Merge branch 'for-2.6.37/barrier' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.37/barrier' of git://git.kernel.dk/linux-2.6-block: (46 commits)
  xen-blkfront: disable barrier/flush write support
  Added blk-lib.c and blk-barrier.c was renamed to blk-flush.c
  block: remove BLKDEV_IFL_WAIT
  aic7xxx_old: removed unused 'req' variable
  block: remove the BH_Eopnotsupp flag
  block: remove the BLKDEV_IFL_BARRIER flag
  block: remove the WRITE_BARRIER flag
  swap: do not send discards as barriers
  fat: do not send discards as barriers
  ext4: do not send discards as barriers
  jbd2: replace barriers with explicit flush / FUA usage
  jbd2: Modify ASYNC_COMMIT code to not rely on queue draining on barrier
  jbd: replace barriers with explicit flush / FUA usage
  nilfs2: replace barriers with explicit flush / FUA usage
  reiserfs: replace barriers with explicit flush / FUA usage
  gfs2: replace barriers with explicit flush / FUA usage
  btrfs: replace barriers with explicit flush / FUA usage
  xfs: replace barriers with explicit flush / FUA usage
  block: pass gfp_mask and flags to sb_issue_discard
  dm: convey that all flushes are processed as empty
  ...

19 files changed, 226 insertions, 611 deletions

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 368e8e98f70..d5b0e4c0e70 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1278,7 +1278,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio,
 	struct dm_crypt_io *io;
 	struct crypt_config *cc;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		cc = ti->private;
 		bio->bi_bdev = cc->dev->bdev;
 		return DM_MAPIO_REMAPPED;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 0590c75b0ab..136d4f71a11 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -31,7 +31,6 @@ struct dm_io_client {
  */
 struct io {
 	unsigned long error_bits;
-	unsigned long eopnotsupp_bits;
 	atomic_t count;
 	struct task_struct *sleeper;
 	struct dm_io_client *client;
@@ -130,11 +129,8 @@ static void retrieve_io_and_region_from_bio(struct bio *bio, struct io **io,
  *---------------------------------------------------------------*/
 static void dec_count(struct io *io, unsigned int region, int error)
 {
-	if (error) {
+	if (error)
 		set_bit(region, &io->error_bits);
-		if (error == -EOPNOTSUPP)
-			set_bit(region, &io->eopnotsupp_bits);
-	}
 
 	if (atomic_dec_and_test(&io->count)) {
 		if (io->sleeper)
@@ -310,8 +306,8 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 	sector_t remaining = where->count;
 
 	/*
-	 * where->count may be zero if rw holds a write barrier and we
-	 * need to send a zero-sized barrier.
+	 * where->count may be zero if rw holds a flush and we need to
+	 * send a zero-sized flush.
 	 */
 	do {
 		/*
@@ -364,7 +360,7 @@ static void dispatch_io(int rw, unsigned int num_regions,
 	 */
 	for (i = 0; i < num_regions; i++) {
 		*dp = old_pages;
-		if (where[i].count || (rw & REQ_HARDBARRIER))
+		if (where[i].count || (rw & REQ_FLUSH))
 			do_region(rw, i, where + i, dp, io);
 	}
 
@@ -393,9 +389,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 		return -EIO;
 	}
 
-retry:
 	io->error_bits = 0;
-	io->eopnotsupp_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->sleeper = current;
 	io->client = client;
@@ -412,11 +406,6 @@ retry:
 	}
 	set_current_state(TASK_RUNNING);
 
-	if (io->eopnotsupp_bits && (rw & REQ_HARDBARRIER)) {
-		rw &= ~REQ_HARDBARRIER;
-		goto retry;
-	}
-
 	if (error_bits)
 		*error_bits = io->error_bits;
 
@@ -437,7 +426,6 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 
 	io = mempool_alloc(client->pool, GFP_NOIO);
 	io->error_bits = 0;
-	io->eopnotsupp_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->sleeper = NULL;
 	io->client = client;
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 5a08be0222d..33420e68d15 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -300,7 +300,7 @@ static int flush_header(struct log_c *lc)
 		.count = 0,
 	};
 
-	lc->io_req.bi_rw = WRITE_BARRIER;
+	lc->io_req.bi_rw = WRITE_FLUSH;
 
 	return dm_io(&lc->io_req, 1, &null_location, NULL);
 }
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 7c081bcbc3c..19a59b041c2 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -259,7 +259,7 @@ static int mirror_flush(struct dm_target *ti)
 	struct dm_io_region io[ms->nr_mirrors];
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE_BARRIER,
+		.bi_rw = WRITE_FLUSH,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.bvec = NULL,
 		.client = ms->io_client,
@@ -629,7 +629,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 	struct dm_io_region io[ms->nr_mirrors], *dest = io;
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE | (bio->bi_rw & WRITE_BARRIER),
+		.bi_rw = WRITE | (bio->bi_rw & WRITE_FLUSH_FUA),
 		.mem.type = DM_IO_BVEC,
 		.mem.ptr.bvec = bio->bi_io_vec + bio->bi_idx,
 		.notify.fn = write_callback,
@@ -670,7 +670,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	bio_list_init(&requeue);
 
 	while ((bio = bio_list_pop(writes))) {
-		if (unlikely(bio_empty_barrier(bio))) {
+		if (bio->bi_rw & REQ_FLUSH) {
 			bio_list_add(&sync, bio);
 			continue;
 		}
@@ -1203,7 +1203,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 	 * We need to dec pending if this was a write.
 	 */
 	if (rw == WRITE) {
-		if (likely(!bio_empty_barrier(bio)))
+		if (!(bio->bi_rw & REQ_FLUSH))
 			dm_rh_dec(ms->rh, map_context->ll);
 		return error;
 	}
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index bd5c58b2886..dad011aed0c 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -81,9 +81,9 @@ struct dm_region_hash {
 	struct list_head failed_recovered_regions;
 
 	/*
-	 * If there was a barrier failure no regions can be marked clean.
+	 * If there was a flush failure no regions can be marked clean.
 	 */
-	int barrier_failure;
+	int flush_failure;
 
 	void *context;
 	sector_t target_begin;
@@ -217,7 +217,7 @@ struct dm_region_hash *dm_region_hash_create(
 	INIT_LIST_HEAD(&rh->quiesced_regions);
 	INIT_LIST_HEAD(&rh->recovered_regions);
 	INIT_LIST_HEAD(&rh->failed_recovered_regions);
-	rh->barrier_failure = 0;
+	rh->flush_failure = 0;
 
 	rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS,
 						      sizeof(struct dm_region));
@@ -399,8 +399,8 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio)
 	region_t region = dm_rh_bio_to_region(rh, bio);
 	int recovering = 0;
 
-	if (bio_empty_barrier(bio)) {
-		rh->barrier_failure = 1;
+	if (bio->bi_rw & REQ_FLUSH) {
+		rh->flush_failure = 1;
 		return;
 	}
 
@@ -524,7 +524,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios)
 	struct bio *bio;
 
 	for (bio = bios->head; bio; bio = bio->bi_next) {
-		if (bio_empty_barrier(bio))
+		if (bio->bi_rw & REQ_FLUSH)
 			continue;
 		rh_inc(rh, dm_rh_bio_to_region(rh, bio));
 	}
@@ -555,9 +555,9 @@ void dm_rh_dec(struct dm_region_hash *rh, region_t region)
 		 */
 
 		/* do nothing for DM_RH_NOSYNC */
-		if (unlikely(rh->barrier_failure)) {
+		if (unlikely(rh->flush_failure)) {
 			/*
-			 * If a write barrier failed some time ago, we
+			 * If a write flush failed some time ago, we
 			 * don't know whether or not this write made it
 			 * to the disk, so we must resync the device.
 			 */
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index cc2bdb83f9a..0b61792a278 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -687,7 +687,7 @@ static void persistent_commit_exception(struct dm_exception_store *store,
 	/*
 	 * Commit exceptions to disk.
 	 */
-	if (ps->valid && area_io(ps, WRITE_BARRIER))
+	if (ps->valid && area_io(ps, WRITE_FLUSH_FUA))
 		ps->valid = 0;
 
 	/*
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index f30f6e8d594..53cf79d8bcb 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1585,7 +1585,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio,
 	chunk_t chunk;
 	struct dm_snap_pending_exception *pe = NULL;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		bio->bi_bdev = s->cow->bdev;
 		return DM_MAPIO_REMAPPED;
 	}
@@ -1689,7 +1689,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio,
 	int r = DM_MAPIO_REMAPPED;
 	chunk_t chunk;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		if (!map_context->target_request_nr)
 			bio->bi_bdev = s->origin->bdev;
 		else
@@ -2133,7 +2133,7 @@ static int origin_map(struct dm_target *ti, struct bio *bio,
 	struct dm_dev *dev = ti->private;
 	bio->bi_bdev = dev->bdev;
 
-	if (unlikely(bio_empty_barrier(bio)))
+	if (bio->bi_rw & REQ_FLUSH)
 		return DM_MAPIO_REMAPPED;
 
 	/* Only tell snapshots if this is a write */
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index c297f6da91e..f0371b4c4fb 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -271,7 +271,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio,
 	uint32_t stripe;
 	unsigned target_request_nr;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		target_request_nr = map_context->target_request_nr;
 		BUG_ON(target_request_nr >= sc->stripes);
 		bio->bi_bdev = sc->stripe[target_request_nr].dev->bdev;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 7967eca5a2d..7cb1352f7e7 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -110,7 +110,6 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
 #define DMF_FREEING 3
 #define DMF_DELETING 4
 #define DMF_NOFLUSH_SUSPENDING 5
-#define DMF_QUEUE_IO_TO_THREAD 6
 
 /*
  * Work processed by per-device workqueue.
@@ -144,24 +143,9 @@ struct mapped_device {
 	spinlock_t deferred_lock;
 
 	/*
-	 * An error from the barrier request currently being processed.
-	 */
-	int barrier_error;
-
-	/*
-	 * Protect barrier_error from concurrent endio processing
-	 * in request-based dm.
-	 */
-	spinlock_t barrier_error_lock;
-
-	/*
-	 * Processing queue (flush/barriers)
+	 * Processing queue (flush)
 	 */
 	struct workqueue_struct *wq;
-	struct work_struct barrier_work;
-
-	/* A pointer to the currently processing pre/post flush request */
-	struct request *flush_request;
 
 	/*
 	 * The current mapping.
@@ -200,8 +184,8 @@ struct mapped_device {
 	/* sysfs handle */
 	struct kobject kobj;
 
-	/* zero-length barrier that will be cloned and submitted to targets */
-	struct bio barrier_bio;
+	/* zero-length flush that will be cloned and submitted to targets */
+	struct bio flush_bio;
 };
 
 /*
@@ -512,7 +496,7 @@ static void end_io_acct(struct dm_io *io)
 
 	/*
 	 * After this is decremented the bio must not be touched if it is
-	 * a barrier.
+	 * a flush.
 	 */
 	dm_disk(md)->part0.in_flight[rw] = pending =
 		atomic_dec_return(&md->pending[rw]);
@@ -528,16 +512,12 @@ static void end_io_acct(struct dm_io *io)
  */
 static void queue_io(struct mapped_device *md, struct bio *bio)
 {
-	down_write(&md->io_lock);
+	unsigned long flags;
 
-	spin_lock_irq(&md->deferred_lock);
+	spin_lock_irqsave(&md->deferred_lock, flags);
 	bio_list_add(&md->deferred, bio);
-	spin_unlock_irq(&md->deferred_lock);
-
-	if (!test_and_set_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags))
-		queue_work(md->wq, &md->work);
-
-	up_write(&md->io_lock);
+	spin_unlock_irqrestore(&md->deferred_lock, flags);
+	queue_work(md->wq, &md->work);
 }
 
 /*
@@ -625,11 +605,9 @@ static void dec_pending(struct dm_io *io, int error)
 			 * Target requested pushing back the I/O.
 			 */
 			spin_lock_irqsave(&md->deferred_lock, flags);
-			if (__noflush_suspending(md)) {
-				if (!(io->bio->bi_rw & REQ_HARDBARRIER))
-					bio_list_add_head(&md->deferred,
-							  io->bio);
-			} else
+			if (__noflush_suspending(md))
+				bio_list_add_head(&md->deferred, io->bio);
+			else
 				/* noflush suspend was interrupted. */
 				io->error = -EIO;
 			spin_unlock_irqrestore(&md->deferred_lock, flags);
@@ -637,32 +615,23 @@ static void dec_pending(struct dm_io *io, int error)
 
 		io_error = io->error;
 		bio = io->bio;
+		end_io_acct(io);
+		free_io(md, io);
+
+		if (io_error == DM_ENDIO_REQUEUE)
+			return;
 
-		if (bio->bi_rw & REQ_HARDBARRIER) {
+		if ((bio->bi_rw & REQ_FLUSH) && bio->bi_size) {
 			/*
-			 * There can be just one barrier request so we use
-			 * a per-device variable for error reporting.
-			 * Note that you can't touch the bio after end_io_acct
-			 *
-			 * We ignore -EOPNOTSUPP for empty flush reported by
-			 * underlying devices. We assume that if the device
-			 * doesn't support empty barriers, it doesn't need
-			 * cache flushing commands.
+			 * Preflush done for flush with data, reissue
+			 * without REQ_FLUSH.
 			 */
-			if (!md->barrier_error &&
-			    !(bio_empty_barrier(bio) && io_error == -EOPNOTSUPP))
-				md->barrier_error = io_error;
-			end_io_acct(io);
-			free_io(md, io);
+			bio->bi_rw &= ~REQ_FLUSH;
+			queue_io(md, bio);
 		} else {
-			end_io_acct(io);
-			free_io(md, io);
-
-			if (io_error != DM_ENDIO_REQUEUE) {
-				trace_block_bio_complete(md->queue, bio);
-
-				bio_endio(bio, io_error);
-			}
+			/* done with normal IO or empty flush */
+			trace_block_bio_complete(md->queue, bio);
+			bio_endio(bio, io_error);
 		}
 	}
 }
@@ -755,23 +724,6 @@ static void end_clone_bio(struct bio *clone, int error)
 	blk_update_request(tio->orig, 0, nr_bytes);
 }
 
-static void store_barrier_error(struct mapped_device *md, int error)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&md->barrier_error_lock, flags);
-	/*
-	 * Basically, the first error is taken, but:
-	 *   -EOPNOTSUPP supersedes any I/O error.
-	 *   Requeue request supersedes any I/O error but -EOPNOTSUPP.
-	 */
-	if (!md->barrier_error || error == -EOPNOTSUPP ||
-	    (md->barrier_error != -EOPNOTSUPP &&
-	     error == DM_ENDIO_REQUEUE))
-		md->barrier_error = error;
-	spin_unlock_irqrestore(&md->barrier_error_lock, flags);
-}
-
 /*
  * Don't touch any member of the md after calling this function because
  * the md may be freed in dm_put() at the end of this function.
@@ -809,13 +761,11 @@ static void free_rq_clone(struct request *clone)
 static void dm_end_request(struct request *clone, int error)
 {
 	int rw = rq_data_dir(clone);
-	int run_queue = 1;
-	bool is_barrier = clone->cmd_flags & REQ_HARDBARRIER;
 	struct dm_rq_target_io *tio = clone->end_io_data;
 	struct mapped_device *md = tio->md;
 	struct request *rq = tio->orig;
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !is_barrier) {
+	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		rq->errors = clone->errors;
 		rq->resid_len = clone->resid_len;
 
@@ -829,15 +779,8 @@ static void dm_end_request(struct request *clone, int error)
 	}
 
 	free_rq_clone(clone);
-
-	if (unlikely(is_barrier)) {
-		if (unlikely(error))
-			store_barrier_error(md, error);
-		run_queue = 0;
-	} else
-		blk_end_request_all(rq, error);
-
-	rq_completed(md, rw, run_queue);
+	blk_end_request_all(rq, error);
+	rq_completed(md, rw, true);
 }
 
 static void dm_unprep_request(struct request *rq)
@@ -862,16 +805,6 @@ void dm_requeue_unmapped_request(struct request *clone)
 	struct request_queue *q = rq->q;
 	unsigned long flags;
 
-	if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) {
-		/*
-		 * Barrier clones share an original request.
-		 * Leave it to dm_end_request(), which handles this special
-		 * case.
-		 */
-		dm_end_request(clone, DM_ENDIO_REQUEUE);
-		return;
-	}
-
 	dm_unprep_request(rq);
 
 	spin_lock_irqsave(q->queue_lock, flags);
@@ -961,19 +894,6 @@ static void dm_complete_request(struct request *clone, int error)
 	struct dm_rq_target_io *tio = clone->end_io_data;
 	struct request *rq = tio->orig;
 
-	if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) {
-		/*
-		 * Barrier clones share an original request.  So can't use
-		 * softirq_done with the original.
-		 * Pass the clone to dm_done() directly in this special case.
-		 * It is safe (even if clone->q->queue_lock is held here)
-		 * because there is no I/O dispatching during the completion
-		 * of barrier clone.
-		 */
-		dm_done(clone, error, true);
-		return;
-	}
-
 	tio->error = error;
 	rq->completion_data = clone;
 	blk_complete_request(rq);
@@ -990,17 +910,6 @@ void dm_kill_unmapped_request(struct request *clone, int error)
 	struct dm_rq_target_io *tio = clone->end_io_data;
 	struct request *rq = tio->orig;
 
-	if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) {
-		/*
-		 * Barrier clones share an original request.
-		 * Leave it to dm_end_request(), which handles this special
-		 * case.
-		 */
-		BUG_ON(error > 0);
-		dm_end_request(clone, error);
-		return;
-	}
-
 	rq->cmd_flags |= REQ_FAILED;
 	dm_complete_request(clone, error);
 }
@@ -1119,7 +1028,7 @@ static void dm_bio_destructor(struct bio *bio)
 }
 
 /*
- * Creates a little bio that is just does part of a bvec.
+ * 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,
@@ -1134,7 +1043,7 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector,
 
 	clone->bi_sector = sector;
 	clone->bi_bdev = bio->bi_bdev;
-	clone->bi_rw = bio->bi_rw & ~REQ_HARDBARRIER;
+	clone->bi_rw = bio->bi_rw;
 	clone->bi_vcnt = 1;
 	clone->bi_size = to_bytes(len);
 	clone->bi_io_vec->bv_offset = offset;
@@ -1161,7 +1070,6 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector,
 
 	clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs);
 	__bio_clone(clone, bio);
-	clone->bi_rw &= ~REQ_HARDBARRIER;
 	clone->bi_destructor = dm_bio_destructor;
 	clone->bi_sector = sector;
 	clone->bi_idx = idx;
@@ -1225,16 +1133,15 @@ static void __issue_target_requests(struct clone_info *ci, struct dm_target *ti,
 		__issue_target_request(ci, ti, request_nr, len);
 }
 
-static int __clone_and_map_empty_barrier(struct clone_info *ci)
+static int __clone_and_map_empty_flush(struct clone_info *ci)
 {
 	unsigned target_nr = 0;
 	struct dm_target *ti;
 
+	BUG_ON(bio_has_data(ci->bio));
 	while ((ti = dm_table_get_target(ci->map, target_nr++)))
 		__issue_target_requests(ci, ti, ti->num_flush_requests, 0);
 
-	ci->sector_count = 0;
-
 	return 0;
 }
 
@@ -1289,9 +1196,6 @@ static int __clone_and_map(struct clone_info *ci)
 	sector_t len = 0, max;
 	struct dm_target_io *tio;
 
-	if (unlikely(bio_empty_barrier(bio)))
-		return __clone_and_map_empty_barrier(ci);
-
 	if (unlikely(bio->bi_rw & REQ_DISCARD))
 		return __clone_and_map_discard(ci);
 
@@ -1383,16 +1287,11 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
 
 	ci.map = dm_get_live_table(md);
 	if (unlikely(!ci.map)) {
-		if (!(bio->bi_rw & REQ_HARDBARRIER))
-			bio_io_error(bio);
-		else
-			if (!md->barrier_error)
-				md->barrier_error = -EIO;
+		bio_io_error(bio);
 		return;
 	}
 
 	ci.md = md;
-	ci.bio = bio;
 	ci.io = alloc_io(md);
 	ci.io->error = 0;
 	atomic_set(&ci.io->io_count, 1);
@@ -1400,14 +1299,20 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
 	ci.io->md = md;
 	spin_lock_init(&ci.io->endio_lock);
 	ci.sector = bio->bi_sector;
-	ci.sector_count = bio_sectors(bio);
-	if (unlikely(bio_empty_barrier(bio)))
-		ci.sector_count = 1;
 	ci.idx = bio->bi_idx;
 
 	start_io_acct(ci.io);
-	while (ci.sector_count && !error)
-		error = __clone_and_map(&ci);
+	if (bio->bi_rw & REQ_FLUSH) {
+		ci.bio = &ci.md->flush_bio;
+		ci.sector_count = 0;
+		error = __clone_and_map_empty_flush(&ci);
+		/* dec_pending submits any data associated with flush */
+	} else {
+		ci.bio = bio;
+		ci.sector_count = bio_sectors(bio);
+		while (ci.sector_count && !error)
+			error = __clone_and_map(&ci);
+	}
 
 	/* drop the extra reference count */
 	dec_pending(ci.io, error);
@@ -1491,22 +1396,14 @@ static int _dm_request(struct request_queue *q, struct bio *bio)
 	part_stat_add(cpu, &dm_disk(md)->part0, sectors[rw], bio_sectors(bio));
 	part_stat_unlock();
 
-	/*
-	 * If we're suspended or the thread is processing barriers
-	 * we have to queue this io for later.
-	 */
-	if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) ||
-	    unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
+	/* if we're suspended, we have to queue this io for later */
+	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
 		up_read(&md->io_lock);
 
-		if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) &&
-		    bio_rw(bio) == READA) {
+		if (bio_rw(bio) != READA)
+			queue_io(md, bio);
+		else
 			bio_io_error(bio);
-			return 0;
-		}
-
-		queue_io(md, bio);
-
 		return 0;
 	}
 
@@ -1537,14 +1434,6 @@ static int dm_request(struct request_queue *q, struct bio *bio)
 	return _dm_request(q, bio);
 }
 
-static bool dm_rq_is_flush_request(struct request *rq)
-{
-	if (rq->cmd_flags & REQ_FLUSH)
-		return true;
-	else
-		return false;
-}
-
 void dm_dispatch_request(struct request *rq)
 {
 	int r;
@@ -1592,22 +1481,15 @@ static int setup_clone(struct request *clone, struct request *rq,
 {
 	int r;
 
-	if (dm_rq_is_flush_request(rq)) {
-		blk_rq_init(NULL, clone);
-		clone->cmd_type = REQ_TYPE_FS;
-		clone->cmd_flags |= (REQ_HARDBARRIER | WRITE);
-	} else {
-		r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC,
-				      dm_rq_bio_constructor, tio);
-		if (r)
-			return r;
-
-		clone->cmd = rq->cmd;
-		clone->cmd_len = rq->cmd_len;
-		clone->sense = rq->sense;
-		clone->buffer = rq->buffer;
-	}
+	r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC,
+			      dm_rq_bio_constructor, tio);
+	if (r)
+		return r;
 
+	clone->cmd = rq->cmd;
+	clone->cmd_len = rq->cmd_len;
+	clone->sense = rq->sense;
+	clone->buffer = rq->buffer;
 	clone->end_io = end_clone_request;
 	clone->end_io_data = tio;
 
@@ -1648,9 +1530,6 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq)
 	struct mapped_device *md = q->queuedata;
 	struct request *clone;
 
-	if (unlikely(dm_rq_is_flush_request(rq)))
-		return BLKPREP_OK;
-
 	if (unlikely(rq->special)) {
 		DMWARN("Already has something in rq->special.");
 		return BLKPREP_KILL;
@@ -1727,6 +1606,7 @@ static void dm_request_fn(struct request_queue *q)
 	struct dm_table *map = dm_get_live_table(md);
 	struct dm_target *ti;
 	struct request *rq, *clone;
+	sector_t pos;
 
 	/*
 	 * For suspend, check blk_queue_stopped() and increment
@@ -1739,15 +1619,14 @@ static void dm_request_fn(struct request_queue *q)
 		if (!rq)
 			goto plug_and_out;
 
-		if (unlikely(dm_rq_is_flush_request(rq))) {
-			BUG_ON(md->flush_request);
-			md->flush_request = rq;
-			blk_start_request(rq);
-			queue_work(md->wq, &md->barrier_work);
-			goto out;
-		}
+		/* always use block 0 to find the target for flushes for now */
+		pos = 0;
+		if (!(rq->cmd_flags & REQ_FLUSH))
+			pos = blk_rq_pos(rq);
+
+		ti = dm_table_find_target(map, pos);
+		BUG_ON(!dm_target_is_valid(ti));
 
-		ti = dm_table_find_target(map, blk_rq_pos(rq));
 		if (ti->type->busy && ti->type->busy(ti))
 			goto plug_and_out;
 
@@ -1918,7 +1797,6 @@ out:
 static const struct block_device_operations dm_blk_dops;
 
 static void dm_wq_work(struct work_struct *work);
-static void dm_rq_barrier_work(struct work_struct *work);
 
 static void dm_init_md_queue(struct mapped_device *md)
 {
@@ -1940,6 +1818,7 @@ static void dm_init_md_queue(struct mapped_device *md)
 	blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
 	md->queue->unplug_fn = dm_unplug_all;
 	blk_queue_merge_bvec(md->queue, dm_merge_bvec);
+	blk_queue_flush(md->queue, REQ_FLUSH | REQ_FUA);
 }
 
 /*
@@ -1972,7 +1851,6 @@ static struct mapped_device *alloc_dev(int minor)
 	mutex_init(&md->suspend_lock);
 	mutex_init(&md->type_lock);
 	spin_lock_init(&md->deferred_lock);
-	spin_lock_init(&md->barrier_error_lock);
 	rwlock_init(&md->map_lock);
 	atomic_set(&md->holders, 1);
 	atomic_set(&md->open_count, 0);
@@ -1995,7 +1873,6 @@ static struct mapped_device *alloc_dev(int minor)
 	atomic_set(&md->pending[1], 0);
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
-	INIT_WORK(&md->barrier_work, dm_rq_barrier_work);
 	init_waitqueue_head(&md->eventq);
 
 	md->disk->major = _major;
@@ -2015,6 +1892,10 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->bdev)
 		goto bad_bdev;
 
+	bio_init(&md->flush_bio);
+	md->flush_bio.bi_bdev = md->bdev;
+	md->flush_bio.bi_rw = WRITE_FLUSH;
+
 	/* Populate the mapping, nobody knows we exist yet */
 	spin_lock(&_minor_lock);
 	old_md = idr_replace(&_minor_idr, md, minor);
@@ -2245,7 +2126,6 @@ static int dm_init_request_based_queue(struct mapped_device *md)
 	blk_queue_softirq_done(md->queue, dm_softirq_done);
 	blk_queue_prep_rq(md->queue, dm_prep_fn);
 	blk_queue_lld_busy(md->queue, dm_lld_busy);
-	blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH);
 
 	elv_register_queue(md->queue);
 
@@ -2406,43 +2286,6 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible)
 	return r;
 }
 
-static void dm_flush(struct mapped_device *md)
-{
-	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
-
-	bio_init(&md->barrier_bio);
-	md->barrier_bio.bi_bdev = md->bdev;
-	md->barrier_bio.bi_rw = WRITE_BARRIER;
-	__split_and_process_bio(md, &md->barrier_bio);
-
-	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
-}
-
-static void process_barrier(struct mapped_device *md, struct bio *bio)
-{
-	md->barrier_error = 0;
-
-	dm_flush(md);
-
-	if (!bio_empty_barrier(bio)) {
-		__split_and_process_bio(md, bio);
-		/*
-		 * If the request isn't supported, don't waste time with
-		 * the second flush.
-		 */
-		if (md->barrier_error != -EOPNOTSUPP)
-			dm_flush(md);
-	}
-
-	if (md->barrier_error != DM_ENDIO_REQUEUE)
-		bio_endio(bio, md->barrier_error);
-	else {
-		spin_lock_irq(&md->deferred_lock);
-		bio_list_add_head(&md->deferred, bio);
-		spin_unlock_irq(&md->deferred_lock);
-	}
-}
-
 /*
  * Process the deferred bios
  */
@@ -2452,33 +2295,27 @@ static void dm_wq_work(struct work_struct *work)
 						work);
 	struct bio *c;
 
-	down_write(&md->io_lock);
+	down_read(&md->io_lock);
 
 	while (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) {
 		spin_lock_irq(&md->deferred_lock);
 		c = bio_list_pop(&md->deferred);
 		spin_unlock_irq(&md->deferred_lock);
 
-		if (!c) {
-			clear_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags);
+		if (!c)
 			break;
-		}
 
-		up_write(&md->io_lock);
+		up_read(&md->io_lock);
 
 		if (dm_request_based(md))
 			generic_make_request(c);
-		else {
-			if (c->bi_rw & REQ_HARDBARRIER)
-				process_barrier(md, c);
-			else
-				__split_and_process_bio(md, c);
-		}
+		else
+			__split_and_process_bio(md, c);
 
-		down_write(&md->io_lock);
+		down_read(&md->io_lock);
 	}
 
-	up_write(&md->io_lock);
+	up_read(&md->io_lock);
 }
 
 static void dm_queue_flush(struct mapped_device *md)
@@ -2488,73 +2325,6 @@ static void dm_queue_flush(struct mapped_device *md)
 	queue_work(md->wq, &md->work);
 }
 
-static void dm_rq_set_target_request_nr(struct request *clone, unsigned request_nr)
-{
-	struct dm_rq_target_io *tio = clone->end_io_data;
-
-	tio->info.target_request_nr = request_nr;
-}
-
-/* Issue barrier requests to targets and wait for their completion. */
-static int dm_rq_barrier(struct mapped_device *md)
-{
-	int i, j;
-	struct dm_table *map = dm_get_live_table(md);
-	unsigned num_targets = dm_table_get_num_targets(map);
-	struct dm_target *ti;
-	struct request *clone;
-
-	md->barrier_error = 0;
-
-	for (i = 0; i < num_targets; i++) {
-		ti = dm_table_get_target(map, i);
-		for (j = 0; j < ti->num_flush_requests; j++) {
-			clone = clone_rq(md->flush_request, md, GFP_NOIO);
-			dm_rq_set_target_request_nr(clone, j);
-			atomic_inc(&md->pending[rq_data_dir(clone)]);
-			map_request(ti, clone, md);
-		}
-	}
-
-	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
-	dm_table_put(map);
-
-	return md->barrier_error;
-}
-
-static void dm_rq_barrier_work(struct work_struct *work)
-{
-	int error;
-	struct mapped_device *md = container_of(work, struct mapped_device,
-						barrier_work);
-	struct request_queue *q = md->queue;
-	struct request *rq;
-	unsigned long flags;
-
-	/*
-	 * Hold the md reference here and leave it at the last part so that
-	 * the md can't be deleted by device opener when the barrier request
-	 * completes.
-	 */
-	dm_get(md);
-
-	error = dm_rq_barrier(md);
-
-	rq = md->flush_request;
-	md->flush_request = NULL;
-
-	if (error == DM_ENDIO_REQUEUE) {
-		spin_lock_irqsave(q->queue_lock, flags);
-		blk_