llvm-mc: Start MCAssembler and MCMachOStreamer.

 - Together these form the (Mach-O) back end of the assembler.

 - MCAssembler is the actual assembler backend, which is designed to have a
   reasonable API. This will eventually grow to support multiple object file
   implementations, but for now its Mach-O/i386 only.

 - MCMachOStreamer adapts the MCStreamer "actions" API to the MCAssembler API,
   e.g. converting the various directives into fragments, managing state like
   the current section, and so on.

 - llvm-mc will use the new backend via '-filetype=obj', which may eventually
   be, but is not yet, since I hear that people like assemblers which actually
   assemble.

 - The only thing that works at the moment is changing sections. For the time
   being I have a Python Mach-O dumping tool in test/scripts so this stuff can
   be easily tested, eventually I expect to replace this with a real LLVM tool.

 - More doxyments to come.

I assume that since this stuff doesn't touch any of the things which are part of
2.6 that it is ok to put this in not so long before the freeze, but if someone
objects let me know, I can pull it.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@79612 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 159 insertions, 0 deletions

diff --git a/test/Scripts/macho-dump b/test/Scripts/macho-dump
new file mode 100755
index 0000000000..e844197a6c
--- /dev/null
+++ b/test/Scripts/macho-dump
@@ -0,0 +1,159 @@
+#!/usr/bin/env python
+
+import struct
+import sys
+
+class Reader:
+   def __init__(self, path):
+      if path == '-':
+         self.file = sys.stdin
+      else:
+         self.file = open(path,'rb')
+      self.isLSB = None
+      self.pos = 0
+
+   def setLSB(self, isLSB):
+      self.isLSB = bool(isLSB)
+
+   def tell(self):
+      return self.pos
+
+   def read(self, N):
+      data = self.file.read(N)
+      self.pos += len(data)
+      if len(data) != N:
+         raise ValueError,"Out of data!"
+      return data
+
+   def read32(self):
+      return struct.unpack('><'[self.isLSB] + 'I', self.read(4))[0]
+
+def dumpmacho(path, opts):
+   f = Reader(path)
+
+   magic = f.read(4)
+   if magic == '\xFE\xED\xFA\xCE':
+      f.setLSB(False)
+   elif magic == '\xCE\xFA\xED\xFE':
+      f.setLSB(True)
+   else:
+      raise ValueError,"Not a Mach-O object file: %r (bad magic)" % path
+
+   print "('cputype', %r)" % f.read32()
+   print "('cpusubtype', %r)" % f.read32()
+   filetype = f.read32()
+   print "('filetype', %r)" % filetype
+   
+   numLoadCommands = f.read32()
+   print "('num_load_commands', %r)" % filetype
+
+   loadCommandsSize = f.read32()
+   print "('load_commands_size', %r)" % loadCommandsSize
+
+   print "('flag', %r)" % f.read32()
+
+   start = f.tell()
+
+   print "('load_commands', ["
+   for i in range(numLoadCommands):
+      dumpLoadCommand(f, i, opts)
+   print "])"
+
+   if f.tell() - start != loadCommandsSize:
+      raise ValueError,"%s: warning: invalid load commands size: %r" % (sys.argv, loadCommandsSize)
+
+def dumpLoadCommand(f, i, opts):
+   start = f.tell()
+
+   print "  # Load Command %r" % i
+   cmd = f.read32()
+   print " (('command', %r)" % cmd
+   cmdSize = f.read32()
+   print "  ('size', %r)" % cmdSize
+
+   if cmd == 1:
+      dumpSegmentLoadCommand32(f, opts)
+   elif cmd == 2:
+      dumpSymtabCommand(f, opts)
+   elif cmd == 11:
+      dumpDysymtabCommand(f, opts)
+   else:
+      print >>sys.stderr,"%s: warning: unknown load command: %r" % (sys.argv[0], cmd)
+      f.read(cmdSize - 8)
+   print " ),"
+
+   if f.tell() - start != cmdSize:
+      raise ValueError,"%s: warning: invalid load command size: %r" % (sys.argv, cmdSize)
+
+def dumpSegmentLoadCommand32(f, opts):
+   print "  ('segment_name', %r)" % f.read(16) 
+   print "  ('vm_addr', %r)" % f.read32()
+   print "  ('vm_size', %r)" % f.read32()
+   print "  ('file_offset', %r)" % f.read32()
+   print "  ('file_size', %r)" % f.read32()
+   print "  ('maxprot', %r)" % f.read32()
+   print "  ('initprot', %r)" % f.read32()
+   numSections = f.read32()
+   print "  ('num_sections', %r)" % numSections
+   print "  ('flags', %r)" % f.read32()
+
+   print "  ('sections', ["
+   for i in range(numSections):
+      dumpSection32(f, i, opts)
+   print "  ])"
+
+def dumpSymtabCommand(f, opts):
+   print "  ('symoff', %r)" % f.read32()
+   print "  ('nsyms', %r)" % f.read32()
+   print "  ('stroff', %r)" % f.read32()
+   print "  ('strsize', %r)" % f.read32()
+
+def dumpDysymtabCommand(f, opts):   
+   print "  ('ilocalsym', %r)" % f.read32()
+   print "  ('nlocalsym', %r)" % f.read32()
+   print "  ('iextdefsym', %r)" % f.read32()
+   print "  ('nextdefsym', %r)" % f.read32()
+   print "  ('iundefsym', %r)" % f.read32()
+   print "  ('nundefsym', %r)" % f.read32()
+   print "  ('tocoff', %r)" % f.read32()
+   print "  ('ntoc', %r)" % f.read32()
+   print "  ('modtaboff', %r)" % f.read32()
+   print "  ('nmodtab', %r)" % f.read32()
+   print "  ('extrefsymoff', %r)" % f.read32()
+   print "  ('nextrefsyms', %r)" % f.read32()
+   print "  ('indirectsymoff', %r)" % f.read32()
+   print "  ('nindirectsyms', %r)" % f.read32()
+   print "  ('extreloff', %r)" % f.read32()
+   print "  ('nextrel', %r)" % f.read32()
+   print "  ('locreloff', %r)" % f.read32()
+   print "  ('nlocrel', %r)" % f.read32()
+
+def dumpSection32(f, i, opts):
+   print "    # Section %r" % i
+   print "   (('section_name', %r)" % f.read(16)
+   print "    ('segment_name', %r)" % f.read(16)
+   print "    ('address', %r)" % f.read32()
+   print "    ('size', %r)" % f.read32()
+   print "    ('offset', %r)" % f.read32()
+   print "    ('alignment', %r)" % f.read32()
+   print "    ('reloc_offset', %r)" % f.read32()
+   print "    ('num_reloc', %r)" % f.read32()
+   print "    ('flags', %#x)" % f.read32()
+   print "    ('reserved1', %r)" % f.read32()
+   print "    ('reserved2', %r)" % f.read32()
+   print "   ),"
+   
+def main():
+    from optparse import OptionParser, OptionGroup
+    parser = OptionParser("usage: %prog [options] {files}")
+
+    (opts, args) = parser.parse_args()
+
+    if not args:
+       args.append('-')
+
+    for arg in args:
+       dumpmacho(arg, opts)
+
+if __name__ == '__main__':
+   main()