diff -Naurp linux-4.4.0-20160123.orig/block/bfq-cgroup.c linux-4.4.0-20160123/block/bfq-cgroup.c --- linux-4.4.0-20160123.orig/block/bfq-cgroup.c 1969-12-31 19:00:00.000000000 -0500 +++ linux-4.4.0-20160123/block/bfq-cgroup.c 2016-01-27 02:03:31.599861505 -0500 @@ -0,0 +1,1186 @@ +/* + * BFQ: CGROUPS support. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2010 Paolo Valente + * + * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ + * file. + */ + +#ifdef CONFIG_BFQ_GROUP_IOSCHED + +/* bfqg stats flags */ +enum bfqg_stats_flags { + BFQG_stats_waiting = 0, + BFQG_stats_idling, + BFQG_stats_empty, +}; + +#define BFQG_FLAG_FNS(name) \ +static void bfqg_stats_mark_##name(struct bfqg_stats *stats) \ +{ \ + stats->flags |= (1 << BFQG_stats_##name); \ +} \ +static void bfqg_stats_clear_##name(struct bfqg_stats *stats) \ +{ \ + stats->flags &= ~(1 << BFQG_stats_##name); \ +} \ +static int bfqg_stats_##name(struct bfqg_stats *stats) \ +{ \ + return (stats->flags & (1 << BFQG_stats_##name)) != 0; \ +} \ + +BFQG_FLAG_FNS(waiting) +BFQG_FLAG_FNS(idling) +BFQG_FLAG_FNS(empty) +#undef BFQG_FLAG_FNS + +/* This should be called with the queue_lock held. */ +static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats) +{ + unsigned long long now; + + if (!bfqg_stats_waiting(stats)) + return; + + now = sched_clock(); + if (time_after64(now, stats->start_group_wait_time)) + blkg_stat_add(&stats->group_wait_time, + now - stats->start_group_wait_time); + bfqg_stats_clear_waiting(stats); +} + +/* This should be called with the queue_lock held. */ +static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg, + struct bfq_group *curr_bfqg) +{ + struct bfqg_stats *stats = &bfqg->stats; + + if (bfqg_stats_waiting(stats)) + return; + if (bfqg == curr_bfqg) + return; + stats->start_group_wait_time = sched_clock(); + bfqg_stats_mark_waiting(stats); +} + +/* This should be called with the queue_lock held. */ +static void bfqg_stats_end_empty_time(struct bfqg_stats *stats) +{ + unsigned long long now; + + if (!bfqg_stats_empty(stats)) + return; + + now = sched_clock(); + if (time_after64(now, stats->start_empty_time)) + blkg_stat_add(&stats->empty_time, + now - stats->start_empty_time); + bfqg_stats_clear_empty(stats); +} + +static void bfqg_stats_update_dequeue(struct bfq_group *bfqg) +{ + blkg_stat_add(&bfqg->stats.dequeue, 1); +} + +static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) +{ + struct bfqg_stats *stats = &bfqg->stats; + + if (blkg_rwstat_total(&stats->queued)) + return; + + /* + * group is already marked empty. This can happen if bfqq got new + * request in parent group and moved to this group while being added + * to service tree. Just ignore the event and move on. + */ + if (bfqg_stats_empty(stats)) + return; + + stats->start_empty_time = sched_clock(); + bfqg_stats_mark_empty(stats); +} + +static void bfqg_stats_update_idle_time(struct bfq_group *bfqg) +{ + struct bfqg_stats *stats = &bfqg->stats; + + if (bfqg_stats_idling(stats)) { + unsigned long long now = sched_clock(); + + if (time_after64(now, stats->start_idle_time)) + blkg_stat_add(&stats->idle_time, + now - stats->start_idle_time); + bfqg_stats_clear_idling(stats); + } +} + +static void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) +{ + struct bfqg_stats *stats = &bfqg->stats; + + stats->start_idle_time = sched_clock(); + bfqg_stats_mark_idling(stats); +} + +static void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) +{ + struct bfqg_stats *stats = &bfqg->stats; + + blkg_stat_add(&stats->avg_queue_size_sum, + blkg_rwstat_total(&stats->queued)); + blkg_stat_add(&stats->avg_queue_size_samples, 1); + bfqg_stats_update_group_wait_time(stats); +} + +static struct blkcg_policy blkcg_policy_bfq; + +/* + * blk-cgroup policy-related handlers + * The following functions help in converting between blk-cgroup + * internal structures and BFQ-specific structures. + */ + +static struct bfq_group *pd_to_bfqg(struct blkg_policy_data *pd) +{ + return pd ? container_of(pd, struct bfq_group, pd) : NULL; +} + +static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg) +{ + return pd_to_blkg(&bfqg->pd); +} + +static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg) +{ + struct blkg_policy_data *pd = blkg_to_pd(blkg, &blkcg_policy_bfq); + BUG_ON(!pd); + return pd_to_bfqg(pd); +} + +/* + * bfq_group handlers + * The following functions help in navigating the bfq_group hierarchy + * by allowing to find the parent of a bfq_group or the bfq_group + * associated to a bfq_queue. + */ + +static struct bfq_group *bfqg_parent(struct bfq_group *bfqg) +{ + struct blkcg_gq *pblkg = bfqg_to_blkg(bfqg)->parent; + + return pblkg ? blkg_to_bfqg(pblkg) : NULL; +} + +static struct bfq_group *bfqq_group(struct bfq_queue *bfqq) +{ + struct bfq_entity *group_entity = bfqq->entity.parent; + + return group_entity ? container_of(group_entity, struct bfq_group, + entity) : + bfqq->bfqd->root_group; +} + +/* + * The following two functions handle get and put of a bfq_group by + * wrapping the related blk-cgroup hooks. + */ + +static void bfqg_get(struct bfq_group *bfqg) +{ + return blkg_get(bfqg_to_blkg(bfqg)); +} + +static void bfqg_put(struct bfq_group *bfqg) +{ + return blkg_put(bfqg_to_blkg(bfqg)); +} + +static void bfqg_stats_update_io_add(struct bfq_group *bfqg, + struct bfq_queue *bfqq, + int rw) +{ + blkg_rwstat_add(&bfqg->stats.queued, rw, 1); + bfqg_stats_end_empty_time(&bfqg->stats); + if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue)) + bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq)); +} + +static void bfqg_stats_update_io_remove(struct bfq_group *bfqg, int rw) +{ + blkg_rwstat_add(&bfqg->stats.queued, rw, -1); +} + +static void bfqg_stats_update_io_merged(struct bfq_group *bfqg, int rw) +{ + blkg_rwstat_add(&bfqg->stats.merged, rw, 1); +} + +static void bfqg_stats_update_dispatch(struct bfq_group *bfqg, + uint64_t bytes, int rw) +{ + blkg_stat_add(&bfqg->stats.sectors, bytes >> 9); + blkg_rwstat_add(&bfqg->stats.serviced, rw, 1); + blkg_rwstat_add(&bfqg->stats.service_bytes, rw, bytes); +} + +static void bfqg_stats_update_completion(struct bfq_group *bfqg, + uint64_t start_time, uint64_t io_start_time, int rw) +{ + struct bfqg_stats *stats = &bfqg->stats; + unsigned long long now = sched_clock(); + + if (time_after64(now, io_start_time)) + blkg_rwstat_add(&stats->service_time, rw, now - io_start_time); + if (time_after64(io_start_time, start_time)) + blkg_rwstat_add(&stats->wait_time, rw, + io_start_time - start_time); +} + +/* @stats = 0 */ +static void bfqg_stats_reset(struct bfqg_stats *stats) +{ + if (!stats) + return; + + /* queued stats shouldn't be cleared */ + blkg_rwstat_reset(&stats->service_bytes); + blkg_rwstat_reset(&stats->serviced); + blkg_rwstat_reset(&stats->merged); + blkg_rwstat_reset(&stats->service_time); + blkg_rwstat_reset(&stats->wait_time); + blkg_stat_reset(&stats->time); + blkg_stat_reset(&stats->unaccounted_time); + blkg_stat_reset(&stats->avg_queue_size_sum); + blkg_stat_reset(&stats->avg_queue_size_samples); + blkg_stat_reset(&stats->dequeue); + blkg_stat_reset(&stats->group_wait_time); + blkg_stat_reset(&stats->idle_time); + blkg_stat_reset(&stats->empty_time); +} + +/* @to += @from */ +static void bfqg_stats_merge(struct bfqg_stats *to, struct bfqg_stats *from) +{ + if (!to || !from) + return; + + /* queued stats shouldn't be cleared */ + blkg_rwstat_add_aux(&to->service_bytes, &from->service_bytes); + blkg_rwstat_add_aux(&to->serviced, &from->serviced); + blkg_rwstat_add_aux(&to->merged, &from->merged); + blkg_rwstat_add_aux(&to->service_time, &from->service_time); + blkg_rwstat_add_aux(&to->wait_time, &from->wait_time); + blkg_stat_add_aux(&from->time, &from->time); + blkg_stat_add_aux(&to->unaccounted_time, &from->unaccounted_time); + blkg_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum); + blkg_stat_add_aux(&to->avg_queue_size_samples, &from->avg_queue_size_samples); + blkg_stat_add_aux(&to->dequeue, &from->dequeue); + blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time); + blkg_stat_add_aux(&to->idle_time, &from->idle_time); + blkg_stat_add_aux(&to->empty_time, &from->empty_time); +} + +/* + * Transfer @bfqg's stats to its parent's dead_stats so that the ancestors' + * recursive stats can still account for the amount used by this bfqg after + * it's gone. + */ +static void bfqg_stats_xfer_dead(struct bfq_group *bfqg) +{ + struct bfq_group *parent; + + if (!bfqg) /* root_group */ + return; + + parent = bfqg_parent(bfqg); + + lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock); + + if (unlikely(!parent)) + return; + + bfqg_stats_merge(&parent->dead_stats, &bfqg->stats); + bfqg_stats_merge(&parent->dead_stats, &bfqg->dead_stats); + bfqg_stats_reset(&bfqg->stats); + bfqg_stats_reset(&bfqg->dead_stats); +} + +static void bfq_init_entity(struct bfq_entity *entity, + struct bfq_group *bfqg) +{ + struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); + + entity->weight = entity->new_weight; + entity->orig_weight = entity->new_weight; + if (bfqq) { + bfqq->ioprio = bfqq->new_ioprio; + bfqq->ioprio_class = bfqq->new_ioprio_class; + bfqg_get(bfqg); + } + entity->parent = bfqg->my_entity; + entity->sched_data = &bfqg->sched_data; +} + +static void bfqg_stats_exit(struct bfqg_stats *stats) +{ + blkg_rwstat_exit(&stats->service_bytes); + blkg_rwstat_exit(&stats->serviced); + blkg_rwstat_exit(&stats->merged); + blkg_rwstat_exit(&stats->service_time); + blkg_rwstat_exit(&stats->wait_time); + blkg_rwstat_exit(&stats->queued); + blkg_stat_exit(&stats->sectors); + blkg_stat_exit(&stats->time); + blkg_stat_exit(&stats->unaccounted_time); + blkg_stat_exit(&stats->avg_queue_size_sum); + blkg_stat_exit(&stats->avg_queue_size_samples); + blkg_stat_exit(&stats->dequeue); + blkg_stat_exit(&stats->group_wait_time); + blkg_stat_exit(&stats->idle_time); + blkg_stat_exit(&stats->empty_time); +} + +static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp) +{ + if (blkg_rwstat_init(&stats->service_bytes, gfp) || + blkg_rwstat_init(&stats->serviced, gfp) || + blkg_rwstat_init(&stats->merged, gfp) || + blkg_rwstat_init(&stats->service_time, gfp) || + blkg_rwstat_init(&stats->wait_time, gfp) || + blkg_rwstat_init(&stats->queued, gfp) || + blkg_stat_init(&stats->sectors, gfp) || + blkg_stat_init(&stats->time, gfp) || + blkg_stat_init(&stats->unaccounted_time, gfp) || + blkg_stat_init(&stats->avg_queue_size_sum, gfp) || + blkg_stat_init(&stats->avg_queue_size_samples, gfp) || + blkg_stat_init(&stats->dequeue, gfp) || + blkg_stat_init(&stats->group_wait_time, gfp) || + blkg_stat_init(&stats->idle_time, gfp) || + blkg_stat_init(&stats->empty_time, gfp)) { + bfqg_stats_exit(stats); + return -ENOMEM; + } + + return 0; +} + +static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd) + { + return cpd ? container_of(cpd, struct bfq_group_data, pd) : NULL; + } + +static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg) +{ + return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq)); +} + +static void bfq_cpd_init(struct blkcg_policy_data *cpd) +{ + struct bfq_group_data *d = cpd_to_bfqgd(cpd); + + d->weight = BFQ_DEFAULT_GRP_WEIGHT; +} + +static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node) +{ + struct bfq_group *bfqg; + + bfqg = kzalloc_node(sizeof(*bfqg), gfp, node); + if (!bfqg) + return NULL; + + if (bfqg_stats_init(&bfqg->stats, gfp) || + bfqg_stats_init(&bfqg->dead_stats, gfp)) { + kfree(bfqg); + return NULL; + } + + return &bfqg->pd; +} + +static void bfq_group_set_parent(struct bfq_group *bfqg, + struct bfq_group *parent) +{ + struct bfq_entity *entity; + + BUG_ON(!parent); + BUG_ON(!bfqg); + BUG_ON(bfqg == parent); + + entity = &bfqg->entity; + entity->parent = parent->my_entity; + entity->sched_data = &parent->sched_data; +} + +static void bfq_pd_init(struct blkg_policy_data *pd) +{ + struct blkcg_gq *blkg = pd_to_blkg(pd); + struct bfq_group *bfqg = blkg_to_bfqg(blkg); + struct bfq_data *bfqd = blkg->q->elevator->elevator_data; + struct bfq_entity *entity = &bfqg->entity; + struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg); + + entity->orig_weight = entity->weight = entity->new_weight = d->weight; + entity->my_sched_data = &bfqg->sched_data; + bfqg->my_entity = entity; /* + * the root_group's will be set to NULL + * in bfq_init_queue() + */ + bfqg->bfqd = bfqd; + bfqg->active_entities = 0; + bfqg->rq_pos_tree = RB_ROOT; +} + +static void bfq_pd_free(struct blkg_policy_data *pd) +{ + struct bfq_group *bfqg = pd_to_bfqg(pd); + + bfqg_stats_exit(&bfqg->stats); + bfqg_stats_exit(&bfqg->dead_stats); + + return kfree(bfqg); +} + +/* offset delta from bfqg->stats to bfqg->dead_stats */ +static const int dead_stats_off_delta = offsetof(struct bfq_group, dead_stats) - + offsetof(struct bfq_group, stats); + +/* to be used by recursive prfill, sums live and dead stats recursively */ +static u64 bfqg_stat_pd_recursive_sum(struct blkg_policy_data *pd, int off) +{ + u64 sum = 0; + + sum += blkg_stat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off); + sum += blkg_stat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, + off + dead_stats_off_delta); + return sum; +} + +/* to be used by recursive prfill, sums live and dead rwstats recursively */ +static struct blkg_rwstat bfqg_rwstat_pd_recursive_sum(struct blkg_policy_data *pd, + int off) +{ + struct blkg_rwstat a, b; + + a = blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off); + b = blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, + off + dead_stats_off_delta); + blkg_rwstat_add_aux(&a, &b); + return a; +} + +static void bfq_pd_reset_stats(struct blkg_policy_data *pd) +{ + struct bfq_group *bfqg = pd_to_bfqg(pd); + + bfqg_stats_reset(&bfqg->stats); + bfqg_stats_reset(&bfqg->dead_stats); +} + +static struct bfq_group *bfq_find_alloc_group(struct bfq_data *bfqd, + struct blkcg *blkcg) +{ + struct request_queue *q = bfqd->queue; + struct bfq_group *bfqg = NULL, *parent; + struct bfq_entity *entity = NULL; + + assert_spin_locked(bfqd->queue->queue_lock); + + /* avoid lookup for the common case where there's no blkcg */ + if (blkcg == &blkcg_root) { + bfqg = bfqd->root_group; + } else { + struct blkcg_gq *blkg; + + blkg = blkg_lookup_create(blkcg, q); + if (!IS_ERR(blkg)) + bfqg = blkg_to_bfqg(blkg); + else /* fallback to root_group */ + bfqg = bfqd->root_group; + } + + BUG_ON(!bfqg); + + /* + * Update chain of bfq_groups as we might be handling a leaf group + * which, along with some of its relatives, has not been hooked yet + * to the private hierarchy of BFQ. + */ + entity = &bfqg->entity; + for_each_entity(entity) { + bfqg = container_of(entity, struct bfq_group, entity); + BUG_ON(!bfqg); + if (bfqg != bfqd->root_group) { + parent = bfqg_parent(bfqg); + if (!parent) + parent = bfqd->root_group; + BUG_ON(!parent); + bfq_group_set_parent(bfqg, parent); + } + } + + return bfqg; +} + +static void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq); + +/** + * 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); + bfqg_put(bfqq_group(bfqq)); + + /* + * 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; + bfqg_get(bfqg); + + if (busy) { + bfq_pos_tree_add_move(bfqd, bfqq); + if (resume) + bfq_activate_bfqq(bfqd, bfqq); + } + + if (!bfqd->in_service_queue && !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. + * @blkcg: the blk-cgroup to move to. + * + * Move bic to blkcg, 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 blkcg *blkcg) +{ + struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0); + struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1); + struct bfq_group *bfqg; + struct bfq_entity *entity; + + lockdep_assert_held(bfqd->queue->queue_lock); + + bfqg = bfq_find_alloc_group(bfqd, blkcg); + if (async_bfqq) { + 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) { + entity = &sync_bfqq->entity; + if (entity->sched_data != &bfqg->sched_data) + bfq_bfqq_move(bfqd, sync_bfqq, entity, bfqg); + } + + return bfqg; +} + +static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) +{ + struct bfq_data *bfqd = bic_to_bfqd(bic); + struct blkcg *blkcg; + struct bfq_group *bfqg = NULL; + uint64_t id; + + rcu_read_lock(); + blkcg = bio_blkcg(bio); + id = blkcg->css.serial_nr; + rcu_read_unlock(); + + /* + * Check whether blkcg has changed. The condition may trigger + * spuriously on a newly created cic but there's no harm. + */ + if (unlikely(!bfqd) || likely(bic->blkcg_id == id)) + return; + + bfqg = __bfq_bic_change_cgroup(bfqd, bic, blkcg); + BUG_ON(!bfqg); + bic->blkcg_id = id; +} + +/** + * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st. + * @st: the service tree being flushed. + */ +static void bfq_flush_idle_tree(struct bfq_service_tree *st) +{ + struct bfq_entity *entity = st->first_idle; + + for (; entity ; 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 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); + 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 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 ; entity = bfq_entity_of(rb_first(active))) + bfq_reparent_leaf_entity(bfqd, entity); + + if (bfqg->sched_data.in_service_entity) + bfq_reparent_leaf_entity(bfqd, + bfqg->sched_data.in_service_entity); + + return; +} + +/** + * bfq_destroy_group - destroy @bfqg. + * @bfqg: the group being destroyed. + * + * Destroy @bfqg, making sure that it is not referenced from its parent. + * blkio already grabs the queue_lock for us, so no need to use RCU-based magic + */ +static void bfq_pd_offline(struct blkg_policy_data *pd) +{ + struct bfq_service_tree *st; + struct bfq_group *bfqg; + struct bfq_data *bfqd; + struct bfq_entity *entity; + int i; + + BUG_ON(!pd); + bfqg = pd_to_bfqg(pd); + BUG_ON(!bfqg); + bfqd = bfqg->bfqd; + BUG_ON(bfqd && !bfqd->root_group); + + entity = bfqg->my_entity; + + if (!entity) /* root group */ + return; + + /* + * Empty all service_trees belonging to this group before + * deactivating the group itself. + */ + for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) { + BUG_ON(!bfqg->sched_data.service_tree); + 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. + */ + bfq_reparent_active_entities(bfqd, bfqg, st); + BUG_ON(!RB_EMPTY_ROOT(&st->active)); + BUG_ON(!RB_EMPTY_ROOT(&st->idle)); + } + BUG_ON(bfqg->sched_data.next_in_service); + BUG_ON(bfqg->sched_data.in_service_entity); + + __bfq_deactivate_entity(entity, 0); + bfq_put_async_queues(bfqd, bfqg); + BUG_ON(entity->tree); + + bfqg_stats_xfer_dead(bfqg); +} + +static void bfq_end_wr_async(struct bfq_data *bfqd) +{ + struct blkcg_gq *blkg; + + list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) { + struct bfq_group *bfqg = blkg_to_bfqg(blkg); + + bfq_end_wr_async_queues(bfqd, bfqg); + } + bfq_end_wr_async_queues(bfqd, bfqd->root_group); +} + +static u64 bfqio_cgroup_weight_read(struct cgroup_subsys_state *css, + struct cftype *cftype) +{ + struct blkcg *blkcg = css_to_blkcg(css); + struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg); + int ret = -EINVAL; + + spin_lock_irq(&blkcg->lock); + ret = bfqgd->weight; + spin_unlock_irq(&blkcg->lock); + + return ret; +} + +static int bfqio_cgroup_weight_read_dfl(struct seq_file *sf, void *v) +{ + struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); + struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg); + + spin_lock_irq(&blkcg->lock); + seq_printf(sf, "%u\n", bfqgd->weight); + spin_unlock_irq(&blkcg->lock); + + return 0; +} + +static int bfqio_cgroup_weight_write(struct cgroup_subsys_state *css, + struct cftype *cftype, + u64 val) +{ + struct blkcg *blkcg = css_to_blkcg(css); + struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg); + struct blkcg_gq *blkg; + int ret = -EINVAL; + + if (val < BFQ_MIN_WEIGHT || val > BFQ_MAX_WEIGHT) + return ret; + + ret = 0; + spin_lock_irq(&blkcg->lock); + bfqgd->weight = (unsigned short)val; + hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { + struct bfq_group *bfqg = blkg_to_bfqg(blkg); + if (!bfqg) + continue; + /* + * Setting the prio_changed flag of the entity + * to 1 with new_weight == weight 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_weight) { + bfqg->entity.new_weight = (unsigned short)val; + /* + * Make sure that the above new value has been + * stored in bfqg->entity.new_weight before + * setting the prio_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_weight (in + * __bfq_entity_update_weight_prio). + * This barrier makes sure that the new value + * of bfqg->entity.new_weight is correctly + * seen in that code. + */ + smp_wmb(); + bfqg->entity.prio_changed = 1; + } + } + spin_unlock_irq(&blkcg->lock); + + return ret; +} + +static ssize_t bfqio_cgroup_weight_write_dfl(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + /* First unsigned long found in the file is used */ + return bfqio_cgroup_weight_write(of_css(of), NULL, + simple_strtoull(strim(buf), NULL, 0)); +} + +static int bfqg_print_stat(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat, + &blkcg_policy_bfq, seq_cft(sf)->private, false); + return 0; +} + +static int bfqg_print_rwstat(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat, + &blkcg_policy_bfq, seq_cft(sf)->private, true); + return 0; +} + +static u64 bfqg_prfill_stat_recursive(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + u64 sum = bfqg_stat_pd_recursive_sum(pd, off); + + return __blkg_prfill_u64(sf, pd, sum); +} + +static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + struct blkg_rwstat sum = bfqg_rwstat_pd_recursive_sum(pd, off); + + return __blkg_prfill_rwstat(sf, pd, &sum); +} + +static int bfqg_print_stat_recursive(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + bfqg_prfill_stat_recursive, &blkcg_policy_bfq, + seq_cft(sf)->private, false); + return 0; +} + +static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq, + seq_cft(sf)->private, true); + return 0; +} + +static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + struct bfq_group *bfqg = pd_to_bfqg(pd); + u64 samples = blkg_stat_read(&bfqg->stats.avg_queue_size_samples); + u64 v = 0; + + if (samples) { + v = blkg_stat_read(&bfqg->stats.avg_queue_size_sum); + v = div64_u64(v, samples); + } + __blkg_prfill_u64(sf, pd, v); + return 0; +} + +/* print avg_queue_size */ +static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + bfqg_prfill_avg_queue_size, &blkcg_policy_bfq, + 0, false); + return 0; +} + +static struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) +{ + int ret; + + ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq); + if (ret) + return NULL; + + return blkg_to_bfqg(bfqd->queue->root_blkg); +} + +static struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp) +{ + struct bfq_group_data *bgd; + + bgd = kzalloc(sizeof(*bgd), GFP_KERNEL); + if (!bgd) + return NULL; + return &bgd->pd; +} + +static void bfq_cpd_free(struct blkcg_policy_data *cpd) +{ + kfree(cpd_to_bfqgd(cpd)); +} + +static struct cftype bfqio_files_dfl[] = { + { + .name = "weight", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = bfqio_cgroup_weight_read_dfl, + .write = bfqio_cgroup_weight_write_dfl, + }, + {} /* terminate */ +}; + +static struct cftype bfqio_files[] = { + { + .name = "bfq.weight", + .read_u64 = bfqio_cgroup_weight_read, + .write_u64 = bfqio_cgroup_weight_write, + }, + /* statistics, cover only the tasks in the bfqg */ + { + .name = "bfq.time", + .private = offsetof(struct bfq_group, stats.time), + .seq_show = bfqg_print_stat, + }, + { + .name = "bfq.sectors", + .private = offsetof(struct bfq_group, stats.sectors), + .seq_show = bfqg_print_stat, + }, + { + .name = "bfq.io_service_bytes", + .private = offsetof(struct bfq_group, stats.service_bytes), + .seq_show = bfqg_print_rwstat, + }, + { + .name = "bfq.io_serviced", + .private = offsetof(struct bfq_group, stats.serviced), + .seq_show = bfqg_print_rwstat, + }, + { + .name = "bfq.io_service_time", + .private = offsetof(struct bfq_group, stats.service_time), + .seq_show = bfqg_print_rwstat, + }, + { + .name = "bfq.io_wait_time", + .private = offsetof(struct bfq_group, stats.wait_time), + .seq_show = bfqg_print_rwstat, + }, + { + .name = "bfq.io_merged", + .private = offsetof(struct bfq_group, stats.merged), + .seq_show = bfqg_print_rwstat, + }, + { + .name = "bfq.io_queued", + .private = offsetof(struct bfq_group, stats.queued), + .seq_show = bfqg_print_rwstat, + }, + + /* the same statictics which cover the bfqg and its descendants */ + { + .name = "bfq.time_recursive", + .private = offsetof(struct bfq_group, stats.time), + .seq_show = bfqg_print_stat_recursive, + }, + { + .name = "bfq.sectors_recursive", + .private = offsetof(struct bfq_group, stats.sectors), + .seq_show = bfqg_print_stat_recursive, + }, + { + .name = "bfq.io_service_bytes_recursive", + .private = offsetof(struct bfq_group, stats.service_bytes), + .seq_show = bfqg_print_rwstat_recursive, + }, + { + .name = "bfq.io_serviced_recursive", + .private = offsetof(struct bfq_group, stats.serviced), + .seq_show = bfqg_print_rwstat_recursive, + }, + { + .name = "bfq.io_service_time_recursive", + .private = offsetof(struct bfq_group, stats.service_time), + .seq_show = bfqg_print_rwstat_recursive, + }, + { + .name = "bfq.io_wait_time_recursive", + .private = offsetof(struct bfq_group, stats.wait_time), + .seq_show = bfqg_print_rwstat_recursive, + }, + { + .name = "bfq.io_merged_recursive", + .private = offsetof(struct bfq_group, stats.merged), + .seq_show = bfqg_print_rwstat_recursive, + }, + { + .name = "bfq.io_queued_recursive", + .private = offsetof(struct bfq_group, stats.queued), + .seq_show = bfqg_print_rwstat_recursive, + }, + { + .name = "bfq.avg_queue_size", + .seq_show = bfqg_print_avg_queue_size, + }, + { + .name = "bfq.group_wait_time", + .private = offsetof(struct bfq_group, stats.group_wait_time), + .seq_show = bfqg_print_stat, + }, + { + .name = "bfq.idle_time", + .private = offsetof(struct bfq_group, stats.idle_time), + .seq_show = bfqg_print_stat, + }, + { + .name = "bfq.empty_time", + .private = offsetof(struct bfq_group, stats.empty_time), + .seq_show = bfqg_print_stat, + }, + { + .name = "bfq.dequeue", + .private = offsetof(struct bfq_group, stats.dequeue), + .seq_show = bfqg_print_stat, + }, + { + .name = "bfq.unaccounted_time", + .private = offsetof(struct bfq_group, stats.unaccounted_time), + .seq_show = bfqg_print_stat, + }, + { } /* terminate */ +}; + +static struct blkcg_policy blkcg_policy_bfq = { + .dfl_cftypes = bfqio_files_dfl, + .legacy_cftypes = bfqio_files, + + .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, + + .cpd_alloc_fn = bfq_cpd_alloc, + .cpd_init_fn = bfq_cpd_init, + .cpd_bind_fn = bfq_cpd_init, + .cpd_free_fn = bfq_cpd_free, + +}; + +#else + +static void bfq_init_entity(struct bfq_entity *entity, + struct bfq_group *bfqg) +{ + struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); + entity->weight = entity->new_weight; + entity->orig_weight = entity->new_weight; + if (bfqq) { + bfqq->ioprio = bfqq->new_ioprio; + bfqq->ioprio_class = bfqq->new_ioprio_class; + } + entity->sched_data = &bfqg->sched_data; +} + +static struct bfq_group * +bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) +{ + struct bfq_data *bfqd = bic_to_bfqd(bic); + return bfqd->root_group; +} + +static 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 void bfq_disconnect_groups(struct bfq_data *bfqd) +{ + bfq_put_async_queues(bfqd, bfqd->root_group); +} + +static struct bfq_group *bfq_find_alloc_group(struct bfq_data *bfqd, + struct blkcg *blkcg) +{ + return bfqd->root_group; +} + +static struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) +{ + struct bfq_group *bfqg; + int i; + + bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node); + if (!bfqg) + return NULL; + + for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) + bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT; + + return bfqg; +} +#endif diff -Naurp linux-4.4.0-20160123.orig/block/bfq.h linux-4.4.0-20160123/block/bfq.h --- linux-4.4.0-20160123.orig/block/bfq.h 1969-12-31 19:00:00.000000000 -0500 +++ linux-4.4.0-20160123/block/bfq.h 2016-01-27 02:03:31.599861505 -0500 @@ -0,0 +1,867 @@ +/* + * BFQ-v7r11 for 4.4.0: data structures and common functions prototypes. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2010 Paolo Valente + */ + +#ifndef _BFQ_H +#define _BFQ_H + +#include +#include +#include +#include +#include + +#define BFQ_IOPRIO_CLASSES 3 +#define BFQ_CL_IDLE_TIMEOUT (HZ/5) + +#define BFQ_MIN_WEIGHT 1 +#define BFQ_MAX_WEIGHT 1000 +#define BFQ_WEIGHT_CONVERSION_COEFF 10 + +#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 + * @prio_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 @prio_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; + + int 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; + + int prio_changed; +}; + +struct bfq_group; + +/** + * struct bfq_queue - leaf schedulable entity. + * @ref: reference counter. + * @bfqd: parent bfq_data. + * @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. + * @new_bfqq: shared bfq_queue if queue is cooperating with + * one or more other queues. + * @pos_node: request-position tree member (see bfq_group's @rq_pos_tree). + * @pos_root: request-position tree root (see bfq_group'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 + * @bic: pointer to the bfq_io_cq owning the bfq_queue, set to %NULL if the + * queue is shared + * + * 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; + + unsigned short ioprio, new_ioprio; + unsigned short ioprio_class, new_ioprio_class; + + /* 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; + + int 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; + struct bfq_io_cq *bic; + + /* 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 + * @ioprio: per (request_queue, blkcg) ioprio. + * @blkcg_id: id of the blkcg the related io_cq belongs to. + * @wr_time_left: snapshot of the time left before weight raising ends + * for the sync queue associated to this process; this + * snapshot is taken to remember this value while the weight + * raising is suspended because the queue is merged with a + * shared queue, and is used to set @raising_cur_max_time + * when the queue is split from the shared queue and its + * weight is raised again + * @saved_idle_window: same purpose as the previous field for the idle + * window + * @saved_IO_bound: same purpose as the previous two fields for the I/O + * bound classification of a queue + * @saved_in_large_burst: same purpose as the previous fields for the + * value of the field keeping the queue's belonging + * to a large burst + * @was_in_burst_list: true if the queue belonged to a burst list + * before its merge with another cooperating queue + * @cooperations: counter of consecutive successful queue merges underwent + * by any of the process' @bfq_queues + * @failed_cooperations: counter of consecutive failed queue merges of any + * of the process' @bfq_queues + */ +struct bfq_io_cq { + struct io_cq icq; /* must be the first member */ + struct bfq_queue *bfqq[2]; + struct bfq_ttime ttime; + int ioprio; + +#ifdef CONFIG_BFQ_GROUP_IOSCHED + uint64_t blkcg_id; /* the current blkcg ID */ +#endif + + unsigned int wr_time_left; + bool saved_idle_window; + bool saved_IO_bound; + + bool saved_in_large_burst; + bool was_in_burst_list; + + unsigned int cooperations; + unsigned int failed_cooperations; +}; + +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. + * @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. + * @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_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; + +#ifdef CONFIG_BFQ_GROUP_IOSCHED + 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; + int bfq_max_budget; + + struct list_head active_list; + struct list_head idle_list; + + 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; + + int bfq_user_max_budget; + 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_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 split */ + BFQ_BFQQ_FLAG_just_split, /* queue has just been split */ +}; + +#define BFQ_BFQQ_FNS(name) \ +static void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \ +{ \ + (bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name); \ +} \ +static void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \ +{ \ + (bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name); \ +} \ +static 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(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(just_split); +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_BFQ_GROUP_IOSCHED + +struct bfqg_stats { + /* total bytes transferred */ + struct blkg_rwstat service_bytes; + /* total IOs serviced, post merge */ + struct blkg_rwstat serviced; + /* number of ios merged */ + struct blkg_rwstat merged; + /* total time spent on device in ns, may not be accurate w/ queueing */ + struct blkg_rwstat service_time; + /* total time spent waiting in scheduler queue in ns */ + struct blkg_rwstat wait_time; + /* number of IOs queued up */ + struct blkg_rwstat queued; + /* total sectors transferred */ + struct blkg_stat sectors; + /* total disk time and nr sectors dispatched by this group */ + struct blkg_stat time; + /* time not charged to this cgroup */ + struct blkg_stat unaccounted_time; + /* sum of number of ios queued across all samples */ + struct blkg_stat avg_queue_size_sum; + /* count of samples taken for average */ + struct blkg_stat avg_queue_size_samples; + /* how many times this group has been removed from service tree */ + struct blkg_stat dequeue; + /* total time spent waiting for it to be assigned a timeslice. */ + struct blkg_stat group_wait_time; + /* time spent idling for this blkcg_gq */ + struct blkg_stat idle_time; + /* total time with empty current active q with other requests queued */ + struct blkg_stat empty_time; + /* fields after this shouldn't be cleared on stat reset */ + uint64_t start_group_wait_time; + uint64_t start_idle_time; + uint64_t start_empty_time; + uint16_t flags; +}; + +/* + * struct bfq_group_data - per-blkcg storage for the blkio subsystem. + * + * @ps: @blkcg_policy_storage that this structure inherits + * @weight: weight of the bfq_group + */ +struct bfq_group_data { + /* must be the first member */ + struct blkcg_policy_data pd; + + unsigned short weight; +}; + +/** + * 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). + * @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()). + * @rq_pos_tree: rbtree sorted by next_request position, used when + * determining if two or more queues have interleaving + * requests (see bfq_find_close_cooperator()). + * + * 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 @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 { + /* must be the first member */ + struct blkg_policy_data pd; + + struct bfq_entity entity; + struct bfq_sched_data sched_data; + + 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 rb_root rq_pos_tree; + + struct bfqg_stats stats; + struct bfqg_stats dead_stats; /* stats pushed from dead children */ +}; + +#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; + + struct rb_root rq_pos_tree; +}; +#endif + +static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity); + +static struct bfq_service_tree * +bfq_entity_service_tree(struct bfq_entity *entity) +{ + struct bfq_sched_data *sched_data = entity->sched_data; + struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); + unsigned int idx = bfqq ? bfqq->ioprio_class - 1 : + BFQ_DEFAULT_GRP_CLASS; + + BUG_ON(idx >= BFQ_IOPRIO_CLASSES); + BUG_ON(sched_data == NULL); + + return sched_data->service_tree + idx; +} + +static struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync) +{ + return bic->bfqq[is_sync]; +} + +static void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, + bool is_sync) +{ + bic->bfqq[is_sync] = bfqq; +} + +static 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 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 == NULL) + printk(KERN_CRIT "get_bfqd_locked pointer NULL\n"); + else if (*ptr == bfqd) + goto out; + spin_unlock_irqrestore(bfqd->queue->queue_lock, *flags); + } + + bfqd = NULL; +out: + rcu_read_unlock(); + return bfqd; +} + +static void bfq_put_bfqd_unlock(struct bfq_data *bfqd, unsigned long *flags) +{ + spin_unlock_irqrestore(bfqd->queue->queue_lock, *flags); +} + +#ifdef CONFIG_BFQ_GROUP_IOSCHED + +static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq) +{ + struct bfq_entity *group_entity = bfqq->entity.parent; + + if (!group_entity) + group_entity = &bfqq->bfqd->root_group->entity; + + return container_of(group_entity, struct bfq_group, entity); +} + +#else + +static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq) +{ + return bfqq->bfqd->root_group; +} + +#endif + +static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio); +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 bio *bio, 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 */ diff -Naurp linux-4.4.0-20160123.orig/block/bfq-ioc.c linux-4.4.0-20160123/block/bfq-ioc.c --- linux-4.4.0-20160123.orig/block/bfq-ioc.c 1969-12-31 19:00:00.000000000 -0500 +++ linux-4.4.0-20160123/block/bfq-ioc.c 2016-01-27 02:03:28.329861525 -0500 @@ -0,0 +1,36 @@ +/* + * BFQ: I/O context handling. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2010 Paolo Valente + */ + +/** + * icq_to_bic - convert iocontext queue structure to bfq_io_cq. + * @icq: the iocontext queue. + */ +static 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 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 -Naurp linux-4.4.0-20160123.orig/block/bfq-iosched.c linux-4.4.0-20160123/block/bfq-iosched.c --- linux-4.4.0-20160123.orig/block/bfq-iosched.c 1969-12-31 19:00:00.000000000 -0500 +++ linux-4.4.0-20160123/block/bfq-iosched.c 2016-01-27 02:03:31.599861505 -0500 @@ -0,0 +1,4413 @@ +/* + * Budget Fair Queueing (BFQ) disk scheduler. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2010 Paolo Valente + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include "bfq.h" +#include "blk.h" + +/* 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; + +/* Minimum number of assigned budgets for which stats are safe to compute. */ +static const int bfq_stats_min_budgets = 194; + +/* 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 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)->ioprio_class == IOPRIO_CLASS_IDLE) +#define bfq_class_rt(bfqq) ((bfqq)->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 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 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 || rq1 == rq2) + return rq2; + if (!rq2) + 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 ? bfqq->pid : 0); + + return bfqq; +} + +static void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + struct rb_node **p, *parent; + struct bfq_queue *__bfqq; + + if (bfqq->pos_root) { + 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 = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree; + __bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root, + blk_rq_pos(bfqq->next_rq), &parent, &p); + if (!__bfqq) { + 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 bool bfq_differentiated_weights(struct bfq_data *bfqd) +{ + /* + * 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_BFQ_GROUP_IOSCHED + ) || + (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) && + (bfqd->group_weights_tree.rb_node->rb_left || + bfqd->group_weights_tree.rb_node->rb_right) +#endif + ); +} + +/* + * The following function returns true if every queue must receive the + * same share of the throughput (this condition is used when deciding + * whether idling may be disabled, see the comments in the function + * bfq_bfqq_may_idle()). + * + * Such a scenario occurs when: + * 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. + * + * Unfortunately, keeping the necessary state for evaluating exactly the + * above symmetry conditions would be quite complex and time-consuming. + * Therefore this function 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, thus no state needs + * to be maintained in this case. + */ +static bool bfq_symmetric_scenario(struct bfq_data *bfqd) +{ + return +#ifdef CONFIG_BFQ_GROUP_IOSCHED + !bfqd->active_numerous_groups && +#endif + !bfq_differentiated_weights(bfqd); +} + +/* + * 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 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 (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) +{ + 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) + prev = rb_entry_rq(rbprev); + + if (rbnext) + 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 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) + 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 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; +} + +static unsigned bfq_bfqq_cooperations(struct bfq_queue *bfqq) +{ + return bfqq->bic ? bfqq->bic->cooperations : 0; +} + +static void +bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic) +{ + if (bic->saved_idle_window) + bfq_mark_bfqq_idle_window(bfqq); + else + bfq_clear_bfqq_idle_window(bfqq); + if (bic->saved_IO_bound) + bfq_mark_bfqq_IO_bound(bfqq); + else + bfq_clear_bfqq_IO_bound(bfqq); + /* Assuming that the flag in_large_burst is already correctly set */ + if (bic->wr_time_left && bfqq->bfqd->low_latency && + !bfq_bfqq_in_large_burst(bfqq) && + bic->cooperations < bfqq->bfqd->bfq_coop_thresh) { + /* + * Start a weight raising period with the duration given by + * the raising_time_left snapshot. + */ + if (bfq_bfqq_busy(bfqq)) + bfqq->bfqd->wr_busy_queues++; + bfqq->wr_coeff = bfqq->bfqd->bfq_wr_coeff; + bfqq->wr_cur_max_time = bic->wr_time_left; + bfqq->last_wr_start_finish = jiffies; + bfqq->entity.prio_changed = 1; + } + /* + * Clear wr_time_left to prevent bfq_bfqq_save_state() from + * getting confused about the queue's need of a weight-raising + * period. + */ + bic->wr_time_left = 0; +} + +static int bfqq_process_refs(struct bfq_queue *bfqq) +{ + int process_refs, io_refs; + + lockdep_assert_held(bfqq->bfqd->queue->queue_lock); + + 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; +} + +/* Empty burst list and add just bfqq (see comments to bfq_handle_burst) */ +static 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); + bfqq->next_rq = next_rq; + + /* + * Adjust priority tree position, if next_rq changes. + */ + if (prev != bfqq->next_rq) + bfq_pos_tree_add_move(bfqd, bfqq); + + if (!bfq_bfqq_busy(bfqq)) { + bool soft_rt, coop_or_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; + } + + coop_or_in_burst = bfq_bfqq_in_large_burst(bfqq) || + bfq_bfqq_cooperations(bfqq) >= bfqd->bfq_coop_thresh; + soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 && + !coop_or_in_burst && + time_is_before_jiffies(bfqq->soft_rt_next_start); + interactive = !coop_or_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 (bfq_bfqq_just_split(bfqq)) + goto set_prio_changed; + + /* + * 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 (coop_or_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; + } + } +set_prio_changed: + 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", + (long long unsigned)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; + /* + * 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_pos_tree_add_move(bfqd, bfqq); + } + } +} + +#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 sector_t bfq_io_struct_pos(void *io_struct, bool request) +{ + if (request) + return blk_rq_pos(io_struct); + else + return ((struct bio *)io_struct)->bi_iter.bi_sector; +} + +static int bfq_rq_close_to_sector(void *io_struct, bool request, + sector_t sector) +{ + return abs(bfq_io_struct_pos(io_struct, request) - sector) <= + BFQQ_SEEK_THR; +} + +static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + sector_t sector) +{ + struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree; + struct rb_node *parent, *node; + struct bfq_queue *__bfqq; + + 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) + 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_to_sector(__bfqq->next_rq, true, sector)) + 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) + return NULL; + + __bfqq = rb_entry(node, struct bfq_queue, pos_node); + if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) + return __bfqq; + + return NULL; +} + +static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd, + struct bfq_queue *cur_bfqq, + sector_t sector) +{ + struct bfq_queue *bfqq; + + /* + * We shall notice if some of the queues are cooperating, + * e.g., working closely on the same area of the device. In + * that case, we can group them together and: 1) don't waste + * time idling, and 2) serve the union of their requests in + * the best possible order for throughput. + */ + bfqq = bfqq_find_close(bfqd, cur_bfqq, sector); + if (!bfqq || bfqq == cur_bfqq) + return NULL; + + return bfqq; +} + +static struct bfq_queue * +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 NULL; + + /* Avoid a circular list and skip interim queue merges. */ + while ((__bfqq = new_bfqq->new_bfqq)) { + if (__bfqq == bfqq) + return NULL; + 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 NULL; + + bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", + new_bfqq->pid); + + /* + * Merging is just a redirection: the requests of the process + * owning one of the two queues are redirected to the other queue. + * The latter queue, in its turn, is set as shared if this is the + * first time that the requests of some process are redirected to + * it. + * + * We redirect bfqq to new_bfqq and not the opposite, because we + * are in the context of the process owning bfqq, hence we have + * the io_cq of this process. So we can immediately configure this + * io_cq to redirect the requests of the process to new_bfqq. + * + * NOTE, even if new_bfqq coincides with the in-service queue, the + * io_cq of new_bfqq is not available, because, if the in-service + * queue is shared, bfqd->in_service_bic may not point to the + * io_cq of the in-service queue. + * Redirecting the requests of the process owning bfqq to the + * currently in-service queue is in any case the best option, as + * we feed the in-service queue with new requests close to the + * last request served and, by doing so, hopefully increase the + * throughput. + */ + bfqq->new_bfqq = new_bfqq; + atomic_add(process_refs, &new_bfqq->ref); + return new_bfqq; +} + +static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq, + struct bfq_queue *new_bfqq) +{ + if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) || + (bfqq->ioprio_class != new_bfqq->ioprio_class)) + return false; + + /* + * If either of the queues has already been detected as seeky, + * then merging it with the other queue is unlikely to lead to + * sequential I/O. + */ + if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq)) + return false; + + /* + * Interleaved I/O is known to be done by (some) applications + * only for reads, so it does not make sense to merge async + * queues. + */ + if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq)) + return false; + + return true; +} + +/* + * Attempt to schedule a merge of bfqq with the currently in-service queue + * or with a close queue among the scheduled queues. + * Return NULL if no merge was scheduled, a pointer to the shared bfq_queue + * structure otherwise. + * + * The OOM queue is not allowed to participate to cooperation: in fact, since + * the requests temporarily redirected to the OOM queue could be redirected + * again to dedicated queues at any time, the state needed to correctly + * handle merging with the OOM queue would be quite complex and expensive + * to maintain. Besides, in such a critical condition as an out of memory, + * the benefits of queue merging may be little relevant, or even negligible. + */ +static struct bfq_queue * +bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, + void *io_struct, bool request) +{ + struct bfq_queue *in_service_bfqq, *new_bfqq; + + if (bfqq->new_bfqq) + return bfqq->new_bfqq; + if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq)) + return NULL; + /* If device has only one backlogged bfq_queue, don't search. */ + if (bfqd->busy_queues == 1) + return NULL; + + in_service_bfqq = bfqd->in_service_queue; + + if (!in_service_bfqq || in_service_bfqq == bfqq || + !bfqd->in_service_bic || + unlikely(in_service_bfqq == &bfqd->oom_bfqq)) + goto check_scheduled; + + if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) && + bfqq->entity.parent == in_service_bfqq->entity.parent && + bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) { + new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq); + if (new_bfqq) + return new_bfqq; + } + /* + * Check whether there is a cooperator among currently scheduled + * queues. The only thing we need is that the bio/request is not + * NULL, as we need it to establish whether a cooperator exists. + */ +check_scheduled: + new_bfqq = bfq_find_close_cooperator(bfqd, bfqq, + bfq_io_struct_pos(io_struct, request)); + + BUG_ON(new_bfqq && bfqq->entity.parent != new_bfqq->entity.parent); + + if (new_bfqq && likely(new_bfqq != &bfqd->oom_bfqq) && + bfq_may_be_close_cooperator(bfqq, new_bfqq)) + return bfq_setup_merge(bfqq, new_bfqq); + + return NULL; +} + +static void bfq_bfqq_save_state(struct bfq_queue *bfqq) +{ + /* + * If !bfqq->bic, the queue is already shared or its requests + * have already been redirected to a shared queue; both idle window + * and weight raising state have already been saved. Do nothing. + */ + if (!bfqq->bic) + return; + if (bfqq->bic->wr_time_left) + /* + * This is the queue of a just-started process, and would + * deserve weight raising: we set wr_time_left to the full + * weight-raising duration to trigger weight-raising when + * and if the queue is split and the first request of the + * queue is enqueued. + */ + bfqq->bic->wr_time_left = bfq_wr_duration(bfqq->bfqd); + else if (bfqq->wr_coeff > 1) { + unsigned long wr_duration = + jiffies - bfqq->last_wr_start_finish; + /* + * It may happen that a queue's weight raising period lasts + * longer than its wr_cur_max_time, as weight raising is + * handled only when a request is enqueued or dispatched (it + * does not use any timer). If the weight raising period is + * about to end, don't save it. + */ + if (bfqq->wr_cur_max_time <= wr_duration) + bfqq->bic->wr_time_left = 0; + else + bfqq->bic->wr_time_left = + bfqq->wr_cur_max_time - wr_duration; + /* + * The bfq_queue is becoming shared or the requests of the + * process owning the queue are being redirected to a shared + * queue. Stop the weight raising period of the queue, as in + * both cases it should not be owned by an interactive or + * soft real-time application. + */ + bfq_bfqq_end_wr(bfqq); + } else + bfqq->bic->wr_time_left = 0; + bfqq->bic->saved_idle_window = bfq_bfqq_idle_window(bfqq); + bfqq->bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq); + bfqq->bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq); + bfqq->bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node); + bfqq->bic->cooperations++; + bfqq->bic->failed_cooperations = 0; +} + +static void bfq_get_bic_reference(struct bfq_queue *bfqq) +{ + /* + * If bfqq->bic has a non-NULL value, the bic to which it belongs + * is about to begin using a shared bfq_queue. + */ + if (bfqq->bic) + atomic_long_inc(&bfqq->bic->icq.ioc->refcount); +} + +static void +bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, + struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) +{ + bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", + (long unsigned)new_bfqq->pid); + /* Save weight raising and idle window of the merged queues */ + bfq_bfqq_save_state(bfqq); + bfq_bfqq_save_state(new_bfqq); + if (bfq_bfqq_IO_bound(bfqq)) + bfq_mark_bfqq_IO_bound(new_bfqq); + bfq_clear_bfqq_IO_bound(bfqq); + /* + * Grab a reference to the bic, to prevent it from being destroyed + * before being possibly touched by a bfq_split_bfqq(). + */ + bfq_get_bic_reference(bfqq); + bfq_get_bic_reference(new_bfqq); + /* + * Merge queues (that is, let bic redirect its requests to new_bfqq) + */ + bic_set_bfqq(bic, new_bfqq, 1); + bfq_mark_bfqq_coop(new_bfqq); + /* + * new_bfqq now belongs to at least two bics (it is a shared queue): + * set new_bfqq->bic to NULL. bfqq either: + * - does not belong to any bic any more, and hence bfqq->bic must + * be set to NULL, or + * - is a queue whose owning bics have already been redirected to a + * different queue, hence the queue is destined to not belong to + * any bic soon and bfqq->bic is already NULL (therefore the next + * assignment causes no harm). + */ + new_bfqq->bic = NULL; + bfqq->bic = NULL; + bfq_put_queue(bfqq); +} + +static void bfq_bfqq_increase_failed_cooperations(struct bfq_queue *bfqq) +{ + struct bfq_io_cq *bic = bfqq->bic; + struct bfq_data *bfqd = bfqq->bfqd; + + if (bic && bfq_bfqq_cooperations(bfqq) >= bfqd->bfq_coop_thresh) { + bic->failed_cooperations++; + if (bic->failed_cooperations >= bfqd->bfq_failed_cooperations) + bic->cooperations = 0; + } +} + +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, *new_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) + return 0; + + bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio)); + /* + * We take advantage of this function to perform an early merge + * of the queues of possible cooperating processes. + */ + if (bfqq) { + new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false); + if (new_bfqq) { + bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq); + /* + * If we get here, the bio will be queued in the + * shared queue, i.e., new_bfqq, so use new_bfqq + * to decide whether bio and rq can be merged. + */ + bfqq = new_bfqq; + } else + bfq_bfqq_increase_failed_cooperations(bfqq); + } + + return bfqq == 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 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_pos_tree_add_move(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 + * 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 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 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, + bool compensate, + enum bfqq_expiration reason) +{ + bool 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 bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq) +{ + if (bfq_bfqq_budget_new(bfqq) || + time_before(jiffies, bfqq->budget_timeout)) + return false; + return true; +} + +/* + * 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 bool 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); +} + +/* + * For a queue that becomes empty, device idling is allowed only if + * this function returns true for that queue. As a consequence, since + * device idling plays a critical role for both throughput boosting + * and service guarantees, the return value of this function plays a + * critical role as well. + * + * In a nutshell, this function returns true only if idling is + * beneficial for throughput or, even if detrimental for throughput, + * idling is however necessary to preserve service guarantees (low + * latency, desired throughput distribution, ...). In particular, on + * NCQ-capable devices, this function tries to return false, so as to + * help keep the drives' internal queues full, whenever this helps the + * device boost the throughput without causing any service-guarantee + * issue. + * + * In more detail, the return value of this function is obtained by, + * first, computing a number of boolean variables that take into + * account throughput and service-guarantee issues, and, then, + * combining these variables in a logical expression. Most of the + * issues taken into account are not trivial. We discuss these issues + * while introducing the variables. + */ +static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq) +{ + struct bfq_data *bfqd = bfqq->bfqd; + bool idling_boosts_thr, idling_boosts_thr_without_issues, + all_queues_seeky, on_hdd_and_not_all_queues_seeky, + idling_needed_for_service_guarantees, + asymmetric_scenario; + + /* + * The next variable takes into account the cases where idling + * boosts the throughput. + * + * The value of the variable is computed considering, first, that + * idling is virtually always beneficial for the throughput if: + * (a) the device is not NCQ-capable, or + * (b) regardless of the presence of NCQ, the device is rotational + * and the request pattern for bfqq is I/O-bound and sequential. + * + * Secondly, and in contrast to the above item (b), idling an + * NCQ-capable flash-based device would not boost the + * throughput even with sequential I/O; rather it would lower + * the throughput in proportion to how fast the device + * is. Accordingly, the next variable is true if any of the + * above conditions (a) and (b) is true, and, in particular, + * happens to be false if bfqd is an NCQ-capable flash-based + * device. + */ + idling_boosts_thr = !bfqd->hw_tag || + (!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq) && + bfq_bfqq_idle_window(bfqq)) ; + + /* + * The value of the next variable, + * idling_boosts_thr_without_issues, is equal to that of + * idling_boosts_thr, unless a special case holds. In this + * special case, described below, idling may cause problems to + * weight-raised queues. + * + * When the request pool is saturated (e.g., in the presence + * of write hogs), if the processes associated with + * non-weight-raised queues ask for requests at a lower rate, + * then processes associated with weight-raised queues have a + * higher probability to get a request from the pool + * immediately (or at least soon) when they need one. Thus + * they have a higher probability to actually get a fraction + * of the device 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. + * + * For this reason, we force to false the value of + * idling_boosts_thr_without_issues if there are weight-raised + * busy queues. In this case, and if bfqq is not weight-raised, + * this guarantees that the device is not idled for bfqq (if, + * instead, bfqq is weight-raised, then idling will be + * guaranteed by another variable, see below). Combined with + * the timestamping rules of BFQ (see [1] for details), this + * behavior causes bfqq, and hence any sync non-weight-raised + * queue, to get a lower number of requests served, and thus + * to ask for a lower number of requests from the request + * pool, before the busy weight-raised queues get served + * again. This often mitigates starvation problems in the + * presence of heavy write workloads and NCQ, thereby + * guaranteeing a higher application and system responsiveness + * in these hostile scenarios. + */ + idling_boosts_thr_without_issues = idling_boosts_thr && + bfqd->wr_busy_queues == 0; + + /* + * There are then two cases where idling must be performed not + * for throughput concerns, but to preserve service + * guarantees. In the description of these cases, we say, for + * short, that a queue is sequential/random if the process + * associated to the queue issues sequential/random requests + * (in the second case the queue may be tagged as seeky or + * even constantly_seeky). + * + * To introduce the first case, we note that, since + * bfq_bfqq_idle_window(bfqq) is false if the device is + * NCQ-capable and bfqq is random (see + * bfq_update_idle_window()), then, from the above two + * assignments it follows that + * idling_boosts_thr_without_issues is false if the device is + * NCQ-capable and bfqq is random. Therefore, for this case, + * device idling would never be allowed if we used just + * idling_boosts_thr_without_issues to decide whether to allow + * it. And, beneficially, this would imply that throughput + * would always be boosted also with random I/O on NCQ-capable + * HDDs. + * + * But we must be careful on this point, to avoid an unfair + * treatment for bfqq. In fact, because of the same above + * assignments, idling_boosts_thr_without_issues is, on the + * other hand, true if 1) the device is an HDD and bfqq is + * sequential, and 2) there are no busy weight-raised + * queues. As a consequence, if we used just + * idling_boosts_thr_without_issues to decide whether to idle + * the device, then with an HDD we might easily bump into a + * scenario where queues that are sequential and I/O-bound + * would enjoy idling, whereas random queues would not. The + * latter might then get a low share of the device throughput, + * simply because the former would get many requests served + * after being set as in service, while the latter would not. + * + * To address this issue, we start by setting to true a + * sentinel variable, on_hdd_and_not_all_queues_seeky, if the + * device is rotational and not all queues with pending or + * in-flight requests are constantly seeky (i.e., there are + * active sequential queues, and bfqq might then be mistreated + * if it does not enjoy idling because it is random). + */ + all_queues_seeky = bfq_bfqq_constantly_seeky(bfqq) && + bfqd->busy_in_flight_queues == + bfqd->const_seeky_busy_in_flight_queues; + + on_hdd_and_not_all_queues_seeky = + !blk_queue_nonrot(bfqd->queue) && !all_queues_seeky; + + /* + * To introduce the second case where idling needs to be + * performed to preserve service guarantees, we can note that + * 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 particular, + * the critical situation is when requests from different + * processes happens to be present, at the same time, in the + * internal queue(s) of the drive. In such a situation, the + * drive, by deciding the service order of the + * internally-queued requests, does determine also the actual + * throughput distribution among these processes. But the + * drive typically has no notion or concern about per-process + * throughput distribution, and makes its decisions only on a + * per-request basis. Therefore, the service distribution + * enforced by the drive's internal scheduler is likely to + * coincide with the desired device-throughput distribution + * only in a completely symmetric scenario where: + * (i) each of these processes must get the same throughput as + * the others; + * (ii) all these processes have the same I/O pattern + (either sequential or random). + * In fact, in such a scenario, the drive will tend to treat + * the requests of each of these processes in about the same + * way as the requests of the others, and thus to provide + * each of these processes with about the same throughput + * (which is exactly the desired throughput distribution). In + * contrast, in any asymmetric scenario, device idling is + * certainly needed to guarantee that bfqq receives its + * assigned fraction of the device throughput (see [1] for + * details). + * + * We address this issue by controlling, actually, only the + * symmetry sub-condition (i), i.e., provided that + * sub-condition (i) holds, idling is not performed, + * regardless of whether sub-condition (ii) holds. In other + * words, only if sub-condition (i) holds, then idling is + * allowed, and the device tends to be prevented from queueing + * many requests, possibly of several processes. The reason + * for not controlling also sub-condition (ii) is that, first, + * in the case of an HDD, the asymmetry in terms of types of + * I/O patterns is already taken in to account in the above + * sentinel variable + * on_hdd_and_not_all_queues_seeky. Secondly, in the case of a + * flash-based device, we prefer however to privilege + * throughput (and idling lowers throughput for this type of + * devices), for the following reasons: + * 1) differently from HDDs, the service time of random + * requests is not orders of magnitudes lower than the service + * time of sequential requests; thus, even if processes doing + * sequential I/O get a preferential treatment with respect to + * others doing random I/O, the consequences are not as + * dramatic as with HDDs; + * 2) if a process doing random I/O does need strong + * throughput guarantees, it is hopefully already being + * weight-raised, or the user is likely to have assigned it a + * higher weight than the other processes (and thus + * sub-condition (i) is likely to be false, which triggers + * idling). + * + * According to the above considerations, the next variable is + * true (only) if sub-condition (i) holds. To compute the + * value of this variable, we not only use the return value of + * the function bfq_symmetric_scenario(), but also check + * whether bfqq is being weight-raised, because + * bfq_symmetric_scenario() does not take into account also + * weight-raised queues (see comments to + * bfq_weights_tree_add()). + * + * As a side note, it is worth considering that the above + * device-idling countermeasures may however fail in the + * following unlucky scenario: if idling is (correctly) + * disabled in a time period during which all symmetry + * sub-conditions hold, and hence the device is allowed to + * enqueue many requests, but at some later point in time some + * sub-condition stops to hold, then it may become impossible + * to let requests be served in the desired order until all + * the requests already queued in the device have been served. + */ + asymmetric_scenario = bfqq->wr_coeff > 1 || + !bfq_symmetric_scenario(bfqd); + + /* + * Finally, there is a case where maximizing throughput is the + * best choice even if it may cause unfairness toward + * bfqq. Such a case is when bfqq became active in a burst of + * queue activations. Queues that became active during a large + * burst benefit only from throughput, as discussed in the + * comments to bfq_handle_burst. Thus, if bfqq became active + * in a burst and not idling the device maximizes throughput, + * then the device must no be idled, because not idling the + * device provides bfqq and all other queues in the burst with + * maximum benefit. Combining this and the two cases above, we + * can now establish when idling is actually needed to + * preserve service guarantees. + */ + idling_needed_for_service_guarantees = + (on_hdd_and_not_all_queues_seeky || asymmetric_scenario) && + !bfq_bfqq_in_large_burst(bfqq); + + /* + * We have now all the components we need to compute the return + * value of the function, which is true only if both the following + * conditions hold: + * 1) bfqq is sync, because idling make sense only for sync queues; + * 2) idling either boosts the throughput (without issues), or + * is necessary to preserve service guarantees. + */ + return bfq_bfqq_sync(bfqq) && + (idling_boosts_thr_without_issues || + idling_needed_for_service_guarantees); +} + +/* + * If the in-service queue is empty but the function bfq_bfqq_may_idle + * returns true, then: + * 1) the queue must remain in service and cannot be expired, and + * 2) the device must be idled to wait for the possible arrival of a new + * request for the queue. + * See the comments to the function bfq_bfqq_may_idle for the reasons + * why performing device idling is the best choice to boost the throughput + * and preserve service guarantees when bfq_bfqq_may_idle itself + * returns true. + */ +static 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_may_idle(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; + struct request *next_rq; + enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT; + + bfqq = bfqd->in_service_queue; + if (!bfqq) + goto new_queue; + + bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue"); + + 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) { + 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); +#ifdef CONFIG_BFQ_GROUP_IOSCHED + bfqg_stats_update_idle_time(bfqq_group(bfqq)); +#endif + } + goto keep_queue; + } + } + + /* + * No requests pending. However, if the in-service queue is idling + * for a new request, or has requests waiting for a completion and + * may idle after their completion, then keep it anyway. + */ + if (timer_pending(&bfqd->idle_slice_timer) || + (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) { + bfqq = NULL; + goto keep_queue; + } + + reason = BFQ_BFQQ_NO_MORE_REQUESTS; +expire: + bfq_bfqq_expire(bfqd, bfqq, false, reason); +new_queue: + bfqq = bfq_set_in_service_queue(bfqd); + bfq_log(bfqd, "select_queue: new queue %d returned", + bfqq ? bfqq->pid : 0); +keep_queue: + return bfqq; +} + +static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + struct bfq_entity *entity = &bfqq->entity; + if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */ + 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->prio_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 period, or the queue has + * exceeded the acceptable number of cooperations, + * then end weight raising. + */ + if (bfq_bfqq_in_large_burst(bfqq) || + bfq_bfqq_cooperations(bfqq) >= bfqd->bfq_coop_thresh || + 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); + } + } + /* Update weight both if it must be raised and if it must be lowered */ + if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1)) + __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) + 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 %d", + blk_rq_sectors(rq), + (long long unsigned)blk_rq_pos(rq), + bfq_bfqq_budget_left(bfqq)); + + dispatched++; + + if (!bfqd->in_service_bic) { + 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, false, BFQ_BFQQ_BUDGET_EXHAUSTED); + return dispatched; +} + +static int __bfq_forced_dispatch_bfqq(struct bfq_queue *bfqq) +{ + int dispatched = 0; + + while (bfqq->next_rq) { + 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) + __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) + return 0; + + if (bfq_class_idle(bfqq)) + max_dispatch = 1; + + if (!bfq_bfqq_sync(bfqq)) + max_dispatch = bfqd->bfq_max_budget_async_rq; + + if (!bfq_bfqq_sync(bfqq) && 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 %s request", + bfq_bfqq_sync(bfqq) ? "sync" : "async"); + + 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; +#ifdef CONFIG_BFQ_GROUP_IOSCHED + struct bfq_group *bfqg = bfqq_group(bfqq); +#endif + + 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)); + BUG_ON(bfqq->allocated[READ] + bfqq->allocated[WRITE] != 0); + BUG_ON(bfqq->entity.tree); + 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); +#ifdef CONFIG_BFQ_GROUP_IOSCHED + bfqg_put(bfqg); +#endif +} + +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 void bfq_init_icq(struct io_cq *icq) +{ + struct bfq_io_cq *bic = icq_to_bic(icq); + + bic->ttime.last_end_request = jiffies; + /* + * A newly created bic indicates that the process has just + * started doing I/O, and is probably mapping into memory its + * executable and libraries: it definitely needs weight raising. + * There is however the possibility that the process performs, + * for a while, I/O close to some other process. EQM intercepts + * this behavior and may merge the queue corresponding to the + * process with some other queue, BEFORE the weight of the queue + * is raised. Merged queues are not weight-raised (they are assumed + * to belong to processes that benefit only from high throughput). + * If the merge is basically the consequence of an accident, then + * the queue will be split soon and will get back its old weight. + * It is then important to write down somewhere that this queue + * does need weight raising, even if it did not make it to get its + * weight raised before being merged. To this purpose, we overload + * the field raising_time_left and assign 1 to it, to mark the queue + * as needing weight raising. + */ + bic->wr_time_left = 1; +} + +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]) { + /* + * If the bic is using a shared queue, put the reference + * taken on the io_context when the bic started using a + * shared bfq_queue. + */ + if (bfq_bfqq_coop(bic->bfqq[BLK_RW_SYNC])) + put_io_context(icq->ioc); + 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_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) +{ + struct task_struct *tsk = current; + int ioprio_class; + + 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->new_ioprio = task_nice_ioprio(tsk); + bfqq->new_ioprio_class = task_nice_ioclass(tsk); + break; + case IOPRIO_CLASS_RT: + bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + bfqq->new_ioprio_class = IOPRIO_CLASS_RT; + break; + case IOPRIO_CLASS_BE: + bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + bfqq->new_ioprio_class = IOPRIO_CLASS_BE; + break; + case IOPRIO_CLASS_IDLE: + bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE; + bfqq->new_ioprio = 7; + bfq_clear_bfqq_idle_window(bfqq); + break; + } + + if (bfqq->new_ioprio < 0 || bfqq->new_ioprio >= IOPRIO_BE_NR) { + printk(KERN_CRIT "bfq_set_next_ioprio_data: new_ioprio %d\n", + bfqq->new_ioprio); + BUG(); + } + + bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio); + bfqq->entity.prio_changed = 1; +} + +static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) +{ + struct bfq_data *bfqd; + struct bfq_queue *bfqq, *new_bfqq; + 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) || likely(bic->ioprio == ioprio)) + goto out; + + bic->ioprio = ioprio; + + bfqq = bic->bfqq[BLK_RW_ASYNC]; + if (bfqq) { + new_bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic, + GFP_ATOMIC); + if (new_bfqq) { + bic->bfqq[BLK_RW_ASYNC] = new_bfqq; + bfq_log_bfqq(bfqd, bfqq, + "check_ioprio_change: bfqq %p %d", + bfqq, atomic_read(&bfqq->ref)); + bfq_put_queue(bfqq); + } + } + + bfqq = bic->bfqq[BLK_RW_SYNC]; + if (bfqq) + bfq_set_next_ioprio_data(bfqq, bic); + +out: + bfq_put_bfqd_unlock(bfqd, &flags); +} + +static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, + struct bfq_io_cq *bic, 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; + + 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); + 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 bio *bio, int is_sync, + struct bfq_io_cq *bic, + gfp_t gfp_mask) +{ + struct bfq_group *bfqg; + struct bfq_queue *bfqq, *new_bfqq = NULL; + struct blkcg *blkcg; + +retry: + rcu_read_lock(); + + blkcg = bio_blkcg(bio); + bfqg = bfq_find_alloc_group(bfqd, blkcg); + /* 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 || bfqq == &bfqd->oom_bfqq) { + bfqq = NULL; + if (new_bfqq) { + bfqq = new_bfqq; + new_bfqq = NULL; + } else if (gfpflags_allow_blocking(gfp_mask)) { + rcu_read_unlock(); + 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) + goto retry; + } else { + bfqq = kmem_cache_alloc_node(bfq_pool, + gfp_mask | __GFP_ZERO, + 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"); + } + } + + if (new_bfqq) + kmem_cache_free(bfq_pool, new_bfqq); + + rcu_read_unlock(); + + 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 bio *bio, 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) { + struct blkcg *blkcg; + struct bfq_group *bfqg; + + rcu_read_lock(); + blkcg = bio_blkcg(bio); + rcu_read_unlock(); + bfqg = bfq_find_alloc_group(bfqd, blkcg); + async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class, + ioprio); + bfqq = *async_bfqq; + } + + if (!bfqq) + bfqq = bfq_find_alloc_queue(bfqd, bio, is_sync, bic, gfp_mask); + + /* + * Pin the queue now that it's allocated, scheduler exit will + * prune it. + */ + if (!is_sync && !(*async_bfqq)) { + 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; + + /* Idle window just restored, statistics are meaningless. */ + if (bfq_bfqq_just_split(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_clear_bfqq_just_split(bfqq); + + 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)) { + 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 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); +#ifdef CONFIG_BFQ_GROUP_IOSCHED + bfqg_stats_update_idle_time(bfqq_group(bfqq)); +#endif + + /* + * 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, + 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), *new_bfqq; + + assert_spin_locked(bfqd->queue->queue_lock); + + /* + * An unplug may trigger a requeue of a request from the device + * driver: make sure we are in process context while trying to + * merge two bfq_queues. + */ + if (!in_interrupt()) { + new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true); + if (new_bfqq) { + if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq) + new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1); + /* + * Release the request's reference to the old bfqq + * and make sure one is taken to the shared queue. + */ + new_bfqq->allocated[rq_data_dir(rq)]++; + bfqq->allocated[rq_data_dir(rq)]--; + atomic_inc(&new_bfqq->ref); + bfq_put_queue(bfqq); + if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq) + bfq_merge_bfqqs(bfqd, RQ_BIC(rq), + bfqq, new_bfqq); + rq->elv.priv[1] = new_bfqq; + bfqq = new_bfqq; + } else + bfq_bfqq_increase_failed_cooperations(bfqq); + } + + bfq_add_request(rq); + + /* + * Here a newly-created bfq_queue has already started a weight-raising + * period: clear raising_time_left to prevent bfq_bfqq_save_state() + * from assigning it a full weight-raising period. See the detailed + * comments about this field in bfq_init_icq(). + */ + if (bfqq->bic) + bfqq->bic->wr_time_left = 0; + 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--; +#ifdef CONFIG_BFQ_GROUP_IOSCHED + bfqg_stats_update_completion(bfqq_group(bfqq), + rq_start_time_ns(rq), + rq_io_start_time_ns(rq), rq->cmd_flags); +#endif + + 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, false, + BFQ_BFQQ_BUDGET_TIMEOUT); + else if (RB_EMPTY_ROOT(&bfqq->sort_list) && + (bfqq->dispatched == 0 || + !bfq_bfqq_may_idle(bfqq))) + bfq_bfqq_expire(bfqd, bfqq, false, + BFQ_BFQQ_NO_MORE_REQUESTS); + } + + if (!bfqd->rq_in_driver) + bfq_schedule_dispatch(bfqd); + +out: + return; +} + +static 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) + return ELV_MQUEUE_MAY; + + bfqq = bic_to_bfqq(bic, rw_is_sync(rw)); + if (bfqq) + 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) { + 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); + } +} + +/* + * 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"); + + put_io_context(bic->icq.ioc); + + 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; + unsigned long flags; + bool split = false; + + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); + + bfq_check_ioprio_change(bic, bio); + + spin_lock_irqsave(q->queue_lock, flags); + + if (!bic) + goto queue_fail; + + bfq_bic_update_cgroup(bic, bio); + +new_queue: + bfqq = bic_to_bfqq(bic, is_sync); + if (!bfqq || bfqq == &bfqd->oom_bfqq) { + bfqq = bfq_get_queue(bfqd, bio, is_sync, bic, gfp_mask); + bic_set_bfqq(bic, bfqq, is_sync); + if (split && is_sync) { + if ((bic->was_in_burst_list && bfqd->large_burst) || + bic->saved_in_large_burst) + bfq_mark_bfqq_in_large_burst(bfqq); + else { + bfq_clear_bfqq_in_large_burst(bfqq); + if (bic->was_in_burst_list) + hlist_add_head(&bfqq->burst_list_node, + &bfqd->burst_list); + } + } + } 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); + split = true; + if (!bfqq) + goto new_queue; + } + } + + 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; + + /* + * If a bfq_queue has only one process reference, it is owned + * by only one bfq_io_cq: we can set the bic field of the + * bfq_queue to the address of that structure. Also, if the + * queue has just been split, mark a flag so that the + * information is available to the other scheduler hooks. + */ + if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) { + bfqq->bic = bic; + if (split) { + bfq_mark_bfqq_just_split(bfqq); + /* + * If the queue has just been split from a shared + * queue, restore the idle window and the possible + * weight raising period. + */ + bfq_bfqq_resume_state(bfqq, bic); + } + } + + 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) { + 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, true, 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 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) { + 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); + list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) + bfq_deactivate_bfqq(bfqd, bfqq, 0); + + spin_unlock_irq(q->queue_lock); + + bfq_shutdown_timer_wq(bfqd); + + synchronize_rcu(); + + BUG_ON(timer_pending(&bfqd->idle_slice_timer)); + +#ifdef CONFIG_BFQ_GROUP_IOSCHED + blkcg_deactivate_policy(q, &blkcg_policy_bfq); +#else + kfree(bfqd->root_group); +#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 + root_group->rq_pos_tree = RB_ROOT; + for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) + root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT; +} + +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; + + /* + * 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); + atomic_inc(&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; + + spin_lock_irq(q->queue_lock); + q->elevator = eq; + spin_unlock_irq(q->queue_lock); + + 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); +#ifdef CONFIG_BFQ_GROUP_IOSCHED + 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->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_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; + +out_free: + kfree(bfqd); + kobject_put(&eq->kobj); + return -ENOMEM; +} + +static void bfq_slab_kill(void) +{ + if (bfq_pool) + 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, "%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_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_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 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(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, +#ifdef CONFIG_BFQ_GROUP_IOSCHED + .elevator_bio_merged_fn = bfq_bio_merged, +#endif + .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) +{ + int ret; + + /* + * 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; + +#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; + + /* + * 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; + + ret = elv_register(&iosched_bfq); + if (ret) + goto err_pol_unreg; + + pr_info("BFQ I/O-scheduler: v7r11"); + + 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); +#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("Arianna Avanzini, Fabio Checconi, Paolo Valente"); +MODULE_LICENSE("GPL"); diff -Naurp linux-4.4.0-20160123.orig/block/bfq-sched.c linux-4.4.0-20160123/block/bfq-sched.c --- linux-4.4.0-20160123.orig/block/bfq-sched.c 1969-12-31 19:00:00.000000000 -0500 +++ linux-4.4.0-20160123/block/bfq-sched.c 2016-01-27 02:03:28.329861525 -0500 @@ -0,0 +1,1200 @@ +/* + * BFQ: Hierarchical B-WF2Q+ scheduler. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2010 Paolo Valente + */ + +#ifdef CONFIG_BFQ_GROUP_IOSCHED +#define for_each_entity(entity) \ + for (; entity ; 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 struct bfq_group *bfqq_group(struct bfq_queue *bfqq); + +static 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); + + 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) + 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) + /* 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) + bfq_update_budget(next_in_service); + + return 1; +} + +static 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 ; entity = NULL) + +#define for_each_entity_safe(entity, parent) \ + for (parent = NULL; entity ; entity = parent) + +static int bfq_update_next_in_service(struct bfq_sched_data *sd) +{ + return 0; +} + +static void bfq_check_next_in_service(struct bfq_sched_data *sd, + struct bfq_entity *entity) +{ +} + +static 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 int bfq_gt(u64 a, u64 b) +{ + return (s64)(a - b) > 0; +} + +static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity) +{ + struct bfq_queue *bfqq = NULL; + + BUG_ON(!entity); + + if (!entity->my_sched_data) + 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 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 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) { + 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 struct bfq_entity *bfq_entity_of(struct rb_node *node) +{ + struct bfq_entity *entity = NULL; + + if (node) + 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 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) + 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); + + while (*node) { + 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 void bfq_update_min(struct bfq_entity *entity, struct rb_node *node) +{ + struct bfq_entity *child; + + if (node) { + 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 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) + return; + + if (node == parent->rb_left && parent->rb_right) + bfq_update_active_node(parent->rb_right); + else if (parent->rb_left) + 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_BFQ_GROUP_IOSCHED + 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) + node = node->rb_left; + else if (node->rb_right) + node = node->rb_right; + + bfq_update_active_tree(node); + +#ifdef CONFIG_BFQ_GROUP_IOSCHED + 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) + list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list); +#ifdef CONFIG_BFQ_GROUP_IOSCHED + 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 unsigned short bfq_ioprio_to_weight(int ioprio) +{ + BUG_ON(ioprio < 0 || ioprio >= IOPRIO_BE_NR); + return IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - ioprio; +} + +/** + * bfq_weight_to_ioprio - calc an ioprio from a weight. + * @weight: the weight value to convert. + * + * To preserve as much 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 * BFQ_WEIGHT_CONVERSION_COEFF. + */ +static unsigned short bfq_weight_to_ioprio(int weight) +{ + BUG_ON(weight < BFQ_MIN_WEIGHT || weight > BFQ_MAX_WEIGHT); + return IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight < 0 ? + 0 : IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight; +} + +static void bfq_get_entity(struct bfq_entity *entity) +{ + struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); + + if (bfqq) { + 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 && !node->rb_left) + deepest = rb_parent(node); + else if (!node->rb_right) + deepest = node->rb_left; + else if (!node->rb_left) + deepest = node->rb_right; + else { + deepest = rb_next(node); + if (deepest->rb_right) + 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_BFQ_GROUP_IOSCHED + 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) + bfq_update_active_tree(node); + +#ifdef CONFIG_BFQ_GROUP_IOSCHED + 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) + list_del(&bfqq->bfqq_list); +#ifdef CONFIG_BFQ_GROUP_IOSCHED + 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 || bfq_gt(first_idle->finish, entity->finish)) + st->first_idle = entity; + if (!last_idle || bfq_gt(entity->finish, last_idle->finish)) + st->last_idle = entity; + + bfq_insert(&st->idle, entity); + + if (bfqq) + 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) { + 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 && + !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 && !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->prio_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_BFQ_GROUP_IOSCHED + struct bfq_sched_data *sd; + struct bfq_group *bfqg; +#endif + + if (bfqq) + bfqd = bfqq->bfqd; +#ifdef CONFIG_BFQ_GROUP_IOSCHED + 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; + if (bfqq) + bfqq->ioprio = + bfq_weight_to_ioprio(entity->orig_weight); + } + + if (bfqq) + bfqq->ioprio_class = bfqq->new_ioprio_class; + entity->prio_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 ? 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; +} + +#ifdef CONFIG_BFQ_GROUP_IOSCHED +static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg); +#endif + +/** + * 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, int 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); + } +#ifdef CONFIG_BFQ_GROUP_IOSCHED + bfqg_stats_set_start_empty_time(bfqq_group(bfqq)); +#endif + bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d 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 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); + /* + * 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; + int was_in_service; + int ret = 0; + + if (sd == NULL || !entity->on_st) /* never activated, or inactive */ + return 0; + + st = bfq_entity_service_tree(entity); + was_in_service = entity == sd->in_service_entity; + + BUG_ON(was_in_service && entity->tree); + + 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) + 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) + /* + * 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) { + 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) { + 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) + break; + node = node->rb_right; + } + + BUG_ON(!first && !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); + + if (bfqd && + jiffies - bfqd->bfq_class_idle_last_service > BFQ_CL_IDLE_TIMEOUT) { + entity = __bfq_lookup_next_entity(st + BFQ_IOPRIO_CLASSES - 1, + true); + if (entity) { + 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) { + 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); + + if (bfqd->busy_queues == 0) + return NULL; + + sd = &bfqd->root_group->sched_data; + for (; sd ; sd = entity->my_sched_data) { + entity = bfq_lookup_next_entity(sd, 1, bfqd); + BUG_ON(!entity); + entity->service = 0; + } + + bfqq = bfq_entity_to_bfqq(entity); + BUG_ON(!bfqq); + + return bfqq; +} + +static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd) +{ + if (bfqd->in_service_bic) { + 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); +} + +#ifdef CONFIG_BFQ_GROUP_IOSCHED +static void bfqg_stats_update_dequeue(struct bfq_group *bfqg); +#endif + +/* + * 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--; + +#ifdef CONFIG_BFQ_GROUP_IOSCHED + bfqg_stats_update_dequeue(bfqq_group(bfqq)); +#endif + + 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 -Naurp linux-4.4.0-20160123.orig/block/Kconfig.iosched linux-4.4.0-20160123/block/Kconfig.iosched --- linux-4.4.0-20160123.orig/block/Kconfig.iosched 2016-01-27 02:02:57.139861710 -0500 +++ linux-4.4.0-20160123/block/Kconfig.iosched 2016-01-27 02:03:28.329861525 -0500 @@ -39,6 +39,25 @@ config CFQ_GROUP_IOSCHED ---help--- Enable group IO scheduling in CFQ. +config IOSCHED_BFQ + tristate "BFQ I/O scheduler" + default n + ---help--- + The BFQ I/O scheduler tries to distribute bandwidth among + all processes according to their weights. + It aims at distributing the bandwidth as desired, independently of + the disk parameters and with any workload. It also tries to + guarantee low latency to interactive and soft real-time + applications. If compiled built-in (saying Y here), BFQ can + be configured to support hierarchical scheduling. + +config BFQ_GROUP_IOSCHED + bool "BFQ hierarchical scheduling support" + depends on CGROUPS && IOSCHED_BFQ=y + default n + ---help--- + Enable hierarchical scheduling in BFQ, using the blkio controller. + choice prompt "Default I/O scheduler" default DEFAULT_CFQ @@ -52,6 +71,16 @@ choice config DEFAULT_CFQ bool "CFQ" if IOSCHED_CFQ=y + config DEFAULT_BFQ + bool "BFQ" if IOSCHED_BFQ=y + help + Selects BFQ as the default I/O scheduler which will be + used by default for all block devices. + The BFQ I/O scheduler aims at distributing the bandwidth + as desired, independently of the disk parameters and with + any workload. It also tries to guarantee low latency to + interactive and soft real-time applications. + config DEFAULT_NOOP bool "No-op" @@ -61,6 +90,7 @@ config DEFAULT_IOSCHED string default "deadline" if DEFAULT_DEADLINE default "cfq" if DEFAULT_CFQ + default "bfq" if DEFAULT_BFQ default "noop" if DEFAULT_NOOP endmenu diff -Naurp linux-4.4.0-20160123.orig/block/Makefile linux-4.4.0-20160123/block/Makefile --- linux-4.4.0-20160123.orig/block/Makefile 2016-01-27 02:02:57.139861710 -0500 +++ linux-4.4.0-20160123/block/Makefile 2016-01-27 02:03:23.129861556 -0500 @@ -18,6 +18,7 @@ obj-$(CONFIG_BLK_DEV_THROTTLING) += blk- obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o +obj-$(CONFIG_IOSCHED_BFQ) += bfq-iosched.o obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o diff -Naurp linux-4.4.0-20160123.orig/include/linux/blkdev.h linux-4.4.0-20160123/include/linux/blkdev.h --- linux-4.4.0-20160123.orig/include/linux/blkdev.h 2016-01-27 02:02:57.139861710 -0500 +++ linux-4.4.0-20160123/include/linux/blkdev.h 2016-01-27 02:03:23.129861556 -0500 @@ -44,7 +44,7 @@ struct pr_ops; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 2 +#define BLKCG_MAX_POLS 3 struct request; typedef void (rq_end_io_fn)(struct request *, int);