9 files changed, 1262 insertions, 152 deletions

diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
index 7569d892967a..49daae73c41e 100644
--- a/tools/testing/selftests/net/mptcp/.gitignore
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 mptcp_connect
+mptcp_inq
 mptcp_sockopt
 pm_nl_ctl
 *.pcap
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index bbf4e448bad9..0356c4501c99 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -8,7 +8,7 @@ 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 mptcp_sockopt.sh
 
-TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt
+TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index 0faaccd21447..d36b7da5082a 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -9,9 +9,13 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NETFILTER_NETLINK=m
 CONFIG_NF_TABLES=m
-CONFIG_NFT_COUNTER=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XTABLES=m
 CONFIG_NETFILTER_XT_MATCH_BPF=m
-CONFIG_NF_TABLES_IPV4=y
-CONFIG_NF_TABLES_IPV6=y
+CONFIG_NF_TABLES_INET=y
+CONFIG_NFT_TPROXY=m
+CONFIG_NFT_SOCKET=m
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IPV6_MULTIPLE_TABLES=y
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 95e81d557b08..8628aa61b763 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -16,6 +16,7 @@
 #include <unistd.h>
 #include <time.h>
 
+#include <sys/ioctl.h>
 #include <sys/poll.h>
 #include <sys/sendfile.h>
 #include <sys/stat.h>
@@ -28,6 +29,7 @@
 
 #include <linux/tcp.h>
 #include <linux/time_types.h>
+#include <linux/sockios.h>
 
 extern int optind;
 
@@ -59,7 +61,6 @@ static enum cfg_peek cfg_peek = CFG_NONE_PEEK;
 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;
@@ -69,32 +70,56 @@ static unsigned int cfg_time;
 static unsigned int cfg_do_w;
 static int cfg_wait;
 static uint32_t cfg_mark;
+static char *cfg_input;
+static int cfg_repeat = 1;
 
 struct cfg_cmsg_types {
 	unsigned int cmsg_enabled:1;
 	unsigned int timestampns:1;
+	unsigned int tcp_inq:1;
 };
 
+struct cfg_sockopt_types {
+	unsigned int transparent:1;
+};
+
+struct tcp_inq_state {
+	unsigned int last;
+	bool expect_eof;
+};
+
+static struct tcp_inq_state tcp_inq;
+
 static struct cfg_cmsg_types cfg_cmsg_types;
+static struct cfg_sockopt_types cfg_sockopt_types;
 
 static void die_usage(void)
 {
-	fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]"
-		"[-l] [-w sec] [-t num] [-T num] connect_address\n");
+	fprintf(stderr, "Usage: mptcp_connect [-6] [-c cmsg] [-i file] [-I num] [-j] [-l] "
+		"[-m mode] [-M mark] [-o option] [-p port] [-P mode] [-j] [-l] [-r num] "
+		"[-s MPTCP|TCP] [-S num] [-r num] [-t num] [-T num] [-u] [-w sec] connect_address\n");
 	fprintf(stderr, "\t-6 use ipv6\n");
+	fprintf(stderr, "\t-c cmsg -- test cmsg type <cmsg>\n");
+	fprintf(stderr, "\t-i file -- read the data to send from the given file instead of stdin");
+	fprintf(stderr, "\t-I num -- repeat the transfer 'num' times. In listen mode accepts num "
+		"incoming connections, in client mode, disconnect and reconnect to the server\n");
+	fprintf(stderr, "\t-j     -- add additional sleep at connection start and tear down "
+		"-- for MPJ tests\n");
+	fprintf(stderr, "\t-l     -- listens mode, accepts incoming connection\n");
+	fprintf(stderr, "\t-m [poll|mmap|sendfile] -- use poll(default)/mmap+write/sendfile\n");
+	fprintf(stderr, "\t-M mark -- set socket packet mark\n");
+	fprintf(stderr, "\t-o option -- test sockopt <option>\n");
+	fprintf(stderr, "\t-p num -- use port num\n");
+	fprintf(stderr,
+		"\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n");
 	fprintf(stderr, "\t-t num -- set poll timeout to num\n");
 	fprintf(stderr, "\t-T num -- set expected runtime to num ms\n");
-	fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n");
+	fprintf(stderr, "\t-r num -- enable slow mode, limiting each write to num bytes "
+		"-- for remove addr tests\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-M mark -- set socket packet mark\n");
-	fprintf(stderr, "\t-u -- check mptcp ulp\n");
+	fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n");
 	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
-	fprintf(stderr, "\t-c cmsg -- test cmsg type <cmsg>\n");
-	fprintf(stderr,
-		"\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n");
 	exit(1);
 }
 
@@ -185,6 +210,58 @@ static void set_mark(int fd, uint32_t mark)
 	}
 }
 
+static void set_transparent(int fd, int pf)
+{
+	int one = 1;
+
+	switch (pf) {
+	case AF_INET:
+		if (-1 == setsockopt(fd, SOL_IP, IP_TRANSPARENT, &one, sizeof(one)))
+			perror("IP_TRANSPARENT");
+		break;
+	case AF_INET6:
+		if (-1 == setsockopt(fd, IPPROTO_IPV6, IPV6_TRANSPARENT, &one, sizeof(one)))
+			perror("IPV6_TRANSPARENT");
+		break;
+	}
+}
+
+static int do_ulp_so(int sock, const char *name)
+{
+	return setsockopt(sock, IPPROTO_TCP, TCP_ULP, name, strlen(name));
+}
+
+#define X(m)	xerror("%s:%u: %s: failed for proto %d at line %u", __FILE__, __LINE__, (m), proto, line)
+static void sock_test_tcpulp(int sock, int proto, unsigned int line)
+{
+	socklen_t buflen = 8;
+	char buf[8] = "";
+	int ret = getsockopt(sock, IPPROTO_TCP, TCP_ULP, buf, &buflen);
+
+	if (ret != 0)
+		X("getsockopt");
+
+	if (buflen > 0) {
+		if (strcmp(buf, "mptcp") != 0)
+			xerror("unexpected ULP '%s' for proto %d at line %u", buf, proto, line);
+		ret = do_ulp_so(sock, "tls");
+		if (ret == 0)
+			X("setsockopt");
+	} else if (proto == IPPROTO_MPTCP) {
+		ret = do_ulp_so(sock, "tls");
+		if (ret != -1)
+			X("setsockopt");
+	}
+
+	ret = do_ulp_so(sock, "mptcp");
+	if (ret != -1)
+		X("setsockopt");
+
+#undef X
+}
+
+#define SOCK_TEST_TCPULP(s, p) sock_test_tcpulp((s), (p), __LINE__)
+
 static int sock_listen_mptcp(const char * const listenaddr,
 			     const char * const port)
 {
@@ -208,10 +285,15 @@ static int sock_listen_mptcp(const char * const listenaddr,
 		if (sock < 0)
 			continue;
 
+		SOCK_TEST_TCPULP(sock, cfg_sock_proto);
+
 		if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one,
 				     sizeof(one)))
 			perror("setsockopt");
 
+		if (cfg_sockopt_types.transparent)
+			set_transparent(sock, pf);
+
 		if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
 			break; /* success */
 
@@ -227,54 +309,22 @@ static int sock_listen_mptcp(const char * const listenaddr,
 		return sock;
 	}
 
+	SOCK_TEST_TCPULP(sock, cfg_sock_proto);
+
 	if (listen(sock, 20)) {
 		perror("listen");
 		close(sock);
 		return -1;
 	}
 
-	return sock;
-}
+	SOCK_TEST_TCPULP(sock, cfg_sock_proto);
 
-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;
+	return sock;
 }
 
 static int sock_connect_mptcp(const char * const remoteaddr,
-			      const char * const port, int proto)
+			      const char * const port, int proto,
+			      struct addrinfo **peer)
 {
 	struct addrinfo hints = {
 		.ai_protocol = IPPROTO_TCP,
@@ -293,11 +343,15 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 			continue;
 		}
 
+		SOCK_TEST_TCPULP(sock, proto);
+
 		if (cfg_mark)
 			set_mark(sock, cfg_mark);
 
-		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
+		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0) {
+			*peer = a;
 			break; /* success */
+		}
 
 		perror("connect()");
 		close(sock);
@@ -305,6 +359,8 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 	}
 
 	freeaddrinfo(addr);
+	if (sock != -1)
+		SOCK_TEST_TCPULP(sock, proto);
 	return sock;
 }
 
@@ -364,7 +420,9 @@ static size_t do_write(const int fd, char *buf, const size_t len)
 static void process_cmsg(struct msghdr *msgh)
 {
 	struct __kernel_timespec ts;
+	bool inq_found = false;
 	bool ts_found = false;
+	unsigned int inq = 0;
 	struct cmsghdr *cmsg;
 
 	for (cmsg = CMSG_FIRSTHDR(msgh); cmsg ; cmsg = CMSG_NXTHDR(msgh, cmsg)) {
@@ -373,12 +431,27 @@ static void process_cmsg(struct msghdr *msgh)
 			ts_found = true;
 			continue;
 		}
+		if (cmsg->cmsg_level == IPPROTO_TCP && cmsg->cmsg_type == TCP_CM_INQ) {
+			memcpy(&inq, CMSG_DATA(cmsg), sizeof(inq));
+			inq_found = true;
+			continue;
+		}
+
 	}
 
 	if (cfg_cmsg_types.timestampns) {
 		if (!ts_found)
 			xerror("TIMESTAMPNS not present\n");
 	}
+
+	if (cfg_cmsg_types.tcp_inq) {
+		if (!inq_found)
+			xerror("TCP_INQ not present\n");
+
+		if (inq > 1024)
+			xerror("tcp_inq %u is larger than one kbyte\n", inq);
+		tcp_inq.last = inq;
+	}
 }
 
 static ssize_t do_recvmsg_cmsg(const int fd, char *buf, const size_t len)
@@ -395,10 +468,23 @@ static ssize_t do_recvmsg_cmsg(const int fd, char *buf, const size_t len)
 		.msg_controllen = sizeof(msg_buf),
 	};
 	int flags = 0;
+	unsigned int last_hint = tcp_inq.last;
 	int ret = recvmsg(fd, &msg, flags);
 
-	if (ret <= 0)
+	if (ret <= 0) {
+		if (ret == 0 && tcp_inq.expect_eof)
+			return ret;
+
+		if (ret == 0 && cfg_cmsg_types.tcp_inq)
+			if (last_hint != 1 && last_hint != 0)
+				xerror("EOF but last tcp_inq hint was %u\n", last_hint);
+
 		return ret;
+	}
+
+	if (tcp_inq.expect_eof)
+		xerror("expected EOF, last_hint %u, now %u\n",
+		       last_hint, tcp_inq.last);
 
 	if (msg.msg_controllen && !cfg_cmsg_types.cmsg_enabled)
 		xerror("got %lu bytes of cmsg data, expected 0\n",
@@ -410,6 +496,19 @@ static ssize_t do_recvmsg_cmsg(const int fd, char *buf, const size_t len)
 	if (msg.msg_controllen)
 		process_cmsg(&msg);
 
+	if (cfg_cmsg_types.tcp_inq) {
+		if ((size_t)ret < len && last_hint > (unsigned int)ret) {
+			if (ret + 1 != (int)last_hint) {
+				int next = read(fd, msg_buf, sizeof(msg_buf));
+
+				xerror("read %u of %u, last_hint was %u tcp_inq hint now %u next_read returned %d/%m\n",
+				       ret, (unsigned int)len, last_hint, tcp_inq.last, next);
+			} else {
+				tcp_inq.expect_eof = true;
+			}
+		}
+	}
+
 	return ret;
 }
 
@@ -441,14 +540,17 @@ static ssize_t do_rnd_read(const int fd, char *buf, const size_t len)
 	return ret;
 }
 
-static void set_nonblock(int fd)
+static void set_nonblock(int fd, bool nonblock)
 {
 	int flags = fcntl(fd, F_GETFL);
 
 	if (flags == -1)
 		return;
 
-	fcntl(fd, F_SETFL, flags | O_NONBLOCK);
+	if (nonblock)
+		fcntl(fd, F_SETFL, flags | O_NONBLOCK);
+	else
+		fcntl(fd, F_SETFL, flags & ~O_NONBLOCK);
 }
 
 static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after_out)
@@ -460,7 +562,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after
 	unsigned int woff = 0, wlen = 0;
 	char wbuf[8192];
 
-	set_nonblock(peerfd);
+	set_nonblock(peerfd, true);
 
 	for (;;) {
 		char rbuf[8192];
@@ -555,7 +657,6 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after
 	if (cfg_remove)
 		usleep(cfg_wait);
 
-	close(peerfd);
 	return 0;
 }
 
@@ -697,7 +798,7 @@ static int copyfd_io_sendfile(int infd, int peerfd, int outfd,
 	return err;
 }
 
-static int copyfd_io(int infd, int peerfd, int outfd)
+static int copyfd_io(int infd, int peerfd, int outfd, bool close_peerfd)
 {
 	bool in_closed_after_out = false;
 	struct timespec start, end;
@@ -736,6 +837,9 @@ static int copyfd_io(int infd, int peerfd, int outfd)
 	if (ret)
 		return ret;
 
+	if (close_peerfd)
+		close(peerfd);
+
 	if (cfg_time) {
 		unsigned int delta_ms;
 
@@ -847,7 +951,7 @@ static void maybe_close(int fd)
 {
 	unsigned int r = rand();
 
-	if (!(cfg_join || cfg_remove) && (r & 1))
+	if (!(cfg_join || cfg_remove || cfg_repeat > 1) && (r & 1))
 		close(fd);
 }
 
@@ -857,7 +961,9 @@ int main_loop_s(int listensock)
 	struct pollfd polls;
 	socklen_t salen;
 	int remotesock;
+	int fd = 0;
 
+again:
 	polls.fd = listensock;
 	polls.events = POLLIN;
 
@@ -878,12 +984,27 @@ int main_loop_s(int listensock)
 		check_sockaddr(pf, &ss, salen);
 		check_getpeername(remotesock, &ss, salen);
 
-		return copyfd_io(0, remotesock, 1);
+		if (cfg_input) {
+			fd = open(cfg_input, O_RDONLY);
+			if (fd < 0)
+				xerror("can't open %s: %d", cfg_input, errno);
+		}
+
+		SOCK_TEST_TCPULP(remotesock, 0);
+
+		copyfd_io(fd, remotesock, 1, true);
+	} else {
+		perror("accept");
+		return 1;
 	}
 
-	perror("accept");
+	if (--cfg_repeat > 0) {
+		if (cfg_input)
+			close(fd);
+		goto again;
+	}
 
-	return 1;
+	return 0;
 }
 
 static void init_rng(void)
@@ -919,6 +1040,8 @@ static void apply_cmsg_types(int fd, const struct cfg_cmsg_types *cmsg)
 
 	if (cmsg->timestampns)
 		xsetsockopt(fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW, &on, sizeof(on));
+	if (cmsg->tcp_inq)
+		xsetsockopt(fd, IPPROTO_TCP, TCP_INQ, &on, sizeof(on));
 }
 
 static void parse_cmsg_types(const char *type)
@@ -940,21 +1063,81 @@ static void parse_cmsg_types(const char *type)
 		return;
 	}
 
+	if (strncmp(type, "TCPINQ", len) == 0) {
+		cfg_cmsg_types.tcp_inq = 1;
+		return;
+	}
+
 	fprintf(stderr, "Unrecognized cmsg option %s\n", type);
 	exit(1);
 }
 
+static void parse_setsock_options(const char *name)
+{
+	char *next = strchr(name, ',');
+	unsigned int len = 0;
+
+	if (next) {
+		parse_setsock_options(next + 1);
+		len = next - name;
+	} else {
+		len = strlen(name);
+	}
+
+	if (strncmp(name, "TRANSPARENT", len) == 0) {
+		cfg_sockopt_types.transparent = 1;
+		return;
+	}
+
+	fprintf(stderr, "Unrecognized setsockopt option %s\n", name);
+	exit(1);
+}
+
+void xdisconnect(int fd, int addrlen)
+{
+	struct sockaddr_storage empty;
+	int msec_sleep = 10;
+	int queued = 1;
+	int i;
+
+	shutdown(fd, SHUT_WR);
+
+	/* while until the pending data is completely flushed, the later
+	 * disconnect will bypass/ignore/drop any pending data.
+	 */
+	for (i = 0; ; i += msec_sleep) {
+		if (ioctl(fd, SIOCOUTQ, &queued) < 0)
+			xerror("can't query out socket queue: %d", errno);
+
+		if (!queued)
+			break;
+
+		if (i > poll_timeout)
+			xerror("timeout while waiting for spool to complete");
+		usleep(msec_sleep * 1000);
+	}
+
+	memset(&empty, 0, sizeof(empty));
+	empty.ss_family = AF_UNSPEC;
+	if (connect(fd, (struct sockaddr *)&empty, addrlen) < 0)
+		xerror("can't disconnect: %d", errno);
+}
+
 int main_loop(void)
 {
-	int fd;
+	int fd, ret, fd_in = 0;
+	struct addrinfo *peer;
 
 	/* listener is ready. */
-	fd = sock_connect_mptcp(cfg_host, cfg_port, cfg_sock_proto);
+	fd = sock_connect_mptcp(cfg_host, cfg_port, cfg_sock_proto, &peer);
 	if (fd < 0)
 		return 2;
 
+again:
 	check_getpeername_connect(fd);
 
+	SOCK_TEST_TCPULP(fd, cfg_sock_proto);
+
 	if (cfg_rcvbuf)
 		set_rcvbuf(fd, cfg_rcvbuf);
 	if (cfg_sndbuf)
@@ -962,7 +1145,31 @@ int main_loop(void)
 	if (cfg_cmsg_types.cmsg_enabled)
 		apply_cmsg_types(fd, &cfg_cmsg_types);
 
-	return copyfd_io(0, fd, 1);
+	if (cfg_input) {
+		fd_in = open(cfg_input, O_RDONLY);
+		if (fd < 0)
+			xerror("can't open %s:%d", cfg_input, errno);
+	}
+
+	/* close the client socket open only if we are not going to reconnect */
+	ret = copyfd_io(fd_in, fd, 1, cfg_repeat == 1);
+	if (ret)
+		return ret;
+
+	if (--cfg_repeat > 0) {
+		xdisconnect(fd, peer->ai_addrlen);
+
+		/* the socket could be unblocking at this point, we need the
+		 * connect to be blocking
+		 */
+		set_nonblock(fd, false);
+		if (connect(fd, peer->ai_addr, peer->ai_addrlen))
+			xerror("can't reconnect: %d", errno);
+		if (cfg_input)
+			close(fd_in);
+		goto again;
+	}
+	return 0;
 }
 
 int parse_proto(const char *proto)
@@ -1047,7 +1254,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jr:lp:s:hut:T:m:S:R:w:M:P:c:")) != -1) {
+	while ((c = getopt(argc, argv, "6c:hi:I:jlm:M:o:p:P:r:R:s:S:t:T:w:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
@@ -1061,6 +1268,12 @@ static void parse_opts(int argc, char **argv)
 			if (cfg_do_w <= 0)
 				cfg_do_w = 50;
 			break;
+		case 'i':
+			cfg_input = optarg;
+			break;
+		case 'I':
+			cfg_repeat = atoi(optarg);
+			break;
 		case 'l':
 			listen_mode = true;
 			break;
@@ -1073,9 +1286,6 @@ static void parse_opts(int argc, char **argv)
 		case 'h':
 			die_usage();
 			break;
-		case 'u':
-			tcpulp_audit = true;
-			break;
 		case '6':
 			pf = AF_INET6;
 			break;
@@ -1108,6 +1318,9 @@ static void parse_opts(int argc, char **argv)
 		case 'c':
 			parse_cmsg_types(optarg);
 			break;
+		case 'o':
+			parse_setsock_options(optarg);
+			break;
 		}
 	}
 
@@ -1126,9 +1339,6 @@ int main(int argc, char *argv[])
 	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);
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 559173a8e387..cb5809b89081 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -7,6 +7,7 @@ optstring="S:R:d:e:l:r:h4cm:f:tC"
 ret=0
 sin=""
 sout=""
+cin_disconnect=""
 cin=""
 cout=""
 ksft_skip=4
@@ -24,6 +25,7 @@ options_log=true
 do_tcp=0
 checksum=false
 filesize=0
+connect_per_transfer=1
 
 if [ $tc_loss -eq 100 ];then
 	tc_loss=1%
@@ -127,6 +129,7 @@ TEST_COUNT=0
 
 cleanup()
 {
+	rm -f "$cin_disconnect" "$cout_disconnect"
 	rm -f "$cin" "$cout"
 	rm -f "$sin" "$sout"
 	rm -f "$capout"
@@ -149,6 +152,8 @@ sout=$(mktemp)
 cin=$(mktemp)
 cout=$(mktemp)
 capout=$(mktemp)
+cin_disconnect="$cin".disconnect
+cout_disconnect="$cout".disconnect
 trap cleanup EXIT
 
 for i in "$ns1" "$ns2" "$ns3" "$ns4";do
@@ -296,24 +301,6 @@ check_mptcp_disabled()
 	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
-}
-
 # $1: IP address
 is_v6()
 {
@@ -518,8 +505,8 @@ do_transfer()
 	cookies=${cookies##*=}
 
 	if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then
-		expect_synrx=$((stat_synrx_last_l+1))
-		expect_ackrx=$((stat_ackrx_last_l+1))
+		expect_synrx=$((stat_synrx_last_l+$connect_per_transfer))
+		expect_ackrx=$((stat_ackrx_last_l+$connect_per_transfer))
 	fi
 
 	if [ ${stat_synrx_now_l} -lt ${expect_synrx} ]; then
@@ -671,6 +658,82 @@ 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=""
+
+	# skip if we don't want v6
+	if ! $ipv6 && is_v6 "${connect_addr}"; then
+		return 0
+	fi
+
+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
+	if [ $? -ne 0 ]; then
+		echo "SKIP: $msg, could not load nft ruleset"
+		return
+	fi
+
+	local local_addr
+	if is_v6 "${connect_addr}"; then
+		local_addr="::"
+		r6flag="-6"
+	else
+		local_addr="0.0.0.0"
+	fi
+
+	ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100
+	if [ $? -ne 0 ]; then
+		ip netns exec "$listener_ns" nft flush ruleset
+		echo "SKIP: $msg, ip $r6flag rule failed"
+		return
+	fi
+
+	ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100
+	if [ $? -ne 0 ]; then
+		ip netns exec "$listener_ns" nft flush ruleset
+		ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100
+		echo "SKIP: $msg, ip route add local $local_addr failed"
+		return
+	fi
+
+	echo "INFO: test $msg"
+
+	TEST_COUNT=10000
+	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
+		echo "FAIL: $msg, mptcp connection error" 1>&2
+		ret=$lret
+		return 1
+	fi
+
+	echo "PASS: $msg"
+	return 0
+}
+
 run_tests_peekmode()
 {
 	local peekmode="$1"
@@ -680,6 +743,33 @@ run_tests_peekmode()
 	run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-P ${peekmode}"
 }
 
+run_tests_disconnect()
+{
+	local peekmode="$1"
+	local old_cin=$cin
+	local old_sin=$sin
+
+	cat $cin $cin $cin > "$cin".disconnect
+
+	# force do_transfer to cope with the multiple tranmissions
+	sin="$cin.disconnect"
+	sin_disconnect=$old_sin
+	cin="$cin.disconnect"
+	cin_disconnect="$old_cin"
+	connect_per_transfer=3
+
+	echo "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 $old_cin"
+
+	# restore previous status
+	cout=$old_cout
+	cout_disconnect="$cout".disconnect
+	cin=$old_cin
+	cin_disconnect="$cin".disconnect
+	connect_per_transfer=1
+}
+
 display_time()
 {
 	time_end=$(date +%s)
@@ -704,8 +794,6 @@ make_file "$sin" "server"
 
 check_mptcp_disabled
 
-check_mptcp_ulp_setsockopt
-
 stop_if_error "The kernel configuration is not valid for MPTCP"
 
 echo "INFO: validating network environment with pings"
@@ -794,5 +882,12 @@ run_tests_peekmode "saveWithPeek"
 run_tests_peekmode "saveAfterPeek"
 stop_if_error "Tests with peek mode 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"
+stop_if_error "Tests with tproxy have failed"
+
+run_tests_disconnect
+
 display_time
 exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
new file mode 100644
index 000000000000..29f75e2a1116
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -0,0 +1,602 @@
+// 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/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>
+
+#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 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 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,
+			 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 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, 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_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)
+			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);
+
+	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)
+{
+	int fd = open("/dev/urandom", O_RDONLY);
+	unsigned int foo;
+
+	if (fd > 0) {
+		int ret = read(fd, &foo, sizeof(foo));
+
+		if (ret < 0)
+			srand(fd + foo);
+		close(fd);
+	}
+
+	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)
+		return server(unixfds[1]);
+
+	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;
+}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 7ef639a9d4a6..27d0eb9afdca 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -238,6 +238,45 @@ is_v6()
 	[ -z "${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 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
+			break
+		sleep 0.1
+	done
+}
+
+rm_addr_count()
+{
+	ns=${1}
+
+	ip netns exec ${ns} nstat -as | grep MPTcpExtRmAddr | awk '{print $2}'
+}
+
+# $1: ns, $2: old rm_addr counter in $ns
+wait_rm_addr()
+{
+	local ns="${1}"
+	local old_cnt="${2}"
+	local cnt
+	local i
+
+	for i in $(seq 10); do
+		cnt=$(rm_addr_count ${ns})
+		[ "$cnt" = "${old_cnt}" ] || break
+		sleep 0.1
+	done
+}
+
 do_transfer()
 {
 	listener_ns="$1"
@@ -307,7 +346,7 @@ do_transfer()
 	fi
 	spid=$!
 
-	sleep 1
+	wait_local_port_listen "${listener_ns}" "${port}"
 
 	if [ "$test_link_fail" -eq 0 ];then
 		timeout ${timeout_test} \
@@ -324,10 +363,13 @@ do_transfer()
 	fi
 	cpid=$!
 
+	# let the mptcp subflow be established in background before
+	# do endpoint manipulation
+	[ $addr_nr_ns1 = "0" -a $addr_nr_ns2 = "0" ] || sleep 1
+
 	if [ $addr_nr_ns1 -gt 0 ]; then
 		let add_nr_ns1=addr_nr_ns1
 		counter=2
-		sleep 1
 		while [ $add_nr_ns1 -gt 0 ]; do
 			local addr
 			if is_v6 "${connect_addr}"; then
@@ -339,7 +381,6 @@ do_transfer()
 			let counter+=1
 			let add_nr_ns1-=1
 		done
-		sleep 1
 	elif [ $addr_nr_ns1 -lt 0 ]; then
 		let rm_nr_ns1=-addr_nr_ns1
 		if [ $rm_nr_ns1 -lt 8 ]; then
@@ -347,22 +388,19 @@ do_transfer()
 			pos=1
 			dump=(`ip netns exec ${listener_ns} ./pm_nl_ctl dump`)
 			if [ ${#dump[@]} -gt 0 ]; then
-				sleep 1
-
 				while [ $counter -le $rm_nr_ns1 ]
 				do
 					id=${dump[$pos]}
+					rm_addr=$(rm_addr_count ${connector_ns})
 					ip netns exec ${listener_ns} ./pm_nl_ctl del $id
-					sleep 1
+					wait_rm_addr ${connector_ns} ${rm_addr}
 					let counter+=1
 					let pos+=5
 				done
 			fi
 		elif [ $rm_nr_ns1 -eq 8 ]; then
-			sleep 1
 			ip netns exec ${listener_ns} ./pm_nl_ctl flush
 		elif [ $rm_nr_ns1 -eq 9 ]; then
-			sleep 1
 			ip netns exec ${listener_ns} ./pm_nl_ctl del 0 ${connect_addr}
 		fi
 	fi
@@ -373,10 +411,13 @@ do_transfer()
 		addr_nr_ns2=${addr_nr_ns2:9}
 	fi
 
+	# if newly added endpoints must be deleted, give the background msk
+	# some time to created them
+	[ $addr_nr_ns1 -gt 0 -a $addr_nr_ns2 -lt 0 ] && sleep 1
+
 	if [ $addr_nr_ns2 -gt 0 ]; then
 		let add_nr_ns2=addr_nr_ns2
 		counter=3
-		sleep 1
 		while [ $add_nr_ns2 -gt 0 ]; do
 			local addr
 			if is_v6 "${connect_addr}"; then
@@ -388,7 +429,6 @@ do_transfer()
 			let counter+=1
 			let add_nr_ns2-=1
 		done
-		sleep 1
 	elif [ $addr_nr_ns2 -lt 0 ]; then
 		let rm_nr_ns2=-addr_nr_ns2
 		if [ $rm_nr_ns2 -lt 8 ]; then
@@ -396,19 +436,18 @@ do_transfer()
 			pos=1
 			dump=(`ip netns exec ${connector_ns} ./pm_nl_ctl dump`)
 			if [ ${#dump[@]} -gt 0 ]; then
-				sleep 1
-
 				while [ $counter -le $rm_nr_ns2 ]
 				do
+					# rm_addr are serialized, allow the previous one to complete
 					id=${dump[$pos]}
+					rm_addr=$(rm_addr_count ${listener_ns})
 					ip netns exec ${connector_ns} ./pm_nl_ctl del $id
-					sleep 1
+					wait_rm_addr ${listener_ns} ${rm_addr}
 					let counter+=1
 					let pos+=5
 				done
 			fi
 		elif [ $rm_nr_ns2 -eq 8 ]; then
-			sleep 1
 			ip netns exec ${connector_ns} ./pm_nl_ctl flush
 		elif [ $rm_nr_ns2 -eq 9 ]; then
 			local addr
@@ -417,7 +456,6 @@ do_transfer()
 			else
 				addr="10.0.1.2"
 			fi
-			sleep 1
 			ip netns exec ${connector_ns} ./pm_nl_ctl del 0 $addr
 		fi
 	fi
@@ -539,6 +577,14 @@ run_tests()
 	lret=$?
 }
 
+dump_stats()
+{
+	echo Server ns stats
+	ip netns exec $ns1 nstat -as | grep Tcp
+	echo Client ns stats
+	ip netns exec $ns2 nstat -as | grep Tcp
+}
+
 chk_csum_nr()
 {
 	local msg=${1:-""}
@@ -570,12 +616,7 @@ chk_csum_nr()
 	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 $ns2 nstat -as | grep MPTcp
-	fi
+	[ "${dump_stats}" = 1 ] && dump_stats
 }
 
 chk_fail_nr()
@@ -607,12 +648,7 @@ chk_fail_nr()
 		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 $ns2 nstat -as | grep MPTcp
-	fi
+	[ "${dump_stats}" = 1 ] && dump_stats
 }
 
 chk_join_nr()
@@ -656,12 +692,7 @@ chk_join_nr()
 	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 $ns2 nstat -as | grep MPTcp
-	fi
+	[ "${dump_stats}" = 1 ] && dump_stats
 	if [ $checksum -eq 1 ]; then
 		chk_csum_nr
 		chk_fail_nr 0 0
@@ -823,12 +854,7 @@ chk_add_nr()
 		echo ""
 	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 $ns2 nstat -as | grep MPTcp
-	fi
+	[ "${dump_stats}" = 1 ] && dump_stats
 }
 
 chk_rm_nr()
@@ -871,12 +897,7 @@ chk_rm_nr()
 		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 $ns2 nstat -as | grep MPTcp
-	fi
+	[ "${dump_stats}" = 1 ] && dump_stats
 }
 
 chk_prio_nr()
@@ -908,12 +929,7 @@ chk_prio_nr()
 		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 $ns2 nstat -as | grep MPTcp
-	fi
+	[ "${dump_stats}" = 1 ] && dump_stats
 }
 
 chk_link_usage()
@@ -937,6 +953,22 @@ chk_link_usage()
 	fi
 }
 
+wait_for_tw()
+{
+	local timeout_ms=$((timeout_poll * 1000))
+	local time=0
+	local ns=$1
+
+	while [ $time -lt $timeout_ms ]; do
+		local cnt=$(ip netns exec $ns ss -t state time-wait |wc -l)
+
+		[ "$cnt" = 1 ] && return 1
+		time=$((time + 100))
+		sleep 0.1
+	done
+	return 1
+}
+
 subflows_tests()
 {
 	reset
@@ -994,6 +1026,61 @@ subflows_tests()
 	chk_join_nr "single subflow, dev" 1 1 1
 }
 
+subflows_error_tests()
+{
+	# If a single subflow is configured, and matches the MPC src
+	# address, no additional subflow should be created
+	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 10.0.1.2 flags subflow
+	run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
+	chk_join_nr "no MPC reuse with single endpoint" 0 0 0
+
+	# multiple subflows, with subflow creation error
+	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
+	ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT
+	run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
+	chk_join_nr "multi subflows, with failing subflow" 1 1 1
+
+	# multiple subflows, with subflow timeout on MPJ
+	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
+	ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j DROP
+	run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
+	chk_join_nr "multi subflows, with subflow timeout" 1 1 1
+
+	# multiple subflows, check that the endpoint corresponding to
+	# closed subflow (due to reset) is not reused if additional
+	# subflows are added later
+	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
+	ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT
+	run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow &
+
+	# updates in the child shell do not have any effect here, we
+	# need to bump the test counter for the above case
+	TEST_COUNT=$((TEST_COUNT+1))
+
+	# mpj subflow will be in TW after the reset
+	wait_for_tw $ns2
+	ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+	wait
+
+	# additional subflow could be created only if the PM select
+	# the later endpoint, skipping the already used one
+	chk_join_nr "multi subflows, fair usage on close" 1 1 1
+}
+
 signal_address_tests()
 {
 	# add_address, unused
@@ -1071,7 +1158,10 @@ signal_address_tests()
 	ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal
 	ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal
 	run_tests $ns1 $ns2 10.0.1.1
-	chk_add_nr 4 4
+
+	# the server will not signal the address terminating
+	# the MPC subflow
+	chk_add_nr 3 3
 }
 
 link_failure_tests()
@@ -1577,7 +1667,7 @@ add_addr_ports_tests()
 	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 0 -8 -8 slow
+	run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow
 	chk_join_nr "flush subflows and signal with port" 3 3 3
 	chk_add_nr 1 1
 	chk_rm_nr 2 2
@@ -1802,6 +1892,7 @@ fullmesh_tests()
 all_tests()
 {
 	subflows_tests
+	subflows_error_tests
 	signal_address_tests
 	link_failure_tests
 	add_addr_timeout_tests
@@ -1821,6 +1912,7 @@ usage()
 {
 	echo "mptcp_join usage:"
 	echo "  -f subflows_tests"
+	echo "  -e subflows_error_tests"
 	echo "  -s signal_address_tests"
 	echo "  -l link_failure_tests"
 	echo "  -t add_addr_timeout_tests"
@@ -1869,11 +1961,14 @@ if [ $do_all_tests -eq 1 ]; then
 	exit $ret
 fi
 
-while getopts 'fsltra64bpkdmchCS' opt; do
+while getopts 'fesltra64bpkdmchCS' opt; do
 	case $opt in
 		f)
 			subflows_tests
 			;;
+		e)
+			subflows_error_tests
+			;;
 		s)
 			signal_address_tests
 			;;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index 417b11cafafe..ac9a4d9c1764 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -4,6 +4,7 @@
 
 #include <assert.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <limits.h>
 #include <string.h>
 #include <stdarg.h>
@@ -13,6 +14,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <strings.h>
+#include <time.h>
 #include <unistd.h>
 
 #include <sys/socket.h>
@@ -594,6 +596,44 @@ static int server(int pipefd)
 	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;
@@ -611,6 +651,8 @@ static int client(int pipefd)
 		xerror("Unknown pf %d\n", pf);
 	}
 
+	test_ip_tos_sockopt(fd);
+
 	connect_one_server(fd, pipefd);
 
 	return 0;
@@ -642,6 +684,25 @@ static int rcheck(int wstatus, const char *what)
 	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;
@@ -650,6 +711,8 @@ int main(int argc, char *argv[])
 
 	parse_opts(argc, argv);
 
+	init_rng();
+
 	e1 = pipe(pipefds);
 	if (e1 < 0)
 		die_perror("pipe");
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index 41de643788b8..0879da915014 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -178,7 +178,7 @@ do_transfer()
 
 	timeout ${timeout_test} \
 		ip netns exec ${listener_ns} \
-			$mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS \
+			$mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS,TCPINQ \
 				${local_addr} < "$sin" > "$sout" &
 	spid=$!
 
@@ -186,7 +186,7 @@ do_transfer()
 
 	timeout ${timeout_test} \
 		ip netns exec ${connector_ns} \
-			$mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS \
+			$mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS,TCPINQ \
 				$connect_addr < "$cin" > "$cout" &
 
 	cpid=$!
@@ -279,6 +279,45 @@ run_tests()
 	fi
 }
 
+do_tcpinq_test()
+{
+	ip netns exec "$ns1" ./mptcp_inq "$@"
+	lret=$?
+	if [ $lret -ne 0 ];then
+		ret=$lret
+		echo "FAIL: mptcp_inq $@" 1>&2
+		return $lret
+	fi
+
+	echo "PASS: TCP_INQ cmsg/ioctl $@"
+	return $lret
+}
+
+do_tcpinq_tests()
+{
+	local lret=0
+
+	ip netns exec "$ns1" iptables -F
+	ip netns exec "$ns1" ip6tables -F
+
+	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)
@@ -300,4 +339,5 @@ if [ $ret -eq 0 ];then
 	echo "PASS: SOL_MPTCP getsockopt has expected information"
 fi
 
+do_tcpinq_tests
 exit $ret