C编译过程

编译过程

编译C代码包括4个阶段,分为预处理、编译、汇编及链接。
C代码编译过程

预处理阶段

C的源文件包含宏(#define表示)和#include指令。#include指令包含源文件所依赖的头文件。预处理阶段扩展了源文件中的所有#define和#include指令,剩下的就是准备编译的纯C代码。

我们以编译hello world为例,使用gcc命令编译,-E参数告诉GCC在预处理后停止,-P参数使GCC忽略调试信息

#include <stdio.h>

#define FORMAT_STRING "%s"
#define MESSAGE	      "Hello, world!\n"

int main(int argc, char *argv[]){
	printf(FORMAT_STRING, MESSAGE);
	return 0;
}

编译结果

typedef long unsigned int size_t;
typedef unsigned char __u_char;
typedef unsigned short int __u_short;
typedef unsigned int __u_int;
typedef unsigned long int __u_long;
typedef signed char __int8_t;
typedef unsigned char __uint8_t;
typedef signed short int __int16_t;
typedef unsigned short int __uint16_t;
typedef signed int __int32_t;
typedef unsigned int __uint32_t;
typedef signed long int __int64_t;
typedef unsigned long int __uint64_t;
typedef long int __quad_t;
typedef unsigned long int __u_quad_t;
typedef long int __intmax_t;
typedef unsigned long int __uintmax_t;
typedef unsigned long int __dev_t;
typedef unsigned int __uid_t;
typedef unsigned int __gid_t;
typedef unsigned long int __ino_t;
typedef unsigned long int __ino64_t;
typedef unsigned int __mode_t;
typedef unsigned long int __nlink_t;
typedef long int __off_t;
typedef long int __off64_t;
typedef int __pid_t;
typedef struct { int __val[2]; } __fsid_t;
typedef long int __clock_t;
typedef unsigned long int __rlim_t;
typedef unsigned long int __rlim64_t;
typedef unsigned int __id_t;
typedef long int __time_t;
typedef unsigned int __useconds_t;
typedef long int __suseconds_t;
typedef int __daddr_t;
typedef int __key_t;
typedef int __clockid_t;
typedef void * __timer_t;
typedef long int __blksize_t;
typedef long int __blkcnt_t;
typedef long int __blkcnt64_t;
typedef unsigned long int __fsblkcnt_t;
typedef unsigned long int __fsblkcnt64_t;
typedef unsigned long int __fsfilcnt_t;
typedef unsigned long int __fsfilcnt64_t;
typedef long int __fsword_t;
typedef long int __ssize_t;
typedef long int __syscall_slong_t;
typedef unsigned long int __syscall_ulong_t;
typedef __off64_t __loff_t;
typedef char *__caddr_t;
typedef long int __intptr_t;
typedef unsigned int __socklen_t;
typedef int __sig_atomic_t;
struct _IO_FILE;
typedef struct _IO_FILE __FILE;
struct _IO_FILE;
typedef struct _IO_FILE FILE;
typedef struct
{
  int __count;
  union
  {
    unsigned int __wch;
    char __wchb[4];
  } __value;
} __mbstate_t;
typedef struct
{
  __off_t __pos;
  __mbstate_t __state;
} _G_fpos_t;
typedef struct
{
  __off64_t __pos;
  __mbstate_t __state;
} _G_fpos64_t;
typedef __builtin_va_list __gnuc_va_list;
struct _IO_jump_t; struct _IO_FILE;
typedef void _IO_lock_t;
struct _IO_marker {
  struct _IO_marker *_next;
  struct _IO_FILE *_sbuf;
  int _pos;
};
enum __codecvt_result
{
  __codecvt_ok,
  __codecvt_partial,
  __codecvt_error,
  __codecvt_noconv
};
struct _IO_FILE {
  int _flags;
  char* _IO_read_ptr;
  char* _IO_read_end;
  char* _IO_read_base;
  char* _IO_write_base;
  char* _IO_write_ptr;
  char* _IO_write_end;
  char* _IO_buf_base;
  char* _IO_buf_end;
  char *_IO_save_base;
  char *_IO_backup_base;
  char *_IO_save_end;
  struct _IO_marker *_markers;
  struct _IO_FILE *_chain;
  int _fileno;
  int _flags2;
  __off_t _old_offset;
  unsigned short _cur_column;
  signed char _vtable_offset;
  char _shortbuf[1];
  _IO_lock_t *_lock;
  __off64_t _offset;
  void *__pad1;
  void *__pad2;
  void *__pad3;
  void *__pad4;
  size_t __pad5;
  int _mode;
  char _unused2[15 * sizeof (int) - 4 * sizeof (void *) - sizeof (size_t)];
};
typedef struct _IO_FILE _IO_FILE;
struct _IO_FILE_plus;
extern struct _IO_FILE_plus _IO_2_1_stdin_;
extern struct _IO_FILE_plus _IO_2_1_stdout_;
extern struct _IO_FILE_plus _IO_2_1_stderr_;
typedef __ssize_t __io_read_fn (void *__cookie, char *__buf, size_t __nbytes);
typedef __ssize_t __io_write_fn (void *__cookie, const char *__buf,
     size_t __n);
typedef int __io_seek_fn (void *__cookie, __off64_t *__pos, int __w);
typedef int __io_close_fn (void *__cookie);
extern int __underflow (_IO_FILE *);
extern int __uflow (_IO_FILE *);
extern int __overflow (_IO_FILE *, int);
extern int _IO_getc (_IO_FILE *__fp);
extern int _IO_putc (int __c, _IO_FILE *__fp);
extern int _IO_feof (_IO_FILE *__fp) __attribute__ ((__nothrow__ , __leaf__));
extern int _IO_ferror (_IO_FILE *__fp) __attribute__ ((__nothrow__ , __leaf__));
extern int _IO_peekc_locked (_IO_FILE *__fp);
extern void _IO_flockfile (_IO_FILE *) __attribute__ ((__nothrow__ , __leaf__));
extern void _IO_funlockfile (_IO_FILE *) __attribute__ ((__nothrow__ , __leaf__));
extern int _IO_ftrylockfile (_IO_FILE *) __attribute__ ((__nothrow__ , __leaf__));
extern int _IO_vfscanf (_IO_FILE * __restrict, const char * __restrict,
   __gnuc_va_list, int *__restrict);
extern int _IO_vfprintf (_IO_FILE *__restrict, const char *__restrict,
    __gnuc_va_list);
extern __ssize_t _IO_padn (_IO_FILE *, int, __ssize_t);
extern size_t _IO_sgetn (_IO_FILE *, void *, size_t);
extern __off64_t _IO_seekoff (_IO_FILE *, __off64_t, int, int);
extern __off64_t _IO_seekpos (_IO_FILE *, __off64_t, int);
extern void _IO_free_backup_area (_IO_FILE *) __attribute__ ((__nothrow__ , __leaf__));
typedef __gnuc_va_list va_list;
typedef __off_t off_t;
typedef __ssize_t ssize_t;
typedef _G_fpos_t fpos_t;
extern struct _IO_FILE *stdin;
extern struct _IO_FILE *stdout;
extern struct _IO_FILE *stderr;
extern int remove (const char *__filename) __attribute__ ((__nothrow__ , __leaf__));
extern int rename (const char *__old, const char *__new) __attribute__ ((__nothrow__ , __leaf__));
extern int renameat (int __oldfd, const char *__old, int __newfd,
       const char *__new) __attribute__ ((__nothrow__ , __leaf__));
extern FILE *tmpfile (void) ;
extern char *tmpnam (char *__s) __attribute__ ((__nothrow__ , __leaf__)) ;
extern char *tmpnam_r (char *__s) __attribute__ ((__nothrow__ , __leaf__)) ;
extern char *tempnam (const char *__dir, const char *__pfx)
     __attribute__ ((__nothrow__ , __leaf__)) __attribute__ ((__malloc__)) ;
extern int fclose (FILE *__stream);
extern int fflush (FILE *__stream);
extern int fflush_unlocked (FILE *__stream);
extern FILE *fopen (const char *__restrict __filename,
      const char *__restrict __modes) ;
extern FILE *freopen (const char *__restrict __filename,
        const char *__restrict __modes,
        FILE *__restrict __stream) ;
extern FILE *fdopen (int __fd, const char *__modes) __attribute__ ((__nothrow__ , __leaf__)) ;
extern FILE *fmemopen (void *__s, size_t __len, const char *__modes)
  __attribute__ ((__nothrow__ , __leaf__)) ;
extern FILE *open_memstream (char **__bufloc, size_t *__sizeloc) __attribute__ ((__nothrow__ , __leaf__)) ;
extern void setbuf (FILE *__restrict __stream, char *__restrict __buf) __attribute__ ((__nothrow__ , __leaf__));
extern int setvbuf (FILE *__restrict __stream, char *__restrict __buf,
      int __modes, size_t __n) __attribute__ ((__nothrow__ , __leaf__));
extern void setbuffer (FILE *__restrict __stream, char *__restrict __buf,
         size_t __size) __attribute__ ((__nothrow__ , __leaf__));
extern void setlinebuf (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__));
extern int fprintf (FILE *__restrict __stream,
      const char *__restrict __format, ...);
extern int printf (const char *__restrict __format, ...);
extern int sprintf (char *__restrict __s,
      const char *__restrict __format, ...) __attribute__ ((__nothrow__));
extern int vfprintf (FILE *__restrict __s, const char *__restrict __format,
       __gnuc_va_list __arg);
extern int vprintf (const char *__restrict __format, __gnuc_va_list __arg);
extern int vsprintf (char *__restrict __s, const char *__restrict __format,
       __gnuc_va_list __arg) __attribute__ ((__nothrow__));
extern int snprintf (char *__restrict __s, size_t __maxlen,
       const char *__restrict __format, ...)
     __attribute__ ((__nothrow__)) __attribute__ ((__format__ (__printf__, 3, 4)));
extern int vsnprintf (char *__restrict __s, size_t __maxlen,
        const char *__restrict __format, __gnuc_va_list __arg)
     __attribute__ ((__nothrow__)) __attribute__ ((__format__ (__printf__, 3, 0)));
extern int vdprintf (int __fd, const char *__restrict __fmt,
       __gnuc_va_list __arg)
     __attribute__ ((__format__ (__printf__, 2, 0)));
extern int dprintf (int __fd, const char *__restrict __fmt, ...)
     __attribute__ ((__format__ (__printf__, 2, 3)));
extern int fscanf (FILE *__restrict __stream,
     const char *__restrict __format, ...) ;
extern int scanf (const char *__restrict __format, ...) ;
extern int sscanf (const char *__restrict __s,
     const char *__restrict __format, ...) __attribute__ ((__nothrow__ , __leaf__));
extern int fscanf (FILE *__restrict __stream, const char *__restrict __format, ...) __asm__ ("" "__isoc99_fscanf") ;
extern int scanf (const char *__restrict __format, ...) __asm__ ("" "__isoc99_scanf") ;
extern int sscanf (const char *__restrict __s, const char *__restrict __format, ...) __asm__ ("" "__isoc99_sscanf") __attribute__ ((__nothrow__ , __leaf__));
extern int vfscanf (FILE *__restrict __s, const char *__restrict __format,
      __gnuc_va_list __arg)
     __attribute__ ((__format__ (__scanf__, 2, 0))) ;
extern int vscanf (const char *__restrict __format, __gnuc_va_list __arg)
     __attribute__ ((__format__ (__scanf__, 1, 0))) ;
extern int vsscanf (const char *__restrict __s,
      const char *__restrict __format, __gnuc_va_list __arg)
     __attribute__ ((__nothrow__ , __leaf__)) __attribute__ ((__format__ (__scanf__, 2, 0)));
extern int vfscanf (FILE *__restrict __s, const char *__restrict __format, __gnuc_va_list __arg) __asm__ ("" "__isoc99_vfscanf")
     __attribute__ ((__format__ (__scanf__, 2, 0))) ;
extern int vscanf (const char *__restrict __format, __gnuc_va_list __arg) __asm__ ("" "__isoc99_vscanf")
     __attribute__ ((__format__ (__scanf__, 1, 0))) ;
extern int vsscanf (const char *__restrict __s, const char *__restrict __format, __gnuc_va_list __arg) __asm__ ("" "__isoc99_vsscanf") __attribute__ ((__nothrow__ , __leaf__))
     __attribute__ ((__format__ (__scanf__, 2, 0)));
extern int fgetc (FILE *__stream);
extern int getc (FILE *__stream);
extern int getchar (void);
extern int getc_unlocked (FILE *__stream);
extern int getchar_unlocked (void);
extern int fgetc_unlocked (FILE *__stream);
extern int fputc (int __c, FILE *__stream);
extern int putc (int __c, FILE *__stream);
extern int putchar (int __c);
extern int fputc_unlocked (int __c, FILE *__stream);
extern int putc_unlocked (int __c, FILE *__stream);
extern int putchar_unlocked (int __c);
extern int getw (FILE *__stream);
extern int putw (int __w, FILE *__stream);
extern char *fgets (char *__restrict __s, int __n, FILE *__restrict __stream)
     ;
extern __ssize_t __getdelim (char **__restrict __lineptr,
          size_t *__restrict __n, int __delimiter,
          FILE *__restrict __stream) ;
extern __ssize_t getdelim (char **__restrict __lineptr,
        size_t *__restrict __n, int __delimiter,
        FILE *__restrict __stream) ;
extern __ssize_t getline (char **__restrict __lineptr,
       size_t *__restrict __n,
       FILE *__restrict __stream) ;
extern int fputs (const char *__restrict __s, FILE *__restrict __stream);
extern int puts (const char *__s);
extern int ungetc (int __c, FILE *__stream);
extern size_t fread (void *__restrict __ptr, size_t __size,
       size_t __n, FILE *__restrict __stream) ;
extern size_t fwrite (const void *__restrict __ptr, size_t __size,
        size_t __n, FILE *__restrict __s);
extern size_t fread_unlocked (void *__restrict __ptr, size_t __size,
         size_t __n, FILE *__restrict __stream) ;
extern size_t fwrite_unlocked (const void *__restrict __ptr, size_t __size,
          size_t __n, FILE *__restrict __stream);
extern int fseek (FILE *__stream, long int __off, int __whence);
extern long int ftell (FILE *__stream) ;
extern void rewind (FILE *__stream);
extern int fseeko (FILE *__stream, __off_t __off, int __whence);
extern __off_t ftello (FILE *__stream) ;
extern int fgetpos (FILE *__restrict __stream, fpos_t *__restrict __pos);
extern int fsetpos (FILE *__stream, const fpos_t *__pos);
extern void clearerr (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__));
extern int feof (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
extern int ferror (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
extern void clearerr_unlocked (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__));
extern int feof_unlocked (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
extern int ferror_unlocked (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
extern void perror (const char *__s);
extern int sys_nerr;
extern const char *const sys_errlist[];
extern int fileno (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
extern int fileno_unlocked (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
extern FILE *popen (const char *__command, const char *__modes) ;
extern int pclose (FILE *__stream);
extern char *ctermid (char *__s) __attribute__ ((__nothrow__ , __leaf__));
extern void flockfile (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__));
extern int ftrylockfile (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
extern void funlockfile (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__));

int main(int argc, char *argv[]){
 printf("%s", "Hello, world!\n");
 return 0;
}

从编译的结果中可以看到,stdio.h头文件全部包含在内,其所有的类型定义、全局变量及函数原型都被复制到源文件中。预处理器还完整地扩展了#define定义的任何宏的所有用法。

编译阶段

预处理阶段完成后,就可以编译源代码了。编译阶段采用预处理代码并将代码转换为汇编语言。编译阶段的输出,是以人类可读的形式进行汇编的,其中的符号信息完整无缺。GCC的-S标志执行此操作,还可以传入-masm=intel,让它以Intel语法而不是默认的AT&T语法翻译汇编语言

	.file	"compilation_example.c"
	.intel_syntax noprefix
	.text
	.section	.rodata
.LC0:
	.string	"Hello, world!"
	.text
	.globl	main
	.type	main, @function
main:
.LFB0:
	.cfi_startproc
	push	rbp
	.cfi_def_cfa_offset 16
	.cfi_offset 6, -16
	mov	rbp, rsp
	.cfi_def_cfa_register 6
	sub	rsp, 16
	mov	DWORD PTR -4[rbp], edi
	mov	QWORD PTR -16[rbp], rsi
	lea	rdi, .LC0[rip]
	call	puts@PLT
	mov	eax, 0
	leave
	.cfi_def_cfa 7, 8
	ret
	.cfi_endproc
.LFE0:
	.size	main, .-main
	.ident	"GCC: (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0"
	.section	.note.GNU-stack,"",@progbits

汇编阶段

汇编阶段的输入是在编译阶段生成的汇编语言集,输出是一组对象文件,有时简称模块。对象文件原则上包含可由处理器执行的机器指令。通常每个源文件对应一个汇编文件,每个汇编文件对应一个对象文件。

在这里插入图片描述
第一部分显示了该文件符合二进制可执行文件的ELF规范,并且它是一个64位的ELF二进制文件,并且是最低有效位,这意味着数字在内存中的排序是以最低有效字节优先的,这个文件是可重定位的。

可重定位文件不依赖于放置在内存中的任何特定地址,他们可以随意移动,而不会破坏代码中的任何假设。对象文件相互独立编译,因此汇编程序在组装对象时无法知道其他对象文件的内存地址。

链接阶段

链接阶段是编译过程的最后阶段。执行链接阶段的程序被称为链接器或者链接编辑器。通常链接器与编译器相互独立,编译器通常实现前面的所有步骤。

对象文件是可重定位的,因为他们是相互独立编译的,这使得编译器无法假设对象最终会出现在任意特定的基址上。对象文件可以引用其他对象文件或程序外部库中的函数或者变量。在此链接阶段前,引用代码和数据的地址尚不清楚,因此对象文件只包含重定位符号,这些符号指定最终如何解析函数和变量引用。依赖于重定位符号的引用成为符号引用,当一个对象文件通过绝对地址引用自己的函数或变量时,该引用也会被符号化。

静态库被合并到二进制可执行文件中,允许完全解析对静态库的任何引用。还有动态库,他们在系统上运行的所有程序的内存中共享。因此,不是将库文件复制到使用它的每个二进制文件都需要使用此共享副本。在链接阶段,动态库将驻留的内存地址尚不清楚,因此无法解析对它们的引用。即使在最终的可执行文件中,链接器也会对这些库文件留下符号引用,并且在将二进制文件实际加载到要执行的内存中之前,不会解析这些引用。

在这里插入图片描述
file命令告诉你,这是一个ELF64位LSB可执行文件,而不是在汇编阶段结束时看到的可重定位文件,此外还有一个重要信息是文件是动态链接的,这意味着它使用的某些库未合并到可执行文件中,而是在同一系统上运行的所有程序之间共享。最后解释器/lib64/ld-linux-x86-64.so.2的文件输出告诉你,当可执行文件加载到内存中执行时,哪个动态链接器将会被用来解析动态库的最终依赖关系。

  • 1
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 1
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

平凡的学者

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值