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
  ...

9 files changed, 350 insertions, 486 deletions

diff --git a/block/Makefile b/block/Makefile
index c850d5ef80a..0fec4b3fab5 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -3,7 +3,7 @@
 #
 
 obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
-			blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \
+			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o
 
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
deleted file mode 100644
index f0faefca032..00000000000
--- a/block/blk-barrier.c
+++ /dev/null
@@ -1,350 +0,0 @@
-/*
- * Functions related to barrier IO handling
- */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/bio.h>
-#include <linux/blkdev.h>
-#include <linux/gfp.h>
-
-#include "blk.h"
-
-/**
- * blk_queue_ordered - does this queue support ordered writes
- * @q:        the request queue
- * @ordered:  one of QUEUE_ORDERED_*
- *
- * Description:
- *   For journalled file systems, doing ordered writes on a commit
- *   block instead of explicitly doing wait_on_buffer (which is bad
- *   for performance) can be a big win. Block drivers supporting this
- *   feature should call this function and indicate so.
- *
- **/
-int blk_queue_ordered(struct request_queue *q, unsigned ordered)
-{
-	if (ordered != QUEUE_ORDERED_NONE &&
-	    ordered != QUEUE_ORDERED_DRAIN &&
-	    ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
-	    ordered != QUEUE_ORDERED_DRAIN_FUA &&
-	    ordered != QUEUE_ORDERED_TAG &&
-	    ordered != QUEUE_ORDERED_TAG_FLUSH &&
-	    ordered != QUEUE_ORDERED_TAG_FUA) {
-		printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
-		return -EINVAL;
-	}
-
-	q->ordered = ordered;
-	q->next_ordered = ordered;
-
-	return 0;
-}
-EXPORT_SYMBOL(blk_queue_ordered);
-
-/*
- * Cache flushing for ordered writes handling
- */
-unsigned blk_ordered_cur_seq(struct request_queue *q)
-{
-	if (!q->ordseq)
-		return 0;
-	return 1 << ffz(q->ordseq);
-}
-
-unsigned blk_ordered_req_seq(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-
-	BUG_ON(q->ordseq == 0);
-
-	if (rq == &q->pre_flush_rq)
-		return QUEUE_ORDSEQ_PREFLUSH;
-	if (rq == &q->bar_rq)
-		return QUEUE_ORDSEQ_BAR;
-	if (rq == &q->post_flush_rq)
-		return QUEUE_ORDSEQ_POSTFLUSH;
-
-	/*
-	 * !fs requests don't need to follow barrier ordering.  Always
-	 * put them at the front.  This fixes the following deadlock.
-	 *
-	 * http://thread.gmane.org/gmane.linux.kernel/537473
-	 */
-	if (rq->cmd_type != REQ_TYPE_FS)
-		return QUEUE_ORDSEQ_DRAIN;
-
-	if ((rq->cmd_flags & REQ_ORDERED_COLOR) ==
-	    (q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR))
-		return QUEUE_ORDSEQ_DRAIN;
-	else
-		return QUEUE_ORDSEQ_DONE;
-}
-
-bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
-{
-	struct request *rq;
-
-	if (error && !q->orderr)
-		q->orderr = error;
-
-	BUG_ON(q->ordseq & seq);
-	q->ordseq |= seq;
-
-	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
-		return false;
-
-	/*
-	 * Okay, sequence complete.
-	 */
-	q->ordseq = 0;
-	rq = q->orig_bar_rq;
-	__blk_end_request_all(rq, q->orderr);
-	return true;
-}
-
-static void pre_flush_end_io(struct request *rq, int error)
-{
-	elv_completed_request(rq->q, rq);
-	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_PREFLUSH, error);
-}
-
-static void bar_end_io(struct request *rq, int error)
-{
-	elv_completed_request(rq->q, rq);
-	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_BAR, error);
-}
-
-static void post_flush_end_io(struct request *rq, int error)
-{
-	elv_completed_request(rq->q, rq);
-	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
-}
-
-static void queue_flush(struct request_queue *q, unsigned which)
-{
-	struct request *rq;
-	rq_end_io_fn *end_io;
-
-	if (which == QUEUE_ORDERED_DO_PREFLUSH) {
-		rq = &q->pre_flush_rq;
-		end_io = pre_flush_end_io;
-	} else {
-		rq = &q->post_flush_rq;
-		end_io = post_flush_end_io;
-	}
-
-	blk_rq_init(q, rq);
-	rq->cmd_type = REQ_TYPE_FS;
-	rq->cmd_flags = REQ_HARDBARRIER | REQ_FLUSH;
-	rq->rq_disk = q->orig_bar_rq->rq_disk;
-	rq->end_io = end_io;
-
-	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
-}
-
-static inline bool start_ordered(struct request_queue *q, struct request **rqp)
-{
-	struct request *rq = *rqp;
-	unsigned skip = 0;
-
-	q->orderr = 0;
-	q->ordered = q->next_ordered;
-	q->ordseq |= QUEUE_ORDSEQ_STARTED;
-
-	/*
-	 * For an empty barrier, there's no actual BAR request, which
-	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
-	 */
-	if (!blk_rq_sectors(rq)) {
-		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
-				QUEUE_ORDERED_DO_POSTFLUSH);
-		/*
-		 * Empty barrier on a write-through device w/ ordered
-		 * tag has no command to issue and without any command
-		 * to issue, ordering by tag can't be used.  Drain
-		 * instead.
-		 */
-		if ((q->ordered & QUEUE_ORDERED_BY_TAG) &&
-		    !(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) {
-			q->ordered &= ~QUEUE_ORDERED_BY_TAG;
-			q->ordered |= QUEUE_ORDERED_BY_DRAIN;
-		}
-	}
-
-	/* stash away the original request */
-	blk_dequeue_request(rq);
-	q->orig_bar_rq = rq;
-	rq = NULL;
-
-	/*
-	 * Queue ordered sequence.  As we stack them at the head, we
-	 * need to queue in reverse order.  Note that we rely on that
-	 * no fs request uses ELEVATOR_INSERT_FRONT and thus no fs
-	 * request gets inbetween ordered sequence.
-	 */
-	if (q->ordered & QUEUE_ORDERED_DO_POSTFLUSH) {
-		queue_flush(q, QUEUE_ORDERED_DO_POSTFLUSH);
-		rq = &q->post_flush_rq;
-	} else
-		skip |= QUEUE_ORDSEQ_POSTFLUSH;
-
-	if (q->ordered & QUEUE_ORDERED_DO_BAR) {
-		rq = &q->bar_rq;
-
-		/* initialize proxy request and queue it */
-		blk_rq_init(q, rq);
-		if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
-			rq->cmd_flags |= REQ_WRITE;
-		if (q->ordered & QUEUE_ORDERED_DO_FUA)
-			rq->cmd_flags |= REQ_FUA;
-		init_request_from_bio(rq, q->orig_bar_rq->bio);
-		rq->end_io = bar_end_io;
-
-		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
-	} else
-		skip |= QUEUE_ORDSEQ_BAR;
-
-	if (q->ordered & QUEUE_ORDERED_DO_PREFLUSH) {
-		queue_flush(q, QUEUE_ORDERED_DO_PREFLUSH);
-		rq = &q->pre_flush_rq;
-	} else
-		skip |= QUEUE_ORDSEQ_PREFLUSH;
-
-	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && queue_in_flight(q))
-		rq = NULL;
-	else
-		skip |= QUEUE_ORDSEQ_DRAIN;
-
-	*rqp = rq;
-
-	/*
-	 * Complete skipped sequences.  If whole sequence is complete,
-	 * return false to tell elevator that this request is gone.
-	 */
-	return !blk_ordered_complete_seq(q, skip, 0);
-}
-
-bool blk_do_ordered(struct request_queue *q, struct request **rqp)
-{
-	struct request *rq = *rqp;
-	const int is_barrier = rq->cmd_type == REQ_TYPE_FS &&
-				(rq->cmd_flags & REQ_HARDBARRIER);
-
-	if (!q->ordseq) {
-		if (!is_barrier)
-			return true;
-
-		if (q->next_ordered != QUEUE_ORDERED_NONE)
-			return start_ordered(q, rqp);
-		else {
-			/*
-			 * Queue ordering not supported.  Terminate
-			 * with prejudice.
-			 */
-			blk_dequeue_request(rq);
-			__blk_end_request_all(rq, -EOPNOTSUPP);
-			*rqp = NULL;
-			return false;
-		}
-	}
-
-	/*
-	 * Ordered sequence in progress
-	 */
-
-	/* Special requests are not subject to ordering rules. */
-	if (rq->cmd_type != REQ_TYPE_FS &&
-	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
-		return true;
-
-	if (q->ordered & QUEUE_ORDERED_BY_TAG) {
-		/* Ordered by tag.  Blocking the next barrier is enough. */
-		if (is_barrier && rq != &q->bar_rq)
-			*rqp = NULL;
-	} else {
-		/* Ordered by draining.  Wait for turn. */
-		WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
-		if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
-			*rqp = NULL;
-	}
-
-	return true;
-}
-
-static void bio_end_empty_barrier(struct bio *bio, int err)
-{
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	}
-	if (bio->bi_private)
-		complete(bio->bi_private);
-	bio_put(bio);
-}
-
-/**
- * blkdev_issue_flush - queue a flush
- * @bdev:	blockdev to issue flush for
- * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @error_sector:	error sector
- * @flags:	BLKDEV_IFL_* flags to control behaviour
- *
- * Description:
- *    Issue a flush for the block device in question. Caller can supply
- *    room for storing the error offset in case of a flush error, if they
- *    wish to. If WAIT flag is not passed then caller may check only what
- *    request was pushed in some internal queue for later handling.
- */
-int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
-		sector_t *error_sector, unsigned long flags)
-{
-	DECLARE_COMPLETION_ONSTACK(wait);
-	struct request_queue *q;
-	struct bio *bio;
-	int ret = 0;
-
-	if (bdev->bd_disk == NULL)
-		return -ENXIO;
-
-	q = bdev_get_queue(bdev);
-	if (!q)
-		return -ENXIO;
-
-	/*
-	 * some block devices may not have their queue correctly set up here
-	 * (e.g. loop device without a backing file) and so issuing a flush
-	 * here will panic. Ensure there is a request function before issuing
-	 * the barrier.
-	 */
-	if (!q->make_request_fn)
-		return -ENXIO;
-
-	bio = bio_alloc(gfp_mask, 0);
-	bio->bi_end_io = bio_end_empty_barrier;
-	bio->bi_bdev = bdev;
-	if (test_bit(BLKDEV_WAIT, &flags))
-		bio->bi_private = &wait;
-
-	bio_get(bio);
-	submit_bio(WRITE_BARRIER, bio);
-	if (test_bit(BLKDEV_WAIT, &flags)) {
-		wait_for_completion(&wait);
-		/*
-		 * The driver must store the error location in ->bi_sector, if
-		 * it supports it. For non-stacked drivers, this should be
-		 * copied from blk_rq_pos(rq).
-		 */
-		if (error_sector)
-			*error_sector = bio->bi_sector;
-	}
-
-	if (bio_flagged(bio, BIO_EOPNOTSUPP))
-		ret = -EOPNOTSUPP;
-	else if (!bio_flagged(bio, BIO_UPTODATE))
-		ret = -EIO;
-
-	bio_put(bio);
-	return ret;
-}
-EXPORT_SYMBOL(blkdev_issue_flush);
diff --git a/block/blk-core.c b/block/blk-core.c
index 500eb859886..45141469e89 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -139,7 +139,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 {
 	struct request_queue *q = rq->q;
 
-	if (&q->bar_rq != rq) {
+	if (&q->flush_rq != rq) {
 		if (error)
 			clear_bit(BIO_UPTODATE, &bio->bi_flags);
 		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
@@ -163,13 +163,12 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		if (bio->bi_size == 0)
 			bio_endio(bio, error);
 	} else {
-
 		/*
-		 * Okay, this is the barrier request in progress, just
-		 * record the error;
+		 * Okay, this is the sequenced flush request in
+		 * progress, just record the error;
 		 */
-		if (error && !q->orderr)
-			q->orderr = error;
+		if (error && !q->flush_err)
+			q->flush_err = error;
 	}
 }
 
@@ -531,6 +530,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	init_timer(&q->unplug_timer);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->timeout_list);
+	INIT_LIST_HEAD(&q->pending_flushes);
 	INIT_WORK(&q->unplug_work, blk_unplug_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
@@ -1053,22 +1053,6 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(blk_insert_request);
 
-/*
- * add-request adds a request to the linked list.
- * queue lock is held and interrupts disabled, as we muck with the
- * request queue list.
- */
-static inline void add_request(struct request_queue *q, struct request *req)
-{
-	drive_stat_acct(req, 1);
-
-	/*
-	 * elevator indicated where it wants this request to be
-	 * inserted at elevator_merge time
-	 */
-	__elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
-}
-
 static void part_round_stats_single(int cpu, struct hd_struct *part,
 				    unsigned long now)
 {
@@ -1217,13 +1201,16 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	const bool sync = !!(bio->bi_rw & REQ_SYNC);
 	const bool unplug = !!(bio->bi_rw & REQ_UNPLUG);
 	const unsigned long ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	int where = ELEVATOR_INSERT_SORT;
 	int rw_flags;
 
-	if ((bio->bi_rw & REQ_HARDBARRIER) &&
-	    (q->next_ordered == QUEUE_ORDERED_NONE)) {
+	/* REQ_HARDBARRIER is no more */
+	if (WARN_ONCE(bio->bi_rw & REQ_HARDBARRIER,
+		"block: HARDBARRIER is deprecated, use FLUSH/FUA instead\n")) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
+
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even
@@ -1233,7 +1220,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (unlikely((bio->bi_rw & REQ_HARDBARRIER)) || elv_queue_empty(q))
+	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
+		where = ELEVATOR_INSERT_FRONT;
+		goto get_rq;
+	}
+
+	if (elv_queue_empty(q))
 		goto get_rq;
 
 	el_ret = elv_merge(q, &req, bio);
@@ -1330,7 +1322,10 @@ get_rq:
 		req->cpu = blk_cpu_to_group(smp_processor_id());
 	if (queue_should_plug(q) && elv_queue_empty(q))
 		blk_plug_device(q);
-	add_request(q, req);
+
+	/* insert the request into the elevator */
+	drive_stat_acct(req, 1);
+	__elv_add_request(q, req, where, 0);
 out:
 	if (unplug || !queue_should_plug(q))
 		__generic_unplug_device(q);
@@ -1530,6 +1525,19 @@ static inline void __generic_make_request(struct bio *bio)
 		if (bio_check_eod(bio, nr_sectors))
 			goto end_io;
 
+		/*
+		 * Filter flush bio's early so that make_request based
+		 * drivers without flush support don't have to worry
+		 * about them.
+		 */
+		if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) {
+			bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
+			if (!nr_sectors) {
+				err = 0;
+				goto end_io;
+			}
+		}
+
 		if ((bio->bi_rw & REQ_DISCARD) &&
 		    (!blk_queue_discard(q) ||
 		     ((bio->bi_rw & REQ_SECURE) &&
@@ -1794,11 +1802,11 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 static void blk_account_io_done(struct request *req)
 {
 	/*
-	 * Account IO completion.  bar_rq isn't accounted as a normal
-	 * IO on queueing nor completion.  Accounting the containing
-	 * request is enough.
+	 * Account IO completion.  flush_rq isn't accounted as a
+	 * normal IO on queueing nor completion.  Accounting the
+	 * containing request is enough.
 	 */
-	if (blk_do_io_stat(req) && req != &req->q->bar_rq) {
+	if (blk_do_io_stat(req) && req != &req->q->flush_rq) {
 		unsigned long duration = jiffies - req->start_time;
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;
@@ -2523,9 +2531,7 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags = (rq_data_dir(src) | REQ_NOMERGE);
-	if (src->cmd_flags & REQ_DISCARD)
-		dst->cmd_flags |= REQ_DISCARD;
+	dst->cmd_flags = (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
diff --git a/block/blk-flush.c b/block/blk-flush.c
new file mode 100644
index 00000000000..54b123d6563
--- /dev/null
+++ b/block/blk-flush.c
@@ -0,0 +1,262 @@
+/*
+ * Functions to sequence FLUSH and FUA writes.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/gfp.h>
+
+#include "blk.h"
+
+/* FLUSH/FUA sequences */
+enum {
+	QUEUE_FSEQ_STARTED	= (1 << 0), /* flushing in progress */
+	QUEUE_FSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
+	QUEUE_FSEQ_DATA		= (1 << 2), /* data write in progress */
+	QUEUE_FSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
+	QUEUE_FSEQ_DONE		= (1 << 4),
+};
+
+static struct request *queue_next_fseq(struct request_queue *q);
+
+unsigned blk_flush_cur_seq(struct request_queue *q)
+{
+	if (!q->flush_seq)
+		return 0;
+	return 1 << ffz(q->flush_seq);
+}
+
+static struct request *blk_flush_complete_seq(struct request_queue *q,
+					      unsigned seq, int error)
+{
+	struct request *next_rq = NULL;
+
+	if (error && !q->flush_err)
+		q->flush_err = error;
+
+	BUG_ON(q->flush_seq & seq);
+	q->flush_seq |= seq;
+
+	if (blk_flush_cur_seq(q) != QUEUE_FSEQ_DONE) {
+		/* not complete yet, queue the next flush sequence */
+		next_rq = queue_next_fseq(q);
+	} else {
+		/* complete this flush request */
+		__blk_end_request_all(q->orig_flush_rq, q->flush_err);
+		q->orig_flush_rq = NULL;
+		q->flush_seq = 0;
+
+		/* dispatch the next flush if there's one */
+		if (!list_empty(&q->pending_flushes)) {
+			next_rq = list_entry_rq(q->pending_flushes.next);
+			list_move(&next_rq->queuelist, &q->queue_head);
+		}
+	}
+	return next_rq;
+}
+
+static void blk_flush_complete_seq_end_io(struct request_queue *q,
+					  unsigned seq, int error)
+{
+	bool was_empty = elv_queue_empty(q);
+	struct request *next_rq;
+
+	next_rq = blk_flush_complete_seq(q, seq, error);
+
+	/*
+	 * Moving a request silently to empty queue_head may stall the
+	 * queue.  Kick the queue in those cases.
+	 */
+	if (was_empty && next_rq)
+		__blk_run_queue(q);
+}
+
+static void pre_flush_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_PREFLUSH, error);
+}
+
+static void flush_data_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_DATA, error);
+}
+
+static void post_flush_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_POSTFLUSH, error);
+}
+
+static void init_flush_request(struct request *rq, struct gendisk *disk)
+{
+	rq->cmd_type = REQ_TYPE_FS;
+	rq->cmd_flags = WRITE_FLUSH;
+	rq->rq_disk = disk;
+}
+
+static struct request *queue_next_fseq(struct request_queue *q)
+{
+	struct request *orig_rq = q->orig_flush_rq;
+	struct request *rq = &q->flush_rq;
+
+	blk_rq_init(q, rq);
+
+	switch (blk_flush_cur_seq(q)) {
+	case QUEUE_FSEQ_PREFLUSH:
+		init_flush_request(rq, orig_rq->rq_disk);
+		rq->end_io = pre_flush_end_io;
+		break;
+	case QUEUE_FSEQ_DATA:
+		init_request_from_bio(rq, orig_rq->bio);
+		/*
+		 * orig_rq->rq_disk may be different from
+		 * bio->bi_bdev->bd_disk if orig_rq got here through
+		 * remapping drivers.  Make sure rq->rq_disk points
+		 * to the same one as orig_rq.
+		 */
+		rq->rq_disk = orig_rq->rq_disk;
+		rq->cmd_flags &= ~(REQ_FLUSH | REQ_FUA);
+		rq->cmd_flags |= orig_rq->cmd_flags & (REQ_FLUSH | REQ_FUA);
+		rq->end_io = flush_data_end_io;
+		break;
+	case QUEUE_FSEQ_POSTFLUSH:
+		init_flush_request(rq, orig_rq->rq_disk);
+		rq->end_io = post_flush_end_io;
+		break;
+	default:
+		BUG();
+	}
+
+	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
+	return rq;
+}
+
+struct request *blk_do_flush(struct request_queue *q, struct request *rq)
+{
+	unsigned int fflags = q->flush_flags; /* may change, cache it */
+	bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA;
+	bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH);
+	bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA);
+	unsigned skip = 0;
+
+	/*
+	 * Special case.  If there's data but flush is not necessary,
+	 * the request can be issued directly.
+	 *
+	 * Flush w/o data should be able to be issued directly too but
+	 * currently some drivers assume that rq->bio contains
+	 * non-zero data if it isn't NULL and empty FLUSH requests
+	 * getting here usually have bio's without data.
+	 */
+	if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) {
+		rq->cmd_flags &= ~REQ_FLUSH;
+		if (!has_fua)
+			rq->cmd_flags &= ~REQ_FUA;
+		return rq;
+	}
+
+	/*
+	 * Sequenced flushes can't be processed in parallel.  If
+	 * another one is already in progress, queue for later
+	 * processing.
+	 */
+	if (q->flush_seq) {
+		list_move_tail(&rq->queuelist, &q->pending_flushes);
+		return NULL;
+	}
+
+	/*
+	 * Start a new flush sequence
+	 */
+	q->flush_err = 0;
+	q->flush_seq |= QUEUE_FSEQ_STARTED;
+
+	/* adjust FLUSH/FUA of the original request and stash it away */
+	rq->cmd_flags &= ~REQ_FLUSH;
+	if (!has_fua)
+		rq->cmd_flags &= ~REQ_FUA;
+	blk_dequeue_request(rq);
+	q->orig_flush_rq = rq;
+
+	/* skip unneded sequences and return the first one */
+	if (!do_preflush)
+		skip |= QUEUE_FSEQ_PREFLUSH;
+	if (!blk_rq_sectors(rq))
+		skip |= QUEUE_FSEQ_DATA;
+	if (!do_postflush)
+		skip |= QUEUE_FSEQ_POSTFLUSH;
+	return blk_flush_complete_seq(q, skip, 0);
+}
+
+static void bio_end_flush(struct bio *bio, int err)
+{
+	if (err)
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	if (bio->bi_private)
+		complete(bio->bi_private);
+	bio_put(bio);
+}
+
+/**
+ * blkdev_issue_flush - queue a flush
+ * @bdev:	blockdev to issue flush for
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @error_sector:	error sector
+ *
+ * Description:
+ *    Issue a flush for the block device in question. Caller can supply
+ *    room for storing the error offset in case of a flush error, if they
+ *    wish to. If WAIT flag is not passed then caller may check only what
+ *    request was pushed in some internal queue for later handling.
+ */
+int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
+		sector_t *error_sector)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+	struct request_queue *q;
+	struct bio *bio;
+	int ret = 0;
+
+	if (bdev->bd_disk == NULL)
+		return -ENXIO;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	/*
+	 * some block devices may not have their queue correctly set up here
+	 * (e.g. loop device without a backing file) and so issuing a flush
+	 * here will panic. Ensure there is a request function before issuing
+	 * the flush.
+	 */
+	if (!q->make_request_fn)
+		return -ENXIO;
+
+	bio = bio_alloc(gfp_mask, 0);
+	bio->bi_end_io = bio_end_flush;
+	bio->bi_bdev = bdev;
+	bio->bi_private = &wait;
+
+	bio_get(bio);
+	submit_bio(WRITE_FLUSH, bio);
+	wait_for_completion(&wait);
+
+	/*
+	 * The driver must store the error location in ->bi_sector, if
+	 * it supports it. For non-stacked drivers, this should be
+	 * copied from blk_rq_pos(rq).
+	 */
+	if (error_sector)
+               *error_sector = bio->bi_sector;
+
+	if (!bio_flagged(bio, BIO_UPTODATE))
+		ret = -EIO;
+
+	bio_put(bio);
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_flush);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index c392029a104..1a320d2406b 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -39,8 +39,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
 	struct request_queue *q = bdev_get_queue(bdev);
-	int type = flags & BLKDEV_IFL_BARRIER ?
-		DISCARD_BARRIER : DISCARD_NOBARRIER;
+	int type = REQ_WRITE | REQ_DISCARD;
 	unsigned int max_discard_sectors;
 	struct bio *bio;
 	int ret = 0;
@@ -62,10 +61,10 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		max_discard_sectors &= ~(disc_sects - 1);
 	}
 
-	if (flags & BLKDEV_IFL_SECURE) {
+	if (flags & BLKDEV_DISCARD_SECURE) {
 		if (!blk_queue_secdiscard(q))
 			return -EOPNOTSUPP;
-		type |= DISCARD_SECURE;
+		type |= REQ_SECURE;
 	}
 
 	while (nr_sects && !ret) {
@@ -78,8 +77,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		bio->bi_sector = sector;
 		bio->bi_end_io = blkdev_discard_end_io;
 		bio->bi_bdev = bdev;
-		if (flags & BLKDEV_IFL_WAIT)
-			bio->bi_private = &wait;
+		bio->bi_private = &wait;
 
 		if (nr_sects > max_discard_sectors) {
 			bio->bi_size = max_discard_sectors << 9;
@@ -93,8 +91,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		bio_get(bio);
 		submit_bio(type, bio);
 
-		if (flags & BLKDEV_IFL_WAIT)
-			wait_for_completion(&wait);
+		wait_for_completion(&wait);
 
 		if (bio_flagged(bio, BIO_EOPNOTSUPP))
 			ret = -EOPNOTSUPP;
@@ -140,7 +137,6 @@ static void bio_batch_end_io(struct bio *bio, int err)
  * @sector:	start sector
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @flags:	BLKDEV_IFL_* flags to control behaviour
  *
  * Description:
  *  Generate and issue number of bios with zerofiled pages.
@@ -149,7 +145,7 @@ static void bio_batch_end_io(struct bio *bio, int err)
  */
 
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+			sector_t nr_sects, gfp_t gfp_mask)
 {
 	int ret;
 	struct bio *bio;
@@ -162,12 +158,6 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	bb.wait = &wait;
 	bb.end_io = NULL;
 
-	if (flags & BLKDEV_IFL_BARRIER) {
-		/* issue async barrier before the data */
-		ret = blkdev_issue_flush(bdev, gfp_mask, NULL, 0);
-		if (ret)
-			return ret;
-	}
 submit:
 	ret = 0;
 	while (nr_sects != 0) {
@@ -181,8 +171,7 @@ submit:
 		bio->bi_sector = sector;
 		bio->bi_bdev   = bdev;
 		bio->bi_end_io = bio_batch_end_io;
-		if (flags & BLKDEV_IFL_WAIT)
-			bio->bi_private = &bb;
+		bio->bi_private = &bb;
 
 		while (nr_sects != 0) {
 			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
@@ -199,18 +188,10 @@ submit:
 		issued++;
 		submit_bio(WRITE, bio);
 	}
-	/*
-	 * When all data bios are in flight. Send final barrier if requeted.
-	 */
-	if (nr_sects == 0 && flags & BLKDEV_IFL_BARRIER)
-		ret = blkdev_issue_flush(bdev, gfp_mask, NULL,
-					flags & BLKDEV_IFL_WAIT);
-
 
-	if (flags & BLKDEV_IFL_WAIT)
-		/* Wait for bios in-flight */
-		while ( issued != atomic_read(&bb.done))
-			wait_for_completion(&wait);
+	/* Wait for bios in-flight */
+	while (issued != atomic_read(&bb.done))
+		wait_for_completion(&wait);
 
 	if (!test_bit(BIO_UPTODATE, &bb.flags))
 		/* One of bios in the batch was completed with error.*/
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 315b88c8cbb..701859fb964 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -792,6 +792,26 @@ void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
 }
 EXPORT_SYMBOL(blk_queue_update_dma_alignment);
 
+/**
+ * blk_queue_flush - configure queue's cache flush capability
+ * @q:		the request queue for the device
+ * @flush:	0, REQ_FLUSH or REQ_FLUSH | REQ_FUA
+ *
+ * Tell block layer cache flush capability of @q.  If it supports
+ * flushing, REQ_FLUSH should be set.  If it supports bypassing
+ * write cache for individual writes, REQ_FUA should be set.
+ */
+void blk_queue_flush(struct request_queue *q, unsigned int flush)
+{
+	WARN_ON_ONCE(flush & ~(REQ_FLUSH | REQ_FUA));
+
+	if (WARN_ON_ONCE(!(flush & REQ_FLUSH) && (flush & REQ_FUA)))
+		flush &= ~REQ_FUA;
+
+	q->flush_flags = flush & (REQ_FLUSH | REQ_FUA);
+}
+EXPORT_SYMBOL_GPL(blk_queue_flush);
+
 static int __init blk_settings_init(void)
 {
 	blk_max_low_pfn = max_low_pfn - 1;
diff --git a/block/blk.h b/block/blk.h
index f864012ec30..1e675e5ade0 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -51,6 +51,8 @@ static inline void blk_clear_rq_complete(struct request *rq)
  */
 #define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
 
+struct request *blk_do_flush(struct request_queue *q, struct request *rq);
+
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
 	struct request *rq;
@@ -58,7 +60,11 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 	while (1) {
 		while (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
-			if (blk_do_ordered(q, &rq))
+			if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) ||
+			    rq == &q->flush_rq)
+				return rq;
+			rq = blk_do_flush(q, rq);
+			if (rq)
 				return rq;
 		}
 
diff --git a/block/elevator.c b/block/elevator.c
index 4e11559aa2b..282e8308f7e 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -617,8 +617,6 @@ void elv_quiesce_end(struct request_queue *q)
 
 void elv_insert(struct request_queue *q, struct request *rq, int where)
 {
-	struct list_head *pos;
-	unsigned ordseq;
 	int unplug_it = 1;
 
 	trace_block_rq_insert(q, rq);
@@ -626,9 +624,16 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 	rq->q = q;
 
 	switch (where) {
+	case ELEVATOR_INSERT_REQUEUE:
+		/*
+		 * Most requeues happen because of a busy condition,
+		 * don't force unplug of the queue for that case.
+		 * Clear unplug_it and fall through.
+		 */
+		unplug_it = 0;
+
 	case ELEVATOR_INSERT_FRONT:
 		rq->cmd_flags |= REQ_SOFTBARRIER;
-
 		list_add(&rq->queuelist, &q->queue_head);
 		break;
 
@@ -668,36 +673,6 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		q->elevator->ops->elevator_add_req_fn(q, rq);
 		break;
 
-	case ELEVATOR_INSERT_REQUEUE:
-		/*
-		 * If ordered flush isn't in progress, we do front
-		 * insertion; otherwise, requests should be requeued
-		 * in ordseq order.
-		 */
-		rq->cmd_flags |= REQ_SOFTBARRIER;
-
-		/*
-		 * Most requeues happen because of a busy condition,
-		 * don't force unplug of the queue for that case.
-		 */
-		unplug_it = 0;
-
-		if (q->ordseq == 0) {
-			list_add(&rq->queuelist, &q->queue_head);
-			break;
-		}
-
-		ordseq = blk_ordered_req_seq(rq);
-
-		list_for_each(pos, &q->queue_head) {
-			struct request *pos_rq = list_entry_rq(pos);
-			if (ordseq <= blk_ordered_req_seq(pos_rq))
-				break;
-		}
-
-		list_add_tail(&rq->queuelist, pos);
-		break;
-
 	default:
 		printk(KERN_ERR "%s: bad insertion point %d\n",
 		       __func__, where);
@@ -716,26 +691,8 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 void __elv_add_request(struct request_queue *q, struct request *rq, int where,
 		       int plug)
 {
-	if (q->ordcolor)
-		rq->cmd_flags |= REQ_ORDERED_COLOR;
-
 	if (rq->cmd_flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) {
-		/*
-		 * toggle ordered color
-		 */
-		if (rq->cmd_flags & REQ_HARDBARRIER)
-			q->ordcolor ^= 1;
-
-		/*
-		 * barriers implicitly indicate back insertion
-		 */
-		if (where == ELEVATOR_INSERT_SORT)
-			where = ELEVATOR_INSERT_BACK;
-
-		/*
-		 * this request is scheduling boundary, update
-		 * end_sector
-		 */
+		/* barriers are scheduling boundary, update end_sector */
 		if (rq->cmd_type == REQ_TYPE_FS ||
 		    (rq->cmd_flags & REQ_DISCARD)) {
 			q->end_sector = rq_end_sector(rq);
@@ -855,24 +812,6 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 		    e->ops->elevator_completed_req_fn)
 			e->ops->elevator_completed_req_fn(q, rq);
 	}
-
-	/*
-	 * Check if the queue is waiting for fs requests to be
-	 * drained for flush sequence.
-	 */
-	if (unlikely(q->ordseq)) {
-		struct request *next = NULL;
-
-		if (!list_empty(&q->queue_head))
-			next = list_entry_rq(q->queue_head.next);
-
-		if (!queue_in_flight(q) &&
-		    blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
-		    (!next || blk_ordered_req_seq(next) > QUEUE_ORDSEQ_DRAIN)) {
-			blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
-			__blk_run_queue(q);
-		}
-	}
 }
 
 #define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)
diff --git a/block/ioctl.c b/block/ioctl.c
index 2c15fe0912c..d724ceb1d46 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -116,7 +116,7 @@ static int blkdev_reread_part(struct block_device *bdev)
 static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 			     uint64_t len, int secure)
 {
-	unsigned long flags = BLKDEV_IFL_WAIT;
+	unsigned long flags = 0;
 
 	if (start & 511)
 		return -EINVAL;
@@ -128,7 +128,7 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 	if (start + len > (bdev->bd_inode->i_size >> 9))
 		return -EINVAL;
 	if (secure)
-		flags |= BLKDEV_IFL_SECURE;
+		flags |= BLKDEV_DISCARD_SECURE;
 	return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags);
 }