#include <linux/cpu.h>
#include <linux/blktrace_api.h>
#include <linux/fault-inject.h>
+#include <linux/scatterlist.h>
/*
* for max sense size
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 nr_sectors, int new_io);
+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);
EXPORT_SYMBOL(blk_queue_ordered);
-/**
- * blk_queue_issue_flush_fn - set function for issuing a flush
- * @q: the request queue
- * @iff: the function to be called issuing the flush
- *
- * Description:
- * If a driver supports issuing a flush command, the support is notified
- * to the block layer by defining it through this call.
- *
- **/
-void blk_queue_issue_flush_fn(struct request_queue *q, issue_flush_fn *iff)
-{
- q->issue_flush_fn = iff;
-}
-
-EXPORT_SYMBOL(blk_queue_issue_flush_fn);
-
/*
* Cache flushing for ordered writes handling
*/
* 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.
+ * 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)
+ if ((q->ordered & QUEUE_ORDERED_POSTFLUSH) && !blk_empty_barrier(rq))
queue_flush(q, QUEUE_ORDERED_POSTFLUSH);
else
q->ordseq |= QUEUE_ORDSEQ_POSTFLUSH;
int blk_do_ordered(struct request_queue *q, struct request **rqp)
{
struct request *rq = *rqp;
- int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
+ const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
if (!q->ordseq) {
if (!is_barrier)
retval = atomic_dec_and_test(&bqt->refcnt);
if (retval) {
BUG_ON(bqt->busy);
- BUG_ON(!list_empty(&bqt->busy_list));
kfree(bqt->tag_index);
bqt->tag_index = NULL;
if (init_tag_map(q, tags, depth))
goto fail;
- INIT_LIST_HEAD(&tags->busy_list);
tags->busy = 0;
atomic_set(&tags->refcnt, 1);
return tags;
*/
q->queue_tags = tags;
q->queue_flags |= (1 << QUEUE_FLAG_QUEUED);
+ INIT_LIST_HEAD(&q->tag_busy_list);
return 0;
fail:
kfree(tags);
bqt->tag_index[tag] = NULL;
- /*
- * We use test_and_clear_bit's memory ordering properties here.
- * The tag_map bit acts as a lock for tag_index[bit], so we need
- * a barrer before clearing the bit (precisely: release semantics).
- * Could use clear_bit_unlock when it is merged.
- */
- if (unlikely(!test_and_clear_bit(tag, bqt->tag_map))) {
+ 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--;
}
if (tag >= bqt->max_depth)
return 1;
- } while (test_and_set_bit(tag, bqt->tag_map));
+ } while (test_and_set_bit_lock(tag, bqt->tag_map));
/*
- * We rely on test_and_set_bit providing lock memory ordering semantics
- * (could use test_and_set_bit_lock when it is merged).
+ * 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, &bqt->busy_list);
+ list_add(&rq->queuelist, &q->tag_busy_list);
bqt->busy++;
return 0;
}
**/
void blk_queue_invalidate_tags(struct request_queue *q)
{
- struct blk_queue_tag *bqt = q->queue_tags;
struct list_head *tmp, *n;
- struct request *rq;
-
- list_for_each_safe(tmp, n, &bqt->busy_list) {
- rq = list_entry_rq(tmp);
- if (rq->tag == -1) {
- printk(KERN_ERR
- "%s: bad tag found on list\n", __FUNCTION__);
- list_del_init(&rq->queuelist);
- rq->cmd_flags &= ~REQ_QUEUED;
- } else
- blk_queue_end_tag(q, rq);
-
- rq->cmd_flags &= ~REQ_STARTED;
- __elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 0);
- }
+ list_for_each_safe(tmp, n, &q->tag_busy_list)
+ blk_requeue_request(q, list_entry_rq(tmp));
}
EXPORT_SYMBOL(blk_queue_invalidate_tags);
* 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 *sg)
+ struct scatterlist *sglist)
{
struct bio_vec *bvec, *bvprv;
struct req_iterator iter;
+ struct scatterlist *sg;
int nsegs, cluster;
nsegs = 0;
* 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[nsegs - 1].length + nbytes > q->max_segment_size)
+ if (sg->length + nbytes > q->max_segment_size)
goto new_segment;
if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
goto new_segment;
- sg[nsegs - 1].length += nbytes;
+ sg->length += nbytes;
} else {
new_segment:
- memset(&sg[nsegs],0,sizeof(struct scatterlist));
- sg[nsegs].page = bvec->bv_page;
- sg[nsegs].length = nbytes;
- sg[nsegs].offset = bvec->bv_offset;
+ if (!sg)
+ sg = sglist;
+ else {
+ /*
+ * If the driver previously mapped a shorter
+ * list, we could see a termination bit
+ * prematurely unless it fully inits the sg
+ * table on each mapping. We KNOW that there
+ * must be more entries here or the driver
+ * would be buggy, so force clear the
+ * termination bit to avoid doing a full
+ * sg_init_table() in drivers for each command.
+ */
+ sg->page_link &= ~0x02;
+ sg = sg_next(sg);
+ }
+ sg_set_page(sg, bvec->bv_page, nbytes, bvec->bv_offset);
nsegs++;
}
bvprv = bvec;
} /* segments in rq */
+ if (sg)
+ sg_mark_end(sg);
+
return nsegs;
}
{
struct request_queue *q = bdi->unplug_io_data;
- /*
- * devices don't necessarily have an ->unplug_fn defined
- */
- if (q->unplug_fn) {
- blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
- q->rq.count[READ] + q->rq.count[WRITE]);
-
- q->unplug_fn(q);
- }
+ blk_unplug(q);
}
static void blk_unplug_work(struct work_struct *work)
kblockd_schedule_work(&q->unplug_work);
}
+void blk_unplug(struct request_queue *q)
+{
+ /*
+ * devices don't necessarily have an ->unplug_fn defined
+ */
+ if (q->unplug_fn) {
+ blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
+ q->rq.count[READ] + q->rq.count[WRITE]);
+
+ q->unplug_fn(q);
+ }
+}
+EXPORT_SYMBOL(blk_unplug);
+
/**
* blk_start_queue - restart a previously stopped queue
* @q: The &struct request_queue in question
void blk_sync_queue(struct request_queue *q)
{
del_timer_sync(&q->unplug_timer);
+ kblockd_flush_work(&q->unplug_work);
}
EXPORT_SYMBOL(blk_sync_queue);
blk_trace_shutdown(q);
+ bdi_destroy(&q->backing_dev_info);
kmem_cache_free(requestq_cachep, q);
}
struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
struct request_queue *q;
+ int err;
q = kmem_cache_alloc_node(requestq_cachep,
gfp_mask | __GFP_ZERO, node_id);
if (!q)
return NULL;
- init_timer(&q->unplug_timer);
-
- kobject_set_name(&q->kobj, "%s", "queue");
- q->kobj.ktype = &queue_ktype;
- kobject_init(&q->kobj);
-
q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
q->backing_dev_info.unplug_io_data = q;
+ err = bdi_init(&q->backing_dev_info);
+ if (err) {
+ kmem_cache_free(requestq_cachep, q);
+ return NULL;
+ }
+
+ init_timer(&q->unplug_timer);
+
+ kobject_init(&q->kobj, &queue_ktype);
mutex_init(&q->sysfs_lock);
if (blk_rq_tagged(rq))
blk_queue_end_tag(q, rq);
- drive_stat_acct(rq, rq->nr_sectors, 1);
+ drive_stat_acct(rq, 1);
__elv_add_request(q, rq, where, 0);
blk_start_queueing(q);
spin_unlock_irqrestore(q->queue_lock, flags);
EXPORT_SYMBOL(blk_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
*/
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;
- if (!q->issue_flush_fn)
- return -EOPNOTSUPP;
- return q->issue_flush_fn(q, bdev->bd_disk, error_sector);
+ 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 nr_sectors, int new_io)
+static void drive_stat_acct(struct request *rq, int new_io)
{
int rw = rq_data_dir(rq);
*/
static inline void add_request(struct request_queue * q, struct request * req)
{
- drive_stat_acct(req, req->nr_sectors, 1);
+ drive_stat_acct(req, 1);
/*
* elevator indicated where it wants this request to be
req->biotail = bio;
req->nr_sectors = req->hard_nr_sectors += nr_sectors;
req->ioprio = ioprio_best(req->ioprio, prio);
- drive_stat_acct(req, nr_sectors, 0);
+ drive_stat_acct(req, 0);
if (!attempt_back_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out;
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, nr_sectors, 0);
+ drive_stat_acct(req, 0);
if (!attempt_front_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out;
{
struct block_device *bdev = bio->bi_bdev;
- if (bdev != bdev->bd_contains) {
+ if (bio_sectors(bio) && bdev != bdev->bd_contains) {
struct hd_struct *p = bdev->bd_part;
const int rw = bio_data_dir(bio);
#endif /* CONFIG_FAIL_MAKE_REQUEST */
+/*
+ * Check whether this bio extends beyond the end of the device.
+ */
+static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
+{
+ sector_t maxsector;
+
+ if (!nr_sectors)
+ return 0;
+
+ /* Test device or partition size, when known. */
+ maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
+ if (maxsector) {
+ sector_t sector = bio->bi_sector;
+
+ if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
+ /*
+ * This may well happen - the kernel calls bread()
+ * without checking the size of the device, e.g., when
+ * mounting a device.
+ */
+ handle_bad_sector(bio);
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
/**
* 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.
static inline void __generic_make_request(struct bio *bio)
{
struct request_queue *q;
- sector_t maxsector;
sector_t old_sector;
int ret, nr_sectors = bio_sectors(bio);
dev_t old_dev;
+ int err = -EIO;
might_sleep();
- /* Test device or partition size, when known. */
- maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
- if (maxsector) {
- sector_t sector = bio->bi_sector;
- if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
- /*
- * This may well happen - the kernel calls bread()
- * without checking the size of the device, e.g., when
- * mounting a device.
- */
- handle_bad_sector(bio);
- goto end_io;
- }
- }
+ if (bio_check_eod(bio, nr_sectors))
+ goto end_io;
/*
* Resolve the mapping until finished. (drivers are
bdevname(bio->bi_bdev, b),
(long long) bio->bi_sector);
end_io:
- bio_endio(bio, -EIO);
+ bio_endio(bio, err);
break;
}
old_sector = bio->bi_sector;
old_dev = bio->bi_bdev->bd_dev;
- maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
- if (maxsector) {
- sector_t sector = bio->bi_sector;
-
- if (maxsector < nr_sectors ||
- maxsector - nr_sectors < sector) {
- /*
- * This may well happen - partitions are not
- * checked to make sure they are within the size
- * of the whole device.
- */
- handle_bad_sector(bio);
- goto end_io;
- }
+ if (bio_check_eod(bio, nr_sectors))
+ goto end_io;
+ if (bio_empty_barrier(bio) && !q->prepare_flush_fn) {
+ err = -EOPNOTSUPP;
+ goto end_io;
}
ret = q->make_request_fn(q, bio);
{
int count = bio_sectors(bio);
- BIO_BUG_ON(!bio->bi_size);
- BIO_BUG_ON(!bio->bi_io_vec);
bio->bi_rw |= rw;
- if (rw & WRITE) {
- count_vm_events(PGPGOUT, count);
- } else {
- task_io_account_read(bio->bi_size);
- count_vm_events(PGPGIN, count);
- }
- if (unlikely(block_dump)) {
- char b[BDEVNAME_SIZE];
- printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
- current->comm, current->pid,
- (rw & WRITE) ? "WRITE" : "READ",
- (unsigned long long)bio->bi_sector,
- bdevname(bio->bi_bdev,b));
+ /*
+ * 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 (rw & WRITE) {
+ count_vm_events(PGPGOUT, count);
+ } else {
+ task_io_account_read(bio->bi_size);
+ count_vm_events(PGPGIN, count);
+ }
+
+ if (unlikely(block_dump)) {
+ char b[BDEVNAME_SIZE];
+ printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
+ current->comm, task_pid_nr(current),
+ (rw & WRITE) ? "WRITE" : "READ",
+ (unsigned long long)bio->bi_sector,
+ bdevname(bio->bi_bdev,b));
+ }
}
generic_make_request(bio);
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;
EXPORT_SYMBOL(end_that_request_last);
-void end_request(struct request *req, int uptodate)
+static inline void __end_request(struct request *rq, int uptodate,
+ unsigned int nr_bytes, int dequeue)
{
- if (!end_that_request_first(req, uptodate, req->hard_cur_sectors)) {
- add_disk_randomness(req->rq_disk);
- blkdev_dequeue_request(req);
- end_that_request_last(req, uptodate);
+ if (!end_that_request_chunk(rq, uptodate, nr_bytes)) {
+ if (dequeue)
+ blkdev_dequeue_request(rq);
+ add_disk_randomness(rq->rq_disk);
+ end_that_request_last(rq, uptodate);
}
}
+static unsigned int rq_byte_size(struct request *rq)
+{
+ if (blk_fs_request(rq))
+ return rq->hard_nr_sectors << 9;
+
+ return rq->data_len;
+}
+
+/**
+ * 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, rq_byte_size(rq), 1);
+}
+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, rq_byte_size(rq), 0);
+}
+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, 1);
+}
EXPORT_SYMBOL(end_request);
static void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
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);
- int ra_kb;
if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
return -EINVAL;
* values synchronously:
*/
spin_lock_irq(q->queue_lock);
- /*
- * Trim readahead window as well, if necessary:
- */
- ra_kb = q->backing_dev_info.ra_pages << (PAGE_CACHE_SHIFT - 10);
- if (ra_kb > max_sectors_kb)
- q->backing_dev_info.ra_pages =
- max_sectors_kb >> (PAGE_CACHE_SHIFT - 10);
-
q->max_sectors = max_sectors_kb << 1;
spin_unlock_irq(q->queue_lock);
if (!q || !q->request_fn)
return -ENXIO;
- q->kobj.parent = kobject_get(&disk->kobj);
-
- ret = kobject_add(&q->kobj);
+ ret = kobject_add(&q->kobj, kobject_get(&disk->dev.kobj),
+ "%s", "queue");
if (ret < 0)
return ret;
kobject_uevent(&q->kobj, KOBJ_REMOVE);
kobject_del(&q->kobj);
- kobject_put(&disk->kobj);
+ kobject_put(&disk->dev.kobj);
}
}