diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 6be58b696377d9c6b013de935fed0578c823a375..daf25d0890b3d6cdf9852b739593648f00b86425 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -967,13 +967,22 @@ bool dm_table_request_based(struct dm_table *t)
 int dm_table_alloc_md_mempools(struct dm_table *t)
 {
 	unsigned type = dm_table_get_type(t);
+	unsigned per_bio_data_size = 0;
+	struct dm_target *tgt;
+	unsigned i;
 
 	if (unlikely(type == DM_TYPE_NONE)) {
 		DMWARN("no table type is set, can't allocate mempools");
 		return -EINVAL;
 	}
 
-	t->mempools = dm_alloc_md_mempools(type, t->integrity_supported);
+	if (type == DM_TYPE_BIO_BASED)
+		for (i = 0; i < t->num_targets; i++) {
+			tgt = t->targets + i;
+			per_bio_data_size = max(per_bio_data_size, tgt->per_bio_data_size);
+		}
+
+	t->mempools = dm_alloc_md_mempools(type, t->integrity_supported, per_bio_data_size);
 	if (!t->mempools)
 		return -ENOMEM;
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5401cdce0fc5cf14e294e936e1c140225c453159..2765cf2ba0ff1b4da44649948a967af8e1c22f03 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -62,18 +62,6 @@ struct dm_io {
 	spinlock_t endio_lock;
 };
 
-/*
- * For bio-based dm.
- * One of these is allocated per target within a bio.  Hopefully
- * this will be simplified out one day.
- */
-struct dm_target_io {
-	struct dm_io *io;
-	struct dm_target *ti;
-	union map_info info;
-	struct bio clone;
-};
-
 /*
  * For request-based dm.
  * One of these is allocated per request.
@@ -1980,13 +1968,20 @@ static void free_dev(struct mapped_device *md)
 
 static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 {
-	struct dm_md_mempools *p;
+	struct dm_md_mempools *p = dm_table_get_md_mempools(t);
 
-	if (md->io_pool && (md->tio_pool || dm_table_get_type(t) == DM_TYPE_BIO_BASED) && md->bs)
-		/* the md already has necessary mempools */
+	if (md->io_pool && (md->tio_pool || dm_table_get_type(t) == DM_TYPE_BIO_BASED) && md->bs) {
+		/*
+		 * The md already has necessary mempools. Reload just the
+		 * bioset because front_pad may have changed because
+		 * a different table was loaded.
+		 */
+		bioset_free(md->bs);
+		md->bs = p->bs;
+		p->bs = NULL;
 		goto out;
+	}
 
-	p = dm_table_get_md_mempools(t);
 	BUG_ON(!p || md->io_pool || md->tio_pool || md->bs);
 
 	md->io_pool = p->io_pool;
@@ -2745,7 +2740,7 @@ int dm_noflush_suspending(struct dm_target *ti)
 }
 EXPORT_SYMBOL_GPL(dm_noflush_suspending);
 
-struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity)
+struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, unsigned per_bio_data_size)
 {
 	struct dm_md_mempools *pools = kmalloc(sizeof(*pools), GFP_KERNEL);
 	unsigned int pool_size = (type == DM_TYPE_BIO_BASED) ? 16 : MIN_IOS;
@@ -2753,6 +2748,8 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity)
 	if (!pools)
 		return NULL;
 
+	per_bio_data_size = roundup(per_bio_data_size, __alignof__(struct dm_target_io));
+
 	pools->io_pool = (type == DM_TYPE_BIO_BASED) ?
 			 mempool_create_slab_pool(MIN_IOS, _io_cache) :
 			 mempool_create_slab_pool(MIN_IOS, _rq_bio_info_cache);
@@ -2768,7 +2765,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity)
 
 	pools->bs = (type == DM_TYPE_BIO_BASED) ?
 		bioset_create(pool_size,
-			      offsetof(struct dm_target_io, clone)) :
+			      per_bio_data_size + offsetof(struct dm_target_io, clone)) :
 		bioset_create(pool_size,
 			      offsetof(struct dm_rq_clone_bio_info, clone));
 	if (!pools->bs)
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 6a99fefaa74306aa6e586c47c3eacf33706556b1..45b97da1bd061f02a32e0e7523fdf5125ffb1089 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -159,7 +159,7 @@ void dm_kcopyd_exit(void);
 /*
  * Mempool operations
  */
-struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity);
+struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, unsigned per_bio_data_size);
 void dm_free_md_mempools(struct dm_md_mempools *pools);
 
 #endif
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index d1f6cd8486f28e890407bce23ecea5e181069886..6f0e73b4a80de30a92452c6a8b4a92f1eb722e2a 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -210,6 +210,12 @@ struct dm_target {
 	 */
 	unsigned num_write_same_requests;
 
+	/*
+	 * The minimum number of extra bytes allocated in each bio for the
+	 * target to use.  dm_per_bio_data returns the data location.
+	 */
+	unsigned per_bio_data_size;
+
 	/* target specific data */
 	void *private;
 
@@ -246,6 +252,30 @@ struct dm_target_callbacks {
 	int (*congested_fn) (struct dm_target_callbacks *, int);
 };
 
+/*
+ * For bio-based dm.
+ * One of these is allocated for each bio.
+ * This structure shouldn't be touched directly by target drivers.
+ * It is here so that we can inline dm_per_bio_data and
+ * dm_bio_from_per_bio_data
+ */
+struct dm_target_io {
+	struct dm_io *io;
+	struct dm_target *ti;
+	union map_info info;
+	struct bio clone;
+};
+
+static inline void *dm_per_bio_data(struct bio *bio, size_t data_size)
+{
+	return (char *)bio - offsetof(struct dm_target_io, clone) - data_size;
+}
+
+static inline struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size)
+{
+	return (struct bio *)((char *)data + data_size + offsetof(struct dm_target_io, clone));
+}
+
 int dm_register_target(struct target_type *t);
 void dm_unregister_target(struct target_type *t);