Files
codex-app-server/chv-guest/chv-broker.py
T
host 0203f32627 part 5 修复 3:P2-9 degraded_logged=False——降级日志文案漂移
定位结论(已定位,不是时序、不是日志路径变化):part 4 提交
7a22732 把 serve() 从 peer_allowed 切到 peer_allowed_multi 时,
降级分支的 reason 与警告行都被改写成了“无 cell pid 文件”,
“cell.pid 缺失”这个串自此再也没进过 journal——P2-9 驱动
grep 'cell.pid 缺失' 自然命中不了,RETEST4 的
degraded_logged=False 即由此来。RETEST3 同项为 True,是因为
当时跑的还是 part 4 之前的 broker(serve 直接打印含该串的
警告行)。降级 ping 本身一直 ok=True,降级逻辑没坏,坏的是
日志里的认领字符串。

修复:peer_allowed_multi 无 pid 文件时的 reason 改回与单 cell
版 peer_allowed 完全一致的“uid 在范围内(cell.pid 缺失,未做
pid ns 对照)”;serve() 的警告行改走新 helper
_degraded_warning(reason, pid, uid),把 reason 原样打进日志
(不再手写第二份文案,避免两者再次悄悄漂移;今后改文案只改
reason 一处)。journalctl grep 'cell.pid 缺失' 恢复命中。

新测试 cloud/tests/test_chv_muse_p2.py::BrokerMultiTest(2 项):
reason 含“cell.pid 缺失”、警告行含该串且带 pid/uid。
2026-11-07 12:07:32 +00:00

337 lines
13 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
"""chv-broker:单元外 IPC broker(客机侧、单元外服务)。
对齐 Muse P2(见 docs/chv-muse-p2-gap.md):单元内外走 Unix socket +
SO_PEERCRED 的最小权限 IPC。broker 只认白名单操作,凭证与浏览器
都在单元外——单元看不见 token,只能请 broker 代办。
校验(双重,缺一不可才放行;无 cell pid 文件时只做 uid 检查并打日志):
1. SO_PEERCRED 的 uid 须在单元映射范围 [1000, 1000+65536) 内;
2. 对端 pid 的 pid ns 须与任一活着的单元 init 同 ns(part 4:
并发 cell 各有 cell-<machine>.pid,旧的单文件 cell.pid 只记
最新单元;读不到任何 pid 文件时跳过第 2 项并警告;有 pid 文
件但对端 ns 与任一可读的单元 ns 都对不上时拒绝,不降级)。
操作白名单:
ping -> {"ok": true}
sync {action: pull|push|status, repo?} -> 单元外以 chv 身份跑
chv-sync(list argv,不进 shell;仓目录只允许
~/workspace 下,realpath + commonpath 校验)。
browser {…} -> 原样转发给 chv-browser.sock(浏览器子代理),
回包原样返回;浏览器服务不在时报错,不替它跑 playwright。
只用标准库。单连接一请求一响应(JSON 行,≤64KB);异常只断本
连接,绝不杀死 broker 循环。
"""
import glob
import grp
import json
import os
import socket
import struct
import subprocess
import sys
BROKER_SOCK = "/run/chv/broker.sock"
# round-11 真机修复(缺陷 4):browser.sock 从 /run/chv 移到
# chv-browser 自有目录——/run/chv 是 0755 root root,
# chv-browser 在 bind 时 EACCES 而无限 crash loop(restart 21);
# 放进组可写的 /run/chv 会给 chv-browser 对 broker.sock/cell.pid
# 的 unlink 能力,所以用独立目录(0755 chv-browser 所有)。
BROWSER_SOCK = "/run/chv-browser/browser.sock"
CELL_PID_FILE = "/run/chv/cell.pid"
CELL_PID_GLOB = "/run/chv/cell-*.pid"
UID_BASE = 1000
UID_COUNT = 65536
WORKSPACE = "/home/chv/workspace"
SYNC_USER = "chv"
SYNC_BIN = "/usr/local/bin/chv-sync"
MAX_REQUEST_BYTES = 65536
MAX_OUTPUT_BYTES = 8192
SYNC_ACTIONS = ("pull", "push", "status")
def _read_ns_link(pid, proc_root="/proc"):
"""读 /proc/<pid>/ns/pid 的链接目标;读不到返回 None。"""
try:
return os.readlink(os.path.join(proc_root, str(pid), "ns", "pid"))
except OSError:
return None
def peer_allowed(peer_uid, peer_pid, cell_pid=None, proc_root="/proc"):
"""对端是否允许用 broker。返回 (allowed, reason)。
cell_pid 为 None 时只做 uid 检查(broker 打日志警告,调用方负责)。"""
if not (UID_BASE <= peer_uid < UID_BASE + UID_COUNT):
return False, "uid %d 不在单元映射范围 [%d, %d)" % (
peer_uid, UID_BASE, UID_BASE + UID_COUNT)
if cell_pid is None:
return True, "uid 在范围内(cell.pid 缺失,未做 pid ns 对照)"
cell_ns = _read_ns_link(cell_pid, proc_root)
if cell_ns is None:
return False, "cell.pid 的 pid ns 读不到,拒绝(不降级)"
peer_ns = _read_ns_link(peer_pid, proc_root)
if peer_ns is None:
return False, "对端 pid ns 读不到,拒绝"
if peer_ns != cell_ns:
return False, "对端 pid ns 与单元不一致"
return True, "ok"
def peer_allowed_multi(peer_uid, peer_pid, cell_pids, proc_root="/proc"):
"""多 cell 版:对端 pid ns 与任一活 cell 的 init 同 ns 即放行
(part 4 并发 cell 用;单 cell 时与 peer_allowed 等价)。
cell_pids 为空即只做 uid 检查;全部 pid 的 ns 都读不到时
拒绝(不降级);个别 pid 的 ns 读不到(已退出的残留文件)
只跳过该项,不因此拒绝整个请求。"""
if not (UID_BASE <= peer_uid < UID_BASE + UID_COUNT):
return False, "uid %d 不在单元映射范围 [%d, %d)" % (
peer_uid, UID_BASE, UID_BASE + UID_COUNT)
if not cell_pids:
# part 5:reason 文案与单 cell 版 peer_allowed 对齐,保留
# “cell.pid 缺失”字样——P2-9 驱动 grep 该串认降级日志;
# part 4 切到 multi 版时把这里改写成“无 cell pid 文件”,
# 该串自此再也没进过 journal,是 RETEST4
# degraded_logged=False 的根因(不是时序、不是日志路径)。
return True, "uid 在范围内(cell.pid 缺失,未做 pid ns 对照)"
peer_ns = _read_ns_link(peer_pid, proc_root)
if peer_ns is None:
return False, "对端 pid ns 读不到,拒绝"
readable = 0
for cell_pid in cell_pids:
cell_ns = _read_ns_link(cell_pid, proc_root)
if cell_ns is None:
continue
readable += 1
if peer_ns == cell_ns:
return True, "ok"
if readable == 0:
return False, "cell pid 的 pid ns 均读不到,拒绝(不降级)"
return False, "对端 pid ns 与任何单元不一致"
def _read_cell_pid():
try:
with open(CELL_PID_FILE) as fh:
return int(fh.read().strip())
except (OSError, ValueError):
return None
def _read_cell_pids(cell_dir="/run/chv"):
"""读全部 cell pid:每单元一份 cell-<machine>.pid + 兼容旧
路径 cell.pid(最新单元)。去重、跳过坏内容,返回 int 列表。"""
pids = []
paths = sorted(glob.glob(os.path.join(cell_dir, "cell-*.pid")))
paths.append(os.path.join(cell_dir, "cell.pid"))
for path in paths:
try:
with open(path) as fh:
pid = int(fh.read().strip())
except (OSError, ValueError):
continue
if pid not in pids:
pids.append(pid)
return pids
def _degraded_warning(reason, pid, uid):
"""降级警告行:reason 原样进日志。serve() 在无 cell pid 文件
时打这条;P2-9 驱动 grep 'cell.pid 缺失' 认的就是它(part 5:
part 4 之前 serve 直接打印含该串的警告行,RETEST3 同项为
True;part 4 切到 peer_allowed_multi 后警告行改写成
“无 cell pid 文件”,该串再也没进过 journal——RETEST4 的
degraded_logged=False 即由此来,不是时序、不是日志路径
变化。reason 与警告行分开写曾让两者悄悄漂移,今后改文案
只改 peer_allowed_multi 的 reason,警告行自动跟随)。"""
return ("chv-broker: 警告:%s (pid=%d uid=%d)"
% (reason, pid, uid))
def _resolve_repo(repo):
"""仓目录只允许 ~/workspace 下。repo 为空时返回 None(由
chv-sync 自己取唯一仓)。返回解析后的绝对路径或抛 ValueError。"""
if not repo:
return None
base = os.path.realpath(WORKSPACE)
target = os.path.realpath(repo)
if os.path.commonpath([base, target]) != base or target == base:
raise ValueError("仓目录只允许 %s 下:%s" % (WORKSPACE, repo))
return target
def _truncate(text, limit=MAX_OUTPUT_BYTES):
if text is None:
return ""
if len(text) > limit:
return text[:limit] + "\n…(已截断)"
return text
def _run_sync(action, repo):
if action not in SYNC_ACTIONS:
return {"ok": False,
"error": "sync action 只允许 %s:%s"
% ("/".join(SYNC_ACTIONS), action)}
try:
repo_path = _resolve_repo(repo)
except ValueError as e:
return {"ok": False, "error": str(e)}
cmd = ["runuser", "-u", SYNC_USER, "--", "env", "HOME=/home/chv",
SYNC_BIN, action]
if repo_path:
cmd.append(repo_path)
try:
proc = subprocess.run(cmd, capture_output=True, text=True,
timeout=300)
except subprocess.TimeoutExpired:
return {"ok": False, "error": "chv-sync 超时(300 秒)"}
except OSError as e:
return {"ok": False, "error": "chv-sync 起不来:%s" % e}
return {"ok": proc.returncode == 0,
"stdout": _truncate(proc.stdout),
"stderr": _truncate(proc.stderr),
"returncode": proc.returncode}
def _forward_browser(req, sock_path=BROWSER_SOCK, timeout=120):
"""转发给浏览器子代理;回包须是带 ok 的 dict,否则报错。"""
try:
conn = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
conn.settimeout(timeout)
conn.connect(sock_path)
except OSError as e:
return {"ok": False,
"error": "浏览器子代理未就绪:%s" % e}
try:
conn.sendall((json.dumps(req, ensure_ascii=False) + "\n").encode())
data = b""
while len(data) < MAX_REQUEST_BYTES:
chunk = conn.recv(4096)
if not chunk:
break
data += chunk
if data.endswith(b"\n"):
break
except OSError as e:
return {"ok": False, "error": "浏览器子代理通信失败:%s" % e}
finally:
conn.close()
try:
resp = json.loads(data.decode())
except (ValueError, UnicodeDecodeError):
return {"ok": False, "error": "浏览器子代理回包不是 JSON"}
if not isinstance(resp, dict) or "ok" not in resp:
return {"ok": False, "error": "浏览器子代理回包格式不对"}
return resp
def handle_request(req, browser_sock=BROWSER_SOCK):
"""处理一个请求 dict,返回响应 dict(纯逻辑,可单测)。"""
if not isinstance(req, dict):
return {"ok": False, "error": "请求须是 JSON 对象"}
op = req.get("op")
if op == "ping":
return {"ok": True, "cell": True}
if op == "sync":
return _run_sync(req.get("action"), req.get("repo"))
if op == "browser":
return _forward_browser(req, sock_path=browser_sock)
return {"ok": False, "error": "未知操作:%r(白名单:ping/sync/browser)"
% (op,)}
def _peer_creds(conn):
"""SO_PEERCRED:返回 (pid, uid, gid)。Linux struct ucred = 3 个 int。"""
raw = conn.getsockopt(socket.SOL_SOCKET, socket.SO_PEERCRED,
struct.calcsize("3i"))
pid, uid, gid = struct.unpack("3i", raw)
return pid, uid, gid
def serve(sock_path=BROKER_SOCK, browser_sock=BROWSER_SOCK):
"""监听 Unix socket,逐连接处理。返回码 0 只能是被信号杀死;
socket 建不起来即抛错(systemd 会重启服务,不要静默带病跑)。"""
if os.path.exists(sock_path):
os.remove(sock_path)
os.makedirs(os.path.dirname(sock_path), exist_ok=True)
srv = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
srv.bind(sock_path)
srv.listen(16)
# 0660 + 组 chv:单元内 root 在客机侧是 uid 1000(chv),
# 组 chv 可连;其它用户连不上(再叠加 SO_PEERCRED 校验)。
os.chmod(sock_path, 0o660)
try:
gid = grp.getgrnam("chv").gr_gid
except KeyError:
print("chv-broker: 组 chv 不存在,socket 权限置不全,拒绝启动",
file=sys.stderr)
raise SystemExit(1)
os.chown(sock_path, -1, gid)
print("chv-broker: 监听 %s" % sock_path, file=sys.stderr, flush=True)
while True:
try:
conn, _ = srv.accept()
except OSError:
continue
try:
pid, uid, _gid = _peer_creds(conn)
cell_pids = _read_cell_pids()
allowed, reason = peer_allowed_multi(uid, pid, cell_pids)
if not allowed:
print("chv-broker: 拒绝连接 pid=%d uid=%d:%s"
% (pid, uid, reason), file=sys.stderr, flush=True)
conn.close()
continue
if not cell_pids:
print(_degraded_warning(reason, pid, uid),
file=sys.stderr, flush=True)
conn.settimeout(310)
data = b""
while len(data) < MAX_REQUEST_BYTES:
chunk = conn.recv(4096)
if not chunk:
break
data += chunk
if data.endswith(b"\n"):
break
try:
req = json.loads(data.decode())
except (ValueError, UnicodeDecodeError):
resp = {"ok": False, "error": "请求不是合法 JSON"}
else:
resp = handle_request(req, browser_sock=browser_sock)
conn.sendall((json.dumps(resp, ensure_ascii=False)
+ "\n").encode())
except OSError as e:
print("chv-broker: 连接处理异常:%s" % e, file=sys.stderr,
flush=True)
finally:
try:
conn.close()
except OSError:
pass
def main(argv):
sock_path = BROKER_SOCK
browser_sock = BROWSER_SOCK
i = 0
while i < len(argv):
if argv[i] == "--socket" and i + 1 < len(argv):
sock_path = argv[i + 1]
i += 2
elif argv[i] == "--browser-socket" and i + 1 < len(argv):
browser_sock = argv[i + 1]
i += 2
else:
print("chv-broker: 未知参数:%s" % argv[i], file=sys.stderr)
return 2
serve(sock_path, browser_sock)
return 0
if __name__ == "__main__":
raise SystemExit(main(sys.argv[1:]))