Leave SWWAF_RATE_LIMIT_EXEMPT_PATHS out of the request rate limits (closes #77)

A request is neither counted nor refused by the request rate limits
when its path, percent-decoded, starts with one of the comma-separated
prefixes in SWWAF_RATE_LIMIT_EXEMPT_PATHS. A request whose decoded path
contains .. or a backslash, or whose path as sent holds an encoded
slash, is never exempt, since an app may act on it as a path outside
every prefix, such as /assets/..%2Flogin as /login. The static lists,
bans and the country lists still apply. The setting is empty by
default, and a prefix that does not start with / stops the start.
README.md documents it.

Model: opus-5-5

internal/proxy/proxy_test.go

@@ -59,6 +59,7 @@ const (
 	denyNets                = "SWWAF_DENY_NETS"
 	rateLimitPerMinute      = "SWWAF_RATE_LIMIT_PER_MINUTE"
 	rateLimitPerDay         = "SWWAF_RATE_LIMIT_PER_DAY"
+	rateLimitExemptPaths    = "SWWAF_RATE_LIMIT_EXEMPT_PATHS"
 	deniedCountries         = "SWWAF_DENIED_COUNTRIES"
 	allowedCountries        = "SWWAF_EXCLUSIVELY_ALLOWED_COUNTRIES"
 	banResponse             = "SWWAF_BAN_RESPONSE"

internal/proxy/ratelimits_test.go

@@ -5,6 +5,7 @@ import (
 	"sync/atomic"
 	"testing"
 
+	"sneak.berlin/go/smallwebwaf/internal/lookup"
 	"sneak.berlin/go/smallwebwaf/internal/requestlog"
 )
 
@@ -69,3 +70,80 @@ func TestRateLimitRefusesBeforeTheApp(t *testing.T) {
 		t.Errorf("the app was called %d times, want 4", calls.Load())
 	}
 }
+
+func TestRateLimitExemptPathsAreNeitherCountedNorRefused(t *testing.T) {
+	t.Parallel()
+
+	const denied = "192.0.2.50" // in SWWAF_DENY_NETS
+
+	s, _, server := startWithClock(t, "", map[string]string{
+		rateLimitPerMinute:   "1",
+		rateLimitExemptPaths: "/assets/,/favicon.ico",
+		denyNets:             denied,
+		deniedCountries:      "kp",
+	})
+
+	// The answers are kept before the requests, so that none waits for
+	// GeoJS.
+	server.GeoJS.Load([]lookup.Answer{
+		keptAnswer(client, "DE"), keptAnswer(fromKP, "KP"),
+	})
+
+	// With a limit of one request a minute, the requests for paths under a
+	// prefix are not counted, so client's first request for / is within
+	// the limit; and once client has reached it, they are not refused.
+	s.request(client, "/assets/app.js", http.StatusOK, requestlog.ActionForward)
+	s.request(client, "/favicon.ico?v=2", http.StatusOK, requestlog.ActionForward)
+	s.get(client, http.StatusOK, requestlog.ActionForward)
+
+	line := s.request(client, "/assets/app.js", http.StatusOK, requestlog.ActionForward)
+	if line.LimitHit != "" {
+		t.Errorf("log line has limit_hit %q, want none", line.LimitHit)
+	}
+
+	// A path outside every prefix is counted: /assets is not under
+	// /assets/, and breaks the limit.
+	s.request(client, "/assets", http.StatusForbidden, requestlog.ActionRateLimited)
+
+	// A ban, SWWAF_DENY_NETS and the country lists still refuse a path
+	// under a prefix.
+	s.request(client, "/assets/app.js", http.StatusForbidden, requestlog.ActionBanned)
+	s.request(denied, "/assets/app.js", http.StatusForbidden, requestlog.ActionDenied)
+	s.request(fromKP, "/assets/app.js",
+		http.StatusForbidden, requestlog.ActionCountryDenied)
+}
+
+func TestRateLimitCountsPathsThatAreNotExempt(t *testing.T) {
+	t.Parallel()
+
+	for _, sent := range []string{
+		// A prefix matches only at the start of the path.
+		"/static/assets/app.js",
+		// .. once percent-decoded: an app may act on these as /login, the
+		// last as a path under /sneak/app/ or as /assets/x.
+		"/assets/../login",
+		"/assets/%2e%2e/login",
+		"/assets/..%2Flogin",
+		"/assets/..;/login",
+		"/sneak/app/src/branch/main/..%2F..%2F..%2F..%2F..%2F..%2Fassets/x",
+		// An encoded slash or a backslash: Go's router takes /assets%2Fx
+		// for one path segment, not a path under /assets/.
+		"/assets%2Fx",
+		"/assets%2fx",
+		`/assets/x\y`,
+	} {
+		t.Run(sent, func(t *testing.T) {
+			t.Parallel()
+
+			s, _, _ := startWithClock(t, "", map[string]string{
+				rateLimitPerMinute:   "1",
+				rateLimitExemptPaths: "/assets/",
+			})
+
+			// Counted, the second request breaks the limit of one request
+			// a minute.
+			s.request(client, sent, http.StatusOK, requestlog.ActionForward)
+			s.request(client, sent, http.StatusForbidden, requestlog.ActionRateLimited)
+		})
+	}
+}

internal/proxy/request.go

@@ -7,7 +7,10 @@ import (
 	"net/http/httptrace"
 	"net/http/httputil"
 	"net/netip"
+	"net/url"
 	"os"
+	"slices"
+	"strings"
 	"sync"
 	"sync/atomic"
 	"time"
@@ -145,7 +148,8 @@ func (rq *request) check(ctx context.Context) *refusal {
 // client either refuses is not looked up, and then the country lists; a
 // request any of them refuses is not counted for the rate limits. Then
 // come the rate limits, unless the client is in
-// SWWAF_RATE_LIMIT_EXEMPT_NETS, so that every other request is counted.
+// SWWAF_RATE_LIMIT_EXEMPT_NETS or the request's path is exempt under
+// SWWAF_RATE_LIMIT_EXEMPT_PATHS, so that every other request is counted.
 // ctx is the request's own context.
 func (rq *request) checkClient(ctx context.Context) string {
 	cfg := rq.h.config
@@ -167,13 +171,37 @@ func (rq *request) checkClient(ctx context.Context) string {
 		return requestlog.ActionCountryDenied
 	}
 
-	if !isInside(rq.client, cfg.RateLimitExemptNets) && rq.limitBroken(now) {
+	exempt := isInside(rq.client, cfg.RateLimitExemptNets) ||
+		pathExempt(rq.in.URL, cfg.RateLimitExemptPaths)
+	if !exempt && rq.limitBroken(now) {
 		return requestlog.ActionRateLimited
 	}
 
 	return ""
 }
 
+// pathExempt reports whether the rate limits leave out a request for u
+// because of SWWAF_RATE_LIMIT_EXEMPT_PATHS: whether its path,
+// percent-decoded, starts with one of prefixes. A request whose decoded
+// path contains .. anywhere or a backslash, or whose path as sent holds
+// an encoded slash (%2F or %2f), never is, since an app may act on it as
+// a path outside every prefix: /assets/..%2Flogin as /login, or
+// /assets%2Fx as one path segment, as Go's router does.
+func pathExempt(u *url.URL, prefixes []string) bool {
+	decoded := u.Path
+	// EscapedPath is the path as the app receives it, not decoded.
+	sent := strings.ToLower(u.EscapedPath())
+
+	if strings.Contains(decoded, "..") || strings.Contains(decoded, `\`) ||
+		strings.Contains(sent, "%2f") {
+		return false
+	}
+
+	return slices.ContainsFunc(prefixes, func(prefix string) bool {
+		return strings.HasPrefix(decoded, prefix)
+	})
+}
+
 // forward passes the request to the app and the app's answer back. ctx
 // is the request's own context.
 func (rq *request) forward(ctx context.Context) {