insnwidth = 32
insnmask = 0xffffffff
+variablewidth = False
fields = {}
arguments = {}
formats = {}
patterns = []
+allpatterns = []
translate_prefix = 'trans'
translate_scope = 'static '
return '{0}(insn, {1}, {2})'.format(extr, self.pos, self.len)
def __eq__(self, other):
- return self.sign == other.sign and self.sign == other.sign
+ return self.sign == other.sign and self.mask == other.mask
def __ne__(self, other):
return not self.__eq__(other)
return self.func + '(' + str(self.base) + ')'
def str_extract(self):
- return self.func + '(' + self.base.str_extract() + ')'
+ return self.func + '(ctx, ' + self.base.str_extract() + ')'
def __eq__(self, other):
return self.func == other.func and self.base == other.base
class General:
"""Common code between instruction formats and instruction patterns"""
- def __init__(self, name, lineno, base, fixb, fixm, udfm, fldm, flds):
+ def __init__(self, name, lineno, base, fixb, fixm, udfm, fldm, flds, w):
self.name = name
self.file = input_file
self.lineno = lineno
self.undefmask = udfm
self.fieldmask = fldm
self.fields = flds
+ self.width = w
def __str__(self):
- r = self.name
- if self.base:
- r = r + ' ' + self.base.name
- else:
- r = r + ' ' + str(self.fields)
- r = r + ' ' + str_match_bits(self.fixedbits, self.fixedmask)
- return r
+ return self.name + ' ' + str_match_bits(self.fixedbits, self.fixedmask)
def str1(self, i):
return str_indent(i) + self.__str__()
"""Class representing an instruction format"""
def extract_name(self):
- return 'extract_' + self.name
+ global decode_function
+ return decode_function + '_extract_' + self.name
def output_extract(self):
- output('static void ', self.extract_name(), '(',
+ output('static void ', self.extract_name(), '(DisasContext *ctx, ',
self.base.struct_name(), ' *a, ', insntype, ' insn)\n{\n')
for n, f in self.fields.items():
output(' a->', n, ' = ', f.str_extract(), ';\n')
arg = self.base.base.name
output(ind, '/* ', self.file, ':', str(self.lineno), ' */\n')
if not extracted:
- output(ind, self.base.extract_name(), '(&u.f_', arg, ', insn);\n')
+ output(ind, self.base.extract_name(),
+ '(ctx, &u.f_', arg, ', insn);\n')
for n, f in self.fields.items():
output(ind, 'u.f_', arg, '.', n, ' = ', f.str_extract(), ';\n')
- output(ind, 'return ', translate_prefix, '_', self.name,
- '(ctx, &u.f_', arg, ');\n')
+ output(ind, 'if (', translate_prefix, '_', self.name,
+ '(ctx, &u.f_', arg, ')) return true;\n')
# end Pattern
+class MultiPattern(General):
+ """Class representing an overlapping set of instruction patterns"""
+
+ def __init__(self, lineno, pats, fixb, fixm, udfm, w):
+ self.file = input_file
+ self.lineno = lineno
+ self.pats = pats
+ self.base = None
+ self.fixedbits = fixb
+ self.fixedmask = fixm
+ self.undefmask = udfm
+ self.width = w
+
+ def __str__(self):
+ r = "{"
+ for p in self.pats:
+ r = r + ' ' + str(p)
+ return r + "}"
+
+ def output_decl(self):
+ for p in self.pats:
+ p.output_decl()
+
+ 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
+ output(ind, 'if ((insn & ',
+ '0x{0:08x}) == 0x{1:08x}'.format(innermask, innerbits),
+ ') {\n')
+ output(ind, ' /* ',
+ str_match_bits(p.fixedbits, p.fixedmask), ' */\n')
+ p.output_code(i + 4, extracted, p.fixedbits, p.fixedmask)
+ output(ind, '}\n')
+ else:
+ p.output_code(i, extracted, p.fixedbits, p.fixedmask)
+#end MultiPattern
+
+
def parse_field(lineno, name, toks):
"""Parse one instruction field from TOKS at LINENO"""
global fields
return arg
-def infer_format(arg, fieldmask, flds):
+def infer_format(arg, fieldmask, flds, width):
global arguments
global formats
global decode_function
continue
if fieldmask != fmt.fieldmask:
continue
+ if width != fmt.width:
+ continue
if not eq_fields_for_fmts(flds, fmt.fields):
continue
return (fmt, const_flds)
if not arg:
arg = infer_argument_set(flds)
- fmt = Format(name, 0, arg, 0, 0, 0, fieldmask, var_flds)
+ fmt = Format(name, 0, arg, 0, 0, 0, fieldmask, var_flds, width)
formats[name] = fmt
return (fmt, const_flds)
global arguments
global formats
global patterns
+ global allpatterns
global re_ident
global insnwidth
global insnmask
+ global variablewidth
fixedmask = 0
fixedbits = 0
continue
# 'Foo=number' sets an argument field to a constant value
- if re_fullmatch(re_ident + '=[0-9]+', t):
+ if re_fullmatch(re_ident + '=[+-]?[0-9]+', t):
(fname, value) = t.split('=')
value = int(value)
flds = add_field(lineno, flds, fname, ConstField(value))
sign = True
flen = flen[1:]
shift = int(flen, 10)
+ if shift + width > insnwidth:
+ error(lineno, 'field {0} exceeds insnwidth'.format(fname))
f = Field(sign, insnwidth - width - shift, shift)
flds = add_field(lineno, flds, fname, f)
fixedbits <<= shift
error(lineno, 'invalid token "{0}"'.format(t))
width += shift
+ if variablewidth and width < insnwidth and width % 8 == 0:
+ shift = insnwidth - width
+ fixedbits <<= shift
+ fixedmask <<= shift
+ undefmask <<= shift
+ undefmask |= (1 << shift) - 1
+
# We should have filled in all of the bits of the instruction.
- if not (is_format and width == 0) and width != insnwidth:
+ elif not (is_format and width == 0) and width != insnwidth:
error(lineno, 'definition has {0} bits'.format(width))
# Do not check for fields overlaping fields; one valid usage
if name in formats:
error(lineno, 'duplicate format name', name)
fmt = Format(name, lineno, arg, fixedbits, fixedmask,
- undefmask, fieldmask, flds)
+ undefmask, fieldmask, flds, width)
formats[name] = fmt
else:
# Patterns can reference a format ...
error(lineno, 'pattern specifies both format and argument set')
if fixedmask & fmt.fixedmask:
error(lineno, 'pattern fixed bits overlap format fixed bits')
+ if width != fmt.width:
+ error(lineno, 'pattern uses format of different width')
fieldmask |= fmt.fieldmask
fixedbits |= fmt.fixedbits
fixedmask |= fmt.fixedmask
undefmask |= fmt.undefmask
else:
- (fmt, flds) = infer_format(arg, fieldmask, flds)
+ (fmt, flds) = infer_format(arg, fieldmask, flds, width)
arg = fmt.base
for f in flds.keys():
if f not in arg.fields:
if f not in flds.keys() and f not in fmt.fields.keys():
error(lineno, 'field {0} not initialized'.format(f))
pat = Pattern(name, lineno, fmt, fixedbits, fixedmask,
- undefmask, fieldmask, flds)
+ undefmask, fieldmask, flds, width)
patterns.append(pat)
+ allpatterns.append(pat)
# Validate the masks that we have assembled.
if fieldmask & fixedmask:
.format(allbits ^ insnmask))
# end parse_general
+def build_multi_pattern(lineno, pats):
+ """Validate the Patterns going into a MultiPattern."""
+ global patterns
+ global insnmask
+
+ if len(pats) < 2:
+ error(lineno, 'less than two patterns within braces')
+
+ fixedmask = insnmask
+ undefmask = insnmask
+
+ # Collect fixed/undefmask for all of the children.
+ # Move the defining lineno back to that of the first child.
+ for p in pats:
+ fixedmask &= p.fixedmask
+ undefmask &= p.undefmask
+ if p.lineno < lineno:
+ lineno = p.lineno
+
+ width = None
+ for p in pats:
+ if width is None:
+ width = p.width
+ elif width != p.width:
+ error(lineno, 'width mismatch in patterns within braces')
+
+ repeat = True
+ while repeat:
+ if fixedmask == 0:
+ error(lineno, 'no overlap in patterns within braces')
+ fixedbits = None
+ for p in pats:
+ thisbits = p.fixedbits & fixedmask
+ if fixedbits is None:
+ fixedbits = thisbits
+ elif fixedbits != thisbits:
+ fixedmask &= ~(fixedbits ^ thisbits)
+ break
+ else:
+ repeat = False
+
+ mp = MultiPattern(lineno, pats, fixedbits, fixedmask, undefmask, width)
+ patterns.append(mp)
+# end build_multi_pattern
def parse_file(f):
"""Parse all of the patterns within a file"""
+ global patterns
+
# Read all of the lines of the file. Concatenate lines
# ending in backslash; discard empty lines and comments.
toks = []
lineno = 0
+ nesting = 0
+ saved_pats = []
+
for line in f:
lineno += 1
+ # Expand and strip spaces, to find indent.
+ line = line.rstrip()
+ line = line.expandtabs()
+ len1 = len(line)
+ line = line.lstrip()
+ len2 = len(line)
+
# Discard comments
end = line.find('#')
if end >= 0:
if len(toks) != 0:
# Next line after continuation
toks.extend(t)
- elif len(t) == 0:
- # Empty line
- continue
else:
+ # 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
toks = t
# Continuation?
toks.pop()
continue
- if len(toks) < 2:
- error(lineno, 'short line')
-
name = toks[0]
del toks[0]
+ # End nesting?
+ if name == '}':
+ if nesting == 0:
+ error(start_lineno, 'mismatched close brace')
+ if len(toks) != 0:
+ error(start_lineno, 'extra tokens after close brace')
+ nesting -= 2
+ if indent != nesting:
+ error(start_lineno, 'indentation ', indent, ' != ', nesting)
+ pats = patterns
+ patterns = saved_pats.pop()
+ build_multi_pattern(lineno, pats)
+ toks = []
+ continue
+
+ # Everything else should have current indentation.
+ if indent != nesting:
+ error(start_lineno, 'indentation ', indent, ' != ', nesting)
+
+ # Start nesting?
+ if name == '{':
+ if len(toks) != 0:
+ error(start_lineno, 'extra tokens after open brace')
+ saved_pats.append(patterns)
+ patterns = []
+ nesting += 2
+ toks = []
+ continue
+
# Determine the type of object needing to be parsed.
if name[0] == '%':
- parse_field(lineno, name[1:], toks)
+ parse_field(start_lineno, name[1:], toks)
elif name[0] == '&':
- parse_arguments(lineno, name[1:], toks)
+ parse_arguments(start_lineno, name[1:], toks)
elif name[0] == '@':
- parse_generic(lineno, True, name[1:], toks)
+ parse_generic(start_lineno, True, name[1:], toks)
else:
- parse_generic(lineno, False, name, toks)
+ parse_generic(start_lineno, False, name, toks)
toks = []
# end parse_file
# extract the fields now.
if not extracted and self.base:
output(ind, self.base.extract_name(),
- '(&u.f_', self.base.base.name, ', insn);\n')
+ '(ctx, &u.f_', self.base.base.name, ', insn);\n')
extracted = True
# Attempt to aid the compiler in producing compact switch statements.
output(ind, ' /* ',
str_match_bits(innerbits, innermask), ' */\n')
s.output_code(i + 4, extracted, innerbits, innermask)
+ output(ind, ' return false;\n')
output(ind, '}\n')
- output(ind, 'return false;\n')
# end Tree
innermask &= i.fixedmask
if innermask == 0:
- pnames = []
+ text = 'overlapping patterns:'
for p in pats:
- pnames.append(p.name + ':' + p.file + ':' + str(p.lineno))
- error_with_file(pats[0].file, pats[0].lineno,
- 'overlapping patterns:', pnames)
+ text += '\n' + p.file + ':' + str(p.lineno) + ': ' + str(p)
+ error_with_file(pats[0].file, pats[0].lineno, text)
fullmask = outermask | innermask
# end build_tree
+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)
+ r = '{0}{1:08x}'.format(ind, self.mask)
+ r += ' [\n'
+ for (b, s) in self.subs:
+ r += '{0} {1:08x}:\n'.format(ind, b)
+ 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:
+ output(ind, 'insn = ', decode_function,
+ '_load_bytes(ctx, insn, {0}, {1});\n'
+ .format(extracted / 8, self.width / 8));
+ 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):
+ return '(insn >> {0}) & 0x{1:x}'.format(sh, b >> sh)
+
+ def str_case(b, sh=sh):
+ return '0x{0:x}'.format(b >> sh)
+ else:
+ def str_switch(b):
+ return 'insn & 0x{0:08x}'.format(b)
+
+ def str_case(b):
+ return '0x{0:08x}'.format(b)
+
+ 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):
+ ind = str_indent(i)
+ return '{0}{1:08x}'.format(ind, self.mask)
+
+ 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:
+ output(ind, 'insn = ', decode_function,
+ '_load_bytes(ctx, insn, {0}, {1});\n'
+ .format(extracted / 8, self.width / 8));
+ 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,
+ 'overlapping patterns size {0}:'.format(width), pnames)
+
+ 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_format(tree):
"""Propagate Format objects into the decode tree"""
# end prop_format
+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
+
+
def main():
global arguments
global formats
global patterns
+ global allpatterns
global translate_scope
global translate_prefix
global output_fd
global insntype
global insnmask
global decode_function
+ global variablewidth
decode_scope = 'static '
- long_opts = ['decode=', 'translate=', 'output=', 'insnwidth=']
+ long_opts = ['decode=', 'translate=', 'output=', 'insnwidth=',
+ 'static-decode=', 'varinsnwidth=']
try:
- (opts, args) = getopt.getopt(sys.argv[1:], 'o:w:', long_opts)
+ (opts, args) = getopt.getopt(sys.argv[1:], 'o:vw:', long_opts)
except getopt.GetoptError as err:
error(0, err)
for o, a in opts:
elif o == '--decode':
decode_function = a
decode_scope = ''
+ elif o == '--static-decode':
+ decode_function = a
elif o == '--translate':
translate_prefix = a
translate_scope = ''
- elif o in ('-w', '--insnwidth'):
+ elif o in ('-w', '--insnwidth', '--varinsnwidth'):
+ if o == '--varinsnwidth':
+ variablewidth = True
insnwidth = int(a)
if insnwidth == 16:
insntype = 'uint16_t'
parse_file(f)
f.close()
- t = build_tree(patterns, 0, 0)
- prop_format(t)
+ if variablewidth:
+ stree = build_size_tree(patterns, 8, 0, 0)
+ prop_size(stree)
+
+ dtree = build_tree(patterns, 0, 0)
+ prop_format(dtree)
if output_file:
output_fd = open(output_file, 'w')
# Make sure that the argument sets are the same, and declare the
# function only once.
out_pats = {}
- for i in patterns:
+ for i in allpatterns:
if i.name in out_pats:
p = out_pats[i.name]
if i.base.base != p.base.base:
'(DisasContext *ctx, ', insntype, ' insn)\n{\n')
i4 = str_indent(4)
- 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')
- t.output_code(4, False, 0, 0)
+ 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')
+ dtree.output_code(4, False, 0, 0)
+ output(i4, 'return false;\n')
output('}\n')
+ 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')
+
if output_file:
output_fd.close()
# end main