selftests/net: packetdrill: report benign debug flakes as xfail

JIRA: https://issues.redhat.com/browse/RHEL-88651
Upstream Status: net.git commit 912d6f6

commit 912d6f6
Author: Willem de Bruijn <willemb@google.com>
Date:   Fri Jan 3 06:31:14 2025 -0500

    selftests/net: packetdrill: report benign debug flakes as xfail

    A few recently added packetdrill tests that are known time sensitive
    (e.g., because testing timestamping) occasionally fail in debug mode:
    https://netdev.bots.linux.dev/contest.html?executor=vmksft-packetdrill-dbg

    These failures are well understood. Correctness of the tests is
    verified in non-debug mode. Continue running in debug mode also, to
    keep coverage with debug instrumentation.

    But, only in debug mode, mark these tests with well understood
    timing issues as XFAIL (known failing) rather than FAIL when failing.

    Introduce an allow list xfail_list with known cases.

    Expand the ktap infrastructure with XFAIL support.

    Fixes: eab3598 ("selftests/net: packetdrill: import tcp/fast_recovery, tcp/nagle, tcp/timestamping")
    Reported-by: Jakub Kicinski <kuba@kernel.org>
    Closes: https://lore.kernel.org/netdev/20241218100013.0c698629@kernel.org/
    Signed-off-by: Willem de Bruijn <willemb@google.com>
    Link: https://patch.msgid.link/20250103113142.129251-1-willemdebruijn.kernel@gmail.com
    Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Signed-off-by: Hangbin Liu <haliu@redhat.com>

Author: Hangbin Liu

tools/testing/selftests/kselftest/ktap_helpers.sh

@@ -7,6 +7,7 @@
 KTAP_TESTNO=1
 KTAP_CNT_PASS=0
 KTAP_CNT_FAIL=0
+KTAP_CNT_XFAIL=0
 KTAP_CNT_SKIP=0
 
 KSFT_PASS=0
@@ -69,6 +70,16 @@ ktap_test_skip() {
 	KTAP_CNT_SKIP=$((KTAP_CNT_SKIP+1))
 }
 
+ktap_test_xfail() {
+	description="$1"
+
+	result="ok"
+	directive="XFAIL"
+	__ktap_test "$result" "$description" "$directive"
+
+	KTAP_CNT_XFAIL=$((KTAP_CNT_XFAIL+1))
+}
+
 ktap_test_fail() {
 	description="$1"
 
@@ -99,13 +110,13 @@ ktap_exit_fail_msg() {
 ktap_finished() {
 	ktap_print_totals
 
-	if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP)) -eq "$KSFT_NUM_TESTS" ]; then
+	if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP + KTAP_CNT_XFAIL)) -eq "$KSFT_NUM_TESTS" ]; then
 		exit "$KSFT_PASS"
 	else
 		exit "$KSFT_FAIL"
 	fi
 }
 
 ktap_print_totals() {
-	echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0"
+	echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:$KTAP_CNT_XFAIL xpass:0 skip:$KTAP_CNT_SKIP error:0"
 }

tools/testing/selftests/net/packetdrill/ksft_runner.sh

@@ -23,24 +23,37 @@ if [ $# -ne 1 ]; then
 	ktap_exit_fail_msg "usage: $0 <script>"
 	exit "$KSFT_FAIL"
 fi
-script="$1"
+script="$(basename $1)"
 
 if [ -z "$(which packetdrill)" ]; then
 	ktap_skip_all "packetdrill not found in PATH"
 	exit "$KSFT_SKIP"
 fi
 
 declare -a optargs
+failfunc=ktap_test_fail
+
 if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then
 	optargs+=('--tolerance_usecs=14000')
+
+	# xfail tests that are known flaky with dbg config, not fixable.
+	# still run them for coverage (and expect 100% pass without dbg).
+	declare -ar xfail_list=(
+		"tcp_fast_recovery_prr-ss.*.pkt"
+		"tcp_timestamping.*.pkt"
+		"tcp_user_timeout_user-timeout-probe.pkt"
+		"tcp_zerocopy_epoll_.*.pkt"
+	)
+	readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$"
+	[[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail
 fi
 
 ktap_print_header
 ktap_set_plan 2
 
-unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $(basename $script) > /dev/null \
-	&& ktap_test_pass "ipv4" || ktap_test_fail "ipv4"
-unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $(basename $script) > /dev/null \
-	&& ktap_test_pass "ipv6" || ktap_test_fail "ipv6"
+unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $script > /dev/null \
+	&& ktap_test_pass "ipv4" || $failfunc "ipv4"
+unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $script > /dev/null \
+	&& ktap_test_pass "ipv6" || $failfunc "ipv6"
 
 ktap_finished