Merge tag 'dm-3.7-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-dm

Pull device-mapper changes from Alasdair G Kergon:
 "Remove the power-of-2 block size constraint on discards in dm thin
  provisioning and factor the bio_prison code out into a separate module
  (for sharing with the forthcoming cache target).

  Use struct bio's front_pad to eliminate the use of one separate
  mempool by bio-based devices.

  A few other tiny clean-ups."

* tag 'dm-3.7-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-dm:
  dm: store dm_target_io in bio front_pad
  dm thin: move bio_prison code to separate module
  dm thin: prepare to separate bio_prison code
  dm thin: support discard with non power of two block size
  dm persistent data: convert to use le32_add_cpu
  dm: use ACCESS_ONCE for sysfs values
  dm bufio: use list_move
  dm mpath: fix check for null mpio in end_io fn

drivers/md/Kconfig

@@ -216,6 +216,13 @@ config DM_BUFIO
 	 as a cache, holding recently-read blocks in memory and performing
 	 delayed writes.
 
+config DM_BIO_PRISON
+       tristate
+       depends on BLK_DEV_DM && EXPERIMENTAL
+       ---help---
+	 Some bio locking schemes used by other device-mapper targets
+	 including thin provisioning.
+
 source "drivers/md/persistent-data/Kconfig"
 
 config DM_CRYPT
@@ -247,6 +254,7 @@ config DM_THIN_PROVISIONING
        tristate "Thin provisioning target (EXPERIMENTAL)"
        depends on BLK_DEV_DM && EXPERIMENTAL
        select DM_PERSISTENT_DATA
+       select DM_BIO_PRISON
        ---help---
          Provides thin provisioning and snapshots that share a data store.
 

drivers/md/Makefile

@@ -29,6 +29,7 @@ obj-$(CONFIG_MD_FAULTY)		+= faulty.o
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
 obj-$(CONFIG_BLK_DEV_DM)	+= dm-mod.o
 obj-$(CONFIG_DM_BUFIO)		+= dm-bufio.o
+obj-$(CONFIG_DM_BIO_PRISON)	+= dm-bio-prison.o
 obj-$(CONFIG_DM_CRYPT)		+= dm-crypt.o
 obj-$(CONFIG_DM_DELAY)		+= dm-delay.o
 obj-$(CONFIG_DM_FLAKEY)		+= dm-flakey.o

drivers/md/dm-bio-prison.h

+/*
+ * Copyright (C) 2011-2012 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_BIO_PRISON_H
+#define DM_BIO_PRISON_H
+
+#include "persistent-data/dm-block-manager.h" /* FIXME: for dm_block_t */
+#include "dm-thin-metadata.h" /* FIXME: for dm_thin_id */
+
+#include <linux/list.h>
+#include <linux/bio.h>
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Sometimes we can't deal with a bio straight away.  We put them in prison
+ * where they can't cause any mischief.  Bios are put in a cell identified
+ * by a key, multiple bios can be in the same cell.  When the cell is
+ * subsequently unlocked the bios become available.
+ */
+struct dm_bio_prison;
+struct dm_bio_prison_cell;
+
+/* FIXME: this needs to be more abstract */
+struct dm_cell_key {
+	int virtual;
+	dm_thin_id dev;
+	dm_block_t block;
+};
+
+struct dm_bio_prison *dm_bio_prison_create(unsigned nr_cells);
+void dm_bio_prison_destroy(struct dm_bio_prison *prison);
+
+/*
+ * This may block if a new cell needs allocating.  You must ensure that
+ * cells will be unlocked even if the calling thread is blocked.
+ *
+ * Returns 1 if the cell was already held, 0 if @inmate is the new holder.
+ */
+int dm_bio_detain(struct dm_bio_prison *prison, struct dm_cell_key *key,
+		  struct bio *inmate, struct dm_bio_prison_cell **ref);
+
+void dm_cell_release(struct dm_bio_prison_cell *cell, struct bio_list *bios);
+void dm_cell_release_singleton(struct dm_bio_prison_cell *cell, struct bio *bio); // FIXME: bio arg not needed
+void dm_cell_release_no_holder(struct dm_bio_prison_cell *cell, struct bio_list *inmates);
+void dm_cell_error(struct dm_bio_prison_cell *cell);
+
+/*----------------------------------------------------------------*/
+
+/*
+ * We use the deferred set to keep track of pending reads to shared blocks.
+ * We do this to ensure the new mapping caused by a write isn't performed
+ * until these prior reads have completed.  Otherwise the insertion of the
+ * new mapping could free the old block that the read bios are mapped to.
+ */
+
+struct dm_deferred_set;
+struct dm_deferred_entry;
+
+struct dm_deferred_set *dm_deferred_set_create(void);
+void dm_deferred_set_destroy(struct dm_deferred_set *ds);
+
+struct dm_deferred_entry *dm_deferred_entry_inc(struct dm_deferred_set *ds);
+void dm_deferred_entry_dec(struct dm_deferred_entry *entry, struct list_head *head);
+int dm_deferred_set_add_work(struct dm_deferred_set *ds, struct list_head *work);
+
+/*----------------------------------------------------------------*/
+
+#endif

drivers/md/dm-bufio.c

@@ -280,9 +280,7 @@ static void __cache_size_refresh(void)
 	BUG_ON(!mutex_is_locked(&dm_bufio_clients_lock));
 	BUG_ON(dm_bufio_client_count < 0);
 
-	dm_bufio_cache_size_latch = dm_bufio_cache_size;
-
-	barrier();
+	dm_bufio_cache_size_latch = ACCESS_ONCE(dm_bufio_cache_size);
 
 	/*
 	 * Use default if set to 0 and report the actual cache size used.
@@ -441,8 +439,7 @@ static void __relink_lru(struct dm_buffer *b, int dirty)
 	c->n_buffers[b->list_mode]--;
 	c->n_buffers[dirty]++;
 	b->list_mode = dirty;
-	list_del(&b->lru_list);
-	list_add(&b->lru_list, &c->lru[dirty]);
+	list_move(&b->lru_list, &c->lru[dirty]);
 }
 
 /*----------------------------------------------------------------
@@ -813,7 +810,7 @@ static void __get_memory_limit(struct dm_bufio_client *c,
 {
 	unsigned long buffers;
 
-	if (dm_bufio_cache_size != dm_bufio_cache_size_latch) {
+	if (ACCESS_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch) {
 		mutex_lock(&dm_bufio_clients_lock);
 		__cache_size_refresh();
 		mutex_unlock(&dm_bufio_clients_lock);
@@ -1591,11 +1588,9 @@ EXPORT_SYMBOL_GPL(dm_bufio_client_destroy);
 
 static void cleanup_old_buffers(void)
 {
-	unsigned long max_age = dm_bufio_max_age;
+	unsigned long max_age = ACCESS_ONCE(dm_bufio_max_age);
 	struct dm_bufio_client *c;
 
-	barrier();
-
 	if (max_age > ULONG_MAX / HZ)
 		max_age = ULONG_MAX / HZ;
 

drivers/md/dm-mpath.c

@@ -1309,13 +1309,14 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 {
 	struct multipath *m = ti->private;
 	struct dm_mpath_io *mpio = map_context->ptr;
-	struct pgpath *pgpath = mpio->pgpath;
+	struct pgpath *pgpath;
 	struct path_selector *ps;
 	int r;
 
 	BUG_ON(!mpio);
 
 	r  = do_end_io(m, clone, error, mpio);
+	pgpath = mpio->pgpath;
 	if (pgpath) {
 		ps = &pgpath->pg->ps;
 		if (ps->type->end_io)

drivers/md/dm-verity.c

@@ -438,7 +438,7 @@ static void verity_prefetch_io(struct dm_verity *v, struct dm_verity_io *io)
 		verity_hash_at_level(v, io->block, i, &hash_block_start, NULL);
 		verity_hash_at_level(v, io->block + io->n_blocks - 1, i, &hash_block_end, NULL);
 		if (!i) {
-			unsigned cluster = *(volatile unsigned *)&dm_verity_prefetch_cluster;
+			unsigned cluster = ACCESS_ONCE(dm_verity_prefetch_cluster);
 
 			cluster >>= v->data_dev_block_bits;
 			if (unlikely(!cluster))

drivers/md/dm.c

@@ -71,6 +71,7 @@ struct dm_target_io {
 	struct dm_io *io;
 	struct dm_target *ti;
 	union map_info info;
+	struct bio clone;
 };
 
 /*
@@ -214,7 +215,6 @@ struct dm_md_mempools {
 
 #define MIN_IOS 256
 static struct kmem_cache *_io_cache;
-static struct kmem_cache *_tio_cache;
 static struct kmem_cache *_rq_tio_cache;
 
 /*
@@ -232,14 +232,9 @@ static int __init local_init(void)
 	if (!_io_cache)
 		return r;
 
-	/* allocate a slab for the target ios */
-	_tio_cache = KMEM_CACHE(dm_target_io, 0);
-	if (!_tio_cache)
-		goto out_free_io_cache;
-
 	_rq_tio_cache = KMEM_CACHE(dm_rq_target_io, 0);
 	if (!_rq_tio_cache)
-		goto out_free_tio_cache;
+		goto out_free_io_cache;
 
 	_rq_bio_info_cache = KMEM_CACHE(dm_rq_clone_bio_info, 0);
 	if (!_rq_bio_info_cache)
@@ -265,8 +260,6 @@ static int __init local_init(void)
 	kmem_cache_destroy(_rq_bio_info_cache);
 out_free_rq_tio_cache:
 	kmem_cache_destroy(_rq_tio_cache);
-out_free_tio_cache:
-	kmem_cache_destroy(_tio_cache);
 out_free_io_cache:
 	kmem_cache_destroy(_io_cache);
 
@@ -277,7 +270,6 @@ static void local_exit(void)
 {
 	kmem_cache_destroy(_rq_bio_info_cache);
 	kmem_cache_destroy(_rq_tio_cache);
-	kmem_cache_destroy(_tio_cache);
 	kmem_cache_destroy(_io_cache);
 	unregister_blkdev(_major, _name);
 	dm_uevent_exit();
@@ -463,7 +455,7 @@ static void free_io(struct mapped_device *md, struct dm_io *io)
 
 static void free_tio(struct mapped_device *md, struct dm_target_io *tio)
 {
-	mempool_free(tio, md->tio_pool);
+	bio_put(&tio->clone);
 }
 
 static struct dm_rq_target_io *alloc_rq_tio(struct mapped_device *md,
@@ -682,7 +674,6 @@ static void clone_endio(struct bio *bio, int error)
 	}
 
 	free_tio(md, tio);
-	bio_put(bio);
 	dec_pending(io, error);
 }
 
@@ -1002,12 +993,12 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
 }
 EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
 
-static void __map_bio(struct dm_target *ti, struct bio *clone,
-		      struct dm_target_io *tio)
+static void __map_bio(struct dm_target *ti, struct dm_target_io *tio)
 {
 	int r;
 	sector_t sector;
 	struct mapped_device *md;
+	struct bio *clone = &tio->clone;
 
 	clone->bi_end_io = clone_endio;
 	clone->bi_private = tio;
@@ -1031,7 +1022,6 @@ static void __map_bio(struct dm_target *ti, struct bio *clone,
 		/* error the io and bail out, or requeue it if needed */
 		md = tio->io->md;
 		dec_pending(tio->io, r);
-		bio_put(clone);
 		free_tio(md, tio);
 	} else if (r) {
 		DMWARN("unimplemented target map return value: %d", r);
@@ -1052,14 +1042,13 @@ struct clone_info {
 /*
  * Creates a little bio that just does part of a bvec.
  */
-static struct bio *split_bvec(struct bio *bio, sector_t sector,
-			      unsigned short idx, unsigned int offset,
+static void split_bvec(struct dm_target_io *tio, struct bio *bio,
+		       sector_t sector, unsigned short idx, unsigned int offset,
 		       unsigned int len, struct bio_set *bs)
 {
-	struct bio *clone;
+	struct bio *clone = &tio->clone;
 	struct bio_vec *bv = bio->bi_io_vec + idx;
 
-	clone = bio_alloc_bioset(GFP_NOIO, 1, bs);
 	*clone->bi_io_vec = *bv;
 
 	clone->bi_sector = sector;
@@ -1076,20 +1065,18 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector,
 		bio_integrity_trim(clone,
 				   bio_sector_offset(bio, idx, offset), len);
 	}
-
-	return clone;
 }
 
 /*
  * Creates a bio that consists of range of complete bvecs.
  */
-static struct bio *clone_bio(struct bio *bio, sector_t sector,
-			     unsigned short idx, unsigned short bv_count,
-			     unsigned int len, struct bio_set *bs)
+static void clone_bio(struct dm_target_io *tio, struct bio *bio,
+		      sector_t sector, unsigned short idx,
+		      unsigned short bv_count, unsigned int len,
+		      struct bio_set *bs)
 {
-	struct bio *clone;
+	struct bio *clone = &tio->clone;
 
-	clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs);
 	__bio_clone(clone, bio);
 	clone->bi_sector = sector;
 	clone->bi_idx = idx;
@@ -1104,14 +1091,16 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector,
 			bio_integrity_trim(clone,
 					   bio_sector_offset(bio, idx, 0), len);
 	}
-
-	return clone;
 }
 
 static struct dm_target_io *alloc_tio(struct clone_info *ci,
-				      struct dm_target *ti)
+				      struct dm_target *ti, int nr_iovecs)
 {
-	struct dm_target_io *tio = mempool_alloc(ci->md->tio_pool, GFP_NOIO);
+	struct dm_target_io *tio;
+	struct bio *clone;
+
+	clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, ci->md->bs);
+	tio = container_of(clone, struct dm_target_io, clone);
 
 	tio->io = ci->io;
 	tio->ti = ti;
@@ -1123,8 +1112,8 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci,
 static void __issue_target_request(struct clone_info *ci, struct dm_target *ti,
 				   unsigned request_nr, sector_t len)
 {
-	struct dm_target_io *tio = alloc_tio(ci, ti);
-	struct bio *clone;
+	struct dm_target_io *tio = alloc_tio(ci, ti, ci->bio->bi_max_vecs);
+	struct bio *clone = &tio->clone;
 
 	tio->info.target_request_nr = request_nr;
 
@@ -1133,14 +1122,14 @@ static void __issue_target_request(struct clone_info *ci, struct dm_target *ti,
 	 * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
 	 * and discard, so no need for concern about wasted bvec allocations.
 	 */
-	clone = bio_clone_bioset(ci->bio, GFP_NOIO, ci->md->bs);
 
+	 __bio_clone(clone, ci->bio);
 	if (len) {
 		clone->bi_sector = ci->sector;
 		clone->bi_size = to_bytes(len);
 	}
 
-	__map_bio(ti, clone, tio);
+	__map_bio(ti, tio);
 }
 
 static void __issue_target_requests(struct clone_info *ci, struct dm_target *ti,
@@ -1169,14 +1158,13 @@ static int __clone_and_map_empty_flush(struct clone_info *ci)
  */
 static void __clone_and_map_simple(struct clone_info *ci, struct dm_target *ti)
 {
-	struct bio *clone, *bio = ci->bio;
+	struct bio *bio = ci->bio;
 	struct dm_target_io *tio;
 
-	tio = alloc_tio(ci, ti);
-	clone = clone_bio(bio, ci->sector, ci->idx,
-			  bio->bi_vcnt - ci->idx, ci->sector_count,
-			  ci->md->bs);
-	__map_bio(ti, clone, tio);
+	tio = alloc_tio(ci, ti, bio->bi_max_vecs);
+	clone_bio(tio, bio, ci->sector, ci->idx, bio->bi_vcnt - ci->idx,
+		  ci->sector_count, ci->md->bs);
+	__map_bio(ti, tio);
 	ci->sector_count = 0;
 }
 
@@ -1214,7 +1202,7 @@ static int __clone_and_map_discard(struct clone_info *ci)
 
 static int __clone_and_map(struct clone_info *ci)
 {
-	struct bio *clone, *bio = ci->bio;
+	struct bio *bio = ci->bio;
 	struct dm_target *ti;
 	sector_t len = 0, max;
 	struct dm_target_io *tio;
@@ -1254,10 +1242,10 @@ static int __clone_and_map(struct clone_info *ci)
 			len += bv_len;
 		}
 
-		tio = alloc_tio(ci, ti);
-		clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len,
+		tio = alloc_tio(ci, ti, bio->bi_max_vecs);
+		clone_bio(tio, bio, ci->sector, ci->idx, i - ci->idx, len,
 			  ci->md->bs);
-		__map_bio(ti, clone, tio);
+		__map_bio(ti, tio);
 
 		ci->sector += len;
 		ci->sector_count -= len;
@@ -1282,12 +1270,11 @@ static int __clone_and_map(struct clone_info *ci)
 
 			len = min(remaining, max);
 
-			tio = alloc_tio(ci, ti);
-			clone = split_bvec(bio, ci->sector, ci->idx,
-					   bv->bv_offset + offset, len,
-					   ci->md->bs);
+			tio = alloc_tio(ci, ti, 1);
+			split_bvec(tio, bio, ci->sector, ci->idx,
+				   bv->bv_offset + offset, len, ci->md->bs);
 
-			__map_bio(ti, clone, tio);
+			__map_bio(ti, tio);
 
 			ci->sector += len;
 			ci->sector_count -= len;
@@ -1955,7 +1942,7 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 {
 	struct dm_md_mempools *p;
 
-	if (md->io_pool && md->tio_pool && md->bs)
+	if (md->io_pool && (md->tio_pool || dm_table_get_type(t) == DM_TYPE_BIO_BASED) && md->bs)
 		/* the md already has necessary mempools */
 		goto out;
 
@@ -2732,14 +2719,16 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity)
 	if (!pools->io_pool)
 		goto free_pools_and_out;
 
-	pools->tio_pool = (type == DM_TYPE_BIO_BASED) ?
-			  mempool_create_slab_pool(MIN_IOS, _tio_cache) :
-			  mempool_create_slab_pool(MIN_IOS, _rq_tio_cache);
+	pools->tio_pool = NULL;
+	if (type == DM_TYPE_REQUEST_BASED) {
+		pools->tio_pool = mempool_create_slab_pool(MIN_IOS, _rq_tio_cache);
 		if (!pools->tio_pool)
 			goto free_io_pool_and_out;
+	}
 
 	pools->bs = (type == DM_TYPE_BIO_BASED) ?
-		bioset_create(pool_size, 0) :
+		bioset_create(pool_size,
+			      offsetof(struct dm_target_io, clone)) :
 		bioset_create(pool_size,
 			      offsetof(struct dm_rq_clone_bio_info, clone));
 	if (!pools->bs)
@@ -2754,6 +2743,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity)
 	bioset_free(pools->bs);
 
 free_tio_pool_and_out:
+	if (pools->tio_pool)
 		mempool_destroy(pools->tio_pool);
 
 free_io_pool_and_out:

drivers/md/persistent-data/dm-space-map-common.c

@@ -434,14 +434,14 @@ int sm_ll_insert(struct ll_disk *ll, dm_block_t b,
 	if (ref_count && !old) {
 		*ev = SM_ALLOC;
 		ll->nr_allocated++;
-		ie_disk.nr_free = cpu_to_le32(le32_to_cpu(ie_disk.nr_free) - 1);
+		le32_add_cpu(&ie_disk.nr_free, -1);
 		if (le32_to_cpu(ie_disk.none_free_before) == bit)
 			ie_disk.none_free_before = cpu_to_le32(bit + 1);
 
 	} else if (old && !ref_count) {
 		*ev = SM_FREE;
 		ll->nr_allocated--;
-		ie_disk.nr_free = cpu_to_le32(le32_to_cpu(ie_disk.nr_free) + 1);
+		le32_add_cpu(&ie_disk.nr_free, 1);
 		ie_disk.none_free_before = cpu_to_le32(min(le32_to_cpu(ie_disk.none_free_before), bit));
 	}