Replace discovery flooding with bloom-filter-guided tree routing:
lookups sent only to tree peers (parent + children) whose bloom
filter contains the target. If no tree peer matches, fall back to
non-tree peers with bloom matches before dropping the request. This
produces single-path forwarding through the spanning tree (90%
traffic reduction) while recovering from dead ends caused by stale
bloom filters, tree restructuring, or transit node failures.
Remove visited bloom filter from LookupRequest wire format (-257
bytes per request). Tree routing is inherently loop-free; request_id
dedup handles edge cases during tree restructuring. Add response-
forwarded flag to prevent response routing loops from convergent
request paths.
Add originator-side exponential backoff (30s base, 300s cap) after
lookup timeouts and bloom misses. Backoff resets on topology changes
(parent switch, new peer, first RTT, reconnection).
Add transit-side per-target rate limiting (2s minimum interval) for
forwarded lookups as defense-in-depth.
Add discovery retry within the timeout window (default: send at T=0,
retry at T=5s, fail at T=10s) to compensate for single-path fragility.
Lookups with zero eligible tree peers fail immediately.
Improve discovery logging: promote key events to info (initiation,
success, timeout with failure count). Add debug logging for dedup,
pending packet retry, backoff suppression, forward rate limiting,
and backoff reset.
New config: discovery.backoff_base_secs, backoff_max_secs,
forward_min_interval_secs, retry_interval_secs, max_attempts.
New stats: req_backoff_suppressed, req_forward_rate_limited,
req_bloom_miss, req_no_tree_peer, req_fallback_forwarded.
Removed: req_already_visited, visited bloom filter.
The PTB source was set to the local FIPS address, which Linux ignores
(loopback PTB security check). Change the source to the original
packet's destination (the remote peer) so the kernel sees it as coming
from a remote router and honors the PMTU update.
Add test coverage for the PTB source address invariant in both the
icmp unit tests and the node integration tests.
Cherry-picked from v0l PR #6 (issue #5):
1. remove_active_peer() now removes the end-to-end session from
self.sessions when evicting a peer. The stale Established entry
caused initiate_session() to silently return Ok(()) via the
is_established() guard, preventing session re-establishment after
link-layer reconnection.
2. initiate_peer_connections() pre-seeds the identity cache from
configured peer npubs at startup, so TUN packets can be dispatched
immediately without waiting for handshake completion.
3. schedule_reconnect() preserves accumulated backoff when a retry
entry already exists, preventing exponential backoff reset on
repeated link-dead cycles.
Includes regression tests for all three fixes.
Previously, static peers configured with AutoConnect gave up after 6
attempts (1 initial + 5 retries). If the remote peer was offline at
startup, the node permanently abandoned the connection. The reconnect
path (after MMP link-dead) already retried indefinitely but only
activated after a peer had been previously connected.
Remove the reconnect parameter from schedule_retry() and always set
reconnect=true when creating retry entries, since only auto-connect
peers reach this code path. The 300s backoff cap prevents resource waste.
The max_retries=0 config still works as an explicit kill switch.
Breaking wire format change: DataPacket payloads inside the AEAD envelope
now carry a 4-byte port header [src_port:2 LE][dst_port:2 LE] before the
service payload. The receiver dispatches by destination port.
Port multiplexing:
- send_session_data() takes src_port/dst_port params, prepends port header
- New send_ipv6_packet() compresses IPv6 header and sends on port 256
- Receive path dispatches DataPackets by port: port 256 decompresses IPv6
header from session context and delivers to TUN, unknown ports dropped
- Port constants: FSP_PORT_HEADER_SIZE (4 bytes), FSP_PORT_IPV6_SHIM (256)
IPv6 header compression:
- New ipv6_shim module with compress_ipv6()/decompress_ipv6() pure functions
- Strips src/dst addresses (32 bytes) and payload length (2 bytes) from each
packet, preserving traffic class, flow label, next header, and hop limit
as 6-byte residual fields
- Addresses reconstructed from session context on receive side
- Net savings: 29 bytes per packet (overhead 106 → 77 bytes)
- FIPS_IPV6_OVERHEAD constant (77 bytes), effective_ipv6_mtu() updated
- 16 unit tests for round-trip fidelity, field preservation, error cases
Documentation:
- fips-wire-formats: DataPacket port header, port registry, IPv6 shim
format tables, updated encapsulation walkthrough and overhead budget
- fips-ipv6-adapter: FIPS_IPV6_OVERHEAD (77 bytes), updated MTU numbers,
TUN reader/writer flow with compression steps, impl status
- fips-session-layer: port-based service dispatch section, data transfer
description, impl status
- fips-intro: IPv6 adapter as port 256 service, node architecture updated
- fips-mesh-operation: packet size summary with compressed overhead
- DataPacket doc updated with port header and dispatch model
- session_wire.rs module doc: DataPacket Port Multiplexing section
Five tests covering the full TCP transport stack at the node level:
two-node handshake, three-node chain convergence with bloom filter
reachability, mixed UDP+TCP transport coexistence, MMP link-dead
detection after connection loss, and reconnection after link death
via connect-on-send.
Implement hop-by-hop ECN congestion signaling through the FMP layer,
transport-level congestion detection via kernel drop counters, and
chaos harness integration for end-to-end validation.
FMP/session ECN plumbing:
- Thread ce_flag parsed at link layer through dispatch_link_message,
handle_session_datagram, handle_session_payload, and
handle_encrypted_session_msg to session delivery
- Replace hardcoded false in session-layer record_recv() with actual
ce_flag, activating ecn_ce_count tracking in session MMP
ECN congestion detection and CE relay:
- Add EcnConfig (node.ecn.*) with configurable loss_threshold (5%)
and etx_threshold (3.0) for transit congestion detection
- Add send_encrypted_link_message_with_ce() that ORs FLAG_CE into FMP
header flags; original method delegates with ce_flag=false
- Compute outgoing_ce = incoming_ce || local congestion on next-hop
link, enabling hop-by-hop CE relay through transit nodes
IPv6 ECN-CE marking:
- Mark ECN-CE (0b11) in IPv6 Traffic Class on received DataPackets
before TUN delivery when FMP CE flag is set
- Only marks ECN-capable packets (ECT(0)/ECT(1)); Not-ECT packets
unchanged per RFC 3168
Transport congestion abstraction and UDP kernel drop detection:
- Add TransportCongestion struct to transport layer for transport-
agnostic local congestion indicators
- Replace tokio::UdpSocket with AsyncFd<socket2::Socket> using
libc::recvmsg() with ancillary data parsing
- Enable SO_RXQ_OVFL for kernel receive buffer drop counter on every
packet, wiring up previously-stubbed UdpStats.kernel_drops
- Add TransportDropState for per-transport delta tracking with 1s
tick sampling via sample_transport_congestion()
- Extend detect_congestion() with transport kernel drop check
alongside MMP loss metrics
Congestion monitoring and control:
- Add CongestionStats (ce_forwarded, ce_received, congestion_detected,
kernel_drop_events) to NodeStats with snapshot serialization
- Wire counters into forwarding path, session handler, and transport
drop sampling with rate-limited warn logging (5s interval)
- Expose congestion data in show_routing control query and
ecn_ce_count in show_mmp peer entries
- Add congestion counters to fipstop routing tab in two-column layout
Chaos harness integration:
- Add query_routing(), query_transports(), snapshot_all_congestion()
to chaos control module
- Add congestion/kernel-drop log analysis in logs module
- Add congestion-stress scenario: 10-node tree, 1 Mbps bandwidth,
5-10% netem loss, heavy iperf3 traffic
- Add IngressConfig for tc ingress policing with per-peer policer
filters simulating upstream bandwidth bottlenecks
- Add iperf3 JSON result capture to traffic manager for throughput
measurement across scenarios
- Add ECN A/B test scenarios (ecn-ab-on/off.yaml) with ingress
policing and comparison script
- Enable TCP ECN negotiation (tcp_ecn=1 sysctl) in container
entrypoint for end-to-end CE propagation
Tests:
- 10 ECN unit/integration tests: mark_ipv6_ecn_ce variants, CE relay
chain (3-node propagation), EcnConfig serde roundtrip
- 3 transport drop congestion detection unit tests
Documentation:
- Update fips-mesh-layer.md: replace outdated CE Echo stub with full
ECN Congestion Signaling section covering detection logic, CE relay,
IPv6 marking, session tracking, and monitoring counters
- Update fips-configuration.md: add node.ecn.* parameter table and
ecn block in complete reference YAML
- Update fips-transport-layer.md: add Congestion Reporting section
with TransportCongestion struct, congestion() trait method, and
per-transport status; document AsyncFd/recvmsg/SO_RXQ_OVFL in UDP
- Update chaos README: add congestion/ECN scenario docs, ingress
traffic control, and iperf3 JSON capture sections
- Update README.md: add ECN to features list and "What works today";
update transport and tooling entries
Two bugs prevented Path MTU Discovery from working across heterogeneous
links (e.g., ethernet→UDP boundary):
1. ICMPv6 Packet Too Big wrote the MTU as u16 into a 32-bit field
(RFC 4443 §3.2), causing the kernel to read an inflated value.
Fixed by changing build_packet_too_big() to use u32 and writing
all 4 bytes.
2. handle_tun_outbound() only checked the local transport MTU, not
the per-destination PathMtuState updated by MtuExceeded signals.
Added a PathMtuState check after session lookup so subsequent
oversized packets generate ICMPv6 PTB on TUN instead of being
forwarded and dropped at the bottleneck hop.
Added integration test exercising the full PMTUD loop across a 3-node
chain with heterogeneous MTUs: oversized packet → forwarding failure →
MtuExceeded signal → PathMtuState update → ICMPv6 PTB on TUN.
Update the default UDP bind port from 4000 to 2121 (decimal) and the
default Ethernet EtherType from 0x88B5 to 0x2121 across all source
code, documentation, configuration templates, test fixtures, and
scripts. Remove references to "IEEE 802 experimental range" since
0x2121 is not in that range.
Implement raw Ethernet transport using AF_PACKET SOCK_DGRAM on Linux
with EtherType 0x88B5 (IEEE experimental range) and 1-byte frame type
prefix (0x00=data, 0x01=beacon).
Transport implementation:
- EthernetConfig with interface, ethertype, MTU, buffer sizes, and
four independent discovery knobs (discovery, announce, auto_connect,
accept_connections)
- PacketSocket/AsyncPacketSocket wrappers with ioctl helpers for
interface index, MAC address, and MTU queries
- EthernetTransport with Transport trait impl, async start/stop/send,
receive loop dispatching data frames and discovery beacons
- Discovery beacons (34 bytes: type + version + x-only pubkey) with
DiscoveryBuffer for peer accumulation and dedup
- Atomic statistics counters (frames, bytes, errors, beacons)
- Platform-gated with #[cfg(target_os = "linux")]
Transport-layer discovery integration:
- Promote auto_connect() and accept_connections() to Transport trait
with default implementations and TransportHandle dispatch
- Extract initiate_connection() so both static peer config and
discovery auto-connect share the same handshake initiation path
- Add poll_transport_discovery() to the tick handler to drain
discovery buffers and auto-connect to discovered peers
- Enforce accept_connections() in handle_msg1() — transports with
accept_connections=false silently drop inbound handshakes
Node integration:
- create_transports() handles Ethernet named instances
- resolve_ethernet_addr() parses "interface/mac" address format
- transport_mtu() generalized for multi-transport operation
Test harness:
- VethPair RAII struct for veth pair lifecycle management
- Three #[ignore] integration tests requiring root/CAP_NET_RAW:
two-node handshake, data exchange, mixed transport coexistence
- Chaos harness: transport-aware topology model, VethManager for
veth pairs between Docker containers, Ethernet-aware config gen,
netem split (HTB+u32 for UDP, root netem for veth), transport-aware
link flaps and node churn with veth re-setup
- Container entrypoint waits for configured Ethernet interfaces
before starting FIPS (handles veth creation timing)
- New scenarios: ethernet-only (4-node ring), ethernet-mesh (6-node
mixed UDP+Ethernet with netem and link flaps)
Documentation:
- fips-transport-layer.md: Ethernet section, beacon discovery, WiFi
compatibility, updated discovery state, trait surface additions,
implementation status table
- fips-configuration.md: Ethernet parameter table, named instances,
peer address format, mixed UDP+Ethernet example, complete reference
- fips-wire-formats.md: Ethernet frame type prefix note
Bump rand (0.8→0.10), rtnetlink (0.14→0.20), tun (0.7→0.8),
simple-dns (0.9→0.11), socket2 (0.5→0.6), and criterion (0.5→0.8).
Migrate all rand call sites: thread_rng()→rng(), gen()→random(),
gen_range()→random_range(), RngCore→Rng trait. Work around secp256k1
0.30 requiring rand 0.8 by generating random bytes directly and
constructing SecretKey from slice.
Migrate rtnetlink to builder-based API: LinkSetRequest replaced with
LinkUnspec builder + change(), RouteAddRequest replaced with
RouteMessageBuilder.
Remove bloom benchmark (criterion 0.8 incompatible with old harness
config).
Guard discovery triggers in handle_path_broken() and
handle_coords_required() with has_cached_identity() check. When the
XK responder receives an error signal before msg3 completes, the
initiator's identity is unknown, making LookupResponse proof
verification impossible. Skip discovery in this case — the handshake
retry mechanism handles recovery.
Downgrade the identity_cache miss log from ERROR to WARN since it's a
known race condition, not a bug.
Gate peer_inbound_filters() to only collect from tree peers (parent
and children), so outgoing filter computation merges only tree-sourced
information. All peers still receive FilterAnnounce messages and store
filters locally for routing queries — the restriction is only on what
gets merged into outgoing filters.
This prevents bloom filter saturation where mesh shortcuts cause every
node's filter to converge toward the full network. With tree-only
merge, filters contain subtree (from children) + complement (from
parent) + single-hop mesh views.
Implementation:
- Add is_tree_peer() helper to determine tree parent/child relationship
- Gate peer_inbound_filters() to tree peers only (single control point)
- Trigger bloom filter exchange on tree relationship changes
- Add est_entries, set_bits, fill ratio, and tree_peer fields to
FilterAnnounce send/receive debug logs
- Add test_bloom_filter_split_horizon test verifying directional
asymmetry: upward filters contain only the child's subtree, downward
filters contain only the complement
- Add print_filter_cardinality diagnostic helper for test inspection
Design docs:
- fips-bloom-filters.md: Add directional asymmetry and mesh peer filter
subsections, update per-peer filter model, saturation mitigation,
implementation status table
- fips-mesh-operation.md: Update filter propagation description, add
directional asymmetry, tree relationship change trigger
- fips-intro.md: Rewrite bloom propagation paragraph for tree-only merge
The session-layer handshake now uses the 3-message XK pattern instead
of the 2-message IK pattern, providing stronger initiator identity
hiding. The initiator static key is deferred to msg3 and encrypted
under the es+ee DH chain, so eavesdroppers cannot identify the
initiator from the handshake.
XK pattern: -> e, es (msg1) / <- e, ee + epoch (msg2) / -> s, se + epoch (msg3)
Key changes:
- Add XK handshake methods alongside existing IK methods in noise module
- Add SessionMsg3 wire format and FSP_PHASE_MSG3 (0x03) prefix
- Replace Responding state with AwaitingMsg3 in session state machine
- Rewrite session handlers: handle_session_setup defers identity to msg3,
handle_session_ack processes msg2 and sends msg3, new handle_session_msg3
completes the responder handshake and registers identity
- Link-layer (FMP) continues to use Noise IK unchanged
- Add comprehensive XK unit tests and update all integration tests
Add min_mtu (u16) to LookupRequest and path_mtu (u16) to
LookupResponse, enabling the discovery system to report transport
MTU capability along the lookup path.
LookupRequest carries min_mtu (origin's minimum MTU requirement,
default 0 = no requirement). LookupResponse carries path_mtu
(initialized to u16::MAX by the target, reduced by transit nodes
via min(path_mtu, outgoing_link_mtu) on the reverse path).
path_mtu is a transit annotation like SessionDatagram.path_mtu and
is NOT included in the proof signature. The originator stores the
discovered path_mtu in CacheEntry alongside cached coordinates.
Wire format: +2 bytes each for LookupRequest and LookupResponse.
The target node's send_lookup_response() was using greedy tree routing
(find_next_hop) as the primary method to route responses back to the
origin. When the target had the origin's coords cached from a prior
lookup, find_next_hop would route the response to whichever peer was
closest to the origin in tree space -- which might not have been on the
request's forward path. That peer would have no recent_requests entry
for the request_id, causing it to treat the response as if it were the
originator, fail identity_cache lookup, and discard the response.
Fix: prefer the reverse-path (recent_requests.from_peer) as the
primary routing method for the first hop, falling back to
find_next_hop only if no recent_request entry exists.
Also adds diagnostic output on failure to aid future debugging.
Each node generates a random 8-byte startup epoch, encrypted inside
both Noise IK handshake messages (msg1 and msg2). When a peer's msg1
arrives with a different epoch than the stored value, the node tears
down the stale session and processes the msg1 as a new connection,
enabling near-instant restart detection instead of the 30-second
dead timeout.
Wire format impact:
- msg1: 82 -> 106 bytes (added 24-byte encrypted epoch after ss DH)
- msg2: 33 -> 57 bytes (added 24-byte encrypted epoch after se DH)
- Wire msg1: 90 -> 114 bytes, wire msg2: 45 -> 69 bytes
Include target_coords in proof_bytes() signed data to prevent transit
nodes from substituting fake coordinates. Add mandatory signature
verification at the originator using the target's public key from
identity_cache (guaranteed available since lookups are only initiated
from contexts where the key is already cached).
Verification failure discards the response. Identity cache miss (should
never happen) logs an error and discards. Add four new tests covering
verification success, failure, cache miss, and coordinate substitution
detection.
Rename FIPS Link Protocol (FLP) to FIPS Mesh Protocol (FMP)
The "Link Protocol" name understated the layer's scope — spanning tree
construction, bloom filter routing, greedy forwarding, and mesh-wide
coordination go well beyond link-level concerns. Rename fips-link-layer.md
to fips-mesh-layer.md, update FLP→FMP throughout docs and source code
(FLP_VERSION→FMP_VERSION, wire.rs, rx_loop.rs, spanning_tree.rs).
New SVG illustrations
- Protocol stack: color-coded layer diagram replacing ASCII art
- OSI mapping: side-by-side comparison with traditional networking layers
- Bloom filter propagation: 6-node tree with sender-colored filter boxes
showing split-horizon computation per link
- Routing decision flowchart: 5-step priority chain with candidate ranking
by tree distance and link performance
- Coordinate discovery: sequence diagram showing LookupRequest propagation,
response caching, and SessionSetup cache warming
Redesigned existing SVGs
- Architecture overview: uniform node layout, U-shaped encrypted link
connectors, separate end-to-end session line
- Node architecture: split Router Core into FSP and FMP layers, reorganize
transports into Overlay/Shared Medium/Point-to-Point categories
- Identity derivation: wider boxes, visible encode arrow, dashed npub line
fips-intro.md revisions
- Add inline references to prior work: Yggdrasil/Ironwood for coordinate
routing, Noise Protocol Framework for IK handshakes, WireGuard for
index-based session dispatch, Wikipedia for bloom filters, split-horizon,
and greedy embedding
- Add explanatory paragraphs after bloom filter diagram describing
split-horizon filter computation and candidate selection behavior
- Simplify transport abstraction language, remove I2P/LoRa references
- Fix LookupRequest wording ("propagates" not "floods"), note intermediate
node coordinate caching on lookup responses
- Rewrite architecture overview prose to match redesigned diagrams
SessionAck previously only carried the responder's coordinates
(src_coords). When the return path diverged from the forward path
(e.g., after tree reconvergence), transit nodes on the return path
lacked the initiator's coordinates and couldn't route the SessionAck
back, causing handshake timeouts.
Add dest_coords (initiator's coordinates) to the SessionAck wire
format, mirroring SessionSetup's design. Transit nodes now cache both
endpoints' coordinates when forwarding a SessionAck, making the return
path self-sufficient regardless of path asymmetry.
Root cause confirmed by churn-20 sim log analysis: the n04-n14
handshake failure was caused by n15 (return-path transit) lacking
n04's coordinates, not by stale tree routes through a downed node.
Auto-reconnect:
- Add per-peer auto_reconnect config (default true) to PeerConfig
- schedule_reconnect() feeds removed peers back into retry system with
unlimited retries and exponential backoff after MMP dead timeout
- RetryState gains reconnect flag to distinguish startup retries
(max_retries-limited) from auto-reconnect (unlimited)
Retry re-fire fix:
- process_pending_retries() now pushes retry_after_ms past the handshake
timeout window after successful initiate_peer_connection(), preventing
retries from firing every tick with no backoff
Chaos sim improvements:
- Directed outbound configs: BFS spanning tree + lower-ID-first assignment
eliminates dual-connect race conditions in simulation
- Save runner log (runner.log) alongside per-node logs for event correlation
- Increase churn-20 traffic aggressiveness and node churn (max_down_nodes
3→5, traffic interval min 0s, duration max 90s, concurrent flows 5→10)
Add resend logic for SessionSetup/SessionAck messages routed through
the mesh. Stores the encoded payload on SessionEntry for resend in a
fresh SessionDatagram (so routing can adapt to topology changes).
Uses the same config parameters as link-layer retry.
Also fixes a latent bug: Initiating/Responding sessions previously
had no timeout — a stuck handshake would live forever. Now cleaned up
after handshake_timeout_secs (default 30s).
Responder idempotency: duplicate SessionSetup triggers resend of
stored SessionAck instead of being silently dropped. Initiator-side
duplicate SessionAck already handled safely (entry.take_state() sees
Established, puts it back and returns).
Handshake payload cleared on Established transition at both initiator
(handle_session_ack) and responder (handle_encrypted_session_msg).
Add message-level retry for Noise IK handshake within the 30s timeout
window. Previously, a lost msg1 or msg2 required the full timeout to
expire before cleanup and retry. Under 10% bidirectional loss (~19%
per attempt), this made connection establishment unreliable.
Initiator resends stored msg1 bytes with exponential backoff (1s, 2s,
4s, 8s, 16s — 5 resends). Responder stores msg2 and resends on
duplicate msg1 receipt. Duplicate msg2 at initiator drops silently
via existing pending_outbound cleanup.
Config: handshake_resend_interval_ms (1000), handshake_resend_backoff
(2.0), handshake_max_resends (5) on node.rate_limit.
P(all 6 attempts fail) under 19% loss = 0.19^6 ≈ 0.005%.
Under high-throughput forwarding, the kernel default 212KB receive
buffer overflows, silently dropping ~11% of UDP datagrams at transit
nodes. Add configurable recv_buf_size and send_buf_size to UdpConfig
(default 2MB each) using socket2 for pre-bind buffer configuration.
Startup log now reports actual buffer sizes granted by the kernel.
Requires net.core.rmem_max >= 2097152 on the host for the full 2MB
to take effect; otherwise the kernel silently clamps.
MMP reports (SenderReport, ReceiverReport, PathMtuNotification) were
resetting the idle timer on both RX and TX paths, preventing sessions
from ever timing out when MMP traffic kept flowing. Changed touch() to
only be called for DataPacket send/receive and session establishment,
so sessions with no application data tear down after the idle timeout
even with active MMP measurement traffic.
Session-layer encryption used an implicit nonce counter with no counter
on the wire, requiring packets to arrive in exact order. Under bulk
transfer load (e.g., SCP), UDP packet loss or reordering permanently
desynchronized sender/receiver counters, causing all subsequent
decryption to fail with no recovery.
Add an 8-byte counter field to the DataPacket wire format and switch
from implicit-counter decrypt() to decrypt_with_replay_check() which
uses the explicit wire counter plus a 2048-packet sliding replay
window — the same pattern already used at the link layer.
Wire format: msg_type(1) + flags(1) + counter(8) + payload_len(2) = 12
bytes (was 4). FIPS_OVERHEAD updated 127 → 135 bytes accordingly.
Include source and destination coordinates on the first N DataPackets
of each session (default 5, configurable via
node.session.coords_warmup_packets). This warms transit node
coord_caches so multi-hop forwarding and error signal routing work
after SessionSetup cache entries expire.
On CoordsRequired receipt, reset the counter to re-enable coordinate
inclusion for the next N packets, handling mid-session cache expiry
and path changes.
Changes:
- SessionConfig: add coords_warmup_packets field (default 5)
- SessionEntry: add coords_warmup_remaining counter, initialized on
Established transition (both initiator and responder paths)
- send_session_data(): attach coords via DataPacket::with_coords()
while counter > 0, decrement per send
- handle_coords_required(): reset counter for affected session
- 4 new unit tests for counter lifecycle and config default
Identity cache: remove TTL-based expiry (60s TTL broke active sessions
after expiry since handle_tun_outbound checks identity_cache before
session table). Replace with LRU-only eviction bounded by configurable
identity_size (default 10K). Lookup now touches timestamp for LRU
freshness.
Cache merge: unify coord_cache and route_cache into single coordinate
cache. Both stored NodeAddr→TreeCoordinate; the layer distinction was
conceptual, not functional. Discovery-sourced entries now get the same
TTL+refresh treatment as session-sourced entries. Simplifies
find_next_hop() to single cache lookup.
Parent-change flush: clear coord_cache after recompute_coords() in both
parent-switch paths of handle_tree_announce(). Stale coordinates after
tree reconvergence cause dead-end routing that's more expensive than
re-discovery.
Tested: 493 unit tests passed, clippy clean, Docker mesh 20/20,
Docker chain 6/6.
Sessions in the Established state that have no activity for 90 seconds
are now automatically removed. This ensures idle sessions are torn down
before transit node coord_cache entries expire (300s TTL), so that when
traffic resumes a fresh SessionSetup re-warms transit node caches with
current coordinates.
The identity cache now stores registration timestamps and expires
entries after 60 seconds via lazy expiry on lookup. This prevents
unbounded growth while allowing natural repopulation through DNS
resolution on next use.
Timer ordering: identity (60s) < session (90s) < coord_cache (300s).
Both timeouts are configurable: node.session.idle_timeout_secs and
node.cache.identity_ttl_secs. Setting idle_timeout_secs to 0 disables
session idle purging.
Changes:
- Add idle_timeout_secs (default 90) to SessionConfig
- Add identity_ttl_secs (default 60) to CacheConfig
- Add timestamp to identity_cache entries, lazy expiry on lookup
- Add purge_idle_sessions() called from tick loop
- Remove #[cfg(test)] from SessionEntry::last_activity()
- 7 new tests covering timeout behavior and edge cases
Transit nodes cache destination coordinates when they forward
SessionSetup messages (via try_warm_coord_cache). These coord_cache
entries have a 5-minute TTL, after which they expire. Once expired,
the transit node can no longer forward data packets for that
destination — find_next_hop returns None and the node sends
CoordsRequired errors back to the source. This creates a permanent
routing failure for any multi-hop path after 5 minutes of the initial
session establishment, even if traffic is actively flowing.
The root cause was that find_next_hop used coord_cache.get(), a
read-only lookup that checks expiry but never extends it. Active
forwarding did not keep the cache warm. Meanwhile, get_and_touch()
existed but only updated last_used without extending expires_at.
Fix:
- find_next_hop now calls coord_cache.get_and_touch() instead of get()
- get_and_touch now calls entry.refresh() instead of entry.touch(),
which extends expires_at by the default TTL on each access
- find_next_hop signature changed from &self to &mut self to allow
the mutable cache access
This ensures that as long as traffic flows through a transit node,
the coord_cache entries stay warm and routing continues to work.
Entries still expire after 5 minutes of inactivity as designed.
Wire the discovery protocol into the data plane path so that
find_next_hop() consults route_cache as a fallback when coord_cache
has no entry. When session initiation fails due to missing routes,
trigger discovery (initiate_lookup) instead of immediately sending
ICMPv6 Destination Unreachable. On discovery completion, retry
session initiation for any pending TUN packets.
Changes:
- find_next_hop() falls back to route_cache when coord_cache misses
- handle_tun_outbound() triggers discovery on session failure
- handle_lookup_response() retries session after discovery completes
- handle_coords_required() triggers discovery for missing coordinates
- Add pending_lookups deduplication with 10-second timeout
- Periodic cleanup of stale lookups in tick handler
- New test: route_cache fallback verification in find_next_hop
Wire the TUN reader to the session layer for end-to-end IPv6 packet
delivery through the mesh. TUN reader forwards FIPS-destined packets
(fd::/8) to Node via tokio::sync::mpsc channel. Identity cache maps
FipsAddress prefix bytes to NodeAddr + PublicKey for reverse address
resolution, populated at peer promotion and session creation. Outbound
handler validates IPv6, looks up destination identity, routes through
established session or initiates new one with pending packet queue
(16/dest, 256 dests max). Queue flushed on session establishment.
ICMPv6 Destination Unreachable for unknown destinations. 6 new tests
including 3-node forwarded TUN data and pending queue flush. 410 tests
pass, clean build.
Implement Noise IK session handshake between arbitrary endpoints, carried
inside SessionDatagram envelopes through the mesh. Sessions use a three-state
machine (Initiating → Established for initiator, Responding → Established
for responder on first DataPacket). Includes session initiation API,
encrypted data transfer, simultaneous initiation tie-break, error signal
handlers (CoordsRequired, PathBroken), and local delivery wiring in the
forwarding handler.
New files: node/session.rs (state types), handlers/session.rs (~500 lines,
all session message handlers + send path), tests/session.rs (11 tests).
100-node integration test establishes sessions across random topology,
sends bidirectional encrypted datagrams through injected TUN channels,
and verifies 200/200 deliveries with 100% session establishment. Reports
routing statistics including avg 4.1 link hops per datagram.
404 tests pass (up from 393).
Add handle_session_datagram handler replacing the 0x40 dispatch stub.
Transit nodes now decode the datagram envelope, enforce hop limits,
warm coordinate caches from SessionSetup/SessionAck/DataPacket payloads,
route via find_next_hop, and generate CoordsRequired/PathBroken error
signals on routing failure.
14 new tests covering decode errors, hop limit enforcement, local
delivery, cache warming for all session message types, single-hop and
multi-hop forwarding through live node chains, error signal generation,
and cache warming enabling subsequent routing. 375 tests pass.
Add src_addr to SessionDatagram envelope (34-byte header: msg_type +
src_addr + dest_addr + hop_limit) so transit routers can route error
signals back to the packet's originator.
Reclassify CoordsRequired/PathBroken as link-layer error signals
(plaintext inside SessionDatagram) rather than e2e encrypted session
messages. Transit routers generate these when forwarding fails and
route them to src_addr; if source is also unreachable, drop silently.
Remove redundant src_addr/dest_addr/hop_limit from SessionSetup,
SessionAck, and DataPacket (now in envelope). DataPacket header
reduced from 36 to 4 bytes. Remove PathBroken.original_src.
Fix routing loop vulnerability: gate bloom filter path on having
cached dest_coords to prevent blind forwarding between peers.
Simplify select_best_candidate() to require coordinates.
Fix gossip protocol type codes (0x11->0x20, 0x12->0x30, 0x13->0x31)
for consistency across all design docs.
All 5 design docs updated and cross-checked for consistency.
335 tests pass, zero warnings.
Add the full next-hop routing algorithm to Node::find_next_hop():
- Local delivery, direct peer, bloom filter candidates, greedy tree
routing fallback, with (link_cost, tree_distance, node_addr) ordering
- select_best_candidate() scores by peer→dest distance (not us→peer)
with self-distance check to prevent routing loops
- TreeState::find_next_hop() for greedy tree routing with progress
guarantee
- ActivePeer::link_cost() placeholder (constant 1.0) for future link
quality metrics
Add routing tests including 100-node all-pairs reachability simulation
(9900/9900 delivered, 0 loops, avg 4.0 hops, max 8).
Update fips-routing.md to reflect bloom filter routing as the primary
forwarding mechanism, with greedy tree routing as fallback during
convergence windows.
Split handlers.rs (986 lines) into handlers/ with 5 subfiles organized
by responsibility: rx_loop, encrypted, handshake, dispatch, timeout.
Split tests.rs (2350 lines) into tests/ with 4 subfiles: unit tests,
handshake integration, spanning tree convergence, and bloom filter tests.
Shared test helpers extracted to tests/mod.rs.
Visibility adjusted from pub(super) to pub(in crate::node) for handler
methods now two levels deep. Unused imports cleaned up in node/mod.rs.
All 316 tests pass, zero warnings.
Johnathan Corgan
KieranandJohnathan Corgan
Origami74andJohnathan Corgan