def main(): from argparse import RawTextHelpFormatter parser = argparse.ArgumentParser(description=__doc__, formatter_class=RawTextHelpFormatter) parser.add_argument('--opt-binary', default='opt', help='The opt binary used to generate the test case') parser.add_argument('--function', help='The function in the test file to update') parser.add_argument('tests', nargs='+') args = common.parse_commandline_args(parser) script_name = os.path.basename(__file__) autogenerated_note = (ADVERT + 'utils/' + script_name) opt_basename = os.path.basename(args.opt_binary) if (opt_basename != "opt"): common.error('Unexpected opt name: ' + opt_basename) sys.exit(1) test_paths = [ test for pattern in args.tests for test in glob.glob(pattern) ] for test in test_paths: with open(test) as f: input_lines = [l.rstrip() for l in f] first_line = input_lines[0] if input_lines else "" if 'autogenerated' in first_line and script_name not in first_line: common.warn("Skipping test which wasn't autogenerated by " + script_name + ": " + test) continue if args.update_only: if not first_line or 'autogenerated' not in first_line: common.warn("Skipping test which isn't autogenerated: " + test) continue run_lines = common.find_run_lines(test, input_lines) prefix_list = [] for l in run_lines: if '|' not in l: common.warn('Skipping unparseable RUN line: ' + l) continue (tool_cmd, filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)]) common.verify_filecheck_prefixes(filecheck_cmd) if not tool_cmd.startswith(opt_basename + ' '): common.warn('WSkipping non-%s RUN line: %s' % (opt_basename, l)) continue if not filecheck_cmd.startswith('FileCheck '): common.warn('Skipping non-FileChecked RUN line: ' + l) continue tool_cmd_args = tool_cmd[len(opt_basename):].strip() tool_cmd_args = tool_cmd_args.replace('< %s', '').replace('%s', '').strip() check_prefixes = [ item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd) for item in m.group(1).split(',') ] if not check_prefixes: check_prefixes = ['CHECK'] # FIXME: We should use multiple check prefixes to common check lines. For # now, we just ignore all but the last. prefix_list.append((check_prefixes, tool_cmd_args)) builder = common.FunctionTestBuilder( run_list=prefix_list, flags=type( '', (object, ), { 'verbose': args.verbose, 'function_signature': False, 'check_attributes': False, 'replace_value_regex': [] }), scrubber_args=[]) for prefixes, opt_args in prefix_list: common.debug('Extracted opt cmd:', opt_basename, opt_args, file=sys.stderr) common.debug('Extracted FileCheck prefixes:', str(prefixes), file=sys.stderr) raw_tool_outputs = common.invoke_tool(args.opt_binary, opt_args, test) # Split analysis outputs by "Printing analysis " declarations. for raw_tool_output in re.split(r'Printing analysis ', raw_tool_outputs): builder.process_run_line(common.ANALYZE_FUNCTION_RE, common.scrub_body, raw_tool_output, prefixes) func_dict = builder.finish_and_get_func_dict() is_in_function = False is_in_function_start = False prefix_set = set( [prefix for prefixes, _ in prefix_list for prefix in prefixes]) common.debug('Rewriting FileCheck prefixes:', str(prefix_set), file=sys.stderr) output_lines = [] output_lines.append(autogenerated_note) for input_line in input_lines: if is_in_function_start: if input_line == '': continue if input_line.lstrip().startswith(';'): m = common.CHECK_RE.match(input_line) if not m or m.group(1) not in prefix_set: output_lines.append(input_line) continue # Print out the various check lines here. common.add_analyze_checks(output_lines, ';', prefix_list, func_dict, func_name) is_in_function_start = False if is_in_function: if common.should_add_line_to_output(input_line, prefix_set): # This input line of the function body will go as-is into the output. # Except make leading whitespace uniform: 2 spaces. input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub( r' ', input_line) output_lines.append(input_line) else: continue if input_line.strip() == '}': is_in_function = False continue # Discard any previous script advertising. if input_line.startswith(ADVERT): continue # If it's outside a function, it just gets copied to the output. output_lines.append(input_line) m = common.IR_FUNCTION_RE.match(input_line) if not m: continue func_name = m.group(1) if args.function is not None and func_name != args.function: # When filtering on a specific function, skip all others. continue is_in_function = is_in_function_start = True common.debug('Writing %d lines to %s...' % (len(output_lines), test)) with open(test, 'wb') as f: f.writelines( ['{}\n'.format(l).encode('utf-8') for l in output_lines])
def get_line2spell_and_mangled(args, clang_args): ret = {} # Use clang's JSON AST dump to get the mangled name json_dump_args = [args.clang] + clang_args + ['-fsyntax-only', '-o', '-'] if '-cc1' not in json_dump_args: # For tests that invoke %clang instead if %clang_cc1 we have to use # -Xclang -ast-dump=json instead: json_dump_args.append('-Xclang') json_dump_args.append('-ast-dump=json') common.debug('Running', ' '.join(json_dump_args)) popen = subprocess.Popen(json_dump_args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True) stdout, stderr = popen.communicate() if popen.returncode != 0: sys.stderr.write('Failed to run ' + ' '.join(json_dump_args) + '\n') sys.stderr.write(stderr) sys.stderr.write(stdout) sys.exit(2) # Parse the clang JSON and add all children of type FunctionDecl. # TODO: Should we add checks for global variables being emitted? def parse_clang_ast_json(node): node_kind = node['kind'] # Recurse for the following nodes that can contain nested function decls: if node_kind in ('NamespaceDecl', 'LinkageSpecDecl', 'TranslationUnitDecl'): for inner in node['inner']: parse_clang_ast_json(inner) # Otherwise we ignore everything except functions: if node['kind'] != 'FunctionDecl': return if node.get('isImplicit') is True and node.get( 'storageClass') == 'extern': common.debug('Skipping builtin function:', node['name'], '@', node['loc']) return common.debug('Found function:', node['kind'], node['name'], '@', node['loc']) line = node['loc'].get('line') # If there is no line it is probably a builtin function -> skip if line is None: common.debug('Skipping function without line number:', node['name'], '@', node['loc']) return spell = node['name'] mangled = node.get('mangledName', spell) ret[int(line) - 1] = (spell, mangled) ast = json.loads(stdout) if ast['kind'] != 'TranslationUnitDecl': common.error('Clang AST dump JSON format changed?') sys.exit(2) parse_clang_ast_json(ast) for line, func_name in sorted(ret.items()): common.debug('line {}: found function {}'.format(line + 1, func_name), file=sys.stderr) if not ret: common.warn('Did not find any functions using', ' '.join(json_dump_args)) return ret
def main(): from argparse import RawTextHelpFormatter parser = argparse.ArgumentParser(description=__doc__, formatter_class=RawTextHelpFormatter) parser.add_argument('--opt-binary', default='opt', help='The opt binary used to generate the test case') parser.add_argument('--function', help='The function in the test file to update') parser.add_argument('-p', '--preserve-names', action='store_true', help='Do not scrub IR names') parser.add_argument( '--function-signature', action='store_true', help='Keep function signature information around for the check line') parser.add_argument( '--scrub-attributes', action='store_true', help='Remove attribute annotations (#0) from the end of check line') parser.add_argument('--check-attributes', action='store_true', help='Check "Function Attributes" for functions') parser.add_argument( '--check-globals', action='store_true', help= 'Check global entries (global variables, metadata, attribute sets, ...) for functions' ) parser.add_argument('tests', nargs='+') initial_args = common.parse_commandline_args(parser) script_name = os.path.basename(__file__) opt_basename = os.path.basename(initial_args.opt_binary) if not re.match(r'^opt(-\d+)?(\.exe)?$', opt_basename): common.error('Unexpected opt name: ' + opt_basename) sys.exit(1) opt_basename = 'opt' for ti in common.itertests(initial_args.tests, parser, script_name='utils/' + script_name): # If requested we scrub trailing attribute annotations, e.g., '#0', together with whitespaces if ti.args.scrub_attributes: common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_AND_ATTRIBUTES_RE else: common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_RE prefix_list = [] for l in ti.run_lines: if '|' not in l: common.warn('Skipping unparseable RUN line: ' + l) continue commands = [cmd.strip() for cmd in l.split('|')] assert len(commands) >= 2 preprocess_cmd = None if len(commands) > 2: preprocess_cmd = " | ".join(commands[:-2]) tool_cmd = commands[-2] filecheck_cmd = commands[-1] common.verify_filecheck_prefixes(filecheck_cmd) if not tool_cmd.startswith(opt_basename + ' '): common.warn('Skipping non-%s RUN line: %s' % (opt_basename, l)) continue if not filecheck_cmd.startswith('FileCheck '): common.warn('Skipping non-FileChecked RUN line: ' + l) continue tool_cmd_args = tool_cmd[len(opt_basename):].strip() tool_cmd_args = tool_cmd_args.replace('< %s', '').replace('%s', '').strip() check_prefixes = [ item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd) for item in m.group(1).split(',') ] if not check_prefixes: check_prefixes = ['CHECK'] # FIXME: We should use multiple check prefixes to common check lines. For # now, we just ignore all but the last. prefix_list.append((check_prefixes, tool_cmd_args, preprocess_cmd)) global_vars_seen_dict = {} builder = common.FunctionTestBuilder(run_list=prefix_list, flags=ti.args, scrubber_args=[]) for prefixes, opt_args, preprocess_cmd in prefix_list: common.debug('Extracted opt cmd: ' + opt_basename + ' ' + opt_args) common.debug('Extracted FileCheck prefixes: ' + str(prefixes)) raw_tool_output = common.invoke_tool(ti.args.opt_binary, opt_args, ti.path, preprocess_cmd=preprocess_cmd, verbose=ti.args.verbose) builder.process_run_line(common.OPT_FUNCTION_RE, common.scrub_body, raw_tool_output, prefixes) func_dict = builder.finish_and_get_func_dict() is_in_function = False is_in_function_start = False has_checked_pre_function_globals = False prefix_set = set( [prefix for prefixes, _, _ in prefix_list for prefix in prefixes]) common.debug('Rewriting FileCheck prefixes:', str(prefix_set)) output_lines = [] include_generated_funcs = common.find_arg_in_test( ti, lambda args: ti.args.include_generated_funcs, '--include-generated-funcs', True) if include_generated_funcs: # Generate the appropriate checks for each function. We need to emit # these in the order according to the generated output so that CHECK-LABEL # works properly. func_order provides that. # We can't predict where various passes might insert functions so we can't # be sure the input function order is maintained. Therefore, first spit # out all the source lines. common.dump_input_lines(output_lines, ti, prefix_set, ';') args = ti.args if args.check_globals: common.add_global_checks(builder.global_var_dict(), ';', prefix_list, output_lines, global_vars_seen_dict, args.preserve_names, True) # Now generate all the checks. common.add_checks_at_end( output_lines, prefix_list, builder.func_order(), ';', lambda my_output_lines, prefixes, func: common.add_ir_checks( my_output_lines, ';', prefixes, func_dict, func, False, args.function_signature, global_vars_seen_dict)) else: # "Normal" mode. for input_line_info in ti.iterlines(output_lines): input_line = input_line_info.line args = input_line_info.args if is_in_function_start: if input_line == '': continue if input_line.lstrip().startswith(';'): m = common.CHECK_RE.match(input_line) if not m or m.group(1) not in prefix_set: output_lines.append(input_line) continue # Print out the various check lines here. common.add_ir_checks(output_lines, ';', prefix_list, func_dict, func_name, args.preserve_names, args.function_signature, global_vars_seen_dict) is_in_function_start = False m = common.IR_FUNCTION_RE.match(input_line) if m and not has_checked_pre_function_globals: if args.check_globals: common.add_global_checks(builder.global_var_dict(), ';', prefix_list, output_lines, global_vars_seen_dict, args.preserve_names, True) has_checked_pre_function_globals = True if common.should_add_line_to_output(input_line, prefix_set, not is_in_function): # This input line of the function body will go as-is into the output. # Except make leading whitespace uniform: 2 spaces. input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub( r' ', input_line) output_lines.append(input_line) if input_line.strip() == '}': is_in_function = False continue if is_in_function: continue m = common.IR_FUNCTION_RE.match(input_line) if not m: continue func_name = m.group(1) if args.function is not None and func_name != args.function: # When filtering on a specific function, skip all others. continue is_in_function = is_in_function_start = True if args.check_globals: common.add_global_checks(builder.global_var_dict(), ';', prefix_list, output_lines, global_vars_seen_dict, args.preserve_names, False) common.debug('Writing %d lines to %s...' % (len(output_lines), ti.path)) with open(ti.path, 'wb') as f: f.writelines( ['{}\n'.format(l).encode('utf-8') for l in output_lines])
def main(): initial_args, parser = config() script_name = os.path.basename(__file__) for ti in common.itertests(initial_args.tests, parser, 'utils/' + script_name, comment_prefix='//', argparse_callback=infer_dependent_args): # Build a list of clang command lines and check prefixes from RUN lines. run_list = [] line2spell_and_mangled_list = collections.defaultdict(list) for l in ti.run_lines: commands = [cmd.strip() for cmd in l.split('|')] triple_in_cmd = None m = common.TRIPLE_ARG_RE.search(commands[0]) if m: triple_in_cmd = m.groups()[0] # Apply %clang substitution rule, replace %s by `filename`, and append args.clang_args clang_args = shlex.split(commands[0]) if clang_args[0] not in SUBST: print('WARNING: Skipping non-clang RUN line: ' + l, file=sys.stderr) continue clang_args[0:1] = SUBST[clang_args[0]] clang_args = [ti.path if i == '%s' else i for i in clang_args] + ti.args.clang_args # Remove all -verify arguments since they could cause the IR generation to fail clang_args = [x for x in clang_args if not x.startswith("-verify")] if '-ast-dump' in clang_args: print('WARNING: Skipping -ast-dump RUN line: ' + l, file=sys.stderr) continue if '-fsynatx-only' in clang_args: print('WARNING: Skipping -fsynatx-only RUN line: ' + l, file=sys.stderr) continue # Permit piping the output through opt if not (len(commands) == 2 or (len(commands) == 3 and commands[1].startswith('opt'))): print('WARNING: Skipping non-clang RUN line: ' + l, file=sys.stderr) # Extract -check-prefix in FileCheck args filecheck_cmd = commands[-1] common.verify_filecheck_prefixes(filecheck_cmd) if not filecheck_cmd.startswith( 'FileCheck ') and not filecheck_cmd.startswith( '%cheri_FileCheck '): print('WARNING: Skipping non-FileChecked RUN line: ' + l, file=sys.stderr) continue check_prefixes = [ item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd) for item in m.group(1).split(',') ] if not check_prefixes: check_prefixes = ['CHECK'] run_list.append( (check_prefixes, clang_args, commands[1:-1], triple_in_cmd)) # Execute clang, generate LLVM IR, and extract functions. func_dict = {} for p in run_list: prefixes = p[0] for prefix in prefixes: func_dict.update({prefix: dict()}) for prefixes, clang_args, extra_commands, triple_in_cmd in run_list: common.debug('Extracted clang cmd: clang {}'.format(clang_args)) common.debug('Extracted FileCheck prefixes: {}'.format(prefixes)) get_function_body(ti.args, ti.path, clang_args, extra_commands, prefixes, triple_in_cmd, func_dict) # Invoke clang -Xclang -ast-dump=json to get mapping from start lines to # mangled names. Forward all clang args for now. for k, v in get_line2spell_and_mangled(ti.args, clang_args).items(): line2spell_and_mangled_list[k].append(v) global_vars_seen_dict = {} prefix_set = set([prefix for p in run_list for prefix in p[0]]) output_lines = [] for line_info in ti.iterlines(output_lines): idx = line_info.line_number line = line_info.line args = line_info.args include_line = True m = common.CHECK_RE.match(line) if m and m.group(1) in prefix_set: continue # Don't append the existing CHECK lines if idx in line2spell_and_mangled_list: added = set() for spell, mangled in line2spell_and_mangled_list[idx]: # One line may contain multiple function declarations. # Skip if the mangled name has been added before. # The line number may come from an included file, # we simply require the spelling name to appear on the line # to exclude functions from other files. if mangled in added or spell not in line: continue if args.functions is None or any( re.search(regex, spell) for regex in args.functions): last_line = output_lines[-1].strip() while last_line == '//': # Remove the comment line since we will generate a new comment # line as part of common.add_ir_checks() output_lines.pop() last_line = output_lines[-1].strip() if added: output_lines.append('//') added.add(mangled) common.add_ir_checks(output_lines, '//', run_list, func_dict, mangled, False, args.function_signature, global_vars_seen_dict) if line.rstrip('\n') == '//': include_line = False if include_line: output_lines.append(line.rstrip('\n')) common.debug('Writing %d lines to %s...' % (len(output_lines), ti.path)) with open(ti.path, 'wb') as f: f.writelines( ['{}\n'.format(l).encode('utf-8') for l in output_lines]) return 0
def main(): args = config() script_name = os.path.basename(__file__) autogenerated_note = (ADVERT + 'utils/' + script_name) for filename in args.tests: with open(filename) as f: input_lines = [l.rstrip() for l in f] first_line = input_lines[0] if input_lines else "" if 'autogenerated' in first_line and script_name not in first_line: common.warn( "Skipping test which wasn't autogenerated by " + script_name, filename) continue if args.update_only: if not first_line or 'autogenerated' not in first_line: common.warn("Skipping test which isn't autogenerated: " + filename) continue # Extract RUN lines. run_lines = common.find_run_lines(filename, input_lines) # Build a list of clang command lines and check prefixes from RUN lines. run_list = [] line2spell_and_mangled_list = collections.defaultdict(list) for l in run_lines: commands = [cmd.strip() for cmd in l.split('|')] triple_in_cmd = None m = common.TRIPLE_ARG_RE.search(commands[0]) if m: triple_in_cmd = m.groups()[0] # Apply %clang substitution rule, replace %s by `filename`, and append args.clang_args clang_args = shlex.split(commands[0]) if clang_args[0] not in SUBST: print('WARNING: Skipping non-clang RUN line: ' + l, file=sys.stderr) continue clang_args[0:1] = SUBST[clang_args[0]] clang_args = [filename if i == '%s' else i for i in clang_args] + args.clang_args # Permit piping the output through opt if not (len(commands) == 2 or (len(commands) == 3 and commands[1].startswith('opt'))): print('WARNING: Skipping non-clang RUN line: ' + l, file=sys.stderr) # Extract -check-prefix in FileCheck args filecheck_cmd = commands[-1] common.verify_filecheck_prefixes(filecheck_cmd) if not filecheck_cmd.startswith( 'FileCheck ') and not filecheck_cmd.startswith( '%cheri_FileCheck '): print('WARNING: Skipping non-FileChecked RUN line: ' + l, file=sys.stderr) continue check_prefixes = [ item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd) for item in m.group(1).split(',') ] if not check_prefixes: check_prefixes = ['CHECK'] run_list.append( (check_prefixes, clang_args, commands[1:-1], triple_in_cmd)) # Strip CHECK lines which are in `prefix_set`, update test file. prefix_set = set([prefix for p in run_list for prefix in p[0]]) input_lines = [] with open(filename, 'r+') as f: for line in f: m = common.CHECK_RE.match(line) if not (m and m.group(1) in prefix_set) and line != '//\n': input_lines.append(line) f.seek(0) f.writelines(input_lines) f.truncate() # Execute clang, generate LLVM IR, and extract functions. func_dict = {} for p in run_list: prefixes = p[0] for prefix in prefixes: func_dict.update({prefix: dict()}) for prefixes, clang_args, extra_commands, triple_in_cmd in run_list: common.debug('Extracted clang cmd: clang {}'.format(clang_args)) common.debug('Extracted FileCheck prefixes: {}'.format(prefixes)) get_function_body(args, filename, clang_args, extra_commands, prefixes, triple_in_cmd, func_dict) # Invoke clang -Xclang -ast-dump=json to get mapping from start lines to # mangled names. Forward all clang args for now. for k, v in get_line2spell_and_mangled(args, clang_args).items(): line2spell_and_mangled_list[k].append(v) output_lines = [autogenerated_note] for idx, line in enumerate(input_lines): # Discard any previous script advertising. if line.startswith(ADVERT): continue if idx in line2spell_and_mangled_list: added = set() for spell, mangled in line2spell_and_mangled_list[idx]: # One line may contain multiple function declarations. # Skip if the mangled name has been added before. # The line number may come from an included file, # we simply require the spelling name to appear on the line # to exclude functions from other files. if mangled in added or spell not in line: continue if args.functions is None or any( re.search(regex, spell) for regex in args.functions): if added: output_lines.append('//') added.add(mangled) common.add_ir_checks(output_lines, '//', run_list, func_dict, mangled, False, args.function_signature) output_lines.append(line.rstrip('\n')) # Update the test file. with open(filename, 'w') as f: for line in output_lines: f.write(line + '\n') return 0
def main(): initial_args, parser = config() script_name = os.path.basename(__file__) for ti in common.itertests(initial_args.tests, parser, 'utils/' + script_name, comment_prefix='//', argparse_callback=infer_dependent_args): # Build a list of filechecked and non-filechecked RUN lines. run_list = [] line2func_list = collections.defaultdict(list) subs = { '%s': ti.path, '%t': tempfile.NamedTemporaryFile().name, '%S': os.path.dirname(ti.path), } for l in ti.run_lines: commands = [cmd.strip() for cmd in l.split('|')] triple_in_cmd = None m = common.TRIPLE_ARG_RE.search(commands[0]) if m: triple_in_cmd = m.groups()[0] # Parse executable args. exec_args = shlex.split(commands[0]) # Execute non-clang runline. if exec_args[0] not in SUBST: # Do lit-like substitutions. for s in subs: exec_args = [ i.replace(s, subs[s]) if s in i else i for i in exec_args ] run_list.append((None, exec_args, None, None)) continue # This is a clang runline, apply %clang substitution rule, do lit-like substitutions, # and append args.clang_args clang_args = exec_args clang_args[0:1] = SUBST[clang_args[0]] for s in subs: clang_args = [ i.replace(s, subs[s]) if s in i else i for i in clang_args ] clang_args += ti.args.clang_args # Extract -check-prefix in FileCheck args filecheck_cmd = commands[-1] common.verify_filecheck_prefixes(filecheck_cmd) if not filecheck_cmd.startswith('FileCheck '): # Execute non-filechecked clang runline. exe = [ti.args.clang] + clang_args run_list.append((None, exe, None, None)) continue check_prefixes = [ item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd) for item in m.group(1).split(',') ] if not check_prefixes: check_prefixes = ['CHECK'] run_list.append( (check_prefixes, clang_args, commands[1:-1], triple_in_cmd)) # Execute clang, generate LLVM IR, and extract functions. # Store only filechecked runlines. filecheck_run_list = [i for i in run_list if i[0]] builder = common.FunctionTestBuilder(run_list=filecheck_run_list, flags=ti.args, scrubber_args=[], path=ti.path) for prefixes, args, extra_commands, triple_in_cmd in run_list: # Execute non-filechecked runline. if not prefixes: print('NOTE: Executing non-FileChecked RUN line: ' + ' '.join(args), file=sys.stderr) exec_run_line(args) continue clang_args = args common.debug('Extracted clang cmd: clang {}'.format(clang_args)) common.debug('Extracted FileCheck prefixes: {}'.format(prefixes)) get_function_body(builder, ti.args, ti.path, clang_args, extra_commands, prefixes) # Invoke clang -Xclang -ast-dump=json to get mapping from start lines to # mangled names. Forward all clang args for now. for k, v in get_line2func_list(ti.args, clang_args).items(): line2func_list[k].extend(v) func_dict = builder.finish_and_get_func_dict() global_vars_seen_dict = {} prefix_set = set( [prefix for p in filecheck_run_list for prefix in p[0]]) output_lines = [] has_checked_pre_function_globals = False include_generated_funcs = common.find_arg_in_test( ti, lambda args: ti.args.include_generated_funcs, '--include-generated-funcs', True) if include_generated_funcs: # Generate the appropriate checks for each function. We need to emit # these in the order according to the generated output so that CHECK-LABEL # works properly. func_order provides that. # It turns out that when clang generates functions (for example, with # -fopenmp), it can sometimes cause functions to be re-ordered in the # output, even functions that exist in the source file. Therefore we # can't insert check lines before each source function and instead have to # put them at the end. So the first thing to do is dump out the source # lines. common.dump_input_lines(output_lines, ti, prefix_set, '//') # Now generate all the checks. def check_generator(my_output_lines, prefixes, func): if '-emit-llvm' in clang_args: return common.add_ir_checks( my_output_lines, '//', prefixes, func_dict, func, False, ti.args.function_signature, global_vars_seen_dict, is_filtered=builder.is_filtered()) else: return asm.add_checks(my_output_lines, '//', prefixes, func_dict, func, global_vars_seen_dict, is_filtered=builder.is_filtered()) if ti.args.check_globals: common.add_global_checks(builder.global_var_dict(), '//', run_list, output_lines, global_vars_seen_dict, True, True) common.add_checks_at_end( output_lines, filecheck_run_list, builder.func_order(), '//', lambda my_output_lines, prefixes, func: check_generator( my_output_lines, prefixes, func)) else: # Normal mode. Put checks before each source function. for line_info in ti.iterlines(output_lines): idx = line_info.line_number line = line_info.line args = line_info.args include_line = True m = common.CHECK_RE.match(line) if m and m.group(1) in prefix_set: continue # Don't append the existing CHECK lines # Skip special separator comments added by commmon.add_global_checks. if line.strip() == '//' + common.SEPARATOR: continue if idx in line2func_list: added = set() for spell, mangled, search in line2func_list[idx]: # One line may contain multiple function declarations. # Skip if the mangled name has been added before. # The line number may come from an included file, we simply require # the search string (normally the function's spelling name, but is # the class's spelling name for class specializations) to appear on # the line to exclude functions from other files. if mangled in added or search not in line: continue if args.functions is None or any( re.search(regex, spell) for regex in args.functions): last_line = output_lines[-1].strip() while last_line == '//': # Remove the comment line since we will generate a new comment # line as part of common.add_ir_checks() output_lines.pop() last_line = output_lines[-1].strip() if ti.args.check_globals and not has_checked_pre_function_globals: common.add_global_checks( builder.global_var_dict(), '//', run_list, output_lines, global_vars_seen_dict, True, True) has_checked_pre_function_globals = True if added: output_lines.append('//') added.add(mangled) common.add_ir_checks( output_lines, '//', filecheck_run_list, func_dict, mangled, False, args.function_signature, global_vars_seen_dict, is_filtered=builder.is_filtered()) if line.rstrip('\n') == '//': include_line = False if include_line: output_lines.append(line.rstrip('\n')) if ti.args.check_globals: common.add_global_checks(builder.global_var_dict(), '//', run_list, output_lines, global_vars_seen_dict, True, False) common.debug('Writing %d lines to %s...' % (len(output_lines), ti.path)) with open(ti.path, 'wb') as f: f.writelines( ['{}\n'.format(l).encode('utf-8') for l in output_lines]) return 0
def get_line2func_list(args, clang_args): ret = collections.defaultdict(list) # Use clang's JSON AST dump to get the mangled name json_dump_args = [args.clang] + clang_args + ['-fsyntax-only', '-o', '-'] if '-cc1' not in json_dump_args: # For tests that invoke %clang instead if %clang_cc1 we have to use # -Xclang -ast-dump=json instead: json_dump_args.append('-Xclang') json_dump_args.append('-ast-dump=json') common.debug('Running', ' '.join(json_dump_args)) popen = subprocess.Popen(json_dump_args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True) stdout, stderr = popen.communicate() if popen.returncode != 0: sys.stderr.write('Failed to run ' + ' '.join(json_dump_args) + '\n') sys.stderr.write(stderr) sys.stderr.write(stdout) sys.exit(2) # Parse the clang JSON and add all children of type FunctionDecl. # TODO: Should we add checks for global variables being emitted? def parse_clang_ast_json(node, loc, search): node_kind = node['kind'] # Recurse for the following nodes that can contain nested function decls: if node_kind in ('NamespaceDecl', 'LinkageSpecDecl', 'TranslationUnitDecl', 'CXXRecordDecl', 'ClassTemplateSpecializationDecl'): # Specializations must use the loc from the specialization, not the # template, and search for the class's spelling as the specialization # does not mention the method names in the source. if node_kind == 'ClassTemplateSpecializationDecl': inner_loc = node['loc'] inner_search = node['name'] else: inner_loc = None inner_search = None if 'inner' in node: for inner in node['inner']: parse_clang_ast_json(inner, inner_loc, inner_search) # Otherwise we ignore everything except functions: if node_kind not in ('FunctionDecl', 'CXXMethodDecl', 'CXXConstructorDecl', 'CXXDestructorDecl', 'CXXConversionDecl'): return if loc is None: loc = node['loc'] if node.get('isImplicit') is True and node.get( 'storageClass') == 'extern': common.debug('Skipping builtin function:', node['name'], '@', loc) return common.debug('Found function:', node['kind'], node['name'], '@', loc) line = loc.get('line') # If there is no line it is probably a builtin function -> skip if line is None: common.debug('Skipping function without line number:', node['name'], '@', loc) return # If there is no 'inner' object, it is a function declaration and we can # skip it. However, function declarations may also contain an 'inner' list, # but in that case it will only contains ParmVarDecls. If we find an entry # that is not a ParmVarDecl, we know that this is a function definition. has_body = False if 'inner' in node: for i in node['inner']: if i.get('kind', 'ParmVarDecl') != 'ParmVarDecl': has_body = True break if not has_body: common.debug('Skipping function without body:', node['name'], '@', loc) return spell = node['name'] if search is None: search = spell mangled = node.get('mangledName', spell) ret[int(line) - 1].append((spell, mangled, search)) ast = json.loads(stdout) if ast['kind'] != 'TranslationUnitDecl': common.error('Clang AST dump JSON format changed?') sys.exit(2) parse_clang_ast_json(ast, None, None) for line, funcs in sorted(ret.items()): for func in funcs: common.debug('line {}: found function {}'.format(line + 1, func), file=sys.stderr) if not ret: common.warn('Did not find any functions using', ' '.join(json_dump_args)) return ret
def main(): from argparse import RawTextHelpFormatter parser = argparse.ArgumentParser(description=__doc__, formatter_class=RawTextHelpFormatter) parser.add_argument('--opt-binary', default='opt', help='The opt binary used to generate the test case') parser.add_argument('--function', help='The function in the test file to update') parser.add_argument('-p', '--preserve-names', action='store_true', help='Do not scrub IR names') parser.add_argument( '--function-signature', action='store_true', help='Keep function signature information around for the check line') parser.add_argument( '--scrub-attributes', action='store_true', help='Remove attribute annotations (#0) from the end of check line') parser.add_argument('tests', nargs='+') args = common.parse_commandline_args(parser) script_name = os.path.basename(__file__) autogenerated_note = (ADVERT + 'utils/' + script_name) opt_basename = os.path.basename(args.opt_binary) if not re.match(r'^opt(-\d+)?$', opt_basename): common.error('Unexpected opt name: ' + opt_basename) sys.exit(1) opt_basename = 'opt' for test in args.tests: if not glob.glob(test): common.warn("Test file pattern '%s' was not found. Ignoring it." % (test, )) continue # On Windows we must expand the patterns ourselves. test_paths = [ test for pattern in args.tests for test in glob.glob(pattern) ] for test in test_paths: with open(test) as f: input_lines = [l.rstrip() for l in f] first_line = input_lines[0] if input_lines else "" if 'autogenerated' in first_line and script_name not in first_line and not args.force_update: common.warn( "Skipping test which wasn't autogenerated by " + script_name, test) continue if args.update_only: if not first_line or 'autogenerated' not in first_line: common.warn("Skipping test which isn't autogenerated: " + test) continue run_lines = common.find_run_lines(test, input_lines) # If requested we scrub trailing attribute annotations, e.g., '#0', together with whitespaces if args.scrub_attributes: common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_AND_ATTRIBUTES_RE else: common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_RE prefix_list = [] for l in run_lines: if '|' not in l: common.warn('Skipping unparseable RUN line: ' + l) continue (tool_cmd, filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)]) if tool_cmd.startswith("%"): tool_cmd = tool_cmd.replace( "%cheri_purecap_opt", "opt -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128" ) tool_cmd = tool_cmd.replace( "%cheri128_purecap_opt", "opt -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128" ) tool_cmd = tool_cmd.replace( "%cheri256_purecap_opt", "opt -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri256 -mattr=+cheri256" ) tool_cmd = tool_cmd.replace( "%cheri_opt", "opt -mtriple=cheri-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128" ) tool_cmd = tool_cmd.replace( "%cheri128_opt", "opt -mtriple=cheri-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128" ) tool_cmd = tool_cmd.replace( "%cheri256_opt", "opt -mtriple=cheri-unknown-freebsd -mcpu=cheri256 -mattr=+cheri256" ) tool_cmd = tool_cmd.replace( "%riscv32_cheri_purecap_opt", "opt -mtriple=riscv32-unknown-freebsd -target-abi il32pc64 -mattr=+xcheri,+cap-mode" ) tool_cmd = tool_cmd.replace( "%riscv64_cheri_purecap_opt", "opt -mtriple=riscv64-unknown-freebsd -target-abi l64pc128 -mattr=+xcheri,+cap-mode" ) tool_cmd = tool_cmd.replace( "%riscv32_cheri_opt", "opt -mtriple=riscv32-unknown-freebsd -mattr=+xcheri") tool_cmd = tool_cmd.replace( "%riscv64_cheri_opt", "opt -mtriple=riscv64-unknown-freebsd -mattr=+xcheri") common.verify_filecheck_prefixes(filecheck_cmd) if not tool_cmd.startswith(opt_basename + ' '): common.warn('Skipping non-%s RUN line: %s' % (opt_basename, l)) continue if not filecheck_cmd.startswith('FileCheck '): common.warn('Skipping non-FileChecked RUN line: ' + l) continue tool_cmd_args = tool_cmd[len(opt_basename):].strip() tool_cmd_args = tool_cmd_args.replace('< %s', '').replace('%s', '').strip() check_prefixes = [ item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd) for item in m.group(1).split(',') ] if not check_prefixes: check_prefixes = ['CHECK'] # FIXME: We should use multiple check prefixes to common check lines. For # now, we just ignore all but the last. prefix_list.append((check_prefixes, tool_cmd_args)) func_dict = {} for prefixes, _ in prefix_list: for prefix in prefixes: func_dict.update({prefix: dict()}) for prefixes, opt_args in prefix_list: common.debug('Extracted opt cmd: ' + opt_basename + ' ' + opt_args) common.debug('Extracted FileCheck prefixes: ' + str(prefixes)) raw_tool_output = common.invoke_tool(args.opt_binary, opt_args, test) common.build_function_body_dictionary(common.OPT_FUNCTION_RE, common.scrub_body, [], raw_tool_output, prefixes, func_dict, args.verbose, args.function_signature) is_in_function = False is_in_function_start = False prefix_set = set( [prefix for prefixes, _ in prefix_list for prefix in prefixes]) common.debug('Rewriting FileCheck prefixes:', str(prefix_set)) output_lines = [] output_lines.append(autogenerated_note) for input_line in input_lines: if is_in_function_start: if input_line == '': continue if input_line.lstrip().startswith(';'): m = common.CHECK_RE.match(input_line) if not m or m.group(1) not in prefix_set: output_lines.append(input_line) continue # Print out the various check lines here. common.add_ir_checks(output_lines, ';', prefix_list, func_dict, func_name, args.preserve_names, args.function_signature) is_in_function_start = False if is_in_function: if common.should_add_line_to_output(input_line, prefix_set): # This input line of the function body will go as-is into the output. # Except make leading whitespace uniform: 2 spaces. input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub( r' ', input_line) output_lines.append(input_line) else: continue if input_line.strip() == '}': is_in_function = False continue # Discard any previous script advertising. if input_line.startswith(ADVERT): continue # If it's outside a function, it just gets copied to the output. output_lines.append(input_line) m = IR_FUNCTION_RE.match(input_line) if not m: continue func_name = m.group(1) if args.function is not None and func_name != args.function: # When filtering on a specific function, skip all others. continue is_in_function = is_in_function_start = True common.debug('Writing %d lines to %s...' % (len(output_lines), test)) with open(test, 'wb') as f: if args.verbose: sys.stderr.writelines(['{}\n'.format(l) for l in output_lines]) f.writelines( ['{}\n'.format(l).encode('utf-8') for l in output_lines])
def main(): initial_args, parser = config() script_name = os.path.basename(__file__) for ti in common.itertests(initial_args.tests, parser, 'utils/' + script_name, comment_prefix='//', argparse_callback=infer_dependent_args): # Build a list of clang command lines and check prefixes from RUN lines. run_list = [] line2spell_and_mangled_list = collections.defaultdict(list) for l in ti.run_lines: commands = [cmd.strip() for cmd in l.split('|')] triple_in_cmd = None m = common.TRIPLE_ARG_RE.search(commands[0]) if m: triple_in_cmd = m.groups()[0] # Apply %clang substitution rule, replace %s by `filename`, and append args.clang_args clang_args = shlex.split(commands[0]) if clang_args[0] not in SUBST: print('WARNING: Skipping non-clang RUN line: ' + l, file=sys.stderr) continue clang_args[0:1] = SUBST[clang_args[0]] clang_args = [ti.path if i == '%s' else i for i in clang_args] + ti.args.clang_args # Permit piping the output through opt if not (len(commands) == 2 or (len(commands) == 3 and commands[1].startswith('opt'))): print('WARNING: Skipping non-clang RUN line: ' + l, file=sys.stderr) # Extract -check-prefix in FileCheck args filecheck_cmd = commands[-1] common.verify_filecheck_prefixes(filecheck_cmd) if not filecheck_cmd.startswith('FileCheck '): print('WARNING: Skipping non-FileChecked RUN line: ' + l, file=sys.stderr) continue check_prefixes = [item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd) for item in m.group(1).split(',')] if not check_prefixes: check_prefixes = ['CHECK'] run_list.append((check_prefixes, clang_args, commands[1:-1], triple_in_cmd)) # Execute clang, generate LLVM IR, and extract functions. func_dict = {} func_order = {} for p in run_list: prefixes = p[0] for prefix in prefixes: func_dict.update({prefix: dict()}) func_order.update({prefix: []}) for prefixes, clang_args, extra_commands, triple_in_cmd in run_list: common.debug('Extracted clang cmd: clang {}'.format(clang_args)) common.debug('Extracted FileCheck prefixes: {}'.format(prefixes)) get_function_body(ti.args, ti.path, clang_args, extra_commands, prefixes, triple_in_cmd, func_dict, func_order) # Invoke clang -Xclang -ast-dump=json to get mapping from start lines to # mangled names. Forward all clang args for now. for k, v in get_line2spell_and_mangled(ti.args, clang_args).items(): line2spell_and_mangled_list[k].append(v) global_vars_seen_dict = {} prefix_set = set([prefix for p in run_list for prefix in p[0]]) output_lines = [] include_generated_funcs = common.find_arg_in_test(ti, lambda args: ti.args.include_generated_funcs, '--include-generated-funcs', True) if include_generated_funcs: # Generate the appropriate checks for each function. We need to emit # these in the order according to the generated output so that CHECK-LABEL # works properly. func_order provides that. # It turns out that when clang generates functions (for example, with # -fopenmp), it can sometimes cause functions to be re-ordered in the # output, even functions that exist in the source file. Therefore we # can't insert check lines before each source function and instead have to # put them at the end. So the first thing to do is dump out the source # lines. common.dump_input_lines(output_lines, ti, prefix_set, '//') # Now generate all the checks. def check_generator(my_output_lines, prefixes, func): if '-emit-llvm' in clang_args: common.add_ir_checks(my_output_lines, '//', prefixes, func_dict, func, False, ti.args.function_signature, global_vars_seen_dict) else: asm.add_asm_checks(my_output_lines, '//', prefixes, func_dict, func) common.add_checks_at_end(output_lines, run_list, func_order, '//', lambda my_output_lines, prefixes, func: check_generator(my_output_lines, prefixes, func)) else: # Normal mode. Put checks before each source function. for line_info in ti.iterlines(output_lines): idx = line_info.line_number line = line_info.line args = line_info.args include_line = True m = common.CHECK_RE.match(line) if m and m.group(1) in prefix_set: continue # Don't append the existing CHECK lines if idx in line2spell_and_mangled_list: added = set() for spell, mangled in line2spell_and_mangled_list[idx]: # One line may contain multiple function declarations. # Skip if the mangled name has been added before. # The line number may come from an included file, # we simply require the spelling name to appear on the line # to exclude functions from other files. if mangled in added or spell not in line: continue if args.functions is None or any(re.search(regex, spell) for regex in args.functions): last_line = output_lines[-1].strip() while last_line == '//': # Remove the comment line since we will generate a new comment # line as part of common.add_ir_checks() output_lines.pop() last_line = output_lines[-1].strip() if added: output_lines.append('//') added.add(mangled) common.add_ir_checks(output_lines, '//', run_list, func_dict, mangled, False, args.function_signature, global_vars_seen_dict) if line.rstrip('\n') == '//': include_line = False if include_line: output_lines.append(line.rstrip('\n')) common.debug('Writing %d lines to %s...' % (len(output_lines), ti.path)) with open(ti.path, 'wb') as f: f.writelines(['{}\n'.format(l).encode('utf-8') for l in output_lines]) return 0
def main(): parser = argparse.ArgumentParser(description=__doc__) parser.add_argument( '--llc-binary', default=None, help='The "llc" binary to use to generate the test case') parser.add_argument('--function', help='The function in the test file to update') parser.add_argument( '--extra_scrub', action='store_true', help= 'Always use additional regex to further reduce diffs between various subtargets' ) parser.add_argument( '--x86_scrub_sp', action='store_true', default=True, help= 'Use regex for x86 sp matching to reduce diffs between various subtargets' ) parser.add_argument('--no_x86_scrub_sp', action='store_false', dest='x86_scrub_sp') parser.add_argument( '--x86_scrub_rip', action='store_true', default=True, help= 'Use more regex for x86 rip matching to reduce diffs between various subtargets' ) parser.add_argument('--no_x86_scrub_rip', action='store_false', dest='x86_scrub_rip') parser.add_argument('--no_x86_scrub_mem_shuffle', action='store_true', default=False, help='Reduce scrubbing shuffles with memory operands') parser.add_argument('tests', nargs='+') initial_args = common.parse_commandline_args(parser) script_name = os.path.basename(__file__) for ti in common.itertests(initial_args.tests, parser, script_name='utils/' + script_name): triple_in_ir = None for l in ti.input_lines: m = common.TRIPLE_IR_RE.match(l) if m: triple_in_ir = m.groups()[0] break run_list = [] for l in ti.run_lines: if '|' not in l: common.warn('Skipping unparseable RUN line: ' + l) continue commands = [cmd.strip() for cmd in l.split('|')] assert len(commands) >= 2 preprocess_cmd = None if len(commands) > 2: preprocess_cmd = " | ".join(commands[:-2]) llc_cmd = commands[-2] filecheck_cmd = commands[-1] llc_tool = llc_cmd.split(' ')[0] triple_in_cmd = None m = common.TRIPLE_ARG_RE.search(llc_cmd) if m: triple_in_cmd = m.groups()[0] march_in_cmd = None m = common.MARCH_ARG_RE.search(llc_cmd) if m: march_in_cmd = m.groups()[0] common.verify_filecheck_prefixes(filecheck_cmd) if llc_tool not in LLC_LIKE_TOOLS: common.warn('Skipping non-llc RUN line: ' + l) continue if not filecheck_cmd.startswith('FileCheck '): common.warn('Skipping non-FileChecked RUN line: ' + l) continue llc_cmd_args = llc_cmd[len(llc_tool):].strip() llc_cmd_args = llc_cmd_args.replace('< %s', '').replace('%s', '').strip() if ti.path.endswith('.mir'): llc_cmd_args += ' -x mir' check_prefixes = [ item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd) for item in m.group(1).split(',') ] if not check_prefixes: check_prefixes = ['CHECK'] # FIXME: We should use multiple check prefixes to common check lines. For # now, we just ignore all but the last. run_list.append((check_prefixes, llc_tool, llc_cmd_args, preprocess_cmd, triple_in_cmd, march_in_cmd)) if ti.path.endswith('.mir'): check_indent = ' ' else: check_indent = '' builder = common.FunctionTestBuilder( run_list=run_list, flags=type( '', (object, ), { 'verbose': ti.args.verbose, 'function_signature': False, 'check_attributes': False, 'replace_value_regex': [] }), scrubber_args=[ti.args]) for prefixes, llc_tool, llc_args, preprocess_cmd, triple_in_cmd, march_in_cmd in run_list: common.debug('Extracted LLC cmd:', llc_tool, llc_args) common.debug('Extracted FileCheck prefixes:', str(prefixes)) raw_tool_output = common.invoke_tool(ti.args.llc_binary or llc_tool, llc_args, ti.path, preprocess_cmd, verbose=ti.args.verbose) triple = triple_in_cmd or triple_in_ir if not triple: triple = asm.get_triple_from_march(march_in_cmd) scrubber, function_re = asm.get_run_handler(triple) builder.process_run_line(function_re, scrubber, raw_tool_output, prefixes) func_dict = builder.finish_and_get_func_dict() is_in_function = False is_in_function_start = False func_name = None prefix_set = set([prefix for p in run_list for prefix in p[0]]) common.debug('Rewriting FileCheck prefixes:', str(prefix_set)) output_lines = [] include_generated_funcs = common.find_arg_in_test( ti, lambda args: ti.args.include_generated_funcs, '--include-generated-funcs', True) if include_generated_funcs: # Generate the appropriate checks for each function. We need to emit # these in the order according to the generated output so that CHECK-LABEL # works properly. func_order provides that. # We can't predict where various passes might insert functions so we can't # be sure the input function order is maintained. Therefore, first spit # out all the source lines. common.dump_input_lines(output_lines, ti, prefix_set, ';') # Now generate all the checks. common.add_checks_at_end( output_lines, run_list, builder.func_order(), check_indent + ';', lambda my_output_lines, prefixes, func: asm.add_asm_checks( my_output_lines, check_indent + ';', prefixes, func_dict, func)) else: for input_info in ti.iterlines(output_lines): input_line = input_info.line args = input_info.args if is_in_function_start: if input_line == '': continue if input_line.lstrip().startswith(';'): m = common.CHECK_RE.match(input_line) if not m or m.group(1) not in prefix_set: output_lines.append(input_line) continue # Print out the various check lines here. asm.add_asm_checks(output_lines, check_indent + ';', run_list, func_dict, func_name) is_in_function_start = False if is_in_function: if common.should_add_line_to_output( input_line, prefix_set): # This input line of the function body will go as-is into the output. output_lines.append(input_line) else: continue if input_line.strip() == '}': is_in_function = False continue # If it's outside a function, it just gets copied to the output. output_lines.append(input_line) m = common.IR_FUNCTION_RE.match(input_line) if not m: continue func_name = m.group(1) if args.function is not None and func_name != args.function: # When filtering on a specific function, skip all others. continue is_in_function = is_in_function_start = True common.debug('Writing %d lines to %s...' % (len(output_lines), ti.path)) with open(ti.path, 'wb') as f: f.writelines( ['{}\n'.format(l).encode('utf-8') for l in output_lines])
def main(): parser = argparse.ArgumentParser(description=__doc__) parser.add_argument('--llc-binary', default='llc', help='The "llc" binary to use to generate the test case') parser.add_argument( '--function', help='The function in the test file to update') parser.add_argument( '--extra_scrub', action='store_true', help='Always use additional regex to further reduce diffs between various subtargets') parser.add_argument( '--x86_scrub_rip', action='store_true', default=True, help='Use more regex for x86 matching to reduce diffs between various subtargets') parser.add_argument( '--no_x86_scrub_rip', action='store_false', dest='x86_scrub_rip') parser.add_argument('tests', nargs='+') args = common.parse_commandline_args(parser) script_name = os.path.basename(__file__) test_paths = [test for pattern in args.tests for test in glob.glob(pattern)] for test in test_paths: with open(test) as f: input_lines = [l.rstrip() for l in f] first_line = input_lines[0] if input_lines else "" if 'autogenerated' in first_line and script_name not in first_line: common.warn("Skipping test which wasn't autogenerated by " + script_name, test) continue if args.update_only: if not first_line or 'autogenerated' not in first_line: common.warn("Skipping test which isn't autogenerated: " + test) continue triple_in_ir = None for l in input_lines: m = common.TRIPLE_IR_RE.match(l) if m: triple_in_ir = m.groups()[0] break run_lines = common.find_run_lines(test, input_lines) run_list = [] for l in run_lines: if '|' not in l: common.warn('Skipping unparseable RUN line: ' + l) continue commands = [cmd.strip() for cmd in l.split('|', 2)] preprocess_cmd = None # Allow pre-preocessing test inputs with sed, etc. if len(commands) == 3: # TODO: allow other tools if commands[0].startswith("sed"): preprocess_cmd = commands[0] commands = commands[1:] else: common.warn('WARNING: Skipping RUN line with more than two commands and unknown first tool: ' + l) continue llc_cmd = commands[0] if llc_cmd.startswith("%"): llc_cmd = llc_cmd.replace("%cheri_purecap_llc", "llc -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128") llc_cmd = llc_cmd.replace("%cheri128_purecap_llc", "llc -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128") llc_cmd = llc_cmd.replace("%cheri256_purecap_llc", "llc -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri256 -mattr=+cheri256") llc_cmd = llc_cmd.replace("%cheri_llc", "llc -mtriple=cheri-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128") llc_cmd = llc_cmd.replace("%cheri128_llc", "llc -mtriple=cheri-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128") llc_cmd = llc_cmd.replace("%cheri256_llc", "llc -mtriple=cheri-unknown-freebsd -mcpu=cheri256 -mattr=+cheri256") llc_cmd = llc_cmd.replace("%riscv32_cheri_purecap_llc", "llc -mtriple=riscv32-unknown-freebsd -target-abi il32pc64 -mattr=+xcheri,+cap-mode") llc_cmd = llc_cmd.replace("%riscv64_cheri_purecap_llc", "llc -mtriple=riscv64-unknown-freebsd -target-abi l64pc128 -mattr=+xcheri,+cap-mode") llc_cmd = llc_cmd.replace("%riscv32_cheri_llc", "llc -mtriple=riscv32-unknown-freebsd -mattr=+xcheri") llc_cmd = llc_cmd.replace("%riscv64_cheri_llc", "llc -mtriple=riscv64-unknown-freebsd -mattr=+xcheri") llc_tool = llc_cmd.split(' ')[0] triple_in_cmd = None m = common.TRIPLE_ARG_RE.search(llc_cmd) if m: triple_in_cmd = m.groups()[0] march_in_cmd = None m = common.MARCH_ARG_RE.search(llc_cmd) if m: march_in_cmd = m.groups()[0] filecheck_cmd = '' if len(commands) > 1: filecheck_cmd = commands[1] if filecheck_cmd.startswith("%cheri_FileCheck"): filecheck_cmd = filecheck_cmd.replace("%cheri_FileCheck", "FileCheck '-D#CAP_SIZE=16'") common.verify_filecheck_prefixes(filecheck_cmd) if llc_tool != 'llc': common.warn('Skipping non-llc RUN line: ' + l) continue if not filecheck_cmd.startswith('FileCheck '): common.warn('Skipping non-FileChecked RUN line: ' + l) continue llc_cmd_args = llc_cmd[len(llc_tool):].strip() llc_cmd_args = llc_cmd_args.replace('< %s', '').replace('%s', '').strip() if test.endswith('.mir'): llc_cmd_args += ' -x mir' check_prefixes = [item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd) for item in m.group(1).split(',')] if not check_prefixes: check_prefixes = ['CHECK'] # FIXME: We should use multiple check prefixes to common check lines. For # now, we just ignore all but the last. run_list.append((check_prefixes, llc_cmd_args, triple_in_cmd, preprocess_cmd, march_in_cmd)) if test.endswith('.mir'): comment_sym = '#' check_indent = ' ' else: comment_sym = ';' check_indent = '' autogenerated_note = (comment_sym + ADVERT + 'utils/' + script_name) func_dict = {} for p in run_list: prefixes = p[0] for prefix in prefixes: func_dict.update({prefix: dict()}) for prefixes, llc_args, triple_in_cmd, preprocess_cmd, march_in_cmd in run_list: common.debug('Extracted LLC cmd:', llc_tool, llc_args) common.debug('Extracted FileCheck prefixes:', str(prefixes)) if preprocess_cmd: common.debug('Extracted pre-processing command: ' + str(preprocess_cmd)) raw_tool_output = common.invoke_tool(args.llc_binary, llc_args, test, preprocess_cmd) triple = triple_in_cmd or triple_in_ir if not triple: triple = asm.get_triple_from_march(march_in_cmd) asm.build_function_body_dictionary_for_triple(args, raw_tool_output, triple, prefixes, func_dict) is_in_function = False is_in_function_start = False func_name = None prefix_set = set([prefix for p in run_list for prefix in p[0]]) common.debug('Rewriting FileCheck prefixes:', str(prefix_set)) output_lines = [] output_lines.append(autogenerated_note) for input_line in input_lines: if is_in_function_start: if input_line == '': continue if input_line.lstrip().startswith(';'): m = common.CHECK_RE.match(input_line) if not m or m.group(1) not in prefix_set: output_lines.append(input_line) continue # Print out the various check lines here. asm.add_asm_checks(output_lines, check_indent + ';', run_list, func_dict, func_name) is_in_function_start = False if is_in_function: if common.should_add_line_to_output(input_line, prefix_set): # This input line of the function body will go as-is into the output. output_lines.append(input_line) else: continue if input_line.strip() == '}': is_in_function = False continue # Discard any previous script advertising. if input_line.startswith(comment_sym + ADVERT): continue # If it's outside a function, it just gets copied to the output. output_lines.append(input_line) m = common.IR_FUNCTION_RE.match(input_line) if not m: continue func_name = m.group(1) if args.function is not None and func_name != args.function: # When filtering on a specific function, skip all others. continue is_in_function = is_in_function_start = True common.debug('Writing %d lines to %s...' % (len(output_lines), test)) with open(test, 'wb') as f: f.writelines(['{}\n'.format(l).encode('utf-8') for l in output_lines])
def main(): from argparse import RawTextHelpFormatter parser = argparse.ArgumentParser(description=__doc__, formatter_class=RawTextHelpFormatter) parser.add_argument('--opt-binary', default='opt', help='The opt binary used to generate the test case') parser.add_argument('--function', help='The function in the test file to update') parser.add_argument('-p', '--preserve-names', action='store_true', help='Do not scrub IR names') parser.add_argument( '--function-signature', action='store_true', help='Keep function signature information around for the check line') parser.add_argument( '--scrub-attributes', action='store_true', help='Remove attribute annotations (#0) from the end of check line') parser.add_argument('tests', nargs='+') initial_args = common.parse_commandline_args(parser) script_name = os.path.basename(__file__) opt_basename = os.path.basename(initial_args.opt_binary) if not re.match(r'^opt(-\d+)?$', opt_basename): common.error('Unexpected opt name: ' + opt_basename) sys.exit(1) opt_basename = 'opt' for ti in common.itertests(initial_args.tests, parser, script_name='utils/' + script_name): # If requested we scrub trailing attribute annotations, e.g., '#0', together with whitespaces if ti.args.scrub_attributes: common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_AND_ATTRIBUTES_RE else: common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_RE prefix_list = [] for l in ti.run_lines: if '|' not in l: common.warn('Skipping unparseable RUN line: ' + l) continue (tool_cmd, filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)]) common.verify_filecheck_prefixes(filecheck_cmd) if not tool_cmd.startswith(opt_basename + ' '): common.warn('Skipping non-%s RUN line: %s' % (opt_basename, l)) continue if not filecheck_cmd.startswith('FileCheck '): common.warn('Skipping non-FileChecked RUN line: ' + l) continue tool_cmd_args = tool_cmd[len(opt_basename):].strip() tool_cmd_args = tool_cmd_args.replace('< %s', '').replace('%s', '').strip() check_prefixes = [ item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd) for item in m.group(1).split(',') ] if not check_prefixes: check_prefixes = ['CHECK'] # FIXME: We should use multiple check prefixes to common check lines. For # now, we just ignore all but the last. prefix_list.append((check_prefixes, tool_cmd_args)) func_dict = {} for prefixes, _ in prefix_list: for prefix in prefixes: func_dict.update({prefix: dict()}) for prefixes, opt_args in prefix_list: common.debug('Extracted opt cmd: ' + opt_basename + ' ' + opt_args) common.debug('Extracted FileCheck prefixes: ' + str(prefixes)) raw_tool_output = common.invoke_tool(ti.args.opt_binary, opt_args, ti.path) common.build_function_body_dictionary(common.OPT_FUNCTION_RE, common.scrub_body, [], raw_tool_output, prefixes, func_dict, ti.args.verbose, ti.args.function_signature) is_in_function = False is_in_function_start = False prefix_set = set( [prefix for prefixes, _ in prefix_list for prefix in prefixes]) common.debug('Rewriting FileCheck prefixes:', str(prefix_set)) output_lines = [] for input_line_info in ti.iterlines(output_lines): input_line = input_line_info.line args = input_line_info.args if is_in_function_start: if input_line == '': continue if input_line.lstrip().startswith(';'): m = common.CHECK_RE.match(input_line) if not m or m.group(1) not in prefix_set: output_lines.append(input_line) continue # Print out the various check lines here. common.add_ir_checks(output_lines, ';', prefix_list, func_dict, func_name, args.preserve_names, args.function_signature) is_in_function_start = False if is_in_function: if common.should_add_line_to_output(input_line, prefix_set): # This input line of the function body will go as-is into the output. # Except make leading whitespace uniform: 2 spaces. input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub( r' ', input_line) output_lines.append(input_line) else: continue if input_line.strip() == '}': is_in_function = False continue # If it's outside a function, it just gets copied to the output. output_lines.append(input_line) m = common.IR_FUNCTION_RE.match(input_line) if not m: continue func_name = m.group(1) if args.function is not None and func_name != args.function: # When filtering on a specific function, skip all others. continue is_in_function = is_in_function_start = True common.debug('Writing %d lines to %s...' % (len(output_lines), ti.path)) with open(ti.path, 'wb') as f: f.writelines( ['{}\n'.format(l).encode('utf-8') for l in output_lines])