blob: 8b919940b2abdb37119cd9927b6f45dbec66aa31 [file] [log] [blame]
/*
* 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/task_io_accounting_ops.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/blktrace_api.h>
#include <linux/fault-inject.h>
#include <linux/scatterlist.h>
/*
* for max sense size
*/
#include <scsi/scsi_cmnd.h>
static void blk_unplug_work(struct work_struct *work);
static void blk_unplug_timeout(unsigned long data);
static void drive_stat_acct(struct request *rq, int new_io);
static void init_request_from_bio(struct request *req, struct bio *bio);
static int __make_request(struct request_queue *q, struct bio *bio);
static struct io_context *current_io_context(gfp_t gfp_flags, int node);
static void blk_recalc_rq_segments(struct request *rq);
static void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio);
/*
* For the allocated request tables
*/
static struct kmem_cache *request_cachep;
/*
* For queue allocation
*/
static struct kmem_cache *requestq_cachep;
/*
* For io context allocations
*/
static struct kmem_cache *iocontext_cachep;
/*
* 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;
}
/**
* blk_get_backing_dev_info - get the address of a queue's backing_dev_info
* @bdev: device
*
* Locates the passed device's request queue and returns the address of its
* backing_dev_info
*
* Will return NULL if the request queue cannot be located.
*/
struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
{
struct backing_dev_info *ret = NULL;
struct request_queue *q = bdev_get_queue(bdev);
if (q)
ret = &q->backing_dev_info;
return ret;
}
EXPORT_SYMBOL(blk_get_backing_dev_info);
/**
* 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(struct request_queue *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(struct request_queue *q, merge_bvec_fn *mbfn)
{
q->merge_bvec_fn = mbfn;
}
EXPORT_SYMBOL(blk_queue_merge_bvec);
void blk_queue_softirq_done(struct request_queue *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(struct request_queue * 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->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);
}
EXPORT_SYMBOL(blk_queue_make_request);
static void rq_init(struct request_queue *q, struct request *rq)
{
INIT_LIST_HEAD(&rq->queuelist);
INIT_LIST_HEAD(&rq->donelist);
rq->errors = 0;
rq->bio = rq->biotail = NULL;
INIT_HLIST_NODE(&rq->hash);
RB_CLEAR_NODE(&rq->rb_node);
rq->ioprio = 0;
rq->buffer = NULL;
rq->ref_count = 1;
rq->q = q;
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;
rq->next_rq = 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(struct request_queue *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);
/*
* Cache flushing for ordered writes handling
*/
inline unsigned blk_ordered_cur_seq(struct request_queue *q)
{
if (!q->ordseq)
return 0;
return 1 << ffz(q->ordseq);
}
unsigned blk_ordered_req_seq(struct request *rq)
{
struct request_queue *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;
/*
* !fs requests don't need to follow barrier ordering. Always
* put them at the front. This fixes the following deadlock.
*
* http://thread.gmane.org/gmane.linux.kernel/537473
*/
if (!blk_fs_request(rq))
return QUEUE_ORDSEQ_DRAIN;
if ((rq->cmd_flags & REQ_ORDERED_COLOR) ==
(q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR))
return QUEUE_ORDSEQ_DRAIN;
else
return QUEUE_ORDSEQ_DONE;
}
void blk_ordered_complete_seq(struct request_queue *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.
*/
uptodate = 1;
if (q->orderr)
uptodate = q->orderr;
q->ordseq = 0;
rq = q->orig_bar_rq;
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(struct request_queue *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->cmd_flags = REQ_HARDBARRIER;
rq_init(q, rq);
rq->elevator_private = NULL;
rq->elevator_private2 = NULL;
rq->rq_disk = q->bar_rq.rq_disk;
rq->end_io = end_io;
q->prepare_flush_fn(q, rq);
elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
}
static inline struct request *start_ordered(struct request_queue *q,
struct request *rq)
{
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->cmd_flags = 0;
rq_init(q, rq);
if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
rq->cmd_flags |= REQ_RW;
if (q->ordered & QUEUE_ORDERED_FUA)
rq->cmd_flags |= REQ_FUA;
rq->elevator_private = NULL;
rq->elevator_private2 = 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 this request is
* an empty barrier, we don't need to do a postflush ever since
* there will be no data written between the pre and post flush.
* Hence a single flush will suffice.
*/
if ((q->ordered & QUEUE_ORDERED_POSTFLUSH) && !blk_empty_barrier(rq))
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(struct request_queue *q, struct request **rqp)
{
struct request *rq = *rqp;
const 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 void req_bio_endio(struct request *rq, struct bio *bio,
unsigned int nbytes, int error)
{
struct request_queue *q = rq->q;
if (&q->bar_rq != rq) {
if (error)
clear_bit(BIO_UPTODATE, &bio->bi_flags);
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
error = -EIO;
if (unlikely(nbytes > bio->bi_size)) {
printk("%s: want %u bytes done, only %u left\n",
__FUNCTION__, nbytes, bio->bi_size);
nbytes = bio->bi_size;
}
bio->bi_size -= nbytes;
bio->bi_sector += (nbytes >> 9);
if (bio->bi_size == 0)
bio_endio(bio, error);
} else {
/*
* Okay, this is the barrier request in progress, just
* record the error;
*/
if (error && !q->orderr)
q->orderr = error;
}
}
/**
* 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(struct request_queue *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(struct request_queue *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(struct request_queue *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(struct request_queue *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(struct request_queue *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(struct request_queue *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(struct request_queue *t, struct request_queue *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(struct request_queue *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(struct request_queue *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(struct request_queue *q, int tag)
{
return blk_map_queue_find_tag(q->queue_tags, tag);
}
EXPORT_SYMBOL(blk_queue_find_tag);
/**
* __blk_free_tags - release a given set of tag maintenance info
* @bqt: the tag map to free
*
* Tries to free the specified @bqt@. Returns true if it was
* actually freed and false if there are still references using it
*/
static int __blk_free_tags(struct blk_queue_tag *bqt)
{
int retval;
retval = atomic_dec_and_test(&bqt->refcnt);
if (retval) {
BUG_ON(bqt->busy);
kfree(bqt->tag_index);
bqt->tag_index = NULL;
kfree(bqt->tag_map);
bqt->tag_map = NULL;
kfree(bqt);
}
return retval;
}
/**
* __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(struct request_queue *q)
{
struct blk_queue_tag *bqt = q->queue_tags;
if (!bqt)
return;
__blk_free_tags(bqt);
q->queue_tags = NULL;
q->queue_flags &= ~(1 << QUEUE_FLAG_QUEUED);
}
/**
* blk_free_tags - release a given set of tag maintenance info
* @bqt: the tag map to free
*
* For externally managed @bqt@ frees the map. Callers of this
* function must guarantee to have released all the queues that
* might have been using this tag map.
*/
void blk_free_tags(struct blk_queue_tag *bqt)
{
if (unlikely(!__blk_free_tags(bqt)))
BUG();
}
EXPORT_SYMBOL(blk_free_tags);
/**
* 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(struct request_queue *q)
{
clear_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
}
EXPORT_SYMBOL(blk_queue_free_tags);
static int
init_tag_map(struct request_queue *q, struct blk_queue_tag *tags, int depth)
{
struct request **tag_index;
unsigned long *tag_map;
int nr_ulongs;
if (q && 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;
}
static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
int depth)
{
struct blk_queue_tag *tags;
tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC);
if (!tags)
goto fail;
if (init_tag_map(q, tags, depth))
goto fail;
tags->busy = 0;
atomic_set(&tags->refcnt, 1);
return tags;
fail:
kfree(tags);
return NULL;
}
/**
* blk_init_tags - initialize the tag info for an external tag map
* @depth: the maximum queue depth supported
* @tags: the tag to use
**/
struct blk_queue_tag *blk_init_tags(int depth)
{
return __blk_queue_init_tags(NULL, depth);
}
EXPORT_SYMBOL(blk_init_tags);
/**
* 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(struct request_queue *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 = __blk_queue_init_tags(q, depth);
if (!tags)
goto fail;
} 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);
INIT_LIST_HEAD(&q->tag_busy_list);
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(struct request_queue *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;
}
/*
* Currently cannot replace a shared tag map with a new
* one, so error out if this is the case
*/
if (atomic_read(&bqt->refcnt) != 1)
return -EBUSY;
/*
* 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(struct request_queue *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;
list_del_init(&rq->queuelist);
rq->cmd_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;
if (unlikely(!test_bit(tag, bqt->tag_map))) {
printk(KERN_ERR "%s: attempt to clear non-busy tag (%d)\n",
__FUNCTION__, tag);
return;
}
/*
* The tag_map bit acts as a lock for tag_index[bit], so we need
* unlock memory barrier semantics.
*/
clear_bit_unlock(tag, bqt->tag_map);
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(struct request_queue *q, struct request *rq)
{
struct blk_queue_tag *bqt = q->queue_tags;
int tag;
if (unlikely((rq->cmd_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();
}
/*
* Protect against shared tag maps, as we may not have exclusive
* access to the tag map.
*/
do {
tag = find_first_zero_bit(bqt->tag_map, bqt->max_depth);
if (tag >= bqt->max_depth)
return 1;
} while (test_and_set_bit_lock(tag, bqt->tag_map));
/*
* We need lock ordering semantics given by test_and_set_bit_lock.
* See blk_queue_end_tag for details.
*/
rq->cmd_flags |= REQ_QUEUED;
rq->tag = tag;
bqt->tag_index[tag] = rq;
blkdev_dequeue_request(rq);
list_add(&rq->queuelist, &q->tag_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(struct request_queue *q)
{
struct list_head *tmp, *n;
list_for_each_safe(tmp, n, &q->tag_busy_list)
blk_requeue_request(q, list_entry_rq(tmp));
}
EXPORT_SYMBOL(blk_queue_invalidate_tags);
void blk_dump_rq_flags(struct request *rq, char *msg)
{
int bit;
printk("%s: dev %s: type=%x, flags=%x\n", msg,
rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
rq->cmd_flags);
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 (blk_pc_request(rq)) {
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(struct request_queue *q, struct bio *bio)
{
struct request rq;
struct bio *nxt = bio->bi_next;
rq.q = q;
rq.bio = rq.biotail = bio;
bio->bi_next = NULL;
blk_recalc_rq_segments(&rq);
bio->bi_next = nxt;
bio->bi_phys_segments = rq.nr_phys_segments;
bio->bi_hw_segments = rq.nr_hw_segments;
bio->bi_flags |= (1 << BIO_SEG_VALID);
}
EXPORT_SYMBOL(blk_recount_segments);
static void blk_recalc_rq_segments(struct request *rq)
{
int nr_phys_segs;
int nr_hw_segs;
unsigned int phys_size;
unsigned int hw_size;
struct bio_vec *bv, *bvprv = NULL;
int seg_size;
int hw_seg_size;
int cluster;
struct req_iterator iter;
int high, highprv = 1;
struct request_queue *q = rq->q;
if (!rq->bio)
return;
cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
hw_seg_size = seg_size = 0;
phys_size = hw_size = nr_phys_segs = nr_hw_segs = 0;
rq_for_each_segment(bv, rq, iter) {
/*
* 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 (nr_hw_segs == 1 &&
hw_seg_size > rq->bio->bi_hw_front_size)
rq->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 (nr_hw_segs == 1 &&
hw_seg_size > rq->bio->bi_hw_front_size)
rq->bio->bi_hw_front_size = hw_seg_size;
if (hw_seg_size > rq->biotail->bi_hw_back_size)
rq->biotail->bi_hw_back_size = hw_seg_size;
rq->nr_phys_segments = nr_phys_segs;
rq->nr_hw_segments = nr_hw_segs;
}
static int blk_phys_contig_segment(struct request_queue *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(struct request_queue *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_back_size + nxt->bi_hw_front_size))
return 0;
if (bio->bi_hw_back_size + nxt->bi_hw_front_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(struct request_queue *q, struct request *rq,
struct scatterlist *sglist)
{
struct bio_vec *bvec, *bvprv;
struct req_iterator iter;
struct scatterlist *sg;
int nsegs, cluster;
nsegs = 0;
cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
/*
* for each bio in rq
*/
bvprv = NULL;
sg = NULL;
rq_for_each_segment(bvec, rq, iter) {
int nbytes = bvec->bv_len;
if (bvprv && cluster) {
if (sg->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->length += nbytes;
} else {
new_segment:
if (!sg)
sg = sglist;
else {
/*
* If the driver previously mapped a shorter
* list, we could see a termination bit
* prematurely unless it fully inits the sg
* table on each mapping. We KNOW that there
* must be more entries here or the driver
* would be buggy, so force clear the
* termination bit to avoid doing a full
* sg_init_table() in drivers for each command.
*/
sg->page_link &= ~0x02;
sg = sg_next(sg);
}
sg_set_page(sg, bvec->bv_page, nbytes, bvec->bv_offset);
nsegs++;
}
bvprv = bvec;
} /* segments in rq */
if (sg)
sg_mark_end(sg);
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(struct request_queue *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->cmd_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(struct request_queue *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->cmd_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(struct request_queue *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->cmd_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(struct request_queue *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->cmd_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(struct request_queue *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(struct request_queue *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(struct request_queue *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(struct request_queue *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 &struct request_queue 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(struct request_queue *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)
{
struct request_queue *q = bdi->unplug_io_data;
blk_unplug(q);
}
static void blk_unplug_work(struct work_struct *work)
{
struct request_queue *q =
container_of(work, struct request_queue, unplug_work);
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)
{
struct request_queue *q = (struct request_queue *)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);
}
void blk_unplug(struct request_queue *q)
{
/*
* 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);
}
}
EXPORT_SYMBOL(blk_unplug);
/**
* blk_start_queue - restart a previously stopped queue
* @q: The &struct request_queue in question
*
* Description:
* blk_start_queue() will clear the stop flag on the queue, and call
* the request_fn for the queue if it was in a stopped state when
* entered. Also see blk_stop_queue(). Queue lock must be held.
**/
void blk_start_queue(struct request_queue *q)
{
WARN_ON(!irqs_disabled());
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 &struct request_queue in question
*
* Description:
* The Linux block layer assumes that a block driver will consume all
* entries on the request queue when the request_fn strategy is called.
* Often this will not happen, because of hardware limitations (queue
* depth settings). If a device driver gets a 'queue full' response,
* or if it simply chooses not to queue more I/O at one point, it can
* call this function to prevent the request_fn from being called until
* the driver has signalled it's ready to go again. This happens by calling
* blk_start_queue() to restart queue operations. Queue lock must be held.
**/
void blk_stop_queue(struct request_queue *q)
{
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
* that the callbacks might use. The caller must already have made sure
* that its ->make_request_fn will not re-add plugging prior to calling
* this function.
*
*/
void blk_sync_queue(struct request_queue *q)
{
del_timer_sync(&q->unplug_timer);
kblockd_flush_work(&q->unplug_work);
}
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 &struct request_queue 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)
{
struct request_queue *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);
blk_trace_shutdown(q);
bdi_destroy(&q->backing_dev_info);
kmem_cache_free(requestq_cachep, q);
}
void blk_put_queue(struct request_queue *q)
{
kobject_put(&q->kobj);
}
EXPORT_SYMBOL(blk_put_queue);
void blk_cleanup_queue(struct request_queue * 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(struct request_queue *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;
}
struct request_queue *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;
struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
struct request_queue *q;
int err;
q = kmem_cache_alloc_node(requestq_cachep,
gfp_mask | __GFP_ZERO, node_id);
if (!q)
return NULL;
q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
q->backing_dev_info.unplug_io_data = q;
err = bdi_init(&q->backing_dev_info);
if (err) {
kmem_cache_free(requestq_cachep, q);
return NULL;
}
init_timer(&q->unplug_timer);
kobject_set_name(&q->kobj, "%s", "queue");
q->kobj.ktype = &queue_ktype;
kobject_init(&q->kobj);
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).
**/
struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
{
return blk_init_queue_node(rfn, lock, -1);
}
EXPORT_SYMBOL(blk_init_queue);
struct request_queue *
blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
{
struct request_queue *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->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);
q->sg_reserved_size = INT_MAX;
/*
* 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(struct request_queue *q)
{
if (likely(!test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
kobject_get(&q->kobj);
return 0;
}
return 1;
}
EXPORT_SYMBOL(blk_get_queue);
static inline void blk_free_request(struct request_queue *q, struct request *rq)
{
if (rq->cmd_flags & REQ_ELVPRIV)
elv_put_request(q, rq);
mempool_free(rq, q->rq.rq_pool);
}
static struct request *
blk_alloc_request(struct request_queue *q, int rw, 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->cmd_flags and bio->bi_rw,
* see bio.h and blkdev.h
*/
rq->cmd_flags = rw | REQ_ALLOCED;
if (priv) {
if (unlikely(elv_set_request(q, rq, gfp_mask))) {
mempool_free(rq, q->rq.rq_pool);
return NULL;
}
rq->cmd_flags |= REQ_ELVPRIV;
}
return rq;
}
/*
* ioc_batching returns true if the ioc is a valid batching request and
* should be given priority access to a request.
*/
static inline int ioc_batching(struct request_queue *q, struct io_context *ioc)
{
if (!ioc)
return 0;
/*
* Make sure the process is able to allocate at least 1 request
* even if the batch times out, otherwise we could theoretically
* lose wakeups.
*/
return ioc->nr_batch_requests == q->nr_batching ||
(ioc->nr_batch_requests > 0
&& time_before(jiffies, ioc->last_waited + BLK_BATCH_TIME));
}
/*
* ioc_set_batching sets ioc to be a new "batcher" if it is not one. This
* will cause the process to be a "batcher" on all queues in the system. This
* is the behaviour we want though - once it gets a wakeup it should be given
* a nice run.
*/
static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)
{
if (!ioc || ioc_batching(q, ioc))
return;
ioc->nr_batch_requests = q->nr_batching;
ioc->last_waited = jiffies;
}
static void __freed_request(struct request_queue *q, int rw)
{
struct request_list *rl = &q->rq;
if (rl->count[rw] < queue_congestion_off_threshold(q))
blk_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(struct request_queue *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(struct request_queue *q, int rw_flags,
struct bio *bio, gfp_t gfp_mask)
{
struct request *rq = NULL;
struct request_list *rl = &q->rq;
struct io_context *ioc = NULL;
const int rw = rw_flags & 0x01;
int may_queue, priv;
may_queue = elv_may_queue(q, rw_flags);
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, q->node);
/*
* The queue will fill after this allocation, so set
* it as full, and mark this process as "batching".
* This process will be allowed to complete a batch of
* requests, others will be blocked.
*/
if (!blk_queue_full(q, 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;
}
}
}
blk_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_flags, priv, gfp_mask);
if (unlikely(!rq)) {
/*
* Allocation failed presumably due to memory. Undo anything
* we might have messed up.
*
* Allocating task should really be put onto the front of the
* wait queue, but this is pretty rare.
*/
spin_lock_irq(q->queue_lock);
freed_request(q, 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);
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(struct request_queue *q, int rw_flags,
struct bio *bio)
{
const int rw = rw_flags & 0x01;
struct request *rq;
rq = get_request(q, rw_flags, 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_flags, 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, q->node);
ioc_set_batching(q, ioc);
spin_lock_irq(q->queue_lock);
}
finish_wait(&rl->wait[rw], &wait);
}
return rq;
}
struct request *blk_get_request(struct request_queue *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_start_queueing - initiate dispatch of requests to device
* @q: request queue to kick into gear
*
* This is basically a helper to remove the need to know whether a queue
* is plugged or not if someone just wants to initiate dispatch of requests
* for this queue.
*
* The queue lock must be held with interrupts disabled.
*/
void blk_start_queueing(struct request_queue *q)
{
if (!blk_queue_plugged(q))
q->request_fn(q);
else
__generic_unplug_device(q);
}
EXPORT_SYMBOL(blk_start_queueing);
/**
* blk_requeue_request - put a request back on queue
* @q: request queue where request should be inserted
* @rq: request to be inserted
*
* Description:
* Drivers often keep queueing requests until the hardware cannot accept
* more, when that condition happens we need to put the request back
* on the queue. Must be called with queue lock held.
*/
void blk_requeue_request(struct request_queue *q, struct request *rq)
{
blk_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(struct request_queue *q, struct request *rq,
int at_head, void *data)
{
int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
unsigned long flags;
/*
* tell I/O scheduler that this isn't a regular read/write (ie it
* must not attempt merges on this) and that it acts as a soft
* barrier
*/
rq->cmd_type = REQ_TYPE_SPECIAL;
rq->cmd_flags |= 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, 1);
__elv_add_request(q, rq, where, 0);
blk_start_queueing(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_insert_request);
static int __blk_rq_unmap_user(struct bio *bio)
{
int ret = 0;
if (bio) {
if (bio_flagged(bio, BIO_USER_MAPPED))
bio_unmap_user(bio);
else
ret = bio_uncopy_user(bio);
}
return ret;
}
int blk_rq_append_bio(struct request_queue *q, struct request *rq,
struct bio *bio)
{
if (!rq->bio)
blk_rq_bio_prep(q, rq, bio);
else if (!ll_back_merge_fn(q, rq, bio))
return -EINVAL;
else {
rq->biotail->bi_next = bio;
rq->biotail = bio;
rq->data_len += bio->bi_size;
}
return 0;
}
EXPORT_SYMBOL(blk_rq_append_bio);
static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
void __user *ubuf, unsigned int len)
{
unsigned long uaddr;
struct bio *bio, *orig_bio;
int reading, ret;
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))
return PTR_ERR(bio);
orig_bio = bio;
blk_queue_bounce(q, &bio);
/*
* We link the bounce buffer in and could have to traverse it
* later so we have to get a ref to prevent it from being freed
*/
bio_get(bio);
ret = blk_rq_append_bio(q, rq, bio);
if (!ret)
return bio->bi_size;
/* if it was boucned we must call the end io function */
bio_endio(bio, 0);
__blk_rq_unmap_user(orig_bio);
bio_put(bio);
return ret;
}
/**
* 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(struct request_queue *q, struct request *rq,
void __user *ubuf, unsigned long len)
{
unsigned long bytes_read = 0;
struct bio *bio = NULL;
int ret;
if (len > (q->max_hw_sectors << 9))
return -EINVAL;
if (!len || !ubuf)
return -EINVAL;
while (bytes_read != len) {
unsigned long map_len, end, start;
map_len = min_t(unsigned long, len - bytes_read, BIO_MAX_SIZE);
end = ((unsigned long)ubuf + map_len + PAGE_SIZE - 1)
>> PAGE_SHIFT;
start = (unsigned long)ubuf >> PAGE_SHIFT;
/*
* A bad offset could cause us to require BIO_MAX_PAGES + 1
* pages. If this happens we just lower the requested
* mapping len by a page so that we can fit
*/
if (end - start > BIO_MAX_PAGES)
map_len -= PAGE_SIZE;
ret = __blk_rq_map_user(q, rq, ubuf, map_len);
if (ret < 0)
goto unmap_rq;
if (!bio)
bio = rq->bio;
bytes_read += ret;
ubuf += ret;
}
rq->buffer = rq->data = NULL;
return 0;
unmap_rq:
blk_rq_unmap_user(bio);
return ret;
}
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
* @len: I/O byte count
*
* 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(struct request_queue *q, struct request *rq,
struct sg_iovec *iov, int iov_count, unsigned int len)
{
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);
if (bio->bi_size != len) {
bio_endio(bio, 0);
bio_unmap_user(bio);
return -EINVAL;
}
bio_get(bio);
blk_rq_bio_prep(q, rq, bio);
rq->buffer = rq->data = NULL;
return 0;
}
EXPORT_SYMBOL(blk_rq_map_user_iov);
/**
* blk_rq_unmap_user - unmap a request with user data
* @bio: start of bio list
*
* Description:
* Unmap a rq previously mapped by blk_rq_map_user(). The caller must
* supply the original rq->bio from the blk_rq_map_user() return, since
* the io completion may have changed rq->bio.
*/
int blk_rq_unmap_user(struct bio *bio)
{
struct bio *mapped_bio;
int ret = 0, ret2;
while (bio) {
mapped_bio = bio;
if (unlikely(bio_flagged(bio, BIO_BOUNCED)))
mapped_bio = bio->bi_private;
ret2 = __blk_rq_unmap_user(mapped_bio);
if (ret2 && !ret)
ret = ret2;
mapped_bio = bio;
bio = bio->bi_next;
bio_put(mapped_bio);
}
return ret;
}
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(struct request_queue *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);
blk_rq_bio_prep(q, rq, bio);
blk_queue_bounce(q, &rq->bio);
rq->buffer = rq->data = NULL;
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(struct request_queue *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->cmd_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(struct request_queue *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->end_io_data = &wait;
blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
wait_for_completion(&wait);
if (rq->errors)
err = -EIO;
return err;
}
EXPORT_SYMBOL(blk_execute_rq);
static void bio_end_empty_barrier(struct bio *bio, int err)
{
if (err)
clear_bit(BIO_UPTODATE, &bio->bi_flags);
complete(bio->bi_private);
}
/**
* 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)
{
DECLARE_COMPLETION_ONSTACK(wait);
struct request_queue *q;
struct bio *bio;
int ret;
if (bdev->bd_disk == NULL)
return -ENXIO;
q = bdev_get_queue(bdev);
if (!q)
return -ENXIO;
bio = bio_alloc(GFP_KERNEL, 0);
if (!bio)
return -ENOMEM;
bio->bi_end_io = bio_end_empty_barrier;
bio->bi_private = &wait;
bio->bi_bdev = bdev;
submit_bio(1 << BIO_RW_BARRIER, bio);
wait_for_completion(&wait);
/*
* The driver must store the error location in ->bi_sector, if
* it supports it. For non-stacked drivers, this should be copied
* from rq->sector.
*/
if (error_sector)
*error_sector = bio->bi_sector;
ret = 0;
if (!bio_flagged(bio, BIO_UPTODATE))
ret = -EIO;
bio_put(bio);
return ret;
}
EXPORT_SYMBOL(blkdev_issue_flush);
static void drive_stat_acct(struct request *rq, 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(struct request_queue * q, struct request * req)
{
drive_stat_acct(req, 1);
/*
* 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(struct request_queue *q, struct request *req)
{
if (unlikely(!q))
return;
if (unlikely(--req->ref_count))
return;
elv_completed_request(q, req);
/*
* Request may not have originated from ll_rw_blk. if not,
* it didn't come out of our reserved rq pools
*/
if (req->cmd_flags & REQ_ALLOCED) {
int rw = rq_data_dir(req);
int priv = req->cmd_flags & REQ_ELVPRIV;
BUG_ON(!list_empty(&req->queuelist));
BUG_ON(!hlist_unhashed(&req->hash));
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;
struct request_queue *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->end_io_data;
rq->end_io_data = 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);
/*
* Has to be called with the request spinlock acquired
*/
static int attempt_merge(struct request_queue *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->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 (!ll_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(struct request_queue *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(struct request_queue *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->cmd_type = REQ_TYPE_FS;
/*
* inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
*/
if (bio_rw_ahead(bio) || bio_failfast(bio))
req->cmd_flags |= REQ_FAILFAST;
/*
* REQ_BARRIER implies no merging, but lets make it explicit
*/
if (unlikely(bio_barrier(bio)))