ServerHello fixes + Docker Health-Check + Conntrack Control for Docker: merge pull request #717 from telemt/flow

ServerHello fixes + Docker Health-Check + Conntrack Control for Docker

Cargo.lock

@@ -2780,7 +2780,7 @@ checksum = "7b2093cf4c8eb1e67749a6762251bc9cd836b6fc171623bd0a9d324d37af2417"
 
 [[package]]
 name = "telemt"
-version = "3.4.2"
+version = "3.4.3"
 dependencies = [
  "aes",
  "anyhow",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "telemt"
-version = "3.4.2"
+version = "3.4.3"
 edition = "2024"
 
 [features]

Dockerfile

@@ -82,6 +82,32 @@ HEALTHCHECK --interval=30s --timeout=5s --start-period=20s --retries=3 CMD ["/ap
 ENTRYPOINT ["/app/telemt"]
 CMD ["config.toml"]
 
+# ==========================
+# Production Netfilter Profile
+# ==========================
+FROM debian:12-slim AS prod-netfilter
+
+RUN set -eux; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+        ca-certificates \
+        conntrack \
+        nftables \
+        iptables; \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY --from=minimal /telemt /app/telemt
+COPY config.toml /app/config.toml
+
+EXPOSE 443 9090 9091
+
+HEALTHCHECK --interval=30s --timeout=5s --start-period=20s --retries=3 CMD ["/app/telemt", "healthcheck", "/app/config.toml", "--mode", "liveness"]
+
+ENTRYPOINT ["/app/telemt"]
+CMD ["config.toml"]
+
 # ==========================
 # Production Distroless on MUSL
 # ==========================

docker-compose.host-netfilter.yml

@@ -0,0 +1,10 @@
+services:
+  telemt:
+    build:
+      context: .
+      target: prod-netfilter
+    network_mode: host
+    ports: []
+    cap_add:
+      - NET_BIND_SERVICE
+      - NET_ADMIN

docker-compose.netfilter.yml

@@ -0,0 +1,8 @@
+services:
+  telemt:
+    build:
+      context: .
+      target: prod-netfilter
+    cap_add:
+      - NET_BIND_SERVICE
+      - NET_ADMIN

docker-compose.yml

@@ -1,7 +1,9 @@
 services:
   telemt:
     image: ghcr.io/telemt/telemt:latest
-    build: .
+    build:
+      context: .
+      target: prod
     container_name: telemt
     restart: unless-stopped
     ports:
@@ -28,7 +30,6 @@ services:
       - ALL
     cap_add:
       - NET_BIND_SERVICE
-      - NET_ADMIN
     read_only: true
     security_opt:
       - no-new-privileges:true

src/api/mod.rs

@@ -41,8 +41,8 @@ use config_store::{current_revision, load_config_from_disk, parse_if_match};
 use events::ApiEventStore;
 use http_utils::{error_response, read_json, read_optional_json, success_response};
 use model::{
-    ApiFailure, CreateUserRequest, DeleteUserResponse, HealthData, HealthReadyData, PatchUserRequest,
-    RotateSecretRequest, SummaryData, UserActiveIps,
+    ApiFailure, CreateUserRequest, DeleteUserResponse, HealthData, HealthReadyData,
+    PatchUserRequest, RotateSecretRequest, SummaryData, UserActiveIps,
 };
 use runtime_edge::{
     EdgeConnectionsCacheEntry, build_runtime_connections_summary_data,

src/config/load.rs

@@ -343,6 +343,10 @@ impl ProxyConfig {
         let network_table = parsed_toml
             .get("network")
             .and_then(|value| value.as_table());
+        let server_table = parsed_toml.get("server").and_then(|value| value.as_table());
+        let conntrack_control_table = server_table
+            .and_then(|table| table.get("conntrack_control"))
+            .and_then(|value| value.as_table());
         let update_every_is_explicit = general_table
             .map(|table| table.contains_key("update_every"))
             .unwrap_or(false);
@@ -372,10 +376,17 @@ impl ProxyConfig {
         let stun_servers_is_explicit = network_table
             .map(|table| table.contains_key("stun_servers"))
             .unwrap_or(false);
+        let inline_conntrack_control_is_explicit = conntrack_control_table
+            .map(|table| table.contains_key("inline_conntrack_control"))
+            .unwrap_or(false);
 
         let mut config: ProxyConfig = parsed_toml
             .try_into()
             .map_err(|e| ProxyError::Config(e.to_string()))?;
+        config
+            .server
+            .conntrack_control
+            .inline_conntrack_control_explicit = inline_conntrack_control_is_explicit;
 
         if !update_every_is_explicit && (legacy_secret_is_explicit || legacy_config_is_explicit) {
             config.general.update_every = None;
@@ -1881,6 +1892,43 @@ mod tests {
         );
     }
 
+    #[test]
+    fn conntrack_inline_explicit_flag_is_false_when_omitted() {
+        let cfg = load_config_from_temp_toml(
+            r#"
+            [general]
+            [network]
+            [server]
+            [server.conntrack_control]
+            [access]
+            "#,
+        );
+        assert!(
+            !cfg.server
+                .conntrack_control
+                .inline_conntrack_control_explicit
+        );
+    }
+
+    #[test]
+    fn conntrack_inline_explicit_flag_is_true_when_present() {
+        let cfg = load_config_from_temp_toml(
+            r#"
+            [general]
+            [network]
+            [server]
+            [server.conntrack_control]
+            inline_conntrack_control = true
+            [access]
+            "#,
+        );
+        assert!(
+            cfg.server
+                .conntrack_control
+                .inline_conntrack_control_explicit
+        );
+    }
+
     #[test]
     fn unknown_sni_action_parses_and_defaults_to_drop() {
         let cfg_default: ProxyConfig = toml::from_str(

src/config/types.rs

@@ -1329,6 +1329,10 @@ pub struct ConntrackControlConfig {
     #[serde(default = "default_conntrack_control_enabled")]
     pub inline_conntrack_control: bool,
 
+    /// Tracks whether inline_conntrack_control was explicitly set in config.
+    #[serde(skip)]
+    pub inline_conntrack_control_explicit: bool,
+
     /// Conntrack mode for listener ingress traffic.
     #[serde(default)]
     pub mode: ConntrackMode,
@@ -1363,6 +1367,7 @@ impl Default for ConntrackControlConfig {
     fn default() -> Self {
         Self {
             inline_conntrack_control: default_conntrack_control_enabled(),
+            inline_conntrack_control_explicit: false,
             mode: ConntrackMode::default(),
             backend: ConntrackBackend::default(),
             profile: ConntrackPressureProfile::default(),

src/conntrack_control.rs

@@ -24,6 +24,13 @@ enum NetfilterBackend {
     Iptables,
 }
 
+#[derive(Clone, Copy)]
+struct ConntrackRuntimeSupport {
+    netfilter_backend: Option<NetfilterBackend>,
+    has_cap_net_admin: bool,
+    has_conntrack_binary: bool,
+}
+
 #[derive(Clone, Copy)]
 struct PressureSample {
     conn_pct: Option<u8>,
@@ -56,11 +63,8 @@ pub(crate) fn spawn_conntrack_controller(
     shared: Arc<ProxySharedState>,
 ) {
     if !cfg!(target_os = "linux") {
-        let enabled = config_rx
-            .borrow()
-            .server
-            .conntrack_control
-            .inline_conntrack_control;
+        let cfg = config_rx.borrow();
+        let enabled = cfg.server.conntrack_control.inline_conntrack_control;
         stats.set_conntrack_control_enabled(enabled);
         stats.set_conntrack_control_available(false);
         stats.set_conntrack_pressure_active(false);
@@ -68,9 +72,14 @@ pub(crate) fn spawn_conntrack_controller(
         stats.set_conntrack_rule_apply_ok(false);
         shared.disable_conntrack_close_sender();
         shared.set_conntrack_pressure_active(false);
-        if enabled {
+        if enabled
+            && cfg
+                .server
+                .conntrack_control
+                .inline_conntrack_control_explicit
+        {
             warn!(
-                "conntrack control is configured but unsupported on this OS; disabling runtime worker"
+                "conntrack control explicitly enabled but unsupported on this OS; disabling runtime worker"
             );
         }
         return;
@@ -92,16 +101,17 @@ async fn run_conntrack_controller(
     let mut cfg = config_rx.borrow().clone();
     let mut pressure_state = PressureState::new(stats.as_ref());
     let mut delete_budget_tokens = cfg.server.conntrack_control.delete_budget_per_sec;
-    let mut backend = pick_backend(cfg.server.conntrack_control.backend);
+    let mut runtime_support = probe_runtime_support(cfg.server.conntrack_control.backend);
+    let mut effective_enabled = effective_conntrack_enabled(&cfg, runtime_support);
 
     apply_runtime_state(
         stats.as_ref(),
         shared.as_ref(),
         &cfg,
-        backend.is_some(),
+        runtime_support,
         false,
     );
-    reconcile_rules(&cfg, backend, stats.as_ref()).await;
+    reconcile_rules(&cfg, runtime_support, stats.as_ref()).await;
 
     loop {
         tokio::select! {
@@ -110,17 +120,18 @@ async fn run_conntrack_controller(
                     break;
                 }
                 cfg = config_rx.borrow_and_update().clone();
-                backend = pick_backend(cfg.server.conntrack_control.backend);
+                runtime_support = probe_runtime_support(cfg.server.conntrack_control.backend);
+                effective_enabled = effective_conntrack_enabled(&cfg, runtime_support);
                 delete_budget_tokens = cfg.server.conntrack_control.delete_budget_per_sec;
-                apply_runtime_state(stats.as_ref(), shared.as_ref(), &cfg, backend.is_some(), pressure_state.active);
-                reconcile_rules(&cfg, backend, stats.as_ref()).await;
+                apply_runtime_state(stats.as_ref(), shared.as_ref(), &cfg, runtime_support, pressure_state.active);
+                reconcile_rules(&cfg, runtime_support, stats.as_ref()).await;
             }
             event = close_rx.recv() => {
                 let Some(event) = event else {
                     break;
                 };
                 stats.set_conntrack_event_queue_depth(close_rx.len() as u64);
-                if !cfg.server.conntrack_control.inline_conntrack_control {
+                if !effective_enabled {
                     continue;
                 }
                 if !pressure_state.active {
@@ -156,6 +167,7 @@ async fn run_conntrack_controller(
                     stats.as_ref(),
                     shared.as_ref(),
                     &cfg,
+                    effective_enabled,
                     &sample,
                     &mut pressure_state,
                 );
@@ -175,20 +187,30 @@ fn apply_runtime_state(
     stats: &Stats,
     shared: &ProxySharedState,
     cfg: &ProxyConfig,
-    backend_available: bool,
+    runtime_support: ConntrackRuntimeSupport,
     pressure_active: bool,
 ) {
     let enabled = cfg.server.conntrack_control.inline_conntrack_control;
-    let available = enabled && backend_available && has_cap_net_admin();
-    if enabled && !available {
+    let available = effective_conntrack_enabled(cfg, runtime_support);
+    if enabled
+        && !available
+        && cfg
+            .server
+            .conntrack_control
+            .inline_conntrack_control_explicit
+    {
         warn!(
-            "conntrack control enabled but unavailable (missing CAP_NET_ADMIN or backend binaries)"
+            has_cap_net_admin = runtime_support.has_cap_net_admin,
+            backend_available = runtime_support.netfilter_backend.is_some(),
+            conntrack_binary_available = runtime_support.has_conntrack_binary,
+            configured_backend = ?cfg.server.conntrack_control.backend,
+            "conntrack control explicitly enabled but unavailable; disabling runtime features"
         );
     }
     stats.set_conntrack_control_enabled(enabled);
     stats.set_conntrack_control_available(available);
-    shared.set_conntrack_pressure_active(enabled && pressure_active);
-    stats.set_conntrack_pressure_active(enabled && pressure_active);
+    shared.set_conntrack_pressure_active(available && pressure_active);
+    stats.set_conntrack_pressure_active(available && pressure_active);
 }
 
 fn collect_pressure_sample(
@@ -228,10 +250,11 @@ fn update_pressure_state(
     stats: &Stats,
     shared: &ProxySharedState,
     cfg: &ProxyConfig,
+    effective_enabled: bool,
     sample: &PressureSample,
     state: &mut PressureState,
 ) {
-    if !cfg.server.conntrack_control.inline_conntrack_control {
+    if !effective_enabled {
         if state.active {
             state.active = false;
             state.low_streak = 0;
@@ -285,22 +308,26 @@ fn update_pressure_state(
     state.low_streak = 0;
 }
 
-async fn reconcile_rules(cfg: &ProxyConfig, backend: Option<NetfilterBackend>, stats: &Stats) {
+async fn reconcile_rules(
+    cfg: &ProxyConfig,
+    runtime_support: ConntrackRuntimeSupport,
+    stats: &Stats,
+) {
     if !cfg.server.conntrack_control.inline_conntrack_control {
         clear_notrack_rules_all_backends().await;
         stats.set_conntrack_rule_apply_ok(true);
         return;
     }
 
-    if !has_cap_net_admin() {
+    if !effective_conntrack_enabled(cfg, runtime_support) {
+        clear_notrack_rules_all_backends().await;
         stats.set_conntrack_rule_apply_ok(false);
         return;
     }
 
-    let Some(backend) = backend else {
-        stats.set_conntrack_rule_apply_ok(false);
-        return;
-    };
+    let backend = runtime_support
+        .netfilter_backend
+        .expect("netfilter backend must be available for effective conntrack control");
 
     let apply_result = match backend {
         NetfilterBackend::Nftables => apply_nft_rules(cfg).await,
@@ -315,6 +342,24 @@ async fn reconcile_rules(cfg: &ProxyConfig, backend: Option<NetfilterBackend>, s
     }
 }
 
+fn probe_runtime_support(configured_backend: ConntrackBackend) -> ConntrackRuntimeSupport {
+    ConntrackRuntimeSupport {
+        netfilter_backend: pick_backend(configured_backend),
+        has_cap_net_admin: has_cap_net_admin(),
+        has_conntrack_binary: command_exists("conntrack"),
+    }
+}
+
+fn effective_conntrack_enabled(
+    cfg: &ProxyConfig,
+    runtime_support: ConntrackRuntimeSupport,
+) -> bool {
+    cfg.server.conntrack_control.inline_conntrack_control
+        && runtime_support.has_cap_net_admin
+        && runtime_support.netfilter_backend.is_some()
+        && runtime_support.has_conntrack_binary
+}
+
 fn pick_backend(configured: ConntrackBackend) -> Option<NetfilterBackend> {
     match configured {
         ConntrackBackend::Auto => {
@@ -710,7 +755,7 @@ mod tests {
             me_queue_pressure_delta: 0,
         };
 
-        update_pressure_state(&stats, shared.as_ref(), &cfg, &sample, &mut state);
+        update_pressure_state(&stats, shared.as_ref(), &cfg, true, &sample, &mut state);
 
         assert!(state.active);
         assert!(shared.conntrack_pressure_active());
@@ -731,7 +776,14 @@ mod tests {
             accept_timeout_delta: 0,
             me_queue_pressure_delta: 0,
         };
-        update_pressure_state(&stats, shared.as_ref(), &cfg, &high_sample, &mut state);
+        update_pressure_state(
+            &stats,
+            shared.as_ref(),
+            &cfg,
+            true,
+            &high_sample,
+            &mut state,
+        );
         assert!(state.active);
 
         let low_sample = PressureSample {
@@ -740,11 +792,11 @@ mod tests {
             accept_timeout_delta: 0,
             me_queue_pressure_delta: 0,
         };
-        update_pressure_state(&stats, shared.as_ref(), &cfg, &low_sample, &mut state);
+        update_pressure_state(&stats, shared.as_ref(), &cfg, true, &low_sample, &mut state);
         assert!(state.active);
-        update_pressure_state(&stats, shared.as_ref(), &cfg, &low_sample, &mut state);
+        update_pressure_state(&stats, shared.as_ref(), &cfg, true, &low_sample, &mut state);
         assert!(state.active);
-        update_pressure_state(&stats, shared.as_ref(), &cfg, &low_sample, &mut state);
+        update_pressure_state(&stats, shared.as_ref(), &cfg, true, &low_sample, &mut state);
 
         assert!(!state.active);
         assert!(!shared.conntrack_pressure_active());
@@ -765,7 +817,7 @@ mod tests {
             me_queue_pressure_delta: 10,
         };
 
-        update_pressure_state(&stats, shared.as_ref(), &cfg, &sample, &mut state);
+        update_pressure_state(&stats, shared.as_ref(), &cfg, false, &sample, &mut state);
 
         assert!(!state.active);
         assert!(!shared.conntrack_pressure_active());

src/healthcheck.rs

@@ -111,7 +111,10 @@ fn probe_target(listen: SocketAddr) -> SocketAddr {
 }
 
 fn build_request(target: SocketAddr, path: &str, auth_header: &str) -> String {
-    let mut request = format!("GET {path} HTTP/1.1\r\nHost: {}\r\nConnection: close\r\n", target);
+    let mut request = format!(
+        "GET {path} HTTP/1.1\r\nHost: {}\r\nConnection: close\r\n",
+        target
+    );
     if !auth_header.is_empty() {
         request.push_str("Authorization: ");
         request.push_str(auth_header);

src/tls_front/emulator.rs

@@ -253,7 +253,18 @@ pub fn build_emulated_server_hello(
     }
 
     // --- ApplicationData (fake encrypted records) ---
-    let mut sizes = jitter_and_clamp_sizes(&emulated_app_data_sizes(cached), rng);
+    let mut sizes = {
+        let base_sizes = emulated_app_data_sizes(cached);
+        match cached.behavior_profile.source {
+            TlsProfileSource::Raw | TlsProfileSource::Merged => base_sizes
+                .into_iter()
+                .map(|size| size.clamp(MIN_APP_DATA, MAX_APP_DATA))
+                .collect(),
+            TlsProfileSource::Default | TlsProfileSource::Rustls => {
+                jitter_and_clamp_sizes(&base_sizes, rng)
+            }
+        }
+    };
     let compact_payload = cached
         .cert_info
         .as_ref()