dump-static-initializers: Add an option to show the size of static initializers, and change insta...

tools/linux/dump-static-initializers.py

Index: tools/linux/dump-static-initializers.py
===================================================================
--- tools/linux/dump-static-initializers.py	(revision 104532)
+++ tools/linux/dump-static-initializers.py	(working copy)
@@ -47,11 +47,26 @@
     return self.cppfilt.stdout.readline().strip()
 
 
-# Regex matching nm output for the symbols we're interested in.
-# Example line:
-#   0000000001919920 0000000000000008 b _ZN12_GLOBAL__N_119g_nine_box_prelightE
+# Regex matching nm output.
+# Example bss section symbol:
+#   0000000004021a20 0000000000000008 b  _ZGVZL16GetProcessLocalevE6locale
+bss_section_re = re.compile(r'\S+ \S+ b (.*)')
+def GetBSSFromNm(binary):
+  """Given a binary, return a set of symbols from the BSS section."""
+  bss_section = set()
+  nm = subprocess.Popen(['nm', '-S', binary], stdout=subprocess.PIPE)
+  for line in nm.stdout:
+    match = bss_section_re.match(line)
+    if match:
+      bss_section.add(match.groups()[0])
+  return bss_section
+
+
+# Regex matching nm output.
+# Example static initializer section line to yield:
+#   0000000001919920 0000000000000008 t _ZN12_GLOBAL__I_safe_browsing_service.cc
 nm_re = re.compile(r'(\S+) (\S+) t _GLOBAL__I_(.*)')
-def ParseNm(binary):
+def GetStaticInitializersFromNm(binary):
   """Given a binary, yield static initializers as (start, size, file) pairs."""
 
   nm = subprocess.Popen(['nm', '-S', binary], stdout=subprocess.PIPE)
@@ -98,37 +113,52 @@
   parser = optparse.OptionParser(usage='%prog filename')
   parser.add_option('-i', '--instances', dest='calculate_instances',
                     action='store_true', default=False,
-                    help='Only print out the number of static initializers')
+                    help='Only print out the number of files with '
+                         'static initializers')
+  parser.add_option('-I', '--show-instances', dest='show_instances',
+                    action='store_true', default=False,
+                    help='Only print out the static initializers without'
+                         'references')
   opts, args = parser.parse_args()
   if len(args) != 1:
     parser.error('missing filename argument')
     return 1
+  if opts.calculate_instances and opts.show_instances:
+    parser.error('-i and -I are mutually exclusive')
+    return 1
   binary = args[0]
 
   demangler = Demangler()
   static_initializers_count = 0
-  for addr, size, filename in ParseNm(binary):
+  if opts.calculate_instances or opts.show_instances:
+    bss_section = GetBSSFromNm(binary)
+
+  for addr, size, filename in GetStaticInitializersFromNm(binary):
     if size == 2:
       # gcc generates a two-byte 'repz retq' initializer when there is nothing
       # to do.  jyasskin tells me this is fixed in gcc 4.6.
       # Two bytes is too small to do anything, so just ignore it.
       continue
 
-    if (opts.calculate_instances):
-      static_initializers_count += 1
-      continue
+    if opts.calculate_instances:
+      for ref in ExtractSymbolReferences(binary, addr, addr+size):
+        if ref in bss_section:
+          static_initializers_count += 1
+    else:
+      print '%s (initializer offset 0x%x size 0x%x)' % (filename, addr, size)
+      for ref in ExtractSymbolReferences(binary, addr, addr+size):
+        if opts.show_instances and ref not in bss_section:
+          continue
+        ref = demangler.Demangle(ref)
+        if ref in NOTES:
+          print ' ', '%s [%s]' % (ref, NOTES[ref])
+        else:
+          print ' ', ref
+      print
 
-    print '%s (initializer offset 0x%x size 0x%x)' % (filename, addr, size)
-    for ref in ExtractSymbolReferences(binary, addr, addr+size):
-      ref = demangler.Demangle(ref)
-      if ref in NOTES:
-        print ' ', '%s [%s]' % (ref, NOTES[ref])
-      else:
-        print ' ', ref
-    print
-
   if opts.calculate_instances:
     print static_initializers_count
+
   return 0