mirror of
https://github.com/jmcorgan/fips.git
synced 2026-08-09 00:04:54 +00:00
Fix FSP rekey cutover race and MMP metric discontinuity
The FSP XK rekey handshake has a race condition where the initiator can cut over (K-bit flip) and send data encrypted with the new session before msg3 reaches the responder. The responder has no pending session yet, so K-bit detection fails and packets are dropped. Defer FSP initiator cutover by 2 seconds after handshake completion (FSP_CUTOVER_DELAY_MS) to give msg3 time to traverse the mesh. FMP (IK, 2 messages) is unaffected since the responder completes during msg1 processing. Also fix MMP metric corruption after rekey cutover: the new session starts with counter 0 but MMP state carries highest_counter and GapTracker.expected_next from the old session, producing false reorder counts, jitter spikes, and invalid OWD trends. Add reset_for_rekey() methods that clear counter-dependent state while preserving RTT estimates. Additional fixes: - Remove stale peers_by_index entry on abandon_rekey error path - Replace redundant peers_by_index inserts with debug assertions verifying the pre-registration invariant - Tighten rekey integration test to zero tolerance (was 4 failures)
This commit is contained in:
@@ -63,9 +63,6 @@ FIRST_REKEY_WAIT=40 # > REKEY_AFTER_SECS, allow margin
|
||||
REKEY_SETTLE=5 # settle time after rekey for cutover to complete
|
||||
SECOND_REKEY_WAIT=40 # wait for second cycle
|
||||
|
||||
# Phase 3 allows transient failures during cutover; Phase 5 must be clean
|
||||
MAX_PHASE3_FAILURES=4 # allow up to 4 pair failures during first rekey
|
||||
|
||||
TIMEOUT=5
|
||||
PASSED=0
|
||||
FAILED=0
|
||||
@@ -199,20 +196,11 @@ assert_min_count "Rekey cutover complete (initiator), K-bit flipped" 1 "FMP reke
|
||||
phase_result "FMP rekey events"
|
||||
echo ""
|
||||
|
||||
# Verify connectivity after first rekey (allow transient cutover failures)
|
||||
# Verify connectivity after first rekey (strict — no failures allowed)
|
||||
echo "Phase 3: Post-rekey connectivity (settling ${REKEY_SETTLE}s)"
|
||||
sleep "$REKEY_SETTLE"
|
||||
ping_all
|
||||
if [ "$FAILED" -le "$MAX_PHASE3_FAILURES" ]; then
|
||||
if [ "$FAILED" -gt 0 ]; then
|
||||
echo " (transient failures within threshold: $FAILED <= $MAX_PHASE3_FAILURES)"
|
||||
fi
|
||||
TOTAL_PASSED=$((TOTAL_PASSED + PASSED))
|
||||
# Don't count transient failures toward total
|
||||
echo " ✓ Post-first-rekey (all 20 pairs): $PASSED passed, $FAILED transient"
|
||||
else
|
||||
phase_result "Post-first-rekey (all 20 pairs)"
|
||||
fi
|
||||
phase_result "Post-first-rekey (all 20 pairs)"
|
||||
echo ""
|
||||
|
||||
# ── Phase 4: Wait for second rekey cycle ──────────────────────────────
|
||||
@@ -247,6 +235,8 @@ assert_zero_count "MMP link teardown" "Spurious link teardowns"
|
||||
assert_zero_count "Excessive decrypt failures" \
|
||||
"Excessive decrypt failure removals"
|
||||
assert_zero_count "Rekey msg2 processing failed" "Rekey msg2 failures"
|
||||
assert_zero_count "Session AEAD decryption failed" \
|
||||
"FSP decryption failures during rekey"
|
||||
|
||||
phase_result "Log analysis"
|
||||
echo ""
|
||||
|
||||
Reference in New Issue
Block a user