#!/usr/bin/env python3
"""Hostile raw-9P2000 client for the 9proc-demo server (stdlib only).

Usage:
    adv_9proc_hostile.py --server zig-out/bin/9proc-demo   # spawns it on a temp unix socket
    adv_9proc_hostile.py --socket PATH                      # attacks a running server

Every attack is followed by a "server still healthy" probe on a fresh connection.
Exit status is non-zero if any check fails, the server dies, or a probe hangs.
"""
import argparse
import os
import signal
import socket
import struct
import subprocess
import sys
import tempfile
import threading
import time

NOTAG = 0xFFFF
NOFID = 0xFFFFFFFF

# The Rerror strings of the conditions cloud9.fs (the file-server engine the
# core is a backend of) decides itself; the tree's own refusals keep the
# Plan 9 strings ("file does not exist", "bad command", ...).
MSIZE_MIN = 217                                 # one full Rwalk must fit
E_UNKNOWN_FID = "fid unknown or out of range"
E_FID_IN_USE = "fid already in use"
E_TOO_MANY_FIDS = "Too many open files in system"
E_BAD_USE = "bad use of fid"                    # I/O on an unopened fid; a walk or clone from an open one
E_ALREADY_OPEN = "file already open for I/O"    # open or create on an open fid
E_BAD_OFFSET = "bad offset in directory read"
E_PERM = "permission denied"                    # the engine's own refusals: dirs for write, OEXEC, static trees
E_WSTAT = "wstat prohibited"                    # engine-owned stat fields, or a length on a directory
E_ILLEGAL_NAME = "illegal name"                 # names of creates and renames
E_INVAL = "Invalid argument"                    # a reply that cannot fit msize; a dir read count below one record
E_INTERRUPTED = "Interrupted system call"
Tversion, Rversion, Tauth, Rauth, Tattach, Rattach, Rerror = 100, 101, 102, 103, 104, 105, 107
Tflush, Rflush, Twalk, Rwalk, Topen, Ropen, Tcreate, Rcreate = 108, 109, 110, 111, 112, 113, 114, 115
Tread, Rread, Twrite, Rwrite, Tclunk, Rclunk, Tremove, Rremove = 116, 117, 118, 119, 120, 121, 122, 123
Tstat, Rstat, Twstat, Rwstat = 124, 125, 126, 127
OREAD, OWRITE, ORDWR, OEXEC, OTRUNC, ORCLOSE = 0, 1, 2, 3, 0x10, 0x40
DMDIR, DMAPPEND, DMEXCL = 0x80000000, 0x40000000, 0x20000000
NAMES = {v: k for k, v in globals().items() if k[:1] in "TR" and isinstance(v, int) and 100 <= v <= 127}

FAILS = []
PASSES = 0


def ok(name, cond, detail=""):
    global PASSES
    if cond:
        PASSES += 1
        print(f"ok   - {name}")
    else:
        FAILS.append(name)
        print(f"FAIL - {name} {detail}")


def s16(b):
    return struct.pack("<H", len(b)) + b


def frame(typ, tag, body):
    return struct.pack("<IBH", 7 + len(body), typ, tag) + body


def mkstat(name=b"", uid=b"", gid=b"", muid=b"", typ=0xFFFF, dev=0xFFFFFFFF, qtype=0xFF, qvers=0xFFFFFFFF,
           qpath=0xFFFFFFFFFFFFFFFF, mode=0xFFFFFFFF, atime=0xFFFFFFFF, mtime=0xFFFFFFFF,
           length=0xFFFFFFFFFFFFFFFF):
    body = struct.pack("<HIBIQIIIQ", typ, dev, qtype, qvers, qpath, mode, atime, mtime, length)
    body += s16(name) + s16(uid) + s16(gid) + s16(muid)
    return struct.pack("<H", len(body)) + body


def parse_stat(b):
    n, = struct.unpack_from("<H", b, 0)
    typ, dev, qtype, qvers, qpath, mode, atime, mtime, length = struct.unpack_from("<HIBIQIIIQ", b, 2)
    off = 2 + 2 + 4 + 13 + 4 + 4 + 4 + 8
    strs = []
    for _ in range(4):
        ln, = struct.unpack_from("<H", b, off)
        strs.append(b[off + 2:off + 2 + ln])
        off += 2 + ln
    assert off == n + 2, (off, n)
    return dict(type=typ, dev=dev, qid=(qtype, qvers, qpath), mode=mode, atime=atime, mtime=mtime,
                length=length, name=strs[0], uid=strs[1], gid=strs[2], muid=strs[3])


class Nine:
    """One raw 9P connection; every call returns (type, tag, body) or raises."""

    def __init__(self, path, timeout=5.0):
        self.s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
        self.s.settimeout(timeout)
        self.s.connect(path)
        self.tag = 1
        self.buf = b""

    def close(self):
        try:
            self.s.close()
        except OSError:
            pass

    def raw(self, data):
        try:
            self.s.sendall(data)
        except OSError:
            pass  # the server may already have closed; the caller checks with expect_dead()

    def recv_frame(self):
        while len(self.buf) < 4:
            d = self.s.recv(65536)
            if not d:
                raise EOFError("server closed")
            self.buf += d
        size, = struct.unpack_from("<I", self.buf)
        while len(self.buf) < size:
            d = self.s.recv(65536)
            if not d:
                raise EOFError("server closed")
            self.buf += d
        f, self.buf = self.buf[:size], self.buf[size:]
        typ, tag = struct.unpack_from("<BH", f, 4)
        return typ, tag, f[7:]

    def call(self, typ, body, tag=None):
        if tag is None:
            tag = self.tag
            self.tag = (self.tag + 1) & 0xFFFE
        try:
            self.raw(frame(typ, tag, body))
            rt, rtag, rb = self.recv_frame()
        except (EOFError, OSError):
            return None, None, b""
        return rt, rtag, rb

    def expect(self, typ, body, want, tag=None):
        rt, rtag, rb = self.call(typ, body, tag)
        return rt == want, rt, rb

    def err(self, typ, body):
        rt, _, rb = self.call(typ, body)
        if rt != Rerror:
            return None
        n, = struct.unpack_from("<H", rb)
        return rb[2:2 + n].decode("utf-8", "replace")

    # conveniences
    def version(self, msize=65536, version=b"9P2000"):
        rt, rtag, rb = self.call(Tversion, struct.pack("<I", msize) + s16(version), NOTAG)
        if rt != Rversion:
            return rt, None, None
        ms, = struct.unpack_from("<I", rb)
        n, = struct.unpack_from("<H", rb, 4)
        return rt, ms, rb[6:6 + n]

    def attach(self, fid=0, uname=b"hostile", aname=b""):
        return self.call(Tattach, struct.pack("<II", fid, NOFID) + s16(uname) + s16(aname))

    def walk(self, fid, newfid, names):
        b = struct.pack("<IIH", fid, newfid, len(names)) + b"".join(s16(n) for n in names)
        return self.call(Twalk, b)

    def walk_ok(self, fid, newfid, names):
        rt, _, rb = self.walk(fid, newfid, names)
        if rt != Rwalk:
            return None
        n, = struct.unpack_from("<H", rb)
        return n

    def open(self, fid, mode):
        return self.call(Topen, struct.pack("<IB", fid, mode))

    def create(self, fid, name, perm, mode):
        return self.call(Tcreate, struct.pack("<I", fid) + s16(name) + struct.pack("<IB", perm, mode))

    def read(self, fid, offset, count):
        rt, _, rb = self.call(Tread, struct.pack("<IQI", fid, offset, count))
        if rt != Rread:
            return rt, rb
        n, = struct.unpack_from("<I", rb)
        return rt, rb[4:4 + n]

    def write(self, fid, offset, data):
        return self.call(Twrite, struct.pack("<IQI", fid, offset, len(data)) + data)

    def clunk(self, fid):
        return self.call(Tclunk, struct.pack("<I", fid))

    def remove(self, fid):
        return self.call(Tremove, struct.pack("<I", fid))

    def stat(self, fid):
        rt, _, rb = self.call(Tstat, struct.pack("<I", fid))
        if rt != Rstat:
            return rt, rb
        n, = struct.unpack_from("<H", rb)
        return rt, parse_stat(rb[2:2 + n])

    def wstat(self, fid, st):
        return self.call(Twstat, struct.pack("<I", fid) + s16(st))

    def read_all(self, fid, chunk=8192):
        out = b""
        while True:
            rt, d = self.read(fid, len(out), chunk)
            if rt != Rread:
                return None
            if not d:
                return out
            out += d

    def path_read(self, names, fid=77):
        if self.walk_ok(0, fid, names) != len(names):
            return None
        rt, _, _ = self.open(fid, OREAD)
        if rt != Ropen:
            self.clunk(fid)
            return None
        d = self.read_all(fid)
        self.clunk(fid)
        return d

    def session(self, msize=65536):
        rt, ms, _ = self.version(msize)
        assert rt == Rversion, rt
        rt, _, _ = self.attach()
        assert rt == Rattach, rt
        return ms


def healthy(path):
    """Fresh connection; the tree must still answer and /build/zig_version must be non-empty."""
    try:
        c = Nine(path, timeout=5.0)
        c.session()
        d = c.path_read([b"build", b"zig_version"])
        c.close()
        return bool(d)
    except Exception as e:  # noqa: BLE001
        print(f"      probe failed: {e!r}")
        return False


def expect_dead(c):
    """The server must close the connection (EOF) rather than answer or hang."""
    try:
        c.s.settimeout(5.0)
        d = c.s.recv(4096)
        return d == b""
    except socket.timeout:
        return False
    except OSError:
        return True


def rss_kb(pid):
    try:
        with open(f"/proc/{pid}/status") as f:
            for line in f:
                if line.startswith("VmRSS:"):
                    return int(line.split()[1])
    except OSError:
        return -1
    return -1


def threads(pid):
    try:
        return len(os.listdir(f"/proc/{pid}/task"))
    except OSError:
        return -1


# --------------------------------------------------------------------------- attacks


def attack_framing(path):
    print("# framing")
    c = Nine(path)
    c.raw(os.urandom(64))
    ok("garbage bytes: connection closed", expect_dead(c))
    c.close()
    for size in (0, 1, 6, 7, 0xFFFFFFFF, (1 << 20) + 1):
        c = Nine(path)
        c.raw(struct.pack("<I", size) + b"\x64\xff\xff" + b"\x00" * 16)
        ok(f"frame size {size}: connection closed", expect_dead(c))
        c.close()
    # exactly 7 bytes claiming size 7 with a bogus type
    c = Nine(path)
    c.raw(struct.pack("<IBH", 7, 0xEE, 1))
    ok("size-7 frame with unknown type: closed", expect_dead(c))
    c.close()
    # Terror (type 106) is reserved
    c = Nine(path)
    c.raw(frame(106, 1, b""))
    ok("Terror frame: closed", expect_dead(c))
    c.close()
    # an R-type sent to the server
    c = Nine(path)
    c.raw(frame(Rversion, NOTAG, struct.pack("<I", 8192) + s16(b"9P2000")))
    ok("R-message sent to server: closed", expect_dead(c))
    c.close()
    # half a frame then disconnect
    c = Nine(path)
    c.raw(frame(Tversion, NOTAG, struct.pack("<I", 8192) + s16(b"9P2000"))[:9])
    c.close()
    # request before Tversion
    c = Nine(path)
    c.raw(frame(Tattach, 1, struct.pack("<II", 0, NOFID) + s16(b"u") + s16(b"")))
    ok("Tattach before Tversion: closed", expect_dead(c))
    c.close()
    # Tversion with a tag other than NOTAG
    c = Nine(path)
    c.raw(frame(Tversion, 5, struct.pack("<I", 8192) + s16(b"9P2000")))
    ok("Tversion with tag 5: closed", expect_dead(c))
    c.close()
    # Tversion msize below the engine's floor (one full Rwalk must fit): no Rversion
    for ms in (0, 1, 23, 24, 64, MSIZE_MIN - 1):
        c = Nine(path)
        rt, _, _ = c.version(ms)
        ok(f"Tversion msize {ms}: no Rversion (closed or Rerror)", rt in (None, Rerror) or expect_dead(c))
        c.close()
    # the floor itself is negotiable, and everything that fits is served at it
    c = Nine(path)
    rt, ms, ver = c.version(MSIZE_MIN)
    ok(f"Tversion msize {MSIZE_MIN} accepted", rt == Rversion and ms == MSIZE_MIN and ver == b"9P2000", f"{rt} {ms} {ver}")
    rt, _, _ = c.attach(uname=b"u")
    ok("attach at the floor", rt == Rattach, rt)
    rt, rb = c.stat(0)
    ok("stat of the root at the floor fits", rt == Rstat, f"{rt} {rb!r}")
    rt, _, rb = c.walk(0, 1, [b"."] * 16)
    ok("16-element walk at the floor fits exactly", rt == Rwalk, f"{rt} {rb!r}")
    c.clunk(1)
    rt, _, _ = c.walk(0, 1, [b"README"])
    ok("1-element walk at the floor", rt == Rwalk, rt)
    rt, _, _ = c.open(1, OREAD)
    ok("open at the floor", rt == Ropen, rt)
    rt, d = c.read(1, 0, 4096)
    ok(f"read at the floor returns <= {MSIZE_MIN - 11} bytes", rt == Rread and 0 < len(d) <= MSIZE_MIN - 11, f"{rt} {d!r}")
    rt, _, _ = c.clunk(1)
    ok("clunk at the floor still works", rt == Rclunk, rt)
    c.close()
    # huge msize is clamped to the server's max (1 MiB)
    c = Nine(path)
    rt, ms, ver = c.version(0xFFFFFFFF)
    ok("Tversion msize 2^32-1 clamped to 1 MiB", rt == Rversion and ms == 1 << 20, f"{rt} {ms}")
    # a frame larger than the negotiated msize
    c.attach()
    c.raw(frame(Twrite, 1, struct.pack("<IQI", 0, 0, (1 << 20)) + b"x" * (1 << 20)))
    ok("frame larger than msize: closed", expect_dead(c))
    c.close()
    # unknown version string
    c = Nine(path)
    rt, ms, ver = c.version(8192, b"9P2001")
    ok("unknown version answered 'unknown'", rt == Rversion and ver == b"unknown", f"{rt} {ver}")
    rt, _, _ = c.attach()
    ok("request after unknown version: closed", rt is None or expect_dead(c))
    c.close()
    c = Nine(path)
    rt, ms, ver = c.version(8192, b"9P2000.L")
    ok("9P2000.L falls back to 9P2000", rt == Rversion and ver == b"9P2000", f"{rt} {ver}")
    c.close()
    ok("server healthy after framing attacks", healthy(path))


def attack_tags(path):
    print("# tags and flush")
    c = Nine(path)
    c.session()
    # Tflush for a tag that was never used
    rt, tag, _ = c.call(Tflush, struct.pack("<H", 4242), 9)
    ok("Tflush of unknown oldtag is Rflush", rt == Rflush and tag == 9, rt)
    rt, _, _ = c.call(Tflush, struct.pack("<H", NOTAG), 10)
    ok("Tflush of NOTAG is Rflush", rt == Rflush, rt)
    # same tag twice in a row (sequential: fine)
    rt, _, _ = c.call(Tstat, struct.pack("<I", 0), 7)
    rt2, _, _ = c.call(Tstat, struct.pack("<I", 0), 7)
    ok("tag reuse after reply works", rt == Rstat and rt2 == Rstat)
    # two requests with the same tag pipelined: the server is synchronous so both get answered
    c.raw(frame(Tstat, 7, struct.pack("<I", 0)) + frame(Tstat, 7, struct.pack("<I", 0)))
    a = c.recv_frame()
    b = c.recv_frame()
    ok("pipelined duplicate tags: both answered in order", a[0] == Rstat and b[0] == Rstat and a[1] == 7 and b[1] == 7)
    # a request with NOTAG
    c.raw(frame(Tstat, NOTAG, struct.pack("<I", 0)))
    ok("non-version request with NOTAG: closed", expect_dead(c))
    c.close()
    # 100 pipelined requests in one send
    c = Nine(path)
    c.session()
    blob = b"".join(frame(Tstat, i, struct.pack("<I", 0)) for i in range(100))
    c.raw(blob)
    got = [c.recv_frame() for _ in range(100)]
    ok("100 pipelined Tstat all answered in order", all(g[0] == Rstat and g[1] == i for i, g in enumerate(got)))
    c.close()
    ok("server healthy after tag attacks", healthy(path))


def attack_walk(path):
    print("# walk")
    c = Nine(path)
    c.session()
    # 17 names is a wire violation -> connection closed
    c.raw(frame(Twalk, 1, struct.pack("<IIH", 0, 1, 17) + s16(b"a") * 17))
    ok("Twalk with 17 names: closed", expect_dead(c))
    c.close()
    c = Nine(path)
    c.session()
    ok("Twalk with 16 names ('.' x16) succeeds", c.walk_ok(0, 1, [b"."] * 16) == 16)
    c.clunk(1)
    ok("walk '..' from root stays at root", c.walk_ok(0, 1, [b"..", b"..", b"build"]) == 3)
    c.clunk(1)
    ok("walk with '/' in name fails", c.err(Twalk, struct.pack("<IIH", 0, 1, 1) + s16(b"build/target")) is not None)
    ok("walk with empty name fails", c.err(Twalk, struct.pack("<IIH", 0, 1, 1) + s16(b"")) is not None)
    ok("walk with NUL name fails", c.err(Twalk, struct.pack("<IIH", 0, 1, 1) + s16(b"bui\x00ld")) is not None)
    ok("walk 300-byte name fails", c.err(Twalk, struct.pack("<IIH", 0, 1, 1) + s16(b"a" * 300)) is not None)
    ok("walk 60000-byte name fails", c.err(Twalk, struct.pack("<IIH", 0, 1, 1) + s16(b"a" * 60000)) is not None)
    # partial walk: newfid not bound
    n = c.walk_ok(0, 1, [b"build", b"nope", b"x"])
    ok("partial walk returns 1 qid", n == 1, n)
    ok("partial walk does not bind newfid", c.err(Tclunk, struct.pack("<I", 1)) == E_UNKNOWN_FID)
    # walk through a file
    n = c.walk_ok(0, 1, [b"build", b"target", b"x"])
    ok("walk through a file is partial (2)", n == 2, n)
    ok("newfid unbound after partial walk through file", c.err(Tclunk, struct.pack("<I", 1)) == E_UNKNOWN_FID)
    # walk from a file with nwname>0
    ok("walk to file", c.walk_ok(0, 1, [b"build", b"target"]) == 2)
    ok("walk from file fails 'not a directory'", c.err(Twalk, struct.pack("<IIH", 1, 2, 1) + s16(b"x")) == "not a directory")
    # walk from an open fid
    c.open(1, OREAD)
    ok("walk from open fid with names fails", c.err(Twalk, struct.pack("<IIH", 1, 2, 1) + s16(b"x")) is not None)
    # clone (nwname 0) from open fid with newfid == fid must not silently close the fid
    rt, _, _ = c.walk(1, 1, [])
    rt2, d = c.read(1, 0, 100)
    ok("self-walk nwname=0 on open fid does not lose open state", rt == Rerror or (rt2 == Rread and d), f"{rt} {rt2}")
    c.clunk(1)
    # newfid in use
    c.walk_ok(0, 1, [])
    ok("walk to a fid in use", c.err(Twalk, struct.pack("<IIH", 0, 1, 0)) == E_FID_IN_USE)
    ok("walk from unknown fid", c.err(Twalk, struct.pack("<IIH", 999, 2, 0)) == E_UNKNOWN_FID)
    # attach twice
    ok("attach twice same fid", c.err(Tattach, struct.pack("<II", 0, NOFID) + s16(b"u") + s16(b"")) == E_FID_IN_USE)
    ok("auth is refused", c.err(Tauth, struct.pack("<I", 5) + s16(b"u") + s16(b"")) is not None)
    c.close()
    ok("server healthy after walk attacks", healthy(path))


def attack_io(path):
    print("# open/read/write")
    c = Nine(path)
    ms = c.session()
    c.walk_ok(0, 1, [b"build", b"target"])
    rt, _, _ = c.open(1, OREAD)
    ok("open target", rt == Ropen)
    ok("open twice fails", c.err(Topen, struct.pack("<IB", 1, OREAD)) is not None)
    rt, d = c.read(1, 0, 0xFFFFFFFF)
    ok("read count 2^32-1 clamped", rt == Rread and 0 < len(d) < ms, f"{rt} {len(d) if d else d}")
    rt, d = c.read(1, (1 << 64) - 1, 100)
    ok("read at offset 2^64-1 returns empty", rt == Rread and d == b"", f"{rt} {d!r}")
    rt, d = c.read(1, (1 << 63), 100)
    ok("read at offset 2^63 returns empty", rt == Rread and d == b"")
    ok("write to read-only static file", c.err(Twrite, struct.pack("<IQI", 1, 0, 1) + b"x") is not None)
    c.clunk(1)
    # read on unopened fid
    c.walk_ok(0, 2, [b"README"])
    ok("read on unopened fid", c.err(Tread, struct.pack("<IQI", 2, 0, 10)) == E_BAD_USE)
    ok("write on unopened fid", c.err(Twrite, struct.pack("<IQI", 2, 0, 1) + b"x") == E_BAD_USE)
    ok("read unknown fid", c.err(Tread, struct.pack("<IQI", 555, 0, 10)) == E_UNKNOWN_FID)
    c.clunk(2)
    # directory: write/trunc/write on a dir
    c.walk_ok(0, 3, [b"build"])
    ok("open dir for write is refused by the engine", c.err(Topen, struct.pack("<IB", 3, OWRITE)) == E_PERM)
    ok("open dir with OTRUNC is refused", c.err(Topen, struct.pack("<IB", 3, OREAD | OTRUNC)) is not None)
    rt, _, _ = c.open(3, OREAD)
    ok("write on open dir", c.err(Twrite, struct.pack("<IQI", 3, 0, 1) + b"x") is not None)
    rt, d = c.read(3, 0, 8192)
    ok("read dir", rt == Rread and len(d) > 0)
    ok("read dir at bad offset", c.err(Tread, struct.pack("<IQI", 3, 3, 8192)) == E_BAD_OFFSET)
    ok("read dir at 2^64-1 is bad offset", c.err(Tread, struct.pack("<IQI", 3, (1 << 64) - 1, 8192)) == E_BAD_OFFSET)
    rt, d2 = c.read(3, len(d), 8192)
    ok("read dir at end returns empty", rt == Rread and d2 == b"")
    # read of an open write-only file
    c.clunk(3)
    # dynamic file: second read after short read returns 0; nonzero offset works
    c.walk_ok(0, 4, [b"runtime", b"fn", b"uname"])
    c.open(4, OREAD)
    rt, d = c.read(4, 0, 8192)
    rt2, d2 = c.read(4, len(d), 8192)
    rt3, d3 = c.read(4, 1, 8192)
    ok("dynamic read then read-at-end is empty", rt == Rread and d and rt2 == Rread and d2 == b"")
    ok("dynamic read at offset 1 is the tail", rt3 == Rread and d3 == d[1:], f"{d!r} {d3!r}")
    c.clunk(4)
    # ctl
    c.walk_ok(0, 5, [b"runtime", b"ctl"])
    c.open(5, ORDWR)
    rt, _, _ = c.write(5, 0, b"add 9223372036854775807 1")
    rt2, d = c.read(5, 0, 100)
    ok("ctl add overflow wraps, no trap", rt == Rwrite and rt2 == Rread and d == b"-9223372036854775808", f"{rt} {d!r}")
    ok("ctl fib 94 rejected", c.err(Twrite, struct.pack("<IQI", 5, 0, 6) + b"fib 94") == "bad command")
    rt, _, _ = c.write(5, 0, b"fib 93")
    rt, d = c.read(5, 0, 100)
    ok("ctl fib 93", d == b"12200160415121876738", d)
    rt, st = c.stat(5)
    ok("ctl length is last result length", rt == Rstat and st["length"] == 20, st)
    ok("ctl bad command", c.err(Twrite, struct.pack("<IQI", 5, 0, 4) + b"nope") == "bad command")
    rt, st = c.stat(5)
    ok("ctl length unchanged after error", rt == Rstat and st["length"] == 20, st)
    rt, _, _ = c.write(5, 0, b"sleep-ms 99999999999999999999")
    ok("ctl sleep-ms huge number is a bad command (no trap)", rt == Rerror, rt)
    rt, _, _ = c.write(5, 0, b"echo " + b"\xff" * 1000)
    ok("ctl echo binary", rt == Rwrite)
    rt, _, _ = c.write(5, 0, b"")
    ok("ctl empty write is bad command", rt == Rerror)
    c.clunk(5)
    c.close()
    ok("server healthy after io attacks", healthy(path))


def attack_scratch(path):
    print("# scratch")
    c = Nine(path)
    c.session()
    tag = os.urandom(4).hex().encode()
    root = b"h-" + tag
    c.walk_ok(0, 1, [b"scratch"])
    rt, _, _ = c.create(1, root, DMDIR | 0o755, OREAD)
    ok("mkdir test root", rt == Rcreate, rt)
    c.clunk(1)
    S = [b"scratch", root]

    def fresh(fid, extra=()):
        return c.walk_ok(0, fid, S + list(extra))

    fresh(1)
    ok("create name with '/'", c.err(Tcreate, struct.pack("<I", 1) + s16(b"a/b") + struct.pack("<IB", 0o644, OWRITE)) == E_ILLEGAL_NAME)
    ok("create '.'", c.err(Tcreate, struct.pack("<I", 1) + s16(b".") + struct.pack("<IB", 0o644, OWRITE)) == E_ILLEGAL_NAME)
    ok("create '..'", c.err(Tcreate, struct.pack("<I", 1) + s16(b"..") + struct.pack("<IB", 0o644, OWRITE)) == E_ILLEGAL_NAME)
    ok("create empty name", c.err(Tcreate, struct.pack("<I", 1) + s16(b"") + struct.pack("<IB", 0o644, OWRITE)) == E_ILLEGAL_NAME)
    ok("create NUL name", c.err(Tcreate, struct.pack("<I", 1) + s16(b"a\x00b") + struct.pack("<IB", 0o644, OWRITE)) == E_ILLEGAL_NAME)
    ok("create 256-byte name", c.err(Tcreate, struct.pack("<I", 1) + s16(b"a" * 256) + struct.pack("<IB", 0o644, OWRITE)) == E_ILLEGAL_NAME)
    rt, _, _ = c.create(1, b"b" * 255, 0o644, OWRITE)
    ok("create 255-byte name ok", rt == Rcreate, rt)
    rt, st = c.stat(1)
    ok("stat of 255-byte name round-trips", rt == Rstat and st["name"] == b"b" * 255)
    c.clunk(1)
    fresh(1)
    ok("create over existing name", c.err(Tcreate, struct.pack("<I", 1) + s16(b"b" * 255) + struct.pack("<IB", 0o644, OWRITE)) == "file already exists")
    ok("mkdir over existing file", c.err(Tcreate, struct.pack("<I", 1) + s16(b"b" * 255) + struct.pack("<IB", DMDIR | 0o755, OREAD)) == "file already exists")
    ok("create DMDIR with OWRITE", c.err(Tcreate, struct.pack("<I", 1) + s16(b"dd") + struct.pack("<IB", DMDIR | 0o755, OWRITE)) is not None)
    ok("create DMDIR with OTRUNC", c.err(Tcreate, struct.pack("<I", 1) + s16(b"dd") + struct.pack("<IB", DMDIR | 0o755, OREAD | OTRUNC)) is not None)
    # create in a file
    rt, _, _ = c.create(1, b"f", 0o644, ORDWR)
    ok("create f (fid becomes open file)", rt == Rcreate)
    ok("create inside open fid", c.err(Tcreate, struct.pack("<I", 1) + s16(b"g") + struct.pack("<IB", 0o644, OWRITE)) is not None)
    c.clunk(1)
    fresh(1, [b"f"])
    ok("create inside a file is 'not a directory'", c.err(Tcreate, struct.pack("<I", 1) + s16(b"g") + struct.pack("<IB", 0o644, OWRITE)) == "not a directory")
    # writes: past the cap, at huge offsets
    rt, _, _ = c.open(1, OWRITE)
    ok("write at 64MiB-1 of 2 bytes is no space", c.err(Twrite, struct.pack("<IQI", 1, (64 << 20) - 1, 2) + b"xy") == "no space left on device")
    ok("write at 2^64-1 is no space", c.err(Twrite, struct.pack("<IQI", 1, (1 << 64) - 1, 1) + b"x") == "no space left on device")
    rt, _, _ = c.write(1, (1 << 64) - 1, b"")
    rt2, st = c.stat(1)
    ok("zero-length write at 2^64-1 does not extend the file", rt == Rwrite and st["length"] == 0, f"{rt} {st}")
    rt, _, _ = c.write(1, (64 << 20) - 1, b"x")
    rt2, st = c.stat(1)
    ok("write at 64MiB-1 of 1 byte allowed (file now 64 MiB)", rt == Rwrite and st["length"] == 64 << 20, f"{rt} {st}")
    st = mkstat(length=0)
    rt, _, _ = c.wstat(1, st)
    ok("truncate back to 0", rt == Rwstat)
    ok("wstat length 64MiB+1 is no space", c.err(Twstat, struct.pack("<I", 1) + s16(mkstat(length=(64 << 20) + 1))) == "no space left on device")
    ok("wstat length 2^64-2 is no space", c.err(Twstat, struct.pack("<I", 1) + s16(mkstat(length=(1 << 64) - 2))) == "no space left on device")
    # read on a write-only fid
    ok("read on OWRITE fid", c.err(Tread, struct.pack("<IQI", 1, 0, 10)) == E_BAD_USE)
    c.clunk(1)
    # wstat with name, mode, mtime and length equal to the current values: no-op
    fresh(1, [b"f"])
    rt, st = c.stat(1)
    same = mkstat(name=st["name"], mode=st["mode"], mtime=st["mtime"], length=st["length"])
    rt, _, _ = c.wstat(1, same)
    ok("wstat with name/mode/mtime/length equal to current is ok", rt == Rwstat, rt)
    rt, st2 = c.stat(1)
    ok("stat/wstat round trip fidelity", st2 == st, f"{st}\n{st2}")
    # the engine owns type, dev, qid, atime and the owner names: naming them at all is refused, even unchanged
    full = mkstat(name=st["name"], uid=st["uid"], gid=st["gid"], muid=st["muid"], typ=st["type"], dev=st["dev"],
                  qtype=st["qid"][0], qvers=st["qid"][1], qpath=st["qid"][2], mode=st["mode"], atime=st["atime"],
                  mtime=st["mtime"], length=st["length"])
    ok("wstat naming the engine-owned fields is 'wstat prohibited' even when equal", c.err(Twstat, struct.pack("<I", 1) + s16(full)) == E_WSTAT)
    # wstat changing immutable fields
    ok("wstat changing qid.path", c.err(Twstat, struct.pack("<I", 1) + s16(mkstat(qpath=12345))) == E_WSTAT)
    ok("wstat changing uid", c.err(Twstat, struct.pack("<I", 1) + s16(mkstat(uid=b"root"))) == E_WSTAT)
    ok("wstat DMDIR on a file", c.err(Twstat, struct.pack("<I", 1) + s16(mkstat(mode=DMDIR | 0o755))) == E_WSTAT)
    ok("wstat rename to '.'", c.err(Twstat, struct.pack("<I", 1) + s16(mkstat(name=b"."))) == E_ILLEGAL_NAME)
    ok("wstat rename to '..'", c.err(Twstat, struct.pack("<I", 1) + s16(mkstat(name=b".."))) == E_ILLEGAL_NAME)
    ok("wstat rename to 'a/b'", c.err(Twstat, struct.pack("<I", 1) + s16(mkstat(name=b"a/b"))) == E_ILLEGAL_NAME)
    ok("wstat rename to existing", c.err(Twstat, struct.pack("<I", 1) + s16(mkstat(name=b"b" * 255))) == "file already exists")
    rt, _, _ = c.wstat(1, mkstat(name=b"F"))
    rt2, st = c.stat(1)
    ok("rename differing only by case works", rt == Rwstat and st["name"] == b"F")
    rt, _, _ = c.wstat(1, mkstat(mtime=12345))
    rt2, st = c.stat(1)
    ok("wstat mtime is honoured", rt == Rwstat and st["mtime"] == 12345, st)
    c.clunk(1)
    # remove of root / scratch root / static
    ok("remove of attach root", c.err(Tremove, struct.pack("<I", 0)) == "permission denied")
    ok("fid clunked by failed remove", c.err(Tstat, struct.pack("<I", 0)) == E_UNKNOWN_FID)
    c.attach()
    c.walk_ok(0, 1, [b"scratch"])
    ok("remove of /scratch", c.err(Tremove, struct.pack("<I", 1)) == "permission denied")
    ok("fid clunked by failed remove of /scratch", c.err(Tclunk, struct.pack("<I", 1)) == E_UNKNOWN_FID)
    c.walk_ok(0, 1, [b"build", b"target"])
    ok("remove of static file", c.err(Tremove, struct.pack("<I", 1)) == "permission denied")
    ok("clunk unknown fid", c.err(Tclunk, struct.pack("<I", 1)) == E_UNKNOWN_FID)
    # remove non-empty dir; fid clunked
    fresh(1)
    ok("remove non-empty dir", c.err(Tremove, struct.pack("<I", 1)) == "directory not empty")
    ok("fid clunked after failed remove", c.err(Tclunk, struct.pack("<I", 1)) == E_UNKNOWN_FID)
    # a fid on a removed file: everything but stat/clunk fails cleanly
    fresh(1, [b"F"])
    fresh(2, [b"F"])
    rt, _, _ = c.remove(2)
    ok("remove F", rt == Rremove)
    ok("open removed file", c.err(Topen, struct.pack("<IB", 1, OREAD)) == "file does not exist")
    ok("walk .. from removed file", c.err(Twalk, struct.pack("<IIH", 1, 3, 1) + s16(b"..")) is not None)
    ok("wstat removed file", c.err(Twstat, struct.pack("<I", 1) + s16(mkstat(name=b"G"))) == "file does not exist")
    rt, st = c.stat(1)
    ok("stat removed file still answers", rt == Rstat)
    ok("remove removed file", c.err(Tremove, struct.pack("<I", 1)) == "file does not exist")
    # fid reuse after clunk
    fresh(1)
    c.clunk(1)
    ok("fid reusable after clunk", fresh(1) == 2)
    c.clunk(1)
    # ORCLOSE
    fresh(1)
    rt, _, _ = c.create(1, b"tmp", 0o644, OWRITE | ORCLOSE)
    c.clunk(1)
    ok("ORCLOSE removed the file on clunk", fresh(1, [b"tmp"]) == 2)
    # DMAPPEND ignores offset; OTRUNC on append file is ignored
    fresh(1)
    rt, _, _ = c.create(1, b"log", DMAPPEND | 0o644, OWRITE)
    c.write(1, 500, b"a")
    c.write(1, 0, b"b")
    c.clunk(1)
    fresh(1, [b"log"])
    rt, _, _ = c.open(1, OWRITE | OTRUNC)
    c.write(1, 0, b"c")
    c.clunk(1)
    fresh(1, [b"log"])
    c.open(1, OREAD)
    d = c.read_all(1)
    ok("append-only file", d == b"abc", d)
    rt, st = c.stat(1)
    ok("append qid bit", st["qid"][0] & 0x40 != 0)
    c.clunk(1)
    # DMEXCL: a second open must fail while the first is open
    fresh(1)
    rt, _, _ = c.create(1, b"lock", DMEXCL | 0o644, OWRITE)
    ok("create DMEXCL", rt == Rcreate)
    fresh(2, [b"lock"])
    e = c.err(Topen, struct.pack("<IB", 2, OREAD))
    ok("second open of DMEXCL file is refused while open", e is not None, e)
    c.clunk(1)
    rt, _, _ = c.open(2, OREAD)
    ok("DMEXCL file opens again after the first fid is clunked", rt == Ropen, rt)
    c.clunk(2)
    # mkdir with DMAPPEND|DMEXCL bits, then create inside it
    fresh(1)
    rt, _, _ = c.create(1, b"weird", DMDIR | DMAPPEND | DMEXCL | 0o755, OREAD)
    c.clunk(1)
    fresh(1, [b"weird"])
    rt, _, _ = c.create(1, b"inner", 0o644, OWRITE)
    ok("create inside DMDIR|DMAPPEND|DMEXCL dir works", rt == Rcreate, rt)
    c.clunk(1)
    # directory read across offsets while the directory changes
    fresh(1)
    c.open(1, OREAD)
    rt, d = c.read(1, 0, 8192)
    first = struct.unpack_from("<H", d)[0] + 2
    rt, d = c.read(1, 0, first)  # exactly one record (the engine never splits one)
    fresh(2, [b"weird", b"inner"])
    c.remove(2)
    fresh(2, [b"weird"])
    c.remove(2)
    fresh(2, [b"log"])
    c.remove(2)
    rt2, d2 = c.read(1, len(d), 8192)
    ok("dir read continues after entries were removed (no crash)", rt == Rread and rt2 == Rread)
    rt3, d3 = c.read(1, 0, 8192)
    ok("dir rewind after change lists current entries", rt3 == Rread)
    c.clunk(1)
    # perm inheritance: 0o777 file in 0o755 dir
    fresh(1)
    rt, _, _ = c.create(1, b"px", 0o777, OREAD)
    rt, st = c.stat(1)
    ok("create perm masked by parent (0o777 & 0o755 & 0o666)", st["mode"] == 0o644, oct(st["mode"]))
    c.clunk(1)
    # mode 0 file: open refused; chmod back via wstat
    fresh(1, [b"px"])
    c.wstat(1, mkstat(mode=0))
    ok("open mode-0 file refused", c.err(Topen, struct.pack("<IB", 1, OREAD)) == "permission denied")
    c.wstat(1, mkstat(mode=0o644))
    rt, _, _ = c.open(1, OREAD)
    ok("open after chmod", rt == Ropen)
    c.clunk(1)
    # Tversion mid-session resets fids (retained scratch nodes released)
    fresh(1, [b"px"])
    fresh(2, [b"px"])
    c.remove(2)
    rt, ms, _ = c.version(65536)
    ok("mid-session Tversion", rt == Rversion)
    ok("fids gone after Tversion", c.err(Tstat, struct.pack("<I", 1)) is not None)
    ok("fids gone after Tversion (0)", c.err(Tstat, struct.pack("<I", 0)) == E_UNKNOWN_FID)
    c.attach()
    # cleanup: remove everything under root
    c.walk_ok(0, 1, S)
    c.open(1, OREAD)
    d = c.read_all(1)
    names = []
    while d:
        n, = struct.unpack_from("<H", d)
        names.append(parse_stat(d[:n + 2])["name"])
        d = d[n + 2:]
    c.clunk(1)
    for nm in names:
        if c.walk_ok(0, 1, S + [nm]) == 3:
            c.remove(1)
    c.walk_ok(0, 1, S)
    rt, _, _ = c.remove(1)
    ok("cleanup removed test root", rt == Rremove, names)
    c.close()
    ok("server healthy after scratch attacks", healthy(path))


def attack_many_fids(path):
    print("# many fids")
    c = Nine(path, timeout=30)
    c.session()
    n = 20000
    blob = b"".join(frame(Twalk, i & 0xFFFE, struct.pack("<IIH", 0, i + 1, 0)) for i in range(n))
    got = [0]
    dead = [False]

    def reader():  # a pipelining client must read concurrently or it deadlocks itself on socket buffers
        try:
            for _ in range(n):
                rt, _, _ = c.recv_frame()
                got[0] += rt == Rwalk
        except (EOFError, OSError):
            dead[0] = True

    t = threading.Thread(target=reader)
    t.start()
    t0 = time.time()
    c.raw(blob)
    t.join(60)
    ok("20000 clones answered", got[0] == n and not dead[0] and not t.is_alive(), f"got={got[0]} dead={dead[0]}")
    print(f"      {n} clones in {time.time() - t0:.2f}s")
    rt, _, _ = c.version(65536)
    ok("Tversion after 20000 fids", rt == Rversion)
    c.close()
    ok("server healthy after fid flood", healthy(path))


def attack_connections(path, pid, count=500):
    print(f"# {count} idle connections")
    before = rss_kb(pid)
    socks = []
    try:
        for _ in range(count):
            s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
            s.connect(path)  # blocking connect waits for backlog room instead of failing with EAGAIN
            s.settimeout(5)
            socks.append(s)
    except OSError as e:
        print(f"      connect failed after {len(socks)}: {e!r}")
    time.sleep(1.0)
    mid = rss_kb(pid)
    th = threads(pid)
    print(f"      rss before={before} KiB, with {len(socks)} idle conns={mid} KiB, threads={th}")
    ok(f"{count} idle connections accepted (or refused cleanly), server alive", healthy(path) and len(socks) == count, len(socks))
    # send one Tversion from each (no reply read), then half a frame, then close
    for s in socks:
        try:
            s.sendall(frame(Tversion, NOTAG, struct.pack("<I", 8192) + s16(b"9P2000")) + b"\x10\x00\x00")
        except OSError:
            pass
    for s in socks:
        s.close()
    time.sleep(1.0)
    after = rss_kb(pid)
    print(f"      rss after close={after} KiB, threads={threads(pid)}")
    ok("server alive after mass disconnect", healthy(path))
    ok("thread count returned to baseline (<= 4)", threads(pid) <= 4, threads(pid))
    return before, mid, after


def attack_concurrent(path, clients=8, ops=1000):
    print(f"# {clients} clients x {ops} mixed ops on /scratch")
    errors = []
    tag = os.urandom(3).hex().encode()

    def worker(k):
        try:
            c = Nine(path, timeout=30)
            c.session()
            me = b"c%d-%s" % (k, tag)
            for i in range(ops):
                op = i % 7
                if op == 0:
                    c.walk_ok(0, 1, [b"scratch"])
                    c.create(1, me, 0o644, OWRITE)
                    c.write(1, 0, b"x" * (i % 500))
                    c.clunk(1)
                elif op == 1:
                    if c.walk_ok(0, 1, [b"scratch", me]) == 2:
                        c.open(1, OREAD)
                        c.read_all(1)
                    c.clunk(1)
                elif op == 2:
                    if c.walk_ok(0, 1, [b"scratch", me]) == 2:
                        c.wstat(1, mkstat(name=me + b"-r"))
                    c.clunk(1)
                elif op == 3:
                    if c.walk_ok(0, 1, [b"scratch", me + b"-r"]) == 2:
                        c.wstat(1, mkstat(length=7))
                    c.clunk(1)
                elif op == 4:
                    c.walk_ok(0, 1, [b"scratch"])
                    c.open(1, OREAD)
                    c.read_all(1, 300)
                    c.clunk(1)
                elif op == 5:
                    for nm in (me, me + b"-r"):
                        if c.walk_ok(0, 1, [b"scratch", nm]) == 2:
                            c.remove(1)
                        else:
                            c.clunk(1)
                else:
                    if k % 2 == 0:
                        c.version(65536)
                        c.attach()
                    else:
                        c.walk_ok(0, 1, [b"runtime", b"ctl"])
                        c.open(1, ORDWR)
                        c.write(1, 0, b"add %d 1" % i)
                        c.read(1, 0, 100)
                        c.clunk(1)
            for nm in (me, me + b"-r"):
                if c.walk_ok(0, 1, [b"scratch", nm]) == 2:
                    c.remove(1)
                else:
                    c.clunk(1)
            c.close()
        except Exception as e:  # noqa: BLE001
            errors.append((k, repr(e)))

    ts = [threading.Thread(target=worker, args=(k,)) for k in range(clients)]
    t0 = time.time()
    for t in ts:
        t.start()
    for t in ts:
        t.join(120)
    ok("concurrent clients finished without errors", not errors and all(not t.is_alive() for t in ts), errors)
    print(f"      {clients * ops} ops in {time.time() - t0:.1f}s")
    ok("server healthy after concurrency", healthy(path))


def attack_sleep(path):
    print("# sleep-ms must not block other clients")
    a = Nine(path, timeout=10)
    a.session()
    a.walk_ok(0, 1, [b"runtime", b"ctl"])
    a.open(1, OWRITE)
    a.raw(frame(Twrite, 3, struct.pack("<IQI", 1, 0, 13) + b"sleep-ms 3000"))
    t0 = time.time()
    b = Nine(path, timeout=10)
    b.session()
    d = b.path_read([b"build", b"zig_version"])
    dt = time.time() - t0
    ok("other client served during sleep-ms", bool(d) and dt < 1.0, f"{dt:.2f}s")
    rt, _, _ = a.recv_frame()
    ok("sleeper got Rwrite", rt == Rwrite)
    a.close()
    b.close()


def attack_env(path):
    print("# runtime files")
    c = Nine(path)
    c.session()
    env = c.path_read([b"runtime", b"env"])
    ok("/runtime/env readable", env is not None)
    if env and any(k in env for k in (b"TOKEN", b"SECRET", b"KEY", b"PASS")):
        print("      note: /runtime/env exposes variables that look like secrets")
    for nm in (b"pid", b"ppid", b"uptime", b"argv", b"cwd", b"clients"):
        d = c.path_read([b"runtime", nm])
        ok(f"/runtime/{nm.decode()} readable", d is not None, d)
    for nm in (b"hostname", b"now", b"random", b"uname", b"fib30"):
        d = c.path_read([b"runtime", b"fn", nm])
        ok(f"/runtime/fn/{nm.decode()} readable and non-empty", bool(d), d)
    # random gives different values on each open
    r1 = c.path_read([b"runtime", b"fn", b"random"])
    r2 = c.path_read([b"runtime", b"fn", b"random"])
    ok("random differs across opens", r1 != r2)
    # stat of dynamic file reports 0, static reports real length
    c.walk_ok(0, 1, [b"runtime", b"pid"])
    rt, st = c.stat(1)
    ok("dynamic file length 0", st["length"] == 0 and st["mode"] == 0o444, st)
    c.clunk(1)
    c.walk_ok(0, 1, [b"README"])
    rt, st = c.stat(1)
    d = c.path_read([b"README"])
    ok("static file length matches content", st["length"] == len(d), (st["length"], len(d)))
    # every directory in the static tree: names in listing match walkable names, '.' and '..' absent
    def walk_tree(names, depth=0):
        if depth > 6:
            return
        if c.walk_ok(0, 9, names) != len(names):
            ok("walk " + b"/".join(names).decode(), False)
            return
        rt, st = c.stat(9)
        if st["mode"] & DMDIR:
            c.open(9, OREAD)
            d = c.read_all(9, 512)
            c.clunk(9)
            while d:
                n, = struct.unpack_from("<H", d)
                e = parse_stat(d[:n + 2])
                d = d[n + 2:]
                if e["name"] in (b".", b"..", b""):
                    ok("dir listing has no '.'/'..'/empty names", False, names)
                if names == [b"scratch"]:
                    continue
                walk_tree(names + [e["name"]], depth + 1)
        else:
            c.clunk(9)
    walk_tree([])
    ok("entire static tree walkable", True)
    c.close()


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--server")
    ap.add_argument("--socket")
    ap.add_argument("--connections", type=int, default=500)
    ap.add_argument("--fast", action="store_true")
    args = ap.parse_args()
    proc = None
    tmp = None
    if args.server:
        tmp = tempfile.mkdtemp(prefix="adv9p.")
        path = os.path.join(tmp, "sock")
        proc = subprocess.Popen([os.path.abspath(args.server), "--unix", path], stderr=subprocess.PIPE)
        for _ in range(200):
            if os.path.exists(path):
                break
            time.sleep(0.02)
        pid = proc.pid
    elif args.socket:
        path = args.socket
        pid = -1
    else:
        ap.error("--server or --socket")
    try:
        rss0 = rss_kb(pid)
        attack_framing(path)
        attack_tags(path)
        attack_walk(path)
        attack_io(path)
        attack_scratch(path)
        attack_env(path)
        attack_sleep(path)
        attack_many_fids(path)
        if not args.fast:
            attack_connections(path, pid, args.connections)
            attack_concurrent(path)
        rss1 = rss_kb(pid)
        print(f"# rss start={rss0} KiB end={rss1} KiB threads={threads(pid)}")
        if pid > 0:
            ok("server process still running", proc.poll() is None, proc.poll())
    finally:
        if proc is not None:
            proc.send_signal(signal.SIGTERM)
            try:
                _, err = proc.communicate(timeout=5)
            except subprocess.TimeoutExpired:
                proc.kill()
                _, err = proc.communicate()
            lines = [ln for ln in err.decode("utf-8", "replace").splitlines() if "connection ended" not in ln and "read: " not in ln]
            if lines:
                print("# server stderr (filtered):")
                for ln in lines[:40]:
                    print("      " + ln)
            if tmp:
                try:
                    os.unlink(path)
                    os.rmdir(tmp)
                except OSError:
                    pass
    print(f"# {PASSES} passed, {len(FAILS)} failed")
    for f in FAILS:
        print("#   FAIL " + f)
    sys.exit(1 if FAILS else 0)


if __name__ == "__main__":
    main()