md: add a mutex to synchronize idle and frozen in action_store()

Currently, for idle and frozen, action_store will hold 'reconfig_mutex'
and call md_reap_sync_thread() to stop sync thread, however, this will
cause deadlock (explained in the next patch). In order to fix the
problem, following patch will release 'reconfig_mutex' and wait on
'resync_wait', like md_set_readonly() and do_md_stop() does.

Consider that action_store() will set/clear 'MD_RECOVERY_FROZEN'
unconditionally, which might cause unexpected problems, for example,
frozen just set 'MD_RECOVERY_FROZEN' and is still in progress, while
'idle' clear 'MD_RECOVERY_FROZEN' and new sync thread is started, which
might starve in progress frozen. A mutex is added to synchronize idle
and frozen from action_store().
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230529132037.2124527-4-yukuai1@huaweicloud.com

drivers/md/md.c

@@ -643,6 +643,7 @@ void mddev_init(struct mddev *mddev)
 {
 	mutex_init(&mddev->open_mutex);
 	mutex_init(&mddev->reconfig_mutex);
+	mutex_init(&mddev->sync_mutex);
 	mutex_init(&mddev->bitmap_info.mutex);
 	INIT_LIST_HEAD(&mddev->disks);
 	INIT_LIST_HEAD(&mddev->all_mddevs);
@@ -4777,14 +4778,18 @@ static void stop_sync_thread(struct mddev *mddev)
 
 static void idle_sync_thread(struct mddev *mddev)
 {
+	mutex_lock(&mddev->sync_mutex);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	stop_sync_thread(mddev);
+	mutex_unlock(&mddev->sync_mutex);
 }
 
 static void frozen_sync_thread(struct mddev *mddev)
 {
+	mutex_lock(&mddev->sync_mutex);
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	stop_sync_thread(mddev);
+	mutex_unlock(&mddev->sync_mutex);
 }
 
 static ssize_t

drivers/md/md.h

@@ -535,6 +535,9 @@ struct mddev {
 	 */
 	struct list_head		deleting;
 
+	/* Used to synchronize idle and frozen for action_store() */
+	struct mutex			sync_mutex;
+
 	bool	has_superblocks:1;
 	bool	fail_last_dev:1;
 	bool	serialize_policy:1;