summaryrefslogtreecommitdiff
path: root/drivers/md/dm-zoned.h
diff options
context:
space:
mode:
authorDamien Le Moal <damien.lemoal@wdc.com>2017-06-07 09:55:39 +0300
committerMike Snitzer <snitzer@redhat.com>2017-06-19 18:05:20 +0300
commit3b1a94c88b798d4f3bd1a5b61f5c8fb9d987c242 (patch)
tree173fcaced4dffd3e7d334a2992e40a9466747b91 /drivers/md/dm-zoned.h
parentb73c67c2cbb0004e6da9720a167fe42e31f7a6e8 (diff)
downloadlinux-3b1a94c88b798d4f3bd1a5b61f5c8fb9d987c242.tar.xz
dm zoned: drive-managed zoned block device target
The dm-zoned device mapper target provides transparent write access to zoned block devices (ZBC and ZAC compliant block devices). dm-zoned hides to the device user (a file system or an application doing raw block device accesses) any constraint imposed on write requests by the device, equivalent to a drive-managed zoned block device model. Write requests are processed using a combination of on-disk buffering using the device conventional zones and direct in-place processing for requests aligned to a zone sequential write pointer position. A background reclaim process implemented using dm_kcopyd_copy ensures that conventional zones are always available for executing unaligned write requests. The reclaim process overhead is minimized by managing buffer zones in a least-recently-written order and first targeting the oldest buffer zones. Doing so, blocks under regular write access (such as metadata blocks of a file system) remain stored in conventional zones, resulting in no apparent overhead. dm-zoned implementation focus on simplicity and on minimizing overhead (CPU, memory and storage overhead). For a 14TB host-managed disk with 256 MB zones, dm-zoned memory usage per disk instance is at most about 3 MB and as little as 5 zones will be used internally for storing metadata and performing buffer zone reclaim operations. This is achieved using zone level indirection rather than a full block indirection system for managing block movement between zones. dm-zoned primary target is host-managed zoned block devices but it can also be used with host-aware device models to mitigate potential device-side performance degradation due to excessive random writing. Zoned block devices can be formatted and checked for use with the dm-zoned target using the dmzadm utility available at: https://github.com/hgst/dm-zoned-tools Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> [Mike Snitzer partly refactored Damien's original work to cleanup the code] Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Diffstat (limited to 'drivers/md/dm-zoned.h')
-rw-r--r--drivers/md/dm-zoned.h228
1 files changed, 228 insertions, 0 deletions
diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h
new file mode 100644
index 000000000000..12419f0bfe78
--- /dev/null
+++ b/drivers/md/dm-zoned.h
@@ -0,0 +1,228 @@
+/*
+ * Copyright (C) 2017 Western Digital Corporation or its affiliates.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_ZONED_H
+#define DM_ZONED_H
+
+#include <linux/types.h>
+#include <linux/blkdev.h>
+#include <linux/device-mapper.h>
+#include <linux/dm-kcopyd.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/rwsem.h>
+#include <linux/rbtree.h>
+#include <linux/radix-tree.h>
+#include <linux/shrinker.h>
+
+/*
+ * dm-zoned creates block devices with 4KB blocks, always.
+ */
+#define DMZ_BLOCK_SHIFT 12
+#define DMZ_BLOCK_SIZE (1 << DMZ_BLOCK_SHIFT)
+#define DMZ_BLOCK_MASK (DMZ_BLOCK_SIZE - 1)
+
+#define DMZ_BLOCK_SHIFT_BITS (DMZ_BLOCK_SHIFT + 3)
+#define DMZ_BLOCK_SIZE_BITS (1 << DMZ_BLOCK_SHIFT_BITS)
+#define DMZ_BLOCK_MASK_BITS (DMZ_BLOCK_SIZE_BITS - 1)
+
+#define DMZ_BLOCK_SECTORS_SHIFT (DMZ_BLOCK_SHIFT - SECTOR_SHIFT)
+#define DMZ_BLOCK_SECTORS (DMZ_BLOCK_SIZE >> SECTOR_SHIFT)
+#define DMZ_BLOCK_SECTORS_MASK (DMZ_BLOCK_SECTORS - 1)
+
+/*
+ * 4KB block <-> 512B sector conversion.
+ */
+#define dmz_blk2sect(b) ((sector_t)(b) << DMZ_BLOCK_SECTORS_SHIFT)
+#define dmz_sect2blk(s) ((sector_t)(s) >> DMZ_BLOCK_SECTORS_SHIFT)
+
+#define dmz_bio_block(bio) dmz_sect2blk((bio)->bi_iter.bi_sector)
+#define dmz_bio_blocks(bio) dmz_sect2blk(bio_sectors(bio))
+
+/*
+ * Zoned block device information.
+ */
+struct dmz_dev {
+ struct block_device *bdev;
+
+ char name[BDEVNAME_SIZE];
+
+ sector_t capacity;
+
+ unsigned int nr_zones;
+
+ sector_t zone_nr_sectors;
+ unsigned int zone_nr_sectors_shift;
+
+ sector_t zone_nr_blocks;
+ sector_t zone_nr_blocks_shift;
+};
+
+#define dmz_bio_chunk(dev, bio) ((bio)->bi_iter.bi_sector >> \
+ (dev)->zone_nr_sectors_shift)
+#define dmz_chunk_block(dev, b) ((b) & ((dev)->zone_nr_blocks - 1))
+
+/*
+ * Zone descriptor.
+ */
+struct dm_zone {
+ /* For listing the zone depending on its state */
+ struct list_head link;
+
+ /* Zone type and state */
+ unsigned long flags;
+
+ /* Zone activation reference count */
+ atomic_t refcount;
+
+ /* Zone write pointer block (relative to the zone start block) */
+ unsigned int wp_block;
+
+ /* Zone weight (number of valid blocks in the zone) */
+ unsigned int weight;
+
+ /* The chunk that the zone maps */
+ unsigned int chunk;
+
+ /*
+ * For a sequential data zone, pointer to the random zone
+ * used as a buffer for processing unaligned writes.
+ * For a buffer zone, this points back to the data zone.
+ */
+ struct dm_zone *bzone;
+};
+
+/*
+ * Zone flags.
+ */
+enum {
+ /* Zone write type */
+ DMZ_RND,
+ DMZ_SEQ,
+
+ /* Zone critical condition */
+ DMZ_OFFLINE,
+ DMZ_READ_ONLY,
+
+ /* How the zone is being used */
+ DMZ_META,
+ DMZ_DATA,
+ DMZ_BUF,
+
+ /* Zone internal state */
+ DMZ_ACTIVE,
+ DMZ_RECLAIM,
+ DMZ_SEQ_WRITE_ERR,
+};
+
+/*
+ * Zone data accessors.
+ */
+#define dmz_is_rnd(z) test_bit(DMZ_RND, &(z)->flags)
+#define dmz_is_seq(z) test_bit(DMZ_SEQ, &(z)->flags)
+#define dmz_is_empty(z) ((z)->wp_block == 0)
+#define dmz_is_offline(z) test_bit(DMZ_OFFLINE, &(z)->flags)
+#define dmz_is_readonly(z) test_bit(DMZ_READ_ONLY, &(z)->flags)
+#define dmz_is_active(z) test_bit(DMZ_ACTIVE, &(z)->flags)
+#define dmz_in_reclaim(z) test_bit(DMZ_RECLAIM, &(z)->flags)
+#define dmz_seq_write_err(z) test_bit(DMZ_SEQ_WRITE_ERR, &(z)->flags)
+
+#define dmz_is_meta(z) test_bit(DMZ_META, &(z)->flags)
+#define dmz_is_buf(z) test_bit(DMZ_BUF, &(z)->flags)
+#define dmz_is_data(z) test_bit(DMZ_DATA, &(z)->flags)
+
+#define dmz_weight(z) ((z)->weight)
+
+/*
+ * Message functions.
+ */
+#define dmz_dev_info(dev, format, args...) \
+ DMINFO("(%s): " format, (dev)->name, ## args)
+
+#define dmz_dev_err(dev, format, args...) \
+ DMERR("(%s): " format, (dev)->name, ## args)
+
+#define dmz_dev_warn(dev, format, args...) \
+ DMWARN("(%s): " format, (dev)->name, ## args)
+
+#define dmz_dev_debug(dev, format, args...) \
+ DMDEBUG("(%s): " format, (dev)->name, ## args)
+
+struct dmz_metadata;
+struct dmz_reclaim;
+
+/*
+ * Functions defined in dm-zoned-metadata.c
+ */
+int dmz_ctr_metadata(struct dmz_dev *dev, struct dmz_metadata **zmd);
+void dmz_dtr_metadata(struct dmz_metadata *zmd);
+int dmz_resume_metadata(struct dmz_metadata *zmd);
+
+void dmz_lock_map(struct dmz_metadata *zmd);
+void dmz_unlock_map(struct dmz_metadata *zmd);
+void dmz_lock_metadata(struct dmz_metadata *zmd);
+void dmz_unlock_metadata(struct dmz_metadata *zmd);
+void dmz_lock_flush(struct dmz_metadata *zmd);
+void dmz_unlock_flush(struct dmz_metadata *zmd);
+int dmz_flush_metadata(struct dmz_metadata *zmd);
+
+unsigned int dmz_id(struct dmz_metadata *zmd, struct dm_zone *zone);
+sector_t dmz_start_sect(struct dmz_metadata *zmd, struct dm_zone *zone);
+sector_t dmz_start_block(struct dmz_metadata *zmd, struct dm_zone *zone);
+unsigned int dmz_nr_chunks(struct dmz_metadata *zmd);
+
+#define DMZ_ALLOC_RND 0x01
+#define DMZ_ALLOC_RECLAIM 0x02
+
+struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned long flags);
+void dmz_free_zone(struct dmz_metadata *zmd, struct dm_zone *zone);
+
+void dmz_map_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
+ unsigned int chunk);
+void dmz_unmap_zone(struct dmz_metadata *zmd, struct dm_zone *zone);
+unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd);
+unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd);
+
+void dmz_activate_zone(struct dm_zone *zone);
+void dmz_deactivate_zone(struct dm_zone *zone);
+
+int dmz_lock_zone_reclaim(struct dm_zone *zone);
+void dmz_unlock_zone_reclaim(struct dm_zone *zone);
+struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd);
+
+struct dm_zone *dmz_get_chunk_mapping(struct dmz_metadata *zmd,
+ unsigned int chunk, int op);
+void dmz_put_chunk_mapping(struct dmz_metadata *zmd, struct dm_zone *zone);
+struct dm_zone *dmz_get_chunk_buffer(struct dmz_metadata *zmd,
+ struct dm_zone *dzone);
+
+int dmz_validate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
+ sector_t chunk_block, unsigned int nr_blocks);
+int dmz_invalidate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
+ sector_t chunk_block, unsigned int nr_blocks);
+int dmz_block_valid(struct dmz_metadata *zmd, struct dm_zone *zone,
+ sector_t chunk_block);
+int dmz_first_valid_block(struct dmz_metadata *zmd, struct dm_zone *zone,
+ sector_t *chunk_block);
+int dmz_copy_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone,
+ struct dm_zone *to_zone);
+int dmz_merge_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone,
+ struct dm_zone *to_zone, sector_t chunk_block);
+
+/*
+ * Functions defined in dm-zoned-reclaim.c
+ */
+int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd,
+ struct dmz_reclaim **zrc);
+void dmz_dtr_reclaim(struct dmz_reclaim *zrc);
+void dmz_suspend_reclaim(struct dmz_reclaim *zrc);
+void dmz_resume_reclaim(struct dmz_reclaim *zrc);
+void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc);
+void dmz_schedule_reclaim(struct dmz_reclaim *zrc);
+
+#endif /* DM_ZONED_H */