编译过程

最新推荐文章于 2025-02-25 17:11:57 发布

L.G.F

最新推荐文章于 2025-02-25 17:11:57 发布

阅读量245

点赞数

分类专栏： C

本文链接：https://blog.youkuaiyun.com/u010659887/article/details/108916829

版权

C 专栏收录该内容

11 篇文章

订阅专栏

本文详细介绍了GCC对C语言代码的编译过程，包括预处理（处理宏定义、头文件等）、编译（生成汇编代码）、汇编（转换为机器代码）和链接（生成可执行文件）。在预处理阶段，头文件展开，宏定义被处理，#if条件语句按需展开；编译阶段将源代码翻译成汇编语言，并计算常量表达式；汇编阶段则将汇编代码转化为机器语言；最后链接阶段将所有目标文件合并为单一可执行文件。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

gcc对C语言的编译分为四个步骤：

预处理

预处理阶段会针对#开头的语句做处理，头文件和宏定义会展开直接插入到代码中，但是比如#if这样的判断会根据条件是否满足做展开处理。

#include <stdio.h>    //预处理阶段此处会展开
#include "io.h"    //预处理阶段会在此处展开
typedef struct
{
   int a;
   char b;
   short c;
}ST_HELLO;
#define WHILE(value) while((value) < 10)      //预处理阶段此处会展开
int main()
{
   int i = 0;
   show("hello");
   printf("%lu\n", sizeof(ST_HELLO));
   WHILE(i+1)
   {
     printf("hello\n");
     i++;
   }
   #if 0        //根据条件是否满足判断是否展开
   printf("Yes\n");
   #else
   printf("NO\n");
   #endif
}

接下来用作预处理，gcc -E hello.c -o hello.i ; -E选项是预处理选项，-o则是输出命令，由于stdio.h太大了，这里只截取一部分

extern char *ctermid (char *__s) __attribute__ ((__nothrow__ , __leaf__));
# 912 "/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__));
# 942 "/usr/include/stdio.h" 3 4

# 2 "hello.c" 2
# 1 "io.h" 1

# 1 "io.h"
extern void show(char *s);
# 3 "hello.c" 2
typedef struct
{
   int a;
   char b;
   short c;
}ST_HELLO;

int main()
{
   int i = 0;
   show("hello");
   printf("%lu\n", sizeof(ST_HELLO));
   while((i+1) < 10)
   {
     printf("hello\n");
     i++;
   }



   printf("NO\n"); 

}

很明显，头文件宏定义被展开，#if 0语句也被去除，其他没有变化，甚至多打的换行业依然存在，接下来就是编译阶段了。

编译

编译阶段会把展开后hello.i翻译成汇编语言：gcc -Og -S hello.c


	.file	"hello.c"
	.section	.rodata.str1.1,"aMS",@progbits,1
.LC0:
	.string	"hello"
.LC1:
	.string	"%lu\n"
.LC2:
	.string	"NO"
	.text
	.globl	main
	.type	main, @function
main:
.LFB23:
	.cfi_startproc
	pushq	%rbx    //将i压栈
	.cfi_def_cfa_offset 16
	.cfi_offset 3, -16
	movl	$.LC0, %edi
	call	show    //调用show函数
	movl	$8, %edx  //这里编译器已经将sizeof(ST_HELLO)的大小算出来了=8
	movl	$.LC1, %esi
	movl	$1, %edi
	movl	$0, %eax
	call	__printf_chk
	movl	$0, %ebx
	jmp	.L2
.L3:
	movl	$.LC0, %edi
	call	puts
.L2:
	addl	$1, %ebx
	cmpl	$9, %ebx
	jle	.L3
	movl	$.LC2, %edi
	call	puts
	movl	$0, %eax
	popq	%rbx
	.cfi_def_cfa_offset 8
	ret
	.cfi_endproc
.LFE23:
	.size	main, .-main
	.ident	"GCC: (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609"
	.section	.note.GNU-stack,"",@progbits

有意思的是这里已经将sizeof(ST_HELLO)的值算出来的，也就是说后面程序运行的时候就不需要再计算了。

这里代码比较难以理解，可以使用反汇编逐行对比：objdump -d -S -l hello

汇编

汇编将hello.s翻译成机器语言，生成一个重定位文件hello.o

gcc -c hello.c io.c 可以使用readelf命令查看hello.o的内容

ELF头	编译及系统信息
.text	已经编译程序的机器代码
.rodata	只读数据
.data	已经初始化的全局和静态变量
.bss	未初始化(初始化为0)的全局和静态变量
.symtab	符号表：全局变量函数
.rel.text	.text节的位置表，链接时用
.rel.data	.data节的位置表，链接时用
.debug	调试符号表
.line	代码行信息
.strtab	字符串表

ELF Header:
  Magic:   7f 45 4c 46 02 01 01 00 00 00 00 00 00 00 00 00 
  Class:                             ELF64
  Data:                              2's complement, little endian
  Version:                           1 (current)
  OS/ABI:                            UNIX - System V
  ABI Version:                       0
  Type:                              REL (Relocatable file)
  Machine:                           Advanced Micro Devices X86-64
  Version:                           0x1
  Entry point address:               0x0
  Start of program headers:          0 (bytes into file)
  Start of section headers:          2192 (bytes into file)
  Flags:                             0x0
  Size of this header:               64 (bytes)
  Size of program headers:           0 (bytes)
  Number of program headers:         0
  Size of section headers:           64 (bytes)
  Number of section headers:         21
  Section header string table index: 18

Section Headers:
  [Nr] Name              Type             Address           Offset
       Size              EntSize          Flags  Link  Info  Align
  [ 0]                   NULL             0000000000000000  00000000
       0000000000000000  0000000000000000           0     0     0
  [ 1] .text             PROGBITS         0000000000000000  00000040
       0000000000000059  0000000000000000  AX       0     0     1
  [ 2] .rela.text        RELA             0000000000000000  00000528
       00000000000000c0  0000000000000018   I      19     1     8
  [ 3] .data             PROGBITS         0000000000000000  00000099
       0000000000000000  0000000000000000  WA       0     0     1
  [ 4] .bss              NOBITS           0000000000000000  00000099
       0000000000000000  0000000000000000  WA       0     0     1
  [ 5] .rodata           PROGBITS         0000000000000000  00000099
       000000000000000e  0000000000000000   A       0     0     1
  [ 6] .debug_info       PROGBITS         0000000000000000  000000a7
       000000000000009e  0000000000000000           0     0     1
  [ 7] .rela.debug_info  RELA             0000000000000000  000005e8
       0000000000000198  0000000000000018   I      19     6     8
  [ 8] .debug_abbrev     PROGBITS         0000000000000000  00000145
       0000000000000051  0000000000000000           0     0     1
  [ 9] .debug_aranges    PROGBITS         0000000000000000  00000196
       0000000000000030  0000000000000000           0     0     1
  [10] .rela.debug_arang RELA             0000000000000000  00000780
       0000000000000030  0000000000000018   I      19     9     8
  [11] .debug_line       PROGBITS         0000000000000000  000001c6
       0000000000000045  0000000000000000           0     0     1
  [12] .rela.debug_line  RELA             0000000000000000  000007b0
       0000000000000018  0000000000000018   I      19    11     8
  [13] .debug_str        PROGBITS         0000000000000000  0000020b
       00000000000000db  0000000000000001  MS       0     0     1
  [14] .comment          PROGBITS         0000000000000000  000002e6
       0000000000000036  0000000000000001  MS       0     0     1
  [15] .note.GNU-stack   PROGBITS         0000000000000000  0000031c
       0000000000000000  0000000000000000           0     0     1
  [16] .eh_frame         PROGBITS         0000000000000000  00000320
       0000000000000038  0000000000000000   A       0     0     8
  [17] .rela.eh_frame    RELA             0000000000000000  000007c8
       0000000000000018  0000000000000018   I      19    16     8
  [18] .shstrtab         STRTAB           0000000000000000  000007e0
       00000000000000b0  0000000000000000           0     0     1
  [19] .symtab           SYMTAB           0000000000000000  00000358
       00000000000001b0  0000000000000018          20    14     8
  [20] .strtab           STRTAB           0000000000000000  00000508
       000000000000001f  0000000000000000           0     0     1
Key to Flags:
  W (write), A (alloc), X (execute), M (merge), S (strings), l (large)
  I (info), L (link order), G (group), T (TLS), E (exclude), x (unknown)
  O (extra OS processing required) o (OS specific), p (processor specific)

There are no section groups in this file.

There are no program headers in this file.

Relocation section '.rela.text' at offset 0x528 contains 8 entries:
  Offset          Info           Type           Sym. Value    Sym. Name + Addend
000000000010  00050000000a R_X86_64_32       0000000000000000 .rodata + 0
000000000015  000f00000002 R_X86_64_PC32     0000000000000000 show - 4
00000000001f  00050000000a R_X86_64_32       0000000000000000 .rodata + 6
000000000029  001000000002 R_X86_64_PC32     0000000000000000 printf - 4
000000000030  00050000000a R_X86_64_32       0000000000000000 .rodata + 0
000000000035  001100000002 R_X86_64_PC32     0000000000000000 puts - 4
000000000049  00050000000a R_X86_64_32       0000000000000000 .rodata + b
00000000004e  001100000002 R_X86_64_PC32     0000000000000000 puts - 4

Relocation section '.rela.debug_info' at offset 0x5e8 contains 17 entries:
  Offset          Info           Type           Sym. Value    Sym. Name + Addend
000000000006  00070000000a R_X86_64_32       0000000000000000 .debug_abbrev + 0
00000000000c  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 8b
000000000011  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 5b
000000000015  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 63
000000000019  000200000001 R_X86_64_64       0000000000000000 .text + 0
000000000029  00090000000a R_X86_64_32       0000000000000000 .debug_line + 0
000000000030  000a0000000a R_X86_64_32       0000000000000000 .debug_str + d
000000000037  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 1f
00000000003e  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 39
000000000045  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 0
00000000004c  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 2d
000000000053  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 4c
000000000061  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 74
000000000068  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 7d
00000000006f  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 56
000000000074  000a0000000a R_X86_64_32       0000000000000000 .debug_str + 86
00000000007e  000200000001 R_X86_64_64       0000000000000000 .text + 0

Relocation section '.rela.debug_aranges' at offset 0x780 contains 2 entries:
  Offset          Info           Type           Sym. Value    Sym. Name + Addend
000000000006  00060000000a R_X86_64_32       0000000000000000 .debug_info + 0
000000000010  000200000001 R_X86_64_64       0000000000000000 .text + 0

Relocation section '.rela.debug_line' at offset 0x7b0 contains 1 entries:
  Offset          Info           Type           Sym. Value    Sym. Name + Addend
00000000002b  000200000001 R_X86_64_64       0000000000000000 .text + 0

Relocation section '.rela.eh_frame' at offset 0x7c8 contains 1 entries:
  Offset          Info           Type           Sym. Value    Sym. Name + Addend
000000000020  000200000002 R_X86_64_PC32     0000000000000000 .text + 0

The decoding of unwind sections for machine type Advanced Micro Devices X86-64 is not currently supported.

Symbol table '.symtab' contains 18 entries:
   Num:    Value          Size Type    Bind   Vis      Ndx Name
     0: 0000000000000000     0 NOTYPE  LOCAL  DEFAULT  UND 
     1: 0000000000000000     0 FILE    LOCAL  DEFAULT  ABS hello.c
     2: 0000000000000000     0 SECTION LOCAL  DEFAULT    1 
     3: 0000000000000000     0 SECTION LOCAL  DEFAULT    3 
     4: 0000000000000000     0 SECTION LOCAL  DEFAULT    4 
     5: 0000000000000000     0 SECTION LOCAL  DEFAULT    5 
     6: 0000000000000000     0 SECTION LOCAL  DEFAULT    6 
     7: 0000000000000000     0 SECTION LOCAL  DEFAULT    8 
     8: 0000000000000000     0 SECTION LOCAL  DEFAULT    9 
     9: 0000000000000000     0 SECTION LOCAL  DEFAULT   11 
    10: 0000000000000000     0 SECTION LOCAL  DEFAULT   13 
    11: 0000000000000000     0 SECTION LOCAL  DEFAULT   15 
    12: 0000000000000000     0 SECTION LOCAL  DEFAULT   16 
    13: 0000000000000000     0 SECTION LOCAL  DEFAULT   14 
    14: 0000000000000000    89 FUNC    GLOBAL DEFAULT    1 main
    15: 0000000000000000     0 NOTYPE  GLOBAL DEFAULT  UND show
    16: 0000000000000000     0 NOTYPE  GLOBAL DEFAULT  UND printf
    17: 0000000000000000     0 NOTYPE  GLOBAL DEFAULT  UND puts

No version information found in this file.