feat(chv-guest): 对齐 Muse P2——nspawn 单元 + broker + 浏览器子代理
- chv-cell:systemd-nspawn 单命令单元,--private-users=1000:65536 (单元 root → 客机 chv),丢 8 项能力(含 SYS_PTRACE/NET_ADMIN), syscall 过滤扣 io_uring,遮蔽 /etc/chv 与 playwright, --network-veth(10.200.0.0/24 + NAT),白名单环境透传 - chv-broker:Unix socket + SO_PEERCRED(uid 范围 + pid ns 对照), 白名单 ping/sync/browser;sync 只调 chv-sync(runuser -u chv) - chv-browser:单元外独立进程,只暴露 open/snapshot/screenshot/ close/ping,返回无障碍树快照(截断);evaluate/content 拒绝 - build.sh:装 systemd-container/iproute2/iptables,拷入三脚本, 建 chv-browser 用户与两个 systemd 单元;vsock_notify 条件拷入 - buildinfo:内容项加 P2 四项,支持可选 extra_contents - 测试:cloud/tests/test_chv_muse_p2.py 40 项全过;broker/browser 真实 socket 回路冒烟通过(root 连 broker 被拒) - 差距表:docs/chv-muse-p2-gap.md;真机验证待测试机空闲(round 11) 本地做,不推、不合、不部署
This commit is contained in:
1 parent
06c3e172fe
commit
c61484aa68
8 files changed
+1826
-9
No files matched your search
+38
-4
@@ -26,6 +26,12 @@
|
||||
# 失败关闭(不 --force、不自动 rebase)。token 绝不进镜像、
|
||||
# 代码、日志。
|
||||
#
|
||||
# 对齐 Muse P2(2026-11-07):镜像里加 systemd-nspawn 运行时单元
|
||||
#(chv-cell:codex 跑在单元内)+ 单元外 broker(chv-broker:
|
||||
#Unix socket + SO_PEERCRED 白名单代办)+ 浏览器子代理(chv-browser:
|
||||
#单元外独立进程,只返回无障碍树快照)。boot clone 仍在单元外做;
|
||||
#单元隔离口径见 docs/chv-muse-p2-gap.md。
|
||||
#
|
||||
# 用法(必须在带 /dev/kvm 的宿主上跑全量模式):
|
||||
# CODEX_BIN_DIR=bin UBUNTU_VERSION=24.04 CODEX_VERSION=0.164.0-alpha.9 \
|
||||
# REPO_COMMIT=$(git rev-parse --short HEAD) \
|
||||
@@ -166,6 +172,13 @@ if [ ! -f "$SCRIPT_DIR/chv-sync.sh" ]; then
|
||||
echo "缺少 chv-sync.sh(Gitea 双向同步脚本):$SCRIPT_DIR" >&2
|
||||
exit 1
|
||||
fi
|
||||
# 对齐 Muse P2:单元启动器 / broker / 浏览器子代理三脚本缺一即失败。
|
||||
for p2_script in chv-cell.py chv-broker.py chv-browser.py; do
|
||||
if [ ! -f "$SCRIPT_DIR/$p2_script" ]; then
|
||||
echo "缺少 $p2_script(Muse P2 客机脚本):$SCRIPT_DIR" >&2
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
if [ "$DRY_RUN" = "0" ]; then
|
||||
if [ ! -e /dev/kvm ]; then
|
||||
echo "CHV_GUEST_BUILD needs a KVM host: /dev/kvm 不存在" >&2
|
||||
@@ -249,7 +262,7 @@ run qemu-img convert -f qcow2 -O raw "$IMG" "$OUT/disk.raw"
|
||||
# 写进 /app/guest-versions-chromium.txt)。
|
||||
GT_INSTALL_CMD="curl -fsSL -o /tmp/gt-install.sh https://gitea.com/gitea/cli/raw/branch/main/scripts/install.sh && echo \"${GT_INSTALL_SH_SHA256} /tmp/gt-install.sh\" | sha256sum -c - && GITEA_CLI_VERSION=${GT_VERSION} GITEA_CLI_INSTALL_DIR=/usr/local/bin sh /tmp/gt-install.sh && rm -f /tmp/gt-install.sh && /usr/local/bin/gt version"
|
||||
VC_ARGS=(-a "$OUT/disk.raw"
|
||||
--run-command 'apt-get update -qq && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends git openssh-server openssh-client cloud-init python3 python3-pip curl ca-certificates xz-utils fonts-wqy-microhei fontconfig && apt-get clean'
|
||||
--run-command 'apt-get update -qq && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends git openssh-server openssh-client cloud-init python3 python3-pip curl ca-certificates xz-utils fonts-wqy-microhei fontconfig systemd-container iproute2 iptables && apt-get clean'
|
||||
--copy-in "$CODEX_BIN_DIR/codex:/usr/local/bin/"
|
||||
--copy-in "$CODEX_BIN_DIR/codex-code-mode-host:/usr/local/bin/"
|
||||
--copy-in "$CODEX_BIN_DIR/codex-resources:/usr/local/bin/"
|
||||
@@ -258,13 +271,32 @@ VC_ARGS=(-a "$OUT/disk.raw"
|
||||
--copy-in "$REPO_DIR/host.py:/app/"
|
||||
--copy-in "$SCRIPT_DIR/chv-sync.sh:/usr/local/bin/"
|
||||
--run-command 'mv /usr/local/bin/chv-sync.sh /usr/local/bin/chv-sync && chmod +x /usr/local/bin/chv-sync'
|
||||
--copy-in "$SCRIPT_DIR/chv-cell.py:/usr/local/bin/"
|
||||
--copy-in "$SCRIPT_DIR/chv-broker.py:/usr/local/bin/"
|
||||
--copy-in "$SCRIPT_DIR/chv-browser.py:/usr/local/bin/"
|
||||
--run-command 'mv /usr/local/bin/chv-cell.py /usr/local/bin/chv-cell && mv /usr/local/bin/chv-broker.py /usr/local/bin/chv-broker && mv /usr/local/bin/chv-browser.py /usr/local/bin/chv-browser && chmod +x /usr/local/bin/chv-cell /usr/local/bin/chv-broker /usr/local/bin/chv-browser'
|
||||
--run-command 'printf "runcmd:\n - systemctl restart ssh || service ssh restart || true\n - /usr/local/bin/chv-sync boot >>/var/log/chv-sync.log 2>&1 || true\n" > /etc/cloud/cloud.cfg.d/99-chv-sync.cfg'
|
||||
--run-command 'git config --system user.name chv && git config --system user.email chv@localhost && git config --system credential.helper store && git config --system init.defaultBranch main'
|
||||
--run-command "$GT_INSTALL_CMD"
|
||||
--run-command '/usr/local/bin/gt version > /app/guest-versions-gt.txt'
|
||||
--run-command 'printf "ssh_deletekeys: false\nbootcmd:\n - \"[ -f /etc/ssh/ssh_host_ed25519_key ] || ssh-keygen -A\"\n" > /etc/cloud/cloud.cfg.d/99-chv-hostkey.cfg; systemctl enable ssh || true'
|
||||
--run-command 'printf "PasswordAuthentication no\nPermitRootLogin prohibit-password\nChallengeResponseAuthentication no\nKbdInteractiveAuthentication no\nPubkeyAuthentication yes\n" > /etc/ssh/sshd_config.d/99-chv.conf && mkdir -p /run/sshd && ssh-keygen -A && sshd -t && grep -q "^PasswordAuthentication no" /etc/ssh/sshd_config.d/99-chv.conf && grep -q "^PermitRootLogin prohibit-password" /etc/ssh/sshd_config.d/99-chv.conf && rm -f /etc/ssh/ssh_host_* && test -z "$(ls /etc/ssh/ssh_host_* 2>/dev/null)"'
|
||||
--run-command 'dpkg-query -W -f "\${Package} \${Version}\n" > /app/guest-versions-dpkg.txt; pip3 freeze > /app/guest-versions-pip.txt || true')
|
||||
--run-command 'dpkg-query -W -f "\${Package} \${Version}\n" > /app/guest-versions-dpkg.txt; pip3 freeze > /app/guest-versions-pip.txt || true'
|
||||
--run-command 'useradd --system --home-dir /var/lib/chv-browser --shell /usr/sbin/nologin chv-browser && mkdir -p /var/lib/chv-browser /run/chv/shots && chown chv-browser:chv-browser /var/lib/chv-browser /run/chv/shots && chmod 0755 /run/chv /run/chv/shots'
|
||||
--run-command 'printf "[Unit]\nDescription=CHV cell broker (Muse P2)\nAfter=network.target\n\n[Service]\nType=simple\nExecStart=/usr/bin/python3 /usr/local/bin/chv-broker\nRestart=on-failure\nRestartSec=2\n\n[Install]\nWantedBy=multi-user.target\n" > /etc/systemd/system/chv-broker.service'
|
||||
--run-command 'printf "[Unit]\nDescription=CHV browser sub-agent (Muse P2)\nAfter=network.target\n\n[Service]\nType=simple\nUser=chv-browser\nGroup=chv-browser\nExecStart=/usr/bin/python3 /usr/local/bin/chv-browser\nRestart=on-failure\nRestartSec=2\n\n[Install]\nWantedBy=multi-user.target\n" > /etc/systemd/system/chv-browser.service'
|
||||
--run-command 'printf "d /run/chv 0755 root root -\nd /run/chv/shots 0755 chv-browser chv-browser -\n" > /etc/tmpfiles.d/chv.conf && systemctl enable chv-broker chv-browser || true')
|
||||
# P1 交接(Muse P1 的 vsock_notify.py):文件在仓库里存在时拷入
|
||||
# 镜像(P1 分支才有,本分支尚无);不存在时只警告、不失败——
|
||||
# 合并后自动生效,P2 不改该脚本内容。
|
||||
VSOCK_NOTIFY_PRESENT=0
|
||||
if [ -f "$REPO_DIR/cloud/chv/guest/vsock_notify.py" ]; then
|
||||
VC_ARGS+=(--copy-in "$REPO_DIR/cloud/chv/guest/vsock_notify.py:/usr/local/bin/"
|
||||
--run-command 'mv /usr/local/bin/vsock_notify.py /usr/local/bin/vsock-notify && chmod +x /usr/local/bin/vsock-notify')
|
||||
VSOCK_NOTIFY_PRESENT=1
|
||||
else
|
||||
echo "警告:cloud/chv/guest/vsock_notify.py 不在仓库里(P1 未合并),镜像暂不含 vsock notify" >&2
|
||||
fi
|
||||
if [ "${PLAYWRIGHT:-1}" = "1" ]; then
|
||||
VC_ARGS+=(
|
||||
--run-command '(pip3 install --no-cache-dir --break-system-packages playwright || pip3 install --no-cache-dir playwright) && PLAYWRIGHT_BROWSERS_PATH=/usr/local/share/ms-playwright python3 -m playwright install --with-deps chromium-headless-shell'
|
||||
@@ -316,14 +348,16 @@ fi
|
||||
# 产物校验(干跑只打印,不执行校验命令的副作用部分)。
|
||||
if [ "$DRY_RUN" = "1" ]; then
|
||||
echo "DRY-RUN: test -s $OUT/vmlinux && test -s $OUT/disk.raw"
|
||||
echo "DRY-RUN: python3 $SCRIPT_DIR/buildinfo.py $OUT $TAG $UBUNTU_VERSION $CODEX_VERSION $REPO_COMMIT <sha256> ${PLAYWRIGHT:-1} ${CHROMIUM_HEADLESS_SHELL_REV:-} # 生成 $OUT/BUILDINFO.json 并校验 tag=$TAG"
|
||||
echo "DRY-RUN: python3 $SCRIPT_DIR/buildinfo.py $OUT $TAG $UBUNTU_VERSION $CODEX_VERSION $REPO_COMMIT <sha256> ${PLAYWRIGHT:-1} ${CHROMIUM_HEADLESS_SHELL_REV:-} [vsock_notify?] # 生成 $OUT/BUILDINFO.json 并校验 tag=$TAG"
|
||||
else
|
||||
test -s "$OUT/vmlinux" || { echo "内核产物为空:$OUT/vmlinux" >&2; exit 1; }
|
||||
test -s "$OUT/disk.raw" || { echo "磁盘产物为空:$OUT/disk.raw" >&2; exit 1; }
|
||||
if [ "${PLAYWRIGHT:-1}" = "1" ] && [ -z "$CHROMIUM_HEADLESS_SHELL_REV" ]; then
|
||||
echo "警告:CHROMIUM_HEADLESS_SHELL_REV 未设,Chromium 版本只记录、不钉死(V-9 验收须设该变量重建)" >&2
|
||||
fi
|
||||
python3 "$SCRIPT_DIR/buildinfo.py" "$OUT" "$TAG" "$UBUNTU_VERSION" "$CODEX_VERSION" "$REPO_COMMIT" "$UBUNTU_IMAGE_SHA256" "${PLAYWRIGHT:-1}" "${CHROMIUM_HEADLESS_SHELL_REV:-}"
|
||||
EXTRA_CONTENTS=""
|
||||
[ "$VSOCK_NOTIFY_PRESENT" = "1" ] && EXTRA_CONTENTS="vsock_notify"
|
||||
python3 "$SCRIPT_DIR/buildinfo.py" "$OUT" "$TAG" "$UBUNTU_VERSION" "$CODEX_VERSION" "$REPO_COMMIT" "$UBUNTU_IMAGE_SHA256" "${PLAYWRIGHT:-1}" "${CHROMIUM_HEADLESS_SHELL_REV:-}" "$EXTRA_CONTENTS"
|
||||
fi
|
||||
echo "tag=$TAG"
|
||||
echo "out=$OUT"
|
||||
|
||||
+17
-5
@@ -37,6 +37,8 @@ BASE_CONTENTS = [
|
||||
"xz-utils", "fonts-wqy-microhei", "fontconfig", "codex",
|
||||
"codex-code-mode-host", "codex-resources/bwrap",
|
||||
"/app/host.py", "gt", "chv-sync",
|
||||
# 对齐 Muse P2:nspawn 单元启动器 + broker + 浏览器子代理。
|
||||
"systemd-container", "chv-cell", "chv-broker", "chv-browser",
|
||||
]
|
||||
|
||||
# 执行器默认内核 cmdline(config.py),构建产物须与它一起记录(B-12),
|
||||
@@ -67,12 +69,18 @@ def _sha256_size(path):
|
||||
|
||||
|
||||
def build(outdir, tag, ubuntu, codex_version, repo_commit,
|
||||
ubuntu_image_sha256, playwright, chromium_pinned_rev=None):
|
||||
ubuntu_image_sha256, playwright, chromium_pinned_rev=None,
|
||||
extra_contents=None):
|
||||
disk_path = os.path.join(outdir, "disk.raw")
|
||||
vmlinux_path = os.path.join(outdir, "vmlinux")
|
||||
disk_sha, disk_size = _sha256_size(disk_path)
|
||||
vmlinux_sha, vmlinux_size = _sha256_size(vmlinux_path)
|
||||
contents = list(BASE_CONTENTS)
|
||||
# extra_contents:构建时才确定的附加内容(如 P1 的 vsock_notify,
|
||||
# 文件存在才拷入)。调用方传什么记什么,不编默认值。
|
||||
for item in extra_contents or []:
|
||||
if item and item not in contents:
|
||||
contents.append(item)
|
||||
versions = {
|
||||
"dpkg": _read_lines(
|
||||
os.path.join(outdir, "guest-versions-dpkg.txt")),
|
||||
@@ -123,14 +131,18 @@ def build(outdir, tag, ubuntu, codex_version, repo_commit,
|
||||
|
||||
|
||||
def main(argv):
|
||||
if len(argv) not in (8, 9):
|
||||
if len(argv) not in (8, 9, 10):
|
||||
print("用法:buildinfo.py OUT TAG UBUNTU CODEX_VERSION "
|
||||
"REPO_COMMIT UBUNTU_IMAGE_SHA256 PLAYWRIGHT "
|
||||
"[CHROMIUM_HEADLESS_SHELL_REV]", file=sys.stderr)
|
||||
"[CHROMIUM_HEADLESS_SHELL_REV] [EXTRA_CONTENTS]", file=sys.stderr)
|
||||
return 2
|
||||
_, outdir, tag, ubuntu, codex_version, repo_commit, \
|
||||
ubuntu_image_sha256, playwright = argv[:8]
|
||||
chromium_pinned_rev = argv[8] if len(argv) == 9 else None
|
||||
chromium_pinned_rev = argv[8] if len(argv) >= 9 else None
|
||||
# 第 10 参数:逗号分隔的附加内容(如 vsock_notify),可空。
|
||||
extra_contents = None
|
||||
if len(argv) == 10 and argv[9]:
|
||||
extra_contents = [s for s in argv[9].split(",") if s]
|
||||
if chromium_pinned_rev and not re.fullmatch(r"[0-9]+",
|
||||
chromium_pinned_rev):
|
||||
print("CHROMIUM_HEADLESS_SHELL_REV 须为纯数字:%s"
|
||||
@@ -138,7 +150,7 @@ def main(argv):
|
||||
return 2
|
||||
info = build(outdir, tag, ubuntu, codex_version, repo_commit,
|
||||
ubuntu_image_sha256, playwright == "1",
|
||||
chromium_pinned_rev)
|
||||
chromium_pinned_rev, extra_contents)
|
||||
if not info["versions"]["dpkg"]:
|
||||
print("BUILDINFO versions.dpkg 为空", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
@@ -0,0 +1,267 @@
|
||||
#!/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;cell.pid 不存在时只做 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 /run/chv/cell.pid 记的单元 init 同 ns
|
||||
(读不到 cell.pid 时跳过第 2 项并警告;cell.pid 存在但对端 ns
|
||||
读不到时拒绝,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 grp
|
||||
import json
|
||||
import os
|
||||
import socket
|
||||
import struct
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
BROKER_SOCK = "/run/chv/broker.sock"
|
||||
BROWSER_SOCK = "/run/chv/browser.sock"
|
||||
CELL_PID_FILE = "/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 _read_cell_pid():
|
||||
try:
|
||||
with open(CELL_PID_FILE) as fh:
|
||||
return int(fh.read().strip())
|
||||
except (OSError, ValueError):
|
||||
return None
|
||||
|
||||
|
||||
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_pid = _read_cell_pid()
|
||||
allowed, reason = peer_allowed(uid, pid, cell_pid)
|
||||
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 cell_pid is None:
|
||||
print("chv-broker: 警告:cell.pid 缺失,只做了 uid 检查 "
|
||||
"(pid=%d uid=%d)" % (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:]))
|
||||
@@ -0,0 +1,301 @@
|
||||
#!/usr/bin/env python3
|
||||
"""chv-browser:浏览器子代理(客机侧、单元外独立进程)。
|
||||
|
||||
对齐 Muse P2(见 docs/chv-muse-p2-gap.md):浏览器任务由专门子代理
|
||||
完成,与 codex 单元分离。子代理只向单元返回页面无障碍树快照
|
||||
(Playwright accessibility.snapshot),不见原始 DOM,不能在页面
|
||||
上下文跑 JS,不暴露 evaluate/content,不开 DevTools。
|
||||
|
||||
操作(Unix socket /run/chv/browser.sock,JSON 行):
|
||||
open {url} -> 导航并返回 {title, url, a11y, truncated}
|
||||
snapshot {} -> 当前页的 {title, url, a11y, truncated}
|
||||
screenshot {} -> 截图落盘 /run/chv/shots/<uuid>.png,返回 {path}
|
||||
close {} -> 关当前页(浏览器进程继续跑,等下一次 open)
|
||||
ping {} -> {"ok": true}
|
||||
|
||||
URL 只允许 http/https;localhost 与私有地址字面量直接拒绝(主机名
|
||||
判定,不做 DNS 解析——DNS 重绑定防护是 P3 Sentinel 的事,这里不
|
||||
冒充已做)。无障碍树截断到 200 节点 / 64KB,超了标 truncated=true,
|
||||
绝不把整棵树无上限灌进 socket。
|
||||
|
||||
playwright 是懒加载:import 本模块不需要 playwright 已装(单测
|
||||
在无 playwright 环境跑);真正 open 时才加载,缺失即报错。
|
||||
|
||||
只用标准库 + playwright(运行时)。运行身份:系统用户 chv-browser,
|
||||
socket 0600(broker 以 root 连,不受模式限制)。
|
||||
"""
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import socket
|
||||
import sys
|
||||
import uuid
|
||||
|
||||
BROWSER_SOCK = "/run/chv/browser.sock"
|
||||
SHOTS_DIR = "/run/chv/shots"
|
||||
PLAYWRIGHT_BROWSERS_PATH = "/usr/local/share/ms-playwright"
|
||||
MAX_REQUEST_BYTES = 65536
|
||||
MAX_A11Y_NODES = 200
|
||||
MAX_A11Y_CHARS = 65536
|
||||
NAV_TIMEOUT_MS = 30000
|
||||
|
||||
# 拒绝的 URL 主机:localhost 与私有地址字面量(主机名判定)。
|
||||
_PRIVATE_HOST_RE = re.compile(
|
||||
r"^(localhost|127\.\d+\.\d+\.\d+|10\.\d+\.\d+\.\d+|"
|
||||
r"172\.(1[6-9]|2\d|3[01])\.\d+\.\d+|192\.168\.\d+\.\d+|"
|
||||
r"\[::1\]|\[fe8[0-9a-f]*:.*\])$",
|
||||
re.IGNORECASE)
|
||||
|
||||
|
||||
def validate_url(url):
|
||||
"""URL 校验:只允许 http/https,且主机不是 localhost/私有地址
|
||||
字面量。返回 (ok, error)。DNS 重绑定不在本层防(见模块 docstring)。"""
|
||||
if not isinstance(url, str) or not url:
|
||||
return False, "url 不能为空"
|
||||
m = re.match(r"^(https?)://([^/]+)", url, re.IGNORECASE)
|
||||
if not m:
|
||||
return False, "只允许 http/https URL:%s" % url[:80]
|
||||
host = m.group(2).split("@")[-1].split(":")[0].lower()
|
||||
if _PRIVATE_HOST_RE.match(host):
|
||||
return False, "拒绝 localhost/私有地址:%s" % host
|
||||
return True, ""
|
||||
|
||||
|
||||
def truncate_a11y(node, max_nodes=MAX_A11Y_NODES,
|
||||
max_chars=MAX_A11Y_CHARS):
|
||||
"""截断无障碍树:节点数超上限时剪掉多余子树。返回 (tree, truncated)。
|
||||
纯函数,可单测。节点计数按 dict 节点数(含 children 展开)。"""
|
||||
state = {"count": 0, "truncated": False}
|
||||
|
||||
def walk(n):
|
||||
if not isinstance(n, dict):
|
||||
return n
|
||||
state["count"] += 1
|
||||
if state["count"] > max_nodes:
|
||||
state["truncated"] = True
|
||||
return None
|
||||
out = {}
|
||||
for key, value in n.items():
|
||||
if key == "children" and isinstance(value, list):
|
||||
children = []
|
||||
for child in value:
|
||||
walked = walk(child)
|
||||
if walked is None:
|
||||
state["truncated"] = True
|
||||
break
|
||||
children.append(walked)
|
||||
out[key] = children
|
||||
else:
|
||||
out[key] = value
|
||||
return out
|
||||
|
||||
tree = walk(node)
|
||||
text = json.dumps(tree, ensure_ascii=False)
|
||||
if len(text) > max_chars:
|
||||
state["truncated"] = True
|
||||
# 字符超限时只留顶层角色/名字/URL 信息,不灌整棵树。
|
||||
tree = {"role": (node or {}).get("role"),
|
||||
"name": (node or {}).get("name"),
|
||||
"truncated_chars": True}
|
||||
return tree, state["truncated"]
|
||||
|
||||
|
||||
def _load_playwright():
|
||||
"""懒加载 playwright;缺失时报明错(不静默假装有浏览器)。"""
|
||||
os.environ.setdefault("PLAYWRIGHT_BROWSERS_PATH",
|
||||
PLAYWRIGHT_BROWSERS_PATH)
|
||||
try:
|
||||
from playwright.sync_api import sync_playwright
|
||||
except ImportError as e:
|
||||
raise RuntimeError(
|
||||
"chv-browser: playwright 未装(%s),浏览器子代理不可用"
|
||||
% e)
|
||||
return sync_playwright
|
||||
|
||||
|
||||
class BrowserAgent:
|
||||
"""单页浏览器子代理。playwright_factory 供单测注入假实现;
|
||||
正常运行时用 _load_playwright()。"""
|
||||
|
||||
def __init__(self, playwright_factory=None, shots_dir=SHOTS_DIR):
|
||||
self._factory = playwright_factory or _load_playwright
|
||||
self._shots_dir = shots_dir
|
||||
self._pw = None
|
||||
self._browser = None
|
||||
self._page = None
|
||||
|
||||
def _ensure_browser(self):
|
||||
if self._browser is not None:
|
||||
return
|
||||
self._pw = self._factory()
|
||||
# sync_playwright() 返回上下文管理器;__enter__ 后拿 chromium。
|
||||
entered = self._pw.__enter__()
|
||||
self._browser = entered.chromium.launch(headless=True)
|
||||
|
||||
def open(self, url):
|
||||
ok, err = validate_url(url)
|
||||
if not ok:
|
||||
return {"ok": False, "error": err}
|
||||
try:
|
||||
self._ensure_browser()
|
||||
if self._page is not None:
|
||||
try:
|
||||
self._page.close()
|
||||
except Exception:
|
||||
pass
|
||||
self._page = self._browser.new_page()
|
||||
self._page.goto(url, timeout=NAV_TIMEOUT_MS)
|
||||
self._page.wait_for_load_state("domcontentloaded",
|
||||
timeout=NAV_TIMEOUT_MS)
|
||||
except Exception as e:
|
||||
return {"ok": False,
|
||||
"error": "打开 %s 失败:%s" % (url[:80], e)}
|
||||
return self.snapshot()
|
||||
|
||||
def snapshot(self):
|
||||
if self._page is None:
|
||||
return {"ok": False, "error": "还没有打开的页面(先 open)"}
|
||||
try:
|
||||
title = self._page.title()
|
||||
url = self._page.url
|
||||
tree = self._page.accessibility.snapshot()
|
||||
except Exception as e:
|
||||
return {"ok": False, "error": "取快照失败:%s" % e}
|
||||
tree, truncated = truncate_a11y(tree or {})
|
||||
return {"ok": True, "title": title, "url": url,
|
||||
"a11y": tree, "truncated": truncated}
|
||||
|
||||
def screenshot(self):
|
||||
if self._page is None:
|
||||
return {"ok": False, "error": "还没有打开的页面(先 open)"}
|
||||
try:
|
||||
os.makedirs(self._shots_dir, exist_ok=True)
|
||||
path = os.path.join(self._shots_dir, "%s.png"
|
||||
% uuid.uuid4().hex)
|
||||
self._page.screenshot(path=path)
|
||||
except Exception as e:
|
||||
return {"ok": False, "error": "截图失败:%s" % e}
|
||||
return {"ok": True, "path": path}
|
||||
|
||||
def close(self):
|
||||
if self._page is not None:
|
||||
try:
|
||||
self._page.close()
|
||||
except Exception:
|
||||
pass
|
||||
self._page = None
|
||||
return {"ok": True, "closed": True}
|
||||
|
||||
def shutdown(self):
|
||||
try:
|
||||
if self._browser is not None:
|
||||
self._browser.close()
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
if self._pw is not None:
|
||||
self._pw.__exit__(None, None, None)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
# 本层不暴露的操作:evaluate / content(原始 DOM)/ DevTools。
|
||||
# 收到即拒绝,不转发、不执行。
|
||||
FORBIDDEN_OPS = ("evaluate", "content", "devtools", "js")
|
||||
|
||||
|
||||
def handle_request(agent, req):
|
||||
"""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 in FORBIDDEN_OPS:
|
||||
return {"ok": False,
|
||||
"error": "操作 %r 不暴露(无 JS/无原始 DOM)" % op}
|
||||
if op == "ping":
|
||||
return {"ok": True, "browser": True}
|
||||
if op == "open":
|
||||
return agent.open(req.get("url"))
|
||||
if op == "snapshot":
|
||||
return agent.snapshot()
|
||||
if op == "screenshot":
|
||||
return agent.screenshot()
|
||||
if op == "close":
|
||||
return agent.close()
|
||||
return {"ok": False,
|
||||
"error": "未知操作:%r(白名单:open/snapshot/screenshot/"
|
||||
"close/ping)" % (op,)}
|
||||
|
||||
|
||||
def serve(sock_path=BROWSER_SOCK, shots_dir=SHOTS_DIR):
|
||||
"""监听 Unix socket,逐连接处理。socket 0600(只给属主 +
|
||||
broker 的 root 连)。建不起来即抛错,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)
|
||||
os.chmod(sock_path, 0o600)
|
||||
print("chv-browser: 监听 %s" % sock_path, file=sys.stderr, flush=True)
|
||||
agent = BrowserAgent(shots_dir=shots_dir)
|
||||
try:
|
||||
while True:
|
||||
try:
|
||||
conn, _ = srv.accept()
|
||||
except OSError:
|
||||
continue
|
||||
try:
|
||||
conn.settimeout(120)
|
||||
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:
|
||||
try:
|
||||
resp = handle_request(agent, req)
|
||||
except Exception as e:
|
||||
resp = {"ok": False,
|
||||
"error": "浏览器子代理内部错误:%s" % e}
|
||||
conn.sendall((json.dumps(resp, ensure_ascii=False)
|
||||
+ "\n").encode())
|
||||
except OSError as e:
|
||||
print("chv-browser: 连接处理异常:%s" % e, file=sys.stderr,
|
||||
flush=True)
|
||||
finally:
|
||||
try:
|
||||
conn.close()
|
||||
except OSError:
|
||||
pass
|
||||
finally:
|
||||
agent.shutdown()
|
||||
|
||||
|
||||
def main(argv):
|
||||
sock_path = BROWSER_SOCK
|
||||
shots_dir = SHOTS_DIR
|
||||
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] == "--shots-dir" and i + 1 < len(argv):
|
||||
shots_dir = argv[i + 1]
|
||||
i += 2
|
||||
else:
|
||||
print("chv-browser: 未知参数:%s" % argv[i], file=sys.stderr)
|
||||
return 2
|
||||
serve(sock_path, shots_dir)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main(sys.argv[1:]))
|
||||
@@ -0,0 +1,409 @@
|
||||
#!/usr/bin/env python3
|
||||
"""chv-cell:客机内 systemd-nspawn 运行时单元(Hatch 式)启动器。
|
||||
|
||||
对齐 Muse P2(见 docs/chv-muse-p2-gap.md):codex 跑在单元内,不再
|
||||
直接跑在客机用户态。单元是单命令容器(--as-pid2,不 boot 第二个
|
||||
systemd),单元即沙箱——单元内 codex 用 danger-full-access,不再
|
||||
套 bwrap(bwrap 的 --proc 挂载在嵌套命名空间里走不通,见 AGENTS.md
|
||||
内层 proc 定位)。
|
||||
|
||||
关键映射(与 Muse“单元 root 映射为 host 侧非特权用户”同款):
|
||||
--private-users=1000:65536 —— 单元内 uid 0 → 客机侧 chv(uid 1000)。
|
||||
效果:workspace / ~/.codex(chv 所有)单元内仍可写;host-root 0600
|
||||
文件(如 /etc/chv/guest-env)在单元内显示为 overflow uid、不可读;
|
||||
再加 --inaccessible 遮蔽作纵深防御。
|
||||
|
||||
网络:--network-veth。宿主侧 ve-chv-cell(10.200.0.1/24),单元侧
|
||||
host0(10.200.0.2/24,默认路由经 10.200.0.1),客机侧 NAT 出站
|
||||
(MASQUERADE 走客机默认路由的上行口,动态发现)。单元内配网经
|
||||
nsenter 进单元 init 的 netns 做。veth 建不起来即大声失败,不静默
|
||||
回落共享网络;CHV_CELL_NETWORK=shared 是显式调试逃生口,须显式
|
||||
设置并打日志,绝不默认。
|
||||
|
||||
环境透传:nspawn 不透传调用方环境,本脚本只转发白名单变量(模型
|
||||
网关与代理变量)。GITEA_TOKEN 等凭证变量不在白名单里,绝不进单元。
|
||||
|
||||
用法(客机侧 root 运行,执行器经 SSH 调):
|
||||
chv-cell run [--network veth|shared] -- <cmd...>
|
||||
# 例:chv-cell run -- python3 /app/host.py --state
|
||||
# /home/chv/.codex/host-state.json --codex-home /home/chv/.codex
|
||||
# --sandbox danger-full-access dispatch --name t --task ...
|
||||
chv-cell argv [--network veth|shared] -- <cmd...>
|
||||
# 只打印 nspawn 参数表(JSON),不启动
|
||||
chv-cell network-commands [--uplink IFACE] [--cell-pid PID]
|
||||
# 只打印配网命令表(JSON),不执行
|
||||
只用标准库。单元启动失败、配网失败一律非零退出,不静默降级。
|
||||
"""
|
||||
import json
|
||||
import os
|
||||
import pwd
|
||||
import re
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
|
||||
MACHINE = "chv-cell"
|
||||
# 单元映射:单元内 uid 0 → 客机侧 chv(uid 1000,非特权用户)。
|
||||
UID_BASE = 1000
|
||||
UID_COUNT = 65536
|
||||
CELL_USER = "chv"
|
||||
CELL_UID = 1000
|
||||
CELL_GID = 1000
|
||||
WORKSPACE = "/home/chv/workspace"
|
||||
CODEX_HOME = "/home/chv/.codex"
|
||||
BROKER_DIR = "/run/chv"
|
||||
CELL_PID_FILE = "/run/chv/cell.pid"
|
||||
|
||||
# 单元网络(与客机 tap 网 192.168.10.0/24 不重叠的独立 /24)。
|
||||
CELL_NET = "10.200.0.0/24"
|
||||
HOST_IP = "10.200.0.1"
|
||||
CELL_IP = "10.200.0.2"
|
||||
HOST_IFACE = "ve-chv-cell"
|
||||
CELL_IFACE = "host0"
|
||||
|
||||
# Muse 点名要丢的能力 + 同批丢的危险能力(nspawn 默认集已有限,
|
||||
# 这里是显式再丢,--drop-capability 逐项写,测试逐项断言)。
|
||||
DROP_CAPABILITIES = [
|
||||
"CAP_SYS_ADMIN",
|
||||
"CAP_SYS_PTRACE",
|
||||
"CAP_NET_ADMIN",
|
||||
"CAP_NET_RAW",
|
||||
"CAP_SYS_MODULE",
|
||||
"CAP_SYS_RAWIO",
|
||||
"CAP_SYS_BOOT",
|
||||
"CAP_MKNOD",
|
||||
]
|
||||
|
||||
# syscall 过滤:@system-service 集合再扣掉 io_uring 三件套
|
||||
#(Muse 点名禁用 io_uring)。
|
||||
SYSCALL_FILTER = ("@system-service ~io_uring_setup "
|
||||
"~io_uring_enter ~io_uring_register")
|
||||
|
||||
# 单元内遮掉的路径:凭证与浏览器(单元内跑不起自己的浏览器,
|
||||
# 只能走 broker 的 chv-browser)。
|
||||
INACCESSIBLE_BASE = [
|
||||
"/etc/chv",
|
||||
"/home/chv/.git-credentials",
|
||||
"/usr/local/share/ms-playwright",
|
||||
]
|
||||
|
||||
# 只转发白名单环境变量进单元。凭证类变量(GITEA_TOKEN 等)
|
||||
# 不在白名单里,绝不进单元。
|
||||
FORWARD_ENV_ALLOWLIST = (
|
||||
"SUB2API_BASE_URL",
|
||||
"SUB2API_API_KEY",
|
||||
"XCM_API_KEY",
|
||||
"HTTP_PROXY",
|
||||
"HTTPS_PROXY",
|
||||
"NO_PROXY",
|
||||
"http_proxy",
|
||||
"https_proxy",
|
||||
"no_proxy",
|
||||
)
|
||||
|
||||
|
||||
def _playwright_package_dir():
|
||||
"""playwright pip 包目录(遮蔽用)。算不出时回落到 noble 默认路径。"""
|
||||
try:
|
||||
import sysconfig
|
||||
purelib = sysconfig.get_path("purelib")
|
||||
if purelib:
|
||||
return os.path.join(purelib, "playwright")
|
||||
except Exception:
|
||||
pass
|
||||
return "/usr/local/lib/python3.12/dist-packages/playwright"
|
||||
|
||||
|
||||
def build_nspawn_argv(command, network="veth",
|
||||
workspace=WORKSPACE, codex_home=CODEX_HOME,
|
||||
broker_dir=BROKER_DIR,
|
||||
playwright_package_dir=None):
|
||||
"""产 nspawn 参数表(纯函数,可单测)。command 是单元内要跑的命令
|
||||
(list,如 ["python3", "/app/host.py", ...])。"""
|
||||
if not command:
|
||||
raise ValueError("chv-cell: 单元内命令不能为空")
|
||||
if network not in ("veth", "shared"):
|
||||
raise ValueError("chv-cell: network 只能是 veth|shared:%r"
|
||||
% network)
|
||||
if playwright_package_dir is None:
|
||||
playwright_package_dir = _playwright_package_dir()
|
||||
argv = [
|
||||
"systemd-nspawn", "--quiet",
|
||||
"--machine=%s" % MACHINE,
|
||||
"--directory=/",
|
||||
"--as-pid2",
|
||||
"--private-users=%d:%d" % (UID_BASE, UID_COUNT),
|
||||
"--no-new-privileges",
|
||||
"--system-call-filter=%s" % SYSCALL_FILTER,
|
||||
]
|
||||
for cap in DROP_CAPABILITIES:
|
||||
argv.append("--drop-capability=%s" % cap)
|
||||
for path in INACCESSIBLE_BASE + [playwright_package_dir]:
|
||||
argv.append("--inaccessible=%s" % path)
|
||||
argv += [
|
||||
"--bind=%s" % workspace,
|
||||
"--bind=%s" % codex_home,
|
||||
"--bind=%s" % broker_dir,
|
||||
"--tmpfs=/tmp",
|
||||
]
|
||||
if network == "veth":
|
||||
argv.append("--network-veth")
|
||||
argv += [
|
||||
"--setenv=CHV_CELL=1",
|
||||
"--setenv=HOME=/home/chv",
|
||||
]
|
||||
for name in FORWARD_ENV_ALLOWLIST:
|
||||
value = os.environ.get(name)
|
||||
if value:
|
||||
argv.append("--setenv=%s=%s" % (name, value))
|
||||
argv += ["--chdir=%s" % workspace]
|
||||
argv += list(command)
|
||||
return argv
|
||||
|
||||
|
||||
def parse_default_route_iface(ip_route_output):
|
||||
"""从 `ip route show default` 的输出里解析上行口名。
|
||||
无默认路由时返回 None(调用方大声失败)。"""
|
||||
for line in (ip_route_output or "").splitlines():
|
||||
line = line.strip()
|
||||
if not line.startswith("default "):
|
||||
continue
|
||||
m = re.search(r"\bdev\s+(\S+)", line)
|
||||
if m:
|
||||
return m.group(1)
|
||||
return None
|
||||
|
||||
|
||||
def find_uplink_iface(run=None):
|
||||
"""发现客机上行口(默认路由的 dev)。run 供单测注入。"""
|
||||
run = run or subprocess.run
|
||||
proc = run(["ip", "route", "show", "default"],
|
||||
capture_output=True, text=True)
|
||||
if proc.returncode != 0:
|
||||
return None
|
||||
return parse_default_route_iface(proc.stdout)
|
||||
|
||||
|
||||
def host_network_commands(uplink_iface):
|
||||
"""客机侧配网命令表(纯函数):ve 接口起 IP + 转发 + NAT。
|
||||
调用方按顺序执行,任一失败即停。"""
|
||||
if not uplink_iface:
|
||||
raise ValueError("chv-cell: 上行口名为空,配不出 NAT")
|
||||
return [
|
||||
["ip", "addr", "add", "%s/24" % HOST_IP, "dev", HOST_IFACE],
|
||||
["ip", "link", "set", HOST_IFACE, "up"],
|
||||
["sysctl", "-w", "net.ipv4.ip_forward=1"],
|
||||
["iptables", "-t", "nat", "-A", "POSTROUTING",
|
||||
"-s", CELL_NET, "-o", uplink_iface, "-j", "MASQUERADE"],
|
||||
["iptables", "-A", "FORWARD", "-i", HOST_IFACE,
|
||||
"-o", uplink_iface, "-j", "ACCEPT"],
|
||||
["iptables", "-A", "FORWARD", "-i", uplink_iface,
|
||||
"-o", HOST_IFACE, "-m", "state", "--state",
|
||||
"RELATED,ESTABLISHED", "-j", "ACCEPT"],
|
||||
]
|
||||
|
||||
|
||||
def host_network_cleanup_commands(uplink_iface):
|
||||
"""配网清理命令表(与 host_network_commands 配对,-A 改 -D)。
|
||||
清理是 best-effort:删不掉(规则已不在)不报错。"""
|
||||
if not uplink_iface:
|
||||
raise ValueError("chv-cell: 上行口名为空,清不了 NAT")
|
||||
cmds = []
|
||||
for cmd in host_network_commands(uplink_iface):
|
||||
if "iptables" not in cmd:
|
||||
continue
|
||||
cleaned = [c if c != "-A" else "-D" for c in cmd]
|
||||
cmds.append(cleaned)
|
||||
return cmds
|
||||
|
||||
|
||||
def find_cell_init_pid(nspawn_pid, proc_root="/proc"):
|
||||
"""找单元 init 的 pid:nspawn 进程的第一个子进程
|
||||
(--as-pid2 时它是 stub init,payload 是 PID 2;两者同 netns)。
|
||||
找不到返回 None。"""
|
||||
try:
|
||||
task_dir = os.path.join(proc_root, str(nspawn_pid), "task")
|
||||
for tid in os.listdir(task_dir):
|
||||
children_path = os.path.join(task_dir, tid, "children")
|
||||
try:
|
||||
with open(children_path) as fh:
|
||||
children = fh.read().split()
|
||||
except OSError:
|
||||
continue
|
||||
if children:
|
||||
return int(children[0])
|
||||
except (OSError, ValueError):
|
||||
return None
|
||||
return None
|
||||
|
||||
|
||||
def cell_network_commands(cell_pid):
|
||||
"""单元内配网命令表(纯函数):nsenter 进单元 init 的 netns,
|
||||
给 host0 配 IP、起接口、加默认路由。"""
|
||||
if not cell_pid:
|
||||
raise ValueError("chv-cell: 单元 init pid 为空,配不了单元内网络")
|
||||
prefix = ["nsenter", "-t", str(cell_pid), "-n"]
|
||||
return [
|
||||
prefix + ["ip", "addr", "add", "%s/24" % CELL_IP,
|
||||
"dev", CELL_IFACE],
|
||||
prefix + ["ip", "link", "set", CELL_IFACE, "up"],
|
||||
prefix + ["ip", "route", "add", "default", "via", HOST_IP],
|
||||
]
|
||||
|
||||
|
||||
def _ensure_bind_source(path, uid=CELL_UID, gid=CELL_GID):
|
||||
"""bind 源目录须存在且属 chv(单元内 root 即客机 chv,属主不对
|
||||
就写不进 workspace)。root 建的目录要 chown 回 chv。"""
|
||||
os.makedirs(path, exist_ok=True)
|
||||
try:
|
||||
st = os.stat(path)
|
||||
if st.st_uid != uid or st.st_gid != gid:
|
||||
os.chown(path, uid, gid)
|
||||
except OSError as e:
|
||||
print("chv-cell: chown %s 失败:%s" % (path, e), file=sys.stderr)
|
||||
raise
|
||||
|
||||
|
||||
def _wait_for_iface(iface, timeout=10.0):
|
||||
deadline = time.time() + timeout
|
||||
while time.time() < deadline:
|
||||
proc = subprocess.run(["ip", "link", "show", iface],
|
||||
capture_output=True)
|
||||
if proc.returncode == 0:
|
||||
return True
|
||||
time.sleep(0.2)
|
||||
return False
|
||||
|
||||
|
||||
def _run_cmds(cmds, what):
|
||||
for cmd in cmds:
|
||||
print("chv-cell: + %s" % " ".join(cmd), file=sys.stderr)
|
||||
proc = subprocess.run(cmd)
|
||||
if proc.returncode != 0:
|
||||
raise RuntimeError(
|
||||
"chv-cell: %s 失败(rc=%d):%s"
|
||||
% (what, proc.returncode, " ".join(cmd)))
|
||||
|
||||
|
||||
def run_cell(command, network="veth"):
|
||||
"""起单元、配网、等 payload 退出、清 NAT,返回 payload 退出码。"""
|
||||
if os.geteuid() != 0:
|
||||
print("chv-cell: 须以 root 运行(nspawn + 配网都要 root)",
|
||||
file=sys.stderr)
|
||||
return 2
|
||||
_ensure_bind_source(WORKSPACE)
|
||||
_ensure_bind_source(CODEX_HOME)
|
||||
_ensure_bind_source(BROKER_DIR, uid=0, gid=0)
|
||||
argv = build_nspawn_argv(command, network=network)
|
||||
print("chv-cell: 启动单元:%s" % " ".join(argv), file=sys.stderr)
|
||||
proc = subprocess.Popen(argv)
|
||||
uplink = None
|
||||
cell_pid = None
|
||||
try:
|
||||
if network == "veth":
|
||||
if not _wait_for_iface(HOST_IFACE):
|
||||
raise RuntimeError(
|
||||
"chv-cell: veth 接口 %s 未出现,拒绝回落共享网络"
|
||||
% HOST_IFACE)
|
||||
uplink = find_uplink_iface()
|
||||
if not uplink:
|
||||
raise RuntimeError(
|
||||
"chv-cell: 客机无默认路由,配不出 NAT")
|
||||
_run_cmds(host_network_commands(uplink), "客机侧配网")
|
||||
cell_pid = find_cell_init_pid(proc.pid)
|
||||
if not cell_pid:
|
||||
raise RuntimeError("chv-cell: 找不到单元 init pid")
|
||||
with open(CELL_PID_FILE, "w") as fh:
|
||||
fh.write(str(cell_pid))
|
||||
_run_cmds(cell_network_commands(cell_pid), "单元内配网")
|
||||
return proc.wait()
|
||||
finally:
|
||||
if uplink:
|
||||
for cmd in host_network_cleanup_commands(uplink):
|
||||
subprocess.run(cmd, capture_output=True)
|
||||
try:
|
||||
if os.path.exists(CELL_PID_FILE):
|
||||
os.remove(CELL_PID_FILE)
|
||||
except OSError:
|
||||
pass
|
||||
if proc.poll() is None:
|
||||
proc.terminate()
|
||||
try:
|
||||
proc.wait(timeout=10)
|
||||
except subprocess.TimeoutExpired:
|
||||
proc.kill()
|
||||
|
||||
|
||||
def main(argv):
|
||||
if len(argv) < 1:
|
||||
print("用法:chv-cell run|argv|network-commands …",
|
||||
file=sys.stderr)
|
||||
return 2
|
||||
verb = argv[0]
|
||||
rest = argv[1:]
|
||||
network = os.environ.get("CHV_CELL_NETWORK", "veth")
|
||||
# --network 只在 run/argv 前接受,其它位置一律不认。
|
||||
if rest and rest[0] == "--network":
|
||||
if len(rest) < 2:
|
||||
print("chv-cell: --network 缺值", file=sys.stderr)
|
||||
return 2
|
||||
network = rest[1]
|
||||
rest = rest[2:]
|
||||
if network not in ("veth", "shared"):
|
||||
print("chv-cell: network 只能是 veth|shared:%r" % network,
|
||||
file=sys.stderr)
|
||||
return 2
|
||||
if network == "shared":
|
||||
print("chv-cell: 警告:共享网络模式(调试逃生口),单元与"
|
||||
"客机共用网络命名空间", file=sys.stderr)
|
||||
if verb == "run":
|
||||
if not rest or rest[0] != "--":
|
||||
print("chv-cell: run 用法:chv-cell run -- <cmd...>",
|
||||
file=sys.stderr)
|
||||
return 2
|
||||
command = rest[1:]
|
||||
if not command:
|
||||
print("chv-cell: 单元内命令不能为空", file=sys.stderr)
|
||||
return 2
|
||||
try:
|
||||
return run_cell(command, network=network)
|
||||
except RuntimeError as e:
|
||||
print(str(e), file=sys.stderr)
|
||||
return 1
|
||||
if verb == "argv":
|
||||
if not rest or rest[0] != "--":
|
||||
print("chv-cell: argv 用法:chv-cell argv -- <cmd...>",
|
||||
file=sys.stderr)
|
||||
return 2
|
||||
print(json.dumps(build_nspawn_argv(rest[1:], network=network),
|
||||
ensure_ascii=False))
|
||||
return 0
|
||||
if verb == "network-commands":
|
||||
uplink = None
|
||||
cell_pid = None
|
||||
i = 0
|
||||
while i < len(rest):
|
||||
if rest[i] == "--uplink" and i + 1 < len(rest):
|
||||
uplink = rest[i + 1]
|
||||
i += 2
|
||||
elif rest[i] == "--cell-pid" and i + 1 < len(rest):
|
||||
cell_pid = int(rest[i + 1])
|
||||
i += 2
|
||||
else:
|
||||
print("chv-cell: network-commands 未知参数:%s"
|
||||
% rest[i], file=sys.stderr)
|
||||
return 2
|
||||
out = {}
|
||||
if uplink:
|
||||
out["host"] = host_network_commands(uplink)
|
||||
out["host_cleanup"] = host_network_cleanup_commands(uplink)
|
||||
if cell_pid:
|
||||
out["cell"] = cell_network_commands(cell_pid)
|
||||
print(json.dumps(out, ensure_ascii=False))
|
||||
return 0
|
||||
print("chv-cell: 未知子命令:%s" % verb, file=sys.stderr)
|
||||
return 2
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main(sys.argv[1:]))
|
||||
Reference in new issue
Block a user