Series comparison

From: Geliang Tang <tanggeliang@kylinos.cn>

v2:
 - patch 4, a new patch, add do_setsockopt_inq helper.
 - cleanups.

v1:
 - https://patchwork.kernel.org/project/mptcp/cover/cover.1754620968.git.tanggeliang@kylinos.cn/

This series consolidates the TCP_INQ test functionality from mptcp_inq
into mptcp_sockopt, simplifying the test suite while maintaining full
test coverage. The key changes include:

1. Adding necessary protocol arguments and IPC improvements to sockopt
2. Implementing TCP_INQ test logic within the sockopt test binary
3. Migrating test execution to use the enhanced sockopt binary
4. Removing the now-obsolete mptcp_inq test binary

The consolidation provides several benefits:
- Reduces code duplication by sharing common infrastructure
- Simplifies maintenance with a single test binary
- Maintains identical test coverage for TCP_INQ functionality
- Improves code clarity with better IPC naming
- Enhances flexibility through new protocol selection options

The changes maintain backward compatibility while extending
functionality, and all tests pass with the same coverage as before.

Geliang Tang (9):
  selftests: mptcp: sockopt: use getrandom for initialization
  selftests: mptcp: sockopt: add protocol arguments
  selftests: mptcp: sockopt: add inq argument
  selftests: mptcp: sockopt: set TCP_INQ on accepted sockets
  selftests: mptcp: sockopt: rename pipefd to ipcfd
  selftests: mptcp: sockopt: add TCP_INQ client processing
  selftests: mptcp: sockopt: add TCP_INQ server connection
  selftests: mptcp: sockopt: replace mptcp_inq with sockopt
  selftests: mptcp: sockopt: remove obsolete mptcp_inq

tools/testing/selftests/net/mptcp/.gitignore  |   1 -
 tools/testing/selftests/net/mptcp/Makefile    |   2 +-
 tools/testing/selftests/net/mptcp/mptcp_inq.c | 608 ------------------
 .../selftests/net/mptcp/mptcp_sockopt.c       | 359 ++++++++++-
 .../selftests/net/mptcp/mptcp_sockopt.sh      |   6 +-
 5 files changed, 333 insertions(+), 643 deletions(-)
 delete mode 100644 tools/testing/selftests/net/mptcp/mptcp_inq.c

-- 
2.48.1

From: Geliang Tang <tanggeliang@kylinos.cn>

Replace /dev/urandom with getrandom() for initializing the RNG. This
simplifies the code and avoids potential failures from opening device
files while maintaining cryptographic quality randomness.

These codes are from mptcp_inq.c.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 20 +++++++------------
 1 file changed, 7 insertions(+), 13 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Add -t and -r options to specify tx/rx protocols (TCP/MPTCP). This
increases testing flexibility by allowing explicit protocol selection
for both transmission and reception paths.

These codes are from mptcp_inq.c.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 29 +++++++++++++++----
 1 file changed, 24 insertions(+), 5 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Introduce -i option to enable TCP_INQ testing. This prepares for
consolidating TCP_INQ tests into a single binary by adding the necessary
command-line interface.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/net/mptcp/mptcp_sockopt.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Add helper functions to conditionally set TCP_INQ sockopt on accepted
sockets when running in inq mode. This ensures proper testing of TCP_CM_INQ
functionality by enabling the required socket option on both ends of the
connection. This setup is necessary for validating TCP_CM_INQ behavior
during TCP_INQ-specific tests.

These codes are from mptcp_inq.c.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../testing/selftests/net/mptcp/mptcp_sockopt.c  | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

From: Geliang Tang <tanggeliang@kylinos.cn>

Rename pipefd to ipcfd to better reflect its generalized purpose since
it now handles both pipes and Unix domain sockets. This naming improves
code clarity for IPC channel handling.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 25 ++++++++++---------
 1 file changed, 13 insertions(+), 12 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Implement process_one_client_inq() to handle TCP_INQ-specific client
logic including:
- Setting TCP_INQ sockopt
- Validating INQ values via cmsg
- Handling large data transfers with INQ checks
- Verifying FIN sequence INQ semantics

These codes are from mptcp_inq.c.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 153 +++++++++++++++++-
 1 file changed, 152 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -XXX,XX +XXX,XX @@
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <sys/random.h>
+#include <sys/ioctl.h>
 
 #include <netdb.h>
 #include <netinet/in.h>
@@ -XXX,XX +XXX,XX @@ static void process_one_client(int fd, int pipefd)
 	close(fd);
 }
 
+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_inq(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 void do_setsockopt_inq(int fd)
 {
 	int on = 1;
@@ -XXX,XX +XXX,XX @@ static int server(int ipcfd)
 	alarm(15);
 	r = xaccept(fd);
 
-	process_one_client(r, ipcfd);
+	if (inq)
+		process_one_client_inq(r, ipcfd);
+	else
+		process_one_client(r, ipcfd);
 
 	return 0;
 }
-- 
2.48.1

From: Geliang Tang <tanggeliang@kylinos.cn>

Implement connect_one_server_inq() featuring:
- Wait mechanisms for ACK verification
- Large data transmission with flow control
- Proper shutdown sequence handling
- Integration with IPC signaling

These codes are from mptcp_inq.c.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 116 +++++++++++++++++-
 1 file changed, 115 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -XXX,XX +XXX,XX @@
 #include <netinet/in.h>
 
 #include <linux/tcp.h>
+#include <linux/sockios.h>
 
 static int pf = AF_INET;
 static int proto_tx = IPPROTO_MPTCP;
@@ -XXX,XX +XXX,XX @@ static void connect_one_server(int fd, int pipefd)
 	close(fd);
 }
 
+/* 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_inq(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 process_one_client(int fd, int pipefd)
 {
 	ssize_t ret, ret2, ret3;
@@ -XXX,XX +XXX,XX @@ static int client(int ipcfd)
 
 	test_ip_tos_sockopt(fd);
 
-	connect_one_server(fd, ipcfd);
+	if (inq)
+		connect_one_server_inq(fd, ipcfd);
+	else
+		connect_one_server(fd, ipcfd);
 
 	return 0;
 }
-- 
2.48.1

From: Geliang Tang <tanggeliang@kylinos.cn>

Update mptcp_sockopt.sh to use mptcp_sockopt binary instead of
mptcp_inq. This consolidates TCP_INQ testing into a single test binary
while maintaining equivalent test coverage.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index XXXXXXX..XXXXXXX 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -XXX,XX +XXX,XX @@ run_tests()
 do_tcpinq_test()
 {
 	print_title "TCP_INQ cmsg/ioctl $*"
-	ip netns exec "$ns_sbox" ./mptcp_inq "$@"
+	ip netns exec "$ns_sbox" ./mptcp_sockopt "$@"
 	local lret=$?
 	if [ $lret -ne 0 ];then
 		ret=$lret
@@ -XXX,XX +XXX,XX @@ do_tcpinq_tests()
 	fi
 
 	local args
-	for args in "-t tcp" "-r tcp"; do
+	for args in "-t tcp -i" "-r tcp -i"; do
 		do_tcpinq_test $args
 		lret=$?
 		if [ $lret -ne 0 ] ; then
@@ -XXX,XX +XXX,XX @@ do_tcpinq_tests()
 		fi
 	done
 
-	do_tcpinq_test -r tcp -t tcp
+	do_tcpinq_test -r tcp -t tcp -i
 
 	return $?
 }
-- 
2.48.1

From: Geliang Tang <tanggeliang@kylinos.cn>

Delete mptcp_inq binary and references since its functionality has been
fully integrated into mptcp_sockopt. This simplifies the test suite
structure and reduces maintenance overhead.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/net/mptcp/.gitignore  |   1 -
 tools/testing/selftests/net/mptcp/Makefile    |   2 +-
 tools/testing/selftests/net/mptcp/mptcp_inq.c | 608 ------------------
 3 files changed, 1 insertion(+), 610 deletions(-)
 delete mode 100644 tools/testing/selftests/net/mptcp/mptcp_inq.c

diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/net/mptcp/.gitignore
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -XXX,XX +XXX,XX @@
 # SPDX-License-Identifier: GPL-2.0-only
 mptcp_connect
 mptcp_diag
-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 XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -XXX,XX +XXX,XX @@ TEST_PROGS := mptcp_connect.sh mptcp_connect_mmap.sh mptcp_connect_sendfile.sh \
 	      mptcp_connect_checksum.sh pm_netlink.sh mptcp_join.sh diag.sh \
 	      simult_flows.sh mptcp_sockopt.sh userspace_pm.sh
 
-TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag
+TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_diag
 
 TEST_FILES := mptcp_lib.sh settings
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
deleted file mode 100644
index XXXXXXX..XXXXXXX
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ /dev/null
@@ -XXX,XX +XXX,XX @@
-// SPDX-License-Identifier: GPL-2.0
-
-#define _GNU_SOURCE
-
-#include <assert.h>
-#include <errno.h>
-#include <fcntl.h>
-#include <limits.h>
-#include <string.h>
-#include <stdarg.h>
-#include <stdbool.h>
-#include <stdint.h>
-#include <inttypes.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <strings.h>
-#include <unistd.h>
-#include <time.h>
-
-#include <sys/ioctl.h>
-#include <sys/random.h>
-#include <sys/socket.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-
-#include <netdb.h>
-#include <netinet/in.h>
-
-#include <linux/tcp.h>
-#include <linux/sockios.h>
-
-#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,
-			 struct addrinfo *hints,
-			 struct addrinfo **res)
-{
-	int err;
-
-again:
-	err = getaddrinfo(node, service, hints, res);
-	if (err) {
-		const char *errstr;
-
-		if (err == EAI_SOCKTYPE) {
-			hints->ai_protocol = IPPROTO_TCP;
-			goto again;
-		}
-
-		errstr = getxinfo_strerr(err);
-
-		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
-			node ? node : "", service ? service : "", errstr);
-		exit(1);
-	}
-}
-
-static int sock_listen_mptcp(const char * const listenaddr,
-			     const char * const port)
-{
-	int sock = -1;
-	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_MPTCP,
-		.ai_socktype = SOCK_STREAM,
-		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
-	};
-
-	hints.ai_family = pf;
-
-	struct addrinfo *a, *addr;
-	int one = 1;
-
-	xgetaddrinfo(listenaddr, port, &hints, &addr);
-	hints.ai_family = pf;
-
-	for (a = addr; a; a = a->ai_next) {
-		sock = socket(a->ai_family, a->ai_socktype, proto_rx);
-		if (sock < 0)
-			continue;
-
-		if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one,
-				     sizeof(one)))
-			perror("setsockopt");
-
-		if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
-			break; /* success */
-
-		perror("bind");
-		close(sock);
-		sock = -1;
-	}
-
-	freeaddrinfo(addr);
-
-	if (sock < 0)
-		xerror("could not create listen socket");
-
-	if (listen(sock, 20))
-		die_perror("listen");
-
-	return sock;
-}
-
-static int sock_connect_mptcp(const char * const remoteaddr,
-			      const char * const port, int proto)
-{
-	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_MPTCP,
-		.ai_socktype = SOCK_STREAM,
-	};
-	struct addrinfo *a, *addr;
-	int sock = -1;
-
-	hints.ai_family = pf;
-
-	xgetaddrinfo(remoteaddr, port, &hints, &addr);
-	for (a = addr; a; a = a->ai_next) {
-		sock = socket(a->ai_family, a->ai_socktype, proto);
-		if (sock < 0)
-			continue;
-
-		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
-			break; /* success */
-
-		die_perror("connect");
-	}
-
-	if (sock < 0)
-		xerror("could not create connect socket");
-
-	freeaddrinfo(addr);
-	return sock;
-}
-
-static int protostr_to_num(const char *s)
-{
-	if (strcasecmp(s, "tcp") == 0)
-		return IPPROTO_TCP;
-	if (strcasecmp(s, "mptcp") == 0)
-		return IPPROTO_MPTCP;
-
-	die_usage(1);
-	return 0;
-}
-
-static void parse_opts(int argc, char **argv)
-{
-	int c;
-
-	while ((c = getopt(argc, argv, "h6t:r:")) != -1) {
-		switch (c) {
-		case 'h':
-			die_usage(0);
-			break;
-		case '6':
-			pf = AF_INET6;
-			break;
-		case 't':
-			proto_tx = protostr_to_num(optarg);
-			break;
-		case 'r':
-			proto_rx = protostr_to_num(optarg);
-			break;
-		default:
-			die_usage(1);
-			break;
-		}
-	}
-}
-
-/* wait up to timeout milliseconds */
-static void wait_for_ack(int fd, int timeout, size_t total)
-{
-	int i;
-
-	for (i = 0; i < timeout; i++) {
-		int nsd, ret, queued = -1;
-		struct timespec req;
-
-		ret = ioctl(fd, TIOCOUTQ, &queued);
-		if (ret < 0)
-			die_perror("TIOCOUTQ");
-
-		ret = ioctl(fd, SIOCOUTQNSD, &nsd);
-		if (ret < 0)
-			die_perror("SIOCOUTQNSD");
-
-		if ((size_t)queued > total)
-			xerror("TIOCOUTQ %u, but only %zu expected\n", queued, total);
-		assert(nsd <= queued);
-
-		if (queued == 0)
-			return;
-
-		/* wait for peer to ack rx of all data */
-		req.tv_sec = 0;
-		req.tv_nsec = 1 * 1000 * 1000ul; /* 1ms */
-		nanosleep(&req, NULL);
-	}
-
-	xerror("still tx data queued after %u ms\n", timeout);
-}
-
-static void connect_one_server(int fd, int unixfd)
-{
-	size_t len, i, total, sent;
-	char buf[4096], buf2[4096];
-	ssize_t ret;
-
-	len = rand() % (sizeof(buf) - 1);
-
-	if (len < 128)
-		len = 128;
-
-	for (i = 0; i < len ; i++) {
-		buf[i] = rand() % 26;
-		buf[i] += 'A';
-	}
-
-	buf[i] = '\n';
-
-	/* un-block server */
-	ret = read(unixfd, buf2, 4);
-	assert(ret == 4);
-
-	assert(strncmp(buf2, "xmit", 4) == 0);
-
-	ret = write(unixfd, &len, sizeof(len));
-	assert(ret == (ssize_t)sizeof(len));
-
-	ret = write(fd, buf, len);
-	if (ret < 0)
-		die_perror("write");
-
-	if (ret != (ssize_t)len)
-		xerror("short write");
-
-	ret = read(unixfd, buf2, 4);
-	assert(strncmp(buf2, "huge", 4) == 0);
-
-	total = rand() % (16 * 1024 * 1024);
-	total += (1 * 1024 * 1024);
-	sent = total;
-
-	ret = write(unixfd, &total, sizeof(total));
-	assert(ret == (ssize_t)sizeof(total));
-
-	wait_for_ack(fd, 5000, len);
-
-	while (total > 0) {
-		if (total > sizeof(buf))
-			len = sizeof(buf);
-		else
-			len = total;
-
-		ret = write(fd, buf, len);
-		if (ret < 0)
-			die_perror("write");
-		total -= ret;
-
-		/* we don't have to care about buf content, only
-		 * number of total bytes sent
-		 */
-	}
-
-	ret = read(unixfd, buf2, 4);
-	assert(ret == 4);
-	assert(strncmp(buf2, "shut", 4) == 0);
-
-	wait_for_ack(fd, 5000, sent);
-
-	ret = write(fd, buf, 1);
-	assert(ret == 1);
-	close(fd);
-	ret = write(unixfd, "closed", 6);
-	assert(ret == 6);
-
-	close(unixfd);
-}
-
-static void get_tcp_inq(struct msghdr *msgh, unsigned int *inqv)
-{
-	struct cmsghdr *cmsg;
-
-	for (cmsg = CMSG_FIRSTHDR(msgh); cmsg ; cmsg = CMSG_NXTHDR(msgh, cmsg)) {
-		if (cmsg->cmsg_level == IPPROTO_TCP && cmsg->cmsg_type == TCP_CM_INQ) {
-			memcpy(inqv, CMSG_DATA(cmsg), sizeof(*inqv));
-			return;
-		}
-	}
-
-	xerror("could not find TCP_CM_INQ cmsg type");
-}
-
-static void process_one_client(int fd, int unixfd)
-{
-	unsigned int tcp_inq;
-	size_t expect_len;
-	char msg_buf[4096];
-	char buf[4096];
-	char tmp[16];
-	struct iovec iov = {
-		.iov_base = buf,
-		.iov_len = 1,
-	};
-	struct msghdr msg = {
-		.msg_iov = &iov,
-		.msg_iovlen = 1,
-		.msg_control = msg_buf,
-		.msg_controllen = sizeof(msg_buf),
-	};
-	ssize_t ret, tot;
-
-	ret = write(unixfd, "xmit", 4);
-	assert(ret == 4);
-
-	ret = read(unixfd, &expect_len, sizeof(expect_len));
-	assert(ret == (ssize_t)sizeof(expect_len));
-
-	if (expect_len > sizeof(buf))
-		xerror("expect len %zu exceeds buffer size", expect_len);
-
-	for (;;) {
-		struct timespec req;
-		unsigned int queued;
-
-		ret = ioctl(fd, FIONREAD, &queued);
-		if (ret < 0)
-			die_perror("FIONREAD");
-		if (queued > expect_len)
-			xerror("FIONREAD returned %u, but only %zu expected\n",
-			       queued, expect_len);
-		if (queued == expect_len)
-			break;
-
-		req.tv_sec = 0;
-		req.tv_nsec = 1000 * 1000ul;
-		nanosleep(&req, NULL);
-	}
-
-	/* read one byte, expect cmsg to return expected - 1 */
-	ret = recvmsg(fd, &msg, 0);
-	if (ret < 0)
-		die_perror("recvmsg");
-
-	if (msg.msg_controllen == 0)
-		xerror("msg_controllen is 0");
-
-	get_tcp_inq(&msg, &tcp_inq);
-
-	assert((size_t)tcp_inq == (expect_len - 1));
-
-	iov.iov_len = sizeof(buf);
-	ret = recvmsg(fd, &msg, 0);
-	if (ret < 0)
-		die_perror("recvmsg");
-
-	/* should have gotten exact remainder of all pending data */
-	assert(ret == (ssize_t)tcp_inq);
-
-	/* should be 0, all drained */
-	get_tcp_inq(&msg, &tcp_inq);
-	assert(tcp_inq == 0);
-
-	/* request a large swath of data. */
-	ret = write(unixfd, "huge", 4);
-	assert(ret == 4);
-
-	ret = read(unixfd, &expect_len, sizeof(expect_len));
-	assert(ret == (ssize_t)sizeof(expect_len));
-
-	/* peer should send us a few mb of data */
-	if (expect_len <= sizeof(buf))
-		xerror("expect len %zu too small\n", expect_len);
-
-	tot = 0;
-	do {
-		iov.iov_len = sizeof(buf);
-		ret = recvmsg(fd, &msg, 0);
-		if (ret < 0)
-			die_perror("recvmsg");
-
-		tot += ret;
-
-		get_tcp_inq(&msg, &tcp_inq);
-
-		if (tcp_inq > expect_len - tot)
-			xerror("inq %d, remaining %d total_len %d\n",
-			       tcp_inq, expect_len - tot, (int)expect_len);
-
-		assert(tcp_inq <= expect_len - tot);
-	} while ((size_t)tot < expect_len);
-
-	ret = write(unixfd, "shut", 4);
-	assert(ret == 4);
-
-	/* wait for hangup. Should have received one more byte of data. */
-	ret = read(unixfd, tmp, sizeof(tmp));
-	assert(ret == 6);
-	assert(strncmp(tmp, "closed", 6) == 0);
-
-	sleep(1);
-
-	iov.iov_len = 1;
-	ret = recvmsg(fd, &msg, 0);
-	if (ret < 0)
-		die_perror("recvmsg");
-	assert(ret == 1);
-
-	get_tcp_inq(&msg, &tcp_inq);
-
-	/* tcp_inq should be 1 due to received fin. */
-	assert(tcp_inq == 1);
-
-	iov.iov_len = 1;
-	ret = recvmsg(fd, &msg, 0);
-	if (ret < 0)
-		die_perror("recvmsg");
-
-	/* expect EOF */
-	assert(ret == 0);
-	get_tcp_inq(&msg, &tcp_inq);
-	assert(tcp_inq == 1);
-
-	close(fd);
-}
-
-static int xaccept(int s)
-{
-	int fd = accept(s, NULL, 0);
-
-	if (fd < 0)
-		die_perror("accept");
-
-	return fd;
-}
-
-static int server(int unixfd)
-{
-	int fd = -1, r, on = 1;
-
-	switch (pf) {
-	case AF_INET:
-		fd = sock_listen_mptcp("127.0.0.1", "15432");
-		break;
-	case AF_INET6:
-		fd = sock_listen_mptcp("::1", "15432");
-		break;
-	default:
-		xerror("Unknown pf %d\n", pf);
-		break;
-	}
-
-	r = write(unixfd, "conn", 4);
-	assert(r == 4);
-
-	alarm(15);
-	r = xaccept(fd);
-
-	if (-1 == setsockopt(r, IPPROTO_TCP, TCP_INQ, &on, sizeof(on)))
-		die_perror("setsockopt");
-
-	process_one_client(r, unixfd);
-
-	return 0;
-}
-
-static int client(int unixfd)
-{
-	int fd = -1;
-
-	alarm(15);
-
-	switch (pf) {
-	case AF_INET:
-		fd = sock_connect_mptcp("127.0.0.1", "15432", proto_tx);
-		break;
-	case AF_INET6:
-		fd = sock_connect_mptcp("::1", "15432", proto_tx);
-		break;
-	default:
-		xerror("Unknown pf %d\n", pf);
-	}
-
-	connect_one_server(fd, unixfd);
-
-	return 0;
-}
-
-static void init_rng(void)
-{
-	unsigned int foo;
-
-	if (getrandom(&foo, sizeof(foo), 0) == -1) {
-		perror("getrandom");
-		exit(1);
-	}
-
-	srand(foo);
-}
-
-static pid_t xfork(void)
-{
-	pid_t p = fork();
-
-	if (p < 0)
-		die_perror("fork");
-	else if (p == 0)
-		init_rng();
-
-	return p;
-}
-
-static int rcheck(int wstatus, const char *what)
-{
-	if (WIFEXITED(wstatus)) {
-		if (WEXITSTATUS(wstatus) == 0)
-			return 0;
-		fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus));
-		return WEXITSTATUS(wstatus);
-	} else if (WIFSIGNALED(wstatus)) {
-		xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus));
-	} else if (WIFSTOPPED(wstatus)) {
-		xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus));
-	}
-
-	return 111;
-}
-
-int main(int argc, char *argv[])
-{
-	int e1, e2, wstatus;
-	pid_t s, c, ret;
-	int unixfds[2];
-
-	parse_opts(argc, argv);
-
-	e1 = socketpair(AF_UNIX, SOCK_DGRAM, 0, unixfds);
-	if (e1 < 0)
-		die_perror("pipe");
-
-	s = xfork();
-	if (s == 0)
-		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;
-}
-- 
2.48.1

From: Geliang Tang <tanggeliang@kylinos.cn>

v7:
 - Add a new patch to reseed RNG in child after fork.
 - Add a new patch to fix bytes_acked validation against sent bytes.
 - Add a new patch to use r/w for byte counts in process_one_client().
 - Split v6-0004 into two separate patches: read exact payload length,
   and pass len over unixfd.
 - Change socketpair type from SOCK_DGRAM to SOCK_STREAM to avoid
   indefinite blocking when peer exits.
 - Fully initialize buf in server_huge_transfer() to silence MSAN/Valgrind
   warnings.
 - Use a union containing struct cmsghdr for control message buffers to
   prevent unaligned access on strict-alignment architectures.
 - Reorder and renumber patches accordingly.

v6:
 - A new patch to use recvmsg instead of read.
 - Squash the four original patches into two.
 - Reset msg.msg_controllen.
 - Check cmsg_len in get_tcp_inq.
 - Check return value of client_huge_transfer.
 - Address other comments from Sashiko.
 - https://patchwork.kernel.org/project/mptcp/cover/cover.1783673158.git.tanggeliang@kylinos.cn/

v5:
 - Continue using the approach from v3 and fix the instability issues.
   This version has undergone extensive loop testing.
 - The new two separate functions, server_huge_transfer() and 
   client_huge_transfer(), improve code structure.
 - https://patchwork.kernel.org/project/mptcp/cover/cover.1783579976.git.tanggeliang@kylinos.cn/

v4:
 - v3 changed the behavior of process_one_client and connect_one_server,
   causing intermittent failures during loop testing. Revert to using the 
   v2 approach, along with some cleanups.
 - https://patchwork.kernel.org/project/mptcp/cover/cover.1757686538.git.tanggeliang@kylinos.cn/

v3:
 - No longer using process_one_client_inq() and connect_one_server_inq()
   for switching; instead, the inq-related code has been merged into
   process_one_client() and connect_one_server().
 - https://patchwork.kernel.org/project/mptcp/cover/cover.1756200029.git.tanggeliang@kylinos.cn/

v2:
 - patch 4, a new patch, add do_setsockopt_inq helper.
 - cleanups.
 - https://patchwork.kernel.org/project/mptcp/cover/cover.1754664106.git.tanggeliang@kylinos.cn/

v1:
 - https://patchwork.kernel.org/project/mptcp/cover/cover.1754620968.git.tanggeliang@kylinos.cn/

This series consolidates the TCP_INQ test functionality from mptcp_inq
into mptcp_sockopt, simplifying the test suite while maintaining full
test coverage.

Geliang Tang (14):
  selftests: mptcp: sockopt: reseed RNG after fork
  selftests: mptcp: sockopt: validate bytes_acked against sent bytes
  selftests: mptcp: sockopt: use r and w for byte counts
  selftests: mptcp: sockopt: add tx/rx protocol options
  selftests: mptcp: sockopt: add TCP_INQ test option
  selftests: mptcp: sockopt: use unix socket instead of pipe
  selftests: mptcp: sockopt: read exact payload length
  selftests: mptcp: sockopt: pass echo length over unixfd
  selftests: mptcp: sockopt: set FIONREAD ioctl
  selftests: mptcp: sockopt: add huge data transfer tests
  selftests: mptcp: sockopt: wait ack for huge transfer
  selftests: mptcp: sockopt: use recvmsg instead of read
  selftests: mptcp: sockopt: get and verify TCP_INQ
  selftests: mptcp: sockopt: replace mptcp_inq with sockopt

tools/testing/selftests/net/mptcp/.gitignore  |   1 -
 tools/testing/selftests/net/mptcp/Makefile    |   1 -
 tools/testing/selftests/net/mptcp/mptcp_inq.c | 614 ------------------
 .../selftests/net/mptcp/mptcp_sockopt.c       | 415 ++++++++++--
 .../selftests/net/mptcp/mptcp_sockopt.sh      |   8 +-
 5 files changed, 372 insertions(+), 667 deletions(-)
 delete mode 100644 tools/testing/selftests/net/mptcp/mptcp_inq.c

-- 
2.53.0

From: Geliang Tang <tanggeliang@kylinos.cn>

xfork() leaves the child sharing its parent's srand() state, so server
and client processes drive rand() off the same seed. After the recent
consolidation of mptcp_inq.c into mptcp_sockopt.c, mptcp_inq's
per-fork reseed was lost. Restore it: have the child call init_rng()
again so each fork gets an independent seed from /dev/urandom.

This mirrors what the standalone mptcp_inq binary used to do, and
keeps buffer-filling and huge-transfer sizes uncorrelated across the
two processes.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/net/mptcp/mptcp_sockopt.c | 4 ++++
 1 file changed, 4 insertions(+)

From: Geliang Tang <tanggeliang@kylinos.cn>

mptcpi_bytes_acked tracks the number of bytes sent and acknowledged,
so it should be compared with the amount of data written (ret2), not
the amount read (ret). This corrects a logical error in the test
validation.

Fixes: b86418beade1 ("selftests: mptcp: sockopt: fix error messages")
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/net/mptcp/mptcp_sockopt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Replace ret/ret2/ret3 with r (received) and w (sent) for readability.
This prepares for future updates where r will be modified via '+='.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 39 ++++++++++---------
 1 file changed, 21 insertions(+), 18 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Add -t and -r options to specify tx/rx protocols (TCP/MPTCP). This
increases testing flexibility by allowing explicit protocol selection
for both transmission and reception paths.

These codes are from mptcp_inq.c.

Enhance compatibility with TCP tests by skipping MPTCP getsockopt checks
during TCP tests since MPTCP socket options are not available.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 37 ++++++++++++++++---
 1 file changed, 31 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -XXX,XX +XXX,XX @@
 #include <linux/compiler.h>
 
 static int pf = AF_INET;
+static int proto_tx = IPPROTO_MPTCP;
+static int proto_rx = IPPROTO_MPTCP;
 
 #ifndef IPPROTO_MPTCP
 #define IPPROTO_MPTCP 262
@@ -XXX,XX +XXX,XX @@ static void __noreturn die_perror(const char *msg)
 static void die_usage(int r)
 {
 	fprintf(stderr, "Usage: mptcp_sockopt [-6]\n");
+	fprintf(stderr, "                     [-t tcp|mptcp] [-r tcp|mptcp]\n");
 	exit(r);
 }
 
@@ -XXX,XX +XXX,XX @@ static int sock_listen_mptcp(const char * const listenaddr,
 	hints.ai_family = pf;
 
 	for (a = addr; a; a = a->ai_next) {
-		sock = socket(a->ai_family, a->ai_socktype, IPPROTO_MPTCP);
+		sock = socket(a->ai_family, a->ai_socktype, proto_rx);
 		if (sock < 0)
 			continue;
 
@@ -XXX,XX +XXX,XX @@ static int sock_connect_mptcp(const char * const remoteaddr,
 	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, "h6")) != -1) {
+	while ((c = getopt(argc, argv, "h6t:r:")) != -1) {
 		switch (c) {
 		case 'h':
 			die_usage(0);
@@ -XXX,XX +XXX,XX @@ static void parse_opts(int argc, char **argv)
 		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;
@@ -XXX,XX +XXX,XX @@ static void do_getsockopt_mptcp_full_info(struct so_state *s, int fd)
 
 static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w)
 {
+	if (proto_tx != IPPROTO_MPTCP || proto_rx != IPPROTO_MPTCP)
+		return;
+
 	do_getsockopt_mptcp_info(s, fd, w);
 
 	do_getsockopt_tcp_info(s, fd, r, w);
@@ -XXX,XX +XXX,XX @@ static void connect_one_server(int fd, int pipefd)
 	if (eof)
 		total += 1; /* sequence advances due to FIN */
 
-	assert(s.mptcpi_rcv_delta == (uint64_t)total);
+	if (proto_tx == IPPROTO_MPTCP && proto_rx == IPPROTO_MPTCP)
+		assert(s.mptcpi_rcv_delta == (uint64_t)total);
 	close(fd);
 }
 
@@ -XXX,XX +XXX,XX @@ static void process_one_client(int fd, int pipefd)
 	r += ret;
 
 	do_getsockopts(&s, fd, r, w);
-	if (s.mptcpi_rcv_delta != (uint64_t)r + 1)
+	if (proto_tx == IPPROTO_MPTCP && proto_rx == IPPROTO_MPTCP &&
+	    s.mptcpi_rcv_delta != (uint64_t)r + 1)
 		xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64 ", diff %" PRId64,
 		       s.mptcpi_rcv_delta, r + 1, s.mptcpi_rcv_delta - (r + 1));
 
@@ -XXX,XX +XXX,XX @@ static int client(int pipefd)
 
 	switch (pf) {
 	case AF_INET:
-		fd = sock_connect_mptcp("127.0.0.1", "15432", IPPROTO_MPTCP);
+		fd = sock_connect_mptcp("127.0.0.1", "15432", proto_tx);
 		break;
 	case AF_INET6:
-		fd = sock_connect_mptcp("::1", "15432", IPPROTO_MPTCP);
+		fd = sock_connect_mptcp("::1", "15432", proto_tx);
 		break;
 	default:
 		xerror("Unknown pf %d\n", pf);
-- 
2.53.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Add -i option to enable TCP_INQ testing. This prepares for consolidating
TCP_INQ tests into a single binary by adding the necessary command-line
interface.

These codes are from mptcp_inq.c.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c        | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Replace pipe-based synchronization with Unix domain socket pairs
(SOCK_STREAM) for bidirectional communication between the server and
client processes. Pipes only support one-way flow, which required the
code to open and close the pipe file descriptor at awkward points; a
SOCK_STREAM socketpair gives a clean two-way channel.

These IPC helpers are reused from mptcp_inq.c (which used SOCK_DGRAM);
switching to SOCK_STREAM is correct here because the existing protocol
exchanges fixed-size, byte-aligned control records rather than discrete
datagrams.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 40 +++++++++----------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -XXX,XX +XXX,XX @@ static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w)
 		do_getsockopt_mptcp_full_info(s, fd);
 }
 
-static void connect_one_server(int fd, int pipefd)
+static void connect_one_server(int fd, int unixfd)
 {
 	char buf[4096], buf2[4096];
 	size_t len, i, total;
@@ -XXX,XX +XXX,XX @@ static void connect_one_server(int fd, int pipefd)
 	do_getsockopts(&s, fd, 0, 0);
 
 	/* un-block server */
-	ret = read(pipefd, buf2, 4);
+	ret = read(unixfd, buf2, 4);
 	assert(ret == 4);
-	close(pipefd);
+	close(unixfd);
 
 	assert(strncmp(buf2, "xmit", 4) == 0);
 
@@ -XXX,XX +XXX,XX @@ static void connect_one_server(int fd, int pipefd)
 	close(fd);
 }
 
-static void process_one_client(int fd, int pipefd)
+static void process_one_client(int fd, int unixfd)
 {
 	ssize_t ret, r, w;
 	struct so_state s;
@@ -XXX,XX +XXX,XX @@ static void process_one_client(int fd, int pipefd)
 	memset(&s, 0, sizeof(s));
 	do_getsockopts(&s, fd, 0, 0);
 
-	ret = write(pipefd, "xmit", 4);
+	ret = write(unixfd, "xmit", 4);
 	assert(ret == 4);
 
 	ret = read(fd, buf, sizeof(buf));
@@ -XXX,XX +XXX,XX @@ static int xaccept(int s)
 	return fd;
 }
 
-static int server(int pipefd)
+static int server(int unixfd)
 {
 	int fd = -1, r;
 
@@ -XXX,XX +XXX,XX @@ static int server(int pipefd)
 		break;
 	}
 
-	r = write(pipefd, "conn", 4);
+	r = write(unixfd, "conn", 4);
 	assert(r == 4);
 
 	alarm(15);
 	r = xaccept(fd);
 
-	process_one_client(r, pipefd);
+	process_one_client(r, unixfd);
 
 	close(fd);
 	return 0;
@@ -XXX,XX +XXX,XX @@ static void test_ip_tos_sockopt(int fd)
 		xerror("expect socklen_t == -1");
 }
 
-static int client(int pipefd)
+static int client(int unixfd)
 {
 	int fd = -1;
 
@@ -XXX,XX +XXX,XX @@ static int client(int pipefd)
 
 	test_ip_tos_sockopt(fd);
 
-	connect_one_server(fd, pipefd);
+	connect_one_server(fd, unixfd);
 
 	return 0;
 }
@@ -XXX,XX +XXX,XX @@ int main(int argc, char *argv[])
 {
 	int e1, e2, wstatus;
 	pid_t s, c, ret;
-	int pipefds[2];
+	int unixfds[2];
 
 	parse_opts(argc, argv);
 
 	init_rng();
 
-	e1 = pipe(pipefds);
+	e1 = socketpair(AF_UNIX, SOCK_STREAM, 0, unixfds);
 	if (e1 < 0)
-		die_perror("pipe");
+		die_perror("socketpair");
 
 	s = xfork();
 	if (s == 0) {
-		close(pipefds[0]);
-		ret = server(pipefds[1]);
-		close(pipefds[1]);
+		close(unixfds[0]);
+		ret = server(unixfds[1]);
+		close(unixfds[1]);
 		return ret;
 	}
 
-	close(pipefds[1]);
+	close(unixfds[1]);
 
 	/* wait until server bound a socket */
-	e1 = read(pipefds[0], &e1, 4);
+	e1 = read(unixfds[0], &e1, 4);
 	assert(e1 == 4);
 
 	c = xfork();
 	if (c == 0)
-		return client(pipefds[0]);
+		return client(unixfds[0]);
 
-	close(pipefds[0]);
+	close(unixfds[0]);
 
 	ret = waitpid(s, &wstatus, 0);
 	if (ret == -1)
-- 
2.53.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Use the exact remaining length ('len - total') when reading the echoed
data from the socket, instead of the full buffer size. This is possible
now that the payload length is passed from the client via the unixfd
control channel, making the read size explicit and avoiding any potential
over-read.

This also silences a false positive -Wstringop-overflow warning from GCC,
as the compiler can now prove that the destination buffer is large enough
for the specified read size.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/net/mptcp/mptcp_sockopt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Pass 'len' from the client to the server over the unixfd control channel so
that the client knows the server's payload size in advance for the FIONREAD
loop and TCP_CM_INQ validation in subsequent patches.

Also keep the unixfd open for the second write by moving 'close(unixfd)' to
the end of connect_one_server().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/net/mptcp/mptcp_sockopt.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Implement FIONREAD ioctl checks to validate available data size, ensuring
synchronization between write and read operations with non-blocking waits.

These codes are from mptcp_inq.c.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

From: Geliang Tang <tanggeliang@kylinos.cn>

Introduce huge data transfer tests (1-17 MB) to validate MPTCP socket
options under high-volume conditions, including proper EOF handling,
preparing for TCP_INQ support in subsequent patches.

These codes are from mptcp_inq.c, but here they have been placed into
two separate functions.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 135 ++++++++++++++++++
 1 file changed, 135 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -XXX,XX +XXX,XX @@ static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w)
 		do_getsockopt_mptcp_full_info(s, fd);
 }
 
+static void server_huge_transfer(int fd, int unixfd, size_t len)
+{
+	char buf[4096], buf2[4];
+	size_t i, total;
+	ssize_t ret;
+
+	for (i = 0; i < sizeof(buf) - 1; i++) {
+		buf[i] = rand() % 26;
+		buf[i] += 'A';
+	}
+
+	buf[i] = '\n';
+
+	ret = read(unixfd, buf2, 4);
+	assert(ret == 4);
+	assert(strncmp(buf2, "huge", 4) == 0);
+
+	total = rand() % (16 * 1024 * 1024);
+	total += (1 * 1024 * 1024);
+
+	ret = write(unixfd, &total, sizeof(total));
+	assert(ret == (ssize_t)sizeof(total));
+
+	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);
+
+	ret = write(fd, buf, 1);
+	assert(ret == 1);
+	ret = write(unixfd, "closed", 6);
+	assert(ret == 6);
+}
+
 static void connect_one_server(int fd, int unixfd)
 {
 	char buf[4096], buf2[4096];
@@ -XXX,XX +XXX,XX @@ static void connect_one_server(int fd, int unixfd)
 
 	if (proto_tx == IPPROTO_MPTCP && proto_rx == IPPROTO_MPTCP)
 		assert(s.mptcpi_rcv_delta == (uint64_t)total);
+
+	if (inq)
+		server_huge_transfer(fd, unixfd, len);
+
 	close(fd);
 	close(unixfd);
 }
 
+struct inq_msg {
+	char buf[4096];
+	union {
+		struct cmsghdr cmsg;
+		char msg_buf[4096];
+	} control;
+	struct iovec iov;
+	struct msghdr hdr;
+};
+
+static void inq_msg_init(struct inq_msg *m, size_t iov_len)
+{
+	memset(m, 0, sizeof(*m));
+	m->iov.iov_base = m->buf;
+	m->iov.iov_len = iov_len;
+	m->hdr.msg_iov = &m->iov;
+	m->hdr.msg_iovlen = 1;
+	m->hdr.msg_control = m->control.msg_buf;
+	m->hdr.msg_controllen = sizeof(m->control.msg_buf);
+}
+
+static void inq_msg_reset(struct inq_msg *m, size_t iov_len, void *base)
+{
+	m->iov.iov_base = base;
+	m->iov.iov_len = iov_len;
+	m->hdr.msg_controllen = sizeof(m->control.msg_buf);
+}
+
+static size_t client_huge_transfer(int fd, int unixfd)
+{
+	size_t expect_len;
+	ssize_t ret, tot;
+	struct inq_msg m;
+	char tmp[16];
+
+	inq_msg_init(&m, 1);
+
+	/* 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(m.buf))
+		xerror("expect len %zu too small\n", expect_len);
+
+	tot = 0;
+	do {
+		inq_msg_reset(&m, sizeof(m.buf), m.buf);
+		ret = recvmsg(fd, &m.hdr, 0);
+		if (ret < 0)
+			die_perror("recvmsg");
+		if (ret == 0)
+			xerror("unexpected EOF in huge recv");
+
+		tot += ret;
+	} 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);
+
+	inq_msg_reset(&m, 1, m.buf);
+	ret = recvmsg(fd, &m.hdr, 0);
+	if (ret < 0)
+		die_perror("recvmsg");
+	assert(ret == 1);
+
+	return tot + 1;
+}
+
 static void process_one_client(int fd, int unixfd)
 {
 	ssize_t ret, r, w;
@@ -XXX,XX +XXX,XX @@ static void process_one_client(int fd, int unixfd)
 		die_perror("write");
 	w = ret;
 
+	if (inq)
+		r += client_huge_transfer(fd, unixfd);
+
 	/* wait for hangup */
 	ret = read(fd, buf, 1);
 	if (ret != 0)
-- 
2.53.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Add wait_for_ack() helper to synchronize test steps by waiting until the
send queue is drained (all data ACKed). Used in server_huge_transfer()
to ensure reliable TCP_INQ validation.

These codes are from mptcp_inq.c.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 41 +++++++++++++++++++
 1 file changed, 41 insertions(+)

From: Geliang Tang <tanggeliang@kylinos.cn>

Replace read() with recvmsg() in process_one_client() to enable control
message (CMSG) handling. The original read(fd, buf, sizeof(buf)) is split
into two recvmsg() calls: the first reads exactly one byte, and the second
reads the remaining bytes. This allows the code to access CMSG data for
each received segment, facilitating the upcoming TCP_INQ validation.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 22 ++++++++++++++-----
 1 file changed, 16 insertions(+), 6 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Add get_tcp_inq() helper to extract and verify TCP_CM_INQ values from
received control messages. Integrate it into the echo test and huge data
transfer to validate in-queue byte counts at key stages, ensuring correct
TCP_INQ behavior with MPTCP.

Code adapted from mptcp_inq.c.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/net/mptcp/mptcp_sockopt.c       | 58 +++++++++++++++++++
 1 file changed, 58 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -XXX,XX +XXX,XX @@ static void inq_msg_reset(struct inq_msg *m, size_t iov_len, void *base)
 	m->hdr.msg_controllen = sizeof(m->control.msg_buf);
 }
 
+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) {
+			if (cmsg->cmsg_len < CMSG_LEN(sizeof(*inqv)))
+				xerror("TCP_CM_INQ cmsg_len too small: %u",
+				       cmsg->cmsg_len);
+			memcpy(inqv, CMSG_DATA(cmsg), sizeof(*inqv));
+			return;
+		}
+	}
+
+	xerror("could not find TCP_CM_INQ cmsg type");
+}
+
 static size_t client_huge_transfer(int fd, int unixfd)
 {
+	unsigned int tcp_inq;
 	size_t expect_len;
 	ssize_t ret, tot;
 	struct inq_msg m;
@@ -XXX,XX +XXX,XX @@ static size_t client_huge_transfer(int fd, int unixfd)
 			xerror("unexpected EOF in huge recv");
 
 		tot += ret;
+
+		get_tcp_inq(&m.hdr, &tcp_inq);
+
+		if (tcp_inq > expect_len - tot)
+			xerror("inq %d, remaining %zu 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);
@@ -XXX,XX +XXX,XX @@ static size_t client_huge_transfer(int fd, int unixfd)
 		die_perror("recvmsg");
 	assert(ret == 1);
 
+	get_tcp_inq(&m.hdr, &tcp_inq);
+
+	/* tcp_inq should be 1 due to received fin. */
+	assert(tcp_inq == 1);
+
 	return tot + 1;
 }
 
 static void process_one_client(int fd, int unixfd)
 {
+	unsigned int tcp_inq;
 	ssize_t ret, r, w;
 	struct so_state s;
 	size_t expect_len;
@@ -XXX,XX +XXX,XX @@ static void process_one_client(int fd, int unixfd)
 		die_perror("recvmsg");
 	r = ret;
 
+	if (inq) {
+		if (m.hdr.msg_controllen == 0)
+			xerror("msg_controllen is 0");
+
+		get_tcp_inq(&m.hdr, &tcp_inq);
+
+		/* expect cmsg to return expected - 1 */
+		assert((size_t)tcp_inq == (expect_len - 1));
+	}
+
 	inq_msg_reset(&m, sizeof(m.buf) - 1, m.buf + 1);
 	ret = recvmsg(fd, &m.hdr, 0);
 	if (ret < 0)
 		die_perror("recvmsg");
 	r += ret;
 
+	if (inq) {
+		/* should have gotten exact remainder of all pending data */
+		assert(ret == (ssize_t)tcp_inq);
+
+		/* should be 0, all drained */
+		get_tcp_inq(&m.hdr, &tcp_inq);
+		assert(tcp_inq == 0);
+	}
+
 	assert(s.mptcpi_rcv_delta <= (uint64_t)ret);
 
 	if (s.tcpi_rcv_delta)
@@ -XXX,XX +XXX,XX @@ static void process_one_client(int fd, int unixfd)
 		xerror("expected EOF, got %lu", ret);
 	r += ret;
 
+	if (inq) {
+		get_tcp_inq(&m.hdr, &tcp_inq);
+		assert(tcp_inq == 1);
+	}
+
 	do_getsockopts(&s, fd, r, w);
 	if (proto_tx == IPPROTO_MPTCP && proto_rx == IPPROTO_MPTCP &&
 	    s.mptcpi_rcv_delta != (uint64_t)r + 1)
-- 
2.53.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Update mptcp_sockopt.sh to use mptcp_sockopt binary instead of
mptcp_inq. This consolidates TCP_INQ testing into a single test binary
while maintaining equivalent test coverage.

Delete mptcp_inq binary and references since its functionality has been
fully integrated into mptcp_sockopt. This simplifies the test suite
structure and reduces maintenance overhead.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/net/mptcp/.gitignore  |   1 -
 tools/testing/selftests/net/mptcp/Makefile    |   1 -
 tools/testing/selftests/net/mptcp/mptcp_inq.c | 614 ------------------
 .../selftests/net/mptcp/mptcp_sockopt.sh      |   8 +-
 4 files changed, 4 insertions(+), 620 deletions(-)
 delete mode 100644 tools/testing/selftests/net/mptcp/mptcp_inq.c

diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/net/mptcp/.gitignore
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -XXX,XX +XXX,XX @@
 # SPDX-License-Identifier: GPL-2.0-only
 mptcp_connect
 mptcp_diag
-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 XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -XXX,XX +XXX,XX @@ TEST_PROGS := \
 TEST_GEN_FILES := \
 	mptcp_connect \
 	mptcp_diag \
-	mptcp_inq \
 	mptcp_sockopt \
 	pm_nl_ctl \
 # end of TEST_GEN_FILES
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
deleted file mode 100644
index XXXXXXX..XXXXXXX
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ /dev/null
@@ -XXX,XX +XXX,XX @@
-// SPDX-License-Identifier: GPL-2.0
-
-#define _GNU_SOURCE
-
-#include <assert.h>
-#include <errno.h>
-#include <fcntl.h>
-#include <limits.h>
-#include <string.h>
-#include <stdarg.h>
-#include <stdbool.h>
-#include <stdint.h>
-#include <inttypes.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <strings.h>
-#include <unistd.h>
-#include <time.h>
-
-#include <sys/ioctl.h>
-#include <sys/random.h>
-#include <sys/socket.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-
-#include <netdb.h>
-#include <netinet/in.h>
-
-#include <linux/tcp.h>
-#include <linux/sockios.h>
-#include <linux/compiler.h>
-
-#ifndef IPPROTO_MPTCP
-#define IPPROTO_MPTCP 262
-#endif
-#ifndef SOL_MPTCP
-#define SOL_MPTCP 284
-#endif
-
-static int pf = AF_INET;
-static int proto_tx = IPPROTO_MPTCP;
-static int proto_rx = IPPROTO_MPTCP;
-
-static void __noreturn die_perror(const char *msg)
-{
-	perror(msg);
-	exit(1);
-}
-
-static void die_usage(int r)
-{
-	fprintf(stderr, "Usage: mptcp_inq [-6] [ -t tcp|mptcp ] [ -r tcp|mptcp]\n");
-	exit(r);
-}
-
-static void __noreturn xerror(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	vfprintf(stderr, fmt, ap);
-	va_end(ap);
-	fputc('\n', stderr);
-	exit(1);
-}
-
-static const char *getxinfo_strerr(int err)
-{
-	if (err == EAI_SYSTEM)
-		return strerror(errno);
-
-	return gai_strerror(err);
-}
-
-static void xgetaddrinfo(const char *node, const char *service,
-			 struct addrinfo *hints,
-			 struct addrinfo **res)
-{
-	int err;
-
-again:
-	err = getaddrinfo(node, service, hints, res);
-	if (err) {
-		const char *errstr;
-
-		if (err == EAI_SOCKTYPE) {
-			hints->ai_protocol = IPPROTO_TCP;
-			goto again;
-		}
-
-		errstr = getxinfo_strerr(err);
-
-		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
-			node ? node : "", service ? service : "", errstr);
-		exit(1);
-	}
-}
-
-static int sock_listen_mptcp(const char * const listenaddr,
-			     const char * const port)
-{
-	int sock = -1;
-	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_MPTCP,
-		.ai_socktype = SOCK_STREAM,
-		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
-	};
-
-	hints.ai_family = pf;
-
-	struct addrinfo *a, *addr;
-	int one = 1;
-
-	xgetaddrinfo(listenaddr, port, &hints, &addr);
-	hints.ai_family = pf;
-
-	for (a = addr; a; a = a->ai_next) {
-		sock = socket(a->ai_family, a->ai_socktype, proto_rx);
-		if (sock < 0)
-			continue;
-
-		if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one,
-				     sizeof(one)))
-			perror("setsockopt");
-
-		if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
-			break; /* success */
-
-		perror("bind");
-		close(sock);
-		sock = -1;
-	}
-
-	freeaddrinfo(addr);
-
-	if (sock < 0)
-		xerror("could not create listen socket");
-
-	if (listen(sock, 20))
-		die_perror("listen");
-
-	return sock;
-}
-
-static int sock_connect_mptcp(const char * const remoteaddr,
-			      const char * const port, int proto)
-{
-	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_MPTCP,
-		.ai_socktype = SOCK_STREAM,
-	};
-	struct addrinfo *a, *addr;
-	int sock = -1;
-
-	hints.ai_family = pf;
-
-	xgetaddrinfo(remoteaddr, port, &hints, &addr);
-	for (a = addr; a; a = a->ai_next) {
-		sock = socket(a->ai_family, a->ai_socktype, proto);
-		if (sock < 0)
-			continue;
-
-		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
-			break; /* success */
-
-		die_perror("connect");
-	}
-
-	if (sock < 0)
-		xerror("could not create connect socket");
-
-	freeaddrinfo(addr);
-	return sock;
-}
-
-static int protostr_to_num(const char *s)
-{
-	if (strcasecmp(s, "tcp") == 0)
-		return IPPROTO_TCP;
-	if (strcasecmp(s, "mptcp") == 0)
-		return IPPROTO_MPTCP;
-
-	die_usage(1);
-	return 0;
-}
-
-static void parse_opts(int argc, char **argv)
-{
-	int c;
-
-	while ((c = getopt(argc, argv, "h6t:r:")) != -1) {
-		switch (c) {
-		case 'h':
-			die_usage(0);
-			break;
-		case '6':
-			pf = AF_INET6;
-			break;
-		case 't':
-			proto_tx = protostr_to_num(optarg);
-			break;
-		case 'r':
-			proto_rx = protostr_to_num(optarg);
-			break;
-		default:
-			die_usage(1);
-			break;
-		}
-	}
-}
-
-/* wait up to timeout milliseconds */
-static void wait_for_ack(int fd, int timeout, size_t total)
-{
-	int i;
-
-	for (i = 0; i < timeout; i++) {
-		int nsd, ret, queued = -1;
-		struct timespec req;
-
-		ret = ioctl(fd, TIOCOUTQ, &queued);
-		if (ret < 0)
-			die_perror("TIOCOUTQ");
-
-		ret = ioctl(fd, SIOCOUTQNSD, &nsd);
-		if (ret < 0)
-			die_perror("SIOCOUTQNSD");
-
-		if ((size_t)queued > total)
-			xerror("TIOCOUTQ %u, but only %zu expected\n", queued, total);
-		assert(nsd <= queued);
-
-		if (queued == 0)
-			return;
-
-		/* wait for peer to ack rx of all data */
-		req.tv_sec = 0;
-		req.tv_nsec = 1 * 1000 * 1000ul; /* 1ms */
-		nanosleep(&req, NULL);
-	}
-
-	xerror("still tx data queued after %u ms\n", timeout);
-}
-
-static void connect_one_server(int fd, int unixfd)
-{
-	size_t len, i, total, sent;
-	char buf[4096], buf2[4096];
-	ssize_t ret;
-
-	len = rand() % (sizeof(buf) - 1);
-
-	if (len < 128)
-		len = 128;
-
-	for (i = 0; i < len ; i++) {
-		buf[i] = rand() % 26;
-		buf[i] += 'A';
-	}
-
-	buf[i] = '\n';
-
-	/* un-block server */
-	ret = read(unixfd, buf2, 4);
-	assert(ret == 4);
-
-	assert(strncmp(buf2, "xmit", 4) == 0);
-
-	ret = write(unixfd, &len, sizeof(len));
-	assert(ret == (ssize_t)sizeof(len));
-
-	ret = write(fd, buf, len);
-	if (ret < 0)
-		die_perror("write");
-
-	if (ret != (ssize_t)len)
-		xerror("short write");
-
-	ret = read(unixfd, buf2, 4);
-	assert(strncmp(buf2, "huge", 4) == 0);
-
-	total = rand() % (16 * 1024 * 1024);
-	total += (1 * 1024 * 1024);
-	sent = total;
-
-	ret = write(unixfd, &total, sizeof(total));
-	assert(ret == (ssize_t)sizeof(total));
-
-	wait_for_ack(fd, 5000, len);
-
-	while (total > 0) {
-		if (total > sizeof(buf))
-			len = sizeof(buf);
-		else
-			len = total;
-
-		ret = write(fd, buf, len);
-		if (ret < 0)
-			die_perror("write");
-		total -= ret;
-
-		/* we don't have to care about buf content, only
-		 * number of total bytes sent
-		 */
-	}
-
-	ret = read(unixfd, buf2, 4);
-	assert(ret == 4);
-	assert(strncmp(buf2, "shut", 4) == 0);
-
-	wait_for_ack(fd, 5000, sent);
-
-	ret = write(fd, buf, 1);
-	assert(ret == 1);
-	close(fd);
-	ret = write(unixfd, "closed", 6);
-	assert(ret == 6);
-
-	close(unixfd);
-}
-
-static void get_tcp_inq(struct msghdr *msgh, unsigned int *inqv)
-{
-	struct cmsghdr *cmsg;
-
-	for (cmsg = CMSG_FIRSTHDR(msgh); cmsg ; cmsg = CMSG_NXTHDR(msgh, cmsg)) {
-		if (cmsg->cmsg_level == IPPROTO_TCP && cmsg->cmsg_type == TCP_CM_INQ) {
-			memcpy(inqv, CMSG_DATA(cmsg), sizeof(*inqv));
-			return;
-		}
-	}
-
-	xerror("could not find TCP_CM_INQ cmsg type");
-}
-
-static void process_one_client(int fd, int unixfd)
-{
-	unsigned int tcp_inq;
-	size_t expect_len;
-	char msg_buf[4096];
-	char buf[4096];
-	char tmp[16];
-	struct iovec iov = {
-		.iov_base = buf,
-		.iov_len = 1,
-	};
-	struct msghdr msg = {
-		.msg_iov = &iov,
-		.msg_iovlen = 1,
-		.msg_control = msg_buf,
-		.msg_controllen = sizeof(msg_buf),
-	};
-	ssize_t ret, tot;
-
-	ret = write(unixfd, "xmit", 4);
-	assert(ret == 4);
-
-	ret = read(unixfd, &expect_len, sizeof(expect_len));
-	assert(ret == (ssize_t)sizeof(expect_len));
-
-	if (expect_len > sizeof(buf))
-		xerror("expect len %zu exceeds buffer size", expect_len);
-
-	for (;;) {
-		struct timespec req;
-		unsigned int queued;
-
-		ret = ioctl(fd, FIONREAD, &queued);
-		if (ret < 0)
-			die_perror("FIONREAD");
-		if (queued > expect_len)
-			xerror("FIONREAD returned %u, but only %zu expected\n",
-			       queued, expect_len);
-		if (queued == expect_len)
-			break;
-
-		req.tv_sec = 0;
-		req.tv_nsec = 1000 * 1000ul;
-		nanosleep(&req, NULL);
-	}
-
-	/* read one byte, expect cmsg to return expected - 1 */
-	ret = recvmsg(fd, &msg, 0);
-	if (ret < 0)
-		die_perror("recvmsg");
-
-	if (msg.msg_controllen == 0)
-		xerror("msg_controllen is 0");
-
-	get_tcp_inq(&msg, &tcp_inq);
-
-	assert((size_t)tcp_inq == (expect_len - 1));
-
-	iov.iov_len = sizeof(buf);
-	ret = recvmsg(fd, &msg, 0);
-	if (ret < 0)
-		die_perror("recvmsg");
-
-	/* should have gotten exact remainder of all pending data */
-	assert(ret == (ssize_t)tcp_inq);
-
-	/* should be 0, all drained */
-	get_tcp_inq(&msg, &tcp_inq);
-	assert(tcp_inq == 0);
-
-	/* request a large swath of data. */
-	ret = write(unixfd, "huge", 4);
-	assert(ret == 4);
-
-	ret = read(unixfd, &expect_len, sizeof(expect_len));
-	assert(ret == (ssize_t)sizeof(expect_len));
-
-	/* peer should send us a few mb of data */
-	if (expect_len <= sizeof(buf))
-		xerror("expect len %zu too small\n", expect_len);
-
-	tot = 0;
-	do {
-		iov.iov_len = sizeof(buf);
-		ret = recvmsg(fd, &msg, 0);
-		if (ret < 0)
-			die_perror("recvmsg");
-
-		tot += ret;
-
-		get_tcp_inq(&msg, &tcp_inq);
-
-		if (tcp_inq > expect_len - tot)
-			xerror("inq %d, remaining %d total_len %d\n",
-			       tcp_inq, expect_len - tot, (int)expect_len);
-
-		assert(tcp_inq <= expect_len - tot);
-	} while ((size_t)tot < expect_len);
-
-	ret = write(unixfd, "shut", 4);
-	assert(ret == 4);
-
-	/* wait for hangup. Should have received one more byte of data. */
-	ret = read(unixfd, tmp, sizeof(tmp));
-	assert(ret == 6);
-	assert(strncmp(tmp, "closed", 6) == 0);
-
-	sleep(1);
-
-	iov.iov_len = 1;
-	ret = recvmsg(fd, &msg, 0);
-	if (ret < 0)
-		die_perror("recvmsg");
-	assert(ret == 1);
-
-	get_tcp_inq(&msg, &tcp_inq);
-
-	/* tcp_inq should be 1 due to received fin. */
-	assert(tcp_inq == 1);
-
-	iov.iov_len = 1;
-	ret = recvmsg(fd, &msg, 0);
-	if (ret < 0)
-		die_perror("recvmsg");
-
-	/* expect EOF */
-	assert(ret == 0);
-	get_tcp_inq(&msg, &tcp_inq);
-	assert(tcp_inq == 1);
-
-	close(fd);
-}
-
-static int xaccept(int s)
-{
-	int fd = accept(s, NULL, 0);
-
-	if (fd < 0)
-		die_perror("accept");
-
-	return fd;
-}
-
-static int server(int unixfd)
-{
-	int fd = -1, r, on = 1;
-
-	switch (pf) {
-	case AF_INET:
-		fd = sock_listen_mptcp("127.0.0.1", "15432");
-		break;
-	case AF_INET6:
-		fd = sock_listen_mptcp("::1", "15432");
-		break;
-	default:
-		xerror("Unknown pf %d\n", pf);
-		break;
-	}
-
-	r = write(unixfd, "conn", 4);
-	assert(r == 4);
-
-	alarm(15);
-	r = xaccept(fd);
-
-	if (-1 == setsockopt(r, IPPROTO_TCP, TCP_INQ, &on, sizeof(on)))
-		die_perror("setsockopt");
-
-	process_one_client(r, unixfd);
-
-	close(fd);
-	return 0;
-}
-
-static int client(int unixfd)
-{
-	int fd = -1;
-
-	alarm(15);
-
-	switch (pf) {
-	case AF_INET:
-		fd = sock_connect_mptcp("127.0.0.1", "15432", proto_tx);
-		break;
-	case AF_INET6:
-		fd = sock_connect_mptcp("::1", "15432", proto_tx);
-		break;
-	default:
-		xerror("Unknown pf %d\n", pf);
-	}
-
-	connect_one_server(fd, unixfd);
-
-	return 0;
-}
-
-static void init_rng(void)
-{
-	unsigned int foo;
-
-	if (getrandom(&foo, sizeof(foo), 0) == -1) {
-		perror("getrandom");
-		exit(1);
-	}
-
-	srand(foo);
-}
-
-static pid_t xfork(void)
-{
-	pid_t p = fork();
-
-	if (p < 0)
-		die_perror("fork");
-	else if (p == 0)
-		init_rng();
-
-	return p;
-}
-
-static int rcheck(int wstatus, const char *what)
-{
-	if (WIFEXITED(wstatus)) {
-		if (WEXITSTATUS(wstatus) == 0)
-			return 0;
-		fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus));
-		return WEXITSTATUS(wstatus);
-	} else if (WIFSIGNALED(wstatus)) {
-		xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus));
-	} else if (WIFSTOPPED(wstatus)) {
-		xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus));
-	}
-
-	return 111;
-}
-
-int main(int argc, char *argv[])
-{
-	int e1, e2, wstatus;
-	pid_t s, c, ret;
-	int unixfds[2];
-
-	parse_opts(argc, argv);
-
-	e1 = socketpair(AF_UNIX, SOCK_DGRAM, 0, unixfds);
-	if (e1 < 0)
-		die_perror("pipe");
-
-	s = xfork();
-	if (s == 0) {
-		close(unixfds[0]);
-		ret = server(unixfds[1]);
-		close(unixfds[1]);
-		return ret;
-	}
-
-	close(unixfds[1]);
-
-	/* wait until server bound a socket */
-	e1 = read(unixfds[0], &e1, 4);
-	assert(e1 == 4);
-
-	c = xfork();
-	if (c == 0)
-		return client(unixfds[0]);
-
-	close(unixfds[0]);
-
-	ret = waitpid(s, &wstatus, 0);
-	if (ret == -1)
-		die_perror("waitpid");
-	e1 = rcheck(wstatus, "server");
-	ret = waitpid(c, &wstatus, 0);
-	if (ret == -1)
-		die_perror("waitpid");
-	e2 = rcheck(wstatus, "client");
-
-	return e1 ? e1 : e2;
-}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index XXXXXXX..XXXXXXX 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -XXX,XX +XXX,XX @@ run_tests()
 do_tcpinq_test()
 {
 	print_title "TCP_INQ cmsg/ioctl $*"
-	ip netns exec "$ns_sbox" ./mptcp_inq "$@"
+	ip netns exec "$ns_sbox" ./mptcp_sockopt "$@"
 	local lret=$?
 	if [ $lret -ne 0 ];then
 		ret=$lret
@@ -XXX,XX +XXX,XX @@ do_tcpinq_tests()
 
 	local args
 	for args in "-t tcp" "-r tcp"; do
-		do_tcpinq_test $args
+		do_tcpinq_test $args -i
 		lret=$?
 		if [ $lret -ne 0 ] ; then
 			return $lret
 		fi
-		do_tcpinq_test -6 $args
+		do_tcpinq_test -6 $args -i
 		lret=$?
 		if [ $lret -ne 0 ] ; then
 			return $lret
 		fi
 	done
 
-	do_tcpinq_test -r tcp -t tcp
+	do_tcpinq_test -r tcp -t tcp -i
 
 	return $?
 }
-- 
2.53.0