Merge tag 'md-fixes-20231207-1' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into block-6.7

Pull MD fix from Song:

"This change from Yu Kuai fixes a bug reported in
 https://bugzilla.kernel.org/show_bug.cgi?id=218200"

* tag 'md-fixes-20231207-1' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md: split MD_RECOVERY_NEEDED out of mddev_resume

Author: axboe

drivers/md/md.c

@@ -490,7 +490,7 @@ int mddev_suspend(struct mddev *mddev, bool interruptible)
 }
 EXPORT_SYMBOL_GPL(mddev_suspend);
 
-void mddev_resume(struct mddev *mddev)
+static void __mddev_resume(struct mddev *mddev, bool recovery_needed)
 {
 	lockdep_assert_not_held(&mddev->reconfig_mutex);
 
@@ -507,12 +507,18 @@ void mddev_resume(struct mddev *mddev)
 	percpu_ref_resurrect(&mddev->active_io);
 	wake_up(&mddev->sb_wait);
 
-	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	if (recovery_needed)
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	mutex_unlock(&mddev->suspend_mutex);
 }
+
+void mddev_resume(struct mddev *mddev)
+{
+	return __mddev_resume(mddev, true);
+}
 EXPORT_SYMBOL_GPL(mddev_resume);
 
 /*
@@ -9389,7 +9395,15 @@ static void md_start_sync(struct work_struct *ws)
 		goto not_running;
 	}
 
-	suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
+	mddev_unlock(mddev);
+	/*
+	 * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
+	 * not set it again. Otherwise, we may cause issue like this one:
+	 *     https://bugzilla.kernel.org/show_bug.cgi?id=218200
+	 * Therefore, use __mddev_resume(mddev, false).
+	 */
+	if (suspend)
+		__mddev_resume(mddev, false);
 	md_wakeup_thread(mddev->sync_thread);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	md_new_event();
@@ -9401,7 +9415,15 @@ static void md_start_sync(struct work_struct *ws)
 	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-	suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
+	mddev_unlock(mddev);
+	/*
+	 * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
+	 * not set it again. Otherwise, we may cause issue like this one:
+	 *     https://bugzilla.kernel.org/show_bug.cgi?id=218200
+	 * Therefore, use __mddev_resume(mddev, false).
+	 */
+	if (suspend)
+		__mddev_resume(mddev, false);
 
 	wake_up(&resync_wait);
 	if (test_and_clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery) &&