blk-core.c

/*
 * 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/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>

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

#include "blk.h"

EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);

static int __make_request(struct request_queue *q, struct bio *bio);

/*
 * For the allocated request tables
 */
static 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 drive_stat_acct(struct request *rq, int new_io)
{
	struct hd_struct *part;
	int rw = rq_data_dir(rq);
	int cpu;

	if (!blk_do_io_stat(rq))
		return;

	cpu = part_stat_lock();

	if (!new_io) {
		part = rq->part;
		part_stat_inc(cpu, part, merges[rw]);
	} else {
		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
		if (!hd_struct_try_get(part)) {
			/*
			 * The partition is already being removed,
			 * the request will be accounted on the disk only
			 *
			 * We take a reference on disk->part0 although that
			 * partition will never be deleted, so we can treat
			 * it as any other partition.
			 */
			part = &rq->rq_disk->part0;
			hd_struct_get(part);
		}
		part_round_stats(cpu, part);
		part_inc_in_flight(part, rw);
		rq->part = part;
	}

	part_stat_unlock();
}

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;
}

/**
 * blk_get_backing_dev_info - get the address of a queue's backing_dev_info
 * @bdev:	device
 *
 * Locates the passed device's request queue and returns the address of its
 * backing_dev_info
 *
 * Will return NULL if the request queue cannot be located.
 */
struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
{
	struct backing_dev_info *ret = NULL;
	struct request_queue *q = bdev_get_queue(bdev);

	if (q)
		ret = &q->backing_dev_info;
	return ret;
}
EXPORT_SYMBOL(blk_get_backing_dev_info);

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->cmd = rq->__cmd;
	rq->cmd_len = BLK_MAX_CDB;
	rq->tag = -1;
	rq->ref_count = 1;
	rq->start_time = jiffies;
	set_start_time_ns(rq);
	rq->part = NULL;
}
EXPORT_SYMBOL(blk_rq_init);

static void req_bio_endio(struct request *rq, struct bio *bio,
			  unsigned int nbytes, int error)
{
	if (error)
		clear_bit(BIO_UPTODATE, &bio->bi_flags);
	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
		error = -EIO;

	if (unlikely(nbytes > bio->bi_size)) {
		printk(KERN_ERR "%s: want %u bytes done, %u left\n",
		       __func__, nbytes, bio->bi_size);
		nbytes = bio->bi_size;
	}

	if (unlikely(rq->cmd_flags & REQ_QUIET))
		set_bit(BIO_QUIET, &bio->bi_flags);

	bio->bi_size -= nbytes;
	bio->bi_sector += (nbytes >> 9);

	if (bio_integrity(bio))
		bio_integrity_advance(bio, nbytes);

	/* don't actually finish bio if it's part of flush sequence */
	if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
		bio_endio(bio, error);
}

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

	printk(KERN_INFO "%s: dev %s: type=%x, flags=%x\n", msg,
		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
		rq->cmd_flags);

	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
	       (unsigned long long)blk_rq_pos(rq),
	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
	printk(KERN_INFO "  bio %p, biotail %p, buffer %p, len %u\n",
	       rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));

	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
		printk(KERN_INFO "  cdb: ");
		for (bit = 0; bit < BLK_MAX_CDB; bit++)
			printk("%02x ", rq->cmd[bit]);
		printk("\n");
	}
}
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)
{
	queue_delayed_work(kblockd_workqueue, &q->delay_work,
				msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_delay_queue);

/**
 * 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(). Queue lock must be held.
 **/
void blk_start_queue(struct request_queue *q)
{
	WARN_ON(!irqs_disabled());

	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. Queue lock must be held.
 **/
void blk_stop_queue(struct request_queue *q)
{
	__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 elevaotor_exit()
 *     and blk_throtl_exit() to be called with queue lock initialized.
 *
 */
void blk_sync_queue(struct request_queue *q)
{
	del_timer_sync(&q->timeout);
	cancel_delayed_work_sync(&q->delay_work);
}
EXPORT_SYMBOL(blk_sync_queue);

/**
 * __blk_run_queue - run a single device queue
 * @q:	The queue to run
 *
 * Description:
 *    See @blk_run_queue. This variant must be called with the queue lock
 *    held and interrupts disabled.
 */
void __blk_run_queue(struct request_queue *q)
{
	if (unlikely(blk_queue_stopped(q)))
		return;

	q->request_fn(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.
 */
void blk_run_queue_async(struct request_queue *q)
{
	if (likely(!blk_queue_stopped(q))) {
		__cancel_delayed_work(&q->delay_work);
		queue_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;

	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);

/*
 * Note: If a driver supplied the queue lock, it is disconnected
 * by this function. The actual state of the lock doesn't matter
 * here as the request_queue isn't accessible after this point
 * (QUEUE_FLAG_DEAD is set) and no other requests will be queued.
 */
void blk_cleanup_queue(struct request_queue *q)
{
	/*
	 * We know we have process context here, so we can be a little
	 * cautious and ensure that pending block actions on this device
	 * are done before moving on. Going into this function, we should
	 * not have processes doing IO to this device.
	 */
	blk_sync_queue(q);

	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
	mutex_lock(&q->sysfs_lock);
	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
	mutex_unlock(&q->sysfs_lock);

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

	blk_put_queue(q);
}
EXPORT_SYMBOL(blk_cleanup_queue);

static int blk_init_free_list(struct request_queue *q)
{
	struct request_list *rl = &q->rq;

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

	rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
	rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
	rl->elvpriv = 0;
	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);

	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
				mempool_free_slab, request_cachep, q->node);

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

	return 0;
}

struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
{
	return blk_alloc_queue_node(gfp_mask, -1);
}
EXPORT_SYMBOL(blk_alloc_queue);

struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
	struct request_queue *q;
	int err;

	q = kmem_cache_alloc_node(blk_requestq_cachep,
				gfp_mask | __GFP_ZERO, node_id);
	if (!q)
		return NULL;

	q->backing_dev_info.ra_pages =
			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
	q->backing_dev_info.state = 0;
	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
	q->backing_dev_info.name = "block";

	err = bdi_init(&q->backing_dev_info);
	if (err) {
		kmem_cache_free(blk_requestq_cachep, q);
		return NULL;
	}

	if (blk_throtl_init(q)) {
		kmem_cache_free(blk_requestq_cachep, q);
		return NULL;
	}

	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_LIST_HEAD(&q->timeout_list);
	INIT_LIST_HEAD(&q->flush_queue[0]);
	INIT_LIST_HEAD(&q->flush_queue[1]);
	INIT_LIST_HEAD(&q->flush_data_in_flight);
	INIT_DELAYED_WORK(&q->delay_work, blk_delay_work);

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

	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;

	return q;
}
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, -1);
}
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 *uninit_q, *q;

	uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id);
	if (!uninit_q)
		return NULL;

	q = blk_init_allocated_queue_node(uninit_q, rfn, lock, node_id);
	if (!q)
		blk_cleanup_queue(uninit_q);

	return q;
}
EXPORT_SYMBOL(blk_init_queue_node);

struct request_queue *
blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
			 spinlock_t *lock)
{
	return blk_init_allocated_queue_node(q, rfn, lock, -1);
}
EXPORT_SYMBOL(blk_init_allocated_queue);

struct request_queue *
blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn,
			      spinlock_t *lock, int node_id)
{
	if (!q)
		return NULL;

	q->node = node_id;
	if (blk_init_free_list(q))
		return NULL;

	q->request_fn		= rfn;
	q->prep_rq_fn		= NULL;
	q->unprep_rq_fn		= NULL;
	q->queue_flags		= QUEUE_FLAG_DEFAULT;

	/* Override internal queue lock with supplied lock pointer */
	if (lock)
		q->queue_lock		= lock;

	/*
	 * This also sets hw/phys segments, boundary and size
	 */
	blk_queue_make_request(q, __make_request);

	q->sg_reserved_size = INT_MAX;

	/*
	 * all done
	 */
	if (!elevator_init(q, NULL)) {
		blk_queue_congestion_threshold(q);
		return q;
	}

	return NULL;
}
EXPORT_SYMBOL(blk_init_allocated_queue_node);

int blk_get_queue(struct request_queue *q)
{
	if (likely(!test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
		kobject_get(&q->kobj);
		return 0;
	}

	return 1;
}
EXPORT_SYMBOL(blk_get_queue);

static inline void blk_free_request(struct request_queue *q, struct request *rq)
{
	if (rq->cmd_flags & REQ_ELVPRIV)
		elv_put_request(q, rq);
	mempool_free(rq, q->rq.rq_pool);
}

static struct request *
blk_alloc_request(struct request_queue *q, int flags, int priv, gfp_t gfp_mask)
{
	struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);

	if (!rq)
		return NULL;

	blk_rq_init(q, rq);

	rq->cmd_flags = flags | REQ_ALLOCED;

	if (priv) {
		if (unlikely(elv_set_request(q, rq, gfp_mask))) {
			mempool_free(rq, q->rq.rq_pool);
			return NULL;
		}
		rq->cmd_flags |= REQ_ELVPRIV;
	}

	return rq;
}

/*
 * 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_queue *q, int sync)
{
	struct request_list *rl = &q->rq;

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

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

		blk_clear_queue_full(q, 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_queue *q, int sync, int priv)
{
	struct request_list *rl = &q->rq;

	rl->count[sync]--;
	if (priv)
		rl->elvpriv--;

	__freed_request(q, sync);

	if (unlikely(rl->starved[sync ^ 1]))
		__freed_request(q, sync ^ 1);
}

/*
 * Determine if elevator data should be initialized when allocating the
 * request associated with @bio.
 */
static bool blk_rq_should_init_elevator(struct bio *bio)
{
	if (!bio)
		return true;

	/*
	 * Flush requests do not use the elevator so skip initialization.
	 * This allows a request to share the flush and elevator data.
	 */
	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA))
		return false;

	return true;
}

/*
 * Get a free request, queue_lock must be held.
 * Returns NULL on failure, with queue_lock held.
 * Returns !NULL on success, with queue_lock *not held*.
 */
static struct request *get_request(struct request_queue *q, int rw_flags,
				   struct bio *bio, gfp_t gfp_mask)
{
	struct request *rq = NULL;
	struct request_list *rl = &q->rq;
	struct io_context *ioc = NULL;
	const bool is_sync = rw_is_sync(rw_flags) != 0;
	int may_queue, priv = 0;

	may_queue = elv_may_queue(q, rw_flags);
	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) {
			ioc = current_io_context(GFP_ATOMIC, q->node);
			/*
			 * 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_queue_full(q, is_sync)) {
				ioc_set_batching(q, ioc);
				blk_set_queue_full(q, 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
					 */
					goto out;
				}
			}
		}
		blk_set_queue_congested(q, 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))
		goto out;

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

	if (blk_rq_should_init_elevator(bio)) {
		priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
		if (priv)
			rl->elvpriv++;
	}

	if (blk_queue_io_stat(q))
		rw_flags |= REQ_IO_STAT;
	spin_unlock_irq(q->queue_lock);

	rq = blk_alloc_request(q, rw_flags, priv, gfp_mask);
	if (unlikely(!rq)) {
		/*
		 * 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(q, is_sync, priv);

		/*
		 * 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;

		goto 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, rw_flags & 1);
out:
	return rq;
}

/*
 * No available requests for this queue, wait for some requests to become
 * available.
 *
 * Called with q->queue_lock held, and returns with it unlocked.
 */
static struct request *get_request_wait(struct request_queue *q, int rw_flags,
					struct bio *bio)
{
	const bool is_sync = rw_is_sync(rw_flags) != 0;
	struct request *rq;

	rq = get_request(q, rw_flags, bio, GFP_NOIO);
	while (!rq) {
		DEFINE_WAIT(wait);
		struct io_context *ioc;
		struct request_list *rl = &q->rq;

		prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
				TASK_UNINTERRUPTIBLE);

		trace_block_sleeprq(q, bio, rw_flags & 1);

		spin_unlock_irq(q->queue_lock);
		io_schedule();

		/*
		 * After sleeping, we become a "batching" process and
		 * will be able to allocate at least one request, and
		 * up to a big batch of them for a small period time.
		 * See ioc_batching, ioc_set_batching
		 */
		ioc = current_io_context(GFP_NOIO, q->node);
		ioc_set_batching(q, ioc);

		spin_lock_irq(q->queue_lock);
		finish_wait(&rl->wait[is_sync], &wait);

		rq = get_request(q, rw_flags, bio, GFP_NOIO);
	};

	return rq;
}

struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
{
	struct request *rq;

	if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
		return NULL;

	BUG_ON(rw != READ && rw != WRITE);

	spin_lock_irq(q->queue_lock);
	if (gfp_mask & __GFP_WAIT) {
		rq = get_request_wait(q, rw, NULL);
	} else {
		rq = get_request(q, rw, NULL, gfp_mask);
		if (!rq)
			spin_unlock_irq(q->queue_lock);
	}
	/* q->queue_lock is unlocked at this point */

	return rq;
}
EXPORT_SYMBOL(blk_get_request);

/**
 * blk_make_request - given a bio, allocate a corresponding struct request.
 * @q: target request queue
 * @bio:  The bio describing the memory mappings that will be submitted for IO.
 *        It may be a chained-bio properly constructed by block/bio layer.
 * @gfp_mask: gfp flags to be used for memory allocation
 *
 * blk_make_request is the parallel of generic_make_request for BLOCK_PC
 * type commands. Where the struct request needs to be farther initialized by
 * the caller. It is passed a &struct bio, which describes the memory info of
 * the I/O transfer.
 *
 * The caller of blk_make_request must make sure that bi_io_vec
 * are set to describe the memory buffers. That bio_data_dir() will return
 * the needed direction of the request. (And all bio's in the passed bio-chain
 * are properly set accordingly)
 *
 * If called under none-sleepable conditions, mapped bio buffers must not
 * need bouncing, by calling the appropriate masked or flagged allocator,
 * suitable for the target device. Otherwise the call to blk_queue_bounce will
 * BUG.
 *
 * WARNING: When allocating/cloning a bio-chain, careful consideration should be
 * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for
 * anything but the first bio in the chain. Otherwise you risk waiting for IO
 * completion of a bio that hasn't been submitted yet, thus resulting in a
 * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead
 * of bio_alloc(), as that avoids the mempool deadlock.
 * If possible a big IO should be split into smaller parts when allocation
 * fails. Partial allocation should not be an error, or you risk a live-lock.
 */
struct request *blk_make_request(struct request_queue *q, struct bio *bio,
				 gfp_t gfp_mask)
{
	struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);

	if (unlikely(!rq))
		return ERR_PTR(-ENOMEM);

	for_each_bio(bio) {
		struct bio *bounce_bio = bio;
		int ret;

		blk_queue_bounce(q, &bounce_bio);
		ret = blk_rq_append_bio(q, rq, bounce_bio);
		if (unlikely(ret)) {
			blk_put_request(rq);
			return ERR_PTR(ret);
		}
	}

	return rq;
}
EXPORT_SYMBOL(blk_make_request);

/**
 * blk_requeue_request - put a request back on queue
 * @q:		request queue where request should be inserted
 * @rq:		request to be inserted
 *
 * Description:
 *    Drivers often keep queueing requests until the hardware cannot accept
 *    more, when that condition happens we need to put the request back
 *    on the queue. Must be called with queue lock held.
 */
void blk_requeue_request(struct request_queue *q, struct request *rq)
{
	blk_delete_timer(rq);
	blk_clear_rq_complete(rq);
	trace_block_rq_requeue(q, rq);

	if (blk_rq_tagged(rq))
		blk_queue_end_tag(q, rq);

	BUG_ON(blk_queued_rq(rq));

	elv_requeue_request(q, rq);
}
EXPORT_SYMBOL(blk_requeue_request);

static void add_acct_request(struct request_queue *q, struct request *rq,
			     int where)
{
	drive_stat_acct(rq, 1);
	__elv_add_request(q, rq, where);
}

/**
 * blk_insert_request - insert a special request into a request queue
 * @q:		request queue where request should be inserted
 * @rq:		request to be inserted
 * @at_head:	insert request at head or tail of queue
 * @data:	private data
 *
 * Description:
 *    Many block devices need to execute commands asynchronously, so they don't
 *    block the whole kernel from preemption during request execution.  This is
 *    accomplished normally by inserting aritficial requests tagged as
 *    REQ_TYPE_SPECIAL in to the corresponding request queue, and letting them
 *    be scheduled for actual execution by the request queue.
 *
 *    We have the option of inserting the head or the tail of the queue.
 *    Typically we use the tail for new ioctls and so forth.  We use the head
 *    of the queue for things like a QUEUE_FULL message from a device, or a
 *    host that is unable to accept a particular command.
 */
void blk_insert_request(struct request_queue *q, struct request *rq,
			int at_head, void *data)
{
	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
	unsigned long flags;

	/*
	 * tell I/O scheduler that this isn't a regular read/write (ie it
	 * must not attempt merges on this) and that it acts as a soft
	 * barrier
	 */
	rq->cmd_type = REQ_TYPE_SPECIAL;

	rq->special = data;

	spin_lock_irqsave(q->queue_lock, flags);

	/*
	 * If command is tagged, release the tag
	 */
	if (blk_rq_tagged(rq))
		blk_queue_end_tag(q, rq);

	add_acct_request(q, rq, where);
	__blk_run_queue(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_insert_request);

static void part_round_stats_single(int cpu, struct hd_struct *part,
				    unsigned long now)
{
	if (now == part->stamp)
		return;