Files
pxe-server/tests/pxe-nic-check/test_helpers.py
cproudlock 21ff95af78 NIC guard: ignore client EAPOL, re-check on carrier change, SMB-only lease cleanup
- pxe-nic-check: count 802.1X only from an authenticator (EAPOL type 0
  with EAP Request/Success/Failure). iPXE sends EAPOL-Start on every NIC
  open and Windows sends Start/Response, so a PXE-booting bay made the
  verdict 'ge' and the watch stopped dnsmasq for the floor.
- pxe-nic-check: join the STP/PAE/LLDP/CDP/PVST+ multicast groups on
  every capture socket, so CDP-only ports are heard on a plain NIC.
- pxe-nic-check --watch: if dnsmasq was (re)started inside the window,
  re-check (~6 s) before stopping it; skip when already stopped.
  New --state-cmd and --print-imaging.
- pxe-nic-carrier (+ pxe-nic-carrier.service): networkd-dispatcher hook
  for the imaging NIC only. Carrier loss stops dnsmasq; carrier gain
  restarts it through its guard if it was running or the hook stopped it.
- pxe-dhcp-hook.sh: clear only SMB (tcp 445/139) conntrack entries and
  sockets, not all traffic for the client, which raced iPXE's first
  HTTP fetch.
- GetPxeScript.aspx: every boot line has a failure branch (iPXE 2.0
  accepts an unsigned EFI kernel and fails at boot under Secure Boot,
  which aborted the script).
- Tests: client EAPOL, packet_mreq packing, watch race, shell helpers on
  stub PATH, lab scenarios eapol-client, br-eapol-client, race, carrier.
2026-10-15 14:26:39 -04:00

291 lines
11 KiB
Python

"""
Tests for the shell helpers next to pxe-nic-check: pxe-dhcp-hook.sh (the
dnsmasq dhcp-script) and pxe-nic-carrier (the networkd-dispatcher hook).
No root, no network: every command they run (ss, conntrack, logger,
systemctl, pxe-nic-check) is a stub on a fake PATH that records its argv.
python3 -m unittest discover -s tests/pxe-nic-check -v
"""
import os
import shutil
import subprocess
import tempfile
import unittest
HERE = os.path.dirname(os.path.abspath(__file__))
HELPERS = os.path.normpath(os.path.join(HERE, "..", "..", "playbook",
"pxe-server-helpers"))
HOOK = os.path.join(HELPERS, "pxe-dhcp-hook.sh")
CARRIER = os.path.join(HELPERS, "pxe-nic-carrier")
# Each stub appends "name arg1 arg2 ..." (args joined by \x1f) to $CALLS.
STUB = r"""#!/bin/bash
{ printf '%s' "$(basename "$0")"; for a in "$@"; do printf '\x1f%s' "$a"; done
printf '\n'; } >> "$CALLS"
"""
SYSTEMCTL = STUB + r"""
case "$1" in
is-active) s=$(cat "$STUBDIR/dnsmasq.state" 2>/dev/null || echo active)
echo "$s"; [ "$s" = active ] ;;
restart) [ "$2" = dnsmasq ] && exit "$(cat "$STUBDIR/restart.rc" 2>/dev/null || echo 0)"
exit 0 ;;
*) exit 0 ;;
esac
"""
CHECK = STUB + r"""
[ "$1" = --print-imaging ] && cat "$STUBDIR/imaging" 2>/dev/null
exit 0
"""
class Stubs:
def __init__(self):
self.dir = tempfile.mkdtemp(prefix="pxe-helper-test-")
self.bin = os.path.join(self.dir, "bin")
os.mkdir(self.bin)
self.calls = os.path.join(self.dir, "calls")
for name, body in (("ss", STUB), ("conntrack", STUB),
("logger", STUB), ("systemctl", SYSTEMCTL),
("pxe-nic-check", CHECK)):
self.write(os.path.join(self.bin, name), body, 0o755)
self.sys = os.path.join(self.dir, "sys")
self.run_dir = os.path.join(self.dir, "run")
def write(self, path, text, mode=0o644):
with open(path, "w") as f:
f.write(text)
os.chmod(path, mode)
def env(self, **extra):
env = {"PATH": self.bin + ":/usr/bin:/bin", "CALLS": self.calls,
"STUBDIR": self.dir,
"PXE_NIC_CHECK": os.path.join(self.bin, "pxe-nic-check"),
"PXE_SYSTEMCTL": os.path.join(self.bin, "systemctl"),
"PXE_SYS_NET": self.sys,
"PXE_NIC_CARRIER_RUN": self.run_dir,
"PXE_NIC_CARRIER_SETTLE": "0"}
env.update(extra)
return env
def get_calls(self, name=None):
try:
with open(self.calls) as f:
lines = f.read().splitlines()
except OSError:
return []
out = [ln.split("\x1f") for ln in lines]
return [c for c in out if name is None or c[0] == name]
def reset(self):
if os.path.exists(self.calls):
os.unlink(self.calls)
def link(self, iface, carrier):
d = os.path.join(self.sys, iface)
os.makedirs(d, exist_ok=True)
path = os.path.join(d, "carrier")
if carrier is None: # admin down: reading carrier fails
if os.path.exists(path):
os.unlink(path)
else:
self.write(path, "%d\n" % carrier)
def cleanup(self):
shutil.rmtree(self.dir, ignore_errors=True)
class DhcpHook(unittest.TestCase):
def setUp(self):
self.s = Stubs()
def tearDown(self):
self.s.cleanup()
def run_hook(self, action, vendor=None):
env = self.s.env()
if vendor is not None:
env["DNSMASQ_VENDOR_CLASS"] = vendor
r = subprocess.run(["bash", HOOK, action, "02:aa:00:00:00:05",
"172.16.9.50", "bay3105"], env=env,
capture_output=True, text=True, timeout=10)
self.assertEqual(r.returncode, 0, r.stderr)
return self.s.get_calls()
def assert_smb_only(self, calls):
ct = [c[1:] for c in calls if c[0] == "conntrack"]
self.assertEqual(sorted(ct), sorted([
["-D", "-p", "tcp", "-s", "172.16.9.50", "--dport", "445"],
["-D", "-p", "tcp", "-d", "172.16.9.50", "--sport", "445"],
["-D", "-p", "tcp", "-s", "172.16.9.50", "--dport", "139"],
["-D", "-p", "tcp", "-d", "172.16.9.50", "--sport", "139"],
]))
ss = [c[1:] for c in calls if c[0] == "ss"]
self.assertEqual(ss, [["-K", "-t", "( sport = :445 or sport = :139 )"
" and dst = 172.16.9.50"]])
logs = [c for c in calls if c[0] == "logger"]
self.assertEqual(len(logs), 1)
self.assertIn("SMB", logs[0][-1])
def test_add_and_del_clear_smb_state_whatever_the_vendor(self):
for action in ("add", "del"):
for vendor in ("PXEClient:Arch:00007:UNDI:003016",
"MSFT 5.0", None):
self.s.reset()
self.assert_smb_only(self.run_hook(action, vendor))
def test_old_only_for_network_boot(self):
self.s.reset()
calls = self.run_hook("old", "PXEClient:Arch:00007:UNDI:003016")
self.assert_smb_only(calls)
self.assertIn("network boot, PXEClient:Arch:00007",
[c for c in calls if c[0] == "logger"][0][-1])
for vendor in ("MSFT 5.0", None, ""):
self.s.reset()
self.assertEqual(self.run_hook("old", vendor), [], vendor)
def test_never_clears_all_traffic(self):
calls = self.run_hook("add", "PXEClient")
for c in calls:
if c[0] == "conntrack":
self.assertIn("-p", c)
self.assertIn("tcp", c)
if c[0] == "ss":
self.assertIn("sport = :445", c[-1])
def test_no_ip_does_nothing(self):
r = subprocess.run(["bash", HOOK, "add", "02:aa:00:00:00:05", ""],
env=self.s.env(), capture_output=True, timeout=10)
self.assertEqual(r.returncode, 0)
self.assertEqual(self.s.get_calls(), [])
class Carrier(unittest.TestCase):
def setUp(self):
self.s = Stubs()
self.s.write(os.path.join(self.s.dir, "imaging"), "pxe0\n")
self.s.link("pxe0", 1)
self.s.link("corp0", 1)
def tearDown(self):
self.s.cleanup()
def event(self, iface, state="routable"):
r = subprocess.run(["bash", CARRIER], env=self.s.env(
IFACE=iface, STATE=state), capture_output=True, text=True,
timeout=20)
self.assertEqual(r.returncode, 0, r.stderr)
return self.s.get_calls()
def gain(self):
r = subprocess.run(["bash", CARRIER, "--gain"], env=self.s.env(),
capture_output=True, text=True, timeout=20)
self.assertEqual(r.returncode, 0, r.stderr)
return self.s.get_calls()
def systemctl(self, calls):
return [c[1:] for c in calls if c[0] == "systemctl"]
def dnsmasq(self, state):
self.s.write(os.path.join(self.s.dir, "dnsmasq.state"), state + "\n")
def marker(self):
return os.path.exists(os.path.join(self.s.run_dir, "stopped-dnsmasq"))
def test_ge_nic_is_never_touched(self):
for carrier in (0, 1, None, 1):
self.s.reset()
self.s.link("corp0", carrier)
calls = self.event("corp0", "no-carrier")
self.assertEqual([c[0] for c in calls], ["pxe-nic-check"])
self.assertFalse(os.path.exists(os.path.join(self.s.run_dir,
"link.corp0")))
def test_unknown_imaging_nic_does_nothing(self):
self.s.write(os.path.join(self.s.dir, "imaging"), "")
calls = self.event("pxe0", "no-carrier")
self.assertEqual([c[0] for c in calls], ["pxe-nic-check"])
def test_loss_stops_running_dnsmasq_and_marks(self):
self.event("pxe0", "routable") # first sight: up
self.s.reset()
self.s.link("pxe0", 0)
sc = self.systemctl(self.event("pxe0", "no-carrier"))
self.assertIn(["stop", "pxe-nic-carrier.service"], sc)
self.assertIn(["stop", "--no-block", "dnsmasq"], sc)
self.assertLess(sc.index(["stop", "pxe-nic-carrier.service"]),
sc.index(["stop", "--no-block", "dnsmasq"]))
self.assertTrue(self.marker())
# same state again (off after no-carrier): idempotent, no calls
self.s.reset()
self.s.link("pxe0", None)
self.assertEqual(self.systemctl(self.event("pxe0", "off")), [])
def test_loss_with_dnsmasq_stopped_leaves_no_marker(self):
self.dnsmasq("inactive")
self.s.link("pxe0", 0)
sc = self.systemctl(self.event("pxe0", "no-carrier"))
self.assertNotIn(["stop", "--no-block", "dnsmasq"], sc)
self.assertFalse(self.marker())
def test_gain_hands_off_once(self):
self.s.link("pxe0", 0)
self.event("pxe0", "no-carrier")
self.s.reset()
self.s.link("pxe0", 1)
sc = self.systemctl(self.event("pxe0", "carrier"))
self.assertEqual(sc[-1], ["restart", "--no-block",
"pxe-nic-carrier.service"])
self.assertNotIn("dnsmasq", [x for c in sc for x in c])
self.s.reset() # routable right after carrier
self.assertEqual(self.systemctl(self.event("pxe0", "routable")), [])
def test_bridge_port_events_count(self):
self.s.write(os.path.join(self.s.dir, "imaging"), "br-pxe\npxe0\n")
self.s.link("br-pxe", 1)
self.event("pxe0", "enslaved")
self.s.reset()
self.s.link("pxe0", 0)
sc = self.systemctl(self.event("pxe0", "no-carrier"))
self.assertIn(["stop", "--no-block", "dnsmasq"], sc)
def test_gain_restarts_dnsmasq_through_its_guard(self):
os.makedirs(self.s.run_dir)
self.s.write(os.path.join(self.s.run_dir, "stopped-dnsmasq"), "")
self.dnsmasq("inactive") # the hook stopped it
sc = self.systemctl(self.gain())
self.assertIn(["restart", "dnsmasq"], sc)
self.assertFalse(self.marker())
def test_gain_restarts_running_dnsmasq(self):
# loss never seen (fast swap, boot): dnsmasq running, no marker
sc = self.systemctl(self.gain())
self.assertIn(["restart", "dnsmasq"], sc)
def test_gain_logs_crit_when_guard_refuses(self):
self.s.write(os.path.join(self.s.dir, "restart.rc"), "1\n")
calls = self.gain()
logs = [c for c in calls if c[0] == "logger"]
self.assertTrue(any("daemon.crit" in c and "NOT started" in c[-1]
for c in logs), logs)
def test_gain_leaves_operator_stopped_dnsmasq_alone(self):
self.dnsmasq("inactive")
calls = self.gain()
self.assertNotIn(["restart", "dnsmasq"], self.systemctl(calls))
self.assertNotIn(["start", "dnsmasq"], self.systemctl(calls))
self.assertIn(["pxe-nic-check", "--guard"],
[c for c in calls if c[0] == "pxe-nic-check"])
def test_gain_does_nothing_if_link_dropped_again(self):
self.s.link("pxe0", 0)
calls = self.gain()
self.assertEqual(self.systemctl(calls), [])
self.assertNotIn(["pxe-nic-check", "--guard"], calls)
if __name__ == "__main__":
unittest.main()