环境
- Time 2022-11-08
- WSL-Ubuntu 22.04
- QEMU 6.2.0
- NASM 2.15.05
前言
说明
参考:《x86汇编语言:从实模式到保护模式》李忠
参考:https://astralvx.com/debugging-16-bit-in-qemu-with-gdb-on-windows/
目标
使用 GDB 调试十六位的汇编代码。
实模式
在 8086 CPU 加电执行完 ROM 之后,进入的是实模式。访问的内存地址对应真实的物理地址。
访问方式是通过段地址 * 16 + 偏移地址的方式来访问。不过 GDB 不支持段地址访问,所以需要特别适配。
下载需要的文件
一共需要下载三个文件,如果不能访问,附录中有原文:
- https://astralvx.com/storage/2021/05/gdb_init_real_mode.txt
- https://astralvx.com/storage/2021/05/target.xml
- https://astralvx.com/storage/2021/05/i386-32bit.xml
启动脚本
#! /usr/bin/bash
gdb -ix "gdb_init_real_mode.txt" \
-ex "set tdesc filename target.xml" \
-ex "target remote localhost:1234" \
-ex "br *0x7c00" -ex "c"
这个脚本启动后,会自动切换到 16 位模式,并且打印各种寄存器的信息。
会自动跳转到 0x7c00 断点处。
调试实模式
mov al,4
mov ax,0x4444
times 510 - $ + $$ db 0
db 0x55
db 0xaa
总结
使用 GDB 来调试实模式,通过下载三个文件来完成配置,并显示出来各种寄存器的信息。
附录
target.xml
<?xml version="1.0"?><!DOCTYPE target SYSTEM "gdb-target.dtd">
<target>
<architecture>i8086</architecture>
<xi:include href="i386-32bit.xml"/>
i386-32bit.xml
<?xml version="1.0"?>
<!-- Copyright (C) 2010-2017 Free Software Foundation, Inc.
Copying and distribution of this file, with or without modification,
are permitted in any medium without royalty provided the copyright
notice and this notice are preserved. -->
<!-- I386 with SSE -->
<!DOCTYPE target SYSTEM "gdb-target.dtd">
<feature name="org.gnu.gdb.i386.core">
<flags id="i386_eflags" size="4">
<field name="" start="22" end="31"/>
<field name="ID" start="21" end="21"/>
<field name="VIP" start="20" end="20"/>
<field name="VIF" start="19" end="19"/>
<field name="AC" start="18" end="18"/>
<field name="VM" start="17" end="17"/>
<field name="RF" start="16" end="16"/>
<field name="" start="15" end="15"/>
<field name="NT" start="14" end="14"/>
<field name="IOPL" start="12" end="13"/>
<field name="OF" start="11" end="11"/>
<field name="DF" start="10" end="10"/>
<field name="IF" start="9" end="9"/>
<field name="TF" start="8" end="8"/>
<field name="SF" start="7" end="7"/>
<field name="ZF" start="6" end="6"/>
<field name="" start="5" end="5"/>
<field name="AF" start="4" end="4"/>
<field name="" start="3" end="3"/>
<field name="PF" start="2" end="2"/>
<field name="" start="1" end="1"/>
<field name="CF" start="0" end="0"/>
</flags>
<reg name="eax" bitsize="32" type="int32" regnum="0"/>
<reg name="ecx" bitsize="32" type="int32"/>
<reg name="edx" bitsize="32" type="int32"/>
<reg name="ebx" bitsize="32" type="int32"/>
<reg name="esp" bitsize="32" type="data_ptr"/>
<reg name="ebp" bitsize="32" type="data_ptr"/>
<reg name="esi" bitsize="32" type="int32"/>
<reg name="edi" bitsize="32" type="int32"/>
<reg name="eip" bitsize="32" type="code_ptr"/>
<reg name="eflags" bitsize="32" type="i386_eflags"/>
<reg name="cs" bitsize="32" type="int32"/>
<reg name="ss" bitsize="32" type="int32"/>
<reg name="ds" bitsize="32" type="int32"/>
<reg name="es" bitsize="32" type="int32"/>
<reg name="fs" bitsize="32" type="int32"/>
<reg name="gs" bitsize="32" type="int32"/>
<!-- Segment descriptor caches and TLS base MSRs -->
<!--reg name="cs_base" bitsize="32" type="int32"/>
<reg name="ss_base" bitsize="32" type="int32"/>
<reg name="ds_base" bitsize="32" type="int32"/>
<reg name="es_base" bitsize="32" type="int32"/-->
<reg name="fs_base" bitsize="32" type="int32"/>
<reg name="gs_base" bitsize="32" type="int32"/>
<reg name="k_gs_base" bitsize="32" type="int32"/>
<flags id="i386_cr0" size="4">
<field name="PG" start="31" end="31"/>
<field name="CD" start="30" end="30"/>
<field name="NW" start="29" end="29"/>
<field name="AM" start="18" end="18"/>
<field name="WP" start="16" end="16"/>
<field name="NE" start="5" end="5"/>
<field name="ET" start="4" end="4"/>
<field name="TS" start="3" end="3"/>
<field name="EM" start="2" end="2"/>
<field name="MP" start="1" end="1"/>
<field name="PE" start="0" end="0"/>
</flags>
<flags id="i386_cr3" size="4">
<field name="PDBR" start="12" end="31"/>
<!--field name="" start="3" end="11"/>
<field name="WT" start="2" end="2"/>
<field name="CD" start="1" end="1"/>
<field name="" start="0" end="0"/-->
<field name="PCID" start="0" end="11"/>
</flags>
<flags id="i386_cr4" size="4">
<field name="VME" start="0" end="0"/>
<field name="PVI" start="1" end="1"/>
<field name="TSD" start="2" end="2"/>
<field name="DE" start="3" end="3"/>
<field name="PSE" start="4" end="4"/>
<field name="PAE" start="5" end="5"/>
<field name="MCE" start="6" end="6"/>
<field name="PGE" start="7" end="7"/>
<field name="PCE" start="8" end="8"/>
<field name="OSFXSR" start="9" end="9"/>
<field name="OSXMMEXCPT" start="10" end="10"/>
<field name="UMIP" start="11" end="11"/>
<field name="LA57" start="12" end="12"/>
<field name="VMXE" start="13" end="13"/>
<field name="SMXE" start="14" end="14"/>
<field name="FSGSBASE" start="16" end="16"/>
<field name="PCIDE" start="17" end="17"/>
<field name="OSXSAVE" start="18" end="18"/>
<field name="SMEP" start="20" end="20"/>
<field name="SMAP" start="21" end="21"/>
<field name="PKE" start="22" end="22"/>
</flags>
<flags id="i386_efer" size="8">
<field name="TCE" start="15" end="15"/>
<field name="FFXSR" start="14" end="14"/>
<field name="LMSLE" start="13" end="13"/>
<field name="SVME" start="12" end="12"/>
<field name="NXE" start="11" end="11"/>
<field name="LMA" start="10" end="10"/>
<field name="LME" start="8" end="8"/>
<field name="SCE" start="0" end="0"/>
</flags>
<reg name="cr0" bitsize="32" type="i386_cr0"/>
<reg name="cr2" bitsize="32" type="int32"/>
<reg name="cr3" bitsize="32" type="i386_cr3"/>
<reg name="cr4" bitsize="32" type="i386_cr4"/>
<reg name="cr8" bitsize="32" type="int32"/>
<reg name="efer" bitsize="32" type="i386_efer"/>
<reg name="st0" bitsize="80" type="i387_ext"/>
<reg name="st1" bitsize="80" type="i387_ext"/>
<reg name="st2" bitsize="80" type="i387_ext"/>
<reg name="st3" bitsize="80" type="i387_ext"/>
<reg name="st4" bitsize="80" type="i387_ext"/>
<reg name="st5" bitsize="80" type="i387_ext"/>
<reg name="st6" bitsize="80" type="i387_ext"/>
<reg name="st7" bitsize="80" type="i387_ext"/>
<reg name="fctrl" bitsize="32" type="int" group="float"/>
<reg name="fstat" bitsize="32" type="int" group="float"/>
<reg name="ftag" bitsize="32" type="int" group="float"/>
<reg name="fiseg" bitsize="32" type="int" group="float"/>
<reg name="fioff" bitsize="32" type="int" group="float"/>
<reg name="foseg" bitsize="32" type="int" group="float"/>
<reg name="fooff" bitsize="32" type="int" group="float"/>
<reg name="fop" bitsize="32" type="int" group="float"/>
<!--/feature>
<feature name="org.gnu.gdb.i386.32bit.sse"-->
<vector id="v4f" type="ieee_single" count="4"/>
<vector id="v2d" type="ieee_double" count="2"/>
<vector id="v16i8" type="int8" count="16"/>
<vector id="v8i16" type="int16" count="8"/>
<vector id="v4i32" type="int32" count="4"/>
<vector id="v2i64" type="int64" count="2"/>
<union id="vec128">
<field name="v4_float" type="v4f"/>
<field name="v2_double" type="v2d"/>
<field name="v16_int8" type="v16i8"/>
<field name="v8_int16" type="v8i16"/>
<field name="v4_int32" type="v4i32"/>
<field name="v2_int64" type="v2i64"/>
<field name="uint128" type="uint128"/>
</union>
<flags id="i386_mxcsr" size="4">
<field name="IE" start="0" end="0"/>
<field name="DE" start="1" end="1"/>
<field name="ZE" start="2" end="2"/>
<field name="OE" start="3" end="3"/>
<field name="UE" start="4" end="4"/>
<field name="PE" start="5" end="5"/>
<field name="DAZ" start="6" end="6"/>
<field name="IM" start="7" end="7"/>
<field name="DM" start="8" end="8"/>
<field name="ZM" start="9" end="9"/>
<field name="OM" start="10" end="10"/>
<field name="UM" start="11" end="11"/>
<field name="PM" start="12" end="12"/>
<field name="FZ" start="15" end="15"/>
</flags>
<reg name="xmm0" bitsize="128" type="vec128"/>
<reg name="xmm1" bitsize="128" type="vec128"/>
<reg name="xmm2" bitsize="128" type="vec128"/>
<reg name="xmm3" bitsize="128" type="vec128"/>
<reg name="xmm4" bitsize="128" type="vec128"/>
<reg name="xmm5" bitsize="128" type="vec128"/>
<reg name="xmm6" bitsize="128" type="vec128"/>
<reg name="xmm7" bitsize="128" type="vec128"/>
<reg name="mxcsr" bitsize="32" type="i386_mxcsr" group="vector"/>
gdb_init_real_mode.txt
# Special mode for GDB that allows to debug/disassemble REAL MODE x86 code
#
# It has been designed to be used with QEMU or BOCHS gdb-stub
#
# 08/2011 Hugo Mercier - GPL v3 license
#
# Freely inspired from "A user-friendly gdb configuration file" widely available
# on the Internet
set confirm off
set verbose off
set prompt \033[31mreal-mode-gdb$ \033[0m
set output-radix 0d10
set input-radix 0d10
# These make gdb never pause in its output
set height 0
set width 0
# Intel syntax
set disassembly-flavor intel
# Real mode
#set architecture i8086
set $SHOW_CONTEXT = 1
set $REAL_MODE = 1
# By default A20 is present
set $ADDRESS_MASK = 0x1FFFFF
# nb of instructions to display
set $CODE_SIZE = 10
define enable-a20
set $ADDRESS_MASK = 0x1FFFFF
end
define disable-a20
set $ADDRESS_MASK = 0x0FFFFF
end
# convert segment:offset address to physical address
define r2p
if $argc < 2
printf "Arguments: segment offset\n"
else
set $ADDR = (((unsigned long)$arg0 & 0xFFFF) << 4) + (((unsigned long)$arg1 & 0xFFFF) & $ADDRESS_MASK)
printf "0x%05X\n", $ADDR
end
end
document r2p
Convert segment:offset address to physical address
Set the global variable $ADDR to the computed one
end
# get address of Interruption
define int_addr
if $argc < 1
printf "Argument: interruption_number\n"
else
set $offset = (unsigned short)*($arg0 * 4)
set $segment = (unsigned short)*($arg0 * 4 + 2)
r2p $segment $offset
printf "%04X:%04X\n", $segment, $offset
end
end
document int_addr
Get address of interruption
end
define compute_regs
set $rax = ((unsigned long)$eax & 0xFFFF)
set $rbx = ((unsigned long)$ebx & 0xFFFF)
set $rcx = ((unsigned long)$ecx & 0xFFFF)
set $rdx = ((unsigned long)$edx & 0xFFFF)
set $rsi = ((unsigned long)$esi & 0xFFFF)
set $rdi = ((unsigned long)$edi & 0xFFFF)
set $rbp = ((unsigned long)$ebp & 0xFFFF)
set $rsp = ((unsigned long)$esp & 0xFFFF)
set $rcs = ((unsigned long)$cs & 0xFFFF)
set $rds = ((unsigned long)$ds & 0xFFFF)
set $res = ((unsigned long)$es & 0xFFFF)
set $rss = ((unsigned long)$ss & 0xFFFF)
set $rip = ((((unsigned long)$cs & 0xFFFF) << 4) + ((unsigned long)$eip & 0xFFFF)) & $ADDRESS_MASK
set $r_ss_sp = ((((unsigned long)$ss & 0xFFFF) << 4) + ((unsigned long)$esp & 0xFFFF)) & $ADDRESS_MASK
set $r_ss_bp = ((((unsigned long)$ss & 0xFFFF) << 4) + ((unsigned long)$ebp & 0xFFFF)) & $ADDRESS_MASK
end
define print_regs
printf "AX: %04X BX: %04X ", $rax, $rbx
printf "CX: %04X DX: %04X\n", $rcx, $rdx
printf "SI: %04X DI: %04X ", $rsi, $rdi
printf "SP: %04X BP: %04X\n", $rsp, $rbp
printf "CS: %04X DS: %04X ", $rcs, $rds
printf "ES: %04X SS: %04X\n", $res, $rss
printf "\n"
printf "IP: %04X EIP:%08X\n", ((unsigned short)$eip & 0xFFFF), $eip
printf "CS:IP: %04X:%04X (0x%05X)\n", $rcs, ((unsigned short)$eip & 0xFFFF), $rip
printf "SS:SP: %04X:%04X (0x%05X)\n", $rss, $rsp, $r_ss_sp
printf "SS:BP: %04X:%04X (0x%05X)\n", $rss, $rbp, $r_ss_bp
end
document print_regs
Print CPU registers
end
define print_eflags
printf "OF <%d> DF <%d> IF <%d> TF <%d>",\
(($eflags >> 0xB) & 1), (($eflags >> 0xA) & 1), \
(($eflags >> 9) & 1), (($eflags >> 8) & 1)
printf " SF <%d> ZF <%d> AF <%d> PF <%d> CF <%d>\n",\
(($eflags >> 7) & 1), (($eflags >> 6) & 1),\
(($eflags >> 4) & 1), (($eflags >> 2) & 1), ($eflags & 1)
printf "ID <%d> VIP <%d> VIF <%d> AC <%d>",\
(($eflags >> 0x15) & 1), (($eflags >> 0x14) & 1), \
(($eflags >> 0x13) & 1), (($eflags >> 0x12) & 1)
printf " VM <%d> RF <%d> NT <%d> IOPL <%d>\n",\
(($eflags >> 0x11) & 1), (($eflags >> 0x10) & 1),\
(($eflags >> 0xE) & 1), (($eflags >> 0xC) & 3)
end
document print_eflags
Print eflags register.
end
# dump content of bytes in memory
# arg0 : addr
# arg1 : nb of bytes
define _dump_memb
if $argc < 2
printf "Arguments: address number_of_bytes\n"
else
set $_nb = $arg1
set $_i = 0
set $_addr = $arg0
while ($_i < $_nb)
printf "%02X ", *((unsigned char*)$_addr + $_i)
set $_i++
end
end
end
# dump content of memory in words
# arg0 : addr
# arg1 : nb of words
define _dump_memw
if $argc < 2
printf "Arguments: address number_of_words\n"
else
set $_nb = $arg1
set $_i = 0
set $_addr = $arg0
while ($_i < $_nb)
printf "%04X ", *((unsigned short*)$_addr + $_i)
set $_i++
end
end
end
# display data at given address
define print_data
if ($argc > 0)
set $seg = $arg0
set $off = $arg1
set $raddr = ($arg0 << 16) + $arg1
set $maddr = ($arg0 << 4) + $arg1
set $w = 16
set $i = (int)0
while ($i < 4)
printf "%08X: ", ($raddr + $i * $w)
set $j = (int)0
while ($j < $w)
printf "%02X ", *(unsigned char*)($maddr + $i * $w + $j)
set $j++
end
printf " "
set $j = (int)0
while ($j < $w)
set $c = *(unsigned char*)($maddr + $i * $w + $j)
if ($c > 32) && ($c < 128)
printf "%c", $c
else
printf "."
end
set $j++
end
printf "\n"
set $i++
end
end
end
define context
printf "---------------------------[ STACK ]---\n"
_dump_memw $r_ss_sp 8
printf "\n"
set $_a = $r_ss_sp + 16
_dump_memw $_a 8
printf "\n"
printf "---------------------------[ DS:SI ]---\n"
print_data $ds $rsi
printf "---------------------------[ ES:DI ]---\n"
print_data $es $rdi
printf "----------------------------[ CPU ]----\n"
print_regs
print_eflags
printf "---------------------------[ CODE ]----\n"
set $_code_size = $CODE_SIZE
# disassemble
# first call x/i with an address
# subsequent calls to x/i will increment address
if ($_code_size > 0)
x /i $rip
set $_code_size--
end
while ($_code_size > 0)
x /i
set $_code_size--
end
end
document context
Print context window, i.e. regs, stack, ds:esi and disassemble cs:eip.
end
define hook-stop
compute_regs
if ($SHOW_CONTEXT > 0)
context
end
end
document hook-stop
!!! FOR INTERNAL USE ONLY - DO NOT CALL !!!
end
# add a breakpoint on an interrupt
define break_int
set $offset = (unsigned short)*($arg0 * 4)
set $segment = (unsigned short)*($arg0 * 4 + 2)
break *$offset
end
define break_int_if_ah
if ($argc < 2)
printf "Arguments: INT_N AH\n"
else
set $addr = (unsigned short)*($arg0 * 4)
set $segment = (unsigned short)*($arg0 * 4 + 2)
break *$addr if ((unsigned long)$eax & 0xFF00) == ($arg1 << 8)
end
end
document break_int_if_ah
Install a breakpoint on INT N only if AH is equal to the expected value
end
define break_int_if_ax
if ($argc < 2)
printf "Arguments: INT_N AX\n"
else
set $addr = (unsigned short)*($arg0 * 4)
set $segment = (unsigned short)*($arg0 * 4 + 2)
break *$addr if ((unsigned long)$eax & 0xFFFF) == $arg1
end
end
document break_int_if_ax
Install a breakpoint on INT N only if AX is equal to the expected value
end
define stepo
## we know that an opcode starting by 0xE8 has a fixed length
## for the 0xFF opcodes, we can enumerate what is possible to have
set $lip = $rip
set $offset = 0
# first, get rid of segment prefixes, if any
set $_byte1 = *(unsigned char *)$rip
# CALL DS:xx CS:xx, etc.
if ($_byte1 == 0x3E || $_byte1 == 0x26 || $_byte1 == 0x2E || $_byte1 == 0x36 || $_byte1 == 0x3E || $_byte1 == 0x64 || $_byte1 == 0x65)
set $lip = $rip + 1
set $_byte1 = *(unsigned char*)$lip
set $offset = 1
end
set $_byte2 = *(unsigned char *)($lip+1)
set $_byte3 = *(unsigned char *)($lip+2)
set $noffset = 0
if ($_byte1 == 0xE8)
# call near
set $noffset = 3
else
if ($_byte1 == 0xFF)
# A "ModR/M" byte follows
set $_mod = ($_byte2 & 0xC0) >> 6
set $_reg = ($_byte2 & 0x38) >> 3
set $_rm = ($_byte2 & 7)
#printf "mod: %d reg: %d rm: %d\n", $_mod, $_reg, $_rm
# only for CALL instructions
if ($_reg == 2 || $_reg == 3)
# default offset
set $noffset = 2
if ($_mod == 0)
if ($_rm == 6)
# a 16bit address follows
set $noffset = 4
end
else
if ($_mod == 1)
# a 8bit displacement follows
set $noffset = 3
else
if ($_mod == 2)
# 16bit displacement
set $noffset = 4
end
end
end
end
# end of _reg == 2 or _reg == 3
else
# else byte1 != 0xff
if ($_byte1 == 0x9A)
# call far
set $noffset = 5
else
if ($_byte1 == 0xCD)
# INTERRUPT CASE
set $noffset = 2
end
end
end
# end of byte1 == 0xff
end
# else byte1 != 0xe8
# if we have found a call to bypass we set a temporary breakpoint on next instruction and continue
if ($noffset != 0)
set $_nextaddress = $eip + $offset + $noffset
printf "Setting BP to %04X\n", $_nextaddress
tbreak *$_nextaddress
continue
# else we just single step
else
nexti
end
end
document stepo
Step over calls
This function will set a temporary breakpoint on next instruction after the call so the call will be bypassed
You can safely use it instead nexti since it will single step code if it's not a call instruction (unless you want to go into the call function)
end
define step_until_iret
set $SHOW_CONTEXT=0
set $_found = 0
while (!$_found)
if (*(unsigned char*)$rip == 0xCF)
set $_found = 1
else
stepo
end
end
set $SHOW_CONTEXT=1
context
end
define step_until_ret
set $SHOW_CONTEXT=0
set $_found = 0
while (!$_found)
set $_p = *(unsigned char*)$rip
if ($_p == 0xC3 || $_p == 0xCB || $_p == 0xC2 || $_p == 0xCA)
set $_found = 1
else
stepo
end
end
set $SHOW_CONTEXT=1
context
end
define step_until_int
set $SHOW_CONTEXT = 0
while (*(unsigned char*)$rip != 0xCD)
stepo
end
set $SHOW_CONTEXT = 1
context
end
# Find a pattern in memory
# The pattern is given by a string as arg0
# If another argument is present it gives the starting address (0 otherwise)
define find_in_mem
if ($argc >= 2)
set $_addr = $arg1
else
set $_addr = 0
end
set $_found = 0
set $_tofind = $arg0
while ($_addr < $ADDRESS_MASK) && (!$_found)
if ($_addr % 0x100 == 0)
printf "%08X\n", $_addr
end
set $_i = 0
set $_found = 1
while ($_tofind[$_i] != 0 && $_found == 1)
set $_b = *((char*)$_addr + $_i)
set $_t = (char)$_tofind[$_i]
if ($_t != $_b)
set $_found = 0
end
set $_i++
end
if ($_found == 1)
printf "Code found at 0x%05X\n", $_addr
end
set $_addr++
end
end
document find_in_mem
Find a pattern in memory
The pattern is given by a string as arg0
If another argument is present it gives the starting address (0 otherwise)
end
define step_until_code
set $_tofind = $arg0
set $SHOW_CONTEXT = 0
set $_found = 0
while (!$_found)
set $_i = 0
set $_found = 1
while ($_tofind[$_i] != 0 && $_found == 1)
set $_b = *((char*)$rip + $_i)
set $_t = (char)$_tofind[$_i]
if ($_t != $_b)
set $_found = 0
end
set $_i++
end
if ($_found == 0)
stepo
end
end
set $SHOW_CONTEXT = 1
context
标签:set,end,addr,0161,GDB,eflags,printf,found,调试
From: https://www.cnblogs.com/jiangbo4444/p/17079748.html