8:1::3
+
+DEV_ADDR=192.51.100.1
+DEV=dummy0
+
+log_test()
+{
+	local rc=$1
+	local expected=$2
+	local msg="$3"
+
+	if [ ${rc} -eq ${expected} ]; then
+		nsuccess=$((nsuccess+1))
+		printf "\n    TEST: %-50s  [ OK ]\n" "${msg}"
+	else
+		nfail=$((nfail+1))
+		printf "\n    TEST: %-50s  [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
+}
+
+log_section()
+{
+	echo
+	echo "######################################################################"
+	echo "TEST SECTION: $*"
+	echo "######################################################################"
+}
+
+setup()
+{
+	set -e
+	ip netns add testns
+	$IP link set dev lo up
+
+	$IP link add dummy0 type dummy
+	$IP link set dev dummy0 up
+	$IP address add 198.51.100.1/24 dev dummy0
+	$IP -6 address add 2001:db8:1::1/64 dev dummy0
+
+	set +e
+}
+
+cleanup()
+{
+	$IP link del dev dummy0 &> /dev/null
+	ip netns del testns
+}
+
+fib_check_iproute_support()
+{
+	ip rule help 2>&1 | grep -q $1
+	if [ $? -ne 0 ]; then
+		echo "SKIP: iproute2 iprule too old, missing $1 match"
+		return 1
+	fi
+
+	ip route get help 2>&1 | grep -q $2
+	if [ $? -ne 0 ]; then
+		echo "SKIP: iproute2 get route too old, missing $2 match"
+		return 1
+	fi
+
+	return 0
+}
+
+fib_rule6_del()
+{
+	$IP -6 rule del $1
+	log_test $? 0 "rule6 del $1"
+}
+
+fib_rule6_del_by_pref()
+{
+	pref=$($IP -6 rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1)
+	$IP -6 rule del pref $pref
+}
+
+fib_rule6_test_match_n_redirect()
+{
+	local match="$1"
+	local getmatch="$2"
+
+	$IP -6 rule add $match table $RTABLE
+	$IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE"
+	log_test $? 0 "rule6 check: $1"
+
+	fib_rule6_del_by_pref "$match"
+	log_test $? 0 "rule6 del by pref: $match"
+}
+
+fib_rule6_test()
+{
+	# setup the fib rule redirect route
+	$IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink
+
+	match="oif $DEV"
+	fib_rule6_test_match_n_redirect "$match" "$match" "oif redirect to table"
+
+	match="from $SRC_IP6 iif $DEV"
+	fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table"
+
+	match="tos 0x10"
+	fib_rule6_test_match_n_redirect "$match" "$match" "tos redirect to table"
+
+	match="fwmark 0x64"
+	getmatch="mark 0x64"
+	fib_rule6_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table"
+
+	fib_check_iproute_support "uidrange" "uid"
+	if [ $? -eq 0 ]; then
+		match="uidrange 100-100"
+		getmatch="uid 100"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" "uid redirect to table"
+	fi
+
+	fib_check_iproute_support "sport" "sport"
+	if [ $? -eq 0 ]; then
+		match="sport 666 dport 777"
+		fib_rule6_test_match_n_redirect "$match" "$match" "sport and dport redirect to table"
+	fi
+
+	fib_check_iproute_support "ipproto" "ipproto"
+	if [ $? -eq 0 ]; then
+		match="ipproto tcp"
+		fib_rule6_test_match_n_redirect "$match" "$match" "ipproto match"
+	fi
+
+	fib_check_iproute_support "ipproto" "ipproto"
+	if [ $? -eq 0 ]; then
+		match="ipproto icmp"
+		fib_rule6_test_match_n_redirect "$match" "$match" "ipproto icmp match"
+	fi
+}
+
+fib_rule4_del()
+{
+	$IP rule del $1
+	log_test $? 0 "del $1"
+}
+
+fib_rule4_del_by_pref()
+{
+	pref=$($IP rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1)
+	$IP rule del pref $pref
+}
+
+fib_rule4_test_match_n_redirect()
+{
+	local match="$1"
+	local getmatch="$2"
+
+	$IP rule add $match table $RTABLE
+	$IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE"
+	log_test $? 0 "rule4 check: $1"
+
+	fib_rule4_del_by_pref "$match"
+	log_test $? 0 "rule4 del by pref: $match"
+}
+
+fib_rule4_test()
+{
+	# setup the fib rule redirect route
+	$IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink
+
+	match="oif $DEV"
+	fib_rule4_test_match_n_redirect "$match" "$match" "oif redirect to table"
+
+	match="from $SRC_IP iif $DEV"
+	fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table"
+
+	match="tos 0x10"
+	fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table"
+
+	match="fwmark 0x64"
+	getmatch="mark 0x64"
+	fib_rule4_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table"
+
+	fib_check_iproute_support "uidrange" "uid"
+	if [ $? -eq 0 ]; then
+		match="uidrange 100-100"
+		getmatch="uid 100"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" "uid redirect to table"
+	fi
+
+	fib_check_iproute_support "sport" "sport"
+	if [ $? -eq 0 ]; then
+		match="sport 666 dport 777"
+		fib_rule4_test_match_n_redirect "$match" "$match" "sport and dport redirect to table"
+	fi
+
+	fib_check_iproute_support "ipproto" "ipproto"
+	if [ $? -eq 0 ]; then
+		match="ipproto tcp"
+		fib_rule4_test_match_n_redirect "$match" "$match" "ipproto tcp match"
+	fi
+
+	fib_check_iproute_support "ipproto" "ipproto"
+	if [ $? -eq 0 ]; then
+		match="ipproto icmp"
+		fib_rule4_test_match_n_redirect "$match" "$match" "ipproto icmp match"
+	fi
+}
+
+run_fibrule_tests()
+{
+	log_section "IPv4 fib rule"
+	fib_rule4_test
+	log_section "IPv6 fib rule"
+	fib_rule6_test
+}
+
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit 0
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+	echo "SKIP: Could not run test without ip tool"
+	exit 0
+fi
+
+# start clean
+cleanup &> /dev/null
+setup
+run_fibrule_tests
+cleanup
+
+exit $ret
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 5baac82b9287..78245d60d8bc 100755..100644
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -8,8 +8,11 @@ ret=0
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 
-VERBOSE=${VERBOSE:=0}
-PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+# all tests in this script. Can be overridden with -t option
+TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric"
+VERBOSE=0
+PAUSE_ON_FAIL=no
+PAUSE=no
 IP="ip -netns testns"
 
 log_test()
@@ -20,8 +23,10 @@ log_test()
 
 	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
@@ -30,6 +35,13 @@ log_test()
 			[ "$a" = "q" ] && exit 1
 		fi
 	fi
+
+	if [ "${PAUSE}" = "yes" ]; then
+		echo
+		echo "hit enter to continue, 'q' to quit"
+		read a
+		[ "$a" = "q" ] && exit 1
+	fi
 }
 
 setup()
@@ -565,20 +577,825 @@ fib_nexthop_test()
 }
 
 ################################################################################
-#
+# Tests on route add and replace
+
+run_cmd()
+{
+	local cmd="$1"
+	local out
+	local stderr="2>/dev/null"
+
+	if [ "$VERBOSE" = "1" ]; then
+		printf "    COMMAND: $cmd\n"
+		stderr=
+	fi
+
+	out=$(eval $cmd $stderr)
+	rc=$?
+	if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+		echo "    $out"
+	fi
+
+	[ "$VERBOSE" = "1" ] && echo
+
+	return $rc
+}
+
+# add route for a prefix, flushing any existing routes first
+# expected to be the first step of a test
+add_route6()
+{
+	local pfx="$1"
+	local nh="$2"
+	local out
+
+	if [ "$VERBOSE" = "1" ]; then
+		echo
+		echo "    ##################################################"
+		echo
+	fi
+
+	run_cmd "$IP -6 ro flush ${pfx}"
+	[ $? -ne 0 ] && exit 1
+
+	out=$($IP -6 ro ls match ${pfx})
+	if [ -n "$out" ]; then
+		echo "Failed to flush routes for prefix used for tests."
+		exit 1
+	fi
+
+	run_cmd "$IP -6 ro add ${pfx} ${nh}"
+	if [ $? -ne 0 ]; then
+		echo "Failed to add initial route for test."
+		exit 1
+	fi
+}
+
+# add initial route - used in replace route tests
+add_initial_route6()
+{
+	add_route6 "2001:db8:104::/64" "$1"
+}
+
+check_route6()
+{
+	local pfx="2001:db8:104::/64"
+	local expected="$1"
+	local out
+	local rc=0
+
+	out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//')
+	[ "${out}" = "${expected}" ] && return 0
+
+	if [ -z "${out}" ]; then
+		if [ "$VERBOSE" = "1" ]; then
+			printf "\nNo route entry found\n"
+			printf "Expected:\n"
+			printf "    ${expected}\n"
+		fi
+		return 1
+	fi
+
+	# tricky way to convert output to 1-line without ip's
+	# messy '\'; this drops all extra white space
+	out=$(echo ${out})
+	if [ "${out}" != "${expected}" ]; then
+		rc=1
+		if [ "${VERBOSE}" = "1" ]; then
+			printf "    Unexpected route entry. Have:\n"
+			printf "        ${out}\n"
+			printf "    Expected:\n"
+			printf "        ${expected}\n\n"
+		fi
+	fi
+
+	return $rc
+}
+
+route_cleanup()
+{
+	$IP li del red 2>/dev/null
+	$IP li del dummy1 2>/dev/null
+	$IP li del veth1 2>/dev/null
+	$IP li del veth3 2>/dev/null
+
+	cleanup &> /dev/null
+}
+
+route_setup()
+{
+	route_cleanup
+	setup
+
+	[ "${VERBOSE}" = "1" ] && set -x
+	set -e
+
+	$IP li add red up type vrf table 101
+	$IP li add veth1 type veth peer name veth2
+	$IP li add veth3 type veth peer name veth4
+
+	$IP li set veth1 up
+	$IP li set veth3 up
+	$IP li set veth2 vrf red up
+	$IP li set veth4 vrf red up
+	$IP li add dummy1 type dummy
+	$IP li set dummy1 vrf red up
+
+	$IP -6 addr add 2001:db8:101::1/64 dev veth1
+	$IP -6 addr add 2001:db8:101::2/64 dev veth2
+	$IP -6 addr add 2001:db8:103::1/64 dev veth3
+	$IP -6 addr add 2001:db8:103::2/64 dev veth4
+	$IP -6 addr add 2001:db8:104::1/64 dev dummy1
+
+	$IP addr add 172.16.101.1/24 dev veth1
+	$IP addr add 172.16.101.2/24 dev veth2
+	$IP addr add 172.16.103.1/24 dev veth3
+	$IP addr add 172.16.103.2/24 dev veth4
+	$IP addr add 172.16.104.1/24 dev dummy1
+
+	set +ex
+}
+
+# assumption is that basic add of a single path route works
+# otherwise just adding an address on an interface is broken
+ipv6_rt_add()
+{
+	local rc
+
+	echo
+	echo "IPv6 route add / append tests"
+
+	# route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::2"
+	log_test $? 2 "Attempt to add duplicate route - gw"
+
+	# route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro add 2001:db8:104::/64 dev veth3"
+	log_test $? 2 "Attempt to add duplicate route - dev only"
+
+	# route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
+	log_test $? 2 "Attempt to add duplicate route - reject route"
+
+	# iproute2 prepend only sets NLM_F_CREATE
+	# - adds a new route; does NOT convert existing route to ECMP
+	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2"
+	check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
+	log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)"
+
+	# route append with same prefix adds a new route
+	# - iproute2 sets NLM_F_CREATE | NLM_F_APPEND
+	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2"
+	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+	log_test $? 0 "Append nexthop to existing route - gw"
+
+	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
+	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1"
+	log_test $? 0 "Append nexthop to existing route - dev only"
+
+	# multipath route can not have a nexthop that is a reject route
+	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64"
+	log_test $? 2 "Append nexthop to existing route - reject route"
+
+	# reject route can not be converted to multipath route
+	run_cmd "$IP -6 ro flush 2001:db8:104::/64"
+	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
+	run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2"
+	log_test $? 2 "Append nexthop to existing reject route - gw"
+
+	run_cmd "$IP -6 ro flush 2001:db8:104::/64"
+	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
+	run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
+	log_test $? 2 "Append nexthop to existing reject route - dev only"
+
+	# insert mpath directly
+	add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	check_route6  "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+	log_test $? 0 "Add multipath route"
+
+	add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro add 2001:db8:104::/64 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	log_test $? 2 "Attempt to add duplicate multipath route"
+
+	# insert of a second route without append but different metric
+	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::2 metric 512"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::3 metric 256"
+		rc=$?
+	fi
+	log_test $rc 0 "Route add with different metrics"
+
+	run_cmd "$IP -6 ro del 2001:db8:104::/64 metric 512"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 "2001:db8:104::/64 via 2001:db8:103::3 dev veth3 metric 256 2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024"
+		rc=$?
+	fi
+	log_test $rc 0 "Route delete with metric"
+}
 
-fib_test()
+ipv6_rt_replace_single()
 {
-	if [ -n "$TEST" ]; then
-		eval $TEST
+	# single path with single path
+	#
+	add_initial_route6 "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:103::2"
+	check_route6 "2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
+	log_test $? 0 "Single path with single path"
+
+	# single path with multipath
+	#
+	add_initial_route6 "nexthop via 2001:db8:101::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::2"
+	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+	log_test $? 0 "Single path with multipath"
+
+	# single path with reject
+	#
+	add_initial_route6 "nexthop via 2001:db8:101::2"
+	run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
+	check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
+	log_test $? 0 "Single path with reject route"
+
+	# single path with single path using MULTIPATH attribute
+	#
+	add_initial_route6 "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:103::2"
+	check_route6 "2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
+	log_test $? 0 "Single path with single path via multipath attribute"
+
+	# route replace fails - invalid nexthop
+	add_initial_route6 "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:104::2"
+	if [ $? -eq 0 ]; then
+		# previous command is expected to fail so if it returns 0
+		# that means the test failed.
+		log_test 0 1 "Invalid nexthop"
 	else
-		fib_unreg_test
-		fib_down_test
-		fib_carrier_test
-		fib_nexthop_test
+		check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024"
+		log_test $? 0 "Invalid nexthop"
 	fi
+
+	# replace non-existent route
+	# - note use of change versus replace since ip adds NLM_F_CREATE
+	#   for replace
+	add_initial_route6 "via 2001:db8:101::2"
+	run_cmd "$IP -6 ro change 2001:db8:105::/64 via 2001:db8:101::2"
+	log_test $? 2 "Single path - replace of non-existent route"
+}
+
+ipv6_rt_replace_mpath()
+{
+	# multipath with multipath
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::3"
+	check_route6  "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::3 dev veth3 weight 1"
+	log_test $? 0 "Multipath with multipath"
+
+	# multipath with single
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:101::3"
+	check_route6  "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
+	log_test $? 0 "Multipath with single path"
+
+	# multipath with single
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3"
+	check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
+	log_test $? 0 "Multipath with single path via multipath attribute"
+
+	# multipath with reject
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
+	check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
+	log_test $? 0 "Multipath with reject route"
+
+	# route replace fails - invalid nexthop 1
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
+	check_route6  "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+	log_test $? 0 "Multipath - invalid first nexthop"
+
+	# route replace fails - invalid nexthop 2
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:113::3"
+	check_route6  "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+	log_test $? 0 "Multipath - invalid second nexthop"
+
+	# multipath non-existent route
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro change 2001:db8:105::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::3"
+	log_test $? 2 "Multipath - replace of non-existent route"
+}
+
+ipv6_rt_replace()
+{
+	echo
+	echo "IPv6 route replace tests"
+
+	ipv6_rt_replace_single
+	ipv6_rt_replace_mpath
+}
+
+ipv6_route_test()
+{
+	route_setup
+
+	ipv6_rt_add
+	ipv6_rt_replace
+
+	route_cleanup
 }
 
+ip_addr_metric_check()
+{
+	ip addr help 2>&1 | grep -q metric
+	if [ $? -ne 0 ]; then
+		echo "iproute2 command does not support metric for addresses. Skipping test"
+		return 1
+	fi
+
+	return 0
+}
+
+ipv6_addr_metric_test()
+{
+	local rc
+
+	echo
+	echo "IPv6 prefix route tests"
+
+	ip_addr_metric_check || return 1
+
+	setup
+
+	set -e
+	$IP li add dummy1 type dummy
+	$IP li add dummy2 type dummy
+	$IP li set dummy1 up
+	$IP li set dummy2 up
+
+	# default entry is metric 256
+	run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64"
+	run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64"
+	set +e
+
+	check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 256 2001:db8:104::/64 dev dummy2 proto kernel metric 256"
+	log_test $? 0 "Default metric"
+
+	set -e
+	run_cmd "$IP -6 addr flush dev dummy1"
+	run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64 metric 257"
+	set +e
+
+	check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 256 2001:db8:104::/64 dev dummy1 proto kernel metric 257"
+	log_test $? 0 "User specified metric on first device"
+
+	set -e
+	run_cmd "$IP -6 addr flush dev dummy2"
+	run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64 metric 258"
+	set +e
+
+	check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 257 2001:db8:104::/64 dev dummy2 proto kernel metric 258"
+	log_test $? 0 "User specified metric on second device"
+
+	run_cmd "$IP -6 addr del dev dummy1 2001:db8:104::1/64 metric 257"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 258"
+		rc=$?
+	fi
+	log_test $rc 0 "Delete of address on first device"
+
+	run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::2/64 metric 259"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259"
+		rc=$?
+	fi
+	log_test $rc 0 "Modify metric of address"
+
+	# verify prefix route removed on down
+	run_cmd "ip netns exec testns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
+	run_cmd "$IP li set dev dummy2 down"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 ""
+		rc=$?
+	fi
+	log_test $rc 0 "Prefix route removed on link down"
+
+	# verify prefix route re-inserted with assigned metric
+	run_cmd "$IP li set dev dummy2 up"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259"
+		rc=$?
+	fi
+	log_test $rc 0 "Prefix route with metric on link up"
+
+	$IP li del dummy1
+	$IP li del dummy2
+	cleanup
+}
+
+# add route for a prefix, flushing any existing routes first
+# expected to be the first step of a test
+add_route()
+{
+	local pfx="$1"
+	local nh="$2"
+	local out
+
+	if [ "$VERBOSE" = "1" ]; then
+		echo
+		echo "    ##################################################"
+		echo
+	fi
+
+	run_cmd "$IP ro flush ${pfx}"
+	[ $? -ne 0 ] && exit 1
+
+	out=$($IP ro ls match ${pfx})
+	if [ -n "$out" ]; then
+		echo "Failed to flush routes for prefix used for tests."
+		exit 1
+	fi
+
+	run_cmd "$IP ro add ${pfx} ${nh}"
+	if [ $? -ne 0 ]; then
+		echo "Failed to add initial route for test."
+		exit 1
+	fi
+}
+
+# add initial route - used in replace route tests
+add_initial_route()
+{
+	add_route "172.16.104.0/24" "$1"
+}
+
+check_route()
+{
+	local pfx="172.16.104.0/24"
+	local expected="$1"
+	local out
+	local rc=0
+
+	out=$($IP ro ls match ${pfx})
+	[ "${out}" = "${expected}" ] && return 0
+
+	if [ -z "${out}" ]; then
+		if [ "$VERBOSE" = "1" ]; then
+			printf "\nNo route entry found\n"
+			printf "Expected:\n"
+			printf "    ${expected}\n"
+		fi
+		return 1
+	fi
+
+	# tricky way to convert output to 1-line without ip's
+	# messy '\'; this drops all extra white space
+	out=$(echo ${out})
+	if [ "${out}" != "${expected}" ]; then
+		rc=1
+		if [ "${VERBOSE}" = "1" ]; then
+			printf "    Unexpected route entry. Have:\n"
+			printf "        ${out}\n"
+			printf "    Expected:\n"
+			printf "        ${expected}\n\n"
+		fi
+	fi
+
+	return $rc
+}
+
+# assumption is that basic add of a single path route works
+# otherwise just adding an address on an interface is broken
+ipv4_rt_add()
+{
+	local rc
+
+	echo
+	echo "IPv4 route add / append tests"
+
+	# route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+	add_route "172.16.104.0/24" "via 172.16.101.2"
+	run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.2"
+	log_test $? 2 "Attempt to add duplicate route - gw"
+
+	# route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+	add_route "172.16.104.0/24" "via 172.16.101.2"
+	run_cmd "$IP ro add 172.16.104.0/24 dev veth3"
+	log_test $? 2 "Attempt to add duplicate route - dev only"
+
+	# route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+	add_route "172.16.104.0/24" "via 172.16.101.2"
+	run_cmd "$IP ro add unreachable 172.16.104.0/24"
+	log_test $? 2 "Attempt to add duplicate route - reject route"
+
+	# iproute2 prepend only sets NLM_F_CREATE
+	# - adds a new route; does NOT convert existing route to ECMP
+	add_route "172.16.104.0/24" "via 172.16.101.2"
+	run_cmd "$IP ro prepend 172.16.104.0/24 via 172.16.103.2"
+	check_route "172.16.104.0/24 via 172.16.103.2 dev veth3 172.16.104.0/24 via 172.16.101.2 dev veth1"
+	log_test $? 0 "Add new nexthop for existing prefix"
+
+	# route append with same prefix adds a new route
+	# - iproute2 sets NLM_F_CREATE | NLM_F_APPEND
+	add_route "172.16.104.0/24" "via 172.16.101.2"
+	run_cmd "$IP ro append 172.16.104.0/24 via 172.16.103.2"
+	check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 via 172.16.103.2 dev veth3"
+	log_test $? 0 "Append nexthop to existing route - gw"
+
+	add_route "172.16.104.0/24" "via 172.16.101.2"
+	run_cmd "$IP ro append 172.16.104.0/24 dev veth3"
+	check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 dev veth3 scope link"
+	log_test $? 0 "Append nexthop to existing route - dev only"
+
+	add_route "172.16.104.0/24" "via 172.16.101.2"
+	run_cmd "$IP ro append unreachable 172.16.104.0/24"
+	check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 unreachable 172.16.104.0/24"
+	log_test $? 0 "Append nexthop to existing route - reject route"
+
+	run_cmd "$IP ro flush 172.16.104.0/24"
+	run_cmd "$IP ro add unreachable 172.16.104.0/24"
+	run_cmd "$IP ro append 172.16.104.0/24 via 172.16.103.2"
+	check_route "unreachable 172.16.104.0/24 172.16.104.0/24 via 172.16.103.2 dev veth3"
+	log_test $? 0 "Append nexthop to existing reject route - gw"
+
+	run_cmd "$IP ro flush 172.16.104.0/24"
+	run_cmd "$IP ro add unreachable 172.16.104.0/24"
+	run_cmd "$IP ro append 172.16.104.0/24 dev veth3"
+	check_route "unreachable 172.16.104.0/24 172.16.104.0/24 dev veth3 scope link"
+	log_test $? 0 "Append nexthop to existing reject route - dev only"
+
+	# insert mpath directly
+	add_route "172.16.104.0/24" "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	check_route  "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+	log_test $? 0 "add multipath route"
+
+	add_route "172.16.104.0/24" "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	run_cmd "$IP ro add 172.16.104.0/24 nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	log_test $? 2 "Attempt to add duplicate multipath route"
+
+	# insert of a second route without append but different metric
+	add_route "172.16.104.0/24" "via 172.16.101.2"
+	run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.2 metric 512"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.3 metric 256"
+		rc=$?
+	fi
+	log_test $rc 0 "Route add with different metrics"
+
+	run_cmd "$IP ro del 172.16.104.0/24 metric 512"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 via 172.16.103.3 dev veth3 metric 256"
+		rc=$?
+	fi
+	log_test $rc 0 "Route delete with metric"
+}
+
+ipv4_rt_replace_single()
+{
+	# single path with single path
+	#
+	add_initial_route "via 172.16.101.2"
+	run_cmd "$IP ro replace 172.16.104.0/24 via 172.16.103.2"
+	check_route "172.16.104.0/24 via 172.16.103.2 dev veth3"
+	log_test $? 0 "Single path with single path"
+
+	# single path with multipath
+	#
+	add_initial_route "nexthop via 172.16.101.2"
+	run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.2"
+	check_route "172.16.104.0/24 nexthop via 172.16.101.3 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+	log_test $? 0 "Single path with multipath"
+
+	# single path with reject
+	#
+	add_initial_route "nexthop via 172.16.101.2"
+	run_cmd "$IP ro replace unreachable 172.16.104.0/24"
+	check_route "unreachable 172.16.104.0/24"
+	log_test $? 0 "Single path with reject route"
+
+	# single path with single path using MULTIPATH attribute
+	#
+	add_initial_route "via 172.16.101.2"
+	run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.103.2"
+	check_route "172.16.104.0/24 via 172.16.103.2 dev veth3"
+	log_test $? 0 "Single path with single path via multipath attribute"
+
+	# route replace fails - invalid nexthop
+	add_initial_route "via 172.16.101.2"
+	run_cmd "$IP ro replace 172.16.104.0/24 via 2001:db8:104::2"
+	if [ $? -eq 0 ]; then
+		# previous command is expected to fail so if it returns 0
+		# that means the test failed.
+		log_test 0 1 "Invalid nexthop"
+	else
+		check_route "172.16.104.0/24 via 172.16.101.2 dev veth1"
+		log_test $? 0 "Invalid nexthop"
+	fi
+
+	# replace non-existent route
+	# - note use of change versus replace since ip adds NLM_F_CREATE
+	#   for replace
+	add_initial_route "via 172.16.101.2"
+	run_cmd "$IP ro change 172.16.105.0/24 via 172.16.101.2"
+	log_test $? 2 "Single path - replace of non-existent route"
+}
+
+ipv4_rt_replace_mpath()
+{
+	# multipath with multipath
+	add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.3"
+	check_route  "172.16.104.0/24 nexthop via 172.16.101.3 dev veth1 weight 1 nexthop via 172.16.103.3 dev veth3 weight 1"
+	log_test $? 0 "Multipath with multipath"
+
+	# multipath with single
+	add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	run_cmd "$IP ro replace 172.16.104.0/24 via 172.16.101.3"
+	check_route  "172.16.104.0/24 via 172.16.101.3 dev veth1"
+	log_test $? 0 "Multipath with single path"
+
+	# multipath with single
+	add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3"
+	check_route "172.16.104.0/24 via 172.16.101.3 dev veth1"
+	log_test $? 0 "Multipath with single path via multipath attribute"
+
+	# multipath with reject
+	add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	run_cmd "$IP ro replace unreachable 172.16.104.0/24"
+	check_route "unreachable 172.16.104.0/24"
+	log_test $? 0 "Multipath with reject route"
+
+	# route replace fails - invalid nexthop 1
+	add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.111.3 nexthop via 172.16.103.3"
+	check_route  "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+	log_test $? 0 "Multipath - invalid first nexthop"
+
+	# route replace fails - invalid nexthop 2
+	add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.113.3"
+	check_route  "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+	log_test $? 0 "Multipath - invalid second nexthop"
+
+	# multipath non-existent route
+	add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	run_cmd "$IP ro change 172.16.105.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.3"
+	log_test $? 2 "Multipath - replace of non-existent route"
+}
+
+ipv4_rt_replace()
+{
+	echo
+	echo "IPv4 route replace tests"
+
+	ipv4_rt_replace_single
+	ipv4_rt_replace_mpath
+}
+
+ipv4_route_test()
+{
+	route_setup
+
+	ipv4_rt_add
+	ipv4_rt_replace
+
+	route_cleanup
+}
+
+ipv4_addr_metric_test()
+{
+	local rc
+
+	echo
+	echo "IPv4 prefix route tests"
+
+	ip_addr_metric_check || return 1
+
+	setup
+
+	set -e
+	$IP li add dummy1 type dummy
+	$IP li add dummy2 type dummy
+	$IP li set dummy1 up
+	$IP li set dummy2 up
+
+	# default entry is metric 256
+	run_cmd "$IP addr add dev dummy1 172.16.104.1/24"
+	run_cmd "$IP addr add dev dummy2 172.16.104.2/24"
+	set +e
+
+	check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2"
+	log_test $? 0 "Default metric"
+
+	set -e
+	run_cmd "$IP addr flush dev dummy1"
+	run_cmd "$IP addr add dev dummy1 172.16.104.1/24 metric 257"
+	set +e
+
+	check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257"
+	log_test $? 0 "User specified metric on first device"
+
+	set -e
+	run_cmd "$IP addr flush dev dummy2"
+	run_cmd "$IP addr add dev dummy2 172.16.104.2/24 metric 258"
+	set +e
+
+	check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258"
+	log_test $? 0 "User specified metric on second device"
+
+	run_cmd "$IP addr del dev dummy1 172.16.104.1/24 metric 257"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258"
+		rc=$?
+	fi
+	log_test $rc 0 "Delete of address on first device"
+
+	run_cmd "$IP addr change dev dummy2 172.16.104.2/24 metric 259"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259"
+		rc=$?
+	fi
+	log_test $rc 0 "Modify metric of address"
+
+	# verify prefix route removed on down
+	run_cmd "$IP li set dev dummy2 down"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route ""
+		rc=$?
+	fi
+	log_test $rc 0 "Prefix route removed on link down"
+
+	# verify prefix route re-inserted with assigned metric
+	run_cmd "$IP li set dev dummy2 up"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259"
+		rc=$?
+	fi
+	log_test $rc 0 "Prefix route with metric on link up"
+
+	$IP li del dummy1
+	$IP li del dummy2
+	cleanup
+}
+
+################################################################################
+# usage
+
+usage()
+{
+	cat <<EOF
+usage: ${0##*/} OPTS
+
+        -t <test>   Test(s) to run (default: all)
+                    (options: $TESTS)
+        -p          Pause on fail
+        -P          Pause after each test before cleanup
+        -v          verbose mode (show commands and output)
+EOF
+}
+
+################################################################################
+# main
+
+while getopts :t:pPhv o
+do
+	case $o in
+		t) TESTS=$OPTARG;;
+		p) PAUSE_ON_FAIL=yes;;
+		P) PAUSE=yes;;
+		v) VERBOSE=$(($VERBOSE + 1));;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
+PEER_CMD="ip netns exec ${PEER_NS}"
+
+# make sure we don't pause twice
+[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no
+
 if [ "$(id -u)" -ne 0 ];then
 	echo "SKIP: Need root privileges"
 	exit $ksft_skip;
@@ -598,6 +1415,25 @@ fi
 # start clean
 cleanup &> /dev/null
 
-fib_test
+for t in $TESTS
+do
+	case $t in
+	fib_unreg_test|unregister)	fib_unreg_test;;
+	fib_down_test|down)		fib_down_test;;
+	fib_carrier_test|carrier)	fib_carrier_test;;
+	fib_nexthop_test|nexthop)	fib_nexthop_test;;
+	ipv6_route_test|ipv6_rt)	ipv6_route_test;;
+	ipv4_route_test|ipv4_rt)	ipv4_route_test;;
+	ipv6_addr_metric)		ipv6_addr_metric_test;;
+	ipv4_addr_metric)		ipv4_addr_metric_test;;
+
+	help) echo "Test names: $TESTS"; exit 0;;
+	esac
+done
+
+if [ "$TESTS" != "none" ]; then
+	printf "\nTests passed: %3d\n" ${nsuccess}
+	printf "Tests failed: %3d\n"   ${nfail}
+fi
 
 exit $ret
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index 75d922438bc9..d8313d0438b7 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,6 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding"
 NUM_NETIFS=4
 CHECK_TC="yes"
 source lib.sh
@@ -75,14 +76,31 @@ cleanup()
 	vrf_cleanup
 }
 
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.2
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:1::2
+}
+
+learning()
+{
+	learning_test "br0" $swp1 $h1 $h2
+}
+
+flooding()
+{
+	flood_test $swp2 $h1 $h2
+}
+
 trap cleanup EXIT
 
 setup_prepare
 setup_wait
 
-ping_test $h1 192.0.2.2
-ping6_test $h1 2001:db8:1::2
-learning_test "br0" $swp1 $h1 $h2
-flood_test $swp2 $h1 $h2
+tests_run
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh
index 1cddf06f691d..c15c6c85c984 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh
@@ -1,6 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding"
 NUM_NETIFS=4
 source lib.sh
 
@@ -73,14 +74,31 @@ cleanup()
 	vrf_cleanup
 }
 
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.2
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:1::2
+}
+
+learning()
+{
+	learning_test "br0" $swp1 $h1 $h2
+}
+
+flooding()
+{
+	flood_test $swp2 $h1 $h2
+}
+
 trap cleanup EXIT
 
 setup_prepare
 setup_wait
 
-ping_test $h1 192.0.2.2
-ping6_test $h1 2001:db8:1::2
-learning_test "br0" $swp1 $h1 $h2
-flood_test $swp2 $h1 $h2
+tests_run
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 1ac6c62271f3..7b18a53aa556 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -321,6 +321,50 @@ simple_if_fini()
 	vrf_destroy $vrf_name
 }
 
+tunnel_create()
+{
+	local name=$1; shift
+	local type=$1; shift
+	local local=$1; shift
+	local remote=$1; shift
+
+	ip link add name $name type $type \
+	   local $local remote $remote "$@"
+	ip link set dev $name up
+}
+
+tunnel_destroy()
+{
+	local name=$1; shift
+
+	ip link del dev $name
+}
+
+vlan_create()
+{
+	local if_name=$1; shift
+	local vid=$1; shift
+	local vrf=$1; shift
+	local ips=("${@}")
+	local name=$if_name.$vid
+
+	ip link add name $name link $if_name type vlan id $vid
+	if [ "$vrf" != "" ]; then
+		ip link set dev $name master $vrf
+	fi
+	ip link set dev $name up
+	__addr_add_del $name add "${ips[@]}"
+}
+
+vlan_destroy()
+{
+	local if_name=$1; shift
+	local vid=$1; shift
+	local name=$if_name.$vid
+
+	ip link del dev $name
+}
+
 master_name_get()
 {
 	local if_name=$1
@@ -335,6 +379,15 @@ link_stats_tx_packets_get()
        ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]'
 }
 
+tc_rule_stats_get()
+{
+	local dev=$1; shift
+	local pref=$1; shift
+
+	tc -j -s filter show dev $dev ingress pref $pref |
+	jq '.[1].options.actions[].stats.packets'
+}
+
 mac_get()
 {
 	local if_name=$1
@@ -353,19 +406,33 @@ bridge_ageing_time_get()
 	echo $((ageing_time / 100))
 }
 
-forwarding_enable()
+declare -A SYSCTL_ORIG
+sysctl_set()
+{
+	local key=$1; shift
+	local value=$1; shift
+
+	SYSCTL_ORIG[$key]=$(sysctl -n $key)
+	sysctl -qw $key=$value
+}
+
+sysctl_restore()
 {
-       ipv4_fwd=$(sysctl -n net.ipv4.conf.all.forwarding)
-       ipv6_fwd=$(sysctl -n net.ipv6.conf.all.forwarding)
+	local key=$1; shift
 
-       sysctl -q -w net.ipv4.conf.all.forwarding=1
-       sysctl -q -w net.ipv6.conf.all.forwarding=1
+	sysctl -qw $key=${SYSCTL_ORIG["$key"]}
+}
+
+forwarding_enable()
+{
+	sysctl_set net.ipv4.conf.all.forwarding 1
+	sysctl_set net.ipv6.conf.all.forwarding 1
 }
 
 forwarding_restore()
 {
-       sysctl -q -w net.ipv6.conf.all.forwarding=$ipv6_fwd
-       sysctl -q -w net.ipv4.conf.all.forwarding=$ipv4_fwd
+	sysctl_restore net.ipv6.conf.all.forwarding
+	sysctl_restore net.ipv4.conf.all.forwarding
 }
 
 tc_offload_check()
@@ -381,6 +448,115 @@ tc_offload_check()
 	return 0
 }
 
+trap_install()
+{
+	local dev=$1; shift
+	local direction=$1; shift
+
+	# For slow-path testing, we need to install a trap to get to
+	# slow path the packets that would otherwise be switched in HW.
+	tc filter add dev $dev $direction pref 1 flower skip_sw action trap
+}
+
+trap_uninstall()
+{
+	local dev=$1; shift
+	local direction=$1; shift
+
+	tc filter del dev $dev $direction pref 1 flower skip_sw
+}
+
+slow_path_trap_install()
+{
+	if [ "${tcflags/skip_hw}" != "$tcflags" ]; then
+		trap_install "$@"
+	fi
+}
+
+slow_path_trap_uninstall()
+{
+	if [ "${tcflags/skip_hw}" != "$tcflags" ]; then
+		trap_uninstall "$@"
+	fi
+}
+
+__icmp_capture_add_del()
+{
+	local add_del=$1; shift
+	local pref=$1; shift
+	local vsuf=$1; shift
+	local tundev=$1; shift
+	local filter=$1; shift
+
+	tc filter $add_del dev "$tundev" ingress \
+	   proto ip$vsuf pref $pref \
+	   flower ip_proto icmp$vsuf $filter \
+	   action pass
+}
+
+icmp_capture_install()
+{
+	__icmp_capture_add_del add 100 "" "$@"
+}
+
+icmp_capture_uninstall()
+{
+	__icmp_capture_add_del del 100 "" "$@"
+}
+
+icmp6_capture_install()
+{
+	__icmp_capture_add_del add 100 v6 "$@"
+}
+
+icmp6_capture_uninstall()
+{
+	__icmp_capture_add_del del 100 v6 "$@"
+}
+
+__vlan_capture_add_del()
+{
+	local add_del=$1; shift
+	local pref=$1; shift
+	local dev=$1; shift
+	local filter=$1; shift
+
+	tc filter $add_del dev "$dev" ingress \
+	   proto 802.1q pref $pref \
+	   flower $filter \
+	   action pass
+}
+
+vlan_capture_install()
+{
+	__vlan_capture_add_del add 100 "$@"
+}
+
+vlan_capture_uninstall()
+{
+	__vlan_capture_add_del del 100 "$@"
+}
+
+matchall_sink_create()
+{
+	local dev=$1; shift
+
+	tc qdisc add dev $dev clsact
+	tc filter add dev $dev ingress \
+	   pref 10000 \
+	   matchall \
+	   action drop
+}
+
+tests_run()
+{
+	local current_test
+
+	for current_test in ${TESTS:-$ALL_TESTS}; do
+		$current_test
+	done
+}
+
 ##############################################################################
 # Tests
 
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh
new file mode 100755
index 000000000000..e6fd7a18c655
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh
@@ -0,0 +1,159 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for "tc action mirred egress mirror" when the device to mirror to is a
+# gretap or ip6gretap netdevice. Expect that the packets come out encapsulated,
+# and another gretap / ip6gretap netdevice is then capable of decapsulating the
+# traffic. Test that the payload is what is expected (ICMP ping request or
+# reply, depending on test).
+
+ALL_TESTS="
+	test_gretap
+	test_ip6gretap
+	test_gretap_mac
+	test_ip6gretap_mac
+	test_two_spans
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	ip address add dev $swp3 192.0.2.129/28
+	ip address add dev $h3 192.0.2.130/28
+
+	ip address add dev $swp3 2001:db8:2::1/64
+	ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip address del dev $h3 2001:db8:2::2/64
+	ip address del dev $swp3 2001:db8:2::1/64
+
+	ip address del dev $h3 192.0.2.130/28
+	ip address del dev $swp3 192.0.2.129/28
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+}
+
+test_span_gre_mac()
+{
+	local tundev=$1; shift
+	local direction=$1; shift
+	local prot=$1; shift
+	local what=$1; shift
+
+	local swp3mac=$(mac_get $swp3)
+	local h3mac=$(mac_get $h3)
+
+	RET=0
+
+	mirror_install $swp1 $direction $tundev "matchall $tcflags"
+	tc filter add dev $h3 ingress pref 77 prot $prot \
+		flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \
+		action pass
+
+	mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+
+	tc filter del dev $h3 ingress pref 77
+	mirror_uninstall $swp1 $direction
+
+	log_test "$direction $what: envelope MAC ($tcflags)"
+}
+
+test_two_spans()
+{
+	RET=0
+
+	mirror_install $swp1 ingress gt4 "matchall $tcflags"
+	mirror_install $swp1 egress gt6 "matchall $tcflags"
+	quick_test_span_gre_dir gt4 ingress
+	quick_test_span_gre_dir gt6 egress
+
+	mirror_uninstall $swp1 ingress
+	fail_test_span_gre_dir gt4 ingress
+	quick_test_span_gre_dir gt6 egress
+
+	mirror_install $swp1 ingress gt4 "matchall $tcflags"
+	mirror_uninstall $swp1 egress
+	quick_test_span_gre_dir gt4 ingress
+	fail_test_span_gre_dir gt6 egress
+
+	mirror_uninstall $swp1 ingress
+	log_test "two simultaneously configured mirrors ($tcflags)"
+}
+
+test_gretap()
+{
+	full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+	full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+	full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap"
+	full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap"
+}
+
+test_gretap_mac()
+{
+	test_span_gre_mac gt4 ingress ip "mirror to gretap"
+	test_span_gre_mac gt4 egress ip "mirror to gretap"
+}
+
+test_ip6gretap_mac()
+{
+	test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap"
+	test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap"
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh
new file mode 100755
index 000000000000..360ca133bead
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh
@@ -0,0 +1,226 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+#   +---------------------+                             +---------------------+
+#   | H1                  |                             |                  H2 |
+#   |     + $h1           |                             |           $h2 +     |
+#   |     | 192.0.2.1/28  |                             |  192.0.2.2/28 |     |
+#   +-----|---------------+                             +---------------|-----+
+#         |                                                             |
+#   +-----|-------------------------------------------------------------|-----+
+#   | SW  o--> mirror                                                   |     |
+#   | +---|-------------------------------------------------------------|---+ |
+#   | |   + $swp1                    BR                           $swp2 +   | |
+#   | +---------------------------------------------------------------------+ |
+#   |                                                                         |
+#   | +---------------------------------------------------------------------+ |
+#   | | OL                      + gt6 (ip6gretap)      + gt4 (gretap)       | |
+#   | |                         : loc=2001:db8:2::1    : loc=192.0.2.129    | |
+#   | |                         : rem=2001:db8:2::2    : rem=192.0.2.130    | |
+#   | |                         : ttl=100              : ttl=100            | |
+#   | |                         : tos=inherit          : tos=inherit        | |
+#   | +-------------------------:--|-------------------:--|-----------------+ |
+#   |                           :  |                   :  |                   |
+#   | +-------------------------:--|-------------------:--|-----------------+ |
+#   | | UL                      :  |,---------------------'                 | |
+#   | |   + $swp3               :  ||                  :                    | |
+#   | |   | 192.0.2.129/28      :  vv                  :                    | |
+#   | |   | 2001:db8:2::1/64    :  + ul (dummy)        :                    | |
+#   | +---|---------------------:----------------------:--------------------+ |
+#   +-----|---------------------:----------------------:----------------------+
+#         |                     :                      :
+#   +-----|---------------------:----------------------:----------------------+
+#   | H3  + $h3                 + h3-gt6 (ip6gretap)   + h3-gt4 (gretap)      |
+#   |       192.0.2.130/28        loc=2001:db8:2::2      loc=192.0.2.130      |
+#   |       2001:db8:2::2/64      rem=2001:db8:2::1      rem=192.0.2.129      |
+#   |                             ttl=100                ttl=100              |
+#   |                             tos=inherit            tos=inherit          |
+#   |                                                                         |
+#   +-------------------------------------------------------------------------+
+#
+# This tests mirroring to gretap and ip6gretap configured in an overlay /
+# underlay manner, i.e. with a bound dummy device that marks underlay VRF where
+# the encapsulated packed should be routed.
+
+ALL_TESTS="
+	test_gretap
+	test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/28
+}
+
+h2_destroy()
+{
+	simple_if_fini $h2 192.0.2.2/28
+}
+
+h3_create()
+{
+	simple_if_init $h3 192.0.2.130/28 2001:db8:2::2/64
+
+	tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129
+	ip link set h3-gt4 vrf v$h3
+	matchall_sink_create h3-gt4
+
+	tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1
+	ip link set h3-gt6 vrf v$h3
+	matchall_sink_create h3-gt6
+}
+
+h3_destroy()
+{
+	tunnel_destroy h3-gt6
+	tunnel_destroy h3-gt4
+
+	simple_if_fini $h3 192.0.2.130/28 2001:db8:2::2/64
+}
+
+switch_create()
+{
+	# Bridge between H1 and H2.
+
+	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 up
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 master br1
+	ip link set dev $swp2 up
+
+	tc qdisc add dev $swp1 clsact
+
+	# Underlay.
+
+	simple_if_init $swp3 192.0.2.129/28 2001:db8:2::1/64
+
+	ip link add name ul type dummy
+	ip link set dev ul master v$swp3
+	ip link set dev ul up
+
+	# Overlay.
+
+	vrf_create vrf-ol
+	ip link set dev vrf-ol up
+
+	tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \
+		      ttl 100 tos inherit dev ul
+	ip link set dev gt4 master vrf-ol
+	ip link set dev gt4 up
+
+	tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \
+		      ttl 100 tos inherit dev ul allow-localremote
+	ip link set dev gt6 master vrf-ol
+	ip link set dev gt6 up
+}
+
+switch_destroy()
+{
+	vrf_destroy vrf-ol
+
+	tunnel_destroy gt6
+	tunnel_destroy gt4
+
+	simple_if_fini $swp3 192.0.2.129/28 2001:db8:2::1/64
+
+	ip link del dev ul
+
+	tc qdisc del dev $swp1 clsact
+
+	ip link set dev $swp1 down
+	ip link set dev $swp2 down
+	ip link del dev br1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	h3_create
+
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+
+	h3_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+test_gretap()
+{
+	full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap w/ UL"
+	full_test_span_gre_dir gt4 egress  0 8 "mirror to gretap w/ UL"
+}
+
+test_ip6gretap()
+{
+	full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap w/ UL"
+	full_test_span_gre_dir gt6 egress  0 8 "mirror to ip6gretap w/ UL"
+}
+
+test_all()
+{
+	RET=0
+
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
new file mode 100755
index 000000000000..3bb4c2ba7b14
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
@@ -0,0 +1,121 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# bridge device without vlan filtering (802.1d). The device attached to that
+# bridge is a VLAN.
+
+ALL_TESTS="
+	test_gretap
+	test_ip6gretap
+	test_gretap_stp
+	test_ip6gretap_stp
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	ip link add name br2 type bridge vlan_filtering 0
+	ip link set dev br2 up
+
+	vlan_create $swp3 555
+
+	ip link set dev $swp3.555 master br2
+	ip route add 192.0.2.130/32 dev br2
+	ip -6 route add 2001:db8:2::2/128 dev br2
+
+	ip address add dev br2 192.0.2.129/32
+	ip address add dev br2 2001:db8:2::1/128
+
+	vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	vlan_destroy $h3 555
+	ip link del dev br2
+	vlan_destroy $swp3 555
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+}
+
+test_vlan_match()
+{
+	local tundev=$1; shift
+	local vlan_match=$1; shift
+	local what=$1; shift
+
+	full_test_span_gre_dir_vlan $tundev ingress "$vlan_match" 8 0 "$what"
+	full_test_span_gre_dir_vlan $tundev egress "$vlan_match" 0 8 "$what"
+}
+
+test_gretap()
+{
+	test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+	test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap"
+}
+
+test_gretap_stp()
+{
+	full_test_span_gre_stp gt4 $swp3.555 "mirror to gretap"
+}
+
+test_ip6gretap_stp()
+{
+	full_test_span_gre_stp gt6 $swp3.555 "mirror to ip6gretap"
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh
new file mode 100755
index 000000000000..aa29d46186a8
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh
@@ -0,0 +1,278 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test how mirrors to gretap and ip6gretap react to changes to relevant
+# configuration.
+
+ALL_TESTS="
+	test_ttl
+	test_tun_up
+	test_egress_up
+	test_remote_ip
+	test_tun_del
+	test_route_del
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	# This test downs $swp3, which deletes the configured IPv6 address
+	# unless this sysctl is set.
+	sysctl_set net.ipv6.conf.$swp3.keep_addr_on_down 1
+
+	ip address add dev $swp3 192.0.2.129/28
+	ip address add dev $h3 192.0.2.130/28
+
+	ip address add dev $swp3 2001:db8:2::1/64
+	ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip address del dev $h3 2001:db8:2::2/64
+	ip address del dev $swp3 2001:db8:2::1/64
+
+	ip address del dev $h3 192.0.2.130/28
+	ip address del dev $swp3 192.0.2.129/28
+
+	sysctl_restore net.ipv6.conf.$swp3.keep_addr_on_down
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+}
+
+test_span_gre_ttl()
+{
+	local tundev=$1; shift
+	local type=$1; shift
+	local prot=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	tc filter add dev $h3 ingress pref 77 prot $prot \
+		flower ip_ttl 50 action pass
+
+	mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 0
+
+	ip link set dev $tundev type $type ttl 50
+	mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+
+	ip link set dev $tundev type $type ttl 100
+	tc filter del dev $h3 ingress pref 77
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: TTL change ($tcflags)"
+}
+
+test_span_gre_tun_up()
+{
+	local tundev=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	ip link set dev $tundev down
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	fail_test_span_gre_dir $tundev ingress
+
+	ip link set dev $tundev up
+
+	quick_test_span_gre_dir $tundev ingress
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: tunnel down/up ($tcflags)"
+}
+
+test_span_gre_egress_up()
+{
+	local tundev=$1; shift
+	local remote_ip=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	ip link set dev $swp3 down
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	fail_test_span_gre_dir $tundev ingress
+
+	# After setting the device up, wait for neighbor to get resolved so that
+	# we can expect mirroring to work.
+	ip link set dev $swp3 up
+	while true; do
+		ip neigh sh dev $swp3 $remote_ip nud reachable |
+		    grep -q ^
+		if [[ $? -ne 0 ]]; then
+			sleep 1
+		else
+			break
+		fi
+	done
+
+	quick_test_span_gre_dir $tundev ingress
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: egress down/up ($tcflags)"
+}
+
+test_span_gre_remote_ip()
+{
+	local tundev=$1; shift
+	local type=$1; shift
+	local correct_ip=$1; shift
+	local wrong_ip=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	ip link set dev $tundev type $type remote $wrong_ip
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	fail_test_span_gre_dir $tundev ingress
+
+	ip link set dev $tundev type $type remote $correct_ip
+	quick_test_span_gre_dir $tundev ingress
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: remote address change ($tcflags)"
+}
+
+test_span_gre_tun_del()
+{
+	local tundev=$1; shift
+	local type=$1; shift
+	local flags=$1; shift
+	local local_ip=$1; shift
+	local remote_ip=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	quick_test_span_gre_dir $tundev ingress
+	ip link del dev $tundev
+	fail_test_span_gre_dir $tundev ingress
+
+	tunnel_create $tundev $type $local_ip $remote_ip \
+		      ttl 100 tos inherit $flags
+
+	# Recreating the tunnel doesn't reestablish mirroring, so reinstall it
+	# and verify it works for the follow-up tests.
+	mirror_uninstall $swp1 ingress
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	quick_test_span_gre_dir $tundev ingress
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: tunnel deleted ($tcflags)"
+}
+
+test_span_gre_route_del()
+{
+	local tundev=$1; shift
+	local edev=$1; shift
+	local route=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	quick_test_span_gre_dir $tundev ingress
+
+	ip route del $route dev $edev
+	fail_test_span_gre_dir $tundev ingress
+
+	ip route add $route dev $edev
+	quick_test_span_gre_dir $tundev ingress
+
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: underlay route removal ($tcflags)"
+}
+
+test_ttl()
+{
+	test_span_gre_ttl gt4 gretap ip "mirror to gretap"
+	test_span_gre_ttl gt6 ip6gretap ipv6 "mirror to ip6gretap"
+}
+
+test_tun_up()
+{
+	test_span_gre_tun_up gt4 "mirror to gretap"
+	test_span_gre_tun_up gt6 "mirror to ip6gretap"
+}
+
+test_egress_up()
+{
+	test_span_gre_egress_up gt4 192.0.2.130 "mirror to gretap"
+	test_span_gre_egress_up gt6 2001:db8:2::2 "mirror to ip6gretap"
+}
+
+test_remote_ip()
+{
+	test_span_gre_remote_ip gt4 gretap 192.0.2.130 192.0.2.132 "mirror to gretap"
+	test_span_gre_remote_ip gt6 ip6gretap 2001:db8:2::2 2001:db8:2::4 "mirror to ip6gretap"
+}
+
+test_tun_del()
+{
+	test_span_gre_tun_del gt4 gretap "" \
+			      192.0.2.129 192.0.2.130 "mirror to gretap"
+	test_span_gre_tun_del gt6 ip6gretap allow-localremote \
+			      2001:db8:2::1 2001:db8:2::2 "mirror to ip6gretap"
+}
+
+test_route_del()
+{
+	test_span_gre_route_del gt4 $swp3 192.0.2.128/28 "mirror to gretap"
+	test_span_gre_route_del gt6 $swp3 2001:db8:2::/64 "mirror to ip6gretap"
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh
new file mode 100755
index 000000000000..12914f40612d
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh
@@ -0,0 +1,137 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# This tests flower-triggered mirroring to gretap and ip6gretap netdevices. The
+# interfaces on H1 and H2 have two addresses each. Flower match on one of the
+# addresses is configured with mirror action. It is expected that when pinging
+# this address, mirroring takes place, whereas when pinging the other one,
+# there's no mirroring.
+
+ALL_TESTS="
+	test_gretap
+	test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	ip address add dev $swp3 192.0.2.129/28
+	ip address add dev $h3 192.0.2.130/28
+
+	ip address add dev $swp3 2001:db8:2::1/64
+	ip address add dev $h3 2001:db8:2::2/64
+
+	ip address add dev $h1 192.0.2.3/28
+	ip address add dev $h2 192.0.2.4/28
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip address del dev $h2 192.0.2.4/28
+	ip address del dev $h1 192.0.2.3/28
+
+	ip address del dev $h3 2001:db8:2::2/64
+	ip address del dev $swp3 2001:db8:2::1/64
+
+	ip address del dev $h3 192.0.2.130/28
+	ip address del dev $swp3 192.0.2.129/28
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+}
+
+test_span_gre_dir_acl()
+{
+	test_span_gre_dir_ips "$@" 192.0.2.3 192.0.2.4
+}
+
+fail_test_span_gre_dir_acl()
+{
+	fail_test_span_gre_dir_ips "$@" 192.0.2.3 192.0.2.4
+}
+
+full_test_span_gre_dir_acl()
+{
+	local tundev=$1; shift
+	local direction=$1; shift
+	local forward_type=$1; shift
+	local backward_type=$1; shift
+	local match_dip=$1; shift
+	local what=$1; shift
+
+	mirror_install $swp1 $direction $tundev \
+		       "protocol ip flower $tcflags dst_ip $match_dip"
+	fail_test_span_gre_dir $tundev $direction
+	test_span_gre_dir_acl "$tundev" "$direction" \
+			  "$forward_type" "$backward_type"
+	mirror_uninstall $swp1 $direction
+
+	# Test lack of mirroring after ACL mirror is uninstalled.
+	fail_test_span_gre_dir_acl "$tundev" "$direction"
+
+	log_test "$direction $what ($tcflags)"
+}
+
+test_gretap()
+{
+	full_test_span_gre_dir_acl gt4 ingress 8 0 192.0.2.4 "ACL mirror to gretap"
+	full_test_span_gre_dir_acl gt4 egress 0 8 192.0.2.3 "ACL mirror to gretap"
+}
+
+test_ip6gretap()
+{
+	full_test_span_gre_dir_acl gt6 ingress 8 0 192.0.2.4 "ACL mirror to ip6gretap"
+	full_test_span_gre_dir_acl gt6 egress 0 8 192.0.2.3 "ACL mirror to ip6gretap"
+}
+
+test_all()
+{
+	RET=0
+
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
new file mode 100644
index 000000000000..619b469365be
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
@@ -0,0 +1,130 @@
+# SPDX-License-Identifier: GPL-2.0
+
+source mirror_lib.sh
+
+quick_test_span_gre_dir_ips()
+{
+	local tundev=$1; shift
+
+	do_test_span_dir_ips 10 h3-$tundev "$@"
+}
+
+fail_test_span_gre_dir_ips()
+{
+	local tundev=$1; shift
+
+	do_test_span_dir_ips 0 h3-$tundev "$@"
+}
+
+test_span_gre_dir_ips()
+{
+	local tundev=$1; shift
+
+	test_span_dir_ips h3-$tundev "$@"
+}
+
+full_test_span_gre_dir_ips()
+{
+	local tundev=$1; shift
+	local direction=$1; shift
+	local forward_type=$1; shift
+	local backward_type=$1; shift
+	local what=$1; shift
+	local ip1=$1; shift
+	local ip2=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 $direction $tundev "matchall $tcflags"
+	test_span_dir_ips "h3-$tundev" "$direction" "$forward_type" \
+			  "$backward_type" "$ip1" "$ip2"
+	mirror_uninstall $swp1 $direction
+
+	log_test "$direction $what ($tcflags)"
+}
+
+full_test_span_gre_dir_vlan_ips()
+{
+	local tundev=$1; shift
+	local direction=$1; shift
+	local vlan_match=$1; shift
+	local forward_type=$1; shift
+	local backward_type=$1; shift
+	local what=$1; shift
+	local ip1=$1; shift
+	local ip2=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 $direction $tundev "matchall $tcflags"
+
+	test_span_dir_ips "h3-$tundev" "$direction" "$forward_type" \
+			  "$backward_type" "$ip1" "$ip2"
+
+	tc filter add dev $h3 ingress pref 77 prot 802.1q \
+		flower $vlan_match ip_proto 0x2f \
+		action pass
+	mirror_test v$h1 $ip1 $ip2 $h3 77 10
+	tc filter del dev $h3 ingress pref 77
+
+	mirror_uninstall $swp1 $direction
+
+	log_test "$direction $what ($tcflags)"
+}
+
+quick_test_span_gre_dir()
+{
+	quick_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+fail_test_span_gre_dir()
+{
+	fail_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+test_span_gre_dir()
+{
+	test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+full_test_span_gre_dir()
+{
+	full_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+full_test_span_gre_dir_vlan()
+{
+	full_test_span_gre_dir_vlan_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+full_test_span_gre_stp_ips()
+{
+	local tundev=$1; shift
+	local nbpdev=$1; shift
+	local what=$1; shift
+	local ip1=$1; shift
+	local ip2=$1; shift
+	local h3mac=$(mac_get $h3)
+
+	RET=0
+
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	quick_test_span_gre_dir_ips $tundev ingress $ip1 $ip2
+
+	bridge link set dev $nbpdev state disabled
+	sleep 1
+	fail_test_span_gre_dir_ips $tundev ingress $ip1 $ip2
+
+	bridge link set dev $nbpdev state forwarding
+	sleep 1
+	quick_test_span_gre_dir_ips $tundev ingress $ip1 $ip2
+
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: STP state ($tcflags)"
+}
+
+full_test_span_gre_stp()
+{
+	full_test_span_gre_stp_ips "$@" 192.0.2.1 192.0.2.2
+}
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh
new file mode 100755
index 000000000000..fc0508e40fca
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh
@@ -0,0 +1,115 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for mirroring to gretap and ip6gretap, such that the neighbor entry for
+# the tunnel remote address has invalid address at the time that the mirroring
+# is set up. Later on, the neighbor is deleted and it is expected to be
+# reinitialized using the usual ARP process, and the mirroring offload updated.
+
+ALL_TESTS="
+	test_gretap
+	test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	ip address add dev $swp3 192.0.2.129/28
+	ip address add dev $h3 192.0.2.130/28
+
+	ip address add dev $swp3 2001:db8:2::1/64
+	ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip address del dev $h3 2001:db8:2::2/64
+	ip address del dev $swp3 2001:db8:2::1/64
+
+	ip address del dev $h3 192.0.2.130/28
+	ip address del dev $swp3 192.0.2.129/28
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+}
+
+test_span_gre_neigh()
+{
+	local addr=$1; shift
+	local tundev=$1; shift
+	local direction=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	ip neigh replace dev $swp3 $addr lladdr 00:11:22:33:44:55
+	mirror_install $swp1 $direction $tundev "matchall $tcflags"
+	fail_test_span_gre_dir $tundev ingress
+	ip neigh del dev $swp3 $addr
+	quick_test_span_gre_dir $tundev ingress
+	mirror_uninstall $swp1 $direction
+
+	log_test "$direction $what: neighbor change ($tcflags)"
+}
+
+test_gretap()
+{
+	test_span_gre_neigh 192.0.2.130 gt4 ingress "mirror to gretap"
+	test_span_gre_neigh 192.0.2.130 gt4 egress "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+	test_span_gre_neigh 2001:db8:2::2 gt6 ingress "mirror to ip6gretap"
+	test_span_gre_neigh 2001:db8:2::2 gt6 egress "mirror to ip6gretap"
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh
new file mode 100755
index 000000000000..8fa681eb90e7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh
@@ -0,0 +1,127 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test that gretap and ip6gretap mirroring works when the other tunnel endpoint
+# is reachable through a next-hop route (as opposed to directly-attached route).
+
+ALL_TESTS="
+	test_gretap
+	test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	sysctl_set net.ipv4.conf.all.rp_filter 0
+	sysctl_set net.ipv4.conf.$h3.rp_filter 0
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	ip address add dev $swp3 192.0.2.161/28
+	ip address add dev $h3 192.0.2.162/28
+	ip address add dev gt4 192.0.2.129/32
+	ip address add dev h3-gt4 192.0.2.130/32
+
+	# IPv6 route can't be added after address. Such routes are rejected due
+	# to the gateway address having been configured on the local system. It
+	# works the other way around though.
+	ip address add dev $swp3 2001:db8:4::1/64
+	ip -6 route add 2001:db8:2::2/128 via 2001:db8:4::2
+	ip address add dev $h3 2001:db8:4::2/64
+	ip address add dev gt6 2001:db8:2::1
+	ip address add dev h3-gt6 2001:db8:2::2
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip -6 route del 2001:db8:2::2/128 via 2001:db8:4::2
+	ip address del dev $h3 2001:db8:4::2/64
+	ip address del dev $swp3 2001:db8:4::1/64
+
+	ip address del dev $h3 192.0.2.162/28
+	ip address del dev $swp3 192.0.2.161/28
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+
+	sysctl_restore net.ipv4.conf.$h3.rp_filter
+	sysctl_restore net.ipv4.conf.all.rp_filter
+}
+
+test_gretap()
+{
+	RET=0
+	mirror_install $swp1 ingress gt4 "matchall $tcflags"
+
+	# For IPv4, test that there's no mirroring without the route directing
+	# the traffic to tunnel remote address. Then add it and test that
+	# mirroring starts. For IPv6 we can't test this due to the limitation
+	# that routes for locally-specified IPv6 addresses can't be added.
+	fail_test_span_gre_dir gt4 ingress
+
+	ip route add 192.0.2.130/32 via 192.0.2.162
+	quick_test_span_gre_dir gt4 ingress
+	ip route del 192.0.2.130/32 via 192.0.2.162
+
+	mirror_uninstall $swp1 ingress
+	log_test "mirror to gre with next-hop remote ($tcflags)"
+}
+
+test_ip6gretap()
+{
+	RET=0
+
+	mirror_install $swp1 ingress gt6 "matchall $tcflags"
+	quick_test_span_gre_dir gt6 ingress
+	mirror_uninstall $swp1 ingress
+
+	log_test "mirror to ip6gre with next-hop remote ($tcflags)"
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh
new file mode 100644
index 000000000000..253419564708
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh
@@ -0,0 +1,94 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# This is the standard topology for testing mirroring to gretap and ip6gretap
+# netdevices. The tests that use it tweak it in one way or another--importantly,
+# $swp3 and $h3 need to have addresses set up.
+#
+#   +---------------------+                             +---------------------+
+#   | H1                  |                             |                  H2 |
+#   |     + $h1           |                             |           $h2 +     |
+#   |     | 192.0.2.1/28  |                             |  192.0.2.2/28 |     |
+#   +-----|---------------+                             +---------------|-----+
+#         |                                                             |
+#   +-----|-------------------------------------------------------------|-----+
+#   | SW  o--> mirror                                                   |     |
+#   | +---|-------------------------------------------------------------|---+ |
+#   | |   + $swp1                    BR                           $swp2 +   | |
+#   | +---------------------------------------------------------------------+ |
+#   |                                                                         |
+#   |     + $swp3               + gt6 (ip6gretap)      + gt4 (gretap)         |
+#   |     |                     : loc=2001:db8:2::1    : loc=192.0.2.129      |
+#   |     |                     : rem=2001:db8:2::2    : rem=192.0.2.130      |
+#   |     |                     : ttl=100              : ttl=100              |
+#   |     |                     : tos=inherit          : tos=inherit          |
+#   |     |                     :                      :                      |
+#   +-----|---------------------:----------------------:----------------------+
+#         |                     :                      :
+#   +-----|---------------------:----------------------:----------------------+
+#   | H3  + $h3                 + h3-gt6 (ip6gretap)   + h3-gt4 (gretap)      |
+#   |                             loc=2001:db8:2::2      loc=192.0.2.130      |
+#   |                             rem=2001:db8:2::1      rem=192.0.2.129      |
+#   |                             ttl=100                ttl=100              |
+#   |                             tos=inherit            tos=inherit          |
+#   |                                                                         |
+#   +-------------------------------------------------------------------------+
+
+source mirror_topo_lib.sh
+
+mirror_gre_topo_h3_create()
+{
+	mirror_topo_h3_create
+
+	tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129
+	ip link set h3-gt4 vrf v$h3
+	matchall_sink_create h3-gt4
+
+	tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1
+	ip link set h3-gt6 vrf v$h3
+	matchall_sink_create h3-gt6
+}
+
+mirror_gre_topo_h3_destroy()
+{
+	tunnel_destroy h3-gt6
+	tunnel_destroy h3-gt4
+
+	mirror_topo_h3_destroy
+}
+
+mirror_gre_topo_switch_create()
+{
+	mirror_topo_switch_create
+
+	tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \
+		      ttl 100 tos inherit
+
+	tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \
+		      ttl 100 tos inherit allow-localremote
+}
+
+mirror_gre_topo_switch_destroy()
+{
+	tunnel_destroy gt6
+	tunnel_destroy gt4
+
+	mirror_topo_switch_destroy
+}
+
+mirror_gre_topo_create()
+{
+	mirror_topo_h1_create
+	mirror_topo_h2_create
+	mirror_gre_topo_h3_create
+
+	mirror_gre_topo_switch_create
+}
+
+mirror_gre_topo_destroy()
+{
+	mirror_gre_topo_switch_destroy
+
+	mirror_gre_topo_h3_destroy
+	mirror_topo_h2_destroy
+	mirror_topo_h1_destroy
+}
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh
new file mode 100755
index 000000000000..88cecdb9a861
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh
@@ -0,0 +1,92 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for "tc action mirred egress mirror" that mirrors to a gretap netdevice
+# whose underlay route points at a vlan device.
+
+ALL_TESTS="
+	test_gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	ip link add name $swp3.555 link $swp3 type vlan id 555
+	ip address add dev $swp3.555 192.0.2.129/32
+	ip address add dev $swp3.555 2001:db8:2::1/128
+	ip link set dev $swp3.555 up
+
+	ip route add 192.0.2.130/32 dev $swp3.555
+	ip -6 route add 2001:db8:2::2/128 dev $swp3.555
+
+	ip link add name $h3.555 link $h3 type vlan id 555
+	ip link set dev $h3.555 master v$h3
+	ip address add dev $h3.555 192.0.2.130/28
+	ip address add dev $h3.555 2001:db8:2::2/64
+	ip link set dev $h3.555 up
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link del dev $h3.555
+	ip link del dev $swp3.555
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+}
+
+test_gretap()
+{
+	full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+	full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
new file mode 100755
index 000000000000..5dbc7a08f4bd
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
@@ -0,0 +1,270 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# vlan device on top of a bridge device with vlan filtering (802.1q).
+
+ALL_TESTS="
+	test_gretap
+	test_ip6gretap
+	test_gretap_forbidden_cpu
+	test_ip6gretap_forbidden_cpu
+	test_gretap_forbidden_egress
+	test_ip6gretap_forbidden_egress
+	test_gretap_untagged_egress
+	test_ip6gretap_untagged_egress
+	test_gretap_fdb_roaming
+	test_ip6gretap_fdb_roaming
+	test_gretap_stp
+	test_ip6gretap_stp
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	vlan_create br1 555 "" 192.0.2.129/32 2001:db8:2::1/128
+	bridge vlan add dev br1 vid 555 self
+	ip route rep 192.0.2.130/32 dev br1.555
+	ip -6 route rep 2001:db8:2::2/128 dev br1.555
+
+	vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64
+
+	ip link set dev $swp3 master br1
+	bridge vlan add dev $swp3 vid 555
+	bridge vlan add dev $swp2 vid 555
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp3 nomaster
+	vlan_destroy $h3 555
+	vlan_destroy br1 555
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+}
+
+test_vlan_match()
+{
+	local tundev=$1; shift
+	local vlan_match=$1; shift
+	local what=$1; shift
+
+	full_test_span_gre_dir_vlan $tundev ingress "$vlan_match" 8 0 "$what"
+	full_test_span_gre_dir_vlan $tundev egress "$vlan_match" 0 8 "$what"
+}
+
+test_gretap()
+{
+	test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+	test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap"
+}
+
+test_span_gre_forbidden_cpu()
+{
+	local tundev=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	# Run the pass-test first, to prime neighbor table.
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	quick_test_span_gre_dir $tundev ingress
+
+	# Now forbid the VLAN at the bridge and see it fail.
+	bridge vlan del dev br1 vid 555 self
+	sleep 1
+	fail_test_span_gre_dir $tundev ingress
+
+	bridge vlan add dev br1 vid 555 self
+	sleep 1
+	quick_test_span_gre_dir $tundev ingress
+
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: vlan forbidden at a bridge ($tcflags)"
+}
+
+test_gretap_forbidden_cpu()
+{
+	test_span_gre_forbidden_cpu gt4 "mirror to gretap"
+}
+
+test_ip6gretap_forbidden_cpu()
+{
+	test_span_gre_forbidden_cpu gt6 "mirror to ip6gretap"
+}
+
+test_span_gre_forbidden_egress()
+{
+	local tundev=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	quick_test_span_gre_dir $tundev ingress
+
+	bridge vlan del dev $swp3 vid 555
+	sleep 1
+	fail_test_span_gre_dir $tundev ingress
+
+	bridge vlan add dev $swp3 vid 555
+	# Re-prime FDB
+	arping -I br1.555 192.0.2.130 -fqc 1
+	sleep 1
+	quick_test_span_gre_dir $tundev ingress
+
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: vlan forbidden at a bridge egress ($tcflags)"
+}
+
+test_gretap_forbidden_egress()
+{
+	test_span_gre_forbidden_egress gt4 "mirror to gretap"
+}
+
+test_ip6gretap_forbidden_egress()
+{
+	test_span_gre_forbidden_egress gt6 "mirror to ip6gretap"
+}
+
+test_span_gre_untagged_egress()
+{
+	local tundev=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+
+	quick_test_span_gre_dir $tundev ingress
+	quick_test_span_vlan_dir $h3 555 ingress
+
+	bridge vlan add dev $swp3 vid 555 pvid untagged
+	sleep 1
+	quick_test_span_gre_dir $tundev ingress
+	fail_test_span_vlan_dir $h3 555 ingress
+
+	bridge vlan add dev $swp3 vid 555
+	sleep 1
+	quick_test_span_gre_dir $tundev ingress
+	quick_test_span_vlan_dir $h3 555 ingress
+
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: vlan untagged at a bridge egress ($tcflags)"
+}
+
+test_gretap_untagged_egress()
+{
+	test_span_gre_untagged_egress gt4 "mirror to gretap"
+}
+
+test_ip6gretap_untagged_egress()
+{
+	test_span_gre_untagged_egress gt6 "mirror to ip6gretap"
+}
+
+test_span_gre_fdb_roaming()
+{
+	local tundev=$1; shift
+	local what=$1; shift
+	local h3mac=$(mac_get $h3)
+
+	RET=0
+
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	quick_test_span_gre_dir $tundev ingress
+
+	bridge fdb del dev $swp3 $h3mac vlan 555 master
+	bridge fdb add dev $swp2 $h3mac vlan 555 master
+	sleep 1
+	fail_test_span_gre_dir $tundev ingress
+
+	bridge fdb del dev $swp2 $h3mac vlan 555 master
+	# Re-prime FDB
+	arping -I br1.555 192.0.2.130 -fqc 1
+	sleep 1
+	quick_test_span_gre_dir $tundev ingress
+
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: MAC roaming ($tcflags)"
+}
+
+test_gretap_fdb_roaming()
+{
+	test_span_gre_fdb_roaming gt4 "mirror to gretap"
+}
+
+test_ip6gretap_fdb_roaming()
+{
+	test_span_gre_fdb_roaming gt6 "mirror to ip6gretap"
+}
+
+test_gretap_stp()
+{
+	full_test_span_gre_stp gt4 $swp3 "mirror to gretap"
+}
+
+test_ip6gretap_stp()
+{
+	full_test_span_gre_stp gt6 $swp3 "mirror to ip6gretap"
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh
new file mode 100644
index 000000000000..d36dc26c6c51
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh
@@ -0,0 +1,132 @@
+# SPDX-License-Identifier: GPL-2.0
+
+mirror_install()
+{
+	local from_dev=$1; shift
+	local direction=$1; shift
+	local to_dev=$1; shift
+	local filter=$1; shift
+
+	tc filter add dev $from_dev $direction \
+	   pref 1000 $filter \
+	   action mirred egress mirror dev $to_dev
+}
+
+mirror_uninstall()
+{
+	local from_dev=$1; shift
+	local direction=$1; shift
+
+	tc filter del dev $swp1 $direction pref 1000
+}
+
+mirror_test()
+{
+	local vrf_name=$1; shift
+	local sip=$1; shift
+	local dip=$1; shift
+	local dev=$1; shift
+	local pref=$1; shift
+	local expect=$1; shift
+
+	local t0=$(tc_rule_stats_get $dev $pref)
+	ip vrf exec $vrf_name \
+	   ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.1 -w 2 &> /dev/null
+	local t1=$(tc_rule_stats_get $dev $pref)
+	local delta=$((t1 - t0))
+	# Tolerate a couple stray extra packets.
+	((expect <= delta && delta <= expect + 2))
+	check_err $? "Expected to capture $expect packets, got $delta."
+}
+
+do_test_span_dir_ips()
+{
+	local expect=$1; shift
+	local dev=$1; shift
+	local direction=$1; shift
+	local ip1=$1; shift
+	local ip2=$1; shift
+
+	icmp_capture_install $dev
+	mirror_test v$h1 $ip1 $ip2 $dev 100 $expect
+	mirror_test v$h2 $ip2 $ip1 $dev 100 $expect
+	icmp_capture_uninstall $dev
+}
+
+quick_test_span_dir_ips()
+{
+	do_test_span_dir_ips 10 "$@"
+}
+
+fail_test_span_dir_ips()
+{
+	do_test_span_dir_ips 0 "$@"
+}
+
+test_span_dir_ips()
+{
+	local dev=$1; shift
+	local direction=$1; shift
+	local forward_type=$1; shift
+	local backward_type=$1; shift
+	local ip1=$1; shift
+	local ip2=$1; shift
+
+	quick_test_span_dir_ips "$dev" "$direction" "$ip1" "$ip2"
+
+	icmp_capture_install $dev "type $forward_type"
+	mirror_test v$h1 $ip1 $ip2 $dev 100 10
+	icmp_capture_uninstall $dev
+
+	icmp_capture_install $dev "type $backward_type"
+	mirror_test v$h2 $ip2 $ip1 $dev 100 10
+	icmp_capture_uninstall $dev
+}
+
+fail_test_span_dir()
+{
+	fail_test_span_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+test_span_dir()
+{
+	test_span_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+do_test_span_vlan_dir_ips()
+{
+	local expect=$1; shift
+	local dev=$1; shift
+	local vid=$1; shift
+	local direction=$1; shift
+	local ip1=$1; shift
+	local ip2=$1; shift
+
+	# Install the capture as skip_hw to avoid double-counting of packets.
+	# The traffic is meant for local box anyway, so will be trapped to
+	# kernel.
+	vlan_capture_install $dev "skip_hw vlan_id $vid"
+	mirror_test v$h1 $ip1 $ip2 $dev 100 $expect
+	mirror_test v$h2 $ip2 $ip1 $dev 100 $expect
+	vlan_capture_uninstall $dev
+}
+
+quick_test_span_vlan_dir_ips()
+{
+	do_test_span_vlan_dir_ips 10 "$@"
+}
+
+fail_test_span_vlan_dir_ips()
+{
+	do_test_span_vlan_dir_ips 0 "$@"
+}
+
+quick_test_span_vlan_dir()
+{
+	quick_test_span_vlan_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+fail_test_span_vlan_dir()
+{
+	fail_test_span_vlan_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
diff --git a/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh
new file mode 100644
index 000000000000..04979e5962e7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh
@@ -0,0 +1,101 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# This is the standard topology for testing mirroring. The tests that use it
+# tweak it in one way or another--typically add more devices to the topology.
+#
+#   +---------------------+                             +---------------------+
+#   | H1                  |                             |                  H2 |
+#   |     + $h1           |                             |           $h2 +     |
+#   |     | 192.0.2.1/28  |                             |  192.0.2.2/28 |     |
+#   +-----|---------------+                             +---------------|-----+
+#         |                                                             |
+#   +-----|-------------------------------------------------------------|-----+
+#   | SW  o--> mirror                                                   |     |
+#   | +---|-------------------------------------------------------------|---+ |
+#   | |   + $swp1                    BR                           $swp2 +   | |
+#   | +---------------------------------------------------------------------+ |
+#   |                                                                         |
+#   |     + $swp3                                                             |
+#   +-----|-------------------------------------------------------------------+
+#         |
+#   +-----|-------------------------------------------------------------------+
+#   | H3  + $h3                                                               |
+#   |                                                                         |
+#   +-------------------------------------------------------------------------+
+
+mirror_topo_h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28
+}
+
+mirror_topo_h1_destroy()
+{
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+mirror_topo_h2_create()
+{
+	simple_if_init $h2 192.0.2.2/28
+}
+
+mirror_topo_h2_destroy()
+{
+	simple_if_fini $h2 192.0.2.2/28
+}
+
+mirror_topo_h3_create()
+{
+	simple_if_init $h3
+	tc qdisc add dev $h3 clsact
+}
+
+mirror_topo_h3_destroy()
+{
+	tc qdisc del dev $h3 clsact
+	simple_if_fini $h3
+}
+
+mirror_topo_switch_create()
+{
+	ip link set dev $swp3 up
+
+	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 up
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 master br1
+	ip link set dev $swp2 up
+
+	tc qdisc add dev $swp1 clsact
+}
+
+mirror_topo_switch_destroy()
+{
+	tc qdisc del dev $swp1 clsact
+
+	ip link set dev $swp1 down
+	ip link set dev $swp2 down
+	ip link del dev br1
+
+	ip link set dev $swp3 down
+}
+
+mirror_topo_create()
+{
+	mirror_topo_h1_create
+	mirror_topo_h2_create
+	mirror_topo_h3_create
+
+	mirror_topo_switch_create
+}
+
+mirror_topo_destroy()
+{
+	mirror_topo_switch_destroy
+
+	mirror_topo_h3_destroy
+	mirror_topo_h2_destroy
+	mirror_topo_h1_destroy
+}
diff --git a/tools/testing/selftests/net/forwarding/mirror_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_vlan.sh
new file mode 100755
index 000000000000..9ab2ce77b332
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_vlan.sh
@@ -0,0 +1,131 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing mirroring. See mirror_topo_lib.sh
+# for more details.
+#
+# Test for "tc action mirred egress mirror" that mirrors to a vlan device.
+
+ALL_TESTS="
+	test_vlan
+	test_tagged_vlan
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_topo_create
+
+	vlan_create $swp3 555
+
+	vlan_create $h3 555 v$h3
+	matchall_sink_create $h3.555
+
+	vlan_create $h1 111 v$h1 192.0.2.17/28
+	bridge vlan add dev $swp1 vid 111
+
+	vlan_create $h2 111 v$h2 192.0.2.18/28
+	bridge vlan add dev $swp2 vid 111
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	vlan_destroy $h2 111
+	vlan_destroy $h1 111
+	vlan_destroy $h3 555
+	vlan_destroy $swp3 555
+
+	mirror_topo_destroy
+	vrf_cleanup
+}
+
+test_vlan_dir()
+{
+	local direction=$1; shift
+	local forward_type=$1; shift
+	local backward_type=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 $direction $swp3.555 "matchall $tcflags"
+	test_span_dir "$h3.555" "$direction" "$forward_type" "$backward_type"
+	mirror_uninstall $swp1 $direction
+
+	log_test "$direction mirror to vlan ($tcflags)"
+}
+
+test_vlan()
+{
+	test_vlan_dir ingress 8 0
+	test_vlan_dir egress 0 8
+}
+
+test_tagged_vlan_dir()
+{
+	local direction=$1; shift
+	local forward_type=$1; shift
+	local backward_type=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 $direction $swp3.555 "matchall $tcflags"
+	do_test_span_vlan_dir_ips 10 "$h3.555" 111 "$direction" \
+				  192.0.2.17 192.0.2.18
+	do_test_span_vlan_dir_ips  0 "$h3.555" 555 "$direction" \
+				  192.0.2.17 192.0.2.18
+	mirror_uninstall $swp1 $direction
+
+	log_test "$direction mirror tagged to vlan ($tcflags)"
+}
+
+test_tagged_vlan()
+{
+	test_tagged_vlan_dir ingress 8 0
+	test_tagged_vlan_dir egress 0 8
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+	trap_install $h3 ingress
+
+	tests_run
+
+	trap_uninstall $h3 ingress
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh
index cc6a14abfa87..a75cb51cc5bd 100755
--- a/tools/testing/selftests/net/forwarding/router.sh
+++ b/tools/testing/selftests/net/forwarding/router.sh
@@ -1,6 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+ALL_TESTS="ping_ipv4 ping_ipv6"
 NUM_NETIFS=4
 source lib.sh
 
@@ -114,12 +115,21 @@ cleanup()
 	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
 
-ping_test $h1 198.51.100.2
-ping6_test $h1 2001:db8:2::2
+tests_run
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh
index 3bc351008db6..8b6d0fb6d604 100755
--- a/tools/testing/selftests/net/forwarding/router_multipath.sh
+++ b/tools/testing/selftests/net/forwarding/router_multipath.sh
@@ -1,6 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+ALL_TESTS="ping_ipv4 ping_ipv6 multipath_test"
 NUM_NETIFS=8
 source lib.sh
 
@@ -191,7 +192,7 @@ multipath_eval()
        diff=$(echo $weights_ratio - $packets_ratio | bc -l)
        diff=${diff#-}
 
-       test "$(echo "$diff / $weights_ratio > 0.1" | bc -l)" -eq 0
+       test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
        check_err $? "Too large discrepancy between expected and measured ratios"
        log_test "$desc"
        log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
@@ -204,13 +205,11 @@ multipath4_test()
        local weight_rp13=$3
        local t0_rp12 t0_rp13 t1_rp12 t1_rp13
        local packets_rp12 packets_rp13
-       local hash_policy
 
        # Transmit multiple flows from h1 to h2 and make sure they are
        # distributed between both multipath links (rp12 and rp13)
        # according to the configured weights.
-       hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy)
-       sysctl -q -w net.ipv4.fib_multipath_hash_policy=1
+       sysctl_set net.ipv4.fib_multipath_hash_policy 1
        ip route replace 198.51.100.0/24 vrf vrf-r1 \
                nexthop via 169.254.2.22 dev $rp12 weight $weight_rp12 \
                nexthop via 169.254.3.23 dev $rp13 weight $weight_rp13
@@ -232,7 +231,7 @@ multipath4_test()
        ip route replace 198.51.100.0/24 vrf vrf-r1 \
                nexthop via 169.254.2.22 dev $rp12 \
                nexthop via 169.254.3.23 dev $rp13
-       sysctl -q -w net.ipv4.fib_multipath_hash_policy=$hash_policy
+       sysctl_restore net.ipv4.fib_multipath_hash_policy
 }
 
 multipath6_l4_test()
@@ -242,13 +241,11 @@ multipath6_l4_test()
        local weight_rp13=$3
        local t0_rp12 t0_rp13 t1_rp12 t1_rp13
        local packets_rp12 packets_rp13
-       local hash_policy
 
        # Transmit multiple flows from h1 to h2 and make sure they are
        # distributed between both multipath links (rp12 and rp13)
        # according to the configured weights.
-       hash_policy=$(sysctl -n net.ipv6.fib_multipath_hash_policy)
-       sysctl -q -w net.ipv6.fib_multipath_hash_policy=1
+       sysctl_set net.ipv6.fib_multipath_hash_policy 1
 
        ip route replace 2001:db8:2::/64 vrf vrf-r1 \
 	       nexthop via fe80:2::22 dev $rp12 weight $weight_rp12 \
@@ -271,7 +268,7 @@ multipath6_l4_test()
 	       nexthop via fe80:2::22 dev $rp12 \
 	       nexthop via fe80:3::23 dev $rp13
 
-       sysctl -q -w net.ipv6.fib_multipath_hash_policy=$hash_policy
+       sysctl_restore net.ipv6.fib_multipath_hash_policy
 }
 
 multipath6_test()
@@ -364,13 +361,21 @@ cleanup()
 	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
 
-ping_test $h1 198.51.100.2
-ping6_test $h1 2001:db8:2::2
-multipath_test
+tests_run
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index 3a6385ebd5d0..813d02d1939d 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -1,6 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
+	mirred_egress_mirror_test gact_trap_test"
 NUM_NETIFS=4
 source tc_common.sh
 source lib.sh
@@ -111,6 +113,10 @@ gact_trap_test()
 {
 	RET=0
 
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
 	tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
 		skip_hw dst_ip 192.0.2.2 action drop
 	tc filter add dev $swp1 ingress protocol ip pref 3 handle 103 flower \
@@ -179,24 +185,29 @@ cleanup()
 	ip link set $swp1 address $swp1origmac
 }
 
+mirred_egress_redirect_test()
+{
+	mirred_egress_test "redirect"
+}
+
+mirred_egress_mirror_test()
+{
+	mirred_egress_test "mirror"
+}
+
 trap cleanup EXIT
 
 setup_prepare
 setup_wait
 
-gact_drop_and_ok_test
-mirred_egress_test "redirect"
-mirred_egress_test "mirror"
+tests_run
 
 tc_offload_check
 if [[ $? -ne 0 ]]; then
 	log_info "Could not test offloaded functionality"
 else
 	tcflags="skip_sw"
-	gact_drop_and_ok_test
-	mirred_egress_test "redirect"
-	mirred_egress_test "mirror"
-	gact_trap_test
+	tests_run
 fi
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh
index 2fd15226974b..d2c783e94df3 100755
--- a/tools/testing/selftests/net/forwarding/tc_chains.sh
+++ b/tools/testing/selftests/net/forwarding/tc_chains.sh
@@ -1,6 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+ALL_TESTS="unreachable_chain_test gact_goto_chain_test"
 NUM_NETIFS=2
 source tc_common.sh
 source lib.sh
@@ -107,16 +108,14 @@ trap cleanup EXIT
 setup_prepare
 setup_wait
 
-unreachable_chain_test
-gact_goto_chain_test
+tests_run
 
 tc_offload_check
 if [[ $? -ne 0 ]]; then
 	log_info "Could not test offloaded functionality"
 else
 	tcflags="skip_sw"
-	unreachable_chain_test
-	gact_goto_chain_test
+	tests_run
 fi
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh
index 032b882adfc0..20d1077e5a3d 100755
--- a/tools/testing/selftests/net/forwarding/tc_flower.sh
+++ b/tools/testing/selftests/net/forwarding/tc_flower.sh
@@ -1,6 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \
+	match_src_ip_test match_ip_flags_test"
 NUM_NETIFS=2
 source tc_common.sh
 source lib.sh
@@ -149,6 +151,74 @@ match_src_ip_test()
 	log_test "src_ip match ($tcflags)"
 }
 
+match_ip_flags_test()
+{
+	RET=0
+
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		$tcflags ip_flags frag action continue
+	tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+		$tcflags ip_flags firstfrag action continue
+	tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+		$tcflags ip_flags nofirstfrag action continue
+	tc filter add dev $h2 ingress protocol ip pref 4 handle 104 flower \
+		$tcflags ip_flags nofrag action drop
+
+	$MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip "frag=0" -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_fail $? "Matched on wrong frag filter (nofrag)"
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_fail $? "Matched on wrong firstfrag filter (nofrag)"
+
+	tc_check_packets "dev $h2 ingress" 103 1
+	check_err $? "Did not match on nofirstfrag filter (nofrag) "
+
+	tc_check_packets "dev $h2 ingress" 104 1
+	check_err $? "Did not match on nofrag filter (nofrag)"
+
+	$MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip "frag=0,mf" -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_err $? "Did not match on frag filter (1stfrag)"
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_err $? "Did not match fistfrag filter (1stfrag)"
+
+	tc_check_packets "dev $h2 ingress" 103 1
+	check_err $? "Matched on wrong nofirstfrag filter (1stfrag)"
+
+	tc_check_packets "dev $h2 ingress" 104 1
+	check_err $? "Match on wrong nofrag filter (1stfrag)"
+
+	$MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip "frag=256,mf" -q
+	$MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip "frag=256" -q
+
+	tc_check_packets "dev $h2 ingress" 101 3
+	check_err $? "Did not match on frag filter (no1stfrag)"
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_err $? "Matched on wrong firstfrag filter (no1stfrag)"
+
+	tc_check_packets "dev $h2 ingress" 103 3
+	check_err $? "Did not match on nofirstfrag filter (no1stfrag)"
+
+	tc_check_packets "dev $h2 ingress" 104 1
+	check_err $? "Matched on nofrag filter (no1stfrag)"
+
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+	tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+	tc filter del dev $h2 ingress protocol ip pref 4 handle 104 flower
+
+	log_test "ip_flags match ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
@@ -177,20 +247,14 @@ trap cleanup EXIT
 setup_prepare
 setup_wait
 
-match_dst_mac_test
-match_src_mac_test
-match_dst_ip_test
-match_src_ip_test
+tests_run
 
 tc_offload_check
 if [[ $? -ne 0 ]]; then
 	log_info "Could not test offloaded functionality"
 else
 	tcflags="skip_sw"
-	match_dst_mac_test
-	match_src_mac_test
-	match_dst_ip_test
-	match_src_ip_test
+	tests_run
 fi
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_shblocks.sh b/tools/testing/selftests/net/forwarding/tc_shblocks.sh
index 077b98048ef4..b5b917203815 100755
--- a/tools/testing/selftests/net/forwarding/tc_shblocks.sh
+++ b/tools/testing/selftests/net/forwarding/tc_shblocks.sh
@@ -1,6 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+ALL_TESTS="shared_block_test"
 NUM_NETIFS=4
 source tc_common.sh
 source lib.sh
@@ -109,14 +110,14 @@ trap cleanup EXIT
 setup_prepare
 setup_wait
 
-shared_block_test
+tests_run
 
 tc_offload_check
 if [[ $? -ne 0 ]]; then
 	log_info "Could not test offloaded functionality"
 else
 	tcflags="skip_sw"
-	shared_block_test
+	tests_run
 fi
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh
index d571d213418d..c43c6debda06 100755
--- a/tools/testing/selftests/net/msg_zerocopy.sh
+++ b/tools/testing/selftests/net/msg_zerocopy.sh
@@ -21,6 +21,14 @@ readonly DADDR6='fd::2'
 
 readonly path_sysctl_mem="net.core.optmem_max"
 
+# No arguments: automated test
+if [[ "$#" -eq "0" ]]; then
+	$0 4 tcp -t 1
+	$0 6 tcp -t 1
+	echo "OK. All tests passed"
+	exit 0
+fi
+
 # Argument parsing
 if [[ "$#" -lt "2" ]]; then
 	echo "Usage: $0 [4|6] [tcp|udp|raw|raw_hdrincl|packet|packet_dgram] <args>"
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 7514f93e1624..f8cc38afffa2 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -371,7 +371,7 @@ test_pmtu_vti6_link_add_mtu() {
 
 	fail=0
 
-	min=1280
+	min=68			# vti6 can carry IPv4 packets too
 	max=$((65535 - 40))
 	# Check invalid values first
 	for v in $((min - 1)) $((max + 1)); do
@@ -387,7 +387,7 @@ test_pmtu_vti6_link_add_mtu() {
 	done
 
 	# Now check valid values
-	for v in 1280 1300 $((65535 - 40)); do
+	for v in 68 1280 1300 $((65535 - 40)); do
 		${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
 		mtu="$(link_get_mtu "${ns_a}" vti6_a)"
 		${ns_a} ip link del vti6_a
diff --git a/tools/testing/selftests/net/psock_snd.c b/tools/testing/selftests/net/psock_snd.c
new file mode 100644
index 000000000000..7d15e10a9fb6
--- /dev/null
+++ b/tools/testing/selftests/net/psock_snd.c
@@ -0,0 +1,397 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+#include <linux/if_packet.h>
+#include <linux/if_vlan.h>
+#include <linux/virtio_net.h>
+#include <net/if.h>
+#include <net/ethernet.h>
+#include <netinet/ip.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "psock_lib.h"
+
+static bool	cfg_use_bind;
+static bool	cfg_use_csum_off;
+static bool	cfg_use_csum_off_bad;
+static bool	cfg_use_dgram;
+static bool	cfg_use_gso;
+static bool	cfg_use_qdisc_bypass;
+static bool	cfg_use_vlan;
+static bool	cfg_use_vnet;
+
+static char	*cfg_ifname = "lo";
+static int	cfg_mtu	= 1500;
+static int	cfg_payload_len = DATA_LEN;
+static int	cfg_truncate_len = INT_MAX;
+static uint16_t	cfg_port = 8000;
+
+/* test sending up to max mtu + 1 */
+#define TEST_SZ	(sizeof(struct virtio_net_hdr) + ETH_HLEN + ETH_MAX_MTU + 1)
+
+static char tbuf[TEST_SZ], rbuf[TEST_SZ];
+
+static unsigned long add_csum_hword(const uint16_t *start, int num_u16)
+{
+	unsigned long sum = 0;
+	int i;
+
+	for (i = 0; i < num_u16; i++)
+		sum += start[i];
+
+	return sum;
+}
+
+static uint16_t build_ip_csum(const uint16_t *start, int num_u16,
+			      unsigned long sum)
+{
+	sum += add_csum_hword(start, num_u16);
+
+	while (sum >> 16)
+		sum = (sum & 0xffff) + (sum >> 16);
+
+	return ~sum;
+}
+
+static int build_vnet_header(void *header)
+{
+	struct virtio_net_hdr *vh = header;
+
+	vh->hdr_len = ETH_HLEN + sizeof(struct iphdr) + sizeof(struct udphdr);
+
+	if (cfg_use_csum_off) {
+		vh->flags |= VIRTIO_NET_HDR_F_NEEDS_CSUM;
+		vh->csum_start = ETH_HLEN + sizeof(struct iphdr);
+		vh->csum_offset = __builtin_offsetof(struct udphdr, check);
+
+		/* position check field exactly one byte beyond end of packet */
+		if (cfg_use_csum_off_bad)
+			vh->csum_start += sizeof(struct udphdr) + cfg_payload_len -
+					  vh->csum_offset - 1;
+	}
+
+	if (cfg_use_gso) {
+		vh->gso_type = VIRTIO_NET_HDR_GSO_UDP;
+		vh->gso_size = cfg_mtu - sizeof(struct iphdr);
+	}
+
+	return sizeof(*vh);
+}
+
+static int build_eth_header(void *header)
+{
+	struct ethhdr *eth = header;
+
+	if (cfg_use_vlan) {
+		uint16_t *tag = header + ETH_HLEN;
+
+		eth->h_proto = htons(ETH_P_8021Q);
+		tag[1] = htons(ETH_P_IP);
+		return ETH_HLEN + 4;
+	}
+
+	eth->h_proto = htons(ETH_P_IP);
+	return ETH_HLEN;
+}
+
+static int build_ipv4_header(void *header, int payload_len)
+{
+	struct iphdr *iph = header;
+
+	iph->ihl = 5;
+	iph->version = 4;
+	iph->ttl = 8;
+	iph->tot_len = htons(sizeof(*iph) + sizeof(struct udphdr) + payload_len);
+	iph->id = htons(1337);
+	iph->protocol = IPPROTO_UDP;
+	iph->saddr = htonl((172 << 24) | (17 << 16) | 2);
+	iph->daddr = htonl((172 << 24) | (17 << 16) | 1);
+	iph->check = build_ip_csum((void *) iph, iph->ihl << 1, 0);
+
+	return iph->ihl << 2;
+}
+
+static int build_udp_header(void *header, int payload_len)
+{
+	const int alen = sizeof(uint32_t);
+	struct udphdr *udph = header;
+	int len = sizeof(*udph) + payload_len;
+
+	udph->source = htons(9);
+	udph->dest = htons(cfg_port);
+	udph->len = htons(len);
+
+	if (cfg_use_csum_off)
+		udph->check = build_ip_csum(header - (2 * alen), alen,
+					    htons(IPPROTO_UDP) + udph->len);
+	else
+		udph->check = 0;
+
+	return sizeof(*udph);
+}
+
+static int build_packet(int payload_len)
+{
+	int off = 0;
+
+	off += build_vnet_header(tbuf);
+	off += build_eth_header(tbuf + off);
+	off += build_ipv4_header(tbuf + off, payload_len);
+	off += build_udp_header(tbuf + off, payload_len);
+
+	if (off + payload_len > sizeof(tbuf))
+		error(1, 0, "payload length exceeds max");
+
+	memset(tbuf + off, DATA_CHAR, payload_len);
+
+	return off + payload_len;
+}
+
+static void do_bind(int fd)
+{
+	struct sockaddr_ll laddr = {0};
+
+	laddr.sll_family = AF_PACKET;
+	laddr.sll_protocol = htons(ETH_P_IP);
+	laddr.sll_ifindex = if_nametoindex(cfg_ifname);
+	if (!laddr.sll_ifindex)
+		error(1, errno, "if_nametoindex");
+
+	if (bind(fd, (void *)&laddr, sizeof(laddr)))
+		error(1, errno, "bind");
+}
+
+static void do_send(int fd, char *buf, int len)
+{
+	int ret;
+
+	if (!cfg_use_vnet) {
+		buf += sizeof(struct virtio_net_hdr);
+		len -= sizeof(struct virtio_net_hdr);
+	}
+	if (cfg_use_dgram) {
+		buf += ETH_HLEN;
+		len -= ETH_HLEN;
+	}
+
+	if (cfg_use_bind) {
+		ret = write(fd, buf, len);
+	} else {
+		struct sockaddr_ll laddr = {0};
+
+		laddr.sll_protocol = htons(ETH_P_IP);
+		laddr.sll_ifindex = if_nametoindex(cfg_ifname);
+		if (!laddr.sll_ifindex)
+			error(1, errno, "if_nametoindex");
+
+		ret = sendto(fd, buf, len, 0, (void *)&laddr, sizeof(laddr));
+	}
+
+	if (ret == -1)
+		error(1, errno, "write");
+	if (ret != len)
+		error(1, 0, "write: %u %u", ret, len);
+
+	fprintf(stderr, "tx: %u\n", ret);
+}
+
+static int do_tx(void)
+{
+	const int one = 1;
+	int fd, len;
+
+	fd = socket(PF_PACKET, cfg_use_dgram ? SOCK_DGRAM : SOCK_RAW, 0);
+	if (fd == -1)
+		error(1, errno, "socket t");
+
+	if (cfg_use_bind)
+		do_bind(fd);
+
+	if (cfg_use_qdisc_bypass &&
+	    setsockopt(fd, SOL_PACKET, PACKET_QDISC_BYPASS, &one, sizeof(one)))
+		error(1, errno, "setsockopt qdisc bypass");
+
+	if (cfg_use_vnet &&
+	    setsockopt(fd, SOL_PACKET, PACKET_VNET_HDR, &one, sizeof(one)))
+		error(1, errno, "setsockopt vnet");
+
+	len = build_packet(cfg_payload_len);
+
+	if (cfg_truncate_len < len)
+		len = cfg_truncate_len;
+
+	do_send(fd, tbuf, len);
+
+	if (close(fd))
+		error(1, errno, "close t");
+
+	return len;
+}
+
+static int setup_rx(void)
+{
+	struct timeval tv = { .tv_usec = 100 * 1000 };
+	struct sockaddr_in raddr = {0};
+	int fd;
+
+	fd = socket(PF_INET, SOCK_DGRAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket r");
+
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+		error(1, errno, "setsockopt rcv timeout");
+
+	raddr.sin_family = AF_INET;
+	raddr.sin_port = htons(cfg_port);
+	raddr.sin_addr.s_addr = htonl(INADDR_ANY);
+
+	if (bind(fd, (void *)&raddr, sizeof(raddr)))
+		error(1, errno, "bind r");
+
+	return fd;
+}
+
+static void do_rx(int fd, int expected_len, char *expected)
+{
+	int ret;
+
+	ret = recv(fd, rbuf, sizeof(rbuf), 0);
+	if (ret == -1)
+		error(1, errno, "recv");
+	if (ret != expected_len)
+		error(1, 0, "recv: %u != %u", ret, expected_len);
+
+	if (memcmp(rbuf, expected, ret))
+		error(1, 0, "recv: data mismatch");
+
+	fprintf(stderr, "rx: %u\n", ret);
+}
+
+static int setup_sniffer(void)
+{
+	struct timeval tv = { .tv_usec = 100 * 1000 };
+	int fd;
+
+	fd = socket(PF_PACKET, SOCK_RAW, 0);
+	if (fd == -1)
+		error(1, errno, "socket p");
+
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+		error(1, errno, "setsockopt rcv timeout");
+
+	pair_udp_setfilter(fd);
+	do_bind(fd);
+
+	return fd;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "bcCdgl:qt:vV")) != -1) {
+		switch (c) {
+		case 'b':
+			cfg_use_bind = true;
+			break;
+		case 'c':
+			cfg_use_csum_off = true;
+			break;
+		case 'C':
+			cfg_use_csum_off_bad = true;
+			break;
+		case 'd':
+			cfg_use_dgram = true;
+			break;
+		case 'g':
+			cfg_use_gso = true;
+			break;
+		case 'l':
+			cfg_payload_len = strtoul(optarg, NULL, 0);
+			break;
+		case 'q':
+			cfg_use_qdisc_bypass = true;
+			break;
+		case 't':
+			cfg_truncate_len = strtoul(optarg, NULL, 0);
+			break;
+		case 'v':
+			cfg_use_vnet = true;
+			break;
+		case 'V':
+			cfg_use_vlan = true;
+			break;
+		default:
+			error(1, 0, "%s: parse error", argv[0]);
+		}
+	}
+
+	if (cfg_use_vlan && cfg_use_dgram)
+		error(1, 0, "option vlan (-V) conflicts with dgram (-d)");
+
+	if (cfg_use_csum_off && !cfg_use_vnet)
+		error(1, 0, "option csum offload (-c) requires vnet (-v)");
+
+	if (cfg_use_csum_off_bad && !cfg_use_csum_off)
+		error(1, 0, "option csum bad (-C) requires csum offload (-c)");
+
+	if (cfg_use_gso && !cfg_use_csum_off)
+		error(1, 0, "option gso (-g) requires csum offload (-c)");
+}
+
+static void run_test(void)
+{
+	int fdr, fds, total_len;
+
+	fdr = setup_rx();
+	fds = setup_sniffer();
+
+	total_len = do_tx();
+
+	/* BPF filter accepts only this length, vlan changes MAC */
+	if (cfg_payload_len == DATA_LEN && !cfg_use_vlan)
+		do_rx(fds, total_len - sizeof(struct virtio_net_hdr),
+		      tbuf + sizeof(struct virtio_net_hdr));
+
+	do_rx(fdr, cfg_payload_len, tbuf + total_len - cfg_payload_len);
+
+	if (close(fds))
+		error(1, errno, "close s");
+	if (close(fdr))
+		error(1, errno, "close r");
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+
+	if (system("ip link set dev lo mtu 1500"))
+		error(1, errno, "ip link set mtu");
+	if (system("ip addr add dev lo 172.17.0.1/24"))
+		error(1, errno, "ip addr add");
+
+	run_test();
+
+	fprintf(stderr, "OK\n\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/net/psock_snd.sh b/tools/testing/selftests/net/psock_snd.sh
new file mode 100755
index 000000000000..6331d91b86a6
--- /dev/null
+++ b/tools/testing/selftests/net/psock_snd.sh
@@ -0,0 +1,98 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of packet socket send regression tests
+
+set -e
+
+readonly mtu=1500
+readonly iphlen=20
+readonly udphlen=8
+
+readonly vnet_hlen=10
+readonly eth_hlen=14
+
+readonly mss="$((${mtu} - ${iphlen} - ${udphlen}))"
+readonly mss_exceeds="$((${mss} + 1))"
+
+readonly max_mtu=65535
+readonly max_mss="$((${max_mtu} - ${iphlen} - ${udphlen}))"
+readonly max_mss_exceeds="$((${max_mss} + 1))"
+
+# functional checks (not a full cross-product)
+
+echo "dgram"
+./in_netns.sh ./psock_snd -d
+
+echo "dgram bind"
+./in_netns.sh ./psock_snd -d -b
+
+echo "raw"
+./in_netns.sh ./psock_snd
+
+echo "raw bind"
+./in_netns.sh ./psock_snd -b
+
+echo "raw qdisc bypass"
+./in_netns.sh ./psock_snd -q
+
+echo "raw vlan"
+./in_netns.sh ./psock_snd -V
+
+echo "raw vnet hdr"
+./in_netns.sh ./psock_snd -v
+
+echo "raw csum_off"
+./in_netns.sh ./psock_snd -v -c
+
+echo "raw csum_off with bad offset (fails)"
+(! ./in_netns.sh ./psock_snd -v -c -C)
+
+
+# bounds check: send {max, max + 1, min, min - 1} lengths
+
+echo "raw min size"
+./in_netns.sh ./psock_snd -l 0
+
+echo "raw mtu size"
+./in_netns.sh ./psock_snd -l "${mss}"
+
+echo "raw mtu size + 1 (fails)"
+(! ./in_netns.sh ./psock_snd -l "${mss_exceeds}")
+
+# fails due to ARPHRD_ETHER check in packet_extra_vlan_len_allowed
+#
+# echo "raw vlan mtu size"
+# ./in_netns.sh ./psock_snd -V -l "${mss}"
+
+echo "raw vlan mtu size + 1 (fails)"
+(! ./in_netns.sh ./psock_snd -V -l "${mss_exceeds}")
+
+echo "dgram mtu size"
+./in_netns.sh ./psock_snd -d -l "${mss}"
+
+echo "dgram mtu size + 1 (fails)"
+(! ./in_netns.sh ./psock_snd -d -l "${mss_exceeds}")
+
+echo "raw truncate hlen (fails: does not arrive)"
+(! ./in_netns.sh ./psock_snd -t "$((${vnet_hlen} + ${eth_hlen}))")
+
+echo "raw truncate hlen - 1 (fails: EINVAL)"
+(! ./in_netns.sh ./psock_snd -t "$((${vnet_hlen} + ${eth_hlen} - 1))")
+
+
+# gso checks: implies -l, because with gso len must exceed gso_size
+
+echo "raw gso min size"
+./in_netns.sh ./psock_snd -v -c -g -l "${mss_exceeds}"
+
+echo "raw gso min size - 1 (fails)"
+(! ./in_netns.sh ./psock_snd -v -c -g -l "${mss}")
+
+echo "raw gso max size"
+./in_netns.sh ./psock_snd -v -c -g -l "${max_mss}"
+
+echo "raw gso max size + 1 (fails)"
+(! ./in_netns.sh ./psock_snd -v -c -g -l "${max_mss_exceeds}")
+
+echo "OK. All tests passed"
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index fb3767844e42..0d7a44fa30af 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -505,6 +505,108 @@ kci_test_macsec()
 	echo "PASS: macsec"
 }
 
+#-------------------------------------------------------------------
+# Example commands
+#   ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \
+#            spi 0x07 mode transport reqid 0x07 replay-window 32 \
+#            aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \
+#            sel src 14.0.0.52/24 dst 14.0.0.70/24
+#   ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \
+#            tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \
+#            spi 0x07 mode transport reqid 0x07
+#
+# Subcommands not tested
+#    ip x s update
+#    ip x s allocspi
+#    ip x s deleteall
+#    ip x p update
+#    ip x p deleteall
+#    ip x p set
+#-------------------------------------------------------------------
+kci_test_ipsec()
+{
+	srcip="14.0.0.52"
+	dstip="14.0.0.70"
+	algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
+
+	# flush to be sure there's nothing configured
+	ip x s flush ; ip x p flush
+	check_err $?
+
+	# start the monitor in the background
+	tmpfile=`mktemp ipsectestXXX`
+	ip x m > $tmpfile &
+	mpid=$!
+	sleep 0.2
+
+	ipsecid="proto esp src $srcip dst $dstip spi 0x07"
+	ip x s add $ipsecid \
+            mode transport reqid 0x07 replay-window 32 \
+            $algo sel src $srcip/24 dst $dstip/24
+	check_err $?
+
+	lines=`ip x s list | grep $srcip | grep $dstip | wc -l`
+	test $lines -eq 2
+	check_err $?
+
+	ip x s count | grep -q "SAD count 1"
+	check_err $?
+
+	lines=`ip x s get $ipsecid | grep $srcip | grep $dstip | wc -l`
+	test $lines -eq 2
+	check_err $?
+
+	ip x s delete $ipsecid
+	check_err $?
+
+	lines=`ip x s list | wc -l`
+	test $lines -eq 0
+	check_err $?
+
+	ipsecsel="dir out src $srcip/24 dst $dstip/24"
+	ip x p add $ipsecsel \
+		    tmpl proto esp src $srcip dst $dstip \
+		    spi 0x07 mode transport reqid 0x07
+	check_err $?
+
+	lines=`ip x p list | grep $srcip | grep $dstip | wc -l`
+	test $lines -eq 2
+	check_err $?
+
+	ip x p count | grep -q "SPD IN  0 OUT 1 FWD 0"
+	check_err $?
+
+	lines=`ip x p get $ipsecsel | grep $srcip | grep $dstip | wc -l`
+	test $lines -eq 2
+	check_err $?
+
+	ip x p delete $ipsecsel
+	check_err $?
+
+	lines=`ip x p list | wc -l`
+	test $lines -eq 0
+	check_err $?
+
+	# check the monitor results
+	kill $mpid
+	lines=`wc -l $tmpfile | cut "-d " -f1`
+	test $lines -eq 20
+	check_err $?
+	rm -rf $tmpfile
+
+	# clean up any leftovers
+	ip x s flush
+	check_err $?
+	ip x p flush
+	check_err $?
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: ipsec"
+		return 1
+	fi
+	echo "PASS: ipsec"
+}
+
 kci_test_gretap()
 {
 	testns="testns"
@@ -758,6 +860,7 @@ kci_test_rtnl()
 	kci_test_vrf
 	kci_test_encap
 	kci_test_macsec
+	kci_test_ipsec
 
 	kci_del_dummy
 }
diff --git a/tools/testing/selftests/net/tcp_inq.c b/tools/testing/selftests/net/tcp_inq.c
new file mode 100644
index 000000000000..d044b29ddabc
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_inq.c
@@ -0,0 +1,189 @@
+/*
+ * Copyright 2018 Google Inc.
+ * Author: Soheil Hassas Yeganeh (soheil@google.com)
+ *
+ * Simple example on how to use TCP_INQ and TCP_CM_INQ.
+ *
+ * License (GPLv2):
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for
+ * more details.
+ */
+#define _GNU_SOURCE
+
+#include <error.h>
+#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+#ifndef TCP_INQ
+#define TCP_INQ 36
+#endif
+
+#ifndef TCP_CM_INQ
+#define TCP_CM_INQ TCP_INQ
+#endif
+
+#define BUF_SIZE 8192
+#define CMSG_SIZE 32
+
+static int family = AF_INET6;
+static socklen_t addr_len = sizeof(struct sockaddr_in6);
+static int port = 4974;
+
+static void setup_loopback_addr(int family, struct sockaddr_storage *sockaddr)
+{
+	struct sockaddr_in6 *addr6 = (void *) sockaddr;
+	struct sockaddr_in *addr4 = (void *) sockaddr;
+
+	switch (family) {
+	case PF_INET:
+		memset(addr4, 0, sizeof(*addr4));
+		addr4->sin_family = AF_INET;
+		addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+		addr4->sin_port = htons(port);
+		break;
+	case PF_INET6:
+		memset(addr6, 0, sizeof(*addr6));
+		addr6->sin6_family = AF_INET6;
+		addr6->sin6_addr = in6addr_loopback;
+		addr6->sin6_port = htons(port);
+		break;
+	default:
+		error(1, 0, "illegal family");
+	}
+}
+
+void *start_server(void *arg)
+{
+	int server_fd = (int)(unsigned long)arg;
+	struct sockaddr_in addr;
+	socklen_t addrlen = sizeof(addr);
+	char *buf;
+	int fd;
+	int r;
+
+	buf = malloc(BUF_SIZE);
+
+	for (;;) {
+		fd = accept(server_fd, (struct sockaddr *)&addr, &addrlen);
+		if (fd == -1) {
+			perror("accept");
+			break;
+		}
+		do {
+			r = send(fd, buf, BUF_SIZE, 0);
+		} while (r < 0 && errno == EINTR);
+		if (r < 0)
+			perror("send");
+		if (r != BUF_SIZE)
+			fprintf(stderr, "can only send %d bytes\n", r);
+		/* TCP_INQ can overestimate in-queue by one byte if we send
+		 * the FIN packet. Sleep for 1 second, so that the client
+		 * likely invoked recvmsg().
+		 */
+		sleep(1);
+		close(fd);
+	}
+
+	free(buf);
+	close(server_fd);
+	pthread_exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	struct sockaddr_storage listen_addr, addr;
+	int c, one = 1, inq = -1;
+	pthread_t server_thread;
+	char cmsgbuf[CMSG_SIZE];
+	struct iovec iov[1];
+	struct cmsghdr *cm;
+	struct msghdr msg;
+	int server_fd, fd;
+	char *buf;
+
+	while ((c = getopt(argc, argv, "46p:")) != -1) {
+		switch (c) {
+		case '4':
+			family = PF_INET;
+			addr_len = sizeof(struct sockaddr_in);
+			break;
+		case '6':
+			family = PF_INET6;
+			addr_len = sizeof(struct sockaddr_in6);
+			break;
+		case 'p':
+			port = atoi(optarg);
+			break;
+		}
+	}
+
+	server_fd = socket(family, SOCK_STREAM, 0);
+	if (server_fd < 0)
+		error(1, errno, "server socket");
+	setup_loopback_addr(family, &listen_addr);
+	if (setsockopt(server_fd, SOL_SOCKET, SO_REUSEADDR,
+		       &one, sizeof(one)) != 0)
+		error(1, errno, "setsockopt(SO_REUSEADDR)");
+	if (bind(server_fd, (const struct sockaddr *)&listen_addr,
+		 addr_len) == -1)
+		error(1, errno, "bind");
+	if (listen(server_fd, 128) == -1)
+		error(1, errno, "listen");
+	if (pthread_create(&server_thread, NULL, start_server,
+			   (void *)(unsigned long)server_fd) != 0)
+		error(1, errno, "pthread_create");
+
+	fd = socket(family, SOCK_STREAM, 0);
+	if (fd < 0)
+		error(1, errno, "client socket");
+	setup_loopback_addr(family, &addr);
+	if (connect(fd, (const struct sockaddr *)&addr, addr_len) == -1)
+		error(1, errno, "connect");
+	if (setsockopt(fd, SOL_TCP, TCP_INQ, &one, sizeof(one)) != 0)
+		error(1, errno, "setsockopt(TCP_INQ)");
+
+	msg.msg_name = NULL;
+	msg.msg_namelen = 0;
+	msg.msg_iov = iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cmsgbuf;
+	msg.msg_controllen = sizeof(cmsgbuf);
+	msg.msg_flags = 0;
+
+	buf = malloc(BUF_SIZE);
+	iov[0].iov_base = buf;
+	iov[0].iov_len = BUF_SIZE / 2;
+
+	if (recvmsg(fd, &msg, 0) != iov[0].iov_len)
+		error(1, errno, "recvmsg");
+	if (msg.msg_flags & MSG_CTRUNC)
+		error(1, 0, "control message is truncated");
+
+	for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm))
+		if (cm->cmsg_level == SOL_TCP && cm->cmsg_type == TCP_CM_INQ)
+			inq = *((int *) CMSG_DATA(cm));
+
+	if (inq != BUF_SIZE - iov[0].iov_len) {
+		fprintf(stderr, "unexpected inq: %d\n", inq);
+		exit(1);
+	}
+
+	printf("PASSED\n");
+	free(buf);
+	close(fd);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
new file mode 100644
index 000000000000..77f762780199
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -0,0 +1,447 @@
+/*
+ * Copyright 2018 Google Inc.
+ * Author: Eric Dumazet (edumazet@google.com)
+ *
+ * Reference program demonstrating tcp mmap() usage,
+ * and SO_RCVLOWAT hints for receiver.
+ *
+ * Note : NIC with header split is needed to use mmap() on TCP :
+ * Each incoming frame must be a multiple of PAGE_SIZE bytes of TCP payload.
+ *
+ * How to use on loopback interface :
+ *
+ *  ifconfig lo mtu 61512  # 15*4096 + 40 (ipv6 header) + 32 (TCP with TS option header)
+ *  tcp_mmap -s -z &
+ *  tcp_mmap -H ::1 -z
+ *
+ *  Or leave default lo mtu, but use -M option to set TCP_MAXSEG option to (4096 + 12)
+ *      (4096 : page size on x86, 12: TCP TS option length)
+ *  tcp_mmap -s -z -M $((4096+12)) &
+ *  tcp_mmap -H ::1 -z -M $((4096+12))
+ *
+ * Note: -z option on sender uses MSG_ZEROCOPY, which forces a copy when packets go through loopback interface.
+ *       We might use sendfile() instead, but really this test program is about mmap(), for receivers ;)
+ *
+ * $ ./tcp_mmap -s &                                 # Without mmap()
+ * $ for i in {1..4}; do ./tcp_mmap -H ::1 -z ; done
+ * received 32768 MB (0 % mmap'ed) in 14.1157 s, 19.4732 Gbit
+ *   cpu usage user:0.057 sys:7.815, 240.234 usec per MB, 65531 c-switches
+ * received 32768 MB (0 % mmap'ed) in 14.6833 s, 18.7204 Gbit
+ *  cpu usage user:0.043 sys:8.103, 248.596 usec per MB, 65524 c-switches
+ * received 32768 MB (0 % mmap'ed) in 11.143 s, 24.6682 Gbit
+ *   cpu usage user:0.044 sys:6.576, 202.026 usec per MB, 65519 c-switches
+ * received 32768 MB (0 % mmap'ed) in 14.9056 s, 18.4413 Gbit
+ *   cpu usage user:0.036 sys:8.193, 251.129 usec per MB, 65530 c-switches
+ * $ kill %1   # kill tcp_mmap server
+ *
+ * $ ./tcp_mmap -s -z &                              # With mmap()
+ * $ for i in {1..4}; do ./tcp_mmap -H ::1 -z ; done
+ * received 32768 MB (99.9939 % mmap'ed) in 6.73792 s, 40.7956 Gbit
+ *   cpu usage user:0.045 sys:2.827, 87.6465 usec per MB, 65532 c-switches
+ * received 32768 MB (99.9939 % mmap'ed) in 7.26732 s, 37.8238 Gbit
+ *   cpu usage user:0.037 sys:3.087, 95.3369 usec per MB, 65532 c-switches
+ * received 32768 MB (99.9939 % mmap'ed) in 7.61661 s, 36.0893 Gbit
+ *   cpu usage user:0.046 sys:3.559, 110.016 usec per MB, 65529 c-switches
+ * received 32768 MB (99.9939 % mmap'ed) in 7.43764 s, 36.9577 Gbit
+ *   cpu usage user:0.035 sys:3.467, 106.873 usec per MB, 65530 c-switches
+ *
+ * License (GPLv2):
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sys/types.h>
+#include <fcntl.h>
+#include <error.h>
+#include <sys/socket.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <poll.h>
+#include <linux/tcp.h>
+#include <assert.h>
+
+#ifndef MSG_ZEROCOPY
+#define MSG_ZEROCOPY    0x4000000
+#endif
+
+#define FILE_SZ (1UL << 35)
+static int cfg_family = AF_INET6;
+static socklen_t cfg_alen = sizeof(struct sockaddr_in6);
+static int cfg_port = 8787;
+
+static int rcvbuf; /* Default: autotuning.  Can be set with -r <integer> option */
+static int sndbuf; /* Default: autotuning.  Can be set with -w <integer> option */
+static int zflg; /* zero copy option. (MSG_ZEROCOPY for sender, mmap() for receiver */
+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;
+
+unsigned long htotal;
+
+static inline void prefetch(const void *x)
+{
+#if defined(__x86_64__)
+	asm volatile("prefetcht0 %P0" : : "m" (*(const char *)x));
+#endif
+}
+
+void hash_zone(void *zone, unsigned int length)
+{
+	unsigned long temp = htotal;
+
+	while (length >= 8*sizeof(long)) {
+		prefetch(zone + 384);
+		temp ^= *(unsigned long *)zone;
+		temp ^= *(unsigned long *)(zone + sizeof(long));
+		temp ^= *(unsigned long *)(zone + 2*sizeof(long));
+		temp ^= *(unsigned long *)(zone + 3*sizeof(long));
+		temp ^= *(unsigned long *)(zone + 4*sizeof(long));
+		temp ^= *(unsigned long *)(zone + 5*sizeof(long));
+		temp ^= *(unsigned long *)(zone + 6*sizeof(long));
+		temp ^= *(unsigned long *)(zone + 7*sizeof(long));
+		zone += 8*sizeof(long);
+		length -= 8*sizeof(long);
+	}
+	while (length >= 1) {
+		temp ^= *(unsigned char *)zone;
+		zone += 1;
+		length--;
+	}
+	htotal = temp;
+}
+
+void *child_thread(void *arg)
+{
+	unsigned long total_mmap = 0, total = 0;
+	struct tcp_zerocopy_receive zc;
+	unsigned long delta_usec;
+	int flags = MAP_SHARED;
+	struct timeval t0, t1;
+	char *buffer = NULL;
+	void *addr = NULL;
+	double throughput;
+	struct rusage ru;
+	int lu, fd;
+
+	fd = (int)(unsigned long)arg;
+
+	gettimeofday(&t0, NULL);
+
+	fcntl(fd, F_SETFL, O_NDELAY);
+	buffer = malloc(chunk_size);
+	if (!buffer) {
+		perror("malloc");
+		goto error;
+	}
+	if (zflg) {
+		addr = mmap(NULL, chunk_size, PROT_READ, flags, fd, 0);
+		if (addr == (void *)-1)
+			zflg = 0;
+	}
+	while (1) {
+		struct pollfd pfd = { .fd = fd, .events = POLLIN, };
+		int sub;
+
+		poll(&pfd, 1, 10000);
+		if (zflg) {
+			socklen_t zc_len = sizeof(zc);
+			int res;
+
+			zc.address = (__u64)addr;
+			zc.length = chunk_size;
+			zc.recv_skip_hint = 0;
+			res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE,
+					 &zc, &zc_len);
+			if (res == -1)
+				break;
+
+			if (zc.length) {
+				assert(zc.length <= chunk_size);
+				total_mmap += zc.length;
+				if (xflg)
+					hash_zone(addr, zc.length);
+				total += zc.length;
+			}
+			if (zc.recv_skip_hint) {
+				assert(zc.recv_skip_hint <= chunk_size);
+				lu = read(fd, buffer, zc.recv_skip_hint);
+				if (lu > 0) {
+					if (xflg)
+						hash_zone(buffer, lu);
+					total += lu;
+				}
+			}
+			continue;
+		}
+		sub = 0;
+		while (sub < chunk_size) {
+			lu = read(fd, buffer + sub, chunk_size - sub);
+			if (lu == 0)
+				goto end;
+			if (lu < 0)
+				break;
+			if (xflg)
+				hash_zone(buffer + sub, lu);
+			total += lu;
+			sub += lu;
+		}
+	}
+end:
+	gettimeofday(&t1, NULL);
+	delta_usec = (t1.tv_sec - t0.tv_sec) * 1000000 + t1.tv_usec - t0.tv_usec;
+
+	throughput = 0;
+	if (delta_usec)
+		throughput = total * 8.0 / (double)delta_usec / 1000.0;
+	getrusage(RUSAGE_THREAD, &ru);
+	if (total > 1024*1024) {
+		unsigned long total_usec;
+		unsigned long mb = total >> 20;
+		total_usec = 1000000*ru.ru_utime.tv_sec + ru.ru_utime.tv_usec +
+			     1000000*ru.ru_stime.tv_sec + ru.ru_stime.tv_usec;
+		printf("received %lg MB (%lg %% mmap'ed) in %lg s, %lg Gbit\n"
+		       "  cpu usage user:%lg sys:%lg, %lg usec per MB, %lu c-switches\n",
+				total / (1024.0 * 1024.0),
+				100.0*total_mmap/total,
+				(double)delta_usec / 1000000.0,
+				throughput,
+				(double)ru.ru_utime.tv_sec + (double)ru.ru_utime.tv_usec / 1000000.0,
+				(double)ru.ru_stime.tv_sec + (double)ru.ru_stime.tv_usec / 1000000.0,
+				(double)total_usec/mb,
+				ru.ru_nvcsw);
+	}
+error:
+	free(buffer);
+	close(fd);
+	if (zflg)
+		munmap(addr, chunk_size);
+	pthread_exit(0);
+}
+
+static void apply_rcvsnd_buf(int fd)
+{
+	if (rcvbuf && setsockopt(fd, SOL_SOCKET,
+				 SO_RCVBUF, &rcvbuf, sizeof(rcvbuf)) == -1) {
+		perror("setsockopt SO_RCVBUF");
+	}
+
+	if (sndbuf && setsockopt(fd, SOL_SOCKET,
+				 SO_SNDBUF, &sndbuf, sizeof(sndbuf)) == -1) {
+		perror("setsockopt SO_SNDBUF");
+	}
+}
+
+
+static void setup_sockaddr(int domain, const char *str_addr,
+			   struct sockaddr_storage *sockaddr)
+{
+	struct sockaddr_in6 *addr6 = (void *) sockaddr;
+	struct sockaddr_in *addr4 = (void *) sockaddr;
+
+	switch (domain) {
+	case PF_INET:
+		memset(addr4, 0, sizeof(*addr4));
+		addr4->sin_family = AF_INET;
+		addr4->sin_port = htons(cfg_port);
+		if (str_addr &&
+		    inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+			error(1, 0, "ipv4 parse error: %s", str_addr);
+		break;
+	case PF_INET6:
+		memset(addr6, 0, sizeof(*addr6));
+		addr6->sin6_family = AF_INET6;
+		addr6->sin6_port = htons(cfg_port);
+		if (str_addr &&
+		    inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+			error(1, 0, "ipv6 parse error: %s", str_addr);
+		break;
+	default:
+		error(1, 0, "illegal domain");
+	}
+}
+
+static void do_accept(int fdlisten)
+{
+	if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT,
+		       &chunk_size, sizeof(chunk_size)) == -1) {
+		perror("setsockopt SO_RCVLOWAT");
+	}
+
+	apply_rcvsnd_buf(fdlisten);
+
+	while (1) {
+		struct sockaddr_in addr;
+		socklen_t addrlen = sizeof(addr);
+		pthread_t th;
+		int fd, res;
+
+		fd = accept(fdlisten, (struct sockaddr *)&addr, &addrlen);
+		if (fd == -1) {
+			perror("accept");
+			continue;
+		}
+		res = pthread_create(&th, NULL, child_thread,
+				     (void *)(unsigned long)fd);
+		if (res) {
+			errno = res;
+			perror("pthread_create");
+			close(fd);
+		}
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	struct sockaddr_storage listenaddr, addr;
+	unsigned int max_pacing_rate = 0;
+	unsigned long total = 0;
+	char *host = NULL;
+	int fd, c, on = 1;
+	char *buffer;
+	int sflg = 0;
+	int mss = 0;
+
+	while ((c = getopt(argc, argv, "46p:svr:w:H:zxkP:M:")) != -1) {
+		switch (c) {
+		case '4':
+			cfg_family = PF_INET;
+			cfg_alen = sizeof(struct sockaddr_in);
+			break;
+		case '6':
+			cfg_family = PF_INET6;
+			cfg_alen = sizeof(struct sockaddr_in6);
+			break;
+		case 'p':
+			cfg_port = atoi(optarg);
+			break;
+		case 'H':
+			host = optarg;
+			break;
+		case 's': /* server : listen for incoming connections */
+			sflg++;
+			break;
+		case 'r':
+			rcvbuf = atoi(optarg);
+			break;
+		case 'w':
+			sndbuf = atoi(optarg);
+			break;
+		case 'z':
+			zflg = 1;
+			break;
+		case 'M':
+			mss = atoi(optarg);
+			break;
+		case 'x':
+			xflg = 1;
+			break;
+		case 'k':
+			keepflag = 1;
+			break;
+		case 'P':
+			max_pacing_rate = atoi(optarg) ;
+			break;
+		default:
+			exit(1);
+		}
+	}
+	if (sflg) {
+		int fdlisten = socket(cfg_family, SOCK_STREAM, 0);
+
+		if (fdlisten == -1) {
+			perror("socket");
+			exit(1);
+		}
+		apply_rcvsnd_buf(fdlisten);
+		setsockopt(fdlisten, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on));
+
+		setup_sockaddr(cfg_family, host, &listenaddr);
+
+		if (mss &&
+		    setsockopt(fdlisten, IPPROTO_TCP, TCP_MAXSEG,
+			       &mss, sizeof(mss)) == -1) {
+			perror("setsockopt TCP_MAXSEG");
+			exit(1);
+		}
+		if (bind(fdlisten, (const struct sockaddr *)&listenaddr, cfg_alen) == -1) {
+			perror("bind");
+			exit(1);
+		}
+		if (listen(fdlisten, 128) == -1) {
+			perror("listen");
+			exit(1);
+		}
+		do_accept(fdlisten);
+	}
+	buffer = mmap(NULL, chunk_size, PROT_READ | PROT_WRITE,
+			      MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (buffer == (char *)-1) {
+		perror("mmap");
+		exit(1);
+	}
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1) {
+		perror("socket");
+		exit(1);
+	}
+	apply_rcvsnd_buf(fd);
+
+	setup_sockaddr(cfg_family, host, &addr);
+
+	if (mss &&
+	    setsockopt(fd, IPPROTO_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) {
+		perror("setsockopt TCP_MAXSEG");
+		exit(1);
+	}
+	if (connect(fd, (const struct sockaddr *)&addr, cfg_alen) == -1) {
+		perror("connect");
+		exit(1);
+	}
+	if (max_pacing_rate &&
+	    setsockopt(fd, SOL_SOCKET, SO_MAX_PACING_RATE,
+		       &max_pacing_rate, sizeof(max_pacing_rate)) == -1)
+		perror("setsockopt SO_MAX_PACING_RATE");
+
+	if (zflg && setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY,
+			       &on, sizeof(on)) == -1) {
+		perror("setsockopt SO_ZEROCOPY, (-z option disabled)");
+		zflg = 0;
+	}
+	while (total < FILE_SZ) {
+		long wr = FILE_SZ - total;
+
+		if (wr > chunk_size)
+			wr = chunk_size;
+		/* Note : we just want to fill the pipe with 0 bytes */
+		wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0);
+		if (wr <= 0)
+			break;
+		total += wr;
+	}
+	close(fd);
+	munmap(buffer, chunk_size);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
new file mode 100644
index 000000000000..e279051bc631
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso.c
@@ -0,0 +1,693 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <stddef.h>
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <net/if.h>
+#include <linux/in.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <netinet/if_ether.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#ifndef ETH_MAX_MTU
+#define ETH_MAX_MTU	0xFFFFU
+#endif
+
+#ifndef UDP_SEGMENT
+#define UDP_SEGMENT		103
+#endif
+
+#ifndef UDP_MAX_SEGMENTS
+#define UDP_MAX_SEGMENTS	(1 << 6UL)
+#endif
+
+#define CONST_MTU_TEST	1500
+
+#define CONST_HDRLEN_V4		(sizeof(struct iphdr) + sizeof(struct udphdr))
+#define CONST_HDRLEN_V6		(sizeof(struct ip6_hdr) + sizeof(struct udphdr))
+
+#define CONST_MSS_V4		(CONST_MTU_TEST - CONST_HDRLEN_V4)
+#define CONST_MSS_V6		(CONST_MTU_TEST - CONST_HDRLEN_V6)
+
+#define CONST_MAX_SEGS_V4	(ETH_MAX_MTU / CONST_MSS_V4)
+#define CONST_MAX_SEGS_V6	(ETH_MAX_MTU / CONST_MSS_V6)
+
+static bool		cfg_do_ipv4;
+static bool		cfg_do_ipv6;
+static bool		cfg_do_connected;
+static bool		cfg_do_connectionless;
+static bool		cfg_do_msgmore;
+static bool		cfg_do_setsockopt;
+static int		cfg_specific_test_id = -1;
+
+static const char	cfg_ifname[] = "lo";
+static unsigned short	cfg_port = 9000;
+
+static char buf[ETH_MAX_MTU];
+
+struct testcase {
+	int tlen;		/* send() buffer size, may exceed mss */
+	bool tfail;		/* send() call is expected to fail */
+	int gso_len;		/* mss after applying gso */
+	int r_num_mss;		/* recv(): number of calls of full mss */
+	int r_len_last;		/* recv(): size of last non-mss dgram, if any */
+};
+
+const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT;
+const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+
+struct testcase testcases_v4[] = {
+	{
+		/* no GSO: send a single byte */
+		.tlen = 1,
+		.r_len_last = 1,
+	},
+	{
+		/* no GSO: send a single MSS */
+		.tlen = CONST_MSS_V4,
+		.r_num_mss = 1,
+	},
+	{
+		/* no GSO: send a single MSS + 1B: fail */
+		.tlen = CONST_MSS_V4 + 1,
+		.tfail = true,
+	},
+	{
+		/* send a single MSS: will fail with GSO, because the segment
+		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
+		 */
+		.tlen = CONST_MSS_V4,
+		.gso_len = CONST_MSS_V4,
+		.tfail = true,
+		.r_num_mss = 1,
+	},
+	{
+		/* send a single MSS + 1B */
+		.tlen = CONST_MSS_V4 + 1,
+		.gso_len = CONST_MSS_V4,
+		.r_num_mss = 1,
+		.r_len_last = 1,
+	},
+	{
+		/* send exactly 2 MSS */
+		.tlen = CONST_MSS_V4 * 2,
+		.gso_len = CONST_MSS_V4,
+		.r_num_mss = 2,
+	},
+	{
+		/* send 2 MSS + 1B */
+		.tlen = (CONST_MSS_V4 * 2) + 1,
+		.gso_len = CONST_MSS_V4,
+		.r_num_mss = 2,
+		.r_len_last = 1,
+	},
+	{
+		/* send MAX segs */
+		.tlen = (ETH_MAX_MTU / CONST_MSS_V4) * CONST_MSS_V4,
+		.gso_len = CONST_MSS_V4,
+		.r_num_mss = (ETH_MAX_MTU / CONST_MSS_V4),
+	},
+
+	{
+		/* send MAX bytes */
+		.tlen = ETH_MAX_MTU - CONST_HDRLEN_V4,
+		.gso_len = CONST_MSS_V4,
+		.r_num_mss = CONST_MAX_SEGS_V4,
+		.r_len_last = ETH_MAX_MTU - CONST_HDRLEN_V4 -
+			      (CONST_MAX_SEGS_V4 * CONST_MSS_V4),
+	},
+	{
+		/* send MAX + 1: fail */
+		.tlen = ETH_MAX_MTU - CONST_HDRLEN_V4 + 1,
+		.gso_len = CONST_MSS_V4,
+		.tfail = true,
+	},
+	{
+		/* send a single 1B MSS: will fail, see single MSS above */
+		.tlen = 1,
+		.gso_len = 1,
+		.tfail = true,
+		.r_num_mss = 1,
+	},
+	{
+		/* send 2 1B segments */
+		.tlen = 2,
+		.gso_len = 1,
+		.r_num_mss = 2,
+	},
+	{
+		/* send 2B + 2B + 1B segments */
+		.tlen = 5,
+		.gso_len = 2,
+		.r_num_mss = 2,
+		.r_len_last = 1,
+	},
+	{
+		/* send max number of min sized segments */
+		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4,
+		.gso_len = 1,
+		.r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4,
+	},
+	{
+		/* send max number + 1 of min sized segments: fail */
+		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4 + 1,
+		.gso_len = 1,
+		.tfail = true,
+	},
+	{
+		/* EOL */
+	}
+};
+
+#ifndef IP6_MAX_MTU
+#define IP6_MAX_MTU	(ETH_MAX_MTU + sizeof(struct ip6_hdr))
+#endif
+
+struct testcase testcases_v6[] = {
+	{
+		/* no GSO: send a single byte */
+		.tlen = 1,
+		.r_len_last = 1,
+	},
+	{
+		/* no GSO: send a single MSS */
+		.tlen = CONST_MSS_V6,
+		.r_num_mss = 1,
+	},
+	{
+		/* no GSO: send a single MSS + 1B: fail */
+		.tlen = CONST_MSS_V6 + 1,
+		.tfail = true,
+	},
+	{
+		/* send a single MSS: will fail with GSO, because the segment
+		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
+		 */
+		.tlen = CONST_MSS_V6,
+		.gso_len = CONST_MSS_V6,
+		.tfail = true,
+		.r_num_mss = 1,
+	},
+	{
+		/* send a single MSS + 1B */
+		.tlen = CONST_MSS_V6 + 1,
+		.gso_len = CONST_MSS_V6,
+		.r_num_mss = 1,
+		.r_len_last = 1,
+	},
+	{
+		/* send exactly 2 MSS */
+		.tlen = CONST_MSS_V6 * 2,
+		.gso_len = CONST_MSS_V6,
+		.r_num_mss = 2,
+	},
+	{
+		/* send 2 MSS + 1B */
+		.tlen = (CONST_MSS_V6 * 2) + 1,
+		.gso_len = CONST_MSS_V6,
+		.r_num_mss = 2,
+		.r_len_last = 1,
+	},
+	{
+		/* send MAX segs */
+		.tlen = (IP6_MAX_MTU / CONST_MSS_V6) * CONST_MSS_V6,
+		.gso_len = CONST_MSS_V6,
+		.r_num_mss = (IP6_MAX_MTU / CONST_MSS_V6),
+	},
+
+	{
+		/* send MAX bytes */
+		.tlen = IP6_MAX_MTU - CONST_HDRLEN_V6,
+		.gso_len = CONST_MSS_V6,
+		.r_num_mss = CONST_MAX_SEGS_V6,
+		.r_len_last = IP6_MAX_MTU - CONST_HDRLEN_V6 -
+			      (CONST_MAX_SEGS_V6 * CONST_MSS_V6),
+	},
+	{
+		/* send MAX + 1: fail */
+		.tlen = IP6_MAX_MTU - CONST_HDRLEN_V6 + 1,
+		.gso_len = CONST_MSS_V6,
+		.tfail = true,
+	},
+	{
+		/* send a single 1B MSS: will fail, see single MSS above */
+		.tlen = 1,
+		.gso_len = 1,
+		.tfail = true,
+		.r_num_mss = 1,
+	},
+	{
+		/* send 2 1B segments */
+		.tlen = 2,
+		.gso_len = 1,
+		.r_num_mss = 2,
+	},
+	{
+		/* send 2B + 2B + 1B segments */
+		.tlen = 5,
+		.gso_len = 2,
+		.r_num_mss = 2,
+		.r_len_last = 1,
+	},
+	{
+		/* send max number of min sized segments */
+		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6,
+		.gso_len = 1,
+		.r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6,
+	},
+	{
+		/* send max number + 1 of min sized segments: fail */
+		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6 + 1,
+		.gso_len = 1,
+		.tfail = true,
+	},
+	{
+		/* EOL */
+	}
+};
+
+static unsigned int get_device_mtu(int fd, const char *ifname)
+{
+	struct ifreq ifr;
+
+	memset(&ifr, 0, sizeof(ifr));
+
+	strcpy(ifr.ifr_name, ifname);
+
+	if (ioctl(fd, SIOCGIFMTU, &ifr))
+		error(1, errno, "ioctl get mtu");
+
+	return ifr.ifr_mtu;
+}
+
+static void __set_device_mtu(int fd, const char *ifname, unsigned int mtu)
+{
+	struct ifreq ifr;
+
+	memset(&ifr, 0, sizeof(ifr));
+
+	ifr.ifr_mtu = mtu;
+	strcpy(ifr.ifr_name, ifname);
+
+	if (ioctl(fd, SIOCSIFMTU, &ifr))
+		error(1, errno, "ioctl set mtu");
+}
+
+static void set_device_mtu(int fd, int mtu)
+{
+	int val;
+
+	val = get_device_mtu(fd, cfg_ifname);
+	fprintf(stderr, "device mtu (orig): %u\n", val);
+
+	__set_device_mtu(fd, cfg_ifname, mtu);
+	val = get_device_mtu(fd, cfg_ifname);
+	if (val != mtu)
+		error(1, 0, "unable to set device mtu to %u\n", val);
+
+	fprintf(stderr, "device mtu (test): %u\n", val);
+}
+
+static void set_pmtu_discover(int fd, bool is_ipv4)
+{
+	int level, name, val;
+
+	if (is_ipv4) {
+		level	= SOL_IP;
+		name	= IP_MTU_DISCOVER;
+		val	= IP_PMTUDISC_DO;
+	} else {
+		level	= SOL_IPV6;
+		name	= IPV6_MTU_DISCOVER;
+		val	= IPV6_PMTUDISC_DO;
+	}
+
+	if (setsockopt(fd, level, name, &val, sizeof(val)))
+		error(1, errno, "setsockopt path mtu");
+}
+
+static unsigned int get_path_mtu(int fd, bool is_ipv4)
+{
+	socklen_t vallen;
+	unsigned int mtu;
+	int ret;
+
+	vallen = sizeof(mtu);
+	if (is_ipv4)
+		ret = getsockopt(fd, SOL_IP, IP_MTU, &mtu, &vallen);
+	else
+		ret = getsockopt(fd, SOL_IPV6, IPV6_MTU, &mtu, &vallen);
+
+	if (ret)
+		error(1, errno, "getsockopt mtu");
+
+
+	fprintf(stderr, "path mtu (read):  %u\n", mtu);
+	return mtu;
+}
+
+/* very wordy version of system("ip route add dev lo mtu 1500 127.0.0.3/32") */
+static void set_route_mtu(int mtu, bool is_ipv4)
+{
+	struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+	struct nlmsghdr *nh;
+	struct rtattr *rta;
+	struct rtmsg *rt;
+	char data[NLMSG_ALIGN(sizeof(*nh)) +
+		  NLMSG_ALIGN(sizeof(*rt)) +
+		  NLMSG_ALIGN(RTA_LENGTH(sizeof(addr6))) +
+		  NLMSG_ALIGN(RTA_LENGTH(sizeof(int))) +
+		  NLMSG_ALIGN(RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)))];
+	int fd, ret, alen, off = 0;
+
+	alen = is_ipv4 ? sizeof(addr4) : sizeof(addr6);
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (fd == -1)
+		error(1, errno, "socket netlink");
+
+	memset(data, 0, sizeof(data));
+
+	nh = (void *)data;
+	nh->nlmsg_type = RTM_NEWROUTE;
+	nh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE;
+	off += NLMSG_ALIGN(sizeof(*nh));
+
+	rt = (void *)(data + off);
+	rt->rtm_family = is_ipv4 ? AF_INET : AF_INET6;
+	rt->rtm_table = RT_TABLE_MAIN;
+	rt->rtm_dst_len = alen << 3;
+	rt->rtm_protocol = RTPROT_BOOT;
+	rt->rtm_scope = RT_SCOPE_UNIVERSE;
+	rt->rtm_type = RTN_UNICAST;
+	off += NLMSG_ALIGN(sizeof(*rt));
+
+	rta = (void *)(data + off);
+	rta->rta_type = RTA_DST;
+	rta->rta_len = RTA_LENGTH(alen);
+	if (is_ipv4)
+		memcpy(RTA_DATA(rta), &addr4, alen);
+	else
+		memcpy(RTA_DATA(rta), &addr6, alen);
+	off += NLMSG_ALIGN(rta->rta_len);
+
+	rta = (void *)(data + off);
+	rta->rta_type = RTA_OIF;
+	rta->rta_len = RTA_LENGTH(sizeof(int));
+	*((int *)(RTA_DATA(rta))) = 1; //if_nametoindex("lo");
+	off += NLMSG_ALIGN(rta->rta_len);
+
+	/* MTU is a subtype in a metrics type */
+	rta = (void *)(data + off);
+	rta->rta_type = RTA_METRICS;
+	rta->rta_len = RTA_LENGTH(0) + RTA_LENGTH(sizeof(int));
+	off += NLMSG_ALIGN(rta->rta_len);
+
+	/* now fill MTU subtype. Note that it fits within above rta_len */
+	rta = (void *)(((char *) rta) + RTA_LENGTH(0));
+	rta->rta_type = RTAX_MTU;
+	rta->rta_len = RTA_LENGTH(sizeof(int));
+	*((int *)(RTA_DATA(rta))) = mtu;
+
+	nh->nlmsg_len = off;
+
+	ret = sendto(fd, data, off, 0, (void *)&nladdr, sizeof(nladdr));
+	if (ret != off)
+		error(1, errno, "send netlink: %uB != %uB\n", ret, off);
+
+	if (close(fd))
+		error(1, errno, "close netlink");
+
+	fprintf(stderr, "route mtu (test): %u\n", mtu);
+}
+
+static bool __send_one(int fd, struct msghdr *msg, int flags)
+{
+	int ret;
+
+	ret = sendmsg(fd, msg, flags);
+	if (ret == -1 &&
+	    (errno == EMSGSIZE || errno == ENOMEM || errno == EINVAL))
+		return false;
+	if (ret == -1)
+		error(1, errno, "sendmsg");
+	if (ret != msg->msg_iov->iov_len)
+		error(1, 0, "sendto: %d != %lu", ret, msg->msg_iov->iov_len);
+	if (msg->msg_flags)
+		error(1, 0, "sendmsg: return flags 0x%x\n", msg->msg_flags);
+
+	return true;
+}
+
+static bool send_one(int fd, int len, int gso_len,
+		     struct sockaddr *addr, socklen_t alen)
+{
+	char control[CMSG_SPACE(sizeof(uint16_t))] = {0};
+	struct msghdr msg = {0};
+	struct iovec iov = {0};
+	struct cmsghdr *cm;
+
+	iov.iov_base = buf;
+	iov.iov_len = len;
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
+	msg.msg_name = addr;
+	msg.msg_namelen = alen;
+
+	if (gso_len && !cfg_do_setsockopt) {
+		msg.msg_control = control;
+		msg.msg_controllen = sizeof(control);
+
+		cm = CMSG_FIRSTHDR(&msg);
+		cm->cmsg_level = SOL_UDP;
+		cm->cmsg_type = UDP_SEGMENT;
+		cm->cmsg_len = CMSG_LEN(sizeof(uint16_t));
+		*((uint16_t *) CMSG_DATA(cm)) = gso_len;
+	}
+
+	/* If MSG_MORE, send 1 byte followed by remainder */
+	if (cfg_do_msgmore && len > 1) {
+		iov.iov_len = 1;
+		if (!__send_one(fd, &msg, MSG_MORE))
+			error(1, 0, "send 1B failed");
+
+		iov.iov_base++;
+		iov.iov_len = len - 1;
+	}
+
+	return __send_one(fd, &msg, 0);
+}
+
+static int recv_one(int fd, int flags)
+{
+	int ret;
+
+	ret = recv(fd, buf, sizeof(buf), flags);
+	if (ret == -1 && errno == EAGAIN && (flags & MSG_DONTWAIT))
+		return 0;
+	if (ret == -1)
+		error(1, errno, "recv");
+
+	return ret;
+}
+
+static void run_one(struct testcase *test, int fdt, int fdr,
+		    struct sockaddr *addr, socklen_t alen)
+{
+	int i, ret, val, mss;
+	bool sent;
+
+	fprintf(stderr, "ipv%d tx:%d gso:%d %s\n",
+			addr->sa_family == AF_INET ? 4 : 6,
+			test->tlen, test->gso_len,
+			test->tfail ? "(fail)" : "");
+
+	val = test->gso_len;
+	if (cfg_do_setsockopt) {
+		if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val)))
+			error(1, errno, "setsockopt udp segment");
+	}
+
+	sent = send_one(fdt, test->tlen, test->gso_len, addr, alen);
+	if (sent && test->tfail)
+		error(1, 0, "send succeeded while expecting failure");
+	if (!sent && !test->tfail)
+		error(1, 0, "send failed while expecting success");
+	if (!sent)
+		return;
+
+	if (test->gso_len)
+		mss = test->gso_len;
+	else
+		mss = addr->sa_family == AF_INET ? CONST_MSS_V4 : CONST_MSS_V6;
+
+
+	/* Recv all full MSS datagrams */
+	for (i = 0; i < test->r_num_mss; i++) {
+		ret = recv_one(fdr, 0);
+		if (ret != mss)
+			error(1, 0, "recv.%d: %d != %d", i, ret, mss);
+	}
+
+	/* Recv the non-full last datagram, if tlen was not a multiple of mss */
+	if (test->r_len_last) {
+		ret = recv_one(fdr, 0);
+		if (ret != test->r_len_last)
+			error(1, 0, "recv.%d: %d != %d (last)",
+			      i, ret, test->r_len_last);
+	}
+
+	/* Verify received all data */
+	ret = recv_one(fdr, MSG_DONTWAIT);
+	if (ret)
+		error(1, 0, "recv: unexpected datagram");
+}
+
+static void run_all(int fdt, int fdr, struct sockaddr *addr, socklen_t alen)
+{
+	struct testcase *tests, *test;
+
+	tests = addr->sa_family == AF_INET ? testcases_v4 : testcases_v6;
+
+	for (test = tests; test->tlen; test++) {
+		/* if a specific test is given, then skip all others */
+		if (cfg_specific_test_id == -1 ||
+		    cfg_specific_test_id == test - tests)
+			run_one(test, fdt, fdr, addr, alen);
+	}
+}
+
+static void run_test(struct sockaddr *addr, socklen_t alen)
+{
+	struct timeval tv = { .tv_usec = 100 * 1000 };
+	int fdr, fdt, val;
+
+	fdr = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fdr == -1)
+		error(1, errno, "socket r");
+
+	if (bind(fdr, addr, alen))
+		error(1, errno, "bind");
+
+	/* Have tests fail quickly instead of hang */
+	if (setsockopt(fdr, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+		error(1, errno, "setsockopt rcv timeout");
+
+	fdt = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fdt == -1)
+		error(1, errno, "socket t");
+
+	/* Do not fragment these datagrams: only succeed if GSO works */
+	set_pmtu_discover(fdt, addr->sa_family == AF_INET);
+
+	if (cfg_do_connectionless) {
+		set_device_mtu(fdt, CONST_MTU_TEST);
+		run_all(fdt, fdr, addr, alen);
+	}
+
+	if (cfg_do_connected) {
+		set_device_mtu(fdt, CONST_MTU_TEST + 100);
+		set_route_mtu(CONST_MTU_TEST, addr->sa_family == AF_INET);
+
+		if (connect(fdt, addr, alen))
+			error(1, errno, "connect");
+
+		val = get_path_mtu(fdt, addr->sa_family == AF_INET);
+		if (val != CONST_MTU_TEST)
+			error(1, 0, "bad path mtu %u\n", val);
+
+		run_all(fdt, fdr, addr, 0 /* use connected addr */);
+	}
+
+	if (close(fdt))
+		error(1, errno, "close t");
+	if (close(fdr))
+		error(1, errno, "close r");
+}
+
+static void run_test_v4(void)
+{
+	struct sockaddr_in addr = {0};
+
+	addr.sin_family = AF_INET;
+	addr.sin_port = htons(cfg_port);
+	addr.sin_addr = addr4;
+
+	run_test((void *)&addr, sizeof(addr));
+}
+
+static void run_test_v6(void)
+{
+	struct sockaddr_in6 addr = {0};
+
+	addr.sin6_family = AF_INET6;
+	addr.sin6_port = htons(cfg_port);
+	addr.sin6_addr = addr6;
+
+	run_test((void *)&addr, sizeof(addr));
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "46cCmst:")) != -1) {
+		switch (c) {
+		case '4':
+			cfg_do_ipv4 = true;
+			break;
+		case '6':
+			cfg_do_ipv6 = true;
+			break;
+		case 'c':
+			cfg_do_connected = true;
+			break;
+		case 'C':
+			cfg_do_connectionless = true;
+			break;
+		case 'm':
+			cfg_do_msgmore = true;
+			break;
+		case 's':
+			cfg_do_setsockopt = true;
+			break;
+		case 't':
+			cfg_specific_test_id = strtoul(optarg, NULL, 0);
+			break;
+		default:
+			error(1, 0, "%s: parse error", argv[0]);
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+
+	if (cfg_do_ipv4)
+		run_test_v4();
+	if (cfg_do_ipv6)
+		run_test_v6();
+
+	fprintf(stderr, "OK\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/net/udpgso.sh b/tools/testing/selftests/net/udpgso.sh
new file mode 100755
index 000000000000..fec24f584fe9
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso.sh
@@ -0,0 +1,29 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgso regression tests
+
+echo "ipv4 cmsg"
+./in_netns.sh ./udpgso -4 -C
+
+echo "ipv4 setsockopt"
+./in_netns.sh ./udpgso -4 -C -s
+
+echo "ipv6 cmsg"
+./in_netns.sh ./udpgso -6 -C
+
+echo "ipv6 setsockopt"
+./in_netns.sh ./udpgso -6 -C -s
+
+echo "ipv4 connected"
+./in_netns.sh ./udpgso -4 -c
+
+# blocked on 2nd loopback address
+# echo "ipv6 connected"
+# ./in_netns.sh ./udpgso -6 -c
+
+echo "ipv4 msg_more"
+./in_netns.sh ./udpgso -4 -C -m
+
+echo "ipv6 msg_more"
+./in_netns.sh ./udpgso -6 -C -m
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
new file mode 100755
index 000000000000..792fa4d0285e
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -0,0 +1,74 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgso benchmarks
+
+wake_children() {
+	local -r jobs="$(jobs -p)"
+
+	if [[ "${jobs}" != "" ]]; then
+		kill -1 ${jobs} 2>/dev/null
+	fi
+}
+trap wake_children EXIT
+
+run_one() {
+	local -r args=$@
+
+	./udpgso_bench_rx &
+	./udpgso_bench_rx -t &
+
+	./udpgso_bench_tx ${args}
+}
+
+run_in_netns() {
+	local -r args=$@
+
+	./in_netns.sh $0 __subprocess ${args}
+}
+
+run_udp() {
+	local -r args=$@
+
+	echo "udp"
+	run_in_netns ${args}
+
+	echo "udp gso"
+	run_in_netns ${args} -S
+
+	echo "udp gso zerocopy"
+	run_in_netns ${args} -S -z
+}
+
+run_tcp() {
+	local -r args=$@
+
+	echo "tcp"
+	run_in_netns ${args} -t
+
+	echo "tcp zerocopy"
+	run_in_netns ${args} -t -z
+}
+
+run_all() {
+	local -r core_args="-l 4"
+	local -r ipv4_args="${core_args} -4 -D 127.0.0.1"
+	local -r ipv6_args="${core_args} -6 -D ::1"
+
+	echo "ipv4"
+	run_tcp "${ipv4_args}"
+	run_udp "${ipv4_args}"
+
+	echo "ipv6"
+	run_tcp "${ipv4_args}"
+	run_udp "${ipv6_args}"
+}
+
+if [[ $# -eq 0 ]]; then
+	run_all
+elif [[ $1 == "__subprocess" ]]; then
+	shift
+	run_one $@
+else
+	run_in_netns $@
+fi
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
new file mode 100644
index 000000000000..727cf67a3f75
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <limits.h>
+#include <linux/errqueue.h>
+#include <linux/if_packet.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+static int  cfg_port		= 8000;
+static bool cfg_tcp;
+static bool cfg_verify;
+
+static bool interrupted;
+static unsigned long packets, bytes;
+
+static void sigint_handler(int signum)
+{
+	if (signum == SIGINT)
+		interrupted = true;
+}
+
+static unsigned long gettimeofday_ms(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static void do_poll(int fd)
+{
+	struct pollfd pfd;
+	int ret;
+
+	pfd.events = POLLIN;
+	pfd.revents = 0;
+	pfd.fd = fd;
+
+	do {
+		ret = poll(&pfd, 1, 10);
+		if (ret == -1)
+			error(1, errno, "poll");
+		if (ret == 0)
+			continue;
+		if (pfd.revents != POLLIN)
+			error(1, errno, "poll: 0x%x expected 0x%x\n",
+					pfd.revents, POLLIN);
+	} while (!ret && !interrupted);
+}
+
+static int do_socket(bool do_tcp)
+{
+	struct sockaddr_in6 addr = {0};
+	int fd, val;
+
+	fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket");
+
+	val = 1 << 21;
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val)))
+		error(1, errno, "setsockopt rcvbuf");
+	val = 1;
+	if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val)))
+		error(1, errno, "setsockopt reuseport");
+
+	addr.sin6_family =	PF_INET6;
+	addr.sin6_port =	htons(cfg_port);
+	addr.sin6_addr =	in6addr_any;
+	if (bind(fd, (void *) &addr, sizeof(addr)))
+		error(1, errno, "bind");
+
+	if (do_tcp) {
+		int accept_fd = fd;
+
+		if (listen(accept_fd, 1))
+			error(1, errno, "listen");
+
+		do_poll(accept_fd);
+
+		fd = accept(accept_fd, NULL, NULL);
+		if (fd == -1)
+			error(1, errno, "accept");
+		if (close(accept_fd))
+			error(1, errno, "close accept fd");
+	}
+
+	return fd;
+}
+
+/* Flush all outstanding bytes for the tcp receive queue */
+static void do_flush_tcp(int fd)
+{
+	int ret;
+
+	while (true) {
+		/* MSG_TRUNC flushes up to len bytes */
+		ret = recv(fd, NULL, 1 << 21, MSG_TRUNC | MSG_DONTWAIT);
+		if (ret == -1 && errno == EAGAIN)
+			return;
+		if (ret == -1)
+			error(1, errno, "flush");
+		if (ret == 0) {
+			/* client detached */
+			exit(0);
+		}
+
+		packets++;
+		bytes += ret;
+	}
+
+}
+
+static char sanitized_char(char val)
+{
+	return (val >= 'a' && val <= 'z') ? val : '.';
+}
+
+static void do_verify_udp(const char *data, int len)
+{
+	char cur = data[0];
+	int i;
+
+	/* verify contents */
+	if (cur < 'a' || cur > 'z')
+		error(1, 0, "data initial byte out of range");
+
+	for (i = 1; i < len; i++) {
+		if (cur == 'z')
+			cur = 'a';
+		else
+			cur++;
+
+		if (data[i] != cur)
+			error(1, 0, "data[%d]: len %d, %c(%hhu) != %c(%hhu)\n",
+			      i, len,
+			      sanitized_char(data[i]), data[i],
+			      sanitized_char(cur), cur);
+	}
+}
+
+/* Flush all outstanding datagrams. Verify first few bytes of each. */
+static void do_flush_udp(int fd)
+{
+	static char rbuf[ETH_DATA_LEN];
+	int ret, len, budget = 256;
+
+	len = cfg_verify ? sizeof(rbuf) : 0;
+	while (budget--) {
+		/* MSG_TRUNC will make return value full datagram length */
+		ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+		if (ret == -1 && errno == EAGAIN)
+			return;
+		if (ret == -1)
+			error(1, errno, "recv");
+		if (len) {
+			if (ret == 0)
+				error(1, errno, "recv: 0 byte datagram\n");
+
+			do_verify_udp(rbuf, ret);
+		}
+
+		packets++;
+		bytes += ret;
+	}
+}
+
+static void usage(const char *filepath)
+{
+	error(1, 0, "Usage: %s [-tv] [-p port]", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "ptv")) != -1) {
+		switch (c) {
+		case 'p':
+			cfg_port = htons(strtoul(optarg, NULL, 0));
+			break;
+		case 't':
+			cfg_tcp = true;
+			break;
+		case 'v':
+			cfg_verify = true;
+			break;
+		}
+	}
+
+	if (optind != argc)
+		usage(argv[0]);
+
+	if (cfg_tcp && cfg_verify)
+		error(1, 0, "TODO: implement verify mode for tcp");
+}
+
+static void do_recv(void)
+{
+	unsigned long tnow, treport;
+	int fd;
+
+	fd = do_socket(cfg_tcp);
+
+	treport = gettimeofday_ms() + 1000;
+	do {
+		do_poll(fd);
+
+		if (cfg_tcp)
+			do_flush_tcp(fd);
+		else
+			do_flush_udp(fd);
+
+		tnow = gettimeofday_ms();
+		if (tnow > treport) {
+			if (packets)
+				fprintf(stderr,
+					"%s rx: %6lu MB/s %8lu calls/s\n",
+					cfg_tcp ? "tcp" : "udp",
+					bytes >> 20, packets);
+			bytes = packets = 0;
+			treport = tnow + 1000;
+		}
+
+	} while (!interrupted);
+
+	if (close(fd))
+		error(1, errno, "close");
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+
+	signal(SIGINT, sigint_handler);
+
+	do_recv();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
new file mode 100644
index 000000000000..e821564053cf
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -0,0 +1,420 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <netinet/if_ether.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#ifndef ETH_MAX_MTU
+#define ETH_MAX_MTU 0xFFFFU
+#endif
+
+#ifndef UDP_SEGMENT
+#define UDP_SEGMENT		103
+#endif
+
+#ifndef SO_ZEROCOPY
+#define SO_ZEROCOPY	60
+#endif
+
+#ifndef MSG_ZEROCOPY
+#define MSG_ZEROCOPY	0x4000000
+#endif
+
+#define NUM_PKT		100
+
+static bool	cfg_cache_trash;
+static int	cfg_cpu		= -1;
+static int	cfg_connected	= true;
+static int	cfg_family	= PF_UNSPEC;
+static uint16_t	cfg_mss;
+static int	cfg_payload_len	= (1472 * 42);
+static int	cfg_port	= 8000;
+static int	cfg_runtime_ms	= -1;
+static bool	cfg_segment;
+static bool	cfg_sendmmsg;
+static bool	cfg_tcp;
+static bool	cfg_zerocopy;
+
+static socklen_t cfg_alen;
+static struct sockaddr_storage cfg_dst_addr;
+
+static bool interrupted;
+static char buf[NUM_PKT][ETH_MAX_MTU];
+
+static void sigint_handler(int signum)
+{
+	if (signum == SIGINT)
+		interrupted = true;
+}
+
+static unsigned long gettimeofday_ms(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static int set_cpu(int cpu)
+{
+	cpu_set_t mask;
+
+	CPU_ZERO(&mask);
+	CPU_SET(cpu, &mask);
+	if (sched_setaffinity(0, sizeof(mask), &mask))
+		error(1, 0, "setaffinity %d", cpu);
+
+	return 0;
+}
+
+static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
+{
+	struct sockaddr_in6 *addr6 = (void *) sockaddr;
+	struct sockaddr_in *addr4 = (void *) sockaddr;
+
+	switch (domain) {
+	case PF_INET:
+		addr4->sin_family = AF_INET;
+		addr4->sin_port = htons(cfg_port);
+		if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+			error(1, 0, "ipv4 parse error: %s", str_addr);
+		break;
+	case PF_INET6:
+		addr6->sin6_family = AF_INET6;
+		addr6->sin6_port = htons(cfg_port);
+		if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+			error(1, 0, "ipv6 parse error: %s", str_addr);
+		break;
+	default:
+		error(1, 0, "illegal domain");
+	}
+}
+
+static void flush_zerocopy(int fd)
+{
+	struct msghdr msg = {0};	/* flush */
+	int ret;
+
+	while (1) {
+		ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+		if (ret == -1 && errno == EAGAIN)
+			break;
+		if (ret == -1)
+			error(1, errno, "errqueue");
+		if (msg.msg_flags != (MSG_ERRQUEUE | MSG_CTRUNC))
+			error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags);
+		msg.msg_flags = 0;
+	}
+}
+
+static int send_tcp(int fd, char *data)
+{
+	int ret, done = 0, count = 0;
+
+	while (done < cfg_payload_len) {
+		ret = send(fd, data + done, cfg_payload_len - done,
+			   cfg_zerocopy ? MSG_ZEROCOPY : 0);
+		if (ret == -1)
+			error(1, errno, "write");
+
+		done += ret;
+		count++;
+	}
+
+	return count;
+}
+
+static int send_udp(int fd, char *data)
+{
+	int ret, total_len, len, count = 0;
+
+	total_len = cfg_payload_len;
+
+	while (total_len) {
+		len = total_len < cfg_mss ? total_len : cfg_mss;
+
+		ret = sendto(fd, data, len, cfg_zerocopy ? MSG_ZEROCOPY : 0,
+			     cfg_connected ? NULL : (void *)&cfg_dst_addr,
+			     cfg_connected ? 0 : cfg_alen);
+		if (ret == -1)
+			error(1, errno, "write");
+		if (ret != len)
+			error(1, errno, "write: %uB != %uB\n", ret, len);
+
+		total_len -= len;
+		count++;
+	}
+
+	return count;
+}
+
+static int send_udp_sendmmsg(int fd, char *data)
+{
+	const int max_nr_msg = ETH_MAX_MTU / ETH_DATA_LEN;
+	struct mmsghdr mmsgs[max_nr_msg];
+	struct iovec iov[max_nr_msg];
+	unsigned int off = 0, left;
+	int i = 0, ret;
+
+	memset(mmsgs, 0, sizeof(mmsgs));
+
+	left = cfg_payload_len;
+	while (left) {
+		if (i == max_nr_msg)
+			error(1, 0, "sendmmsg: exceeds max_nr_msg");
+
+		iov[i].iov_base = data + off;
+		iov[i].iov_len = cfg_mss < left ? cfg_mss : left;
+
+		mmsgs[i].msg_hdr.msg_iov = iov + i;
+		mmsgs[i].msg_hdr.msg_iovlen = 1;
+
+		off += iov[i].iov_len;
+		left -= iov[i].iov_len;
+		i++;
+	}
+
+	ret = sendmmsg(fd, mmsgs, i, cfg_zerocopy ? MSG_ZEROCOPY : 0);
+	if (ret == -1)
+		error(1, errno, "sendmmsg");
+
+	return ret;
+}
+
+static void send_udp_segment_cmsg(struct cmsghdr *cm)
+{
+	uint16_t *valp;
+
+	cm->cmsg_level = SOL_UDP;
+	cm->cmsg_type = UDP_SEGMENT;
+	cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss));
+	valp = (void *)CMSG_DATA(cm);
+	*valp = cfg_mss;
+}
+
+static int send_udp_segment(int fd, char *data)
+{
+	char control[CMSG_SPACE(sizeof(cfg_mss))] = {0};
+	struct msghdr msg = {0};
+	struct iovec iov = {0};
+	int ret;
+
+	iov.iov_base = data;
+	iov.iov_len = cfg_payload_len;
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
+	msg.msg_control = control;
+	msg.msg_controllen = sizeof(control);
+	send_udp_segment_cmsg(CMSG_FIRSTHDR(&msg));
+
+	msg.msg_name = (void *)&cfg_dst_addr;
+	msg.msg_namelen = cfg_alen;
+
+	ret = sendmsg(fd, &msg, cfg_zerocopy ? MSG_ZEROCOPY : 0);
+	if (ret == -1)
+		error(1, errno, "sendmsg");
+	if (ret != iov.iov_len)
+		error(1, 0, "sendmsg: %u != %lu\n", ret, iov.iov_len);
+
+	return 1;
+}
+
+static void usage(const char *filepath)
+{
+	error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]",
+		    filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int max_len, hdrlen;
+	int c;
+
+	while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) {
+		switch (c) {
+		case '4':
+			if (cfg_family != PF_UNSPEC)
+				error(1, 0, "Pass one of -4 or -6");
+			cfg_family = PF_INET;
+			cfg_alen = sizeof(struct sockaddr_in);
+			break;
+		case '6':
+			if (cfg_family != PF_UNSPEC)
+				error(1, 0, "Pass one of -4 or -6");
+			cfg_family = PF_INET6;
+			cfg_alen = sizeof(struct sockaddr_in6);
+			break;
+		case 'c':
+			cfg_cache_trash = true;
+			break;
+		case 'C':
+			cfg_cpu = strtol(optarg, NULL, 0);
+			break;
+		case 'D':
+			setup_sockaddr(cfg_family, optarg, &cfg_dst_addr);
+			break;
+		case 'l':
+			cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
+			break;
+		case 'm':
+			cfg_sendmmsg = true;
+			break;
+		case 'p':
+			cfg_port = strtoul(optarg, NULL, 0);
+			break;
+		case 's':
+			cfg_payload_len = strtoul(optarg, NULL, 0);
+			break;
+		case 'S':
+			cfg_segment = true;
+			break;
+		case 't':
+			cfg_tcp = true;
+			break;
+		case 'u':
+			cfg_connected = false;
+			break;
+		case 'z':
+			cfg_zerocopy = true;
+			break;
+		}
+	}
+
+	if (optind != argc)
+		usage(argv[0]);
+
+	if (cfg_family == PF_UNSPEC)
+		error(1, 0, "must pass one of -4 or -6");
+	if (cfg_tcp && !cfg_connected)
+		error(1, 0, "connectionless tcp makes no sense");
+	if (cfg_segment && cfg_sendmmsg)
+		error(1, 0, "cannot combine segment offload and sendmmsg");
+
+	if (cfg_family == PF_INET)
+		hdrlen = sizeof(struct iphdr) + sizeof(struct udphdr);
+	else
+		hdrlen = sizeof(struct ip6_hdr) + sizeof(struct udphdr);
+
+	cfg_mss = ETH_DATA_LEN - hdrlen;
+	max_len = ETH_MAX_MTU - hdrlen;
+
+	if (cfg_payload_len > max_len)
+		error(1, 0, "payload length %u exceeds max %u",
+		      cfg_payload_len, max_len);
+}
+
+static void set_pmtu_discover(int fd, bool is_ipv4)
+{
+	int level, name, val;
+
+	if (is_ipv4) {
+		level	= SOL_IP;
+		name	= IP_MTU_DISCOVER;
+		val	= IP_PMTUDISC_DO;
+	} else {
+		level	= SOL_IPV6;
+		name	= IPV6_MTU_DISCOVER;
+		val	= IPV6_PMTUDISC_DO;
+	}
+
+	if (setsockopt(fd, level, name, &val, sizeof(val)))
+		error(1, errno, "setsockopt path mtu");
+}
+
+int main(int argc, char **argv)
+{
+	unsigned long num_msgs, num_sends;
+	unsigned long tnow, treport, tstop;
+	int fd, i, val;
+
+	parse_opts(argc, argv);
+
+	if (cfg_cpu > 0)
+		set_cpu(cfg_cpu);
+
+	for (i = 0; i < sizeof(buf[0]); i++)
+		buf[0][i] = 'a' + (i % 26);
+	for (i = 1; i < NUM_PKT; i++)
+		memcpy(buf[i], buf[0], sizeof(buf[0]));
+
+	signal(SIGINT, sigint_handler);
+
+	fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket");
+
+	if (cfg_zerocopy) {
+		val = 1;
+		if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val)))
+			error(1, errno, "setsockopt zerocopy");
+	}
+
+	if (cfg_connected &&
+	    connect(fd, (void *)&cfg_dst_addr, cfg_alen))
+		error(1, errno, "connect");
+
+	if (cfg_segment)
+		set_pmtu_discover(fd, cfg_family == PF_INET);
+
+	num_msgs = num_sends = 0;
+	tnow = gettimeofday_ms();
+	tstop = tnow + cfg_runtime_ms;
+	treport = tnow + 1000;
+
+	i = 0;
+	do {
+		if (cfg_tcp)
+			num_sends += send_tcp(fd, buf[i]);
+		else if (cfg_segment)
+			num_sends += send_udp_segment(fd, buf[i]);
+		else if (cfg_sendmmsg)
+			num_sends += send_udp_sendmmsg(fd, buf[i]);
+		else
+			num_sends += send_udp(fd, buf[i]);
+		num_msgs++;
+
+		if (cfg_zerocopy && ((num_msgs & 0xF) == 0))
+			flush_zerocopy(fd);
+
+		tnow = gettimeofday_ms();
+		if (tnow > treport) {
+			fprintf(stderr,
+				"%s tx: %6lu MB/s %8lu calls/s %6lu msg/s\n",
+				cfg_tcp ? "tcp" : "udp",
+				(num_msgs * cfg_payload_len) >> 20,
+				num_sends, num_msgs);
+			num_msgs = num_sends = 0;
+			treport = tnow + 1000;
+		}
+
+		/* cold cache when writing buffer */
+		if (cfg_cache_trash)
+			i = ++i < NUM_PKT ? i : 0;
+
+	} while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop));
+
+	if (close(fd))
+		error(1, errno, "close");
+
+	return 0;
+}