capstone/bindings/python/test_basic.py
Rot127 ef89b18a88 Architecture updater (auto-sync) - Updating AArch64 (#2026)
* Update sysop inc file

* Fix missing  braces warning

* Handle new system operands

* Fix build errors by renaming.

* Fix segfault

* Fix segfault

* Add custom MCOperand valiadtors

* Add AArch64 case for getFeatureBits

* Fix infinite loop

* Fix braces warning.

* Implement loopuo by name for sys operands

* Fix incorrect translation which remove else if statements.

* Fix several segfaults

* Rename GetRegFromClass patch

* Fix segfaults and asserts

* Fix segfault

* Move MRI setting to Mapping

* Remove unused code

* Add add_op_X functinos for AArch64.

* Add fill detail functins

* Handle RegWithShiftExtend operands

* Handle TypedVectorList operands.

* Handle ComplexRoatation operands

* Handle MemExtend operands

* Handle ImmRangeScale operands

* Handle ExactFPImm operands

* Handle GPRSeqPairsClass operands

* Handle Imm8OptLsl operands

* Handle ImmScale operands

* Handle LogicalImm operands

* Handle Matrix operands

* Handle SME Matrix tiles and vectors.

* Handle normal operands.

* Fix segfault.

* Handle PostInc operands.

* Reorder VecLayout enum to have no duplicate enum value.

* Handle PredicateAsCounter operands

* Handle ZPRasFPR operands

* Handle VectorIndex operands

* Handle UImm12Offset operands.

* Move reg suffix to enum val to single function.

* Handle SVERegOp operands

* Handle SVELogicalImm operands

* Handle SImm operand

* Handle PrefetchOp operands

* Handle Imm and ImmHex operands

* Handle GPR64as32 and GPR64x8 operands

* Add missing break

* Handle FPImm operand

* Handle ExtendedRegister opreand

* Handle CondCode operands

* Handle BTIHintOp operands

* Handle BarrierOption operands

* Handle BarrierXSOption

* Add not implemeted case again

* Handle ArithExtend operands

* Handle AdrpLabel and AlignedLabel operands

* Handle AMNoIndex operands

* Handle AddSubImm operands

* Handle MSRSystemRegisters and MRSSystemRegister operands

* Handle PSBHntOp and RPRFMOperand operands

* Remove unused variables

* Handle InverseCondCode operands

* Handle ImplicityTypedVectorList operands

* Handle ShiftedRegister operands

* Handle Shifter operands

* Handle SIMDType10Operand operands

* Handle SVCROp operands

* Handle SVEPattern operands

* Handle SVEVecLenSpecifier operands

* Handle SysCROperands

* Handle SysXzrPair operands

* Handle PState operands

* Handle VRegOperands

* Primt SME oeprands.

* Fix cs_operand.h include

* Rename arm64 -> aarch64 in python bindings.

* Add Python bindings for SH

* Fix ARM Python bindings (#2127)

* Restructure auto-sync update scripts.

* Move Helper functions to Updater dir

* Move requirements.txt

* Add basic ASUpdater.py

* Run black.

* Add inc file generater to updater

* Add option to select certain inc files fore generation.

* Enable clean build and implement patcher for inc files.

* Format config

* Patch main header files after inc generation.

* Implement clang-format function (unused yet, because it takes forever.)

* Copy generated inc files to arch dir

* Invert clean option (noramlly we need to clean the build dir.)

* Clearify arg doc

* Rename SystemRegister file for AArch64

* Centralize handling of path variables.

* Check if SystemOperands had to be generated before renaming on of its files.

* Replace class parameters by calling get_path

* Remove updater config which only contained paths.

* Add refactor option.

* Remove more path handling in the Configurator.

* Add translation step to updater.

* Fix includes after CppTranslator was moved into the Updater

* Remove updater config

* Fix several issue in the Configurator

* Fix file operations

* Remove addition argument from translator.

* Add Differ step to updater.

* Add path variable for arch_config

* Add diff step.

* Fix typo

* Introduce .clang-format path variable.

* Remove duplicate functions

* Add option to select update steps to execute.

* Check in write functions for write flag.

* Rename PatchMainHeader -> HeaderPatcher

* Move .gitignore

* Add README to vendor dir.

* Add all system operands to cstool output

* Update cstest with aarch64 changes

* Remove wb flag of aarch64 detail struct

* Set updates_flag after decoding

* Set writeback after decoding.

* Rename ARM64 -> AArch64

* Update printer and op mapping

* Exit normally

* Add AArch64 alias

* Fix some tmeplate function calls

* Fix flag check after rebase.

* Fix build by commentig unnused code.

* Add memory operand flag

* Handle memory operands printed via generic printOperand function.

* Handle UImm memory offsets

* Introduce MEM_REG and MEM_IMM op types

* Handle scaled memory immediates

* Check for op_count before checking for mem op at -1 index.

* Update memory operand flags.

* Pass imm/reg memory ops in set_imm/reg to set_mem.

* Add missing set_sme_operand call and fix assert.

* Remove CS_OP_MEM flag before entering switch.

* Preidcates are registers.

* Add shift info always to the previous operand

* Check for generic system regs

* Handle NumLanes = 0 LaneKind = q case

* Replace printImm call with normal print logic. Otherwise ops get added twice to detail.

* Handle FP operands in printOperand.

* Add access information to float operands.

* Rewrite SME matrix handling.

* Set correct SME layouts and allow for immediate range sme offsets.

* Handle cases of unknown system alias by setting their raw values

* Update cstool and header file with new SME offset handling

* Handle SME Tile lists.

* Fix build error in cstest

* Update MC tests for AArch64

* Handle TLBI operands and fix printing bug.

* Fix: Print signed value as signed.

* Add more system alias to detail.

* Remove duplicate hex prefix

* Set correct values for the register info

* Replace tabs with white spaces

* Move string append logic to own function.

* Set DecodeComplete = true before decoding (as originally in the LLVM code).

* Change type of feature argument, since only LLVM features are passed, not CS groups.

* Imitate lower_bound for the index table binary search.

* Remove trailing comments from test files.

* Print shift amount in decimal

* Save detail of shift alias instructions.

* Add extension details fot ext instruction alias

* Print LSB and width in decimal

* Fix LLVM bug. The feature check for V8_2a doesn't check if all features are enabled.

* Fix lower_bounds check.
For m == 0 we wrap around 0 of cause.

* Fix feature check. Add check for FeatureAll since it includes XS

* Operate on temporary MCInst when trying decoding.

* Add lower_bound behavior to IndexTypeStr binsearch.

* Fix MC tests which were incorrect because of missing FeatureAll check

* Add Alias handling for AArch64

* Update system operands with SYSIMM types and add additional sysop category.

* Add macros for meta programming (ARM64 <-> AArch64 selection).

* Fix union/struct confusion and add raw_value member to uninions.

* Allow to set Syntax and mode options for AArch64

* Fix build warning by using correct type

* Print shift value in decimal

* Add missing call to add_cs_detail.

* Update name map files with normalized names.

* Remove unused function

* Add check if detail should be filled.

* Fill detail for real instructions if only real detail is requested.

* Add always the extension.

* Make dir creation log message debug level

* Implement ADR immediate operand printer.

See: c3484b1fdc

* Check for flag registers beeing written and update flag.

* Move multiple CondCode helpers to aarch64.h because they are so freaking useful.

+ Print CC if it is EQ

* Fix incorrectly initialized CC and VectorLayout.

* Add LSL shift type for extensions.

* Fix case when shift amount is 0

* Fix post-index memory instructions.

* Pass raw immediate through getShiftValue to extract actual shift amount

* Setup AArch64 detail ops.

* Add flag for operands part of a list.

* Set vector indices for all relevant registers.

* Add missing call to add_cs_detail for postIncOperands

* Add ugly yet reliable way to determine post-index addressing mode

* Add support for old Capstone register alias.

* Remove leading space before some alias mnemonics.

* add AARCH64 to `cmake.sh`

* add HAS_AARCH64 to `cs.c`

* should probably just reference `cs_operand.h` in `aarch64.h`

* hint compiler at `AArch64_SYSREG` enum type for casting purposes

* update `Makefile` for AARCH64

leaves `CAPSTONE_HAS_ARM64` supported

* `testFeatureBits` platform function check

`testFeatureBits` should check if the platform function is visible first

* update tests to use AARCH64 convention

* hack: avoid enum casts for `MCInst` Values

Apple compiler really hates typecasting a enum, even if bounded from a unsigned. Lets set the raw_value directly

is a hack and needs proper review

* Check for present detail before accessing it.

* Add CS only groups

* Use general map ins_op type

* Fix build warning about str size computation.

* Disable warning about unitialized value for GCC 11.

Imm is initialized and the warning does not appear
in later versions.

* Use correct include guard for PPC

* Add missing requirements

* Update SystemOperand enums.

* Fix overlapping comparison warning

* Fix reachable assert where OpNum is not of type IMM

* Handle 0.0 operand for fcmp

* Fix incorrect variable passed.

* Fix for MacOS which doesn't know the warning and throws another one.

* Make getExtendEncoding static to fix build warning on MSVC.

* Fix build error: 'missing binary operator before token' by checking __GNUC__

* Add string search to add vector layout info.

* Add missing mem disponents of several ldr and str instructions.

* Add 0 immediates to several instructions.

* Rename v regs to q and d variant.

The cs_regname API can not pass the variant name of the register requested.
So we simply emit the default variant name.

* Fix incorrect enum value.

* Fix tests for system operands.

* Fix syntax issues in tests.

* Rename Arm64 -> AArch64 Python bindings.

* Fix Python bindings C structs.

* Fix generation of constants (ARMCC skipped because it starts with ARM)

* Update const files

* Remove -Wmaybe-uninitialized warning since it fails fuzz build

* Add missing comma

* Fix case

* Fix AArch64 Python bindings:

- Do not generate constants automatically (dscript is way too buggy).
- Update printing of details.

* Rename ARM64 -> AArch64 in test_corpus.py

* Rename test_arm64 -> test_aarch64

* Rename ARM-64 -> AArch64

* Fix diff CI test by disassembling AArch64 at former ARM64 place

* Fix several wrong types and remove unnecessary memebers from Python binding

* Fix: Same printing format of detail for cstool, test_ and test_*.py

* Fix: pass correct op index for mov alias with op[1] == reg wzr.

* Set prfm op manuall in case of unnown sysop. set_imm would add it to an memory operand wihtout base.

* Fix: If barrier ops are not set an assert is reached.

We fix it here by simply getting the immediate as the printing code does.

---------

Co-authored-by: Peace-Maker <peace-maker@wcfan.de>
Co-authored-by: Dayton <5340801+watbulb@users.noreply.github.com>
2023-11-15 12:12:14 +08:00

140 lines
8.3 KiB
Python
Executable file

#!/usr/bin/env python
# Capstone Python bindings, by Nguyen Anh Quynnh <aquynh@gmail.com>
from __future__ import print_function
from capstone import *
import binascii
import sys
from xprint import to_hex
_python3 = sys.version_info.major == 3
X86_CODE16 = b"\x8d\x4c\x32\x08\x01\xd8\x81\xc6\x34\x12\x00\x00"
X86_CODE32 = b"\xba\xcd\xab\x00\x00\x8d\x4c\x32\x08\x01\xd8\x81\xc6\x34\x12\x00\x00"
X86_CODE64 = b"\x55\x48\x8b\x05\xb8\x13\x00\x00"
ARM_CODE = b"\xED\xFF\xFF\xEB\x04\xe0\x2d\xe5\x00\x00\x00\x00\xe0\x83\x22\xe5\xf1\x02\x03\x0e\x00\x00\xa0\xe3\x02\x30\xc1\xe7\x00\x00\x53\xe3"
ARM_CODE2 = b"\x10\xf1\x10\xe7\x11\xf2\x31\xe7\xdc\xa1\x2e\xf3\xe8\x4e\x62\xf3"
THUMB_CODE = b"\x70\x47\xeb\x46\x83\xb0\xc9\x68"
THUMB_CODE2 = b"\x4f\xf0\x00\x01\xbd\xe8\x00\x88\xd1\xe8\x00\xf0"
THUMB_MCLASS = b"\xef\xf3\x02\x80"
ARMV8 = b"\xe0\x3b\xb2\xee\x42\x00\x01\xe1\x51\xf0\x7f\xf5"
MIPS_CODE = b"\x0C\x10\x00\x97\x00\x00\x00\x00\x24\x02\x00\x0c\x8f\xa2\x00\x00\x34\x21\x34\x56"
MIPS_CODE2 = b"\x56\x34\x21\x34\xc2\x17\x01\x00"
MIPS_32R6M = b"\x00\x07\x00\x07\x00\x11\x93\x7c\x01\x8c\x8b\x7c\x00\xc7\x48\xd0"
MIPS_32R6 = b"\xec\x80\x00\x19\x7c\x43\x22\xa0"
AARCH64_CODE = b"\x21\x7c\x02\x9b\x21\x7c\x00\x53\x00\x40\x21\x4b\xe1\x0b\x40\xb9"
PPC_CODE = b"\x80\x20\x00\x00\x80\x3f\x00\x00\x10\x43\x23\x0e\xd0\x44\x00\x80\x4c\x43\x22\x02\x2d\x03\x00\x80\x7c\x43\x20\x14\x7c\x43\x20\x93\x4f\x20\x00\x21\x4c\xc8\x00\x21"
PPC_CODE2 = b"\x10\x60\x2a\x10\x10\x64\x28\x88\x7c\x4a\x5d\x0f"
SPARC_CODE = b"\x80\xa0\x40\x02\x85\xc2\x60\x08\x85\xe8\x20\x01\x81\xe8\x00\x00\x90\x10\x20\x01\xd5\xf6\x10\x16\x21\x00\x00\x0a\x86\x00\x40\x02\x01\x00\x00\x00\x12\xbf\xff\xff\x10\xbf\xff\xff\xa0\x02\x00\x09\x0d\xbf\xff\xff\xd4\x20\x60\x00\xd4\x4e\x00\x16\x2a\xc2\x80\x03"
SPARCV9_CODE = b"\x81\xa8\x0a\x24\x89\xa0\x10\x20\x89\xa0\x1a\x60\x89\xa0\x00\xe0"
SYSZ_CODE = b"\xed\x00\x00\x00\x00\x1a\x5a\x0f\x1f\xff\xc2\x09\x80\x00\x00\x00\x07\xf7\xeb\x2a\xff\xff\x7f\x57\xe3\x01\xff\xff\x7f\x57\xeb\x00\xf0\x00\x00\x24\xb2\x4f\x00\x78"
XCORE_CODE = b"\xfe\x0f\xfe\x17\x13\x17\xc6\xfe\xec\x17\x97\xf8\xec\x4f\x1f\xfd\xec\x37\x07\xf2\x45\x5b\xf9\xfa\x02\x06\x1b\x10"
M68K_CODE = b"\xd4\x40\x87\x5a\x4e\x71\x02\xb4\xc0\xde\xc0\xde\x5c\x00\x1d\x80\x71\x12\x01\x23\xf2\x3c\x44\x22\x40\x49\x0e\x56\x54\xc5\xf2\x3c\x44\x00\x44\x7a\x00\x00\xf2\x00\x0a\x28\x4E\xB9\x00\x00\x00\x12\x4E\x75"
TMS320C64X_CODE = b"\x01\xac\x88\x40\x81\xac\x88\x43\x00\x00\x00\x00\x02\x90\x32\x96\x02\x80\x46\x9e\x05\x3c\x83\xe6\x0b\x0c\x8b\x24"
M680X_CODE = b"\x06\x10\x19\x1a\x55\x1e\x01\x23\xe9\x31\x06\x34\x55\xa6\x81\xa7\x89\x7f\xff\xa6\x9d\x10\x00\xa7\x91\xa6\x9f\x10\x00\x11\xac\x99\x10\x00\x39"
EVM_CODE = b"\x60\x61"
WASM_CODE = b"\x20\x00\x20\x01\x41\x20\x10\xc9\x01\x45\x0b"
MOS65XX_CODE = b"\x0d\x34\x12\x00\x81\x65\x6c\x01\x00\x85\xFF\x10\x00\x19\x42\x42\x00\x49\x42"
EBPF_CODE = b"\x97\x09\x00\x00\x37\x13\x03\x00\xdc\x02\x00\x00\x20\x00\x00\x00\x30\x00\x00\x00\x00\x00\x00\x00\xdb\x3a\x00\x01\x00\x00\x00\x00\x84\x02\x00\x00\x00\x00\x00\x00\x6d\x33\x17\x02\x00\x00\x00\x00"
RISCV_CODE32 = b"\x37\x34\x00\x00\x97\x82\x00\x00\xef\x00\x80\x00\xef\xf0\x1f\xff\xe7\x00\x45\x00\xe7\x00\xc0\xff\x63\x05\x41\x00\xe3\x9d\x61\xfe\x63\xca\x93\x00\x63\x53\xb5\x00\x63\x65\xd6\x00\x63\x76\xf7\x00\x03\x88\x18\x00\x03\x99\x49\x00\x03\xaa\x6a\x00\x03\xcb\x2b\x01\x03\xdc\x8c\x01\x23\x86\xad\x03\x23\x9a\xce\x03\x23\x8f\xef\x01\x93\x00\xe0\x00\x13\xa1\x01\x01\x13\xb2\x02\x7d\x13\xc3\x03\xdd\x13\xe4\xc4\x12\x13\xf5\x85\x0c\x13\x96\xe6\x01\x13\xd7\x97\x01\x13\xd8\xf8\x40\x33\x89\x49\x01\xb3\x0a\x7b\x41\x33\xac\xac\x01\xb3\x3d\xde\x01\x33\xd2\x62\x40\xb3\x43\x94\x00\x33\xe5\xc5\x00\xb3\x76\xf7\x00\xb3\x54\x39\x01\xb3\x50\x31\x00\x33\x9f\x0f\x00"
RISCV_CODE64 = b"\x13\x04\xa8\x7a"
all_tests = (
(CS_ARCH_X86, CS_MODE_16, X86_CODE16, "X86 16bit (Intel syntax)", None),
(CS_ARCH_X86, CS_MODE_32, X86_CODE32, "X86 32bit (ATT syntax)", CS_OPT_SYNTAX_ATT),
(CS_ARCH_X86, CS_MODE_32, X86_CODE32, "X86 32 (Intel syntax)", None),
(CS_ARCH_X86, CS_MODE_32, X86_CODE32, "X86 32 (MASM syntax)", CS_OPT_SYNTAX_MASM),
(CS_ARCH_X86, CS_MODE_64, X86_CODE64, "X86 64 (Intel syntax)", None),
(CS_ARCH_ARM, CS_MODE_ARM, ARM_CODE, "ARM", None),
(CS_ARCH_ARM, CS_MODE_THUMB, THUMB_CODE2, "THUMB-2", None),
(CS_ARCH_ARM, CS_MODE_ARM, ARM_CODE2, "ARM: Cortex-A15 + NEON", None),
(CS_ARCH_ARM, CS_MODE_THUMB, THUMB_CODE, "THUMB", None),
(CS_ARCH_ARM, CS_MODE_THUMB + CS_MODE_MCLASS, THUMB_MCLASS, "Thumb-MClass", None),
(CS_ARCH_ARM, CS_MODE_ARM + CS_MODE_V8, ARMV8, "Arm-V8", None),
(CS_ARCH_MIPS, CS_MODE_MIPS32 + CS_MODE_BIG_ENDIAN, MIPS_CODE, "MIPS-32 (Big-endian)", None),
(CS_ARCH_MIPS, CS_MODE_MIPS64 + CS_MODE_LITTLE_ENDIAN, MIPS_CODE2, "MIPS-64-EL (Little-endian)", None),
(CS_ARCH_MIPS, CS_MODE_MIPS32R6 + CS_MODE_MICRO + CS_MODE_BIG_ENDIAN, MIPS_32R6M, "MIPS-32R6 | Micro (Big-endian)", None),
(CS_ARCH_MIPS, CS_MODE_MIPS32R6 + CS_MODE_BIG_ENDIAN, MIPS_32R6, "MIPS-32R6 (Big-endian)", None),
(CS_ARCH_AARCH64, CS_MODE_ARM, AARCH64_CODE, "AARCH64", None),
(CS_ARCH_PPC, CS_MODE_BIG_ENDIAN, PPC_CODE, "PPC-64", None),
(CS_ARCH_PPC, CS_MODE_BIG_ENDIAN, PPC_CODE, "PPC-64, print register with number only", CS_OPT_SYNTAX_NOREGNAME),
(CS_ARCH_PPC, CS_MODE_BIG_ENDIAN + CS_MODE_QPX, PPC_CODE2, "PPC-64 + QPX", None),
(CS_ARCH_SPARC, CS_MODE_BIG_ENDIAN, SPARC_CODE, "Sparc", None),
(CS_ARCH_SPARC, CS_MODE_BIG_ENDIAN + CS_MODE_V9, SPARCV9_CODE, "SparcV9", None),
(CS_ARCH_SYSZ, 0, SYSZ_CODE, "SystemZ", None),
(CS_ARCH_XCORE, 0, XCORE_CODE, "XCore", None),
(CS_ARCH_M68K, CS_MODE_BIG_ENDIAN | CS_MODE_M68K_040, M68K_CODE, "M68K", None),
(CS_ARCH_TMS320C64X, 0, TMS320C64X_CODE, "TMS320C64x", None),
(CS_ARCH_M680X, CS_MODE_M680X_6809, M680X_CODE, "M680X_M6809", None),
(CS_ARCH_EVM, 0, EVM_CODE, "EVM", None),
(CS_ARCH_WASM, 0, WASM_CODE, "WASM", None),
(CS_ARCH_MOS65XX, 0, MOS65XX_CODE, "MOS65XX", None),
(CS_ARCH_BPF, CS_MODE_LITTLE_ENDIAN | CS_MODE_BPF_EXTENDED, EBPF_CODE, "eBPF", None),
(CS_ARCH_RISCV, CS_MODE_RISCV32, RISCV_CODE32, "RISCV32", None),
(CS_ARCH_RISCV, CS_MODE_RISCV64, RISCV_CODE64, "RISCV64", None),
)
# ## Test cs_disasm_quick()
def test_cs_disasm_quick():
for arch, mode, code, comment, syntax in all_tests:
print('*' * 40)
print("Platform: %s" % comment)
print("Disasm:")
print(to_hex(code))
for insn in cs_disasm_quick(arch, mode, code, 0x1000):
print("0x%x:\t%s\t%s" % (insn.address, insn.mnemonic, insn.op_str))
print()
def test_different_data_formats():
if _python3:
data = bytes.fromhex('4831C948F7E1043B48BB0A2F62696E2F2F736852530A545F5257545E0F05')
else:
data = bytes(bytearray.fromhex('4831C948F7E1043B48BB0A2F62696E2F2F736852530A545F5257545E0F05'))
mnemonics = ['xor', 'mul', 'add', 'movabs', 'push', 'pop', 'push', 'push', 'push', 'pop', 'syscall']
disassembler = Cs(CS_ARCH_X86, CS_MODE_64)
for name, code in (
('bytearray', bytearray(data)),
('memoryview of bytearray', memoryview(bytearray(data))),
('memoryview of data', memoryview(data)),
('raw data', data)
):
if mnemonics != [op for _, _, op, _ in disassembler.disasm_lite(code, 0)]:
print('failure in disassemble-lite for %s.' % name)
if mnemonics != [instruction.mnemonic for instruction in disassembler.disasm(code, 0)]:
print('failure in disassemble-full for %s.' % name)
# ## Test class Cs
def test_class():
for arch, mode, code, comment, syntax in all_tests:
print('*' * 16)
print("Platform: %s" % comment)
print("Code: %s" % to_hex(code))
print("Disasm:")
try:
md = Cs(arch, mode)
if syntax is not None:
md.syntax = syntax
for insn in md.disasm(code, 0x1000):
# bytes = binascii.hexlify(insn.bytes)
# print("0x%x:\t%s\t%s\t// hex-code: %s" %(insn.address, insn.mnemonic, insn.op_str, bytes))
print("0x%x:\t%s\t\t%s" % (insn.address, insn.mnemonic, insn.op_str))
print("0x%x:" % (insn.address + insn.size))
print()
except CsError as e:
print("ERROR: %s" % e)
# test_cs_disasm_quick()
# print ("*" * 40)
if __name__ == '__main__':
test_class()
test_different_data_formats()