0002-block-introduce-the-BFQ-v7r11-I-O-sched-to-be-ported.patch

+ *        . 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);
+	bfqq->next_rq = next_rq;
+
+	if (!bfq_bfqq_busy(bfqq)) {
+		bool soft_rt, in_burst,
+		     idle_for_long_time = time_is_before_jiffies(
+						bfqq->budget_timeout +
+						bfqd->bfq_wr_min_idle_time);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+		bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq,
+					 rq->cmd_flags);
+#endif
+		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;
+		}
+
+		in_burst = bfq_bfqq_in_large_burst(bfqq);
+		soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+			!in_burst &&
+			time_is_before_jiffies(bfqq->soft_rt_next_start);
+		interactive = !in_burst && 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,
+		 * - has been idle for enough time,
+		 * - is not a sync queue or is linked to a bfq_io_cq (it is
+		 *   shared "for its nature" or it is not shared and its
+		 *   requests have not been redirected to a shared queue)
+		 * start a weight-raising period.
+		 */
+		if (old_wr_coeff == 1 && (interactive || soft_rt) &&
+		    (!bfq_bfqq_sync(bfqq) || bfqq->bic)) {
+			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 (in_burst ||
+				 (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->prio_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->prio_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)
+		return NULL;
+
+	bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
+	if (bfqq)
+		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",
+		(unsigned long long) bfqd->last_position);
+}
+
+static 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);
+	}
+
+	if (rq->queuelist.prev != &rq->queuelist)
+		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) {
+			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--;
+	}
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
+#endif
+}
+
+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 && 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);
+		bfqq->next_rq = next_rq;
+	}
+}
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+static void bfq_bio_merged(struct request_queue *q, struct request *req,
+			   struct bio *bio)
+{
+	bfqg_stats_update_io_merged(bfqq_group(RQ_BFQQ(req)), bio->bi_rw);
+}
+#endif
+
+static void bfq_merged_requests(struct request_queue *q, struct request *rq,
+				struct request *next)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
+
+	/*
+	 * If next and rq belong to the same bfq_queue and next is older
+	 * than rq, then reposition rq in the fifo (by substituting next
+	 * with rq). Otherwise, if next and rq belong to different
+	 * bfq_queues, never reposition rq: in fact, we would have to
+	 * reposition it with respect to next's position in its own fifo,
+	 * which would most certainly be too expensive with respect to
+	 * the benefits.
+	 */
+	if (bfqq == next_bfqq &&
+	    !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
+	    time_before(next->fifo_time, rq->fifo_time)) {
+		list_del_init(&rq->queuelist);
+		list_replace_init(&next->queuelist, &rq->queuelist);
+		rq->fifo_time = next->fifo_time;
+	}
+
+	if (bfqq->next_rq == next)
+		bfqq->next_rq = rq;
+
+	bfq_remove_request(next);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
+#endif
+}
+
+/* Must be called with bfqq != NULL */
+static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
+{
+	BUG_ON(!bfqq);
+	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.prio_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])
+				bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
+	if (bfqg->async_idle_bfqq)
+		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;
+
+	/*
+	 * 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)
+		return 0;
+
+	return bic_to_bfqq(bic, bfq_bio_sync(bio)) == RQ_BFQQ(rq);
+}
+
+static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
+				       struct bfq_queue *bfqq)
+{
+	if (bfqq) {
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+		bfqg_stats_update_avg_queue_size(bfqq_group(bfqq));
+#endif
+		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 = %d",
+			     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 = bfq_get_next_queue(bfqd);
+
+	__bfq_set_in_service_queue(bfqd, bfqq);
+	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 int bfq_max_budget(struct bfq_data *bfqd)
+{
+	if (bfqd->budgets_assigned < bfq_stats_min_budgets)
+		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 int bfq_min_budget(struct bfq_data *bfqd)
+{
+	if (bfqd->budgets_assigned < bfq_stats_min_budgets)
+		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 || 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 or the scenario is
+	 * asymmetric, 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 &&
+	    bfq_symmetric_scenario(bfqd))
+		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);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
+#endif
+	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++;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	bfqg_stats_update_dispatch(bfqq_group(bfqq), blk_rq_bytes(rq),
+				   rq->cmd_flags);
+#endif
+}
+
+/*
+ * 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;
+}
+
+static int 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 (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);
+}
+
+/**
+ * __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 at queue expiration.
+ * 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;
+	int 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 %d, budg left %d",
+		bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %d, min budg %d",
+		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 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 >= bfq_stats_min_budgets &&
+	    !bfqd->bfq_user_max_budget)
+		bfqq->max_budget = min(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)
+		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 %d",
+			next_rq ? 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 bool bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+				 bool 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 false;
+
+	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 false;
+
+	/*
+	 * 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=%d",
+					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 false;
+
+	/*
+	 * 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