Merge branch 'generic-dispatch' of git://brick.kernel.dk/data/git/linux-2.6-block

9 files changed, 459 insertions, 847 deletions

diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 6dd274d7e1c..2d65c218216 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -906,9 +906,20 @@ Aside:
 
 
 4. The I/O scheduler
-I/O schedulers are now per queue. They should be runtime switchable and modular
-but aren't yet. Jens has most bits to do this, but the sysfs implementation is
-missing.
+I/O scheduler, a.k.a. elevator, is implemented in two layers.  Generic dispatch
+queue and specific I/O schedulers.  Unless stated otherwise, elevator is used
+to refer to both parts and I/O scheduler to specific I/O schedulers.
+
+Block layer implements generic dispatch queue in ll_rw_blk.c and elevator.c.
+The generic dispatch queue is responsible for properly ordering barrier
+requests, requeueing, handling non-fs requests and all other subtleties.
+
+Specific I/O schedulers are responsible for ordering normal filesystem
+requests.  They can also choose to delay certain requests to improve
+throughput or whatever purpose.  As the plural form indicates, there are
+multiple I/O schedulers.  They can be built as modules but at least one should
+be built inside the kernel.  Each queue can choose different one and can also
+change to another one dynamically.
 
 A block layer call to the i/o scheduler follows the convention elv_xxx(). This
 calls elevator_xxx_fn in the elevator switch (drivers/block/elevator.c). Oh,
@@ -921,44 +932,36 @@ keeping work.
 The functions an elevator may implement are: (* are mandatory)
 elevator_merge_fn		called to query requests for merge with a bio
 
-elevator_merge_req_fn		" " "  with another request
+elevator_merge_req_fn		called when two requests get merged. the one
+				which gets merged into the other one will be
+				never seen by I/O scheduler again. IOW, after
+				being merged, the request is gone.
 
 elevator_merged_fn		called when a request in the scheduler has been
 				involved in a merge. It is used in the deadline
 				scheduler for example, to reposition the request
 				if its sorting order has changed.
 
-*elevator_next_req_fn		returns the next scheduled request, or NULL
-				if there are none (or none are ready).
+elevator_dispatch_fn		fills the dispatch queue with ready requests.
+				I/O schedulers are free to postpone requests by
+				not filling the dispatch queue unless @force
+				is non-zero.  Once dispatched, I/O schedulers
+				are not allowed to manipulate the requests -
+				they belong to generic dispatch queue.
 
-*elevator_add_req_fn		called to add a new request into the scheduler
+elevator_add_req_fn		called to add a new request into the scheduler
 
 elevator_queue_empty_fn		returns true if the merge queue is empty.
 				Drivers shouldn't use this, but rather check
 				if elv_next_request is NULL (without losing the
 				request if one exists!)
 
-elevator_remove_req_fn		This is called when a driver claims ownership of
-				the target request - it now belongs to the
-				driver. It must not be modified or merged.
-				Drivers must not lose the request! A subsequent
-				call of elevator_next_req_fn must  return the
-				_next_ request.
-
-elevator_requeue_req_fn		called to add a request to the scheduler. This
-				is used when the request has alrnadebeen
-				returned by elv_next_request, but hasn't
-				completed. If this is not implemented then
-				elevator_add_req_fn is called instead.
-
 elevator_former_req_fn
 elevator_latter_req_fn		These return the request before or after the
 				one specified in disk sort order. Used by the
 				block layer to find merge possibilities.
 
-elevator_completed_req_fn	called when a request is completed. This might
-				come about due to being merged with another or
-				when the device completes the request.
+elevator_completed_req_fn	called when a request is completed.
 
 elevator_may_queue_fn		returns true if the scheduler wants to allow the
 				current context to queue a new request even if
@@ -967,13 +970,33 @@ elevator_may_queue_fn		returns true if the scheduler wants to allow the
 
 elevator_set_req_fn
 elevator_put_req_fn		Must be used to allocate and free any elevator
-				specific storate for a request.
+				specific storage for a request.
+
+elevator_activate_req_fn	Called when device driver first sees a request.
+				I/O schedulers can use this callback to
+				determine when actual execution of a request
+				starts.
+elevator_deactivate_req_fn	Called when device driver decides to delay
+				a request by requeueing it.
 
 elevator_init_fn
 elevator_exit_fn		Allocate and free any elevator specific storage
 				for a queue.
 
-4.2 I/O scheduler implementation
+4.2 Request flows seen by I/O schedulers
+All requests seens by I/O schedulers strictly follow one of the following three
+flows.
+
+ set_req_fn ->
+
+ i.   add_req_fn -> (merged_fn ->)* -> dispatch_fn -> activate_req_fn ->
+      (deactivate_req_fn -> activate_req_fn ->)* -> completed_req_fn
+ ii.  add_req_fn -> (merged_fn ->)* -> merge_req_fn
+ iii. [none]
+
+ -> put_req_fn
+
+4.3 I/O scheduler implementation
 The generic i/o scheduler algorithm attempts to sort/merge/batch requests for
 optimal disk scan and request servicing performance (based on generic
 principles and device capabilities), optimized for:
@@ -993,18 +1016,7 @@ request in sort order to prevent binary tree lookups.
 This arrangement is not a generic block layer characteristic however, so
 elevators may implement queues as they please.
 
-ii. Last merge hint
-The last merge hint is part of the generic queue layer. I/O schedulers must do
-some management on it. For the most part, the most important thing is to make
-sure q->last_merge is cleared (set to NULL) when the request on it is no longer
-a candidate for merging (for example if it has been sent to the driver).
-
-The last merge performed is cached as a hint for the subsequent request. If
-sequential data is being submitted, the hint is used to perform merges without
-any scanning. This is not sufficient when there are multiple processes doing
-I/O though, so a "merge hash" is used by some schedulers.
-
-iii. Merge hash
+ii. Merge hash
 AS and deadline use a hash table indexed by the last sector of a request. This
 enables merging code to quickly look up "back merge" candidates, even when
 multiple I/O streams are being performed at once on one disk.
@@ -1013,29 +1025,8 @@ multiple I/O streams are being performed at once on one disk.
 are far less common than "back merges" due to the nature of most I/O patterns.
 Front merges are handled by the binary trees in AS and deadline schedulers.
 
-iv. Handling barrier cases
-A request with flags REQ_HARDBARRIER or REQ_SOFTBARRIER must not be ordered
-around. That is, they must be processed after all older requests, and before
-any newer ones. This includes merges!
-
-In AS and deadline schedulers, barriers have the effect of flushing the reorder
-queue. The performance cost of this will vary from nothing to a lot depending
-on i/o patterns and device characteristics. Obviously they won't improve
-performance, so their use should be kept to a minimum.
-
-v. Handling insertion position directives
-A request may be inserted with a position directive. The directives are one of
-ELEVATOR_INSERT_BACK, ELEVATOR_INSERT_FRONT, ELEVATOR_INSERT_SORT.
-
-ELEVATOR_INSERT_SORT is a general directive for non-barrier requests.
-ELEVATOR_INSERT_BACK is used to insert a barrier to the back of the queue.
-ELEVATOR_INSERT_FRONT is used to insert a barrier to the front of the queue, and
-overrides the ordering requested by any previous barriers. In practice this is
-harmless and required, because it is used for SCSI requeueing. This does not
-require flushing the reorder queue, so does not impose a performance penalty.
-
-vi. Plugging the queue to batch requests in anticipation of opportunities for
-  merge/sort optimizations
+iii. Plugging the queue to batch requests in anticipation of opportunities for
+     merge/sort optimizations
 
 This is just the same as in 2.4 so far, though per-device unplugging
 support is anticipated for 2.5. Also with a priority-based i/o scheduler,
@@ -1069,7 +1060,7 @@ Aside:
   blk_kick_queue() to unplug a specific queue (right away ?)
   or optionally, all queues, is in the plan.
 
-4.3 I/O contexts
+4.4 I/O contexts
 I/O contexts provide a dynamically allocated per process data area. They may
 be used in I/O schedulers, and in the block layer (could be used for IO statis,
 priorities for example). See *io_context in drivers/block/ll_rw_blk.c, and
diff --git a/drivers/block/as-iosched.c b/drivers/block/as-iosched.c
index 1f08e14697e..4081c36c8c1 100644
--- a/drivers/block/as-iosched.c
+++ b/drivers/block/as-iosched.c
@@ -98,7 +98,6 @@ struct as_data {
 
 	struct as_rq *next_arq[2];	/* next in sort order */
 	sector_t last_sector[2];	/* last REQ_SYNC & REQ_ASYNC sectors */
-	struct list_head *dispatch;	/* driver dispatch queue */
 	struct list_head *hash;		/* request hash */
 
 	unsigned long exit_prob;	/* probability a task will exit while
@@ -239,6 +238,25 @@ static struct io_context *as_get_io_context(void)
 	return ioc;
 }
 
+static void as_put_io_context(struct as_rq *arq)
+{
+	struct as_io_context *aic;
+
+	if (unlikely(!arq->io_context))
+		return;
+
+	aic = arq->io_context->aic;
+
+	if (arq->is_sync == REQ_SYNC && aic) {
+		spin_lock(&aic->lock);
+		set_bit(AS_TASK_IORUNNING, &aic->state);
+		aic->last_end_request = jiffies;
+		spin_unlock(&aic->lock);
+	}
+
+	put_io_context(arq->io_context);
+}
+
 /*
  * the back merge hash support functions
  */
@@ -261,14 +279,6 @@ static inline void as_del_arq_hash(struct as_rq *arq)
 		__as_del_arq_hash(arq);
 }
 
-static void as_remove_merge_hints(request_queue_t *q, struct as_rq *arq)
-{
-	as_del_arq_hash(arq);
-
-	if (q->last_merge == arq->request)
-		q->last_merge = NULL;
-}
-
 static void as_add_arq_hash(struct as_data *ad, struct as_rq *arq)
 {
 	struct request *rq = arq->request;
@@ -312,7 +322,7 @@ static struct request *as_find_arq_hash(struct as_data *ad, sector_t offset)
 		BUG_ON(!arq->on_hash);
 
 		if (!rq_mergeable(__rq)) {
-			as_remove_merge_hints(ad->q, arq);
+			as_del_arq_hash(arq);
 			continue;
 		}
 
@@ -950,23 +960,12 @@ static void as_completed_request(request_queue_t *q, struct request *rq)
 
 	WARN_ON(!list_empty(&rq->queuelist));
 
-	if (arq->state == AS_RQ_PRESCHED) {
-		WARN_ON(arq->io_context);
-		goto out;
-	}
-
-	if (arq->state == AS_RQ_MERGED)
-		goto out_ioc;
-
 	if (arq->state != AS_RQ_REMOVED) {
 		printk("arq->state %d\n", arq->state);
 		WARN_ON(1);
 		goto out;
 	}
 
-	if (!blk_fs_request(rq))
-		goto out;
-
 	if (ad->changed_batch && ad->nr_dispatched == 1) {
 		kblockd_schedule_work(&ad->antic_work);
 		ad->changed_batch = 0;
@@ -1001,21 +1000,7 @@ static void as_completed_request(request_queue_t *q, struct request *rq)
 		}
 	}
 
-out_ioc:
-	if (!arq->io_context)
-		goto out;
-
-	if (arq->is_sync == REQ_SYNC) {
-		struct as_io_context *aic = arq->io_context->aic;
-		if (aic) {
-			spin_lock(&aic->lock);
-			set_bit(AS_TASK_IORUNNING, &aic->state);
-			aic->last_end_request = jiffies;
-			spin_unlock(&aic->lock);
-		}
-	}
-
-	put_io_context(arq->io_context);
+	as_put_io_context(arq);
 out:
 	arq->state = AS_RQ_POSTSCHED;
 }
@@ -1047,73 +1032,11 @@ static void as_remove_queued_request(request_queue_t *q, struct request *rq)
 		ad->next_arq[data_dir] = as_find_next_arq(ad, arq);
 
 	list_del_init(&arq->fifo);
-	as_remove_merge_hints(q, arq);
+	as_del_arq_hash(arq);
 	as_del_arq_rb(ad, arq);
 }
 
 /*
- * as_remove_dispatched_request is called to remove a request which has gone
- * to the dispatch list.
- */
-static void as_remove_dispatched_request(request_queue_t *q, struct request *rq)
-{
-	struct as_rq *arq = RQ_DATA(rq);
-	struct as_io_context *aic;
-
-	if (!arq) {
-		WARN_ON(1);
-		return;
-	}
-
-	WARN_ON(arq->state != AS_RQ_DISPATCHED);
-	WARN_ON(ON_RB(&arq->rb_node));
-	if (arq->io_context && arq->io_context->aic) {
-		aic = arq->io_context->aic;
-		if (aic) {
-			WARN_ON(!atomic_read(&aic->nr_dispatched));
-			atomic_dec(&aic->nr_dispatched);
-		}
-	}
-}
-
-/*
- * as_remove_request is called when a driver has finished with a request.
- * This should be only called for dispatched requests, but for some reason
- * a POWER4 box running hwscan it does not.
- */
-static void as_remove_request(request_queue_t *q, struct request *rq)
-{
-	struct as_rq *arq = RQ_DATA(rq);
-
-	if (unlikely(arq->state == AS_RQ_NEW))
-		goto out;
-
-	if (ON_RB(&arq->rb_node)) {
-		if (arq->state != AS_RQ_QUEUED) {
-			printk("arq->state %d\n", arq->state);
-			WARN_ON(1);
-			goto out;
-		}
-		/*
-		 * We'll lose the aliased request(s) here. I don't think this
-		 * will ever happen, but if it does, hopefully someone will
-		 * report it.
-		 */
-		WARN_ON(!list_empty(&rq->queuelist));
-		as_remove_queued_request(q, rq);
-	} else {
-		if (arq->state != AS_RQ_DISPATCHED) {
-			printk("arq->state %d\n", arq->state);
-			WARN_ON(1);
-			goto out;
-		}
-		as_remove_dispatched_request(q, rq);
-	}
-out:
-	arq->state = AS_RQ_REMOVED;
-}
-
-/*
  * as_fifo_expired returns 0 if there are no expired reads on the fifo,
  * 1 otherwise.  It is ratelimited so that we only perform the check once per
  * `fifo_expire' interval.  Otherwise a large number of expired requests
@@ -1165,7 +1088,6 @@ static inline int as_batch_expired(struct as_data *ad)
 static void as_move_to_dispatch(struct as_data *ad, struct as_rq *arq)
 {
 	struct request *rq = arq->request;
-	struct list_head *insert;
 	const int data_dir = arq->is_sync;
 
 	BUG_ON(!ON_RB(&arq->rb_node));
@@ -1198,13 +1120,13 @@ static void as_move_to_dispatch(struct as_data *ad, struct as_rq *arq)
 	/*
 	 * take it off the sort and fifo list, add to dispatch queue
 	 */
-	insert = ad->dispatch->prev;
-
 	while (!list_empty(&rq->queuelist)) {
 		struct request *__rq = list_entry_rq(rq->queuelist.next);
 		struct as_rq *__arq = RQ_DATA(__rq);
 
-		list_move_tail(&__rq->queuelist, ad->dispatch);
+		list_del(&__rq->queuelist);
+
+		elv_dispatch_add_tail(ad->q, __rq);
 
 		if (__arq->io_context && __arq->io_context->aic)
 			atomic_inc(&__arq->io_context->aic->nr_dispatched);
@@ -1218,7 +1140,8 @@ static void as_move_to_dispatch(struct as_data *ad, struct as_rq *arq)
 	as_remove_queued_request(ad->q, rq);
 	WARN_ON(arq->state != AS_RQ_QUEUED);
 
-	list_add(&rq->queuelist, insert);
+	elv_dispatch_sort(ad->q, rq);
+
 	arq->state = AS_RQ_DISPATCHED;
 	if (arq->io_context && arq->io_context->aic)
 		atomic_inc(&arq->io_context->aic->nr_dispatched);
@@ -1230,12 +1153,42 @@ static void as_move_to_dispatch(struct as_data *ad, struct as_rq *arq)
  * read/write expire, batch expire, etc, and moves it to the dispatch
  * queue. Returns 1 if a request was found, 0 otherwise.
  */
-static int as_dispatch_request(struct as_data *ad)
+static int as_dispatch_request(request_queue_t *q, int force)
 {
+	struct as_data *ad = q->elevator->elevator_data;
 	struct as_rq *arq;
 	const int reads = !list_empty(&ad->fifo_list[REQ_SYNC]);
 	const int writes = !list_empty(&ad->fifo_list[REQ_ASYNC]);
 
+	if (unlikely(force)) {
+		/*
+		 * Forced dispatch, accounting is useless.  Reset
+		 * accounting states and dump fifo_lists.  Note that
+		 * batch_data_dir is reset to REQ_SYNC to avoid
+		 * screwing write batch accounting as write batch
+		 * accounting occurs on W->R transition.
+		 */
+		int dispatched = 0;
+
+		ad->batch_data_dir = REQ_SYNC;
+		ad->changed_batch = 0;
+		ad->new_batch = 0;
+
+		while (ad->next_arq[REQ_SYNC]) {
+			as_move_to_dispatch(ad, ad->next_arq[REQ_SYNC]);
+			dispatched++;
+		}
+		ad->last_check_fifo[REQ_SYNC] = jiffies;
+
+		while (ad->next_arq[REQ_ASYNC]) {
+			as_move_to_dispatch(ad, ad->next_arq[REQ_ASYNC]);
+			dispatched++;
+		}
+		ad->last_check_fifo[REQ_ASYNC] = jiffies;
+
+		return dispatched;
+	}
+
 	/* Signal that the write batch was uncontended, so we can't time it */
 	if (ad->batch_data_dir == REQ_ASYNC && !reads) {
 		if (ad->current_write_count == 0 || !writes)
@@ -1359,20 +1312,6 @@ fifo_expired:
 	return 1;
 }
 
-static struct request *as_next_request(request_queue_t *q)
-{
-	struct as_data *ad = q->elevator->elevator_data;
-	struct request *rq = NULL;
-
-	/*
-	 * if there are still requests on the dispatch queue, grab the first
-	 */
-	if (!list_empty(ad->dispatch) || as_dispatch_request(ad))
-		rq = list_entry_rq(ad->dispatch->next);
-
-	return rq;
-}
-
 /*
  * Add arq to a list behind alias
  */
@@ -1404,17 +1343,25 @@ as_add_aliased_request(struct as_data *ad, struct as_rq *arq, struct as_rq *alia
 	/*
 	 * Don't want to have to handle merges.
 	 */
-	as_remove_merge_hints(ad->q, arq);
+	as_del_arq_hash(arq);
 }
 
 /*
  * add arq to rbtree and fifo
  */
-static void as_add_request(struct as_data *ad, struct as_rq *arq)
+static void as_add_request(request_queue_t *q, struct request *rq)
 {
+	struct as_data *ad = q->elevator->elevator_data;
+	struct as_rq *arq = RQ_DATA(rq);
 	struct as_rq *alias;
 	int data_dir;
 
+	if (arq->state != AS_RQ_PRESCHED) {
+		printk("arq->state: %d\n", arq->state);
+		WARN_ON(1);
+	}
+	arq->state = AS_RQ_NEW;
+
 	if (rq_data_dir(arq->request) == READ
 			|| current->flags&PF_SYNCWRITE)
 		arq->is_sync = 1;
@@ -1437,12 +1384,8 @@ static void as_add_request(struct as_data *ad, struct as_rq *arq)
 		arq->expires = jiffies + ad->fifo_expire[data_dir];
 		list_add_tail(&arq->fifo, &ad->fifo_list[data_dir]);
 
-		if (rq_mergeable(arq->request)) {
+		if (rq_mergeable(arq->request))
 			as_add_arq_hash(ad, arq);
-
-			if (!ad->q->last_merge)
-				ad->q->last_merge = arq->request;
-		}
 		as_update_arq(ad, arq); /* keep state machine up to date */
 
 	} else {
@@ -1463,96 +1406,24 @@ static void as_add_request(struct as_data *ad, struct as_rq *arq)
 	arq->state = AS_RQ_QUEUED;
 }
 
-static void as_deactivate_request(request_queue_t *q, struct request *rq)
+static void as_activate_request(request_queue_t *q, struct request *rq)
 {
-	struct as_data *ad = q->elevator->elevator_data;
 	struct as_rq *arq = RQ_DATA(rq);
 
-	if (arq) {
-		if (arq->state == AS_RQ_REMOVED) {
-			arq->state = AS_RQ_DISPATCHED;
-			if (arq->io_context && arq->io_context->aic)
-				atomic_inc(&arq->io_context->aic->nr_dispatched);
-		}
-	} else
-		WARN_ON(blk_fs_request(rq)
-			&& (!(rq->flags & (REQ_HARDBARRIER|REQ_SOFTBARRIER))) );
-
-	/* Stop anticipating - let this request get through */
-	as_antic_stop(ad);
-}
-
-/*
- * requeue the request. The request has not been completed, nor is it a
- * new request, so don't touch accounting.
- */
-static void as_requeue_request(request_queue_t *q, struct request *rq)
-{
-	as_deactivate_request(q, rq);
-	list_add(&rq->queuelist, &q->queue_head);
-}
-
-/*
- * Account a request that is inserted directly onto the dispatch queue.
- * arq->io_context->aic->nr_dispatched should not need to be incremented
- * because only new requests should come through here: requeues go through
- * our explicit requeue handler.
- */
-static void as_account_queued_request(struct as_data *ad, struct request *rq)
-{
-	if (blk_fs_request(rq)) {
-		struct as_rq *arq = RQ_DATA(rq);
-		arq->state = AS_RQ_DISPATCHED;
-		ad->nr_dispatched++;
-	}
+	WARN_ON(arq->state != AS_RQ_DISPATCHED);
+	arq->state = AS_RQ_REMOVED;
+	if (arq->io_context && arq->io_context->aic)
+		atomic_dec(&arq->io_context->aic->nr_dispatched);
 }
 
-static void
-as_insert_request(request_queue_t *q, struct request *rq, int where)
+static void as_deactivate_request(request_queue_t *q, struct request *rq)
 {
-	struct as_data *ad = q->elevator->elevator_data;
 	struct as_rq *arq = RQ_DATA(rq);
 
-	if (arq) {
-		if (arq->state != AS_RQ_PRESCHED) {
-			printk("arq->state: %d\n", arq->state);
-			WARN_ON(1);
-		}
-		arq->state = AS_RQ_NEW;
-	}
-
-	/* barriers must flush the reorder queue */
-	if (unlikely(rq->flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)
-			&& where == ELEVATOR_INSERT_SORT)) {
-		WARN_ON(1);
-		where = ELEVATOR_INSERT_BACK;
-	}
-
-	switch (where) {
-		case ELEVATOR_INSERT_BACK:
-			while (ad->next_arq[REQ_SYNC])
-				as_move_to_dispatch(ad, ad->next_arq[REQ_SYNC]);
-
-			while (ad->next_arq[REQ_ASYNC])
-				as_move_to_dispatch(ad, ad->next_arq[REQ_ASYNC]);
-
-			list_add_tail(&rq->queuelist, ad->dispatch);
-			as_account_queued_request(ad, rq);
-			as_antic_stop(ad);
-			break;
-		case ELEVATOR_INSERT_FRONT:
-			list_add(&rq->queuelist, ad->dispatch);
-			as_account_queued_request(ad, rq);
-			as_antic_stop(ad);
-			break;
-		case ELEVATOR_INSERT_SORT:
-			BUG_ON(!blk_fs_request(rq));
-			as_add_request(ad, arq);
-			break;
-		default:
-			BUG();
-			return;
-	}
+	WARN_ON(arq->state != AS_RQ_REMOVED);
+	arq->state = AS_RQ_DISPATCHED;
+	if (arq->io_context && arq->io_context->aic)
+		atomic_inc(&arq->io_context->aic->nr_dispatched);
 }
 
 /*
@@ -1565,12 +1436,8 @@ static int as_queue_empty(request_queue_t *q)
 {
 	struct as_data *ad = q->elevator->elevator_data;
 
-	if (!list_empty(&ad->fifo_list[REQ_ASYNC])
-		|| !list_empty(&ad->fifo_list[REQ_SYNC])
-		|| !list_empty(ad->dispatch))
-			return 0;
-
-	return 1;
+	return list_empty(&ad->fifo_list[REQ_ASYNC])
+		&& list_empty(&ad->fifo_list[REQ_SYNC]);
 }
 
 static struct request *
@@ -1608,15 +1475,6 @@ as_merge(request_queue_t *q, struct request **req, struct bio *bio)
 	int ret;
 
 	/*
-	 * try last_merge to avoid going to hash
-	 */
-	ret = elv_try_last_merge(q, bio);
-	if (ret != ELEVATOR_NO_MERGE) {
-		__rq = q->last_merge;
-		goto out_insert;
-	}
-
-	/*
 	 * see if the merge hash can satisfy a back merge
 	 */
 	__rq = as_find_arq_hash(ad, bio->bi_sector);
@@ -1644,9 +1502,6 @@ as_merge(request_queue_t *q, struct request **req, struct bio *bio)
 
 	return ELEVATOR_NO_MERGE;
 out:
-	if (rq_mergeable(__rq))
-		q->last_merge = __rq;
-out_insert:
 	if (ret) {
 		if (rq_mergeable(__rq))
 			as_hot_arq_hash(ad, RQ_DATA(__rq));
@@ -1693,9 +1548,6 @@ static void as_merged_request(request_queue_t *q, struct request *req)
 		 * behind the disk head. We currently don't bother adjusting.
 		 */
 	}
-
-	if (arq->on_hash)
-		q->last_merge = req;
 }
 
 static void
@@ -1763,6 +1615,7 @@ as_merged_requests(request_queue_t *q, struct request *req,
 	 * kill knowledge of next, this one is a goner
 	 */
 	as_remove_queued_request(q, next);
+	as_put_io_context(anext);
 
 	anext->state = AS_RQ_MERGED;
 }
@@ -1782,7 +1635,7 @@ static void as_work_handler(void *data)
 	unsigned long flags;
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	if (as_next_request(q))
+	if (!as_queue_empty(q))
 		q->request_fn(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
@@ -1797,7 +1650,9 @@ static void as_put_request(request_queue_t *q, struct request *rq)
 		return;
 	}
 
-	if (arq->state != AS_RQ_POSTSCHED && arq->state != AS_RQ_PRESCHED) {
+	if (unlikely(arq->state != AS_RQ_POSTSCHED &&
+		     arq->state != AS_RQ_PRESCHED &&
+		     arq->state != AS_RQ_MERGED)) {
 		printk("arq->state %d\n", arq->state);
 		WARN_ON(1);
 	}
@@ -1907,7 +1762,6 @@ static int as_init_queue(request_queue_t *q, elevator_t *e)
 	INIT_LIST_HEAD(&ad->fifo_list[REQ_ASYNC]);
 	ad->sort_list[REQ_SYNC] = RB_ROOT;
 	ad->sort_list[REQ_ASYNC] = RB_ROOT;
-	ad->dispatch = &q->queue_head;
 	ad->fifo_expire[REQ_SYNC] = default_read_expire;
 	ad->fifo_expire[REQ_ASYNC] = default_write_expire;
 	ad->antic_expire = default_antic_expire;
@@ -2072,10 +1926,9 @@ static struct elevator_type iosched_as = {
 		.elevator_merge_fn = 		as_merge,
 		.elevator_merged_fn =		as_merged_request,
 		.elevator_merge_req_fn =	as_merged_requests,
-		.elevator_next_req_fn =		as_next_request,
-		.elevator_add_req_fn =		as_insert_request,
-		.elevator_remove_req_fn =	as_remove_request,
-		.elevator_requeue_req_fn = 	as_requeue_request,
+		.elevator_dispatch_fn =		as_dispatch_request,
+		.elevator_add_req_fn =		as_add_request,
+		.elevator_activate_req_fn =	as_activate_request,
 		.elevator_deactivate_req_fn = 	as_deactivate_request,
 		.elevator_queue_empty_fn =	as_queue_empty,
 		.elevator_completed_req_fn =	as_completed_request,
diff --git a/drivers/block/cfq-iosched.c b/drivers/block/cfq-iosched.c
index d3bfe8cfb03..94690e4d41e 100644
--- a/drivers/block/cfq-iosched.c
+++ b/drivers/block/cfq-iosched.c
@@ -84,7 +84,6 @@ static int cfq_max_depth = 2;
 	(node)->rb_left = NULL;		\
 } while (0)
 #define RB_CLEAR_ROOT(root)	((root)->rb_node = NULL)
-#define ON_RB(node)		((node)->rb_color != RB_NONE)
 #define rb_entry_crq(node)	rb_entry((node), struct cfq_rq, rb_node)
 #define rq_rb_key(rq)		(rq)->sector
 
@@ -271,10 +270,7 @@ CFQ_CFQQ_FNS(expired);
 #undef CFQ_CFQQ_FNS
 
 enum cfq_rq_state_flags {
-	CFQ_CRQ_FLAG_in_flight = 0,
-	CFQ_CRQ_FLAG_in_driver,
-	CFQ_CRQ_FLAG_is_sync,
-	CFQ_CRQ_FLAG_requeued,
+	CFQ_CRQ_FLAG_is_sync = 0,
 };
 
 #define CFQ_CRQ_FNS(name)						\
@@ -291,14 +287,11 @@ static inline int cfq_crq_##name(const struct cfq_rq *crq)		\
 	return (crq->crq_flags & (1 << CFQ_CRQ_FLAG_##name)) != 0;	\
 }
 
-CFQ_CRQ_FNS(in_flight);
-CFQ_CRQ_FNS(in_driver);
 CFQ_CRQ_FNS(is_sync);
-CFQ_CRQ_FNS(requeued);
 #undef CFQ_CRQ_FNS
 
 static struct cfq_queue *cfq_find_cfq_hash(struct cfq_data *, unsigned int, unsigned short);
-static void cfq_dispatch_sort(request_queue_t *, struct cfq_rq *);
+static void cfq_dispatch_insert(request_queue_t *, struct cfq_rq *);
 static void cfq_put_cfqd(struct cfq_data *cfqd);
 
 #define process_sync(tsk)	((tsk)->flags & PF_SYNCWRITE)
@@ -311,14 +304,6 @@ static inline void cfq_del_crq_hash(struct cfq_rq *crq)
 	hlist_del_init(&crq->hash);
 }
 
-static void cfq_remove_merge_hints(request_queue_t *q, struct cfq_rq *crq)
-{
-	cfq_del_crq_hash(crq);
-
-	if (q->last_merge == crq->request)
-		q->last_merge = NULL;
-}
-
 static inline void cfq_add_crq_hash(struct cfq_data *cfqd, struct cfq_rq *crq)
 {
 	const int hash_idx = CFQ_MHASH_FN(rq_hash_key(crq->request));
@@ -347,18 +332,13 @@ static struct request *cfq_find_rq_hash(struct cfq_data *cfqd, sector_t offset)
 	return NULL;
 }
 
-static inline int cfq_pending_requests(struct cfq_data *cfqd)
-{
-	return !list_empty(&cfqd->queue->queue_head) || cfqd->busy_queues;
-}
-
 /*
  * scheduler run of queue, if there are requests pending and no one in the
  * driver that will restart queueing
  */
 static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
 {
-	if (!cfqd->rq_in_driver && cfq_pending_requests(cfqd))
+	if (!cfqd->rq_in_driver && cfqd->busy_queues)
 		kblockd_schedule_work(&cfqd->unplug_work);
 }
 
@@ -366,7 +346,7 @@ static int cfq_queue_empty(request_queue_t *q)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 
-	return !cfq_pending_requests(cfqd);
+	return !cfqd->busy_queues;
 }
 
 /*
@@ -386,11 +366,6 @@ cfq_choose_req(struct cfq_data *cfqd, struct cfq_rq *crq1, struct cfq_rq *crq2)
 	if (crq2 == NULL)
 		return crq1;
 
-	if (cfq_crq_requeued(crq1) && !cfq_crq_requeued(crq2))
-		return crq1;
-	else if (cfq_crq_requeued(crq2) && !cfq_crq_requeued(crq1))
-		return crq2;
-
 	if (cfq_crq_is_sync(crq1) && !cfq_crq_is_sync(crq2))
 		return crq1;
 	else if (cfq_crq_is_sync(crq2) && !cfq_crq_is_sync(crq1))
@@ -461,10 +436,7 @@ cfq_find_next_crq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	struct cfq_rq *crq_next = NULL, *crq_prev = NULL;
 	struct rb_node *rbnext, *rbprev;
 
-	rbnext = NULL;
-	if (ON_RB(&last->rb_node))
-		rbnext = rb_next(&last->rb_node);
-	if (!rbnext) {
+	if (!(rbnext = rb_next(&last->rb_node))) {
 		rbnext = rb_first(&cfqq->sort_list);
 		if (rbnext == &last->rb_node)
 			rbnext = NULL;
@@ -545,13 +517,13 @@ static void cfq_resort_rr_list(struct cfq_queue *cfqq, int preempted)
  * the pending list according to last request service
  */
 static inline void
-cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq, int requeue)
+cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	cfq_mark_cfqq_on_rr(cfqq);
 	cfqd->busy_queues++;
 
-	cfq_resort_rr_list(cfqq, requeue);
+	cfq_resort_rr_list(cfqq, 0);
 }
 
 static inline void
@@ -571,22 +543,19 @@ cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static inline void cfq_del_crq_rb(struct cfq_rq *crq)
 {
 	struct cfq_queue *cfqq = crq->cfq_queue;
+	struct cfq_data *cfqd = cfqq->cfqd;
+	const int sync = cfq_crq_is_sync(crq);
 
-	if (ON_RB(&crq->rb_node)) {
-		struct cfq_data *cfqd = cfqq->cfqd;
-		const int sync = cfq_crq_is_sync(crq);
+	BUG_ON(!cfqq->queued[sync]);
+	cfqq->queued[sync]--;
 
-		BUG_ON(!cfqq->queued[sync]);
-		cfqq->queued[sync]--;
+	cfq_update_next_crq(crq);
 
-		cfq_update_next_crq(crq);
+	rb_erase(&crq->rb_node, &cfqq->sort_list);
+	RB_CLEAR_COLOR(&crq->rb_node);
 
-		rb_erase(&crq->rb_node, &cfqq->sort_list);
-		RB_CLEAR_COLOR(&crq->rb_node);
-
-		if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY(&cfqq->sort_list))
-			cfq_del_cfqq_rr(cfqd, cfqq);
-	}
+	if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY(&cfqq->sort_list))
+		cfq_del_cfqq_rr(cfqd, cfqq);
 }
 
 static struct cfq_rq *
@@ -627,12 +596,12 @@ static void cfq_add_crq_rb(struct cfq_rq *crq)
 	 * if that happens, put the alias on the dispatch list
 	 */
 	while ((__alias = __cfq_add_crq_rb(crq)) != NULL)
-		cfq_dispatch_sort(cfqd->queue, __alias);
+		cfq_dispatch_insert(cfqd->queue, __alias);
 
 	rb_insert_color(&crq->rb_node, &cfqq->sort_list);
 
 	if (!cfq_cfqq_on_rr(cfqq))
-		cfq_add_cfqq_rr(cfqd, cfqq, cfq_crq_requeued(crq));
+		cfq_add_cfqq_rr(cfqd, cfqq);
 
 	/*
 	 * check if this request is a better next-serve candidate
@@ -643,10 +612,8 @@ static void cfq_add_crq_rb(struct cfq_rq *crq)
 static inline void
 cfq_reposition_crq_rb(struct cfq_queue *cfqq, struct cfq_rq *crq)
 {
-	if (ON_RB(&crq->rb_node)) {
-		rb_erase(&crq->rb_node, &cfqq->sort_list);
-		cfqq->queued[cfq_crq_is_sync(crq)]--;
-	}
+	rb_erase(&crq->rb_node, &cfqq->sort_list);
+	cfqq->queued[cfq_crq_is_sync(crq)]--;
 
 	cfq_add_crq_rb(crq);
 }
@@ -676,49 +643,28 @@ out:
 	return NULL;
 }
 
-static void cfq_deactivate_request(request_queue_t *q, struct request *rq)
+static void cfq_activate_request(request_queue_t *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
-	struct cfq_rq *crq = RQ_DATA(rq);
-
-	if (crq) {
-		struct cfq_queue *cfqq = crq->cfq_queue;
-
-		if (cfq_crq_in_driver(crq)) {
-			cfq_clear_crq_in_driver(crq);
-			WARN_ON(!cfqd->rq_in_driver);
-			cfqd->rq_in_driver--;
-		}
-		if (cfq_crq_in_flight(crq)) {
-			const int sync = cfq_crq_is_sync(crq);
 
-			cfq_clear_crq_in_flight(crq);
-			WARN_ON(!cfqq->on_dispatch[sync]);
-			cfqq->on_dispatch[sync]--;
-		}
-		cfq_mark_crq_requeued(crq);
-	}
+	cfqd->rq_in_driver++;
 }
 
-/*
- * make sure the service time gets corrected on reissue of this request
- */
-static void cfq_requeue_request(request_queue_t *q, struct request *rq)
+static void cfq_deactivate_request(request_queue_t *q, struct request *rq)
 {
-	cfq_deactivate_request(q, rq);
-	list_add(&rq->queuelist, &q->queue_head);
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+
+	WARN_ON(!cfqd->rq_in_driver);
+	cfqd->rq_in_driver--;
 }
 
-static void cfq_remove_request(request_queue_t *q, struct request *rq)
+static void cfq_remove_request(struct request *rq)
 {
 	struct cfq_rq *crq = RQ_DATA(rq);
 
-	if (crq) {
-		list_del_init(&rq->queuelist);
-		cfq_del_crq_rb(crq);
-		cfq_remove_merge_hints(q, crq);
-
-	}
+	list_del_init(&rq->queuelist);
+	cfq_del_crq_rb(crq);
+	cfq_del_crq_hash(crq);
 }
 
 static int
@@ -728,12 +674,6 @@ cfq_merge(request_queue_t *q, struct request **req, struct bio *bio)
 	struct request *__rq;
 	int ret;
 
-	ret = elv_try_last_merge(q, bio);
-	if (ret != ELEVATOR_NO_MERGE) {
-		__rq = q->last_merge;
-		goto out_insert;
-	}
-
 	__rq = cfq_find_rq_hash(cfqd, bio->bi_sector);
 	if (__rq && elv_rq_merge_ok(__rq, bio)) {
 		ret = ELEVATOR_BACK_MERGE;
@@ -748,8 +688,6 @@ cfq_merge(request_queue_t *q, struct request **req, struct bio *bio)
 
 	return ELEVATOR_NO_MERGE;
 out:
-	q->last_merge = __rq;
-out_insert:
 	*req = __rq;
 	return ret;
 }
@@ -762,14 +700,12 @@ static void cfq_merged_request(request_queue_t *q, struct request *req)
 	cfq_del_crq_hash(crq);
 	cfq_add_crq_hash(cfqd, crq);
 
-	if (ON_RB(&crq->rb_node) && (rq_rb_key(req) != crq->rb_key)) {
+	if (rq_rb_key(req) != crq->rb_key) {
 		struct cfq_queue *cfqq = crq->cfq_queue;
 
 		cfq_update_nex