// 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/kmemleak.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/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 <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;
}

/*
 * 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 blk_mq_hw_ctx *hctx,
                                  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
         * and waits for it to return to zero.  For this reason there is
         * no blk_unfreeze_queue(), and blk_freeze_queue() is not
         * exported to drivers as the only user for unfreeze is blk_mq.
         */
        blk_freeze_queue_start(q);
        blk_mq_freeze_queue_wait(q);
}

void blk_mq_freeze_queue(struct request_queue *q)
{
        /*
         * ...just an alias to keep freeze and unfreeze actions balanced
         * in the blk_mq_* namespace
         */
        blk_freeze_queue(q);
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);

void blk_mq_unfreeze_queue(struct request_queue *q)
{
        mutex_lock(&q->mq_freeze_lock);
        q->mq_freeze_depth--;
        WARN_ON_ONCE(q->mq_freeze_depth < 0);
        if (!q->mq_freeze_depth) {
                percpu_ref_resurrect(&q->q_usage_counter);
                wake_up_all(&q->mq_freeze_wq);
        }
        mutex_unlock(&q->mq_freeze_lock);
}
EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);

/*
 * FIXME: replace the scsi_internal_device_*block_nowait() calls in the
 * mpt3sas driver such that this function can be removed.
 */
void blk_mq_quiesce_queue_nowait(struct request_queue *q)
{
        blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q);
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);

/**
 * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
 * @q: request queue.
 *
 * Note: this function does not prevent that the struct request end_io()
 * callback function is invoked. Once this function is returned, we make
 * sure no dispatch can happen until the queue is unquiesced via
 * blk_mq_unquiesce_queue().
 */
void blk_mq_quiesce_queue(struct request_queue *q)
{
        struct blk_mq_hw_ctx *hctx;
        unsigned int i;
        bool rcu = false;

        blk_mq_quiesce_queue_nowait(q);

        queue_for_each_hw_ctx(q, hctx, i) {
                if (hctx->flags & BLK_MQ_F_BLOCKING)
                        synchronize_srcu(hctx->srcu);
                else
                        rcu = true;
        }
        if (rcu)
                synchronize_rcu();
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);

/*
 * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
 * @q: request queue.
 *
 * This function recovers queue into the state before quiescing
 * which is done by blk_mq_quiesce_queue.
 */
void blk_mq_unquiesce_queue(struct request_queue *q)
{
        blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);

        /* dispatch requests which are inserted during quiescing */
        blk_mq_run_hw_queues(q, true);
}
EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);

void blk_mq_wake_waiters(struct request_queue *q)
{
        struct blk_mq_hw_ctx *hctx;
        unsigned int i;

        queue_for_each_hw_ctx(q, hctx, i)
                if (blk_mq_hw_queue_mapped(hctx))
                        blk_mq_tag_wakeup_all(hctx->tags, true);
}

/*
 * Only need start/end time stamping if we have iostat or
 * blk stats enabled, or using an IO scheduler.
 */
static inline bool blk_mq_need_time_stamp(struct request *rq)
{
        return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS)) || rq->q->elevator;
}

static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
                unsigned int tag, u64 alloc_time_ns)
{
        struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
        struct request *rq = tags->static_rqs[tag];

        if (data->q->elevator) {
                rq->tag = BLK_MQ_NO_TAG;
                rq->internal_tag = tag;
        } else {
                rq->tag = tag;
                rq->internal_tag = BLK_MQ_NO_TAG;
        }

        /* csd/requeue_work/fifo_time is initialized before use */
        rq->q = data->q;
        rq->mq_ctx = data->ctx;
        rq->mq_hctx = data->hctx;
        rq->rq_flags = 0;
        rq->cmd_flags = data->cmd_flags;
        if (data->flags & BLK_MQ_REQ_PM)
                rq->rq_flags |= RQF_PM;
        if (blk_queue_io_stat(data->q))
                rq->rq_flags |= RQF_IO_STAT;
        INIT_LIST_HEAD(&rq->queuelist);
        INIT_HLIST_NODE(&rq->hash);
        RB_CLEAR_NODE(&rq->rb_node);
        rq->rq_disk = NULL;
        rq->part = NULL;
#ifdef CONFIG_BLK_RQ_ALLOC_TIME
        rq->alloc_time_ns = alloc_time_ns;
#endif
        if (blk_mq_need_time_stamp(rq))
                rq->start_time_ns = ktime_get_ns();
        else
                rq->start_time_ns = 0;
        rq->io_start_time_ns = 0;
        rq->stats_sectors = 0;
        rq->nr_phys_segments = 0;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
        rq->nr_integrity_segments = 0;
#endif
        blk_crypto_rq_set_defaults(rq);
        /* tag was already set */
        WRITE_ONCE(rq->deadline, 0);

        rq->timeout = 0;

        rq->end_io = NULL;
        rq->end_io_data = NULL;

        data->ctx->rq_dispatched[op_is_sync(data->cmd_flags)]++;
        refcount_set(&rq->ref, 1);

        if (!op_is_flush(data->cmd_flags)) {
                struct elevator_queue *e = data->q->elevator;

                rq->elv.icq = NULL;
                if (e && e->type->ops.prepare_request) {
                        if (e->type->icq_cache)
                                blk_mq_sched_assign_ioc(rq);

                        e->type->ops.prepare_request(rq);
                        rq->rq_flags |= RQF_ELVPRIV;
                }
        }

        data->hctx->queued++;
        return rq;
}

static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data)
{
        struct request_queue *q = data->q;
        struct elevator_queue *e = q->elevator;
        u64 alloc_time_ns = 0;
        unsigned int tag;

        /* alloc_time includes depth and tag waits */
        if (blk_queue_rq_alloc_time(q))
                alloc_time_ns = ktime_get_ns();

        if (data->cmd_flags & REQ_NOWAIT)
                data->flags |= BLK_MQ_REQ_NOWAIT;

        if (e) {
                /*
                 * Flush/passthrough requests are special and go directly to the
                 * dispatch list. Don't include reserved tags in the
                 * limiting, as it isn't useful.
                 */
                if (!op_is_flush(data->cmd_flags) &&
                    !blk_op_is_passthrough(data->cmd_flags) &&
                    e->type->ops.limit_depth &&
                    !(data->flags & BLK_MQ_REQ_RESERVED))
                        e->type->ops.limit_depth(data->cmd_flags, data);
        }

retry:
        data->ctx = blk_mq_get_ctx(q);
        data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
        if (!e)
                blk_mq_tag_busy(data->hctx);

        /*
         * Waiting allocations only fail because of an inactive hctx.  In that
         * case just retry the hctx assignment and tag allocation as CPU hotplug
         * should have migrated us to an online CPU by now.
         */
        tag = blk_mq_get_tag(data);
        if (tag == BLK_MQ_NO_TAG) {
                if (data->flags & BLK_MQ_REQ_NOWAIT)
                        return NULL;

                /*
                 * Give up the CPU and sleep for a random short time to ensure
                 * that thread using a realtime scheduling class are migrated
                 * off the CPU, and thus off the hctx that is going away.
                 */
                msleep(3);
                goto retry;
        }
        return blk_mq_rq_ctx_init(data, tag, alloc_time_ns);
}

struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
                blk_mq_req_flags_t flags)
{
        struct blk_mq_alloc_data data = {
                .q              = q,
                .flags          = flags,
                .cmd_flags      = op,
        };
        struct request *rq;
        int ret;

        ret = blk_queue_enter(q, flags);
        if (ret)
                return ERR_PTR(ret);

        rq = __blk_mq_alloc_request(&data);
        if (!rq)
                goto out_queue_exit;
        rq->__data_len = 0;
        rq->__sector = (sector_t) -1;
        rq->bio = rq->biotail = NULL;
        return rq;
out_queue_exit:
        blk_queue_exit(q);
        return ERR_PTR(-EWOULDBLOCK);
}
EXPORT_SYMBOL(blk_mq_alloc_request);

struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
        unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
{
        struct blk_mq_alloc_data data = {
                .q              = q,
                .flags          = flags,
                .cmd_flags      = op,
        };
        u64 alloc_time_ns = 0;
        unsigned int cpu;
        unsigned int tag;
        int ret;

        /* alloc_time includes depth and tag waits */
        if (blk_queue_rq_alloc_time(q))
                alloc_time_ns = ktime_get_ns();

        /*
         * If the tag allocator sleeps we could get an allocation for a
         * different hardware context.  No need to complicate the low level
         * allocator for this for the rare use case of a command tied to
         * a specific queue.
         */
        if (WARN_ON_ONCE(!(flags & (BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED))))
                return ERR_PTR(-EINVAL);

        if (hctx_idx >= q->nr_hw_queues)
                return ERR_PTR(-EIO);

        ret = blk_queue_enter(q, flags);
        if (ret)
                return ERR_PTR(ret);

        /*
         * Check if the hardware context is actually mapped to anything.
         * If not tell the caller that it should skip this queue.
         */
        ret = -EXDEV;
        data.hctx = q->queue_hw_ctx[hctx_idx];
        if (!blk_mq_hw_queue_mapped(data.hctx))
                goto out_queue_exit;
        cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
        data.ctx = __blk_mq_get_ctx(q, cpu);

        if (!q->elevator)
                blk_mq_tag_busy(data.hctx);

        ret = -EWOULDBLOCK;
        tag = blk_mq_get_tag(&data);
        if (tag == BLK_MQ_NO_TAG)
                goto out_queue_exit;
        return blk_mq_rq_ctx_init(&data, tag, alloc_time_ns);

out_queue_exit:
        blk_queue_exit(q);
        return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);

static void __blk_mq_free_request(struct request *rq)
{
        struct request_queue *q = rq->q;
        struct blk_mq_ctx *ctx = rq->mq_ctx;
        struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
        const int sched_tag = rq->internal_tag;

        blk_crypto_free_request(rq);
        blk_pm_mark_last_busy(rq);
        rq->mq_hctx = NULL;
        if (rq->tag != BLK_MQ_NO_TAG)
                blk_mq_put_tag(hctx->tags, ctx, rq->tag);
        if (sched_tag != BLK_MQ_NO_TAG)
                blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag);
        blk_mq_sched_restart(hctx);
        blk_queue_exit(q);
}

void blk_mq_free_request(struct request *rq)
{
        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 = rq->mq_hctx;

        if (rq->rq_flags & RQF_ELVPRIV) {
                if (e && e->type->ops.finish_request)
                        e->type->ops.finish_request(rq);
                if (rq->elv.icq) {
                        put_io_context(rq->elv.icq->ioc);
                        rq->elv.icq = NULL;
                }
        }

        ctx->rq_completed[rq_is_sync(rq)]++;
        if (rq->rq_flags & RQF_MQ_INFLIGHT)
                __blk_mq_dec_active_requests(hctx);

        if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
                laptop_io_completion(q->backing_dev_info);

        rq_qos_done(q, rq);

        WRITE_ONCE(rq->state, MQ_RQ_IDLE);
        if (refcount_dec_and_test(&rq->ref))
                __blk_mq_free_request(rq);
}
EXPORT_SYMBOL_GPL(blk_mq_free_request);

inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
{
        u64 now = 0;

        if (blk_mq_need_time_stamp(rq))
                now = ktime_get_ns();

        if (rq->rq_flags & RQF_STATS) {
                blk_mq_poll_stats_start(rq->q);
                blk_stat_add(rq, now);
        }

        blk_mq_sched_completed_request(rq, now);

        blk_account_io_done(rq, now);

        if (rq->end_io) {
                rq_qos_done(rq->q, rq);
                rq->end_io(rq, error);
        } else {
                blk_mq_free_request(rq);
        }
}
EXPORT_SYMBOL(__blk_mq_end_request);

void blk_mq_end_request(struct request *rq, blk_status_t error)
{
        if (blk_update_request(rq, error, blk_rq_bytes(rq)))
                BUG();
        __blk_mq_end_request(rq, error);
}
EXPORT_SYMBOL(blk_mq_end_request);

static void blk_complete_reqs(struct llist_head *list)
{
        struct llist_node *entry = llist_reverse_order(llist_del_all(list));
        struct request *rq, *next;

        llist_for_each_entry_safe(rq, next, entry, ipi_list)
                rq->q->mq_ops->complete(rq);
}

static __latent_entropy void blk_done_softirq(struct softirq_action *h)
{
        blk_complete_reqs(this_cpu_ptr(&blk_cpu_done));
}

static int blk_softirq_cpu_dead(unsigned int cpu)
{
        blk_complete_reqs(&per_cpu(blk_cpu_done, cpu));
        return 0;
}

static void __blk_mq_complete_request_remote(void *data)
{
        __raise_softirq_irqoff(BLOCK_SOFTIRQ);
}

static inline bool blk_mq_complete_need_ipi(struct request *rq)
{
        int cpu = raw_smp_processor_id();

        if (!IS_ENABLED(CONFIG_SMP) ||
            !test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags))
                return false;
        /*
         * With force threaded interrupts enabled, raising softirq from an SMP
         * function call will always result in waking the ksoftirqd thread.
         * This is probably worse than completing the request on a different
         * cache domain.
         */
        if (force_irqthreads)
                return false;

        /* same CPU or cache domain?  Complete locally */
        if (cpu == rq->mq_ctx->cpu ||
            (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) &&
             cpus_share_cache(cpu, rq->mq_ctx->cpu)))
                return false;

        /* don't try to IPI to an offline CPU */
        return cpu_online(rq->mq_ctx->cpu);
}

static void blk_mq_complete_send_ipi(struct request *rq)
{
        struct llist_head *list;
        unsigned int cpu;

        cpu = rq->mq_ctx->cpu;
        list = &per_cpu(blk_cpu_done, cpu);
        if (llist_add(&rq->ipi_list, list)) {
                INIT_CSD(&rq->csd, __blk_mq_complete_request_remote, rq);
                smp_call_function_single_async(cpu, &rq->csd);
        }
}

static void blk_mq_raise_softirq(struct request *rq)
{
        struct llist_head *list;

        preempt_disable();
        list = this_cpu_ptr(&blk_cpu_done);
        if (llist_add(&rq->ipi_list, list))
                raise_softirq(BLOCK_SOFTIRQ);
        preempt_enable();
}

bool blk_mq_complete_request_remote(struct request *rq)
{
        WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);

        /*
         * For a polled request, always complete locallly, it's pointless
         * to redirect the completion.
         */
        if (rq->cmd_flags & REQ_HIPRI)
                return false;

        if (blk_mq_complete_need_ipi(rq)) {
                blk_mq_complete_send_ipi(rq);
                return true;
        }

        if (rq->q->nr_hw_queues == 1) {
                blk_mq_raise_softirq(rq);
                return true;
        }
        return false;
}
EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote);

/**
 * blk_mq_complete_request - end I/O on a request
 * @rq:         the request being processed
 *
 * Description:
 *      Complete a request by scheduling the ->complete_rq operation.
 **/
void blk_mq_complete_request(struct request *rq)
{
        if (!blk_mq_complete_request_remote(rq))
                rq->q->mq_ops->complete(rq);
}
EXPORT_SYMBOL(blk_mq_complete_request);

static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
        __releases(hctx->srcu)
{
        if (!(hctx->flags & BLK_MQ_F_BLOCKING))
                rcu_read_unlock();
        else
                srcu_read_unlock(hctx->srcu, srcu_idx);
}

static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx)
        __acquires(hctx->srcu)
{
        if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
                /* shut up gcc false positive */
                *srcu_idx = 0;
                rcu_read_lock();
        } else
                *srcu_idx = srcu_read_lock(hctx->srcu);
}

/**
 * blk_mq_start_request - Start processing a request
 * @rq: Pointer to request to be started
 *
 * Function used by device drivers to notify the block layer that a request
 * is going to be processed now, so blk layer can do proper initializations
 * such as starting the timeout timer.
 */
void blk_mq_start_request(struct request *rq)
{
        struct request_queue *q = rq->q;

        trace_block_rq_issue(rq);

        if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
                rq->io_start_time_ns = ktime_get_ns();
                rq->stats_sectors = blk_rq_sectors(rq);
                rq->rq_flags |= RQF_STATS;
                rq_qos_issue(q, rq);
        }

        WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);

        blk_add_timer(rq);
        WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);

#ifdef CONFIG_BLK_DEV_INTEGRITY
        if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
                q->integrity.profile->prepare_fn(rq);
#endif
}
EXPORT_SYMBOL(blk_mq_start_request);

static void __blk_mq_requeue_request(struct request *rq)
{
        struct request_queue *q = rq->q;

        blk_mq_put_driver_tag(rq);

        trace_block_rq_requeue(rq);
        rq_qos_requeue(q, rq);

        if (blk_mq_request_started(rq)) {
                WRITE_ONCE(rq->state, MQ_RQ_IDLE);
                rq->rq_flags &= ~RQF_TIMED_OUT;
        }
}

void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
{
        __blk_mq_requeue_request(rq);

        /* this request will be re-inserted to io scheduler queue */
        blk_mq_sched_requeue_request(rq);

        BUG_ON(!list_empty(&rq->queuelist));
        blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
}
EXPORT_SYMBOL(blk_mq_requeue_request);

static void blk_mq_requeue_work(struct work_struct *work)
{
        struct request_queue *q =
                container_of(work, struct request_queue, requeue_work.work);
        LIST_HEAD(rq_list);
        struct request *rq, *next;

        spin_lock_irq(&q->requeue_lock);
        list_splice_init(&q->requeue_list, &rq_list);
        spin_unlock_irq(&q->requeue_lock);

        list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
                if (!(rq->rq_flags & (RQF_SOFTBARRIER | RQF_DONTPREP)))
                        continue;

                rq->rq_flags &= ~RQF_SOFTBARRIER;
                list_del_init(&rq->queuelist);
                /*
                 * If RQF_DONTPREP, rq has contained some driver specific
                 * data, so insert it to hctx dispatch list to avoid any
                 * merge.
                 */
                if (rq->rq_flags & RQF_DONTPREP)
                        blk_mq_request_bypass_insert(rq, false, false);
                else
                        blk_mq_sched_insert_request(rq, true, false, false);
        }

        while (!list_empty(&rq_list)) {
                rq = list_entry(rq_list.next, struct request, queuelist);
                list_del_init(&rq->queuelist);
                blk_mq_sched_insert_request(rq, false, false, false);
        }

        blk_mq_run_hw_queues(q, false);
}

void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
                                bool kick_requeue_list)
{
        struct request_queue *q = rq->q;
        unsigned long flags;

        /*
         * We abuse this flag that is otherwise used by the I/O scheduler to
         * request head insertion from the workqueue.
         */
        BUG_ON(rq->rq_flags & RQF_SOFTBARRIER);

        spin_lock_irqsave(&q->requeue_lock, flags);
        if (at_head) {
                rq->rq_flags |= RQF_SOFTBARRIER;
                list_add(&rq->queuelist, &q->requeue_list);
        } else {
                list_add_tail(&rq->queuelist, &q->requeue_list);
        }
        spin_unlock_irqrestore(&q->requeue_lock, flags);

        if (kick_requeue_list)
                blk_mq_kick_requeue_list(q);
}

void blk_mq_kick_requeue_list(struct request_queue *q)
{
        kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0);
}
EXPORT_SYMBOL(blk_mq_kick_requeue_list);

void blk_mq_delay_kick_requeue_list(struct request_queue *q,
                                    unsigned long msecs)
{
        kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work,
                                    msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);

struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
{
        if (tag < tags->nr_tags) {
                prefetch(tags->rqs[tag]);
                return tags->rqs[tag];
        }

        return NULL;
}
EXPORT_SYMBOL(blk_mq_tag_to_rq);

static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq,
                               void *priv, bool reserved)
{
        /*
         * If we find a request that isn't idle and the queue matches,
         * we know the queue is busy. Return false to stop the iteration.
         */
        if (blk_mq_request_started(rq) && rq->q == hctx->queue) {
                bool *busy = priv;

                *busy = true;
                return false;
        }

        return true;
}

bool blk_mq_queue_inflight(struct request_queue *q)
{
        bool busy = false;

        blk_mq_queue_tag_busy_iter(q, blk_mq_rq_inflight, &busy);
        return busy;
}
EXPORT_SYMBOL_GPL(blk_mq_queue_inflight);

static void blk_mq_rq_timed_out(struct request *req, bool reserved)
{
        req->rq_flags |= RQF_TIMED_OUT;
        if (req->q->mq_ops->timeout) {
                enum blk_eh_timer_return ret;

                ret = req->q->mq_ops->timeout(req, reserved);
                if (ret == BLK_EH_DONE)
                        return;
                WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
        }

        blk_add_timer(req);
}

static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
{
        unsigned long deadline;

        if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT)
                return false;
        if (rq->rq_flags & RQF_TIMED_OUT)
                return false;

        deadline = READ_ONCE(rq->deadline);
        if (time_after_eq(jiffies, deadline))
                return true;

        if (*next == 0)
                *next = deadline;
        else if (time_after(*next, deadline))
                *next = deadline;
        return false;
}

void blk_mq_put_rq_ref(struct request *rq)
{
        if (is_flush_rq(rq))
                rq->end_io(rq, 0);
        else if (refcount_dec_and_test(&rq->ref))
                __blk_mq_free_request(rq);
}

static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
                struct request *rq, void *priv, bool reserved)
{
        unsigned long *next = priv;

        /*
         * blk_mq_queue_tag_busy_iter() has locked the request, so it cannot
         * be reallocated underneath the timeout handler's processing, then
         * the expire check is reliable. If the request is not expired, then
         * it was completed and reallocated as a new request after returning
         * from blk_mq_check_expired().
         */
        if (blk_mq_req_expired(rq, next))
                blk_mq_rq_timed_out(rq, reserved);
        return true;
}

static void blk_mq_timeout_work(struct work_struct *work)
{
        struct request_queue *q =
                container_of(work, struct request_queue, timeout_work);
        unsigned long next = 0;
        struct blk_mq_hw_ctx *hctx;
        int i;

        /* A deadlock might occur if a request is stuck requiring a
         * timeout at the same time a queue freeze is waiting
         * completion, since the timeout code would not be able to
         * acquire the queue reference here.
         *
         * That's why we don't use blk_queue_enter here; instead, we use
         * percpu_ref_tryget directly, because we need to be able to
         * obtain a reference even in the short window between the queue
         * starting to freeze, by dropping the first reference in
         * blk_freeze_queue_start, and the moment the last request is
         * consumed, marked by the instant q_usage_counter reaches
         * zero.
         */
        if (!percpu_ref_tryget(&q->q_usage_counter))
                return;

        blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &next);

        if (next != 0) {
                mod_timer(&q->timeout, next);
        } else {
                /*
                 * Request timeouts are handled as a forward rolling timer. If
                 * we end up here it means that no requests are pending and
                 * also that no request has been pending for a while. Mark
                 * each hctx as idle.
                 */
                queue_for_each_hw_ctx(q, hctx, i) {
                        /* the hctx may be unmapped, so check it here */
                        if (blk_mq_hw_queue_mapped(hctx))
                                blk_mq_tag_idle(hctx);
                }
        }
        blk_queue_exit(q);
}

struct flush_busy_ctx_data {
        struct blk_mq_hw_ctx *hctx;
        struct list_head *list;
};

static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
{
        struct flush_busy_ctx_data *flush_data = data;
        struct blk_mq_hw_ctx *hctx = flush_data->hctx;
        struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
        enum hctx_type type = hctx->type;

        spin_lock(&ctx->lock);
        list_splice_tail_init(&ctx->rq_lists[type], flush_data->list);
        sbitmap_clear_bit(sb, bitnr);
        spin_unlock(&ctx->lock);
        return true;
}

/*

 * Process software queues that have been marked busy, splicing them
 * to the for-dispatch
 */
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
{
        struct flush_busy_ctx_data data = {
                .hctx = hctx,
                .list = list,
        };

        sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data);
}
EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs);

struct dispatch_rq_data {
        struct blk_mq_hw_ctx *hctx;
        struct request *rq;
};

static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr,
                void *data)
{
        struct dispatch_rq_data *dispatch_data = data;
        struct blk_mq_hw_ctx *hctx = dispatch_data->hctx;
        struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
        enum hctx_type type = hctx->type;

        spin_lock(&ctx->lock);
        if (!list_empty(&ctx->rq_lists[type])) {
                dispatch_data->rq = list_entry_rq(ctx->rq_lists[type].next);
                list_del_init(&dispatch_data->rq->queuelist);
                if (list_empty(&ctx->rq_lists[type]))
                        sbitmap_clear_bit(sb, bitnr);
        }
        spin_unlock(&ctx->lock);

        return !dispatch_data->rq;
}

struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
                                        struct blk_mq_ctx *start)
{
        unsigned off = start ? start->index_hw[hctx->type] : 0;
        struct dispatch_rq_data data = {
                .hctx = hctx,
                .rq   = NULL,
        };

        __sbitmap_for_each_set(&hctx->ctx_map, off,
                               dispatch_rq_from_ctx, &data);

        return data.rq;
}

static inline unsigned int queued_to_index(unsigned int queued)
{
        if (!queued)
                return 0;

        return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
}

static bool __blk_mq_get_driver_tag(struct request *rq)
{
        struct sbitmap_queue *bt = rq->mq_hctx->tags->bitmap_tags;
        unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
        int tag;

        blk_mq_tag_busy(rq->mq_hctx);

        if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) {
                bt = rq->mq_hctx->tags->breserved_tags;
                tag_offset = 0;
        } else {
                if (!hctx_may_queue(rq->mq_hctx, bt))
                        return false;
        }

        tag = __sbitmap_queue_get(bt);
        if (tag == BLK_MQ_NO_TAG)
                return false;

        rq->tag = tag + tag_offset;
        return true;
}

static bool blk_mq_get_driver_tag(struct request *rq)
{
        struct blk_mq_hw_ctx *hctx = rq->mq_hctx;

        if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
                return false;

        if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
                        !(rq->rq_flags & RQF_MQ_INFLIGHT)) {
                rq->rq_flags |= RQF_MQ_INFLIGHT;
                __blk_mq_inc_active_requests(hctx);
        }
        hctx->tags->rqs[rq->tag] = rq;
        return true;
}

static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
                                int flags, void *key)
{
        struct blk_mq_hw_ctx *hctx;

        hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);

        spin_lock(&hctx->dispatch_wait_lock);
        if (!list_empty(&wait->entry)) {
                struct sbitmap_queue *sbq;

                list_del_init(&wait->entry);
                sbq = hctx->tags->bitmap_tags;
                atomic_dec(&sbq->ws_active);
        }
        spin_unlock(&hctx->dispatch_wait_lock);

        blk_mq_run_hw_queue(hctx, true);
        return 1;
}

/*
 * Mark us waiting for a tag. For shared tags, this involves hooking us into
 * the tag wakeups. For non-shared tags, we can simply mark us needing a
 * restart. For both cases, take care to check the condition again after
 * marking us as waiting.
 */
static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
                                 struct request *rq)
{
        struct sbitmap_queue *sbq = hctx->tags->bitmap_tags;
        struct wait_queue_head *wq;
        wait_queue_entry_t *wait;
        bool ret;

        if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
                blk_mq_sched_mark_restart_hctx(hctx);

                /*
                 * It's possible that a tag was freed in the window between the
                 * allocation failure and adding the hardware queue to the wait
                 * queue.
                 *
                 * Don't clear RESTART here, someone else could have set it.
                 * At most this will cost an extra queue run.
                 */
                return blk_mq_get_driver_tag(rq);
        }

        wait = &hctx->dispatch_wait;
        if (!list_empty_careful(&wait->entry))
                return false;

        wq = &bt_wait_ptr(sbq, hctx)->wait;

        spin_lock_irq(&wq->lock);
        spin_lock(&hctx->dispatch_wait_lock);
        if (!list_empty(&wait->entry)) {
                spin_unlock(&hctx->dispatch_wait_lock);
                spin_unlock_irq(&wq->lock);
                return false;
        }

        atomic_inc(&sbq->ws_active);
        wait->flags &= ~WQ_FLAG_EXCLUSIVE;
        __add_wait_queue(wq, wait);

        /*
         * It's possible that a tag was freed in the window between the
         * allocation failure and adding the hardware queue to the wait
         * queue.
         */
        ret = blk_mq_get_driver_tag(rq);
        if (!ret) {
                spin_unlock(&hctx->dispatch_wait_lock);
                spin_unlock_irq(&wq->lock);
                return false;
        }

        /*
         * We got a tag, remove ourselves from the wait queue to ensure
         * someone else gets the wakeup.
         */
        list_del_init(&wait->entry);
        atomic_dec(&sbq->ws_active);
        spin_unlock(&hctx->dispatch_wait_lock);
        spin_unlock_irq(&wq->lock);

        return true;
}

#define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT  8
#define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR  4
/*
 * Update dispatch busy with the Exponential Weighted Moving Average(EWMA):
 * - EWMA is one simple way to compute running average value
 * - weight(7/8 and 1/8) is applied so that it can decrease exponentially
 * - take 4 as factor for avoiding to get too small(0) result, and this
 *   factor doesn't matter because EWMA decreases exponentially
 */
static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
{
        unsigned int ewma;

        ewma = hctx->dispatch_busy;

        if (!ewma && !busy)
                return;

        ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1;
        if (busy)
                ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR;
        ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT;

        hctx->dispatch_busy = ewma;
}

#define BLK_MQ_RESOURCE_DELAY   3               /* ms units */

static void blk_mq_handle_dev_resource(struct request *rq,
                                       struct list_head *list)
{
        struct request *next =
                list_first_entry_or_null(list, struct request, queuelist);

        /*
         * If an I/O scheduler has been configured and we got a driver tag for
         * the next request already, free it.
         */
        if (next)
                blk_mq_put_driver_tag(next);

        list_add(&rq->queuelist, list);
        __blk_mq_requeue_request(rq);
}

static void blk_mq_handle_zone_resource(struct request *rq,
                                        struct list_head *zone_list)
{
        /*
         * If we end up here it is because we cannot dispatch a request to a
         * specific zone due to LLD level zone-write locking or other zone
         * related resource not being available. In this case, set the request
         * aside in zone_list for retrying it later.
         */
        list_add(&rq->queuelist, zone_list);
        __blk_mq_requeue_request(rq);
}

enum prep_dispatch {
        PREP_DISPATCH_OK,
        PREP_DISPATCH_NO_TAG,
        PREP_DISPATCH_NO_BUDGET,
};

static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq,
                                                  bool need_budget)
{
        struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
        int budget_token = -1;

        if (need_budget) {
                budget_token = blk_mq_get_dispatch_budget(rq->q);
                if (budget_token < 0) {
                        blk_mq_put_driver_tag(rq);
                        return PREP_DISPATCH_NO_BUDGET;
                }
                blk_mq_set_rq_budget_token(rq, budget_token);
        }

        if (!blk_mq_get_driver_tag(rq)) {
                /*
                 * The initial allocation attempt failed, so we need to
                 * rerun the hardware queue when a tag is freed. The
                 * waitqueue takes care of that. If the queue is run
                 * before we add this entry back on the dispatch list,
                 * we'll re-run it below.
                 */
                if (!blk_mq_mark_tag_wait(hctx, rq)) {
                        /*
                         * All budgets not got from this function will be put
                         * together during handling partial dispatch
                         */
                        if (need_budget)
                                blk_mq_put_dispatch_budget(rq->q, budget_token);
                        return PREP_DISPATCH_NO_TAG;
                }
        }

        return PREP_DISPATCH_OK;
}

/* release all allocated budgets before calling to blk_mq_dispatch_rq_list */
static void blk_mq_release_budgets(struct request_queue *q,
                struct list_head *list)
{
        struct request *rq;

        list_for_each_entry(rq, list, queuelist) {
                int budget_token = blk_mq_get_rq_budget_token(rq);

                if (budget_token >= 0)
                        blk_mq_put_dispatch_budget(q, budget_token);
        }
}

/*
 * Returns true if we did some work AND can potentially do more.
 */
bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
                             unsigned int nr_budgets)
{
        enum prep_dispatch prep;
        struct request_queue *q = hctx->queue;
        struct request *rq, *nxt;
        int errors, queued;
        blk_status_t ret = BLK_STS_OK;
        LIST_HEAD(zone_list);

        if (list_empty(list))
                return false;

        /*
         * Now process all the entries, sending them to the driver.
         */
        errors = queued = 0;
        do {
                struct blk_mq_queue_data bd;

                rq = list_first_entry(list, struct request, queuelist);

                WARN_ON_ONCE(hctx != rq->mq_hctx);
                prep = blk_mq_prep_dispatch_rq(rq, !nr_budgets);
                if (prep != PREP_DISPATCH_OK)
                        break;

                list_del_init(&rq->queuelist);

                bd.rq = rq;

                /*
                 * Flag last if we have no more requests, or if we have more
                 * but can't assign a driver tag to it.
                 */
                if (list_empty(list))
                        bd.last = true;
                else {
                        nxt = list_first_entry(list, struct request, queuelist);
                        bd.last = !blk_mq_get_driver_tag(nxt);
                }

                /*
                 * once the request is queued to lld, no need to cover the
                 * budget any more
                 */
                if (nr_budgets)
                        nr_budgets--;
                ret = q->mq_ops->queue_rq(hctx, &bd);
                switch (ret) {
                case BLK_STS_OK:
                        queued++;
                        break;
                case BLK_STS_RESOURCE:
                case BLK_STS_DEV_RESOURCE:
                        blk_mq_handle_dev_resource(rq, list);
                        goto out;
                case BLK_STS_ZONE_RESOURCE:
                        /*
                         * Move the request to zone_list and keep going through
                         * the dispatch list to find more requests the drive can
                         * accept.
                         */
                        blk_mq_handle_zone_resource(rq, &zone_list);
                        break;
                default:
                        errors++;
                        blk_mq_end_request(rq, ret);
                }
        } while (!list_empty(list));
out:
        if (!list_empty(&zone_list))
                list_splice_tail_init(&zone_list, list);

        hctx->dispatched[queued_to_index(queued)]++;

        /* If we didn't flush the entire list, we could have told the driver
         * there was more coming, but that turned out to be a lie.
         */
        if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued)
                q->mq_ops->commit_rqs(hctx);
        /*
         * Any items that need requeuing? Stuff them into hctx->dispatch,
         * that is where we will continue on next queue run.
         */
        if (!list_empty(list)) {
                bool needs_restart;
                /* For non-shared tags, the RESTART check will suffice */
                bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
                        (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
                bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;

                if (nr_budgets)
                        blk_mq_release_budgets(q, list);

                spin_lock(&hctx->lock);
                list_splice_tail_init(list, &hctx->dispatch);
                spin_unlock(&hctx->lock);

                /*
                 * Order adding requests to hctx->dispatch and checking
                 * SCHED_RESTART flag. The pair of this smp_mb() is the one
                 * in blk_mq_sched_restart(). Avoid restart code path to
                 * miss the new added requests to hctx->dispatch, meantime
                 * SCHED_RESTART is observed here.
                 */
                smp_mb();

                /*
                 * If SCHED_RESTART was set by the caller of this function and
                 * it is no longer set that means that it was cleared by another
                 * thread and hence that a queue rerun is needed.
                 *
                 * If 'no_tag' is set, that means that we failed getting
                 * a driver tag with an I/O scheduler attached. If our dispatch
                 * waitqueue is no longer active, ensure that we run the queue
                 * AFTER adding our entries back to the list.
                 *
                 * If no I/O scheduler has been configured it is possible that
                 * the hardware queue got stopped and restarted before requests
                 * were pushed back onto the dispatch list. Rerun the queue to
                 * avoid starvation. Notes:
                 * - blk_mq_run_hw_queue() checks whether or not a queue has
                 *   been stopped before rerunning a queue.
                 * - Some but not all block drivers stop a queue before
                 *   returning BLK_STS_RESOURCE. Two exceptions are scsi-mq
                 *   and dm-rq.
                 *
                 * If driver returns BLK_STS_RESOURCE and SCHED_RESTART
                 * bit is set, run queue after a delay to avoid IO stalls
                 * that could otherwise occur if the queue is idle.  We'll do
                 * similar if we couldn't get budget and SCHED_RESTART is set.
                 */
                needs_restart = blk_mq_sched_needs_restart(hctx);
                if (!needs_restart ||
                    (no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
                        blk_mq_run_hw_queue(hctx, true);
                else if (needs_restart && (ret == BLK_STS_RESOURCE ||
                                           no_budget_avail))
                        blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);

                blk_mq_update_dispatch_busy(hctx, true);
                return false;
        } else
                blk_mq_update_dispatch_busy(hctx, false);

        return (queued + errors) != 0;
}

/**
 * __blk_mq_run_hw_queue - Run a hardware queue.
 * @hctx: Pointer to the hardware queue to run.
 *
 * Send pending requests to the hardware.
 */
static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
{
        int srcu_idx;

        /*
         * We can't run the queue inline with ints disabled. Ensure that
         * we catch bad users of this early.
         */
        WARN_ON_ONCE(in_interrupt());

        might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);

        hctx_lock(hctx, &srcu_idx);
        blk_mq_sched_dispatch_requests(hctx);
        hctx_unlock(hctx, srcu_idx);
}

static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
{
        int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);

        if (cpu >= nr_cpu_ids)
                cpu = cpumask_first(hctx->cpumask);
        return cpu;
}

/*
 * It'd be great if the workqueue API had a way to pass
 * in a mask and had some smarts for more clever placement.
 * For now we just round-robin here, switching for every
 * BLK_MQ_CPU_WORK_BATCH queued items.
 */
static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
{
        bool tried = false;
        int next_cpu = hctx->next_cpu;

        if (hctx->queue->nr_hw_queues == 1)
                return WORK_CPU_UNBOUND;

        if (--hctx->next_cpu_batch <= 0) {
select_cpu:
                next_cpu = cpumask_next_and(next_cpu, hctx->cpumask,
                                cpu_online_mask);
                if (next_cpu >= nr_cpu_ids)
                        next_cpu = blk_mq_first_mapped_cpu(hctx);
                hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
        }

        /*
         * Do unbound schedule if we can't find a online CPU for this hctx,
         * and it should only happen in the path of handling CPU DEAD.
         */
        if (!cpu_online(next_cpu)) {
                if (!tried) {
                        tried = true;
                        goto select_cpu;
                }

                /*
                 * Make sure to re-select CPU next time once after CPUs
                 * in hctx->cpumask become online again.
                 */
                hctx->next_cpu = next_cpu;
                hctx->next_cpu_batch = 1;
                return WORK_CPU_UNBOUND;
        }

        hctx->next_cpu = next_cpu;
        return next_cpu;
}

/**
 * __blk_mq_delay_run_hw_queue - Run (or schedule to run) a hardware queue.
 * @hctx: Pointer to the hardware queue to run.
 * @async: If we want to run the queue asynchronously.
 * @msecs: Milliseconds of delay to wait before running the queue.
 *
 * If !@async, try to run the queue now. Else, run the queue asynchronously and
 * with a delay of @msecs.
 */
static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
                                        unsigned long msecs)
{
        if (unlikely(blk_mq_hctx_stopped(hctx)))
                return;

        if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
                int cpu = get_cpu();
                if (cpumask_test_cpu(cpu, hctx->cpumask)) {
                        __blk_mq_run_hw_queue(hctx);
                        put_cpu();
                        return;
                }

                put_cpu();
        }

        kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
                                    msecs_to_jiffies(msecs));
}

/**
 * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously.
 * @hctx: Pointer to the hardware queue to run.
 * @msecs: Milliseconds of delay to wait before running the queue.
 *
 * Run a hardware queue asynchronously with a delay of @msecs.
 */
void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
{
        __blk_mq_delay_run_hw_queue(hctx, true, msecs);
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);

/**
 * blk_mq_run_hw_queue - Start to run a hardware queue.
 * @hctx: Pointer to the hardware queue to run.
 * @async: If we want to run the queue asynchronously.
 *
 * Check if the request queue is not in a quiesced state and if there are
 * pending requests to be sent. If this is true, run the queue to send requests
 * to hardware.
 */
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
        int srcu_idx;
        bool need_run;

        /*
         * When queue is quiesced, we may be switching io scheduler, or
         * updating nr_hw_queues, or other things, and we can't run queue
         * any more, even __blk_mq_hctx_has_pending() can't be called safely.
         *
         * And queue will be rerun in blk_mq_unquiesce_queue() if it is
         * quiesced.
         */
        hctx_lock(hctx, &srcu_idx);
        need_run = !blk_queue_quiesced(hctx->queue) &&
                blk_mq_hctx_has_pending(hctx);
        hctx_unlock(hctx, srcu_idx);

        if (need_run)
                __blk_mq_delay_run_hw_queue(hctx, async, 0);
}
EXPORT_SYMBOL(blk_mq_run_hw_queue);

/*
 * Is the request queue handled by an IO scheduler that does not respect
 * hardware queues when dispatching?
 */
static bool blk_mq_has_sqsched(struct request_queue *q)
{
        struct elevator_queue *e = q->elevator;

        if (e && e->type->ops.dispatch_request &&
            !(e->type->elevator_features & ELEVATOR_F_MQ_AWARE))
                return true;
        return false;
}

/*
 * Return prefered queue to dispatch from (if any) for non-mq aware IO
 * scheduler.
 */
static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q)
{
        struct blk_mq_hw_ctx *hctx;

        /*
         * If the IO scheduler does not respect hardware queues when
         * dispatching, we just don't bother with multiple HW queues and
         * dispatch from hctx for the current CPU since running multiple queues
         * just causes lock contention inside the scheduler and pointless cache
         * bouncing.
         */
        hctx = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT,
                                     raw_smp_processor_id());
        if (!blk_mq_hctx_stopped(hctx))
                return hctx;
        return NULL;
}

/**
 * blk_mq_run_hw_queues - Run all hardware queues in a request queue.
 * @q: Pointer to the request queue to run.
 * @async: If we want to run the queue asynchronously.
 */
void blk_mq_run_hw_queues(struct request_queue *q, bool async)
{
        struct blk_mq_hw_ctx *hctx, *sq_hctx;
        int i;

        sq_hctx = NULL;
        if (blk_mq_has_sqsched(q))
                sq_hctx = blk_mq_get_sq_hctx(q);
        queue_for_each_hw_ctx(q, hctx, i) {
                if (blk_mq_hctx_stopped(hctx))
                        continue;
                /*
                 * Dispatch from this hctx either if there's no hctx preferred
                 * by IO scheduler or if it has requests that bypass the
                 * scheduler.
                 */
                if (!sq_hctx || sq_hctx == hctx ||
                    !list_empty_careful(&hctx->dispatch))
                        blk_mq_run_hw_queue(hctx, async);
        }
}
EXPORT_SYMBOL(blk_mq_run_hw_queues);

/**
 * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously.
 * @q: Pointer to the request queue to run.
 * @msecs: Milliseconds of delay to wait before running the queues.
 */
void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
{
        struct blk_mq_hw_ctx *hctx, *sq_hctx;
        int i;

        sq_hctx = NULL;
        if (blk_mq_has_sqsched(q))
                sq_hctx = blk_mq_get_sq_hctx(q);
        queue_for_each_hw_ctx(q, hctx, i) {
                if (blk_mq_hctx_stopped(hctx))
                        continue;
                /*
                 * Dispatch from this hctx either if there's no hctx preferred
                 * by IO scheduler or if it has requests that bypass the
                 * scheduler.
                 */
                if (!sq_hctx || sq_hctx == hctx ||
                    !list_empty_careful(&hctx->dispatch))
                        blk_mq_delay_run_hw_queue(hctx, msecs);
        }
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);

/**
 * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped
 * @q: request queue.
 *
 * The caller is responsible for serializing this function against
 * blk_mq_{start,stop}_hw_queue().
 */
bool blk_mq_queue_stopped(struct request_queue *q)
{
        struct blk_mq_hw_ctx *hctx;
        int i;

        queue_for_each_hw_ctx(q, hctx, i)
                if (blk_mq_hctx_stopped(hctx))
                        return true;

        return false;
}
EXPORT_SYMBOL(blk_mq_queue_stopped);

/*
 * This function is often used for pausing .queue_rq() by driver when
 * there isn't enough resource or some conditions aren't satisfied, and
 * BLK_STS_RESOURCE is usually returned.
 *
 * We do not guarantee that dispatch can be drained or blocked
 * after blk_mq_stop_hw_queue() returns. Please use
 * blk_mq_quiesce_queue() for that requirement.
 */
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
{
        cancel_delayed_work(&hctx->run_work);

        set_bit(BLK_MQ_S_STOPPED, &hctx->state);
}
EXPORT_SYMBOL(blk_mq_stop_hw_queue);

/*
 * This function is often used for pausing .queue_rq() by driver when
 * there isn't enough resource or some conditions aren't satisfied, and
 * BLK_STS_RESOURCE is usually returned.
 *
 * We do not guarantee that dispatch can be drained or blocked
 * after blk_mq_stop_hw_queues() returns. Please use
 * blk_mq_quiesce_queue() for that requirement.
 */
void blk_mq_stop_hw_queues(struct request_queue *q)
{
        struct blk_mq_hw_ctx *hctx;
        int i;

        queue_for_each_hw_ctx(q, hctx, i)
                blk_mq_stop_hw_queue(hctx);
}
EXPORT_SYMBOL(blk_mq_stop_hw_queues);

void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx)
{
        clear_bit(BLK_MQ_S_STOPPED, &hctx->state);

        blk_mq_run_hw_queue(hctx, false);
}
EXPORT_SYMBOL(blk_mq_start_hw_queue);

void blk_mq_start_hw_queues(struct request_queue *q)
{
        struct blk_mq_hw_ctx *hctx;
        int i;

        queue_for_each_hw_ctx(q, hctx, i)
                blk_mq_start_hw_queue(hctx);
}
EXPORT_SYMBOL(blk_mq_start_hw_queues);

void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
        if (!blk_mq_hctx_stopped(hctx))
                return;

        clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
        blk_mq_run_hw_queue(hctx, async);
}
EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue);

void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async)
{
        struct blk_mq_hw_ctx *hctx;
        int i;

        queue_for_each_hw_ctx(q, hctx, i)
                blk_mq_start_stopped_hw_queue(hctx, async);
}
EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);

static void blk_mq_run_work_fn(struct work_struct *work)
{
        struct blk_mq_hw_ctx *hctx;

        hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);

        /*
         * If we are stopped, don't run the queue.
         */
        if (blk_mq_hctx_stopped(hctx))
                return;

        __blk_mq_run_hw_queue(hctx);
}

static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
                                            struct request *rq,
                                            bool at_head)
{
        struct blk_mq_ctx *ctx = rq->mq_ctx;
        enum hctx_type type = hctx->type;

        lockdep_assert_held(&ctx->lock);

        trace_block_rq_insert(rq);

        if (at_head)
                list_add(&rq->queuelist, &ctx->rq_lists[type]);
        else
                list_add_tail(&rq->queuelist, &ctx->rq_lists[type]);
}

void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
                             bool at_head)
{
        struct blk_mq_ctx *ctx = rq->mq_ctx;

        lockdep_assert_held(&ctx->lock);

        __blk_mq_insert_req_list(hctx, rq, at_head);
        blk_mq_hctx_mark_pending(hctx, ctx);
}

/**
 * blk_mq_request_bypass_insert - Insert a request at dispatch list.
 * @rq: Pointer to request to be inserted.
 * @at_head: true if the request should be inserted at the head of the list.
 * @run_queue: If we should run the hardware queue after inserting the request.
 *
 * Should only be used carefully, when the caller knows we want to
 * bypass a potential IO scheduler on the target device.
 */
void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
                                  bool run_queue)
{
        struct blk_mq_hw_ctx *hctx = rq->mq_hctx;

        spin_lock(&hctx->lock);
        if (at_head)
                list_add(&rq->queuelist, &hctx->dispatch);
        else
                list_add_tail(&rq->queuelist, &hctx->dispatch);
        spin_unlock(&hctx->lock);

        if (run_queue)
                blk_mq_run_hw_queue(hctx, false);
}

void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
                            struct list_head *list)

{
        struct request *rq;
        enum hctx_type type = hctx->type;

        /*
         * preemption doesn't flush plug list, so it's possible ctx->cpu is
         * offline now
         */
        list_for_each_entry(rq, list, queuelist) {
                BUG_ON(rq->mq_ctx != ctx);
                trace_block_rq_insert(rq);
        }

        spin_lock(&ctx->lock);
        list_splice_tail_init(list, &ctx->rq_lists[type]);
        blk_mq_hctx_mark_pending(hctx, ctx);
        spin_unlock(&ctx->lock);
}

static int plug_rq_cmp(void *priv, const struct list_head *a,
                       const struct list_head *b)
{
        struct request *rqa = container_of(a, struct request, queuelist);
        struct request *rqb = container_of(b, struct request, queuelist);

        if (rqa->mq_ctx != rqb->mq_ctx)
                return rqa->mq_ctx > rqb->mq_ctx;
        if (rqa->mq_hctx != rqb->mq_hctx)
                return rqa->mq_hctx > rqb->mq_hctx;

        return blk_rq_pos(rqa) > blk_rq_pos(rqb);
}

void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
        LIST_HEAD(list);

        if (list_empty(&plug->mq_list))
                return;
        list_splice_init(&plug->mq_list, &list);

        if (plug->rq_count > 2 && plug->multiple_queues)
                list_sort(NULL, &list, plug_rq_cmp);

        plug->rq_count = 0;

        do {
                struct list_head rq_list;
                struct request *rq, *head_rq = list_entry_rq(list.next);
                struct list_head *pos = &head_rq->queuelist; /* skip first */
                struct blk_mq_hw_ctx *this_hctx = head_rq->mq_hctx;
                struct blk_mq_ctx *this_ctx = head_rq->mq_ctx;
                unsigned int depth = 1;

                list_for_each_continue(pos, &list) {
                        rq = list_entry_rq(pos);
                        BUG_ON(!rq->q);
                        if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx)
                                break;
                        depth++;
                }

                list_cut_before(&rq_list, &list, pos);
                trace_block_unplug(head_rq->q, depth, !from_schedule);
                blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list,
                                                from_schedule);
        } while(!list_empty(&list));
}

static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
                unsigned int nr_segs)
{
        int err;

        if (bio->bi_opf & REQ_RAHEAD)
                rq->cmd_flags |= REQ_FAILFAST_MASK;

        rq->__sector = bio->bi_iter.bi_sector;
        rq->write_hint = bio->bi_write_hint;
        blk_rq_bio_prep(rq, bio, nr_segs);

        /* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */
        err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO);
        WARN_ON_ONCE(err);

        blk_account_io_start(rq);
}

static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
                                            struct request *rq,
                                            blk_qc_t *cookie, bool last)
{
        struct request_queue *q = rq->q;
        struct blk_mq_queue_data bd = {
                .rq = rq,
                .last = last,
        };
        blk_qc_t new_cookie;
        blk_status_t ret;

        new_cookie = request_to_qc_t(hctx, rq);

        /*
         * For OK queue, we are done. For error, caller may kill it.
         * Any other error (busy), just add it to our list as we
         * previously would have done.
         */
        ret = q->mq_ops->queue_rq(hctx, &bd);
        switch (ret) {
        case BLK_STS_OK:
                blk_mq_update_dispatch_busy(hctx, false);
                *cookie = new_cookie;
                break;
        case BLK_STS_RESOURCE:
        case BLK_STS_DEV_RESOURCE:
                blk_mq_update_dispatch_busy(hctx, true);
                __blk_mq_requeue_request(rq);
                break;
        default:
                blk_mq_update_dispatch_busy(hctx, false);
                *cookie = BLK_QC_T_NONE;
                break;
        }

        return ret;
}

static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
                                                struct request *rq,
                                                blk_qc_t *cookie,