Merge branch 'for-4.2/core' of git://git.kernel.dk/linux-block

Pull core block IO update from Jens Axboe:
 "Nothing really major in here, mostly a collection of smaller
  optimizations and cleanups, mixed with various fixes.  In more detail,
  this contains:

   - Addition of policy specific data to blkcg for block cgroups.  From
     Arianna Avanzini.

   - Various cleanups around command types from Christoph.

   - Cleanup of the suspend block I/O path from Christoph.

   - Plugging updates from Shaohua and Jeff Moyer, for blk-mq.

   - Eliminating atomic inc/dec of both remaining IO count and reference
     count in a bio.  From me.

   - Fixes for SG gap and chunk size support for data-less (discards)
     IO, so we can merge these better.  From me.

   - Small restructuring of blk-mq shared tag support, freeing drivers
     from iterating hardware queues.  From Keith Busch.

   - A few cfq-iosched tweaks, from Tahsin Erdogan and me.  Makes the
     IOPS mode the default for non-rotational storage"

* 'for-4.2/core' of git://git.kernel.dk/linux-block: (35 commits)
  cfq-iosched: fix other locations where blkcg_to_cfqgd() can return NULL
  cfq-iosched: fix sysfs oops when attempting to read unconfigured weights
  cfq-iosched: move group scheduling functions under ifdef
  cfq-iosched: fix the setting of IOPS mode on SSDs
  blktrace: Add blktrace.c to BLOCK LAYER in MAINTAINERS file
  block, cgroup: implement policy-specific per-blkcg data
  block: Make CFQ default to IOPS mode on SSDs
  block: add blk_set_queue_dying() to blkdev.h
  blk-mq: Shared tag enhancements
  block: don't honor chunk sizes for data-less IO
  block: only honor SG gap prevention for merges that contain data
  block: fix returnvar.cocci warnings
  block, dm: don't copy bios for request clones
  block: remove management of bi_remaining when restoring original bi_end_io
  block: replace trylock with mutex_lock in blkdev_reread_part()
  block: export blkdev_reread_part() and __blkdev_reread_part()
  suspend: simplify block I/O handling
  block: collapse bio bit space
  block: remove unused BIO_RW_BLOCK and BIO_EOF flags
  block: remove BIO_EOPNOTSUPP
  ...

10 files changed, 65 insertions, 160 deletions

diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index fa028fa82df4..cb64e64a4789 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -55,7 +55,7 @@ static void bch_bio_submit_split_done(struct closure *cl)
 
 	s->bio->bi_end_io = s->bi_end_io;
 	s->bio->bi_private = s->bi_private;
-	bio_endio_nodec(s->bio, 0);
+	bio_endio(s->bio, 0);
 
 	closure_debug_destroy(&s->cl);
 	mempool_free(s, s->p->bio_split_hook);
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index ab43faddb447..1616f668a4cb 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -619,7 +619,7 @@ static void do_bio_hook(struct search *s, struct bio *orig_bio)
 	bio->bi_end_io		= request_endio;
 	bio->bi_private		= &s->cl;
 
-	atomic_set(&bio->bi_cnt, 3);
+	bio_cnt_set(bio, 3);
 }
 
 static void search_free(struct closure *cl)
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 7755af351867..41b2594a80c6 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -86,12 +86,6 @@ static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio)
 {
 	bio->bi_end_io = h->bi_end_io;
 	bio->bi_private = h->bi_private;
-
-	/*
-	 * Must bump bi_remaining to allow bio to complete with
-	 * restored bi_end_io.
-	 */
-	atomic_inc(&bio->bi_remaining);
 }
 
 /*----------------------------------------------------------------*/
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 089d62751f7f..743fa9bbae9e 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1254,8 +1254,6 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 			dm_bio_restore(bd, bio);
 			bio_record->details.bi_bdev = NULL;
 
-			atomic_inc(&bio->bi_remaining);
-
 			queue_bio(ms, bio, rw);
 			return DM_ENDIO_INCOMPLETE;
 		}
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index f83a0f3fc365..7c82d3ccce87 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1478,7 +1478,6 @@ out:
 	if (full_bio) {
 		full_bio->bi_end_io = pe->full_bio_end_io;
 		full_bio->bi_private = pe->full_bio_private;
-		atomic_inc(&full_bio->bi_remaining);
 	}
 	increment_pending_exceptions_done_count();
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 16ba55ad7089..a5f94125ad01 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -942,21 +942,28 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
 {
 	unsigned type = dm_table_get_type(t);
 	unsigned per_bio_data_size = 0;
-	struct dm_target *tgt;
 	unsigned i;
 
-	if (unlikely(type == DM_TYPE_NONE)) {
+	switch (type) {
+	case DM_TYPE_BIO_BASED:
+		for (i = 0; i < t->num_targets; i++) {
+			struct dm_target *tgt = t->targets + i;
+
+			per_bio_data_size = max(per_bio_data_size,
+						tgt->per_bio_data_size);
+		}
+		t->mempools = dm_alloc_bio_mempools(t->integrity_supported,
+						    per_bio_data_size);
+		break;
+	case DM_TYPE_REQUEST_BASED:
+	case DM_TYPE_MQ_REQUEST_BASED:
+		t->mempools = dm_alloc_rq_mempools(md, type);
+		break;
+	default:
 		DMWARN("no table type is set, can't allocate mempools");
 		return -EINVAL;
 	}
 
-	if (type == DM_TYPE_BIO_BASED)
-		for (i = 0; i < t->num_targets; i++) {
-			tgt = t->targets + i;
-			per_bio_data_size = max(per_bio_data_size, tgt->per_bio_data_size);
-		}
-
-	t->mempools = dm_alloc_md_mempools(md, type, t->integrity_supported, per_bio_data_size);
 	if (!t->mempools)
 		return -ENOMEM;
 
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 921aafd12aee..e852602c0091 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -793,10 +793,9 @@ static void inc_remap_and_issue_cell(struct thin_c *tc,
 
 static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m)
 {
-	if (m->bio) {
+	if (m->bio)
 		m->bio->bi_end_io = m->saved_bi_end_io;
-		atomic_inc(&m->bio->bi_remaining);
-	}
+
 	cell_error(m->tc->pool, m->cell);
 	list_del(&m->list);
 	mempool_free(m, m->tc->pool->mapping_pool);
@@ -810,10 +809,8 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 	int r;
 
 	bio = m->bio;
-	if (bio) {
+	if (bio)
 		bio->bi_end_io = m->saved_bi_end_io;
-		atomic_inc(&bio->bi_remaining);
-	}
 
 	if (m->err) {
 		cell_error(pool, m->cell);
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index 66616db33e6f..bb9c6a00e4b0 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -459,7 +459,7 @@ 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_endio_nodec(bio, error);
+	bio_endio(bio, error);
 }
 
 static void verity_work(struct work_struct *w)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 2caf492890d6..4d6f089a0e9e 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -990,57 +990,6 @@ static void clone_endio(struct bio *bio, int error)
 	dec_pending(io, error);
 }
 
-/*
- * Partial completion handling for request-based dm
- */
-static void end_clone_bio(struct bio *clone, int error)
-{
-	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;
-
-	bio_put(clone);
-
-	if (tio->error)
-		/*
-		 * An error has already been detected on the request.
-		 * Once error occurred, just let clone->end_io() handle
-		 * the remainder.
-		 */
-		return;
-	else if (error) {
-		/*
-		 * Don't notice the error to the upper layer yet.
-		 * The error handling decision is made by the target driver,
-		 * when the request is completed.
-		 */
-		tio->error = error;
-		return;
-	}
-
-	/*
-	 * I/O for the bio successfully completed.
-	 * Notice the data completion to the upper layer.
-	 */
-
-	/*
-	 * bios are processed from the head of the list.
-	 * So the completing bio should always be rq->bio.
-	 * If it's not, something wrong is happening.
-	 */
-	if (tio->orig->bio != bio)
-		DMERR("bio completion is going in the middle of the request");
-
-	/*
-	 * Update the original request.
-	 * Do not use blk_end_request() here, because it may complete
-	 * the original request before the clone, and break the ordering.
-	 */
-	blk_update_request(tio->orig, 0, nr_bytes);
-}
-
 static struct dm_rq_target_io *tio_from_request(struct request *rq)
 {
 	return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
@@ -1087,8 +1036,6 @@ static void free_rq_clone(struct request *clone)
 	struct dm_rq_target_io *tio = clone->end_io_data;
 	struct mapped_device *md = tio->md;
 
-	blk_rq_unprep_clone(clone);
-
 	if (md->type == DM_TYPE_MQ_REQUEST_BASED)
 		/* stacked on blk-mq queue(s) */
 		tio->ti->type->release_clone_rq(clone);
@@ -1827,39 +1774,13 @@ static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
 		dm_complete_request(rq, r);
 }
 
-static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
-				 void *data)
+static void setup_clone(struct request *clone, struct request *rq,
+		        struct dm_rq_target_io *tio)
 {
-	struct dm_rq_target_io *tio = data;
-	struct dm_rq_clone_bio_info *info =
-		container_of(bio, struct dm_rq_clone_bio_info, clone);
-
-	info->orig = bio_orig;
-	info->tio = tio;
-	bio->bi_end_io = end_clone_bio;
-
-	return 0;
-}
-
-static int setup_clone(struct request *clone, struct request *rq,
-		       struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
-	int r;
-
-	r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
-			      dm_rq_bio_constructor, tio);
-	if (r)
-		return r;
-
-	clone->cmd = rq->cmd;
-	clone->cmd_len = rq->cmd_len;
-	clone->sense = rq->sense;
+	blk_rq_prep_clone(clone, rq);
 	clone->end_io = end_clone_request;
 	clone->end_io_data = tio;
-
 	tio->clone = clone;
-
-	return 0;
 }
 
 static struct request *clone_rq(struct request *rq, struct mapped_device *md,
@@ -1880,12 +1801,7 @@ static struct request *clone_rq(struct request *rq, struct mapped_device *md,
 		clone = tio->clone;
 
 	blk_rq_init(NULL, clone);
-	if (setup_clone(clone, rq, tio, gfp_mask)) {
-		/* -ENOMEM */
-		if (alloc_clone)
-			free_clone_request(md, clone);
-		return NULL;
-	}
+	setup_clone(clone, rq, tio);
 
 	return clone;
 }
@@ -1979,11 +1895,7 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
 		}
 		if (r != DM_MAPIO_REMAPPED)
 			return r;
-		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
-			/* -ENOMEM */
-			ti->type->release_clone_rq(clone);
-			return DM_MAPIO_REQUEUE;
-		}
+		setup_clone(clone, rq, tio);
 	}
 
 	switch (r) {
@@ -2437,8 +2349,6 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 		goto out;
 	}
 
-	BUG_ON(!p || md->io_pool || md->rq_pool || md->bs);
-
 	md->io_pool = p->io_pool;
 	p->io_pool = NULL;
 	md->rq_pool = p->rq_pool;
@@ -3544,48 +3454,23 @@ int dm_noflush_suspending(struct dm_target *ti)
 }
 EXPORT_SYMBOL_GPL(dm_noflush_suspending);
 
-struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type,
-					    unsigned integrity, unsigned per_bio_data_size)
+struct dm_md_mempools *dm_alloc_bio_mempools(unsigned integrity,
+					     unsigned per_bio_data_size)
 {
-	struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL);
-	struct kmem_cache *cachep = NULL;
-	unsigned int pool_size = 0;
+	struct dm_md_mempools *pools;
+	unsigned int pool_size = dm_get_reserved_bio_based_ios();
 	unsigned int front_pad;
 
+	pools = kzalloc(sizeof(*pools), GFP_KERNEL);
 	if (!pools)
 		return NULL;
 
-	type = filter_md_type(type, md);
+	front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) +
+		offsetof(struct dm_target_io, clone);
 
-	switch (type) {
-	case DM_TYPE_BIO_BASED:
-		cachep = _io_cache;
-		pool_size = dm_get_reserved_bio_based_ios();
-		front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
-		break;
-	case DM_TYPE_REQUEST_BASED:
-		cachep = _rq_tio_cache;
-		pool_size = dm_get_reserved_rq_based_ios();
-		pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
-		if (!pools->rq_pool)
-			goto out;
-		/* fall through to setup remaining rq-based pools */
-	case DM_TYPE_MQ_REQUEST_BASED:
-		if (!pool_size)
-			pool_size = dm_get_reserved_rq_based_ios();
-		front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
-		/* per_bio_data_size is not used. See __bind_mempools(). */
-		WARN_ON(per_bio_data_size != 0);
-		break;
-	default:
-		BUG();
-	}
-
-	if (cachep) {
-		pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
-		if (!pools->io_pool)
-			goto out;
-	}
+	pools->io_pool = mempool_create_slab_pool(pool_size, _io_cache);
+	if (!pools->io_pool)
+		goto out;
 
 	pools->bs = bioset_create_nobvec(pool_size, front_pad);
 	if (!pools->bs)
@@ -3595,10 +3480,34 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 		goto out;
 
 	return pools;
-
 out:
 	dm_free_md_mempools(pools);
+	return NULL;
+}
+
+struct dm_md_mempools *dm_alloc_rq_mempools(struct mapped_device *md,
+					    unsigned type)
+{
+	unsigned int pool_size = dm_get_reserved_rq_based_ios();
+	struct dm_md_mempools *pools;
+
+	pools = kzalloc(sizeof(*pools), GFP_KERNEL);
+	if (!pools)
+		return NULL;
+
+	if (filter_md_type(type, md) == DM_TYPE_REQUEST_BASED) {
+		pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
+		if (!pools->rq_pool)
+			goto out;
+	}
 
+	pools->io_pool = mempool_create_slab_pool(pool_size, _rq_tio_cache);
+	if (!pools->io_pool)
+		goto out;
+
+	return pools;
+out:
+	dm_free_md_mempools(pools);
 	return NULL;
 }
 
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 6123c2bf9150..e6e66d087b26 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -222,8 +222,9 @@ void dm_kcopyd_exit(void);
 /*
  * Mempool operations
  */
-struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type,
-					    unsigned integrity, unsigned per_bio_data_size);
+struct dm_md_mempools *dm_alloc_bio_mempools(unsigned integrity,
+					     unsigned per_bio_data_size);
+struct dm_md_mempools *dm_alloc_rq_mempools(struct mapped_device *md, unsigned type);
 void dm_free_md_mempools(struct dm_md_mempools *pools);
 
 /*