最近在为distri.lua实现一个lua调试系统,有一个简单的需求,lua导入一个文件的时候,将这个文件的文件名记录下来,
以方便调试器在设置断点的时候判断是否一个合法的文件.
lua导入文件是通过luaL_loadfilex实现的,一个简单的思路就是修改luaL_loadfilex,在luaL_loadfilex中调用一个外部定义的函数将导入的文件名传给那个外部函数，由它记录下来.
但这种侵入式的方案，除非在逼不得已的情况下不应该使用.
另一个思路是hook luaL_loadfilex,在运行时用另外一个函数替换luaL_loadfilex,由这个替换函数去记录下需要的信息
然后在跳转回原luaL_loadfilex的执行流程上.
与是我从decode中提取除了Hook.h,Hook.c稍加调整以适应Linux系统.
hook的原理很简单:
* 首先,使用mprotect将luaL_loadfilex所在代码段设置为可读/可写/可执行,以避免在修改代码时出现段访问异常
* 之后需要把luaL_loadfilex最前面的一段指令替换成一个跳转指令,跳转到替换函数中去执行.为了在替换函数执行
完之后可以正确的回到luaL_loadfilex的正常执行路径上,需要把luaL_loadfilex中被替换部分的指令保存下来,然后
在后面再添加一条跳转指令,调到luaL_loadfilex后面的执行路径去.
被替换掉的指令布局和执行流程如下图:
luaL_loadfilex:
jmp hook
-------------
其余指令 <-------------------------------------------------|
|
hook: |
执行必要的记录 |
--保存的代码---- |
luaL_loadfilex中被替换的指令 |
jmp其余指令--------------------------------------------------|
HookFunction实现如下:
void* HookFunction(void* function, void* hook)
{
// Don't allow rehooking of the same function since that screws things up.
assert(!GetIsHooked(function, hook));
if (GetIsHooked(function, hook))
{
return NULL;
}
// Missing from windows.h
//#define HEAP_CREATE_ENABLE_EXECUTE 0x00040000
// Jump instruction is 5 bytes.
const int jumpSize = 5;
// Compute the instruction boundary so we don't override half an instruction.
int boundary = GetInstructionBoundary(function, jumpSize);
size_t pagesize = sysconf(_SC_PAGE_SIZE);
unsigned char* trampoline = NULL;
trampoline = (unsigned char*)/*aligned_alloc*/memalign(pagesize,pagesize);
if(mprotect(trampoline, pagesize, PROT_WRITE|PROT_READ|PROT_EXEC)){
free(trampoline);
return NULL;
}
// Copy the original bytes to the trampoline area and append a jump back
// to the original function (after our jump).
memcpy(trampoline, function, boundary);
AdjustRelativeJumps(trampoline, boundary, ((unsigned char*)function) - trampoline);
WriteJump(trampoline + boundary, ((unsigned char*)function) + boundary);
void *ptr = (void*)(((size_t)function/pagesize)*pagesize);
// Give ourself write access to the region.
if(!mprotect(ptr, pagesize, PROT_WRITE|PROT_READ|PROT_EXEC))
{
// Fill the area with nops and write the jump instruction to our
// hook function.
memset(function, 0x90, boundary);
WriteJump(function, hook);
// Restore the original protections.
//VirtualProtect(function, boundary, protection, &protection);
mprotect(ptr, pagesize, PROT_READ|PROT_EXEC);
// Flush the cache so we know that our new code gets executed.
//FlushInstructionCache(GetCurrentProcess(), NULL, NULL);
return trampoline;
//return 0;
}
free(trampoline);
return NULL;
//return -1;
}
本以为一切就这样结束了,运行程序的时候,正确的进入了替换函数,但在执行完记录操作要回到luaL_loadfilex后续执行流程的时候程序
挂了,报段访问异常.
为啥呢,我们看下WriteJump的实现:
/**
* Writes a relative jmp instruction.
*/
void WriteJump(void* dst, void* address)
{
unsigned char* jump = (unsigned char*)(dst);
// Setup a jump instruction.
jump[0] = 0xE9;
*((unsigned long*)(&jump[1])) = (unsigned long)(address) - (unsigned long)(dst) - 5;
}
使用的是E9跳转指令+4字节的立即数做相对rip计数器的跳转.这在32位程序下这是没问题的,因为trampoline和luaL_loadfilex的位移差必定
在4字节的范围内.但我程序的运行环境是64位的,这个时候程序就出问题了, trampoline和luaL_loadfilex的位移差已经超过4个字节.这就导致
[jmp其余指令]跳转到到错误的地址上了.
如何解决这个问题:
* 用FF指令做跳转,但这个方案要修改的地方就多了,除了` WriteJump`,还有`AdjustRelativeJumps`并且还会导致指令长度变长.
* 用static数据区保存luaL_loadfilex中被替换的指令,使得位移差被控制在4字节以内.
针对我的需求，我选择了方案2,下面是修改过的HookFunction和WriteJump以及使用示例:
/**
* Writes a relative jmp instruction.
*/
void WriteJump(void* dst, void* address)
{
unsigned char* jump = (unsigned char*)(dst);
// Setup a jump instruction.
jump[0] = 0xE9;
*((unsigned int*)(&jump[1])) = (unsigned int)((unsigned long)(address) - (unsigned long)(dst) - 5);
}
void* HookFunction(void* function, void* hook,void *saveaddr,size_t saveaddr_size)
{
// Don't allow rehooking of the same function since that screws things up.
assert(!GetIsHooked(function, hook));
if (GetIsHooked(function, hook))
{
return NULL;
}
// Missing from windows.h
//#define HEAP_CREATE_ENABLE_EXECUTE 0x00040000
// Jump instruction is 5 bytes.
const int jumpSize = 5;
// Compute the instruction boundary so we don't override half an instruction.
int boundary = GetInstructionBoundary(function, jumpSize);
if(saveaddr_size < (size_t)boundary) return NULL;
size_t pagesize = sysconf(_SC_PAGE_SIZE);
if(mprotect(saveaddr, boundary, PROT_WRITE|PROT_READ|PROT_EXEC)){
//free(trampoline);
return NULL;
}
// Copy the original bytes to the trampoline area and append a jump back
// to the original function (after our jump).
memcpy(saveaddr, function, boundary);
AdjustRelativeJumps(saveaddr, boundary, ((unsigned char*)function) - (unsigned char*)saveaddr);
WriteJump(saveaddr + boundary, ((unsigned char*)function) + boundary);
void *ptr = (void*)(((size_t)function/pagesize)*pagesize);
// Give ourself write access to the region.
if(!mprotect(ptr, pagesize, PROT_WRITE|PROT_READ|PROT_EXEC))
{
// Fill the area with nops and write the jump instruction to our
// hook function.
memset(function, 0x90, boundary);
WriteJump(function, hook);
// Restore the original protections.
//VirtualProtect(function, boundary, protection, &protection);
mprotect(ptr, pagesize, PROT_READ|PROT_EXEC);
// Flush the cache so we know that our new code gets executed.
//FlushInstructionCache(GetCurrentProcess(), NULL, NULL);
return saveaddr;
//return 0;
}
return NULL;
//return -1;
}
////使用示例
int (*ori_luaL_loadfilex)(lua_State *L, const char *filename,const char *mode) = NULL;
int my_luaL_loadfilex(lua_State *L, const char *filename,const char *mode){
printf("%s\n",filename);//记录导入的lua文件，供调试器使用
return ori_luaL_loadfilex(L,filename,mode);
}
static char luaL_loadfilex_buf[4096] __attribute__((aligned(4096)));
int debug_init(){
ori_luaL_loadfilex = HookFunction(luaL_loadfilex,my_luaL_loadfilex,luaL_loadfilex_buf,4096);
if(!ori_luaL_loadfilex){
return -1;
}
return 0;
}