selftests: mptcp: add packet mark test case

Extend mptcp_connect tool with SO_MARK support (-M <value>) and
add a test case that checks that the packet mark gets copied to all
subflows.

This is done by only allowing packets with either skb->mark 1 or 2
via iptables.

DROP rule packet counter is checked; if its not zero, print an error
message and fail the test case.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 299 insertions, 2 deletions

diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index 00bb158b4a5d..f1464f09b080 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -6,7 +6,7 @@ KSFT_KHDR_INSTALL := 1
 CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g  -I$(top_srcdir)/usr/include
 
 TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
-	      simult_flows.sh
+	      simult_flows.sh mptcp_sockopt.sh
 
 TEST_GEN_FILES = mptcp_connect pm_nl_ctl
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 69d89b5d666f..2f207cf33661 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -57,6 +57,7 @@ static bool cfg_join;
 static bool cfg_remove;
 static unsigned int cfg_do_w;
 static int cfg_wait;
+static uint32_t cfg_mark;
 
 static void die_usage(void)
 {
@@ -69,6 +70,7 @@ static void die_usage(void)
 	fprintf(stderr, "\t-p num -- use port num\n");
 	fprintf(stderr, "\t-s [MPTCP|TCP] -- use mptcp(default) or tcp sockets\n");
 	fprintf(stderr, "\t-m [poll|mmap|sendfile] -- use poll(default)/mmap+write/sendfile\n");
+	fprintf(stderr, "\t-M mark -- set socket packet mark\n");
 	fprintf(stderr, "\t-u -- check mptcp ulp\n");
 	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
 	exit(1);
@@ -140,6 +142,17 @@ static void set_sndbuf(int fd, unsigned int size)
 	}
 }
 
+static void set_mark(int fd, uint32_t mark)
+{
+	int err;
+
+	err = setsockopt(fd, SOL_SOCKET, SO_MARK, &mark, sizeof(mark));
+	if (err) {
+		perror("set SO_MARK");
+		exit(1);
+	}
+}
+
 static int sock_listen_mptcp(const char * const listenaddr,
 			     const char * const port)
 {
@@ -248,6 +261,9 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 			continue;
 		}
 
+		if (cfg_mark)
+			set_mark(sock, cfg_mark);
+
 		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
 			break; /* success */
 
@@ -830,7 +846,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:")) != -1) {
+	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
@@ -880,6 +896,9 @@ static void parse_opts(int argc, char **argv)
 		case 'w':
 			cfg_wait = atoi(optarg)*1000000;
 			break;
+		case 'M':
+			cfg_mark = strtol(optarg, NULL, 0);
+			break;
 		}
 	}
 
@@ -911,6 +930,8 @@ int main(int argc, char *argv[])
 			set_rcvbuf(fd, cfg_rcvbuf);
 		if (cfg_sndbuf)
 			set_sndbuf(fd, cfg_sndbuf);
+		if (cfg_mark)
+			set_mark(fd, cfg_mark);
 
 		return main_loop_s(fd);
 	}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
new file mode 100755
index 000000000000..2fa13946ac04
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -0,0 +1,276 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ret=0
+sin=""
+sout=""
+cin=""
+cout=""
+ksft_skip=4
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
+mptcp_connect=""
+do_all_tests=1
+
+add_mark_rules()
+{
+	local ns=$1
+	local m=$2
+
+	for t in iptables ip6tables; do
+		# just to debug: check we have multiple subflows connection requests
+		ip netns exec $ns $t -A OUTPUT -p tcp --syn -m mark --mark $m -j ACCEPT
+
+		# RST packets might be handled by a internal dummy socket
+		ip netns exec $ns $t -A OUTPUT -p tcp --tcp-flags RST RST -m mark --mark 0 -j ACCEPT
+
+		ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark $m -j ACCEPT
+		ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark 0 -j DROP
+	done
+}
+
+init()
+{
+	rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+
+	ns1="ns1-$rndh"
+	ns2="ns2-$rndh"
+
+	for netns in "$ns1" "$ns2";do
+		ip netns add $netns || exit $ksft_skip
+		ip -net $netns link set lo up
+		ip netns exec $netns sysctl -q net.mptcp.enabled=1
+		ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0
+		ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0
+	done
+
+	for i in `seq 1 4`; do
+		ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2"
+		ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i
+		ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad
+		ip -net "$ns1" link set ns1eth$i up
+
+		ip -net "$ns2" addr add 10.0.$i.2/24 dev ns2eth$i
+		ip -net "$ns2" addr add dead:beef:$i::2/64 dev ns2eth$i nodad
+		ip -net "$ns2" link set ns2eth$i up
+
+		# let $ns2 reach any $ns1 address from any interface
+		ip -net "$ns2" route add default via 10.0.$i.1 dev ns2eth$i metric 10$i
+
+		ip netns exec $ns1 ./pm_nl_ctl add 10.0.$i.1 flags signal
+		ip netns exec $ns1 ./pm_nl_ctl add dead:beef:$i::1 flags signal
+
+		ip netns exec $ns2 ./pm_nl_ctl add 10.0.$i.2 flags signal
+		ip netns exec $ns2 ./pm_nl_ctl add dead:beef:$i::2 flags signal
+	done
+
+	ip netns exec $ns1 ./pm_nl_ctl limits 8 8
+	ip netns exec $ns2 ./pm_nl_ctl limits 8 8
+
+	add_mark_rules $ns1 1
+	add_mark_rules $ns2 2
+}
+
+cleanup()
+{
+	for netns in "$ns1" "$ns2"; do
+		ip netns del $netns
+	done
+	rm -f "$cin" "$cout"
+	rm -f "$sin" "$sout"
+}
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+iptables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run all tests without iptables tool"
+	exit $ksft_skip
+fi
+
+ip6tables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run all tests without ip6tables tool"
+	exit $ksft_skip
+fi
+
+check_mark()
+{
+	local ns=$1
+	local af=$2
+
+	tables=iptables
+
+	if [ $af -eq 6 ];then
+		tables=ip6tables
+	fi
+
+	counters=$(ip netns exec $ns $tables -v -L OUTPUT | grep DROP)
+	values=${counters%DROP*}
+
+	for v in $values; do
+		if [ $v -ne 0 ]; then
+			echo "FAIL: got $tables $values in ns $ns , not 0 - not all expected packets marked" 1>&2
+			return 1
+		fi
+	done
+
+	return 0
+}
+
+print_file_err()
+{
+	ls -l "$1" 1>&2
+	echo "Trailing bytes are: "
+	tail -c 27 "$1"
+}
+
+check_transfer()
+{
+	in=$1
+	out=$2
+	what=$3
+
+	cmp "$in" "$out" > /dev/null 2>&1
+	if [ $? -ne 0 ] ;then
+		echo "[ FAIL ] $what does not match (in, out):"
+		print_file_err "$in"
+		print_file_err "$out"
+		ret=1
+
+		return 1
+	fi
+
+	return 0
+}
+
+# $1: IP address
+is_v6()
+{
+	[ -z "${1##*:*}" ]
+}
+
+do_transfer()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	cl_proto="$3"
+	srv_proto="$4"
+	connect_addr="$5"
+
+	port=12001
+
+	:> "$cout"
+	:> "$sout"
+
+	mptcp_connect="./mptcp_connect -r 20"
+
+	local local_addr
+	if is_v6 "${connect_addr}"; then
+		local_addr="::"
+	else
+		local_addr="0.0.0.0"
+	fi
+
+	timeout ${timeout_test} \
+		ip netns exec ${listener_ns} \
+			$mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} \
+				${local_addr} < "$sin" > "$sout" &
+	spid=$!
+
+	sleep 1
+
+	timeout ${timeout_test} \
+		ip netns exec ${connector_ns} \
+			$mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} \
+				$connect_addr < "$cin" > "$cout" &
+
+	cpid=$!
+
+	wait $cpid
+	retc=$?
+	wait $spid
+	rets=$?
+
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+		echo " client exit code $retc, server $rets" 1>&2
+		echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2
+		ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port"
+
+		echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2
+		ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port"
+
+		ret=1
+		return 1
+	fi
+
+	if [ $local_addr = "::" ];then
+		check_mark $listener_ns 6
+		check_mark $connector_ns 6
+	else
+		check_mark $listener_ns 4
+		check_mark $connector_ns 4
+	fi
+
+	check_transfer $cin $sout "file received by server"
+
+	rets=$?
+
+	if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
+		return 0
+	fi
+
+	return 1
+}
+
+make_file()
+{
+	name=$1
+	who=$2
+	size=$3
+
+	dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null
+	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
+
+	echo "Created $name (size $size KB) containing data sent by $who"
+}
+
+run_tests()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	connect_addr="$3"
+	lret=0
+
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr}
+
+	lret=$?
+
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return
+	fi
+}
+
+sin=$(mktemp)
+sout=$(mktemp)
+cin=$(mktemp)
+cout=$(mktemp)
+init
+make_file "$cin" "client" 1
+make_file "$sin" "server" 1
+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
+
+exit $ret