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
  ...

1 files changed, 55 insertions, 153 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a57aba553ebb..2c5f9e585211 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -74,38 +74,6 @@ struct clone_info {
 	unsigned sector_count;
 };
 
-/*
- * One of these is allocated per clone bio.
- */
-#define DM_TIO_MAGIC 7282014
-struct dm_target_io {
-	unsigned magic;
-	struct dm_io *io;
-	struct dm_target *ti;
-	unsigned target_bio_nr;
-	unsigned *len_ptr;
-	bool inside_dm_io;
-	struct bio clone;
-};
-
-/*
- * One of these is allocated per original bio.
- * It contains the first clone used for that original.
- */
-#define DM_IO_MAGIC 5191977
-struct dm_io {
-	unsigned magic;
-	struct mapped_device *md;
-	blk_status_t status;
-	atomic_t io_count;
-	struct bio *orig_bio;
-	unsigned long start_time;
-	spinlock_t endio_lock;
-	struct dm_stats_aux stats_aux;
-	/* last member of dm_target_io is 'struct bio' */
-	struct dm_target_io tio;
-};
-
 #define DM_TARGET_IO_BIO_OFFSET (offsetof(struct dm_target_io, clone))
 #define DM_IO_BIO_OFFSET \
 	(offsetof(struct dm_target_io, clone) + offsetof(struct dm_io, tio))
@@ -137,19 +105,6 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr);
 
 #define MINOR_ALLOCED ((void *)-1)
 
-/*
- * Bits for the md->flags field.
- */
-#define DMF_BLOCK_IO_FOR_SUSPEND 0
-#define DMF_SUSPENDED 1
-#define DMF_FROZEN 2
-#define DMF_FREEING 3
-#define DMF_DELETING 4
-#define DMF_NOFLUSH_SUSPENDING 5
-#define DMF_DEFERRED_REMOVE 6
-#define DMF_SUSPENDED_INTERNALLY 7
-#define DMF_POST_SUSPENDING 8
-
 #define DM_NUMA_NODE NUMA_NO_NODE
 static int dm_numa_node = DM_NUMA_NODE;
 
@@ -444,84 +399,6 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return dm_get_geometry(md, geo);
 }
 
-#ifdef CONFIG_BLK_DEV_ZONED
-int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data)
-{
-	struct dm_report_zones_args *args = data;
-	sector_t sector_diff = args->tgt->begin - args->start;
-
-	/*
-	 * Ignore zones beyond the target range.
-	 */
-	if (zone->start >= args->start + args->tgt->len)
-		return 0;
-
-	/*
-	 * Remap the start sector and write pointer position of the zone
-	 * to match its position in the target range.
-	 */
-	zone->start += sector_diff;
-	if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) {
-		if (zone->cond == BLK_ZONE_COND_FULL)
-			zone->wp = zone->start + zone->len;
-		else if (zone->cond == BLK_ZONE_COND_EMPTY)
-			zone->wp = zone->start;
-		else
-			zone->wp += sector_diff;
-	}
-
-	args->next_sector = zone->start + zone->len;
-	return args->orig_cb(zone, args->zone_idx++, args->orig_data);
-}
-EXPORT_SYMBOL_GPL(dm_report_zones_cb);
-
-static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
-		unsigned int nr_zones, report_zones_cb cb, void *data)
-{
-	struct mapped_device *md = disk->private_data;
-	struct dm_table *map;
-	int srcu_idx, ret;
-	struct dm_report_zones_args args = {
-		.next_sector = sector,
-		.orig_data = data,
-		.orig_cb = cb,
-	};
-
-	if (dm_suspended_md(md))
-		return -EAGAIN;
-
-	map = dm_get_live_table(md, &srcu_idx);
-	if (!map) {
-		ret = -EIO;
-		goto out;
-	}
-
-	do {
-		struct dm_target *tgt;
-
-		tgt = dm_table_find_target(map, args.next_sector);
-		if (WARN_ON_ONCE(!tgt->type->report_zones)) {
-			ret = -EIO;
-			goto out;
-		}
-
-		args.tgt = tgt;
-		ret = tgt->type->report_zones(tgt, &args,
-					      nr_zones - args.zone_idx);
-		if (ret < 0)
-			goto out;
-	} while (args.zone_idx < nr_zones &&
-		 args.next_sector < get_capacity(disk));
-
-	ret = args.zone_idx;
-out:
-	dm_put_live_table(md, srcu_idx);
-	return ret;
-}
-#else
-#define dm_blk_report_zones		NULL
-#endif /* CONFIG_BLK_DEV_ZONED */
-
 static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx,
 			    struct block_device **bdev)
 {
@@ -903,7 +780,7 @@ static int __noflush_suspending(struct mapped_device *md)
  * Decrements the number of outstanding ios that a bio has been
  * cloned into, completing the original io if necc.
  */
-static void dec_pending(struct dm_io *io, blk_status_t error)
+void dm_io_dec_pending(struct dm_io *io, blk_status_t error)
 {
 	unsigned long flags;
 	blk_status_t io_error;
@@ -919,22 +796,27 @@ static void dec_pending(struct dm_io *io, blk_status_t error)
 	}
 
 	if (atomic_dec_and_test(&io->io_count)) {
+		bio = io->orig_bio;
 		if (io->status == BLK_STS_DM_REQUEUE) {
 			/*
 			 * Target requested pushing back the I/O.
 			 */
 			spin_lock_irqsave(&md->deferred_lock, flags);
-			if (__noflush_suspending(md))
+			if (__noflush_suspending(md) &&
+			    !WARN_ON_ONCE(dm_is_zone_write(md, bio))) {
 				/* NOTE early return due to BLK_STS_DM_REQUEUE below */
-				bio_list_add_head(&md->deferred, io->orig_bio);
-			else
-				/* noflush suspend was interrupted. */
+				bio_list_add_head(&md->deferred, bio);
+			} else {
+				/*
+				 * noflush suspend was interrupted or this is
+				 * a write to a zoned target.
+				 */
 				io->status = BLK_STS_IOERR;
+			}
 			spin_unlock_irqrestore(&md->deferred_lock, flags);
 		}
 
 		io_error = io->status;
-		bio = io->orig_bio;
 		end_io_acct(io);
 		free_io(md, io);
 
@@ -994,7 +876,6 @@ static void clone_endio(struct bio *bio)
 	struct dm_io *io = tio->io;
 	struct mapped_device *md = tio->io->md;
 	dm_endio_fn endio = tio->ti->type->end_io;
-	struct bio *orig_bio = io->orig_bio;
 	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
 
 	if (unlikely(error == BLK_STS_TARGET)) {
@@ -1009,23 +890,22 @@ static void clone_endio(struct bio *bio)
 			disable_write_zeroes(md);
 	}
 
-	/*
-	 * For zone-append bios get offset in zone of the written
-	 * sector and add that to the original bio sector pos.
-	 */
-	if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) {
-		sector_t written_sector = bio->bi_iter.bi_sector;
-		struct request_queue *q = orig_bio->bi_bdev->bd_disk->queue;
-		u64 mask = (u64)blk_queue_zone_sectors(q) - 1;
-
-		orig_bio->bi_iter.bi_sector += written_sector & mask;
-	}
+	if (blk_queue_is_zoned(q))
+		dm_zone_endio(io, bio);
 
 	if (endio) {
 		int r = endio(tio->ti, bio, &error);
 		switch (r) {
 		case DM_ENDIO_REQUEUE:
-			error = BLK_STS_DM_REQUEUE;
+			/*
+			 * Requeuing writes to a sequential zone of a zoned
+			 * target will break the sequential write pattern:
+			 * fail such IO.
+			 */
+			if (WARN_ON_ONCE(dm_is_zone_write(md, bio)))
+				error = BLK_STS_IOERR;
+			else
+				error = BLK_STS_DM_REQUEUE;
 			fallthrough;
 		case DM_ENDIO_DONE:
 			break;
@@ -1044,7 +924,7 @@ static void clone_endio(struct bio *bio)
 	}
 
 	free_tio(tio);
-	dec_pending(io, error);
+	dm_io_dec_pending(io, error);
 }
 
 /*
@@ -1237,8 +1117,8 @@ static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
- * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET,
- * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH.
+ * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_* zone management
+ * operations and REQ_OP_ZONE_APPEND (zone append writes).
  *
  * dm_accept_partial_bio informs the dm that the target only wants to process
  * additional n_sectors sectors of the bio and the rest of the data should be
@@ -1268,9 +1148,13 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
 {
 	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
 	unsigned bi_size = bio->bi_iter.bi_size >> SECTOR_SHIFT;
+
 	BUG_ON(bio->bi_opf & REQ_PREFLUSH);
+	BUG_ON(op_is_zone_mgmt(bio_op(bio)));
+	BUG_ON(bio_op(bio) == REQ_OP_ZONE_APPEND);
 	BUG_ON(bi_size > *tio->len_ptr);
 	BUG_ON(n_sectors > bi_size);
+
 	*tio->len_ptr -= bi_size - n_sectors;
 	bio->bi_iter.bi_size = n_sectors << SECTOR_SHIFT;
 }
@@ -1308,7 +1192,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 	 * anything, the target has assumed ownership of
 	 * this io.
 	 */
-	atomic_inc(&io->io_count);
+	dm_io_inc_pending(io);
 	sector = clone->bi_iter.bi_sector;
 
 	if (unlikely(swap_bios_limit(ti, clone))) {
@@ -1319,7 +1203,16 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 		down(&md->swap_bios_semaphore);
 	}
 
-	r = ti->type->map(ti, clone);
+	/*
+	 * Check if the IO needs a special mapping due to zone append emulation
+	 * on zoned target. In this case, dm_zone_map_bio() calls the target
+	 * map operation.
+	 */
+	if (dm_emulate_zone_append(io->md))
+		r = dm_zone_map_bio(tio);
+	else
+		r = ti->type->map(ti, clone);
+
 	switch (r) {
 	case DM_MAPIO_SUBMITTED:
 		break;
@@ -1334,7 +1227,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 			up(&md->swap_bios_semaphore);
 		}
 		free_tio(tio);
-		dec_pending(io, BLK_STS_IOERR);
+		dm_io_dec_pending(io, BLK_STS_IOERR);
 		break;
 	case DM_MAPIO_REQUEUE:
 		if (unlikely(swap_bios_limit(ti, clone))) {
@@ -1342,7 +1235,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 			up(&md->swap_bios_semaphore);
 		}
 		free_tio(tio);
-		dec_pending(io, BLK_STS_DM_REQUEUE);
+		dm_io_dec_pending(io, BLK_STS_DM_REQUEUE);
 		break;
 	default:
 		DMWARN("unimplemented target map return value: %d", r);
@@ -1631,7 +1524,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 
 	if (bio->bi_opf & REQ_PREFLUSH) {
 		error = __send_empty_flush(&ci);
-		/* dec_pending submits any data associated with flush */
+		/* dm_io_dec_pending submits any data associated with flush */
 	} else if (op_is_zone_mgmt(bio_op(bio))) {
 		ci.bio = bio;
 		ci.sector_count = 0;
@@ -1672,7 +1565,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 	}
 
 	/* drop the extra reference count */
-	dec_pending(ci.io, errno_to_blk_status(error));
+	dm_io_dec_pending(ci.io, errno_to_blk_status(error));
 	return ret;
 }
 
@@ -1817,6 +1710,7 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	mutex_destroy(&md->swap_bios_lock);
 
 	dm_mq_cleanup_mapped_device(md);
+	dm_cleanup_zoned_dev(md);
 }
 
 /*
@@ -2060,11 +1954,16 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 		goto out;
 	}
 
+	ret = dm_table_set_restrictions(t, q, limits);
+	if (ret) {
+		old_map = ERR_PTR(ret);
+		goto out;
+	}
+
 	old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
 	rcu_assign_pointer(md->map, (void *)t);
 	md->immutable_target_type = dm_table_get_immutable_target_type(t);
 
-	dm_table_set_restrictions(t, q, limits);
 	if (old_map)
 		dm_sync_table(md);
 
@@ -2183,7 +2082,10 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 		DMERR("Cannot calculate initial queue limits");
 		return r;
 	}
-	dm_table_set_restrictions(t, md->queue, &limits);
+	r = dm_table_set_restrictions(t, md->queue, &limits);
+	if (r)
+		return r;
+
 	blk_register_queue(md->disk);
 
 	return 0;