Create easytier-core as the portable owner of configuration,
connectivity, tunnels, peer and routing state, gateways, management,
the data plane, and instance lifecycle. Keep operating-system
integration, native protocol engines, process startup, and presentation
in easytier behind explicit Host capability adapters.
Create easytier-proto to own schemas, generated RPC types, descriptors,
and feature-scoped protocol slices. Remove runtime protobuf reflection
from core while preserving unknown route-peer fields across forwarding.
Normalize instance construction through CoreInstance, CoreHostAdapters,
CoreProcessRuntime, and InstanceManager. Make the runtime config store
the only authoritative mutable configuration after startup.
Move the portable TCP/UDP data plane into core and extract a generic
OperationBroker for completion, cancellation, disposal, and capacity
accounting. Expose the session-based FFI v2 completion API and keep the
WASI guest ABI, wire schemas, and adapters with core.
Migrate CLI, GUI, web, FFI, Android JNI, OHOS, uptime, and mobile
consumers to the shared manager and core state. Add explicit user/web
config ownership and revision-aware web reconciliation.
Preserve configuration, wire, and management behavior while fixing
regressions discovered by the full platform and integration matrix:
- inherit advertised relay capabilities in foreign networks;
- refresh OSPF peer state immediately after runtime config changes;
- restore CLI GlobalCtx event output without forcing GUI logging;
- retain legacy encryption names and standalone RPC tunnel metadata;
- restore ICMP host composition and fragmented UDP handling;
- use portable 64-bit atomics on 32-bit MIPS targets; and
- retain discarded operations until late cancellation completes.
Validate the refactor across 45 GitHub checks, including Linux, macOS,
Windows, FreeBSD, web, GUI, Android, OHOS, feature profiles, and
three-node and subnet-proxy integration tests.
BREAKING CHANGE: internal Rust module paths are not preserved. Legacy
native data-plane APIs are replaced by the session-based FFI v2 API.
The dedicated Android data-plane wrapper is removed.
* bench: add packet bytes extraction Criterion benchmark
Adds a Criterion benchmark under easytier/benches/ covering
ZCPacket::payload_bytes and tunnel_payload_bytes at 1280/4096-byte payload
sizes, using iter_batched so ZCPacket construction stays in the setup phase
and is excluded from the timed region.
- Register the [[bench]] entry in easytier/Cargo.toml.
- Document the bench and PACKET_BYTES_* env vars in benches/README.md.
* perf: reduce packet buffer slicing churn
Replace BytesMut::split_off with Buf::advance in ZCPacket bytes
extraction paths (payload_bytes, tunnel_payload_bytes, convert_type,
drop_foreign_header) and in TunZCPacketToBytes, and simplify the
copy_from_slice in new_from_payload.
When the buffer is in its unique (VEC) representation, split_off promotes
it to the shared (ARC) representation, allocating a Shared control block
and bumping the refcount on every call, and pins the buffer in shared
mode. advance only mutates the in-place ptr/len/cap fields, avoiding that
allocation/refcount churn on the TX hot path. The byte data itself is not
copied by either path.
This PR fixes IPv6 UDP hole punching for peers with multiple public IPv6
addresses by adding two RPC signals:
- connector_addrs: connector-side candidate public IPv6 socket addresses
that the remote peer should punch back to.
- preferred_src_ipv6: remote listener IPv6 address that the remote peer
should use as the UDP source when sending hole-punch packets back.
Together, these let the connector try all usable local IPv6 candidates
while keeping the remote punch-back
packet sourced from the same IPv6 address that the connector is dialing.
Replace std::time::Instant with quanta::Instant on per-packet, per-RPC,
and per-session paths. TSC-based, ~5ns vs ~25ns per now() call.
Reuses the existing `extern crate self as hotpath` alias so
`use hotpath::instant::Instant;` resolves to the same quanta type with
or without the hotpath feature. Leaves tokio::time::Instant and
smoltcp::time::Instant untouched.
Handle TUN receive errors by marking the fake TCP stack closed and
clearing registered sockets instead of panicking.
Refuse new sockets on closed stacks and let listeners recreate stacks
when the reader task exits.
Remove quinn-plaintext to fix connection errors caused
by different hash values across platforms.
On x64, maintain compatibility with quinn-plaintext.
Adds a Linux-only socket_mark u32 config flag (CLI: --socket-mark, env:
ET_SOCKET_MARK, TOML/proto: flags.socket_mark, 0 = disabled) that is
applied as SO_MARK to every outbound underlay socket EasyTier creates:
TCP, UDP, QUIC, WebSocket, WireGuard connectors and listeners, plus the
FakeTCP decoy socket. Lets the host policy-route or filter EasyTier
underlay traffic with 'ip rule fwmark ...' or iptables -m mark.
Plumbing mirrors the existing bind_device pattern:
- FlagsInConfig.socket_mark (proto) + default 0 in gen_default_flags
- bind() builder gets a socket_mark arg; setup_socket2_ext calls
apply_socket_mark which is a no-op for mark=0 and on non-Linux
- TunnelConnector trait gets set_socket_mark(u32) default-no-op method
- IP-based connectors override; create_listener_by_url and the connector
factory pass mark from global_ctx flags
- QUIC threads mark through QuicEndpointManager::{server,connect}
- WebSocket/FakeTCP/TCP default-bind bypass paths apply mark via
socket2::SockRef::from(&tokio_socket)
- ForeignNetworkEntry propagates parent socket_mark into its derived ctx
Includes a Linux smoke test plus a CAP_NET_ADMIN-gated test that does a
getsockopt(SO_MARK) round-trip to confirm the kernel applied the value.
SO_MARK requires CAP_NET_ADMIN; ignored silently on non-Linux. FakeTCP's
TUN-written segments are not covered (kernel doesn't tag raw TUN
writes); operators relying on fwmark for FakeTCP must apply an iptables
rule on the FakeTCP TUN device separately.
Co-authored-by: Claude <noreply@anthropic.com>
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>
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.
Normalize composite tunnel display values before rendering peer and
debug output so IPv6 tunnel types no longer append `6` to the port.
- Preserve prefixes like `txt-` while converting tunnel schemes to
their IPv6 form.
- Recover malformed values such as `txt-tcp://...:110106` into
`txt-tcp6://...:11010`.
- Reuse the normalized remote address display in CLI debug output.
* machine-id should be scoped unbder same user-id
* feat: report device os metadata to console
* fix sync root key cause packet loss
* fix tun packet not invalid
* fix faketcp cause lat jitter
* fix some packet not decrypt
* fix peer info patch, improve performance of update self info
* fix foreign credential identity mismatch handling
- Explicitly shutdown tokio runtime on launcher cleanup to fix slow exit
- Add timeout to tunnel connector in tests to prevent hanging
- Reduce test wait durations from 5s to 100ms for faster test execution
- Bump num-bigint-dig from 0.8.4 to 0.8.6
Enable encryption for non-direct nodes requiring relay forwarding.
When secure_mode is enabled, peers perform Noise IK handshake to
establish an encrypted PeerSession. Relay packets are encrypted at
the sender and decrypted at the receiver. Intermediate forwarding
nodes cannot read plaintext data.
---------
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: KKRainbow <5665404+KKRainbow@users.noreply.github.com>
Prevent crashes when users input quic://...:0 by rejecting port 0 explicitly and propagating connect setup errors. Add a regression test to ensure invalid QUIC targets fail gracefully.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* feat: separate faketcp into a feature
* fix: no need to initialize out_len
* feat: separate zstd into a feature
* clippy: remove unnecessary cast, because for unix size_t always equals usize
* use quinn-plaintext
* remove server_cert in QUICTunnelListener
* remove some customized transport config
* leave max_concurrent_bidi_streams as default
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Use noise protocol on handshake. Check peer's public key if needed. Also support rekey and replay attack prevention.
E2EE and temporary password will be implemented based on this.
