gcc/gdbhooks.py

   1 # Python hooks for gdb for debugging GCC
   2 # Copyright (C) 2013-2015 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 import sys
 136
 137 import gdb
 138 import gdb.printing
 139 import gdb.types
 140
 141 # Convert "enum tree_code" (tree.def and tree.h) to a dict:
 142 tree_code_dict = gdb.types.make_enum_dict(gdb.lookup_type('enum tree_code'))
 143
 144 # ...and look up specific values for use later:
 145 IDENTIFIER_NODE = tree_code_dict['IDENTIFIER_NODE']
 146 TYPE_DECL = tree_code_dict['TYPE_DECL']
 147
 148 # Similarly for "enum tree_code_class" (tree.h):
 149 tree_code_class_dict = gdb.types.make_enum_dict(gdb.lookup_type('enum tree_code_class'))
 150 tcc_type = tree_code_class_dict['tcc_type']
 151 tcc_declaration = tree_code_class_dict['tcc_declaration']
 152
 153 # Python3 has int() with arbitrary precision (bignum).  Python2 int() is 32-bit
 154 # on 32-bit hosts but remote targets may have 64-bit pointers there; Python2
 155 # long() is always 64-bit but Python3 no longer has anything named long.
 156 def intptr(gdbval):
 157     return long(gdbval) if sys.version_info.major == 2 else int(gdbval)
 158
 159 class Tree:
 160     """
 161     Wrapper around a gdb.Value for a tree, with various methods
 162     corresponding to macros in gcc/tree.h
 163     """
 164     def __init__(self, gdbval):
 165         self.gdbval = gdbval
 166
 167     def is_nonnull(self):
 168         return intptr(self.gdbval)
 169
 170     def TREE_CODE(self):
 171         """
 172         Get gdb.Value corresponding to TREE_CODE (self)
 173         as per:
 174           #define TREE_CODE(NODE) ((enum tree_code) (NODE)->base.code)
 175         """
 176         return self.gdbval['base']['code']
 177
 178     def DECL_NAME(self):
 179         """
 180         Get Tree instance corresponding to DECL_NAME (self)
 181         """
 182         return Tree(self.gdbval['decl_minimal']['name'])
 183
 184     def TYPE_NAME(self):
 185         """
 186         Get Tree instance corresponding to result of TYPE_NAME (self)
 187         """
 188         return Tree(self.gdbval['type_common']['name'])
 189
 190     def IDENTIFIER_POINTER(self):
 191         """
 192         Get str correspoinding to result of IDENTIFIER_NODE (self)
 193         """
 194         return self.gdbval['identifier']['id']['str'].string()
 195
 196 class TreePrinter:
 197     "Prints a tree"
 198
 199     def __init__ (self, gdbval):
 200         self.gdbval = gdbval
 201         self.node = Tree(gdbval)
 202
 203     def to_string (self):
 204         # like gcc/print-tree.c:print_node_brief
 205         # #define TREE_CODE(NODE) ((enum tree_code) (NODE)->base.code)
 206         # tree_code_name[(int) TREE_CODE (node)])
 207         if intptr(self.gdbval) == 0:
 208             return '<tree 0x0>'
 209
 210         val_TREE_CODE = self.node.TREE_CODE()
 211
 212         # extern const enum tree_code_class tree_code_type[];
 213         # #define TREE_CODE_CLASS(CODE) tree_code_type[(int) (CODE)]
 214
 215         val_tree_code_type = gdb.parse_and_eval('tree_code_type')
 216         val_tclass = val_tree_code_type[val_TREE_CODE]
 217
 218         val_tree_code_name = gdb.parse_and_eval('tree_code_name')
 219         val_code_name = val_tree_code_name[intptr(val_TREE_CODE)]
 220         #print(val_code_name.string())
 221
 222         result = '<%s 0x%x' % (val_code_name.string(), intptr(self.gdbval))
 223         if intptr(val_tclass) == tcc_declaration:
 224             tree_DECL_NAME = self.node.DECL_NAME()
 225             if tree_DECL_NAME.is_nonnull():
 226                  result += ' %s' % tree_DECL_NAME.IDENTIFIER_POINTER()
 227             else:
 228                 pass # TODO: labels etc
 229         elif intptr(val_tclass) == tcc_type:
 230             tree_TYPE_NAME = Tree(self.gdbval['type_common']['name'])
 231             if tree_TYPE_NAME.is_nonnull():
 232                 if tree_TYPE_NAME.TREE_CODE() == IDENTIFIER_NODE:
 233                     result += ' %s' % tree_TYPE_NAME.IDENTIFIER_POINTER()
 234                 elif tree_TYPE_NAME.TREE_CODE() == TYPE_DECL:
 235                     if tree_TYPE_NAME.DECL_NAME().is_nonnull():
 236                         result += ' %s' % tree_TYPE_NAME.DECL_NAME().IDENTIFIER_POINTER()
 237         if self.node.TREE_CODE() == IDENTIFIER_NODE:
 238             result += ' %s' % self.node.IDENTIFIER_POINTER()
 239         # etc
 240         result += '>'
 241         return result
 242
 243 ######################################################################
 244 # Callgraph pretty-printers
 245 ######################################################################
 246
 247 class CGraphNodePrinter:
 248     def __init__(self, gdbval):
 249         self.gdbval = gdbval
 250
 251     def to_string (self):
 252         result = '<cgraph_node* 0x%x' % intptr(self.gdbval)
 253         if intptr(self.gdbval):
 254             # symtab_node::name calls lang_hooks.decl_printable_name
 255             # default implementation (lhd_decl_printable_name) is:
 256             #    return IDENTIFIER_POINTER (DECL_NAME (decl));
 257             tree_decl = Tree(self.gdbval['decl'])
 258             result += ' "%s"' % tree_decl.DECL_NAME().IDENTIFIER_POINTER()
 259         result += '>'
 260         return result
 261
 262 ######################################################################
 263 # Dwarf DIE pretty-printers
 264 ######################################################################
 265
 266 class DWDieRefPrinter:
 267     def __init__(self, gdbval):
 268         self.gdbval = gdbval
 269
 270     def to_string (self):
 271         if intptr(self.gdbval) == 0:
 272             return '<dw_die_ref 0x0>'
 273         result = '<dw_die_ref 0x%x' % intptr(self.gdbval)
 274         result += ' %s' % self.gdbval['die_tag']
 275         if intptr(self.gdbval['die_parent']) != 0:
 276             result += ' <parent=0x%x %s>' % (intptr(self.gdbval['die_parent']),
 277                                              self.gdbval['die_parent']['die_tag'])
 278
 279         result += '>'
 280         return result
 281
 282 ######################################################################
 283
 284 class GimplePrinter:
 285     def __init__(self, gdbval):
 286         self.gdbval = gdbval
 287
 288     def to_string (self):
 289         if intptr(self.gdbval) == 0:
 290             return '<gimple 0x0>'
 291         val_gimple_code = self.gdbval['code']
 292         val_gimple_code_name = gdb.parse_and_eval('gimple_code_name')
 293         val_code_name = val_gimple_code_name[intptr(val_gimple_code)]
 294         result = '<%s 0x%x' % (val_code_name.string(),
 295                                intptr(self.gdbval))
 296         result += '>'
 297         return result
 298
 299 ######################################################################
 300 # CFG pretty-printers
 301 ######################################################################
 302
 303 def bb_index_to_str(index):
 304     if index == 0:
 305         return 'ENTRY'
 306     elif index == 1:
 307         return 'EXIT'
 308     else:
 309         return '%i' % index
 310
 311 class BasicBlockPrinter:
 312     def __init__(self, gdbval):
 313         self.gdbval = gdbval
 314
 315     def to_string (self):
 316         result = '<basic_block 0x%x' % intptr(self.gdbval)
 317         if intptr(self.gdbval):
 318             result += ' (%s)' % bb_index_to_str(intptr(self.gdbval['index']))
 319         result += '>'
 320         return result
 321
 322 class CfgEdgePrinter:
 323     def __init__(self, gdbval):
 324         self.gdbval = gdbval
 325
 326     def to_string (self):
 327         result = '<edge 0x%x' % intptr(self.gdbval)
 328         if intptr(self.gdbval):
 329             src = bb_index_to_str(intptr(self.gdbval['src']['index']))
 330             dest = bb_index_to_str(intptr(self.gdbval['dest']['index']))
 331             result += ' (%s -> %s)' % (src, dest)
 332         result += '>'
 333         return result
 334
 335 ######################################################################
 336
 337 class Rtx:
 338     def __init__(self, gdbval):
 339         self.gdbval = gdbval
 340
 341     def GET_CODE(self):
 342         return self.gdbval['code']
 343
 344 def GET_RTX_LENGTH(code):
 345     val_rtx_length = gdb.parse_and_eval('rtx_length')
 346     return intptr(val_rtx_length[code])
 347
 348 def GET_RTX_NAME(code):
 349     val_rtx_name = gdb.parse_and_eval('rtx_name')
 350     return val_rtx_name[code].string()
 351
 352 def GET_RTX_FORMAT(code):
 353     val_rtx_format = gdb.parse_and_eval('rtx_format')
 354     return val_rtx_format[code].string()
 355
 356 class RtxPrinter:
 357     def __init__(self, gdbval):
 358         self.gdbval = gdbval
 359         self.rtx = Rtx(gdbval)
 360
 361     def to_string (self):
 362         """
 363         For now, a cheap kludge: invoke the inferior's print
 364         function to get a string to use the user, and return an empty
 365         string for gdb
 366         """
 367         # We use print_inline_rtx to avoid a trailing newline
 368         gdb.execute('call print_inline_rtx (stderr, (const_rtx) %s, 0)'
 369                     % intptr(self.gdbval))
 370         return ''
 371
 372         # or by hand; based on gcc/print-rtl.c:print_rtx
 373         result = ('<rtx_def 0x%x'
 374                   % (intptr(self.gdbval)))
 375         code = self.rtx.GET_CODE()
 376         result += ' (%s' % GET_RTX_NAME(code)
 377         format_ = GET_RTX_FORMAT(code)
 378         for i in range(GET_RTX_LENGTH(code)):
 379             print(format_[i])
 380         result += ')>'
 381         return result
 382
 383 ######################################################################
 384
 385 class PassPrinter:
 386     def __init__(self, gdbval):
 387         self.gdbval = gdbval
 388
 389     def to_string (self):
 390         result = '<opt_pass* 0x%x' % intptr(self.gdbval)
 391         if intptr(self.gdbval):
 392             result += (' "%s"(%i)'
 393                        % (self.gdbval['name'].string(),
 394                           intptr(self.gdbval['static_pass_number'])))
 395         result += '>'
 396         return result
 397
 398 ######################################################################
 399
 400 class VecPrinter:
 401     #    -ex "up" -ex "p bb->preds"
 402     def __init__(self, gdbval):
 403         self.gdbval = gdbval
 404
 405     def display_hint (self):
 406         return 'array'
 407
 408     def to_string (self):
 409         # A trivial implementation; prettyprinting the contents is done
 410         # by gdb calling the "children" method below.
 411         return '0x%x' % intptr(self.gdbval)
 412
 413     def children (self):
 414         if intptr(self.gdbval) == 0:
 415             return
 416         m_vecpfx = self.gdbval['m_vecpfx']
 417         m_num = m_vecpfx['m_num']
 418         m_vecdata = self.gdbval['m_vecdata']
 419         for i in range(m_num):
 420             yield ('[%d]' % i, m_vecdata[i])
 421
 422 ######################################################################
 423
 424 # TODO:
 425 #   * hashtab
 426 #   * location_t
 427
 428 class GdbSubprinter(gdb.printing.SubPrettyPrinter):
 429     def __init__(self, name, class_):
 430         super(GdbSubprinter, self).__init__(name)
 431         self.class_ = class_
 432
 433     def handles_type(self, str_type):
 434         raise NotImplementedError
 435
 436 class GdbSubprinterTypeList(GdbSubprinter):
 437     """
 438     A GdbSubprinter that handles a specific set of types
 439     """
 440     def __init__(self, str_types, name, class_):
 441         super(GdbSubprinterTypeList, self).__init__(name, class_)
 442         self.str_types = frozenset(str_types)
 443
 444     def handles_type(self, str_type):
 445         return str_type in self.str_types
 446
 447 class GdbSubprinterRegex(GdbSubprinter):
 448     """
 449     A GdbSubprinter that handles types that match a regex
 450     """
 451     def __init__(self, regex, name, class_):
 452         super(GdbSubprinterRegex, self).__init__(name, class_)
 453         self.regex = re.compile(regex)
 454
 455     def handles_type(self, str_type):
 456         return self.regex.match(str_type)
 457
 458 class GdbPrettyPrinters(gdb.printing.PrettyPrinter):
 459     def __init__(self, name):
 460         super(GdbPrettyPrinters, self).__init__(name, [])
 461
 462     def add_printer_for_types(self, name, class_, types):
 463         self.subprinters.append(GdbSubprinterTypeList(name, class_, types))
 464
 465     def add_printer_for_regex(self, name, class_, regex):
 466         self.subprinters.append(GdbSubprinterRegex(name, class_, regex))
 467
 468     def __call__(self, gdbval):
 469         type_ = gdbval.type.unqualified()
 470         str_type = str(type_)
 471         for printer in self.subprinters:
 472             if printer.enabled and printer.handles_type(str_type):
 473                 return printer.class_(gdbval)
 474
 475         # Couldn't find a pretty printer (or it was disabled):
 476         return None
 477
 478
 479 def build_pretty_printer():
 480     pp = GdbPrettyPrinters('gcc')
 481     pp.add_printer_for_types(['tree'],
 482                              'tree', TreePrinter)
 483     pp.add_printer_for_types(['cgraph_node *'],
 484                              'cgraph_node', CGraphNodePrinter)
 485     pp.add_printer_for_types(['dw_die_ref'],
 486                              'dw_die_ref', DWDieRefPrinter)
 487     pp.add_printer_for_types(['gimple', 'gimple_statement_base *',
 488
 489                               # Keep this in the same order as gimple.def:
 490                               'gimple_cond', 'const_gimple_cond',
 491                               'gimple_statement_cond *',
 492                               'gimple_debug', 'const_gimple_debug',
 493                               'gimple_statement_debug *',
 494                               'gimple_label', 'const_gimple_label',
 495                               'gimple_statement_label *',
 496                               'gimple_switch', 'const_gimple_switch',
 497                               'gimple_statement_switch *',
 498                               'gimple_assign', 'const_gimple_assign',
 499                               'gimple_statement_assign *',
 500                               'gimple_bind', 'const_gimple_bind',
 501                               'gimple_statement_bind *',
 502                               'gimple_phi', 'const_gimple_phi',
 503                               'gimple_statement_phi *'],
 504
 505                              'gimple',
 506                              GimplePrinter)
 507     pp.add_printer_for_types(['basic_block', 'basic_block_def *'],
 508                              'basic_block',
 509                              BasicBlockPrinter)
 510     pp.add_printer_for_types(['edge', 'edge_def *'],
 511                              'edge',
 512                              CfgEdgePrinter)
 513     pp.add_printer_for_types(['rtx_def *'], 'rtx_def', RtxPrinter)
 514     pp.add_printer_for_types(['opt_pass *'], 'opt_pass', PassPrinter)
 515
 516     pp.add_printer_for_regex(r'vec<(\S+), (\S+), (\S+)> \*',
 517                              'vec',
 518                              VecPrinter)
 519
 520     return pp
 521
 522 gdb.printing.register_pretty_printer(
 523     gdb.current_objfile(),
 524     build_pretty_printer())
 525
 526 def find_gcc_source_dir():
 527     # Use location of global "g" to locate the source tree
 528     sym_g = gdb.lookup_global_symbol('g')
 529     path = sym_g.symtab.filename # e.g. '../../src/gcc/context.h'
 530     srcdir = os.path.split(path)[0] # e.g. '../../src/gcc'
 531     return srcdir
 532
 533 class PassNames:
 534     """Parse passes.def, gathering a list of pass class names"""
 535     def __init__(self):
 536         srcdir = find_gcc_source_dir()
 537         self.names = []
 538         with open(os.path.join(srcdir, 'passes.def')) as f:
 539             for line in f:
 540                 m = re.match('\s*NEXT_PASS \((.+)\);', line)
 541                 if m:
 542                     self.names.append(m.group(1))
 543
 544 class BreakOnPass(gdb.Command):
 545     """
 546     A custom command for putting breakpoints on the execute hook of passes.
 547     This is largely a workaround for issues with tab-completion in gdb when
 548     setting breakpoints on methods on classes within anonymous namespaces.
 549
 550     Example of use: putting a breakpoint on "final"
 551       (gdb) break-on-pass
 552     Press <TAB>; it autocompletes to "pass_":
 553       (gdb) break-on-pass pass_
 554     Press <TAB>:
 555       Display all 219 possibilities? (y or n)
 556     Press "n"; then type "f":
 557       (gdb) break-on-pass pass_f
 558     Press <TAB> to autocomplete to pass classnames beginning with "pass_f":
 559       pass_fast_rtl_dce              pass_fold_builtins
 560       pass_feedback_split_functions  pass_forwprop
 561       pass_final                     pass_fre
 562       pass_fixup_cfg                 pass_free_cfg
 563     Type "in<TAB>" to complete to "pass_final":
 564       (gdb) break-on-pass pass_final
 565     ...and hit <RETURN>:
 566       Breakpoint 6 at 0x8396ba: file ../../src/gcc/final.c, line 4526.
 567     ...and we have a breakpoint set; continue execution:
 568       (gdb) cont
 569       Continuing.
 570       Breakpoint 6, (anonymous namespace)::pass_final::execute (this=0x17fb990) at ../../src/gcc/final.c:4526
 571       4526        virtual unsigned int execute (function *) { return rest_of_handle_final (); }
 572     """
 573     def __init__(self):
 574         gdb.Command.__init__(self, 'break-on-pass', gdb.COMMAND_BREAKPOINTS)
 575         self.pass_names = None
 576
 577     def complete(self, text, word):
 578         # Lazily load pass names:
 579         if not self.pass_names:
 580             self.pass_names = PassNames()
 581
 582         return [name
 583                 for name in sorted(self.pass_names.names)
 584                 if name.startswith(text)]
 585
 586     def invoke(self, arg, from_tty):
 587         sym = '(anonymous namespace)::%s::execute' % arg
 588         breakpoint = gdb.Breakpoint(sym)
 589
 590 BreakOnPass()
 591
 592 print('Successfully loaded GDB hooks for GCC')