1 files changed, 235 insertions, 207 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6a5e9ed2fcc..32b958dbc49 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -49,6 +49,13 @@ static unsigned int _major = 0;
 static DEFINE_IDR(_minor_idr);
 
 static DEFINE_SPINLOCK(_minor_lock);
+
+static void do_deferred_remove(struct work_struct *w);
+
+static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
+
+static struct workqueue_struct *deferred_remove_workqueue;
+
 /*
  * For bio-based dm.
  * One of these is allocated per bio.
@@ -89,13 +96,6 @@ struct dm_rq_clone_bio_info {
 	struct bio clone;
 };
 
-union map_info *dm_get_mapinfo(struct bio *bio)
-{
-	if (bio && bio->bi_private)
-		return &((struct dm_target_io *)bio->bi_private)->info;
-	return NULL;
-}
-
 union map_info *dm_get_rq_mapinfo(struct request *rq)
 {
 	if (rq && rq->end_io_data)
@@ -116,6 +116,7 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
 #define DMF_DELETING 4
 #define DMF_NOFLUSH_SUSPENDING 5
 #define DMF_MERGE_IS_OPTIONAL 6
+#define DMF_DEFERRED_REMOVE 7
 
 /*
  * A dummy definition to make RCU happy.
@@ -194,8 +195,8 @@ struct mapped_device {
 	/* forced geometry settings */
 	struct hd_geometry geometry;
 
-	/* sysfs handle */
-	struct kobject kobj;
+	/* kobject and completion */
+	struct dm_kobject_holder kobj_holder;
 
 	/* zero-length flush that will be cloned and submitted to targets */
 	struct bio flush_bio;
@@ -211,10 +212,55 @@ struct dm_md_mempools {
 	struct bio_set *bs;
 };
 
-#define MIN_IOS 256
+#define RESERVED_BIO_BASED_IOS		16
+#define RESERVED_REQUEST_BASED_IOS	256
+#define RESERVED_MAX_IOS		1024
 static struct kmem_cache *_io_cache;
 static struct kmem_cache *_rq_tio_cache;
 
+/*
+ * Bio-based DM's mempools' reserved IOs set by the user.
+ */
+static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS;
+
+/*
+ * Request-based DM's mempools' reserved IOs set by the user.
+ */
+static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
+
+static unsigned __dm_get_reserved_ios(unsigned *reserved_ios,
+				      unsigned def, unsigned max)
+{
+	unsigned ios = ACCESS_ONCE(*reserved_ios);
+	unsigned modified_ios = 0;
+
+	if (!ios)
+		modified_ios = def;
+	else if (ios > max)
+		modified_ios = max;
+
+	if (modified_ios) {
+		(void)cmpxchg(reserved_ios, ios, modified_ios);
+		ios = modified_ios;
+	}
+
+	return ios;
+}
+
+unsigned dm_get_reserved_bio_based_ios(void)
+{
+	return __dm_get_reserved_ios(&reserved_bio_based_ios,
+				     RESERVED_BIO_BASED_IOS, RESERVED_MAX_IOS);
+}
+EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios);
+
+unsigned dm_get_reserved_rq_based_ios(void)
+{
+	return __dm_get_reserved_ios(&reserved_rq_based_ios,
+				     RESERVED_REQUEST_BASED_IOS, RESERVED_MAX_IOS);
+}
+EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);
+
 static int __init local_init(void)
 {
 	int r = -ENOMEM;
@@ -232,16 +278,24 @@ static int __init local_init(void)
 	if (r)
 		goto out_free_rq_tio_cache;
 
+	deferred_remove_workqueue = alloc_workqueue("kdmremove", WQ_UNBOUND, 1);
+	if (!deferred_remove_workqueue) {
+		r = -ENOMEM;
+		goto out_uevent_exit;
+	}
+
 	_major = major;
 	r = register_blkdev(_major, _name);
 	if (r < 0)
-		goto out_uevent_exit;
+		goto out_free_workqueue;
 
 	if (!_major)
 		_major = r;
 
 	return 0;
 
+out_free_workqueue:
+	destroy_workqueue(deferred_remove_workqueue);
 out_uevent_exit:
 	dm_uevent_exit();
 out_free_rq_tio_cache:
@@ -254,6 +308,9 @@ out_free_io_cache:
 
 static void local_exit(void)
 {
+	flush_scheduled_work();
+	destroy_workqueue(deferred_remove_workqueue);
+
 	kmem_cache_destroy(_rq_tio_cache);
 	kmem_cache_destroy(_io_cache);
 	unregister_blkdev(_major, _name);
@@ -359,7 +416,10 @@ static void dm_blk_close(struct gendisk *disk, fmode_t mode)
 
 	spin_lock(&_minor_lock);
 
-	atomic_dec(&md->open_count);
+	if (atomic_dec_and_test(&md->open_count) &&
+	    (test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
+		queue_work(deferred_remove_workqueue, &deferred_remove_work);
+
 	dm_put(md);
 
 	spin_unlock(&_minor_lock);
@@ -373,14 +433,18 @@ int dm_open_count(struct mapped_device *md)
 /*
  * Guarantees nothing is using the device before it's deleted.
  */
-int dm_lock_for_deletion(struct mapped_device *md)
+int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred)
 {
 	int r = 0;
 
 	spin_lock(&_minor_lock);
 
-	if (dm_open_count(md))
+	if (dm_open_count(md)) {
 		r = -EBUSY;
+		if (mark_deferred)
+			set_bit(DMF_DEFERRED_REMOVE, &md->flags);
+	} else if (only_deferred && !test_bit(DMF_DEFERRED_REMOVE, &md->flags))
+		r = -EEXIST;
 	else
 		set_bit(DMF_DELETING, &md->flags);
 
@@ -389,11 +453,37 @@ int dm_lock_for_deletion(struct mapped_device *md)
 	return r;
 }
 
+int dm_cancel_deferred_remove(struct mapped_device *md)
+{
+	int r = 0;
+
+	spin_lock(&_minor_lock);
+
+	if (test_bit(DMF_DELETING, &md->flags))
+		r = -EBUSY;
+	else
+		clear_bit(DMF_DEFERRED_REMOVE, &md->flags);
+
+	spin_unlock(&_minor_lock);
+
+	return r;
+}
+
+static void do_deferred_remove(struct work_struct *w)
+{
+	dm_deferred_remove();
+}
+
 sector_t dm_get_size(struct mapped_device *md)
 {
 	return get_capacity(md->disk);
 }
 
+struct request_queue *dm_get_md_queue(struct mapped_device *md)
+{
+	return md->queue;
+}
+
 struct dm_stats *dm_get_stats(struct mapped_device *md)
 {
 	return &md->stats;
@@ -494,7 +584,7 @@ static void start_io_acct(struct dm_io *io)
 		atomic_inc_return(&md->pending[rw]));
 
 	if (unlikely(dm_stats_used(&md->stats)))
-		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_sector,
+		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector,
 				    bio_sectors(bio), false, 0, &io->stats_aux);
 }
 
@@ -512,7 +602,7 @@ static void end_io_acct(struct dm_io *io)
 	part_stat_unlock();
 
 	if (unlikely(dm_stats_used(&md->stats)))
-		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_sector,
+		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector,
 				    bio_sectors(bio), true, duration, &io->stats_aux);
 
 	/*
@@ -661,7 +751,7 @@ static void dec_pending(struct dm_io *io, int error)
 		if (io_error == DM_ENDIO_REQUEUE)
 			return;
 
-		if ((bio->bi_rw & REQ_FLUSH) && bio->bi_size) {
+		if ((bio->bi_rw & REQ_FLUSH) && bio->bi_iter.bi_size) {
 			/*
 			 * Preflush done for flush with data, reissue
 			 * without REQ_FLUSH.
@@ -676,10 +766,18 @@ static void dec_pending(struct dm_io *io, int error)
 	}
 }
 
+static void disable_write_same(struct mapped_device *md)
+{
+	struct queue_limits *limits = dm_get_queue_limits(md);
+
+	/* device doesn't really support WRITE SAME, disable it */
+	limits->max_write_same_sectors = 0;
+}
+
 static void clone_endio(struct bio *bio, int error)
 {
 	int r = 0;
-	struct dm_target_io *tio = bio->bi_private;
+	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
 	struct dm_io *io = tio->io;
 	struct mapped_device *md = tio->io->md;
 	dm_endio_fn endio = tio->ti->type->end_io;
@@ -704,6 +802,10 @@ static void clone_endio(struct bio *bio, int error)
 		}
 	}
 
+	if (unlikely(r == -EREMOTEIO && (bio->bi_rw & REQ_WRITE_SAME) &&
+		     !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors))
+		disable_write_same(md);
+
 	free_tio(md, tio);
 	dec_pending(io, error);
 }
@@ -713,10 +815,11 @@ static void clone_endio(struct bio *bio, int error)
  */
 static void end_clone_bio(struct bio *clone, int error)
 {
-	struct dm_rq_clone_bio_info *info = clone->bi_private;
+	struct dm_rq_clone_bio_info *info =
+		container_of(clone, struct dm_rq_clone_bio_info, clone);
 	struct dm_rq_target_io *tio = info->tio;
 	struct bio *bio = info->orig;
-	unsigned int nr_bytes = info->orig->bi_size;
+	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
 
 	bio_put(clone);
 
@@ -897,6 +1000,10 @@ static void dm_done(struct request *clone, int error, bool mapped)
 			r = rq_end_io(tio->ti, clone, error, &tio->info);
 	}
 
+	if (unlikely(r == -EREMOTEIO && (clone->cmd_flags & REQ_WRITE_SAME) &&
+		     !clone->q->limits.max_write_same_sectors))
+		disable_write_same(tio->md);
+
 	if (r <= 0)
 		/* The target wants to complete the I/O */
 		dm_end_request(clone, r);
@@ -1030,6 +1137,46 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
 }
 EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
 
+/*
+ * A target may call dm_accept_partial_bio only from the map routine.  It is
+ * allowed for all bio types except REQ_FLUSH.
+ *
+ * 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
+ * sent in a next bio.
+ *
+ * A diagram that explains the arithmetics:
+ * +--------------------+---------------+-------+
+ * |         1          |       2       |   3   |
+ * +--------------------+---------------+-------+
+ *
+ * <-------------- *tio->len_ptr --------------->
+ *                      <------- bi_size ------->
+ *                      <-- n_sectors -->
+ *
+ * Region 1 was already iterated over with bio_advance or similar function.
+ *	(it may be empty if the target doesn't use bio_advance)
+ * Region 2 is the remaining bio size that the target wants to process.
+ *	(it may be empty if region 1 is non-empty, although there is no reason
+ *	 to make it empty)
+ * The target requires that region 3 is to be sent in the next bio.
+ *
+ * If the target wants to receive multiple copies of the bio (via num_*bios, etc),
+ * the partially processed part (the sum of regions 1+2) must be the same for all
+ * copies of the bio.
+ */
+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_rw & REQ_FLUSH);
+	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;
+}
+EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
+
 static void __map_bio(struct dm_target_io *tio)
 {
 	int r;
@@ -1039,7 +1186,6 @@ static void __map_bio(struct dm_target_io *tio)
 	struct dm_target *ti = tio->ti;
 
 	clone->bi_end_io = clone_endio;
-	clone->bi_private = tio;
 
 	/*
 	 * Map the clone.  If r == 0 we don't need to do
@@ -1047,7 +1193,7 @@ static void __map_bio(struct dm_target_io *tio)
 	 * this io.
 	 */
 	atomic_inc(&tio->io->io_count);
-	sector = clone->bi_sector;
+	sector = clone->bi_iter.bi_sector;
 	r = ti->type->map(ti, clone);
 	if (r == DM_MAPIO_REMAPPED) {
 		/* the bio has been remapped so dispatch it */
@@ -1073,77 +1219,33 @@ struct clone_info {
 	struct bio *bio;
 	struct dm_io *io;
 	sector_t sector;
-	sector_t sector_count;
-	unsigned short idx;
+	unsigned sector_count;
 };
 
-static void bio_setup_sector(struct bio *bio, sector_t sector, sector_t len)
-{
-	bio->bi_sector = sector;
-	bio->bi_size = to_bytes(len);
-}
-
-static void bio_setup_bv(struct bio *bio, unsigned short idx, unsigned short bv_count)
-{
-	bio->bi_idx = idx;
-	bio->bi_vcnt = idx + bv_count;
-	bio->bi_flags &= ~(1 << BIO_SEG_VALID);
-}
-
-static void clone_bio_integrity(struct bio *bio, struct bio *clone,
-				unsigned short idx, unsigned len, unsigned offset,
-				unsigned trim)
-{
-	if (!bio_integrity(bio))
-		return;
-
-	bio_integrity_clone(clone, bio, GFP_NOIO);
-
-	if (trim)
-		bio_integrity_trim(clone, bio_sector_offset(bio, idx, offset), len);
-}
-
-/*
- * Creates a little bio that just does part of a bvec.
- */
-static void clone_split_bio(struct dm_target_io *tio, struct bio *bio,
-			    sector_t sector, unsigned short idx,
-			    unsigned offset, unsigned len)
+static void bio_setup_sector(struct bio *bio, sector_t sector, unsigned len)
 {
-	struct bio *clone = &tio->clone;
-	struct bio_vec *bv = bio->bi_io_vec + idx;
-
-	*clone->bi_io_vec = *bv;
-
-	bio_setup_sector(clone, sector, len);
-
-	clone->bi_bdev = bio->bi_bdev;
-	clone->bi_rw = bio->bi_rw;
-	clone->bi_vcnt = 1;
-	clone->bi_io_vec->bv_offset = offset;
-	clone->bi_io_vec->bv_len = clone->bi_size;
-	clone->bi_flags |= 1 << BIO_CLONED;
-
-	clone_bio_integrity(bio, clone, idx, len, offset, 1);
+	bio->bi_iter.bi_sector = sector;
+	bio->bi_iter.bi_size = to_bytes(len);
 }
 
 /*
  * Creates a bio that consists of range of complete bvecs.
  */
 static void clone_bio(struct dm_target_io *tio, struct bio *bio,
-		      sector_t sector, unsigned short idx,
-		      unsigned short bv_count, unsigned len)
+		      sector_t sector, unsigned len)
 {
 	struct bio *clone = &tio->clone;
-	unsigned trim = 0;
 
-	__bio_clone(clone, bio);
-	bio_setup_sector(clone, sector, len);
-	bio_setup_bv(clone, idx, bv_count);
+	__bio_clone_fast(clone, bio);
+
+	if (bio_integrity(bio))
+		bio_integrity_clone(clone, bio, GFP_NOIO);
 
-	if (idx != bio->bi_idx || clone->bi_size < bio->bi_size)
-		trim = 1;
-	clone_bio_integrity(bio, clone, idx, len, 0, trim);
+	bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
+	clone->bi_iter.bi_size = to_bytes(len);
+
+	if (bio_integrity(bio))
+		bio_integrity_trim(clone, 0, len);
 }
 
 static struct dm_target_io *alloc_tio(struct clone_info *ci,
@@ -1158,7 +1260,6 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci,
 
 	tio->io = ci->io;
 	tio->ti = ti;
-	memset(&tio->info, 0, sizeof(tio->info));
 	tio->target_bio_nr = target_bio_nr;
 
 	return tio;
@@ -1166,25 +1267,27 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci,
 
 static void __clone_and_map_simple_bio(struct clone_info *ci,
 				       struct dm_target *ti,
-				       unsigned target_bio_nr, sector_t len)
+				       unsigned target_bio_nr, unsigned *len)
 {
 	struct dm_target_io *tio = alloc_tio(ci, ti, ci->bio->bi_max_vecs, target_bio_nr);
 	struct bio *clone = &tio->clone;
 
+	tio->len_ptr = len;
+
 	/*
 	 * Discard requests require the bio's inline iovecs be initialized.
 	 * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
 	 * and discard, so no need for concern about wasted bvec allocations.
 	 */
-	 __bio_clone(clone, ci->bio);
+	 __bio_clone_fast(clone, ci->bio);
 	if (len)
-		bio_setup_sector(clone, ci->sector, len);
+		bio_setup_sector(clone, ci->sector, *len);
 
 	__map_bio(tio);
 }
 
 static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
-				  unsigned num_bios, sector_t len)
+				  unsigned num_bios, unsigned *len)
 {
 	unsigned target_bio_nr;
 
@@ -1199,16 +1302,13 @@ static int __send_empty_flush(struct clone_info *ci)
 
 	BUG_ON(bio_has_data(ci->bio));
 	while ((ti = dm_table_get_target(ci->map, target_nr++)))
-		__send_duplicate_bios(ci, ti, ti->num_flush_bios, 0);
+		__send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
 
 	return 0;
 }
 
 static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti,
-				     sector_t sector, int nr_iovecs,
-				     unsigned short idx, unsigned short bv_count,
-				     unsigned offset, unsigned len,
-				     unsigned split_bvec)
+				     sector_t sector, unsigned *len)
 {
 	struct bio *bio = ci->bio;
 	struct dm_target_io *tio;
@@ -1222,11 +1322,9 @@ static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti
 		num_target_bios = ti->num_write_bios(ti, bio);
 
 	for (target_bio_nr = 0; target_bio_nr < num_target_bios; target_bio_nr++) {
-		tio = alloc_tio(ci, ti, nr_iovecs, target_bio_nr);
-		if (split_bvec)
-			clone_split_bio(tio, bio, sector, idx, offset, len);
-		else
-			clone_bio(tio, bio, sector, idx, bv_count, len);
+		tio = alloc_tio(ci, ti, 0, target_bio_nr);
+		tio->len_ptr = len;
+		clone_bio(tio, bio, sector, *len);
 		__map_bio(tio);
 	}
 }
@@ -1255,7 +1353,7 @@ static int __send_changing_extent_only(struct clone_info *ci,
 				       is_split_required_fn is_split_required)
 {
 	struct dm_target *ti;
-	sector_t len;
+	unsigned len;
 	unsigned num_bios;
 
 	do {
@@ -1274,11 +1372,11 @@ static int __send_changing_extent_only(struct clone_info *ci,
 			return -EOPNOTSUPP;
 
 		if (is_split_required && !is_split_required(ti))
-			len = min(ci->sector_count, max_io_len_target_boundary(ci->sector, ti));
+			len = min((sector_t)ci->sector_count, max_io_len_target_boundary(ci->sector, ti));
 		else
-			len = min(ci->sector_count, max_io_len(ci->sector, ti));
+			len = min((sector_t)ci->sector_count, max_io_len(ci->sector, ti));
 
-		__send_duplicate_bios(ci, ti, num_bios, len);
+		__send_duplicate_bios(ci, ti, num_bios, &len);
 
 		ci->sector += len;
 	} while (ci->sector_count -= len);
@@ -1298,68 +1396,13 @@ static int __send_write_same(struct clone_info *ci)
 }
 
 /*
- * Find maximum number of sectors / bvecs we can process with a single bio.
- */
-static sector_t __len_within_target(struct clone_info *ci, sector_t max, int *idx)
-{
-	struct bio *bio = ci->bio;
-	sector_t bv_len, total_len = 0;
-
-	for (*idx = ci->idx; max && (*idx < bio->bi_vcnt); (*idx)++) {
-		bv_len = to_sector(bio->bi_io_vec[*idx].bv_len);
-
-		if (bv_len > max)
-			break;
-
-		max -= bv_len;
-		total_len += bv_len;
-	}
-
-	return total_len;
-}
-
-static int __split_bvec_across_targets(struct clone_info *ci,
-				       struct dm_target *ti, sector_t max)
-{
-	struct bio *bio = ci->bio;
-	struct bio_vec *bv = bio->bi_io_vec + ci->idx;
-	sector_t remaining = to_sector(bv->bv_len);
-	unsigned offset = 0;
-	sector_t len;
-
-	do {
-		if (offset) {
-			ti = dm_table_find_target(ci->map, ci->sector);
-			if (!dm_target_is_valid(ti))
-				return -EIO;
-
-			max = max_io_len(ci->sector, ti);
-		}
-
-		len = min(remaining, max);
-
-		__clone_and_map_data_bio(ci, ti, ci->sector, 1, ci->idx, 0,
-					 bv->bv_offset + offset, len, 1);
-
-		ci->sector += len;
-		ci->sector_count -= len;
-		offset += to_bytes(len);
-	} while (remaining -= len);
-
-	ci->idx++;
-
-	return 0;
-}
-
-/*
  * Select the correct strategy for processing a non-flush bio.
  */
 static int __split_and_process_non_flush(struct clone_info *ci)
 {
 	struct bio *bio = ci->bio;
 	struct dm_target *ti;
-	sector_t len, max;
-	int idx;
+	unsigned len;
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD))
 		return __send_discard(ci);
@@ -1370,41 +1413,14 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 	if (!dm_target_is_valid(ti))
 		return -EIO;
 
-	max = max_io_len(ci->sector, ti);
+	len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);
 
-	/*
-	 * Optimise for the simple case where we can do all of
-	 * the remaining io with a single clone.
-	 */
-	if (ci->sector_count <= max) {
-		__clone_and_map_data_bio(ci, ti, ci->sector, bio->bi_max_vecs,
-					 ci->idx, bio->bi_vcnt - ci->idx, 0,
-					 ci->sector_count, 0);
-		ci->sector_count = 0;
-		return 0;
-	}
+	__clone_and_map_data_bio(ci, ti, ci->sector, &len);
 
-	/*
-	 * There are some bvecs that don't span targets.
-	 * Do as many of these as possible.
-	 */
-	if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) {
-		len = __len_within_target(ci, max, &idx);
-
-		__clone_and_map_data_bio(ci, ti, ci->sector, bio->bi_max_vecs,
-					 ci->idx, idx - ci->idx, 0, len, 0);
-
-		ci->sector += len;
-		ci->sector_count -= len;
-		ci->idx = idx;
+	ci->sector += len;
+	ci->sector_count -= len;
 
-		return 0;
-	}
-
-	/*
-	 * Handle a bvec that must be split between two or more targets.
-	 */
-	return __split_bvec_across_targets(ci, ti, max);
+	return 0;
 }
 
 /*
@@ -1429,8 +1445,7 @@ static void __split_and_process_bio(struct mapped_device *md,
 	ci.io->bio = bio;
 	ci.io->md = md;
 	spin_lock_init(&ci.io->endio_lock);
-	ci.sector = bio->bi_sector;
-	ci.idx = bio->bi_idx;
+	ci.sector = bio->bi_iter.bi_sector;
 
 	start_io_acct(ci.io);
 
@@ -1494,7 +1509,6 @@ static int dm_merge_bvec(struct request_queue *q,
 	 * just one page.
 	 */
 	else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9)
-
 		max_size = 0;
 
 out:
@@ -1582,7 +1596,6 @@ static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
 	info->orig = bio_orig;
 	info->tio = tio;
 	bio->bi_end_io = end_clone_bio;
-	bio->bi_private = info;
 
 	return 0;
 }
@@ -1600,7 +1613,6 @@ static int setup_clone(struct request *clone, struct request *rq,
 	clone->cmd = rq->cmd;
 	clone->cmd_len = rq->cmd_len;
 	clone->sense = rq->sense;
-	clone->buffer = rq->buffer;
 	clone->end_io = end_clone_request;
 	clone->end_io_data = tio;
 
@@ -1960,6 +1972,7 @@ static struct mapped_device *alloc_dev(int minor)
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
+	init_completion(&md->kobj_holder.completion);
 
 	md->disk->major = _major;
 	md->disk->first_minor = minor;
@@ -2223,7 +2236,7 @@ static struct dm_table *__unbind(struct mapped_device *md)
 		return NULL;
 
 	dm_table_event_callback(map, NULL, NULL);
-	rcu_assign_pointer(md->map, NULL);
+	RCU_INIT_POINTER(md->map, NULL);
 	dm_sync_table(md);
 
 	return map;
@@ -2278,6 +2291,17 @@ struct target_type *dm_get_immutable_target_type(struct mapped_device *md)
 }
 
 /*
+ * The queue_limits are only valid as long as you have a reference
+ * count on 'md'.
+ */
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
+{
+	BUG_ON(!atomic_read(&md->holders));
+	return &md->queue->limits;
+}
+EXPORT_SYMBOL_GPL(dm_get_queue_limits);
+
+/*
  * Fully initialize a request-based queue (->elevator, ->request_fn, etc).
  */
 static int dm_init_request_based_queue(struct mapped_device *md)
@@ -2491,7 +2515,7 @@ static void dm_wq_work(struct work_struct *work)
 static void dm_queue_flush(struct mapped_device *md)
 {
 	clear_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	queue_work(md->wq, &md->work);
 }
 
@@ -2810,20 +2834,14 @@ struct gendisk *dm_disk(struct mapped_device *md)
 
 struct kobject *dm_kobject(struct mapped_device *md)
 {
-	return &md->kobj;
+	return &md->kobj_holder.kobj;
 }
 
-/*
- * struct mapped_device should not be exported outside of dm.c
- * so use this check to verify that kobj is part of md structure
- */
 struct mapped_device *dm_get_from_kobject(struct kobject *kobj)
 {
 	struct mapped_device *md;
 
-	md = container_of(kobj, struct mapped_device, kobj);
-	if (&md->kobj != kobj)
-		return NULL;
+	md = container_of(kobj, struct mapped_device, kobj_holder.kobj);
 
 	if (test_bit(DMF_FREEING, &md->flags) ||
 	    dm_deleting_md(md))
@@ -2838,6 +2856,11 @@ int dm_suspended_md(struct mapped_device *md)
 	return test_bit(DMF_SUSPENDED, &md->flags);
 }
 
+int dm_test_deferred_remove_flag(struct mapped_device *md)
+{
+	return test_bit(DMF_DEFERRED_REMOVE, &md->flags);
+}
+
 int dm_suspended(struct dm_target *ti)
 {
 	return dm_suspended_md(dm_table_get_md(ti->table));
@@ -2862,18 +2885,18 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u
 
 	if (type == DM_TYPE_BIO_BASED) {
 		cachep = _io_cache;
-		pool_size = 16;
+		pool_size = dm_get_reserved_bio_based_ios();
 		front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
 	} else if (type == DM_TYPE_REQUEST_BASED) {
 		cachep = _rq_tio_cache;
-		pool_size = MIN_IOS;
+		pool_size = dm_get_reserved_rq_based_ios();
 		front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
 		/* per_bio_data_size is not used. See __bind_mempools(). */
 		WARN_ON(per_bio_data_size != 0);
 	} else
 		goto out;
 
-	pools->io_pool = mempool_create_slab_pool(MIN_IOS, cachep);
+	pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
 	if (!pools->io_pool)
 		goto out;
 
@@ -2914,8 +2937,6 @@ static const struct block_device_operations dm_blk_dops = {
 	.owner = THIS_MODULE
 };
 
-EXPORT_SYMBOL(dm_get_mapinfo);
-
 /*
  * module hooks
  */
@@ -2924,6 +2945,13 @@ module_exit(dm_exit);
 
 module_param(major, uint, 0);
 MODULE_PARM_DESC(major, "The major number of the device mapper");
+
+module_param(reserved_bio_based_ios, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools");
+
+module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");
+
 MODULE_DESCRIPTION(DM_NAME " driver");
 MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");