Add allowed ip check

docs/howto/ingest_geoip.md

@@ -2,26 +2,7 @@
 
 Elasticsearch provides default GeoIP databases that can be downloaded in runtime and which weights ~70 MB. This can be
 a root cause of flakiness of package tests, so elastic-package embeds small samples of GeoIP databases, that can identify
-accurately only few ranges of IP addresses:
-
-```
-1.128.3.4
-175.16.199.1
-216.160.83.57
-216.160.83.61
-67.43.156.12
-81.2.69.143
-81.2.69.144
-81.2.69.145
-81.2.69.193
-89.160.20.112
-89.160.20.156
-67.43.156.12
-67.43.156.13
-67.43.156.14
-67.43.156.15
-2a02:cf40:add:4002:91f2:a9b2:e09a:6fc6
-```
+accurately only few ranges of IP addresses included [here](../../internal/fields/_static/allowed_geo_ips.txt)
 
 If you want the ingest pipeline to include a "geo" section in the event, feel free to use one of above IP addresses.
 Embedded databases contain information about: cities, countries and ASNs.

internal/fields/_static/allowed_geo_ips.txt

@@ -0,0 +1,15 @@
+1.128.3.4
+175.16.199.1
+216.160.83.57
+216.160.83.61
+81.2.69.143
+81.2.69.144
+81.2.69.145
+81.2.69.193
+89.160.20.112
+89.160.20.156
+67.43.156.12
+67.43.156.13
+67.43.156.14
+67.43.156.15
+2a02:cf40:add:4002:91f2:a9b2:e09a:6fc6

internal/fields/validate.go

@@ -5,8 +5,10 @@
 package fields
 
 import (
+	_ "embed"
 	"encoding/json"
 	"fmt"
+	"net"
 	"os"
 	"path/filepath"
 	"regexp"
@@ -31,6 +33,9 @@ type Validator struct {
 	numericKeywordFields     map[string]struct{}
 
 	disabledDependencyManagement bool
+
+	enabledAllowedIPCheck bool
+	allowedIPs            map[string]struct{}
 }
 
 // ValidatorOption represents an optional flag that can be passed to  CreateValidatorForDataStream.
@@ -64,6 +69,14 @@ func WithDisabledDependencyManagement() ValidatorOption {
 	}
 }
 
+// WithEnabledAllowedIPCheck configures the validator to perform check on the IP values against an allowed list.
+func WithEnabledAllowedIPCheck() ValidatorOption {
+	return func(v *Validator) error {
+		v.enabledAllowedIPCheck = true
+		return nil
+	}
+}
+
 // CreateValidatorForDataStream function creates a validator for the data stream.
 func CreateValidatorForDataStream(dataStreamRootPath string, opts ...ValidatorOption) (v *Validator, err error) {
 	v = new(Validator)
@@ -72,6 +85,9 @@ func CreateValidatorForDataStream(dataStreamRootPath string, opts ...ValidatorOp
 			return nil, err
 		}
 	}
+
+	v.allowedIPs = initializeAllowedIPsList()
+
 	v.Schema, err = loadFieldsForDataStream(dataStreamRootPath)
 	if err != nil {
 		return nil, errors.Wrapf(err, "can't load fields for data stream (path: %s)", dataStreamRootPath)
@@ -99,6 +115,25 @@ func CreateValidatorForDataStream(dataStreamRootPath string, opts ...ValidatorOp
 	return v, nil
 }
 
+//go:embed _static/allowed_geo_ips.txt
+var allowedGeoIPs string
+
+func initializeAllowedIPsList() map[string]struct{} {
+	m := map[string]struct{}{
+		"0.0.0.0": {}, "255.255.255.255": {},
+		"0:0:0:0:0:0:0:0": {}, "ffff:ffff:ffff:ffff:ffff:ffff:ffff:ffff": {},
+	}
+	for _, ip := range strings.Split(allowedGeoIPs, "\n") {
+		ip = strings.Trim(ip, " \n\t")
+		if ip == "" {
+			continue
+		}
+		m[ip] = struct{}{}
+	}
+
+	return m
+}
+
 func loadFieldsForDataStream(dataStreamRootPath string) ([]FieldDefinition, error) {
 	fieldsDir := filepath.Join(dataStreamRootPath, "fields")
 	files, err := filepath.Glob(filepath.Join(fieldsDir, "*.yml"))
@@ -306,7 +341,7 @@ func (v *Validator) parseElementValue(key string, definition FieldDefinition, va
 		if err := ensurePatternMatches(key, valStr, definition.Pattern); err != nil {
 			return err
 		}
-	case "date", "ip", "keyword", "text":
+	case "date", "keyword", "text":
 		var valStr string
 		valStr, valid = val.(string)
 		if !valid {
@@ -316,6 +351,20 @@ func (v *Validator) parseElementValue(key string, definition FieldDefinition, va
 		if err := ensurePatternMatches(key, valStr, definition.Pattern); err != nil {
 			return err
 		}
+	case "ip":
+		var valStr string
+		valStr, valid = val.(string)
+		if !valid {
+			break
+		}
+
+		if err := ensurePatternMatches(key, valStr, definition.Pattern); err != nil {
+			return err
+		}
+
+		if v.enabledAllowedIPCheck && !v.isAllowedIPValue(valStr) {
+			return fmt.Errorf("the IP %q is not one of the allowed test IPs", valStr)
+		}
 	case "float", "long", "double":
 		_, valid = val.(float64)
 	default:
@@ -328,6 +377,30 @@ func (v *Validator) parseElementValue(key string, definition FieldDefinition, va
 	return nil
 }
 
+// isAllowedIPValue checks if the provided IP is allowed for testing
+// The set of allowed IPs are:
+// - private IPs as described in RFC 1918 & RFC 4193
+// - public IPs allowed by MaxMind for testing
+// - 0.0.0.0 and 255.255.255.255 for IPv4
+// - 0:0:0:0:0:0:0:0 and ffff:ffff:ffff:ffff:ffff:ffff:ffff:ffff for IPv6
+func (v *Validator) isAllowedIPValue(s string) bool {
+	if _, found := v.allowedIPs[s]; found {
+		return true
+	}
+
+	ip := net.ParseIP(s)
+	if ip == nil {
+		return false
+	}
+
+	if ip.IsPrivate() || ip.IsLoopback() ||
+		ip.IsLinkLocalUnicast() || ip.IsLinkLocalMulticast() {
+		return true
+	}
+
+	return false
+}
+
 // ensureSingleElementValue extracts single entity from a potential array, which is a valid field representation
 // in Elasticsearch. For type assertion we need a single value.
 func ensureSingleElementValue(val interface{}) (interface{}, bool) {

internal/testrunner/runners/pipeline/runner.go

@@ -131,7 +131,11 @@ func (r *runner) run() ([]testrunner.TestResult, error) {
 
 		tr.TimeElapsed = time.Since(startTime)
 		fieldsValidator, err := fields.CreateValidatorForDataStream(dataStreamPath,
-			fields.WithNumericKeywordFields(tc.config.NumericKeywordFields))
+			fields.WithNumericKeywordFields(tc.config.NumericKeywordFields),
+			// explicitly enabled for pipeline tests only
+			// since system tests can have dynamic public IPs
+			fields.WithEnabledAllowedIPCheck(),
+		)
 		if err != nil {
 			return nil, errors.Wrapf(err, "creating fields validator for data stream failed (path: %s, test case file: %s)", dataStreamPath, testCaseFile)
 		}