vprof/server-patch/tools/verify_gamedata.py

#!/usr/bin/env python3
"""
verify_gamedata.py — offline validator for vprof_timings.txt.

Mimics the parts of SourceMod's GameConfig signature resolution and Source
Scramble's MemPatch application that matter, so the gamedata can be checked
against a target binary without running a server:

  * KeyValues/SMC parse of the gamedata (comments, nested sections, duplicate
    keys preserved).
  * `@mangled` signatures resolved from the ELF `.symtab` (the same thing
    MemoryUtils::ResolveSymbol does when a game reports hidden symbols, as
    TF2 does).  Byte-pattern signatures with `\\x2A` wildcards are still
    supported for completeness.
  * Source Scramble's `offset`/`verify`/`patch` semantics.

Usage:
    python3 verify_gamedata.py vprof_timings.txt engine_srv.so engine_srv.x64.so

The two binaries are matched to the `linux` and `linux64` blocks respectively.
"""

import struct
import sys


# --------------------------------------------------------------------------
# Minimal SMC/KeyValues parser
# --------------------------------------------------------------------------

def tokenize(text):
    i, n = 0, len(text)
    while i < n:
        c = text[i]
        if c in " \t\r\n":
            i += 1
            continue
        if c == "/" and i + 1 < n and text[i + 1] == "/":
            while i < n and text[i] != "\n":
                i += 1
            continue
        if c == "{":
            yield "{"
            i += 1
            continue
        if c == "}":
            yield "}"
            i += 1
            continue
        if c == '"':
            i += 1
            buf = []
            while i < n and text[i] != '"':
                if text[i] == "\\" and i + 1 < n:
                    buf.append(text[i])
                    buf.append(text[i + 1])
                    i += 2
                else:
                    buf.append(text[i])
                    i += 1
            i += 1
            yield ("str", "".join(buf))
            continue
        j = i
        while j < n and text[j] not in " \t\r\n{}":
            j += 1
        yield ("str", text[i:j])
        i = j


def parse_block(it):
    entries = []
    while True:
        try:
            t = next(it)
        except StopIteration:
            return entries
        if t == "}":
            return entries
        if t == "{":
            continue
        key = t[1]
        nxt = next(it)
        if nxt == "{":
            entries.append((key, parse_block(it)))
        else:
            entries.append((key, nxt[1]))


def sub(entries, key):
    if entries is None:
        return None
    for k, v in entries:
        if k == key:
            return v
    return None


# --------------------------------------------------------------------------
# ELF symbol table (`@symbol` resolution)
# --------------------------------------------------------------------------

def elf_symbols(path):
    data = open(path, "rb").read()
    if data[:4] != b"\x7fELF":
        raise ValueError("%s is not an ELF file" % path)
    ei_class, ei_data = data[4], data[5]
    if ei_data != 1:
        raise ValueError("only little-endian ELF is supported")

    if ei_class == 1:
        e_shoff = struct.unpack_from("<I", data, 0x20)[0]
        e_shentsize = struct.unpack_from("<H", data, 0x2E)[0]
        e_shnum = struct.unpack_from("<H", data, 0x30)[0]
        e_shstrndx = struct.unpack_from("<H", data, 0x32)[0]
        sh_fmt = "<IIIIIIIIII"
        sym_fmt = "<IIIBBH"
        sym_entsize = 16
    elif ei_class == 2:
        e_shoff = struct.unpack_from("<Q", data, 0x28)[0]
        e_shentsize = struct.unpack_from("<H", data, 0x3A)[0]
        e_shnum = struct.unpack_from("<H", data, 0x3C)[0]
        e_shstrndx = struct.unpack_from("<H", data, 0x3E)[0]
        sh_fmt = "<IIQQQQIIQQ"
        sym_fmt = "<IBBHQQ"
        sym_entsize = 24
    else:
        raise ValueError("unknown ELF class %d" % ei_class)

    def section(i):
        return struct.unpack_from(sh_fmt, data, e_shoff + i * e_shentsize)

    shstr = section(e_shstrndx)
    shstr_off = shstr[4]

    def section_name(name_off):
        end = data.index(b"\0", shstr_off + name_off)
        return data[shstr_off + name_off : end].decode("ascii", "replace")

    symtab = strtab = None
    for i in range(e_shnum):
        s = section(i)
        name = section_name(s[0])
        if name == ".symtab":
            symtab = s
        elif name == ".strtab":
            strtab = s

    symbols = {}
    if symtab is None or strtab is None:
        return symbols

    sym_off, sym_size, sym_entsize_hdr = symtab[4], symtab[5], symtab[9]
    entsize = sym_entsize_hdr or sym_entsize
    str_off = strtab[4]
    count = sym_size // entsize

    for i in range(count):
        fields = struct.unpack_from(sym_fmt, data, sym_off + i * entsize)
        if ei_class == 1:
            st_name, st_value, _st_size, _st_info, _st_other, st_shndx = fields
        else:
            st_name, _st_info, _st_other, st_shndx, st_value, _st_size = fields
        if st_name == 0 or st_shndx == 0:
            continue
        end = data.index(b"\0", str_off + st_name)
        name = data[str_off + st_name : end].decode("ascii", "replace")
        symbols.setdefault(name, st_value)
    return symbols


# --------------------------------------------------------------------------
# Byte-pattern signatures (legacy fallback)
# --------------------------------------------------------------------------

def decode_pattern(s):
    out = bytearray()
    i = 0
    while i < len(s):
        if s[i] == "\\" and i + 1 < len(s) and s[i + 1] == "x":
            out.append(int(s[i + 2 : i + 4], 16))
            i += 4
        else:
            out.append(ord(s[i]))
            i += 1
    return bytes(out)


def find_pattern(hay, pat):
    for off in range(0, len(hay) - len(pat) + 1):
        ok = True
        for i in range(len(pat)):
            if pat[i] != 0x2A and pat[i] != hay[off + i]:
                ok = False
                break
        if ok:
            return off
    return None


def parse_offset(s):
    if s.lower().endswith("h"):
        return int(s[:-1], 16)
    return int(s, 0)


# --------------------------------------------------------------------------
# Main
# --------------------------------------------------------------------------

def main(argv):
    if len(argv) != 4:
        sys.stderr.write(__doc__)
        return 2

    gamedata, bin32, bin64 = argv[1], argv[2], argv[3]
    text = open(gamedata, encoding="utf-8", errors="replace").read()
    root = parse_block(iter(tokenize(text)))

    tf = sub(sub(root, "Games"), "tf")
    sigs = sub(tf, "Signatures")
    patches = sub(tf, "MemPatches")

    targets = {
        "linux": {
            "bin": bin32,
            "bytes": open(bin32, "rb").read(),
            "syms": elf_symbols(bin32),
        },
        "linux64": {
            "bin": bin64,
            "bytes": open(bin64, "rb").read(),
            "syms": elf_symbols(bin64),
        },
    }

    failures = 0
    for plat in ("linux", "linux64"):
        tgt = targets[plat]
        hay, syms = tgt["bytes"], tgt["syms"]
        print("=== %s (%s) ===" % (plat, tgt["bin"]))
        for name, body in patches:
            sig_name = sub(body, "signature")
            sigdef = sub(sigs, sig_name)
            library = sub(sigdef, "library")
            sig = sub(sigdef, plat)
            block = sub(body, plat)

            if sig.startswith("@"):
                symname = sig[1:]
                addr = syms.get(symname)
                how = "@%s" % symname
            else:
                addr = find_pattern(hay, decode_pattern(sig))
                how = "pattern"

            if addr is None:
                print("  [FAIL] %-62s %s not found" % (name, how))
                failures += 1
                continue
            if not isinstance(block, list):
                print("  [skip] %-62s no %s block" % (name, plat))
                continue

            off = parse_offset(sub(block, "offset"))
            verify = decode_pattern(sub(block, "verify"))
            replace = decode_pattern(sub(block, "patch"))
            at = addr + off
            current = hay[at : at + len(verify)]
            ok = all(v == 0x2A or v == c for v, c in zip(verify, current))

            if not ok:
                failures += 1
            print(
                "  [%s] %-62s lib=%s addr=0x%x off=0x%x verify=%s patch=%s"
                % (
                    "OK" if ok else "VERIFY-MISMATCH",
                    name,
                    library,
                    addr,
                    off,
                    current.hex(),
                    replace.hex(),
                )
            )

    print("\n%s" % ("ALL PATCHES VERIFIED" if failures == 0 else "FAILURES: %d" % failures))
    return 1 if failures else 0


if __name__ == "__main__":
    raise SystemExit(main(sys.argv))