feat(cells): fix PIC-to-PIC connection + add service-sharing permissions

Phase 1 — connection fixes:
- routing_manager.stop(): remove iptables -F / -t nat -F nuclear flush that
  would wipe WireGuard MASQUERADE and all peer rules on any UI stop action
- wireguard_manager.add_cell_peer(): reject vpn_subnet that overlaps the local
  WG network (routing blackhole — was the root cause of no handshake)
- wireguard_manager._syncconf(): pass Endpoint to 'wg set' so cell peers with
  static endpoints are synced to the kernel (not just AllowedIPs)

Phase 2 — service-sharing permissions backend:
- firewall_manager: add _cell_tag(), clear_cell_rules(), apply_cell_rules(),
  apply_all_cell_rules() — iptables FORWARD rules for cell-to-cell traffic
  using 'pic-cell-<name>' comment tags, distinct from 'pic-peer-*'
- app.py startup enforcement: call apply_all_cell_rules(cell_links) so rules
  survive API restarts
- cell_link_manager: permissions schema {inbound, outbound} per service;
  lazy migration for existing entries; update_permissions(), get_permissions();
  apply_cell_rules wired into add_connection/remove_connection
- routes/cells.py: GET /api/cells/services, GET+PUT /api/cells/<n>/permissions;
  RuntimeError now returns 400 (not 500) from add_connection

Removed broken 'test' cell (subnet 10.0.0.0/24 collided with local WG network).
Second PIC must use a distinct subnet (e.g. 10.0.1.0/24) before reconnecting.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-01 08:35:24 -04:00
parent f3118ff401
commit 0b103ffafb
6 changed files with 256 additions and 30 deletions
+77
View File
@@ -221,6 +221,83 @@ def apply_all_peer_rules(peers: List[Dict[str, Any]]) -> None:
})
# ---------------------------------------------------------------------------
# Cell-to-cell firewall rules
# ---------------------------------------------------------------------------
def _cell_tag(cell_name: str) -> str:
"""iptables comment tag for cell rules — distinct prefix from pic-peer-* to prevent collision."""
safe = re.sub(r'[^a-z0-9]', '-', cell_name.lower())
return f'pic-cell-{safe}'
def clear_cell_rules(cell_name: str) -> None:
"""Remove all FORWARD rules tagged for this cell (atomic save/restore)."""
tag = _cell_tag(cell_name)
comment_re = re.compile(rf'--comment\s+["\']?{re.escape(tag)}["\']?(\s|$)')
try:
save = _wg_exec(['iptables-save'])
if save.returncode != 0:
return
lines = save.stdout.splitlines()
filtered = [l for l in lines if not comment_re.search(l)]
if len(filtered) == len(lines):
return
restore_input = '\n'.join(filtered) + '\n'
restore = subprocess.run(
['docker', 'exec', '-i', WIREGUARD_CONTAINER, 'iptables-restore'],
input=restore_input, capture_output=True, text=True, timeout=10
)
if restore.returncode != 0:
logger.warning(f"clear_cell_rules iptables-restore failed: {restore.stderr.strip()}")
except Exception as e:
logger.error(f"clear_cell_rules({cell_name}): {e}")
def apply_cell_rules(cell_name: str, vpn_subnet: str, inbound_services: List[str]) -> bool:
"""Apply FORWARD rules for a cell-to-cell peer.
Traffic from vpn_subnet is allowed only to service VIPs listed in
inbound_services; all other cell traffic is DROPped. Cells get no
internet or peer access — only explicit service VIPs.
Rule insertion order (last inserted → top of chain):
1. Catch-all DROP for the subnet (inserted first → bottom)
2. Per-service ACCEPT/DROP (inserted in reversed() order → top)
"""
try:
tag = _cell_tag(cell_name)
clear_cell_rules(cell_name)
# Catch-all DROP — inserted first so it ends up at the bottom
_iptables(['-I', 'FORWARD', '-s', vpn_subnet,
'-m', 'comment', '--comment', tag, '-j', 'DROP'])
# Per-service rules — inserted in reverse dict order, highest-priority last
for service, svc_ip in reversed(list(SERVICE_IPS.items())):
target = 'ACCEPT' if service in inbound_services else 'DROP'
_iptables(['-I', 'FORWARD', '-s', vpn_subnet, '-d', svc_ip,
'-m', 'comment', '--comment', tag, '-j', target])
logger.info(f"Applied cell rules for {cell_name} ({vpn_subnet}): inbound={inbound_services}")
return True
except Exception as e:
logger.error(f"apply_cell_rules({cell_name}): {e}")
return False
def apply_all_cell_rules(cell_links: List[Dict[str, Any]]) -> None:
"""Re-apply firewall rules for all cell connections (called on startup)."""
for link in cell_links:
name = link.get('cell_name')
subnet = link.get('vpn_subnet')
if not name or not subnet:
continue
perms = link.get('permissions', {})
inbound = [s for s, v in perms.get('inbound', {}).items() if v]
apply_cell_rules(name, subnet, inbound)
# ---------------------------------------------------------------------------
# DNS ACL (CoreDNS Corefile generation)
# ---------------------------------------------------------------------------