selftests: mptcp: more stable diag tests

The mentioned test-case still use an hard-coded-len sleep to
wait for a relative large number of connection to be established.

On very slow VM and with debug build such timeout could be exceeded,
causing failures in our CI.

Address the issue polling for the expected condition several times,
up to an unreasonable high amount of time. On reasonably fast system
the self-tests will be faster then before, on very slow one we will
still catch the correct condition.

Fixes: df62f2ec ("selftests/mptcp: add diag interface tests")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

tools/testing/selftests/net/mptcp/diag.sh

@@ -61,6 +61,39 @@ chk_msk_nr()
 	__chk_nr "grep -c token:" $*
 }
 
+wait_msk_nr()
+{
+	local condition="grep -c token:"
+	local expected=$1
+	local timeout=20
+	local msg nr
+	local max=0
+	local i=0
+
+	shift 1
+	msg=$*
+
+	while [ $i -lt $timeout ]; do
+		nr=$(ss -inmHMN $ns | $condition)
+		[ $nr == $expected ] && break;
+		[ $nr -gt $max ] && max=$nr
+		i=$((i + 1))
+		sleep 1
+	done
+
+	printf "%-50s" "$msg"
+	if [ $i -ge $timeout ]; then
+		echo "[ fail ] timeout while expecting $expected max $max last $nr"
+		ret=$test_cnt
+	elif [ $nr != $expected ]; then
+		echo "[ fail ] expected $expected found $nr"
+		ret=$test_cnt
+	else
+		echo "[  ok  ]"
+	fi
+	test_cnt=$((test_cnt+1))
+}
+
 chk_msk_fallback_nr()
 {
 		__chk_nr "grep -c fallback" $*
@@ -146,7 +179,7 @@ ip -n $ns link set dev lo up
 echo "a" | \
 	timeout ${timeout_test} \
 		ip netns exec $ns \
-			./mptcp_connect -p 10000 -l -t ${timeout_poll} \
+			./mptcp_connect -p 10000 -l -t ${timeout_poll} -w 20 \
 				0.0.0.0 >/dev/null &
 wait_local_port_listen $ns 10000
 chk_msk_nr 0 "no msk on netns creation"
@@ -155,7 +188,7 @@ chk_msk_listen 10000
 echo "b" | \
 	timeout ${timeout_test} \
 		ip netns exec $ns \
-			./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \
+			./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} -w 20 \
 				127.0.0.1 >/dev/null &
 wait_connected $ns 10000
 chk_msk_nr 2 "after MPC handshake "
@@ -167,13 +200,13 @@ flush_pids
 echo "a" | \
 	timeout ${timeout_test} \
 		ip netns exec $ns \
-			./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \
+			./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} -w 20 \
 				0.0.0.0 >/dev/null &
 wait_local_port_listen $ns 10001
 echo "b" | \
 	timeout ${timeout_test} \
 		ip netns exec $ns \
-			./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \
+			./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} -w 20 \
 				127.0.0.1 >/dev/null &
 wait_connected $ns 10001
 chk_msk_fallback_nr 1 "check fallback"
@@ -184,7 +217,7 @@ for I in `seq 1 $NR_CLIENTS`; do
 	echo "a" | \
 		timeout ${timeout_test} \
 			ip netns exec $ns \
-				./mptcp_connect -p $((I+10001)) -l -w 10 \
+				./mptcp_connect -p $((I+10001)) -l -w 20 \
 					-t ${timeout_poll} 0.0.0.0 >/dev/null &
 done
 wait_local_port_listen $ns $((NR_CLIENTS + 10001))
@@ -193,12 +226,11 @@ for I in `seq 1 $NR_CLIENTS`; do
 	echo "b" | \
 		timeout ${timeout_test} \
 			ip netns exec $ns \
-				./mptcp_connect -p $((I+10001)) -w 10 \
+				./mptcp_connect -p $((I+10001)) -w 20 \
 					-t ${timeout_poll} 127.0.0.1 >/dev/null &
 done
-sleep 1.5
 
-chk_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
+wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
 flush_pids
 
 exit $ret