diff options
Diffstat (limited to 'block')
| -rw-r--r-- | block/bfq-iosched.c | 3 | ||||
| -rw-r--r-- | block/bfq-iosched.h | 24 | ||||
| -rw-r--r-- | block/bfq-wf2q.c | 148 | ||||
| -rw-r--r-- | block/bio-integrity.c | 6 | ||||
| -rw-r--r-- | block/blk-core.c | 4 | ||||
| -rw-r--r-- | block/blk-mq-cpumap.c | 4 | ||||
| -rw-r--r-- | block/blk-mq.c | 21 |
7 files changed, 126 insertions, 84 deletions
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 60a6835265fc..436b6ca6b175 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4299,6 +4299,9 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_NO_MORE_REQUESTS); } + + if (!bfqd->rq_in_driver) + bfq_schedule_dispatch(bfqd); } static void bfq_put_rq_priv_body(struct bfq_queue *bfqq) diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 8fd83b885774..859f0a8c97c8 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -52,7 +52,7 @@ struct bfq_entity; struct bfq_service_tree { /* tree for active entities (i.e., those backlogged) */ struct rb_root active; - /* tree for idle entities (i.e., not backlogged, with V <= F_i)*/ + /* tree for idle entities (i.e., not backlogged, with V < F_i)*/ struct rb_root idle; /* idle entity with minimum F_i */ @@ -71,17 +71,29 @@ struct bfq_service_tree { * * 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. It is used to reduce the number of steps - * needed for each hierarchical-schedule update. + * intermediate queue in a hierarchical setup. * * 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. + * + * The schedule is implemented by the service trees, plus the field + * @next_in_service, which points to the entity on the active trees + * that will be served next, if 1) no changes in the schedule occurs + * before the current in-service entity is expired, 2) the in-service + * queue becomes idle when it expires, and 3) if the entity pointed by + * in_service_entity is not a queue, then the in-service child entity + * of the entity pointed by in_service_entity becomes idle on + * expiration. This peculiar definition allows for the following + * optimization, not yet exploited: while a given entity is still in + * service, we already know which is the best candidate for next + * service among the other active entitities in the same parent + * entity. We can then quickly compare the timestamps of the + * in-service entity with those of such best candidate. + * + * All fields are protected by the lock of the containing bfqd. */ struct bfq_sched_data { /* entity in service */ diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index 5ec05cd42b80..911aa7431dbe 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -188,21 +188,23 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service) /* * This function tells whether entity stops being a candidate for next - * service, according to the following logic. + * service, according to the restrictive definition of the field + * next_in_service. In particular, this function is invoked for an + * entity that is about to be set in service. * - * This function is invoked for an entity that is about to be set in - * service. If such an entity is a queue, then the entity is no longer - * a candidate for next service (i.e, a candidate entity to serve - * after the in-service entity is expired). The function then returns - * true. + * If entity is a queue, then the entity is no longer a candidate for + * next service according to the that definition, because entity is + * about to become the in-service queue. This function then returns + * true if entity is a queue. * - * In contrast, the entity could stil be a candidate for next service - * if it is not a queue, and has more than one child. In fact, even if - * one of its children is about to be set in service, other children - * may still be the next to serve. As a consequence, a non-queue - * entity is not a candidate for next-service only if it has only one - * child. And only if this condition holds, then the function returns - * true for a non-queue entity. + * In contrast, entity could still be a candidate for next service if + * it is not a queue, and has more than one active child. In fact, + * even if one of its children is about to be set in service, other + * active children may still be the next to serve, for the parent + * entity, even according to the above definition. As a consequence, a + * non-queue entity is not a candidate for next-service only if it has + * only one active child. And only if this condition holds, then this + * function returns true for a non-queue entity. */ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity) { @@ -213,6 +215,18 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity) bfqg = container_of(entity, struct bfq_group, entity); + /* + * The field active_entities does not always contain the + * actual number of active children entities: it happens to + * not account for the in-service entity in case the latter is + * removed from its active tree (which may get done after + * invoking the function bfq_no_longer_next_in_service in + * bfq_get_next_queue). Fortunately, here, i.e., while + * bfq_no_longer_next_in_service is not yet completed in + * bfq_get_next_queue, bfq_active_extract has not yet been + * invoked, and thus active_entities still coincides with the + * actual number of active entities. + */ if (bfqg->active_entities == 1) return true; @@ -954,7 +968,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity, * one of its children receives a new request. * * Basically, this function updates the timestamps of entity and - * inserts entity into its active tree, ater possible extracting it + * inserts entity into its active tree, ater possibly extracting it * from its idle tree. */ static void __bfq_activate_entity(struct bfq_entity *entity, @@ -1048,7 +1062,7 @@ static void __bfq_requeue_entity(struct bfq_entity *entity) entity->start = entity->finish; /* * In addition, if the entity had more than one child - * when set in service, then was not extracted from + * when set in service, then it was not extracted from * the active tree. This implies that the position of * the entity in the active tree may need to be * changed now, because we have just updated the start @@ -1056,9 +1070,8 @@ static void __bfq_requeue_entity(struct bfq_entity *entity) * time in a moment (the requeueing is then, more * precisely, a repositioning in this case). To * implement this repositioning, we: 1) dequeue the - * entity here, 2) update the finish time and - * requeue the entity according to the new - * timestamps below. + * entity here, 2) update the finish time and requeue + * the entity according to the new timestamps below. */ if (entity->tree) bfq_active_extract(st, entity); @@ -1105,9 +1118,10 @@ static void __bfq_activate_requeue_entity(struct bfq_entity *entity, /** - * bfq_activate_entity - activate or requeue an entity representing a bfq_queue, - * and activate, requeue or reposition all ancestors - * for which such an update becomes necessary. + * bfq_activate_requeue_entity - activate or requeue an entity representing a + * bfq_queue, and activate, requeue or reposition + * all ancestors for which such an update becomes + * necessary. * @entity: the entity to activate. * @non_blocking_wait_rq: true if this entity was waiting for a request * @requeue: true if this is a requeue, which implies that bfqq is @@ -1135,9 +1149,9 @@ static void bfq_activate_requeue_entity(struct bfq_entity *entity, * @ins_into_idle_tree: if false, the entity will not be put into the * idle tree. * - * Deactivates an entity, independently from its previous state. Must + * Deactivates an entity, independently of its previous state. Must * be invoked only if entity is on a service tree. Extracts the entity - * from that tree, and if necessary and allowed, puts it on the idle + * from that tree, and if necessary and allowed, puts it into the idle * tree. */ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree) @@ -1158,8 +1172,10 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree) st = bfq_entity_service_tree(entity); is_in_service = entity == sd->in_service_entity; - if (is_in_service) + if (is_in_service) { bfq_calc_finish(entity, entity->service); + sd->in_service_entity = NULL; + } if (entity->tree == &st->active) bfq_active_extract(st, entity); @@ -1177,7 +1193,7 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree) /** * bfq_deactivate_entity - deactivate an entity representing a bfq_queue. * @entity: the entity to deactivate. - * @ins_into_idle_tree: true if the entity can be put on the idle tree + * @ins_into_idle_tree: true if the entity can be put into the idle tree */ static void bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree, @@ -1208,16 +1224,29 @@ static void bfq_deactivate_entity(struct bfq_entity *entity, */ bfq_update_next_in_service(sd, NULL); - if (sd->next_in_service) + if (sd->next_in_service || sd->in_service_entity) { /* - * The parent entity is still backlogged, - * because next_in_service is not NULL. So, no - * further upwards deactivation must be - * performed. Yet, next_in_service has - * changed. Then the schedule does need to be - * updated upwards. + * The parent entity is still active, because + * either next_in_service or in_service_entity + * is not NULL. So, no further upwards + * deactivation must be performed. Yet, + * next_in_service has changed. Then the + * schedule does need to be updated upwards. + * + * NOTE If in_service_entity is not NULL, then + * next_in_service may happen to be NULL, + * although the parent entity is evidently + * active. This happens if 1) the entity + * pointed by in_service_entity is the only + * active entity in the parent entity, and 2) + * according to the definition of + * next_in_service, the in_service_entity + * cannot be considered as + * next_in_service. See the comments on the + * definition of next_in_service for details. */ break; + } /* * If we get here, then the parent is no more @@ -1297,7 +1326,7 @@ static void bfq_update_vtime(struct bfq_service_tree *st, u64 new_value) * * 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 + * 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. */ @@ -1494,47 +1523,34 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd) /* * If entity is no longer a candidate for next - * service, then we extract it from its active tree, - * for the following reason. To further boost the - * throughput in some special case, BFQ needs to know - * which is the next candidate entity to serve, while - * there is already an entity in service. In this - * respect, to make it easy to compute/update the next - * candidate entity to serve after the current - * candidate has been set in service, there is a case - * where it is necessary to extract the current - * candidate from its service tree. Such a case is - * when the entity just set in service cannot be also - * a candidate for next service. Details about when - * this conditions holds are reported in the comments - * on the function bfq_no_longer_next_in_service() - * invoked below. + * service, then it must be extracted from its active + * tree, so as to make sure that it won't be + * considered when computing next_in_service. See the + * comments on the function + * bfq_no_longer_next_in_service() for details. */ if (bfq_no_longer_next_in_service(entity)) bfq_active_extract(bfq_entity_service_tree(entity), entity); /* - * For the same reason why we may have just extracted - * entity from its active tree, we may need to update - * next_in_service for the sched_data of entity too, - * regardless of whether entity has been extracted. - * In fact, even if entity has not been extracted, a - * descendant entity may get extracted. Such an event - * would cause a change in next_in_service for the - * level of the descendant entity, and thus possibly - * back to upper levels. + * Even if entity is not to be extracted according to + * the above check, a descendant entity may get + * extracted in one of the next iterations of this + * loop. Such an event could cause a change in + * next_in_service for the level of the descendant + * entity, and thus possibly back to this level. * - * We cannot perform the resulting needed update - * before the end of this loop, because, to know which - * is the correct next-to-serve candidate entity for - * each level, we need first to find the leaf entity - * to set in service. In fact, only after we know - * which is the next-to-serve leaf entity, we can - * discover whether the parent entity of the leaf - * entity becomes the next-to-serve, and so on. + * However, we cannot perform the resulting needed + * update of next_in_service for this level before the + * end of the whole loop, because, to know which is + * the correct next-to-serve candidate entity for each + * level, we need first to find the leaf entity to set + * in service. In fact, only after we know which is + * the next-to-serve leaf entity, we can discover + * whether the parent entity of the leaf entity + * becomes the next-to-serve, and so on. */ - } bfqq = bfq_entity_to_bfqq(entity); diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 83e92beb3c9f..9b1ea478577b 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -387,9 +387,11 @@ static void bio_integrity_verify_fn(struct work_struct *work) */ bool __bio_integrity_endio(struct bio *bio) { - if (bio_op(bio) == REQ_OP_READ && !bio->bi_status) { - struct bio_integrity_payload *bip = bio_integrity(bio); + struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev); + struct bio_integrity_payload *bip = bio_integrity(bio); + if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && + (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->profile->verify_fn) { INIT_WORK(&bip->bip_work, bio_integrity_verify_fn); queue_work(kintegrityd_wq, &bip->bip_work); return false; diff --git a/block/blk-core.c b/block/blk-core.c index 970b9c9638c5..dbecbf4a64e0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -3421,6 +3421,10 @@ EXPORT_SYMBOL(blk_finish_plug); */ void blk_pm_runtime_init(struct request_queue *q, struct device *dev) { + /* not support for RQF_PM and ->rpm_status in blk-mq yet */ + if (q->mq_ops) + return; + q->dev = dev; q->rpm_status = RPM_ACTIVE; pm_runtime_set_autosuspend_delay(q->dev, -1); diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index 4891f042a22f..9f8cffc8a701 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -17,9 +17,9 @@ static int cpu_to_queue_index(unsigned int nr_queues, const int cpu) { /* - * Non online CPU will be mapped to queue index 0. + * Non present CPU will be mapped to queue index 0. */ - if (!cpu_online(cpu)) + if (!cpu_present(cpu)) return 0; return cpu % nr_queues; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 041f7b7fa0d6..535cbdf32aab 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -301,11 +301,12 @@ static struct request *blk_mq_get_request(struct request_queue *q, struct elevator_queue *e = q->elevator; struct request *rq; unsigned int tag; + struct blk_mq_ctx *local_ctx = NULL; blk_queue_enter_live(q); data->q = q; if (likely(!data->ctx)) - data->ctx = blk_mq_get_ctx(q); + data->ctx = local_ctx = blk_mq_get_ctx(q); if (likely(!data->hctx)) data->hctx = blk_mq_map_queue(q, data->ctx->cpu); if (op & REQ_NOWAIT) @@ -324,6 +325,10 @@ static struct request *blk_mq_get_request(struct request_queue *q, tag = blk_mq_get_tag(data); if (tag == BLK_MQ_TAG_FAIL) { + if (local_ctx) { + blk_mq_put_ctx(local_ctx); + data->ctx = NULL; + } blk_queue_exit(q); return NULL; } @@ -356,12 +361,12 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, rq = blk_mq_get_request(q, NULL, op, &alloc_data); - blk_mq_put_ctx(alloc_data.ctx); - blk_queue_exit(q); - if (!rq) return ERR_PTR(-EWOULDBLOCK); + blk_mq_put_ctx(alloc_data.ctx); + blk_queue_exit(q); + rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; @@ -407,11 +412,11 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, rq = blk_mq_get_request(q, NULL, op, &alloc_data); - blk_queue_exit(q); - if (!rq) return ERR_PTR(-EWOULDBLOCK); + blk_queue_exit(q); + return rq; } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); @@ -679,8 +684,8 @@ EXPORT_SYMBOL(blk_mq_kick_requeue_list); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs) { - kblockd_schedule_delayed_work(&q->requeue_work, - msecs_to_jiffies(msecs)); + kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, + msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); |