NTQQServiceExport/quickScanElf.py at main · identify4cloud/NTQQServiceExport · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
from elftools.elf.elffile import ELFFile
from capstone import *

def find_symbol_in_got_plt(elf,symbol_name):
    symtab = elf.get_section_by_name('.dynsym')
    if not symtab:
       print("符号表不存在")
       return None
    rel_section = elf.get_section_by_name('.rela.plt')
    if rel_section:
        for rel in rel_section.iter_relocations():
            r_info = rel.entry['r_info']
            rel_symbol_index = r_info >> 32
            rel_symbol = symtab.get_symbol(rel_symbol_index)
            if rel_symbol.name == symbol_name:
                symbol_address = rel['r_offset']
                return symbol_address
    print(f"符号 {symbol_name} 不在段中")
    return None


def get_text_section(elf):
    for section in elf.iter_sections():
        if section.name == '.text':
            return section
    return None

def get_function_ranges(elf):
    md = Cs(CS_ARCH_X86, CS_MODE_64)
    md.skipdata = True
    text_section = get_text_section(elf)
    code = text_section.data()
    start_addr = text_section['sh_addr']
    end_addr = start_addr + text_section['sh_size']

    functions = []
    current_func = None

    insn_list = list(md.disasm(code, start_addr))

    i = 0
    while i < len(insn_list):
        insn = insn_list[i]
        if insn.mnemonic == 'push' and insn.op_str == 'rbp':
            j = i - 1
            while j >= 0 and insn_list[j].mnemonic == 'push':
                j -= 1
            if current_func:
                functions.append(current_func)
            current_func = {'start': insn_list[j + 1].address, 'end': None}
        elif insn.mnemonic == 'mov' and insn.op_str == 'rbp, rsp':
            if current_func:
                functions.append(current_func)
            current_func = {'start': insn.address, 'end': None}
        if current_func:
            current_func['end'] = insn.address + insn.size
        i += 1

    if current_func:
        functions.append(current_func)

    return functions

def find_function_containing_address(functions, address):
    for func in functions:
        if func['start'] <= address < func['end']:
            return func
    return None

def get_section_range_rva(elf, section_name):
    for section in elf.iter_sections():
        if section.name == section_name:
            return section['sh_addr'], section['sh_addr'] + section['sh_size']
    return None, None

def search_bytes(elf, start, end, bytes):
    for section in elf.iter_sections():
        if section['sh_addr'] <= start < section['sh_addr'] + section['sh_size']:
            data = section.data()
            offset = start - section['sh_addr']
            for i in range(offset, offset + (end - start + 1)):
                if data[i:i + len(bytes)] == bytes:
                    return section['sh_addr'] + i
    return None

def search_bytes_all(elf, start, end, bytes):
    rva_list = []
    for section in elf.iter_sections():
        if section['sh_addr'] <= start < section['sh_addr'] + section['sh_size']:
            data = section.data()
            offset = start - section['sh_addr']
            for i in range(offset, offset + (end - start + 1)):
                if data[i:i + len(bytes)] == bytes:
                    rva_list.append(section['sh_addr'] + i)
    return rva_list

def search_data_pattern_all(elf, pattern, start, end):
    rva_list = []
    pattern = pattern.replace(' ', '').replace('0x', '').lower()
    for section in elf.iter_sections():
        if section['sh_addr'] <= start < section['sh_addr'] + section['sh_size']:
            data = section.data()
            offset = start - section['sh_addr']
            for i in range(offset, offset + (end - start + 1)):
                hex_data = ''.join(['%02x' % x for x in data[i:i + len(pattern) // 2]])
                for j in range(0, len(pattern)):
                    if pattern[j] != '?' and pattern[j] != hex_data[j]:
                        break
                else:
                    rva_list.append(section['sh_addr'] + i)
    return rva_list

def search_data_pattern(elf, pattern, start, end):
    pattern = pattern.replace(' ', '').replace('0x', '').lower()
    for section in elf.iter_sections():
        if section['sh_addr'] <= start < section['sh_addr'] + section['sh_size']:
            data = section.data()
            offset = start - section['sh_addr']
            for i in range(offset, offset + (end - start + 1)):
                hex_data = ''.join(['%02x' % x for x in data[i:i + len(pattern) // 2]])
                for j in range(0, len(pattern)):
                    if pattern[j] != '?' and pattern[j] != hex_data[j]:
                        break
                else:
                    return section['sh_addr'] + i
    return None

def search_data_maybe_xref(elf, string_rva, start, end):
    for section in elf.iter_sections():
        if section['sh_addr'] <= start < section['sh_addr'] + section['sh_size']:
            data = section.data()
            offset = start - section['sh_addr']
            for i in range(offset, offset + (end - start + 1)):
                if int.from_bytes(data[i:i + 4], 'little', signed=True) + section['sh_addr'] + i + 4 == string_rva:
                    return section['sh_addr'] + i
    return None

def search_data_maybe_xref_pattern(elf, pattern, string_rva, start, end):
    pattern = pattern.replace(' ', '').replace('0x', '').lower()
    for section in elf.iter_sections():
        if section['sh_addr'] <= start < section['sh_addr'] + section['sh_size']:
            data = section.data()
            offset = start - section['sh_addr']
            for i in range(offset, offset + (end - start + 1)):
                pattern_len = len(pattern) // 2
                hex_data = ''.join(['%02x' % x for x in data[i:i + pattern_len]]) # hex + 4字节偏移
                for j in range(0, len(pattern)):
                    if pattern[j] != '?' and pattern[j] != hex_data[j]:
                        break
                else:
                    if int.from_bytes(data[i+pattern_len:i + 4+pattern_len], 'little', signed=True) + section['sh_addr'] + i + 4 + pattern_len == string_rva:
                        return section['sh_addr'] + i + pattern_len
    return None

def search_data_maybe_xref_all(elf, string_rva, start, end):
    rva_list = []
    for section in elf.iter_sections():
        if section['sh_addr'] <= start < section['sh_addr'] + section['sh_size']:
            data = section.data()
            offset = start - section['sh_addr']
            for i in range(offset, offset + (end - start + 1)):
                if int.from_bytes(data[i:i + 4], 'little', signed=True) + section['sh_addr'] + i + 4 == string_rva:
                    rva_list.append(section['sh_addr'] + i)
    return rva_list

def get_all_call_range(elf, start, end):
    md = Cs(CS_ARCH_X86, CS_MODE_64)
    md.skipdata = True
    code = b''
    for section in elf.iter_sections():
        if section['sh_addr'] <= start < section['sh_addr'] + section['sh_size']:
            offset = start - section['sh_addr']
            code = section.data()[offset:offset + (end - start)]
            break
    insn_list = list(md.disasm(code, start))
    call_list = []
    for insn in insn_list:
        if insn.mnemonic == 'call':
            call_target = int(insn.op_str, 16)
            call_list.append(call_target)
    return call_list

def get_all_push_range(elf, start, end):
    md = Cs(CS_ARCH_X86, CS_MODE_64)
    md.skipdata = True
    code = elf.get_section_by_name('.text').data()[start:end]
    push_count = 0
    for insn in md.disasm(code, start):
        if insn.mnemonic == 'push':
            push_count += 1
    return push_count

def get_function_param_count(elf, start, end):
    md = Cs(CS_ARCH_X86, CS_MODE_64)
    md.detail = True
    md.skipdata = True
    code = elf.get_section_by_name('.text').data()[start:end]
    param_count = 0
    registers = ['rdi', 'rsi', 'rdx', 'rcx', 'r8', 'r9']
    used_registers = set()

    for insn in md.disasm(code, start):
        if insn.mnemonic == 'push':
            param_count += 1
        elif insn.mnemonic == 'mov' and insn.operands[0].type == CS_OP_REG:
            reg_name = insn.reg_name(insn.operands[0].reg)
            if reg_name in registers and reg_name not in used_registers:
                used_registers.add(reg_name)
                param_count += 1

    return param_count