[KYUUBI #6118] Migrate to shaded HMS client for getting delegation to…

…ken on server # 🔍 Description ## Issue References 🔗 ## Describe Your Solution 🔧 Kyuubi Shaded 0.3 introduces a light kyuubi-relocated-hive-metastore-client, for refreshing delegation token, this PR aims to migrate from the vanilla HMS client to this light shaded HMS client, then we can get rid of Hive dependencies, especially the vulnerable thrift 0.9, from the Kyuubi server. ## Types of changes 🔖 - [ ] Bugfix (non-breaking change which fixes an issue) - [ ] New feature (non-breaking change which adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) ## Test Plan 🧪 Pass GA. --- # Checklist 📝 - [x] This patch was not authored or co-authored using [Generative Tooling](https://www.apache.org/legal/generative-tooling.html) **Be nice. Be informative.** Closes #6118 from zhouyifan279/relocated-hms-client. Closes #6118 4d7e509 [Cheng Pan] comment 845e39f [Cheng Pan] notice b4a58a6 [Cheng Pan] Update NOTICE f4bfa93 [zhouyifan279] Use kyuubi-relocated-hive-metastore-client af17be1 [zhouyifan279] Use kyuubi-relocated-hive-metastore-client Lead-authored-by: zhouyifan279 <[email protected]> Co-authored-by: Cheng Pan <[email protected]> Signed-off-by: Cheng Pan <[email protected]>
apache · Mar 8, 2024 · 6fc7552 · 6fc7552
1 parent 02bf4f0
commit 6fc7552
Show file tree

Hide file tree

Showing 8 changed files with 45 additions and 54 deletions.
diff --git a/LICENSE-binary b/LICENSE-binary
@@ -230,14 +230,6 @@ com.google.guava:failureaccess
 com.google.guava:guava
 org.apache.hadoop:hadoop-client-api
 org.apache.hadoop:hadoop-client-runtime
-org.apache.hive:hive-common
-org.apache.hive:hive-metastore
-org.apache.hive:hive-standalone-metastore
-org.apache.hive:hive-llap-client
-org.apache.hive:hive-serde
-org.apache.hive:hive-service-rpc
-org.apache.hive:hive-shims-0.23
-org.apache.hive:hive-shims-common
 com.google.j2objc:j2objc-annotations
 com.fasterxml.jackson.core:jackson-annotations
 com.fasterxml.jackson.core:jackson-core
@@ -270,8 +262,6 @@ org.eclipse.jetty:jetty-servlet
 org.eclipse.jetty:jetty-util-ajax
 org.eclipse.jetty:jetty-util
 org.eclipse.jetty:jetty-proxy
-org.apache.thrift:libfb303
-org.apache.thrift:libthrift
 org.apache.logging.log4j:log4j-1.2-api
 org.apache.logging.log4j:log4j-api
 org.apache.logging.log4j:log4j-core

diff --git a/NOTICE-binary b/NOTICE-binary
@@ -198,33 +198,12 @@ Copyright 2022 The Apache Software Foundation
 Hive JDBC
 Copyright 2022 The Apache Software Foundation
 
-Hive Llap Client
-Copyright 2022 The Apache Software Foundation
-
-Hive Metastore
-Copyright 2022 The Apache Software Foundation
-
-Hive Serde
-Copyright 2022 The Apache Software Foundation
-
 Hive Service
 Copyright 2022 The Apache Software Foundation
 
 Hive Service RPC
 Copyright 2022 The Apache Software Foundation
 
-Hive Shims 0.23
-Copyright 2022 The Apache Software Foundation
-
-Hive Shims Common
-Copyright 2022 The Apache Software Foundation
-
-Hive Standalone Metastore
-Copyright 2022 The Apache Software Foundation
-
-Hive Storage API
-Copyright 2020 The Apache Software Foundation
-
 Apache HttpClient
 Copyright 1999-2020 The Apache Software Foundation
 
@@ -798,9 +777,6 @@ Permission to use, copy, modify and distribute UnixCrypt
 for non-commercial or commercial purposes and without fee is
 granted provided that the copyright notice appears in all copies.
 
-Apache Thrift
-Copyright 2006-2010 The Apache Software Foundation.
-
 Apache Log4j 1.x Compatibility API
 Copyright 1999-2022 The Apache Software Foundation
 

diff --git a/dev/dependencyList b/dev/dependencyList
@@ -51,14 +51,6 @@ gson/2.10.1//gson-2.10.1.jar
 guava/32.0.1-jre//guava-32.0.1-jre.jar
 hadoop-client-api/3.3.6//hadoop-client-api-3.3.6.jar
 hadoop-client-runtime/3.3.6//hadoop-client-runtime-3.3.6.jar
-hive-common/3.1.3//hive-common-3.1.3.jar
-hive-metastore/3.1.3//hive-metastore-3.1.3.jar
-hive-serde/3.1.3//hive-serde-3.1.3.jar
-hive-service-rpc/3.1.3//hive-service-rpc-3.1.3.jar
-hive-shims-0.23/3.1.3//hive-shims-0.23-3.1.3.jar
-hive-shims-common/3.1.3//hive-shims-common-3.1.3.jar
-hive-standalone-metastore/3.1.3//hive-standalone-metastore-3.1.3.jar
-hive-storage-api/2.7.0//hive-storage-api-2.7.0.jar
 hk2-api/2.6.1//hk2-api-2.6.1.jar
 hk2-locator/2.6.1//hk2-locator-2.6.1.jar
 hk2-utils/2.6.1//hk2-utils-2.6.1.jar
@@ -133,8 +125,6 @@ kubernetes-model-rbac/6.8.1//kubernetes-model-rbac-6.8.1.jar
 kubernetes-model-resource/6.8.1//kubernetes-model-resource-6.8.1.jar
 kubernetes-model-scheduling/6.8.1//kubernetes-model-scheduling-6.8.1.jar
 kubernetes-model-storageclass/6.8.1//kubernetes-model-storageclass-6.8.1.jar
-libfb303/0.9.3//libfb303-0.9.3.jar
-libthrift/0.9.3//libthrift-0.9.3.jar
 log4j-1.2-api/2.20.0//log4j-1.2-api-2.20.0.jar
 log4j-api/2.20.0//log4j-api-2.20.0.jar
 log4j-core/2.20.0//log4j-core-2.20.0.jar

diff --git a/kyuubi-server/pom.xml b/kyuubi-server/pom.xml
@@ -78,6 +78,12 @@
             <version>${project.version}</version>
         </dependency>
 
+        <dependency>
+            <groupId>org.apache.kyuubi</groupId>
+            <artifactId>kyuubi-relocated-hive-metastore-client</artifactId>
+            <version>${kyuubi-relocated.version}</version>
+        </dependency>
+
         <dependency>
             <groupId>org.antlr</groupId>
             <artifactId>antlr4-runtime</artifactId>
@@ -107,6 +113,7 @@
             <groupId>org.apache.hive</groupId>
             <artifactId>hive-metastore</artifactId>
             <version>${hive.version}</version>
+            <scope>test</scope>
             <exclusions>
                 <exclusion>
                     <groupId>*</groupId>
@@ -119,6 +126,7 @@
             <groupId>org.apache.hive</groupId>
             <artifactId>hive-standalone-metastore</artifactId>
             <version>${hive.version}</version>
+            <scope>test</scope>
             <exclusions>
                 <exclusion>
                     <groupId>*</groupId>
@@ -131,6 +139,7 @@
             <groupId>org.apache.hive</groupId>
             <artifactId>hive-serde</artifactId>
             <version>${hive.version}</version>
+            <scope>test</scope>
             <exclusions>
                 <exclusion>
                     <groupId>*</groupId>
@@ -143,6 +152,7 @@
             <groupId>org.apache.hive.shims</groupId>
             <artifactId>hive-shims-common</artifactId>
             <version>${hive.version}</version>
+            <scope>test</scope>
             <exclusions>
                 <exclusion>
                     <groupId>*</groupId>
@@ -155,6 +165,7 @@
             <groupId>org.apache.hive.shims</groupId>
             <artifactId>hive-shims-0.23</artifactId>
             <version>${hive.version}</version>
+            <scope>test</scope>
             <exclusions>
                 <exclusion>
                     <groupId>*</groupId>
@@ -167,6 +178,7 @@
             <groupId>org.apache.hive</groupId>
             <artifactId>hive-common</artifactId>
             <version>${hive.version}</version>
+            <scope>test</scope>
             <exclusions>
                 <exclusion>
                     <groupId>*</groupId>
@@ -179,6 +191,7 @@
             <groupId>org.apache.hive</groupId>
             <artifactId>hive-storage-api</artifactId>
             <version>${hive.storage-api.version}</version>
+            <scope>test</scope>
             <exclusions>
                 <exclusion>
                     <groupId>*</groupId>
@@ -190,16 +203,19 @@
         <dependency>
             <groupId>org.apache.thrift</groupId>
             <artifactId>libfb303</artifactId>
+            <scope>test</scope>
         </dependency>
 
         <dependency>
             <groupId>org.apache.thrift</groupId>
             <artifactId>libthrift</artifactId>
+            <scope>test</scope>
         </dependency>
 
         <dependency>
             <groupId>org.apache.hive</groupId>
             <artifactId>hive-service-rpc</artifactId>
+            <scope>test</scope>
         </dependency>
 
         <dependency>

diff --git a/...ver/src/main/resources/META-INF/services/org.apache.hadoop.security.token.TokenIdentifier b/...ver/src/main/resources/META-INF/services/org.apache.hadoop.security.token.TokenIdentifier
@@ -15,4 +15,4 @@
 # limitations under the License.
 #
 
-org.apache.hadoop.hive.metastore.security.DelegationTokenIdentifier
+org.apache.kyuubi.shaded.hive.metastore.security.DelegationTokenIdentifier
diff --git a/kyuubi-server/src/main/scala/org/apache/kyuubi/credentials/HiveDelegationTokenProvider.scala b/kyuubi-server/src/main/scala/org/apache/kyuubi/credentials/HiveDelegationTokenProvider.scala
@@ -18,16 +18,16 @@
 package org.apache.kyuubi.credentials
 
 import org.apache.hadoop.conf.Configuration
-import org.apache.hadoop.hive.conf.HiveConf
-import org.apache.hadoop.hive.metastore.{IMetaStoreClient, RetryingMetaStoreClient}
-import org.apache.hadoop.hive.metastore.security.DelegationTokenIdentifier
 import org.apache.hadoop.io.Text
 import org.apache.hadoop.security.{Credentials, SecurityUtil}
 import org.apache.hadoop.security.UserGroupInformation.AuthenticationMethod
 import org.apache.hadoop.security.token.Token
 
 import org.apache.kyuubi.Logging
 import org.apache.kyuubi.config.KyuubiConf
+import org.apache.kyuubi.shaded.hive.metastore.{IMetaStoreClient, RetryingMetaStoreClient}
+import org.apache.kyuubi.shaded.hive.metastore.conf.MetastoreConf
+import org.apache.kyuubi.shaded.hive.metastore.security.DelegationTokenIdentifier
 
 class HiveDelegationTokenProvider extends HadoopDelegationTokenProvider with Logging {
 
@@ -38,7 +38,7 @@ class HiveDelegationTokenProvider extends HadoopDelegationTokenProvider with Log
   override def serviceName: String = "hive"
 
   override def initialize(hadoopConf: Configuration, kyuubiConf: KyuubiConf): Unit = {
-    val conf = new HiveConf(hadoopConf, classOf[HiveConf])
+    val conf = MetastoreConf.newMetastoreConf(hadoopConf)
     val metastoreUris = conf.getTrimmed("hive.metastore.uris", "")
     // SQL engine requires token alias to be `hive.metastore.uris`
     tokenAlias = new Text(metastoreUris)
@@ -51,7 +51,7 @@ class HiveDelegationTokenProvider extends HadoopDelegationTokenProvider with Log
       principal = conf.getTrimmed(principalKey, "")
       require(principal.nonEmpty, s"Hive principal $principalKey undefined")
 
-      client = Some(RetryingMetaStoreClient.getProxy(conf, false))
+      client = Some(RetryingMetaStoreClient.getProxy(conf))
       info(s"Created HiveMetaStoreClient with metastore uris $metastoreUris")
     }
   }

diff --git a/kyuubi-server/src/main/scala/org/apache/kyuubi/server/http/ThriftHttpServlet.scala b/kyuubi-server/src/main/scala/org/apache/kyuubi/server/http/ThriftHttpServlet.scala
@@ -26,8 +26,6 @@ import javax.ws.rs.core.NewCookie
 
 import scala.collection.mutable
 
-import org.apache.hadoop.hive.shims.Utils
-
 import org.apache.kyuubi.Logging
 import org.apache.kyuubi.config.KyuubiConf
 import org.apache.kyuubi.config.KyuubiConf.FRONTEND_PROXY_HTTP_CLIENT_IP_HEADER
@@ -57,6 +55,8 @@ class ThriftHttpServlet(
   private var isHttpOnlyCookie = false
   private val X_FORWARDED_FOR_HEADER = "X-Forwarded-For"
   private val authenticationFilter = new AuthenticationFilter(conf)
+  private val XSRF_HEADER_DEFAULT = "X-XSRF-HEADER"
+  private val XSRF_METHODS_TO_IGNORE_DEFAULT = Set("GET", "OPTIONS", "HEAD", "TRACE")
 
   override def init(): Unit = {
     isCookieAuthEnabled = conf.get(KyuubiConf.FRONTEND_THRIFT_HTTP_COOKIE_AUTH_ENABLED)
@@ -82,7 +82,7 @@ class ThriftHttpServlet(
     var requireNewCookie: Boolean = false
     try {
       if (conf.get(KyuubiConf.FRONTEND_THRIFT_HTTP_XSRF_FILTER_ENABLED)) {
-        val continueProcessing = Utils.doXsrfFilter(request, response, null, null)
+        val continueProcessing = doXsrfFilter(request, response)
         if (!continueProcessing) {
           warn("Request did not have valid XSRF header, rejecting.")
           return
@@ -303,4 +303,22 @@ class ThriftHttpServlet(
 
     null
   }
+
+  private def doXsrfFilter(
+      httpRequest: HttpServletRequest,
+      response: HttpServletResponse): Boolean = {
+    if (XSRF_METHODS_TO_IGNORE_DEFAULT.contains(httpRequest.getMethod)
+      || httpRequest.getHeader(XSRF_HEADER_DEFAULT) != null) {
+      true
+    } else {
+      response.sendError(
+        HttpServletResponse.SC_BAD_REQUEST,
+        "Missing Required Header for Vulnerability Protection")
+      // scalastyle:off println
+      response.getWriter.println(
+        "XSRF filter denial, requests must contain header : " + XSRF_HEADER_DEFAULT)
+      // scalastyle:on println
+      false
+    }
+  }
 }
diff --git a/...erver/src/test/scala/org/apache/kyuubi/credentials/HiveDelegationTokenProviderSuite.scala b/...erver/src/test/scala/org/apache/kyuubi/credentials/HiveDelegationTokenProviderSuite.scala
@@ -31,7 +31,7 @@ import org.apache.hadoop.conf.Configuration
 import org.apache.hadoop.hive.conf.HiveConf
 import org.apache.hadoop.hive.conf.HiveConf.ConfVars._
 import org.apache.hadoop.hive.metastore.{HiveMetaException, HiveMetaStore}
-import org.apache.hadoop.hive.metastore.security.{DelegationTokenIdentifier, HadoopThriftAuthBridge, HadoopThriftAuthBridge23}
+import org.apache.hadoop.hive.metastore.security.{HadoopThriftAuthBridge, HadoopThriftAuthBridge23}
 import org.apache.hadoop.io.Text
 import org.apache.hadoop.security.{Credentials, UserGroupInformation}
 import org.apache.hadoop.security.authorize.ProxyUsers
@@ -44,6 +44,7 @@ import org.scalatest.time.SpanSugar.convertIntToGrainOfTime
 import org.apache.kyuubi.{KerberizedTestHelper, Logging, Utils}
 import org.apache.kyuubi.config.KyuubiConf
 import org.apache.kyuubi.credentials.LocalMetaServer.defaultHiveConf
+import org.apache.kyuubi.shaded.hive.metastore.security.DelegationTokenIdentifier
 
 class HiveDelegationTokenProviderSuite extends KerberizedTestHelper {