8 files changed, 794 insertions, 44 deletions

diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
index 260336d5f0b1..7569d892967a 100644
--- a/tools/testing/selftests/net/mptcp/.gitignore
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 mptcp_connect
+mptcp_sockopt
 pm_nl_ctl
 *.pcap
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index f1464f09b080..bbf4e448bad9 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
+TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 89c4753c2760..95e81d557b08 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -14,6 +14,7 @@
 #include <strings.h>
 #include <signal.h>
 #include <unistd.h>
+#include <time.h>
 
 #include <sys/poll.h>
 #include <sys/sendfile.h>
@@ -64,6 +65,7 @@ static int cfg_sndbuf;
 static int cfg_rcvbuf;
 static bool cfg_join;
 static bool cfg_remove;
+static unsigned int cfg_time;
 static unsigned int cfg_do_w;
 static int cfg_wait;
 static uint32_t cfg_mark;
@@ -78,9 +80,10 @@ static struct cfg_cmsg_types cfg_cmsg_types;
 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");
+		"[-l] [-w sec] [-t num] [-T num] connect_address\n");
 	fprintf(stderr, "\t-6 use ipv6\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 -- set SO_RCVBUF to num\n");
 	fprintf(stderr, "\t-p num -- use port num\n");
@@ -448,7 +451,7 @@ static void set_nonblock(int fd)
 	fcntl(fd, F_SETFL, flags | O_NONBLOCK);
 }
 
-static int copyfd_io_poll(int infd, int peerfd, int outfd)
+static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after_out)
 {
 	struct pollfd fds = {
 		.fd = peerfd,
@@ -487,9 +490,11 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd)
 				 */
 				fds.events &= ~POLLIN;
 
-				if ((fds.events & POLLOUT) == 0)
+				if ((fds.events & POLLOUT) == 0) {
+					*in_closed_after_out = true;
 					/* and nothing more to send */
 					break;
+				}
 
 			/* Else, still have data to transmit */
 			} else if (len < 0) {
@@ -547,7 +552,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd)
 	}
 
 	/* leave some time for late join/announce */
-	if (cfg_join || cfg_remove)
+	if (cfg_remove)
 		usleep(cfg_wait);
 
 	close(peerfd);
@@ -646,7 +651,7 @@ static int do_sendfile(int infd, int outfd, unsigned int count)
 }
 
 static int copyfd_io_mmap(int infd, int peerfd, int outfd,
-			  unsigned int size)
+			  unsigned int size, bool *in_closed_after_out)
 {
 	int err;
 
@@ -664,13 +669,14 @@ static int copyfd_io_mmap(int infd, int peerfd, int outfd,
 		shutdown(peerfd, SHUT_WR);
 
 		err = do_recvfile(peerfd, outfd);
+		*in_closed_after_out = true;
 	}
 
 	return err;
 }
 
 static int copyfd_io_sendfile(int infd, int peerfd, int outfd,
-			      unsigned int size)
+			      unsigned int size, bool *in_closed_after_out)
 {
 	int err;
 
@@ -685,6 +691,7 @@ static int copyfd_io_sendfile(int infd, int peerfd, int outfd,
 		if (err)
 			return err;
 		err = do_recvfile(peerfd, outfd);
+		*in_closed_after_out = true;
 	}
 
 	return err;
@@ -692,27 +699,62 @@ static int copyfd_io_sendfile(int infd, int peerfd, int outfd,
 
 static int copyfd_io(int infd, int peerfd, int outfd)
 {
+	bool in_closed_after_out = false;
+	struct timespec start, end;
 	int file_size;
+	int ret;
+
+	if (cfg_time && (clock_gettime(CLOCK_MONOTONIC, &start) < 0))
+		xerror("can not fetch start time %d", errno);
 
 	switch (cfg_mode) {
 	case CFG_MODE_POLL:
-		return copyfd_io_poll(infd, peerfd, outfd);
+		ret = copyfd_io_poll(infd, peerfd, outfd, &in_closed_after_out);
+		break;
+
 	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);
+		ret = copyfd_io_mmap(infd, peerfd, outfd, file_size, &in_closed_after_out);
+		break;
+
 	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);
+		ret = copyfd_io_sendfile(infd, peerfd, outfd, file_size, &in_closed_after_out);
+		break;
+
+	default:
+		fprintf(stderr, "Invalid mode %d\n", cfg_mode);
+
+		die_usage();
+		return 1;
 	}
 
-	fprintf(stderr, "Invalid mode %d\n", cfg_mode);
+	if (ret)
+		return ret;
 
-	die_usage();
-	return 1;
+	if (cfg_time) {
+		unsigned int delta_ms;
+
+		if (clock_gettime(CLOCK_MONOTONIC, &end) < 0)
+			xerror("can not fetch end time %d", errno);
+		delta_ms = (end.tv_sec - start.tv_sec) * 1000 + (end.tv_nsec - start.tv_nsec) / 1000000;
+		if (delta_ms > cfg_time) {
+			xerror("transfer slower than expected! runtime %d ms, expected %d ms",
+			       delta_ms, cfg_time);
+		}
+
+		/* show the runtime only if this end shutdown(wr) before receiving the EOF,
+		 * (that is, if this end got the longer runtime)
+		 */
+		if (in_closed_after_out)
+			fprintf(stderr, "%d", delta_ms);
+	}
+
+	return 0;
 }
 
 static void check_sockaddr(int pf, struct sockaddr_storage *ss,
@@ -1005,12 +1047,11 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:P:c:")) != -1) {
+	while ((c = getopt(argc, argv, "6jr:lp:s:hut:T:m:S:R:w:M:P:c:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
 			cfg_mode = CFG_MODE_POLL;
-			cfg_wait = 400000;
 			break;
 		case 'r':
 			cfg_remove = true;
@@ -1043,6 +1084,9 @@ static void parse_opts(int argc, char **argv)
 			if (poll_timeout <= 0)
 				poll_timeout = -1;
 			break;
+		case 'T':
+			cfg_time = atoi(optarg);
+			break;
 		case 'm':
 			cfg_mode = parse_mode(optarg);
 			break;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 255793c5ac4f..7ef639a9d4a6 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -297,7 +297,7 @@ do_transfer()
 	if [ "$test_link_fail" -eq 2 ];then
 		timeout ${timeout_test} \
 			ip netns exec ${listener_ns} \
-				$mptcp_connect -t ${timeout_poll} -l -p $port -s ${cl_proto} \
+				$mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \
 					${local_addr} < "$sinfail" > "$sout" &
 	else
 		timeout ${timeout_test} \
@@ -945,12 +945,15 @@ subflows_tests()
 
 	# subflow limited by client
 	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 0
+	ip netns exec $ns2 ./pm_nl_ctl limits 0 0
 	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 limited by server
 	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 0
 	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
@@ -973,7 +976,7 @@ subflows_tests()
 	run_tests $ns1 $ns2 10.0.1.1
 	chk_join_nr "multiple subflows" 2 2 2
 
-	# multiple subflows limited by serverf
+	# multiple subflows limited by server
 	reset
 	ip netns exec $ns1 ./pm_nl_ctl limits 0 1
 	ip netns exec $ns2 ./pm_nl_ctl limits 0 2
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
new file mode 100644
index 000000000000..417b11cafafe
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -0,0 +1,683 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <assert.h>
+#include <errno.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 <sys/socket.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include <netdb.h>
+#include <netinet/in.h>
+
+#include <linux/tcp.h>
+
+static int pf = AF_INET;
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+#ifndef SOL_MPTCP
+#define SOL_MPTCP 284
+#endif
+
+#ifndef MPTCP_INFO
+struct mptcp_info {
+	__u8	mptcpi_subflows;
+	__u8	mptcpi_add_addr_signal;
+	__u8	mptcpi_add_addr_accepted;
+	__u8	mptcpi_subflows_max;
+	__u8	mptcpi_add_addr_signal_max;
+	__u8	mptcpi_add_addr_accepted_max;
+	__u32	mptcpi_flags;
+	__u32	mptcpi_token;
+	__u64	mptcpi_write_seq;
+	__u64	mptcpi_snd_una;
+	__u64	mptcpi_rcv_nxt;
+	__u8	mptcpi_local_addr_used;
+	__u8	mptcpi_local_addr_max;
+	__u8	mptcpi_csum_enabled;
+};
+
+struct mptcp_subflow_data {
+	__u32		size_subflow_data;		/* size of this structure in userspace */
+	__u32		num_subflows;			/* must be 0, set by kernel */
+	__u32		size_kernel;			/* must be 0, set by kernel */
+	__u32		size_user;			/* size of one element in data[] */
+} __attribute__((aligned(8)));
+
+struct mptcp_subflow_addrs {
+	union {
+		__kernel_sa_family_t sa_family;
+		struct sockaddr sa_local;
+		struct sockaddr_in sin_local;
+		struct sockaddr_in6 sin6_local;
+		struct __kernel_sockaddr_storage ss_local;
+	};
+	union {
+		struct sockaddr sa_remote;
+		struct sockaddr_in sin_remote;
+		struct sockaddr_in6 sin6_remote;
+		struct __kernel_sockaddr_storage ss_remote;
+	};
+};
+
+#define MPTCP_INFO		1
+#define MPTCP_TCPINFO		2
+#define MPTCP_SUBFLOW_ADDRS	3
+#endif
+
+struct so_state {
+	struct mptcp_info mi;
+	uint64_t mptcpi_rcv_delta;
+	uint64_t tcpi_rcv_delta;
+};
+
+static void die_perror(const char *msg)
+{
+	perror(msg);
+	exit(1);
+}
+
+static void die_usage(int r)
+{
+	fprintf(stderr, "Usage: mptcp_sockopt [-6]\n");
+	exit(r);
+}
+
+static void 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, IPPROTO_MPTCP);
+		if (sock < 0)
+			continue;
+
+		if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one,
+				     sizeof(one)))
+			perror("setsockopt");
+
+		if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
+			break; /* success */
+
+		perror("bind");
+		close(sock);
+		sock = -1;
+	}
+
+	freeaddrinfo(addr);
+
+	if (sock < 0)
+		xerror("could not create listen socket");
+
+	if (listen(sock, 20))
+		die_perror("listen");
+
+	return sock;
+}
+
+static int sock_connect_mptcp(const char * const remoteaddr,
+			      const char * const port, int proto)
+{
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_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 void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "h6")) != -1) {
+		switch (c) {
+		case 'h':
+			die_usage(0);
+			break;
+		case '6':
+			pf = AF_INET6;
+			break;
+		default:
+			die_usage(1);
+			break;
+		}
+	}
+}
+
+static void do_getsockopt_bogus_sf_data(int fd, int optname)
+{
+	struct mptcp_subflow_data good_data;
+	struct bogus_data {
+		struct mptcp_subflow_data d;
+		char buf[2];
+	} bd;
+	socklen_t olen, _olen;
+	int ret;
+
+	memset(&bd, 0, sizeof(bd));
+	memset(&good_data, 0, sizeof(good_data));
+
+	olen = sizeof(good_data);
+	good_data.size_subflow_data = olen;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* 0 size_subflow_data */
+	assert(olen == sizeof(good_data));
+
+	bd.d = good_data;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret == 0);
+	assert(olen == sizeof(good_data));
+	assert(bd.d.num_subflows == 1);
+	assert(bd.d.size_kernel > 0);
+	assert(bd.d.size_user == 0);
+
+	bd.d = good_data;
+	_olen = rand() % olen;
+	olen = _olen;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0);	/* bogus olen */
+	assert(olen == _olen);	/* must be unchanged */
+
+	bd.d = good_data;
+	olen = sizeof(good_data);
+	bd.d.size_kernel = 1;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* size_kernel not 0 */
+
+	bd.d = good_data;
+	olen = sizeof(good_data);
+	bd.d.num_subflows = 1;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* num_subflows not 0 */
+
+	/* forward compat check: larger struct mptcp_subflow_data on 'old' kernel */
+	bd.d = good_data;
+	olen = sizeof(bd);
+	bd.d.size_subflow_data = sizeof(bd);
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret == 0);
+
+	/* olen must be truncated to real data size filled by kernel: */
+	assert(olen == sizeof(good_data));
+
+	assert(bd.d.size_subflow_data == sizeof(bd));
+
+	bd.d = good_data;
+	bd.d.size_subflow_data += 1;
+	bd.d.size_user = 1;
+	olen = bd.d.size_subflow_data + 1;
+	_olen = olen;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &_olen);
+	assert(ret == 0);
+
+	/* no truncation, kernel should have filled 1 byte of optname payload in buf[1]: */
+	assert(olen == _olen);
+
+	assert(bd.d.size_subflow_data == sizeof(good_data) + 1);
+	assert(bd.buf[0] == 0);
+}
+
+static void do_getsockopt_mptcp_info(struct so_state *s, int fd, size_t w)
+{
+	struct mptcp_info i;
+	socklen_t olen;
+	int ret;
+
+	olen = sizeof(i);
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &i, &olen);
+
+	if (ret < 0)
+		die_perror("getsockopt MPTCP_INFO");
+
+	assert(olen == sizeof(i));
+
+	if (s->mi.mptcpi_write_seq == 0)
+		s->mi = i;
+
+	assert(s->mi.mptcpi_write_seq + w == i.mptcpi_write_seq);
+
+	s->mptcpi_rcv_delta = i.mptcpi_rcv_nxt - s->mi.mptcpi_rcv_nxt;
+}
+
+static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t w)
+{
+	struct my_tcp_info {
+		struct mptcp_subflow_data d;
+		struct tcp_info ti[2];
+	} ti;
+	int ret, tries = 5;
+	socklen_t olen;
+
+	do {
+		memset(&ti, 0, sizeof(ti));
+
+		ti.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+		ti.d.size_user = sizeof(struct tcp_info);
+		olen = sizeof(ti);
+
+		ret = getsockopt(fd, SOL_MPTCP, MPTCP_TCPINFO, &ti, &olen);
+		if (ret < 0)
+			xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)");
+
+		assert(olen <= sizeof(ti));
+		assert(ti.d.size_user == ti.d.size_kernel);
+		assert(ti.d.size_user == sizeof(struct tcp_info));
+		assert(ti.d.num_subflows == 1);
+
+		assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data));
+		olen -= sizeof(struct mptcp_subflow_data);
+		assert(olen == sizeof(struct tcp_info));
+
+		if (ti.ti[0].tcpi_bytes_sent == w &&
+		    ti.ti[0].tcpi_bytes_received == r)
+			goto done;
+
+		if (r == 0 && ti.ti[0].tcpi_bytes_sent == w &&
+		    ti.ti[0].tcpi_bytes_received) {
+			s->tcpi_rcv_delta = ti.ti[0].tcpi_bytes_received;
+			goto done;
+		}
+
+		/* wait and repeat, might be that tx is still ongoing */
+		sleep(1);
+	} while (tries-- > 0);
+
+	xerror("tcpi_bytes_sent %" PRIu64 ", want %zu. tcpi_bytes_received %" PRIu64 ", want %zu",
+		ti.ti[0].tcpi_bytes_sent, w, ti.ti[0].tcpi_bytes_received, r);
+
+done:
+	do_getsockopt_bogus_sf_data(fd, MPTCP_TCPINFO);
+}
+
+static void do_getsockopt_subflow_addrs(int fd)
+{
+	struct sockaddr_storage remote, local;
+	socklen_t olen, rlen, llen;
+	int ret;
+	struct my_addrs {
+		struct mptcp_subflow_data d;
+		struct mptcp_subflow_addrs addr[2];
+	} addrs;
+
+	memset(&addrs, 0, sizeof(addrs));
+	memset(&local, 0, sizeof(local));
+	memset(&remote, 0, sizeof(remote));
+
+	addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+	addrs.d.size_user = sizeof(struct mptcp_subflow_addrs);
+	olen = sizeof(addrs);
+
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen);
+	if (ret < 0)
+		die_perror("getsockopt MPTCP_SUBFLOW_ADDRS");
+
+	assert(olen <= sizeof(addrs));
+	assert(addrs.d.size_user == addrs.d.size_kernel);
+	assert(addrs.d.size_user == sizeof(struct mptcp_subflow_addrs));
+	assert(addrs.d.num_subflows == 1);
+
+	assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data));
+	olen -= sizeof(struct mptcp_subflow_data);
+	assert(olen == sizeof(struct mptcp_subflow_addrs));
+
+	llen = sizeof(local);
+	ret = getsockname(fd, (struct sockaddr *)&local, &llen);
+	if (ret < 0)
+		die_perror("getsockname");
+	rlen = sizeof(remote);
+	ret = getpeername(fd, (struct sockaddr *)&remote, &rlen);
+	if (ret < 0)
+		die_perror("getpeername");
+
+	assert(rlen > 0);
+	assert(rlen == llen);
+
+	assert(remote.ss_family == local.ss_family);
+
+	assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) == 0);
+	assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) == 0);
+
+	memset(&addrs, 0, sizeof(addrs));
+
+	addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+	addrs.d.size_user = sizeof(sa_family_t);
+	olen = sizeof(addrs.d) + sizeof(sa_family_t);
+
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen);
+	assert(ret == 0);
+	assert(olen == sizeof(addrs.d) + sizeof(sa_family_t));
+
+	assert(addrs.addr[0].sa_family == pf);
+	assert(addrs.addr[0].sa_family == local.ss_family);
+
+	assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) != 0);
+	assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) != 0);
+
+	do_getsockopt_bogus_sf_data(fd, MPTCP_SUBFLOW_ADDRS);
+}
+
+static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w)
+{
+	do_getsockopt_mptcp_info(s, fd, w);
+
+	do_getsockopt_tcp_info(s, fd, r, w);
+
+	do_getsockopt_subflow_addrs(fd);
+}
+
+static void connect_one_server(int fd, int pipefd)
+{
+	char buf[4096], buf2[4096];
+	size_t len, i, total;
+	struct so_state s;
+	bool eof = false;
+	ssize_t ret;
+
+	memset(&s, 0, sizeof(s));
+
+	len = rand() % (sizeof(buf) - 1);
+
+	if (len < 128)
+		len = 128;
+
+	for (i = 0; i < len ; i++) {
+		buf[i] = rand() % 26;
+		buf[i] += 'A';
+	}
+
+	buf[i] = '\n';
+
+	do_getsockopts(&s, fd, 0, 0);
+
+	/* un-block server */
+	ret = read(pipefd, buf2, 4);
+	assert(ret == 4);
+	close(pipefd);
+
+	assert(strncmp(buf2, "xmit", 4) == 0);
+
+	ret = write(fd, buf, len);
+	if (ret < 0)
+		die_perror("write");
+
+	if (ret != (ssize_t)len)
+		xerror("short write");
+
+	total = 0;
+	do {
+		ret = read(fd, buf2 + total, sizeof(buf2) - total);
+		if (ret < 0)
+			die_perror("read");
+		if (ret == 0) {
+			eof = true;
+			break;
+		}
+
+		total += ret;
+	} while (total < len);
+
+	if (total != len)
+		xerror("total %lu, len %lu eof %d\n", total, len, eof);
+
+	if (memcmp(buf, buf2, len))
+		xerror("data corruption");
+
+	if (s.tcpi_rcv_delta)
+		assert(s.tcpi_rcv_delta <= total);
+
+	do_getsockopts(&s, fd, ret, ret);
+
+	if (eof)
+		total += 1; /* sequence advances due to FIN */
+
+	assert(s.mptcpi_rcv_delta == (uint64_t)total);
+	close(fd);
+}
+
+static void process_one_client(int fd, int pipefd)
+{
+	ssize_t ret, ret2, ret3;
+	struct so_state s;
+	char buf[4096];
+
+	memset(&s, 0, sizeof(s));
+	do_getsockopts(&s, fd, 0, 0);
+
+	ret = write(pipefd, "xmit", 4);
+	assert(ret == 4);
+
+	ret = read(fd, buf, sizeof(buf));
+	if (ret < 0)
+		die_perror("read");
+
+	assert(s.mptcpi_rcv_delta <= (uint64_t)ret);
+
+	if (s.tcpi_rcv_delta)
+		assert(s.tcpi_rcv_delta == (uint64_t)ret);
+
+	ret2 = write(fd, buf, ret);
+	if (ret2 < 0)
+		die_perror("write");
+
+	/* wait for hangup */
+	ret3 = read(fd, buf, 1);
+	if (ret3 != 0)
+		xerror("expected EOF, got %lu", ret3);
+
+	do_getsockopts(&s, fd, ret, ret2);
+	if (s.mptcpi_rcv_delta != (uint64_t)ret + 1)
+		xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret);
+	close(fd);
+}
+
+static int xaccept(int s)
+{
+	int fd = accept(s, NULL, 0);
+
+	if (fd < 0)
+		die_perror("accept");
+
+	return fd;
+}
+
+static int server(int pipefd)
+{
+	int fd = -1, r;
+
+	switch (pf) {
+	case AF_INET:
+		fd = sock_listen_mptcp("127.0.0.1", "15432");
+		break;
+	case AF_INET6:
+		fd = sock_listen_mptcp("::1", "15432");
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+		break;
+	}
+
+	r = write(pipefd, "conn", 4);
+	assert(r == 4);
+
+	alarm(15);
+	r = xaccept(fd);
+
+	process_one_client(r, pipefd);
+
+	return 0;
+}
+
+static int client(int pipefd)
+{
+	int fd = -1;
+
+	alarm(15);
+
+	switch (pf) {
+	case AF_INET:
+		fd = sock_connect_mptcp("127.0.0.1", "15432", IPPROTO_MPTCP);
+		break;
+	case AF_INET6:
+		fd = sock_connect_mptcp("::1", "15432", IPPROTO_MPTCP);
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+	}
+
+	connect_one_server(fd, pipefd);
+
+	return 0;
+}
+
+static pid_t xfork(void)
+{
+	pid_t p = fork();
+
+	if (p < 0)
+		die_perror("fork");
+
+	return p;
+}
+
+static int rcheck(int wstatus, const char *what)
+{
+	if (WIFEXITED(wstatus)) {
+		if (WEXITSTATUS(wstatus) == 0)
+			return 0;
+		fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus));
+		return WEXITSTATUS(wstatus);
+	} else if (WIFSIGNALED(wstatus)) {
+		xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus));
+	} else if (WIFSTOPPED(wstatus)) {
+		xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus));
+	}
+
+	return 111;
+}
+
+int main(int argc, char *argv[])
+{
+	int e1, e2, wstatus;
+	pid_t s, c, ret;
+	int pipefds[2];
+
+	parse_opts(argc, argv);
+
+	e1 = pipe(pipefds);
+	if (e1 < 0)
+		die_perror("pipe");
+
+	s = xfork();
+	if (s == 0)
+		return server(pipefds[1]);
+
+	close(pipefds[1]);
+
+	/* wait until server bound a socket */
+	e1 = read(pipefds[0], &e1, 4);
+	assert(e1 == 4);
+
+	c = xfork();
+	if (c == 0)
+		return client(pipefds[0]);
+
+	close(pipefds[0]);
+
+	ret = waitpid(s, &wstatus, 0);
+	if (ret == -1)
+		die_perror("waitpid");
+	e1 = rcheck(wstatus, "server");
+	ret = waitpid(c, &wstatus, 0);
+	if (ret == -1)
+		die_perror("waitpid");
+	e2 = rcheck(wstatus, "client");
+
+	return e1 ? e1 : e2;
+}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index 1579e471a5e7..41de643788b8 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -239,12 +239,35 @@ make_file()
 	echo "Created $name (size $size KB) containing data sent by $who"
 }
 
+do_mptcp_sockopt_tests()
+{
+	local lret=0
+
+	./mptcp_sockopt
+	lret=$?
+
+	if [ $lret -ne 0 ]; then
+		echo "FAIL: SOL_MPTCP getsockopt" 1>&2
+		ret=$lret
+		return
+	fi
+
+	./mptcp_sockopt -6
+	lret=$?
+
+	if [ $lret -ne 0 ]; then
+		echo "FAIL: SOL_MPTCP getsockopt (ipv6)" 1>&2
+		ret=$lret
+		return
+	fi
+}
+
 run_tests()
 {
 	listener_ns="$1"
 	connector_ns="$2"
 	connect_addr="$3"
-	lret=0
+	local lret=0
 
 	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr}
 
@@ -268,9 +291,13 @@ trap cleanup EXIT
 run_tests $ns1 $ns2 10.0.1.1
 run_tests $ns1 $ns2 dead:beef:1::1
 
-
 if [ $ret -eq 0 ];then
 	echo "PASS: all packets had packet mark set"
 fi
 
+do_mptcp_sockopt_tests
+if [ $ret -eq 0 ];then
+	echo "PASS: SOL_MPTCP getsockopt has expected information"
+fi
+
 exit $ret
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 3c741abe034e..cbacf9f6538b 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -70,7 +70,7 @@ check()
 
 check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list"
 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0
-subflows 0" "defaults limits"
+subflows 2" "defaults limits"
 
 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
@@ -118,11 +118,11 @@ 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" "accept 0
-subflows 0" "rcv addrs above hard limit"
+subflows 2" "rcv addrs above hard limit"
 
 ip netns exec $ns1 ./pm_nl_ctl limits 1 9
 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0
-subflows 0" "subflows above hard limit"
+subflows 2" "subflows above hard limit"
 
 ip netns exec $ns1 ./pm_nl_ctl limits 8 8
 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 910d8126af8f..f441ff7904fc 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -51,7 +51,7 @@ setup()
 	sout=$(mktemp)
 	cout=$(mktemp)
 	capout=$(mktemp)
-	size=$((2048 * 4096))
+	size=$((2 * 2048 * 4096))
 	dd if=/dev/zero of=$small bs=4096 count=20 >/dev/null 2>&1
 	dd if=/dev/zero of=$large bs=4096 count=$((size / 4096)) >/dev/null 2>&1
 
@@ -161,17 +161,15 @@ do_transfer()
 
 	timeout ${timeout_test} \
 		ip netns exec ${ns3} \
-			./mptcp_connect -jt ${timeout_poll} -l -p $port \
+			./mptcp_connect -jt ${timeout_poll} -l -p $port -T $time \
 				0.0.0.0 < "$sin" > "$sout" &
 	local spid=$!
 
 	wait_local_port_listen "${ns3}" "${port}"
 
-	local start
-	start=$(date +%s%3N)
 	timeout ${timeout_test} \
 		ip netns exec ${ns1} \
-			./mptcp_connect -jt ${timeout_poll} -p $port \
+			./mptcp_connect -jt ${timeout_poll} -p $port -T $time \
 				10.0.3.3 < "$cin" > "$cout" &
 	local cpid=$!
 
@@ -180,27 +178,20 @@ do_transfer()
 	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 "
+	printf "%-16s" " max $max_time "
 	if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \
-	   [ $cmpc -eq 0 ] && [ $cmps -eq 0 ] && \
-	   [ $duration -lt $max_time ]; then
+	   [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then
 		echo "[ OK ]"
 		cat "$capout"
 		return 0
@@ -244,23 +235,24 @@ run_test()
 	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 + $rate2) * 1024 *1024) ))
+	# time is measured in ms, account for transfer size, affegated link speed
+	# and header overhead (10%)
+	local time=$((size * 8 * 1000 * 10 / (( $rate1 + $rate2) * 1024 *1024 * 9) ))
 
 	# mptcp_connect will do some sleeps to allow the mp_join handshake
-	# completion
-	time=$((time + 1350))
+	# completion (see mptcp_connect): 200ms on each side, add some slack
+	time=$((time + 450))
 
-	printf "%-50s" "$msg"
-	do_transfer $small $large $((time * 11 / 10))
+	printf "%-60s" "$msg"
+	do_transfer $small $large $time
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
 	fi
 
-	printf "%-50s" "$msg - reverse direction"
-	do_transfer $large $small $((time * 11 / 10))
+	printf "%-60s" "$msg - reverse direction"
+	do_transfer $large $small $time
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret