kunit: test: add test plan to KUnit TAP format

TAP 14 allows an optional test plan to be emitted before the start of
the start of testing[1]; this is valuable because it makes it possible
for a test harness to detect whether the number of tests run matches the
number of tests expected to be run, ensuring that no tests silently
failed.

Link[1]: https://github.com/isaacs/testanything.github.io/blob/tap14/tap-version-14-specification.md#the-plan
Signed-off-by: Brendan Higgins <brendanhiggins@google.com>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>

4 files changed, 65 insertions, 14 deletions

diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index f13e0c0d6663..8019e3dd4c32 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -45,10 +45,11 @@ class TestStatus(Enum):
 	FAILURE = auto()
 	TEST_CRASHED = auto()
 	NO_TESTS = auto()
+	FAILURE_TO_PARSE_TESTS = auto()
 
 kunit_start_re = re.compile(r'TAP version [0-9]+$')
 kunit_end_re = re.compile('(List of all partitions:|'
-			  'Kernel panic - not syncing: VFS:|reboot: System halted)')
+			  'Kernel panic - not syncing: VFS:)')
 
 def isolate_kunit_output(kernel_output):
 	started = False
@@ -109,7 +110,7 @@ OkNotOkResult = namedtuple('OkNotOkResult', ['is_ok','description', 'text'])
 
 OK_NOT_OK_SUBTEST = re.compile(r'^[\s]+(ok|not ok) [0-9]+ - (.*)$')
 
-OK_NOT_OK_MODULE = re.compile(r'^(ok|not ok) [0-9]+ - (.*)$')
+OK_NOT_OK_MODULE = re.compile(r'^(ok|not ok) ([0-9]+) - (.*)$')
 
 def parse_ok_not_ok_test_case(lines: List[str], test_case: TestCase) -> bool:
 	save_non_diagnositic(lines, test_case)
@@ -197,7 +198,9 @@ def max_status(left: TestStatus, right: TestStatus) -> TestStatus:
 	else:
 		return TestStatus.SUCCESS
 
-def parse_ok_not_ok_test_suite(lines: List[str], test_suite: TestSuite) -> bool:
+def parse_ok_not_ok_test_suite(lines: List[str],
+			       test_suite: TestSuite,
+			       expected_suite_index: int) -> bool:
 	consume_non_diagnositic(lines)
 	if not lines:
 		test_suite.status = TestStatus.TEST_CRASHED
@@ -210,6 +213,12 @@ def parse_ok_not_ok_test_suite(lines: List[str], test_suite: TestSuite) -> bool:
 			test_suite.status = TestStatus.SUCCESS
 		else:
 			test_suite.status = TestStatus.FAILURE
+		suite_index = int(match.group(2))
+		if suite_index != expected_suite_index:
+			print_with_timestamp(
+				red('[ERROR] ') + 'expected_suite_index ' +
+				str(expected_suite_index) + ', but got ' +
+				str(suite_index))
 		return True
 	else:
 		return False
@@ -222,7 +231,7 @@ def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus:
 	max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases)
 	return max_status(max_test_case_status, test_suite.status)
 
-def parse_test_suite(lines: List[str]) -> TestSuite:
+def parse_test_suite(lines: List[str], expected_suite_index: int) -> TestSuite:
 	if not lines:
 		return None
 	consume_non_diagnositic(lines)
@@ -241,7 +250,7 @@ def parse_test_suite(lines: List[str]) -> TestSuite:
 			break
 		test_suite.cases.append(test_case)
 		expected_test_case_num -= 1
-	if parse_ok_not_ok_test_suite(lines, test_suite):
+	if parse_ok_not_ok_test_suite(lines, test_suite, expected_suite_index):
 		test_suite.status = bubble_up_test_case_errors(test_suite)
 		return test_suite
 	elif not lines:
@@ -261,6 +270,17 @@ def parse_tap_header(lines: List[str]) -> bool:
 	else:
 		return False
 
+TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)')
+
+def parse_test_plan(lines: List[str]) -> int:
+	consume_non_diagnositic(lines)
+	match = TEST_PLAN.match(lines[0])
+	if match:
+		lines.pop(0)
+		return int(match.group(1))
+	else:
+		return None
+
 def bubble_up_suite_errors(test_suite_list: List[TestSuite]) -> TestStatus:
 	return bubble_up_errors(lambda x: x.status, test_suite_list)
 
@@ -268,20 +288,33 @@ def parse_test_result(lines: List[str]) -> TestResult:
 	consume_non_diagnositic(lines)
 	if not lines or not parse_tap_header(lines):
 		return TestResult(TestStatus.NO_TESTS, [], lines)
+	expected_test_suite_num = parse_test_plan(lines)
+	if not expected_test_suite_num:
+		return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines)
 	test_suites = []
-	test_suite = parse_test_suite(lines)
-	while test_suite:
-		test_suites.append(test_suite)
-		test_suite = parse_test_suite(lines)
-	return TestResult(bubble_up_suite_errors(test_suites), test_suites, lines)
+	for i in range(1, expected_test_suite_num + 1):
+		test_suite = parse_test_suite(lines, i)
+		if test_suite:
+			test_suites.append(test_suite)
+		else:
+			print_with_timestamp(
+				red('[ERROR] ') + ' expected ' +
+				str(expected_test_suite_num) +
+				' test suites, but got ' + str(i - 2))
+			break
+	test_suite = parse_test_suite(lines, -1)
+	if test_suite:
+		print_with_timestamp(red('[ERROR] ') +
+			'got unexpected test suite: ' + test_suite.name)
+	if test_suites:
+		return TestResult(bubble_up_suite_errors(test_suites), test_suites, lines)
+	else:
+		return TestResult(TestStatus.NO_TESTS, [], lines)
 
-def parse_run_tests(kernel_output) -> TestResult:
+def print_and_count_results(test_result: TestResult) -> None:
 	total_tests = 0
 	failed_tests = 0
 	crashed_tests = 0
-	test_result = parse_test_result(list(isolate_kunit_output(kernel_output)))
-	if test_result.status == TestStatus.NO_TESTS:
-		print_with_timestamp(red('[ERROR] ') + 'no kunit output detected')
 	for test_suite in test_result.suites:
 		if test_suite.status == TestStatus.SUCCESS:
 			print_suite_divider(green('[PASSED] ') + test_suite.name)
@@ -303,6 +336,21 @@ def parse_run_tests(kernel_output) -> TestResult:
 				print_with_timestamp(red('[FAILED] ') + test_case.name)
 				print_log(map(yellow, test_case.log))
 				print_with_timestamp('')
+	return total_tests, failed_tests, crashed_tests
+
+def parse_run_tests(kernel_output) -> TestResult:
+	total_tests = 0
+	failed_tests = 0
+	crashed_tests = 0
+	test_result = parse_test_result(list(isolate_kunit_output(kernel_output)))
+	if test_result.status == TestStatus.NO_TESTS:
+		print(red('[ERROR] ') + yellow('no tests run!'))
+	elif test_result.status == TestStatus.FAILURE_TO_PARSE_TESTS:
+		print(red('[ERROR] ') + yellow('could not parse test results!'))
+	else:
+		(total_tests,
+		 failed_tests,
+		 crashed_tests) = print_and_count_results(test_result)
 	print_with_timestamp(DIVIDER)
 	fmt = green if test_result.status == TestStatus.SUCCESS else red
 	print_with_timestamp(
diff --git a/tools/testing/kunit/test_data/test_is_test_passed-all_passed.log b/tools/testing/kunit/test_data/test_is_test_passed-all_passed.log
index 62ebc0288355..bc0dc8fe35b7 100644
--- a/tools/testing/kunit/test_data/test_is_test_passed-all_passed.log
+++ b/tools/testing/kunit/test_data/test_is_test_passed-all_passed.log
@@ -1,4 +1,5 @@
 TAP version 14
+1..2
 	# Subtest: sysctl_test
 	1..8
 	# sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed
diff --git a/tools/testing/kunit/test_data/test_is_test_passed-crash.log b/tools/testing/kunit/test_data/test_is_test_passed-crash.log
index 0b249870c8be..4d97f6708c4a 100644
--- a/tools/testing/kunit/test_data/test_is_test_passed-crash.log
+++ b/tools/testing/kunit/test_data/test_is_test_passed-crash.log
@@ -1,6 +1,7 @@
 printk: console [tty0] enabled
 printk: console [mc-1] enabled
 TAP version 14
+1..2
 	# Subtest: sysctl_test
 	1..8
 	# sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed
diff --git a/tools/testing/kunit/test_data/test_is_test_passed-failure.log b/tools/testing/kunit/test_data/test_is_test_passed-failure.log
index 9e89d32d5667..7a416497e3be 100644
--- a/tools/testing/kunit/test_data/test_is_test_passed-failure.log
+++ b/tools/testing/kunit/test_data/test_is_test_passed-failure.log
@@ -1,4 +1,5 @@
 TAP version 14
+1..2
 	# Subtest: sysctl_test
 	1..8
 	# sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed