Merge pull request #522 from 9seconds/sni-router-host-mode-real-ips

sni-router: host-net HAProxy to preserve real client IPs

contrib/sni-router/Caddyfile

 	# to Caddy's access log.  The `tls` wrapper must follow so that TLS
 	# is terminated on the unwrapped connection.
 	#
-	# `allow` lists the networks permitted to send PROXY headers.  These
-	# ranges cover docker compose's default bridge networks; tighten
-	# them if you pin a specific subnet in docker-compose.yml.
+	# `allow` lists the networks permitted to send PROXY headers.
+	# 127.0.0.1/32 covers HAProxy reaching Caddy over host loopback (HAProxy
+	# runs in network_mode: host and connects to the published 127.0.0.1
+	# port).  The RFC1918 ranges cover mtg → Caddy on the compose bridge
+	# (fronting path; see "Fronting loop" in README.md).
 	servers :8443 {
 		listener_wrappers {
 			proxy_protocol {
 				timeout 5s
-				allow 10.0.0.0/8 172.16.0.0/12 192.168.0.0/16
+				allow 127.0.0.1/32 10.0.0.0/8 172.16.0.0/12 192.168.0.0/16
 			}
 			tls
 		}

contrib/sni-router/README.md

 If you disable one, disable all four, otherwise the backend will fail
 to parse the connection.
 
+### Why HAProxy uses `network_mode: host`
+
+A published port on a bridge network rewrites the source IP of inbound
+connections to the bridge gateway before HAProxy sees it (Docker's
+`docker-proxy`, Podman's `slirp4netns`/`pasta`), so the PROXY v2 header
+HAProxy forwards downstream carries that gateway address, not the real
+client.  Host-mode HAProxy binds in the host netns directly, no NAT in
+the path, and the rewrite never happens.  mtg and Caddy stay on the
+compose bridge and are published on `127.0.0.1` only — HAProxy reaches
+them over host loopback.  `mtg-config.toml` does not need to change;
+fronting still uses `host = "web"` over compose-network DNS.
+
+**Trade-offs.**
+- HAProxy owns the host's `:443` and `:80` — don't run anything else
+  on those ports.
+- Linux host only.  On Docker Desktop (macOS/Windows), "host" means
+  the Linux VM, not the user's machine, so external clients can't
+  reach the proxy.
+- If you run Docker with `userns-remap`, the in-container "root"
+  loses the privilege to bind `<1024` on the host; either disable
+  `userns-remap` for this stack or lower `net.ipv4.ip_unprivileged_port_start`
+  on the host.
+
 ## Fronting loop (why `[domain-fronting]` is set explicitly)
 
 When mtg sees TLS that isn't valid Telegram (a probe or a browser

contrib/sni-router/docker-compose.yml

 services:
   haproxy:
     image: haproxy:lts-alpine
-    ports:
-      - "443:443"
-      - "80:80"
+    # Host netns so HAProxy sees real client IPs (v4/v6) instead of the
+    # bridge gateway address.  Linux host only; see README → "Why HAProxy
+    # uses network_mode: host" for the rationale and trade-off.
+    network_mode: host
     volumes:
       - ./haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro,Z
     environment:
       - mtg
       - web
     restart: unless-stopped
-    sysctls:
-      - net.ipv4.ip_unprivileged_port_start=80
 
   mtg:
     # FIXME: :master until #480 lands in a tagged release; switch back to :2/:3 after release
     image: nineseconds/mtg:master
     volumes:
       - ./mtg-config.toml:/config/config.toml:ro,Z
-    expose:
-      - "3128"
+    # Published on host loopback only — HAProxy (host netns) reaches it via
+    # 127.0.0.1.
+    ports:
+      - "127.0.0.1:3128:3128"
     restart: unless-stopped
     extra_hosts:
       - "host.containers.internal:host-gateway"
       - ./Caddyfile:/etc/caddy/Caddyfile:ro,Z
       - caddy_data:/data
       - ./www:/srv:ro,Z
-    expose:
-      - "80"
-      - "8443"
+    # Published on host loopback only — HAProxy reaches Caddy on 127.0.0.1.
+    # Port 8080 (not 80) on the host because HAProxy already owns host :80.
+    ports:
+      - "127.0.0.1:8080:80"
+      - "127.0.0.1:8443:8443"
     environment:
       <<: *domain-env
     restart: unless-stopped

contrib/sni-router/haproxy.cfg

 # --- HTTP :80 — ACME challenges + redirect -----------------------------------
 
 frontend http
-    bind *:80
+    # Explicit v4 + v6 binds so IPv6 clients are accepted regardless of
+    # the host's net.ipv6.bindv6only sysctl.
+    bind :80,[::]:80
     mode http
 
     # Let Caddy answer ACME HTTP-01 challenges for Let's Encrypt.
 # --- TLS :443 — SNI-based routing -------------------------------------------
 
 frontend tls
-    bind *:443
+    bind :443,[::]:443
     tcp-request inspect-delay 5s
     tcp-request content accept if { req_ssl_hello_type 1 }
 
 
     default_backend web
 
+# Backends reach mtg and web on host loopback — they publish to 127.0.0.1
+# (see docker-compose.yml), and HAProxy runs in the host netns
+# (network_mode: host).  PROXY v2 still carries the real client address
+# (v4 or v6) end-to-end, independent of the loopback transport.
+
 backend mtg
     # send-proxy-v2 prepends a PROXY protocol v2 header so mtg sees the
     # real client IP instead of HAProxy's.  mtg must have
     # `proxy-protocol-listener = true` in its config.
-    server mtg mtg:3128 send-proxy-v2
+    server mtg 127.0.0.1:3128 send-proxy-v2
 
 backend web
     # send-proxy-v2 prepends a PROXY protocol v2 header so Caddy logs the
     # real client IP instead of HAProxy's.  Caddy must enable the
     # proxy_protocol listener wrapper on :8443 (see Caddyfile).
-    server web web:8443 send-proxy-v2
+    server web 127.0.0.1:8443 send-proxy-v2
 
 backend web_acme
     mode http
-    server web web:80
+    server web 127.0.0.1:8080