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-toolsSigned-off-by: NDamien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NBart Van Assche <bart.vanassche@sandisk.com>
[Mike Snitzer partly refactored Damien's original work to cleanup the code]
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Documentation/device-mapper/dm-zoned.txt

+dm-zoned
+========
+
+The dm-zoned device mapper target exposes a zoned block device (ZBC and
+ZAC compliant devices) as a regular block device without any write
+pattern constraints. In effect, it implements a drive-managed zoned
+block device which hides from the user (a file system or an application
+doing raw block device accesses) the sequential write constraints of
+host-managed zoned block devices and can mitigate the potential
+device-side performance degradation due to excessive random writes on
+host-aware zoned block devices.
+
+For a more detailed description of the zoned block device models and
+their constraints see (for SCSI devices):
+
+http://www.t10.org/drafts.htm#ZBC_Family
+
+and (for ATA devices):
+
+http://www.t13.org/Documents/UploadedDocuments/docs2015/di537r05-Zoned_Device_ATA_Command_Set_ZAC.pdf
+
+The dm-zoned implementation is simple and minimizes system overhead (CPU
+and memory usage as well as storage capacity loss). For a 10TB
+host-managed disk with 256 MB zones, dm-zoned memory usage per disk
+instance is at most 4.5 MB and as little as 5 zones will be used
+internally for storing metadata and performaing reclaim operations.
+
+dm-zoned target devices are formatted and checked using the dmzadm
+utility available at:
+
+https://github.com/hgst/dm-zoned-tools
+
+Algorithm
+=========
+
+dm-zoned implements an on-disk buffering scheme to handle non-sequential
+write accesses to the sequential zones of a zoned block device.
+Conventional zones are used for caching as well as for storing internal
+metadata.
+
+The zones of the device are separated into 2 types:
+
+1) Metadata zones: these are conventional zones used to store metadata.
+Metadata zones are not reported as useable capacity to the user.
+
+2) Data zones: all remaining zones, the vast majority of which will be
+sequential zones used exclusively to store user data. The conventional
+zones of the device may be used also for buffering user random writes.
+Data in these zones may be directly mapped to the conventional zone, but
+later moved to a sequential zone so that the conventional zone can be
+reused for buffering incoming random writes.
+
+dm-zoned exposes a logical device with a sector size of 4096 bytes,
+irrespective of the physical sector size of the backend zoned block
+device being used. This allows reducing the amount of metadata needed to
+manage valid blocks (blocks written).
+
+The on-disk metadata format is as follows:
+
+1) The first block of the first conventional zone found contains the
+super block which describes the on disk amount and position of metadata
+blocks.
+
+2) Following the super block, a set of blocks is used to describe the
+mapping of the logical device blocks. The mapping is done per chunk of
+blocks, with the chunk size equal to the zoned block device size. The
+mapping table is indexed by chunk number and each mapping entry
+indicates the zone number of the device storing the chunk of data. Each
+mapping entry may also indicate if the zone number of a conventional
+zone used to buffer random modification to the data zone.
+
+3) A set of blocks used to store bitmaps indicating the validity of
+blocks in the data zones follows the mapping table. A valid block is
+defined as a block that was written and not discarded. For a buffered
+data chunk, a block is always valid only in the data zone mapping the
+chunk or in the buffer zone of the chunk.
+
+For a logical chunk mapped to a conventional zone, all write operations
+are processed by directly writing to the zone. If the mapping zone is a
+sequential zone, the write operation is processed directly only if the
+write offset within the logical chunk is equal to the write pointer
+offset within of the sequential data zone (i.e. the write operation is
+aligned on the zone write pointer). Otherwise, write operations are
+processed indirectly using a buffer zone. In that case, an unused
+conventional zone is allocated and assigned to the chunk being
+accessed. Writing a block to the buffer zone of a chunk will
+automatically invalidate the same block in the sequential zone mapping
+the chunk. If all blocks of the sequential zone become invalid, the zone
+is freed and the chunk buffer zone becomes the primary zone mapping the
+chunk, resulting in native random write performance similar to a regular
+block device.
+
+Read operations are processed according to the block validity
+information provided by the bitmaps. Valid blocks are read either from
+the sequential zone mapping a chunk, or if the chunk is buffered, from
+the buffer zone assigned. If the accessed chunk has no mapping, or the
+accessed blocks are invalid, the read buffer is zeroed and the read
+operation terminated.
+
+After some time, the limited number of convnetional zones available may
+be exhausted (all used to map chunks or buffer sequential zones) and
+unaligned writes to unbuffered chunks become impossible. To avoid this
+situation, a reclaim process regularly scans used conventional zones and
+tries to reclaim the least recently used zones by copying the valid
+blocks of the buffer zone to a free sequential zone. Once the copy
+completes, the chunk mapping is updated to point to the sequential zone
+and the buffer zone freed for reuse.
+
+Metadata Protection
+===================
+
+To protect metadata against corruption in case of sudden power loss or
+system crash, 2 sets of metadata zones are used. One set, the primary
+set, is used as the main metadata region, while the secondary set is
+used as a staging area. Modified metadata is first written to the
+secondary set and validated by updating the super block in the secondary
+set, a generation counter is used to indicate that this set contains the
+newest metadata. Once this operation completes, in place of metadata
+block updates can be done in the primary metadata set. This ensures that
+one of the set is always consistent (all modifications committed or none
+at all). Flush operations are used as a commit point. Upon reception of
+a flush request, metadata modification activity is temporarily blocked
+(for both incoming BIO processing and reclaim process) and all dirty
+metadata blocks are staged and updated. Normal operation is then
+resumed. Flushing metadata thus only temporarily delays write and
+discard requests. Read requests can be processed concurrently while
+metadata flush is being executed.
+
+Usage
+=====
+
+A zoned block device must first be formatted using the dmzadm tool. This
+will analyze the device zone configuration, determine where to place the
+metadata sets on the device and initialize the metadata sets.
+
+Ex:
+
+dmzadm --format /dev/sdxx
+
+For a formatted device, the target can be created normally with the
+dmsetup utility. The only parameter that dm-zoned requires is the
+underlying zoned block device name. Ex:
+
+echo "0 `blockdev --getsize ${dev}` zoned ${dev}" | dmsetup create dmz-`basename ${dev}`

drivers/md/Kconfig

@@ -521,6 +521,23 @@ config DM_INTEGRITY
 	  To compile this code as a module, choose M here: the module will
 	  be called dm-integrity.
 
+config DM_ZONED
+	tristate "Drive-managed zoned block device target support"
+	depends on BLK_DEV_DM
+	depends on BLK_DEV_ZONED
+	---help---
+	  This device-mapper target takes a host-managed or host-aware zoned
+	  block device and exposes most of its capacity as a regular block
+	  device (drive-managed zoned block device) without any write
+	  constraints. This is mainly intended for use with file systems that
+	  do not natively support zoned block devices but still want to
+	  benefit from the increased capacity offered by SMR disks. Other uses
+	  by applications using raw block devices (for example object stores)
+	  are also possible.
+
+	  To compile this code as a module, choose M here: the module will
+	  be called dm-zoned.
+
 	  If unsure, say N.
 
 endif # MD

drivers/md/Makefile

@@ -20,6 +20,7 @@ dm-era-y	+= dm-era-target.o
 dm-verity-y	+= dm-verity-target.o
 md-mod-y	+= md.o bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
+dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise 
@@ -60,6 +61,7 @@ obj-$(CONFIG_DM_CACHE_SMQ)	+= dm-cache-smq.o
 obj-$(CONFIG_DM_ERA)		+= dm-era.o
 obj-$(CONFIG_DM_LOG_WRITES)	+= dm-log-writes.o
 obj-$(CONFIG_DM_INTEGRITY)	+= dm-integrity.o
+obj-$(CONFIG_DM_ZONED)		+= dm-zoned.o
 
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o

drivers/md/dm-zoned-reclaim.c

+/*
+ * Copyright (C) 2017 Western Digital Corporation or its affiliates.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-zoned.h"
+
+#include <linux/module.h>
+
+#define	DM_MSG_PREFIX		"zoned reclaim"
+
+struct dmz_reclaim {
+	struct dmz_metadata     *metadata;
+	struct dmz_dev		*dev;
+
+	struct delayed_work	work;
+	struct workqueue_struct *wq;
+
+	struct dm_kcopyd_client	*kc;
+	struct dm_kcopyd_throttle kc_throttle;
+	int			kc_err;
+
+	unsigned long		flags;
+
+	/* Last target access time */
+	unsigned long		atime;
+};
+
+/*
+ * Reclaim state flags.
+ */
+enum {
+	DMZ_RECLAIM_KCOPY,
+};
+
+/*
+ * Number of seconds of target BIO inactivity to consider the target idle.
+ */
+#define DMZ_IDLE_PERIOD		(10UL * HZ)
+
+/*
+ * Percentage of unmapped (free) random zones below which reclaim starts
+ * even if the target is busy.
+ */
+#define DMZ_RECLAIM_LOW_UNMAP_RND	30
+
+/*
+ * Percentage of unmapped (free) random zones above which reclaim will
+ * stop if the target is busy.
+ */
+#define DMZ_RECLAIM_HIGH_UNMAP_RND	50
+
+/*
+ * Align a sequential zone write pointer to chunk_block.
+ */
+static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone,
+				sector_t block)
+{
+	struct dmz_metadata *zmd = zrc->metadata;
+	sector_t wp_block = zone->wp_block;
+	unsigned int nr_blocks;
+	int ret;
+
+	if (wp_block == block)
+		return 0;
+
+	if (wp_block > block)
+		return -EIO;
+
+	/*
+	 * Zeroout the space between the write
+	 * pointer and the requested position.
+	 */
+	nr_blocks = block - wp_block;
+	ret = blkdev_issue_zeroout(zrc->dev->bdev,
+				   dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block),
+				   dmz_blk2sect(nr_blocks), GFP_NOFS, false);
+	if (ret) {
+		dmz_dev_err(zrc->dev,
+			    "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d",
+			    dmz_id(zmd, zone), (unsigned long long)wp_block,
+			    (unsigned long long)block, nr_blocks, ret);
+		return ret;
+	}
+
+	zone->wp_block = block;
+
+	return 0;
+}
+
+/*
+ * dm_kcopyd_copy end notification.
+ */
+static void dmz_reclaim_kcopy_end(int read_err, unsigned long write_err,
+				  void *context)
+{
+	struct dmz_reclaim *zrc = context;
+
+	if (read_err || write_err)
+		zrc->kc_err = -EIO;
+	else
+		zrc->kc_err = 0;
+
+	clear_bit_unlock(DMZ_RECLAIM_KCOPY, &zrc->flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&zrc->flags, DMZ_RECLAIM_KCOPY);
+}
+
+/*
+ * Copy valid blocks of src_zone into dst_zone.
+ */
+static int dmz_reclaim_copy(struct dmz_reclaim *zrc,
+			    struct dm_zone *src_zone, struct dm_zone *dst_zone)
+{
+	struct dmz_metadata *zmd = zrc->metadata;
+	struct dmz_dev *dev = zrc->dev;
+	struct dm_io_region src, dst;
+	sector_t block = 0, end_block;
+	sector_t nr_blocks;
+	sector_t src_zone_block;
+	sector_t dst_zone_block;
+	unsigned long flags = 0;
+	int ret;
+
+	if (dmz_is_seq(src_zone))
+		end_block = src_zone->wp_block;
+	else
+		end_block = dev->zone_nr_blocks;
+	src_zone_block = dmz_start_block(zmd, src_zone);
+	dst_zone_block = dmz_start_block(zmd, dst_zone);
+
+	if (dmz_is_seq(dst_zone))
+		set_bit(DM_KCOPYD_WRITE_SEQ, &flags);
+
+	while (block < end_block) {
+		/* Get a valid region from the source zone */
+		ret = dmz_first_valid_block(zmd, src_zone, &block);
+		if (ret <= 0)
+			return ret;
+		nr_blocks = ret;
+
+		/*
+		 * If we are writing in a sequential zone, we must make sure
+		 * that writes are sequential. So Zeroout any eventual hole
+		 * between writes.
+		 */
+		if (dmz_is_seq(dst_zone)) {
+			ret = dmz_reclaim_align_wp(zrc, dst_zone, block);
+			if (ret)
+				return ret;
+		}
+
+		src.bdev = dev->bdev;
+		src.sector = dmz_blk2sect(src_zone_block + block);
+		src.count = dmz_blk2sect(nr_blocks);
+
+		dst.bdev = dev->bdev;
+		dst.sector = dmz_blk2sect(dst_zone_block + block);
+		dst.count = src.count;
+
+		/* Copy the valid region */
+		set_bit(DMZ_RECLAIM_KCOPY, &zrc->flags);
+		ret = dm_kcopyd_copy(zrc->kc, &src, 1, &dst, flags,
+				     dmz_reclaim_kcopy_end, zrc);
+		if (ret)
+			return ret;
+
+		/* Wait for copy to complete */
+		wait_on_bit_io(&zrc->flags, DMZ_RECLAIM_KCOPY,
+			       TASK_UNINTERRUPTIBLE);
+		if (zrc->kc_err)
+			return zrc->kc_err;
+
+		block += nr_blocks;
+		if (dmz_is_seq(dst_zone))
+			dst_zone->wp_block = block;
+	}
+
+	return 0;
+}
+
+/*
+ * Move valid blocks of dzone buffer zone into dzone (after its write pointer)
+ * and free the buffer zone.
+ */
+static int dmz_reclaim_buf(struct dmz_reclaim *zrc, struct dm_zone *dzone)
+{
+	struct dm_zone *bzone = dzone->bzone;
+	sector_t chunk_block = dzone->wp_block;
+	struct dmz_metadata *zmd = zrc->metadata;
+	int ret;
+
+	dmz_dev_debug(zrc->dev,
+		      "Chunk %u, move buf zone %u (weight %u) to data zone %u (weight %u)",
+		      dzone->chunk, dmz_id(zmd, bzone), dmz_weight(bzone),
+		      dmz_id(zmd, dzone), dmz_weight(dzone));
+
+	/* Flush data zone into the buffer zone */
+	ret = dmz_reclaim_copy(zrc, bzone, dzone);
+	if (ret < 0)
+		return ret;
+
+	dmz_lock_flush(zmd);
+
+	/* Validate copied blocks */
+	ret = dmz_merge_valid_blocks(zmd, bzone, dzone, chunk_block);
+	if (ret == 0) {
+		/* Free the buffer zone */
+		dmz_invalidate_blocks(zmd, bzone, 0, zrc->dev->zone_nr_blocks);
+		dmz_lock_map(zmd);
+		dmz_unmap_zone(zmd, bzone);
+		dmz_unlock_zone_reclaim(dzone);
+		dmz_free_zone(zmd, bzone);
+		dmz_unlock_map(zmd);
+	}
+
+	dmz_unlock_flush(zmd);
+
+	return 0;
+}
+
+/*
+ * Merge valid blocks of dzone into its buffer zone and free dzone.
+ */
+static int dmz_reclaim_seq_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)
+{
+	unsigned int chunk = dzone->chunk;
+	struct dm_zone *bzone = dzone->bzone;
+	struct dmz_metadata *zmd = zrc->metadata;
+	int ret = 0;
+
+	dmz_dev_debug(zrc->dev,
+		      "Chunk %u, move data zone %u (weight %u) to buf zone %u (weight %u)",
+		      chunk, dmz_id(zmd, dzone), dmz_weight(dzone),
+		      dmz_id(zmd, bzone), dmz_weight(bzone));
+
+	/* Flush data zone into the buffer zone */
+	ret = dmz_reclaim_copy(zrc, dzone, bzone);
+	if (ret < 0)
+		return ret;
+
+	dmz_lock_flush(zmd);
+
+	/* Validate copied blocks */
+	ret = dmz_merge_valid_blocks(zmd, dzone, bzone, 0);
+	if (ret == 0) {
+		/*
+		 * Free the data zone and remap the chunk to
+		 * the buffer zone.
+		 */
+		dmz_invalidate_blocks(zmd, dzone, 0, zrc->dev->zone_nr_blocks);
+		dmz_lock_map(zmd);
+		dmz_unmap_zone(zmd, bzone);
+		dmz_unmap_zone(zmd, dzone);
+		dmz_unlock_zone_reclaim(dzone);
+		dmz_free_zone(zmd, dzone);
+		dmz_map_zone(zmd, bzone, chunk);
+		dmz_unlock_map(zmd);
+	}
+
+	dmz_unlock_flush(zmd);
+
+	return 0;
+}
+
+/*
+ * Move valid blocks of the random data zone dzone into a free sequential zone.
+ * Once blocks are moved, remap the zone chunk to the sequential zone.
+ */
+static int dmz_reclaim_rnd_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)
+{
+	unsigned int chunk = dzone->chunk;
+	struct dm_zone *szone = NULL;
+	struct dmz_metadata *zmd = zrc->metadata;
+	int ret;
+
+	/* Get a free sequential zone */
+	dmz_lock_map(zmd);
+	szone = dmz_alloc_zone(zmd, DMZ_ALLOC_RECLAIM);
+	dmz_unlock_map(zmd);
+	if (!szone)
+		return -ENOSPC;
+
+	dmz_dev_debug(zrc->dev,
+		      "Chunk %u, move rnd zone %u (weight %u) to seq zone %u",
+		      chunk, dmz_id(zmd, dzone), dmz_weight(dzone),
+		      dmz_id(zmd, szone));
+
+	/* Flush the random data zone into the sequential zone */
+	ret = dmz_reclaim_copy(zrc, dzone, szone);
+
+	dmz_lock_flush(zmd);
+
+	if (ret == 0) {
+		/* Validate copied blocks */
+		ret = dmz_copy_valid_blocks(zmd, dzone, szone);
+	}
+	if (ret) {
+		/* Free the sequential zone */
+		dmz_lock_map(zmd);
+		dmz_free_zone(zmd, szone);
+		dmz_unlock_map(zmd);
+	} else {
+		/* Free the data zone and remap the chunk */
+		dmz_invalidate_blocks(zmd, dzone, 0, zrc->dev->zone_nr_blocks);
+		dmz_lock_map(zmd);
+		dmz_unmap_zone(zmd, dzone);
+		dmz_unlock_zone_reclaim(dzone);
+		dmz_free_zone(zmd, dzone);
+		dmz_map_zone(zmd, szone, chunk);
+		dmz_unlock_map(zmd);
+	}
+
+	dmz_unlock_flush(zmd);
+
+	return 0;
+}
+
+/*
+ * Reclaim an empty zone.
+ */
+static void dmz_reclaim_empty(struct dmz_reclaim *zrc, struct dm_zone *dzone)
+{
+	struct dmz_metadata *zmd = zrc->metadata;
+
+	dmz_lock_flush(zmd);
+	dmz_lock_map(zmd);
+	dmz_unmap_zone(zmd, dzone);
+	dmz_unlock_zone_reclaim(dzone);
+	dmz_free_zone(zmd, dzone);
+	dmz_unlock_map(zmd);
+	dmz_unlock_flush(zmd);
+}
+
+/*
+ * Find a candidate zone for reclaim and process it.
+ */
+static void dmz_reclaim(struct dmz_reclaim *zrc)
+{
+	struct dmz_metadata *zmd = zrc->metadata;
+	struct dm_zone *dzone;
+	struct dm_zone *rzone;
+	unsigned long start;
+	int ret;
+
+	/* Get a data zone */
+	dzone = dmz_get_zone_for_reclaim(zmd);
+	if (!dzone)
+		return;
+
+	start = jiffies;
+
+	if (dmz_is_rnd(dzone)) {
+		if (!dmz_weight(dzone)) {
+			/* Empty zone */
+			dmz_reclaim_empty(zrc, dzone);
+			ret = 0;
+		} else {
+			/*
+			 * Reclaim the random data zone by moving its
+			 * valid data blocks to a free sequential zone.
+			 */
+			ret = dmz_reclaim_rnd_data(zrc, dzone);
+		}
+		rzone = dzone;
+
+	} else {
+		struct dm_zone *bzone = dzone->bzone;
+		sector_t chunk_block = 0;
+
+		ret = dmz_first_valid_block(zmd, bzone, &chunk_block);
+		if (ret < 0)
+			goto out;
+
+		if (ret == 0 || chunk_block >= dzone->wp_block) {
+			/*
+			 * The buffer zone is empty or its valid blocks are
+			 * after the data zone write pointer.
+			 */
+			ret = dmz_reclaim_buf(zrc, dzone);
+			rzone = bzone;
+		} else {
+			/*
+			 * Reclaim the data zone by merging it into the
+			 * buffer zone so that the buffer zone itself can
+			 * be later reclaimed.
+			 */
+			ret = dmz_reclaim_seq_data(zrc, dzone);
+			rzone = dzone;
+		}
+	}
+out:
+	if (ret) {
+		dmz_unlock_zone_reclaim(dzone);
+		return;
+	}
+
+	(void) dmz_flush_metadata(zrc->metadata);
+
+	dmz_dev_debug(zrc->dev, "Reclaimed zone %u in %u ms",
+		      dmz_id(zmd, rzone), jiffies_to_msecs(jiffies - start));
+}
+
+/*
+ * Test if the target device is idle.
+ */
+static inline int dmz_target_idle(struct dmz_reclaim *zrc)
+{
+	return time_is_before_jiffies(zrc->atime + DMZ_IDLE_PERIOD);
+}
+
+/*
+ * Test if reclaim is necessary.
+ */
+static bool dmz_should_reclaim(struct dmz_reclaim *zrc)
+{
+	struct dmz_metadata *zmd = zrc->metadata;
+	unsigned int nr_rnd = dmz_nr_rnd_zones(zmd);
+	unsigned int nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd);
+	unsigned int p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd;
+
+	/* Reclaim when idle */
+	if (dmz_target_idle(zrc) && nr_unmap_rnd < nr_rnd)
+		return true;
+
+	/* If there are still plenty of random zones, do not reclaim */
+	if (p_unmap_rnd >= DMZ_RECLAIM_HIGH_UNMAP_RND)
+		return false;
+
+	/*
+	 * If the percentage of unmappped random zones is low,
+	 * reclaim even if the target is busy.
+	 */
+	return p_unmap_rnd <= DMZ_RECLAIM_LOW_UNMAP_RND;
+}
+
+/*
+ * Reclaim work function.
+ */
+static void dmz_reclaim_work(struct work_struct *work)
+{
+	struct dmz_reclaim *zrc = container_of(work, struct dmz_reclaim, work.work);
+	struct dmz_metadata *zmd = zrc->metadata;
+	unsigned int nr_rnd, nr_unmap_rnd;
+	unsigned int p_unmap_rnd;
+
+	if (!dmz_should_reclaim(zrc)) {
+		mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD);
+		return;
+	}
+
+	/*
+	 * We need to start reclaiming random zones: set up zone copy
+	 * throttling to either go fast if we are very low on random zones
+	 * and slower if there are still some free random zones to avoid
+	 * as much as possible to negatively impact the user workload.
+	 */
+	nr_rnd = dmz_nr_rnd_zones(zmd);
+	nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd);
+	p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd;
+	if (dmz_target_idle(zrc) || p_unmap_rnd < DMZ_RECLAIM_LOW_UNMAP_RND / 2) {
+		/* Idle or very low percentage: go fast */
+		zrc->kc_throttle.throttle = 100;
+	} else {
+		/* Busy but we still have some random zone: throttle */
+		zrc->kc_throttle.throttle = min(75U, 100U - p_unmap_rnd / 2);
+	}
+
+	dmz_dev_debug(zrc->dev,
+		      "Reclaim (%u): %s, %u%% free rnd zones (%u/%u)",
+		      zrc->kc_throttle.throttle,
+		      (dmz_target_idle(zrc) ? "Idle" : "Busy"),
+		      p_unmap_rnd, nr_unmap_rnd, nr_rnd);
+
+	dmz_reclaim(zrc);
+
+	dmz_schedule_reclaim(zrc);
+}
+
+/*
+ * Initialize reclaim.
+ */
+int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd,
+		    struct dmz_reclaim **reclaim)
+{
+	struct dmz_reclaim *zrc;
+	int ret;
+
+	zrc = kzalloc(sizeof(struct dmz_reclaim), GFP_KERNEL);
+	if (!zrc)
+		return -ENOMEM;
+
+	zrc->dev = dev;
+	zrc->metadata = zmd;
+	zrc->atime = jiffies;
+
+	/* Reclaim kcopyd client */
+	zrc->kc = dm_kcopyd_client_create(&zrc->kc_throttle);
+	if (IS_ERR(zrc->kc)) {
+		ret = PTR_ERR(zrc->kc);
+		zrc->kc = NULL;
+		goto err;
+	}
+
+	/* Reclaim work */
+	INIT_DELAYED_WORK(&zrc->work, dmz_reclaim_work);
+	zrc->wq = alloc_ordered_workqueue("dmz_rwq_%s", WQ_MEM_RECLAIM,
+					  dev->name);
+	if (!zrc->wq) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	*reclaim = zrc;
+	queue_delayed_work(zrc->wq, &zrc->work, 0);
+
+	return 0;
+err:
+	if (zrc->kc)
+		dm_kcopyd_client_destroy(zrc->kc);
+	kfree(zrc);
+
+	return ret;
+}
+
+/*
+ * Terminate reclaim.
+ */
+void dmz_dtr_reclaim(struct dmz_reclaim *zrc)
+{
+	cancel_delayed_work_sync(&zrc->work);
+	destroy_workqueue(zrc->wq);
+	dm_kcopyd_client_destroy(zrc->kc);
+	kfree(zrc);
+}
+
+/*
+ * Suspend reclaim.
+ */
+void dmz_suspend_reclaim(struct dmz_reclaim *zrc)
+{
+	cancel_delayed_work_sync(&zrc->work);
+}
+
+/*
+ * Resume reclaim.
+ */
+void dmz_resume_reclaim(struct dmz_reclaim *zrc)
+{
+	queue_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD);
+}
+
+/*
+ * BIO accounting.
+ */
+void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc)
+{
+	zrc->atime = jiffies;
+}
+
+/*
+ * Start reclaim if necessary.
+ */
+void dmz_schedule_reclaim(struct dmz_reclaim *zrc)
+{
+	if (dmz_should_reclaim(zrc))
+		mod_delayed_work(zrc->wq, &zrc->work, 0);
+}
+

drivers/md/dm-zoned.h

+/*
+ * 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 */