善用backtrace

程序在得到一个Segmentation fault这样的错误信息毫无保留地就跳出来了，遇到这样的问题让人很痛苦，查找问题不亚于你N多天辛苦劳累编写代码的难度。那么有没有更好的方法可以在产生SIGSEGV信号的时候得到调试可用的信息呢？看看下面的例程吧！

sigsegv.h

#ifndef __sigsegv_h__
#define __sigsegv_h__

#ifdef __cplusplus
extern "C" {
#endif

  int setup_sigsegv();

#ifdef __cplusplus
}
#endif

#endif /* __sigsegv_h__ */

sigsegv.c

#define _GNU_SOURCE
#include <memory.h>
#include <stdlib.h>
#include <stdio.h>
#include <signal.h>
#include <ucontext.h>
#include <dlfcn.h>
#include <execinfo.h>
#ifndef NO_CPP_DEMANGLE
#include <cxxabi.h>
#endif

#if defined(REG_RIP)
# define SIGSEGV_STACK_IA64
# define REGFORMAT "%016lx"
#elif defined(REG_EIP)
# define SIGSEGV_STACK_X86
# define REGFORMAT "%08x"
#else
# define SIGSEGV_STACK_GENERIC
# define REGFORMAT "%x"
#endif

static void signal_segv(int signum, siginfo_t* info, void*ptr) {
  static const char *si_codes[3] = {"", "SEGV_MAPERR", "SEGV_ACCERR"};

  size_t i;
  ucontext_t *ucontext = (ucontext_t*)ptr;

#if defined(SIGSEGV_STACK_X86) || defined(SIGSEGV_STACK_IA64)
  int f = 0;
  Dl_info dlinfo;
  void **bp = 0;
  void *ip = 0;
#else
  void *bt[20];
  char **strings;
  size_t sz;
#endif

  fprintf(stderr, "Segmentation Fault!\n");
  fprintf(stderr, "info.si_signo = %d\n", signum);
  fprintf(stderr, "info.si_errno = %d\n", info->si_errno);
  fprintf(stderr, "info.si_code  = %d (%s)\n", info->si_code, si_codes[info->si_code]);
  fprintf(stderr, "info.si_addr  = %p\n", info->si_addr);
  for(i = 0; i < NGREG; i++)
    fprintf(stderr, "reg[%02d]       = 0x" REGFORMAT "\n", i, ucontext->uc_mcontext.gregs[i]);

#if defined(SIGSEGV_STACK_X86) || defined(SIGSEGV_STACK_IA64)
# if defined(SIGSEGV_STACK_IA64)
  ip = (void*)ucontext->uc_mcontext.gregs[REG_RIP];
  bp = (void**)ucontext->uc_mcontext.gregs[REG_RBP];
# elif defined(SIGSEGV_STACK_X86)
  ip = (void*)ucontext->uc_mcontext.gregs[REG_EIP];
  bp = (void**)ucontext->uc_mcontext.gregs[REG_EBP];
# endif

  fprintf(stderr, "Stack trace:\n");
  while(bp && ip) {
    if(!dladdr(ip, &dlinfo))
      break;

    const char *symname = dlinfo.dli_sname;
#ifndef NO_CPP_DEMANGLE
    int status;
    char *tmp = __cxa_demangle(symname, NULL, 0, &status);

    if(status == 0 && tmp)
      symname = tmp;
#endif

    fprintf(stderr, "% 2d: %p <%s+%u> (%s)\n",
            ++f,
            ip,
            symname,
            (unsigned)(ip - dlinfo.dli_saddr),
            dlinfo.dli_fname);

#ifndef NO_CPP_DEMANGLE
    if(tmp)
      free(tmp);
#endif

    if(dlinfo.dli_sname && !strcmp(dlinfo.dli_sname, "main"))
      break;

    ip = bp[1];
    bp = (void**)bp[0];
  }
#else
  fprintf(stderr, "Stack trace (non-dedicated):\n");
  sz = backtrace(bt, 20);
  strings = backtrace_symbols(bt, sz);

  for(i = 0; i < sz; ++i)
    fprintf(stderr, "%s\n", strings[i]);
#endif
  fprintf(stderr, "End of stack trace\n");
  exit (-1);
}

int setup_sigsegv() {
  struct sigaction action;
  memset(&action, 0, sizeof(action));
  action.sa_sigaction = signal_segv;
  action.sa_flags = SA_SIGINFO;
  if(sigaction(SIGSEGV, &action, NULL) < 0) {
    perror("sigaction");
    return 0;
  }

  return 1;
}

#ifndef SIGSEGV_NO_AUTO_INIT
static void __attribute((constructor)) init(void) {
  setup_sigsegv();
}
#endif

main.c

#include "sigsegv.h"
#include <string.h>

int die() {
  char *err = NULL;
  strcpy(err, "gonner");
  return 0;
}

int main() {
  return die();
}

下面来编译上面的main.c程序看看将会产生什么样的信息呢，不过要注意的就是如果要在你的程序里引用sigsegv.h、sigsegv.c得到堆栈信息的话记得加上-rdynamic -ldl参数。

/data/codes/c/test/backtraces $ gcc -o test -rdynamic -ldl -ggdb -g sigsegv.c main.c
/data/codes/c/test/backtraces $ ./test
Segmentation Fault!
info.si_signo = 11
info.si_errno = 0
info.si_code  = 1 (SEGV_MAPERR)
info.si_addr  = (nil)
reg[00]       = 0x00000033
reg[01]       = 0x00000000
reg[02]       = 0xc010007b
reg[03]       = 0x0000007b
reg[04]       = 0x00000000
reg[05]       = 0xb7fc8ca0
reg[06]       = 0xbff04c2c
reg[07]       = 0xbff04c1c
reg[08]       = 0xb7f8cff4
reg[09]       = 0x00000001
reg[10]       = 0xbff04c50
reg[11]       = 0x00000000
reg[12]       = 0x0000000e
reg[13]       = 0x00000006
reg[14]       = 0x080489ec
reg[15]       = 0x00000073
reg[16]       = 0x00010282
reg[17]       = 0xbff04c1c
reg[18]       = 0x0000007b
Stack trace:
 1: 0x80489ec <die+16> (/data/codes/c/test/backtraces/test)
 2: 0x8048a16 <main+19> (/data/codes/c/test/backtraces/test)
End of stack trace
/data/codes/c/test/backtraces $ 

下面用gdb来看看出错的地方左右的代码：

/data/codes/c/test/backtraces $ gdb ./test
gdb> disassemble die+16
Dump of assembler code for function die:
0x080489dc <die+0>:     push   %ebp
0x080489dd <die+1>:     mov    %esp,%ebp
0x080489df <die+3>:     sub    $0x10,%esp
0x080489e2 <die+6>:     movl   $0x0,0xfffffffc(%ebp)
0x080489e9 <die+13>:    mov    0xfffffffc(%ebp),%eax
0x080489ec <die+16>:    movl   $0x6e6e6f67,(%eax)
0x080489f2 <die+22>:    movw   $0x7265,0x4(%eax)
0x080489f8 <die+28>:    movb   $0x0,0x6(%eax)
0x080489fc <die+32>:    mov    $0x0,%eax
0x08048a01 <die+37>:    leave  
0x08048a02 <die+38>:    ret    
End of assembler dump.
gdb> 

也可以直接break *die+16进行调试，看看在出错之前的堆栈情况，那么下面我们再来看看代码问题到底出在什么地方了。

/data/codes/c/test/backtraces $ gdb ./test
gdb> break *die+16
Breakpoint 1 at 0x80489f2: file main.c, line 6.
gdb> list *die+16
0x80489f2 is in die (main.c:6).
1       #include "sigsegv.h"
2       #include <string.h>
3       
4       int die() {
5         char *err = NULL;
6         strcpy(err, "gonner");
7         return 0;
8       }
9       
10      int main() {
gdb> 

现在看看定位错误将会多么方便，上面的调试指令中list之前break不是必须的，只是让你可以看到break其实就已经指出了哪一行代码导致Segmentation fault了。如果你要发布你的程序你一般会为了减少体积不会附带调试信息的(也就是不加-ggdb -g参数)，不过没关系，你一样可以得到上面stack-trace信息，然后你调试之前只要加上调试信息即可。