bfq-iosched.c

	INIT_LIST_HEAD(&bfqq->fifo);

	bfqq->ref = 0;
	bfqq->bfqd = bfqd;

	if (bic)
		bfq_set_next_ioprio_data(bfqq, bic);

	if (is_sync) {
		if (!bfq_class_idle(bfqq))
			bfq_mark_bfqq_idle_window(bfqq);
		bfq_mark_bfqq_sync(bfqq);
	} else
		bfq_clear_bfqq_sync(bfqq);

	/* set end request to minus infinity from now */
	bfqq->ttime.last_end_request = ktime_get_ns() + 1;

	bfq_mark_bfqq_IO_bound(bfqq);

	bfqq->pid = pid;

	/* Tentative initial value to trade off between thr and lat */
	bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
	bfqq->budget_timeout = bfq_smallest_from_now();

	/* first request is almost certainly seeky */
	bfqq->seek_history = 1;
}

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:
		return NULL;
	}
}

static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
				       struct bio *bio, bool is_sync,
				       struct bfq_io_cq *bic)
{
	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;
	struct bfq_group *bfqg;

	rcu_read_lock();

	bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio));
	if (!bfqg) {
		bfqq = &bfqd->oom_bfqq;
		goto out;
	}

	if (!is_sync) {
		async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
						  ioprio);
		bfqq = *async_bfqq;
		if (bfqq)
			goto out;
	}

	bfqq = kmem_cache_alloc_node(bfq_pool,
				     GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN,
				     bfqd->queue->node);

	if (bfqq) {
		bfq_init_bfqq(bfqd, bfqq, bic, current->pid,
			      is_sync);
		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");
		goto out;
	}

	/*
	 * Pin the queue now that it's allocated, scheduler exit will
	 * prune it.
	 */
	if (async_bfqq) {
		bfqq->ref++; /*
			      * Extra group reference, w.r.t. sync
			      * queue. This extra reference is removed
			      * only if bfqq->bfqg disappears, to
			      * guarantee that this queue is not freed
			      * until its group goes away.
			      */
		bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
			     bfqq, bfqq->ref);
		*async_bfqq = bfqq;
	}

out:
	bfqq->ref++; /* get a process reference to this queue */
	bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, bfqq->ref);
	rcu_read_unlock();
	return bfqq;
}

static void bfq_update_io_thinktime(struct bfq_data *bfqd,
				    struct bfq_queue *bfqq)
{
	struct bfq_ttime *ttime = &bfqq->ttime;
	u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;

	elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);

	ttime->ttime_samples = (7*bfqq->ttime.ttime_samples + 256) / 8;
	ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed,  8);
	ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
				     ttime->ttime_samples);
}

static void
bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
		       struct request *rq)
{
	sector_t sdist = 0;

	if (bfqq->last_request_pos) {
		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);
	}

	bfqq->seek_history <<= 1;
	bfqq->seek_history |= sdist > BFQQ_SEEK_THR &&
		(!blk_queue_nonrot(bfqd->queue) ||
		 blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT);
}

/*
 * 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)))
		enable_idle = 0;
	else if (bfq_sample_valid(bfqq->ttime.ttime_samples)) {
		if (bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle)
			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, bfqq);
	bfq_update_io_seektime(bfqd, bfqq, rq);
	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)",
		     bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq));

	bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);

	if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
		bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
				 blk_rq_sectors(rq) < 32;
		bool 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 device is being idled to wait
		 * for a new request from the in-service queue, we
		 * avoid unplugging the device and committing the
		 * device 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);
		hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
		bfqg_stats_update_idle_time(bfqq_group(bfqq));

		/*
		 * 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, false,
					BFQQE_BUDGET_TIMEOUT);
	}
}

static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq);

	bfq_add_request(rq);

	rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
	list_add_tail(&rq->queuelist, &bfqq->fifo);

	bfq_rq_enqueued(bfqd, bfqq, rq);
}

static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
			       bool at_head)
{
	struct request_queue *q = hctx->queue;
	struct bfq_data *bfqd = q->elevator->elevator_data;

	spin_lock_irq(&bfqd->lock);
	if (blk_mq_sched_try_insert_merge(q, rq)) {
		spin_unlock_irq(&bfqd->lock);
		return;
	}

	spin_unlock_irq(&bfqd->lock);

	blk_mq_sched_request_inserted(rq);

	spin_lock_irq(&bfqd->lock);
	if (at_head || blk_rq_is_passthrough(rq)) {
		if (at_head)
			list_add(&rq->queuelist, &bfqd->dispatch);
		else
			list_add_tail(&rq->queuelist, &bfqd->dispatch);
	} else {
		__bfq_insert_request(bfqd, rq);

		if (rq_mergeable(rq)) {
			elv_rqhash_add(q, rq);
			if (!q->last_merge)
				q->last_merge = rq;
		}
	}

	spin_unlock_irq(&bfqd->lock);
}

static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
				struct list_head *list, bool at_head)
{
	while (!list_empty(list)) {
		struct request *rq;

		rq = list_first_entry(list, struct request, queuelist);
		list_del_init(&rq->queuelist);
		bfq_insert_request(hctx, rq, at_head);
	}
}

static void bfq_update_hw_tag(struct bfq_data *bfqd)
{
	bfqd->max_rq_in_driver = max_t(int, 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 bfq_queue *bfqq, struct bfq_data *bfqd)
{
	bfq_update_hw_tag(bfqd);

	bfqd->rq_in_driver--;
	bfqq->dispatched--;

	bfqq->ttime.last_end_request = ktime_get_ns();

	/*
	 * 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);
			return;
		} else if (bfq_may_expire_for_budg_timeout(bfqq))
			bfq_bfqq_expire(bfqd, bfqq, false,
					BFQQE_BUDGET_TIMEOUT);
		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
			 (bfqq->dispatched == 0 ||
			  !bfq_bfqq_may_idle(bfqq)))
			bfq_bfqq_expire(bfqd, bfqq, false,
					BFQQE_NO_MORE_REQUESTS);
	}
}

static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
{
	bfqq->allocated--;

	bfq_put_queue(bfqq);
}

static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq);
	struct bfq_data *bfqd = bfqq->bfqd;

	if (rq->rq_flags & RQF_STARTED)
		bfqg_stats_update_completion(bfqq_group(bfqq),
					     rq_start_time_ns(rq),
					     rq_io_start_time_ns(rq),
					     rq->cmd_flags);

	if (likely(rq->rq_flags & RQF_STARTED)) {
		unsigned long flags;

		spin_lock_irqsave(&bfqd->lock, flags);

		bfq_completed_request(bfqq, bfqd);
		bfq_put_rq_priv_body(bfqq);

		spin_unlock_irqrestore(&bfqd->lock, flags);
	} else {
		/*
		 * Request rq may be still/already in the scheduler,
		 * in which case we need to remove it. And we cannot
		 * defer such a check and removal, to avoid
		 * inconsistencies in the time interval from the end
		 * of this function to the start of the deferred work.
		 * This situation seems to occur only in process
		 * context, as a consequence of a merge. In the
		 * current version of the code, this implies that the
		 * lock is held.
		 */

		if (!RB_EMPTY_NODE(&rq->rb_node))
			bfq_remove_request(q, rq);
		bfq_put_rq_priv_body(bfqq);
	}

	rq->elv.priv[0] = NULL;
	rq->elv.priv[1] = NULL;
}

/*
 * Allocate bfq data structures associated with this request.
 */
static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
			      struct bio *bio)
{
	struct bfq_data *bfqd = q->elevator->elevator_data;
	struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
	const int is_sync = rq_is_sync(rq);
	struct bfq_queue *bfqq;

	spin_lock_irq(&bfqd->lock);

	bfq_check_ioprio_change(bic, bio);

	if (!bic)
		goto queue_fail;

	bfq_bic_update_cgroup(bic, bio);

	bfqq = bic_to_bfqq(bic, is_sync);
	if (!bfqq || bfqq == &bfqd->oom_bfqq) {
		if (bfqq)
			bfq_put_queue(bfqq);
		bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
		bic_set_bfqq(bic, bfqq, is_sync);
	}

	bfqq->allocated++;
	bfqq->ref++;
	bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d",
		     rq, bfqq, bfqq->ref);

	rq->elv.priv[0] = bic;
	rq->elv.priv[1] = bfqq;

	spin_unlock_irq(&bfqd->lock);

	return 0;

queue_fail:
	spin_unlock_irq(&bfqd->lock);

	return 1;
}

static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
{
	struct bfq_data *bfqd = bfqq->bfqd;
	enum bfqq_expiration reason;
	unsigned long flags;

	spin_lock_irqsave(&bfqd->lock, flags);
	bfq_clear_bfqq_wait_request(bfqq);

	if (bfqq != bfqd->in_service_queue) {
		spin_unlock_irqrestore(&bfqd->lock, flags);
		return;
	}

	if (bfq_bfqq_budget_timeout(bfqq))
		/*
		 * Also here the queue can be safely expired
		 * for budget timeout without wasting
		 * guarantees
		 */
		reason = BFQQE_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 = BFQQE_TOO_IDLE;
	else
		goto schedule_dispatch;

	bfq_bfqq_expire(bfqd, bfqq, true, reason);

schedule_dispatch:
	spin_unlock_irqrestore(&bfqd->lock, flags);
	bfq_schedule_dispatch(bfqd);
}

/*
 * Handler of the expiration of the timer running if the in-service queue
 * is idling inside its time slice.
 */
static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
{
	struct bfq_data *bfqd = container_of(timer, struct bfq_data,
					     idle_slice_timer);
	struct bfq_queue *bfqq = bfqd->in_service_queue;

	/*
	 * Theoretical race here: the in-service queue can be NULL or
	 * different from the queue that was idling if 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)
		bfq_idle_slice_timer_body(bfqq);

	return HRTIMER_NORESTART;
}

static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
				 struct bfq_queue **bfqq_ptr)
{
	struct bfq_queue *bfqq = *bfqq_ptr;

	bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
	if (bfqq) {
		bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);

		bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
			     bfqq, 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 bfq_queue *bfqq, *n;

	hrtimer_cancel(&bfqd->idle_slice_timer);

	spin_lock_irq(&bfqd->lock);
	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
	spin_unlock_irq(&bfqd->lock);

	hrtimer_cancel(&bfqd->idle_slice_timer);

#ifdef CONFIG_BFQ_GROUP_IOSCHED
	blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
#else
	spin_lock_irq(&bfqd->lock);
	bfq_put_async_queues(bfqd, bfqd->root_group);
	kfree(bfqd->root_group);
	spin_unlock_irq(&bfqd->lock);
#endif

	kfree(bfqd);
}

static void bfq_init_root_group(struct bfq_group *root_group,
				struct bfq_data *bfqd)
{
	int i;

#ifdef CONFIG_BFQ_GROUP_IOSCHED
	root_group->entity.parent = NULL;
	root_group->my_entity = NULL;
	root_group->bfqd = bfqd;
#endif
	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
		root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
	root_group->sched_data.bfq_class_idle_last_service = jiffies;
}

static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
{
	struct bfq_data *bfqd;
	struct elevator_queue *eq;

	eq = elevator_alloc(q, e);
	if (!eq)
		return -ENOMEM;

	bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
	if (!bfqd) {
		kobject_put(&eq->kobj);
		return -ENOMEM;
	}
	eq->elevator_data = bfqd;

	spin_lock_irq(q->queue_lock);
	q->elevator = eq;
	spin_unlock_irq(q->queue_lock);

	/*
	 * 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, NULL, 1, 0);
	bfqd->oom_bfqq.ref++;
	bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO;
	bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE;
	bfqd->oom_bfqq.entity.new_weight =
		bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio);
	/*
	 * 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.prio_changed = 1;

	bfqd->queue = q;

	INIT_LIST_HEAD(&bfqd->dispatch);

	hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
		     HRTIMER_MODE_REL);
	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;

	INIT_LIST_HEAD(&bfqd->active_list);
	INIT_LIST_HEAD(&bfqd->idle_list);

	bfqd->hw_tag = -1;

	bfqd->bfq_max_budget = bfq_default_max_budget;

	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_timeout = bfq_timeout;

	bfqd->bfq_requests_within_timer = 120;

	spin_lock_init(&bfqd->lock);

	/*
	 * The invocation of the next bfq_create_group_hierarchy
	 * function is the head of a chain of function calls
	 * (bfq_create_group_hierarchy->blkcg_activate_policy->
	 * blk_mq_freeze_queue) that may lead to the invocation of the
	 * has_work hook function. For this reason,
	 * bfq_create_group_hierarchy is invoked only after all
	 * scheduler data has been initialized, apart from the fields
	 * that can be initialized only after invoking
	 * bfq_create_group_hierarchy. This, in particular, enables
	 * has_work to correctly return false. Of course, to avoid
	 * other inconsistencies, the blk-mq stack must then refrain
	 * from invoking further scheduler hooks before this init
	 * function is finished.
	 */
	bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node);
	if (!bfqd->root_group)
		goto out_free;
	bfq_init_root_group(bfqd->root_group, bfqd);
	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);


	return 0;

out_free:
	kfree(bfqd);
	kobject_put(&eq->kobj);
	return -ENOMEM;
}

static void bfq_slab_kill(void)
{
	kmem_cache_destroy(bfq_pool);
}

static int __init bfq_slab_setup(void)
{
	bfq_pool = KMEM_CACHE(bfq_queue, 0);
	if (!bfq_pool)
		return -ENOMEM;
	return 0;
}

static ssize_t bfq_var_show(unsigned int var, char *page)
{
	return sprintf(page, "%u\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;
}

#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
{									\
	struct bfq_data *bfqd = e->elevator_data;			\
	u64 __data = __VAR;						\
	if (__CONV == 1)						\
		__data = jiffies_to_msecs(__data);			\
	else if (__CONV == 2)						\
		__data = div_u64(__data, NSEC_PER_MSEC);		\
	return bfq_var_show(__data, (page));				\
}
SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2);
SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2);
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, 2);
SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
#undef SHOW_FUNCTION

#define USEC_SHOW_FUNCTION(__FUNC, __VAR)				\
static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
{									\
	struct bfq_data *bfqd = e->elevator_data;			\
	u64 __data = __VAR;						\
	__data = div_u64(__data, NSEC_PER_USEC);			\
	return bfq_var_show(__data, (page));				\
}
USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle);
#undef USEC_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 == 1)						\
		*(__PTR) = msecs_to_jiffies(__data);			\
	else if (__CONV == 2)						\
		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
	else								\
		*(__PTR) = __data;					\
	return ret;							\
}
STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
		INT_MAX, 2);
STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
		INT_MAX, 2);
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, 2);
#undef STORE_FUNCTION

#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)			\
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);						\
	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
	return ret;							\
}
USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0,
		    UINT_MAX);
#undef USEC_STORE_FUNCTION

static unsigned long bfq_estimated_max_budget(struct bfq_data *bfqd)
{
	u64 timeout = jiffies_to_msecs(bfqd->bfq_timeout);

	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;
}

/*
 * Leaving this name to preserve name compatibility with cfq
 * parameters, but this timeout is used for both sync and async.
 */
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 = 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_strict_guarantees_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 (!bfqd->strict_guarantees && __data == 1
	    && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC)
		bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC;

	bfqd->strict_guarantees = __data;

	return ret;
}

#define BFQ_ATTR(name) \
	__ATTR(name, 0644, bfq_##name##_show, bfq_##name##_store)

static struct elv_fs_entry bfq_attrs[] = {
	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(slice_idle_us),
	BFQ_ATTR(max_budget),
	BFQ_ATTR(timeout_sync),
	BFQ_ATTR(strict_guarantees),
	__ATTR_NULL
};

static struct elevator_type iosched_bfq_mq = {
	.ops.mq = {
		.get_rq_priv		= bfq_get_rq_private,
		.put_rq_priv		= bfq_put_rq_private,
		.exit_icq		= bfq_exit_icq,
		.insert_requests	= bfq_insert_requests,
		.dispatch_request	= bfq_dispatch_request,
		.next_request		= elv_rb_latter_request,
		.former_request		= elv_rb_former_request,
		.allow_merge		= bfq_allow_bio_merge,
		.bio_merge		= bfq_bio_merge,
		.request_merge		= bfq_request_merge,
		.requests_merged	= bfq_requests_merged,
		.request_merged		= bfq_request_merged,
		.has_work		= bfq_has_work,
		.init_sched		= bfq_init_queue,
		.exit_sched		= bfq_exit_queue,
	},

	.uses_mq =		true,
	.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,
};

#ifdef CONFIG_BFQ_GROUP_IOSCHED
static struct blkcg_policy blkcg_policy_bfq = {
	.dfl_cftypes		= bfq_blkg_files,
	.legacy_cftypes		= bfq_blkcg_legacy_files,

	.cpd_alloc_fn		= bfq_cpd_alloc,
	.cpd_init_fn		= bfq_cpd_init,
	.cpd_bind_fn	        = bfq_cpd_init,
	.cpd_free_fn		= bfq_cpd_free,

	.pd_alloc_fn		= bfq_pd_alloc,
	.pd_init_fn		= bfq_pd_init,
	.pd_offline_fn		= bfq_pd_offline,
	.pd_free_fn		= bfq_pd_free,
	.pd_reset_stats_fn	= bfq_pd_reset_stats,
};
#endif

static int __init bfq_init(void)
{
	int ret;

#ifdef CONFIG_BFQ_GROUP_IOSCHED
	ret = blkcg_policy_register(&blkcg_policy_bfq);
	if (ret)
		return ret;
#endif

	ret = -ENOMEM;
	if (bfq_slab_setup())
		goto err_pol_unreg;

	ret = elv_register(&iosched_bfq_mq);
	if (ret)
		goto err_pol_unreg;

	return 0;

err_pol_unreg:
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	blkcg_policy_unregister(&blkcg_policy_bfq);
#endif
	return ret;
}

static void __exit bfq_exit(void)
{
	elv_unregister(&iosched_bfq_mq);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	blkcg_policy_unregister(&blkcg_policy_bfq);
#endif
	bfq_slab_kill();
}

module_init(bfq_init);
module_exit(bfq_exit);

MODULE_AUTHOR("Paolo Valente");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MQ Budget Fair Queueing I/O Scheduler");