萌新的学习笔记,写错了恳请斧正。
目录
在ANSI C的标准中,源代码先经过翻译环境生成可执行程序,再于运行环境中执行
翻译环境由编译与链接两个过程组成
一个C语言项目可能存在多个.c文件,在编译的过程中,编译器处理每个.c文件产生对应的目标文件(在Windows下目标文件后缀默认为.obj,Linux下默认为.o)
在链接的过程中,多个目标文件和链接库一起经过链接器最终生成一个可执行程序文件
编译的过程又分为三个部分:预处理、编译、汇编
以Linux系统为例,每个.c为后缀的文件和其所包含的头文件预处理后变成.i为后缀的预处理源码文件,在经过编译成为.s为后缀的汇编源码文件,最后在汇编的过程产生.o为后缀的二进制目标文件
在Linux gcc环境下,我们通过如下指令生成test.c对应的预处理文件test.i:
$ cd 所在路径
$ gcc test.c -E -o test.i
预处理阶段主要是处理那些源文件中以#开始的预编译指令,比如#include、#define
处理的规则如下(具体的预处理指令含义下面讲,这里仅介绍规则):
比方说某test.c文件如下:
#include <stdio.h>
int g_val = 1919810;
int main()
{
printf("114514\n");
printf("%d\n", g_val);
return 0;
}
在本人安装gcc13.1.0的Windows的WSL2子系统Ubuntu 20.04.6 LTS中得到的test.i如下:
# 0 "test.c"
# 0 "<built-in>"
# 0 "<命令行>"
# 1 "/usr/include/stdc-predef.h" 1 3 4
# 0 "<命令行>" 2
# 1 "test.c"
# 1 "/usr/include/stdio.h" 1 3 4
# 27 "/usr/include/stdio.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/libc-header-start.h" 1 3 4
# 33 "/usr/include/x86_64-linux-gnu/bits/libc-header-start.h" 3 4
# 1 "/usr/include/features.h" 1 3 4
# 461 "/usr/include/features.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/sys/cdefs.h" 1 3 4
# 452 "/usr/include/x86_64-linux-gnu/sys/cdefs.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/wordsize.h" 1 3 4
# 453 "/usr/include/x86_64-linux-gnu/sys/cdefs.h" 2 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/long-double.h" 1 3 4
# 454 "/usr/include/x86_64-linux-gnu/sys/cdefs.h" 2 3 4
# 462 "/usr/include/features.h" 2 3 4
# 485 "/usr/include/features.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/gnu/stubs.h" 1 3 4
# 10 "/usr/include/x86_64-linux-gnu/gnu/stubs.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/gnu/stubs-64.h" 1 3 4
# 11 "/usr/include/x86_64-linux-gnu/gnu/stubs.h" 2 3 4
# 486 "/usr/include/features.h" 2 3 4
# 34 "/usr/include/x86_64-linux-gnu/bits/libc-header-start.h" 2 3 4
# 28 "/usr/include/stdio.h" 2 3 4
# 1 "/usr/local/lib/gcc/x86_64-pc-linux-gnu/13.1.0/include/stddef.h" 1 3 4
# 214 "/usr/local/lib/gcc/x86_64-pc-linux-gnu/13.1.0/include/stddef.h" 3 4
# 214 "/usr/local/lib/gcc/x86_64-pc-linux-gnu/13.1.0/include/stddef.h" 3 4
typedef long unsigned int size_t;
# 34 "/usr/include/stdio.h" 2 3 4
# 1 "/usr/local/lib/gcc/x86_64-pc-linux-gnu/13.1.0/include/stdarg.h" 1 3 4
# 40 "/usr/local/lib/gcc/x86_64-pc-linux-gnu/13.1.0/include/stdarg.h" 3 4
typedef __builtin_va_list __gnuc_va_list;
# 37 "/usr/include/stdio.h" 2 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/types.h" 1 3 4
# 27 "/usr/include/x86_64-linux-gnu/bits/types.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/wordsize.h" 1 3 4
# 28 "/usr/include/x86_64-linux-gnu/bits/types.h" 2 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/timesize.h" 1 3 4
# 29 "/usr/include/x86_64-linux-gnu/bits/types.h" 2 3 4
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 __int8_t __int_least8_t;
typedef __uint8_t __uint_least8_t;
typedef __int16_t __int_least16_t;
typedef __uint16_t __uint_least16_t;
typedef __int32_t __int_least32_t;
typedef __uint32_t __uint_least32_t;
typedef __int64_t __int_least64_t;
typedef __uint64_t __uint_least64_t;
typedef long int __quad_t;
typedef unsigned long int __u_quad_t;
typedef long int __intmax_t;
typedef unsigned long int __uintmax_t;
# 141 "/usr/include/x86_64-linux-gnu/bits/types.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/typesizes.h" 1 3 4
# 142 "/usr/include/x86_64-linux-gnu/bits/types.h" 2 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/time64.h" 1 3 4
# 143 "/usr/include/x86_64-linux-gnu/bits/types.h" 2 3 4
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;
# 39 "/usr/include/stdio.h" 2 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h" 1 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h" 1 3 4
# 13 "/usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h" 3 4
typedef struct
{
int __count;
union
{
unsigned int __wch;
char __wchb[4];
} __value;
} __mbstate_t;
# 6 "/usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h" 2 3 4
typedef struct _G_fpos_t
{
__off_t __pos;
__mbstate_t __state;
} __fpos_t;
# 40 "/usr/include/stdio.h" 2 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h" 1 3 4
# 10 "/usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h" 3 4
typedef struct _G_fpos64_t
{
__off64_t __pos;
__mbstate_t __state;
} __fpos64_t;
# 41 "/usr/include/stdio.h" 2 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/types/__FILE.h" 1 3 4
struct _IO_FILE;
typedef struct _IO_FILE __FILE;
# 42 "/usr/include/stdio.h" 2 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/types/FILE.h" 1 3 4
struct _IO_FILE;
typedef struct _IO_FILE FILE;
# 43 "/usr/include/stdio.h" 2 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h" 1 3 4
# 35 "/usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h" 3 4
struct _IO_FILE;
struct _IO_marker;
struct _IO_codecvt;
struct _IO_wide_data;
typedef void _IO_lock_t;
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;
struct _IO_codecvt *_codecvt;
struct _IO_wide_data *_wide_data;
struct _IO_FILE *_freeres_list;
void *_freeres_buf;
size_t __pad5;
int _mode;
char _unused2[15 * sizeof (int) - 4 * sizeof (void *) - sizeof (size_t)];
};
# 44 "/usr/include/stdio.h" 2 3 4
# 52 "/usr/include/stdio.h" 3 4
typedef __gnuc_va_list va_list;
# 63 "/usr/include/stdio.h" 3 4
typedef __off_t off_t;
# 77 "/usr/include/stdio.h" 3 4
typedef __ssize_t ssize_t;
typedef __fpos_t fpos_t;
# 133 "/usr/include/stdio.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/stdio_lim.h" 1 3 4
# 134 "/usr/include/stdio.h" 2 3 4
extern FILE *stdin;
extern FILE *stdout;
extern 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__));
# 173 "/usr/include/stdio.h" 3 4
extern FILE *tmpfile (void) ;
# 187 "/usr/include/stdio.h" 3 4
extern char *tmpnam (char *__s) __attribute__ ((__nothrow__ , __leaf__)) ;
extern char *tmpnam_r (char *__s) __attribute__ ((__nothrow__ , __leaf__)) ;
# 204 "/usr/include/stdio.h" 3 4
extern char *tempnam (const char *__dir, const char *__pfx)
__attribute__ ((__nothrow__ , __leaf__)) __attribute__ ((__malloc__)) ;
extern int fclose (FILE *__stream);
extern int fflush (FILE *__stream);
# 227 "/usr/include/stdio.h" 3 4
extern int fflush_unlocked (FILE *__stream);
# 246 "/usr/include/stdio.h" 3 4
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) ;
# 279 "/usr/include/stdio.h" 3 4
extern FILE *fdopen (int __fd, const char *__modes) __attribute__ ((__nothrow__ , __leaf__)) ;
# 292 "/usr/include/stdio.h" 3 4
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)));
# 379 "/usr/include/stdio.h" 3 4
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__))
;
# 432 "/usr/include/stdio.h" 3 4
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)));
# 485 "/usr/include/stdio.h" 3 4
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);
# 510 "/usr/include/stdio.h" 3 4
extern int fgetc_unlocked (FILE *__stream);
# 521 "/usr/include/stdio.h" 3 4
extern int fputc (int __c, FILE *__stream);
extern int putc (int __c, FILE *__stream);
extern int putchar (int __c);
# 537 "/usr/include/stdio.h" 3 4
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)
;
# 603 "/usr/include/stdio.h" 3 4
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);
# 673 "/usr/include/stdio.h" 3 4
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);
# 707 "/usr/include/stdio.h" 3 4
extern int fseeko (FILE *__stream, __off_t __off, int __whence);
extern __off_t ftello (FILE *__stream) ;
# 731 "/usr/include/stdio.h" 3 4
extern int fgetpos (FILE *__restrict __stream, fpos_t *__restrict __pos);
extern int fsetpos (FILE *__stream, const fpos_t *__pos);
# 757 "/usr/include/stdio.h" 3 4
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);
# 1 "/usr/include/x86_64-linux-gnu/bits/sys_errlist.h" 1 3 4
# 26 "/usr/include/x86_64-linux-gnu/bits/sys_errlist.h" 3 4
extern int sys_nerr;
extern const char *const sys_errlist[];
# 782 "/usr/include/stdio.h" 2 3 4
extern int fileno (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
extern int fileno_unlocked (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
# 800 "/usr/include/stdio.h" 3 4
extern FILE *popen (const char *__command, const char *__modes) ;
extern int pclose (FILE *__stream);
extern char *ctermid (char *__s) __attribute__ ((__nothrow__ , __leaf__));
# 840 "/usr/include/stdio.h" 3 4
extern void flockfile (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__));
extern int ftrylockfile (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
extern void funlockfile (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__));
# 858 "/usr/include/stdio.h" 3 4
extern int __uflow (FILE *);
extern int __overflow (FILE *, int);
# 873 "/usr/include/stdio.h" 3 4
# 2 "test.c" 2
# 3 "test.c"
int g_val = 1919810;
int main()
{
printf("114514\n");
printf("%d\n", g_val);
return 0;
}
在Linux gcc环境下,我们通过如下指令生成test.i对应的预处理文件test.s:
$ cd 所在路径
$ gcc -s test.i -o test.s
编译的过程就是将预处理后的文件进行一系列的:词法分析、语法分析、语义分析、优化,生成相应的汇编语言代码文件
比方说上面的test.i在该环境下进一步编译得到的test.s为:
.file "test.c"
.text
.globl g_val
.data
.align 4
.type g_val, @object
.size g_val, 4
g_val:
.long 1919810
.section .rodata
.LC0:
.string "114514"
.LC1:
.string "%d\n"
.text
.globl main
.type main, @function
main:
.LFB0:
.cfi_startproc
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
movq %rsp, %rbp
.cfi_def_cfa_register 6
movl $.LC0, %edi
call puts
movl g_val(%rip), %eax
movl %eax, %esi
movl $.LC1, %edi
movl $0, %eax
call printf
movl $0, %eax
popq %rbp
.cfi_def_cfa 7, 8
ret
.cfi_endproc
.LFE0:
.size main, .-main
.ident "GCC: (GNU) 13.1.0"
.section .note.GNU-stack,"",@progbits
在Linux gcc环境下,我们通过如下指令生成test.s对应的目标文件test.o:
$ cd 所在路径
$ gcc -c test.s -o test.o
这一阶段,汇编器将汇编代码直接变成机器可执行的指令
得到的test.o是一种二进制文件
链接用于解决一个项目中存在多个文件、多模块之间互相调用的问题
链接是一个复杂的过程,涉及到地址和空间分配、符号决议、重定位等步骤
比如我们在源文件a中调用源文件b的内容,在编译时这里的相关地址就会被搁置。在链接时,链接器根据引用的符号在其他模块中去寻找相关内容,然后将这些含引用的指令重新修正,让它们操作的地址为真正应该操作的地址。这就是重定位。
其他的这里不多作介绍了(咱也不会)
首先程序必须被载入内存中。在有操作系统的环境下,这个操作一般就直接由操作系统完成;在独立环境中,程序的载入可能需要人工进行。
随后程序开始执行,调用main函数,逐步执行程序代码。此时程序有一个运行时堆栈用于存储函数的局部变量和返回地址。同时程序可以使用静态内存。
最后就是程序的终止,没什么好说的。