/*

   * Copyright (C) 1991, 1992 Linus Torvalds
   * Copyright (C) 1994,      Karl Keyte: Added support for disk statistics
   * Elevator latency, (C) 2000  Andrea Arcangeli <andrea@suse.de> SuSE
   * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de>

   * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au>
   *	-  July2000

   * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001
   */
  
  /*
   * This handles all read/write requests to block devices
   */

  #include <linux/kernel.h>
  #include <linux/module.h>
  #include <linux/backing-dev.h>
  #include <linux/bio.h>
  #include <linux/blkdev.h>

  #include <linux/blk-mq.h>

  #include <linux/highmem.h>
  #include <linux/mm.h>
  #include <linux/kernel_stat.h>
  #include <linux/string.h>
  #include <linux/init.h>

  #include <linux/completion.h>
  #include <linux/slab.h>
  #include <linux/swap.h>
  #include <linux/writeback.h>

  #include <linux/task_io_accounting_ops.h>

  #include <linux/fault-inject.h>

  #include <linux/list_sort.h>

  #include <linux/delay.h>

  #include <linux/ratelimit.h>

  #include <linux/pm_runtime.h>

  #include <linux/blk-cgroup.h>

  #include <linux/debugfs.h>

  
  #define CREATE_TRACE_POINTS
  #include <trace/events/block.h>

  #include "blk.h"

  #include "blk-mq.h"

  #include "blk-mq-sched.h"

  #include "blk-wbt.h"

  #ifdef CONFIG_DEBUG_FS
  struct dentry *blk_debugfs_root;
  #endif

  EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);

  EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);

  EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);

  EXPORT_TRACEPOINT_SYMBOL_GPL(block_split);

  EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);

  DEFINE_IDA(blk_queue_ida);

  /*
   * For the allocated request tables
   */

  struct kmem_cache *request_cachep;

  
  /*
   * For queue allocation
   */

  struct kmem_cache *blk_requestq_cachep;

  
  /*

   * Controlling structure to kblockd
   */

  static struct workqueue_struct *kblockd_workqueue;

  static void blk_clear_congested(struct request_list *rl, int sync)
  {

  #ifdef CONFIG_CGROUP_WRITEBACK
  	clear_wb_congested(rl->blkg->wb_congested, sync);
  #else

  	/*
  	 * If !CGROUP_WRITEBACK, all blkg's map to bdi->wb and we shouldn't
  	 * flip its congestion state for events on other blkcgs.
  	 */
  	if (rl == &rl->q->root_rl)

  		clear_wb_congested(rl->q->backing_dev_info->wb.congested, sync);

  #endif
  }
  
  static void blk_set_congested(struct request_list *rl, int sync)
  {

  #ifdef CONFIG_CGROUP_WRITEBACK
  	set_wb_congested(rl->blkg->wb_congested, sync);
  #else

  	/* see blk_clear_congested() */
  	if (rl == &rl->q->root_rl)

  		set_wb_congested(rl->q->backing_dev_info->wb.congested, sync);

  #endif
  }

  void blk_queue_congestion_threshold(struct request_queue *q)

  {
  	int nr;
  
  	nr = q->nr_requests - (q->nr_requests / 8) + 1;
  	if (nr > q->nr_requests)
  		nr = q->nr_requests;
  	q->nr_congestion_on = nr;
  
  	nr = q->nr_requests - (q->nr_requests / 8) - (q->nr_requests / 16) - 1;
  	if (nr < 1)
  		nr = 1;
  	q->nr_congestion_off = nr;
  }

  void blk_rq_init(struct request_queue *q, struct request *rq)

  {

  	memset(rq, 0, sizeof(*rq));

  	INIT_LIST_HEAD(&rq->queuelist);

  	INIT_LIST_HEAD(&rq->timeout_list);

  	rq->cpu = -1;

  	rq->q = q;

  	rq->__sector = (sector_t) -1;

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

  	rq->tag = -1;

  	rq->internal_tag = -1;

  	rq->start_time = jiffies;

  	set_start_time_ns(rq);

  	rq->part = NULL;

  }

  EXPORT_SYMBOL(blk_rq_init);

  static const struct {
  	int		errno;
  	const char	*name;
  } blk_errors[] = {
  	[BLK_STS_OK]		= { 0,		"" },
  	[BLK_STS_NOTSUPP]	= { -EOPNOTSUPP, "operation not supported" },
  	[BLK_STS_TIMEOUT]	= { -ETIMEDOUT,	"timeout" },
  	[BLK_STS_NOSPC]		= { -ENOSPC,	"critical space allocation" },
  	[BLK_STS_TRANSPORT]	= { -ENOLINK,	"recoverable transport" },
  	[BLK_STS_TARGET]	= { -EREMOTEIO,	"critical target" },
  	[BLK_STS_NEXUS]		= { -EBADE,	"critical nexus" },
  	[BLK_STS_MEDIUM]	= { -ENODATA,	"critical medium" },
  	[BLK_STS_PROTECTION]	= { -EILSEQ,	"protection" },
  	[BLK_STS_RESOURCE]	= { -ENOMEM,	"kernel resource" },

  	[BLK_STS_AGAIN]		= { -EAGAIN,	"nonblocking retry" },

  	/* device mapper special case, should not leak out: */
  	[BLK_STS_DM_REQUEUE]	= { -EREMCHG, "dm internal retry" },

  	/* everything else not covered above: */
  	[BLK_STS_IOERR]		= { -EIO,	"I/O" },
  };
  
  blk_status_t errno_to_blk_status(int errno)
  {
  	int i;
  
  	for (i = 0; i < ARRAY_SIZE(blk_errors); i++) {
  		if (blk_errors[i].errno == errno)
  			return (__force blk_status_t)i;
  	}
  
  	return BLK_STS_IOERR;
  }
  EXPORT_SYMBOL_GPL(errno_to_blk_status);
  
  int blk_status_to_errno(blk_status_t status)
  {
  	int idx = (__force int)status;

  	if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))

  		return -EIO;
  	return blk_errors[idx].errno;
  }
  EXPORT_SYMBOL_GPL(blk_status_to_errno);
  
  static void print_req_error(struct request *req, blk_status_t status)
  {
  	int idx = (__force int)status;

  	if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))

  		return;
  
  	printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu
  ",
  			   __func__, blk_errors[idx].name, req->rq_disk ?
  			   req->rq_disk->disk_name : "?",
  			   (unsigned long long)blk_rq_pos(req));
  }

  static void req_bio_endio(struct request *rq, struct bio *bio,

  			  unsigned int nbytes, blk_status_t error)

  {

  	if (error)

  		bio->bi_status = error;

  	if (unlikely(rq->rq_flags & RQF_QUIET))

  		bio_set_flag(bio, BIO_QUIET);

  	bio_advance(bio, nbytes);

  	/* don't actually finish bio if it's part of flush sequence */

  	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))

  		bio_endio(bio);

  }

  void blk_dump_rq_flags(struct request *rq, char *msg)
  {

  	printk(KERN_INFO "%s: dev %s: flags=%llx
  ", msg,
  		rq->rq_disk ? rq->rq_disk->disk_name : "?",

  		(unsigned long long) rq->cmd_flags);

  	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u
  ",
  	       (unsigned long long)blk_rq_pos(rq),
  	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));

  	printk(KERN_INFO "  bio %p, biotail %p, len %u
  ",
  	       rq->bio, rq->biotail, blk_rq_bytes(rq));

  }

  EXPORT_SYMBOL(blk_dump_rq_flags);

  static void blk_delay_work(struct work_struct *work)

  {

  	struct request_queue *q;

  	q = container_of(work, struct request_queue, delay_work.work);
  	spin_lock_irq(q->queue_lock);

  	__blk_run_queue(q);

  	spin_unlock_irq(q->queue_lock);

  }

  
  /**

   * blk_delay_queue - restart queueing after defined interval
   * @q:		The &struct request_queue in question
   * @msecs:	Delay in msecs

   *
   * Description:

   *   Sometimes queueing needs to be postponed for a little while, to allow
   *   resources to come back. This function will make sure that queueing is

   *   restarted around the specified time.

   */
  void blk_delay_queue(struct request_queue *q, unsigned long msecs)

  {

  	lockdep_assert_held(q->queue_lock);

  	WARN_ON_ONCE(q->mq_ops);

  	if (likely(!blk_queue_dead(q)))
  		queue_delayed_work(kblockd_workqueue, &q->delay_work,
  				   msecs_to_jiffies(msecs));

  }

  EXPORT_SYMBOL(blk_delay_queue);

  /**

   * blk_start_queue_async - asynchronously restart a previously stopped queue
   * @q:    The &struct request_queue in question
   *
   * Description:
   *   blk_start_queue_async() will clear the stop flag on the queue, and
   *   ensure that the request_fn for the queue is run from an async
   *   context.
   **/
  void blk_start_queue_async(struct request_queue *q)
  {

  	lockdep_assert_held(q->queue_lock);

  	WARN_ON_ONCE(q->mq_ops);

  	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
  	blk_run_queue_async(q);
  }
  EXPORT_SYMBOL(blk_start_queue_async);
  
  /**

   * blk_start_queue - restart a previously stopped queue

   * @q:    The &struct request_queue in question

   *
   * Description:
   *   blk_start_queue() will clear the stop flag on the queue, and call
   *   the request_fn for the queue if it was in a stopped state when

   *   entered. Also see blk_stop_queue().

   **/

  void blk_start_queue(struct request_queue *q)

  {

  	lockdep_assert_held(q->queue_lock);

  	WARN_ON(!in_interrupt() && !irqs_disabled());

  	WARN_ON_ONCE(q->mq_ops);

  	queue_flag_clear(QUEUE_FLAG_STOPPED, q);

  	__blk_run_queue(q);

  }

  EXPORT_SYMBOL(blk_start_queue);
  
  /**
   * blk_stop_queue - stop a queue

   * @q:    The &struct request_queue in question

   *
   * Description:
   *   The Linux block layer assumes that a block driver will consume all
   *   entries on the request queue when the request_fn strategy is called.
   *   Often this will not happen, because of hardware limitations (queue
   *   depth settings). If a device driver gets a 'queue full' response,
   *   or if it simply chooses not to queue more I/O at one point, it can
   *   call this function to prevent the request_fn from being called until
   *   the driver has signalled it's ready to go again. This happens by calling

   *   blk_start_queue() to restart queue operations.

   **/

  void blk_stop_queue(struct request_queue *q)

  {

  	lockdep_assert_held(q->queue_lock);

  	WARN_ON_ONCE(q->mq_ops);

  	cancel_delayed_work(&q->delay_work);

  	queue_flag_set(QUEUE_FLAG_STOPPED, q);

  }
  EXPORT_SYMBOL(blk_stop_queue);
  
  /**
   * blk_sync_queue - cancel any pending callbacks on a queue
   * @q: the queue
   *
   * Description:
   *     The block layer may perform asynchronous callback activity
   *     on a queue, such as calling the unplug function after a timeout.
   *     A block device may call blk_sync_queue to ensure that any
   *     such activity is cancelled, thus allowing it to release resources

   *     that the callbacks might use. The caller must already have made sure

   *     that its ->make_request_fn will not re-add plugging prior to calling
   *     this function.
   *

   *     This function does not cancel any asynchronous activity arising

   *     out of elevator or throttling code. That would require elevator_exit()

   *     and blkcg_exit_queue() to be called with queue lock initialized.

   *

   */
  void blk_sync_queue(struct request_queue *q)
  {

  	del_timer_sync(&q->timeout);

  	cancel_work_sync(&q->timeout_work);

  
  	if (q->mq_ops) {
  		struct blk_mq_hw_ctx *hctx;
  		int i;

  		cancel_delayed_work_sync(&q->requeue_work);

  		queue_for_each_hw_ctx(q, hctx, i)

  			cancel_delayed_work_sync(&hctx->run_work);

  	} else {
  		cancel_delayed_work_sync(&q->delay_work);
  	}

  }
  EXPORT_SYMBOL(blk_sync_queue);
  
  /**

   * __blk_run_queue_uncond - run a queue whether or not it has been stopped
   * @q:	The queue to run
   *
   * Description:
   *    Invoke request handling on a queue if there are any pending requests.
   *    May be used to restart request handling after a request has completed.
   *    This variant runs the queue whether or not the queue has been
   *    stopped. Must be called with the queue lock held and interrupts
   *    disabled. See also @blk_run_queue.
   */
  inline void __blk_run_queue_uncond(struct request_queue *q)
  {

  	lockdep_assert_held(q->queue_lock);

  	WARN_ON_ONCE(q->mq_ops);

  	if (unlikely(blk_queue_dead(q)))
  		return;

  	/*
  	 * Some request_fn implementations, e.g. scsi_request_fn(), unlock
  	 * the queue lock internally. As a result multiple threads may be
  	 * running such a request function concurrently. Keep track of the
  	 * number of active request_fn invocations such that blk_drain_queue()
  	 * can wait until all these request_fn calls have finished.
  	 */
  	q->request_fn_active++;

  	q->request_fn(q);

  	q->request_fn_active--;

  }

  EXPORT_SYMBOL_GPL(__blk_run_queue_uncond);

  
  /**

   * __blk_run_queue - run a single device queue

   * @q:	The queue to run

   *
   * Description:

   *    See @blk_run_queue.

   */

  void __blk_run_queue(struct request_queue *q)

  {

  	lockdep_assert_held(q->queue_lock);

  	WARN_ON_ONCE(q->mq_ops);

  	if (unlikely(blk_queue_stopped(q)))
  		return;

  	__blk_run_queue_uncond(q);

  }
  EXPORT_SYMBOL(__blk_run_queue);

  /**

   * blk_run_queue_async - run a single device queue in workqueue context
   * @q:	The queue to run
   *
   * Description:
   *    Tells kblockd to perform the equivalent of @blk_run_queue on behalf

   *    of us.
   *
   * Note:
   *    Since it is not allowed to run q->delay_work after blk_cleanup_queue()
   *    has canceled q->delay_work, callers must hold the queue lock to avoid
   *    race conditions between blk_cleanup_queue() and blk_run_queue_async().

   */
  void blk_run_queue_async(struct request_queue *q)
  {

  	lockdep_assert_held(q->queue_lock);

  	WARN_ON_ONCE(q->mq_ops);

  	if (likely(!blk_queue_stopped(q) && !blk_queue_dead(q)))

  		mod_delayed_work(kblockd_workqueue, &q->delay_work, 0);

  }

  EXPORT_SYMBOL(blk_run_queue_async);

  
  /**

   * blk_run_queue - run a single device queue
   * @q: The queue to run

   *
   * Description:
   *    Invoke request handling on this queue, if it has pending work to do.

   *    May be used to restart queueing when a request has completed.

   */
  void blk_run_queue(struct request_queue *q)
  {
  	unsigned long flags;

  	WARN_ON_ONCE(q->mq_ops);

  	spin_lock_irqsave(q->queue_lock, flags);

  	__blk_run_queue(q);

  	spin_unlock_irqrestore(q->queue_lock, flags);
  }
  EXPORT_SYMBOL(blk_run_queue);

  void blk_put_queue(struct request_queue *q)

  {
  	kobject_put(&q->kobj);
  }

  EXPORT_SYMBOL(blk_put_queue);

  /**

   * __blk_drain_queue - drain requests from request_queue

   * @q: queue to drain

   * @drain_all: whether to drain all requests or only the ones w/ ELVPRIV

   *

   * Drain requests from @q.  If @drain_all is set, all requests are drained.
   * If not, only ELVPRIV requests are drained.  The caller is responsible
   * for ensuring that no new requests which need to be drained are queued.

   */

  static void __blk_drain_queue(struct request_queue *q, bool drain_all)
  	__releases(q->queue_lock)
  	__acquires(q->queue_lock)

  {

  	int i;

  	lockdep_assert_held(q->queue_lock);

  	WARN_ON_ONCE(q->mq_ops);

  	while (true) {

  		bool drain = false;

  		/*
  		 * The caller might be trying to drain @q before its
  		 * elevator is initialized.
  		 */
  		if (q->elevator)
  			elv_drain_elevator(q);

  		blkcg_drain_queue(q);

  		/*
  		 * This function might be called on a queue which failed

  		 * driver init after queue creation or is not yet fully
  		 * active yet.  Some drivers (e.g. fd and loop) get unhappy
  		 * in such cases.  Kick queue iff dispatch queue has
  		 * something on it and @q has request_fn set.

  		 */

  		if (!list_empty(&q->queue_head) && q->request_fn)

  			__blk_run_queue(q);

  		drain |= q->nr_rqs_elvpriv;

  		drain |= q->request_fn_active;

  
  		/*
  		 * Unfortunately, requests are queued at and tracked from
  		 * multiple places and there's no single counter which can
  		 * be drained.  Check all the queues and counters.
  		 */
  		if (drain_all) {

  			struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);

  			drain |= !list_empty(&q->queue_head);
  			for (i = 0; i < 2; i++) {

  				drain |= q->nr_rqs[i];

  				drain |= q->in_flight[i];

  				if (fq)
  				    drain |= !list_empty(&fq->flush_queue[i]);

  			}
  		}

  		if (!drain)

  			break;

  
  		spin_unlock_irq(q->queue_lock);

  		msleep(10);

  
  		spin_lock_irq(q->queue_lock);

  	}

  
  	/*
  	 * With queue marked dead, any woken up waiter will fail the
  	 * allocation path, so the wakeup chaining is lost and we're
  	 * left with hung waiters. We need to wake up those waiters.
  	 */
  	if (q->request_fn) {

  		struct request_list *rl;

  		blk_queue_for_each_rl(rl, q)
  			for (i = 0; i < ARRAY_SIZE(rl->wait); i++)
  				wake_up_all(&rl->wait[i]);

  	}

  }

  void blk_drain_queue(struct request_queue *q)
  {
  	spin_lock_irq(q->queue_lock);
  	__blk_drain_queue(q, true);
  	spin_unlock_irq(q->queue_lock);
  }

  /**

   * blk_queue_bypass_start - enter queue bypass mode
   * @q: queue of interest
   *
   * In bypass mode, only the dispatch FIFO queue of @q is used.  This
   * function makes @q enter bypass mode and drains all requests which were

   * throttled or issued before.  On return, it's guaranteed that no request

   * is being throttled or has ELVPRIV set and blk_queue_bypass() %true
   * inside queue or RCU read lock.

   */
  void blk_queue_bypass_start(struct request_queue *q)
  {

  	WARN_ON_ONCE(q->mq_ops);

  	spin_lock_irq(q->queue_lock);

  	q->bypass_depth++;

  	queue_flag_set(QUEUE_FLAG_BYPASS, q);
  	spin_unlock_irq(q->queue_lock);

  	/*
  	 * Queues start drained.  Skip actual draining till init is
  	 * complete.  This avoids lenghty delays during queue init which
  	 * can happen many times during boot.
  	 */
  	if (blk_queue_init_done(q)) {

  		spin_lock_irq(q->queue_lock);
  		__blk_drain_queue(q, false);
  		spin_unlock_irq(q->queue_lock);

  		/* ensure blk_queue_bypass() is %true inside RCU read lock */
  		synchronize_rcu();
  	}

  }
  EXPORT_SYMBOL_GPL(blk_queue_bypass_start);
  
  /**
   * blk_queue_bypass_end - leave queue bypass mode
   * @q: queue of interest
   *
   * Leave bypass mode and restore the normal queueing behavior.

   *
   * Note: although blk_queue_bypass_start() is only called for blk-sq queues,
   * this function is called for both blk-sq and blk-mq queues.

   */
  void blk_queue_bypass_end(struct request_queue *q)
  {
  	spin_lock_irq(q->queue_lock);
  	if (!--q->bypass_depth)
  		queue_flag_clear(QUEUE_FLAG_BYPASS, q);
  	WARN_ON_ONCE(q->bypass_depth < 0);
  	spin_unlock_irq(q->queue_lock);
  }
  EXPORT_SYMBOL_GPL(blk_queue_bypass_end);

  void blk_set_queue_dying(struct request_queue *q)
  {

  	spin_lock_irq(q->queue_lock);
  	queue_flag_set(QUEUE_FLAG_DYING, q);
  	spin_unlock_irq(q->queue_lock);

  	/*
  	 * When queue DYING flag is set, we need to block new req
  	 * entering queue, so we call blk_freeze_queue_start() to
  	 * prevent I/O from crossing blk_queue_enter().
  	 */
  	blk_freeze_queue_start(q);

  	if (q->mq_ops)
  		blk_mq_wake_waiters(q);
  	else {
  		struct request_list *rl;

  		spin_lock_irq(q->queue_lock);

  		blk_queue_for_each_rl(rl, q) {
  			if (rl->rq_pool) {

  				wake_up_all(&rl->wait[BLK_RW_SYNC]);
  				wake_up_all(&rl->wait[BLK_RW_ASYNC]);

  			}
  		}

  		spin_unlock_irq(q->queue_lock);

  	}
  }
  EXPORT_SYMBOL_GPL(blk_set_queue_dying);

  /**

   * blk_cleanup_queue - shutdown a request queue
   * @q: request queue to shutdown
   *

   * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and
   * put it.  All future requests will be failed immediately with -ENODEV.

   */

  void blk_cleanup_queue(struct request_queue *q)

  {

  	spinlock_t *lock = q->queue_lock;

  	/* mark @q DYING, no new request or merges will be allowed afterwards */

  	mutex_lock(&q->sysfs_lock);

  	blk_set_queue_dying(q);

  	spin_lock_irq(lock);

  	/*

  	 * A dying queue is permanently in bypass mode till released.  Note

  	 * that, unlike blk_queue_bypass_start(), we aren't performing
  	 * synchronize_rcu() after entering bypass mode to avoid the delay
  	 * as some drivers create and destroy a lot of queues while
  	 * probing.  This is still safe because blk_release_queue() will be
  	 * called only after the queue refcnt drops to zero and nothing,
  	 * RCU or not, would be traversing the queue by then.
  	 */

  	q->bypass_depth++;
  	queue_flag_set(QUEUE_FLAG_BYPASS, q);

  	queue_flag_set(QUEUE_FLAG_NOMERGES, q);
  	queue_flag_set(QUEUE_FLAG_NOXMERGES, q);

  	queue_flag_set(QUEUE_FLAG_DYING, q);

  	spin_unlock_irq(lock);
  	mutex_unlock(&q->sysfs_lock);

  	/*
  	 * Drain all requests queued before DYING marking. Set DEAD flag to
  	 * prevent that q->request_fn() gets invoked after draining finished.
  	 */

  	blk_freeze_queue(q);

  	spin_lock_irq(lock);

  	queue_flag_set(QUEUE_FLAG_DEAD, q);

  	spin_unlock_irq(lock);

  	/*
  	 * make sure all in-progress dispatch are completed because
  	 * blk_freeze_queue() can only complete all requests, and
  	 * dispatch may still be in-progress since we dispatch requests

  	 * from more than one contexts.
  	 *
  	 * No need to quiesce queue if it isn't initialized yet since
  	 * blk_freeze_queue() should be enough for cases of passthrough
  	 * request.

  	 */

  	if (q->mq_ops && blk_queue_init_done(q))

  		blk_mq_quiesce_queue(q);

  	/* for synchronous bio-based driver finish in-flight integrity i/o */
  	blk_flush_integrity();

  	/* @q won't process any more request, flush async actions */

  	del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer);

  	blk_sync_queue(q);

  	if (q->mq_ops)
  		blk_mq_free_queue(q);

  	percpu_ref_exit(&q->q_usage_counter);

  	spin_lock_irq(lock);
  	if (q->queue_lock != &q->__queue_lock)
  		q->queue_lock = &q->__queue_lock;
  	spin_unlock_irq(lock);

  	/* @q is and will stay empty, shutdown and put */

  	blk_put_queue(q);
  }

  EXPORT_SYMBOL(blk_cleanup_queue);

  /* Allocate memory local to the request queue */

  static void *alloc_request_simple(gfp_t gfp_mask, void *data)

  {

  	struct request_queue *q = data;
  
  	return kmem_cache_alloc_node(request_cachep, gfp_mask, q->node);

  }

  static void free_request_simple(void *element, void *data)

  {
  	kmem_cache_free(request_cachep, element);
  }

  static void *alloc_request_size(gfp_t gfp_mask, void *data)
  {
  	struct request_queue *q = data;
  	struct request *rq;
  
  	rq = kmalloc_node(sizeof(struct request) + q->cmd_size, gfp_mask,
  			q->node);
  	if (rq && q->init_rq_fn && q->init_rq_fn(q, rq, gfp_mask) < 0) {
  		kfree(rq);
  		rq = NULL;
  	}
  	return rq;
  }
  
  static void free_request_size(void *element, void *data)
  {
  	struct request_queue *q = data;
  
  	if (q->exit_rq_fn)
  		q->exit_rq_fn(q, element);
  	kfree(element);
  }

  int blk_init_rl(struct request_list *rl, struct request_queue *q,
  		gfp_t gfp_mask)

  {

  	if (unlikely(rl->rq_pool))
  		return 0;

  	rl->q = q;

  	rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
  	rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;

  	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
  	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);

  	if (q->cmd_size) {
  		rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ,
  				alloc_request_size, free_request_size,
  				q, gfp_mask, q->node);
  	} else {
  		rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ,
  				alloc_request_simple, free_request_simple,
  				q, gfp_mask, q->node);
  	}

  	if (!rl->rq_pool)
  		return -ENOMEM;

  	if (rl != &q->root_rl)
  		WARN_ON_ONCE(!blk_get_queue(q));

  	return 0;
  }

  void blk_exit_rl(struct request_queue *q, struct request_list *rl)

  {

  	if (rl->rq_pool) {

  		mempool_destroy(rl->rq_pool);

  		if (rl != &q->root_rl)
  			blk_put_queue(q);
  	}

  }

  struct request_queue *blk_alloc_queue(gfp_t gfp_mask)

  {

  	return blk_alloc_queue_node(gfp_mask, NUMA_NO_NODE);

  }
  EXPORT_SYMBOL(blk_alloc_queue);

  int blk_queue_enter(struct request_queue *q, bool nowait)

  {
  	while (true) {

  
  		if (percpu_ref_tryget_live(&q->q_usage_counter))
  			return 0;

  		if (nowait)

  			return -EBUSY;

  		/*

  		 * read pair of barrier in blk_freeze_queue_start(),

  		 * we need to order reading __PERCPU_REF_DEAD flag of

  		 * .q_usage_counter and reading .mq_freeze_depth or
  		 * queue dying flag, otherwise the following wait may
  		 * never return if the two reads are reordered.

  		 */
  		smp_rmb();

  		wait_event(q->mq_freeze_wq,
  			   !atomic_read(&q->mq_freeze_depth) ||
  			   blk_queue_dying(q));

  		if (blk_queue_dying(q))
  			return -ENODEV;

  	}
  }
  
  void blk_queue_exit(struct request_queue *q)
  {
  	percpu_ref_put(&q->q_usage_counter);
  }
  
  static void blk_queue_usage_counter_release(struct percpu_ref *ref)
  {
  	struct request_queue *q =
  		container_of(ref, struct request_queue, q_usage_counter);
  
  	wake_up_all(&q->mq_freeze_wq);
  }

  static void blk_rq_timed_out_timer(unsigned long data)
  {
  	struct request_queue *q = (struct request_queue *)data;
  
  	kblockd_schedule_work(&q->timeout_work);
  }

  struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)

  {

  	struct request_queue *q;

  	q = kmem_cache_alloc_node(blk_requestq_cachep,

  				gfp_mask | __GFP_ZERO, node_id);

  	if (!q)
  		return NULL;

  	q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);

  	if (q->id < 0)

  		goto fail_q;

  	q->bio_split = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);

  	if (!q->bio_split)
  		goto fail_id;

  	q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id);
  	if (!q->backing_dev_info)
  		goto fail_split;

  	q->stats = blk_alloc_queue_stats();
  	if (!q->stats)
  		goto fail_stats;

  	q->backing_dev_info->ra_pages =

  			(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;

  	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
  	q->backing_dev_info->name = "block";

  	q->node = node_id;

  	setup_timer(&q->backing_dev_info->laptop_mode_wb_timer,

  		    laptop_mode_timer_fn, (unsigned long) q);

  	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);

  	INIT_WORK(&q->timeout_work, NULL);

  	INIT_LIST_HEAD(&q->queue_head);

  	INIT_LIST_HEAD(&q->timeout_list);

  	INIT_LIST_HEAD(&q->icq_list);

  #ifdef CONFIG_BLK_CGROUP

  	INIT_LIST_HEAD(&q->blkg_list);

  #endif

  	INIT_DELAYED_WORK(&q->delay_work, blk_delay_work);

  	kobject_init(&q->kobj, &blk_queue_ktype);

  #ifdef CONFIG_BLK_DEV_IO_TRACE
  	mutex_init(&q->blk_trace_mutex);
  #endif

  	mutex_init(&q->sysfs_lock);

  	spin_lock_init(&q->__queue_lock);

  	/*
  	 * By default initialize queue_lock to internal lock and driver can
  	 * override it later if need be.
  	 */
  	q->queue_lock = &q->__queue_lock;

  	/*
  	 * A queue starts its life with bypass turned on to avoid
  	 * unnecessary bypass on/off overhead and nasty surprises during

  	 * init.  The initial bypass will be finished when the queue is
  	 * registered by blk_register_queue().

  	 */
  	q->bypass_depth = 1;
  	__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);

  	init_waitqueue_head(&q->mq_freeze_wq);

  	/*
  	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
  	 * See blk_register_queue() for details.
  	 */
  	if (percpu_ref_init(&q->q_usage_counter,
  				blk_queue_usage_counter_release,
  				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))

  		goto fail_bdi;

  	if (blkcg_init_queue(q))
  		goto fail_ref;

  	return q;

  fail_ref:
  	percpu_ref_exit(&q->q_usage_counter);

  fail_bdi:

  	blk_free_queue_stats(q->stats);
  fail_stats:

  	bdi_put(q->backing_dev_info);

  fail_split:
  	bioset_free(q->bio_split);

  fail_id:
  	ida_simple_remove(&blk_queue_ida, q->id);
  fail_q:
  	kmem_cache_free(blk_requestq_cachep, q);
  	return NULL;

  }

  EXPORT_SYMBOL(blk_alloc_queue_node);

  
  /**
   * blk_init_queue  - prepare a request queue for use with a block device
   * @rfn:  The function to be called to process requests that have been
   *        placed on the queue.
   * @lock: Request queue spin lock
   *
   * Description:
   *    If a block device wishes to use the standard request handling procedures,
   *    which sorts requests and coalesces adjacent requests, then it must
   *    call blk_init_queue().  The function @rfn will be called when there
   *    are requests on the queue that need to be processed.  If the device
   *    supports plugging, then @rfn may not be called immediately when requests
   *    are available on the queue, but may be called at some time later instead.
   *    Plugged queues are generally unplugged when a buffer belonging to one
   *    of the requests on the queue is needed, or due to memory pressure.
   *
   *    @rfn is not required, or even expected, to remove all requests off the
   *    queue, but only as many as it can handle at a time.  If it does leave
   *    requests on the queue, it is responsible for arranging that the requests
   *    get dealt with eventually.
   *
   *    The queue spin lock must be held while manipulating the requests on the

   *    request queue; this lock will be taken also from interrupt context, so irq
   *    disabling is needed for it.

   *

   *    Function returns a pointer to the initialized request queue, or %NULL if

   *    it didn't succeed.
   *
   * Note:
   *    blk_init_queue() must be paired with a blk_cleanup_queue() call
   *    when the block device is deactivated (such as at module unload).
   **/

  struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)

  {

  	return blk_init_queue_node(rfn, lock, NUMA_NO_NODE);

  }
  EXPORT_SYMBOL(blk_init_queue);

  struct request_queue *

  blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
  {

  	struct request_queue *q;

  	q = blk_alloc_queue_node(GFP_KERNEL, node_id);
  	if (!q)

  		return NULL;

  	q->request_fn = rfn;
  	if (lock)
  		q->queue_lock = lock;
  	if (blk_init_allocated_queue(q) < 0) {
  		blk_cleanup_queue(q);
  		return NULL;
  	}

  	return q;

  }
  EXPORT_SYMBOL(blk_init_queue_node);

  static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio);

  int blk_init_allocated_queue(struct request_queue *q)
  {

  	WARN_ON_ONCE(q->mq_ops);

  	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size);

  	if (!q->fq)

  		return -ENOMEM;

  	if (q->init_rq_fn && q->init_rq_fn(q, q->fq->flush_rq, GFP_KERNEL))
  		goto out_free_flush_queue;

  	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))

  		goto out_exit_flush_rq;

  	INIT_WORK(&q->timeout_work, blk_timeout_work);

  	q->queue_flags		|= QUEUE_FLAG_DEFAULT;

  	/*
  	 * This also sets hw/phys segments, boundary and size
  	 */

  	blk_queue_make_request(q, blk_queue_bio);

  	q->sg_reserved_size = INT_MAX;

  	/* Protect q->elevator from elevator_change */
  	mutex_lock(&q->sysfs_lock);

  	/* init elevator */

  	if (elevator_init(q, NULL)) {
  		mutex_unlock(&q->sysfs_lock);

  		goto out_exit_flush_rq;

  	}
  
  	mutex_unlock(&q->sysfs_lock);

  	return 0;

  out_exit_flush_rq:
  	if (q->exit_rq_fn)
  		q->exit_rq_fn(q, q->fq->flush_rq);
  out_free_flush_queue:

  	blk_free_flush_queue(q->fq);

  	q->fq = NULL;

  	return -ENOMEM;

  }

  EXPORT_SYMBOL(blk_init_allocated_queue);

  bool blk_get_queue(struct request_queue *q)

  {

  	if (likely(!blk_queue_dying(q))) {

  		__blk_get_queue(q);
  		return true;

  	}

  	return false;

  }

  EXPORT_SYMBOL(blk_get_queue);

  static inline void blk_free_request(struct request_list *rl, struct request *rq)

  {

  	if (rq->rq_flags & RQF_ELVPRIV) {

  		elv_put_request(rl->q, rq);

  		if (rq->elv.icq)

  			put_io_context(rq->elv.icq->ioc);

  	}

  	mempool_free(rq, rl->rq_pool);

  }

  /*
   * ioc_batching returns true if the ioc is a valid batching request and
   * should be given priority access to a request.
   */

  static inline int ioc_batching(struct request_queue *q, struct io_context *ioc)

  {
  	if (!ioc)
  		return 0;
  
  	/*
  	 * Make sure the process is able to allocate at least 1 request
  	 * even if the batch times out, otherwise we could theoretically
  	 * lose wakeups.
  	 */
  	return ioc->nr_batch_requests == q->nr_batching ||
  		(ioc->nr_batch_requests > 0
  		&& time_before(jiffies, ioc->last_waited + BLK_BATCH_TIME));
  }
  
  /*
   * ioc_set_batching sets ioc to be a new "batcher" if it is not one. This
   * will cause the process to be a "batcher" on all queues in the system. This
   * is the behaviour we want though - once it gets a wakeup it should be given
   * a nice run.
   */

  static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)

  {
  	if (!ioc || ioc_batching(q, ioc))
  		return;
  
  	ioc->nr_batch_requests = q->nr_batching;
  	ioc->last_waited = jiffies;
  }

  static void __freed_request(struct request_list *rl, int sync)

  {

  	struct request_queue *q = rl->q;

  	if (rl->count[sync] < queue_congestion_off_threshold(q))
  		blk_clear_congested(rl, sync);

  	if (rl->count[sync] + 1 <= q->nr_requests) {
  		if (waitqueue_active(&rl->wait[sync]))
  			wake_up(&rl->wait[sync]);

  		blk_clear_rl_full(rl, sync);

  	}
  }
  
  /*
   * A request has just been released.  Account for it, update the full and
   * congestion status, wake up any waiters.   Called under q->queue_lock.
   */

  static void freed_request(struct request_list *rl, bool sync,
  		req_flags_t rq_flags)

  {

  	struct request_queue *q = rl->q;

  	q->nr_rqs[sync]--;

  	rl->count[sync]--;

  	if (rq_flags & RQF_ELVPRIV)

  		q->nr_rqs_elvpriv--;

  	__freed_request(rl, sync);

  	if (unlikely(rl->starved[sync ^ 1]))

  		__freed_request(rl, sync ^ 1);

  }

  int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
  {
  	struct request_list *rl;

  	int on_thresh, off_thresh;

  	WARN_ON_ONCE(q->mq_ops);

  	spin_lock_irq(q->queue_lock);
  	q->nr_requests = nr;
  	blk_queue_congestion_threshold(q);

  	on_thresh = queue_congestion_on_threshold(q);
  	off_thresh = queue_congestion_off_threshold(q);

  	blk_queue_for_each_rl(rl, q) {
  		if (rl->count[BLK_RW_SYNC] >= on_thresh)
  			blk_set_congested(rl, BLK_RW_SYNC);
  		else if (rl->count[BLK_RW_SYNC] < off_thresh)
  			blk_clear_congested(rl, BLK_RW_SYNC);

  		if (rl->count[BLK_RW_ASYNC] >= on_thresh)
  			blk_set_congested(rl, BLK_RW_ASYNC);
  		else if (rl->count[BLK_RW_ASYNC] < off_thresh)
  			blk_clear_congested(rl, BLK_RW_ASYNC);

  		if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
  			blk_set_rl_full(rl, BLK_RW_SYNC);
  		} else {
  			blk_clear_rl_full(rl, BLK_RW_SYNC);
  			wake_up(&rl->wait[BLK_RW_SYNC]);
  		}
  
  		if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
  			blk_set_rl_full(rl, BLK_RW_ASYNC);
  		} else {
  			blk_clear_rl_full(rl, BLK_RW_ASYNC);
  			wake_up(&rl->wait[BLK_RW_ASYNC]);
  		}
  	}
  
  	spin_unlock_irq(q->queue_lock);
  	return 0;
  }

  /**

   * __get_request - get a free request

   * @rl: request list to allocate from

   * @op: operation and flags

   * @bio: bio to allocate request for (can be %NULL)
   * @gfp_mask: allocation mask
   *
   * Get a free request from @q.  This function may fail under memory
   * pressure or if @q is dead.
   *

   * Must be called with @q->queue_lock held and,

   * Returns ERR_PTR on failure, with @q->queue_lock held.
   * Returns request pointer on success, with @q->queue_lock *not held*.

   */

  static struct request *__get_request(struct request_list *rl, unsigned int op,
  		struct bio *bio, gfp_t gfp_mask)

  {

  	struct request_queue *q = rl->q;

  	struct request *rq;

  	struct elevator_type *et = q->elevator->type;
  	struct io_context *ioc = rq_ioc(bio);

  	struct io_cq *icq = NULL;

  	const bool is_sync = op_is_sync(op);

  	int may_queue;

  	req_flags_t rq_flags = RQF_ALLOCED;

  	lockdep_assert_held(q->queue_lock);

  	if (unlikely(blk_queue_dying(q)))

  		return ERR_PTR(-ENODEV);

  	may_queue = elv_may_queue(q, op);

  	if (may_queue == ELV_MQUEUE_NO)
  		goto rq_starved;

  	if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) {
  		if (rl->count[is_sync]+1 >= q->nr_requests) {

  			/*

  			 * The queue will fill after this allocation, so set
  			 * it as full, and mark this process as "batching".
  			 * This process will be allowed to complete a batch of
  			 * requests, others will be blocked.
  			 */

  			if (!blk_rl_full(rl, is_sync)) {

  				ioc_set_batching(q, ioc);

  				blk_set_rl_full(rl, is_sync);

  			} else {
  				if (may_queue != ELV_MQUEUE_MUST
  						&& !ioc_batching(q, ioc)) {
  					/*
  					 * The queue is full and the allocating
  					 * process is not a "batcher", and not
  					 * exempted by the IO scheduler
  					 */

  					return ERR_PTR(-ENOMEM);

  				}
  			}

  		}

  		blk_set_congested(rl, is_sync);

  	}

  	/*
  	 * Only allow batching queuers to allocate up to 50% over the defined
  	 * limit of requests, otherwise we could have thousands of requests
  	 * allocated with any setting of ->nr_requests
  	 */

  	if (rl->count[is_sync] >= (3 * q->nr_requests / 2))

  		return ERR_PTR(-ENOMEM);

  	q->nr_rqs[is_sync]++;

  	rl->count[is_sync]++;
  	rl->starved[is_sync] = 0;

  	/*
  	 * Decide whether the new request will be managed by elevator.  If

  	 * so, mark @rq_flags and increment elvpriv.  Non-zero elvpriv will

  	 * prevent the current elevator from being destroyed until the new
  	 * request is freed.  This guarantees icq's won't be destroyed and
  	 * makes creating new ones safe.
  	 *

  	 * Flush requests do not use the elevator so skip initialization.
  	 * This allows a request to share the flush and elevator data.
  	 *

  	 * Also, lookup icq while holding queue_lock.  If it doesn't exist,
  	 * it will be created after releasing queue_lock.
  	 */

  	if (!op_is_flush(op) && !blk_queue_bypass(q)) {

  		rq_flags |= RQF_ELVPRIV;

  		q->nr_rqs_elvpriv++;

  		if (et->icq_cache && ioc)
  			icq = ioc_lookup_icq(ioc, q);

  	}

  	if (blk_queue_io_stat(q))

  		rq_flags |= RQF_IO_STAT;

  	spin_unlock_irq(q->queue_lock);

  	/* allocate and init request */

  	rq = mempool_alloc(rl->rq_pool, gfp_mask);

  	if (!rq)

  		goto fail_alloc;

  	blk_rq_init(q, rq);

  	blk_rq_set_rl(rq, rl);

  	rq->cmd_flags = op;

  	rq->rq_flags = rq_flags;

  	/* init elvpriv */

  	if (rq_flags & RQF_ELVPRIV) {

  		if (unlikely(et->icq_cache && !icq)) {

  			if (ioc)
  				icq = ioc_create_icq(ioc, q, gfp_mask);

  			if (!icq)
  				goto fail_elvpriv;

  		}

  
  		rq->elv.icq = icq;
  		if (unlikely(elv_set_request(q, rq, bio, gfp_mask)))
  			goto fail_elvpriv;
  
  		/* @rq->elv.icq holds io_context until @rq is freed */

  		if (icq)
  			get_io_context(icq->ioc);
  	}

  out:

  	/*
  	 * ioc may be NULL here, and ioc_batching will be false. That's
  	 * OK, if the queue is under the request limit then requests need
  	 * not count toward the nr_batch_requests limit. There will always
  	 * be some limit enforced by BLK_BATCH_TIME.
  	 */

  	if (ioc_batching(q, ioc))
  		ioc->nr_batch_requests--;

  	trace_block_getrq(q, bio, op);

  	return rq;

  fail_elvpriv:
  	/*
  	 * elvpriv init failed.  ioc, icq and elvpriv aren't mempool backed
  	 * and may fail indefinitely under memory pressure and thus
  	 * shouldn't stall IO.  Treat this request as !elvpriv.  This will
  	 * disturb iosched and blkcg but weird is bettern than dead.
  	 */

  	printk_ratelimited(KERN_WARNING "%s: dev %s: request aux data allocation failed, iosched may be disturbed
  ",

  			   __func__, dev_name(q->backing_dev_info->dev));

  	rq->rq_flags &= ~RQF_ELVPRIV;

  	rq->elv.icq = NULL;
  
  	spin_lock_irq(q->queue_lock);

  	q->nr_rqs_elvpriv--;

  	spin_unlock_irq(q->queue_lock);
  	goto out;

  fail_alloc:
  	/*
  	 * Allocation failed presumably due to memory. Undo anything we
  	 * might have messed up.
  	 *
  	 * Allocating task should really be put onto the front of the wait
  	 * queue, but this is pretty rare.
  	 */
  	spin_lock_irq(q->queue_lock);

  	freed_request(rl, is_sync, rq_flags);

  
  	/*
  	 * in the very unlikely event that allocation failed and no
  	 * requests for this direction was pending, mark us starved so that
  	 * freeing of a request in the other direction will notice
  	 * us. another possible fix would be to split the rq mempool into
  	 * READ and WRITE
  	 */
  rq_starved:
  	if (unlikely(rl->count[is_sync] == 0))
  		rl->starved[is_sync] = 1;

  	return ERR_PTR(-ENOMEM);

  }

  /**

   * get_request - get a free request

   * @q: request_queue to allocate request from

   * @op: operation and flags

   * @bio: bio to allocate request for (can be %NULL)

   * @gfp_mask: allocation mask

   *

   * Get a free request from @q.  If %__GFP_DIRECT_RECLAIM is set in @gfp_mask,
   * this function keeps retrying under memory pressure and fails iff @q is dead.

   *

   * Must be called with @q->queue_lock held and,

   * Returns ERR_PTR on failure, with @q->queue_lock held.
   * Returns request pointer on success, with @q->queue_lock *not held*.

   */

  static struct request *get_request(struct request_queue *q, unsigned int op,
  		struct bio *bio, gfp_t gfp_mask)

  {

  	const bool is_sync = op_is_sync(op);

  	DEFINE_WAIT(wait);

  	struct request_list *rl;

  	struct request *rq;