gcc/gdbhooks.py

   1 # Python hooks for gdb for debugging GCC
   2 # Copyright (C) 2013-2014 Free Software Foundation, Inc.
   3
   4 # Contributed by David Malcolm <dmalcolm@redhat.com>
   5
   6 # This file is part of GCC.
   7
   8 # GCC is free software; you can redistribute it and/or modify it under
   9 # the terms of the GNU General Public License as published by the Free
  10 # Software Foundation; either version 3, or (at your option) any later
  11 # version.
  12
  13 # GCC is distributed in the hope that it will be useful, but WITHOUT
  14 # ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  15 # FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  16 # for more details.
  17
  18 # You should have received a copy of the GNU General Public License
  19 # along with GCC; see the file COPYING3.  If not see
  20 # <http://www.gnu.org/licenses/>.
  21
  22 """
  23 Enabling the debugging hooks
  24 ----------------------------
  25 gcc/configure (from configure.ac) generates a .gdbinit within the "gcc"
  26 subdirectory of the build directory, and when run by gdb, this imports
  27 gcc/gdbhooks.py from the source directory, injecting useful Python code
  28 into gdb.
  29
  30 You may see a message from gdb of the form:
  31   "path-to-build/gcc/.gdbinit" auto-loading has been declined by your `auto-load safe-path'
  32 as a protection against untrustworthy python scripts.  See
  33   http://sourceware.org/gdb/onlinedocs/gdb/Auto_002dloading-safe-path.html
  34
  35 The fix is to mark the paths of the build/gcc directory as trustworthy.
  36 An easy way to do so is by adding the following to your ~/.gdbinit script:
  37   add-auto-load-safe-path /absolute/path/to/build/gcc
  38 for the build directories for your various checkouts of gcc.
  39
  40 If it's working, you should see the message:
  41   Successfully loaded GDB hooks for GCC
  42 as gdb starts up.
  43
  44 During development, I've been manually invoking the code in this way, as a
  45 precanned way of printing a variety of different kinds of value:
  46
  47   gdb \
  48     -ex "break expand_gimple_stmt" \
  49     -ex "run" \
  50     -ex "bt" \
  51     --args \
  52       ./cc1 foo.c -O3
  53
  54 Examples of output using the pretty-printers
  55 --------------------------------------------
  56 Pointer values are generally shown in the form:
  57   <type address extra_info>
  58
  59 For example, an opt_pass* might appear as:
  60   (gdb) p pass
  61   $2 = <opt_pass* 0x188b600 "expand"(170)>
  62
  63 The name of the pass is given ("expand"), together with the
  64 static_pass_number.
  65
  66 Note that you can dereference the pointer in the normal way:
  67   (gdb) p *pass
  68   $4 = {type = RTL_PASS, name = 0x120a312 "expand",
  69   [etc, ...snipped...]
  70
  71 and you can suppress pretty-printers using /r (for "raw"):
  72   (gdb) p /r pass
  73   $3 = (opt_pass *) 0x188b600
  74
  75 Basic blocks are shown with their index in parentheses, apart from the
  76 CFG's entry and exit blocks, which are given as "ENTRY" and "EXIT":
  77   (gdb) p bb
  78   $9 = <basic_block 0x7ffff041f1a0 (2)>
  79   (gdb) p cfun->cfg->x_entry_block_ptr
  80   $10 = <basic_block 0x7ffff041f0d0 (ENTRY)>
  81   (gdb) p cfun->cfg->x_exit_block_ptr
  82   $11 = <basic_block 0x7ffff041f138 (EXIT)>
  83
  84 CFG edges are shown with the src and dest blocks given in parentheses:
  85   (gdb) p e
  86   $1 = <edge 0x7ffff043f118 (ENTRY -> 6)>
  87
  88 Tree nodes are printed using Python code that emulates print_node_brief,
  89 running in gdb, rather than in the inferior:
  90   (gdb) p cfun->decl
  91   $1 = <function_decl 0x7ffff0420b00 foo>
  92 For usability, the type is printed first (e.g. "function_decl"), rather
  93 than just "tree".
  94
  95 RTL expressions use a kludge: they are pretty-printed by injecting
  96 calls into print-rtl.c into the inferior:
  97   Value returned is $1 = (note 9 8 10 [bb 3] NOTE_INSN_BASIC_BLOCK)
  98   (gdb) p $1
  99   $2 = (note 9 8 10 [bb 3] NOTE_INSN_BASIC_BLOCK)
 100   (gdb) p /r $1
 101   $3 = (rtx_def *) 0x7ffff043e140
 102 This won't work for coredumps, and probably in other circumstances, but
 103 it's a quick way of getting lots of debuggability quickly.
 104
 105 Callgraph nodes are printed with the name of the function decl, if
 106 available:
 107   (gdb) frame 5
 108   #5  0x00000000006c288a in expand_function (node=<cgraph_node* 0x7ffff0312720 "foo">) at ../../src/gcc/cgraphunit.c:1594
 109   1594    execute_pass_list (g->get_passes ()->all_passes);
 110   (gdb) p node
 111   $1 = <cgraph_node* 0x7ffff0312720 "foo">
 112
 113 vec<> pointers are printed as the address followed by the elements in
 114 braces.  Here's a length 2 vec:
 115   (gdb) p bb->preds
 116   $18 = 0x7ffff0428b68 = {<edge 0x7ffff044d380 (3 -> 5)>, <edge 0x7ffff044d3b8 (4 -> 5)>}
 117
 118 and here's a length 1 vec:
 119   (gdb) p bb->succs
 120   $19 = 0x7ffff0428bb8 = {<edge 0x7ffff044d3f0 (5 -> EXIT)>}
 121
 122 You cannot yet use array notation [] to access the elements within the
 123 vector: attempting to do so instead gives you the vec itself (for vec[0]),
 124 or a (probably) invalid cast to vec<> for the memory after the vec (for
 125 vec[1] onwards).
 126
 127 Instead (for now) you must access m_vecdata:
 128   (gdb) p bb->preds->m_vecdata[0]
 129   $20 = <edge 0x7ffff044d380 (3 -> 5)>
 130   (gdb) p bb->preds->m_vecdata[1]
 131   $21 = <edge 0x7ffff044d3b8 (4 -> 5)>
 132 """
 133 import os.path
 134 import re
 135
 136 import gdb
 137 import gdb.printing
 138 import gdb.types
 139
 140 # Convert "enum tree_code" (tree.def and tree.h) to a dict:
 141 tree_code_dict = gdb.types.make_enum_dict(gdb.lookup_type('enum tree_code'))
 142
 143 # ...and look up specific values for use later:
 144 IDENTIFIER_NODE = tree_code_dict['IDENTIFIER_NODE']
 145 TYPE_DECL = tree_code_dict['TYPE_DECL']
 146
 147 # Similarly for "enum tree_code_class" (tree.h):
 148 tree_code_class_dict = gdb.types.make_enum_dict(gdb.lookup_type('enum tree_code_class'))
 149 tcc_type = tree_code_class_dict['tcc_type']
 150 tcc_declaration = tree_code_class_dict['tcc_declaration']
 151
 152 class Tree:
 153     """
 154     Wrapper around a gdb.Value for a tree, with various methods
 155     corresponding to macros in gcc/tree.h
 156     """
 157     def __init__(self, gdbval):
 158         self.gdbval = gdbval
 159
 160     def is_nonnull(self):
 161         return long(self.gdbval)
 162
 163     def TREE_CODE(self):
 164         """
 165         Get gdb.Value corresponding to TREE_CODE (self)
 166         as per:
 167           #define TREE_CODE(NODE) ((enum tree_code) (NODE)->base.code)
 168         """
 169         return self.gdbval['base']['code']
 170
 171     def DECL_NAME(self):
 172         """
 173         Get Tree instance corresponding to DECL_NAME (self)
 174         """
 175         return Tree(self.gdbval['decl_minimal']['name'])
 176
 177     def TYPE_NAME(self):
 178         """
 179         Get Tree instance corresponding to result of TYPE_NAME (self)
 180         """
 181         return Tree(self.gdbval['type_common']['name'])
 182
 183     def IDENTIFIER_POINTER(self):
 184         """
 185         Get str correspoinding to result of IDENTIFIER_NODE (self)
 186         """
 187         return self.gdbval['identifier']['id']['str'].string()
 188
 189 class TreePrinter:
 190     "Prints a tree"
 191
 192     def __init__ (self, gdbval):
 193         self.gdbval = gdbval
 194         self.node = Tree(gdbval)
 195
 196     def to_string (self):
 197         # like gcc/print-tree.c:print_node_brief
 198         # #define TREE_CODE(NODE) ((enum tree_code) (NODE)->base.code)
 199         # tree_code_name[(int) TREE_CODE (node)])
 200         if long(self.gdbval) == 0:
 201             return '<tree 0x0>'
 202
 203         val_TREE_CODE = self.node.TREE_CODE()
 204
 205         # extern const enum tree_code_class tree_code_type[];
 206         # #define TREE_CODE_CLASS(CODE) tree_code_type[(int) (CODE)]
 207
 208         val_tree_code_type = gdb.parse_and_eval('tree_code_type')
 209         val_tclass = val_tree_code_type[val_TREE_CODE]
 210
 211         val_tree_code_name = gdb.parse_and_eval('tree_code_name')
 212         val_code_name = val_tree_code_name[long(val_TREE_CODE)]
 213         #print val_code_name.string()
 214
 215         result = '<%s 0x%x' % (val_code_name.string(), long(self.gdbval))
 216         if long(val_tclass) == tcc_declaration:
 217             tree_DECL_NAME = self.node.DECL_NAME()
 218             if tree_DECL_NAME.is_nonnull():
 219                  result += ' %s' % tree_DECL_NAME.IDENTIFIER_POINTER()
 220             else:
 221                 pass # TODO: labels etc
 222         elif long(val_tclass) == tcc_type:
 223             tree_TYPE_NAME = Tree(self.gdbval['type_common']['name'])
 224             if tree_TYPE_NAME.is_nonnull():
 225                 if tree_TYPE_NAME.TREE_CODE() == IDENTIFIER_NODE:
 226                     result += ' %s' % tree_TYPE_NAME.IDENTIFIER_POINTER()
 227                 elif tree_TYPE_NAME.TREE_CODE() == TYPE_DECL:
 228                     if tree_TYPE_NAME.DECL_NAME().is_nonnull():
 229                         result += ' %s' % tree_TYPE_NAME.DECL_NAME().IDENTIFIER_POINTER()
 230         if self.node.TREE_CODE() == IDENTIFIER_NODE:
 231             result += ' %s' % self.node.IDENTIFIER_POINTER()
 232         # etc
 233         result += '>'
 234         return result
 235
 236 ######################################################################
 237 # Callgraph pretty-printers
 238 ######################################################################
 239
 240 class CGraphNodePrinter:
 241     def __init__(self, gdbval):
 242         self.gdbval = gdbval
 243
 244     def to_string (self):
 245         result = '<cgraph_node* 0x%x' % long(self.gdbval)
 246         if long(self.gdbval):
 247             # symtab_node::name calls lang_hooks.decl_printable_name
 248             # default implementation (lhd_decl_printable_name) is:
 249             #    return IDENTIFIER_POINTER (DECL_NAME (decl));
 250             tree_decl = Tree(self.gdbval['decl'])
 251             result += ' "%s"' % tree_decl.DECL_NAME().IDENTIFIER_POINTER()
 252         result += '>'
 253         return result
 254
 255 ######################################################################
 256
 257 class GimplePrinter:
 258     def __init__(self, gdbval):
 259         self.gdbval = gdbval
 260
 261     def to_string (self):
 262         if long(self.gdbval) == 0:
 263             return '<gimple 0x0>'
 264         val_gimple_code = self.gdbval['code']
 265         val_gimple_code_name = gdb.parse_and_eval('gimple_code_name')
 266         val_code_name = val_gimple_code_name[long(val_gimple_code)]
 267         result = '<%s 0x%x' % (val_code_name.string(),
 268                                long(self.gdbval))
 269         result += '>'
 270         return result
 271
 272 ######################################################################
 273 # CFG pretty-printers
 274 ######################################################################
 275
 276 def bb_index_to_str(index):
 277     if index == 0:
 278         return 'ENTRY'
 279     elif index == 1:
 280         return 'EXIT'
 281     else:
 282         return '%i' % index
 283
 284 class BasicBlockPrinter:
 285     def __init__(self, gdbval):
 286         self.gdbval = gdbval
 287
 288     def to_string (self):
 289         result = '<basic_block 0x%x' % long(self.gdbval)
 290         if long(self.gdbval):
 291             result += ' (%s)' % bb_index_to_str(long(self.gdbval['index']))
 292         result += '>'
 293         return result
 294
 295 class CfgEdgePrinter:
 296     def __init__(self, gdbval):
 297         self.gdbval = gdbval
 298
 299     def to_string (self):
 300         result = '<edge 0x%x' % long(self.gdbval)
 301         if long(self.gdbval):
 302             src = bb_index_to_str(long(self.gdbval['src']['index']))
 303             dest = bb_index_to_str(long(self.gdbval['dest']['index']))
 304             result += ' (%s -> %s)' % (src, dest)
 305         result += '>'
 306         return result
 307
 308 ######################################################################
 309
 310 class Rtx:
 311     def __init__(self, gdbval):
 312         self.gdbval = gdbval
 313
 314     def GET_CODE(self):
 315         return self.gdbval['code']
 316
 317 def GET_RTX_LENGTH(code):
 318     val_rtx_length = gdb.parse_and_eval('rtx_length')
 319     return long(val_rtx_length[code])
 320
 321 def GET_RTX_NAME(code):
 322     val_rtx_name = gdb.parse_and_eval('rtx_name')
 323     return val_rtx_name[code].string()
 324
 325 def GET_RTX_FORMAT(code):
 326     val_rtx_format = gdb.parse_and_eval('rtx_format')
 327     return val_rtx_format[code].string()
 328
 329 class RtxPrinter:
 330     def __init__(self, gdbval):
 331         self.gdbval = gdbval
 332         self.rtx = Rtx(gdbval)
 333
 334     def to_string (self):
 335         """
 336         For now, a cheap kludge: invoke the inferior's print
 337         function to get a string to use the user, and return an empty
 338         string for gdb
 339         """
 340         # We use print_inline_rtx to avoid a trailing newline
 341         gdb.execute('call print_inline_rtx (stderr, (const_rtx) %s, 0)'
 342                     % long(self.gdbval))
 343         return ''
 344
 345         # or by hand; based on gcc/print-rtl.c:print_rtx
 346         result = ('<rtx_def 0x%x'
 347                   % (long(self.gdbval)))
 348         code = self.rtx.GET_CODE()
 349         result += ' (%s' % GET_RTX_NAME(code)
 350         format_ = GET_RTX_FORMAT(code)
 351         for i in range(GET_RTX_LENGTH(code)):
 352             print format_[i]
 353         result += ')>'
 354         return result
 355
 356 ######################################################################
 357
 358 class PassPrinter:
 359     def __init__(self, gdbval):
 360         self.gdbval = gdbval
 361
 362     def to_string (self):
 363         result = '<opt_pass* 0x%x' % long(self.gdbval)
 364         if long(self.gdbval):
 365             result += (' "%s"(%i)'
 366                        % (self.gdbval['name'].string(),
 367                           long(self.gdbval['static_pass_number'])))
 368         result += '>'
 369         return result
 370
 371 ######################################################################
 372
 373 class VecPrinter:
 374     #    -ex "up" -ex "p bb->preds"
 375     def __init__(self, gdbval):
 376         self.gdbval = gdbval
 377
 378     def display_hint (self):
 379         return 'array'
 380
 381     def to_string (self):
 382         # A trivial implementation; prettyprinting the contents is done
 383         # by gdb calling the "children" method below.
 384         return '0x%x' % long(self.gdbval)
 385
 386     def children (self):
 387         if long(self.gdbval) == 0:
 388             return
 389         m_vecpfx = self.gdbval['m_vecpfx']
 390         m_num = m_vecpfx['m_num']
 391         m_vecdata = self.gdbval['m_vecdata']
 392         for i in range(m_num):
 393             yield ('[%d]' % i, m_vecdata[i])
 394
 395 ######################################################################
 396
 397 # TODO:
 398 #   * hashtab
 399 #   * location_t
 400
 401 class GdbSubprinter(gdb.printing.SubPrettyPrinter):
 402     def __init__(self, name, class_):
 403         super(GdbSubprinter, self).__init__(name)
 404         self.class_ = class_
 405
 406     def handles_type(self, str_type):
 407         raise NotImplementedError
 408
 409 class GdbSubprinterTypeList(GdbSubprinter):
 410     """
 411     A GdbSubprinter that handles a specific set of types
 412     """
 413     def __init__(self, str_types, name, class_):
 414         super(GdbSubprinterTypeList, self).__init__(name, class_)
 415         self.str_types = frozenset(str_types)
 416
 417     def handles_type(self, str_type):
 418         return str_type in self.str_types
 419
 420 class GdbSubprinterRegex(GdbSubprinter):
 421     """
 422     A GdbSubprinter that handles types that match a regex
 423     """
 424     def __init__(self, regex, name, class_):
 425         super(GdbSubprinterRegex, self).__init__(name, class_)
 426         self.regex = re.compile(regex)
 427
 428     def handles_type(self, str_type):
 429         return self.regex.match(str_type)
 430
 431 class GdbPrettyPrinters(gdb.printing.PrettyPrinter):
 432     def __init__(self, name):
 433         super(GdbPrettyPrinters, self).__init__(name, [])
 434
 435     def add_printer_for_types(self, name, class_, types):
 436         self.subprinters.append(GdbSubprinterTypeList(name, class_, types))
 437
 438     def add_printer_for_regex(self, name, class_, regex):
 439         self.subprinters.append(GdbSubprinterRegex(name, class_, regex))
 440
 441     def __call__(self, gdbval):
 442         type_ = gdbval.type.unqualified()
 443         str_type = str(type_)
 444         for printer in self.subprinters:
 445             if printer.enabled and printer.handles_type(str_type):
 446                 return printer.class_(gdbval)
 447
 448         # Couldn't find a pretty printer (or it was disabled):
 449         return None
 450
 451
 452 def build_pretty_printer():
 453     pp = GdbPrettyPrinters('gcc')
 454     pp.add_printer_for_types(['tree'],
 455                              'tree', TreePrinter)
 456     pp.add_printer_for_types(['cgraph_node *'],
 457                              'cgraph_node', CGraphNodePrinter)
 458     pp.add_printer_for_types(['gimple', 'gimple_statement_base *',
 459
 460                               # Keep this in the same order as gimple.def:
 461                               'gimple_cond', 'const_gimple_cond',
 462                               'gimple_statement_cond *',
 463                               'gimple_debug', 'const_gimple_debug',
 464                               'gimple_statement_debug *',
 465                               'gimple_label', 'const_gimple_label',
 466                               'gimple_statement_label *',
 467                               'gimple_switch', 'const_gimple_switch',
 468                               'gimple_statement_switch *',
 469                               'gimple_assign', 'const_gimple_assign',
 470                               'gimple_statement_assign *',
 471                               'gimple_bind', 'const_gimple_bind',
 472                               'gimple_statement_bind *',
 473                               'gimple_phi', 'const_gimple_phi',
 474                               'gimple_statement_phi *'],
 475
 476                              'gimple',
 477                              GimplePrinter)
 478     pp.add_printer_for_types(['basic_block', 'basic_block_def *'],
 479                              'basic_block',
 480                              BasicBlockPrinter)
 481     pp.add_printer_for_types(['edge', 'edge_def *'],
 482                              'edge',
 483                              CfgEdgePrinter)
 484     pp.add_printer_for_types(['rtx_def *'], 'rtx_def', RtxPrinter)
 485     pp.add_printer_for_types(['opt_pass *'], 'opt_pass', PassPrinter)
 486
 487     pp.add_printer_for_regex(r'vec<(\S+), (\S+), (\S+)> \*',
 488                              'vec',
 489                              VecPrinter)
 490
 491     return pp
 492
 493 gdb.printing.register_pretty_printer(
 494     gdb.current_objfile(),
 495     build_pretty_printer())
 496
 497 def find_gcc_source_dir():
 498     # Use location of global "g" to locate the source tree
 499     sym_g = gdb.lookup_global_symbol('g')
 500     path = sym_g.symtab.filename # e.g. '../../src/gcc/context.h'
 501     srcdir = os.path.split(path)[0] # e.g. '../../src/gcc'
 502     return srcdir
 503
 504 class PassNames:
 505     """Parse passes.def, gathering a list of pass class names"""
 506     def __init__(self):
 507         srcdir = find_gcc_source_dir()
 508         self.names = []
 509         with open(os.path.join(srcdir, 'passes.def')) as f:
 510             for line in f:
 511                 m = re.match('\s*NEXT_PASS \((.+)\);', line)
 512                 if m:
 513                     self.names.append(m.group(1))
 514
 515 class BreakOnPass(gdb.Command):
 516     """
 517     A custom command for putting breakpoints on the execute hook of passes.
 518     This is largely a workaround for issues with tab-completion in gdb when
 519     setting breakpoints on methods on classes within anonymous namespaces.
 520
 521     Example of use: putting a breakpoint on "final"
 522       (gdb) break-on-pass
 523     Press <TAB>; it autocompletes to "pass_":
 524       (gdb) break-on-pass pass_
 525     Press <TAB>:
 526       Display all 219 possibilities? (y or n)
 527     Press "n"; then type "f":
 528       (gdb) break-on-pass pass_f
 529     Press <TAB> to autocomplete to pass classnames beginning with "pass_f":
 530       pass_fast_rtl_dce              pass_fold_builtins
 531       pass_feedback_split_functions  pass_forwprop
 532       pass_final                     pass_fre
 533       pass_fixup_cfg                 pass_free_cfg
 534     Type "in<TAB>" to complete to "pass_final":
 535       (gdb) break-on-pass pass_final
 536     ...and hit <RETURN>:
 537       Breakpoint 6 at 0x8396ba: file ../../src/gcc/final.c, line 4526.
 538     ...and we have a breakpoint set; continue execution:
 539       (gdb) cont
 540       Continuing.
 541       Breakpoint 6, (anonymous namespace)::pass_final::execute (this=0x17fb990) at ../../src/gcc/final.c:4526
 542       4526        virtual unsigned int execute (function *) { return rest_of_handle_final (); }
 543     """
 544     def __init__(self):
 545         gdb.Command.__init__(self, 'break-on-pass', gdb.COMMAND_BREAKPOINTS)
 546         self.pass_names = None
 547
 548     def complete(self, text, word):
 549         # Lazily load pass names:
 550         if not self.pass_names:
 551             self.pass_names = PassNames()
 552
 553         return [name
 554                 for name in sorted(self.pass_names.names)
 555                 if name.startswith(text)]
 556
 557     def invoke(self, arg, from_tty):
 558         sym = '(anonymous namespace)::%s::execute' % arg
 559         breakpoint = gdb.Breakpoint(sym)
 560
 561 BreakOnPass()
 562
 563 print('Successfully loaded GDB hooks for GCC')