unicorn入门篇

1、准备

Python开发环境

unicorn官网

unicorn仓库地址

https://github.com/unicorn-engine/unicorn

2、安装

pip install unicorn

3、简单跑起来

这里使用官方示例
https://github.com/unicorn-engine/unicorn/blob/master/bindings/python/sample_arm.py

#!/usr/bin/env python
# Sample code for ARM of Unicorn. Nguyen Anh Quynh <aquynh@gmail.com>
# Python sample ported by Loi Anh Tuan <loianhtuan@gmail.com>

from __future__ import print_function
from unicorn import *
from unicorn.arm_const import *


# code to be emulated
ARM_CODE   = b"\x37\x00\xa0\xe3\x03\x10\x42\xe0" # mov r0, #0x37; sub r1, r2, r3
THUMB_CODE = b"\x83\xb0" # sub    sp, #0xc
# memory address where emulation starts
ADDRESS    = 0x10000


# callback for tracing basic blocks
def hook_block(uc, address, size, user_data):
    print(">>> Tracing basic block at 0x%x, block size = 0x%x" %(address, size))


# callback for tracing instructions
def hook_code(uc, address, size, user_data):
    print(">>> Tracing instruction at 0x%x, instruction size = 0x%x" %(address, size))


# Test ARM
def test_arm():
    print("Emulate ARM code")
    try:
        # Initialize emulator in ARM mode
        mu = Uc(UC_ARCH_ARM, UC_MODE_ARM)

        # map 2MB memory for this emulation
        mu.mem_map(ADDRESS, 2 * 1024 * 1024)

        # write machine code to be emulated to memory
        mu.mem_write(ADDRESS, ARM_CODE)

        # initialize machine registers
        mu.reg_write(UC_ARM_REG_R0, 0x1234)
        mu.reg_write(UC_ARM_REG_R2, 0x6789)
        mu.reg_write(UC_ARM_REG_R3, 0x3333)
        mu.reg_write(UC_ARM_REG_APSR, 0xFFFFFFFF) #All application flags turned on
   
        # tracing all basic blocks with customized callback
        mu.hook_add(UC_HOOK_BLOCK, hook_block)

        # tracing one instruction at ADDRESS with customized callback
        mu.hook_add(UC_HOOK_CODE, hook_code, begin=ADDRESS, end=ADDRESS)

        # emulate machine code in infinite time
        mu.emu_start(ADDRESS, ADDRESS + len(ARM_CODE))

        # now print out some registers
        print(">>> Emulation done. Below is the CPU context")

        r0 = mu.reg_read(UC_ARM_REG_R0)
        r1 = mu.reg_read(UC_ARM_REG_R1)
        print(">>> R0 = 0x%x" %r0)
        print(">>> R1 = 0x%x" %r1)

    except UcError as e:
        print("ERROR: %s" % e)


def test_thumb():
    print("Emulate THUMB code")
    try:
        # Initialize emulator in thumb mode
        mu = Uc(UC_ARCH_ARM, UC_MODE_THUMB)

        # map 2MB memory for this emulation
        mu.mem_map(ADDRESS, 2 * 1024 * 1024)

        # write machine code to be emulated to memory
        mu.mem_write(ADDRESS, THUMB_CODE)

        # initialize machine registers
        mu.reg_write(UC_ARM_REG_SP, 0x1234)

        # tracing all basic blocks with customized callback
        mu.hook_add(UC_HOOK_BLOCK, hook_block)

        # tracing all instructions with customized callback
        mu.hook_add(UC_HOOK_CODE, hook_code)

        # emulate machine code in infinite time
        # Note we start at ADDRESS | 1 to indicate THUMB mode.
        mu.emu_start(ADDRESS | 1, ADDRESS + len(THUMB_CODE))

        # now print out some registers
        print(">>> Emulation done. Below is the CPU context")

        sp = mu.reg_read(UC_ARM_REG_SP)
        print(">>> SP = 0x%x" %sp)

    except UcError as e:
        print("ERROR: %s" % e)


if __name__ == '__main__':
    test_arm()
    print("=" * 26)
    test_thumb()

简单介绍下每段代码的作用

这里以test_arm函数作为例子

常用函数

模拟器初始化
unicorn.Uc(arch, mode)

内存映射
mem_map(address, size, perms=uc.UC_PROT_ALL)

向内存中写入数据 data为byte类型
mem_write(address, data)

向内存中读出数据
mem_read(address, size)

向寄存器中写入值
reg_write(reg_id, value)

向寄存器中读出值
reg_read(reg_id)

添加hook
hook_add(htype, callback, user_data=None, begin=1, end=0, arg1=0)

模拟器的初始化操作

ARM_CODE   = b"\x37\x00\xa0\xe3\x03\x10\x42\xe0" # mov r0, #0x37; sub r1, r2, r3
ADDRESS    = 0x10000

# 在ARM模式下初始化模拟器
mu = Uc(UC_ARCH_ARM, UC_MODE_ARM)

# 为模拟器映射2MB内存
mu.mem_map(ADDRESS, 2 * 1024 * 1024)

# 将代码写入到内存中
mu.mem_write(ADDRESS, ARM_CODE)

寄存器操作

分别给寄存器 R0,R2,R3,APSR 赋值
顺便解释下，传参时
在ARM下，如果参数少于等于4个，使用寄存器R0~R3进行传递，超过4个参数前4个参数依然使用寄存器传递，第5个及之后的使用堆栈进行传递（SP寄存器）
在ARM64下，如果参数少于等于8个时，使用寄存器X0~X7进行传递，超过也需要使用SP寄存器

# initialize machine registers
mu.reg_write(UC_ARM_REG_R0, 0x1234)
mu.reg_write(UC_ARM_REG_R2, 0x6789)
mu.reg_write(UC_ARM_REG_R3, 0x3333)
mu.reg_write(UC_ARM_REG_APSR, 0xFFFFFFFF) #All application flags turned on```

hook

# callback for tracing basic blocks
def hook_block(uc, address, size, user_data):
    print(">>> Tracing basic block at 0x%x, block size = 0x%x" %(address, size))

# callback for tracing instructions
def hook_code(uc, address, size, user_data):
    print(">>> Tracing instruction at 0x%x, instruction size = 0x%x" %(address, size))

# 当指令首次进入代码块的时候会调用回调函数
mu.hook_add(UC_HOOK_BLOCK, hook_block)

# 执行到指定地址的指令时会调用回调函数，begin，end 不填写为每条指令都hook
mu.hook_add(UC_HOOK_CODE, hook_code, begin=ADDRESS, end=ADDRESS)

开始执行指令

# 参数1为指令开始地址，参数2位指令结束地址
mu.emu_start(ADDRESS, ADDRESS + len(ARM_CODE))

读取寄存器值

r0 = mu.reg_read(UC_ARM_REG_R0)
r1 = mu.reg_read(UC_ARM_REG_R1)