[PATCH v4 1/4] block: support cloning partitions

[John Garry]

For NVMe multipath support, per-path gendisks have flag GENHD_FL_HIDDEN
set. This means that no partition scan will be run for those disks.
However the head disk will still have its partitions scanned.

Even though for hidden disks there is no partition scan, it can be useful
to have the partition table available. Such is a case for NVMe multipath
when we want to send bios to specific partitions.

Support allowing a disk to clone the partitions from a multipath head disk.

Add struct block_device_operations.disk_changed_notify callback to allow
block drivers be notified of when partition layout may have changed. In
the NVMe multipath case, the head disk would use this callback to re-clone
the partitions onto the per-path disks.

Signed-off-by: John Garry <john.garry at linux.dev>
---
 block/partitions/core.c | 43 +++++++++++++++++++++++++++++++++++++++++
 include/linux/blkdev.h  |  2 ++
 2 files changed, 45 insertions(+)

diff --git a/block/partitions/core.c b/block/partitions/core.c
index b5c59b79ca7c..b03b206bc050 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -703,6 +703,9 @@ int bdev_disk_changed(struct gendisk *disk, bool invalidate)
 		kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
 	}
 
+	if (disk->fops->disk_changed_notify)
+		disk->fops->disk_changed_notify(disk);
+
 	return ret;
 }
 /*
@@ -711,6 +714,46 @@ int bdev_disk_changed(struct gendisk *disk, bool invalidate)
  */
 EXPORT_SYMBOL_GPL(bdev_disk_changed);
 
+int bdev_clone_partitions(struct gendisk *disk, struct gendisk *mirror)
+{
+	struct block_device *part;
+	unsigned long idx;
+
+	if (disk_has_partscan(mirror))
+		return -EINVAL;
+
+	lockdep_assert_held(&disk->open_mutex);
+	mutex_lock_nested(&mirror->open_mutex, SINGLE_DEPTH_NESTING);
+
+	xa_for_each_start(&mirror->part_tbl, idx, part, 1) {
+		/* Same as bdev_disk_changed() */
+		bdev_unhash(part);
+		WARN_ON_ONCE(atomic_read(&part->bd_openers));
+		invalidate_bdev(part);
+		drop_partition(part);
+	}
+
+	xa_for_each_start(&disk->part_tbl, idx, part, 1) {
+		struct block_device *part_added;
+
+		part_added = add_partition(mirror, idx, part->bd_start_sect,
+					part->bd_nr_sectors, ADDPART_FLAG_NONE,
+					part->bd_meta_info);
+		if (IS_ERR(part_added)) {
+			if (PTR_ERR(part_added) != -ENXIO) {
+				dev_err(disk_to_dev(mirror), "p%ld could not be added: %pe\n",
+				       idx, part_added);
+			}
+			mutex_unlock(&mirror->open_mutex);
+			return PTR_ERR(part_added);
+		}
+	}
+	mutex_unlock(&mirror->open_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bdev_clone_partitions);
+
 void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p)
 {
 	struct address_space *mapping = state->disk->part0->bd_mapping;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d003a9d2d1f6..249a4250a56d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -978,6 +978,7 @@ static inline unsigned int bdev_nr_zones(struct block_device *bdev)
 }
 
 int bdev_disk_changed(struct gendisk *disk, bool invalidate);
+int bdev_clone_partitions(struct gendisk *disk, struct gendisk *mirror);
 
 void put_disk(struct gendisk *disk);
 struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node,
@@ -1599,6 +1600,7 @@ struct block_device_operations {
 	/* returns the length of the identifier or a negative errno: */
 	int (*get_unique_id)(struct gendisk *disk, u8 id[16],
 			enum blk_unique_id id_type);
+	void (*disk_changed_notify)(struct gendisk *disk);
 	struct module *owner;
 	const struct pr_ops *pr_ops;
 
-- 
2.43.0