2020-01-30 19:32:25 +03:00
|
|
|
#!/usr/bin/env python3
|
2017-12-07 23:44:09 +03:00
|
|
|
# Copyright (c) 2018 Linaro Limited
|
|
|
|
#
|
|
|
|
# This library is free software; you can redistribute it and/or
|
|
|
|
# modify it under the terms of the GNU Lesser General Public
|
|
|
|
# License as published by the Free Software Foundation; either
|
2020-10-23 15:33:53 +03:00
|
|
|
# version 2.1 of the License, or (at your option) any later version.
|
2017-12-07 23:44:09 +03:00
|
|
|
#
|
|
|
|
# This library is distributed in the hope that it will be useful,
|
|
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
# Lesser General Public License for more details.
|
|
|
|
#
|
|
|
|
# You should have received a copy of the GNU Lesser General Public
|
|
|
|
# License along with this library; if not, see <http://www.gnu.org/licenses/>.
|
|
|
|
#
|
|
|
|
|
|
|
|
#
|
|
|
|
# Generate a decoding tree from a specification file.
|
2019-02-24 00:00:10 +03:00
|
|
|
# See the syntax and semantics in docs/devel/decodetree.rst.
|
2017-12-07 23:44:09 +03:00
|
|
|
#
|
|
|
|
|
decodetree: Open files with encoding='utf-8'
When decodetree.py was added in commit 568ae7efae7, QEMU was
using Python 2 which happily reads UTF-8 files in text mode.
Python 3 requires either UTF-8 locale or an explicit encoding
passed to open(). Now that Python 3 is required, explicit
UTF-8 encoding for decodetree source files.
To avoid further problems with the user locale, also explicit
UTF-8 encoding for the generated C files.
Explicit both input/output are plain text by using the 't' mode.
This fixes:
$ /usr/bin/python3 scripts/decodetree.py test.decode
Traceback (most recent call last):
File "scripts/decodetree.py", line 1397, in <module>
main()
File "scripts/decodetree.py", line 1308, in main
parse_file(f, toppat)
File "scripts/decodetree.py", line 994, in parse_file
for line in f:
File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode
return codecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 80:
ordinal not in range(128)
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Suggested-by: Yonggang Luo <luoyonggang@gmail.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20210110000240.761122-1-f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-01-10 03:02:40 +03:00
|
|
|
import io
|
2017-12-07 23:44:09 +03:00
|
|
|
import os
|
|
|
|
import re
|
|
|
|
import sys
|
|
|
|
import getopt
|
|
|
|
|
|
|
|
insnwidth = 32
|
2021-04-08 01:18:49 +03:00
|
|
|
bitop_width = 32
|
2017-12-07 23:44:09 +03:00
|
|
|
insnmask = 0xffffffff
|
2019-01-31 05:01:29 +03:00
|
|
|
variablewidth = False
|
2017-12-07 23:44:09 +03:00
|
|
|
fields = {}
|
|
|
|
arguments = {}
|
|
|
|
formats = {}
|
2019-02-23 22:35:36 +03:00
|
|
|
allpatterns = []
|
2019-08-09 18:12:50 +03:00
|
|
|
anyextern = False
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
translate_prefix = 'trans'
|
|
|
|
translate_scope = 'static '
|
|
|
|
input_file = ''
|
|
|
|
output_file = None
|
|
|
|
output_fd = None
|
|
|
|
insntype = 'uint32_t'
|
2018-10-23 12:26:25 +03:00
|
|
|
decode_function = 'decode'
|
2017-12-07 23:44:09 +03:00
|
|
|
|
2020-09-03 22:23:34 +03:00
|
|
|
# An identifier for C.
|
|
|
|
re_C_ident = '[a-zA-Z][a-zA-Z0-9_]*'
|
2017-12-07 23:44:09 +03:00
|
|
|
|
2020-09-03 22:23:34 +03:00
|
|
|
# Identifiers for Arguments, Fields, Formats and Patterns.
|
|
|
|
re_arg_ident = '&[a-zA-Z0-9_]*'
|
|
|
|
re_fld_ident = '%[a-zA-Z0-9_]*'
|
|
|
|
re_fmt_ident = '@[a-zA-Z0-9_]*'
|
|
|
|
re_pat_ident = '[a-zA-Z0-9_]*'
|
2017-12-07 23:44:09 +03:00
|
|
|
|
2018-10-26 16:59:43 +03:00
|
|
|
def error_with_file(file, lineno, *args):
|
2017-12-07 23:44:09 +03:00
|
|
|
"""Print an error message from file:line and args and exit."""
|
|
|
|
global output_file
|
|
|
|
global output_fd
|
|
|
|
|
2020-05-16 00:48:54 +03:00
|
|
|
prefix = ''
|
|
|
|
if file:
|
2021-04-29 02:37:02 +03:00
|
|
|
prefix += f'{file}:'
|
2017-12-07 23:44:09 +03:00
|
|
|
if lineno:
|
2021-04-29 02:37:02 +03:00
|
|
|
prefix += f'{lineno}:'
|
2020-05-16 00:48:54 +03:00
|
|
|
if prefix:
|
|
|
|
prefix += ' '
|
|
|
|
print(prefix, end='error: ', file=sys.stderr)
|
|
|
|
print(*args, file=sys.stderr)
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
if output_file and output_fd:
|
|
|
|
output_fd.close()
|
|
|
|
os.remove(output_file)
|
|
|
|
exit(1)
|
2020-05-16 00:48:54 +03:00
|
|
|
# end error_with_file
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
|
2018-10-26 16:59:43 +03:00
|
|
|
def error(lineno, *args):
|
2020-05-16 00:48:54 +03:00
|
|
|
error_with_file(input_file, lineno, *args)
|
|
|
|
# end error
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
def output(*args):
|
|
|
|
global output_fd
|
|
|
|
for a in args:
|
|
|
|
output_fd.write(a)
|
|
|
|
|
|
|
|
|
|
|
|
def output_autogen():
|
|
|
|
output('/* This file is autogenerated by scripts/decodetree.py. */\n\n')
|
|
|
|
|
|
|
|
|
|
|
|
def str_indent(c):
|
|
|
|
"""Return a string with C spaces"""
|
|
|
|
return ' ' * c
|
|
|
|
|
|
|
|
|
|
|
|
def str_fields(fields):
|
2020-09-17 10:50:23 +03:00
|
|
|
"""Return a string uniquely identifying FIELDS"""
|
2017-12-07 23:44:09 +03:00
|
|
|
r = ''
|
|
|
|
for n in sorted(fields.keys()):
|
|
|
|
r += '_' + n
|
|
|
|
return r[1:]
|
|
|
|
|
|
|
|
|
2021-04-29 02:27:56 +03:00
|
|
|
def whex(val):
|
|
|
|
"""Return a hex string for val padded for insnwidth"""
|
|
|
|
global insnwidth
|
|
|
|
return f'0x{val:0{insnwidth // 4}x}'
|
|
|
|
|
|
|
|
|
|
|
|
def whexC(val):
|
|
|
|
"""Return a hex string for val padded for insnwidth,
|
|
|
|
and with the proper suffix for a C constant."""
|
|
|
|
suffix = ''
|
2021-04-08 01:18:49 +03:00
|
|
|
if val >= 0x100000000:
|
|
|
|
suffix = 'ull'
|
|
|
|
elif val >= 0x80000000:
|
2021-04-29 02:27:56 +03:00
|
|
|
suffix = 'u'
|
|
|
|
return whex(val) + suffix
|
|
|
|
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
def str_match_bits(bits, mask):
|
|
|
|
"""Return a string pretty-printing BITS/MASK"""
|
|
|
|
global insnwidth
|
|
|
|
|
|
|
|
i = 1 << (insnwidth - 1)
|
|
|
|
space = 0x01010100
|
|
|
|
r = ''
|
|
|
|
while i != 0:
|
|
|
|
if i & mask:
|
|
|
|
if i & bits:
|
|
|
|
r += '1'
|
|
|
|
else:
|
|
|
|
r += '0'
|
|
|
|
else:
|
|
|
|
r += '.'
|
|
|
|
if i & space:
|
|
|
|
r += ' '
|
|
|
|
i >>= 1
|
|
|
|
return r
|
|
|
|
|
|
|
|
|
|
|
|
def is_pow2(x):
|
|
|
|
"""Return true iff X is equal to a power of 2."""
|
|
|
|
return (x & (x - 1)) == 0
|
|
|
|
|
|
|
|
|
|
|
|
def ctz(x):
|
|
|
|
"""Return the number of times 2 factors into X."""
|
2020-05-16 23:15:02 +03:00
|
|
|
assert x != 0
|
2017-12-07 23:44:09 +03:00
|
|
|
r = 0
|
|
|
|
while ((x >> r) & 1) == 0:
|
|
|
|
r += 1
|
|
|
|
return r
|
|
|
|
|
|
|
|
|
|
|
|
def is_contiguous(bits):
|
2020-05-16 23:15:02 +03:00
|
|
|
if bits == 0:
|
|
|
|
return -1
|
2017-12-07 23:44:09 +03:00
|
|
|
shift = ctz(bits)
|
|
|
|
if is_pow2((bits >> shift) + 1):
|
|
|
|
return shift
|
|
|
|
else:
|
|
|
|
return -1
|
|
|
|
|
|
|
|
|
2021-04-29 20:03:59 +03:00
|
|
|
def eq_fields_for_args(flds_a, arg):
|
|
|
|
if len(flds_a) != len(arg.fields):
|
2017-12-07 23:44:09 +03:00
|
|
|
return False
|
2021-04-29 20:03:59 +03:00
|
|
|
# Only allow inference on default types
|
|
|
|
for t in arg.types:
|
|
|
|
if t != 'int':
|
|
|
|
return False
|
2017-12-07 23:44:09 +03:00
|
|
|
for k, a in flds_a.items():
|
2021-04-29 20:03:59 +03:00
|
|
|
if k not in arg.fields:
|
2017-12-07 23:44:09 +03:00
|
|
|
return False
|
|
|
|
return True
|
|
|
|
|
|
|
|
|
|
|
|
def eq_fields_for_fmts(flds_a, flds_b):
|
|
|
|
if len(flds_a) != len(flds_b):
|
|
|
|
return False
|
|
|
|
for k, a in flds_a.items():
|
|
|
|
if k not in flds_b:
|
|
|
|
return False
|
|
|
|
b = flds_b[k]
|
|
|
|
if a.__class__ != b.__class__ or a != b:
|
|
|
|
return False
|
|
|
|
return True
|
|
|
|
|
|
|
|
|
|
|
|
class Field:
|
|
|
|
"""Class representing a simple instruction field"""
|
|
|
|
def __init__(self, sign, pos, len):
|
|
|
|
self.sign = sign
|
|
|
|
self.pos = pos
|
|
|
|
self.len = len
|
|
|
|
self.mask = ((1 << len) - 1) << pos
|
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
if self.sign:
|
|
|
|
s = 's'
|
|
|
|
else:
|
|
|
|
s = ''
|
2018-10-04 19:18:50 +03:00
|
|
|
return str(self.pos) + ':' + s + str(self.len)
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
def str_extract(self):
|
2021-04-08 01:18:49 +03:00
|
|
|
global bitop_width
|
|
|
|
s = 's' if self.sign else ''
|
|
|
|
return f'{s}extract{bitop_width}(insn, {self.pos}, {self.len})'
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
def __eq__(self, other):
|
2019-06-11 18:39:41 +03:00
|
|
|
return self.sign == other.sign and self.mask == other.mask
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
def __ne__(self, other):
|
|
|
|
return not self.__eq__(other)
|
|
|
|
# end Field
|
|
|
|
|
|
|
|
|
|
|
|
class MultiField:
|
|
|
|
"""Class representing a compound instruction field"""
|
|
|
|
def __init__(self, subs, mask):
|
|
|
|
self.subs = subs
|
|
|
|
self.sign = subs[0].sign
|
|
|
|
self.mask = mask
|
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
return str(self.subs)
|
|
|
|
|
|
|
|
def str_extract(self):
|
2021-04-08 01:18:49 +03:00
|
|
|
global bitop_width
|
2017-12-07 23:44:09 +03:00
|
|
|
ret = '0'
|
|
|
|
pos = 0
|
|
|
|
for f in reversed(self.subs):
|
2021-04-29 02:37:02 +03:00
|
|
|
ext = f.str_extract()
|
2017-12-07 23:44:09 +03:00
|
|
|
if pos == 0:
|
2021-04-29 02:37:02 +03:00
|
|
|
ret = ext
|
2017-12-07 23:44:09 +03:00
|
|
|
else:
|
2021-04-08 01:18:49 +03:00
|
|
|
ret = f'deposit{bitop_width}({ret}, {pos}, {bitop_width - pos}, {ext})'
|
2017-12-07 23:44:09 +03:00
|
|
|
pos += f.len
|
|
|
|
return ret
|
|
|
|
|
|
|
|
def __ne__(self, other):
|
|
|
|
if len(self.subs) != len(other.subs):
|
|
|
|
return True
|
|
|
|
for a, b in zip(self.subs, other.subs):
|
|
|
|
if a.__class__ != b.__class__ or a != b:
|
|
|
|
return True
|
|
|
|
return False
|
|
|
|
|
|
|
|
def __eq__(self, other):
|
|
|
|
return not self.__ne__(other)
|
|
|
|
# end MultiField
|
|
|
|
|
|
|
|
|
|
|
|
class ConstField:
|
|
|
|
"""Class representing an argument field with constant value"""
|
|
|
|
def __init__(self, value):
|
|
|
|
self.value = value
|
|
|
|
self.mask = 0
|
|
|
|
self.sign = value < 0
|
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
return str(self.value)
|
|
|
|
|
|
|
|
def str_extract(self):
|
|
|
|
return str(self.value)
|
|
|
|
|
|
|
|
def __cmp__(self, other):
|
|
|
|
return self.value - other.value
|
|
|
|
# end ConstField
|
|
|
|
|
|
|
|
|
|
|
|
class FunctionField:
|
2019-07-23 03:02:56 +03:00
|
|
|
"""Class representing a field passed through a function"""
|
2017-12-07 23:44:09 +03:00
|
|
|
def __init__(self, func, base):
|
|
|
|
self.mask = base.mask
|
|
|
|
self.sign = base.sign
|
|
|
|
self.base = base
|
|
|
|
self.func = func
|
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
return self.func + '(' + str(self.base) + ')'
|
|
|
|
|
|
|
|
def str_extract(self):
|
2019-03-21 05:21:31 +03:00
|
|
|
return self.func + '(ctx, ' + self.base.str_extract() + ')'
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
def __eq__(self, other):
|
|
|
|
return self.func == other.func and self.base == other.base
|
|
|
|
|
|
|
|
def __ne__(self, other):
|
|
|
|
return not self.__eq__(other)
|
|
|
|
# end FunctionField
|
|
|
|
|
|
|
|
|
2019-07-23 03:02:56 +03:00
|
|
|
class ParameterField:
|
|
|
|
"""Class representing a pseudo-field read from a function"""
|
|
|
|
def __init__(self, func):
|
|
|
|
self.mask = 0
|
|
|
|
self.sign = 0
|
|
|
|
self.func = func
|
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
return self.func
|
|
|
|
|
|
|
|
def str_extract(self):
|
|
|
|
return self.func + '(ctx)'
|
|
|
|
|
|
|
|
def __eq__(self, other):
|
|
|
|
return self.func == other.func
|
|
|
|
|
|
|
|
def __ne__(self, other):
|
|
|
|
return not self.__eq__(other)
|
|
|
|
# end ParameterField
|
|
|
|
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
class Arguments:
|
|
|
|
"""Class representing the extracted fields of a format"""
|
2021-04-29 20:03:59 +03:00
|
|
|
def __init__(self, nm, flds, types, extern):
|
2017-12-07 23:44:09 +03:00
|
|
|
self.name = nm
|
2018-10-23 12:26:25 +03:00
|
|
|
self.extern = extern
|
2021-04-29 20:03:59 +03:00
|
|
|
self.fields = flds
|
|
|
|
self.types = types
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
return self.name + ' ' + str(self.fields)
|
|
|
|
|
|
|
|
def struct_name(self):
|
|
|
|
return 'arg_' + self.name
|
|
|
|
|
|
|
|
def output_def(self):
|
2018-10-23 12:26:25 +03:00
|
|
|
if not self.extern:
|
|
|
|
output('typedef struct {\n')
|
2021-04-29 20:03:59 +03:00
|
|
|
for (n, t) in zip(self.fields, self.types):
|
|
|
|
output(f' {t} {n};\n')
|
2018-10-23 12:26:25 +03:00
|
|
|
output('} ', self.struct_name(), ';\n\n')
|
2017-12-07 23:44:09 +03:00
|
|
|
# end Arguments
|
|
|
|
|
|
|
|
|
|
|
|
class General:
|
|
|
|
"""Common code between instruction formats and instruction patterns"""
|
2019-01-31 05:01:29 +03:00
|
|
|
def __init__(self, name, lineno, base, fixb, fixm, udfm, fldm, flds, w):
|
2017-12-07 23:44:09 +03:00
|
|
|
self.name = name
|
2018-10-26 16:59:43 +03:00
|
|
|
self.file = input_file
|
2017-12-07 23:44:09 +03:00
|
|
|
self.lineno = lineno
|
|
|
|
self.base = base
|
|
|
|
self.fixedbits = fixb
|
|
|
|
self.fixedmask = fixm
|
|
|
|
self.undefmask = udfm
|
|
|
|
self.fieldmask = fldm
|
|
|
|
self.fields = flds
|
2019-01-31 05:01:29 +03:00
|
|
|
self.width = w
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
def __str__(self):
|
2019-02-23 22:35:36 +03:00
|
|
|
return self.name + ' ' + str_match_bits(self.fixedbits, self.fixedmask)
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
def str1(self, i):
|
|
|
|
return str_indent(i) + self.__str__()
|
|
|
|
# end General
|
|
|
|
|
|
|
|
|
|
|
|
class Format(General):
|
|
|
|
"""Class representing an instruction format"""
|
|
|
|
|
|
|
|
def extract_name(self):
|
2019-03-01 01:45:50 +03:00
|
|
|
global decode_function
|
|
|
|
return decode_function + '_extract_' + self.name
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
def output_extract(self):
|
2019-03-21 05:21:31 +03:00
|
|
|
output('static void ', self.extract_name(), '(DisasContext *ctx, ',
|
2017-12-07 23:44:09 +03:00
|
|
|
self.base.struct_name(), ' *a, ', insntype, ' insn)\n{\n')
|
|
|
|
for n, f in self.fields.items():
|
|
|
|
output(' a->', n, ' = ', f.str_extract(), ';\n')
|
|
|
|
output('}\n\n')
|
|
|
|
# end Format
|
|
|
|
|
|
|
|
|
|
|
|
class Pattern(General):
|
|
|
|
"""Class representing an instruction pattern"""
|
|
|
|
|
|
|
|
def output_decl(self):
|
|
|
|
global translate_scope
|
|
|
|
global translate_prefix
|
|
|
|
output('typedef ', self.base.base.struct_name(),
|
|
|
|
' arg_', self.name, ';\n')
|
2018-03-02 13:45:35 +03:00
|
|
|
output(translate_scope, 'bool ', translate_prefix, '_', self.name,
|
2018-10-23 13:05:27 +03:00
|
|
|
'(DisasContext *ctx, arg_', self.name, ' *a);\n')
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
def output_code(self, i, extracted, outerbits, outermask):
|
|
|
|
global translate_prefix
|
|
|
|
ind = str_indent(i)
|
|
|
|
arg = self.base.base.name
|
2018-10-26 16:59:43 +03:00
|
|
|
output(ind, '/* ', self.file, ':', str(self.lineno), ' */\n')
|
2017-12-07 23:44:09 +03:00
|
|
|
if not extracted:
|
2019-03-21 05:21:31 +03:00
|
|
|
output(ind, self.base.extract_name(),
|
|
|
|
'(ctx, &u.f_', arg, ', insn);\n')
|
2017-12-07 23:44:09 +03:00
|
|
|
for n, f in self.fields.items():
|
|
|
|
output(ind, 'u.f_', arg, '.', n, ' = ', f.str_extract(), ';\n')
|
2019-02-23 19:57:46 +03:00
|
|
|
output(ind, 'if (', translate_prefix, '_', self.name,
|
|
|
|
'(ctx, &u.f_', arg, ')) return true;\n')
|
2020-05-17 20:14:11 +03:00
|
|
|
|
|
|
|
# Normal patterns do not have children.
|
|
|
|
def build_tree(self):
|
|
|
|
return
|
|
|
|
def prop_masks(self):
|
|
|
|
return
|
|
|
|
def prop_format(self):
|
|
|
|
return
|
|
|
|
def prop_width(self):
|
|
|
|
return
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
# end Pattern
|
|
|
|
|
|
|
|
|
2020-05-16 21:19:45 +03:00
|
|
|
class MultiPattern(General):
|
|
|
|
"""Class representing a set of instruction patterns"""
|
2019-02-23 22:35:36 +03:00
|
|
|
|
2020-05-17 20:14:11 +03:00
|
|
|
def __init__(self, lineno):
|
2019-02-23 22:35:36 +03:00
|
|
|
self.file = input_file
|
|
|
|
self.lineno = lineno
|
2020-05-17 20:14:11 +03:00
|
|
|
self.pats = []
|
2019-02-23 22:35:36 +03:00
|
|
|
self.base = None
|
2020-05-16 21:19:45 +03:00
|
|
|
self.fixedbits = 0
|
|
|
|
self.fixedmask = 0
|
|
|
|
self.undefmask = 0
|
|
|
|
self.width = None
|
2019-02-23 22:35:36 +03:00
|
|
|
|
|
|
|
def __str__(self):
|
2020-05-16 21:19:45 +03:00
|
|
|
r = 'group'
|
|
|
|
if self.fixedbits is not None:
|
|
|
|
r += ' ' + str_match_bits(self.fixedbits, self.fixedmask)
|
|
|
|
return r
|
2019-02-23 22:35:36 +03:00
|
|
|
|
|
|
|
def output_decl(self):
|
|
|
|
for p in self.pats:
|
|
|
|
p.output_decl()
|
2020-05-17 20:14:11 +03:00
|
|
|
|
|
|
|
def prop_masks(self):
|
|
|
|
global insnmask
|
|
|
|
|
|
|
|
fixedmask = insnmask
|
|
|
|
undefmask = insnmask
|
|
|
|
|
|
|
|
# Collect fixedmask/undefmask for all of the children.
|
|
|
|
for p in self.pats:
|
|
|
|
p.prop_masks()
|
|
|
|
fixedmask &= p.fixedmask
|
|
|
|
undefmask &= p.undefmask
|
|
|
|
|
|
|
|
# Widen fixedmask until all fixedbits match
|
|
|
|
repeat = True
|
|
|
|
fixedbits = 0
|
|
|
|
while repeat and fixedmask != 0:
|
|
|
|
fixedbits = None
|
|
|
|
for p in self.pats:
|
|
|
|
thisbits = p.fixedbits & fixedmask
|
|
|
|
if fixedbits is None:
|
|
|
|
fixedbits = thisbits
|
|
|
|
elif fixedbits != thisbits:
|
|
|
|
fixedmask &= ~(fixedbits ^ thisbits)
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
repeat = False
|
|
|
|
|
|
|
|
self.fixedbits = fixedbits
|
|
|
|
self.fixedmask = fixedmask
|
|
|
|
self.undefmask = undefmask
|
|
|
|
|
|
|
|
def build_tree(self):
|
|
|
|
for p in self.pats:
|
|
|
|
p.build_tree()
|
|
|
|
|
|
|
|
def prop_format(self):
|
|
|
|
for p in self.pats:
|
|
|
|
p.build_tree()
|
|
|
|
|
|
|
|
def prop_width(self):
|
|
|
|
width = None
|
|
|
|
for p in self.pats:
|
|
|
|
p.prop_width()
|
|
|
|
if width is None:
|
|
|
|
width = p.width
|
|
|
|
elif width != p.width:
|
|
|
|
error_with_file(self.file, self.lineno,
|
|
|
|
'width mismatch in patterns within braces')
|
|
|
|
self.width = width
|
|
|
|
|
2020-05-16 21:19:45 +03:00
|
|
|
# end MultiPattern
|
|
|
|
|
|
|
|
|
|
|
|
class IncMultiPattern(MultiPattern):
|
|
|
|
"""Class representing an overlapping set of instruction patterns"""
|
|
|
|
|
2019-02-23 22:35:36 +03:00
|
|
|
def output_code(self, i, extracted, outerbits, outermask):
|
|
|
|
global translate_prefix
|
|
|
|
ind = str_indent(i)
|
|
|
|
for p in self.pats:
|
|
|
|
if outermask != p.fixedmask:
|
|
|
|
innermask = p.fixedmask & ~outermask
|
|
|
|
innerbits = p.fixedbits & ~outermask
|
2021-04-29 02:27:56 +03:00
|
|
|
output(ind, f'if ((insn & {whexC(innermask)}) == {whexC(innerbits)}) {{\n')
|
|
|
|
output(ind, f' /* {str_match_bits(p.fixedbits, p.fixedmask)} */\n')
|
2019-02-23 22:35:36 +03:00
|
|
|
p.output_code(i + 4, extracted, p.fixedbits, p.fixedmask)
|
|
|
|
output(ind, '}\n')
|
|
|
|
else:
|
|
|
|
p.output_code(i, extracted, p.fixedbits, p.fixedmask)
|
2020-05-16 20:50:43 +03:00
|
|
|
#end IncMultiPattern
|
2019-02-23 22:35:36 +03:00
|
|
|
|
|
|
|
|
2020-05-17 20:14:11 +03:00
|
|
|
class Tree:
|
|
|
|
"""Class representing a node in a decode tree"""
|
|
|
|
|
|
|
|
def __init__(self, fm, tm):
|
|
|
|
self.fixedmask = fm
|
|
|
|
self.thismask = tm
|
|
|
|
self.subs = []
|
|
|
|
self.base = None
|
|
|
|
|
|
|
|
def str1(self, i):
|
|
|
|
ind = str_indent(i)
|
2021-04-29 02:27:56 +03:00
|
|
|
r = ind + whex(self.fixedmask)
|
2020-05-17 20:14:11 +03:00
|
|
|
if self.format:
|
|
|
|
r += ' ' + self.format.name
|
|
|
|
r += ' [\n'
|
|
|
|
for (b, s) in self.subs:
|
2021-04-29 02:27:56 +03:00
|
|
|
r += ind + f' {whex(b)}:\n'
|
2020-05-17 20:14:11 +03:00
|
|
|
r += s.str1(i + 4) + '\n'
|
|
|
|
r += ind + ']'
|
|
|
|
return r
|
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
return self.str1(0)
|
|
|
|
|
|
|
|
def output_code(self, i, extracted, outerbits, outermask):
|
|
|
|
ind = str_indent(i)
|
|
|
|
|
|
|
|
# If we identified all nodes below have the same format,
|
|
|
|
# extract the fields now.
|
|
|
|
if not extracted and self.base:
|
|
|
|
output(ind, self.base.extract_name(),
|
|
|
|
'(ctx, &u.f_', self.base.base.name, ', insn);\n')
|
|
|
|
extracted = True
|
|
|
|
|
|
|
|
# Attempt to aid the compiler in producing compact switch statements.
|
|
|
|
# If the bits in the mask are contiguous, extract them.
|
|
|
|
sh = is_contiguous(self.thismask)
|
|
|
|
if sh > 0:
|
|
|
|
# Propagate SH down into the local functions.
|
|
|
|
def str_switch(b, sh=sh):
|
2021-04-29 02:27:56 +03:00
|
|
|
return f'(insn >> {sh}) & {b >> sh:#x}'
|
2020-05-17 20:14:11 +03:00
|
|
|
|
|
|
|
def str_case(b, sh=sh):
|
2021-04-29 02:27:56 +03:00
|
|
|
return hex(b >> sh)
|
2020-05-17 20:14:11 +03:00
|
|
|
else:
|
|
|
|
def str_switch(b):
|
2021-04-29 02:27:56 +03:00
|
|
|
return f'insn & {whexC(b)}'
|
2020-05-17 20:14:11 +03:00
|
|
|
|
|
|
|
def str_case(b):
|
2021-04-29 02:27:56 +03:00
|
|
|
return whexC(b)
|
2020-05-17 20:14:11 +03:00
|
|
|
|
|
|
|
output(ind, 'switch (', str_switch(self.thismask), ') {\n')
|
|
|
|
for b, s in sorted(self.subs):
|
|
|
|
assert (self.thismask & ~s.fixedmask) == 0
|
|
|
|
innermask = outermask | self.thismask
|
|
|
|
innerbits = outerbits | b
|
|
|
|
output(ind, 'case ', str_case(b), ':\n')
|
|
|
|
output(ind, ' /* ',
|
|
|
|
str_match_bits(innerbits, innermask), ' */\n')
|
|
|
|
s.output_code(i + 4, extracted, innerbits, innermask)
|
2020-10-19 18:12:52 +03:00
|
|
|
output(ind, ' break;\n')
|
2020-05-17 20:14:11 +03:00
|
|
|
output(ind, '}\n')
|
|
|
|
# end Tree
|
|
|
|
|
|
|
|
|
|
|
|
class ExcMultiPattern(MultiPattern):
|
|
|
|
"""Class representing a non-overlapping set of instruction patterns"""
|
|
|
|
|
|
|
|
def output_code(self, i, extracted, outerbits, outermask):
|
|
|
|
# Defer everything to our decomposed Tree node
|
|
|
|
self.tree.output_code(i, extracted, outerbits, outermask)
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
def __build_tree(pats, outerbits, outermask):
|
|
|
|
# Find the intersection of all remaining fixedmask.
|
|
|
|
innermask = ~outermask & insnmask
|
|
|
|
for i in pats:
|
|
|
|
innermask &= i.fixedmask
|
|
|
|
|
|
|
|
if innermask == 0:
|
|
|
|
# Edge condition: One pattern covers the entire insnmask
|
|
|
|
if len(pats) == 1:
|
|
|
|
t = Tree(outermask, innermask)
|
|
|
|
t.subs.append((0, pats[0]))
|
|
|
|
return t
|
|
|
|
|
|
|
|
text = 'overlapping patterns:'
|
|
|
|
for p in pats:
|
|
|
|
text += '\n' + p.file + ':' + str(p.lineno) + ': ' + str(p)
|
|
|
|
error_with_file(pats[0].file, pats[0].lineno, text)
|
|
|
|
|
|
|
|
fullmask = outermask | innermask
|
|
|
|
|
|
|
|
# Sort each element of pats into the bin selected by the mask.
|
|
|
|
bins = {}
|
|
|
|
for i in pats:
|
|
|
|
fb = i.fixedbits & innermask
|
|
|
|
if fb in bins:
|
|
|
|
bins[fb].append(i)
|
|
|
|
else:
|
|
|
|
bins[fb] = [i]
|
|
|
|
|
|
|
|
# We must recurse if any bin has more than one element or if
|
|
|
|
# the single element in the bin has not been fully matched.
|
|
|
|
t = Tree(fullmask, innermask)
|
|
|
|
|
|
|
|
for b, l in bins.items():
|
|
|
|
s = l[0]
|
|
|
|
if len(l) > 1 or s.fixedmask & ~fullmask != 0:
|
|
|
|
s = ExcMultiPattern.__build_tree(l, b | outerbits, fullmask)
|
|
|
|
t.subs.append((b, s))
|
|
|
|
|
|
|
|
return t
|
|
|
|
|
|
|
|
def build_tree(self):
|
|
|
|
super().prop_format()
|
|
|
|
self.tree = self.__build_tree(self.pats, self.fixedbits,
|
|
|
|
self.fixedmask)
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
def __prop_format(tree):
|
|
|
|
"""Propagate Format objects into the decode tree"""
|
|
|
|
|
|
|
|
# Depth first search.
|
|
|
|
for (b, s) in tree.subs:
|
|
|
|
if isinstance(s, Tree):
|
|
|
|
ExcMultiPattern.__prop_format(s)
|
|
|
|
|
|
|
|
# If all entries in SUBS have the same format, then
|
|
|
|
# propagate that into the tree.
|
|
|
|
f = None
|
|
|
|
for (b, s) in tree.subs:
|
|
|
|
if f is None:
|
|
|
|
f = s.base
|
|
|
|
if f is None:
|
|
|
|
return
|
|
|
|
if f is not s.base:
|
|
|
|
return
|
|
|
|
tree.base = f
|
|
|
|
|
|
|
|
def prop_format(self):
|
|
|
|
super().prop_format()
|
|
|
|
self.__prop_format(self.tree)
|
|
|
|
|
|
|
|
# end ExcMultiPattern
|
|
|
|
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
def parse_field(lineno, name, toks):
|
|
|
|
"""Parse one instruction field from TOKS at LINENO"""
|
|
|
|
global fields
|
|
|
|
global insnwidth
|
|
|
|
|
|
|
|
# A "simple" field will have only one entry;
|
|
|
|
# a "multifield" will have several.
|
|
|
|
subs = []
|
|
|
|
width = 0
|
|
|
|
func = None
|
|
|
|
for t in toks:
|
2020-09-03 22:23:34 +03:00
|
|
|
if re.match('^!function=', t):
|
2017-12-07 23:44:09 +03:00
|
|
|
if func:
|
|
|
|
error(lineno, 'duplicate function')
|
|
|
|
func = t.split('=')
|
|
|
|
func = func[1]
|
|
|
|
continue
|
|
|
|
|
2020-05-14 06:52:30 +03:00
|
|
|
if re.fullmatch('[0-9]+:s[0-9]+', t):
|
2017-12-07 23:44:09 +03:00
|
|
|
# Signed field extract
|
|
|
|
subtoks = t.split(':s')
|
|
|
|
sign = True
|
2020-05-14 06:52:30 +03:00
|
|
|
elif re.fullmatch('[0-9]+:[0-9]+', t):
|
2017-12-07 23:44:09 +03:00
|
|
|
# Unsigned field extract
|
|
|
|
subtoks = t.split(':')
|
|
|
|
sign = False
|
|
|
|
else:
|
2021-04-29 02:37:02 +03:00
|
|
|
error(lineno, f'invalid field token "{t}"')
|
2017-12-07 23:44:09 +03:00
|
|
|
po = int(subtoks[0])
|
|
|
|
le = int(subtoks[1])
|
|
|
|
if po + le > insnwidth:
|
2021-04-29 02:37:02 +03:00
|
|
|
error(lineno, f'field {t} too large')
|
2017-12-07 23:44:09 +03:00
|
|
|
f = Field(sign, po, le)
|
|
|
|
subs.append(f)
|
|
|
|
width += le
|
|
|
|
|
|
|
|
if width > insnwidth:
|
|
|
|
error(lineno, 'field too large')
|
2019-07-23 03:02:56 +03:00
|
|
|
if len(subs) == 0:
|
|
|
|
if func:
|
|
|
|
f = ParameterField(func)
|
|
|
|
else:
|
|
|
|
error(lineno, 'field with no value')
|
2017-12-07 23:44:09 +03:00
|
|
|
else:
|
2019-07-23 03:02:56 +03:00
|
|
|
if len(subs) == 1:
|
|
|
|
f = subs[0]
|
|
|
|
else:
|
|
|
|
mask = 0
|
|
|
|
for s in subs:
|
|
|
|
if mask & s.mask:
|
|
|
|
error(lineno, 'field components overlap')
|
|
|
|
mask |= s.mask
|
|
|
|
f = MultiField(subs, mask)
|
|
|
|
if func:
|
|
|
|
f = FunctionField(func, f)
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
if name in fields:
|
|
|
|
error(lineno, 'duplicate field', name)
|
|
|
|
fields[name] = f
|
|
|
|
# end parse_field
|
|
|
|
|
|
|
|
|
|
|
|
def parse_arguments(lineno, name, toks):
|
|
|
|
"""Parse one argument set from TOKS at LINENO"""
|
|
|
|
global arguments
|
2020-09-03 22:23:34 +03:00
|
|
|
global re_C_ident
|
2019-08-09 18:12:50 +03:00
|
|
|
global anyextern
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
flds = []
|
2021-04-29 20:03:59 +03:00
|
|
|
types = []
|
2018-10-23 12:26:25 +03:00
|
|
|
extern = False
|
2021-04-29 20:03:59 +03:00
|
|
|
for n in toks:
|
|
|
|
if re.fullmatch('!extern', n):
|
2018-10-23 12:26:25 +03:00
|
|
|
extern = True
|
2019-08-09 18:12:50 +03:00
|
|
|
anyextern = True
|
2018-10-23 12:26:25 +03:00
|
|
|
continue
|
2021-04-29 20:03:59 +03:00
|
|
|
if re.fullmatch(re_C_ident + ':' + re_C_ident, n):
|
|
|
|
(n, t) = n.split(':')
|
|
|
|
elif re.fullmatch(re_C_ident, n):
|
|
|
|
t = 'int'
|
|
|
|
else:
|
|
|
|
error(lineno, f'invalid argument set token "{n}"')
|
|
|
|
if n in flds:
|
|
|
|
error(lineno, f'duplicate argument "{n}"')
|
|
|
|
flds.append(n)
|
|
|
|
types.append(t)
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
if name in arguments:
|
|
|
|
error(lineno, 'duplicate argument set', name)
|
2021-04-29 20:03:59 +03:00
|
|
|
arguments[name] = Arguments(name, flds, types, extern)
|
2017-12-07 23:44:09 +03:00
|
|
|
# end parse_arguments
|
|
|
|
|
|
|
|
|
|
|
|
def lookup_field(lineno, name):
|
|
|
|
global fields
|
|
|
|
if name in fields:
|
|
|
|
return fields[name]
|
|
|
|
error(lineno, 'undefined field', name)
|
|
|
|
|
|
|
|
|
|
|
|
def add_field(lineno, flds, new_name, f):
|
|
|
|
if new_name in flds:
|
|
|
|
error(lineno, 'duplicate field', new_name)
|
|
|
|
flds[new_name] = f
|
|
|
|
return flds
|
|
|
|
|
|
|
|
|
|
|
|
def add_field_byname(lineno, flds, new_name, old_name):
|
|
|
|
return add_field(lineno, flds, new_name, lookup_field(lineno, old_name))
|
|
|
|
|
|
|
|
|
|
|
|
def infer_argument_set(flds):
|
|
|
|
global arguments
|
2018-10-23 12:26:25 +03:00
|
|
|
global decode_function
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
for arg in arguments.values():
|
2021-04-29 20:03:59 +03:00
|
|
|
if eq_fields_for_args(flds, arg):
|
2017-12-07 23:44:09 +03:00
|
|
|
return arg
|
|
|
|
|
2018-10-23 12:26:25 +03:00
|
|
|
name = decode_function + str(len(arguments))
|
2021-04-29 20:03:59 +03:00
|
|
|
arg = Arguments(name, flds.keys(), ['int'] * len(flds), False)
|
2017-12-07 23:44:09 +03:00
|
|
|
arguments[name] = arg
|
|
|
|
return arg
|
|
|
|
|
|
|
|
|
2019-01-31 05:01:29 +03:00
|
|
|
def infer_format(arg, fieldmask, flds, width):
|
2017-12-07 23:44:09 +03:00
|
|
|
global arguments
|
|
|
|
global formats
|
2018-10-23 12:26:25 +03:00
|
|
|
global decode_function
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
const_flds = {}
|
|
|
|
var_flds = {}
|
|
|
|
for n, c in flds.items():
|
|
|
|
if c is ConstField:
|
|
|
|
const_flds[n] = c
|
|
|
|
else:
|
|
|
|
var_flds[n] = c
|
|
|
|
|
|
|
|
# Look for an existing format with the same argument set and fields
|
|
|
|
for fmt in formats.values():
|
|
|
|
if arg and fmt.base != arg:
|
|
|
|
continue
|
|
|
|
if fieldmask != fmt.fieldmask:
|
|
|
|
continue
|
2019-01-31 05:01:29 +03:00
|
|
|
if width != fmt.width:
|
|
|
|
continue
|
2017-12-07 23:44:09 +03:00
|
|
|
if not eq_fields_for_fmts(flds, fmt.fields):
|
|
|
|
continue
|
|
|
|
return (fmt, const_flds)
|
|
|
|
|
2018-10-23 12:26:25 +03:00
|
|
|
name = decode_function + '_Fmt_' + str(len(formats))
|
2017-12-07 23:44:09 +03:00
|
|
|
if not arg:
|
|
|
|
arg = infer_argument_set(flds)
|
|
|
|
|
2019-01-31 05:01:29 +03:00
|
|
|
fmt = Format(name, 0, arg, 0, 0, 0, fieldmask, var_flds, width)
|
2017-12-07 23:44:09 +03:00
|
|
|
formats[name] = fmt
|
|
|
|
|
|
|
|
return (fmt, const_flds)
|
|
|
|
# end infer_format
|
|
|
|
|
|
|
|
|
2020-05-17 20:14:11 +03:00
|
|
|
def parse_generic(lineno, parent_pat, name, toks):
|
2017-12-07 23:44:09 +03:00
|
|
|
"""Parse one instruction format from TOKS at LINENO"""
|
|
|
|
global fields
|
|
|
|
global arguments
|
|
|
|
global formats
|
2019-02-23 22:35:36 +03:00
|
|
|
global allpatterns
|
2020-09-03 22:23:34 +03:00
|
|
|
global re_arg_ident
|
|
|
|
global re_fld_ident
|
|
|
|
global re_fmt_ident
|
|
|
|
global re_C_ident
|
2017-12-07 23:44:09 +03:00
|
|
|
global insnwidth
|
|
|
|
global insnmask
|
2019-01-31 05:01:29 +03:00
|
|
|
global variablewidth
|
2017-12-07 23:44:09 +03:00
|
|
|
|
2020-05-17 20:14:11 +03:00
|
|
|
is_format = parent_pat is None
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
fixedmask = 0
|
|
|
|
fixedbits = 0
|
|
|
|
undefmask = 0
|
|
|
|
width = 0
|
|
|
|
flds = {}
|
|
|
|
arg = None
|
|
|
|
fmt = None
|
|
|
|
for t in toks:
|
2020-09-17 10:50:23 +03:00
|
|
|
# '&Foo' gives a format an explicit argument set.
|
2020-09-03 22:23:34 +03:00
|
|
|
if re.fullmatch(re_arg_ident, t):
|
2017-12-07 23:44:09 +03:00
|
|
|
tt = t[1:]
|
|
|
|
if arg:
|
|
|
|
error(lineno, 'multiple argument sets')
|
|
|
|
if tt in arguments:
|
|
|
|
arg = arguments[tt]
|
|
|
|
else:
|
|
|
|
error(lineno, 'undefined argument set', t)
|
|
|
|
continue
|
|
|
|
|
|
|
|
# '@Foo' gives a pattern an explicit format.
|
2020-09-03 22:23:34 +03:00
|
|
|
if re.fullmatch(re_fmt_ident, t):
|
2017-12-07 23:44:09 +03:00
|
|
|
tt = t[1:]
|
|
|
|
if fmt:
|
|
|
|
error(lineno, 'multiple formats')
|
|
|
|
if tt in formats:
|
|
|
|
fmt = formats[tt]
|
|
|
|
else:
|
|
|
|
error(lineno, 'undefined format', t)
|
|
|
|
continue
|
|
|
|
|
|
|
|
# '%Foo' imports a field.
|
2020-09-03 22:23:34 +03:00
|
|
|
if re.fullmatch(re_fld_ident, t):
|
2017-12-07 23:44:09 +03:00
|
|
|
tt = t[1:]
|
|
|
|
flds = add_field_byname(lineno, flds, tt, tt)
|
|
|
|
continue
|
|
|
|
|
|
|
|
# 'Foo=%Bar' imports a field with a different name.
|
2020-09-03 22:23:34 +03:00
|
|
|
if re.fullmatch(re_C_ident + '=' + re_fld_ident, t):
|
2017-12-07 23:44:09 +03:00
|
|
|
(fname, iname) = t.split('=%')
|
|
|
|
flds = add_field_byname(lineno, flds, fname, iname)
|
|
|
|
continue
|
|
|
|
|
|
|
|
# 'Foo=number' sets an argument field to a constant value
|
2020-09-03 22:23:34 +03:00
|
|
|
if re.fullmatch(re_C_ident + '=[+-]?[0-9]+', t):
|
2017-12-07 23:44:09 +03:00
|
|
|
(fname, value) = t.split('=')
|
|
|
|
value = int(value)
|
|
|
|
flds = add_field(lineno, flds, fname, ConstField(value))
|
|
|
|
continue
|
|
|
|
|
|
|
|
# Pattern of 0s, 1s, dots and dashes indicate required zeros,
|
|
|
|
# required ones, or dont-cares.
|
2020-05-14 06:52:30 +03:00
|
|
|
if re.fullmatch('[01.-]+', t):
|
2017-12-07 23:44:09 +03:00
|
|
|
shift = len(t)
|
|
|
|
fms = t.replace('0', '1')
|
|
|
|
fms = fms.replace('.', '0')
|
|
|
|
fms = fms.replace('-', '0')
|
|
|
|
fbs = t.replace('.', '0')
|
|
|
|
fbs = fbs.replace('-', '0')
|
|
|
|
ubm = t.replace('1', '0')
|
|
|
|
ubm = ubm.replace('.', '0')
|
|
|
|
ubm = ubm.replace('-', '1')
|
|
|
|
fms = int(fms, 2)
|
|
|
|
fbs = int(fbs, 2)
|
|
|
|
ubm = int(ubm, 2)
|
|
|
|
fixedbits = (fixedbits << shift) | fbs
|
|
|
|
fixedmask = (fixedmask << shift) | fms
|
|
|
|
undefmask = (undefmask << shift) | ubm
|
|
|
|
# Otherwise, fieldname:fieldwidth
|
2020-09-03 22:23:34 +03:00
|
|
|
elif re.fullmatch(re_C_ident + ':s?[0-9]+', t):
|
2017-12-07 23:44:09 +03:00
|
|
|
(fname, flen) = t.split(':')
|
|
|
|
sign = False
|
|
|
|
if flen[0] == 's':
|
|
|
|
sign = True
|
|
|
|
flen = flen[1:]
|
|
|
|
shift = int(flen, 10)
|
2019-03-06 02:34:41 +03:00
|
|
|
if shift + width > insnwidth:
|
2021-04-29 02:37:02 +03:00
|
|
|
error(lineno, f'field {fname} exceeds insnwidth')
|
2017-12-07 23:44:09 +03:00
|
|
|
f = Field(sign, insnwidth - width - shift, shift)
|
|
|
|
flds = add_field(lineno, flds, fname, f)
|
|
|
|
fixedbits <<= shift
|
|
|
|
fixedmask <<= shift
|
|
|
|
undefmask <<= shift
|
|
|
|
else:
|
2021-04-29 02:37:02 +03:00
|
|
|
error(lineno, f'invalid token "{t}"')
|
2017-12-07 23:44:09 +03:00
|
|
|
width += shift
|
|
|
|
|
2019-01-31 05:01:29 +03:00
|
|
|
if variablewidth and width < insnwidth and width % 8 == 0:
|
|
|
|
shift = insnwidth - width
|
|
|
|
fixedbits <<= shift
|
|
|
|
fixedmask <<= shift
|
|
|
|
undefmask <<= shift
|
|
|
|
undefmask |= (1 << shift) - 1
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
# We should have filled in all of the bits of the instruction.
|
2019-01-31 05:01:29 +03:00
|
|
|
elif not (is_format and width == 0) and width != insnwidth:
|
2021-04-29 02:37:02 +03:00
|
|
|
error(lineno, f'definition has {width} bits')
|
2017-12-07 23:44:09 +03:00
|
|
|
|
2020-09-17 10:50:23 +03:00
|
|
|
# Do not check for fields overlapping fields; one valid usage
|
2017-12-07 23:44:09 +03:00
|
|
|
# is to be able to duplicate fields via import.
|
|
|
|
fieldmask = 0
|
|
|
|
for f in flds.values():
|
|
|
|
fieldmask |= f.mask
|
|
|
|
|
|
|
|
# Fix up what we've parsed to match either a format or a pattern.
|
|
|
|
if is_format:
|
|
|
|
# Formats cannot reference formats.
|
|
|
|
if fmt:
|
|
|
|
error(lineno, 'format referencing format')
|
|
|
|
# If an argument set is given, then there should be no fields
|
|
|
|
# without a place to store it.
|
|
|
|
if arg:
|
|
|
|
for f in flds.keys():
|
|
|
|
if f not in arg.fields:
|
2021-04-29 02:37:02 +03:00
|
|
|
error(lineno, f'field {f} not in argument set {arg.name}')
|
2017-12-07 23:44:09 +03:00
|
|
|
else:
|
|
|
|
arg = infer_argument_set(flds)
|
|
|
|
if name in formats:
|
|
|
|
error(lineno, 'duplicate format name', name)
|
|
|
|
fmt = Format(name, lineno, arg, fixedbits, fixedmask,
|
2019-01-31 05:01:29 +03:00
|
|
|
undefmask, fieldmask, flds, width)
|
2017-12-07 23:44:09 +03:00
|
|
|
formats[name] = fmt
|
|
|
|
else:
|
|
|
|
# Patterns can reference a format ...
|
|
|
|
if fmt:
|
|
|
|
# ... but not an argument simultaneously
|
|
|
|
if arg:
|
|
|
|
error(lineno, 'pattern specifies both format and argument set')
|
|
|
|
if fixedmask & fmt.fixedmask:
|
|
|
|
error(lineno, 'pattern fixed bits overlap format fixed bits')
|
2019-01-31 05:01:29 +03:00
|
|
|
if width != fmt.width:
|
|
|
|
error(lineno, 'pattern uses format of different width')
|
2017-12-07 23:44:09 +03:00
|
|
|
fieldmask |= fmt.fieldmask
|
|
|
|
fixedbits |= fmt.fixedbits
|
|
|
|
fixedmask |= fmt.fixedmask
|
|
|
|
undefmask |= fmt.undefmask
|
|
|
|
else:
|
2019-01-31 05:01:29 +03:00
|
|
|
(fmt, flds) = infer_format(arg, fieldmask, flds, width)
|
2017-12-07 23:44:09 +03:00
|
|
|
arg = fmt.base
|
|
|
|
for f in flds.keys():
|
|
|
|
if f not in arg.fields:
|
2021-04-29 02:37:02 +03:00
|
|
|
error(lineno, f'field {f} not in argument set {arg.name}')
|
2017-12-07 23:44:09 +03:00
|
|
|
if f in fmt.fields.keys():
|
2021-04-29 02:37:02 +03:00
|
|
|
error(lineno, f'field {f} set by format and pattern')
|
2017-12-07 23:44:09 +03:00
|
|
|
for f in arg.fields:
|
|
|
|
if f not in flds.keys() and f not in fmt.fields.keys():
|
2021-04-29 02:37:02 +03:00
|
|
|
error(lineno, f'field {f} not initialized')
|
2017-12-07 23:44:09 +03:00
|
|
|
pat = Pattern(name, lineno, fmt, fixedbits, fixedmask,
|
2019-01-31 05:01:29 +03:00
|
|
|
undefmask, fieldmask, flds, width)
|
2020-05-17 20:14:11 +03:00
|
|
|
parent_pat.pats.append(pat)
|
2019-02-23 22:35:36 +03:00
|
|
|
allpatterns.append(pat)
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
# Validate the masks that we have assembled.
|
|
|
|
if fieldmask & fixedmask:
|
2021-04-29 02:27:56 +03:00
|
|
|
error(lineno, 'fieldmask overlaps fixedmask ',
|
|
|
|
f'({whex(fieldmask)} & {whex(fixedmask)})')
|
2017-12-07 23:44:09 +03:00
|
|
|
if fieldmask & undefmask:
|
2021-04-29 02:27:56 +03:00
|
|
|
error(lineno, 'fieldmask overlaps undefmask ',
|
|
|
|
f'({whex(fieldmask)} & {whex(undefmask)})')
|
2017-12-07 23:44:09 +03:00
|
|
|
if fixedmask & undefmask:
|
2021-04-29 02:27:56 +03:00
|
|
|
error(lineno, 'fixedmask overlaps undefmask ',
|
|
|
|
f'({whex(fixedmask)} & {whex(undefmask)})')
|
2017-12-07 23:44:09 +03:00
|
|
|
if not is_format:
|
|
|
|
allbits = fieldmask | fixedmask | undefmask
|
|
|
|
if allbits != insnmask:
|
2021-04-29 02:27:56 +03:00
|
|
|
error(lineno, 'bits left unspecified ',
|
|
|
|
f'({whex(allbits ^ insnmask)})')
|
2017-12-07 23:44:09 +03:00
|
|
|
# end parse_general
|
|
|
|
|
2019-02-23 22:35:36 +03:00
|
|
|
|
2020-05-17 20:14:11 +03:00
|
|
|
def parse_file(f, parent_pat):
|
2017-12-07 23:44:09 +03:00
|
|
|
"""Parse all of the patterns within a file"""
|
2020-09-03 22:23:34 +03:00
|
|
|
global re_arg_ident
|
|
|
|
global re_fld_ident
|
|
|
|
global re_fmt_ident
|
|
|
|
global re_pat_ident
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
# Read all of the lines of the file. Concatenate lines
|
|
|
|
# ending in backslash; discard empty lines and comments.
|
|
|
|
toks = []
|
|
|
|
lineno = 0
|
2019-02-23 22:35:36 +03:00
|
|
|
nesting = 0
|
2020-05-17 20:14:11 +03:00
|
|
|
nesting_pats = []
|
2019-02-23 22:35:36 +03:00
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
for line in f:
|
|
|
|
lineno += 1
|
|
|
|
|
2019-02-23 22:35:36 +03:00
|
|
|
# Expand and strip spaces, to find indent.
|
|
|
|
line = line.rstrip()
|
|
|
|
line = line.expandtabs()
|
|
|
|
len1 = len(line)
|
|
|
|
line = line.lstrip()
|
|
|
|
len2 = len(line)
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
# Discard comments
|
|
|
|
end = line.find('#')
|
|
|
|
if end >= 0:
|
|
|
|
line = line[:end]
|
|
|
|
|
|
|
|
t = line.split()
|
|
|
|
if len(toks) != 0:
|
|
|
|
# Next line after continuation
|
|
|
|
toks.extend(t)
|
|
|
|
else:
|
2019-02-23 22:35:36 +03:00
|
|
|
# Allow completely blank lines.
|
|
|
|
if len1 == 0:
|
|
|
|
continue
|
|
|
|
indent = len1 - len2
|
|
|
|
# Empty line due to comment.
|
|
|
|
if len(t) == 0:
|
|
|
|
# Indentation must be correct, even for comment lines.
|
|
|
|
if indent != nesting:
|
|
|
|
error(lineno, 'indentation ', indent, ' != ', nesting)
|
|
|
|
continue
|
|
|
|
start_lineno = lineno
|
2017-12-07 23:44:09 +03:00
|
|
|
toks = t
|
|
|
|
|
|
|
|
# Continuation?
|
|
|
|
if toks[-1] == '\\':
|
|
|
|
toks.pop()
|
|
|
|
continue
|
|
|
|
|
|
|
|
name = toks[0]
|
|
|
|
del toks[0]
|
|
|
|
|
2019-02-23 22:35:36 +03:00
|
|
|
# End nesting?
|
2020-05-18 18:45:32 +03:00
|
|
|
if name == '}' or name == ']':
|
2019-02-23 22:35:36 +03:00
|
|
|
if len(toks) != 0:
|
|
|
|
error(start_lineno, 'extra tokens after close brace')
|
2020-05-17 20:14:11 +03:00
|
|
|
|
2020-05-18 18:45:32 +03:00
|
|
|
# Make sure { } and [ ] nest properly.
|
|
|
|
if (name == '}') != isinstance(parent_pat, IncMultiPattern):
|
|
|
|
error(lineno, 'mismatched close brace')
|
|
|
|
|
2020-05-17 20:14:11 +03:00
|
|
|
try:
|
|
|
|
parent_pat = nesting_pats.pop()
|
|
|
|
except:
|
2020-05-18 18:45:32 +03:00
|
|
|
error(lineno, 'extra close brace')
|
2020-05-17 20:14:11 +03:00
|
|
|
|
2019-02-23 22:35:36 +03:00
|
|
|
nesting -= 2
|
|
|
|
if indent != nesting:
|
2020-05-17 20:14:11 +03:00
|
|
|
error(lineno, 'indentation ', indent, ' != ', nesting)
|
|
|
|
|
2019-02-23 22:35:36 +03:00
|
|
|
toks = []
|
|
|
|
continue
|
|
|
|
|
|
|
|
# Everything else should have current indentation.
|
|
|
|
if indent != nesting:
|
|
|
|
error(start_lineno, 'indentation ', indent, ' != ', nesting)
|
|
|
|
|
|
|
|
# Start nesting?
|
2020-05-18 18:45:32 +03:00
|
|
|
if name == '{' or name == '[':
|
2019-02-23 22:35:36 +03:00
|
|
|
if len(toks) != 0:
|
|
|
|
error(start_lineno, 'extra tokens after open brace')
|
2020-05-17 20:14:11 +03:00
|
|
|
|
2020-05-18 18:45:32 +03:00
|
|
|
if name == '{':
|
|
|
|
nested_pat = IncMultiPattern(start_lineno)
|
|
|
|
else:
|
|
|
|
nested_pat = ExcMultiPattern(start_lineno)
|
2020-05-17 20:14:11 +03:00
|
|
|
parent_pat.pats.append(nested_pat)
|
|
|
|
nesting_pats.append(parent_pat)
|
|
|
|
parent_pat = nested_pat
|
|
|
|
|
2019-02-23 22:35:36 +03:00
|
|
|
nesting += 2
|
|
|
|
toks = []
|
|
|
|
continue
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
# Determine the type of object needing to be parsed.
|
2020-09-03 22:23:34 +03:00
|
|
|
if re.fullmatch(re_fld_ident, name):
|
2019-02-23 22:35:36 +03:00
|
|
|
parse_field(start_lineno, name[1:], toks)
|
2020-09-03 22:23:34 +03:00
|
|
|
elif re.fullmatch(re_arg_ident, name):
|
2019-02-23 22:35:36 +03:00
|
|
|
parse_arguments(start_lineno, name[1:], toks)
|
2020-09-03 22:23:34 +03:00
|
|
|
elif re.fullmatch(re_fmt_ident, name):
|
2020-05-17 20:14:11 +03:00
|
|
|
parse_generic(start_lineno, None, name[1:], toks)
|
2020-09-03 22:23:34 +03:00
|
|
|
elif re.fullmatch(re_pat_ident, name):
|
2020-05-17 20:14:11 +03:00
|
|
|
parse_generic(start_lineno, parent_pat, name, toks)
|
2020-09-03 22:23:34 +03:00
|
|
|
else:
|
2021-04-29 02:37:02 +03:00
|
|
|
error(lineno, f'invalid token "{name}"')
|
2017-12-07 23:44:09 +03:00
|
|
|
toks = []
|
2020-05-18 18:45:32 +03:00
|
|
|
|
|
|
|
if nesting != 0:
|
|
|
|
error(lineno, 'missing close brace')
|
2017-12-07 23:44:09 +03:00
|
|
|
# end parse_file
|
|
|
|
|
|
|
|
|
2019-01-31 22:34:11 +03:00
|
|
|
class SizeTree:
|
|
|
|
"""Class representing a node in a size decode tree"""
|
|
|
|
|
|
|
|
def __init__(self, m, w):
|
|
|
|
self.mask = m
|
|
|
|
self.subs = []
|
|
|
|
self.base = None
|
|
|
|
self.width = w
|
|
|
|
|
|
|
|
def str1(self, i):
|
|
|
|
ind = str_indent(i)
|
2021-04-29 02:27:56 +03:00
|
|
|
r = ind + whex(self.mask) + ' [\n'
|
2019-01-31 22:34:11 +03:00
|
|
|
for (b, s) in self.subs:
|
2021-04-29 02:27:56 +03:00
|
|
|
r += ind + f' {whex(b)}:\n'
|
2019-01-31 22:34:11 +03:00
|
|
|
r += s.str1(i + 4) + '\n'
|
|
|
|
r += ind + ']'
|
|
|
|
return r
|
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
return self.str1(0)
|
|
|
|
|
|
|
|
def output_code(self, i, extracted, outerbits, outermask):
|
|
|
|
ind = str_indent(i)
|
|
|
|
|
|
|
|
# If we need to load more bytes to test, do so now.
|
|
|
|
if extracted < self.width:
|
2021-04-29 02:37:02 +03:00
|
|
|
output(ind, f'insn = {decode_function}_load_bytes',
|
|
|
|
f'(ctx, insn, {extracted // 8}, {self.width // 8});\n')
|
2019-01-31 22:34:11 +03:00
|
|
|
extracted = self.width
|
|
|
|
|
|
|
|
# Attempt to aid the compiler in producing compact switch statements.
|
|
|
|
# If the bits in the mask are contiguous, extract them.
|
|
|
|
sh = is_contiguous(self.mask)
|
|
|
|
if sh > 0:
|
|
|
|
# Propagate SH down into the local functions.
|
|
|
|
def str_switch(b, sh=sh):
|
2021-04-29 02:27:56 +03:00
|
|
|
return f'(insn >> {sh}) & {b >> sh:#x}'
|
2019-01-31 22:34:11 +03:00
|
|
|
|
|
|
|
def str_case(b, sh=sh):
|
2021-04-29 02:27:56 +03:00
|
|
|
return hex(b >> sh)
|
2019-01-31 22:34:11 +03:00
|
|
|
else:
|
|
|
|
def str_switch(b):
|
2021-04-29 02:27:56 +03:00
|
|
|
return f'insn & {whexC(b)}'
|
2019-01-31 22:34:11 +03:00
|
|
|
|
|
|
|
def str_case(b):
|
2021-04-29 02:27:56 +03:00
|
|
|
return whexC(b)
|
2019-01-31 22:34:11 +03:00
|
|
|
|
|
|
|
output(ind, 'switch (', str_switch(self.mask), ') {\n')
|
|
|
|
for b, s in sorted(self.subs):
|
|
|
|
innermask = outermask | self.mask
|
|
|
|
innerbits = outerbits | b
|
|
|
|
output(ind, 'case ', str_case(b), ':\n')
|
|
|
|
output(ind, ' /* ',
|
|
|
|
str_match_bits(innerbits, innermask), ' */\n')
|
|
|
|
s.output_code(i + 4, extracted, innerbits, innermask)
|
|
|
|
output(ind, '}\n')
|
|
|
|
output(ind, 'return insn;\n')
|
|
|
|
# end SizeTree
|
|
|
|
|
|
|
|
class SizeLeaf:
|
|
|
|
"""Class representing a leaf node in a size decode tree"""
|
|
|
|
|
|
|
|
def __init__(self, m, w):
|
|
|
|
self.mask = m
|
|
|
|
self.width = w
|
|
|
|
|
|
|
|
def str1(self, i):
|
2021-04-29 02:27:56 +03:00
|
|
|
return str_indent(i) + whex(self.mask)
|
2019-01-31 22:34:11 +03:00
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
return self.str1(0)
|
|
|
|
|
|
|
|
def output_code(self, i, extracted, outerbits, outermask):
|
|
|
|
global decode_function
|
|
|
|
ind = str_indent(i)
|
|
|
|
|
|
|
|
# If we need to load more bytes, do so now.
|
|
|
|
if extracted < self.width:
|
2021-04-29 02:37:02 +03:00
|
|
|
output(ind, f'insn = {decode_function}_load_bytes',
|
|
|
|
f'(ctx, insn, {extracted // 8}, {self.width // 8});\n')
|
2019-01-31 22:34:11 +03:00
|
|
|
extracted = self.width
|
|
|
|
output(ind, 'return insn;\n')
|
|
|
|
# end SizeLeaf
|
|
|
|
|
|
|
|
|
|
|
|
def build_size_tree(pats, width, outerbits, outermask):
|
|
|
|
global insnwidth
|
|
|
|
|
|
|
|
# Collect the mask of bits that are fixed in this width
|
|
|
|
innermask = 0xff << (insnwidth - width)
|
|
|
|
innermask &= ~outermask
|
|
|
|
minwidth = None
|
|
|
|
onewidth = True
|
|
|
|
for i in pats:
|
|
|
|
innermask &= i.fixedmask
|
|
|
|
if minwidth is None:
|
|
|
|
minwidth = i.width
|
|
|
|
elif minwidth != i.width:
|
|
|
|
onewidth = False;
|
|
|
|
if minwidth < i.width:
|
|
|
|
minwidth = i.width
|
|
|
|
|
|
|
|
if onewidth:
|
|
|
|
return SizeLeaf(innermask, minwidth)
|
|
|
|
|
|
|
|
if innermask == 0:
|
|
|
|
if width < minwidth:
|
|
|
|
return build_size_tree(pats, width + 8, outerbits, outermask)
|
|
|
|
|
|
|
|
pnames = []
|
|
|
|
for p in pats:
|
|
|
|
pnames.append(p.name + ':' + p.file + ':' + str(p.lineno))
|
|
|
|
error_with_file(pats[0].file, pats[0].lineno,
|
2021-04-29 02:37:02 +03:00
|
|
|
f'overlapping patterns size {width}:', pnames)
|
2019-01-31 22:34:11 +03:00
|
|
|
|
|
|
|
bins = {}
|
|
|
|
for i in pats:
|
|
|
|
fb = i.fixedbits & innermask
|
|
|
|
if fb in bins:
|
|
|
|
bins[fb].append(i)
|
|
|
|
else:
|
|
|
|
bins[fb] = [i]
|
|
|
|
|
|
|
|
fullmask = outermask | innermask
|
|
|
|
lens = sorted(bins.keys())
|
|
|
|
if len(lens) == 1:
|
|
|
|
b = lens[0]
|
|
|
|
return build_size_tree(bins[b], width + 8, b | outerbits, fullmask)
|
|
|
|
|
|
|
|
r = SizeTree(innermask, width)
|
|
|
|
for b, l in bins.items():
|
|
|
|
s = build_size_tree(l, width, b | outerbits, fullmask)
|
|
|
|
r.subs.append((b, s))
|
|
|
|
return r
|
|
|
|
# end build_size_tree
|
|
|
|
|
|
|
|
|
|
|
|
def prop_size(tree):
|
|
|
|
"""Propagate minimum widths up the decode size tree"""
|
|
|
|
|
|
|
|
if isinstance(tree, SizeTree):
|
|
|
|
min = None
|
|
|
|
for (b, s) in tree.subs:
|
|
|
|
width = prop_size(s)
|
|
|
|
if min is None or min > width:
|
|
|
|
min = width
|
|
|
|
assert min >= tree.width
|
|
|
|
tree.width = min
|
|
|
|
else:
|
|
|
|
min = tree.width
|
|
|
|
return min
|
|
|
|
# end prop_size
|
|
|
|
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
def main():
|
|
|
|
global arguments
|
|
|
|
global formats
|
2019-02-23 22:35:36 +03:00
|
|
|
global allpatterns
|
2017-12-07 23:44:09 +03:00
|
|
|
global translate_scope
|
|
|
|
global translate_prefix
|
|
|
|
global output_fd
|
|
|
|
global output_file
|
|
|
|
global input_file
|
|
|
|
global insnwidth
|
|
|
|
global insntype
|
2018-03-19 14:58:46 +03:00
|
|
|
global insnmask
|
2018-10-23 12:26:25 +03:00
|
|
|
global decode_function
|
2021-04-08 01:18:49 +03:00
|
|
|
global bitop_width
|
2019-01-31 05:01:29 +03:00
|
|
|
global variablewidth
|
2019-08-09 18:12:50 +03:00
|
|
|
global anyextern
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
decode_scope = 'static '
|
|
|
|
|
2019-02-24 04:44:31 +03:00
|
|
|
long_opts = ['decode=', 'translate=', 'output=', 'insnwidth=',
|
2019-01-31 05:01:29 +03:00
|
|
|
'static-decode=', 'varinsnwidth=']
|
2017-12-07 23:44:09 +03:00
|
|
|
try:
|
2020-08-07 13:10:23 +03:00
|
|
|
(opts, args) = getopt.gnu_getopt(sys.argv[1:], 'o:vw:', long_opts)
|
2017-12-07 23:44:09 +03:00
|
|
|
except getopt.GetoptError as err:
|
|
|
|
error(0, err)
|
|
|
|
for o, a in opts:
|
|
|
|
if o in ('-o', '--output'):
|
|
|
|
output_file = a
|
|
|
|
elif o == '--decode':
|
|
|
|
decode_function = a
|
|
|
|
decode_scope = ''
|
2019-02-24 04:44:31 +03:00
|
|
|
elif o == '--static-decode':
|
|
|
|
decode_function = a
|
2017-12-07 23:44:09 +03:00
|
|
|
elif o == '--translate':
|
|
|
|
translate_prefix = a
|
|
|
|
translate_scope = ''
|
2019-01-31 05:01:29 +03:00
|
|
|
elif o in ('-w', '--insnwidth', '--varinsnwidth'):
|
|
|
|
if o == '--varinsnwidth':
|
|
|
|
variablewidth = True
|
2017-12-07 23:44:09 +03:00
|
|
|
insnwidth = int(a)
|
|
|
|
if insnwidth == 16:
|
|
|
|
insntype = 'uint16_t'
|
|
|
|
insnmask = 0xffff
|
2021-04-08 01:18:49 +03:00
|
|
|
elif insnwidth == 64:
|
|
|
|
insntype = 'uint64_t'
|
|
|
|
insnmask = 0xffffffffffffffff
|
|
|
|
bitop_width = 64
|
2017-12-07 23:44:09 +03:00
|
|
|
elif insnwidth != 32:
|
|
|
|
error(0, 'cannot handle insns of width', insnwidth)
|
|
|
|
else:
|
|
|
|
assert False, 'unhandled option'
|
|
|
|
|
|
|
|
if len(args) < 1:
|
|
|
|
error(0, 'missing input file')
|
2020-05-17 20:14:11 +03:00
|
|
|
|
|
|
|
toppat = ExcMultiPattern(0)
|
|
|
|
|
2018-10-26 16:59:43 +03:00
|
|
|
for filename in args:
|
|
|
|
input_file = filename
|
decodetree: Open files with encoding='utf-8'
When decodetree.py was added in commit 568ae7efae7, QEMU was
using Python 2 which happily reads UTF-8 files in text mode.
Python 3 requires either UTF-8 locale or an explicit encoding
passed to open(). Now that Python 3 is required, explicit
UTF-8 encoding for decodetree source files.
To avoid further problems with the user locale, also explicit
UTF-8 encoding for the generated C files.
Explicit both input/output are plain text by using the 't' mode.
This fixes:
$ /usr/bin/python3 scripts/decodetree.py test.decode
Traceback (most recent call last):
File "scripts/decodetree.py", line 1397, in <module>
main()
File "scripts/decodetree.py", line 1308, in main
parse_file(f, toppat)
File "scripts/decodetree.py", line 994, in parse_file
for line in f:
File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode
return codecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 80:
ordinal not in range(128)
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Suggested-by: Yonggang Luo <luoyonggang@gmail.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20210110000240.761122-1-f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-01-10 03:02:40 +03:00
|
|
|
f = open(filename, 'rt', encoding='utf-8')
|
2020-05-17 20:14:11 +03:00
|
|
|
parse_file(f, toppat)
|
2018-10-26 16:59:43 +03:00
|
|
|
f.close()
|
2017-12-07 23:44:09 +03:00
|
|
|
|
2020-05-17 20:14:11 +03:00
|
|
|
# We do not want to compute masks for toppat, because those masks
|
|
|
|
# are used as a starting point for build_tree. For toppat, we must
|
|
|
|
# insist that decode begins from naught.
|
|
|
|
for i in toppat.pats:
|
|
|
|
i.prop_masks()
|
|
|
|
|
|
|
|
toppat.build_tree()
|
|
|
|
toppat.prop_format()
|
|
|
|
|
2019-01-31 22:34:11 +03:00
|
|
|
if variablewidth:
|
2020-05-17 20:14:11 +03:00
|
|
|
for i in toppat.pats:
|
|
|
|
i.prop_width()
|
|
|
|
stree = build_size_tree(toppat.pats, 8, 0, 0)
|
2019-01-31 22:34:11 +03:00
|
|
|
prop_size(stree)
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
if output_file:
|
decodetree: Open files with encoding='utf-8'
When decodetree.py was added in commit 568ae7efae7, QEMU was
using Python 2 which happily reads UTF-8 files in text mode.
Python 3 requires either UTF-8 locale or an explicit encoding
passed to open(). Now that Python 3 is required, explicit
UTF-8 encoding for decodetree source files.
To avoid further problems with the user locale, also explicit
UTF-8 encoding for the generated C files.
Explicit both input/output are plain text by using the 't' mode.
This fixes:
$ /usr/bin/python3 scripts/decodetree.py test.decode
Traceback (most recent call last):
File "scripts/decodetree.py", line 1397, in <module>
main()
File "scripts/decodetree.py", line 1308, in main
parse_file(f, toppat)
File "scripts/decodetree.py", line 994, in parse_file
for line in f:
File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode
return codecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 80:
ordinal not in range(128)
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Suggested-by: Yonggang Luo <luoyonggang@gmail.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20210110000240.761122-1-f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-01-10 03:02:40 +03:00
|
|
|
output_fd = open(output_file, 'wt', encoding='utf-8')
|
2017-12-07 23:44:09 +03:00
|
|
|
else:
|
decodetree: Open files with encoding='utf-8'
When decodetree.py was added in commit 568ae7efae7, QEMU was
using Python 2 which happily reads UTF-8 files in text mode.
Python 3 requires either UTF-8 locale or an explicit encoding
passed to open(). Now that Python 3 is required, explicit
UTF-8 encoding for decodetree source files.
To avoid further problems with the user locale, also explicit
UTF-8 encoding for the generated C files.
Explicit both input/output are plain text by using the 't' mode.
This fixes:
$ /usr/bin/python3 scripts/decodetree.py test.decode
Traceback (most recent call last):
File "scripts/decodetree.py", line 1397, in <module>
main()
File "scripts/decodetree.py", line 1308, in main
parse_file(f, toppat)
File "scripts/decodetree.py", line 994, in parse_file
for line in f:
File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode
return codecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 80:
ordinal not in range(128)
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Suggested-by: Yonggang Luo <luoyonggang@gmail.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20210110000240.761122-1-f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-01-10 03:02:40 +03:00
|
|
|
output_fd = io.TextIOWrapper(sys.stdout.buffer,
|
|
|
|
encoding=sys.stdout.encoding,
|
|
|
|
errors="ignore")
|
2017-12-07 23:44:09 +03:00
|
|
|
|
|
|
|
output_autogen()
|
|
|
|
for n in sorted(arguments.keys()):
|
|
|
|
f = arguments[n]
|
|
|
|
f.output_def()
|
|
|
|
|
|
|
|
# A single translate function can be invoked for different patterns.
|
|
|
|
# Make sure that the argument sets are the same, and declare the
|
|
|
|
# function only once.
|
2019-08-09 18:12:50 +03:00
|
|
|
#
|
|
|
|
# If we're sharing formats, we're likely also sharing trans_* functions,
|
|
|
|
# but we can't tell which ones. Prevent issues from the compiler by
|
|
|
|
# suppressing redundant declaration warnings.
|
|
|
|
if anyextern:
|
2020-07-08 21:19:44 +03:00
|
|
|
output("#pragma GCC diagnostic push\n",
|
|
|
|
"#pragma GCC diagnostic ignored \"-Wredundant-decls\"\n",
|
|
|
|
"#ifdef __clang__\n"
|
2019-08-09 18:12:50 +03:00
|
|
|
"# pragma GCC diagnostic ignored \"-Wtypedef-redefinition\"\n",
|
|
|
|
"#endif\n\n")
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
out_pats = {}
|
2019-02-23 22:35:36 +03:00
|
|
|
for i in allpatterns:
|
2017-12-07 23:44:09 +03:00
|
|
|
if i.name in out_pats:
|
|
|
|
p = out_pats[i.name]
|
|
|
|
if i.base.base != p.base.base:
|
|
|
|
error(0, i.name, ' has conflicting argument sets')
|
|
|
|
else:
|
|
|
|
i.output_decl()
|
|
|
|
out_pats[i.name] = i
|
|
|
|
output('\n')
|
|
|
|
|
2019-08-09 18:12:50 +03:00
|
|
|
if anyextern:
|
2020-07-08 21:19:44 +03:00
|
|
|
output("#pragma GCC diagnostic pop\n\n")
|
2019-08-09 18:12:50 +03:00
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
for n in sorted(formats.keys()):
|
|
|
|
f = formats[n]
|
|
|
|
f.output_extract()
|
|
|
|
|
|
|
|
output(decode_scope, 'bool ', decode_function,
|
|
|
|
'(DisasContext *ctx, ', insntype, ' insn)\n{\n')
|
|
|
|
|
|
|
|
i4 = str_indent(4)
|
|
|
|
|
2019-02-28 08:37:32 +03:00
|
|
|
if len(allpatterns) != 0:
|
|
|
|
output(i4, 'union {\n')
|
|
|
|
for n in sorted(arguments.keys()):
|
|
|
|
f = arguments[n]
|
|
|
|
output(i4, i4, f.struct_name(), ' f_', f.name, ';\n')
|
|
|
|
output(i4, '} u;\n\n')
|
2020-05-17 20:14:11 +03:00
|
|
|
toppat.output_code(4, False, 0, 0)
|
2017-12-07 23:44:09 +03:00
|
|
|
|
2019-02-28 08:37:32 +03:00
|
|
|
output(i4, 'return false;\n')
|
2017-12-07 23:44:09 +03:00
|
|
|
output('}\n')
|
|
|
|
|
2019-01-31 22:34:11 +03:00
|
|
|
if variablewidth:
|
|
|
|
output('\n', decode_scope, insntype, ' ', decode_function,
|
|
|
|
'_load(DisasContext *ctx)\n{\n',
|
|
|
|
' ', insntype, ' insn = 0;\n\n')
|
|
|
|
stree.output_code(4, 0, 0, 0)
|
|
|
|
output('}\n')
|
|
|
|
|
2017-12-07 23:44:09 +03:00
|
|
|
if output_file:
|
|
|
|
output_fd.close()
|
|
|
|
# end main
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
main()
|