diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index 4ed7b5c..d915c16 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@@ -343,34 +343,6 @@
 
 CFQ sysfs tunable
 =================
-/sys/block/<disk>/queue/iosched/group_isolation
------------------------------------------------
-
-If group_isolation=1, it provides stronger isolation between groups at the
-expense of throughput. By default group_isolation is 0. In general that
-means that if group_isolation=0, expect fairness for sequential workload
-only. Set group_isolation=1 to see fairness for random IO workload also.
-
-Generally CFQ will put random seeky workload in sync-noidle category. CFQ
-will disable idling on these queues and it does a collective idling on group
-of such queues. Generally these are slow moving queues and if there is a
-sync-noidle service tree in each group, that group gets exclusive access to
-disk for certain period. That means it will bring the throughput down if
-group does not have enough IO to drive deeper queue depths and utilize disk
-capacity to the fullest in the slice allocated to it. But the flip side is
-that even a random reader should get better latencies and overall throughput
-if there are lots of sequential readers/sync-idle workload running in the
-system.
-
-If group_isolation=0, then CFQ automatically moves all the random seeky queues
-in the root group. That means there will be no service differentiation for
-that kind of workload. This leads to better throughput as we do collective
-idling on root sync-noidle tree.
-
-By default one should run with group_isolation=0. If that is not sufficient
-and one wants stronger isolation between groups, then set group_isolation=1
-but this will come at cost of reduced throughput.
-
 /sys/block/<disk>/queue/iosched/slice_idle
 ------------------------------------------
 On a faster hardware CFQ can be slow, especially with sequential workload.
diff --git a/block/blk-core.c b/block/blk-core.c
index 518dd42..74d496c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -149,39 +149,29 @@
 static void req_bio_endio(struct request *rq, struct bio *bio,
 			  unsigned int nbytes, int error)
 {
-	struct request_queue *q = rq->q;
+	if (error)
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+		error = -EIO;
 
-	if (&q->flush_rq != rq) {
-		if (error)
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
-		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-			error = -EIO;
-
-		if (unlikely(nbytes > bio->bi_size)) {
-			printk(KERN_ERR "%s: want %u bytes done, %u left\n",
-			       __func__, nbytes, bio->bi_size);
-			nbytes = bio->bi_size;
-		}
-
-		if (unlikely(rq->cmd_flags & REQ_QUIET))
-			set_bit(BIO_QUIET, &bio->bi_flags);
-
-		bio->bi_size -= nbytes;
-		bio->bi_sector += (nbytes >> 9);
-
-		if (bio_integrity(bio))
-			bio_integrity_advance(bio, nbytes);
-
-		if (bio->bi_size == 0)
-			bio_endio(bio, error);
-	} else {
-		/*
-		 * Okay, this is the sequenced flush request in
-		 * progress, just record the error;
-		 */
-		if (error && !q->flush_err)
-			q->flush_err = error;
+	if (unlikely(nbytes > bio->bi_size)) {
+		printk(KERN_ERR "%s: want %u bytes done, %u left\n",
+		       __func__, nbytes, bio->bi_size);
+		nbytes = bio->bi_size;
 	}
+
+	if (unlikely(rq->cmd_flags & REQ_QUIET))
+		set_bit(BIO_QUIET, &bio->bi_flags);
+
+	bio->bi_size -= nbytes;
+	bio->bi_sector += (nbytes >> 9);
+
+	if (bio_integrity(bio))
+		bio_integrity_advance(bio, nbytes);
+
+	/* don't actually finish bio if it's part of flush sequence */
+	if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+		bio_endio(bio, error);
 }
 
 void blk_dump_rq_flags(struct request *rq, char *msg)
@@ -390,13 +380,16 @@
  *     that its ->make_request_fn will not re-add plugging prior to calling
  *     this function.
  *
+ *     This function does not cancel any asynchronous activity arising
+ *     out of elevator or throttling code. That would require elevaotor_exit()
+ *     and blk_throtl_exit() to be called with queue lock initialized.
+ *
  */
 void blk_sync_queue(struct request_queue *q)
 {
 	del_timer_sync(&q->unplug_timer);
 	del_timer_sync(&q->timeout);
 	cancel_work_sync(&q->unplug_work);
-	throtl_shutdown_timer_wq(q);
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
@@ -457,6 +450,11 @@
 	kobject_put(&q->kobj);
 }
 
+/*
+ * Note: If a driver supplied the queue lock, it should not zap that lock
+ * unexpectedly as some queue cleanup components like elevator_exit() and
+ * blk_throtl_exit() need queue lock.
+ */
 void blk_cleanup_queue(struct request_queue *q)
 {
 	/*
@@ -475,6 +473,8 @@
 	if (q->elevator)
 		elevator_exit(q->elevator);
 
+	blk_throtl_exit(q);
+
 	blk_put_queue(q);
 }
 EXPORT_SYMBOL(blk_cleanup_queue);
@@ -541,7 +541,9 @@
 	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_LIST_HEAD(&q->flush_queue[0]);
+	INIT_LIST_HEAD(&q->flush_queue[1]);
+	INIT_LIST_HEAD(&q->flush_data_in_flight);
 	INIT_WORK(&q->unplug_work, blk_unplug_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
@@ -549,6 +551,12 @@
 	mutex_init(&q->sysfs_lock);
 	spin_lock_init(&q->__queue_lock);
 
+	/*
+	 * By default initialize queue_lock to internal lock and driver can
+	 * override it later if need be.
+	 */
+	q->queue_lock = &q->__queue_lock;
+
 	return q;
 }
 EXPORT_SYMBOL(blk_alloc_queue_node);
@@ -633,7 +641,10 @@
 	q->unprep_rq_fn		= NULL;
 	q->unplug_fn		= generic_unplug_device;
 	q->queue_flags		= QUEUE_FLAG_DEFAULT;
-	q->queue_lock		= lock;
+
+	/* Override internal queue lock with supplied lock pointer */
+	if (lock)
+		q->queue_lock		= lock;
 
 	/*
 	 * This also sets hw/phys segments, boundary and size
@@ -762,6 +773,25 @@
 }
 
 /*
+ * Determine if elevator data should be initialized when allocating the
+ * request associated with @bio.
+ */
+static bool blk_rq_should_init_elevator(struct bio *bio)
+{
+	if (!bio)
+		return true;
+
+	/*
+	 * Flush requests do not use the elevator so skip initialization.
+	 * This allows a request to share the flush and elevator data.
+	 */
+	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA))
+		return false;
+
+	return true;
+}
+
+/*
  * Get a free request, queue_lock must be held.
  * Returns NULL on failure, with queue_lock held.
  * Returns !NULL on success, with queue_lock *not held*.
@@ -773,7 +803,7 @@
 	struct request_list *rl = &q->rq;
 	struct io_context *ioc = NULL;
 	const bool is_sync = rw_is_sync(rw_flags) != 0;
-	int may_queue, priv;
+	int may_queue, priv = 0;
 
 	may_queue = elv_may_queue(q, rw_flags);
 	if (may_queue == ELV_MQUEUE_NO)
@@ -817,9 +847,11 @@
 	rl->count[is_sync]++;
 	rl->starved[is_sync] = 0;
 
-	priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
-	if (priv)
-		rl->elvpriv++;
+	if (blk_rq_should_init_elevator(bio)) {
+		priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+		if (priv)
+			rl->elvpriv++;
+	}
 
 	if (blk_queue_io_stat(q))
 		rw_flags |= REQ_IO_STAT;
@@ -1220,7 +1252,7 @@
 	spin_lock_irq(q->queue_lock);
 
 	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
-		where = ELEVATOR_INSERT_FRONT;
+		where = ELEVATOR_INSERT_FLUSH;
 		goto get_rq;
 	}
 
@@ -1805,7 +1837,7 @@
 	 * normal IO on queueing nor completion.  Accounting the
 	 * containing request is enough.
 	 */
-	if (blk_do_io_stat(req) && req != &req->q->flush_rq) {
+	if (blk_do_io_stat(req) && !(req->cmd_flags & REQ_FLUSH_SEQ)) {
 		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 b27d020..0bd8c9c 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -1,6 +1,69 @@
 /*
  * Functions to sequence FLUSH and FUA writes.
+ *
+ * Copyright (C) 2011		Max Planck Institute for Gravitational Physics
+ * Copyright (C) 2011		Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ *
+ * REQ_{FLUSH|FUA} requests are decomposed to sequences consisted of three
+ * optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request
+ * properties and hardware capability.
+ *
+ * If a request doesn't have data, only REQ_FLUSH makes sense, which
+ * indicates a simple flush request.  If there is data, REQ_FLUSH indicates
+ * that the device cache should be flushed before the data is executed, and
+ * REQ_FUA means that the data must be on non-volatile media on request
+ * completion.
+ *
+ * If the device doesn't have writeback cache, FLUSH and FUA don't make any
+ * difference.  The requests are either completed immediately if there's no
+ * data or executed as normal requests otherwise.
+ *
+ * If the device has writeback cache and supports FUA, REQ_FLUSH is
+ * translated to PREFLUSH but REQ_FUA is passed down directly with DATA.
+ *
+ * If the device has writeback cache and doesn't support FUA, REQ_FLUSH is
+ * translated to PREFLUSH and REQ_FUA to POSTFLUSH.
+ *
+ * The actual execution of flush is double buffered.  Whenever a request
+ * needs to execute PRE or POSTFLUSH, it queues at
+ * q->flush_queue[q->flush_pending_idx].  Once certain criteria are met, a
+ * flush is issued and the pending_idx is toggled.  When the flush
+ * completes, all the requests which were pending are proceeded to the next
+ * step.  This allows arbitrary merging of different types of FLUSH/FUA
+ * requests.
+ *
+ * Currently, the following conditions are used to determine when to issue
+ * flush.
+ *
+ * C1. At any given time, only one flush shall be in progress.  This makes
+ *     double buffering sufficient.
+ *
+ * C2. Flush is deferred if any request is executing DATA of its sequence.
+ *     This avoids issuing separate POSTFLUSHes for requests which shared
+ *     PREFLUSH.
+ *
+ * C3. The second condition is ignored if there is a request which has
+ *     waited longer than FLUSH_PENDING_TIMEOUT.  This is to avoid
+ *     starvation in the unlikely case where there are continuous stream of
+ *     FUA (without FLUSH) requests.
+ *
+ * For devices which support FUA, it isn't clear whether C2 (and thus C3)
+ * is beneficial.
+ *
+ * Note that a sequenced FLUSH/FUA request with DATA is completed twice.
+ * Once while executing DATA and again after the whole sequence is
+ * complete.  The first completion updates the contained bio but doesn't
+ * finish it so that the bio submitter is notified only after the whole
+ * sequence is complete.  This is implemented by testing REQ_FLUSH_SEQ in
+ * req_bio_endio().
+ *
+ * The above peculiarity requires that each FLUSH/FUA request has only one
+ * bio attached to it, which is guaranteed as they aren't allowed to be
+ * merged in the usual way.
  */
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/bio.h>
@@ -11,58 +74,143 @@
 
 /* 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),
+	REQ_FSEQ_PREFLUSH	= (1 << 0), /* pre-flushing in progress */
+	REQ_FSEQ_DATA		= (1 << 1), /* data write in progress */
+	REQ_FSEQ_POSTFLUSH	= (1 << 2), /* post-flushing in progress */
+	REQ_FSEQ_DONE		= (1 << 3),
+
+	REQ_FSEQ_ACTIONS	= REQ_FSEQ_PREFLUSH | REQ_FSEQ_DATA |
+				  REQ_FSEQ_POSTFLUSH,
+
+	/*
+	 * If flush has been pending longer than the following timeout,
+	 * it's issued even if flush_data requests are still in flight.
+	 */
+	FLUSH_PENDING_TIMEOUT	= 5 * HZ,
 };
 
-static struct request *queue_next_fseq(struct request_queue *q);
+static bool blk_kick_flush(struct request_queue *q);
 
-unsigned blk_flush_cur_seq(struct request_queue *q)
+static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq)
 {
-	if (!q->flush_seq)
-		return 0;
-	return 1 << ffz(q->flush_seq);
-}
+	unsigned int policy = 0;
 
-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);
-		}
+	if (fflags & REQ_FLUSH) {
+		if (rq->cmd_flags & REQ_FLUSH)
+			policy |= REQ_FSEQ_PREFLUSH;
+		if (blk_rq_sectors(rq))
+			policy |= REQ_FSEQ_DATA;
+		if (!(fflags & REQ_FUA) && (rq->cmd_flags & REQ_FUA))
+			policy |= REQ_FSEQ_POSTFLUSH;
 	}
-	return next_rq;
+	return policy;
 }
 
-static void blk_flush_complete_seq_end_io(struct request_queue *q,
-					  unsigned seq, int error)
+static unsigned int blk_flush_cur_seq(struct request *rq)
 {
-	bool was_empty = elv_queue_empty(q);
-	struct request *next_rq;
+	return 1 << ffz(rq->flush.seq);
+}
 
-	next_rq = blk_flush_complete_seq(q, seq, error);
+static void blk_flush_restore_request(struct request *rq)
+{
+	/*
+	 * After flush data completion, @rq->bio is %NULL but we need to
+	 * complete the bio again.  @rq->biotail is guaranteed to equal the
+	 * original @rq->bio.  Restore it.
+	 */
+	rq->bio = rq->biotail;
+
+	/* make @rq a normal request */
+	rq->cmd_flags &= ~REQ_FLUSH_SEQ;
+	rq->end_io = NULL;
+}
+
+/**
+ * blk_flush_complete_seq - complete flush sequence
+ * @rq: FLUSH/FUA request being sequenced
+ * @seq: sequences to complete (mask of %REQ_FSEQ_*, can be zero)
+ * @error: whether an error occurred
+ *
+ * @rq just completed @seq part of its flush sequence, record the
+ * completion and trigger the next step.
+ *
+ * CONTEXT:
+ * spin_lock_irq(q->queue_lock)
+ *
+ * RETURNS:
+ * %true if requests were added to the dispatch queue, %false otherwise.
+ */
+static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
+				   int error)
+{
+	struct request_queue *q = rq->q;
+	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
+	bool queued = false;
+
+	BUG_ON(rq->flush.seq & seq);
+	rq->flush.seq |= seq;
+
+	if (likely(!error))
+		seq = blk_flush_cur_seq(rq);
+	else
+		seq = REQ_FSEQ_DONE;
+
+	switch (seq) {
+	case REQ_FSEQ_PREFLUSH:
+	case REQ_FSEQ_POSTFLUSH:
+		/* queue for flush */
+		if (list_empty(pending))
+			q->flush_pending_since = jiffies;
+		list_move_tail(&rq->flush.list, pending);
+		break;
+
+	case REQ_FSEQ_DATA:
+		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
+		list_add(&rq->queuelist, &q->queue_head);
+		queued = true;
+		break;
+
+	case REQ_FSEQ_DONE:
+		/*
+		 * @rq was previously adjusted by blk_flush_issue() for
+		 * flush sequencing and may already have gone through the
+		 * flush data request completion path.  Restore @rq for
+		 * normal completion and end it.
+		 */
+		BUG_ON(!list_empty(&rq->queuelist));
+		list_del_init(&rq->flush.list);
+		blk_flush_restore_request(rq);
+		__blk_end_request_all(rq, error);
+		break;
+
+	default:
+		BUG();
+	}
+
+	return blk_kick_flush(q) | queued;
+}
+
+static void flush_end_io(struct request *flush_rq, int error)
+{
+	struct request_queue *q = flush_rq->q;
+	struct list_head *running = &q->flush_queue[q->flush_running_idx];
+	bool was_empty = elv_queue_empty(q);
+	bool queued = false;
+	struct request *rq, *n;
+
+	BUG_ON(q->flush_pending_idx == q->flush_running_idx);
+
+	/* account completion of the flush request */
+	q->flush_running_idx ^= 1;
+	elv_completed_request(q, flush_rq);
+
+	/* and push the waiting requests to the next stage */
+	list_for_each_entry_safe(rq, n, running, flush.list) {
+		unsigned int seq = blk_flush_cur_seq(rq);
+
+		BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH);
+		queued |= blk_flush_complete_seq(rq, seq, error);
+	}
 
 	/*
 	 * Moving a request silently to empty queue_head may stall the
@@ -70,127 +218,154 @@
 	 * from request completion path and calling directly into
 	 * request_fn may confuse the driver.  Always use kblockd.
 	 */
-	if (was_empty && next_rq)
+	if (queued && was_empty)
 		__blk_run_queue(q, true);
 }
 
-static void pre_flush_end_io(struct request *rq, int error)
+/**
+ * blk_kick_flush - consider issuing flush request
+ * @q: request_queue being kicked
+ *
+ * Flush related states of @q have changed, consider issuing flush request.
+ * Please read the comment at the top of this file for more info.
+ *
+ * CONTEXT:
+ * spin_lock_irq(q->queue_lock)
+ *
+ * RETURNS:
+ * %true if flush was issued, %false otherwise.
+ */
+static bool blk_kick_flush(struct request_queue *q)
 {
-	elv_completed_request(rq->q, rq);
-	blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_PREFLUSH, error);
+	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
+	struct request *first_rq =
+		list_first_entry(pending, struct request, flush.list);
+
+	/* C1 described at the top of this file */
+	if (q->flush_pending_idx != q->flush_running_idx || list_empty(pending))
+		return false;
+
+	/* C2 and C3 */
+	if (!list_empty(&q->flush_data_in_flight) &&
+	    time_before(jiffies,
+			q->flush_pending_since + FLUSH_PENDING_TIMEOUT))
+		return false;
+
+	/*
+	 * Issue flush and toggle pending_idx.  This makes pending_idx
+	 * different from running_idx, which means flush is in flight.
+	 */
+	blk_rq_init(q, &q->flush_rq);
+	q->flush_rq.cmd_type = REQ_TYPE_FS;
+	q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+	q->flush_rq.rq_disk = first_rq->rq_disk;
+	q->flush_rq.end_io = flush_end_io;
+
+	q->flush_pending_idx ^= 1;
+	elv_insert(q, &q->flush_rq, ELEVATOR_INSERT_REQUEUE);
+	return true;
 }
 
 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_REQUEUE);
-	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;
+	struct request_queue *q = rq->q;
+	bool was_empty = elv_queue_empty(q);
 
 	/*
-	 * 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.
+	 * After populating an empty queue, kick it to avoid stall.  Read
+	 * the comment in flush_end_io().
 	 */
-	if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) {
-		rq->cmd_flags &= ~REQ_FLUSH;
-		if (!has_fua)
-			rq->cmd_flags &= ~REQ_FUA;
-		return rq;
-	}
+	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error) && was_empty)
+		__blk_run_queue(q, true);
+}
+
+/**
+ * blk_insert_flush - insert a new FLUSH/FUA request
+ * @rq: request to insert
+ *
+ * To be called from elv_insert() for %ELEVATOR_INSERT_FLUSH insertions.
+ * @rq is being submitted.  Analyze what needs to be done and put it on the
+ * right queue.
+ *
+ * CONTEXT:
+ * spin_lock_irq(q->queue_lock)
+ */
+void blk_insert_flush(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	unsigned int fflags = q->flush_flags;	/* may change, cache */
+	unsigned int policy = blk_flush_policy(fflags, rq);
+
+	BUG_ON(rq->end_io);
+	BUG_ON(!rq->bio || rq->bio != rq->biotail);
 
 	/*
-	 * Sequenced flushes can't be processed in parallel.  If
-	 * another one is already in progress, queue for later
-	 * processing.
+	 * @policy now records what operations need to be done.  Adjust
+	 * REQ_FLUSH and FUA for the driver.
 	 */
-	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)
+	if (!(fflags & REQ_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);
+	/*
+	 * If there's data but flush is not necessary, the request can be
+	 * processed directly without going through flush machinery.  Queue
+	 * for normal execution.
+	 */
+	if ((policy & REQ_FSEQ_DATA) &&
+	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
+		list_add(&rq->queuelist, &q->queue_head);
+		return;
+	}
+
+	/*
+	 * @rq should go through flush machinery.  Mark it part of flush
+	 * sequence and submit for further processing.
+	 */
+	memset(&rq->flush, 0, sizeof(rq->flush));
+	INIT_LIST_HEAD(&rq->flush.list);
+	rq->cmd_flags |= REQ_FLUSH_SEQ;
+	rq->end_io = flush_data_end_io;
+
+	blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0);
+}
+
+/**
+ * blk_abort_flushes - @q is being aborted, abort flush requests
+ * @q: request_queue being aborted
+ *
+ * To be called from elv_abort_queue().  @q is being aborted.  Prepare all
+ * FLUSH/FUA requests for abortion.
+ *
+ * CONTEXT:
+ * spin_lock_irq(q->queue_lock)
+ */
+void blk_abort_flushes(struct request_queue *q)
+{
+	struct request *rq, *n;
+	int i;
+
+	/*
+	 * Requests in flight for data are already owned by the dispatch
+	 * queue or the device driver.  Just restore for normal completion.
+	 */
+	list_for_each_entry_safe(rq, n, &q->flush_data_in_flight, flush.list) {
+		list_del_init(&rq->flush.list);
+		blk_flush_restore_request(rq);
+	}
+
+	/*
+	 * We need to give away requests on flush queues.  Restore for
+	 * normal completion and put them on the dispatch queue.
+	 */
+	for (i = 0; i < ARRAY_SIZE(q->flush_queue); i++) {
+		list_for_each_entry_safe(rq, n, &q->flush_queue[i],
+					 flush.list) {
+			list_del_init(&rq->flush.list);
+			blk_flush_restore_request(rq);
+			list_add_tail(&rq->queuelist, &q->queue_head);
+		}
+	}
 }
 
 static void bio_end_flush(struct bio *bio, int err)
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 36c8c1f..df649fa 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -176,13 +176,6 @@
 	blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS);
 
 	/*
-	 * If the caller didn't supply a lock, fall back to our embedded
-	 * per-queue locks
-	 */
-	if (!q->queue_lock)
-		q->queue_lock = &q->__queue_lock;
-
-	/*
 	 * by default assume old behaviour and bounce for any highmem page
 	 */
 	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 41fb691..261c75c 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -471,8 +471,6 @@
 
 	blk_sync_queue(q);
 
-	blk_throtl_exit(q);
-
 	if (rl->rq_pool)
 		mempool_destroy(rl->rq_pool);
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index e36cc10..061dee6 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -968,7 +968,7 @@
 	throtl_schedule_delayed_work(td, 0);
 }
 
-void throtl_shutdown_timer_wq(struct request_queue *q)
+static void throtl_shutdown_wq(struct request_queue *q)
 {
 	struct throtl_data *td = q->td;
 
@@ -1102,7 +1102,7 @@
 
 	BUG_ON(!td);
 
-	throtl_shutdown_timer_wq(q);
+	throtl_shutdown_wq(q);
 
 	spin_lock_irq(q->queue_lock);
 	throtl_release_tgs(td);
@@ -1132,7 +1132,7 @@
 	 * update limits through cgroup and another work got queued, cancel
 	 * it.
 	 */
-	throtl_shutdown_timer_wq(q);
+	throtl_shutdown_wq(q);
 	throtl_td_free(td);
 }
 
diff --git a/block/blk.h b/block/blk.h
index 2db8f32..284b500 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -51,21 +51,17 @@
  */
 #define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
 
-struct request *blk_do_flush(struct request_queue *q, struct request *rq);
+void blk_insert_flush(struct request *rq);
+void blk_abort_flushes(struct request_queue *q);
 
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
 	struct request *rq;
 
 	while (1) {
-		while (!list_empty(&q->queue_head)) {
+		if (!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;
+			return rq;
 		}
 
 		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index ea83a4f..89dc745 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -54,9 +54,9 @@
 #define CFQQ_SEEKY(cfqq)	(hweight32(cfqq->seek_history) > 32/8)
 
 #define RQ_CIC(rq)		\
-	((struct cfq_io_context *) (rq)->elevator_private)
-#define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private2)
-#define RQ_CFQG(rq)		(struct cfq_group *) ((rq)->elevator_private3)
+	((struct cfq_io_context *) (rq)->elevator_private[0])
+#define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private[1])
+#define RQ_CFQG(rq)		(struct cfq_group *) ((rq)->elevator_private[2])
 
 static struct kmem_cache *cfq_pool;
 static struct kmem_cache *cfq_ioc_pool;
@@ -146,7 +146,6 @@
 	struct cfq_rb_root *service_tree;
 	struct cfq_queue *new_cfqq;
 	struct cfq_group *cfqg;
-	struct cfq_group *orig_cfqg;
 	/* Number of sectors dispatched from queue in single dispatch round */
 	unsigned long nr_sectors;
 };
@@ -285,7 +284,6 @@
 	unsigned int cfq_slice_idle;
 	unsigned int cfq_group_idle;
 	unsigned int cfq_latency;
-	unsigned int cfq_group_isolation;
 
 	unsigned int cic_index;
 	struct list_head cic_list;
@@ -1187,32 +1185,6 @@
 	int new_cfqq = 1;
 	int group_changed = 0;
 
-#ifdef CONFIG_CFQ_GROUP_IOSCHED
-	if (!cfqd->cfq_group_isolation
-	    && cfqq_type(cfqq) == SYNC_NOIDLE_WORKLOAD
-	    && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) {
-		/* Move this cfq to root group */
-		cfq_log_cfqq(cfqd, cfqq, "moving to root group");
-		if (!RB_EMPTY_NODE(&cfqq->rb_node))
-			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
-		cfqq->orig_cfqg = cfqq->cfqg;
-		cfqq->cfqg = &cfqd->root_group;
-		cfqd->root_group.ref++;
-		group_changed = 1;
-	} else if (!cfqd->cfq_group_isolation
-		   && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
-		/* cfqq is sequential now needs to go to its original group */
-		BUG_ON(cfqq->cfqg != &cfqd->root_group);
-		if (!RB_EMPTY_NODE(&cfqq->rb_node))
-			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
-		cfq_put_cfqg(cfqq->cfqg);
-		cfqq->cfqg = cfqq->orig_cfqg;
-		cfqq->orig_cfqg = NULL;
-		group_changed = 1;
-		cfq_log_cfqq(cfqd, cfqq, "moved to origin group");
-	}
-#endif
-
 	service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
 						cfqq_type(cfqq));
 	if (cfq_class_idle(cfqq)) {
@@ -2542,7 +2514,7 @@
 static void cfq_put_queue(struct cfq_queue *cfqq)
 {
 	struct cfq_data *cfqd = cfqq->cfqd;
-	struct cfq_group *cfqg, *orig_cfqg;
+	struct cfq_group *cfqg;
 
 	BUG_ON(cfqq->ref <= 0);
 
@@ -2554,7 +2526,6 @@
 	BUG_ON(rb_first(&cfqq->sort_list));
 	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
 	cfqg = cfqq->cfqg;
-	orig_cfqg = cfqq->orig_cfqg;
 
 	if (unlikely(cfqd->active_queue == cfqq)) {
 		__cfq_slice_expired(cfqd, cfqq, 0);
@@ -2564,8 +2535,6 @@
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	kmem_cache_free(cfq_pool, cfqq);
 	cfq_put_cfqg(cfqg);
-	if (orig_cfqg)
-		cfq_put_cfqg(orig_cfqg);
 }
 
 /*
@@ -3613,12 +3582,12 @@
 
 		put_io_context(RQ_CIC(rq)->ioc);
 
-		rq->elevator_private = NULL;
-		rq->elevator_private2 = NULL;
+		rq->elevator_private[0] = NULL;
+		rq->elevator_private[1] = NULL;
 
 		/* Put down rq reference on cfqg */
 		cfq_put_cfqg(RQ_CFQG(rq));
-		rq->elevator_private3 = NULL;
+		rq->elevator_private[2] = NULL;
 
 		cfq_put_queue(cfqq);
 	}
@@ -3705,13 +3674,13 @@
 	}
 
 	cfqq->allocated[rw]++;
-	cfqq->ref++;
-	rq->elevator_private = cic;
-	rq->elevator_private2 = cfqq;
-	rq->elevator_private3 = cfq_ref_get_cfqg(cfqq->cfqg);
 
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
+	cfqq->ref++;
+	rq->elevator_private[0] = cic;
+	rq->elevator_private[1] = cfqq;
+	rq->elevator_private[2] = cfq_ref_get_cfqg(cfqq->cfqg);
 	return 0;
 
 queue_fail:
@@ -3953,7 +3922,6 @@
 	cfqd->cfq_slice_idle = cfq_slice_idle;
 	cfqd->cfq_group_idle = cfq_group_idle;
 	cfqd->cfq_latency = 1;
-	cfqd->cfq_group_isolation = 0;
 	cfqd->hw_tag = -1;
 	/*
 	 * we optimistically start assuming sync ops weren't delayed in last
@@ -4029,7 +3997,6 @@
 SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
 SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
 SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0);
-SHOW_FUNCTION(cfq_group_isolation_show, cfqd->cfq_group_isolation, 0);
 #undef SHOW_FUNCTION
 
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
@@ -4063,7 +4030,6 @@
 STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1,
 		UINT_MAX, 0);
 STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
-STORE_FUNCTION(cfq_group_isolation_store, &cfqd->cfq_group_isolation, 0, 1, 0);
 #undef STORE_FUNCTION
 
 #define CFQ_ATTR(name) \
@@ -4081,7 +4047,6 @@
 	CFQ_ATTR(slice_idle),
 	CFQ_ATTR(group_idle),
 	CFQ_ATTR(low_latency),
-	CFQ_ATTR(group_isolation),
 	__ATTR_NULL
 };
 
diff --git a/block/elevator.c b/block/elevator.c
index 236e93c..fabf367 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -673,6 +673,11 @@
 		q->elevator->ops->elevator_add_req_fn(q, rq);
 		break;
 
+	case ELEVATOR_INSERT_FLUSH:
+		rq->cmd_flags |= REQ_SOFTBARRIER;
+		blk_insert_flush(rq);
+		break;
+
 	default:
 		printk(KERN_ERR "%s: bad insertion point %d\n",
 		       __func__, where);
@@ -759,7 +764,7 @@
 	if (e->ops->elevator_set_req_fn)
 		return e->ops->elevator_set_req_fn(q, rq, gfp_mask);
 
-	rq->elevator_private = NULL;
+	rq->elevator_private[0] = NULL;
 	return 0;
 }
 
@@ -785,6 +790,8 @@
 {
 	struct request *rq;
 
+	blk_abort_flushes(q);
+
 	while (!list_empty(&q->queue_head)) {
 		rq = list_entry_rq(q->queue_head.next);
 		rq->cmd_flags |= REQ_QUIET;
diff --git a/block/genhd.c b/block/genhd.c
index cbf1112..3e2b57b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1158,14 +1158,14 @@
 			   "%u %lu %lu %llu %u %u %u %u\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
-			   part_stat_read(hd, ios[0]),
-			   part_stat_read(hd, merges[0]),
-			   (unsigned long long)part_stat_read(hd, sectors[0]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[0])),
-			   part_stat_read(hd, ios[1]),
-			   part_stat_read(hd, merges[1]),
-			   (unsigned long long)part_stat_read(hd, sectors[1]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[1])),
+			   part_stat_read(hd, ios[READ]),
+			   part_stat_read(hd, merges[READ]),
+			   (unsigned long long)part_stat_read(hd, sectors[READ]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[READ])),
+			   part_stat_read(hd, ios[WRITE]),
+			   part_stat_read(hd, merges[WRITE]),
+			   (unsigned long long)part_stat_read(hd, sectors[WRITE]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])),
 			   part_in_flight(hd),
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
 			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index dbf31ec..79c3079 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1636,9 +1636,6 @@
 
 static void loop_free(struct loop_device *lo)
 {
-	if (!lo->lo_queue->queue_lock)
-		lo->lo_queue->queue_lock = &lo->lo_queue->__queue_lock;
-
 	blk_cleanup_queue(lo->lo_queue);
 	put_disk(lo->lo_disk);
 	list_del(&lo->lo_list);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 46ad519..dddedfc 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -148,6 +148,7 @@
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_COPY_USER,	/* contains copies of user pages */
 	__REQ_FLUSH,		/* request for cache flush */
+	__REQ_FLUSH_SEQ,	/* request for flush sequence */
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_SECURE,		/* secure discard (used with __REQ_DISCARD) */
@@ -188,6 +189,7 @@
 #define REQ_ALLOCED		(1 << __REQ_ALLOCED)
 #define REQ_COPY_USER		(1 << __REQ_COPY_USER)
 #define REQ_FLUSH		(1 << __REQ_FLUSH)
+#define REQ_FLUSH_SEQ		(1 << __REQ_FLUSH_SEQ)
 #define REQ_IO_STAT		(1 << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
 #define REQ_SECURE		(1 << __REQ_SECURE)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d5063e1..13b75ca 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -108,11 +108,17 @@
 
 	/*
 	 * Three pointers are available for the IO schedulers, if they need
-	 * more they have to dynamically allocate it.
+	 * more they have to dynamically allocate it.  Flush requests are
+	 * never put on the IO scheduler. So let the flush fields share
+	 * space with the three elevator_private pointers.
 	 */
-	void *elevator_private;
-	void *elevator_private2;
-	void *elevator_private3;
+	union {
+		void *elevator_private[3];
+		struct {
+			unsigned int		seq;
+			struct list_head	list;
+		} flush;
+	};
 
 	struct gendisk *rq_disk;
 	struct hd_struct *part;
@@ -363,11 +369,12 @@
 	 * for flush operations
 	 */
 	unsigned int		flush_flags;
-	unsigned int		flush_seq;
-	int			flush_err;
+	unsigned int		flush_pending_idx:1;
+	unsigned int		flush_running_idx:1;
+	unsigned long		flush_pending_since;
+	struct list_head	flush_queue[2];
+	struct list_head	flush_data_in_flight;
 	struct request		flush_rq;
-	struct request		*orig_flush_rq;
-	struct list_head	pending_flushes;
 
 	struct mutex		sysfs_lock;
 
@@ -1135,7 +1142,6 @@
 extern int blk_throtl_init(struct request_queue *q);
 extern void blk_throtl_exit(struct request_queue *q);
 extern int blk_throtl_bio(struct request_queue *q, struct bio **bio);
-extern void throtl_shutdown_timer_wq(struct request_queue *q);
 #else /* CONFIG_BLK_DEV_THROTTLING */
 static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio)
 {
@@ -1144,7 +1150,6 @@
 
 static inline int blk_throtl_init(struct request_queue *q) { return 0; }
 static inline int blk_throtl_exit(struct request_queue *q) { return 0; }
-static inline void throtl_shutdown_timer_wq(struct request_queue *q) {}
 #endif /* CONFIG_BLK_DEV_THROTTLING */
 
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 4d85797..39b68ed 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -167,6 +167,7 @@
 #define ELEVATOR_INSERT_BACK	2
 #define ELEVATOR_INSERT_SORT	3
 #define ELEVATOR_INSERT_REQUEUE	4
+#define ELEVATOR_INSERT_FLUSH	5
 
 /*
  * return values from elevator_may_queue_fn