Resguardo inicial

linux-7.2.3/tools/testing/selftests/net/mptcp/.gitignore

@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+mptcp_connect
+mptcp_diag
+mptcp_inq
+mptcp_sockopt
+pm_nl_ctl
+*.pcap

linux-7.2.3/tools/testing/selftests/net/mptcp/Makefile

@@ -0,0 +1,39 @@
+# SPDX-License-Identifier: GPL-2.0
+
+top_srcdir = ../../../../..
+
+CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
+CFLAGS += -I$(top_srcdir)/tools/include
+
+TEST_PROGS := \
+	diag.sh \
+	mptcp_connect.sh \
+	mptcp_connect_checksum.sh \
+	mptcp_connect_mmap.sh \
+	mptcp_connect_sendfile.sh \
+	mptcp_connect_splice.sh \
+	mptcp_join.sh \
+	mptcp_sockopt.sh \
+	pm_netlink.sh \
+	simult_flows.sh \
+	userspace_pm.sh \
+# end of TEST_PROGS
+
+TEST_GEN_FILES := \
+	mptcp_connect \
+	mptcp_diag \
+	mptcp_inq \
+	mptcp_sockopt \
+	pm_nl_ctl \
+# end of TEST_GEN_FILES
+
+TEST_FILES := \
+	mptcp_lib.sh \
+	settings \
+# end of TEST_FILES
+
+TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh)
+
+EXTRA_CLEAN := *.pcap
+
+include ../../lib.mk

linux-7.2.3/tools/testing/selftests/net/mptcp/config

@@ -0,0 +1,36 @@
+CONFIG_INET_DIAG=m
+CONFIG_INET_MPTCP_DIAG=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IPV6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_KALLSYMS=y
+CONFIG_MPTCP=y
+CONFIG_MPTCP_IPV6=y
+CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_PEDIT=m
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_CLS_FW=m
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_ADVANCED=y
+CONFIG_NETFILTER_NETLINK=m
+CONFIG_NETFILTER_XTABLES=m
+CONFIG_NETFILTER_XTABLES_LEGACY=y
+CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NETFILTER_XT_MATCH_LENGTH=m
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
+CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NET_SCH_INGRESS=m
+CONFIG_NET_SCH_NETEM=m
+CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NFT_COMPAT=m
+CONFIG_NFT_SOCKET=m
+CONFIG_NFT_TPROXY=m
+CONFIG_SYN_COOKIES=y
+CONFIG_VETH=y

linux-7.2.3/tools/testing/selftests/net/mptcp/diag.sh

@@ -0,0 +1,447 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Double quotes to prevent globbing and word splitting is recommended in new
+# code but we accept it, especially because there were too many before having
+# address all other issues detected by shellcheck.
+#shellcheck disable=SC2086
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+ns=""
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
+ret=0
+
+flush_pids()
+{
+	# mptcp_connect in join mode will sleep a bit before completing,
+	# give it some time
+	sleep 1.1
+
+	ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGUSR1 &>/dev/null
+
+	for _ in $(seq $((timeout_poll * 10))); do
+		[ -z "$(ip netns pids "${ns}")" ] && break
+		sleep 0.1
+	done
+}
+
+# This function is used in the cleanup trap
+#shellcheck disable=SC2317,SC2329
+cleanup()
+{
+	ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null
+
+	mptcp_lib_ns_exit "${ns}"
+}
+
+mptcp_lib_check_mptcp
+mptcp_lib_check_tools ip ss
+
+get_msk_inuse()
+{
+	ip netns exec $ns cat /proc/net/protocols | awk '$1~/^MPTCP$/{print $3}'
+}
+
+__chk_nr()
+{
+	local command="$1"
+	local expected=$2
+	local msg="$3"
+	local skip="${4-SKIP}"
+	local nr
+
+	nr=$(eval $command)
+
+	mptcp_lib_print_title "$msg"
+	if [ "$nr" != "$expected" ]; then
+		if [ "$nr" = "$skip" ] && ! mptcp_lib_expect_all_features; then
+			mptcp_lib_pr_skip "Feature probably not supported"
+			mptcp_lib_result_skip "${msg}"
+		else
+			mptcp_lib_pr_fail "expected $expected found $nr"
+			mptcp_lib_result_fail "${msg}"
+			ret=${KSFT_FAIL}
+		fi
+	else
+		mptcp_lib_pr_ok
+		mptcp_lib_result_pass "${msg}"
+	fi
+}
+
+__chk_msk_nr()
+{
+	local condition=$1
+	shift 1
+
+	__chk_nr "ss -inmHMN $ns | $condition" "$@"
+}
+
+chk_msk_nr()
+{
+	__chk_msk_nr "grep -c token:" "$@"
+}
+
+chk_listener_nr()
+{
+	local expected=$1
+	local msg="$2"
+
+	__chk_nr "ss -nlHMON $ns | wc -l" "$expected" "$msg - mptcp" 0
+	__chk_nr "ss -nlHtON $ns | wc -l" "$expected" "$msg - subflows"
+}
+
+wait_msk_nr()
+{
+	local condition="grep -c token:"
+	local expected=$1
+	local timeout=20
+	local msg nr
+	local max=0
+	local i=0
+
+	shift 1
+	msg=$*
+
+	while [ $i -lt $timeout ]; do
+		nr=$(ss -inmHMN $ns | $condition)
+		[ $nr == $expected ] && break;
+		[ $nr -gt $max ] && max=$nr
+		i=$((i + 1))
+		sleep 1
+	done
+
+	mptcp_lib_print_title "$msg"
+	if [ $i -ge $timeout ]; then
+		mptcp_lib_pr_fail "timeout while expecting $expected max $max last $nr"
+		mptcp_lib_result_fail "${msg} # timeout"
+		ret=${KSFT_FAIL}
+	elif [ $nr != $expected ]; then
+		mptcp_lib_pr_fail "expected $expected found $nr"
+		mptcp_lib_result_fail "${msg} # unexpected result"
+		ret=${KSFT_FAIL}
+	else
+		mptcp_lib_pr_ok
+		mptcp_lib_result_pass "${msg}"
+	fi
+}
+
+chk_msk_fallback_nr()
+{
+	__chk_msk_nr "grep -c fallback" "$@"
+}
+
+chk_msk_remote_key_nr()
+{
+	__chk_msk_nr "grep -c remote_key" "$@"
+}
+
+__chk_listen()
+{
+	local filter="$1"
+	local expected=$2
+	local msg="$3"
+
+	__chk_nr "ss -N $ns -Ml '$filter' | grep -c LISTEN" "$expected" "$msg" 0
+}
+
+chk_msk_listen()
+{
+	lport=$1
+
+	# destination port search should always return empty list
+	__chk_listen "dport $lport" 0 "listen match for dport $lport"
+
+	# should return 'our' mptcp listen socket
+	__chk_listen "sport $lport" 1 "listen match for sport $lport"
+
+	__chk_listen "src inet:0.0.0.0:$lport" 1 "listen match for saddr and sport"
+
+	__chk_listen "" 1 "all listen sockets"
+
+	nr=$(ss -Ml $filter | wc -l)
+}
+
+chk_msk_inuse()
+{
+	local expected=$1
+	local msg="....chk ${2:-${expected}} msk in use"
+	local listen_nr
+
+	if [ "${expected}" -eq 0 ]; then
+		msg+=" after flush"
+	fi
+
+	listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN)
+	expected=$((expected + listen_nr))
+
+	for _ in $(seq 10); do
+		if [ "$(get_msk_inuse)" -eq $expected ]; then
+			break
+		fi
+		sleep 0.1
+	done
+
+	__chk_nr get_msk_inuse $expected "${msg}" 0
+}
+
+# $1: cestab nr
+chk_msk_cestab()
+{
+	local expected=$1
+	local msg="....chk ${2:-${expected}} cestab"
+
+	if [ "${expected}" -eq 0 ]; then
+		msg+=" after flush"
+	fi
+
+	__chk_nr "mptcp_lib_get_counter ${ns} MPTcpExtMPCurrEstab" \
+		 "${expected}" "${msg}" ""
+}
+
+chk_dump_one()
+{
+	local ss_token
+	local token
+	local msg
+
+	ss_token="$(ss -inmHMN $ns |
+		    mptcp_lib_get_info_value "token" "token")"
+
+	token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\
+		 awk -F':[ \t]+' '/^token/ {print $2}')"
+
+	msg="....chk dump_one"
+
+	mptcp_lib_print_title "$msg"
+	if [ -n "$ss_token" ] && [ "$ss_token" = "$token" ]; then
+		mptcp_lib_pr_ok
+		mptcp_lib_result_pass "${msg}"
+	else
+		mptcp_lib_pr_fail "expected $ss_token found $token"
+		mptcp_lib_result_fail "${msg}"
+		ret=${KSFT_FAIL}
+	fi
+}
+
+chk_dump_subflow()
+{
+	local inet_diag_token
+	local subflow_line
+	local ss_output
+	local ss_token
+	local msg
+
+	ss_output=$(ss -tniN $ns)
+
+	subflow_line=$(echo "$ss_output" | \
+		       grep -m1 -Eo '[0-9.]+:[0-9].+ +[0-9.]+:[0-9.]+')
+
+	ss_token=$(echo "$ss_output" | grep -m1 -Eo 'token:[^ ]+')
+
+	inet_diag_token=$(ip netns exec $ns ./mptcp_diag -s "$subflow_line" | \
+			  grep -Eo 'token:[^ ]+')
+
+	msg="....chk dump_subflow"
+
+	mptcp_lib_print_title "$msg"
+	if [ -n "$ss_token" ] && [ "$ss_token" = "$inet_diag_token" ]; then
+		mptcp_lib_pr_ok
+		mptcp_lib_result_pass "${msg}"
+	else
+		mptcp_lib_pr_fail "expected $ss_token found $inet_diag_token"
+		mptcp_lib_result_fail "${msg}"
+		ret=${KSFT_FAIL}
+	fi
+}
+
+msk_info_get_value()
+{
+	local port="${1}"
+	local info="${2}"
+
+	ss -N "${ns}" -inHM dport "${port}" | \
+		mptcp_lib_get_info_value "${info}" "${info}"
+}
+
+chk_msk_info()
+{
+	local port="${1}"
+	local info="${2}"
+	local cnt="${3}"
+	local msg="....chk ${info}"
+	local delta_ms=250  # half what we waited before, just to be sure
+	local now
+
+	now=$(msk_info_get_value "${port}" "${info}")
+
+	mptcp_lib_print_title "${msg}"
+	if { [ -z "${cnt}" ] || [ -z "${now}" ]; } &&
+	   ! mptcp_lib_expect_all_features; then
+		mptcp_lib_pr_skip "Feature probably not supported"
+		mptcp_lib_result_skip "${msg}"
+	elif [ "$((cnt + delta_ms))" -lt "${now}" ]; then
+		mptcp_lib_pr_ok
+		mptcp_lib_result_pass "${msg}"
+	else
+		mptcp_lib_pr_fail "value of ${info} changed by $((now - cnt))ms," \
+				  "expected at least ${delta_ms}ms"
+		mptcp_lib_result_fail "${msg}"
+		ret=${KSFT_FAIL}
+	fi
+}
+
+chk_last_time_info()
+{
+	local port="${1}"
+	local data_sent data_recv ack_recv
+
+	data_sent=$(msk_info_get_value "${port}" "last_data_sent")
+	data_recv=$(msk_info_get_value "${port}" "last_data_recv")
+	ack_recv=$(msk_info_get_value "${port}" "last_ack_recv")
+
+	sleep 0.5  # wait to check after if the timestamps difference
+
+	chk_msk_info "${port}" "last_data_sent" "${data_sent}"
+	chk_msk_info "${port}" "last_data_recv" "${data_recv}"
+	chk_msk_info "${port}" "last_ack_recv" "${ack_recv}"
+}
+
+wait_connected()
+{
+	local listener_ns="${1}"
+	local port="${2}"
+
+	local port_hex i
+
+	port_hex="$(printf "%04X" "${port}")"
+	for i in $(seq 10); do
+		ip netns exec ${listener_ns} grep -q " 0100007F:${port_hex} " /proc/net/tcp && break
+		sleep 0.1
+	done
+}
+
+chk_sndbuf()
+{
+	local server_sndbuf client_sndbuf msg
+	local port=${1}
+
+	msg="....chk sndbuf server/client"
+	server_sndbuf=$(ss -N "${ns}" -inmHM "sport" "${port}" | \
+			sed -n 's/.*tb\([0-9]\+\).*/\1/p')
+	client_sndbuf=$(ss -N "${ns}" -inmHM "dport" "${port}" | \
+			sed -n 's/.*tb\([0-9]\+\).*/\1/p')
+
+	mptcp_lib_print_title "${msg}"
+	if [ -z "${server_sndbuf}" ] || [ -z "${client_sndbuf}" ]; then
+		mptcp_lib_pr_fail "sndbuf S=${server_sndbuf} C=${client_sndbuf}"
+		mptcp_lib_result_fail "${msg}"
+		ret=${KSFT_FAIL}
+	elif [ "${server_sndbuf}" != "${client_sndbuf}" ]; then
+		mptcp_lib_pr_fail "sndbuf S=${server_sndbuf} != C=${client_sndbuf}"
+		mptcp_lib_result_fail "${msg}"
+		ret=${KSFT_FAIL}
+	else
+		mptcp_lib_pr_ok
+		mptcp_lib_result_pass "${msg}"
+	fi
+}
+
+
+trap cleanup EXIT
+mptcp_lib_ns_init ns
+
+echo "a" | \
+	timeout ${timeout_test} \
+		ip netns exec $ns \
+			./mptcp_connect -p 10000 -l -t ${timeout_poll} -w 20 \
+				0.0.0.0 >/dev/null &
+mptcp_lib_wait_local_port_listen $ns 10000
+chk_msk_nr 0 "no msk on netns creation"
+chk_msk_listen 10000
+
+echo "b" | \
+	timeout ${timeout_test} \
+		ip netns exec $ns \
+			./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} -w 20 \
+				127.0.0.1 >/dev/null &
+wait_connected $ns 10000
+chk_msk_nr 2 "after MPC handshake"
+chk_sndbuf 10000
+chk_last_time_info 10000
+chk_msk_remote_key_nr 2 "....chk remote_key"
+chk_msk_fallback_nr 0 "....chk no fallback"
+chk_msk_inuse 2
+chk_msk_cestab 2
+chk_dump_one
+chk_dump_subflow
+flush_pids
+
+chk_msk_inuse 0 "2->0"
+chk_msk_cestab 0 "2->0"
+
+echo "a" | \
+	timeout ${timeout_test} \
+		ip netns exec $ns \
+			./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} -w 20 \
+				0.0.0.0 >/dev/null &
+mptcp_lib_wait_local_port_listen $ns 10001
+echo "b" | \
+	timeout ${timeout_test} \
+		ip netns exec $ns \
+			./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} -w 20 \
+				127.0.0.1 >/dev/null &
+wait_connected $ns 10001
+chk_msk_fallback_nr 1 "check fallback"
+chk_msk_inuse 1
+chk_msk_cestab 1
+flush_pids
+
+chk_msk_inuse 0 "1->0"
+chk_msk_cestab 0 "1->0"
+
+NR_CLIENTS=100
+for I in $(seq 1 $NR_CLIENTS); do
+	echo "a" | \
+		timeout ${timeout_test} \
+			ip netns exec $ns \
+				./mptcp_connect -p $((I+10001)) -l -w 20 \
+					-t ${timeout_poll} 0.0.0.0 >/dev/null &
+done
+mptcp_lib_wait_local_port_listen $ns $((NR_CLIENTS + 10001))
+
+for I in $(seq 1 $NR_CLIENTS); do
+	echo "b" | \
+		timeout ${timeout_test} \
+			ip netns exec $ns \
+				./mptcp_connect -p $((I+10001)) -w 20 \
+					-t ${timeout_poll} 127.0.0.1 >/dev/null &
+done
+
+wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
+chk_msk_inuse $((NR_CLIENTS*2)) "many"
+chk_msk_cestab $((NR_CLIENTS*2)) "many"
+flush_pids
+
+chk_msk_inuse 0 "many->0"
+chk_msk_cestab 0 "many->0"
+
+chk_listener_nr 0 "no listener sockets"
+NR_SERVERS=100
+for I in $(seq 1 $NR_SERVERS); do
+	ip netns exec $ns ./mptcp_connect -p $((I + 20001)) \
+		-t ${timeout_poll} -l 0.0.0.0 >/dev/null 2>&1 &
+done
+mptcp_lib_wait_local_port_listen $ns $((NR_SERVERS + 20001))
+
+chk_listener_nr $NR_SERVERS "many listener sockets"
+
+# graceful termination
+for I in $(seq 1 $NR_SERVERS); do
+	echo a | ip netns exec $ns ./mptcp_connect -p $((I + 20001)) 127.0.0.1 >/dev/null 2>&1 &
+done
+flush_pids
+
+mptcp_lib_result_print_all_tap
+exit $ret

linux-7.2.3/tools/testing/selftests/net/mptcp/mptcp_connect.sh

@@ -0,0 +1,964 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Double quotes to prevent globbing and word splitting is recommended in new
+# code but we accept it, especially because there were too many before having
+# address all other issues detected by shellcheck.
+#shellcheck disable=SC2086
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+time_start=$(date +%s)
+
+optstring="S:R:d:e:l:r:h4cm:f:tC"
+ret=0
+final_ret=0
+sin=""
+sout=""
+cin_disconnect=""
+cin=""
+cout=""
+capture=false
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
+ipv6=true
+ethtool_random_on=true
+tc_delay="$((RANDOM%50))"
+tc_loss=$((RANDOM%101))
+testmode=""
+sndbuf=0
+rcvbuf=0
+options_log=true
+do_tcp=0
+checksum=false
+filesize=0
+connect_per_transfer=1
+port=$((10000 - 1))
+
+if [ $tc_loss -eq 100 ];then
+	tc_loss=1%
+elif [ $tc_loss -ge 10 ]; then
+	tc_loss=0.$tc_loss%
+elif [ $tc_loss -ge 1 ]; then
+	tc_loss=0.0$tc_loss%
+else
+	tc_loss=""
+fi
+
+usage() {
+	echo "Usage: $0 [ -a ]"
+	echo -e "\t-d: tc/netem delay in milliseconds, e.g. \"-d 10\" (default random)"
+	echo -e "\t-l: tc/netem loss percentage, e.g. \"-l 0.02\" (default random)"
+	echo -e "\t-r: tc/netem reorder mode, e.g. \"-r 25% 50% gap 5\", use "-r 0" to disable reordering (default random)"
+	echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)"
+	echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)"
+	echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
+	echo -e "\t-f: size of file to transfer in bytes (default random)"
+	echo -e "\t-S: set sndbuf value (default: use kernel default)"
+	echo -e "\t-R: set rcvbuf value (default: use kernel default)"
+	echo -e "\t-m: test mode (poll, sendfile; default: poll)"
+	echo -e "\t-t: also run tests with TCP (use twice to non-fallback tcp)"
+	echo -e "\t-C: enable the MPTCP data checksum"
+}
+
+while getopts "$optstring" option;do
+	case "$option" in
+	"h")
+		usage $0
+		exit ${KSFT_PASS}
+		;;
+	"d")
+		if [ $OPTARG -ge 0 ];then
+			tc_delay="$OPTARG"
+		else
+			echo "-d requires numeric argument, got \"$OPTARG\"" 1>&2
+			exit ${KSFT_FAIL}
+		fi
+		;;
+	"e")
+		ethtool_args="$ethtool_args $OPTARG off"
+		ethtool_random_on=false
+		;;
+	"l")
+		tc_loss="$OPTARG"
+		;;
+	"r")
+		tc_reorder="$OPTARG"
+		;;
+	"4")
+		ipv6=false
+		;;
+	"c")
+		capture=true
+		;;
+	"S")
+		if [ $OPTARG -ge 0 ];then
+			sndbuf="$OPTARG"
+		else
+			echo "-S requires numeric argument, got \"$OPTARG\"" 1>&2
+			exit ${KSFT_FAIL}
+		fi
+		;;
+	"R")
+		if [ $OPTARG -ge 0 ];then
+			rcvbuf="$OPTARG"
+		else
+			echo "-R requires numeric argument, got \"$OPTARG\"" 1>&2
+			exit ${KSFT_FAIL}
+		fi
+		;;
+	"m")
+		testmode="$OPTARG"
+		;;
+	"f")
+		filesize="$OPTARG"
+		;;
+	"t")
+		do_tcp=$((do_tcp+1))
+		;;
+	"C")
+		checksum=true
+		;;
+	"?")
+		usage $0
+		exit ${KSFT_FAIL}
+		;;
+	esac
+done
+
+ns1=""
+ns2=""
+ns3=""
+ns4=""
+
+TEST_GROUP=""
+
+# This function is used in the cleanup trap
+#shellcheck disable=SC2317,SC2329
+cleanup()
+{
+	rm -f "$cin_disconnect"
+	rm -f "$cin" "$cout"
+	rm -f "$sin" "$sout"
+	rm -f "$capout"
+
+	mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns3}" "${ns4}"
+}
+
+mptcp_lib_check_mptcp
+mptcp_lib_check_kallsyms
+mptcp_lib_check_tools ip tc
+
+sin=$(mktemp)
+sout=$(mktemp)
+cin=$(mktemp)
+cout=$(mktemp)
+capout=$(mktemp)
+cin_disconnect="$cin".disconnect
+trap cleanup EXIT
+
+mptcp_lib_ns_init ns1 ns2 ns3 ns4
+
+#  "$ns1"              ns2                    ns3                     ns4
+# ns1eth2    ns2eth1   ns2eth3      ns3eth2   ns3eth4       ns4eth3
+#                           - drop 1% ->            reorder 25%
+#                           <- TSO off -
+
+ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth1 netns "$ns2"
+ip link add ns2eth3 netns "$ns2" type veth peer name ns3eth2 netns "$ns3"
+ip link add ns3eth4 netns "$ns3" type veth peer name ns4eth3 netns "$ns4"
+
+ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth2
+ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth2 nodad
+
+ip -net "$ns1" link set ns1eth2 up
+ip -net "$ns1" route add default via 10.0.1.2
+ip -net "$ns1" route add default via dead:beef:1::2
+
+ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1
+ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad
+ip -net "$ns2" link set ns2eth1 up
+
+ip -net "$ns2" addr add 10.0.2.1/24 dev ns2eth3
+ip -net "$ns2" addr add dead:beef:2::1/64 dev ns2eth3 nodad
+ip -net "$ns2" link set ns2eth3 up
+ip -net "$ns2" route add default via 10.0.2.2
+ip -net "$ns2" route add default via dead:beef:2::2
+ip netns exec "$ns2" sysctl -q net.ipv4.ip_forward=1
+ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.forwarding=1
+
+ip -net "$ns3" addr add 10.0.2.2/24 dev ns3eth2
+ip -net "$ns3" addr add dead:beef:2::2/64 dev ns3eth2 nodad
+ip -net "$ns3" link set ns3eth2 up
+
+ip -net "$ns3" addr add 10.0.3.2/24 dev ns3eth4
+ip -net "$ns3" addr add dead:beef:3::2/64 dev ns3eth4 nodad
+ip -net "$ns3" link set ns3eth4 up
+ip -net "$ns3" route add default via 10.0.2.1
+ip -net "$ns3" route add default via dead:beef:2::1
+ip netns exec "$ns3" sysctl -q net.ipv4.ip_forward=1
+ip netns exec "$ns3" sysctl -q net.ipv6.conf.all.forwarding=1
+
+ip -net "$ns4" addr add 10.0.3.1/24 dev ns4eth3
+ip -net "$ns4" addr add dead:beef:3::1/64 dev ns4eth3 nodad
+ip -net "$ns4" link set ns4eth3 up
+ip -net "$ns4" route add default via 10.0.3.2
+ip -net "$ns4" route add default via dead:beef:3::2
+
+if $checksum; then
+	for i in "$ns1" "$ns2" "$ns3" "$ns4";do
+		ip netns exec $i sysctl -q net.mptcp.checksum_enabled=1
+	done
+fi
+
+if $capture; then
+	rndh="${ns1:4}"
+	mptcp_lib_pr_info "Packet capture files will have this prefix: ${rndh}-"
+fi
+
+set_ethtool_flags() {
+	local ns="$1"
+	local dev="$2"
+	local flags="$3"
+
+	if ip netns exec $ns ethtool -K $dev $flags 2>/dev/null; then
+		mptcp_lib_pr_info "set $ns dev $dev: ethtool -K $flags"
+	fi
+}
+
+set_random_ethtool_flags() {
+	local flags=""
+	local r=$RANDOM
+
+	local pick1=$((r & 1))
+	local pick2=$((r & 2))
+	local pick3=$((r & 4))
+
+	[ $pick1 -ne 0 ] && flags="tso off"
+	[ $pick2 -ne 0 ] && flags="$flags gso off"
+	[ $pick3 -ne 0 ] && flags="$flags gro off"
+
+	[ -z "$flags" ] && return
+
+	set_ethtool_flags "$1" "$2" "$flags"
+}
+
+if $ethtool_random_on;then
+	set_random_ethtool_flags "$ns3" ns3eth2
+	set_random_ethtool_flags "$ns4" ns4eth3
+else
+	set_ethtool_flags "$ns3" ns3eth2 "$ethtool_args"
+	set_ethtool_flags "$ns4" ns4eth3 "$ethtool_args"
+fi
+
+print_larger_title() {
+	# here we don't have the time, a bit longer for the alignment
+	MPTCP_LIB_TEST_FORMAT="%02u %-69s" \
+		mptcp_lib_print_title "${@}"
+}
+
+check_mptcp_disabled()
+{
+	local disabled_ns
+	mptcp_lib_ns_init disabled_ns
+
+	print_larger_title "New MPTCP socket can be blocked via sysctl"
+
+	# mainly to cover more code
+	if ! ip netns exec ${disabled_ns} sysctl net.mptcp >/dev/null; then
+		mptcp_lib_pr_fail "not able to list net.mptcp sysctl knobs"
+		mptcp_lib_result_fail "not able to list net.mptcp sysctl knobs"
+		ret=${KSFT_FAIL}
+		return 1
+	fi
+
+	# net.mptcp.enabled should be enabled by default
+	if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then
+		mptcp_lib_pr_fail "net.mptcp.enabled sysctl is not 1 by default"
+		mptcp_lib_result_fail "net.mptcp.enabled sysctl is not 1 by default"
+		ret=${KSFT_FAIL}
+		return 1
+	fi
+	ip netns exec ${disabled_ns} sysctl -q net.mptcp.enabled=0
+
+	local err=0
+	LC_ALL=C ip netns exec ${disabled_ns} ./mptcp_connect -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \
+		grep -q "^socket: Protocol not available$" && err=1
+	mptcp_lib_ns_exit "${disabled_ns}"
+
+	if [ ${err} -eq 0 ]; then
+		mptcp_lib_pr_fail "New MPTCP socket cannot be blocked via sysctl"
+		mptcp_lib_result_fail "New MPTCP socket cannot be blocked via sysctl"
+		ret=${KSFT_FAIL}
+		return 1
+	fi
+
+	mptcp_lib_pr_ok
+	mptcp_lib_result_pass "New MPTCP socket can be blocked via sysctl"
+	return 0
+}
+
+do_ping()
+{
+	local listener_ns="$1"
+	local connector_ns="$2"
+	local connect_addr="$3"
+	local ping_args="-q -c 1"
+	local rc=0
+
+	if mptcp_lib_is_v6 "${connect_addr}"; then
+		$ipv6 || return 0
+		ping_args="${ping_args} -6"
+	fi
+
+	ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null || rc=1
+
+	if [ $rc -ne 0 ] ; then
+		mptcp_lib_pr_fail "$listener_ns -> $connect_addr connectivity"
+		ret=${KSFT_FAIL}
+
+		return 1
+	fi
+
+	return 0
+}
+
+do_transfer()
+{
+	local listener_ns="$1"
+	local connector_ns="$2"
+	local cl_proto="$3"
+	local srv_proto="$4"
+	local connect_addr="$5"
+	local local_addr="$6"
+	local extra_args="$7"
+
+	port=$((port + 1))
+
+	if [ "$rcvbuf" -gt 0 ]; then
+		extra_args+=" -R $rcvbuf"
+	fi
+
+	if [ "$sndbuf" -gt 0 ]; then
+		extra_args+=" -S $sndbuf"
+	fi
+
+	if [ -n "$testmode" ]; then
+		extra_args+=" -m $testmode"
+	fi
+
+	if [ -n "$extra_args" ] && $options_log; then
+		mptcp_lib_pr_info "extra options: $extra_args"
+	fi
+	options_log=false
+
+	:> "$cout"
+	:> "$sout"
+	:> "$capout"
+
+	local addr_port
+	addr_port=$(printf "%s:%d" ${connect_addr} ${port})
+	local pretty_title
+	pretty_title="$(printf "%.3s %-5s -> %.3s (%-20s) %-5s" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto})"
+	mptcp_lib_print_title "${pretty_title}"
+
+	local tap_title="${connector_ns:0:3} ${cl_proto} -> ${listener_ns:0:3} (${addr_port}) ${srv_proto}"
+
+	if $capture; then
+		local capuser
+		if [ -z $SUDO_USER ] ; then
+			capuser=""
+		else
+			capuser="-Z $SUDO_USER"
+		fi
+
+		local capfile="${rndh}-${connector_ns:0:3}-${listener_ns:0:3}-${cl_proto}-${srv_proto}-${connect_addr}-${port}"
+		local capopt="-i any -s 65535 -B 32768 ${capuser}"
+
+		ip netns exec ${listener_ns} tcpdump ${capopt} \
+			-w "${capfile}-listener.pcap" >> "${capout}" 2>&1 &
+		local cappid_listener=$!
+
+		if [ ${listener_ns} != ${connector_ns} ]; then
+			ip netns exec ${connector_ns} tcpdump ${capopt} \
+				-w "${capfile}-connector.pcap" >> "${capout}" 2>&1 &
+			local cappid_connector=$!
+		fi
+
+		sleep 1
+	fi
+
+	mptcp_lib_nstat_init "${listener_ns}"
+	if [ ${listener_ns} != ${connector_ns} ]; then
+		mptcp_lib_nstat_init "${connector_ns}"
+	fi
+
+	ip netns exec ${listener_ns} \
+		./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \
+			$extra_args $local_addr < "$sin" > "$sout" &
+	local spid=$!
+
+	mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}"
+
+	local start
+	start=$(date +%s%N)
+	ip netns exec ${connector_ns} \
+		./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \
+			$extra_args $connect_addr < "$cin" > "$cout" &
+	local cpid=$!
+
+	mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \
+		"${connector_ns}" "${port}" "${cpid}" "${spid}" &
+	local timeout_pid=$!
+
+	wait $cpid
+	local retc=$?
+	wait $spid
+	local rets=$?
+
+	if kill -0 $timeout_pid; then
+		# Finished before the timeout: kill the background job
+		mptcp_lib_kill_group_wait $timeout_pid
+		timeout_pid=0
+	fi
+
+	local stop
+	stop=$(date +%s%N)
+
+	if $capture; then
+		sleep 1
+		kill ${cappid_listener}
+		if [ ${listener_ns} != ${connector_ns} ]; then
+			kill ${cappid_connector}
+		fi
+	fi
+
+	mptcp_lib_nstat_get "${listener_ns}"
+	if [ ${listener_ns} != ${connector_ns} ]; then
+		mptcp_lib_nstat_get "${connector_ns}"
+	fi
+
+	local duration
+	duration=$(((stop-start) / 1000000))
+	printf "(duration %05sms) " "${duration}"
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then
+		mptcp_lib_pr_fail "client exit code $retc, server $rets"
+		mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}"
+
+		echo
+		cat "$capout"
+		mptcp_lib_result_fail "${TEST_GROUP}: ${tap_title}"
+		return 1
+	fi
+
+	mptcp_lib_check_transfer $sin $cout "file received by client"
+	retc=$?
+	mptcp_lib_check_transfer $cin $sout "file received by server"
+	rets=$?
+
+	local extra=""
+	local stat_synrx
+	local stat_ackrx
+	local stat_cookietx
+	local stat_cookierx
+	local stat_ooo
+	local stat_tcpfb
+	stat_synrx=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
+	stat_ackrx=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
+	stat_cookietx=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
+	stat_cookierx=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
+	stat_ooo=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue")
+	stat_tcpfb=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
+
+	expect_synrx=0
+	expect_ackrx=0
+
+	cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies)
+	cookies=${cookies##*=}
+
+	if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then
+		expect_synrx=${connect_per_transfer}
+		expect_ackrx=${connect_per_transfer}
+	fi
+
+	if [ ${stat_synrx} -lt ${expect_synrx} ]; then
+		mptcp_lib_pr_fail "lower MPC SYN rx (${stat_synrx})" \
+				  "than expected (${expect_synrx})"
+		retc=1
+	fi
+	if [ ${stat_ackrx} -lt ${expect_ackrx} ]; then
+		if [ ${stat_ooo} -eq 0 ]; then
+			mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx})" \
+					  "than expected (${expect_ackrx})"
+			rets=1
+		else
+			extra+=" [ Note ] fallback due to TCP OoO"
+		fi
+	fi
+
+	if $checksum; then
+		local csum_err_s
+		local csum_err_c
+		csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
+		csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
+
+		if [ $csum_err_s -gt 0 ]; then
+			mptcp_lib_pr_fail "server got ${csum_err_s} data checksum error[s]"
+			rets=1
+		fi
+
+		if [ $csum_err_c -gt 0 ]; then
+			mptcp_lib_pr_fail "client got ${csum_err_c} data checksum error[s]"
+			retc=1
+		fi
+	fi
+
+	if [ ${stat_ooo} -eq 0 ] && [ ${stat_tcpfb} -gt 0 ]; then
+		mptcp_lib_pr_fail "unexpected fallback to TCP"
+		rets=1
+	fi
+
+	if [ $cookies -eq 2 ];then
+		if [ $stat_cookietx -eq 0 ] ;then
+			extra+=" WARN: CookieSent: did not advance"
+		fi
+		if [ $stat_cookierx -eq 0 ] ;then
+			extra+=" WARN: CookieRecv: did not advance"
+		fi
+	else
+		if [ $stat_cookietx -gt 0 ] ;then
+			extra+=" WARN: CookieSent: changed"
+		fi
+		if [ $stat_cookierx -gt 0 ] ;then
+			extra+=" WARN: CookieRecv: changed"
+		fi
+	fi
+
+	if [ ${stat_synrx} -gt ${expect_synrx} ]; then
+		extra+=" WARN: SYNRX: expect ${expect_synrx},"
+		extra+=" got ${stat_synrx} (probably retransmissions)"
+	fi
+	if [ ${stat_ackrx} -gt ${expect_ackrx} ]; then
+		extra+=" WARN: ACKRX: expect ${expect_ackrx},"
+		extra+=" got ${stat_ackrx} (probably retransmissions)"
+	fi
+
+	if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then
+		mptcp_lib_pr_ok "${extra:1}"
+		mptcp_lib_result_pass "${TEST_GROUP}: ${tap_title}"
+	else
+		if [ -n "${extra}" ]; then
+			mptcp_lib_print_warn "${extra:1}"
+		fi
+		mptcp_lib_result_fail "${TEST_GROUP}: ${tap_title}"
+	fi
+
+	cat "$capout"
+	[ $retc -eq 0 ] && [ $rets -eq 0 ]
+}
+
+make_file()
+{
+	local name=$1
+	local who=$2
+	local SIZE=$filesize
+	local ksize
+	local rem
+
+	if [ $SIZE -eq 0 ]; then
+		local MAXSIZE=$((1024 * 1024 * 8))
+		local MINSIZE=$((1024 * 256))
+
+		SIZE=$(((RANDOM * RANDOM + MINSIZE) % MAXSIZE))
+	fi
+
+	ksize=$((SIZE / 1024))
+	rem=$((SIZE - (ksize * 1024)))
+
+	mptcp_lib_make_file $name 1024 $ksize
+	dd if=/dev/urandom conv=notrunc of="$name" oflag=append bs=1 count=$rem 2> /dev/null
+
+	echo "Created $name (size $(stat -c "%s" "$name") B) containing data sent by $who"
+}
+
+run_tests_lo()
+{
+	local listener_ns="$1"
+	local connector_ns="$2"
+	local connect_addr="$3"
+	local loopback="$4"
+	local extra_args="$5"
+	local lret=0
+
+	# skip if test programs are running inside same netns for subsequent runs.
+	if [ $loopback -eq 0 ] && [ ${listener_ns} = ${connector_ns} ]; then
+		return 0
+	fi
+
+	# skip if we don't want v6
+	if ! $ipv6 && mptcp_lib_is_v6 "${connect_addr}"; then
+		return 0
+	fi
+
+	local local_addr
+	if mptcp_lib_is_v6 "${connect_addr}"; then
+		local_addr="::"
+	else
+		local_addr="0.0.0.0"
+	fi
+
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return 1
+	fi
+
+	if [ $do_tcp -eq 0 ]; then
+		# don't bother testing fallback tcp except for loopback case.
+		if [ ${listener_ns} != ${connector_ns} ]; then
+			return 0
+		fi
+	fi
+
+	do_transfer ${listener_ns} ${connector_ns} MPTCP TCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return 1
+	fi
+
+	do_transfer ${listener_ns} ${connector_ns} TCP MPTCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return 1
+	fi
+
+	if [ $do_tcp -gt 1 ] ;then
+		do_transfer ${listener_ns} ${connector_ns} TCP TCP \
+			    ${connect_addr} ${local_addr} "${extra_args}"
+		lret=$?
+		if [ $lret -ne 0 ]; then
+			ret=$lret
+			return 1
+		fi
+	fi
+
+	return 0
+}
+
+run_tests()
+{
+	run_tests_lo $1 $2 $3 0
+}
+
+run_test_transparent()
+{
+	local connect_addr="$1"
+	local msg="$2"
+
+	local connector_ns="$ns1"
+	local listener_ns="$ns2"
+	local lret=0
+	local r6flag=""
+
+	TEST_GROUP="${msg}"
+
+	# skip if we don't want v6
+	if ! $ipv6 && mptcp_lib_is_v6 "${connect_addr}"; then
+		return 0
+	fi
+
+	# IP(V6)_TRANSPARENT has been added after TOS support which came with
+	# the required infrastructure in MPTCP sockopt code. To support TOS, the
+	# following function has been exported (T). Not great but better than
+	# checking for a specific kernel version.
+	if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then
+		mptcp_lib_pr_skip "${msg} not supported by the kernel"
+		mptcp_lib_result_skip "${TEST_GROUP}"
+		return
+	fi
+
+	if ! ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF"
+flush ruleset
+table inet mangle {
+	chain divert {
+		type filter hook prerouting priority -150;
+
+		meta l4proto tcp socket transparent 1 meta mark set 1 accept
+		tcp dport 20000 tproxy to :20000 meta mark set 1 accept
+	}
+}
+EOF
+	then
+		mptcp_lib_pr_skip "$msg, could not load nft ruleset"
+		mptcp_lib_fail_if_expected_feature "nft rules"
+		mptcp_lib_result_skip "${TEST_GROUP}"
+		return
+	fi
+
+	local local_addr
+	if mptcp_lib_is_v6 "${connect_addr}"; then
+		local_addr="::"
+		r6flag="-6"
+	else
+		local_addr="0.0.0.0"
+	fi
+
+	if ! ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100; then
+		ip netns exec "$listener_ns" nft flush ruleset
+		mptcp_lib_pr_skip "$msg, ip $r6flag rule failed"
+		mptcp_lib_fail_if_expected_feature "ip rule"
+		mptcp_lib_result_skip "${TEST_GROUP}"
+		return
+	fi
+
+	if ! ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100; then
+		ip netns exec "$listener_ns" nft flush ruleset
+		ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100
+		mptcp_lib_pr_skip "$msg, ip route add local $local_addr failed"
+		mptcp_lib_fail_if_expected_feature "ip route"
+		mptcp_lib_result_skip "${TEST_GROUP}"
+		return
+	fi
+
+	mptcp_lib_pr_info "test $msg"
+
+	port=$((20000 - 1))
+	local extra_args="-o TRANSPARENT"
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
+	lret=$?
+
+	ip netns exec "$listener_ns" nft flush ruleset
+	ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100
+	ip -net "$listener_ns" route del local $local_addr/0 dev lo table 100
+
+	if [ $lret -ne 0 ]; then
+		mptcp_lib_pr_fail "$msg, mptcp connection error"
+		ret=$lret
+		return 1
+	fi
+
+	mptcp_lib_pr_info "$msg pass"
+	return 0
+}
+
+run_tests_peekmode()
+{
+	local peekmode="$1"
+
+	TEST_GROUP="peek mode: ${peekmode}"
+	mptcp_lib_pr_info "with peek mode: ${peekmode}"
+	run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 "-P ${peekmode}"
+	run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-P ${peekmode}"
+}
+
+run_tests_mptfo()
+{
+	TEST_GROUP="MPTFO"
+
+	if ! mptcp_lib_kallsyms_has "mptcp_fastopen_"; then
+		mptcp_lib_pr_skip "TFO not supported by the kernel"
+		mptcp_lib_result_skip "${TEST_GROUP}"
+		return
+	fi
+
+	mptcp_lib_pr_info "with MPTFO start"
+	ip netns exec "$ns1" sysctl -q net.ipv4.tcp_fastopen=2
+	ip netns exec "$ns2" sysctl -q net.ipv4.tcp_fastopen=1
+
+	run_tests_lo "$ns1" "$ns2" 10.0.1.1 0 "-o MPTFO"
+	run_tests_lo "$ns1" "$ns2" 10.0.1.1 0 "-o MPTFO"
+
+	run_tests_lo "$ns1" "$ns2" dead:beef:1::1 0 "-o MPTFO"
+	run_tests_lo "$ns1" "$ns2" dead:beef:1::1 0 "-o MPTFO"
+
+	ip netns exec "$ns1" sysctl -q net.ipv4.tcp_fastopen=0
+	ip netns exec "$ns2" sysctl -q net.ipv4.tcp_fastopen=0
+	mptcp_lib_pr_info "with MPTFO end"
+}
+
+run_tests_disconnect()
+{
+	local old_cin=$cin
+	local old_sin=$sin
+
+	TEST_GROUP="full disconnect"
+
+	if ! mptcp_lib_kallsyms_has "mptcp_pm_data_reset$"; then
+		mptcp_lib_pr_skip "Full disconnect not supported"
+		mptcp_lib_result_skip "${TEST_GROUP}"
+		return
+	fi
+
+	cat $cin $cin $cin > "$cin".disconnect
+
+	# force do_transfer to cope with the multiple transmissions
+	sin="$cin.disconnect"
+	cin="$cin.disconnect"
+	cin_disconnect="$old_cin"
+	connect_per_transfer=3
+
+	mptcp_lib_pr_info "disconnect"
+	run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 "-I 3 -i $old_cin"
+	run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-I 3 -i $old_cin"
+
+	# restore previous status
+	sin=$old_sin
+	cin=$old_cin
+	cin_disconnect="$cin".disconnect
+	connect_per_transfer=1
+}
+
+display_time()
+{
+	time_end=$(date +%s)
+	time_run=$((time_end-time_start))
+
+	echo "Time: ${time_run} seconds"
+}
+
+log_if_error()
+{
+	local msg="$1"
+
+	if [ ${ret} -ne 0 ]; then
+		mptcp_lib_pr_fail "${msg}"
+
+		final_ret=${ret}
+		ret=${KSFT_PASS}
+
+		return ${final_ret}
+	fi
+}
+
+stop_if_error()
+{
+	if ! log_if_error "${@}"; then
+		display_time
+		mptcp_lib_result_print_all_tap
+		exit ${final_ret}
+	fi
+}
+
+make_file "$cin" "client"
+make_file "$sin" "server"
+
+mptcp_lib_subtests_last_ts_reset
+
+check_mptcp_disabled
+
+stop_if_error "The kernel configuration is not valid for MPTCP"
+
+print_larger_title "Validating network environment with pings"
+for sender in "$ns1" "$ns2" "$ns3" "$ns4";do
+	do_ping "$ns1" $sender 10.0.1.1
+	do_ping "$ns1" $sender dead:beef:1::1
+
+	do_ping "$ns2" $sender 10.0.1.2
+	do_ping "$ns2" $sender dead:beef:1::2
+	do_ping "$ns2" $sender 10.0.2.1
+	do_ping "$ns2" $sender dead:beef:2::1
+
+	do_ping "$ns3" $sender 10.0.2.2
+	do_ping "$ns3" $sender dead:beef:2::2
+	do_ping "$ns3" $sender 10.0.3.2
+	do_ping "$ns3" $sender dead:beef:3::2
+
+	do_ping "$ns4" $sender 10.0.3.1
+	do_ping "$ns4" $sender dead:beef:3::1
+done
+
+mptcp_lib_result_code "${ret}" "ping tests"
+
+stop_if_error "Could not even run ping tests"
+mptcp_lib_pr_ok
+
+[ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss delay ${tc_delay}ms
+tc_info="loss of $tc_loss "
+test "$tc_delay" -gt 0 && tc_info+="delay $tc_delay ms "
+
+reorder_delay=$((tc_delay / 4))
+
+if [ -z "${tc_reorder}" ]; then
+	reorder1=$((RANDOM%10))
+	reorder1=$((100 - reorder1))
+	reorder2=$((RANDOM%100))
+
+	if [ $reorder_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then
+		tc_reorder="reorder ${reorder1}% ${reorder2}%"
+		tc_info+="$tc_reorder with delay ${reorder_delay}ms "
+	fi
+elif [ "$tc_reorder" = "0" ];then
+	tc_reorder=""
+elif [ "$reorder_delay" -gt 0 ];then
+	# reordering requires some delay
+	tc_reorder="reorder $tc_reorder"
+	tc_info+="$tc_reorder with delay ${reorder_delay}ms "
+fi
+
+mptcp_lib_pr_info "Using ${tc_info}on ns3eth4"
+
+tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${reorder_delay}ms $tc_reorder
+
+TEST_GROUP="loopback v4"
+run_tests_lo "$ns1" "$ns1" 10.0.1.1 1
+stop_if_error "Could not even run loopback test"
+
+TEST_GROUP="loopback v6"
+run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1
+stop_if_error "Could not even run loopback v6 test"
+
+TEST_GROUP="multihosts"
+for sender in $ns1 $ns2 $ns3 $ns4;do
+	# ns1<->ns2 is not subject to reordering/tc delays. Use it to test
+	# mptcp syncookie support.
+	if [ $sender = $ns1 ]; then
+		ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2
+	else
+		ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=1
+	fi
+
+	run_tests "$ns1" $sender 10.0.1.1
+	run_tests "$ns1" $sender dead:beef:1::1
+
+	run_tests "$ns2" $sender 10.0.1.2
+	run_tests "$ns2" $sender dead:beef:1::2
+	run_tests "$ns2" $sender 10.0.2.1
+	run_tests "$ns2" $sender dead:beef:2::1
+
+	run_tests "$ns3" $sender 10.0.2.2
+	run_tests "$ns3" $sender dead:beef:2::2
+	run_tests "$ns3" $sender 10.0.3.2
+	run_tests "$ns3" $sender dead:beef:3::2
+
+	run_tests "$ns4" $sender 10.0.3.1
+	run_tests "$ns4" $sender dead:beef:3::1
+
+	log_if_error "Tests with $sender as a sender have failed"
+done
+
+run_tests_peekmode "saveWithPeek"
+run_tests_peekmode "saveAfterPeek"
+log_if_error "Tests with peek mode have failed"
+
+# MPTFO (MultiPath TCP Fatopen tests)
+run_tests_mptfo
+log_if_error "Tests with MPTFO have failed"
+
+# connect to ns4 ip address, ns2 should intercept/proxy
+run_test_transparent 10.0.3.1 "tproxy ipv4"
+run_test_transparent dead:beef:3::1 "tproxy ipv6"
+log_if_error "Tests with tproxy have failed"
+
+run_tests_disconnect
+log_if_error "Tests of the full disconnection have failed"
+
+display_time
+mptcp_lib_result_print_all_tap
+exit ${final_ret}

linux-7.2.3/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \
+	"$(dirname "${0}")/mptcp_connect.sh" -C "${@}"

linux-7.2.3/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \
+	"$(dirname "${0}")/mptcp_connect.sh" -m mmap "${@}"

linux-7.2.3/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \
+	"$(dirname "${0}")/mptcp_connect.sh" -m sendfile "${@}"

linux-7.2.3/tools/testing/selftests/net/mptcp/mptcp_connect_splice.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \
+	"$(dirname "${0}")/mptcp_connect.sh" -m splice "${@}"

linux-7.2.3/tools/testing/selftests/net/mptcp/mptcp_diag.c

@@ -0,0 +1,439 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Kylin Software */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+
+#include <arpa/inet.h>
+
+#include <netinet/in.h>
+
+#include <linux/compiler.h>
+#include <linux/inet_diag.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/sock_diag.h>
+#include <linux/tcp.h>
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
+#define parse_rtattr_nested(tb, max, rta) \
+	(parse_rtattr_flags((tb), (max), RTA_DATA(rta), RTA_PAYLOAD(rta), \
+			    NLA_F_NESTED))
+
+struct params {
+	__u32 target_token;
+	char subflow_addrs[1024];
+};
+
+struct mptcp_info {
+	__u8	mptcpi_subflows;
+	__u8	mptcpi_add_addr_signal;
+	__u8	mptcpi_add_addr_accepted;
+	__u8	mptcpi_subflows_max;
+	__u8	mptcpi_add_addr_signal_max;
+	__u8	mptcpi_add_addr_accepted_max;
+	__u32	mptcpi_flags;
+	__u32	mptcpi_token;
+	__u64	mptcpi_write_seq;
+	__u64	mptcpi_snd_una;
+	__u64	mptcpi_rcv_nxt;
+	__u8	mptcpi_local_addr_used;
+	__u8	mptcpi_local_addr_max;
+	__u8	mptcpi_csum_enabled;
+	__u32	mptcpi_retransmits;
+	__u64	mptcpi_bytes_retrans;
+	__u64	mptcpi_bytes_sent;
+	__u64	mptcpi_bytes_received;
+	__u64	mptcpi_bytes_acked;
+	__u8	mptcpi_subflows_total;
+	__u8	reserved[3];
+	__u32	mptcpi_last_data_sent;
+	__u32	mptcpi_last_data_recv;
+	__u32	mptcpi_last_ack_recv;
+};
+
+enum {
+	MPTCP_SUBFLOW_ATTR_UNSPEC,
+	MPTCP_SUBFLOW_ATTR_TOKEN_REM,
+	MPTCP_SUBFLOW_ATTR_TOKEN_LOC,
+	MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ,
+	MPTCP_SUBFLOW_ATTR_MAP_SEQ,
+	MPTCP_SUBFLOW_ATTR_MAP_SFSEQ,
+	MPTCP_SUBFLOW_ATTR_SSN_OFFSET,
+	MPTCP_SUBFLOW_ATTR_MAP_DATALEN,
+	MPTCP_SUBFLOW_ATTR_FLAGS,
+	MPTCP_SUBFLOW_ATTR_ID_REM,
+	MPTCP_SUBFLOW_ATTR_ID_LOC,
+	MPTCP_SUBFLOW_ATTR_PAD,
+
+	__MPTCP_SUBFLOW_ATTR_MAX
+};
+
+#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1)
+
+#define MPTCP_SUBFLOW_FLAG_MCAP_REM		_BITUL(0)
+#define MPTCP_SUBFLOW_FLAG_MCAP_LOC		_BITUL(1)
+#define MPTCP_SUBFLOW_FLAG_JOIN_REM		_BITUL(2)
+#define MPTCP_SUBFLOW_FLAG_JOIN_LOC		_BITUL(3)
+#define MPTCP_SUBFLOW_FLAG_BKUP_REM		_BITUL(4)
+#define MPTCP_SUBFLOW_FLAG_BKUP_LOC		_BITUL(5)
+#define MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED	_BITUL(6)
+#define MPTCP_SUBFLOW_FLAG_CONNECTED		_BITUL(7)
+#define MPTCP_SUBFLOW_FLAG_MAPVALID		_BITUL(8)
+
+#define rta_getattr(type, value)		(*(type *)RTA_DATA(value))
+
+static void __noreturn die_perror(const char *msg)
+{
+	perror(msg);
+	exit(1);
+}
+
+static void die_usage(int r)
+{
+	fprintf(stderr, "Usage:\n"
+			"mptcp_diag -t <token>\n"
+			"mptcp_diag -s \"<saddr>:<sport> <daddr>:<dport>\"\n");
+	exit(r);
+}
+
+static void send_query(int fd, struct inet_diag_req_v2 *r, __u32 proto)
+{
+	struct sockaddr_nl nladdr = {
+		.nl_family = AF_NETLINK
+	};
+	struct {
+		struct nlmsghdr nlh;
+		struct inet_diag_req_v2 r;
+	} req = {
+		.nlh = {
+			.nlmsg_len = sizeof(req),
+			.nlmsg_type = SOCK_DIAG_BY_FAMILY,
+			.nlmsg_flags = NLM_F_REQUEST
+		},
+		.r = *r
+	};
+	struct rtattr rta_proto;
+	struct iovec iov[6];
+	int iovlen = 0;
+
+	iov[iovlen++] = (struct iovec) {
+		.iov_base = &req,
+		.iov_len = sizeof(req)
+	};
+
+	if (proto == IPPROTO_MPTCP) {
+		rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL;
+		rta_proto.rta_len = RTA_LENGTH(sizeof(proto));
+
+		iov[iovlen++] = (struct iovec){ &rta_proto, sizeof(rta_proto)};
+		iov[iovlen++] = (struct iovec){ &proto, sizeof(proto)};
+		req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto));
+	}
+
+	struct msghdr msg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = iov,
+		.msg_iovlen = iovlen
+	};
+
+	for (;;) {
+		if (sendmsg(fd, &msg, 0) < 0) {
+			if (errno == EINTR)
+				continue;
+			die_perror("sendmsg");
+		}
+		break;
+	}
+}
+
+static void parse_rtattr_flags(struct rtattr *tb[], int max, struct rtattr *rta,
+			       int len, unsigned short flags)
+{
+	unsigned short type;
+
+	memset(tb, 0, sizeof(struct rtattr *) * (max + 1));
+	while (RTA_OK(rta, len)) {
+		type = rta->rta_type & ~flags;
+		if (type <= max && !tb[type])
+			tb[type] = rta;
+		rta = RTA_NEXT(rta, len);
+	}
+}
+
+static void print_info_msg(struct mptcp_info *info)
+{
+	printf("Token & Flags\n");
+	printf("token:        %x\n", info->mptcpi_token);
+	printf("flags:        %x\n", info->mptcpi_flags);
+	printf("csum_enabled: %u\n", info->mptcpi_csum_enabled);
+
+	printf("\nBasic Info\n");
+	printf("subflows:              %u\n", info->mptcpi_subflows);
+	printf("subflows_max:          %u\n", info->mptcpi_subflows_max);
+	printf("subflows_total:        %u\n", info->mptcpi_subflows_total);
+	printf("local_addr_used:       %u\n", info->mptcpi_local_addr_used);
+	printf("local_addr_max:        %u\n", info->mptcpi_local_addr_max);
+	printf("add_addr_signal:       %u\n", info->mptcpi_add_addr_signal);
+	printf("add_addr_accepted:     %u\n", info->mptcpi_add_addr_accepted);
+	printf("add_addr_signal_max:   %u\n", info->mptcpi_add_addr_signal_max);
+	printf("add_addr_accepted_max: %u\n", info->mptcpi_add_addr_accepted_max);
+
+	printf("\nTransmission Info\n");
+	printf("write_seq:        %llu\n", info->mptcpi_write_seq);
+	printf("snd_una:          %llu\n", info->mptcpi_snd_una);
+	printf("rcv_nxt:          %llu\n", info->mptcpi_rcv_nxt);
+	printf("last_data_sent:   %u\n", info->mptcpi_last_data_sent);
+	printf("last_data_recv:   %u\n", info->mptcpi_last_data_recv);
+	printf("last_ack_recv:    %u\n", info->mptcpi_last_ack_recv);
+	printf("retransmits:      %u\n", info->mptcpi_retransmits);
+	printf("retransmit bytes: %llu\n", info->mptcpi_bytes_retrans);
+	printf("bytes_sent:       %llu\n", info->mptcpi_bytes_sent);
+	printf("bytes_received:   %llu\n", info->mptcpi_bytes_received);
+	printf("bytes_acked:      %llu\n", info->mptcpi_bytes_acked);
+}
+
+/*
+ * 'print_subflow_info' is from 'mptcp_subflow_info'
+ * which is a function in 'misc/ss.c' of iproute2.
+ */
+static void print_subflow_info(struct rtattr *tb[])
+{
+	u_int32_t flags = 0;
+
+	printf("It's a mptcp subflow, the subflow info:\n");
+	if (tb[MPTCP_SUBFLOW_ATTR_FLAGS]) {
+		char caps[32 + 1] = { 0 }, *cap = &caps[0];
+
+		flags = rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_FLAGS]);
+
+		if (flags & MPTCP_SUBFLOW_FLAG_MCAP_REM)
+			*cap++ = 'M';
+		if (flags & MPTCP_SUBFLOW_FLAG_MCAP_LOC)
+			*cap++ = 'm';
+		if (flags & MPTCP_SUBFLOW_FLAG_JOIN_REM)
+			*cap++ = 'J';
+		if (flags & MPTCP_SUBFLOW_FLAG_JOIN_LOC)
+			*cap++ = 'j';
+		if (flags & MPTCP_SUBFLOW_FLAG_BKUP_REM)
+			*cap++ = 'B';
+		if (flags & MPTCP_SUBFLOW_FLAG_BKUP_LOC)
+			*cap++ = 'b';
+		if (flags & MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED)
+			*cap++ = 'e';
+		if (flags & MPTCP_SUBFLOW_FLAG_CONNECTED)
+			*cap++ = 'c';
+		if (flags & MPTCP_SUBFLOW_FLAG_MAPVALID)
+			*cap++ = 'v';
+
+		if (flags)
+			printf(" flags:%s", caps);
+	}
+	if (tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM] &&
+	    tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC] &&
+	    tb[MPTCP_SUBFLOW_ATTR_ID_REM] &&
+	    tb[MPTCP_SUBFLOW_ATTR_ID_LOC])
+		printf(" token:%04x(id:%u)/%04x(id:%u)",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM]),
+		       rta_getattr(__u8, tb[MPTCP_SUBFLOW_ATTR_ID_REM]),
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC]),
+		       rta_getattr(__u8, tb[MPTCP_SUBFLOW_ATTR_ID_LOC]));
+	if (tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ])
+		printf(" seq:%llu",
+		       rta_getattr(__u64, tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ]));
+	if (tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ])
+		printf(" sfseq:%u",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ]));
+	if (tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET])
+		printf(" ssnoff:%u",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET]));
+	if (tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN])
+		printf(" maplen:%u",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN]));
+	printf("\n");
+}
+
+static void parse_nlmsg(struct nlmsghdr *nlh, __u32 proto)
+{
+	struct inet_diag_msg *r = NLMSG_DATA(nlh);
+	struct rtattr *tb[INET_DIAG_MAX + 1];
+
+	parse_rtattr_flags(tb, INET_DIAG_MAX, (struct rtattr *)(r + 1),
+			   nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)),
+			   NLA_F_NESTED);
+
+	if (proto == IPPROTO_MPTCP && tb[INET_DIAG_INFO]) {
+		int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]);
+		struct mptcp_info *info;
+
+		/* workaround fort older kernels with less fields */
+		if (len < sizeof(*info)) {
+			info = alloca(sizeof(*info));
+			memcpy(info, RTA_DATA(tb[INET_DIAG_INFO]), len);
+			memset((char *)info + len, 0, sizeof(*info) - len);
+		} else {
+			info = RTA_DATA(tb[INET_DIAG_INFO]);
+		}
+		print_info_msg(info);
+	}
+	if (proto == IPPROTO_TCP && tb[INET_DIAG_ULP_INFO]) {
+		struct rtattr *ulpinfo[INET_ULP_INFO_MAX + 1] = { 0 };
+
+		parse_rtattr_nested(ulpinfo, INET_ULP_INFO_MAX,
+				    tb[INET_DIAG_ULP_INFO]);
+
+		if (ulpinfo[INET_ULP_INFO_MPTCP]) {
+			struct rtattr *sfinfo[MPTCP_SUBFLOW_ATTR_MAX + 1] = { 0 };
+
+			parse_rtattr_nested(sfinfo, MPTCP_SUBFLOW_ATTR_MAX,
+					    ulpinfo[INET_ULP_INFO_MPTCP]);
+			print_subflow_info(sfinfo);
+		} else {
+			printf("It's a normal TCP!\n");
+		}
+	}
+}
+
+static void recv_nlmsg(int fd, __u32 proto)
+{
+	char rcv_buff[8192];
+	struct nlmsghdr *nlh = (struct nlmsghdr *)rcv_buff;
+	struct sockaddr_nl rcv_nladdr = {
+		.nl_family = AF_NETLINK
+	};
+	struct iovec rcv_iov = {
+		.iov_base = rcv_buff,
+		.iov_len = sizeof(rcv_buff)
+	};
+	struct msghdr rcv_msg = {
+		.msg_name = &rcv_nladdr,
+		.msg_namelen = sizeof(rcv_nladdr),
+		.msg_iov = &rcv_iov,
+		.msg_iovlen = 1
+	};
+	int len;
+
+	len = recvmsg(fd, &rcv_msg, 0);
+
+	while (NLMSG_OK(nlh, len)) {
+		if (nlh->nlmsg_type == NLMSG_DONE) {
+			printf("NLMSG_DONE\n");
+			break;
+		} else if (nlh->nlmsg_type == NLMSG_ERROR) {
+			struct nlmsgerr *err;
+
+			err = (struct nlmsgerr *)NLMSG_DATA(nlh);
+			printf("Error %d:%s\n",
+			       -(err->error), strerror(-(err->error)));
+			break;
+		}
+		parse_nlmsg(nlh, proto);
+		nlh = NLMSG_NEXT(nlh, len);
+	}
+}
+
+static void get_mptcpinfo(__u32 token)
+{
+	struct inet_diag_req_v2 r = {
+		.sdiag_family           = AF_INET,
+		/* Real proto is set via INET_DIAG_REQ_PROTOCOL */
+		.sdiag_protocol         = IPPROTO_TCP,
+		.idiag_ext              = 1 << (INET_DIAG_INFO - 1),
+		.id.idiag_cookie[0]     = token,
+	};
+	__u32 proto = IPPROTO_MPTCP;
+	int fd;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+	if (fd < 0)
+		die_perror("Netlink socket");
+
+	send_query(fd, &r, proto);
+	recv_nlmsg(fd, proto);
+
+	close(fd);
+}
+
+static void get_subflow_info(char *subflow_addrs)
+{
+	struct inet_diag_req_v2 r = {
+		.sdiag_family           = AF_INET,
+		.sdiag_protocol         = IPPROTO_TCP,
+		.idiag_ext              = 1 << (INET_DIAG_INFO - 1),
+		.id.idiag_cookie[0]     = INET_DIAG_NOCOOKIE,
+		.id.idiag_cookie[1]     = INET_DIAG_NOCOOKIE,
+	};
+	char saddr[64], daddr[64];
+	int sport, dport;
+	int ret;
+	int fd;
+
+	ret = sscanf(subflow_addrs, "%[^:]:%d %[^:]:%d", saddr, &sport, daddr, &dport);
+	if (ret != 4)
+		die_perror("IP PORT Pairs has style problems!");
+
+	printf("%s:%d -> %s:%d\n", saddr, sport, daddr, dport);
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+	if (fd < 0)
+		die_perror("Netlink socket");
+
+	r.id.idiag_sport = htons(sport);
+	r.id.idiag_dport = htons(dport);
+
+	inet_pton(AF_INET, saddr, &r.id.idiag_src);
+	inet_pton(AF_INET, daddr, &r.id.idiag_dst);
+	send_query(fd, &r, IPPROTO_TCP);
+	recv_nlmsg(fd, IPPROTO_TCP);
+}
+
+static void parse_opts(int argc, char **argv, struct params *p)
+{
+	int c;
+
+	if (argc < 2)
+		die_usage(1);
+
+	while ((c = getopt(argc, argv, "ht:s:")) != -1) {
+		switch (c) {
+		case 'h':
+			die_usage(0);
+			break;
+		case 't':
+			sscanf(optarg, "%x", &p->target_token);
+			break;
+		case 's':
+			strncpy(p->subflow_addrs, optarg,
+				sizeof(p->subflow_addrs) - 1);
+			break;
+		default:
+			die_usage(1);
+			break;
+		}
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	struct params p = { 0 };
+
+	parse_opts(argc, argv, &p);
+
+	if (p.target_token)
+		get_mptcpinfo(p.target_token);
+
+	if (p.subflow_addrs[0] != '\0')
+		get_subflow_info(p.subflow_addrs);
+
+	return 0;
+}
+

linux-7.2.3/tools/testing/selftests/net/mptcp/mptcp_inq.c

@@ -0,0 +1,614 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <string.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <strings.h>
+#include <unistd.h>
+#include <time.h>
+
+#include <sys/ioctl.h>
+#include <sys/random.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include <netdb.h>
+#include <netinet/in.h>
+
+#include <linux/tcp.h>
+#include <linux/sockios.h>
+#include <linux/compiler.h>
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+#ifndef SOL_MPTCP
+#define SOL_MPTCP 284
+#endif
+
+static int pf = AF_INET;
+static int proto_tx = IPPROTO_MPTCP;
+static int proto_rx = IPPROTO_MPTCP;
+
+static void __noreturn die_perror(const char *msg)
+{
+	perror(msg);
+	exit(1);
+}
+
+static void die_usage(int r)
+{
+	fprintf(stderr, "Usage: mptcp_inq [-6] [ -t tcp|mptcp ] [ -r tcp|mptcp]\n");
+	exit(r);
+}
+
+static void __noreturn xerror(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	fputc('\n', stderr);
+	exit(1);
+}
+
+static const char *getxinfo_strerr(int err)
+{
+	if (err == EAI_SYSTEM)
+		return strerror(errno);
+
+	return gai_strerror(err);
+}
+
+static void xgetaddrinfo(const char *node, const char *service,
+			 struct addrinfo *hints,
+			 struct addrinfo **res)
+{
+	int err;
+
+again:
+	err = getaddrinfo(node, service, hints, res);
+	if (err) {
+		const char *errstr;
+
+		if (err == EAI_SOCKTYPE) {
+			hints->ai_protocol = IPPROTO_TCP;
+			goto again;
+		}
+
+		errstr = getxinfo_strerr(err);
+
+		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
+			node ? node : "", service ? service : "", errstr);
+		exit(1);
+	}
+}
+
+static int sock_listen_mptcp(const char * const listenaddr,
+			     const char * const port)
+{
+	int sock = -1;
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_MPTCP,
+		.ai_socktype = SOCK_STREAM,
+		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
+	};
+
+	hints.ai_family = pf;
+
+	struct addrinfo *a, *addr;
+	int one = 1;
+
+	xgetaddrinfo(listenaddr, port, &hints, &addr);
+	hints.ai_family = pf;
+
+	for (a = addr; a; a = a->ai_next) {
+		sock = socket(a->ai_family, a->ai_socktype, proto_rx);
+		if (sock < 0)
+			continue;
+
+		if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one,
+				     sizeof(one)))
+			perror("setsockopt");
+
+		if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
+			break; /* success */
+
+		perror("bind");
+		close(sock);
+		sock = -1;
+	}
+
+	freeaddrinfo(addr);
+
+	if (sock < 0)
+		xerror("could not create listen socket");
+
+	if (listen(sock, 20))
+		die_perror("listen");
+
+	return sock;
+}
+
+static int sock_connect_mptcp(const char * const remoteaddr,
+			      const char * const port, int proto)
+{
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_MPTCP,
+		.ai_socktype = SOCK_STREAM,
+	};
+	struct addrinfo *a, *addr;
+	int sock = -1;
+
+	hints.ai_family = pf;
+
+	xgetaddrinfo(remoteaddr, port, &hints, &addr);
+	for (a = addr; a; a = a->ai_next) {
+		sock = socket(a->ai_family, a->ai_socktype, proto);
+		if (sock < 0)
+			continue;
+
+		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
+			break; /* success */
+
+		die_perror("connect");
+	}
+
+	if (sock < 0)
+		xerror("could not create connect socket");
+
+	freeaddrinfo(addr);
+	return sock;
+}
+
+static int protostr_to_num(const char *s)
+{
+	if (strcasecmp(s, "tcp") == 0)
+		return IPPROTO_TCP;
+	if (strcasecmp(s, "mptcp") == 0)
+		return IPPROTO_MPTCP;
+
+	die_usage(1);
+	return 0;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "h6t:r:")) != -1) {
+		switch (c) {
+		case 'h':
+			die_usage(0);
+			break;
+		case '6':
+			pf = AF_INET6;
+			break;
+		case 't':
+			proto_tx = protostr_to_num(optarg);
+			break;
+		case 'r':
+			proto_rx = protostr_to_num(optarg);
+			break;
+		default:
+			die_usage(1);
+			break;
+		}
+	}
+}
+
+/* wait up to timeout milliseconds */
+static void wait_for_ack(int fd, int timeout, size_t total)
+{
+	int i;
+
+	for (i = 0; i < timeout; i++) {
+		int nsd, ret, queued = -1;
+		struct timespec req;
+
+		ret = ioctl(fd, TIOCOUTQ, &queued);
+		if (ret < 0)
+			die_perror("TIOCOUTQ");
+
+		ret = ioctl(fd, SIOCOUTQNSD, &nsd);
+		if (ret < 0)
+			die_perror("SIOCOUTQNSD");
+
+		if ((size_t)queued > total)
+			xerror("TIOCOUTQ %u, but only %zu expected\n", queued, total);
+		assert(nsd <= queued);
+
+		if (queued == 0)
+			return;
+
+		/* wait for peer to ack rx of all data */
+		req.tv_sec = 0;
+		req.tv_nsec = 1 * 1000 * 1000ul; /* 1ms */
+		nanosleep(&req, NULL);
+	}
+
+	xerror("still tx data queued after %u ms\n", timeout);
+}
+
+static void connect_one_server(int fd, int unixfd)
+{
+	size_t len, i, total, sent;
+	char buf[4096], buf2[4096];
+	ssize_t ret;
+
+	len = rand() % (sizeof(buf) - 1);
+
+	if (len < 128)
+		len = 128;
+
+	for (i = 0; i < len ; i++) {
+		buf[i] = rand() % 26;
+		buf[i] += 'A';
+	}
+
+	buf[i] = '\n';
+
+	/* un-block server */
+	ret = read(unixfd, buf2, 4);
+	assert(ret == 4);
+
+	assert(strncmp(buf2, "xmit", 4) == 0);
+
+	ret = write(unixfd, &len, sizeof(len));
+	assert(ret == (ssize_t)sizeof(len));
+
+	ret = write(fd, buf, len);
+	if (ret < 0)
+		die_perror("write");
+
+	if (ret != (ssize_t)len)
+		xerror("short write");
+
+	ret = read(unixfd, buf2, 4);
+	assert(strncmp(buf2, "huge", 4) == 0);
+
+	total = rand() % (16 * 1024 * 1024);
+	total += (1 * 1024 * 1024);
+	sent = total;
+
+	ret = write(unixfd, &total, sizeof(total));
+	assert(ret == (ssize_t)sizeof(total));
+
+	wait_for_ack(fd, 5000, len);
+
+	while (total > 0) {
+		if (total > sizeof(buf))
+			len = sizeof(buf);
+		else
+			len = total;
+
+		ret = write(fd, buf, len);
+		if (ret < 0)
+			die_perror("write");
+		total -= ret;
+
+		/* we don't have to care about buf content, only
+		 * number of total bytes sent
+		 */
+	}
+
+	ret = read(unixfd, buf2, 4);
+	assert(ret == 4);
+	assert(strncmp(buf2, "shut", 4) == 0);
+
+	wait_for_ack(fd, 5000, sent);
+
+	ret = write(fd, buf, 1);
+	assert(ret == 1);
+	close(fd);
+	ret = write(unixfd, "closed", 6);
+	assert(ret == 6);
+
+	close(unixfd);
+}
+
+static void get_tcp_inq(struct msghdr *msgh, unsigned int *inqv)
+{
+	struct cmsghdr *cmsg;
+
+	for (cmsg = CMSG_FIRSTHDR(msgh); cmsg ; cmsg = CMSG_NXTHDR(msgh, cmsg)) {
+		if (cmsg->cmsg_level == IPPROTO_TCP && cmsg->cmsg_type == TCP_CM_INQ) {
+			memcpy(inqv, CMSG_DATA(cmsg), sizeof(*inqv));
+			return;
+		}
+	}
+
+	xerror("could not find TCP_CM_INQ cmsg type");
+}
+
+static void process_one_client(int fd, int unixfd)
+{
+	unsigned int tcp_inq;
+	size_t expect_len;
+	char msg_buf[4096];
+	char buf[4096];
+	char tmp[16];
+	struct iovec iov = {
+		.iov_base = buf,
+		.iov_len = 1,
+	};
+	struct msghdr msg = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+		.msg_control = msg_buf,
+		.msg_controllen = sizeof(msg_buf),
+	};
+	ssize_t ret, tot;
+
+	ret = write(unixfd, "xmit", 4);
+	assert(ret == 4);
+
+	ret = read(unixfd, &expect_len, sizeof(expect_len));
+	assert(ret == (ssize_t)sizeof(expect_len));
+
+	if (expect_len > sizeof(buf))
+		xerror("expect len %zu exceeds buffer size", expect_len);
+
+	for (;;) {
+		struct timespec req;
+		unsigned int queued;
+
+		ret = ioctl(fd, FIONREAD, &queued);
+		if (ret < 0)
+			die_perror("FIONREAD");
+		if (queued > expect_len)
+			xerror("FIONREAD returned %u, but only %zu expected\n",
+			       queued, expect_len);
+		if (queued == expect_len)
+			break;
+
+		req.tv_sec = 0;
+		req.tv_nsec = 1000 * 1000ul;
+		nanosleep(&req, NULL);
+	}
+
+	/* read one byte, expect cmsg to return expected - 1 */
+	ret = recvmsg(fd, &msg, 0);
+	if (ret < 0)
+		die_perror("recvmsg");
+
+	if (msg.msg_controllen == 0)
+		xerror("msg_controllen is 0");
+
+	get_tcp_inq(&msg, &tcp_inq);
+
+	assert((size_t)tcp_inq == (expect_len - 1));
+
+	iov.iov_len = sizeof(buf);
+	ret = recvmsg(fd, &msg, 0);
+	if (ret < 0)
+		die_perror("recvmsg");
+
+	/* should have gotten exact remainder of all pending data */
+	assert(ret == (ssize_t)tcp_inq);
+
+	/* should be 0, all drained */
+	get_tcp_inq(&msg, &tcp_inq);
+	assert(tcp_inq == 0);
+
+	/* request a large swath of data. */
+	ret = write(unixfd, "huge", 4);
+	assert(ret == 4);
+
+	ret = read(unixfd, &expect_len, sizeof(expect_len));
+	assert(ret == (ssize_t)sizeof(expect_len));
+
+	/* peer should send us a few mb of data */
+	if (expect_len <= sizeof(buf))
+		xerror("expect len %zu too small\n", expect_len);
+
+	tot = 0;
+	do {
+		iov.iov_len = sizeof(buf);
+		ret = recvmsg(fd, &msg, 0);
+		if (ret < 0)
+			die_perror("recvmsg");
+
+		tot += ret;
+
+		get_tcp_inq(&msg, &tcp_inq);
+
+		if (tcp_inq > expect_len - tot)
+			xerror("inq %d, remaining %d total_len %d\n",
+			       tcp_inq, expect_len - tot, (int)expect_len);
+
+		assert(tcp_inq <= expect_len - tot);
+	} while ((size_t)tot < expect_len);
+
+	ret = write(unixfd, "shut", 4);
+	assert(ret == 4);
+
+	/* wait for hangup. Should have received one more byte of data. */
+	ret = read(unixfd, tmp, sizeof(tmp));
+	assert(ret == 6);
+	assert(strncmp(tmp, "closed", 6) == 0);
+
+	sleep(1);
+
+	iov.iov_len = 1;
+	ret = recvmsg(fd, &msg, 0);
+	if (ret < 0)
+		die_perror("recvmsg");
+	assert(ret == 1);
+
+	get_tcp_inq(&msg, &tcp_inq);
+
+	/* tcp_inq should be 1 due to received fin. */
+	assert(tcp_inq == 1);
+
+	iov.iov_len = 1;
+	ret = recvmsg(fd, &msg, 0);
+	if (ret < 0)
+		die_perror("recvmsg");
+
+	/* expect EOF */
+	assert(ret == 0);
+	get_tcp_inq(&msg, &tcp_inq);
+	assert(tcp_inq == 1);
+
+	close(fd);
+}
+
+static int xaccept(int s)
+{
+	int fd = accept(s, NULL, 0);
+
+	if (fd < 0)
+		die_perror("accept");
+
+	return fd;
+}
+
+static int server(int unixfd)
+{
+	int fd = -1, r, on = 1;
+
+	switch (pf) {
+	case AF_INET:
+		fd = sock_listen_mptcp("127.0.0.1", "15432");
+		break;
+	case AF_INET6:
+		fd = sock_listen_mptcp("::1", "15432");
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+		break;
+	}
+
+	r = write(unixfd, "conn", 4);
+	assert(r == 4);
+
+	alarm(15);
+	r = xaccept(fd);
+
+	if (-1 == setsockopt(r, IPPROTO_TCP, TCP_INQ, &on, sizeof(on)))
+		die_perror("setsockopt");
+
+	process_one_client(r, unixfd);
+
+	close(fd);
+	return 0;
+}
+
+static int client(int unixfd)
+{
+	int fd = -1;
+
+	alarm(15);
+
+	switch (pf) {
+	case AF_INET:
+		fd = sock_connect_mptcp("127.0.0.1", "15432", proto_tx);
+		break;
+	case AF_INET6:
+		fd = sock_connect_mptcp("::1", "15432", proto_tx);
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+	}
+
+	connect_one_server(fd, unixfd);
+
+	return 0;
+}
+
+static void init_rng(void)
+{
+	unsigned int foo;
+
+	if (getrandom(&foo, sizeof(foo), 0) == -1) {
+		perror("getrandom");
+		exit(1);
+	}
+
+	srand(foo);
+}
+
+static pid_t xfork(void)
+{
+	pid_t p = fork();
+
+	if (p < 0)
+		die_perror("fork");
+	else if (p == 0)
+		init_rng();
+
+	return p;
+}
+
+static int rcheck(int wstatus, const char *what)
+{
+	if (WIFEXITED(wstatus)) {
+		if (WEXITSTATUS(wstatus) == 0)
+			return 0;
+		fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus));
+		return WEXITSTATUS(wstatus);
+	} else if (WIFSIGNALED(wstatus)) {
+		xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus));
+	} else if (WIFSTOPPED(wstatus)) {
+		xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus));
+	}
+
+	return 111;
+}
+
+int main(int argc, char *argv[])
+{
+	int e1, e2, wstatus;
+	pid_t s, c, ret;
+	int unixfds[2];
+
+	parse_opts(argc, argv);
+
+	e1 = socketpair(AF_UNIX, SOCK_DGRAM, 0, unixfds);
+	if (e1 < 0)
+		die_perror("pipe");
+
+	s = xfork();
+	if (s == 0) {
+		close(unixfds[0]);
+		ret = server(unixfds[1]);
+		close(unixfds[1]);
+		return ret;
+	}
+
+	close(unixfds[1]);
+
+	/* wait until server bound a socket */
+	e1 = read(unixfds[0], &e1, 4);
+	assert(e1 == 4);
+
+	c = xfork();
+	if (c == 0)
+		return client(unixfds[0]);
+
+	close(unixfds[0]);
+
+	ret = waitpid(s, &wstatus, 0);
+	if (ret == -1)
+		die_perror("waitpid");
+	e1 = rcheck(wstatus, "server");
+	ret = waitpid(c, &wstatus, 0);
+	if (ret == -1)
+		die_perror("waitpid");
+	e2 = rcheck(wstatus, "client");
+
+	return e1 ? e1 : e2;
+}

linux-7.2.3/tools/testing/selftests/net/mptcp/mptcp_lib.sh

@@ -0,0 +1,764 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(dirname "${0}")/../lib.sh"
+
+readonly KSFT_PASS=0
+readonly KSFT_FAIL=1
+readonly KSFT_SKIP=4
+
+# shellcheck disable=SC2155 # declare and assign separately
+readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}"
+
+# These variables are used in some selftests, read-only
+declare -rx MPTCP_LIB_EVENT_CREATED=1           # MPTCP_EVENT_CREATED
+declare -rx MPTCP_LIB_EVENT_ESTABLISHED=2       # MPTCP_EVENT_ESTABLISHED
+declare -rx MPTCP_LIB_EVENT_CLOSED=3            # MPTCP_EVENT_CLOSED
+declare -rx MPTCP_LIB_EVENT_ANNOUNCED=6         # MPTCP_EVENT_ANNOUNCED
+declare -rx MPTCP_LIB_EVENT_REMOVED=7           # MPTCP_EVENT_REMOVED
+declare -rx MPTCP_LIB_EVENT_SUB_ESTABLISHED=10  # MPTCP_EVENT_SUB_ESTABLISHED
+declare -rx MPTCP_LIB_EVENT_SUB_CLOSED=11       # MPTCP_EVENT_SUB_CLOSED
+declare -rx MPTCP_LIB_EVENT_SUB_PRIORITY=13     # MPTCP_EVENT_SUB_PRIORITY
+declare -rx MPTCP_LIB_EVENT_LISTENER_CREATED=15 # MPTCP_EVENT_LISTENER_CREATED
+declare -rx MPTCP_LIB_EVENT_LISTENER_CLOSED=16  # MPTCP_EVENT_LISTENER_CLOSED
+
+declare -rx MPTCP_LIB_AF_INET=2
+declare -rx MPTCP_LIB_AF_INET6=10
+
+MPTCP_LIB_SUBTESTS=()
+MPTCP_LIB_SUBTESTS_DUPLICATED=0
+MPTCP_LIB_SUBTEST_FLAKY=0
+MPTCP_LIB_SUBTESTS_LAST_TS_NS=
+MPTCP_LIB_TEST_COUNTER=0
+MPTCP_LIB_TEST_FORMAT="%02u %-50s"
+MPTCP_LIB_IP_MPTCP=0
+
+# only if supported (or forced) and not disabled, see no-color.org
+if { [ -t 1 ] || [ "${SELFTESTS_MPTCP_LIB_COLOR_FORCE:-}" = "1" ]; } &&
+   [ "${NO_COLOR:-}" != "1" ]; then
+	readonly MPTCP_LIB_COLOR_RED="\E[1;31m"
+	readonly MPTCP_LIB_COLOR_GREEN="\E[1;32m"
+	readonly MPTCP_LIB_COLOR_YELLOW="\E[1;33m"
+	readonly MPTCP_LIB_COLOR_BLUE="\E[1;34m"
+	readonly MPTCP_LIB_COLOR_RESET="\E[0m"
+else
+	readonly MPTCP_LIB_COLOR_RED=
+	readonly MPTCP_LIB_COLOR_GREEN=
+	readonly MPTCP_LIB_COLOR_YELLOW=
+	readonly MPTCP_LIB_COLOR_BLUE=
+	readonly MPTCP_LIB_COLOR_RESET=
+fi
+
+# SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY env var can be set not to ignore errors
+# from subtests marked as flaky
+mptcp_lib_override_flaky() {
+	[ "${SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY:-}" = 1 ]
+}
+
+mptcp_lib_subtest_is_flaky() {
+	[ "${MPTCP_LIB_SUBTEST_FLAKY}" = 1 ] && ! mptcp_lib_override_flaky
+}
+
+# $1: color, $2: text
+mptcp_lib_print_color() {
+	echo -e "${MPTCP_LIB_START_PRINT:-}${*}${MPTCP_LIB_COLOR_RESET}"
+}
+
+mptcp_lib_print_ok() {
+	mptcp_lib_print_color "${MPTCP_LIB_COLOR_GREEN}${*}"
+}
+
+mptcp_lib_print_warn() {
+	mptcp_lib_print_color "${MPTCP_LIB_COLOR_YELLOW}${*}"
+}
+
+mptcp_lib_print_info() {
+	mptcp_lib_print_color "${MPTCP_LIB_COLOR_BLUE}${*}"
+}
+
+mptcp_lib_print_err() {
+	mptcp_lib_print_color "${MPTCP_LIB_COLOR_RED}${*}"
+}
+
+# shellcheck disable=SC2120 # parameters are optional
+mptcp_lib_pr_ok() {
+	mptcp_lib_print_ok "[ OK ]${1:+ ${*}}"
+}
+
+mptcp_lib_pr_skip() {
+	mptcp_lib_print_warn "[SKIP]${1:+ ${*}}"
+}
+
+mptcp_lib_pr_fail() {
+	local title cmt
+
+	if mptcp_lib_subtest_is_flaky; then
+		title="IGNO"
+		cmt=" (flaky)"
+	else
+		title="FAIL"
+	fi
+
+	mptcp_lib_print_err "[${title}]${cmt}${1:+ ${*}}"
+}
+
+mptcp_lib_pr_info() {
+	mptcp_lib_print_info "INFO: ${*}"
+}
+
+mptcp_lib_pr_nstat() {
+	local ns="${1}"
+	local hist="/tmp/${ns}.out"
+
+	if [ -f "${hist}" ]; then
+		awk '$2 != 0 { print "  "$0 }' "${hist}"
+	else
+		ip netns exec "${ns}" nstat -as | grep Tcp
+	fi
+}
+
+# $1-2: listener/connector ns ; $3 port
+mptcp_lib_pr_err_stats() {
+	local lns="${1}"
+	local cns="${2}"
+	local port="${3}"
+
+	echo -en "${MPTCP_LIB_COLOR_RED}"
+	{
+		printf "\nnetns %s (listener) socket stat for %d:\n" "${lns}" "${port}"
+		ip netns exec "${lns}" ss -Menitam -o "sport = :${port}"
+		mptcp_lib_pr_nstat "${lns}"
+
+		printf "\nnetns %s (connector) socket stat for %d:\n" "${cns}" "${port}"
+		ip netns exec "${cns}" ss -Menitam -o "dport = :${port}"
+		[ "${lns}" != "${cns}" ] && mptcp_lib_pr_nstat "${cns}"
+	} 1>&2
+	echo -en "${MPTCP_LIB_COLOR_RESET}"
+}
+
+# SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all
+# features using the last version of the kernel and the selftests to make sure
+# a test is not being skipped by mistake.
+mptcp_lib_expect_all_features() {
+	[ "${SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES:-}" = "1" ]
+}
+
+# $1: msg
+mptcp_lib_fail_if_expected_feature() {
+	if mptcp_lib_expect_all_features; then
+		echo "ERROR: missing feature: ${*}"
+		exit ${KSFT_FAIL}
+	fi
+
+	return 1
+}
+
+# $1: file
+mptcp_lib_has_file() {
+	local f="${1}"
+
+	if [ -f "${f}" ]; then
+		return 0
+	fi
+
+	mptcp_lib_fail_if_expected_feature "${f} file not found"
+}
+
+mptcp_lib_check_mptcp() {
+	if ! mptcp_lib_has_file "/proc/sys/net/mptcp/enabled"; then
+		mptcp_lib_pr_skip "MPTCP support is not available"
+		exit ${KSFT_SKIP}
+	fi
+}
+
+mptcp_lib_check_kallsyms() {
+	if ! mptcp_lib_has_file "/proc/kallsyms"; then
+		mptcp_lib_pr_skip "CONFIG_KALLSYMS is missing"
+		exit ${KSFT_SKIP}
+	fi
+}
+
+# Internal: use mptcp_lib_kallsyms_has() instead
+__mptcp_lib_kallsyms_has() {
+	local sym="${1}"
+
+	mptcp_lib_check_kallsyms
+
+	grep -q " ${sym}" /proc/kallsyms
+}
+
+# $1: part of a symbol to look at, add '$' at the end for full name
+mptcp_lib_kallsyms_has() {
+	local sym="${1}"
+
+	if __mptcp_lib_kallsyms_has "${sym}"; then
+		return 0
+	fi
+
+	mptcp_lib_fail_if_expected_feature "${sym} symbol not found"
+}
+
+# $1: part of a symbol to look at, add '$' at the end for full name
+mptcp_lib_kallsyms_doesnt_have() {
+	local sym="${1}"
+
+	if ! __mptcp_lib_kallsyms_has "${sym}"; then
+		return 0
+	fi
+
+	mptcp_lib_fail_if_expected_feature "${sym} symbol has been found"
+}
+
+# !!!AVOID USING THIS!!!
+# Features might not land in the expected version and features can be backported
+#
+# $1: kernel version, e.g. 6.3
+mptcp_lib_kversion_ge() {
+	local exp_maj="${1%.*}"
+	local exp_min="${1#*.}"
+	local v maj min
+
+	# If the kernel has backported features, set this env var to 1:
+	if [ "${SELFTESTS_MPTCP_LIB_NO_KVERSION_CHECK:-}" = "1" ]; then
+		return 0
+	fi
+
+	v=$(uname -r | cut -d'.' -f1,2)
+	maj=${v%.*}
+	min=${v#*.}
+
+	if   [ "${maj}" -gt "${exp_maj}" ] ||
+	   { [ "${maj}" -eq "${exp_maj}" ] && [ "${min}" -ge "${exp_min}" ]; }; then
+		return 0
+	fi
+
+	mptcp_lib_fail_if_expected_feature "kernel version ${1} lower than ${v}"
+}
+
+mptcp_lib_subtests_last_ts_reset() {
+	MPTCP_LIB_SUBTESTS_LAST_TS_NS="$(date +%s%N)"
+}
+mptcp_lib_subtests_last_ts_reset
+
+__mptcp_lib_result_check_duplicated() {
+	local subtest
+
+	for subtest in "${MPTCP_LIB_SUBTESTS[@]}"; do
+		if [[ "${subtest}" == *" - ${KSFT_TEST}: ${*%% #*}" ]]; then
+			MPTCP_LIB_SUBTESTS_DUPLICATED=1
+			mptcp_lib_print_err "Duplicated entry: ${*}"
+			break
+		fi
+	done
+}
+
+__mptcp_lib_result_add() {
+	local result="${1}"
+	local time="time="
+	local ts_prev_ns
+	shift
+
+	local id=$((${#MPTCP_LIB_SUBTESTS[@]} + 1))
+
+	__mptcp_lib_result_check_duplicated "${*}"
+
+	# not to add two '#'
+	[[ "${*}" != *"#"* ]] && time="# ${time}"
+
+	ts_prev_ns="${MPTCP_LIB_SUBTESTS_LAST_TS_NS}"
+	mptcp_lib_subtests_last_ts_reset
+	time+="$(((MPTCP_LIB_SUBTESTS_LAST_TS_NS - ts_prev_ns) / 1000000))ms"
+
+	MPTCP_LIB_SUBTESTS+=("${result} ${id} - ${KSFT_TEST}: ${*} ${time}")
+}
+
+# $1: test name
+mptcp_lib_result_pass() {
+	__mptcp_lib_result_add "ok" "${1}"
+}
+
+# $1: test name
+mptcp_lib_result_fail() {
+	if mptcp_lib_subtest_is_flaky; then
+		# It might sound better to use 'not ok # TODO' or 'ok # SKIP',
+		# but some CIs don't understand 'TODO' and treat SKIP as errors.
+		__mptcp_lib_result_add "ok" "${1} # IGNORE Flaky"
+	else
+		__mptcp_lib_result_add "not ok" "${1}"
+	fi
+}
+
+# $1: test name
+mptcp_lib_result_skip() {
+	__mptcp_lib_result_add "ok" "${1} # SKIP"
+}
+
+# $1: result code ; $2: test name
+mptcp_lib_result_code() {
+	local ret="${1}"
+	local name="${2}"
+
+	case "${ret}" in
+		"${KSFT_PASS}")
+			mptcp_lib_result_pass "${name}"
+			;;
+		"${KSFT_FAIL}")
+			mptcp_lib_result_fail "${name}"
+			;;
+		"${KSFT_SKIP}")
+			mptcp_lib_result_skip "${name}"
+			;;
+		*)
+			echo "ERROR: wrong result code: ${ret}"
+			exit ${KSFT_FAIL}
+			;;
+	esac
+}
+
+mptcp_lib_result_print_all_tap() {
+	local subtest
+
+	if [ ${#MPTCP_LIB_SUBTESTS[@]} -eq 0 ] ||
+	   [ "${SELFTESTS_MPTCP_LIB_NO_TAP:-}" = "1" ]; then
+		return
+	fi
+
+	printf "\nTAP version 13\n"
+	printf "1..%d\n" "${#MPTCP_LIB_SUBTESTS[@]}"
+
+	for subtest in "${MPTCP_LIB_SUBTESTS[@]}"; do
+		printf "%s\n" "${subtest}"
+	done
+
+	if [ "${MPTCP_LIB_SUBTESTS_DUPLICATED}" = 1 ] &&
+	   mptcp_lib_expect_all_features; then
+		mptcp_lib_print_err "Duplicated test entries"
+		exit ${KSFT_FAIL}
+	fi
+}
+
+# get the value of keyword $1 in the line marked by keyword $2
+mptcp_lib_get_info_value() {
+	grep "${2}" 2>/dev/null |
+		sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q'
+		# the ';q' at the end limits to the first matched entry.
+}
+
+# $1: info name ; $2: evts_ns ; [$3: event type; [$4: addr]]
+mptcp_lib_evts_get_info() {
+	grep "${4:-}" "${2}" 2>/dev/null |
+		mptcp_lib_get_info_value "${1}" "^type:${3:-1},"
+}
+
+mptcp_lib_wait_timeout() {
+	local timeout_test="${1}"
+	local listener_ns="${2}"
+	local connector_ns="${3}"
+	local port="${4}"
+	shift 4 # rest are PIDs
+
+	sleep "${timeout_test}"
+	mptcp_lib_print_err "timeout"
+	mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}"
+	kill "${@}" 2>/dev/null
+}
+
+# $1: PID
+mptcp_lib_kill_wait() {
+	[ "${1}" -eq 0 ] && return 0
+
+	kill -SIGUSR1 "${1}" > /dev/null 2>&1
+	kill "${1}" > /dev/null 2>&1
+	wait "${1}" 2>/dev/null
+}
+
+# $1: PID
+mptcp_lib_pid_list_children() {
+	local curr="${1}"
+	# evoke 'ps' only once
+	local pids="${2:-"$(ps o pid,ppid)"}"
+
+	echo "${curr}"
+
+	local pid
+	for pid in $(echo "${pids}" | awk "\$2 == ${curr} { print \$1 }"); do
+		mptcp_lib_pid_list_children "${pid}" "${pids}"
+	done
+}
+
+# $1: PID
+mptcp_lib_kill_group_wait() {
+	# Some users might not have procps-ng: cannot use "kill -- -PID"
+	mptcp_lib_pid_list_children "${1}" | xargs -r kill &>/dev/null
+	wait "${1}" 2>/dev/null
+}
+
+# $1: IP address
+mptcp_lib_is_v6() {
+	[ -z "${1##*:*}" ]
+}
+
+mptcp_lib_nstat_init() {
+	local ns="${1}"
+
+	rm -f "/tmp/${ns}."{nstat,out}
+	NSTAT_HISTORY="/tmp/${ns}.nstat" ip netns exec "${ns}" nstat -n
+}
+
+mptcp_lib_nstat_get() {
+	local ns="${1}"
+
+	# filter out non-*TCP stats, and the rate (last column)
+	NSTAT_HISTORY="/tmp/${ns}.nstat" ip netns exec "${ns}" nstat -sz |
+		grep -o ".*Tcp\S\+\s\+[0-9]\+" > "/tmp/${ns}.out"
+}
+
+# $1: ns, $2: MIB counter
+# Get the counter from the history (mptcp_lib_nstat_{init,get}()) if available.
+# If not, get the counter from nstat ignoring any history.
+mptcp_lib_get_counter() {
+	local ns="${1}"
+	local counter="${2}"
+	local hist="/tmp/${ns}.out"
+	local count
+
+	if [[ -s "${hist}" && "${counter}" == *"Tcp"* ]]; then
+		count=$(awk "/^${counter} / {print \$2; exit}" "${hist}")
+	else
+		count=$(ip netns exec "${ns}" nstat -asz "${counter}" |
+			awk 'NR==1 {next} {print $2}')
+	fi
+	if [ -z "${count}" ]; then
+		mptcp_lib_fail_if_expected_feature "${counter} counter"
+		return 1
+	fi
+
+	echo "${count}"
+}
+
+mptcp_lib_make_file() {
+	local name="${1}"
+	local bs="${2}"
+	local size="${3}"
+
+	dd if=/dev/urandom of="${name}" bs="${bs}" count="${size}" 2> /dev/null
+	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "${name}"
+}
+
+# $1: file
+mptcp_lib_print_file_err() {
+	ls -l "${1}" 1>&2
+	echo "Trailing bytes are: "
+	tail -c 32 "${1}" | od -x | head -n2
+}
+
+# $1: input file ; $2: output file ; $3: what kind of file
+mptcp_lib_check_transfer() {
+	local in="${1}"
+	local out="${2}"
+	local what="${3}"
+
+	if ! cmp "$in" "$out" > /dev/null 2>&1; then
+		mptcp_lib_pr_fail "$what does not match (in, out):"
+		mptcp_lib_print_file_err "$in"
+		mptcp_lib_print_file_err "$out"
+
+		return 1
+	fi
+
+	return 0
+}
+
+# $1: ns, $2: port
+mptcp_lib_wait_local_port_listen() {
+	wait_local_port_listen "${@}" "tcp"
+}
+
+# $1: error file, $2: cmd, $3: expected msg, [$4: expected error]
+mptcp_lib_check_output() {
+	local err="${1}"
+	local cmd="${2}"
+	local expected="${3}"
+	local exp_error="${4:-0}"
+	local cmd_ret=0
+	local out
+
+	out=$(${cmd} 2>"${err}") || cmd_ret=1
+
+	if [ "${cmd_ret}" != "${exp_error}" ]; then
+		mptcp_lib_pr_fail "unexpected returned code for '${cmd}', info:"
+		if [ "${exp_error}" = 0 ]; then
+			cat "${err}"
+		else
+			echo "${out}"
+		fi
+		return 2
+	elif [ "${out}" = "${expected}" ]; then
+		return 0
+	else
+		mptcp_lib_pr_fail "expected '${expected}' got '${out}'"
+		return 1
+	fi
+}
+
+mptcp_lib_check_tools() {
+	local tool
+
+	for tool in "${@}"; do
+		case "${tool}" in
+		"ip")
+			if ! ip -Version &> /dev/null; then
+				mptcp_lib_pr_skip "Could not run test without ip tool"
+				exit ${KSFT_SKIP}
+			fi
+			;;
+		"tc")
+			if ! tc -help &> /dev/null; then
+				mptcp_lib_pr_skip "Could not run test without tc tool"
+				exit ${KSFT_SKIP}
+			fi
+			;;
+		"ss")
+			if ! ss -h | grep -q MPTCP; then
+				mptcp_lib_pr_skip "ss tool does not support MPTCP"
+				exit ${KSFT_SKIP}
+			fi
+			;;
+		"iptables"* | "ip6tables"*)
+			if ! "${tool}" -V &> /dev/null; then
+				mptcp_lib_pr_skip "Could not run all tests without ${tool}"
+				exit ${KSFT_SKIP}
+			fi
+			;;
+		*)
+			mptcp_lib_pr_fail "Internal error: unsupported tool: ${tool}"
+			exit ${KSFT_FAIL}
+			;;
+		esac
+	done
+}
+
+mptcp_lib_ns_init() {
+	if ! setup_ns "${@}"; then
+		mptcp_lib_pr_fail "Failed to setup namespaces ${*}"
+		exit ${KSFT_FAIL}
+	fi
+
+	local netns
+	for netns in "${@}"; do
+		ip netns exec "${!netns}" sysctl -q net.mptcp.enabled=1
+	done
+}
+
+mptcp_lib_ns_exit() {
+	cleanup_ns "${@}"
+
+	local netns
+	for netns in "${@}"; do
+		rm -f /tmp/"${netns}".{nstat,out}
+	done
+}
+
+mptcp_lib_events() {
+	local ns="${1}"
+	local evts="${2}"
+	declare -n pid="${3}"
+
+	:>"${evts}"
+
+	mptcp_lib_kill_wait "${pid:-0}"
+	ip netns exec "${ns}" ./pm_nl_ctl events >> "${evts}" 2>&1 &
+	pid=$!
+}
+
+mptcp_lib_print_title() {
+	: "${MPTCP_LIB_TEST_COUNTER:?}"
+	: "${MPTCP_LIB_TEST_FORMAT:?}"
+
+	# shellcheck disable=SC2059 # the format is in a variable
+	printf "${MPTCP_LIB_TEST_FORMAT}" "$((++MPTCP_LIB_TEST_COUNTER))" "${*}"
+}
+
+# $1: var name ; $2: prev ret
+mptcp_lib_check_expected_one() {
+	local var="${1}"
+	local exp="e_${var}"
+	local prev_ret="${2}"
+
+	if [ "${!var}" = "${!exp}" ]; then
+		return 0
+	fi
+
+	if [ "${prev_ret}" = "0" ]; then
+		mptcp_lib_pr_fail
+	fi
+
+	mptcp_lib_print_err "Expected value for '${var}': '${!exp}', got '${!var}'."
+	return 1
+}
+
+# $@: all var names to check
+mptcp_lib_check_expected() {
+	local rc=0
+	local var
+
+	for var in "${@}"; do
+		mptcp_lib_check_expected_one "${var}" "${rc}" || rc=1
+	done
+
+	return "${rc}"
+}
+
+# shellcheck disable=SC2034 # Some variables are used below but indirectly
+mptcp_lib_verify_listener_events() {
+	local evt=${1}
+	local e_type=${2}
+	local e_family=${3}
+	local e_saddr=${4}
+	local e_sport=${5}
+	local type
+	local family
+	local saddr
+	local sport
+	local rc=0
+
+	type=$(mptcp_lib_evts_get_info type "${evt}" "${e_type}")
+	family=$(mptcp_lib_evts_get_info family "${evt}" "${e_type}")
+	if [ "${family}" ] && [ "${family}" = "${AF_INET6}" ]; then
+		saddr=$(mptcp_lib_evts_get_info saddr6 "${evt}" "${e_type}")
+	else
+		saddr=$(mptcp_lib_evts_get_info saddr4 "${evt}" "${e_type}")
+	fi
+	sport=$(mptcp_lib_evts_get_info sport "${evt}" "${e_type}")
+
+	mptcp_lib_check_expected "type" "family" "saddr" "sport" || rc="${?}"
+	return "${rc}"
+}
+
+mptcp_lib_set_ip_mptcp() {
+	MPTCP_LIB_IP_MPTCP=1
+}
+
+mptcp_lib_is_ip_mptcp() {
+	[ "${MPTCP_LIB_IP_MPTCP}" = "1" ]
+}
+
+# format: <id>,<ip>,<flags>,<dev>
+mptcp_lib_pm_nl_format_endpoints() {
+	local entry id ip flags dev port
+
+	for entry in "${@}"; do
+		IFS=, read -r id ip flags dev port <<< "${entry}"
+		if mptcp_lib_is_ip_mptcp; then
+			echo -n "${ip}"
+			[ -n "${port}" ] && echo -n " port ${port}"
+			echo -n " id ${id}"
+			[ -n "${flags}" ] && echo -n " ${flags}"
+			[ -n "${dev}" ] && echo -n " dev ${dev}"
+			echo " " # always a space at the end
+		else
+			echo -n "id ${id}"
+			echo -n " flags ${flags//" "/","}"
+			[ -n "${dev}" ] && echo -n " dev ${dev}"
+			echo -n " ${ip}"
+			[ -n "${port}" ] && echo -n " ${port}"
+			echo ""
+		fi
+	done
+}
+
+mptcp_lib_pm_nl_get_endpoint() {
+	local ns=${1}
+	local id=${2}
+
+	if mptcp_lib_is_ip_mptcp; then
+		ip -n "${ns}" mptcp endpoint show id "${id}"
+	else
+		ip netns exec "${ns}" ./pm_nl_ctl get "${id}"
+	fi
+}
+
+mptcp_lib_pm_nl_set_limits() {
+	local ns=${1}
+	local addrs=${2}
+	local subflows=${3}
+
+	if mptcp_lib_is_ip_mptcp; then
+		ip -n "${ns}" mptcp limits set add_addr_accepted "${addrs}" subflows "${subflows}"
+	else
+		ip netns exec "${ns}" ./pm_nl_ctl limits "${addrs}" "${subflows}"
+	fi
+}
+
+mptcp_lib_pm_nl_add_endpoint() {
+	local ns=${1}
+	local addr=${2}
+	local flags dev id port
+	local nr=2
+
+	local p
+	for p in "${@}"; do
+		case "${p}" in
+		"flags" | "dev" | "id" | "port")
+			eval "${p}"=\$"${nr}"
+			;;
+		esac
+
+		nr=$((nr + 1))
+	done
+
+	if mptcp_lib_is_ip_mptcp; then
+		# shellcheck disable=SC2086 # blanks in flags, no double quote
+		ip -n "${ns}" mptcp endpoint add "${addr}" ${flags//","/" "} \
+			${dev:+dev "${dev}"} ${id:+id "${id}"} ${port:+port "${port}"}
+	else
+		ip netns exec "${ns}" ./pm_nl_ctl add "${addr}" ${flags:+flags "${flags}"} \
+			${dev:+dev "${dev}"} ${id:+id "${id}"} ${port:+port "${port}"}
+	fi
+}
+
+mptcp_lib_pm_nl_del_endpoint() {
+	local ns=${1}
+	local id=${2}
+	local addr=${3}
+
+	if mptcp_lib_is_ip_mptcp; then
+		[ "${id}" -ne 0 ] && addr=''
+		ip -n "${ns}" mptcp endpoint delete id "${id}" ${addr:+"${addr}"}
+	else
+		ip netns exec "${ns}" ./pm_nl_ctl del "${id}" "${addr}"
+	fi
+}
+
+mptcp_lib_pm_nl_flush_endpoint() {
+	local ns=${1}
+
+	if mptcp_lib_is_ip_mptcp; then
+		ip -n "${ns}" mptcp endpoint flush
+	else
+		ip netns exec "${ns}" ./pm_nl_ctl flush
+	fi
+}
+
+mptcp_lib_pm_nl_show_endpoints() {
+	local ns=${1}
+
+	if mptcp_lib_is_ip_mptcp; then
+		ip -n "${ns}" mptcp endpoint show
+	else
+		ip netns exec "${ns}" ./pm_nl_ctl dump
+	fi
+}
+
+mptcp_lib_pm_nl_change_endpoint() {
+	local ns=${1}
+	local id=${2}
+	local flags=${3}
+
+	if mptcp_lib_is_ip_mptcp; then
+		# shellcheck disable=SC2086 # blanks in flags, no double quote
+		ip -n "${ns}" mptcp endpoint change id "${id}" ${flags//","/" "}
+	else
+		ip netns exec "${ns}" ./pm_nl_ctl set id "${id}" flags "${flags}"
+	fi
+}

linux-7.2.3/tools/testing/selftests/net/mptcp/mptcp_sockopt.c

@@ -0,0 +1,885 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <string.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <strings.h>
+#include <time.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include <netdb.h>
+#include <netinet/in.h>
+
+#include <linux/tcp.h>
+#include <linux/compiler.h>
+
+static int pf = AF_INET;
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+#ifndef SOL_MPTCP
+#define SOL_MPTCP 284
+#endif
+
+#ifndef MPTCP_INFO
+struct mptcp_info {
+	__u8	mptcpi_subflows;
+	__u8	mptcpi_add_addr_signal;
+	__u8	mptcpi_add_addr_accepted;
+	__u8	mptcpi_subflows_max;
+	__u8	mptcpi_add_addr_signal_max;
+	__u8	mptcpi_add_addr_accepted_max;
+	__u32	mptcpi_flags;
+	__u32	mptcpi_token;
+	__u64	mptcpi_write_seq;
+	__u64	mptcpi_snd_una;
+	__u64	mptcpi_rcv_nxt;
+	__u8	mptcpi_local_addr_used;
+	__u8	mptcpi_local_addr_max;
+	__u8	mptcpi_csum_enabled;
+	__u32	mptcpi_retransmits;
+	__u64	mptcpi_bytes_retrans;
+	__u64	mptcpi_bytes_sent;
+	__u64	mptcpi_bytes_received;
+	__u64	mptcpi_bytes_acked;
+};
+
+struct mptcp_subflow_data {
+	__u32		size_subflow_data;		/* size of this structure in userspace */
+	__u32		num_subflows;			/* must be 0, set by kernel */
+	__u32		size_kernel;			/* must be 0, set by kernel */
+	__u32		size_user;			/* size of one element in data[] */
+} __attribute__((aligned(8)));
+
+struct mptcp_subflow_addrs {
+	union {
+		__kernel_sa_family_t sa_family;
+		struct sockaddr sa_local;
+		struct sockaddr_in sin_local;
+		struct sockaddr_in6 sin6_local;
+		struct __kernel_sockaddr_storage ss_local;
+	};
+	union {
+		struct sockaddr sa_remote;
+		struct sockaddr_in sin_remote;
+		struct sockaddr_in6 sin6_remote;
+		struct __kernel_sockaddr_storage ss_remote;
+	};
+};
+
+#define MPTCP_INFO		1
+#define MPTCP_TCPINFO		2
+#define MPTCP_SUBFLOW_ADDRS	3
+#endif
+
+#ifndef MPTCP_FULL_INFO
+struct mptcp_subflow_info {
+	__u32				id;
+	struct mptcp_subflow_addrs	addrs;
+};
+
+struct mptcp_full_info {
+	__u32		size_tcpinfo_kernel;	/* must be 0, set by kernel */
+	__u32		size_tcpinfo_user;
+	__u32		size_sfinfo_kernel;	/* must be 0, set by kernel */
+	__u32		size_sfinfo_user;
+	__u32		num_subflows;		/* must be 0, set by kernel (real subflow count) */
+	__u32		size_arrays_user;	/* max subflows that userspace is interested in;
+						 * the buffers at subflow_info/tcp_info
+						 * are respectively at least:
+						 *  size_arrays * size_sfinfo_user
+						 *  size_arrays * size_tcpinfo_user
+						 * bytes wide
+						 */
+	__aligned_u64		subflow_info;
+	__aligned_u64		tcp_info;
+	struct mptcp_info	mptcp_info;
+};
+
+#define MPTCP_FULL_INFO		4
+#endif
+
+struct so_state {
+	struct mptcp_info mi;
+	struct mptcp_info last_sample;
+	struct tcp_info tcp_info;
+	struct mptcp_subflow_addrs addrs;
+	uint64_t mptcpi_rcv_delta;
+	uint64_t tcpi_rcv_delta;
+	bool pkt_stats_avail;
+};
+
+#ifndef MIN
+#define MIN(a, b) ((a) < (b) ? (a) : (b))
+#endif
+
+static void __noreturn die_perror(const char *msg)
+{
+	perror(msg);
+	exit(1);
+}
+
+static void die_usage(int r)
+{
+	fprintf(stderr, "Usage: mptcp_sockopt [-6]\n");
+	exit(r);
+}
+
+static void __noreturn xerror(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	fputc('\n', stderr);
+	exit(1);
+}
+
+static const char *getxinfo_strerr(int err)
+{
+	if (err == EAI_SYSTEM)
+		return strerror(errno);
+
+	return gai_strerror(err);
+}
+
+static void xgetaddrinfo(const char *node, const char *service,
+			 struct addrinfo *hints,
+			 struct addrinfo **res)
+{
+	int err;
+
+again:
+	err = getaddrinfo(node, service, hints, res);
+	if (err) {
+		const char *errstr;
+
+		if (err == EAI_SOCKTYPE) {
+			hints->ai_protocol = IPPROTO_TCP;
+			goto again;
+		}
+
+		errstr = getxinfo_strerr(err);
+
+		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
+			node ? node : "", service ? service : "", errstr);
+		exit(1);
+	}
+}
+
+static int sock_listen_mptcp(const char * const listenaddr,
+			     const char * const port)
+{
+	int sock = -1;
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_MPTCP,
+		.ai_socktype = SOCK_STREAM,
+		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
+	};
+
+	hints.ai_family = pf;
+
+	struct addrinfo *a, *addr;
+	int one = 1;
+
+	xgetaddrinfo(listenaddr, port, &hints, &addr);
+	hints.ai_family = pf;
+
+	for (a = addr; a; a = a->ai_next) {
+		sock = socket(a->ai_family, a->ai_socktype, IPPROTO_MPTCP);
+		if (sock < 0)
+			continue;
+
+		if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one,
+				     sizeof(one)))
+			perror("setsockopt");
+
+		if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
+			break; /* success */
+
+		perror("bind");
+		close(sock);
+		sock = -1;
+	}
+
+	freeaddrinfo(addr);
+
+	if (sock < 0)
+		xerror("could not create listen socket");
+
+	if (listen(sock, 20))
+		die_perror("listen");
+
+	return sock;
+}
+
+static int sock_connect_mptcp(const char * const remoteaddr,
+			      const char * const port, int proto)
+{
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_MPTCP,
+		.ai_socktype = SOCK_STREAM,
+	};
+	struct addrinfo *a, *addr;
+	int sock = -1;
+
+	hints.ai_family = pf;
+
+	xgetaddrinfo(remoteaddr, port, &hints, &addr);
+	for (a = addr; a; a = a->ai_next) {
+		sock = socket(a->ai_family, a->ai_socktype, proto);
+		if (sock < 0)
+			continue;
+
+		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
+			break; /* success */
+
+		die_perror("connect");
+	}
+
+	if (sock < 0)
+		xerror("could not create connect socket");
+
+	freeaddrinfo(addr);
+	return sock;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "h6")) != -1) {
+		switch (c) {
+		case 'h':
+			die_usage(0);
+			break;
+		case '6':
+			pf = AF_INET6;
+			break;
+		default:
+			die_usage(1);
+			break;
+		}
+	}
+}
+
+static void do_getsockopt_bogus_sf_data(int fd, int optname)
+{
+	struct mptcp_subflow_data good_data;
+	struct bogus_data {
+		struct mptcp_subflow_data d;
+		char buf[2];
+	} bd;
+	socklen_t olen, _olen;
+	int ret;
+
+	memset(&bd, 0, sizeof(bd));
+	memset(&good_data, 0, sizeof(good_data));
+
+	olen = sizeof(good_data);
+	good_data.size_subflow_data = olen;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* 0 size_subflow_data */
+	assert(olen == sizeof(good_data));
+
+	bd.d = good_data;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret == 0);
+	assert(olen == sizeof(good_data));
+	assert(bd.d.num_subflows == 1);
+	assert(bd.d.size_kernel > 0);
+	assert(bd.d.size_user == 0);
+
+	bd.d = good_data;
+	_olen = rand() % olen;
+	olen = _olen;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0);	/* bogus olen */
+	assert(olen == _olen);	/* must be unchanged */
+
+	bd.d = good_data;
+	olen = sizeof(good_data);
+	bd.d.size_kernel = 1;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* size_kernel not 0 */
+
+	bd.d = good_data;
+	olen = sizeof(good_data);
+	bd.d.num_subflows = 1;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* num_subflows not 0 */
+
+	/* forward compat check: larger struct mptcp_subflow_data on 'old' kernel */
+	bd.d = good_data;
+	olen = sizeof(bd);
+	bd.d.size_subflow_data = sizeof(bd);
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret == 0);
+
+	/* olen must be truncated to real data size filled by kernel: */
+	assert(olen == sizeof(good_data));
+
+	assert(bd.d.size_subflow_data == sizeof(bd));
+
+	bd.d = good_data;
+	bd.d.size_subflow_data += 1;
+	bd.d.size_user = 1;
+	olen = bd.d.size_subflow_data + 1;
+	_olen = olen;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &_olen);
+	assert(ret == 0);
+
+	/* no truncation, kernel should have filled 1 byte of optname payload in buf[1]: */
+	assert(olen == _olen);
+
+	assert(bd.d.size_subflow_data == sizeof(good_data) + 1);
+	assert(bd.buf[0] == 0);
+}
+
+static void do_getsockopt_mptcp_info(struct so_state *s, int fd, size_t w)
+{
+	struct mptcp_info i;
+	socklen_t olen;
+	int ret;
+
+	olen = sizeof(i);
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &i, &olen);
+
+	if (ret < 0)
+		die_perror("getsockopt MPTCP_INFO");
+
+	s->pkt_stats_avail = olen >= sizeof(i);
+
+	s->last_sample = i;
+	if (s->mi.mptcpi_write_seq == 0)
+		s->mi = i;
+
+	assert(s->mi.mptcpi_write_seq + w == i.mptcpi_write_seq);
+
+	s->mptcpi_rcv_delta = i.mptcpi_rcv_nxt - s->mi.mptcpi_rcv_nxt;
+}
+
+static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t w)
+{
+	struct my_tcp_info {
+		struct mptcp_subflow_data d;
+		struct tcp_info ti[2];
+	} ti;
+	int ret, tries = 5;
+	socklen_t olen;
+
+	do {
+		memset(&ti, 0, sizeof(ti));
+
+		ti.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+		ti.d.size_user = sizeof(struct tcp_info);
+		olen = sizeof(ti);
+
+		ret = getsockopt(fd, SOL_MPTCP, MPTCP_TCPINFO, &ti, &olen);
+		if (ret < 0)
+			xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)");
+
+		assert(olen <= sizeof(ti));
+		assert(ti.d.size_kernel > 0);
+		assert(ti.d.size_user ==
+		       MIN(ti.d.size_kernel, sizeof(struct tcp_info)));
+		assert(ti.d.num_subflows == 1);
+
+		assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data));
+		olen -= sizeof(struct mptcp_subflow_data);
+		assert(olen == ti.d.size_user);
+
+		s->tcp_info = ti.ti[0];
+
+		if (ti.ti[0].tcpi_bytes_sent == w &&
+		    ti.ti[0].tcpi_bytes_received == r)
+			goto done;
+
+		if (r == 0 && ti.ti[0].tcpi_bytes_sent == w &&
+		    ti.ti[0].tcpi_bytes_received) {
+			s->tcpi_rcv_delta = ti.ti[0].tcpi_bytes_received;
+			goto done;
+		}
+
+		/* wait and repeat, might be that tx is still ongoing */
+		sleep(1);
+	} while (tries-- > 0);
+
+	xerror("tcpi_bytes_sent %" PRIu64 ", want %zu. tcpi_bytes_received %" PRIu64 ", want %zu",
+		ti.ti[0].tcpi_bytes_sent, w, ti.ti[0].tcpi_bytes_received, r);
+
+done:
+	do_getsockopt_bogus_sf_data(fd, MPTCP_TCPINFO);
+}
+
+static void do_getsockopt_subflow_addrs(struct so_state *s, int fd)
+{
+	struct sockaddr_storage remote, local;
+	socklen_t olen, rlen, llen;
+	int ret;
+	struct my_addrs {
+		struct mptcp_subflow_data d;
+		struct mptcp_subflow_addrs addr[2];
+	} addrs;
+
+	memset(&addrs, 0, sizeof(addrs));
+	memset(&local, 0, sizeof(local));
+	memset(&remote, 0, sizeof(remote));
+
+	addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+	addrs.d.size_user = sizeof(struct mptcp_subflow_addrs);
+	olen = sizeof(addrs);
+
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen);
+	if (ret < 0)
+		die_perror("getsockopt MPTCP_SUBFLOW_ADDRS");
+
+	assert(olen <= sizeof(addrs));
+	assert(addrs.d.size_kernel > 0);
+	assert(addrs.d.size_user ==
+	       MIN(addrs.d.size_kernel, sizeof(struct mptcp_subflow_addrs)));
+	assert(addrs.d.num_subflows == 1);
+
+	assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data));
+	olen -= sizeof(struct mptcp_subflow_data);
+	assert(olen == addrs.d.size_user);
+
+	llen = sizeof(local);
+	ret = getsockname(fd, (struct sockaddr *)&local, &llen);
+	if (ret < 0)
+		die_perror("getsockname");
+	rlen = sizeof(remote);
+	ret = getpeername(fd, (struct sockaddr *)&remote, &rlen);
+	if (ret < 0)
+		die_perror("getpeername");
+
+	assert(rlen > 0);
+	assert(rlen == llen);
+
+	assert(remote.ss_family == local.ss_family);
+
+	assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) == 0);
+	assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) == 0);
+	s->addrs = addrs.addr[0];
+
+	memset(&addrs, 0, sizeof(addrs));
+
+	addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+	addrs.d.size_user = sizeof(sa_family_t);
+	olen = sizeof(addrs.d) + sizeof(sa_family_t);
+
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen);
+	assert(ret == 0);
+	assert(olen == sizeof(addrs.d) + sizeof(sa_family_t));
+
+	assert(addrs.addr[0].sa_family == pf);
+	assert(addrs.addr[0].sa_family == local.ss_family);
+
+	assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) != 0);
+	assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) != 0);
+
+	do_getsockopt_bogus_sf_data(fd, MPTCP_SUBFLOW_ADDRS);
+}
+
+static void do_getsockopt_mptcp_full_info(struct so_state *s, int fd)
+{
+	size_t data_size = sizeof(struct mptcp_full_info);
+	struct mptcp_subflow_info sfinfo[2];
+	struct tcp_info tcp_info[2];
+	struct mptcp_full_info mfi;
+	socklen_t olen;
+	int ret;
+
+	memset(&mfi, 0, data_size);
+	memset(tcp_info, 0, sizeof(tcp_info));
+	memset(sfinfo, 0, sizeof(sfinfo));
+
+	mfi.size_tcpinfo_user = sizeof(struct tcp_info);
+	mfi.size_sfinfo_user = sizeof(struct mptcp_subflow_info);
+	mfi.size_arrays_user = 2;
+	mfi.subflow_info = (unsigned long)&sfinfo[0];
+	mfi.tcp_info = (unsigned long)&tcp_info[0];
+	olen = data_size;
+
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_FULL_INFO, &mfi, &olen);
+	if (ret < 0) {
+		if (errno == EOPNOTSUPP) {
+			perror("MPTCP_FULL_INFO test skipped");
+			return;
+		}
+		xerror("getsockopt MPTCP_FULL_INFO");
+	}
+
+	assert(olen <= data_size);
+	assert(mfi.size_tcpinfo_kernel > 0);
+	assert(mfi.size_tcpinfo_user ==
+	       MIN(mfi.size_tcpinfo_kernel, sizeof(struct tcp_info)));
+	assert(mfi.size_sfinfo_kernel > 0);
+	assert(mfi.size_sfinfo_user ==
+	       MIN(mfi.size_sfinfo_kernel, sizeof(struct mptcp_subflow_info)));
+	assert(mfi.num_subflows == 1);
+
+	/* Tolerate future extension to mptcp_info struct and running newer
+	 * test on top of older kernel.
+	 * Anyway any kernel supporting MPTCP_FULL_INFO must at least include
+	 * the following in mptcp_info.
+	 */
+	assert(olen > (socklen_t)__builtin_offsetof(struct mptcp_full_info, tcp_info));
+	assert(mfi.mptcp_info.mptcpi_subflows == 0);
+	assert(mfi.mptcp_info.mptcpi_bytes_sent == s->last_sample.mptcpi_bytes_sent);
+	assert(mfi.mptcp_info.mptcpi_bytes_received == s->last_sample.mptcpi_bytes_received);
+
+	assert(sfinfo[0].id == 1);
+	assert(tcp_info[0].tcpi_bytes_sent == s->tcp_info.tcpi_bytes_sent);
+	assert(tcp_info[0].tcpi_bytes_received == s->tcp_info.tcpi_bytes_received);
+	assert(!memcmp(&sfinfo->addrs, &s->addrs, sizeof(struct mptcp_subflow_addrs)));
+}
+
+static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w)
+{
+	do_getsockopt_mptcp_info(s, fd, w);
+
+	do_getsockopt_tcp_info(s, fd, r, w);
+
+	do_getsockopt_subflow_addrs(s, fd);
+
+	if (r)
+		do_getsockopt_mptcp_full_info(s, fd);
+}
+
+static void connect_one_server(int fd, int pipefd)
+{
+	char buf[4096], buf2[4096];
+	size_t len, i, total;
+	struct so_state s;
+	bool eof = false;
+	ssize_t ret;
+
+	memset(&s, 0, sizeof(s));
+
+	len = rand() % (sizeof(buf) - 1);
+
+	if (len < 128)
+		len = 128;
+
+	for (i = 0; i < len ; i++) {
+		buf[i] = rand() % 26;
+		buf[i] += 'A';
+	}
+
+	buf[i] = '\n';
+
+	do_getsockopts(&s, fd, 0, 0);
+
+	/* un-block server */
+	ret = read(pipefd, buf2, 4);
+	assert(ret == 4);
+	close(pipefd);
+
+	assert(strncmp(buf2, "xmit", 4) == 0);
+
+	ret = write(fd, buf, len);
+	if (ret < 0)
+		die_perror("write");
+
+	if (ret != (ssize_t)len)
+		xerror("short write");
+
+	total = 0;
+	do {
+		ret = read(fd, buf2 + total, sizeof(buf2) - total);
+		if (ret < 0)
+			die_perror("read");
+		if (ret == 0) {
+			eof = true;
+			break;
+		}
+
+		total += ret;
+	} while (total < len);
+
+	if (total != len)
+		xerror("total %lu, len %lu eof %d\n", total, len, eof);
+
+	if (memcmp(buf, buf2, len))
+		xerror("data corruption");
+
+	if (s.tcpi_rcv_delta)
+		assert(s.tcpi_rcv_delta <= total);
+
+	do_getsockopts(&s, fd, ret, ret);
+
+	if (eof)
+		total += 1; /* sequence advances due to FIN */
+
+	assert(s.mptcpi_rcv_delta == (uint64_t)total);
+	close(fd);
+}
+
+static void process_one_client(int fd, int pipefd)
+{
+	ssize_t ret, ret2, ret3;
+	struct so_state s;
+	char buf[4096];
+
+	memset(&s, 0, sizeof(s));
+	do_getsockopts(&s, fd, 0, 0);
+
+	ret = write(pipefd, "xmit", 4);
+	assert(ret == 4);
+
+	ret = read(fd, buf, sizeof(buf));
+	if (ret < 0)
+		die_perror("read");
+
+	assert(s.mptcpi_rcv_delta <= (uint64_t)ret);
+
+	if (s.tcpi_rcv_delta)
+		assert(s.tcpi_rcv_delta == (uint64_t)ret);
+
+	ret2 = write(fd, buf, ret);
+	if (ret2 < 0)
+		die_perror("write");
+
+	/* wait for hangup */
+	ret3 = read(fd, buf, 1);
+	if (ret3 != 0)
+		xerror("expected EOF, got %lu", ret3);
+
+	do_getsockopts(&s, fd, ret, ret2);
+	if (s.mptcpi_rcv_delta != (uint64_t)ret + 1)
+		xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64 ", diff %" PRId64,
+		       s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - (ret + 1));
+
+	/* be nice when running on top of older kernel */
+	if (s.pkt_stats_avail) {
+		if (s.last_sample.mptcpi_bytes_sent != ret2)
+			xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64
+			       ", diff %" PRId64,
+			       s.last_sample.mptcpi_bytes_sent, ret2,
+			       s.last_sample.mptcpi_bytes_sent - ret2);
+		if (s.last_sample.mptcpi_bytes_received != ret)
+			xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64
+			       ", diff %" PRId64,
+			       s.last_sample.mptcpi_bytes_received, ret,
+			       s.last_sample.mptcpi_bytes_received - ret);
+		if (s.last_sample.mptcpi_bytes_acked != ret)
+			xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64
+			       ", diff %" PRId64,
+			       s.last_sample.mptcpi_bytes_acked, ret,
+			       s.last_sample.mptcpi_bytes_acked - ret);
+	}
+
+	close(fd);
+}
+
+static int xaccept(int s)
+{
+	int fd = accept(s, NULL, 0);
+
+	if (fd < 0)
+		die_perror("accept");
+
+	return fd;
+}
+
+static int server(int pipefd)
+{
+	int fd = -1, r;
+
+	switch (pf) {
+	case AF_INET:
+		fd = sock_listen_mptcp("127.0.0.1", "15432");
+		break;
+	case AF_INET6:
+		fd = sock_listen_mptcp("::1", "15432");
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+		break;
+	}
+
+	r = write(pipefd, "conn", 4);
+	assert(r == 4);
+
+	alarm(15);
+	r = xaccept(fd);
+
+	process_one_client(r, pipefd);
+
+	close(fd);
+	return 0;
+}
+
+static void test_ip_tos_sockopt(int fd)
+{
+	uint8_t tos_in, tos_out;
+	socklen_t s;
+	int r;
+
+	tos_in = rand() & 0xfc;
+	r = setsockopt(fd, SOL_IP, IP_TOS, &tos_in, sizeof(tos_out));
+	if (r != 0)
+		die_perror("setsockopt IP_TOS");
+
+	tos_out = 0;
+	s = sizeof(tos_out);
+	r = getsockopt(fd, SOL_IP, IP_TOS, &tos_out, &s);
+	if (r != 0)
+		die_perror("getsockopt IP_TOS");
+
+	if (tos_in != tos_out)
+		xerror("tos %x != %x socklen_t %d\n", tos_in, tos_out, s);
+
+	if (s != 1)
+		xerror("tos should be 1 byte");
+
+	s = 0;
+	r = getsockopt(fd, SOL_IP, IP_TOS, &tos_out, &s);
+	if (r != 0)
+		die_perror("getsockopt IP_TOS 0");
+	if (s != 0)
+		xerror("expect socklen_t == 0");
+
+	s = -1;
+	r = getsockopt(fd, SOL_IP, IP_TOS, &tos_out, &s);
+	if (r != -1 && errno != EINVAL)
+		die_perror("getsockopt IP_TOS did not indicate -EINVAL");
+	if (s != -1)
+		xerror("expect socklen_t == -1");
+}
+
+static int client(int pipefd)
+{
+	int fd = -1;
+
+	alarm(15);
+
+	switch (pf) {
+	case AF_INET:
+		fd = sock_connect_mptcp("127.0.0.1", "15432", IPPROTO_MPTCP);
+		break;
+	case AF_INET6:
+		fd = sock_connect_mptcp("::1", "15432", IPPROTO_MPTCP);
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+	}
+
+	test_ip_tos_sockopt(fd);
+
+	connect_one_server(fd, pipefd);
+
+	return 0;
+}
+
+static pid_t xfork(void)
+{
+	pid_t p = fork();
+
+	if (p < 0)
+		die_perror("fork");
+
+	return p;
+}
+
+static int rcheck(int wstatus, const char *what)
+{
+	if (WIFEXITED(wstatus)) {
+		if (WEXITSTATUS(wstatus) == 0)
+			return 0;
+		fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus));
+		return WEXITSTATUS(wstatus);
+	} else if (WIFSIGNALED(wstatus)) {
+		xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus));
+	} else if (WIFSTOPPED(wstatus)) {
+		xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus));
+	}
+
+	return 111;
+}
+
+static void init_rng(void)
+{
+	int fd = open("/dev/urandom", O_RDONLY);
+
+	if (fd >= 0) {
+		unsigned int foo;
+		ssize_t ret;
+
+		/* can't fail */
+		ret = read(fd, &foo, sizeof(foo));
+		assert(ret == sizeof(foo));
+
+		close(fd);
+		srand(foo);
+	} else {
+		srand(time(NULL));
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	int e1, e2, wstatus;
+	pid_t s, c, ret;
+	int pipefds[2];
+
+	parse_opts(argc, argv);
+
+	init_rng();
+
+	e1 = pipe(pipefds);
+	if (e1 < 0)
+		die_perror("pipe");
+
+	s = xfork();
+	if (s == 0) {
+		close(pipefds[0]);
+		ret = server(pipefds[1]);
+		close(pipefds[1]);
+		return ret;
+	}
+
+	close(pipefds[1]);
+
+	/* wait until server bound a socket */
+	e1 = read(pipefds[0], &e1, 4);
+	assert(e1 == 4);
+
+	c = xfork();
+	if (c == 0)
+		return client(pipefds[0]);
+
+	close(pipefds[0]);
+
+	ret = waitpid(s, &wstatus, 0);
+	if (ret == -1)
+		die_perror("waitpid");
+	e1 = rcheck(wstatus, "server");
+	ret = waitpid(c, &wstatus, 0);
+	if (ret == -1)
+		die_perror("waitpid");
+	e2 = rcheck(wstatus, "client");
+
+	return e1 ? e1 : e2;
+}

linux-7.2.3/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh

@@ -0,0 +1,371 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Double quotes to prevent globbing and word splitting is recommended in new
+# code but we accept it, especially because there were too many before having
+# address all other issues detected by shellcheck.
+#shellcheck disable=SC2086
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+ret=0
+sin=""
+sout=""
+cin=""
+cout=""
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
+iptables="iptables"
+ip6tables="ip6tables"
+
+ns1=""
+ns2=""
+ns_sbox=""
+
+usage() {
+	echo "Usage: $0 [ -i ] [ -h ]"
+	echo -e "\t-i: use 'ip mptcp' instead of 'pm_nl_ctl'"
+	echo -e "\t-h: help"
+}
+
+while getopts "hi" option;do
+	case "$option" in
+	"h")
+		usage "$0"
+		exit ${KSFT_PASS}
+		;;
+	"i")
+		mptcp_lib_set_ip_mptcp
+		;;
+	"?")
+		usage "$0"
+		exit ${KSFT_FAIL}
+		;;
+	esac
+done
+
+add_mark_rules()
+{
+	local ns=$1
+	local m=$2
+
+	local t
+	for t in ${iptables} ${ip6tables}; do
+		# just to debug: check we have multiple subflows connection requests
+		ip netns exec $ns $t -A OUTPUT -p tcp --syn -m mark --mark $m -j ACCEPT
+
+		# RST packets might be handled by a internal dummy socket
+		ip netns exec $ns $t -A OUTPUT -p tcp --tcp-flags RST RST -m mark --mark 0 -j ACCEPT
+
+		ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark $m -j ACCEPT
+		ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark 0 -j DROP
+	done
+}
+
+init()
+{
+	mptcp_lib_ns_init ns1 ns2 ns_sbox
+
+	local i
+	for i in $(seq 1 4); do
+		ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2"
+		ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i
+		ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad
+		ip -net "$ns1" link set ns1eth$i up
+
+		ip -net "$ns2" addr add 10.0.$i.2/24 dev ns2eth$i
+		ip -net "$ns2" addr add dead:beef:$i::2/64 dev ns2eth$i nodad
+		ip -net "$ns2" link set ns2eth$i up
+
+		# let $ns2 reach any $ns1 address from any interface
+		ip -net "$ns2" route add default via 10.0.$i.1 dev ns2eth$i metric 10$i
+
+		mptcp_lib_pm_nl_add_endpoint "${ns1}" "10.0.${i}.1" flags signal
+		mptcp_lib_pm_nl_add_endpoint "${ns1}" "dead:beef:${i}::1" flags signal
+
+		mptcp_lib_pm_nl_add_endpoint "${ns2}" "10.0.${i}.2" flags signal
+		mptcp_lib_pm_nl_add_endpoint "${ns2}" "dead:beef:${i}::2" flags signal
+	done
+
+	mptcp_lib_pm_nl_set_limits "${ns1}" 8 8
+	mptcp_lib_pm_nl_set_limits "${ns2}" 8 8
+
+	add_mark_rules $ns1 1
+	add_mark_rules $ns2 2
+}
+
+# This function is used in the cleanup trap
+#shellcheck disable=SC2317,SC2329
+cleanup()
+{
+	mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns_sbox}"
+	rm -f "$cin" "$cout"
+	rm -f "$sin" "$sout"
+}
+
+mptcp_lib_check_mptcp
+mptcp_lib_check_kallsyms
+mptcp_lib_check_tools ip "${iptables}" "${ip6tables}"
+
+check_mark()
+{
+	local ns=$1
+	local af=$2
+
+	local tables=${iptables}
+
+	if [ $af -eq 6 ];then
+		tables=${ip6tables}
+	fi
+
+	local counters values
+	counters=$(ip netns exec $ns $tables -v -L OUTPUT | grep DROP)
+	values=${counters%DROP*}
+
+	local v
+	for v in $values; do
+		if [ $v -ne 0 ]; then
+			mptcp_lib_pr_fail "got $tables $values in ns $ns," \
+					  "not 0 - not all expected packets marked"
+			ret=${KSFT_FAIL}
+			return 1
+		fi
+	done
+
+	return 0
+}
+
+print_title()
+{
+	mptcp_lib_print_title "${@}"
+}
+
+do_transfer()
+{
+	local listener_ns="$1"
+	local connector_ns="$2"
+	local cl_proto="$3"
+	local srv_proto="$4"
+	local connect_addr="$5"
+
+	local port=12001
+
+	:> "$cout"
+	:> "$sout"
+
+	local mptcp_connect="./mptcp_connect -r 20"
+
+	local local_addr ip
+	if mptcp_lib_is_v6 "${connect_addr}"; then
+		local_addr="::"
+		ip=ipv6
+	else
+		local_addr="0.0.0.0"
+		ip=ipv4
+	fi
+
+	cmsg="TIMESTAMPNS"
+	if mptcp_lib_kallsyms_has "mptcp_ioctl$"; then
+		cmsg+=",TCPINQ"
+	fi
+
+	mptcp_lib_nstat_init "${listener_ns}"
+	mptcp_lib_nstat_init "${connector_ns}"
+
+	ip netns exec ${listener_ns} \
+		$mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \
+			${local_addr} < "$sin" > "$sout" &
+	local spid=$!
+
+	mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}"
+
+	ip netns exec ${connector_ns} \
+		$mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \
+			$connect_addr < "$cin" > "$cout" &
+
+	local cpid=$!
+
+	mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \
+		"${connector_ns}" "${port}" "${cpid}" "${spid}" &
+	local timeout_pid=$!
+
+	wait $cpid
+	local retc=$?
+	wait $spid
+	local rets=$?
+
+	if kill -0 $timeout_pid; then
+		# Finished before the timeout: kill the background job
+		mptcp_lib_kill_group_wait $timeout_pid
+		timeout_pid=0
+	fi
+
+	mptcp_lib_nstat_get "${listener_ns}"
+	mptcp_lib_nstat_get "${connector_ns}"
+
+	print_title "Transfer ${ip:2}"
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then
+		mptcp_lib_pr_fail "client exit code $retc, server $rets"
+		mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}"
+
+		mptcp_lib_result_fail "transfer ${ip}"
+
+		ret=${KSFT_FAIL}
+		return 1
+	fi
+	if ! mptcp_lib_check_transfer $cin $sout "file received by server"; then
+		rets=1
+	else
+		mptcp_lib_pr_ok
+	fi
+	mptcp_lib_result_code "${rets}" "transfer ${ip}"
+
+	print_title "Mark ${ip:2}"
+	if [ $local_addr = "::" ];then
+		check_mark $listener_ns 6 || retc=1
+		check_mark $connector_ns 6 || retc=1
+	else
+		check_mark $listener_ns 4 || retc=1
+		check_mark $connector_ns 4 || retc=1
+	fi
+
+	mptcp_lib_result_code "${retc}" "mark ${ip}"
+
+	if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
+		mptcp_lib_pr_ok
+		return 0
+	fi
+	mptcp_lib_pr_fail
+
+	return 1
+}
+
+make_file()
+{
+	local name=$1
+	local who=$2
+	local size=$3
+
+	mptcp_lib_make_file $name 1024 $size
+
+	echo "Created $name (size $size KB) containing data sent by $who"
+}
+
+do_mptcp_sockopt_tests()
+{
+	local lret=0
+
+	if ! mptcp_lib_kallsyms_has "mptcp_diag_fill_info$"; then
+		mptcp_lib_pr_skip "MPTCP sockopt not supported"
+		mptcp_lib_result_skip "sockopt"
+		return
+	fi
+
+	ip netns exec "$ns_sbox" ./mptcp_sockopt
+	lret=$?
+
+	print_title "SOL_MPTCP sockopt v4"
+	if [ $lret -ne 0 ]; then
+		mptcp_lib_pr_fail
+		mptcp_lib_result_fail "sockopt v4"
+		ret=$lret
+		return
+	fi
+	mptcp_lib_pr_ok
+	mptcp_lib_result_pass "sockopt v4"
+
+	ip netns exec "$ns_sbox" ./mptcp_sockopt -6
+	lret=$?
+
+	print_title "SOL_MPTCP sockopt v6"
+	if [ $lret -ne 0 ]; then
+		mptcp_lib_pr_fail
+		mptcp_lib_result_fail "sockopt v6"
+		ret=$lret
+		return
+	fi
+	mptcp_lib_pr_ok
+	mptcp_lib_result_pass "sockopt v6"
+}
+
+run_tests()
+{
+	local listener_ns="$1"
+	local connector_ns="$2"
+	local connect_addr="$3"
+	local lret=0
+
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr}
+
+	lret=$?
+
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return
+	fi
+}
+
+do_tcpinq_test()
+{
+	print_title "TCP_INQ cmsg/ioctl $*"
+	ip netns exec "$ns_sbox" ./mptcp_inq "$@"
+	local lret=$?
+	if [ $lret -ne 0 ];then
+		ret=$lret
+		mptcp_lib_pr_fail
+		mptcp_lib_result_fail "TCP_INQ: $*"
+		return $lret
+	fi
+
+	mptcp_lib_pr_ok
+	mptcp_lib_result_pass "TCP_INQ: $*"
+	return $lret
+}
+
+do_tcpinq_tests()
+{
+	local lret=0
+
+	if ! mptcp_lib_kallsyms_has "mptcp_ioctl$"; then
+		mptcp_lib_pr_skip "TCP_INQ not supported"
+		mptcp_lib_result_skip "TCP_INQ"
+		return
+	fi
+
+	local args
+	for args in "-t tcp" "-r tcp"; do
+		do_tcpinq_test $args
+		lret=$?
+		if [ $lret -ne 0 ] ; then
+			return $lret
+		fi
+		do_tcpinq_test -6 $args
+		lret=$?
+		if [ $lret -ne 0 ] ; then
+			return $lret
+		fi
+	done
+
+	do_tcpinq_test -r tcp -t tcp
+
+	return $?
+}
+
+sin=$(mktemp)
+sout=$(mktemp)
+cin=$(mktemp)
+cout=$(mktemp)
+trap cleanup EXIT
+init
+make_file "$cin" "client" 1
+make_file "$sin" "server" 1
+mptcp_lib_subtests_last_ts_reset
+
+run_tests $ns1 $ns2 10.0.1.1
+run_tests $ns1 $ns2 dead:beef:1::1
+
+do_mptcp_sockopt_tests
+do_tcpinq_tests
+
+mptcp_lib_result_print_all_tap
+exit $ret

linux-7.2.3/tools/testing/selftests/net/mptcp/pm_netlink.sh

@@ -0,0 +1,298 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+ret=0
+
+usage() {
+	echo "Usage: $0 [ -i ] [ -h ]"
+	echo -e "\t-i: use 'ip mptcp' instead of 'pm_nl_ctl'"
+	echo -e "\t-h: help"
+}
+
+optstring=hi
+while getopts "$optstring" option;do
+	case "$option" in
+	"h")
+		usage "$0"
+		exit ${KSFT_PASS}
+		;;
+	"i")
+		mptcp_lib_set_ip_mptcp
+		;;
+	"?")
+		usage "$0"
+		exit ${KSFT_FAIL}
+		;;
+	esac
+done
+
+ns1=""
+err=$(mktemp)
+
+# This function is used in the cleanup trap
+#shellcheck disable=SC2317,SC2329
+cleanup()
+{
+	rm -f "${err}"
+	mptcp_lib_ns_exit "${ns1}"
+}
+
+mptcp_lib_check_mptcp
+mptcp_lib_check_tools ip
+
+trap cleanup EXIT
+
+mptcp_lib_ns_init ns1
+
+format_limits() {
+	local accept="${1}"
+	local subflows="${2}"
+
+	if mptcp_lib_is_ip_mptcp; then
+		# with a space at the end
+		printf "add_addr_accepted %d subflows %d \n" "${accept}" "${subflows}"
+	else
+		printf "accept %d\nsubflows %d\n" "${accept}" "${subflows}"
+	fi
+}
+
+get_limits() {
+	if mptcp_lib_is_ip_mptcp; then
+		ip -n "${ns1}" mptcp limits
+	else
+		ip netns exec "${ns1}" ./pm_nl_ctl limits
+	fi
+}
+
+get_limits_nb() {
+	if mptcp_lib_is_ip_mptcp; then
+		ip -n "${ns1}" mptcp limits | awk '{ print $2" "$4 }'
+	else
+		ip netns exec "${ns1}" ./pm_nl_ctl limits | \
+			awk '{ printf "%s ", $2 }'
+	fi
+}
+
+format_endpoints() {
+	mptcp_lib_pm_nl_format_endpoints "${@}"
+}
+
+# This function is invoked indirectly
+#shellcheck disable=SC2317,SC2329
+get_endpoint() {
+	mptcp_lib_pm_nl_get_endpoint "${ns1}" "${@}"
+}
+
+change_address() {
+	local addr=${1}
+	local flags=${2}
+
+	if mptcp_lib_is_ip_mptcp; then
+		ip -n "${ns1}" mptcp endpoint change "${addr}" "${flags}"
+	else
+		ip netns exec "${ns1}" ./pm_nl_ctl set "${addr}" flags "${flags}"
+	fi
+}
+
+set_limits()
+{
+	mptcp_lib_pm_nl_set_limits "${ns1}" "${@}"
+}
+
+add_endpoint()
+{
+	mptcp_lib_pm_nl_add_endpoint "${ns1}" "${@}"
+}
+
+del_endpoint()
+{
+	mptcp_lib_pm_nl_del_endpoint "${ns1}" "${@}"
+}
+
+flush_endpoint()
+{
+	mptcp_lib_pm_nl_flush_endpoint "${ns1}"
+}
+
+show_endpoints()
+{
+	mptcp_lib_pm_nl_show_endpoints "${ns1}"
+}
+
+change_endpoint()
+{
+	mptcp_lib_pm_nl_change_endpoint "${ns1}" "${@}"
+}
+
+check()
+{
+	local cmd="$1"
+	local expected="$2"
+	local msg="$3"
+	local exp_error="$4"
+	local rc=0
+
+	mptcp_lib_print_title "$msg"
+	mptcp_lib_check_output "${err}" "${cmd}" "${expected}" "${exp_error}" ||
+		rc=${?}
+	if [ ${rc} -eq 2 ]; then
+		mptcp_lib_result_fail "${msg} # error ${rc}"
+		ret=${KSFT_FAIL}
+	elif [ ${rc} -eq 0 ]; then
+		mptcp_lib_print_ok "[ OK ]"
+		mptcp_lib_result_pass "${msg}"
+	elif [ ${rc} -eq 1 ]; then
+		mptcp_lib_result_fail "${msg} # different output"
+		ret=${KSFT_FAIL}
+	fi
+}
+
+mptcp_lib_subtests_last_ts_reset
+
+check "show_endpoints" "" "defaults addr list"
+
+default_limits="$(get_limits)"
+if mptcp_lib_expect_all_features; then
+	check "get_limits" "$(format_limits 0 2)" "defaults limits"
+fi
+
+add_endpoint 10.0.1.1
+add_endpoint 10.0.1.2 flags subflow dev lo
+add_endpoint 10.0.1.3 flags signal,backup
+check "get_endpoint 1" "$(format_endpoints "1,10.0.1.1")" "simple add/get addr"
+
+check "show_endpoints" \
+	"$(format_endpoints "1,10.0.1.1" \
+			    "2,10.0.1.2,subflow,lo" \
+			    "3,10.0.1.3,signal backup")" "dump addrs"
+
+del_endpoint 2
+check "get_endpoint 2" "" "simple del addr" 1
+check "show_endpoints" \
+	"$(format_endpoints "1,10.0.1.1" \
+			    "3,10.0.1.3,signal backup")" "dump addrs after del"
+add_endpoint 10.0.1.2 id 2
+
+add_endpoint 10.0.1.3 2>/dev/null
+check "get_endpoint 4" "" "duplicate addr" 1
+
+add_endpoint 10.0.1.4 flags signal
+check "get_endpoint 4" "$(format_endpoints "4,10.0.1.4,signal")" "id addr increment"
+
+read -r -a default_limits_nb <<< "$(get_limits_nb)"
+# limits have been increased: from 8 to 64 for subflows/add_addr & 255 for endp
+if mptcp_lib_expect_all_features || set_limits 9 9 2>/dev/null; then
+	max_endp=255
+	max_limits=64
+else
+	max_endp=8
+	max_limits=8
+fi
+set_limits "${default_limits_nb[@]}"
+
+for i in $(seq 5 ${max_endp}); do
+	add_endpoint "10.0.0.${i}" id "${i}"
+done
+check "get_endpoint ${max_endp}" \
+	"$(format_endpoints "${max_endp},10.0.0.${max_endp}")" "id limit"
+
+if add_endpoint '10.0.0.1' &>/dev/null; then
+	hardlimit="no error"
+else
+	hardlimit="error"
+fi
+check "echo ${hardlimit}" "error" "above hard addr limit"
+
+flush_endpoint
+check "show_endpoints" "" "flush addrs"
+
+# "unknown" flag is only supported by pm_nl_ctl
+if ! mptcp_lib_is_ip_mptcp; then
+	add_endpoint 10.0.1.1 flags unknown
+	check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" \
+	      "ignore unknown flags"
+	flush_endpoint
+fi
+
+set_limits $((max_limits + 1)) 1 2>/dev/null
+check "get_limits" "${default_limits}" "rcv addrs above hard limit"
+
+set_limits 1 $((max_limits + 1)) 2>/dev/null
+check "get_limits" "${default_limits}" "subflows above hard limit"
+
+set_limits ${max_limits} ${max_limits}
+flush_endpoint  ## to make sure it doesn't affect the limits
+check "get_limits" "$(format_limits ${max_limits} ${max_limits})" "set limits"
+
+flush_endpoint
+add_endpoint 10.0.1.1
+add_endpoint 10.0.1.2
+add_endpoint 10.0.1.3 id 100
+add_endpoint 10.0.1.4
+add_endpoint 10.0.1.5 id 254
+add_endpoint 10.0.1.6
+add_endpoint 10.0.1.7
+add_endpoint 10.0.1.8
+check "show_endpoints" \
+	"$(format_endpoints "1,10.0.1.1" \
+			    "2,10.0.1.2" \
+			    "3,10.0.1.7" \
+			    "4,10.0.1.8" \
+			    "100,10.0.1.3" \
+			    "101,10.0.1.4" \
+			    "254,10.0.1.5" \
+			    "255,10.0.1.6")" "set ids"
+
+flush_endpoint
+add_endpoint 10.0.0.1
+add_endpoint 10.0.0.2 id 254
+add_endpoint 10.0.0.3
+add_endpoint 10.0.0.4
+add_endpoint 10.0.0.5 id 253
+add_endpoint 10.0.0.6
+add_endpoint 10.0.0.7
+add_endpoint 10.0.0.8
+check "show_endpoints" \
+	"$(format_endpoints "1,10.0.0.1" \
+			    "2,10.0.0.4" \
+			    "3,10.0.0.6" \
+			    "4,10.0.0.7" \
+			    "5,10.0.0.8" \
+			    "253,10.0.0.5" \
+			    "254,10.0.0.2" \
+			    "255,10.0.0.3")" "wrap-around ids"
+
+flush_endpoint
+add_endpoint 10.0.1.1 flags subflow
+change_address 10.0.1.1 backup
+check "show_endpoints" "$(format_endpoints "1,10.0.1.1,subflow backup")" \
+	"set flags (backup)"
+change_address 10.0.1.1 nobackup
+check "show_endpoints" "$(format_endpoints "1,10.0.1.1,subflow")" \
+	"          (nobackup)"
+
+# fullmesh support has been added later
+change_endpoint 1 fullmesh 2>/dev/null
+if show_endpoints | grep -q "fullmesh" ||
+   mptcp_lib_expect_all_features; then
+	check "show_endpoints" "$(format_endpoints "1,10.0.1.1,subflow fullmesh")" \
+		"          (fullmesh)"
+	change_endpoint 1 nofullmesh
+	check "show_endpoints" "$(format_endpoints "1,10.0.1.1,subflow")" \
+		"          (nofullmesh)"
+	change_endpoint 1 backup,fullmesh
+	check "show_endpoints" "$(format_endpoints "1,10.0.1.1,subflow backup fullmesh")" \
+		"          (backup,fullmesh)"
+else
+	for st in fullmesh nofullmesh backup,fullmesh; do
+		st="          (${st})"
+		mptcp_lib_print_title "${st}"
+		mptcp_lib_pr_skip
+		mptcp_lib_result_skip "${st}"
+	done
+fi
+
+mptcp_lib_result_print_all_tap
+exit $ret

linux-7.2.3/tools/testing/selftests/net/mptcp/settings

@@ -0,0 +1 @@
+timeout=1800

linux-7.2.3/tools/testing/selftests/net/mptcp/simult_flows.sh

@@ -0,0 +1,315 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Double quotes to prevent globbing and word splitting is recommended in new
+# code but we accept it, especially because there were too many before having
+# address all other issues detected by shellcheck.
+#shellcheck disable=SC2086
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+ns1=""
+ns2=""
+ns3=""
+capture=false
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
+# a bit more space: because we have more to display
+MPTCP_LIB_TEST_FORMAT="%02u %-60s"
+ret=0
+bail=0
+slack=50
+large=""
+small=""
+sout=""
+cout=""
+capout=""
+size=0
+
+usage() {
+	echo "Usage: $0 [ -b ] [ -c ] [ -d ] [ -i]"
+	echo -e "\t-b: bail out after first error, otherwise runs all testcases"
+	echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
+	echo -e "\t-d: debug this script"
+	echo -e "\t-i: use 'ip mptcp' instead of 'pm_nl_ctl'"
+}
+
+# This function is used in the cleanup trap
+#shellcheck disable=SC2317,SC2329
+cleanup()
+{
+	rm -f "$cout" "$sout"
+	rm -f "$large" "$small"
+	rm -f "$capout"
+
+	mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns3}"
+}
+
+mptcp_lib_check_mptcp
+mptcp_lib_check_tools ip tc
+
+#  "$ns1"              ns2                    ns3
+#     ns1eth1    ns2eth1   ns2eth3      ns3eth1
+#            netem
+#     ns1eth2    ns2eth2
+#            netem
+
+setup()
+{
+	large=$(mktemp)
+	small=$(mktemp)
+	sout=$(mktemp)
+	cout=$(mktemp)
+	capout=$(mktemp)
+	size=$((2 * 2048 * 4096))
+
+	dd if=/dev/zero of=$small bs=4096 count=20 >/dev/null 2>&1
+	dd if=/dev/zero of=$large bs=4096 count=$((size / 4096)) >/dev/null 2>&1
+
+	trap cleanup EXIT
+
+	mptcp_lib_ns_init ns1 ns2 ns3
+
+	ip link add ns1eth1 netns "$ns1" type veth peer name ns2eth1 netns "$ns2"
+	ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth2 netns "$ns2"
+	ip link add ns2eth3 netns "$ns2" type veth peer name ns3eth1 netns "$ns3"
+
+	ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth1
+	ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth1 nodad
+	ip -net "$ns1" link set ns1eth1 up mtu 1500 gso_max_segs 0
+	ip -net "$ns1" route add default via 10.0.1.2
+	ip -net "$ns1" route add default via dead:beef:1::2
+
+	ip -net "$ns1" addr add 10.0.2.1/24 dev ns1eth2
+	ip -net "$ns1" addr add dead:beef:2::1/64 dev ns1eth2 nodad
+	ip -net "$ns1" link set ns1eth2 up mtu 1500 gso_max_segs 0
+	ip -net "$ns1" route add default via 10.0.2.2 metric 101
+	ip -net "$ns1" route add default via dead:beef:2::2 metric 101
+
+	mptcp_lib_pm_nl_set_limits "${ns1}" 1 1
+	mptcp_lib_pm_nl_add_endpoint "${ns1}" 10.0.2.1 dev ns1eth2 flags subflow
+
+	ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1
+	ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad
+	ip -net "$ns2" link set ns2eth1 up mtu 1500 gso_max_segs 0
+
+	ip -net "$ns2" addr add 10.0.2.2/24 dev ns2eth2
+	ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth2 nodad
+	ip -net "$ns2" link set ns2eth2 up mtu 1500 gso_max_segs 0
+
+	ip -net "$ns2" addr add 10.0.3.2/24 dev ns2eth3
+	ip -net "$ns2" addr add dead:beef:3::2/64 dev ns2eth3 nodad
+	ip -net "$ns2" link set ns2eth3 up mtu 1500 gso_max_segs 0
+	ip netns exec "$ns2" sysctl -q net.ipv4.ip_forward=1
+	ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.forwarding=1
+
+	ip -net "$ns3" addr add 10.0.3.3/24 dev ns3eth1
+	ip -net "$ns3" addr add dead:beef:3::3/64 dev ns3eth1 nodad
+	ip -net "$ns3" link set ns3eth1 up mtu 1500 gso_max_segs 0
+	ip -net "$ns3" route add default via 10.0.3.2
+	ip -net "$ns3" route add default via dead:beef:3::2
+
+	mptcp_lib_pm_nl_set_limits "${ns3}" 1 1
+
+	# debug build can slow down measurably the test program
+	# we use quite tight time limit on the run-time, to ensure
+	# maximum B/W usage.
+	# Use kmemleak/lockdep/kasan/prove_locking presence as a rough
+	# estimate for this being a debug kernel and increase the
+	# maximum run-time accordingly. Observed run times for CI builds
+	# running selftests, including kbuild, were used to determine the
+	# amount of time to add.
+	grep -q ' kmemleak_init$\| lockdep_init$\| kasan_init$\| prove_locking$' /proc/kallsyms && slack=$((slack+550))
+}
+
+do_transfer()
+{
+	local cin=$1
+	local sin=$2
+	local max_time=$3
+	local port
+	port=$((10000+MPTCP_LIB_TEST_COUNTER))
+
+	:> "$cout"
+	:> "$sout"
+	:> "$capout"
+
+	if $capture; then
+		local capuser
+		local rndh="${ns1:4}"
+		if [ -z $SUDO_USER ] ; then
+			capuser=""
+		else
+			capuser="-Z $SUDO_USER"
+		fi
+
+		local capfile="${rndh}-${port}"
+		local capopt="-i any -s 65535 -B 32768 ${capuser}"
+
+		ip netns exec ${ns3}  tcpdump ${capopt} -w "${capfile}-listener.pcap"  >> "${capout}" 2>&1 &
+		local cappid_listener=$!
+
+		ip netns exec ${ns1} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 &
+		local cappid_connector=$!
+
+		sleep 1
+	fi
+
+	mptcp_lib_nstat_init "${ns3}"
+	mptcp_lib_nstat_init "${ns1}"
+
+	ip netns exec ${ns3} \
+		./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \
+			0.0.0.0 < "$sin" > "$sout" &
+	local spid=$!
+
+	mptcp_lib_wait_local_port_listen "${ns3}" "${port}"
+
+	ip netns exec ${ns1} \
+		./mptcp_connect -jt ${timeout_poll} -p $port -T $max_time \
+			10.0.3.3 < "$cin" > "$cout" &
+	local cpid=$!
+
+	mptcp_lib_wait_timeout "${timeout_test}" "${ns3}" "${ns1}" "${port}" \
+		"${cpid}" "${spid}" &
+	local timeout_pid=$!
+
+	wait $cpid
+	local retc=$?
+	wait $spid
+	local rets=$?
+
+	if kill -0 $timeout_pid; then
+		# Finished before the timeout: kill the background job
+		mptcp_lib_kill_group_wait $timeout_pid
+		timeout_pid=0
+	fi
+
+	if $capture; then
+		sleep 1
+		kill ${cappid_listener}
+		kill ${cappid_connector}
+	fi
+
+	mptcp_lib_nstat_get "${ns3}"
+	mptcp_lib_nstat_get "${ns1}"
+
+	cmp $sin $cout > /dev/null 2>&1
+	local cmps=$?
+	cmp $cin $sout > /dev/null 2>&1
+	local cmpc=$?
+
+	if [ $retc -eq 0 ] && [ $rets -eq 0 ] &&
+	   [ $cmpc -eq 0 ] && [ $cmps -eq 0 ] &&
+	   [ $timeout_pid -eq 0 ]; then
+		printf "%-16s" " max $max_time "
+		mptcp_lib_pr_ok
+		cat "$capout"
+		return 0
+	fi
+
+	mptcp_lib_pr_fail "client exit code $retc, server $rets"
+	mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}"
+	ls -l $sin $cout
+	ls -l $cin $sout
+
+	cat "$capout"
+	return 1
+}
+
+run_test()
+{
+	local rate1=$1
+	local rate2=$2
+	local delay1=$3
+	local delay2=$4
+	local limit1=$5
+	local limit2=$6
+	local lret
+	local dev
+	shift 6
+	local msg=$*
+
+	[ $delay1 -gt 0 ] && delay1="delay ${delay1}ms" || delay1=""
+	[ $delay2 -gt 0 ] && delay2="delay ${delay2}ms" || delay2=""
+
+	for dev in ns1eth1 ns1eth2; do
+		tc -n $ns1 qdisc del dev $dev root >/dev/null 2>&1
+	done
+	for dev in ns2eth1 ns2eth2; do
+		tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1
+	done
+
+	# keep the queued pkts number low, or the RTT estimator will see
+	# increasing latency over time.
+	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 limit ${limit1}
+	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 limit ${limit2}
+	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 limit ${limit1}
+	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 limit ${limit2}
+
+	# time is measured in ms, account for transfer size, aggregated link speed
+	# and header overhead (10%)
+	#              ms    byte -> bit   10%        mbit      -> kbit -> bit  10%
+	local time=$((1000 * size  *  8  * 10 / ((rate1 + rate2) * 1000 * 1000 * 9) ))
+
+	# mptcp_connect will do some sleeps to allow the mp_join handshake
+	# completion (see mptcp_connect): 200ms on each side, add some slack
+	time=$((time + 400 + slack))
+
+	mptcp_lib_print_title "$msg"
+	do_transfer $small $large $time
+	lret=$?
+	mptcp_lib_result_code "${lret}" "${msg}"
+	if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then
+		ret=$lret
+		[ $bail -eq 0 ] || exit $ret
+	fi
+
+	msg+=" - reverse direction"
+	mptcp_lib_print_title "${msg}"
+	do_transfer $large $small $time
+	lret=$?
+	mptcp_lib_result_code "${lret}" "${msg}"
+	if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then
+		ret=$lret
+		[ $bail -eq 0 ] || exit $ret
+	fi
+}
+
+while getopts "bcdhi" option;do
+	case "$option" in
+	"h")
+		usage $0
+		exit ${KSFT_PASS}
+		;;
+	"b")
+		bail=1
+		;;
+	"c")
+		capture=true
+		;;
+	"d")
+		set -x
+		;;
+	"i")
+		mptcp_lib_set_ip_mptcp
+		;;
+	"?")
+		usage $0
+		exit ${KSFT_FAIL}
+		;;
+	esac
+done
+
+setup
+mptcp_lib_subtests_last_ts_reset
+run_test 10 10 0 0  20 20 "balanced bwidth"
+run_test 10 10 1 25 20 50 "balanced bwidth with unbalanced delay"
+
+# we still need some additional infrastructure to pass the following test-cases
+MPTCP_LIB_SUBTEST_FLAKY=1 run_test 10 3 0 0  30 20 "unbalanced bwidth"
+run_test 10 3 1 25 40 30 "unbalanced bwidth with unbalanced delay"
+run_test 10 3 25 1 50 30 "unbalanced bwidth with opposed, unbalanced delay"
+
+mptcp_lib_result_print_all_tap
+exit $ret

linux-7.2.3/tools/testing/selftests/net/mptcp/userspace_pm.sh

@@ -0,0 +1,945 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Double quotes to prevent globbing and word splitting is recommended in new
+# code but we accept it.
+#shellcheck disable=SC2086
+
+# Some variables are used below but indirectly, see verify_*_event()
+#shellcheck disable=SC2034
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+mptcp_lib_check_mptcp
+mptcp_lib_check_kallsyms
+
+if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
+	echo "userspace pm tests are not supported by the kernel: SKIP"
+	exit ${KSFT_SKIP}
+fi
+mptcp_lib_check_tools ip
+
+ANNOUNCED=${MPTCP_LIB_EVENT_ANNOUNCED}
+REMOVED=${MPTCP_LIB_EVENT_REMOVED}
+SUB_ESTABLISHED=${MPTCP_LIB_EVENT_SUB_ESTABLISHED}
+SUB_CLOSED=${MPTCP_LIB_EVENT_SUB_CLOSED}
+LISTENER_CREATED=${MPTCP_LIB_EVENT_LISTENER_CREATED}
+LISTENER_CLOSED=${MPTCP_LIB_EVENT_LISTENER_CLOSED}
+
+AF_INET=${MPTCP_LIB_AF_INET}
+AF_INET6=${MPTCP_LIB_AF_INET6}
+
+file=""
+server_evts=""
+client_evts=""
+server_evts_pid=0
+client_evts_pid=0
+client4_pid=0
+server4_pid=0
+client6_pid=0
+server6_pid=0
+client4_token=""
+server4_token=""
+client6_token=""
+server6_token=""
+client4_port=0;
+client6_port=0;
+app4_port=50002
+new4_port=50003
+app6_port=50004
+client_addr_id=${RANDOM:0:2}
+server_addr_id=${RANDOM:0:2}
+
+ns1=""
+ns2=""
+ret=0
+test_name=""
+# a bit more space: because we have more to display
+MPTCP_LIB_TEST_FORMAT="%02u %-68s"
+
+print_title()
+{
+	mptcp_lib_pr_info "${1}"
+}
+
+# $1: test name
+print_test()
+{
+	test_name="${1}"
+
+	mptcp_lib_print_title "${test_name}"
+}
+
+test_pass()
+{
+	mptcp_lib_pr_ok
+	mptcp_lib_result_pass "${test_name}"
+}
+
+test_skip()
+{
+	mptcp_lib_pr_skip
+	mptcp_lib_result_skip "${test_name}"
+}
+
+# $1: msg
+test_fail()
+{
+	if [ ${#} -gt 0 ]
+	then
+		mptcp_lib_pr_fail "${@}"
+	fi
+	ret=${KSFT_FAIL}
+	mptcp_lib_result_fail "${test_name}"
+}
+
+# This function is used in the cleanup trap
+#shellcheck disable=SC2317,SC2329
+cleanup()
+{
+	print_title "Cleanup"
+
+	# Terminate the MPTCP connection and related processes
+	local pid
+	for pid in $client4_pid $server4_pid $client6_pid $server6_pid\
+		   $server_evts_pid $client_evts_pid
+	do
+		mptcp_lib_kill_wait $pid
+	done
+
+	mptcp_lib_ns_exit "${ns1}" "${ns2}"
+
+	rm -rf $file $client_evts $server_evts
+
+	mptcp_lib_pr_info "Done"
+}
+
+trap cleanup EXIT
+
+# Create and configure network namespaces for testing
+print_title "Init"
+mptcp_lib_ns_init ns1 ns2
+
+# check path_manager and pm_type sysctl mapping
+if [ -f /proc/sys/net/mptcp/path_manager ]; then
+	ip netns exec "$ns1" sysctl -q net.mptcp.path_manager=userspace
+	pm_type="$(ip netns exec "$ns1" sysctl -n net.mptcp.pm_type)"
+	if [ "${pm_type}" != "1" ]; then
+		test_fail "unexpected pm_type: ${pm_type}"
+		mptcp_lib_result_print_all_tap
+		exit ${KSFT_FAIL}
+	fi
+
+	ip netns exec "$ns1" sysctl -q net.mptcp.path_manager=error 2>/dev/null
+	pm_type="$(ip netns exec "$ns1" sysctl -n net.mptcp.pm_type)"
+	if [ "${pm_type}" != "1" ]; then
+		test_fail "unexpected pm_type after error: ${pm_type}"
+		mptcp_lib_result_print_all_tap
+		exit ${KSFT_FAIL}
+	fi
+
+	ip netns exec "$ns1" sysctl -q net.mptcp.pm_type=0
+	pm_name="$(ip netns exec "$ns1" sysctl -n net.mptcp.path_manager)"
+	if [ "${pm_name}" != "kernel" ]; then
+		test_fail "unexpected path-manager: ${pm_name}"
+		mptcp_lib_result_print_all_tap
+		exit ${KSFT_FAIL}
+	fi
+fi
+
+for i in "$ns1" "$ns2" ;do
+	ip netns exec "$i" sysctl -q net.mptcp.pm_type=1
+done
+
+#  "$ns1"              ns2
+#     ns1eth2    ns2eth1
+
+ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth1 netns "$ns2"
+
+# Add IPv4/v6 addresses to the namespaces
+ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth2
+ip -net "$ns1" addr add 10.0.2.1/24 dev ns1eth2
+ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth2 nodad
+ip -net "$ns1" addr add dead:beef:2::1/64 dev ns1eth2 nodad
+ip -net "$ns1" link set ns1eth2 up
+
+ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1
+ip -net "$ns2" addr add 10.0.2.2/24 dev ns2eth1
+ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad
+ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth1 nodad
+ip -net "$ns2" link set ns2eth1 up
+
+file=$(mktemp)
+mptcp_lib_make_file "$file" 2 1
+
+# Capture netlink events over the two network namespaces running
+# the MPTCP client and server
+client_evts=$(mktemp)
+mptcp_lib_events "${ns2}" "${client_evts}" client_evts_pid
+server_evts=$(mktemp)
+mptcp_lib_events "${ns1}" "${server_evts}" server_evts_pid
+sleep 0.5
+mptcp_lib_subtests_last_ts_reset
+
+print_test "Created network namespaces ns1, ns2"
+test_pass
+
+make_connection()
+{
+	local is_v6=$1
+	local app_port=$app4_port
+	local connect_addr="10.0.1.1"
+	local client_addr="10.0.1.2"
+	local listen_addr="0.0.0.0"
+	if [ "$is_v6" = "v6" ]
+	then
+		connect_addr="dead:beef:1::1"
+		client_addr="dead:beef:1::2"
+		listen_addr="::"
+		app_port=$app6_port
+	else
+		is_v6="v4"
+	fi
+
+	# set this on the client side only: will not affect the rest
+	ip netns exec "$ns2" sysctl -q net.mptcp.allow_join_initial_addr_port=0
+
+	:>"$client_evts"
+	:>"$server_evts"
+
+	# Run the server
+	ip netns exec "$ns1" \
+	   ./mptcp_connect -s MPTCP -w 300 -p $app_port -l $listen_addr > /dev/null 2>&1 &
+	local server_pid=$!
+
+	mptcp_lib_wait_local_port_listen "${ns1}" "${app_port}"
+
+	# Run the client, transfer $file and stay connected to the server
+	# to conduct tests
+	ip netns exec "$ns2" \
+	   ./mptcp_connect -s MPTCP -w 300 -m sendfile -p $app_port $connect_addr\
+	   2>&1 > /dev/null < "$file" &
+	local client_pid=$!
+	sleep 1
+
+	# Capture client/server attributes from MPTCP connection netlink events
+
+	local client_token
+	local client_port
+	local client_serverside
+	local client_nojoin
+	local server_token
+	local server_serverside
+	local server_nojoin
+
+	client_token=$(mptcp_lib_evts_get_info token "$client_evts")
+	client_port=$(mptcp_lib_evts_get_info sport "$client_evts")
+	client_serverside=$(mptcp_lib_evts_get_info server_side "$client_evts")
+	client_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$client_evts")
+	server_token=$(mptcp_lib_evts_get_info token "$server_evts")
+	server_serverside=$(mptcp_lib_evts_get_info server_side "$server_evts")
+	server_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$server_evts")
+
+	print_test "Established IP${is_v6} MPTCP Connection ns2 => ns1"
+	if [ "${client_token}" != "" ] && [ "${server_token}" != "" ] &&
+	   [ "${client_serverside:-0}" = 0 ] && [ "${server_serverside:-0}" = 1 ] &&
+	   [ "${client_nojoin:-0}" = 0 ] && [ "${server_nojoin:-0}" = 1 ]
+	then
+		test_pass
+		print_title "Connection info: ${client_addr}:${client_port} -> ${connect_addr}:${app_port}"
+	else
+		test_fail "Expected tokens (c:${client_token} - s:${server_token}), server (c:${client_serverside} - s:${server_serverside}), nojoin (c:${client_nojoin} - s:${server_nojoin})"
+		mptcp_lib_result_print_all_tap
+		exit ${KSFT_FAIL}
+	fi
+
+	if [ "$is_v6" = "v6" ]
+	then
+		client6_token=$client_token
+		server6_token=$server_token
+		client6_port=$client_port
+		client6_pid=$client_pid
+		server6_pid=$server_pid
+	else
+		client4_token=$client_token
+		server4_token=$server_token
+		client4_port=$client_port
+		client4_pid=$client_pid
+		server4_pid=$server_pid
+	fi
+}
+
+# $@: all var names to check
+check_expected()
+{
+	if mptcp_lib_check_expected "${@}"
+	then
+		test_pass
+		return 0
+	fi
+
+	test_fail
+	return 1
+}
+
+verify_announce_event()
+{
+	local evt=$1
+	local e_type=$2
+	local e_token=$3
+	local e_addr=$4
+	local e_id=$5
+	local e_dport=$6
+	local e_af=$7
+	local type
+	local token
+	local addr
+	local dport
+	local id
+
+	type=$(mptcp_lib_evts_get_info type "$evt" $e_type)
+	token=$(mptcp_lib_evts_get_info token "$evt" $e_type)
+	if [ "$e_af" = "v6" ]
+	then
+		addr=$(mptcp_lib_evts_get_info daddr6 "$evt" $e_type)
+	else
+		addr=$(mptcp_lib_evts_get_info daddr4 "$evt" $e_type)
+	fi
+	dport=$(mptcp_lib_evts_get_info dport "$evt" $e_type)
+	id=$(mptcp_lib_evts_get_info rem_id "$evt" $e_type)
+
+	check_expected "type" "token" "addr" "dport" "id"
+}
+
+test_announce()
+{
+	print_title "Announce tests"
+
+	# Capture events on the network namespace running the server
+	:>"$server_evts"
+
+	# ADD_ADDR using an invalid token should result in no action
+	local invalid_token=$(( client4_token - 1))
+	ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token $invalid_token id\
+	   $client_addr_id dev ns2eth1 > /dev/null 2>&1
+
+	local type
+	type=$(mptcp_lib_evts_get_info type "$server_evts")
+	print_test "ADD_ADDR 10.0.2.2 (ns2) => ns1, invalid token"
+	if [ "$type" = "" ]
+	then
+		test_pass
+	else
+		test_fail "type defined: ${type}"
+	fi
+
+	# ADD_ADDR from the client to server machine reusing the subflow port
+	:>"$server_evts"
+	ip netns exec "$ns2"\
+	   ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id $client_addr_id dev\
+	   ns2eth1
+	print_test "ADD_ADDR id:client 10.0.2.2 (ns2) => ns1, reuse port"
+	sleep 0.5
+	verify_announce_event $server_evts $ANNOUNCED $server4_token "10.0.2.2" $client_addr_id \
+			      "$client4_port"
+
+	# ADD_ADDR6 from the client to server machine reusing the subflow port
+	:>"$server_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl ann\
+	   dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1
+	print_test "ADD_ADDR6 id:client dead:beef:2::2 (ns2) => ns1, reuse port"
+	sleep 0.5
+	verify_announce_event "$server_evts" "$ANNOUNCED" "$server6_token" "dead:beef:2::2"\
+			      "$client_addr_id" "$client6_port" "v6"
+
+	# ADD_ADDR from the client to server machine using a new port
+	:>"$server_evts"
+	client_addr_id=$((client_addr_id+1))
+	ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\
+	   $client_addr_id dev ns2eth1 port $new4_port
+	print_test "ADD_ADDR id:client+1 10.0.2.2 (ns2) => ns1, new port"
+	sleep 0.5
+	verify_announce_event "$server_evts" "$ANNOUNCED" "$server4_token" "10.0.2.2"\
+			      "$client_addr_id" "$new4_port"
+
+	# Capture events on the network namespace running the client
+	:>"$client_evts"
+
+	# ADD_ADDR from the server to client machine reusing the subflow port
+	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
+	   $server_addr_id dev ns1eth2
+	print_test "ADD_ADDR id:server 10.0.2.1 (ns1) => ns2, reuse port"
+	sleep 0.5
+	verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\
+			      "$server_addr_id" "$app4_port"
+
+	# ADD_ADDR6 from the server to client machine reusing the subflow port
+	:>"$client_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\
+	   $server_addr_id dev ns1eth2
+	print_test "ADD_ADDR6 id:server dead:beef:2::1 (ns1) => ns2, reuse port"
+	sleep 0.5
+	verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "dead:beef:2::1"\
+			      "$server_addr_id" "$app6_port" "v6"
+
+	# ADD_ADDR from the server to client machine using a new port
+	:>"$client_evts"
+	server_addr_id=$((server_addr_id+1))
+	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
+	   $server_addr_id dev ns1eth2 port $new4_port
+	print_test "ADD_ADDR id:server+1 10.0.2.1 (ns1) => ns2, new port"
+	sleep 0.5
+	verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\
+			      "$server_addr_id" "$new4_port"
+}
+
+verify_remove_event()
+{
+	local evt=$1
+	local e_type=$2
+	local e_token=$3
+	local e_id=$4
+	local type
+	local token
+	local id
+
+	type=$(mptcp_lib_evts_get_info type "$evt" $e_type)
+	token=$(mptcp_lib_evts_get_info token "$evt" $e_type)
+	id=$(mptcp_lib_evts_get_info rem_id "$evt" $e_type)
+
+	check_expected "type" "token" "id"
+}
+
+test_remove()
+{
+	print_title "Remove tests"
+
+	# Capture events on the network namespace running the server
+	:>"$server_evts"
+
+	# RM_ADDR using an invalid token should result in no action
+	local invalid_token=$(( client4_token - 1 ))
+	ip netns exec "$ns2" ./pm_nl_ctl rem token $invalid_token id\
+	   $client_addr_id > /dev/null 2>&1
+	print_test "RM_ADDR id:client ns2 => ns1, invalid token"
+	local type
+	type=$(mptcp_lib_evts_get_info type "$server_evts")
+	if [ "$type" = "" ]
+	then
+		test_pass
+	else
+		test_fail "unexpected type: ${type}"
+	fi
+
+	# RM_ADDR using an invalid addr id should result in no action
+	local invalid_id=$(( client_addr_id + 1 ))
+	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
+	   $invalid_id > /dev/null 2>&1
+	print_test "RM_ADDR id:client+1 ns2 => ns1, invalid id"
+	type=$(mptcp_lib_evts_get_info type "$server_evts")
+	if [ "$type" = "" ]
+	then
+		test_pass
+	else
+		test_fail "unexpected type: ${type}"
+	fi
+
+	# RM_ADDR from the client to server machine
+	:>"$server_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
+	   $client_addr_id
+	print_test "RM_ADDR id:client ns2 => ns1"
+	sleep 0.5
+	verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id"
+
+	# RM_ADDR from the client to server machine
+	:>"$server_evts"
+	client_addr_id=$(( client_addr_id - 1 ))
+	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\
+	   $client_addr_id
+	print_test "RM_ADDR id:client-1 ns2 => ns1"
+	sleep 0.5
+	verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id"
+
+	# RM_ADDR6 from the client to server machine
+	:>"$server_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl rem token "$client6_token" id\
+	   $client_addr_id
+	print_test "RM_ADDR6 id:client-1 ns2 => ns1"
+	sleep 0.5
+	verify_remove_event "$server_evts" "$REMOVED" "$server6_token" "$client_addr_id"
+
+	# Capture events on the network namespace running the client
+	:>"$client_evts"
+
+	# RM_ADDR from the server to client machine
+	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\
+	   $server_addr_id
+	print_test "RM_ADDR id:server ns1 => ns2"
+	sleep 0.5
+	verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id"
+
+	# RM_ADDR from the server to client machine
+	:>"$client_evts"
+	server_addr_id=$(( server_addr_id - 1 ))
+	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\
+	   $server_addr_id
+	print_test "RM_ADDR id:server-1 ns1 => ns2"
+	sleep 0.5
+	verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id"
+
+	# RM_ADDR6 from the server to client machine
+	:>"$client_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl rem token "$server6_token" id\
+	   $server_addr_id
+	print_test "RM_ADDR6 id:server-1 ns1 => ns2"
+	sleep 0.5
+	verify_remove_event "$client_evts" "$REMOVED" "$client6_token" "$server_addr_id"
+}
+
+verify_subflow_events()
+{
+	local evt=$1
+	local e_type=$2
+	local e_token=$3
+	local e_family=$4
+	local e_saddr=$5
+	local e_daddr=$6
+	local e_dport=$7
+	local e_locid=$8
+	local e_remid=$9
+	shift 2
+	local e_from=$8
+	local e_to=$9
+	local type
+	local token
+	local family
+	local saddr
+	local daddr
+	local dport
+	local locid
+	local remid
+	local info
+	local e_dport_txt
+
+	# only display the fixed ports
+	if [ "${e_dport}" -ge "${app4_port}" ] && [ "${e_dport}" -le "${app6_port}" ]; then
+		e_dport_txt=":${e_dport}"
+	fi
+
+	info="${e_saddr} (${e_from}) => ${e_daddr}${e_dport_txt} (${e_to})"
+
+	if [ "$e_type" = "$SUB_ESTABLISHED" ]
+	then
+		if [ "$e_family" = "$AF_INET6" ]
+		then
+			print_test "CREATE_SUBFLOW6 ${info}"
+		else
+			print_test "CREATE_SUBFLOW ${info}"
+		fi
+	else
+		if [ "$e_family" = "$AF_INET6" ]
+		then
+			print_test "DESTROY_SUBFLOW6 ${info}"
+		else
+			print_test "DESTROY_SUBFLOW ${info}"
+		fi
+	fi
+
+	type=$(mptcp_lib_evts_get_info type "$evt" $e_type)
+	token=$(mptcp_lib_evts_get_info token "$evt" $e_type)
+	family=$(mptcp_lib_evts_get_info family "$evt" $e_type)
+	dport=$(mptcp_lib_evts_get_info dport "$evt" $e_type)
+	locid=$(mptcp_lib_evts_get_info loc_id "$evt" $e_type)
+	remid=$(mptcp_lib_evts_get_info rem_id "$evt" $e_type)
+	if [ "$family" = "$AF_INET6" ]
+	then
+		saddr=$(mptcp_lib_evts_get_info saddr6 "$evt" $e_type)
+		daddr=$(mptcp_lib_evts_get_info daddr6 "$evt" $e_type)
+	else
+		saddr=$(mptcp_lib_evts_get_info saddr4 "$evt" $e_type)
+		daddr=$(mptcp_lib_evts_get_info daddr4 "$evt" $e_type)
+	fi
+
+	check_expected "type" "token" "daddr" "dport" "family" "saddr" "locid" "remid"
+}
+
+test_subflows()
+{
+	print_title "Subflows v4 or v6 only tests"
+
+	# Capture events on the network namespace running the server
+	:>"$server_evts"
+
+	# Attempt to add a listener at 10.0.2.2:<subflow-port>
+	ip netns exec "$ns2" ./pm_nl_ctl listen 10.0.2.2\
+	   "$client4_port" &
+	local listener_pid=$!
+
+	# ADD_ADDR from client to server machine reusing the subflow port
+	ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\
+	   $client_addr_id
+	sleep 0.5
+
+	# CREATE_SUBFLOW from server to client machine
+	:>"$server_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2\
+	   rport "$client4_port" token "$server4_token"
+	sleep 0.5
+	verify_subflow_events $server_evts $SUB_ESTABLISHED $server4_token $AF_INET "10.0.2.1" \
+			      "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2"
+
+	# Delete the listener from the client ns, if one was created
+	mptcp_lib_kill_wait $listener_pid
+
+	local sport
+	sport=$(mptcp_lib_evts_get_info sport "$server_evts" $SUB_ESTABLISHED)
+
+	# DESTROY_SUBFLOW from server to client machine
+	:>"$server_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl dsf lip 10.0.2.1 lport "$sport" rip 10.0.2.2 rport\
+	   "$client4_port" token "$server4_token"
+	sleep 0.5
+	verify_subflow_events "$server_evts" "$SUB_CLOSED" "$server4_token" "$AF_INET" "10.0.2.1"\
+			      "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2"
+
+	# RM_ADDR from client to server machine
+	ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\
+	   "$client4_token"
+	sleep 0.5
+
+	# Attempt to add a listener at dead:beef:2::2:<subflow-port>
+	ip netns exec "$ns2" ./pm_nl_ctl listen dead:beef:2::2\
+	   "$client6_port" &
+	listener_pid=$!
+
+	# ADD_ADDR6 from client to server machine reusing the subflow port
+	:>"$server_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl ann dead:beef:2::2 token "$client6_token" id\
+	   $client_addr_id
+	sleep 0.5
+
+	# CREATE_SUBFLOW6 from server to client machine
+	:>"$server_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl csf lip dead:beef:2::1 lid 23 rip\
+	   dead:beef:2::2 rport "$client6_port" token "$server6_token"
+	sleep 0.5
+	verify_subflow_events "$server_evts" "$SUB_ESTABLISHED" "$server6_token" "$AF_INET6"\
+			      "dead:beef:2::1" "dead:beef:2::2" "$client6_port" "23"\
+			      "$client_addr_id" "ns1" "ns2"
+
+	# Delete the listener from the client ns, if one was created
+	mptcp_lib_kill_wait $listener_pid
+
+	sport=$(mptcp_lib_evts_get_info sport "$server_evts" $SUB_ESTABLISHED)
+
+	# DESTROY_SUBFLOW6 from server to client machine
+	:>"$server_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl dsf lip dead:beef:2::1 lport "$sport" rip\
+	   dead:beef:2::2 rport "$client6_port" token "$server6_token"
+	sleep 0.5
+	verify_subflow_events "$server_evts" "$SUB_CLOSED" "$server6_token" "$AF_INET6"\
+			      "dead:beef:2::1" "dead:beef:2::2" "$client6_port" "23"\
+			      "$client_addr_id" "ns1" "ns2"
+
+	# RM_ADDR from client to server machine
+	ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\
+	   "$client6_token"
+	sleep 0.5
+
+	# Attempt to add a listener at 10.0.2.2:<new-port>
+	ip netns exec "$ns2" ./pm_nl_ctl listen 10.0.2.2\
+	   $new4_port &
+	listener_pid=$!
+
+	# ADD_ADDR from client to server machine using a new port
+	:>"$server_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\
+	   $client_addr_id port $new4_port
+	sleep 0.5
+
+	# CREATE_SUBFLOW from server to client machine
+	:>"$server_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2 rport\
+	   $new4_port token "$server4_token"
+	sleep 0.5
+	verify_subflow_events "$server_evts" "$SUB_ESTABLISHED" "$server4_token" "$AF_INET"\
+			      "10.0.2.1" "10.0.2.2" "$new4_port" "23"\
+			      "$client_addr_id" "ns1" "ns2"
+
+	# Delete the listener from the client ns, if one was created
+	mptcp_lib_kill_wait $listener_pid
+
+	sport=$(mptcp_lib_evts_get_info sport "$server_evts" $SUB_ESTABLISHED)
+
+	# DESTROY_SUBFLOW from server to client machine
+	:>"$server_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl dsf lip 10.0.2.1 lport "$sport" rip 10.0.2.2 rport\
+	   $new4_port token "$server4_token"
+	sleep 0.5
+	verify_subflow_events "$server_evts" "$SUB_CLOSED" "$server4_token" "$AF_INET" "10.0.2.1"\
+			      "10.0.2.2" "$new4_port" "23" "$client_addr_id" "ns1" "ns2"
+
+	# RM_ADDR from client to server machine
+	ip netns exec "$ns2" ./pm_nl_ctl rem id $client_addr_id token\
+	   "$client4_token"
+
+	# Capture events on the network namespace running the client
+	:>"$client_evts"
+
+	# Attempt to add a listener at 10.0.2.1:<subflow-port>
+	ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\
+	   $app4_port &
+	listener_pid=$!
+
+	# ADD_ADDR from server to client machine reusing the subflow port
+	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
+	   $server_addr_id
+	sleep 0.5
+
+	# CREATE_SUBFLOW from client to server machine
+	:>"$client_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\
+	   $app4_port token "$client4_token"
+	sleep 0.5
+	verify_subflow_events $client_evts $SUB_ESTABLISHED $client4_token $AF_INET "10.0.2.2"\
+			      "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1"
+
+	# Delete the listener from the server ns, if one was created
+	mptcp_lib_kill_wait $listener_pid
+
+	sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED)
+
+	# DESTROY_SUBFLOW from client to server machine
+	:>"$client_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\
+	   $app4_port token "$client4_token"
+	sleep 0.5
+	verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client4_token" "$AF_INET" "10.0.2.2"\
+			      "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1"
+
+	# RM_ADDR from server to client machine
+	ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
+	   "$server4_token"
+	sleep 0.5
+
+	# Attempt to add a listener at dead:beef:2::1:<subflow-port>
+	ip netns exec "$ns1" ./pm_nl_ctl listen dead:beef:2::1\
+	   $app6_port &
+	listener_pid=$!
+
+	# ADD_ADDR6 from server to client machine reusing the subflow port
+	:>"$client_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\
+	   $server_addr_id
+	sleep 0.5
+
+	# CREATE_SUBFLOW6 from client to server machine
+	:>"$client_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl csf lip dead:beef:2::2 lid 23 rip\
+	   dead:beef:2::1 rport $app6_port token "$client6_token"
+	sleep 0.5
+	verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\
+			      "$AF_INET6" "dead:beef:2::2"\
+			      "dead:beef:2::1" "$app6_port" "23"\
+			      "$server_addr_id" "ns2" "ns1"
+
+	# Delete the listener from the server ns, if one was created
+	mptcp_lib_kill_wait $listener_pid
+
+	sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED)
+
+	# DESTROY_SUBFLOW6 from client to server machine
+	:>"$client_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl dsf lip dead:beef:2::2 lport "$sport" rip\
+	   dead:beef:2::1 rport $app6_port token "$client6_token"
+	sleep 0.5
+	verify_subflow_events $client_evts $SUB_CLOSED $client6_token $AF_INET6 "dead:beef:2::2"\
+			      "dead:beef:2::1" "$app6_port" "23" "$server_addr_id" "ns2" "ns1"
+
+	# RM_ADDR6 from server to client machine
+	ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
+	   "$server6_token"
+	sleep 0.5
+
+	# Attempt to add a listener at 10.0.2.1:<new-port>
+	ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\
+	   $new4_port &
+	listener_pid=$!
+
+	# ADD_ADDR from server to client machine using a new port
+	:>"$client_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\
+	   $server_addr_id port $new4_port
+	sleep 0.5
+
+	# CREATE_SUBFLOW from client to server machine
+	:>"$client_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\
+	   $new4_port token "$client4_token"
+	sleep 0.5
+	verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client4_token" "$AF_INET"\
+			      "10.0.2.2" "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1"
+
+	# Delete the listener from the server ns, if one was created
+	mptcp_lib_kill_wait $listener_pid
+
+	sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED)
+
+	# DESTROY_SUBFLOW from client to server machine
+	:>"$client_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\
+	   $new4_port token "$client4_token"
+	sleep 0.5
+	verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client4_token" "$AF_INET" "10.0.2.2"\
+			      "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1"
+
+	# RM_ADDR from server to client machine
+	ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
+	   "$server4_token"
+}
+
+test_subflows_v4_v6_mix()
+{
+	print_title "Subflows v4 and v6 mix tests"
+
+	# Attempt to add a listener at 10.0.2.1:<subflow-port>
+	ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\
+	   $app6_port &
+	local listener_pid=$!
+
+	# ADD_ADDR4 from server to client machine reusing the subflow port on
+	# the established v6 connection
+	:>"$client_evts"
+	ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\
+	   $server_addr_id dev ns1eth2
+	print_test "ADD_ADDR4 id:server 10.0.2.1 (ns1) => ns2, reuse port"
+	sleep 0.5
+	verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\
+			      "$server_addr_id" "$app6_port"
+
+	# CREATE_SUBFLOW from client to server machine
+	:>"$client_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\
+	   $app6_port token "$client6_token"
+	sleep 0.5
+	verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\
+			      "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\
+			      "$server_addr_id" "ns2" "ns1"
+
+	# Delete the listener from the server ns, if one was created
+	mptcp_lib_kill_wait $listener_pid
+
+	sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED)
+
+	# DESTROY_SUBFLOW from client to server machine
+	:>"$client_evts"
+	ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\
+	   $app6_port token "$client6_token"
+	sleep 0.5
+	verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client6_token" \
+			      "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\
+			      "$server_addr_id" "ns2" "ns1"
+
+	# RM_ADDR from server to client machine
+	ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
+	   "$server6_token"
+	sleep 0.5
+}
+
+test_prio()
+{
+	print_title "Prio tests"
+
+	local count
+
+	# Send MP_PRIO signal from client to server machine
+	ip netns exec "$ns2" ./pm_nl_ctl set 10.0.1.2 port "$client4_port" flags backup token "$client4_token" rip 10.0.1.1 rport "$app4_port"
+	sleep 0.5
+
+	# Check TX
+	print_test "MP_PRIO TX"
+	count=$(mptcp_lib_get_counter "$ns2" "MPTcpExtMPPrioTx")
+	if [ -z "$count" ]; then
+		test_skip
+	elif [ $count != 1 ]; then
+		test_fail "Count != 1: ${count}"
+	else
+		test_pass
+	fi
+
+	# Check RX
+	print_test "MP_PRIO RX"
+	count=$(mptcp_lib_get_counter "$ns1" "MPTcpExtMPPrioRx")
+	if [ -z "$count" ]; then
+		test_skip
+	elif [ $count != 1 ]; then
+		test_fail "Count != 1: ${count}"
+	else
+		test_pass
+	fi
+}
+
+verify_listener_events()
+{
+	if mptcp_lib_verify_listener_events "${@}"; then
+		test_pass
+	else
+		test_fail
+	fi
+}
+
+test_listener()
+{
+	print_title "Listener tests"
+
+	if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then
+		print_test "LISTENER events"
+		test_skip
+		return
+	fi
+
+	# Capture events on the network namespace running the client
+	:>$client_evts
+
+	# Attempt to add a listener at 10.0.2.2:<subflow-port>
+	ip netns exec $ns2 ./pm_nl_ctl listen 10.0.2.2\
+		$client4_port &
+	local listener_pid=$!
+
+	sleep 0.5
+	print_test "CREATE_LISTENER 10.0.2.2 (client port)"
+	verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port
+
+	# ADD_ADDR from client to server machine reusing the subflow port
+	ip netns exec $ns2 ./pm_nl_ctl ann 10.0.2.2 token $client4_token id\
+		$client_addr_id
+	sleep 0.5
+
+	# CREATE_SUBFLOW from server to client machine
+	ip netns exec $ns1 ./pm_nl_ctl csf lip 10.0.2.1 lid 23 rip 10.0.2.2\
+		rport $client4_port token $server4_token
+	sleep 0.5
+
+	# Delete the listener from the client ns, if one was created
+	mptcp_lib_kill_wait $listener_pid
+
+	sleep 0.5
+	print_test "CLOSE_LISTENER 10.0.2.2 (client port)"
+	verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port
+}
+
+print_title "Make connections"
+make_connection
+make_connection "v6"
+print_title "Will be using address IDs ${client_addr_id} (client) and ${server_addr_id} (server)"
+
+test_announce
+test_remove
+test_subflows
+test_subflows_v4_v6_mix
+test_prio
+test_listener
+
+mptcp_lib_result_print_all_tap
+exit ${ret}