Contributors: 7
Author Tokens Token Proportion Commits Commit Proportion
Jens Axboe 1218 51.72% 9 24.32%
Ming Lei 698 29.64% 15 40.54%
Omar Sandoval 372 15.80% 7 18.92%
Christoph Hellwig 48 2.04% 3 8.11%
Keith Busch 13 0.55% 1 2.70%
Sagi Grimberg 3 0.13% 1 2.70%
Paolo Valente 3 0.13% 1 2.70%
Total 2355 37 


/*
 * blk-mq scheduling framework
 *
 * Copyright (C) 2016 Jens Axboe
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/blk-mq.h>

#include <trace/events/block.h>

#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
#include "blk-mq-sched.h"
#include "blk-mq-tag.h"
#include "blk-wbt.h"

void blk_mq_sched_free_hctx_data(struct request_queue *q,
				 void (*exit)(struct blk_mq_hw_ctx *))
{
	struct blk_mq_hw_ctx *hctx;
	int i;

	queue_for_each_hw_ctx(q, hctx, i) {
		if (exit && hctx->sched_data)
			exit(hctx);
		kfree(hctx->sched_data);
		hctx->sched_data = NULL;
	}
}
EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);

void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio)
{
	struct request_queue *q = rq->q;
	struct io_context *ioc = rq_ioc(bio);
	struct io_cq *icq;

	spin_lock_irq(q->queue_lock);
	icq = ioc_lookup_icq(ioc, q);
	spin_unlock_irq(q->queue_lock);

	if (!icq) {
		icq = ioc_create_icq(ioc, q, GFP_ATOMIC);
		if (!icq)
			return;
	}
	get_io_context(icq->ioc);
	rq->elv.icq = icq;
}

/*
 * Mark a hardware queue as needing a restart. For shared queues, maintain
 * a count of how many hardware queues are marked for restart.
 */
static void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
{
	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
		return;

	set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
}

void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
{
	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
		return;
	clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);

	blk_mq_run_hw_queue(hctx, true);
}

/*
 * Only SCSI implements .get_budget and .put_budget, and SCSI restarts
 * its queue by itself in its completion handler, so we don't need to
 * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE.
 */
static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
{
	struct request_queue *q = hctx->queue;
	struct elevator_queue *e = q->elevator;
	LIST_HEAD(rq_list);

	do {
		struct request *rq;

		if (e->type->ops.mq.has_work &&
				!e->type->ops.mq.has_work(hctx))
			break;

		if (!blk_mq_get_dispatch_budget(hctx))
			break;

		rq = e->type->ops.mq.dispatch_request(hctx);
		if (!rq) {
			blk_mq_put_dispatch_budget(hctx);
			break;
		}

		/*
		 * Now this rq owns the budget which has to be released
		 * 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(q, &rq_list, true));
}

static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx,
					  struct blk_mq_ctx *ctx)
{
	unsigned idx = ctx->index_hw;

	if (++idx == hctx->nr_ctx)
		idx = 0;

	return hctx->ctxs[idx];
}

/*
 * Only SCSI implements .get_budget and .put_budget, and SCSI restarts
 * its queue by itself in its completion handler, so we don't need to
 * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE.
 */
static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
{
	struct request_queue *q = hctx->queue;
	LIST_HEAD(rq_list);
	struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from);

	do {
		struct request *rq;

		if (!sbitmap_any_bit_set(&hctx->ctx_map))
			break;

		if (!blk_mq_get_dispatch_budget(hctx))
			break;

		rq = blk_mq_dequeue_from_ctx(hctx, ctx);
		if (!rq) {
			blk_mq_put_dispatch_budget(hctx);
			break;
		}

		/*
		 * Now this rq owns the budget which has to be released
		 * if this rq won't be queued to driver via .queue_rq()
		 * in blk_mq_dispatch_rq_list().
		 */
		list_add(&rq->queuelist, &rq_list);

		/* round robin for fair dispatch */
		ctx = blk_mq_next_ctx(hctx, rq->mq_ctx);

	} while (blk_mq_dispatch_rq_list(q, &rq_list, true));

	WRITE_ONCE(hctx->dispatch_from, ctx);
}

void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
{
	struct request_queue *q = hctx->queue;
	struct elevator_queue *e = q->elevator;
	const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
	LIST_HEAD(rq_list);

	/* RCU or SRCU read lock is needed before checking quiesced flag */
	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
		return;

	hctx->run++;

	/*
	 * If we have previous entries on our dispatch list, grab them first for
	 * more fair dispatch.
	 */
	if (!list_empty_careful(&hctx->dispatch)) {
		spin_lock(&hctx->lock);
		if (!list_empty(&hctx->dispatch))
			list_splice_init(&hctx->dispatch, &rq_list);
		spin_unlock(&hctx->lock);
	}

	/*
	 * Only ask the scheduler for requests, if we didn't have residual
	 * requests from the dispatch list. This is to avoid the case where
	 * we only ever dispatch a fraction of the requests available because
	 * of low device queue depth. Once we pull requests out of the IO
	 * scheduler, we can no longer merge or sort them. So it's best to
	 * leave them there for as long as we can. Mark the hw queue as
	 * needing a restart in that case.
	 *
	 * We want to dispatch from the scheduler if there was nothing
	 * on the dispatch list or we were able to dispatch from the
	 * dispatch list.
	 */
	if (!list_empty(&rq_list)) {
		blk_mq_sched_mark_restart_hctx(hctx);
		if (blk_mq_dispatch_rq_list(q, &rq_list, false)) {
			if (has_sched_dispatch)
				blk_mq_do_dispatch_sched(hctx);
			else
				blk_mq_do_dispatch_ctx(hctx);
		}
	} else if (has_sched_dispatch) {
		blk_mq_do_dispatch_sched(hctx);
	} else if (hctx->dispatch_busy) {
		/* dequeue request one by one from sw queue if queue is busy */
		blk_mq_do_dispatch_ctx(hctx);
	} else {
		blk_mq_flush_busy_ctxs(hctx, &rq_list);
		blk_mq_dispatch_rq_list(q, &rq_list, false);
	}
}

bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
			    struct request **merged_request)
{
	struct request *rq;

	switch (elv_merge(q, &rq, bio)) {
	case ELEVATOR_BACK_MERGE:
		if (!blk_mq_sched_allow_merge(q, rq, bio))
			return false;
		if (!bio_attempt_back_merge(q, rq, bio))
			return false;
		*merged_request = attempt_back_merge(q, rq);
		if (!*merged_request)
			elv_merged_request(q, rq, ELEVATOR_BACK_MERGE);
		return true;
	case ELEVATOR_FRONT_MERGE:
		if (!blk_mq_sched_allow_merge(q, rq, bio))
			return false;
		if (!bio_attempt_front_merge(q, rq, bio))
			return false;
		*merged_request = attempt_front_merge(q, rq);
		if (!*merged_request)
			elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE);
		return true;
	case ELEVATOR_DISCARD_MERGE:
		return bio_attempt_discard_merge(q, rq, bio);
	default:
		return false;
	}
}
EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);

/*
 * Iterate list of requests and see if we can merge this bio with any
 * of them.
 */
bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
			   struct bio *bio)
{
	struct request *rq;
	int checked = 8;

	list_for_each_entry_reverse(rq, list, queuelist) {
		bool merged = false;

		if (!checked--)
			break;

		if (!blk_rq_merge_ok(rq, bio))
			continue;

		switch (blk_try_merge(rq, bio)) {
		case ELEVATOR_BACK_MERGE:
			if (blk_mq_sched_allow_merge(q, rq, bio))
				merged = bio_attempt_back_merge(q, rq, bio);
			break;
		case ELEVATOR_FRONT_MERGE:
			if (blk_mq_sched_allow_merge(q, rq, bio))
				merged = bio_attempt_front_merge(q, rq, bio);
			break;
		case ELEVATOR_DISCARD_MERGE:
			merged = bio_attempt_discard_merge(q, rq, bio);
			break;
		default:
			continue;
		}

		return merged;
	}

	return false;
}
EXPORT_SYMBOL_GPL(blk_mq_bio_list_merge);

/*
 * Reverse check our software queue for entries that we could potentially
 * merge with. Currently includes a hand-wavy stop count of 8, to not spend
 * too much time checking for merges.
 */
static bool blk_mq_attempt_merge(struct request_queue *q,
				 struct blk_mq_ctx *ctx, struct bio *bio)
{
	lockdep_assert_held(&ctx->lock);

	if (blk_mq_bio_list_merge(q, &ctx->rq_list, bio)) {
		ctx->rq_merged++;
		return true;
	}

	return false;
}

bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
	struct elevator_queue *e = q->elevator;
	struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
	bool ret = false;

	if (e && e->type->ops.mq.bio_merge) {
		blk_mq_put_ctx(ctx);
		return e->type->ops.mq.bio_merge(hctx, bio);
	}

	if ((hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
			!list_empty_careful(&ctx->rq_list)) {
		/* default per sw-queue merge */
		spin_lock(&ctx->lock);
		ret = blk_mq_attempt_merge(q, ctx, bio);
		spin_unlock(&ctx->lock);
	}

	blk_mq_put_ctx(ctx);
	return ret;
}

bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq)
{
	return rq_mergeable(rq) && elv_attempt_insert_merge(q, rq);
}
EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge);

void blk_mq_sched_request_inserted(struct request *rq)
{
	trace_block_rq_insert(rq->q, rq);
}
EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);

static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
				       bool has_sched,
				       struct request *rq)
{
	/* dispatch flush rq directly */
	if (rq->rq_flags & RQF_FLUSH_SEQ) {
		spin_lock(&hctx->lock);
		list_add(&rq->queuelist, &hctx->dispatch);
		spin_unlock(&hctx->lock);
		return true;
	}

	if (has_sched)
		rq->rq_flags |= RQF_SORTED;

	return false;
}

void blk_mq_sched_insert_request(struct request *rq, bool at_head,
				 bool run_queue, bool async)
{
	struct request_queue *q = rq->q;
	struct elevator_queue *e = q->elevator;
	struct blk_mq_ctx *ctx = rq->mq_ctx;
	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);

	/* flush rq in flush machinery need to be dispatched directly */
	if (!(rq->rq_flags & RQF_FLUSH_SEQ) && op_is_flush(rq->cmd_flags)) {
		blk_insert_flush(rq);
		goto run;
	}

	WARN_ON(e && (rq->tag != -1));

	if (blk_mq_sched_bypass_insert(hctx, !!e, rq))
		goto run;

	if (e && e->type->ops.mq.insert_requests) {
		LIST_HEAD(list);

		list_add(&rq->queuelist, &list);
		e->type->ops.mq.insert_requests(hctx, &list, at_head);
	} else {
		spin_lock(&ctx->lock);
		__blk_mq_insert_request(hctx, rq, at_head);
		spin_unlock(&ctx->lock);
	}

run:
	if (run_queue)
		blk_mq_run_hw_queue(hctx, async);
}

void blk_mq_sched_insert_requests(struct request_queue *q,
				  struct blk_mq_ctx *ctx,
				  struct list_head *list, bool run_queue_async)
{
	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
	struct elevator_queue *e = hctx->queue->elevator;

	if (e && e->type->ops.mq.insert_requests)
		e->type->ops.mq.insert_requests(hctx, list, false);
	else {
		/*
		 * try to issue requests directly if the hw queue isn't
		 * busy in case of 'none' scheduler, and this way may save
		 * us one extra enqueue & dequeue to sw queue.
		 */
		if (!hctx->dispatch_busy && !e && !run_queue_async) {
			blk_mq_try_issue_list_directly(hctx, list);
			if (list_empty(list))
				return;
		}
		blk_mq_insert_requests(hctx, ctx, list);
	}

	blk_mq_run_hw_queue(hctx, run_queue_async);
}

static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
				   struct blk_mq_hw_ctx *hctx,
				   unsigned int hctx_idx)
{
	if (hctx->sched_tags) {
		blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx);
		blk_mq_free_rq_map(hctx->sched_tags);
		hctx->sched_tags = NULL;
	}
}

static int blk_mq_sched_alloc_tags(struct request_queue *q,
				   struct blk_mq_hw_ctx *hctx,
				   unsigned int hctx_idx)
{
	struct blk_mq_tag_set *set = q->tag_set;
	int ret;

	hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests,
					       set->reserved_tags);
	if (!hctx->sched_tags)
		return -ENOMEM;

	ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests);
	if (ret)
		blk_mq_sched_free_tags(set, hctx, hctx_idx);

	return ret;
}

static void blk_mq_sched_tags_teardown(struct request_queue *q)
{
	struct blk_mq_tag_set *set = q->tag_set;
	struct blk_mq_hw_ctx *hctx;
	int i;

	queue_for_each_hw_ctx(q, hctx, i)
		blk_mq_sched_free_tags(set, hctx, i);
}

int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
{
	struct blk_mq_hw_ctx *hctx;
	struct elevator_queue *eq;
	unsigned int i;
	int ret;

	if (!e) {
		q->elevator = NULL;
		q->nr_requests = q->tag_set->queue_depth;
		return 0;
	}

	/*
	 * Default to double of smaller one between hw queue_depth and 128,
	 * since we don't split into sync/async like the old code did.
	 * Additionally, this is a per-hw queue depth.
	 */
	q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth,
				   BLKDEV_MAX_RQ);

	queue_for_each_hw_ctx(q, hctx, i) {
		ret = blk_mq_sched_alloc_tags(q, hctx, i);
		if (ret)
			goto err;
	}

	ret = e->ops.mq.init_sched(q, e);
	if (ret)
		goto err;

	blk_mq_debugfs_register_sched(q);

	queue_for_each_hw_ctx(q, hctx, i) {
		if (e->ops.mq.init_hctx) {
			ret = e->ops.mq.init_hctx(hctx, i);
			if (ret) {
				eq = q->elevator;
				blk_mq_exit_sched(q, eq);
				kobject_put(&eq->kobj);
				return ret;
			}
		}
		blk_mq_debugfs_register_sched_hctx(q, hctx);
	}

	return 0;

err:
	blk_mq_sched_tags_teardown(q);
	q->elevator = NULL;
	return ret;
}

void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
{
	struct blk_mq_hw_ctx *hctx;
	unsigned int i;

	queue_for_each_hw_ctx(q, hctx, i) {
		blk_mq_debugfs_unregister_sched_hctx(hctx);
		if (e->type->ops.mq.exit_hctx && hctx->sched_data) {
			e->type->ops.mq.exit_hctx(hctx, i);
			hctx->sched_data = NULL;
		}
	}
	blk_mq_debugfs_unregister_sched(q);
	if (e->type->ops.mq.exit_sched)
		e->type->ops.mq.exit_sched(e);
	blk_mq_sched_tags_teardown(q);
	q->elevator = NULL;
}