cpython/Include/internal/pycore_runtime_init.h

244 lines
8.7 KiB
C
Raw Normal View History

#ifndef Py_INTERNAL_RUNTIME_INIT_H
#define Py_INTERNAL_RUNTIME_INIT_H
#ifdef __cplusplus
extern "C" {
#endif
#ifndef Py_BUILD_CORE
# error "this header requires Py_BUILD_CORE define"
#endif
#include "pycore_long.h"
#include "pycore_object.h"
#include "pycore_parser.h"
#include "pycore_pymem_init.h"
#include "pycore_obmalloc_init.h"
extern PyTypeObject _PyExc_MemoryError;
/* The static initializers defined here should only be used
in the runtime init code (in pystate.c and pylifecycle.c). */
#define _PyRuntimeState_INIT(runtime) \
{ \
.debug_offsets = { \
.cookie = "xdebugpy", \
.version = PY_VERSION_HEX, \
.runtime_state = { \
.finalizing = offsetof(_PyRuntimeState, _finalizing), \
.interpreters_head = offsetof(_PyRuntimeState, interpreters.head), \
}, \
.interpreter_state = { \
.next = offsetof(PyInterpreterState, next), \
.threads_head = offsetof(PyInterpreterState, threads.head), \
.gc = offsetof(PyInterpreterState, gc), \
.imports_modules = offsetof(PyInterpreterState, imports.modules), \
.sysdict = offsetof(PyInterpreterState, sysdict), \
.builtins = offsetof(PyInterpreterState, builtins), \
.ceval_gil = offsetof(PyInterpreterState, ceval.gil), \
.gil_runtime_state_locked = offsetof(PyInterpreterState, _gil.locked), \
.gil_runtime_state_holder = offsetof(PyInterpreterState, _gil.last_holder), \
}, \
.thread_state = { \
.prev = offsetof(PyThreadState, prev), \
.next = offsetof(PyThreadState, next), \
.interp = offsetof(PyThreadState, interp), \
.cframe = offsetof(PyThreadState, cframe), \
.thread_id = offsetof(PyThreadState, thread_id), \
.native_thread_id = offsetof(PyThreadState, native_thread_id), \
}, \
.interpreter_frame = { \
.previous = offsetof(_PyInterpreterFrame, previous), \
.executable = offsetof(_PyInterpreterFrame, f_executable), \
.prev_instr = offsetof(_PyInterpreterFrame, prev_instr), \
.localsplus = offsetof(_PyInterpreterFrame, localsplus), \
.owner = offsetof(_PyInterpreterFrame, owner), \
}, \
.cframe = { \
.current_frame = offsetof(_PyCFrame, current_frame), \
.previous = offsetof(_PyCFrame, previous), \
}, \
.code_object = { \
.filename = offsetof(PyCodeObject, co_filename), \
.name = offsetof(PyCodeObject, co_name), \
.linetable = offsetof(PyCodeObject, co_linetable), \
.firstlineno = offsetof(PyCodeObject, co_firstlineno), \
.argcount = offsetof(PyCodeObject, co_argcount), \
.localsplusnames = offsetof(PyCodeObject, co_localsplusnames), \
.localspluskinds = offsetof(PyCodeObject, co_localspluskinds), \
.co_code_adaptive = offsetof(PyCodeObject, co_code_adaptive), \
}, \
.pyobject = { \
.ob_type = offsetof(PyObject, ob_type), \
}, \
.type_object = { \
.tp_name = offsetof(PyTypeObject, tp_name), \
}, \
.tuple_object = { \
.ob_item = offsetof(PyTupleObject, ob_item), \
}, \
}, \
.allocators = { \
.standard = _pymem_allocators_standard_INIT(runtime), \
.debug = _pymem_allocators_debug_INIT, \
.obj_arena = _pymem_allocators_obj_arena_INIT, \
}, \
.obmalloc = _obmalloc_global_state_INIT, \
.pyhash_state = pyhash_state_INIT, \
.signals = _signals_RUNTIME_INIT, \
.interpreters = { \
/* This prevents interpreters from getting created \
until _PyInterpreterState_Enable() is called. */ \
.next_id = -1, \
}, \
/* A TSS key must be initialized with Py_tss_NEEDS_INIT \
in accordance with the specification. */ \
.autoTSSkey = Py_tss_NEEDS_INIT, \
.parser = _parser_runtime_state_INIT, \
gh-100227: Make the Global PyModuleDef Cache Safe for Isolated Interpreters (gh-103084) Sharing mutable (or non-immortal) objects between interpreters is generally not safe. We can work around that but not easily. There are two restrictions that are critical for objects that break interpreter isolation. The first is that the object's state be guarded by a global lock. For now the GIL meets this requirement, but a granular global lock is needed once we have a per-interpreter GIL. The second restriction is that the object (and, for a container, its items) be deallocated/resized only when the interpreter in which it was allocated is the current one. This is because every interpreter has (or will have, see gh-101660) its own object allocator. Deallocating an object with a different allocator can cause crashes. The dict for the cache of module defs is completely internal, which simplifies what we have to do to meet those requirements. To do so, we do the following: * add a mechanism for re-using a temporary thread state tied to the main interpreter in an arbitrary thread * add _PyRuntime.imports.extensions.main_tstate` * add _PyThreadState_InitDetached() and _PyThreadState_ClearDetached() (pystate.c) * add _PyThreadState_BindDetached() and _PyThreadState_UnbindDetached() (pystate.c) * make sure the cache dict (_PyRuntime.imports.extensions.dict) and its items are all owned by the main interpreter) * add a placeholder using for a granular global lock Note that the cache is only used for legacy extension modules and not for multi-phase init modules. https://github.com/python/cpython/issues/100227
2023-03-29 20:15:43 -03:00
.imports = { \
.extensions = { \
.main_tstate = _PyThreadState_INIT, \
}, \
}, \
.ceval = { \
.perf = _PyEval_RUNTIME_PERF_INIT, \
}, \
.gilstate = { \
.check_enabled = 1, \
}, \
.fileutils = { \
.force_ascii = -1, \
}, \
.faulthandler = _faulthandler_runtime_state_INIT, \
.tracemalloc = _tracemalloc_runtime_state_INIT, \
.float_state = { \
.float_format = _py_float_format_unknown, \
.double_format = _py_float_format_unknown, \
}, \
.types = { \
.next_version_tag = 1, \
}, \
.static_objects = { \
.singletons = { \
.small_ints = _Py_small_ints_INIT, \
.bytes_empty = _PyBytes_SIMPLE_INIT(0, 0), \
.bytes_characters = _Py_bytes_characters_INIT, \
.strings = { \
.literals = _Py_str_literals_INIT, \
.identifiers = _Py_str_identifiers_INIT, \
.ascii = _Py_str_ascii_INIT, \
.latin1 = _Py_str_latin1_INIT, \
}, \
.tuple_empty = { \
.ob_base = _PyVarObject_HEAD_INIT(&PyTuple_Type, 0) \
}, \
.hamt_bitmap_node_empty = { \
.ob_base = _PyVarObject_HEAD_INIT(&_PyHamt_BitmapNode_Type, 0) \
}, \
.context_token_missing = { \
.ob_base = _PyObject_HEAD_INIT(&_PyContextTokenMissing_Type) \
}, \
}, \
}, \
._main_interpreter = _PyInterpreterState_INIT(runtime._main_interpreter), \
}
#define _PyInterpreterState_INIT(INTERP) \
{ \
.id_refcount = -1, \
.imports = IMPORTS_INIT, \
.obmalloc = _obmalloc_state_INIT(INTERP.obmalloc), \
.ceval = { \
.recursion_limit = Py_DEFAULT_RECURSION_LIMIT, \
}, \
.gc = { \
.enabled = 1, \
.generations = { \
/* .head is set in _PyGC_InitState(). */ \
{ .threshold = 700, }, \
{ .threshold = 10, }, \
{ .threshold = 10, }, \
}, \
}, \
.dtoa = _dtoa_state_INIT(&(INTERP)), \
.dict_state = _dict_state_INIT, \
.func_state = { \
.next_version = 1, \
}, \
.types = { \
.next_version_tag = _Py_TYPE_BASE_VERSION_TAG, \
}, \
.static_objects = { \
.singletons = { \
._not_used = 1, \
.hamt_empty = { \
.ob_base = _PyObject_HEAD_INIT(&_PyHamt_Type) \
.h_root = (PyHamtNode*)&_Py_SINGLETON(hamt_bitmap_node_empty), \
}, \
.last_resort_memory_error = { \
_PyObject_HEAD_INIT(&_PyExc_MemoryError) \
}, \
}, \
}, \
._initial_thread = _PyThreadState_INIT, \
}
#define _PyThreadState_INIT \
{ \
.py_recursion_limit = Py_DEFAULT_RECURSION_LIMIT, \
.context_ver = 1, \
}
// global objects
#define _PyBytes_SIMPLE_INIT(CH, LEN) \
{ \
_PyVarObject_HEAD_INIT(&PyBytes_Type, (LEN)) \
.ob_shash = -1, \
.ob_sval = { (CH) }, \
}
#define _PyBytes_CHAR_INIT(CH) \
{ \
_PyBytes_SIMPLE_INIT((CH), 1) \
}
#define _PyUnicode_ASCII_BASE_INIT(LITERAL, ASCII) \
bpo-46541: Replace core use of _Py_IDENTIFIER() with statically initialized global objects. (gh-30928) We're no longer using _Py_IDENTIFIER() (or _Py_static_string()) in any core CPython code. It is still used in a number of non-builtin stdlib modules. The replacement is: PyUnicodeObject (not pointer) fields under _PyRuntimeState, statically initialized as part of _PyRuntime. A new _Py_GET_GLOBAL_IDENTIFIER() macro facilitates lookup of the fields (along with _Py_GET_GLOBAL_STRING() for non-identifier strings). https://bugs.python.org/issue46541#msg411799 explains the rationale for this change. The core of the change is in: * (new) Include/internal/pycore_global_strings.h - the declarations for the global strings, along with the macros * Include/internal/pycore_runtime_init.h - added the static initializers for the global strings * Include/internal/pycore_global_objects.h - where the struct in pycore_global_strings.h is hooked into _PyRuntimeState * Tools/scripts/generate_global_objects.py - added generation of the global string declarations and static initializers I've also added a --check flag to generate_global_objects.py (along with make check-global-objects) to check for unused global strings. That check is added to the PR CI config. The remainder of this change updates the core code to use _Py_GET_GLOBAL_IDENTIFIER() instead of _Py_IDENTIFIER() and the related _Py*Id functions (likewise for _Py_GET_GLOBAL_STRING() instead of _Py_static_string()). This includes adding a few functions where there wasn't already an alternative to _Py*Id(), replacing the _Py_Identifier * parameter with PyObject *. The following are not changed (yet): * stop using _Py_IDENTIFIER() in the stdlib modules * (maybe) get rid of _Py_IDENTIFIER(), etc. entirely -- this may not be doable as at least one package on PyPI using this (private) API * (maybe) intern the strings during runtime init https://bugs.python.org/issue46541
2022-02-08 16:39:07 -04:00
{ \
.ob_base = _PyObject_HEAD_INIT(&PyUnicode_Type) \
.length = sizeof(LITERAL) - 1, \
.hash = -1, \
.state = { \
.kind = 1, \
.compact = 1, \
.ascii = (ASCII), \
bpo-46541: Replace core use of _Py_IDENTIFIER() with statically initialized global objects. (gh-30928) We're no longer using _Py_IDENTIFIER() (or _Py_static_string()) in any core CPython code. It is still used in a number of non-builtin stdlib modules. The replacement is: PyUnicodeObject (not pointer) fields under _PyRuntimeState, statically initialized as part of _PyRuntime. A new _Py_GET_GLOBAL_IDENTIFIER() macro facilitates lookup of the fields (along with _Py_GET_GLOBAL_STRING() for non-identifier strings). https://bugs.python.org/issue46541#msg411799 explains the rationale for this change. The core of the change is in: * (new) Include/internal/pycore_global_strings.h - the declarations for the global strings, along with the macros * Include/internal/pycore_runtime_init.h - added the static initializers for the global strings * Include/internal/pycore_global_objects.h - where the struct in pycore_global_strings.h is hooked into _PyRuntimeState * Tools/scripts/generate_global_objects.py - added generation of the global string declarations and static initializers I've also added a --check flag to generate_global_objects.py (along with make check-global-objects) to check for unused global strings. That check is added to the PR CI config. The remainder of this change updates the core code to use _Py_GET_GLOBAL_IDENTIFIER() instead of _Py_IDENTIFIER() and the related _Py*Id functions (likewise for _Py_GET_GLOBAL_STRING() instead of _Py_static_string()). This includes adding a few functions where there wasn't already an alternative to _Py*Id(), replacing the _Py_Identifier * parameter with PyObject *. The following are not changed (yet): * stop using _Py_IDENTIFIER() in the stdlib modules * (maybe) get rid of _Py_IDENTIFIER(), etc. entirely -- this may not be doable as at least one package on PyPI using this (private) API * (maybe) intern the strings during runtime init https://bugs.python.org/issue46541
2022-02-08 16:39:07 -04:00
}, \
}
#define _PyASCIIObject_INIT(LITERAL) \
{ \
._ascii = _PyUnicode_ASCII_BASE_INIT((LITERAL), 1), \
._data = (LITERAL) \
bpo-46541: Replace core use of _Py_IDENTIFIER() with statically initialized global objects. (gh-30928) We're no longer using _Py_IDENTIFIER() (or _Py_static_string()) in any core CPython code. It is still used in a number of non-builtin stdlib modules. The replacement is: PyUnicodeObject (not pointer) fields under _PyRuntimeState, statically initialized as part of _PyRuntime. A new _Py_GET_GLOBAL_IDENTIFIER() macro facilitates lookup of the fields (along with _Py_GET_GLOBAL_STRING() for non-identifier strings). https://bugs.python.org/issue46541#msg411799 explains the rationale for this change. The core of the change is in: * (new) Include/internal/pycore_global_strings.h - the declarations for the global strings, along with the macros * Include/internal/pycore_runtime_init.h - added the static initializers for the global strings * Include/internal/pycore_global_objects.h - where the struct in pycore_global_strings.h is hooked into _PyRuntimeState * Tools/scripts/generate_global_objects.py - added generation of the global string declarations and static initializers I've also added a --check flag to generate_global_objects.py (along with make check-global-objects) to check for unused global strings. That check is added to the PR CI config. The remainder of this change updates the core code to use _Py_GET_GLOBAL_IDENTIFIER() instead of _Py_IDENTIFIER() and the related _Py*Id functions (likewise for _Py_GET_GLOBAL_STRING() instead of _Py_static_string()). This includes adding a few functions where there wasn't already an alternative to _Py*Id(), replacing the _Py_Identifier * parameter with PyObject *. The following are not changed (yet): * stop using _Py_IDENTIFIER() in the stdlib modules * (maybe) get rid of _Py_IDENTIFIER(), etc. entirely -- this may not be doable as at least one package on PyPI using this (private) API * (maybe) intern the strings during runtime init https://bugs.python.org/issue46541
2022-02-08 16:39:07 -04:00
}
#define INIT_STR(NAME, LITERAL) \
._py_ ## NAME = _PyASCIIObject_INIT(LITERAL)
bpo-46541: Replace core use of _Py_IDENTIFIER() with statically initialized global objects. (gh-30928) We're no longer using _Py_IDENTIFIER() (or _Py_static_string()) in any core CPython code. It is still used in a number of non-builtin stdlib modules. The replacement is: PyUnicodeObject (not pointer) fields under _PyRuntimeState, statically initialized as part of _PyRuntime. A new _Py_GET_GLOBAL_IDENTIFIER() macro facilitates lookup of the fields (along with _Py_GET_GLOBAL_STRING() for non-identifier strings). https://bugs.python.org/issue46541#msg411799 explains the rationale for this change. The core of the change is in: * (new) Include/internal/pycore_global_strings.h - the declarations for the global strings, along with the macros * Include/internal/pycore_runtime_init.h - added the static initializers for the global strings * Include/internal/pycore_global_objects.h - where the struct in pycore_global_strings.h is hooked into _PyRuntimeState * Tools/scripts/generate_global_objects.py - added generation of the global string declarations and static initializers I've also added a --check flag to generate_global_objects.py (along with make check-global-objects) to check for unused global strings. That check is added to the PR CI config. The remainder of this change updates the core code to use _Py_GET_GLOBAL_IDENTIFIER() instead of _Py_IDENTIFIER() and the related _Py*Id functions (likewise for _Py_GET_GLOBAL_STRING() instead of _Py_static_string()). This includes adding a few functions where there wasn't already an alternative to _Py*Id(), replacing the _Py_Identifier * parameter with PyObject *. The following are not changed (yet): * stop using _Py_IDENTIFIER() in the stdlib modules * (maybe) get rid of _Py_IDENTIFIER(), etc. entirely -- this may not be doable as at least one package on PyPI using this (private) API * (maybe) intern the strings during runtime init https://bugs.python.org/issue46541
2022-02-08 16:39:07 -04:00
#define INIT_ID(NAME) \
._py_ ## NAME = _PyASCIIObject_INIT(#NAME)
#define _PyUnicode_LATIN1_INIT(LITERAL, UTF8) \
{ \
._latin1 = { \
._base = _PyUnicode_ASCII_BASE_INIT((LITERAL), 0), \
.utf8 = (UTF8), \
.utf8_length = sizeof(UTF8) - 1, \
}, \
._data = (LITERAL), \
}
#include "pycore_runtime_init_generated.h"
#ifdef __cplusplus
}
#endif
#endif /* !Py_INTERNAL_RUNTIME_INIT_H */