From dd831006d5be7f74c3fe7aef82380c51c3637960 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 3 Sep 2010 11:56:16 +0200
Subject: block: misc cleanups in barrier code

Make the following cleanups in preparation of barrier/flush update.

* blk_do_ordered() declaration is moved from include/linux/blkdev.h to
  block/blk.h.

* blk_do_ordered() now returns pointer to struct request, with %NULL
  meaning "try the next request" and ERR_PTR(-EAGAIN) "try again
  later".  The third case will be dropped with further changes.

* In the initialization of proxy barrier request, data direction is
  already set by init_request_from_bio().  Drop unnecessary explicit
  REQ_WRITE setting and move init_request_from_bio() above REQ_FUA
  flag setting.

* add_request() is collapsed into __make_request().

These changes don't make any functional difference.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'block/blk.h')

diff --git a/block/blk.h b/block/blk.h
index 6e7dc87141e4..874eb4ea8093 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_ordered(struct request_queue *q, struct request *rq);
+
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
 	struct request *rq;
@@ -58,8 +60,9 @@ 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))
-				return rq;
+			rq = blk_do_ordered(q, rq);
+			if (rq)
+				return !IS_ERR(rq) ? rq : NULL;
 		}
 
 		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
-- 
cgit v1.2.3-70-g09d2


From 28e7d1845216538303bb95d679d8fd4de50e2f1a Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 3 Sep 2010 11:56:16 +0200
Subject: block: drop barrier ordering by queue draining

Filesystems will take all the responsibilities for ordering requests
around commit writes and will only indicate how the commit writes
themselves should be handled by block layers.  This patch drops
barrier ordering by queue draining from block layer.  Ordering by
draining implementation was somewhat invasive to request handling.
List of notable changes follow.

* Each queue has 1 bit color which is flipped on each barrier issue.
  This is used to track whether a given request is issued before the
  current barrier or not.  REQ_ORDERED_COLOR flag and coloring
  implementation in __elv_add_request() are removed.

* Requests which shouldn't be processed yet for draining were stalled
  by returning -EAGAIN from blk_do_ordered() according to the test
  result between blk_ordered_req_seq() and blk_blk_ordered_cur_seq().
  This logic is removed.

* Draining completion logic in elv_completed_request() removed.

* All barrier sequence requests were queued to request queue and then
  trckled to lower layer according to progress and thus maintaining
  request orders during requeue was necessary.  This is replaced by
  queueing the next request in the barrier sequence only after the
  current one is complete from blk_ordered_complete_seq(), which
  removes the need for multiple proxy requests in struct request_queue
  and the request sorting logic in the ELEVATOR_INSERT_REQUEUE path of
  elv_insert().

* As barriers no longer have ordering constraints, there's no need to
  dump the whole elevator onto the dispatch queue on each barrier.
  Insert barriers at the front instead.

* If other barrier requests come to the front of the dispatch queue
  while one is already in progress, they are stored in
  q->pending_barriers and restored to dispatch queue one-by-one after
  each barrier completion from blk_ordered_complete_seq().

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-barrier.c       | 220 ++++++++++++++++++----------------------------
 block/blk-core.c          |  11 ++-
 block/blk.h               |   2 +-
 block/elevator.c          |  79 ++---------------
 include/linux/blk_types.h |   2 -
 include/linux/blkdev.h    |  19 ++--
 6 files changed, 113 insertions(+), 220 deletions(-)

(limited to 'block/blk.h')

diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index f1be85ba2bb5..e8b2e5c091b1 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -9,6 +9,8 @@
 
 #include "blk.h"
 
+static struct request *queue_next_ordseq(struct request_queue *q);
+
 /*
  * Cache flushing for ordered writes handling
  */
@@ -19,38 +21,10 @@ unsigned blk_ordered_cur_seq(struct request_queue *q)
 	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)
+static struct request *blk_ordered_complete_seq(struct request_queue *q,
+						unsigned seq, int error)
 {
-	struct request *rq;
+	struct request *next_rq = NULL;
 
 	if (error && !q->orderr)
 		q->orderr = error;
@@ -58,16 +32,22 @@ bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int 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;
+	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE) {
+		/* not complete yet, queue the next ordered sequence */
+		next_rq = queue_next_ordseq(q);
+	} else {
+		/* complete this barrier request */
+		__blk_end_request_all(q->orig_bar_rq, q->orderr);
+		q->orig_bar_rq = NULL;
+		q->ordseq = 0;
+
+		/* dispatch the next barrier if there's one */
+		if (!list_empty(&q->pending_barriers)) {
+			next_rq = list_entry_rq(q->pending_barriers.next);
+			list_move(&next_rq->queuelist, &q->queue_head);
+		}
+	}
+	return next_rq;
 }
 
 static void pre_flush_end_io(struct request *rq, int error)
@@ -88,133 +68,105 @@ static void post_flush_end_io(struct request *rq, int error)
 	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
 }
 
-static void queue_flush(struct request_queue *q, unsigned which)
+static void queue_flush(struct request_queue *q, struct request *rq,
+			rq_end_io_fn *end_io)
 {
-	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->cmd_flags = 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 struct request *start_ordered(struct request_queue *q,
-					    struct request *rq)
+static struct request *queue_next_ordseq(struct request_queue *q)
 {
-	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);
-
-	/* 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;
+	struct request *rq = &q->bar_rq;
 
-	if (q->ordered & QUEUE_ORDERED_DO_BAR) {
-		rq = &q->bar_rq;
+	switch (blk_ordered_cur_seq(q)) {
+	case QUEUE_ORDSEQ_PREFLUSH:
+		queue_flush(q, rq, pre_flush_end_io);
+		break;
 
+	case QUEUE_ORDSEQ_BAR:
 		/* initialize proxy request and queue it */
 		blk_rq_init(q, rq);
 		init_request_from_bio(rq, q->orig_bar_rq->bio);
+		rq->cmd_flags &= ~REQ_HARDBARRIER;
 		if (q->ordered & QUEUE_ORDERED_DO_FUA)
 			rq->cmd_flags |= REQ_FUA;
 		rq->end_io = bar_end_io;
 
 		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
-	} else
-		skip |= QUEUE_ORDSEQ_BAR;
+		break;
 
-	if (q->ordered & QUEUE_ORDERED_DO_PREFLUSH) {
-		queue_flush(q, QUEUE_ORDERED_DO_PREFLUSH);
-		rq = &q->pre_flush_rq;
-	} else
-		skip |= QUEUE_ORDSEQ_PREFLUSH;
+	case QUEUE_ORDSEQ_POSTFLUSH:
+		queue_flush(q, rq, post_flush_end_io);
+		break;
 
-	if (queue_in_flight(q))
-		rq = NULL;
-	else
-		skip |= QUEUE_ORDSEQ_DRAIN;
-
-	/*
-	 * Complete skipped sequences.  If whole sequence is complete,
-	 * return %NULL to tell elevator that this request is gone.
-	 */
-	if (blk_ordered_complete_seq(q, skip, 0))
-		rq = NULL;
+	default:
+		BUG();
+	}
 	return rq;
 }
 
 struct request *blk_do_ordered(struct request_queue *q, struct request *rq)
 {
-	const int is_barrier = rq->cmd_type == REQ_TYPE_FS &&
-				(rq->cmd_flags & REQ_HARDBARRIER);
-
-	if (!q->ordseq) {
-		if (!is_barrier)
-			return rq;
-
-		if (q->next_ordered != QUEUE_ORDERED_NONE)
-			return start_ordered(q, rq);
-		else {
-			/*
-			 * Queue ordering not supported.  Terminate
-			 * with prejudice.
-			 */
-			blk_dequeue_request(rq);
-			__blk_end_request_all(rq, -EOPNOTSUPP);
-			return NULL;
-		}
+	unsigned skip = 0;
+
+	if (!(rq->cmd_flags & REQ_HARDBARRIER))
+		return rq;
+
+	if (q->ordseq) {
+		/*
+		 * Barrier is already in progress and they can't be
+		 * processed in parallel.  Queue for later processing.
+		 */
+		list_move_tail(&rq->queuelist, &q->pending_barriers);
+		return NULL;
+	}
+
+	if (unlikely(q->next_ordered == QUEUE_ORDERED_NONE)) {
+		/*
+		 * Queue ordering not supported.  Terminate
+		 * with prejudice.
+		 */
+		blk_dequeue_request(rq);
+		__blk_end_request_all(rq, -EOPNOTSUPP);
+		return NULL;
 	}
 
 	/*
-	 * Ordered sequence in progress
+	 * Start a new ordered sequence
 	 */
+	q->orderr = 0;
+	q->ordered = q->next_ordered;
+	q->ordseq |= QUEUE_ORDSEQ_STARTED;
 
-	/* 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 rq;
+	/*
+	 * 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);
 
-	/* 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))
-		rq = ERR_PTR(-EAGAIN);
+	/* stash away the original request */
+	blk_dequeue_request(rq);
+	q->orig_bar_rq = rq;
 
-	return rq;
+	if (!(q->ordered & QUEUE_ORDERED_DO_PREFLUSH))
+		skip |= QUEUE_ORDSEQ_PREFLUSH;
+
+	if (!(q->ordered & QUEUE_ORDERED_DO_BAR))
+		skip |= QUEUE_ORDSEQ_BAR;
+
+	if (!(q->ordered & QUEUE_ORDERED_DO_POSTFLUSH))
+		skip |= QUEUE_ORDSEQ_POSTFLUSH;
+
+	/* complete skipped sequences and return the first sequence */
+	return blk_ordered_complete_seq(q, skip, 0);
 }
 
 static void bio_end_empty_barrier(struct bio *bio, int err)
diff --git a/block/blk-core.c b/block/blk-core.c
index f8d37a8e2c55..d316662682c8 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -520,6 +520,7 @@ 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_barriers);
 	INIT_WORK(&q->unplug_work, blk_unplug_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
@@ -1185,6 +1186,7 @@ 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 int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	int where = ELEVATOR_INSERT_SORT;
 	int rw_flags;
 
 	/* REQ_HARDBARRIER is no more */
@@ -1203,7 +1205,12 @@ 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_HARDBARRIER) {
+		where = ELEVATOR_INSERT_FRONT;
+		goto get_rq;
+	}
+
+	if (elv_queue_empty(q))
 		goto get_rq;
 
 	el_ret = elv_merge(q, &req, bio);
@@ -1303,7 +1310,7 @@ get_rq:
 
 	/* insert the request into the elevator */
 	drive_stat_acct(req, 1);
-	__elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
+	__elv_add_request(q, req, where, 0);
 out:
 	if (unplug || !queue_should_plug(q))
 		__generic_unplug_device(q);
diff --git a/block/blk.h b/block/blk.h
index 874eb4ea8093..08081e4b294e 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -62,7 +62,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			rq = list_entry_rq(q->queue_head.next);
 			rq = blk_do_ordered(q, rq);
 			if (rq)
-				return !IS_ERR(rq) ? rq : NULL;
+				return rq;
 		}
 
 		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
diff --git a/block/elevator.c b/block/elevator.c
index ec585c9554d3..241c69c45c5f 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/include/linux/blk_types.h b/include/linux/blk_types.h
index ca83a97c9715..9192282b4259 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -143,7 +143,6 @@ enum rq_flag_bits {
 	__REQ_FAILED,		/* set if the request failed */
 	__REQ_QUIET,		/* don't worry about errors */
 	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
-	__REQ_ORDERED_COLOR,	/* is before or after barrier */
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_COPY_USER,	/* contains copies of user pages */
 	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
@@ -184,7 +183,6 @@ enum rq_flag_bits {
 #define REQ_FAILED		(1 << __REQ_FAILED)
 #define REQ_QUIET		(1 << __REQ_QUIET)
 #define REQ_PREEMPT		(1 << __REQ_PREEMPT)
-#define REQ_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)
 #define REQ_ALLOCED		(1 << __REQ_ALLOCED)
 #define REQ_COPY_USER		(1 << __REQ_COPY_USER)
 #define REQ_INTEGRITY		(1 << __REQ_INTEGRITY)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 996549d71923..20a3710a481b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -360,9 +360,10 @@ struct request_queue
 	unsigned int		flush_flags;
 
 	unsigned int		ordered, next_ordered, ordseq;
-	int			orderr, ordcolor;
-	struct request		pre_flush_rq, bar_rq, post_flush_rq;
+	int			orderr;
+	struct request		bar_rq;
 	struct request		*orig_bar_rq;
+	struct list_head	pending_barriers;
 
 	struct mutex		sysfs_lock;
 
@@ -491,12 +492,11 @@ enum {
 	/*
 	 * Ordered operation sequence
 	 */
-	QUEUE_ORDSEQ_STARTED	= 0x01,	/* flushing in progress */
-	QUEUE_ORDSEQ_DRAIN	= 0x02,	/* waiting for the queue to be drained */
-	QUEUE_ORDSEQ_PREFLUSH	= 0x04,	/* pre-flushing in progress */
-	QUEUE_ORDSEQ_BAR	= 0x08,	/* original barrier req in progress */
-	QUEUE_ORDSEQ_POSTFLUSH	= 0x10,	/* post-flushing in progress */
-	QUEUE_ORDSEQ_DONE	= 0x20,
+	QUEUE_ORDSEQ_STARTED	= (1 << 0), /* flushing in progress */
+	QUEUE_ORDSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
+	QUEUE_ORDSEQ_BAR	= (1 << 2), /* barrier write in progress */
+	QUEUE_ORDSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
+	QUEUE_ORDSEQ_DONE	= (1 << 4),
 };
 
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
@@ -869,9 +869,6 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern void blk_queue_flush(struct request_queue *q, unsigned int flush);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
-extern unsigned blk_ordered_cur_seq(struct request_queue *);
-extern unsigned blk_ordered_req_seq(struct request *);
-extern bool blk_ordered_complete_seq(struct request_queue *, unsigned, int);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
-- 
cgit v1.2.3-70-g09d2


From dd4c133f387c48f526022860ad70354637a80f4c Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 3 Sep 2010 11:56:16 +0200
Subject: block: rename barrier/ordered to flush

With ordering requirements dropped, barrier and ordered are misnomers.
Now all block layer does is sequencing FLUSH and FUA.  Rename them to
flush.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-core.c       | 21 ++++++-----
 block/blk-flush.c      | 98 +++++++++++++++++++++++++-------------------------
 block/blk.h            |  4 +--
 include/linux/blkdev.h | 24 ++++++-------
 4 files changed, 72 insertions(+), 75 deletions(-)

(limited to 'block/blk.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index d316662682c8..8870ae40179d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -136,7 +136,7 @@ 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))
@@ -160,13 +160,12 @@ 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;
 	}
 }
 
@@ -520,7 +519,7 @@ 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_barriers);
+	INIT_LIST_HEAD(&q->pending_flushes);
 	INIT_WORK(&q->unplug_work, blk_unplug_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
@@ -1764,11 +1763,11 @@ 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;
diff --git a/block/blk-flush.c b/block/blk-flush.c
index e8b2e5c091b1..dd873225da97 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -9,41 +9,38 @@
 
 #include "blk.h"
 
-static struct request *queue_next_ordseq(struct request_queue *q);
+static struct request *queue_next_fseq(struct request_queue *q);
 
-/*
- * Cache flushing for ordered writes handling
- */
-unsigned blk_ordered_cur_seq(struct request_queue *q)
+unsigned blk_flush_cur_seq(struct request_queue *q)
 {
-	if (!q->ordseq)
+	if (!q->flush_seq)
 		return 0;
-	return 1 << ffz(q->ordseq);
+	return 1 << ffz(q->flush_seq);
 }
 
-static struct request *blk_ordered_complete_seq(struct request_queue *q,
-						unsigned seq, int error)
+static struct request *blk_flush_complete_seq(struct request_queue *q,
+					      unsigned seq, int error)
 {
 	struct request *next_rq = NULL;
 
-	if (error && !q->orderr)
-		q->orderr = error;
+	if (error && !q->flush_err)
+		q->flush_err = error;
 
-	BUG_ON(q->ordseq & seq);
-	q->ordseq |= seq;
+	BUG_ON(q->flush_seq & seq);
+	q->flush_seq |= seq;
 
-	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE) {
-		/* not complete yet, queue the next ordered sequence */
-		next_rq = queue_next_ordseq(q);
+	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 barrier request */
-		__blk_end_request_all(q->orig_bar_rq, q->orderr);
-		q->orig_bar_rq = NULL;
-		q->ordseq = 0;
-
-		/* dispatch the next barrier if there's one */
-		if (!list_empty(&q->pending_barriers)) {
-			next_rq = list_entry_rq(q->pending_barriers.next);
+		/* 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);
 		}
 	}
@@ -53,19 +50,19 @@ static struct request *blk_ordered_complete_seq(struct request_queue *q,
 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);
+	blk_flush_complete_seq(rq->q, QUEUE_FSEQ_PREFLUSH, error);
 }
 
-static void bar_end_io(struct request *rq, int error)
+static void flush_data_end_io(struct request *rq, int error)
 {
 	elv_completed_request(rq->q, rq);
-	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_BAR, error);
+	blk_flush_complete_seq(rq->q, QUEUE_FSEQ_DATA, 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);
+	blk_flush_complete_seq(rq->q, QUEUE_FSEQ_POSTFLUSH, error);
 }
 
 static void queue_flush(struct request_queue *q, struct request *rq,
@@ -74,34 +71,34 @@ static void queue_flush(struct request_queue *q, struct request *rq,
 	blk_rq_init(q, rq);
 	rq->cmd_type = REQ_TYPE_FS;
 	rq->cmd_flags = REQ_FLUSH;
-	rq->rq_disk = q->orig_bar_rq->rq_disk;
+	rq->rq_disk = q->orig_flush_rq->rq_disk;
 	rq->end_io = end_io;
 
 	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
 }
 
-static struct request *queue_next_ordseq(struct request_queue *q)
+static struct request *queue_next_fseq(struct request_queue *q)
 {
-	struct request *rq = &q->bar_rq;
+	struct request *rq = &q->flush_rq;
 
-	switch (blk_ordered_cur_seq(q)) {
-	case QUEUE_ORDSEQ_PREFLUSH:
+	switch (blk_flush_cur_seq(q)) {
+	case QUEUE_FSEQ_PREFLUSH:
 		queue_flush(q, rq, pre_flush_end_io);
 		break;
 
-	case QUEUE_ORDSEQ_BAR:
+	case QUEUE_FSEQ_DATA:
 		/* initialize proxy request and queue it */
 		blk_rq_init(q, rq);
-		init_request_from_bio(rq, q->orig_bar_rq->bio);
+		init_request_from_bio(rq, q->orig_flush_rq->bio);
 		rq->cmd_flags &= ~REQ_HARDBARRIER;
 		if (q->ordered & QUEUE_ORDERED_DO_FUA)
 			rq->cmd_flags |= REQ_FUA;
-		rq->end_io = bar_end_io;
+		rq->end_io = flush_data_end_io;
 
 		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
 		break;
 
-	case QUEUE_ORDSEQ_POSTFLUSH:
+	case QUEUE_FSEQ_POSTFLUSH:
 		queue_flush(q, rq, post_flush_end_io);
 		break;
 
@@ -111,19 +108,20 @@ static struct request *queue_next_ordseq(struct request_queue *q)
 	return rq;
 }
 
-struct request *blk_do_ordered(struct request_queue *q, struct request *rq)
+struct request *blk_do_flush(struct request_queue *q, struct request *rq)
 {
 	unsigned skip = 0;
 
 	if (!(rq->cmd_flags & REQ_HARDBARRIER))
 		return rq;
 
-	if (q->ordseq) {
+	if (q->flush_seq) {
 		/*
-		 * Barrier is already in progress and they can't be
-		 * processed in parallel.  Queue for later processing.
+		 * Sequenced flush is already in progress and they
+		 * can't be processed in parallel.  Queue for later
+		 * processing.
 		 */
-		list_move_tail(&rq->queuelist, &q->pending_barriers);
+		list_move_tail(&rq->queuelist, &q->pending_flushes);
 		return NULL;
 	}
 
@@ -138,11 +136,11 @@ struct request *blk_do_ordered(struct request_queue *q, struct request *rq)
 	}
 
 	/*
-	 * Start a new ordered sequence
+	 * Start a new flush sequence
 	 */
-	q->orderr = 0;
+	q->flush_err = 0;
 	q->ordered = q->next_ordered;
-	q->ordseq |= QUEUE_ORDSEQ_STARTED;
+	q->flush_seq |= QUEUE_FSEQ_STARTED;
 
 	/*
 	 * For an empty barrier, there's no actual BAR request, which
@@ -154,19 +152,19 @@ struct request *blk_do_ordered(struct request_queue *q, struct request *rq)
 
 	/* stash away the original request */
 	blk_dequeue_request(rq);
-	q->orig_bar_rq = rq;
+	q->orig_flush_rq = rq;
 
 	if (!(q->ordered & QUEUE_ORDERED_DO_PREFLUSH))
-		skip |= QUEUE_ORDSEQ_PREFLUSH;
+		skip |= QUEUE_FSEQ_PREFLUSH;
 
 	if (!(q->ordered & QUEUE_ORDERED_DO_BAR))
-		skip |= QUEUE_ORDSEQ_BAR;
+		skip |= QUEUE_FSEQ_DATA;
 
 	if (!(q->ordered & QUEUE_ORDERED_DO_POSTFLUSH))
-		skip |= QUEUE_ORDSEQ_POSTFLUSH;
+		skip |= QUEUE_FSEQ_POSTFLUSH;
 
 	/* complete skipped sequences and return the first sequence */
-	return blk_ordered_complete_seq(q, skip, 0);
+	return blk_flush_complete_seq(q, skip, 0);
 }
 
 static void bio_end_empty_barrier(struct bio *bio, int err)
diff --git a/block/blk.h b/block/blk.h
index 08081e4b294e..24b92bd78f37 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -51,7 +51,7 @@ static inline void blk_clear_rq_complete(struct request *rq)
  */
 #define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
 
-struct request *blk_do_ordered(struct request_queue *q, struct request *rq);
+struct request *blk_do_flush(struct request_queue *q, struct request *rq);
 
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
@@ -60,7 +60,7 @@ 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);
-			rq = blk_do_ordered(q, rq);
+			rq = blk_do_flush(q, rq);
 			if (rq)
 				return rq;
 		}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 20a3710a481b..1cd83ec077db 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -357,13 +357,13 @@ struct request_queue
 	/*
 	 * for flush operations
 	 */
+	unsigned int		ordered, next_ordered;
 	unsigned int		flush_flags;
-
-	unsigned int		ordered, next_ordered, ordseq;
-	int			orderr;
-	struct request		bar_rq;
-	struct request		*orig_bar_rq;
-	struct list_head	pending_barriers;
+	unsigned int		flush_seq;
+	int			flush_err;
+	struct request		flush_rq;
+	struct request		*orig_flush_rq;
+	struct list_head	pending_flushes;
 
 	struct mutex		sysfs_lock;
 
@@ -490,13 +490,13 @@ enum {
 					  QUEUE_ORDERED_DO_FUA,
 
 	/*
-	 * Ordered operation sequence
+	 * FLUSH/FUA sequences.
 	 */
-	QUEUE_ORDSEQ_STARTED	= (1 << 0), /* flushing in progress */
-	QUEUE_ORDSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
-	QUEUE_ORDSEQ_BAR	= (1 << 2), /* barrier write in progress */
-	QUEUE_ORDSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
-	QUEUE_ORDSEQ_DONE	= (1 << 4),
+	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),
 };
 
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
-- 
cgit v1.2.3-70-g09d2


From 4fed947cb311e5aa51781d316cefca836352f6ce Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 3 Sep 2010 11:56:17 +0200
Subject: block: implement REQ_FLUSH/FUA based interface for FLUSH/FUA requests

Now that the backend conversion is complete, export sequenced
FLUSH/FUA capability through REQ_FLUSH/FUA flags.  REQ_FLUSH means the
device cache should be flushed before executing the request.  REQ_FUA
means that the data in the request should be on non-volatile media on
completion.

Block layer will choose the correct way of implementing the semantics
and execute it.  The request may be passed to the device directly if
the device can handle it; otherwise, it will be sequenced using one or
more proxy requests.  Devices will never see REQ_FLUSH and/or FUA
which it doesn't support.

Also, unlike the original REQ_HARDBARRIER, REQ_FLUSH/FUA requests are
never failed with -EOPNOTSUPP.  If the underlying device doesn't
support FLUSH/FUA, the block layer simply make those noop.  IOW, it no
longer distinguishes between writeback cache which doesn't support
cache flush and writethrough/no cache.  Devices which have WB cache
w/o flush are very difficult to come by these days and there's nothing
much we can do anyway, so it doesn't make sense to require everyone to
implement -EOPNOTSUPP handling.  This will simplify filesystems and
block drivers as they can drop -EOPNOTSUPP retry logic for barriers.

* QUEUE_ORDERED_* are removed and QUEUE_FSEQ_* are moved into
  blk-flush.c.

* REQ_FLUSH w/o data can also be directly passed to drivers without
  sequencing but some drivers assume that zero length requests don't
  have rq->bio which isn't true for these requests requiring the use
  of proxy requests.

* REQ_COMMON_MASK now includes REQ_FLUSH | REQ_FUA so that they are
  copied from bio to request.

* WRITE_BARRIER is marked deprecated and WRITE_FLUSH, WRITE_FUA and
  WRITE_FLUSH_FUA are added.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-core.c            |  2 +-
 block/blk-flush.c           | 85 ++++++++++++++++++++++++---------------------
 block/blk.h                 |  3 ++
 include/linux/blk_types.h   |  2 +-
 include/linux/blkdev.h      | 38 ++------------------
 include/linux/buffer_head.h |  2 +-
 include/linux/fs.h          | 19 ++++++----
 7 files changed, 67 insertions(+), 84 deletions(-)

(limited to 'block/blk.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index 8870ae40179d..18455c4f618a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1204,7 +1204,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (bio->bi_rw & REQ_HARDBARRIER) {
+	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
 		where = ELEVATOR_INSERT_FRONT;
 		goto get_rq;
 	}
diff --git a/block/blk-flush.c b/block/blk-flush.c
index dd873225da97..452c552e9ead 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -1,5 +1,5 @@
 /*
- * Functions related to barrier IO handling
+ * Functions to sequence FLUSH and FUA writes.
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -9,6 +9,15 @@
 
 #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)
@@ -79,6 +88,7 @@ static void queue_flush(struct request_queue *q, struct request *rq,
 
 static struct request *queue_next_fseq(struct request_queue *q)
 {
+	struct request *orig_rq = q->orig_flush_rq;
 	struct request *rq = &q->flush_rq;
 
 	switch (blk_flush_cur_seq(q)) {
@@ -87,12 +97,11 @@ static struct request *queue_next_fseq(struct request_queue *q)
 		break;
 
 	case QUEUE_FSEQ_DATA:
-		/* initialize proxy request and queue it */
+		/* initialize proxy request, inherit FLUSH/FUA and queue it */
 		blk_rq_init(q, rq);
-		init_request_from_bio(rq, q->orig_flush_rq->bio);
-		rq->cmd_flags &= ~REQ_HARDBARRIER;
-		if (q->ordered & QUEUE_ORDERED_DO_FUA)
-			rq->cmd_flags |= REQ_FUA;
+		init_request_from_bio(rq, orig_rq->bio);
+		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;
 
 		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
@@ -110,60 +119,58 @@ static struct request *queue_next_fseq(struct request_queue *q)
 
 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;
 
-	if (!(rq->cmd_flags & REQ_HARDBARRIER))
+	/*
+	 * 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) {
-		/*
-		 * Sequenced flush is already in progress and they
-		 * can't be processed in parallel.  Queue for later
-		 * processing.
-		 */
 		list_move_tail(&rq->queuelist, &q->pending_flushes);
 		return NULL;
 	}
 
-	if (unlikely(q->next_ordered == QUEUE_ORDERED_NONE)) {
-		/*
-		 * Queue ordering not supported.  Terminate
-		 * with prejudice.
-		 */
-		blk_dequeue_request(rq);
-		__blk_end_request_all(rq, -EOPNOTSUPP);
-		return NULL;
-	}
-
 	/*
 	 * Start a new flush sequence
 	 */
 	q->flush_err = 0;
-	q->ordered = q->next_ordered;
 	q->flush_seq |= QUEUE_FSEQ_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);
-
-	/* stash away the original request */
+	/* 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;
 
-	if (!(q->ordered & QUEUE_ORDERED_DO_PREFLUSH))
+	/* skip unneded sequences and return the first one */
+	if (!do_preflush)
 		skip |= QUEUE_FSEQ_PREFLUSH;
-
-	if (!(q->ordered & QUEUE_ORDERED_DO_BAR))
+	if (!blk_rq_sectors(rq))
 		skip |= QUEUE_FSEQ_DATA;
-
-	if (!(q->ordered & QUEUE_ORDERED_DO_POSTFLUSH))
+	if (!do_postflush)
 		skip |= QUEUE_FSEQ_POSTFLUSH;
-
-	/* complete skipped sequences and return the first sequence */
 	return blk_flush_complete_seq(q, skip, 0);
 }
 
diff --git a/block/blk.h b/block/blk.h
index 24b92bd78f37..a09c18b19116 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -60,6 +60,9 @@ 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 (!(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/include/linux/blk_types.h b/include/linux/blk_types.h
index 9192282b4259..179799479e6f 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -167,7 +167,7 @@ enum rq_flag_bits {
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
 	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \
-	 REQ_META| REQ_DISCARD | REQ_NOIDLE)
+	 REQ_META | REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
 
 #define REQ_UNPLUG		(1 << __REQ_UNPLUG)
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1cd83ec077db..8ef705f800ab 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -357,7 +357,6 @@ struct request_queue
 	/*
 	 * for flush operations
 	 */
-	unsigned int		ordered, next_ordered;
 	unsigned int		flush_flags;
 	unsigned int		flush_seq;
 	int			flush_err;
@@ -465,40 +464,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 	__clear_bit(flag, &q->queue_flags);
 }
 
-enum {
-	/*
-	 * Hardbarrier is supported with one of the following methods.
-	 *
-	 * NONE		: hardbarrier unsupported
-	 * DRAIN	: ordering by draining is enough
-	 * DRAIN_FLUSH	: ordering by draining w/ pre and post flushes
-	 * DRAIN_FUA	: ordering by draining w/ pre flush and FUA write
-	 */
-	QUEUE_ORDERED_DO_PREFLUSH	= 0x10,
-	QUEUE_ORDERED_DO_BAR		= 0x20,
-	QUEUE_ORDERED_DO_POSTFLUSH	= 0x40,
-	QUEUE_ORDERED_DO_FUA		= 0x80,
-
-	QUEUE_ORDERED_NONE		= 0x00,
-
-	QUEUE_ORDERED_DRAIN		= QUEUE_ORDERED_DO_BAR,
-	QUEUE_ORDERED_DRAIN_FLUSH	= QUEUE_ORDERED_DRAIN |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_POSTFLUSH,
-	QUEUE_ORDERED_DRAIN_FUA		= QUEUE_ORDERED_DRAIN |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_FUA,
-
-	/*
-	 * FLUSH/FUA sequences.
-	 */
-	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),
-};
-
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
@@ -578,7 +543,8 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync)
  * it already be started by driver.
  */
 #define RQ_NOMERGE_FLAGS	\
-	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER)
+	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER | \
+	 REQ_FLUSH | REQ_FUA)
 #define rq_mergeable(rq)	\
 	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
 	 (((rq)->cmd_flags & REQ_DISCARD) || \
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index ec94c12f21da..fc999f583fda 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -32,7 +32,7 @@ enum bh_state_bits {
 	BH_Delay,	/* Buffer is not yet allocated on disk */
 	BH_Boundary,	/* Block is followed by a discontiguity */
 	BH_Write_EIO,	/* I/O error on write */
-	BH_Eopnotsupp,	/* operation not supported (barrier) */
+	BH_Eopnotsupp,	/* DEPRECATED: operation not supported (barrier) */
 	BH_Unwritten,	/* Buffer is allocated on disk but not written */
 	BH_Quiet,	/* Buffer Error Prinks to be quiet */
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 76041b614758..352c48627381 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -135,12 +135,13 @@ struct inodes_stat_t {
  *			immediately after submission. The write equivalent
  *			of READ_SYNC.
  * WRITE_ODIRECT_PLUG	Special case write for O_DIRECT only.
- * WRITE_BARRIER	Like WRITE_SYNC, but tells the block layer that all
- *			previously submitted writes must be safely on storage
- *			before this one is started. Also guarantees that when
- *			this write is complete, it itself is also safely on
- *			storage. Prevents reordering of writes on both sides
- *			of this IO.
+ * WRITE_BARRIER	DEPRECATED. Always fails. Use FLUSH/FUA instead.
+ * WRITE_FLUSH		Like WRITE_SYNC but with preceding cache flush.
+ * WRITE_FUA		Like WRITE_SYNC but data is guaranteed to be on
+ *			non-volatile media on completion.
+ * WRITE_FLUSH_FUA	Combination of WRITE_FLUSH and FUA. The IO is preceded
+ *			by a cache flush and data is guaranteed to be on
+ *			non-volatile media on completion.
  *
  */
 #define RW_MASK			REQ_WRITE
@@ -158,6 +159,12 @@ struct inodes_stat_t {
 #define WRITE_META		(WRITE | REQ_META)
 #define WRITE_BARRIER		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
 				 REQ_HARDBARRIER)
+#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FLUSH)
+#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FUA)
+#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FLUSH | REQ_FUA)
 
 /*
  * These aren't really reads or writes, they pass down information about
-- 
cgit v1.2.3-70-g09d2