Merge tag 'for-5.14/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Various DM persistent-data library improvements and fixes that
   benefit both the DM thinp and cache targets.

 - A few small DM kcopyd efficiency improvements.

 - Significant zoned related block core, DM core and DM zoned target
   changes that culminate with adding zoned append emulation (which is
   required to properly fix DM crypt's zoned support).

 - Various DM writecache target changes that improve efficiency. Adds an
   optional "metadata_only" feature that only promotes bios flagged with
   REQ_META. But the most significant improvement is writecache's
   ability to pause writeback, for a confiurable time, if/when the
   working set is larger than the cache (and the cache is full) -- this
   ensures performance is no worse than the slower origin device.

* tag 'for-5.14/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (35 commits)
  dm writecache: make writeback pause configurable
  dm writecache: pause writeback if cache full and origin being written directly
  dm io tracker: factor out IO tracker
  dm btree remove: assign new_root only when removal succeeds
  dm zone: fix dm_revalidate_zones() memory allocation
  dm ps io affinity: remove redundant continue statement
  dm writecache: add optional "metadata_only" parameter
  dm writecache: add "cleaner" and "max_age" to Documentation
  dm writecache: write at least 4k when committing
  dm writecache: flush origin device when writing and cache is full
  dm writecache: have ssd writeback wait if the kcopyd workqueue is busy
  dm writecache: use list_move instead of list_del/list_add in writecache_writeback()
  dm writecache: commit just one block, not a full page
  dm writecache: remove unused gfp_t argument from wc_add_block()
  dm crypt: Fix zoned block device support
  dm: introduce zone append emulation
  dm: rearrange core declarations for extended use from dm-zone.c
  block: introduce BIO_ZONE_WRITE_LOCKED bio flag
  block: introduce bio zone helpers
  block: improve handling of all zones reset operation
  ...

Author: torvalds

Documentation/admin-guide/device-mapper/writecache.rst

@@ -12,7 +12,6 @@ first sector should contain valid superblock from previous invocation.
 Constructor parameters:
 
 1. type of the cache device - "p" or "s"
-
 	- p - persistent memory
 	- s - SSD
 2. the underlying device that will be cached
@@ -21,7 +20,6 @@ Constructor parameters:
    size)
 5. the number of optional parameters (the parameters with an argument
    count as two)
-
 	start_sector n		(default: 0)
 		offset from the start of cache device in 512-byte sectors
 	high_watermark n	(default: 50)
@@ -53,6 +51,27 @@ Constructor parameters:
 
 		- some underlying devices perform better with fua, some
 		  with nofua. The user should test it
+	cleaner
+		when this option is activated (either in the constructor
+		arguments or by a message), the cache will not promote
+		new writes (however, writes to already cached blocks are
+		promoted, to avoid data corruption due to misordered
+		writes) and it will gradually writeback any cached
+		data. The userspace can then monitor the cleaning
+		process with "dmsetup status". When the number of cached
+		blocks drops to zero, userspace can unload the
+		dm-writecache target and replace it with dm-linear or
+		other targets.
+	max_age n
+		specifies the maximum age of a block in milliseconds. If
+		a block is stored in the cache for too long, it will be
+		written to the underlying device and cleaned up.
+	metadata_only
+		only metadata is promoted to the cache. This option
+		improves performance for heavier REQ_META workloads.
+	pause_writeback n	(default: 3000)
+		pause writeback if there was some write I/O redirected to
+		the origin volume in the last n milliseconds
 
 Status:
 1. error indicator - 0 if there was no error, otherwise error number
@@ -77,3 +96,5 @@ Messages:
 		5. resume the device, so that it will use the linear
 		   target
 		6. the cache device is now inactive and it can be deleted
+	cleaner
+		See above "cleaner" constructor documentation.

block/blk-zoned.c

@@ -161,18 +161,89 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
-static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
-						sector_t sector,
-						sector_t nr_sectors)
+static inline unsigned long *blk_alloc_zone_bitmap(int node,
+						   unsigned int nr_zones)
 {
-	if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
-		return false;
+	return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
+			    GFP_NOIO, node);
+}
 
+static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
+				  void *data)
+{
 	/*
-	 * REQ_OP_ZONE_RESET_ALL can be executed only if the number of sectors
-	 * of the applicable zone range is the entire disk.
+	 * For an all-zones reset, ignore conventional, empty, read-only
+	 * and offline zones.
 	 */
-	return !sector && nr_sectors == get_capacity(bdev->bd_disk);
+	switch (zone->cond) {
+	case BLK_ZONE_COND_NOT_WP:
+	case BLK_ZONE_COND_EMPTY:
+	case BLK_ZONE_COND_READONLY:
+	case BLK_ZONE_COND_OFFLINE:
+		return 0;
+	default:
+		set_bit(idx, (unsigned long *)data);
+		return 0;
+	}
+}
+
+static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
+					  gfp_t gfp_mask)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	sector_t capacity = get_capacity(bdev->bd_disk);
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
+	unsigned long *need_reset;
+	struct bio *bio = NULL;
+	sector_t sector = 0;
+	int ret;
+
+	need_reset = blk_alloc_zone_bitmap(q->node, q->nr_zones);
+	if (!need_reset)
+		return -ENOMEM;
+
+	ret = bdev->bd_disk->fops->report_zones(bdev->bd_disk, 0,
+				q->nr_zones, blk_zone_need_reset_cb,
+				need_reset);
+	if (ret < 0)
+		goto out_free_need_reset;
+
+	ret = 0;
+	while (sector < capacity) {
+		if (!test_bit(blk_queue_zone_no(q, sector), need_reset)) {
+			sector += zone_sectors;
+			continue;
+		}
+
+		bio = blk_next_bio(bio, 0, gfp_mask);
+		bio_set_dev(bio, bdev);
+		bio->bi_opf = REQ_OP_ZONE_RESET | REQ_SYNC;
+		bio->bi_iter.bi_sector = sector;
+		sector += zone_sectors;
+
+		/* This may take a while, so be nice to others */
+		cond_resched();
+	}
+
+	if (bio) {
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+
+out_free_need_reset:
+	kfree(need_reset);
+	return ret;
+}
+
+static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
+{
+	struct bio bio;
+
+	bio_init(&bio, NULL, 0);
+	bio_set_dev(&bio, bdev);
+	bio.bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC;
+
+	return submit_bio_wait(&bio);
 }
 
 /**
@@ -200,7 +271,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 	sector_t capacity = get_capacity(bdev->bd_disk);
 	sector_t end_sector = sector + nr_sectors;
 	struct bio *bio = NULL;
-	int ret;
+	int ret = 0;
 
 	if (!blk_queue_is_zoned(q))
 		return -EOPNOTSUPP;
@@ -222,20 +293,21 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 	if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity)
 		return -EINVAL;
 
+	/*
+	 * In the case of a zone reset operation over all zones,
+	 * REQ_OP_ZONE_RESET_ALL can be used with devices supporting this
+	 * command. For other devices, we emulate this command behavior by
+	 * identifying the zones needing a reset.
+	 */
+	if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) {
+		if (!blk_queue_zone_resetall(q))
+			return blkdev_zone_reset_all_emulated(bdev, gfp_mask);
+		return blkdev_zone_reset_all(bdev, gfp_mask);
+	}
+
 	while (sector < end_sector) {
 		bio = blk_next_bio(bio, 0, gfp_mask);
 		bio_set_dev(bio, bdev);
-
-		/*
-		 * Special case for the zone reset operation that reset all
-		 * zones, this is useful for applications like mkfs.
-		 */
-		if (op == REQ_OP_ZONE_RESET &&
-		    blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
-			bio->bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC;
-			break;
-		}
-
 		bio->bi_opf = op | REQ_SYNC;
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
@@ -396,13 +468,6 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 	return ret;
 }
 
-static inline unsigned long *blk_alloc_zone_bitmap(int node,
-						   unsigned int nr_zones)
-{
-	return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
-			    GFP_NOIO, node);
-}
-
 void blk_queue_free_zone_bitmaps(struct request_queue *q)
 {
 	kfree(q->conv_zones_bitmap);

drivers/md/Makefile

@@ -92,6 +92,10 @@ ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o
 endif
 
+ifeq ($(CONFIG_BLK_DEV_ZONED),y)
+dm-mod-objs			+= dm-zone.o
+endif
+
 ifeq ($(CONFIG_DM_VERITY_FEC),y)
 dm-verity-objs			+= dm-verity-fec.o
 endif

drivers/md/dm-cache-target.c

@@ -8,6 +8,7 @@
 #include "dm-bio-prison-v2.h"
 #include "dm-bio-record.h"
 #include "dm-cache-metadata.h"
+#include "dm-io-tracker.h"
 
 #include <linux/dm-io.h>
 #include <linux/dm-kcopyd.h>
@@ -39,77 +40,6 @@ DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(cache_copy_throttle,
 
 /*----------------------------------------------------------------*/
 
-struct io_tracker {
-	spinlock_t lock;
-
-	/*
-	 * Sectors of in-flight IO.
-	 */
-	sector_t in_flight;
-
-	/*
-	 * The time, in jiffies, when this device became idle (if it is
-	 * indeed idle).
-	 */
-	unsigned long idle_time;
-	unsigned long last_update_time;
-};
-
-static void iot_init(struct io_tracker *iot)
-{
-	spin_lock_init(&iot->lock);
-	iot->in_flight = 0ul;
-	iot->idle_time = 0ul;
-	iot->last_update_time = jiffies;
-}
-
-static bool __iot_idle_for(struct io_tracker *iot, unsigned long jifs)
-{
-	if (iot->in_flight)
-		return false;
-
-	return time_after(jiffies, iot->idle_time + jifs);
-}
-
-static bool iot_idle_for(struct io_tracker *iot, unsigned long jifs)
-{
-	bool r;
-
-	spin_lock_irq(&iot->lock);
-	r = __iot_idle_for(iot, jifs);
-	spin_unlock_irq(&iot->lock);
-
-	return r;
-}
-
-static void iot_io_begin(struct io_tracker *iot, sector_t len)
-{
-	spin_lock_irq(&iot->lock);
-	iot->in_flight += len;
-	spin_unlock_irq(&iot->lock);
-}
-
-static void __iot_io_end(struct io_tracker *iot, sector_t len)
-{
-	if (!len)
-		return;
-
-	iot->in_flight -= len;
-	if (!iot->in_flight)
-		iot->idle_time = jiffies;
-}
-
-static void iot_io_end(struct io_tracker *iot, sector_t len)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&iot->lock, flags);
-	__iot_io_end(iot, len);
-	spin_unlock_irqrestore(&iot->lock, flags);
-}
-
-/*----------------------------------------------------------------*/
-
 /*
  * Represents a chunk of future work.  'input' allows continuations to pass
  * values between themselves, typically error values.
@@ -470,7 +400,7 @@ struct cache {
 	struct batcher committer;
 	struct work_struct commit_ws;
 
-	struct io_tracker tracker;
+	struct dm_io_tracker tracker;
 
 	mempool_t migration_pool;
 
@@ -866,15 +796,15 @@ static void accounted_begin(struct cache *cache, struct bio *bio)
 	if (accountable_bio(cache, bio)) {
 		pb = get_per_bio_data(bio);
 		pb->len = bio_sectors(bio);
-		iot_io_begin(&cache->tracker, pb->len);
+		dm_iot_io_begin(&cache->tracker, pb->len);
 	}
 }
 
 static void accounted_complete(struct cache *cache, struct bio *bio)
 {
 	struct per_bio_data *pb = get_per_bio_data(bio);
 
-	iot_io_end(&cache->tracker, pb->len);
+	dm_iot_io_end(&cache->tracker, pb->len);
 }
 
 static void accounted_request(struct cache *cache, struct bio *bio)
@@ -1642,7 +1572,7 @@ enum busy {
 
 static enum busy spare_migration_bandwidth(struct cache *cache)
 {
-	bool idle = iot_idle_for(&cache->tracker, HZ);
+	bool idle = dm_iot_idle_for(&cache->tracker, HZ);
 	sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) *
 		cache->sectors_per_block;
 
@@ -2603,7 +2533,7 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 
 	batcher_init(&cache->committer, commit_op, cache,
 		     issue_op, cache, cache->wq);
-	iot_init(&cache->tracker);
+	dm_iot_init(&cache->tracker);
 
 	init_rwsem(&cache->background_work_lock);
 	prevent_background_work(cache);