【程序员的自我修养—编译和链接】
IDE或者编译器的构建过程
构建过程分为4个过程：预处理、编译、汇编、链接。
通过gcc命令来进行编译，实际上是对 预编译程序cc1、汇编器as、连接器ld的封装，可以直接使用这些命令来得到对应的文件。
以"hello world"程序为例子，整个过程可以用如下的图表示。
#include
int main() {
printf("Hello World!\n");
return 0;
}
// 编译执行的过程如下
// gcc hello.c
// ./a.out 
预编译
gcc -E hello.c -o hello.i
# or
cpp hello.c > hello.i处理 #define 和 #include 等预编译指令，处理规则：
- #删除 #define ，展开宏定义；
- 处理条件编译，如 #if
- 处理 #include，将被包含的文件插入到该预编译指令的位置（递归展开）；
- 删除所有注释
- 添加行号和文件名标识，用于编译和调试产生错误或者警告能够显示行号；
- 保留#pragma编译器指令；
预编译后的文件如下：
# 1 "hello.c"
# 1 ""
# 1 ""
# 31 ""
# 1 "/usr/include/stdc-predef.h" 1 3 4
# 32 "" 2
# 1 "hello.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/lib/gcc/x86_64-linux-gnu/9/include/stddef.h" 1 3 4
# 209 "/usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h" 3 4
# 209 "/usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h" 3 4
typedef long unsigned int size_t;
# 34 "/usr/include/stdio.h" 2 3 4
# 1 "/usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.h" 1 3 4
# 40 "/usr/lib/gcc/x86_64-linux-gnu/9/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 "hello.c" 2
# 2 "hello.c"
int main() {
printf("Hello World!\n");
return 0;
}
编译
编译过程就是把预处理的文件进行词法分析、语法分析、语义分析及优化后生成对应的汇编代码。
gcc -S hello.i -o hello.s或者直接将预编译和编译合在一起执行
gcc -S hello.c -o hello.s
# 也可以直接调用后台程序
/usr/lib/gcc/x86_64-linux-gnu/9/cc1 hello.c
编译过程如下：
Ubuntu20.04系统遇到 fatal error: bits/libc-header-start.h: No such file or directory，通过安装系统库完成。
sudo apt-get install gcc-multilib
汇编
汇编就是将汇编代码转换为机器可以执行的指令。
as hello.s -o hello.o
# or
gcc -C hello.s -o hello.o
# or
gcc -C hello.c -o hello.o链接
将多个 .o 文件链接在一起可到可执行文件。
编译器的作用
编译过程：扫描、语法分析、语义分析、源代码优化、代码生成和目标代码优化。
词法分析
将代码分割成一系列记号：
关键字、标识符、字面量（数字和字符串等）和特殊符号（如加号、等号）
将标识符放到符号表，将字面量放到文字表中
语法分析和语义分析
语法分析会将记号生成为一个语法树，会进行表达式检查如括号不匹配等；
语义分析会将语法树的表达式标记上类型，这个过程会进行一些类型转换的检查等。
中间语言生成
这个过程会对源码进行一些优化，如一些编译期能确定的值会被优化掉
还会生成中间代码，比如：三地址码和P-代码
中间代码使得编译器可以被分为前端和后端：
- 前端：产生与机器无关的中间代码
- 后端：将中间代码转换为目标机器代码（不同的平台能针对性调整）
目标代码生成和优化
- 代码生成：依赖目标机器（不同机器有不同的字长、寄存器、数据类型等）
- 代码优化：比如选择合适的寻址方式、使用位移代替乘法运算，删除多余指令等
在这个过程中一些变量的地址还未确定，要在链接器将所有目标文件链接在一起形成可执行文件才能确定。
链接器的作用
随着代码量的增加，考虑到日后的阅读、修改和维护等，需要将程序划分为不同的模块，将不同的模块重新组合执行的过程称为链接。
例如静态语言C/C++中，会以函数和变量为单位组成一个模块，不同的模块之间需要通过目标函数或者目标变量的符号（地址）进行访问，这个过程类似于拼图（定义符号的模块多一块，引用符合的模块少一块），整个拼接的过程称为链接。
静态链接
将每个源代码文件独立编译，按照需要组装的过程称为链接，包括：地址和空间分配、符合决议和重定位等步骤。
最基本静态链接过程是将目标文件和库一起链接形成可执行文件。
- 库：如运行时库，是支持程序允许的基本函数的集合，打包成一组目标文件存放。
重定位：
例如编写两个文件A和B，全局变量var在A中，在B中需要访问var并且赋值；
由于编译文件B的时候并不知道var的地址，编译器默认将该地址置为0；
等所有目标文件被链接一起后，需要重新修正该地址，这个过程被称为重定位，每个被修正的位置被称为重定位入口