/*
   * 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 <trace/events/block.h>
  
  #include <linux/blk-mq.h>
  #include "blk.h"
  #include "blk-mq.h"

  #include "blk-mq-debugfs.h"

  #include "blk-mq-tag.h"

  #include "blk-stat.h"

  #include "blk-wbt.h"

  #include "blk-mq-sched.h"

  static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie);

  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, bytes, bucket;

  	ddir = rq_data_dir(rq);

  	bytes = blk_rq_bytes(rq);
  
  	bucket = ddir + 2*(ilog2(bytes) - 9);
  
  	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's have pending work in this hardware queue
   */

  bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)

  {

  	return sbitmap_any_bit_set(&hctx->ctx_map) ||
  			!list_empty_careful(&hctx->dispatch) ||
  			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)
  {

  	if (!sbitmap_test_bit(&hctx->ctx_map, ctx->index_hw))
  		sbitmap_set_bit(&hctx->ctx_map, ctx->index_hw);

  }
  
  static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
  				      struct blk_mq_ctx *ctx)
  {

  	sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw);

  }

  struct mq_inflight {
  	struct hd_struct *part;
  	unsigned int *inflight;
  };
  
  static void blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
  				  struct request *rq, void *priv,
  				  bool reserved)
  {
  	struct mq_inflight *mi = priv;
  
  	if (test_bit(REQ_ATOM_STARTED, &rq->atomic_flags) &&
  	    !test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags)) {
  		/*

  		 * index[0] counts the specific partition that was asked
  		 * for. index[1] counts the ones that are active on the
  		 * whole device, so increment that if mi->part is indeed
  		 * a partition, and not a whole device.

  		 */

  		if (rq->part == mi->part)

  			mi->inflight[0]++;

  		if (mi->part->partno)
  			mi->inflight[1]++;

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

  	inflight[0] = inflight[1] = 0;

  	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
  }

  static void blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
  				     struct request *rq, void *priv,
  				     bool reserved)
  {
  	struct mq_inflight *mi = priv;
  
  	if (rq->part == mi->part)
  		mi->inflight[rq_data_dir(rq)]++;
  }
  
  void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
  			 unsigned int inflight[2])
  {
  	struct mq_inflight mi = { .part = part, .inflight = inflight, };
  
  	inflight[0] = inflight[1] = 0;
  	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
  }

  void blk_freeze_queue_start(struct request_queue *q)

  {

  	int freeze_depth;

  	freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
  	if (freeze_depth == 1) {

  		percpu_ref_kill(&q->q_usage_counter);

  		blk_mq_run_hw_queues(q, false);

  	}

  }

  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);

  	if (!q->mq_ops)
  		blk_drain_queue(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)

  {

  	int freeze_depth;

  	freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
  	WARN_ON_ONCE(freeze_depth < 0);
  	if (!freeze_depth) {

  		percpu_ref_reinit(&q->q_usage_counter);

  		wake_up_all(&q->mq_freeze_wq);

  	}

  }

  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)
  {
  	unsigned long flags;
  
  	spin_lock_irqsave(q->queue_lock, flags);
  	queue_flag_set(QUEUE_FLAG_QUIESCED, q);
  	spin_unlock_irqrestore(q->queue_lock, flags);
  }
  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->queue_rq_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)
  {

  	unsigned long flags;
  
  	spin_lock_irqsave(q->queue_lock, flags);

  	queue_flag_clear(QUEUE_FLAG_QUIESCED, q);

  	spin_unlock_irqrestore(q->queue_lock, flags);

  	/* 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);

  
  	/*
  	 * If we are called because the queue has now been marked as
  	 * dying, we need to ensure that processes currently waiting on
  	 * the queue are notified as well.
  	 */
  	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 struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
  		unsigned int tag, unsigned int op)

  {

  	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
  	struct request *rq = tags->static_rqs[tag];

  	rq->rq_flags = 0;

  	if (data->flags & BLK_MQ_REQ_INTERNAL) {
  		rq->tag = -1;
  		rq->internal_tag = tag;
  	} else {
  		if (blk_mq_tag_busy(data->hctx)) {
  			rq->rq_flags = RQF_MQ_INFLIGHT;
  			atomic_inc(&data->hctx->nr_active);
  		}
  		rq->tag = tag;
  		rq->internal_tag = -1;
  		data->hctx->tags->rqs[rq->tag] = rq;
  	}

  	INIT_LIST_HEAD(&rq->queuelist);
  	/* csd/requeue_work/fifo_time is initialized before use */

  	rq->q = data->q;
  	rq->mq_ctx = data->ctx;

  	rq->cmd_flags = op;

  	if (blk_queue_io_stat(data->q))

  		rq->rq_flags |= RQF_IO_STAT;

  	/* do not touch atomic flags, it needs atomic ops against the timer */
  	rq->cpu = -1;

  	INIT_HLIST_NODE(&rq->hash);
  	RB_CLEAR_NODE(&rq->rb_node);

  	rq->rq_disk = NULL;
  	rq->part = NULL;

  	rq->start_time = jiffies;

  #ifdef CONFIG_BLK_CGROUP
  	rq->rl = NULL;

  	set_start_time_ns(rq);

  	rq->io_start_time_ns = 0;
  #endif
  	rq->nr_phys_segments = 0;
  #if defined(CONFIG_BLK_DEV_INTEGRITY)
  	rq->nr_integrity_segments = 0;
  #endif

  	rq->special = NULL;
  	/* tag was already set */

  	rq->extra_len = 0;

  	INIT_LIST_HEAD(&rq->timeout_list);

  	rq->timeout = 0;

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

  	data->ctx->rq_dispatched[op_is_sync(op)]++;
  	return rq;

  }

  static struct request *blk_mq_get_request(struct request_queue *q,
  		struct bio *bio, unsigned int op,
  		struct blk_mq_alloc_data *data)
  {
  	struct elevator_queue *e = q->elevator;
  	struct request *rq;

  	unsigned int tag;

  	struct blk_mq_ctx *local_ctx = NULL;

  
  	blk_queue_enter_live(q);
  	data->q = q;
  	if (likely(!data->ctx))

  		data->ctx = local_ctx = blk_mq_get_ctx(q);

  	if (likely(!data->hctx))
  		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);

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

  
  	if (e) {
  		data->flags |= BLK_MQ_REQ_INTERNAL;
  
  		/*
  		 * Flush requests are special and go directly to the
  		 * dispatch list.
  		 */

  		if (!op_is_flush(op) && e->type->ops.mq.limit_depth)
  			e->type->ops.mq.limit_depth(op, data);

  	}

  	tag = blk_mq_get_tag(data);
  	if (tag == BLK_MQ_TAG_FAIL) {

  		if (local_ctx) {
  			blk_mq_put_ctx(local_ctx);
  			data->ctx = NULL;
  		}

  		blk_queue_exit(q);
  		return NULL;

  	}

  	rq = blk_mq_rq_ctx_init(data, tag, op);

  	if (!op_is_flush(op)) {
  		rq->elv.icq = NULL;

  		if (e && e->type->ops.mq.prepare_request) {

  			if (e->type->icq_cache && rq_ioc(bio))
  				blk_mq_sched_assign_ioc(rq, bio);

  			e->type->ops.mq.prepare_request(rq, bio);
  			rq->rq_flags |= RQF_ELVPRIV;

  		}

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

  }

  struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,

  		unsigned int flags)

  {

  	struct blk_mq_alloc_data alloc_data = { .flags = flags };

  	struct request *rq;

  	int ret;

  	ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT);

  	if (ret)
  		return ERR_PTR(ret);

  	rq = blk_mq_get_request(q, NULL, op, &alloc_data);

  	blk_queue_exit(q);

  	if (!rq)

  		return ERR_PTR(-EWOULDBLOCK);

  	blk_mq_put_ctx(alloc_data.ctx);

  	rq->__data_len = 0;
  	rq->__sector = (sector_t) -1;
  	rq->bio = rq->biotail = NULL;

  	return rq;
  }

  EXPORT_SYMBOL(blk_mq_alloc_request);

  struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
  		unsigned int op, unsigned int flags, unsigned int hctx_idx)

  {

  	struct blk_mq_alloc_data alloc_data = { .flags = flags };

  	struct request *rq;

  	unsigned int cpu;

  	int ret;
  
  	/*
  	 * 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)))
  		return ERR_PTR(-EINVAL);
  
  	if (hctx_idx >= q->nr_hw_queues)
  		return ERR_PTR(-EIO);
  
  	ret = blk_queue_enter(q, true);
  	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.
  	 */

  	alloc_data.hctx = q->queue_hw_ctx[hctx_idx];
  	if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) {
  		blk_queue_exit(q);
  		return ERR_PTR(-EXDEV);

  	}

  	cpu = cpumask_first(alloc_data.hctx->cpumask);
  	alloc_data.ctx = __blk_mq_get_ctx(q, cpu);

  	rq = blk_mq_get_request(q, NULL, op, &alloc_data);

  	blk_queue_exit(q);

  	if (!rq)
  		return ERR_PTR(-EWOULDBLOCK);
  
  	return rq;

  }
  EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);

  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 = blk_mq_map_queue(q, ctx->cpu);
  	const int sched_tag = rq->internal_tag;

  	if (rq->rq_flags & RQF_ELVPRIV) {

  		if (e && e->type->ops.mq.finish_request)
  			e->type->ops.mq.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)

  		atomic_dec(&hctx->nr_active);

  
  	wbt_done(q->rq_wb, &rq->issue_stat);

  	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);

  	clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);

  	if (rq->tag != -1)
  		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
  	if (sched_tag != -1)

  		blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);

  	blk_mq_sched_restart(hctx);

  	blk_queue_exit(q);

  }

  EXPORT_SYMBOL_GPL(blk_mq_free_request);

  inline void __blk_mq_end_request(struct request *rq, blk_status_t error)

  {

  	blk_account_io_done(rq);

  	if (rq->end_io) {

  		wbt_done(rq->q->rq_wb, &rq->issue_stat);

  		rq->end_io(rq, error);

  	} else {
  		if (unlikely(blk_bidi_rq(rq)))
  			blk_mq_free_request(rq->next_rq);

  		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_mq_complete_request_remote(void *data)

  {

  	struct request *rq = data;

  	rq->q->softirq_done_fn(rq);

  }

  static void __blk_mq_complete_request(struct request *rq)

  {
  	struct blk_mq_ctx *ctx = rq->mq_ctx;

  	bool shared = false;

  	int cpu;

  	if (rq->internal_tag != -1)
  		blk_mq_sched_completed_request(rq);
  	if (rq->rq_flags & RQF_STATS) {
  		blk_mq_poll_stats_start(rq->q);
  		blk_stat_add(rq);
  	}

  	if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {

  		rq->q->softirq_done_fn(rq);
  		return;
  	}

  
  	cpu = get_cpu();

  	if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags))
  		shared = cpus_share_cache(cpu, ctx->cpu);
  
  	if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {

  		rq->csd.func = __blk_mq_complete_request_remote;

  		rq->csd.info = rq;
  		rq->csd.flags = 0;

  		smp_call_function_single_async(ctx->cpu, &rq->csd);

  	} else {

  		rq->q->softirq_done_fn(rq);

  	}

  	put_cpu();
  }

  
  /**
   * blk_mq_complete_request - end I/O on a request
   * @rq:		the request being processed
   *
   * Description:
   *	Ends all I/O on a request. It does not handle partial completions.
   *	The actual completion happens out-of-order, through a IPI handler.
   **/

  void blk_mq_complete_request(struct request *rq)

  {

  	struct request_queue *q = rq->q;
  
  	if (unlikely(blk_should_fake_timeout(q)))

  		return;

  	if (!blk_mark_rq_complete(rq))

  		__blk_mq_complete_request(rq);

  }
  EXPORT_SYMBOL(blk_mq_complete_request);

  int blk_mq_request_started(struct request *rq)
  {
  	return test_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
  }
  EXPORT_SYMBOL_GPL(blk_mq_request_started);

  void blk_mq_start_request(struct request *rq)

  {
  	struct request_queue *q = rq->q;

  	blk_mq_sched_started_request(rq);

  	trace_block_rq_issue(q, rq);

  	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {

  		blk_stat_set_issue(&rq->issue_stat, blk_rq_sectors(rq));

  		rq->rq_flags |= RQF_STATS;

  		wbt_issue(q->rq_wb, &rq->issue_stat);

  	}

  	blk_add_timer(rq);

  
  	/*

  	 * Ensure that ->deadline is visible before set the started
  	 * flag and clear the completed flag.
  	 */
  	smp_mb__before_atomic();
  
  	/*

  	 * Mark us as started and clear complete. Complete might have been
  	 * set if requeue raced with timeout, which then marked it as
  	 * complete. So be sure to clear complete again when we start
  	 * the request, otherwise we'll ignore the completion event.
  	 */

  	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
  		set_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
  	if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags))
  		clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);

  
  	if (q->dma_drain_size && blk_rq_bytes(rq)) {
  		/*
  		 * Make sure space for the drain appears.  We know we can do
  		 * this because max_hw_segments has been adjusted to be one
  		 * fewer than the device can handle.
  		 */
  		rq->nr_phys_segments++;
  	}

  }

  EXPORT_SYMBOL(blk_mq_start_request);

  /*
   * When we reach here because queue is busy, REQ_ATOM_COMPLETE

   * flag isn't set yet, so there may be race with timeout handler,

   * but given rq->deadline is just set in .queue_rq() under
   * this situation, the race won't be possible in reality because
   * rq->timeout should be set as big enough to cover the window
   * between blk_mq_start_request() called from .queue_rq() and
   * clearing REQ_ATOM_STARTED here.
   */

  static void __blk_mq_requeue_request(struct request *rq)

  {
  	struct request_queue *q = rq->q;
  
  	trace_block_rq_requeue(q, rq);

  	wbt_requeue(q->rq_wb, &rq->issue_stat);

  	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
  		if (q->dma_drain_size && blk_rq_bytes(rq))
  			rq->nr_phys_segments--;
  	}

  }

  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(blk_queued_rq(rq));

  	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))

  			continue;

  		rq->rq_flags &= ~RQF_SOFTBARRIER;

  		list_del_init(&rq->queuelist);

  		blk_mq_sched_insert_request(rq, true, false, false, true);

  	}
  
  	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, true);

  	}

  	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 insertation 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);

  }
  EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
  
  void blk_mq_kick_requeue_list(struct request_queue *q)
  {

  	kblockd_schedule_delayed_work(&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);

  struct blk_mq_timeout_data {

  	unsigned long next;
  	unsigned int next_set;

  };

  void blk_mq_rq_timed_out(struct request *req, bool reserved)

  {

  	const struct blk_mq_ops *ops = req->q->mq_ops;

  	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;

  
  	/*
  	 * We know that complete is set at this point. If STARTED isn't set
  	 * anymore, then the request isn't active and the "timeout" should
  	 * just be ignored. This can happen due to the bitflag ordering.
  	 * Timeout first checks if STARTED is set, and if it is, assumes
  	 * the request is active. But if we race with completion, then

  	 * both flags will get cleared. So check here again, and ignore

  	 * a timeout event with a request that isn't active.
  	 */

  	if (!test_bit(REQ_ATOM_STARTED, &req->atomic_flags))
  		return;

  	if (ops->timeout)

  		ret = ops->timeout(req, reserved);

  
  	switch (ret) {
  	case BLK_EH_HANDLED:
  		__blk_mq_complete_request(req);
  		break;
  	case BLK_EH_RESET_TIMER:
  		blk_add_timer(req);
  		blk_clear_rq_complete(req);
  		break;
  	case BLK_EH_NOT_HANDLED:
  		break;
  	default:
  		printk(KERN_ERR "block: bad eh return: %d
  ", ret);
  		break;
  	}

  }

  static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
  		struct request *rq, void *priv, bool reserved)
  {
  	struct blk_mq_timeout_data *data = priv;

  	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))

  		return;

  	/*
  	 * The rq being checked may have been freed and reallocated
  	 * out already here, we avoid this race by checking rq->deadline
  	 * and REQ_ATOM_COMPLETE flag together:
  	 *
  	 * - if rq->deadline is observed as new value because of
  	 *   reusing, the rq won't be timed out because of timing.
  	 * - if rq->deadline is observed as previous value,
  	 *   REQ_ATOM_COMPLETE flag won't be cleared in reuse path
  	 *   because we put a barrier between setting rq->deadline
  	 *   and clearing the flag in blk_mq_start_request(), so
  	 *   this rq won't be timed out too.
  	 */

  	if (time_after_eq(jiffies, rq->deadline)) {
  		if (!blk_mark_rq_complete(rq))

  			blk_mq_rq_timed_out(rq, reserved);

  	} else if (!data->next_set || time_after(data->next, rq->deadline)) {
  		data->next = rq->deadline;
  		data->next_set = 1;
  	}

  }

  static void blk_mq_timeout_work(struct work_struct *work)

  {

  	struct request_queue *q =
  		container_of(work, struct request_queue, timeout_work);

  	struct blk_mq_timeout_data data = {
  		.next		= 0,
  		.next_set	= 0,
  	};

  	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, &data);

  	if (data.next_set) {
  		data.next = blk_rq_timeout(round_jiffies_up(data.next));
  		mod_timer(&q->timeout, data.next);

  	} else {

  		struct blk_mq_hw_ctx *hctx;

  		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];
  
  	sbitmap_clear_bit(sb, bitnr);
  	spin_lock(&ctx->lock);
  	list_splice_tail_init(&ctx->rq_list, flush_data->list);
  	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);

  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);

  }

  bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
  			   bool wait)

  {
  	struct blk_mq_alloc_data data = {
  		.q = rq->q,

  		.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
  		.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
  	};

  	might_sleep_if(wait);

  	if (rq->tag != -1)
  		goto done;

  	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
  		data.flags |= BLK_MQ_REQ_RESERVED;

  	rq->tag = blk_mq_get_tag(&data);
  	if (rq->tag >= 0) {

  		if (blk_mq_tag_busy(data.hctx)) {
  			rq->rq_flags |= RQF_MQ_INFLIGHT;
  			atomic_inc(&data.hctx->nr_active);
  		}

  		data.hctx->tags->rqs[rq->tag] = rq;

  	}

  done:
  	if (hctx)
  		*hctx = data.hctx;
  	return rq->tag != -1;

  }

  static void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
  				    struct request *rq)

  {

  	blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
  	rq->tag = -1;
  
  	if (rq->rq_flags & RQF_MQ_INFLIGHT) {
  		rq->rq_flags &= ~RQF_MQ_INFLIGHT;
  		atomic_dec(&hctx->nr_active);
  	}
  }

  static void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx,
  				       struct request *rq)
  {
  	if (rq->tag == -1 || rq->internal_tag == -1)
  		return;
  
  	__blk_mq_put_driver_tag(hctx, rq);
  }
  
  static void blk_mq_put_driver_tag(struct request *rq)
  {
  	struct blk_mq_hw_ctx *hctx;
  
  	if (rq->tag == -1 || rq->internal_tag == -1)
  		return;
  
  	hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
  	__blk_mq_put_driver_tag(hctx, rq);
  }

  /*
   * If we fail getting a driver tag because all the driver tags are already
   * assigned and on the dispatch list, BUT the first entry does not have a
   * tag, then we could deadlock. For that case, move entries with assigned
   * driver tags to the front, leaving the set of tagged requests in the
   * same order, and the untagged set in the same order.
   */
  static bool reorder_tags_to_front(struct list_head *list)
  {
  	struct request *rq, *tmp, *first = NULL;
  
  	list_for_each_entry_safe_reverse(rq, tmp, list, queuelist) {
  		if (rq == first)
  			break;
  		if (rq->tag != -1) {
  			list_move(&rq->queuelist, list);
  			if (!first)
  				first = rq;
  		}
  	}
  
  	return first != NULL;
  }

  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);

  	list_del(&wait->entry);

  	clear_bit_unlock(BLK_MQ_S_TAG_WAITING, &hctx->state);
  	blk_mq_run_hw_queue(hctx, true);
  	return 1;
  }
  
  static bool blk_mq_dispatch_wait_add(struct blk_mq_hw_ctx *hctx)
  {
  	struct sbq_wait_state *ws;
  
  	/*
  	 * The TAG_WAITING bit serves as a lock protecting hctx->dispatch_wait.
  	 * The thread which wins the race to grab this bit adds the hardware
  	 * queue to the wait queue.
  	 */
  	if (test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state) ||
  	    test_and_set_bit_lock(BLK_MQ_S_TAG_WAITING, &hctx->state))
  		return false;
  
  	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
  	ws = bt_wait_ptr(&hctx->tags->bitmap_tags, hctx);
  
  	/*
  	 * As soon as this returns, it's no longer safe to fiddle with
  	 * hctx->dispatch_wait, since a completion can wake up the wait queue
  	 * and unlock the bit.
  	 */
  	add_wait_queue(&ws->wait, &hctx->dispatch_wait);
  	return true;
  }

  bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)

  {

  	struct blk_mq_hw_ctx *hctx;

  	struct request *rq;

  	int errors, queued;

  	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;

  		blk_status_t ret;

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

  		if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
  			if (!queued && reorder_tags_to_front(list))
  				continue;

  
  			/*

  			 * The initial allocation attempt failed, so we need to
  			 * rerun the hardware queue when a tag is freed.

  			 */

  			if (!blk_mq_dispatch_wait_add(hctx))
  				break;
  
  			/*
  			 * It's possible that a tag was freed in the window
  			 * between the allocation failure and adding the
  			 * hardware queue to the wait queue.
  			 */
  			if (!blk_mq_get_driver_tag(rq, &hctx, false))

  				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 {
  			struct request *nxt;
  
  			nxt = list_first_entry(list, struct request, queuelist);
  			bd.last = !blk_mq_get_driver_tag(nxt, NULL, false);
  		}

  
  		ret = q->mq_ops->queue_rq(hctx, &bd);

  		if (ret == BLK_STS_RESOURCE) {

  			blk_mq_put_driver_tag_hctx(hctx, rq);

  			list_add(&rq->queuelist, list);

  			__blk_mq_requeue_request(rq);

  			break;

  		}
  
  		if (unlikely(ret != BLK_STS_OK)) {

  			errors++;

  			blk_mq_end_request(rq, BLK_STS_IOERR);

  			continue;

  		}

  		queued++;

  	} while (!list_empty(list));

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

  
  	/*
  	 * Any items that need requeuing? Stuff them into hctx->dispatch,
  	 * that is where we will continue on next queue run.
  	 */

  	if (!list_empty(list)) {

  		/*

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

  		 */
  		rq = list_first_entry(list, struct request, queuelist);
  		blk_mq_put_driver_tag(rq);

  		spin_lock(&hctx->lock);

  		list_splice_init(list, &hctx->dispatch);

  		spin_unlock(&hctx->lock);

  		/*

  		 * 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 TAG_WAITING is set that means that an I/O scheduler has
  		 * been configured and another thread is waiting for a driver
  		 * tag. To guarantee fairness, do not rerun this hardware queue
  		 * but let the other thread grab the driver tag.

  		 *

  		 * 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 (!blk_mq_sched_needs_restart(hctx) &&
  		    !test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state))

  			blk_mq_run_hw_queue(hctx, true);

  	}

  	return (queued + errors) != 0;

  }

  static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
  {
  	int srcu_idx;

  	/*
  	 * We should be running this queue from one of the CPUs that
  	 * are mapped to it.

  	 *
  	 * There are at least two related races now between setting
  	 * hctx->next_cpu from blk_mq_hctx_next_cpu() and running
  	 * __blk_mq_run_hw_queue():
  	 *
  	 * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(),
  	 *   but later it becomes online, then this warning is harmless
  	 *   at all
  	 *
  	 * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(),
  	 *   but later it becomes offline, then the warning can't be
  	 *   triggered, and we depend on blk-mq timeout handler to
  	 *   handle dispatched requests to this hctx

  	 */

  	if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
  		cpu_online(hctx->next_cpu)) {
  		printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s
  ",
  			raw_smp_processor_id(),
  			cpumask_empty(hctx->cpumask) ? "inactive": "active");
  		dump_stack();
  	}

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

  	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
  		rcu_read_lock();

  		blk_mq_sched_dispatch_requests(hctx);

  		rcu_read_unlock();
  	} else {

  		might_sleep();

  		srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);

  		blk_mq_sched_dispatch_requests(hctx);

  		srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);

  	}
  }

  /*
   * 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)
  {

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

  
  	if (--hctx->next_cpu_batch <= 0) {

  		int next_cpu;

  
  		next_cpu = cpumask_next(hctx->next_cpu, hctx->cpumask);
  		if (next_cpu >= nr_cpu_ids)
  			next_cpu = cpumask_first(hctx->cpumask);
  
  		hctx->next_cpu = next_cpu;
  		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
  	}

  	return hctx->next_cpu;

  }

  static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
  					unsigned long msecs)

  {

  	if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
  		return;
  
  	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_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
  					 &hctx->run_work,
  					 msecs_to_jiffies(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);
  
  void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
  {
  	__blk_mq_delay_run_hw_queue(hctx, async, 0);

  }

  EXPORT_SYMBOL(blk_mq_run_hw_queue);

  void blk_mq_run_hw_queues(struct request_queue *q, bool async)

  {
  	struct blk_mq_hw_ctx *hctx;
  	int i;
  
  	queue_for_each_hw_ctx(q, hctx, i) {

  		if (!blk_mq_hctx_has_pending(hctx) ||

  		    blk_mq_hctx_stopped(hctx))

  			continue;

  		blk_mq_run_hw_queue(hctx, async);

  	}
  }

  EXPORT_SYMBOL(blk_mq_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. The exception is if
  	 * BLK_MQ_S_START_ON_RUN is set. For that case, we auto-clear
  	 * the STOPPED bit and run it.
  	 */
  	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state)) {
  		if (!test_bit(BLK_MQ_S_START_ON_RUN, &hctx->state))
  			return;

  		clear_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
  		clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
  	}

  
  	__blk_mq_run_hw_queue(hctx);
  }

  
  void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
  {

  	if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))

  		return;

  	/*
  	 * Stop the hw queue, then modify currently delayed work.
  	 * This should prevent us from running the queue prematurely.
  	 * Mark the queue as auto-clearing STOPPED when it runs.
  	 */

  	blk_mq_stop_hw_queue(hctx);

  	set_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
  	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
  					&hctx->run_work,
  					msecs_to_jiffies(msecs));

  }
  EXPORT_SYMBOL(blk_mq_delay_queue);

  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;

  	lockdep_assert_held(&ctx->lock);

  	trace_block_rq_insert(hctx->queue, rq);

  	if (at_head)
  		list_add(&rq->queuelist, &ctx->rq_list);
  	else
  		list_add_tail(&rq->queuelist, &ctx->rq_list);

  }

  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);

  }

  /*
   * 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)
  {
  	struct blk_mq_ctx *ctx = rq->mq_ctx;
  	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
  
  	spin_lock(&hctx->lock);
  	list_add_tail(&rq->queuelist, &hctx->dispatch);
  	spin_unlock(&hctx->lock);
  
  	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)

  
  {

  	/*
  	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
  	 * offline now
  	 */
  	spin_lock(&ctx->lock);
  	while (!list_empty(list)) {
  		struct request *rq;
  
  		rq = list_first_entry(list, struct request, queuelist);

  		BUG_ON(rq->mq_ctx != ctx);

  		list_del_init(&rq->queuelist);

  		__blk_mq_insert_req_list(hctx, rq, false);

  	}

  	blk_mq_hctx_mark_pending(hctx, ctx);

  	spin_unlock(&ctx->lock);

  }
  
  static int plug_ctx_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_ctx < rqb->mq_ctx ||
  		 (rqa->mq_ctx == rqb->mq_ctx &&
  		  blk_rq_pos(rqa) < blk_rq_pos(rqb)));
  }
  
  void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
  {
  	struct blk_mq_ctx *this_ctx;
  	struct request_queue *this_q;
  	struct request *rq;
  	LIST_HEAD(list);
  	LIST_HEAD(ctx_list);
  	unsigned int depth;
  
  	list_splice_init(&plug->mq_list, &list);
  
  	list_sort(NULL, &list, plug_ctx_cmp);
  
  	this_q = NULL;
  	this_ctx = NULL;
  	depth = 0;
  
  	while (!list_empty(&list)) {
  		rq = list_entry_rq(list.next);
  		list_del_init(&rq->queuelist);
  		BUG_ON(!rq->q);
  		if (rq->mq_ctx != this_ctx) {
  			if (this_ctx) {

  				trace_block_unplug(this_q, depth, !from_schedule);

  				blk_mq_sched_insert_requests(this_q, this_ctx,
  								&ctx_list,
  								from_schedule);

  			}
  
  			this_ctx = rq->mq_ctx;
  			this_q = rq->q;
  			depth = 0;
  		}
  
  		depth++;
  		list_add_tail(&rq->queuelist, &ctx_list);
  	}
  
  	/*
  	 * If 'this_ctx' is set, we know we have entries to complete
  	 * on 'ctx_list'. Do those.
  	 */
  	if (this_ctx) {

  		trace_block_unplug(this_q, depth, !from_schedule);

  		blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
  						from_schedule);

  	}
  }
  
  static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
  {

  	blk_init_request_from_bio(rq, bio);

  	blk_account_io_start(rq, true);

  }

  static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx)
  {
  	return (hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
  		!blk_queue_nomerges(hctx->queue);
  }

  static inline void blk_mq_queue_io(struct blk_mq_hw_ctx *hctx,
  				   struct blk_mq_ctx *ctx,
  				   struct request *rq)
  {
  	spin_lock(&ctx->lock);
  	__blk_mq_insert_request(hctx, rq, false);
  	spin_unlock(&ctx->lock);

  }

  static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
  {

  	if (rq->tag != -1)
  		return blk_tag_to_qc_t(rq->tag, hctx->queue_num, false);
  
  	return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);

  }

  static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
  					struct request *rq,
  					blk_qc_t *cookie, bool may_sleep)

  {

  	struct request_queue *q = rq->q;

  	struct blk_mq_queue_data bd = {
  		.rq = rq,

  		.last = true,

  	};

  	blk_qc_t new_cookie;

  	blk_status_t ret;

  	bool run_queue = true;

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

  		run_queue = false;
  		goto insert;
  	}

  	if (q->elevator)

  		goto insert;

  	if (!blk_mq_get_driver_tag(rq, NULL, false))

  		goto insert;
  
  	new_cookie = request_to_qc_t(hctx, rq);

  	/*
  	 * For OK queue, we are done. For error, 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:

  		*cookie = new_cookie;

  		return;

  	case BLK_STS_RESOURCE:
  		__blk_mq_requeue_request(rq);
  		goto insert;
  	default:

  		*cookie = BLK_QC_T_NONE;

  		blk_mq_end_request(rq, ret);

  		return;

  	}

  insert:

  	blk_mq_sched_insert_request(rq, false, run_queue, false, may_sleep);

  }

  static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
  		struct request *rq, blk_qc_t *cookie)
  {
  	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
  		rcu_read_lock();

  		__blk_mq_try_issue_directly(hctx, rq, cookie, false);

  		rcu_read_unlock();
  	} else {

  		unsigned int srcu_idx;
  
  		might_sleep();

  		srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);

  		__blk_mq_try_issue_directly(hctx, rq, cookie, true);

  		srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);

  	}
  }

  static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)

  {

  	const int is_sync = op_is_sync(bio->bi_opf);

  	const int is_flush_fua = op_is_flush(bio->bi_opf);

  	struct blk_mq_alloc_data data = { .flags = 0 };

  	struct request *rq;

  	unsigned int request_count = 0;

  	struct blk_plug *plug;

  	struct request *same_queue_rq = NULL;

  	blk_qc_t cookie;