Merge branch 'selftests-mptcp-mark-unstable-subtests-as-flaky'

Matthieu Baerts says:

====================
selftests: mptcp: mark unstable subtests as flaky

Some subtests can be unstable, failing once every X runs. Fixing them
can take time: there could be an issue in the kernel or in the subtest,
and it is then important to do a proper analysis, not to hide real bugs.

To avoid creating noises on the different CIs where tests are more
unstable than on our side, some subtests have been marked as flaky. As a
result, errors with these subtests (if any) are ignored.

Note that the MPTCP CI will continue to track these flaky subtests. All
these unstable subtests are also tracked by our bug tracker.

These are fixes for the -net tree, because the instabilities are visible
there. The first patch introducing the flake support has no 'Fixes'
tags, mainly because it requires recent and important refactoring done
in all MPTCP selftests. Backporting that to old versions where the flaky
tests have been introduced would be too difficult, and probably not
worth it. The other patches, adding MPTCP_LIB_SUBTEST_FLAKY=1, have a
Fixes tag, simply to ease the backport of the future fixes removing them
along with the proper fix.
====================

Link: https://lore.kernel.org/r/20240524-upstream-net-20240524-selftests-mptcp-flaky-v1-0-a352362f3f8e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 40 insertions, 6 deletions

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index fefa9173bdaa..2b66c5fa71eb 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -261,6 +261,8 @@ reset()
 
 	TEST_NAME="${1}"
 
+	MPTCP_LIB_SUBTEST_FLAKY=0 # reset if modified
+
 	if skip_test; then
 		MPTCP_LIB_TEST_COUNTER=$((MPTCP_LIB_TEST_COUNTER+1))
 		last_test_ignored=1
@@ -448,7 +450,9 @@ reset_with_tcp_filter()
 # $1: err msg
 fail_test()
 {
-	ret=${KSFT_FAIL}
+	if ! mptcp_lib_subtest_is_flaky; then
+		ret=${KSFT_FAIL}
+	fi
 
 	if [ ${#} -gt 0 ]; then
 		print_fail "${@}"
@@ -3069,6 +3073,7 @@ fullmesh_tests()
 fastclose_tests()
 {
 	if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=1024 fastclose=client \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
@@ -3077,6 +3082,7 @@ fastclose_tests()
 	fi
 
 	if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=1024 fastclose=server \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0 0 0 0 1
@@ -3095,6 +3101,7 @@ fail_tests()
 {
 	# single subflow
 	if reset_with_fail "Infinite map" 1; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=128 \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)"
@@ -3103,6 +3110,7 @@ fail_tests()
 
 	# multiple subflows
 	if reset_with_fail "MP_FAIL MP_RST" 2; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		tc -n $ns2 qdisc add dev ns2eth1 root netem rate 1mbit delay 5ms
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index ad2ebda5cb64..6ffa9b7a3260 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -21,6 +21,7 @@ declare -rx MPTCP_LIB_AF_INET6=10
 
 MPTCP_LIB_SUBTESTS=()
 MPTCP_LIB_SUBTESTS_DUPLICATED=0
+MPTCP_LIB_SUBTEST_FLAKY=0
 MPTCP_LIB_TEST_COUNTER=0
 MPTCP_LIB_TEST_FORMAT="%02u %-50s"
 MPTCP_LIB_IP_MPTCP=0
@@ -41,6 +42,16 @@ else
 	readonly MPTCP_LIB_COLOR_RESET=
 fi
 
+# SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY env var can be set not to ignore errors
+# from subtests marked as flaky
+mptcp_lib_override_flaky() {
+	[ "${SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY:-}" = 1 ]
+}
+
+mptcp_lib_subtest_is_flaky() {
+	[ "${MPTCP_LIB_SUBTEST_FLAKY}" = 1 ] && ! mptcp_lib_override_flaky
+}
+
 # $1: color, $2: text
 mptcp_lib_print_color() {
 	echo -e "${MPTCP_LIB_START_PRINT:-}${*}${MPTCP_LIB_COLOR_RESET}"
@@ -72,7 +83,16 @@ mptcp_lib_pr_skip() {
 }
 
 mptcp_lib_pr_fail() {
-	mptcp_lib_print_err "[FAIL]${1:+ ${*}}"
+	local title cmt
+
+	if mptcp_lib_subtest_is_flaky; then
+		title="IGNO"
+		cmt=" (flaky)"
+	else
+		title="FAIL"
+	fi
+
+	mptcp_lib_print_err "[${title}]${cmt}${1:+ ${*}}"
 }
 
 mptcp_lib_pr_info() {
@@ -208,7 +228,13 @@ mptcp_lib_result_pass() {
 
 # $1: test name
 mptcp_lib_result_fail() {
-	__mptcp_lib_result_add "not ok" "${1}"
+	if mptcp_lib_subtest_is_flaky; then
+		# It might sound better to use 'not ok # TODO' or 'ok # SKIP',
+		# but some CIs don't understand 'TODO' and treat SKIP as errors.
+		__mptcp_lib_result_add "ok" "${1} # IGNORE Flaky"
+	else
+		__mptcp_lib_result_add "not ok" "${1}"
+	fi
 }
 
 # $1: test name
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 4b14b4412166..f74e1c3c126d 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -244,7 +244,7 @@ run_test()
 	do_transfer $small $large $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
-	if [ $lret -ne 0 ]; then
+	if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
 	fi
@@ -254,7 +254,7 @@ run_test()
 	do_transfer $large $small $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
-	if [ $lret -ne 0 ]; then
+	if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
 	fi
@@ -290,7 +290,7 @@ run_test 10 10 0 0 "balanced bwidth"
 run_test 10 10 1 25 "balanced bwidth with unbalanced delay"
 
 # we still need some additional infrastructure to pass the following test-cases
-run_test 10 3 0 0 "unbalanced bwidth"
+MPTCP_LIB_SUBTEST_FLAKY=1 run_test 10 3 0 0 "unbalanced bwidth"
 run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay"
 run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay"