diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala
index e55e8c2cea02b..a4f92eb4ef078 100644
--- a/project/SparkBuild.scala
+++ b/project/SparkBuild.scala
@@ -1688,6 +1688,59 @@ object Unidoc {
       .map(_.filterNot(_.data.getCanonicalPath.contains("connect-shims")))
   }
 
+  // genjavadoc emits top-level package-private Scala types (`private` or `private[x]`, e.g.
+  // `private[spark] trait Foo` or a bare `private class Bar`) as *public* Java stubs even with
+  // `-P:genjavadoc:strictVisibility=true`, because a top-level package-private type compiles to a
+  // JVM-public symbol, and the Javadoc `-public` option cannot drop a stub that really is public.
+  // ScalaDoc honors the qualifier and hides such types, so we drop their stubs here to keep the
+  // published Java API doc aligned with the Scala one. A stub `<module>/target/java/<pkg>/<Name>.java`
+  // is dropped iff EVERY top-level Scala declaration of `<Name>` in that package is `private` or
+  // `private[...]`; a public class with a private companion object (e.g. `SparkConf`) is kept, since
+  // the class itself is public. The private regex tolerates other modifiers around the access
+  // qualifier (e.g. `final private[x] class`).
+  private val publicTopTypeRe =
+    """(?m)^(?:@\w+(?:\([^\n)]*\))?\s+)*(?:(?:final|sealed|abstract|implicit|case)\s+)*(?:class|trait|object)\s+(\w+)""".r
+  private val privateTopTypeRe =
+    """(?m)^(?:@\w+(?:\([^\n)]*\))?\s+)*(?:(?:final|sealed|abstract|implicit|case)\s+)*private(?:\[[^\]]+\])?\s+(?:(?:final|sealed|abstract|implicit|case)\s+)*(?:class|trait|object)\s+(\w+)""".r
+
+  private def dropPackagePrivateJavaStubs(sources: Seq[Seq[File]]): Seq[Seq[File]] = {
+    val cache = scala.collection.mutable.Map.empty[String, (Set[String], Set[String])]
+    def scanPkg(dir: String): (Set[String], Set[String]) = cache.getOrElseUpdate(dir, {
+      val d = new File(dir)
+      val scalaFiles =
+        if (d.isDirectory) d.listFiles.filter(_.getName.endsWith(".scala")) else Array.empty[File]
+      val text = scalaFiles
+        .map(f => new String(java.nio.file.Files.readAllBytes(f.toPath), "UTF-8"))
+        .mkString("\n")
+      (publicTopTypeRe.findAllMatchIn(text).map(_.group(1)).toSet,
+        privateTopTypeRe.findAllMatchIn(text).map(_.group(1)).toSet)
+    })
+    val marker = "/target/java/"
+    sources.map(_.filterNot { f =>
+      val path = f.getCanonicalPath.replace('\\', '/')
+      val idx = path.indexOf(marker)
+      if (idx < 0 || !path.endsWith(".java")) {
+        false
+      } else {
+        val rel = path.substring(idx + marker.length) // <pkg>/<Name>.java
+        val slash = rel.lastIndexOf('/')
+        if (slash < 0) {
+          false
+        } else {
+          val moduleRoot = path.substring(0, idx)
+          val pkgPath = rel.substring(0, slash)
+          val name = f.getName.stripSuffix(".java")
+          val (pub, priv) = Seq("src/main/scala", "src/main/scala-2.13")
+            .map(d => scanPkg(s"$moduleRoot/$d/$pkgPath"))
+            .foldLeft((Set.empty[String], Set.empty[String])) {
+              case ((p, q), (a, b)) => (p ++ a, q ++ b)
+            }
+          priv.contains(name) && !pub.contains(name)
+        }
+      }
+    })
+  }
+
   val unidocSourceBase = settingKey[String]("Base URL of source links in Scaladoc.")
 
   lazy val settings = BaseUnidocPlugin.projectSettings ++
@@ -1712,8 +1765,9 @@ object Unidoc {
 
     // Skip class names containing $ and some internal packages in Javadocs
     (JavaUnidoc / unidoc / unidocAllSources) := {
-      ignoreUndocumentedPackages((JavaUnidoc / unidoc / unidocAllSources).value)
-        .map(_.filterNot(_.getCanonicalPath.contains("org/apache/hadoop")))
+      dropPackagePrivateJavaStubs(
+        ignoreUndocumentedPackages((JavaUnidoc / unidoc / unidocAllSources).value)
+          .map(_.filterNot(_.getCanonicalPath.contains("org/apache/hadoop"))))
     },
 
     (JavaUnidoc / unidoc / javacOptions) := {