/*
 * 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/bootmem.h>      /* for max_pfn/max_low_pfn */
#include <linux/completion.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/blktrace_api.h>

/*
 * for max sense size
 */
#include <scsi/scsi_cmnd.h>

static void blk_unplug_work(void *data);
static void blk_unplug_timeout(unsigned long data);
static void drive_stat_acct(struct request *rq, int nr_sectors, int new_io);
static void init_request_from_bio(struct request *req, struct bio *bio);
static int __make_request(request_queue_t *q, struct bio *bio);

/*
 * For the allocated request tables
 */
static kmem_cache_t *request_cachep;

/*
 * For queue allocation
 */
static kmem_cache_t *requestq_cachep;

/*
 * For io context allocations
 */
static kmem_cache_t *iocontext_cachep;

static wait_queue_head_t congestion_wqh[2] = {
                __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
                __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
        };

/*
 * Controlling structure to kblockd
 */
static struct workqueue_struct *kblockd_workqueue;

unsigned long blk_max_low_pfn, blk_max_pfn;

EXPORT_SYMBOL(blk_max_low_pfn);
EXPORT_SYMBOL(blk_max_pfn);

static DEFINE_PER_CPU(struct list_head, blk_cpu_done);

/* Amount of time in which a process may batch requests */
#define BLK_BATCH_TIME  (HZ/50UL)

/* Number of requests a "batching" process may submit */
#define BLK_BATCH_REQ   32

/*
 * Return the threshold (number of used requests) at which the queue is
 * considered to be congested.  It include a little hysteresis to keep the
 * context switch rate down.
 */
static inline int queue_congestion_on_threshold(struct request_queue *q)
{
        return q->nr_congestion_on;
}

/*
 * The threshold at which a queue is considered to be uncongested
 */
static inline int queue_congestion_off_threshold(struct request_queue *q)
{
        return q->nr_congestion_off;
}

static 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;
}

/*
 * A queue has just exitted congestion.  Note this in the global counter of
 * congested queues, and wake up anyone who was waiting for requests to be
 * put back.
 */
static void clear_queue_congested(request_queue_t *q, int rw)
{
        enum bdi_state bit;
        wait_queue_head_t *wqh = &congestion_wqh[rw];

        bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
        clear_bit(bit, &q->backing_dev_info.state);
        smp_mb__after_clear_bit();
        if (waitqueue_active(wqh))
                wake_up(wqh);
}

/*
 * A queue has just entered congestion.  Flag that in the queue's VM-visible
 * state flags and increment the global gounter of congested queues.
 */
static void set_queue_congested(request_queue_t *q, int rw)
{
        enum bdi_state bit;

        bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
        set_bit(bit, &q->backing_dev_info.state);
}

/**
 * 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;
        request_queue_t *q = bdev_get_queue(bdev);

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

EXPORT_SYMBOL(blk_get_backing_dev_info);

void blk_queue_activity_fn(request_queue_t *q, activity_fn *fn, void *data)
{
        q->activity_fn = fn;
        q->activity_data = data;
}

EXPORT_SYMBOL(blk_queue_activity_fn);

/**
 * blk_queue_prep_rq - set a prepare_request function for queue
 * @q:          queue
 * @pfn:        prepare_request function
 *
 * It's possible for a queue to register a prepare_request callback which
 * is invoked before the request is handed to the request_fn. The goal of
 * the function is to prepare a request for I/O, it can be used to build a
 * cdb from the request data for instance.
 *
 */
void blk_queue_prep_rq(request_queue_t *q, prep_rq_fn *pfn)
{
        q->prep_rq_fn = pfn;
}

EXPORT_SYMBOL(blk_queue_prep_rq);

/**
 * blk_queue_merge_bvec - set a merge_bvec function for queue
 * @q:          queue
 * @mbfn:       merge_bvec_fn
 *
 * Usually queues have static limitations on the max sectors or segments that
 * we can put in a request. Stacking drivers may have some settings that
 * are dynamic, and thus we have to query the queue whether it is ok to
 * add a new bio_vec to a bio at a given offset or not. If the block device
 * has such limitations, it needs to register a merge_bvec_fn to control
 * the size of bio's sent to it. Note that a block device *must* allow a
 * single page to be added to an empty bio. The block device driver may want
 * to use the bio_split() function to deal with these bio's. By default
 * no merge_bvec_fn is defined for a queue, and only the fixed limits are
 * honored.
 */
void blk_queue_merge_bvec(request_queue_t *q, merge_bvec_fn *mbfn)
{
        q->merge_bvec_fn = mbfn;
}

EXPORT_SYMBOL(blk_queue_merge_bvec);

void blk_queue_softirq_done(request_queue_t *q, softirq_done_fn *fn)
{
        q->softirq_done_fn = fn;
}

EXPORT_SYMBOL(blk_queue_softirq_done);

/**
 * blk_queue_make_request - define an alternate make_request function for a device
 * @q:  the request queue for the device to be affected
 * @mfn: the alternate make_request function
 *
 * Description:
 *    The normal way for &struct bios to be passed to a device
 *    driver is for them to be collected into requests on a request
 *    queue, and then to allow the device driver to select requests
 *    off that queue when it is ready.  This works well for many block
 *    devices. However some block devices (typically virtual devices
 *    such as md or lvm) do not benefit from the processing on the
 *    request queue, and are served best by having the requests passed
 *    directly to them.  This can be achieved by providing a function
 *    to blk_queue_make_request().
 *
 * Caveat:
 *    The driver that does this *must* be able to deal appropriately
 *    with buffers in "highmemory". This can be accomplished by either calling
 *    __bio_kmap_atomic() to get a temporary kernel mapping, or by calling
 *    blk_queue_bounce() to create a buffer in normal memory.
 **/
void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn)
{
        /*
         * set defaults
         */
        q->nr_requests = BLKDEV_MAX_RQ;
        blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
        blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
        q->make_request_fn = mfn;
        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;
        blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
        blk_queue_hardsect_size(q, 512);
        blk_queue_dma_alignment(q, 511);
        blk_queue_congestion_threshold(q);
        q->nr_batching = BLK_BATCH_REQ;

        q->unplug_thresh = 4;           /* hmm */
        q->unplug_delay = (3 * HZ) / 1000;      /* 3 milliseconds */
        if (q->unplug_delay == 0)
                q->unplug_delay = 1;

        INIT_WORK(&q->unplug_work, blk_unplug_work, q);

        q->unplug_timer.function = blk_unplug_timeout;
        q->unplug_timer.data = (unsigned long)q;

        /*
         * by default assume old behaviour and bounce for any highmem page
         */
        blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);

        blk_queue_activity_fn(q, NULL, NULL);
}

EXPORT_SYMBOL(blk_queue_make_request);

static inline void rq_init(request_queue_t *q, struct request *rq)
{
        INIT_LIST_HEAD(&rq->queuelist);
        INIT_LIST_HEAD(&rq->donelist);

        rq->errors = 0;
        rq->rq_status = RQ_ACTIVE;
        rq->bio = rq->biotail = NULL;
        rq->ioprio = 0;
        rq->buffer = NULL;
        rq->ref_count = 1;
        rq->q = q;
        rq->waiting = NULL;
        rq->special = NULL;
        rq->data_len = 0;
        rq->data = NULL;
        rq->nr_phys_segments = 0;
        rq->sense = NULL;
        rq->end_io = NULL;
        rq->end_io_data = NULL;
        rq->completion_data = NULL;
}

/**
 * blk_queue_ordered - does this queue support ordered writes
 * @q:        the request queue
 * @ordered:  one of QUEUE_ORDERED_*
 * @prepare_flush_fn: rq setup helper for cache flush ordered writes
 *
 * Description:
 *   For journalled file systems, doing ordered writes on a commit
 *   block instead of explicitly doing wait_on_buffer (which is bad
 *   for performance) can be a big win. Block drivers supporting this
 *   feature should call this function and indicate so.
 *
 **/
int blk_queue_ordered(request_queue_t *q, unsigned ordered,
                      prepare_flush_fn *prepare_flush_fn)
{
        if (ordered & (QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH) &&
            prepare_flush_fn == NULL) {
                printk(KERN_ERR "blk_queue_ordered: prepare_flush_fn required\n");
                return -EINVAL;
        }

        if (ordered != QUEUE_ORDERED_NONE &&
            ordered != QUEUE_ORDERED_DRAIN &&
            ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
            ordered != QUEUE_ORDERED_DRAIN_FUA &&
            ordered != QUEUE_ORDERED_TAG &&
            ordered != QUEUE_ORDERED_TAG_FLUSH &&
            ordered != QUEUE_ORDERED_TAG_FUA) {
                printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
                return -EINVAL;
        }

        q->ordered = ordered;
        q->next_ordered = ordered;
        q->prepare_flush_fn = prepare_flush_fn;

        return 0;
}

EXPORT_SYMBOL(blk_queue_ordered);

/**
 * blk_queue_issue_flush_fn - set function for issuing a flush
 * @q:     the request queue
 * @iff:   the function to be called issuing the flush
 *
 * Description:
 *   If a driver supports issuing a flush command, the support is notified
 *   to the block layer by defining it through this call.
 *
 **/
void blk_queue_issue_flush_fn(request_queue_t *q, issue_flush_fn *iff)
{
        q->issue_flush_fn = iff;
}

EXPORT_SYMBOL(blk_queue_issue_flush_fn);

/*
 * Cache flushing for ordered writes handling
 */
inline unsigned blk_ordered_cur_seq(request_queue_t *q)
{
        if (!q->ordseq)
                return 0;
        return 1 << ffz(q->ordseq);
}

unsigned blk_ordered_req_seq(struct request *rq)
{
        request_queue_t *q = rq->q;

        BUG_ON(q->ordseq == 0);

        if (rq == &q->pre_flush_rq)
                return QUEUE_ORDSEQ_PREFLUSH;
        if (rq == &q->bar_rq)
                return QUEUE_ORDSEQ_BAR;
        if (rq == &q->post_flush_rq)
                return QUEUE_ORDSEQ_POSTFLUSH;

        if ((rq->flags & REQ_ORDERED_COLOR) ==
            (q->orig_bar_rq->flags & REQ_ORDERED_COLOR))
                return QUEUE_ORDSEQ_DRAIN;
        else
                return QUEUE_ORDSEQ_DONE;
}

void blk_ordered_complete_seq(request_queue_t *q, unsigned seq, int error)
{
        struct request *rq;
        int uptodate;

        if (error && !q->orderr)
                q->orderr = error;

        BUG_ON(q->ordseq & seq);
        q->ordseq |= seq;

        if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
                return;

        /*
         * Okay, sequence complete.
         */
        rq = q->orig_bar_rq;
        uptodate = q->orderr ? q->orderr : 1;

        q->ordseq = 0;

        end_that_request_first(rq, uptodate, rq->hard_nr_sectors);
        end_that_request_last(rq, uptodate);
}

static void pre_flush_end_io(struct request *rq, int error)
{
        elv_completed_request(rq->q, rq);
        blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_PREFLUSH, error);
}

static void bar_end_io(struct request *rq, int error)
{
        elv_completed_request(rq->q, rq);
        blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_BAR, error);
}

static void post_flush_end_io(struct request *rq, int error)
{
        elv_completed_request(rq->q, rq);
        blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
}

static void queue_flush(request_queue_t *q, unsigned which)
{
        struct request *rq;
        rq_end_io_fn *end_io;

        if (which == QUEUE_ORDERED_PREFLUSH) {
                rq = &q->pre_flush_rq;
                end_io = pre_flush_end_io;
        } else {
                rq = &q->post_flush_rq;
                end_io = post_flush_end_io;
        }

        rq_init(q, rq);
        rq->flags = REQ_HARDBARRIER;
        rq->elevator_private = NULL;
        rq->rq_disk = q->bar_rq.rq_disk;
        rq->rl = NULL;
        rq->end_io = end_io;
        q->prepare_flush_fn(q, rq);

        elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
}

static inline struct request *start_ordered(request_queue_t *q,
                                            struct request *rq)
{
        q->bi_size = 0;
        q->orderr = 0;
        q->ordered = q->next_ordered;
        q->ordseq |= QUEUE_ORDSEQ_STARTED;

        /*
         * Prep proxy barrier request.
         */
        blkdev_dequeue_request(rq);
        q->orig_bar_rq = rq;
        rq = &q->bar_rq;
        rq_init(q, rq);
        rq->flags = bio_data_dir(q->orig_bar_rq->bio);
        rq->flags |= q->ordered & QUEUE_ORDERED_FUA ? REQ_FUA : 0;
        rq->elevator_private = NULL;
        rq->rl = NULL;
        init_request_from_bio(rq, q->orig_bar_rq->bio);
        rq->end_io = bar_end_io;

        /*
         * Queue ordered sequence.  As we stack them at the head, we
         * need to queue in reverse order.  Note that we rely on that
         * no fs request uses ELEVATOR_INSERT_FRONT and thus no fs
         * request gets inbetween ordered sequence.
         */
        if (q->ordered & QUEUE_ORDERED_POSTFLUSH)
                queue_flush(q, QUEUE_ORDERED_POSTFLUSH);
        else
                q->ordseq |= QUEUE_ORDSEQ_POSTFLUSH;

        elv_insert(q, rq, ELEVATOR_INSERT_FRONT);

        if (q->ordered & QUEUE_ORDERED_PREFLUSH) {
                queue_flush(q, QUEUE_ORDERED_PREFLUSH);
                rq = &q->pre_flush_rq;
        } else
                q->ordseq |= QUEUE_ORDSEQ_PREFLUSH;

        if ((q->ordered & QUEUE_ORDERED_TAG) || q->in_flight == 0)
                q->ordseq |= QUEUE_ORDSEQ_DRAIN;
        else
                rq = NULL;

        return rq;
}

int blk_do_ordered(request_queue_t *q, struct request **rqp)
{
        struct request *rq = *rqp;
        int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);

        if (!q->ordseq) {
                if (!is_barrier)
                        return 1;

                if (q->next_ordered != QUEUE_ORDERED_NONE) {
                        *rqp = start_ordered(q, rq);
                        return 1;
                } else {
                        /*
                         * This can happen when the queue switches to
                         * ORDERED_NONE while this request is on it.
                         */
                        blkdev_dequeue_request(rq);
                        end_that_request_first(rq, -EOPNOTSUPP,
                                               rq->hard_nr_sectors);
                        end_that_request_last(rq, -EOPNOTSUPP);
                        *rqp = NULL;
                        return 0;
                }
        }

        /*
         * Ordered sequence in progress
         */

        /* Special requests are not subject to ordering rules. */
        if (!blk_fs_request(rq) &&
            rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
                return 1;

        if (q->ordered & QUEUE_ORDERED_TAG) {
                /* Ordered by tag.  Blocking the next barrier is enough. */
                if (is_barrier && rq != &q->bar_rq)
                        *rqp = NULL;
        } else {
                /* Ordered by draining.  Wait for turn. */
                WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
                if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
                        *rqp = NULL;
        }

        return 1;
}

static int flush_dry_bio_endio(struct bio *bio, unsigned int bytes, int error)
{
        request_queue_t *q = bio->bi_private;
        struct bio_vec *bvec;
        int i;

        /*
         * This is dry run, restore bio_sector and size.  We'll finish
         * this request again with the original bi_end_io after an
         * error occurs or post flush is complete.
         */
        q->bi_size += bytes;

        if (bio->bi_size)
                return 1;

        /* Rewind bvec's */
        bio->bi_idx = 0;
        bio_for_each_segment(bvec, bio, i) {
                bvec->bv_len += bvec->bv_offset;
                bvec->bv_offset = 0;
        }

        /* Reset bio */
        set_bit(BIO_UPTODATE, &bio->bi_flags);
        bio->bi_size = q->bi_size;
        bio->bi_sector -= (q->bi_size >> 9);
        q->bi_size = 0;

        return 0;
}

static inline int ordered_bio_endio(struct request *rq, struct bio *bio,
                                    unsigned int nbytes, int error)
{
        request_queue_t *q = rq->q;
        bio_end_io_t *endio;
        void *private;

        if (&q->bar_rq != rq)
                return 0;

        /*
         * Okay, this is the barrier request in progress, dry finish it.
         */
        if (error && !q->orderr)
                q->orderr = error;

        endio = bio->bi_end_io;
        private = bio->bi_private;
        bio->bi_end_io = flush_dry_bio_endio;
        bio->bi_private = q;

        bio_endio(bio, nbytes, error);

        bio->bi_end_io = endio;
        bio->bi_private = private;

        return 1;
}

/**
 * blk_queue_bounce_limit - set bounce buffer limit for queue
 * @q:  the request queue for the device
 * @dma_addr:   bus address limit
 *
 * Description:
 *    Different hardware can have different requirements as to what pages
 *    it can do I/O directly to. A low level driver can call
 *    blk_queue_bounce_limit to have lower memory pages allocated as bounce
 *    buffers for doing I/O to pages residing above @page.
 **/
void blk_queue_bounce_limit(request_queue_t *q, u64 dma_addr)
{
        unsigned long bounce_pfn = dma_addr >> PAGE_SHIFT;
        int dma = 0;

        q->bounce_gfp = GFP_NOIO;
#if BITS_PER_LONG == 64
        /* Assume anything <= 4GB can be handled by IOMMU.
           Actually some IOMMUs can handle everything, but I don't
           know of a way to test this here. */
        if (bounce_pfn < (min_t(u64,0xffffffff,BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
                dma = 1;
        q->bounce_pfn = max_low_pfn;
#else
        if (bounce_pfn < blk_max_low_pfn)
                dma = 1;
        q->bounce_pfn = bounce_pfn;
#endif
        if (dma) {
                init_emergency_isa_pool();
                q->bounce_gfp = GFP_NOIO | GFP_DMA;
                q->bounce_pfn = bounce_pfn;
        }
}

EXPORT_SYMBOL(blk_queue_bounce_limit);

/**
 * blk_queue_max_sectors - set max sectors for a request for this queue
 * @q:  the request queue for the device
 * @max_sectors:  max sectors in the usual 512b unit
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the size of
 *    received requests.
 **/
void blk_queue_max_sectors(request_queue_t *q, unsigned int max_sectors)
{
        if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
                max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
                printk("%s: set to minimum %d\n", __FUNCTION__, max_sectors);
        }

        if (BLK_DEF_MAX_SECTORS > max_sectors)
                q->max_hw_sectors = q->max_sectors = max_sectors;
        else {
                q->max_sectors = BLK_DEF_MAX_SECTORS;
                q->max_hw_sectors = max_sectors;
        }
}

EXPORT_SYMBOL(blk_queue_max_sectors);

/**
 * blk_queue_max_phys_segments - set max phys segments for a request for this queue
 * @q:  the request queue for the device
 * @max_segments:  max number of segments
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the number of
 *    physical data segments in a request.  This would be the largest sized
 *    scatter list the driver could handle.
 **/
void blk_queue_max_phys_segments(request_queue_t *q, unsigned short max_segments)
{
        if (!max_segments) {
                max_segments = 1;
                printk("%s: set to minimum %d\n", __FUNCTION__, max_segments);
        }

        q->max_phys_segments = max_segments;
}

EXPORT_SYMBOL(blk_queue_max_phys_segments);

/**
 * blk_queue_max_hw_segments - set max hw segments for a request for this queue
 * @q:  the request queue for the device
 * @max_segments:  max number of segments
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the number of
 *    hw data segments in a request.  This would be the largest number of
 *    address/length pairs the host adapter can actually give as once
 *    to the device.
 **/
void blk_queue_max_hw_segments(request_queue_t *q, unsigned short max_segments)
{
        if (!max_segments) {
                max_segments = 1;
                printk("%s: set to minimum %d\n", __FUNCTION__, max_segments);
        }

        q->max_hw_segments = max_segments;
}

EXPORT_SYMBOL(blk_queue_max_hw_segments);

/**
 * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
 * @q:  the request queue for the device
 * @max_size:  max size of segment in bytes
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the size of a
 *    coalesced segment
 **/
void blk_queue_max_segment_size(request_queue_t *q, unsigned int max_size)
{
        if (max_size < PAGE_CACHE_SIZE) {
                max_size = PAGE_CACHE_SIZE;
                printk("%s: set to minimum %d\n", __FUNCTION__, max_size);
        }

        q->max_segment_size = max_size;
}

EXPORT_SYMBOL(blk_queue_max_segment_size);

/**
 * blk_queue_hardsect_size - set hardware sector size for the queue
 * @q:  the request queue for the device
 * @size:  the hardware sector size, in bytes
 *
 * Description:
 *   This should typically be set to the lowest possible sector size
 *   that the hardware can operate on (possible without reverting to
 *   even internal read-modify-write operations). Usually the default
 *   of 512 covers most hardware.
 **/
void blk_queue_hardsect_size(request_queue_t *q, unsigned short size)
{
        q->hardsect_size = size;
}

EXPORT_SYMBOL(blk_queue_hardsect_size);

/*
 * Returns the minimum that is _not_ zero, unless both are zero.
 */
#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))

/**
 * blk_queue_stack_limits - inherit underlying queue limits for stacked drivers
 * @t:  the stacking driver (top)
 * @b:  the underlying device (bottom)
 **/
void blk_queue_stack_limits(request_queue_t *t, request_queue_t *b)
{
        /* zero is "infinity" */
        t->max_sectors = min_not_zero(t->max_sectors,b->max_sectors);
        t->max_hw_sectors = min_not_zero(t->max_hw_sectors,b->max_hw_sectors);

        t->max_phys_segments = min(t->max_phys_segments,b->max_phys_segments);
        t->max_hw_segments = min(t->max_hw_segments,b->max_hw_segments);
        t->max_segment_size = min(t->max_segment_size,b->max_segment_size);
        t->hardsect_size = max(t->hardsect_size,b->hardsect_size);
        if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
                clear_bit(QUEUE_FLAG_CLUSTER, &t->queue_flags);
}

EXPORT_SYMBOL(blk_queue_stack_limits);

/**
 * blk_queue_segment_boundary - set boundary rules for segment merging
 * @q:  the request queue for the device
 * @mask:  the memory boundary mask
 **/
void blk_queue_segment_boundary(request_queue_t *q, unsigned long mask)
{
        if (mask < PAGE_CACHE_SIZE - 1) {
                mask = PAGE_CACHE_SIZE - 1;
                printk("%s: set to minimum %lx\n", __FUNCTION__, mask);
        }

        q->seg_boundary_mask = mask;
}

EXPORT_SYMBOL(blk_queue_segment_boundary);

/**
 * blk_queue_dma_alignment - set dma length and memory alignment
 * @q:     the request queue for the device
 * @mask:  alignment mask
 *
 * description:
 *    set required memory and length aligment for direct dma transactions.
 *    this is used when buiding direct io requests for the queue.
 *
 **/
void blk_queue_dma_alignment(request_queue_t *q, int mask)
{
        q->dma_alignment = mask;
}

EXPORT_SYMBOL(blk_queue_dma_alignment);

/**
 * blk_queue_find_tag - find a request by its tag and queue
 * @q:   The request queue for the device
 * @tag: The tag of the request
 *
 * Notes:
 *    Should be used when a device returns a tag and you want to match
 *    it with a request.
 *
 *    no locks need be held.
 **/
struct request *blk_queue_find_tag(request_queue_t *q, int tag)
{
        struct blk_queue_tag *bqt = q->queue_tags;

        if (unlikely(bqt == NULL || tag >= bqt->real_max_depth))
                return NULL;

        return bqt->tag_index[tag];
}

EXPORT_SYMBOL(blk_queue_find_tag);

/**
 * __blk_queue_free_tags - release tag maintenance info
 * @q:  the request queue for the device
 *
 *  Notes:
 *    blk_cleanup_queue() will take care of calling this function, if tagging
 *    has been used. So there's no need to call this directly.
 **/
static void __blk_queue_free_tags(request_queue_t *q)
{
        struct blk_queue_tag *bqt = q->queue_tags;

        if (!bqt)
                return;

        if (atomic_dec_and_test(&bqt->refcnt)) {
                BUG_ON(bqt->busy);
                BUG_ON(!list_empty(&bqt->busy_list));

                kfree(bqt->tag_index);
                bqt->tag_index = NULL;

                kfree(bqt->tag_map);
                bqt->tag_map = NULL;

                kfree(bqt);
        }

        q->queue_tags = NULL;
        q->queue_flags &= ~(1 << QUEUE_FLAG_QUEUED);
}

/**
 * blk_queue_free_tags - release tag maintenance info
 * @q:  the request queue for the device
 *
 *  Notes:
 *      This is used to disabled tagged queuing to a device, yet leave
 *      queue in function.
 **/
void blk_queue_free_tags(request_queue_t *q)
{
        clear_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
}

EXPORT_SYMBOL(blk_queue_free_tags);

static int
init_tag_map(request_queue_t *q, struct blk_queue_tag *tags, int depth)
{
        struct request **tag_index;
        unsigned long *tag_map;
        int nr_ulongs;

        if (depth > q->nr_requests * 2) {
                depth = q->nr_requests * 2;
                printk(KERN_ERR "%s: adjusted depth to %d\n",
                                __FUNCTION__, depth);
        }

        tag_index = kzalloc(depth * sizeof(struct request *), GFP_ATOMIC);
        if (!tag_index)
                goto fail;

        nr_ulongs = ALIGN(depth, BITS_PER_LONG) / BITS_PER_LONG;
        tag_map = kzalloc(nr_ulongs * sizeof(unsigned long), GFP_ATOMIC);
        if (!tag_map)
                goto fail;

        tags->real_max_depth = depth;
        tags->max_depth = depth;
        tags->tag_index = tag_index;
        tags->tag_map = tag_map;

        return 0;
fail:
        kfree(tag_index);
        return -ENOMEM;
}

/**
 * blk_queue_init_tags - initialize the queue tag info
 * @q:  the request queue for the device
 * @depth:  the maximum queue depth supported
 * @tags: the tag to use
 **/
int blk_queue_init_tags(request_queue_t *q, int depth,
                        struct blk_queue_tag *tags)
{
        int rc;

        BUG_ON(tags && q->queue_tags && tags != q->queue_tags);

        if (!tags && !q->queue_tags) {
                tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC);
                if (!tags)
                        goto fail;

                if (init_tag_map(q, tags, depth))
                        goto fail;

                INIT_LIST_HEAD(&tags->busy_list);
                tags->busy = 0;
                atomic_set(&tags->refcnt, 1);
        } else if (q->queue_tags) {
                if ((rc = blk_queue_resize_tags(q, depth)))
                        return rc;
                set_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
                return 0;
        } else
                atomic_inc(&tags->refcnt);

        /*
         * assign it, all done
         */
        q->queue_tags = tags;
        q->queue_flags |= (1 << QUEUE_FLAG_QUEUED);
        return 0;
fail:
        kfree(tags);
        return -ENOMEM;
}

EXPORT_SYMBOL(blk_queue_init_tags);

/**
 * blk_queue_resize_tags - change the queueing depth
 * @q:  the request queue for the device
 * @new_depth: the new max command queueing depth
 *
 *  Notes:
 *    Must be called with the queue lock held.
 **/
int blk_queue_resize_tags(request_queue_t *q, int new_depth)
{
        struct blk_queue_tag *bqt = q->queue_tags;
        struct request **tag_index;
        unsigned long *tag_map;
        int max_depth, nr_ulongs;

        if (!bqt)
                return -ENXIO;

        /*
         * if we already have large enough real_max_depth.  just
         * adjust max_depth.  *NOTE* as requests with tag value
         * between new_depth and real_max_depth can be in-flight, tag
         * map can not be shrunk blindly here.
         */
        if (new_depth <= bqt->real_max_depth) {
                bqt->max_depth = new_depth;

                return 0;
        }

        /*
         * save the old state info, so we can copy it back
         */
        tag_index = bqt->tag_index;
        tag_map = bqt->tag_map;
        max_depth = bqt->real_max_depth;

        if (init_tag_map(q, bqt, new_depth))
                return -ENOMEM;

        memcpy(bqt->tag_index, tag_index, max_depth * sizeof(struct request *));
        nr_ulongs = ALIGN(max_depth, BITS_PER_LONG) / BITS_PER_LONG;
        memcpy(bqt->tag_map, tag_map, nr_ulongs * sizeof(unsigned long));

        kfree(tag_index);
        kfree(tag_map);
        return 0;
}

EXPORT_SYMBOL(blk_queue_resize_tags);

/**
 * blk_queue_end_tag - end tag operations for a request
 * @q:  the request queue for the device
 * @rq: the request that has completed
 *
 *  Description:
 *    Typically called when end_that_request_first() returns 0, meaning
 *    all transfers have been done for a request. It's important to call
 *    this function before end_that_request_last(), as that will put the
 *    request back on the free list thus corrupting the internal tag list.
 *
 *  Notes:
 *   queue lock must be held.
 **/
void blk_queue_end_tag(request_queue_t *q, struct request *rq)
{
        struct blk_queue_tag *bqt = q->queue_tags;
        int tag = rq->tag;

        BUG_ON(tag == -1);

        if (unlikely(tag >= bqt->real_max_depth))
                /*
                 * This can happen after tag depth has been reduced.
                 * FIXME: how about a warning or info message here?
                 */
                return;

        if (unlikely(!__test_and_clear_bit(tag, bqt->tag_map))) {
                printk(KERN_ERR "%s: attempt to clear non-busy tag (%d)\n",
                       __FUNCTION__, tag);
                return;
        }

        list_del_init(&rq->queuelist);
        rq->flags &= ~REQ_QUEUED;
        rq->tag = -1;

        if (unlikely(bqt->tag_index[tag] == NULL))
                printk(KERN_ERR "%s: tag %d is missing\n",
                       __FUNCTION__, tag);

        bqt->tag_index[tag] = NULL;
        bqt->busy--;
}

EXPORT_SYMBOL(blk_queue_end_tag);

/**
 * blk_queue_start_tag - find a free tag and assign it
 * @q:  the request queue for the device
 * @rq:  the block request that needs tagging
 *
 *  Description:
 *    This can either be used as a stand-alone helper, or possibly be
 *    assigned as the queue &prep_rq_fn (in which case &struct request
 *    automagically gets a tag assigned). Note that this function
 *    assumes that any type of request can be queued! if this is not
 *    true for your device, you must check the request type before
 *    calling this function.  The request will also be removed from
 *    the request queue, so it's the drivers responsibility to readd
 *    it if it should need to be restarted for some reason.
 *
 *  Notes:
 *   queue lock must be held.
 **/
int blk_queue_start_tag(request_queue_t *q, struct request *rq)
{
        struct blk_queue_tag *bqt = q->queue_tags;
        int tag;

        if (unlikely((rq->flags & REQ_QUEUED))) {
                printk(KERN_ERR 
                       "%s: request %p for device [%s] already tagged %d",
                       __FUNCTION__, rq,
                       rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->tag);
                BUG();
        }

        tag = find_first_zero_bit(bqt->tag_map, bqt->max_depth);
        if (tag >= bqt->max_depth)
                return 1;

        __set_bit(tag, bqt->tag_map);

        rq->flags |= REQ_QUEUED;
        rq->tag = tag;
        bqt->tag_index[tag] = rq;
        blkdev_dequeue_request(rq);
        list_add(&rq->queuelist, &bqt->busy_list);
        bqt->busy++;
        return 0;
}

EXPORT_SYMBOL(blk_queue_start_tag);

/**
 * blk_queue_invalidate_tags - invalidate all pending tags
 * @q:  the request queue for the device
 *
 *  Description:
 *   Hardware conditions may dictate a need to stop all pending requests.
 *   In this case, we will safely clear the block side of the tag queue and
 *   readd all requests to the request queue in the right order.
 *
 *  Notes:
 *   queue lock must be held.
 **/
void blk_queue_invalidate_tags(request_queue_t *q)
{
        struct blk_queue_tag *bqt = q->queue_tags;
        struct list_head *tmp, *n;
        struct request *rq;

        list_for_each_safe(tmp, n, &bqt->busy_list) {
                rq = list_entry_rq(tmp);

                if (rq->tag == -1) {
                        printk(KERN_ERR
                               "%s: bad tag found on list\n", __FUNCTION__);
                        list_del_init(&rq->queuelist);
                        rq->flags &= ~REQ_QUEUED;
                } else
                        blk_queue_end_tag(q, rq);

                rq->flags &= ~REQ_STARTED;
                __elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 0);
        }
}

EXPORT_SYMBOL(blk_queue_invalidate_tags);

static const char * const rq_flags[] = {
        "REQ_RW",
        "REQ_FAILFAST",
        "REQ_SORTED",
        "REQ_SOFTBARRIER",
        "REQ_HARDBARRIER",
        "REQ_FUA",
        "REQ_CMD",
        "REQ_NOMERGE",
        "REQ_STARTED",
        "REQ_DONTPREP",
        "REQ_QUEUED",
        "REQ_ELVPRIV",
        "REQ_PC",
        "REQ_BLOCK_PC",
        "REQ_SENSE",
        "REQ_FAILED",
        "REQ_QUIET",
        "REQ_SPECIAL",
        "REQ_DRIVE_CMD",
        "REQ_DRIVE_TASK",
        "REQ_DRIVE_TASKFILE",
        "REQ_PREEMPT",
        "REQ_PM_SUSPEND",
        "REQ_PM_RESUME",
        "REQ_PM_SHUTDOWN",
        "REQ_ORDERED_COLOR",
};

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

        printk("%s: dev %s: flags = ", msg,
                rq->rq_disk ? rq->rq_disk->disk_name : "?");
        bit = 0;
        do {
                if (rq->flags & (1 << bit))
                        printk("%s ", rq_flags[bit]);
                bit++;
        } while (bit < __REQ_NR_BITS);

        printk("\nsector %llu, nr/cnr %lu/%u\n", (unsigned long long)rq->sector,
                                                       rq->nr_sectors,
                                                       rq->current_nr_sectors);
        printk("bio %p, biotail %p, buffer %p, data %p, len %u\n", rq->bio, rq->biotail, rq->buffer, rq->data, rq->data_len);

        if (rq->flags & (REQ_BLOCK_PC | REQ_PC)) {
                printk("cdb: ");
                for (bit = 0; bit < sizeof(rq->cmd); bit++)
                        printk("%02x ", rq->cmd[bit]);
                printk("\n");
        }
}

EXPORT_SYMBOL(blk_dump_rq_flags);

void blk_recount_segments(request_queue_t *q, struct bio *bio)
{
        struct bio_vec *bv, *bvprv = NULL;
        int i, nr_phys_segs, nr_hw_segs, seg_size, hw_seg_size, cluster;
        int high, highprv = 1;

        if (unlikely(!bio->bi_io_vec))
                return;

        cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
        hw_seg_size = seg_size = nr_phys_segs = nr_hw_segs = 0;
        bio_for_each_segment(bv, bio, i) {
                /*
                 * the trick here is making sure that a high page is never
                 * considered part of another segment, since that might
                 * change with the bounce page.
                 */
                high = page_to_pfn(bv->bv_page) >= q->bounce_pfn;
                if (high || highprv)
                        goto new_hw_segment;
                if (cluster) {
                        if (seg_size + bv->bv_len > q->max_segment_size)
                                goto new_segment;
                        if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
                                goto new_segment;
                        if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
                                goto new_segment;
                        if (BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len))
                                goto new_hw_segment;

                        seg_size += bv->bv_len;
                        hw_seg_size += bv->bv_len;
                        bvprv = bv;
                        continue;
                }
new_segment:
                if (BIOVEC_VIRT_MERGEABLE(bvprv, bv) &&
                    !BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len)) {
                        hw_seg_size += bv->bv_len;
                } else {
new_hw_segment:
                        if (hw_seg_size > bio->bi_hw_front_size)
                                bio->bi_hw_front_size = hw_seg_size;
                        hw_seg_size = BIOVEC_VIRT_START_SIZE(bv) + bv->bv_len;
                        nr_hw_segs++;
                }

                nr_phys_segs++;
                bvprv = bv;
                seg_size = bv->bv_len;
                highprv = high;
        }
        if (hw_seg_size > bio->bi_hw_back_size)
                bio->bi_hw_back_size = hw_seg_size;
        if (nr_hw_segs == 1 && hw_seg_size > bio->bi_hw_front_size)
                bio->bi_hw_front_size = hw_seg_size;
        bio->bi_phys_segments = nr_phys_segs;
        bio->bi_hw_segments = nr_hw_segs;
        bio->bi_flags |= (1 << BIO_SEG_VALID);
}


static int blk_phys_contig_segment(request_queue_t *q, struct bio *bio,
                                   struct bio *nxt)
{
        if (!(q->queue_flags & (1 << QUEUE_FLAG_CLUSTER)))
                return 0;

        if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
                return 0;
        if (bio->bi_size + nxt->bi_size > q->max_segment_size)
                return 0;

        /*
         * bio and nxt are contigous in memory, check if the queue allows
         * these two to be merged into one
         */
        if (BIO_SEG_BOUNDARY(q, bio, nxt))
                return 1;

        return 0;
}

static int blk_hw_contig_segment(request_queue_t *q, struct bio *bio,
                                 struct bio *nxt)
{
        if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
                blk_recount_segments(q, bio);
        if (unlikely(!bio_flagged(nxt, BIO_SEG_VALID)))
                blk_recount_segments(q, nxt);
        if (!BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)) ||
            BIOVEC_VIRT_OVERSIZE(bio->bi_hw_front_size + bio->bi_hw_back_size))
                return 0;
        if (bio->bi_size + nxt->bi_size > q->max_segment_size)
                return 0;

        return 1;
}

/*
 * map a request to scatterlist, return number of sg entries setup. Caller
 * must make sure sg can hold rq->nr_phys_segments entries
 */
int blk_rq_map_sg(request_queue_t *q, struct request *rq, struct scatterlist *sg)
{
        struct bio_vec *bvec, *bvprv;
        struct bio *bio;
        int nsegs, i, cluster;

        nsegs = 0;
        cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);

        /*
         * for each bio in rq
         */
        bvprv = NULL;
        rq_for_each_bio(bio, rq) {
                /*
                 * for each segment in bio
                 */
                bio_for_each_segment(bvec, bio, i) {
                        int nbytes = bvec->bv_len;

                        if (bvprv && cluster) {
                                if (sg[nsegs - 1].length + nbytes > q->max_segment_size)
                                        goto new_segment;

                                if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
                                        goto new_segment;
                                if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
                                        goto new_segment;

                                sg[nsegs - 1].length += nbytes;
                        } else {
new_segment:
                                memset(&sg[nsegs],0,sizeof(struct scatterlist));
                                sg[nsegs].page = bvec->bv_page;
                                sg[nsegs].length = nbytes;
                                sg[nsegs].offset = bvec->bv_offset;

                                nsegs++;
                        }
                        bvprv = bvec;
                } /* segments in bio */
        } /* bios in rq */

        return nsegs;
}

EXPORT_SYMBOL(blk_rq_map_sg);

/*
 * the standard queue merge functions, can be overridden with device
 * specific ones if so desired
 */

static inline int ll_new_mergeable(request_queue_t *q,
                                   struct request *req,
                                   struct bio *bio)
{
        int nr_phys_segs = bio_phys_segments(q, bio);

        if (req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
                req->flags |= REQ_NOMERGE;
                if (req == q->last_merge)
                        q->last_merge = NULL;
                return 0;
        }

        /*
         * A hw segment is just getting larger, bump just the phys
         * counter.
         */
        req->nr_phys_segments += nr_phys_segs;
        return 1;
}

static inline int ll_new_hw_segment(request_queue_t *q,
                                    struct request *req,
                                    struct bio *bio)
{
        int nr_hw_segs = bio_hw_segments(q, bio);
        int nr_phys_segs = bio_phys_segments(q, bio);

        if (req->nr_hw_segments + nr_hw_segs > q->max_hw_segments
            || req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
                req->flags |= REQ_NOMERGE;
                if (req == q->last_merge)
                        q->last_merge = NULL;
                return 0;
        }

        /*
         * This will form the start of a new hw segment.  Bump both
         * counters.
         */
        req->nr_hw_segments += nr_hw_segs;
        req->nr_phys_segments += nr_phys_segs;
        return 1;
}

static int ll_back_merge_fn(request_queue_t *q, struct request *req, 
                            struct bio *bio)
{
        unsigned short max_sectors;
        int len;

        if (unlikely(blk_pc_request(req)))
                max_sectors = q->max_hw_sectors;
        else
                max_sectors = q->max_sectors;

        if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
                req->flags |= REQ_NOMERGE;
                if (req == q->last_merge)
                        q->last_merge = NULL;
                return 0;
        }
        if (unlikely(!bio_flagged(req->biotail, BIO_SEG_VALID)))
                blk_recount_segments(q, req->biotail);
        if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
                blk_recount_segments(q, bio);
        len = req->biotail->bi_hw_back_size + bio->bi_hw_front_size;
        if (BIOVEC_VIRT_MERGEABLE(__BVEC_END(req->biotail), __BVEC_START(bio)) &&
            !BIOVEC_VIRT_OVERSIZE(len)) {
                int mergeable =  ll_new_mergeable(q, req, bio);

                if (mergeable) {
                        if (req->nr_hw_segments == 1)
                                req->bio->bi_hw_front_size = len;
                        if (bio->bi_hw_segments == 1)
                                bio->bi_hw_back_size = len;
                }
                return mergeable;
        }

        return ll_new_hw_segment(q, req, bio);
}

static int ll_front_merge_fn(request_queue_t *q, struct request *req, 
                             struct bio *bio)
{
        unsigned short max_sectors;
        int len;

        if (unlikely(blk_pc_request(req)))
                max_sectors = q->max_hw_sectors;
        else
                max_sectors = q->max_sectors;


        if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
                req->flags |= REQ_NOMERGE;
                if (req == q->last_merge)
                        q->last_merge = NULL;
                return 0;
        }
        len = bio->bi_hw_back_size + req->bio->bi_hw_front_size;
        if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
                blk_recount_segments(q, bio);
        if (unlikely(!bio_flagged(req->bio, BIO_SEG_VALID)))
                blk_recount_segments(q, req->bio);
        if (BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(req->bio)) &&
            !BIOVEC_VIRT_OVERSIZE(len)) {
                int mergeable =  ll_new_mergeable(q, req, bio);

                if (mergeable) {
                        if (bio->bi_hw_segments == 1)
                                bio->bi_hw_front_size = len;
                        if (req->nr_hw_segments == 1)
                                req->biotail->bi_hw_back_size = len;
                }
                return mergeable;
        }

        return ll_new_hw_segment(q, req, bio);
}

static int ll_merge_requests_fn(request_queue_t *q, struct request *req,
                                struct request *next)
{
        int total_phys_segments;
        int total_hw_segments;

        /*
         * First check if the either of the requests are re-queued
         * requests.  Can't merge them if they are.
         */
        if (req->special || next->special)
                return 0;

        /*
         * Will it become too large?
         */
        if ((req->nr_sectors + next->nr_sectors) > q->max_sectors)
                return 0;

        total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
        if (blk_phys_contig_segment(q, req->biotail, next->bio))
                total_phys_segments--;

        if (total_phys_segments > q->max_phys_segments)
                return 0;

        total_hw_segments = req->nr_hw_segments + next->nr_hw_segments;
        if (blk_hw_contig_segment(q, req->biotail, next->bio)) {
                int len = req->biotail->bi_hw_back_size + next->bio->bi_hw_front_size;
                /*
                 * propagate the combined length to the end of the requests
                 */
                if (req->nr_hw_segments == 1)
                        req->bio->bi_hw_front_size = len;
                if (next->nr_hw_segments == 1)
                        next->biotail->bi_hw_back_size = len;
                total_hw_segments--;
        }

        if (total_hw_segments > q->max_hw_segments)
                return 0;

        /* Merge is OK... */
        req->nr_phys_segments = total_phys_segments;
        req->nr_hw_segments = total_hw_segments;
        return 1;
}

/*
 * "plug" the device if there are no outstanding requests: this will
 * force the transfer to start only after we have put all the requests
 * on the list.
 *
 * This is called with interrupts off and no requests on the queue and
 * with the queue lock held.
 */
void blk_plug_device(request_queue_t *q)
{
        WARN_ON(!irqs_disabled());

        /*
         * don't plug a stopped queue, it must be paired with blk_start_queue()
         * which will restart the queueing
         */
        if (blk_queue_stopped(q))
                return;

        if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
                mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
                blk_add_trace_generic(q, NULL, 0, BLK_TA_PLUG);
        }
}

EXPORT_SYMBOL(blk_plug_device);

/*
 * remove the queue from the plugged list, if present. called with
 * queue lock held and interrupts disabled.
 */
int blk_remove_plug(request_queue_t *q)
{
        WARN_ON(!irqs_disabled());

        if (!test_and_clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
                return 0;

        del_timer(&q->unplug_timer);
        return 1;
}

EXPORT_SYMBOL(blk_remove_plug);

/*
 * remove the plug and let it rip..
 */
void __generic_unplug_device(request_queue_t *q)
{
        if (unlikely(blk_queue_stopped(q)))
                return;

        if (!blk_remove_plug(q))
                return;

        q->request_fn(q);
}
EXPORT_SYMBOL(__generic_unplug_device);

/**
 * generic_unplug_device - fire a request queue
 * @q:    The &request_queue_t in question
 *
 * Description:
 *   Linux uses plugging to build bigger requests queues before letting
 *   the device have at them. If a queue is plugged, the I/O scheduler
 *   is still adding and merging requests on the queue. Once the queue
 *   gets unplugged, the request_fn defined for the queue is invoked and
 *   transfers started.
 **/
void generic_unplug_device(request_queue_t *q)
{
        spin_lock_irq(q->queue_lock);
        __generic_unplug_device(q);
        spin_unlock_irq(q->queue_lock);
}
EXPORT_SYMBOL(generic_unplug_device);

static void blk_backing_dev_unplug(struct backing_dev_info *bdi,
                                   struct page *page)
{
        request_queue_t *q = bdi->unplug_io_data;

        /*
         * devices don't necessarily have an ->unplug_fn defined
         */
        if (q->unplug_fn) {
                blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
                                        q->rq.count[READ] + q->rq.count[WRITE]);

                q->unplug_fn(q);
        }
}

static void blk_unplug_work(void *data)
{
        request_queue_t *q = data;

        blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
                                q->rq.count[READ] + q->rq.count[WRITE]);

        q->unplug_fn(q);
}

static void blk_unplug_timeout(unsigned long data)
{
        request_queue_t *q = (request_queue_t *)data;

        blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_TIMER, NULL,
                                q->rq.count[READ] + q->rq.count[WRITE]);

        kblockd_schedule_work(&q->unplug_work);
}

/**
 * blk_start_queue - restart a previously stopped queue
 * @q:    The &request_queue_t 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(request_queue_t *q)
{
        WARN_ON(!irqs_disabled());

        clear_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);

        /*
         * one level of recursion is ok and is much faster than kicking
         * the unplug handling
         */
        if (!test_and_set_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
                q->request_fn(q);
                clear_bit(QUEUE_FLAG_REENTER, &q->queue_flags);
        } else {
                blk_plug_device(q);
                kblockd_schedule_work(&q->unplug_work);
        }
}

EXPORT_SYMBOL(blk_start_queue);

/**
 * blk_stop_queue - stop a queue
 * @q:    The &request_queue_t 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(request_queue_t *q)
{
        blk_remove_plug(q);
        set_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
}
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
 *     the 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.
 *
 */
void blk_sync_queue(struct request_queue *q)
{
        del_timer_sync(&q->unplug_timer);
        kblockd_flush();
}
EXPORT_SYMBOL(blk_sync_queue);

/**
 * blk_run_queue - run a single device queue
 * @q:  The queue to run
 */
void blk_run_queue(struct request_queue *q)
{
        unsigned long flags;

        spin_lock_irqsave(q->queue_lock, flags);
        blk_remove_plug(q);

        /*
         * Only recurse once to avoid overrunning the stack, let the unplug
         * handling reinvoke the handler shortly if we already got there.
         */
        if (!elv_queue_empty(q)) {
                if (!test_and_set_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
                        q->request_fn(q);
                        clear_bit(QUEUE_FLAG_REENTER, &q->queue_flags);
                } else {
                        blk_plug_device(q);
                        kblockd_schedule_work(&q->unplug_work);
                }
        }

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

/**
 * blk_cleanup_queue: - release a &request_queue_t when it is no longer needed
 * @kobj:    the kobj belonging of the request queue to be released
 *
 * Description:
 *     blk_cleanup_queue is the pair to blk_init_queue() or
 *     blk_queue_make_request().  It should be called when a request queue is
 *     being released; typically when a block device is being de-registered.
 *     Currently, its primary task it to free all the &struct request
 *     structures that were allocated to the queue and the queue itself.
 *
 * Caveat:
 *     Hopefully the low level driver will have finished any
 *     outstanding requests first...
 **/
static void blk_release_queue(struct kobject *kobj)
{
        request_queue_t *q = container_of(kobj, struct request_queue, kobj);
        struct request_list *rl = &q->rq;

        blk_sync_queue(q);

        if (rl->rq_pool)
                mempool_destroy(rl->rq_pool);

        if (q->queue_tags)
                __blk_queue_free_tags(q);

        if (q->blk_trace)
                blk_trace_shutdown(q);

        kmem_cache_free(requestq_cachep, q);
}

void blk_put_queue(request_queue_t *q)
{
        kobject_put(&q->kobj);
}
EXPORT_SYMBOL(blk_put_queue);

void blk_cleanup_queue(request_queue_t * q)
{
        mutex_lock(&q->sysfs_lock);
        set_bit(QUEUE_FLAG_DEAD, &q->queue_flags);
        mutex_unlock(&q->sysfs_lock);

        if (q->elevator)
                elevator_exit(q->elevator);

        blk_put_queue(q);
}

EXPORT_SYMBOL(blk_cleanup_queue);

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

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

        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;
}

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

static struct kobj_type queue_ktype;

request_queue_t *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
        request_queue_t *q;

        q = kmem_cache_alloc_node(requestq_cachep, gfp_mask, node_id);
        if (!q)
                return NULL;

        memset(q, 0, sizeof(*q));
        init_timer(&q->unplug_timer);

        snprintf(q->kobj.name, KOBJ_NAME_LEN, "%s", "queue");
        q->kobj.ktype = &queue_ktype;
        kobject_init(&q->kobj);

        q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
        q->backing_dev_info.unplug_io_data = q;

        mutex_init(&q->sysfs_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).
 **/

request_queue_t *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
{
        return blk_init_queue_node(rfn, lock, -1);
}
EXPORT_SYMBOL(blk_init_queue);

request_queue_t *
blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
{
        request_queue_t *q = blk_alloc_queue_node(GFP_KERNEL, node_id);

        if (!q)
                return NULL;

        q->node = node_id;
        if (blk_init_free_list(q)) {
                kmem_cache_free(requestq_cachep, q);
                return NULL;
        }

        /*
         * if caller didn't supply a lock, they get per-queue locking with
         * our embedded lock
         */
        if (!lock) {
                spin_lock_init(&q->__queue_lock);
                lock = &q->__queue_lock;
        }

        q->request_fn           = rfn;
        q->back_merge_fn        = ll_back_merge_fn;
        q->front_merge_fn       = ll_front_merge_fn;
        q->merge_requests_fn    = ll_merge_requests_fn;
        q->prep_rq_fn           = NULL;
        q->unplug_fn            = generic_unplug_device;
        q->queue_flags          = (1 << QUEUE_FLAG_CLUSTER);
        q->queue_lock           = lock;

        blk_queue_segment_boundary(q, 0xffffffff);

        blk_queue_make_request(q, __make_request);
        blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);

        blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
        blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);

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

        blk_put_queue(q);
        return NULL;
}
EXPORT_SYMBOL(blk_init_queue_node);

int blk_get_queue(request_queue_t *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(request_queue_t *q, struct request *rq)
{
        if (rq->flags & REQ_ELVPRIV)
                elv_put_request(q, rq);
        mempool_free(rq, q->rq.rq_pool);
}

static inline struct request *
blk_alloc_request(request_queue_t *q, int rw, struct bio *bio,
                  int priv, gfp_t gfp_mask)
{
        struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);

        if (!rq)
                return NULL;

        /*
         * first three bits are identical in rq->flags and bio->bi_rw,
         * see bio.h and blkdev.h
         */
        rq->flags = rw;

        if (priv) {
                if (unlikely(elv_set_request(q, rq, bio, gfp_mask))) {
                        mempool_free(rq, q->rq.rq_pool);
                        return NULL;
                }
                rq->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(request_queue_t *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(request_queue_t *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(request_queue_t *q, int rw)
{
        struct request_list *rl = &q->rq;

        if (rl->count[rw] < queue_congestion_off_threshold(q))
                clear_queue_congested(q, rw);

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

                blk_clear_queue_full(q, rw);
        }
}

/*
 * 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(request_queue_t *q, int rw, int priv)
{
        struct request_list *rl = &q->rq;

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

        __freed_request(q, rw);

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

#define blkdev_free_rq(list) list_entry((list)->next, struct request, queuelist)
/*
 * 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(request_queue_t *q, int rw, struct bio *bio,
                                   gfp_t gfp_mask)
{
        struct request *rq = NULL;
        struct request_list *rl = &q->rq;
        struct io_context *ioc = NULL;
        int may_queue, priv;

        may_queue = elv_may_queue(q, rw, bio);
        if (may_queue == ELV_MQUEUE_NO)
                goto rq_starved;

        if (rl->count[rw]+1 >= queue_congestion_on_threshold(q)) {
                if (rl->count[rw]+1 >= q->nr_requests) {
                        ioc = current_io_context(GFP_ATOMIC);
                        /*
                         * 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, rw)) {
                                ioc_set_batching(q, ioc);
                                blk_set_queue_full(q, rw);
                        } 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;
                                }
                        }
                }
                set_queue_congested(q, rw);
        }

        /*
         * 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[rw] >= (3 * q->nr_requests / 2))
                goto out;

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

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

        spin_unlock_irq(q->queue_lock);

        rq = blk_alloc_request(q, rw, bio, 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, rw, 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[rw] == 0))
                        rl->starved[rw] = 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--;
        
        rq_init(q, rq);
        rq->rl = rl;

        blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ);
out:
        return rq;
}

/*
 * No available requests for this queue, unplug the device and wait for some
 * requests to become available.
 *
 * Called with q->queue_lock held, and returns with it unlocked.
 */
static struct request *get_request_wait(request_queue_t *q, int rw,
                                        struct bio *bio)
{
        struct request *rq;

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

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

                rq = get_request(q, rw, bio, GFP_NOIO);

                if (!rq) {
                        struct io_context *ioc;

                        blk_add_trace_generic(q, bio, rw, BLK_TA_SLEEPRQ);

                        __generic_unplug_device(q);
                        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);
                        ioc_set_batching(q, ioc);

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

        return rq;
}

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

        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_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(request_queue_t *q, struct request *rq)
{
        blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);

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

        elv_requeue_request(q, rq);
}

EXPORT_SYMBOL(blk_requeue_request);

/**
 * blk_insert_request - insert a special request in to 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_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(request_queue_t *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->flags |= REQ_SPECIAL | REQ_SOFTBARRIER;

        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);

        drive_stat_acct(rq, rq->nr_sectors, 1);
        __elv_add_request(q, rq, where, 0);

        if (blk_queue_plugged(q))
                __generic_unplug_device(q);
        else
                q->request_fn(q);
        spin_unlock_irqrestore(q->queue_lock, flags);
}

EXPORT_SYMBOL(blk_insert_request);

/**
 * blk_rq_map_user - map user data to a request, for REQ_BLOCK_PC usage
 * @q:          request queue where request should be inserted
 * @rq:         request structure to fill
 * @ubuf:       the user buffer
 * @len:        length of user data
 *
 * Description:
 *    Data will be mapped directly for zero copy io, if possible. Otherwise
 *    a kernel bounce buffer is used.
 *
 *    A matching blk_rq_unmap_user() must be issued at the end of io, while
 *    still in process context.
 *
 *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
 *    before being submitted to the device, as pages mapped may be out of
 *    reach. It's the callers responsibility to make sure this happens. The
 *    original bio must be passed back in to blk_rq_unmap_user() for proper
 *    unmapping.
 */
int blk_rq_map_user(request_queue_t *q, struct request *rq, void __user *ubuf,
                    unsigned int len)
{
        unsigned long uaddr;
        struct bio *bio;
        int reading;

        if (len > (q->max_hw_sectors << 9))
                return -EINVAL;
        if (!len || !ubuf)
                return -EINVAL;

        reading = rq_data_dir(rq) == READ;

        /*
         * if alignment requirement is satisfied, map in user pages for
         * direct dma. else, set up kernel bounce buffers
         */
        uaddr = (unsigned long) ubuf;
        if (!(uaddr & queue_dma_alignment(q)) && !(len & queue_dma_alignment(q)))
                bio = bio_map_user(q, NULL, uaddr, len, reading);
        else
                bio = bio_copy_user(q, uaddr, len, reading);

        if (!IS_ERR(bio)) {
                rq->bio = rq->biotail = bio;
                blk_rq_bio_prep(q, rq, bio);

                rq->buffer = rq->data = NULL;
                rq->data_len = len;
                return 0;
        }

        /*
         * bio is the err-ptr
         */
        return PTR_ERR(bio);
}

EXPORT_SYMBOL(blk_rq_map_user);

/**
 * blk_rq_map_user_iov - map user data to a request, for REQ_BLOCK_PC usage
 * @q:          request queue where request should be inserted
 * @rq:         request to map data to
 * @iov:        pointer to the iovec
 * @iov_count:  number of elements in the iovec
 *
 * Description:
 *    Data will be mapped directly for zero copy io, if possible. Otherwise
 *    a kernel bounce buffer is used.
 *
 *    A matching blk_rq_unmap_user() must be issued at the end of io, while
 *    still in process context.
 *
 *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
 *    before being submitted to the device, as pages mapped may be out of
 *    reach. It's the callers responsibility to make sure this happens. The
 *    original bio must be passed back in to blk_rq_unmap_user() for proper
 *    unmapping.
 */
int blk_rq_map_user_iov(request_queue_t *q, struct request *rq,
                        struct sg_iovec *iov, int iov_count)
{
        struct bio *bio;

        if (!iov || iov_count <= 0)
                return -EINVAL;

        /* we don't allow misaligned data like bio_map_user() does.  If the
         * user is using sg, they're expected to know the alignment constraints
         * and respect them accordingly */
        bio = bio_map_user_iov(q, NULL, iov, iov_count, rq_data_dir(rq)== READ);
        if (IS_ERR(bio))
                return PTR_ERR(bio);

        rq->bio = rq->biotail = bio;
        blk_rq_bio_prep(q, rq, bio);
        rq->buffer = rq->data = NULL;
        rq->data_len = bio->bi_size;
        return 0;
}

EXPORT_SYMBOL(blk_rq_map_user_iov);

/**
 * blk_rq_unmap_user - unmap a request with user data
 * @bio:        bio to be unmapped
 * @ulen:       length of user buffer
 *
 * Description:
 *    Unmap a bio previously mapped by blk_rq_map_user().
 */
int blk_rq_unmap_user(struct bio *bio, unsigned int ulen)
{
        int ret = 0;

        if (bio) {
                if (bio_flagged(bio, BIO_USER_MAPPED))
                        bio_unmap_user(bio);
                else
                        ret = bio_uncopy_user(bio);
        }

        return 0;
}

EXPORT_SYMBOL(blk_rq_unmap_user);

/**
 * blk_rq_map_kern - map kernel data to a request, for REQ_BLOCK_PC usage
 * @q:          request queue where request should be inserted
 * @rq:         request to fill
 * @kbuf:       the kernel buffer
 * @len:        length of user data
 * @gfp_mask:   memory allocation flags
 */
int blk_rq_map_kern(request_queue_t *q, struct request *rq, void *kbuf,
                    unsigned int len, gfp_t gfp_mask)
{
        struct bio *bio;

        if (len > (q->max_hw_sectors << 9))
                return -EINVAL;
        if (!len || !kbuf)
                return -EINVAL;

        bio = bio_map_kern(q, kbuf, len, gfp_mask);
        if (IS_ERR(bio))
                return PTR_ERR(bio);

        if (rq_data_dir(rq) == WRITE)
                bio->bi_rw |= (1 << BIO_RW);

        rq->bio = rq->biotail = bio;
        blk_rq_bio_prep(q, rq, bio);

        rq->buffer = rq->data = NULL;
        rq->data_len = len;
        return 0;
}

EXPORT_SYMBOL(blk_rq_map_kern);

/**
 * blk_execute_rq_nowait - insert a request into queue for execution
 * @q:          queue to insert the request in
 * @bd_disk:    matching gendisk
 * @rq:         request to insert
 * @at_head:    insert request at head or tail of queue
 * @done:       I/O completion handler
 *
 * Description:
 *    Insert a fully prepared request at the back of the io scheduler queue
 *    for execution.  Don't wait for completion.
 */
void blk_execute_rq_nowait(request_queue_t *q, struct gendisk *bd_disk,
                           struct request *rq, int at_head,
                           rq_end_io_fn *done)
{
        int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;

        rq->rq_disk = bd_disk;
        rq->flags |= REQ_NOMERGE;
        rq->end_io = done;
        WARN_ON(irqs_disabled());
        spin_lock_irq(q->queue_lock);
        __elv_add_request(q, rq, where, 1);
        __generic_unplug_device(q);
        spin_unlock_irq(q->queue_lock);
}
EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);

/**
 * blk_execute_rq - insert a request into queue for execution
 * @q:          queue to insert the request in
 * @bd_disk:    matching gendisk
 * @rq:         request to insert
 * @at_head:    insert request at head or tail of queue
 *
 * Description:
 *    Insert a fully prepared request at the back of the io scheduler queue
 *    for execution and wait for completion.
 */
int blk_execute_rq(request_queue_t *q, struct gendisk *bd_disk,
                   struct request *rq, int at_head)
{
        DECLARE_COMPLETION_ONSTACK(wait);
        char sense[SCSI_SENSE_BUFFERSIZE];
        int err = 0;

        /*
         * we need an extra reference to the request, so we can look at
         * it after io completion
         */
        rq->ref_count++;

        if (!rq->sense) {
                memset(sense, 0, sizeof(sense));
                rq->sense = sense;
                rq->sense_len = 0;
        }

        rq->waiting = &wait;
        blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
        wait_for_completion(&wait);
        rq->waiting = NULL;

        if (rq->errors)
                err = -EIO;

        return err;
}

EXPORT_SYMBOL(blk_execute_rq);

/**
 * blkdev_issue_flush - queue a flush
 * @bdev:       blockdev to issue flush for
 * @error_sector:       error sector
 *
 * Description:
 *    Issue a flush for the block device in question. Caller can supply
 *    room for storing the error offset in case of a flush error, if they
 *    wish to.  Caller must run wait_for_completion() on its own.
 */
int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
{
        request_queue_t *q;

        if (bdev->bd_disk == NULL)
                return -ENXIO;

        q = bdev_get_queue(bdev);
        if (!q)
                return -ENXIO;
        if (!q->issue_flush_fn)
                return -EOPNOTSUPP;

        return q->issue_flush_fn(q, bdev->bd_disk, error_sector);
}

EXPORT_SYMBOL(blkdev_issue_flush);

static void drive_stat_acct(struct request *rq, int nr_sectors, int new_io)
{
        int rw = rq_data_dir(rq);

        if (!blk_fs_request(rq) || !rq->rq_disk)
                return;

        if (!new_io) {
                __disk_stat_inc(rq->rq_disk, merges[rw]);
        } else {
                disk_round_stats(rq->rq_disk);
                rq->rq_disk->in_flight++;
        }
}

/*
 * add-request adds a request to the linked list.
 * queue lock is held and interrupts disabled, as we muck with the
 * request queue list.
 */
static inline void add_request(request_queue_t * q, struct request * req)
{
        drive_stat_acct(req, req->nr_sectors, 1);

        if (q->activity_fn)
                q->activity_fn(q->activity_data, rq_data_dir(req));

        /*
         * elevator indicated where it wants this request to be
         * inserted at elevator_merge time
         */
        __elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
}
 
/*
 * disk_round_stats()   - Round off the performance stats on a struct
 * disk_stats.
 *
 * The average IO queue length and utilisation statistics are maintained
 * by observing the current state of the queue length and the amount of
 * time it has been in this state for.
 *
 * Normally, that accounting is done on IO completion, but that can result
 * in more than a second's worth of IO being accounted for within any one
 * second, leading to >100% utilisation.  To deal with that, we call this
 * function to do a round-off before returning the results when reading
 * /proc/diskstats.  This accounts immediately for all queue usage up to
 * the current jiffies and restarts the counters again.
 */
void disk_round_stats(struct gendisk *disk)
{
        unsigned long now = jiffies;

        if (now == disk->stamp)
                return;

        if (disk->in_flight) {
                __disk_stat_add(disk, time_in_queue,
                                disk->in_flight * (now - disk->stamp));
                __disk_stat_add(disk, io_ticks, (now - disk->stamp));
        }
        disk->stamp = now;
}

EXPORT_SYMBOL_GPL(disk_round_stats);

/*
 * queue lock must be held
 */
void __blk_put_request(request_queue_t *q, struct request *req)
{
        struct request_list *rl = req->rl;

        if (unlikely(!q))
                return;
        if (unlikely(--req->ref_count))
                return;

        elv_completed_request(q, req);

        req->rq_status = RQ_INACTIVE;
        req->rl = NULL;

        /*
         * Request may not have originated from ll_rw_blk. if not,
         * it didn't come out of our reserved rq pools
         */
        if (rl) {
                int rw = rq_data_dir(req);
                int priv = req->flags & REQ_ELVPRIV;

                BUG_ON(!list_empty(&req->queuelist));

                blk_free_request(q, req);
                freed_request(q, rw, priv);
        }
}

EXPORT_SYMBOL_GPL(__blk_put_request);

void blk_put_request(struct request *req)
{
        unsigned long flags;
        request_queue_t *q = req->q;

        /*
         * Gee, IDE calls in w/ NULL q.  Fix IDE and remove the
         * following if (q) test.
         */
        if (q) {
                spin_lock_irqsave(q->queue_lock, flags);
                __blk_put_request(q, req);
                spin_unlock_irqrestore(q->queue_lock, flags);
        }
}

EXPORT_SYMBOL(blk_put_request);

/**
 * blk_end_sync_rq - executes a completion event on a request
 * @rq: request to complete
 * @error: end io status of the request
 */
void blk_end_sync_rq(struct request *rq, int error)
{
        struct completion *waiting = rq->waiting;

        rq->waiting = NULL;
        __blk_put_request(rq->q, rq);

        /*
         * complete last, if this is a stack request the process (and thus
         * the rq pointer) could be invalid right after this complete()
         */
        complete(waiting);
}
EXPORT_SYMBOL(blk_end_sync_rq);

/**
 * blk_congestion_wait - wait for a queue to become uncongested
 * @rw: READ or WRITE
 * @timeout: timeout in jiffies
 *
 * Waits for up to @timeout jiffies for a queue (any queue) to exit congestion.
 * If no queues are congested then just wait for the next request to be
 * returned.
 */
long blk_congestion_wait(int rw, long timeout)
{
        long ret;
        DEFINE_WAIT(wait);
        wait_queue_head_t *wqh = &congestion_wqh[rw];

        prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
        ret = io_schedule_timeout(timeout);
        finish_wait(wqh, &wait);
        return ret;
}

EXPORT_SYMBOL(blk_congestion_wait);

/*
 * Has to be called with the request spinlock acquired
 */
static int attempt_merge(request_queue_t *q, struct request *req,
                          struct request *next)
{
        if (!rq_mergeable(req) || !rq_mergeable(next))
                return 0;

        /*
         * not contiguous
         */
        if (req->sector + req->nr_sectors != next->sector)
                return 0;

        if (rq_data_dir(req) != rq_data_dir(next)
            || req->rq_disk != next->rq_disk
            || next->waiting || next->special)
                return 0;

        /*
         * If we are allowed to merge, then append bio list
         * from next to rq and release next. merge_requests_fn
         * will have updated segment counts, update sector
         * counts here.
         */
        if (!q->merge_requests_fn(q, req, next))
                return 0;

        /*
         * At this point we have either done a back merge
         * or front merge. We need the smaller start_time of
         * the merged requests to be the current request
         * for accounting purposes.
         */
        if (time_after(req->start_time, next->start_time))
                req->start_time = next->start_time;

        req->biotail->bi_next = next->bio;
        req->biotail = next->biotail;

        req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;

        elv_merge_requests(q, req, next);

        if (req->rq_disk) {
                disk_round_stats(req->rq_disk);
                req->rq_disk->in_flight--;
        }

        req->ioprio = ioprio_best(req->ioprio, next->ioprio);

        __blk_put_request(q, next);
        return 1;
}

static inline int attempt_back_merge(request_queue_t *q, struct request *rq)
{
        struct request *next = elv_latter_request(q, rq);

        if (next)
                return attempt_merge(q, rq, next);

        return 0;
}

static inline int attempt_front_merge(request_queue_t *q, struct request *rq)
{
        struct request *prev = elv_former_request(q, rq);

        if (prev)
                return attempt_merge(q, prev, rq);

        return 0;
}

static void init_request_from_bio(struct request *req, struct bio *bio)
{
        req->flags |= REQ_CMD;

        /*
         * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
         */
        if (bio_rw_ahead(bio) || bio_failfast(bio))
                req->flags |= REQ_FAILFAST;

        /*
         * REQ_BARRIER implies no merging, but lets make it explicit
         */
        if (unlikely(bio_barrier(bio)))
                req->flags |= (REQ_HARDBARRIER | REQ_NOMERGE);

        if (bio_sync(bio))
                req->flags |= REQ_RW_SYNC;

        req->errors = 0;
        req->hard_sector = req->sector = bio->bi_sector;
        req->hard_nr_sectors = req->nr_sectors = bio_sectors(bio);
        req->current_nr_sectors = req->hard_cur_sectors = bio_cur_sectors(bio);
        req->nr_phys_segments = bio_phys_segments(req->q, bio);
        req->nr_hw_segments = bio_hw_segments(req->q, bio);
        req->buffer = bio_data(bio);    /* see ->buffer comment above */
        req->waiting = NULL;
        req->bio = req->biotail = bio;
        req->ioprio = bio_prio(bio);
        req->rq_disk = bio->bi_bdev->bd_disk;
        req->start_time = jiffies;
}

static int __make_request(request_queue_t *q, struct bio *bio)
{
        struct request *req;
        int el_ret, rw, nr_sectors, cur_nr_sectors, barrier, err, sync;
        unsigned short prio;
        sector_t sector;

        sector = bio->bi_sector;
        nr_sectors = bio_sectors(bio);
        cur_nr_sectors = bio_cur_sectors(bio);
        prio = bio_prio(bio);

        rw = bio_data_dir(bio);
        sync = bio_sync(bio);

        /*
         * low level driver can indicate that it wants pages above a
         * certain limit bounced to low memory (ie for highmem, or even
         * ISA dma in theory)
         */
        blk_queue_bounce(q, &bio);

        spin_lock_prefetch(q->queue_lock);

        barrier = bio_barrier(bio);
        if (unlikely(barrier) && (q->next_ordered == QUEUE_ORDERED_NONE)) {
                err = -EOPNOTSUPP;
                goto end_io;
        }

        spin_lock_irq(q->queue_lock);

        if (unlikely(barrier) || elv_queue_empty(q))
                goto get_rq;

        el_ret = elv_merge(q, &req, bio);
        switch (el_ret) {
                case ELEVATOR_BACK_MERGE:
                        BUG_ON(!rq_mergeable(req));

                        if (!q->back_merge_fn(q, req, bio))
                                break;

                        blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);

                        req->biotail->bi_next = bio;
                        req->biotail = bio;
                        req->nr_sectors = req->hard_nr_sectors += nr_sectors;
                        req->ioprio = ioprio_best(req->ioprio, prio);
                        drive_stat_acct(req, nr_sectors, 0);
                        if (!attempt_back_merge(q, req))
                                elv_merged_request(q, req);
                        goto out;

                case ELEVATOR_FRONT_MERGE:
                        BUG_ON(!rq_mergeable(req));

                        if (!q->front_merge_fn(q, req, bio))
                                break;

                        blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);

                        bio->bi_next = req->bio;
                        req->bio = bio;

                        /*
                         * may not be valid. if the low level driver said
                         * it didn't need a bounce buffer then it better
                         * not touch req->buffer either...
                         */
                        req->buffer = bio_data(bio);
                        req->current_nr_sectors = cur_nr_sectors;
                        req->hard_cur_sectors = cur_nr_sectors;
                        req->sector = req->hard_sector = sector;
                        req->nr_sectors = req->hard_nr_sectors += nr_sectors;
                        req->ioprio = ioprio_best(req->ioprio, prio);
                        drive_stat_acct(req, nr_sectors, 0);
                        if (!attempt_front_merge(q, req))
                                elv_merged_request(q, req);
                        goto out;

                /* ELV_NO_MERGE: elevator says don't/can't merge. */
                default:
                        ;
        }

get_rq:
        /*
         * Grab a free request. This is might sleep but can not fail.
         * Returns with the queue unlocked.
         */
        req = get_request_wait(q, rw, bio);

        /*
         * After dropping the lock and possibly sleeping here, our request
         * may now be mergeable after it had proven unmergeable (above).
         * We don't worry about that case for efficiency. It won't happen
         * often, and the elevators are able to handle it.
         */
        init_request_from_bio(req, bio);

        spin_lock_irq(q->queue_lock);
        if (elv_queue_empty(q))
                blk_plug_device(q);
        add_request(q, req);
out:
        if (sync)
                __generic_unplug_device(q);

        spin_unlock_irq(q->queue_lock);
        return 0;

end_io:
        bio_endio(bio, nr_sectors << 9, err);
        return 0;
}

/*
 * If bio->bi_dev is a partition, remap the location
 */
static inline void blk_partition_remap(struct bio *bio)
{
        struct block_device *bdev = bio->bi_bdev;

        if (bdev != bdev->bd_contains) {
                struct hd_struct *p = bdev->bd_part;
                const int rw = bio_data_dir(bio);

                p->sectors[rw] += bio_sectors(bio);
                p->ios[rw]++;

                bio->bi_sector += p->start_sect;
                bio->bi_bdev = bdev->bd_contains;
        }
}

static void handle_bad_sector(struct bio *bio)
{
        char b[BDEVNAME_SIZE];

        printk(KERN_INFO "attempt to access beyond end of device\n");
        printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
                        bdevname(bio->bi_bdev, b),
                        bio->bi_rw,
                        (unsigned long long)bio->bi_sector + bio_sectors(bio),
                        (long long)(bio->bi_bdev->bd_inode->i_size >> 9));

        set_bit(BIO_EOF, &bio->bi_flags);
}

/**
 * generic_make_request: hand a buffer to its device driver for I/O
 * @bio:  The bio describing the location in memory and on the device.
 *
 * generic_make_request() is used to make I/O requests of block