* 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
+ * 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
*/
#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;
-
- 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.
- */
- q->ordseq = 0;
- rq = q->orig_bar_rq;
-
- if (__blk_end_request(rq, q->orderr, blk_rq_bytes(rq)))
- BUG();
-}
-
-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);
- if (__blk_end_request(rq, -EOPNOTSUPP,
- blk_rq_bytes(rq)))
- BUG();
- *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_dma_drain - Set up a drain buffer for excess dma.
- *
- * @q: the request queue for the device
- * @buf: physically contiguous buffer
- * @size: size of the buffer in bytes
- *
- * Some devices have excess DMA problems and can't simply discard (or
- * zero fill) the unwanted piece of the transfer. They have to have a
- * real area of memory to transfer it into. The use case for this is
- * ATAPI devices in DMA mode. If the packet command causes a transfer
- * bigger than the transfer size some HBAs will lock up if there
- * aren't DMA elements to contain the excess transfer. What this API
- * does is adjust the queue so that the buf is always appended
- * silently to the scatterlist.
- *
- * Note: This routine adjusts max_hw_segments to make room for
- * appending the drain buffer. If you call
- * blk_queue_max_hw_segments() or blk_queue_max_phys_segments() after
- * calling this routine, you must set the limit to one fewer than your
- * device can support otherwise there won't be room for the drain
- * buffer.
- */
-int blk_queue_dma_drain(struct request_queue *q, void *buf,
- unsigned int size)
-{
- if (q->max_hw_segments < 2 || q->max_phys_segments < 2)
- return -EINVAL;
- /* make room for appending the drain */
- --q->max_hw_segments;
- --q->max_phys_segments;
- q->dma_drain_buffer = buf;
- q->dma_drain_size = size;
-
- return 0;
-}
-
-EXPORT_SYMBOL_GPL(blk_queue_dma_drain);
-
-/**
- * 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_update_dma_alignment - update dma length and memory alignment
- * @q: the request queue for the device
- * @mask: alignment mask
- *
- * description:
- * update required memory and length aligment for direct dma transactions.
- * If the requested alignment is larger than the current alignment, then
- * the current queue alignment is updated to the new value, otherwise it
- * is left alone. The design of this is to allow multiple objects
- * (driver, device, transport etc) to set their respective
- * alignments without having them interfere.
- *
- **/
-void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
-{
- BUG_ON(mask > PAGE_SIZE);
-
- if (mask > q->dma_alignment)
- q->dma_alignment = mask;
-}
-
-EXPORT_SYMBOL(blk_queue_update_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);
+#define CREATE_TRACE_POINTS
+#include <trace/events/block.h>
-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);
+#include "blk.h"
-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;
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
- if (!rq->bio)
- return;
+static int __make_request(struct request_queue *q, struct bio *bio);
- 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++;
- }
+/*
+ * For the allocated request tables
+ */
+static struct kmem_cache *request_cachep;
- nr_phys_segs++;
- bvprv = bv;
- seg_size = bv->bv_len;
- highprv = high;
- }
+/*
+ * For queue allocation
+ */
+struct kmem_cache *blk_requestq_cachep;
- 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;
-}
+/*
+ * Controlling structure to kblockd
+ */
+static struct workqueue_struct *kblockd_workqueue;
-static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
- struct bio *nxt)
+static void drive_stat_acct(struct request *rq, int new_io)
{
- 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;
+ struct hd_struct *part;
+ int rw = rq_data_dir(rq);
+ int cpu;
- /*
- * 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;
+ if (!blk_do_io_stat(rq))
+ return;
- return 0;
-}
+ cpu = part_stat_lock();
+ part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
-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;
+ if (!new_io)
+ part_stat_inc(cpu, part, merges[rw]);
+ else {
+ part_round_stats(cpu, part);
+ part_inc_in_flight(part, rw);
+ }
- return 1;
+ part_stat_unlock();
}
-/*
- * 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)
+void blk_queue_congestion_threshold(struct request_queue *q)
{
- 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 (q->dma_drain_size) {
- sg->page_link &= ~0x02;
- sg = sg_next(sg);
- sg_set_page(sg, virt_to_page(q->dma_drain_buffer),
- q->dma_drain_size,
- ((unsigned long)q->dma_drain_buffer) &
- (PAGE_SIZE - 1));
- nsegs++;
- }
+ int nr;
- if (sg)
- sg_mark_end(sg);
+ nr = q->nr_requests - (q->nr_requests / 8) + 1;
+ if (nr > q->nr_requests)
+ nr = q->nr_requests;
+ q->nr_congestion_on = nr;
- return nsegs;
+ nr = q->nr_requests - (q->nr_requests / 8) - (q->nr_requests / 16) - 1;
+ if (nr < 1)
+ nr = 1;
+ q->nr_congestion_off = nr;
}
-EXPORT_SYMBOL(blk_rq_map_sg);
-
-/*
- * the standard queue merge functions, can be overridden with device
- * specific ones if so desired
+/**
+ * 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.
*/
-
-static inline int ll_new_mergeable(struct request_queue *q,
- struct request *req,
- struct bio *bio)
+struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
{
- 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;
- }
+ struct backing_dev_info *ret = NULL;
+ struct request_queue *q = bdev_get_queue(bdev);
- /*
- * A hw segment is just getting larger, bump just the phys
- * counter.
- */
- req->nr_phys_segments += nr_phys_segs;
- return 1;
+ if (q)
+ ret = &q->backing_dev_info;
+ return ret;
}
+EXPORT_SYMBOL(blk_get_backing_dev_info);
-static inline int ll_new_hw_segment(struct request_queue *q,
- struct request *req,
- struct bio *bio)
+void blk_rq_init(struct request_queue *q, struct request *rq)
{
- 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;
- }
+ memset(rq, 0, sizeof(*rq));
- /*
- * 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;
+ INIT_LIST_HEAD(&rq->queuelist);
+ INIT_LIST_HEAD(&rq->timeout_list);
+ rq->cpu = -1;
+ rq->q = q;
+ rq->__sector = (sector_t) -1;
+ INIT_HLIST_NODE(&rq->hash);
+ RB_CLEAR_NODE(&rq->rb_node);
+ rq->cmd = rq->__cmd;
+ rq->cmd_len = BLK_MAX_CDB;
+ rq->tag = -1;
+ rq->ref_count = 1;
+ rq->start_time = jiffies;
}
+EXPORT_SYMBOL(blk_rq_init);
-static int ll_back_merge_fn(struct request_queue *q, struct request *req,
- struct bio *bio)
+static void req_bio_endio(struct request *rq, struct bio *bio,
+ unsigned int nbytes, int error)
{
- unsigned short max_sectors;
- int len;
+ struct request_queue *q = rq->q;
- if (unlikely(blk_pc_request(req)))
- max_sectors = q->max_hw_sectors;
- else
- max_sectors = q->max_sectors;
+ 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 (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;
+ if (unlikely(nbytes > bio->bi_size)) {
+ printk(KERN_ERR "%s: want %u bytes done, %u left\n",
+ __func__, nbytes, bio->bi_size);
+ nbytes = bio->bi_size;
}
- return mergeable;
- }
- return ll_new_hw_segment(q, req, bio);
-}
+ if (unlikely(rq->cmd_flags & REQ_QUIET))
+ set_bit(BIO_QUIET, &bio->bi_flags);
-static int ll_front_merge_fn(struct request_queue *q, struct request *req,
- struct bio *bio)
-{
- unsigned short max_sectors;
- int len;
+ bio->bi_size -= nbytes;
+ bio->bi_sector += (nbytes >> 9);
- if (unlikely(blk_pc_request(req)))
- max_sectors = q->max_hw_sectors;
- else
- max_sectors = q->max_sectors;
+ if (bio_integrity(bio))
+ bio_integrity_advance(bio, nbytes);
+ if (bio->bi_size == 0)
+ bio_endio(bio, error);
+ } else {
- 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;
+ /*
+ * Okay, this is the barrier request in progress, just
+ * record the error;
+ */
+ if (error && !q->orderr)
+ q->orderr = error;
}
-
- return ll_new_hw_segment(q, req, bio);
}
-static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
- struct request *next)
+void blk_dump_rq_flags(struct request *rq, char *msg)
{
- 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;
+ int bit;
- total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
- if (blk_phys_contig_segment(q, req->biotail, next->bio))
- total_phys_segments--;
+ printk(KERN_INFO "%s: dev %s: type=%x, flags=%x\n", msg,
+ rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
+ rq->cmd_flags);
- if (total_phys_segments > q->max_phys_segments)
- return 0;
+ printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n",
+ (unsigned long long)blk_rq_pos(rq),
+ blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
+ printk(KERN_INFO " bio %p, biotail %p, buffer %p, len %u\n",
+ rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));
- 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 (blk_pc_request(rq)) {
+ printk(KERN_INFO " cdb: ");
+ for (bit = 0; bit < BLK_MAX_CDB; bit++)
+ printk("%02x ", rq->cmd[bit]);
+ printk("\n");
}
-
- 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;
}
+EXPORT_SYMBOL(blk_dump_rq_flags);
/*
* "plug" the device if there are no outstanding requests: this will
if (blk_queue_stopped(q))
return;
- if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
+ if (!queue_flag_test_and_set(QUEUE_FLAG_PLUGGED, q)) {
mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
- blk_add_trace_generic(q, NULL, 0, BLK_TA_PLUG);
+ trace_block_plug(q);
}
}
-
EXPORT_SYMBOL(blk_plug_device);
+/**
+ * blk_plug_device_unlocked - plug a device without queue lock held
+ * @q: The &struct request_queue to plug
+ *
+ * Description:
+ * Like @blk_plug_device(), but grabs the queue lock and disables
+ * interrupts.
+ **/
+void blk_plug_device_unlocked(struct request_queue *q)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ blk_plug_device(q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+}
+EXPORT_SYMBOL(blk_plug_device_unlocked);
+
/*
* remove the queue from the plugged list, if present. called with
* queue lock held and interrupts disabled.
{
WARN_ON(!irqs_disabled());
- if (!test_and_clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
+ if (!queue_flag_test_and_clear(QUEUE_FLAG_PLUGGED, q))
return 0;
del_timer(&q->unplug_timer);
return 1;
}
-
EXPORT_SYMBOL(blk_remove_plug);
/*
{
if (unlikely(blk_queue_stopped(q)))
return;
-
- if (!blk_remove_plug(q))
+ if (!blk_remove_plug(q) && !blk_queue_nonrot(q))
return;
q->request_fn(q);
}
-EXPORT_SYMBOL(__generic_unplug_device);
/**
* generic_unplug_device - fire a request queue
**/
void generic_unplug_device(struct request_queue *q)
{
- spin_lock_irq(q->queue_lock);
- __generic_unplug_device(q);
- spin_unlock_irq(q->queue_lock);
+ if (blk_queue_plugged(q)) {
+ spin_lock_irq(q->queue_lock);
+ __generic_unplug_device(q);
+ spin_unlock_irq(q->queue_lock);
+ }
}
EXPORT_SYMBOL(generic_unplug_device);
blk_unplug(q);
}
-static void blk_unplug_work(struct work_struct *work)
+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]);
-
+ trace_block_unplug_io(q);
q->unplug_fn(q);
}
-static void blk_unplug_timeout(unsigned long data)
+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);
+ trace_block_unplug_timer(q);
+ kblockd_schedule_work(q, &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]);
-
+ trace_block_unplug_io(q);
q->unplug_fn(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);
- }
+ queue_flag_clear(QUEUE_FLAG_STOPPED, q);
+ __blk_run_queue(q);
}
-
EXPORT_SYMBOL(blk_start_queue);
/**
void blk_stop_queue(struct request_queue *q)
{
blk_remove_plug(q);
- set_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
+ queue_flag_set(QUEUE_FLAG_STOPPED, q);
}
EXPORT_SYMBOL(blk_stop_queue);
void blk_sync_queue(struct request_queue *q)
{
del_timer_sync(&q->unplug_timer);
- kblockd_flush_work(&q->unplug_work);
+ del_timer_sync(&q->timeout);
+ cancel_work_sync(&q->unplug_work);
}
EXPORT_SYMBOL(blk_sync_queue);
/**
- * blk_run_queue - run a single device queue
+ * __blk_run_queue - run a single device queue
* @q: The queue to run
+ *
+ * Description:
+ * See @blk_run_queue. This variant must be called with the queue lock
+ * held and interrupts disabled.
+ *
*/
-void blk_run_queue(struct request_queue *q)
+void __blk_run_queue(struct request_queue *q)
{
- unsigned long flags;
-
- spin_lock_irqsave(q->queue_lock, flags);
blk_remove_plug(q);
+ if (unlikely(blk_queue_stopped(q)))
+ return;
+
+ if (elv_queue_empty(q))
+ return;
+
/*
* 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);
- }
+ if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
+ q->request_fn(q);
+ queue_flag_clear(QUEUE_FLAG_REENTER, q);
+ } else {
+ queue_flag_set(QUEUE_FLAG_PLUGGED, q);
+ kblockd_schedule_work(q, &q->unplug_work);
}
-
- spin_unlock_irqrestore(q->queue_lock, flags);
}
-EXPORT_SYMBOL(blk_run_queue);
+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
+ * blk_run_queue - run a single device queue
+ * @q: The queue to run
*
* 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)
+ * Invoke request handling on this queue, if it has pending work to do.
+ * May be used to restart queueing when a request has completed.
+ */
+void blk_run_queue(struct request_queue *q)
{
- 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);
+ unsigned long flags;
- bdi_destroy(&q->backing_dev_info);
- kmem_cache_free(requestq_cachep, q);
+ spin_lock_irqsave(q->queue_lock, flags);
+ __blk_run_queue(q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
}
+EXPORT_SYMBOL(blk_run_queue);
void blk_put_queue(struct request_queue *q)
{
kobject_put(&q->kobj);
}
-EXPORT_SYMBOL(blk_put_queue);
-void blk_cleanup_queue(struct request_queue * q)
+void blk_cleanup_queue(struct request_queue *q)
{
+ /*
+ * We know we have process context here, so we can be a little
+ * cautious and ensure that pending block actions on this device
+ * are done before moving on. Going into this function, we should
+ * not have processes doing IO to this device.
+ */
+ blk_sync_queue(q);
+
mutex_lock(&q->sysfs_lock);
- set_bit(QUEUE_FLAG_DEAD, &q->queue_flags);
+ queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
mutex_unlock(&q->sysfs_lock);
if (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->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
+ rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
rl->elvpriv = 0;
- init_waitqueue_head(&rl->wait[READ]);
- init_waitqueue_head(&rl->wait[WRITE]);
+ init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
+ init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
mempool_free_slab, request_cachep, q->node);
}
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,
+ q = kmem_cache_alloc_node(blk_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;
+ q->backing_dev_info.ra_pages =
+ (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+ q->backing_dev_info.state = 0;
+ q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+ q->backing_dev_info.name = "block";
+
err = bdi_init(&q->backing_dev_info);
if (err) {
- kmem_cache_free(requestq_cachep, q);
+ kmem_cache_free(blk_requestq_cachep, q);
return NULL;
}
init_timer(&q->unplug_timer);
+ setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
+ INIT_LIST_HEAD(&q->timeout_list);
+ INIT_WORK(&q->unplug_work, blk_unplug_work);
- kobject_init(&q->kobj, &queue_ktype);
+ kobject_init(&q->kobj, &blk_queue_ktype);
mutex_init(&q->sysfs_lock);
+ spin_lock_init(&q->__queue_lock);
return q;
}
* 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
+ * Function returns a pointer to the initialized request queue, or %NULL if
* it didn't succeed.
*
* Note:
q->node = node_id;
if (blk_init_free_list(q)) {
- kmem_cache_free(requestq_cachep, q);
+ kmem_cache_free(blk_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_flags = QUEUE_FLAG_DEFAULT;
q->queue_lock = lock;
- blk_queue_segment_boundary(q, 0xffffffff);
-
+ /*
+ * This also sets hw/phys segments, boundary and size
+ */
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;
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)
}
static struct request *
-blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask)
+blk_alloc_request(struct request_queue *q, int flags, int priv, gfp_t gfp_mask)
{
struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);
if (!rq)
return NULL;
- /*
- * 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;
+ blk_rq_init(q, rq);
+
+ rq->cmd_flags = flags | REQ_ALLOCED;
if (priv) {
if (unlikely(elv_set_request(q, rq, gfp_mask))) {
ioc->last_waited = jiffies;
}
-static void __freed_request(struct request_queue *q, int rw)
+static void __freed_request(struct request_queue *q, int sync)
{
struct request_list *rl = &q->rq;
- if (rl->count[rw] < queue_congestion_off_threshold(q))
- blk_clear_queue_congested(q, rw);
+ if (rl->count[sync] < queue_congestion_off_threshold(q))
+ blk_clear_queue_congested(q, sync);
- if (rl->count[rw] + 1 <= q->nr_requests) {
- if (waitqueue_active(&rl->wait[rw]))
- wake_up(&rl->wait[rw]);
+ if (rl->count[sync] + 1 <= q->nr_requests) {
+ if (waitqueue_active(&rl->wait[sync]))
+ wake_up(&rl->wait[sync]);
- blk_clear_queue_full(q, rw);
+ blk_clear_queue_full(q, sync);
}
}
* A request has just been released. Account for it, update the full and
* congestion status, wake up any waiters. Called under q->queue_lock.
*/
-static void freed_request(struct request_queue *q, int rw, int priv)
+static void freed_request(struct request_queue *q, int sync, int priv)
{
struct request_list *rl = &q->rq;
- rl->count[rw]--;
+ rl->count[sync]--;
if (priv)
rl->elvpriv--;
- __freed_request(q, rw);
+ __freed_request(q, sync);
- if (unlikely(rl->starved[rw ^ 1]))
- __freed_request(q, rw ^ 1);
+ if (unlikely(rl->starved[sync ^ 1]))
+ __freed_request(q, sync ^ 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.
struct request *rq = NULL;
struct request_list *rl = &q->rq;
struct io_context *ioc = NULL;
- const int rw = rw_flags & 0x01;
+ const bool is_sync = rw_is_sync(rw_flags) != 0;
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) {
+ if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) {
+ if (rl->count[is_sync]+1 >= q->nr_requests) {
ioc = current_io_context(GFP_ATOMIC, q->node);
/*
* The queue will fill after this allocation, so set
* This process will be allowed to complete a batch of
* requests, others will be blocked.
*/
- if (!blk_queue_full(q, rw)) {
+ if (!blk_queue_full(q, is_sync)) {
ioc_set_batching(q, ioc);
- blk_set_queue_full(q, rw);
+ blk_set_queue_full(q, is_sync);
} else {
if (may_queue != ELV_MQUEUE_MUST
&& !ioc_batching(q, ioc)) {
}
}
}
- blk_set_queue_congested(q, rw);
+ blk_set_queue_congested(q, is_sync);
}
/*
* 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))
+ if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
goto out;
- rl->count[rw]++;
- rl->starved[rw] = 0;
+ rl->count[is_sync]++;
+ rl->starved[is_sync] = 0;
priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
if (priv)
rl->elvpriv++;
+ if (blk_queue_io_stat(q))
+ rw_flags |= REQ_IO_STAT;
spin_unlock_irq(q->queue_lock);
rq = blk_alloc_request(q, rw_flags, priv, gfp_mask);
* wait queue, but this is pretty rare.
*/
spin_lock_irq(q->queue_lock);
- freed_request(q, rw, priv);
+ freed_request(q, is_sync, priv);
/*
* in the very unlikely event that allocation failed and no
* rq mempool into READ and WRITE
*/
rq_starved:
- if (unlikely(rl->count[rw] == 0))
- rl->starved[rw] = 1;
+ if (unlikely(rl->count[is_sync] == 0))
+ rl->starved[is_sync] = 1;
goto out;
}
*/
if (ioc_batching(q, ioc))
ioc->nr_batch_requests--;
-
- rq_init(q, rq);
- blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ);
+ trace_block_getrq(q, bio, rw_flags & 1);
out:
return rq;
}
static struct request *get_request_wait(struct request_queue *q, int rw_flags,
struct bio *bio)
{
- const int rw = rw_flags & 0x01;
+ const bool is_sync = rw_is_sync(rw_flags) != 0;
struct request *rq;
rq = get_request(q, rw_flags, bio, GFP_NOIO);
while (!rq) {
DEFINE_WAIT(wait);
+ struct io_context *ioc;
struct request_list *rl = &q->rq;
- prepare_to_wait_exclusive(&rl->wait[rw], &wait,
+ prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
TASK_UNINTERRUPTIBLE);
- rq = get_request(q, rw_flags, bio, GFP_NOIO);
-
- if (!rq) {
- struct io_context *ioc;
+ trace_block_sleeprq(q, bio, rw_flags & 1);
- blk_add_trace_generic(q, bio, rw, BLK_TA_SLEEPRQ);
+ __generic_unplug_device(q);
+ spin_unlock_irq(q->queue_lock);
+ io_schedule();
- __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);
- /*
- * After sleeping, we become a "batching" process and
- * will be able to allocate at least one request, and
- * up to a big batch of them for a small period time.
- * See ioc_batching, ioc_set_batching
- */
- ioc = current_io_context(GFP_NOIO, q->node);
- ioc_set_batching(q, ioc);
+ spin_lock_irq(q->queue_lock);
+ finish_wait(&rl->wait[is_sync], &wait);
- spin_lock_irq(q->queue_lock);
- }
- finish_wait(&rl->wait[rw], &wait);
- }
+ rq = get_request(q, rw_flags, bio, GFP_NOIO);
+ };
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.
+ * blk_make_request - given a bio, allocate a corresponding struct request.
+ * @q: target request queue
+ * @bio: The bio describing the memory mappings that will be submitted for IO.
+ * It may be a chained-bio properly constructed by block/bio layer.
+ * @gfp_mask: gfp flags to be used for memory allocation
+ *
+ * blk_make_request is the parallel of generic_make_request for BLOCK_PC
+ * type commands. Where the struct request needs to be farther initialized by
+ * the caller. It is passed a &struct bio, which describes the memory info of
+ * the I/O transfer.
+ *
+ * The caller of blk_make_request must make sure that bi_io_vec
+ * are set to describe the memory buffers. That bio_data_dir() will return
+ * the needed direction of the request. (And all bio's in the passed bio-chain
+ * are properly set accordingly)
+ *
+ * If called under none-sleepable conditions, mapped bio buffers must not
+ * need bouncing, by calling the appropriate masked or flagged allocator,
+ * suitable for the target device. Otherwise the call to blk_queue_bounce will
+ * BUG.
+ *
+ * WARNING: When allocating/cloning a bio-chain, careful consideration should be
+ * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for
+ * anything but the first bio in the chain. Otherwise you risk waiting for IO
+ * completion of a bio that hasn't been submitted yet, thus resulting in a
+ * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead
+ * of bio_alloc(), as that avoids the mempool deadlock.
+ * If possible a big IO should be split into smaller parts when allocation
+ * fails. Partial allocation should not be an error, or you risk a live-lock.
*/
-void blk_start_queueing(struct request_queue *q)
+struct request *blk_make_request(struct request_queue *q, struct bio *bio,
+ gfp_t gfp_mask)
{
- if (!blk_queue_plugged(q))
- q->request_fn(q);
- else
- __generic_unplug_device(q);
+ struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);
+
+ if (unlikely(!rq))
+ return ERR_PTR(-ENOMEM);
+
+ for_each_bio(bio) {
+ struct bio *bounce_bio = bio;
+ int ret;
+
+ blk_queue_bounce(q, &bounce_bio);
+ ret = blk_rq_append_bio(q, rq, bounce_bio);
+ if (unlikely(ret)) {
+ blk_put_request(rq);
+ return ERR_PTR(ret);
+ }
+ }
+
+ return rq;
}
-EXPORT_SYMBOL(blk_start_queueing);
+EXPORT_SYMBOL(blk_make_request);
/**
* blk_requeue_request - put a request back on queue
*/
void blk_requeue_request(struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+ blk_delete_timer(rq);
+ blk_clear_rq_complete(rq);
+ trace_block_rq_requeue(q, rq);
if (blk_rq_tagged(rq))
blk_queue_end_tag(q, rq);
+ BUG_ON(blk_queued_rq(rq));
+
elv_requeue_request(q, rq);
}
-
EXPORT_SYMBOL(blk_requeue_request);
/**
- * blk_insert_request - insert a special request in to a request queue
+ * blk_insert_request - insert a special request into a request queue
* @q: request queue where request should be inserted
* @rq: request to be inserted
* @at_head: insert request at head or tail of queue
* 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.
+ * REQ_TYPE_SPECIAL in to the corresponding request queue, and letting them
+ * be scheduled for actual execution by the request queue.
*
* We have the option of inserting the head or the tail of the queue.
* Typically we use the tail for new ioctls and so forth. We use the head
* barrier
*/
rq->cmd_type = REQ_TYPE_SPECIAL;
- rq->cmd_flags |= REQ_SOFTBARRIER;
rq->special = data;
drive_stat_acct(rq, 1);
__elv_add_request(q, rq, where, 0);
- blk_start_queueing(q);
+ __blk_run_queue(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)
+static inline void add_request(struct request_queue *q, struct request *req)
{
drive_stat_acct(req, 1);
*/
__elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
}
-
-/*
- * disk_round_stats() - Round off the performance stats on a struct
- * disk_stats.
+
+static void part_round_stats_single(int cpu, struct hd_struct *part,
+ unsigned long now)
+{
+ if (now == part->stamp)
+ return;
+
+ if (part_in_flight(part)) {
+ __part_stat_add(cpu, part, time_in_queue,
+ part_in_flight(part) * (now - part->stamp));
+ __part_stat_add(cpu, part, io_ticks, (now - part->stamp));
+ }
+ part->stamp = now;
+}
+
+/**
+ * part_round_stats() - Round off the performance stats on a struct disk_stats.
+ * @cpu: cpu number for stats access
+ * @part: target partition
*
* The average IO queue length and utilisation statistics are maintained
* by observing the current state of the queue length and the amount of
* /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)
+void part_round_stats(int cpu, struct hd_struct *part)
{
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;
+ if (part->partno)
+ part_round_stats_single(cpu, &part_to_disk(part)->part0, now);
+ part_round_stats_single(cpu, part, now);
}
-
-EXPORT_SYMBOL_GPL(disk_round_stats);
+EXPORT_SYMBOL_GPL(part_round_stats);
/*
* queue lock must be held
elv_completed_request(q, req);
+ /* this is a bio leak */
+ WARN_ON(req->bio != NULL);
+
/*
* 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 is_sync = rq_is_sync(req) != 0;
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);
+ freed_request(q, is_sync, 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);
- }
+ 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)
+void init_request_from_bio(struct request *req, struct bio *bio)
{
+ req->cpu = bio->bi_comp_cpu;
req->cmd_type = REQ_TYPE_FS;
/*
- * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
+ * Inherit FAILFAST from bio (for read-ahead, and explicit
+ * FAILFAST). FAILFAST flags are identical for req and bio.
*/
- if (bio_rw_ahead(bio) || bio_failfast(bio))
- req->cmd_flags |= REQ_FAILFAST;
+ if (bio_rw_flagged(bio, BIO_RW_AHEAD))
+ req->cmd_flags |= REQ_FAILFAST_MASK;
+ else
+ req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK;
- /*
- * REQ_BARRIER implies no merging, but lets make it explicit
- */
- if (unlikely(bio_barrier(bio)))
- req->cmd_flags |= (REQ_HARDBARRIER | REQ_NOMERGE);
+ if (unlikely(bio_rw_flagged(bio, BIO_RW_DISCARD))) {
+ req->cmd_flags |= REQ_DISCARD;
+ if (bio_rw_flagged(bio, BIO_RW_BARRIER))
+ req->cmd_flags |= REQ_SOFTBARRIER;
+ } else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)))
+ req->cmd_flags |= REQ_HARDBARRIER;
- if (bio_sync(bio))
+ if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
req->cmd_flags |= REQ_RW_SYNC;
- if (bio_rw_meta(bio))
+ if (bio_rw_flagged(bio, BIO_RW_META))
req->cmd_flags |= REQ_RW_META;
+ if (bio_rw_flagged(bio, BIO_RW_NOIDLE))
+ req->cmd_flags |= REQ_NOIDLE;
req->errors = 0;
- req->hard_sector = req->sector = bio->bi_sector;
+ req->__sector = bio->bi_sector;
req->ioprio = bio_prio(bio);
- req->start_time = jiffies;
blk_rq_bio_prep(req->q, req, bio);
}
+/*
+ * Only disabling plugging for non-rotational devices if it does tagging
+ * as well, otherwise we do need the proper merging
+ */
+static inline bool queue_should_plug(struct request_queue *q)
+{
+ return !(blk_queue_nonrot(q) && blk_queue_queuing(q));
+}
+
static int __make_request(struct request_queue *q, struct bio *bio)
{
struct request *req;
- int el_ret, nr_sectors, barrier, err;
+ int el_ret;
+ unsigned int bytes = bio->bi_size;
const unsigned short prio = bio_prio(bio);
- const int sync = bio_sync(bio);
+ const bool sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
+ const bool unplug = bio_rw_flagged(bio, BIO_RW_UNPLUG);
+ const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
int rw_flags;
- nr_sectors = bio_sectors(bio);
-
+ if (bio_rw_flagged(bio, BIO_RW_BARRIER) && bio_has_data(bio) &&
+ (q->next_ordered == QUEUE_ORDERED_NONE)) {
+ bio_endio(bio, -EOPNOTSUPP);
+ return 0;
+ }
/*
* low level driver can indicate that it wants pages above a
* certain limit bounced to low memory (ie for highmem, or even
*/
blk_queue_bounce(q, &bio);
- 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))
+ if (unlikely(bio_rw_flagged(bio, BIO_RW_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));
+ case ELEVATOR_BACK_MERGE:
+ BUG_ON(!rq_mergeable(req));
- if (!ll_back_merge_fn(q, req, bio))
- break;
+ if (!ll_back_merge_fn(q, req, bio))
+ break;
- blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
+ trace_block_bio_backmerge(q, bio);
- 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, 0);
- if (!attempt_back_merge(q, req))
- elv_merged_request(q, req, el_ret);
- goto out;
+ if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+ blk_rq_set_mixed_merge(req);
- case ELEVATOR_FRONT_MERGE:
- BUG_ON(!rq_mergeable(req));
+ req->biotail->bi_next = bio;
+ req->biotail = bio;
+ req->__data_len += bytes;
+ req->ioprio = ioprio_best(req->ioprio, prio);
+ if (!blk_rq_cpu_valid(req))
+ req->cpu = bio->bi_comp_cpu;
+ drive_stat_acct(req, 0);
+ if (!attempt_back_merge(q, req))
+ elv_merged_request(q, req, el_ret);
+ goto out;
- if (!ll_front_merge_fn(q, req, bio))
- break;
+ case ELEVATOR_FRONT_MERGE:
+ BUG_ON(!rq_mergeable(req));
- blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
+ if (!ll_front_merge_fn(q, req, bio))
+ break;
- bio->bi_next = req->bio;
- req->bio = bio;
+ trace_block_bio_frontmerge(q, 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 = bio_cur_sectors(bio);
- req->hard_cur_sectors = req->current_nr_sectors;
- req->sector = req->hard_sector = bio->bi_sector;
- req->nr_sectors = req->hard_nr_sectors += nr_sectors;
- req->ioprio = ioprio_best(req->ioprio, prio);
- drive_stat_acct(req, 0);
- if (!attempt_front_merge(q, req))
- elv_merged_request(q, req, el_ret);
- goto out;
-
- /* ELV_NO_MERGE: elevator says don't/can't merge. */
- default:
- ;
+ if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
+ blk_rq_set_mixed_merge(req);
+ req->cmd_flags &= ~REQ_FAILFAST_MASK;
+ req->cmd_flags |= ff;
+ }
+
+ 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->__sector = bio->bi_sector;
+ req->__data_len += bytes;
+ req->ioprio = ioprio_best(req->ioprio, prio);
+ if (!blk_rq_cpu_valid(req))
+ req->cpu = bio->bi_comp_cpu;
+ drive_stat_acct(req, 0);
+ if (!attempt_front_merge(q, req))
+ elv_merged_request(q, req, el_ret);
+ goto out;
+
+ /* ELV_NO_MERGE: elevator says don't/can't merge. */
+ default:
+ ;
}
get_rq:
init_request_from_bio(req, bio);
spin_lock_irq(q->queue_lock);
- if (elv_queue_empty(q))
+ if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) ||
+ bio_flagged(bio, BIO_CPU_AFFINE))
+ req->cpu = blk_cpu_to_group(smp_processor_id());
+ if (queue_should_plug(q) && elv_queue_empty(q))
blk_plug_device(q);
add_request(q, req);
out:
- if (sync)
+ if (unplug || !queue_should_plug(q))
__generic_unplug_device(q);
-
spin_unlock_irq(q->queue_lock);
return 0;
-
-end_io:
- bio_endio(bio, err);
- return 0;
}
/*
if (bio_sectors(bio) && 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;
- blk_add_trace_remap(bdev_get_queue(bio->bi_bdev), bio,
- bdev->bd_dev, bio->bi_sector,
+ trace_block_remap(bdev_get_queue(bio->bi_bdev), bio,
+ bdev->bd_dev,
bio->bi_sector - p->start_sect);
}
}
static int should_fail_request(struct bio *bio)
{
- if ((bio->bi_bdev->bd_disk->flags & GENHD_FL_FAIL) ||
- (bio->bi_bdev->bd_part && bio->bi_bdev->bd_part->make_it_fail))
+ struct hd_struct *part = bio->bi_bdev->bd_part;
+
+ if (part_to_disk(part)->part0.make_it_fail || part->make_it_fail)
return should_fail(&fail_make_request, bio->bi_size);
return 0;
}
/**
- * generic_make_request: hand a buffer to its device driver for I/O
+ * 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
char b[BDEVNAME_SIZE];
q = bdev_get_queue(bio->bi_bdev);
- if (!q) {
+ if (unlikely(!q)) {
printk(KERN_ERR
"generic_make_request: Trying to access "
"nonexistent block-device %s (%Lu)\n",
bdevname(bio->bi_bdev, b),
(long long) bio->bi_sector);
-end_io:
- bio_endio(bio, err);
- break;
+ goto end_io;
}
- if (unlikely(nr_sectors > q->max_hw_sectors)) {
- printk("bio too big device %s (%u > %u)\n",
- bdevname(bio->bi_bdev, b),
- bio_sectors(bio),
- q->max_hw_sectors);
+ if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+ nr_sectors > queue_max_hw_sectors(q))) {
+ printk(KERN_ERR "bio too big device %s (%u > %u)\n",
+ bdevname(bio->bi_bdev, b),
+ bio_sectors(bio),
+ queue_max_hw_sectors(q));
goto end_io;
}
*/
blk_partition_remap(bio);
- if (old_sector != -1)
- blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
- old_sector);
+ if (bio_integrity_enabled(bio) && bio_integrity_prep(bio))
+ goto end_io;
- blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
+ if (old_sector != -1)
+ trace_block_remap(q, bio, old_dev, old_sector);
old_sector = bio->bi_sector;
old_dev = bio->bi_bdev->bd_dev;
if (bio_check_eod(bio, nr_sectors))
goto end_io;
- if (bio_empty_barrier(bio) && !q->prepare_flush_fn) {
+
+ if (bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+ !blk_queue_discard(q)) {
err = -EOPNOTSUPP;
goto end_io;
}
+ trace_block_bio_queue(q, bio);
+
ret = q->make_request_fn(q, bio);
} while (ret);
+
+ return;
+
+end_io:
+ bio_endio(bio, err);
}
/*
} while (bio);
current->bio_tail = NULL; /* deactivate */
}
-
EXPORT_SYMBOL(generic_make_request);
/**
- * submit_bio: submit a bio to the block device layer for I/O
+ * submit_bio - submit a bio to the block device layer for I/O
* @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
* @bio: The &struct bio which describes the I/O
*
* submit_bio() is very similar in purpose to generic_make_request(), and
* uses that function to do most of the work. Both are fairly rough
- * interfaces, @bio must be presetup and ready for I/O.
+ * interfaces; @bio must be presetup and ready for I/O.
*
*/
void submit_bio(int rw, struct bio *bio)
* If it's a regular read/write or a barrier with data attached,
* go through the normal accounting stuff before submission.
*/
- if (!bio_empty_barrier(bio)) {
-
- BIO_BUG_ON(!bio->bi_size);
- BIO_BUG_ON(!bio->bi_io_vec);
-
+ if (bio_has_data(bio)) {
if (rw & WRITE) {
count_vm_events(PGPGOUT, count);
} else {
current->comm, task_pid_nr(current),
(rw & WRITE) ? "WRITE" : "READ",
(unsigned long long)bio->bi_sector,
- bdevname(bio->bi_bdev,b));
+ bdevname(bio->bi_bdev, b));
}
}
generic_make_request(bio);
}
-
EXPORT_SYMBOL(submit_bio);
-static void blk_recalc_rq_sectors(struct request *rq, int nsect)
+/**
+ * blk_rq_check_limits - Helper function to check a request for the queue limit
+ * @q: the queue
+ * @rq: the request being checked
+ *
+ * Description:
+ * @rq may have been made based on weaker limitations of upper-level queues
+ * in request stacking drivers, and it may violate the limitation of @q.
+ * Since the block layer and the underlying device driver trust @rq
+ * after it is inserted to @q, it should be checked against @q before
+ * the insertion using this generic function.
+ *
+ * This function should also be useful for request stacking drivers
+ * in some cases below, so export this fuction.
+ * Request stacking drivers like request-based dm may change the queue
+ * limits while requests are in the queue (e.g. dm's table swapping).
+ * Such request stacking drivers should check those requests agaist
+ * the new queue limits again when they dispatch those requests,
+ * although such checkings are also done against the old queue limits
+ * when submitting requests.
+ */
+int blk_rq_check_limits(struct request_queue *q, struct request *rq)
{
- if (blk_fs_request(rq)) {
- rq->hard_sector += nsect;
- rq->hard_nr_sectors -= nsect;
+ if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
+ blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
+ printk(KERN_ERR "%s: over max size limit.\n", __func__);
+ return -EIO;
+ }
- /*
- * Move the I/O submission pointers ahead if required.
- */
- if ((rq->nr_sectors >= rq->hard_nr_sectors) &&
- (rq->sector <= rq->hard_sector)) {
- rq->sector = rq->hard_sector;
- rq->nr_sectors = rq->hard_nr_sectors;
- rq->hard_cur_sectors = bio_cur_sectors(rq->bio);
- rq->current_nr_sectors = rq->hard_cur_sectors;
- rq->buffer = bio_data(rq->bio);
+ /*
+ * queue's settings related to segment counting like q->bounce_pfn
+ * may differ from that of other stacking queues.
+ * Recalculate it to check the request correctly on this queue's
+ * limitation.
+ */
+ blk_recalc_rq_segments(rq);
+ if (rq->nr_phys_segments > queue_max_phys_segments(q) ||
+ rq->nr_phys_segments > queue_max_hw_segments(q)) {
+ printk(KERN_ERR "%s: over max segments limit.\n", __func__);
+ return -EIO;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(blk_rq_check_limits);
+
+/**
+ * blk_insert_cloned_request - Helper for stacking drivers to submit a request
+ * @q: the queue to submit the request
+ * @rq: the request being queued
+ */
+int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
+{
+ unsigned long flags;
+
+ if (blk_rq_check_limits(q, rq))
+ return -EIO;
+
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+ if (rq->rq_disk && rq->rq_disk->part0.make_it_fail &&
+ should_fail(&fail_make_request, blk_rq_bytes(rq)))
+ return -EIO;
+#endif
+
+ spin_lock_irqsave(q->queue_lock, flags);
+
+ /*
+ * Submitting request must be dequeued before calling this function
+ * because it will be linked to another request_queue
+ */
+ BUG_ON(blk_queued_rq(rq));
+
+ drive_stat_acct(rq, 1);
+ __elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 0);
+
+ spin_unlock_irqrestore(q->queue_lock, flags);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
+
+/**
+ * blk_rq_err_bytes - determine number of bytes till the next failure boundary
+ * @rq: request to examine
+ *
+ * Description:
+ * A request could be merge of IOs which require different failure
+ * handling. This function determines the number of bytes which
+ * can be failed from the beginning of the request without
+ * crossing into area which need to be retried further.
+ *
+ * Return:
+ * The number of bytes to fail.
+ *
+ * Context:
+ * queue_lock must be held.
+ */
+unsigned int blk_rq_err_bytes(const struct request *rq)
+{
+ unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+ unsigned int bytes = 0;
+ struct bio *bio;
+
+ if (!(rq->cmd_flags & REQ_MIXED_MERGE))
+ return blk_rq_bytes(rq);
+
+ /*
+ * Currently the only 'mixing' which can happen is between
+ * different fastfail types. We can safely fail portions
+ * which have all the failfast bits that the first one has -
+ * the ones which are at least as eager to fail as the first
+ * one.
+ */
+ for (bio = rq->bio; bio; bio = bio->bi_next) {
+ if ((bio->bi_rw & ff) != ff)
+ break;
+ bytes += bio->bi_size;
+ }
+
+ /* this could lead to infinite loop */
+ BUG_ON(blk_rq_bytes(rq) && !bytes);
+ return bytes;
+}
+EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
+
+static void blk_account_io_completion(struct request *req, unsigned int bytes)
+{
+ if (blk_do_io_stat(req)) {
+ const int rw = rq_data_dir(req);
+ struct hd_struct *part;
+ int cpu;
+
+ cpu = part_stat_lock();
+ part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+ part_stat_add(cpu, part, sectors[rw], bytes >> 9);
+ part_stat_unlock();
+ }
+}
+
+static void blk_account_io_done(struct request *req)
+{
+ /*
+ * Account IO completion. bar_rq isn't accounted as a normal
+ * IO on queueing nor completion. Accounting the containing
+ * request is enough.
+ */
+ if (blk_do_io_stat(req) && req != &req->q->bar_rq) {
+ unsigned long duration = jiffies - req->start_time;
+ const int rw = rq_data_dir(req);
+ struct hd_struct *part;
+ int cpu;
+
+ cpu = part_stat_lock();
+ part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+
+ part_stat_inc(cpu, part, ios[rw]);
+ part_stat_add(cpu, part, ticks[rw], duration);
+ part_round_stats(cpu, part);
+ part_dec_in_flight(part, rw);
+
+ part_stat_unlock();
+ }
+}
+
+/**
+ * blk_peek_request - peek at the top of a request queue
+ * @q: request queue to peek at
+ *
+ * Description:
+ * Return the request at the top of @q. The returned request
+ * should be started using blk_start_request() before LLD starts
+ * processing it.
+ *
+ * Return:
+ * Pointer to the request at the top of @q if available. Null
+ * otherwise.
+ *
+ * Context:
+ * queue_lock must be held.
+ */
+struct request *blk_peek_request(struct request_queue *q)
+{
+ struct request *rq;
+ int ret;
+
+ while ((rq = __elv_next_request(q)) != NULL) {
+ if (!(rq->cmd_flags & REQ_STARTED)) {
+ /*
+ * This is the first time the device driver
+ * sees this request (possibly after
+ * requeueing). Notify IO scheduler.
+ */
+ if (blk_sorted_rq(rq))
+ elv_activate_rq(q, rq);
+
+ /*
+ * just mark as started even if we don't start
+ * it, a request that has been delayed should
+ * not be passed by new incoming requests
+ */
+ rq->cmd_flags |= REQ_STARTED;
+ trace_block_rq_issue(q, rq);
+ }
+
+ if (!q->boundary_rq || q->boundary_rq == rq) {
+ q->end_sector = rq_end_sector(rq);
+ q->boundary_rq = NULL;
+ }
+
+ if (rq->cmd_flags & REQ_DONTPREP)
+ break;
+
+ if (q->dma_drain_size && blk_rq_bytes(rq)) {
+ /*
+ * make sure space for the drain appears we
+ * know we can do this because max_hw_segments
+ * has been adjusted to be one fewer than the
+ * device can handle
+ */
+ rq->nr_phys_segments++;
+ }
+
+ if (!q->prep_rq_fn)
+ break;
+
+ ret = q->prep_rq_fn(q, rq);
+ if (ret == BLKPREP_OK) {
+ break;
+ } else if (ret == BLKPREP_DEFER) {
+ /*
+ * the request may have been (partially) prepped.
+ * we need to keep this request in the front to
+ * avoid resource deadlock. REQ_STARTED will
+ * prevent other fs requests from passing this one.
+ */
+ if (q->dma_drain_size && blk_rq_bytes(rq) &&
+ !(rq->cmd_flags & REQ_DONTPREP)) {
+ /*
+ * remove the space for the drain we added
+ * so that we don't add it again
+ */
+ --rq->nr_phys_segments;
+ }
+
+ rq = NULL;
+ break;
+ } else if (ret == BLKPREP_KILL) {
+ rq->cmd_flags |= REQ_QUIET;
+ /*
+ * Mark this request as started so we don't trigger
+ * any debug logic in the end I/O path.
+ */
+ blk_start_request(rq);
+ __blk_end_request_all(rq, -EIO);
+ } else {
+ printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
+ break;
}
+ }
+
+ return rq;
+}
+EXPORT_SYMBOL(blk_peek_request);
+
+void blk_dequeue_request(struct request *rq)
+{
+ struct request_queue *q = rq->q;
+ BUG_ON(list_empty(&rq->queuelist));
+ BUG_ON(ELV_ON_HASH(rq));
+
+ list_del_init(&rq->queuelist);
+
+ /*
+ * the time frame between a request being removed from the lists
+ * and to it is freed is accounted as io that is in progress at
+ * the driver side.
+ */
+ if (blk_account_rq(rq)) {
+ q->in_flight[rq_is_sync(rq)]++;
/*
- * if total number of sectors is less than the first segment
- * size, something has gone terribly wrong
+ * Mark this device as supporting hardware queuing, if
+ * we have more IOs in flight than 4.
*/
- if (rq->nr_sectors < rq->current_nr_sectors) {
- printk("blk: request botched\n");
- rq->nr_sectors = rq->current_nr_sectors;
- }
+ if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
+ set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
}
}
/**
- * __end_that_request_first - end I/O on a request
+ * blk_start_request - start request processing on the driver
+ * @req: request to dequeue
+ *
+ * Description:
+ * Dequeue @req and start timeout timer on it. This hands off the
+ * request to the driver.
+ *
+ * Block internal functions which don't want to start timer should
+ * call blk_dequeue_request().
+ *
+ * Context:
+ * queue_lock must be held.
+ */
+void blk_start_request(struct request *req)
+{
+ blk_dequeue_request(req);
+
+ /*
+ * We are now handing the request to the hardware, initialize
+ * resid_len to full count and add the timeout handler.
+ */
+ req->resid_len = blk_rq_bytes(req);
+ if (unlikely(blk_bidi_rq(req)))
+ req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
+
+ blk_add_timer(req);
+}
+EXPORT_SYMBOL(blk_start_request);
+
+/**
+ * blk_fetch_request - fetch a request from a request queue
+ * @q: request queue to fetch a request from
+ *
+ * Description:
+ * Return the request at the top of @q. The request is started on
+ * return and LLD can start processing it immediately.
+ *
+ * Return:
+ * Pointer to the request at the top of @q if available. Null
+ * otherwise.
+ *
+ * Context:
+ * queue_lock must be held.
+ */
+struct request *blk_fetch_request(struct request_queue *q)
+{
+ struct request *rq;
+
+ rq = blk_peek_request(q);
+ if (rq)
+ blk_start_request(rq);
+ return rq;
+}
+EXPORT_SYMBOL(blk_fetch_request);
+
+/**
+ * blk_update_request - Special helper function for request stacking drivers
* @req: the request being processed
- * @error: 0 for success, < 0 for error
- * @nr_bytes: number of bytes to complete
+ * @error: %0 for success, < %0 for error
+ * @nr_bytes: number of bytes to complete @req
*
* Description:
- * Ends I/O on a number of bytes attached to @req, and sets it up
- * for the next range of segments (if any) in the cluster.
+ * Ends I/O on a number of bytes attached to @req, but doesn't complete
+ * the request structure even if @req doesn't have leftover.
+ * If @req has leftover, sets it up for the next range of segments.
+ *
+ * This special helper function is only for request stacking drivers
+ * (e.g. request-based dm) so that they can handle partial completion.
+ * Actual device drivers should use blk_end_request instead.
+ *
+ * Passing the result of blk_rq_bytes() as @nr_bytes guarantees
+ * %false return from this function.
*
* Return:
- * 0 - we are done with this request, call end_that_request_last()
- * 1 - still buffers pending for this request
+ * %false - this request doesn't have any more data
+ * %true - this request has more data
**/
-static int __end_that_request_first(struct request *req, int error,
- int nr_bytes)
+bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
{
int total_bytes, bio_nbytes, next_idx = 0;
struct bio *bio;
- blk_add_trace_rq(req->q, req, BLK_TA_COMPLETE);
+ if (!req->bio)
+ return false;
+
+ trace_block_rq_complete(req->q, req);
/*
- * for a REQ_BLOCK_PC request, we want to carry any eventual
- * sense key with us all the way through
+ * For fs requests, rq is just carrier of independent bio's
+ * and each partial completion should be handled separately.
+ * Reset per-request error on each partial completion.
+ *
+ * TODO: tj: This is too subtle. It would be better to let
+ * low level drivers do what they see fit.
*/
- if (!blk_pc_request(req))
+ if (blk_fs_request(req))
req->errors = 0;
- if (error) {
- if (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))
- printk("end_request: I/O error, dev %s, sector %llu\n",
+ if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) {
+ printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n",
req->rq_disk ? req->rq_disk->disk_name : "?",
- (unsigned long long)req->sector);
+ (unsigned long long)blk_rq_pos(req));
}
- if (blk_fs_request(req) && req->rq_disk) {
- const int rw = rq_data_dir(req);
-
- disk_stat_add(req->rq_disk, sectors[rw], nr_bytes >> 9);
- }
+ blk_account_io_completion(req, nr_bytes);
total_bytes = bio_nbytes = 0;
while ((bio = req->bio) != NULL) {
int nbytes;
- /*
- * For an empty barrier request, the low level driver must
- * store a potential error location in ->sector. We pass
- * that back up in ->bi_sector.
- */
- if (blk_empty_barrier(req))
- bio->bi_sector = req->sector;
-
if (nr_bytes >= bio->bi_size) {
req->bio = bio->bi_next;
nbytes = bio->bi_size;
} else {
int idx = bio->bi_idx + next_idx;
- if (unlikely(bio->bi_idx >= bio->bi_vcnt)) {
+ if (unlikely(idx >= bio->bi_vcnt)) {
blk_dump_rq_flags(req, "__end_that");
- printk("%s: bio idx %d >= vcnt %d\n",
- __FUNCTION__,
- bio->bi_idx, bio->bi_vcnt);
+ printk(KERN_ERR "%s: bio idx %d >= vcnt %d\n",
+ __func__, idx, bio->bi_vcnt);
break;
}
total_bytes += nbytes;
nr_bytes -= nbytes;
- if ((bio = req->bio)) {
+ bio = req->bio;
+ if (bio) {
/*
* end more in this run, or just return 'not-done'
*/
/*
* completely done
*/
- if (!req->bio)
- return 0;
+ if (!req->bio) {
+ /*
+ * Reset counters so that the request stacking driver
+ * can find how many bytes remain in the request
+ * later.
+ */
+ req->__data_len = 0;
+ return false;
+ }
/*
* if the request wasn't completed, update state
bio_iovec(bio)->bv_len -= nr_bytes;
}
- blk_recalc_rq_sectors(req, total_bytes >> 9);
- blk_recalc_rq_segments(req);
- return 1;
-}
-
-/*
- * splice the completion data to a local structure and hand off to
- * process_completion_queue() to complete the requests
- */
-static void blk_done_softirq(struct softirq_action *h)
-{
- struct list_head *cpu_list, local_list;
-
- local_irq_disable();
- cpu_list = &__get_cpu_var(blk_cpu_done);
- list_replace_init(cpu_list, &local_list);
- local_irq_enable();
+ req->__data_len -= total_bytes;
+ req->buffer = bio_data(req->bio);
- while (!list_empty(&local_list)) {
- struct request *rq = list_entry(local_list.next, struct request, donelist);
+ /* update sector only for requests with clear definition of sector */
+ if (blk_fs_request(req) || blk_discard_rq(req))
+ req->__sector += total_bytes >> 9;
- list_del_init(&rq->donelist);
- rq->q->softirq_done_fn(rq);
+ /* mixed attributes always follow the first bio */
+ if (req->cmd_flags & REQ_MIXED_MERGE) {
+ req->cmd_flags &= ~REQ_FAILFAST_MASK;
+ req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
}
-}
-static int __cpuinit blk_cpu_notify(struct notifier_block *self, unsigned long action,
- void *hcpu)
-{
/*
- * If a CPU goes away, splice its entries to the current CPU
- * and trigger a run of the softirq
+ * If total number of sectors is less than the first segment
+ * size, something has gone terribly wrong.
*/
- if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
- int cpu = (unsigned long) hcpu;
-
- local_irq_disable();
- list_splice_init(&per_cpu(blk_cpu_done, cpu),
- &__get_cpu_var(blk_cpu_done));
- raise_softirq_irqoff(BLOCK_SOFTIRQ);
- local_irq_enable();
+ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
+ printk(KERN_ERR "blk: request botched\n");
+ req->__data_len = blk_rq_cur_bytes(req);
}
- return NOTIFY_OK;
-}
-
-
-static struct notifier_block blk_cpu_notifier __cpuinitdata = {
- .notifier_call = blk_cpu_notify,
-};
+ /* recalculate the number of segments */
+ blk_recalc_rq_segments(req);
-/**
- * blk_complete_request - end I/O on a request
- * @req: the request being processed
- *
- * Description:
- * Ends all I/O on a request. It does not handle partial completions,
- * unless the driver actually implements this in its completion callback
- * through requeueing. The actual completion happens out-of-order,
- * through a softirq handler. The user must have registered a completion
- * callback through blk_queue_softirq_done().
- **/
+ return true;
+}
+EXPORT_SYMBOL_GPL(blk_update_request);
-void blk_complete_request(struct request *req)
+static bool blk_update_bidi_request(struct request *rq, int error,
+ unsigned int nr_bytes,
+ unsigned int bidi_bytes)
{
- struct list_head *cpu_list;
- unsigned long flags;
+ if (blk_update_request(rq, error, nr_bytes))
+ return true;
- BUG_ON(!req->q->softirq_done_fn);
-
- local_irq_save(flags);
+ /* Bidi request must be completed as a whole */
+ if (unlikely(blk_bidi_rq(rq)) &&
+ blk_update_request(rq->next_rq, error, bidi_bytes))
+ return true;
- cpu_list = &__get_cpu_var(blk_cpu_done);
- list_add_tail(&req->donelist, cpu_list);
- raise_softirq_irqoff(BLOCK_SOFTIRQ);
+ add_disk_randomness(rq->rq_disk);
- local_irq_restore(flags);
+ return false;
}
-EXPORT_SYMBOL(blk_complete_request);
-
/*
* queue lock must be held
*/
-static void end_that_request_last(struct request *req, int error)
+static void blk_finish_request(struct request *req, int error)
{
- struct gendisk *disk = req->rq_disk;
-
if (blk_rq_tagged(req))
blk_queue_end_tag(req->q, req);
- if (blk_queued_rq(req))
- blkdev_dequeue_request(req);
-
- if (unlikely(laptop_mode) && blk_fs_request(req))
- laptop_io_completion();
-
- /*
- * Account IO completion. bar_rq isn't accounted as a normal
- * IO on queueing nor completion. Accounting the containing
- * request is enough.
- */
- if (disk && blk_fs_request(req) && req != &req->q->bar_rq) {
- unsigned long duration = jiffies - req->start_time;
- const int rw = rq_data_dir(req);
-
- __disk_stat_inc(disk, ios[rw]);
- __disk_stat_add(disk, ticks[rw], duration);
- disk_round_stats(disk);
- disk->in_flight--;
- }
+ BUG_ON(blk_queued_rq(req));
+
+ if (unlikely(laptop_mode) && blk_fs_request(req))
+ laptop_io_completion();
+
+ blk_delete_timer(req);
+
+ blk_account_io_done(req);
if (req->end_io)
req->end_io(req, error);
}
}
-static inline void __end_request(struct request *rq, int uptodate,
- unsigned int nr_bytes)
-{
- int error = 0;
-
- if (uptodate <= 0)
- error = uptodate ? uptodate : -EIO;
-
- __blk_end_request(rq, error, nr_bytes);
-}
-
/**
- * blk_rq_bytes - Returns bytes left to complete in the entire request
+ * blk_end_bidi_request - Complete a bidi request
+ * @rq: the request to complete
+ * @error: %0 for success, < %0 for error
+ * @nr_bytes: number of bytes to complete @rq
+ * @bidi_bytes: number of bytes to complete @rq->next_rq
+ *
+ * Description:
+ * Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
+ * Drivers that supports bidi can safely call this member for any
+ * type of request, bidi or uni. In the later case @bidi_bytes is
+ * just ignored.
+ *
+ * Return:
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
**/
-unsigned int blk_rq_bytes(struct request *rq)
+static bool blk_end_bidi_request(struct request *rq, int error,
+ unsigned int nr_bytes, unsigned int bidi_bytes)
{
- if (blk_fs_request(rq))
- return rq->hard_nr_sectors << 9;
-
- return rq->data_len;
-}
-EXPORT_SYMBOL_GPL(blk_rq_bytes);
+ struct request_queue *q = rq->q;
+ unsigned long flags;
-/**
- * blk_rq_cur_bytes - Returns bytes left to complete in the current segment
- **/
-unsigned int blk_rq_cur_bytes(struct request *rq)
-{
- if (blk_fs_request(rq))
- return rq->current_nr_sectors << 9;
+ if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
+ return true;
- if (rq->bio)
- return rq->bio->bi_size;
+ spin_lock_irqsave(q->queue_lock, flags);
+ blk_finish_request(rq, error);
+ spin_unlock_irqrestore(q->queue_lock, flags);
- return rq->data_len;
+ return false;
}
-EXPORT_SYMBOL_GPL(blk_rq_cur_bytes);
/**
- * end_queued_request - end all I/O on a queued request
- * @rq: the request being processed
- * @uptodate: error value or 0/1 uptodate flag
+ * __blk_end_bidi_request - Complete a bidi request with queue lock held
+ * @rq: the request to complete
+ * @error: %0 for success, < %0 for error
+ * @nr_bytes: number of bytes to complete @rq
+ * @bidi_bytes: number of bytes to complete @rq->next_rq
*
* Description:
- * Ends all I/O on a request, and removes it from the block layer queues.
- * Not suitable for normal IO completion, unless the driver still has
- * the request attached to the block layer.
+ * Identical to blk_end_bidi_request() except that queue lock is
+ * assumed to be locked on entry and remains so on return.
*
+ * Return:
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
**/
-void end_queued_request(struct request *rq, int uptodate)
+static bool __blk_end_bidi_request(struct request *rq, int error,
+ unsigned int nr_bytes, unsigned int bidi_bytes)
{
- __end_request(rq, uptodate, blk_rq_bytes(rq));
+ if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
+ return true;
+
+ blk_finish_request(rq, error);
+
+ return false;
}
-EXPORT_SYMBOL(end_queued_request);
/**
- * end_dequeued_request - end all I/O on a dequeued request
- * @rq: the request being processed
- * @uptodate: error value or 0/1 uptodate flag
+ * blk_end_request - Helper function for drivers to complete the request.
+ * @rq: the request being processed
+ * @error: %0 for success, < %0 for error
+ * @nr_bytes: number of bytes to complete
*
* Description:
- * Ends all I/O on a request. The request must already have been
- * dequeued using blkdev_dequeue_request(), as is normally the case
- * for most drivers.
+ * Ends I/O on a number of bytes attached to @rq.
+ * If @rq has leftover, sets it up for the next range of segments.
*
+ * Return:
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
**/
-void end_dequeued_request(struct request *rq, int uptodate)
+bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
{
- __end_request(rq, uptodate, blk_rq_bytes(rq));
+ return blk_end_bidi_request(rq, error, nr_bytes, 0);
}
-EXPORT_SYMBOL(end_dequeued_request);
-
+EXPORT_SYMBOL(blk_end_request);
/**
- * end_request - end I/O on the current segment of the request
- * @req: the request being processed
- * @uptodate: error value or 0/1 uptodate flag
+ * blk_end_request_all - Helper function for drives to finish the request.
+ * @rq: the request to finish
+ * @error: %0 for success, < %0 for error
*
* Description:
- * Ends I/O on the current segment of a request. If that is the only
- * remaining segment, the request is also completed and freed.
- *
- * This is a remnant of how older block drivers handled IO completions.
- * Modern drivers typically end IO on the full request in one go, unless
- * they have a residual value to account for. For that case this function
- * isn't really useful, unless the residual just happens to be the
- * full current segment. In other words, don't use this function in new
- * code. Either use end_request_completely(), or the
- * end_that_request_chunk() (along with end_that_request_last()) for
- * partial completions.
- *
- **/
-void end_request(struct request *req, int uptodate)
+ * Completely finish @rq.
+ */
+void blk_end_request_all(struct request *rq, int error)
{
- __end_request(req, uptodate, req->hard_cur_sectors << 9);
+ bool pending;
+ unsigned int bidi_bytes = 0;
+
+ if (unlikely(blk_bidi_rq(rq)))
+ bidi_bytes = blk_rq_bytes(rq->next_rq);
+
+ pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
+ BUG_ON(pending);
}
-EXPORT_SYMBOL(end_request);
+EXPORT_SYMBOL(blk_end_request_all);
/**
- * blk_end_io - Generic end_io function to complete a request.
- * @rq: the request being processed
- * @error: 0 for success, < 0 for error
- * @nr_bytes: number of bytes to complete @rq
- * @bidi_bytes: number of bytes to complete @rq->next_rq
- * @drv_callback: function called between completion of bios in the request
- * and completion of the request.
- * If the callback returns non 0, this helper returns without
- * completion of the request.
+ * blk_end_request_cur - Helper function to finish the current request chunk.
+ * @rq: the request to finish the current chunk for
+ * @error: %0 for success, < %0 for error
*
* Description:
- * Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
- * If @rq has leftover, sets it up for the next range of segments.
+ * Complete the current consecutively mapped chunk from @rq.
*
* Return:
- * 0 - we are done with this request
- * 1 - this request is not freed yet, it still has pending buffers.
- **/
-static int blk_end_io(struct request *rq, int error, int nr_bytes,
- int bidi_bytes, int (drv_callback)(struct request *))
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
+ */
+bool blk_end_request_cur(struct request *rq, int error)
{
- struct request_queue *q = rq->q;
- unsigned long flags = 0UL;
-
- if (blk_fs_request(rq) || blk_pc_request(rq)) {
- if (__end_that_request_first(rq, error, nr_bytes))
- return 1;
-
- /* Bidi request must be completed as a whole */
- if (blk_bidi_rq(rq) &&
- __end_that_request_first(rq->next_rq, error, bidi_bytes))
- return 1;
- }
-
- /* Special feature for tricky drivers */
- if (drv_callback && drv_callback(rq))
- return 1;
-
- add_disk_randomness(rq->rq_disk);
-
- spin_lock_irqsave(q->queue_lock, flags);
- end_that_request_last(rq, error);
- spin_unlock_irqrestore(q->queue_lock, flags);
-
- return 0;
+ return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
+EXPORT_SYMBOL(blk_end_request_cur);
/**
- * blk_end_request - Helper function for drivers to complete the request.
- * @rq: the request being processed
- * @error: 0 for success, < 0 for error
- * @nr_bytes: number of bytes to complete
+ * blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
*
* Description:
- * Ends I/O on a number of bytes attached to @rq.
- * If @rq has leftover, sets it up for the next range of segments.
+ * Complete @rq till the next failure boundary.
*
* Return:
- * 0 - we are done with this request
- * 1 - still buffers pending for this request
- **/
-int blk_end_request(struct request *rq, int error, int nr_bytes)
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
+ */
+bool blk_end_request_err(struct request *rq, int error)
{
- return blk_end_io(rq, error, nr_bytes, 0, NULL);
+ WARN_ON(error >= 0);
+ return blk_end_request(rq, error, blk_rq_err_bytes(rq));
}
-EXPORT_SYMBOL_GPL(blk_end_request);
+EXPORT_SYMBOL_GPL(blk_end_request_err);
/**
* __blk_end_request - Helper function for drivers to complete the request.
* @rq: the request being processed
- * @error: 0 for success, < 0 for error
+ * @error: %0 for success, < %0 for error
* @nr_bytes: number of bytes to complete
*
* Description:
* Must be called with queue lock held unlike blk_end_request().
*
* Return:
- * 0 - we are done with this request
- * 1 - still buffers pending for this request
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
**/
-int __blk_end_request(struct request *rq, int error, int nr_bytes)
+bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
{
- if (blk_fs_request(rq) || blk_pc_request(rq)) {
- if (__end_that_request_first(rq, error, nr_bytes))
- return 1;
- }
+ return __blk_end_bidi_request(rq, error, nr_bytes, 0);
+}
+EXPORT_SYMBOL(__blk_end_request);
- add_disk_randomness(rq->rq_disk);
+/**
+ * __blk_end_request_all - Helper function for drives to finish the request.
+ * @rq: the request to finish
+ * @error: %0 for success, < %0 for error
+ *
+ * Description:
+ * Completely finish @rq. Must be called with queue lock held.
+ */
+void __blk_end_request_all(struct request *rq, int error)
+{
+ bool pending;
+ unsigned int bidi_bytes = 0;
- end_that_request_last(rq, error);
+ if (unlikely(blk_bidi_rq(rq)))
+ bidi_bytes = blk_rq_bytes(rq->next_rq);
- return 0;
+ pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
+ BUG_ON(pending);
}
-EXPORT_SYMBOL_GPL(__blk_end_request);
+EXPORT_SYMBOL(__blk_end_request_all);
/**
- * blk_end_bidi_request - Helper function for drivers to complete bidi request.
- * @rq: the bidi request being processed
- * @error: 0 for success, < 0 for error
- * @nr_bytes: number of bytes to complete @rq
- * @bidi_bytes: number of bytes to complete @rq->next_rq
+ * __blk_end_request_cur - Helper function to finish the current request chunk.
+ * @rq: the request to finish the current chunk for
+ * @error: %0 for success, < %0 for error
*
* Description:
- * Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
+ * Complete the current consecutively mapped chunk from @rq. Must
+ * be called with queue lock held.
*
* Return:
- * 0 - we are done with this request
- * 1 - still buffers pending for this request
- **/
-int blk_end_bidi_request(struct request *rq, int error, int nr_bytes,
- int bidi_bytes)
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
+ */
+bool __blk_end_request_cur(struct request *rq, int error)
{
- return blk_end_io(rq, error, nr_bytes, bidi_bytes, NULL);
+ return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
-EXPORT_SYMBOL_GPL(blk_end_bidi_request);
+EXPORT_SYMBOL(__blk_end_request_cur);
/**
- * blk_end_request_callback - Special helper function for tricky drivers
- * @rq: the request being processed
- * @error: 0 for success, < 0 for error
- * @nr_bytes: number of bytes to complete
- * @drv_callback: function called between completion of bios in the request
- * and completion of the request.
- * If the callback returns non 0, this helper returns without
- * completion of the request.
+ * __blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
*
* Description:
- * Ends I/O on a number of bytes attached to @rq.
- * If @rq has leftover, sets it up for the next range of segments.
- *
- * This special helper function is used only for existing tricky drivers.
- * (e.g. cdrom_newpc_intr() of ide-cd)
- * This interface will be removed when such drivers are rewritten.
- * Don't use this interface in other places anymore.
+ * Complete @rq till the next failure boundary. Must be called
+ * with queue lock held.
*
* Return:
- * 0 - we are done with this request
- * 1 - this request is not freed yet.
- * this request still has pending buffers or
- * the driver doesn't want to finish this request yet.
- **/
-int blk_end_request_callback(struct request *rq, int error, int nr_bytes,
- int (drv_callback)(struct request *))
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
+ */
+bool __blk_end_request_err(struct request *rq, int error)
{
- return blk_end_io(rq, error, nr_bytes, 0, drv_callback);
+ WARN_ON(error >= 0);
+ return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
}
-EXPORT_SYMBOL_GPL(blk_end_request_callback);
+EXPORT_SYMBOL_GPL(__blk_end_request_err);
-static void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
- struct bio *bio)
+void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
+ struct bio *bio)
{
- /* first two bits are identical in rq->cmd_flags and bio->bi_rw */
- rq->cmd_flags |= (bio->bi_rw & 3);
-
- rq->nr_phys_segments = bio_phys_segments(q, bio);
- rq->nr_hw_segments = bio_hw_segments(q, bio);
- rq->current_nr_sectors = bio_cur_sectors(bio);
- rq->hard_cur_sectors = rq->current_nr_sectors;
- rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio);
- rq->buffer = bio_data(bio);
- rq->data_len = bio->bi_size;
+ /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
+ rq->cmd_flags |= bio->bi_rw & REQ_RW;
+ if (bio_has_data(bio)) {
+ rq->nr_phys_segments = bio_phys_segments(q, bio);
+ rq->buffer = bio_data(bio);
+ }
+ rq->__data_len = bio->bi_size;
rq->bio = rq->biotail = bio;
if (bio->bi_bdev)
rq->rq_disk = bio->bi_bdev->bd_disk;
}
-int kblockd_schedule_work(struct work_struct *work)
-{
- return queue_work(kblockd_workqueue, work);
-}
-
-EXPORT_SYMBOL(kblockd_schedule_work);
-
-void kblockd_flush_work(struct work_struct *work)
-{
- cancel_work_sync(work);
-}
-EXPORT_SYMBOL(kblockd_flush_work);
-
-int __init blk_dev_init(void)
-{
- int i;
-
- kblockd_workqueue = create_workqueue("kblockd");
- if (!kblockd_workqueue)
- panic("Failed to create kblockd\n");
-
- request_cachep = kmem_cache_create("blkdev_requests",
- sizeof(struct request), 0, SLAB_PANIC, NULL);
-
- requestq_cachep = kmem_cache_create("blkdev_queue",
- sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
-
- iocontext_cachep = kmem_cache_create("blkdev_ioc",
- sizeof(struct io_context), 0, SLAB_PANIC, NULL);
-
- for_each_possible_cpu(i)
- INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
-
- open_softirq(BLOCK_SOFTIRQ, blk_done_softirq, NULL);
- register_hotcpu_notifier(&blk_cpu_notifier);
-
- blk_max_low_pfn = max_low_pfn - 1;
- blk_max_pfn = max_pfn - 1;
-
- return 0;
-}
-
-static void cfq_dtor(struct io_context *ioc)
-{
- struct cfq_io_context *cic[1];
- int r;
-
- /*
- * We don't have a specific key to lookup with, so use the gang
- * lookup to just retrieve the first item stored. The cfq exit
- * function will iterate the full tree, so any member will do.
- */
- r = radix_tree_gang_lookup(&ioc->radix_root, (void **) cic, 0, 1);
- if (r > 0)
- cic[0]->dtor(ioc);
-}
-
-/*
- * IO Context helper functions. put_io_context() returns 1 if there are no
- * more users of this io context, 0 otherwise.
+/**
+ * blk_lld_busy - Check if underlying low-level drivers of a device are busy
+ * @q : the queue of the device being checked
+ *
+ * Description:
+ * Check if underlying low-level drivers of a device are busy.
+ * If the drivers want to export their busy state, they must set own
+ * exporting function using blk_queue_lld_busy() first.
+ *
+ * Basically, this function is used only by request stacking drivers
+ * to stop dispatching requests to underlying devices when underlying
+ * devices are busy. This behavior helps more I/O merging on the queue
+ * of the request stacking driver and prevents I/O throughput regression
+ * on burst I/O load.
+ *
+ * Return:
+ * 0 - Not busy (The request stacking driver should dispatch request)
+ * 1 - Busy (The request stacking driver should stop dispatching request)
*/
-int put_io_context(struct io_context *ioc)
+int blk_lld_busy(struct request_queue *q)
{
- if (ioc == NULL)
- return 1;
-
- BUG_ON(atomic_read(&ioc->refcount) == 0);
+ if (q->lld_busy_fn)
+ return q->lld_busy_fn(q);
- if (atomic_dec_and_test(&ioc->refcount)) {
- rcu_read_lock();
- if (ioc->aic && ioc->aic->dtor)
- ioc->aic->dtor(ioc->aic);
- rcu_read_unlock();
- cfq_dtor(ioc);
-
- kmem_cache_free(iocontext_cachep, ioc);
- return 1;
- }
return 0;
}
-EXPORT_SYMBOL(put_io_context);
+EXPORT_SYMBOL_GPL(blk_lld_busy);
-static void cfq_exit(struct io_context *ioc)
-{
- struct cfq_io_context *cic[1];
- int r;
-
- rcu_read_lock();
- /*
- * See comment for cfq_dtor()
- */
- r = radix_tree_gang_lookup(&ioc->radix_root, (void **) cic, 0, 1);
- rcu_read_unlock();
-
- if (r > 0)
- cic[0]->exit(ioc);
-}
-
-/* Called by the exitting task */
-void exit_io_context(void)
+/**
+ * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
+ * @rq: the clone request to be cleaned up
+ *
+ * Description:
+ * Free all bios in @rq for a cloned request.
+ */
+void blk_rq_unprep_clone(struct request *rq)
{
- struct io_context *ioc;
-
- task_lock(current);
- ioc = current->io_context;
- current->io_context = NULL;
- task_unlock(current);
-
- if (atomic_dec_and_test(&ioc->nr_tasks)) {
- if (ioc->aic && ioc->aic->exit)
- ioc->aic->exit(ioc->aic);
- cfq_exit(ioc);
+ struct bio *bio;
- put_io_context(ioc);
- }
-}
+ while ((bio = rq->bio) != NULL) {
+ rq->bio = bio->bi_next;
-struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
-{
- struct io_context *ret;
-
- ret = kmem_cache_alloc_node(iocontext_cachep, gfp_flags, node);
- if (ret) {
- atomic_set(&ret->refcount, 1);
- atomic_set(&ret->nr_tasks, 1);
- spin_lock_init(&ret->lock);
- ret->ioprio_changed = 0;
- ret->ioprio = 0;
- ret->last_waited = jiffies; /* doesn't matter... */
- ret->nr_batch_requests = 0; /* because this is 0 */
- ret->aic = NULL;
- INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
- ret->ioc_data = NULL;
+ bio_put(bio);
}
-
- return ret;
}
+EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
/*
- * If the current task has no IO context then create one and initialise it.
- * Otherwise, return its existing IO context.
- *
- * This returned IO context doesn't have a specifically elevated refcount,
- * but since the current task itself holds a reference, the context can be
- * used in general code, so long as it stays within `current` context.
+ * Copy attributes of the original request to the clone request.
+ * The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied.
*/
-static struct io_context *current_io_context(gfp_t gfp_flags, int node)
+static void __blk_rq_prep_clone(struct request *dst, struct request *src)
{
- struct task_struct *tsk = current;
- struct io_context *ret;
-
- ret = tsk->io_context;
- if (likely(ret))
- return ret;
-
- ret = alloc_io_context(gfp_flags, node);
- if (ret) {
- /* make sure set_task_ioprio() sees the settings above */
- smp_wmb();
- tsk->io_context = ret;
- }
-
- return ret;
+ dst->cpu = src->cpu;
+ dst->cmd_flags = (rq_data_dir(src) | REQ_NOMERGE);
+ dst->cmd_type = src->cmd_type;
+ dst->__sector = blk_rq_pos(src);
+ dst->__data_len = blk_rq_bytes(src);
+ dst->nr_phys_segments = src->nr_phys_segments;
+ dst->ioprio = src->ioprio;
+ dst->extra_len = src->extra_len;
}
-/*
- * If the current task has no IO context then create one and initialise it.
- * If it does have a context, take a ref on it.
+/**
+ * blk_rq_prep_clone - Helper function to setup clone request
+ * @rq: the request to be setup
+ * @rq_src: original request to be cloned
+ * @bs: bio_set that bios for clone are allocated from
+ * @gfp_mask: memory allocation mask for bio
+ * @bio_ctr: setup function to be called for each clone bio.
+ * Returns %0 for success, non %0 for failure.
+ * @data: private data to be passed to @bio_ctr
*
- * This is always called in the context of the task which submitted the I/O.
+ * Description:
+ * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
+ * The actual data parts of @rq_src (e.g. ->cmd, ->buffer, ->sense)
+ * are not copied, and copying such parts is the caller's responsibility.
+ * Also, pages which the original bios are pointing to are not copied
+ * and the cloned bios just point same pages.
+ * So cloned bios must be completed before original bios, which means
+ * the caller must complete @rq before @rq_src.
*/
-struct io_context *get_io_context(gfp_t gfp_flags, int node)
-{
- struct io_context *ret = NULL;
-
- /*
- * Check for unlikely race with exiting task. ioc ref count is
- * zero when ioc is being detached.
- */
- do {
- ret = current_io_context(gfp_flags, node);
- if (unlikely(!ret))
- break;
- } while (!atomic_inc_not_zero(&ret->refcount));
-
- return ret;
-}
-EXPORT_SYMBOL(get_io_context);
-
-void copy_io_context(struct io_context **pdst, struct io_context **psrc)
-{
- struct io_context *src = *psrc;
- struct io_context *dst = *pdst;
-
- if (src) {
- BUG_ON(atomic_read(&src->refcount) == 0);
- atomic_inc(&src->refcount);
- put_io_context(dst);
- *pdst = src;
- }
-}
-EXPORT_SYMBOL(copy_io_context);
-
-void swap_io_context(struct io_context **ioc1, struct io_context **ioc2)
+int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
+ struct bio_set *bs, gfp_t gfp_mask,
+ int (*bio_ctr)(struct bio *, struct bio *, void *),
+ void *data)
{
- struct io_context *temp;
- temp = *ioc1;
- *ioc1 = *ioc2;
- *ioc2 = temp;
-}
-EXPORT_SYMBOL(swap_io_context);
+ struct bio *bio, *bio_src;
-/*
- * sysfs parts below
- */
-struct queue_sysfs_entry {
- struct attribute attr;
- ssize_t (*show)(struct request_queue *, char *);
- ssize_t (*store)(struct request_queue *, const char *, size_t);
-};
-
-static ssize_t
-queue_var_show(unsigned int var, char *page)
-{
- return sprintf(page, "%d\n", var);
-}
+ if (!bs)
+ bs = fs_bio_set;
-static ssize_t
-queue_var_store(unsigned long *var, const char *page, size_t count)
-{
- char *p = (char *) page;
+ blk_rq_init(NULL, rq);
- *var = simple_strtoul(p, &p, 10);
- return count;
-}
+ __rq_for_each_bio(bio_src, rq_src) {
+ bio = bio_alloc_bioset(gfp_mask, bio_src->bi_max_vecs, bs);
+ if (!bio)
+ goto free_and_out;
-static ssize_t queue_requests_show(struct request_queue *q, char *page)
-{
- return queue_var_show(q->nr_requests, (page));
-}
+ __bio_clone(bio, bio_src);
-static ssize_t
-queue_requests_store(struct request_queue *q, const char *page, size_t count)
-{
- struct request_list *rl = &q->rq;
- unsigned long nr;
- int ret = queue_var_store(&nr, page, count);
- if (nr < BLKDEV_MIN_RQ)
- nr = BLKDEV_MIN_RQ;
+ if (bio_integrity(bio_src) &&
+ bio_integrity_clone(bio, bio_src, gfp_mask, bs))
+ goto free_and_out;
- spin_lock_irq(q->queue_lock);
- q->nr_requests = nr;
- blk_queue_congestion_threshold(q);
-
- if (rl->count[READ] >= queue_congestion_on_threshold(q))
- blk_set_queue_congested(q, READ);
- else if (rl->count[READ] < queue_congestion_off_threshold(q))
- blk_clear_queue_congested(q, READ);
-
- if (rl->count[WRITE] >= queue_congestion_on_threshold(q))
- blk_set_queue_congested(q, WRITE);
- else if (rl->count[WRITE] < queue_congestion_off_threshold(q))
- blk_clear_queue_congested(q, WRITE);
-
- if (rl->count[READ] >= q->nr_requests) {
- blk_set_queue_full(q, READ);
- } else if (rl->count[READ]+1 <= q->nr_requests) {
- blk_clear_queue_full(q, READ);
- wake_up(&rl->wait[READ]);
- }
+ if (bio_ctr && bio_ctr(bio, bio_src, data))
+ goto free_and_out;
- if (rl->count[WRITE] >= q->nr_requests) {
- blk_set_queue_full(q, WRITE);
- } else if (rl->count[WRITE]+1 <= q->nr_requests) {
- blk_clear_queue_full(q, WRITE);
- wake_up(&rl->wait[WRITE]);
+ if (rq->bio) {
+ rq->biotail->bi_next = bio;
+ rq->biotail = bio;
+ } else
+ rq->bio = rq->biotail = bio;
}
- spin_unlock_irq(q->queue_lock);
- return ret;
-}
-
-static ssize_t queue_ra_show(struct request_queue *q, char *page)
-{
- int ra_kb = q->backing_dev_info.ra_pages << (PAGE_CACHE_SHIFT - 10);
-
- return queue_var_show(ra_kb, (page));
-}
-
-static ssize_t
-queue_ra_store(struct request_queue *q, const char *page, size_t count)
-{
- unsigned long ra_kb;
- ssize_t ret = queue_var_store(&ra_kb, page, count);
-
- spin_lock_irq(q->queue_lock);
- q->backing_dev_info.ra_pages = ra_kb >> (PAGE_CACHE_SHIFT - 10);
- spin_unlock_irq(q->queue_lock);
-
- return ret;
-}
-
-static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
-{
- int max_sectors_kb = q->max_sectors >> 1;
-
- return queue_var_show(max_sectors_kb, (page));
-}
-
-static ssize_t
-queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
-{
- unsigned long max_sectors_kb,
- max_hw_sectors_kb = q->max_hw_sectors >> 1,
- page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
- ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
-
- if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
- return -EINVAL;
- /*
- * Take the queue lock to update the readahead and max_sectors
- * values synchronously:
- */
- spin_lock_irq(q->queue_lock);
- q->max_sectors = max_sectors_kb << 1;
- spin_unlock_irq(q->queue_lock);
- return ret;
-}
-
-static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
-{
- int max_hw_sectors_kb = q->max_hw_sectors >> 1;
-
- return queue_var_show(max_hw_sectors_kb, (page));
-}
+ __blk_rq_prep_clone(rq, rq_src);
+ return 0;
-static struct queue_sysfs_entry queue_requests_entry = {
- .attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
- .show = queue_requests_show,
- .store = queue_requests_store,
-};
-
-static struct queue_sysfs_entry queue_ra_entry = {
- .attr = {.name = "read_ahead_kb", .mode = S_IRUGO | S_IWUSR },
- .show = queue_ra_show,
- .store = queue_ra_store,
-};
-
-static struct queue_sysfs_entry queue_max_sectors_entry = {
- .attr = {.name = "max_sectors_kb", .mode = S_IRUGO | S_IWUSR },
- .show = queue_max_sectors_show,
- .store = queue_max_sectors_store,
-};
-
-static struct queue_sysfs_entry queue_max_hw_sectors_entry = {
- .attr = {.name = "max_hw_sectors_kb", .mode = S_IRUGO },
- .show = queue_max_hw_sectors_show,
-};
-
-static struct queue_sysfs_entry queue_iosched_entry = {
- .attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
- .show = elv_iosched_show,
- .store = elv_iosched_store,
-};
-
-static struct attribute *default_attrs[] = {
- &queue_requests_entry.attr,
- &queue_ra_entry.attr,
- &queue_max_hw_sectors_entry.attr,
- &queue_max_sectors_entry.attr,
- &queue_iosched_entry.attr,
- NULL,
-};
-
-#define to_queue(atr) container_of((atr), struct queue_sysfs_entry, attr)
-
-static ssize_t
-queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
-{
- struct queue_sysfs_entry *entry = to_queue(attr);
- struct request_queue *q =
- container_of(kobj, struct request_queue, kobj);
- ssize_t res;
+free_and_out:
+ if (bio)
+ bio_free(bio, bs);
+ blk_rq_unprep_clone(rq);
- if (!entry->show)
- return -EIO;
- mutex_lock(&q->sysfs_lock);
- if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)) {
- mutex_unlock(&q->sysfs_lock);
- return -ENOENT;
- }
- res = entry->show(q, page);
- mutex_unlock(&q->sysfs_lock);
- return res;
+ return -ENOMEM;
}
+EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
-static ssize_t
-queue_attr_store(struct kobject *kobj, struct attribute *attr,
- const char *page, size_t length)
+int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
{
- struct queue_sysfs_entry *entry = to_queue(attr);
- struct request_queue *q = container_of(kobj, struct request_queue, kobj);
-
- ssize_t res;
-
- if (!entry->store)
- return -EIO;
- mutex_lock(&q->sysfs_lock);
- if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)) {
- mutex_unlock(&q->sysfs_lock);
- return -ENOENT;
- }
- res = entry->store(q, page, length);
- mutex_unlock(&q->sysfs_lock);
- return res;
+ return queue_work(kblockd_workqueue, work);
}
+EXPORT_SYMBOL(kblockd_schedule_work);
-static struct sysfs_ops queue_sysfs_ops = {
- .show = queue_attr_show,
- .store = queue_attr_store,
-};
-
-static struct kobj_type queue_ktype = {
- .sysfs_ops = &queue_sysfs_ops,
- .default_attrs = default_attrs,
- .release = blk_release_queue,
-};
-
-int blk_register_queue(struct gendisk *disk)
+int __init blk_dev_init(void)
{
- int ret;
-
- struct request_queue *q = disk->queue;
-
- if (!q || !q->request_fn)
- return -ENXIO;
+ BUILD_BUG_ON(__REQ_NR_BITS > 8 *
+ sizeof(((struct request *)0)->cmd_flags));
- ret = kobject_add(&q->kobj, kobject_get(&disk->dev.kobj),
- "%s", "queue");
- if (ret < 0)
- return ret;
+ kblockd_workqueue = create_workqueue("kblockd");
+ if (!kblockd_workqueue)
+ panic("Failed to create kblockd\n");
- kobject_uevent(&q->kobj, KOBJ_ADD);
+ request_cachep = kmem_cache_create("blkdev_requests",
+ sizeof(struct request), 0, SLAB_PANIC, NULL);
- ret = elv_register_queue(q);
- if (ret) {
- kobject_uevent(&q->kobj, KOBJ_REMOVE);
- kobject_del(&q->kobj);
- return ret;
- }
+ blk_requestq_cachep = kmem_cache_create("blkdev_queue",
+ sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
return 0;
}
-void blk_unregister_queue(struct gendisk *disk)
-{
- struct request_queue *q = disk->queue;
-
- if (q && q->request_fn) {
- elv_unregister_queue(q);
-
- kobject_uevent(&q->kobj, KOBJ_REMOVE);
- kobject_del(&q->kobj);
- kobject_put(&disk->dev.kobj);
- }
-}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff