blk-mq.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Block multiqueue core code
 *
 * Copyright (C) 2013-2014 Jens Axboe
 * Copyright (C) 2013-2014 Christoph Hellwig
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/blk-integrity.h>
#include <linux/kmemleak.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/llist.h>
#include <linux/cpu.h>
#include <linux/cache.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/topology.h>
#include <linux/sched/signal.h>
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/prefetch.h>
#include <linux/blk-crypto.h>
#include <linux/part_stat.h>

#include <trace/events/block.h>

#include <linux/blk-mq.h>
#include <linux/t10-pi.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
#include "blk-mq-tag.h"
#include "blk-pm.h"
#include "blk-stat.h"
#include "blk-mq-sched.h"
#include "blk-rq-qos.h"

static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);

static void blk_mq_poll_stats_start(struct request_queue *q);
static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);

static int blk_mq_poll_stats_bkt(const struct request *rq)
{
	int ddir, sectors, bucket;

	ddir = rq_data_dir(rq);
	sectors = blk_rq_stats_sectors(rq);

	bucket = ddir + 2 * ilog2(sectors);

	if (bucket < 0)
		return -1;
	else if (bucket >= BLK_MQ_POLL_STATS_BKTS)
		return ddir + BLK_MQ_POLL_STATS_BKTS - 2;

	return bucket;
}

#define BLK_QC_T_SHIFT		16
#define BLK_QC_T_INTERNAL	(1U << 31)

static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q,
		blk_qc_t qc)
{
	return xa_load(&q->hctx_table,
			(qc & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT);
}

static inline struct request *blk_qc_to_rq(struct blk_mq_hw_ctx *hctx,
		blk_qc_t qc)
{
	unsigned int tag = qc & ((1U << BLK_QC_T_SHIFT) - 1);

	if (qc & BLK_QC_T_INTERNAL)
		return blk_mq_tag_to_rq(hctx->sched_tags, tag);
	return blk_mq_tag_to_rq(hctx->tags, tag);
}

static inline blk_qc_t blk_rq_to_qc(struct request *rq)
{
	return (rq->mq_hctx->queue_num << BLK_QC_T_SHIFT) |
		(rq->tag != -1 ?
		 rq->tag : (rq->internal_tag | BLK_QC_T_INTERNAL));
}

/*
 * Check if any of the ctx, dispatch list or elevator
 * have pending work in this hardware queue.
 */
static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
{
	return !list_empty_careful(&hctx->dispatch) ||
		sbitmap_any_bit_set(&hctx->ctx_map) ||
			blk_mq_sched_has_work(hctx);
}

/*
 * 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)
{
	const int bit = ctx->index_hw[hctx->type];

	if (!sbitmap_test_bit(&hctx->ctx_map, bit))
		sbitmap_set_bit(&hctx->ctx_map, bit);
}

static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
				      struct blk_mq_ctx *ctx)
{
	const int bit = ctx->index_hw[hctx->type];

	sbitmap_clear_bit(&hctx->ctx_map, bit);
}

struct mq_inflight {
	struct block_device *part;
	unsigned int inflight[2];
};

static bool blk_mq_check_inflight(struct request *rq, void *priv,
				  bool reserved)
{
	struct mq_inflight *mi = priv;

	if ((!mi->part->bd_partno || rq->part == mi->part) &&
	    blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
		mi->inflight[rq_data_dir(rq)]++;

	return true;
}

unsigned int blk_mq_in_flight(struct request_queue *q,
		struct block_device *part)
{
	struct mq_inflight mi = { .part = part };

	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);

	return mi.inflight[0] + mi.inflight[1];
}

void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
		unsigned int inflight[2])
{
	struct mq_inflight mi = { .part = part };

	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
	inflight[0] = mi.inflight[0];
	inflight[1] = mi.inflight[1];
}

void blk_freeze_queue_start(struct request_queue *q)
{
	mutex_lock(&q->mq_freeze_lock);
	if (++q->mq_freeze_depth == 1) {
		percpu_ref_kill(&q->q_usage_counter);
		mutex_unlock(&q->mq_freeze_lock);
		if (queue_is_mq(q))
			blk_mq_run_hw_queues(q, false);
	} else {
		mutex_unlock(&q->mq_freeze_lock);
	}
}
EXPORT_SYMBOL_GPL(blk_freeze_queue_start);

void blk_mq_freeze_queue_wait(struct request_queue *q)
{
	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait);

int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
				     unsigned long timeout)
{
	return wait_event_timeout(q->mq_freeze_wq,
					percpu_ref_is_zero(&q->q_usage_counter),
					timeout);
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout);

/*
 * Guarantee no request is in use, so we can change any data structure of
 * the queue afterward.
 */
void blk_freeze_queue(struct request_queue *q)
{
	/*
	 * In the !blk_mq case we are only calling this to kill the
	 * q_usage_counter, otherwise this increases the freeze depth