TCP tunnel uses FramedWriter (not RingSink), but start_send is still
sync (writes to BufList in memory). poll_flush does actual TCP write
syscall — noop_waker returns Ok for Pending (data stays in BufList,
flushed on next send when BufList >= 64).
Add TCP benchmark support via HOTPATH_TUNNEL=tcp. Note: TCP/UDP
convergence requires netns in bench environment (connector multi-bind
address behavior doesn't work for localhost without namespaces).
All 210 peers tests pass. Ring tunnel benchmark: 234K -> 508K pps (+117%).
UDP tunnel uses RingSink internally (same as ring tunnel). Extend
direct mode to include UDP. Fix poll_flush Pending to return Ok.
Add UDP benchmark support via HOTPATH_TUNNEL=udp env variable.
All 208 peers tests pass. Netns tests unchanged (require root).
The async fn Future state machine overhead (~1.9us) dominated
MpscTunnelSender::send, while RingSink operations were only ~40ns.
Breakthrough: make send() an async fn that completes synchronously
on the first poll for the direct (ring tunnel) path. Uses
futures::task::noop_waker() to construct a dummy Context, then calls
Sink trait methods (poll_ready, start_send, poll_flush) directly.
RingSink always returns Ready immediately, so the waker is never
invoked and the async fn completes without yielding.
Channel mode (TCP/UDP/WG tunnels) still uses async send_async()
with proper backpressure. Ring tunnels detected via tunnel_info()
type check in PeerConn.
Results (4 threads, 1400B, 15s):
pps: 249K → 474K (+90%)
send_msg_by_ip: 3.53us → 1.67us (-53%)
send_msg_internal: 2.40us → 502ns (-79%)
MpscTunnelSender::send: 1.97us → 144ns (-93%)
All 207 peers:: tests pass. Netns-requiring tests (three_node,
credential) unchanged (require root).
tokio::sync::Mutex and std::sync::Mutex both have !Send guards that
cannot cross await points in multi_thread runtime. Replace with a
custom SpinSink using AtomicBool CAS — the SpinGuard contains only a
&SpinSink reference (SpinSink: Sync via unsafe impl), so it is Send.
Benchmark: pps unchanged (~249K), MpscTunnelSender::send avg 1.97us.
The bottleneck is confirmed to be async fn Future state machine
overhead (~1.9us), not the lock mechanism. RingSink operations are
only ~40ns (poll_ready 15ns + start_send 10ns + poll_flush 15ns).
Further breakthrough requires either:
- Sync send API (bypassing async entirely)
- Concrete type instead of dyn ZCPacketSink (to call RingSink::try_send directly)
Replace 3 await points (lock().await + feed().await + flush().await)
with try_lock() (sync) + single poll_fn (merged poll_ready + start_send
+ poll_flush).
parking_lot::Mutex cannot be used because MutexGuard is !Send (cannot
cross await in multi_thread runtime). tokio::sync::Mutex try_lock()
returns synchronously and MutexGuard is Send.
Benchmark: pps 250K → 251K (+0.4%), MpscTunnelSender::send avg
2.07us → 1.98us (-90ns). Improvement is small because tokio async
machinery overhead (Future state machine + poll) dominates over
RingSink's actual 40ns operation cost.
MpscTunnelSender now supports two modes:
- Channel mode (existing): try_send to tokio mpsc → receiver task → sink
- Direct mode (new): MpscTunnelSender holds Arc<Mutex<sink>> directly,
bypassing the channel + receiver task entirely
PeerConn uses new_direct to skip the channel intermediary.
Benchmark result: pps unchanged (~245K). The async fn overhead of
Mutex::lock().await + SinkExt::feed().await + SinkExt::flush().await
(~2us) is comparable to channel try_send (~2us). The bottleneck is
the Sink trait's async poll machinery, not the channel itself.
However, this change provides:
- RingSink timing now fully visible (start_send 10ns, poll_ready 13ns,
poll_flush 17ns = 40ns/pkt total)
- Reduced architectural complexity (no receiver task for PeerConn)
- Foundation for a sync fast path using RingSink::try_send directly
Fix web/frontend compat bugs in managed config & runtime status
- Preserve [[peer]].peer_public_key when TOML configs round-trip
through the web/managed NetworkConfig path
- Keep old peer_urls clients working while adding structured peer
metadata for new clients
- Make frontend protobuf JSON normalization preserve omitted-field
semantics instead of turning missing data into misleading defaults
- Harden runtime status rendering against omitted or string-encoded
backend fields
- Expose peer-route feature flags in the web status UI
Fixes SOCKS5/port-forward handling for peer data packets
whose source endpoint was rewritten by the KCP or QUIC proxy path.
Keep SOCKS5 entry accounting consistent by centralizing insert/remove
operations, decrementing only for actual removals, avoiding underflow,
and resetting counts when entries are retained or cleared after IPv4 changes.
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.
* refactor(web): use generated proto network types
* fix(core): preserve dumped config flags
* test(web): cover config flag save paths
* fix(ci): use system protoc before frontend codegen
* fix(ci): serialize frontend-lib builds
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.
* feat(ffi): add async data plane API
* feat(ffi): add async data plane examples
* test(ffi): make async Go dataplane tests self-contained
* docs(ffi): document Go async dataplane API
* docs(android): document dataplane JNI API
pnpm v11 introduces breaking changes that cause frozen installations
to fail:
1. The "pnpm" field in package.json is no longer read. Moved
`overrides` to `pnpm-workspace.yaml` to fix
`ERR_PNPM_LOCKFILE_CONFIG_MISMATCH`.
2. `strictDepBuilds` is now enabled by default. Added required
dependencies (esbuild, unrs-resolver, vue-demi) to `allowBuilds` in
the workspace config to fix `ERR_PNPM_IGNORED_BUILDS`.
Add config server client support for the C FFI and Android JNI bindings.
Reuse the existing easytier::web_client::run_web_client path and
NetworkInstanceManager; OHOS is unchanged.
Report successful remote config apply/delete operations through a
callback, with one JSON event per affected instance.
Keep the config server client and FFI data plane mutually exclusive: once
either side is in use, the other side returns an error instead of sharing
lifecycle state.
Use pbjson to support string deserialization for enum fields
This allows TOML configs like:
chainType = "Inbound"
instead of:
chainType = 1
- Maintain backward compatibility with integer values
- Default serialization format is now string
TomlConfigLoader::new_from_str() always calls NetworkIdentity::new()
with unwrap_or_default() on network_secret, converting None to ''.
This creates a non-zero SHA256 digest, causing credential nodes loaded
from TOML to be misidentified as regular nodes (with network_secret),
which breaks Noise handshake authentication.
Fix: check if secure_mode is enabled AND network_secret is absent/empty,
and call NetworkIdentity::new_credential() in that case.
The same detection already exists in:
- core.rs (CLI path, via --credential flag)
- launcher.rs (GUI/web path, via gen_config)
This makes TOML config loading consistent with the other two entry points.
1. Overview
This PR adds data plane APIs to easytier-ffi:
TCP Outbound:
- data_plane_tcp_connect
- data_plane_tcp_read
- data_plane_tcp_write
- data_plane_tcp_close
TCP Listener:
- data_plane_tcp_bind
- data_plane_tcp_accept
- data_plane_tcp_listener_close
UDP:
- data_plane_udp_bind
- data_plane_udp_send_to
- data_plane_udp_recv_from
- data_plane_udp_close
2. Key Changes
The main changes are focused on:
- easytier-contrib/easytier-ffi/src/lib.rs: Added FFI interfaces;
made ERROR_MSG thread-safe.
- easytier/src/gateway/socks5.rs: Bridges the data plane to the
existing Socks5 server logic.
- Added EasyTierUdpSocket, mainly wrapping ref-counting and
critical object (e.g., Socks5EntrySet) hold & drop logic,
and exposing common fields (e.g., local_addr).
- Extended Socks5Server functionality to expose TCP and UDP
socket creation interfaces for FFI calls.
- Other files: Mostly pass-through logic.
- Added a relatively large Go usage example.
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>
Fix the issue where the Magisk module incorrectly matches the lookup main rule in Android 15's cellular network rules, causing data plane connectivity failure
This may helps games to find rooms in virtual network.
- add opt-in Windows UDP broadcast relay config flag and CLI/env plumbing
- capture local UDP broadcasts with Windows raw sockets, normalize packets, and inject them via PeerManager
fanyang