2 files changed, 328 insertions, 0 deletions
diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py
new file mode 100755
index 000000000000..e4fb686dfaa9
--- /dev/null
+++ b/scripts/clang-tools/gen_compile_commands.py
@@ -0,0 +1,228 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) Google LLC, 2018
+#
+# Author: Tom Roeder <tmroeder@google.com>
+#
+"""A tool for generating compile_commands.json in the Linux kernel."""
+
+import argparse
+import json
+import logging
+import os
+import re
+import subprocess
+import sys
+
+_DEFAULT_OUTPUT = 'compile_commands.json'
+_DEFAULT_LOG_LEVEL = 'WARNING'
+
+_FILENAME_PATTERN = r'^\..*\.cmd$'
+_LINE_PATTERN = r'^(saved)?cmd_[^ ]*\.o := (?P<command_prefix>.* )(?P<file_path>[^ ]*\.[cS]) *(;|$)'
+_VALID_LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
+# The tools/ directory adopts a different build system, and produces .cmd
+# files in a different format. Do not support it.
+_EXCLUDE_DIRS = ['.git', 'Documentation', 'include', 'tools']
+
+def parse_arguments():
+    """Sets up and parses command-line arguments.
+
+    Returns:
+        log_level: A logging level to filter log output.
+        directory: The work directory where the objects were built.
+        ar: Command used for parsing .a archives.
+        output: Where to write the compile-commands JSON file.
+        paths: The list of files/directories to handle to find .cmd files.
+    """
+    usage = 'Creates a compile_commands.json database from kernel .cmd files'
+    parser = argparse.ArgumentParser(description=usage)
+
+    directory_help = ('specify the output directory used for the kernel build '
+                      '(defaults to the working directory)')
+    parser.add_argument('-d', '--directory', type=str, default='.',
+                        help=directory_help)
+
+    output_help = ('path to the output command database (defaults to ' +
+                   _DEFAULT_OUTPUT + ')')
+    parser.add_argument('-o', '--output', type=str, default=_DEFAULT_OUTPUT,
+                        help=output_help)
+
+    log_level_help = ('the level of log messages to produce (defaults to ' +
+                      _DEFAULT_LOG_LEVEL + ')')
+    parser.add_argument('--log_level', choices=_VALID_LOG_LEVELS,
+                        default=_DEFAULT_LOG_LEVEL, help=log_level_help)
+
+    ar_help = 'command used for parsing .a archives'
+    parser.add_argument('-a', '--ar', type=str, default='llvm-ar', help=ar_help)
+
+    paths_help = ('directories to search or files to parse '
+                  '(files should be *.o, *.a, or modules.order). '
+                  'If nothing is specified, the current directory is searched')
+    parser.add_argument('paths', type=str, nargs='*', help=paths_help)
+
+    args = parser.parse_args()
+
+    return (args.log_level,
+            os.path.realpath(args.directory),
+            args.output,
+            args.ar,
+            args.paths if len(args.paths) > 0 else [args.directory])
+
+
+def cmdfiles_in_dir(directory):
+    """Generate the iterator of .cmd files found under the directory.
+
+    Walk under the given directory, and yield every .cmd file found.
+
+    Args:
+        directory: The directory to search for .cmd files.
+
+    Yields:
+        The path to a .cmd file.
+    """
+
+    filename_matcher = re.compile(_FILENAME_PATTERN)
+    exclude_dirs = [ os.path.join(directory, d) for d in _EXCLUDE_DIRS ]
+
+    for dirpath, dirnames, filenames in os.walk(directory, topdown=True):
+        # Prune unwanted directories.
+        if dirpath in exclude_dirs:
+            dirnames[:] = []
+            continue
+
+        for filename in filenames:
+            if filename_matcher.match(filename):
+                yield os.path.join(dirpath, filename)
+
+
+def to_cmdfile(path):
+    """Return the path of .cmd file used for the given build artifact
+
+    Args:
+        Path: file path
+
+    Returns:
+        The path to .cmd file
+    """
+    dir, base = os.path.split(path)
+    return os.path.join(dir, '.' + base + '.cmd')
+
+
+def cmdfiles_for_a(archive, ar):
+    """Generate the iterator of .cmd files associated with the archive.
+
+    Parse the given archive, and yield every .cmd file used to build it.
+
+    Args:
+        archive: The archive to parse
+
+    Yields:
+        The path to every .cmd file found
+    """
+    for obj in subprocess.check_output([ar, '-t', archive]).decode().split():
+        yield to_cmdfile(obj)
+
+
+def cmdfiles_for_modorder(modorder):
+    """Generate the iterator of .cmd files associated with the modules.order.
+
+    Parse the given modules.order, and yield every .cmd file used to build the
+    contained modules.
+
+    Args:
+        modorder: The modules.order file to parse
+
+    Yields:
+        The path to every .cmd file found
+    """
+    with open(modorder) as f:
+        for line in f:
+            obj = line.rstrip()
+            base, ext = os.path.splitext(obj)
+            if ext != '.o':
+                sys.exit('{}: module path must end with .o'.format(obj))
+            mod = base + '.mod'
+            # Read from *.mod, to get a list of objects that compose the module.
+            with open(mod) as m:
+                for mod_line in m:
+                    yield to_cmdfile(mod_line.rstrip())
+
+
+def process_line(root_directory, command_prefix, file_path):
+    """Extracts information from a .cmd line and creates an entry from it.
+
+    Args:
+        root_directory: The directory that was searched for .cmd files. Usually
+            used directly in the "directory" entry in compile_commands.json.
+        command_prefix: The extracted command line, up to the last element.
+        file_path: The .c file from the end of the extracted command.
+            Usually relative to root_directory, but sometimes absolute.
+
+    Returns:
+        An entry to append to compile_commands.
+
+    Raises:
+        ValueError: Could not find the extracted file based on file_path and
+            root_directory or file_directory.
+    """
+    # The .cmd files are intended to be included directly by Make, so they
+    # escape the pound sign '#', either as '\#' or '$(pound)' (depending on the
+    # kernel version). The compile_commands.json file is not interepreted
+    # by Make, so this code replaces the escaped version with '#'.
+    prefix = command_prefix.replace(r'\#', '#').replace('$(pound)', '#')
+
+    # Return the canonical path, eliminating any symbolic links encountered in the path.
+    abs_path = os.path.realpath(os.path.join(root_directory, file_path))
+    if not os.path.exists(abs_path):
+        raise ValueError('File %s not found' % abs_path)
+    return {
+        'directory': root_directory,
+        'file': abs_path,
+        'command': prefix + file_path,
+    }
+
+
+def main():
+    """Walks through the directory and finds and parses .cmd files."""
+    log_level, directory, output, ar, paths = parse_arguments()
+
+    level = getattr(logging, log_level)
+    logging.basicConfig(format='%(levelname)s: %(message)s', level=level)
+
+    line_matcher = re.compile(_LINE_PATTERN)
+
+    compile_commands = []
+
+    for path in paths:
+        # If 'path' is a directory, handle all .cmd files under it.
+        # Otherwise, handle .cmd files associated with the file.
+        # built-in objects are linked via vmlinux.a
+        # Modules are listed in modules.order.
+        if os.path.isdir(path):
+            cmdfiles = cmdfiles_in_dir(path)
+        elif path.endswith('.a'):
+            cmdfiles = cmdfiles_for_a(path, ar)
+        elif path.endswith('modules.order'):
+            cmdfiles = cmdfiles_for_modorder(path)
+        else:
+            sys.exit('{}: unknown file type'.format(path))
+
+        for cmdfile in cmdfiles:
+            with open(cmdfile, 'rt') as f:
+                result = line_matcher.match(f.readline())
+                if result:
+                    try:
+                        entry = process_line(directory, result.group('command_prefix'),
+                                             result.group('file_path'))
+                        compile_commands.append(entry)
+                    except ValueError as err:
+                        logging.info('Could not add line from %s: %s',
+                                     cmdfile, err)
+
+    with open(output, 'wt') as f:
+        json.dump(sorted(compile_commands, key=lambda x: x["file"]), f, indent=2, sort_keys=True)
+
+
+if __name__ == '__main__':
+    main()
diff --git a/scripts/clang-tools/run-clang-tools.py b/scripts/clang-tools/run-clang-tools.py
new file mode 100755
index 000000000000..f31ffd09e1ea
--- /dev/null
+++ b/scripts/clang-tools/run-clang-tools.py
@@ -0,0 +1,100 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) Google LLC, 2020
+#
+# Author: Nathan Huckleberry <nhuck@google.com>
+#
+"""A helper routine run clang-tidy and the clang static-analyzer on
+compile_commands.json.
+"""
+
+import argparse
+import json
+import multiprocessing
+import subprocess
+import sys
+
+
+def parse_arguments():
+    """Set up and parses command-line arguments.
+    Returns:
+        args: Dict of parsed args
+        Has keys: [path, type]
+    """
+    usage = """Run clang-tidy or the clang static-analyzer on a
+        compilation database."""
+    parser = argparse.ArgumentParser(description=usage)
+
+    type_help = "Type of analysis to be performed"
+    parser.add_argument("type",
+                        choices=["clang-tidy", "clang-analyzer"],
+                        help=type_help)
+    path_help = "Path to the compilation database to parse"
+    parser.add_argument("path", type=str, help=path_help)
+
+    checks_help = "Checks to pass to the analysis"
+    parser.add_argument("-checks", type=str, default=None, help=checks_help)
+    header_filter_help = "Pass the -header-filter value to the tool"
+    parser.add_argument("-header-filter", type=str, default=None, help=header_filter_help)
+
+    return parser.parse_args()
+
+
+def init(l, a):
+    global lock
+    global args
+    lock = l
+    args = a
+
+
+def run_analysis(entry):
+    # Disable all checks, then re-enable the ones we want
+    global args
+    checks = None
+    if args.checks:
+        checks = args.checks.split(',')
+    else:
+        checks = ["-*"]
+        if args.type == "clang-tidy":
+            checks.append("linuxkernel-*")
+        else:
+            checks.append("clang-analyzer-*")
+            checks.append("-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling")
+    file = entry["file"]
+    if not file.endswith(".c") and not file.endswith(".cpp"):
+        with lock:
+            print(f"Skipping non-C file: '{file}'", file=sys.stderr)
+        return
+    pargs = ["clang-tidy", "-p", args.path, "-checks=" + ",".join(checks)]
+    if args.header_filter:
+        pargs.append("-header-filter=" + args.header_filter)
+    pargs.append(file)
+    p = subprocess.run(pargs,
+                       stdout=subprocess.PIPE,
+                       stderr=subprocess.STDOUT,
+                       cwd=entry["directory"])
+    with lock:
+        sys.stderr.buffer.write(p.stdout)
+
+
+def main():
+    try:
+        args = parse_arguments()
+
+        lock = multiprocessing.Lock()
+        pool = multiprocessing.Pool(initializer=init, initargs=(lock, args))
+        # Read JSON data into the datastore variable
+        with open(args.path, "r") as f:
+            datastore = json.load(f)
+            pool.map(run_analysis, datastore)
+    except BrokenPipeError:
+        # Python flushes standard streams on exit; redirect remaining output
+        # to devnull to avoid another BrokenPipeError at shutdown
+        devnull = os.open(os.devnull, os.O_WRONLY)
+        os.dup2(devnull, sys.stdout.fileno())
+        sys.exit(1)  # Python exits with error code 1 on EPIPE
+
+
+if __name__ == "__main__":
+    main()