#include <linux/task_io_accounting_ops.h>
#include <linux/blktrace_api.h>
#include <linux/fault-inject.h>
+#include <trace/block.h>
#include "blk.h"
+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);
/*
memset(rq, 0, sizeof(*rq));
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;
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 (!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);
{
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
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]);
-
+ trace_block_unplug_timer(q);
kblockd_schedule_work(q, &q->unplug_work);
}
* 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);
}
}
static void blk_invoke_request_fn(struct request_queue *q)
{
+ if (unlikely(blk_queue_stopped(q)))
+ return;
+
/*
* one level of recursion is ok and is much faster than kicking
* the unplug handling
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)
{
/**
* 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. Also
+ * See @blk_start_queueing.
+ *
*/
void blk_run_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);
queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
mutex_unlock(&q->sysfs_lock);
}
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);
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 = (1 << QUEUE_FLAG_CLUSTER |
+ 1 << QUEUE_FLAG_STACKABLE);
q->queue_lock = lock;
- blk_queue_segment_boundary(q, 0xffffffff);
+ blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
blk_queue_make_request(q, __make_request);
blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
if (ioc_batching(q, ioc))
ioc->nr_batch_requests--;
- blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ);
+ trace_block_getrq(q, bio, rw);
out:
return rq;
}
prepare_to_wait_exclusive(&rl->wait[rw], &wait,
TASK_UNINTERRUPTIBLE);
- blk_add_trace_generic(q, bio, rw, BLK_TA_SLEEPRQ);
+ trace_block_sleeprq(q, bio, rw);
__generic_unplug_device(q);
spin_unlock_irq(q->queue_lock);
*
* 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.
+ * for this queue. Should be used to start queueing on a device outside
+ * of ->request_fn() context. Also see @blk_run_queue.
*
* The queue lock must be held with interrupts disabled.
*/
void blk_start_queueing(struct request_queue *q)
{
- if (!blk_queue_plugged(q))
+ if (!blk_queue_plugged(q)) {
+ if (unlikely(blk_queue_stopped(q)))
+ return;
q->request_fn(q);
- else
+ } else
__generic_unplug_device(q);
}
EXPORT_SYMBOL(blk_start_queueing);
*/
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);
}
/**
- * part_round_stats() - Round off the performance stats on a struct
- * disk_stats.
+ * 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
/*
* inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
*/
- if (bio_rw_ahead(bio) || bio_failfast(bio))
- req->cmd_flags |= REQ_FAILFAST;
+ 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;
/*
* REQ_BARRIER implies no merging, but lets make it explicit
static int __make_request(struct request_queue *q, struct bio *bio)
{
struct request *req;
- int el_ret, nr_sectors, barrier, discard, err;
+ int el_ret, nr_sectors;
const unsigned short prio = bio_prio(bio);
const int sync = bio_sync(bio);
int rw_flags;
*/
blk_queue_bounce(q, &bio);
- barrier = bio_barrier(bio);
- if (unlikely(barrier) && bio_has_data(bio) &&
- (q->next_ordered == QUEUE_ORDERED_NONE)) {
- err = -EOPNOTSUPP;
- goto end_io;
- }
-
- discard = bio_discard(bio);
- if (unlikely(discard) && !q->prepare_discard_fn) {
- 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);
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;
if (!ll_front_merge_fn(q, req, bio))
break;
- blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
+ trace_block_bio_frontmerge(q, bio);
bio->bi_next = req->bio;
req->bio = bio;
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 (elv_queue_empty(q))
+ if (!blk_queue_nonrot(q) && elv_queue_empty(q))
blk_plug_device(q);
add_request(q, req);
out:
- if (sync)
+ if (sync || blk_queue_nonrot(q))
__generic_unplug_device(q);
spin_unlock_irq(q->queue_lock);
return 0;
-
-end_io:
- bio_endio(bio, err);
- return 0;
}
/*
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);
}
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)) {
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) ||
- (bio_discard(bio) && !q->prepare_discard_fn)) {
+
+ if (bio_discard(bio) && !q->prepare_discard_fn) {
err = -EOPNOTSUPP;
goto end_io;
}
ret = q->make_request_fn(q, bio);
} while (ret);
+
+ return;
+
+end_io:
+ bio_endio(bio, err);
}
/*
EXPORT_SYMBOL(submit_bio);
/**
+ * 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 (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;
+ }
+
+ /*
+ * 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);
+
+/**
* __end_that_request_first - end I/O on a request
* @req: the request being processed
* @error: %0 for success, < %0 for error
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_TYPE_BLOCK_PC request, we want to carry any eventual
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;
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();
+ blk_delete_timer(req);
+
/*
* Account IO completion. bar_rq isn't accounted as a normal
* IO on queueing nor completion. Accounting the containing
}
}
-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
* @rq: the request being processed
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 I/O 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
* 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.
- *
+ * code. Use blk_end_request() or __blk_end_request() to end a request.
**/
void end_request(struct request *req, int uptodate)
{
- __end_request(req, uptodate, req->hard_cur_sectors << 9);
+ int error = 0;
+
+ if (uptodate <= 0)
+ error = uptodate ? uptodate : -EIO;
+
+ __blk_end_request(req, error, req->hard_cur_sectors << 9);
}
EXPORT_SYMBOL(end_request);
+static int end_that_request_data(struct request *rq, int error,
+ unsigned int nr_bytes, unsigned int bidi_bytes)
+{
+ if (rq->bio) {
+ 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;
+ }
+
+ return 0;
+}
+
/**
* blk_end_io - Generic end_io function to complete a request.
* @rq: the request being processed
struct request_queue *q = rq->q;
unsigned long flags = 0UL;
- if (rq->bio) {
- 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;
- }
+ if (end_that_request_data(rq, error, nr_bytes, bidi_bytes))
+ return 1;
/* Special feature for tricky drivers */
if (drv_callback && drv_callback(rq))
EXPORT_SYMBOL_GPL(blk_end_bidi_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 @rq
+ *
+ * Description:
+ * 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 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)
+{
+ 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_update_request);
+
+/**
* blk_end_request_callback - Special helper function for tricky drivers
* @rq: the request being processed
* @error: %0 for success, < %0 for error
rq->rq_disk = bio->bi_bdev->bd_disk;
}
-int kblockd_schedule_work(struct request_queue *q, 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);
+
+ return 0;
}
-EXPORT_SYMBOL(kblockd_schedule_work);
+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)
{
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff