feat: Enable opa authorization

CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 
 ## [Unreleased]
 
+### Added
+
+- Add OPA authorization using the operator-rs `OpaConfig` ([#652]).
+
+[#652]: https://github.com/stackabletech/hive-operator/pull/652
+
 ## [25.11.0] - 2025-11-07
 
 ## [25.11.0-rc1] - 2025-11-06

deploy/helm/hive-operator/crds/crds.yaml

@@ -49,6 +49,33 @@ spec:
                       required:
                         - kerberos
                       type: object
+                    authorization:
+                      description: |-
+                        Authorization options for Hive.
+                        Learn more in the [Hive authorization usage guide](https://docs.stackable.tech/home/nightly/hive/usage-guide/security#authorization).
+                      nullable: true
+                      properties:
+                        opa:
+                          description: |-
+                            Configure the OPA stacklet [discovery ConfigMap](https://docs.stackable.tech/home/nightly/concepts/service_discovery)
+                            and the name of the Rego package containing your authorization rules.
+                            Consult the [OPA authorization documentation](https://docs.stackable.tech/home/nightly/concepts/opa)
+                            to learn how to deploy Rego authorization rules with OPA.
+                          nullable: true
+                          properties:
+                            configMapName:
+                              description: |-
+                                The [discovery ConfigMap](https://docs.stackable.tech/home/nightly/concepts/service_discovery)
+                                for the OPA stacklet that should be used for authorization requests.
+                              type: string
+                            package:
+                              description: The name of the Rego package containing the Rego rules for the product.
+                              nullable: true
+                              type: string
+                          required:
+                            - configMapName
+                          type: object
+                      type: object
                     database:
                       description: Database connection specification for the metadata database.
                       properties:

docs/modules/hive/pages/usage-guide/security.adoc

@@ -1,5 +1,6 @@
 = Security
 :description: Secure Apache Hive with Kerberos authentication in Kubernetes. Configure Kerberos server, SecretClass, and access Hive securely with provided guides.
+:opa-rego-docs: https://www.openpolicyagent.org/docs/latest/#rego
 
 == Authentication
 Currently, the only supported authentication mechanism is Kerberos, which is disabled by default.
@@ -45,3 +46,118 @@ The `kerberos.secretClass` is used to give Hive the possibility to request keyta
 === 5. Access Hive
 In case you want to access Hive it is recommended to start up a client Pod that connects to Hive, rather than shelling into the master.
 We have an https://github.com/stackabletech/hive-operator/blob/main/tests/templates/kuttl/kerberos/70-install-access-hive.yaml.j2[integration test] for this exact purpose, where you can see how to connect and get a valid keytab.
+
+
+== Authorization
+The Stackable Operator for Apache Hive supports the following authorization methods.
+
+=== Open Policy Agent (OPA)
+The Apache Hive metastore can be configured to delegate authorization decisions to an Open Policy Agent (OPA) instance.
+More information on the setup and configuration of OPA can be found in the xref:opa:index.adoc[OPA Operator documentation].
+A Hive cluster can be configured using OPA authorization by adding this section to the configuration:
+
+[source,yaml]
+----
+spec:
+  clusterConfig:
+    authorization:
+      opa:
+        configMapName: opa # <1>
+        package: hms # <2>
+----
+<1> The name of your OPA Stacklet (`opa` in this case)
+<2> The rego rule package to use for policy decisions.
+This is optional and defaults to the name of the Hive Stacklet.
+
+==== Defining rego rules
+For a general explanation of how rules are written, please refer to the {opa-rego-docs}[OPA documentation].
+Authorization with OPA is done using the https://github.com/boschglobal/hive-metastore-opa-authorizer[hive-metastore-opa-authorizer] plugin.
+
+===== OPA Inputs
+The payload sent by Hive with each request to OPA, that is accessible within the rego rules, has the following structure:
+
+[source,json]
+----
+{
+  "identity": {
+    "username": "<user>",
+    "groups": ["<group1>", "<group2>"]
+  },
+  "resources": {
+    "database": null,
+    "table": null,
+    "partition": null,
+    "columns": ["col1", "col2"]
+  },
+  "privileges": {
+    "readRequiredPriv": [],
+    "writeRequiredPriv": [],
+    "inputs": null,
+    "outputs": null
+  }
+}
+----
+* `identity`: Contains user information.
+** `username`: The name of the user.
+** `groups`: A list of groups the user belongs to.
+* `resources`: Specifies the resources involved in the request.
+** `database`: The database object.
+** `table`: The table object.
+** `partition`: The partition object.
+** `columns`: A list of column names involved in the request.
+* `privileges`: Details the privileges required for the request.
+** `readRequiredPriv`: A list of required read privileges.
+** `writeRequiredPriv`: A list of required write privileges.
+** `inputs`: Input tables for the request.
+** `outputs`: Output tables for the request.
+
+===== Example OPA Rego Rule
+Below is a basic rego rule that demonstrates how to handle input dictionary sent from the hive authorizer to OPA:
+
+[source,rego]
+----
+package hms
+
+default database_allow = false
+default table_allow = false
+default column_allow = false
+default partition_allow = false
+default user_allow = false
+
+database_allow if {
+  input.identity.username == "stackable"
+  input.resources.database.name == "test_db"
+}
+
+table_allow if {
+  input.identity.username == "stackable"
+  input.resources.table.dbName == "test_db"
+  input.resources.table.tableName == "test_table"
+  input.privileges.readRequiredPriv[0].priv == "SELECT"
+}
+
+table_allow if {
+  input.identity.username == "stackable"
+  input.resources.table.dbName == "test_db"
+  input.privileges.writeRequiredPriv[0].priv == "CREATE"
+}
+----
+* `database_allow` grants access if the user is `stackable` and the database is `test_db`.
+* `table_allow` grants access if the user is `stackable`, the database is `test_db` and:
+** the table is `test_table` and the required read privilege is `SELECT`.
+** the required write privilege is `CREATE` without any table restriction.
+
+==== Configuring policy URLs
+
+The `database_allow`, `table_allow`, `column_allow`, `partition_allow`, and `user_allow` policy URLs can be xref:usage-guide/overrides.adoc#_configuration_properties[config overridden] using the properties in `hive-site.xml`:
+
+* `com.bosch.bdps.opa.authorization.policy.url.database`
+* `com.bosch.bdps.opa.authorization.policy.url.table`
+* `com.bosch.bdps.opa.authorization.policy.url.column`
+* `com.bosch.bdps.opa.authorization.policy.url.partition`
+* `com.bosch.bdps.opa.authorization.policy.url.user`
+
+==== TLS secured OPA cluster
+
+Stackable OPA clusters secured via TLS are supported and no further configuration is required.
+The Stackable Hive operator automatically adds the certificate from the SecretClass used to secure the OPA cluster to its trust.

examples/hive-opa-cluster.yaml

@@ -0,0 +1,89 @@
+# helm install postgresql oci://registry-1.docker.io/bitnamicharts/postgresql \
+#   --version 16.5.0 \
+#   --namespace default \
+#   --set image.repository=bitnamilegacy/postgresql \
+#   --set volumePermissions.image.repository=bitnamilegacy/os-shell \
+#   --set metrics.image.repository=bitnamilegacy/postgres-exporter \
+#   --set global.security.allowInsecureImages=true \
+#   --set auth.username=hive \
+#   --set auth.password=hive \
+#   --set auth.database=hive \
+#   --set primary.extendedConfiguration="password_encryption=md5" \
+#   --wait
+---
+apiVersion: hive.stackable.tech/v1alpha1
+kind: HiveCluster
+metadata:
+  name: hive
+spec:
+  image:
+    productVersion: 4.1.0
+    pullPolicy: IfNotPresent
+  clusterConfig:
+    authorization:
+      opa:
+        configMapName: opa
+        package: hms
+    database:
+      connString: jdbc:postgresql://postgresql:5432/hive
+      credentialsSecret: hive-postgresql-credentials
+      dbType: postgres
+  metastore:
+    roleGroups:
+      default:
+        replicas: 1
+        config:
+          resources:
+            cpu:
+              min: 300m
+              max: "2"
+            memory:
+              limit: 5Gi
+---
+apiVersion: v1
+kind: Secret
+metadata:
+  name: hive-postgresql-credentials
+type: Opaque
+stringData:
+  username: hive
+  password: hive
+---
+apiVersion: opa.stackable.tech/v1alpha1
+kind: OpaCluster
+metadata:
+  name: opa
+spec:
+  image:
+    productVersion: 1.8.0
+  servers:
+    config:
+      logging:
+        enableVectorAgent: false
+        containers:
+          opa:
+            console:
+              level: INFO
+            file:
+              level: INFO
+            loggers:
+              decision:
+                level: INFO
+    roleGroups:
+      default: {}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: hive-opa-bundle
+  labels:
+    opa.stackable.tech/bundle: "hms"
+data:
+  hive.rego: |
+    package hms
+
+    database_allow = true
+    table_allow = true
+    column_allow = true
+    partition_allow = true
+    user_allow = true

rust/operator-binary/src/command.rs

@@ -1,16 +1,20 @@
 use stackable_operator::crd::s3;
 
-use crate::crd::{
-    DB_PASSWORD_ENV, DB_PASSWORD_PLACEHOLDER, DB_USERNAME_ENV, DB_USERNAME_PLACEHOLDER,
-    HIVE_METASTORE_LOG4J2_PROPERTIES, HIVE_SITE_XML, STACKABLE_CONFIG_DIR,
-    STACKABLE_CONFIG_MOUNT_DIR, STACKABLE_LOG_CONFIG_MOUNT_DIR, STACKABLE_TRUST_STORE,
-    STACKABLE_TRUST_STORE_PASSWORD, v1alpha1,
+use crate::{
+    config::opa::HiveOpaConfig,
+    crd::{
+        DB_PASSWORD_ENV, DB_PASSWORD_PLACEHOLDER, DB_USERNAME_ENV, DB_USERNAME_PLACEHOLDER,
+        HIVE_METASTORE_LOG4J2_PROPERTIES, HIVE_SITE_XML, STACKABLE_CONFIG_DIR,
+        STACKABLE_CONFIG_MOUNT_DIR, STACKABLE_LOG_CONFIG_MOUNT_DIR, STACKABLE_TRUST_STORE,
+        STACKABLE_TRUST_STORE_PASSWORD, v1alpha1,
+    },
 };
 
 pub fn build_container_command_args(
     hive: &v1alpha1::HiveCluster,
     start_command: String,
     s3_connection_spec: Option<&s3::v1alpha1::ConnectionSpec>,
+    hive_opa_config: Option<&HiveOpaConfig>,
 ) -> Vec<String> {
     let mut args = vec![
         // copy config files to a writeable empty folder in order to set s3 access and secret keys
@@ -51,6 +55,14 @@ pub fn build_container_command_args(
         }
     }
 
+    if let Some(opa) = hive_opa_config {
+        if let Some(ca_cert_dir) = opa.tls_ca_cert_mount_path() {
+            args.push(format!(
+                "cert-tools generate-pkcs12-truststore --pkcs12 {STACKABLE_TRUST_STORE}:{STACKABLE_TRUST_STORE_PASSWORD} --pem {ca_cert_dir}/ca.crt --out {STACKABLE_TRUST_STORE} --out-password {STACKABLE_TRUST_STORE_PASSWORD}"
+            ));
+        }
+    }
+
     // db credentials
     args.extend([
         format!("echo replacing {DB_USERNAME_PLACEHOLDER} and {DB_PASSWORD_PLACEHOLDER} with secret values."),

rust/operator-binary/src/config/mod.rs

@@ -1 +1,2 @@
 pub mod jvm;
+pub mod opa;