/*
   * 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/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-tag.h"
  
  static DEFINE_MUTEX(all_q_mutex);
  static LIST_HEAD(all_q_list);

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

  	return sbitmap_any_bit_set(&hctx->ctx_map);

  }

  /*
   * 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);

  }

  void blk_mq_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_mq_freeze_queue_start);

  
  static void blk_mq_freeze_queue_wait(struct request_queue *q)
  {

  	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));

  }

  /*
   * 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_mq_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)

  {

  	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);

  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 void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,

  			       struct request *rq, int op,
  			       unsigned int op_flags)

  {

  	if (blk_queue_io_stat(q))

  		op_flags |= REQ_IO_STAT;

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

  	rq->mq_ctx = ctx;

  	req_set_op_attrs(rq, op, op_flags);

  	/* 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->errors = 0;

  	rq->cmd = rq->__cmd;

  	rq->extra_len = 0;
  	rq->sense_len = 0;
  	rq->resid_len = 0;
  	rq->sense = NULL;

  	INIT_LIST_HEAD(&rq->timeout_list);

  	rq->timeout = 0;

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

  	ctx->rq_dispatched[rw_is_sync(op, op_flags)]++;

  }

  static struct request *

  __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags)

  {
  	struct request *rq;
  	unsigned int tag;

  	tag = blk_mq_get_tag(data);

  	if (tag != BLK_MQ_TAG_FAIL) {

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

  		if (blk_mq_tag_busy(data->hctx)) {

  			rq->cmd_flags = REQ_MQ_INFLIGHT;

  			atomic_inc(&data->hctx->nr_active);

  		}
  
  		rq->tag = tag;

  		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op, op_flags);

  		return rq;
  	}
  
  	return NULL;
  }

  struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
  		unsigned int flags)

  {

  	struct blk_mq_ctx *ctx;
  	struct blk_mq_hw_ctx *hctx;

  	struct request *rq;

  	struct blk_mq_alloc_data alloc_data;

  	int ret;

  	ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT);

  	if (ret)
  		return ERR_PTR(ret);

  	ctx = blk_mq_get_ctx(q);

  	hctx = blk_mq_map_queue(q, ctx->cpu);

  	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);

  	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);

  	blk_mq_put_ctx(ctx);

  	if (!rq) {

  		blk_queue_exit(q);

  		return ERR_PTR(-EWOULDBLOCK);

  	}

  
  	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, int rw,
  		unsigned int flags, unsigned int hctx_idx)
  {
  	struct blk_mq_hw_ctx *hctx;
  	struct blk_mq_ctx *ctx;
  	struct request *rq;
  	struct blk_mq_alloc_data alloc_data;
  	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.
  	 */

  	hctx = q->queue_hw_ctx[hctx_idx];

  	if (!blk_mq_hw_queue_mapped(hctx)) {
  		ret = -EXDEV;
  		goto out_queue_exit;
  	}

  	ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask));
  
  	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
  	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
  	if (!rq) {

  		ret = -EWOULDBLOCK;
  		goto out_queue_exit;

  	}
  
  	return rq;

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

  	if (rq->cmd_flags & REQ_MQ_INFLIGHT)
  		atomic_dec(&hctx->nr_active);

  	rq->cmd_flags = 0;

  	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);

  	blk_mq_put_tag(hctx, ctx, tag);

  	blk_queue_exit(q);

  }

  void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *hctx, struct request *rq)

  {
  	struct blk_mq_ctx *ctx = rq->mq_ctx;

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

  	__blk_mq_free_request(hctx, ctx, rq);

  
  }
  EXPORT_SYMBOL_GPL(blk_mq_free_hctx_request);
  
  void blk_mq_free_request(struct request *rq)
  {

  	blk_mq_free_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);

  }

  EXPORT_SYMBOL_GPL(blk_mq_free_request);

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

  {

  	blk_account_io_done(rq);

  	if (rq->end_io) {

  		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, int 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_ipi_complete_request(struct request *rq)

  {
  	struct blk_mq_ctx *ctx = rq->mq_ctx;

  	bool shared = false;

  	int cpu;

  	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();
  }

  static void __blk_mq_complete_request(struct request *rq)

  {
  	struct request_queue *q = rq->q;
  
  	if (!q->softirq_done_fn)

  		blk_mq_end_request(rq, rq->errors);

  	else
  		blk_mq_ipi_complete_request(rq);
  }

  /**
   * 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, int error)

  {

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

  		return;

  	if (!blk_mark_rq_complete(rq)) {
  		rq->errors = error;

  		__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;
  
  	trace_block_rq_issue(q, rq);

  	rq->resid_len = blk_rq_bytes(rq);

  	if (unlikely(blk_bidi_rq(rq)))
  		rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);

  	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);

  static void __blk_mq_requeue_request(struct request *rq)

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

  	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)
  {

  	__blk_mq_requeue_request(rq);

  	BUG_ON(blk_queued_rq(rq));

  	blk_mq_add_to_requeue_list(rq, true);

  }
  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;
  	unsigned long flags;
  
  	spin_lock_irqsave(&q->requeue_lock, flags);
  	list_splice_init(&q->requeue_list, &rq_list);
  	spin_unlock_irqrestore(&q->requeue_lock, flags);
  
  	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
  		if (!(rq->cmd_flags & REQ_SOFTBARRIER))
  			continue;
  
  		rq->cmd_flags &= ~REQ_SOFTBARRIER;
  		list_del_init(&rq->queuelist);
  		blk_mq_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_insert_request(rq, false, false, false);
  	}

  	/*
  	 * Use the start variant of queue running here, so that running
  	 * the requeue work will kick stopped queues.
  	 */
  	blk_mq_start_hw_queues(q);

  }
  
  void blk_mq_add_to_requeue_list(struct request *rq, bool at_head)
  {
  	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->cmd_flags & REQ_SOFTBARRIER);
  
  	spin_lock_irqsave(&q->requeue_lock, flags);
  	if (at_head) {
  		rq->cmd_flags |= REQ_SOFTBARRIER;
  		list_add(&rq->queuelist, &q->requeue_list);
  	} else {
  		list_add_tail(&rq->queuelist, &q->requeue_list);
  	}
  	spin_unlock_irqrestore(&q->requeue_lock, flags);
  }
  EXPORT_SYMBOL(blk_mq_add_to_requeue_list);

  void blk_mq_cancel_requeue_work(struct request_queue *q)
  {

  	cancel_delayed_work_sync(&q->requeue_work);

  }
  EXPORT_SYMBOL_GPL(blk_mq_cancel_requeue_work);

  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_schedule_delayed_work(&q->requeue_work,
  				      msecs_to_jiffies(msecs));
  }
  EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);

  void blk_mq_abort_requeue_list(struct request_queue *q)
  {
  	unsigned long flags;
  	LIST_HEAD(rq_list);
  
  	spin_lock_irqsave(&q->requeue_lock, flags);
  	list_splice_init(&q->requeue_list, &rq_list);
  	spin_unlock_irqrestore(&q->requeue_lock, flags);
  
  	while (!list_empty(&rq_list)) {
  		struct request *rq;
  
  		rq = list_first_entry(&rq_list, struct request, queuelist);
  		list_del_init(&rq->queuelist);
  		rq->errors = -EIO;
  		blk_mq_end_request(rq, rq->errors);
  	}
  }
  EXPORT_SYMBOL(blk_mq_abort_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)

  {

  	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
  	 * we 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)) {
  		/*
  		 * If a request wasn't started before the queue was
  		 * marked dying, kill it here or it'll go unnoticed.
  		 */

  		if (unlikely(blk_queue_dying(rq->q))) {
  			rq->errors = -EIO;
  			blk_mq_end_request(rq, rq->errors);
  		}

  		return;

  	}

  	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_mq_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);

  }
  
  /*
   * Reverse check our software queue for entries that we could potentially
   * merge with. Currently includes a hand-wavy stop count of 8, to not spend
   * too much time checking for merges.
   */
  static bool blk_mq_attempt_merge(struct request_queue *q,
  				 struct blk_mq_ctx *ctx, struct bio *bio)
  {
  	struct request *rq;
  	int checked = 8;
  
  	list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
  		int el_ret;
  
  		if (!checked--)
  			break;
  
  		if (!blk_rq_merge_ok(rq, bio))
  			continue;
  
  		el_ret = blk_try_merge(rq, bio);
  		if (el_ret == ELEVATOR_BACK_MERGE) {
  			if (bio_attempt_back_merge(q, rq, bio)) {
  				ctx->rq_merged++;
  				return true;
  			}
  			break;
  		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
  			if (bio_attempt_front_merge(q, rq, bio)) {
  				ctx->rq_merged++;
  				return true;
  			}
  			break;
  		}
  	}
  
  	return false;
  }

  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
   */
  static void 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);

  }

  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);

  }
  
  /*

   * Run this hardware queue, pulling any software queues mapped to it in.
   * Note that this function currently has various problems around ordering
   * of IO. In particular, we'd like FIFO behaviour on handling existing
   * items on the hctx->dispatch list. Ignore that for now.
   */
  static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
  {
  	struct request_queue *q = hctx->queue;

  	struct request *rq;
  	LIST_HEAD(rq_list);

  	LIST_HEAD(driver_list);
  	struct list_head *dptr;

  	int queued;

  	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))

  		return;

  	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
  		cpu_online(hctx->next_cpu));

  	hctx->run++;
  
  	/*
  	 * Touch any software queue that has pending entries.
  	 */

  	flush_busy_ctxs(hctx, &rq_list);

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

  	 * Start off with dptr being NULL, so we start the first request
  	 * immediately, even if we have more pending.
  	 */
  	dptr = NULL;
  
  	/*

  	 * Now process all the entries, sending them to the driver.
  	 */

  	queued = 0;

  	while (!list_empty(&rq_list)) {

  		struct blk_mq_queue_data bd;

  		int ret;
  
  		rq = list_first_entry(&rq_list, struct request, queuelist);
  		list_del_init(&rq->queuelist);

  		bd.rq = rq;
  		bd.list = dptr;
  		bd.last = list_empty(&rq_list);
  
  		ret = q->mq_ops->queue_rq(hctx, &bd);

  		switch (ret) {
  		case BLK_MQ_RQ_QUEUE_OK:
  			queued++;

  			break;

  		case BLK_MQ_RQ_QUEUE_BUSY:

  			list_add(&rq->queuelist, &rq_list);

  			__blk_mq_requeue_request(rq);

  			break;
  		default:
  			pr_err("blk-mq: bad return on queue: %d
  ", ret);

  		case BLK_MQ_RQ_QUEUE_ERROR:

  			rq->errors = -EIO;

  			blk_mq_end_request(rq, rq->errors);

  			break;
  		}
  
  		if (ret == BLK_MQ_RQ_QUEUE_BUSY)
  			break;

  
  		/*
  		 * We've done the first request. If we have more than 1
  		 * left in the list, set dptr to defer issue.
  		 */
  		if (!dptr && rq_list.next != rq_list.prev)
  			dptr = &driver_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(&rq_list)) {
  		spin_lock(&hctx->lock);
  		list_splice(&rq_list, &hctx->dispatch);
  		spin_unlock(&hctx->lock);

  		/*
  		 * the queue is expected stopped with BLK_MQ_RQ_QUEUE_BUSY, but
  		 * it's possible the queue is stopped and restarted again
  		 * before this. Queue restart will dispatch requests. And since
  		 * requests in rq_list aren't added into hctx->dispatch yet,
  		 * the requests in rq_list might get lost.
  		 *
  		 * blk_mq_run_hw_queue() already checks the STOPPED bit
  		 **/
  		blk_mq_run_hw_queue(hctx, true);

  	}
  }

  /*
   * 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 cpu = hctx->next_cpu, 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 cpu;

  	}

  	return hctx->next_cpu;

  }

  void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
  {

  	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state) ||
  	    !blk_mq_hw_queue_mapped(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_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work);

  }

  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) &&
  		    list_empty_careful(&hctx->dispatch)) ||

  		    test_bit(BLK_MQ_S_STOPPED, &hctx->state))

  			continue;

  		blk_mq_run_hw_queue(hctx, async);

  	}
  }

  EXPORT_SYMBOL(blk_mq_run_hw_queues);

  
  void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
  {

  	cancel_work(&hctx->run_work);

  	cancel_delayed_work(&hctx->delay_work);

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

  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_queues(struct request_queue *q, bool async)

  {
  	struct blk_mq_hw_ctx *hctx;
  	int i;
  
  	queue_for_each_hw_ctx(q, hctx, i) {
  		if (!test_bit(BLK_MQ_S_STOPPED, &hctx->state))
  			continue;
  
  		clear_bit(BLK_MQ_S_STOPPED, &hctx->state);

  		blk_mq_run_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);

  	__blk_mq_run_hw_queue(hctx);
  }

  static void blk_mq_delay_work_fn(struct work_struct *work)
  {
  	struct blk_mq_hw_ctx *hctx;
  
  	hctx = container_of(work, struct blk_mq_hw_ctx, delay_work.work);
  
  	if (test_and_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 (unlikely(!blk_mq_hw_queue_mapped(hctx)))
  		return;

  	kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
  			&hctx->delay_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;

  	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);

  }

  static 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;

  	__blk_mq_insert_req_list(hctx, rq, at_head);

  	blk_mq_hctx_mark_pending(hctx, ctx);

  }

  void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,

  			   bool async)

  {

  	struct blk_mq_ctx *ctx = rq->mq_ctx;

  	struct request_queue *q = rq->q;

  	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);

  	spin_lock(&ctx->lock);
  	__blk_mq_insert_request(hctx, rq, at_head);
  	spin_unlock(&ctx->lock);

  	if (run_queue)
  		blk_mq_run_hw_queue(hctx, async);
  }
  
  static void blk_mq_insert_requests(struct request_queue *q,
  				     struct blk_mq_ctx *ctx,
  				     struct list_head *list,
  				     int depth,
  				     bool from_schedule)
  
  {

  	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);

  
  	trace_block_unplug(q, depth, !from_schedule);

  	/*
  	 * 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);

  	blk_mq_run_hw_queue(hctx, from_schedule);
  }
  
  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) {
  				blk_mq_insert_requests(this_q, this_ctx,
  							&ctx_list, depth,
  							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) {
  		blk_mq_insert_requests(this_q, this_ctx, &ctx_list, depth,
  				       from_schedule);
  	}
  }
  
  static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
  {
  	init_request_from_bio(rq, bio);

  	blk_account_io_start(rq, 1);

  }

  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 bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx,
  					 struct blk_mq_ctx *ctx,
  					 struct request *rq, struct bio *bio)

  {

  	if (!hctx_allow_merges(hctx) || !bio_mergeable(bio)) {

  		blk_mq_bio_to_request(rq, bio);
  		spin_lock(&ctx->lock);
  insert_rq:
  		__blk_mq_insert_request(hctx, rq, false);
  		spin_unlock(&ctx->lock);
  		return false;
  	} else {

  		struct request_queue *q = hctx->queue;

  		spin_lock(&ctx->lock);
  		if (!blk_mq_attempt_merge(q, ctx, bio)) {
  			blk_mq_bio_to_request(rq, bio);
  			goto insert_rq;
  		}

  		spin_unlock(&ctx->lock);
  		__blk_mq_free_request(hctx, ctx, rq);
  		return true;

  	}

  }

  struct blk_map_ctx {
  	struct blk_mq_hw_ctx *hctx;
  	struct blk_mq_ctx *ctx;
  };
  
  static struct request *blk_mq_map_request(struct request_queue *q,
  					  struct bio *bio,
  					  struct blk_map_ctx *data)
  {
  	struct blk_mq_hw_ctx *hctx;
  	struct blk_mq_ctx *ctx;
  	struct request *rq;

  	int op = bio_data_dir(bio);
  	int op_flags = 0;

  	struct blk_mq_alloc_data alloc_data;

  	blk_queue_enter_live(q);

  	ctx = blk_mq_get_ctx(q);

  	hctx = blk_mq_map_queue(q, ctx->cpu);

  	if (rw_is_sync(bio_op(bio), bio->bi_opf))

  		op_flags |= REQ_SYNC;

  	trace_block_getrq(q, bio, op);

  	blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx);

  	rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);

  
  	hctx->queued++;

  	data->hctx = hctx;
  	data->ctx = ctx;
  	return rq;
  }

  static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)

  {
  	int ret;
  	struct request_queue *q = rq->q;

  	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);

  	struct blk_mq_queue_data bd = {
  		.rq = rq,
  		.list = NULL,
  		.last = 1
  	};

  	blk_qc_t new_cookie = blk_tag_to_qc_t(rq->tag, hctx->queue_num);

  
  	/*
  	 * 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);

  	if (ret == BLK_MQ_RQ_QUEUE_OK) {
  		*cookie = new_cookie;

  		return 0;

  	}

  	__blk_mq_requeue_request(rq);
  
  	if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
  		*cookie = BLK_QC_T_NONE;
  		rq->errors = -EIO;
  		blk_mq_end_request(rq, rq->errors);
  		return 0;

  	}

  
  	return -1;

  }

  /*
   * Multiple hardware queue variant. This will not use per-process plugs,
   * but will attempt to bypass the hctx queueing if we can go straight to
   * hardware for SYNC IO.
   */

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

  {

  	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf);
  	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);

  	struct blk_map_ctx data;
  	struct request *rq;

  	unsigned int request_count = 0;
  	struct blk_plug *plug;

  	struct request *same_queue_rq = NULL;

  	blk_qc_t cookie;

  
  	blk_queue_bounce(q, &bio);
  
  	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {

  		bio_io_error(bio);

  		return BLK_QC_T_NONE;

  	}

  	blk_queue_split(q, &bio, q->bio_split);

  	if (!is_flush_fua && !blk_queue_nomerges(q) &&
  	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
  		return BLK_QC_T_NONE;

  	rq = blk_mq_map_request(q, bio, &data);
  	if (unlikely(!rq))

  		return BLK_QC_T_NONE;

  	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);

  
  	if (unlikely(is_flush_fua)) {
  		blk_mq_bio_to_request(rq, bio);
  		blk_insert_flush(rq);
  		goto run_queue;
  	}

  	plug = current->plug;

  	/*
  	 * If the driver supports defer issued based on 'last', then
  	 * queue it up like normal since we can potentially save some
  	 * CPU this way.
  	 */

  	if (((plug && !blk_queue_nomerges(q)) || is_sync) &&
  	    !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
  		struct request *old_rq = NULL;

  
  		blk_mq_bio_to_request(rq, bio);

  
  		/*

  		 * We do limited pluging. If the bio can be merged, do that.

  		 * Otherwise the existing request in the plug list will be
  		 * issued. So the plug list will have one request at most

  		 */

  		if (plug) {

  			/*
  			 * The plug list might get flushed before this. If that

  			 * happens, same_queue_rq is invalid and plug list is
  			 * empty
  			 */

  			if (same_queue_rq && !list_empty(&plug->mq_list)) {
  				old_rq = same_queue_rq;

  				list_del_init(&old_rq->queuelist);

  			}

  			list_add_tail(&rq->queuelist, &plug->mq_list);
  		} else /* is_sync */
  			old_rq = rq;
  		blk_mq_put_ctx(data.ctx);
  		if (!old_rq)

  			goto done;
  		if (!blk_mq_direct_issue_request(old_rq, &cookie))
  			goto done;

  		blk_mq_insert_request(old_rq, false, true, true);

  		goto done;

  	}
  
  	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
  		/*
  		 * For a SYNC request, send it to the hardware immediately. For
  		 * an ASYNC request, just ensure that we run it later on. The
  		 * latter allows for merging opportunities and more efficient
  		 * dispatching.
  		 */
  run_queue:
  		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
  	}

  	blk_mq_put_ctx(data.ctx);

  done:
  	return cookie;

  }
  
  /*
   * Single hardware queue variant. This will attempt to use any per-process
   * plug for merging and IO deferral.
   */

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

  {

  	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf);
  	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);

  	struct blk_plug *plug;
  	unsigned int request_count = 0;

  	struct blk_map_ctx data;
  	struct request *rq;

  	blk_qc_t cookie;

  	blk_queue_bounce(q, &bio);
  
  	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {

  		bio_io_error(bio);

  		return BLK_QC_T_NONE;

  	}

  	blk_queue_split(q, &bio, q->bio_split);

  	if (!is_flush_fua && !blk_queue_nomerges(q)) {
  		if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
  			return BLK_QC_T_NONE;
  	} else
  		request_count = blk_plug_queued_count(q);

  
  	rq = blk_mq_map_request(q, bio, &data);

  	if (unlikely(!rq))

  		return BLK_QC_T_NONE;

  	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);

  
  	if (unlikely(is_flush_fua)) {
  		blk_mq_bio_to_request(rq, bio);

  		blk_insert_flush(rq);
  		goto run_queue;
  	}
  
  	/*
  	 * A task plug currently exists. Since this is completely lockless,
  	 * utilize that to temporarily store requests until the task is
  	 * either done or scheduled away.
  	 */

  	plug = current->plug;
  	if (plug) {
  		blk_mq_bio_to_request(rq, bio);

  		if (!request_count)

  			trace_block_plug(q);

  
  		blk_mq_put_ctx(data.ctx);
  
  		if (request_count >= BLK_MAX_REQUEST_COUNT) {

  			blk_flush_plug_list(plug, false);
  			trace_block_plug(q);

  		}

  		list_add_tail(&rq->queuelist, &plug->mq_list);

  		return cookie;

  	}

  	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
  		/*
  		 * For a SYNC request, send it to the hardware immediately. For
  		 * an ASYNC request, just ensure that we run it later on. The
  		 * latter allows for merging opportunities and more efficient
  		 * dispatching.
  		 */
  run_queue:
  		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);

  	}

  	blk_mq_put_ctx(data.ctx);

  	return cookie;

  }

  static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
  		struct blk_mq_tags *tags, unsigned int hctx_idx)

  {

  	struct page *page;

  	if (tags->rqs && set->ops->exit_request) {

  		int i;

  		for (i = 0; i < tags->nr_tags; i++) {
  			if (!tags->rqs[i])

  				continue;

  			set->ops->exit_request(set->driver_data, tags->rqs[i],
  						hctx_idx, i);

  			tags->rqs[i] = NULL;

  		}

  	}

  	while (!list_empty(&tags->page_list)) {
  		page = list_first_entry(&tags->page_list, struct page, lru);

  		list_del_init(&page->lru);

  		/*
  		 * Remove kmemleak object previously allocated in
  		 * blk_mq_init_rq_map().
  		 */
  		kmemleak_free(page_address(page));

  		__free_pages(page, page->private);
  	}

  	kfree(tags->rqs);

  	blk_mq_free_tags(tags);

  }
  
  static size_t order_to_size(unsigned int order)
  {

  	return (size_t)PAGE_SIZE << order;

  }

  static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
  		unsigned int hctx_idx)

  {

  	struct blk_mq_tags *tags;

  	unsigned int i, j, entries_per_page, max_order = 4;
  	size_t rq_size, left;

  	tags = blk_mq_init_tags(set->queue_depth, set->reserved_tags,

  				set->numa_node,
  				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));

  	if (!tags)
  		return NULL;

  	INIT_LIST_HEAD(&tags->page_list);

  	tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *),
  				 GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
  				 set->numa_node);

  	if (!tags->rqs) {
  		blk_mq_free_tags(tags);
  		return NULL;
  	}

  
  	/*
  	 * rq_size is the size of the request plus driver payload, rounded
  	 * to the cacheline size
  	 */

  	rq_size = round_up(sizeof(struct request) + set->cmd_size,

  				cache_line_size());

  	left = rq_size * set->queue_depth;

  	for (i = 0; i < set->queue_depth; ) {

  		int this_order = max_order;
  		struct page *page;
  		int to_do;
  		void *p;

  		while (this_order && left < order_to_size(this_order - 1))

  			this_order--;
  
  		do {

  			page = alloc_pages_node(set->numa_node,

  				GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,

  				this_order);

  			if (page)
  				break;
  			if (!this_order--)
  				break;
  			if (order_to_size(this_order) < rq_size)
  				break;
  		} while (1);
  
  		if (!page)

  			goto fail;

  
  		page->private = this_order;

  		list_add_tail(&page->lru, &tags->page_list);

  
  		p = page_address(page);

  		/*
  		 * Allow kmemleak to scan these pages as they contain pointers
  		 * to additional allocations like via ops->init_request().
  		 */
  		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_KERNEL);

  		entries_per_page = order_to_size(this_order) / rq_size;

  		to_do = min(entries_per_page, set->queue_depth - i);

  		left -= to_do * rq_size;
  		for (j = 0; j < to_do; j++) {

  			tags->rqs[i] = p;
  			if (set->ops->init_request) {
  				if (set->ops->init_request(set->driver_data,
  						tags->rqs[i], hctx_idx, i,

  						set->numa_node)) {
  					tags->rqs[i] = NULL;

  					goto fail;

  				}

  			}

  			p += rq_size;
  			i++;
  		}
  	}

  	return tags;

  fail:

  	blk_mq_free_rq_map(set, tags, hctx_idx);
  	return NULL;

  }

  /*
   * 'cpu' is going away. splice any existing rq_list entries from this
   * software queue to the hw queue dispatch list, and ensure that it
   * gets run.
   */

  static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)

  {

  	struct blk_mq_hw_ctx *hctx;

  	struct blk_mq_ctx *ctx;
  	LIST_HEAD(tmp);

  	hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);

  	ctx = __blk_mq_get_ctx(hctx->queue, cpu);

  
  	spin_lock(&ctx->lock);
  	if (!list_empty(&ctx->rq_list)) {
  		list_splice_init(&ctx->rq_list, &tmp);
  		blk_mq_hctx_clear_pending(hctx, ctx);
  	}
  	spin_unlock(&ctx->lock);
  
  	if (list_empty(&tmp))

  		return 0;

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

  
  	blk_mq_run_hw_queue(hctx, true);

  	return 0;

  }

  static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)

  {

  	cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
  					    &hctx->cpuhp_dead);

  }

  /* hctx->ctxs will be freed in queue's release handler */

  static void blk_mq_exit_hctx(struct request_queue *q,
  		struct blk_mq_tag_set *set,
  		struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
  {

  	unsigned flush_start_tag = set->queue_depth;

  	blk_mq_tag_idle(hctx);

  	if (set->ops->exit_request)
  		set->ops->exit_request(set->driver_data,
  				       hctx->fq->flush_rq, hctx_idx,
  				       flush_start_tag + hctx_idx);

  	if (set->ops->exit_hctx)
  		set->ops->exit_hctx(hctx, hctx_idx);

  	blk_mq_remove_cpuhp(hctx);

  	blk_free_flush_queue(hctx->fq);

  	sbitmap_free(&hctx->ctx_map);

  }

  static void blk_mq_exit_hw_queues(struct request_queue *q,
  		struct blk_mq_tag_set *set, int nr_queue)
  {
  	struct blk_mq_hw_ctx *hctx;
  	unsigned int i;
  
  	queue_for_each_hw_ctx(q, hctx, i) {
  		if (i == nr_queue)
  			break;

  		blk_mq_exit_hctx(q, set, hctx, i);

  	}

  }
  
  static void blk_mq_free_hw_queues(struct request_queue *q,
  		struct blk_mq_tag_set *set)
  {
  	struct blk_mq_hw_ctx *hctx;
  	unsigned int i;

  	queue_for_each_hw_ctx(q, hctx, i)

  		free_cpumask_var(hctx->cpumask);

  }

  static int blk_mq_init_hctx(struct request_queue *q,
  		struct blk_mq_tag_set *set,
  		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)

  {

  	int node;

  	unsigned flush_start_tag = set->queue_depth;

  
  	node = hctx->numa_node;
  	if (node == NUMA_NO_NODE)
  		node = hctx->numa_node = set->numa_node;

  	INIT_WORK(&hctx->run_work, blk_mq_run_work_fn);

  	INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn);
  	spin_lock_init(&hctx->lock);
  	INIT_LIST_HEAD(&hctx->dispatch);
  	hctx->queue = q;
  	hctx->queue_num = hctx_idx;

  	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;

  	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);

  
  	hctx->tags = set->tags[hctx_idx];

  
  	/*

  	 * Allocate space for all possible cpus to avoid allocation at
  	 * runtime

  	 */

  	hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *),
  					GFP_KERNEL, node);
  	if (!hctx->ctxs)
  		goto unregister_cpu_notifier;

  	if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), GFP_KERNEL,
  			      node))

  		goto free_ctxs;

  	hctx->nr_ctx = 0;

  	if (set->ops->init_hctx &&
  	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
  		goto free_bitmap;

  	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size);
  	if (!hctx->fq)
  		goto exit_hctx;

  	if (set->ops->init_request &&
  	    set->ops->init_request(set->driver_data,
  				   hctx->fq->flush_rq, hctx_idx,
  				   flush_start_tag + hctx_idx, node))
  		goto free_fq;