path: root/block/blk-mq.c

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/smp.h>
#include <linux/llist.h>
#include <linux/list_sort.h>
#include <linux/cpu.h>
#include <linux/cache.h>
#include <linux/sched/sysctl.h>
#include <linux/delay.h>

#include <trace/events/block.h>

#include <linux/blk-mq.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"

static DEFINE_MUTEX(all_q_mutex);
static LIST_HEAD(all_q_list);

static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx);

DEFINE_PER_CPU(struct llist_head, ipi_lists);

static struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
					   unsigned int cpu)
{
	return per_cpu_ptr(q->queue_ctx, cpu);
}

/*
 * This assumes per-cpu software queueing queues. They could be per-node
 * as well, for instance. For now this is hardcoded as-is. Note that we don't
 * care about preemption, since we know the ctx's are persistent. This does
 * mean that we can't rely on ctx always matching the currently running CPU.
 */
static struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
{
	return __blk_mq_get_ctx(q, get_cpu());
}

static void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
{
	put_cpu();
}

/*
 * Check if any of the ctx's have pending work in this hardware queue
 */
static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
{
	unsigned int i;

	for (i = 0; i < hctx->nr_ctx_map; i++)
		if (hctx->ctx_map[i])
			return true;

	return false;
}

/*
 * Mark this ctx as having pending work in this hardware queue
 */
static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
				     struct blk_mq_ctx *ctx)
{
	if (!test_bit(ctx->index_hw, hctx->ctx_map))
		set_bit(ctx->index_hw, hctx->ctx_map);
}

static struct request *blk_mq_alloc_rq(struct blk_mq_hw_ctx *hctx, gfp_t gfp,
				       bool reserved)
{
	struct request *rq;
	unsigned int tag;

	tag = blk_mq_get_tag(hctx->tags, gfp, reserved);
	if (tag != BLK_MQ_TAG_FAIL) {
		rq = hctx->rqs[tag];
		rq->tag = tag;

		return rq;
	}

	return NULL;
}

static int blk_mq_queue_enter(struct request_queue *q)
{
	int ret;

	__percpu_counter_add(&q->mq_usage_counter, 1, 1000000);
	smp_wmb();
	/* we have problems to freeze the queue if it's initializing */
	if (!blk_queue_bypass(q) || !blk_queue_init_done(q))
		return 0;

	__percpu_counter_add(&q->mq_usage_counter, -1, 1000000);

	spin_lock_irq(q->queue_lock);
	ret = wait_event_interruptible_lock_irq(q->mq_freeze_wq,
		!blk_queue_bypass(q) || blk_queue_dying(q),
		*q->queue_lock);
	/* inc usage with lock hold to avoid freeze_queue runs here */
	if (!ret && !blk_queue_dying(q))
		__percpu_counter_add(&q->mq_usage_counter, 1, 1000000);
	else if (blk_queue_dying(q))
		ret = -ENODEV;
	spin_unlock_irq(q->queue_lock);

	return ret;
}

static void blk_mq_queue_exit(struct request_queue *q)
{
	__percpu_counter_add(&q->mq_usage_counter, -1, 1000000);
}

static void __blk_mq_drain_queue(struct request_queue *q)
{
	while (true) {
		s64 count;

		spin_lock_irq(q->queue_lock);
		count = percpu_counter_sum(&q->mq_usage_counter);
		spin_unlock_irq(q->queue_lock);

		if (count == 0)
			break;
		blk_mq_run_queues(q, false);
		msleep(10);
	}
}

/*
 * Guarantee no request is in use, so we can change any data structure of
 * the queue afterward.
 */
static void blk_mq_freeze_queue(struct request_queue *q)
{
	bool drain;

	spin_lock_irq(q->queue_lock);
	drain = !q->bypass_depth++;
	queue_flag_set(QUEUE_FLAG_BYPASS, q);
	spin_unlock_irq(q->queue_lock);

	if (drain)
		__blk_mq_drain_queue(q);
}

void blk_mq_drain_queue(struct request_queue *q)
{
	__blk_mq_drain_queue(q);
}

static void blk_mq_unfreeze_queue(struct request_queue *q)
{
	bool wake = false;

	spin_lock_irq(q->queue_lock);
	if (!--q->bypass_depth) {
		queue_flag_clear(QUEUE_FLAG_BYPASS, q);
		wake = true;
	}
	WARN_ON_ONCE(q->bypass_depth < 0);
	spin_unlock_irq(q->queue_lock);
	if (wake)
		wake_up_all(&q->mq_freeze_wq);
}

bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
{
	return blk_mq_has_free_tags(hctx->tags);
}
EXPORT_SYMBOL(blk_mq_can_queue);

static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
			       struct request *rq, unsigned int rw_flags)
{
	if (blk_queue_io_stat(q))
		rw_flags |= REQ_IO_STAT;

	rq->mq_ctx = ctx;
	rq->cmd_flags = rw_flags;
	rq->start_time = jiffies;
	set_start_time_ns(rq);
	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
}

static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
					      gfp_t gfp, bool reserved)
{
	return blk_mq_alloc_rq(hctx, gfp, reserved);
}

static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
						   int rw, gfp_t gfp,
						   bool reserved)
{
	struct request *rq;

	do {
		struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
		struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q, ctx->cpu);

		rq = __blk_mq_alloc_request(hctx, gfp & ~__GFP_WAIT, reserved);
		if (rq) {
			blk_mq_rq_ctx_init(q, ctx, rq, rw);
			break;
		}

		blk_mq_put_ctx(ctx);
		if (!(gfp & __GFP_WAIT))
			break;

		__blk_mq_run_hw_queue(hctx);
		blk_mq_wait_for_tags(hctx->tags);
	} while (1);

	return rq;
}

struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
		gfp_t gfp, bool reserved)
{
	struct request *rq;

	if (blk_mq_queue_enter(q))
		return NULL;

	rq = blk_mq_alloc_request_pinned(q, rw, gfp, reserved);
	if (rq)
		blk_mq_put_ctx(rq->mq_ctx);
	return rq;
}

struct request *blk_mq_alloc_reserved_request(struct request_queue *q, int rw,
					      gfp_t gfp)
{
	struct request *rq;

	if (blk_mq_queue_enter(q))
		return NULL;

	rq = blk_mq_alloc_request_pinned(q, rw, gfp, true);
	if (rq)
		blk_mq_put_ctx(rq->mq_ctx);
	return rq;
}
EXPORT_SYMBOL(blk_mq_alloc_reserved_request);

/*
 * Re-init and set pdu, if we have it
 */
static void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
	blk_rq_init(hctx->queue, rq);

	if (hctx->cmd_size)
		rq->special = blk_mq_rq_to_pdu(rq);
}

static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
				  struct blk_mq_ctx *ctx, struct request *rq)
{
	const int tag = rq->tag;
	struct request_queue *q = rq->q;

	blk_mq_rq_init(hctx, rq);
	blk_mq_put_tag(hctx->tags, tag);

	blk_mq_queue_exit(q);
}

void blk_mq_free_request(struct request *rq)
{
	struct blk_mq_ctx *ctx = rq->mq_ctx;
	struct blk_mq_hw_ctx *hctx;
	struct request_queue *q = rq->q;

	ctx->rq_completed[rq_is_sync(rq)]++;

	hctx = q->mq_ops->map_queue(q, ctx->cpu);
	__blk_mq_free_request(hctx, ctx, rq);
}

static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error)
{
	if (error)
		clear_bit(BIO_UPTODATE, &bio->bi_flags);
	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
		error = -EIO;

	if (unlikely(rq->cmd_flags & REQ_QUIET))
		set_bit(BIO_QUIET, &bio->bi_flags);

	/* don't actually finish bio if it's part of flush sequence */
	if (!(rq->cmd_flags & REQ_FLUSH_SEQ))
		bio_endio(bio, error);
}

void blk_mq_complete_request(struct request *rq, int error)
{
	struct bio *bio = rq->bio;
	unsigned int bytes = 0;

	trace_block_rq_complete(rq->q, rq);

	while (bio) {
		struct bio *next = bio->bi_next;

		bio->bi_next = NULL;
		bytes += bio->bi_iter.bi_size;
		blk_mq_bio_endio(rq, bio, error);
		bio = next;
	}

	blk_account_io_completion(rq, bytes);

	blk_account_io_done(rq);

	if (rq->end_io)
		rq->end_io(rq, error);
	else
		blk_mq_free_request(rq);
}

void __blk_mq_end_io(struct request *rq, int error)
{
	if (!blk_mark_rq_complete(rq))
		blk_mq_complete_request(rq, error);
}

#if defined(CONFIG_SMP)

/*
 * Called with interrupts disabled