rproxy and servewaf replace the one-process smallwebwaf (closes #172, closes #165)

`smallwebwaf` with no command now prints the commands and exits with status 2.
The image runs rproxy, or servewaf with SMALLWEBWAF_COMMAND=servewaf. The
passing-on code, its settings and its log fields and metric go. internal/proxy
keeps the checks, answers, reports and own endpoints; its tests run through the
real rproxy. The documents describe the pair.

Judgement call: clients.json keeps token_refused, since state files refuse unknown fields.
Deviation: script/gitea-requests sets SWWAF_LOG_REQUEST_HEADERS, to label requests.

Model: opus-5-5

README.md

@@ -16,7 +16,8 @@ commands that do this together:
   counters and history. One `servewaf` serves many sites.
 
 The site keeps answering while `servewaf` is down, slow or restarting. `rproxy`
-waits 2 seconds for an answer, and then passes the request to the app.
+waits at most 2 seconds for `servewaf`'s answer, and without one passes the
+request to the app.
 
 `rproxy` requires one setting, `SWRP_WAF_BACKEND`, which says where `servewaf`
 is. In a container of its own, it also needs `SWRP_UPSTREAM_URL`, which says
@@ -214,9 +215,9 @@ gave it, and `SWRP_DEFAULT_DISPOSITION` plays no part.
 ## What happens to a request
 
 A request goes through fifteen steps, in this order. Once `servewaf` refuses a
-request, the steps after that are skipped, apart from step 15, and nothing of
+request, the steps after that are skipped, apart from the report of step 15, and
-the request reaches the app. "What happens to a request" in [`SPEC.md`](SPEC.md)
+nothing of the request reaches the app. "What happens to a request" in
-gives each step in full, under the same numbers.
+[`SPEC.md`](SPEC.md) gives each step in full, under the same numbers.
 
 `rproxy` takes the first two:
 
@@ -242,8 +243,9 @@ gives each step in full, under the same numbers.
 `rproxy` takes the rest, with `servewaf` counting at the end:
 
 14. The request is passed to the app.
-15. After the answer, `rproxy` sends `servewaf` a report. `servewaf` counts the
+15. After the answer, `rproxy` sends `servewaf` a report. For an allowed
-    byte limits and adds the request to the client's history.
+    request, `servewaf` counts the byte limits and adds the request to the
+    client's history.
 
 A refused visitor is answered with `SWWAF_BAN_RESPONSE`, `403` by default (see
 "Ban lengths, response and scope" in [`SPEC.md`](SPEC.md)). A `block` rule or a

SPEC.md

@@ -1579,8 +1579,8 @@ It sets no `ENTRYPOINT` or `USER` of its own. The container must start
   `SMALLWEBWAF_COMMAND` names, `rproxy` when it is unset or empty, as the
   `smallwebwaf` user (uid and gid 65532) with runit's `chpst`. For `servewaf`,
   it first makes `SWWAF_STATE_DIR` and every file in it belong to that user. For
-  `rproxy` it changes no owner. With any other value, `smallwebwaf` prints its
+  `rproxy` it changes no owner. With any other value, it starts nothing, and
-  commands and exits, and the health check fails.
+  stops with a message naming `SMALLWEBWAF_COMMAND` and its value.
 
 Every `run` script, the app's included, is a bash script. It starts with
 `#!/usr/bin/env bash` and `set -euo pipefail`, and puts its code in a `main`
@@ -1629,10 +1629,13 @@ says what it checks:
 - With `SMALLWEBWAF_COMMAND=servewaf`, it passes while `servewaf` answers
   `GET /_smallwebwaf/healthz` on `127.0.0.1`, at the port in
   `SWWAF_LISTEN_ADDR`.
-- Otherwise it passes while `rproxy` answers that request on `127.0.0.1`, at the
+- With `SMALLWEBWAF_COMMAND` unset, empty or `rproxy`, it passes while `rproxy`
-  port in `SWRP_LISTEN_ADDR`, and the app accepts connections at
+  answers that request on `127.0.0.1`, at the port in `SWRP_LISTEN_ADDR`, and
-  `SWRP_UPSTREAM_URL`. It does not ask `servewaf`, so that the site stays in
+  the app accepts connections at `SWRP_UPSTREAM_URL`. It does not ask
-  traefik's routes while `servewaf` is down.
+  `servewaf`, so that the site stays in traefik's routes while `servewaf` is
+  down.
+- With any other value, it fails with a message naming `SMALLWEBWAF_COMMAND` and
+  its value.
 
 traefik sends a container no requests until it shows as healthy. So the check
 runs every second from the container's start until it first passes, for up to a

internal/config/config.go

@@ -3,7 +3,8 @@
 // servewaf` start with SWWAF_, every one of them has a default, and most can be
 // given as a file instead. Those of `smallwebwaf rproxy` start with SWRP_. Each
 // of them but SWRP_WAF_BACKEND has a default, and none can be given as a file,
-// since rproxy never touches disk.
+// since rproxy never touches disk. SMALLWEBWAF_COMMAND chooses which of the two
+// the image runs.
 package config
 
 import (
@@ -370,6 +371,7 @@ var (
 	errDBPathUnused    = errors.New("only file reads it")
 	errOver64K         = errors.New(
 		"is more than 64K, the most servewaf gets of a body")
+	errNotCommand           = errors.New("is not rproxy or servewaf")
 	errNotDurationAboveZero = errors.New(
 		"is not a duration above zero, such as 1h or 7d")
 	errNotNumberAboveZero = errors.New(
@@ -570,6 +572,22 @@ func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 	return cfg, nil
 }
 
+// Command reads only SMALLWEBWAF_COMMAND, the command the image runs and its
+// health check checks: rproxy when it is unset or empty, or servewaf. It cannot
+// be given as a file. Any other value is an error that names the setting.
+func Command(lookupEnv func(string) (string, bool)) (string, error) {
+	command, _ := lookupEnv("SMALLWEBWAF_COMMAND")
+
+	switch command {
+	case "", "rproxy":
+		return "rproxy", nil
+	case "servewaf":
+		return command, nil
+	default:
+		return "", fmt.Errorf("SMALLWEBWAF_COMMAND: %q %w", command, errNotCommand)
+	}
+}
+
 // ServeWAFListenAddr reads only SWWAF_LISTEN_ADDR, which may be given as a
 // file, as FromEnvironment does. The health check in servewaf's container needs
 // no other setting, so it reads no other, nor a file that another names.

internal/smallwebwaf/healthcheck.go

@@ -21,11 +21,13 @@ var errHealthEndpoint = errors.New("the health endpoint answered")
 
 // HealthCheck is the container's health check. In servewaf's container, where
 // SMALLWEBWAF_COMMAND is servewaf, it returns 0 while servewaf answers its health
-// endpoint on 127.0.0.1, at the port in SWWAF_LISTEN_ADDR. In any other container
+// endpoint on 127.0.0.1, at the port in SWWAF_LISTEN_ADDR. In rproxy's container,
-// it returns 0 while rproxy answers its health endpoint on 127.0.0.1, at the port
+// where SMALLWEBWAF_COMMAND is rproxy, unset or empty, it returns 0 while rproxy
-// in SWRP_LISTEN_ADDR, and the app accepts connections at the address in
+// answers its health endpoint on 127.0.0.1, at the port in SWRP_LISTEN_ADDR, and
-// SWRP_UPSTREAM_URL. Otherwise it writes why to stderr and returns 1. It reads no
+// the app accepts connections at the address in SWRP_UPSTREAM_URL. Otherwise,
-// other setting, nor a file that another names, so neither can fail it.
+// any other value of SMALLWEBWAF_COMMAND included, it writes why to stderr and
+// returns 1. It reads no other setting, nor a file that another names, so neither
+// can fail it.
 // args are the arguments after `healthcheck`; it takes none, and given
 // one it names it on stderr and returns 1 without checking anything.
 func HealthCheck(
@@ -42,12 +44,17 @@ func HealthCheck(
 	ctx, cancel := context.WithTimeout(ctx, healthCheckTimeout)
 	defer cancel()
 
-	check := checkRProxyAndApp
+	command, err := config.Command(lookupEnv)
-	if command, _ := lookupEnv("SMALLWEBWAF_COMMAND"); command == "servewaf" {
+
-		check = checkServeWAF
+	switch {
+	case err != nil:
+		err = fmt.Errorf("invalid setting: %w", err)
+	case command == "servewaf":
+		err = checkServeWAF(ctx, lookupEnv)
+	default:
+		err = checkRProxyAndApp(ctx, lookupEnv)
 	}
 
-	err := check(ctx, lookupEnv)
 	if err != nil {
 		_, _ = fmt.Fprintln(stderr, "unhealthy:", err)
 

internal/smallwebwaf/healthcheck_test.go

@@ -103,8 +103,13 @@ func TestHealthCheckInRProxysContainer(t *testing.T) {
 	}
 
 	wantHealthCheck(t, settings(), 0, "")
+	wantHealthCheck(t, settings(commandSetting, ""), 0, "")
 	wantHealthCheck(t, settings(commandSetting, "rproxy"), 0, "")
 
+	// SMALLWEBWAF_COMMAND cannot be given as a file.
+	wantHealthCheck(t, settings(commandSetting+"_FILE", writeFile(t, "servewaf\n")),
+		0, "")
+
 	// Another setting does not fail it, even an invalid one, and neither does
 	// SWRP_WAF_BACKEND being unset.
 	wantHealthCheck(t, settings("SWRP_TIMEOUT_MS", "soon"), 0, "")
@@ -127,6 +132,14 @@ func TestHealthCheckInRProxysContainer(t *testing.T) {
 	}, 1, "unhealthy: ask rproxy: ")
 }
 
+func TestHealthCheckFailsWithAnyOtherCommand(t *testing.T) {
+	t.Parallel()
+
+	wantHealthCheck(t, map[string]string{commandSetting: "healthcheck"}, 1,
+		"unhealthy: invalid setting: SMALLWEBWAF_COMMAND: "+
+			"\"healthcheck\" is not rproxy or servewaf\n")
+}
+
 func TestHealthCheckRefusesAnArgument(t *testing.T) {
 	t.Parallel()
 

share/smallwebwaf.run

@@ -3,14 +3,21 @@ set -euo pipefail
 
 # runit's run script for smallwebwaf, run again whenever smallwebwaf
 # exits; the wait spaces out the restarts. SMALLWEBWAF_COMMAND names the
-# command to run: rproxy when it is unset, or servewaf. exec, so that the
+# command to run: rproxy when it is unset or empty, or servewaf. With any
-# signal `sv stop` sends reaches smallwebwaf itself.
+# other value the script starts nothing and stops with a message naming it.
+# exec, so that the signal `sv stop` sends reaches smallwebwaf itself.
 main() {
     sleep 1
     local command="${SMALLWEBWAF_COMMAND:-rproxy}"
-    if [[ "$command" == servewaf ]]; then
+    case "$command" in
-        give_state_dir_to_smallwebwaf
+        rproxy) ;;
-    fi
+        servewaf) give_state_dir_to_smallwebwaf ;;
+        *)
+            printf 'SMALLWEBWAF_COMMAND: "%s" is not rproxy or servewaf\n' \
+                "$command" >&2
+            exit 1
+            ;;
+    esac
     exec chpst -u smallwebwaf:smallwebwaf /usr/local/bin/smallwebwaf "$command"
 }