elevator_add_req_fn* called to add a new request into the scheduler
-elevator_queue_empty_fn returns true if the merge queue is empty.
- Drivers shouldn't use this, but rather check
- if elv_next_request is NULL (without losing the
- request if one exists!)
-
elevator_former_req_fn
elevator_latter_req_fn These return the request before or after the
one specified in disk sort order. Used by the
}
EXPORT_SYMBOL(blk_dump_rq_flags);
+/*
+ * Make sure that plugs that were pending when this function was entered,
+ * are now complete and requests pushed to the queue.
+*/
+static inline void queue_sync_plugs(struct request_queue *q)
+{
+ /*
+ * If the current process is plugged and has barriers submitted,
+ * we will livelock if we don't unplug first.
+ */
+ blk_flush_plug(current);
+}
+
static void blk_delay_work(struct work_struct *work)
{
struct request_queue *q;
}
EXPORT_SYMBOL(blk_delay_queue);
-/*
- * "plug" the device if there are no outstanding requests: this will
- * force the transfer to start only after we have put all the requests
- * on the list.
- *
- * This is called with interrupts off and no requests on the queue and
- * with the queue lock held.
- */
-void blk_plug_device(struct request_queue *q)
-{
- WARN_ON(!irqs_disabled());
-
- /*
- * don't plug a stopped queue, it must be paired with blk_start_queue()
- * which will restart the queueing
- */
- if (blk_queue_stopped(q))
- return;
-
- if (!queue_flag_test_and_set(QUEUE_FLAG_PLUGGED, q)) {
- mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
- 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.
- */
-int blk_remove_plug(struct request_queue *q)
-{
- WARN_ON(!irqs_disabled());
-
- if (!queue_flag_test_and_clear(QUEUE_FLAG_PLUGGED, q))
- return 0;
-
- del_timer(&q->unplug_timer);
- return 1;
-}
-EXPORT_SYMBOL(blk_remove_plug);
-
-/*
- * remove the plug and let it rip..
- */
-void __generic_unplug_device(struct request_queue *q)
-{
- if (unlikely(blk_queue_stopped(q)))
- return;
- if (!blk_remove_plug(q) && !blk_queue_nonrot(q))
- return;
-
- q->request_fn(q);
-}
-
-/**
- * generic_unplug_device - fire a request queue
- * @q: The &struct request_queue in question
- *
- * Description:
- * Linux uses plugging to build bigger requests queues before letting
- * the device have at them. If a queue is plugged, the I/O scheduler
- * is still adding and merging requests on the queue. Once the queue
- * gets unplugged, the request_fn defined for the queue is invoked and
- * transfers started.
- **/
-void generic_unplug_device(struct request_queue *q)
-{
- 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);
-
-static void blk_backing_dev_unplug(struct backing_dev_info *bdi,
- struct page *page)
-{
- struct request_queue *q = bdi->unplug_io_data;
-
- blk_unplug(q);
-}
-
-void blk_unplug_work(struct work_struct *work)
-{
- struct request_queue *q =
- container_of(work, struct request_queue, unplug_work);
-
- trace_block_unplug_io(q);
- q->unplug_fn(q);
-}
-
-void blk_unplug_timeout(unsigned long data)
-{
- struct request_queue *q = (struct request_queue *)data;
-
- 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) {
- trace_block_unplug_io(q);
- 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_stop_queue(struct request_queue *q)
{
- blk_remove_plug(q);
cancel_delayed_work(&q->delay_work);
queue_flag_set(QUEUE_FLAG_STOPPED, q);
}
*/
void blk_sync_queue(struct request_queue *q)
{
- del_timer_sync(&q->unplug_timer);
del_timer_sync(&q->timeout);
- cancel_work_sync(&q->unplug_work);
throtl_shutdown_timer_wq(q);
cancel_delayed_work_sync(&q->delay_work);
+ queue_sync_plugs(q);
}
EXPORT_SYMBOL(blk_sync_queue);
*/
void __blk_run_queue(struct request_queue *q)
{
- 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 (!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);
- }
+ } else
+ queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
}
EXPORT_SYMBOL(__blk_run_queue);
if (!q)
return NULL;
- q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
- q->backing_dev_info.unplug_io_data = q;
q->backing_dev_info.ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->backing_dev_info.state = 0;
setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
laptop_mode_timer_fn, (unsigned long) q);
- init_timer(&q->unplug_timer);
setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
INIT_LIST_HEAD(&q->timeout_list);
INIT_LIST_HEAD(&q->flush_queue[0]);
INIT_LIST_HEAD(&q->flush_queue[1]);
INIT_LIST_HEAD(&q->flush_data_in_flight);
- INIT_WORK(&q->unplug_work, blk_unplug_work);
INIT_DELAYED_WORK(&q->delay_work, blk_delay_work);
kobject_init(&q->kobj, &blk_queue_ktype);
q->request_fn = rfn;
q->prep_rq_fn = NULL;
q->unprep_rq_fn = NULL;
- q->unplug_fn = generic_unplug_device;
q->queue_flags = QUEUE_FLAG_DEFAULT;
q->queue_lock = lock;
}
/*
- * No available requests for this queue, unplug the device and wait for some
- * requests to become available.
+ * No available requests for this queue, wait for some requests to become
+ * available.
*
* Called with q->queue_lock held, and returns with it unlocked.
*/
trace_block_sleeprq(q, bio, rw_flags & 1);
- __generic_unplug_device(q);
spin_unlock_irq(q->queue_lock);
io_schedule();
int where)
{
drive_stat_acct(rq, 1);
- __elv_add_request(q, rq, where, 0);
+ __elv_add_request(q, rq, where);
}
/**
/*
* rq is already accounted, so use raw insert
*/
- __elv_add_request(q, rq, ELEVATOR_INSERT_SORT, 0);
+ __elv_add_request(q, rq, ELEVATOR_INSERT_SORT);
}
if (q) {
rq->end_io = done;
WARN_ON(irqs_disabled());
spin_lock_irq(q->queue_lock);
- __elv_add_request(q, rq, where, 1);
- __generic_unplug_device(q);
+ __elv_add_request(q, rq, where);
+ __blk_run_queue(q);
/* the queue is stopped so it won't be plugged+unplugged */
if (rq->cmd_type == REQ_TYPE_PM_RESUME)
q->request_fn(q);
{
struct request_queue *q = flush_rq->q;
struct list_head *running = &q->flush_queue[q->flush_running_idx];
- bool was_empty = elv_queue_empty(q);
bool queued = false;
struct request *rq, *n;
}
/* after populating an empty queue, kick it to avoid stall */
- if (queued && was_empty)
+ if (queued)
__blk_run_queue(q);
}
blk_queue_congestion_threshold(q);
q->nr_batching = BLK_BATCH_REQ;
- q->unplug_thresh = 4; /* hmm */
- q->unplug_delay = msecs_to_jiffies(3); /* 3 milliseconds */
- if (q->unplug_delay == 0)
- q->unplug_delay = 1;
-
- q->unplug_timer.function = blk_unplug_timeout;
- q->unplug_timer.data = (unsigned long)q;
-
blk_set_default_limits(&q->limits);
blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS);
if (nr_disp) {
while((bio = bio_list_pop(&bio_list_on_stack)))
generic_make_request(bio);
- blk_unplug(q);
}
return nr_disp;
}
void blk_dequeue_request(struct request *rq);
void __blk_queue_free_tags(struct request_queue *q);
-void blk_unplug_work(struct work_struct *work);
-void blk_unplug_timeout(unsigned long data);
void blk_rq_timed_out_timer(unsigned long data);
void blk_delete_timer(struct request *);
void blk_add_timer(struct request *);
}
}
-static int cfq_queue_empty(struct request_queue *q)
-{
- struct cfq_data *cfqd = q->elevator->elevator_data;
-
- return !cfqd->rq_queued;
-}
-
/*
* Scale schedule slice based on io priority. Use the sync time slice only
* if a queue is marked sync and has sync io queued. A sync queue with async
.elevator_add_req_fn = cfq_insert_request,
.elevator_activate_req_fn = cfq_activate_request,
.elevator_deactivate_req_fn = cfq_deactivate_request,
- .elevator_queue_empty_fn = cfq_queue_empty,
.elevator_completed_req_fn = cfq_completed_request,
.elevator_former_req_fn = elv_rb_former_request,
.elevator_latter_req_fn = elv_rb_latter_request,
return 1;
}
-static int deadline_queue_empty(struct request_queue *q)
-{
- struct deadline_data *dd = q->elevator->elevator_data;
-
- return list_empty(&dd->fifo_list[WRITE])
- && list_empty(&dd->fifo_list[READ]);
-}
-
static void deadline_exit_queue(struct elevator_queue *e)
{
struct deadline_data *dd = e->elevator_data;
.elevator_merge_req_fn = deadline_merged_requests,
.elevator_dispatch_fn = deadline_dispatch_requests,
.elevator_add_req_fn = deadline_add_request,
- .elevator_queue_empty_fn = deadline_queue_empty,
.elevator_former_req_fn = elv_rb_former_request,
.elevator_latter_req_fn = elv_rb_latter_request,
.elevator_init_fn = deadline_init_queue,
void elv_insert(struct request_queue *q, struct request *rq, int where)
{
- int unplug_it = 1;
-
trace_block_rq_insert(q, rq);
rq->q = q;
switch (where) {
case ELEVATOR_INSERT_REQUEUE:
- /*
- * Most requeues happen because of a busy condition,
- * don't force unplug of the queue for that case.
- * Clear unplug_it and fall through.
- */
- unplug_it = 0;
-
case ELEVATOR_INSERT_FRONT:
rq->cmd_flags |= REQ_SOFTBARRIER;
list_add(&rq->queuelist, &q->queue_head);
rq->cmd_flags |= REQ_SOFTBARRIER;
blk_insert_flush(rq);
break;
-
default:
printk(KERN_ERR "%s: bad insertion point %d\n",
__func__, where);
BUG();
}
-
- if (unplug_it && blk_queue_plugged(q)) {
- int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC]
- - queue_in_flight(q);
-
- if (nrq >= q->unplug_thresh)
- __generic_unplug_device(q);
- }
}
-void __elv_add_request(struct request_queue *q, struct request *rq, int where,
- int plug)
+void __elv_add_request(struct request_queue *q, struct request *rq, int where)
{
BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
where == ELEVATOR_INSERT_SORT)
where = ELEVATOR_INSERT_BACK;
- if (plug)
- blk_plug_device(q);
-
elv_insert(q, rq, where);
}
EXPORT_SYMBOL(__elv_add_request);
-void elv_add_request(struct request_queue *q, struct request *rq, int where,
- int plug)
+void elv_add_request(struct request_queue *q, struct request *rq, int where)
{
unsigned long flags;
spin_lock_irqsave(q->queue_lock, flags);
- __elv_add_request(q, rq, where, plug);
+ __elv_add_request(q, rq, where);
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(elv_add_request);
-int elv_queue_empty(struct request_queue *q)
-{
- struct elevator_queue *e = q->elevator;
-
- if (!list_empty(&q->queue_head))
- return 0;
-
- if (e->ops->elevator_queue_empty_fn)
- return e->ops->elevator_queue_empty_fn(q);
-
- return 1;
-}
-EXPORT_SYMBOL(elv_queue_empty);
-
struct request *elv_latter_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
list_add_tail(&rq->queuelist, &nd->queue);
}
-static int noop_queue_empty(struct request_queue *q)
-{
- struct noop_data *nd = q->elevator->elevator_data;
-
- return list_empty(&nd->queue);
-}
-
static struct request *
noop_former_request(struct request_queue *q, struct request *rq)
{
.elevator_merge_req_fn = noop_merged_requests,
.elevator_dispatch_fn = noop_dispatch,
.elevator_add_req_fn = noop_add_request,
- .elevator_queue_empty_fn = noop_queue_empty,
.elevator_former_req_fn = noop_former_request,
.elevator_latter_req_fn = noop_latter_request,
.elevator_init_fn = noop_init_queue,
int sg_index = 0;
int chained = 0;
- /* We call start_io here in case there is a command waiting on the
- * queue that has not been sent.
- */
- if (blk_queue_plugged(q))
- goto startio;
-
queue:
creq = blk_peek_request(q);
if (!creq)
struct scatterlist tmp_sg[SG_MAX];
int i, dir, seg;
- if (blk_queue_plugged(q))
- goto startio;
-
queue_next:
creq = blk_peek_request(q);
if (!creq)
}
}
- drbd_blk_run_queue(bdev_get_queue(mdev->ldev->md_bdev));
-
/* always (try to) flush bitmap to stable storage */
drbd_md_flush(mdev);
for (i = 0; i < num_pages; i++)
bm_page_io_async(mdev, b, i, rw);
- drbd_blk_run_queue(bdev_get_queue(mdev->ldev->md_bdev));
wait_event(b->bm_io_wait, atomic_read(&b->bm_async_io) == 0);
if (test_bit(BM_MD_IO_ERROR, &b->bm_flags)) {
return QUEUE_ORDERED_NONE;
}
-static inline void drbd_blk_run_queue(struct request_queue *q)
-{
- if (q && q->unplug_fn)
- q->unplug_fn(q);
-}
-
-static inline void drbd_kick_lo(struct drbd_conf *mdev)
-{
- if (get_ldev(mdev)) {
- drbd_blk_run_queue(bdev_get_queue(mdev->ldev->backing_bdev));
- put_ldev(mdev);
- }
-}
-
static inline void drbd_md_flush(struct drbd_conf *mdev)
{
int r;
return 0;
}
-static void drbd_unplug_fn(struct request_queue *q)
-{
- struct drbd_conf *mdev = q->queuedata;
-
- /* unplug FIRST */
- spin_lock_irq(q->queue_lock);
- blk_remove_plug(q);
- spin_unlock_irq(q->queue_lock);
-
- /* only if connected */
- spin_lock_irq(&mdev->req_lock);
- if (mdev->state.pdsk >= D_INCONSISTENT && mdev->state.conn >= C_CONNECTED) {
- D_ASSERT(mdev->state.role == R_PRIMARY);
- if (test_and_clear_bit(UNPLUG_REMOTE, &mdev->flags)) {
- /* add to the data.work queue,
- * unless already queued.
- * XXX this might be a good addition to drbd_queue_work
- * anyways, to detect "double queuing" ... */
- if (list_empty(&mdev->unplug_work.list))
- drbd_queue_work(&mdev->data.work,
- &mdev->unplug_work);
- }
- }
- spin_unlock_irq(&mdev->req_lock);
-
- if (mdev->state.disk >= D_INCONSISTENT)
- drbd_kick_lo(mdev);
-}
-
static void drbd_set_defaults(struct drbd_conf *mdev)
{
/* This way we get a compile error when sync_conf grows,
blk_queue_max_segment_size(q, DRBD_MAX_SEGMENT_SIZE);
blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
blk_queue_merge_bvec(q, drbd_merge_bvec);
- q->queue_lock = &mdev->req_lock; /* needed since we use */
- /* plugging on a queue, that actually has no requests! */
- q->unplug_fn = drbd_unplug_fn;
+ q->queue_lock = &mdev->req_lock;
mdev->md_io_page = alloc_page(GFP_KERNEL);
if (!mdev->md_io_page)
return NULL;
}
-/* kick lower level device, if we have more than (arbitrary number)
- * reference counts on it, which typically are locally submitted io
- * requests. don't use unacked_cnt, so we speed up proto A and B, too. */
-static void maybe_kick_lo(struct drbd_conf *mdev)
-{
- if (atomic_read(&mdev->local_cnt) >= mdev->net_conf->unplug_watermark)
- drbd_kick_lo(mdev);
-}
-
static void reclaim_net_ee(struct drbd_conf *mdev, struct list_head *to_be_freed)
{
struct drbd_epoch_entry *e;
LIST_HEAD(reclaimed);
struct drbd_epoch_entry *e, *t;
- maybe_kick_lo(mdev);
spin_lock_irq(&mdev->req_lock);
reclaim_net_ee(mdev, &reclaimed);
spin_unlock_irq(&mdev->req_lock);
while (!list_empty(head)) {
prepare_to_wait(&mdev->ee_wait, &wait, TASK_UNINTERRUPTIBLE);
spin_unlock_irq(&mdev->req_lock);
- drbd_kick_lo(mdev);
- schedule();
+ io_schedule();
finish_wait(&mdev->ee_wait, &wait);
spin_lock_irq(&mdev->req_lock);
}
drbd_generic_make_request(mdev, fault_type, bio);
} while (bios);
- maybe_kick_lo(mdev);
return 0;
fail:
inc_unacked(mdev);
- if (mdev->net_conf->wire_protocol != DRBD_PROT_C)
- drbd_kick_lo(mdev);
-
mdev->current_epoch->barrier_nr = p->barrier;
rv = drbd_may_finish_epoch(mdev, mdev->current_epoch, EV_GOT_BARRIER_NR);
static int receive_UnplugRemote(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
{
- if (mdev->state.disk >= D_INCONSISTENT)
- drbd_kick_lo(mdev);
-
/* Make sure we've acked all the TCP data associated
* with the data requests being unplugged */
drbd_tcp_quickack(mdev->data.socket);
bio_endio(req->private_bio, -EIO);
}
- /* we need to plug ALWAYS since we possibly need to kick lo_dev.
- * we plug after submit, so we won't miss an unplug event */
- drbd_plug_device(mdev);
-
return 0;
fail_conflicting:
* queue (or even the read operations for those packets
* is not finished by now). Retry in 100ms. */
- drbd_kick_lo(mdev);
__set_current_state(TASK_INTERRUPTIBLE);
schedule_timeout(HZ / 10);
w = kmalloc(sizeof(struct drbd_work), GFP_ATOMIC);
generic_make_request(bio);
}
-static inline void drbd_plug_device(struct drbd_conf *mdev)
-{
- struct request_queue *q;
- q = bdev_get_queue(mdev->this_bdev);
-
- spin_lock_irq(q->queue_lock);
-
-/* XXX the check on !blk_queue_plugged is redundant,
- * implicitly checked in blk_plug_device */
-
- if (!blk_queue_plugged(q)) {
- blk_plug_device(q);
- del_timer(&q->unplug_timer);
- /* unplugging should not happen automatically... */
- }
- spin_unlock_irq(q->queue_lock);
-}
-
static inline int drbd_crypto_is_hash(struct crypto_tfm *tfm)
{
return (crypto_tfm_alg_type(tfm) & CRYPTO_ALG_TYPE_HASH_MASK)
bio.bi_end_io = floppy_rb0_complete;
submit_bio(READ, &bio);
- generic_unplug_device(bdev_get_queue(bdev));
process_fd_request();
wait_for_completion(&complete);
return 0;
}
-/*
- * kick off io on the underlying address space
- */
-static void loop_unplug(struct request_queue *q)
-{
- struct loop_device *lo = q->queuedata;
-
- queue_flag_clear_unlocked(QUEUE_FLAG_PLUGGED, q);
- blk_run_address_space(lo->lo_backing_file->f_mapping);
-}
-
struct switch_request {
struct file *file;
struct completion wait;
*/
blk_queue_make_request(lo->lo_queue, loop_make_request);
lo->lo_queue->queuedata = lo;
- lo->lo_queue->unplug_fn = loop_unplug;
if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
blk_queue_flush(lo->lo_queue, REQ_FLUSH);
kthread_stop(lo->lo_thread);
- lo->lo_queue->unplug_fn = NULL;
lo->lo_backing_file = NULL;
loop_release_xfer(lo);
min_sleep_time = pkt->sleep_time;
}
- generic_unplug_device(bdev_get_queue(pd->bdev));
-
VPRINTK("kcdrwd: sleeping\n");
residue = schedule_timeout(min_sleep_time);
VPRINTK("kcdrwd: wake up\n");
*
* Whenever IO on the active page completes, the Ready page is activated
* and the ex-Active page is clean out and made Ready.
- * Otherwise the Ready page is only activated when it becomes full, or
- * when mm_unplug_device is called via the unplug_io_fn.
+ * Otherwise the Ready page is only activated when it becomes full.
*
* If a request arrives while both pages a full, it is queued, and b_rdev is
* overloaded to record whether it was a read or a write.
page->biotail = &page->bio;
}
-static void mm_unplug_device(struct request_queue *q)
-{
- struct cardinfo *card = q->queuedata;
- unsigned long flags;
-
- spin_lock_irqsave(&card->lock, flags);
- if (blk_remove_plug(q))
- activate(card);
- spin_unlock_irqrestore(&card->lock, flags);
-}
-
/*
* If there is room on Ready page, take
* one bh off list and add it.
*card->biotail = bio;
bio->bi_next = NULL;
card->biotail = &bio->bi_next;
- blk_plug_device(q);
spin_unlock_irq(&card->lock);
return 0;
blk_queue_make_request(card->queue, mm_make_request);
card->queue->queue_lock = &card->lock;
card->queue->queuedata = card;
- card->queue->unplug_fn = mm_unplug_device;
tasklet_init(&card->tasklet, process_page, (unsigned long)card);
drive->hwif->rq = NULL;
- elv_add_request(drive->queue, &drive->sense_rq,
- ELEVATOR_INSERT_FRONT, 0);
+ elv_add_request(drive->queue, &drive->sense_rq, ELEVATOR_INSERT_FRONT);
return 0;
}
EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
if (rq)
blk_requeue_request(q, rq);
- if (!elv_queue_empty(q))
- blk_plug_device(q);
}
void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq)
if (rq)
blk_requeue_request(q, rq);
- if (!elv_queue_empty(q))
- blk_plug_device(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
rq->cmd[0] = REQ_UNPARK_HEADS;
rq->cmd_len = 1;
rq->cmd_type = REQ_TYPE_SPECIAL;
- elv_add_request(q, rq, ELEVATOR_INSERT_FRONT, 1);
+ elv_add_request(q, rq, ELEVATOR_INSERT_FRONT);
out:
return;
prepare_to_wait(&bitmap->overflow_wait, &__wait,
TASK_UNINTERRUPTIBLE);
spin_unlock_irq(&bitmap->lock);
- md_unplug(bitmap->mddev);
- schedule();
+ io_schedule();
finish_wait(&bitmap->overflow_wait, &__wait);
continue;
}
clone->bi_destructor = dm_crypt_bio_destructor;
}
-static void kcryptd_unplug(struct crypt_config *cc)
-{
- blk_unplug(bdev_get_queue(cc->dev->bdev));
-}
-
static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
{
struct crypt_config *cc = io->target->private;
* one in order to decrypt the whole bio data *afterwards*.
*/
clone = bio_alloc_bioset(gfp, bio_segments(base_bio), cc->bs);
- if (!clone) {
- kcryptd_unplug(cc);
+ if (!clone)
return 1;
- }
crypt_inc_pending(io);
unsigned int nr_pages;
unsigned int nr_free_pages;
- /*
- * Block devices to unplug.
- * Non-NULL pointer means that a block device has some pending requests
- * and needs to be unplugged.
- */
- struct block_device *unplug[2];
-
struct dm_io_client *io_client;
wait_queue_head_t destroyq;
return 0;
}
-/*
- * Unplug the block device at the specified index.
- */
-static void unplug(struct dm_kcopyd_client *kc, int rw)
-{
- if (kc->unplug[rw] != NULL) {
- blk_unplug(bdev_get_queue(kc->unplug[rw]));
- kc->unplug[rw] = NULL;
- }
-}
-
-/*
- * Prepare block device unplug. If there's another device
- * to be unplugged at the same array index, we unplug that
- * device first.
- */
-static void prepare_unplug(struct dm_kcopyd_client *kc, int rw,
- struct block_device *bdev)
-{
- if (likely(kc->unplug[rw] == bdev))
- return;
- unplug(kc, rw);
- kc->unplug[rw] = bdev;
-}
-
static void complete_io(unsigned long error, void *context)
{
struct kcopyd_job *job = (struct kcopyd_job *) context;
.client = job->kc->io_client,
};
- if (job->rw == READ) {
+ if (job->rw == READ)
r = dm_io(&io_req, 1, &job->source, NULL);
- prepare_unplug(job->kc, READ, job->source.bdev);
- } else {
+ else {
if (job->num_dests > 1)
io_req.bi_rw |= REQ_UNPLUG;
r = dm_io(&io_req, job->num_dests, job->dests, NULL);
- if (!(io_req.bi_rw & REQ_UNPLUG))
- prepare_unplug(job->kc, WRITE, job->dests[0].bdev);
}
return r;
{
struct dm_kcopyd_client *kc = container_of(work,
struct dm_kcopyd_client, kcopyd_work);
+ struct blk_plug plug;
/*
* The order that these are called is *very* important.
* Pages jobs when successful will jump onto the io jobs
* list. io jobs call wake when they complete and it all
* starts again.
- *
- * Note that io_jobs add block devices to the unplug array,
- * this array is cleared with "unplug" calls. It is thus
- * forbidden to run complete_jobs after io_jobs and before
- * unplug because the block device could be destroyed in
- * job completion callback.
*/
+ blk_start_plug(&plug);
process_jobs(&kc->complete_jobs, kc, run_complete_job);
process_jobs(&kc->pages_jobs, kc, run_pages_job);
process_jobs(&kc->io_jobs, kc, run_io_job);
- unplug(kc, READ);
- unplug(kc, WRITE);
+ blk_finish_plug(&plug);
}
/*
INIT_LIST_HEAD(&kc->io_jobs);
INIT_LIST_HEAD(&kc->pages_jobs);
- memset(kc->unplug, 0, sizeof(kc->unplug));
-
kc->job_pool = mempool_create_slab_pool(MIN_JOBS, _job_cache);
if (!kc->job_pool)
goto bad_slab;
{
struct raid_set *rs = container_of(cb, struct raid_set, callbacks);
- md_raid5_unplug_device(rs->md.private);
+ md_raid5_kick_device(rs->md.private);
}
/*
do_reads(ms, &reads);
do_writes(ms, &writes);
do_failures(ms, &failures);
-
- dm_table_unplug_all(ms->ti->table);
}
/*-----------------------------------------------------------------
return 0;
}
-void dm_table_unplug_all(struct dm_table *t)
-{
- struct dm_dev_internal *dd;
- struct list_head *devices = dm_table_get_devices(t);
- struct dm_target_callbacks *cb;
-
- list_for_each_entry(dd, devices, list) {
- struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);
- char b[BDEVNAME_SIZE];
-
- if (likely(q))
- blk_unplug(q);
- else
- DMWARN_LIMIT("%s: Cannot unplug nonexistent device %s",
- dm_device_name(t->md),
- bdevname(dd->dm_dev.bdev, b));
- }
-
- list_for_each_entry(cb, &t->target_callbacks, list)
- if (cb->unplug_fn)
- cb->unplug_fn(cb);
-}
-
struct mapped_device *dm_table_get_md(struct dm_table *t)
{
return t->md;
EXPORT_SYMBOL(dm_table_get_md);
EXPORT_SYMBOL(dm_table_put);
EXPORT_SYMBOL(dm_table_get);
-EXPORT_SYMBOL(dm_table_unplug_all);
dm_unprep_request(rq);
spin_lock_irqsave(q->queue_lock, flags);
- if (elv_queue_empty(q))
- blk_plug_device(q);
blk_requeue_request(q, rq);
spin_unlock_irqrestore(q->queue_lock, flags);
* number of in-flight I/Os after the queue is stopped in
* dm_suspend().
*/
- while (!blk_queue_plugged(q) && !blk_queue_stopped(q)) {
+ while (!blk_queue_stopped(q)) {
rq = blk_peek_request(q);
if (!rq)
- goto plug_and_out;
+ goto delay_and_out;
/* always use block 0 to find the target for flushes for now */
pos = 0;
BUG_ON(!dm_target_is_valid(ti));
if (ti->type->busy && ti->type->busy(ti))
- goto plug_and_out;
+ goto delay_and_out;
blk_start_request(rq);
clone = rq->special;
BUG_ON(!irqs_disabled());
spin_lock(q->queue_lock);
-plug_and_out:
- if (!elv_queue_empty(q))
- /* Some requests still remain, retry later */
- blk_plug_device(q);
-
+delay_and_out:
+ blk_delay_queue(q, HZ / 10);
out:
dm_table_put(map);
return r;
}
-static void dm_unplug_all(struct request_queue *q)
-{
- struct mapped_device *md = q->queuedata;
- struct dm_table *map = dm_get_live_table(md);
-
- if (map) {
- if (dm_request_based(md))
- generic_unplug_device(q);
-
- dm_table_unplug_all(map);
- dm_table_put(map);
- }
-}
-
static int dm_any_congested(void *congested_data, int bdi_bits)
{
int r = bdi_bits;
md->queue->backing_dev_info.congested_data = md;
blk_queue_make_request(md->queue, dm_request);
blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
- md->queue->unplug_fn = dm_unplug_all;
blk_queue_merge_bvec(md->queue, dm_merge_bvec);
blk_queue_flush(md->queue, REQ_FLUSH | REQ_FUA);
}
int r = 0;
DECLARE_WAITQUEUE(wait, current);
- dm_unplug_all(md->queue);
-
add_wait_queue(&md->wait, &wait);
while (1) {
clear_bit(DMF_SUSPENDED, &md->flags);
- dm_table_unplug_all(map);
r = 0;
out:
dm_table_put(map);
return maxsectors << 9;
}
-static void linear_unplug(struct request_queue *q)
-{
- mddev_t *mddev = q->queuedata;
- linear_conf_t *conf;
- int i;
-
- rcu_read_lock();
- conf = rcu_dereference(mddev->private);
-
- for (i=0; i < mddev->raid_disks; i++) {
- struct request_queue *r_queue = bdev_get_queue(conf->disks[i].rdev->bdev);
- blk_unplug(r_queue);
- }
- rcu_read_unlock();
-}
-
static int linear_congested(void *data, int bits)
{
mddev_t *mddev = data;
md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
- mddev->queue->unplug_fn = linear_unplug;
mddev->queue->backing_dev_info.congested_fn = linear_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
md_integrity_register(mddev);
__md_stop_writes(mddev);
md_stop(mddev);
mddev->queue->merge_bvec_fn = NULL;
- mddev->queue->unplug_fn = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
/* tell userspace to handle 'inactive' */
void md_unplug(mddev_t *mddev)
{
- if (mddev->queue)
- blk_unplug(mddev->queue);
if (mddev->plug)
mddev->plug->unplug_fn(mddev->plug);
}
>= mddev->resync_max - mddev->curr_resync_completed
)) {
/* time to update curr_resync_completed */
- md_unplug(mddev);
wait_event(mddev->recovery_wait,
atomic_read(&mddev->recovery_active) == 0);
mddev->curr_resync_completed = j;
* about not overloading the IO subsystem. (things like an
* e2fsck being done on the RAID array should execute fast)
*/
- md_unplug(mddev);
cond_resched();
currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2
* this also signals 'finished resyncing' to md_stop
*/
out:
- md_unplug(mddev);
-
wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
/* tell personality that we are finished */
rdev_dec_pending(rdev, conf->mddev);
}
-static void unplug_slaves(mddev_t *mddev)
-{
- multipath_conf_t *conf = mddev->private;
- int i;
-
- rcu_read_lock();
- for (i=0; i<mddev->raid_disks; i++) {
- mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
- if (rdev && !test_bit(Faulty, &rdev->flags)
- && atomic_read(&rdev->nr_pending)) {
- struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
-
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
-
- blk_unplug(r_queue);
-
- rdev_dec_pending(rdev, mddev);
- rcu_read_lock();
- }
- }
- rcu_read_unlock();
-}
-
-static void multipath_unplug(struct request_queue *q)
-{
- unplug_slaves(q->queuedata);
-}
-
-
static int multipath_make_request(mddev_t *mddev, struct bio * bio)
{
multipath_conf_t *conf = mddev->private;
*/
md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
- mddev->queue->unplug_fn = multipath_unplug;
mddev->queue->backing_dev_info.congested_fn = multipath_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
md_integrity_register(mddev);
#include "raid0.h"
#include "raid5.h"
-static void raid0_unplug(struct request_queue *q)
-{
- mddev_t *mddev = q->queuedata;
- raid0_conf_t *conf = mddev->private;
- mdk_rdev_t **devlist = conf->devlist;
- int raid_disks = conf->strip_zone[0].nb_dev;
- int i;
-
- for (i=0; i < raid_disks; i++) {
- struct request_queue *r_queue = bdev_get_queue(devlist[i]->bdev);
-
- blk_unplug(r_queue);
- }
-}
-
static int raid0_congested(void *data, int bits)
{
mddev_t *mddev = data;
mdname(mddev),
(unsigned long long)smallest->sectors);
}
- mddev->queue->unplug_fn = raid0_unplug;
mddev->queue->backing_dev_info.congested_fn = raid0_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
#define NR_RAID1_BIOS 256
-static void unplug_slaves(mddev_t *mddev);
-
static void allow_barrier(conf_t *conf);
static void lower_barrier(conf_t *conf);
static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
{
struct pool_info *pi = data;
- r1bio_t *r1_bio;
int size = offsetof(r1bio_t, bios[pi->raid_disks]);
/* allocate a r1bio with room for raid_disks entries in the bios array */
- r1_bio = kzalloc(size, gfp_flags);
- if (!r1_bio && pi->mddev)
- unplug_slaves(pi->mddev);
-
- return r1_bio;
+ return kzalloc(size, gfp_flags);
}
static void r1bio_pool_free(void *r1_bio, void *data)
int i, j;
r1_bio = r1bio_pool_alloc(gfp_flags, pi);
- if (!r1_bio) {
- unplug_slaves(pi->mddev);
+ if (!r1_bio)
return NULL;
- }
/*
* Allocate bios : 1 for reading, n-1 for writing
return new_disk;
}
-static void unplug_slaves(mddev_t *mddev)
-{
- conf_t *conf = mddev->private;
- int i;
-
- rcu_read_lock();
- for (i=0; i<mddev->raid_disks; i++) {
- mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
- if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
- struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
-
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
-
- blk_unplug(r_queue);
-
- rdev_dec_pending(rdev, mddev);
- rcu_read_lock();
- }
- }
- rcu_read_unlock();
-}
-
-static void raid1_unplug(struct request_queue *q)
-{
- mddev_t *mddev = q->queuedata;
-
- unplug_slaves(mddev);
- md_wakeup_thread(mddev->thread);
-}
-
static int raid1_congested(void *data, int bits)
{
mddev_t *mddev = data;
}
-static int flush_pending_writes(conf_t *conf)
+static void flush_pending_writes(conf_t *conf)
{
/* Any writes that have been queued but are awaiting
* bitmap updates get flushed here.
- * We return 1 if any requests were actually submitted.
*/
- int rv = 0;
-
spin_lock_irq(&conf->device_lock);
if (conf->pending_bio_list.head) {
struct bio *bio;
bio = bio_list_get(&conf->pending_bio_list);
- blk_remove_plug(conf->mddev->queue);
spin_unlock_irq(&conf->device_lock);
/* flush any pending bitmap writes to
* disk before proceeding w/ I/O */
generic_make_request(bio);
bio = next;
}
- rv = 1;
} else
spin_unlock_irq(&conf->device_lock);
- return rv;
+}
+
+static void md_kick_device(mddev_t *mddev)
+{
+ blk_flush_plug(current);
+ md_wakeup_thread(mddev->thread);
}
/* Barriers....
/* Wait until no block IO is waiting */
wait_event_lock_irq(conf->wait_barrier, !conf->nr_waiting,
- conf->resync_lock,
- raid1_unplug(conf->mddev->queue));
+ conf->resync_lock, md_kick_device(conf->mddev));
/* block any new IO from starting */
conf->barrier++;
/* Now wait for all pending IO to complete */
wait_event_lock_irq(conf->wait_barrier,
!conf->nr_pending && conf->barrier < RESYNC_DEPTH,
- conf->resync_lock,
- raid1_unplug(conf->mddev->queue));
+ conf->resync_lock, md_kick_device(conf->mddev));
spin_unlock_irq(&conf->resync_lock);
}
conf->nr_waiting++;
wait_event_lock_irq(conf->wait_barrier, !conf->barrier,
conf->resync_lock,
- raid1_unplug(conf->mddev->queue));
+ md_kick_device(conf->mddev));
conf->nr_waiting--;
}
conf->nr_pending++;
conf->nr_pending == conf->nr_queued+1,
conf->resync_lock,
({ flush_pending_writes(conf);
- raid1_unplug(conf->mddev->queue); }));
+ md_kick_device(conf->mddev); }));
spin_unlock_irq(&conf->resync_lock);
}
static void unfreeze_array(conf_t *conf)
atomic_inc(&r1_bio->remaining);
spin_lock_irqsave(&conf->device_lock, flags);
bio_list_add(&conf->pending_bio_list, mbio);
- blk_plug_device(mddev->queue);
spin_unlock_irqrestore(&conf->device_lock, flags);
}
r1_bio_write_done(r1_bio, bio->bi_vcnt, behind_pages, behind_pages != NULL);
/* In case raid1d snuck in to freeze_array */
wake_up(&conf->wait_barrier);
- if (do_sync)
+ if (do_sync || !bitmap)
md_wakeup_thread(mddev->thread);
return 0;
unsigned long flags;
conf_t *conf = mddev->private;
struct list_head *head = &conf->retry_list;
- int unplug=0;
mdk_rdev_t *rdev;
md_check_recovery(mddev);
for (;;) {
char b[BDEVNAME_SIZE];
- unplug += flush_pending_writes(conf);
+ flush_pending_writes(conf);
spin_lock_irqsave(&conf->device_lock, flags);
if (list_empty(head)) {
mddev = r1_bio->mddev;
conf = mddev->private;
- if (test_bit(R1BIO_IsSync, &r1_bio->state)) {
+ if (test_bit(R1BIO_IsSync, &r1_bio->state))
sync_request_write(mddev, r1_bio);
- unplug = 1;
- } else {
+ else {
int disk;
/* we got a read error. Maybe the drive is bad. Maybe just
bio->bi_end_io = raid1_end_read_request;
bio->bi_rw = READ | do_sync;
bio->bi_private = r1_bio;
- unplug = 1;
generic_make_request(bio);
}
}
cond_resched();
}
- if (unplug)
- unplug_slaves(mddev);
}
md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
- mddev->queue->unplug_fn = raid1_unplug;
mddev->queue->backing_dev_info.congested_fn = raid1_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
md_integrity_register(mddev);
*/
#define NR_RAID10_BIOS 256
-static void unplug_slaves(mddev_t *mddev);
-
static void allow_barrier(conf_t *conf);
static void lower_barrier(conf_t *conf);
static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
{
conf_t *conf = data;
- r10bio_t *r10_bio;
int size = offsetof(struct r10bio_s, devs[conf->copies]);
/* allocate a r10bio with room for raid_disks entries in the bios array */
- r10_bio = kzalloc(size, gfp_flags);
- if (!r10_bio && conf->mddev)
- unplug_slaves(conf->mddev);
-
- return r10_bio;
+ return kzalloc(size, gfp_flags);
}
static void r10bio_pool_free(void *r10_bio, void *data)
int nalloc;
r10_bio = r10bio_pool_alloc(gfp_flags, conf);
- if (!r10_bio) {
- unplug_slaves(conf->mddev);
+ if (!r10_bio)
return NULL;
- }
if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery))
nalloc = conf->copies; /* resync */
return disk;
}
-static void unplug_slaves(mddev_t *mddev)
-{
- conf_t *conf = mddev->private;
- int i;
-
- rcu_read_lock();
- for (i=0; i < conf->raid_disks; i++) {
- mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
- if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
- struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
-
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
-
- blk_unplug(r_queue);
-
- rdev_dec_pending(rdev, mddev);
- rcu_read_lock();
- }
- }
- rcu_read_unlock();
-}
-
-static void raid10_unplug(struct request_queue *q)
-{
- mddev_t *mddev = q->queuedata;
-
- unplug_slaves(q->queuedata);
- md_wakeup_thread(mddev->thread);
-}
-
static int raid10_congested(void *data, int bits)
{
mddev_t *mddev = data;
return ret;
}
-static int flush_pending_writes(conf_t *conf)
+static void flush_pending_writes(conf_t *conf)
{
/* Any writes that have been queued but are awaiting
* bitmap updates get flushed here.
- * We return 1 if any requests were actually submitted.
*/
- int rv = 0;
-
spin_lock_irq(&conf->device_lock);
if (conf->pending_bio_list.head) {
struct bio *bio;
bio = bio_list_get(&conf->pending_bio_list);
- blk_remove_plug(conf->mddev->queue);
spin_unlock_irq(&conf->device_lock);
/* flush any pending bitmap writes to disk
* before proceeding w/ I/O */
generic_make_request(bio);
bio = next;
}
- rv = 1;
} else
spin_unlock_irq(&conf->device_lock);
- return rv;
}
+
+static void md_kick_device(mddev_t *mddev)
+{
+ blk_flush_plug(current);
+ md_wakeup_thread(mddev->thread);
+}
+
/* Barriers....
* Sometimes we need to suspend IO while we do something else,
* either some resync/recovery, or reconfigure the array.
/* Wait until no block IO is waiting (unless 'force') */
wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
- conf->resync_lock,
- raid10_unplug(conf->mddev->queue));
+ conf->resync_lock, md_kick_device(conf->mddev));
/* block any new IO from starting */
conf->barrier++;
/* No wait for all pending IO to complete */
wait_event_lock_irq(conf->wait_barrier,
!conf->nr_pending && conf->barrier < RESYNC_DEPTH,
- conf->resync_lock,
- raid10_unplug(conf->mddev->queue));
+ conf->resync_lock, md_kick_device(conf->mddev));
spin_unlock_irq(&conf->resync_lock);
}
conf->nr_waiting++;
wait_event_lock_irq(conf->wait_barrier, !conf->barrier,
conf->resync_lock,
- raid10_unplug(conf->mddev->queue));
+ md_kick_device(conf->mddev));
conf->nr_waiting--;
}
conf->nr_pending++;
conf->nr_pending == conf->nr_queued+1,
conf->resync_lock,
({ flush_pending_writes(conf);
- raid10_unplug(conf->mddev->queue); }));
+ md_kick_device(conf->mddev); }));
spin_unlock_irq(&conf->resync_lock);
}
atomic_inc(&r10_bio->remaining);
spin_lock_irqsave(&conf->device_lock, flags);
bio_list_add(&conf->pending_bio_list, mbio);
- blk_plug_device(mddev->queue);
spin_unlock_irqrestore(&conf->device_lock, flags);
}
/* In case raid10d snuck in to freeze_array */
wake_up(&conf->wait_barrier);
- if (do_sync)
+ if (do_sync || !mddev->bitmap)
md_wakeup_thread(mddev->thread);
return 0;
unsigned long flags;
conf_t *conf = mddev->private;
struct list_head *head = &conf->retry_list;
- int unplug=0;
mdk_rdev_t *rdev;
md_check_recovery(mddev);
for (;;) {
char b[BDEVNAME_SIZE];
- unplug += flush_pending_writes(conf);
+ flush_pending_writes(conf);
spin_lock_irqsave(&conf->device_lock, flags);
if (list_empty(head)) {
mddev = r10_bio->mddev;
conf = mddev->private;
- if (test_bit(R10BIO_IsSync, &r10_bio->state)) {
+ if (test_bit(R10BIO_IsSync, &r10_bio->state))
sync_request_write(mddev, r10_bio);
- unplug = 1;
- } else if (test_bit(R10BIO_IsRecover, &r10_bio->state)) {
+ else if (test_bit(R10BIO_IsRecover, &r10_bio->state))
recovery_request_write(mddev, r10_bio);
- unplug = 1;
- } else {
+ else {
int mirror;
/* we got a read error. Maybe the drive is bad. Maybe just
* the block and we can fix it.
bio->bi_rw = READ | do_sync;
bio->bi_private = r10_bio;
bio->bi_end_io = raid10_end_read_request;
- unplug = 1;
generic_make_request(bio);
}
}
cond_resched();
}
- if (unplug)
- unplug_slaves(mddev);
}
md_set_array_sectors(mddev, size);
mddev->resync_max_sectors = size;
- mddev->queue->unplug_fn = raid10_unplug;
mddev->queue->backing_dev_info.congested_fn = raid10_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
return 0;
}
-static void unplug_slaves(mddev_t *mddev);
-
static struct stripe_head *
get_active_stripe(raid5_conf_t *conf, sector_t sector,
int previous, int noblock, int noquiesce)
< (conf->max_nr_stripes *3/4)
|| !conf->inactive_blocked),
conf->device_lock,
- md_raid5_unplug_device(conf)
- );
+ md_raid5_kick_device(conf));
conf->inactive_blocked = 0;
} else
init_stripe(sh, sector, previous);
wait_event_lock_irq(conf->wait_for_stripe,
!list_empty(&conf->inactive_list),
conf->device_lock,
- unplug_slaves(conf->mddev)
- );
+ blk_flush_plug(current));
osh = get_free_stripe(conf);
spin_unlock_irq(&conf->device_lock);
atomic_set(&nsh->count, 1);
}
}
-static void unplug_slaves(mddev_t *mddev)
+void md_raid5_kick_device(raid5_conf_t *conf)
{
- raid5_conf_t *conf = mddev->private;
- int i;
- int devs = max(conf->raid_disks, conf->previous_raid_disks);
-
- rcu_read_lock();
- for (i = 0; i < devs; i++) {
- mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
- struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
-
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
-
- blk_unplug(r_queue);
-
- rdev_dec_pending(rdev, mddev);
- rcu_read_lock();
- }
- }
- rcu_read_unlock();
-}
-
-void md_raid5_unplug_device(raid5_conf_t *conf)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&conf->device_lock, flags);
-
- if (plugger_remove_plug(&conf->plug)) {
- conf->seq_flush++;
- raid5_activate_delayed(conf);
- }
+ blk_flush_plug(current);
+ raid5_activate_delayed(conf);
md_wakeup_thread(conf->mddev->thread);
-
- spin_unlock_irqrestore(&conf->device_lock, flags);
-
- unplug_slaves(conf->mddev);
}
-EXPORT_SYMBOL_GPL(md_raid5_unplug_device);
+EXPORT_SYMBOL_GPL(md_raid5_kick_device);
static void raid5_unplug(struct plug_handle *plug)
{
raid5_conf_t *conf = container_of(plug, raid5_conf_t, plug);
- md_raid5_unplug_device(conf);
-}
-static void raid5_unplug_queue(struct request_queue *q)
-{
- mddev_t *mddev = q->queuedata;
- md_raid5_unplug_device(mddev->private);
+ md_raid5_kick_device(conf);
}
int md_raid5_congested(mddev_t *mddev, int bits)
* add failed due to overlap. Flush everything
* and wait a while
*/
- md_raid5_unplug_device(conf);
+ md_raid5_kick_device(conf);
release_stripe(sh);
schedule();
goto retry;
if (sector_nr >= max_sector) {
/* just being told to finish up .. nothing much to do */
- unplug_slaves(mddev);
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
end_reshape(conf);
spin_unlock_irq(&conf->device_lock);
async_tx_issue_pending_all();
- unplug_slaves(mddev);
pr_debug("--- raid5d inactive\n");
}
mddev->queue->backing_dev_info.congested_data = mddev;
mddev->queue->backing_dev_info.congested_fn = raid5_congested;
mddev->queue->queue_lock = &conf->device_lock;
- mddev->queue->unplug_fn = raid5_unplug_queue;
chunk_size = mddev->chunk_sectors << 9;
blk_queue_io_min(mddev->queue, chunk_size);
}
extern int md_raid5_congested(mddev_t *mddev, int bits);
-extern void md_raid5_unplug_device(raid5_conf_t *conf);
+extern void md_raid5_kick_device(raid5_conf_t *conf);
extern int raid5_set_cache_size(mddev_t *mddev, int size);
#endif
{
struct request *req;
- while (!blk_queue_plugged(q)) {
- req = blk_peek_request(q);
- if (!req)
- break;
-
+ while ((req = blk_peek_request(q)) != NULL) {
if (req->cmd_type == REQ_TYPE_FS) {
struct i2o_block_delayed_request *dreq;
struct i2o_block_request *ireq = req->special;
spin_lock_irq(q->queue_lock);
set_current_state(TASK_INTERRUPTIBLE);
- if (!blk_queue_plugged(q))
- req = blk_fetch_request(q);
+ req = blk_fetch_request(q);
mq->req = req;
spin_unlock_irq(q->queue_lock);
return;
}
/* Now we try to fetch requests from the request queue */
- while (!blk_queue_plugged(queue) && (req = blk_peek_request(queue))) {
+ while ((req = blk_peek_request(queue))) {
if (basedev->features & DASD_FEATURE_READONLY &&
rq_data_dir(req) == WRITE) {
DBF_DEV_EVENT(DBF_ERR, basedev,
spin_lock_irq(&device->blk_data.request_queue_lock);
while (
- !blk_queue_plugged(queue) &&
blk_peek_request(queue) &&
nr_queued < TAPEBLOCK_MIN_REQUEUE
) {
if (!get_device(dev))
return;
- while (!blk_queue_plugged(q)) {
+ while (1) {
if (rport && (rport->port_state == FC_PORTSTATE_BLOCKED) &&
!(rport->flags & FC_RPORT_FAST_FAIL_TIMEDOUT))
break;
int ret;
int (*handler)(struct Scsi_Host *, struct sas_rphy *, struct request *);
- while (!blk_queue_plugged(q)) {
- req = blk_fetch_request(q);
- if (!req)
- break;
-
+ while ((req = blk_fetch_request(q)) != NULL) {
spin_unlock_irq(q->queue_lock);
handler = to_sas_internal(shost->transportt)->f->smp_handler;
{
struct se_device *dev = task->task_se_cmd->se_dev;
struct iblock_req *req = IBLOCK_REQ(task);
- struct iblock_dev *ibd = (struct iblock_dev *)req->ib_dev;
- struct request_queue *q = bdev_get_queue(ibd->ibd_bd);
struct bio *bio = req->ib_bio, *nbio = NULL;
+ struct blk_plug plug;
int rw;
if (task->task_data_direction == DMA_TO_DEVICE) {
rw = READ;
}
+ blk_start_plug(&plug);
while (bio) {
nbio = bio->bi_next;
bio->bi_next = NULL;
submit_bio(rw, bio);
bio = nbio;
}
+ blk_finish_plug(&plug);
- if (q->unplug_fn)
- q->unplug_fn(q);
return PYX_TRANSPORT_SENT_TO_TRANSPORT;
}
static const struct address_space_operations adfs_aops = {
.readpage = adfs_readpage,
.writepage = adfs_writepage,
- .sync_page = block_sync_page,
.write_begin = adfs_write_begin,
.write_end = generic_write_end,
.bmap = _adfs_bmap
const struct address_space_operations affs_aops = {
.readpage = affs_readpage,
.writepage = affs_writepage,
- .sync_page = block_sync_page,
.write_begin = affs_write_begin,
.write_end = generic_write_end,
.bmap = _affs_bmap
const struct address_space_operations affs_aops_ofs = {
.readpage = affs_readpage_ofs,
//.writepage = affs_writepage_ofs,
- //.sync_page = affs_sync_page_ofs,
.write_begin = affs_write_begin_ofs,
.write_end = affs_write_end_ofs
};
struct hlist_node *pos, *n;
int i;
+ /*
+ * TODO: kill this
+ */
for (i = 0; i < AIO_BATCH_HASH_SIZE; i++) {
hlist_for_each_entry_safe(abe, pos, n, &batch_hash[i], list) {
- blk_run_address_space(abe->mapping);
iput(abe->mapping->host);
hlist_del(&abe->list);
mempool_free(abe, abe_pool);
static const struct address_space_operations befs_aops = {
.readpage = befs_readpage,
- .sync_page = block_sync_page,
.bmap = befs_bmap,
};
const struct address_space_operations bfs_aops = {
.readpage = bfs_readpage,
.writepage = bfs_writepage,
- .sync_page = block_sync_page,
.write_begin = bfs_write_begin,
.write_end = generic_write_end,
.bmap = bfs_bmap,
static const struct address_space_operations def_blk_aops = {
.readpage = blkdev_readpage,
.writepage = blkdev_writepage,
- .sync_page = block_sync_page,
.write_begin = blkdev_write_begin,
.write_end = blkdev_write_end,
.writepages = generic_writepages,
.writepages = btree_writepages,
.releasepage = btree_releasepage,
.invalidatepage = btree_invalidatepage,
- .sync_page = block_sync_page,
#ifdef CONFIG_MIGRATION
.migratepage = btree_migratepage,
#endif
}
/*
- * this unplugs every device on the box, and it is only used when page
- * is null
- */
-static void __unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
- struct btrfs_device *device;
- struct btrfs_fs_info *info;
-
- info = (struct btrfs_fs_info *)bdi->unplug_io_data;
- list_for_each_entry(device, &info->fs_devices->devices, dev_list) {
- if (!device->bdev)
- continue;
-
- bdi = blk_get_backing_dev_info(device->bdev);
- if (bdi->unplug_io_fn)
- bdi->unplug_io_fn(bdi, page);
- }
-}
-
-static void btrfs_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
- struct inode *inode;
- struct extent_map_tree *em_tree;
- struct extent_map *em;
- struct address_space *mapping;
- u64 offset;
-
- /* the generic O_DIRECT read code does this */
- if (1 || !page) {
- __unplug_io_fn(bdi, page);
- return;
- }
-
- /*
- * page->mapping may change at any time. Get a consistent copy
- * and use that for everything below
- */
- smp_mb();
- mapping = page->mapping;
- if (!mapping)
- return;
-
- inode = mapping->host;
-
- /*
- * don't do the expensive searching for a small number of
- * devices
- */
- if (BTRFS_I(inode)->root->fs_info->fs_devices->open_devices <= 2) {
- __unplug_io_fn(bdi, page);
- return;
- }
-
- offset = page_offset(page);
-
- em_tree = &BTRFS_I(inode)->extent_tree;
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, offset, PAGE_CACHE_SIZE);
- read_unlock(&em_tree->lock);
- if (!em) {
- __unplug_io_fn(bdi, page);
- return;
- }
-
- if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- free_extent_map(em);
- __unplug_io_fn(bdi, page);
- return;
- }
- offset = offset - em->start;
- btrfs_unplug_page(&BTRFS_I(inode)->root->fs_info->mapping_tree,
- em->block_start + offset, page);
- free_extent_map(em);
-}
-
-/*
* If this fails, caller must call bdi_destroy() to get rid of the
* bdi again.
*/
return err;
bdi->ra_pages = default_backing_dev_info.ra_pages;
- bdi->unplug_io_fn = btrfs_unplug_io_fn;
- bdi->unplug_io_data = info;
bdi->congested_fn = btrfs_congested_fn;
bdi->congested_data = info;
return 0;
.writepage = btrfs_writepage,
.writepages = btrfs_writepages,
.readpages = btrfs_readpages,
- .sync_page = block_sync_page,
.direct_IO = btrfs_direct_IO,
.invalidatepage = btrfs_invalidatepage,
.releasepage = btrfs_releasepage,
struct bio *cur;
int again = 0;
unsigned long num_run;
- unsigned long num_sync_run;
unsigned long batch_run = 0;
unsigned long limit;
unsigned long last_waited = 0;
limit = btrfs_async_submit_limit(fs_info);
limit = limit * 2 / 3;
- /* we want to make sure that every time we switch from the sync
- * list to the normal list, we unplug
- */
- num_sync_run = 0;
-
loop:
spin_lock(&device->io_lock);
spin_unlock(&device->io_lock);
- /*
- * if we're doing the regular priority list, make sure we unplug
- * for any high prio bios we've sent down
- */
- if (pending_bios == &device->pending_bios && num_sync_run > 0) {
- num_sync_run = 0;
- blk_run_backing_dev(bdi, NULL);
- }
-
while (pending) {
rmb();
BUG_ON(atomic_read(&cur->bi_cnt) == 0);
- if (cur->bi_rw & REQ_SYNC)
- num_sync_run++;
-
submit_bio(cur->bi_rw, cur);
num_run++;
batch_run++;
- if (need_resched()) {
- if (num_sync_run) {
- blk_run_backing_dev(bdi, NULL);
- num_sync_run = 0;
- }
+ if (need_resched())
cond_resched();
- }
/*
* we made progress, there is more work to do and the bdi
* against it before looping
*/
last_waited = ioc->last_waited;
- if (need_resched()) {
- if (num_sync_run) {
- blk_run_backing_dev(bdi, NULL);
- num_sync_run = 0;
- }
+ if (need_resched())
cond_resched();
- }
continue;
}
spin_lock(&device->io_lock);
}
}
- if (num_sync_run) {
- num_sync_run = 0;
- blk_run_backing_dev(bdi, NULL);
- }
- /*
- * IO has already been through a long path to get here. Checksumming,
- * async helper threads, perhaps compression. We've done a pretty
- * good job of collecting a batch of IO and should just unplug
- * the device right away.
- *
- * This will help anyone who is waiting on the IO, they might have
- * already unplugged, but managed to do so before the bio they
- * cared about found its way down here.
- */
- blk_run_backing_dev(bdi, NULL);
-
cond_resched();
if (again)
goto loop;
static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
u64 logical, u64 *length,
struct btrfs_multi_bio **multi_ret,
- int mirror_num, struct page *unplug_page)
+ int mirror_num)
{
struct extent_map *em;
struct map_lookup *map;
em = lookup_extent_mapping(em_tree, logical, *length);
read_unlock(&em_tree->lock);
- if (!em && unplug_page) {
- kfree(multi);
- return 0;
- }
-
if (!em) {
printk(KERN_CRIT "unable to find logical %llu len %llu\n",
(unsigned long long)logical,
*length = em->len - offset;
}
- if (!multi_ret && !unplug_page)
+ if (!multi_ret)
goto out;
num_stripes = 1;
stripe_index = 0;
if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
- if (unplug_page || (rw & REQ_WRITE))
+ if (rw & REQ_WRITE)
num_stripes = map->num_stripes;
else if (mirror_num)
stripe_index = mirror_num - 1;
stripe_index = do_div(stripe_nr, factor);
stripe_index *= map->sub_stripes;
- if (unplug_page || (rw & REQ_WRITE))
+ if (rw & REQ_WRITE)
num_stripes = map->sub_stripes;
else if (mirror_num)
stripe_index += mirror_num - 1;
BUG_ON(stripe_index >= map->num_stripes);
for (i = 0; i < num_stripes; i++) {
- if (unplug_page) {
- struct btrfs_device *device;
- struct backing_dev_info *bdi;
-
- device = map->stripes[stripe_index].dev;
- if (device->bdev) {
- bdi = blk_get_backing_dev_info(device->bdev);
- if (bdi->unplug_io_fn)
- bdi->unplug_io_fn(bdi, unplug_page);
- }
- } else {
- multi->stripes[i].physical =
- map->stripes[stripe_index].physical +
- stripe_offset + stripe_nr * map->stripe_len;
- multi->stripes[i].dev = map->stripes[stripe_index].dev;
- }
+ multi->stripes[i].physical =
+ map->stripes[stripe_index].physical +
+ stripe_offset + stripe_nr * map->stripe_len;
+ multi->stripes[i].dev = map->stripes[stripe_index].dev;
stripe_index++;
}
if (multi_ret) {
struct btrfs_multi_bio **multi_ret, int mirror_num)
{
return __btrfs_map_block(map_tree, rw, logical, length, multi_ret,
- mirror_num, NULL);
+ mirror_num);
}
int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
return 0;
}
-int btrfs_unplug_page(struct btrfs_mapping_tree *map_tree,
- u64 logical, struct page *page)
-{
- u64 length = PAGE_CACHE_SIZE;
- return __btrfs_map_block(map_tree, READ, logical, &length,
- NULL, 0, page);
-}
-
static void end_bio_multi_stripe(struct bio *bio, int err)
{
struct btrfs_multi_bio *multi = bio->bi_private;
}
EXPORT_SYMBOL(init_buffer);
-static int sync_buffer(void *word)
+static int sleep_on_buffer(void *word)
{
- struct block_device *bd;
- struct buffer_head *bh
- = container_of(word, struct buffer_head, b_state);
-
- smp_mb();
- bd = bh->b_bdev;
- if (bd)
- blk_run_address_space(bd->bd_inode->i_mapping);
io_schedule();
return 0;
}
void __lock_buffer(struct buffer_head *bh)
{
- wait_on_bit_lock(&bh->b_state, BH_Lock, sync_buffer,
+ wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_buffer);
*/
void __wait_on_buffer(struct buffer_head * bh)
{
- wait_on_bit(&bh->b_state, BH_Lock, sync_buffer, TASK_UNINTERRUPTIBLE);
+ wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__wait_on_buffer);
{
struct buffer_head *bh;
struct list_head tmp;
- struct address_space *mapping, *prev_mapping = NULL;
+ struct address_space *mapping;
int err = 0, err2;
INIT_LIST_HEAD(&tmp);
* wait_on_buffer() will do that for us
* through sync_buffer().
*/
- if (prev_mapping && prev_mapping != mapping)
- blk_run_address_space(prev_mapping);
- prev_mapping = mapping;
-
brelse(bh);
spin_lock(lock);
}
}
EXPORT_SYMBOL(try_to_free_buffers);
-void block_sync_page(struct page *page)
-{
- struct address_space *mapping;
-
- smp_mb();
- mapping = page_mapping(page);
- if (mapping)
- blk_run_backing_dev(mapping->backing_dev_info, page);
-}
-EXPORT_SYMBOL(block_sync_page);
-
/*
* There are no bdflush tunables left. But distributions are
* still running obsolete flush daemons, so we terminate them here.
return rc;
}
-/* static void cifs_sync_page(struct page *page)
-{
- struct address_space *mapping;
- struct inode *inode;
- unsigned long index = page->index;
- unsigned int rpages = 0;
- int rc = 0;
-
- cFYI(1, "sync page %p", page);
- mapping = page->mapping;
- if (!mapping)
- return 0;
- inode = mapping->host;
- if (!inode)
- return; */
-
-/* fill in rpages then
- result = cifs_pagein_inode(inode, index, rpages); */ /* BB finish */
-
-/* cFYI(1, "rpages is %d for sync page of Index %ld", rpages, index);
-
-#if 0
- if (rc < 0)
- return rc;
- return 0;
-#endif
-} */
-
/*
* As file closes, flush all cached write data for this inode checking
* for write behind errors.
.set_page_dirty = __set_page_dirty_nobuffers,
.releasepage = cifs_release_page,
.invalidatepage = cifs_invalidate_page,
- /* .sync_page = cifs_sync_page, */
/* .direct_IO = */
};
.set_page_dirty = __set_page_dirty_nobuffers,
.releasepage = cifs_release_page,
.invalidatepage = cifs_invalidate_page,
- /* .sync_page = cifs_sync_page, */
/* .direct_IO = */
};
((rw & READ) || (dio->result == dio->size)))
ret = -EIOCBQUEUED;
- if (ret != -EIOCBQUEUED) {
- /* All IO is now issued, send it on its way */
- blk_run_address_space(inode->i_mapping);
+ if (ret != -EIOCBQUEUED)
dio_await_completion(dio);
- }
/*
* Sync will always be dropping the final ref and completing the
}
static const struct address_space_operations efs_aops = {
.readpage = efs_readpage,
- .sync_page = block_sync_page,
.bmap = _efs_bmap
};
.direct_IO = NULL, /* TODO: Should be trivial to do */
/* With these NULL has special meaning or default is not exported */
- .sync_page = NULL,
.get_xip_mem = NULL,
.migratepage = NULL,
.launder_page = NULL,
.readpage = ext2_readpage,
.readpages = ext2_readpages,
.writepage = ext2_writepage,
- .sync_page = block_sync_page,
.write_begin = ext2_write_begin,
.write_end = ext2_write_end,
.bmap = ext2_bmap,
.readpage = ext2_readpage,
.readpages = ext2_readpages,
.writepage = ext2_nobh_writepage,
- .sync_page = block_sync_page,
.write_begin = ext2_nobh_write_begin,
.write_end = nobh_write_end,
.bmap = ext2_bmap,
.readpage = ext3_readpage,
.readpages = ext3_readpages,
.writepage = ext3_ordered_writepage,
- .sync_page = block_sync_page,
.write_begin = ext3_write_begin,
.write_end = ext3_ordered_write_end,
.bmap = ext3_bmap,
.readpage = ext3_readpage,
.readpages = ext3_readpages,
.writepage = ext3_writeback_writepage,
- .sync_page = block_sync_page,
.write_begin = ext3_write_begin,
.write_end = ext3_writeback_write_end,
.bmap = ext3_bmap,
.readpage = ext3_readpage,
.readpages = ext3_readpages,
.writepage = ext3_journalled_writepage,
- .sync_page = block_sync_page,
.write_begin = ext3_write_begin,
.write_end = ext3_journalled_write_end,
.set_page_dirty = ext3_journalled_set_page_dirty,
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
- .sync_page = block_sync_page,
.write_begin = ext4_write_begin,
.write_end = ext4_ordered_write_end,
.bmap = ext4_bmap,
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
- .sync_page = block_sync_page,
.write_begin = ext4_write_begin,
.write_end = ext4_writeback_write_end,
.bmap = ext4_bmap,
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
- .sync_page = block_sync_page,
.write_begin = ext4_write_begin,
.write_end = ext4_journalled_write_end,
.set_page_dirty = ext4_journalled_set_page_dirty,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
.writepages = ext4_da_writepages,
- .sync_page = block_sync_page,
.write_begin = ext4_da_write_begin,
.write_end = ext4_da_write_end,
.bmap = ext4_bmap,
.readpages = fat_readpages,
.writepage = fat_writepage,
.writepages = fat_writepages,
- .sync_page = block_sync_page,
.write_begin = fat_write_begin,
.write_end = fat_write_end,
.direct_IO = fat_direct_IO,
const struct address_space_operations vxfs_aops = {
.readpage = vxfs_readpage,
.bmap = vxfs_bmap,
- .sync_page = block_sync_page,
};
inline void
fc->bdi.name = "fuse";
fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
- fc->bdi.unplug_io_fn = default_unplug_io_fn;
/* fuse does it's own writeback accounting */
fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB;
.writepages = gfs2_writeback_writepages,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
- .sync_page = block_sync_page,
.write_begin = gfs2_write_begin,
.write_end = gfs2_write_end,
.bmap = gfs2_bmap,
.writepage = gfs2_ordered_writepage,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
- .sync_page = block_sync_page,
.write_begin = gfs2_write_begin,
.write_end = gfs2_write_end,
.set_page_dirty = gfs2_set_page_dirty,
.writepages = gfs2_jdata_writepages,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
- .sync_page = block_sync_page,
.write_begin = gfs2_write_begin,
.write_end = gfs2_write_end,
.set_page_dirty = gfs2_set_page_dirty,
const struct address_space_operations gfs2_meta_aops = {
.writepage = gfs2_aspace_writepage,
.releasepage = gfs2_releasepage,
- .sync_page = block_sync_page,
};
/**
const struct address_space_operations hfs_btree_aops = {
.readpage = hfs_readpage,
.writepage = hfs_writepage,
- .sync_page = block_sync_page,
.write_begin = hfs_write_begin,
.write_end = generic_write_end,
.bmap = hfs_bmap,
const struct address_space_operations hfs_aops = {
.readpage = hfs_readpage,
.writepage = hfs_writepage,
- .sync_page = block_sync_page,
.write_begin = hfs_write_begin,
.write_end = generic_write_end,
.bmap = hfs_bmap,
const struct address_space_operations hfsplus_btree_aops = {
.readpage = hfsplus_readpage,
.writepage = hfsplus_writepage,
- .sync_page = block_sync_page,
.write_begin = hfsplus_write_begin,
.write_end = generic_write_end,
.bmap = hfsplus_bmap,
const struct address_space_operations hfsplus_aops = {
.readpage = hfsplus_readpage,
.writepage = hfsplus_writepage,
- .sync_page = block_sync_page,
.write_begin = hfsplus_write_begin,
.write_end = generic_write_end,
.bmap = hfsplus_bmap,
const struct address_space_operations hpfs_aops = {
.readpage = hpfs_readpage,
.writepage = hpfs_writepage,
- .sync_page = block_sync_page,
.write_begin = hpfs_write_begin,
.write_end = generic_write_end,
.bmap = _hpfs_bmap
static const struct address_space_operations isofs_aops = {
.readpage = isofs_readpage,
- .sync_page = block_sync_page,
.bmap = _isofs_bmap
};
.readpages = jfs_readpages,
.writepage = jfs_writepage,
.writepages = jfs_writepages,
- .sync_page = block_sync_page,
.write_begin = jfs_write_begin,
.write_end = nobh_write_end,
.bmap = jfs_bmap,
const struct address_space_operations jfs_metapage_aops = {
.readpage = metapage_readpage,
.writepage = metapage_writepage,
- .sync_page = block_sync_page,
.releasepage = metapage_releasepage,
.invalidatepage = metapage_invalidatepage,
.set_page_dirty = __set_page_dirty_nobuffers,
bio.bi_end_io = request_complete;
submit_bio(rw, &bio);
- generic_unplug_device(bdev_get_queue(bdev));
wait_for_completion(&complete);
return test_bit(BIO_UPTODATE, &bio.bi_flags) ? 0 : -EIO;
}
}
len = PAGE_ALIGN(len);
__bdev_writeseg(sb, ofs, ofs >> PAGE_SHIFT, len >> PAGE_SHIFT);
- generic_unplug_device(bdev_get_queue(logfs_super(sb)->s_bdev));
}
static const struct address_space_operations minix_aops = {
.readpage = minix_readpage,
.writepage = minix_writepage,
- .sync_page = block_sync_page,
.write_begin = minix_write_begin,
.write_end = generic_write_end,
.bmap = minix_bmap
nilfs_mapping_init_once(btnc);
}
-static const struct address_space_operations def_btnode_aops = {
- .sync_page = block_sync_page,
-};
-
void nilfs_btnode_cache_init(struct address_space *btnc,
struct backing_dev_info *bdi)
{
- nilfs_mapping_init(btnc, bdi, &def_btnode_aops);
+ nilfs_mapping_init(btnc, bdi);
}
void nilfs_btnode_cache_clear(struct address_space *btnc)
#include "ifile.h"
static const struct address_space_operations def_gcinode_aops = {
- .sync_page = block_sync_page,
};
/*
const struct address_space_operations nilfs_aops = {
.writepage = nilfs_writepage,
.readpage = nilfs_readpage,
- .sync_page = block_sync_page,
.writepages = nilfs_writepages,
.set_page_dirty = nilfs_set_page_dirty,
.readpages = nilfs_readpages,
static const struct address_space_operations def_mdt_aops = {
.writepage = nilfs_mdt_write_page,
- .sync_page = block_sync_page,
};
static const struct inode_operations def_mdt_iops;
mi->mi_first_entry_offset = DIV_ROUND_UP(header_size, entry_size);
}
-static const struct address_space_operations shadow_map_aops = {
- .sync_page = block_sync_page,
-};
-
/**
* nilfs_mdt_setup_shadow_map - setup shadow map and bind it to metadata file
* @inode: inode of the metadata file
INIT_LIST_HEAD(&shadow->frozen_buffers);
nilfs_mapping_init_once(&shadow->frozen_data);
- nilfs_mapping_init(&shadow->frozen_data, bdi, &shadow_map_aops);
+ nilfs_mapping_init(&shadow->frozen_data, bdi);
nilfs_mapping_init_once(&shadow->frozen_btnodes);
- nilfs_mapping_init(&shadow->frozen_btnodes, bdi, &shadow_map_aops);
+ nilfs_mapping_init(&shadow->frozen_btnodes, bdi);
mi->mi_shadow = shadow;
return 0;
}
}
void nilfs_mapping_init(struct address_space *mapping,
- struct backing_dev_info *bdi,
- const struct address_space_operations *aops)
+ struct backing_dev_info *bdi)
{
mapping->host = NULL;
mapping->flags = 0;
mapping_set_gfp_mask(mapping, GFP_NOFS);
mapping->assoc_mapping = NULL;
mapping->backing_dev_info = bdi;
- mapping->a_ops = aops;
+ mapping->a_ops = NULL;
}
/*
void nilfs_clear_dirty_pages(struct address_space *);
void nilfs_mapping_init_once(struct address_space *mapping);
void nilfs_mapping_init(struct address_space *mapping,
- struct backing_dev_info *bdi,
- const struct address_space_operations *aops);
+ struct backing_dev_info *bdi);
unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);
unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
sector_t start_blk,
*/
const struct address_space_operations ntfs_aops = {
.readpage = ntfs_readpage, /* Fill page with data. */
- .sync_page = block_sync_page, /* Currently, just unplugs the
- disk request queue. */
#ifdef NTFS_RW
.writepage = ntfs_writepage, /* Write dirty page to disk. */
#endif /* NTFS_RW */
*/
const struct address_space_operations ntfs_mst_aops = {
.readpage = ntfs_readpage, /* Fill page with data. */
- .sync_page = block_sync_page, /* Currently, just unplugs the
- disk request queue. */
#ifdef NTFS_RW
.writepage = ntfs_writepage, /* Write dirty page to disk. */
.set_page_dirty = __set_page_dirty_nobuffers, /* Set the page dirty
"uptodate! Unplugging the disk queue "
"and rescheduling.");
get_bh(tbh);
- blk_run_address_space(mapping);
- schedule();
+ io_schedule();
put_bh(tbh);
if (unlikely(!buffer_uptodate(tbh)))
goto read_err;
.write_begin = ocfs2_write_begin,
.write_end = ocfs2_write_end,
.bmap = ocfs2_bmap,
- .sync_page = block_sync_page,
.direct_IO = ocfs2_direct_IO,
.invalidatepage = ocfs2_invalidatepage,
.releasepage = ocfs2_releasepage,
static void o2hb_wait_on_io(struct o2hb_region *reg,
struct o2hb_bio_wait_ctxt *wc)
{
- struct address_space *mapping = reg->hr_bdev->bd_inode->i_mapping;
-
- blk_run_address_space(mapping);
o2hb_bio_wait_dec(wc, 1);
-
wait_for_completion(&wc->wc_io_complete);
}
.readpages = omfs_readpages,
.writepage = omfs_writepage,
.writepages = omfs_writepages,
- .sync_page = block_sync_page,
.write_begin = omfs_write_begin,
.write_end = generic_write_end,
.bmap = omfs_bmap,
static const struct address_space_operations qnx4_aops = {
.readpage = qnx4_readpage,
.writepage = qnx4_writepage,
- .sync_page = block_sync_page,
.write_begin = qnx4_write_begin,
.write_end = generic_write_end,
.bmap = qnx4_bmap
.readpages = reiserfs_readpages,
.releasepage = reiserfs_releasepage,
.invalidatepage = reiserfs_invalidatepage,
- .sync_page = block_sync_page,
.write_begin = reiserfs_write_begin,
.write_end = reiserfs_write_end,
.bmap = reiserfs_aop_bmap,
const struct address_space_operations sysv_aops = {
.readpage = sysv_readpage,
.writepage = sysv_writepage,
- .sync_page = block_sync_page,
.write_begin = sysv_write_begin,
.write_end = generic_write_end,
.bmap = sysv_bmap
*/
c->bdi.name = "ubifs",
c->bdi.capabilities = BDI_CAP_MAP_COPY;
- c->bdi.unplug_io_fn = default_unplug_io_fn;
err = bdi_init(&c->bdi);
if (err)
goto out_close;
const struct address_space_operations udf_adinicb_aops = {
.readpage = udf_adinicb_readpage,
.writepage = udf_adinicb_writepage,
- .sync_page = block_sync_page,
.write_begin = simple_write_begin,
.write_end = udf_adinicb_write_end,
};
const struct address_space_operations udf_aops = {
.readpage = udf_readpage,
.writepage = udf_writepage,
- .sync_page = block_sync_page,
.write_begin = udf_write_begin,
.write_end = generic_write_end,
.bmap = udf_bmap,
const struct address_space_operations ufs_aops = {
.readpage = ufs_readpage,
.writepage = ufs_writepage,
- .sync_page = block_sync_page,
.write_begin = ufs_write_begin,
.write_end = generic_write_end,
.bmap = ufs_bmap
break;
if (IS_SYNC(inode) && (inode->i_state & I_DIRTY))
ufs_sync_inode (inode);
- blk_run_address_space(inode->i_mapping);
+ blk_flush_plug(current);
yield();
}
.readpages = xfs_vm_readpages,
.writepage = xfs_vm_writepage,
.writepages = xfs_vm_writepages,
- .sync_page = block_sync_page,
.releasepage = xfs_vm_releasepage,
.invalidatepage = xfs_vm_invalidatepage,
.write_begin = xfs_vm_write_begin,
if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
xfs_log_force(bp->b_target->bt_mount, 0);
if (atomic_read(&bp->b_io_remaining))
- blk_run_address_space(bp->b_target->bt_mapping);
+ blk_flush_plug(current);
down(&bp->b_sema);
XB_SET_OWNER(bp);
set_current_state(TASK_UNINTERRUPTIBLE);
if (atomic_read(&bp->b_pin_count) == 0)
break;
- if (atomic_read(&bp->b_io_remaining))
- blk_run_address_space(bp->b_target->bt_mapping);
- schedule();
+ io_schedule();
}
remove_wait_queue(&bp->b_waiters, &wait);
set_current_state(TASK_RUNNING);
trace_xfs_buf_iowait(bp, _RET_IP_);
if (atomic_read(&bp->b_io_remaining))
- blk_run_address_space(bp->b_target->bt_mapping);
+ blk_flush_plug(current);
wait_for_completion(&bp->b_iowait);
trace_xfs_buf_iowait_done(bp, _RET_IP_);
struct inode *inode;
struct address_space *mapping;
static const struct address_space_operations mapping_aops = {
- .sync_page = block_sync_page,
.migratepage = fail_migrate_page,
};
count++;
}
if (count)
- blk_run_address_space(target->bt_mapping);
+ blk_flush_plug(current);
} while (!kthread_should_stop());
if (wait) {
/* Expedite and wait for IO to complete. */
- blk_run_address_space(target->bt_mapping);
+ blk_flush_plug(current);
while (!list_empty(&wait_list)) {
bp = list_first_entry(&wait_list, struct xfs_buf, b_list);
unsigned int capabilities; /* Device capabilities */
congested_fn *congested_fn; /* Function pointer if device is md/dm */
void *congested_data; /* Pointer to aux data for congested func */
- void (*unplug_io_fn)(struct backing_dev_info *, struct page *);
- void *unplug_io_data;
char *name;
extern struct backing_dev_info default_backing_dev_info;
extern struct backing_dev_info noop_backing_dev_info;
-void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page);
int writeback_in_progress(struct backing_dev_info *bdi);
return 0;
}
-static inline void blk_run_backing_dev(struct backing_dev_info *bdi,
- struct page *page)
-{
- if (bdi && bdi->unplug_io_fn)
- bdi->unplug_io_fn(bdi, page);
-}
-
-static inline void blk_run_address_space(struct address_space *mapping)
-{
- if (mapping)
- blk_run_backing_dev(mapping->backing_dev_info, NULL);
-}
-
#endif /* _LINUX_BACKING_DEV_H */
typedef int (make_request_fn) (struct request_queue *q, struct bio *bio);
typedef int (prep_rq_fn) (struct request_queue *, struct request *);
typedef void (unprep_rq_fn) (struct request_queue *, struct request *);
-typedef void (unplug_fn) (struct request_queue *);
struct bio_vec;
struct bvec_merge_data {
make_request_fn *make_request_fn;
prep_rq_fn *prep_rq_fn;
unprep_rq_fn *unprep_rq_fn;
- unplug_fn *unplug_fn;
merge_bvec_fn *merge_bvec_fn;
softirq_done_fn *softirq_done_fn;
rq_timed_out_fn *rq_timed_out_fn;
struct request *boundary_rq;
/*
- * Auto-unplugging state
- */
- struct timer_list unplug_timer;
- int unplug_thresh; /* After this many requests */
- unsigned long unplug_delay; /* After this many jiffies */
- struct work_struct unplug_work;
-
- /*
* Delayed queue handling
*/
struct delayed_work delay_work;
#define QUEUE_FLAG_ASYNCFULL 4 /* write queue has been filled */
#define QUEUE_FLAG_DEAD 5 /* queue being torn down */
#define QUEUE_FLAG_REENTER 6 /* Re-entrancy avoidance */
-#define QUEUE_FLAG_PLUGGED 7 /* queue is plugged */
-#define QUEUE_FLAG_ELVSWITCH 8 /* don't use elevator, just do FIFO */
-#define QUEUE_FLAG_BIDI 9 /* queue supports bidi requests */
-#define QUEUE_FLAG_NOMERGES 10 /* disable merge attempts */
-#define QUEUE_FLAG_SAME_COMP 11 /* force complete on same CPU */
-#define QUEUE_FLAG_FAIL_IO 12 /* fake timeout */
-#define QUEUE_FLAG_STACKABLE 13 /* supports request stacking */
-#define QUEUE_FLAG_NONROT 14 /* non-rotational device (SSD) */
+#define QUEUE_FLAG_ELVSWITCH 7 /* don't use elevator, just do FIFO */
+#define QUEUE_FLAG_BIDI 8 /* queue supports bidi requests */
+#define QUEUE_FLAG_NOMERGES 9 /* disable merge attempts */
+#define QUEUE_FLAG_SAME_COMP 10 /* force complete on same CPU */
+#define QUEUE_FLAG_FAIL_IO 11 /* fake timeout */
+#define QUEUE_FLAG_STACKABLE 12 /* supports request stacking */
+#define QUEUE_FLAG_NONROT 13 /* non-rotational device (SSD) */
#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */
#define QUEUE_FLAG_IO_STAT 15 /* do IO stats */
#define QUEUE_FLAG_DISCARD 16 /* supports DISCARD */
__clear_bit(flag, &q->queue_flags);
}
-#define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
#define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
#define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
#define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
extern void blk_rq_unprep_clone(struct request *rq);
extern int blk_insert_cloned_request(struct request_queue *q,
struct request *rq);
-extern void blk_plug_device(struct request_queue *);
-extern void blk_plug_device_unlocked(struct request_queue *);
-extern int blk_remove_plug(struct request_queue *);
extern void blk_delay_queue(struct request_queue *, unsigned long);
extern void blk_recount_segments(struct request_queue *, struct bio *);
extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
struct request *, int);
extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
struct request *, int, rq_end_io_fn *);
-extern void blk_unplug(struct request_queue *q);
static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
{
extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
extern void blk_dump_rq_flags(struct request *, char *);
-extern void generic_unplug_device(struct request_queue *);
extern long nr_blockdev_pages(void);
int blk_get_queue(struct request_queue *);
int block_commit_write(struct page *page, unsigned from, unsigned to);
int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block);
-void block_sync_page(struct page *);
sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
int block_truncate_page(struct address_space *, loff_t, get_block_t *);
int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned,
int dm_table_complete(struct dm_table *t);
/*
- * Unplug all devices in a table.
- */
-void dm_table_unplug_all(struct dm_table *t);
-
-/*
* Table reference counting.
*/
struct dm_table *dm_get_live_table(struct mapped_device *md);
typedef int (elevator_dispatch_fn) (struct request_queue *, int);
typedef void (elevator_add_req_fn) (struct request_queue *, struct request *);
-typedef int (elevator_queue_empty_fn) (struct request_queue *);
typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *);
typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *);
typedef int (elevator_may_queue_fn) (struct request_queue *, int);
elevator_activate_req_fn *elevator_activate_req_fn;
elevator_deactivate_req_fn *elevator_deactivate_req_fn;
- elevator_queue_empty_fn *elevator_queue_empty_fn;
elevator_completed_req_fn *elevator_completed_req_fn;
elevator_request_list_fn *elevator_former_req_fn;
*/
extern void elv_dispatch_sort(struct request_queue *, struct request *);
extern void elv_dispatch_add_tail(struct request_queue *, struct request *);
-extern void elv_add_request(struct request_queue *, struct request *, int, int);
-extern void __elv_add_request(struct request_queue *, struct request *, int, int);
+extern void elv_add_request(struct request_queue *, struct request *, int);
+extern void __elv_add_request(struct request_queue *, struct request *, int);
extern void elv_insert(struct request_queue *, struct request *, int);
extern int elv_merge(struct request_queue *, struct request **, struct bio *);
extern int elv_try_merge(struct request *, struct bio *);
extern void elv_bio_merged(struct request_queue *q, struct request *,
struct bio *);
extern void elv_requeue_request(struct request_queue *, struct request *);
-extern int elv_queue_empty(struct request_queue *);
extern struct request *elv_former_request(struct request_queue *, struct request *);
extern struct request *elv_latter_request(struct request_queue *, struct request *);
extern int elv_register_queue(struct request_queue *q);
struct address_space_operations {
int (*writepage)(struct page *page, struct writeback_control *wbc);
int (*readpage)(struct file *, struct page *);
- void (*sync_page)(struct page *);
/* Write back some dirty pages from this mapping. */
int (*writepages)(struct address_space *, struct writeback_control *);
extern void __lock_page(struct page *page);
extern int __lock_page_killable(struct page *page);
-extern void __lock_page_nosync(struct page *page);
extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags);
extern void unlock_page(struct page *page);
}
/*
- * lock_page_nosync should only be used if we can't pin the page's inode.
- * Doesn't play quite so well with block device plugging.
- */
-static inline void lock_page_nosync(struct page *page)
-{
- might_sleep();
- if (!trylock_page(page))
- __lock_page_nosync(page);
-}
-
-/*
* lock_page_or_retry - Lock the page, unless this would block and the
* caller indicated that it can handle a retry.
*/
struct page **pagep, swp_entry_t *ent);
#endif
-extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *);
-
#ifdef CONFIG_SWAP
/* linux/mm/page_io.c */
extern int swap_readpage(struct page *);
static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
-void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-}
-EXPORT_SYMBOL(default_unplug_io_fn);
-
struct backing_dev_info default_backing_dev_info = {
.name = "default",
.ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
.state = 0,
.capabilities = BDI_CAP_MAP_COPY,
- .unplug_io_fn = default_unplug_io_fn,
};
EXPORT_SYMBOL_GPL(default_backing_dev_info);
}
EXPORT_SYMBOL(remove_from_page_cache);
-static int sync_page(void *word)
+static int sleep_on_page(void *word)
{
- struct address_space *mapping;
- struct page *page;
-
- page = container_of((unsigned long *)word, struct page, flags);
-
- /*
- * page_mapping() is being called without PG_locked held.
- * Some knowledge of the state and use of the page is used to
- * reduce the requirements down to a memory barrier.
- * The danger here is of a stale page_mapping() return value
- * indicating a struct address_space different from the one it's
- * associated with when it is associated with one.
- * After smp_mb(), it's either the correct page_mapping() for
- * the page, or an old page_mapping() and the page's own
- * page_mapping() has gone NULL.
- * The ->sync_page() address_space operation must tolerate
- * page_mapping() going NULL. By an amazing coincidence,
- * this comes about because none of the users of the page
- * in the ->sync_page() methods make essential use of the
- * page_mapping(), merely passing the page down to the backing
- * device's unplug functions when it's non-NULL, which in turn
- * ignore it for all cases but swap, where only page_private(page) is
- * of interest. When page_mapping() does go NULL, the entire
- * call stack gracefully ignores the page and returns.
- * -- wli
- */
- smp_mb();
- mapping = page_mapping(page);
- if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
- mapping->a_ops->sync_page(page);
io_schedule();
return 0;
}
-static int sync_page_killable(void *word)
+static int sleep_on_page_killable(void *word)
{
- sync_page(word);
+ sleep_on_page(word);
return fatal_signal_pending(current) ? -EINTR : 0;
}
EXPORT_SYMBOL(__page_cache_alloc);
#endif
-static int __sleep_on_page_lock(void *word)
-{
- io_schedule();
- return 0;
-}
-
/*
* In order to wait for pages to become available there must be
* waitqueues associated with pages. By using a hash table of
DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
if (test_bit(bit_nr, &page->flags))
- __wait_on_bit(page_waitqueue(page), &wait, sync_page,
+ __wait_on_bit(page_waitqueue(page), &wait, sleep_on_page,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_on_page_bit);
/**
* __lock_page - get a lock on the page, assuming we need to sleep to get it
* @page: the page to lock
- *
- * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary. If some
- * random driver's requestfn sets TASK_RUNNING, we could busywait. However
- * chances are that on the second loop, the block layer's plug list is empty,
- * so sync_page() will then return in state TASK_UNINTERRUPTIBLE.
*/
void __lock_page(struct page *page)
{
DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
- __wait_on_bit_lock(page_waitqueue(page), &wait, sync_page,
+ __wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_page);
DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
return __wait_on_bit_lock(page_waitqueue(page), &wait,
- sync_page_killable, TASK_KILLABLE);
+ sleep_on_page_killable, TASK_KILLABLE);
}
EXPORT_SYMBOL_GPL(__lock_page_killable);
-/**
- * __lock_page_nosync - get a lock on the page, without calling sync_page()
- * @page: the page to lock
- *
- * Variant of lock_page that does not require the caller to hold a reference
- * on the page's mapping.
- */
-void __lock_page_nosync(struct page *page)
-{
- DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
- __wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock,
- TASK_UNINTERRUPTIBLE);
-}
-
int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags)
{
collect_procs(ppage, &tokill);
if (hpage != ppage)
- lock_page_nosync(ppage);
+ lock_page(ppage);
ret = try_to_unmap(ppage, ttu);
if (ret != SWAP_SUCCESS)
* Check "just unpoisoned", "filter hit", and
* "race with other subpage."
*/
- lock_page_nosync(hpage);
+ lock_page(hpage);
if (!PageHWPoison(hpage)
|| (hwpoison_filter(p) && TestClearPageHWPoison(p))
|| (p != hpage && TestSetPageHWPoison(hpage))) {
* It's very difficult to mess with pages currently under IO
* and in many cases impossible, so we just avoid it here.
*/
- lock_page_nosync(hpage);
+ lock_page(hpage);
/*
* unpoison always clear PG_hwpoison inside page lock
return 0;
}
- lock_page_nosync(page);
+ lock_page(page);
/*
* This test is racy because PG_hwpoison is set outside of page lock.
* That's acceptable because that won't trigger kernel panic. Instead,
}
EXPORT_SYMBOL(remap_vmalloc_range);
-void swap_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-}
-
unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
{
int ret;
- lock_page_nosync(page);
+ lock_page(page);
ret = set_page_dirty(page);
unlock_page(page);
return ret;
/* do read-ahead */
ondemand_readahead(mapping, ra, filp, true, offset, req_size);
-
-#ifdef CONFIG_BLOCK
- /*
- * Normally the current page is !uptodate and lock_page() will be
- * immediately called to implicitly unplug the device. However this
- * is not always true for RAID conifgurations, where data arrives
- * not strictly in their submission order. In this case we need to
- * explicitly kick off the IO.
- */
- if (PageUptodate(page))
- blk_run_backing_dev(mapping->backing_dev_info, NULL);
-#endif
}
EXPORT_SYMBOL_GPL(page_cache_async_readahead);
static struct backing_dev_info shmem_backing_dev_info __read_mostly = {
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
- .unplug_io_fn = default_unplug_io_fn,
};
static LIST_HEAD(shmem_swaplist);
/*
* swapper_space is a fiction, retained to simplify the path through
- * vmscan's shrink_page_list, to make sync_page look nicer, and to allow
- * future use of radix_tree tags in the swap cache.
+ * vmscan's shrink_page_list.
*/
static const struct address_space_operations swap_aops = {
.writepage = swap_writepage,
- .sync_page = block_sync_page,
.set_page_dirty = __set_page_dirty_nobuffers,
.migratepage = migrate_page,
};
static struct backing_dev_info swap_backing_dev_info = {
.name = "swap",
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
- .unplug_io_fn = swap_unplug_io_fn,
};
struct address_space swapper_space = {
}
/*
- * We need this because the bdev->unplug_fn can sleep and we cannot
- * hold swap_lock while calling the unplug_fn. And swap_lock
- * cannot be turned into a mutex.
- */
-static DECLARE_RWSEM(swap_unplug_sem);
-
-void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page)
-{
- swp_entry_t entry;
-
- down_read(&swap_unplug_sem);
- entry.val = page_private(page);
- if (PageSwapCache(page)) {
- struct block_device *bdev = swap_info[swp_type(entry)]->bdev;
- struct backing_dev_info *bdi;
-
- /*
- * If the page is removed from swapcache from under us (with a
- * racy try_to_unuse/swapoff) we need an additional reference
- * count to avoid reading garbage from page_private(page) above.
- * If the WARN_ON triggers during a swapoff it maybe the race
- * condition and it's harmless. However if it triggers without
- * swapoff it signals a problem.
- */
- WARN_ON(page_count(page) <= 1);
-
- bdi = bdev->bd_inode->i_mapping->backing_dev_info;
- blk_run_backing_dev(bdi, page);
- }
- up_read(&swap_unplug_sem);
-}
-
-/*
* swapon tell device that all the old swap contents can be discarded,
* to allow the swap device to optimize its wear-levelling.
*/
goto out_dput;
}
- /* wait for any unplug function to finish */
- down_write(&swap_unplug_sem);
- up_write(&swap_unplug_sem);
-
destroy_swap_extents(p);
if (p->flags & SWP_CONTINUED)
free_swap_count_continuations(p);
static void handle_write_error(struct address_space *mapping,
struct page *page, int error)
{
- lock_page_nosync(page);
+ lock_page(page);
if (page_mapping(page) == mapping)
mapping_set_error(mapping, error);
unlock_page(page);
projects / linux-flexiantxendom0.git / commitdiff