Re: [PATCH] Partial fix for PR backtrace/1718

[Michael Chastain <mec dot gnu at mindspring dot com>]

"Eli Zaretskii" <eliz@gnu.org> wrote:
> Perhaps, then, you could post a list of all the opcodes and subsequent
> bytes that we need to cover in i386_analyze_frame_setup?

The compiler could schedule just about anything into the prologue!

Let's get empirical.  I ran cc1plus and gdb through "objdump -d" and
some perl fu.

We have to have "mov 0xADDRESS, %reg".  After that, recognizing
"cmpl $IMMEDIATE, 0xADDRESS" would help.  That instruction gets scheduled
even before "push %ebp".  Those two additions would cover 99.9% of cc1plus
and gdb.

This cc1plus is for gcc HEAD on native i686-pc-linux-gnu.
It was built with gcc 3.3.4 on native i686-pc-linux-gnu on an Intel Celeron.

cc1plus has 10849 symbols, broken down as:

  10849  total symbols
   9271	 push %ebp | mov %esp, %ebp
   1549  push %ebp | INSN | mov %esp, %ebp
     19  push %ebp | INSN | INSN | mov %esp, %ebp
     10  all other

The 1549 single-instruction interleaves break down as:

      2	push %ebp | fldz | mov %esp, %ebp
      1	push %ebp | mov $0xIMMEDIATE, %al | mov %esp, %ebp
      1	push %ebp | mov $0xIMMEDIATE, %cl | mov %esp, %ebp
    473	push %ebp | mov $0xIMMEDIATE, %eax | mov %esp, %ebp
    185	push %ebp | mov $0xIMMEDIATE, %ecx | mov %esp, %ebp
    126	push %ebp | mov $0xIMMEDIATE, %edx | mov %esp, %ebp
     76	push %ebp | mov 0xADDRESS, %eax | mov %esp, %ebp
      8	push %ebp | mov 0xADDRESS, %ecx | mov %esp, %ebp
     20	push %ebp | mov 0xADDRESS, %edx | mov %esp, %ebp
    404	push %ebp | xor %eax, %eax | mov %esp, %ebp
    124	push %ebp | xor %ecx, %ecx | mov %esp, %ebp
    129	push %ebp | xor %edx, %edx | mov %esp, %ebp

The 19 double-instruction interleaves are innocuous, just more MOV and XOR:

  clear_aux_for_edges : push %ebp | mov 0xADDRESS, %edx | mov 0xADDRESS, %ecx | mov %esp, %ebp
  cplus_demangle_set_style : push %ebp | mov 0xADDRESS, %eax | mov $0xIMMEDIATE, %edx | mov %esp, %ebp
  default_spill_heuristic : push %ebp | mov 0xADDRESS, %eax | mov $0xIMMEDIATE, %edx | mov %esp, %ebp
  dwarf2out_do_frame : push %ebp | mov 0xADDRESS, %edx | xor %eax, %eax | mov %esp, %ebp
  earlyclobber_operand_p : push %ebp | mov 0xADDRESS, %edx | xor %eax, %eax | mov %esp, %ebp
  enumerate_ldsts : push %ebp | mov 0xADDRESS, %edx | xor %ecx, %ecx | mov %esp, %ebp
  fast_math_flags_set_p : push %ebp | mov 0xADDRESS, %ecx | xor %eax, %eax | mov %esp, %ebp
  free_block_changes : push %ebp | mov 0xADDRESS, %eax | xor %edx, %edx | mov %esp, %ebp
  gate_all_optimizations : push %ebp | mov 0xADDRESS, %edx | xor %eax, %eax | mov %esp, %ebp
  ia32_multipass_dfa_lookahead : push %ebp | mov 0xADDRESS, %eax | mov $0xIMMEDIATE, %edx | mov %esp, %ebp
  kept_level_p : push %ebp | mov 0xADDRESS, %edx | xor %ecx, %ecx | mov %esp, %ebp
  move_replacements : push %ebp | mov 0xADDRESS, %ecx | xor %edx, %edx | mov %esp, %ebp
  optimization_options : push %ebp | xor %eax, %eax | mov 0xADDRESS, %ecx | mov %esp, %ebp
  pop_topmost_sequence : push %ebp | mov 0xADDRESS, %edx | xor %ecx, %ecx | mov %esp, %ebp
  reg_alternate_class : push %ebp | mov 0xADDRESS, %edx | mov $0xIMMEDIATE, %eax | mov %esp, %ebp
  reg_preferred_class : push %ebp | mov 0xADDRESS, %edx | mov $0xIMMEDIATE, %eax | mov %esp, %ebp
  schedule_more_p : push %ebp | mov 0xADDRESS, %eax | xor %edx, %edx | mov %esp, %ebp
  transfer_replacements : push %ebp | mov 0xADDRESS, %ecx | xor %edx, %edx | mov %esp, %ebp
  tree_ssa_lim_finalize : push %ebp | mov 0xADDRESS, %eax | mov 0xADDRESS, %edx | mov %esp, %ebp

The 10 truly freaky prologues are:

  .plt : pushl 0x86039e8 | jmp *0x86039ec | add %al, (%eax) | add %al, (%eax) | jmp *0x86039f0 | push $0x0 | jmp 80494cc <_init+0x18>
  _start : xor %ebp, %ebp | pop %esi | mov %esp, %ecx | and $0xfffffff0, %esp | push %eax | push %esp | push %edx
  constrain_operands_cached : cmpl $0xffffffff, 0x8619c0c | push %ebp | mov %esp, %ebp | je 841d293 <constrain_operands_cached+0x13> | pop %ebp | mov $0x1, %eax | ret 
  default_elf_select_rtx_section : cmpl $0x0, 0x8610da8 | push %ebp | mov %esp, %ebp | mov 0x8(%ebp), %ecx | mov 0xc(%ebp), %eax | mov 0x10(%ebp), %edx | je 84898d4 <default_elf_select_rtx_section+0x24>
  get_best_mode : movzbl 0x85b0e0c, %ecx | push %ebp | mov %esp, %ebp | push %edi | test %ecx, %ecx | mov 0x8(%ebp), %edi | push %esi
  get_pending_sizes : push %ebp | mov 0x867793c, %eax | xor %edx, %edx | mov %edx, 0x867793c | mov %esp, %ebp | pop %ebp | ret 
  init_branch_prob : push %ebp | xor %eax, %eax | xor %ecx, %ecx | mov %eax, 0x8611090 | xor %edx, %edx | mov %esp, %ebp | mov %ecx, 0x8611088
  init_temp_slots : push %ebp | mov 0x860ff64, %eax | xor %edx, %edx | xor %ecx, %ecx | mov %esp, %ebp | mov %edx, 0xa8(%eax) | xor %edx, %edx
  is_body_block : cmpb $0x0, 0x8563326 | push %ebp | mov %esp, %ebp | mov 0x8(%ebp), %eax | jne 84548a5 <is_body_block+0x15> | cmpb $0x4, 0xc(%eax) | je 84548b0 <is_body_block+0x20>
  ix86_init_builtins : testb $0x20, 0x8677745 | push %ebp | mov %esp, %ebp | jne 84a7bd0 <ix86_init_builtins+0x10> | pop %ebp | ret  | mov %esi, %esi

Next I did the same for gdb:

   6612  total symbols
   5492	 push %ebp | mov %esp, %ebp
   1087  push %ebp | INSN | mov %esp, %ebp
     19  push %ebp | INSN | INSN | mov %esp, %ebp
     18  all other

There weren't any new surprise in the push|INSN|mov and push|INSN|INSN|mov
prologues.  Here are the "all other":

  .plt : pushl 0x8282f2c | jmp *0x8282f30 | add %al, (%eax) | add %al, (%eax) | jmp *0x8282f34 | push $0x0 | jmp 80797dc <_init+0x18>
  NOP_Fixup : cmpl $0x1, 0x829c3c4 | push %ebp | mov %esp, %ebp | je 81ed520 <NOP_Fixup+0x10> | pop %ebp | ret  | mov %esi, %esi
  OP_0f07 : cmpl $0x3, 0x829c4d4 | push %ebp | mov %esp, %ebp | mov 0x8(%ebp), %edx | mov 0xc(%ebp), %eax | je 81ed458 <OP_0f07+0x18> | pop %ebp
  OP_M : cmpl $0x3, 0x829c4d4 | push %ebp | mov %esp, %ebp | mov 0x8(%ebp), %edx | mov 0xc(%ebp), %eax | je 81ed430 <OP_M+0x20> | mov %eax, 0xc(%ebp)
  OP_MS : cmpl $0x3, 0x829c4d4 | push %ebp | mov %esp, %ebp | je 81ed3e2 <OP_MS+0x12> | pop %ebp | jmp 81ed8b0 <BadOp> | pop %ebp
  OP_Rd : cmpl $0x3, 0x829c4d4 | push %ebp | mov %esp, %ebp | je 81ed192 <OP_Rd+0x12> | pop %ebp | jmp 81ed8b0 <BadOp> | pop %ebp
  OP_XS : cmpl $0x3, 0x829c4d4 | push %ebp | mov %esp, %ebp | je 81ed402 <OP_XS+0x12> | pop %ebp | jmp 81ed8b0 <BadOp> | pop %ebp
  __i686.get_pc_thunk.cx : mov (%esp, 1), %ecx | ret 
  _initialize_annotate : cmpl $0x1, 0x82873ec | push %ebp | mov %esp, %ebp | jle 80cc800 <_initialize_annotate+0x20> | mov $0x80cc7d0, %eax | mov %eax, 0x829ca64 | mov $0x80cc7d0, %eax
  _start : xor %ebp, %ebp | pop %esi | mov %esp, %ecx | and $0xfffffff0, %esp | push %eax | push %esp | push %edx
  annotate_ignore_count_change : cmpl $0x1, 0x82873ec | push %ebp | mov %esp, %ebp | jle 80cba96 <annotate_ignore_count_change+0x16> | mov $0x1, %eax | mov %eax, 0x8286d6c | pop %ebp
  init_child_ops : push %ebp | mov $0x82031d0, %eax | mov $0x80967c0, %ecx | mov %eax, 0x829cf04 | mov $0x80a2ab0, %edx | mov %esp, %ebp | mov %ecx, 0x829cf20
  init_remote_async_ops : push %ebp | mov $0x8207f00, %eax | mov $0x8209094, %ecx | mov %eax, 0x8284e0c | mov $0x8208020, %edx | mov %esp, %ebp | mov %ecx, 0x8284e04
  init_remote_ops : push %ebp | mov $0x820ec28, %eax | mov $0x80a50d0, %ecx | mov %eax, 0x8284b44 | mov $0x80a4d10, %edx | mov %esp, %ebp | mov %ecx, 0x8284b54
  rl_insert : cmpl $0x1, 0x827f794 | push %ebp | mov %esp, %ebp | mov 0x8(%ebp), %edx | mov 0xc(%ebp), %eax | je 81e4c20 <rl_insert+0x20> | mov %eax, 0xc(%ebp)
  selected_architecture_name : push %ebp | xor %eax, %eax | mov 0x82877a8, %edx | cmpl $0x0, 0x827d7b4 | mov %esp, %ebp | pop %ebp | setne %al
  set_inferior_args : push %ebp | mov 0x8287320, %eax | xor %ecx, %ecx | mov %ecx, 0x8287324 | mov %esp, %ebp | mov 0x8(%ebp), %edx | pop %ebp
  tui_clear_source_windows : push %ebp | mov 0x827f210, %eax | xor %ecx, %ecx | mov %ecx, 0x827f214 | mov %esp, %ebp | movl $0x0, (%eax) | movl $0x0, 0x4(%eax)

These are both C programs, I'd feel better if I could do this on eclipse
(java) and mozilla (c++) as well.  Also some PIC code would be nice.
I'm also ignoring floating point programs -- I bet a lot of floating
point instructions could get scheduled into the prologue.

Michael C