# Python hooks for gdb for debugging GCC # Copyright (C) 2013-2017 Free Software Foundation, Inc. # Contributed by David Malcolm # This file is part of GCC. # GCC is free software; you can redistribute it and/or modify it under # the terms of the GNU General Public License as published by the Free # Software Foundation; either version 3, or (at your option) any later # version. # GCC is distributed in the hope that it will be useful, but WITHOUT # ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License # for more details. # You should have received a copy of the GNU General Public License # along with GCC; see the file COPYING3. If not see # . """ Enabling the debugging hooks ---------------------------- gcc/configure (from configure.ac) generates a .gdbinit within the "gcc" subdirectory of the build directory, and when run by gdb, this imports gcc/gdbhooks.py from the source directory, injecting useful Python code into gdb. You may see a message from gdb of the form: "path-to-build/gcc/.gdbinit" auto-loading has been declined by your `auto-load safe-path' as a protection against untrustworthy python scripts. See http://sourceware.org/gdb/onlinedocs/gdb/Auto_002dloading-safe-path.html The fix is to mark the paths of the build/gcc directory as trustworthy. An easy way to do so is by adding the following to your ~/.gdbinit script: add-auto-load-safe-path /absolute/path/to/build/gcc for the build directories for your various checkouts of gcc. If it's working, you should see the message: Successfully loaded GDB hooks for GCC as gdb starts up. During development, I've been manually invoking the code in this way, as a precanned way of printing a variety of different kinds of value: gdb \ -ex "break expand_gimple_stmt" \ -ex "run" \ -ex "bt" \ --args \ ./cc1 foo.c -O3 Examples of output using the pretty-printers -------------------------------------------- Pointer values are generally shown in the form: For example, an opt_pass* might appear as: (gdb) p pass $2 = The name of the pass is given ("expand"), together with the static_pass_number. Note that you can dereference the pointer in the normal way: (gdb) p *pass $4 = {type = RTL_PASS, name = 0x120a312 "expand", [etc, ...snipped...] and you can suppress pretty-printers using /r (for "raw"): (gdb) p /r pass $3 = (opt_pass *) 0x188b600 Basic blocks are shown with their index in parentheses, apart from the CFG's entry and exit blocks, which are given as "ENTRY" and "EXIT": (gdb) p bb $9 = (gdb) p cfun->cfg->x_entry_block_ptr $10 = (gdb) p cfun->cfg->x_exit_block_ptr $11 = CFG edges are shown with the src and dest blocks given in parentheses: (gdb) p e $1 = 6)> Tree nodes are printed using Python code that emulates print_node_brief, running in gdb, rather than in the inferior: (gdb) p cfun->decl $1 = For usability, the type is printed first (e.g. "function_decl"), rather than just "tree". RTL expressions use a kludge: they are pretty-printed by injecting calls into print-rtl.c into the inferior: Value returned is $1 = (note 9 8 10 [bb 3] NOTE_INSN_BASIC_BLOCK) (gdb) p $1 $2 = (note 9 8 10 [bb 3] NOTE_INSN_BASIC_BLOCK) (gdb) p /r $1 $3 = (rtx_def *) 0x7ffff043e140 This won't work for coredumps, and probably in other circumstances, but it's a quick way of getting lots of debuggability quickly. Callgraph nodes are printed with the name of the function decl, if available: (gdb) frame 5 #5 0x00000000006c288a in expand_function (node=) at ../../src/gcc/cgraphunit.c:1594 1594 execute_pass_list (g->get_passes ()->all_passes); (gdb) p node $1 = vec<> pointers are printed as the address followed by the elements in braces. Here's a length 2 vec: (gdb) p bb->preds $18 = 0x7ffff0428b68 = { 5)>, 5)>} and here's a length 1 vec: (gdb) p bb->succs $19 = 0x7ffff0428bb8 = { EXIT)>} You cannot yet use array notation [] to access the elements within the vector: attempting to do so instead gives you the vec itself (for vec[0]), or a (probably) invalid cast to vec<> for the memory after the vec (for vec[1] onwards). Instead (for now) you must access m_vecdata: (gdb) p bb->preds->m_vecdata[0] $20 = 5)> (gdb) p bb->preds->m_vecdata[1] $21 = 5)> """ import os.path import re import sys import tempfile import gdb import gdb.printing import gdb.types # Convert "enum tree_code" (tree.def and tree.h) to a dict: tree_code_dict = gdb.types.make_enum_dict(gdb.lookup_type('enum tree_code')) # ...and look up specific values for use later: IDENTIFIER_NODE = tree_code_dict['IDENTIFIER_NODE'] TYPE_DECL = tree_code_dict['TYPE_DECL'] # Similarly for "enum tree_code_class" (tree.h): tree_code_class_dict = gdb.types.make_enum_dict(gdb.lookup_type('enum tree_code_class')) tcc_type = tree_code_class_dict['tcc_type'] tcc_declaration = tree_code_class_dict['tcc_declaration'] # Python3 has int() with arbitrary precision (bignum). Python2 int() is 32-bit # on 32-bit hosts but remote targets may have 64-bit pointers there; Python2 # long() is always 64-bit but Python3 no longer has anything named long. def intptr(gdbval): return long(gdbval) if sys.version_info.major == 2 else int(gdbval) class Tree: """ Wrapper around a gdb.Value for a tree, with various methods corresponding to macros in gcc/tree.h """ def __init__(self, gdbval): self.gdbval = gdbval def is_nonnull(self): return intptr(self.gdbval) def TREE_CODE(self): """ Get gdb.Value corresponding to TREE_CODE (self) as per: #define TREE_CODE(NODE) ((enum tree_code) (NODE)->base.code) """ return self.gdbval['base']['code'] def DECL_NAME(self): """ Get Tree instance corresponding to DECL_NAME (self) """ return Tree(self.gdbval['decl_minimal']['name']) def TYPE_NAME(self): """ Get Tree instance corresponding to result of TYPE_NAME (self) """ return Tree(self.gdbval['type_common']['name']) def IDENTIFIER_POINTER(self): """ Get str correspoinding to result of IDENTIFIER_NODE (self) """ return self.gdbval['identifier']['id']['str'].string() class TreePrinter: "Prints a tree" def __init__ (self, gdbval): self.gdbval = gdbval self.node = Tree(gdbval) def to_string (self): # like gcc/print-tree.c:print_node_brief # #define TREE_CODE(NODE) ((enum tree_code) (NODE)->base.code) # tree_code_name[(int) TREE_CODE (node)]) if intptr(self.gdbval) == 0: return '' val_TREE_CODE = self.node.TREE_CODE() # extern const enum tree_code_class tree_code_type[]; # #define TREE_CODE_CLASS(CODE) tree_code_type[(int) (CODE)] val_tree_code_type = gdb.parse_and_eval('tree_code_type') val_tclass = val_tree_code_type[val_TREE_CODE] val_tree_code_name = gdb.parse_and_eval('tree_code_name') val_code_name = val_tree_code_name[intptr(val_TREE_CODE)] #print(val_code_name.string()) result = '<%s 0x%x' % (val_code_name.string(), intptr(self.gdbval)) if intptr(val_tclass) == tcc_declaration: tree_DECL_NAME = self.node.DECL_NAME() if tree_DECL_NAME.is_nonnull(): result += ' %s' % tree_DECL_NAME.IDENTIFIER_POINTER() else: pass # TODO: labels etc elif intptr(val_tclass) == tcc_type: tree_TYPE_NAME = Tree(self.gdbval['type_common']['name']) if tree_TYPE_NAME.is_nonnull(): if tree_TYPE_NAME.TREE_CODE() == IDENTIFIER_NODE: result += ' %s' % tree_TYPE_NAME.IDENTIFIER_POINTER() elif tree_TYPE_NAME.TREE_CODE() == TYPE_DECL: if tree_TYPE_NAME.DECL_NAME().is_nonnull(): result += ' %s' % tree_TYPE_NAME.DECL_NAME().IDENTIFIER_POINTER() if self.node.TREE_CODE() == IDENTIFIER_NODE: result += ' %s' % self.node.IDENTIFIER_POINTER() # etc result += '>' return result ###################################################################### # Callgraph pretty-printers ###################################################################### class CGraphNodePrinter: def __init__(self, gdbval): self.gdbval = gdbval def to_string (self): result = '' result = '' val_gimple_code = self.gdbval['code'] val_gimple_code_name = gdb.parse_and_eval('gimple_code_name') val_code_name = val_gimple_code_name[intptr(val_gimple_code)] result = '<%s 0x%x' % (val_code_name.string(), intptr(self.gdbval)) result += '>' return result ###################################################################### # CFG pretty-printers ###################################################################### def bb_index_to_str(index): if index == 0: return 'ENTRY' elif index == 1: return 'EXIT' else: return '%i' % index class BasicBlockPrinter: def __init__(self, gdbval): self.gdbval = gdbval def to_string (self): result = 'preds" def __init__(self, gdbval): self.gdbval = gdbval def display_hint (self): return 'array' def to_string (self): # A trivial implementation; prettyprinting the contents is done # by gdb calling the "children" method below. return '0x%x' % intptr(self.gdbval) def children (self): if intptr(self.gdbval) == 0: return m_vecpfx = self.gdbval['m_vecpfx'] m_num = m_vecpfx['m_num'] m_vecdata = self.gdbval['m_vecdata'] for i in range(m_num): yield ('[%d]' % i, m_vecdata[i]) ###################################################################### # TODO: # * hashtab # * location_t class GdbSubprinter(gdb.printing.SubPrettyPrinter): def __init__(self, name, class_): super(GdbSubprinter, self).__init__(name) self.class_ = class_ def handles_type(self, str_type): raise NotImplementedError class GdbSubprinterTypeList(GdbSubprinter): """ A GdbSubprinter that handles a specific set of types """ def __init__(self, str_types, name, class_): super(GdbSubprinterTypeList, self).__init__(name, class_) self.str_types = frozenset(str_types) def handles_type(self, str_type): return str_type in self.str_types class GdbSubprinterRegex(GdbSubprinter): """ A GdbSubprinter that handles types that match a regex """ def __init__(self, regex, name, class_): super(GdbSubprinterRegex, self).__init__(name, class_) self.regex = re.compile(regex) def handles_type(self, str_type): return self.regex.match(str_type) class GdbPrettyPrinters(gdb.printing.PrettyPrinter): def __init__(self, name): super(GdbPrettyPrinters, self).__init__(name, []) def add_printer_for_types(self, name, class_, types): self.subprinters.append(GdbSubprinterTypeList(name, class_, types)) def add_printer_for_regex(self, name, class_, regex): self.subprinters.append(GdbSubprinterRegex(name, class_, regex)) def __call__(self, gdbval): type_ = gdbval.type.unqualified() str_type = str(type_) for printer in self.subprinters: if printer.enabled and printer.handles_type(str_type): return printer.class_(gdbval) # Couldn't find a pretty printer (or it was disabled): return None def build_pretty_printer(): pp = GdbPrettyPrinters('gcc') pp.add_printer_for_types(['tree'], 'tree', TreePrinter) pp.add_printer_for_types(['cgraph_node *'], 'cgraph_node', CGraphNodePrinter) pp.add_printer_for_types(['dw_die_ref'], 'dw_die_ref', DWDieRefPrinter) pp.add_printer_for_types(['gimple', 'gimple *', # Keep this in the same order as gimple.def: 'gimple_cond', 'const_gimple_cond', 'gimple_statement_cond *', 'gimple_debug', 'const_gimple_debug', 'gimple_statement_debug *', 'gimple_label', 'const_gimple_label', 'gimple_statement_label *', 'gimple_switch', 'const_gimple_switch', 'gimple_statement_switch *', 'gimple_assign', 'const_gimple_assign', 'gimple_statement_assign *', 'gimple_bind', 'const_gimple_bind', 'gimple_statement_bind *', 'gimple_phi', 'const_gimple_phi', 'gimple_statement_phi *'], 'gimple', GimplePrinter) pp.add_printer_for_types(['basic_block', 'basic_block_def *'], 'basic_block', BasicBlockPrinter) pp.add_printer_for_types(['edge', 'edge_def *'], 'edge', CfgEdgePrinter) pp.add_printer_for_types(['rtx_def *'], 'rtx_def', RtxPrinter) pp.add_printer_for_types(['opt_pass *'], 'opt_pass', PassPrinter) pp.add_printer_for_regex(r'vec<(\S+), (\S+), (\S+)> \*', 'vec', VecPrinter) return pp gdb.printing.register_pretty_printer( gdb.current_objfile(), build_pretty_printer()) def find_gcc_source_dir(): # Use location of global "g" to locate the source tree sym_g = gdb.lookup_global_symbol('g') path = sym_g.symtab.filename # e.g. '../../src/gcc/context.h' srcdir = os.path.split(path)[0] # e.g. '../../src/gcc' return srcdir class PassNames: """Parse passes.def, gathering a list of pass class names""" def __init__(self): srcdir = find_gcc_source_dir() self.names = [] with open(os.path.join(srcdir, 'passes.def')) as f: for line in f: m = re.match('\s*NEXT_PASS \(([^,]+).*\);', line) if m: self.names.append(m.group(1)) class BreakOnPass(gdb.Command): """ A custom command for putting breakpoints on the execute hook of passes. This is largely a workaround for issues with tab-completion in gdb when setting breakpoints on methods on classes within anonymous namespaces. Example of use: putting a breakpoint on "final" (gdb) break-on-pass Press ; it autocompletes to "pass_": (gdb) break-on-pass pass_ Press : Display all 219 possibilities? (y or n) Press "n"; then type "f": (gdb) break-on-pass pass_f Press to autocomplete to pass classnames beginning with "pass_f": pass_fast_rtl_dce pass_fold_builtins pass_feedback_split_functions pass_forwprop pass_final pass_fre pass_fixup_cfg pass_free_cfg Type "in" to complete to "pass_final": (gdb) break-on-pass pass_final ...and hit : Breakpoint 6 at 0x8396ba: file ../../src/gcc/final.c, line 4526. ...and we have a breakpoint set; continue execution: (gdb) cont Continuing. Breakpoint 6, (anonymous namespace)::pass_final::execute (this=0x17fb990) at ../../src/gcc/final.c:4526 4526 virtual unsigned int execute (function *) { return rest_of_handle_final (); } """ def __init__(self): gdb.Command.__init__(self, 'break-on-pass', gdb.COMMAND_BREAKPOINTS) self.pass_names = None def complete(self, text, word): # Lazily load pass names: if not self.pass_names: self.pass_names = PassNames() return [name for name in sorted(self.pass_names.names) if name.startswith(text)] def invoke(self, arg, from_tty): sym = '(anonymous namespace)::%s::execute' % arg breakpoint = gdb.Breakpoint(sym) BreakOnPass() class DumpFn(gdb.Command): """ A custom command to dump a gimple/rtl function to file. By default, it dumps the current function using 0 as dump_flags, but the function and flags can also be specified. If /f are passed as the first two arguments, the dump is written to that file. Otherwise, a temporary file is created and opened in the text editor specified in the EDITOR environment variable. Examples of use: (gdb) dump-fn (gdb) dump-fn /f foo.1.txt (gdb) dump-fn cfun->decl (gdb) dump-fn /f foo.1.txt cfun->decl (gdb) dump-fn cfun->decl 0 (gdb) dump-fn cfun->decl dump_flags """ def __init__(self): gdb.Command.__init__(self, 'dump-fn', gdb.COMMAND_USER) def invoke(self, arg, from_tty): # Parse args, check number of args args = gdb.string_to_argv(arg) if len(args) >= 1 and args[0] == "/f": if len(args) == 1: print ("Missing file argument") return filename = args[1] editor_mode = False base_arg = 2 else: editor = os.getenv("EDITOR", "") if editor == "": print ("EDITOR environment variable not defined") return editor_mode = True base_arg = 0 if len(args) - base_arg > 2: print ("Too many arguments") return # Set func if len(args) - base_arg >= 1: funcname = args[base_arg] printfuncname = "function %s" % funcname else: funcname = "cfun ? cfun->decl : current_function_decl" printfuncname = "current function" func = gdb.parse_and_eval(funcname) if func == 0: print ("Could not find %s" % printfuncname) return func = "(tree)%u" % func # Set flags if len(args) - base_arg >= 2: flags = gdb.parse_and_eval(args[base_arg + 1]) else: flags = 0 # Get tempory file, if necessary if editor_mode: f = tempfile.NamedTemporaryFile(delete=False, suffix=".txt") filename = f.name f.close() # Open file fp = gdb.parse_and_eval("fopen (\"%s\", \"w\")" % filename) if fp == 0: print ("Could not open file: %s" % filename) return fp = "(FILE *)%u" % fp # Dump function to file _ = gdb.parse_and_eval("dump_function_to_file (%s, %s, %u)" % (func, fp, flags)) # Close file ret = gdb.parse_and_eval("fclose (%s)" % fp) if ret != 0: print ("Could not close file: %s" % filename) return # Open file in editor, if necessary if editor_mode: os.system("( %s \"%s\"; rm \"%s\" ) &" % (editor, filename, filename)) DumpFn() class DotFn(gdb.Command): """ A custom command to show a gimple/rtl function control flow graph. By default, it show the current function, but the function can also be specified. Examples of use: (gdb) dot-fn (gdb) dot-fn cfun (gdb) dot-fn cfun 0 (gdb) dot-fn cfun dump_flags """ def __init__(self): gdb.Command.__init__(self, 'dot-fn', gdb.COMMAND_USER) def invoke(self, arg, from_tty): # Parse args, check number of args args = gdb.string_to_argv(arg) if len(args) > 2: print("Too many arguments") return # Set func if len(args) >= 1: funcname = args[0] printfuncname = "function %s" % funcname else: funcname = "cfun" printfuncname = "current function" func = gdb.parse_and_eval(funcname) if func == 0: print("Could not find %s" % printfuncname) return func = "(struct function *)%s" % func # Set flags if len(args) >= 2: flags = gdb.parse_and_eval(args[1]) else: flags = 0 # Get temp file f = tempfile.NamedTemporaryFile(delete=False) filename = f.name # Close and reopen temp file to get C FILE* f.close() fp = gdb.parse_and_eval("fopen (\"%s\", \"w\")" % filename) if fp == 0: print("Cannot open temp file") return fp = "(FILE *)%u" % fp # Write graph to temp file _ = gdb.parse_and_eval("start_graph_dump (%s, \"\")" % fp) _ = gdb.parse_and_eval("print_graph_cfg (%s, %s, %u)" % (fp, func, flags)) _ = gdb.parse_and_eval("end_graph_dump (%s)" % fp) # Close temp file ret = gdb.parse_and_eval("fclose (%s)" % fp) if ret != 0: print("Could not close temp file: %s" % filename) return # Show graph in temp file os.system("( dot -Tx11 \"%s\"; rm \"%s\" ) &" % (filename, filename)) DotFn() print('Successfully loaded GDB hooks for GCC')