path: root/5002_block-introduce-the-BFQ-v7r7-I-O-sched-for-4.0.patch1

From 8cdf2dae6ee87049c7bb086d34e2ce981b545813 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@unimore.it>
Date: Thu, 9 May 2013 19:10:02 +0200
Subject: [PATCH 2/3] block: introduce the BFQ-v7r7 I/O sched for 4.0

Add the BFQ-v7r7 I/O scheduler to 4.0.
The general structure is borrowed from CFQ, as much of the code for
handling I/O contexts. Over time, several useful features have been
ported from CFQ as well (details in the changelog in README.BFQ). A
(bfq_)queue is associated to each task doing I/O on a device, and each
time a scheduling decision has to be made a queue is selected and served
until it expires.

    - Slices are given in the service domain: tasks are assigned
      budgets, measured in number of sectors. Once got the disk, a task
      must however consume its assigned budget within a configurable
      maximum time (by default, the maximum possible value of the
      budgets is automatically computed to comply with this timeout).
      This allows the desired latency vs "throughput boosting" tradeoff
      to be set.

    - Budgets are scheduled according to a variant of WF2Q+, implemented
      using an augmented rb-tree to take eligibility into account while
      preserving an O(log N) overall complexity.

    - A low-latency tunable is provided; if enabled, both interactive
      and soft real-time applications are guaranteed a very low latency.

    - Latency guarantees are preserved also in the presence of NCQ.

    - Also with flash-based devices, a high throughput is achieved
      while still preserving latency guarantees.

    - BFQ features Early Queue Merge (EQM), a sort of fusion of the
      cooperating-queue-merging and the preemption mechanisms present
      in CFQ. EQM is in fact a unified mechanism that tries to get a
      sequential read pattern, and hence a high throughput, with any
      set of processes performing interleaved I/O over a contiguous
      sequence of sectors.

    - BFQ supports full hierarchical scheduling, exporting a cgroups
      interface.  Since each node has a full scheduler, each group can
      be assigned its own weight.

    - If the cgroups interface is not used, only I/O priorities can be
      assigned to processes, with ioprio values mapped to weights
      with the relation weight = IOPRIO_BE_NR - ioprio.

    - ioprio classes are served in strict priority order, i.e., lower
      priority queues are not served as long as there are higher
      priority queues.  Among queues in the same class the bandwidth is
      distributed in proportion to the weight of each queue. A very
      thin extra bandwidth is however guaranteed to the Idle class, to
      prevent it from starving.

Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
 block/bfq-cgroup.c  |  936 ++++++++++++
 block/bfq-ioc.c     |   36 +
 block/bfq-iosched.c | 3902 +++++++++++++++++++++++++++++++++++++++++++++++++++
 block/bfq-sched.c   | 1214 ++++++++++++++++
 block/bfq.h         |  775 ++++++++++
 5 files changed, 6863 insertions(+)
 create mode 100644 block/bfq-cgroup.c
 create mode 100644 block/bfq-ioc.c
 create mode 100644 block/bfq-iosched.c
 create mode 100644 block/bfq-sched.c
 create mode 100644 block/bfq.h

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
new file mode 100644
index 0000000..11e2f1d
--- /dev/null
+++ b/block/bfq-cgroup.c
@@ -0,0 +1,936 @@
+/*
+ * BFQ: CGROUPS support.
+ *
+ * Based on ideas and code from CFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ *		      Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ
+ * file.
+ */
+
+#ifdef CONFIG_CGROUP_BFQIO
+
+static DEFINE_MUTEX(bfqio_mutex);
+
+static bool bfqio_is_removed(struct bfqio_cgroup *bgrp)
+{
+	return bgrp ? !bgrp->online : false;
+}
+
+static struct bfqio_cgroup bfqio_root_cgroup = {
+	.weight = BFQ_DEFAULT_GRP_WEIGHT,
+	.ioprio = BFQ_DEFAULT_GRP_IOPRIO,
+	.ioprio_class = BFQ_DEFAULT_GRP_CLASS,
+};
+
+static inline void bfq_init_entity(struct bfq_entity *entity,
+				   struct bfq_group *bfqg)
+{
+	entity->weight = entity->new_weight;
+	entity->orig_weight = entity->new_weight;
+	entity->ioprio = entity->new_ioprio;
+	entity->ioprio_class = entity->new_ioprio_class;
+	entity->parent = bfqg->my_entity;
+	entity->sched_data = &bfqg->sched_data;
+}
+
+static struct bfqio_cgroup *css_to_bfqio(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct bfqio_cgroup, css) : NULL;
+}
+
+/*
+ * Search the bfq_group for bfqd into the hash table (by now only a list)
+ * of bgrp.  Must be called under rcu_read_lock().
+ */
+static struct bfq_group *bfqio_lookup_group(struct bfqio_cgroup *bgrp,
+					    struct bfq_data *bfqd)
+{
+	struct bfq_group *bfqg;
+	void *key;
+
+	hlist_for_each_entry_rcu(bfqg, &bgrp->group_data, group_node) {
+		key = rcu_dereference(bfqg->bfqd);
+		if (key == bfqd)
+			return bfqg;
+	}
+
+	return NULL;
+}
+
+static inline void bfq_group_init_entity(struct bfqio_cgroup *bgrp,
+					 struct bfq_group *bfqg)
+{
+	struct bfq_entity *entity = &bfqg->entity;
+
+	/*
+	 * If the weight of the entity has never been set via the sysfs
+	 * interface, then bgrp->weight == 0. In this case we initialize
+	 * the weight from the current ioprio value. Otherwise, the group
+	 * weight, if set, has priority over the ioprio value.
+	 */
+	if (bgrp->weight == 0) {
+		entity->new_weight = bfq_ioprio_to_weight(bgrp->ioprio);
+		entity->new_ioprio = bgrp->ioprio;
+	} else {
+		if (bgrp->weight < BFQ_MIN_WEIGHT ||
+		    bgrp->weight > BFQ_MAX_WEIGHT) {
+			printk(KERN_CRIT "bfq_group_init_entity: "
+					 "bgrp->weight %d\n", bgrp->weight);
+			BUG();
+		}
+		entity->new_weight = bgrp->weight;
+		entity->new_ioprio = bfq_weight_to_ioprio(bgrp->weight);
+	}
+	entity->orig_weight = entity->weight = entity->new_weight;
+	entity->ioprio = entity->new_ioprio;
+	entity->ioprio_class = entity->new_ioprio_class = bgrp->ioprio_class;
+	entity->my_sched_data = &bfqg->sched_data;
+	bfqg->active_entities = 0;
+}
+
+static inline void bfq_group_set_parent(struct bfq_group *bfqg,
+					struct bfq_group *parent)
+{
+	struct bfq_entity *entity;
+
+	BUG_ON(parent == NULL);
+	BUG_ON(bfqg == NULL);
+
+	entity = &bfqg->entity;
+	entity->parent = parent->my_entity;
+	entity->sched_data = &parent->sched_data;
+}
+
+/**
+ * bfq_group_chain_alloc - allocate a chain of groups.
+ * @bfqd: queue descriptor.
+ * @css: the leaf cgroup_subsys_state this chain starts from.
+ *
+ * Allocate a chain of groups starting from the one belonging to
+ * @cgroup up to the root cgroup.  Stop if a cgroup on the chain
+ * to the root has already an allocated group on @bfqd.
+ */
+static struct bfq_group *bfq_group_chain_alloc(struct bfq_data *bfqd,
+					       struct cgroup_subsys_state *css)
+{
+	struct bfqio_cgroup *bgrp;
+	struct bfq_group *bfqg, *prev = NULL, *leaf = NULL;
+
+	for (; css != NULL; css = css->parent) {
+		bgrp = css_to_bfqio(css);
+
+		bfqg = bfqio_lookup_group(bgrp, bfqd);
+		if (bfqg != NULL) {
+			/*
+			 * All the cgroups in the path from there to the
+			 * root must have a bfq_group for bfqd, so we don't
+			 * need any more allocations.
+			 */
+			break;
+		}
+
+		bfqg = kzalloc(sizeof(*bfqg), GFP_ATOMIC);
+		if (bfqg == NULL)
+			goto cleanup;
+
+		bfq_group_init_entity(bgrp, bfqg);
+		bfqg->my_entity = &bfqg->entity;
+
+		if (leaf == NULL) {
+			leaf = bfqg;
+			prev = leaf;
+		} else {
+			bfq_group_set_parent(prev, bfqg);
+			/*
+			 * Build a list of allocated nodes using the bfqd
+			 * filed, that is still unused and will be
+			 * initialized only after the node will be
+			 * connected.
+			 */
+			prev->bfqd = bfqg;
+			prev = bfqg;
+		}
+	}
+
+	return leaf;
+
+cleanup:
+	while (leaf != NULL) {
+		prev = leaf;
+		leaf = leaf->bfqd;
+		kfree(prev);
+	}
+
+	return NULL;
+}
+
+/**
+ * bfq_group_chain_link - link an allocated group chain to a cgroup
+ *                        hierarchy.
+ * @bfqd: the queue descriptor.
+ * @css: the leaf cgroup_subsys_state to start from.
+ * @leaf: the leaf group (to be associated to @cgroup).
+ *
+ * Try to link a chain of groups to a cgroup hierarchy, connecting the
+ * nodes bottom-up, so we can be sure that when we find a cgroup in the
+ * hierarchy that already as a group associated to @bfqd all the nodes
+ * in the path to the root cgroup have one too.
+ *
+ * On locking: the queue lock protects the hierarchy (there is a hierarchy
+ * per device) while the bfqio_cgroup lock protects the list of groups
+ * belonging to the same cgroup.
+ */
+static void bfq_group_chain_link(struct bfq_data *bfqd,
+				 struct cgroup_subsys_state *css,
+				 struct bfq_group *leaf)
+{
+	struct bfqio_cgroup *bgrp;
+	struct bfq_group *bfqg, *next, *prev = NULL;
+	unsigned long flags;
+
+	assert_spin_locked(bfqd->queue->queue_lock);
+
+	for (; css != NULL && leaf != NULL; css = css->parent) {
+		bgrp = css_to_bfqio(css);
+		next = leaf->bfqd;
+
+		bfqg = bfqio_lookup_group(bgrp, bfqd);
+		BUG_ON(bfqg != NULL);
+
+		spin_lock_irqsave(&bgrp->lock, flags);
+
+		rcu_assign_pointer(leaf->bfqd, bfqd);
+		hlist_add_head_rcu(&leaf->group_node, &bgrp->group_data);
+		hlist_add_head(&leaf->bfqd_node, &bfqd->group_list);
+
+		spin_unlock_irqrestore(&bgrp->lock, flags);
+
+		prev = leaf;
+		leaf = next;
+	}
+
+	BUG_ON(css == NULL && leaf != NULL);
+	if (css != NULL && prev != NULL) {
+		bgrp = css_to_bfqio(css);
+		bfqg = bfqio_lookup_group(bgrp, bfqd);
+		bfq_group_set_parent(prev, bfqg);
+	}
+}
+
+/**
+ * bfq_find_alloc_group - return the group associated to @bfqd in @cgroup.
+ * @bfqd: queue descriptor.
+ * @cgroup: cgroup being searched for.
+ *
+ * Return a group associated to @bfqd in @cgroup, allocating one if
+ * necessary.  When a group is returned all the cgroups in the path
+ * to the root have a group associated to @bfqd.
+ *
+ * If the allocation fails, return the root group: this breaks guarantees
+ * but is a safe fallback.  If this loss becomes a problem it can be
+ * mitigated using the equivalent weight (given by the product of the
+ * weights of the groups in the path from @group to the root) in the
+ * root scheduler.
+ *
+ * We allocate all the missing nodes in the path from the leaf cgroup
+ * to the root and we connect the nodes only after all the allocations
+ * have been successful.
+ */
+static struct bfq_group *bfq_find_alloc_group(struct bfq_data *bfqd,
+					      struct cgroup_subsys_state *css)
+{
+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);
+	struct bfq_group *bfqg;
+
+	bfqg = bfqio_lookup_group(bgrp, bfqd);
+	if (bfqg != NULL)
+		return bfqg;
+
+	bfqg = bfq_group_chain_alloc(bfqd, css);
+	if (bfqg != NULL)
+		bfq_group_chain_link(bfqd, css, bfqg);
+	else
+		bfqg = bfqd->root_group;
+
+	return bfqg;
+}
+
+/**
+ * bfq_bfqq_move - migrate @bfqq to @bfqg.
+ * @bfqd: queue descriptor.
+ * @bfqq: the queue to move.
+ * @entity: @bfqq's entity.
+ * @bfqg: the group to move to.
+ *
+ * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
+ * it on the new one.  Avoid putting the entity on the old group idle tree.
+ *
+ * Must be called under the queue lock; the cgroup owning @bfqg must
+ * not disappear (by now this just means that we are called under
+ * rcu_read_lock()).
+ */
+static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			  struct bfq_entity *entity, struct bfq_group *bfqg)
+{
+	int busy, resume;
+
+	busy = bfq_bfqq_busy(bfqq);
+	resume = !RB_EMPTY_ROOT(&bfqq->sort_list);
+
+	BUG_ON(resume && !entity->on_st);
+	BUG_ON(busy && !resume && entity->on_st &&
+	       bfqq != bfqd->in_service_queue);
+
+	if (busy) {
+		BUG_ON(atomic_read(&bfqq->ref) < 2);
+
+		if (!resume)
+			bfq_del_bfqq_busy(bfqd, bfqq, 0);
+		else
+			bfq_deactivate_bfqq(bfqd, bfqq, 0);
+	} else if (entity->on_st)
+		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
+
+	/*
+	 * Here we use a reference to bfqg.  We don't need a refcounter
+	 * as the cgroup reference will not be dropped, so that its
+	 * destroy() callback will not be invoked.
+	 */
+	entity->parent = bfqg->my_entity;
+	entity->sched_data = &bfqg->sched_data;
+
+	if (busy && resume)
+		bfq_activate_bfqq(bfqd, bfqq);
+
+	if (bfqd->in_service_queue == NULL && !bfqd->rq_in_driver)
+		bfq_schedule_dispatch(bfqd);
+}
+
+/**
+ * __bfq_bic_change_cgroup - move @bic to @cgroup.
+ * @bfqd: the queue descriptor.
+ * @bic: the bic to move.
+ * @cgroup: the cgroup to move to.
+ *
+ * Move bic to cgroup, assuming that bfqd->queue is locked; the caller
+ * has to make sure that the reference to cgroup is valid across the call.
+ *
+ * NOTE: an alternative approach might have been to store the current
+ * cgroup in bfqq and getting a reference to it, reducing the lookup
+ * time here, at the price of slightly more complex code.
+ */
+static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
+						struct bfq_io_cq *bic,
+						struct cgroup_subsys_state *css)
+{
+	struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
+	struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
+	struct bfq_entity *entity;
+	struct bfq_group *bfqg;
+	struct bfqio_cgroup *bgrp;
+
+	bgrp = css_to_bfqio(css);
+
+	bfqg = bfq_find_alloc_group(bfqd, css);
+	if (async_bfqq != NULL) {
+		entity = &async_bfqq->entity;
+
+		if (entity->sched_data != &bfqg->sched_data) {
+			bic_set_bfqq(bic, NULL, 0);
+			bfq_log_bfqq(bfqd, async_bfqq,
+				     "bic_change_group: %p %d",
+				     async_bfqq, atomic_read(&async_bfqq->ref));
+			bfq_put_queue(async_bfqq);
+		}
+	}
+
+	if (sync_bfqq != NULL) {
+		entity = &sync_bfqq->entity;
+		if (entity->sched_data != &bfqg->sched_data)
+			bfq_bfqq_move(bfqd, sync_bfqq, entity, bfqg);
+	}
+
+	return bfqg;
+}
+
+/**
+ * bfq_bic_change_cgroup - move @bic to @cgroup.
+ * @bic: the bic being migrated.
+ * @cgroup: the destination cgroup.
+ *
+ * When the task owning @bic is moved to @cgroup, @bic is immediately
+ * moved into its new parent group.
+ */
+static void bfq_bic_change_cgroup(struct bfq_io_cq *bic,
+				  struct cgroup_subsys_state *css)
+{
+	struct bfq_data *bfqd;
+	unsigned long uninitialized_var(flags);
+
+	bfqd = bfq_get_bfqd_locked(&(bic->icq.q->elevator->elevator_data),
+				   &flags);
+	if (bfqd != NULL) {
+		__bfq_bic_change_cgroup(bfqd, bic, css);
+		bfq_put_bfqd_unlock(bfqd, &flags);
+	}
+}
+
+/**
+ * bfq_bic_update_cgroup - update the cgroup of @bic.
+ * @bic: the @bic to update.
+ *
+ * Make sure that @bic is enqueued in the cgroup of the current task.
+ * We need this in addition to moving bics during the cgroup attach
+ * phase because the task owning @bic could be at its first disk
+ * access or we may end up in the root cgroup as the result of a
+ * memory allocation failure and here we try to move to the right
+ * group.
+ *
+ * Must be called under the queue lock.  It is safe to use the returned
+ * value even after the rcu_read_unlock() as the migration/destruction
+ * paths act under the queue lock too.  IOW it is impossible to race with
+ * group migration/destruction and end up with an invalid group as:
+ *   a) here cgroup has not yet been destroyed, nor its destroy callback
+ *      has started execution, as current holds a reference to it,
+ *   b) if it is destroyed after rcu_read_unlock() [after current is
+ *      migrated to a different cgroup] its attach() callback will have
+ *      taken care of remove all the references to the old cgroup data.
+ */
+static struct bfq_group *bfq_bic_update_cgroup(struct bfq_io_cq *bic)
+{
+	struct bfq_data *bfqd = bic_to_bfqd(bic);
+	struct bfq_group *bfqg;
+	struct cgroup_subsys_state *css;
+
+	BUG_ON(bfqd == NULL);
+
+	rcu_read_lock();
+	css = task_css(current, bfqio_cgrp_id);
+	bfqg = __bfq_bic_change_cgroup(bfqd, bic, css);
+	rcu_read_unlock();
+
+	return bfqg;
+}
+
+/**
+ * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st.
+ * @st: the service tree being flushed.
+ */
+static inline void bfq_flush_idle_tree(struct bfq_service_tree *st)
+{
+	struct bfq_entity *entity = st->first_idle;
+
+	for (; entity != NULL; entity = st->first_idle)
+		__bfq_deactivate_entity(entity, 0);
+}
+
+/**
+ * bfq_reparent_leaf_entity - move leaf entity to the root_group.
+ * @bfqd: the device data structure with the root group.
+ * @entity: the entity to move.
+ */
+static inline void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
+					    struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	BUG_ON(bfqq == NULL);
+	bfq_bfqq_move(bfqd, bfqq, entity, bfqd->root_group);
+	return;
+}
+
+/**
+ * bfq_reparent_active_entities - move to the root group all active
+ *                                entities.
+ * @bfqd: the device data structure with the root group.
+ * @bfqg: the group to move from.
+ * @st: the service tree with the entities.
+ *
+ * Needs queue_lock to be taken and reference to be valid over the call.
+ */
+static inline void bfq_reparent_active_entities(struct bfq_data *bfqd,
+						struct bfq_group *bfqg,
+						struct bfq_service_tree *st)
+{
+	struct rb_root *active = &st->active;
+	struct bfq_entity *entity = NULL;
+
+	if (!RB_EMPTY_ROOT(&st->active))
+		entity = bfq_entity_of(rb_first(active));
+
+	for (; entity != NULL; entity = bfq_entity_of(rb_first(active)))
+		bfq_reparent_leaf_entity(bfqd, entity);
+
+	if (bfqg->sched_data.in_service_entity != NULL)
+		bfq_reparent_leaf_entity(bfqd,
+			bfqg->sched_data.in_service_entity);
+
+	return;
+}
+
+/**
+ * bfq_destroy_group - destroy @bfqg.
+ * @bgrp: the bfqio_cgroup containing @bfqg.
+ * @bfqg: the group being destroyed.
+ *
+ * Destroy @bfqg, making sure that it is not referenced from its parent.
+ */
+static void bfq_destroy_group(struct bfqio_cgroup *bgrp, struct bfq_group *bfqg)
+{
+	struct bfq_data *bfqd;
+	struct bfq_service_tree *st;
+	struct bfq_entity *entity = bfqg->my_entity;
+	unsigned long uninitialized_var(flags);
+	int i;
+
+	hlist_del(&bfqg->group_node);
+
+	/*
+	 * Empty all service_trees belonging to this group before
+	 * deactivating the group itself.
+	 */
+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
+		st = bfqg->sched_data.service_tree + i;
+
+		/*
+		 * The idle tree may still contain bfq_queues belonging
+		 * to exited task because they never migrated to a different
+		 * cgroup from the one being destroyed now.  No one else
+		 * can access them so it's safe to act without any lock.
+		 */
+		bfq_flush_idle_tree(st);
+
+		/*
+		 * It may happen that some queues are still active
+		 * (busy) upon group destruction (if the corresponding
+		 * processes have been forced to terminate). We move
+		 * all the leaf entities corresponding to these queues
+		 * to the root_group.
+		 * Also, it may happen that the group has an entity
+		 * in service, which is disconnected from the active
+		 * tree: it must be moved, too.
+		 * There is no need to put the sync queues, as the
+		 * scheduler has taken no reference.
+		 */
+		bfqd = bfq_get_bfqd_locked(&bfqg->bfqd, &flags);
+		if (bfqd != NULL) {
+			bfq_reparent_active_entities(bfqd, bfqg, st);
+			bfq_put_bfqd_unlock(bfqd, &flags);
+		}
+		BUG_ON(!RB_EMPTY_ROOT(&st->active));
+		BUG_ON(!RB_EMPTY_ROOT(&st->idle));
+	}
+	BUG_ON(bfqg->sched_data.next_in_service != NULL);
+	BUG_ON(bfqg->sched_data.in_service_entity != NULL);
+
+	/*
+	 * We may race with device destruction, take extra care when
+	 * dereferencing bfqg->bfqd.
+	 */
+	bfqd = bfq_get_bfqd_locked(&bfqg->bfqd, &flags);
+	if (bfqd != NULL) {
+		hlist_del(&bfqg->bfqd_node);
+		__bfq_deactivate_entity(entity, 0);
+		bfq_put_async_queues(bfqd, bfqg);
+		bfq_put_bfqd_unlock(bfqd, &flags);
+	}
+	BUG_ON(entity->tree != NULL);
+
+	/*
+	 * No need to defer the kfree() to the end of the RCU grace
+	 * period: we are called from the destroy() callback of our
+	 * cgroup, so we can be sure that no one is a) still using
+	 * this cgroup or b) doing lookups in it.
+	 */
+	kfree(bfqg);
+}
+
+static void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+	struct hlist_node *tmp;
+	struct bfq_group *bfqg;
+
+	hlist_for_each_entry_safe(bfqg, tmp, &bfqd->group_list, bfqd_node)
+		bfq_end_wr_async_queues(bfqd, bfqg);
+	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
+/**
+ * bfq_disconnect_groups - disconnect @bfqd from all its groups.
+ * @bfqd: the device descriptor being exited.
+ *
+ * When the device exits we just make sure that no lookup can return
+ * the now unused group structures.  They will be deallocated on cgroup
+ * destruction.
+ */
+static void bfq_disconnect_groups(struct bfq_data *bfqd)
+{
+	struct hlist_node *tmp;
+	struct bfq_group *bfqg;
+
+	bfq_log(bfqd, "disconnect_groups beginning");
+	hlist_for_each_entry_safe(bfqg, tmp, &bfqd->group_list, bfqd_node) {
+		hlist_del(&bfqg->bfqd_node);
+
+		__bfq_deactivate_entity(bfqg->my_entity, 0);
+
+		/*
+		 * Don't remove from the group hash, just set an
+		 * invalid key.  No lookups can race with the
+		 * assignment as bfqd is being destroyed; this
+		 * implies also that new elements cannot be added
+		 * to the list.
+		 */
+		rcu_assign_pointer(bfqg->bfqd, NULL);
+
+		bfq_log(bfqd, "disconnect_groups: put async for group %p",
+			bfqg);
+		bfq_put_async_queues(bfqd, bfqg);
+	}
+}
+
+static inline void bfq_free_root_group(struct bfq_data *bfqd)
+{
+	struct bfqio_cgroup *bgrp = &bfqio_root_cgroup;
+	struct bfq_group *bfqg = bfqd->root_group;
+
+	bfq_put_async_queues(bfqd, bfqg);
+
+	spin_lock_irq(&bgrp->lock);
+	hlist_del_rcu(&bfqg->group_node);
+	spin_unlock_irq(&bgrp->lock);
+
+	/*
+	 * No need to synchronize_rcu() here: since the device is gone
+	 * there cannot be any read-side access to its root_group.
+	 */
+	kfree(bfqg);
+}
+
+static struct bfq_group *bfq_alloc_root_group(struct bfq_data *bfqd, int node)
+{
+	struct bfq_group *bfqg;
+	struct bfqio_cgroup *bgrp;
+	int i;
+
+	bfqg = kzalloc_node(sizeof(*bfqg), GFP_KERNEL, node);
+	if (bfqg == NULL)
+		return NULL;
+
+	bfqg->entity.parent = NULL;
+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+		bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+
+	bgrp = &bfqio_root_cgroup;
+	spin_lock_irq(&bgrp->lock);
+	rcu_assign_pointer(bfqg->bfqd, bfqd);
+	hlist_add_head_rcu(&bfqg->group_node, &bgrp->group_data);
+	spin_unlock_irq(&bgrp->lock);
+
+	return bfqg;
+}
+
+#define SHOW_FUNCTION(__VAR)						\
+static u64 bfqio_cgroup_##__VAR##_read(struct cgroup_subsys_state *css, \
+				       struct cftype *cftype)		\
+{									\
+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);			\
+	u64 ret = -ENODEV;						\
+									\
+	mutex_lock(&bfqio_mutex);					\
+	if (bfqio_is_removed(bgrp))					\
+		goto out_unlock;					\
+									\
+	spin_lock_irq(&bgrp->lock);					\
+	ret = bgrp->__VAR;						\
+	spin_unlock_irq(&bgrp->lock);					\
+									\
+out_unlock:								\
+	mutex_unlock(&bfqio_mutex);					\
+	return ret;							\
+}
+
+SHOW_FUNCTION(weight);
+SHOW_FUNCTION(ioprio);
+SHOW_FUNCTION(ioprio_class);
+#undef SHOW_FUNCTION
+
+#define STORE_FUNCTION(__VAR, __MIN, __MAX)				\
+static int bfqio_cgroup_##__VAR##_write(struct cgroup_subsys_state *css,\
+					struct cftype *cftype,		\
+					u64 val)			\
+{									\
+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);			\
+	struct bfq_group *bfqg;						\
+	int ret = -EINVAL;						\
+									\
+	if (val < (__MIN) || val > (__MAX))				\
+		return ret;						\
+									\
+	ret = -ENODEV;							\
+	mutex_lock(&bfqio_mutex);					\
+	if (bfqio_is_removed(bgrp))					\
+		goto out_unlock;					\
+	ret = 0;							\
+									\
+	spin_lock_irq(&bgrp->lock);					\
+	bgrp->__VAR = (unsigned short)val;				\
+	hlist_for_each_entry(bfqg, &bgrp->group_data, group_node) {	\
+		/*							\
+		 * Setting the ioprio_changed flag of the entity        \
+		 * to 1 with new_##__VAR == ##__VAR would re-set        \
+		 * the value of the weight to its ioprio mapping.       \
+		 * Set the flag only if necessary.			\
+		 */							\
+		if ((unsigned short)val != bfqg->entity.new_##__VAR) {  \
+			bfqg->entity.new_##__VAR = (unsigned short)val; \
+			/*						\
+			 * Make sure that the above new value has been	\
+			 * stored in bfqg->entity.new_##__VAR before	\
+			 * setting the ioprio_changed flag. In fact,	\
+			 * this flag may be read asynchronously (in	\
+			 * critical sections protected by a different	\
+			 * lock than that held here), and finding this	\
+			 * flag set may cause the execution of the code	\
+			 * for updating parameters whose value may	\
+			 * depend also on bfqg->entity.new_##__VAR (in	\
+			 * __bfq_entity_update_weight_prio).		\
+			 * This barrier makes sure that the new value	\
+			 * of bfqg->entity.new_##__VAR is correctly	\
+			 * seen in that code.				\
+			 */						\
+			smp_wmb();                                      \
+			bfqg->entity.ioprio_changed = 1;                \
+		}							\
+	}								\
+	spin_unlock_irq(&bgrp->lock);					\
+									\
+out_unlock:								\
+	mutex_unlock(&bfqio_mutex);					\
+	return ret;							\
+}
+
+STORE_FUNCTION(weight, BFQ_MIN_WEIGHT, BFQ_MAX_WEIGHT);
+STORE_FUNCTION(ioprio, 0, IOPRIO_BE_NR - 1);
+STORE_FUNCTION(ioprio_class, IOPRIO_CLASS_RT, IOPRIO_CLASS_IDLE);
+#undef STORE_FUNCTION
+
+static struct cftype bfqio_files[] = {
+	{
+		.name = "weight",
+		.read_u64 = bfqio_cgroup_weight_read,
+		.write_u64 = bfqio_cgroup_weight_write,
+	},
+	{
+		.name = "ioprio",
+		.read_u64 = bfqio_cgroup_ioprio_read,
+		.write_u64 = bfqio_cgroup_ioprio_write,
+	},
+	{
+		.name = "ioprio_class",
+		.read_u64 = bfqio_cgroup_ioprio_class_read,
+		.write_u64 = bfqio_cgroup_ioprio_class_write,
+	},
+	{ },	/* terminate */
+};
+
+static struct cgroup_subsys_state *bfqio_create(struct cgroup_subsys_state
+						*parent_css)
+{
+	struct bfqio_cgroup *bgrp;
+
+	if (parent_css != NULL) {
+		bgrp = kzalloc(sizeof(*bgrp), GFP_KERNEL);
+		if (bgrp == NULL)
+			return ERR_PTR(-ENOMEM);
+	} else
+		bgrp = &bfqio_root_cgroup;
+
+	spin_lock_init(&bgrp->lock);
+	INIT_HLIST_HEAD(&bgrp->group_data);
+	bgrp->ioprio = BFQ_DEFAULT_GRP_IOPRIO;
+	bgrp->ioprio_class = BFQ_DEFAULT_GRP_CLASS;
+
+	return &bgrp->css;
+}
+
+/*
+ * We cannot support shared io contexts, as we have no means to support
+ * two tasks with the same ioc in two different groups without major rework
+ * of the main bic/bfqq data structures.  By now we allow a task to change
+ * its cgroup only if it's the only owner of its ioc; the drawback of this
+ * behavior is that a group containing a task that forked using CLONE_IO
+ * will not be destroyed until the tasks sharing the ioc die.
+ */
+static int bfqio_can_attach(struct cgroup_subsys_state *css,
+			    struct cgroup_taskset *tset)
+{
+	struct task_struct *task;
+	struct io_context *ioc;
+	int ret = 0;
+
+	cgroup_taskset_for_each(task, tset) {
+		/*
+		 * task_lock() is needed to avoid races with
+		 * exit_io_context()
+		 */
+		task_lock(task);
+		ioc = task->io_context;
+		if (ioc != NULL && atomic_read(&ioc->nr_tasks) > 1)
+			/*
+			 * ioc == NULL means that the task is either too
+			 * young or exiting: if it has still no ioc the
+			 * ioc can't be shared, if the task is exiting the
+			 * attach will fail anyway, no matter what we
+			 * return here.
+			 */
+			ret = -EINVAL;
+		task_unlock(task);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static void bfqio_attach(struct cgroup_subsys_state *css,
+			 struct cgroup_taskset *tset)
+{
+	struct task_struct *task;
+	struct io_context *ioc;
+	struct io_cq *icq;
+
+	/*
+	 * IMPORTANT NOTE: The move of more than one process at a time to a
+	 * new group has not yet been tested.
+	 */
+	cgroup_taskset_for_each(task, tset) {
+		ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
+		if (ioc) {
+			/*
+			 * Handle cgroup change here.
+			 */
+			rcu_read_lock();
+			hlist_for_each_entry_rcu(icq, &ioc->icq_list, ioc_node)
+				if (!strncmp(
+					icq->q->elevator->type->elevator_name,
+					"bfq", ELV_NAME_MAX))
+					bfq_bic_change_cgroup(icq_to_bic(icq),
+							      css);
+			rcu_read_unlock();
+			put_io_context(ioc);
+		}
+	}
+}
+
+static void bfqio_destroy(struct cgroup_subsys_state *css)
+{
+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);
+	struct hlist_node *tmp;
+	struct bfq_group *bfqg;
+
+	/*
+	 * Since we are destroying the cgroup, there are no more tasks
+	 * referencing it, and all the RCU grace periods that may have
+	 * referenced it are ended (as the destruction of the parent
+	 * cgroup is RCU-safe); bgrp->group_data will not be accessed by
+	 * anything else and we don't need any synchronization.
+	 */
+	hlist_for_each_entry_safe(bfqg, tmp, &bgrp->group_data, group_node)
+		bfq_destroy_group(bgrp, bfqg);
+
+	BUG_ON(!hlist_empty(&bgrp->group_data));
+
+	kfree(bgrp);
+}
+
+static int bfqio_css_online(struct cgroup_subsys_state *css)
+{
+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);
+
+	mutex_lock(&bfqio_mutex);
+	bgrp->online = true;
+	mutex_unlock(&bfqio_mutex);
+
+	return 0;
+}
+
+static void bfqio_css_offline(struct cgroup_subsys_state *css)
+{
+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);
+
+	mutex_lock(&bfqio_mutex);
+	bgrp->online = false;
+	mutex_unlock(&bfqio_mutex);
+}
+
+struct cgroup_subsys bfqio_cgrp_subsys = {
+	.css_alloc = bfqio_create,
+	.css_online = bfqio_css_online,
+	.css_offline = bfqio_css_offline,
+	.can_attach = bfqio_can_attach,
+	.attach = bfqio_attach,
+	.css_free = bfqio_destroy,
+	.legacy_cftypes = bfqio_files,
+};
+#else
+static inline void bfq_init_entity(struct bfq_entity *entity,
+				   struct bfq_group *bfqg)
+{
+	entity->weight = entity->new_weight;
+	entity->orig_weight = entity->new_weight;
+	entity->ioprio = entity->new_ioprio;
+	entity->ioprio_class = entity->new_ioprio_class;
+	entity->sched_data = &bfqg->sched_data;
+}
+
+static inline struct bfq_group *
+bfq_bic_update_cgroup(struct bfq_io_cq *bic)
+{
+	struct bfq_data *bfqd = bic_to_bfqd(bic);
+	return bfqd->root_group;
+}
+
+static inline void bfq_bfqq_move(struct bfq_data *bfqd,
+				 struct bfq_queue *bfqq,
+				 struct bfq_entity *entity,
+				 struct bfq_group *bfqg)
+{
+}
+
+static void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
+static inline void bfq_disconnect_groups(struct bfq_data *bfqd)
+{
+	bfq_put_async_queues(bfqd, bfqd->root_group);
+}
+
+static inline void bfq_free_root_group(struct bfq_data *bfqd)
+{
+	kfree(bfqd->root_group);
+}
+
+static struct bfq_group *bfq_alloc_root_group(struct bfq_data *bfqd, int node)
+{
+	struct bfq_group *bfqg;
+	int i;
+
+	bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node);
+	if (bfqg == NULL)
+		return NULL;
+
+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+		bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+
+	return bfqg;
+}
+#endif
diff --git a/block/bfq-ioc.c b/block/bfq-ioc.c
new file mode 100644
index 0000000..7f6b000
--- /dev/null
+++ b/block/bfq-ioc.c
@@ -0,0 +1,36 @@
+/*
+ * BFQ: I/O context handling.
+ *
+ * Based on ideas and code from CFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ *		      Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
+ */
+
+/**
+ * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
+ * @icq: the iocontext queue.
+ */
+static inline struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
+{
+	/* bic->icq is the first member, %NULL will convert to %NULL */
+	return container_of(icq, struct bfq_io_cq, icq);
+}
+
+/**
+ * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
+ * @bfqd: the lookup key.
+ * @ioc: the io_context of the process doing I/O.
+ *
+ * Queue lock must be held.
+ */
+static inline struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
+					       struct io_context *ioc)
+{
+	if (ioc)
+		return icq_to_bic(ioc_lookup_icq(ioc, bfqd->queue));
+	return NULL;
+}
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
new file mode 100644
index 0000000..97ee934
--- /dev/null
+++ b/block/bfq-iosched.c
@@ -0,0 +1,3902 @@
+/*
+ * Budget Fair Queueing (BFQ) disk scheduler.
+ *
+ * Based on ideas and code from CFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ *		      Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ
+ * file.
+ *
+ * BFQ is a proportional-share storage-I/O scheduling algorithm based on
+ * the slice-by-slice service scheme of CFQ. But BFQ assigns budgets,
+ * measured in number of sectors, to processes instead of time slices. The
+ * device is not granted to the in-service process for a given time slice,
+ * but until it has exhausted its assigned budget. This change from the time
+ * to the service domain allows BFQ to distribute the device throughput
+ * among processes as desired, without any distortion due to ZBR, workload
+ * fluctuations or other factors. BFQ uses an ad hoc internal scheduler,
+ * called B-WF2Q+, to schedule processes according to their budgets. More
+ * precisely, BFQ schedules queues associated to processes. Thanks to the
+ * accurate policy of B-WF2Q+, BFQ can afford to assign high budgets to
+ * I/O-bound processes issuing sequential requests (to boost the
+ * throughput), and yet guarantee a low latency to interactive and soft
+ * real-time applications.
+ *
+ * BFQ is described in [1], where also a reference to the initial, more
+ * theoretical paper on BFQ can be found. The interested reader can find
+ * in the latter paper full details on the main algorithm, as well as
+ * formulas of the guarantees and formal proofs of all the properties.
+ * With respect to the version of BFQ presented in these papers, this
+ * implementation adds a few more heuristics, such as the one that
+ * guarantees a low latency to soft real-time applications, and a
+ * hierarchical extension based on H-WF2Q+.
+ *
+ * B-WF2Q+ is based on WF2Q+, that is described in [2], together with
+ * H-WF2Q+, while the augmented tree used to implement B-WF2Q+ with O(log N)
+ * complexity derives from the one introduced with EEVDF in [3].
+ *
+ * [1] P. Valente and M. Andreolini, ``Improving Application Responsiveness
+ *     with the BFQ Disk I/O Scheduler'',
+ *     Proceedings of the 5th Annual International Systems and Storage
+ *     Conference (SYSTOR '12), June 2012.
+ *
+ * http://algogroup.unimo.it/people/paolo/disk_sched/bf1-v1-suite-results.pdf
+ *
+ * [2] Jon C.R. Bennett and H. Zhang, ``Hierarchical Packet Fair Queueing
+ *     Algorithms,'' IEEE/ACM Transactions on Networking, 5(5):675-689,
+ *     Oct 1997.
+ *
+ * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz
+ *
+ * [3] I. Stoica and H. Abdel-Wahab, ``Earliest Eligible Virtual Deadline
+ *     First: A Flexible and Accurate Mechanism for Proportional Share
+ *     Resource Allocation,'' technical report.
+ *
+ * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/cgroup.h>
+#include <linux/elevator.h>
+#include <linux/jiffies.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include "bfq.h"
+#include "blk.h"
+
+/* Max number of dispatches in one round of service. */
+static const int bfq_quantum = 4;
+
+/* Expiration time of sync (0) and async (1) requests, in jiffies. */
+static const int bfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
+
+/* Maximum backwards seek, in KiB. */
+static const int bfq_back_max = 16 * 1024;
+
+/* Penalty of a backwards seek, in number of sectors. */
+static const int bfq_back_penalty = 2;
+
+/* Idling period duration, in jiffies. */
+static int bfq_slice_idle = HZ / 125;
+
+/* Default maximum budget values, in sectors and number of requests. */
+static const int bfq_default_max_budget = 16 * 1024;
+static const int bfq_max_budget_async_rq = 4;
+
+/*
+ * Async to sync throughput distribution is controlled as follows:
+ * when an async request is served, the entity is charged the number
+ * of sectors of the request, multiplied by the factor below
+ */
+static const int bfq_async_charge_factor = 10;
+
+/* Default timeout values, in jiffies, approximating CFQ defaults. */
+static const int bfq_timeout_sync = HZ / 8;
+static int bfq_timeout_async = HZ / 25;
+
+struct kmem_cache *bfq_pool;
+
+/* Below this threshold (in ms), we consider thinktime immediate. */
+#define BFQ_MIN_TT		2
+
+/* hw_tag detection: parallel requests threshold and min samples needed. */
+#define BFQ_HW_QUEUE_THRESHOLD	4
+#define BFQ_HW_QUEUE_SAMPLES	32
+
+#define BFQQ_SEEK_THR	 (sector_t)(8 * 1024)
+#define BFQQ_SEEKY(bfqq) ((bfqq)->seek_mean > BFQQ_SEEK_THR)
+
+/* Min samples used for peak rate estimation (for autotuning). */
+#define BFQ_PEAK_RATE_SAMPLES	32
+
+/* Shift used for peak rate fixed precision calculations. */
+#define BFQ_RATE_SHIFT		16
+
+/*
+ * By default, BFQ computes the duration of the weight raising for
+ * interactive applications automatically, using the following formula:
+ * duration = (R / r) * T, where r is the peak rate of the device, and
+ * R and T are two reference parameters.
+ * In particular, R is the peak rate of the reference device (see below),
+ * and T is a reference time: given the systems that are likely to be
+ * installed on the reference device according to its speed class, T is
+ * about the maximum time needed, under BFQ and while reading two files in
+ * parallel, to load typical large applications on these systems.
+ * In practice, the slower/faster the device at hand is, the more/less it
+ * takes to load applications with respect to the reference device.
+ * Accordingly, the longer/shorter BFQ grants weight raising to interactive
+ * applications.
+ *
+ * BFQ uses four different reference pairs (R, T), depending on:
+ * . whether the device is rotational or non-rotational;
+ * . whether the device is slow, such as old or portable HDDs, as well as
+ *   SD cards, or fast, such as newer HDDs and SSDs.
+ *
+ * The device's speed class is dynamically (re)detected in
+ * bfq_update_peak_rate() every time the estimated peak rate is updated.
+ *
+ * In the following definitions, R_slow[0]/R_fast[0] and T_slow[0]/T_fast[0]
+ * are the reference values for a slow/fast rotational device, whereas
+ * R_slow[1]/R_fast[1] and T_slow[1]/T_fast[1] are the reference values for
+ * a slow/fast non-rotational device. Finally, device_speed_thresh are the
+ * thresholds used to switch between speed classes.
+ * Both the reference peak rates and the thresholds are measured in
+ * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
+ */
+static int R_slow[2] = {1536, 10752};
+static int R_fast[2] = {17415, 34791};
+/*
+ * To improve readability, a conversion function is used to initialize the
+ * following arrays, which entails that they can be initialized only in a
+ * function.
+ */
+static int T_slow[2];
+static int T_fast[2];
+static int device_speed_thresh[2];
+
+#define BFQ_SERVICE_TREE_INIT	((struct bfq_service_tree)		\
+				{ RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })
+
+#define RQ_BIC(rq)		((struct bfq_io_cq *) (rq)->elv.priv[0])
+#define RQ_BFQQ(rq)		((rq)->elv.priv[1])
+
+static inline void bfq_schedule_dispatch(struct bfq_data *bfqd);
+
+#include "bfq-ioc.c"
+#include "bfq-sched.c"
+#include "bfq-cgroup.c"
+
+#define bfq_class_idle(bfqq)	((bfqq)->entity.ioprio_class ==\
+				 IOPRIO_CLASS_IDLE)
+#define bfq_class_rt(bfqq)	((bfqq)->entity.ioprio_class ==\
+				 IOPRIO_CLASS_RT)
+
+#define bfq_sample_valid(samples)	((samples) > 80)
+
+/*
+ * We regard a request as SYNC, if either it's a read or has the SYNC bit
+ * set (in which case it could also be a direct WRITE).
+ */
+static inline int bfq_bio_sync(struct bio *bio)
+{
+	if (bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Scheduler run of queue, if there are requests pending and no one in the
+ * driver that will restart queueing.
+ */
+static inline void bfq_schedule_dispatch(struct bfq_data *bfqd)
+{
+	if (bfqd->queued != 0) {
+		bfq_log(bfqd, "schedule dispatch");
+		kblockd_schedule_work(&bfqd->unplug_work);
+	}
+}
+
+/*
+ * Lifted from AS - choose which of rq1 and rq2 that is best served now.
+ * We choose the request that is closesr to the head right now.  Distance
+ * behind the head is penalized and only allowed to a certain extent.
+ */
+static struct request *bfq_choose_req(struct bfq_data *bfqd,
+				      struct request *rq1,
+				      struct request *rq2,
+				      sector_t last)
+{
+	sector_t s1, s2, d1 = 0, d2 = 0;
+	unsigned long back_max;
+#define BFQ_RQ1_WRAP	0x01 /* request 1 wraps */
+#define BFQ_RQ2_WRAP	0x02 /* request 2 wraps */
+	unsigned wrap = 0; /* bit mask: requests behind the disk head? */
+
+	if (rq1 == NULL || rq1 == rq2)
+		return rq2;
+	if (rq2 == NULL)
+		return rq1;
+
+	if (rq_is_sync(rq1) && !rq_is_sync(rq2))
+		return rq1;
+	else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
+		return rq2;
+	if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
+		return rq1;
+	else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META))
+		return rq2;
+
+	s1 = blk_rq_pos(rq1);
+	s2 = blk_rq_pos(rq2);
+
+	/*
+	 * By definition, 1KiB is 2 sectors.
+	 */
+	back_max = bfqd->bfq_back_max * 2;
+
+	/*
+	 * Strict one way elevator _except_ in the case where we allow
+	 * short backward seeks which are biased as twice the cost of a
+	 * similar forward seek.
+	 */
+	if (s1 >= last)
+		d1 = s1 - last;
+	else if (s1 + back_max >= last)
+		d1 = (last - s1) * bfqd->bfq_back_penalty;
+	else
+		wrap |= BFQ_RQ1_WRAP;
+
+	if (s2 >= last)
+		d2 = s2 - last;
+	else if (s2 + back_max >= last)
+		d2 = (last - s2) * bfqd->bfq_back_penalty;
+	else
+		wrap |= BFQ_RQ2_WRAP;
+
+	/* Found required data */
+
+	/*
+	 * By doing switch() on the bit mask "wrap" we avoid having to
+	 * check two variables for all permutations: --> faster!
+	 */
+	switch (wrap) {
+	case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
+		if (d1 < d2)
+			return rq1;
+		else if (d2 < d1)
+			return rq2;
+		else {
+			if (s1 >= s2)
+				return rq1;
+			else
+				return rq2;
+		}
+
+	case BFQ_RQ2_WRAP:
+		return rq1;
+	case BFQ_RQ1_WRAP:
+		return rq2;
+	case (BFQ_RQ1_WRAP|BFQ_RQ2_WRAP): /* both rqs wrapped */
+	default:
+		/*
+		 * Since both rqs are wrapped,
+		 * start with the one that's further behind head
+		 * (--> only *one* back seek required),
+		 * since back seek takes more time than forward.
+		 */
+		if (s1 <= s2)
+			return rq1;
+		else
+			return rq2;
+	}
+}
+
+static struct bfq_queue *
+bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
+		     sector_t sector, struct rb_node **ret_parent,
+		     struct rb_node ***rb_link)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *bfqq = NULL;
+
+	parent = NULL;
+	p = &root->rb_node;
+	while (*p) {
+		struct rb_node **n;
+
+		parent = *p;
+		bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+
+		/*
+		 * Sort strictly based on sector. Smallest to the left,
+		 * largest to the right.
+		 */
+		if (sector > blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_right;
+		else if (sector < blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_left;
+		else
+			break;
+		p = n;
+		bfqq = NULL;
+	}
+
+	*ret_parent = parent;
+	if (rb_link)
+		*rb_link = p;
+
+	bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
+		(long long unsigned)sector,
+		bfqq != NULL ? bfqq->pid : 0);
+
+	return bfqq;
+}
+
+static void bfq_rq_pos_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *__bfqq;
+
+	if (bfqq->pos_root != NULL) {
+		rb_erase(&bfqq->pos_node, bfqq->pos_root);
+		bfqq->pos_root = NULL;
+	}
+
+	if (bfq_class_idle(bfqq))
+		return;
+	if (!bfqq->next_rq)
+		return;
+
+	bfqq->pos_root = &bfqd->rq_pos_tree;
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
+			blk_rq_pos(bfqq->next_rq), &parent, &p);
+	if (__bfqq == NULL) {
+		rb_link_node(&bfqq->pos_node, parent, p);
+		rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
+	} else
+		bfqq->pos_root = NULL;
+}
+
+/*
+ * Tell whether there are active queues or groups with differentiated weights.
+ */
+static inline bool bfq_differentiated_weights(struct bfq_data *bfqd)
+{
+	BUG_ON(!bfqd->hw_tag);
+	/*
+	 * For weights to differ, at least one of the trees must contain
+	 * at least two nodes.
+	 */
+	return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
+		(bfqd->queue_weights_tree.rb_node->rb_left ||
+		 bfqd->queue_weights_tree.rb_node->rb_right)
+#ifdef CONFIG_CGROUP_BFQIO
+	       ) ||
+	       (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
+		(bfqd->group_weights_tree.rb_node->rb_left ||
+		 bfqd->group_weights_tree.rb_node->rb_right)
+#endif
+	       );
+}
+
+/*
+ * If the weight-counter tree passed as input contains no counter for
+ * the weight of the input entity, then add that counter; otherwise just
+ * increment the existing counter.
+ *
+ * Note that weight-counter trees contain few nodes in mostly symmetric
+ * scenarios. For example, if all queues have the same weight, then the
+ * weight-counter tree for the queues may contain at most one node.
+ * This holds even if low_latency is on, because weight-raised queues
+ * are not inserted in the tree.
+ * In most scenarios, the rate at which nodes are created/destroyed
+ * should be low too.
+ */
+static void bfq_weights_tree_add(struct bfq_data *bfqd,
+				 struct bfq_entity *entity,
+				 struct rb_root *root)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	/*
+	 * Do not insert if:
+	 * - the device does not support queueing;
+	 * - the entity is already associated with a counter, which happens if:
+	 *   1) the entity is associated with a queue, 2) a request arrival
+	 *   has caused the queue to become both non-weight-raised, and hence
+	 *   change its weight, and backlogged; in this respect, each
+	 *   of the two events causes an invocation of this function,
+	 *   3) this is the invocation of this function caused by the second
+	 *   event. This second invocation is actually useless, and we handle
+	 *   this fact by exiting immediately. More efficient or clearer
+	 *   solutions might possibly be adopted.
+	 */
+	if (!bfqd->hw_tag || entity->weight_counter)
+		return;
+
+	while (*new) {
+		struct bfq_weight_counter *__counter = container_of(*new,
+						struct bfq_weight_counter,
+						weights_node);
+		parent = *new;
+
+		if (entity->weight == __counter->weight) {
+			entity->weight_counter = __counter;
+			goto inc_counter;
+		}
+		if (entity->weight < __counter->weight)
+			new = &((*new)->rb_left);
+		else
+			new = &((*new)->rb_right);
+	}
+
+	entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
+					 GFP_ATOMIC);
+	entity->weight_counter->weight = entity->weight;
+	rb_link_node(&entity->weight_counter->weights_node, parent, new);
+	rb_insert_color(&entity->weight_counter->weights_node, root);
+
+inc_counter:
+	entity->weight_counter->num_active++;
+}
+
+/*
+ * Decrement the weight counter associated with the entity, and, if the
+ * counter reaches 0, remove the counter from the tree.
+ * See the comments to the function bfq_weights_tree_add() for considerations
+ * about overhead.
+ */
+static void bfq_weights_tree_remove(struct bfq_data *bfqd,
+				    struct bfq_entity *entity,
+				    struct rb_root *root)
+{
+	/*
+	 * Check whether the entity is actually associated with a counter.
+	 * In fact, the device may not be considered NCQ-capable for a while,
+	 * which implies that no insertion in the weight trees is performed,
+	 * after which the device may start to be deemed NCQ-capable, and hence
+	 * this function may start to be invoked. This may cause the function
+	 * to be invoked for entities that are not associated with any counter.
+	 */
+	if (!entity->weight_counter)
+		return;
+
+	BUG_ON(RB_EMPTY_ROOT(root));
+	BUG_ON(entity->weight_counter->weight != entity->weight);
+
+	BUG_ON(!entity->weight_counter->num_active);
+	entity->weight_counter->num_active--;
+	if (entity->weight_counter->num_active > 0)
+		goto reset_entity_pointer;
+
+	rb_erase(&entity->weight_counter->weights_node, root);
+	kfree(entity->weight_counter);
+
+reset_entity_pointer:
+	entity->weight_counter = NULL;
+}
+
+static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
+					struct bfq_queue *bfqq,
+					struct request *last)
+{
+	struct rb_node *rbnext = rb_next(&last->rb_node);
+	struct rb_node *rbprev = rb_prev(&last->rb_node);
+	struct request *next = NULL, *prev = NULL;
+
+	BUG_ON(RB_EMPTY_NODE(&last->rb_node));
+
+	if (rbprev != NULL)
+		prev = rb_entry_rq(rbprev);
+
+	if (rbnext != NULL)
+		next = rb_entry_rq(rbnext);
+	else {
+		rbnext = rb_first(&bfqq->sort_list);
+		if (rbnext && rbnext != &last->rb_node)
+			next = rb_entry_rq(rbnext);
+	}
+
+	return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
+}
+
+/* see the definition of bfq_async_charge_factor for details */
+static inline unsigned long bfq_serv_to_charge(struct request *rq,
+					       struct bfq_queue *bfqq)
+{
+	return blk_rq_sectors(rq) *
+		(1 + ((!bfq_bfqq_sync(bfqq)) * (bfqq->wr_coeff == 1) *
+		bfq_async_charge_factor));
+}
+
+/**
+ * bfq_updated_next_req - update the queue after a new next_rq selection.
+ * @bfqd: the device data the queue belongs to.
+ * @bfqq: the queue to update.
+ *
+ * If the first request of a queue changes we make sure that the queue
+ * has enough budget to serve at least its first request (if the
+ * request has grown).  We do this because if the queue has not enough
+ * budget for its first request, it has to go through two dispatch
+ * rounds to actually get it dispatched.
+ */
+static void bfq_updated_next_req(struct bfq_data *bfqd,
+				 struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+	struct request *next_rq = bfqq->next_rq;
+	unsigned long new_budget;
+
+	if (next_rq == NULL)
+		return;
+
+	if (bfqq == bfqd->in_service_queue)
+		/*
+		 * In order not to break guarantees, budgets cannot be
+		 * changed after an entity has been selected.
+		 */
+		return;
+
+	BUG_ON(entity->tree != &st->active);
+	BUG_ON(entity == entity->sched_data->in_service_entity);
+
+	new_budget = max_t(unsigned long, bfqq->max_budget,
+			   bfq_serv_to_charge(next_rq, bfqq));
+	if (entity->budget != new_budget) {
+		entity->budget = new_budget;
+		bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
+					 new_budget);
+		bfq_activate_bfqq(bfqd, bfqq);
+	}
+}
+
+static inline unsigned int bfq_wr_duration(struct bfq_data *bfqd)
+{
+	u64 dur;
+
+	if (bfqd->bfq_wr_max_time > 0)
+		return bfqd->bfq_wr_max_time;
+
+	dur = bfqd->RT_prod;
+	do_div(dur, bfqd->peak_rate);
+
+	return dur;
+}
+
+/* Empty burst list and add just bfqq (see comments to bfq_handle_burst) */
+static inline void bfq_reset_burst_list(struct bfq_data *bfqd,
+					struct bfq_queue *bfqq)
+{
+	struct bfq_queue *item;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
+		hlist_del_init(&item->burst_list_node);
+	hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+	bfqd->burst_size = 1;
+}
+
+/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
+static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/* Increment burst size to take into account also bfqq */
+	bfqd->burst_size++;
+
+	if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
+		struct bfq_queue *pos, *bfqq_item;
+		struct hlist_node *n;
+
+		/*
+		 * Enough queues have been activated shortly after each
+		 * other to consider this burst as large.
+		 */
+		bfqd->large_burst = true;
+
+		/*
+		 * We can now mark all queues in the burst list as
+		 * belonging to a large burst.
+		 */
+		hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
+				     burst_list_node)
+		        bfq_mark_bfqq_in_large_burst(bfqq_item);
+		bfq_mark_bfqq_in_large_burst(bfqq);
+
+		/*
+		 * From now on, and until the current burst finishes, any
+		 * new queue being activated shortly after the last queue
+		 * was inserted in the burst can be immediately marked as
+		 * belonging to a large burst. So the burst list is not
+		 * needed any more. Remove it.
+		 */
+		hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
+					  burst_list_node)
+			hlist_del_init(&pos->burst_list_node);
+	} else /* burst not yet large: add bfqq to the burst list */
+		hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+}
+
+/*
+ * If many queues happen to become active shortly after each other, then,
+ * to help the processes associated to these queues get their job done as
+ * soon as possible, it is usually better to not grant either weight-raising
+ * or device idling to these queues. In this comment we describe, firstly,
+ * the reasons why this fact holds, and, secondly, the next function, which
+ * implements the main steps needed to properly mark these queues so that
+ * they can then be treated in a different way.
+ *
+ * As for the terminology, we say that a queue becomes active, i.e.,
+ * switches from idle to backlogged, either when it is created (as a
+ * consequence of the arrival of an I/O request), or, if already existing,
+ * when a new request for the queue arrives while the queue is idle.
+ * Bursts of activations, i.e., activations of different queues occurring
+ * shortly after each other, are typically caused by services or applications
+ * that spawn or reactivate many parallel threads/processes. Examples are
+ * systemd during boot or git grep.
+ *
+ * These services or applications benefit mostly from a high throughput:
+ * the quicker the requests of the activated queues are cumulatively served,
+ * the sooner the target job of these queues gets completed. As a consequence,
+ * weight-raising any of these queues, which also implies idling the device
+ * for it, is almost always counterproductive: in most cases it just lowers
+ * throughput.
+ *
+ * On the other hand, a burst of activations may be also caused by the start
+ * of an application that does not consist in a lot of parallel I/O-bound
+ * threads. In fact, with a complex application, the burst may be just a
+ * consequence of the fact that several processes need to be executed to
+ * start-up the application. To start an application as quickly as possible,
+ * the best thing to do is to privilege the I/O related to the application
+ * with respect to all other I/O. Therefore, the best strategy to start as
+ * quickly as possible an application that causes a burst of activations is
+ * to weight-raise all the queues activated during the burst. This is the
+ * exact opposite of the best strategy for the other type of bursts.
+ *
+ * In the end, to take the best action for each of the two cases, the two
+ * types of bursts need to be distinguished. Fortunately, this seems
+ * relatively easy to do, by looking at the sizes of the bursts. In
+ * particular, we found a threshold such that bursts with a larger size
+ * than that threshold are apparently caused only by services or commands
+ * such as systemd or git grep. For brevity, hereafter we call just 'large'
+ * these bursts. BFQ *does not* weight-raise queues whose activations occur
+ * in a large burst. In addition, for each of these queues BFQ performs or
+ * does not perform idling depending on which choice boosts the throughput
+ * most. The exact choice depends on the device and request pattern at
+ * hand.
+ *
+ * Turning back to the next function, it implements all the steps needed
+ * to detect the occurrence of a large burst and to properly mark all the
+ * queues belonging to it (so that they can then be treated in a different
+ * way). This goal is achieved by maintaining a special "burst list" that
+ * holds, temporarily, the queues that belong to the burst in progress. The
+ * list is then used to mark these queues as belonging to a large burst if
+ * the burst does become large. The main steps are the following.
+ *
+ * . when the very first queue is activated, the queue is inserted into the
+ *   list (as it could be the first queue in a possible burst)
+ *
+ * . if the current burst has not yet become large, and a queue Q that does
+ *   not yet belong to the burst is activated shortly after the last time
+ *   at which a new queue entered the burst list, then the function appends
+ *   Q to the burst list
+ *
+ * . if, as a consequence of the previous step, the burst size reaches
+ *   the large-burst threshold, then
+ *
+ *     . all the queues in the burst list are marked as belonging to a
+ *       large burst
+ *
+ *     . the burst list is deleted; in fact, the burst list already served
+ *       its purpose (keeping temporarily track of the queues in a burst,
+ *       so as to be able to mark them as belonging to a large burst in the
+ *       previous sub-step), and now is not needed any more
+ *
+ *     . the device enters a large-burst mode
+ *
+ * . if a queue Q that does not belong to the burst is activated while
+ *   the device is in large-burst mode and shortly after the last time
+ *   at which a queue either entered the burst list or was marked as
+ *   belonging to the current large burst, then Q is immediately marked
+ *   as belonging to a large burst.
+ *
+ * . if a queue Q that does not belong to the burst is activated a while
+ *   later, i.e., not shortly after, than the last time at which a queue
+ *   either entered the burst list or was marked as belonging to the
+ *   current large burst, then the current burst is deemed as finished and:
+ *
+ *        . the large-burst mode is reset if set
+ *
+ *        . the burst list is emptied
+ *
+ *        . Q is inserted in the burst list, as Q may be the first queue
+ *          in a possible new burst (then the burst list contains just Q
+ *          after this step).
+ */
+static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			     bool idle_for_long_time)
+{
+	/*
+	 * If bfqq happened to be activated in a burst, but has been idle
+	 * for at least as long as an interactive queue, then we assume
+	 * that, in the overall I/O initiated in the burst, the I/O
+	 * associated to bfqq is finished. So bfqq does not need to be
+	 * treated as a queue belonging to a burst anymore. Accordingly,
+	 * we reset bfqq's in_large_burst flag if set, and remove bfqq
+	 * from the burst list if it's there. We do not decrement instead
+	 * burst_size, because the fact that bfqq does not need to belong
+	 * to the burst list any more does not invalidate the fact that
+	 * bfqq may have been activated during the current burst.
+	 */
+	if (idle_for_long_time) {
+		hlist_del_init(&bfqq->burst_list_node);
+		bfq_clear_bfqq_in_large_burst(bfqq);
+	}
+
+	/*
+	 * If bfqq is already in the burst list or is part of a large
+	 * burst, then there is nothing else to do.
+	 */
+	if (!hlist_unhashed(&bfqq->burst_list_node) ||
+	    bfq_bfqq_in_large_burst(bfqq))
+		return;
+
+	/*
+	 * If bfqq's activation happens late enough, then the current
+	 * burst is finished, and related data structures must be reset.
+	 *
+	 * In this respect, consider the special case where bfqq is the very
+	 * first queue being activated. In this case, last_ins_in_burst is
+	 * not yet significant when we get here. But it is easy to verify
+	 * that, whether or not the following condition is true, bfqq will
+	 * end up being inserted into the burst list. In particular the
+	 * list will happen to contain only bfqq. And this is exactly what
+	 * has to happen, as bfqq may be the first queue in a possible
+	 * burst.
+	 */
+	if (time_is_before_jiffies(bfqd->last_ins_in_burst +
+	    bfqd->bfq_burst_interval)) {
+		bfqd->large_burst = false;
+		bfq_reset_burst_list(bfqd, bfqq);
+		return;
+	}
+
+	/*
+	 * If we get here, then bfqq is being activated shortly after the
+	 * last queue. So, if the current burst is also large, we can mark
+	 * bfqq as belonging to this large burst immediately.
+	 */
+	if (bfqd->large_burst) {
+		bfq_mark_bfqq_in_large_burst(bfqq);
+		return;
+	}
+
+	/*
+	 * If we get here, then a large-burst state has not yet been
+	 * reached, but bfqq is being activated shortly after the last
+	 * queue. Then we add bfqq to the burst.
+	 */
+	bfq_add_to_burst(bfqd, bfqq);
+}
+
+static void bfq_add_request(struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_entity *entity = &bfqq->entity;
+	struct bfq_data *bfqd = bfqq->bfqd;
+	struct request *next_rq, *prev;
+	unsigned long old_wr_coeff = bfqq->wr_coeff;
+	bool interactive = false;
+
+	bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
+	bfqq->queued[rq_is_sync(rq)]++;
+	bfqd->queued++;
+
+	elv_rb_add(&bfqq->sort_list, rq);
+
+	/*
+	 * Check if this request is a better next-serve candidate.
+	 */
+	prev = bfqq->next_rq;
+	next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
+	BUG_ON(next_rq == NULL);
+	bfqq->next_rq = next_rq;
+
+	/*
+	 * Adjust priority tree position, if next_rq changes.
+	 */
+	if (prev != bfqq->next_rq)
+		bfq_rq_pos_tree_add(bfqd, bfqq);
+
+	if (!bfq_bfqq_busy(bfqq)) {
+		bool soft_rt,
+		     idle_for_long_time = time_is_before_jiffies(
+						bfqq->budget_timeout +
+						bfqd->bfq_wr_min_idle_time);
+
+		if (bfq_bfqq_sync(bfqq)) {
+			bool already_in_burst =
+			   !hlist_unhashed(&bfqq->burst_list_node) ||
+			   bfq_bfqq_in_large_burst(bfqq);
+			bfq_handle_burst(bfqd, bfqq, idle_for_long_time);
+			/*
+			 * If bfqq was not already in the current burst,
+			 * then, at this point, bfqq either has been
+			 * added to the current burst or has caused the
+			 * current burst to terminate. In particular, in
+			 * the second case, bfqq has become the first
+			 * queue in a possible new burst.
+			 * In both cases last_ins_in_burst needs to be
+			 * moved forward.
+			 */
+			if (!already_in_burst)
+				bfqd->last_ins_in_burst = jiffies;
+		}
+
+		soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+			!bfq_bfqq_in_large_burst(bfqq) &&
+			time_is_before_jiffies(bfqq->soft_rt_next_start);
+		interactive = !bfq_bfqq_in_large_burst(bfqq) &&
+			      idle_for_long_time;
+		entity->budget = max_t(unsigned long, bfqq->max_budget,
+				       bfq_serv_to_charge(next_rq, bfqq));
+
+		if (!bfq_bfqq_IO_bound(bfqq)) {
+			if (time_before(jiffies,
+					RQ_BIC(rq)->ttime.last_end_request +
+					bfqd->bfq_slice_idle)) {
+				bfqq->requests_within_timer++;
+				if (bfqq->requests_within_timer >=
+				    bfqd->bfq_requests_within_timer)
+					bfq_mark_bfqq_IO_bound(bfqq);
+			} else
+				bfqq->requests_within_timer = 0;
+		}
+
+		if (!bfqd->low_latency)
+			goto add_bfqq_busy;
+
+		/*
+		 * If the queue is not being boosted and has been idle
+		 * for enough time, start a weight-raising period
+		 */
+		if (old_wr_coeff == 1 && (interactive || soft_rt)) {
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			if (interactive)
+				bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+			else
+				bfqq->wr_cur_max_time =
+					bfqd->bfq_wr_rt_max_time;
+			bfq_log_bfqq(bfqd, bfqq,
+				     "wrais starting at %lu, rais_max_time %u",
+				     jiffies,
+				     jiffies_to_msecs(bfqq->wr_cur_max_time));
+		} else if (old_wr_coeff > 1) {
+			if (interactive)
+				bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+			else if (bfq_bfqq_in_large_burst(bfqq) ||
+				 (bfqq->wr_cur_max_time ==
+				  bfqd->bfq_wr_rt_max_time &&
+				  !soft_rt)) {
+				bfqq->wr_coeff = 1;
+				bfq_log_bfqq(bfqd, bfqq,
+					"wrais ending at %lu, rais_max_time %u",
+					jiffies,
+					jiffies_to_msecs(bfqq->
+						wr_cur_max_time));
+			} else if (time_before(
+					bfqq->last_wr_start_finish +
+					bfqq->wr_cur_max_time,
+					jiffies +
+					bfqd->bfq_wr_rt_max_time) &&
+				   soft_rt) {
+				/*
+				 *
+				 * The remaining weight-raising time is lower
+				 * than bfqd->bfq_wr_rt_max_time, which
+				 * means that the application is enjoying
+				 * weight raising either because deemed soft-
+				 * rt in the near past, or because deemed
+				 * interactive a long ago. In both cases,
+				 * resetting now the current remaining weight-
+				 * raising time for the application to the
+				 * weight-raising duration for soft rt
+				 * applications would not cause any latency
+				 * increase for the application (as the new
+				 * duration would be higher than the remaining
+				 * time).
+				 *
+				 * In addition, the application is now meeting
+				 * the requirements for being deemed soft rt.
+				 * In the end we can correctly and safely
+				 * (re)charge the weight-raising duration for
+				 * the application with the weight-raising
+				 * duration for soft rt applications.
+				 *
+				 * In particular, doing this recharge now, i.e.,
+				 * before the weight-raising period for the
+				 * application finishes, reduces the probability
+				 * of the following negative scenario:
+				 * 1) the weight of a soft rt application is
+				 *    raised at startup (as for any newly
+				 *    created application),
+				 * 2) since the application is not interactive,
+				 *    at a certain time weight-raising is
+				 *    stopped for the application,
+				 * 3) at that time the application happens to
+				 *    still have pending requests, and hence
+				 *    is destined to not have a chance to be
+				 *    deemed soft rt before these requests are
+				 *    completed (see the comments to the
+				 *    function bfq_bfqq_softrt_next_start()
+				 *    for details on soft rt detection),
+				 * 4) these pending requests experience a high
+				 *    latency because the application is not
+				 *    weight-raised while they are pending.
+				 */
+				bfqq->last_wr_start_finish = jiffies;
+				bfqq->wr_cur_max_time =
+					bfqd->bfq_wr_rt_max_time;
+			}
+		}
+		if (old_wr_coeff != bfqq->wr_coeff)
+			entity->ioprio_changed = 1;
+add_bfqq_busy:
+		bfqq->last_idle_bklogged = jiffies;
+		bfqq->service_from_backlogged = 0;
+		bfq_clear_bfqq_softrt_update(bfqq);
+		bfq_add_bfqq_busy(bfqd, bfqq);
+	} else {
+		if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) &&
+		    time_is_before_jiffies(
+				bfqq->last_wr_start_finish +
+				bfqd->bfq_wr_min_inter_arr_async)) {
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+
+			bfqd->wr_busy_queues++;
+			entity->ioprio_changed = 1;
+			bfq_log_bfqq(bfqd, bfqq,
+			    "non-idle wrais starting at %lu, rais_max_time %u",
+			    jiffies,
+			    jiffies_to_msecs(bfqq->wr_cur_max_time));
+		}
+		if (prev != bfqq->next_rq)
+			bfq_updated_next_req(bfqd, bfqq);
+	}
+
+	if (bfqd->low_latency &&
+		(old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive))
+		bfqq->last_wr_start_finish = jiffies;
+}
+
+static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
+					  struct bio *bio)
+{
+	struct task_struct *tsk = current;
+	struct bfq_io_cq *bic;
+	struct bfq_queue *bfqq;
+
+	bic = bfq_bic_lookup(bfqd, tsk->io_context);
+	if (bic == NULL)
+		return NULL;
+
+	bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
+	if (bfqq != NULL)
+		return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
+
+	return NULL;
+}
+
+static void bfq_activate_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+
+	bfqd->rq_in_driver++;
+	bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
+	bfq_log(bfqd, "activate_request: new bfqd->last_position %llu",
+		(long long unsigned)bfqd->last_position);
+}
+
+static inline void bfq_deactivate_request(struct request_queue *q,
+					  struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+
+	BUG_ON(bfqd->rq_in_driver == 0);
+	bfqd->rq_in_driver--;
+}
+
+static void bfq_remove_request(struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+	const int sync = rq_is_sync(rq);
+
+	if (bfqq->next_rq == rq) {
+		bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
+		bfq_updated_next_req(bfqd, bfqq);
+	}
+
+	list_del_init(&rq->queuelist);
+	BUG_ON(bfqq->queued[sync] == 0);
+	bfqq->queued[sync]--;
+	bfqd->queued--;
+	elv_rb_del(&bfqq->sort_list, rq);
+
+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue)
+			bfq_del_bfqq_busy(bfqd, bfqq, 1);
+		/*
+		 * Remove queue from request-position tree as it is empty.
+		 */
+		if (bfqq->pos_root != NULL) {
+			rb_erase(&bfqq->pos_node, bfqq->pos_root);
+			bfqq->pos_root = NULL;
+		}
+	}
+
+	if (rq->cmd_flags & REQ_META) {
+		BUG_ON(bfqq->meta_pending == 0);
+		bfqq->meta_pending--;
+	}
+}
+
+static int bfq_merge(struct request_queue *q, struct request **req,
+		     struct bio *bio)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct request *__rq;
+
+	__rq = bfq_find_rq_fmerge(bfqd, bio);
+	if (__rq != NULL && elv_rq_merge_ok(__rq, bio)) {
+		*req = __rq;
+		return ELEVATOR_FRONT_MERGE;
+	}
+
+	return ELEVATOR_NO_MERGE;
+}
+
+static void bfq_merged_request(struct request_queue *q, struct request *req,
+			       int type)
+{
+	if (type == ELEVATOR_FRONT_MERGE &&
+	    rb_prev(&req->rb_node) &&
+	    blk_rq_pos(req) <
+	    blk_rq_pos(container_of(rb_prev(&req->rb_node),
+				    struct request, rb_node))) {
+		struct bfq_queue *bfqq = RQ_BFQQ(req);
+		struct bfq_data *bfqd = bfqq->bfqd;
+		struct request *prev, *next_rq;
+
+		/* Reposition request in its sort_list */
+		elv_rb_del(&bfqq->sort_list, req);
+		elv_rb_add(&bfqq->sort_list, req);
+		/* Choose next request to be served for bfqq */
+		prev = bfqq->next_rq;
+		next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
+					 bfqd->last_position);
+		BUG_ON(next_rq == NULL);
+		bfqq->next_rq = next_rq;
+		/*
+		 * If next_rq changes, update both the queue's budget to
+		 * fit the new request and the queue's position in its
+		 * rq_pos_tree.
+		 */
+		if (prev != bfqq->next_rq) {
+			bfq_updated_next_req(bfqd, bfqq);
+			bfq_rq_pos_tree_add(bfqd, bfqq);
+		}
+	}
+}
+
+static void bfq_merged_requests(struct request_queue *q, struct request *rq,
+				struct request *next)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+	/*
+	 * Reposition in fifo if next is older than rq.
+	 */
+	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
+	    time_before(next->fifo_time, rq->fifo_time)) {
+		list_move(&rq->queuelist, &next->queuelist);
+		rq->fifo_time = next->fifo_time;
+	}
+
+	if (bfqq->next_rq == next)
+		bfqq->next_rq = rq;
+
+	bfq_remove_request(next);
+}
+
+/* Must be called with bfqq != NULL */
+static inline void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
+{
+	BUG_ON(bfqq == NULL);
+	if (bfq_bfqq_busy(bfqq))
+		bfqq->bfqd->wr_busy_queues--;
+	bfqq->wr_coeff = 1;
+	bfqq->wr_cur_max_time = 0;
+	/* Trigger a weight change on the next activation of the queue */
+	bfqq->entity.ioprio_changed = 1;
+}
+
+static void bfq_end_wr_async_queues(struct bfq_data *bfqd,
+				    struct bfq_group *bfqg)
+{
+	int i, j;
+
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < IOPRIO_BE_NR; j++)
+			if (bfqg->async_bfqq[i][j] != NULL)
+				bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
+	if (bfqg->async_idle_bfqq != NULL)
+		bfq_bfqq_end_wr(bfqg->async_idle_bfqq);
+}
+
+static void bfq_end_wr(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq;
+
+	spin_lock_irq(bfqd->queue->queue_lock);
+
+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
+		bfq_bfqq_end_wr(bfqq);
+	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
+		bfq_bfqq_end_wr(bfqq);
+	bfq_end_wr_async(bfqd);
+
+	spin_unlock_irq(bfqd->queue->queue_lock);
+}
+
+static int bfq_allow_merge(struct request_queue *q, struct request *rq,
+			   struct bio *bio)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_io_cq *bic;
+	struct bfq_queue *bfqq;
+
+	/*
+	 * Disallow merge of a sync bio into an async request.
+	 */
+	if (bfq_bio_sync(bio) && !rq_is_sync(rq))
+		return 0;
+
+	/*
+	 * Lookup the bfqq that this bio will be queued with. Allow
+	 * merge only if rq is queued there.
+	 * Queue lock is held here.
+	 */
+	bic = bfq_bic_lookup(bfqd, current->io_context);
+	if (bic == NULL)
+		return 0;
+
+	bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
+	return bfqq == RQ_BFQQ(rq);
+}
+
+static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
+				       struct bfq_queue *bfqq)
+{
+	if (bfqq != NULL) {
+		bfq_mark_bfqq_must_alloc(bfqq);
+		bfq_mark_bfqq_budget_new(bfqq);
+		bfq_clear_bfqq_fifo_expire(bfqq);
+
+		bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
+
+		bfq_log_bfqq(bfqd, bfqq,
+			     "set_in_service_queue, cur-budget = %lu",
+			     bfqq->entity.budget);
+	}
+
+	bfqd->in_service_queue = bfqq;
+}
+
+/*
+ * Get and set a new queue for service.
+ */
+static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd,
+						  struct bfq_queue *bfqq)
+{
+	if (!bfqq)
+		bfqq = bfq_get_next_queue(bfqd);
+	else
+		bfq_get_next_queue_forced(bfqd, bfqq);
+
+	__bfq_set_in_service_queue(bfqd, bfqq);
+	return bfqq;
+}
+
+static inline sector_t bfq_dist_from_last(struct bfq_data *bfqd,
+					  struct request *rq)
+{
+	if (blk_rq_pos(rq) >= bfqd->last_position)
+		return blk_rq_pos(rq) - bfqd->last_position;
+	else
+		return bfqd->last_position - blk_rq_pos(rq);
+}
+
+/*
+ * Return true if bfqq has no request pending and rq is close enough to
+ * bfqd->last_position, or if rq is closer to bfqd->last_position than
+ * bfqq->next_rq
+ */
+static inline int bfq_rq_close(struct bfq_data *bfqd, struct request *rq)
+{
+	return bfq_dist_from_last(bfqd, rq) <= BFQQ_SEEK_THR;
+}
+
+static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
+{
+	struct rb_root *root = &bfqd->rq_pos_tree;
+	struct rb_node *parent, *node;
+	struct bfq_queue *__bfqq;
+	sector_t sector = bfqd->last_position;
+
+	if (RB_EMPTY_ROOT(root))
+		return NULL;
+
+	/*
+	 * First, if we find a request starting at the end of the last
+	 * request, choose it.
+	 */
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
+	if (__bfqq != NULL)
+		return __bfqq;
+
+	/*
+	 * If the exact sector wasn't found, the parent of the NULL leaf
+	 * will contain the closest sector (rq_pos_tree sorted by
+	 * next_request position).
+	 */
+	__bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+	if (bfq_rq_close(bfqd, __bfqq->next_rq))
+		return __bfqq;
+
+	if (blk_rq_pos(__bfqq->next_rq) < sector)
+		node = rb_next(&__bfqq->pos_node);
+	else
+		node = rb_prev(&__bfqq->pos_node);
+	if (node == NULL)
+		return NULL;
+
+	__bfqq = rb_entry(node, struct bfq_queue, pos_node);
+	if (bfq_rq_close(bfqd, __bfqq->next_rq))
+		return __bfqq;
+
+	return NULL;
+}
+
+/*
+ * bfqd - obvious
+ * cur_bfqq - passed in so that we don't decide that the current queue
+ *            is closely cooperating with itself.
+ *
+ * We are assuming that cur_bfqq has dispatched at least one request,
+ * and that bfqd->last_position reflects a position on the disk associated
+ * with the I/O issued by cur_bfqq.
+ */
+static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd,
+					      struct bfq_queue *cur_bfqq)
+{
+	struct bfq_queue *bfqq;
+
+	if (bfq_class_idle(cur_bfqq))
+		return NULL;
+	if (!bfq_bfqq_sync(cur_bfqq))
+		return NULL;
+	if (BFQQ_SEEKY(cur_bfqq))
+		return NULL;
+
+	/* If device has only one backlogged bfq_queue, don't search. */
+	if (bfqd->busy_queues == 1)
+		return NULL;
+
+	/*
+	 * We should notice if some of the queues are cooperating, e.g.
+	 * working closely on the same area of the disk. In that case,
+	 * we can group them together and don't waste time idling.
+	 */
+	bfqq = bfqq_close(bfqd);
+	if (bfqq == NULL || bfqq == cur_bfqq)
+		return NULL;
+
+	/*
+	 * Do not merge queues from different bfq_groups.
+	*/
+	if (bfqq->entity.parent != cur_bfqq->entity.parent)
+		return NULL;
+
+	/*
+	 * It only makes sense to merge sync queues.
+	 */
+	if (!bfq_bfqq_sync(bfqq))
+		return NULL;
+	if (BFQQ_SEEKY(bfqq))
+		return NULL;
+
+	/*
+	 * Do not merge queues of different priority classes.
+	 */
+	if (bfq_class_rt(bfqq) != bfq_class_rt(cur_bfqq))
+		return NULL;
+
+	return bfqq;
+}
+
+/*
+ * If enough samples have been computed, return the current max budget
+ * stored in bfqd, which is dynamically updated according to the
+ * estimated disk peak rate; otherwise return the default max budget
+ */
+static inline unsigned long bfq_max_budget(struct bfq_data *bfqd)
+{
+	if (bfqd->budgets_assigned < 194)
+		return bfq_default_max_budget;
+	else
+		return bfqd->bfq_max_budget;
+}
+
+/*
+ * Return min budget, which is a fraction of the current or default
+ * max budget (trying with 1/32)
+ */
+static inline unsigned long bfq_min_budget(struct bfq_data *bfqd)
+{
+	if (bfqd->budgets_assigned < 194)
+		return bfq_default_max_budget / 32;
+	else
+		return bfqd->bfq_max_budget / 32;
+}
+
+static void bfq_arm_slice_timer(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq = bfqd->in_service_queue;
+	struct bfq_io_cq *bic;
+	unsigned long sl;
+
+	BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
+
+	/* Processes have exited, don't wait. */
+	bic = bfqd->in_service_bic;
+	if (bic == NULL || atomic_read(&bic->icq.ioc->active_ref) == 0)
+		return;
+
+	bfq_mark_bfqq_wait_request(bfqq);
+
+	/*
+	 * We don't want to idle for seeks, but we do want to allow
+	 * fair distribution of slice time for a process doing back-to-back
+	 * seeks. So allow a little bit of time for him to submit a new rq.
+	 *
+	 * To prevent processes with (partly) seeky workloads from
+	 * being too ill-treated, grant them a small fraction of the
+	 * assigned budget before reducing the waiting time to
+	 * BFQ_MIN_TT. This happened to help reduce latency.
+	 */
+	sl = bfqd->bfq_slice_idle;
+	/*
+	 * Unless the queue is being weight-raised, grant only minimum idle
+	 * time if the queue either has been seeky for long enough or has
+	 * already proved to be constantly seeky.
+	 */
+	if (bfq_sample_valid(bfqq->seek_samples) &&
+	    ((BFQQ_SEEKY(bfqq) && bfqq->entity.service >
+				  bfq_max_budget(bfqq->bfqd) / 8) ||
+	      bfq_bfqq_constantly_seeky(bfqq)) && bfqq->wr_coeff == 1)
+		sl = min(sl, msecs_to_jiffies(BFQ_MIN_TT));
+	else if (bfqq->wr_coeff > 1)
+		sl = sl * 3;
+	bfqd->last_idling_start = ktime_get();
+	mod_timer(&bfqd->idle_slice_timer, jiffies + sl);
+	bfq_log(bfqd, "arm idle: %u/%u ms",
+		jiffies_to_msecs(sl), jiffies_to_msecs(bfqd->bfq_slice_idle));
+}
+
+/*
+ * Set the maximum time for the in-service queue to consume its
+ * budget. This prevents seeky processes from lowering the disk
+ * throughput (always guaranteed with a time slice scheme as in CFQ).
+ */
+static void bfq_set_budget_timeout(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq = bfqd->in_service_queue;
+	unsigned int timeout_coeff;
+	if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time)
+		timeout_coeff = 1;
+	else
+		timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
+
+	bfqd->last_budget_start = ktime_get();
+
+	bfq_clear_bfqq_budget_new(bfqq);
+	bfqq->budget_timeout = jiffies +
+		bfqd->bfq_timeout[bfq_bfqq_sync(bfqq)] * timeout_coeff;
+
+	bfq_log_bfqq(bfqd, bfqq, "set budget_timeout %u",
+		jiffies_to_msecs(bfqd->bfq_timeout[bfq_bfqq_sync(bfqq)] *
+		timeout_coeff));
+}
+
+/*
+ * Move request from internal lists to the request queue dispatch list.
+ */
+static void bfq_dispatch_insert(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+	/*
+	 * For consistency, the next instruction should have been executed
+	 * after removing the request from the queue and dispatching it.
+	 * We execute instead this instruction before bfq_remove_request()
+	 * (and hence introduce a temporary inconsistency), for efficiency.
+	 * In fact, in a forced_dispatch, this prevents two counters related
+	 * to bfqq->dispatched to risk to be uselessly decremented if bfqq
+	 * is not in service, and then to be incremented again after
+	 * incrementing bfqq->dispatched.
+	 */
+	bfqq->dispatched++;
+	bfq_remove_request(rq);
+	elv_dispatch_sort(q, rq);
+
+	if (bfq_bfqq_sync(bfqq))
+		bfqd->sync_flight++;
+}
+
+/*
+ * Return expired entry, or NULL to just start from scratch in rbtree.
+ */
+static struct request *bfq_check_fifo(struct bfq_queue *bfqq)
+{
+	struct request *rq = NULL;
+
+	if (bfq_bfqq_fifo_expire(bfqq))
+		return NULL;
+
+	bfq_mark_bfqq_fifo_expire(bfqq);
+
+	if (list_empty(&bfqq->fifo))
+		return NULL;
+
+	rq = rq_entry_fifo(bfqq->fifo.next);
+
+	if (time_before(jiffies, rq->fifo_time))
+		return NULL;
+
+	return rq;
+}
+
+/* Must be called with the queue_lock held. */
+static int bfqq_process_refs(struct bfq_queue *bfqq)
+{
+	int process_refs, io_refs;
+
+	io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
+	process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st;
+	BUG_ON(process_refs < 0);
+	return process_refs;
+}
+
+static void bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	int process_refs, new_process_refs;
+	struct bfq_queue *__bfqq;
+
+	/*
+	 * If there are no process references on the new_bfqq, then it is
+	 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
+	 * may have dropped their last reference (not just their last process
+	 * reference).
+	 */
+	if (!bfqq_process_refs(new_bfqq))
+		return;
+
+	/* Avoid a circular list and skip interim queue merges. */
+	while ((__bfqq = new_bfqq->new_bfqq)) {
+		if (__bfqq == bfqq)
+			return;
+		new_bfqq = __bfqq;
+	}
+
+	process_refs = bfqq_process_refs(bfqq);
+	new_process_refs = bfqq_process_refs(new_bfqq);
+	/*
+	 * If the process for the bfqq has gone away, there is no
+	 * sense in merging the queues.
+	 */
+	if (process_refs == 0 || new_process_refs == 0)
+		return;
+
+	/*
+	 * Merge in the direction of the lesser amount of work.
+	 */
+	if (new_process_refs >= process_refs) {
+		bfqq->new_bfqq = new_bfqq;
+		atomic_add(process_refs, &new_bfqq->ref);
+	} else {
+		new_bfqq->new_bfqq = bfqq;
+		atomic_add(new_process_refs, &bfqq->ref);
+	}
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
+		new_bfqq->pid);
+}
+
+static inline unsigned long bfq_bfqq_budget_left(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+	return entity->budget - entity->service;
+}
+
+static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	BUG_ON(bfqq != bfqd->in_service_queue);
+
+	__bfq_bfqd_reset_in_service(bfqd);
+
+	/*
+	 * If this bfqq is shared between multiple processes, check
+	 * to make sure that those processes are still issuing I/Os
+	 * within the mean seek distance. If not, it may be time to
+	 * break the queues apart again.
+	 */
+	if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
+		bfq_mark_bfqq_split_coop(bfqq);
+
+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		/*
+		 * Overloading budget_timeout field to store the time
+		 * at which the queue remains with no backlog; used by
+		 * the weight-raising mechanism.
+		 */
+		bfqq->budget_timeout = jiffies;
+		bfq_del_bfqq_busy(bfqd, bfqq, 1);
+	} else {
+		bfq_activate_bfqq(bfqd, bfqq);
+		/*
+		 * Resort priority tree of potential close cooperators.
+		 */
+		bfq_rq_pos_tree_add(bfqd, bfqq);
+	}
+}
+
+/**
+ * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior.
+ * @bfqd: device data.
+ * @bfqq: queue to update.
+ * @reason: reason for expiration.
+ *
+ * Handle the feedback on @bfqq budget.  See the body for detailed
+ * comments.
+ */
+static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
+				     struct bfq_queue *bfqq,
+				     enum bfqq_expiration reason)
+{
+	struct request *next_rq;
+	unsigned long budget, min_budget;
+
+	budget = bfqq->max_budget;
+	min_budget = bfq_min_budget(bfqd);
+
+	BUG_ON(bfqq != bfqd->in_service_queue);
+
+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %lu, budg left %lu",
+		bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %lu, min budg %lu",
+		budget, bfq_min_budget(bfqd));
+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d",
+		bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue));
+
+	if (bfq_bfqq_sync(bfqq)) {
+		switch (reason) {
+		/*
+		 * Caveat: in all the following cases we trade latency
+		 * for throughput.
+		 */
+		case BFQ_BFQQ_TOO_IDLE:
+			/*
+			 * This is the only case where we may reduce
+			 * the budget: if there is no request of the
+			 * process still waiting for completion, then
+			 * we assume (tentatively) that the timer has
+			 * expired because the batch of requests of
+			 * the process could have been served with a
+			 * smaller budget.  Hence, betting that
+			 * process will behave in the same way when it
+			 * becomes backlogged again, we reduce its
+			 * next budget.  As long as we guess right,
+			 * this budget cut reduces the latency
+			 * experienced by the process.
+			 *
+			 * However, if there are still outstanding
+			 * requests, then the process may have not yet
+			 * issued its next request just because it is
+			 * still waiting for the completion of some of
+			 * the still outstanding ones.  So in this
+			 * subcase we do not reduce its budget, on the
+			 * contrary we increase it to possibly boost
+			 * the throughput, as discussed in the
+			 * comments to the BUDGET_TIMEOUT case.
+			 */
+			if (bfqq->dispatched > 0) /* still outstanding reqs */
+				budget = min(budget * 2, bfqd->bfq_max_budget);
+			else {
+				if (budget > 5 * min_budget)
+					budget -= 4 * min_budget;
+				else
+					budget = min_budget;
+			}
+			break;
+		case BFQ_BFQQ_BUDGET_TIMEOUT:
+			/*
+			 * We double the budget here because: 1) it
+			 * gives the chance to boost the throughput if
+			 * this is not a seeky process (which may have
+			 * bumped into this timeout because of, e.g.,
+			 * ZBR), 2) together with charge_full_budget
+			 * it helps give seeky processes higher
+			 * timestamps, and hence be served less
+			 * frequently.
+			 */
+			budget = min(budget * 2, bfqd->bfq_max_budget);
+			break;
+		case BFQ_BFQQ_BUDGET_EXHAUSTED:
+			/*
+			 * The process still has backlog, and did not
+			 * let either the budget timeout or the disk
+			 * idling timeout expire. Hence it is not
+			 * seeky, has a short thinktime and may be
+			 * happy with a higher budget too. So
+			 * definitely increase the budget of this good
+			 * candidate to boost the disk throughput.
+			 */
+			budget = min(budget * 4, bfqd->bfq_max_budget);
+			break;
+		case BFQ_BFQQ_NO_MORE_REQUESTS:
+		       /*
+			* Leave the budget unchanged.
+			*/
+		default:
+			return;
+		}
+	} else /* async queue */
+	    /* async queues get always the maximum possible budget
+	     * (their ability to dispatch is limited by
+	     * @bfqd->bfq_max_budget_async_rq).
+	     */
+		budget = bfqd->bfq_max_budget;
+
+	bfqq->max_budget = budget;
+
+	if (bfqd->budgets_assigned >= 194 && bfqd->bfq_user_max_budget == 0 &&
+	    bfqq->max_budget > bfqd->bfq_max_budget)
+		bfqq->max_budget = bfqd->bfq_max_budget;
+
+	/*
+	 * Make sure that we have enough budget for the next request.
+	 * Since the finish time of the bfqq must be kept in sync with
+	 * the budget, be sure to call __bfq_bfqq_expire() after the
+	 * update.
+	 */
+	next_rq = bfqq->next_rq;
+	if (next_rq != NULL)
+		bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
+					    bfq_serv_to_charge(next_rq, bfqq));
+	else
+		bfqq->entity.budget = bfqq->max_budget;
+
+	bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %lu",
+			next_rq != NULL ? blk_rq_sectors(next_rq) : 0,
+			bfqq->entity.budget);
+}
+
+static unsigned long bfq_calc_max_budget(u64 peak_rate, u64 timeout)
+{
+	unsigned long max_budget;
+
+	/*
+	 * The max_budget calculated when autotuning is equal to the
+	 * amount of sectors transfered in timeout_sync at the
+	 * estimated peak rate.
+	 */
+	max_budget = (unsigned long)(peak_rate * 1000 *
+				     timeout >> BFQ_RATE_SHIFT);
+
+	return max_budget;
+}
+
+/*
+ * In addition to updating the peak rate, checks whether the process
+ * is "slow", and returns 1 if so. This slow flag is used, in addition
+ * to the budget timeout, to reduce the amount of service provided to
+ * seeky processes, and hence reduce their chances to lower the
+ * throughput. See the code for more details.
+ */
+static int bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+				int compensate, enum bfqq_expiration reason)
+{
+	u64 bw, usecs, expected, timeout;
+	ktime_t delta;
+	int update = 0;
+
+	if (!bfq_bfqq_sync(bfqq) || bfq_bfqq_budget_new(bfqq))
+		return 0;
+
+	if (compensate)
+		delta = bfqd->last_idling_start;
+	else
+		delta = ktime_get();
+	delta = ktime_sub(delta, bfqd->last_budget_start);
+	usecs = ktime_to_us(delta);
+
+	/* Don't trust short/unrealistic values. */
+	if (usecs < 100 || usecs >= LONG_MAX)
+		return 0;
+
+	/*
+	 * Calculate the bandwidth for the last slice.  We use a 64 bit
+	 * value to store the peak rate, in sectors per usec in fixed
+	 * point math.  We do so to have enough precision in the estimate
+	 * and to avoid overflows.
+	 */
+	bw = (u64)bfqq->entity.service << BFQ_RATE_SHIFT;
+	do_div(bw, (unsigned long)usecs);
+
+	timeout = jiffies_to_msecs(bfqd->bfq_timeout[BLK_RW_SYNC]);
+
+	/*
+	 * Use only long (> 20ms) intervals to filter out spikes for
+	 * the peak rate estimation.
+	 */
+	if (usecs > 20000) {
+		if (bw > bfqd->peak_rate ||
+		   (!BFQQ_SEEKY(bfqq) &&
+		    reason == BFQ_BFQQ_BUDGET_TIMEOUT)) {
+			bfq_log(bfqd, "measured bw =%llu", bw);
+			/*
+			 * To smooth oscillations use a low-pass filter with
+			 * alpha=7/8, i.e.,
+			 * new_rate = (7/8) * old_rate + (1/8) * bw
+			 */
+			do_div(bw, 8);
+			if (bw == 0)
+				return 0;
+			bfqd->peak_rate *= 7;
+			do_div(bfqd->peak_rate, 8);
+			bfqd->peak_rate += bw;
+			update = 1;
+			bfq_log(bfqd, "new peak_rate=%llu", bfqd->peak_rate);
+		}
+
+		update |= bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES - 1;
+
+		if (bfqd->peak_rate_samples < BFQ_PEAK_RATE_SAMPLES)
+			bfqd->peak_rate_samples++;
+
+		if (bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES &&
+		    update) {
+			int dev_type = blk_queue_nonrot(bfqd->queue);
+			if (bfqd->bfq_user_max_budget == 0) {
+				bfqd->bfq_max_budget =
+					bfq_calc_max_budget(bfqd->peak_rate,
+							    timeout);
+				bfq_log(bfqd, "new max_budget=%lu",
+					bfqd->bfq_max_budget);
+			}
+			if (bfqd->device_speed == BFQ_BFQD_FAST &&
+			    bfqd->peak_rate < device_speed_thresh[dev_type]) {
+				bfqd->device_speed = BFQ_BFQD_SLOW;
+				bfqd->RT_prod = R_slow[dev_type] *
+						T_slow[dev_type];
+			} else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
+			    bfqd->peak_rate > device_speed_thresh[dev_type]) {
+				bfqd->device_speed = BFQ_BFQD_FAST;
+				bfqd->RT_prod = R_fast[dev_type] *
+						T_fast[dev_type];
+			}
+		}
+	}
+
+	/*
+	 * If the process has been served for a too short time
+	 * interval to let its possible sequential accesses prevail on
+	 * the initial seek time needed to move the disk head on the
+	 * first sector it requested, then give the process a chance
+	 * and for the moment return false.
+	 */
+	if (bfqq->entity.budget <= bfq_max_budget(bfqd) / 8)
+		return 0;
+
+	/*
+	 * A process is considered ``slow'' (i.e., seeky, so that we
+	 * cannot treat it fairly in the service domain, as it would
+	 * slow down too much the other processes) if, when a slice
+	 * ends for whatever reason, it has received service at a
+	 * rate that would not be high enough to complete the budget
+	 * before the budget timeout expiration.
+	 */
+	expected = bw * 1000 * timeout >> BFQ_RATE_SHIFT;
+
+	/*
+	 * Caveat: processes doing IO in the slower disk zones will
+	 * tend to be slow(er) even if not seeky. And the estimated
+	 * peak rate will actually be an average over the disk
+	 * surface. Hence, to not be too harsh with unlucky processes,
+	 * we keep a budget/3 margin of safety before declaring a
+	 * process slow.
+	 */
+	return expected > (4 * bfqq->entity.budget) / 3;
+}
+
+/*
+ * To be deemed as soft real-time, an application must meet two
+ * requirements. First, the application must not require an average
+ * bandwidth higher than the approximate bandwidth required to playback or
+ * record a compressed high-definition video.
+ * The next function is invoked on the completion of the last request of a
+ * batch, to compute the next-start time instant, soft_rt_next_start, such
+ * that, if the next request of the application does not arrive before
+ * soft_rt_next_start, then the above requirement on the bandwidth is met.
+ *
+ * The second requirement is that the request pattern of the application is
+ * isochronous, i.e., that, after issuing a request or a batch of requests,
+ * the application stops issuing new requests until all its pending requests
+ * have been completed. After that, the application may issue a new batch,
+ * and so on.
+ * For this reason the next function is invoked to compute
+ * soft_rt_next_start only for applications that meet this requirement,
+ * whereas soft_rt_next_start is set to infinity for applications that do
+ * not.
+ *
+ * Unfortunately, even a greedy application may happen to behave in an
+ * isochronous way if the CPU load is high. In fact, the application may
+ * stop issuing requests while the CPUs are busy serving other processes,
+ * then restart, then stop again for a while, and so on. In addition, if
+ * the disk achieves a low enough throughput with the request pattern
+ * issued by the application (e.g., because the request pattern is random
+ * and/or the device is slow), then the application may meet the above
+ * bandwidth requirement too. To prevent such a greedy application to be
+ * deemed as soft real-time, a further rule is used in the computation of
+ * soft_rt_next_start: soft_rt_next_start must be higher than the current
+ * time plus the maximum time for which the arrival of a request is waited
+ * for when a sync queue becomes idle, namely bfqd->bfq_slice_idle.
+ * This filters out greedy applications, as the latter issue instead their
+ * next request as soon as possible after the last one has been completed
+ * (in contrast, when a batch of requests is completed, a soft real-time
+ * application spends some time processing data).
+ *
+ * Unfortunately, the last filter may easily generate false positives if
+ * only bfqd->bfq_slice_idle is used as a reference time interval and one
+ * or both the following cases occur:
+ * 1) HZ is so low that the duration of a jiffy is comparable to or higher
+ *    than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with
+ *    HZ=100.
+ * 2) jiffies, instead of increasing at a constant rate, may stop increasing
+ *    for a while, then suddenly 'jump' by several units to recover the lost
+ *    increments. This seems to happen, e.g., inside virtual machines.
+ * To address this issue, we do not use as a reference time interval just
+ * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In
+ * particular we add the minimum number of jiffies for which the filter
+ * seems to be quite precise also in embedded systems and KVM/QEMU virtual
+ * machines.
+ */
+static inline unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
+						       struct bfq_queue *bfqq)
+{
+	return max(bfqq->last_idle_bklogged +
+		   HZ * bfqq->service_from_backlogged /
+		   bfqd->bfq_wr_max_softrt_rate,
+		   jiffies + bfqq->bfqd->bfq_slice_idle + 4);
+}
+
+/*
+ * Return the largest-possible time instant such that, for as long as possible,
+ * the current time will be lower than this time instant according to the macro
+ * time_is_before_jiffies().
+ */
+static inline unsigned long bfq_infinity_from_now(unsigned long now)
+{
+	return now + ULONG_MAX / 2;
+}
+
+/**
+ * bfq_bfqq_expire - expire a queue.
+ * @bfqd: device owning the queue.
+ * @bfqq: the queue to expire.
+ * @compensate: if true, compensate for the time spent idling.
+ * @reason: the reason causing the expiration.
+ *
+ *
+ * If the process associated to the queue is slow (i.e., seeky), or in
+ * case of budget timeout, or, finally, if it is async, we
+ * artificially charge it an entire budget (independently of the
+ * actual service it received). As a consequence, the queue will get
+ * higher timestamps than the correct ones upon reactivation, and
+ * hence it will be rescheduled as if it had received more service
+ * than what it actually received. In the end, this class of processes
+ * will receive less service in proportion to how slowly they consume
+ * their budgets (and hence how seriously they tend to lower the
+ * throughput).
+ *
+ * In contrast, when a queue expires because it has been idling for
+ * too much or because it exhausted its budget, we do not touch the
+ * amount of service it has received. Hence when the queue will be
+ * reactivated and its timestamps updated, the latter will be in sync
+ * with the actual service received by the queue until expiration.
+ *
+ * Charging a full budget to the first type of queues and the exact
+ * service to the others has the effect of using the WF2Q+ policy to
+ * schedule the former on a timeslice basis, without violating the
+ * service domain guarantees of the latter.
+ */
+static void bfq_bfqq_expire(struct bfq_data *bfqd,
+			    struct bfq_queue *bfqq,
+			    int compensate,
+			    enum bfqq_expiration reason)
+{
+	int slow;
+	BUG_ON(bfqq != bfqd->in_service_queue);
+
+	/* Update disk peak rate for autotuning and check whether the
+	 * process is slow (see bfq_update_peak_rate).
+	 */
+	slow = bfq_update_peak_rate(bfqd, bfqq, compensate, reason);
+
+	/*
+	 * As above explained, 'punish' slow (i.e., seeky), timed-out
+	 * and async queues, to favor sequential sync workloads.
+	 *
+	 * Processes doing I/O in the slower disk zones will tend to be
+	 * slow(er) even if not seeky. Hence, since the estimated peak
+	 * rate is actually an average over the disk surface, these
+	 * processes may timeout just for bad luck. To avoid punishing
+	 * them we do not charge a full budget to a process that
+	 * succeeded in consuming at least 2/3 of its budget.
+	 */
+	if (slow || (reason == BFQ_BFQQ_BUDGET_TIMEOUT &&
+		     bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3))
+		bfq_bfqq_charge_full_budget(bfqq);
+
+	bfqq->service_from_backlogged += bfqq->entity.service;
+
+	if (BFQQ_SEEKY(bfqq) && reason == BFQ_BFQQ_BUDGET_TIMEOUT &&
+	    !bfq_bfqq_constantly_seeky(bfqq)) {
+		bfq_mark_bfqq_constantly_seeky(bfqq);
+		if (!blk_queue_nonrot(bfqd->queue))
+			bfqd->const_seeky_busy_in_flight_queues++;
+	}
+
+	if (reason == BFQ_BFQQ_TOO_IDLE &&
+	    bfqq->entity.service <= 2 * bfqq->entity.budget / 10 )
+		bfq_clear_bfqq_IO_bound(bfqq);
+
+	if (bfqd->low_latency && bfqq->wr_coeff == 1)
+		bfqq->last_wr_start_finish = jiffies;
+
+	if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 &&
+	    RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		/*
+		 * If we get here, and there are no outstanding requests,
+		 * then the request pattern is isochronous (see the comments
+		 * to the function bfq_bfqq_softrt_next_start()). Hence we
+		 * can compute soft_rt_next_start. If, instead, the queue
+		 * still has outstanding requests, then we have to wait
+		 * for the completion of all the outstanding requests to
+		 * discover whether the request pattern is actually
+		 * isochronous.
+		 */
+		if (bfqq->dispatched == 0)
+			bfqq->soft_rt_next_start =
+				bfq_bfqq_softrt_next_start(bfqd, bfqq);
+		else {
+			/*
+			 * The application is still waiting for the
+			 * completion of one or more requests:
+			 * prevent it from possibly being incorrectly
+			 * deemed as soft real-time by setting its
+			 * soft_rt_next_start to infinity. In fact,
+			 * without this assignment, the application
+			 * would be incorrectly deemed as soft
+			 * real-time if:
+			 * 1) it issued a new request before the
+			 *    completion of all its in-flight
+			 *    requests, and
+			 * 2) at that time, its soft_rt_next_start
+			 *    happened to be in the past.
+			 */
+			bfqq->soft_rt_next_start =
+				bfq_infinity_from_now(jiffies);
+			/*
+			 * Schedule an update of soft_rt_next_start to when
+			 * the task may be discovered to be isochronous.
+			 */
+			bfq_mark_bfqq_softrt_update(bfqq);
+		}
+	}
+
+	bfq_log_bfqq(bfqd, bfqq,
+		"expire (%d, slow %d, num_disp %d, idle_win %d)", reason,
+		slow, bfqq->dispatched, bfq_bfqq_idle_window(bfqq));
+
+	/*
+	 * Increase, decrease or leave budget unchanged according to
+	 * reason.
+	 */
+	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
+	__bfq_bfqq_expire(bfqd, bfqq);
+}
+
+/*
+ * Budget timeout is not implemented through a dedicated timer, but
+ * just checked on request arrivals and completions, as well as on
+ * idle timer expirations.
+ */
+static int bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
+{
+	if (bfq_bfqq_budget_new(bfqq) ||
+	    time_before(jiffies, bfqq->budget_timeout))
+		return 0;
+	return 1;
+}
+
+/*
+ * If we expire a queue that is waiting for the arrival of a new
+ * request, we may prevent the fictitious timestamp back-shifting that
+ * allows the guarantees of the queue to be preserved (see [1] for
+ * this tricky aspect). Hence we return true only if this condition
+ * does not hold, or if the queue is slow enough to deserve only to be
+ * kicked off for preserving a high throughput.
+*/
+static inline int bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		"may_budget_timeout: wait_request %d left %d timeout %d",
+		bfq_bfqq_wait_request(bfqq),
+			bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3,
+		bfq_bfqq_budget_timeout(bfqq));
+
+	return (!bfq_bfqq_wait_request(bfqq) ||
+		bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3)
+		&&
+		bfq_bfqq_budget_timeout(bfqq);
+}
+
+/*
+ * Device idling is allowed only for the queues for which this function
+ * returns true. For this reason, the return value of this function plays a
+ * critical role for both throughput boosting and service guarantees. The
+ * return value is computed through a logical expression. In this rather
+ * long comment, we try to briefly describe all the details and motivations
+ * behind the components of this logical expression.
+ *
+ * First, the expression is false if bfqq is not sync, or if: bfqq happened
+ * to become active during a large burst of queue activations, and the
+ * pattern of requests bfqq contains boosts the throughput if bfqq is
+ * expired. In fact, queues that became active during a large burst benefit
+ * only from throughput, as discussed in the comments to bfq_handle_burst.
+ * In this respect, expiring bfqq certainly boosts the throughput on NCQ-
+ * capable flash-based devices, whereas, on rotational devices, it boosts
+ * the throughput only if bfqq contains random requests.
+ *
+ * On the opposite end, if (a) bfqq is sync, (b) the above burst-related
+ * condition does not hold, and (c) bfqq is being weight-raised, then the
+ * expression always evaluates to true, as device idling is instrumental
+ * for preserving low-latency guarantees (see [1]). If, instead, conditions
+ * (a) and (b) do hold, but (c) does not, then the expression evaluates to
+ * true only if: (1) bfqq is I/O-bound and has a non-null idle window, and
+ * (2) at least one of the following two conditions holds.
+ * The first condition is that the device is not performing NCQ, because
+ * idling the device most certainly boosts the throughput if this condition
+ * holds and bfqq is I/O-bound and has been granted a non-null idle window.
+ * The second compound condition is made of the logical AND of two components.
+ *
+ * The first component is true only if there is no weight-raised busy
+ * queue. This guarantees that the device is not idled for a sync non-
+ * weight-raised queue when there are busy weight-raised queues. The former
+ * is then expired immediately if empty. Combined with the timestamping
+ * rules of BFQ (see [1] for details), this causes sync non-weight-raised
+ * queues to get a lower number of requests served, and hence to ask for a
+ * lower number of requests from the request pool, before the busy weight-
+ * raised queues get served again.
+ *
+ * This is beneficial for the processes associated with weight-raised
+ * queues, when the request pool is saturated (e.g., in the presence of
+ * write hogs). In fact, if the processes associated with the other queues
+ * ask for requests at a lower rate, then weight-raised processes have a
+ * higher probability to get a request from the pool immediately (or at
+ * least soon) when they need one. Hence they have a higher probability to
+ * actually get a fraction of the disk throughput proportional to their
+ * high weight. This is especially true with NCQ-capable drives, which
+ * enqueue several requests in advance and further reorder internally-
+ * queued requests.
+ *
+ * In the end, mistreating non-weight-raised queues when there are busy
+ * weight-raised queues seems to mitigate starvation problems in the
+ * presence of heavy write workloads and NCQ, and hence to guarantee a
+ * higher application and system responsiveness in these hostile scenarios.
+ *
+ * If the first component of the compound condition is instead true, i.e.,
+ * there is no weight-raised busy queue, then the second component of the
+ * compound condition takes into account service-guarantee and throughput
+ * issues related to NCQ (recall that the compound condition is evaluated
+ * only if the device is detected as supporting NCQ).
+ *
+ * As for service guarantees, allowing the drive to enqueue more than one
+ * request at a time, and hence delegating de facto final scheduling
+ * decisions to the drive's internal scheduler, causes loss of control on
+ * the actual request service order. In this respect, when the drive is
+ * allowed to enqueue more than one request at a time, the service
+ * distribution enforced by the drive's internal scheduler is likely to
+ * coincide with the desired device-throughput distribution only in the
+ * following, perfectly symmetric, scenario:
+ * 1) all active queues have the same weight,
+ * 2) all active groups at the same level in the groups tree have the same
+ *    weight,
+ * 3) all active groups at the same level in the groups tree have the same
+ *    number of children.
+ *
+ * Even in such a scenario, sequential I/O may still receive a preferential
+ * treatment, but this is not likely to be a big issue with flash-based
+ * devices, because of their non-dramatic loss of throughput with random
+ * I/O. Things do differ with HDDs, for which additional care is taken, as
+ * explained after completing the discussion for flash-based devices.
+ *
+ * Unfortunately, keeping the necessary state for evaluating exactly the
+ * above symmetry conditions would be quite complex and time-consuming.
+ * Therefore BFQ evaluates instead the following stronger sub-conditions,
+ * for which it is much easier to maintain the needed state:
+ * 1) all active queues have the same weight,
+ * 2) all active groups have the same weight,
+ * 3) all active groups have at most one active child each.
+ * In particular, the last two conditions are always true if hierarchical
+ * support and the cgroups interface are not enabled, hence no state needs
+ * to be maintained in this case.
+ *
+ * According to the above considerations, the second component of the
+ * compound condition evaluates to true if any of the above symmetry
+ * sub-condition does not hold, or the device is not flash-based. Therefore,
+ * if also the first component is true, then idling is allowed for a sync
+ * queue. These are the only sub-conditions considered if the device is
+ * flash-based, as, for such a device, it is sensible to force idling only
+ * for service-guarantee issues. In fact, as for throughput, idling
+ * NCQ-capable flash-based devices would not boost the throughput even
+ * with sequential I/O; rather it would lower the throughput in proportion
+ * to how fast the device is. In the end, (only) if all the three
+ * sub-conditions hold and the device is flash-based, the compound
+ * condition evaluates to false and therefore no idling is performed.
+ *
+ * As already said, things change with a rotational device, where idling
+ * boosts the throughput with sequential I/O (even with NCQ). Hence, for
+ * such a device the second component of the compound condition evaluates
+ * to true also if the following additional sub-condition does not hold:
+ * the queue is constantly seeky. Unfortunately, this different behavior
+ * with respect to flash-based devices causes an additional asymmetry: if
+ * some sync queues enjoy idling and some other sync queues do not, then
+ * the latter get a low share of the device throughput, simply because the
+ * former get many requests served after being set as in service, whereas
+ * the latter do not. As a consequence, to guarantee the desired throughput
+ * distribution, on HDDs the compound expression evaluates to true (and
+ * hence device idling is performed) also if the following last symmetry
+ * condition does not hold: no other queue is benefiting from idling. Also
+ * this last condition is actually replaced with a simpler-to-maintain and
+ * stronger condition: there is no busy queue which is not constantly seeky
+ * (and hence may also benefit from idling).
+ *
+ * To sum up, when all the required symmetry and throughput-boosting
+ * sub-conditions hold, the second component of the compound condition
+ * evaluates to false, and hence no idling is performed. This helps to
+ * keep the drives' internal queues full on NCQ-capable devices, and hence
+ * to boost the throughput, without causing 'almost' any loss of service
+ * guarantees. The 'almost' follows from the fact that, if the internal
+ * queue of one such device is filled while all the sub-conditions hold,
+ * but at some point in time some sub-condition stops to hold, then it may
+ * become impossible to let requests be served in the new desired order
+ * until all the requests already queued in the device have been served.
+ */
+static inline bool bfq_bfqq_must_not_expire(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+#ifdef CONFIG_CGROUP_BFQIO
+#define symmetric_scenario	  (!bfqd->active_numerous_groups && \
+				   !bfq_differentiated_weights(bfqd))
+#else
+#define symmetric_scenario	  (!bfq_differentiated_weights(bfqd))
+#endif
+#define cond_for_seeky_on_ncq_hdd (bfq_bfqq_constantly_seeky(bfqq) && \
+				   bfqd->busy_in_flight_queues == \
+				   bfqd->const_seeky_busy_in_flight_queues)
+
+#define cond_for_expiring_in_burst	(bfq_bfqq_in_large_burst(bfqq) && \
+					 bfqd->hw_tag && \
+					 (blk_queue_nonrot(bfqd->queue) || \
+					  bfq_bfqq_constantly_seeky(bfqq)))
+
+/*
+ * Condition for expiring a non-weight-raised queue (and hence not idling
+ * the device).
+ */
+#define cond_for_expiring_non_wr  (bfqd->hw_tag && \
+				   (bfqd->wr_busy_queues > 0 || \
+				    (symmetric_scenario && \
+				     (blk_queue_nonrot(bfqd->queue) || \
+				      cond_for_seeky_on_ncq_hdd))))
+
+	return bfq_bfqq_sync(bfqq) &&
+		!cond_for_expiring_in_burst &&
+		(bfqq->wr_coeff > 1 ||
+		 (bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_idle_window(bfqq) &&
+		  !cond_for_expiring_non_wr)
+	);
+}
+
+/*
+ * If the in-service queue is empty but sync, and the function
+ * bfq_bfqq_must_not_expire returns true, then:
+ * 1) the queue must remain in service and cannot be expired, and
+ * 2) the disk must be idled to wait for the possible arrival of a new
+ *    request for the queue.
+ * See the comments to the function bfq_bfqq_must_not_expire for the reasons
+ * why performing device idling is the best choice to boost the throughput
+ * and preserve service guarantees when bfq_bfqq_must_not_expire itself
+ * returns true.
+ */
+static inline bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+
+	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfqd->bfq_slice_idle != 0 &&
+	       bfq_bfqq_must_not_expire(bfqq);
+}
+
+/*
+ * Select a queue for service.  If we have a current queue in service,
+ * check whether to continue servicing it, or retrieve and set a new one.
+ */
+static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq, *new_bfqq = NULL;
+	struct request *next_rq;
+	enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT;
+
+	bfqq = bfqd->in_service_queue;
+	if (bfqq == NULL)
+		goto new_queue;
+
+	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
+
+	/*
+         * If another queue has a request waiting within our mean seek
+         * distance, let it run. The expire code will check for close
+         * cooperators and put the close queue at the front of the
+         * service tree. If possible, merge the expiring queue with the
+         * new bfqq.
+         */
+        new_bfqq = bfq_close_cooperator(bfqd, bfqq);
+        if (new_bfqq != NULL && bfqq->new_bfqq == NULL)
+                bfq_setup_merge(bfqq, new_bfqq);
+
+	if (bfq_may_expire_for_budg_timeout(bfqq) &&
+	    !timer_pending(&bfqd->idle_slice_timer) &&
+	    !bfq_bfqq_must_idle(bfqq))
+		goto expire;
+
+	next_rq = bfqq->next_rq;
+	/*
+	 * If bfqq has requests queued and it has enough budget left to
+	 * serve them, keep the queue, otherwise expire it.
+	 */
+	if (next_rq != NULL) {
+		if (bfq_serv_to_charge(next_rq, bfqq) >
+			bfq_bfqq_budget_left(bfqq)) {
+			reason = BFQ_BFQQ_BUDGET_EXHAUSTED;
+			goto expire;
+		} else {
+			/*
+			 * The idle timer may be pending because we may
+			 * not disable disk idling even when a new request
+			 * arrives.
+			 */
+			if (timer_pending(&bfqd->idle_slice_timer)) {
+				/*
+				 * If we get here: 1) at least a new request
+				 * has arrived but we have not disabled the
+				 * timer because the request was too small,
+				 * 2) then the block layer has unplugged
+				 * the device, causing the dispatch to be
+				 * invoked.
+				 *
+				 * Since the device is unplugged, now the
+				 * requests are probably large enough to
+				 * provide a reasonable throughput.
+				 * So we disable idling.
+				 */
+				bfq_clear_bfqq_wait_request(bfqq);
+				del_timer(&bfqd->idle_slice_timer);
+			}
+			if (new_bfqq == NULL)
+				goto keep_queue;
+			else
+				goto expire;
+		}
+	}
+
+	/*
+	 * No requests pending.  If the in-service queue still has requests
+	 * in flight (possibly waiting for a completion) or is idling for a
+	 * new request, then keep it.
+	 */
+	if (new_bfqq == NULL && (timer_pending(&bfqd->idle_slice_timer) ||
+	    (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq)))) {
+		bfqq = NULL;
+		goto keep_queue;
+	} else if (new_bfqq != NULL && timer_pending(&bfqd->idle_slice_timer)) {
+		/*
+		 * Expiring the queue because there is a close cooperator,
+		 * cancel timer.
+		 */
+		bfq_clear_bfqq_wait_request(bfqq);
+		del_timer(&bfqd->idle_slice_timer);
+	}
+
+	reason = BFQ_BFQQ_NO_MORE_REQUESTS;
+expire:
+	bfq_bfqq_expire(bfqd, bfqq, 0, reason);
+new_queue:
+	bfqq = bfq_set_in_service_queue(bfqd, new_bfqq);
+	bfq_log(bfqd, "select_queue: new queue %d returned",
+		bfqq != NULL ? bfqq->pid : 0);
+keep_queue:
+	return bfqq;
+}
+
+static void bfq_update_wr_data(struct bfq_data *bfqd,
+			       struct bfq_queue *bfqq)
+{
+	if (bfqq->wr_coeff > 1) { /* queue is being boosted */
+		struct bfq_entity *entity = &bfqq->entity;
+
+		bfq_log_bfqq(bfqd, bfqq,
+			"raising period dur %u/%u msec, old coeff %u, w %d(%d)",
+			jiffies_to_msecs(jiffies -
+				bfqq->last_wr_start_finish),
+			jiffies_to_msecs(bfqq->wr_cur_max_time),
+			bfqq->wr_coeff,
+			bfqq->entity.weight, bfqq->entity.orig_weight);
+
+		BUG_ON(bfqq != bfqd->in_service_queue && entity->weight !=
+		       entity->orig_weight * bfqq->wr_coeff);
+		if (entity->ioprio_changed)
+			bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");
+		/*
+		 * If the queue was activated in a burst, or
+		 * too much time has elapsed from the beginning
+		 * of this weight-raising, then end weight raising.
+		 */
+		if (bfq_bfqq_in_large_burst(bfqq) ||
+		    time_is_before_jiffies(bfqq->last_wr_start_finish +
+					   bfqq->wr_cur_max_time)) {
+			bfqq->last_wr_start_finish = jiffies;
+			bfq_log_bfqq(bfqd, bfqq,
+				     "wrais ending at %lu, rais_max_time %u",
+				     bfqq->last_wr_start_finish,
+				     jiffies_to_msecs(bfqq->wr_cur_max_time));
+			bfq_bfqq_end_wr(bfqq);
+			__bfq_entity_update_weight_prio(
+				bfq_entity_service_tree(entity),
+				entity);
+		}
+	}
+}
+
+/*
+ * Dispatch one request from bfqq, moving it to the request queue
+ * dispatch list.
+ */
+static int bfq_dispatch_request(struct bfq_data *bfqd,
+				struct bfq_queue *bfqq)
+{
+	int dispatched = 0;
+	struct request *rq;
+	unsigned long service_to_charge;
+
+	BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
+
+	/* Follow expired path, else get first next available. */
+	rq = bfq_check_fifo(bfqq);
+	if (rq == NULL)
+		rq = bfqq->next_rq;
+	service_to_charge = bfq_serv_to_charge(rq, bfqq);
+
+	if (service_to_charge > bfq_bfqq_budget_left(bfqq)) {
+		/*
+		 * This may happen if the next rq is chosen in fifo order
+		 * instead of sector order. The budget is properly
+		 * dimensioned to be always sufficient to serve the next
+		 * request only if it is chosen in sector order. The reason
+		 * is that it would be quite inefficient and little useful
+		 * to always make sure that the budget is large enough to
+		 * serve even the possible next rq in fifo order.
+		 * In fact, requests are seldom served in fifo order.
+		 *
+		 * Expire the queue for budget exhaustion, and make sure
+		 * that the next act_budget is enough to serve the next
+		 * request, even if it comes from the fifo expired path.
+		 */
+		bfqq->next_rq = rq;
+		/*
+		 * Since this dispatch is failed, make sure that
+		 * a new one will be performed
+		 */
+		if (!bfqd->rq_in_driver)
+			bfq_schedule_dispatch(bfqd);
+		goto expire;
+	}
+
+	/* Finally, insert request into driver dispatch list. */
+	bfq_bfqq_served(bfqq, service_to_charge);
+	bfq_dispatch_insert(bfqd->queue, rq);
+
+	bfq_update_wr_data(bfqd, bfqq);
+
+	bfq_log_bfqq(bfqd, bfqq,
+			"dispatched %u sec req (%llu), budg left %lu",
+			blk_rq_sectors(rq),
+			(long long unsigned)blk_rq_pos(rq),
+			bfq_bfqq_budget_left(bfqq));
+
+	dispatched++;
+
+	if (bfqd->in_service_bic == NULL) {
+		atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount);
+		bfqd->in_service_bic = RQ_BIC(rq);
+	}
+
+	if (bfqd->busy_queues > 1 && ((!bfq_bfqq_sync(bfqq) &&
+	    dispatched >= bfqd->bfq_max_budget_async_rq) ||
+	    bfq_class_idle(bfqq)))
+		goto expire;
+
+	return dispatched;
+
+expire:
+	bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_EXHAUSTED);
+	return dispatched;
+}
+
+static int __bfq_forced_dispatch_bfqq(struct bfq_queue *bfqq)
+{
+	int dispatched = 0;
+
+	while (bfqq->next_rq != NULL) {
+		bfq_dispatch_insert(bfqq->bfqd->queue, bfqq->next_rq);
+		dispatched++;
+	}
+
+	BUG_ON(!list_empty(&bfqq->fifo));
+	return dispatched;
+}
+
+/*
+ * Drain our current requests.
+ * Used for barriers and when switching io schedulers on-the-fly.
+ */
+static int bfq_forced_dispatch(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq, *n;
+	struct bfq_service_tree *st;
+	int dispatched = 0;
+
+	bfqq = bfqd->in_service_queue;
+	if (bfqq != NULL)
+		__bfq_bfqq_expire(bfqd, bfqq);
+
+	/*
+	 * Loop through classes, and be careful to leave the scheduler
+	 * in a consistent state, as feedback mechanisms and vtime
+	 * updates cannot be disabled during the process.
+	 */
+	list_for_each_entry_safe(bfqq, n, &bfqd->active_list, bfqq_list) {
+		st = bfq_entity_service_tree(&bfqq->entity);
+
+		dispatched += __bfq_forced_dispatch_bfqq(bfqq);
+		bfqq->max_budget = bfq_max_budget(bfqd);
+
+		bfq_forget_idle(st);
+	}
+
+	BUG_ON(bfqd->busy_queues != 0);
+
+	return dispatched;
+}
+
+static int bfq_dispatch_requests(struct request_queue *q, int force)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_queue *bfqq;
+	int max_dispatch;
+
+	bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
+	if (bfqd->busy_queues == 0)
+		return 0;
+
+	if (unlikely(force))
+		return bfq_forced_dispatch(bfqd);
+
+	bfqq = bfq_select_queue(bfqd);
+	if (bfqq == NULL)
+		return 0;
+
+	max_dispatch = bfqd->bfq_quantum;
+	if (bfq_class_idle(bfqq))
+		max_dispatch = 1;
+
+	if (!bfq_bfqq_sync(bfqq))
+		max_dispatch = bfqd->bfq_max_budget_async_rq;
+
+	if (bfqq->dispatched >= max_dispatch) {
+		if (bfqd->busy_queues > 1)
+			return 0;
+		if (bfqq->dispatched >= 4 * max_dispatch)
+			return 0;
+	}
+
+	if (bfqd->sync_flight != 0 && !bfq_bfqq_sync(bfqq))
+		return 0;
+
+	bfq_clear_bfqq_wait_request(bfqq);
+	BUG_ON(timer_pending(&bfqd->idle_slice_timer));
+
+	if (!bfq_dispatch_request(bfqd, bfqq))
+		return 0;
+
+	bfq_log_bfqq(bfqd, bfqq, "dispatched one request of %d (max_disp %d)",
+			bfqq->pid, max_dispatch);
+
+	return 1;
+}
+
+/*
+ * Task holds one reference to the queue, dropped when task exits.  Each rq
+ * in-flight on this queue also holds a reference, dropped when rq is freed.
+ *
+ * Queue lock must be held here.
+ */
+static void bfq_put_queue(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+
+	BUG_ON(atomic_read(&bfqq->ref) <= 0);
+
+	bfq_log_bfqq(bfqd, bfqq, "put_queue: %p %d", bfqq,
+		     atomic_read(&bfqq->ref));
+	if (!atomic_dec_and_test(&bfqq->ref))
+		return;
+
+	BUG_ON(rb_first(&bfqq->sort_list) != NULL);
+	BUG_ON(bfqq->allocated[READ] + bfqq->allocated[WRITE] != 0);
+	BUG_ON(bfqq->entity.tree != NULL);
+	BUG_ON(bfq_bfqq_busy(bfqq));
+	BUG_ON(bfqd->in_service_queue == bfqq);
+
+	if (bfq_bfqq_sync(bfqq))
+		/*
+		 * The fact that this queue is being destroyed does not
+		 * invalidate the fact that this queue may have been
+		 * activated during the current burst. As a consequence,
+		 * although the queue does not exist anymore, and hence
+		 * needs to be removed from the burst list if there,
+		 * the burst size has not to be decremented.
+		 */
+		hlist_del_init(&bfqq->burst_list_node);
+
+	bfq_log_bfqq(bfqd, bfqq, "put_queue: %p freed", bfqq);
+
+	kmem_cache_free(bfq_pool, bfqq);
+}
+
+static void bfq_put_cooperator(struct bfq_queue *bfqq)
+{
+	struct bfq_queue *__bfqq, *next;
+
+	/*
+	 * If this queue was scheduled to merge with another queue, be
+	 * sure to drop the reference taken on that queue (and others in
+	 * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
+	 */
+	__bfqq = bfqq->new_bfqq;
+	while (__bfqq) {
+		if (__bfqq == bfqq)
+			break;
+		next = __bfqq->new_bfqq;
+		bfq_put_queue(__bfqq);
+		__bfqq = next;
+	}
+}
+
+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	if (bfqq == bfqd->in_service_queue) {
+		__bfq_bfqq_expire(bfqd, bfqq);
+		bfq_schedule_dispatch(bfqd);
+	}
+
+	bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq,
+		     atomic_read(&bfqq->ref));
+
+	bfq_put_cooperator(bfqq);
+
+	bfq_put_queue(bfqq);
+}
+
+static inline void bfq_init_icq(struct io_cq *icq)
+{
+	struct bfq_io_cq *bic = icq_to_bic(icq);
+
+	bic->ttime.last_end_request = jiffies;
+}
+
+static void bfq_exit_icq(struct io_cq *icq)
+{
+	struct bfq_io_cq *bic = icq_to_bic(icq);
+	struct bfq_data *bfqd = bic_to_bfqd(bic);
+
+	if (bic->bfqq[BLK_RW_ASYNC]) {
+		bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_ASYNC]);
+		bic->bfqq[BLK_RW_ASYNC] = NULL;
+	}
+
+	if (bic->bfqq[BLK_RW_SYNC]) {
+		bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_SYNC]);
+		bic->bfqq[BLK_RW_SYNC] = NULL;
+	}
+}
+
+/*
+ * Update the entity prio values; note that the new values will not
+ * be used until the next (re)activation.
+ */
+static void bfq_init_prio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+{
+	struct task_struct *tsk = current;
+	int ioprio_class;
+
+	if (!bfq_bfqq_prio_changed(bfqq))
+		return;
+
+	ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
+	switch (ioprio_class) {
+	default:
+		dev_err(bfqq->bfqd->queue->backing_dev_info.dev,
+			"bfq: bad prio class %d\n", ioprio_class);
+	case IOPRIO_CLASS_NONE:
+		/*
+		 * No prio set, inherit CPU scheduling settings.
+		 */
+		bfqq->entity.new_ioprio = task_nice_ioprio(tsk);
+		bfqq->entity.new_ioprio_class = task_nice_ioclass(tsk);
+		break;
+	case IOPRIO_CLASS_RT:
+		bfqq->entity.new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+		bfqq->entity.new_ioprio_class = IOPRIO_CLASS_RT;
+		break;
+	case IOPRIO_CLASS_BE:
+		bfqq->entity.new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+		bfqq->entity.new_ioprio_class = IOPRIO_CLASS_BE;
+		break;
+	case IOPRIO_CLASS_IDLE:
+		bfqq->entity.new_ioprio_class = IOPRIO_CLASS_IDLE;
+		bfqq->entity.new_ioprio = 7;
+		bfq_clear_bfqq_idle_window(bfqq);
+		break;
+	}
+
+	if (bfqq->entity.new_ioprio < 0 ||
+	    bfqq->entity.new_ioprio >= IOPRIO_BE_NR) {
+		printk(KERN_CRIT "bfq_init_prio_data: new_ioprio %d\n",
+				 bfqq->entity.new_ioprio);
+		BUG();
+	}
+
+	bfqq->entity.ioprio_changed = 1;
+
+	bfq_clear_bfqq_prio_changed(bfqq);
+}
+
+static void bfq_changed_ioprio(struct bfq_io_cq *bic)
+{
+	struct bfq_data *bfqd;
+	struct bfq_queue *bfqq, *new_bfqq;
+	struct bfq_group *bfqg;
+	unsigned long uninitialized_var(flags);
+	int ioprio = bic->icq.ioc->ioprio;
+
+	bfqd = bfq_get_bfqd_locked(&(bic->icq.q->elevator->elevator_data),
+				   &flags);
+	/*
+	 * This condition may trigger on a newly created bic, be sure to
+	 * drop the lock before returning.
+	 */
+	if (unlikely(bfqd == NULL) || likely(bic->ioprio == ioprio))
+		goto out;
+
+	bfqq = bic->bfqq[BLK_RW_ASYNC];
+	if (bfqq != NULL) {
+		bfqg = container_of(bfqq->entity.sched_data, struct bfq_group,
+				    sched_data);
+		new_bfqq = bfq_get_queue(bfqd, bfqg, BLK_RW_ASYNC, bic,
+					 GFP_ATOMIC);
+		if (new_bfqq != NULL) {
+			bic->bfqq[BLK_RW_ASYNC] = new_bfqq;
+			bfq_log_bfqq(bfqd, bfqq,
+				     "changed_ioprio: bfqq %p %d",
+				     bfqq, atomic_read(&bfqq->ref));
+			bfq_put_queue(bfqq);
+		}
+	}
+
+	bfqq = bic->bfqq[BLK_RW_SYNC];
+	if (bfqq != NULL)
+		bfq_mark_bfqq_prio_changed(bfqq);
+
+	bic->ioprio = ioprio;
+
+out:
+	bfq_put_bfqd_unlock(bfqd, &flags);
+}
+
+static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			  pid_t pid, int is_sync)
+{
+	RB_CLEAR_NODE(&bfqq->entity.rb_node);
+	INIT_LIST_HEAD(&bfqq->fifo);
+	INIT_HLIST_NODE(&bfqq->burst_list_node);
+
+	atomic_set(&bfqq->ref, 0);
+	bfqq->bfqd = bfqd;
+
+	bfq_mark_bfqq_prio_changed(bfqq);
+
+	if (is_sync) {
+		if (!bfq_class_idle(bfqq))
+			bfq_mark_bfqq_idle_window(bfqq);
+		bfq_mark_bfqq_sync(bfqq);
+	}
+	bfq_mark_bfqq_IO_bound(bfqq);
+
+	/* Tentative initial value to trade off between thr and lat */
+	bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
+	bfqq->pid = pid;
+
+	bfqq->wr_coeff = 1;
+	bfqq->last_wr_start_finish = 0;
+	/*
+	 * Set to the value for which bfqq will not be deemed as
+	 * soft rt when it becomes backlogged.
+	 */
+	bfqq->soft_rt_next_start = bfq_infinity_from_now(jiffies);
+}
+
+static struct bfq_queue *bfq_find_alloc_queue(struct bfq_data *bfqd,
+					      struct bfq_group *bfqg,
+					      int is_sync,
+					      struct bfq_io_cq *bic,
+					      gfp_t gfp_mask)
+{
+	struct bfq_queue *bfqq, *new_bfqq = NULL;
+
+retry:
+	/* bic always exists here */
+	bfqq = bic_to_bfqq(bic, is_sync);
+
+	/*
+	 * Always try a new alloc if we fall back to the OOM bfqq
+	 * originally, since it should just be a temporary situation.
+	 */
+	if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) {
+		bfqq = NULL;
+		if (new_bfqq != NULL) {
+			bfqq = new_bfqq;
+			new_bfqq = NULL;
+		} else if (gfp_mask & __GFP_WAIT) {
+			spin_unlock_irq(bfqd->queue->queue_lock);
+			new_bfqq = kmem_cache_alloc_node(bfq_pool,
+					gfp_mask | __GFP_ZERO,
+					bfqd->queue->node);
+			spin_lock_irq(bfqd->queue->queue_lock);
+			if (new_bfqq != NULL)
+				goto retry;
+		} else {
+			bfqq = kmem_cache_alloc_node(bfq_pool,
+					gfp_mask | __GFP_ZERO,
+					bfqd->queue->node);
+		}
+
+		if (bfqq != NULL) {
+			bfq_init_bfqq(bfqd, bfqq, current->pid, is_sync);
+			bfq_init_prio_data(bfqq, bic);
+			bfq_init_entity(&bfqq->entity, bfqg);
+			bfq_log_bfqq(bfqd, bfqq, "allocated");
+		} else {
+			bfqq = &bfqd->oom_bfqq;
+			bfq_log_bfqq(bfqd, bfqq, "using oom bfqq");
+		}
+	}
+
+	if (new_bfqq != NULL)
+		kmem_cache_free(bfq_pool, new_bfqq);
+
+	return bfqq;
+}
+
+static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
+					       struct bfq_group *bfqg,
+					       int ioprio_class, int ioprio)
+{
+	switch (ioprio_class) {
+	case IOPRIO_CLASS_RT:
+		return &bfqg->async_bfqq[0][ioprio];
+	case IOPRIO_CLASS_NONE:
+		ioprio = IOPRIO_NORM;
+		/* fall through */
+	case IOPRIO_CLASS_BE:
+		return &bfqg->async_bfqq[1][ioprio];
+	case IOPRIO_CLASS_IDLE:
+		return &bfqg->async_idle_bfqq;
+	default:
+		BUG();
+	}
+}
+
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+				       struct bfq_group *bfqg, int is_sync,
+				       struct bfq_io_cq *bic, gfp_t gfp_mask)
+{
+	const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+	const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
+	struct bfq_queue **async_bfqq = NULL;
+	struct bfq_queue *bfqq = NULL;
+
+	if (!is_sync) {
+		async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
+						  ioprio);
+		bfqq = *async_bfqq;
+	}
+
+	if (bfqq == NULL)
+		bfqq = bfq_find_alloc_queue(bfqd, bfqg, is_sync, bic, gfp_mask);
+
+	/*
+	 * Pin the queue now that it's allocated, scheduler exit will
+	 * prune it.
+	 */
+	if (!is_sync && *async_bfqq == NULL) {
+		atomic_inc(&bfqq->ref);
+		bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
+			     bfqq, atomic_read(&bfqq->ref));
+		*async_bfqq = bfqq;
+	}
+
+	atomic_inc(&bfqq->ref);
+	bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq,
+		     atomic_read(&bfqq->ref));
+	return bfqq;
+}
+
+static void bfq_update_io_thinktime(struct bfq_data *bfqd,
+				    struct bfq_io_cq *bic)
+{
+	unsigned long elapsed = jiffies - bic->ttime.last_end_request;
+	unsigned long ttime = min(elapsed, 2UL * bfqd->bfq_slice_idle);
+
+	bic->ttime.ttime_samples = (7*bic->ttime.ttime_samples + 256) / 8;
+	bic->ttime.ttime_total = (7*bic->ttime.ttime_total + 256*ttime) / 8;
+	bic->ttime.ttime_mean = (bic->ttime.ttime_total + 128) /
+				bic->ttime.ttime_samples;
+}
+
+static void bfq_update_io_seektime(struct bfq_data *bfqd,
+				   struct bfq_queue *bfqq,
+				   struct request *rq)
+{
+	sector_t sdist;
+	u64 total;
+
+	if (bfqq->last_request_pos < blk_rq_pos(rq))
+		sdist = blk_rq_pos(rq) - bfqq->last_request_pos;
+	else
+		sdist = bfqq->last_request_pos - blk_rq_pos(rq);
+
+	/*
+	 * Don't allow the seek distance to get too large from the
+	 * odd fragment, pagein, etc.
+	 */
+	if (bfqq->seek_samples == 0) /* first request, not really a seek */
+		sdist = 0;
+	else if (bfqq->seek_samples <= 60) /* second & third seek */
+		sdist = min(sdist, (bfqq->seek_mean * 4) + 2*1024*1024);
+	else
+		sdist = min(sdist, (bfqq->seek_mean * 4) + 2*1024*64);
+
+	bfqq->seek_samples = (7*bfqq->seek_samples + 256) / 8;
+	bfqq->seek_total = (7*bfqq->seek_total + (u64)256*sdist) / 8;
+	total = bfqq->seek_total + (bfqq->seek_samples/2);
+	do_div(total, bfqq->seek_samples);
+	bfqq->seek_mean = (sector_t)total;
+
+	bfq_log_bfqq(bfqd, bfqq, "dist=%llu mean=%llu", (u64)sdist,
+			(u64)bfqq->seek_mean);
+}
+
+/*
+ * Disable idle window if the process thinks too long or seeks so much that
+ * it doesn't matter.
+ */
+static void bfq_update_idle_window(struct bfq_data *bfqd,
+				   struct bfq_queue *bfqq,
+				   struct bfq_io_cq *bic)
+{
+	int enable_idle;
+
+	/* Don't idle for async or idle io prio class. */
+	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
+		return;
+
+	enable_idle = bfq_bfqq_idle_window(bfqq);
+
+	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
+	    bfqd->bfq_slice_idle == 0 ||
+		(bfqd->hw_tag && BFQQ_SEEKY(bfqq) &&
+			bfqq->wr_coeff == 1))
+		enable_idle = 0;
+	else if (bfq_sample_valid(bic->ttime.ttime_samples)) {
+		if (bic->ttime.ttime_mean > bfqd->bfq_slice_idle &&
+			bfqq->wr_coeff == 1)
+			enable_idle = 0;
+		else
+			enable_idle = 1;
+	}
+	bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d",
+		enable_idle);
+
+	if (enable_idle)
+		bfq_mark_bfqq_idle_window(bfqq);
+	else
+		bfq_clear_bfqq_idle_window(bfqq);
+}
+
+/*
+ * Called when a new fs request (rq) is added to bfqq.  Check if there's
+ * something we should do about it.
+ */
+static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			    struct request *rq)
+{
+	struct bfq_io_cq *bic = RQ_BIC(rq);
+
+	if (rq->cmd_flags & REQ_META)
+		bfqq->meta_pending++;
+
+	bfq_update_io_thinktime(bfqd, bic);
+	bfq_update_io_seektime(bfqd, bfqq, rq);
+	if (!BFQQ_SEEKY(bfqq) && bfq_bfqq_constantly_seeky(bfqq)) {
+		bfq_clear_bfqq_constantly_seeky(bfqq);
+		if (!blk_queue_nonrot(bfqd->queue)) {
+			BUG_ON(!bfqd->const_seeky_busy_in_flight_queues);
+			bfqd->const_seeky_busy_in_flight_queues--;
+		}
+	}
+	if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
+	    !BFQQ_SEEKY(bfqq))
+		bfq_update_idle_window(bfqd, bfqq, bic);
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "rq_enqueued: idle_window=%d (seeky %d, mean %llu)",
+		     bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq),
+		     (long long unsigned)bfqq->seek_mean);
+
+	bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
+
+	if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
+		int small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
+				blk_rq_sectors(rq) < 32;
+		int budget_timeout = bfq_bfqq_budget_timeout(bfqq);
+
+		/*
+		 * There is just this request queued: if the request
+		 * is small and the queue is not to be expired, then
+		 * just exit.
+		 *
+		 * In this way, if the disk is being idled to wait for
+		 * a new request from the in-service queue, we avoid
+		 * unplugging the device and committing the disk to serve
+		 * just a small request. On the contrary, we wait for
+		 * the block layer to decide when to unplug the device:
+		 * hopefully, new requests will be merged to this one
+		 * quickly, then the device will be unplugged and
+		 * larger requests will be dispatched.
+		 */
+		if (small_req && !budget_timeout)
+			return;
+
+		/*
+		 * A large enough request arrived, or the queue is to
+		 * be expired: in both cases disk idling is to be
+		 * stopped, so clear wait_request flag and reset
+		 * timer.
+		 */
+		bfq_clear_bfqq_wait_request(bfqq);
+		del_timer(&bfqd->idle_slice_timer);
+
+		/*
+		 * The queue is not empty, because a new request just
+		 * arrived. Hence we can safely expire the queue, in
+		 * case of budget timeout, without risking that the
+		 * timestamps of the queue are not updated correctly.
+		 * See [1] for more details.
+		 */
+		if (budget_timeout)
+			bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_TIMEOUT);
+
+		/*
+		 * Let the request rip immediately, or let a new queue be
+		 * selected if bfqq has just been expired.
+		 */
+		__blk_run_queue(bfqd->queue);
+	}
+}
+
+static void bfq_insert_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+	assert_spin_locked(bfqd->queue->queue_lock);
+	bfq_init_prio_data(bfqq, RQ_BIC(rq));
+
+	bfq_add_request(rq);
+
+	rq->fifo_time = jiffies + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
+	list_add_tail(&rq->queuelist, &bfqq->fifo);
+
+	bfq_rq_enqueued(bfqd, bfqq, rq);
+}
+
+static void bfq_update_hw_tag(struct bfq_data *bfqd)
+{
+	bfqd->max_rq_in_driver = max(bfqd->max_rq_in_driver,
+				     bfqd->rq_in_driver);
+
+	if (bfqd->hw_tag == 1)
+		return;
+
+	/*
+	 * This sample is valid if the number of outstanding requests
+	 * is large enough to allow a queueing behavior.  Note that the
+	 * sum is not exact, as it's not taking into account deactivated
+	 * requests.
+	 */
+	if (bfqd->rq_in_driver + bfqd->queued < BFQ_HW_QUEUE_THRESHOLD)
+		return;
+
+	if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES)
+		return;
+
+	bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD;
+	bfqd->max_rq_in_driver = 0;
+	bfqd->hw_tag_samples = 0;
+}
+
+static void bfq_completed_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+	bool sync = bfq_bfqq_sync(bfqq);
+
+	bfq_log_bfqq(bfqd, bfqq, "completed one req with %u sects left (%d)",
+		     blk_rq_sectors(rq), sync);
+
+	bfq_update_hw_tag(bfqd);
+
+	BUG_ON(!bfqd->rq_in_driver);
+	BUG_ON(!bfqq->dispatched);
+	bfqd->rq_in_driver--;
+	bfqq->dispatched--;
+
+	if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
+		bfq_weights_tree_remove(bfqd, &bfqq->entity,
+					&bfqd->queue_weights_tree);
+		if (!blk_queue_nonrot(bfqd->queue)) {
+			BUG_ON(!bfqd->busy_in_flight_queues);
+			bfqd->busy_in_flight_queues--;
+			if (bfq_bfqq_constantly_seeky(bfqq)) {
+				BUG_ON(!bfqd->
+					const_seeky_busy_in_flight_queues);
+				bfqd->const_seeky_busy_in_flight_queues--;
+			}
+		}
+	}
+
+	if (sync) {
+		bfqd->sync_flight--;
+		RQ_BIC(rq)->ttime.last_end_request = jiffies;
+	}
+
+	/*
+	 * If we are waiting to discover whether the request pattern of the
+	 * task associated with the queue is actually isochronous, and
+	 * both requisites for this condition to hold are satisfied, then
+	 * compute soft_rt_next_start (see the comments to the function
+	 * bfq_bfqq_softrt_next_start()).
+	 */
+	if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
+	    RB_EMPTY_ROOT(&bfqq->sort_list))
+		bfqq->soft_rt_next_start =
+			bfq_bfqq_softrt_next_start(bfqd, bfqq);
+
+	/*
+	 * If this is the in-service queue, check if it needs to be expired,
+	 * or if we want to idle in case it has no pending requests.
+	 */
+	if (bfqd->in_service_queue == bfqq) {
+		if (bfq_bfqq_budget_new(bfqq))
+			bfq_set_budget_timeout(bfqd);
+
+		if (bfq_bfqq_must_idle(bfqq)) {
+			bfq_arm_slice_timer(bfqd);
+			goto out;
+		} else if (bfq_may_expire_for_budg_timeout(bfqq))
+			bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_TIMEOUT);
+		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
+			 (bfqq->dispatched == 0 ||
+			  !bfq_bfqq_must_not_expire(bfqq)))
+			bfq_bfqq_expire(bfqd, bfqq, 0,
+					BFQ_BFQQ_NO_MORE_REQUESTS);
+	}
+
+	if (!bfqd->rq_in_driver)
+		bfq_schedule_dispatch(bfqd);
+
+out:
+	return;
+}
+
+static inline int __bfq_may_queue(struct bfq_queue *bfqq)
+{
+	if (bfq_bfqq_wait_request(bfqq) && bfq_bfqq_must_alloc(bfqq)) {
+		bfq_clear_bfqq_must_alloc(bfqq);
+		return ELV_MQUEUE_MUST;
+	}
+
+	return ELV_MQUEUE_MAY;
+}
+
+static int bfq_may_queue(struct request_queue *q, int rw)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct task_struct *tsk = current;
+	struct bfq_io_cq *bic;
+	struct bfq_queue *bfqq;
+
+	/*
+	 * Don't force setup of a queue from here, as a call to may_queue
+	 * does not necessarily imply that a request actually will be
+	 * queued. So just lookup a possibly existing queue, or return
+	 * 'may queue' if that fails.
+	 */
+	bic = bfq_bic_lookup(bfqd, tsk->io_context);
+	if (bic == NULL)
+		return ELV_MQUEUE_MAY;
+
+	bfqq = bic_to_bfqq(bic, rw_is_sync(rw));
+	if (bfqq != NULL) {
+		bfq_init_prio_data(bfqq, bic);
+
+		return __bfq_may_queue(bfqq);
+	}
+
+	return ELV_MQUEUE_MAY;
+}
+
+/*
+ * Queue lock held here.
+ */
+static void bfq_put_request(struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+	if (bfqq != NULL) {
+		const int rw = rq_data_dir(rq);
+
+		BUG_ON(!bfqq->allocated[rw]);
+		bfqq->allocated[rw]--;
+
+		rq->elv.priv[0] = NULL;
+		rq->elv.priv[1] = NULL;
+
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_request %p, %d",
+			     bfqq, atomic_read(&bfqq->ref));
+		bfq_put_queue(bfqq);
+	}
+}
+
+static struct bfq_queue *
+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+		struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
+		(long unsigned)bfqq->new_bfqq->pid);
+	bic_set_bfqq(bic, bfqq->new_bfqq, 1);
+	bfq_mark_bfqq_coop(bfqq->new_bfqq);
+	bfq_put_queue(bfqq);
+	return bic_to_bfqq(bic, 1);
+}
+
+/*
+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
+ * was the last process referring to said bfqq.
+ */
+static struct bfq_queue *
+bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
+	if (bfqq_process_refs(bfqq) == 1) {
+		bfqq->pid = current->pid;
+		bfq_clear_bfqq_coop(bfqq);
+		bfq_clear_bfqq_split_coop(bfqq);
+		return bfqq;
+	}
+
+	bic_set_bfqq(bic, NULL, 1);
+
+	bfq_put_cooperator(bfqq);
+
+	bfq_put_queue(bfqq);
+	return NULL;
+}
+
+/*
+ * Allocate bfq data structures associated with this request.
+ */
+static int bfq_set_request(struct request_queue *q, struct request *rq,
+			   struct bio *bio, gfp_t gfp_mask)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
+	const int rw = rq_data_dir(rq);
+	const int is_sync = rq_is_sync(rq);
+	struct bfq_queue *bfqq;
+	struct bfq_group *bfqg;
+	unsigned long flags;
+
+	might_sleep_if(gfp_mask & __GFP_WAIT);
+
+	bfq_changed_ioprio(bic);
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	if (bic == NULL)
+		goto queue_fail;
+
+	bfqg = bfq_bic_update_cgroup(bic);
+
+new_queue:
+	bfqq = bic_to_bfqq(bic, is_sync);
+	if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) {
+		bfqq = bfq_get_queue(bfqd, bfqg, is_sync, bic, gfp_mask);
+		bic_set_bfqq(bic, bfqq, is_sync);
+	} else {
+		/*
+		 * If the queue was seeky for too long, break it apart.
+		 */
+		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
+			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
+			bfqq = bfq_split_bfqq(bic, bfqq);
+			if (!bfqq)
+				goto new_queue;
+		}
+
+		/*
+		 * Check to see if this queue is scheduled to merge with
+		 * another closely cooperating queue. The merging of queues
+		 * happens here as it must be done in process context.
+		 * The reference on new_bfqq was taken in merge_bfqqs.
+		 */
+		if (bfqq->new_bfqq != NULL)
+			bfqq = bfq_merge_bfqqs(bfqd, bic, bfqq);
+	}
+
+	bfqq->allocated[rw]++;
+	atomic_inc(&bfqq->ref);
+	bfq_log_bfqq(bfqd, bfqq, "set_request: bfqq %p, %d", bfqq,
+		     atomic_read(&bfqq->ref));
+
+	rq->elv.priv[0] = bic;
+	rq->elv.priv[1] = bfqq;
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return 0;
+
+queue_fail:
+	bfq_schedule_dispatch(bfqd);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return 1;
+}
+
+static void bfq_kick_queue(struct work_struct *work)
+{
+	struct bfq_data *bfqd =
+		container_of(work, struct bfq_data, unplug_work);
+	struct request_queue *q = bfqd->queue;
+
+	spin_lock_irq(q->queue_lock);
+	__blk_run_queue(q);
+	spin_unlock_irq(q->queue_lock);
+}
+
+/*
+ * Handler of the expiration of the timer running if the in-service queue
+ * is idling inside its time slice.
+ */
+static void bfq_idle_slice_timer(unsigned long data)
+{
+	struct bfq_data *bfqd = (struct bfq_data *)data;
+	struct bfq_queue *bfqq;
+	unsigned long flags;
+	enum bfqq_expiration reason;
+
+	spin_lock_irqsave(bfqd->queue->queue_lock, flags);
+
+	bfqq = bfqd->in_service_queue;
+	/*
+	 * Theoretical race here: the in-service queue can be NULL or
+	 * different from the queue that was idling if the timer handler
+	 * spins on the queue_lock and a new request arrives for the
+	 * current queue and there is a full dispatch cycle that changes
+	 * the in-service queue.  This can hardly happen, but in the worst
+	 * case we just expire a queue too early.
+	 */
+	if (bfqq != NULL) {
+		bfq_log_bfqq(bfqd, bfqq, "slice_timer expired");
+		if (bfq_bfqq_budget_timeout(bfqq))
+			/*
+			 * Also here the queue can be safely expired
+			 * for budget timeout without wasting
+			 * guarantees
+			 */
+			reason = BFQ_BFQQ_BUDGET_TIMEOUT;
+		else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0)
+			/*
+			 * The queue may not be empty upon timer expiration,
+			 * because we may not disable the timer when the
+			 * first request of the in-service queue arrives
+			 * during disk idling.
+			 */
+			reason = BFQ_BFQQ_TOO_IDLE;
+		else
+			goto schedule_dispatch;
+
+		bfq_bfqq_expire(bfqd, bfqq, 1, reason);
+	}
+
+schedule_dispatch:
+	bfq_schedule_dispatch(bfqd);
+
+	spin_unlock_irqrestore(bfqd->queue->queue_lock, flags);
+}
+
+static void bfq_shutdown_timer_wq(struct bfq_data *bfqd)
+{
+	del_timer_sync(&bfqd->idle_slice_timer);
+	cancel_work_sync(&bfqd->unplug_work);
+}
+
+static inline void __bfq_put_async_bfqq(struct bfq_data *bfqd,
+					struct bfq_queue **bfqq_ptr)
+{
+	struct bfq_group *root_group = bfqd->root_group;
+	struct bfq_queue *bfqq = *bfqq_ptr;
+
+	bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
+	if (bfqq != NULL) {
+		bfq_bfqq_move(bfqd, bfqq, &bfqq->entity, root_group);
+		bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
+			     bfqq, atomic_read(&bfqq->ref));
+		bfq_put_queue(bfqq);
+		*bfqq_ptr = NULL;
+	}
+}
+
+/*
+ * Release all the bfqg references to its async queues.  If we are
+ * deallocating the group these queues may still contain requests, so
+ * we reparent them to the root cgroup (i.e., the only one that will
+ * exist for sure until all the requests on a device are gone).
+ */
+static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
+{
+	int i, j;
+
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < IOPRIO_BE_NR; j++)
+			__bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]);
+
+	__bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
+}
+
+static void bfq_exit_queue(struct elevator_queue *e)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	struct request_queue *q = bfqd->queue;
+	struct bfq_queue *bfqq, *n;
+
+	bfq_shutdown_timer_wq(bfqd);
+
+	spin_lock_irq(q->queue_lock);
+
+	BUG_ON(bfqd->in_service_queue != NULL);
+	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
+		bfq_deactivate_bfqq(bfqd, bfqq, 0);
+
+	bfq_disconnect_groups(bfqd);
+	spin_unlock_irq(q->queue_lock);
+
+	bfq_shutdown_timer_wq(bfqd);
+
+	synchronize_rcu();
+
+	BUG_ON(timer_pending(&bfqd->idle_slice_timer));
+
+	bfq_free_root_group(bfqd);
+	kfree(bfqd);
+}
+
+static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
+{
+	struct bfq_group *bfqg;
+	struct bfq_data *bfqd;
+	struct elevator_queue *eq;
+
+	eq = elevator_alloc(q, e);
+	if (eq == NULL)
+		return -ENOMEM;
+
+	bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
+	if (bfqd == NULL) {
+		kobject_put(&eq->kobj);
+		return -ENOMEM;
+	}
+	eq->elevator_data = bfqd;
+
+	/*
+	 * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
+	 * Grab a permanent reference to it, so that the normal code flow
+	 * will not attempt to free it.
+	 */
+	bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, 1, 0);
+	atomic_inc(&bfqd->oom_bfqq.ref);
+	bfqd->oom_bfqq.entity.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO;
+	bfqd->oom_bfqq.entity.new_ioprio_class = IOPRIO_CLASS_BE;
+	/*
+	 * Trigger weight initialization, according to ioprio, at the
+	 * oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio
+	 * class won't be changed any more.
+	 */
+	bfqd->oom_bfqq.entity.ioprio_changed = 1;
+
+	bfqd->queue = q;
+
+	spin_lock_irq(q->queue_lock);
+	q->elevator = eq;
+	spin_unlock_irq(q->queue_lock);
+
+	bfqg = bfq_alloc_root_group(bfqd, q->node);
+	if (bfqg == NULL) {
+		kfree(bfqd);
+		kobject_put(&eq->kobj);
+		return -ENOMEM;
+	}
+
+	bfqd->root_group = bfqg;
+	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
+#ifdef CONFIG_CGROUP_BFQIO
+	bfqd->active_numerous_groups = 0;
+#endif
+
+	init_timer(&bfqd->idle_slice_timer);
+	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
+	bfqd->idle_slice_timer.data = (unsigned long)bfqd;
+
+	bfqd->rq_pos_tree = RB_ROOT;
+	bfqd->queue_weights_tree = RB_ROOT;
+	bfqd->group_weights_tree = RB_ROOT;
+
+	INIT_WORK(&bfqd->unplug_work, bfq_kick_queue);
+
+	INIT_LIST_HEAD(&bfqd->active_list);
+	INIT_LIST_HEAD(&bfqd->idle_list);
+	INIT_HLIST_HEAD(&bfqd->burst_list);
+
+	bfqd->hw_tag = -1;
+
+	bfqd->bfq_max_budget = bfq_default_max_budget;
+
+	bfqd->bfq_quantum = bfq_quantum;
+	bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0];
+	bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1];
+	bfqd->bfq_back_max = bfq_back_max;
+	bfqd->bfq_back_penalty = bfq_back_penalty;
+	bfqd->bfq_slice_idle = bfq_slice_idle;
+	bfqd->bfq_class_idle_last_service = 0;
+	bfqd->bfq_max_budget_async_rq = bfq_max_budget_async_rq;
+	bfqd->bfq_timeout[BLK_RW_ASYNC] = bfq_timeout_async;
+	bfqd->bfq_timeout[BLK_RW_SYNC] = bfq_timeout_sync;
+
+	bfqd->bfq_coop_thresh = 2;
+	bfqd->bfq_failed_cooperations = 7000;
+	bfqd->bfq_requests_within_timer = 120;
+
+	bfqd->bfq_large_burst_thresh = 11;
+	bfqd->bfq_burst_interval = msecs_to_jiffies(500);
+
+	bfqd->low_latency = true;
+
+	bfqd->bfq_wr_coeff = 20;
+	bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300);
+	bfqd->bfq_wr_max_time = 0;
+	bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000);
+	bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500);
+	bfqd->bfq_wr_max_softrt_rate = 7000; /*
+					      * Approximate rate required
+					      * to playback or record a
+					      * high-definition compressed
+					      * video.
+					      */
+	bfqd->wr_busy_queues = 0;
+	bfqd->busy_in_flight_queues = 0;
+	bfqd->const_seeky_busy_in_flight_queues = 0;
+
+	/*
+	 * Begin by assuming, optimistically, that the device peak rate is
+	 * equal to the highest reference rate.
+	 */
+	bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
+			T_fast[blk_queue_nonrot(bfqd->queue)];
+	bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)];
+	bfqd->device_speed = BFQ_BFQD_FAST;
+
+	return 0;
+}
+
+static void bfq_slab_kill(void)
+{
+	if (bfq_pool != NULL)
+		kmem_cache_destroy(bfq_pool);
+}
+
+static int __init bfq_slab_setup(void)
+{
+	bfq_pool = KMEM_CACHE(bfq_queue, 0);
+	if (bfq_pool == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+static ssize_t bfq_var_show(unsigned int var, char *page)
+{
+	return sprintf(page, "%d\n", var);
+}
+
+static ssize_t bfq_var_store(unsigned long *var, const char *page,
+			     size_t count)
+{
+	unsigned long new_val;
+	int ret = kstrtoul(page, 10, &new_val);
+
+	if (ret == 0)
+		*var = new_val;
+
+	return count;
+}
+
+static ssize_t bfq_wr_max_time_show(struct elevator_queue *e, char *page)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	return sprintf(page, "%d\n", bfqd->bfq_wr_max_time > 0 ?
+		       jiffies_to_msecs(bfqd->bfq_wr_max_time) :
+		       jiffies_to_msecs(bfq_wr_duration(bfqd)));
+}
+
+static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
+{
+	struct bfq_queue *bfqq;
+	struct bfq_data *bfqd = e->elevator_data;
+	ssize_t num_char = 0;
+
+	num_char += sprintf(page + num_char, "Tot reqs queued %d\n\n",
+			    bfqd->queued);
+
+	spin_lock_irq(bfqd->queue->queue_lock);
+
+	num_char += sprintf(page + num_char, "Active:\n");
+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) {
+	  num_char += sprintf(page + num_char,
+			      "pid%d: weight %hu, nr_queued %d %d, dur %d/%u\n",
+			      bfqq->pid,
+			      bfqq->entity.weight,
+			      bfqq->queued[0],
+			      bfqq->queued[1],
+			jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
+			jiffies_to_msecs(bfqq->wr_cur_max_time));
+	}
+
+	num_char += sprintf(page + num_char, "Idle:\n");
+	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) {
+			num_char += sprintf(page + num_char,
+				"pid%d: weight %hu, dur %d/%u\n",
+				bfqq->pid,
+				bfqq->entity.weight,
+				jiffies_to_msecs(jiffies -
+					bfqq->last_wr_start_finish),
+				jiffies_to_msecs(bfqq->wr_cur_max_time));
+	}
+
+	spin_unlock_irq(bfqd->queue->queue_lock);
+
+	return num_char;
+}
+
+#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	unsigned int __data = __VAR;					\
+	if (__CONV)							\
+		__data = jiffies_to_msecs(__data);			\
+	return bfq_var_show(__data, (page));				\
+}
+SHOW_FUNCTION(bfq_quantum_show, bfqd->bfq_quantum, 0);
+SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 1);
+SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 1);
+SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0);
+SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0);
+SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 1);
+SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
+SHOW_FUNCTION(bfq_max_budget_async_rq_show,
+	      bfqd->bfq_max_budget_async_rq, 0);
+SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout[BLK_RW_SYNC], 1);
+SHOW_FUNCTION(bfq_timeout_async_show, bfqd->bfq_timeout[BLK_RW_ASYNC], 1);
+SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
+SHOW_FUNCTION(bfq_wr_coeff_show, bfqd->bfq_wr_coeff, 0);
+SHOW_FUNCTION(bfq_wr_rt_max_time_show, bfqd->bfq_wr_rt_max_time, 1);
+SHOW_FUNCTION(bfq_wr_min_idle_time_show, bfqd->bfq_wr_min_idle_time, 1);
+SHOW_FUNCTION(bfq_wr_min_inter_arr_async_show, bfqd->bfq_wr_min_inter_arr_async,
+	1);
+SHOW_FUNCTION(bfq_wr_max_softrt_rate_show, bfqd->bfq_wr_max_softrt_rate, 0);
+#undef SHOW_FUNCTION
+
+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
+static ssize_t								\
+__FUNC(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	unsigned long uninitialized_var(__data);			\
+	int ret = bfq_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	if (__CONV)							\
+		*(__PTR) = msecs_to_jiffies(__data);			\
+	else								\
+		*(__PTR) = __data;					\
+	return ret;							\
+}
+STORE_FUNCTION(bfq_quantum_store, &bfqd->bfq_quantum, 1, INT_MAX, 0);
+STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
+		INT_MAX, 1);
+STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
+		INT_MAX, 1);
+STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0);
+STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
+		INT_MAX, 0);
+STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_max_budget_async_rq_store, &bfqd->bfq_max_budget_async_rq,
+		1, INT_MAX, 0);
+STORE_FUNCTION(bfq_timeout_async_store, &bfqd->bfq_timeout[BLK_RW_ASYNC], 0,
+		INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_coeff_store, &bfqd->bfq_wr_coeff, 1, INT_MAX, 0);
+STORE_FUNCTION(bfq_wr_max_time_store, &bfqd->bfq_wr_max_time, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_rt_max_time_store, &bfqd->bfq_wr_rt_max_time, 0, INT_MAX,
+		1);
+STORE_FUNCTION(bfq_wr_min_idle_time_store, &bfqd->bfq_wr_min_idle_time, 0,
+		INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_min_inter_arr_async_store,
+		&bfqd->bfq_wr_min_inter_arr_async, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_max_softrt_rate_store, &bfqd->bfq_wr_max_softrt_rate, 0,
+		INT_MAX, 0);
+#undef STORE_FUNCTION
+
+/* do nothing for the moment */
+static ssize_t bfq_weights_store(struct elevator_queue *e,
+				    const char *page, size_t count)
+{
+	return count;
+}
+
+static inline unsigned long bfq_estimated_max_budget(struct bfq_data *bfqd)
+{
+	u64 timeout = jiffies_to_msecs(bfqd->bfq_timeout[BLK_RW_SYNC]);
+
+	if (bfqd->peak_rate_samples >= BFQ_PEAK_RATE_SAMPLES)
+		return bfq_calc_max_budget(bfqd->peak_rate, timeout);
+	else
+		return bfq_default_max_budget;
+}
+
+static ssize_t bfq_max_budget_store(struct elevator_queue *e,
+				    const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data == 0)
+		bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd);
+	else {
+		if (__data > INT_MAX)
+			__data = INT_MAX;
+		bfqd->bfq_max_budget = __data;
+	}
+
+	bfqd->bfq_user_max_budget = __data;
+
+	return ret;
+}
+
+static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
+				      const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data < 1)
+		__data = 1;
+	else if (__data > INT_MAX)
+		__data = INT_MAX;
+
+	bfqd->bfq_timeout[BLK_RW_SYNC] = msecs_to_jiffies(__data);
+	if (bfqd->bfq_user_max_budget == 0)
+		bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd);
+
+	return ret;
+}
+
+static ssize_t bfq_low_latency_store(struct elevator_queue *e,
+				     const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data > 1)
+		__data = 1;
+	if (__data == 0 && bfqd->low_latency != 0)
+		bfq_end_wr(bfqd);
+	bfqd->low_latency = __data;
+
+	return ret;
+}
+
+#define BFQ_ATTR(name) \
+	__ATTR(name, S_IRUGO|S_IWUSR, bfq_##name##_show, bfq_##name##_store)
+
+static struct elv_fs_entry bfq_attrs[] = {
+	BFQ_ATTR(quantum),
+	BFQ_ATTR(fifo_expire_sync),
+	BFQ_ATTR(fifo_expire_async),
+	BFQ_ATTR(back_seek_max),
+	BFQ_ATTR(back_seek_penalty),
+	BFQ_ATTR(slice_idle),
+	BFQ_ATTR(max_budget),
+	BFQ_ATTR(max_budget_async_rq),
+	BFQ_ATTR(timeout_sync),
+	BFQ_ATTR(timeout_async),
+	BFQ_ATTR(low_latency),
+	BFQ_ATTR(wr_coeff),
+	BFQ_ATTR(wr_max_time),
+	BFQ_ATTR(wr_rt_max_time),
+	BFQ_ATTR(wr_min_idle_time),
+	BFQ_ATTR(wr_min_inter_arr_async),
+	BFQ_ATTR(wr_max_softrt_rate),
+	BFQ_ATTR(weights),
+	__ATTR_NULL
+};
+
+static struct elevator_type iosched_bfq = {
+	.ops = {
+		.elevator_merge_fn =		bfq_merge,
+		.elevator_merged_fn =		bfq_merged_request,
+		.elevator_merge_req_fn =	bfq_merged_requests,
+		.elevator_allow_merge_fn =	bfq_allow_merge,
+		.elevator_dispatch_fn =		bfq_dispatch_requests,
+		.elevator_add_req_fn =		bfq_insert_request,
+		.elevator_activate_req_fn =	bfq_activate_request,
+		.elevator_deactivate_req_fn =	bfq_deactivate_request,
+		.elevator_completed_req_fn =	bfq_completed_request,
+		.elevator_former_req_fn =	elv_rb_former_request,
+		.elevator_latter_req_fn =	elv_rb_latter_request,
+		.elevator_init_icq_fn =		bfq_init_icq,
+		.elevator_exit_icq_fn =		bfq_exit_icq,
+		.elevator_set_req_fn =		bfq_set_request,
+		.elevator_put_req_fn =		bfq_put_request,
+		.elevator_may_queue_fn =	bfq_may_queue,
+		.elevator_init_fn =		bfq_init_queue,
+		.elevator_exit_fn =		bfq_exit_queue,
+	},
+	.icq_size =		sizeof(struct bfq_io_cq),
+	.icq_align =		__alignof__(struct bfq_io_cq),
+	.elevator_attrs =	bfq_attrs,
+	.elevator_name =	"bfq",
+	.elevator_owner =	THIS_MODULE,
+};
+
+static int __init bfq_init(void)
+{
+	/*
+	 * Can be 0 on HZ < 1000 setups.
+	 */
+	if (bfq_slice_idle == 0)
+		bfq_slice_idle = 1;
+
+	if (bfq_timeout_async == 0)
+		bfq_timeout_async = 1;
+
+	if (bfq_slab_setup())
+		return -ENOMEM;
+
+	/*
+	 * Times to load large popular applications for the typical systems
+	 * installed on the reference devices (see the comments before the
+	 * definitions of the two arrays).
+	 */
+	T_slow[0] = msecs_to_jiffies(2600);
+	T_slow[1] = msecs_to_jiffies(1000);
+	T_fast[0] = msecs_to_jiffies(5500);
+	T_fast[1] = msecs_to_jiffies(2000);
+
+	/*
+	 * Thresholds that determine the switch between speed classes (see
+	 * the comments before the definition of the array).
+	 */
+	device_speed_thresh[0] = (R_fast[0] + R_slow[0]) / 2;
+	device_speed_thresh[1] = (R_fast[1] + R_slow[1]) / 2;
+
+	elv_register(&iosched_bfq);
+	pr_info("BFQ I/O-scheduler version: v7r7");
+
+	return 0;
+}
+
+static void __exit bfq_exit(void)
+{
+	elv_unregister(&iosched_bfq);
+	bfq_slab_kill();
+}
+
+module_init(bfq_init);
+module_exit(bfq_exit);
+
+MODULE_AUTHOR("Fabio Checconi, Paolo Valente");
+MODULE_LICENSE("GPL");
diff --git a/block/bfq-sched.c b/block/bfq-sched.c
new file mode 100644
index 0000000..2931563
--- /dev/null
+++ b/block/bfq-sched.c
@@ -0,0 +1,1214 @@
+/*
+ * BFQ: Hierarchical B-WF2Q+ scheduler.
+ *
+ * Based on ideas and code from CFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ *		      Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
+ */
+
+#ifdef CONFIG_CGROUP_BFQIO
+#define for_each_entity(entity)	\
+	for (; entity != NULL; entity = entity->parent)
+
+#define for_each_entity_safe(entity, parent) \
+	for (; entity && ({ parent = entity->parent; 1; }); entity = parent)
+
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
+						 int extract,
+						 struct bfq_data *bfqd);
+
+static inline void bfq_update_budget(struct bfq_entity *next_in_service)
+{
+	struct bfq_entity *bfqg_entity;
+	struct bfq_group *bfqg;
+	struct bfq_sched_data *group_sd;
+
+	BUG_ON(next_in_service == NULL);
+
+	group_sd = next_in_service->sched_data;
+
+	bfqg = container_of(group_sd, struct bfq_group, sched_data);
+	/*
+	 * bfq_group's my_entity field is not NULL only if the group
+	 * is not the root group. We must not touch the root entity
+	 * as it must never become an in-service entity.
+	 */
+	bfqg_entity = bfqg->my_entity;
+	if (bfqg_entity != NULL)
+		bfqg_entity->budget = next_in_service->budget;
+}
+
+static int bfq_update_next_in_service(struct bfq_sched_data *sd)
+{
+	struct bfq_entity *next_in_service;
+
+	if (sd->in_service_entity != NULL)
+		/* will update/requeue at the end of service */
+		return 0;
+
+	/*
+	 * NOTE: this can be improved in many ways, such as returning
+	 * 1 (and thus propagating upwards the update) only when the
+	 * budget changes, or caching the bfqq that will be scheduled
+	 * next from this subtree.  By now we worry more about
+	 * correctness than about performance...
+	 */
+	next_in_service = bfq_lookup_next_entity(sd, 0, NULL);
+	sd->next_in_service = next_in_service;
+
+	if (next_in_service != NULL)
+		bfq_update_budget(next_in_service);
+
+	return 1;
+}
+
+static inline void bfq_check_next_in_service(struct bfq_sched_data *sd,
+					     struct bfq_entity *entity)
+{
+	BUG_ON(sd->next_in_service != entity);
+}
+#else
+#define for_each_entity(entity)	\
+	for (; entity != NULL; entity = NULL)
+
+#define for_each_entity_safe(entity, parent) \
+	for (parent = NULL; entity != NULL; entity = parent)
+
+static inline int bfq_update_next_in_service(struct bfq_sched_data *sd)
+{
+	return 0;
+}
+
+static inline void bfq_check_next_in_service(struct bfq_sched_data *sd,
+					     struct bfq_entity *entity)
+{
+}
+
+static inline void bfq_update_budget(struct bfq_entity *next_in_service)
+{
+}
+#endif
+
+/*
+ * Shift for timestamp calculations.  This actually limits the maximum
+ * service allowed in one timestamp delta (small shift values increase it),
+ * the maximum total weight that can be used for the queues in the system
+ * (big shift values increase it), and the period of virtual time
+ * wraparounds.
+ */
+#define WFQ_SERVICE_SHIFT	22
+
+/**
+ * bfq_gt - compare two timestamps.
+ * @a: first ts.
+ * @b: second ts.
+ *
+ * Return @a > @b, dealing with wrapping correctly.
+ */
+static inline int bfq_gt(u64 a, u64 b)
+{
+	return (s64)(a - b) > 0;
+}
+
+static inline struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = NULL;
+
+	BUG_ON(entity == NULL);
+
+	if (entity->my_sched_data == NULL)
+		bfqq = container_of(entity, struct bfq_queue, entity);
+
+	return bfqq;
+}
+
+
+/**
+ * bfq_delta - map service into the virtual time domain.
+ * @service: amount of service.
+ * @weight: scale factor (weight of an entity or weight sum).
+ */
+static inline u64 bfq_delta(unsigned long service,
+					unsigned long weight)
+{
+	u64 d = (u64)service << WFQ_SERVICE_SHIFT;
+
+	do_div(d, weight);
+	return d;
+}
+
+/**
+ * bfq_calc_finish - assign the finish time to an entity.
+ * @entity: the entity to act upon.
+ * @service: the service to be charged to the entity.
+ */
+static inline void bfq_calc_finish(struct bfq_entity *entity,
+				   unsigned long service)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	BUG_ON(entity->weight == 0);
+
+	entity->finish = entity->start +
+		bfq_delta(service, entity->weight);
+
+	if (bfqq != NULL) {
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			"calc_finish: serv %lu, w %d",
+			service, entity->weight);
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			"calc_finish: start %llu, finish %llu, delta %llu",
+			entity->start, entity->finish,
+			bfq_delta(service, entity->weight));
+	}
+}
+
+/**
+ * bfq_entity_of - get an entity from a node.
+ * @node: the node field of the entity.
+ *
+ * Convert a node pointer to the relative entity.  This is used only
+ * to simplify the logic of some functions and not as the generic
+ * conversion mechanism because, e.g., in the tree walking functions,
+ * the check for a %NULL value would be redundant.
+ */
+static inline struct bfq_entity *bfq_entity_of(struct rb_node *node)
+{
+	struct bfq_entity *entity = NULL;
+
+	if (node != NULL)
+		entity = rb_entry(node, struct bfq_entity, rb_node);
+
+	return entity;
+}
+
+/**
+ * bfq_extract - remove an entity from a tree.
+ * @root: the tree root.
+ * @entity: the entity to remove.
+ */
+static inline void bfq_extract(struct rb_root *root,
+			       struct bfq_entity *entity)
+{
+	BUG_ON(entity->tree != root);
+
+	entity->tree = NULL;
+	rb_erase(&entity->rb_node, root);
+}
+
+/**
+ * bfq_idle_extract - extract an entity from the idle tree.
+ * @st: the service tree of the owning @entity.
+ * @entity: the entity being removed.
+ */
+static void bfq_idle_extract(struct bfq_service_tree *st,
+			     struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct rb_node *next;
+
+	BUG_ON(entity->tree != &st->idle);
+
+	if (entity == st->first_idle) {
+		next = rb_next(&entity->rb_node);
+		st->first_idle = bfq_entity_of(next);
+	}
+
+	if (entity == st->last_idle) {
+		next = rb_prev(&entity->rb_node);
+		st->last_idle = bfq_entity_of(next);
+	}
+
+	bfq_extract(&st->idle, entity);
+
+	if (bfqq != NULL)
+		list_del(&bfqq->bfqq_list);
+}
+
+/**
+ * bfq_insert - generic tree insertion.
+ * @root: tree root.
+ * @entity: entity to insert.
+ *
+ * This is used for the idle and the active tree, since they are both
+ * ordered by finish time.
+ */
+static void bfq_insert(struct rb_root *root, struct bfq_entity *entity)
+{
+	struct bfq_entity *entry;
+	struct rb_node **node = &root->rb_node;
+	struct rb_node *parent = NULL;
+
+	BUG_ON(entity->tree != NULL);
+
+	while (*node != NULL) {
+		parent = *node;
+		entry = rb_entry(parent, struct bfq_entity, rb_node);
+
+		if (bfq_gt(entry->finish, entity->finish))
+			node = &parent->rb_left;
+		else
+			node = &parent->rb_right;
+	}
+
+	rb_link_node(&entity->rb_node, parent, node);
+	rb_insert_color(&entity->rb_node, root);
+
+	entity->tree = root;
+}
+
+/**
+ * bfq_update_min - update the min_start field of a entity.
+ * @entity: the entity to update.
+ * @node: one of its children.
+ *
+ * This function is called when @entity may store an invalid value for
+ * min_start due to updates to the active tree.  The function  assumes
+ * that the subtree rooted at @node (which may be its left or its right
+ * child) has a valid min_start value.
+ */
+static inline void bfq_update_min(struct bfq_entity *entity,
+				  struct rb_node *node)
+{
+	struct bfq_entity *child;
+
+	if (node != NULL) {
+		child = rb_entry(node, struct bfq_entity, rb_node);
+		if (bfq_gt(entity->min_start, child->min_start))
+			entity->min_start = child->min_start;
+	}
+}
+
+/**
+ * bfq_update_active_node - recalculate min_start.
+ * @node: the node to update.
+ *
+ * @node may have changed position or one of its children may have moved,
+ * this function updates its min_start value.  The left and right subtrees
+ * are assumed to hold a correct min_start value.
+ */
+static inline void bfq_update_active_node(struct rb_node *node)
+{
+	struct bfq_entity *entity = rb_entry(node, struct bfq_entity, rb_node);
+
+	entity->min_start = entity->start;
+	bfq_update_min(entity, node->rb_right);
+	bfq_update_min(entity, node->rb_left);
+}
+
+/**
+ * bfq_update_active_tree - update min_start for the whole active tree.
+ * @node: the starting node.
+ *
+ * @node must be the deepest modified node after an update.  This function
+ * updates its min_start using the values held by its children, assuming
+ * that they did not change, and then updates all the nodes that may have
+ * changed in the path to the root.  The only nodes that may have changed
+ * are the ones in the path or their siblings.
+ */
+static void bfq_update_active_tree(struct rb_node *node)
+{
+	struct rb_node *parent;
+
+up:
+	bfq_update_active_node(node);
+
+	parent = rb_parent(node);
+	if (parent == NULL)
+		return;
+
+	if (node == parent->rb_left && parent->rb_right != NULL)
+		bfq_update_active_node(parent->rb_right);
+	else if (parent->rb_left != NULL)
+		bfq_update_active_node(parent->rb_left);
+
+	node = parent;
+	goto up;
+}
+
+static void bfq_weights_tree_add(struct bfq_data *bfqd,
+				 struct bfq_entity *entity,
+				 struct rb_root *root);
+
+static void bfq_weights_tree_remove(struct bfq_data *bfqd,
+				    struct bfq_entity *entity,
+				    struct rb_root *root);
+
+
+/**
+ * bfq_active_insert - insert an entity in the active tree of its
+ *                     group/device.
+ * @st: the service tree of the entity.
+ * @entity: the entity being inserted.
+ *
+ * The active tree is ordered by finish time, but an extra key is kept
+ * per each node, containing the minimum value for the start times of
+ * its children (and the node itself), so it's possible to search for
+ * the eligible node with the lowest finish time in logarithmic time.
+ */
+static void bfq_active_insert(struct bfq_service_tree *st,
+			      struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct rb_node *node = &entity->rb_node;
+#ifdef CONFIG_CGROUP_BFQIO
+	struct bfq_sched_data *sd = NULL;
+	struct bfq_group *bfqg = NULL;
+	struct bfq_data *bfqd = NULL;
+#endif
+
+	bfq_insert(&st->active, entity);
+
+	if (node->rb_left != NULL)
+		node = node->rb_left;
+	else if (node->rb_right != NULL)
+		node = node->rb_right;
+
+	bfq_update_active_tree(node);
+
+#ifdef CONFIG_CGROUP_BFQIO
+	sd = entity->sched_data;
+	bfqg = container_of(sd, struct bfq_group, sched_data);
+	BUG_ON(!bfqg);
+	bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
+	if (bfqq != NULL)
+		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
+#ifdef CONFIG_CGROUP_BFQIO
+	else { /* bfq_group */
+		BUG_ON(!bfqd);
+		bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree);
+	}
+	if (bfqg != bfqd->root_group) {
+		BUG_ON(!bfqg);
+		BUG_ON(!bfqd);
+		bfqg->active_entities++;
+		if (bfqg->active_entities == 2)
+			bfqd->active_numerous_groups++;
+	}
+#endif
+}
+
+/**
+ * bfq_ioprio_to_weight - calc a weight from an ioprio.
+ * @ioprio: the ioprio value to convert.
+ */
+static inline unsigned short bfq_ioprio_to_weight(int ioprio)
+{
+	BUG_ON(ioprio < 0 || ioprio >= IOPRIO_BE_NR);
+	return IOPRIO_BE_NR - ioprio;
+}
+
+/**
+ * bfq_weight_to_ioprio - calc an ioprio from a weight.
+ * @weight: the weight value to convert.
+ *
+ * To preserve as mush as possible the old only-ioprio user interface,
+ * 0 is used as an escape ioprio value for weights (numerically) equal or
+ * larger than IOPRIO_BE_NR
+ */
+static inline unsigned short bfq_weight_to_ioprio(int weight)
+{
+	BUG_ON(weight < BFQ_MIN_WEIGHT || weight > BFQ_MAX_WEIGHT);
+	return IOPRIO_BE_NR - weight < 0 ? 0 : IOPRIO_BE_NR - weight;
+}
+
+static inline void bfq_get_entity(struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	if (bfqq != NULL) {
+		atomic_inc(&bfqq->ref);
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
+			     bfqq, atomic_read(&bfqq->ref));
+	}
+}
+
+/**
+ * bfq_find_deepest - find the deepest node that an extraction can modify.
+ * @node: the node being removed.
+ *
+ * Do the first step of an extraction in an rb tree, looking for the
+ * node that will replace @node, and returning the deepest node that
+ * the following modifications to the tree can touch.  If @node is the
+ * last node in the tree return %NULL.
+ */
+static struct rb_node *bfq_find_deepest(struct rb_node *node)
+{
+	struct rb_node *deepest;
+
+	if (node->rb_right == NULL && node->rb_left == NULL)
+		deepest = rb_parent(node);
+	else if (node->rb_right == NULL)
+		deepest = node->rb_left;
+	else if (node->rb_left == NULL)
+		deepest = node->rb_right;
+	else {
+		deepest = rb_next(node);
+		if (deepest->rb_right != NULL)
+			deepest = deepest->rb_right;
+		else if (rb_parent(deepest) != node)
+			deepest = rb_parent(deepest);
+	}
+
+	return deepest;
+}
+
+/**
+ * bfq_active_extract - remove an entity from the active tree.
+ * @st: the service_tree containing the tree.
+ * @entity: the entity being removed.
+ */
+static void bfq_active_extract(struct bfq_service_tree *st,
+			       struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct rb_node *node;
+#ifdef CONFIG_CGROUP_BFQIO
+	struct bfq_sched_data *sd = NULL;
+	struct bfq_group *bfqg = NULL;
+	struct bfq_data *bfqd = NULL;
+#endif
+
+	node = bfq_find_deepest(&entity->rb_node);
+	bfq_extract(&st->active, entity);
+
+	if (node != NULL)
+		bfq_update_active_tree(node);
+
+#ifdef CONFIG_CGROUP_BFQIO
+	sd = entity->sched_data;
+	bfqg = container_of(sd, struct bfq_group, sched_data);
+	BUG_ON(!bfqg);
+	bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
+	if (bfqq != NULL)
+		list_del(&bfqq->bfqq_list);
+#ifdef CONFIG_CGROUP_BFQIO
+	else { /* bfq_group */
+		BUG_ON(!bfqd);
+		bfq_weights_tree_remove(bfqd, entity,
+					&bfqd->group_weights_tree);
+	}
+	if (bfqg != bfqd->root_group) {
+		BUG_ON(!bfqg);
+		BUG_ON(!bfqd);
+		BUG_ON(!bfqg->active_entities);
+		bfqg->active_entities--;
+		if (bfqg->active_entities == 1) {
+			BUG_ON(!bfqd->active_numerous_groups);
+			bfqd->active_numerous_groups--;
+		}
+	}
+#endif
+}
+
+/**
+ * bfq_idle_insert - insert an entity into the idle tree.
+ * @st: the service tree containing the tree.
+ * @entity: the entity to insert.
+ */
+static void bfq_idle_insert(struct bfq_service_tree *st,
+			    struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct bfq_entity *first_idle = st->first_idle;
+	struct bfq_entity *last_idle = st->last_idle;
+
+	if (first_idle == NULL || bfq_gt(first_idle->finish, entity->finish))
+		st->first_idle = entity;
+	if (last_idle == NULL || bfq_gt(entity->finish, last_idle->finish))
+		st->last_idle = entity;
+
+	bfq_insert(&st->idle, entity);
+
+	if (bfqq != NULL)
+		list_add(&bfqq->bfqq_list, &bfqq->bfqd->idle_list);
+}
+
+/**
+ * bfq_forget_entity - remove an entity from the wfq trees.
+ * @st: the service tree.
+ * @entity: the entity being removed.
+ *
+ * Update the device status and forget everything about @entity, putting
+ * the device reference to it, if it is a queue.  Entities belonging to
+ * groups are not refcounted.
+ */
+static void bfq_forget_entity(struct bfq_service_tree *st,
+			      struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct bfq_sched_data *sd;
+
+	BUG_ON(!entity->on_st);
+
+	entity->on_st = 0;
+	st->wsum -= entity->weight;
+	if (bfqq != NULL) {
+		sd = entity->sched_data;
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "forget_entity: %p %d",
+			     bfqq, atomic_read(&bfqq->ref));
+		bfq_put_queue(bfqq);
+	}
+}
+
+/**
+ * bfq_put_idle_entity - release the idle tree ref of an entity.
+ * @st: service tree for the entity.
+ * @entity: the entity being released.
+ */
+static void bfq_put_idle_entity(struct bfq_service_tree *st,
+				struct bfq_entity *entity)
+{
+	bfq_idle_extract(st, entity);
+	bfq_forget_entity(st, entity);
+}
+
+/**
+ * bfq_forget_idle - update the idle tree if necessary.
+ * @st: the service tree to act upon.
+ *
+ * To preserve the global O(log N) complexity we only remove one entry here;
+ * as the idle tree will not grow indefinitely this can be done safely.
+ */
+static void bfq_forget_idle(struct bfq_service_tree *st)
+{
+	struct bfq_entity *first_idle = st->first_idle;
+	struct bfq_entity *last_idle = st->last_idle;
+
+	if (RB_EMPTY_ROOT(&st->active) && last_idle != NULL &&
+	    !bfq_gt(last_idle->finish, st->vtime)) {
+		/*
+		 * Forget the whole idle tree, increasing the vtime past
+		 * the last finish time of idle entities.
+		 */
+		st->vtime = last_idle->finish;
+	}
+
+	if (first_idle != NULL && !bfq_gt(first_idle->finish, st->vtime))
+		bfq_put_idle_entity(st, first_idle);
+}
+
+static struct bfq_service_tree *
+__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
+			 struct bfq_entity *entity)
+{
+	struct bfq_service_tree *new_st = old_st;
+
+	if (entity->ioprio_changed) {
+		struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+		unsigned short prev_weight, new_weight;
+		struct bfq_data *bfqd = NULL;
+		struct rb_root *root;
+#ifdef CONFIG_CGROUP_BFQIO
+		struct bfq_sched_data *sd;
+		struct bfq_group *bfqg;
+#endif
+
+		if (bfqq != NULL)
+			bfqd = bfqq->bfqd;
+#ifdef CONFIG_CGROUP_BFQIO
+		else {
+			sd = entity->my_sched_data;
+			bfqg = container_of(sd, struct bfq_group, sched_data);
+			BUG_ON(!bfqg);
+			bfqd = (struct bfq_data *)bfqg->bfqd;
+			BUG_ON(!bfqd);
+		}
+#endif
+
+		BUG_ON(old_st->wsum < entity->weight);
+		old_st->wsum -= entity->weight;
+
+		if (entity->new_weight != entity->orig_weight) {
+			if (entity->new_weight < BFQ_MIN_WEIGHT ||
+			    entity->new_weight > BFQ_MAX_WEIGHT) {
+				printk(KERN_CRIT "update_weight_prio: "
+						 "new_weight %d\n",
+					entity->new_weight);
+				BUG();
+			}
+			entity->orig_weight = entity->new_weight;
+			entity->ioprio =
+				bfq_weight_to_ioprio(entity->orig_weight);
+		} else if (entity->new_ioprio != entity->ioprio) {
+			entity->ioprio = entity->new_ioprio;
+			entity->orig_weight =
+					bfq_ioprio_to_weight(entity->ioprio);
+		} else
+			entity->new_weight = entity->orig_weight =
+				bfq_ioprio_to_weight(entity->ioprio);
+
+		entity->ioprio_class = entity->new_ioprio_class;
+		entity->ioprio_changed = 0;
+
+		/*
+		 * NOTE: here we may be changing the weight too early,
+		 * this will cause unfairness.  The correct approach
+		 * would have required additional complexity to defer
+		 * weight changes to the proper time instants (i.e.,
+		 * when entity->finish <= old_st->vtime).
+		 */
+		new_st = bfq_entity_service_tree(entity);
+
+		prev_weight = entity->weight;
+		new_weight = entity->orig_weight *
+			     (bfqq != NULL ? bfqq->wr_coeff : 1);
+		/*
+		 * If the weight of the entity changes, remove the entity
+		 * from its old weight counter (if there is a counter
+		 * associated with the entity), and add it to the counter
+		 * associated with its new weight.
+		 */
+		if (prev_weight != new_weight) {
+			root = bfqq ? &bfqd->queue_weights_tree :
+				      &bfqd->group_weights_tree;
+			bfq_weights_tree_remove(bfqd, entity, root);
+		}
+		entity->weight = new_weight;
+		/*
+		 * Add the entity to its weights tree only if it is
+		 * not associated with a weight-raised queue.
+		 */
+		if (prev_weight != new_weight &&
+		    (bfqq ? bfqq->wr_coeff == 1 : 1))
+			/* If we get here, root has been initialized. */
+			bfq_weights_tree_add(bfqd, entity, root);
+
+		new_st->wsum += entity->weight;
+
+		if (new_st != old_st)
+			entity->start = new_st->vtime;
+	}
+
+	return new_st;
+}
+
+/**
+ * bfq_bfqq_served - update the scheduler status after selection for
+ *                   service.
+ * @bfqq: the queue being served.
+ * @served: bytes to transfer.
+ *
+ * NOTE: this can be optimized, as the timestamps of upper level entities
+ * are synchronized every time a new bfqq is selected for service.  By now,
+ * we keep it to better check consistency.
+ */
+static void bfq_bfqq_served(struct bfq_queue *bfqq, unsigned long served)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+	struct bfq_service_tree *st;
+
+	for_each_entity(entity) {
+		st = bfq_entity_service_tree(entity);
+
+		entity->service += served;
+		BUG_ON(entity->service > entity->budget);
+		BUG_ON(st->wsum == 0);
+
+		st->vtime += bfq_delta(served, st->wsum);
+		bfq_forget_idle(st);
+	}
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %lu secs", served);
+}
+
+/**
+ * bfq_bfqq_charge_full_budget - set the service to the entity budget.
+ * @bfqq: the queue that needs a service update.
+ *
+ * When it's not possible to be fair in the service domain, because
+ * a queue is not consuming its budget fast enough (the meaning of
+ * fast depends on the timeout parameter), we charge it a full
+ * budget.  In this way we should obtain a sort of time-domain
+ * fairness among all the seeky/slow queues.
+ */
+static inline void bfq_bfqq_charge_full_budget(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "charge_full_budget");
+
+	bfq_bfqq_served(bfqq, entity->budget - entity->service);
+}
+
+/**
+ * __bfq_activate_entity - activate an entity.
+ * @entity: the entity being activated.
+ *
+ * Called whenever an entity is activated, i.e., it is not active and one
+ * of its children receives a new request, or has to be reactivated due to
+ * budget exhaustion.  It uses the current budget of the entity (and the
+ * service received if @entity is active) of the queue to calculate its
+ * timestamps.
+ */
+static void __bfq_activate_entity(struct bfq_entity *entity)
+{
+	struct bfq_sched_data *sd = entity->sched_data;
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+
+	if (entity == sd->in_service_entity) {
+		BUG_ON(entity->tree != NULL);
+		/*
+		 * If we are requeueing the current entity we have
+		 * to take care of not charging to it service it has
+		 * not received.
+		 */
+		bfq_calc_finish(entity, entity->service);
+		entity->start = entity->finish;
+		sd->in_service_entity = NULL;
+	} else if (entity->tree == &st->active) {
+		/*
+		 * Requeueing an entity due to a change of some
+		 * next_in_service entity below it.  We reuse the
+		 * old start time.
+		 */
+		bfq_active_extract(st, entity);
+	} else if (entity->tree == &st->idle) {
+		/*
+		 * Must be on the idle tree, bfq_idle_extract() will
+		 * check for that.
+		 */
+		bfq_idle_extract(st, entity);
+		entity->start = bfq_gt(st->vtime, entity->finish) ?
+				       st->vtime : entity->finish;
+	} else {
+		/*
+		 * The finish time of the entity may be invalid, and
+		 * it is in the past for sure, otherwise the queue
+		 * would have been on the idle tree.
+		 */
+		entity->start = st->vtime;
+		st->wsum += entity->weight;
+		bfq_get_entity(entity);
+
+		BUG_ON(entity->on_st);
+		entity->on_st = 1;
+	}
+
+	st = __bfq_entity_update_weight_prio(st, entity);
+	bfq_calc_finish(entity, entity->budget);
+	bfq_active_insert(st, entity);
+}
+
+/**
+ * bfq_activate_entity - activate an entity and its ancestors if necessary.
+ * @entity: the entity to activate.
+ *
+ * Activate @entity and all the entities on the path from it to the root.
+ */
+static void bfq_activate_entity(struct bfq_entity *entity)
+{
+	struct bfq_sched_data *sd;
+
+	for_each_entity(entity) {
+		__bfq_activate_entity(entity);
+
+		sd = entity->sched_data;
+		if (!bfq_update_next_in_service(sd))
+			/*
+			 * No need to propagate the activation to the
+			 * upper entities, as they will be updated when
+			 * the in-service entity is rescheduled.
+			 */
+			break;
+	}
+}
+
+/**
+ * __bfq_deactivate_entity - deactivate an entity from its service tree.
+ * @entity: the entity to deactivate.
+ * @requeue: if false, the entity will not be put into the idle tree.
+ *
+ * Deactivate an entity, independently from its previous state.  If the
+ * entity was not on a service tree just return, otherwise if it is on
+ * any scheduler tree, extract it from that tree, and if necessary
+ * and if the caller did not specify @requeue, put it on the idle tree.
+ *
+ * Return %1 if the caller should update the entity hierarchy, i.e.,
+ * if the entity was in service or if it was the next_in_service for
+ * its sched_data; return %0 otherwise.
+ */
+static int __bfq_deactivate_entity(struct bfq_entity *entity, int requeue)
+{
+	struct bfq_sched_data *sd = entity->sched_data;
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+	int was_in_service = entity == sd->in_service_entity;
+	int ret = 0;
+
+	if (!entity->on_st)
+		return 0;
+
+	BUG_ON(was_in_service && entity->tree != NULL);
+
+	if (was_in_service) {
+		bfq_calc_finish(entity, entity->service);
+		sd->in_service_entity = NULL;
+	} else if (entity->tree == &st->active)
+		bfq_active_extract(st, entity);
+	else if (entity->tree == &st->idle)
+		bfq_idle_extract(st, entity);
+	else if (entity->tree != NULL)
+		BUG();
+
+	if (was_in_service || sd->next_in_service == entity)
+		ret = bfq_update_next_in_service(sd);
+
+	if (!requeue || !bfq_gt(entity->finish, st->vtime))
+		bfq_forget_entity(st, entity);
+	else
+		bfq_idle_insert(st, entity);
+
+	BUG_ON(sd->in_service_entity == entity);
+	BUG_ON(sd->next_in_service == entity);
+
+	return ret;
+}
+
+/**
+ * bfq_deactivate_entity - deactivate an entity.
+ * @entity: the entity to deactivate.
+ * @requeue: true if the entity can be put on the idle tree
+ */
+static void bfq_deactivate_entity(struct bfq_entity *entity, int requeue)
+{
+	struct bfq_sched_data *sd;
+	struct bfq_entity *parent;
+
+	for_each_entity_safe(entity, parent) {
+		sd = entity->sched_data;
+
+		if (!__bfq_deactivate_entity(entity, requeue))
+			/*
+			 * The parent entity is still backlogged, and
+			 * we don't need to update it as it is still
+			 * in service.
+			 */
+			break;
+
+		if (sd->next_in_service != NULL)
+			/*
+			 * The parent entity is still backlogged and
+			 * the budgets on the path towards the root
+			 * need to be updated.
+			 */
+			goto update;
+
+		/*
+		 * If we reach there the parent is no more backlogged and
+		 * we want to propagate the dequeue upwards.
+		 */
+		requeue = 1;
+	}
+
+	return;
+
+update:
+	entity = parent;
+	for_each_entity(entity) {
+		__bfq_activate_entity(entity);
+
+		sd = entity->sched_data;
+		if (!bfq_update_next_in_service(sd))
+			break;
+	}
+}
+
+/**
+ * bfq_update_vtime - update vtime if necessary.
+ * @st: the service tree to act upon.
+ *
+ * If necessary update the service tree vtime to have at least one
+ * eligible entity, skipping to its start time.  Assumes that the
+ * active tree of the device is not empty.
+ *
+ * NOTE: this hierarchical implementation updates vtimes quite often,
+ * we may end up with reactivated processes getting timestamps after a
+ * vtime skip done because we needed a ->first_active entity on some
+ * intermediate node.
+ */
+static void bfq_update_vtime(struct bfq_service_tree *st)
+{
+	struct bfq_entity *entry;
+	struct rb_node *node = st->active.rb_node;
+
+	entry = rb_entry(node, struct bfq_entity, rb_node);
+	if (bfq_gt(entry->min_start, st->vtime)) {
+		st->vtime = entry->min_start;
+		bfq_forget_idle(st);
+	}
+}
+
+/**
+ * bfq_first_active_entity - find the eligible entity with
+ *                           the smallest finish time
+ * @st: the service tree to select from.
+ *
+ * This function searches the first schedulable entity, starting from the
+ * root of the tree and going on the left every time on this side there is
+ * a subtree with at least one eligible (start >= vtime) entity. The path on
+ * the right is followed only if a) the left subtree contains no eligible
+ * entities and b) no eligible entity has been found yet.
+ */
+static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st)
+{
+	struct bfq_entity *entry, *first = NULL;
+	struct rb_node *node = st->active.rb_node;
+
+	while (node != NULL) {
+		entry = rb_entry(node, struct bfq_entity, rb_node);
+left:
+		if (!bfq_gt(entry->start, st->vtime))
+			first = entry;
+
+		BUG_ON(bfq_gt(entry->min_start, st->vtime));
+
+		if (node->rb_left != NULL) {
+			entry = rb_entry(node->rb_left,
+					 struct bfq_entity, rb_node);
+			if (!bfq_gt(entry->min_start, st->vtime)) {
+				node = node->rb_left;
+				goto left;
+			}
+		}
+		if (first != NULL)
+			break;
+		node = node->rb_right;
+	}
+
+	BUG_ON(first == NULL && !RB_EMPTY_ROOT(&st->active));
+	return first;
+}
+
+/**
+ * __bfq_lookup_next_entity - return the first eligible entity in @st.
+ * @st: the service tree.
+ *
+ * Update the virtual time in @st and return the first eligible entity
+ * it contains.
+ */
+static struct bfq_entity *__bfq_lookup_next_entity(struct bfq_service_tree *st,
+						   bool force)
+{
+	struct bfq_entity *entity, *new_next_in_service = NULL;
+
+	if (RB_EMPTY_ROOT(&st->active))
+		return NULL;
+
+	bfq_update_vtime(st);
+	entity = bfq_first_active_entity(st);
+	BUG_ON(bfq_gt(entity->start, st->vtime));
+
+	/*
+	 * If the chosen entity does not match with the sched_data's
+	 * next_in_service and we are forcedly serving the IDLE priority
+	 * class tree, bubble up budget update.
+	 */
+	if (unlikely(force && entity != entity->sched_data->next_in_service)) {
+		new_next_in_service = entity;
+		for_each_entity(new_next_in_service)
+			bfq_update_budget(new_next_in_service);
+	}
+
+	return entity;
+}
+
+/**
+ * bfq_lookup_next_entity - return the first eligible entity in @sd.
+ * @sd: the sched_data.
+ * @extract: if true the returned entity will be also extracted from @sd.
+ *
+ * NOTE: since we cache the next_in_service entity at each level of the
+ * hierarchy, the complexity of the lookup can be decreased with
+ * absolutely no effort just returning the cached next_in_service value;
+ * we prefer to do full lookups to test the consistency of * the data
+ * structures.
+ */
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
+						 int extract,
+						 struct bfq_data *bfqd)
+{
+	struct bfq_service_tree *st = sd->service_tree;
+	struct bfq_entity *entity;
+	int i = 0;
+
+	BUG_ON(sd->in_service_entity != NULL);
+
+	if (bfqd != NULL &&
+	    jiffies - bfqd->bfq_class_idle_last_service > BFQ_CL_IDLE_TIMEOUT) {
+		entity = __bfq_lookup_next_entity(st + BFQ_IOPRIO_CLASSES - 1,
+						  true);
+		if (entity != NULL) {
+			i = BFQ_IOPRIO_CLASSES - 1;
+			bfqd->bfq_class_idle_last_service = jiffies;
+			sd->next_in_service = entity;
+		}
+	}
+	for (; i < BFQ_IOPRIO_CLASSES; i++) {
+		entity = __bfq_lookup_next_entity(st + i, false);
+		if (entity != NULL) {
+			if (extract) {
+				bfq_check_next_in_service(sd, entity);
+				bfq_active_extract(st + i, entity);
+				sd->in_service_entity = entity;
+				sd->next_in_service = NULL;
+			}
+			break;
+		}
+	}
+
+	return entity;
+}
+
+/*
+ * Get next queue for service.
+ */
+static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
+{
+	struct bfq_entity *entity = NULL;
+	struct bfq_sched_data *sd;
+	struct bfq_queue *bfqq;
+
+	BUG_ON(bfqd->in_service_queue != NULL);
+
+	if (bfqd->busy_queues == 0)
+		return NULL;
+
+	sd = &bfqd->root_group->sched_data;
+	for (; sd != NULL; sd = entity->my_sched_data) {
+		entity = bfq_lookup_next_entity(sd, 1, bfqd);
+		BUG_ON(entity == NULL);
+		entity->service = 0;
+	}
+
+	bfqq = bfq_entity_to_bfqq(entity);
+	BUG_ON(bfqq == NULL);
+
+	return bfqq;
+}
+
+/*
+ * Forced extraction of the given queue.
+ */
+static void bfq_get_next_queue_forced(struct bfq_data *bfqd,
+				      struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity;
+	struct bfq_sched_data *sd;
+
+	BUG_ON(bfqd->in_service_queue != NULL);
+
+	entity = &bfqq->entity;
+	/*
+	 * Bubble up extraction/update from the leaf to the root.
+	*/
+	for_each_entity(entity) {
+		sd = entity->sched_data;
+		bfq_update_budget(entity);
+		bfq_update_vtime(bfq_entity_service_tree(entity));
+		bfq_active_extract(bfq_entity_service_tree(entity), entity);
+		sd->in_service_entity = entity;
+		sd->next_in_service = NULL;
+		entity->service = 0;
+	}
+
+	return;
+}
+
+static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+{
+	if (bfqd->in_service_bic != NULL) {
+		put_io_context(bfqd->in_service_bic->icq.ioc);
+		bfqd->in_service_bic = NULL;
+	}
+
+	bfqd->in_service_queue = NULL;
+	del_timer(&bfqd->idle_slice_timer);
+}
+
+static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+				int requeue)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	if (bfqq == bfqd->in_service_queue)
+		__bfq_bfqd_reset_in_service(bfqd);
+
+	bfq_deactivate_entity(entity, requeue);
+}
+
+static void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	bfq_activate_entity(entity);
+}
+
+/*
+ * Called when the bfqq no longer has requests pending, remove it from
+ * the service tree.
+ */
+static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			      int requeue)
+{
+	BUG_ON(!bfq_bfqq_busy(bfqq));
+	BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
+
+	bfq_log_bfqq(bfqd, bfqq, "del from busy");
+
+	bfq_clear_bfqq_busy(bfqq);
+
+	BUG_ON(bfqd->busy_queues == 0);
+	bfqd->busy_queues--;
+
+	if (!bfqq->dispatched) {
+		bfq_weights_tree_remove(bfqd, &bfqq->entity,
+					&bfqd->queue_weights_tree);
+		if (!blk_queue_nonrot(bfqd->queue)) {
+			BUG_ON(!bfqd->busy_in_flight_queues);
+			bfqd->busy_in_flight_queues--;
+			if (bfq_bfqq_constantly_seeky(bfqq)) {
+				BUG_ON(!bfqd->
+					const_seeky_busy_in_flight_queues);
+				bfqd->const_seeky_busy_in_flight_queues--;
+			}
+		}
+	}
+	if (bfqq->wr_coeff > 1)
+		bfqd->wr_busy_queues--;
+
+	bfq_deactivate_bfqq(bfqd, bfqq, requeue);
+}
+
+/*
+ * Called when an inactive queue receives a new request.
+ */
+static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	BUG_ON(bfq_bfqq_busy(bfqq));
+	BUG_ON(bfqq == bfqd->in_service_queue);
+
+	bfq_log_bfqq(bfqd, bfqq, "add to busy");
+
+	bfq_activate_bfqq(bfqd, bfqq);
+
+	bfq_mark_bfqq_busy(bfqq);
+	bfqd->busy_queues++;
+
+	if (!bfqq->dispatched) {
+		if (bfqq->wr_coeff == 1)
+			bfq_weights_tree_add(bfqd, &bfqq->entity,
+					     &bfqd->queue_weights_tree);
+		if (!blk_queue_nonrot(bfqd->queue)) {
+			bfqd->busy_in_flight_queues++;
+			if (bfq_bfqq_constantly_seeky(bfqq))
+				bfqd->const_seeky_busy_in_flight_queues++;
+		}
+	}
+	if (bfqq->wr_coeff > 1)
+		bfqd->wr_busy_queues++;
+}
diff --git a/block/bfq.h b/block/bfq.h
new file mode 100644
index 0000000..518f2ac
--- /dev/null
+++ b/block/bfq.h
@@ -0,0 +1,775 @@
+/*
+ * BFQ-v7r7 for 4.0.0: data structures and common functions prototypes.
+ *
+ * Based on ideas and code from CFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ *		      Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
+ */
+
+#ifndef _BFQ_H
+#define _BFQ_H
+
+#include <linux/blktrace_api.h>
+#include <linux/hrtimer.h>
+#include <linux/ioprio.h>
+#include <linux/rbtree.h>
+
+#define BFQ_IOPRIO_CLASSES	3
+#define BFQ_CL_IDLE_TIMEOUT	(HZ/5)
+
+#define BFQ_MIN_WEIGHT	1
+#define BFQ_MAX_WEIGHT	1000
+
+#define BFQ_DEFAULT_QUEUE_IOPRIO	4
+
+#define BFQ_DEFAULT_GRP_WEIGHT	10
+#define BFQ_DEFAULT_GRP_IOPRIO	0
+#define BFQ_DEFAULT_GRP_CLASS	IOPRIO_CLASS_BE
+
+struct bfq_entity;
+
+/**
+ * struct bfq_service_tree - per ioprio_class service tree.
+ * @active: tree for active entities (i.e., those backlogged).
+ * @idle: tree for idle entities (i.e., those not backlogged, with V <= F_i).
+ * @first_idle: idle entity with minimum F_i.
+ * @last_idle: idle entity with maximum F_i.
+ * @vtime: scheduler virtual time.
+ * @wsum: scheduler weight sum; active and idle entities contribute to it.
+ *
+ * Each service tree represents a B-WF2Q+ scheduler on its own.  Each
+ * ioprio_class has its own independent scheduler, and so its own
+ * bfq_service_tree.  All the fields are protected by the queue lock
+ * of the containing bfqd.
+ */
+struct bfq_service_tree {
+	struct rb_root active;
+	struct rb_root idle;
+
+	struct bfq_entity *first_idle;
+	struct bfq_entity *last_idle;
+
+	u64 vtime;
+	unsigned long wsum;
+};
+
+/**
+ * struct bfq_sched_data - multi-class scheduler.
+ * @in_service_entity: entity in service.
+ * @next_in_service: head-of-the-line entity in the scheduler.
+ * @service_tree: array of service trees, one per ioprio_class.
+ *
+ * bfq_sched_data is the basic scheduler queue.  It supports three
+ * ioprio_classes, and can be used either as a toplevel queue or as
+ * an intermediate queue on a hierarchical setup.
+ * @next_in_service points to the active entity of the sched_data
+ * service trees that will be scheduled next.
+ *
+ * The supported ioprio_classes are the same as in CFQ, in descending
+ * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
+ * Requests from higher priority queues are served before all the
+ * requests from lower priority queues; among requests of the same
+ * queue requests are served according to B-WF2Q+.
+ * All the fields are protected by the queue lock of the containing bfqd.
+ */
+struct bfq_sched_data {
+	struct bfq_entity *in_service_entity;
+	struct bfq_entity *next_in_service;
+	struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
+};
+
+/**
+ * struct bfq_weight_counter - counter of the number of all active entities
+ *                             with a given weight.
+ * @weight: weight of the entities that this counter refers to.
+ * @num_active: number of active entities with this weight.
+ * @weights_node: weights tree member (see bfq_data's @queue_weights_tree
+ *                and @group_weights_tree).
+ */
+struct bfq_weight_counter {
+	short int weight;
+	unsigned int num_active;
+	struct rb_node weights_node;
+};
+
+/**
+ * struct bfq_entity - schedulable entity.
+ * @rb_node: service_tree member.
+ * @weight_counter: pointer to the weight counter associated with this entity.
+ * @on_st: flag, true if the entity is on a tree (either the active or
+ *         the idle one of its service_tree).
+ * @finish: B-WF2Q+ finish timestamp (aka F_i).
+ * @start: B-WF2Q+ start timestamp (aka S_i).
+ * @tree: tree the entity is enqueued into; %NULL if not on a tree.
+ * @min_start: minimum start time of the (active) subtree rooted at
+ *             this entity; used for O(log N) lookups into active trees.
+ * @service: service received during the last round of service.
+ * @budget: budget used to calculate F_i; F_i = S_i + @budget / @weight.
+ * @weight: weight of the queue
+ * @parent: parent entity, for hierarchical scheduling.
+ * @my_sched_data: for non-leaf nodes in the cgroup hierarchy, the
+ *                 associated scheduler queue, %NULL on leaf nodes.
+ * @sched_data: the scheduler queue this entity belongs to.
+ * @ioprio: the ioprio in use.
+ * @new_weight: when a weight change is requested, the new weight value.
+ * @orig_weight: original weight, used to implement weight boosting
+ * @new_ioprio: when an ioprio change is requested, the new ioprio value.
+ * @ioprio_class: the ioprio_class in use.
+ * @new_ioprio_class: when an ioprio_class change is requested, the new
+ *                    ioprio_class value.
+ * @ioprio_changed: flag, true when the user requested a weight, ioprio or
+ *                  ioprio_class change.
+ *
+ * A bfq_entity is used to represent either a bfq_queue (leaf node in the
+ * cgroup hierarchy) or a bfq_group into the upper level scheduler.  Each
+ * entity belongs to the sched_data of the parent group in the cgroup
+ * hierarchy.  Non-leaf entities have also their own sched_data, stored
+ * in @my_sched_data.
+ *
+ * Each entity stores independently its priority values; this would
+ * allow different weights on different devices, but this
+ * functionality is not exported to userspace by now.  Priorities and
+ * weights are updated lazily, first storing the new values into the
+ * new_* fields, then setting the @ioprio_changed flag.  As soon as
+ * there is a transition in the entity state that allows the priority
+ * update to take place the effective and the requested priority
+ * values are synchronized.
+ *
+ * Unless cgroups are used, the weight value is calculated from the
+ * ioprio to export the same interface as CFQ.  When dealing with
+ * ``well-behaved'' queues (i.e., queues that do not spend too much
+ * time to consume their budget and have true sequential behavior, and
+ * when there are no external factors breaking anticipation) the
+ * relative weights at each level of the cgroups hierarchy should be
+ * guaranteed.  All the fields are protected by the queue lock of the
+ * containing bfqd.
+ */
+struct bfq_entity {
+	struct rb_node rb_node;
+	struct bfq_weight_counter *weight_counter;
+
+	int on_st;
+
+	u64 finish;
+	u64 start;
+
+	struct rb_root *tree;
+
+	u64 min_start;
+
+	unsigned long service, budget;
+	unsigned short weight, new_weight;
+	unsigned short orig_weight;
+
+	struct bfq_entity *parent;
+
+	struct bfq_sched_data *my_sched_data;
+	struct bfq_sched_data *sched_data;
+
+	unsigned short ioprio, new_ioprio;
+	unsigned short ioprio_class, new_ioprio_class;
+
+	int ioprio_changed;
+};
+
+struct bfq_group;
+
+/**
+ * struct bfq_queue - leaf schedulable entity.
+ * @ref: reference counter.
+ * @bfqd: parent bfq_data.
+ * @new_bfqq: shared bfq_queue if queue is cooperating with
+ *           one or more other queues.
+ * @pos_node: request-position tree member (see bfq_data's @rq_pos_tree).
+ * @pos_root: request-position tree root (see bfq_data's @rq_pos_tree).
+ * @sort_list: sorted list of pending requests.
+ * @next_rq: if fifo isn't expired, next request to serve.
+ * @queued: nr of requests queued in @sort_list.
+ * @allocated: currently allocated requests.
+ * @meta_pending: pending metadata requests.
+ * @fifo: fifo list of requests in sort_list.
+ * @entity: entity representing this queue in the scheduler.
+ * @max_budget: maximum budget allowed from the feedback mechanism.
+ * @budget_timeout: budget expiration (in jiffies).
+ * @dispatched: number of requests on the dispatch list or inside driver.
+ * @flags: status flags.
+ * @bfqq_list: node for active/idle bfqq list inside our bfqd.
+ * @burst_list_node: node for the device's burst list.
+ * @seek_samples: number of seeks sampled
+ * @seek_total: sum of the distances of the seeks sampled
+ * @seek_mean: mean seek distance
+ * @last_request_pos: position of the last request enqueued
+ * @requests_within_timer: number of consecutive pairs of request completion
+ *                         and arrival, such that the queue becomes idle
+ *                         after the completion, but the next request arrives
+ *                         within an idle time slice; used only if the queue's
+ *                         IO_bound has been cleared.
+ * @pid: pid of the process owning the queue, used for logging purposes.
+ * @last_wr_start_finish: start time of the current weight-raising period if
+ *                        the @bfq-queue is being weight-raised, otherwise
+ *                        finish time of the last weight-raising period
+ * @wr_cur_max_time: current max raising time for this queue
+ * @soft_rt_next_start: minimum time instant such that, only if a new
+ *                      request is enqueued after this time instant in an
+ *                      idle @bfq_queue with no outstanding requests, then
+ *                      the task associated with the queue it is deemed as
+ *                      soft real-time (see the comments to the function
+ *                      bfq_bfqq_softrt_next_start()).
+ * @last_idle_bklogged: time of the last transition of the @bfq_queue from
+ *                      idle to backlogged
+ * @service_from_backlogged: cumulative service received from the @bfq_queue
+ *                           since the last transition from idle to
+ *                           backlogged
+ *
+ * A bfq_queue is a leaf request queue; it can be associated with an io_context
+ * or more, if it is async or shared between cooperating processes. @cgroup
+ * holds a reference to the cgroup, to be sure that it does not disappear while
+ * a bfqq still references it (mostly to avoid races between request issuing and
+ * task migration followed by cgroup destruction).
+ * All the fields are protected by the queue lock of the containing bfqd.
+ */
+struct bfq_queue {
+	atomic_t ref;
+	struct bfq_data *bfqd;
+
+	/* fields for cooperating queues handling */
+	struct bfq_queue *new_bfqq;
+	struct rb_node pos_node;
+	struct rb_root *pos_root;
+
+	struct rb_root sort_list;
+	struct request *next_rq;
+	int queued[2];
+	int allocated[2];
+	int meta_pending;
+	struct list_head fifo;
+
+	struct bfq_entity entity;
+
+	unsigned long max_budget;
+	unsigned long budget_timeout;
+
+	int dispatched;
+
+	unsigned int flags;
+
+	struct list_head bfqq_list;
+
+	struct hlist_node burst_list_node;
+
+	unsigned int seek_samples;
+	u64 seek_total;
+	sector_t seek_mean;
+	sector_t last_request_pos;
+
+	unsigned int requests_within_timer;
+
+	pid_t pid;
+
+	/* weight-raising fields */
+	unsigned long wr_cur_max_time;
+	unsigned long soft_rt_next_start;
+	unsigned long last_wr_start_finish;
+	unsigned int wr_coeff;
+	unsigned long last_idle_bklogged;
+	unsigned long service_from_backlogged;
+};
+
+/**
+ * struct bfq_ttime - per process thinktime stats.
+ * @ttime_total: total process thinktime
+ * @ttime_samples: number of thinktime samples
+ * @ttime_mean: average process thinktime
+ */
+struct bfq_ttime {
+	unsigned long last_end_request;
+
+	unsigned long ttime_total;
+	unsigned long ttime_samples;
+	unsigned long ttime_mean;
+};
+
+/**
+ * struct bfq_io_cq - per (request_queue, io_context) structure.
+ * @icq: associated io_cq structure
+ * @bfqq: array of two process queues, the sync and the async
+ * @ttime: associated @bfq_ttime struct
+ */
+struct bfq_io_cq {
+	struct io_cq icq; /* must be the first member */
+	struct bfq_queue *bfqq[2];
+	struct bfq_ttime ttime;
+	int ioprio;
+};
+
+enum bfq_device_speed {
+	BFQ_BFQD_FAST,
+	BFQ_BFQD_SLOW,
+};
+
+/**
+ * struct bfq_data - per device data structure.
+ * @queue: request queue for the managed device.
+ * @root_group: root bfq_group for the device.
+ * @rq_pos_tree: rbtree sorted by next_request position, used when
+ *               determining if two or more queues have interleaving
+ *               requests (see bfq_close_cooperator()).
+ * @active_numerous_groups: number of bfq_groups containing more than one
+ *                          active @bfq_entity.
+ * @queue_weights_tree: rbtree of weight counters of @bfq_queues, sorted by
+ *                      weight. Used to keep track of whether all @bfq_queues
+ *                     have the same weight. The tree contains one counter
+ *                     for each distinct weight associated to some active
+ *                     and not weight-raised @bfq_queue (see the comments to
+ *                      the functions bfq_weights_tree_[add|remove] for
+ *                     further details).
+ * @group_weights_tree: rbtree of non-queue @bfq_entity weight counters, sorted
+ *                      by weight. Used to keep track of whether all
+ *                     @bfq_groups have the same weight. The tree contains
+ *                     one counter for each distinct weight associated to
+ *                     some active @bfq_group (see the comments to the
+ *                     functions bfq_weights_tree_[add|remove] for further
+ *                     details).
+ * @busy_queues: number of bfq_queues containing requests (including the
+ *		 queue in service, even if it is idling).
+ * @busy_in_flight_queues: number of @bfq_queues containing pending or
+ *                         in-flight requests, plus the @bfq_queue in
+ *                         service, even if idle but waiting for the
+ *                         possible arrival of its next sync request. This
+ *                         field is updated only if the device is rotational,
+ *                         but used only if the device is also NCQ-capable.
+ *                         The reason why the field is updated also for non-
+ *                         NCQ-capable rotational devices is related to the
+ *                         fact that the value of @hw_tag may be set also
+ *                         later than when busy_in_flight_queues may need to
+ *                         be incremented for the first time(s). Taking also
+ *                         this possibility into account, to avoid unbalanced
+ *                         increments/decrements, would imply more overhead
+ *                         than just updating busy_in_flight_queues
+ *                         regardless of the value of @hw_tag.
+ * @const_seeky_busy_in_flight_queues: number of constantly-seeky @bfq_queues
+ *                                     (that is, seeky queues that expired
+ *                                     for budget timeout at least once)
+ *                                     containing pending or in-flight
+ *                                     requests, including the in-service
+ *                                     @bfq_queue if constantly seeky. This
+ *                                     field is updated only if the device
+ *                                     is rotational, but used only if the
+ *                                     device is also NCQ-capable (see the
+ *                                     comments to @busy_in_flight_queues).
+ * @wr_busy_queues: number of weight-raised busy @bfq_queues.
+ * @queued: number of queued requests.
+ * @rq_in_driver: number of requests dispatched and waiting for completion.
+ * @sync_flight: number of sync requests in the driver.
+ * @max_rq_in_driver: max number of reqs in driver in the last
+ *                    @hw_tag_samples completed requests.
+ * @hw_tag_samples: nr of samples used to calculate hw_tag.
+ * @hw_tag: flag set to one if the driver is showing a queueing behavior.
+ * @budgets_assigned: number of budgets assigned.
+ * @idle_slice_timer: timer set when idling for the next sequential request
+ *                    from the queue in service.
+ * @unplug_work: delayed work to restart dispatching on the request queue.
+ * @in_service_queue: bfq_queue in service.
+ * @in_service_bic: bfq_io_cq (bic) associated with the @in_service_queue.
+ * @last_position: on-disk position of the last served request.
+ * @last_budget_start: beginning of the last budget.
+ * @last_idling_start: beginning of the last idle slice.
+ * @peak_rate: peak transfer rate observed for a budget.
+ * @peak_rate_samples: number of samples used to calculate @peak_rate.
+ * @bfq_max_budget: maximum budget allotted to a bfq_queue before
+ *                  rescheduling.
+ * @group_list: list of all the bfq_groups active on the device.
+ * @active_list: list of all the bfq_queues active on the device.
+ * @idle_list: list of all the bfq_queues idle on the device.
+ * @bfq_quantum: max number of requests dispatched per dispatch round.
+ * @bfq_fifo_expire: timeout for async/sync requests; when it expires
+ *                   requests are served in fifo order.
+ * @bfq_back_penalty: weight of backward seeks wrt forward ones.
+ * @bfq_back_max: maximum allowed backward seek.
+ * @bfq_slice_idle: maximum idling time.
+ * @bfq_user_max_budget: user-configured max budget value
+ *                       (0 for auto-tuning).
+ * @bfq_max_budget_async_rq: maximum budget (in nr of requests) allotted to
+ *                           async queues.
+ * @bfq_timeout: timeout for bfq_queues to consume their budget; used to
+ *               to prevent seeky queues to impose long latencies to well
+ *               behaved ones (this also implies that seeky queues cannot
+ *               receive guarantees in the service domain; after a timeout
+ *               they are charged for the whole allocated budget, to try
+ *               to preserve a behavior reasonably fair among them, but
+ *               without service-domain guarantees).
+ * @bfq_coop_thresh: number of queue merges after which a @bfq_queue is
+ *                   no more granted any weight-raising.
+ * @bfq_failed_cooperations: number of consecutive failed cooperation
+ *                           chances after which weight-raising is restored
+ *                           to a queue subject to more than bfq_coop_thresh
+ *                           queue merges.
+ * @bfq_requests_within_timer: number of consecutive requests that must be
+ *                             issued within the idle time slice to set
+ *                             again idling to a queue which was marked as
+ *                             non-I/O-bound (see the definition of the
+ *                             IO_bound flag for further details).
+ * @last_ins_in_burst: last time at which a queue entered the current
+ *                     burst of queues being activated shortly after
+ *                     each other; for more details about this and the
+ *                     following parameters related to a burst of
+ *                     activations, see the comments to the function
+ *                     @bfq_handle_burst.
+ * @bfq_burst_interval: reference time interval used to decide whether a
+ *                      queue has been activated shortly after
+ *                      @last_ins_in_burst.
+ * @burst_size: number of queues in the current burst of queue activations.
+ * @bfq_large_burst_thresh: maximum burst size above which the current
+ * 			    queue-activation burst is deemed as 'large'.
+ * @large_burst: true if a large queue-activation burst is in progress.
+ * @burst_list: head of the burst list (as for the above fields, more details
+ * 		in the comments to the function bfq_handle_burst).
+ * @low_latency: if set to true, low-latency heuristics are enabled.
+ * @bfq_wr_coeff: maximum factor by which the weight of a weight-raised
+ *                queue is multiplied.
+ * @bfq_wr_max_time: maximum duration of a weight-raising period (jiffies).
+ * @bfq_wr_rt_max_time: maximum duration for soft real-time processes.
+ * @bfq_wr_min_idle_time: minimum idle period after which weight-raising
+ *			  may be reactivated for a queue (in jiffies).
+ * @bfq_wr_min_inter_arr_async: minimum period between request arrivals
+ *				after which weight-raising may be
+ *				reactivated for an already busy queue
+ *				(in jiffies).
+ * @bfq_wr_max_softrt_rate: max service-rate for a soft real-time queue,
+ *			    sectors per seconds.
+ * @RT_prod: cached value of the product R*T used for computing the maximum
+ *	     duration of the weight raising automatically.
+ * @device_speed: device-speed class for the low-latency heuristic.
+ * @oom_bfqq: fallback dummy bfqq for extreme OOM conditions.
+ *
+ * All the fields are protected by the @queue lock.
+ */
+struct bfq_data {
+	struct request_queue *queue;
+
+	struct bfq_group *root_group;
+	struct rb_root rq_pos_tree;
+
+#ifdef CONFIG_CGROUP_BFQIO
+	int active_numerous_groups;
+#endif
+
+	struct rb_root queue_weights_tree;
+	struct rb_root group_weights_tree;
+
+	int busy_queues;
+	int busy_in_flight_queues;
+	int const_seeky_busy_in_flight_queues;
+	int wr_busy_queues;
+	int queued;
+	int rq_in_driver;
+	int sync_flight;
+
+	int max_rq_in_driver;
+	int hw_tag_samples;
+	int hw_tag;
+
+	int budgets_assigned;
+
+	struct timer_list idle_slice_timer;
+	struct work_struct unplug_work;
+
+	struct bfq_queue *in_service_queue;
+	struct bfq_io_cq *in_service_bic;
+
+	sector_t last_position;
+
+	ktime_t last_budget_start;
+	ktime_t last_idling_start;
+	int peak_rate_samples;
+	u64 peak_rate;
+	unsigned long bfq_max_budget;
+
+	struct hlist_head group_list;
+	struct list_head active_list;
+	struct list_head idle_list;
+
+	unsigned int bfq_quantum;
+	unsigned int bfq_fifo_expire[2];
+	unsigned int bfq_back_penalty;
+	unsigned int bfq_back_max;
+	unsigned int bfq_slice_idle;
+	u64 bfq_class_idle_last_service;
+
+	unsigned int bfq_user_max_budget;
+	unsigned int bfq_max_budget_async_rq;
+	unsigned int bfq_timeout[2];
+
+	unsigned int bfq_coop_thresh;
+	unsigned int bfq_failed_cooperations;
+	unsigned int bfq_requests_within_timer;
+
+	unsigned long last_ins_in_burst;
+	unsigned long bfq_burst_interval;
+	int burst_size;
+	unsigned long bfq_large_burst_thresh;
+	bool large_burst;
+	struct hlist_head burst_list;
+
+	bool low_latency;
+
+	/* parameters of the low_latency heuristics */
+	unsigned int bfq_wr_coeff;
+	unsigned int bfq_wr_max_time;
+	unsigned int bfq_wr_rt_max_time;
+	unsigned int bfq_wr_min_idle_time;
+	unsigned long bfq_wr_min_inter_arr_async;
+	unsigned int bfq_wr_max_softrt_rate;
+	u64 RT_prod;
+	enum bfq_device_speed device_speed;
+
+	struct bfq_queue oom_bfqq;
+};
+
+enum bfqq_state_flags {
+	BFQ_BFQQ_FLAG_busy = 0,		/* has requests or is in service */
+	BFQ_BFQQ_FLAG_wait_request,	/* waiting for a request */
+	BFQ_BFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
+	BFQ_BFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
+	BFQ_BFQQ_FLAG_idle_window,	/* slice idling enabled */
+	BFQ_BFQQ_FLAG_prio_changed,	/* task priority has changed */
+	BFQ_BFQQ_FLAG_sync,		/* synchronous queue */
+	BFQ_BFQQ_FLAG_budget_new,	/* no completion with this budget */
+	BFQ_BFQQ_FLAG_IO_bound,         /*
+					 * bfqq has timed-out at least once
+					 * having consumed at most 2/10 of
+					 * its budget
+					 */
+	BFQ_BFQQ_FLAG_in_large_burst,	/*
+					 * bfqq activated in a large burst,
+					 * see comments to bfq_handle_burst.
+					 */
+	BFQ_BFQQ_FLAG_constantly_seeky,	/*
+					 * bfqq has proved to be slow and
+					 * seeky until budget timeout
+					 */
+	BFQ_BFQQ_FLAG_softrt_update,    /*
+					 * may need softrt-next-start
+					 * update
+					 */
+	BFQ_BFQQ_FLAG_coop,		/* bfqq is shared */
+	BFQ_BFQQ_FLAG_split_coop,	/* shared bfqq will be splitted */
+};
+
+#define BFQ_BFQQ_FNS(name)						\
+static inline void bfq_mark_bfqq_##name(struct bfq_queue *bfqq)		\
+{									\
+	(bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name);			\
+}									\
+static inline void bfq_clear_bfqq_##name(struct bfq_queue *bfqq)	\
+{									\
+	(bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name);			\
+}									\
+static inline int bfq_bfqq_##name(const struct bfq_queue *bfqq)		\
+{									\
+	return ((bfqq)->flags & (1 << BFQ_BFQQ_FLAG_##name)) != 0;	\
+}
+
+BFQ_BFQQ_FNS(busy);
+BFQ_BFQQ_FNS(wait_request);
+BFQ_BFQQ_FNS(must_alloc);
+BFQ_BFQQ_FNS(fifo_expire);
+BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(prio_changed);
+BFQ_BFQQ_FNS(sync);
+BFQ_BFQQ_FNS(budget_new);
+BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
+BFQ_BFQQ_FNS(constantly_seeky);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
+BFQ_BFQQ_FNS(softrt_update);
+#undef BFQ_BFQQ_FNS
+
+/* Logging facilities. */
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \
+	blk_add_trace_msg((bfqd)->queue, "bfq%d " fmt, (bfqq)->pid, ##args)
+
+#define bfq_log(bfqd, fmt, args...) \
+	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
+
+/* Expiration reasons. */
+enum bfqq_expiration {
+	BFQ_BFQQ_TOO_IDLE = 0,		/*
+					 * queue has been idling for
+					 * too long
+					 */
+	BFQ_BFQQ_BUDGET_TIMEOUT,	/* budget took too long to be used */
+	BFQ_BFQQ_BUDGET_EXHAUSTED,	/* budget consumed */
+	BFQ_BFQQ_NO_MORE_REQUESTS,	/* the queue has no more requests */
+};
+
+#ifdef CONFIG_CGROUP_BFQIO
+/**
+ * struct bfq_group - per (device, cgroup) data structure.
+ * @entity: schedulable entity to insert into the parent group sched_data.
+ * @sched_data: own sched_data, to contain child entities (they may be
+ *              both bfq_queues and bfq_groups).
+ * @group_node: node to be inserted into the bfqio_cgroup->group_data
+ *              list of the containing cgroup's bfqio_cgroup.
+ * @bfqd_node: node to be inserted into the @bfqd->group_list list
+ *             of the groups active on the same device; used for cleanup.
+ * @bfqd: the bfq_data for the device this group acts upon.
+ * @async_bfqq: array of async queues for all the tasks belonging to
+ *              the group, one queue per ioprio value per ioprio_class,
+ *              except for the idle class that has only one queue.
+ * @async_idle_bfqq: async queue for the idle class (ioprio is ignored).
+ * @my_entity: pointer to @entity, %NULL for the toplevel group; used
+ *             to avoid too many special cases during group creation/
+ *             migration.
+ * @active_entities: number of active entities belonging to the group;
+ *                   unused for the root group. Used to know whether there
+ *                   are groups with more than one active @bfq_entity
+ *                   (see the comments to the function
+ *                   bfq_bfqq_must_not_expire()).
+ *
+ * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup
+ * there is a set of bfq_groups, each one collecting the lower-level
+ * entities belonging to the group that are acting on the same device.
+ *
+ * Locking works as follows:
+ *    o @group_node is protected by the bfqio_cgroup lock, and is accessed
+ *      via RCU from its readers.
+ *    o @bfqd is protected by the queue lock, RCU is used to access it
+ *      from the readers.
+ *    o All the other fields are protected by the @bfqd queue lock.
+ */
+struct bfq_group {
+	struct bfq_entity entity;
+	struct bfq_sched_data sched_data;
+
+	struct hlist_node group_node;
+	struct hlist_node bfqd_node;
+
+	void *bfqd;
+
+	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
+	struct bfq_queue *async_idle_bfqq;
+
+	struct bfq_entity *my_entity;
+
+	int active_entities;
+};
+
+/**
+ * struct bfqio_cgroup - bfq cgroup data structure.
+ * @css: subsystem state for bfq in the containing cgroup.
+ * @online: flag marked when the subsystem is inserted.
+ * @weight: cgroup weight.
+ * @ioprio: cgroup ioprio.
+ * @ioprio_class: cgroup ioprio_class.
+ * @lock: spinlock that protects @ioprio, @ioprio_class and @group_data.
+ * @group_data: list containing the bfq_group belonging to this cgroup.
+ *
+ * @group_data is accessed using RCU, with @lock protecting the updates,
+ * @ioprio and @ioprio_class are protected by @lock.
+ */
+struct bfqio_cgroup {
+	struct cgroup_subsys_state css;
+	bool online;
+
+	unsigned short weight, ioprio, ioprio_class;
+
+	spinlock_t lock;
+	struct hlist_head group_data;
+};
+#else
+struct bfq_group {
+	struct bfq_sched_data sched_data;
+
+	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
+	struct bfq_queue *async_idle_bfqq;
+};
+#endif
+
+static inline struct bfq_service_tree *
+bfq_entity_service_tree(struct bfq_entity *entity)
+{
+	struct bfq_sched_data *sched_data = entity->sched_data;
+	unsigned int idx = entity->ioprio_class - 1;
+
+	BUG_ON(idx >= BFQ_IOPRIO_CLASSES);
+	BUG_ON(sched_data == NULL);
+
+	return sched_data->service_tree + idx;
+}
+
+static inline struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic,
+					    bool is_sync)
+{
+	return bic->bfqq[is_sync];
+}
+
+static inline void bic_set_bfqq(struct bfq_io_cq *bic,
+				struct bfq_queue *bfqq, bool is_sync)
+{
+	bic->bfqq[is_sync] = bfqq;
+}
+
+static inline struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
+{
+	return bic->icq.q->elevator->elevator_data;
+}
+
+/**
+ * bfq_get_bfqd_locked - get a lock to a bfqd using a RCU protected pointer.
+ * @ptr: a pointer to a bfqd.
+ * @flags: storage for the flags to be saved.
+ *
+ * This function allows bfqg->bfqd to be protected by the
+ * queue lock of the bfqd they reference; the pointer is dereferenced
+ * under RCU, so the storage for bfqd is assured to be safe as long
+ * as the RCU read side critical section does not end.  After the
+ * bfqd->queue->queue_lock is taken the pointer is rechecked, to be
+ * sure that no other writer accessed it.  If we raced with a writer,
+ * the function returns NULL, with the queue unlocked, otherwise it
+ * returns the dereferenced pointer, with the queue locked.
+ */
+static inline struct bfq_data *bfq_get_bfqd_locked(void **ptr,
+						   unsigned long *flags)
+{
+	struct bfq_data *bfqd;
+
+	rcu_read_lock();
+	bfqd = rcu_dereference(*(struct bfq_data **)ptr);
+
+	if (bfqd != NULL) {
+		spin_lock_irqsave(bfqd->queue->queue_lock, *flags);
+		if (*ptr == bfqd)
+			goto out;
+		spin_unlock_irqrestore(bfqd->queue->queue_lock, *flags);
+	}
+
+	bfqd = NULL;
+out:
+	rcu_read_unlock();
+	return bfqd;
+}
+
+static inline void bfq_put_bfqd_unlock(struct bfq_data *bfqd,
+				       unsigned long *flags)
+{
+	spin_unlock_irqrestore(bfqd->queue->queue_lock, *flags);
+}
+
+static void bfq_changed_ioprio(struct bfq_io_cq *bic);
+static void bfq_put_queue(struct bfq_queue *bfqq);
+static void bfq_dispatch_insert(struct request_queue *q, struct request *rq);
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+				       struct bfq_group *bfqg, int is_sync,
+				       struct bfq_io_cq *bic, gfp_t gfp_mask);
+static void bfq_end_wr_async_queues(struct bfq_data *bfqd,
+				    struct bfq_group *bfqg);
+static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+
+#endif /* _BFQ_H */
-- 
2.1.0