Skip to content

Commit 067e76d

Browse files
committed
add assembly code tutorial
1 parent 487b308 commit 067e76d

File tree

5 files changed

+102
-0
lines changed

5 files changed

+102
-0
lines changed

README.md

+1
Original file line numberDiff line numberDiff line change
@@ -81,6 +81,7 @@ This is a repository of all the tutorials of [The Python Code](https://www.thepy
8181
- [How to Get the Size of Directories in Python](https://www.thepythoncode.com/article/get-directory-size-in-bytes-using-python). ([code](general/calculate-directory-size))
8282
- [How to Play and Record Audio in Python](https://www.thepythoncode.com/article/play-and-record-audio-sound-in-python). ([code](general/recording-and-playing-audio))
8383
- [How to Get Geographic Locations in Python](https://www.thepythoncode.com/article/get-geolocation-in-python). ([code](general/geolocation))
84+
- [How to Assembly, Disassembly and Emulate Machine Code using Python](https://www.thepythoncode.com/article/arm-x86-64-assembly-disassembly-and-emulation-in-python). ([code](general/assembly-code))
8485

8586

8687
- ### [Web Scraping](https://www.thepythoncode.com/topic/web-scraping)

general/assembly-code/README.md

+3
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
# [How to Assembly, Disassembly and Emulate Machine Code using Python](https://www.thepythoncode.com/article/arm-x86-64-assembly-disassembly-and-emulation-in-python)
2+
To run this:
3+
- `pip3 install -r requirements.txt`

general/assembly-code/arm_assembly.py

+56
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,56 @@
1+
# We need to emulate ARM
2+
from unicorn import Uc, UC_ARCH_ARM, UC_MODE_ARM, UcError
3+
# for accessing the R0 and R1 registers
4+
from unicorn.arm_const import UC_ARM_REG_R0, UC_ARM_REG_R1
5+
# We need to assemble ARM code
6+
from keystone import Ks, KS_ARCH_ARM, KS_MODE_ARM, KsError
7+
8+
9+
ARM_CODE = """
10+
// n is r0, we will pass it from python, ans is r1
11+
mov r1, 1 // ans = 1
12+
loop:
13+
cmp r0, 0 // while n >= 0:
14+
mulgt r1, r1, r0 // ans *= n
15+
subgt r0, r0, 1 // n = n - 1
16+
bgt loop //
17+
// answer is in r1
18+
"""
19+
20+
print("Assembling the ARM code")
21+
try:
22+
# initialize the keystone object with the ARM architecture
23+
ks = Ks(KS_ARCH_ARM, KS_MODE_ARM)
24+
# Assemble the ARM code
25+
ARM_BYTECODE, _ = ks.asm(ARM_CODE)
26+
# convert the array of integers into bytes
27+
ARM_BYTECODE = bytes(ARM_BYTECODE)
28+
print(f"Code successfully assembled (length = {len(ARM_BYTECODE)})")
29+
print("ARM bytecode:", ARM_BYTECODE)
30+
except KsError as e:
31+
print("Keystone Error: %s" % e)
32+
exit(1)
33+
34+
35+
# memory address where emulation starts
36+
ADDRESS = 0x1000000
37+
38+
print("Emulating the ARM code")
39+
try:
40+
# Initialize emulator in ARM mode
41+
mu = Uc(UC_ARCH_ARM, UC_MODE_ARM)
42+
# map 2MB memory for this emulation
43+
mu.mem_map(ADDRESS, 2 * 1024 * 1024)
44+
# write machine code to be emulated to memory
45+
mu.mem_write(ADDRESS, ARM_BYTECODE)
46+
# Set the r0 register in the code, let's calculate factorial(5)
47+
mu.reg_write(UC_ARM_REG_R0, 5)
48+
# emulate code in infinite time and unlimited instructions
49+
mu.emu_start(ADDRESS, ADDRESS + len(ARM_BYTECODE))
50+
# now print out the R0 register
51+
print("Emulation done. Below is the result")
52+
# retrieve the result from the R1 register
53+
r1 = mu.reg_read(UC_ARM_REG_R1)
54+
print(">> R1 = %u" % r1)
55+
except UcError as e:
56+
print("Unicorn Error: %s" % e)
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,39 @@
1+
# We need to emulate ARM and x86 code
2+
from unicorn import Uc, UC_ARCH_X86, UC_MODE_64, UcError
3+
# for accessing the RAX and RDI registers
4+
from unicorn.x86_const import UC_X86_REG_RDI, UC_X86_REG_RAX
5+
# We need to disassemble x86_64 code
6+
from capstone import Cs, CS_ARCH_X86, CS_MODE_64, CsError
7+
8+
9+
X86_MACHINE_CODE = b"\x48\x31\xc0\x48\xff\xc0\x48\x85\xff\x0f\x84\x0d\x00\x00\x00\x48\x99\x48\xf7\xe7\x48\xff\xcf\xe9\xea\xff\xff\xff"
10+
11+
# memory address where emulation starts
12+
ADDRESS = 0x1000000
13+
14+
try:
15+
# Initialize the disassembler in x86 mode
16+
md = Cs(CS_ARCH_X86, CS_MODE_64)
17+
# iterate over each instruction and print it
18+
for instruction in md.disasm(X86_MACHINE_CODE, 0x1000):
19+
print("0x%x:\t%s\t%s" % (instruction.address, instruction.mnemonic, instruction.op_str))
20+
except CsError as e:
21+
print("Capstone Error: %s" % e)
22+
23+
try:
24+
# Initialize emulator in x86_64 mode
25+
mu = Uc(UC_ARCH_X86, UC_MODE_64)
26+
# map 2MB memory for this emulation
27+
mu.mem_map(ADDRESS, 2 * 1024 * 1024)
28+
# write machine code to be emulated to memory
29+
mu.mem_write(ADDRESS, X86_MACHINE_CODE)
30+
# Set the r0 register in the code to the number of 7
31+
mu.reg_write(UC_X86_REG_RDI, 7)
32+
# emulate code in infinite time & unlimited instructions
33+
mu.emu_start(ADDRESS, ADDRESS + len(X86_MACHINE_CODE))
34+
# now print out the R0 register
35+
print("Emulation done. Below is the result")
36+
rax = mu.reg_read(UC_X86_REG_RAX)
37+
print(">>> RAX = %u" % rax)
38+
except UcError as e:
39+
print("Unicorn Error: %s" % e)
+3
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
keystone-engine
2+
capstone
3+
unicorn

0 commit comments

Comments
 (0)