Major architectural refactor: eliminate global state and resource leaks

This commit addresses all critical architectural issues identified in the
Matt Holt code review, transforming the module from using anti-patterns
to following Caddy best practices.

### 🔴 CRITICAL FIXES:

**1. Global Registry → Caddy App System**
- Created SIPGuardianApp implementing caddy.App interface (app.go)
- Eliminates memory/goroutine leaks on config reload
- Before: guardians accumulated in global map, never cleaned up
- After: Caddy calls Stop() on old app before loading new config
- Impact: Prevents OOM in production with frequent config reloads

**2. Feature Flags → Instance Fields**
- Moved enableMetrics/Webhooks/Storage from globals to *bool struct fields
- Allows per-instance configuration (not shared across all guardians)
- Helper methods default to true if not set
- Impact: Thread-safe, configurable per guardian instance

**3. Prometheus Panic Prevention**
- Replaced MustRegister() with Register() + AlreadyRegisteredError handling
- Makes RegisterMetrics() idempotent and safe for multiple calls
- Before: panics on second call (e.g., config reload)
- After: silently ignores already-registered collectors
- Impact: No more crashes on config reload

### 🟠 HIGH PRIORITY FIXES:

**4. Storage Worker Pool**
- Fixed pool of 4 workers + 1000-entry buffered channel
- Replaces unbounded go func() spawns (3 locations)
- Before: 100k goroutines during DDoS → memory exhaustion
- After: bounded resources, drops writes when full (fail-fast)
- Impact: Survives attacks without resource exhaustion

**5. Config Immutability**
- MaxFailures/FindTime/BanTime no longer modified on running instance
- Prevents race with RecordFailure() reading values without lock
- Changed mutations to warning logs
- Additive changes still allowed (whitelists, webhooks)
- Impact: No more race conditions, predictable ban behavior

### Modified Files:
- app.go (NEW): SIPGuardianApp with proper lifecycle management
- sipguardian.go: Removed module registration, added worker pool, feature flags
- l4handler.go: Use ctx.App() instead of global registry
- metrics.go: Use ctx.App() instead of global registry
- registry.go: Config immutability warnings instead of mutations

### Test Results:
All tests pass (1.228s) 

### Breaking Changes:
None - backwards compatible, but requires apps {} block in Caddyfile
for proper lifecycle management

### Estimated Impact:
- Memory leak fix: Prevents unbounded growth over time
- Resource usage: 100k goroutines → 4 workers during attack
- Stability: No more panics on config reload
- Performance: O(n log n) sorting (addressed in quick wins)
This commit is contained in:
Ryan Malloy 2025-12-24 23:19:38 -07:00
parent a9d938c64c
commit ca63620316
5 changed files with 371 additions and 84 deletions

View file

@ -104,9 +104,19 @@ func (SIPHandler) CaddyModule() caddy.ModuleInfo {
func (h *SIPHandler) Provision(ctx caddy.Context) error {
h.logger = ctx.Logger()
// Get or create a shared guardian instance from the global registry
// Pass our parsed config so the guardian can be configured
guardian, err := GetOrCreateGuardianWithConfig(ctx, "default", &h.SIPGuardian)
// Get the SIP Guardian app from Caddy's app system (not global registry)
appIface, err := ctx.App("sip_guardian")
if err != nil {
return fmt.Errorf("failed to get sip_guardian app: %w", err)
}
app, ok := appIface.(*SIPGuardianApp)
if !ok {
return fmt.Errorf("sip_guardian app has wrong type: %T", appIface)
}
// Get or create guardian instance from the app
guardian, err := app.GetOrCreateGuardian(ctx, "default", &h.SIPGuardian)
if err != nil {
return err
}
@ -126,7 +136,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
// Check if IP is banned
if h.guardian.IsBanned(host) {
h.logger.Debug("Blocked banned IP", zap.String("ip", host))
if enableMetrics {
if h.guardian.metricsEnabled() {
RecordConnection("blocked")
}
return cx.Close()
@ -134,7 +144,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
// Check if IP is whitelisted - skip further checks
if h.guardian.IsWhitelisted(host) {
if enableMetrics {
if h.guardian.metricsEnabled() {
RecordConnection("allowed")
}
return next.Handle(cx)
@ -146,7 +156,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
zap.String("ip", host),
zap.String("country", country),
)
if enableMetrics {
if h.guardian.metricsEnabled() {
RecordConnection("geo_blocked")
}
return cx.Close()
@ -164,7 +174,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
)
// Record message size metric
if enableMetrics {
if h.guardian.metricsEnabled() {
RecordMessageSize(n)
}
@ -174,7 +184,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
validationResult := validator.Validate(buf)
// Record metrics for violations
if enableMetrics {
if h.guardian.metricsEnabled() {
for _, v := range validationResult.Violations {
RecordValidationViolation(v.Rule)
}
@ -205,7 +215,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
}
if validationResult.ShouldBan {
if enableMetrics {
if h.guardian.metricsEnabled() {
RecordConnection("validation_blocked")
}
h.guardian.RecordFailure(host, validationResult.BanReason)
@ -228,7 +238,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
zap.String("ip", host),
zap.String("method", string(method)),
)
if enableMetrics {
if h.guardian.metricsEnabled() {
RecordConnection("rate_limited")
}
// Record as failure (may trigger ban)
@ -250,7 +260,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
zap.Strings("extensions", result.Extensions),
)
if enableMetrics {
if h.guardian.metricsEnabled() {
RecordEnumerationDetection(result.Reason)
RecordEnumerationExtensions(result.UniqueCount)
RecordConnection("enumeration_blocked")
@ -262,7 +272,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
}
// Emit webhook event
if enableWebhooks {
if h.guardian.webhooksEnabled() {
go EmitEnumerationEvent(h.logger, host, result)
}
@ -272,7 +282,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
}
// Update metrics for tracked IPs
if enableMetrics {
if h.guardian.metricsEnabled() {
stats := detector.GetStats()
if trackedIPs, ok := stats["tracked_ips"].(int); ok {
UpdateEnumerationTrackedIPs(trackedIPs)
@ -288,7 +298,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
zap.String("pattern", suspiciousPattern),
zap.ByteString("sample", buf[:min(64, len(buf))]),
)
if enableMetrics {
if h.guardian.metricsEnabled() {
RecordSuspiciousPattern(suspiciousPattern)
RecordConnection("suspicious")
}
@ -314,7 +324,7 @@ func (h *SIPHandler) Handle(cx *layer4.Connection, next layer4.Handler) error {
}
// Record successful connection
if enableMetrics {
if h.guardian.metricsEnabled() {
RecordConnection("allowed")
}