//===-- ScriptInterpreterPython.cpp ---------------------------------------===// // // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. // See https://llvm.org/LICENSE.txt for license information. // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception // //===----------------------------------------------------------------------===// #include "lldb-python.h" #include "Interfaces/ScriptInterpreterPythonInterfaces.h" #include "PythonDataObjects.h" #include "PythonReadline.h" #include "SWIGPythonBridge.h" #include "ScriptInterpreterPythonImpl.h" #include "lldb/API/SBError.h" #include "lldb/API/SBExecutionContext.h" #include "lldb/API/SBFrame.h" #include "lldb/API/SBValue.h" #include "lldb/Breakpoint/StoppointCallbackContext.h" #include "lldb/Breakpoint/WatchpointOptions.h" #include "lldb/Core/Debugger.h" #include "lldb/Core/PluginManager.h" #include "lldb/Core/ThreadedCommunication.h" #include "lldb/DataFormatters/TypeSummary.h" #include "lldb/Host/Config.h" #include "lldb/Host/ConnectionFileDescriptor.h" #include "lldb/Host/FileSystem.h" #include "lldb/Host/HostInfo.h" #include "lldb/Host/Pipe.h" #include "lldb/Host/StreamFile.h" #include "lldb/Interpreter/CommandInterpreter.h" #include "lldb/Interpreter/CommandReturnObject.h" #include "lldb/Target/Thread.h" #include "lldb/Target/ThreadPlan.h" #include "lldb/Utility/Instrumentation.h" #include "lldb/Utility/LLDBLog.h" #include "lldb/Utility/StructuredData.h" #include "lldb/Utility/Timer.h" #include "lldb/ValueObject/ValueObject.h" #include "lldb/lldb-enumerations.h" #include "lldb/lldb-forward.h" #include "llvm/ADT/STLExtras.h" #include "llvm/ADT/StringExtras.h" #include "llvm/ADT/StringRef.h" #include "llvm/Support/Error.h" #include "llvm/Support/ErrorExtras.h" #include "llvm/Support/FileSystem.h" #include "llvm/Support/FormatAdapters.h" #if defined(_WIN32) #include "lldb/Host/windows/ConnectionGenericFileWindows.h" #endif #include #include #include #include #include #include using namespace lldb; using namespace lldb_private; using namespace lldb_private::python; using llvm::Expected; LLDB_PLUGIN_DEFINE(ScriptInterpreterPython) // Defined in the SWIG source file extern "C" PyObject *PyInit__lldb(void); #define LLDBSwigPyInit PyInit__lldb #if defined(_WIN32) // Don't mess with the signal handlers on Windows. #define LLDB_USE_PYTHON_SET_INTERRUPT 0 #else #define LLDB_USE_PYTHON_SET_INTERRUPT 1 #endif static ScriptInterpreterPythonImpl *GetPythonInterpreter(Debugger &debugger) { ScriptInterpreter *script_interpreter = debugger.GetScriptInterpreter(true, lldb::eScriptLanguagePython); return static_cast(script_interpreter); } namespace { // Initializing Python is not a straightforward process. We cannot control // what external code may have done before getting to this point in LLDB, // including potentially having already initialized Python, so we need to do a // lot of work to ensure that the existing state of the system is maintained // across our initialization. We do this by using an RAII pattern where we // save off initial state at the beginning, and restore it at the end struct InitializePythonRAII { public: InitializePythonRAII() { // The table of built-in modules can only be extended before Python is // initialized. if (!Py_IsInitialized()) { #ifdef LLDB_USE_LIBEDIT_READLINE_COMPAT_MODULE // Python's readline is incompatible with libedit being linked into lldb. // Provide a patched version local to the embedded interpreter. PyImport_AppendInittab("readline", initlldb_readline); #endif // Register _lldb as a built-in module. PyImport_AppendInittab("_lldb", LLDBSwigPyInit); } #if LLDB_EMBED_PYTHON_HOME PyConfig config; PyConfig_InitPythonConfig(&config); static std::string g_python_home = []() -> std::string { if (llvm::sys::path::is_absolute(LLDB_PYTHON_HOME)) return LLDB_PYTHON_HOME; FileSpec spec = HostInfo::GetShlibDir(); if (!spec) return {}; spec.AppendPathComponent(LLDB_PYTHON_HOME); return spec.GetPath(); }(); if (!g_python_home.empty()) { PyConfig_SetBytesString(&config, &config.home, g_python_home.c_str()); } config.install_signal_handlers = 0; Py_InitializeFromConfig(&config); PyConfig_Clear(&config); #else Py_InitializeEx(/*install_sigs=*/0); #endif // The only case we should go further and acquire the GIL: it is unlocked. PyGILState_STATE gil_state = PyGILState_Ensure(); if (gil_state != PyGILState_UNLOCKED) return; m_was_already_initialized = true; m_gil_state = gil_state; LLDB_LOG_VERBOSE( GetLog(LLDBLog::Script), "Ensured PyGILState. Previous state = {0}", m_gil_state == PyGILState_UNLOCKED ? "unlocked" : "locked"); } ~InitializePythonRAII() { if (m_was_already_initialized) { LLDB_LOG_VERBOSE(GetLog(LLDBLog::Script), "Releasing PyGILState. Returning to state = {0}", m_gil_state == PyGILState_UNLOCKED ? "unlocked" : "locked"); PyGILState_Release(m_gil_state); } else { // We initialized the threads in this function, just unlock the GIL. PyEval_SaveThread(); } } private: PyGILState_STATE m_gil_state = PyGILState_UNLOCKED; bool m_was_already_initialized = false; }; #if LLDB_USE_PYTHON_SET_INTERRUPT /// Saves the current signal handler for the specified signal and restores /// it at the end of the current scope. struct RestoreSignalHandlerScope { /// The signal handler. struct sigaction m_prev_handler; int m_signal_code; RestoreSignalHandlerScope(int signal_code) : m_signal_code(signal_code) { // Initialize sigaction to their default state. std::memset(&m_prev_handler, 0, sizeof(m_prev_handler)); // Don't install a new handler, just read back the old one. struct sigaction *new_handler = nullptr; int signal_err = ::sigaction(m_signal_code, new_handler, &m_prev_handler); lldbassert(signal_err == 0 && "sigaction failed to read handler"); } ~RestoreSignalHandlerScope() { int signal_err = ::sigaction(m_signal_code, &m_prev_handler, nullptr); lldbassert(signal_err == 0 && "sigaction failed to restore old handler"); } }; #endif } // namespace void ScriptInterpreterPython::ComputePythonDirForApple( llvm::SmallVectorImpl &path) { auto style = llvm::sys::path::Style::posix; llvm::StringRef path_ref(path.begin(), path.size()); auto rbegin = llvm::sys::path::rbegin(path_ref, style); auto rend = llvm::sys::path::rend(path_ref); auto framework = std::find(rbegin, rend, "LLDB.framework"); if (framework == rend) { ComputePythonDir(path); return; } path.resize(framework - rend); llvm::sys::path::append(path, style, "LLDB.framework", "Resources", "Python"); } void ScriptInterpreterPython::ComputePythonDir( llvm::SmallVectorImpl &path) { // Build the path by backing out of the lib dir, then building with whatever // the real python interpreter uses. (e.g. lib for most, lib64 on RHEL // x86_64, or bin on Windows). llvm::sys::path::remove_filename(path); llvm::sys::path::append(path, LLDB_PYTHON_RELATIVE_LIBDIR); #if defined(_WIN32) // This will be injected directly through FileSpec.SetDirectory(), // so we need to normalize manually. std::replace(path.begin(), path.end(), '\\', '/'); #endif } FileSpec ScriptInterpreterPython::GetPythonDir() { static FileSpec g_spec = []() { FileSpec spec = HostInfo::GetShlibDir(); if (!spec) return FileSpec(); llvm::SmallString<64> path; spec.GetPath(path); #if defined(__APPLE__) ComputePythonDirForApple(path); #else ComputePythonDir(path); #endif spec.SetDirectory(path); return spec; }(); return g_spec; } static const char GetInterpreterInfoScript[] = R"( import os import sys def main(lldb_python_dir, python_exe_relative_path): info = { "lldb-pythonpath": lldb_python_dir, "language": "python", "prefix": sys.prefix, "executable": os.path.join(sys.prefix, python_exe_relative_path) } return info )"; static const char python_exe_relative_path[] = LLDB_PYTHON_EXE_RELATIVE_PATH; StructuredData::DictionarySP ScriptInterpreterPython::GetInterpreterInfo() { GIL gil; FileSpec python_dir_spec = GetPythonDir(); if (!python_dir_spec) return nullptr; PythonScript get_info(GetInterpreterInfoScript); auto info_json = unwrapIgnoringErrors( As(get_info(PythonString(python_dir_spec.GetPath()), PythonString(python_exe_relative_path)))); if (!info_json) return nullptr; return info_json.CreateStructuredDictionary(); } llvm::Expected ScriptInterpreterPython::ExtensionToImportPath( lldb::ScriptedExtension extension) { switch (extension) { case eScriptedExtensionOperatingSystem: return "lldb.plugins.operating_system"; case eScriptedExtensionScriptedPlatform: return "lldb.plugins.scripted_platform"; case eScriptedExtensionScriptedProcess: return "lldb.plugins.scripted_process"; case eScriptedExtensionScriptedHook: return "lldb.plugins.scripted_hook"; case eScriptedExtensionScriptedBreakpointResolver: return "lldb.plugins.scripted_breakpoint"; case eScriptedExtensionScriptedThreadPlan: return "lldb.plugins.scripted_thread_plan"; case eScriptedExtensionScriptedFrameProvider: return "lldb.plugins.scripted_frame_provider"; case eScriptedExtensionScriptedThread: case eScriptedExtensionScriptedFrame: return "lldb.plugins.scripted_process"; case eScriptedExtensionScriptedStackFrameRecognizer: return "lldb.plugins.scripted_stackframe_recognizer"; case eScriptedExtensionScriptedCommand: case eScriptedExtensionParsedCommand: return "lldb.plugins.scripted_command"; case eScriptedExtensionScriptedStringSummary: return "lldb.plugins.scripted_string_summary"; case eScriptedExtensionScriptedSyntheticChildren: return "lldb.plugins.scripted_synthetic_children"; case eScriptedExtensionInvalid: return llvm::createStringError("invalid extension name"); } return llvm::createStringError("invalid extension name"); } llvm::Expected ScriptInterpreterPython::GetExtensionSchema( const llvm::SmallVector &extension_path) { lldb::ScriptedExtension extension = ScriptInterpreter::StringToExtension(extension_path.back()); auto import_path_or_err = ExtensionToImportPath(extension); if (!import_path_or_err) return import_path_or_err.takeError(); StreamString command_stream; // __import__(path, fromlist=['']) imports the submodule and returns it // directly (rather than the top-level package), as a single expression -- // this keeps the whole call eval-able in one line while guaranteeing the // module is imported first; referencing "." // directly would only work if something else had already imported // as a side effect. command_stream.Printf("lldb.embedded_interpreter.generate_extension_schema(" "__import__('%s', fromlist=['']).%s)", import_path_or_err->c_str(), ScriptInterpreter::ExtensionToString(extension).data()); // Use eScriptReturnTypeOpaqueObject: it transfers a real owned reference // we can safely extract the string from. eScriptReturnTypeCharStrOrNone // instead hands back a pointer to a temporary Python object's buffer // that gets destroyed (and, for a freshly created string like this one, // deallocated) as soon as ExecuteOneLineWithReturn returns -- reading // it afterwards is a use-after-free. void *result_obj = nullptr; if (!ExecuteOneLineWithReturn( command_stream.GetData(), ScriptInterpreter::eScriptReturnTypeOpaqueObject, &result_obj, ExecuteScriptOptions().SetEnableIO(false))) return llvm::createStringError("invalid extension schema format"); // ExecuteOneLineWithReturn releases the GIL before returning, so touching // the returned object (Str() below can execute arbitrary Python code) must // re-acquire it first. py_result is scoped so its destructor (a DECREF) // also runs before the GIL is released below, not after. std::string schema_str; { PyGILState_STATE gil_state = PyGILState_Ensure(); { PythonObject py_result(PyRefType::Owned, static_cast(result_obj)); if (py_result.IsAllocated() && py_result.get() != Py_None) schema_str = py_result.Str().GetString().str(); } PyGILState_Release(gil_state); } if (schema_str.empty()) return llvm::createStringError("empty extension schema"); return StructuredData::ParseJSON(schema_str); } llvm::Error ScriptInterpreterPython::ParseExtensionSchema( Stream &s, llvm::StringRef output_script_prefix, const llvm::SmallVector &extension_path, bool generate_non_abstract_methods, std::set &typing_imports) { auto schema_or_err = GetExtensionSchema(extension_path); if (!schema_or_err) return schema_or_err.takeError(); StructuredData::ObjectSP schema = *schema_or_err; if (!schema) return llvm::createStringError("empty extension schema"); StructuredData::Dictionary *dict = schema->GetAsDictionary(); if (!dict) return llvm::createStringError("extension schema is not a JSON object"); // Merge each class' typing imports into the caller-owned set so the // final `from typing import ...` line covers every class we emit. StructuredData::Array *schema_typing; if (dict->GetValueForKeyAsArray("typing_imports", schema_typing)) schema_typing->ForEach([&](StructuredData::Object *entry) { if (auto *str = entry->GetAsString()) typing_imports.insert(str->GetValue().str()); return true; }); llvm::StringRef base_class, import_path; if (!dict->GetValueForKeyAsString("class", base_class)) return llvm::createStringError( llvm::formatv("extension schema dictionary is missing 'class' key") .str()); if (!dict->GetValueForKeyAsString("module", import_path)) return llvm::createStringError( llvm::formatv("extension schema dictionary is missing 'module' key") .str()); // imports s.Printf("from %s import %s\n", import_path.data(), base_class.data()); s.EOL(); // class definition s.Printf("class %s%s(%s):\n", output_script_prefix.data(), base_class.data(), base_class.data()); s.IndentMore(); // Class docstring: list the non-callable members the base class exposes // so the user sees what's available without having to hop back to the // base class definition. bool has_body = false; StructuredData::Array *attributes; if (dict->GetValueForKeyAsArray("attributes", attributes) && attributes->GetSize()) { s.Indent(); s.PutCString("\"\"\"\n"); s.Indent(); s.Printf("Attributes inherited from %s:\n", base_class.data()); for (size_t i = 0; i < attributes->GetSize(); i++) { auto maybe_dict = attributes->GetItemAtIndexAsDictionary(i); if (!maybe_dict) continue; StructuredData::Dictionary *attr_dict = *maybe_dict; llvm::StringRef attr_name; if (!attr_dict->GetValueForKeyAsString("name", attr_name)) continue; llvm::StringRef attr_type; bool has_type = attr_dict->GetValueForKeyAsString("type", attr_type); s.Indent(); s.Printf("- %s", attr_name.data()); if (has_type) s.Printf(": %s", attr_type.data()); s.EOL(); } s.Indent(); s.PutCString("\"\"\"\n\n"); has_body = true; } // members StructuredData::Array *members; if (!dict->GetValueForKeyAsArray("members", members)) return llvm::createStringError("missing 'members' key in extension schema"); // If the base class doesn't mark anything `@abstractmethod`, the filter // "only stub abstract methods" would leave the derived class empty -- // which isn't a useful starting point. Fall back to emitting every // method in that case so the user has actual code to edit. bool any_abstract = false; for (size_t i = 0; i < members->GetSize(); i++) { auto maybe_dict = members->GetItemAtIndexAsDictionary(i); if (!maybe_dict) continue; bool is_abstract = false; if ((*maybe_dict)->GetValueForKeyAsBoolean("is_abstract", is_abstract) && is_abstract) { any_abstract = true; break; } } bool emit_all_methods = generate_non_abstract_methods || !any_abstract; for (size_t i = 0; i < members->GetSize(); i++) { auto maybe_dict = members->GetItemAtIndexAsDictionary(i); if (!maybe_dict) return llvm::createStringError( llvm::formatv( "member at index {0} in extension schema isn't a dictionary") .str()); StructuredData::Dictionary *member_dict = *maybe_dict; llvm::StringRef symbol, args; if (!member_dict->GetValueForKeyAsString("name", symbol)) return llvm::createStringError( llvm::formatv( "member at index {0} in extension schema is missing 'name' key") .str()); if (!member_dict->GetValueForKeyAsString("signature", args)) return llvm::createStringError( llvm::formatv("member at index {0} in extension schema is missing " "'signature' key") .str()); bool is_abstract = false; bool has_is_abstract = member_dict->GetValueForKeyAsBoolean("is_abstract", is_abstract); if (!emit_all_methods) if (!has_is_abstract || !is_abstract) continue; s.Indent(); s.Printf("def %s%s:\n", symbol.data(), args.data()); s.IndentMore(); llvm::StringRef documentation; if (member_dict->GetValueForKeyAsString("doc", documentation)) { s.Indent(); s.PutCString("\"\"\"\n"); llvm::SmallVector lines; documentation.split(lines, "\n"); for (llvm::StringRef line : lines) { s.Indent(); s.PutCString(line); s.EOL(); } s.Indent(); s.PutCString("\"\"\""); s.EOL(); } if (symbol == "__init__") { // The base class' constructor sets up attributes (e.g. self.target, // self.process) that the inherited, non-overridden methods rely on. // Forward the same arguments so that state is still initialized. // Splitting the param list on `,` requires bracket-depth awareness // because annotations like `Union[X, Y]` also contain commas. llvm::StringRef params = args.trim("()"); std::vector forwarded_args; int depth = 0; size_t start = 0; auto flush = [&](size_t end) { llvm::StringRef param = params.slice(start, end); param = param.split(':').first.split('=').first.trim(); if (!param.empty() && param != "self") forwarded_args.push_back(param.str()); }; for (size_t i = 0; i < params.size(); ++i) { char c = params[i]; if (c == '[' || c == '(' || c == '{') ++depth; else if (c == ']' || c == ')' || c == '}') --depth; else if (c == ',' && depth == 0) { flush(i); start = i + 1; } } flush(params.size()); s.Indent(); s.Printf("super().__init__(%s)\n", llvm::join(forwarded_args, ", ").c_str()); } s.Indent(); s.PutCString("# TODO: Implement\n"); s.Indent(); s.PutCString("pass\n\n"); s.IndentLess(); has_body = true; } // A class with no body is a Python syntax error, so emit `pass` when the // base class has nothing to stub out (no methods and no attributes to // document). if (!has_body) { s.Indent(); s.PutCString("pass\n"); } return llvm::Error::success(); } llvm::Expected ScriptInterpreterPython::GenerateExtensionTemplate( const std::string &name, std::vector &extensions, bool generate_non_abstract_methods, std::string output_file) { // `ParseExtensionSchema` accumulates every `typing` generic it sees // (`Optional`, `Union`, `List`, ...) into this set so we can emit a // targeted `from typing import ...` line only for what's actually // referenced. The Python schema does the detection so we don't have // to re-scan strings here. std::set typing_imports; StreamString bodies; for (const ExtensionTemplateRequest &extension : extensions) { if (llvm::Error err = ParseExtensionSchema(bodies, name, extension.path, generate_non_abstract_methods, typing_imports)) return std::move(err); bodies.PutCString("\n\n"); } StreamString generated_file_stream; generated_file_stream.PutCString("import lldb\n"); if (!typing_imports.empty()) { std::vector sorted_imports(typing_imports.begin(), typing_imports.end()); generated_file_stream.Format("from typing import {0}\n", llvm::join(sorted_imports, ", ")); } generated_file_stream.PutCString("\n"); generated_file_stream.PutCString(bodies.GetString()); FileSpec save_location; if (output_file.empty()) { // Sanitize the caller-supplied class prefix so it can't escape the // temp directory (`../`, path separators, ...). Only keep ASCII // alphanumerics; everything else collapses to `_`, and an all-junk // name falls back to a fixed default. std::string sanitized; sanitized.reserve(name.size()); for (char c : name) sanitized.push_back(llvm::isAlnum(c) ? static_cast(llvm::toLower(c)) : '_'); if (sanitized.find_first_not_of('_') == std::string::npos) sanitized = "extension"; const std::string file_name = "lldb_" + sanitized + "_extension.py"; save_location = HostInfo::GetGlobalTempDir(); FileSystem::Instance().Resolve(save_location); save_location.AppendPathComponent(file_name); } else { save_location = FileSpec(output_file); FileSystem::Instance().Resolve(save_location); } File::OpenOptions flags = File::eOpenOptionWriteOnly | File::eOpenOptionCanCreate | File::eOpenOptionTruncate; auto opened_file = FileSystem::Instance().Open(save_location, flags); if (!opened_file) return opened_file.takeError(); FileUP file = std::move(opened_file.get()); size_t byte_size = generated_file_stream.GetSize(); Status error = file->Write(generated_file_stream.GetData(), byte_size); if (error.Fail() || byte_size != generated_file_stream.GetSize()) return llvm::createStringError("Unable to write to destination file. Bytes " "written do not match generated file size."); return save_location; } void ScriptInterpreterPython::SharedLibraryDirectoryHelper( FileSpec &this_file) { // When we're loaded from python, this_file will point to the file inside the // python package directory. Replace it with the one in the lib directory. #ifdef _WIN32 // On windows, we need to manually back out of the python tree, and go into // the bin directory. This is pretty much the inverse of what ComputePythonDir // does. if (this_file.GetFileNameExtension() == ".pyd") { this_file.RemoveLastPathComponent(); // _lldb.pyd or _lldb_d.pyd this_file.RemoveLastPathComponent(); // native this_file.RemoveLastPathComponent(); // lldb llvm::StringRef libdir = LLDB_PYTHON_RELATIVE_LIBDIR; for (auto it = llvm::sys::path::begin(libdir), end = llvm::sys::path::end(libdir); it != end; ++it) this_file.RemoveLastPathComponent(); this_file.AppendPathComponent("bin"); this_file.AppendPathComponent("liblldb.dll"); } #else // The python file is a symlink, so we can find the real library by resolving // it. We can do this unconditionally. FileSystem::Instance().ResolveSymbolicLink(this_file, this_file); #endif } llvm::StringRef ScriptInterpreterPython::GetPluginDescriptionStatic() { return "Embedded Python interpreter"; } void ScriptInterpreterPython::Initialize() { #if LLDB_ENABLE_MTE // Python's allocator (pymalloc) is not aware of Memory Tagging Extension // (MTE) and crashes. // https://bugs.python.org/issue43593 setenv("PYTHONMALLOC", "malloc", /*overwrite=*/true); #endif // When the plugin is a separate shared library, the SWIG wrapper lives in // the plugin library, so the path helper that redirects lookups back to // liblldb is unnecessary. #if !LLDB_ENABLE_DYNAMIC_SCRIPTINTERPRETERS HostInfo::SetSharedLibraryDirectoryHelper( ScriptInterpreterPython::SharedLibraryDirectoryHelper); #endif PluginManager::RegisterPlugin( GetPluginNameStatic(), GetPluginDescriptionStatic(), lldb::eScriptLanguagePython, ScriptInterpreterPythonImpl::CreateInstance, ScriptInterpreterPythonImpl::GetPythonDir); ScriptInterpreterPythonImpl::Initialize(); ScriptInterpreterPythonInterfaces::Initialize(); } void ScriptInterpreterPython::Terminate() { ScriptInterpreterPythonInterfaces::Terminate(); PluginManager::UnregisterPlugin(ScriptInterpreterPythonImpl::CreateInstance); } ScriptInterpreterPythonImpl::Locker::Locker( ScriptInterpreterPythonImpl *py_interpreter, uint16_t on_entry, uint16_t on_leave, FileSP in, FileSP out, FileSP err) : ScriptInterpreterLocker(), m_teardown_session((on_leave & TearDownSession) == TearDownSession), m_python_interpreter(py_interpreter) { DoAcquireLock(); if ((on_entry & InitSession) == InitSession) { if (!DoInitSession(on_entry, in, out, err)) { // Don't teardown the session if we didn't init it. m_teardown_session = false; } } } bool ScriptInterpreterPythonImpl::Locker::DoAcquireLock() { m_GILState = PyGILState_Ensure(); LLDB_LOG_VERBOSE(GetLog(LLDBLog::Script), "Ensured PyGILState. Previous state = {0}", m_GILState == PyGILState_UNLOCKED ? "unlocked" : "locked"); // we need to save the thread state when we first start the command because // we might decide to interrupt it while some action is taking place outside // of Python (e.g. printing to screen, waiting for the network, ...) in that // case, _PyThreadState_Current will be NULL - and we would be unable to set // the asynchronous exception - not a desirable situation m_python_interpreter->SetThreadState(PyThreadState_Get()); m_python_interpreter->IncrementLockCount(); return true; } bool ScriptInterpreterPythonImpl::Locker::DoInitSession(uint16_t on_entry_flags, FileSP in, FileSP out, FileSP err) { if (!m_python_interpreter) return false; return m_python_interpreter->EnterSession(on_entry_flags, in, out, err); } bool ScriptInterpreterPythonImpl::Locker::DoFreeLock() { LLDB_LOG_VERBOSE(GetLog(LLDBLog::Script), "Releasing PyGILState. Returning to state = {0}", m_GILState == PyGILState_UNLOCKED ? "unlocked" : "locked"); PyGILState_Release(m_GILState); m_python_interpreter->DecrementLockCount(); return true; } bool ScriptInterpreterPythonImpl::Locker::DoTearDownSession() { if (!m_python_interpreter) return false; m_python_interpreter->LeaveSession(); return true; } ScriptInterpreterPythonImpl::Locker::~Locker() { if (m_teardown_session) DoTearDownSession(); DoFreeLock(); } ScriptInterpreterPythonImpl::ScriptInterpreterPythonImpl(Debugger &debugger) : ScriptInterpreterPython(debugger), m_saved_stdin(), m_saved_stdout(), m_saved_stderr(), m_main_module(), m_session_dict(PyInitialValue::Invalid), m_sys_module_dict(PyInitialValue::Invalid), m_run_one_line_function(), m_run_one_line_str_global(), m_dictionary_name(m_debugger.GetInstanceName()), m_active_io_handler(eIOHandlerNone), m_session_is_active(false), m_pty_secondary_is_open(false), m_valid_session(true), m_lock_count(0), m_command_thread_state(nullptr) { m_dictionary_name.append("_dict"); StreamString run_string; run_string.Printf("%s = dict()", m_dictionary_name.c_str()); Locker locker(this, Locker::AcquireLock, Locker::FreeAcquiredLock); RunSimpleString(run_string.GetData()); run_string.Clear(); run_string.Printf( "run_one_line (%s, 'import copy, keyword, os, re, sys, uuid, lldb')", m_dictionary_name.c_str()); RunSimpleString(run_string.GetData()); // Reloading modules requires a different syntax in Python 2 and Python 3. // This provides a consistent syntax no matter what version of Python. run_string.Clear(); run_string.Printf( "run_one_line (%s, 'from importlib import reload as reload_module')", m_dictionary_name.c_str()); RunSimpleString(run_string.GetData()); // WARNING: temporary code that loads Cocoa formatters - this should be done // on a per-platform basis rather than loading the whole set and letting the // individual formatter classes exploit APIs to check whether they can/cannot // do their task run_string.Clear(); run_string.Printf( "run_one_line (%s, 'import lldb.formatters, lldb.formatters.cpp')", m_dictionary_name.c_str()); RunSimpleString(run_string.GetData()); run_string.Clear(); run_string.Printf("run_one_line (%s, 'import lldb.embedded_interpreter; from " "lldb.embedded_interpreter import run_python_interpreter; " "from lldb.embedded_interpreter import run_one_line')", m_dictionary_name.c_str()); RunSimpleString(run_string.GetData()); run_string.Clear(); // Configure pydoc (built-in module) to use the "plain" pager. The default one // doesn't play nice with the statusline. run_string.Printf("run_one_line (%s, 'import pydoc; pydoc.pager = " "pydoc.plainpager')", m_dictionary_name.c_str()); RunSimpleString(run_string.GetData()); run_string.Clear(); run_string.Printf("run_one_line (%s, 'lldb.debugger_unique_id = %" PRIu64 "')", m_dictionary_name.c_str(), m_debugger.GetID()); RunSimpleString(run_string.GetData()); } /// A Python sys.stdout/stderr file backed by a pipe whose read end is drained /// by a reader thread that writes to the debugger's terminal under the output /// lock (Debugger::PrintAsync). Handing Python the raw terminal descriptor /// instead lets a script's print() race the statusline, which redraws on the /// event thread under that lock. Its cursor save/restore then rewinds over and /// eats the script's output. class ScriptInterpreterPythonImpl::SessionIORedirect { public: static std::unique_ptr Create(lldb::user_id_t debugger_id, bool is_stdout) { Pipe pipe; if (pipe.CreateNew().Fail()) return nullptr; std::unique_ptr redirect( new SessionIORedirect(debugger_id, is_stdout)); #if defined(_WIN32) lldb::file_t read_handle = pipe.GetReadNativeHandle(); pipe.ReleaseReadFileDescriptor(); std::unique_ptr conn = std::make_unique(read_handle, true); #else std::unique_ptr conn = std::make_unique( pipe.ReleaseReadFileDescriptor(), /*owns_fd=*/true); #endif if (!conn->IsConnected()) return nullptr; redirect->m_communication.SetConnection(std::move(conn)); redirect->m_communication.SetReadThreadBytesReceivedCallback( ReadThreadBytesReceived, redirect.get()); if (!redirect->m_communication.StartReadThread()) return nullptr; redirect->m_connected = true; // The write end is owned here. Python only borrows its descriptor. redirect->m_write_file_sp = std::make_shared( pipe.ReleaseWriteFileDescriptor(), File::eOpenOptionWriteOnly, NativeFile::Owned); return redirect; } ~SessionIORedirect() { if (!m_connected) return; // Close the write end so the reader sees EOF and exits, then join it. if (m_write_file_sp) m_write_file_sp->Close(); m_communication.JoinReadThread(); m_communication.Disconnect(); } int GetWriteDescriptor() const { return m_write_file_sp ? m_write_file_sp->GetDescriptor() : File::kInvalidDescriptor; } private: SessionIORedirect(lldb::user_id_t debugger_id, bool is_stdout) : m_debugger_id(debugger_id), m_is_stdout(is_stdout), m_communication("lldb.ScriptInterpreterPython.io-redirect") {} static void ReadThreadBytesReceived(void *baton, const void *src, size_t src_len) { if (!src || !src_len) return; auto *self = static_cast(baton); if (lldb::DebuggerSP debugger_sp = Debugger::FindDebuggerWithID(self->m_debugger_id)) debugger_sp->PrintAsync(static_cast(src), src_len, self->m_is_stdout); } lldb::user_id_t m_debugger_id; bool m_is_stdout; lldb::FileSP m_write_file_sp; ThreadedCommunication m_communication; bool m_connected = false; }; ScriptInterpreterPythonImpl::~ScriptInterpreterPythonImpl() { // the session dictionary may hold objects with complex state which means // that they may need to be torn down with some level of smarts and that, in // turn, requires a valid thread state force Python to procure itself such a // thread state, nuke the session dictionary and then release it for others // to use and proceed with the rest of the shutdown auto gil_state = PyGILState_Ensure(); m_session_dict.Reset(); PyGILState_Release(gil_state); } void ScriptInterpreterPythonImpl::IOHandlerActivated(IOHandler &io_handler, bool interactive) { const char *instructions = nullptr; switch (m_active_io_handler) { case eIOHandlerNone: break; case eIOHandlerBreakpoint: instructions = R"(Enter your Python command(s). Type 'DONE' to end. def function (frame, bp_loc, internal_dict): """frame: the lldb.SBFrame for the location at which you stopped bp_loc: an lldb.SBBreakpointLocation for the breakpoint location information internal_dict: an LLDB support object not to be used""" )"; break; case eIOHandlerWatchpoint: instructions = "Enter your Python command(s). Type 'DONE' to end.\n"; break; } if (instructions && interactive) { if (LockableStreamFileSP stream_sp = io_handler.GetOutputStreamFileSP()) { LockedStreamFile locked_stream = stream_sp->Lock(); locked_stream.PutCString(instructions); locked_stream.Flush(); } } } void ScriptInterpreterPythonImpl::IOHandlerInputComplete(IOHandler &io_handler, std::string &data) { io_handler.SetIsDone(true); bool batch_mode = m_debugger.GetCommandInterpreter().GetBatchCommandMode(); switch (m_active_io_handler) { case eIOHandlerNone: break; case eIOHandlerBreakpoint: { std::vector> *bp_options_vec = (std::vector> *) io_handler.GetUserData(); for (BreakpointOptions &bp_options : *bp_options_vec) { auto data_up = std::make_unique(); if (!data_up) break; data_up->user_source.SplitIntoLines(data); if (GenerateBreakpointCommandCallbackData(data_up->user_source, data_up->script_source, /*has_extra_args=*/false, /*is_callback=*/false) .Success()) { auto baton_sp = std::make_shared( std::move(data_up)); bp_options.SetCallback( ScriptInterpreterPythonImpl::BreakpointCallbackFunction, baton_sp); } else if (!batch_mode) { if (LockableStreamFileSP error_sp = io_handler.GetErrorStreamFileSP()) { LockedStreamFile locked_stream = error_sp->Lock(); locked_stream.Printf("Warning: No command attached to breakpoint.\n"); } } } m_active_io_handler = eIOHandlerNone; } break; case eIOHandlerWatchpoint: { WatchpointOptions *wp_options = (WatchpointOptions *)io_handler.GetUserData(); auto data_up = std::make_unique(); data_up->user_source.SplitIntoLines(data); if (GenerateWatchpointCommandCallbackData(data_up->user_source, data_up->script_source, /*is_callback=*/false)) { auto baton_sp = std::make_shared(std::move(data_up)); wp_options->SetCallback( ScriptInterpreterPythonImpl::WatchpointCallbackFunction, baton_sp); } else if (!batch_mode) { if (LockableStreamFileSP error_sp = io_handler.GetErrorStreamFileSP()) { LockedStreamFile locked_stream = error_sp->Lock(); locked_stream.Printf("Warning: No command attached to breakpoint.\n"); } } m_active_io_handler = eIOHandlerNone; } break; } } lldb::ScriptInterpreterSP ScriptInterpreterPythonImpl::CreateInstance(Debugger &debugger) { return std::make_shared(debugger); } void ScriptInterpreterPythonImpl::LeaveSession() { Log *log = GetLog(LLDBLog::Script); if (log) log->PutCString("ScriptInterpreterPythonImpl::LeaveSession()"); // Unset the LLDB global variables. RunSimpleString("lldb.debugger = None; lldb.target = None; lldb.process " "= None; lldb.thread = None; lldb.frame = None"); // checking that we have a valid thread state - since we use our own // threading and locking in some (rare) cases during cleanup Python may end // up believing we have no thread state and PyImport_AddModule will crash if // that is the case - since that seems to only happen when destroying the // SBDebugger, we can make do without clearing up stdout and stderr if (PyThreadState_GetDict()) { PythonDictionary &sys_module_dict = GetSysModuleDictionary(); if (sys_module_dict.IsValid()) { // Flush the pipe-backed wrappers while they are still sys.stdout/stderr. // Line buffering already flushes on each newline, but a trailing // unterminated line would otherwise be stranded (and later flushed into // a closed descriptor) once we close the pipe write end below. auto flush_redirect = [&](const char *py_name, std::unique_ptr &redirect) { if (!redirect) return; PythonObject file = sys_module_dict.GetItemForKey(PythonString(py_name)); if (!file.IsValid()) return; if (llvm::Expected result = file.CallMethod("flush")) (void)result; else llvm::consumeError(result.takeError()); }; flush_redirect("stdout", m_stdout_redirect); flush_redirect("stderr", m_stderr_redirect); if (m_saved_stdin.IsValid()) { sys_module_dict.SetItemForKey(PythonString("stdin"), m_saved_stdin); m_saved_stdin.Reset(); } if (m_saved_stdout.IsValid()) { sys_module_dict.SetItemForKey(PythonString("stdout"), m_saved_stdout); m_saved_stdout.Reset(); } if (m_saved_stderr.IsValid()) { sys_module_dict.SetItemForKey(PythonString("stderr"), m_saved_stderr); m_saved_stderr.Reset(); } } } // Tear down the pipe redirects (closes each write end and joins its reader). // The wrappers were flushed above, so nothing buffered is lost. m_stdout_redirect.reset(); m_stderr_redirect.reset(); m_session_is_active = false; } bool ScriptInterpreterPythonImpl::RedirectTerminalHandleThroughLock( const char *py_name, PythonObject &save_file, const char *mode, File &file) { const bool is_stdout = ::strcmp(py_name, "stdout") == 0; if (!is_stdout && ::strcmp(py_name, "stderr") != 0) return false; // The statusline is the only writer that races Python's terminal output. // When it isn't drawing there is nothing to serialize against, so keep the // normal wrapping and skip the reader thread and pipe. if (!m_debugger.StatuslineSupported()) return false; // Only the debugger's own terminal races the statusline. A redirect to a // pipe or user file (a different descriptor) is wrapped normally. lldb::FileSP debugger_file = is_stdout ? m_debugger.GetOutputFileSP() : m_debugger.GetErrorFileSP(); int fd = file.GetDescriptor(); if (!debugger_file || fd == File::kInvalidDescriptor || fd != debugger_file->GetDescriptor()) return false; std::unique_ptr &redirect = is_stdout ? m_stdout_redirect : m_stderr_redirect; redirect = SessionIORedirect::Create(m_debugger.GetID(), is_stdout); if (!redirect) return false; // Line-buffer the wrapper so each print() reaches the reader (and the // terminal) promptly: the pipe descriptor is not a tty, so the default // buffering would hold output back until the buffer filled. PyObject *pipe_file = PyFile_FromFd( redirect->GetWriteDescriptor(), nullptr, mode, /*buffering=*/1, /*encoding=*/nullptr, /*errors=*/"ignore", /*newline=*/nullptr, /*closefd=*/0); if (!pipe_file) { // Fall back to the raw descriptor. That reopens the statusline race, so // leave a breadcrumb rather than failing silently. LLDB_LOG(GetLog(LLDBLog::Script), "failed to wrap sys.{0} on a synchronized pipe; falling back to " "the unsynchronized terminal descriptor", py_name); PyErr_Clear(); redirect.reset(); return false; } PythonObject new_file(PyRefType::Owned, pipe_file); PythonDictionary &sys_module_dict = GetSysModuleDictionary(); save_file = sys_module_dict.GetItemForKey(PythonString(py_name)); sys_module_dict.SetItemForKey(PythonString(py_name), new_file); return true; } bool ScriptInterpreterPythonImpl::SetStdHandle(FileSP file_sp, const char *py_name, PythonObject &save_file, const char *mode, bool serialize_terminal_output) { if (!file_sp || !*file_sp) { save_file.Reset(); return false; } File &file = *file_sp; // When stdout/stderr point at the debugger's own terminal, route Python's // output through a pipe drained under the output lock so a script's print() // cannot race the statusline. Any other target keeps the normal wrapping. if (serialize_terminal_output && RedirectTerminalHandleThroughLock(py_name, save_file, mode, file)) return true; // Flush the file before giving it to python to avoid interleaved output. file.Flush(); PythonDictionary &sys_module_dict = GetSysModuleDictionary(); auto new_file = PythonFile::FromFile(file, mode); if (!new_file) { LLDB_LOG_ERROR(GetLog(LLDBLog::Script), new_file.takeError(), "ScriptInterpreterPythonImpl::SetStdHandle failed to wrap " "sys.{1}: {0}", py_name); return false; } save_file = sys_module_dict.GetItemForKey(PythonString(py_name)); sys_module_dict.SetItemForKey(PythonString(py_name), new_file.get()); return true; } bool ScriptInterpreterPythonImpl::EnterSession(uint16_t on_entry_flags, FileSP in_sp, FileSP out_sp, FileSP err_sp) { // If we have already entered the session, without having officially 'left' // it, then there is no need to 'enter' it again. Log *log = GetLog(LLDBLog::Script); if (m_session_is_active) { LLDB_LOGF( log, "ScriptInterpreterPythonImpl::EnterSession(on_entry_flags=0x%" PRIx16 ") session is already active, returning without doing anything", on_entry_flags); return false; } LLDB_LOGF( log, "ScriptInterpreterPythonImpl::EnterSession(on_entry_flags=0x%" PRIx16 ")", on_entry_flags); m_session_is_active = true; StreamString run_string; if (on_entry_flags & Locker::InitGlobals) { run_string.Printf("run_one_line (%s, 'lldb.debugger_unique_id = %" PRIu64, m_dictionary_name.c_str(), m_debugger.GetID()); run_string.Printf( "; lldb.debugger = lldb.SBDebugger.FindDebuggerWithID (%" PRIu64 ")", m_debugger.GetID()); run_string.PutCString("; lldb.target = lldb.debugger.GetSelectedTarget()"); run_string.PutCString("; lldb.process = lldb.target.GetProcess()"); run_string.PutCString("; lldb.thread = lldb.process.GetSelectedThread ()"); run_string.PutCString("; lldb.frame = lldb.thread.GetSelectedFrame ()"); run_string.PutCString("')"); } else { // If we aren't initing the globals, we should still always set the // debugger (since that is always unique.) run_string.Printf("run_one_line (%s, 'lldb.debugger_unique_id = %" PRIu64, m_dictionary_name.c_str(), m_debugger.GetID()); run_string.Printf( "; lldb.debugger = lldb.SBDebugger.FindDebuggerWithID (%" PRIu64 ")", m_debugger.GetID()); run_string.PutCString("')"); } RunSimpleString(run_string.GetData()); run_string.Clear(); PythonDictionary &sys_module_dict = GetSysModuleDictionary(); if (sys_module_dict.IsValid()) { lldb::FileSP top_in_sp; lldb::LockableStreamFileSP top_out_sp, top_err_sp; if (!in_sp || !out_sp || !err_sp || !*in_sp || !*out_sp || !*err_sp) m_debugger.AdoptTopIOHandlerFilesIfInvalid(top_in_sp, top_out_sp, top_err_sp); if (on_entry_flags & Locker::NoSTDIN) { m_saved_stdin.Reset(); } else { if (!SetStdHandle(in_sp, "stdin", m_saved_stdin, "r", /*serialize_terminal_output=*/false)) { if (top_in_sp) SetStdHandle(top_in_sp, "stdin", m_saved_stdin, "r", /*serialize_terminal_output=*/false); } } // Serialize terminal output for every session except those that opt out // with NoOutputRedirect (see the flag for why). const bool serialize_terminal_output = !(on_entry_flags & Locker::NoOutputRedirect); if (!SetStdHandle(out_sp, "stdout", m_saved_stdout, "w", serialize_terminal_output)) { if (top_out_sp) SetStdHandle(top_out_sp->GetUnlockedFileSP(), "stdout", m_saved_stdout, "w", serialize_terminal_output); } if (!SetStdHandle(err_sp, "stderr", m_saved_stderr, "w", serialize_terminal_output)) { if (top_err_sp) SetStdHandle(top_err_sp->GetUnlockedFileSP(), "stderr", m_saved_stderr, "w", serialize_terminal_output); } } if (PyErr_Occurred()) PyErr_Clear(); return true; } PythonModule &ScriptInterpreterPythonImpl::GetMainModule() { if (!m_main_module.IsValid()) m_main_module = unwrapIgnoringErrors(PythonModule::Import("__main__")); return m_main_module; } PythonDictionary &ScriptInterpreterPythonImpl::GetSessionDictionary() { if (m_session_dict.IsValid()) return m_session_dict; PythonObject &main_module = GetMainModule(); if (!main_module.IsValid()) return m_session_dict; PythonDictionary main_dict(PyRefType::Borrowed, PyModule_GetDict(main_module.get())); if (!main_dict.IsValid()) return m_session_dict; m_session_dict = unwrapIgnoringErrors( As(main_dict.GetItem(m_dictionary_name))); return m_session_dict; } PythonDictionary &ScriptInterpreterPythonImpl::GetSysModuleDictionary() { if (m_sys_module_dict.IsValid()) return m_sys_module_dict; PythonModule sys_module = unwrapIgnoringErrors(PythonModule::Import("sys")); m_sys_module_dict = sys_module.GetDictionary(); return m_sys_module_dict; } llvm::Expected ScriptInterpreterPythonImpl::GetMaxPositionalArgumentsForCallable( const llvm::StringRef &callable_name) { if (callable_name.empty()) { return llvm::createStringError(llvm::inconvertibleErrorCode(), "called with empty callable name."); } Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); auto dict = PythonModule::MainModule().ResolveName( m_dictionary_name); auto pfunc = PythonObject::ResolveNameWithDictionary( callable_name, dict); if (!pfunc.IsAllocated()) { return llvm::createStringError(llvm::inconvertibleErrorCode(), "can't find callable: %s", callable_name.str().c_str()); } llvm::Expected arg_info = pfunc.GetArgInfo(); if (!arg_info) { // `-f` may point at a builtin, unlike other GetArgInfo() callers. LLDB_LOG_ERROR(GetLog(LLDBLog::Script), arg_info.takeError(), "GetArgInfo failed for callable {1}, falling back to " "inspect.signature: {0}", callable_name); arg_info = PythonCallable::GetArgInfoFromInspectSignature(pfunc); } if (!arg_info) return arg_info.takeError(); return arg_info.get().max_positional_args; } static std::string GenerateUniqueName(const char *base_name_wanted, uint32_t &functions_counter, const void *name_token = nullptr) { StreamString sstr; if (!base_name_wanted) return std::string(); if (!name_token) sstr.Printf("%s_%d", base_name_wanted, functions_counter++); else sstr.Printf("%s_%p", base_name_wanted, name_token); return std::string(sstr.GetString()); } bool ScriptInterpreterPythonImpl::GetEmbeddedInterpreterModuleObjects() { if (m_run_one_line_function.IsValid()) return true; PythonObject module(PyRefType::Borrowed, PyImport_AddModule("lldb.embedded_interpreter")); if (!module.IsValid()) return false; PythonDictionary module_dict(PyRefType::Borrowed, PyModule_GetDict(module.get())); if (!module_dict.IsValid()) return false; m_run_one_line_function = module_dict.GetItemForKey(PythonString("run_one_line")); m_run_one_line_str_global = module_dict.GetItemForKey(PythonString("g_run_one_line_str")); return m_run_one_line_function.IsValid(); } bool ScriptInterpreterPythonImpl::ExecuteOneLine( llvm::StringRef command, CommandReturnObject *result, const ExecuteScriptOptions &options) { std::string command_str = command.str(); if (!m_valid_session) return false; if (!command.empty()) { // We want to call run_one_line, passing in the dictionary and the command // string. We cannot do this through RunSimpleString here because the // command string may contain escaped characters, and putting it inside // another string to pass to RunSimpleString messes up the escaping. So // we use the following more complicated method to pass the command string // directly down to Python. llvm::Expected> io_redirect_or_error = ScriptInterpreterIORedirect::Create( options.GetEnableIO(), m_debugger, result); if (!io_redirect_or_error) { if (result) result->AppendErrorWithFormatv( "failed to redirect I/O: {0}\n", llvm::fmt_consume(io_redirect_or_error.takeError())); else llvm::consumeError(io_redirect_or_error.takeError()); return false; } ScriptInterpreterIORedirect &io_redirect = **io_redirect_or_error; bool success = false; { // WARNING! It's imperative that this RAII scope be as tight as // possible. In particular, the scope must end *before* we try to join // the read thread. The reason for this is that a pre-requisite for // joining the read thread is that we close the write handle (to break // the pipe and cause it to wake up and exit). But acquiring the GIL as // below will redirect Python's stdio to use this same handle. If we // close the handle while Python is still using it, bad things will // happen. Locker locker( this, Locker::AcquireLock | Locker::InitSession | (options.GetSetLLDBGlobals() ? Locker::InitGlobals : 0) | ((result && result->GetInteractive()) ? 0 : Locker::NoSTDIN), Locker::FreeAcquiredLock | Locker::TearDownSession, io_redirect.GetInputFile(), io_redirect.GetOutputFile(), io_redirect.GetErrorFile()); // Find the correct script interpreter dictionary in the main module. PythonDictionary &session_dict = GetSessionDictionary(); if (session_dict.IsValid()) { if (GetEmbeddedInterpreterModuleObjects()) { if (PyCallable_Check(m_run_one_line_function.get())) { PythonObject pargs( PyRefType::Owned, Py_BuildValue("(Os)", session_dict.get(), command_str.c_str())); if (pargs.IsValid()) { PythonObject return_value( PyRefType::Owned, PyObject_CallObject(m_run_one_line_function.get(), pargs.get())); if (return_value.IsValid()) success = true; else if (options.GetMaskoutErrors() && PyErr_Occurred()) { PyErr_Print(); PyErr_Clear(); } } } } } io_redirect.Flush(); } if (success) return true; // The one-liner failed. Append the error message. if (result) { result->AppendErrorWithFormat("python failed attempting to evaluate '%s'", command_str.c_str()); } return false; } if (result) result->AppendError("empty command passed to python\n"); return false; } void ScriptInterpreterPythonImpl::ExecuteInterpreterLoop() { LLDB_SCOPED_TIMER(); Debugger &debugger = m_debugger; // At the moment, the only time the debugger does not have an input file // handle is when this is called directly from Python, in which case it is // both dangerous and unnecessary (not to mention confusing) to try to embed // a running interpreter loop inside the already running Python interpreter // loop, so we won't do it. if (!debugger.GetInputFile().IsValid()) return; IOHandlerSP io_handler_sp(new IOHandlerPythonInterpreter(debugger, this)); if (io_handler_sp) { debugger.RunIOHandlerAsync(io_handler_sp); } } bool ScriptInterpreterPythonImpl::Interrupt() { #if LLDB_USE_PYTHON_SET_INTERRUPT // If the interpreter isn't evaluating any Python at the moment then return // false to signal that this function didn't handle the interrupt and the // next component should try handling it. if (!IsExecutingPython()) return false; // Tell Python that it should pretend to have received a SIGINT. PyErr_SetInterrupt(); // PyErr_SetInterrupt has no way to return an error so we can only pretend the // signal got successfully handled and return true. // Python 3.10 introduces PyErr_SetInterruptEx that could return an error, but // the error handling is limited to checking the arguments which would be // just our (hardcoded) input signal code SIGINT, so that's not useful at all. return true; #else Log *log = GetLog(LLDBLog::Script); if (IsExecutingPython()) { PyThreadState *state = PyThreadState_Get(); if (!state) state = GetThreadState(); if (state) { long tid = PyThread_get_thread_ident(); PyThreadState_Swap(state); int num_threads = PyThreadState_SetAsyncExc(tid, PyExc_KeyboardInterrupt); LLDB_LOGF(log, "ScriptInterpreterPythonImpl::Interrupt() sending " "PyExc_KeyboardInterrupt (tid = %li, num_threads = %i)...", tid, num_threads); return true; } } LLDB_LOGF(log, "ScriptInterpreterPythonImpl::Interrupt() python code not running, " "can't interrupt"); return false; #endif } bool ScriptInterpreterPythonImpl::ExecuteOneLineWithReturn( llvm::StringRef in_string, ScriptInterpreter::ScriptReturnType return_type, void *ret_value, const ExecuteScriptOptions &options) { llvm::Expected> io_redirect_or_error = ScriptInterpreterIORedirect::Create( options.GetEnableIO(), m_debugger, /*result=*/nullptr); if (!io_redirect_or_error) { llvm::consumeError(io_redirect_or_error.takeError()); return false; } ScriptInterpreterIORedirect &io_redirect = **io_redirect_or_error; Locker locker(this, Locker::AcquireLock | Locker::InitSession | (options.GetSetLLDBGlobals() ? Locker::InitGlobals : 0) | Locker::NoSTDIN, Locker::FreeAcquiredLock | Locker::TearDownSession, io_redirect.GetInputFile(), io_redirect.GetOutputFile(), io_redirect.GetErrorFile()); PythonModule &main_module = GetMainModule(); PythonDictionary globals = main_module.GetDictionary(); PythonDictionary locals = GetSessionDictionary(); if (!locals.IsValid()) locals = unwrapIgnoringErrors( As(globals.GetAttribute(m_dictionary_name))); if (!locals.IsValid()) locals = globals; Expected maybe_py_return = runStringOneLine(in_string, globals, locals); if (!maybe_py_return) { llvm::handleAllErrors( maybe_py_return.takeError(), [&](PythonException &E) { E.Restore(); if (options.GetMaskoutErrors()) { if (E.Matches(PyExc_SyntaxError)) { PyErr_Print(); } PyErr_Clear(); } }, [](const llvm::ErrorInfoBase &E) {}); return false; } PythonObject py_return = std::move(maybe_py_return.get()); assert(py_return.IsValid()); switch (return_type) { case eScriptReturnTypeCharPtr: // "char *" { const char format[3] = "s#"; return PyArg_Parse(py_return.get(), format, (char **)ret_value); } case eScriptReturnTypeCharStrOrNone: // char* or NULL if py_return == // Py_None { const char format[3] = "z"; return PyArg_Parse(py_return.get(), format, (char **)ret_value); } case eScriptReturnTypeBool: { const char format[2] = "b"; return PyArg_Parse(py_return.get(), format, (bool *)ret_value); } case eScriptReturnTypeShortInt: { const char format[2] = "h"; return PyArg_Parse(py_return.get(), format, (short *)ret_value); } case eScriptReturnTypeShortIntUnsigned: { const char format[2] = "H"; return PyArg_Parse(py_return.get(), format, (unsigned short *)ret_value); } case eScriptReturnTypeInt: { const char format[2] = "i"; return PyArg_Parse(py_return.get(), format, (int *)ret_value); } case eScriptReturnTypeIntUnsigned: { const char format[2] = "I"; return PyArg_Parse(py_return.get(), format, (unsigned int *)ret_value); } case eScriptReturnTypeLongInt: { const char format[2] = "l"; return PyArg_Parse(py_return.get(), format, (long *)ret_value); } case eScriptReturnTypeLongIntUnsigned: { const char format[2] = "k"; return PyArg_Parse(py_return.get(), format, (unsigned long *)ret_value); } case eScriptReturnTypeLongLong: { const char format[2] = "L"; return PyArg_Parse(py_return.get(), format, (long long *)ret_value); } case eScriptReturnTypeLongLongUnsigned: { const char format[2] = "K"; return PyArg_Parse(py_return.get(), format, (unsigned long long *)ret_value); } case eScriptReturnTypeFloat: { const char format[2] = "f"; return PyArg_Parse(py_return.get(), format, (float *)ret_value); } case eScriptReturnTypeDouble: { const char format[2] = "d"; return PyArg_Parse(py_return.get(), format, (double *)ret_value); } case eScriptReturnTypeChar: { const char format[2] = "c"; return PyArg_Parse(py_return.get(), format, (char *)ret_value); } case eScriptReturnTypeOpaqueObject: { *((PyObject **)ret_value) = py_return.release(); return true; } } llvm_unreachable("Fully covered switch!"); } Status ScriptInterpreterPythonImpl::ExecuteMultipleLines( const char *in_string, const ExecuteScriptOptions &options) { if (in_string == nullptr) return Status(); llvm::Expected> io_redirect_or_error = ScriptInterpreterIORedirect::Create( options.GetEnableIO(), m_debugger, /*result=*/nullptr); if (!io_redirect_or_error) return Status::FromError(io_redirect_or_error.takeError()); ScriptInterpreterIORedirect &io_redirect = **io_redirect_or_error; Locker locker(this, Locker::AcquireLock | Locker::InitSession | (options.GetSetLLDBGlobals() ? Locker::InitGlobals : 0) | Locker::NoSTDIN, Locker::FreeAcquiredLock | Locker::TearDownSession, io_redirect.GetInputFile(), io_redirect.GetOutputFile(), io_redirect.GetErrorFile()); PythonModule &main_module = GetMainModule(); PythonDictionary globals = main_module.GetDictionary(); PythonDictionary locals = GetSessionDictionary(); if (!locals.IsValid()) locals = unwrapIgnoringErrors( As(globals.GetAttribute(m_dictionary_name))); if (!locals.IsValid()) locals = globals; Expected return_value = runStringMultiLine(in_string, globals, locals); if (!return_value) { llvm::Error error = llvm::handleErrors(return_value.takeError(), [&](PythonException &E) { llvm::Error error = llvm::createStringError( llvm::inconvertibleErrorCode(), E.ReadBacktrace()); if (!options.GetMaskoutErrors()) E.Restore(); return error; }); return Status::FromError(std::move(error)); } return Status(); } void ScriptInterpreterPythonImpl::CollectDataForBreakpointCommandCallback( std::vector> &bp_options_vec, CommandReturnObject &result) { m_active_io_handler = eIOHandlerBreakpoint; m_debugger.GetCommandInterpreter().GetPythonCommandsFromIOHandler( " ", *this, &bp_options_vec); } void ScriptInterpreterPythonImpl::CollectDataForWatchpointCommandCallback( WatchpointOptions *wp_options, CommandReturnObject &result) { m_active_io_handler = eIOHandlerWatchpoint; m_debugger.GetCommandInterpreter().GetPythonCommandsFromIOHandler( " ", *this, wp_options); } Status ScriptInterpreterPythonImpl::SetBreakpointCommandCallbackFunction( BreakpointOptions &bp_options, const char *function_name, StructuredData::ObjectSP extra_args_sp) { Status error; // For now just cons up a oneliner that calls the provided function. std::string function_signature = function_name; llvm::Expected maybe_args = GetMaxPositionalArgumentsForCallable(function_name); if (!maybe_args) { error = Status::FromErrorStringWithFormat( "could not get num args: %s", llvm::toString(maybe_args.takeError()).c_str()); return error; } size_t max_args = *maybe_args; bool uses_extra_args = false; if (max_args >= 4) { uses_extra_args = true; function_signature += "(frame, bp_loc, extra_args, internal_dict)"; } else if (max_args >= 3) { if (extra_args_sp) { error = Status::FromErrorStringWithFormat( "cannot pass extra_args to a three argument callback"); return error; } uses_extra_args = false; function_signature += "(frame, bp_loc, internal_dict)"; } else { error = Status::FromErrorStringWithFormat("expected 3 or 4 argument " "function, %s can only take %zu", function_name, max_args); return error; } SetBreakpointCommandCallback(bp_options, function_signature.c_str(), extra_args_sp, uses_extra_args, /*is_callback=*/true); return error; } Status ScriptInterpreterPythonImpl::SetBreakpointCommandCallback( BreakpointOptions &bp_options, std::unique_ptr &cmd_data_up) { Status error; error = GenerateBreakpointCommandCallbackData(cmd_data_up->user_source, cmd_data_up->script_source, /*has_extra_args=*/false, /*is_callback=*/false); if (error.Fail()) { return error; } auto baton_sp = std::make_shared(std::move(cmd_data_up)); bp_options.SetCallback( ScriptInterpreterPythonImpl::BreakpointCallbackFunction, baton_sp); return error; } Status ScriptInterpreterPythonImpl::SetBreakpointCommandCallback( BreakpointOptions &bp_options, const char *command_body_text, bool is_callback) { return SetBreakpointCommandCallback(bp_options, command_body_text, {}, /*uses_extra_args=*/false, is_callback); } // Set a Python one-liner as the callback for the breakpoint. Status ScriptInterpreterPythonImpl::SetBreakpointCommandCallback( BreakpointOptions &bp_options, const char *command_body_text, StructuredData::ObjectSP extra_args_sp, bool uses_extra_args, bool is_callback) { auto data_up = std::make_unique(extra_args_sp); // Split the command_body_text into lines, and pass that to // GenerateBreakpointCommandCallbackData. That will wrap the body in an // auto-generated function, and return the function name in script_source. // That is what the callback will actually invoke. data_up->user_source.SplitIntoLines(command_body_text); Status error = GenerateBreakpointCommandCallbackData( data_up->user_source, data_up->script_source, uses_extra_args, is_callback); if (error.Success()) { auto baton_sp = std::make_shared(std::move(data_up)); bp_options.SetCallback( ScriptInterpreterPythonImpl::BreakpointCallbackFunction, baton_sp); return error; } return error; } // Set a Python one-liner as the callback for the watchpoint. void ScriptInterpreterPythonImpl::SetWatchpointCommandCallback( WatchpointOptions *wp_options, const char *user_input, bool is_callback) { auto data_up = std::make_unique(); // It's necessary to set both user_source and script_source to the oneliner. // The former is used to generate callback description (as in watchpoint // command list) while the latter is used for Python to interpret during the // actual callback. data_up->user_source.AppendString(user_input); data_up->script_source.assign(user_input); if (GenerateWatchpointCommandCallbackData( data_up->user_source, data_up->script_source, is_callback)) { auto baton_sp = std::make_shared(std::move(data_up)); wp_options->SetCallback( ScriptInterpreterPythonImpl::WatchpointCallbackFunction, baton_sp); } } Status ScriptInterpreterPythonImpl::ExportFunctionDefinitionToInterpreter( StringList &function_def) { // Convert StringList to one long, newline delimited, const char *. std::string function_def_string(function_def.CopyList()); LLDB_LOG(GetLog(LLDBLog::Script), "Added Function:\n{0}\n", function_def_string.c_str()); Status error = ExecuteMultipleLines( function_def_string.c_str(), ExecuteScriptOptions().SetEnableIO(false)); return error; } Status ScriptInterpreterPythonImpl::GenerateFunction(const char *signature, const StringList &input, bool is_callback) { Status error; int num_lines = input.GetSize(); if (num_lines == 0) { error = Status::FromErrorString("No input data."); return error; } if (!signature || *signature == 0) { error = Status::FromErrorString("No output function name."); return error; } StreamString sstr; StringList auto_generated_function; auto_generated_function.AppendString(signature); auto_generated_function.AppendString( " global_dict = globals()"); // Grab the global dictionary auto_generated_function.AppendString( " new_keys = internal_dict.keys()"); // Make a list of keys in the // session dict auto_generated_function.AppendString( " old_keys = global_dict.keys()"); // Save list of keys in global dict auto_generated_function.AppendString( " global_dict.update(internal_dict)"); // Add the session dictionary // to the global dictionary. if (is_callback) { // If the user input is a callback to a python function, make sure the input // is only 1 line, otherwise appending the user input would break the // generated wrapped function if (num_lines == 1) { sstr.Clear(); sstr.Printf(" __return_val = %s", input.GetStringAtIndex(0)); auto_generated_function.AppendString(sstr.GetData()); } else { return Status::FromErrorString( "ScriptInterpreterPythonImpl::GenerateFunction(is_callback=" "true) = ERROR: python function is multiline."); } } else { auto_generated_function.AppendString( " __return_val = None"); // Initialize user callback return value. auto_generated_function.AppendString( " def __user_code():"); // Create a nested function that will wrap // the user input. This is necessary to // capture the return value of the user input // and prevent early returns. for (int i = 0; i < num_lines; ++i) { sstr.Clear(); sstr.Printf(" %s", input.GetStringAtIndex(i)); auto_generated_function.AppendString(sstr.GetData()); } auto_generated_function.AppendString( " __return_val = __user_code()"); // Call user code and capture // return value } auto_generated_function.AppendString( " for key in new_keys:"); // Iterate over all the keys from session // dict auto_generated_function.AppendString( " if key in old_keys:"); // If key was originally in // global dict auto_generated_function.AppendString( " internal_dict[key] = global_dict[key]"); // Update it auto_generated_function.AppendString( " elif key in global_dict:"); // Then if it is still in the // global dict auto_generated_function.AppendString( " del global_dict[key]"); // remove key/value from the // global dict auto_generated_function.AppendString( " return __return_val"); // Return the user callback return value. // Verify that the results are valid Python. error = ExportFunctionDefinitionToInterpreter(auto_generated_function); return error; } bool ScriptInterpreterPythonImpl::GenerateTypeScriptFunction( StringList &user_input, std::string &output, const void *name_token) { static uint32_t num_created_functions = 0; user_input.RemoveBlankLines(); StreamString sstr; // Check to see if we have any data; if not, just return. if (user_input.GetSize() == 0) return false; // Take what the user wrote, wrap it all up inside one big auto-generated // Python function, passing in the ValueObject as parameter to the function. std::string auto_generated_function_name( GenerateUniqueName("lldb_autogen_python_type_print_func", num_created_functions, name_token)); sstr.Printf("def %s (valobj, internal_dict):", auto_generated_function_name.c_str()); if (!GenerateFunction(sstr.GetData(), user_input, /*is_callback=*/false) .Success()) return false; // Store the name of the auto-generated function to be called. output.assign(auto_generated_function_name); return true; } bool ScriptInterpreterPythonImpl::GenerateScriptAliasFunction( StringList &user_input, std::string &output) { static uint32_t num_created_functions = 0; user_input.RemoveBlankLines(); StreamString sstr; // Check to see if we have any data; if not, just return. if (user_input.GetSize() == 0) return false; std::string auto_generated_function_name(GenerateUniqueName( "lldb_autogen_python_cmd_alias_func", num_created_functions)); sstr.Printf("def %s (debugger, args, exe_ctx, result, internal_dict):", auto_generated_function_name.c_str()); if (!GenerateFunction(sstr.GetData(), user_input, /*is_callback=*/false) .Success()) return false; // Store the name of the auto-generated function to be called. output.assign(auto_generated_function_name); return true; } bool ScriptInterpreterPythonImpl::GenerateTypeSynthClass( StringList &user_input, std::string &output, const void *name_token) { static uint32_t num_created_classes = 0; user_input.RemoveBlankLines(); int num_lines = user_input.GetSize(); StreamString sstr; // Check to see if we have any data; if not, just return. if (user_input.GetSize() == 0) return false; // Wrap all user input into a Python class std::string auto_generated_class_name(GenerateUniqueName( "lldb_autogen_python_type_synth_class", num_created_classes, name_token)); StringList auto_generated_class; // Create the function name & definition string. sstr.Printf("class %s:", auto_generated_class_name.c_str()); auto_generated_class.AppendString(sstr.GetString()); // Wrap everything up inside the class, increasing the indentation. we don't // need to play any fancy indentation tricks here because there is no // surrounding code whose indentation we need to honor for (int i = 0; i < num_lines; ++i) { sstr.Clear(); sstr.Printf(" %s", user_input.GetStringAtIndex(i)); auto_generated_class.AppendString(sstr.GetString()); } // Verify that the results are valid Python. (even though the method is // ExportFunctionDefinitionToInterpreter, a class will actually be exported) // (TODO: rename that method to ExportDefinitionToInterpreter) if (!ExportFunctionDefinitionToInterpreter(auto_generated_class).Success()) return false; // Store the name of the auto-generated class output.assign(auto_generated_class_name); return true; } ScriptedProcessInterfaceUP ScriptInterpreterPythonImpl::CreateScriptedProcessInterface() { return std::make_unique(*this); } ScriptedHookInterfaceSP ScriptInterpreterPythonImpl::CreateScriptedHookInterface() { return std::make_shared(*this); } ScriptedBreakpointInterfaceSP ScriptInterpreterPythonImpl::CreateScriptedBreakpointInterface() { return std::make_shared(*this); } ScriptedStackFrameRecognizerInterfaceSP ScriptInterpreterPythonImpl::CreateScriptedStackFrameRecognizerInterface() { return std::make_shared(*this); } ScriptedCommandInterfaceSP ScriptInterpreterPythonImpl::CreateScriptedCommandInterface() { return std::make_shared(*this); } ScriptedStringSummaryInterfaceSP ScriptInterpreterPythonImpl::CreateScriptedStringSummaryInterface() { return std::make_shared(*this); } ScriptedSyntheticChildrenInterfaceSP ScriptInterpreterPythonImpl::CreateScriptedSyntheticChildrenInterface() { return std::make_shared(*this); } ScriptedThreadInterfaceSP ScriptInterpreterPythonImpl::CreateScriptedThreadInterface() { return std::make_shared(*this); } ScriptedFrameInterfaceSP ScriptInterpreterPythonImpl::CreateScriptedFrameInterface() { return std::make_shared(*this); } ScriptedFrameProviderInterfaceSP ScriptInterpreterPythonImpl::CreateScriptedFrameProviderInterface() { return std::make_shared(*this); } ScriptedThreadPlanInterfaceSP ScriptInterpreterPythonImpl::CreateScriptedThreadPlanInterface() { return std::make_shared(*this); } OperatingSystemInterfaceSP ScriptInterpreterPythonImpl::CreateOperatingSystemInterface() { return std::make_shared(*this); } StructuredData::ObjectSP ScriptInterpreterPythonImpl::CreateStructuredDataFromScriptObject( ScriptObject obj) { void *ptr = const_cast(obj.GetPointer()); Locker py_lock(this, Locker::AcquireLock | Locker::NoSTDIN, Locker::FreeLock); PythonObject py_obj(PyRefType::Borrowed, static_cast(ptr)); if (!py_obj.IsValid() || py_obj.IsNone()) return {}; return py_obj.CreateStructuredObject(); } StructuredData::ObjectSP ScriptInterpreterPythonImpl::LoadPluginModule(const FileSpec &file_spec, lldb_private::Status &error) { if (!FileSystem::Instance().Exists(file_spec)) { error = Status::FromErrorString("no such file"); return StructuredData::ObjectSP(); } StructuredData::ObjectSP module_sp; LoadScriptOptions load_script_options = LoadScriptOptions().SetInitSession(true).SetSilent(false); if (LoadScriptingModule(file_spec.GetPath().c_str(), load_script_options, error, &module_sp)) return module_sp; return StructuredData::ObjectSP(); } StructuredData::DictionarySP ScriptInterpreterPythonImpl::GetDynamicSettings( StructuredData::ObjectSP plugin_module_sp, Target *target, const char *setting_name, lldb_private::Status &error) { if (!plugin_module_sp || !target || !setting_name || !setting_name[0]) return StructuredData::DictionarySP(); StructuredData::Generic *generic = plugin_module_sp->GetAsGeneric(); if (!generic) return StructuredData::DictionarySP(); Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); TargetSP target_sp(target->shared_from_this()); auto setting = (PyObject *)SWIGBridge::LLDBSWIGPython_GetDynamicSetting( generic->GetValue(), setting_name, target_sp); if (!setting) return StructuredData::DictionarySP(); PythonDictionary py_dict = unwrapIgnoringErrors(As(Take(setting))); if (!py_dict) return StructuredData::DictionarySP(); return py_dict.CreateStructuredDictionary(); } bool ScriptInterpreterPythonImpl::GenerateTypeScriptFunction( const char *oneliner, std::string &output, const void *name_token) { StringList input; input.SplitIntoLines(oneliner, strlen(oneliner)); return GenerateTypeScriptFunction(input, output, name_token); } bool ScriptInterpreterPythonImpl::GenerateTypeSynthClass( const char *oneliner, std::string &output, const void *name_token) { StringList input; input.SplitIntoLines(oneliner, strlen(oneliner)); return GenerateTypeSynthClass(input, output, name_token); } Status ScriptInterpreterPythonImpl::GenerateBreakpointCommandCallbackData( StringList &user_input, std::string &output, bool has_extra_args, bool is_callback) { static uint32_t num_created_functions = 0; user_input.RemoveBlankLines(); StreamString sstr; Status error; if (user_input.GetSize() == 0) { error = Status::FromErrorString("No input data."); return error; } std::string auto_generated_function_name(GenerateUniqueName( "lldb_autogen_python_bp_callback_func_", num_created_functions)); if (has_extra_args) sstr.Printf("def %s (frame, bp_loc, extra_args, internal_dict):", auto_generated_function_name.c_str()); else sstr.Printf("def %s (frame, bp_loc, internal_dict):", auto_generated_function_name.c_str()); error = GenerateFunction(sstr.GetData(), user_input, is_callback); if (!error.Success()) return error; // Store the name of the auto-generated function to be called. output.assign(auto_generated_function_name); return error; } bool ScriptInterpreterPythonImpl::GenerateWatchpointCommandCallbackData( StringList &user_input, std::string &output, bool is_callback) { static uint32_t num_created_functions = 0; user_input.RemoveBlankLines(); StreamString sstr; if (user_input.GetSize() == 0) return false; std::string auto_generated_function_name(GenerateUniqueName( "lldb_autogen_python_wp_callback_func_", num_created_functions)); sstr.Printf("def %s (frame, wp, internal_dict):", auto_generated_function_name.c_str()); if (!GenerateFunction(sstr.GetData(), user_input, is_callback).Success()) return false; // Store the name of the auto-generated function to be called. output.assign(auto_generated_function_name); return true; } bool ScriptInterpreterPythonImpl::GetScriptedSummary( const char *python_function_name, lldb::ValueObjectSP valobj, StructuredData::ObjectSP &callee_wrapper_sp, const TypeSummaryOptions &options, std::string &retval) { LLDB_SCOPED_TIMER(); if (!valobj.get()) { retval.assign(""); return false; } void *old_callee = nullptr; StructuredData::Generic *generic = nullptr; if (callee_wrapper_sp) { generic = callee_wrapper_sp->GetAsGeneric(); if (generic) old_callee = generic->GetValue(); } void *new_callee = old_callee; bool ret_val; if (python_function_name && *python_function_name) { { Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); { TypeSummaryOptionsSP options_sp(new TypeSummaryOptions(options)); static Timer::Category func_cat("LLDBSwigPythonCallTypeScript"); Timer scoped_timer(func_cat, "LLDBSwigPythonCallTypeScript"); ret_val = SWIGBridge::LLDBSwigPythonCallTypeScript( python_function_name, GetSessionDictionary().get(), valobj, &new_callee, options_sp, retval); } } } else { retval.assign(""); return false; } if (new_callee && old_callee != new_callee) { Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); callee_wrapper_sp = std::make_shared( PythonObject(PyRefType::Borrowed, static_cast(new_callee))); } return ret_val; } bool ScriptInterpreterPythonImpl::FormatterCallbackFunction( const char *python_function_name, TypeImplSP type_impl_sp) { Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); return SWIGBridge::LLDBSwigPythonFormatterCallbackFunction( python_function_name, m_dictionary_name.c_str(), type_impl_sp); } bool ScriptInterpreterPythonImpl::BreakpointCallbackFunction( void *baton, StoppointCallbackContext *context, user_id_t break_id, user_id_t break_loc_id) { CommandDataPython *bp_option_data = (CommandDataPython *)baton; const char *python_function_name = bp_option_data->script_source.c_str(); if (!context) return true; ExecutionContext exe_ctx(context->exe_ctx_ref); Target *target = exe_ctx.GetTargetPtr(); if (!target) return true; Debugger &debugger = target->GetDebugger(); ScriptInterpreterPythonImpl *python_interpreter = GetPythonInterpreter(debugger); if (!python_interpreter) return true; if (python_function_name && python_function_name[0]) { const StackFrameSP stop_frame_sp(exe_ctx.GetFrameSP()); BreakpointSP breakpoint_sp = target->GetBreakpointByID(break_id); if (breakpoint_sp) { const BreakpointLocationSP bp_loc_sp( breakpoint_sp->FindLocationByID(break_loc_id)); if (stop_frame_sp && bp_loc_sp) { bool ret_val = true; { Locker py_lock(python_interpreter, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); Expected maybe_ret_val = SWIGBridge::LLDBSwigPythonBreakpointCallbackFunction( python_function_name, python_interpreter->m_dictionary_name.c_str(), stop_frame_sp, bp_loc_sp, bp_option_data->m_extra_args); if (!maybe_ret_val) { llvm::handleAllErrors( maybe_ret_val.takeError(), [&](PythonException &E) { *debugger.GetAsyncErrorStream() << E.ReadBacktrace(); }, [&](const llvm::ErrorInfoBase &E) { *debugger.GetAsyncErrorStream() << E.message(); }); } else { ret_val = maybe_ret_val.get(); } } return ret_val; } } } // We currently always true so we stop in case anything goes wrong when // trying to call the script function return true; } bool ScriptInterpreterPythonImpl::WatchpointCallbackFunction( void *baton, StoppointCallbackContext *context, user_id_t watch_id) { WatchpointOptions::CommandData *wp_option_data = (WatchpointOptions::CommandData *)baton; const char *python_function_name = wp_option_data->script_source.c_str(); if (!context) return true; ExecutionContext exe_ctx(context->exe_ctx_ref); Target *target = exe_ctx.GetTargetPtr(); if (!target) return true; Debugger &debugger = target->GetDebugger(); ScriptInterpreterPythonImpl *python_interpreter = GetPythonInterpreter(debugger); if (!python_interpreter) return true; if (python_function_name && python_function_name[0]) { const StackFrameSP stop_frame_sp(exe_ctx.GetFrameSP()); WatchpointSP wp_sp = target->GetWatchpointList().FindByID(watch_id); if (wp_sp) { if (stop_frame_sp && wp_sp) { bool ret_val = true; { Locker py_lock(python_interpreter, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); ret_val = SWIGBridge::LLDBSwigPythonWatchpointCallbackFunction( python_function_name, python_interpreter->m_dictionary_name.c_str(), stop_frame_sp, wp_sp); } return ret_val; } } } // We currently always true so we stop in case anything goes wrong when // trying to call the script function return true; } bool ScriptInterpreterPythonImpl::RunScriptFormatKeyword( const char *impl_function, Process *process, std::string &output, Status &error) { bool ret_val; if (!process) { error = Status::FromErrorString("no process"); return false; } if (!impl_function || !impl_function[0]) { error = Status::FromErrorString("no function to execute"); return false; } { Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); ret_val = SWIGBridge::LLDBSWIGPythonRunScriptKeywordProcess( impl_function, m_dictionary_name.c_str(), process->shared_from_this(), output); if (!ret_val) error = Status::FromErrorString("python script evaluation failed"); } return ret_val; } bool ScriptInterpreterPythonImpl::RunScriptFormatKeyword( const char *impl_function, Thread *thread, std::string &output, Status &error) { if (!thread) { error = Status::FromErrorString("no thread"); return false; } if (!impl_function || !impl_function[0]) { error = Status::FromErrorString("no function to execute"); return false; } Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); if (std::optional result = SWIGBridge::LLDBSWIGPythonRunScriptKeywordThread( impl_function, m_dictionary_name.c_str(), thread->shared_from_this())) { output = std::move(*result); return true; } error = Status::FromErrorString("python script evaluation failed"); return false; } bool ScriptInterpreterPythonImpl::RunScriptFormatKeyword( const char *impl_function, Target *target, std::string &output, Status &error) { bool ret_val; if (!target) { error = Status::FromErrorString("no thread"); return false; } if (!impl_function || !impl_function[0]) { error = Status::FromErrorString("no function to execute"); return false; } { TargetSP target_sp(target->shared_from_this()); Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); ret_val = SWIGBridge::LLDBSWIGPythonRunScriptKeywordTarget( impl_function, m_dictionary_name.c_str(), target_sp, output); if (!ret_val) error = Status::FromErrorString("python script evaluation failed"); } return ret_val; } bool ScriptInterpreterPythonImpl::RunScriptFormatKeyword( const char *impl_function, StackFrame *frame, std::string &output, Status &error) { if (!frame) { error = Status::FromErrorString("no frame"); return false; } if (!impl_function || !impl_function[0]) { error = Status::FromErrorString("no function to execute"); return false; } Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); if (std::optional result = SWIGBridge::LLDBSWIGPythonRunScriptKeywordFrame( impl_function, m_dictionary_name.c_str(), frame->shared_from_this())) { output = std::move(*result); return true; } error = Status::FromErrorString("python script evaluation failed"); return false; } bool ScriptInterpreterPythonImpl::RunScriptFormatKeyword( const char *impl_function, ValueObject *value, std::string &output, Status &error) { bool ret_val; if (!value) { error = Status::FromErrorString("no value"); return false; } if (!impl_function || !impl_function[0]) { error = Status::FromErrorString("no function to execute"); return false; } { Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN); ret_val = SWIGBridge::LLDBSWIGPythonRunScriptKeywordValue( impl_function, m_dictionary_name.c_str(), value->GetSP(), output); if (!ret_val) error = Status::FromErrorString("python script evaluation failed"); } return ret_val; } uint64_t replace_all(std::string &str, const std::string &oldStr, const std::string &newStr) { size_t pos = 0; uint64_t matches = 0; while ((pos = str.find(oldStr, pos)) != std::string::npos) { matches++; str.replace(pos, oldStr.length(), newStr); pos += newStr.length(); } return matches; } bool ScriptInterpreterPythonImpl::LoadScriptingModule( const char *pathname, const LoadScriptOptions &options, lldb_private::Status &error, StructuredData::ObjectSP *module_sp, FileSpec extra_search_dir, lldb::TargetSP target_sp) { namespace fs = llvm::sys::fs; namespace path = llvm::sys::path; ExecuteScriptOptions exc_options = ExecuteScriptOptions() .SetEnableIO(!options.GetSilent()) .SetSetLLDBGlobals(false); if (!pathname || !pathname[0]) { error = Status::FromErrorString("empty path"); return false; } llvm::Expected> io_redirect_or_error = ScriptInterpreterIORedirect::Create( exc_options.GetEnableIO(), m_debugger, /*result=*/nullptr); if (!io_redirect_or_error) { error = Status::FromError(io_redirect_or_error.takeError()); return false; } ScriptInterpreterIORedirect &io_redirect = **io_redirect_or_error; // Before executing Python code, lock the GIL. Locker py_lock(this, Locker::AcquireLock | (options.GetInitSession() ? Locker::InitSession : 0) | Locker::NoSTDIN, Locker::FreeAcquiredLock | (options.GetInitSession() ? Locker::TearDownSession : 0), io_redirect.GetInputFile(), io_redirect.GetOutputFile(), io_redirect.GetErrorFile()); auto ExtendSysPath = [&](std::string directory) -> llvm::Error { if (directory.empty()) { return llvm::createStringError("invalid directory name"); } replace_all(directory, "\\", "\\\\"); replace_all(directory, "'", "\\'"); // Make sure that Python has "directory" in the search path. StreamString command_stream; command_stream.Printf("if not (sys.path.__contains__('%s')):\n " "sys.path.insert(1,'%s');\n\n", directory.c_str(), directory.c_str()); bool syspath_retval = ExecuteMultipleLines(command_stream.GetData(), exc_options).Success(); if (!syspath_retval) return llvm::createStringError("Python sys.path handling failed"); return llvm::Error::success(); }; std::string module_name(pathname); bool possible_package = false; if (extra_search_dir) { if (llvm::Error e = ExtendSysPath(extra_search_dir.GetPath())) { error = Status::FromError(std::move(e)); return false; } } else { FileSpec module_file(pathname); FileSystem::Instance().Resolve(module_file); fs::file_status st; std::error_code ec = status(module_file.GetPath(), st); if (ec || st.type() == fs::file_type::status_error || st.type() == fs::file_type::type_unknown || st.type() == fs::file_type::file_not_found) { // if not a valid file of any sort, check if it might be a filename still // dot can't be used but / and \ can, and if either is found, reject if (strchr(pathname, '\\') || strchr(pathname, '/')) { error = Status::FromErrorStringWithFormatv("invalid pathname '{0}'", pathname); return false; } // Not a filename, probably a package of some sort, let it go through. possible_package = true; } else if (is_directory(st) || is_regular_file(st)) { if (module_file.GetDirectory().empty()) { error = Status::FromErrorStringWithFormatv( "invalid directory name '{0}'", pathname); return false; } if (llvm::Error e = ExtendSysPath(module_file.GetDirectory().str())) { error = Status::FromError(std::move(e)); return false; } module_name = module_file.GetFilename().str(); } else { error = Status::FromErrorString( "no known way to import this module specification"); return false; } } // Strip .py or .pyc extension llvm::StringRef extension = llvm::sys::path::extension(module_name); if (!extension.empty()) { if (extension == ".py") module_name.resize(module_name.length() - 3); else if (extension == ".pyc") module_name.resize(module_name.length() - 4); } if (!possible_package && module_name.find('.') != llvm::StringRef::npos) { error = Status::FromErrorStringWithFormat( "Python does not allow dots in module names: %s", module_name.c_str()); return false; } if (module_name.find('-') != llvm::StringRef::npos) { error = Status::FromErrorStringWithFormat( "Python discourages dashes in module names: %s", module_name.c_str()); return false; } // Check if the module is already imported. StreamString command_stream; command_stream.Clear(); command_stream.Printf("sys.modules.__contains__('%s')", module_name.c_str()); bool does_contain = false; // This call will succeed if the module was ever imported in any Debugger in // the lifetime of the process in which this LLDB framework is living. const bool does_contain_executed = ExecuteOneLineWithReturn( command_stream.GetData(), ScriptInterpreterPythonImpl::eScriptReturnTypeBool, &does_contain, exc_options); const bool was_imported_globally = does_contain_executed && does_contain; const bool was_imported_locally = GetSessionDictionary() .GetItemForKey(PythonString(module_name)) .IsAllocated(); // now actually do the import command_stream.Clear(); if (was_imported_globally || was_imported_locally) { if (!was_imported_locally) command_stream.Printf("import %s ; reload_module(%s)", module_name.c_str(), module_name.c_str()); else command_stream.Printf("reload_module(%s)", module_name.c_str()); } else command_stream.Printf("import %s", module_name.c_str()); error = ExecuteMultipleLines(command_stream.GetData(), exc_options); if (error.Fail()) return false; // if we are here, everything worked // call __lldb_init_module(debugger,dict) if (!SWIGBridge::LLDBSwigPythonCallModuleInit( module_name.c_str(), m_dictionary_name.c_str(), m_debugger.shared_from_this())) { error = Status::FromErrorString("calling __lldb_init_module failed"); return false; } if (module_sp) { // everything went just great, now set the module object command_stream.Clear(); command_stream.Printf("%s", module_name.c_str()); void *module_pyobj = nullptr; if (ExecuteOneLineWithReturn( command_stream.GetData(), ScriptInterpreter::eScriptReturnTypeOpaqueObject, &module_pyobj, exc_options) && module_pyobj) *module_sp = std::make_shared(PythonObject( PyRefType::Owned, static_cast(module_pyobj))); } // Finally, if we got a target passed in, then we should tell the new module // about this target: if (target_sp) return SWIGBridge::LLDBSwigPythonCallModuleNewTarget( module_name.c_str(), m_dictionary_name.c_str(), target_sp); return true; } bool ScriptInterpreterPythonImpl::IsReservedWord(const char *word) { if (!word || !word[0]) return false; llvm::StringRef word_sr(word); // filter out a few characters that would just confuse us and that are // clearly not keyword material anyway if (word_sr.find('"') != llvm::StringRef::npos || word_sr.find('\'') != llvm::StringRef::npos) return false; StreamString command_stream; command_stream.Printf("keyword.iskeyword('%s')", word); bool result; ExecuteScriptOptions options; options.SetEnableIO(false); options.SetMaskoutErrors(true); options.SetSetLLDBGlobals(false); if (ExecuteOneLineWithReturn(command_stream.GetData(), ScriptInterpreter::eScriptReturnTypeBool, &result, options)) return result; return false; } ScriptInterpreterPythonImpl::SynchronicityHandler::SynchronicityHandler( lldb::DebuggerSP debugger_sp, ScriptedCommandSynchronicity synchro) : m_debugger_sp(debugger_sp), m_synch_wanted(synchro), m_old_asynch(debugger_sp->GetAsyncExecution()) { if (m_synch_wanted == eScriptedCommandSynchronicitySynchronous) m_debugger_sp->SetAsyncExecution(false); else if (m_synch_wanted == eScriptedCommandSynchronicityAsynchronous) m_debugger_sp->SetAsyncExecution(true); } ScriptInterpreterPythonImpl::SynchronicityHandler::~SynchronicityHandler() { if (m_synch_wanted != eScriptedCommandSynchronicityCurrentValue) m_debugger_sp->SetAsyncExecution(m_old_asynch); } bool ScriptInterpreterPythonImpl::RunScriptBasedCommand( const char *impl_function, llvm::StringRef args, ScriptedCommandSynchronicity synchronicity, lldb_private::CommandReturnObject &cmd_retobj, Status &error, const lldb_private::ExecutionContext &exe_ctx) { if (!impl_function) { error = Status::FromErrorString("no function to execute"); return false; } lldb::DebuggerSP debugger_sp = m_debugger.shared_from_this(); lldb::ExecutionContextRefSP exe_ctx_ref_sp(new ExecutionContextRef(exe_ctx)); if (!debugger_sp.get()) { error = Status::FromErrorString("invalid Debugger pointer"); return false; } bool ret_val = false; { Locker py_lock(this, Locker::AcquireLock | Locker::InitSession | (cmd_retobj.GetInteractive() ? 0 : Locker::NoSTDIN), Locker::FreeLock | Locker::TearDownSession); SynchronicityHandler synch_handler(debugger_sp, synchronicity); std::string args_str = args.str(); ret_val = SWIGBridge::LLDBSwigPythonCallCommand( impl_function, m_dictionary_name.c_str(), debugger_sp, args_str.c_str(), cmd_retobj, exe_ctx_ref_sp); } if (!ret_val) { error = Status::FromErrorString("unable to execute script function"); return false; } if (cmd_retobj.GetStatus() == eReturnStatusFailed) return false; error.Clear(); return ret_val; } /// In Python, a special attribute __doc__ contains the docstring for an object /// (function, method, class, ...) if any is defined Otherwise, the attribute's /// value is None. bool ScriptInterpreterPythonImpl::GetDocumentationForItem(const char *item, std::string &dest) { dest.clear(); if (!item || !*item) return false; std::string command(item); command += ".__doc__"; // Python is going to point this to valid data if ExecuteOneLineWithReturn // returns successfully. char *result_ptr = nullptr; if (ExecuteOneLineWithReturn( command, ScriptInterpreter::eScriptReturnTypeCharStrOrNone, &result_ptr, ExecuteScriptOptions().SetEnableIO(false))) { if (result_ptr) dest.assign(result_ptr); return true; } StreamString str_stream; str_stream << "Function " << item << " was not found. Containing module might be missing."; dest = std::string(str_stream.GetString()); return false; } std::unique_ptr ScriptInterpreterPythonImpl::AcquireInterpreterLock() { std::unique_ptr py_lock(new Locker( this, Locker::AcquireLock | Locker::InitSession | Locker::NoSTDIN, Locker::FreeLock | Locker::TearDownSession)); return py_lock; } void ScriptInterpreterPythonImpl::Initialize() { LLDB_SCOPED_TIMER(); // RAII-based initialization which correctly handles multiple-initialization, // version- specific differences among Python 2 and Python 3, and saving and // restoring various other pieces of state that can get mucked with during // initialization. InitializePythonRAII initialize_guard; LLDBSwigPyInit(); // Update the path python uses to search for modules to include the current // directory. RunSimpleString("import sys"); AddToSysPath(AddLocation::End, "."); // Don't denormalize paths when calling file_spec.GetPath(). On platforms // that use a backslash as the path separator, this will result in executing // python code containing paths with unescaped backslashes. But Python also // accepts forward slashes, so to make life easier we just use that. if (FileSpec file_spec = GetPythonDir()) AddToSysPath(AddLocation::Beginning, file_spec.GetPath(false)); if (FileSpec file_spec = HostInfo::GetShlibDir()) AddToSysPath(AddLocation::Beginning, file_spec.GetPath(false)); RunSimpleString("sys.dont_write_bytecode = 1; import " "lldb.embedded_interpreter; from " "lldb.embedded_interpreter import run_python_interpreter; " "from lldb.embedded_interpreter import run_one_line"); #if LLDB_USE_PYTHON_SET_INTERRUPT // Python will not just overwrite its internal SIGINT handler but also the // one from the process. Backup the current SIGINT handler to prevent that // Python deletes it. RestoreSignalHandlerScope save_sigint(SIGINT); // Setup a default SIGINT signal handler that works the same way as the // normal Python REPL signal handler which raises a KeyboardInterrupt. // Also make sure to not pollute the user's REPL with the signal module nor // our utility function. RunSimpleString("def lldb_setup_sigint_handler():\n" " import signal;\n" " def signal_handler(sig, frame):\n" " raise KeyboardInterrupt()\n" " signal.signal(signal.SIGINT, signal_handler);\n" "lldb_setup_sigint_handler();\n" "del lldb_setup_sigint_handler\n"); #endif } void ScriptInterpreterPythonImpl::AddToSysPath(AddLocation location, std::string path) { std::string statement; if (location == AddLocation::Beginning) { statement.assign("sys.path.insert(0,\""); statement.append(path); statement.append("\")"); } else { statement.assign("sys.path.append(\""); statement.append(path); statement.append("\")"); } RunSimpleString(statement.c_str()); } // We are intentionally NOT calling Py_Finalize here (this would be the logical // place to call it). Calling Py_Finalize here causes test suite runs to seg // fault: The test suite runs in Python. It registers SBDebugger::Terminate to // be called 'at_exit'. When the test suite Python harness finishes up, it // calls Py_Finalize, which calls all the 'at_exit' registered functions. // SBDebugger::Terminate calls Debugger::Terminate, which calls lldb::Terminate, // which calls ScriptInterpreter::Terminate, which calls // ScriptInterpreterPythonImpl::Terminate. So if we call Py_Finalize here, we // end up with Py_Finalize being called from within Py_Finalize, which results // in a seg fault. Since this function only gets called when lldb is shutting // down and going away anyway, the fact that we don't actually call Py_Finalize // should not cause any problems (everything should shut down/go away anyway // when the process exits). // // void ScriptInterpreterPythonImpl::Terminate() { Py_Finalize (); }