这篇文章主要简单分析了linux下system函数，具有一定的参考价值，感兴趣的小伙伴们可以参考一下
简单分析了linux下system函数的相关内容，具体内容如下
int
libc_system (const char *line)
{
if (line == NULL)
/* Check that we have a command processor available. It might
not be available after a chroot(), for example. */
return do_system ("exit 0") == 0;
return do_system (line);
}
weak_alias (libc_system, system)代码位于glibc/sysdeps/posix/system.c，这里system是libc_system的弱别名，而libc_system是do_system的前端函数，进行了参数的检查，接下来看do_system函数。
static int
do_system (const char *line)
{
int status, save;
pid_t pid;
struct sigaction sa;
#ifndef _LIBC_REENTRANT
struct sigaction intr, quit;
#endif
sigset_t omask;
sa.sa_handler = SIG_IGN;
sa.sa_flags = 0;
sigemptyset (&sa.sa_mask);
DO_LOCK ();
if (ADD_REF () == 0)
{
if (sigaction (SIGINT, &sa, &intr) < 0)
{
(void) SUB_REF ();
goto out;
}
if (sigaction (SIGQUIT, &sa, &quit) < 0)
{
save = errno;
(void) SUB_REF ();
goto out_restore_sigint;
}
}
DO_UNLOCK ();
/* We reuse the bitmap in the 'sa' structure. */
sigaddset (&sa.sa_mask, SIGCHLD);
save = errno;
if (sigprocmask (SIG_BLOCK, &sa.sa_mask, &omask) < 0)
{
#ifndef _LIBC
if (errno == ENOSYS)
set_errno (save);
else
#endif
{
DO_LOCK ();
if (SUB_REF () == 0)
{
save = errno;
(void) sigaction (SIGQUIT, &quit, (struct sigaction *) NULL);
out_restore_sigint:
(void) sigaction (SIGINT, &intr, (struct sigaction *) NULL);
set_errno (save);
}
out:
DO_UNLOCK ();
return -1;
}
}
#ifdef CLEANUP_HANDLER
CLEANUP_HANDLER;
#endif
#ifdef FORK
pid = FORK ();
#else
pid = fork ();
#endif
if (pid == (pid_t) 0)
{
/* Child side. */
const char *new_argv[4];
new_argv[0] = SHELL_NAME;
new_argv[1] = "-c";
new_argv[2] = line;
new_argv[3] = NULL;
/* Restore the signals. */
(void) sigaction (SIGINT, &intr, (struct sigaction *) NULL);
(void) sigaction (SIGQUIT, &quit, (struct sigaction *) NULL);
(void) sigprocmask (SIG_SETMASK, &omask, (sigset_t *) NULL);
INIT_LOCK ();
/* Exec the shell. */
(void) execve (SHELL_PATH, (char *const *) new_argv, environ);
_exit (127);
}
else if (pid < (pid_t) 0)
/* The fork failed. */
status = -1;
else
/* Parent side. */
{
/* Note the system() is a cancellation point. But since we call
waitpid() which itself is a cancellation point we do not
have to do anything here. */
if (TEMP_FAILURE_RETRY (waitpid (pid, &status, 0)) != pid)
status = -1;
}
#ifdef CLEANUP_HANDLER
CLEANUP_RESET;
#endif
save = errno;
DO_LOCK ();
if ((SUB_REF () == 0
&& (sigaction (SIGINT, &intr, (struct sigaction *) NULL)
| sigaction (SIGQUIT, &quit, (struct sigaction *) NULL)) != 0)
|| sigprocmask (SIG_SETMASK, &omask, (sigset_t *) NULL) != 0)
{
#ifndef _LIBC
/* glibc cannot be used on systems without waitpid. */
if (errno == ENOSYS)
set_errno (save);
else
#endif
status = -1;
}
DO_UNLOCK ();
return status;
}
do_system首先函数设置了一些信号处理程序，来处理SIGINT和SIGQUIT信号，此处我们不过多关心，关键代码段在这里
#ifdef FORK
pid = FORK ();
#else
pid = fork ();
#endif
if (pid == (pid_t) 0)
{
/* Child side. */
const char *new_argv[4];
new_argv[0] = SHELL_NAME;
new_argv[1] = "-c";
new_argv[2] = line;
new_argv[3] = NULL;
/* Restore the signals. */
(void) sigaction (SIGINT, &intr, (struct sigaction *) NULL);
(void) sigaction (SIGQUIT, &quit, (struct sigaction *) NULL);
(void) sigprocmask (SIG_SETMASK, &omask, (sigset_t *) NULL);
INIT_LOCK ();
/* Exec the shell. */
(void) execve (SHELL_PATH, (char *const *) new_argv, environ);
_exit (127);
}
else if (pid < (pid_t) 0)
/* The fork failed. */
status = -1;
else
/* Parent side. */
{
/* Note the system() is a cancellation point. But since we call
waitpid() which itself is a cancellation point we do not
have to do anything here. */
if (TEMP_FAILURE_RETRY (waitpid (pid, &status, 0)) != pid)
status = -1;
}首先通过前端函数调用系统调用fork产生一个子进程，其中fork有两个返回值，对父进程返回子进程的pid，对子进程返回0。所以子进程执行6-24行代码，父进程执行30-35行代码。
子进程的逻辑非常清晰，调用execve执行SHELL_PATH指定的程序，参数通过new_argv传递，环境变量为全局变量environ。
其中SHELL_PATH和SHELL_NAME定义如下
#define SHELL_PATH "/bin/sh" /* Path of the shell. */ #define SHELL_NAME "sh" /* Name to give it. */
其实就是生成一个子进程调用/bin/sh -c "命令"来执行向system传入的命令。
下面其实是我研究system函数的原因与重点：
在CTF的pwn题中，通过栈溢出调用system函数有时会失败，听师傅们说是环境变量被覆盖，但是一直都是懵懂，今天深入学习了一下，总算搞明白了。
在这里system函数需要的环境变量储存在全局变量environ中，那么这个变量的内容是什么呢。
environ是在glibc/csu/libc-start.c中定义的，我们来看几个关键语句。
# define LIBC_START_MAIN libc_start_main
libc_start_main是_start调用的函数，这涉及到程序开始时的一些初始化工作，对这些名词不了解的话可以看一下这篇文章。接下来看LIBC_START_MAIN函数。
STATIC int
LIBC_START_MAIN (int (*main) (int, char **, char ** MAIN_AUXVEC_DECL),
int argc, char **argv,
#ifdef LIBC_START_MAIN_AUXVEC_ARG
ElfW(auxv_t) *auxvec,
#endif
typeof (main) init,
void (*fini) (void),
void (*rtld_fini) (void), void *stack_end)
{
/* Result of the 'main' function. */
int result;
libc_multiple_libcs = &_dl_starting_up && !_dl_starting_up;
#ifndef SHARED
char **ev = &argv[argc + 1];
environ = ev;
/* Store the lowest stack address. This is done in ld.so if this is
the code for the DSO. */
libc_stack_end = stack_end;
......
/* Nothing fancy, just call the function. */
result = main (argc, argv, environ MAIN_AUXVEC_PARAM);
#endif
exit (result);
}我们可以看到，在没有define SHARED的情况下，在第19行定义了environ的值。启动程序调用LIBC_START_MAIN之前，会先将环境变量和argv中的字符串保存起来（其实是保存到栈上），然后依次将环境变量中各项字符串的地址，argv中各项字符串的地址和argc入栈，所以环境变量数组一定位于argv数组的正后方，以一个空地址间隔。所以第17行的&argv[argc + 1]语句就是取环境变量数组在栈上的首地址，保存到ev中，最终保存到environ中。第203行调用main函数，会将environ的值入栈，这个被栈溢出覆盖掉没什么问题，只要保证environ中的地址处不被覆盖即可。
所以，当栈溢出的长度过大，溢出的内容覆盖了environ中地址中的重要内容时，调用system函数就会失败。具体环境变量距离溢出地址有多远，可以通过在_start中下断查看。
