Core Rule Set reads request bodies up to SWWAF_WAF_BODY_LIMIT (closes #116)

SWWAF_WAF_BODY_LIMIT (default off, at most 1G) has the Core Rule Set read
form data and multipart up to the limit, the rest streaming on, and JSON
and XML (with +json, text/json and +xml) no larger than it. The part read
is held for the app. A size or time limit met while reading ends the
request. Content-Encoding is refused again on these kinds. A body Coraza
cannot parse, or a multipart body failing its strict checks, adds 5, but
not a multipart body reaching the limit. Coraza is built with
no_fs_access, so writes no file. Rule 900300 moves to phase 2.

Judgement call: Content-Encoding is refused on a JSON or XML body too
large to read, as SPEC.md allows.

Model: opus-5-5

internal/config/config.go

@@ -244,14 +244,16 @@ type Config struct {
 	// level, from 1 to 4 (SWWAF_WAF_PARANOIA_LEVEL), and
 	// WAFAnomalyThreshold the anomaly score at which a request is a match
 	// (SWWAF_WAF_ANOMALY_THRESHOLD), 0 while it is off. WAFDisabledRules
-	// are the ids of its rules switched off (SWWAF_WAF_DISABLED_RULES), and
+	// are the ids of its rules switched off (SWWAF_WAF_DISABLED_RULES),
 	// WAFExemptPaths the path prefixes it does not inspect
-	// (SWWAF_WAF_EXEMPT_PATHS).
+	// (SWWAF_WAF_EXEMPT_PATHS), and WAFBodyLimit the most of a request body
+	// it reads (SWWAF_WAF_BODY_LIMIT), 0 while it is off and it reads none.
 	WAFMode             string
 	WAFParanoiaLevel    int
 	WAFAnomalyThreshold int
 	WAFDisabledRules    []int
 	WAFExemptPaths      []string
+	WAFBodyLimit        int64
 	// TrapPaths are the paths a request for which is a clear sign of
 	// attack (SWWAF_TRAP_PATHS), each starting with / and without a ?.
 	TrapPaths []string
@@ -396,6 +398,7 @@ var (
 	errNeedsDBPath          = errors.New("it names the file to look clients up in")
 	errDBPathUnused         = errors.New("only file reads it")
 	errNotOver4K            = errors.New("is not a size of more than 4K, such as 32K")
+	errOver1G               = errors.New("is more than 1G, the most Coraza reads")
 	errNotDurationAboveZero = errors.New(
 		"is not a duration above zero, such as 1h or 7d")
 	errNotNumberAboveZero = errors.New(
@@ -559,6 +562,7 @@ func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 		WAFDisabledRules: env.ruleIDs("SWWAF_WAF_DISABLED_RULES",
 			"920340,920420,920440,920640,930130,930140"),
 		WAFExemptPaths:       env.pathPrefixes("SWWAF_WAF_EXEMPT_PATHS", ""),
+		WAFBodyLimit:         env.wafBodyLimit("SWWAF_WAF_BODY_LIMIT", off),
 		TrapPaths:            env.trapPaths("SWWAF_TRAP_PATHS"),
 		ErrorBurstThreshold:  env.count("SWWAF_ERROR_BURST_THRESHOLD", "30"),
 		LogRemoteURL:         env.logRemoteURL("SWWAF_LOG_REMOTE_URL"),
@@ -764,6 +768,15 @@ func (e *environment) size(name, defaultValue string) int64 {
 	return size
 }
 
+// wafBodyLimit reads the setting that is the most of a request body the
+// Core Rule Set reads.
+func (e *environment) wafBodyLimit(name, defaultValue string) int64 {
+	limit, err := parseWAFBodyLimit(e.value(name, defaultValue))
+	e.check(name, err)
+
+	return limit
+}
+
 // headerSize reads the setting that is the largest request line and
 // headers.
 func (e *environment) headerSize(name, defaultValue string) int64 {
@@ -1432,6 +1445,22 @@ func parseHeaderSize(value string) (int64, error) {
 	return size, nil
 }
 
+// parseWAFBodyLimit reads the most of a request body the Core Rule Set
+// reads: a size as parseSize reads it, or off, but at most 1G, since
+// Coraza, which runs the Core Rule Set, refuses to load with more.
+func parseWAFBodyLimit(value string) (int64, error) {
+	limit, err := parseSize(value)
+	if err != nil {
+		return 0, err
+	}
+
+	if limit > gibibyte {
+		return 0, fmt.Errorf("%q %w", value, errOver1G)
+	}
+
+	return limit, nil
+}
+
 // splitUnit splits a size into its number and the bytes its suffix
 // stands for.
 func splitUnit(value string) (string, int64) {

internal/config/config_test.go

@@ -96,6 +96,7 @@ const (
 	wafAnomalyThreshold     = "SWWAF_WAF_ANOMALY_THRESHOLD"
 	wafDisabledRules        = "SWWAF_WAF_DISABLED_RULES"
 	wafExemptPaths          = "SWWAF_WAF_EXEMPT_PATHS"
+	wafBodyLimit            = "SWWAF_WAF_BODY_LIMIT"
 	trapPaths               = "SWWAF_TRAP_PATHS"
 	errorBurstThreshold     = "SWWAF_ERROR_BURST_THRESHOLD"
 	logRemoteURL            = "SWWAF_LOG_REMOTE_URL"
@@ -580,15 +581,20 @@ func TestCoreRuleSetSettings(t *testing.T) {
 			environment{
 				wafMode: config.WAFModeDetect, wafParanoiaLevel: "4", wafAnomalyThreshold: "10",
 				wafDisabledRules: "942100, 920350", wafExemptPaths: "/api/, /static/",
+				wafBodyLimit: "128K",
 			},
 			config.Config{
 				WAFMode: config.WAFModeDetect, WAFParanoiaLevel: 4, WAFAnomalyThreshold: 10,
 				WAFDisabledRules: []int{942100, 920350},
 				WAFExemptPaths:   []string{"/api/", "/static/"},
+				WAFBodyLimit:     128 << 10,
 			},
 		},
 		{
-			environment{wafMode: off, wafAnomalyThreshold: off, wafDisabledRules: ""},
+			environment{
+				wafMode: off, wafAnomalyThreshold: off, wafDisabledRules: "",
+				wafBodyLimit: off,
+			},
 			config.Config{
 				WAFMode: config.WAFModeOff, WAFParanoiaLevel: 1, WAFAnomalyThreshold: 0,
 				WAFDisabledRules: []int{}, WAFExemptPaths: []string{},
@@ -601,6 +607,7 @@ func TestCoreRuleSetSettings(t *testing.T) {
 			WAFMode: cfg.WAFMode, WAFParanoiaLevel: cfg.WAFParanoiaLevel,
 			WAFAnomalyThreshold: cfg.WAFAnomalyThreshold,
 			WAFDisabledRules:    cfg.WAFDisabledRules, WAFExemptPaths: cfg.WAFExemptPaths,
+			WAFBodyLimit: cfg.WAFBodyLimit,
 		}
 		if !reflect.DeepEqual(got, tc.want) {
 			t.Errorf("%v gave\n%+v\nwant\n%+v", tc.env, got, tc.want)
@@ -608,6 +615,15 @@ func TestCoreRuleSetSettings(t *testing.T) {
 	}
 }
 
+func TestWAFBodyLimitOf1G(t *testing.T) {
+	t.Parallel()
+
+	cfg := fromEnvironment(t, environment{wafBodyLimit: "1G"})
+	if cfg.WAFBodyLimit != 1<<30 {
+		t.Errorf("1G read as %d", cfg.WAFBodyLimit)
+	}
+}
+
 func TestInvalidCoreRuleSetSettingStopsTheStart(t *testing.T) {
 	t.Parallel()
 
@@ -636,16 +652,28 @@ func TestInvalidCoreRuleSetSettingStopsTheStart(t *testing.T) {
 			`"-942100" is not the id of a Core Rule Set rule, ` +
 				`a whole number such as 942100`,
 		},
-		// The paranoia level, the allowed methods, the headers refused, and
-		// a request with more query parameters than Coraza keeps.
+		// The paranoia level, the allowed methods, the headers refused, a
+		// request with more query parameters than Coraza keeps, and a body
+		// Coraza cannot parse or that fails its strict checks.
 		{wafDisabledRules, "942100,900000", `"900000"` + setupRule},
 		{wafDisabledRules, "942100,900200", `"900200"` + setupRule},
 		{wafDisabledRules, "942100,900250", `"900250"` + setupRule},
 		{wafDisabledRules, "942100,900300", `"900300"` + setupRule},
+		{wafDisabledRules, "942100,900440", `"900440"` + setupRule},
+		{wafDisabledRules, "942100,900450", `"900450"` + setupRule},
 		{
 			wafExemptPaths, "api/",
 			`"api/" is not a path prefix starting with /, such as /assets/`,
 		},
+		{
+			wafBodyLimit, "128KB",
+			`"128KB" is not a size such as 512K, 100M or 5G, or off`,
+		},
+		{wafBodyLimit, "2G", `"2G" is more than 1G, the most Coraza reads`},
+		{
+			wafBodyLimit, "1073741825",
+			`"1073741825" is more than 1G, the most Coraza reads`,
+		},
 	} {
 		t.Run(tc.name+"="+tc.value, func(t *testing.T) {
 			t.Parallel()
@@ -2403,6 +2431,7 @@ func TestLogsEachSettingWithItsValue(t *testing.T) {
 		wafAnomalyThreshold:     "5",
 		wafDisabledRules:        defaultWAFDisabledRules,
 		wafExemptPaths:          "",
+		wafBodyLimit:            off,
 		trapPaths:               "",
 		errorBurstThreshold:     "30",
 		logRemoteURL:            "",