pqkem: recover from persistent rekey failure by re-bootstrapping over signal

OnRekeyFailed now re-runs the KEM bootstrap over Signal (conn.RequestReoffer ->
handshaker.SendOffer) instead of only logging: a fresh signalling offer starts a new
exchange that overwrites the stalled PSK on both sides, resyncing after a persistent
data-path desync. Chosen over a responder-side awaitingAck revert (which fights the
confirm-less ack timing) and a full tunnel teardown (heavier). The tunnel stays up on
the previous PSK meanwhile since Signal is independent of the broken data path.
This commit is contained in:
riccardom
2026-09-11 14:48:54 +02:00
parent e1d5551ba5
commit d485567978
3 changed files with 40 additions and 4 deletions
+16
View File
@@ -726,6 +726,22 @@ func (conn *Conn) onGuardEvent() {
}
}
// RequestReoffer sends a fresh signalling offer for the peer, re-running the
// post-quantum bootstrap over Signal. Used to recover from a persistent data-path
// rekey failure: a new exchange overwrites the stalled PSK on both sides. No-op if the
// connection is not open yet.
func (conn *Conn) RequestReoffer() {
conn.mu.Lock()
h := conn.handshaker
conn.mu.Unlock()
if h == nil {
return
}
if err := h.SendOffer(); err != nil {
conn.Log.Debugf("pqkem: recovery re-offer failed: %v", err)
}
}
func (conn *Conn) onWGDisconnected(watcherCtx context.Context) {
conn.mu.Lock()
defer conn.mu.Unlock()