8000 gh-90997: bpo-46841: Disassembly of quickened code by penguin-wwy · Pull Request #32099 · python/cpython · GitHub
[go: up one dir, main page]
Skip to content

gh-90997: bpo-46841: Disassembly of quickened code #32099

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 16 commits into from
Apr 19, 2022
Merged

gh-90997: bpo-46841: Disassembly of quickened code #32099

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
34e7e3c
Disassembly of quickened code
penguin-wwy Mar 23, 2022
ceabedb
Reset `deoptmap` and fix test_dis
penguin-wwy Mar 24, 2022
9cef324
Clean code
penguin-wwy Mar 24, 2022
733bdd4
Fix assert for deopt code
penguin-wwy Mar 24, 2022
bd59be2
Revert `co_code`
penguin-wwy Mar 24, 2022
f72c1fb
Rename kwarg name and use `_co_code_adaptive`
penguin-wwy Mar 24, 2022
c14ab90
Fix test__opcode
penguin-wwy Mar 24, 2022
026715a
Add News
penguin-wwy Mar 25, 2022
9ab5fac
Merge branch 'main' of https://github.com/python/cpython into dis_qui…
penguin-wwy Mar 29, 2022
88ab80c
Merge branch 'main' of https://github.com/python/cpython into dis_qui…
penguin-wwy Apr 1, 2022
2a4bb97
Move deoptmap to dis module
penguin-wwy Apr 1, 2022
794536f
Add code quicken in test_dis
penguin-wwy Apr 2, 2022
e896538
Get quickened in dis
penguin-wwy Apr 6, 2022
659d570
Merge branch 'main' of https://github.com/python/cpython into dis_qui…
penguin-wwy Apr 6, 2022
ca9a734
Merge branch 'main' of https://github.com/python/cpython into dis_qui…
penguin-wwy Apr 14, 2022
82b053f
Fix test_dis
penguin-wwy Apr 18, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
99 changes: 63 additions & 36 deletions Lib/dis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@

from opcode import *
from opcode import __all__ as _opcodes_all
from opcode import _nb_ops
from opcode import _nb_ops, _inline_cache_entries, _specializations, _specialized_instructions

__all__ = ["code_info", "dis", "disassemble", "distb", "disco",
"findlinestarts", "findlabels", "show_code",
Expand All @@ -34,6 +34,18 @@

CACHE = opmap["CACHE"]

_all_opname = list(opname)
_all_opmap = dict(opmap)
_empty_slot = [slot for slot, name in enumerate(_all_opname) if name.startswith("<")]
for spec_op, specialized in zip(_empty_slot, _specialized_instructions):
# fill opname and opmap
_all_opname[spec_op] = specialized
_all_opmap[specialized] = spec_op

deoptmap = {
specialized: base for base, family in _specializations.items() for specialized in family
}

def _try_compile(source, name):
"""Attempts to compile the given source, first as an expression and
then as a statement if the first approach fails.
Expand All @@ -47,7 +59,7 @@ def _try_compile(source, name):
c = compile(source, name, 'exec')
return c

def dis(x=None, *, file=None, depth=None, show_caches=False):
def dis(x=None, *, file=None, depth=None, show_caches=False, adaptive=False):
"""Disassemble classes, methods, functions, and other compiled objects.

With no argument, disassemble the last traceback.
Expand All @@ -57,7 +69,7 @@ def dis(x=None, *, file=None, depth=None, show_caches=False):
in a special attribute.
"""
if x is None:
distb(file=file, show_caches=show_caches)
distb(file=file, show_caches=show_caches, adaptive=adaptive)
return
# Extract functions from methods.
if hasattr(x, '__func__'):
Expand All @@ -78,29 +90,29 @@ def dis(x=None, *, file=None, depth=None, show_caches=False):
if isinstance(x1, _have_code):
print("Disassembly of %s:" % name, file=file)
try:
dis(x1, file=file, depth=depth, show_caches=show_caches)
dis(x1, file=file, depth=depth, show_caches=show_caches, adaptive=adaptive)
except TypeError as msg:
print("Sorry:", msg, file=file)
print(file=file)
elif hasattr(x, 'co_code'): # Code object
_disassemble_recursive(x, file=file, depth=depth, show_caches=show_caches)
_disassemble_recursive(x, file=file, depth=depth, show_caches=show_caches, adaptive=adaptive)
elif isinstance(x, (bytes, bytearray)): # Raw bytecode
_disassemble_bytes(x, file=file, show_caches=show_caches)
elif isinstance(x, str): # Source code
_disassemble_str(x, file=file, depth=depth, show_caches=show_caches)
_disassemble_str(x, file=file, depth=depth, show_caches=show_caches, adaptive=adaptive)
else:
raise TypeError("don't know how to disassemble %s objects" %
type(x).__name__)

def distb(tb=None, *, file=None, show_caches=False):
def distb(tb=None, *, file=None, show_caches=False, adaptive=False):
"""Disassemble a traceback (default: last traceback)."""
if tb is None:
try:
tb = sys.last_traceback
except AttributeError:
raise RuntimeError("no last traceback to disassemble") from None
while tb.tb_next: tb = tb.tb_next
disassemble(tb.tb_frame.f_code, tb.tb_lasti, file=file, show_caches=show_caches)
disassemble(tb.tb_frame.f_code, tb.tb_lasti, file=file, show_caches=show_caches, adaptive=adaptive)

# The inspect module interrogates this dictionary to build its
# list of CO_* constants. It is also used by pretty_flags to
Expand Down Expand Up @@ -162,6 +174,13 @@ def _get_code_object(x):
raise TypeError("don't know how to disassemble %s objects" %
type(x).__name__)

def _deoptop(op):
name = _all_opname[op]
return _all_opmap[deoptmap[name]] if name in deoptmap else op

def _get_code_array(co, adaptive):
return co._co_code_adaptive if adaptive else co.co_code

def code_info(x):
"""Formatted details of methods, functions, or code."""
return _format_code_info(_get_code_object(x))
Expand Down Expand Up @@ -302,7 +321,7 @@ def _disassemble(self, lineno_width=3, mark_as_current=False, offset_width=4):
return ' '.join(fields).rstrip()


def get_instructions(x, *, first_line=None, show_caches=False):
def get_instructions(x, *, first_line=None, show_caches=False, adaptive=False):
"""Iterator for the opcodes in methods, functions or code

Generates a series of Instruction named tuples giving the details of
Expand All @@ -319,7 +338,7 @@ def get_instructions(x, *, first_line=None, show_caches=False):
line_offset = first_line - co.co_firstlineno
else:
line_offset = 0
return _get_instructions_bytes(co.co_code,
return _get_instructions_bytes(_get_code_array(co, adaptive),
co._varname_from_oparg,
co.co_names, co.co_consts,
linestarts, line_offset,
Expand Down Expand Up @@ -415,8 +434,13 @@ def _get_instructions_bytes(code, varname_from_oparg=None,
for i in range(start, end):
labels.add(target)
starts_line = None
cache_counter = 0
for offset, op, arg in _unpack_opargs(code):
if not show_caches and op == CACHE:
if cache_counter > 0:
if show_caches:
yield Instruction("CACHE", 0, None, None, '',
offset, None, False, None)
cache_counter -= 1
continue
if linestarts is not None:
starts_line = linestarts.get(offset, None)
Expand All @@ -426,61 +450,63 @@ def _get_instructions_bytes(code, varname_from_oparg=None,
argval = None
argrepr = ''
positions = Positions(*next(co_positions, ()))
deop = _deoptop(op)
cache_counter = _inline_cache_entries[deop]
if arg is not None:
# Set argval to the dereferenced value of the argument when
# available, and argrepr to the string representation of argval.
# _disassemble_bytes needs the string repr of the
# raw name index for LOAD_GLOBAL, LOAD_CONST, etc.
argval = arg
if op in hasconst:
argval, argrepr = _get_const_info(op, arg, co_consts)
elif op in hasname:
if op == LOAD_GLOBAL:
if deop in hasconst:
argval, argrepr = _get_const_info(deop, arg, co_consts)
elif deop in hasname:
if deop == LOAD_GLOBAL:
argval, argrepr = _get_name_info(arg//2, get_name)
if (arg & 1) and argrepr:
argrepr = "NULL + " + argrepr
else:
argval, argrepr = _get_name_info(arg, get_name)
elif op in hasjabs:
elif deop in hasjabs:
argval = arg*2
argrepr = "to " + repr(argval)
elif op in hasjrel:
signed_arg = -arg if _is_backward_jump(op) else arg
elif deop in hasjrel:
signed_arg = -arg if _is_backward_jump(deop) else arg
argval = offset + 2 + signed_arg*2
argrepr = "to " + repr(argval)
elif op in haslocal or op in hasfree:
elif deop in haslocal or deop in hasfree:
argval, argrepr = _get_name_info(arg, varname_from_oparg)
elif op in hascompare:
elif deop in hascompare:
argval = cmp_op[arg]
argrepr = argval
elif op == FORMAT_VALUE:
elif deop == FORMAT_VALUE:
argval, argrepr = FORMAT_VALUE_CONVERTERS[arg & 0x3]
argval = (argval, bool(arg & 0x4))
if argval[1]:
if argrepr:
argrepr += ', '
argrepr += 'with format'
elif op == MAKE_FUNCTION:
elif deop == MAKE_FUNCTION:
argrepr = ', '.join(s for i, s in enumerate(MAKE_FUNCTION_FLAGS)
if arg & (1<<i))
elif op == BINARY_OP:
elif deop == BINARY_OP:
_, argrepr = _nb_ops[arg]
yield Instruction(opname[op], op,
yield Instruction(_all_opname[op], op,
arg, argval, argrepr,
offset, starts_line, is_jump_target, positions)

def disassemble(co, lasti=-1, *, file=None, show_caches=False):
def disassemble(co, lasti=-1, *, file=None, show_caches=False, adaptive=False):
"""Disassemble a code object."""
linestarts = dict(findlinestarts(co))
exception_entries = parse_exception_table(co)
_disassemble_bytes(co.co_code, lasti,
co._varname_from_oparg,
_disassemble_bytes(_get_code_array(co, adaptive),
lasti, co._varname_from_oparg,
co.co_names, co.co_consts, linestarts, file=file,
exception_entries=exception_entries,
co_positions=co.co_positions(), show_caches=show_caches)

def _disassemble_recursive(co, *, file=None, depth=None, show_caches=False):
disassemble(co, file=file, show_caches=show_caches)
def _disassemble_recursive(co, *, file=None, depth=None, show_caches=False, adaptive=False):
disassemble(co, file=file, show_caches=show_caches, adaptive=adaptive)
if depth is None or depth > 0:
if depth is not None:
depth = depth - 1
Expand All @@ -489,7 +515,7 @@ def _disassemble_recursive(co, *, file=None, depth=None, show_caches=False):
print(file=file)
print("Disassembly of %r:" % (x,), file=file)
_disassemble_recursive(
x, file=file, depth=depth, show_caches=show_caches
x, file=file, depth=depth, show_caches=show_caches, adaptive=adaptive
)

def _disassemble_bytes(code, lasti=-1, varname_from_oparg=None,
Expand Down Expand Up @@ -548,7 +574,7 @@ def _unpack_opargs(code):
extended_arg = 0
for i in range(0, len(code), 2):
op = code[i]
if op >= HAVE_ARGUMENT:
if _deoptop(op) >= HAVE_ARGUMENT:
arg = code[i+1] | extended_arg
extended_arg = (arg << 8) if op == EXTENDED_ARG else 0
# The oparg is stored as a signed integer
Expand Down Expand Up @@ -641,7 +667,7 @@ class Bytecode:

Iterating over this yields the bytecode operations as Instruction instances.
"""
def __init__(self, x, *, first_line=None, current_offset=None, show_caches=False):
def __init__(self, x, *, first_line=None, current_offset=None, show_caches=False, adaptive=False):
self.codeobj = co = _get_code_object(x)
if first_line is None:
self.first_line = co.co_firstlineno
Expand All @@ -654,10 +680,11 @@ def __init__(self, x, *, first_line=None, current_offset=None, show_caches=False
self.current_offset = current_offset
self.exception_entries = parse_exception_table(co)
self.show_caches = show_caches
self.adaptive = adaptive

def __iter__(self):
co = self.codeobj
return _get_instructions_bytes(co.co_code,
return _get_instructions_bytes(_get_code_array(co, self.adaptive),
co._varname_from_oparg,
co.co_names, co.co_consts,
self._linestarts,
Expand All @@ -671,12 +698,12 @@ def __repr__(self):
self._original_object)

@classmethod
def from_traceback(cls, tb, *, show_caches=False):
def from_traceback(cls, tb, *, show_caches=False, adaptive=False):
""" Construct a Bytecode from the given traceback """
while tb.tb_next:
tb = tb.tb_next
return cls(
tb.tb_frame.f_code, current_offset=tb.tb_lasti, show_caches=show_caches
tb.tb_frame.f_code, current_offset=tb.tb_lasti, show_caches=show_caches, adaptive=adaptive
)

def info(self):
Expand All @@ -691,7 +718,7 @@ def dis(self):
else:
offset = -1
with io.StringIO() as output:
_disassemble_bytes(co.co_code,
_disassemble_bytes(_get_code_array(co, self.adaptive),
varname_from_oparg=co._varname_from_oparg,
names=co.co_names, co_consts=co.co_consts,
linestarts=self._linestarts,
Expand Down
4 changes: 2 additions & 2 deletions Lib/test/test__opcode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ def test_stack_effect(self):
self.assertRaises(ValueError, stack_effect, dis.opmap['BUILD_SLICE'])
self.assertRaises(ValueError, stack_effect, dis.opmap['POP_TOP'], 0)
# All defined opcodes
for name, code in dis.opmap.items():
for name, code in filter(lambda item: item[0] not in dis.deoptmap, dis.opmap.items()):
with self.subTest(opname=name):
if code < dis.HAVE_ARGUMENT:
stack_effect(code)
Expand Down Expand Up @@ -47,7 +47,7 @@ def test_stack_effect_jump(self):
self.assertEqual(stack_effect(JUMP_FORWARD, 0, jump=False), 0)
# All defined opcodes
has_jump = dis.hasjabs + dis.hasjrel
for name, code in dis.opmap.items():
for name, code in filter(lambda item: item[0] not in dis.deoptmap, dis.opmap.items()):
with self.subTest(opname=name):
if code < dis.HAVE_ARGUMENT:
common = stack_effect(code)
Expand Down
Loading
0