--debug-profile: use msgpack instead of marshal by default

scripts/msgpack2marshal.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python3
+import marshal
+import sys
+
+import msgpack
+
+if len(sys.argv) not in (2, 3):
+    print('Synopsis:', sys.argv[0], '<msgpack input>', '[marshal output]', file=sys.stderr)
+    sys.exit(1)
+
+if len(sys.argv) == 2:
+    outfile = sys.stdout
+else:
+    outfile = open(sys.argv[2], 'wb')
+
+with outfile:
+    with open(sys.argv[1], 'rb') as infile:
+        marshal.dump(msgpack.unpack(infile, use_list=False, encoding='utf-8'), outfile)

src/borg/archiver.py

@@ -2050,7 +2050,8 @@ def define_common_options(add_common_option):
                               action='store_true', default=False,
                               help='treat part files like normal files (e.g. to list/extract them)')
             add_common_option('--debug-profile', dest='debug_profile', default=None, metavar='FILE',
-                              help='Store a Python profile at FILE')
+                              help='Write Python profile in msgpack format into FILE. For local use a cProfile-'
+                                   'compatible file can be generated by suffixing FILE with ".pyprof".')
 
         parser = argparse.ArgumentParser(prog=self.prog, description='Borg - Deduplicated Backups',
                                          add_help=False)
@@ -3545,7 +3546,7 @@ def run(self, args):
         if is_slow_msgpack():
             logger.warning("Using a pure-python msgpack! This will result in lower performance.")
         if args.debug_profile:
-            # Import these only when needed - avoids a further increase in startup time
+            # Import only when needed - avoids a further increase in startup time
             import cProfile
             import marshal
             logger.debug('Writing execution profile to %s', args.debug_profile)
@@ -3554,10 +3555,24 @@ def run(self, args):
             with open(args.debug_profile, 'wb') as fd:
                 profiler = cProfile.Profile()
                 variables = dict(locals())
-                profiler.runctx('rc = set_ec(func(args))', globals(), variables)
-                profiler.snapshot_stats()
-                marshal.dump(profiler.stats, fd)
-            return variables['rc']
+                profiler.enable()
+                try:
+                    return set_ec(func(args))
+                finally:
+                    profiler.disable()
+                    profiler.snapshot_stats()
+                    if args.debug_profile.endswith('.pyprof'):
+                        marshal.dump(profiler.stats, fd)
+                    else:
+                        # We use msgpack here instead of the marshal module used by cProfile itself,
+                        # because the latter is insecure. Since these files may be shared over the
+                        # internet we don't want a format that is impossible to interpret outside
+                        # an insecure implementation.
+                        # See scripts/msgpack2marshal.py for a small script that turns a msgpack file
+                        # into a marshal file that can be read by e.g. pyprof2calltree.
+                        # For local use it's unnecessary hassle, though, that's why .pyprof makes
+                        # it compatible (see above).
+                        msgpack.pack(profiler.stats, fd, use_bin_type=True)
         else:
             return set_ec(func(args))
 

src/borg/testsuite/archiver.py

@@ -1686,10 +1686,16 @@ def test_debug_profile(self):
         self.create_test_files()
         self.cmd('init', '--encryption=repokey', self.repository_location)
         self.cmd('create', self.repository_location + '::test', 'input', '--debug-profile=create.prof')
-        stats = pstats.Stats('create.prof')
+        stats = pstats.Stats()
+        with open('create.prof', 'rb') as fd:
+            stats.stats = msgpack.unpack(fd, use_list=False, encoding='utf-8')
+        stats.strip_dirs()
+        stats.sort_stats('cumtime')
+
+        self.cmd('create', self.repository_location + '::test2', 'input', '--debug-profile=create.pyprof')
+        stats = pstats.Stats('create.pyprof')  # Only do this on trusted data!
         stats.strip_dirs()
         stats.sort_stats('cumtime')
-        # Ok, stats can be loaded, good enough.
 
     def test_common_options(self):
         self.create_test_files()