1 files changed, 310 insertions, 72 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4e033c26fdd4..41c476b40c7a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -94,7 +94,6 @@ static struct workqueue_struct *md_wq;
  * workqueue whith reconfig_mutex grabbed.
  */
 static struct workqueue_struct *md_misc_wq;
-struct workqueue_struct *md_bitmap_wq;
 
 static int remove_and_add_spares(struct mddev *mddev,
 				 struct md_rdev *this);
@@ -677,8 +676,64 @@ static void active_io_release(struct percpu_ref *ref)
 
 static void no_op(struct percpu_ref *r) {}
 
+static bool mddev_set_bitmap_ops(struct mddev *mddev)
+{
+	struct bitmap_operations *old = mddev->bitmap_ops;
+	struct md_submodule_head *head;
+
+	if (mddev->bitmap_id == ID_BITMAP_NONE ||
+	    (old && old->head.id == mddev->bitmap_id))
+		return true;
+
+	xa_lock(&md_submodule);
+	head = xa_load(&md_submodule, mddev->bitmap_id);
+
+	if (!head) {
+		pr_warn("md: can't find bitmap id %d\n", mddev->bitmap_id);
+		goto err;
+	}
+
+	if (head->type != MD_BITMAP) {
+		pr_warn("md: invalid bitmap id %d\n", mddev->bitmap_id);
+		goto err;
+	}
+
+	mddev->bitmap_ops = (void *)head;
+	xa_unlock(&md_submodule);
+
+	if (!mddev_is_dm(mddev) && mddev->bitmap_ops->group) {
+		if (sysfs_create_group(&mddev->kobj, mddev->bitmap_ops->group))
+			pr_warn("md: cannot register extra bitmap attributes for %s\n",
+				mdname(mddev));
+		else
+			/*
+			 * Inform user with KOBJ_CHANGE about new bitmap
+			 * attributes.
+			 */
+			kobject_uevent(&mddev->kobj, KOBJ_CHANGE);
+	}
+	return true;
+
+err:
+	xa_unlock(&md_submodule);
+	return false;
+}
+
+static void mddev_clear_bitmap_ops(struct mddev *mddev)
+{
+	if (!mddev_is_dm(mddev) && mddev->bitmap_ops &&
+	    mddev->bitmap_ops->group)
+		sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->group);
+
+	mddev->bitmap_ops = NULL;
+}
+
 int mddev_init(struct mddev *mddev)
 {
+	if (!IS_ENABLED(CONFIG_MD_BITMAP))
+		mddev->bitmap_id = ID_BITMAP_NONE;
+	else
+		mddev->bitmap_id = ID_BITMAP;
 
 	if (percpu_ref_init(&mddev->active_io, active_io_release,
 			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL))
@@ -713,7 +768,6 @@ int mddev_init(struct mddev *mddev)
 	mddev->resync_min = 0;
 	mddev->resync_max = MaxSector;
 	mddev->level = LEVEL_NONE;
-	mddev_set_bitmap_ops(mddev);
 
 	INIT_WORK(&mddev->sync_work, md_start_sync);
 	INIT_WORK(&mddev->del_work, mddev_delayed_delete);
@@ -1020,15 +1074,26 @@ static void super_written(struct bio *bio)
 		wake_up(&mddev->sb_wait);
 }
 
-void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
-		   sector_t sector, int size, struct page *page)
+/**
+ * md_write_metadata - write metadata to underlying disk, including
+ * array superblock, badblocks, bitmap superblock and bitmap bits.
+ * @mddev:	the array to write
+ * @rdev:	the underlying disk to write
+ * @sector:	the offset to @rdev
+ * @size:	the length of the metadata
+ * @page:	the metadata
+ * @offset:	the offset to @page
+ *
+ * Write @size bytes of @page start from @offset, to @sector of @rdev, Increment
+ * mddev->pending_writes before returning, and decrement it on completion,
+ * waking up sb_wait. Caller must call md_super_wait() after issuing io to all
+ * rdev. If an error occurred, md_error() will be called, and the @rdev will be
+ * kicked out from @mddev.
+ */
+void md_write_metadata(struct mddev *mddev, struct md_rdev *rdev,
+		       sector_t sector, int size, struct page *page,
+		       unsigned int offset)
 {
-	/* write first size bytes of page to sector of rdev
-	 * Increment mddev->pending_writes before returning
-	 * and decrement it on completion, waking up sb_wait
-	 * if zero is reached.
-	 * If an error occurred, call md_error
-	 */
 	struct bio *bio;
 
 	if (!page)
@@ -1046,7 +1111,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 	atomic_inc(&rdev->nr_pending);
 
 	bio->bi_iter.bi_sector = sector;
-	__bio_add_page(bio, page, size, 0);
+	__bio_add_page(bio, page, size, offset);
 	bio->bi_private = rdev;
 	bio->bi_end_io = super_written;
 
@@ -1356,6 +1421,9 @@ static u64 md_bitmap_events_cleared(struct mddev *mddev)
 	struct md_bitmap_stats stats;
 	int err;
 
+	if (!md_bitmap_enabled(mddev, false))
+		return 0;
+
 	err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats);
 	if (err)
 		return 0;
@@ -1653,8 +1721,8 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 	if ((u64)num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1)
 		num_sectors = (sector_t)(2ULL << 32) - 2;
 	do {
-		md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
-		       rdev->sb_page);
+		md_write_metadata(rdev->mddev, rdev, rdev->sb_start,
+				  rdev->sb_size, rdev->sb_page, 0);
 	} while (md_super_wait(rdev->mddev) < 0);
 	return num_sectors;
 }
@@ -2302,8 +2370,8 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 	sb->super_offset = cpu_to_le64(rdev->sb_start);
 	sb->sb_csum = calc_sb_1_csum(sb);
 	do {
-		md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
-			       rdev->sb_page);
+		md_write_metadata(rdev->mddev, rdev, rdev->sb_start,
+				  rdev->sb_size, rdev->sb_page, 0);
 	} while (md_super_wait(rdev->mddev) < 0);
 	return num_sectors;
 
@@ -2313,13 +2381,15 @@ static int
 super_1_allow_new_offset(struct md_rdev *rdev,
 			 unsigned long long new_offset)
 {
+	struct mddev *mddev = rdev->mddev;
+
 	/* All necessary checks on new >= old have been done */
 	if (new_offset >= rdev->data_offset)
 		return 1;
 
 	/* with 1.0 metadata, there is no metadata to tread on
 	 * so we can always move back */
-	if (rdev->mddev->minor_version == 0)
+	if (mddev->minor_version == 0)
 		return 1;
 
 	/* otherwise we must be sure not to step on
@@ -2331,8 +2401,7 @@ super_1_allow_new_offset(struct md_rdev *rdev,
 	if (rdev->sb_start + (32+4)*2 > new_offset)
 		return 0;
 
-	if (!rdev->mddev->bitmap_info.file) {
-		struct mddev *mddev = rdev->mddev;
+	if (md_bitmap_registered(mddev) && !mddev->bitmap_info.file) {
 		struct md_bitmap_stats stats;
 		int err;
 
@@ -2804,24 +2873,24 @@ repeat:
 
 	mddev_add_trace_msg(mddev, "md md_update_sb");
 rewrite:
-	mddev->bitmap_ops->update_sb(mddev->bitmap);
+	if (md_bitmap_enabled(mddev, false))
+		mddev->bitmap_ops->update_sb(mddev->bitmap);
 	rdev_for_each(rdev, mddev) {
 		if (rdev->sb_loaded != 1)
 			continue; /* no noise on spare devices */
 
 		if (!test_bit(Faulty, &rdev->flags)) {
-			md_super_write(mddev,rdev,
-				       rdev->sb_start, rdev->sb_size,
-				       rdev->sb_page);
+			md_write_metadata(mddev, rdev, rdev->sb_start,
+					  rdev->sb_size, rdev->sb_page, 0);
 			pr_debug("md: (write) %pg's sb offset: %llu\n",
 				 rdev->bdev,
 				 (unsigned long long)rdev->sb_start);
 			rdev->sb_events = mddev->events;
 			if (rdev->badblocks.size) {
-				md_super_write(mddev, rdev,
-					       rdev->badblocks.sector,
-					       rdev->badblocks.size << 9,
-					       rdev->bb_page);
+				md_write_metadata(mddev, rdev,
+						  rdev->badblocks.sector,
+						  rdev->badblocks.size << 9,
+						  rdev->bb_page, 0);
 				rdev->badblocks.size = 0;
 			}
 
@@ -4150,6 +4219,86 @@ static struct md_sysfs_entry md_new_level =
 __ATTR(new_level, 0664, new_level_show, new_level_store);
 
 static ssize_t
+bitmap_type_show(struct mddev *mddev, char *page)
+{
+	struct md_submodule_head *head;
+	unsigned long i;
+	ssize_t len = 0;
+
+	if (mddev->bitmap_id == ID_BITMAP_NONE)
+		len += sprintf(page + len, "[none] ");
+	else
+		len += sprintf(page + len, "none ");
+
+	xa_lock(&md_submodule);
+	xa_for_each(&md_submodule, i, head) {
+		if (head->type != MD_BITMAP)
+			continue;
+
+		if (mddev->bitmap_id == head->id)
+			len += sprintf(page + len, "[%s] ", head->name);
+		else
+			len += sprintf(page + len, "%s ", head->name);
+	}
+	xa_unlock(&md_submodule);
+
+	len += sprintf(page + len, "\n");
+	return len;
+}
+
+static ssize_t
+bitmap_type_store(struct mddev *mddev, const char *buf, size_t len)
+{
+	struct md_submodule_head *head;
+	enum md_submodule_id id;
+	unsigned long i;
+	int err = 0;
+
+	xa_lock(&md_submodule);
+
+	if (mddev->bitmap_ops) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	if (cmd_match(buf, "none")) {
+		mddev->bitmap_id = ID_BITMAP_NONE;
+		goto out;
+	}
+
+	xa_for_each(&md_submodule, i, head) {
+		if (head->type == MD_BITMAP && cmd_match(buf, head->name)) {
+			mddev->bitmap_id = head->id;
+			goto out;
+		}
+	}
+
+	err = kstrtoint(buf, 10, &id);
+	if (err)
+		goto out;
+
+	if (id == ID_BITMAP_NONE) {
+		mddev->bitmap_id = id;
+		goto out;
+	}
+
+	head = xa_load(&md_submodule, id);
+	if (head && head->type == MD_BITMAP) {
+		mddev->bitmap_id = id;
+		goto out;
+	}
+
+	err = -ENOENT;
+
+out:
+	xa_unlock(&md_submodule);
+	return err ? err : len;
+}
+
+static struct md_sysfs_entry md_bitmap_type =
+__ATTR(bitmap_type, 0664, bitmap_type_show, bitmap_type_store);
+
+static ssize_t
 layout_show(struct mddev *mddev, char *page)
 {
 	/* just a number, not meaningful for all levels */
@@ -4680,6 +4829,9 @@ bitmap_store(struct mddev *mddev, const char *buf, size_t len)
 	unsigned long chunk, end_chunk;
 	int err;
 
+	if (!md_bitmap_enabled(mddev, false))
+		return len;
+
 	err = mddev_lock(mddev);
 	if (err)
 		return err;
@@ -5752,6 +5904,7 @@ __ATTR(serialize_policy, S_IRUGO | S_IWUSR, serialize_policy_show,
 static struct attribute *md_default_attrs[] = {
 	&md_level.attr,
 	&md_new_level.attr,
+	&md_bitmap_type.attr,
 	&md_layout.attr,
 	&md_raid_disks.attr,
 	&md_uuid.attr,
@@ -5801,7 +5954,6 @@ static const struct attribute_group md_redundancy_group = {
 
 static const struct attribute_group *md_attr_groups[] = {
 	&md_default_group,
-	&md_bitmap_group,
 	NULL,
 };
 
@@ -6133,6 +6285,26 @@ static void md_safemode_timeout(struct timer_list *t)
 
 static int start_dirty_degraded;
 
+static int md_bitmap_create(struct mddev *mddev)
+{
+	if (mddev->bitmap_id == ID_BITMAP_NONE)
+		return -EINVAL;
+
+	if (!mddev_set_bitmap_ops(mddev))
+		return -ENOENT;
+
+	return mddev->bitmap_ops->create(mddev);
+}
+
+static void md_bitmap_destroy(struct mddev *mddev)
+{
+	if (!md_bitmap_registered(mddev))
+		return;
+
+	mddev->bitmap_ops->destroy(mddev);
+	mddev_clear_bitmap_ops(mddev);
+}
+
 int md_run(struct mddev *mddev)
 {
 	int err;
@@ -6299,7 +6471,7 @@ int md_run(struct mddev *mddev)
 	}
 	if (err == 0 && pers->sync_request &&
 	    (mddev->bitmap_info.file || mddev->bitmap_info.offset)) {
-		err = mddev->bitmap_ops->create(mddev);
+		err = md_bitmap_create(mddev);
 		if (err)
 			pr_warn("%s: failed to create bitmap (%d)\n",
 				mdname(mddev), err);
@@ -6372,7 +6544,7 @@ bitmap_abort:
 		pers->free(mddev, mddev->private);
 	mddev->private = NULL;
 	put_pers(pers);
-	mddev->bitmap_ops->destroy(mddev);
+	md_bitmap_destroy(mddev);
 abort:
 	bioset_exit(&mddev->io_clone_set);
 exit_sync_set:
@@ -6392,10 +6564,12 @@ int do_md_run(struct mddev *mddev)
 	if (err)
 		goto out;
 
-	err = mddev->bitmap_ops->load(mddev);
-	if (err) {
-		mddev->bitmap_ops->destroy(mddev);
-		goto out;
+	if (md_bitmap_registered(mddev)) {
+		err = mddev->bitmap_ops->load(mddev);
+		if (err) {
+			md_bitmap_destroy(mddev);
+			goto out;
+		}
 	}
 
 	if (mddev_is_clustered(mddev))
@@ -6546,7 +6720,8 @@ static void __md_stop_writes(struct mddev *mddev)
 		mddev->pers->quiesce(mddev, 0);
 	}
 
-	mddev->bitmap_ops->flush(mddev);
+	if (md_bitmap_enabled(mddev, true))
+		mddev->bitmap_ops->flush(mddev);
 
 	if (md_is_rdwr(mddev) &&
 	    ((!mddev->in_sync && !mddev_is_clustered(mddev)) ||
@@ -6573,7 +6748,8 @@ EXPORT_SYMBOL_GPL(md_stop_writes);
 
 static void mddev_detach(struct mddev *mddev)
 {
-	mddev->bitmap_ops->wait_behind_writes(mddev);
+	if (md_bitmap_enabled(mddev, false))
+		mddev->bitmap_ops->wait_behind_writes(mddev);
 	if (mddev->pers && mddev->pers->quiesce && !is_md_suspended(mddev)) {
 		mddev->pers->quiesce(mddev, 1);
 		mddev->pers->quiesce(mddev, 0);
@@ -6589,7 +6765,7 @@ static void __md_stop(struct mddev *mddev)
 {
 	struct md_personality *pers = mddev->pers;
 
-	mddev->bitmap_ops->destroy(mddev);
+	md_bitmap_destroy(mddev);
 	mddev_detach(mddev);
 	spin_lock(&mddev->lock);
 	mddev->pers = NULL;
@@ -7307,6 +7483,9 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 {
 	int err = 0;
 
+	if (!md_bitmap_registered(mddev))
+		return -EINVAL;
+
 	if (mddev->pers) {
 		if (!mddev->pers->quiesce || !mddev->thread)
 			return -EBUSY;
@@ -7363,16 +7542,16 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 	err = 0;
 	if (mddev->pers) {
 		if (fd >= 0) {
-			err = mddev->bitmap_ops->create(mddev);
+			err = md_bitmap_create(mddev);
 			if (!err)
 				err = mddev->bitmap_ops->load(mddev);
 
 			if (err) {
-				mddev->bitmap_ops->destroy(mddev);
+				md_bitmap_destroy(mddev);
 				fd = -1;
 			}
 		} else if (fd < 0) {
-			mddev->bitmap_ops->destroy(mddev);
+			md_bitmap_destroy(mddev);
 		}
 	}
 
@@ -7679,12 +7858,12 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 				mddev->bitmap_info.default_offset;
 			mddev->bitmap_info.space =
 				mddev->bitmap_info.default_space;
-			rv = mddev->bitmap_ops->create(mddev);
+			rv = md_bitmap_create(mddev);
 			if (!rv)
 				rv = mddev->bitmap_ops->load(mddev);
 
 			if (rv)
-				mddev->bitmap_ops->destroy(mddev);
+				md_bitmap_destroy(mddev);
 		} else {
 			struct md_bitmap_stats stats;
 
@@ -7710,7 +7889,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 				put_cluster_ops(mddev);
 				mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY;
 			}
-			mddev->bitmap_ops->destroy(mddev);
+			md_bitmap_destroy(mddev);
 			mddev->bitmap_info.offset = 0;
 		}
 	}
@@ -7747,9 +7926,9 @@ static int set_disk_faulty(struct mddev *mddev, dev_t dev)
  * 4 sectors (with a BIG number of cylinders...). This drives
  * dosfs just mad... ;-)
  */
-static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo)
+static int md_getgeo(struct gendisk *disk, struct hd_geometry *geo)
 {
-	struct mddev *mddev = bdev->bd_disk->private_data;
+	struct mddev *mddev = disk->private_data;
 
 	geo->heads = 2;
 	geo->sectors = 4;
@@ -8491,6 +8670,9 @@ static void md_bitmap_status(struct seq_file *seq, struct mddev *mddev)
 	unsigned long chunk_kb;
 	int err;
 
+	if (!md_bitmap_enabled(mddev, false))
+		return;
+
 	err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats);
 	if (err)
 		return;
@@ -8873,18 +9055,24 @@ EXPORT_SYMBOL_GPL(md_submit_discard_bio);
 static void md_bitmap_start(struct mddev *mddev,
 			    struct md_io_clone *md_io_clone)
 {
+	md_bitmap_fn *fn = unlikely(md_io_clone->rw == STAT_DISCARD) ?
+			   mddev->bitmap_ops->start_discard :
+			   mddev->bitmap_ops->start_write;
+
 	if (mddev->pers->bitmap_sector)
 		mddev->pers->bitmap_sector(mddev, &md_io_clone->offset,
 					   &md_io_clone->sectors);
 
-	mddev->bitmap_ops->start_write(mddev, md_io_clone->offset,
-				       md_io_clone->sectors);
+	fn(mddev, md_io_clone->offset, md_io_clone->sectors);
 }
 
 static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone)
 {
-	mddev->bitmap_ops->end_write(mddev, md_io_clone->offset,
-				     md_io_clone->sectors);
+	md_bitmap_fn *fn = unlikely(md_io_clone->rw == STAT_DISCARD) ?
+			   mddev->bitmap_ops->end_discard :
+			   mddev->bitmap_ops->end_write;
+
+	fn(mddev, md_io_clone->offset, md_io_clone->sectors);
 }
 
 static void md_end_clone_io(struct bio *bio)
@@ -8893,7 +9081,7 @@ static void md_end_clone_io(struct bio *bio)
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
-	if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap)
+	if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, false))
 		md_bitmap_end(mddev, md_io_clone);
 
 	if (bio->bi_status && !orig_bio->bi_status)
@@ -8920,9 +9108,10 @@ static void md_clone_bio(struct mddev *mddev, struct bio **bio)
 	if (blk_queue_io_stat(bdev->bd_disk->queue))
 		md_io_clone->start_time = bio_start_io_acct(*bio);
 
-	if (bio_data_dir(*bio) == WRITE && mddev->bitmap) {
+	if (bio_data_dir(*bio) == WRITE && md_bitmap_enabled(mddev, false)) {
 		md_io_clone->offset = (*bio)->bi_iter.bi_sector;
 		md_io_clone->sectors = bio_sectors(*bio);
+		md_io_clone->rw = op_stat_group(bio_op(*bio));
 		md_bitmap_start(mddev, md_io_clone);
 	}
 
@@ -8944,7 +9133,7 @@ void md_free_cloned_bio(struct bio *bio)
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
-	if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap)
+	if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, false))
 		md_bitmap_end(mddev, md_io_clone);
 
 	if (bio->bi_status && !orig_bio->bi_status)
@@ -9010,6 +9199,39 @@ static sector_t md_sync_max_sectors(struct mddev *mddev,
 	}
 }
 
+/*
+ * If lazy recovery is requested and all rdevs are in sync, select the rdev with
+ * the higest index to perfore recovery to build initial xor data, this is the
+ * same as old bitmap.
+ */
+static bool mddev_select_lazy_recover_rdev(struct mddev *mddev)
+{
+	struct md_rdev *recover_rdev = NULL;
+	struct md_rdev *rdev;
+	bool ret = false;
+
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev) {
+		if (rdev->raid_disk < 0)
+			continue;
+
+		if (test_bit(Faulty, &rdev->flags) ||
+		    !test_bit(In_sync, &rdev->flags))
+			break;
+
+		if (!recover_rdev || recover_rdev->raid_disk < rdev->raid_disk)
+			recover_rdev = rdev;
+	}
+
+	if (recover_rdev) {
+		clear_bit(In_sync, &recover_rdev->flags);
+		ret = true;
+	}
+
+	rcu_read_unlock();
+	return ret;
+}
+
 static sector_t md_sync_position(struct mddev *mddev, enum sync_action action)
 {
 	sector_t start = 0;
@@ -9041,6 +9263,14 @@ static sector_t md_sync_position(struct mddev *mddev, enum sync_action action)
 				start = rdev->recovery_offset;
 		rcu_read_unlock();
 
+		/*
+		 * If there are no spares, and raid456 lazy initial recover is
+		 * requested.
+		 */
+		if (test_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery) &&
+		    start == MaxSector && mddev_select_lazy_recover_rdev(mddev))
+			start = 0;
+
 		/* 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.
@@ -9061,19 +9291,12 @@ static sector_t md_sync_position(struct mddev *mddev, enum sync_action action)
 
 static bool sync_io_within_limit(struct mddev *mddev)
 {
-	int io_sectors;
-
 	/*
 	 * For raid456, sync IO is stripe(4k) per IO, for other levels, it's
 	 * RESYNC_PAGES(64k) per IO.
 	 */
-	if (mddev->level == 4 || mddev->level == 5 || mddev->level == 6)
-		io_sectors = 8;
-	else
-		io_sectors = 128;
-
 	return atomic_read(&mddev->recovery_active) <
-		io_sectors * sync_io_depth(mddev);
+	       (raid_is_456(mddev) ? 8 : 128) * sync_io_depth(mddev);
 }
 
 #define SYNC_MARKS	10
@@ -9283,6 +9506,12 @@ void md_do_sync(struct md_thread *thread)
 		if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 			break;
 
+		if (mddev->bitmap_ops && mddev->bitmap_ops->skip_sync_blocks) {
+			sectors = mddev->bitmap_ops->skip_sync_blocks(mddev, j);
+			if (sectors)
+				goto update;
+		}
+
 		sectors = mddev->pers->sync_request(mddev, j, max_sectors,
 						    &skipped);
 		if (sectors == 0) {
@@ -9298,6 +9527,7 @@ void md_do_sync(struct md_thread *thread)
 		if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 			break;
 
+update:
 		j += sectors;
 		if (j > max_sectors)
 			/* when skipping, extra large numbers can be returned. */
@@ -9607,6 +9837,7 @@ static bool md_choose_sync_action(struct mddev *mddev, int *spares)
 
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 		clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+		clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery);
 		return true;
 	}
 
@@ -9615,6 +9846,7 @@ static bool md_choose_sync_action(struct mddev *mddev, int *spares)
 		remove_spares(mddev, NULL);
 		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+		clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery);
 		return true;
 	}
 
@@ -9624,7 +9856,7 @@ static bool md_choose_sync_action(struct mddev *mddev, int *spares)
 	 * re-add.
 	 */
 	*spares = remove_and_add_spares(mddev, NULL);
-	if (*spares) {
+	if (*spares || test_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery)) {
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
@@ -9682,7 +9914,7 @@ static void md_start_sync(struct work_struct *ws)
 	 * We are adding a device or devices to an array which has the bitmap
 	 * stored on all devices. So make sure all bitmap pages get written.
 	 */
-	if (spares)
+	if (spares && md_bitmap_enabled(mddev, true))
 		mddev->bitmap_ops->write_all(mddev);
 
 	name = test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ?
@@ -9770,7 +10002,7 @@ static void unregister_sync_thread(struct mddev *mddev)
  */
 void md_check_recovery(struct mddev *mddev)
 {
-	if (mddev->bitmap)
+	if (md_bitmap_enabled(mddev, false) && mddev->bitmap_ops->daemon_work)
 		mddev->bitmap_ops->daemon_work(mddev);
 
 	if (signal_pending(current)) {
@@ -9837,6 +10069,7 @@ void md_check_recovery(struct mddev *mddev)
 			}
 
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+			clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery);
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
 
@@ -9947,6 +10180,7 @@ void md_reap_sync_thread(struct mddev *mddev)
 	clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+	clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery);
 	/*
 	 * We call mddev->cluster_ops->update_size here because sync_size could
 	 * be changed by md_update_sb, and MD_RECOVERY_RESHAPE is cleared,
@@ -10094,8 +10328,16 @@ static void md_geninit(void)
 
 static int __init md_init(void)
 {
-	int ret = -ENOMEM;
+	int ret = md_bitmap_init();
+
+	if (ret)
+		return ret;
 
+	ret = md_llbitmap_init();
+	if (ret)
+		goto err_bitmap;
+
+	ret = -ENOMEM;
 	md_wq = alloc_workqueue("md", WQ_MEM_RECLAIM, 0);
 	if (!md_wq)
 		goto err_wq;
@@ -10104,11 +10346,6 @@ static int __init md_init(void)
 	if (!md_misc_wq)
 		goto err_misc_wq;
 
-	md_bitmap_wq = alloc_workqueue("md_bitmap", WQ_MEM_RECLAIM | WQ_UNBOUND,
-				       0);
-	if (!md_bitmap_wq)
-		goto err_bitmap_wq;
-
 	ret = __register_blkdev(MD_MAJOR, "md", md_probe);
 	if (ret < 0)
 		goto err_md;
@@ -10127,12 +10364,13 @@ static int __init md_init(void)
 err_mdp:
 	unregister_blkdev(MD_MAJOR, "md");
 err_md:
-	destroy_workqueue(md_bitmap_wq);
-err_bitmap_wq:
 	destroy_workqueue(md_misc_wq);
 err_misc_wq:
 	destroy_workqueue(md_wq);
 err_wq:
+	md_llbitmap_exit();
+err_bitmap:
+	md_bitmap_exit();
 	return ret;
 }
 
@@ -10150,7 +10388,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 		ret = mddev->pers->resize(mddev, le64_to_cpu(sb->size));
 		if (ret)
 			pr_info("md-cluster: resize failed\n");
-		else
+		else if (md_bitmap_enabled(mddev, false))
 			mddev->bitmap_ops->update_sb(mddev->bitmap);
 	}
 
@@ -10438,8 +10676,8 @@ static __exit void md_exit(void)
 	spin_unlock(&all_mddevs_lock);
 
 	destroy_workqueue(md_misc_wq);
-	destroy_workqueue(md_bitmap_wq);
 	destroy_workqueue(md_wq);
+	md_bitmap_exit();
 }
 
 subsys_initcall(md_init);