cfq-iosched.c

	return dispatched;
}

static int
cfq_dispatch_requests(request_queue_t *q, int force)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct cfq_queue *cfqq, *prev_cfqq;
	int dispatched;

	if (!cfqd->busy_queues)
		return 0;

	if (unlikely(force))
		return cfq_forced_dispatch(cfqd);

	dispatched = 0;
	prev_cfqq = NULL;
	while ((cfqq = cfq_select_queue(cfqd)) != NULL) {
		int max_dispatch;

		/*
		 * Don't repeat dispatch from the previous queue.
		 */
		if (prev_cfqq == cfqq)
			break;

		cfq_clear_cfqq_must_dispatch(cfqq);
		cfq_clear_cfqq_wait_request(cfqq);
		del_timer(&cfqd->idle_slice_timer);

		max_dispatch = cfqd->cfq_quantum;
		if (cfq_class_idle(cfqq))
			max_dispatch = 1;

		dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);

		/*
		 * If the dispatch cfqq has idling enabled and is still
		 * the active queue, break out.
		 */
		if (cfq_cfqq_idle_window(cfqq) && cfqd->active_queue)
			break;

		prev_cfqq = cfqq;
	}

	return dispatched;
}

/*
 * 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 cfq_put_queue(struct cfq_queue *cfqq)
{
	struct cfq_data *cfqd = cfqq->cfqd;

	BUG_ON(atomic_read(&cfqq->ref) <= 0);

	if (!atomic_dec_and_test(&cfqq->ref))
		return;

	BUG_ON(rb_first(&cfqq->sort_list));
	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
	BUG_ON(cfq_cfqq_on_rr(cfqq));

	if (unlikely(cfqd->active_queue == cfqq))
		__cfq_slice_expired(cfqd, cfqq, 0);

	/*
	 * it's on the empty list and still hashed
	 */
	list_del(&cfqq->cfq_list);
	hlist_del(&cfqq->cfq_hash);
	kmem_cache_free(cfq_pool, cfqq);
}

static struct cfq_queue *
__cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned int key, unsigned int prio,
		    const int hashval)
{
	struct hlist_head *hash_list = &cfqd->cfq_hash[hashval];
	struct hlist_node *entry;
	struct cfq_queue *__cfqq;

	hlist_for_each_entry(__cfqq, entry, hash_list, cfq_hash) {
		const unsigned short __p = IOPRIO_PRIO_VALUE(__cfqq->org_ioprio_class, __cfqq->org_ioprio);

		if (__cfqq->key == key && (__p == prio || !prio))
			return __cfqq;
	}

	return NULL;
}

static struct cfq_queue *
cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned int key, unsigned short prio)
{
	return __cfq_find_cfq_hash(cfqd, key, prio, hash_long(key, CFQ_QHASH_SHIFT));
}

static void cfq_free_io_context(struct io_context *ioc)
{
	struct cfq_io_context *__cic;
	struct rb_node *n;
	int freed = 0;

	while ((n = rb_first(&ioc->cic_root)) != NULL) {
		__cic = rb_entry(n, struct cfq_io_context, rb_node);
		rb_erase(&__cic->rb_node, &ioc->cic_root);
		kmem_cache_free(cfq_ioc_pool, __cic);
		freed++;
	}

	elv_ioc_count_mod(ioc_count, -freed);

	if (ioc_gone && !elv_ioc_count_read(ioc_count))
		complete(ioc_gone);
}

static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	if (unlikely(cfqq == cfqd->active_queue))
		__cfq_slice_expired(cfqd, cfqq, 0);

	cfq_put_queue(cfqq);
}

static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
					 struct cfq_io_context *cic)
{
	list_del_init(&cic->queue_list);
	smp_wmb();
	cic->key = NULL;

	if (cic->cfqq[ASYNC]) {
		cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]);
		cic->cfqq[ASYNC] = NULL;
	}

	if (cic->cfqq[SYNC]) {
		cfq_exit_cfqq(cfqd, cic->cfqq[SYNC]);
		cic->cfqq[SYNC] = NULL;
	}
}


/*
 * Called with interrupts disabled
 */
static void cfq_exit_single_io_context(struct cfq_io_context *cic)
{
	struct cfq_data *cfqd = cic->key;

	if (cfqd) {
		request_queue_t *q = cfqd->queue;

		spin_lock_irq(q->queue_lock);
		__cfq_exit_single_io_context(cfqd, cic);
		spin_unlock_irq(q->queue_lock);
	}
}

static void cfq_exit_io_context(struct io_context *ioc)
{
	struct cfq_io_context *__cic;
	struct rb_node *n;

	/*
	 * put the reference this task is holding to the various queues
	 */

	n = rb_first(&ioc->cic_root);
	while (n != NULL) {
		__cic = rb_entry(n, struct cfq_io_context, rb_node);

		cfq_exit_single_io_context(__cic);
		n = rb_next(n);
	}
}

static struct cfq_io_context *
cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
{
	struct cfq_io_context *cic;

	cic = kmem_cache_alloc_node(cfq_ioc_pool, gfp_mask, cfqd->queue->node);
	if (cic) {
		memset(cic, 0, sizeof(*cic));
		cic->last_end_request = jiffies;
		INIT_LIST_HEAD(&cic->queue_list);
		cic->dtor = cfq_free_io_context;
		cic->exit = cfq_exit_io_context;
		elv_ioc_count_inc(ioc_count);
	}

	return cic;
}

static void cfq_init_prio_data(struct cfq_queue *cfqq)
{
	struct task_struct *tsk = current;
	int ioprio_class;

	if (!cfq_cfqq_prio_changed(cfqq))
		return;

	ioprio_class = IOPRIO_PRIO_CLASS(tsk->ioprio);
	switch (ioprio_class) {
		default:
			printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
		case IOPRIO_CLASS_NONE:
			/*
			 * no prio set, place us in the middle of the BE classes
			 */
			cfqq->ioprio = task_nice_ioprio(tsk);
			cfqq->ioprio_class = IOPRIO_CLASS_BE;
			break;
		case IOPRIO_CLASS_RT:
			cfqq->ioprio = task_ioprio(tsk);
			cfqq->ioprio_class = IOPRIO_CLASS_RT;
			break;
		case IOPRIO_CLASS_BE:
			cfqq->ioprio = task_ioprio(tsk);
			cfqq->ioprio_class = IOPRIO_CLASS_BE;
			break;
		case IOPRIO_CLASS_IDLE:
			cfqq->ioprio_class = IOPRIO_CLASS_IDLE;
			cfqq->ioprio = 7;
			cfq_clear_cfqq_idle_window(cfqq);
			break;
	}

	/*
	 * keep track of original prio settings in case we have to temporarily
	 * elevate the priority of this queue
	 */
	cfqq->org_ioprio = cfqq->ioprio;
	cfqq->org_ioprio_class = cfqq->ioprio_class;

	cfq_resort_rr_list(cfqq, 0);
	cfq_clear_cfqq_prio_changed(cfqq);
}

static inline void changed_ioprio(struct cfq_io_context *cic)
{
	struct cfq_data *cfqd = cic->key;
	struct cfq_queue *cfqq;
	unsigned long flags;

	if (unlikely(!cfqd))
		return;

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);

	cfqq = cic->cfqq[ASYNC];
	if (cfqq) {
		struct cfq_queue *new_cfqq;
		new_cfqq = cfq_get_queue(cfqd, CFQ_KEY_ASYNC, cic->ioc->task,
					 GFP_ATOMIC);
		if (new_cfqq) {
			cic->cfqq[ASYNC] = new_cfqq;
			cfq_put_queue(cfqq);
		}
	}

	cfqq = cic->cfqq[SYNC];
	if (cfqq)
		cfq_mark_cfqq_prio_changed(cfqq);

	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

static void cfq_ioc_set_ioprio(struct io_context *ioc)
{
	struct cfq_io_context *cic;
	struct rb_node *n;

	ioc->ioprio_changed = 0;

	n = rb_first(&ioc->cic_root);
	while (n != NULL) {
		cic = rb_entry(n, struct cfq_io_context, rb_node);

		changed_ioprio(cic);
		n = rb_next(n);
	}
}

static struct cfq_queue *
cfq_get_queue(struct cfq_data *cfqd, unsigned int key, struct task_struct *tsk,
	      gfp_t gfp_mask)
{
	const int hashval = hash_long(key, CFQ_QHASH_SHIFT);
	struct cfq_queue *cfqq, *new_cfqq = NULL;
	unsigned short ioprio;

retry:
	ioprio = tsk->ioprio;
	cfqq = __cfq_find_cfq_hash(cfqd, key, ioprio, hashval);

	if (!cfqq) {
		if (new_cfqq) {
			cfqq = new_cfqq;
			new_cfqq = NULL;
		} else if (gfp_mask & __GFP_WAIT) {
			/*
			 * Inform the allocator of the fact that we will
			 * just repeat this allocation if it fails, to allow
			 * the allocator to do whatever it needs to attempt to
			 * free memory.
			 */
			spin_unlock_irq(cfqd->queue->queue_lock);
			new_cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask|__GFP_NOFAIL, cfqd->queue->node);
			spin_lock_irq(cfqd->queue->queue_lock);
			goto retry;
		} else {
			cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask, cfqd->queue->node);
			if (!cfqq)
				goto out;
		}

		memset(cfqq, 0, sizeof(*cfqq));

		INIT_HLIST_NODE(&cfqq->cfq_hash);
		INIT_LIST_HEAD(&cfqq->cfq_list);
		INIT_LIST_HEAD(&cfqq->fifo);

		cfqq->key = key;
		hlist_add_head(&cfqq->cfq_hash, &cfqd->cfq_hash[hashval]);
		atomic_set(&cfqq->ref, 0);
		cfqq->cfqd = cfqd;
		/*
		 * set ->slice_left to allow preemption for a new process
		 */
		cfqq->slice_left = 2 * cfqd->cfq_slice_idle;
		cfq_mark_cfqq_idle_window(cfqq);
		cfq_mark_cfqq_prio_changed(cfqq);
		cfq_mark_cfqq_queue_new(cfqq);
		cfq_init_prio_data(cfqq);
	}

	if (new_cfqq)
		kmem_cache_free(cfq_pool, new_cfqq);

	atomic_inc(&cfqq->ref);
out:
	WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq);
	return cfqq;
}

static void
cfq_drop_dead_cic(struct io_context *ioc, struct cfq_io_context *cic)
{
	WARN_ON(!list_empty(&cic->queue_list));
	rb_erase(&cic->rb_node, &ioc->cic_root);
	kmem_cache_free(cfq_ioc_pool, cic);
	elv_ioc_count_dec(ioc_count);
}

static struct cfq_io_context *
cfq_cic_rb_lookup(struct cfq_data *cfqd, struct io_context *ioc)
{
	struct rb_node *n;
	struct cfq_io_context *cic;
	void *k, *key = cfqd;

restart:
	n = ioc->cic_root.rb_node;
	while (n) {
		cic = rb_entry(n, struct cfq_io_context, rb_node);
		/* ->key must be copied to avoid race with cfq_exit_queue() */
		k = cic->key;
		if (unlikely(!k)) {
			cfq_drop_dead_cic(ioc, cic);
			goto restart;
		}

		if (key < k)
			n = n->rb_left;
		else if (key > k)
			n = n->rb_right;
		else
			return cic;
	}

	return NULL;
}

static inline void
cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc,
	     struct cfq_io_context *cic)
{
	struct rb_node **p;
	struct rb_node *parent;
	struct cfq_io_context *__cic;
	unsigned long flags;
	void *k;

	cic->ioc = ioc;
	cic->key = cfqd;

restart:
	parent = NULL;
	p = &ioc->cic_root.rb_node;
	while (*p) {
		parent = *p;
		__cic = rb_entry(parent, struct cfq_io_context, rb_node);
		/* ->key must be copied to avoid race with cfq_exit_queue() */
		k = __cic->key;
		if (unlikely(!k)) {
			cfq_drop_dead_cic(ioc, __cic);
			goto restart;
		}

		if (cic->key < k)
			p = &(*p)->rb_left;
		else if (cic->key > k)
			p = &(*p)->rb_right;
		else
			BUG();
	}

	rb_link_node(&cic->rb_node, parent, p);
	rb_insert_color(&cic->rb_node, &ioc->cic_root);

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
	list_add(&cic->queue_list, &cfqd->cic_list);
	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

/*
 * Setup general io context and cfq io context. There can be several cfq
 * io contexts per general io context, if this process is doing io to more
 * than one device managed by cfq.
 */
static struct cfq_io_context *
cfq_get_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
{
	struct io_context *ioc = NULL;
	struct cfq_io_context *cic;

	might_sleep_if(gfp_mask & __GFP_WAIT);

	ioc = get_io_context(gfp_mask, cfqd->queue->node);
	if (!ioc)
		return NULL;

	cic = cfq_cic_rb_lookup(cfqd, ioc);
	if (cic)
		goto out;

	cic = cfq_alloc_io_context(cfqd, gfp_mask);
	if (cic == NULL)
		goto err;

	cfq_cic_link(cfqd, ioc, cic);
out:
	smp_read_barrier_depends();
	if (unlikely(ioc->ioprio_changed))
		cfq_ioc_set_ioprio(ioc);

	return cic;
err:
	put_io_context(ioc);
	return NULL;
}

static void
cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_io_context *cic)
{
	unsigned long elapsed = jiffies - cic->last_end_request;
	unsigned long ttime = min(elapsed, 2UL * cfqd->cfq_slice_idle);

	cic->ttime_samples = (7*cic->ttime_samples + 256) / 8;
	cic->ttime_total = (7*cic->ttime_total + 256*ttime) / 8;
	cic->ttime_mean = (cic->ttime_total + 128) / cic->ttime_samples;
}

static void
cfq_update_io_seektime(struct cfq_io_context *cic, struct request *rq)
{
	sector_t sdist;
	u64 total;

	if (cic->last_request_pos < rq->sector)
		sdist = rq->sector - cic->last_request_pos;
	else
		sdist = cic->last_request_pos - rq->sector;

	/*
	 * Don't allow the seek distance to get too large from the
	 * odd fragment, pagein, etc
	 */
	if (cic->seek_samples <= 60) /* second&third seek */
		sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*1024);
	else
		sdist = min(sdist, (cic->seek_mean * 4)	+ 2*1024*64);

	cic->seek_samples = (7*cic->seek_samples + 256) / 8;
	cic->seek_total = (7*cic->seek_total + (u64)256*sdist) / 8;
	total = cic->seek_total + (cic->seek_samples/2);
	do_div(total, cic->seek_samples);
	cic->seek_mean = (sector_t)total;
}

/*
 * Disable idle window if the process thinks too long or seeks so much that
 * it doesn't matter
 */
static void
cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		       struct cfq_io_context *cic)
{
	int enable_idle = cfq_cfqq_idle_window(cfqq);

	if (!cic->ioc->task || !cfqd->cfq_slice_idle ||
	    (cfqd->hw_tag && CIC_SEEKY(cic)))
		enable_idle = 0;
	else if (sample_valid(cic->ttime_samples)) {
		if (cic->ttime_mean > cfqd->cfq_slice_idle)
			enable_idle = 0;
		else
			enable_idle = 1;
	}

	if (enable_idle)
		cfq_mark_cfqq_idle_window(cfqq);
	else
		cfq_clear_cfqq_idle_window(cfqq);
}


/*
 * Check if new_cfqq should preempt the currently active queue. Return 0 for
 * no or if we aren't sure, a 1 will cause a preempt.
 */
static int
cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
		   struct request *rq)
{
	struct cfq_queue *cfqq = cfqd->active_queue;

	if (cfq_class_idle(new_cfqq))
		return 0;

	if (!cfqq)
		return 0;

	if (cfq_class_idle(cfqq))
		return 1;
	if (!cfq_cfqq_wait_request(new_cfqq))
		return 0;
	/*
	 * if it doesn't have slice left, forget it
	 */
	if (new_cfqq->slice_left < cfqd->cfq_slice_idle)
		return 0;
	/*
	 * if the new request is sync, but the currently running queue is
	 * not, let the sync request have priority.
	 */
	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
		return 1;
	/*
	 * So both queues are sync. Let the new request get disk time if
	 * it's a metadata request and the current queue is doing regular IO.
	 */
	if (rq_is_meta(rq) && !cfqq->meta_pending)
		return 1;

	return 0;
}

/*
 * cfqq preempts the active queue. if we allowed preempt with no slice left,
 * let it have half of its nominal slice.
 */
static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	cfq_slice_expired(cfqd, 1);

	if (!cfqq->slice_left)
		cfqq->slice_left = cfq_prio_to_slice(cfqd, cfqq) / 2;

	/*
	 * Put the new queue at the front of the of the current list,
	 * so we know that it will be selected next.
	 */
	BUG_ON(!cfq_cfqq_on_rr(cfqq));
	list_move(&cfqq->cfq_list, &cfqd->cur_rr);

	cfqq->slice_end = cfqq->slice_left + jiffies;
}

/*
 * Called when a new fs request (rq) is added (to cfqq). Check if there's
 * something we should do about it
 */
static void
cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		struct request *rq)
{
	struct cfq_io_context *cic = RQ_CIC(rq);

	if (rq_is_meta(rq))
		cfqq->meta_pending++;

	/*
	 * check if this request is a better next-serve candidate)) {
	 */
	cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq);
	BUG_ON(!cfqq->next_rq);

	/*
	 * we never wait for an async request and we don't allow preemption
	 * of an async request. so just return early
	 */
	if (!rq_is_sync(rq)) {
		/*
		 * sync process issued an async request, if it's waiting
		 * then expire it and kick rq handling.
		 */
		if (cic == cfqd->active_cic &&
		    del_timer(&cfqd->idle_slice_timer)) {
			cfq_slice_expired(cfqd, 0);
			blk_start_queueing(cfqd->queue);
		}
		return;
	}

	cfq_update_io_thinktime(cfqd, cic);
	cfq_update_io_seektime(cic, rq);
	cfq_update_idle_window(cfqd, cfqq, cic);

	cic->last_request_pos = rq->sector + rq->nr_sectors;

	if (cfqq == cfqd->active_queue) {
		/*
		 * if we are waiting for a request for this queue, let it rip
		 * immediately and flag that we must not expire this queue
		 * just now
		 */
		if (cfq_cfqq_wait_request(cfqq)) {
			cfq_mark_cfqq_must_dispatch(cfqq);
			del_timer(&cfqd->idle_slice_timer);
			blk_start_queueing(cfqd->queue);
		}
	} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
		/*
		 * not the active queue - expire current slice if it is
		 * idle and has expired it's mean thinktime or this new queue
		 * has some old slice time left and is of higher priority
		 */
		cfq_preempt_queue(cfqd, cfqq);
		cfq_mark_cfqq_must_dispatch(cfqq);
		blk_start_queueing(cfqd->queue);
	}
}

static void cfq_insert_request(request_queue_t *q, struct request *rq)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct cfq_queue *cfqq = RQ_CFQQ(rq);

	cfq_init_prio_data(cfqq);

	cfq_add_rq_rb(rq);

	list_add_tail(&rq->queuelist, &cfqq->fifo);

	cfq_rq_enqueued(cfqd, cfqq, rq);
}

static void cfq_completed_request(request_queue_t *q, struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);
	struct cfq_data *cfqd = cfqq->cfqd;
	const int sync = rq_is_sync(rq);
	unsigned long now;

	now = jiffies;

	WARN_ON(!cfqd->rq_in_driver);
	WARN_ON(!cfqq->on_dispatch[sync]);
	cfqd->rq_in_driver--;
	cfqq->on_dispatch[sync]--;

	if (!cfq_class_idle(cfqq))
		cfqd->last_end_request = now;

	cfq_resort_rr_list(cfqq, 0);

	if (sync)
		RQ_CIC(rq)->last_end_request = now;

	/*
	 * If this is the active queue, check if it needs to be expired,
	 * or if we want to idle in case it has no pending requests.
	 */
	if (cfqd->active_queue == cfqq) {
		if (time_after(now, cfqq->slice_end))
			cfq_slice_expired(cfqd, 0);
		else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list)) {
			if (!cfq_arm_slice_timer(cfqd, cfqq))
				cfq_schedule_dispatch(cfqd);
		}
	}
}

/*
 * we temporarily boost lower priority queues if they are holding fs exclusive
 * resources. they are boosted to normal prio (CLASS_BE/4)
 */
static void cfq_prio_boost(struct cfq_queue *cfqq)
{
	const int ioprio_class = cfqq->ioprio_class;
	const int ioprio = cfqq->ioprio;

	if (has_fs_excl()) {
		/*
		 * boost idle prio on transactions that would lock out other
		 * users of the filesystem
		 */
		if (cfq_class_idle(cfqq))
			cfqq->ioprio_class = IOPRIO_CLASS_BE;
		if (cfqq->ioprio > IOPRIO_NORM)
			cfqq->ioprio = IOPRIO_NORM;
	} else {
		/*
		 * check if we need to unboost the queue
		 */
		if (cfqq->ioprio_class != cfqq->org_ioprio_class)
			cfqq->ioprio_class = cfqq->org_ioprio_class;
		if (cfqq->ioprio != cfqq->org_ioprio)
			cfqq->ioprio = cfqq->org_ioprio;
	}

	/*
	 * refile between round-robin lists if we moved the priority class
	 */
	if ((ioprio_class != cfqq->ioprio_class || ioprio != cfqq->ioprio))
		cfq_resort_rr_list(cfqq, 0);
}

static inline int __cfq_may_queue(struct cfq_queue *cfqq)
{
	if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) &&
	    !cfq_cfqq_must_alloc_slice(cfqq)) {
		cfq_mark_cfqq_must_alloc_slice(cfqq);
		return ELV_MQUEUE_MUST;
	}

	return ELV_MQUEUE_MAY;
}

static int cfq_may_queue(request_queue_t *q, int rw)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct task_struct *tsk = current;
	struct cfq_queue *cfqq;
	unsigned int key;

	key = cfq_queue_pid(tsk, rw, rw & REQ_RW_SYNC);

	/*
	 * 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
	 */
	cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
	if (cfqq) {
		cfq_init_prio_data(cfqq);
		cfq_prio_boost(cfqq);

		return __cfq_may_queue(cfqq);
	}

	return ELV_MQUEUE_MAY;
}

/*
 * queue lock held here
 */
static void cfq_put_request(struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);

	if (cfqq) {
		const int rw = rq_data_dir(rq);

		BUG_ON(!cfqq->allocated[rw]);
		cfqq->allocated[rw]--;

		put_io_context(RQ_CIC(rq)->ioc);

		rq->elevator_private = NULL;
		rq->elevator_private2 = NULL;

		cfq_put_queue(cfqq);
	}
}

/*
 * Allocate cfq data structures associated with this request.
 */
static int
cfq_set_request(request_queue_t *q, struct request *rq, gfp_t gfp_mask)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct task_struct *tsk = current;
	struct cfq_io_context *cic;
	const int rw = rq_data_dir(rq);
	const int is_sync = rq_is_sync(rq);
	pid_t key = cfq_queue_pid(tsk, rw, is_sync);
	struct cfq_queue *cfqq;
	unsigned long flags;

	might_sleep_if(gfp_mask & __GFP_WAIT);

	cic = cfq_get_io_context(cfqd, gfp_mask);

	spin_lock_irqsave(q->queue_lock, flags);

	if (!cic)
		goto queue_fail;

	if (!cic->cfqq[is_sync]) {
		cfqq = cfq_get_queue(cfqd, key, tsk, gfp_mask);
		if (!cfqq)
			goto queue_fail;

		cic->cfqq[is_sync] = cfqq;
	} else
		cfqq = cic->cfqq[is_sync];

	cfqq->allocated[rw]++;
	cfq_clear_cfqq_must_alloc(cfqq);
	atomic_inc(&cfqq->ref);

	spin_unlock_irqrestore(q->queue_lock, flags);

	rq->elevator_private = cic;
	rq->elevator_private2 = cfqq;
	return 0;

queue_fail:
	if (cic)
		put_io_context(cic->ioc);

	cfq_schedule_dispatch(cfqd);
	spin_unlock_irqrestore(q->queue_lock, flags);
	return 1;
}

static void cfq_kick_queue(struct work_struct *work)
{
	struct cfq_data *cfqd =
		container_of(work, struct cfq_data, unplug_work);
	request_queue_t *q = cfqd->queue;
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	blk_start_queueing(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}

/*
 * Timer running if the active_queue is currently idling inside its time slice
 */
static void cfq_idle_slice_timer(unsigned long data)
{
	struct cfq_data *cfqd = (struct cfq_data *) data;
	struct cfq_queue *cfqq;
	unsigned long flags;

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);

	if ((cfqq = cfqd->active_queue) != NULL) {
		unsigned long now = jiffies;

		/*
		 * expired
		 */
		if (time_after(now, cfqq->slice_end))
			goto expire;

		/*
		 * only expire and reinvoke request handler, if there are
		 * other queues with pending requests
		 */
		if (!cfqd->busy_queues)
			goto out_cont;

		/*
		 * not expired and it has a request pending, let it dispatch
		 */
		if (!RB_EMPTY_ROOT(&cfqq->sort_list)) {
			cfq_mark_cfqq_must_dispatch(cfqq);
			goto out_kick;
		}
	}
expire:
	cfq_slice_expired(cfqd, 0);
out_kick:
	cfq_schedule_dispatch(cfqd);
out_cont:
	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

/*
 * Timer running if an idle class queue is waiting for service
 */
static void cfq_idle_class_timer(unsigned long data)
{
	struct cfq_data *cfqd = (struct cfq_data *) data;
	unsigned long flags, end;

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);

	/*
	 * race with a non-idle queue, reset timer
	 */
	end = cfqd->last_end_request + CFQ_IDLE_GRACE;
	if (!time_after_eq(jiffies, end))
		mod_timer(&cfqd->idle_class_timer, end);
	else
		cfq_schedule_dispatch(cfqd);

	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
{
	del_timer_sync(&cfqd->idle_slice_timer);
	del_timer_sync(&cfqd->idle_class_timer);
	blk_sync_queue(cfqd->queue);
}

static void cfq_exit_queue(elevator_t *e)
{
	struct cfq_data *cfqd = e->elevator_data;
	request_queue_t *q = cfqd->queue;

	cfq_shutdown_timer_wq(cfqd);

	spin_lock_irq(q->queue_lock);

	if (cfqd->active_queue)
		__cfq_slice_expired(cfqd, cfqd->active_queue, 0);

	while (!list_empty(&cfqd->cic_list)) {
		struct cfq_io_context *cic = list_entry(cfqd->cic_list.next,
							struct cfq_io_context,
							queue_list);

		__cfq_exit_single_io_context(cfqd, cic);
	}

	spin_unlock_irq(q->queue_lock);

	cfq_shutdown_timer_wq(cfqd);

	kfree(cfqd->cfq_hash);
	kfree(cfqd);
}

static void *cfq_init_queue(request_queue_t *q)
{
	struct cfq_data *cfqd;
	int i;

	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL, q->node);
	if (!cfqd)
		return NULL;

	memset(cfqd, 0, sizeof(*cfqd));

	for (i = 0; i < CFQ_PRIO_LISTS; i++)
		INIT_LIST_HEAD(&cfqd->rr_list[i]);

	INIT_LIST_HEAD(&cfqd->busy_rr);
	INIT_LIST_HEAD(&cfqd->cur_rr);
	INIT_LIST_HEAD(&cfqd->idle_rr);
	INIT_LIST_HEAD(&cfqd->cic_list);

	cfqd->cfq_hash = kmalloc_node(sizeof(struct hlist_head) * CFQ_QHASH_ENTRIES, GFP_KERNEL, q->node);
	if (!cfqd->cfq_hash)
		goto out_free;

	for (i = 0; i < CFQ_QHASH_ENTRIES; i++)
		INIT_HLIST_HEAD(&cfqd->cfq_hash[i]);

	cfqd->queue = q;

	init_timer(&cfqd->idle_slice_timer);