Linux

虽然已经有人建议使用execinfo.h中的backtrace()函数来打印堆栈跟踪并在出现分段错误时优雅地退出，但我没有看到提到确保所产生的回溯指向错误的实际位置所必需的复杂性(至少对于某些架构- x86和ARM)。

进入信号处理程序时，堆栈帧链中的前两个条目在信号处理程序中包含一个返回地址，在libc中的sigaction()中包含一个返回地址。在信号(即故障位置)之前调用的最后一个函数的堆栈帧丢失。

Code

#ifndef _GNU_SOURCE
#define _GNU_SOURCE
#endif
#ifndef __USE_GNU
#define __USE_GNU
#endif

#include <execinfo.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ucontext.h>
#include <unistd.h>

/* This structure mirrors the one found in /usr/include/asm/ucontext.h */
typedef struct _sig_ucontext {
 unsigned long     uc_flags;
 ucontext_t        *uc_link;
 stack_t           uc_stack;
 sigcontext_t      uc_mcontext;
 sigset_t          uc_sigmask;
} sig_ucontext_t;

void crit_err_hdlr(int sig_num, siginfo_t * info, void * ucontext)
{
 void *             array[50];
 void *             caller_address;
 char **            messages;
 int                size, i;
 sig_ucontext_t *   uc;

 uc = (sig_ucontext_t *)ucontext;

 /* Get the address at the time the signal was raised */
#if defined(__i386__) // gcc specific
 caller_address = (void *) uc->uc_mcontext.eip; // EIP: x86 specific
#elif defined(__x86_64__) // gcc specific
 caller_address = (void *) uc->uc_mcontext.rip; // RIP: x86_64 specific
#else
#error Unsupported architecture. // TODO: Add support for other arch.
#endif

 fprintf(stderr, "signal %d (%s), address is %p from %p\n", 
  sig_num, strsignal(sig_num), info->si_addr, 
  (void *)caller_address);

 size = backtrace(array, 50);

 /* overwrite sigaction with caller's address */
 array[1] = caller_address;

 messages = backtrace_symbols(array, size);

 /* skip first stack frame (points here) */
 for (i = 1; i < size && messages != NULL; ++i)
 {
  fprintf(stderr, "[bt]: (%d) %s\n", i, messages[i]);
 }

 free(messages);

 exit(EXIT_FAILURE);
}

int crash()
{
 char * p = NULL;
 *p = 0;
 return 0;
}

int foo4()
{
 crash();
 return 0;
}

int foo3()
{
 foo4();
 return 0;
}

int foo2()
{
 foo3();
 return 0;
}

int foo1()
{
 foo2();
 return 0;
}

int main(int argc, char ** argv)
{
 struct sigaction sigact;

 sigact.sa_sigaction = crit_err_hdlr;
 sigact.sa_flags = SA_RESTART | SA_SIGINFO;

 if (sigaction(SIGSEGV, &sigact, (struct sigaction *)NULL) != 0)
 {
  fprintf(stderr, "error setting signal handler for %d (%s)\n",
    SIGSEGV, strsignal(SIGSEGV));

  exit(EXIT_FAILURE);
 }

 foo1();

 exit(EXIT_SUCCESS);
}

输出

signal 11 (Segmentation fault), address is (nil) from 0x8c50
[bt]: (1) ./test(crash+0x24) [0x8c50]
[bt]: (2) ./test(foo4+0x10) [0x8c70]
[bt]: (3) ./test(foo3+0x10) [0x8c8c]
[bt]: (4) ./test(foo2+0x10) [0x8ca8]
[bt]: (5) ./test(foo1+0x10) [0x8cc4]
[bt]: (6) ./test(main+0x74) [0x8d44]
[bt]: (7) /lib/libc.so.6(__libc_start_main+0xa8) [0x40032e44]

在信号处理程序中调用backtrace()函数的所有危险仍然存在，不应忽视，但我发现这里描述的功能对调试崩溃非常有帮助。

需要注意的是，我提供的示例是在x86的Linux上开发/测试的。我也成功地实现了这在ARM上使用uc_mcontext。Arm_pc代替uc_mcontext.eip。

下面是我了解这个实现细节的文章的链接: http://www.linuxjournal.com/article/6391

我研究这个问题有一段时间了。

深埋在谷歌性能工具README

http://code.google.com/p/google-perftools/source/browse/trunk/README

谈到libunwind

http://www.nongnu.org/libunwind/

很乐意听听对这个图书馆的意见。

使用-rdynamic的问题是，在某些情况下，它会相对显著地增加二进制文件的大小

You are probably not going to like this - all I can say in its favour is that it works for me, and I have similar but not identical requirements: I am writing a compiler/transpiler for a 1970's Algol-like language which uses C as it's output and then compiles the C so that as far as the user is concerned, they're generally not aware of C being involved, so although you might call it a transpiler, it's effectively a compiler that uses C as it's intermediate code. The language being compiled has a history of providing good diagnostics and a full backtrace in the original native compilers. I've been able to find gcc compiler flags and libraries etc that allow me to trap most of the runtime errors that the original compilers did (although with one glaring exception - unassigned variable trapping). When a runtime error occurs (eg arithmetic overflow, divide by zero, array index out of bounds, etc) the original compilers output a backtrace to the console listing all variables in the stack frames of every active procedure call. I struggled to get this effect in C, but eventually did so with what can only be described as a hack... When the program is invoked, the wrapper that supplies the C "main" looks at its argv, and if a special option is not present, it restarts itself under gdb with an altered argv containing both gdb options and the 'magic' option string for the program itself. This restarted version then hides those strings from the user's code by restoring the original arguments before calling the main block of the code written in our language. When an error occurs (as long as it is not one explicitly trapped within the program by user code), it exits to gdb which prints the required backtrace.

启动序列中的关键代码行包括:

  if ((argc >= 1) && (strcmp(origargv[argc-1], "--restarting-under-gdb")) != 0) {
    // initial invocation
    // the "--restarting-under-gdb" option is how the copy running under gdb knows
    // not to start another gdb process.

and

  char *gdb [] = {
    "/usr/bin/gdb", "-q", "-batch", "-nx", "-nh", "-return-child-result",
    "-ex", "run",
    "-ex", "bt full",
    "--args"
  };

The original arguments are appended to the gdb options above. That should be enough of a hint for you to do something similar for your own system. I did look at other library-supported backtrace options (eg libbacktrace, https://codingrelic.geekhold.com/2010/09/gcc-function-instrumentation.html, etc) but they only output the procedure call stack, not the local variables. However if anyone knows of any cleaner mechanism to get a similar effect, do please let us know. The main downside to this is that the variables are printed in C syntax, not the syntax of the language the user writes in. And (until I add suitable #line directives on every generated line of C :-() the backtrace lists the C source file and line numbers.

G PS我使用的gcc编译选项是:

 GCCOPTS=" -Wall -Wno-return-type -Wno-comment -g -fsanitize=undefined
 -fsanitize-undefined-trap-on-error -fno-sanitize-recover=all -frecord-gcc-switches
 -fsanitize=float-divide-by-zero -fsanitize=float-cast-overflow -ftrapv
 -grecord-gcc-switches -O0 -ggdb3 "

在Linux/unix/MacOSX上使用核心文件(您可以通过ulimit或兼容的系统调用启用它们)。在Windows上使用Microsoft错误报告(您可以成为合作伙伴并访问您的应用程序崩溃数据)。

需要注意的是，一旦生成了核心文件，就需要使用gdb工具来查看它。为了让gdb理解你的核心文件，你必须告诉gcc用调试符号来检测二进制文件:要做到这一点，你需要使用-g标志进行编译:

$ g++ -g prog.cpp -o prog

然后，您可以设置“ulimit -c unlimited”来转储一个核心，或者只是在gdb中运行您的程序。我更喜欢第二种方法:

$ gdb ./prog
... gdb startup output ...
(gdb) run
... program runs and crashes ...
(gdb) where
... gdb outputs your stack trace ...

我希望这能有所帮助。

尽管已经提供了描述如何使用GNU libc backtrace()函数1的正确答案，并且我提供了自己的答案，描述了如何确保从信号处理程序的回溯指向fault2的实际位置，但我没有看到任何从回溯输出的要求c++符号的提及。

当从c++程序获得回溯时，可以通过c++filt1运行输出来要求符号，或者直接使用abi::__cxa_demangle1。

1 Linux & OS X 注意，c++filt和__cxa_demangle是特定于GCC的 2 Linux

下面的c++ Linux示例使用与我的其他答案相同的信号处理程序，并演示如何使用c++filt来要求符号。

代码:

class foo
{
public:
    foo() { foo1(); }

private:
    void foo1() { foo2(); }
    void foo2() { foo3(); }
    void foo3() { foo4(); }
    void foo4() { crash(); }
    void crash() { char * p = NULL; *p = 0; }
};

int main(int argc, char ** argv)
{
    // Setup signal handler for SIGSEGV
    ...

    foo * f = new foo();
    return 0;
}

输出(. /测试):

signal 11 (Segmentation fault), address is (nil) from 0x8048e07
[bt]: (1) ./test(crash__3foo+0x13) [0x8048e07]
[bt]: (2) ./test(foo4__3foo+0x12) [0x8048dee]
[bt]: (3) ./test(foo3__3foo+0x12) [0x8048dd6]
[bt]: (4) ./test(foo2__3foo+0x12) [0x8048dbe]
[bt]: (5) ./test(foo1__3foo+0x12) [0x8048da6]
[bt]: (6) ./test(__3foo+0x12) [0x8048d8e]
[bt]: (7) ./test(main+0xe0) [0x8048d18]
[bt]: (8) ./test(__libc_start_main+0x95) [0x42017589]
[bt]: (9) ./test(__register_frame_info+0x3d) [0x8048981]

需求输出(。/test 2>&1 | c++filt):

signal 11 (Segmentation fault), address is (nil) from 0x8048e07
[bt]: (1) ./test(foo::crash(void)+0x13) [0x8048e07]
[bt]: (2) ./test(foo::foo4(void)+0x12) [0x8048dee]
[bt]: (3) ./test(foo::foo3(void)+0x12) [0x8048dd6]
[bt]: (4) ./test(foo::foo2(void)+0x12) [0x8048dbe]
[bt]: (5) ./test(foo::foo1(void)+0x12) [0x8048da6]
[bt]: (6) ./test(foo::foo(void)+0x12) [0x8048d8e]
[bt]: (7) ./test(main+0xe0) [0x8048d18]
[bt]: (8) ./test(__libc_start_main+0x95) [0x42017589]
[bt]: (9) ./test(__register_frame_info+0x3d) [0x8048981]

下面的代码构建在我原来答案中的信号处理程序之上，可以替换上面示例中的信号处理程序，以演示如何使用abi::__cxa_demangle来提取符号。此信号处理程序产生与上面示例相同的需求输出。

代码:

void crit_err_hdlr(int sig_num, siginfo_t * info, void * ucontext)
{
    sig_ucontext_t * uc = (sig_ucontext_t *)ucontext;

    void * caller_address = (void *) uc->uc_mcontext.eip; // x86 specific

    std::cerr << "signal " << sig_num 
              << " (" << strsignal(sig_num) << "), address is " 
              << info->si_addr << " from " << caller_address 
              << std::endl << std::endl;

    void * array[50];
    int size = backtrace(array, 50);

    array[1] = caller_address;

    char ** messages = backtrace_symbols(array, size);    

    // skip first stack frame (points here)
    for (int i = 1; i < size && messages != NULL; ++i)
    {
        char *mangled_name = 0, *offset_begin = 0, *offset_end = 0;

        // find parantheses and +address offset surrounding mangled name
        for (char *p = messages[i]; *p; ++p)
        {
            if (*p == '(') 
            {
                mangled_name = p; 
            }
            else if (*p == '+') 
            {
                offset_begin = p;
            }
            else if (*p == ')')
            {
                offset_end = p;
                break;
            }
        }

        // if the line could be processed, attempt to demangle the symbol
        if (mangled_name && offset_begin && offset_end && 
            mangled_name < offset_begin)
        {
            *mangled_name++ = '\0';
            *offset_begin++ = '\0';
            *offset_end++ = '\0';

            int status;
            char * real_name = abi::__cxa_demangle(mangled_name, 0, 0, &status);

            // if demangling is successful, output the demangled function name
            if (status == 0)
            {    
                std::cerr << "[bt]: (" << i << ") " << messages[i] << " : " 
                          << real_name << "+" << offset_begin << offset_end 
                          << std::endl;

            }
            // otherwise, output the mangled function name
            else
            {
                std::cerr << "[bt]: (" << i << ") " << messages[i] << " : " 
                          << mangled_name << "+" << offset_begin << offset_end 
                          << std::endl;
            }
            free(real_name);
        }
        // otherwise, print the whole line
        else
        {
            std::cerr << "[bt]: (" << i << ") " << messages[i] << std::endl;
        }
    }
    std::cerr << std::endl;

    free(messages);

    exit(EXIT_FAILURE);
}