Linux-libre 4.3.2-gnu

56 files changed, 899 insertions, 1599 deletions

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index bfec3bdfe..3e01e6fb3 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -393,7 +393,7 @@ config DM_MULTIPATH
 	# of SCSI_DH if the latter isn't defined but if
 	# it is, DM_MULTIPATH must depend on it.  We get a build
 	# error if SCSI_DH=m and DM_MULTIPATH=y
-	depends on SCSI_DH || !SCSI_DH
+	depends on !SCSI_DH || SCSI
 	---help---
 	  Allow volume managers to support multipath hardware.
 
@@ -478,7 +478,7 @@ config DM_LOG_WRITES
 	  This device-mapper target takes two devices, one device to use
 	  normally, one to log all write operations done to the first device.
 	  This is for use by file system developers wishing to verify that
-	  their fs is writing a consitent file system at all times by allowing
+	  their fs is writing a consistent file system at all times by allowing
 	  them to replay the log in a variety of ways and to check the
 	  contents.
 
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 04f7bc28e..6b420a55c 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -243,19 +243,6 @@ struct keybuf {
 	DECLARE_ARRAY_ALLOCATOR(struct keybuf_key, freelist, KEYBUF_NR);
 };
 
-struct bio_split_pool {
-	struct bio_set		*bio_split;
-	mempool_t		*bio_split_hook;
-};
-
-struct bio_split_hook {
-	struct closure		cl;
-	struct bio_split_pool	*p;
-	struct bio		*bio;
-	bio_end_io_t		*bi_end_io;
-	void			*bi_private;
-};
-
 struct bcache_device {
 	struct closure		cl;
 
@@ -288,8 +275,6 @@ struct bcache_device {
 	int (*cache_miss)(struct btree *, struct search *,
 			  struct bio *, unsigned);
 	int (*ioctl) (struct bcache_device *, fmode_t, unsigned, unsigned long);
-
-	struct bio_split_pool	bio_split_hook;
 };
 
 struct io {
@@ -454,8 +439,6 @@ struct cache {
 	atomic_long_t		meta_sectors_written;
 	atomic_long_t		btree_sectors_written;
 	atomic_long_t		sectors_written;
-
-	struct bio_split_pool	bio_split_hook;
 };
 
 struct gc_stat {
@@ -873,7 +856,6 @@ void bch_bbio_endio(struct cache_set *, struct bio *, int, const char *);
 void bch_bbio_free(struct bio *, struct cache_set *);
 struct bio *bch_bbio_alloc(struct cache_set *);
 
-void bch_generic_make_request(struct bio *, struct bio_split_pool *);
 void __bch_submit_bbio(struct bio *, struct cache_set *);
 void bch_submit_bbio(struct bio *, struct cache_set *, struct bkey *, unsigned);
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 00cde40db..83392f856 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -278,7 +278,7 @@ err:
 	goto out;
 }
 
-static void btree_node_read_endio(struct bio *bio, int error)
+static void btree_node_read_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 	closure_put(cl);
@@ -305,7 +305,7 @@ static void bch_btree_node_read(struct btree *b)
 	bch_submit_bbio(bio, b->c, &b->key, 0);
 	closure_sync(&cl);
 
-	if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (bio->bi_error)
 		set_btree_node_io_error(b);
 
 	bch_bbio_free(bio, b->c);
@@ -371,15 +371,15 @@ static void btree_node_write_done(struct closure *cl)
 	__btree_node_write_done(cl);
 }
 
-static void btree_node_write_endio(struct bio *bio, int error)
+static void btree_node_write_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 	struct btree *b = container_of(cl, struct btree, io);
 
-	if (error)
+	if (bio->bi_error)
 		set_btree_node_io_error(b);
 
-	bch_bbio_count_io_errors(b->c, bio, error, "writing btree");
+	bch_bbio_count_io_errors(b->c, bio, bio->bi_error, "writing btree");
 	closure_put(cl);
 }
 
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 79a6d63e8..782cc2c8a 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -38,7 +38,7 @@
  * they are running owned by the thread that is running them. Otherwise, suppose
  * you submit some bios and wish to have a function run when they all complete:
  *
- * foo_endio(struct bio *bio, int error)
+ * foo_endio(struct bio *bio)
  * {
  *	closure_put(cl);
  * }
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index bf6a9ca18..86a0bb871 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -11,105 +11,6 @@
 
 #include <linux/blkdev.h>
 
-static unsigned bch_bio_max_sectors(struct bio *bio)
-{
-	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	struct bio_vec bv;
-	struct bvec_iter iter;
-	unsigned ret = 0, seg = 0;
-
-	if (bio->bi_rw & REQ_DISCARD)
-		return min(bio_sectors(bio), q->limits.max_discard_sectors);
-
-	bio_for_each_segment(bv, bio, iter) {
-		struct bvec_merge_data bvm = {
-			.bi_bdev	= bio->bi_bdev,
-			.bi_sector	= bio->bi_iter.bi_sector,
-			.bi_size	= ret << 9,
-			.bi_rw		= bio->bi_rw,
-		};
-
-		if (seg == min_t(unsigned, BIO_MAX_PAGES,
-				 queue_max_segments(q)))
-			break;
-
-		if (q->merge_bvec_fn &&
-		    q->merge_bvec_fn(q, &bvm, &bv) < (int) bv.bv_len)
-			break;
-
-		seg++;
-		ret += bv.bv_len >> 9;
-	}
-
-	ret = min(ret, queue_max_sectors(q));
-
-	WARN_ON(!ret);
-	ret = max_t(int, ret, bio_iovec(bio).bv_len >> 9);
-
-	return ret;
-}
-
-static void bch_bio_submit_split_done(struct closure *cl)
-{
-	struct bio_split_hook *s = container_of(cl, struct bio_split_hook, cl);
-
-	s->bio->bi_end_io = s->bi_end_io;
-	s->bio->bi_private = s->bi_private;
-	bio_endio(s->bio, 0);
-
-	closure_debug_destroy(&s->cl);
-	mempool_free(s, s->p->bio_split_hook);
-}
-
-static void bch_bio_submit_split_endio(struct bio *bio, int error)
-{
-	struct closure *cl = bio->bi_private;
-	struct bio_split_hook *s = container_of(cl, struct bio_split_hook, cl);
-
-	if (error)
-		clear_bit(BIO_UPTODATE, &s->bio->bi_flags);
-
-	bio_put(bio);
-	closure_put(cl);
-}
-
-void bch_generic_make_request(struct bio *bio, struct bio_split_pool *p)
-{
-	struct bio_split_hook *s;
-	struct bio *n;
-
-	if (!bio_has_data(bio) && !(bio->bi_rw & REQ_DISCARD))
-		goto submit;
-
-	if (bio_sectors(bio) <= bch_bio_max_sectors(bio))
-		goto submit;
-
-	s = mempool_alloc(p->bio_split_hook, GFP_NOIO);
-	closure_init(&s->cl, NULL);
-
-	s->bio		= bio;
-	s->p		= p;
-	s->bi_end_io	= bio->bi_end_io;
-	s->bi_private	= bio->bi_private;
-	bio_get(bio);
-
-	do {
-		n = bio_next_split(bio, bch_bio_max_sectors(bio),
-				   GFP_NOIO, s->p->bio_split);
-
-		n->bi_end_io	= bch_bio_submit_split_endio;
-		n->bi_private	= &s->cl;
-
-		closure_get(&s->cl);
-		generic_make_request(n);
-	} while (n != bio);
-
-	continue_at(&s->cl, bch_bio_submit_split_done, NULL);
-	return;
-submit:
-	generic_make_request(bio);
-}
-
 /* Bios with headers */
 
 void bch_bbio_free(struct bio *bio, struct cache_set *c)
@@ -139,7 +40,7 @@ void __bch_submit_bbio(struct bio *bio, struct cache_set *c)
 	bio->bi_bdev		= PTR_CACHE(c, &b->key, 0)->bdev;
 
 	b->submit_time_us = local_clock_us();
-	closure_bio_submit(bio, bio->bi_private, PTR_CACHE(c, &b->key, 0));
+	closure_bio_submit(bio, bio->bi_private);
 }
 
 void bch_submit_bbio(struct bio *bio, struct cache_set *c,
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 418607a6b..29eba7219 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -24,7 +24,7 @@
  * bit.
  */
 
-static void journal_read_endio(struct bio *bio, int error)
+static void journal_read_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 	closure_put(cl);
@@ -61,7 +61,7 @@ reread:		left = ca->sb.bucket_size - offset;
 		bio->bi_private = &cl;
 		bch_bio_map(bio, data);
 
-		closure_bio_submit(bio, &cl, ca);
+		closure_bio_submit(bio, &cl);
 		closure_sync(&cl);
 
 		/* This function could be simpler now since we no longer write
@@ -401,7 +401,7 @@ retry:
 
 #define last_seq(j)	((j)->seq - fifo_used(&(j)->pin) + 1)
 
-static void journal_discard_endio(struct bio *bio, int error)
+static void journal_discard_endio(struct bio *bio)
 {
 	struct journal_device *ja =
 		container_of(bio, struct journal_device, discard_bio);
@@ -547,11 +547,11 @@ void bch_journal_next(struct journal *j)
 		pr_debug("journal_pin full (%zu)", fifo_used(&j->pin));
 }
 
-static void journal_write_endio(struct bio *bio, int error)
+static void journal_write_endio(struct bio *bio)
 {
 	struct journal_write *w = bio->bi_private;
 
-	cache_set_err_on(error, w->c, "journal io error");
+	cache_set_err_on(bio->bi_error, w->c, "journal io error");
 	closure_put(&w->c->journal.io);
 }
 
@@ -648,7 +648,7 @@ static void journal_write_unlocked(struct closure *cl)
 	spin_unlock(&c->journal.lock);
 
 	while ((bio = bio_list_pop(&list)))
-		closure_bio_submit(bio, cl, c->cache[0]);
+		closure_bio_submit(bio, cl);
 
 	continue_at(cl, journal_write_done, NULL);
 }
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index cd7490311..b929fc944 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -60,20 +60,20 @@ static void write_moving_finish(struct closure *cl)
 	closure_return_with_destructor(cl, moving_io_destructor);
 }
 
-static void read_moving_endio(struct bio *bio, int error)
+static void read_moving_endio(struct bio *bio)
 {
 	struct bbio *b = container_of(bio, struct bbio, bio);
 	struct moving_io *io = container_of(bio->bi_private,
 					    struct moving_io, cl);
 
-	if (error)
-		io->op.error = error;
+	if (bio->bi_error)
+		io->op.error = bio->bi_error;
 	else if (!KEY_DIRTY(&b->key) &&
 		 ptr_stale(io->op.c, &b->key, 0)) {
 		io->op.error = -EINTR;
 	}
 
-	bch_bbio_endio(io->op.c, bio, error, "reading data to move");
+	bch_bbio_endio(io->op.c, bio, bio->bi_error, "reading data to move");
 }
 
 static void moving_init(struct moving_io *io)
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index f29279099..8e9877b04 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -173,22 +173,22 @@ static void bch_data_insert_error(struct closure *cl)
 	bch_data_insert_keys(cl);
 }
 
-static void bch_data_insert_endio(struct bio *bio, int error)
+static void bch_data_insert_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 
-	if (error) {
+	if (bio->bi_error) {
 		/* TODO: We could try to recover from this. */
 		if (op->writeback)
-			op->error = error;
+			op->error = bio->bi_error;
 		else if (!op->replace)
 			set_closure_fn(cl, bch_data_insert_error, op->wq);
 		else
 			set_closure_fn(cl, NULL, NULL);
 	}
 
-	bch_bbio_endio(op->c, bio, error, "writing data to cache");
+	bch_bbio_endio(op->c, bio, bio->bi_error, "writing data to cache");
 }
 
 static void bch_data_insert_start(struct closure *cl)
@@ -477,7 +477,7 @@ struct search {
 	struct data_insert_op	iop;
 };
 
-static void bch_cache_read_endio(struct bio *bio, int error)
+static void bch_cache_read_endio(struct bio *bio)
 {
 	struct bbio *b = container_of(bio, struct bbio, bio);
 	struct closure *cl = bio->bi_private;
@@ -490,15 +490,15 @@ static void bch_cache_read_endio(struct bio *bio, int error)
 	 * from the backing device.
 	 */
 
-	if (error)
-		s->iop.error = error;
+	if (bio->bi_error)
+		s->iop.error = bio->bi_error;
 	else if (!KEY_DIRTY(&b->key) &&
 		 ptr_stale(s->iop.c, &b->key, 0)) {
 		atomic_long_inc(&s->iop.c->cache_read_races);
 		s->iop.error = -EINTR;
 	}
 
-	bch_bbio_endio(s->iop.c, bio, error, "reading from cache");
+	bch_bbio_endio(s->iop.c, bio, bio->bi_error, "reading from cache");
 }
 
 /*
@@ -591,13 +591,13 @@ static void cache_lookup(struct closure *cl)
 
 /* Common code for the make_request functions */
 
-static void request_endio(struct bio *bio, int error)
+static void request_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 
-	if (error) {
+	if (bio->bi_error) {
 		struct search *s = container_of(cl, struct search, cl);
-		s->iop.error = error;
+		s->iop.error = bio->bi_error;
 		/* Only cache read errors are recoverable */
 		s->recoverable = false;
 	}
@@ -613,7 +613,8 @@ static void bio_complete(struct search *s)
 				    &s->d->disk->part0, s->start_time);
 
 		trace_bcache_request_end(s->d, s->orig_bio);
-		bio_endio(s->orig_bio, s->iop.error);
+		s->orig_bio->bi_error = s->iop.error;
+		bio_endio(s->orig_bio);
 		s->orig_bio = NULL;
 	}
 }
@@ -718,7 +719,7 @@ static void cached_dev_read_error(struct closure *cl)
 
 		/* XXX: invalidate cache */
 
-		closure_bio_submit(bio, cl, s->d);
+		closure_bio_submit(bio, cl);
 	}
 
 	continue_at(cl, cached_dev_cache_miss_done, NULL);
@@ -841,7 +842,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	s->cache_miss	= miss;
 	s->iop.bio	= cache_bio;
 	bio_get(cache_bio);
-	closure_bio_submit(cache_bio, &s->cl, s->d);
+	closure_bio_submit(cache_bio, &s->cl);
 
 	return ret;
 out_put:
@@ -849,7 +850,7 @@ out_put:
 out_submit:
 	miss->bi_end_io		= request_endio;
 	miss->bi_private	= &s->cl;
-	closure_bio_submit(miss, &s->cl, s->d);
+	closure_bio_submit(miss, &s->cl);
 	return ret;
 }
 
@@ -914,7 +915,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 
 		if (!(bio->bi_rw & REQ_DISCARD) ||
 		    blk_queue_discard(bdev_get_queue(dc->bdev)))
-			closure_bio_submit(bio, cl, s->d);
+			closure_bio_submit(bio, cl);
 	} else if (s->iop.writeback) {
 		bch_writeback_add(dc);
 		s->iop.bio = bio;
@@ -929,12 +930,12 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 			flush->bi_end_io = request_endio;
 			flush->bi_private = cl;
 
-			closure_bio_submit(flush, cl, s->d);
+			closure_bio_submit(flush, cl);
 		}
 	} else {
 		s->iop.bio = bio_clone_fast(bio, GFP_NOIO, dc->disk.bio_split);
 
-		closure_bio_submit(bio, cl, s->d);
+		closure_bio_submit(bio, cl);
 	}
 
 	closure_call(&s->iop.cl, bch_data_insert, NULL, cl);
@@ -950,7 +951,7 @@ static void cached_dev_nodata(struct closure *cl)
 		bch_journal_meta(s->iop.c, cl);
 
 	/* If it's a flush, we send the flush to the backing device too */
-	closure_bio_submit(bio, cl, s->d);
+	closure_bio_submit(bio, cl);
 
 	continue_at(cl, cached_dev_bio_complete, NULL);
 }
@@ -992,9 +993,9 @@ static void cached_dev_make_request(struct request_queue *q, struct bio *bio)
 	} else {
 		if ((bio->bi_rw & REQ_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(dc->bdev)))
-			bio_endio(bio, 0);
+			bio_endio(bio);
 		else
-			bch_generic_make_request(bio, &d->bio_split_hook);
+			generic_make_request(bio);
 	}
 }
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 94980bfca..679a093a3 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -59,29 +59,6 @@ struct workqueue_struct *bcache_wq;
 
 #define BTREE_MAX_PAGES		(256 * 1024 / PAGE_SIZE)
 
-static void bio_split_pool_free(struct bio_split_pool *p)
-{
-	if (p->bio_split_hook)
-		mempool_destroy(p->bio_split_hook);
-
-	if (p->bio_split)
-		bioset_free(p->bio_split);
-}
-
-static int bio_split_pool_init(struct bio_split_pool *p)
-{
-	p->bio_split = bioset_create(4, 0);
-	if (!p->bio_split)
-		return -ENOMEM;
-
-	p->bio_split_hook = mempool_create_kmalloc_pool(4,
-				sizeof(struct bio_split_hook));
-	if (!p->bio_split_hook)
-		return -ENOMEM;
-
-	return 0;
-}
-
 /* Superblock */
 
 static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
@@ -221,7 +198,7 @@ err:
 	return err;
 }
 
-static void write_bdev_super_endio(struct bio *bio, int error)
+static void write_bdev_super_endio(struct bio *bio)
 {
 	struct cached_dev *dc = bio->bi_private;
 	/* XXX: error checking */
@@ -290,11 +267,11 @@ void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent)
 	closure_return_with_destructor(cl, bch_write_bdev_super_unlock);
 }
 
-static void write_super_endio(struct bio *bio, int error)
+static void write_super_endio(struct bio *bio)
 {
 	struct cache *ca = bio->bi_private;
 
-	bch_count_io_errors(ca, error, "writing superblock");
+	bch_count_io_errors(ca, bio->bi_error, "writing superblock");
 	closure_put(&ca->set->sb_write);
 }
 
@@ -339,12 +316,12 @@ void bcache_write_super(struct cache_set *c)
 
 /* UUID io */
 
-static void uuid_endio(struct bio *bio, int error)
+static void uuid_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 	struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
 
-	cache_set_err_on(error, c, "accessing uuids");
+	cache_set_err_on(bio->bi_error, c, "accessing uuids");
 	bch_bbio_free(bio, c);
 	closure_put(cl);
 }
@@ -512,11 +489,11 @@ static struct uuid_entry *uuid_find_empty(struct cache_set *c)
  * disk.
  */
 
-static void prio_endio(struct bio *bio, int error)
+static void prio_endio(struct bio *bio)
 {
 	struct cache *ca = bio->bi_private;
 
-	cache_set_err_on(error, ca->set, "accessing priorities");
+	cache_set_err_on(bio->bi_error, ca->set, "accessing priorities");
 	bch_bbio_free(bio, ca->set);
 	closure_put(&ca->prio);
 }
@@ -537,7 +514,7 @@ static void prio_io(struct cache *ca, uint64_t bucket, unsigned long rw)
 	bio->bi_private = ca;
 	bch_bio_map(bio, ca->disk_buckets);
 
-	closure_bio_submit(bio, &ca->prio, ca);
+	closure_bio_submit(bio, &ca->prio);
 	closure_sync(cl);
 }
 
@@ -757,7 +734,6 @@ static void bcache_device_free(struct bcache_device *d)
 		put_disk(d->disk);
 	}
 
-	bio_split_pool_free(&d->bio_split_hook);
 	if (d->bio_split)
 		bioset_free(d->bio_split);
 	kvfree(d->full_dirty_stripes);
@@ -804,7 +780,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 		return minor;
 
 	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
-	    bio_split_pool_init(&d->bio_split_hook) ||
 	    !(d->disk = alloc_disk(1))) {
 		ida_simple_remove(&bcache_minor, minor);
 		return -ENOMEM;
@@ -830,7 +805,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	q->limits.max_sectors		= UINT_MAX;
 	q->limits.max_segment_size	= UINT_MAX;
 	q->limits.max_segments		= BIO_MAX_PAGES;
-	q->limits.max_discard_sectors	= UINT_MAX;
+	blk_queue_max_discard_sectors(q, UINT_MAX);
 	q->limits.discard_granularity	= 512;
 	q->limits.io_min		= block_size;
 	q->limits.logical_block_size	= block_size;
@@ -1793,8 +1768,6 @@ void bch_cache_release(struct kobject *kobj)
 		ca->set->cache[ca->sb.nr_this_dev] = NULL;
 	}
 
-	bio_split_pool_free(&ca->bio_split_hook);
-
 	free_pages((unsigned long) ca->disk_buckets, ilog2(bucket_pages(ca)));
 	kfree(ca->prio_buckets);
 	vfree(ca->buckets);
@@ -1839,8 +1812,7 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca)
 					  ca->sb.nbuckets)) ||
 	    !(ca->prio_buckets	= kzalloc(sizeof(uint64_t) * prio_buckets(ca) *
 					  2, GFP_KERNEL)) ||
-	    !(ca->disk_buckets	= alloc_bucket_pages(GFP_KERNEL, ca)) ||
-	    bio_split_pool_init(&ca->bio_split_hook))
+	    !(ca->disk_buckets	= alloc_bucket_pages(GFP_KERNEL, ca)))
 		return -ENOMEM;
 
 	ca->prio_last_buckets = ca->prio_buckets + prio_buckets(ca);
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 1d04c4859..cf2cbc211 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -4,6 +4,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/errno.h>
+#include <linux/blkdev.h>
 #include <linux/kernel.h>
 #include <linux/llist.h>
 #include <linux/ratelimit.h>
@@ -570,10 +571,10 @@ static inline sector_t bdev_sectors(struct block_device *bdev)
 	return bdev->bd_inode->i_size >> 9;
 }
 
-#define closure_bio_submit(bio, cl, dev)				\
+#define closure_bio_submit(bio, cl)					\
 do {									\
 	closure_get(cl);						\
-	bch_generic_make_request(bio, &(dev)->bio_split_hook);		\
+	generic_make_request(bio);					\
 } while (0)
 
 uint64_t bch_crc64_update(uint64_t, const void *, size_t);
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index f1986bcd1..b23f88d9f 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -166,12 +166,12 @@ static void write_dirty_finish(struct closure *cl)
 	closure_return_with_destructor(cl, dirty_io_destructor);
 }
 
-static void dirty_endio(struct bio *bio, int error)
+static void dirty_endio(struct bio *bio)
 {
 	struct keybuf_key *w = bio->bi_private;
 	struct dirty_io *io = w->private;
 
-	if (error)
+	if (bio->bi_error)
 		SET_KEY_DIRTY(&w->key, false);
 
 	closure_put(&io->cl);
@@ -188,27 +188,27 @@ static void write_dirty(struct closure *cl)
 	io->bio.bi_bdev		= io->dc->bdev;
 	io->bio.bi_end_io	= dirty_endio;
 
-	closure_bio_submit(&io->bio, cl, &io->dc->disk);
+	closure_bio_submit(&io->bio, cl);
 
 	continue_at(cl, write_dirty_finish, system_wq);
 }
 
-static void read_dirty_endio(struct bio *bio, int error)
+static void read_dirty_endio(struct bio *bio)
 {
 	struct keybuf_key *w = bio->bi_private;
 	struct dirty_io *io = w->private;
 
 	bch_count_io_errors(PTR_CACHE(io->dc->disk.c, &w->key, 0),
-			    error, "reading dirty data from cache");
+			    bio->bi_error, "reading dirty data from cache");
 
-	dirty_endio(bio, error);
+	dirty_endio(bio);
 }
 
 static void read_dirty_submit(struct closure *cl)
 {
 	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
 
-	closure_bio_submit(&io->bio, cl, &io->dc->disk);
+	closure_bio_submit(&io->bio, cl);
 
 	continue_at(cl, write_dirty, system_wq);
 }
diff --git a/drivers/md/dm-bio-prison.c b/drivers/md/dm-bio-prison.c
index cd6d1d21e..03af17448 100644
--- a/drivers/md/dm-bio-prison.c
+++ b/drivers/md/dm-bio-prison.c
@@ -236,8 +236,10 @@ void dm_cell_error(struct dm_bio_prison *prison,
 	bio_list_init(&bios);
 	dm_cell_release(prison, cell, &bios);
 
-	while ((bio = bio_list_pop(&bios)))
-		bio_endio(bio, error);
+	while ((bio = bio_list_pop(&bios))) {
+		bio->bi_error = error;
+		bio_endio(bio);
+	}
 }
 EXPORT_SYMBOL_GPL(dm_cell_error);
 
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 86dbbc737..83cc52eaf 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -545,7 +545,8 @@ static void dmio_complete(unsigned long error, void *context)
 {
 	struct dm_buffer *b = context;
 
-	b->bio.bi_end_io(&b->bio, error ? -EIO : 0);
+	b->bio.bi_error = error ? -EIO : 0;
+	b->bio.bi_end_io(&b->bio);
 }
 
 static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
@@ -575,13 +576,16 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
 	b->bio.bi_end_io = end_io;
 
 	r = dm_io(&io_req, 1, &region, NULL);
-	if (r)
-		end_io(&b->bio, r);
+	if (r) {
+		b->bio.bi_error = r;
+		end_io(&b->bio);
+	}
 }
 
-static void inline_endio(struct bio *bio, int error)
+static void inline_endio(struct bio *bio)
 {
 	bio_end_io_t *end_fn = bio->bi_private;
+	int error = bio->bi_error;
 
 	/*
 	 * Reset the bio to free any attached resources
@@ -589,7 +593,8 @@ static void inline_endio(struct bio *bio, int error)
 	 */
 	bio_reset(bio);
 
-	end_fn(bio, error);
+	bio->bi_error = error;
+	end_fn(bio);
 }
 
 static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
@@ -661,13 +666,14 @@ static void submit_io(struct dm_buffer *b, int rw, sector_t block,
  * Set the error, clear B_WRITING bit and wake anyone who was waiting on
  * it.
  */
-static void write_endio(struct bio *bio, int error)
+static void write_endio(struct bio *bio)
 {
 	struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
 
-	b->write_error = error;
-	if (unlikely(error)) {
+	b->write_error = bio->bi_error;
+	if (unlikely(bio->bi_error)) {
 		struct dm_bufio_client *c = b->c;
+		int error = bio->bi_error;
 		(void)cmpxchg(&c->async_write_error, 0, error);
 	}
 
@@ -1026,11 +1032,11 @@ found_buffer:
  * The endio routine for reading: set the error, clear the bit and wake up
  * anyone waiting on the buffer.
  */
-static void read_endio(struct bio *bio, int error)
+static void read_endio(struct bio *bio)
 {
 	struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
 
-	b->read_error = error;
+	b->read_error = bio->bi_error;
 
 	BUG_ON(!test_bit(B_READING, &b->state));
 
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 20cc36b01..0a17d1b91 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -634,10 +634,10 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 
 	disk_super = dm_block_data(sblock);
 
+	disk_super->flags = cpu_to_le32(cmd->flags);
 	if (mutator)
 		update_flags(disk_super, mutator);
 
-	disk_super->flags = cpu_to_le32(cmd->flags);
 	disk_super->mapping_root = cpu_to_le64(cmd->root);
 	disk_super->hint_root = cpu_to_le64(cmd->hint_root);
 	disk_super->discard_root = cpu_to_le64(cmd->discard_root);
diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index 200366c62..1ffbeb1b3 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -772,7 +772,7 @@ struct smq_policy {
 	struct dm_cache_policy policy;
 
 	/* protects everything */
-	struct mutex lock;
+	spinlock_t lock;
 	dm_cblock_t cache_size;
 	sector_t cache_block_size;
 
@@ -807,13 +807,7 @@ struct smq_policy {
 	/*
 	 * Keeps track of time, incremented by the core.  We use this to
 	 * avoid attributing multiple hits within the same tick.
-	 *
-	 * Access to tick_protected should be done with the spin lock held.
-	 * It's copied to tick at the start of the map function (within the
-	 * mutex).
 	 */
-	spinlock_t tick_lock;
-	unsigned tick_protected;
 	unsigned tick;
 
 	/*
@@ -1296,46 +1290,20 @@ static void smq_destroy(struct dm_cache_policy *p)
 	kfree(mq);
 }
 
-static void copy_tick(struct smq_policy *mq)
-{
-	unsigned long flags, tick;
-
-	spin_lock_irqsave(&mq->tick_lock, flags);
-	tick = mq->tick_protected;
-	if (tick != mq->tick) {
-		update_sentinels(mq);
-		end_hotspot_period(mq);
-		end_cache_period(mq);
-		mq->tick = tick;
-	}
-	spin_unlock_irqrestore(&mq->tick_lock, flags);
-}
-
-static bool maybe_lock(struct smq_policy *mq, bool can_block)
-{
-	if (can_block) {
-		mutex_lock(&mq->lock);
-		return true;
-	} else
-		return mutex_trylock(&mq->lock);
-}
-
 static int smq_map(struct dm_cache_policy *p, dm_oblock_t oblock,
 		   bool can_block, bool can_migrate, bool fast_promote,
 		   struct bio *bio, struct policy_locker *locker,
 		   struct policy_result *result)
 {
 	int r;
+	unsigned long flags;
 	struct smq_policy *mq = to_smq_policy(p);
 
 	result->op = POLICY_MISS;
 
-	if (!maybe_lock(mq, can_block))
-		return -EWOULDBLOCK;
-
-	copy_tick(mq);
+	spin_lock_irqsave(&mq->lock, flags);
 	r = map(mq, bio, oblock, can_migrate, fast_promote, locker, result);
-	mutex_unlock(&mq->lock);
+	spin_unlock_irqrestore(&mq->lock, flags);
 
 	return r;
 }
@@ -1343,20 +1311,18 @@ static int smq_map(struct dm_cache_policy *p, dm_oblock_t oblock,
 static int smq_lookup(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock)
 {
 	int r;
+	unsigned long flags;
 	struct smq_policy *mq = to_smq_policy(p);
 	struct entry *e;
 
-	if (!mutex_trylock(&mq->lock))
-		return -EWOULDBLOCK;
-
+	spin_lock_irqsave(&mq->lock, flags);
 	e = h_lookup(&mq->table, oblock);
 	if (e) {
 		*cblock = infer_cblock(mq, e);
 		r = 0;
 	} else
 		r = -ENOENT;
-
-	mutex_unlock(&mq->lock);
+	spin_unlock_irqrestore(&mq->lock, flags);
 
 	return r;
 }
@@ -1375,20 +1341,22 @@ static void __smq_set_clear_dirty(struct smq_policy *mq, dm_oblock_t oblock, boo
 
 static void smq_set_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
 {
+	unsigned long flags;
 	struct smq_policy *mq = to_smq_policy(p);
 
-	mutex_lock(&mq->lock);
+	spin_lock_irqsave(&mq->lock, flags);
 	__smq_set_clear_dirty(mq, oblock, true);
-	mutex_unlock(&mq->lock);
+	spin_unlock_irqrestore(&mq->lock, flags);
 }
 
 static void smq_clear_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
 {
 	struct smq_policy *mq = to_smq_policy(p);
+	unsigned long flags;
 
-	mutex_lock(&mq->lock);
+	spin_lock_irqsave(&mq->lock, flags);
 	__smq_set_clear_dirty(mq, oblock, false);
-	mutex_unlock(&mq->lock);
+	spin_unlock_irqrestore(&mq->lock, flags);
 }
 
 static int smq_load_mapping(struct dm_cache_policy *p,
@@ -1433,14 +1401,14 @@ static int smq_walk_mappings(struct dm_cache_policy *p, policy_walk_fn fn,
 	struct smq_policy *mq = to_smq_policy(p);
 	int r = 0;
 
-	mutex_lock(&mq->lock);
-
+	/*
+	 * We don't need to lock here since this method is only called once
+	 * the IO has stopped.
+	 */
 	r = smq_save_hints(mq, &mq->clean, fn, context);
 	if (!r)
 		r = smq_save_hints(mq, &mq->dirty, fn, context);
 
-	mutex_unlock(&mq->lock);
-
 	return r;
 }
 
@@ -1458,10 +1426,11 @@ static void __remove_mapping(struct smq_policy *mq, dm_oblock_t oblock)
 static void smq_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock)
 {
 	struct smq_policy *mq = to_smq_policy(p);
+	unsigned long flags;
 
-	mutex_lock(&mq->lock);
+	spin_lock_irqsave(&mq->lock, flags);
 	__remove_mapping(mq, oblock);
-	mutex_unlock(&mq->lock);
+	spin_unlock_irqrestore(&mq->lock, flags);
 }
 
 static int __remove_cblock(struct smq_policy *mq, dm_cblock_t cblock)
@@ -1480,11 +1449,12 @@ static int __remove_cblock(struct smq_policy *mq, dm_cblock_t cblock)
 static int smq_remove_cblock(struct dm_cache_policy *p, dm_cblock_t cblock)
 {
 	int r;
+	unsigned long flags;
 	struct smq_policy *mq = to_smq_policy(p);
 
-	mutex_lock(&mq->lock);
+	spin_lock_irqsave(&mq->lock, flags);
 	r = __remove_cblock(mq, cblock);
-	mutex_unlock(&mq->lock);
+	spin_unlock_irqrestore(&mq->lock, flags);
 
 	return r;
 }
@@ -1537,11 +1507,12 @@ static int smq_writeback_work(struct dm_cache_policy *p, dm_oblock_t *oblock,
 			      dm_cblock_t *cblock, bool critical_only)
 {
 	int r;
+	unsigned long flags;
 	struct smq_policy *mq = to_smq_policy(p);
 
-	mutex_lock(&mq->lock);
+	spin_lock_irqsave(&mq->lock, flags);
 	r = __smq_writeback_work(mq, oblock, cblock, critical_only);
-	mutex_unlock(&mq->lock);
+	spin_unlock_irqrestore(&mq->lock, flags);
 
 	return r;
 }
@@ -1562,21 +1533,23 @@ static void __force_mapping(struct smq_policy *mq,
 static void smq_force_mapping(struct dm_cache_policy *p,
 			      dm_oblock_t current_oblock, dm_oblock_t new_oblock)
 {
+	unsigned long flags;
 	struct smq_policy *mq = to_smq_policy(p);
 
-	mutex_lock(&mq->lock);
+	spin_lock_irqsave(&mq->lock, flags);
 	__force_mapping(mq, current_oblock, new_oblock);
-	mutex_unlock(&mq->lock);
+	spin_unlock_irqrestore(&mq->lock, flags);
 }
 
 static dm_cblock_t smq_residency(struct dm_cache_policy *p)
 {
 	dm_cblock_t r;
+	unsigned long flags;
 	struct smq_policy *mq = to_smq_policy(p);
 
-	mutex_lock(&mq->lock);
+	spin_lock_irqsave(&mq->lock, flags);
 	r = to_cblock(mq->cache_alloc.nr_allocated);
-	mutex_unlock(&mq->lock);
+	spin_unlock_irqrestore(&mq->lock, flags);
 
 	return r;
 }
@@ -1586,15 +1559,12 @@ static void smq_tick(struct dm_cache_policy *p, bool can_block)
 	struct smq_policy *mq = to_smq_policy(p);
 	unsigned long flags;
 
-	spin_lock_irqsave(&mq->tick_lock, flags);
-	mq->tick_protected++;
-	spin_unlock_irqrestore(&mq->tick_lock, flags);
-
-	if (can_block) {
-		mutex_lock(&mq->lock);
-		copy_tick(mq);
-		mutex_unlock(&mq->lock);
-	}
+	spin_lock_irqsave(&mq->lock, flags);
+	mq->tick++;
+	update_sentinels(mq);
+	end_hotspot_period(mq);
+	end_cache_period(mq);
+	spin_unlock_irqrestore(&mq->lock, flags);
 }
 
 /* Init the policy plugin interface function pointers. */
@@ -1694,10 +1664,8 @@ static struct dm_cache_policy *smq_create(dm_cblock_t cache_size,
 	} else
 		mq->cache_hit_bits = NULL;
 
-	mq->tick_protected = 0;
 	mq->tick = 0;
-	mutex_init(&mq->lock);
-	spin_lock_init(&mq->tick_lock);
+	spin_lock_init(&mq->lock);
 
 	q_init(&mq->hotspot, &mq->es, NR_HOTSPOT_LEVELS);
 	mq->hotspot.nr_top_levels = 8;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 9d0672b58..dd90d1236 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -424,7 +424,6 @@ static void free_migration(struct dm_cache_migration *mg)
 		wake_up(&cache->migration_wait);
 
 	mempool_free(mg, cache->migration_pool);
-	wake_worker(cache);
 }
 
 static int prealloc_data_structs(struct cache *cache, struct prealloc *p)
@@ -919,14 +918,14 @@ static void defer_writethrough_bio(struct cache *cache, struct bio *bio)
 	wake_worker(cache);
 }
 
-static void writethrough_endio(struct bio *bio, int err)
+static void writethrough_endio(struct bio *bio)
 {
 	struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT);
 
 	dm_unhook_bio(&pb->hook_info, bio);
 
-	if (err) {
-		bio_endio(bio, err);
+	if (bio->bi_error) {
+		bio_endio(bio);
 		return;
 	}
 
@@ -1064,14 +1063,6 @@ static void dec_io_migrations(struct cache *cache)
 	atomic_dec(&cache->nr_io_migrations);
 }
 
-static void __cell_release(struct cache *cache, struct dm_bio_prison_cell *cell,
-			   bool holder, struct bio_list *bios)
-{
-	(holder ? dm_cell_release : dm_cell_release_no_holder)
-		(cache->prison, cell, bios);
-	free_prison_cell(cache, cell);
-}
-
 static bool discard_or_flush(struct bio *bio)
 {
 	return bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD);
@@ -1079,14 +1070,13 @@ static bool discard_or_flush(struct bio *bio)
 
 static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell)
 {
-	if (discard_or_flush(cell->holder))
+	if (discard_or_flush(cell->holder)) {
 		/*
-		 * We have to handle these bios
-		 * individually.
+		 * We have to handle these bios individually.
 		 */
-		__cell_release(cache, cell, true, &cache->deferred_bios);
-
-	else
+		dm_cell_release(cache->prison, cell, &cache->deferred_bios);
+		free_prison_cell(cache, cell);
+	} else
 		list_add_tail(&cell->user_list, &cache->deferred_cells);
 }
 
@@ -1113,7 +1103,7 @@ static void cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell, boo
 static void cell_error_with_code(struct cache *cache, struct dm_bio_prison_cell *cell, int err)
 {
 	dm_cell_error(cache->prison, cell, err);
-	dm_bio_prison_free_cell(cache->prison, cell);
+	free_prison_cell(cache, cell);
 }
 
 static void cell_requeue(struct cache *cache, struct dm_bio_prison_cell *cell)
@@ -1123,8 +1113,11 @@ static void cell_requeue(struct cache *cache, struct dm_bio_prison_cell *cell)
 
 static void free_io_migration(struct dm_cache_migration *mg)
 {
-	dec_io_migrations(mg->cache);
+	struct cache *cache = mg->cache;
+
+	dec_io_migrations(cache);
 	free_migration(mg);
+	wake_worker(cache);
 }
 
 static void migration_failure(struct dm_cache_migration *mg)
@@ -1231,7 +1224,7 @@ static void migration_success_post_commit(struct dm_cache_migration *mg)
 			 * The block was promoted via an overwrite, so it's dirty.
 			 */
 			set_dirty(cache, mg->new_oblock, mg->cblock);
-			bio_endio(mg->new_ocell->holder, 0);
+			bio_endio(mg->new_ocell->holder);
 			cell_defer(cache, mg->new_ocell, false);
 		}
 		free_io_migration(mg);
@@ -1284,7 +1277,7 @@ static void issue_copy(struct dm_cache_migration *mg)
 	}
 }
 
-static void overwrite_endio(struct bio *bio, int err)
+static void overwrite_endio(struct bio *bio)
 {
 	struct dm_cache_migration *mg = bio->bi_private;
 	struct cache *cache = mg->cache;
@@ -1294,7 +1287,7 @@ static void overwrite_endio(struct bio *bio, int err)
 
 	dm_unhook_bio(&pb->hook_info, bio);
 
-	if (err)
+	if (bio->bi_error)
 		mg->err = true;
 
 	mg->requeue_holder = false;
@@ -1351,16 +1344,18 @@ static void issue_discard(struct dm_cache_migration *mg)
 {
 	dm_dblock_t b, e;
 	struct bio *bio = mg->new_ocell->holder;
+	struct cache *cache = mg->cache;
 
-	calc_discard_block_range(mg->cache, bio, &b, &e);
+	calc_discard_block_range(cache, bio, &b, &e);
 	while (b != e) {
-		set_discard(mg->cache, b);
+		set_discard(cache, b);
 		b = to_dblock(from_dblock(b) + 1);
 	}
 
-	bio_endio(bio, 0);
-	cell_defer(mg->cache, mg->new_ocell, false);
+	bio_endio(bio);
+	cell_defer(cache, mg->new_ocell, false);
 	free_migration(mg);
+	wake_worker(cache);
 }
 
 static void issue_copy_or_discard(struct dm_cache_migration *mg)
@@ -1631,7 +1626,7 @@ static void process_discard_bio(struct cache *cache, struct prealloc *structs,
 
 	calc_discard_block_range(cache, bio, &b, &e);
 	if (b == e) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -2221,8 +2216,10 @@ static void requeue_deferred_bios(struct cache *cache)
 	bio_list_merge(&bios, &cache->deferred_bios);
 	bio_list_init(&cache->deferred_bios);
 
-	while ((bio = bio_list_pop(&bios)))
-		bio_endio(bio, DM_ENDIO_REQUEUE);
+	while ((bio = bio_list_pop(&bios))) {
+		bio->bi_error = DM_ENDIO_REQUEUE;
+		bio_endio(bio);
+	}
 }
 
 static int more_work(struct cache *cache)
@@ -3127,7 +3124,7 @@ static int cache_map(struct dm_target *ti, struct bio *bio)
 			 * This is a duplicate writethrough io that is no
 			 * longer needed because the block has been demoted.
 			 */
-			bio_endio(bio, 0);
+			bio_endio(bio);
 			// FIXME: remap everything as a miss
 			cell_defer(cache, cell, false);
 			r = DM_MAPIO_SUBMITTED;
@@ -3782,26 +3779,6 @@ static int cache_iterate_devices(struct dm_target *ti,
 	return r;
 }
 
-/*
- * We assume I/O is going to the origin (which is the volume
- * more likely to have restrictions e.g. by being striped).
- * (Looking up the exact location of the data would be expensive
- * and could always be out of date by the time the bio is submitted.)
- */
-static int cache_bvec_merge(struct dm_target *ti,
-			    struct bvec_merge_data *bvm,
-			    struct bio_vec *biovec, int max_size)
-{
-	struct cache *cache = ti->private;
-	struct request_queue *q = bdev_get_queue(cache->origin_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = cache->origin_dev->bdev;
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static void set_discard_limits(struct cache *cache, struct queue_limits *limits)
 {
 	/*
@@ -3845,7 +3822,6 @@ static struct target_type cache_target = {
 	.status = cache_status,
 	.message = cache_message,
 	.iterate_devices = cache_iterate_devices,
-	.merge = cache_bvec_merge,
 	.io_hints = cache_io_hints,
 };
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 0d28c5b9d..4b3b6f8af 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1077,7 +1077,8 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 	if (io->ctx.req)
 		crypt_free_req(cc, io->ctx.req, base_bio);
 
-	bio_endio(base_bio, error);
+	base_bio->bi_error = error;
+	bio_endio(base_bio);
 }
 
 /*
@@ -1097,14 +1098,12 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
  * The work is done per CPU global for all dm-crypt instances.
  * They should not depend on each other and do not block.
  */
-static void crypt_endio(struct bio *clone, int error)
+static void crypt_endio(struct bio *clone)
 {
 	struct dm_crypt_io *io = clone->bi_private;
 	struct crypt_config *cc = io->cc;
 	unsigned rw = bio_data_dir(clone);
-
-	if (unlikely(!bio_flagged(clone, BIO_UPTODATE) && !error))
-		error = -EIO;
+	int error;
 
 	/*
 	 * free the processed pages
@@ -1112,6 +1111,7 @@ static void crypt_endio(struct bio *clone, int error)
 	if (rw == WRITE)
 		crypt_free_buffer_pages(cc, clone);
 
+	error = clone->bi_error;
 	bio_put(clone);
 
 	if (rw == READ && !error) {
@@ -1812,11 +1812,13 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 	cc->iv_offset = tmpll;
 
-	if (dm_get_device(ti, argv[3], dm_table_get_mode(ti->table), &cc->dev)) {
+	ret = dm_get_device(ti, argv[3], dm_table_get_mode(ti->table), &cc->dev);
+	if (ret) {
 		ti->error = "Device lookup failed";
 		goto bad;
 	}
 
+	ret = -EINVAL;
 	if (sscanf(argv[4], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid device sector";
 		goto bad;
@@ -2036,21 +2038,6 @@ error:
 	return -EINVAL;
 }
 
-static int crypt_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		       struct bio_vec *biovec, int max_size)
-{
-	struct crypt_config *cc = ti->private;
-	struct request_queue *q = bdev_get_queue(cc->dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = cc->dev->bdev;
-	bvm->bi_sector = cc->start + dm_target_offset(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int crypt_iterate_devices(struct dm_target *ti,
 				 iterate_devices_callout_fn fn, void *data)
 {
@@ -2082,7 +2069,6 @@ static struct target_type crypt_target = {
 	.preresume = crypt_preresume,
 	.resume = crypt_resume,
 	.message = crypt_message,
-	.merge  = crypt_merge,
 	.iterate_devices = crypt_iterate_devices,
 	.io_hints = crypt_io_hints,
 };
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 57b6a1901..b34f6e272 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -129,6 +129,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	struct delay_c *dc;
 	unsigned long long tmpll;
 	char dummy;
+	int ret;
 
 	if (argc != 3 && argc != 6) {
 		ti->error = "requires exactly 3 or 6 arguments";
@@ -143,6 +144,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	dc->reads = dc->writes = 0;
 
+	ret = -EINVAL;
 	if (sscanf(argv[1], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid device sector";
 		goto bad;
@@ -154,12 +156,14 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
-	if (dm_get_device(ti, argv[0], dm_table_get_mode(ti->table),
-			  &dc->dev_read)) {
+	ret = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table),
+			    &dc->dev_read);
+	if (ret) {
 		ti->error = "Device lookup failed";
 		goto bad;
 	}
 
+	ret = -EINVAL;
 	dc->dev_write = NULL;
 	if (argc == 3)
 		goto out;
@@ -175,13 +179,15 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad_dev_read;
 	}
 
-	if (dm_get_device(ti, argv[3], dm_table_get_mode(ti->table),
-			  &dc->dev_write)) {
+	ret = dm_get_device(ti, argv[3], dm_table_get_mode(ti->table),
+			    &dc->dev_write);
+	if (ret) {
 		ti->error = "Write device lookup failed";
 		goto bad_dev_read;
 	}
 
 out:
+	ret = -EINVAL;
 	dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
 	if (!dc->kdelayd_wq) {
 		DMERR("Couldn't start kdelayd");
@@ -208,7 +214,7 @@ bad_dev_read:
 	dm_put_device(ti, dc->dev_read);
 bad:
 	kfree(dc);
-	return -EINVAL;
+	return ret;
 }
 
 static void delay_dtr(struct dm_target *ti)
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index ad913cd4a..0119ebfb3 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1673,20 +1673,6 @@ static int era_iterate_devices(struct dm_target *ti,
 	return fn(ti, era->origin_dev, 0, get_dev_size(era->origin_dev), data);
 }
 
-static int era_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		     struct bio_vec *biovec, int max_size)
-{
-	struct era *era = ti->private;
-	struct request_queue *q = bdev_get_queue(era->origin_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = era->origin_dev->bdev;
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static void era_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct era *era = ti->private;
@@ -1717,7 +1703,6 @@ static struct target_type era_target = {
 	.status = era_status,
 	.message = era_message,
 	.iterate_devices = era_iterate_devices,
-	.merge = era_merge,
 	.io_hints = era_io_hints
 };
 
diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c
index ebaa4f803..192bb8bee 100644
--- a/drivers/md/dm-exception-store.c
+++ b/drivers/md/dm-exception-store.c
@@ -203,7 +203,7 @@ int dm_exception_store_create(struct dm_target *ti, int argc, char **argv,
 		return -EINVAL;
 	}
 
-	tmp_store = kmalloc(sizeof(*tmp_store), GFP_KERNEL);
+	tmp_store = kzalloc(sizeof(*tmp_store), GFP_KERNEL);
 	if (!tmp_store) {
 		ti->error = "Exception store allocation failed";
 		return -ENOMEM;
@@ -215,7 +215,7 @@ int dm_exception_store_create(struct dm_target *ti, int argc, char **argv,
 	else if (persistent == 'N')
 		type = get_type("N");
 	else {
-		ti->error = "Persistent flag is not P or N";
+		ti->error = "Exception store type is not P or N";
 		r = -EINVAL;
 		goto bad_type;
 	}
@@ -233,7 +233,7 @@ int dm_exception_store_create(struct dm_target *ti, int argc, char **argv,
 	if (r)
 		goto bad;
 
-	r = type->ctr(tmp_store, 0, NULL);
+	r = type->ctr(tmp_store, (strlen(argv[0]) > 1 ? &argv[0][1] : NULL));
 	if (r) {
 		ti->error = "Exception store type constructor failed";
 		goto bad;
diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h
index 0b2536247..fae34e7a0 100644
--- a/drivers/md/dm-exception-store.h
+++ b/drivers/md/dm-exception-store.h
@@ -42,8 +42,7 @@ struct dm_exception_store_type {
 	const char *name;
 	struct module *module;
 
-	int (*ctr) (struct dm_exception_store *store,
-		    unsigned argc, char **argv);
+	int (*ctr) (struct dm_exception_store *store, char *options);
 
 	/*
 	 * Destroys this object when you've finished with it.
@@ -123,6 +122,8 @@ struct dm_exception_store {
 	unsigned chunk_shift;
 
 	void *context;
+
+	bool userspace_supports_overflow;
 };
 
 /*
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index b257e4687..645e8b4f8 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -183,6 +183,7 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	devname = dm_shift_arg(&as);
 
+	r = -EINVAL;
 	if (sscanf(dm_shift_arg(&as), "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid device sector";
 		goto bad;
@@ -211,7 +212,8 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (r)
 		goto bad;
 
-	if (dm_get_device(ti, devname, dm_table_get_mode(ti->table), &fc->dev)) {
+	r = dm_get_device(ti, devname, dm_table_get_mode(ti->table), &fc->dev);
+	if (r) {
 		ti->error = "Device lookup failed";
 		goto bad;
 	}
@@ -224,7 +226,7 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 bad:
 	kfree(fc);
-	return -EINVAL;
+	return r;
 }
 
 static void flakey_dtr(struct dm_target *ti)
@@ -296,7 +298,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 		 * Drop writes?
 		 */
 		if (test_bit(DROP_WRITES, &fc->flags)) {
-			bio_endio(bio, 0);
+			bio_endio(bio);
 			return DM_MAPIO_SUBMITTED;
 		}
 
@@ -387,21 +389,6 @@ static int flakey_ioctl(struct dm_target *ti, unsigned int cmd, unsigned long ar
 	return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
 }
 
-static int flakey_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			struct bio_vec *biovec, int max_size)
-{
-	struct flakey_c *fc = ti->private;
-	struct request_queue *q = bdev_get_queue(fc->dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = fc->dev->bdev;
-	bvm->bi_sector = flakey_map_sector(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
 {
 	struct flakey_c *fc = ti->private;
@@ -419,7 +406,6 @@ static struct target_type flakey_target = {
 	.end_io = flakey_end_io,
 	.status = flakey_status,
 	.ioctl	= flakey_ioctl,
-	.merge	= flakey_merge,
 	.iterate_devices = flakey_iterate_devices,
 };
 
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 74adcd2c9..6f8e83b2a 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -134,12 +134,13 @@ static void dec_count(struct io *io, unsigned int region, int error)
 		complete_io(io);
 }
 
-static void endio(struct bio *bio, int error)
+static void endio(struct bio *bio)
 {
 	struct io *io;
 	unsigned region;
+	int error;
 
-	if (error && bio_data_dir(bio) == READ)
+	if (bio->bi_error && bio_data_dir(bio) == READ)
 		zero_fill_bio(bio);
 
 	/*
@@ -147,6 +148,7 @@ static void endio(struct bio *bio, int error)
 	 */
 	retrieve_io_and_region_from_bio(bio, &io, &region);
 
+	error = bio->bi_error;
 	bio_put(bio);
 
 	dec_count(io, region, error);
@@ -314,7 +316,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 		if ((rw & REQ_DISCARD) || (rw & REQ_WRITE_SAME))
 			num_bvecs = 1;
 		else
-			num_bvecs = min_t(int, bio_get_nr_vecs(where->bdev),
+			num_bvecs = min_t(int, BIO_MAX_PAGES,
 					  dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
 
 		bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 720ceeb7f..80a439543 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1919,9 +1919,7 @@ int __init dm_interface_init(void)
 
 void dm_interface_exit(void)
 {
-	if (misc_deregister(&_dm_misc) < 0)
-		DMERR("misc_deregister failed for control device");
-
+	misc_deregister(&_dm_misc);
 	dm_hash_exit();
 }
 
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 53e848c10..436f5c9b6 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -30,6 +30,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	struct linear_c *lc;
 	unsigned long long tmp;
 	char dummy;
+	int ret;
 
 	if (argc != 2) {
 		ti->error = "Invalid argument count";
@@ -42,13 +43,15 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		return -ENOMEM;
 	}
 
+	ret = -EINVAL;
 	if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1) {
 		ti->error = "dm-linear: Invalid device sector";
 		goto bad;
 	}
 	lc->start = tmp;
 
-	if (dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &lc->dev)) {
+	ret = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &lc->dev);
+	if (ret) {
 		ti->error = "dm-linear: Device lookup failed";
 		goto bad;
 	}
@@ -61,7 +64,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
       bad:
 	kfree(lc);
-	return -EINVAL;
+	return ret;
 }
 
 static void linear_dtr(struct dm_target *ti)
@@ -130,21 +133,6 @@ static int linear_ioctl(struct dm_target *ti, unsigned int cmd,
 	return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
 }
 
-static int linear_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			struct bio_vec *biovec, int max_size)
-{
-	struct linear_c *lc = ti->private;
-	struct request_queue *q = bdev_get_queue(lc->dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = lc->dev->bdev;
-	bvm->bi_sector = linear_map_sector(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int linear_iterate_devices(struct dm_target *ti,
 				  iterate_devices_callout_fn fn, void *data)
 {
@@ -162,7 +150,6 @@ static struct target_type linear_target = {
 	.map    = linear_map,
 	.status = linear_status,
 	.ioctl  = linear_ioctl,
-	.merge  = linear_merge,
 	.iterate_devices = linear_iterate_devices,
 };
 
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index ad1b049ae..b2912dbac 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -146,16 +146,16 @@ static void put_io_block(struct log_writes_c *lc)
 	}
 }
 
-static void log_end_io(struct bio *bio, int err)
+static void log_end_io(struct bio *bio)
 {
 	struct log_writes_c *lc = bio->bi_private;
 	struct bio_vec *bvec;
 	int i;
 
-	if (err) {
+	if (bio->bi_error) {
 		unsigned long flags;
 
-		DMERR("Error writing log block, error=%d", err);
+		DMERR("Error writing log block, error=%d", bio->bi_error);
 		spin_lock_irqsave(&lc->blocks_lock, flags);
 		lc->logging_enabled = false;
 		spin_unlock_irqrestore(&lc->blocks_lock, flags);
@@ -205,7 +205,6 @@ static int write_metadata(struct log_writes_c *lc, void *entry,
 	bio->bi_bdev = lc->logdev->bdev;
 	bio->bi_end_io = log_end_io;
 	bio->bi_private = lc;
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
 
 	page = alloc_page(GFP_KERNEL);
 	if (!page) {
@@ -270,7 +269,6 @@ static int log_one_block(struct log_writes_c *lc,
 	bio->bi_bdev = lc->logdev->bdev;
 	bio->bi_end_io = log_end_io;
 	bio->bi_private = lc;
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
 
 	for (i = 0; i < block->vec_cnt; i++) {
 		/*
@@ -292,7 +290,6 @@ static int log_one_block(struct log_writes_c *lc,
 			bio->bi_bdev = lc->logdev->bdev;
 			bio->bi_end_io = log_end_io;
 			bio->bi_private = lc;
-			set_bit(BIO_UPTODATE, &bio->bi_flags);
 
 			ret = bio_add_page(bio, block->vecs[i].bv_page,
 					   block->vecs[i].bv_len, 0);
@@ -420,6 +417,7 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	struct log_writes_c *lc;
 	struct dm_arg_set as;
 	const char *devname, *logdevname;
+	int ret;
 
 	as.argc = argc;
 	as.argv = argv;
@@ -443,18 +441,22 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	atomic_set(&lc->pending_blocks, 0);
 
 	devname = dm_shift_arg(&as);
-	if (dm_get_device(ti, devname, dm_table_get_mode(ti->table), &lc->dev)) {
+	ret = dm_get_device(ti, devname, dm_table_get_mode(ti->table), &lc->dev);
+	if (ret) {
 		ti->error = "Device lookup failed";
 		goto bad;
 	}
 
 	logdevname = dm_shift_arg(&as);
-	if (dm_get_device(ti, logdevname, dm_table_get_mode(ti->table), &lc->logdev)) {
+	ret = dm_get_device(ti, logdevname, dm_table_get_mode(ti->table),
+			    &lc->logdev);
+	if (ret) {
 		ti->error = "Log device lookup failed";
 		dm_put_device(ti, lc->dev);
 		goto bad;
 	}
 
+	ret = -EINVAL;
 	lc->log_kthread = kthread_run(log_writes_kthread, lc, "log-write");
 	if (!lc->log_kthread) {
 		ti->error = "Couldn't alloc kthread";
@@ -479,7 +481,7 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 bad:
 	kfree(lc);
-	return -EINVAL;
+	return ret;
 }
 
 static int log_mark(struct log_writes_c *lc, char *data)
@@ -606,7 +608,7 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
 		WARN_ON(flush_bio || fua_bio);
 		if (lc->device_supports_discard)
 			goto map_bio;
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return DM_MAPIO_SUBMITTED;
 	}
 
@@ -728,21 +730,6 @@ static int log_writes_ioctl(struct dm_target *ti, unsigned int cmd,
 	return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
 }
 
-static int log_writes_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			    struct bio_vec *biovec, int max_size)
-{
-	struct log_writes_c *lc = ti->private;
-	struct request_queue *q = bdev_get_queue(lc->dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = lc->dev->bdev;
-	bvm->bi_sector = dm_target_offset(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int log_writes_iterate_devices(struct dm_target *ti,
 				      iterate_devices_callout_fn fn,
 				      void *data)
@@ -796,7 +783,6 @@ static struct target_type log_writes_target = {
 	.end_io = normal_end_io,
 	.status = log_writes_status,
 	.ioctl	= log_writes_ioctl,
-	.merge	= log_writes_merge,
 	.message = log_writes_message,
 	.iterate_devices = log_writes_iterate_devices,
 	.io_hints = log_writes_io_hints,
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index eff7bdd77..5a67671a3 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -159,12 +159,9 @@ static struct priority_group *alloc_priority_group(void)
 static void free_pgpaths(struct list_head *pgpaths, struct dm_target *ti)
 {
 	struct pgpath *pgpath, *tmp;
-	struct multipath *m = ti->private;
 
 	list_for_each_entry_safe(pgpath, tmp, pgpaths, list) {
 		list_del(&pgpath->list);
-		if (m->hw_handler_name)
-			scsi_dh_detach(bdev_get_queue(pgpath->path.dev->bdev));
 		dm_put_device(ti, pgpath->path.dev);
 		free_pgpath(pgpath);
 	}
@@ -580,6 +577,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps
 		q = bdev_get_queue(p->path.dev->bdev);
 
 	if (m->retain_attached_hw_handler) {
+retain:
 		attached_handler_name = scsi_dh_attached_handler_name(q, GFP_KERNEL);
 		if (attached_handler_name) {
 			/*
@@ -599,20 +597,14 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps
 	}
 
 	if (m->hw_handler_name) {
-		/*
-		 * Increments scsi_dh reference, even when using an
-		 * already-attached handler.
-		 */
 		r = scsi_dh_attach(q, m->hw_handler_name);
 		if (r == -EBUSY) {
-			/*
-			 * Already attached to different hw_handler:
-			 * try to reattach with correct one.
-			 */
-			scsi_dh_detach(q);
-			r = scsi_dh_attach(q, m->hw_handler_name);
-		}
+			char b[BDEVNAME_SIZE];
 
+			printk(KERN_INFO "dm-mpath: retaining handler on device %s\n",
+				bdevname(p->path.dev->bdev, b));
+			goto retain;
+		}
 		if (r < 0) {
 			ti->error = "error attaching hardware handler";
 			dm_put_device(ti, p->path.dev);
@@ -624,7 +616,6 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps
 			if (r < 0) {
 				ti->error = "unable to set hardware "
 							"handler parameters";
-				scsi_dh_detach(q);
 				dm_put_device(ti, p->path.dev);
 				goto bad;
 			}
@@ -734,12 +725,6 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m)
 		return 0;
 
 	m->hw_handler_name = kstrdup(dm_shift_arg(as), GFP_KERNEL);
-	if (!try_then_request_module(scsi_dh_handler_exist(m->hw_handler_name),
-				     "scsi_dh_%s", m->hw_handler_name)) {
-		ti->error = "unknown hardware handler type";
-		ret = -EINVAL;
-		goto fail;
-	}
 
 	if (hw_argc > 1) {
 		char *p;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1257d4843..a0901214a 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1716,24 +1716,6 @@ static void raid_resume(struct dm_target *ti)
 	mddev_resume(&rs->md);
 }
 
-static int raid_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		      struct bio_vec *biovec, int max_size)
-{
-	struct raid_set *rs = ti->private;
-	struct md_personality *pers = rs->md.pers;
-
-	if (pers && pers->mergeable_bvec)
-		return min(max_size, pers->mergeable_bvec(&rs->md, bvm, biovec));
-
-	/*
-	 * In case we can't request the personality because
-	 * the raid set is not running yet
-	 *
-	 * -> return safe minimum
-	 */
-	return rs->md.chunk_sectors;
-}
-
 static struct target_type raid_target = {
 	.name = "raid",
 	.version = {1, 7, 0},
@@ -1748,7 +1730,6 @@ static struct target_type raid_target = {
 	.presuspend = raid_presuspend,
 	.postsuspend = raid_postsuspend,
 	.resume = raid_resume,
-	.merge = raid_merge,
 };
 
 static int __init dm_raid_init(void)
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index d83696bf4..f2a363a89 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -490,9 +490,11 @@ static void hold_bio(struct mirror_set *ms, struct bio *bio)
 		 * If device is suspended, complete the bio.
 		 */
 		if (dm_noflush_suspending(ms->ti))
-			bio_endio(bio, DM_ENDIO_REQUEUE);
+			bio->bi_error = DM_ENDIO_REQUEUE;
 		else
-			bio_endio(bio, -EIO);
+			bio->bi_error = -EIO;
+
+		bio_endio(bio);
 		return;
 	}
 
@@ -515,7 +517,7 @@ static void read_callback(unsigned long error, void *context)
 	bio_set_m(bio, NULL);
 
 	if (likely(!error)) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -531,7 +533,7 @@ static void read_callback(unsigned long error, void *context)
 
 	DMERR_LIMIT("Read failure on mirror device %s.  Failing I/O.",
 		    m->dev->name);
-	bio_endio(bio, -EIO);
+	bio_io_error(bio);
 }
 
 /* Asynchronous read. */
@@ -580,7 +582,7 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads)
 		if (likely(m))
 			read_async_bio(m, bio);
 		else
-			bio_endio(bio, -EIO);
+			bio_io_error(bio);
 	}
 }
 
@@ -598,7 +600,7 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads)
 
 static void write_callback(unsigned long error, void *context)
 {
-	unsigned i, ret = 0;
+	unsigned i;
 	struct bio *bio = (struct bio *) context;
 	struct mirror_set *ms;
 	int should_wake = 0;
@@ -614,7 +616,7 @@ static void write_callback(unsigned long error, void *context)
 	 * regions with the same code.
 	 */
 	if (likely(!error)) {
-		bio_endio(bio, ret);
+		bio_endio(bio);
 		return;
 	}
 
@@ -623,7 +625,8 @@ static void write_callback(unsigned long error, void *context)
 	 * degrade the array.
 	 */
 	if (bio->bi_rw & REQ_DISCARD) {
-		bio_endio(bio, -EOPNOTSUPP);
+		bio->bi_error = -EOPNOTSUPP;
+		bio_endio(bio);
 		return;
 	}
 
@@ -828,13 +831,12 @@ static void do_failures(struct mirror_set *ms, struct bio_list *failures)
 		 * be wrong if the failed leg returned after reboot and
 		 * got replicated back to the good legs.)
 		 */
-
 		if (unlikely(!get_valid_mirror(ms) || (keep_log(ms) && ms->log_failure)))
-			bio_endio(bio, -EIO);
+			bio_io_error(bio);
 		else if (errors_handled(ms) && !keep_log(ms))
 			hold_bio(ms, bio);
 		else
-			bio_endio(bio, 0);
+			bio_endio(bio);
 	}
 }
 
@@ -943,16 +945,18 @@ static int get_mirror(struct mirror_set *ms, struct dm_target *ti,
 {
 	unsigned long long offset;
 	char dummy;
+	int ret;
 
 	if (sscanf(argv[1], "%llu%c", &offset, &dummy) != 1) {
 		ti->error = "Invalid offset";
 		return -EINVAL;
 	}
 
-	if (dm_get_device(ti, argv[0], dm_table_get_mode(ti->table),
-			  &ms->mirror[mirror].dev)) {
+	ret = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table),
+			    &ms->mirror[mirror].dev);
+	if (ret) {
 		ti->error = "Device lookup failure";
-		return -ENXIO;
+		return ret;
 	}
 
 	ms->mirror[mirror].ms = ms;
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 808b8419b..117a05e40 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -7,6 +7,7 @@
 
 #include "dm-exception-store.h"
 
+#include <linux/ctype.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/vmalloc.h>
@@ -533,7 +534,7 @@ static int read_exceptions(struct pstore *ps,
 		chunk = area_location(ps, ps->current_area);
 
 		area = dm_bufio_read(client, chunk, &bp);
-		if (unlikely(IS_ERR(area))) {
+		if (IS_ERR(area)) {
 			r = PTR_ERR(area);
 			goto ret_destroy_bufio;
 		}
@@ -843,10 +844,10 @@ static void persistent_drop_snapshot(struct dm_exception_store *store)
 		DMWARN("write header failed");
 }
 
-static int persistent_ctr(struct dm_exception_store *store,
-			  unsigned argc, char **argv)
+static int persistent_ctr(struct dm_exception_store *store, char *options)
 {
 	struct pstore *ps;
+	int r;
 
 	/* allocate the pstore */
 	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
@@ -868,14 +869,32 @@ static int persistent_ctr(struct dm_exception_store *store,
 
 	ps->metadata_wq = alloc_workqueue("ksnaphd", WQ_MEM_RECLAIM, 0);
 	if (!ps->metadata_wq) {
-		kfree(ps);
 		DMERR("couldn't start header metadata update thread");
-		return -ENOMEM;
+		r = -ENOMEM;
+		goto err_workqueue;
+	}
+
+	if (options) {
+		char overflow = toupper(options[0]);
+		if (overflow == 'O')
+			store->userspace_supports_overflow = true;
+		else {
+			DMERR("Unsupported persistent store option: %s", options);
+			r = -EINVAL;
+			goto err_options;
+		}
 	}
 
 	store->context = ps;
 
 	return 0;
+
+err_options:
+	destroy_workqueue(ps->metadata_wq);
+err_workqueue:
+	kfree(ps);
+
+	return r;
 }
 
 static unsigned persistent_status(struct dm_exception_store *store,
@@ -888,7 +907,8 @@ static unsigned persistent_status(struct dm_exception_store *store,
 	case STATUSTYPE_INFO:
 		break;
 	case STATUSTYPE_TABLE:
-		DMEMIT(" P %llu", (unsigned long long)store->chunk_size);
+		DMEMIT(" %s %llu", store->userspace_supports_overflow ? "PO" : "P",
+		       (unsigned long long)store->chunk_size);
 	}
 
 	return sz;
diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c
index 1ce9a2586..9b7c8c804 100644
--- a/drivers/md/dm-snap-transient.c
+++ b/drivers/md/dm-snap-transient.c
@@ -70,8 +70,7 @@ static void transient_usage(struct dm_exception_store *store,
 	*metadata_sectors = 0;
 }
 
-static int transient_ctr(struct dm_exception_store *store,
-			 unsigned argc, char **argv)
+static int transient_ctr(struct dm_exception_store *store, char *options)
 {
 	struct transient_c *tc;
 
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 7c82d3ccc..c06b74e91 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -63,6 +63,13 @@ struct dm_snapshot {
 	 */
 	int valid;
 
+	/*
+	 * The snapshot overflowed because of a write to the snapshot device.
+	 * We don't have to invalidate the snapshot in this case, but we need
+	 * to prevent further writes.
+	 */
+	int snapshot_overflowed;
+
 	/* Origin writes don't trigger exceptions until this is set */
 	int active;
 
@@ -1091,7 +1098,7 @@ static void stop_merge(struct dm_snapshot *s)
 }
 
 /*
- * Construct a snapshot mapping: <origin_dev> <COW-dev> <p/n> <chunk-size>
+ * Construct a snapshot mapping: <origin_dev> <COW-dev> <p|po|n> <chunk-size>
  */
 static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
@@ -1152,6 +1159,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	s->ti = ti;
 	s->valid = 1;
+	s->snapshot_overflowed = 0;
 	s->active = 0;
 	atomic_set(&s->pending_exceptions_count, 0);
 	s->exception_start_sequence = 0;
@@ -1294,6 +1302,7 @@ static void __handover_exceptions(struct dm_snapshot *snap_src,
 
 	u.store_swap = snap_dest->store;
 	snap_dest->store = snap_src->store;
+	snap_dest->store->userspace_supports_overflow = u.store_swap->userspace_supports_overflow;
 	snap_src->store = u.store_swap;
 
 	snap_dest->store->snap = snap_dest;
@@ -1301,6 +1310,7 @@ static void __handover_exceptions(struct dm_snapshot *snap_src,
 
 	snap_dest->ti->max_io_len = snap_dest->store->chunk_size;
 	snap_dest->valid = snap_src->valid;
+	snap_dest->snapshot_overflowed = snap_src->snapshot_overflowed;
 
 	/*
 	 * Set source invalid to ensure it receives no further I/O.
@@ -1490,7 +1500,7 @@ out:
 		error_bios(snapshot_bios);
 	} else {
 		if (full_bio)
-			bio_endio(full_bio, 0);
+			bio_endio(full_bio);
 		flush_bios(snapshot_bios);
 	}
 
@@ -1580,11 +1590,11 @@ static void start_copy(struct dm_snap_pending_exception *pe)
 	dm_kcopyd_copy(s->kcopyd_client, &src, 1, &dest, 0, copy_callback, pe);
 }
 
-static void full_bio_end_io(struct bio *bio, int error)
+static void full_bio_end_io(struct bio *bio)
 {
 	void *callback_data = bio->bi_private;
 
-	dm_kcopyd_do_callback(callback_data, 0, error ? 1 : 0);
+	dm_kcopyd_do_callback(callback_data, 0, bio->bi_error ? 1 : 0);
 }
 
 static void start_full_bio(struct dm_snap_pending_exception *pe,
@@ -1691,7 +1701,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
 	 * to copy an exception */
 	down_write(&s->lock);
 
-	if (!s->valid) {
+	if (!s->valid || (unlikely(s->snapshot_overflowed) && bio_rw(bio) == WRITE)) {
 		r = -EIO;
 		goto out_unlock;
 	}
@@ -1715,7 +1725,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
 			pe = alloc_pending_exception(s);
 			down_write(&s->lock);
 
-			if (!s->valid) {
+			if (!s->valid || s->snapshot_overflowed) {
 				free_pending_exception(pe);
 				r = -EIO;
 				goto out_unlock;
@@ -1730,7 +1740,11 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
 
 			pe = __find_pending_exception(s, pe, chunk);
 			if (!pe) {
-				__invalidate_snapshot(s, -ENOMEM);
+				if (s->store->userspace_supports_overflow) {
+					s->snapshot_overflowed = 1;
+					DMERR("Snapshot overflowed: Unable to allocate exception.");
+				} else
+					__invalidate_snapshot(s, -ENOMEM);
 				r = -EIO;
 				goto out_unlock;
 			}
@@ -1990,6 +2004,8 @@ static void snapshot_status(struct dm_target *ti, status_type_t type,
 			DMEMIT("Invalid");
 		else if (snap->merge_failed)
 			DMEMIT("Merge failed");
+		else if (snap->snapshot_overflowed)
+			DMEMIT("Overflow");
 		else {
 			if (snap->store->type->usage) {
 				sector_t total_sectors, sectors_allocated,
@@ -2330,20 +2346,6 @@ static void origin_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-static int origin_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			struct bio_vec *biovec, int max_size)
-{
-	struct dm_origin *o = ti->private;
-	struct request_queue *q = bdev_get_queue(o->dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = o->dev->bdev;
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int origin_iterate_devices(struct dm_target *ti,
 				  iterate_devices_callout_fn fn, void *data)
 {
@@ -2362,13 +2364,12 @@ static struct target_type origin_target = {
 	.resume  = origin_resume,
 	.postsuspend = origin_postsuspend,
 	.status  = origin_status,
-	.merge	 = origin_merge,
 	.iterate_devices = origin_iterate_devices,
 };
 
 static struct target_type snapshot_target = {
 	.name    = "snapshot",
-	.version = {1, 13, 0},
+	.version = {1, 15, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,
@@ -2382,7 +2383,7 @@ static struct target_type snapshot_target = {
 
 static struct target_type merge_target = {
 	.name    = dm_snapshot_merge_target_name,
-	.version = {1, 3, 0},
+	.version = {1, 4, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index a672a1502..797ddb900 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -75,13 +75,15 @@ static int get_stripe(struct dm_target *ti, struct stripe_c *sc,
 {
 	unsigned long long start;
 	char dummy;
+	int ret;
 
 	if (sscanf(argv[1], "%llu%c", &start, &dummy) != 1)
 		return -EINVAL;
 
-	if (dm_get_device(ti, argv[0], dm_table_get_mode(ti->table),
-			  &sc->stripe[stripe].dev))
-		return -ENXIO;
+	ret = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table),
+			    &sc->stripe[stripe].dev);
+	if (ret)
+		return ret;
 
 	sc->stripe[stripe].physical_start = start;
 
@@ -273,7 +275,7 @@ static int stripe_map_range(struct stripe_c *sc, struct bio *bio,
 		return DM_MAPIO_REMAPPED;
 	} else {
 		/* The range doesn't map to the target stripe */
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return DM_MAPIO_SUBMITTED;
 	}
 }
@@ -412,26 +414,6 @@ static void stripe_io_hints(struct dm_target *ti,
 	blk_limits_io_opt(limits, chunk_size * sc->stripes);
 }
 
-static int stripe_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			struct bio_vec *biovec, int max_size)
-{
-	struct stripe_c *sc = ti->private;
-	sector_t bvm_sector = bvm->bi_sector;
-	uint32_t stripe;
-	struct request_queue *q;
-
-	stripe_map_sector(sc, bvm_sector, &stripe, &bvm_sector);
-
-	q = bdev_get_queue(sc->stripe[stripe].dev->bdev);
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = sc->stripe[stripe].dev->bdev;
-	bvm->bi_sector = sc->stripe[stripe].physical_start + bvm_sector;
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static struct target_type stripe_target = {
 	.name   = "striped",
 	.version = {1, 5, 1},
@@ -443,7 +425,6 @@ static struct target_type stripe_target = {
 	.status = stripe_status,
 	.iterate_devices = stripe_iterate_devices,
 	.io_hints = stripe_io_hints,
-	.merge  = stripe_merge,
 };
 
 int __init dm_stripe_init(void)
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 16ba55ad7..e76ed0037 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -440,14 +440,6 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 		       q->limits.alignment_offset,
 		       (unsigned long long) start << SECTOR_SHIFT);
 
-	/*
-	 * Check if merge fn is supported.
-	 * If not we'll force DM to use PAGE_SIZE or
-	 * smaller I/O, just to be safe.
-	 */
-	if (dm_queue_merge_is_compulsory(q) && !ti->type->merge)
-		blk_limits_max_hw_sectors(limits,
-					  (unsigned int) (PAGE_SIZE >> 9));
 	return 0;
 }
 
@@ -1388,14 +1380,6 @@ static int queue_supports_sg_merge(struct dm_target *ti, struct dm_dev *dev,
 	return q && !test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags);
 }
 
-static int queue_supports_sg_gaps(struct dm_target *ti, struct dm_dev *dev,
-				  sector_t start, sector_t len, void *data)
-{
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return q && !test_bit(QUEUE_FLAG_SG_GAPS, &q->queue_flags);
-}
-
 static bool dm_table_all_devices_attribute(struct dm_table *t,
 					   iterate_devices_callout_fn func)
 {
@@ -1516,11 +1500,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	else
 		queue_flag_set_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
 
-	if (dm_table_all_devices_attribute(t, queue_supports_sg_gaps))
-		queue_flag_clear_unlocked(QUEUE_FLAG_SG_GAPS, q);
-	else
-		queue_flag_set_unlocked(QUEUE_FLAG_SG_GAPS, q);
-
 	dm_table_set_integrity(t);
 
 	/*
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 493c38e08..3897b90bd 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -332,9 +332,6 @@ struct thin_c {
  *
  * Description:
  *    Asynchronously issue a discard request for the sectors in question.
- *    NOTE: this variant of blk-core's blkdev_issue_discard() is a stop-gap
- *    that is being kept local to DM thinp until the block changes to allow
- *    late bio splitting land upstream.
  */
 static int __blkdev_issue_discard_async(struct block_device *bdev, sector_t sector,
 					sector_t nr_sects, gfp_t gfp_mask, unsigned long flags,
@@ -342,91 +339,36 @@ static int __blkdev_issue_discard_async(struct block_device *bdev, sector_t sect
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	int type = REQ_WRITE | REQ_DISCARD;
-	unsigned int max_discard_sectors, granularity;
-	int alignment;
 	struct bio *bio;
-	int ret = 0;
-	struct blk_plug plug;
 
-	if (!q)
+	if (!q || !nr_sects)
 		return -ENXIO;
 
 	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
 
-	/* Zero-sector (unknown) and one-sector granularities are the same.  */
-	granularity = max(q->limits.discard_granularity >> 9, 1U);
-	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
-
-	/*
-	 * Ensure that max_discard_sectors is of the proper
-	 * granularity, so that requests stay aligned after a split.
-	 */
-	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
-	max_discard_sectors -= max_discard_sectors % granularity;
-	if (unlikely(!max_discard_sectors)) {
-		/* Avoid infinite loop below. Being cautious never hurts. */
-		return -EOPNOTSUPP;
-	}
-
 	if (flags & BLKDEV_DISCARD_SECURE) {
 		if (!blk_queue_secdiscard(q))
 			return -EOPNOTSUPP;
 		type |= REQ_SECURE;
 	}
 
-	blk_start_plug(&plug);
-	while (nr_sects) {
-		unsigned int req_sects;
-		sector_t end_sect, tmp;
-
-		/*
-		 * Required bio_put occurs in bio_endio thanks to bio_chain below
-		 */
-		bio = bio_alloc(gfp_mask, 1);
-		if (!bio) {
-			ret = -ENOMEM;
-			break;
-		}
-
-		req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
-
-		/*
-		 * If splitting a request, and the next starting sector would be
-		 * misaligned, stop the discard at the previous aligned sector.
-		 */
-		end_sect = sector + req_sects;
-		tmp = end_sect;
-		if (req_sects < nr_sects &&
-		    sector_div(tmp, granularity) != alignment) {
-			end_sect = end_sect - alignment;
-			sector_div(end_sect, granularity);
-			end_sect = end_sect * granularity + alignment;
-			req_sects = end_sect - sector;
-		}
-
-		bio_chain(bio, parent_bio);
-
-		bio->bi_iter.bi_sector = sector;
-		bio->bi_bdev = bdev;
+	/*
+	 * Required bio_put occurs in bio_endio thanks to bio_chain below
+	 */
+	bio = bio_alloc(gfp_mask, 1);
+	if (!bio)
+		return -ENOMEM;
 
-		bio->bi_iter.bi_size = req_sects << 9;
-		nr_sects -= req_sects;
-		sector = end_sect;
+	bio_chain(bio, parent_bio);
 
-		submit_bio(type, bio);
+	bio->bi_iter.bi_sector = sector;
+	bio->bi_bdev = bdev;
+	bio->bi_iter.bi_size = nr_sects << 9;
 
-		/*
-		 * We can loop for a long time in here, if someone does
-		 * full device discards (like mkfs). Be nice and allow
-		 * us to schedule out to avoid softlocking if preempt
-		 * is disabled.
-		 */
-		cond_resched();
-	}
-	blk_finish_plug(&plug);
+	submit_bio(type, bio);
 
-	return ret;
+	return 0;
 }
 
 static bool block_size_is_power_of_two(struct pool *pool)
@@ -615,8 +557,10 @@ static void error_bio_list(struct bio_list *bios, int error)
 {
 	struct bio *bio;
 
-	while ((bio = bio_list_pop(bios)))
-		bio_endio(bio, error);
+	while ((bio = bio_list_pop(bios))) {
+		bio->bi_error = error;
+		bio_endio(bio);
+	}
 }
 
 static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, int error)
@@ -870,14 +814,14 @@ static void copy_complete(int read_err, unsigned long write_err, void *context)
 	complete_mapping_preparation(m);
 }
 
-static void overwrite_endio(struct bio *bio, int err)
+static void overwrite_endio(struct bio *bio)
 {
 	struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
 	struct dm_thin_new_mapping *m = h->overwrite_mapping;
 
 	bio->bi_end_io = m->saved_bi_end_io;
 
-	m->err = err;
+	m->err = bio->bi_error;
 	complete_mapping_preparation(m);
 }
 
@@ -1002,7 +946,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 	 */
 	if (bio) {
 		inc_remap_and_issue_cell(tc, m->cell, m->data_block);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 	} else {
 		inc_all_io_entry(tc->pool, m->cell->holder);
 		remap_and_issue(tc, m->cell->holder, m->data_block);
@@ -1032,7 +976,7 @@ static void process_prepared_discard_fail(struct dm_thin_new_mapping *m)
 
 static void process_prepared_discard_success(struct dm_thin_new_mapping *m)
 {
-	bio_endio(m->bio, 0);
+	bio_endio(m->bio);
 	free_discard_mapping(m);
 }
 
@@ -1046,7 +990,7 @@ static void process_prepared_discard_no_passdown(struct dm_thin_new_mapping *m)
 		metadata_operation_failed(tc->pool, "dm_thin_remove_range", r);
 		bio_io_error(m->bio);
 	} else
-		bio_endio(m->bio, 0);
+		bio_endio(m->bio);
 
 	cell_defer_no_holder(tc, m->cell);
 	mempool_free(m, tc->pool->mapping_pool);
@@ -1117,7 +1061,8 @@ static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
 	 * Even if r is set, there could be sub discards in flight that we
 	 * need to wait for.
 	 */
-	bio_endio(m->bio, r);
+	m->bio->bi_error = r;
+	bio_endio(m->bio);
 	cell_defer_no_holder(tc, m->cell);
 	mempool_free(m, pool->mapping_pool);
 }
@@ -1493,9 +1438,10 @@ static void handle_unserviceable_bio(struct pool *pool, struct bio *bio)
 {
 	int error = should_error_unserviceable_bio(pool);
 
-	if (error)
-		bio_endio(bio, error);
-	else
+	if (error) {
+		bio->bi_error = error;
+		bio_endio(bio);
+	} else
 		retry_on_resume(bio);
 }
 
@@ -1539,9 +1485,8 @@ static void process_discard_cell_no_passdown(struct thin_c *tc,
 }
 
 /*
- * FIXME: DM local hack to defer parent bios's end_io until we
- * _know_ all chained sub range discard bios have completed.
- * Will go away once late bio splitting lands upstream!
+ * __bio_inc_remaining() is used to defer parent bios's end_io until
+ * we _know_ all chained sub range discard bios have completed.
  */
 static inline void __bio_inc_remaining(struct bio *bio)
 {
@@ -1631,7 +1576,7 @@ static void process_discard_cell_passdown(struct thin_c *tc, struct dm_bio_priso
 	 * will prevent completion until the sub range discards have
 	 * completed.
 	 */
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 static void process_discard_bio(struct thin_c *tc, struct bio *bio)
@@ -1645,7 +1590,7 @@ static void process_discard_bio(struct thin_c *tc, struct bio *bio)
 		/*
 		 * The discard covers less than a block.
 		 */
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -1790,7 +1735,7 @@ static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block
 	if (bio_data_dir(bio) == READ) {
 		zero_fill_bio(bio);
 		cell_defer_no_holder(tc, cell);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -1855,7 +1800,7 @@ static void process_cell(struct thin_c *tc, struct dm_bio_prison_cell *cell)
 
 			} else {
 				zero_fill_bio(bio);
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			}
 		} else
 			provision_block(tc, bio, block, cell);
@@ -1926,7 +1871,7 @@ static void __process_bio_read_only(struct thin_c *tc, struct bio *bio,
 		}
 
 		zero_fill_bio(bio);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		break;
 
 	default:
@@ -1951,7 +1896,7 @@ static void process_cell_read_only(struct thin_c *tc, struct dm_bio_prison_cell
 
 static void process_bio_success(struct thin_c *tc, struct bio *bio)
 {
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 static void process_bio_fail(struct thin_c *tc, struct bio *bio)
@@ -2600,7 +2545,8 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 	thin_hook_bio(tc, bio);
 
 	if (tc->requeue_mode) {
-		bio_endio(bio, DM_ENDIO_REQUEUE);
+		bio->bi_error = DM_ENDIO_REQUEUE;
+		bio_endio(bio);
 		return DM_MAPIO_SUBMITTED;
 	}
 
@@ -3875,20 +3821,6 @@ static int pool_iterate_devices(struct dm_target *ti,
 	return fn(ti, pt->data_dev, 0, ti->len, data);
 }
 
-static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		      struct bio_vec *biovec, int max_size)
-{
-	struct pool_c *pt = ti->private;
-	struct request_queue *q = bdev_get_queue(pt->data_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = pt->data_dev->bdev;
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct pool_c *pt = ti->private;
@@ -3965,7 +3897,6 @@ static struct target_type pool_target = {
 	.resume = pool_resume,
 	.message = pool_message,
 	.status = pool_status,
-	.merge = pool_merge,
 	.iterate_devices = pool_iterate_devices,
 	.io_hints = pool_io_hints,
 };
@@ -4292,21 +4223,6 @@ err:
 	DMEMIT("Error");
 }
 
-static int thin_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		      struct bio_vec *biovec, int max_size)
-{
-	struct thin_c *tc = ti->private;
-	struct request_queue *q = bdev_get_queue(tc->pool_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = tc->pool_dev->bdev;
-	bvm->bi_sector = dm_target_offset(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int thin_iterate_devices(struct dm_target *ti,
 				iterate_devices_callout_fn fn, void *data)
 {
@@ -4354,7 +4270,6 @@ static struct target_type thin_target = {
 	.presuspend = thin_presuspend,
 	.postsuspend = thin_postsuspend,
 	.status = thin_status,
-	.merge = thin_merge,
 	.iterate_devices = thin_iterate_devices,
 	.io_hints = thin_io_hints,
 };
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index bb9c6a00e..edc624bcc 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -26,8 +26,6 @@
 #define DM_VERITY_ENV_LENGTH		42
 #define DM_VERITY_ENV_VAR_NAME		"DM_VERITY_ERR_BLOCK_NR"
 
-#define DM_VERITY_IO_VEC_INLINE		16
-#define DM_VERITY_MEMPOOL_SIZE		4
 #define DM_VERITY_DEFAULT_PREFETCH_SIZE	262144
 
 #define DM_VERITY_MAX_LEVELS		63
@@ -76,8 +74,6 @@ struct dm_verity {
 	enum verity_mode mode;	/* mode for handling verification errors */
 	unsigned corrupted_errs;/* Number of errors for corrupted blocks */
 
-	mempool_t *vec_mempool;	/* mempool of bio vector */
-
 	struct workqueue_struct *verify_wq;
 
 	/* starting blocks for each tree level. 0 is the lowest level. */
@@ -271,7 +267,7 @@ static int verity_verify_level(struct dm_verity_io *io, sector_t block,
 	verity_hash_at_level(v, block, level, &hash_block, &offset);
 
 	data = dm_bufio_read(v->bufio, hash_block, &buf);
-	if (unlikely(IS_ERR(data)))
+	if (IS_ERR(data))
 		return PTR_ERR(data);
 
 	aux = dm_bufio_get_aux_data(buf);
@@ -458,8 +454,9 @@ static void verity_finish_io(struct dm_verity_io *io, int error)
 
 	bio->bi_end_io = io->orig_bi_end_io;
 	bio->bi_private = io->orig_bi_private;
+	bio->bi_error = error;
 
-	bio_endio(bio, error);
+	bio_endio(bio);
 }
 
 static void verity_work(struct work_struct *w)
@@ -469,12 +466,12 @@ static void verity_work(struct work_struct *w)
 	verity_finish_io(io, verity_verify_io(io));
 }
 
-static void verity_end_io(struct bio *bio, int error)
+static void verity_end_io(struct bio *bio)
 {
 	struct dm_verity_io *io = bio->bi_private;
 
-	if (error) {
-		verity_finish_io(io, error);
+	if (bio->bi_error) {
+		verity_finish_io(io, bio->bi_error);
 		return;
 	}
 
@@ -648,21 +645,6 @@ static int verity_ioctl(struct dm_target *ti, unsigned cmd,
 				     cmd, arg);
 }
 
-static int verity_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			struct bio_vec *biovec, int max_size)
-{
-	struct dm_verity *v = ti->private;
-	struct request_queue *q = bdev_get_queue(v->data_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = v->data_dev->bdev;
-	bvm->bi_sector = verity_map_sector(v, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int verity_iterate_devices(struct dm_target *ti,
 				  iterate_devices_callout_fn fn, void *data)
 {
@@ -691,9 +673,6 @@ static void verity_dtr(struct dm_target *ti)
 	if (v->verify_wq)
 		destroy_workqueue(v->verify_wq);
 
-	if (v->vec_mempool)
-		mempool_destroy(v->vec_mempool);
-
 	if (v->bufio)
 		dm_bufio_client_destroy(v->bufio);
 
@@ -962,14 +941,6 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	ti->per_bio_data_size = roundup(sizeof(struct dm_verity_io) + v->shash_descsize + v->digest_size * 2, __alignof__(struct dm_verity_io));
 
-	v->vec_mempool = mempool_create_kmalloc_pool(DM_VERITY_MEMPOOL_SIZE,
-					BIO_MAX_PAGES * sizeof(struct bio_vec));
-	if (!v->vec_mempool) {
-		ti->error = "Cannot allocate vector mempool";
-		r = -ENOMEM;
-		goto bad;
-	}
-
 	/* WQ_UNBOUND greatly improves performance when running on ramdisk */
 	v->verify_wq = alloc_workqueue("kverityd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus());
 	if (!v->verify_wq) {
@@ -995,7 +966,6 @@ static struct target_type verity_target = {
 	.map		= verity_map,
 	.status		= verity_status,
 	.ioctl		= verity_ioctl,
-	.merge		= verity_merge,
 	.iterate_devices = verity_iterate_devices,
 	.io_hints	= verity_io_hints,
 };
diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c
index b9a64bbce..766bc9300 100644
--- a/drivers/md/dm-zero.c
+++ b/drivers/md/dm-zero.c
@@ -47,7 +47,7 @@ static int zero_map(struct dm_target *ti, struct bio *bio)
 		break;
 	}
 
-	bio_endio(bio, 0);
+	bio_endio(bio);
 
 	/* accepted bio, don't make new request */
 	return DM_MAPIO_SUBMITTED;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3e32f4e31..1b5c6047e 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -124,9 +124,8 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
 #define DMF_FREEING 3
 #define DMF_DELETING 4
 #define DMF_NOFLUSH_SUSPENDING 5
-#define DMF_MERGE_IS_OPTIONAL 6
-#define DMF_DEFERRED_REMOVE 7
-#define DMF_SUSPENDED_INTERNALLY 8
+#define DMF_DEFERRED_REMOVE 6
+#define DMF_SUSPENDED_INTERNALLY 7
 
 /*
  * A dummy definition to make RCU happy.
@@ -944,7 +943,8 @@ static void dec_pending(struct dm_io *io, int error)
 		} else {
 			/* done with normal IO or empty flush */
 			trace_block_bio_complete(md->queue, bio, io_error);
-			bio_endio(bio, io_error);
+			bio->bi_error = io_error;
+			bio_endio(bio);
 		}
 	}
 }
@@ -957,17 +957,15 @@ static void disable_write_same(struct mapped_device *md)
 	limits->max_write_same_sectors = 0;
 }
 
-static void clone_endio(struct bio *bio, int error)
+static void clone_endio(struct bio *bio)
 {
+	int error = bio->bi_error;
 	int r = error;
 	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;
 
-	if (!bio_flagged(bio, BIO_UPTODATE) && !error)
-		error = -EIO;
-
 	if (endio) {
 		r = endio(tio->ti, bio, error);
 		if (r < 0 || r == DM_ENDIO_REQUEUE)
@@ -996,13 +994,14 @@ static void clone_endio(struct bio *bio, int error)
 /*
  * Partial completion handling for request-based dm
  */
-static void end_clone_bio(struct bio *clone, int error)
+static void end_clone_bio(struct bio *clone)
 {
 	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_iter.bi_size;
+	int error = clone->bi_error;
 
 	bio_put(clone);
 
@@ -1466,7 +1465,7 @@ static void __map_bio(struct dm_target_io *tio)
 		md = tio->io->md;
 		dec_pending(tio->io, r);
 		free_tio(md, tio);
-	} else if (r) {
+	} else if (r != DM_MAPIO_SUBMITTED) {
 		DMWARN("unimplemented target map return value: %d", r);
 		BUG();
 	}
@@ -1722,60 +1721,6 @@ static void __split_and_process_bio(struct mapped_device *md,
  * CRUD END
  *---------------------------------------------------------------*/
 
-static int dm_merge_bvec(struct request_queue *q,
-			 struct bvec_merge_data *bvm,
-			 struct bio_vec *biovec)
-{
-	struct mapped_device *md = q->queuedata;
-	struct dm_table *map = dm_get_live_table_fast(md);
-	struct dm_target *ti;
-	sector_t max_sectors;
-	int max_size = 0;
-
-	if (unlikely(!map))
-		goto out;
-
-	ti = dm_table_find_target(map, bvm->bi_sector);
-	if (!dm_target_is_valid(ti))
-		goto out;
-
-	/*
-	 * Find maximum amount of I/O that won't need splitting
-	 */
-	max_sectors = min(max_io_len(bvm->bi_sector, ti),
-			  (sector_t) BIO_MAX_SECTORS);
-	max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
-	if (max_size < 0)
-		max_size = 0;
-
-	/*
-	 * merge_bvec_fn() returns number of bytes
-	 * it can accept at this offset
-	 * max is precomputed maximal io size
-	 */
-	if (max_size && ti->type->merge)
-		max_size = ti->type->merge(ti, bvm, biovec, max_size);
-	/*
-	 * If the target doesn't support merge method and some of the devices
-	 * provided their merge_bvec method (we know this by looking at
-	 * queue_max_hw_sectors), then we can't allow bios with multiple vector
-	 * entries.  So always set max_size to 0, and the code below allows
-	 * just one page.
-	 */
-	else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9)
-		max_size = 0;
-
-out:
-	dm_put_live_table_fast(md);
-	/*
-	 * Always allow an entire first page
-	 */
-	if (max_size <= biovec->bv_len && !(bvm->bi_size >> SECTOR_SHIFT))
-		max_size = biovec->bv_len;
-
-	return max_size;
-}
-
 /*
  * The request function that just remaps the bio built up by
  * dm_merge_bvec.
@@ -1789,6 +1734,8 @@ static void dm_make_request(struct request_queue *q, struct bio *bio)
 
 	map = dm_get_live_table(md, &srcu_idx);
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	generic_start_io_acct(rw, bio_sectors(bio), &dm_disk(md)->part0);
 
 	/* if we're suspended, we have to queue this io for later */
@@ -2496,59 +2443,6 @@ static void __set_size(struct mapped_device *md, sector_t size)
 }
 
 /*
- * Return 1 if the queue has a compulsory merge_bvec_fn function.
- *
- * If this function returns 0, then the device is either a non-dm
- * device without a merge_bvec_fn, or it is a dm device that is
- * able to split any bios it receives that are too big.
- */
-int dm_queue_merge_is_compulsory(struct request_queue *q)
-{
-	struct mapped_device *dev_md;
-
-	if (!q->merge_bvec_fn)
-		return 0;
-
-	if (q->make_request_fn == dm_make_request) {
-		dev_md = q->queuedata;
-		if (test_bit(DMF_MERGE_IS_OPTIONAL, &dev_md->flags))
-			return 0;
-	}
-
-	return 1;
-}
-
-static int dm_device_merge_is_compulsory(struct dm_target *ti,
-					 struct dm_dev *dev, sector_t start,
-					 sector_t len, void *data)
-{
-	struct block_device *bdev = dev->bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	return dm_queue_merge_is_compulsory(q);
-}
-
-/*
- * Return 1 if it is acceptable to ignore merge_bvec_fn based
- * on the properties of the underlying devices.
- */
-static int dm_table_merge_is_optional(struct dm_table *table)
-{
-	unsigned i = 0;
-	struct dm_target *ti;
-
-	while (i < dm_table_get_num_targets(table)) {
-		ti = dm_table_get_target(table, i++);
-
-		if (ti->type->iterate_devices &&
-		    ti->type->iterate_devices(ti, dm_device_merge_is_compulsory, NULL))
-			return 0;
-	}
-
-	return 1;
-}
-
-/*
  * Returns old map, which caller must destroy.
  */
 static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
@@ -2557,7 +2451,6 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	struct dm_table *old_map;
 	struct request_queue *q = md->queue;
 	sector_t size;
-	int merge_is_optional;
 
 	size = dm_table_get_size(t);
 
@@ -2583,17 +2476,11 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 
 	__bind_mempools(md, t);
 
-	merge_is_optional = dm_table_merge_is_optional(t);
-
 	old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
 	rcu_assign_pointer(md->map, t);
 	md->immutable_target_type = dm_table_get_immutable_target_type(t);
 
 	dm_table_set_restrictions(t, q, limits);
-	if (merge_is_optional)
-		set_bit(DMF_MERGE_IS_OPTIONAL, &md->flags);
-	else
-		clear_bit(DMF_MERGE_IS_OPTIONAL, &md->flags);
 	if (old_map)
 		dm_sync_table(md);
 
@@ -2874,7 +2761,6 @@ int dm_setup_md_queue(struct mapped_device *md)
 	case DM_TYPE_BIO_BASED:
 		dm_init_old_md_queue(md);
 		blk_queue_make_request(md->queue, dm_make_request);
-		blk_queue_merge_bvec(md->queue, dm_merge_bvec);
 		break;
 	}
 
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 4e984993d..7edcf97df 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -78,8 +78,6 @@ bool dm_table_mq_request_based(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
 
-int dm_queue_merge_is_compulsory(struct request_queue *q);
-
 void dm_lock_md_type(struct mapped_device *md);
 void dm_unlock_md_type(struct mapped_device *md);
 void dm_set_md_type(struct mapped_device *md, unsigned type);
diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index 1277eb26b..4a8e15058 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -70,7 +70,7 @@
 #include <linux/seq_file.h>
 
 
-static void faulty_fail(struct bio *bio, int error)
+static void faulty_fail(struct bio *bio)
 {
 	struct bio *b = bio->bi_private;
 
@@ -181,7 +181,7 @@ static void make_request(struct mddev *mddev, struct bio *bio)
 			/* special case - don't decrement, don't generic_make_request,
 			 * just fail immediately
 			 */
-			bio_endio(bio, -EIO);
+			bio_io_error(bio);
 			return;
 		}
 
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index fa7d577f3..b7fe7e9fc 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -52,48 +52,6 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 	return conf->disks + lo;
 }
 
-/**
- *	linear_mergeable_bvec -- tell bio layer if two requests can be merged
- *	@q: request queue
- *	@bvm: properties of new bio
- *	@biovec: the request that could be merged to it.
- *
- *	Return amount of bytes we can take at this offset
- */
-static int linear_mergeable_bvec(struct mddev *mddev,
-				 struct bvec_merge_data *bvm,
-				 struct bio_vec *biovec)
-{
-	struct dev_info *dev0;
-	unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int maxbytes = biovec->bv_len;
-	struct request_queue *subq;
-
-	dev0 = which_dev(mddev, sector);
-	maxsectors = dev0->end_sector - sector;
-	subq = bdev_get_queue(dev0->rdev->bdev);
-	if (subq->merge_bvec_fn) {
-		bvm->bi_bdev = dev0->rdev->bdev;
-		bvm->bi_sector -= dev0->end_sector - dev0->rdev->sectors;
-		maxbytes = min(maxbytes, subq->merge_bvec_fn(subq, bvm,
-							     biovec));
-	}
-
-	if (maxsectors < bio_sectors)
-		maxsectors = 0;
-	else
-		maxsectors -= bio_sectors;
-
-	if (maxsectors <= (PAGE_SIZE >> 9 ) && bio_sectors == 0)
-		return maxbytes;
-
-	if (maxsectors > (maxbytes >> 9))
-		return maxbytes;
-	else
-		return maxsectors << 9;
-}
-
 static int linear_congested(struct mddev *mddev, int bits)
 {
 	struct linear_conf *conf;
@@ -297,7 +255,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 		if (unlikely((split->bi_rw & REQ_DISCARD) &&
 			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
 			/* Just ignore it */
-			bio_endio(split, 0);
+			bio_endio(split);
 		} else
 			generic_make_request(split);
 	} while (split != bio);
@@ -338,7 +296,6 @@ static struct md_personality linear_personality =
 	.size		= linear_size,
 	.quiesce	= linear_quiesce,
 	.congested	= linear_congested,
-	.mergeable_bvec	= linear_mergeable_bvec,
 };
 
 static int __init linear_init (void)
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 007219051..11e3bc9d2 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -45,6 +45,7 @@ struct resync_info {
 /* md_cluster_info flags */
 #define		MD_CLUSTER_WAITING_FOR_NEWDISK		1
 #define		MD_CLUSTER_SUSPEND_READ_BALANCING	2
+#define		MD_CLUSTER_BEGIN_JOIN_CLUSTER		3
 
 
 struct md_cluster_info {
@@ -52,7 +53,6 @@ struct md_cluster_info {
 	dlm_lockspace_t *lockspace;
 	int slot_number;
 	struct completion completion;
-	struct dlm_lock_resource *sb_lock;
 	struct mutex sb_mutex;
 	struct dlm_lock_resource *bitmap_lockres;
 	struct list_head suspend_list;
@@ -75,6 +75,7 @@ enum msg_type {
 	NEWDISK,
 	REMOVE,
 	RE_ADD,
+	BITMAP_NEEDS_SYNC,
 };
 
 struct cluster_msg {
@@ -99,7 +100,6 @@ static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
 {
 	int ret = 0;
 
-	init_completion(&res->completion);
 	ret = dlm_lock(res->ls, mode, &res->lksb,
 			res->flags, res->name, strlen(res->name),
 			0, sync_ast, res, res->bast);
@@ -124,6 +124,7 @@ static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
 	res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL);
 	if (!res)
 		return NULL;
+	init_completion(&res->completion);
 	res->ls = cinfo->lockspace;
 	res->mddev = mddev;
 	namelen = strlen(name);
@@ -165,11 +166,24 @@ out_err:
 
 static void lockres_free(struct dlm_lock_resource *res)
 {
+	int ret;
+
 	if (!res)
 		return;
 
-	init_completion(&res->completion);
-	dlm_unlock(res->ls, res->lksb.sb_lkid, 0, &res->lksb, res);
+	/* cancel a lock request or a conversion request that is blocked */
+	res->flags |= DLM_LKF_CANCEL;
+retry:
+	ret = dlm_unlock(res->ls, res->lksb.sb_lkid, 0, &res->lksb, res);
+	if (unlikely(ret != 0)) {
+		pr_info("%s: failed to unlock %s return %d\n", __func__, res->name, ret);
+
+		/* if a lock conversion is cancelled, then the lock is put
+		 * back to grant queue, need to ensure it is unlocked */
+		if (ret == -DLM_ECANCEL)
+			goto retry;
+	}
+	res->flags &= ~DLM_LKF_CANCEL;
 	wait_for_completion(&res->completion);
 
 	kfree(res->name);
@@ -177,18 +191,6 @@ static void lockres_free(struct dlm_lock_resource *res)
 	kfree(res);
 }
 
-static char *pretty_uuid(char *dest, char *src)
-{
-	int i, len = 0;
-
-	for (i = 0; i < 16; i++) {
-		if (i == 4 || i == 6 || i == 8 || i == 10)
-			len += sprintf(dest + len, "-");
-		len += sprintf(dest + len, "%02x", (__u8)src[i]);
-	}
-	return dest;
-}
-
 static void add_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres,
 		sector_t lo, sector_t hi)
 {
@@ -281,16 +283,11 @@ static void recover_prep(void *arg)
 	set_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state);
 }
 
-static void recover_slot(void *arg, struct dlm_slot *slot)
+static void __recover_slot(struct mddev *mddev, int slot)
 {
-	struct mddev *mddev = arg;
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 
-	pr_info("md-cluster: %s Node %d/%d down. My slot: %d. Initiating recovery.\n",
-			mddev->bitmap_info.cluster_name,
-			slot->nodeid, slot->slot,
-			cinfo->slot_number);
-	set_bit(slot->slot - 1, &cinfo->recovery_map);
+	set_bit(slot, &cinfo->recovery_map);
 	if (!cinfo->recovery_thread) {
 		cinfo->recovery_thread = md_register_thread(recover_bitmaps,
 				mddev, "recover");
@@ -302,6 +299,20 @@ static void recover_slot(void *arg, struct dlm_slot *slot)
 	md_wakeup_thread(cinfo->recovery_thread);
 }
 
+static void recover_slot(void *arg, struct dlm_slot *slot)
+{
+	struct mddev *mddev = arg;
+	struct md_cluster_info *cinfo = mddev->cluster_info;
+
+	pr_info("md-cluster: %s Node %d/%d down. My slot: %d. Initiating recovery.\n",
+			mddev->bitmap_info.cluster_name,
+			slot->nodeid, slot->slot,
+			cinfo->slot_number);
+	/* deduct one since dlm slot starts from one while the num of
+	 * cluster-md begins with 0 */
+	__recover_slot(mddev, slot->slot - 1);
+}
+
 static void recover_done(void *arg, struct dlm_slot *slots,
 		int num_slots, int our_slot,
 		uint32_t generation)
@@ -310,10 +321,17 @@ static void recover_done(void *arg, struct dlm_slot *slots,
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 
 	cinfo->slot_number = our_slot;
-	complete(&cinfo->completion);
+	/* completion is only need to be complete when node join cluster,
+	 * it doesn't need to run during another node's failure */
+	if (test_bit(MD_CLUSTER_BEGIN_JOIN_CLUSTER, &cinfo->state)) {
+		complete(&cinfo->completion);
+		clear_bit(MD_CLUSTER_BEGIN_JOIN_CLUSTER, &cinfo->state);
+	}
 	clear_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state);
 }
 
+/* the ops is called when node join the cluster, and do lock recovery
+ * if node failure occurs */
 static const struct dlm_lockspace_ops md_ls_ops = {
 	.recover_prep = recover_prep,
 	.recover_slot = recover_slot,
@@ -388,7 +406,7 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
 	int len;
 
 	len = snprintf(disk_uuid, 64, "DEVICE_UUID=");
-	pretty_uuid(disk_uuid + len, cmsg->uuid);
+	sprintf(disk_uuid + len, "%pU", cmsg->uuid);
 	snprintf(raid_slot, 16, "RAID_DISK=%d", cmsg->raid_slot);
 	pr_info("%s:%d Sending kobject change with %s and %s\n", __func__, __LINE__, disk_uuid, raid_slot);
 	init_completion(&cinfo->newdisk_completion);
@@ -457,6 +475,11 @@ static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 			__func__, __LINE__, msg->slot);
 		process_readd_disk(mddev, msg);
 		break;
+	case BITMAP_NEEDS_SYNC:
+		pr_info("%s: %d Received BITMAP_NEEDS_SYNC from %d\n",
+			__func__, __LINE__, msg->slot);
+		__recover_slot(mddev, msg->slot);
+		break;
 	default:
 		pr_warn("%s:%d Received unknown message from %d\n",
 			__func__, __LINE__, msg->slot);
@@ -472,6 +495,7 @@ static void recv_daemon(struct md_thread *thread)
 	struct dlm_lock_resource *ack_lockres = cinfo->ack_lockres;
 	struct dlm_lock_resource *message_lockres = cinfo->message_lockres;
 	struct cluster_msg msg;
+	int ret;
 
 	/*get CR on Message*/
 	if (dlm_lock_sync(message_lockres, DLM_LOCK_CR)) {
@@ -484,13 +508,21 @@ static void recv_daemon(struct md_thread *thread)
 	process_recvd_msg(thread->mddev, &msg);
 
 	/*release CR on ack_lockres*/
-	dlm_unlock_sync(ack_lockres);
-	/*up-convert to EX on message_lockres*/
-	dlm_lock_sync(message_lockres, DLM_LOCK_EX);
+	ret = dlm_unlock_sync(ack_lockres);
+	if (unlikely(ret != 0))
+		pr_info("unlock ack failed return %d\n", ret);
+	/*up-convert to PR on message_lockres*/
+	ret = dlm_lock_sync(message_lockres, DLM_LOCK_PR);
+	if (unlikely(ret != 0))
+		pr_info("lock PR on msg failed return %d\n", ret);
 	/*get CR on ack_lockres again*/
-	dlm_lock_sync(ack_lockres, DLM_LOCK_CR);
+	ret = dlm_lock_sync(ack_lockres, DLM_LOCK_CR);
+	if (unlikely(ret != 0))
+		pr_info("lock CR on ack failed return %d\n", ret);
 	/*release CR on message_lockres*/
-	dlm_unlock_sync(message_lockres);
+	ret = dlm_unlock_sync(message_lockres);
+	if (unlikely(ret != 0))
+		pr_info("unlock msg failed return %d\n", ret);
 }
 
 /* lock_comm()
@@ -519,7 +551,7 @@ static void unlock_comm(struct md_cluster_info *cinfo)
  * The function:
  * 1. Grabs the message lockresource in EX mode
  * 2. Copies the message to the message LVB
- * 3. Downconverts message lockresource to CR
+ * 3. Downconverts message lockresource to CW
  * 4. Upconverts ack lock resource from CR to EX. This forces the BAST on other nodes
  *    and the other nodes read the message. The thread will wait here until all other
  *    nodes have released ack lock resource.
@@ -540,12 +572,12 @@ static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
 
 	memcpy(cinfo->message_lockres->lksb.sb_lvbptr, (void *)cmsg,
 			sizeof(struct cluster_msg));
-	/*down-convert EX to CR on Message*/
-	error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_CR);
+	/*down-convert EX to CW on Message*/
+	error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_CW);
 	if (error) {
-		pr_err("md-cluster: failed to convert EX to CR on MESSAGE(%d)\n",
+		pr_err("md-cluster: failed to convert EX to CW on MESSAGE(%d)\n",
 				error);
-		goto failed_message;
+		goto failed_ack;
 	}
 
 	/*up-convert CR to EX on Ack*/
@@ -565,7 +597,13 @@ static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
 	}
 
 failed_ack:
-	dlm_unlock_sync(cinfo->message_lockres);
+	error = dlm_unlock_sync(cinfo->message_lockres);
+	if (unlikely(error != 0)) {
+		pr_err("md-cluster: failed convert to NL on MESSAGE(%d)\n",
+			error);
+		/* in case the message can't be released due to some reason */
+		goto failed_ack;
+	}
 failed_message:
 	return error;
 }
@@ -587,6 +625,7 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots)
 	struct dlm_lock_resource *bm_lockres;
 	struct suspend_info *s;
 	char str[64];
+	sector_t lo, hi;
 
 
 	for (i = 0; i < total_slots; i++) {
@@ -617,9 +656,24 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots)
 			lockres_free(bm_lockres);
 			continue;
 		}
-		if (ret)
+		if (ret) {
+			lockres_free(bm_lockres);
 			goto out;
-		/* TODO: Read the disk bitmap sb and check if it needs recovery */
+		}
+
+		/* Read the disk bitmap sb and check if it needs recovery */
+		ret = bitmap_copy_from_slot(mddev, i, &lo, &hi, false);
+		if (ret) {
+			pr_warn("md-cluster: Could not gather bitmaps from slot %d", i);
+			lockres_free(bm_lockres);
+			continue;
+		}
+		if ((hi > 0) && (lo < mddev->recovery_cp)) {
+			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			mddev->recovery_cp = lo;
+			md_check_recovery(mddev);
+		}
+
 		dlm_unlock_sync(bm_lockres);
 		lockres_free(bm_lockres);
 	}
@@ -633,20 +687,20 @@ static int join(struct mddev *mddev, int nodes)
 	int ret, ops_rv;
 	char str[64];
 
-	if (!try_module_get(THIS_MODULE))
-		return -ENOENT;
-
 	cinfo = kzalloc(sizeof(struct md_cluster_info), GFP_KERNEL);
 	if (!cinfo)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&cinfo->suspend_list);
+	spin_lock_init(&cinfo->suspend_lock);
 	init_completion(&cinfo->completion);
+	set_bit(MD_CLUSTER_BEGIN_JOIN_CLUSTER, &cinfo->state);
 
 	mutex_init(&cinfo->sb_mutex);
 	mddev->cluster_info = cinfo;
 
 	memset(str, 0, 64);
-	pretty_uuid(str, mddev->uuid);
+	sprintf(str, "%pU", mddev->uuid);
 	ret = dlm_new_lockspace(str, mddev->bitmap_info.cluster_name,
 				DLM_LSFL_FS, LVB_SIZE,
 				&md_ls_ops, mddev, &ops_rv, &cinfo->lockspace);
@@ -659,12 +713,6 @@ static int join(struct mddev *mddev, int nodes)
 		ret = -ERANGE;
 		goto err;
 	}
-	cinfo->sb_lock = lockres_init(mddev, "cmd-super",
-					NULL, 0);
-	if (!cinfo->sb_lock) {
-		ret = -ENOMEM;
-		goto err;
-	}
 	/* Initiate the communication resources */
 	ret = -ENOMEM;
 	cinfo->recv_thread = md_register_thread(recv_daemon, mddev, "cluster_recv");
@@ -705,9 +753,6 @@ static int join(struct mddev *mddev, int nodes)
 		goto err;
 	}
 
-	INIT_LIST_HEAD(&cinfo->suspend_list);
-	spin_lock_init(&cinfo->suspend_lock);
-
 	ret = gather_all_resync_info(mddev, nodes);
 	if (ret)
 		goto err;
@@ -719,12 +764,10 @@ err:
 	lockres_free(cinfo->ack_lockres);
 	lockres_free(cinfo->no_new_dev_lockres);
 	lockres_free(cinfo->bitmap_lockres);
-	lockres_free(cinfo->sb_lock);
 	if (cinfo->lockspace)
 		dlm_release_lockspace(cinfo->lockspace, 2);
 	mddev->cluster_info = NULL;
 	kfree(cinfo);
-	module_put(THIS_MODULE);
 	return ret;
 }
 
@@ -740,7 +783,6 @@ static int leave(struct mddev *mddev)
 	lockres_free(cinfo->token_lockres);
 	lockres_free(cinfo->ack_lockres);
 	lockres_free(cinfo->no_new_dev_lockres);
-	lockres_free(cinfo->sb_lock);
 	lockres_free(cinfo->bitmap_lockres);
 	dlm_release_lockspace(cinfo->lockspace, 2);
 	return 0;
@@ -817,8 +859,17 @@ static int resync_start(struct mddev *mddev, sector_t lo, sector_t hi)
 
 static void resync_finish(struct mddev *mddev)
 {
+	struct md_cluster_info *cinfo = mddev->cluster_info;
+	struct cluster_msg cmsg;
+	int slot = cinfo->slot_number - 1;
+
 	pr_info("%s:%d\n", __func__, __LINE__);
 	resync_send(mddev, RESYNCING, 0, 0);
+	if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+		cmsg.type = cpu_to_le32(BITMAP_NEEDS_SYNC);
+		cmsg.slot = cpu_to_le32(slot);
+		sendmsg(cinfo, &cmsg);
+	}
 }
 
 static int area_resyncing(struct mddev *mddev, int direction,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index e25f00f01..3fe3d04a9 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -257,13 +257,17 @@ static void md_make_request(struct request_queue *q, struct bio *bio)
 	unsigned int sectors;
 	int cpu;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (mddev == NULL || mddev->pers == NULL
 	    || !mddev->ready) {
 		bio_io_error(bio);
 		return;
 	}
 	if (mddev->ro == 1 && unlikely(rw == WRITE)) {
-		bio_endio(bio, bio_sectors(bio) == 0 ? 0 : -EROFS);
+		if (bio_sectors(bio) != 0)
+			bio->bi_error = -EROFS;
+		bio_endio(bio);
 		return;
 	}
 	smp_rmb(); /* Ensure implications of  'active' are visible */
@@ -350,34 +354,11 @@ static int md_congested(void *data, int bits)
 	return mddev_congested(mddev, bits);
 }
 
-static int md_mergeable_bvec(struct request_queue *q,
-			     struct bvec_merge_data *bvm,
-			     struct bio_vec *biovec)
-{
-	struct mddev *mddev = q->queuedata;
-	int ret;
-	rcu_read_lock();
-	if (mddev->suspended) {
-		/* Must always allow one vec */
-		if (bvm->bi_size == 0)
-			ret = biovec->bv_len;
-		else
-			ret = 0;
-	} else {
-		struct md_personality *pers = mddev->pers;
-		if (pers && pers->mergeable_bvec)
-			ret = pers->mergeable_bvec(mddev, bvm, biovec);
-		else
-			ret = biovec->bv_len;
-	}
-	rcu_read_unlock();
-	return ret;
-}
 /*
  * Generic flush handling for md
  */
 
-static void md_end_flush(struct bio *bio, int err)
+static void md_end_flush(struct bio *bio)
 {
 	struct md_rdev *rdev = bio->bi_private;
 	struct mddev *mddev = rdev->mddev;
@@ -433,7 +414,7 @@ static void md_submit_flush_data(struct work_struct *ws)
 
 	if (bio->bi_iter.bi_size == 0)
 		/* an empty barrier - all done */
-		bio_endio(bio, 0);
+		bio_endio(bio);
 	else {
 		bio->bi_rw &= ~REQ_FLUSH;
 		mddev->pers->make_request(mddev, bio);
@@ -502,6 +483,8 @@ static void mddev_put(struct mddev *mddev)
 		bioset_free(bs);
 }
 
+static void md_safemode_timeout(unsigned long data);
+
 void mddev_init(struct mddev *mddev)
 {
 	mutex_init(&mddev->open_mutex);
@@ -509,7 +492,8 @@ void mddev_init(struct mddev *mddev)
 	mutex_init(&mddev->bitmap_info.mutex);
 	INIT_LIST_HEAD(&mddev->disks);
 	INIT_LIST_HEAD(&mddev->all_mddevs);
-	init_timer(&mddev->safemode_timer);
+	setup_timer(&mddev->safemode_timer, md_safemode_timeout,
+		    (unsigned long) mddev);
 	atomic_set(&mddev->active, 1);
 	atomic_set(&mddev->openers, 0);
 	atomic_set(&mddev->active_io, 0);
@@ -728,15 +712,13 @@ void md_rdev_clear(struct md_rdev *rdev)
 }
 EXPORT_SYMBOL_GPL(md_rdev_clear);
 
-static void super_written(struct bio *bio, int error)
+static void super_written(struct bio *bio)
 {
 	struct md_rdev *rdev = bio->bi_private;
 	struct mddev *mddev = rdev->mddev;
 
-	if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
-		printk("md: super_written gets error=%d, uptodate=%d\n",
-		       error, test_bit(BIO_UPTODATE, &bio->bi_flags));
-		WARN_ON(test_bit(BIO_UPTODATE, &bio->bi_flags));
+	if (bio->bi_error) {
+		printk("md: super_written gets error=%d\n", bio->bi_error);
 		md_error(mddev, rdev);
 	}
 
@@ -791,7 +773,7 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
 	bio_add_page(bio, page, size, 0);
 	submit_bio_wait(rw, bio);
 
-	ret = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	ret = !bio->bi_error;
 	bio_put(bio);
 	return ret;
 }
@@ -3276,8 +3258,6 @@ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale)
 	return 0;
 }
 
-static void md_safemode_timeout(unsigned long data);
-
 static ssize_t
 safe_delay_show(struct mddev *mddev, char *page)
 {
@@ -4210,6 +4190,8 @@ action_show(struct mddev *mddev, char *page)
 				type = "repair";
 		} else if (test_bit(MD_RECOVERY_RECOVER, &recovery))
 			type = "recover";
+		else if (mddev->reshape_position != MaxSector)
+			type = "reshape";
 	}
 	return sprintf(page, "%s\n", type);
 }
@@ -5186,7 +5168,6 @@ int md_run(struct mddev *mddev)
 	if (mddev->queue) {
 		mddev->queue->backing_dev_info.congested_data = mddev;
 		mddev->queue->backing_dev_info.congested_fn = md_congested;
-		blk_queue_merge_bvec(mddev->queue, md_mergeable_bvec);
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -5202,8 +5183,6 @@ int md_run(struct mddev *mddev)
 	atomic_set(&mddev->max_corr_read_errors,
 		   MD_DEFAULT_MAX_CORRECTED_READ_ERRORS);
 	mddev->safemode = 0;
-	mddev->safemode_timer.function = md_safemode_timeout;
-	mddev->safemode_timer.data = (unsigned long) mddev;
 	mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
 	mddev->in_sync = 1;
 	smp_wmb();
@@ -5216,6 +5195,11 @@ int md_run(struct mddev *mddev)
 			if (sysfs_link_rdev(mddev, rdev))
 				/* failure here is OK */;
 
+	if (mddev->degraded && !mddev->ro)
+		/* This ensures that recovering status is reported immediately
+		 * via sysfs - until a lack of spares is confirmed.
+		 */
+		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 
 	if (mddev->flags & MD_UPDATE_SB_FLAGS)
@@ -5315,7 +5299,6 @@ static void md_clean(struct mddev *mddev)
 	mddev->degraded = 0;
 	mddev->safemode = 0;
 	mddev->private = NULL;
-	mddev->merge_check_needed = 0;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
 	mddev->bitmap_info.default_space = 0;
@@ -5426,9 +5409,13 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 		 * which will now never happen */
 		wake_up_process(mddev->sync_thread->tsk);
 
+	if (mddev->external && test_bit(MD_CHANGE_PENDING, &mddev->flags))
+		return -EBUSY;
 	mddev_unlock(mddev);
 	wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING,
 					  &mddev->recovery));
+	wait_event(mddev->sb_wait,
+		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
 	mddev_lock_nointr(mddev);
 
 	mutex_lock(&mddev->open_mutex);
@@ -5514,7 +5501,6 @@ static int do_md_stop(struct mddev *mddev, int mode,
 
 		__md_stop_writes(mddev);
 		__md_stop(mddev);
-		mddev->queue->merge_bvec_fn = NULL;
 		mddev->queue->backing_dev_info.congested_fn = NULL;
 
 		/* tell userspace to handle 'inactive' */
@@ -5765,16 +5751,16 @@ static int get_bitmap_file(struct mddev *mddev, void __user * arg)
 
 	err = 0;
 	spin_lock(&mddev->lock);
-	/* bitmap disabled, zero the first byte and copy out */
-	if (!mddev->bitmap_info.file)
-		file->pathname[0] = '\0';
-	else if ((ptr = file_path(mddev->bitmap_info.file,
-			       file->pathname, sizeof(file->pathname))),
-		 IS_ERR(ptr))
-		err = PTR_ERR(ptr);
-	else
-		memmove(file->pathname, ptr,
-			sizeof(file->pathname)-(ptr-file->pathname));
+	/* bitmap enabled */
+	if (mddev->bitmap_info.file) {
+		ptr = file_path(mddev->bitmap_info.file, file->pathname,
+				sizeof(file->pathname));
+		if (IS_ERR(ptr))
+			err = PTR_ERR(ptr);
+		else
+			memmove(file->pathname, ptr,
+				sizeof(file->pathname)-(ptr-file->pathname));
+	}
 	spin_unlock(&mddev->lock);
 
 	if (err == 0 &&
@@ -7093,7 +7079,7 @@ static void status_unused(struct seq_file *seq)
 	seq_printf(seq, "\n");
 }
 
-static void status_resync(struct seq_file *seq, struct mddev *mddev)
+static int status_resync(struct seq_file *seq, struct mddev *mddev)
 {
 	sector_t max_sectors, resync, res;
 	unsigned long dt, db;
@@ -7101,18 +7087,32 @@ static void status_resync(struct seq_file *seq, struct mddev *mddev)
 	int scale;
 	unsigned int per_milli;
 
-	if (mddev->curr_resync <= 3)
-		resync = 0;
-	else
-		resync = mddev->curr_resync
-			- atomic_read(&mddev->recovery_active);
-
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
 	    test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
 		max_sectors = mddev->resync_max_sectors;
 	else
 		max_sectors = mddev->dev_sectors;
 
+	resync = mddev->curr_resync;
+	if (resync <= 3) {
+		if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
+			/* Still cleaning up */
+			resync = max_sectors;
+	} else
+		resync -= atomic_read(&mddev->recovery_active);
+
+	if (resync == 0) {
+		if (mddev->recovery_cp < MaxSector) {
+			seq_printf(seq, "\tresync=PENDING");
+			return 1;
+		}
+		return 0;
+	}
+	if (resync < 3) {
+		seq_printf(seq, "\tresync=DELAYED");
+		return 1;
+	}
+
 	WARN_ON(max_sectors == 0);
 	/* Pick 'scale' such that (resync>>scale)*1000 will fit
 	 * in a sector_t, and (max_sectors>>scale) will fit in a
@@ -7177,6 +7177,7 @@ static void status_resync(struct seq_file *seq, struct mddev *mddev)
 		   ((unsigned long)rt % 60)/6);
 
 	seq_printf(seq, " speed=%ldK/sec", db/2/dt);
+	return 1;
 }
 
 static void *md_seq_start(struct seq_file *seq, loff_t *pos)
@@ -7322,13 +7323,8 @@ static int md_seq_show(struct seq_file *seq, void *v)
 			mddev->pers->status(seq, mddev);
 			seq_printf(seq, "\n      ");
 			if (mddev->pers->sync_request) {
-				if (mddev->curr_resync > 2) {
-					status_resync(seq, mddev);
+				if (status_resync(seq, mddev))
 					seq_printf(seq, "\n      ");
-				} else if (mddev->curr_resync >= 1)
-					seq_printf(seq, "\tresync=DELAYED\n      ");
-				else if (mddev->recovery_cp < MaxSector)
-					seq_printf(seq, "\tresync=PENDING\n      ");
 			}
 		} else
 			seq_printf(seq, "\n       ");
@@ -7411,15 +7407,19 @@ int unregister_md_personality(struct md_personality *p)
 }
 EXPORT_SYMBOL(unregister_md_personality);
 
-int register_md_cluster_operations(struct md_cluster_operations *ops, struct module *module)
+int register_md_cluster_operations(struct md_cluster_operations *ops,
+				   struct module *module)
 {
-	if (md_cluster_ops != NULL)
-		return -EALREADY;
+	int ret = 0;
 	spin_lock(&pers_lock);
-	md_cluster_ops = ops;
-	md_cluster_mod = module;
+	if (md_cluster_ops != NULL)
+		ret = -EALREADY;
+	else {
+		md_cluster_ops = ops;
+		md_cluster_mod = module;
+	}
 	spin_unlock(&pers_lock);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(register_md_cluster_operations);
 
@@ -7817,7 +7817,8 @@ void md_do_sync(struct md_thread *thread)
 		      > (max_sectors >> 4)) ||
 		     time_after_eq(jiffies, update_time + UPDATE_FREQUENCY) ||
 		     (j - mddev->curr_resync_completed)*2
-		     >= mddev->resync_max - mddev->curr_resync_completed
+		     >= mddev->resync_max - mddev->curr_resync_completed ||
+		     mddev->curr_resync_completed > mddev->resync_max
 			    )) {
 			/* time to update curr_resync_completed */
 			wait_event(mddev->recovery_wait,
@@ -7862,6 +7863,9 @@ void md_do_sync(struct md_thread *thread)
 			break;
 
 		j += sectors;
+		if (j > max_sectors)
+			/* when skipping, extra large numbers can be returned. */
+			j = max_sectors;
 		if (j > 2)
 			mddev->curr_resync = j;
 		if (mddev_is_clustered(mddev))
@@ -7930,12 +7934,15 @@ void md_do_sync(struct md_thread *thread)
 	blk_finish_plug(&plug);
 	wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
 
+	if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+	    !test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
+	    mddev->curr_resync > 2) {
+		mddev->curr_resync_completed = mddev->curr_resync;
+		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+	}
 	/* tell personality that we are finished */
 	mddev->pers->sync_request(mddev, max_sectors, &skipped);
 
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->resync_finish(mddev);
-
 	if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
 	    mddev->curr_resync > 2) {
 		if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
@@ -7969,6 +7976,9 @@ void md_do_sync(struct md_thread *thread)
 		}
 	}
  skip:
+	if (mddev_is_clustered(mddev))
+		md_cluster_ops->resync_finish(mddev);
+
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 
 	spin_lock(&mddev->lock);
@@ -7979,11 +7989,11 @@ void md_do_sync(struct md_thread *thread)
 		mddev->resync_max = MaxSector;
 	} else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 		mddev->resync_min = mddev->curr_resync_completed;
+	set_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	mddev->curr_resync = 0;
 	spin_unlock(&mddev->lock);
 
 	wake_up(&resync_wait);
-	set_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	return;
 }
@@ -8030,8 +8040,7 @@ static int remove_and_add_spares(struct mddev *mddev,
 		       !test_bit(Bitmap_sync, &rdev->flags)))
 			continue;
 
-		if (rdev->saved_raid_disk < 0)
-			rdev->recovery_offset = 0;
+		rdev->recovery_offset = 0;
 		if (mddev->pers->
 		    hot_add_disk(mddev, rdev) == 0) {
 			if (sysfs_link_rdev(mddev, rdev))
@@ -8152,7 +8161,9 @@ void md_check_recovery(struct mddev *mddev)
 			 */
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 			md_reap_sync_thread(mddev);
+			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
 			goto unlock;
 		}
 
@@ -8598,6 +8609,7 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 		/* Make sure they get written out promptly */
 		sysfs_notify_dirent_safe(rdev->sysfs_state);
 		set_bit(MD_CHANGE_CLEAN, &rdev->mddev->flags);
+		set_bit(MD_CHANGE_PENDING, &rdev->mddev->flags);
 		md_wakeup_thread(rdev->mddev->thread);
 	}
 	return rv;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 7da6e9c3c..ab339571e 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -134,10 +134,6 @@ enum flag_bits {
 	Bitmap_sync,		/* ..actually, not quite In_sync.  Need a
 				 * bitmap-based recovery to get fully in sync
 				 */
-	Unmerged,		/* device is being added to array and should
-				 * be considerred for bvec_merge_fn but not
-				 * yet for actual IO
-				 */
 	WriteMostly,		/* Avoid reading if at all possible */
 	AutoDetected,		/* added by auto-detect */
 	Blocked,		/* An error occurred but has not yet
@@ -374,10 +370,6 @@ struct mddev {
 	int				degraded;	/* whether md should consider
 							 * adding a spare
 							 */
-	int				merge_check_needed; /* at least one
-							     * member device
-							     * has a
-							     * merge_bvec_fn */
 
 	atomic_t			recovery_active; /* blocks scheduled, but not written */
 	wait_queue_head_t		recovery_wait;
@@ -532,10 +524,6 @@ struct md_personality
 	/* congested implements bdi.congested_fn().
 	 * Will not be called while array is 'suspended' */
 	int (*congested)(struct mddev *mddev, int bits);
-	/* mergeable_bvec is use to implement ->merge_bvec_fn */
-	int (*mergeable_bvec)(struct mddev *mddev,
-			      struct bvec_merge_data *bvm,
-			      struct bio_vec *biovec);
 };
 
 struct md_sysfs_entry {
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index ac3ede2bd..d132f06af 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -77,18 +77,18 @@ static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err)
 	struct bio *bio = mp_bh->master_bio;
 	struct mpconf *conf = mp_bh->mddev->private;
 
-	bio_endio(bio, err);
+	bio->bi_error = err;
+	bio_endio(bio);
 	mempool_free(mp_bh, conf->pool);
 }
 
-static void multipath_end_request(struct bio *bio, int error)
+static void multipath_end_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct multipath_bh *mp_bh = bio->bi_private;
 	struct mpconf *conf = mp_bh->mddev->private;
 	struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev;
 
-	if (uptodate)
+	if (!bio->bi_error)
 		multipath_end_bh_io(mp_bh, 0);
 	else if (!(bio->bi_rw & REQ_RAHEAD)) {
 		/*
@@ -101,7 +101,7 @@ static void multipath_end_request(struct bio *bio, int error)
 		       (unsigned long long)bio->bi_iter.bi_sector);
 		multipath_reschedule_retry(mp_bh);
 	} else
-		multipath_end_bh_io(mp_bh, error);
+		multipath_end_bh_io(mp_bh, bio->bi_error);
 	rdev_dec_pending(rdev, conf->mddev);
 }
 
@@ -123,7 +123,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
 
 	mp_bh->path = multipath_map(conf);
 	if (mp_bh->path < 0) {
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 		mempool_free(mp_bh, conf->pool);
 		return;
 	}
@@ -257,18 +257,6 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
 
-		/* as we don't honour merge_bvec_fn, we must never risk
-		 * violating it, so limit ->max_segments to one, lying
-		 * within a single page.
-		 * (Note: it is very unlikely that a device with
-		 * merge_bvec_fn will be involved in multipath.)
-		 */
-			if (q->merge_bvec_fn) {
-				blk_queue_max_segments(mddev->queue, 1);
-				blk_queue_segment_boundary(mddev->queue,
-							   PAGE_CACHE_SIZE - 1);
-			}
-
 			spin_lock_irq(&conf->device_lock);
 			mddev->degraded--;
 			rdev->raid_disk = path;
@@ -432,15 +420,6 @@ static int multipath_run (struct mddev *mddev)
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
 				  rdev->data_offset << 9);
 
-		/* as we don't honour merge_bvec_fn, we must never risk
-		 * violating it, not that we ever expect a device with
-		 * a merge_bvec_fn to be involved in multipath */
-		if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
-			blk_queue_max_segments(mddev->queue, 1);
-			blk_queue_segment_boundary(mddev->queue,
-						   PAGE_CACHE_SIZE - 1);
-		}
-
 		if (!test_bit(Faulty, &rdev->flags))
 			working_disks++;
 	}
@@ -491,8 +470,7 @@ static int multipath_run (struct mddev *mddev)
 	return 0;
 
 out_free_conf:
-	if (conf->pool)
-		mempool_destroy(conf->pool);
+	mempool_destroy(conf->pool);
 	kfree(conf->multipaths);
 	kfree(conf);
 	mddev->private = NULL;
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 4d6c9b689..88dbe7b97 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -454,7 +454,7 @@ int dm_bm_read_lock(struct dm_block_manager *bm, dm_block_t b,
 	int r;
 
 	p = dm_bufio_read(bm->bufio, b, (struct dm_buffer **) result);
-	if (unlikely(IS_ERR(p)))
+	if (IS_ERR(p))
 		return PTR_ERR(p);
 
 	aux = dm_bufio_get_aux_data(to_buffer(*result));
@@ -490,7 +490,7 @@ int dm_bm_write_lock(struct dm_block_manager *bm,
 		return -EPERM;
 
 	p = dm_bufio_read(bm->bufio, b, (struct dm_buffer **) result);
-	if (unlikely(IS_ERR(p)))
+	if (IS_ERR(p))
 		return PTR_ERR(p);
 
 	aux = dm_bufio_get_aux_data(to_buffer(*result));
@@ -523,7 +523,7 @@ int dm_bm_read_try_lock(struct dm_block_manager *bm,
 	int r;
 
 	p = dm_bufio_get(bm->bufio, b, (struct dm_buffer **) result);
-	if (unlikely(IS_ERR(p)))
+	if (IS_ERR(p))
 		return PTR_ERR(p);
 	if (unlikely(!p))
 		return -EWOULDBLOCK;
@@ -559,7 +559,7 @@ int dm_bm_write_lock_zero(struct dm_block_manager *bm,
 		return -EPERM;
 
 	p = dm_bufio_new(bm->bufio, b, (struct dm_buffer **) result);
-	if (unlikely(IS_ERR(p)))
+	if (IS_ERR(p))
 		return PTR_ERR(p);
 
 	memset(p, 0, dm_bm_block_size(bm));
diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c
index 4222f774c..2e4c4cb79 100644
--- a/drivers/md/persistent-data/dm-btree-remove.c
+++ b/drivers/md/persistent-data/dm-btree-remove.c
@@ -301,11 +301,16 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent,
 {
 	int s;
 	uint32_t max_entries = le32_to_cpu(left->header.max_entries);
-	unsigned target = (nr_left + nr_center + nr_right) / 3;
-	BUG_ON(target > max_entries);
+	unsigned total = nr_left + nr_center + nr_right;
+	unsigned target_right = total / 3;
+	unsigned remainder = (target_right * 3) != total;
+	unsigned target_left = target_right + remainder;
+
+	BUG_ON(target_left > max_entries);
+	BUG_ON(target_right > max_entries);
 
 	if (nr_left < nr_right) {
-		s = nr_left - target;
+		s = nr_left - target_left;
 
 		if (s < 0 && nr_center < -s) {
 			/* not enough in central node */
@@ -316,10 +321,10 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent,
 		} else
 			shift(left, center, s);
 
-		shift(center, right, target - nr_right);
+		shift(center, right, target_right - nr_right);
 
 	} else {
-		s = target - nr_right;
+		s = target_right - nr_right;
 		if (s > 0 && nr_center < s) {
 			/* not enough in central node */
 			shift(center, right, nr_center);
@@ -329,7 +334,7 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent,
 		} else
 			shift(center, right, s);
 
-		shift(left, center, nr_left - target);
+		shift(left, center, nr_left - target_left);
 	}
 
 	*key_ptr(parent, c->index) = center->keys[0];
@@ -409,29 +414,11 @@ static int rebalance3(struct shadow_spine *s, struct dm_btree_info *info,
 	return 0;
 }
 
-static int get_nr_entries(struct dm_transaction_manager *tm,
-			  dm_block_t b, uint32_t *result)
-{
-	int r;
-	struct dm_block *block;
-	struct btree_node *n;
-
-	r = dm_tm_read_lock(tm, b, &btree_node_validator, &block);
-	if (r)
-		return r;
-
-	n = dm_block_data(block);
-	*result = le32_to_cpu(n->header.nr_entries);
-
-	return dm_tm_unlock(tm, block);
-}
-
 static int rebalance_children(struct shadow_spine *s,
 			      struct dm_btree_info *info,
 			      struct dm_btree_value_type *vt, uint64_t key)
 {
 	int i, r, has_left_sibling, has_right_sibling;
-	uint32_t child_entries;
 	struct btree_node *n;
 
 	n = dm_block_data(shadow_current(s));
@@ -458,10 +445,6 @@ static int rebalance_children(struct shadow_spine *s,
 	if (i < 0)
 		return -ENODATA;
 
-	r = get_nr_entries(info->tm, value64(n, i), &child_entries);
-	if (r)
-		return r;
-
 	has_left_sibling = i > 0;
 	has_right_sibling = i < (le32_to_cpu(n->header.nr_entries) - 1);
 
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index c7726cebc..0e09aef43 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -420,8 +420,8 @@ EXPORT_SYMBOL_GPL(dm_btree_lookup);
  *
  * Where A* is a shadow of A.
  */
-static int btree_split_sibling(struct shadow_spine *s, dm_block_t root,
-			       unsigned parent_index, uint64_t key)
+static int btree_split_sibling(struct shadow_spine *s, unsigned parent_index,
+			       uint64_t key)
 {
 	int r;
 	size_t size;
@@ -523,7 +523,7 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
 
 	r = new_block(s->info, &right);
 	if (r < 0) {
-		/* FIXME: put left */
+		unlock_block(s->info, left);
 		return r;
 	}
 
@@ -625,7 +625,7 @@ static int btree_insert_raw(struct shadow_spine *s, dm_block_t root,
 			if (top)
 				r = btree_split_beneath(s, key);
 			else
-				r = btree_split_sibling(s, root, i, key);
+				r = btree_split_sibling(s, i, key);
 
 			if (r < 0)
 				return r;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 0875e5e7e..f8e5db0cb 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -203,9 +203,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		}
 		dev[j] = rdev1;
 
-		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
-			conf->has_merge_bvec = 1;
-
 		if (!smallest || (rdev1->sectors < smallest->sectors))
 			smallest = rdev1;
 		cnt++;
@@ -337,58 +334,6 @@ static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
 			     + sector_div(sector, zone->nb_dev)];
 }
 
-/**
- *	raid0_mergeable_bvec -- tell bio layer if two requests can be merged
- *	@mddev: the md device
- *	@bvm: properties of new bio
- *	@biovec: the request that could be merged to it.
- *
- *	Return amount of bytes we can accept at this offset
- */
-static int raid0_mergeable_bvec(struct mddev *mddev,
-				struct bvec_merge_data *bvm,
-				struct bio_vec *biovec)
-{
-	struct r0conf *conf = mddev->private;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	sector_t sector_offset = sector;
-	int max;
-	unsigned int chunk_sectors = mddev->chunk_sectors;
-	unsigned int bio_sectors = bvm->bi_size >> 9;
-	struct strip_zone *zone;
-	struct md_rdev *rdev;
-	struct request_queue *subq;
-
-	if (is_power_of_2(chunk_sectors))
-		max =  (chunk_sectors - ((sector & (chunk_sectors-1))
-						+ bio_sectors)) << 9;
-	else
-		max =  (chunk_sectors - (sector_div(sector, chunk_sectors)
-						+ bio_sectors)) << 9;
-	if (max < 0)
-		max = 0; /* bio_add cannot handle a negative return */
-	if (max <= biovec->bv_len && bio_sectors == 0)
-		return biovec->bv_len;
-	if (max < biovec->bv_len)
-		/* too small already, no need to check further */
-		return max;
-	if (!conf->has_merge_bvec)
-		return max;
-
-	/* May need to check subordinate device */
-	sector = sector_offset;
-	zone = find_zone(mddev->private, &sector_offset);
-	rdev = map_sector(mddev, zone, sector, &sector_offset);
-	subq = bdev_get_queue(rdev->bdev);
-	if (subq->merge_bvec_fn) {
-		bvm->bi_bdev = rdev->bdev;
-		bvm->bi_sector = sector_offset + zone->dev_start +
-			rdev->data_offset;
-		return min(max, subq->merge_bvec_fn(subq, bvm, biovec));
-	} else
-		return max;
-}
-
 static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks)
 {
 	sector_t array_sectors = 0;
@@ -546,7 +491,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 		if (unlikely((split->bi_rw & REQ_DISCARD) &&
 			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
 			/* Just ignore it */
-			bio_endio(split, 0);
+			bio_endio(split);
 		} else
 			generic_make_request(split);
 	} while (split != bio);
@@ -730,7 +675,6 @@ static struct md_personality raid0_personality=
 	.takeover	= raid0_takeover,
 	.quiesce	= raid0_quiesce,
 	.congested	= raid0_congested,
-	.mergeable_bvec	= raid0_mergeable_bvec,
 };
 
 static int __init raid0_init (void)
diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h
index 05539d9c9..7127a623f 100644
--- a/drivers/md/raid0.h
+++ b/drivers/md/raid0.h
@@ -12,8 +12,6 @@ struct r0conf {
 	struct md_rdev		**devlist; /* lists of rdevs, pointed to
 					    * by strip_zone->dev */
 	int			nr_strip_zones;
-	int			has_merge_bvec;	/* at least one member has
-						 * a merge_bvec_fn */
 };
 
 #endif
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 967a4ed73..d9d031ede 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -255,9 +255,10 @@ static void call_bio_endio(struct r1bio *r1_bio)
 		done = 1;
 
 	if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+		bio->bi_error = -EIO;
+
 	if (done) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		/*
 		 * Wake up any possible resync thread that waits for the device
 		 * to go idle.
@@ -312,9 +313,9 @@ static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio)
 	return mirror;
 }
 
-static void raid1_end_read_request(struct bio *bio, int error)
+static void raid1_end_read_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct r1bio *r1_bio = bio->bi_private;
 	int mirror;
 	struct r1conf *conf = r1_bio->mddev->private;
@@ -397,9 +398,8 @@ static void r1_bio_write_done(struct r1bio *r1_bio)
 	}
 }
 
-static void raid1_end_write_request(struct bio *bio, int error)
+static void raid1_end_write_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r1bio *r1_bio = bio->bi_private;
 	int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
 	struct r1conf *conf = r1_bio->mddev->private;
@@ -410,7 +410,7 @@ static void raid1_end_write_request(struct bio *bio, int error)
 	/*
 	 * 'one mirror IO has finished' event handler:
 	 */
-	if (!uptodate) {
+	if (bio->bi_error) {
 		set_bit(WriteErrorSeen,
 			&conf->mirrors[mirror].rdev->flags);
 		if (!test_and_set_bit(WantReplacement,
@@ -557,7 +557,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		rdev = rcu_dereference(conf->mirrors[disk].rdev);
 		if (r1_bio->bios[disk] == IO_BLOCKED
 		    || rdev == NULL
-		    || test_bit(Unmerged, &rdev->flags)
 		    || test_bit(Faulty, &rdev->flags))
 			continue;
 		if (!test_bit(In_sync, &rdev->flags) &&
@@ -708,38 +707,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	return best_disk;
 }
 
-static int raid1_mergeable_bvec(struct mddev *mddev,
-				struct bvec_merge_data *bvm,
-				struct bio_vec *biovec)
-{
-	struct r1conf *conf = mddev->private;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int max = biovec->bv_len;
-
-	if (mddev->merge_check_needed) {
-		int disk;
-		rcu_read_lock();
-		for (disk = 0; disk < conf->raid_disks * 2; disk++) {
-			struct md_rdev *rdev = rcu_dereference(
-				conf->mirrors[disk].rdev);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = sector +
-						rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-		}
-		rcu_read_unlock();
-	}
-	return max;
-
-}
-
 static int raid1_congested(struct mddev *mddev, int bits)
 {
 	struct r1conf *conf = mddev->private;
@@ -793,7 +760,7 @@ static void flush_pending_writes(struct r1conf *conf)
 			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			else
 				generic_make_request(bio);
 			bio = next;
@@ -914,8 +881,7 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 	}
 
 	if (bio && bio_data_dir(bio) == WRITE) {
-		if (bio->bi_iter.bi_sector >=
-		    conf->mddev->curr_resync_completed) {
+		if (bio->bi_iter.bi_sector >= conf->next_resync) {
 			if (conf->start_next_window == MaxSector)
 				conf->start_next_window =
 					conf->next_resync +
@@ -1068,7 +1034,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
-			bio_endio(bio, 0);
+			bio_endio(bio);
 		else
 			generic_make_request(bio);
 		bio = next;
@@ -1158,7 +1124,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	 * non-zero, then it is the number of not-completed requests.
 	 */
 	bio->bi_phys_segments = 0;
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+	bio_clear_flag(bio, BIO_SEG_VALID);
 
 	if (rw == READ) {
 		/*
@@ -1269,8 +1235,7 @@ read_again:
 			break;
 		}
 		r1_bio->bios[i] = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags)
-		    || test_bit(Unmerged, &rdev->flags)) {
+		if (!rdev || test_bit(Faulty, &rdev->flags)) {
 			if (i < conf->raid_disks)
 				set_bit(R1BIO_Degraded, &r1_bio->state);
 			continue;
@@ -1508,6 +1473,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 	 */
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_CHANGE_PENDING, &mddev->flags);
 	printk(KERN_ALERT
 	       "md/raid1:%s: Disk failure on %s, disabling device.\n"
 	       "md/raid1:%s: Operation continuing on %d devices.\n",
@@ -1549,7 +1515,7 @@ static void close_sync(struct r1conf *conf)
 	conf->r1buf_pool = NULL;
 
 	spin_lock_irq(&conf->resync_lock);
-	conf->next_resync = 0;
+	conf->next_resync = MaxSector - 2 * NEXT_NORMALIO_DISTANCE;
 	conf->start_next_window = MaxSector;
 	conf->current_window_requests +=
 		conf->next_window_requests;
@@ -1617,7 +1583,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	struct raid1_info *p;
 	int first = 0;
 	int last = conf->raid_disks - 1;
-	struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 	if (mddev->recovery_disabled == conf->recovery_disabled)
 		return -EBUSY;
@@ -1625,11 +1590,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
-	if (q->merge_bvec_fn) {
-		set_bit(Unmerged, &rdev->flags);
-		mddev->merge_check_needed = 1;
-	}
-
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors+mirror;
 		if (!p->rdev) {
@@ -1661,19 +1621,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			break;
 		}
 	}
-	if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
-		/* Some requests might not have seen this new
-		 * merge_bvec_fn.  We must wait for them to complete
-		 * before merging the device fully.
-		 * First we make sure any code which has tested
-		 * our function has submitted the request, then
-		 * we wait for all outstanding requests to complete.
-		 */
-		synchronize_sched();
-		freeze_array(conf, 0);
-		unfreeze_array(conf);
-		clear_bit(Unmerged, &rdev->flags);
-	}
 	md_integrity_add_rdev(rdev, mddev);
 	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
@@ -1737,7 +1684,7 @@ abort:
 	return err;
 }
 
-static void end_sync_read(struct bio *bio, int error)
+static void end_sync_read(struct bio *bio)
 {
 	struct r1bio *r1_bio = bio->bi_private;
 
@@ -1748,16 +1695,16 @@ static void end_sync_read(struct bio *bio, int error)
 	 * or re-read if the read failed.
 	 * We don't do much here, just schedule handling by raid1d
 	 */
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (!bio->bi_error)
 		set_bit(R1BIO_Uptodate, &r1_bio->state);
 
 	if (atomic_dec_and_test(&r1_bio->remaining))
 		reschedule_retry(r1_bio);
 }
 
-static void end_sync_write(struct bio *bio, int error)
+static void end_sync_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct r1bio *r1_bio = bio->bi_private;
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
@@ -1944,7 +1891,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 		idx ++;
 	}
 	set_bit(R1BIO_Uptodate, &r1_bio->state);
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
+	bio->bi_error = 0;
 	return 1;
 }
 
@@ -1968,15 +1915,14 @@ static void process_checks(struct r1bio *r1_bio)
 	for (i = 0; i < conf->raid_disks * 2; i++) {
 		int j;
 		int size;
-		int uptodate;
+		int error;
 		struct bio *b = r1_bio->bios[i];
 		if (b->bi_end_io != end_sync_read)
 			continue;
-		/* fixup the bio for reuse, but preserve BIO_UPTODATE */
-		uptodate = test_bit(BIO_UPTODATE, &b->bi_flags);
+		/* fixup the bio for reuse, but preserve errno */
+		error = b->bi_error;
 		bio_reset(b);
-		if (!uptodate)
-			clear_bit(BIO_UPTODATE, &b->bi_flags);
+		b->bi_error = error;
 		b->bi_vcnt = vcnt;
 		b->bi_iter.bi_size = r1_bio->sectors << 9;
 		b->bi_iter.bi_sector = r1_bio->sector +
@@ -1999,7 +1945,7 @@ static void process_checks(struct r1bio *r1_bio)
 	}
 	for (primary = 0; primary < conf->raid_disks * 2; primary++)
 		if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
-		    test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) {
+		    !r1_bio->bios[primary]->bi_error) {
 			r1_bio->bios[primary]->bi_end_io = NULL;
 			rdev_dec_pending(conf->mirrors[primary].rdev, mddev);
 			break;
@@ -2009,14 +1955,14 @@ static void process_checks(struct r1bio *r1_bio)
 		int j;
 		struct bio *pbio = r1_bio->bios[primary];
 		struct bio *sbio = r1_bio->bios[i];
-		int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags);
+		int error = sbio->bi_error;
 
 		if (sbio->bi_end_io != end_sync_read)
 			continue;
-		/* Now we can 'fixup' the BIO_UPTODATE flag */
-		set_bit(BIO_UPTODATE, &sbio->bi_flags);
+		/* Now we can 'fixup' the error value */
+		sbio->bi_error = 0;
 
-		if (uptodate) {
+		if (!error) {
 			for (j = vcnt; j-- ; ) {
 				struct page *p, *s;
 				p = pbio->bi_io_vec[j].bv_page;
@@ -2031,7 +1977,7 @@ static void process_checks(struct r1bio *r1_bio)
 		if (j >= 0)
 			atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
 		if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
-			      && uptodate)) {
+			      && !error)) {
 			/* No need to write to this device. */
 			sbio->bi_end_io = NULL;
 			rdev_dec_pending(conf->mirrors[i].rdev, mddev);
@@ -2249,7 +2195,7 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
 		bio_trim(wbio, sector - r1_bio->sector, sectors);
 		wbio->bi_iter.bi_sector += rdev->data_offset;
 		wbio->bi_bdev = rdev->bdev;
-		if (submit_bio_wait(WRITE, wbio) == 0)
+		if (submit_bio_wait(WRITE, wbio) < 0)
 			/* failure! */
 			ok = rdev_set_badblocks(rdev, sector,
 						sectors, 0)
@@ -2272,11 +2218,11 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio
 		struct bio *bio = r1_bio->bios[m];
 		if (bio->bi_end_io == NULL)
 			continue;
-		if (test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+		if (!bio->bi_error &&
 		    test_bit(R1BIO_MadeGood, &r1_bio->state)) {
 			rdev_clear_badblocks(rdev, r1_bio->sector, s, 0);
 		}
-		if (!test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+		if (bio->bi_error &&
 		    test_bit(R1BIO_WriteError, &r1_bio->state)) {
 			if (!rdev_set_badblocks(rdev, r1_bio->sector, s, 0))
 				md_error(conf->mddev, rdev);
@@ -2289,6 +2235,7 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio
 static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 {
 	int m;
+	bool fail = false;
 	for (m = 0; m < conf->raid_disks * 2 ; m++)
 		if (r1_bio->bios[m] == IO_MADE_GOOD) {
 			struct md_rdev *rdev = conf->mirrors[m].rdev;
@@ -2301,6 +2248,7 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 			 * narrow down and record precise write
 			 * errors.
 			 */
+			fail = true;
 			if (!narrow_write_error(r1_bio, m)) {
 				md_error(conf->mddev,
 					 conf->mirrors[m].rdev);
@@ -2310,9 +2258,16 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 			rdev_dec_pending(conf->mirrors[m].rdev,
 					 conf->mddev);
 		}
-	if (test_bit(R1BIO_WriteError, &r1_bio->state))
-		close_write(r1_bio);
-	raid_end_bio_io(r1_bio);
+	if (fail) {
+		spin_lock_irq(&conf->device_lock);
+		list_add(&r1_bio->retry_list, &conf->bio_end_io_list);
+		spin_unlock_irq(&conf->device_lock);
+		md_wakeup_thread(conf->mddev->thread);
+	} else {
+		if (test_bit(R1BIO_WriteError, &r1_bio->state))
+			close_write(r1_bio);
+		raid_end_bio_io(r1_bio);
+	}
 }
 
 static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
@@ -2418,6 +2373,27 @@ static void raid1d(struct md_thread *thread)
 
 	md_check_recovery(mddev);
 
+	if (!list_empty_careful(&conf->bio_end_io_list) &&
+	    !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+		LIST_HEAD(tmp);
+		spin_lock_irqsave(&conf->device_lock, flags);
+		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+			list_add(&tmp, &conf->bio_end_io_list);
+			list_del_init(&conf->bio_end_io_list);
+		}
+		spin_unlock_irqrestore(&conf->device_lock, flags);
+		while (!list_empty(&tmp)) {
+			r1_bio = list_first_entry(&tmp, struct r1bio,
+						  retry_list);
+			list_del(&r1_bio->retry_list);
+			if (mddev->degraded)
+				set_bit(R1BIO_Degraded, &r1_bio->state);
+			if (test_bit(R1BIO_WriteError, &r1_bio->state))
+				close_write(r1_bio);
+			raid_end_bio_io(r1_bio);
+		}
+	}
+
 	blk_start_plug(&plug);
 	for (;;) {
 
@@ -2715,7 +2691,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 						/* remove last page from this bio */
 						bio->bi_vcnt--;
 						bio->bi_iter.bi_size -= len;
-						__clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+						bio_clear_flag(bio, BIO_SEG_VALID);
 					}
 					goto bio_full;
 				}
@@ -2810,8 +2786,6 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 			goto abort;
 		disk->rdev = rdev;
 		q = bdev_get_queue(rdev->bdev);
-		if (q->merge_bvec_fn)
-			mddev->merge_check_needed = 1;
 
 		disk->head_position = 0;
 		disk->seq_start = MaxSector;
@@ -2819,6 +2793,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	conf->raid_disks = mddev->raid_disks;
 	conf->mddev = mddev;
 	INIT_LIST_HEAD(&conf->retry_list);
+	INIT_LIST_HEAD(&conf->bio_end_io_list);
 
 	spin_lock_init(&conf->resync_lock);
 	init_waitqueue_head(&conf->wait_barrier);
@@ -2872,8 +2847,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
  abort:
 	if (conf) {
-		if (conf->r1bio_pool)
-			mempool_destroy(conf->r1bio_pool);
+		mempool_destroy(conf->r1bio_pool);
 		kfree(conf->mirrors);
 		safe_put_page(conf->tmppage);
 		kfree(conf->poolinfo);
@@ -2975,8 +2949,7 @@ static void raid1_free(struct mddev *mddev, void *priv)
 {
 	struct r1conf *conf = priv;
 
-	if (conf->r1bio_pool)
-		mempool_destroy(conf->r1bio_pool);
+	mempool_destroy(conf->r1bio_pool);
 	kfree(conf->mirrors);
 	safe_put_page(conf->tmppage);
 	kfree(conf->poolinfo);
@@ -3113,6 +3086,7 @@ static int raid1_reshape(struct mddev *mddev)
 
 	unfreeze_array(conf);
 
+	set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 
@@ -3176,7 +3150,6 @@ static struct md_personality raid1_personality =
 	.quiesce	= raid1_quiesce,
 	.takeover	= raid1_takeover,
 	.congested	= raid1_congested,
-	.mergeable_bvec	= raid1_mergeable_bvec,
 };
 
 static int __init raid_init(void)
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 14ebb288c..c52d7139c 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -61,6 +61,11 @@ struct r1conf {
 	 * block, or anything else.
 	 */
 	struct list_head	retry_list;
+	/* A separate list of r1bio which just need raid_end_bio_io called.
+	 * This mustn't happen for writes which had any errors if the superblock
+	 * needs to be written.
+	 */
+	struct list_head	bio_end_io_list;
 
 	/* queue pending writes to be submitted on unplug */
 	struct bio_list		pending_bio_list;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 38c58e19c..96f365968 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -39,6 +39,7 @@
  *    far_copies (stored in second byte of layout)
  *    far_offset (stored in bit 16 of layout )
  *    use_far_sets (stored in bit 17 of layout )
+ *    use_far_sets_bugfixed (stored in bit 18 of layout )
  *
  * The data to be stored is divided into chunks using chunksize.  Each device
  * is divided into far_copies sections.   In each section, chunks are laid out
@@ -101,7 +102,7 @@ static int _enough(struct r10conf *conf, int previous, int ignore);
 static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 				int *skipped);
 static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
-static void end_reshape_write(struct bio *bio, int error);
+static void end_reshape_write(struct bio *bio);
 static void end_reshape(struct r10conf *conf);
 
 static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
@@ -307,9 +308,9 @@ static void raid_end_bio_io(struct r10bio *r10_bio)
 	} else
 		done = 1;
 	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+		bio->bi_error = -EIO;
 	if (done) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		/*
 		 * Wake up any possible resync thread that waits for the device
 		 * to go idle.
@@ -358,9 +359,9 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
 	return r10_bio->devs[slot].devnum;
 }
 
-static void raid10_end_read_request(struct bio *bio, int error)
+static void raid10_end_read_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct r10bio *r10_bio = bio->bi_private;
 	int slot, dev;
 	struct md_rdev *rdev;
@@ -438,9 +439,8 @@ static void one_write_done(struct r10bio *r10_bio)
 	}
 }
 
-static void raid10_end_write_request(struct bio *bio, int error)
+static void raid10_end_write_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	int dev;
 	int dec_rdev = 1;
@@ -460,7 +460,7 @@ static void raid10_end_write_request(struct bio *bio, int error)
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	if (!uptodate) {
+	if (bio->bi_error) {
 		if (repl)
 			/* Never record new bad blocks to replacement,
 			 * just fail it.
@@ -672,93 +672,6 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
 	return (vchunk << geo->chunk_shift) + offset;
 }
 
-/**
- *	raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
- *	@mddev: the md device
- *	@bvm: properties of new bio
- *	@biovec: the request that could be merged to it.
- *
- *	Return amount of bytes we can accept at this offset
- *	This requires checking for end-of-chunk if near_copies != raid_disks,
- *	and for subordinate merge_bvec_fns if merge_check_needed.
- */
-static int raid10_mergeable_bvec(struct mddev *mddev,
-				 struct bvec_merge_data *bvm,
-				 struct bio_vec *biovec)
-{
-	struct r10conf *conf = mddev->private;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int max;
-	unsigned int chunk_sectors;
-	unsigned int bio_sectors = bvm->bi_size >> 9;
-	struct geom *geo = &conf->geo;
-
-	chunk_sectors = (conf->geo.chunk_mask & conf->prev.chunk_mask) + 1;
-	if (conf->reshape_progress != MaxSector &&
-	    ((sector >= conf->reshape_progress) !=
-	     conf->mddev->reshape_backwards))
-		geo = &conf->prev;
-
-	if (geo->near_copies < geo->raid_disks) {
-		max = (chunk_sectors - ((sector & (chunk_sectors - 1))
-					+ bio_sectors)) << 9;
-		if (max < 0)
-			/* bio_add cannot handle a negative return */
-			max = 0;
-		if (max <= biovec->bv_len && bio_sectors == 0)
-			return biovec->bv_len;
-	} else
-		max = biovec->bv_len;
-
-	if (mddev->merge_check_needed) {
-		struct {
-			struct r10bio r10_bio;
-			struct r10dev devs[conf->copies];
-		} on_stack;
-		struct r10bio *r10_bio = &on_stack.r10_bio;
-		int s;
-		if (conf->reshape_progress != MaxSector) {
-			/* Cannot give any guidance during reshape */
-			if (max <= biovec->bv_len && bio_sectors == 0)
-				return biovec->bv_len;
-			return 0;
-		}
-		r10_bio->sector = sector;
-		raid10_find_phys(conf, r10_bio);
-		rcu_read_lock();
-		for (s = 0; s < conf->copies; s++) {
-			int disk = r10_bio->devs[s].devnum;
-			struct md_rdev *rdev = rcu_dereference(
-				conf->mirrors[disk].rdev);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = r10_bio->devs[s].addr
-						+ rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-			rdev = rcu_dereference(conf->mirrors[disk].replacement);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = r10_bio->devs[s].addr
-						+ rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-		}
-		rcu_read_unlock();
-	}
-	return max;
-}
-
 /*
  * This routine returns the disk from which the requested read should
  * be done. There is a per-array 'next expected sequential IO' sector
@@ -821,12 +734,10 @@ retry:
 		disk = r10_bio->devs[slot].devnum;
 		rdev = rcu_dereference(conf->mirrors[disk].replacement);
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
-		    test_bit(Unmerged, &rdev->flags) ||
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
 			rdev = rcu_dereference(conf->mirrors[disk].rdev);
 		if (rdev == NULL ||
-		    test_bit(Faulty, &rdev->flags) ||
-		    test_bit(Unmerged, &rdev->flags))
+		    test_bit(Faulty, &rdev->flags))
 			continue;
 		if (!test_bit(In_sync, &rdev->flags) &&
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
@@ -957,7 +868,7 @@ static void flush_pending_writes(struct r10conf *conf)
 			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			else
 				generic_make_request(bio);
 			bio = next;
@@ -1133,7 +1044,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
-			bio_endio(bio, 0);
+			bio_endio(bio);
 		else
 			generic_make_request(bio);
 		bio = next;
@@ -1217,7 +1128,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	 * non-zero, then it is the number of not-completed requests.
 	 */
 	bio->bi_phys_segments = 0;
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+	bio_clear_flag(bio, BIO_SEG_VALID);
 
 	if (rw == READ) {
 		/*
@@ -1326,11 +1237,9 @@ retry_write:
 			blocked_rdev = rrdev;
 			break;
 		}
-		if (rdev && (test_bit(Faulty, &rdev->flags)
-			     || test_bit(Unmerged, &rdev->flags)))
+		if (rdev && (test_bit(Faulty, &rdev->flags)))
 			rdev = NULL;
-		if (rrdev && (test_bit(Faulty, &rrdev->flags)
-			      || test_bit(Unmerged, &rrdev->flags)))
+		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
 			rrdev = NULL;
 
 		r10_bio->devs[i].bio = NULL;
@@ -1589,6 +1498,8 @@ static void status(struct seq_file *seq, struct mddev *mddev)
 			seq_printf(seq, " %d offset-copies", conf->geo.far_copies);
 		else
 			seq_printf(seq, " %d far-copies", conf->geo.far_copies);
+		if (conf->geo.far_set_size != conf->geo.raid_disks)
+			seq_printf(seq, " %d devices per set", conf->geo.far_set_size);
 	}
 	seq_printf(seq, " [%d/%d] [", conf->geo.raid_disks,
 					conf->geo.raid_disks - mddev->degraded);
@@ -1681,6 +1592,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_CHANGE_PENDING, &mddev->flags);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 	printk(KERN_ALERT
 	       "md/raid10:%s: Disk failure on %s, disabling device.\n"
@@ -1777,7 +1689,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	int mirror;
 	int first = 0;
 	int last = conf->geo.raid_disks - 1;
-	struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
@@ -1790,11 +1701,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
-	if (q->merge_bvec_fn) {
-		set_bit(Unmerged, &rdev->flags);
-		mddev->merge_check_needed = 1;
-	}
-
 	if (rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
 		mirror = rdev->saved_raid_disk;
@@ -1833,19 +1739,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		rcu_assign_pointer(p->rdev, rdev);
 		break;
 	}
-	if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
-		/* Some requests might not have seen this new
-		 * merge_bvec_fn.  We must wait for them to complete
-		 * before merging the device fully.
-		 * First we make sure any code which has tested
-		 * our function has submitted the request, then
-		 * we wait for all outstanding requests to complete.
-		 */
-		synchronize_sched();
-		freeze_array(conf, 0);
-		unfreeze_array(conf);
-		clear_bit(Unmerged, &rdev->flags);
-	}
 	md_integrity_add_rdev(rdev, mddev);
 	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
@@ -1916,7 +1809,7 @@ abort:
 	return err;
 }
 
-static void end_sync_read(struct bio *bio, int error)
+static void end_sync_read(struct bio *bio)
 {
 	struct r10bio *r10_bio = bio->bi_private;
 	struct r10conf *conf = r10_bio->mddev->private;
@@ -1928,7 +1821,7 @@ static void end_sync_read(struct bio *bio, int error)
 	} else
 		d = find_bio_disk(conf, r10_bio, bio, NULL, NULL);
 
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (!bio->bi_error)
 		set_bit(R10BIO_Uptodate, &r10_bio->state);
 	else
 		/* The write handler will notice the lack of
@@ -1977,9 +1870,8 @@ static void end_sync_request(struct r10bio *r10_bio)
 	}
 }
 
-static void end_sync_write(struct bio *bio, int error)
+static void end_sync_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
@@ -1996,7 +1888,7 @@ static void end_sync_write(struct bio *bio, int error)
 	else
 		rdev = conf->mirrors[d].rdev;
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		if (repl)
 			md_error(mddev, rdev);
 		else {
@@ -2044,7 +1936,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 
 	/* find the first device with a block */
 	for (i=0; i<conf->copies; i++)
-		if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags))
+		if (!r10_bio->devs[i].bio->bi_error)
 			break;
 
 	if (i == conf->copies)
@@ -2064,7 +1956,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 			continue;
 		if (i == first)
 			continue;
-		if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags)) {
+		if (!r10_bio->devs[i].bio->bi_error) {
 			/* We know that the bi_io_vec layout is the same for
 			 * both 'first' and 'i', so we just compare them.
 			 * All vec entries are PAGE_SIZE;
@@ -2394,7 +2286,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev &&
-			    !test_bit(Unmerged, &rdev->flags) &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
 					&first_bad, &bad_sectors) == 0) {
@@ -2448,7 +2339,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (!rdev ||
-			    test_bit(Unmerged, &rdev->flags) ||
 			    !test_bit(In_sync, &rdev->flags))
 				continue;
 
@@ -2580,7 +2470,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
 				   choose_data_offset(r10_bio, rdev) +
 				   (sector - r10_bio->sector));
 		wbio->bi_bdev = rdev->bdev;
-		if (submit_bio_wait(WRITE, wbio) == 0)
+		if (submit_bio_wait(WRITE, wbio) < 0)
 			/* Failure! */
 			ok = rdev_set_badblocks(rdev, sector,
 						sectors, 0)
@@ -2706,8 +2596,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 			rdev = conf->mirrors[dev].rdev;
 			if (r10_bio->devs[m].bio == NULL)
 				continue;
-			if (test_bit(BIO_UPTODATE,
-				     &r10_bio->devs[m].bio->bi_flags)) {
+			if (!r10_bio->devs[m].bio->bi_error) {
 				rdev_clear_badblocks(
 					rdev,
 					r10_bio->devs[m].addr,
@@ -2722,8 +2611,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 			rdev = conf->mirrors[dev].replacement;
 			if (r10_bio->devs[m].repl_bio == NULL)
 				continue;
-			if (test_bit(BIO_UPTODATE,
-				     &r10_bio->devs[m].repl_bio->bi_flags)) {
+
+			if (!r10_bio->devs[m].repl_bio->bi_error) {
 				rdev_clear_badblocks(
 					rdev,
 					r10_bio->devs[m].addr,
@@ -2738,6 +2627,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 		}
 		put_buf(r10_bio);
 	} else {
+		bool fail = false;
 		for (m = 0; m < conf->copies; m++) {
 			int dev = r10_bio->devs[m].devnum;
 			struct bio *bio = r10_bio->devs[m].bio;
@@ -2748,8 +2638,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 					r10_bio->devs[m].addr,
 					r10_bio->sectors, 0);
 				rdev_dec_pending(rdev, conf->mddev);
-			} else if (bio != NULL &&
-				   !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+			} else if (bio != NULL && bio->bi_error) {
+				fail = true;
 				if (!narrow_write_error(r10_bio, m)) {
 					md_error(conf->mddev, rdev);
 					set_bit(R10BIO_Degraded,
@@ -2767,10 +2657,17 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 		}
-		if (test_bit(R10BIO_WriteError,
-			     &r10_bio->state))
-			close_write(r10_bio);
-		raid_end_bio_io(r10_bio);
+		if (fail) {
+			spin_lock_irq(&conf->device_lock);
+			list_add(&r10_bio->retry_list, &conf->bio_end_io_list);
+			spin_unlock_irq(&conf->device_lock);
+			md_wakeup_thread(conf->mddev->thread);
+		} else {
+			if (test_bit(R10BIO_WriteError,
+				     &r10_bio->state))
+				close_write(r10_bio);
+			raid_end_bio_io(r10_bio);
+		}
 	}
 }
 
@@ -2785,6 +2682,29 @@ static void raid10d(struct md_thread *thread)
 
 	md_check_recovery(mddev);
 
+	if (!list_empty_careful(&conf->bio_end_io_list) &&
+	    !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+		LIST_HEAD(tmp);
+		spin_lock_irqsave(&conf->device_lock, flags);
+		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+			list_add(&tmp, &conf->bio_end_io_list);
+			list_del_init(&conf->bio_end_io_list);
+		}
+		spin_unlock_irqrestore(&conf->device_lock, flags);
+		while (!list_empty(&tmp)) {
+			r10_bio = list_first_entry(&tmp, struct r10bio,
+						   retry_list);
+			list_del(&r10_bio->retry_list);
+			if (mddev->degraded)
+				set_bit(R10BIO_Degraded, &r10_bio->state);
+
+			if (test_bit(R10BIO_WriteError,
+				     &r10_bio->state))
+				close_write(r10_bio);
+			raid_end_bio_io(r10_bio);
+		}
+	}
+
 	blk_start_plug(&plug);
 	for (;;) {
 
@@ -3263,7 +3183,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 
 			bio = r10_bio->devs[i].bio;
 			bio_reset(bio);
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = -EIO;
 			if (conf->mirrors[d].rdev == NULL ||
 			    test_bit(Faulty, &conf->mirrors[d].rdev->flags))
 				continue;
@@ -3300,7 +3220,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			/* Need to set up for writing to the replacement */
 			bio = r10_bio->devs[i].repl_bio;
 			bio_reset(bio);
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = -EIO;
 
 			sector = r10_bio->devs[i].addr;
 			atomic_inc(&conf->mirrors[d].rdev->nr_pending);
@@ -3357,7 +3277,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 				/* remove last page from this bio */
 				bio2->bi_vcnt--;
 				bio2->bi_iter.bi_size -= len;
-				__clear_bit(BIO_SEG_VALID, &bio2->bi_flags);
+				bio_clear_flag(bio2, BIO_SEG_VALID);
 			}
 			goto bio_full;
 		}
@@ -3377,7 +3297,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 
 		if (bio->bi_end_io == end_sync_read) {
 			md_sync_acct(bio->bi_bdev, nr_sectors);
-			set_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = 0;
 			generic_make_request(bio);
 		}
 	}
@@ -3477,7 +3397,7 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new)
 		disks = mddev->raid_disks + mddev->delta_disks;
 		break;
 	}
-	if (layout >> 18)
+	if (layout >> 19)
 		return -1;
 	if (chunk < (PAGE_SIZE >> 9) ||
 	    !is_power_of_2(chunk))
@@ -3489,7 +3409,22 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new)
 	geo->near_copies = nc;
 	geo->far_copies = fc;
 	geo->far_offset = fo;
-	geo->far_set_size = (layout & (1<<17)) ? disks / fc : disks;
+	switch (layout >> 17) {
+	case 0:	/* original layout.  simple but not always optimal */
+		geo->far_set_size = disks;
+		break;
+	case 1: /* "improved" layout which was buggy.  Hopefully no-one is
+		 * actually using this, but leave code here just in case.*/
+		geo->far_set_size = disks/fc;
+		WARN(geo->far_set_size < fc,
+		     "This RAID10 layout does not provide data safety - please backup and create new array\n");
+		break;
+	case 2: /* "improved" layout fixed to match documentation */
+		geo->far_set_size = fc * nc;
+		break;
+	default: /* Not a valid layout */
+		return -1;
+	}
 	geo->chunk_mask = chunk - 1;
 	geo->chunk_shift = ffz(~chunk);
 	return nc*fc;
@@ -3559,6 +3494,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	conf->reshape_safe = conf->reshape_progress;
 	spin_lock_init(&conf->device_lock);
 	INIT_LIST_HEAD(&conf->retry_list);
+	INIT_LIST_HEAD(&conf->bio_end_io_list);
 
 	spin_lock_init(&conf->resync_lock);
 	init_waitqueue_head(&conf->wait_barrier);
@@ -3575,8 +3511,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 		printk(KERN_ERR "md/raid10:%s: couldn't allocate memory.\n",
 		       mdname(mddev));
 	if (conf) {
-		if (conf->r10bio_pool)
-			mempool_destroy(conf->r10bio_pool);
+		mempool_destroy(conf->r10bio_pool);
 		kfree(conf->mirrors);
 		safe_put_page(conf->tmppage);
 		kfree(conf);
@@ -3643,8 +3578,6 @@ static int run(struct mddev *mddev)
 			disk->rdev = rdev;
 		}
 		q = bdev_get_queue(rdev->bdev);
-		if (q->merge_bvec_fn)
-			mddev->merge_check_needed = 1;
 		diff = (rdev->new_data_offset - rdev->data_offset);
 		if (!mddev->reshape_backwards)
 			diff = -diff;
@@ -3773,8 +3706,7 @@ static int run(struct mddev *mddev)
 
 out_free_conf:
 	md_unregister_thread(&mddev->thread);
-	if (conf->r10bio_pool)
-		mempool_destroy(conf->r10bio_pool);
+	mempool_destroy(conf->r10bio_pool);
 	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
 	kfree(conf);
@@ -3787,8 +3719,7 @@ static void raid10_free(struct mddev *mddev, void *priv)
 {
 	struct r10conf *conf = priv;
 
-	if (conf->r10bio_pool)
-		mempool_destroy(conf->r10bio_pool);
+	mempool_destroy(conf->r10bio_pool);
 	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
 	kfree(conf->mirrors_old);
@@ -4215,7 +4146,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 	 * at a time, possibly less if that exceeds RESYNC_PAGES,
 	 * or we hit a bad block or something.
 	 * This might mean we pause for normal IO in the middle of
-	 * a chunk, but that is not a problem was mddev->reshape_position
+	 * a chunk, but that is not a problem as mddev->reshape_position
 	 * can record any location.
 	 *
 	 * If we will want to write to a location that isn't
@@ -4239,7 +4170,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 	 *
 	 * In all this the minimum difference in data offsets
 	 * (conf->offset_diff - always positive) allows a bit of slack,
-	 * so next can be after 'safe', but not by more than offset_disk
+	 * so next can be after 'safe', but not by more than offset_diff
 	 *
 	 * We need to prepare all the bios here before we start any IO
 	 * to ensure the size we choose is acceptable to all devices.
@@ -4382,7 +4313,7 @@ read_more:
 	read_bio->bi_end_io = end_sync_read;
 	read_bio->bi_rw = READ;
 	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
-	__set_bit(BIO_UPTODATE, &read_bio->bi_flags);
+	read_bio->bi_error = 0;
 	read_bio->bi_vcnt = 0;
 	read_bio->bi_iter.bi_size = 0;
 	r10_bio->master_bio = read_bio;
@@ -4439,7 +4370,7 @@ read_more:
 				/* Remove last page from this bio */
 				bio2->bi_vcnt--;
 				bio2->bi_iter.bi_size -= len;
-				__clear_bit(BIO_SEG_VALID, &bio2->bi_flags);
+				bio_clear_flag(bio2, BIO_SEG_VALID);
 			}
 			goto bio_full;
 		}
@@ -4604,9 +4535,8 @@ static int handle_reshape_read_error(struct mddev *mddev,
 	return 0;
 }
 
-static void end_reshape_write(struct bio *bio, int error)
+static void end_reshape_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
@@ -4623,7 +4553,7 @@ static void end_reshape_write(struct bio *bio, int error)
 		rdev = conf->mirrors[d].rdev;
 	}
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		/* FIXME should record badblock */
 		md_error(mddev, rdev);
 	}
@@ -4700,7 +4630,6 @@ static struct md_personality raid10_personality =
 	.start_reshape	= raid10_start_reshape,
 	.finish_reshape	= raid10_finish_reshape,
 	.congested	= raid10_congested,
-	.mergeable_bvec	= raid10_mergeable_bvec,
 };
 
 static int __init raid_init(void)
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index 5ee6473dd..6fc2c7575 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -53,6 +53,12 @@ struct r10conf {
 	sector_t		offset_diff;
 
 	struct list_head	retry_list;
+	/* A separate list of r1bio which just need raid_end_bio_io called.
+	 * This mustn't happen for writes which had any errors if the superblock
+	 * needs to be written.
+	 */
+	struct list_head	bio_end_io_list;
+
 	/* queue pending writes and submit them on unplug */
 	struct bio_list		pending_bio_list;
 	int			pending_count;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f757023fc..45933c160 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -223,18 +223,14 @@ static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
 	return slot;
 }
 
-static void return_io(struct bio *return_bi)
+static void return_io(struct bio_list *return_bi)
 {
-	struct bio *bi = return_bi;
-	while (bi) {
-
-		return_bi = bi->bi_next;
-		bi->bi_next = NULL;
+	struct bio *bi;
+	while ((bi = bio_list_pop(return_bi)) != NULL) {
 		bi->bi_iter.bi_size = 0;
 		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
 					 bi, 0);
-		bio_endio(bi, 0);
-		bi = return_bi;
+		bio_endio(bi);
 	}
 }
 
@@ -887,9 +883,9 @@ static int use_new_offset(struct r5conf *conf, struct stripe_head *sh)
 }
 
 static void
-raid5_end_read_request(struct bio *bi, int error);
+raid5_end_read_request(struct bio *bi);
 static void
-raid5_end_write_request(struct bio *bi, int error);
+raid5_end_write_request(struct bio *bi);
 
 static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 {
@@ -1177,7 +1173,7 @@ async_copy_data(int frombio, struct bio *bio, struct page **page,
 static void ops_complete_biofill(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
-	struct bio *return_bi = NULL;
+	struct bio_list return_bi = BIO_EMPTY_LIST;
 	int i;
 
 	pr_debug("%s: stripe %llu\n", __func__,
@@ -1201,17 +1197,15 @@ static void ops_complete_biofill(void *stripe_head_ref)
 			while (rbi && rbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				rbi2 = r5_next_bio(rbi, dev->sector);
-				if (!raid5_dec_bi_active_stripes(rbi)) {
-					rbi->bi_next = return_bi;
-					return_bi = rbi;
-				}
+				if (!raid5_dec_bi_active_stripes(rbi))
+					bio_list_add(&return_bi, rbi);
 				rbi = rbi2;
 			}
 		}
 	}
 	clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
 
-	return_io(return_bi);
+	return_io(&return_bi);
 
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
@@ -2277,17 +2271,15 @@ static void shrink_stripes(struct r5conf *conf)
 	       drop_one_stripe(conf))
 		;
 
-	if (conf->slab_cache)
-		kmem_cache_destroy(conf->slab_cache);
+	kmem_cache_destroy(conf->slab_cache);
 	conf->slab_cache = NULL;
 }
 
-static void raid5_end_read_request(struct bio * bi, int error)
+static void raid5_end_read_request(struct bio * bi)
 {
 	struct stripe_head *sh = bi->bi_private;
 	struct r5conf *conf = sh->raid_conf;
 	int disks = sh->disks, i;
-	int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
 	char b[BDEVNAME_SIZE];
 	struct md_rdev *rdev = NULL;
 	sector_t s;
@@ -2296,9 +2288,9 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		if (bi == &sh->dev[i].req)
 			break;
 
-	pr_debug("end_read_request %llu/%d, count: %d, uptodate %d.\n",
+	pr_debug("end_read_request %llu/%d, count: %d, error %d.\n",
 		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
-		uptodate);
+		bi->bi_error);
 	if (i == disks) {
 		BUG();
 		return;
@@ -2317,7 +2309,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		s = sh->sector + rdev->new_data_offset;
 	else
 		s = sh->sector + rdev->data_offset;
-	if (uptodate) {
+	if (!bi->bi_error) {
 		set_bit(R5_UPTODATE, &sh->dev[i].flags);
 		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
 			/* Note that this cannot happen on a
@@ -2405,13 +2397,12 @@ static void raid5_end_read_request(struct bio * bi, int error)
 	release_stripe(sh);
 }
 
-static void raid5_end_write_request(struct bio *bi, int error)
+static void raid5_end_write_request(struct bio *bi)
 {
 	struct stripe_head *sh = bi->bi_private;
 	struct r5conf *conf = sh->raid_conf;
 	int disks = sh->disks, i;
 	struct md_rdev *uninitialized_var(rdev);
-	int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
 	sector_t first_bad;
 	int bad_sectors;
 	int replacement = 0;
@@ -2434,23 +2425,23 @@ static void raid5_end_write_request(struct bio *bi, int error)
 			break;
 		}
 	}
-	pr_debug("end_write_request %llu/%d, count %d, uptodate: %d.\n",
+	pr_debug("end_write_request %llu/%d, count %d, error: %d.\n",
 		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
-		uptodate);
+		bi->bi_error);
 	if (i == disks) {
 		BUG();
 		return;
 	}
 
 	if (replacement) {
-		if (!uptodate)
+		if (bi->bi_error)
 			md_error(conf->mddev, rdev);
 		else if (is_badblock(rdev, sh->sector,
 				     STRIPE_SECTORS,
 				     &first_bad, &bad_sectors))
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
-		if (!uptodate) {
+		if (bi->bi_error) {
 			set_bit(STRIPE_DEGRADED, &sh->state);
 			set_bit(WriteErrorSeen, &rdev->flags);
 			set_bit(R5_WriteError, &sh->dev[i].flags);
@@ -2471,7 +2462,7 @@ static void raid5_end_write_request(struct bio *bi, int error)
 	}
 	rdev_dec_pending(rdev, conf->mddev);
 
-	if (sh->batch_head && !uptodate && !replacement)
+	if (sh->batch_head && bi->bi_error && !replacement)
 		set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
 
 	if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
@@ -2519,6 +2510,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_CHANGE_PENDING, &mddev->flags);
 	printk(KERN_ALERT
 	       "md/raid:%s: Disk failure on %s, disabling device.\n"
 	       "md/raid:%s: Operation continuing on %d devices.\n",
@@ -3071,7 +3063,7 @@ static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
 static void
 handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 				struct stripe_head_state *s, int disks,
-				struct bio **return_bi)
+				struct bio_list *return_bi)
 {
 	int i;
 	BUG_ON(sh->batch_head);
@@ -3112,11 +3104,11 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		while (bi && bi->bi_iter.bi_sector <
 			sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
-			clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+			bi->bi_error = -EIO;
 			if (!raid5_dec_bi_active_stripes(bi)) {
 				md_write_end(conf->mddev);
-				bi->bi_next = *return_bi;
-				*return_bi = bi;
+				bio_list_add(return_bi, bi);
 			}
 			bi = nextbi;
 		}
@@ -3136,11 +3128,11 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		while (bi && bi->bi_iter.bi_sector <
 		       sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
-			clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+			bi->bi_error = -EIO;
 			if (!raid5_dec_bi_active_stripes(bi)) {
 				md_write_end(conf->mddev);
-				bi->bi_next = *return_bi;
-				*return_bi = bi;
+				bio_list_add(return_bi, bi);
 			}
 			bi = bi2;
 		}
@@ -3157,15 +3149,16 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			spin_unlock_irq(&sh->stripe_lock);
 			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 				wake_up(&conf->wait_for_overlap);
+			if (bi)
+				s->to_read--;
 			while (bi && bi->bi_iter.bi_sector <
 			       sh->dev[i].sector + STRIPE_SECTORS) {
 				struct bio *nextbi =
 					r5_next_bio(bi, sh->dev[i].sector);
-				clear_bit(BIO_UPTODATE, &bi->bi_flags);
-				if (!raid5_dec_bi_active_stripes(bi)) {
-					bi->bi_next = *return_bi;
-					*return_bi = bi;
-				}
+
+				bi->bi_error = -EIO;
+				if (!raid5_dec_bi_active_stripes(bi))
+					bio_list_add(return_bi, bi);
 				bi = nextbi;
 			}
 		}
@@ -3177,6 +3170,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		 */
 		clear_bit(R5_LOCKED, &sh->dev[i].flags);
 	}
+	s->to_write = 0;
+	s->written = 0;
 
 	if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
 		if (atomic_dec_and_test(&conf->pending_full_writes))
@@ -3308,7 +3303,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 		 */
 		return 0;
 
-	for (i = 0; i < s->failed; i++) {
+	for (i = 0; i < s->failed && i < 2; i++) {
 		if (fdev[i]->towrite &&
 		    !test_bit(R5_UPTODATE, &fdev[i]->flags) &&
 		    !test_bit(R5_OVERWRITE, &fdev[i]->flags))
@@ -3332,7 +3327,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 	    sh->sector < sh->raid_conf->mddev->recovery_cp)
 		/* reconstruct-write isn't being forced */
 		return 0;
-	for (i = 0; i < s->failed; i++) {
+	for (i = 0; i < s->failed && i < 2; i++) {
 		if (s->failed_num[i] != sh->pd_idx &&
 		    s->failed_num[i] != sh->qd_idx &&
 		    !test_bit(R5_UPTODATE, &fdev[i]->flags) &&
@@ -3444,7 +3439,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
  * never LOCKED, so we don't need to test 'failed' directly.
  */
 static void handle_stripe_clean_event(struct r5conf *conf,
-	struct stripe_head *sh, int disks, struct bio **return_bi)
+	struct stripe_head *sh, int disks, struct bio_list *return_bi)
 {
 	int i;
 	struct r5dev *dev;
@@ -3478,8 +3473,7 @@ returnbi:
 					wbi2 = r5_next_bio(wbi, dev->sector);
 					if (!raid5_dec_bi_active_stripes(wbi)) {
 						md_write_end(conf->mddev);
-						wbi->bi_next = *return_bi;
-						*return_bi = wbi;
+						bio_list_add(return_bi, wbi);
 					}
 					wbi = wbi2;
 				}
@@ -3505,6 +3499,7 @@ returnbi:
 		}
 	if (!discard_pending &&
 	    test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
+		int hash;
 		clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
 		clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
 		if (sh->qd_idx >= 0) {
@@ -3518,16 +3513,17 @@ returnbi:
 		 * no updated data, so remove it from hash list and the stripe
 		 * will be reinitialized
 		 */
-		spin_lock_irq(&conf->device_lock);
 unhash:
+		hash = sh->hash_lock_index;
+		spin_lock_irq(conf->hash_locks + hash);
 		remove_hash(sh);
+		spin_unlock_irq(conf->hash_locks + hash);
 		if (head_sh->batch_head) {
 			sh = list_first_entry(&sh->batch_list,
 					      struct stripe_head, batch_list);
 			if (sh != head_sh)
 					goto unhash;
 		}
-		spin_unlock_irq(&conf->device_lock);
 		sh = head_sh;
 
 		if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
@@ -4612,7 +4608,15 @@ finish:
 			md_wakeup_thread(conf->mddev->thread);
 	}
 
-	return_io(s.return_bi);
+	if (!bio_list_empty(&s.return_bi)) {
+		if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) {
+			spin_lock_irq(&conf->device_lock);
+			bio_list_merge(&conf->return_bi, &s.return_bi);
+			spin_unlock_irq(&conf->device_lock);
+			md_wakeup_thread(conf->mddev->thread);
+		} else
+			return_io(&s.return_bi);
+	}
 
 	clear_bit_unlock(STRIPE_ACTIVE, &sh->state);
 }
@@ -4669,43 +4673,14 @@ static int raid5_congested(struct mddev *mddev, int bits)
 	return 0;
 }
 
-/* We want read requests to align with chunks where possible,
- * but write requests don't need to.
- */
-static int raid5_mergeable_bvec(struct mddev *mddev,
-				struct bvec_merge_data *bvm,
-				struct bio_vec *biovec)
-{
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int max;
-	unsigned int chunk_sectors = mddev->chunk_sectors;
-	unsigned int bio_sectors = bvm->bi_size >> 9;
-
-	/*
-	 * always allow writes to be mergeable, read as well if array
-	 * is degraded as we'll go through stripe cache anyway.
-	 */
-	if ((bvm->bi_rw & 1) == WRITE || mddev->degraded)
-		return biovec->bv_len;
-
-	if (mddev->new_chunk_sectors < mddev->chunk_sectors)
-		chunk_sectors = mddev->new_chunk_sectors;
-	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
-	if (max < 0) max = 0;
-	if (max <= biovec->bv_len && bio_sectors == 0)
-		return biovec->bv_len;
-	else
-		return max;
-}
-
 static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
 {
+	struct r5conf *conf = mddev->private;
 	sector_t sector = bio->bi_iter.bi_sector + get_start_sect(bio->bi_bdev);
-	unsigned int chunk_sectors = mddev->chunk_sectors;
+	unsigned int chunk_sectors;
 	unsigned int bio_sectors = bio_sectors(bio);
 
-	if (mddev->new_chunk_sectors < mddev->chunk_sectors)
-		chunk_sectors = mddev->new_chunk_sectors;
+	chunk_sectors = min(conf->chunk_sectors, conf->prev_chunk_sectors);
 	return  chunk_sectors >=
 		((sector & (chunk_sectors - 1)) + bio_sectors);
 }
@@ -4756,13 +4731,13 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf)
  *  first).
  *  If the read failed..
  */
-static void raid5_align_endio(struct bio *bi, int error)
+static void raid5_align_endio(struct bio *bi)
 {
 	struct bio* raid_bi  = bi->bi_private;
 	struct mddev *mddev;
 	struct r5conf *conf;
-	int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
 	struct md_rdev *rdev;
+	int error = bi->bi_error;
 
 	bio_put(bi);
 
@@ -4773,10 +4748,10 @@ static void raid5_align_endio(struct bio *bi, int error)
 
 	rdev_dec_pending(rdev, conf->mddev);
 
-	if (!error && uptodate) {
+	if (!error) {
 		trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
 					 raid_bi, 0);
-		bio_endio(raid_bi, 0);
+		bio_endio(raid_bi);
 		if (atomic_dec_and_test(&conf->active_aligned_reads))
 			wake_up(&conf->wait_for_quiescent);
 		return;
@@ -4787,26 +4762,7 @@ static void raid5_align_endio(struct bio *bi, int error)
 	add_bio_to_retry(raid_bi, conf);
 }
 
-static int bio_fits_rdev(struct bio *bi)
-{
-	struct request_queue *q = bdev_get_queue(bi->bi_bdev);
-
-	if (bio_sectors(bi) > queue_max_sectors(q))
-		return 0;
-	blk_recount_segments(q, bi);
-	if (bi->bi_phys_segments > queue_max_segments(q))
-		return 0;
-
-	if (q->merge_bvec_fn)
-		/* it's too hard to apply the merge_bvec_fn at this stage,
-		 * just just give up
-		 */
-		return 0;
-
-	return 1;
-}
-
-static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
+static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 {
 	struct r5conf *conf = mddev->private;
 	int dd_idx;
@@ -4815,7 +4771,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 	sector_t end_sector;
 
 	if (!in_chunk_boundary(mddev, raid_bio)) {
-		pr_debug("chunk_aligned_read : non aligned\n");
+		pr_debug("%s: non aligned\n", __func__);
 		return 0;
 	}
 	/*
@@ -4857,13 +4813,11 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		rcu_read_unlock();
 		raid_bio->bi_next = (void*)rdev;
 		align_bi->bi_bdev =  rdev->bdev;
-		__clear_bit(BIO_SEG_VALID, &align_bi->bi_flags);
+		bio_clear_flag(align_bi, BIO_SEG_VALID);
 
-		if (!bio_fits_rdev(align_bi) ||
-		    is_badblock(rdev, align_bi->bi_iter.bi_sector,
+		if (is_badblock(rdev, align_bi->bi_iter.bi_sector,
 				bio_sectors(align_bi),
 				&first_bad, &bad_sectors)) {
-			/* too big in some way, or has a known bad block */
 			bio_put(align_bi);
 			rdev_dec_pending(rdev, mddev);
 			return 0;
@@ -4892,6 +4846,31 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 	}
 }
 
+static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
+{
+	struct bio *split;
+
+	do {
+		sector_t sector = raid_bio->bi_iter.bi_sector;
+		unsigned chunk_sects = mddev->chunk_sectors;
+		unsigned sectors = chunk_sects - (sector & (chunk_sects-1));
+
+		if (sectors < bio_sectors(raid_bio)) {
+			split = bio_split(raid_bio, sectors, GFP_NOIO, fs_bio_set);
+			bio_chain(split, raid_bio);
+		} else
+			split = raid_bio;
+
+		if (!raid5_read_one_chunk(mddev, split)) {
+			if (split != raid_bio)
+				generic_make_request(raid_bio);
+			return split;
+		}
+	} while (split != raid_bio);
+
+	return NULL;
+}
+
 /* __get_priority_stripe - get the next stripe to process
  *
  * Full stripe writes are allowed to pass preread active stripes up until
@@ -5140,7 +5119,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 	remaining = raid5_dec_bi_active_stripes(bi);
 	if (remaining == 0) {
 		md_write_end(mddev);
-		bio_endio(bi, 0);
+		bio_endio(bi);
 	}
 }
 
@@ -5169,9 +5148,11 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 	 * data on failed drives.
 	 */
 	if (rw == READ && mddev->degraded == 0 &&
-	     mddev->reshape_position == MaxSector &&
-	     chunk_aligned_read(mddev,bi))
-		return;
+	    mddev->reshape_position == MaxSector) {
+		bi = chunk_aligned_read(mddev, bi);
+		if (!bi)
+			return;
+	}
 
 	if (unlikely(bi->bi_rw & REQ_DISCARD)) {
 		make_discard_request(mddev, bi);
@@ -5304,7 +5285,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 			release_stripe_plug(mddev, sh);
 		} else {
 			/* cannot get stripe for read-ahead, just give-up */
-			clear_bit(BIO_UPTODATE, &bi->bi_flags);
+			bi->bi_error = -EIO;
 			break;
 		}
 	}
@@ -5318,7 +5299,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 
 		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
 					 bi, 0);
-		bio_endio(bi, 0);
+		bio_endio(bi);
 	}
 }
 
@@ -5347,6 +5328,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	sector_t stripe_addr;
 	int reshape_sectors;
 	struct list_head stripes;
+	sector_t retn;
 
 	if (sector_nr == 0) {
 		/* If restarting in the middle, skip the initial sectors */
@@ -5354,6 +5336,10 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 		    conf->reshape_progress < raid5_size(mddev, 0, 0)) {
 			sector_nr = raid5_size(mddev, 0, 0)
 				- conf->reshape_progress;
+		} else if (mddev->reshape_backwards &&
+			   conf->reshape_progress == MaxSector) {
+			/* shouldn't happen, but just in case, finish up.*/
+			sector_nr = MaxSector;
 		} else if (!mddev->reshape_backwards &&
 			   conf->reshape_progress > 0)
 			sector_nr = conf->reshape_progress;
@@ -5362,7 +5348,8 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 			mddev->curr_resync_completed = sector_nr;
 			sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 			*skipped = 1;
-			return sector_nr;
+			retn = sector_nr;
+			goto finish;
 		}
 	}
 
@@ -5370,10 +5357,8 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	 * If old and new chunk sizes differ, we need to process the
 	 * largest of these
 	 */
-	if (mddev->new_chunk_sectors > mddev->chunk_sectors)
-		reshape_sectors = mddev->new_chunk_sectors;
-	else
-		reshape_sectors = mddev->chunk_sectors;
+
+	reshape_sectors = max(conf->chunk_sectors, conf->prev_chunk_sectors);
 
 	/* We update the metadata at least every 10 seconds, or when
 	 * the data about to be copied would over-write the source of
@@ -5388,11 +5373,16 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	safepos = conf->reshape_safe;
 	sector_div(safepos, data_disks);
 	if (mddev->reshape_backwards) {
-		writepos -= min_t(sector_t, reshape_sectors, writepos);
+		BUG_ON(writepos < reshape_sectors);
+		writepos -= reshape_sectors;
 		readpos += reshape_sectors;
 		safepos += reshape_sectors;
 	} else {
 		writepos += reshape_sectors;
+		/* readpos and safepos are worst-case calculations.
+		 * A negative number is overly pessimistic, and causes
+		 * obvious problems for unsigned storage.  So clip to 0.
+		 */
 		readpos -= min_t(sector_t, reshape_sectors, readpos);
 		safepos -= min_t(sector_t, reshape_sectors, safepos);
 	}
@@ -5535,7 +5525,10 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	 * then we need to write out the superblock.
 	 */
 	sector_nr += reshape_sectors;
-	if ((sector_nr - mddev->curr_resync_completed) * 2
+	retn = reshape_sectors;
+finish:
+	if (mddev->curr_resync_completed > mddev->resync_max ||
+	    (sector_nr - mddev->curr_resync_completed) * 2
 	    >= mddev->resync_max - mddev->curr_resync_completed) {
 		/* Cannot proceed until we've updated the superblock... */
 		wait_event(conf->wait_for_overlap,
@@ -5560,7 +5553,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 	}
 ret:
-	return reshape_sectors;
+	return retn;
 }
 
 static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped)
@@ -5714,7 +5707,7 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 	if (remaining == 0) {
 		trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
 					 raid_bio, 0);
-		bio_endio(raid_bio, 0);
+		bio_endio(raid_bio);
 	}
 	if (atomic_dec_and_test(&conf->active_aligned_reads))
 		wake_up(&conf->wait_for_quiescent);
@@ -5816,6 +5809,18 @@ static void raid5d(struct md_thread *thread)
 
 	md_check_recovery(mddev);
 
+	if (!bio_list_empty(&conf->return_bi) &&
+	    !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+		struct bio_list tmp = BIO_EMPTY_LIST;
+		spin_lock_irq(&conf->device_lock);
+		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+			bio_list_merge(&tmp, &conf->return_bi);
+			bio_list_init(&conf->return_bi);
+		}
+		spin_unlock_irq(&conf->device_lock);
+		return_io(&tmp);
+	}
+
 	blk_start_plug(&plug);
 	handled = 0;
 	spin_lock_irq(&conf->device_lock);
@@ -6256,8 +6261,8 @@ raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks)
 		/* size is defined by the smallest of previous and new size */
 		raid_disks = min(conf->raid_disks, conf->previous_raid_disks);
 
-	sectors &= ~((sector_t)mddev->chunk_sectors - 1);
-	sectors &= ~((sector_t)mddev->new_chunk_sectors - 1);
+	sectors &= ~((sector_t)conf->chunk_sectors - 1);
+	sectors &= ~((sector_t)conf->prev_chunk_sectors - 1);
 	return sectors * (raid_disks - conf->max_degraded);
 }
 
@@ -6475,6 +6480,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	INIT_LIST_HEAD(&conf->hold_list);
 	INIT_LIST_HEAD(&conf->delayed_list);
 	INIT_LIST_HEAD(&conf->bitmap_list);
+	bio_list_init(&conf->return_bi);
 	init_llist_head(&conf->released_stripes);
 	atomic_set(&conf->active_stripes, 0);
 	atomic_set(&conf->preread_active_stripes, 0);
@@ -6564,6 +6570,9 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	if (conf->reshape_progress != MaxSector) {
 		conf->prev_chunk_sectors = mddev->chunk_sectors;
 		conf->prev_algo = mddev->layout;
+	} else {
+		conf->prev_chunk_sectors = conf->chunk_sectors;
+		conf->prev_algo = conf->algorithm;
 	}
 
 	conf->min_nr_stripes = NR_STRIPES;
@@ -6683,6 +6692,8 @@ static int run(struct mddev *mddev)
 		sector_t here_new, here_old;
 		int old_disks;
 		int max_degraded = (mddev->level == 6 ? 2 : 1);
+		int chunk_sectors;
+		int new_data_disks;
 
 		if (mddev->new_level != mddev->level) {
 			printk(KERN_ERR "md/raid:%s: unsupported reshape "
@@ -6694,28 +6705,25 @@ static int run(struct mddev *mddev)
 		/* reshape_position must be on a new-stripe boundary, and one
 		 * further up in new geometry must map after here in old
 		 * geometry.
+		 * If the chunk sizes are different, then as we perform reshape
+		 * in units of the largest of the two, reshape_position needs
+		 * be a multiple of the largest chunk size times new data disks.
 		 */
 		here_new = mddev->reshape_position;
-		if (sector_div(here_new, mddev->new_chunk_sectors *
-			       (mddev->raid_disks - max_degraded))) {
+		chunk_sectors = max(mddev->chunk_sectors, mddev->new_chunk_sectors);
+		new_data_disks = mddev->raid_disks - max_degraded;
+		if (sector_div(here_new, chunk_sectors * new_data_disks)) {
 			printk(KERN_ERR "md/raid:%s: reshape_position not "
 			       "on a stripe boundary\n", mdname(mddev));
 			return -EINVAL;
 		}
-		reshape_offset = here_new * mddev->new_chunk_sectors;
+		reshape_offset = here_new * chunk_sectors;
 		/* here_new is the stripe we will write to */
 		here_old = mddev->reshape_position;
-		sector_div(here_old, mddev->chunk_sectors *
-			   (old_disks-max_degraded));
+		sector_div(here_old, chunk_sectors * (old_disks-max_degraded));
 		/* here_old is the first stripe that we might need to read
 		 * from */
 		if (mddev->delta_disks == 0) {
-			if ((here_new * mddev->new_chunk_sectors !=
-			     here_old * mddev->chunk_sectors)) {
-				printk(KERN_ERR "md/raid:%s: reshape position is"
-				       " confused - aborting\n", mdname(mddev));
-				return -EINVAL;
-			}
 			/* We cannot be sure it is safe to start an in-place
 			 * reshape.  It is only safe if user-space is monitoring
 			 * and taking constant backups.
@@ -6734,10 +6742,10 @@ static int run(struct mddev *mddev)
 				return -EINVAL;
 			}
 		} else if (mddev->reshape_backwards
-		    ? (here_new * mddev->new_chunk_sectors + min_offset_diff <=
-		       here_old * mddev->chunk_sectors)
-		    : (here_new * mddev->new_chunk_sectors >=
-		       here_old * mddev->chunk_sectors + (-min_offset_diff))) {
+		    ? (here_new * chunk_sectors + min_offset_diff <=
+		       here_old * chunk_sectors)
+		    : (here_new * chunk_sectors >=
+		       here_old * chunk_sectors + (-min_offset_diff))) {
 			/* Reading from the same stripe as writing to - bad */
 			printk(KERN_ERR "md/raid:%s: reshape_position too early for "
 			       "auto-recovery - aborting.\n",
@@ -6989,7 +6997,7 @@ static void status(struct seq_file *seq, struct mddev *mddev)
 	int i;
 
 	seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
-		mddev->chunk_sectors / 2, mddev->layout);
+		conf->chunk_sectors / 2, mddev->layout);
 	seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded);
 	for (i = 0; i < conf->raid_disks; i++)
 		seq_printf (seq, "%s",
@@ -7195,7 +7203,9 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors)
 	 * worth it.
 	 */
 	sector_t newsize;
-	sectors &= ~((sector_t)mddev->chunk_sectors - 1);
+	struct r5conf *conf = mddev->private;
+
+	sectors &= ~((sector_t)conf->chunk_sectors - 1);
 	newsize = raid5_size(mddev, sectors, mddev->raid_disks);
 	if (mddev->external_size &&
 	    mddev->array_sectors > newsize)
@@ -7434,6 +7444,7 @@ static void end_reshape(struct r5conf *conf)
 			rdev->data_offset = rdev->new_data_offset;
 		smp_wmb();
 		conf->reshape_progress = MaxSector;
+		conf->mddev->reshape_position = MaxSector;
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 
@@ -7779,7 +7790,6 @@ static struct md_personality raid6_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.congested	= raid5_congested,
-	.mergeable_bvec	= raid5_mergeable_bvec,
 };
 static struct md_personality raid5_personality =
 {
@@ -7803,7 +7813,6 @@ static struct md_personality raid5_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.congested	= raid5_congested,
-	.mergeable_bvec	= raid5_mergeable_bvec,
 };
 
 static struct md_personality raid4_personality =
@@ -7828,7 +7837,6 @@ static struct md_personality raid4_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.congested	= raid5_congested,
-	.mergeable_bvec	= raid5_mergeable_bvec,
 };
 
 static int __init raid5_init(void)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index d05144278..828c2925e 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -265,7 +265,7 @@ struct stripe_head_state {
 	int dec_preread_active;
 	unsigned long ops_request;
 
-	struct bio *return_bi;
+	struct bio_list return_bi;
 	struct md_rdev *blocked_rdev;
 	int handle_bad_blocks;
 };
@@ -476,6 +476,9 @@ struct r5conf {
 	int			skip_copy; /* Don't copy data from bio to stripe cache */
 	struct list_head	*last_hold; /* detect hold_list promotions */
 
+	/* bios to have bi_end_io called after metadata is synced */
+	struct bio_list		return_bi;
+
 	atomic_t		reshape_stripes; /* stripes with pending writes for reshape */
 	/* unfortunately we need two cache names as we temporarily have
 	 * two caches.