The UDP recv microbenchmark carried a bare #[ignore] while its sibling in
the link module carries a self-describing one. Match it, so the reason
appears wherever the test is listed rather than only in the doc comment.
Record why [profile.ci] retries = 2 is not applied locally. The two gates
disagree on purpose: the hosted runner retries a flaky test twice, the
local sweep fails on the first failure. It exists for shared-runner packet
loss, a property of that environment rather than of the code, and applying
it locally would suppress a real local flake — a failure that only
reproduces under load is a robustness bug to fix, not to retry past.
Keeping the local sweep strict is what makes it the sharper gate. An
undocumented asymmetry is indistinguishable from an oversight, which is
why this is written down rather than left to be rediscovered.
The cost is stated rather than hidden: a test that fails once and passes
on retry is reported green with no separate signal, so a genuine
intermittent failure can be absorbed. If that starts mattering the fix is
to surface retried-but-passed tests, not to drop the retries.
Quartet clean: fmt, build --workspace, clippy --all-targets -D warnings,
and test --lib at 1376 passed / 0 failed / 7 ignored.
The per-peer control machine has absorbed every field the pending
connection carried. What remained was a struct holding two Noise
handles beside a duplicate copy of bookkeeping nobody read. Replace it
with a small carrier for the two handles and delete the type.
Presence of that carrier, not the state of the handles inside it, is
what marks a machine as mid-handshake. The distinction is essential
rather than stylistic: a failed handshake drops its initiation handle
and is deliberately retained so the stale sweep can reclaim it, and a
completed one has its session taken before disposal. Deriving presence
from the handles would make both invisible to the sweep, the
connection count, and the peering budget at once, leaking the slot
permanently. A test drives an empty carrier past every presence
predicate and then detaches it, so a future edit cannot quietly couple
the two.
The remote startup epoch now comes from the surviving carrier, which
the handshake operations already wrote at the same two points with the
same value. The paired writes onto the pending connection's own
bookkeeping had no readers left and are gone.
The handshake-phase surface leaves the public API: it was public by
accident rather than design, and the machine behind it is crate
internal. Callers outside the crate that need a view of pending
handshakes go through the operator queries, which are unchanged.
ConnectionState::inbound_with_transport loses its last non-test caller
with the inbound seed and is marked test-only.
Make the FIPS core build and run as an embedded Android library. The host
app owns the TUN (e.g. an Android VpnService) and FIPS performs no
system-TUN or CAP_NET_ADMIN operations.
Squashed from the following changes:
- gate desktop transports/TUN by target_os, not features: a plain
`cargo build` now compiles for every target with no flags. Ethernet (raw
AF_PACKET / BPF) is gated to linux/macos, so Android (target_os =
"android", not "linux") self-excludes it as Windows already did; real
system-TUN ops are gated per linux/macos and Android gets a no-op stub;
the ipi6_ifindex cast handles it being i32 on Android vs u32 on macOS. No
Cargo features are introduced; desktop builds are unchanged.
- app-owned TUN seam: Node::enable_app_owned_tun() lets an embedder that
owns the TUN fd exchange IPv6 packet bytes with FIPS over channels
instead of FIPS creating a system TUN device. It returns (app_outbound_tx,
app_inbound_rx): the embedder pushes packets read from its fd into the
outbound sender (app -> mesh) and pulls packets destined for its fd from
the inbound receiver (mesh -> app). start() gates system-TUN creation on
tun_tx being unset, so with the channels pre-installed it skips device
creation and does no system-TUN ops; both directions reuse the existing
inbound-shim and run_rx_loop wiring. Packets entering via app_outbound_tx
bypass handle_tun_packet, so the embedder must push only fd00::/8-destined
packets and clamp TCP MSS on outbound SYNs; the rustdoc and the
IPv6-adapter design doc spell this out.
- keep the android target warning-clean so the cross-compile check passes
clippy -D warnings.
- add an Android cross-compile CI check: cross-compile the library for
aarch64-linux-android via cargo-ndk and run clippy -D warnings. Android
ships as an embedded library (the host app owns the TUN), so there is no
daemon binary to package; this is a check job, not a packaging one.
- docs: list Android as a supported platform.
Tests: app_owned_tun_seam_wires_channels covers the channel round-trip and
the Active state; start_skips_system_tun_when_app_owned runs start() and
asserts no named system device is created.
Rename the Ethernet per-interface config flag from discovery to listen,
so the receive/transmit toggle pair reads as the symmetric announce
(transmit) / listen (receive) neighbor-beacon vocabulary. The old
discovery: key is still accepted via a serde alias, so deployed configs
load unchanged; to_yaml re-emits it under the canonical listen: name.
Marked deprecated for removal at the v2 cutover.
Updates the config field + accessor, the transport listen_enabled local,
the one struct-literal test consumer, the chaos sim config generator,
packaged fips.yaml examples, and the classified operator-facing docs
(ethernet neighbor-beacon subsystem prose; the generic Transport
discovery capability prose is left unchanged). Adds a compat parse test
asserting the legacy alias, the new key, and that deny_unknown_fields
still rejects unknown keys. Behavior-neutral.
Mirror the ethernet neighbor rename in the BLE transport: the internal
peer-detection buffer becomes NeighborBuffer (from DiscoveryBuffer) and
the module is renamed discovery -> neighbor. The BlueR/bluez API terms
(DiscoveryFilter, set_discovery_filter) and the BLE advertise/scan
mechanism vocabulary are unchanged, as is BleConfig. Behavior-neutral.
Rename the ethernet link-local neighbor-beacon subsystem from the
overloaded "discovery" vocabulary to a neighbor umbrella. The beacon
frame vocabulary is retained (build_beacon/parse_beacon/BEACON_SIZE/
FRAME_TYPE_BEACON/FRAME_TYPE_DATA); only the subsystem and buffer
identifiers change: DiscoveryBuffer becomes NeighborBuffer,
discovery_buffer becomes neighbor_buffer, and DISCOVERY_VERSION becomes
BEACON_VERSION (wire value 0x01 unchanged). Config toggles are left for
a follow-up commit. Behavior-neutral.
The module is gated target_os="macos" (not the broader Darwin/iOS family),
so the name now tracks the cfg and matches the *_macos.rs file convention
(io_macos.rs). Drops the redundant inner #![cfg(target_os="macos")] (the
decl gate already covers it) and corrects a stale top comment that claimed
the module stays visible on Linux — it is macos-decl-gated, so it never was.
Mechanical rename; no logic change.
ConnectedPeerSocket and PeerRecvDrain are node/peer-side logic: the Transport
trait never touches them, ActivePeer stores them, and node's encrypt worker
drives them. They only happened to live under transport/udp. Relocate the
handle types to a new src/peer/connected_udp/ module (socket.rs + drain.rs),
which the node handler and encrypt worker reach via node -> peer (no new edge;
a node home would have forced a peer -> node cycle).
The udp transport keeps only the kernel-construction seam: open_connected_fd,
now folded into udp/io.rs (the byte-layer home) behind a linux/macos-gated
submodule and re-exported as transport::udp::open_connected_fd. The node
handler builds the fd through it and adopts it via ConnectedPeerSocket::from_fd.
Behavior-neutral: no wire/config/metric/log change; the per-packet hot path
(bare-RawFd send_batch_gso/raw) is untouched. Preserves the Arc multi-owner
contract, the drop-drain-before-socket ordering, and the drain's detach-on-Drop
deadlock avoidance. Reconciles the old cfg(unix)/any(linux,macos) double-gate
onto the single any(linux,macos) predicate.
Pulls the connected-UDP socket construction (socket/REUSEADDR/REUSEPORT/
BUFFORCE/bind/connect + darwin tuning) out of ConnectedPeerSocket::open into
a pub(crate) open_connected_fd returning an OwnedFd; open() now delegates and
adopts the fd. Error paths still close the fd via the temporary's Drop; the
success tail transfers ownership through OwnedFd. Behavior identical. Prepares
the fast-path handle types to move to the peer module while the socket
construction stays with the udp transport.
Moves the inline TcpConnection/ConnectingEntry structs, the Direction
enum, and the ConnectionPool/ConnectingPool type aliases out of the
1147-line tcp/mod.rs into a dedicated pool.rs, matching the canonical
per-transport layout. Struct fields are pub(crate) so mod.rs can still
construct and read them across the module boundary. Pure relocation; no
logic change.
Moves parse_mac_string into ethernet/addr.rs and re-exports it at the
ethernet module root so the ethernet::parse_mac_string path stays
byte-identical for its one external consumer (zero churn there). Its
unit tests stay in mod.rs, calling through the re-export. Pure
relocation; no logic change.
Normalizes the ethernet transport onto the canonical byte-layer name
(io.rs), including the per-OS files io_linux.rs/io_macos.rs and their
#[path] wiring. Pure file rename plus module-path and doc-comment
updates; no logic, wire, config, metric, or log change.
Normalizes the udp transport onto the canonical per-transport module
layout (ble is the reference: io/pool/addr/stats). Pure file rename plus
module-path updates at the use sites; no logic, wire, config, metric, or
log change. Behavior identical.
The Nym transport was a near-clone of the Tor transport's outbound
SOCKS5 path. Extract the shared logic into src/transport/socks5/ so both
transports drive one implementation instead of two maintained copies:
- share one SOCKS5 mock server between the tor and nym tests
- extract the common send/receive/connect counters into a shared
ProxiedStatsBase (snapshot structs and emitted metrics unchanged)
- add a shared Socks5Dialer that collapses all six connect variants;
the sole dialing difference (tor's per-destination circuit-isolation
auth vs nym's no-auth) is an enum on the dialer
- route both tor and nym dialing through the shared dialer
- share the proxied connection pool, generic over a per-connection meta
type that carries tor's inbound/outbound direction counting (nym uses
the unit type)
- share the proxied receive loop
Behavior-neutral: no wire-format, config-key, emitted-metric, log, or
error-variant change. Tor keeps its control-port, inbound/onion, and
directory surface and its own address validation.
The FMP frame-boundary reader lived in transport/tcp/stream.rs, but the
Tor and Nym transports both reached across module boundaries to
'use crate::transport::tcp::stream::read_fmp_packet', a layering smell:
the reader is a shared stream-framing utility, not a TCP-private one.
Move the file to transport/framing.rs and repoint the tcp/tor/nym use
sites, removing the tor->tcp and nym->tcp dependencies. Behavior
unchanged.
TcpStats and TorStats each carried an identical pair of pool_inbound/
pool_outbound atomics plus the same five record_pool_* / pool_inbound_count
methods over them. Move the counter logic into a shared PoolCounters
struct (new transport/stats_common.rs) embedded as a 'pool' field in both.
The public record_pool_* methods stay as thin delegators so all call
sites and the flat pool_inbound/pool_outbound snapshot fields are
unchanged; only the duplicated atomic bookkeeping is now single-sourced.
EthernetStatsSnapshot derived only Clone/Debug/Default, unlike every
other transport's *StatsSnapshot which also derives Serialize. That gap
forced a hand-rolled serde_json::json!{} arm in TransportHandle::
transport_stats() that re-listed all ten fields by hand. Add the
Serialize derive and collapse the arm to the same one-line
serde_json::to_value(...) form the other transports use. The emitted
JSON keys and values are unchanged.
Relocate the overlay peer-rendezvous subsystem out of the overloaded
src/discovery/ tree into two focused, independent homes: src/nostr/
(relay-mediated overlay endpoint advertise/resolve/auto-mesh plus NAT
traversal) and src/mdns/ (link-local DNS-SD rendezvous). The two
subsystems are independent, so they get separate homes rather than
sharing one.
Drop the ambiguous "Discovery" stem from their identifiers in favor of
"Rendezvous": NostrDiscovery -> NostrRendezvous, LanDiscovery ->
LanRendezvous, and the matching config, policy, field, and method names.
The former src/discovery.rs handoff types (EstablishedTraversal,
BootstrapHandoffResult, the punch-packet helpers) fold into
src/nostr/handoff and stay reachable via the crate-root re-exports.
Pure relocation and rename: no logic, wire-format, config-key, metric,
or tracing-target changes. The operator-facing node.rendezvous.nostr.*
and node.rendezvous.lan.* config keys and the fips-overlay-v1 advert
namespace are byte-identical. cargo fmt/build/clippy clean; lib test
suite 1547 passing (baseline unchanged).
The connect_refused stat counter (the Refused line in fipstop) was
defined but never incremented: every SOCKS5 connect failure recorded
socks5_errors instead, so the counter sat at zero and the operator-facing
gauge was permanently misleading. Both the synchronous connect path and
the background connect_async task now count a genuine SOCKS5 REP=0x05
refusal as connect_refused and every other failure as a socks5_error,
distinguishing them precisely via tokio_socks::Error::ConnectionRefused.
Extends the mock SOCKS5 server with a configurable reply code and adds
two tests covering the refused and general-failure paths.
Add an outbound-only Nym mixnet transport that tunnels FMP peer links
through a local nym-socks5-client SOCKS5 proxy into the Nym mixnet. It
structurally mirrors the Tor SOCKS5 transport (connection pool,
connect-on-send background promotion, FMP-v0 framing reused from TCP)
with the onion, inbound-listener, and control-port machinery removed.
Wires the transport through the full TransportHandle dispatch, NymConfig
(standard transport-instance pattern), and node instantiation, and
surfaces its counters in fipstop. Includes a mock SOCKS5 harness and unit
coverage for the address-parsing paths.
Also adds an isolated single-container example
(examples/sidecar-nostr-mixnet-relay/) demonstrating FIPS peering across
the mixnet end to end. No new crate dependencies: tokio_socks, socket2,
and futures are already pulled in by the Tor transport.
Reworks the fipstop TUI across its rendering, the control read surface it
draws from, and its interaction model, on a machine-verified base.
Test infrastructure:
- Add a ratatui TestBackend snapshot harness (testkit + snapshots
modules) that renders any ui::draw_* into an in-memory Buffer from
canned show_* JSON and asserts the text grid plus per-cell style.
Layout, columns, alignment, labels, grouping, and colour are now
checkable under cargo test; every render below ships a snapshot.
Control read surface (each new field emitted byte-identically on the
live and off-loop builders, published once from the tick, with schema
fixtures regenerated and the parity asserts holding):
- show_status: effective persistence (persistent || nsec.is_some());
root and is_root; and a per-configured-transport-type peer-count map
in which idle-but-configured types stay visible at zero.
- show_peers: per-peer effective_depth (depth + link_cost, the value
evaluate_parent ranks on), null when unmeasured or coordless so
fipstop never recomputes it.
- show_tree: root_npub, resolved once daemon-side (self when root, an
attested peer npub, or an identity-cache hit).
- show_bloom: the last-actually-sent uptree filter fill ratio and
subtree estimate, null for a root or before the first announce.
- show_mmp: session-layer srtt, loss, and etx trend labels.
Rendering:
- Display a 6-byte non-UTF-8 TransportAddr as a colon-separated MAC at
the type layer, so daemon logs, fipsctl, and JSON consumers all
benefit; non-6-byte payloads stay bare hex.
- Right-justify the Bloom Peer Filters numerics into aligned fixed-width
columns, render the Routing panes through a kv_lines helper that shares
one value column across a key-value group, and right-justify the Graphs
by-peer summary columns.
- Truncate an over-long peer name (the npub shown when no friendly name
exists) in the Tree, Bloom, and MMP peer lists so it no longer runs
into the next column.
- Group the Peers table by role (parent, then STP children, then other)
and render it as a full grouped view with styled group labels and
blank separators; the selection stays a peer index and the cursor only
ever lands on a peer row. Apply the same role grouping to the Tree and
Bloom peer lists, joining each peer's role from the peers view by node
address.
- Show min in the Graphs plot titles, rest a steady non-zero metric on
the baseline as a row of dots, render a genuine zero as an empty plot,
and keep a distinct no-data placeholder.
- Replace the metric-by-peer grid, which squeezed plots to nothing once
peers overflowed, with a master/detail Graphs view: a scrollable
per-peer summary list that expands (Enter) to a full-pane btop plot,
with up/down to flip peer, n/N to switch statistic, m to cycle mode,
and Esc to return.
- Put inline colored trend arrows on the Link and Session MMP values
(drawn only on a rising or falling trend, with a fixed blank slot when
stable so the value columns stay aligned), via a shared helper.
- Cycle column sorting on the Link MMP, Session MMP, and Graphs by-peer
tables (one key cycles the active column, another toggles direction),
with the active column marked in each table's header.
- Render the new daemon-surfaced fields: the dashboard root line (a
self-is-root marker, otherwise a truncated root hex), a
transports-by-type line, and an "approx. mesh estimate" line; an
effective_depth column and lines on the Peers, peer-detail, and Tree
sites from the single daemon derivation, showing a dash placeholder
when unmeasured rather than a misleading zero; the full Tree root hex
plus an Npub line; and the Bloom uptree fill and subtree-estimate lines.
Interaction model:
- Add a declarative keybinding registry keyed by (Tab, UiMode) that both
the context footer and the ? help overlay render from, so the two
cannot drift; a test asserts every registry key has a dispatch handler.
- Add a modal ? help overlay, and a context-aware footer that shows the
current state's actions first, drops global hints when the terminal is
narrow, and always keeps a Help affordance as the overflow path.
- Generalize per-pane focus and scroll state on App, wired across the
Tree, Filters, Routing, and MMP tabs (f cycles pane focus and the
focused pane scrolls instead of clipping its overflow); on the MMP tab
the column sort acts on the focused pane. Esc deselects the active row
when no detail is open (detail-close still takes priority).
- Add a Del-disconnect confirmation modal naming the peer, the only
state-mutating action, issuing the control-socket disconnect on confirm
and noting that the peer stays disconnected until manually reconnected.
The per-transport TCP inbound cap was hardwired to 256 and never read
node.limits.max_connections, so raising max_connections was a silent
no-op for inbound TCP. Resolve the effective cap with precedence:
explicit per-transport max_inbound_connections, then node-wide
max_connections, then the built-in default of 256. Established peers
remain bounded node-wide by add_connection, so deriving the per-transport
raw-accept ceiling from max_connections does not admit more real peers
across multiple transports.
Add effective_max_inbound on the TCP transport with a node_max_connections
setter wired from create_transports, plus a precedence unit test.
Brings the maint-line OR-union mesh-size estimator fix and the
per-peer / capacity-cap log-level demotions forward to master.
Conflict resolution: compute_mesh_size resolved to master's config()
accessor form carrying maint's OR-union rewrite (drop the stale summing
`total`); the log-level demotions auto-merged into master's handler
versions. The equivalent master-only log "connected UDP socket installed"
(connected_udp.rs, a file that does not exist on maint) was demoted
info -> debug as part of this merge so the connected-UDP path matches the
rest of the per-peer lifecycle logging.
On a saturated public-mesh node the connection-lifecycle and capacity-cap
events fire continuously and drown out the genuinely notable INFO/WARN
lines. Demote them to debug and drop a redundant duplicate:
- FMP K-bit cutover promotion (encrypted): info -> debug
- "Connection promoted to active peer" (handshake): info -> debug, and
remove the duplicate "Inbound peer promoted to active" line that
shadowed it on the inbound path
- "Peer restart detected" (handshake): info -> debug
- "Peer removed and state cleaned up" (dispatch): info -> debug
- "Rejecting inbound TCP connection (max_inbound_connections reached)"
(tcp): warn -> debug
- "Congestion detected, CE flag set on forwarded packet" (forwarding):
warn -> debug
- "Removing peer: link dead timeout" (mmp): warn -> debug
These are expected, high-frequency conditions on a busy public node (new
and reconnecting peers, ECN CE marking, the inbound connection cap, and
link-dead churn), not operator-actionable signals.
The transport layer used Mutex::lock().unwrap() at ten sites across the
UDP, BLE, and Ethernet code. A std mutex poisons if a thread panics
while holding it, after which every lock().unwrap() on that same mutex
also panics, turning one fault into a cascade. These critical sections
only perform short HashMap/Vec operations on locally constructed values
and are not reachable from peer input, but the idiom is fragile against
any future in-section panic. Replace each with
lock().unwrap_or_else(|e| e.into_inner()), which recovers the guarded
data and removes the cascade with no new dependency and no call-graph
change.
Also replace four self.local_addr.unwrap() calls in the UDP start and
adopt paths with a sentinel fallback. The value is provably set just
above each log line today, but the unwrap is brittle against a future
reordering; logging an unbound sentinel is harmless and cannot panic.
Add a Loopback variant to TransportHandle backed by an unbounded
in-process channel and a shared address-to-receiver registry, so
node-level multi-node tests deliver packets directly between nodes
instead of over real localhost UDP sockets. This removes the kernel
UDP receive-buffer overflow that dropped handshake packets when many
tests ran in parallel under CPU contention, and lets the large-network
convergence tests run reliably in the default suite again (their
parallel-load ignore markers are removed).
The new transport and its enum variant are cfg(test)-gated, so the
daemon build is unaffected.
PeerRecvDrain::drop previously called std::thread::join on the worker
thread synchronously. The worker uses packet_tx.blocking_send on a
tokio mpsc Sender, which internally parks the worker via
tokio::block_on on the same current_thread runtime that drives
rx_loop. Calling join from inside remove_active_peer (which runs on
the runtime thread, the runtime's sole driver) created a circular
wait:
- rx_loop blocks in libc futex via Thread::join
- the worker being joined cannot observe the stop flag because the
runtime that polls it is the very thread now blocked joining it
- all other PeerRecvDrain workers park on the same runtime via
block_on, so a single peer's removal wedges every worker on the
daemon
The /proc snapshot from a production wedge showed exactly this
shape: 107 of 108 threads in futex_do_wait, 101 of them named
fips-peer-drain. fipsctl became unresponsive (EAGAIN on control
socket), SIGTERM was ignored, and Docker SIGKILLed the container
after the 10 s grace period. Two confirmed wedges on the public
test deployment (52 min and 23 min uptime), plus a third on the
admission-gate-Msg2-silent-drop build at 2 min 21 sec — all ending
with the identical "Peer removed and state cleaned up
tree_changed=false" final log line preceding total silence.
Fix: detach the std::thread instead of joining. The stop flag plus
self-pipe write already signal the worker to exit; the worker's
kernel-level libc::poll inside the drain loop sees the wake, checks
the flag, exits, and the OS reclaims the thread state independently
of the JoinHandle being dropped.
The trigger was statistically amplified by aggressive multi-npub-
from-one-NAT peer reconnect patterns at the moment of the 30 s
link-dead-timeout peer-removal, but not bounded to them. Any
peer whose disconnect happens with the per-peer drain worker
parked in block_on can fire the bug. The admission-gate work
that landed earlier in this branch line compressed more handshake
work per rx_loop tick, increasing the rate at which workers are
parked in block_on and so reducing time-to-wedge — but the
underlying bug pre-dated the admission gate and pre-dated this
fix branch.
The deployed wedged daemon is mitigated operationally by blocking
the trigger IP at the host firewall; this commit removes the bug
class entirely.
Add per-direction pool_inbound/pool_outbound counters to TcpStats and
TorStats, updated at every pool-insert, receive-loop-exit, transport-stop,
and send-failure removal site. Compare the max_inbound_connections cap
against pool_inbound rather than the combined pool length, so outbound
connect-on-send connections no longer consume the operator-facing inbound
budget. The configuration field name and operator semantics are preserved;
only the cap-check comparison and accounting change.
Moves both AEAD layers (ChaCha20-Poly1305, one round per layer per
packet) plus the sendmsg syscall off the rx_loop task onto a per-shard
worker pool, adds per-peer connect(2)-ed UDP with SO_REUSEPORT, and
uses Linux UDP GSO (sendmsg+UDP_SEGMENT — kernel splits one super-skb
into N on-the-wire datagrams in a single TX-stack walk) when packets
in a batch are uniform-size. Same kernel primitive WireGuard's
in-kernel module and BoringTun use to hit 2.5–3.2 Gbps single-stream.
Single TCP stream on a 5-node docker-bridge mesh, 5 x 15 s x P=1:
A→D: 1379 → 2708 Mbps (1.96x, RTT +0.12 ms)
A→E: 1394 → 2663 Mbps (1.91x, RTT +0.11 ms)
E→A: 1406 → 2624 Mbps (1.87x, RTT +0.19 ms)
Static-peer pairs only — every CoV under 3%, 0 outliers, 0% ICMP
loss. The ~+100 µs RTT is the worker queue handoff cost; AEAD +
sendmmsg now run on a separate core in exchange.
What lands:
- src/node/encrypt_worker.rs: std::thread + crossbeam_channel
workers; hash-by-destination dispatch pins a TCP flow to one
worker so wire ordering is preserved; per-worker sendmmsg(2)
batching up to 32; Linux uses sendmsg(2)+UDP_SEGMENT when
packets in a group are uniform-size.
- src/node/decrypt_worker.rs: receive-side mirror. Each shard owns
its session's recv cipher + replay window in a thread-local
HashMap (no shared RwLock/Mutex). Sessions are handed off at
promote_connection and re-registered on K-bit flip / rekey
cutover.
- src/node/handlers/session.rs try_send_session_data_pipelined:
FSP+FMP both seal in-place in the worker on one wire-buffer
alloc; no intermediate inner_plaintext / fsp_payload Vecs.
- src/transport/udp/connected_peer.rs + peer_drain.rs: per-peer
connect(2)-ed UDP socket with SO_REUSEPORT (set on the listen
socket too — without that, EADDRINUSE on activation and every
packet falls back to the wildcard path); the worker sends with
msg_name=NULL and the kernel uses its cached 5-tuple. Tick-
driven activation in handlers/connected_udp.rs, idempotent.
- src/transport/udp/mod.rs: mem::replace the recvmmsg backing buffer
instead of buf.to_vec() per packet — single pointer swap, no
MTU-sized memcpy.
- src/protocol/link.rs SessionDatagramRef: zero-copy borrowed view
used by handle_session_datagram for the bulk local-delivery
path; handle_session_payload takes the borrowed payload
directly (no payload[35..].to_vec()).
- src/transport/mod.rs TransportAddr::from_socket_addr: collapses
the two-alloc from_string(addr.to_string()) pattern to one.
- src/node/handlers/rx_loop.rs: decrypt-fallback drain promoted
ahead of packet_rx in the select! (TCP ACK starvation fix);
interleaved fallback drain every 32 packets inside the rx burst
loop.
- noise::Session: send_cipher_clone / recv_cipher_clone /
recv_replay_snapshot_owned / take_send_counter / accept_replay
so off-task workers can hold a cloned cipher + reserved counter
while the dispatcher keeps replay/counter sequencing serial.
CipherState::cipher_clone returns a refcount-bumped LessSafeKey.
AsyncUdpSocket: AsRawFd so workers issue raw sendmmsg / sendmsg
without going through the tokio reactor.
- Worker pool sizing: both default to num_cpus, overridable via
FIPS_ENCRYPT_WORKERS=N / FIPS_DECRYPT_WORKERS=N. Per-peer
connected UDP can be disabled via FIPS_CONNECTED_UDP=0.
- src/perf_profile.rs: optional per-stage timing reporter under
FIPS_PERF=1 (or FIPS_PIPELINE_TRACE=1). Off by default; zero
overhead when disabled.
- All cfg(unix)-gated. Windows continues on the existing tokio-
based send/recv.
Decrypt worker session lifecycle:
- Node::unregister_decrypt_worker_session mirrors the existing
register helper. Wired at the two natural sites that already
iterate peers_by_index: the rekey drain-completion block in
handlers/rekey.rs (drops the worker entry for the old our_index
once the drain window has expired and the cache_key is
unreachable to any in-flight OLD-K packet), and remove_active_peer
in handlers/dispatch.rs (drops the worker entry for each of the
four index slots: current, rekey, pending, previous). Only
our_index is normally registered; unregister_session is fire-
and-forget for missing entries, so calling unconditionally on
all four slots is correct and bounds the cleanup without per-
slot accounting. Without these callers the per-worker sessions
HashMap and the Node's decrypt_registered_sessions set would
grow monotonically per rekey on long-lived peers.
Testing:
- testing/static/scripts/bench-multirun.sh: multi-run iperf3 +
ping bench. N reruns (default 5), median / min / max / CoV % /
per-run outlier flag, avg ping RTT, ICMP loss %, TCP retransmit
total. Plain client→dest labels + topology header. Pre-bench
peer-convergence check (FIPS_BENCH_CONVERGE_SECS, default 15);
per-path route verification via stats.bytes_sent deltas — fails
fast if traffic exits via a non-static-peer link.
- testing/static/docker-compose.yml: passes FIPS_ENCRYPT_WORKERS /
FIPS_DECRYPT_WORKERS / FIPS_PERF through to containers for A/B
benchmarking without rebuilds.
- testing/static/scripts/iperf-test.sh: same plain client→dest
labels + topology header (was multihop/direct/N hop, which
conflated topology distance with on-wire path).
- .config/nextest.toml: synthetic UDP node tests serialized
through a max-threads=1 test group. Localhost handshakes drop
on shared CI runners under parallel load; one-at-a-time keeps
assertions reliable.
- src/node/tests/spanning_tree.rs: repair_missing_edge_handshakes
— retries up to 5 times for synthetic edges whose msg1 was
dropped, with a drain after each edge retry instead of after
each attempt's full burst.
- src/node/decrypt_worker.rs::tests: two unit tests asserting
WorkerMsg::UnregisterSession removes the worker-thread session
HashMap entry (handle_msg_unregister_session_removes_entry) and
is a no-op for never-seen cache_keys
(handle_msg_unregister_session_idempotent_on_unknown_key), which
is the safety invariant the unconditional unregister calls at
the four index slots in remove_active_peer rely on.
- src/node/encrypt_worker.rs::unix_tests
pipelined_send_wire_layout_roundtrips_canonical_decoders: mirrors
the encoder geometry of try_send_session_data_pipelined (no
coords, the common established-session path), runs the worker's
real seal + send via flush_direct_batch_sync, and decodes the
resulting wire packet using only canonical receive-side decoders
(EncryptedHeader::parse, SessionDatagramRef::decode, FSP header
parse, noise::open). Any divergence between the hand-rolled
encoder offsets (fsp_aad_offset, fsp_plaintext_offset) and the
decoders fails at one of the parse / open / decode steps before
the inner-plaintext assertion fires. Complements the existing
fsp_preseal_runs_before_outer_fmp_seal test which covers the
seal-ordering invariant with synthetic headers but does not
exercise the wire-layout invariant.
CHANGELOG.md [Unreleased] # Changed entry added describing the
worker-pool threading model, hash-by-destination dispatch,
sendmmsg/UDP_GSO, per-peer connected UDP, the operator-facing env
vars, and the bench numbers above.
Cherry-picks from mmalmi/master (paths translated from
crates/fips-core/src/ to src/): 9b7c723, 0deb5cb, 13f7339, e036c0e,
3740a68, 3792f83, 8510193, 4910b07, e53f545, e4e2896, 5fe4af5,
1d01ada, 8c37008, e12469e, 6eb2860.
Co-authored-by: Johnathan Corgan <johnathan@corganlabs.com>
The non-Linux test build was emitting warnings from code that is
intentionally platform-specific: the nftables firewall parser is
Linux-only, the utun address-family helper is only used in macOS
TUN paths, and one macOS Ethernet test module trips a clippy
layout lint. These warnings made focused test runs noisy and
encouraged bundling unrelated warning fixes into behavioral PRs.
- Gate the firewall parser dead-code allowance to non-Linux
targets, where the parser is compiled but not used.
- Mark the macOS utun helper and long TUN reader entry point with
narrow allowances.
- Rewrite the small MAC-copy loop to satisfy clippy and mark the
macOS Ethernet test module layout explicitly.
No runtime behavior change.
- Borrowed SessionDatagramRef decoder is used in the forwarding
handler so local delivery and coordinate-cache warming no longer
allocate or copy the session payload. The owned SessionDatagram is
materialized only when re-encoding for the next hop.
- Owned SessionDatagram::decode is reimplemented as Ref::decode +
into_owned, so the two decoders cannot drift.
- recvmmsg / recvmsg_x (Linux + macOS) receive loop moves each filled
slot buffer into ReceivedPacket via mem::replace instead of cloning
it; a fresh empty buffer is installed for the next syscall.
- TransportAddr is formatted directly from the SocketAddr without
going through an intermediate String.
Focused decode bench: ref 1.6 ns/op vs owned 34.7 ns/op (21.4x).
End-to-end iperf is neutral as expected for a ~30 ns saving per
packet.
Unit tests added:
- test_session_datagram_ref_decode_borrows_payload (verifies the
payload slice pointer equals the input slice's offset 35, a real
zero-copy invariant guard against accidental future to_vec)
- bench_session_datagram_decode_owned_vs_ref (ignored, run with
--ignored --nocapture)
- test_transport_addr_from_socket_addr
The Linux recv path drains up to 32 datagrams per kernel wakeup via
recvmmsg(2), amortising the per-syscall + per-task-wakeup cost across
the burst. macOS still fell through to single-packet recv_from, so
the same overhead capped inbound rate on Apple builds.
Add an equivalent batch path for Darwin using recvmsg_x(2). It is a
xnu-private syscall (not in the public SDK) but is the canonical
amortisation primitive on macOS — same shape used by quinn-udp for
the same reason. ABI is the public msghdr layout plus a trailing
msg_datalen (per-datagram bytes-received output), declared via
`unsafe extern "C"` against a local repr(C) `msghdr_x`.
Same `(count, kernel_drops)` contract as the Linux `recv_batch`. macOS
has no SO_RXQ_OVFL equivalent, so `kernel_drops` is always 0 — the
1Hz `sample_transport_congestion()` detector simply sees no kernel
drop signal on Apple hosts (it already tolerates that, since the
field has been 0 there pre-batching too).
cmsg buffer is intentionally null: we never consume ancillary data on
this path, and quinn-udp documents that `recvmsg_x` does not overwrite
`msg_controllen` on macOS 10.15+ (zeroed init is the only safe state).
The udp_receive_loop dispatch widens from cfg(linux) to
cfg(any(linux, macos)); the per-packet recv_from path is now used
only on the remaining unix targets (BSDs etc.) and Windows.
Add test_burst_recv_batch exercising 10 in-flight datagrams to
verify per-datagram boundaries and arrival order across the batch.
Add an ignored bench_udp_recv_amortization measuring recv-side
syscall amortization across 1/2/4/8 sender threads on dedicated
blocking std threads (kernel rx queue stays saturated regardless of
tokio scheduling). Sample numbers on aarch64-apple-darwin (100B
payloads, 3s windows):
senders=1: recv_from 398k pps recv_batch 432k pps 1.09x
senders=2: recv_from 353k pps recv_batch 608k pps 1.72x
senders=4: recv_from 322k pps recv_batch 503k pps 1.56x
senders=8: recv_from 353k pps recv_batch 515k pps 1.46x
Gate the Linux-only IpAddr import in control::listening behind a
cfg(target_os = "linux") so the macOS test build is warning-clean
now that test code paths there compile.
The UDP recv loop drained the kernel queue one packet per recvmsg(2).
Each call paid full per-syscall + per-task-wakeup overhead (~50us avg
including a futex-based scheduler hop), so under sustained load the
loop ran at one rx event per scheduler quantum — the dominant cap on
inbound packet rate.
On Linux, switch the steady-state path to recvmmsg(2) with a 32-packet
batch. A single readable() wakeup drains up to 32 datagrams in one
syscall before yielding back to the reactor. Stack-allocated mmsghdr
arrays sized to a module-level `BATCH_SIZE` constant.
`SO_RXQ_OVFL` is sampled once per batch off the cmsg chain of `msgs[0]`
and plumbed through `AsyncUdpSocket::recv_batch` as `(count, drops)`.
The counter is socket-wide and monotonic, so a single sample per batch
gives the 1Hz `sample_transport_congestion()` detector ample fresh
values under load (one batch = up to 32 datagrams). Cost is one
stack-allocated CMSG_SPACE(4) buffer + one CMSG_FIRSTHDR walk per
batch syscall.
macOS / Windows fall through to the per-packet recv_from loop —
recvmmsg is Linux-specific and the per-packet API is fast enough on
those platforms for now (recvmsg_x for Darwin can be added later).
The slice-array build also drops the `MaybeUninit::uninit().assume_init()`
+ `transmute` pair for `std::array::from_fn` over a single shared
`backing.iter_mut()` — same disjoint mutable borrows, no `unsafe`.
The Ethernet data frame format is `[type:1][length:2 LE][payload]`,
so the per-link payload MTU is the interface MTU minus 3 bytes,
not minus 1. The 2-byte length field is required to trim NIC
minimum-frame padding before AEAD verification.
The implementation in src/transport/ethernet/mod.rs already uses
saturating_sub(3) correctly; only the rustdoc on the effective_mtu
field and the EthernetConfig.mtu field's documentation lagged behind.
No behaviour change.
Add #[cfg(target_os = "macos")] unit tests catching macOS-specific
regressions before they reach the macos-latest GitHub runner.
src/upper/tun.rs: surgical refactor extracts the inline
AF_INET6_HEADER constant into module-scope helpers
utun_af_inet6_header() (encode) and parse_utun_af_prefix() (decode
inverse for round-trip testability). TunWriter::run now calls the
helper instead of the inline const; behavior unchanged. Six new
tests pin the AF=30 constant matching Darwin, big-endian byte order,
encode/parse round-trip, short-buffer rejection, minimum header
acceptance with trailing payload, and no-panic on garbage bytes.
src/transport/ethernet/socket_macos.rs: existing test mod already
covered bpf_wordalign and 5 parse_next_frame cases. Three new tests
fill genuine gaps: struct layout pin against kernel ABI, caplen-
overrun rejection, full Ethernet header round-trip via parse.
Existing tests pre-exist; only adding to the same #[cfg(test)] block.
The Nostr overlay advert publisher serialized `transport: tor`
endpoints as a bare `<onion>.onion` hostname with no port. The Tor
address parser requires `<host>:<port>` form and rejected the bare
shape with `expected host:port`. Any peer receiving a Tor-only
advert went into a persistent retry-fail loop on jittered backoff
until the advert aged out of the discovery cache. The bug had been
latent for as long as Tor adverts have been published on Nostr, and
was masked in deployments where every node also advertised a
non-Tor transport (peers fell through to the working endpoint).
Surfaced first on a deployment where Tor was the only advert path.
Publisher now emits `<onion>.onion:<port>` using a new
`transports.tor.advertised_port` config field that defaults to 443,
matching the Tor `HiddenServicePort 443 127.0.0.1:<bind_port>`
convention. Operators whose torrc uses a non-default virtual port
can override.
Adds a unit test that pins the publisher/parser contract: formats
the advert exactly as the publisher does and asserts `parse_tor_addr`
accepts the result; asserts the bare-onion form (the bug) does not
parse, catching any future regression that drops the port again.
Parser is unchanged (already correct).
Three related UDP transport changes that together close a real gap in
the v0.2.x "this transport accepts inbound" assumption:
- outbound_only (default false). When true, the transport binds a
kernel-assigned ephemeral port (0.0.0.0:0) regardless of the
configured bind_addr, refuses inbound handshakes (Transport trait's
accept_connections() returns false), and is never advertised on
Nostr regardless of advertise_on_nostr. Lets a node participate in
the mesh as a pure client — initiate outbound links without
exposing an inbound listener on a known port. Also closes the
"loopback bind as outbound-only workaround" trap: a UDP socket
bound to 127.0.0.1 pins 127.0.0.1 as the source IP on outbound
packets, and Linux refuses to deliver such packets out an external
interface — the daemon happily reports "transport started" while
no flow ever reaches an external peer.
- accept_connections (default true). Mirrors the existing
Ethernet/BLE knob. Lets operators run UDP in a "client" posture
(initiate outbound, refuse inbound msg1 from new addresses) without
switching transport. The Node-level handshake gate already carves
out msg1 from peers established on the transport so rekey works
on existing sessions.
- Startup validation: reject `transports.udp[*].bind_addr` set to a
loopback address (127.x.x.x, ::1, localhost) when at least one peer
has a non-loopback UDP address. Replaces the silent "peer link
won't establish" failure mode with a clear error pointing at the
bind misconfiguration. outbound_only is exempt (it overrides
bind_addr to 0.0.0.0:0).
The is_punch_packet-based filter from the previous commit, the
Node-level admission gate landed earlier on master, and these new
config fields together cover the three distinct ways the v0.2.x
"this transport accepts inbound" assumption could break.
Tests: validation truth table (loopback+external rejected,
loopback+loopback ok, outbound_only exempt), is_loopback_addr_str
helper, accept_connections wiring (default, explicit-false,
outbound_only-forces-false), end-to-end ephemeral-bind in the runtime.
1082 tests pass with --features nostr-discovery.
When a UDP hole-punch succeeds in only one direction and the local
side adopts the punched socket, the remote end keeps retrying its
own punch attempt for several seconds. Those retries arrive on the
adopted socket and were forwarded to the FMP rx handler, which
parsed the first byte (0x4E from PUNCH_MAGIC's "NPTC" big-endian
encoding) as FMP protocol version 4 and emitted "Unknown FMP
version, dropping" once per probe. The probe stream contaminated
post-adoption handshake logs and added timing pressure during the
handshake window.
Add a transport-level filter in udp_receive_loop that silently
drops any datagram whose first 4 bytes match PUNCH_MAGIC or
PUNCH_ACK_MAGIC. Filter applies to all UDP transports, not just
adopted ones — the magic values cannot collide with valid FMP
frames (FMP version 4 is not assigned, and the protocol's
versioning is wire-format breaking), so universal filtering is
safe and removes any "is this an adopted socket" branching.
Move PUNCH_MAGIC / PUNCH_ACK_MAGIC and the new is_punch_packet()
helper from the `nostr-discovery`-gated submodule up to
crate::discovery (unconditionally compiled) so the UDP transport
can import them without requiring the feature. The
nostr-discovery types module re-exports the constants so the
existing traversal-side imports keep working unchanged.
Test: pushes a probe + ack + real frame through the receive loop
and asserts only the real frame is delivered to packet_tx.
Optional peer discovery and NAT hole-punching path gated behind a new
`nostr-discovery` cargo feature. Nodes publish signed overlay endpoint
adverts to public Nostr relays, consume peer adverts to populate
fallback dial addresses, and use STUN-assisted UDP hole punching with
NIP-59 gift-wrap offer/answer signaling to establish direct UDP paths
between NATed peers. Once a punched socket is up, it is handed into
the existing FIPS UDP transport and the standard Noise/FMP session
stack takes over unchanged.
The cargo feature is in the default feature set
(`default = ["nostr-discovery"]`) so stock builds include it; a
build that explicitly disables default features (or selects a
feature set without `nostr-discovery`) does not link the nostr /
nostr-sdk crates and does not emit a no-op poll in the tick loop.
Runtime behavior is independently gated by
`node.discovery.nostr.enabled`, which defaults to false; if the
config enables Nostr on a non-feature build, startup logs a
warning and continues without it.
== Cargo feature and dependencies
- New cargo feature `nostr-discovery = ["dep:nostr", "dep:nostr-sdk"]`.
Not in the default feature set.
- New optional Linux-only dependencies: `nostr 0.44` (features: std,
nip59) and `nostr-sdk 0.44`. Gift-wrap unwrap is hand-rolled in
`src/discovery/nostr/signal.rs` rather than relying on the SDK's
rumor-author check, which FIPS sidesteps by trusting `seal.pubkey`
exclusively.
== Wire format
Overlay advert event: `kind 37195`, parameterized replaceable
(NIP-01 application-defined replaceable range 30000-39999), with
`d = "fips-overlay-v1"`. The digits visually spell FIPS (7=F, 1=I,
9=P, 5=S); a relay survey confirmed the kind is unused.
Advert content carries the version tag, endpoint list
(`udp|tcp|tor` + addr), optional signal-relay and stun-server
metadata, and `issuedAt` / `expiresAt` timestamps. Endpoint
`addr: "nat"` is the sentinel that triggers traversal on the peer
side. NIP-40 `expiration` tag bounds staleness on permanent
shutdown. Lifecycle relies on parameterized-replaceable
supersession; the daemon does not emit NIP-09 kind-5 deletes —
strict relays (Damus, Primal) race delete-against-replace and can
silently drop the replacement.
Gift-wrapped signal event: `kind 21059`. Punch packets carry magic
values `PUNCH_MAGIC` / `PUNCH_ACK_MAGIC`, a sequence number, and a
16-byte session hash.
== Discovery surface
- `src/discovery.rs` (always compiled)
- `EstablishedTraversal`: bound UDP socket + selected remote +
peer npub + optional transport name/config tuning overrides.
- `BootstrapHandoffResult`: returned on successful handoff —
allocated transport id, local/remote addrs, peer NodeAddr,
session id.
- `src/discovery/nostr/` (`#![cfg(feature = "nostr-discovery")]`)
- `types.rs`: wire and control types described above. `ADVERT_KIND`
constant. `BootstrapError` enumerates failure modes (disabled,
missing advert, missing NAT endpoint, no usable relays, invalid
advert, invalid npub, signal timeout, punch timeout, replay,
STUN failure, protocol, nostr, io, serde, event-parse).
- `runtime.rs`: `NostrDiscovery` coordinator. Owns the shared
nostr-sdk `Client`, subscribes to advert + signal event kinds,
maintains a bounded advert cache and a bounded seen-sessions
replay set, drains `BootstrapEvent::{Established, Failed}` for
the node to consume, exposes `update_local_advert`,
`request_connect`, `advert_endpoints_for_peer`,
`cached_open_discovery_candidates`, and `shutdown`.
- `signal.rs`: NIP-59 gift-wrap encode/decode. Outbound wraps are
built against per-attempt ephemeral keys; inbound events are
unwrapped against the node identity.
- `stun.rs`: RFC 5389/8489 Binding Request client with
XOR-MAPPED-ADDRESS parsing for both IPv4 and IPv6; used only to
observe the initiator's own reflexive address against its
locally configured STUN list (peer-advertised STUN is
informational, never an egress target).
- `traversal.rs`: per-attempt candidate-pair punch planner.
Allocates a fresh `0.0.0.0:0` UDP socket per attempt, enumerates
LAN-private and ULA interface addresses alongside the STUN
reflexive address, schedules probe/ack exchanges at the
configured interval for the configured duration, and picks the
first candidate pair that authenticates end-to-end.
Strategy ordering is Reflexive↔Reflexive first, then LAN, then
Mixed. The STUN-observed pair is the only candidate that's reliable
across arbitrary network topologies; trying it first prevents the
planner from latching onto a misleading host-candidate path before
the reflexive path gets a chance. There is no catch-all
Local↔Local strategy: a previous design that paired every local
host candidate from one side with every local host candidate from
the other could declare success on a one-way reachable asymmetric
L3 path (corporate VPN, Tailscale subnet route, overlapping private
address space), only for the FMP handshake to stall because the
return path didn't match. The legitimate `Lan` strategy still pairs
candidates that share a subnet.
== Configuration surface
`node.discovery.nostr.*` (`NostrDiscoveryConfig`), all `serde(default)`
with `deny_unknown_fields`:
- `enabled` (default false), `advertise` (default true)
- `advert_relays`, `dm_relays`, `stun_servers`: defaults are
`wss://relay.damus.io`, `wss://nos.lol`, `wss://offchain.pub`
for both relay lists, and Google / Cloudflare / Twilio for STUN.
Operators are expected to override for production. Other
verified-working public relays for reference:
`nostr.bitcoiner.social`, `nostr-pub.wellorder.net`,
`nostr.oxtr.dev`, `nostr.mom`.
- `app` (default `"fips-overlay-v1"`), `signal_ttl_secs` (120)
- `policy`: `NostrDiscoveryPolicy::{Disabled, ConfiguredOnly (default),
Open}` — controls whether advert-derived endpoints are consumed
only for peers carrying `via_nostr = true`, or also for
non-configured peers within a budget cap.
- `share_local_candidates` (default false) — when false, the offer's
`local_addresses` list is empty and peers see only the reflexive
address. Enable per-node only for genuinely same-LAN deployments;
off-by-default eliminates the misleading-path failure mode for
the common case where peers are not on the same broadcast domain.
- `open_discovery_max_pending` (64) — caps queued open-discovery
retries; bounded by available outbound slots.
- `max_concurrent_incoming_offers` (16) — semaphore against offer
spam; excess offers are debug-logged and dropped.
- `advert_cache_max_entries` (2048) and `seen_sessions_max_entries`
(2048) — bound memory under ambient relay volume; overflow
evictions are debug-logged.
- `attempt_timeout_secs` (10), `replay_window_secs` (300)
- `punch_start_delay_ms` (2000), `punch_interval_ms` (200),
`punch_duration_ms` (10000)
- `advert_ttl_secs` (3600), `advert_refresh_secs` (1800)
Per-peer and per-transport flags:
- `PeerConfig.via_nostr: bool` — when true (and Nostr is enabled),
advert-derived addresses are appended as fallback dial candidates
after static addresses for that peer.
- `PeerConfig.addresses` is now `serde(default)` and may be empty
when `via_nostr: true`; validation requires at least one of the
two to be present per peer, and the error message names the
peer's npub.
- `UdpConfig.advertise_on_nostr: Option<bool>` and
`UdpConfig.public: Option<bool>` — UDP transports can be
advertised either as direct `host:port` (public = true) or as the
`addr: "nat"` sentinel that triggers rendezvous on the peer side.
- `TcpConfig.advertise_on_nostr` and `TorConfig.advertise_on_nostr`
— TCP and Tor onion endpoints can be advertised as directly
reachable.
- A reserved peer address `transport: udp, addr: "nat"` parses without
special-casing in YAML and routes through the bootstrap runtime.
Cross-field validation (`Config::validate`, called from `Node::new`
and `Node::with_identity`):
- Any transport with `advertise_on_nostr = true` requires
`node.discovery.nostr.enabled = true`.
- Any peer with `via_nostr = true` requires
`node.discovery.nostr.enabled = true`.
- A non-public UDP advert (`advertise_on_nostr = true`,
`public = false` — i.e. `udp:nat`) additionally requires at least
one `dm_relay` and at least one `stun_server`.
Surfaced as `ConfigError::Validation`.
== Node integration
`src/node/lifecycle.rs` is the main integration point.
- At node start (after transports are up, before TUN), if Nostr is
enabled and the feature is compiled in, `NostrDiscovery::start` is
invoked, the initial local overlay advert is built from the live
transport set and published, and the runtime handle is stored.
- The rx tick loop calls `poll_nostr_discovery` (feature-gated both
at method definition and call site), which refreshes the local
advert, drains bootstrap events, adopts established traversals,
schedules retries for failed traversals, and — under `policy:
open` — enqueues outbound retries for non-configured peers
visible in the advert cache, bounded by
`open_discovery_max_pending` and the remaining outbound slots.
- Outbound peer dialing is refactored to `try_peer_addresses`, which
first exhausts the static address list in priority order and only
then appends advert-derived fallback addresses; both lists run
through the same `attempt_peer_address_list` code path. The
`udp:nat` sentinel address triggers `NostrDiscovery::request_connect`
for the peer instead of a direct dial and returns `Ok(())`.
- `build_overlay_advert` walks operational transports, consults
per-instance `UdpConfig` / `TcpConfig` / `TorConfig` (matching by
optional transport instance name), and emits an `OverlayAdvert`
including `signalRelays` and `stunServers` when any UDP endpoint
is advertised as NAT.
- `adopt_established_traversal` is the bootstrap handoff API:
allocates a new `TransportId`, constructs a `UdpTransport` with
the user-supplied (or default) `UdpConfig`, calls the new
`adopt_socket_async` to reuse the punched socket verbatim,
registers the transport in the normal transport map, records it
in `bootstrap_transports`, and calls `initiate_connection` so the
normal handshake path runs. On failure, the transport is stopped
and removed cleanly and the set membership is rolled back.
- On clean shutdown, `NostrDiscovery::shutdown` is awaited so
background tasks stop before transports are torn down. (The
advert is not explicitly retracted; NIP-40 expiration plus the
next refresh from any live publisher supersedes it.)
New `Node` fields:
- `nostr_discovery: Option<Arc<NostrDiscovery>>` (feature-gated).
- `bootstrap_transports: HashSet<TransportId>` — per-peer UDP
transports adopted from NAT traversal, cleaned up via
`cleanup_bootstrap_transport_if_unused` whenever the link,
connection, peer, or pending-connect referencing them is removed.
Retry and error surface:
- `RetryState.expires_at_ms: Option<u64>` — optional absolute expiry
for a retry entry. `pump_retries` drops expired entries with an
info log. Used for open-discovery retries, which expire at two
times the advert TTL.
- New `NodeError::BootstrapHandoff(String)` returned from
`adopt_established_traversal` when the underlying transport
adoption fails or local address discovery fails.
- New `ConfigError::Validation(String)`.
- A small refactor extracts `Node::now_ms()` and reuses it across
lifecycle, rx-loop tick, and timeout bookkeeping.
== UDP transport
`src/transport/udp/`:
- `UdpRawSocket::adopt(std::net::UdpSocket, recv_buf, send_buf)`:
adopts an externally bound socket, makes it non-blocking, applies
the configured buffer sizes (warning if the kernel clamps), and
reports the resulting local address. Preserves the NAT mapping —
no rebind.
- `UdpTransport::adopt_socket_async(std::net::UdpSocket)`: the
`start_async` analogue for an already-bound socket, wiring the
async socket and recv task exactly as the fresh-bind path would.
- `Drop` impl for `UdpTransport`: if a transport is dropped while
still holding a recv task or socket (for example on error
teardown), aborts the task, clears the socket, and emits a debug
log so the cleanup is visible in tracing rather than silent.
== Logging and observability
Default `EnvFilter` demotes third-party relay-pool DEBUG output to
TRACE-only: `nostr_relay_pool`, `nostr_sdk`, and `nostr` are pinned
at INFO when our level is anything below TRACE, and at TRACE when
our level is TRACE — so the raw frames are still reachable when
explicitly asked for. RUST_LOG continues to override completely.
Concise one-line DEBUG events are emitted at the meaningful points
in the discovery / hole-punch sequence:
- `advert: published` (event id, relay count, endpoints, ttl)
- `advert: peer cached` (notify-loop ingress for non-self)
- `advert: resolved` (cache hit / relay fetch outcome)
- `traversal: initiator starting`
- `traversal: initiator STUN observed` (reflexive, local count)
- `traversal: offer sent` (session id, relay count, event id)
- `traversal: answer received` (accepted, reflexive, local)
- `traversal: initiator punch succeeded` (remote addr)
- `traversal: offer received` (responder side)
- `traversal: responder STUN observed`
- `traversal: answer sent`
- `traversal: responder punch succeeded`
Npubs are shortened to `npub1<4>..<4>` and event/session ids to
their first 8 hex characters.
Other operator-facing logs:
- `UdpTransport` adoption and drop paths log at info / debug.
- `adopt_established_traversal` logs at debug on entry and info on
successful return, tagged with peer npub, session id, transport
id, and both socket endpoints, so the bootstrap handoff is
traceable end-to-end alongside the `UdpTransport::drop` log.
- `cleanup_bootstrap_transport_if_unused` logs at debug when the
reference-count check drops an adopted transport.
- `connect_peer` tags its entry `debug!` with `peer_npub` so
downstream STUN, punch, and handshake logs for the same peer
correlate for operators.
- Advert-cache and seen-sessions overflow evictions log at debug so
mis-sized caps are visible under ambient relay volume.
- Gift-wrap unwrap failures on `SIGNAL_KIND` events log at trace
(hot path: fires for every unrelated signal event on the same
relay).
- Traversal-offer handler failures log at debug. Expected conditions
such as punch timeout on symmetric NAT are covered there; real
problems are reported upstream via `BootstrapEvent::Failed`.
- Inbound-offer rate-limit messages name the governing config field
(`max_concurrent_incoming_offers`) and state that the offer was
rate-limited rather than failing.
== Tests
- 18 new unit tests in `src/discovery/nostr/tests.rs` covering advert
encoding, signal envelope round-trip, STUN parsing, punch-packet
codec, and replay-window enforcement. Run under the
`nostr-discovery` feature.
- Config-validation tests in `src/config/mod.rs` covering the three
cross-field invariants and YAML parsing of the full
`node.discovery.nostr` block plus `peers[].via_nostr`, empty
`addresses` with `via_nostr: true`, and a `udp: nat` address.
- `src/node/tests/bootstrap.rs` integration tests that drive a
synthetic traversal (bound UDP socket pair + synthetic peer
identity) through `adopt_established_traversal` and assert the
Noise handshake completes over the adopted socket.
- Punch-planner tests assert reflexive-before-LAN ordering and that
same-LAN scenarios still include the LAN target in the plan.
- `testing/nat/` Docker NAT lab harness:
- Local `strfry` relay, local STUN responder, and one or two
router containers performing `iptables` NAT.
- Node LAN interfaces are provisioned with explicit `veth` pairs
injected into the node and router namespaces so every packet
traverses the router namespace (plain Docker bridges are not
used for the LAN).
- `cone` scenario: both peers behind full-cone-emulation NAT
(SNAT with source-port preservation, inbound DNAT back to the
single LAN host regardless of remote source); asserts UDP
traversal succeeds and link remote addresses are on the router
WAN subnet.
- `symmetric` scenario: `MASQUERADE --random-fully`; asserts UDP
traversal fails and TCP fallback converges over router-
published WAN addresses.
- `lan` scenario: both peers share a LAN subnet; asserts LAN
addresses are preferred over reflexive ones.
- Cleanup tears down all profile-gated services
(`--profile cone --profile symmetric --profile lan`) so no
orphan containers survive a run.
- `testing/scripts/build.sh` builds the Docker test image with
`--features "tui nostr-discovery"` by default so NAT-harness
binaries include bootstrap support.
== CI
- Linux release build and nextest unit-test job both use
`--features "gateway nostr-discovery"` so the feature-gated code
and its unit tests compile and run in CI.
- Three new integration matrix entries (`nat-cone`, `nat-symmetric`,
`nat-lan`) invoke `testing/nat/scripts/nat-test.sh`, collect
`docker compose logs` on failure, and always stop containers.
== Packaging and operations
- `packaging/common/fips.yaml` ships a fully commented
`node.discovery.nostr.*` block, plus documented
`advertise_on_nostr` / `public` examples under the UDP transport,
an `advertise_on_nostr` example under TCP, and a `via_nostr: true`
example under the static peer section with both a direct
`host:port` UDP address and a `udp: nat` fallback.
- `.github/workflows/package-openwrt.yml`: NIP-94 release event
publishes target the new default relay set.
== Documentation
- `README.md`: overlay discovery + NAT traversal moved from
"Near-term priorities" into "What works today".
- `docs/design/fips-intro.md`: rewrites the paragraphs that
previously described Nostr discovery and NAT traversal as future
work; describes the shipped mechanism and the feature gate.
- `docs/design/fips-transport-layer.md`: drops the "(future
direction)" qualifier from the Nostr Relay Discovery section,
expands with the `udp:nat` advertisement and bootstrap handoff
description, and updates the Current State callout.
- `docs/design/fips-mesh-layer.md`: notes that mid-session NAT
rebinding (roaming) and initial NAT traversal (Nostr path) are
distinct mechanisms.
- `docs/design/fips-configuration.md`: documents the full
`node.discovery.nostr.*` surface, including the three resource
caps and `share_local_candidates`.
- `docs/design/fips-nostr-discovery.md`: design and configuration
reference for the shipped mechanism, including the empty-
`addresses`-with-`via_nostr` shorthand.
- `docs/proposals/nostr-udp-hole-punch-protocol.md`: adds an
Implemented status callout, clarifies that the punch socket is
per-peer and per-attempt rather than shared with the application
listener, aligns field names with the shipped JSON
(`sessionId`, `issuedAt` / `expiresAt`, `reflexiveAddress`,
`localAddresses`, `stunServer`), sets the `d`-tag to
`fips-overlay-v1`, names the kind as 37195, and notes that
advertised STUN entries are informational.
- `docs/proposals/README.md`: adds a Status column and marks the
hole-punching proposal Implemented.
- `CHANGELOG.md`: Unreleased > Added entry covering the discovery
path, STUN/punch path, configuration surface, and Docker NAT lab.
Co-authored-by: Johnathan Corgan <johnathan@corganlabs.com>
Drop the `tui`, `ble`, and `gateway` cargo features and replace
them with platform cfg gates. Plain `cargo build` now produces
every subsystem appropriate for the target platform with no
feature flags required.
Motivation:
- `default = ["tui", "ble"]` broke `cargo build` on macOS and
Windows because `ble` pulled in `bluer` (BlueZ, Linux-only).
Every non-Linux packager needed `--no-default-features`.
- The feature flags on `ble` and `gateway` were redundant with
their platform-gated deps (`bluer`, `rustables`). The parallel
gating was inconsistent and error-prone.
- `tui` feature protected against a ratatui binary-size concern
that no longer applies in 2026.
Cargo.toml:
- Remove `tui`, `ble`, `gateway` features; `default = []`.
- Promote `ratatui` to a non-optional top-level dependency.
- Move `rustables` from top-level optional into the Linux
target block, non-optional.
- Split `bluer` into its own target block with
`cfg(all(target_os = "linux", not(target_env = "musl")))`
— BlueZ isn't available on musl router targets and
`libdbus-sys` doesn't cross-compile to musl without pkg-config
sysroot setup.
- Drop `required-features` from the `fipstop` and `fips-gateway`
`[[bin]]` entries.
build.rs:
- Emit a `bluer_available` custom cfg when `target_os == "linux"`
and `target_env != "musl"`, for use in place of the verbose
full predicate in source cfg gates.
Source:
- Replace every `#[cfg(feature = "gateway")]` with
`#[cfg(target_os = "linux")]`. Gateway code works on both
glibc and musl Linux (rustables is fine on musl).
- Replace every `#[cfg(feature = "ble")]` with
`#[cfg(bluer_available)]`. BLE-specific code (BluerIo module,
bluer type conversions, BLE transport instance creation,
resolve_ble_addr) is excluded on musl and non-Linux. Generic
`BleAddr`, `BleIo` trait, `MockBleIo`, and `BleTransport<I>`
still compile on all targets.
- `src/bin/fips-gateway.rs`: always compiled, but `main()` is
gated to Linux. Non-Linux stub exits 1 with a diagnostic.
Existing non-Linux packaging scripts don't ship it, so the
stub binary sits unused.
Packaging and CI:
- Drop `--features` and `--no-default-features` flags from every
packaging script and workflow. Defaults now match each
platform's capabilities.
- AUR `fips-git` automatically aligns with stable `PKGBUILD`
(both build with defaults).
Verified: `cargo build --release` with no flags produces all
four binaries on glibc Linux; all unit and integration tests
pass across Linux/macOS/Windows/OpenWrt (musl) in CI.
Gate platform-specific code behind cfg attributes and add full Windows
support: TUN device via wintun, TCP control socket on localhost:21210,
Windows Service lifecycle (--install-service/--uninstall-service/--service),
CI build and test matrix, and packaging with ZIP builder and PowerShell
service management scripts.
Key changes:
- Cargo.toml: move tun/libc/rtnetlink behind cfg(unix); add wintun and
windows-service dependencies for Windows
- upper/tun.rs: wintun-based TUN implementation with netsh configuration
for IPv6 address, MTU, and fd00::/8 routing
- control/mod.rs: split into unix_impl/windows_impl; Windows uses TCP on
localhost:21210 with shared connection handler
- bin/fips.rs: refactor main() into run_daemon() accepting a shutdown
signal; add Windows Service support via windows-service crate
- transport/udp/socket.rs: platform-gated modules; Windows uses
tokio::net::UdpSocket (kernel drop count unavailable, returns 0)
- transport/ethernet: gate to cfg(unix); add Windows stub types
- config: platform-conditional default paths (socket, hosts) for Windows
- CI: add windows-latest to build matrix and test-windows job with
cargo-nextest
- packaging/windows: build-zip.ps1, install-service.ps1,
uninstall-service.ps1, and package-windows.yml workflow
- README/docs: Windows build instructions, service management, and
control socket platform differences
Linux and macOS behavior is unchanged.
Johnathan Corgan
ArjenandJohnathan Corgan
olekskyandJohnathan Corgan
Martti MalmiandGitHub
OceanSlimandGitHub