Adding upstream version 5.10.209.upstream/5.10.209

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

12 files changed, 3547 insertions, 0 deletions

diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
new file mode 100644
index 000000000..260336d5f
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+mptcp_connect
+pm_nl_ctl
+*.pcap
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
new file mode 100644
index 000000000..7072ef1c0
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+
+top_srcdir = ../../../../..
+KSFT_KHDR_INSTALL := 1
+
+CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g  -I$(top_srcdir)/usr/include
+
+TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
+	      simult_flows.sh
+
+TEST_GEN_FILES = mptcp_connect pm_nl_ctl
+
+TEST_FILES := mptcp_lib.sh settings
+
+EXTRA_CLEAN := *.pcap
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
new file mode 100644
index 000000000..8867c4025
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/config
@@ -0,0 +1,9 @@
+CONFIG_KALLSYMS=y
+CONFIG_MPTCP=y
+CONFIG_IPV6=y
+CONFIG_MPTCP_IPV6=y
+CONFIG_INET_DIAG=m
+CONFIG_INET_MPTCP_DIAG=m
+CONFIG_VETH=y
+CONFIG_NET_SCH_NETEM=m
+CONFIG_SYN_COOKIES=y
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
new file mode 100755
index 000000000..34577d469
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -0,0 +1,125 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+ns="ns1-$rndh"
+ksft_skip=4
+test_cnt=1
+ret=0
+pids=()
+
+flush_pids()
+{
+	# mptcp_connect in join mode will sleep a bit before completing,
+	# give it some time
+	sleep 1.1
+
+	for pid in ${pids[@]}; do
+		[ -d /proc/$pid ] && kill -SIGUSR1 $pid >/dev/null 2>&1
+	done
+	pids=()
+}
+
+cleanup()
+{
+	ip netns del $ns
+	for pid in ${pids[@]}; do
+		[ -d /proc/$pid ] && kill -9 $pid >/dev/null 2>&1
+	done
+}
+
+mptcp_lib_check_mptcp
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+ss -h | grep -q MPTCP
+if [ $? -ne 0 ];then
+	echo "SKIP: ss tool does not support MPTCP"
+	exit $ksft_skip
+fi
+
+__chk_nr()
+{
+	local condition="$1"
+	local expected=$2
+	local msg nr
+
+	shift 2
+	msg=$*
+	nr=$(ss -inmHMN $ns | $condition)
+
+	printf "%-50s" "$msg"
+	if [ $nr != $expected ]; then
+		echo "[ fail ] expected $expected found $nr"
+		ret=$test_cnt
+	else
+		echo "[  ok  ]"
+	fi
+	test_cnt=$((test_cnt+1))
+}
+
+chk_msk_nr()
+{
+	__chk_nr "grep -c token:" $*
+}
+
+chk_msk_fallback_nr()
+{
+		__chk_nr "grep -c fallback" $*
+}
+
+chk_msk_remote_key_nr()
+{
+		__chk_nr "grep -c remote_key" $*
+}
+
+
+trap cleanup EXIT
+ip netns add $ns
+ip -n $ns link set dev lo up
+
+echo "a" | ip netns exec $ns ./mptcp_connect -p 10000 -l 0.0.0.0 -t 100 >/dev/null &
+sleep 0.1
+pids[0]=$!
+chk_msk_nr 0 "no msk on netns creation"
+
+echo "b" | ip netns exec $ns ./mptcp_connect -p 10000 127.0.0.1 -j -t 100 >/dev/null &
+sleep 0.1
+pids[1]=$!
+chk_msk_nr 2 "after MPC handshake "
+chk_msk_remote_key_nr 2 "....chk remote_key"
+chk_msk_fallback_nr 0 "....chk no fallback"
+flush_pids
+
+
+echo "a" | ip netns exec $ns ./mptcp_connect -p 10001 -s TCP -l 0.0.0.0 -t 100 >/dev/null &
+pids[0]=$!
+sleep 0.1
+echo "b" | ip netns exec $ns ./mptcp_connect -p 10001 127.0.0.1 -j -t 100 >/dev/null &
+pids[1]=$!
+sleep 0.1
+chk_msk_fallback_nr 1 "check fallback"
+flush_pids
+
+NR_CLIENTS=100
+for I in `seq 1 $NR_CLIENTS`; do
+	echo "a" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) -l 0.0.0.0 -t 100 -w 10 >/dev/null  &
+	pids[$((I*2))]=$!
+done
+sleep 0.1
+
+for I in `seq 1 $NR_CLIENTS`; do
+	echo "b" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) 127.0.0.1 -t 100 -w 10 >/dev/null &
+	pids[$((I*2 + 1))]=$!
+done
+sleep 1.5
+
+chk_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
+flush_pids
+
+exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
new file mode 100644
index 000000000..37c1ec888
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -0,0 +1,912 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <string.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <strings.h>
+#include <signal.h>
+#include <unistd.h>
+
+#include <sys/poll.h>
+#include <sys/random.h>
+#include <sys/sendfile.h>
+#include <sys/stat.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+
+#include <netdb.h>
+#include <netinet/in.h>
+
+#include <linux/tcp.h>
+
+extern int optind;
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+#ifndef TCP_ULP
+#define TCP_ULP 31
+#endif
+
+static int  poll_timeout = 10 * 1000;
+static bool listen_mode;
+static bool quit;
+
+enum cfg_mode {
+	CFG_MODE_POLL,
+	CFG_MODE_MMAP,
+	CFG_MODE_SENDFILE,
+};
+
+static enum cfg_mode cfg_mode = CFG_MODE_POLL;
+static const char *cfg_host;
+static const char *cfg_port	= "12000";
+static int cfg_sock_proto	= IPPROTO_MPTCP;
+static bool tcpulp_audit;
+static int pf = AF_INET;
+static int cfg_sndbuf;
+static int cfg_rcvbuf;
+static bool cfg_join;
+static bool cfg_remove;
+static int cfg_wait;
+
+static void die_usage(void)
+{
+	fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]"
+		"[-l] [-w sec] connect_address\n");
+	fprintf(stderr, "\t-6 use ipv6\n");
+	fprintf(stderr, "\t-t num -- set poll timeout to num\n");
+	fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n");
+	fprintf(stderr, "\t-R num -- set SO_RCVBUF to num\n");
+	fprintf(stderr, "\t-p num -- use port num\n");
+	fprintf(stderr, "\t-s [MPTCP|TCP] -- use mptcp(default) or tcp sockets\n");
+	fprintf(stderr, "\t-m [poll|mmap|sendfile] -- use poll(default)/mmap+write/sendfile\n");
+	fprintf(stderr, "\t-u -- check mptcp ulp\n");
+	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
+	exit(1);
+}
+
+static void handle_signal(int nr)
+{
+	quit = true;
+}
+
+static const char *getxinfo_strerr(int err)
+{
+	if (err == EAI_SYSTEM)
+		return strerror(errno);
+
+	return gai_strerror(err);
+}
+
+static void xgetnameinfo(const struct sockaddr *addr, socklen_t addrlen,
+			 char *host, socklen_t hostlen,
+			 char *serv, socklen_t servlen)
+{
+	int flags = NI_NUMERICHOST | NI_NUMERICSERV;
+	int err = getnameinfo(addr, addrlen, host, hostlen, serv, servlen,
+			      flags);
+
+	if (err) {
+		const char *errstr = getxinfo_strerr(err);
+
+		fprintf(stderr, "Fatal: getnameinfo: %s\n", errstr);
+		exit(1);
+	}
+}
+
+static void xgetaddrinfo(const char *node, const char *service,
+			 const struct addrinfo *hints,
+			 struct addrinfo **res)
+{
+	int err = getaddrinfo(node, service, hints, res);
+
+	if (err) {
+		const char *errstr = getxinfo_strerr(err);
+
+		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
+			node ? node : "", service ? service : "", errstr);
+		exit(1);
+	}
+}
+
+static void set_rcvbuf(int fd, unsigned int size)
+{
+	int err;
+
+	err = setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &size, sizeof(size));
+	if (err) {
+		perror("set SO_RCVBUF");
+		exit(1);
+	}
+}
+
+static void set_sndbuf(int fd, unsigned int size)
+{
+	int err;
+
+	err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &size, sizeof(size));
+	if (err) {
+		perror("set SO_SNDBUF");
+		exit(1);
+	}
+}
+
+static int sock_listen_mptcp(const char * const listenaddr,
+			     const char * const port)
+{
+	int sock;
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_TCP,
+		.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, cfg_sock_proto);
+		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) {
+		fprintf(stderr, "Could not create listen socket\n");
+		return sock;
+	}
+
+	if (listen(sock, 20)) {
+		perror("listen");
+		close(sock);
+		return -1;
+	}
+
+	return sock;
+}
+
+static bool sock_test_tcpulp(const char * const remoteaddr,
+			     const char * const port)
+{
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_TCP,
+		.ai_socktype = SOCK_STREAM,
+	};
+	struct addrinfo *a, *addr;
+	int sock = -1, ret = 0;
+	bool test_pass = false;
+
+	hints.ai_family = AF_INET;
+
+	xgetaddrinfo(remoteaddr, port, &hints, &addr);
+	for (a = addr; a; a = a->ai_next) {
+		sock = socket(a->ai_family, a->ai_socktype, IPPROTO_TCP);
+		if (sock < 0) {
+			perror("socket");
+			continue;
+		}
+		ret = setsockopt(sock, IPPROTO_TCP, TCP_ULP, "mptcp",
+				 sizeof("mptcp"));
+		if (ret == -1 && errno == EOPNOTSUPP)
+			test_pass = true;
+		close(sock);
+
+		if (test_pass)
+			break;
+		if (!ret)
+			fprintf(stderr,
+				"setsockopt(TCP_ULP) returned 0\n");
+		else
+			perror("setsockopt(TCP_ULP)");
+	}
+	return test_pass;
+}
+
+static int sock_connect_mptcp(const char * const remoteaddr,
+			      const char * const port, int proto)
+{
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_TCP,
+		.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) {
+			perror("socket");
+			continue;
+		}
+
+		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
+			break; /* success */
+
+		perror("connect()");
+		close(sock);
+		sock = -1;
+	}
+
+	freeaddrinfo(addr);
+	return sock;
+}
+
+static size_t do_rnd_write(const int fd, char *buf, const size_t len)
+{
+	static bool first = true;
+	unsigned int do_w;
+	ssize_t bw;
+
+	do_w = rand() & 0xffff;
+	if (do_w == 0 || do_w > len)
+		do_w = len;
+
+	if (cfg_join && first && do_w > 100)
+		do_w = 100;
+
+	if (cfg_remove && do_w > 50)
+		do_w = 50;
+
+	bw = write(fd, buf, do_w);
+	if (bw < 0)
+		perror("write");
+
+	/* let the join handshake complete, before going on */
+	if (cfg_join && first) {
+		usleep(200000);
+		first = false;
+	}
+
+	if (cfg_remove)
+		usleep(200000);
+
+	return bw;
+}
+
+static size_t do_write(const int fd, char *buf, const size_t len)
+{
+	size_t offset = 0;
+
+	while (offset < len) {
+		size_t written;
+		ssize_t bw;
+
+		bw = write(fd, buf + offset, len - offset);
+		if (bw < 0) {
+			perror("write");
+			return 0;
+		}
+
+		written = (size_t)bw;
+		offset += written;
+	}
+
+	return offset;
+}
+
+static ssize_t do_rnd_read(const int fd, char *buf, const size_t len)
+{
+	size_t cap = rand();
+
+	cap &= 0xffff;
+
+	if (cap == 0)
+		cap = 1;
+	else if (cap > len)
+		cap = len;
+
+	return read(fd, buf, cap);
+}
+
+static void set_nonblock(int fd)
+{
+	int flags = fcntl(fd, F_GETFL);
+
+	if (flags == -1)
+		return;
+
+	fcntl(fd, F_SETFL, flags | O_NONBLOCK);
+}
+
+static int copyfd_io_poll(int infd, int peerfd, int outfd)
+{
+	struct pollfd fds = {
+		.fd = peerfd,
+		.events = POLLIN | POLLOUT,
+	};
+	unsigned int woff = 0, wlen = 0;
+	char wbuf[8192];
+
+	set_nonblock(peerfd);
+
+	for (;;) {
+		char rbuf[8192];
+		ssize_t len;
+
+		if (fds.events == 0)
+			break;
+
+		switch (poll(&fds, 1, poll_timeout)) {
+		case -1:
+			if (errno == EINTR)
+				continue;
+			perror("poll");
+			return 1;
+		case 0:
+			fprintf(stderr, "%s: poll timed out (events: "
+				"POLLIN %u, POLLOUT %u)\n", __func__,
+				fds.events & POLLIN, fds.events & POLLOUT);
+			return 2;
+		}
+
+		if (fds.revents & POLLIN) {
+			len = do_rnd_read(peerfd, rbuf, sizeof(rbuf));
+			if (len == 0) {
+				/* no more data to receive:
+				 * peer has closed its write side
+				 */
+				fds.events &= ~POLLIN;
+
+				if ((fds.events & POLLOUT) == 0)
+					/* and nothing more to send */
+					break;
+
+			/* Else, still have data to transmit */
+			} else if (len < 0) {
+				perror("read");
+				return 3;
+			}
+
+			do_write(outfd, rbuf, len);
+		}
+
+		if (fds.revents & POLLOUT) {
+			if (wlen == 0) {
+				woff = 0;
+				wlen = read(infd, wbuf, sizeof(wbuf));
+			}
+
+			if (wlen > 0) {
+				ssize_t bw;
+
+				bw = do_rnd_write(peerfd, wbuf + woff, wlen);
+				if (bw < 0)
+					return 111;
+
+				woff += bw;
+				wlen -= bw;
+			} else if (wlen == 0) {
+				/* We have no more data to send. */
+				fds.events &= ~POLLOUT;
+
+				if ((fds.events & POLLIN) == 0)
+					/* ... and peer also closed already */
+					break;
+
+				/* ... but we still receive.
+				 * Close our write side, ev. give some time
+				 * for address notification and/or checking
+				 * the current status
+				 */
+				if (cfg_wait)
+					usleep(cfg_wait);
+				shutdown(peerfd, SHUT_WR);
+			} else {
+				if (errno == EINTR)
+					continue;
+				perror("read");
+				return 4;
+			}
+		}
+
+		if (fds.revents & (POLLERR | POLLNVAL)) {
+			fprintf(stderr, "Unexpected revents: "
+				"POLLERR/POLLNVAL(%x)\n", fds.revents);
+			return 5;
+		}
+	}
+
+	/* leave some time for late join/announce */
+	if (cfg_join || cfg_remove)
+		usleep(cfg_wait);
+
+	close(peerfd);
+	return 0;
+}
+
+static int do_recvfile(int infd, int outfd)
+{
+	ssize_t r;
+
+	do {
+		char buf[16384];
+
+		r = do_rnd_read(infd, buf, sizeof(buf));
+		if (r > 0) {
+			if (write(outfd, buf, r) != r)
+				break;
+		} else if (r < 0) {
+			perror("read");
+		}
+	} while (r > 0);
+
+	return (int)r;
+}
+
+static int do_mmap(int infd, int outfd, unsigned int size)
+{
+	char *inbuf = mmap(NULL, size, PROT_READ, MAP_SHARED, infd, 0);
+	ssize_t ret = 0, off = 0;
+	size_t rem;
+
+	if (inbuf == MAP_FAILED) {
+		perror("mmap");
+		return 1;
+	}
+
+	rem = size;
+
+	while (rem > 0) {
+		ret = write(outfd, inbuf + off, rem);
+
+		if (ret < 0) {
+			perror("write");
+			break;
+		}
+
+		off += ret;
+		rem -= ret;
+	}
+
+	munmap(inbuf, size);
+	return rem;
+}
+
+static int get_infd_size(int fd)
+{
+	struct stat sb;
+	ssize_t count;
+	int err;
+
+	err = fstat(fd, &sb);
+	if (err < 0) {
+		perror("fstat");
+		return -1;
+	}
+
+	if ((sb.st_mode & S_IFMT) != S_IFREG) {
+		fprintf(stderr, "%s: stdin is not a regular file\n", __func__);
+		return -2;
+	}
+
+	count = sb.st_size;
+	if (count > INT_MAX) {
+		fprintf(stderr, "File too large: %zu\n", count);
+		return -3;
+	}
+
+	return (int)count;
+}
+
+static int do_sendfile(int infd, int outfd, unsigned int count)
+{
+	while (count > 0) {
+		ssize_t r;
+
+		r = sendfile(outfd, infd, NULL, count);
+		if (r < 0) {
+			perror("sendfile");
+			return 3;
+		}
+
+		count -= r;
+	}
+
+	return 0;
+}
+
+static int copyfd_io_mmap(int infd, int peerfd, int outfd,
+			  unsigned int size)
+{
+	int err;
+
+	if (listen_mode) {
+		err = do_recvfile(peerfd, outfd);
+		if (err)
+			return err;
+
+		err = do_mmap(infd, peerfd, size);
+	} else {
+		err = do_mmap(infd, peerfd, size);
+		if (err)
+			return err;
+
+		shutdown(peerfd, SHUT_WR);
+
+		err = do_recvfile(peerfd, outfd);
+	}
+
+	return err;
+}
+
+static int copyfd_io_sendfile(int infd, int peerfd, int outfd,
+			      unsigned int size)
+{
+	int err;
+
+	if (listen_mode) {
+		err = do_recvfile(peerfd, outfd);
+		if (err)
+			return err;
+
+		err = do_sendfile(infd, peerfd, size);
+	} else {
+		err = do_sendfile(infd, peerfd, size);
+		if (err)
+			return err;
+		err = do_recvfile(peerfd, outfd);
+	}
+
+	return err;
+}
+
+static int copyfd_io(int infd, int peerfd, int outfd)
+{
+	int file_size;
+
+	switch (cfg_mode) {
+	case CFG_MODE_POLL:
+		return copyfd_io_poll(infd, peerfd, outfd);
+	case CFG_MODE_MMAP:
+		file_size = get_infd_size(infd);
+		if (file_size < 0)
+			return file_size;
+		return copyfd_io_mmap(infd, peerfd, outfd, file_size);
+	case CFG_MODE_SENDFILE:
+		file_size = get_infd_size(infd);
+		if (file_size < 0)
+			return file_size;
+		return copyfd_io_sendfile(infd, peerfd, outfd, file_size);
+	}
+
+	fprintf(stderr, "Invalid mode %d\n", cfg_mode);
+
+	die_usage();
+	return 1;
+}
+
+static void check_sockaddr(int pf, struct sockaddr_storage *ss,
+			   socklen_t salen)
+{
+	struct sockaddr_in6 *sin6;
+	struct sockaddr_in *sin;
+	socklen_t wanted_size = 0;
+
+	switch (pf) {
+	case AF_INET:
+		wanted_size = sizeof(*sin);
+		sin = (void *)ss;
+		if (!sin->sin_port)
+			fprintf(stderr, "accept: something wrong: ip connection from port 0");
+		break;
+	case AF_INET6:
+		wanted_size = sizeof(*sin6);
+		sin6 = (void *)ss;
+		if (!sin6->sin6_port)
+			fprintf(stderr, "accept: something wrong: ipv6 connection from port 0");
+		break;
+	default:
+		fprintf(stderr, "accept: Unknown pf %d, salen %u\n", pf, salen);
+		return;
+	}
+
+	if (salen != wanted_size)
+		fprintf(stderr, "accept: size mismatch, got %d expected %d\n",
+			(int)salen, wanted_size);
+
+	if (ss->ss_family != pf)
+		fprintf(stderr, "accept: pf mismatch, expect %d, ss_family is %d\n",
+			(int)ss->ss_family, pf);
+}
+
+static void check_getpeername(int fd, struct sockaddr_storage *ss, socklen_t salen)
+{
+	struct sockaddr_storage peerss;
+	socklen_t peersalen = sizeof(peerss);
+
+	if (getpeername(fd, (struct sockaddr *)&peerss, &peersalen) < 0) {
+		perror("getpeername");
+		return;
+	}
+
+	if (peersalen != salen) {
+		fprintf(stderr, "%s: %d vs %d\n", __func__, peersalen, salen);
+		return;
+	}
+
+	if (memcmp(ss, &peerss, peersalen)) {
+		char a[INET6_ADDRSTRLEN];
+		char b[INET6_ADDRSTRLEN];
+		char c[INET6_ADDRSTRLEN];
+		char d[INET6_ADDRSTRLEN];
+
+		xgetnameinfo((struct sockaddr *)ss, salen,
+			     a, sizeof(a), b, sizeof(b));
+
+		xgetnameinfo((struct sockaddr *)&peerss, peersalen,
+			     c, sizeof(c), d, sizeof(d));
+
+		fprintf(stderr, "%s: memcmp failure: accept %s vs peername %s, %s vs %s salen %d vs %d\n",
+			__func__, a, c, b, d, peersalen, salen);
+	}
+}
+
+static void check_getpeername_connect(int fd)
+{
+	struct sockaddr_storage ss;
+	socklen_t salen = sizeof(ss);
+	char a[INET6_ADDRSTRLEN];
+	char b[INET6_ADDRSTRLEN];
+
+	if (getpeername(fd, (struct sockaddr *)&ss, &salen) < 0) {
+		perror("getpeername");
+		return;
+	}
+
+	xgetnameinfo((struct sockaddr *)&ss, salen,
+		     a, sizeof(a), b, sizeof(b));
+
+	if (strcmp(cfg_host, a) || strcmp(cfg_port, b))
+		fprintf(stderr, "%s: %s vs %s, %s vs %s\n", __func__,
+			cfg_host, a, cfg_port, b);
+}
+
+static void maybe_close(int fd)
+{
+	unsigned int r = rand();
+
+	if (!(cfg_join || cfg_remove) && (r & 1))
+		close(fd);
+}
+
+int main_loop_s(int listensock)
+{
+	struct sockaddr_storage ss;
+	struct pollfd polls;
+	socklen_t salen;
+	int remotesock;
+
+	polls.fd = listensock;
+	polls.events = POLLIN;
+
+	switch (poll(&polls, 1, poll_timeout)) {
+	case -1:
+		perror("poll");
+		return 1;
+	case 0:
+		fprintf(stderr, "%s: timed out\n", __func__);
+		close(listensock);
+		return 2;
+	}
+
+	salen = sizeof(ss);
+	remotesock = accept(listensock, (struct sockaddr *)&ss, &salen);
+	if (remotesock >= 0) {
+		maybe_close(listensock);
+		check_sockaddr(pf, &ss, salen);
+		check_getpeername(remotesock, &ss, salen);
+
+		return copyfd_io(0, remotesock, 1);
+	}
+
+	perror("accept");
+
+	return 1;
+}
+
+static void init_rng(void)
+{
+	unsigned int foo;
+
+	if (getrandom(&foo, sizeof(foo), 0) == -1) {
+		perror("getrandom");
+		exit(1);
+	}
+
+	srand(foo);
+}
+
+int main_loop(void)
+{
+	int fd;
+
+	/* listener is ready. */
+	fd = sock_connect_mptcp(cfg_host, cfg_port, cfg_sock_proto);
+	if (fd < 0)
+		return 2;
+
+	check_getpeername_connect(fd);
+
+	if (cfg_rcvbuf)
+		set_rcvbuf(fd, cfg_rcvbuf);
+	if (cfg_sndbuf)
+		set_sndbuf(fd, cfg_sndbuf);
+
+	return copyfd_io(0, fd, 1);
+}
+
+int parse_proto(const char *proto)
+{
+	if (!strcasecmp(proto, "MPTCP"))
+		return IPPROTO_MPTCP;
+	if (!strcasecmp(proto, "TCP"))
+		return IPPROTO_TCP;
+
+	fprintf(stderr, "Unknown protocol: %s\n.", proto);
+	die_usage();
+
+	/* silence compiler warning */
+	return 0;
+}
+
+int parse_mode(const char *mode)
+{
+	if (!strcasecmp(mode, "poll"))
+		return CFG_MODE_POLL;
+	if (!strcasecmp(mode, "mmap"))
+		return CFG_MODE_MMAP;
+	if (!strcasecmp(mode, "sendfile"))
+		return CFG_MODE_SENDFILE;
+
+	fprintf(stderr, "Unknown test mode: %s\n", mode);
+	fprintf(stderr, "Supported modes are:\n");
+	fprintf(stderr, "\t\t\"poll\" - interleaved read/write using poll()\n");
+	fprintf(stderr, "\t\t\"mmap\" - send entire input file (mmap+write), then read response (-l will read input first)\n");
+	fprintf(stderr, "\t\t\"sendfile\" - send entire input file (sendfile), then read response (-l will read input first)\n");
+
+	die_usage();
+
+	/* silence compiler warning */
+	return 0;
+}
+
+static int parse_int(const char *size)
+{
+	unsigned long s;
+
+	errno = 0;
+
+	s = strtoul(size, NULL, 0);
+
+	if (errno) {
+		fprintf(stderr, "Invalid sndbuf size %s (%s)\n",
+			size, strerror(errno));
+		die_usage();
+	}
+
+	if (s > INT_MAX) {
+		fprintf(stderr, "Invalid sndbuf size %s (%s)\n",
+			size, strerror(ERANGE));
+		die_usage();
+	}
+
+	return (int)s;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "6jrlp:s:hut:m:S:R:w:")) != -1) {
+		switch (c) {
+		case 'j':
+			cfg_join = true;
+			cfg_mode = CFG_MODE_POLL;
+			cfg_wait = 400000;
+			break;
+		case 'r':
+			cfg_remove = true;
+			cfg_mode = CFG_MODE_POLL;
+			cfg_wait = 400000;
+			break;
+		case 'l':
+			listen_mode = true;
+			break;
+		case 'p':
+			cfg_port = optarg;
+			break;
+		case 's':
+			cfg_sock_proto = parse_proto(optarg);
+			break;
+		case 'h':
+			die_usage();
+			break;
+		case 'u':
+			tcpulp_audit = true;
+			break;
+		case '6':
+			pf = AF_INET6;
+			break;
+		case 't':
+			poll_timeout = atoi(optarg) * 1000;
+			if (poll_timeout <= 0)
+				poll_timeout = -1;
+			break;
+		case 'm':
+			cfg_mode = parse_mode(optarg);
+			break;
+		case 'S':
+			cfg_sndbuf = parse_int(optarg);
+			break;
+		case 'R':
+			cfg_rcvbuf = parse_int(optarg);
+			break;
+		case 'w':
+			cfg_wait = atoi(optarg)*1000000;
+			break;
+		}
+	}
+
+	if (optind + 1 != argc)
+		die_usage();
+	cfg_host = argv[optind];
+
+	if (strchr(cfg_host, ':'))
+		pf = AF_INET6;
+}
+
+int main(int argc, char *argv[])
+{
+	init_rng();
+
+	signal(SIGUSR1, handle_signal);
+	parse_opts(argc, argv);
+
+	if (tcpulp_audit)
+		return sock_test_tcpulp(cfg_host, cfg_port) ? 0 : 1;
+
+	if (listen_mode) {
+		int fd = sock_listen_mptcp(cfg_host, cfg_port);
+
+		if (fd < 0)
+			return 1;
+
+		if (cfg_rcvbuf)
+			set_rcvbuf(fd, cfg_rcvbuf);
+		if (cfg_sndbuf)
+			set_sndbuf(fd, cfg_sndbuf);
+
+		return main_loop_s(fd);
+	}
+
+	return main_loop();
+}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
new file mode 100755
index 000000000..fb89298bd
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -0,0 +1,697 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+time_start=$(date +%s)
+
+optstring="S:R:d:e:l:r:h4cm:f:t"
+ret=0
+sin=""
+sout=""
+cin=""
+cout=""
+ksft_skip=4
+capture=false
+timeout=30
+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
+filesize=0
+
+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: $0 [ -a ]"
+	echo -e "\t-d: tc/netem delay in milliseconds, e.g. \"-d 10\" (default random)"
+	echo -e "\t-l: tc/netem loss percentage, e.g. \"-l 0.02\" (default random)"
+	echo -e "\t-r: tc/netem reorder mode, e.g. \"-r 25% 50% gap 5\", use "-r 0" to disable reordering (default random)"
+	echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)"
+	echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)"
+	echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
+	echo -e "\t-f: size of file to transfer in bytes (default random)"
+	echo -e "\t-S: set sndbuf value (default: use kernel default)"
+	echo -e "\t-R: set rcvbuf value (default: use kernel default)"
+	echo -e "\t-m: test mode (poll, sendfile; default: poll)"
+	echo -e "\t-t: also run tests with TCP (use twice to non-fallback tcp)"
+}
+
+while getopts "$optstring" option;do
+	case "$option" in
+	"h")
+		usage $0
+		exit 0
+		;;
+	"d")
+		if [ $OPTARG -ge 0 ];then
+			tc_delay="$OPTARG"
+		else
+			echo "-d requires numeric argument, got \"$OPTARG\"" 1>&2
+			exit 1
+		fi
+		;;
+	"e")
+		ethtool_args="$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 1
+		fi
+		;;
+	"R")
+		if [ $OPTARG -ge 0 ];then
+			rcvbuf="$OPTARG"
+		else
+			echo "-R requires numeric argument, got \"$OPTARG\"" 1>&2
+			exit 1
+		fi
+		;;
+	"m")
+		testmode="$OPTARG"
+		;;
+	"f")
+		filesize="$OPTARG"
+		;;
+	"t")
+		do_tcp=$((do_tcp+1))
+		;;
+	"?")
+		usage $0
+		exit 1
+		;;
+	esac
+done
+
+sec=$(date +%s)
+rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+ns1="ns1-$rndh"
+ns2="ns2-$rndh"
+ns3="ns3-$rndh"
+ns4="ns4-$rndh"
+
+TEST_COUNT=0
+
+cleanup()
+{
+	rm -f "$cin" "$cout"
+	rm -f "$sin" "$sout"
+	rm -f "$capout"
+
+	local netns
+	for netns in "$ns1" "$ns2" "$ns3" "$ns4";do
+		ip netns del $netns
+	done
+}
+
+mptcp_lib_check_mptcp
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+sin=$(mktemp)
+sout=$(mktemp)
+cin=$(mktemp)
+cout=$(mktemp)
+capout=$(mktemp)
+trap cleanup EXIT
+
+for i in "$ns1" "$ns2" "$ns3" "$ns4";do
+	ip netns add $i || exit $ksft_skip
+	ip -net $i link set lo up
+done
+
+#  "$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
+
+set_ethtool_flags() {
+	local ns="$1"
+	local dev="$2"
+	local flags="$3"
+
+	ip netns exec $ns ethtool -K $dev $flags 2>/dev/null
+	[ $? -eq 0 ] && echo "INFO: set $ns dev $dev: ethtool -K $flags"
+}
+
+set_random_ethtool_flags() {
+	local flags=""
+	local r=$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_file_err()
+{
+	ls -l "$1" 1>&2
+	echo "Trailing bytes are: "
+	tail -c 27 "$1"
+}
+
+check_transfer()
+{
+	local in=$1
+	local out=$2
+	local what=$3
+
+	cmp "$in" "$out" > /dev/null 2>&1
+	if [ $? -ne 0 ] ;then
+		echo "[ FAIL ] $what does not match (in, out):"
+		print_file_err "$in"
+		print_file_err "$out"
+
+		return 1
+	fi
+
+	return 0
+}
+
+check_mptcp_disabled()
+{
+	local disabled_ns
+	disabled_ns="ns_disabled-$sech-$(mktemp -u XXXXXX)"
+	ip netns add ${disabled_ns} || exit $ksft_skip
+
+	# net.mptcp.enabled should be enabled by default
+	if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then
+		echo -e "net.mptcp.enabled sysctl is not 1 by default\t\t[ FAIL ]"
+		ret=1
+		return 1
+	fi
+	ip netns exec ${disabled_ns} sysctl -q net.mptcp.enabled=0
+
+	local err=0
+	LANG=C ip netns exec ${disabled_ns} ./mptcp_connect -t $timeout -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \
+		grep -q "^socket: Protocol not available$" && err=1
+	ip netns delete ${disabled_ns}
+
+	if [ ${err} -eq 0 ]; then
+		echo -e "New MPTCP socket cannot be blocked via sysctl\t\t[ FAIL ]"
+		ret=1
+		return 1
+	fi
+
+	echo -e "New MPTCP socket can be blocked via sysctl\t\t[ OK ]"
+	return 0
+}
+
+check_mptcp_ulp_setsockopt()
+{
+	local t retval
+	t="ns_ulp-$sech-$(mktemp -u XXXXXX)"
+
+	ip netns add ${t} || exit $ksft_skip
+	if ! ip netns exec ${t} ./mptcp_connect -u -p 10000 -s TCP 127.0.0.1 2>&1; then
+		printf "setsockopt(..., TCP_ULP, \"mptcp\", ...) allowed\t[ FAIL ]\n"
+		retval=1
+		ret=$retval
+	else
+		printf "setsockopt(..., TCP_ULP, \"mptcp\", ...) blocked\t[ OK ]\n"
+		retval=0
+	fi
+	ip netns del ${t}
+	return $retval
+}
+
+# $1: IP address
+is_v6()
+{
+	[ -z "${1##*:*}" ]
+}
+
+do_ping()
+{
+	local listener_ns="$1"
+	local connector_ns="$2"
+	local connect_addr="$3"
+	local ping_args="-q -c 1"
+
+	if is_v6 "${connect_addr}"; then
+		$ipv6 || return 0
+		ping_args="${ping_args} -6"
+	fi
+
+	ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null
+	if [ $? -ne 0 ] ; then
+		echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2
+		ret=1
+
+		return 1
+	fi
+
+	return 0
+}
+
+# $1: ns, $2: port
+wait_local_port_listen()
+{
+	local listener_ns="${1}"
+	local port="${2}"
+
+	local port_hex i
+
+	port_hex="$(printf "%04X" "${port}")"
+	for i in $(seq 10); do
+		ip netns exec "${listener_ns}" cat /proc/net/tcp* | \
+			awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
+			break
+		sleep 0.1
+	done
+}
+
+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="$6"
+	local extra_args=""
+
+	local port
+	port=$((10000+$TEST_COUNT))
+	TEST_COUNT=$((TEST_COUNT+1))
+
+	if [ "$rcvbuf" -gt 0 ]; then
+		extra_args="$extra_args -R $rcvbuf"
+	fi
+
+	if [ "$sndbuf" -gt 0 ]; then
+		extra_args="$extra_args -S $sndbuf"
+	fi
+
+	if [ -n "$testmode" ]; then
+		extra_args="$extra_args -m $testmode"
+	fi
+
+	if [ -n "$extra_args" ] && $options_log; then
+		options_log=false
+		echo "INFO: extra options: $extra_args"
+	fi
+
+	:> "$cout"
+	:> "$sout"
+	:> "$capout"
+
+	local addr_port
+	addr_port=$(printf "%s:%d" ${connect_addr} ${port})
+	printf "%.3s %-5s -> %.3s (%-20s) %-5s\t" ${connector_ns} ${cl_proto} ${listener_ns} ${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"  >> "${capout}" 2>&1 &
+		local cappid_listener=$!
+
+		ip netns exec ${connector_ns} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 &
+		local cappid_connector=$!
+
+		sleep 1
+	fi
+
+	local stat_synrx_last_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableSYNRX | while read a count c rest ;do  echo $count;done)
+	local stat_ackrx_last_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableACKRX | while read a count c rest ;do  echo $count;done)
+	local stat_cookietx_last=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesSent | while read a count c rest ;do  echo $count;done)
+	local stat_cookierx_last=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesRecv | while read a count c rest ;do  echo $count;done)
+
+	ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" &
+	local spid=$!
+
+	wait_local_port_listen "${listener_ns}" "${port}"
+
+	local start
+	start=$(date +%s%3N)
+	ip netns exec ${connector_ns} ./mptcp_connect -t $timeout -p $port -s ${cl_proto} $extra_args $connect_addr < "$cin" > "$cout" &
+	local cpid=$!
+
+	wait $cpid
+	local retc=$?
+	wait $spid
+	local rets=$?
+
+	local stop
+	stop=$(date +%s%3N)
+
+	if $capture; then
+		sleep 1
+		kill ${cappid_listener}
+		kill ${cappid_connector}
+	fi
+
+	local duration
+	duration=$((stop-start))
+	duration=$(printf "(duration %05sms)" $duration)
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+		echo "$duration [ FAIL ] client exit code $retc, server $rets" 1>&2
+		echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2
+		ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port"
+		echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2
+		ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port"
+
+		cat "$capout"
+		return 1
+	fi
+
+	check_transfer $sin $cout "file received by client"
+	retc=$?
+	check_transfer $cin $sout "file received by server"
+	rets=$?
+
+	local stat_synrx_now_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableSYNRX  | while read a count c rest ;do  echo $count;done)
+	local stat_ackrx_now_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableACKRX  | while read a count c rest ;do  echo $count;done)
+
+	local stat_cookietx_now=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesSent | while read a count c rest ;do  echo $count;done)
+	local stat_cookierx_now=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesRecv | while read a count c rest ;do  echo $count;done)
+
+	expect_synrx=$((stat_synrx_last_l))
+	expect_ackrx=$((stat_ackrx_last_l))
+
+	cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies)
+	cookies=${cookies##*=}
+
+	if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then
+		expect_synrx=$((stat_synrx_last_l+1))
+		expect_ackrx=$((stat_ackrx_last_l+1))
+	fi
+	if [ $cookies -eq 2 ];then
+		if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then
+			echo "${listener_ns} CookieSent: ${cl_proto} -> ${srv_proto}: did not advance"
+		fi
+		if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then
+			echo "${listener_ns} CookieRecv: ${cl_proto} -> ${srv_proto}: did not advance"
+		fi
+	else
+		if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then
+			echo "${listener_ns} CookieSent: ${cl_proto} -> ${srv_proto}: changed"
+		fi
+		if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then
+			echo "${listener_ns} CookieRecv: ${cl_proto} -> ${srv_proto}: changed"
+		fi
+	fi
+
+	if [ $expect_synrx -ne $stat_synrx_now_l ] ;then
+		echo "${listener_ns} SYNRX: ${cl_proto} -> ${srv_proto}: expect ${expect_synrx}, got ${stat_synrx_now_l}"
+	fi
+	if [ $expect_ackrx -ne $stat_ackrx_now_l ] ;then
+		echo "${listener_ns} ACKRX: ${cl_proto} -> ${srv_proto}: expect ${expect_ackrx}, got ${stat_ackrx_now_l} "
+	fi
+
+	if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
+		echo "$duration [ OK ]"
+		cat "$capout"
+		return 0
+	fi
+
+	cat "$capout"
+	return 1
+}
+
+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)))
+
+	dd if=/dev/urandom of="$name" bs=1024 count=$ksize 2> /dev/null
+	dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$rem 2> /dev/null
+	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
+
+	echo "Created $name (size $(du -b "$name")) containing data sent by $who"
+}
+
+run_tests_lo()
+{
+	local listener_ns="$1"
+	local connector_ns="$2"
+	local connect_addr="$3"
+	local loopback="$4"
+	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 ! $ipv6 && is_v6 "${connect_addr}"; then
+		return 0
+	fi
+
+	local local_addr
+	if 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} ${local_addr}
+	lret=$?
+	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} ${local_addr}
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return 1
+	fi
+
+	do_transfer ${listener_ns} ${connector_ns} TCP MPTCP ${connect_addr} ${local_addr}
+	lret=$?
+	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} ${local_addr}
+		lret=$?
+		if [ $lret -ne 0 ]; then
+			ret=$lret
+			return 1
+		fi
+	fi
+
+	return 0
+}
+
+run_tests()
+{
+	run_tests_lo $1 $2 $3 0
+}
+
+make_file "$cin" "client"
+make_file "$sin" "server"
+
+check_mptcp_disabled
+
+check_mptcp_ulp_setsockopt
+
+echo "INFO: validating network environment with pings"
+for sender in "$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" $sender dead:beef:3::1
+done
+
+[ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss delay ${tc_delay}ms
+echo -n "INFO: Using loss of $tc_loss "
+test "$tc_delay" -gt 0 && echo -n "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}% ${reorder2}%"
+		echo -n "$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 $tc_reorder"
+	echo -n "$tc_reorder with delay ${reorder_delay}ms "
+fi
+
+echo "on ns3eth4"
+
+tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${reorder_delay}ms $tc_reorder
+
+for sender in $ns1 $ns2 $ns3 $ns4;do
+	run_tests_lo "$ns1" "$sender" 10.0.1.1 1
+	if [ $ret -ne 0 ] ;then
+		echo "FAIL: Could not even run loopback test" 1>&2
+		exit $ret
+	fi
+	run_tests_lo "$ns1" $sender dead:beef:1::1 1
+	if [ $ret -ne 0 ] ;then
+		echo "FAIL: Could not even run loopback v6 test" 2>&1
+		exit $ret
+	fi
+
+	# 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 "$ns2" sysctl -q net.ipv4.tcp_syncookies=1
+	fi
+
+	run_tests "$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" $sender dead:beef:3::1
+done
+
+time_end=$(date +%s)
+time_run=$((time_end-time_start))
+
+echo "Time: ${time_run} seconds"
+
+exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
new file mode 100755
index 000000000..d205828d7
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -0,0 +1,629 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+ret=0
+sin=""
+sout=""
+cin=""
+cout=""
+ksft_skip=4
+timeout=30
+mptcp_connect=""
+capture=0
+
+TEST_COUNT=0
+
+init()
+{
+	capout=$(mktemp)
+
+	rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+
+	ns1="ns1-$rndh"
+	ns2="ns2-$rndh"
+
+	for netns in "$ns1" "$ns2";do
+		ip netns add $netns || exit $ksft_skip
+		ip -net $netns link set lo up
+		ip netns exec $netns sysctl -q net.mptcp.enabled=1
+		ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0
+		ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0
+	done
+
+	#  ns1              ns2
+	# ns1eth1    ns2eth1
+	# ns1eth2    ns2eth2
+	# ns1eth3    ns2eth3
+	# ns1eth4    ns2eth4
+
+	for i in `seq 1 4`; do
+		ip link add ns1eth$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$i
+	done
+}
+
+cleanup_partial()
+{
+	rm -f "$capout"
+
+	for netns in "$ns1" "$ns2"; do
+		ip netns del $netns
+	done
+}
+
+cleanup()
+{
+	rm -f "$cin" "$cout"
+	rm -f "$sin" "$sout"
+	cleanup_partial
+}
+
+reset()
+{
+	cleanup_partial
+	init
+}
+
+reset_with_cookies()
+{
+	reset
+
+	for netns in "$ns1" "$ns2";do
+		ip netns exec $netns sysctl -q net.ipv4.tcp_syncookies=2
+	done
+}
+
+for arg in "$@"; do
+	if [ "$arg" = "-c" ]; then
+		capture=1
+	fi
+done
+
+mptcp_lib_check_mptcp
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+
+check_transfer()
+{
+	in=$1
+	out=$2
+	what=$3
+
+	cmp "$in" "$out" > /dev/null 2>&1
+	if [ $? -ne 0 ] ;then
+		echo "[ FAIL ] $what does not match (in, out):"
+		print_file_err "$in"
+		print_file_err "$out"
+
+		return 1
+	fi
+
+	return 0
+}
+
+do_ping()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	connect_addr="$3"
+
+	ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null
+	if [ $? -ne 0 ] ; then
+		echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2
+		ret=1
+	fi
+}
+
+# $1: ns ; $2: counter
+get_counter()
+{
+	local ns="${1}"
+	local counter="${2}"
+	local count
+
+	count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}')
+	if [ -z "${count}" ]; then
+		mptcp_lib_fail_if_expected_feature "${counter} counter"
+		return 1
+	fi
+
+	echo "${count}"
+}
+
+do_transfer()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	cl_proto="$3"
+	srv_proto="$4"
+	connect_addr="$5"
+	rm_nr_ns1="$6"
+	rm_nr_ns2="$7"
+
+	port=$((10000+$TEST_COUNT))
+	TEST_COUNT=$((TEST_COUNT+1))
+
+	:> "$cout"
+	:> "$sout"
+	:> "$capout"
+
+	if [ $capture -eq 1 ]; then
+		if [ -z $SUDO_USER ] ; then
+			capuser=""
+		else
+			capuser="-Z $SUDO_USER"
+		fi
+
+		capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}")
+
+		echo "Capturing traffic for test $TEST_COUNT into $capfile"
+		ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 &
+		cappid=$!
+
+		sleep 1
+	fi
+
+	if [[ $rm_nr_ns1 -eq 0 && $rm_nr_ns2 -eq 0 ]]; then
+		mptcp_connect="./mptcp_connect -j"
+	else
+		mptcp_connect="./mptcp_connect -r"
+	fi
+
+	ip netns exec ${listener_ns} $mptcp_connect -t $timeout -l -p $port -s ${srv_proto} 0.0.0.0 < "$sin" > "$sout" &
+	spid=$!
+
+	sleep 1
+
+	ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+	cpid=$!
+
+	if [ $rm_nr_ns1 -gt 0 ]; then
+		counter=1
+		sleep 1
+
+		while [ $counter -le $rm_nr_ns1 ]
+		do
+			ip netns exec ${listener_ns} ./pm_nl_ctl del $counter
+			sleep 1
+			let counter+=1
+		done
+	fi
+
+	if [ $rm_nr_ns2 -gt 0 ]; then
+		counter=1
+		sleep 1
+
+		while [ $counter -le $rm_nr_ns2 ]
+		do
+			ip netns exec ${connector_ns} ./pm_nl_ctl del $counter
+			sleep 1
+			let counter+=1
+		done
+	fi
+
+	wait $cpid
+	retc=$?
+	wait $spid
+	rets=$?
+
+	if [ $capture -eq 1 ]; then
+	    sleep 1
+	    kill $cappid
+	fi
+
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+		echo " client exit code $retc, server $rets" 1>&2
+		echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2
+		ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port"
+		echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2
+		ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port"
+
+		cat "$capout"
+		return 1
+	fi
+
+	check_transfer $sin $cout "file received by client"
+	retc=$?
+	check_transfer $cin $sout "file received by server"
+	rets=$?
+
+	if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
+		cat "$capout"
+		return 0
+	fi
+
+	cat "$capout"
+	return 1
+}
+
+make_file()
+{
+	name=$1
+	who=$2
+
+	SIZE=1
+
+	dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null
+	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
+
+	echo "Created $name (size $SIZE KB) containing data sent by $who"
+}
+
+run_tests()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	connect_addr="$3"
+	lret=0
+
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} 0 0
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return
+	fi
+}
+
+run_remove_tests()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	connect_addr="$3"
+	rm_nr_ns1="$4"
+	rm_nr_ns2="$5"
+	lret=0
+
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${rm_nr_ns1} ${rm_nr_ns2}
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return
+	fi
+}
+
+chk_join_nr()
+{
+	local msg="$1"
+	local syn_nr=$2
+	local syn_ack_nr=$3
+	local ack_nr=$4
+	local count
+	local dump_stats
+
+	printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn"
+	count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx")
+	if [ -z "$count" ]; then
+		echo -n "[skip]"
+	elif [ "$count" != "$syn_nr" ]; then
+		echo "[fail] got $count JOIN[s] syn expected $syn_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo -n "[ ok ]"
+	fi
+
+	echo -n " - synack"
+	count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx")
+	if [ -z "$count" ]; then
+		echo -n "[skip]"
+	elif [ "$count" != "$syn_ack_nr" ]; then
+		echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo -n "[ ok ]"
+	fi
+
+	echo -n " - ack"
+	count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx")
+	if [ -z "$count" ]; then
+		echo "[skip]"
+	elif [ "$count" != "$ack_nr" ]; then
+		echo "[fail] got $count JOIN[s] ack expected $ack_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo "[ ok ]"
+	fi
+	if [ "${dump_stats}" = 1 ]; then
+		echo Server ns stats
+		ip netns exec $ns1 nstat -as | grep MPTcp
+		echo Client ns stats
+		ip netns exec $ns2 nstat -as | grep MPTcp
+	fi
+}
+
+chk_add_nr()
+{
+	local add_nr=$1
+	local echo_nr=$2
+	local count
+	local dump_stats
+
+	printf "%-39s %s" " " "add"
+	count=$(get_counter ${ns2} "MPTcpExtAddAddr")
+	if [ -z "$count" ]; then
+		echo -n "[skip]"
+	elif [ "$count" != "$add_nr" ]; then
+		echo "[fail] got $count ADD_ADDR[s] expected $add_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo -n "[ ok ]"
+	fi
+
+	echo -n " - echo  "
+	count=$(get_counter ${ns1} "MPTcpExtEchoAdd")
+	if [ -z "$count" ]; then
+		echo "[skip]"
+	elif [ "$count" != "$echo_nr" ]; then
+		echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo "[ ok ]"
+	fi
+
+	if [ "${dump_stats}" = 1 ]; then
+		echo Server ns stats
+		ip netns exec $ns1 nstat -as | grep MPTcp
+		echo Client ns stats
+		ip netns exec $ns2 nstat -as | grep MPTcp
+	fi
+}
+
+chk_rm_nr()
+{
+	local rm_addr_nr=$1
+	local rm_subflow_nr=$2
+	local count
+	local dump_stats
+
+	printf "%-39s %s" " " "rm "
+	count=$(get_counter ${ns1} "MPTcpExtRmAddr")
+	if [ -z "$count" ]; then
+		echo -n "[skip]"
+	elif [ "$count" != "$rm_addr_nr" ]; then
+		echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo -n "[ ok ]"
+	fi
+
+	echo -n " - sf    "
+	count=$(get_counter ${ns2} "MPTcpExtRmSubflow")
+	if [ -z "$count" ]; then
+		echo "[skip]"
+	elif [ "$count" != "$rm_subflow_nr" ]; then
+		echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo "[ ok ]"
+	fi
+
+	if [ "${dump_stats}" = 1 ]; then
+		echo Server ns stats
+		ip netns exec $ns1 nstat -as | grep MPTcp
+		echo Client ns stats
+		ip netns exec $ns2 nstat -as | grep MPTcp
+	fi
+}
+
+sin=$(mktemp)
+sout=$(mktemp)
+cin=$(mktemp)
+cout=$(mktemp)
+init
+make_file "$cin" "client"
+make_file "$sin" "server"
+trap cleanup EXIT
+
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "no JOIN" "0" "0" "0"
+
+# subflow limted by client
+reset
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "single subflow, limited by client" 0 0 0
+
+# subflow limted by server
+reset
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "single subflow, limited by server" 1 1 0
+
+# subflow
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "single subflow" 1 1 1
+
+# multiple subflows
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "multiple subflows" 2 2 2
+
+# multiple subflows limited by serverf
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "multiple subflows, limited by server" 2 2 1
+
+# add_address, unused
+reset
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "unused signal address" 0 0 0
+chk_add_nr 1 1
+
+# accept and use add_addr
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "signal address" 1 1 1
+chk_add_nr 1 1
+
+# accept and use add_addr with an additional subflow
+# note: signal address in server ns and local addresses in client ns must
+# belong to different subnets or one of the listed local address could be
+# used for 'add_addr' subflow
+reset
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl limits 1 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "subflow and signal" 2 2 2
+chk_add_nr 1 1
+
+# accept and use add_addr with additional subflows
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 3
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "multiple subflows and signal" 3 3 3
+chk_add_nr 1 1
+
+# single subflow, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_remove_tests $ns1 $ns2 10.0.1.1 0 1
+chk_join_nr "remove single subflow" 1 1 1
+chk_rm_nr 1 1
+
+# multiple subflows, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_remove_tests $ns1 $ns2 10.0.1.1 0 2
+chk_join_nr "remove multiple subflows" 2 2 2
+chk_rm_nr 2 2
+
+# single address, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+run_remove_tests $ns1 $ns2 10.0.1.1 1 0
+chk_join_nr "remove single address" 1 1 1
+chk_add_nr 1 1
+chk_rm_nr 0 0
+
+# subflow and signal, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_remove_tests $ns1 $ns2 10.0.1.1 1 1
+chk_join_nr "remove subflow and signal" 2 2 2
+chk_add_nr 1 1
+chk_rm_nr 1 1
+
+# subflows and signal, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 3
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+run_remove_tests $ns1 $ns2 10.0.1.1 1 2
+chk_join_nr "remove subflows and signal" 3 3 3
+chk_add_nr 1 1
+chk_rm_nr 2 2
+
+# single subflow, syncookies
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "single subflow with syn cookies" 1 1 1
+
+# multiple subflows with syn cookies
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "multiple subflows with syn cookies" 2 2 2
+
+# multiple subflows limited by server
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "subflows limited by server w cookies" 2 2 1
+
+# test signal address with cookies
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "signal address with syn cookies" 1 1 1
+chk_add_nr 1 1
+
+# test cookie with subflow and signal
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl limits 1 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "subflow and signal w cookies" 2 2 2
+chk_add_nr 1 1
+
+# accept and use add_addr with additional subflows
+reset_with_cookies
+ip netns exec $ns1 ./pm_nl_ctl limits 0 3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 3
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1
+chk_join_nr "subflows and signal w. cookies" 3 3 3
+chk_add_nr 1 1
+
+exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
new file mode 100644
index 000000000..f32045b23
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -0,0 +1,104 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+readonly KSFT_FAIL=1
+readonly KSFT_SKIP=4
+
+# SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all
+# features using the last version of the kernel and the selftests to make sure
+# a test is not being skipped by mistake.
+mptcp_lib_expect_all_features() {
+	[ "${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
+		echo "SKIP: MPTCP support is not available"
+		exit ${KSFT_SKIP}
+	fi
+}
+
+mptcp_lib_check_kallsyms() {
+	if ! mptcp_lib_has_file "/proc/kallsyms"; then
+		echo "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 ${v}"
+}
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
new file mode 100755
index 000000000..fff6f74eb
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -0,0 +1,136 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+ksft_skip=4
+ret=0
+
+usage() {
+	echo "Usage: $0 [ -h ]"
+}
+
+
+while getopts "$optstring" option;do
+	case "$option" in
+	"h")
+		usage $0
+		exit 0
+		;;
+	"?")
+		usage $0
+		exit 1
+		;;
+	esac
+done
+
+sec=$(date +%s)
+rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+ns1="ns1-$rndh"
+err=$(mktemp)
+ret=0
+
+cleanup()
+{
+	rm -f $err
+	ip netns del $ns1
+}
+
+mptcp_lib_check_mptcp
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+trap cleanup EXIT
+
+ip netns add $ns1 || exit $ksft_skip
+ip -net $ns1 link set lo up
+ip netns exec $ns1 sysctl -q net.mptcp.enabled=1
+
+check()
+{
+	local cmd="$1"
+	local expected="$2"
+	local msg="$3"
+	local out=`$cmd 2>$err`
+	local cmd_ret=$?
+
+	printf "%-50s %s" "$msg"
+	if [ $cmd_ret -ne 0 ]; then
+		echo "[FAIL] command execution '$cmd' stderr "
+		cat $err
+		ret=1
+	elif [ "$out" = "$expected" ]; then
+		echo "[ OK ]"
+	else
+		echo -n "[FAIL] "
+		echo "expected '$expected' got '$out'"
+		ret=1
+	fi
+}
+
+check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list"
+
+default_limits="$(ip netns exec $ns1 ./pm_nl_ctl limits)"
+if mptcp_lib_expect_all_features; then
+	check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0
+subflows 0" "defaults limits"
+fi
+
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3 flags signal,backup
+check "ip netns exec $ns1 ./pm_nl_ctl get 1" "id 1 flags  10.0.1.1" "simple add/get addr"
+
+check "ip netns exec $ns1 ./pm_nl_ctl dump" \
+"id 1 flags  10.0.1.1
+id 2 flags subflow dev lo 10.0.1.2
+id 3 flags signal,backup 10.0.1.3" "dump addrs"
+
+ip netns exec $ns1 ./pm_nl_ctl del 2
+check "ip netns exec $ns1 ./pm_nl_ctl get 2" "" "simple del addr"
+check "ip netns exec $ns1 ./pm_nl_ctl dump" \
+"id 1 flags  10.0.1.1
+id 3 flags signal,backup 10.0.1.3" "dump addrs after del"
+
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.3
+check "ip netns exec $ns1 ./pm_nl_ctl get 4" "" "duplicate addr"
+
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.4 id 10 flags signal
+check "ip netns exec $ns1 ./pm_nl_ctl get 4" "id 4 flags signal 10.0.1.4" "id addr increment"
+
+for i in `seq 5 9`; do
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.$i flags signal >/dev/null 2>&1
+done
+check "ip netns exec $ns1 ./pm_nl_ctl get 9" "id 9 flags signal 10.0.1.9" "hard addr limit"
+check "ip netns exec $ns1 ./pm_nl_ctl get 10" "" "above hard addr limit"
+
+for i in `seq 9 256`; do
+	ip netns exec $ns1 ./pm_nl_ctl del $i
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.9
+done
+check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags  10.0.1.1
+id 3 flags signal,backup 10.0.1.3
+id 4 flags signal 10.0.1.4
+id 5 flags signal 10.0.1.5
+id 6 flags signal 10.0.1.6
+id 7 flags signal 10.0.1.7
+id 8 flags signal 10.0.1.8" "id limit"
+
+ip netns exec $ns1 ./pm_nl_ctl flush
+check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs"
+
+ip netns exec $ns1 ./pm_nl_ctl limits 9 1
+check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "rcv addrs above hard limit"
+
+ip netns exec $ns1 ./pm_nl_ctl limits 1 9
+check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "subflows above hard limit"
+
+ip netns exec $ns1 ./pm_nl_ctl limits 8 8
+check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8
+subflows 8" "set limits"
+
+exit $ret
diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
new file mode 100644
index 000000000..b24a2f17d
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
@@ -0,0 +1,616 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <error.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+#include <sys/types.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include <linux/rtnetlink.h>
+#include <linux/genetlink.h>
+
+#include "linux/mptcp.h"
+
+#ifndef MPTCP_PM_NAME
+#define MPTCP_PM_NAME		"mptcp_pm"
+#endif
+
+static void syntax(char *argv[])
+{
+	fprintf(stderr, "%s add|get|del|flush|dump|accept [<args>]\n", argv[0]);
+	fprintf(stderr, "\tadd [flags signal|subflow|backup] [id <nr>] [dev <name>] <ip>\n");
+	fprintf(stderr, "\tdel <id>\n");
+	fprintf(stderr, "\tget <id>\n");
+	fprintf(stderr, "\tflush\n");
+	fprintf(stderr, "\tdump\n");
+	fprintf(stderr, "\tlimits [<rcv addr max> <subflow max>]\n");
+	exit(0);
+}
+
+static int init_genl_req(char *data, int family, int cmd, int version)
+{
+	struct nlmsghdr *nh = (void *)data;
+	struct genlmsghdr *gh;
+	int off = 0;
+
+	nh->nlmsg_type = family;
+	nh->nlmsg_flags = NLM_F_REQUEST;
+	nh->nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+	off += NLMSG_ALIGN(sizeof(*nh));
+
+	gh = (void *)(data + off);
+	gh->cmd = cmd;
+	gh->version = version;
+	off += NLMSG_ALIGN(sizeof(*gh));
+	return off;
+}
+
+static void nl_error(struct nlmsghdr *nh)
+{
+	struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(nh);
+	int len = nh->nlmsg_len - sizeof(*nh);
+	uint32_t off;
+
+	if (len < sizeof(struct nlmsgerr))
+		error(1, 0, "netlink error message truncated %d min %ld", len,
+		      sizeof(struct nlmsgerr));
+
+	if (!err->error) {
+		/* check messages from kernel */
+		struct rtattr *attrs = (struct rtattr *)NLMSG_DATA(nh);
+
+		while (RTA_OK(attrs, len)) {
+			if (attrs->rta_type == NLMSGERR_ATTR_MSG)
+				fprintf(stderr, "netlink ext ack msg: %s\n",
+					(char *)RTA_DATA(attrs));
+			if (attrs->rta_type == NLMSGERR_ATTR_OFFS) {
+				memcpy(&off, RTA_DATA(attrs), 4);
+				fprintf(stderr, "netlink err off %d\n",
+					(int)off);
+			}
+			attrs = RTA_NEXT(attrs, len);
+		}
+	} else {
+		fprintf(stderr, "netlink error %d", err->error);
+	}
+}
+
+/* do a netlink command and, if max > 0, fetch the reply  */
+static int do_nl_req(int fd, struct nlmsghdr *nh, int len, int max)
+{
+	struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+	socklen_t addr_len;
+	void *data = nh;
+	int rem, ret;
+	int err = 0;
+
+	nh->nlmsg_len = len;
+	ret = sendto(fd, data, len, 0, (void *)&nladdr, sizeof(nladdr));
+	if (ret != len)
+		error(1, errno, "send netlink: %uB != %uB\n", ret, len);
+	if (max == 0)
+		return 0;
+
+	addr_len = sizeof(nladdr);
+	rem = ret = recvfrom(fd, data, max, 0, (void *)&nladdr, &addr_len);
+	if (ret < 0)
+		error(1, errno, "recv netlink: %uB\n", ret);
+
+	/* Beware: the NLMSG_NEXT macro updates the 'rem' argument */
+	for (; NLMSG_OK(nh, rem); nh = NLMSG_NEXT(nh, rem)) {
+		if (nh->nlmsg_type == NLMSG_ERROR) {
+			nl_error(nh);
+			err = 1;
+		}
+	}
+	if (err)
+		error(1, 0, "bailing out due to netlink error[s]");
+	return ret;
+}
+
+static int genl_parse_getfamily(struct nlmsghdr *nlh)
+{
+	struct genlmsghdr *ghdr = NLMSG_DATA(nlh);
+	int len = nlh->nlmsg_len;
+	struct rtattr *attrs;
+
+	if (nlh->nlmsg_type != GENL_ID_CTRL)
+		error(1, errno, "Not a controller message, len=%d type=0x%x\n",
+		      nlh->nlmsg_len, nlh->nlmsg_type);
+
+	len -= NLMSG_LENGTH(GENL_HDRLEN);
+
+	if (len < 0)
+		error(1, errno, "wrong controller message len %d\n", len);
+
+	if (ghdr->cmd != CTRL_CMD_NEWFAMILY)
+		error(1, errno, "Unknown controller command %d\n", ghdr->cmd);
+
+	attrs = (struct rtattr *) ((char *) ghdr + GENL_HDRLEN);
+	while (RTA_OK(attrs, len)) {
+		if (attrs->rta_type == CTRL_ATTR_FAMILY_ID)
+			return *(__u16 *)RTA_DATA(attrs);
+		attrs = RTA_NEXT(attrs, len);
+	}
+
+	error(1, errno, "can't find CTRL_ATTR_FAMILY_ID attr");
+	return -1;
+}
+
+static int resolve_mptcp_pm_netlink(int fd)
+{
+	char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+		  NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+		  1024];
+	struct nlmsghdr *nh;
+	struct rtattr *rta;
+	int namelen;
+	int off = 0;
+
+	memset(data, 0, sizeof(data));
+	nh = (void *)data;
+	off = init_genl_req(data, GENL_ID_CTRL, CTRL_CMD_GETFAMILY, 0);
+
+	rta = (void *)(data + off);
+	namelen = strlen(MPTCP_PM_NAME) + 1;
+	rta->rta_type = CTRL_ATTR_FAMILY_NAME;
+	rta->rta_len = RTA_LENGTH(namelen);
+	memcpy(RTA_DATA(rta), MPTCP_PM_NAME, namelen);
+	off += NLMSG_ALIGN(rta->rta_len);
+
+	do_nl_req(fd, nh, off, sizeof(data));
+	return genl_parse_getfamily((void *)data);
+}
+
+int add_addr(int fd, int pm_family, int argc, char *argv[])
+{
+	char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+		  NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+		  1024];
+	struct rtattr *rta, *nest;
+	struct nlmsghdr *nh;
+	u_int16_t family;
+	u_int32_t flags;
+	int nest_start;
+	u_int8_t id;
+	int off = 0;
+	int arg;
+
+	memset(data, 0, sizeof(data));
+	nh = (void *)data;
+	off = init_genl_req(data, pm_family, MPTCP_PM_CMD_ADD_ADDR,
+			    MPTCP_PM_VER);
+
+	if (argc < 3)
+		syntax(argv);
+
+	nest_start = off;
+	nest = (void *)(data + off);
+	nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR;
+	nest->rta_len = RTA_LENGTH(0);
+	off += NLMSG_ALIGN(nest->rta_len);
+
+	/* addr data */
+	rta = (void *)(data + off);
+	if (inet_pton(AF_INET, argv[2], RTA_DATA(rta))) {
+		family = AF_INET;
+		rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4;
+		rta->rta_len = RTA_LENGTH(4);
+	} else if (inet_pton(AF_INET6, argv[2], RTA_DATA(rta))) {
+		family = AF_INET6;
+		rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6;
+		rta->rta_len = RTA_LENGTH(16);
+	} else
+		error(1, errno, "can't parse ip %s", argv[2]);
+	off += NLMSG_ALIGN(rta->rta_len);
+
+	/* family */
+	rta = (void *)(data + off);
+	rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY;
+	rta->rta_len = RTA_LENGTH(2);
+	memcpy(RTA_DATA(rta), &family, 2);
+	off += NLMSG_ALIGN(rta->rta_len);
+
+	for (arg = 3; arg < argc; arg++) {
+		if (!strcmp(argv[arg], "flags")) {
+			char *tok, *str;
+
+			/* flags */
+			flags = 0;
+			if (++arg >= argc)
+				error(1, 0, " missing flags value");
+
+			/* do not support flag list yet */
+			for (str = argv[arg]; (tok = strtok(str, ","));
+			     str = NULL) {
+				if (!strcmp(tok, "subflow"))
+					flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW;
+				else if (!strcmp(tok, "signal"))
+					flags |= MPTCP_PM_ADDR_FLAG_SIGNAL;
+				else if (!strcmp(tok, "backup"))
+					flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
+				else
+					error(1, errno,
+					      "unknown flag %s", argv[arg]);
+			}
+
+			rta = (void *)(data + off);
+			rta->rta_type = MPTCP_PM_ADDR_ATTR_FLAGS;
+			rta->rta_len = RTA_LENGTH(4);
+			memcpy(RTA_DATA(rta), &flags, 4);
+			off += NLMSG_ALIGN(rta->rta_len);
+		} else if (!strcmp(argv[arg], "id")) {
+			if (++arg >= argc)
+				error(1, 0, " missing id value");
+
+			id = atoi(argv[arg]);
+			rta = (void *)(data + off);
+			rta->rta_type = MPTCP_PM_ADDR_ATTR_ID;
+			rta->rta_len = RTA_LENGTH(1);
+			memcpy(RTA_DATA(rta), &id, 1);
+			off += NLMSG_ALIGN(rta->rta_len);
+		} else if (!strcmp(argv[arg], "dev")) {
+			int32_t ifindex;
+
+			if (++arg >= argc)
+				error(1, 0, " missing dev name");
+
+			ifindex = if_nametoindex(argv[arg]);
+			if (!ifindex)
+				error(1, errno, "unknown device %s", argv[arg]);
+
+			rta = (void *)(data + off);
+			rta->rta_type = MPTCP_PM_ADDR_ATTR_IF_IDX;
+			rta->rta_len = RTA_LENGTH(4);
+			memcpy(RTA_DATA(rta), &ifindex, 4);
+			off += NLMSG_ALIGN(rta->rta_len);
+		} else
+			error(1, 0, "unknown keyword %s", argv[arg]);
+	}
+	nest->rta_len = off - nest_start;
+
+	do_nl_req(fd, nh, off, 0);
+	return 0;
+}
+
+int del_addr(int fd, int pm_family, int argc, char *argv[])
+{
+	char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+		  NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+		  1024];
+	struct rtattr *rta, *nest;
+	struct nlmsghdr *nh;
+	int nest_start;
+	u_int8_t id;
+	int off = 0;
+
+	memset(data, 0, sizeof(data));
+	nh = (void *)data;
+	off = init_genl_req(data, pm_family, MPTCP_PM_CMD_DEL_ADDR,
+			    MPTCP_PM_VER);
+
+	/* the only argument is the address id */
+	if (argc != 3)
+		syntax(argv);
+
+	id = atoi(argv[2]);
+
+	nest_start = off;
+	nest = (void *)(data + off);
+	nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR;
+	nest->rta_len =  RTA_LENGTH(0);
+	off += NLMSG_ALIGN(nest->rta_len);
+
+	/* build a dummy addr with only the ID set */
+	rta = (void *)(data + off);
+	rta->rta_type = MPTCP_PM_ADDR_ATTR_ID;
+	rta->rta_len = RTA_LENGTH(1);
+	memcpy(RTA_DATA(rta), &id, 1);
+	off += NLMSG_ALIGN(rta->rta_len);
+	nest->rta_len = off - nest_start;
+
+	do_nl_req(fd, nh, off, 0);
+	return 0;
+}
+
+static void print_addr(struct rtattr *attrs, int len)
+{
+	uint16_t family = 0;
+	char str[1024];
+	uint32_t flags;
+	uint8_t id;
+
+	while (RTA_OK(attrs, len)) {
+		if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_FAMILY)
+			memcpy(&family, RTA_DATA(attrs), 2);
+		if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ADDR4) {
+			if (family != AF_INET)
+				error(1, errno, "wrong IP (v4) for family %d",
+				      family);
+			inet_ntop(AF_INET, RTA_DATA(attrs), str, sizeof(str));
+			printf("%s", str);
+		}
+		if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ADDR6) {
+			if (family != AF_INET6)
+				error(1, errno, "wrong IP (v6) for family %d",
+				      family);
+			inet_ntop(AF_INET6, RTA_DATA(attrs), str, sizeof(str));
+			printf("%s", str);
+		}
+		if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ID) {
+			memcpy(&id, RTA_DATA(attrs), 1);
+			printf("id %d ", id);
+		}
+		if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_FLAGS) {
+			memcpy(&flags, RTA_DATA(attrs), 4);
+
+			printf("flags ");
+			if (flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
+				printf("signal");
+				flags &= ~MPTCP_PM_ADDR_FLAG_SIGNAL;
+				if (flags)
+					printf(",");
+			}
+
+			if (flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
+				printf("subflow");
+				flags &= ~MPTCP_PM_ADDR_FLAG_SUBFLOW;
+				if (flags)
+					printf(",");
+			}
+
+			if (flags & MPTCP_PM_ADDR_FLAG_BACKUP) {
+				printf("backup");
+				flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP;
+				if (flags)
+					printf(",");
+			}
+
+			/* bump unknown flags, if any */
+			if (flags)
+				printf("0x%x", flags);
+			printf(" ");
+		}
+		if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_IF_IDX) {
+			char name[IF_NAMESIZE], *ret;
+			int32_t ifindex;
+
+			memcpy(&ifindex, RTA_DATA(attrs), 4);
+			ret = if_indextoname(ifindex, name);
+			if (ret)
+				printf("dev %s ", ret);
+			else
+				printf("dev unknown/%d", ifindex);
+		}
+
+		attrs = RTA_NEXT(attrs, len);
+	}
+	printf("\n");
+}
+
+static void print_addrs(struct nlmsghdr *nh, int pm_family, int total_len)
+{
+	struct rtattr *attrs;
+
+	for (; NLMSG_OK(nh, total_len); nh = NLMSG_NEXT(nh, total_len)) {
+		int len = nh->nlmsg_len;
+
+		if (nh->nlmsg_type == NLMSG_DONE)
+			break;
+		if (nh->nlmsg_type == NLMSG_ERROR)
+			nl_error(nh);
+		if (nh->nlmsg_type != pm_family)
+			continue;
+
+		len -= NLMSG_LENGTH(GENL_HDRLEN);
+		attrs = (struct rtattr *) ((char *) NLMSG_DATA(nh) +
+					   GENL_HDRLEN);
+		while (RTA_OK(attrs, len)) {
+			if (attrs->rta_type ==
+			    (MPTCP_PM_ATTR_ADDR | NLA_F_NESTED))
+				print_addr((void *)RTA_DATA(attrs),
+					   attrs->rta_len);
+			attrs = RTA_NEXT(attrs, len);
+		}
+	}
+}
+
+int get_addr(int fd, int pm_family, int argc, char *argv[])
+{
+	char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+		  NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+		  1024];
+	struct rtattr *rta, *nest;
+	struct nlmsghdr *nh;
+	int nest_start;
+	u_int8_t id;
+	int off = 0;
+
+	memset(data, 0, sizeof(data));
+	nh = (void *)data;
+	off = init_genl_req(data, pm_family, MPTCP_PM_CMD_GET_ADDR,
+			    MPTCP_PM_VER);
+
+	/* the only argument is the address id */
+	if (argc != 3)
+		syntax(argv);
+
+	id = atoi(argv[2]);
+
+	nest_start = off;
+	nest = (void *)(data + off);
+	nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR;
+	nest->rta_len =  RTA_LENGTH(0);
+	off += NLMSG_ALIGN(nest->rta_len);
+
+	/* build a dummy addr with only the ID set */
+	rta = (void *)(data + off);
+	rta->rta_type = MPTCP_PM_ADDR_ATTR_ID;
+	rta->rta_len = RTA_LENGTH(1);
+	memcpy(RTA_DATA(rta), &id, 1);
+	off += NLMSG_ALIGN(rta->rta_len);
+	nest->rta_len = off - nest_start;
+
+	print_addrs(nh, pm_family, do_nl_req(fd, nh, off, sizeof(data)));
+	return 0;
+}
+
+int dump_addrs(int fd, int pm_family, int argc, char *argv[])
+{
+	char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+		  NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+		  1024];
+	pid_t pid = getpid();
+	struct nlmsghdr *nh;
+	int off = 0;
+
+	memset(data, 0, sizeof(data));
+	nh = (void *)data;
+	off = init_genl_req(data, pm_family, MPTCP_PM_CMD_GET_ADDR,
+			    MPTCP_PM_VER);
+	nh->nlmsg_flags |= NLM_F_DUMP;
+	nh->nlmsg_seq = 1;
+	nh->nlmsg_pid = pid;
+	nh->nlmsg_len = off;
+
+	print_addrs(nh, pm_family, do_nl_req(fd, nh, off, sizeof(data)));
+	return 0;
+}
+
+int flush_addrs(int fd, int pm_family, int argc, char *argv[])
+{
+	char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+		  NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+		  1024];
+	struct nlmsghdr *nh;
+	int off = 0;
+
+	memset(data, 0, sizeof(data));
+	nh = (void *)data;
+	off = init_genl_req(data, pm_family, MPTCP_PM_CMD_FLUSH_ADDRS,
+			    MPTCP_PM_VER);
+
+	do_nl_req(fd, nh, off, 0);
+	return 0;
+}
+
+static void print_limits(struct nlmsghdr *nh, int pm_family, int total_len)
+{
+	struct rtattr *attrs;
+	uint32_t max;
+
+	for (; NLMSG_OK(nh, total_len); nh = NLMSG_NEXT(nh, total_len)) {
+		int len = nh->nlmsg_len;
+
+		if (nh->nlmsg_type == NLMSG_DONE)
+			break;
+		if (nh->nlmsg_type == NLMSG_ERROR)
+			nl_error(nh);
+		if (nh->nlmsg_type != pm_family)
+			continue;
+
+		len -= NLMSG_LENGTH(GENL_HDRLEN);
+		attrs = (struct rtattr *) ((char *) NLMSG_DATA(nh) +
+					   GENL_HDRLEN);
+		while (RTA_OK(attrs, len)) {
+			int type = attrs->rta_type;
+
+			if (type != MPTCP_PM_ATTR_RCV_ADD_ADDRS &&
+			    type != MPTCP_PM_ATTR_SUBFLOWS)
+				goto next;
+
+			memcpy(&max, RTA_DATA(attrs), 4);
+			printf("%s %u\n", type == MPTCP_PM_ATTR_SUBFLOWS ?
+					  "subflows" : "accept", max);
+
+next:
+			attrs = RTA_NEXT(attrs, len);
+		}
+	}
+}
+
+int get_set_limits(int fd, int pm_family, int argc, char *argv[])
+{
+	char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) +
+		  NLMSG_ALIGN(sizeof(struct genlmsghdr)) +
+		  1024];
+	uint32_t rcv_addr = 0, subflows = 0;
+	int cmd, len = sizeof(data);
+	struct nlmsghdr *nh;
+	int off = 0;
+
+	/* limit */
+	if (argc == 4) {
+		rcv_addr = atoi(argv[2]);
+		subflows = atoi(argv[3]);
+		cmd = MPTCP_PM_CMD_SET_LIMITS;
+	} else {
+		cmd = MPTCP_PM_CMD_GET_LIMITS;
+	}
+
+	memset(data, 0, sizeof(data));
+	nh = (void *)data;
+	off = init_genl_req(data, pm_family, cmd, MPTCP_PM_VER);
+
+	/* limit */
+	if (cmd == MPTCP_PM_CMD_SET_LIMITS) {
+		struct rtattr *rta = (void *)(data + off);
+
+		rta->rta_type = MPTCP_PM_ATTR_RCV_ADD_ADDRS;
+		rta->rta_len = RTA_LENGTH(4);
+		memcpy(RTA_DATA(rta), &rcv_addr, 4);
+		off += NLMSG_ALIGN(rta->rta_len);
+
+		rta = (void *)(data + off);
+		rta->rta_type = MPTCP_PM_ATTR_SUBFLOWS;
+		rta->rta_len = RTA_LENGTH(4);
+		memcpy(RTA_DATA(rta), &subflows, 4);
+		off += NLMSG_ALIGN(rta->rta_len);
+
+		/* do not expect a reply */
+		len = 0;
+	}
+
+	len = do_nl_req(fd, nh, off, len);
+	if (cmd == MPTCP_PM_CMD_GET_LIMITS)
+		print_limits(nh, pm_family, len);
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	int fd, pm_family;
+
+	if (argc < 2)
+		syntax(argv);
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
+	if (fd == -1)
+		error(1, errno, "socket netlink");
+
+	pm_family = resolve_mptcp_pm_netlink(fd);
+
+	if (!strcmp(argv[1], "add"))
+		return add_addr(fd, pm_family, argc, argv);
+	else if (!strcmp(argv[1], "del"))
+		return del_addr(fd, pm_family, argc, argv);
+	else if (!strcmp(argv[1], "flush"))
+		return flush_addrs(fd, pm_family, argc, argv);
+	else if (!strcmp(argv[1], "get"))
+		return get_addr(fd, pm_family, argc, argv);
+	else if (!strcmp(argv[1], "dump"))
+		return dump_addrs(fd, pm_family, argc, argv);
+	else if (!strcmp(argv[1], "limits"))
+		return get_set_limits(fd, pm_family, argc, argv);
+
+	fprintf(stderr, "unknown sub-command: %s", argv[1]);
+	syntax(argv);
+	return 0;
+}
diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings
new file mode 100644
index 000000000..026384c18
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/settings
@@ -0,0 +1 @@
+timeout=450
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
new file mode 100755
index 000000000..b51afba24
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -0,0 +1,297 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(dirname "${0}")/mptcp_lib.sh"
+
+rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+ns1="ns1-$rndh"
+ns2="ns2-$rndh"
+ns3="ns3-$rndh"
+capture=false
+ksft_skip=4
+timeout=30
+test_cnt=1
+ret=0
+bail=0
+
+usage() {
+	echo "Usage: $0 [ -b ] [ -c ] [ -d ]"
+	echo -e "\t-b: bail out after first error, otherwise runs al testcases"
+	echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
+	echo -e "\t-d: debug this script"
+}
+
+cleanup()
+{
+	rm -f "$cout" "$sout"
+	rm -f "$large" "$small"
+	rm -f "$capout"
+
+	local netns
+	for netns in "$ns1" "$ns2" "$ns3";do
+		ip netns del $netns
+	done
+}
+
+mptcp_lib_check_mptcp
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+#  "$ns1"              ns2                    ns3
+#     ns1eth1    ns2eth1   ns2eth3      ns3eth1
+#            netem
+#     ns1eth2    ns2eth2
+#            netem
+
+setup()
+{
+	large=$(mktemp)
+	small=$(mktemp)
+	sout=$(mktemp)
+	cout=$(mktemp)
+	capout=$(mktemp)
+	size=$((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=$((size / 4096)) >/dev/null 2>&1
+
+	trap cleanup EXIT
+
+	for i in "$ns1" "$ns2" "$ns3";do
+		ip netns add $i || exit $ksft_skip
+		ip -net $i link set lo up
+	done
+
+	ip link add ns1eth1 netns "$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
+	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 "$ns1" link set ns1eth2 up mtu 1500
+	ip -net "$ns1" route add default via 10.0.2.2 metric 101
+	ip -net "$ns1" route add default via dead:beef:2::2 metric 101
+
+	ip netns exec "$ns1" ./pm_nl_ctl limits 1 1
+	ip netns exec "$ns1" ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags subflow
+	ip netns exec "$ns1" sysctl -q net.ipv4.conf.all.rp_filter=0
+
+	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 "$ns2" link set ns2eth1 up mtu 1500
+
+	ip -net "$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
+
+	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 "$ns2" link set ns2eth3 up mtu 1500
+	ip netns exec "$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
+	ip -net "$ns3" route add default via 10.0.3.2
+	ip -net "$ns3" route add default via dead:beef:3::2
+
+	ip netns exec "$ns3" ./pm_nl_ctl limits 1 1
+}
+
+# $1: ns, $2: port
+wait_local_port_listen()
+{
+	local listener_ns="${1}"
+	local port="${2}"
+
+	local port_hex i
+
+	port_hex="$(printf "%04X" "${port}")"
+	for i in $(seq 10); do
+		ip netns exec "${listener_ns}" cat /proc/net/tcp* | \
+			awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
+			break
+		sleep 0.1
+	done
+}
+
+do_transfer()
+{
+	local cin=$1
+	local sin=$2
+	local max_time=$3
+	local port
+	port=$((10000+$test_cnt))
+	test_cnt=$((test_cnt+1))
+
+	:> "$cout"
+	:> "$sout"
+	:> "$capout"
+
+	local addr_port
+	addr_port=$(printf "%s:%d" ${connect_addr} ${port})
+
+	if $capture; then
+		local capuser
+		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
+
+	ip netns exec ${ns3} ./mptcp_connect -jt $timeout -l -p $port 0.0.0.0 < "$sin" > "$sout" &
+	local spid=$!
+
+	wait_local_port_listen "${ns3}" "${port}"
+
+	local start
+	start=$(date +%s%3N)
+	ip netns exec ${ns1} ./mptcp_connect -jt $timeout -p $port 10.0.3.3 < "$cin" > "$cout" &
+	local cpid=$!
+
+	wait $cpid
+	local retc=$?
+	wait $spid
+	local rets=$?
+
+	local stop
+	stop=$(date +%s%3N)
+
+	if $capture; then
+		sleep 1
+		kill ${cappid_listener}
+		kill ${cappid_connector}
+	fi
+
+	local duration
+	duration=$((stop-start))
+
+	cmp $sin $cout > /dev/null 2>&1
+	local cmps=$?
+	cmp $cin $sout > /dev/null 2>&1
+	local cmpc=$?
+
+	printf "%16s" "$duration max $max_time "
+	if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \
+	   [ $cmpc -eq 0 ] && [ $cmps -eq 0 ] && \
+	   [ $duration -lt $max_time ]; then
+		echo "[ OK ]"
+		cat "$capout"
+		return 0
+	fi
+
+	echo " [ fail ]"
+	echo "client exit code $retc, server $rets" 1>&2
+	echo -e "\nnetns ${ns3} socket stat for $port:" 1>&2
+	ip netns exec ${ns3} ss -nita 1>&2 -o "sport = :$port"
+	echo -e "\nnetns ${ns1} socket stat for $port:" 1>&2
+	ip netns exec ${ns1} ss -nita 1>&2 -o "dport = :$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=$4
+	local lret
+	local dev
+	shift 4
+	local msg=$*
+
+	[ $delay1 -gt 0 ] && delay1="delay $delay1" || delay1=""
+	[ $delay2 -gt 0 ] && delay2="delay $delay2" || 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
+	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1
+	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2
+	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1
+	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2
+
+	# time is measure in ms
+	local time=$((size * 8 * 1000 / (( $rate1 + $rate2) * 1024 *1024) ))
+
+	# mptcp_connect will do some sleeps to allow the mp_join handshake
+	# completion
+	time=$((time + 1350))
+
+	printf "%-50s" "$msg"
+	do_transfer $small $large $((time * 11 / 10))
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		[ $bail -eq 0 ] || exit $ret
+	fi
+
+	printf "%-50s" "$msg - reverse direction"
+	do_transfer $large $small $((time * 11 / 10))
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		[ $bail -eq 0 ] || exit $ret
+	fi
+}
+
+while getopts "bcdh" option;do
+	case "$option" in
+	"h")
+		usage $0
+		exit 0
+		;;
+	"b")
+		bail=1
+		;;
+	"c")
+		capture=true
+		;;
+	"d")
+		set -x
+		;;
+	"?")
+		usage $0
+		exit 1
+		;;
+	esac
+done
+
+setup
+run_test 10 10 0 0 "balanced bwidth"
+run_test 10 10 1 50 "balanced bwidth with unbalanced delay"
+
+# we still need some additional infrastructure to pass the following test-cases
+# run_test 30 10 0 0 "unbalanced bwidth"
+# run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay"
+# run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay"
+exit $ret