Merge tag 'md-6.11-20240612' of git://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.11/block

Pull MD updates from Song:

"The major changes in this PR are:

- sync_action fix and refactoring, by Yu Kuai;
- Various small fixes by Christoph Hellwig, Li Nan, and Ofir Gal."

* tag 'md-6.11-20240612' of git://git.kernel.org/pub/scm/linux/kernel/git/song/md:
md/raid5: avoid BUG_ON() while continue reshape after reassembling
md: pass in max_sectors for pers->sync_request()
md: factor out helpers for different sync_action in md_do_sync()
md: replace last_sync_action with new enum type
md: use new helpers in md_do_sync()
md: don't fail action_store() if sync_thread is not registered
md: remove parameter check_seq for stop_sync_thread()
md: replace sysfs api sync_action with new helpers
md: factor out helper to start reshape from action_store()
md: add new helpers for sync_action
md: add a new enum type sync_action
md: rearrange recovery_flags
md/md-bitmap: fix writing non bitmap pages
md/raid1: don't free conf on raid0_run failure
md/raid0: don't free conf on raid0_run failure
md: make md_flush_request() more readable
md: fix deadlock between mddev_suspend and flush bio
md: change the return value type of md_write_start to void
md: do not delete safemode_timer in mddev_suspend

drivers/md/dm-raid.c

···
 		recovery = rs->md.recovery;
 		state = decipher_sync_action(mddev, recovery);
 		progress = rs_get_progress(rs, recovery, state, resync_max_sectors);
-		resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ?
+		resync_mismatches = mddev->last_sync_action == ACTION_CHECK ?
 				    atomic64_read(&mddev->resync_mismatches) : 0;
 
 		/* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */

drivers/md/md-bitmap.c

···
 	struct block_device *bdev;
 	struct mddev *mddev = bitmap->mddev;
 	struct bitmap_storage *store = &bitmap->storage;
+	unsigned int bitmap_limit = (bitmap->storage.file_pages - pg_index) <<
+		PAGE_SHIFT;
 	loff_t sboff, offset = mddev->bitmap_info.offset;
 	sector_t ps = pg_index * PAGE_SIZE / SECTOR_SIZE;
 	unsigned int size = PAGE_SIZE;
···
 		if (size == 0)
 			/* bitmap runs in to data */
 			return -EINVAL;
-	} else {
-		/* DATA METADATA BITMAP - no problems */
 	}
 
-	md_super_write(mddev, rdev, sboff + ps, (int) size, page);
+	md_super_write(mddev, rdev, sboff + ps, (int)min(size, bitmap_limit), page);
 	return 0;
 }
 

drivers/md/md.c

···
 #include "md-bitmap.h"
 #include "md-cluster.h"
 
+static const char *action_name[NR_SYNC_ACTIONS] = {
+	[ACTION_RESYNC]		= "resync",
+	[ACTION_RECOVER]	= "recover",
+	[ACTION_CHECK]		= "check",
+	[ACTION_REPAIR]		= "repair",
+	[ACTION_RESHAPE]	= "reshape",
+	[ACTION_FROZEN]		= "frozen",
+	[ACTION_IDLE]		= "idle",
+};
+
 /* pers_list is a list of registered personalities protected by pers_lock. */
 static LIST_HEAD(pers_list);
 static DEFINE_SPINLOCK(pers_lock);
···
 	 */
 	WRITE_ONCE(mddev->suspended, mddev->suspended + 1);
 
-	del_timer_sync(&mddev->safemode_timer);
 	/* restrict memory reclaim I/O during raid array is suspend */
 	mddev->noio_flag = memalloc_noio_save();
 
···
 
 	rdev_dec_pending(rdev, mddev);
 
-	if (atomic_dec_and_test(&mddev->flush_pending)) {
-		/* The pair is percpu_ref_get() from md_flush_request() */
-		percpu_ref_put(&mddev->active_io);
-
+	if (atomic_dec_and_test(&mddev->flush_pending))
 		/* The pre-request flush has finished */
 		queue_work(md_wq, &mddev->flush_work);
-	}
 }
 
 static void md_submit_flush_data(struct work_struct *ws);
···
 			rcu_read_lock();
 		}
 	rcu_read_unlock();
-	if (atomic_dec_and_test(&mddev->flush_pending)) {
-		/* The pair is percpu_ref_get() from md_flush_request() */
-		percpu_ref_put(&mddev->active_io);
-
+	if (atomic_dec_and_test(&mddev->flush_pending))
 		queue_work(md_wq, &mddev->flush_work);
-	}
 }
 
 static void md_submit_flush_data(struct work_struct *ws)
···
 		bio_endio(bio);
 	} else {
 		bio->bi_opf &= ~REQ_PREFLUSH;
-		md_handle_request(mddev, bio);
+
+		/*
+		 * make_requst() will never return error here, it only
+		 * returns error in raid5_make_request() by dm-raid.
+		 * Since dm always splits data and flush operation into
+		 * two separate io, io size of flush submitted by dm
+		 * always is 0, make_request() will not be called here.
+		 */
+		if (WARN_ON_ONCE(!mddev->pers->make_request(mddev, bio)))
+			bio_io_error(bio);;
 	}
+
+	/* The pair is percpu_ref_get() from md_flush_request() */
+	percpu_ref_put(&mddev->active_io);
 }
 
 /*
···
 		WARN_ON(percpu_ref_is_zero(&mddev->active_io));
 		percpu_ref_get(&mddev->active_io);
 		mddev->flush_bio = bio;
-		bio = NULL;
-	}
-	spin_unlock_irq(&mddev->lock);
-
-	if (!bio) {
+		spin_unlock_irq(&mddev->lock);
 		INIT_WORK(&mddev->flush_work, submit_flushes);
 		queue_work(md_wq, &mddev->flush_work);
-	} else {
-		/* flush was performed for some other bio while we waited. */
-		if (bio->bi_iter.bi_size == 0)
-			/* an empty barrier - all done */
-			bio_endio(bio);
-		else {
-			bio->bi_opf &= ~REQ_PREFLUSH;
-			return false;
-		}
+		return true;
 	}
-	return true;
+
+	/* flush was performed for some other bio while we waited. */
+	spin_unlock_irq(&mddev->lock);
+	if (bio->bi_iter.bi_size == 0) {
+		/* pure flush without data - all done */
+		bio_endio(bio);
+		return true;
+	}
+
+	bio->bi_opf &= ~REQ_PREFLUSH;
+	return false;
 }
 EXPORT_SYMBOL(md_flush_request);
 
···
 
 	mutex_init(&mddev->open_mutex);
 	mutex_init(&mddev->reconfig_mutex);
-	mutex_init(&mddev->sync_mutex);
 	mutex_init(&mddev->suspend_mutex);
 	mutex_init(&mddev->bitmap_info.mutex);
 	INIT_LIST_HEAD(&mddev->disks);
···
 	init_waitqueue_head(&mddev->recovery_wait);
 	mddev->reshape_position = MaxSector;
 	mddev->reshape_backwards = 0;
-	mddev->last_sync_action = "none";
+	mddev->last_sync_action = ACTION_IDLE;
 	mddev->resync_min = 0;
 	mddev->resync_max = MaxSector;
 	mddev->level = LEVEL_NONE;
···
 static struct md_sysfs_entry md_metadata =
 __ATTR_PREALLOC(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
 
+enum sync_action md_sync_action(struct mddev *mddev)
+{
+	unsigned long recovery = mddev->recovery;
+
+	/*
+	 * frozen has the highest priority, means running sync_thread will be
+	 * stopped immediately, and no new sync_thread can start.
+	 */
+	if (test_bit(MD_RECOVERY_FROZEN, &recovery))
+		return ACTION_FROZEN;
+
+	/*
+	 * read-only array can't register sync_thread, and it can only
+	 * add/remove spares.
+	 */
+	if (!md_is_rdwr(mddev))
+		return ACTION_IDLE;
+
+	/*
+	 * idle means no sync_thread is running, and no new sync_thread is
+	 * requested.
+	 */
+	if (!test_bit(MD_RECOVERY_RUNNING, &recovery) &&
+	    !test_bit(MD_RECOVERY_NEEDED, &recovery))
+		return ACTION_IDLE;
+
+	if (test_bit(MD_RECOVERY_RESHAPE, &recovery) ||
+	    mddev->reshape_position != MaxSector)
+		return ACTION_RESHAPE;
+
+	if (test_bit(MD_RECOVERY_RECOVER, &recovery))
+		return ACTION_RECOVER;
+
+	if (test_bit(MD_RECOVERY_SYNC, &recovery)) {
+		/*
+		 * MD_RECOVERY_CHECK must be paired with
+		 * MD_RECOVERY_REQUESTED.
+		 */
+		if (test_bit(MD_RECOVERY_CHECK, &recovery))
+			return ACTION_CHECK;
+		if (test_bit(MD_RECOVERY_REQUESTED, &recovery))
+			return ACTION_REPAIR;
+		return ACTION_RESYNC;
+	}
+
+	/*
+	 * MD_RECOVERY_NEEDED or MD_RECOVERY_RUNNING is set, however, no
+	 * sync_action is specified.
+	 */
+	return ACTION_IDLE;
+}
+
+enum sync_action md_sync_action_by_name(const char *page)
+{
+	enum sync_action action;
+
+	for (action = 0; action < NR_SYNC_ACTIONS; ++action) {
+		if (cmd_match(page, action_name[action]))
+			return action;
+	}
+
+	return NR_SYNC_ACTIONS;
+}
+
+const char *md_sync_action_name(enum sync_action action)
+{
+	return action_name[action];
+}
+
 static ssize_t
 action_show(struct mddev *mddev, char *page)
 {
-	char *type = "idle";
-	unsigned long recovery = mddev->recovery;
-	if (test_bit(MD_RECOVERY_FROZEN, &recovery))
-		type = "frozen";
-	else if (test_bit(MD_RECOVERY_RUNNING, &recovery) ||
-	    (md_is_rdwr(mddev) && test_bit(MD_RECOVERY_NEEDED, &recovery))) {
-		if (test_bit(MD_RECOVERY_RESHAPE, &recovery))
-			type = "reshape";
-		else if (test_bit(MD_RECOVERY_SYNC, &recovery)) {
-			if (!test_bit(MD_RECOVERY_REQUESTED, &recovery))
-				type = "resync";
-			else if (test_bit(MD_RECOVERY_CHECK, &recovery))
-				type = "check";
-			else
-				type = "repair";
-		} else if (test_bit(MD_RECOVERY_RECOVER, &recovery))
-			type = "recover";
-		else if (mddev->reshape_position != MaxSector)
-			type = "reshape";
-	}
-	return sprintf(page, "%s\n", type);
+	enum sync_action action = md_sync_action(mddev);
+
+	return sprintf(page, "%s\n", md_sync_action_name(action));
 }
 
 /**
···
  * @locked:	if set, reconfig_mutex will still be held after this function
  *		return; if not set, reconfig_mutex will be released after this
  *		function return.
- * @check_seq:	if set, only wait for curent running sync_thread to stop, noted
- *		that new sync_thread can still start.
  */
-static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
+static void stop_sync_thread(struct mddev *mddev, bool locked)
 {
-	int sync_seq;
-
-	if (check_seq)
-		sync_seq = atomic_read(&mddev->sync_seq);
+	int sync_seq = atomic_read(&mddev->sync_seq);
 
 	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		if (!locked)
···
 
 	wait_event(resync_wait,
 		   !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-		   (check_seq && sync_seq != atomic_read(&mddev->sync_seq)));
+		   (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery) &&
+		    sync_seq != atomic_read(&mddev->sync_seq)));
 
 	if (locked)
 		mddev_lock_nointr(mddev);
···
 	lockdep_assert_held(&mddev->reconfig_mutex);
 
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev, true, true);
+	stop_sync_thread(mddev, true);
 }
 EXPORT_SYMBOL_GPL(md_idle_sync_thread);
 
···
 	lockdep_assert_held(&mddev->reconfig_mutex);
 
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev, true, false);
+	stop_sync_thread(mddev, true);
 }
 EXPORT_SYMBOL_GPL(md_frozen_sync_thread);
 
···
 }
 EXPORT_SYMBOL_GPL(md_unfrozen_sync_thread);
 
-static void idle_sync_thread(struct mddev *mddev)
+static int mddev_start_reshape(struct mddev *mddev)
 {
-	mutex_lock(&mddev->sync_mutex);
-	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	int ret;
 
-	if (mddev_lock(mddev)) {
-		mutex_unlock(&mddev->sync_mutex);
-		return;
+	if (mddev->pers->start_reshape == NULL)
+		return -EINVAL;
+
+	if (mddev->reshape_position == MaxSector ||
+	    mddev->pers->check_reshape == NULL ||
+	    mddev->pers->check_reshape(mddev)) {
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+		ret = mddev->pers->start_reshape(mddev);
+		if (ret)
+			return ret;
+	} else {
+		/*
+		 * If reshape is still in progress, and md_check_recovery() can
+		 * continue to reshape, don't restart reshape because data can
+		 * be corrupted for raid456.
+		 */
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	}
 
-	stop_sync_thread(mddev, false, true);
-	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);
-
-	if (mddev_lock(mddev)) {
-		mutex_unlock(&mddev->sync_mutex);
-		return;
-	}
-
-	stop_sync_thread(mddev, false, false);
-	mutex_unlock(&mddev->sync_mutex);
+	sysfs_notify_dirent_safe(mddev->sysfs_degraded);
+	return 0;
 }
 
 static ssize_t
 action_store(struct mddev *mddev, const char *page, size_t len)
 {
+	int ret;
+	enum sync_action action;
+
 	if (!mddev->pers || !mddev->pers->sync_request)
 		return -EINVAL;
 
+retry:
+	if (work_busy(&mddev->sync_work))
+		flush_work(&mddev->sync_work);
 
-	if (cmd_match(page, "idle"))
-		idle_sync_thread(mddev);
-	else if (cmd_match(page, "frozen"))
-		frozen_sync_thread(mddev);
-	else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		return -EBUSY;
-	else if (cmd_match(page, "resync"))
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	else if (cmd_match(page, "recover")) {
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-	} else if (cmd_match(page, "reshape")) {
-		int err;
-		if (mddev->pers->start_reshape == NULL)
-			return -EINVAL;
-		err = mddev_lock(mddev);
-		if (!err) {
-			if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-				err =  -EBUSY;
-			} else if (mddev->reshape_position == MaxSector ||
-				   mddev->pers->check_reshape == NULL ||
-				   mddev->pers->check_reshape(mddev)) {
-				clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-				err = mddev->pers->start_reshape(mddev);
-			} else {
-				/*
-				 * If reshape is still in progress, and
-				 * md_check_recovery() can continue to reshape,
-				 * don't restart reshape because data can be
-				 * corrupted for raid456.
-				 */
-				clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-			}
-			mddev_unlock(mddev);
-		}
-		if (err)
-			return err;
-		sysfs_notify_dirent_safe(mddev->sysfs_degraded);
-	} else {
-		if (cmd_match(page, "check"))
-			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-		else if (!cmd_match(page, "repair"))
-			return -EINVAL;
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
-		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+	ret = mddev_lock(mddev);
+	if (ret)
+		return ret;
+
+	if (work_busy(&mddev->sync_work)) {
+		mddev_unlock(mddev);
+		goto retry;
 	}
+
+	action = md_sync_action_by_name(page);
+
+	/* TODO: mdadm rely on "idle" to start sync_thread. */
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+		switch (action) {
+		case ACTION_FROZEN:
+			md_frozen_sync_thread(mddev);
+			ret = len;
+			goto out;
+		case ACTION_IDLE:
+			md_idle_sync_thread(mddev);
+			break;
+		case ACTION_RESHAPE:
+		case ACTION_RECOVER:
+		case ACTION_CHECK:
+		case ACTION_REPAIR:
+		case ACTION_RESYNC:
+			ret = -EBUSY;
+			goto out;
+		default:
+			ret = -EINVAL;
+			goto out;
+		}
+	} else {
+		switch (action) {
+		case ACTION_FROZEN:
+			set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+			ret = len;
+			goto out;
+		case ACTION_RESHAPE:
+			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+			ret = mddev_start_reshape(mddev);
+			if (ret)
+				goto out;
+			break;
+		case ACTION_RECOVER:
+			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+			break;
+		case ACTION_CHECK:
+			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+			fallthrough;
+		case ACTION_REPAIR:
+			set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+			fallthrough;
+		case ACTION_RESYNC:
+		case ACTION_IDLE:
+			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+			break;
+		default:
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
 	if (mddev->ro == MD_AUTO_READ) {
 		/* A write to sync_action is enough to justify
 		 * canceling read-auto mode
 		 */
-		flush_work(&mddev->sync_work);
 		mddev->ro = MD_RDWR;
 		md_wakeup_thread(mddev->sync_thread);
 	}
+
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
-	return len;
+	ret = len;
+
+out:
+	mddev_unlock(mddev);
+	return ret;
 }
 
 static struct md_sysfs_entry md_scan_mode =
···
 static ssize_t
 last_sync_action_show(struct mddev *mddev, char *page)
 {
-	return sprintf(page, "%s\n", mddev->last_sync_action);
+	return sprintf(page, "%s\n",
+		       md_sync_action_name(mddev->last_sync_action));
 }
 
 static struct md_sysfs_entry md_last_scan_mode = __ATTR_RO(last_sync_action);
···
 {
 	mddev_lock_nointr(mddev);
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev, true, false);
+	stop_sync_thread(mddev, true);
 	__md_stop_writes(mddev);
 	mddev_unlock(mddev);
 }
···
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	}
 
-	stop_sync_thread(mddev, false, false);
+	stop_sync_thread(mddev, false);
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	mddev_lock_nointr(mddev);
···
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	}
 
-	stop_sync_thread(mddev, true, false);
+	stop_sync_thread(mddev, true);
 
 	if (mddev->sysfs_active ||
 	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
···
  * A return value of 'false' means that the write wasn't recorded
  * and cannot proceed as the array is being suspend.
  */
-bool md_write_start(struct mddev *mddev, struct bio *bi)
+void md_write_start(struct mddev *mddev, struct bio *bi)
 {
 	int did_change = 0;
 
 	if (bio_data_dir(bi) != WRITE)
-		return true;
+		return;
 
 	BUG_ON(mddev->ro == MD_RDONLY);
 	if (mddev->ro == MD_AUTO_READ) {
···
 	if (did_change)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	if (!mddev->has_superblocks)
-		return true;
+		return;
 	wait_event(mddev->sb_wait,
-		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) ||
-		   is_md_suspended(mddev));
-	if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
-		percpu_ref_put(&mddev->writes_pending);
-		return false;
-	}
-	return true;
+		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 }
 EXPORT_SYMBOL(md_write_start);
 
···
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 
+static sector_t md_sync_max_sectors(struct mddev *mddev,
+				    enum sync_action action)
+{
+	switch (action) {
+	case ACTION_RESYNC:
+	case ACTION_CHECK:
+	case ACTION_REPAIR:
+		atomic64_set(&mddev->resync_mismatches, 0);
+		fallthrough;
+	case ACTION_RESHAPE:
+		return mddev->resync_max_sectors;
+	case ACTION_RECOVER:
+		return mddev->dev_sectors;
+	default:
+		return 0;
+	}
+}
+
+static sector_t md_sync_position(struct mddev *mddev, enum sync_action action)
+{
+	sector_t start = 0;
+	struct md_rdev *rdev;
+
+	switch (action) {
+	case ACTION_CHECK:
+	case ACTION_REPAIR:
+		return mddev->resync_min;
+	case ACTION_RESYNC:
+		if (!mddev->bitmap)
+			return mddev->recovery_cp;
+		return 0;
+	case ACTION_RESHAPE:
+		/*
+		 * If the original node aborts reshaping then we continue the
+		 * reshaping, so set again to avoid restart reshape from the
+		 * first beginning
+		 */
+		if (mddev_is_clustered(mddev) &&
+		    mddev->reshape_position != MaxSector)
+			return mddev->reshape_position;
+		return 0;
+	case ACTION_RECOVER:
+		start = MaxSector;
+		rcu_read_lock();
+		rdev_for_each_rcu(rdev, mddev)
+			if (rdev->raid_disk >= 0 &&
+			    !test_bit(Journal, &rdev->flags) &&
+			    !test_bit(Faulty, &rdev->flags) &&
+			    !test_bit(In_sync, &rdev->flags) &&
+			    rdev->recovery_offset < start)
+				start = rdev->recovery_offset;
+		rcu_read_unlock();
+
+		/* If there is a bitmap, we need to make sure all
+		 * writes that started before we added a spare
+		 * complete before we start doing a recovery.
+		 * Otherwise the write might complete and (via
+		 * bitmap_endwrite) set a bit in the bitmap after the
+		 * recovery has checked that bit and skipped that
+		 * region.
+		 */
+		if (mddev->bitmap) {
+			mddev->pers->quiesce(mddev, 1);
+			mddev->pers->quiesce(mddev, 0);
+		}
+		return start;
+	default:
+		return MaxSector;
+	}
+}
+
 #define SYNC_MARKS	10
 #define	SYNC_MARK_STEP	(3*HZ)
 #define UPDATE_FREQUENCY (5*60*HZ)
···
 	sector_t last_check;
 	int skipped = 0;
 	struct md_rdev *rdev;
-	char *desc, *action = NULL;
+	enum sync_action action;
+	const char *desc;
 	struct blk_plug plug;
 	int ret;
 
···
 			goto skip;
 	}
 
-	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
-		if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
-			desc = "data-check";
-			action = "check";
-		} else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
-			desc = "requested-resync";
-			action = "repair";
-		} else
-			desc = "resync";
-	} else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
-		desc = "reshape";
-	else
-		desc = "recovery";
-
-	mddev->last_sync_action = action ?: desc;
+	action = md_sync_action(mddev);
+	desc = md_sync_action_name(action);
+	mddev->last_sync_action = action;
 
 	/*
 	 * Before starting a resync we must have set curr_resync to
···
 		spin_unlock(&all_mddevs_lock);
 	} while (mddev->curr_resync < MD_RESYNC_DELAYED);
 
-	j = 0;
-	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
-		/* resync follows the size requested by the personality,
-		 * which defaults to physical size, but can be virtual size
-		 */
-		max_sectors = mddev->resync_max_sectors;
-		atomic64_set(&mddev->resync_mismatches, 0);
-		/* we don't use the checkpoint if there's a bitmap */
-		if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
-			j = mddev->resync_min;
-		else if (!mddev->bitmap)
-			j = mddev->recovery_cp;
-
-	} else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
-		max_sectors = mddev->resync_max_sectors;
-		/*
-		 * If the original node aborts reshaping then we continue the
-		 * reshaping, so set j again to avoid restart reshape from the
-		 * first beginning
-		 */
-		if (mddev_is_clustered(mddev) &&
-		    mddev->reshape_position != MaxSector)
-			j = mddev->reshape_position;
-	} else {
-		/* recovery follows the physical size of devices */
-		max_sectors = mddev->dev_sectors;
-		j = MaxSector;
-		rcu_read_lock();
-		rdev_for_each_rcu(rdev, mddev)
-			if (rdev->raid_disk >= 0 &&
-			    !test_bit(Journal, &rdev->flags) &&
-			    !test_bit(Faulty, &rdev->flags) &&
-			    !test_bit(In_sync, &rdev->flags) &&
-			    rdev->recovery_offset < j)
-				j = rdev->recovery_offset;
-		rcu_read_unlock();
-
-		/* If there is a bitmap, we need to make sure all
-		 * writes that started before we added a spare
-		 * complete before we start doing a recovery.
-		 * Otherwise the write might complete and (via
-		 * bitmap_endwrite) set a bit in the bitmap after the
-		 * recovery has checked that bit and skipped that
-		 * region.
-		 */
-		if (mddev->bitmap) {
-			mddev->pers->quiesce(mddev, 1);
-			mddev->pers->quiesce(mddev, 0);
-		}
-	}
+	max_sectors = md_sync_max_sectors(mddev, action);
+	j = md_sync_position(mddev, action);
 
 	pr_info("md: %s of RAID array %s\n", desc, mdname(mddev));
 	pr_debug("md: minimum _guaranteed_  speed: %d KB/sec/disk.\n", speed_min(mddev));
···
 		if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 			break;
 
-		sectors = mddev->pers->sync_request(mddev, j, &skipped);
+		sectors = mddev->pers->sync_request(mddev, j, max_sectors,
+						    &skipped);
 		if (sectors == 0) {
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 			break;
···
 		mddev->curr_resync_completed = mddev->curr_resync;
 		sysfs_notify_dirent_safe(mddev->sysfs_completed);
 	}
-	mddev->pers->sync_request(mddev, max_sectors, &skipped);
+	mddev->pers->sync_request(mddev, max_sectors, max_sectors, &skipped);
 
 	if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
 	    mddev->curr_resync > MD_RESYNC_ACTIVE) {

drivers/md/md.h

···
  */
 #define	MD_FAILFAST	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT)
 
+/* Status of sync thread. */
+enum sync_action {
+	/*
+	 * Represent by MD_RECOVERY_SYNC, start when:
+	 * 1) after assemble, sync data from first rdev to other copies, this
+	 * must be done first before other sync actions and will only execute
+	 * once;
+	 * 2) resize the array(notice that this is not reshape), sync data for
+	 * the new range;
+	 */
+	ACTION_RESYNC,
+	/*
+	 * Represent by MD_RECOVERY_RECOVER, start when:
+	 * 1) for new replacement, sync data based on the replace rdev or
+	 * available copies from other rdev;
+	 * 2) for new member disk while the array is degraded, sync data from
+	 * other rdev;
+	 * 3) reassemble after power failure or re-add a hot removed rdev, sync
+	 * data from first rdev to other copies based on bitmap;
+	 */
+	ACTION_RECOVER,
+	/*
+	 * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED |
+	 * MD_RECOVERY_CHECK, start when user echo "check" to sysfs api
+	 * sync_action, used to check if data copies from differenct rdev are
+	 * the same. The number of mismatch sectors will be exported to user
+	 * by sysfs api mismatch_cnt;
+	 */
+	ACTION_CHECK,
+	/*
+	 * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED, start when
+	 * user echo "repair" to sysfs api sync_action, usually paired with
+	 * ACTION_CHECK, used to force syncing data once user found that there
+	 * are inconsistent data,
+	 */
+	ACTION_REPAIR,
+	/*
+	 * Represent by MD_RECOVERY_RESHAPE, start when new member disk is added
+	 * to the conf, notice that this is different from spares or
+	 * replacement;
+	 */
+	ACTION_RESHAPE,
+	/*
+	 * Represent by MD_RECOVERY_FROZEN, can be set by sysfs api sync_action
+	 * or internal usage like setting the array read-only, will forbid above
+	 * actions.
+	 */
+	ACTION_FROZEN,
+	/*
+	 * All above actions don't match.
+	 */
+	ACTION_IDLE,
+	NR_SYNC_ACTIONS,
+};
+
 /*
  * The struct embedded in rdev is used to serialize IO.
  */
···
 	struct md_thread __rcu		*thread;	/* management thread */
 	struct md_thread __rcu		*sync_thread;	/* doing resync or reconstruct */
 
-	/* 'last_sync_action' is initialized to "none".  It is set when a
-	 * sync operation (i.e "data-check", "requested-resync", "resync",
-	 * "recovery", or "reshape") is started.  It holds this value even
+	/*
+	 * Set when a sync operation is started. It holds this value even
 	 * when the sync thread is "frozen" (interrupted) or "idle" (stopped
-	 * or finished).  It is overwritten when a new sync operation is begun.
+	 * or finished). It is overwritten when a new sync operation is begun.
 	 */
-	char				*last_sync_action;
+	enum sync_action		last_sync_action;
 	sector_t			curr_resync;	/* last block scheduled */
 	/* As resync requests can complete out of order, we cannot easily track
 	 * how much resync has been completed.  So we occasionally pause until
···
 	 */
 	struct list_head		deleting;
 
-	/* Used to synchronize idle and frozen for action_store() */
-	struct mutex			sync_mutex;
 	/* The sequence number for sync thread */
 	atomic_t sync_seq;
 
···
 };
 
 enum recovery_flags {
+	/* flags for sync thread running status */
+
 	/*
-	 * If neither SYNC or RESHAPE are set, then it is a recovery.
+	 * set when one of sync action is set and new sync thread need to be
+	 * registered, or just add/remove spares from conf.
 	 */
-	MD_RECOVERY_RUNNING,	/* a thread is running, or about to be started */
-	MD_RECOVERY_SYNC,	/* actually doing a resync, not a recovery */
-	MD_RECOVERY_RECOVER,	/* doing recovery, or need to try it. */
-	MD_RECOVERY_INTR,	/* resync needs to be aborted for some reason */
-	MD_RECOVERY_DONE,	/* thread is done and is waiting to be reaped */
-	MD_RECOVERY_NEEDED,	/* we might need to start a resync/recover */
-	MD_RECOVERY_REQUESTED,	/* user-space has requested a sync (used with SYNC) */
-	MD_RECOVERY_CHECK,	/* user-space request for check-only, no repair */
-	MD_RECOVERY_RESHAPE,	/* A reshape is happening */
-	MD_RECOVERY_FROZEN,	/* User request to abort, and not restart, any action */
-	MD_RECOVERY_ERROR,	/* sync-action interrupted because io-error */
-	MD_RECOVERY_WAIT,	/* waiting for pers->start() to finish */
-	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
+	MD_RECOVERY_NEEDED,
+	/* sync thread is running, or about to be started */
+	MD_RECOVERY_RUNNING,
+	/* sync thread needs to be aborted for some reason */
+	MD_RECOVERY_INTR,
+	/* sync thread is done and is waiting to be unregistered */
+	MD_RECOVERY_DONE,
+	/* running sync thread must abort immediately, and not restart */
+	MD_RECOVERY_FROZEN,
+	/* waiting for pers->start() to finish */
+	MD_RECOVERY_WAIT,
+	/* interrupted because io-error */
+	MD_RECOVERY_ERROR,
+
+	/* flags determines sync action, see details in enum sync_action */
+
+	/* if just this flag is set, action is resync. */
+	MD_RECOVERY_SYNC,
+	/*
+	 * paired with MD_RECOVERY_SYNC, if MD_RECOVERY_CHECK is not set,
+	 * action is repair, means user requested resync.
+	 */
+	MD_RECOVERY_REQUESTED,
+	/*
+	 * paired with MD_RECOVERY_SYNC and MD_RECOVERY_REQUESTED, action is
+	 * check.
+	 */
+	MD_RECOVERY_CHECK,
+	/* recovery, or need to try it */
+	MD_RECOVERY_RECOVER,
+	/* reshape */
+	MD_RECOVERY_RESHAPE,
+	/* remote node is running resync thread */
+	MD_RESYNCING_REMOTE,
 };
 
 enum md_ro_state {
···
 	int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev);
 	int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev);
 	int (*spare_active) (struct mddev *mddev);
-	sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped);
+	sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr,
+				 sector_t max_sector, int *skipped);
 	int (*resize) (struct mddev *mddev, sector_t sectors);
 	sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks);
 	int (*check_reshape) (struct mddev *mddev);
···
 extern void md_wakeup_thread(struct md_thread __rcu *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
-extern bool md_write_start(struct mddev *mddev, struct bio *bi);
+extern enum sync_action md_sync_action(struct mddev *mddev);
+extern enum sync_action md_sync_action_by_name(const char *page);
+extern const char *md_sync_action_name(enum sync_action action);
+extern void md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);
 extern void md_write_end(struct mddev *mddev);
 extern void md_done_sync(struct mddev *mddev, int blocks, int ok);

drivers/md/raid0.c

···
 	return array_sectors;
 }
 
-static void free_conf(struct mddev *mddev, struct r0conf *conf)
-{
-	kfree(conf->strip_zone);
-	kfree(conf->devlist);
-	kfree(conf);
-}
-
 static void raid0_free(struct mddev *mddev, void *priv)
 {
 	struct r0conf *conf = priv;
 
-	free_conf(mddev, conf);
+	kfree(conf->strip_zone);
+	kfree(conf->devlist);
+	kfree(conf);
 }
 
 static int raid0_set_limits(struct mddev *mddev)
···
 	if (!mddev_is_dm(mddev)) {
 		ret = raid0_set_limits(mddev);
 		if (ret)
-			goto out_free_conf;
+			return ret;
 	}
 
 	/* calculate array device size */
···
 
 	dump_zones(mddev);
 
-	ret = md_integrity_register(mddev);
-	if (ret)
-		goto out_free_conf;
-	return 0;
-out_free_conf:
-	free_conf(mddev, conf);
-	return ret;
+	return md_integrity_register(mddev);
 }
 
 /*

drivers/md/raid1.c

···
 	if (bio_data_dir(bio) == READ)
 		raid1_read_request(mddev, bio, sectors, NULL);
 	else {
-		if (!md_write_start(mddev,bio))
-			return false;
+		md_write_start(mddev,bio);
 		raid1_write_request(mddev, bio, sectors);
 	}
 	return true;
···
  */
 
 static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
-				   int *skipped)
+				   sector_t max_sector, int *skipped)
 {
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
 	struct bio *bio;
-	sector_t max_sector, nr_sectors;
+	sector_t nr_sectors;
 	int disk = -1;
 	int i;
 	int wonly = -1;
···
 		if (init_resync(conf))
 			return 0;
 
-	max_sector = mddev->dev_sectors;
 	if (sector_nr >= max_sector) {
 		/* If we aborted, we need to abort the
 		 * sync on the 'current' bitmap chunk (there will
···
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
-static void raid1_free(struct mddev *mddev, void *priv);
 static int raid1_run(struct mddev *mddev)
 {
 	struct r1conf *conf;
···
 	if (!mddev_is_dm(mddev)) {
 		ret = raid1_set_limits(mddev);
 		if (ret)
-			goto abort;
+			return ret;
 	}
 
 	mddev->degraded = 0;
···
 	 */
 	if (conf->raid_disks - mddev->degraded < 1) {
 		md_unregister_thread(mddev, &conf->thread);
-		ret = -EINVAL;
-		goto abort;
+		return -EINVAL;
 	}
 
 	if (conf->raid_disks - mddev->degraded == 1)
···
 	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
 	ret = md_integrity_register(mddev);
-	if (ret) {
+	if (ret)
 		md_unregister_thread(mddev, &mddev->thread);
-		goto abort;
-	}
-	return 0;
-
-abort:
-	raid1_free(mddev, conf);
 	return ret;
 }
 

drivers/md/raid10.c

···
 	    && md_flush_request(mddev, bio))
 		return true;
 
-	if (!md_write_start(mddev, bio))
-		return false;
+	md_write_start(mddev, bio);
 
 	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
 		if (!raid10_handle_discard(mddev, bio))
···
  */
 
 static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
-			     int *skipped)
+				    sector_t max_sector, int *skipped)
 {
 	struct r10conf *conf = mddev->private;
 	struct r10bio *r10_bio;
 	struct bio *biolist = NULL, *bio;
-	sector_t max_sector, nr_sectors;
+	sector_t nr_sectors;
 	int i;
 	int max_sync;
 	sector_t sync_blocks;
···
 			return 0;
 
  skipped:
-	max_sector = mddev->dev_sectors;
-	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
-	    test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
-		max_sector = mddev->resync_max_sectors;
 	if (sector_nr >= max_sector) {
 		conf->cluster_sync_low = 0;
 		conf->cluster_sync_high = 0;

drivers/md/raid5.c

···
 		ctx.do_flush = bi->bi_opf & REQ_PREFLUSH;
 	}
 
-	if (!md_write_start(mddev, bi))
-		return false;
+	md_write_start(mddev, bi);
 	/*
 	 * If array is degraded, better not do chunk aligned read because
 	 * later we might have to read it again in order to reconstruct
···
 	safepos = conf->reshape_safe;
 	sector_div(safepos, data_disks);
 	if (mddev->reshape_backwards) {
-		BUG_ON(writepos < reshape_sectors);
+		if (WARN_ON(writepos < reshape_sectors))
+			return MaxSector;
+
 		writepos -= reshape_sectors;
 		readpos += reshape_sectors;
 		safepos += reshape_sectors;
···
 	 * to set 'stripe_addr' which is where we will write to.
 	 */
 	if (mddev->reshape_backwards) {
-		BUG_ON(conf->reshape_progress == 0);
+		if (WARN_ON(conf->reshape_progress == 0))
+			return MaxSector;
+
 		stripe_addr = writepos;
-		BUG_ON((mddev->dev_sectors &
-			~((sector_t)reshape_sectors - 1))
-		       - reshape_sectors - stripe_addr
-		       != sector_nr);
+		if (WARN_ON((mddev->dev_sectors &
+		    ~((sector_t)reshape_sectors - 1)) -
+		    reshape_sectors - stripe_addr != sector_nr))
+			return MaxSector;
 	} else {
-		BUG_ON(writepos != sector_nr + reshape_sectors);
+		if (WARN_ON(writepos != sector_nr + reshape_sectors))
+			return MaxSector;
+
 		stripe_addr = sector_nr;
 	}
 
···
 }
 
 static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_nr,
-					  int *skipped)
+					  sector_t max_sector, int *skipped)
 {
 	struct r5conf *conf = mddev->private;
 	struct stripe_head *sh;
-	sector_t max_sector = mddev->dev_sectors;
 	sector_t sync_blocks;
 	int still_degraded = 0;
 	int i;