* 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/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>
+#include <trace/block.h>
#include "blk.h"
-static void drive_stat_acct(struct request *rq, int new_io);
+DEFINE_TRACE(block_plug);
+DEFINE_TRACE(block_unplug_io);
+DEFINE_TRACE(block_unplug_timer);
+DEFINE_TRACE(block_getrq);
+DEFINE_TRACE(block_sleeprq);
+DEFINE_TRACE(block_rq_requeue);
+DEFINE_TRACE(block_bio_backmerge);
+DEFINE_TRACE(block_bio_frontmerge);
+DEFINE_TRACE(block_bio_queue);
+DEFINE_TRACE(block_rq_complete);
+DEFINE_TRACE(block_remap); /* Also used in drivers/md/dm.c */
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+
static int __make_request(struct request_queue *q, struct bio *bio);
-static void blk_recalc_rq_segments(struct request *rq);
/*
* For the allocated request tables
*/
-struct kmem_cache *request_cachep;
+static struct kmem_cache *request_cachep;
/*
* For queue allocation
*/
-struct kmem_cache *blk_requestq_cachep = NULL;
+struct kmem_cache *blk_requestq_cachep;
/*
* Controlling structure to kblockd
*/
static struct workqueue_struct *kblockd_workqueue;
-static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
+static void drive_stat_acct(struct request *rq, int new_io)
+{
+ struct hd_struct *part;
+ int rw = rq_data_dir(rq);
+ int cpu;
+
+ if (!blk_fs_request(rq) || !blk_do_io_stat(rq))
+ return;
+
+ cpu = part_stat_lock();
+ part = disk_map_sector_rcu(rq->rq_disk, rq->sector);
+
+ if (!new_io)
+ part_stat_inc(cpu, part, merges[rw]);
+ else {
+ part_round_stats(cpu, part);
+ part_inc_in_flight(part);
+ }
+
+ part_stat_unlock();
+}
void blk_queue_congestion_threshold(struct request_queue *q)
{
}
EXPORT_SYMBOL(blk_get_backing_dev_info);
-void rq_init(struct request_queue *q, struct request *rq)
+void blk_rq_init(struct request_queue *q, struct request *rq)
{
- INIT_LIST_HEAD(&rq->queuelist);
- INIT_LIST_HEAD(&rq->donelist);
+ memset(rq, 0, sizeof(*rq));
- rq->errors = 0;
- rq->bio = rq->biotail = NULL;
+ INIT_LIST_HEAD(&rq->queuelist);
+ INIT_LIST_HEAD(&rq->timeout_list);
+ rq->cpu = -1;
+ rq->q = q;
+ rq->sector = rq->hard_sector = (sector_t) -1;
INIT_HLIST_NODE(&rq->hash);
RB_CLEAR_NODE(&rq->rb_node);
- rq->ioprio = 0;
- rq->buffer = NULL;
+ rq->cmd = rq->__cmd;
+ rq->cmd_len = BLK_MAX_CDB;
+ rq->tag = -1;
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;
}
+EXPORT_SYMBOL(blk_rq_init);
static void req_bio_endio(struct request *rq, struct bio *bio,
unsigned int nbytes, int error)
error = -EIO;
if (unlikely(nbytes > bio->bi_size)) {
- printk("%s: want %u bytes done, only %u left\n",
- __FUNCTION__, nbytes, bio->bi_size);
+ printk(KERN_ERR "%s: want %u bytes done, %u left\n",
+ __func__, nbytes, bio->bi_size);
nbytes = bio->bi_size;
}
+ if (unlikely(rq->cmd_flags & REQ_QUIET))
+ set_bit(BIO_QUIET, &bio->bi_flags);
+
bio->bi_size -= nbytes;
bio->bi_sector += (nbytes >> 9);
+
+ if (bio_integrity(bio))
+ bio_integrity_advance(bio, nbytes);
+
if (bio->bi_size == 0)
bio_endio(bio, error);
} else {
{
int bit;
- printk("%s: dev %s: type=%x, flags=%x\n", msg,
+ printk(KERN_INFO "%s: dev %s: type=%x, flags=%x\n", msg,
rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
rq->cmd_flags);
- printk("\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);
+ printk(KERN_INFO " sector %llu, nr/cnr %lu/%u\n",
+ (unsigned long long)rq->sector,
+ rq->nr_sectors,
+ rq->current_nr_sectors);
+ printk(KERN_INFO " 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(KERN_INFO " cdb: ");
+ for (bit = 0; bit < BLK_MAX_CDB; bit++)
printk("%02x ", rq->cmd[bit]);
printk("\n");
}
}
-
EXPORT_SYMBOL(blk_dump_rq_flags);
-void blk_recount_segments(struct request_queue *q, struct bio *bio)
-{
- struct request rq;
- struct bio *nxt = bio->bi_next;
- rq.q = q;
- rq.bio = rq.biotail = bio;
- bio->bi_next = NULL;
- blk_recalc_rq_segments(&rq);
- bio->bi_next = nxt;
- bio->bi_phys_segments = rq.nr_phys_segments;
- bio->bi_hw_segments = rq.nr_hw_segments;
- bio->bi_flags |= (1 << BIO_SEG_VALID);
-}
-EXPORT_SYMBOL(blk_recount_segments);
-
-static void blk_recalc_rq_segments(struct request *rq)
-{
- int nr_phys_segs;
- int nr_hw_segs;
- unsigned int phys_size;
- unsigned int hw_size;
- struct bio_vec *bv, *bvprv = NULL;
- int seg_size;
- int hw_seg_size;
- int cluster;
- struct req_iterator iter;
- int high, highprv = 1;
- struct request_queue *q = rq->q;
-
- if (!rq->bio)
- return;
-
- cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
- hw_seg_size = seg_size = 0;
- phys_size = hw_size = nr_phys_segs = nr_hw_segs = 0;
- rq_for_each_segment(bv, rq, iter) {
- /*
- * the trick here is making sure that a high page is never
- * considered part of another segment, since that might
- * change with the bounce page.
- */
- high = page_to_pfn(bv->bv_page) > q->bounce_pfn;
- if (high || highprv)
- goto new_hw_segment;
- if (cluster) {
- if (seg_size + bv->bv_len > q->max_segment_size)
- goto new_segment;
- if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
- goto new_segment;
- if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
- goto new_segment;
- if (BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len))
- goto new_hw_segment;
-
- seg_size += bv->bv_len;
- hw_seg_size += bv->bv_len;
- bvprv = bv;
- continue;
- }
-new_segment:
- if (BIOVEC_VIRT_MERGEABLE(bvprv, bv) &&
- !BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len))
- hw_seg_size += bv->bv_len;
- else {
-new_hw_segment:
- if (nr_hw_segs == 1 &&
- hw_seg_size > rq->bio->bi_hw_front_size)
- rq->bio->bi_hw_front_size = hw_seg_size;
- hw_seg_size = BIOVEC_VIRT_START_SIZE(bv) + bv->bv_len;
- nr_hw_segs++;
- }
-
- nr_phys_segs++;
- bvprv = bv;
- seg_size = bv->bv_len;
- highprv = high;
- }
-
- if (nr_hw_segs == 1 &&
- hw_seg_size > rq->bio->bi_hw_front_size)
- rq->bio->bi_hw_front_size = hw_seg_size;
- if (hw_seg_size > rq->biotail->bi_hw_back_size)
- rq->biotail->bi_hw_back_size = hw_seg_size;
- rq->nr_phys_segments = nr_phys_segs;
- rq->nr_hw_segments = nr_hw_segs;
-}
-
-static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
- struct bio *nxt)
-{
- if (!(q->queue_flags & (1 << QUEUE_FLAG_CLUSTER)))
- return 0;
-
- if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
- return 0;
- if (bio->bi_size + nxt->bi_size > q->max_segment_size)
- return 0;
-
- /*
- * bio and nxt are contigous in memory, check if the queue allows
- * these two to be merged into one
- */
- if (BIO_SEG_BOUNDARY(q, bio, nxt))
- return 1;
-
- return 0;
-}
-
-static int blk_hw_contig_segment(struct request_queue *q, struct bio *bio,
- struct bio *nxt)
-{
- if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
- blk_recount_segments(q, bio);
- if (unlikely(!bio_flagged(nxt, BIO_SEG_VALID)))
- blk_recount_segments(q, nxt);
- if (!BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)) ||
- BIOVEC_VIRT_OVERSIZE(bio->bi_hw_back_size + nxt->bi_hw_front_size))
- return 0;
- if (bio->bi_hw_back_size + nxt->bi_hw_front_size > q->max_segment_size)
- return 0;
-
- return 1;
-}
-
-/*
- * map a request to scatterlist, return number of sg entries setup. Caller
- * must make sure sg can hold rq->nr_phys_segments entries
- */
-int blk_rq_map_sg(struct request_queue *q, struct request *rq,
- struct scatterlist *sglist)
-{
- struct bio_vec *bvec, *bvprv;
- struct req_iterator iter;
- struct scatterlist *sg;
- int nsegs, cluster;
-
- nsegs = 0;
- cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
-
- /*
- * for each bio in rq
- */
- bvprv = NULL;
- sg = NULL;
- rq_for_each_segment(bvec, rq, iter) {
- int nbytes = bvec->bv_len;
-
- if (bvprv && cluster) {
- if (sg->length + nbytes > q->max_segment_size)
- goto new_segment;
-
- if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
- goto new_segment;
- if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
- goto new_segment;
-
- sg->length += nbytes;
- } else {
-new_segment:
- if (!sg)
- sg = sglist;
- else {
- /*
- * If the driver previously mapped a shorter
- * list, we could see a termination bit
- * prematurely unless it fully inits the sg
- * table on each mapping. We KNOW that there
- * must be more entries here or the driver
- * would be buggy, so force clear the
- * termination bit to avoid doing a full
- * sg_init_table() in drivers for each command.
- */
- sg->page_link &= ~0x02;
- sg = sg_next(sg);
- }
-
- sg_set_page(sg, bvec->bv_page, nbytes, bvec->bv_offset);
- nsegs++;
- }
- bvprv = bvec;
- } /* segments in rq */
-
- if (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++;
- }
-
- if (sg)
- sg_mark_end(sg);
-
- return nsegs;
-}
-
-EXPORT_SYMBOL(blk_rq_map_sg);
-
-/*
- * the standard queue merge functions, can be overridden with device
- * specific ones if so desired
- */
-
-static inline int ll_new_mergeable(struct request_queue *q,
- struct request *req,
- struct bio *bio)
-{
- int nr_phys_segs = bio_phys_segments(q, bio);
-
- if (req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
- req->cmd_flags |= REQ_NOMERGE;
- if (req == q->last_merge)
- q->last_merge = NULL;
- return 0;
- }
-
- /*
- * A hw segment is just getting larger, bump just the phys
- * counter.
- */
- req->nr_phys_segments += nr_phys_segs;
- return 1;
-}
-
-static inline int ll_new_hw_segment(struct request_queue *q,
- struct request *req,
- struct bio *bio)
-{
- int nr_hw_segs = bio_hw_segments(q, bio);
- int nr_phys_segs = bio_phys_segments(q, bio);
-
- if (req->nr_hw_segments + nr_hw_segs > q->max_hw_segments
- || req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
- req->cmd_flags |= REQ_NOMERGE;
- if (req == q->last_merge)
- q->last_merge = NULL;
- return 0;
- }
-
- /*
- * This will form the start of a new hw segment. Bump both
- * counters.
- */
- req->nr_hw_segments += nr_hw_segs;
- req->nr_phys_segments += nr_phys_segs;
- return 1;
-}
-
-int ll_back_merge_fn(struct request_queue *q, struct request *req,
- struct bio *bio)
-{
- unsigned short max_sectors;
- int len;
-
- if (unlikely(blk_pc_request(req)))
- max_sectors = q->max_hw_sectors;
- else
- max_sectors = q->max_sectors;
-
- if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
- req->cmd_flags |= REQ_NOMERGE;
- if (req == q->last_merge)
- q->last_merge = NULL;
- return 0;
- }
- if (unlikely(!bio_flagged(req->biotail, BIO_SEG_VALID)))
- blk_recount_segments(q, req->biotail);
- if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
- blk_recount_segments(q, bio);
- len = req->biotail->bi_hw_back_size + bio->bi_hw_front_size;
- if (BIOVEC_VIRT_MERGEABLE(__BVEC_END(req->biotail), __BVEC_START(bio)) &&
- !BIOVEC_VIRT_OVERSIZE(len)) {
- int mergeable = ll_new_mergeable(q, req, bio);
-
- if (mergeable) {
- if (req->nr_hw_segments == 1)
- req->bio->bi_hw_front_size = len;
- if (bio->bi_hw_segments == 1)
- bio->bi_hw_back_size = len;
- }
- return mergeable;
- }
-
- return ll_new_hw_segment(q, req, bio);
-}
-
-static int ll_front_merge_fn(struct request_queue *q, struct request *req,
- struct bio *bio)
-{
- unsigned short max_sectors;
- int len;
-
- if (unlikely(blk_pc_request(req)))
- max_sectors = q->max_hw_sectors;
- else
- max_sectors = q->max_sectors;
-
-
- if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
- req->cmd_flags |= REQ_NOMERGE;
- if (req == q->last_merge)
- q->last_merge = NULL;
- return 0;
- }
- len = bio->bi_hw_back_size + req->bio->bi_hw_front_size;
- if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
- blk_recount_segments(q, bio);
- if (unlikely(!bio_flagged(req->bio, BIO_SEG_VALID)))
- blk_recount_segments(q, req->bio);
- if (BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(req->bio)) &&
- !BIOVEC_VIRT_OVERSIZE(len)) {
- int mergeable = ll_new_mergeable(q, req, bio);
-
- if (mergeable) {
- if (bio->bi_hw_segments == 1)
- bio->bi_hw_front_size = len;
- if (req->nr_hw_segments == 1)
- req->biotail->bi_hw_back_size = len;
- }
- return mergeable;
- }
-
- return ll_new_hw_segment(q, req, bio);
-}
-
-static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
- struct request *next)
-{
- int total_phys_segments;
- int total_hw_segments;
-
- /*
- * First check if the either of the requests are re-queued
- * requests. Can't merge them if they are.
- */
- if (req->special || next->special)
- return 0;
-
- /*
- * Will it become too large?
- */
- if ((req->nr_sectors + next->nr_sectors) > q->max_sectors)
- return 0;
-
- total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
- if (blk_phys_contig_segment(q, req->biotail, next->bio))
- total_phys_segments--;
-
- if (total_phys_segments > q->max_phys_segments)
- return 0;
-
- total_hw_segments = req->nr_hw_segments + next->nr_hw_segments;
- if (blk_hw_contig_segment(q, req->biotail, next->bio)) {
- int len = req->biotail->bi_hw_back_size + next->bio->bi_hw_front_size;
- /*
- * propagate the combined length to the end of the requests
- */
- if (req->nr_hw_segments == 1)
- req->bio->bi_hw_front_size = len;
- if (next->nr_hw_segments == 1)
- next->biotail->bi_hw_back_size = len;
- total_hw_segments--;
- }
-
- if (total_hw_segments > q->max_hw_segments)
- return 0;
-
- /* Merge is OK... */
- req->nr_phys_segments = total_phys_segments;
- req->nr_hw_segments = total_hw_segments;
- return 1;
-}
-
/*
* "plug" the device if there are no outstanding requests: this will
* force the transfer to start only after we have put all the requests
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);
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);
}
{
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);
}
+}
+EXPORT_SYMBOL(__blk_run_queue);
+
+/**
+ * blk_run_queue - run a single device queue
+ * @q: The queue to run
+ *
+ * Description:
+ * Invoke request handling on this queue, if it has pending work to do.
+ * May be used to restart queueing when a request has completed.
+ */
+void blk_run_queue(struct request_queue *q)
+{
+ unsigned long flags;
+ spin_lock_irqsave(q->queue_lock, flags);
+ __blk_run_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_run_queue);
{
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);
}
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, &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:
* if caller didn't supply a lock, they get per-queue locking with
* our embedded lock
*/
- if (!lock) {
- spin_lock_init(&q->__queue_lock);
+ if (!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;
+ blk_set_cmd_filter_defaults(&q->cmd_filter);
+
/*
* all done
*/
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.
- */
-void blk_start_queueing(struct request_queue *q)
-{
- if (!blk_queue_plugged(q))
- q->request_fn(q);
- else
- __generic_unplug_device(q);
-}
-EXPORT_SYMBOL(blk_start_queueing);
-
/**
* blk_requeue_request - put a request back on queue
* @q: request queue where request should be inserted
*/
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);
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 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.
- *
- * The average IO queue length and utilisation statistics are maintained
- * by observing the current state of the queue length and the amount of
- * time it has been in this state for.
- *
- * Normally, that accounting is done on IO completion, but that can result
- * in more than a second's worth of IO being accounted for within any one
+
+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_stat_add(cpu, part, time_in_queue,
+ part->in_flight * (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
+ * time it has been in this state for.
+ *
+ * Normally, that accounting is done on IO completion, but that can result
+ * in more than a second's worth of IO being accounted for within any one
* second, leading to >100% utilisation. To deal with that, we call this
* function to do a round-off before returning the results when reading
* /proc/diskstats. This accounts immediately for all queue usage up to
* the current jiffies and restarts the counters again.
*/
-void disk_round_stats(struct gendisk *disk)
+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);
-/*
- * 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;
-}
-
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)
*/
- if (bio_rw_ahead(bio) || bio_failfast(bio))
- req->cmd_flags |= REQ_FAILFAST;
-
- /*
- * REQ_BARRIER implies no merging, but lets make it explicit
- */
- if (unlikely(bio_barrier(bio)))
- req->cmd_flags |= (REQ_HARDBARRIER | REQ_NOMERGE);
+ if (bio_rw_ahead(bio))
+ req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+ REQ_FAILFAST_DRIVER);
+ if (bio_failfast_dev(bio))
+ req->cmd_flags |= REQ_FAILFAST_DEV;
+ if (bio_failfast_transport(bio))
+ req->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+ if (bio_failfast_driver(bio))
+ req->cmd_flags |= REQ_FAILFAST_DRIVER;
+
+ if (unlikely(bio_discard(bio))) {
+ req->cmd_flags |= REQ_DISCARD;
+ if (bio_barrier(bio))
+ req->cmd_flags |= REQ_SOFTBARRIER;
+ req->q->prepare_discard_fn(req->q, req);
+ } else if (unlikely(bio_barrier(bio)))
+ req->cmd_flags |= REQ_HARDBARRIER;
if (bio_sync(bio))
req->cmd_flags |= REQ_RW_SYNC;
if (bio_rw_meta(bio))
req->cmd_flags |= REQ_RW_META;
+ if (bio_noidle(bio))
+ req->cmd_flags |= REQ_NOIDLE;
req->errors = 0;
req->hard_sector = req->sector = bio->bi_sector;
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_tagged(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, nr_sectors;
const unsigned short prio = bio_prio(bio);
const int sync = bio_sync(bio);
+ const int unplug = bio_unplug(bio);
int rw_flags;
nr_sectors = bio_sectors(bio);
*/
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_barrier(bio)) || 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);
+ 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;
- 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;
+ case ELEVATOR_FRONT_MERGE:
+ BUG_ON(!rq_mergeable(req));
- case ELEVATOR_FRONT_MERGE:
- BUG_ON(!rq_mergeable(req));
+ if (!ll_front_merge_fn(q, req, bio))
+ break;
- if (!ll_front_merge_fn(q, req, bio))
- break;
+ trace_block_bio_frontmerge(q, bio);
- blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
+ bio->bi_next = req->bio;
+ req->bio = bio;
- bio->bi_next = req->bio;
- req->bio = bio;
+ /*
+ * may not be valid. if the low level driver said
+ * it didn't need a bounce buffer then it better
+ * not touch req->buffer either...
+ */
+ req->buffer = bio_data(bio);
+ req->current_nr_sectors = 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);
+ 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;
- /*
- * 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:
- ;
+ /* 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,
+ trace_block_remap(bdev_get_queue(bio->bi_bdev), bio,
bdev->bd_dev, bio->bi_sector,
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",
+ printk(KERN_ERR "bio too big device %s (%u > %u)\n",
bdevname(bio->bi_bdev, b),
bio_sectors(bio),
q->max_hw_sectors);
*/
blk_partition_remap(bio);
+ if (bio_integrity_enabled(bio) && bio_integrity_prep(bio))
+ goto end_io;
+
if (old_sector != -1)
- blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
+ trace_block_remap(q, bio, old_dev, bio->bi_sector,
old_sector);
- blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
+ trace_block_bio_queue(q, bio);
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_discard(bio) && !q->prepare_discard_fn) {
+ err = -EOPNOTSUPP;
+ goto end_io;
+ }
+ if (bio_barrier(bio) && bio_has_data(bio) &&
+ (q->next_ordered == QUEUE_ORDERED_NONE)) {
err = -EOPNOTSUPP;
goto end_io;
}
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 (rq->nr_sectors > q->max_sectors ||
+ rq->data_len > q->max_hw_sectors << 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 > q->max_phys_segments ||
+ rq->nr_phys_segments > q->max_hw_segments) {
+ 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);
+
+/**
+ * blkdev_dequeue_request - dequeue request and start timeout timer
+ * @req: request to dequeue
+ *
+ * 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 elv_dequeue_request().
+ */
+void blkdev_dequeue_request(struct request *req)
+{
+ elv_dequeue_request(req->q, req);
+
+ /*
+ * We are now handing the request to the hardware, add the
+ * timeout handler.
+ */
+ blk_add_timer(req);
+}
+EXPORT_SYMBOL(blkdev_dequeue_request);
+
+static void blk_account_io_completion(struct request *req, unsigned int bytes)
+{
+ if (!blk_do_io_stat(req))
+ return;
+
+ if (blk_fs_request(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, req->sector);
+ part_stat_add(cpu, part, sectors[rw], bytes >> 9);
+ part_stat_unlock();
+ }
+}
+
+static void blk_account_io_done(struct request *req)
+{
+ if (!blk_do_io_stat(req))
+ return;
+
+ /*
+ * Account IO completion. bar_rq isn't accounted as a normal
+ * IO on queueing nor completion. Accounting the containing
+ * request is enough.
+ */
+ if (blk_fs_request(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, req->sector);
+
+ 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);
+
+ part_stat_unlock();
+ }
+}
+
+/**
+ * blk_rq_bytes - Returns bytes left to complete in the entire request
+ * @rq: the request being processed
+ **/
+unsigned int blk_rq_bytes(struct request *rq)
+{
+ if (blk_fs_request(rq))
+ return rq->hard_nr_sectors << 9;
+
+ return rq->data_len;
+}
+EXPORT_SYMBOL_GPL(blk_rq_bytes);
+
+/**
+ * blk_rq_cur_bytes - Returns bytes left to complete in the current segment
+ * @rq: the request being processed
+ **/
+unsigned int blk_rq_cur_bytes(struct request *rq)
+{
+ if (blk_fs_request(rq))
+ return rq->current_nr_sectors << 9;
+
+ if (rq->bio)
+ return rq->bio->bi_size;
+
+ return rq->data_len;
+}
+EXPORT_SYMBOL_GPL(blk_rq_cur_bytes);
+
+struct request *elv_next_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 total number of sectors is less than the first segment
- * size, something has gone terribly wrong
- */
- if (rq->nr_sectors < rq->current_nr_sectors) {
- printk("blk: request botched\n");
- rq->nr_sectors = rq->current_nr_sectors;
+ 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 && rq->data_len) {
+ /*
+ * 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 && rq->data_len &&
+ !(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;
+ __blk_end_request(rq, -EIO, blk_rq_bytes(rq));
+ } else {
+ printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
+ break;
}
}
+
+ return rq;
+}
+EXPORT_SYMBOL(elv_next_request);
+
+void elv_dequeue_request(struct request_queue *q, struct request *rq)
+{
+ 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++;
}
/**
* __end_that_request_first - end I/O on a request
* @req: 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:
* for the next range of segments (if any) in the cluster.
*
* Return:
- * 0 - we are done with this request, call end_that_request_last()
- * 1 - still buffers pending for this request
+ * %0 - we are done with this request, call end_that_request_last()
+ * %1 - still buffers pending for this request
**/
static int __end_that_request_first(struct request *req, int error,
int nr_bytes)
int total_bytes, bio_nbytes, next_idx = 0;
struct bio *bio;
- blk_add_trace_rq(req->q, req, BLK_TA_COMPLETE);
+ 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);
}
- 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;
if (unlikely(bio->bi_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__, bio->bi_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'
*/
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)
+static int end_that_request_data(struct request *rq, int error,
+ unsigned int nr_bytes, unsigned int bidi_bytes)
{
- 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();
-
- while (!list_empty(&local_list)) {
- struct request *rq = list_entry(local_list.next, struct request, donelist);
-
- list_del_init(&rq->donelist);
- rq->q->softirq_done_fn(rq);
- }
-}
+ if (rq->bio) {
+ if (__end_that_request_first(rq, error, nr_bytes))
+ return 1;
-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 (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();
+ /* 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;
}
- return NOTIFY_OK;
-}
-
-
-static struct notifier_block blk_cpu_notifier __cpuinitdata = {
- .notifier_call = blk_cpu_notify,
-};
-
-/**
- * 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().
- **/
-
-void blk_complete_request(struct request *req)
-{
- struct list_head *cpu_list;
- unsigned long flags;
-
- BUG_ON(!req->q->softirq_done_fn);
-
- local_irq_save(flags);
-
- cpu_list = &__get_cpu_var(blk_cpu_done);
- list_add_tail(&req->donelist, cpu_list);
- raise_softirq_irqoff(BLOCK_SOFTIRQ);
-
- local_irq_restore(flags);
+ return 0;
}
-EXPORT_SYMBOL(blk_complete_request);
-
/*
* queue lock must be held
*/
static void end_that_request_last(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);
+ elv_dequeue_request(req->q, 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);
+ blk_delete_timer(req);
- __disk_stat_inc(disk, ios[rw]);
- __disk_stat_add(disk, ticks[rw], duration);
- disk_round_stats(disk);
- disk->in_flight--;
- }
+ 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
- **/
-unsigned int blk_rq_bytes(struct request *rq)
-{
- if (blk_fs_request(rq))
- return rq->hard_nr_sectors << 9;
-
- return rq->data_len;
-}
-EXPORT_SYMBOL_GPL(blk_rq_bytes);
-
-/**
- * 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 (rq->bio)
- return rq->bio->bi_size;
-
- return rq->data_len;
-}
-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
- *
- * 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.
- *
- **/
-void end_queued_request(struct request *rq, int uptodate)
-{
- __end_request(rq, uptodate, blk_rq_bytes(rq));
-}
-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
- *
- * 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.
- *
- **/
-void end_dequeued_request(struct request *rq, int uptodate)
-{
- __end_request(rq, uptodate, blk_rq_bytes(rq));
-}
-EXPORT_SYMBOL(end_dequeued_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
- *
- * 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)
-{
- __end_request(req, uptodate, req->hard_cur_sectors << 9);
-}
-EXPORT_SYMBOL(end_request);
-
/**
* blk_end_io - Generic end_io function to complete a 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 @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.
*
* 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.
*
* Return:
- * 0 - we are done with this request
- * 1 - this request is not freed yet, it still has pending buffers.
+ * %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 *))
+static int blk_end_io(struct request *rq, int error, unsigned int nr_bytes,
+ unsigned int bidi_bytes)
{
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))
+ if (end_that_request_data(rq, error, nr_bytes, bidi_bytes))
return 1;
add_disk_randomness(rq->rq_disk);
/**
* 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:
* If @rq has leftover, sets it up for the next range of segments.
*
* Return:
- * 0 - we are done with this request
- * 1 - still buffers pending for this request
+ * %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)
+int blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
{
- return blk_end_io(rq, error, nr_bytes, 0, NULL);
+ return blk_end_io(rq, error, nr_bytes, 0);
}
EXPORT_SYMBOL_GPL(blk_end_request);
/**
* __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
+ * %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)
+int __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;
- }
+ if (rq->bio && __end_that_request_first(rq, error, nr_bytes))
+ return 1;
add_disk_randomness(rq->rq_disk);
/**
* 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
+ * @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
*
* Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
*
* Return:
- * 0 - we are done with this request
- * 1 - still buffers pending for this request
+ * %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)
+int blk_end_bidi_request(struct request *rq, int error, unsigned int nr_bytes,
+ unsigned int bidi_bytes)
{
- return blk_end_io(rq, error, nr_bytes, bidi_bytes, NULL);
+ return blk_end_io(rq, error, nr_bytes, bidi_bytes);
}
EXPORT_SYMBOL_GPL(blk_end_bidi_request);
/**
- * blk_end_request_callback - Special helper function for tricky drivers
+ * 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
+ *
+ * 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 I/O completions.
+ * Modern drivers typically end I/O 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. Use blk_end_request() or __blk_end_request() to end a request.
+ **/
+void end_request(struct request *req, int uptodate)
+{
+ int error = 0;
+
+ if (uptodate <= 0)
+ error = uptodate ? uptodate : -EIO;
+
+ __blk_end_request(req, error, req->hard_cur_sectors << 9);
+}
+EXPORT_SYMBOL(end_request);
+
+/**
+ * blk_update_request - Special helper function for request stacking 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.
+ * @error: %0 for success, < %0 for error
+ * @nr_bytes: number of bytes to complete @rq
*
* Description:
- * Ends I/O on a number of bytes attached to @rq.
+ * Ends I/O on a number of bytes attached to @rq, but doesn't complete
+ * the request structure even if @rq doesn't have leftover.
* 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.
- *
- * 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 *))
+ * 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.
+ */
+void blk_update_request(struct request *rq, int error, unsigned int nr_bytes)
{
- return blk_end_io(rq, error, nr_bytes, 0, drv_callback);
+ if (!end_that_request_data(rq, error, nr_bytes, 0)) {
+ /*
+ * These members are not updated in end_that_request_data()
+ * when all bios are completed.
+ * Update them so that the request stacking driver can find
+ * how many bytes remain in the request later.
+ */
+ rq->nr_sectors = rq->hard_nr_sectors = 0;
+ rq->current_nr_sectors = rq->hard_cur_sectors = 0;
+ }
}
-EXPORT_SYMBOL_GPL(blk_end_request_callback);
+EXPORT_SYMBOL_GPL(blk_update_request);
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 */
+ /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw, and
+ we want BIO_RW_AHEAD (bit 1) to imply REQ_FAILFAST (bit 1). */
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);
+ if (bio_has_data(bio)) {
+ rq->nr_phys_segments = bio_phys_segments(q, bio);
+ rq->buffer = bio_data(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;
rq->bio = rq->biotail = bio;
rq->rq_disk = bio->bi_bdev->bd_disk;
}
-int kblockd_schedule_work(struct work_struct *work)
+/**
+ * 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 blk_lld_busy(struct request_queue *q)
{
- return queue_work(kblockd_workqueue, work);
-}
+ if (q->lld_busy_fn)
+ return q->lld_busy_fn(q);
-EXPORT_SYMBOL(kblockd_schedule_work);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(blk_lld_busy);
-void kblockd_flush_work(struct work_struct *work)
+int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
{
- cancel_work_sync(work);
+ return queue_work(kblockd_workqueue, work);
}
-EXPORT_SYMBOL(kblockd_flush_work);
+EXPORT_SYMBOL(kblockd_schedule_work);
int __init blk_dev_init(void)
{
- int i;
-
kblockd_workqueue = create_workqueue("kblockd");
if (!kblockd_workqueue)
panic("Failed to create kblockd\n");
blk_requestq_cachep = kmem_cache_create("blkdev_queue",
sizeof(struct request_queue), 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);
-
return 0;
}
Code Review / linux-2.6.git / blobdiff