When a node has public IPv6 addresses allocated by EasyTier, those addresses
are installed on the host's network interfaces. The system would then pick
them up as candidate source/destination addresses for underlay connections
(direct peer, UDP hole punch, bind addresses), causing overlay traffic to
loop back into the overlay itself.
Add a central predicate is_ip_easytier_managed_ipv6() and apply it at every
point where IPv6 addresses are selected for underlay use:
- Filter managed IPv6 from DNS-resolved connector addresses, including a
UDP socket getsockname check to detect whether the OS would route through
the overlay to reach a destination
- Skip managed IPv6 in bind address selection and STUN candidate filtering
- Strip managed IPv6 from GetIpListResponse RPC so peers never learn them
- Pass pre-resolved addresses to tunnel connectors to avoid re-resolution
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Avoid resolving Url::as_ref() to the full URL string before TunnelScheme
conversion. Add regression coverage for owned/borrowed URLs and the UDP
IPv6 hole-punch branch condition.
Co-authored-by: KKRainbow <443152178@qq.com>
* feat: support allocating public IPv6 addresses from a provider
Add a provider/leaser architecture for public IPv6 address allocation
between nodes in the same network:
- A node with `--ipv6-public-addr-provider` advertises a delegable
public IPv6 prefix (auto-detected from kernel routes or manually
configured via `--ipv6-public-addr-prefix`).
- Other nodes with `--ipv6-public-addr-auto` request a /128 lease from
the selected provider via a new RPC service (PublicIpv6AddrRpc).
- Leases have a 30s TTL, renewed every 10s by the client routine.
- The provider allocates addresses deterministically from its prefix
using instance-UUID-based hashing to prefer stable assignments.
- Routes to peer leases are installed on the TUN device, and each
client's own /128 is assigned as its IPv6 address.
Also includes netlink IPv6 route table inspection, integration tests,
and event-driven route/address reconciliation.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- propagate reusable through credential storage, CLI, RPC, routing, and tests
- enforce reusable=false owner election with current topology
- preserve proof-backed groups when refreshing credential ACL groups
Fixes a CLI listener parsing regression where url crate special-casing for ws/wss could misinterpret inputs like ws:11011, and adds coverage to prevent future regressions.
Changes:
Refactors listener parsing to avoid url::Url parsing for proto:port forms and to support additional shorthand inputs (port-only / IP-only / SocketAddr).
Centralizes “expand to all IpScheme variants” logic in a helper (gen_listeners) while preserving the “port=0 is dynamic” behavior.
Adds unit tests covering valid/invalid listener inputs and expansion behavior.
* distinct control / data when forward packets
* fix rpc split for udp tunnel
* feat(easytier-web): pass public ip in validate token webhook
* protect rpc port from subnet proxy
Discard malformed fake TCP frames instead of panicking so OpenWrt
nodes can survive unexpected or truncated packets.
Also emit the correct IPv6 ethertype and cover the parser with
round-trip and truncation regression tests.
Addresses issue #2016 where nodes behind unstable networks
(e.g. campus firewalls) cause excessive traffic that can freeze
the remote node.
Two changes in peer_ospf_route.rs:
- Make do_sync_route_info only trigger reverse sync_now when
incoming data actually changed the route table or foreign
network state. The previous unconditional sync_now created
an A->B->A->B ping-pong cycle on every RPC exchange.
- Add exponential backoff (50ms..5s) to session_task retry loop.
The previous fixed 50ms retry produced ~20 RPCs/s during
sustained network instability.
KKRainbow