[Tarantool-patches] [PATCH v2 luajit 1/6] test: introduce tests for debugging extensions

[Sergey Kaplun via Tarantool-patches <tarantool-patches@dev.tarantool.org>]

From: Maxim Kokryashkin <m.kokryashkin@tarantool.org>

This patch adds tests for LuaJIT debugging extensions for lldb and gdb.
The tests are written in Python's unittest framework [1].

Most of the tests are failed for the lldb due to outdated extension
sources and overcomplicated hard-coded C structures fields
introspection. Hence, tests for LLDB are disabled since they are failing
anyway.

The tarantool-debugger-tests target is introduced. This target is
included in the LuaJIT-check-all target but not in the LuaJIT-test
target to avoid it running for all LuaJIT builds by default in CI.

[1]: https://docs.python.org/3/library/unittest.html
---
 test/CMakeLists.txt                           |   7 +
 test/tarantool-debugger-tests/CMakeLists.txt  |  93 ++++++
 .../debug-extension-tests.py                  | 286 ++++++++++++++++++
 3 files changed, 386 insertions(+)
 create mode 100644 test/tarantool-debugger-tests/CMakeLists.txt
 create mode 100644 test/tarantool-debugger-tests/debug-extension-tests.py

diff --git a/test/CMakeLists.txt b/test/CMakeLists.txt
index f48afa25..26b15892 100644
--- a/test/CMakeLists.txt
+++ b/test/CMakeLists.txt
@@ -175,6 +175,7 @@ add_subdirectory(LuaJIT-tests)
 add_subdirectory(PUC-Rio-Lua-5.1-tests)
 add_subdirectory(lua-Harness-tests)
 add_subdirectory(tarantool-c-tests)
+add_subdirectory(tarantool-debugger-tests)
 add_subdirectory(tarantool-tests)
 
 # Each testsuite has its own CMake target, but combining these
@@ -186,6 +187,9 @@ add_subdirectory(tarantool-tests)
 # command that runs all generated CMake tests.
 add_custom_target(${PROJECT_NAME}-test
   COMMAND ${CMAKE_CTEST_COMMAND} ${CTEST_FLAGS}
+    # Omit this target in LuaJIT-test since we don't want to set
+    # up and run debuggers for every build.
+    --label-exclude tarantool-debugger-tests
   DEPENDS tarantool-c-tests-deps
           tarantool-tests-deps
           lua-Harness-tests-deps
@@ -195,5 +199,8 @@ add_custom_target(${PROJECT_NAME}-test
 
 add_custom_target(${PROJECT_NAME}-check-all
   DEPENDS ${PROJECT_NAME}-test
+          # Omit this target in LuaJIT-test since we don't want to
+          # set up and run debuggers for every build.
+          tarantool-debugger-tests
           ${PROJECT_NAME}-lint
 )
diff --git a/test/tarantool-debugger-tests/CMakeLists.txt b/test/tarantool-debugger-tests/CMakeLists.txt
new file mode 100644
index 00000000..7fd0debc
--- /dev/null
+++ b/test/tarantool-debugger-tests/CMakeLists.txt
@@ -0,0 +1,93 @@
+set(TEST_SUITE_NAME "tarantool-debugger-tests")
+
+# XXX: The call produces both test and target
+# <tarantool-debugger-tests-deps> as a side effect.
+add_test_suite_target(tarantool-debugger-tests
+  LABELS ${TEST_SUITE_NAME}
+  DEPENDS ${LUAJIT_TEST_BINARY}
+)
+
+# Debug info is required for testing of extensions.
+if(NOT (CMAKE_BUILD_TYPE MATCHES Debug))
+  message(WARNING
+    "Not a DEBUG build, tarantool-debugger-tests is dummy"
+  )
+  return()
+endif()
+
+# MacOS asks for permission to debug a process even when the
+# machine is set into development mode. To solve the issue,
+# it is required to add relevant users to the `_developer` user
+# group in macOS. Disabled for now.
+if(CMAKE_SYSTEM_NAME STREQUAL "Darwin" AND DEFINED ENV{CI})
+  message(WARNING
+    "Interactive debugging is unavailable for macOS CI builds,"
+    " tarantool-debugger-tests is dummy"
+  )
+  return()
+endif()
+
+if(CMAKE_VERSION VERSION_LESS "3.12")
+  # TODO:Can remove this after upgrading to CMake >= 3.12.
+  find_package(PythonInterp)
+  if(NOT PYTHONINTERP_FOUND)
+    message(WARNING "`python` is not found, tarantool-debugger-tests is dummy")
+    return()
+  endif()
+else()
+  find_package(Python COMPONENTS Interpreter)
+  if(NOT PYTHON_FOUND)
+    message(WARNING "`python` is not found, tarantool-debugger-tests is dummy")
+    return()
+  endif()
+  set(PYTHON_EXECUTABLE "${Python_EXECUTABLE}")
+endif()
+
+set(DEBUGGER_TEST_ENV
+  "LUAJIT_TEST_BINARY=${LUAJIT_TEST_BINARY}"
+  # Suppresses __pycache__ generation.
+  "PYTHONDONTWRITEBYTECODE=1"
+  "DEBUGGER_EXTENSION_PATH=${PROJECT_SOURCE_DIR}/src"
+)
+
+set(TEST_SCRIPT_PATH
+  ${CMAKE_CURRENT_SOURCE_DIR}/debug-extension-tests.py
+)
+
+find_program(GDB gdb)
+if(GDB)
+  set(test_title "test/${TEST_SUITE_NAME}/gdb")
+  set(GDB_TEST_ENV ${DEBUGGER_TEST_ENV} "DEBUGGER_COMMAND=${GDB}")
+  add_test(NAME "${test_title}"
+    COMMAND ${PYTHON_EXECUTABLE} ${TEST_SCRIPT_PATH}
+    WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}
+  )
+  set_tests_properties("${test_title}" PROPERTIES
+    ENVIRONMENT "${GDB_TEST_ENV}"
+    LABELS ${TEST_SUITE_NAME}
+    DEPENDS tarantool-debugger-tests-deps
+  )
+else()
+  message(WARNING
+    "`gdb' is not found, so tarantool-debugger-tests/gdb is omitted"
+  )
+endif()
+
+find_program(LLDB lldb)
+if(LLDB)
+  set(test_title "test/${TEST_SUITE_NAME}/lldb")
+  set(LLDB_TEST_ENV ${DEBUGGER_TEST_ENV} "DEBUGGER_COMMAND=${LLDB}")
+  add_test(NAME "${test_title}"
+    COMMAND ${PYTHON_EXECUTABLE} ${TEST_SCRIPT_PATH}
+    WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}
+  )
+  set_tests_properties("${test_title}" PROPERTIES
+    ENVIRONMENT "${LLDB_TEST_ENV}"
+    LABELS ${TEST_SUITE_NAME}
+    DEPENDS tarantool-debugger-tests-deps
+  )
+else()
+  message(WARNING
+    "`lldb' is not found, so tarantool-debugger-tests/lldb is omitted"
+  )
+endif()
diff --git a/test/tarantool-debugger-tests/debug-extension-tests.py b/test/tarantool-debugger-tests/debug-extension-tests.py
new file mode 100644
index 00000000..6094c535
--- /dev/null
+++ b/test/tarantool-debugger-tests/debug-extension-tests.py
@@ -0,0 +1,286 @@
+# This file provides tests for LuaJIT debug extensions for lldb
+# and gdb.
+
+import os
+import re
+import subprocess
+import sys
+import tempfile
+import unittest
+
+from threading import Timer
+
+LEGACY = re.match(r'^2\.', sys.version)
+
+LUAJIT_BINARY = os.environ['LUAJIT_TEST_BINARY']
+EXTENSION_PATH = os.environ['DEBUGGER_EXTENSION_PATH']
+DEBUGGER = os.environ['DEBUGGER_COMMAND']
+LLDB = 'lldb' in DEBUGGER
+EXTENSION = EXTENSION_PATH + ('/luajit_lldb.py' if LLDB else '/luajit-gdb.py')
+TIMEOUT = 10
+
+# Don't run any initialization scripts.
+RUN_CMD_FILE = []
+
+if LLDB:
+    RUN_CMD_FILE = [
+        '--batch',
+        '--no-lldbinit',
+        '--no-use-colors',
+        '--source-quietly',
+        '--source'
+    ]
+else:
+    # GDB.
+    RUN_CMD_FILE = ['--batch', '--nx', '--quiet', '--command']
+
+INFERIOR_ARGS = '--' if LLDB else '--args'
+PROCESS_RUN = 'process launch' if LLDB else 'r'
+LOAD_EXTENSION = (
+    'command script import {ext}' if LLDB else 'source {ext}'
+).format(ext=EXTENSION)
+
+
+RX_ADDR = r'0x[a-f0-9]+'
+RX_HASH = RX_ADDR  # The same pattern for hexademic values.
+RX_FRAME = r'\[(S|\s)(B|\s)(T|\s)(M|\s)\]'
+
+
+def persist(data):
+    tmp = tempfile.NamedTemporaryFile(mode='w')
+    tmp.write(data)
+    tmp.flush()
+    return tmp
+
+
+def execute_process(cmd, timeout=TIMEOUT):
+    if LEGACY:
+        # XXX: The Python 2.7 version of `subprocess.Popen`
+        # doesn't have a timeout option, so the required
+        # functionality was implemented via `threading.Timer`.
+        process = subprocess.Popen(
+            cmd,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            # This prevents sending of SIGSTTOU to the test when
+            # running by `make'. Stdin is unused anyway.
+            stdin=subprocess.DEVNULL
+        )
+        timer = Timer(TIMEOUT, process.kill)
+        timer.start()
+        stdout, _ = process.communicate()
+        timer.cancel()
+
+        # XXX: If the timeout is exceeded and the process is
+        # killed by the timer, then the return code is non-zero,
+        # and we are going to blow up.
+        assert process.returncode == 0
+        return stdout.decode('ascii')
+    else:
+        process = subprocess.run(
+            cmd,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            # This prevents sending of SIGSTTOU to the test when
+            # running by `make'. Stdin is unused anyway.
+            stdin=subprocess.DEVNULL,
+            universal_newlines=True,
+            timeout=TIMEOUT
+        )
+        return process.stdout
+
+
+class TestCaseBase(unittest.TestCase):
+    @classmethod
+    def construct_cmds(cls):
+        return '\n'.join([
+            'b {loc}'.format(loc=cls.location),
+            PROCESS_RUN,
+            'n',
+            LOAD_EXTENSION,
+            cls.extension_cmds.strip(),
+            'q',
+        ])
+
+    @classmethod
+    def setUpClass(cls):
+        cmd_file = persist(cls.construct_cmds())
+        script_file = persist(cls.lua_script)
+        process_cmd = [
+            DEBUGGER,
+            *RUN_CMD_FILE,
+            cmd_file.name,
+            INFERIOR_ARGS,
+            LUAJIT_BINARY,
+            script_file.name,
+        ]
+        cls.output = execute_process(process_cmd)
+        cmd_file.close()
+        script_file.close()
+
+    def check(self):
+        if LEGACY:
+            self.assertRegexpMatches(self.output, self.pattern.strip())
+        else:
+            self.assertRegex(self.output, self.pattern.strip())
+
+
+class TestLoad(TestCaseBase):
+    extension_cmds = ''
+    location = 'lj_cf_print'
+    lua_script = 'print(1)'
+    pattern = (
+        r'lj-arch command initialized\n'
+        r'lj-tv command initialized\n'
+        r'lj-str command initialized\n'
+        r'lj-tab command initialized\n'
+        r'lj-stack command initialized\n'
+        r'lj-state command initialized\n'
+        r'lj-gc command initialized\n'
+        r'.*is successfully loaded'
+    )
+
+
+class TestLJArch(TestCaseBase):
+    extension_cmds = 'lj-arch'
+    location = 'lj_cf_print'
+    lua_script = 'print(1)'
+    pattern = (
+        r'LJ_64: (True|False), '
+        r'LJ_GC64: (True|False), '
+        r'LJ_DUALNUM: (True|False)'
+    )
+
+
+class TestLJState(TestCaseBase):
+    extension_cmds = 'lj-state'
+    location = 'lj_cf_print'
+    lua_script = 'print(1)'
+    pattern = (
+        r'VM state: [A-Z]+\n'
+        r'GC state: [A-Z]+\n'
+        r'JIT state: [A-Z]+\n'
+    )
+
+
+class TestLJGC(TestCaseBase):
+    extension_cmds = 'lj-gc'
+    location = 'lj_cf_print'
+    lua_script = 'print(1)'
+    pattern = (
+        r'GC stats: [A-Z]+\n'
+        r'\ttotal: \d+\n'
+        r'\tthreshold: \d+\n'
+        r'\tdebt: \d+\n'
+        r'\testimate: \d+\n'
+        r'\tstepmul: \d+\n'
+        r'\tpause: \d+\n'
+        r'\tsweepstr: \d+/\d+\n'
+        r'\troot: \d+ objects\n'
+        r'\tgray: \d+ objects\n'
+        r'\tgrayagain: \d+ objects\n'
+        r'\tweak: \d+ objects\n'
+        r'\tmmudata: \d+ objects\n'
+    )
+
+
+class TestLJStack(TestCaseBase):
+    extension_cmds = 'lj-stack'
+    location = 'lj_cf_print'
+    lua_script = 'print(1)'
+    pattern = (
+        r'-+ Red zone:\s+\d+ slots -+\n'
+        r'(' + RX_ADDR + r'\s+' + RX_FRAME + r' VALUE: nil\n?)*\n'
+        r'-+ Stack:\s+\d+ slots -+\n'
+        r'(' + RX_ADDR + r'(:' + RX_ADDR + r')?\s+' + RX_FRAME + r'.*\n?)+\n'
+    )
+
+
+class TestLJTV(TestCaseBase):
+    location = 'lj_cf_print'
+    extension_cmds = (
+        'lj-tv L->base\n'
+        'lj-tv L->base + 1\n'
+        'lj-tv L->base + 2\n'
+        'lj-tv L->base + 3\n'
+        'lj-tv L->base + 4\n'
+        'lj-tv L->base + 5\n'
+        'lj-tv L->base + 6\n'
+        'lj-tv L->base + 7\n'
+        'lj-tv L->base + 8\n'
+        'lj-tv L->base + 9\n'
+        'lj-tv L->base + 10\n'
+        'lj-tv L->base + 11\n'
+    )
+
+    lua_script = (
+        'local ffi = require("ffi")\n'
+        'print(\n'
+        '  nil,\n'
+        '  false,\n'
+        '  true,\n'
+        '  "hello",\n'
+        '  {1},\n'
+        '  1,\n'
+        '  1.1,\n'
+        '  coroutine.create(function() end),\n'
+        '  ffi.new("int*"),\n'
+        '  function() end,\n'
+        '  print,\n'
+        '  require\n'
+        ')\n'
+    )
+
+    pattern = (
+        r'nil\n'
+        r'false\n'
+        r'true\n'
+        r'string \"hello\" @ ' + RX_ADDR + r'\n'
+        r'table @ ' + RX_ADDR + r' \(asize: \d+, hmask: ' + RX_HASH + r'\)\n'
+        r'(number|integer) .*1.*\n'
+        r'number 1.1\d+\n'
+        r'thread @ ' + RX_ADDR + r'\n'
+        r'cdata @ ' + RX_ADDR + r'\n'
+        r'Lua function @ ' + RX_ADDR + r', [0-9]+ upvalues, .+:[0-9]+\n'
+        r'fast function #[0-9]+\n'
+        r'C function @ ' + RX_ADDR + r'\n'
+    )
+
+
+class TestLJStr(TestCaseBase):
+    extension_cmds = (
+        # XXX: Get the value to the stack slot for the variable.
+        'n\n'
+        'lj-str fname\n'
+    )
+    location = 'lj_cf_dofile'
+    lua_script = 'pcall(dofile("name"))'
+    pattern = r'String: .* \[\d+ bytes\] with hash ' + RX_HASH
+
+
+class TestLJTab(TestCaseBase):
+    extension_cmds = (
+        # XXX: Get the value to the stack slot for the variable.
+        'n\n'
+        'lj-tab t\n'
+    )
+    location = 'lj_cf_unpack'
+    lua_script = 'unpack({1; a = 1})'
+    pattern = (
+        r'Array part: 3 slots\n' +
+        RX_ADDR + r': \[0\]: nil\n' +
+        RX_ADDR + r': \[1\]: .+ 1\n' +
+        RX_ADDR + r': \[2\]: nil\n' +
+        r'Hash part: 2 nodes\n' +
+        RX_ADDR + r': { string "a" @ ' + RX_ADDR + r' } => ' +
+        r'{ .+ 1 }; next = 0x0\n' +
+        RX_ADDR + r': { nil } => { nil }; next = 0x0\n'
+    )
+
+
+for test_cls in TestCaseBase.__subclasses__():
+    test_cls.test = lambda self: self.check()
+
+# FIXME: skip for LLDB since most commands are not working anyway.
+if __name__ == '__main__' and not LLDB:
+    unittest.main(verbosity=2)
-- 
2.53.0