mirror of
https://github.com/jmcorgan/fips.git
synced 2026-08-10 00:26:59 +00:00
fmp: bound rekey msg1 retransmission and make link-dead heartbeat rekey-aware
The FMP rekey msg1 resend driver retransmitted indefinitely with no cap and no abandon, so a rekey that never completed kept resending msg1 forever. Give it a retransmission budget: cap resends at handshake_max_resends with exponential backoff and abandon the rekey cycle cleanly once the budget is exhausted, mirroring the FSP session rekey msg3 driver. With the cap in place the link-dead heartbeat can safely become rekey-aware: check_link_heartbeats now suppresses teardown while a rekey is in progress with msg1 budget remaining, instead of reaping a link that is still actively carrying rekey-handshake traffic. The suppression terminates deterministically (the budget abandons on exhaustion, cutover clears the in-progress flag), so a genuinely dead link is still reaped on the next cycle. Adds a rekey_msg1_resend_count counter on ActivePeer reset at every rekey-clear and cutover site, msg1 resend-budget unit tests, and two-node heartbeat suppression/resume/regression integration tests.
This commit is contained in:
@@ -0,0 +1,114 @@
|
||||
//! Link-dead heartbeat rekey-awareness integration tests.
|
||||
//!
|
||||
//! `check_link_heartbeats()` reaps a peer after the link-dead timeout,
|
||||
//! but suppresses teardown while an FMP rekey is genuinely in flight with
|
||||
//! its msg1 retransmission budget unexhausted. These tests drive a real
|
||||
//! two-node UDP peering, inject rekey state on the peer, and verify the
|
||||
//! suppress / resume / regression behaviors. `link_dead_timeout_secs` is
|
||||
//! set to 0 so the elapsed-time predicate is always satisfied and the only
|
||||
//! variable is the rekey-active guard.
|
||||
|
||||
use super::spanning_tree::*;
|
||||
use super::*;
|
||||
use crate::Identity;
|
||||
use crate::noise::HandshakeState;
|
||||
use crate::utils::index::SessionIndex;
|
||||
|
||||
/// Arm a real (initiator) FMP rekey on the peer the given node holds for
|
||||
/// `peer_addr`, so the msg1 resend budget can be exercised.
|
||||
fn arm_rekey(node: &mut crate::node::Node, peer_addr: &NodeAddr) {
|
||||
let remote = Identity::generate();
|
||||
let local = Identity::generate();
|
||||
let hs = HandshakeState::new_initiator(local.keypair(), remote.pubkey_full());
|
||||
let peer = node.get_peer_mut(peer_addr).expect("peer present");
|
||||
peer.set_rekey_state(hs, SessionIndex::new(7), vec![0xAB; 64], 0);
|
||||
}
|
||||
|
||||
/// A peer past the link-dead timeout is NOT reaped while an FMP rekey is in
|
||||
/// progress with its msg1 budget unexhausted.
|
||||
#[tokio::test]
|
||||
async fn heartbeat_suppressed_during_rekey() {
|
||||
let mut nodes = run_tree_test(2, &[(0, 1)], false).await;
|
||||
verify_tree_convergence(&nodes);
|
||||
|
||||
let addr_1 = *nodes[1].node.node_addr();
|
||||
assert!(nodes[0].node.get_peer(&addr_1).is_some());
|
||||
|
||||
// Force every link to read as dead on elapsed time alone.
|
||||
nodes[0].node.config.node.link_dead_timeout_secs = 0;
|
||||
|
||||
// Arm a rekey with budget left (count 0 < max_resends default 5).
|
||||
arm_rekey(&mut nodes[0].node, &addr_1);
|
||||
assert!(nodes[0].node.get_peer(&addr_1).unwrap().rekey_in_progress());
|
||||
|
||||
nodes[0].node.check_link_heartbeats().await;
|
||||
|
||||
assert!(
|
||||
nodes[0].node.get_peer(&addr_1).is_some(),
|
||||
"peer reaped despite an in-flight rekey with budget remaining"
|
||||
);
|
||||
|
||||
cleanup_nodes(&mut nodes).await;
|
||||
}
|
||||
|
||||
/// Once the msg1 budget is exhausted the rekey-active guard no longer
|
||||
/// holds, so a peer past the link-dead timeout IS reaped.
|
||||
#[tokio::test]
|
||||
async fn heartbeat_resumes_after_budget_exhausted() {
|
||||
let mut nodes = run_tree_test(2, &[(0, 1)], false).await;
|
||||
verify_tree_convergence(&nodes);
|
||||
|
||||
let addr_1 = *nodes[1].node.node_addr();
|
||||
assert!(nodes[0].node.get_peer(&addr_1).is_some());
|
||||
|
||||
nodes[0].node.config.node.link_dead_timeout_secs = 0;
|
||||
let max_resends = nodes[0].node.config.node.rate_limit.handshake_max_resends;
|
||||
|
||||
arm_rekey(&mut nodes[0].node, &addr_1);
|
||||
|
||||
// Exhaust the budget: count reaches max_resends, guard goes false.
|
||||
let peer = nodes[0].node.get_peer_mut(&addr_1).unwrap();
|
||||
for i in 0..max_resends {
|
||||
peer.record_rekey_msg1_resend(1000 + i as u64 * 100);
|
||||
}
|
||||
assert_eq!(
|
||||
nodes[0]
|
||||
.node
|
||||
.get_peer(&addr_1)
|
||||
.unwrap()
|
||||
.rekey_msg1_resend_count(),
|
||||
max_resends
|
||||
);
|
||||
|
||||
nodes[0].node.check_link_heartbeats().await;
|
||||
|
||||
assert!(
|
||||
nodes[0].node.get_peer(&addr_1).is_none(),
|
||||
"peer not reaped after its rekey budget was exhausted"
|
||||
);
|
||||
|
||||
cleanup_nodes(&mut nodes).await;
|
||||
}
|
||||
|
||||
/// Regression guard: with no rekey in flight, a peer past the link-dead
|
||||
/// timeout is reaped exactly as before.
|
||||
#[tokio::test]
|
||||
async fn heartbeat_unaffected_without_rekey() {
|
||||
let mut nodes = run_tree_test(2, &[(0, 1)], false).await;
|
||||
verify_tree_convergence(&nodes);
|
||||
|
||||
let addr_1 = *nodes[1].node.node_addr();
|
||||
assert!(nodes[0].node.get_peer(&addr_1).is_some());
|
||||
assert!(!nodes[0].node.get_peer(&addr_1).unwrap().rekey_in_progress());
|
||||
|
||||
nodes[0].node.config.node.link_dead_timeout_secs = 0;
|
||||
|
||||
nodes[0].node.check_link_heartbeats().await;
|
||||
|
||||
assert!(
|
||||
nodes[0].node.get_peer(&addr_1).is_none(),
|
||||
"dead peer with no rekey in flight should be reaped"
|
||||
);
|
||||
|
||||
cleanup_nodes(&mut nodes).await;
|
||||
}
|
||||
@@ -17,6 +17,7 @@ mod discovery;
|
||||
mod ethernet;
|
||||
mod forwarding;
|
||||
mod handshake;
|
||||
mod heartbeat;
|
||||
mod routing;
|
||||
mod session;
|
||||
mod spanning_tree;
|
||||
|
||||
Reference in New Issue
Block a user