Linux C编译器从零开发一

基础程序汇编

test.c

int main() { return 42; }

查看反汇编

cc -o test test.c objdump -d -M intel test 0000000000001129 <main>: 1129: f3 0f 1e fa endbr64 112d: 55 push rbp 112e: 48 89 e5 mov rbp,rsp 1131: b8 2a 00 00 00 mov eax,0x2a 1136: 5d pop rbp 1137: c3 ret

函数参数汇编

test.c

int plus(int x, int y) {
return x + y;
}

int main() {
return plus(3, 4);
}

.intel_syntax noprefix
.globl plus, main

plus:
add rsi, rdi
mov rax, rsi
ret

main:
mov rdi, 3
mov rsi, 4
call plus
ret

.globl开头表示函数整个程序可见
call原理

• call将下一条指令（在本例中）ret的地址推入堆栈
• call跳转到作为参数给出的地址

自定义编译器编译基础程序

test.c

#include <stdio.h> #include <stdlib.h> int main(int argc, char **argv) { if (argc != 2) { fprintf(stderr, "Please input a Number:\n"); return 1; } printf(".intel_syntax noprefix\n"); printf(".globl main\n"); printf("main:\n"); printf(" mov rax, %d\n", atoi(argv[1])); printf(" ret\n"); return 0; }

编译运行

cc -o test test.c ./test 42 > test.s cc -o tmp test.s ./tmp echo $?

自定义编译器编译加减法程序

test.c

#include <stdio.h> #include <stdlib.h> int main(int argc, char **argv) { if (argc != 2) { fprintf(stderr, "Please input a Number\n"); return 1; } char *p = argv[1]; printf(".intel_syntax noprefix\n"); printf(".globl main\n"); printf("main:\n"); printf(" mov rax, %ld\n", strtol(p, &p, 10)); // strtol读取数字，读完自动跳到下个符号 while (*p) { if (*p == '+') { p++; printf(" add rax, %ld\n", strtol(p, &p, 10)); continue; } if (*p == '-') { p++; printf(" sub rax, %ld\n", strtol(p, &p, 10)); continue; } fprintf(stderr, "illegal sign '%c'\n", *p); return 1; } printf(" ret\n"); return 0; }

编译

cc -o test test.c ./test 12+3+4 > tmp.s cc -o tmp tmp.s ./tmp echo $? ./test 1*3 > tmp.s //会提示非法符号

测试

test.sh

#!/bin/bash assert() { expected="$1" input="$2" ./chibicc "$input" > tmp.s || exit gcc -static -o tmp tmp.s ./tmp actual="$?" if [ "$actual" = "$expected" ]; then echo "$input => $actual" else echo "$input => $expected expected, but got $actual" exit 1 fi } assert 0 0 assert 42 42 assert 21 '5+20-4' echo OK

参考

Compiler Explorer

创作不易，小小的支持一下吧！