diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 4c72073830f3..1c52e56a19b1 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -7,6 +7,7 @@ #include #include #include +#include #include @@ -80,6 +81,37 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) blk_mq_run_hw_queue(hctx, true); } +static int sched_rq_cmp(void *priv, struct list_head *a, struct list_head *b) +{ + struct request *rqa = container_of(a, struct request, queuelist); + struct request *rqb = container_of(b, struct request, queuelist); + + return rqa->mq_hctx > rqb->mq_hctx; +} + +static bool blk_mq_dispatch_hctx_list(struct list_head *rq_list) +{ + struct blk_mq_hw_ctx *hctx = + list_first_entry(rq_list, struct request, queuelist)->mq_hctx; + struct request *rq; + LIST_HEAD(hctx_list); + unsigned int count = 0; + bool ret; + + list_for_each_entry(rq, rq_list, queuelist) { + if (rq->mq_hctx != hctx) { + list_cut_before(&hctx_list, rq_list, &rq->queuelist); + goto dispatch; + } + count++; + } + list_splice_tail_init(rq_list, &hctx_list); + +dispatch: + ret = blk_mq_dispatch_rq_list(hctx, &hctx_list, count); + return ret; +} + #define BLK_MQ_BUDGET_DELAY 3 /* ms units */ /* @@ -90,20 +122,29 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to * be run again. This is necessary to avoid starving flushes. */ -static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) +static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct elevator_queue *e = q->elevator; + bool multi_hctxs = false, run_queue = false; + bool dispatched = false, busy = false; + unsigned int max_dispatch; LIST_HEAD(rq_list); - int ret = 0; - struct request *rq; + int count = 0; + + if (hctx->dispatch_busy) + max_dispatch = 1; + else + max_dispatch = hctx->queue->nr_requests; do { + struct request *rq; + if (e->type->ops.has_work && !e->type->ops.has_work(hctx)) break; if (!list_empty_careful(&hctx->dispatch)) { - ret = -EAGAIN; + busy = true; break; } @@ -120,7 +161,7 @@ static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) * no guarantee anyone will kick the queue. Kick it * ourselves. */ - blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); + run_queue = true; break; } @@ -129,8 +170,42 @@ static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) * if this rq won't be queued to driver via .queue_rq() * in blk_mq_dispatch_rq_list(). */ - list_add(&rq->queuelist, &rq_list); - } while (blk_mq_dispatch_rq_list(rq->mq_hctx, &rq_list, 1)); + list_add_tail(&rq->queuelist, &rq_list); + if (rq->mq_hctx != hctx) + multi_hctxs = true; + } while (++count < max_dispatch); + + if (!count) { + if (run_queue) + blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); + } else if (multi_hctxs) { + /* + * Requests from different hctx may be dequeued from some + * schedulers, such as bfq and deadline. + * + * Sort the requests in the list according to their hctx, + * dispatch batching requests from same hctx at a time. + */ + list_sort(NULL, &rq_list, sched_rq_cmp); + do { + dispatched |= blk_mq_dispatch_hctx_list(&rq_list); + } while (!list_empty(&rq_list)); + } else { + dispatched = blk_mq_dispatch_rq_list(hctx, &rq_list, count); + } + + if (busy) + return -EAGAIN; + return !!dispatched; +} + +static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) +{ + int ret; + + do { + ret = __blk_mq_do_dispatch_sched(hctx); + } while (ret == 1); return ret; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 1b701e166681..a8fac4ff6fef 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1319,8 +1319,6 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, if (list_empty(list)) return false; - WARN_ON(!list_is_singular(list) && nr_budgets); - /* * Now process all the entries, sending them to the driver. */