Merge branch 'for-2.6.39/stack-plug' into for-2.6.39/core

Conflicts:
	block/blk-core.c
	block/blk-flush.c
	drivers/md/raid1.c
	drivers/md/raid10.c
	drivers/md/raid5.c
	fs/nilfs2/btnode.c
	fs/nilfs2/mdt.c

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

Documentation/block/biodoc.txt

@@ -963,11 +963,6 @@ elevator_dispatch_fn*		fills the dispatch queue with ready requests.
 
 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

block/blk-core.c

@@ -27,6 +27,7 @@
 #include <linux/writeback.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/fault-inject.h>
+#include <linux/list_sort.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
@@ -198,135 +199,43 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
 /*
- * "plug" the device if there are no outstanding requests: this will
+ * Make sure that plugs that were pending when this function was entered,
- * force the transfer to start only after we have put all the requests
+ * are now complete and requests pushed to the queue.
- * 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)
+static inline void queue_sync_plugs(struct request_queue *q)
 {
-	WARN_ON(!irqs_disabled());
-
 	/*
-	 * don't plug a stopped queue, it must be paired with blk_start_queue()
+	 * If the current process is plugged and has barriers submitted,
-	 * which will restart the queueing
+	 * we will livelock if we don't unplug first.
 	 */
-	if (blk_queue_stopped(q))
+	blk_flush_plug(current);
-		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);
 
-/**
+static void blk_delay_work(struct work_struct *work)
- * 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;
+	struct request_queue *q;
 
-	spin_lock_irqsave(q->queue_lock, flags);
+	q = container_of(work, struct request_queue, delay_work.work);
-	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);
+	__blk_run_queue(q, false);
 	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)
+ * blk_delay_queue - restart queueing after defined interval
-{
+ * @q:		The &struct request_queue in question
-	struct request_queue *q = bdi->unplug_io_data;
+ * @msecs:	Delay in msecs
-
+ *
-	blk_unplug(q);
+ * Description:
-}
+ *   Sometimes queueing needs to be postponed for a little while, to allow
-
+ *   resources to come back. This function will make sure that queueing is
-void blk_unplug_work(struct work_struct *work)
+ *   restarted around the specified time.
-{
-	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) {
+void blk_delay_queue(struct request_queue *q, unsigned long msecs)
-		trace_block_unplug_io(q);
+{
-		q->unplug_fn(q);
+	schedule_delayed_work(&q->delay_work, msecs_to_jiffies(msecs));
 }
-}
+EXPORT_SYMBOL(blk_delay_queue);
-EXPORT_SYMBOL(blk_unplug);
 
 /**
  * blk_start_queue - restart a previously stopped queue
@@ -362,7 +271,7 @@ EXPORT_SYMBOL(blk_start_queue);
  **/
 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);
 }
 EXPORT_SYMBOL(blk_stop_queue);
@@ -387,9 +296,9 @@ EXPORT_SYMBOL(blk_stop_queue);
  */
 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);
+	cancel_delayed_work_sync(&q->delay_work);
+	queue_sync_plugs(q);
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
@@ -405,14 +314,9 @@ EXPORT_SYMBOL(blk_sync_queue);
  */
 void __blk_run_queue(struct request_queue *q, bool force_kblockd)
 {
-	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.
@@ -420,10 +324,8 @@ void __blk_run_queue(struct request_queue *q, bool force_kblockd)
 	if (!force_kblockd && !queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
 		q->request_fn(q);
 		queue_flag_clear(QUEUE_FLAG_REENTER, q);
-	} else {
+	} else
-		queue_flag_set(QUEUE_FLAG_PLUGGED, q);
+		queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
-		kblockd_schedule_work(q, &q->unplug_work);
-	}
 }
 EXPORT_SYMBOL(__blk_run_queue);
 
@@ -517,8 +419,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (!q)
 		return NULL;
 
-	q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
-	q->backing_dev_info.unplug_io_data = q;
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 	q->backing_dev_info.state = 0;
@@ -538,13 +438,12 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	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);
 
@@ -639,7 +538,6 @@ blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn,
 	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;
 
 	/* Override internal queue lock with supplied lock pointer */
@@ -677,6 +575,8 @@ int blk_get_queue(struct request_queue *q)
 
 static inline void blk_free_request(struct request_queue *q, struct request *rq)
 {
+	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
+
 	if (rq->cmd_flags & REQ_ELVPRIV)
 		elv_put_request(q, rq);
 	mempool_free(rq, q->rq.rq_pool);
@@ -898,8 +798,8 @@ out:
 }
 
 /*
- * No available requests for this queue, unplug the device and wait for some
+ * No available requests for this queue, wait for some requests to become
- * requests to become available.
+ * available.
  *
  * Called with q->queue_lock held, and returns with it unlocked.
  */
@@ -920,7 +820,6 @@ static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 
 		trace_block_sleeprq(q, bio, rw_flags & 1);
 
-		__generic_unplug_device(q);
 		spin_unlock_irq(q->queue_lock);
 		io_schedule();
 
@@ -1042,6 +941,13 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL(blk_requeue_request);
 
+static void add_acct_request(struct request_queue *q, struct request *rq,
+			     int where)
+{
+	drive_stat_acct(rq, 1);
+	__elv_add_request(q, rq, where);
+}
+
 /**
  * blk_insert_request - insert a special request into a request queue
  * @q:		request queue where request should be inserted
@@ -1084,8 +990,7 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 	if (blk_rq_tagged(rq))
 		blk_queue_end_tag(q, rq);
 
-	drive_stat_acct(rq, 1);
+	add_acct_request(q, rq, where);
-	__elv_add_request(q, rq, where, 0);
 	__blk_run_queue(q, false);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
@@ -1206,6 +1111,113 @@ void blk_add_request_payload(struct request *rq, struct page *page,
 }
 EXPORT_SYMBOL_GPL(blk_add_request_payload);
 
+static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
+				   struct bio *bio)
+{
+	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+
+	/*
+	 * Debug stuff, kill later
+	 */
+	if (!rq_mergeable(req)) {
+		blk_dump_rq_flags(req, "back");
+		return false;
+	}
+
+	if (!ll_back_merge_fn(q, req, bio))
+		return false;
+
+	trace_block_bio_backmerge(q, bio);
+
+	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+		blk_rq_set_mixed_merge(req);
+
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->__data_len += bio->bi_size;
+	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
+
+	drive_stat_acct(req, 0);
+	return true;
+}
+
+static bool bio_attempt_front_merge(struct request_queue *q,
+				    struct request *req, struct bio *bio)
+{
+	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	sector_t sector;
+
+	/*
+	 * Debug stuff, kill later
+	 */
+	if (!rq_mergeable(req)) {
+		blk_dump_rq_flags(req, "front");
+		return false;
+	}
+
+	if (!ll_front_merge_fn(q, req, bio))
+		return false;
+
+	trace_block_bio_frontmerge(q, bio);
+
+	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+		blk_rq_set_mixed_merge(req);
+
+	sector = bio->bi_sector;
+
+	bio->bi_next = req->bio;
+	req->bio = bio;
+
+	/*
+	 * may not be valid. if the low level driver said
+	 * it didn't need a bounce buffer then it better
+	 * not touch req->buffer either...
+	 */
+	req->buffer = bio_data(bio);
+	req->__sector = bio->bi_sector;
+	req->__data_len += bio->bi_size;
+	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
+
+	drive_stat_acct(req, 0);
+	return true;
+}
+
+/*
+ * Attempts to merge with the plugged list in the current process. Returns
+ * true if merge was succesful, otherwise false.
+ */
+static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q,
+			       struct bio *bio)
+{
+	struct blk_plug *plug;
+	struct request *rq;
+	bool ret = false;
+
+	plug = tsk->plug;
+	if (!plug)
+		goto out;
+
+	list_for_each_entry_reverse(rq, &plug->list, queuelist) {
+		int el_ret;
+
+		if (rq->q != q)
+			continue;
+
+		el_ret = elv_try_merge(rq, bio);
+		if (el_ret == ELEVATOR_BACK_MERGE) {
+			ret = bio_attempt_back_merge(q, rq, bio);
+			if (ret)
+				break;
+		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
+			ret = bio_attempt_front_merge(q, rq, bio);
+			if (ret)
+				break;
+		}
+	}
+out:
+	return ret;
+}
+
 void init_request_from_bio(struct request *req, struct bio *bio)
 {
 	req->cpu = bio->bi_comp_cpu;
@@ -1221,26 +1233,12 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	blk_rq_bio_prep(req->q, req, bio);
 }
 
-/*
- * Only disabling plugging for non-rotational devices if it does tagging
- * as well, otherwise we do need the proper merging
- */
-static inline bool queue_should_plug(struct request_queue *q)
-{
-	return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
-}
-
 static int __make_request(struct request_queue *q, struct bio *bio)
 {
-	struct request *req;
-	int el_ret;
-	unsigned int bytes = bio->bi_size;
-	const unsigned short prio = bio_prio(bio);
 	const bool sync = !!(bio->bi_rw & REQ_SYNC);
-	const bool unplug = !!(bio->bi_rw & REQ_UNPLUG);
+	struct blk_plug *plug;
-	const unsigned long ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
-	int where = ELEVATOR_INSERT_SORT;
+	struct request *req;
-	int rw_flags;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
@@ -1249,78 +1247,36 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	 */
 	blk_queue_bounce(q, &bio);
 
-	spin_lock_irq(q->queue_lock);
-
 	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
+		spin_lock_irq(q->queue_lock);
 		where = ELEVATOR_INSERT_FLUSH;
 		goto get_rq;
 	}
 
-	if (elv_queue_empty(q))
+	/*
-		goto get_rq;
+	 * Check if we can merge with the plugged list before grabbing
+	 * any locks.
+	 */
+	if (attempt_plug_merge(current, q, bio))
+		goto out;
+
+	spin_lock_irq(q->queue_lock);
 
 	el_ret = elv_merge(q, &req, bio);
-	switch (el_ret) {
+	if (el_ret == ELEVATOR_BACK_MERGE) {
-	case ELEVATOR_BACK_MERGE:
+		BUG_ON(req->cmd_flags & REQ_ON_PLUG);
-		BUG_ON(!rq_mergeable(req));
+		if (bio_attempt_back_merge(q, req, bio)) {
-
-		if (!ll_back_merge_fn(q, req, bio))
-			break;
-
-		trace_block_bio_backmerge(q, bio);
-
-		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
-			blk_rq_set_mixed_merge(req);
-
-		req->biotail->bi_next = bio;
-		req->biotail = bio;
-		req->__data_len += bytes;
-		req->ioprio = ioprio_best(req->ioprio, prio);
-		if (!blk_rq_cpu_valid(req))
-			req->cpu = bio->bi_comp_cpu;
-		drive_stat_acct(req, 0);
-		elv_bio_merged(q, req, bio);
 			if (!attempt_back_merge(q, req))
 				elv_merged_request(q, req, el_ret);
-		goto out;
+			goto out_unlock;
-
-	case ELEVATOR_FRONT_MERGE:
-		BUG_ON(!rq_mergeable(req));
-
-		if (!ll_front_merge_fn(q, req, bio))
-			break;
-
-		trace_block_bio_frontmerge(q, bio);
-
-		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
-			blk_rq_set_mixed_merge(req);
-			req->cmd_flags &= ~REQ_FAILFAST_MASK;
-			req->cmd_flags |= ff;
 		}
-
+	} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-		bio->bi_next = req->bio;
+		BUG_ON(req->cmd_flags & REQ_ON_PLUG);
-		req->bio = bio;
+		if (bio_attempt_front_merge(q, req, bio)) {
-
-		/*
-		 * may not be valid. if the low level driver said
-		 * it didn't need a bounce buffer then it better
-		 * not touch req->buffer either...
-		 */
-		req->buffer = bio_data(bio);
-		req->__sector = bio->bi_sector;
-		req->__data_len += bytes;
-		req->ioprio = ioprio_best(req->ioprio, prio);
-		if (!blk_rq_cpu_valid(req))
-			req->cpu = bio->bi_comp_cpu;
-		drive_stat_acct(req, 0);
-		elv_bio_merged(q, req, bio);
 			if (!attempt_front_merge(q, req))
 				elv_merged_request(q, req, el_ret);
-		goto out;
+			goto out_unlock;
-
+		}
-	/* ELV_NO_MERGE: elevator says don't/can't merge. */
-	default:
-		;
 	}
 
 get_rq:
@@ -1347,20 +1303,35 @@ get_rq:
 	 */
 	init_request_from_bio(req, bio);
 
-	spin_lock_irq(q->queue_lock);
 	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) ||
-	    bio_flagged(bio, BIO_CPU_AFFINE))
+	    bio_flagged(bio, BIO_CPU_AFFINE)) {
-		req->cpu = blk_cpu_to_group(smp_processor_id());
+		req->cpu = blk_cpu_to_group(get_cpu());
-	if (queue_should_plug(q) && elv_queue_empty(q))
+		put_cpu();
-		blk_plug_device(q);
+	}
 
-	/* insert the request into the elevator */
+	plug = current->plug;
+	if (plug) {
+		if (!plug->should_sort && !list_empty(&plug->list)) {
+			struct request *__rq;
+
+			__rq = list_entry_rq(plug->list.prev);
+			if (__rq->q != q)
+				plug->should_sort = 1;
+		}
+		/*
+		 * Debug flag, kill later
+		 */
+		req->cmd_flags |= REQ_ON_PLUG;
+		list_add_tail(&req->queuelist, &plug->list);
 		drive_stat_acct(req, 1);
-	__elv_add_request(q, req, where, 0);
+	} else {
-out:
+		spin_lock_irq(q->queue_lock);
-	if (unplug || !queue_should_plug(q))
+		add_acct_request(q, req, where);
-		__generic_unplug_device(q);
+		__blk_run_queue(q, false);
+out_unlock:
 		spin_unlock_irq(q->queue_lock);
+	}
+out:
 	return 0;
 }
 
@@ -1763,9 +1734,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	drive_stat_acct(rq, 1);
+	add_acct_request(q, rq, ELEVATOR_INSERT_BACK);
-	__elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 0);
-
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
 	return 0;
@@ -2643,6 +2612,113 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
 }
 EXPORT_SYMBOL(kblockd_schedule_work);
 
+int kblockd_schedule_delayed_work(struct request_queue *q,
+			struct delayed_work *dwork, unsigned long delay)
+{
+	return queue_delayed_work(kblockd_workqueue, dwork, delay);
+}
+EXPORT_SYMBOL(kblockd_schedule_delayed_work);
+
+#define PLUG_MAGIC	0x91827364
+
+void blk_start_plug(struct blk_plug *plug)
+{
+	struct task_struct *tsk = current;
+
+	plug->magic = PLUG_MAGIC;
+	INIT_LIST_HEAD(&plug->list);
+	plug->should_sort = 0;
+
+	/*
+	 * If this is a nested plug, don't actually assign it. It will be
+	 * flushed on its own.
+	 */
+	if (!tsk->plug) {
+		/*
+		 * Store ordering should not be needed here, since a potential
+		 * preempt will imply a full memory barrier
+		 */
+		tsk->plug = plug;
+	}
+}
+EXPORT_SYMBOL(blk_start_plug);
+
+static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct request *rqa = container_of(a, struct request, queuelist);
+	struct request *rqb = container_of(b, struct request, queuelist);
+
+	return !(rqa->q == rqb->q);
+}
+
+static void flush_plug_list(struct blk_plug *plug)
+{
+	struct request_queue *q;
+	unsigned long flags;
+	struct request *rq;
+
+	BUG_ON(plug->magic != PLUG_MAGIC);
+
+	if (list_empty(&plug->list))
+		return;
+
+	if (plug->should_sort)
+		list_sort(NULL, &plug->list, plug_rq_cmp);
+
+	q = NULL;
+	local_irq_save(flags);
+	while (!list_empty(&plug->list)) {
+		rq = list_entry_rq(plug->list.next);
+		list_del_init(&rq->queuelist);
+		BUG_ON(!(rq->cmd_flags & REQ_ON_PLUG));
+		BUG_ON(!rq->q);
+		if (rq->q != q) {
+			if (q) {
+				__blk_run_queue(q, false);
+				spin_unlock(q->queue_lock);
+			}
+			q = rq->q;
+			spin_lock(q->queue_lock);
+		}
+		rq->cmd_flags &= ~REQ_ON_PLUG;
+
+		/*
+		 * rq is already accounted, so use raw insert
+		 */
+		__elv_add_request(q, rq, ELEVATOR_INSERT_SORT);
+	}
+
+	if (q) {
+		__blk_run_queue(q, false);
+		spin_unlock(q->queue_lock);
+	}
+
+	BUG_ON(!list_empty(&plug->list));
+	local_irq_restore(flags);
+}
+
+static void __blk_finish_plug(struct task_struct *tsk, struct blk_plug *plug)
+{
+	flush_plug_list(plug);
+
+	if (plug == tsk->plug)
+		tsk->plug = NULL;
+}
+
+void blk_finish_plug(struct blk_plug *plug)
+{
+	if (plug)
+		__blk_finish_plug(current, plug);
+}
+EXPORT_SYMBOL(blk_finish_plug);
+
+void __blk_flush_plug(struct task_struct *tsk, struct blk_plug *plug)
+{
+	__blk_finish_plug(tsk, plug);
+	tsk->plug = plug;
+}
+EXPORT_SYMBOL(__blk_flush_plug);
+
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *

block/blk-exec.c

@@ -54,8 +54,8 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	rq->end_io = done;
 	WARN_ON(irqs_disabled());
 	spin_lock_irq(q->queue_lock);
-	__elv_add_request(q, rq, where, 1);
+	__elv_add_request(q, rq, where);
-	__generic_unplug_device(q);
+	__blk_run_queue(q, false);
 	/* the queue is stopped so it won't be plugged+unplugged */
 	if (rq->cmd_type == REQ_TYPE_PM_RESUME)
 		q->request_fn(q);

block/blk-flush.c

@@ -194,7 +194,6 @@ static void flush_end_io(struct request *flush_rq, int error)
 {
 	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;
 
@@ -218,7 +217,7 @@ static void flush_end_io(struct request *flush_rq, int error)
 	 * from request completion path and calling directly into
 	 * request_fn may confuse the driver.  Always use kblockd.
 	 */
-	if (queued && was_empty)
+	if (queued)
 		__blk_run_queue(q, true);
 }
 
@@ -269,13 +268,12 @@ static bool blk_kick_flush(struct request_queue *q)
 static void flush_data_end_io(struct request *rq, int error)
 {
 	struct request_queue *q = rq->q;
-	bool was_empty = elv_queue_empty(q);
 
 	/*
 	 * After populating an empty queue, kick it to avoid stall.  Read
 	 * the comment in flush_end_io().
 	 */
-	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error) && was_empty)
+	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error))
 		__blk_run_queue(q, true);
 }
 

block/blk-settings.c

@@ -164,14 +164,6 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 	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);
 

block/blk-throttle.c

@@ -768,6 +768,7 @@ static int throtl_dispatch(struct request_queue *q)
 	unsigned int nr_disp = 0;
 	struct bio_list bio_list_on_stack;
 	struct bio *bio;
+	struct blk_plug plug;
 
 	spin_lock_irq(q->queue_lock);
 
@@ -796,9 +797,10 @@ out:
 	 * immediate dispatch
 	 */
 	if (nr_disp) {
+		blk_start_plug(&plug);
 		while((bio = bio_list_pop(&bio_list_on_stack)))
 			generic_make_request(bio);
-		blk_unplug(q);
+		blk_finish_plug(&plug);
 	}
 	return nr_disp;
 }

block/blk.h

@@ -18,8 +18,6 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 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 *);

block/cfq-iosched.c

@@ -500,13 +500,6 @@ static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
 	}
 }
 
-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
@@ -4080,7 +4073,6 @@ static struct elevator_type iosched_cfq = {
 		.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,

block/deadline-iosched.c

@@ -326,14 +326,6 @@ dispatch_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;
@@ -445,7 +437,6 @@ static struct elevator_type iosched_deadline = {
 		.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,

block/elevator.c

@@ -113,7 +113,7 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 }
 EXPORT_SYMBOL(elv_rq_merge_ok);
 
-static inline int elv_try_merge(struct request *__rq, struct bio *bio)
+int elv_try_merge(struct request *__rq, struct bio *bio)
 {
 	int ret = ELEVATOR_NO_MERGE;
 
@@ -421,6 +421,8 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	struct list_head *entry;
 	int stop_flags;
 
+	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
+
 	if (q->last_merge == rq)
 		q->last_merge = NULL;
 
@@ -617,21 +619,12 @@ void elv_quiesce_end(struct request_queue *q)
 
 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);
@@ -677,25 +670,17 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		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,
+void __elv_add_request(struct request_queue *q, struct request *rq, int where)
-		       int plug)
 {
+	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
+
 	if (rq->cmd_flags & REQ_SOFTBARRIER) {
 		/* barriers are scheduling boundary, update end_sector */
 		if (rq->cmd_type == REQ_TYPE_FS ||
@@ -707,38 +692,20 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where,
 		    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,
+void elv_add_request(struct request_queue *q, struct request *rq, int where)
-		     int plug)
 {
 	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;

block/noop-iosched.c

@@ -39,13 +39,6 @@ static void noop_add_request(struct request_queue *q, struct request *rq)
 	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)
 {
@@ -90,7 +83,6 @@ static struct elevator_type elevator_noop = {
 		.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,

drivers/block/cciss.c

@@ -3170,12 +3170,6 @@ static void do_cciss_request(struct request_queue *q)
 	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)

drivers/block/cpqarray.c

@@ -911,9 +911,6 @@ static void do_ida_request(struct request_queue *q)
 	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)

drivers/block/drbd/drbd_actlog.c

@@ -80,7 +80,7 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
 
 	if ((rw & WRITE) && !test_bit(MD_NO_FUA, &mdev->flags))
 		rw |= REQ_FUA;
-	rw |= REQ_UNPLUG | REQ_SYNC;
+	rw |= REQ_SYNC;
 
 	bio = bio_alloc(GFP_NOIO, 1);
 	bio->bi_bdev = bdev->md_bdev;
@@ -689,8 +689,6 @@ void drbd_al_to_on_disk_bm(struct drbd_conf *mdev)
 		}
 	}
 
-	drbd_blk_run_queue(bdev_get_queue(mdev->ldev->md_bdev));
-
 	/* always (try to) flush bitmap to stable storage */
 	drbd_md_flush(mdev);
 

drivers/block/drbd/drbd_bitmap.c

@@ -840,7 +840,6 @@ static int bm_rw(struct drbd_conf *mdev, int rw) __must_hold(local)
 	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)) {

drivers/block/drbd/drbd_int.h

@@ -377,7 +377,7 @@ union p_header {
 #define DP_HARDBARRIER	      1 /* depricated */
 #define DP_RW_SYNC	      2 /* equals REQ_SYNC    */
 #define DP_MAY_SET_IN_SYNC    4
-#define DP_UNPLUG             8 /* equals REQ_UNPLUG  */
+#define DP_UNPLUG             8 /* not used anymore   */
 #define DP_FUA               16 /* equals REQ_FUA     */
 #define DP_FLUSH             32 /* equals REQ_FLUSH   */
 #define DP_DISCARD           64 /* equals REQ_DISCARD */
@@ -2382,20 +2382,6 @@ static inline int drbd_queue_order_type(struct drbd_conf *mdev)
 	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;

drivers/block/drbd/drbd_main.c

@@ -2477,12 +2477,11 @@ static u32 bio_flags_to_wire(struct drbd_conf *mdev, unsigned long bi_rw)
 {
 	if (mdev->agreed_pro_version >= 95)
 		return  (bi_rw & REQ_SYNC ? DP_RW_SYNC : 0) |
-			(bi_rw & REQ_UNPLUG ? DP_UNPLUG : 0) |
 			(bi_rw & REQ_FUA ? DP_FUA : 0) |
 			(bi_rw & REQ_FLUSH ? DP_FLUSH : 0) |
 			(bi_rw & REQ_DISCARD ? DP_DISCARD : 0);
 	else
-		return bi_rw & (REQ_SYNC | REQ_UNPLUG) ? DP_RW_SYNC : 0;
+		return bi_rw & REQ_SYNC ? DP_RW_SYNC : 0;
 }
 
 /* Used to send write requests
@@ -2719,35 +2718,6 @@ static int drbd_release(struct gendisk *gd, fmode_t mode)
 	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,
@@ -3222,9 +3192,7 @@ struct drbd_conf *drbd_new_device(unsigned int minor)
 	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 */
+	q->queue_lock = &mdev->req_lock;
-		/* plugging on a queue, that actually has no requests! */
-	q->unplug_fn = drbd_unplug_fn;
 
 	mdev->md_io_page = alloc_page(GFP_KERNEL);
 	if (!mdev->md_io_page)

drivers/block/drbd/drbd_receiver.c

@@ -187,15 +187,6 @@ static struct page *drbd_pp_first_pages_or_try_alloc(struct drbd_conf *mdev, int
 	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;
@@ -219,7 +210,6 @@ static void drbd_kick_lo_and_reclaim_net(struct drbd_conf *mdev)
 	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);
@@ -436,8 +426,7 @@ void _drbd_wait_ee_list_empty(struct drbd_conf *mdev, struct list_head *head)
 	while (!list_empty(head)) {
 		prepare_to_wait(&mdev->ee_wait, &wait, TASK_UNINTERRUPTIBLE);
 		spin_unlock_irq(&mdev->req_lock);
-		drbd_kick_lo(mdev);
+		io_schedule();
-		schedule();
 		finish_wait(&mdev->ee_wait, &wait);
 		spin_lock_irq(&mdev->req_lock);
 	}
@@ -1111,8 +1100,6 @@ next_bio:
 	/* > e->sector, unless this is the first bio */
 	bio->bi_sector = sector;
 	bio->bi_bdev = mdev->ldev->backing_bdev;
-	/* we special case some flags in the multi-bio case, see below
-	 * (REQ_UNPLUG) */
 	bio->bi_rw = rw;
 	bio->bi_private = e;
 	bio->bi_end_io = drbd_endio_sec;
@@ -1141,13 +1128,8 @@ next_bio:
 		bios = bios->bi_next;
 		bio->bi_next = NULL;
 
-		/* strip off REQ_UNPLUG unless it is the last bio */
-		if (bios)
-			bio->bi_rw &= ~REQ_UNPLUG;
-
 		drbd_generic_make_request(mdev, fault_type, bio);
 	} while (bios);
-	maybe_kick_lo(mdev);
 	return 0;
 
 fail:
@@ -1167,9 +1149,6 @@ static int receive_Barrier(struct drbd_conf *mdev, enum drbd_packets cmd, unsign
 
 	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);
 
@@ -1636,12 +1615,11 @@ static unsigned long write_flags_to_bio(struct drbd_conf *mdev, u32 dpf)
 {
 	if (mdev->agreed_pro_version >= 95)
 		return  (dpf & DP_RW_SYNC ? REQ_SYNC : 0) |
-			(dpf & DP_UNPLUG ? REQ_UNPLUG : 0) |
 			(dpf & DP_FUA ? REQ_FUA : 0) |
 			(dpf & DP_FLUSH ? REQ_FUA : 0) |
 			(dpf & DP_DISCARD ? REQ_DISCARD : 0);
 	else
-		return dpf & DP_RW_SYNC ? (REQ_SYNC | REQ_UNPLUG) : 0;
+		return dpf & DP_RW_SYNC ? REQ_SYNC : 0;
 }
 
 /* mirrored write */
@@ -3556,9 +3534,6 @@ static int receive_skip(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
 
 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);

drivers/block/drbd/drbd_req.c

@@ -960,10 +960,6 @@ allocate_barrier:
 			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:

drivers/block/drbd/drbd_worker.c

@@ -792,7 +792,6 @@ int drbd_resync_finished(struct drbd_conf *mdev)
 		 * 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);

drivers/block/drbd/drbd_wrappers.h

@@ -45,24 +45,6 @@ static inline void drbd_generic_make_request(struct drbd_conf *mdev,
 		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)

drivers/block/floppy.c

@@ -3838,7 +3838,6 @@ static int __floppy_read_block_0(struct block_device *bdev)
 	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);
 

drivers/block/loop.c

@@ -540,17 +540,6 @@ out:
 	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;
@@ -917,7 +906,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	 */
 	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);
@@ -1019,7 +1007,6 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
 
 	kthread_stop(lo->lo_thread);
 
-	lo->lo_queue->unplug_fn = NULL;
 	lo->lo_backing_file = NULL;
 
 	loop_release_xfer(lo);

drivers/block/pktcdvd.c

@@ -1606,8 +1606,6 @@ static int kcdrwd(void *foobar)
 					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");

drivers/block/umem.c

@@ -241,8 +241,7 @@ static void dump_dmastat(struct cardinfo *card, unsigned int dmastat)
  *
  * 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
+ * Otherwise the Ready page is only activated when it becomes full.
- * when mm_unplug_device is called via the unplug_io_fn.
  *
  * 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.
@@ -333,17 +332,6 @@ static inline void reset_page(struct mm_page *page)
 	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.
@@ -535,7 +523,6 @@ static int mm_make_request(struct request_queue *q, struct bio *bio)
 	*card->biotail = bio;
 	bio->bi_next = NULL;
 	card->biotail = &bio->bi_next;
-	blk_plug_device(q);
 	spin_unlock_irq(&card->lock);
 
 	return 0;
@@ -897,7 +884,6 @@ static int __devinit mm_pci_probe(struct pci_dev *dev,
 	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);
 

drivers/ide/ide-atapi.c

@@ -233,8 +233,7 @@ int ide_queue_sense_rq(ide_drive_t *drive, void *special)
 
 	drive->hwif->rq = NULL;
 
-	elv_add_request(drive->queue, &drive->sense_rq,
+	elv_add_request(drive->queue, &drive->sense_rq, ELEVATOR_INSERT_FRONT);
-			ELEVATOR_INSERT_FRONT, 0);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ide_queue_sense_rq);

drivers/ide/ide-cd.c

@@ -258,17 +258,10 @@ static int ide_cd_breathe(ide_drive_t *drive, struct request *rq)
 	if (time_after(jiffies, info->write_timeout))
 		return 0;
 	else {
-		struct request_queue *q = drive->queue;
-		unsigned long flags;
-
 		/*
-		 * take a breather relying on the unplug timer to kick us again
+		 * take a breather
 		 */
-
+		blk_delay_queue(drive->queue, 1);
-		spin_lock_irqsave(q->queue_lock, flags);
-		blk_plug_device(q);
-		spin_unlock_irqrestore(q->queue_lock, flags);
-
 		return 1;
 	}
 }
@@ -1514,8 +1507,6 @@ static int ide_cdrom_setup(ide_drive_t *drive)
 	blk_queue_dma_alignment(q, 31);
 	blk_queue_update_dma_pad(q, 15);
 
-	q->unplug_delay = max((1 * HZ) / 1000, 1);
-
 	drive->dev_flags |= IDE_DFLAG_MEDIA_CHANGED;
 	drive->atapi_flags = IDE_AFLAG_NO_EJECT | ide_cd_flags(id);
 

drivers/ide/ide-io.c

@@ -549,8 +549,6 @@ plug_device_2:
 
 	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)
@@ -562,8 +560,6 @@ 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);
 }

drivers/ide/ide-park.c

@@ -52,7 +52,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	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;

drivers/md/bitmap.c

@@ -347,7 +347,7 @@ static void write_page(struct bitmap *bitmap, struct page *page, int wait)
 			atomic_inc(&bitmap->pending_writes);
 			set_buffer_locked(bh);
 			set_buffer_mapped(bh);
-			submit_bh(WRITE | REQ_UNPLUG | REQ_SYNC, bh);
+			submit_bh(WRITE | REQ_SYNC, bh);
 			bh = bh->b_this_page;
 		}
 
@@ -1339,8 +1339,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 			prepare_to_wait(&bitmap->overflow_wait, &__wait,
 					TASK_UNINTERRUPTIBLE);
 			spin_unlock_irq(&bitmap->lock);
-			md_unplug(bitmap->mddev);
+			io_schedule();
-			schedule();
 			finish_wait(&bitmap->overflow_wait, &__wait);
 			continue;
 		}

drivers/md/dm-crypt.c

@@ -991,11 +991,6 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone)
 	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;
@@ -1008,10 +1003,8 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	 * one in order to decrypt the whole bio data *afterwards*.
 	 */
 	clone = bio_alloc_bioset(gfp, bio_segments(base_bio), cc->bs);
-	if (!clone) {
+	if (!clone)
-		kcryptd_unplug(cc);
 		return 1;
-	}
 
 	crypt_inc_pending(io);
 

drivers/md/dm-io.c

@@ -352,7 +352,7 @@ static void dispatch_io(int rw, unsigned int num_regions,
 	BUG_ON(num_regions > DM_IO_MAX_REGIONS);
 
 	if (sync)
-		rw |= REQ_SYNC | REQ_UNPLUG;
+		rw |= REQ_SYNC;
 
 	/*
 	 * For multiple regions we need to be careful to rewind

drivers/md/dm-kcopyd.c

@@ -37,13 +37,6 @@ struct dm_kcopyd_client {
 	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;
@@ -315,31 +308,6 @@ static int run_complete_job(struct kcopyd_job *job)
 	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;
@@ -386,16 +354,10 @@ static int run_io_job(struct kcopyd_job *job)
 		.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;
 }
@@ -466,6 +428,7 @@ static void do_work(struct work_struct *work)
 {
 	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.
@@ -473,18 +436,12 @@ static void do_work(struct work_struct *work)
 	 * 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);
+	blk_finish_plug(&plug);
-	unplug(kc, WRITE);
 }
 
 /*
@@ -665,8 +622,6 @@ int dm_kcopyd_client_create(unsigned int nr_pages,
 	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;

drivers/md/dm-raid.c

@@ -394,7 +394,7 @@ static void raid_unplug(struct dm_target_callbacks *cb)
 {
 	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);
 }
 
 /*

drivers/md/dm-raid1.c

@@ -842,8 +842,6 @@ static void do_mirror(struct work_struct *work)
 	do_reads(ms, &reads);
 	do_writes(ms, &writes);
 	do_failures(ms, &failures);
-
-	dm_table_unplug_all(ms->ti->table);
 }
 
 /*-----------------------------------------------------------------

drivers/md/dm-table.c

@@ -1275,29 +1275,6 @@ int dm_table_any_busy_target(struct dm_table *t)
 	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;
@@ -1345,4 +1322,3 @@ EXPORT_SYMBOL(dm_table_get_mode);
 EXPORT_SYMBOL(dm_table_get_md);
 EXPORT_SYMBOL(dm_table_put);
 EXPORT_SYMBOL(dm_table_get);
-EXPORT_SYMBOL(dm_table_unplug_all);

drivers/md/dm.c

@@ -807,8 +807,6 @@ void dm_requeue_unmapped_request(struct request *clone)
 	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);
 
@@ -1613,10 +1611,10 @@ static void dm_request_fn(struct request_queue *q)
 	 * 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;
@@ -1627,7 +1625,7 @@ static void dm_request_fn(struct request_queue *q)
 		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;
@@ -1647,11 +1645,8 @@ requeued:
 	BUG_ON(!irqs_disabled());
 	spin_lock(q->queue_lock);
 
-plug_and_out:
+delay_and_out:
-	if (!elv_queue_empty(q))
+	blk_delay_queue(q, HZ / 10);
-		/* Some requests still remain, retry later */
-		blk_plug_device(q);
-
 out:
 	dm_table_put(map);
 
@@ -1680,20 +1675,6 @@ static int dm_lld_busy(struct request_queue *q)
 	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;
@@ -1817,7 +1798,6 @@ static void dm_init_md_queue(struct mapped_device *md)
 	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);
 }
@@ -2263,8 +2243,6 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible)
 	int r = 0;
 	DECLARE_WAITQUEUE(wait, current);
 
-	dm_unplug_all(md->queue);
-
 	add_wait_queue(&md->wait, &wait);
 
 	while (1) {
@@ -2539,7 +2517,6 @@ int dm_resume(struct mapped_device *md)
 
 	clear_bit(DMF_SUSPENDED, &md->flags);
 
-	dm_table_unplug_all(map);
 	r = 0;
 out:
 	dm_table_put(map);

drivers/md/linear.c

@@ -87,22 +87,6 @@ static int linear_mergeable_bvec(struct request_queue *q,
 	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;
@@ -224,7 +208,6 @@ static int linear_run (mddev_t *mddev)
 	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);

drivers/md/md.c

@@ -780,8 +780,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
 	bio->bi_end_io = super_written;
 
 	atomic_inc(&mddev->pending_writes);
-	submit_bio(REQ_WRITE | REQ_SYNC | REQ_UNPLUG | REQ_FLUSH | REQ_FUA,
+	submit_bio(REQ_WRITE | REQ_SYNC | REQ_FLUSH | REQ_FUA, bio);
-		   bio);
 }
 
 void md_super_wait(mddev_t *mddev)
@@ -809,7 +808,7 @@ int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size,
 	struct completion event;
 	int ret;
 
-	rw |= REQ_SYNC | REQ_UNPLUG;
+	rw |= REQ_SYNC;
 
 	bio->bi_bdev = (metadata_op && rdev->meta_bdev) ?
 		rdev->meta_bdev : rdev->bdev;
@@ -4817,7 +4816,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 		__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' */
@@ -6692,8 +6690,6 @@ EXPORT_SYMBOL_GPL(md_allow_write);
 
 void md_unplug(mddev_t *mddev)
 {
-	if (mddev->queue)
-		blk_unplug(mddev->queue);
 	if (mddev->plug)
 		mddev->plug->unplug_fn(mddev->plug);
 }
@@ -6876,7 +6872,6 @@ void md_do_sync(mddev_t *mddev)
 		     >= 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;
@@ -6952,7 +6947,6 @@ void md_do_sync(mddev_t *mddev)
 		 * 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
@@ -6971,8 +6965,6 @@ void md_do_sync(mddev_t *mddev)
 	 * 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 */

drivers/md/multipath.c

@@ -106,36 +106,6 @@ static void multipath_end_request(struct bio *bio, int error)
 	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;
@@ -517,7 +487,6 @@ static int multipath_run (mddev_t *mddev)
 	 */
 	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);

drivers/md/raid0.c

@@ -25,21 +25,6 @@
 #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;
@@ -272,7 +257,6 @@ static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf)
 		       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;
 

drivers/md/raid1.c

@@ -52,23 +52,16 @@
 #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);
+	return kzalloc(size, gfp_flags);
-	if (!r1_bio && pi->mddev)
-		unplug_slaves(pi->mddev);
-
-	return r1_bio;
 }
 
 static void r1bio_pool_free(void *r1_bio, void *data)
@@ -91,10 +84,8 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	int i, j;
 
 	r1_bio = r1bio_pool_alloc(gfp_flags, pi);
-	if (!r1_bio) {
+	if (!r1_bio)
-		unplug_slaves(pi->mddev);
 		return NULL;
-	}
 
 	/*
 	 * Allocate bios : 1 for reading, n-1 for writing
@@ -520,37 +511,6 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 	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;
@@ -580,23 +540,16 @@ static int raid1_congested(void *data, int bits)
 }
 
 
-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);
-		/* Only take the spinlock to quiet a warning */
-		spin_lock(conf->mddev->queue->queue_lock);
-		blk_remove_plug(conf->mddev->queue);
-		spin_unlock(conf->mddev->queue->queue_lock);
 		spin_unlock_irq(&conf->device_lock);
 		/* flush any pending bitmap writes to
 		 * disk before proceeding w/ I/O */
@@ -608,10 +561,14 @@ static int flush_pending_writes(conf_t *conf)
 			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....
@@ -643,8 +600,7 @@ static void raise_barrier(conf_t *conf)
 
 	/* Wait until no block IO is waiting */
 	wait_event_lock_irq(conf->wait_barrier, !conf->nr_waiting,
-			    conf->resync_lock,
+			    conf->resync_lock, md_kick_device(conf->mddev));
-			    raid1_unplug(conf->mddev->queue));
 
 	/* block any new IO from starting */
 	conf->barrier++;
@@ -652,8 +608,7 @@ static void raise_barrier(conf_t *conf)
 	/* 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,
+			    conf->resync_lock, md_kick_device(conf->mddev));
-			    raid1_unplug(conf->mddev->queue));
 
 	spin_unlock_irq(&conf->resync_lock);
 }
@@ -675,7 +630,7 @@ static void wait_barrier(conf_t *conf)
 		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++;
@@ -712,7 +667,7 @@ static void freeze_array(conf_t *conf)
 			    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)
@@ -962,7 +917,6 @@ static int make_request(mddev_t *mddev, struct bio * bio)
 		atomic_inc(&r1_bio->remaining);
 		spin_lock_irqsave(&conf->device_lock, flags);
 		bio_list_add(&conf->pending_bio_list, mbio);
-		blk_plug_device_unlocked(mddev->queue);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
 	r1_bio_write_done(r1_bio, bio->bi_vcnt, behind_pages, behind_pages != NULL);
@@ -971,7 +925,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
 	/* 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;
@@ -1561,7 +1515,6 @@ static void raid1d(mddev_t *mddev)
 	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);
@@ -1569,7 +1522,7 @@ static void raid1d(mddev_t *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)) {
@@ -1583,10 +1536,9 @@ static void raid1d(mddev_t *mddev)
 
 		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
@@ -1636,14 +1588,11 @@ static void raid1d(mddev_t *mddev)
 				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);
 }
 
 
@@ -2066,7 +2015,6 @@ static int run(mddev_t *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);

drivers/md/raid10.c

@@ -57,23 +57,16 @@
  */
 #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);
+	return kzalloc(size, gfp_flags);
-	if (!r10_bio && conf->mddev)
-		unplug_slaves(conf->mddev);
-
-	return r10_bio;
 }
 
 static void r10bio_pool_free(void *r10_bio, void *data)
@@ -106,10 +99,8 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
 	int nalloc;
 
 	r10_bio = r10bio_pool_alloc(gfp_flags, conf);
-	if (!r10_bio) {
+	if (!r10_bio)
-		unplug_slaves(conf->mddev);
 		return NULL;
-	}
 
 	if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery))
 		nalloc = conf->copies; /* resync */
@@ -597,37 +588,6 @@ rb_out:
 	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;
@@ -649,23 +609,16 @@ static int raid10_congested(void *data, int bits)
 	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);
-		/* Spinlock only taken to quiet a warning */
-		spin_lock(conf->mddev->queue->queue_lock);
-		blk_remove_plug(conf->mddev->queue);
-		spin_unlock(conf->mddev->queue->queue_lock);
 		spin_unlock_irq(&conf->device_lock);
 		/* flush any pending bitmap writes to disk
 		 * before proceeding w/ I/O */
@@ -677,11 +630,16 @@ static int flush_pending_writes(conf_t *conf)
 			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.
@@ -711,8 +669,7 @@ static void raise_barrier(conf_t *conf, int force)
 
 	/* Wait until no block IO is waiting (unless 'force') */
 	wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
-			    conf->resync_lock,
+			    conf->resync_lock, md_kick_device(conf->mddev));
-			    raid10_unplug(conf->mddev->queue));
 
 	/* block any new IO from starting */
 	conf->barrier++;
@@ -720,8 +677,7 @@ static void raise_barrier(conf_t *conf, int force)
 	/* 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,
+			    conf->resync_lock, md_kick_device(conf->mddev));
-			    raid10_unplug(conf->mddev->queue));
 
 	spin_unlock_irq(&conf->resync_lock);
 }
@@ -742,7 +698,7 @@ static void wait_barrier(conf_t *conf)
 		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++;
@@ -779,7 +735,7 @@ static void freeze_array(conf_t *conf)
 			    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);
 }
 
@@ -974,7 +930,6 @@ static int make_request(mddev_t *mddev, struct bio * bio)
 		atomic_inc(&r10_bio->remaining);
 		spin_lock_irqsave(&conf->device_lock, flags);
 		bio_list_add(&conf->pending_bio_list, mbio);
-		blk_plug_device_unlocked(mddev->queue);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
 
@@ -991,7 +946,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
 	/* 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;
@@ -1684,7 +1639,6 @@ static void raid10d(mddev_t *mddev)
 	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);
@@ -1692,7 +1646,7 @@ static void raid10d(mddev_t *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)) {
@@ -1706,13 +1660,11 @@ static void raid10d(mddev_t *mddev)
 
 		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.
@@ -1759,14 +1711,11 @@ static void raid10d(mddev_t *mddev)
 				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);
 }
 
 
@@ -2377,7 +2326,6 @@ static int run(mddev_t *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;
 

drivers/md/raid5.c

@@ -433,8 +433,6 @@ static int has_failed(raid5_conf_t *conf)
 	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)
@@ -463,8 +461,7 @@ get_active_stripe(raid5_conf_t *conf, sector_t sector,
 						     < (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);
@@ -1473,8 +1470,7 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
 		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);
@@ -3645,58 +3641,19 @@ static void activate_bit_delay(raid5_conf_t *conf)
 	}
 }
 
-static void unplug_slaves(mddev_t *mddev)
+void md_raid5_kick_device(raid5_conf_t *conf)
 {
-	raid5_conf_t *conf = mddev->private;
+	blk_flush_plug(current);
-	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);
-	}
 	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)
+	md_raid5_kick_device(conf);
-{
-	mddev_t *mddev = q->queuedata;
-	md_raid5_unplug_device(mddev->private);
 }
 
 int md_raid5_congested(mddev_t *mddev, int bits)
@@ -4100,7 +4057,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 				 * 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;
@@ -4365,7 +4322,6 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 
 	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);
@@ -4569,7 +4525,6 @@ static void raid5d(mddev_t *mddev)
 	spin_unlock_irq(&conf->device_lock);
 
 	async_tx_issue_pending_all();
-	unplug_slaves(mddev);
 
 	pr_debug("--- raid5d inactive\n");
 }
@@ -5204,7 +5159,7 @@ static int run(mddev_t *mddev)
 
 		mddev->queue->backing_dev_info.congested_data = mddev;
 		mddev->queue->backing_dev_info.congested_fn = raid5_congested;
-		mddev->queue->unplug_fn = raid5_unplug_queue;
+		mddev->queue->queue_lock = &conf->device_lock;
 
 		chunk_size = mddev->chunk_sectors << 9;
 		blk_queue_io_min(mddev->queue, chunk_size);

drivers/md/raid5.h

@@ -503,6 +503,6 @@ static inline int algorithm_is_DDF(int layout)
 }
 
 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

drivers/message/i2o/i2o_block.c

@@ -897,11 +897,7 @@ static void i2o_block_request_fn(struct request_queue *q)
 {
 	struct request *req;
 
-	while (!blk_queue_plugged(q)) {
+	while ((req = blk_peek_request(q)) != NULL) {
-		req = blk_peek_request(q);
-		if (!req)
-			break;
-
 		if (req->cmd_type == REQ_TYPE_FS) {
 			struct i2o_block_delayed_request *dreq;
 			struct i2o_block_request *ireq = req->special;

drivers/mmc/card/queue.c

@@ -55,7 +55,6 @@ static int mmc_queue_thread(void *d)
 
 		spin_lock_irq(q->queue_lock);
 		set_current_state(TASK_INTERRUPTIBLE);
-		if (!blk_queue_plugged(q))
 		req = blk_fetch_request(q);
 		mq->req = req;
 		spin_unlock_irq(q->queue_lock);

drivers/s390/block/dasd.c

@@ -1917,7 +1917,7 @@ static void __dasd_process_request_queue(struct dasd_block *block)
 		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,

drivers/s390/char/tape_block.c

@@ -161,7 +161,6 @@ tapeblock_requeue(struct work_struct *work) {
 
 	spin_lock_irq(&device->blk_data.request_queue_lock);
 	while (
-		!blk_queue_plugged(queue) &&
 		blk_peek_request(queue) &&
 		nr_queued < TAPEBLOCK_MIN_REQUEUE
 	) {

drivers/scsi/scsi_lib.c

@@ -67,6 +67,13 @@ static struct scsi_host_sg_pool scsi_sg_pools[] = {
 
 struct kmem_cache *scsi_sdb_cache;
 
+/*
+ * When to reinvoke queueing after a resource shortage. It's 3 msecs to
+ * not change behaviour from the previous unplug mechanism, experimentation
+ * may prove this needs changing.
+ */
+#define SCSI_QUEUE_DELAY	3
+
 static void scsi_run_queue(struct request_queue *q);
 
 /*
@@ -149,13 +156,6 @@ static int __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, int unbusy)
 	/*
 	 * Requeue this command.  It will go before all other commands
 	 * that are already in the queue.
-	 *
-	 * NOTE: there is magic here about the way the queue is plugged if
-	 * we have no outstanding commands.
-	 * 
-	 * Although we *don't* plug the queue, we call the request
-	 * function.  The SCSI request function detects the blocked condition
-	 * and plugs the queue appropriately.
 	 */
 	spin_lock_irqsave(q->queue_lock, flags);
 	blk_requeue_request(q, cmd->request);
@@ -1194,11 +1194,11 @@ int scsi_prep_return(struct request_queue *q, struct request *req, int ret)
 	case BLKPREP_DEFER:
 		/*
 		 * If we defer, the blk_peek_request() returns NULL, but the
-		 * queue must be restarted, so we plug here if no returning
+		 * queue must be restarted, so we schedule a callback to happen
-		 * command will automatically do that.
+		 * shortly.
 		 */
 		if (sdev->device_busy == 0)
-			blk_plug_device(q);
+			blk_delay_queue(q, SCSI_QUEUE_DELAY);
 		break;
 	default:
 		req->cmd_flags |= REQ_DONTPREP;
@@ -1237,7 +1237,7 @@ static inline int scsi_dev_queue_ready(struct request_queue *q,
 				   sdev_printk(KERN_INFO, sdev,
 				   "unblocking device at zero depth\n"));
 		} else {
-			blk_plug_device(q);
+			blk_delay_queue(q, SCSI_QUEUE_DELAY);
 			return 0;
 		}
 	}
@@ -1467,7 +1467,7 @@ static void scsi_request_fn(struct request_queue *q)
 	 * the host is no longer able to accept any more requests.
 	 */
 	shost = sdev->host;
-	while (!blk_queue_plugged(q)) {
+	for (;;) {
 		int rtn;
 		/*
 		 * get next queueable request.  We do this early to make sure
@@ -1546,15 +1546,8 @@ static void scsi_request_fn(struct request_queue *q)
 		 */
 		rtn = scsi_dispatch_cmd(cmd);
 		spin_lock_irq(q->queue_lock);
-		if(rtn) {
+		if (rtn)
-			/* we're refusing the command; because of
+			goto out_delay;
-			 * the way locks get dropped, we need to 
-			 * check here if plugging is required */
-			if(sdev->device_busy == 0)
-				blk_plug_device(q);
-
-			break;
-		}
 	}
 
 	goto out;
@@ -1573,8 +1566,9 @@ static void scsi_request_fn(struct request_queue *q)
 	spin_lock_irq(q->queue_lock);
 	blk_requeue_request(q, req);
 	sdev->device_busy--;
+out_delay:
 	if (sdev->device_busy == 0)
-		blk_plug_device(q);
+		blk_delay_queue(q, SCSI_QUEUE_DELAY);
 out:
 	/* must be careful here...if we trigger the ->remove() function
 	 * we cannot be holding the q lock */

drivers/scsi/scsi_transport_fc.c

@@ -3913,7 +3913,7 @@ fc_bsg_request_handler(struct request_queue *q, struct Scsi_Host *shost,
 	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;

drivers/scsi/scsi_transport_sas.c

@@ -173,11 +173,7 @@ static void sas_smp_request(struct request_queue *q, struct Scsi_Host *shost,
 	int ret;
 	int (*handler)(struct Scsi_Host *, struct sas_rphy *, struct request *);
 
-	while (!blk_queue_plugged(q)) {
+	while ((req = blk_fetch_request(q)) != NULL) {
-		req = blk_fetch_request(q);
-		if (!req)
-			break;
-
 		spin_unlock_irq(q->queue_lock);
 
 		handler = to_sas_internal(shost->transportt)->f->smp_handler;

drivers/target/target_core_iblock.c

@@ -392,9 +392,8 @@ static int iblock_do_task(struct se_task *task)
 {
 	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) {
@@ -412,6 +411,7 @@ static int iblock_do_task(struct se_task *task)
 		rw = READ;
 	}
 
+	blk_start_plug(&plug);
 	while (bio) {
 		nbio = bio->bi_next;
 		bio->bi_next = NULL;
@@ -421,9 +421,8 @@ static int iblock_do_task(struct se_task *task)
 		submit_bio(rw, bio);
 		bio = nbio;
 	}
+	blk_finish_plug(&plug);
 
-	if (q->unplug_fn)
-		q->unplug_fn(q);
 	return PYX_TRANSPORT_SENT_TO_TRANSPORT;
 }
 

fs/adfs/inode.c

@@ -73,7 +73,6 @@ static sector_t _adfs_bmap(struct address_space *mapping, sector_t block)
 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

fs/affs/file.c

@@ -429,7 +429,6 @@ static sector_t _affs_bmap(struct address_space *mapping, sector_t block)
 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
@@ -786,7 +785,6 @@ out:
 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
 };

fs/aio.c

@@ -34,8 +34,6 @@
 #include <linux/security.h>
 #include <linux/eventfd.h>
 #include <linux/blkdev.h>
-#include <linux/mempool.h>
-#include <linux/hash.h>
 #include <linux/compat.h>
 
 #include <asm/kmap_types.h>
@@ -65,14 +63,6 @@ static DECLARE_WORK(fput_work, aio_fput_routine);
 static DEFINE_SPINLOCK(fput_lock);
 static LIST_HEAD(fput_head);
 
-#define AIO_BATCH_HASH_BITS	3 /* allocated on-stack, so don't go crazy */
-#define AIO_BATCH_HASH_SIZE	(1 << AIO_BATCH_HASH_BITS)
-struct aio_batch_entry {
-	struct hlist_node list;
-	struct address_space *mapping;
-};
-mempool_t *abe_pool;
-
 static void aio_kick_handler(struct work_struct *);
 static void aio_queue_work(struct kioctx *);
 
@@ -86,8 +76,7 @@ static int __init aio_setup(void)
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
 	aio_wq = create_workqueue("aio");
-	abe_pool = mempool_create_kmalloc_pool(1, sizeof(struct aio_batch_entry));
+	BUG_ON(!aio_wq);
-	BUG_ON(!aio_wq || !abe_pool);
 
 	pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page));
 
@@ -1525,57 +1514,8 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
 	return 0;
 }
 
-static void aio_batch_add(struct address_space *mapping,
-			  struct hlist_head *batch_hash)
-{
-	struct aio_batch_entry *abe;
-	struct hlist_node *pos;
-	unsigned bucket;
-
-	bucket = hash_ptr(mapping, AIO_BATCH_HASH_BITS);
-	hlist_for_each_entry(abe, pos, &batch_hash[bucket], list) {
-		if (abe->mapping == mapping)
-			return;
-	}
-
-	abe = mempool_alloc(abe_pool, GFP_KERNEL);
-
-	/*
-	 * we should be using igrab here, but
-	 * we don't want to hammer on the global
-	 * inode spinlock just to take an extra
-	 * reference on a file that we must already
-	 * have a reference to.
-	 *
-	 * When we're called, we always have a reference
-	 * on the file, so we must always have a reference
-	 * on the inode, so ihold() is safe here.
-	 */
-	ihold(mapping->host);
-	abe->mapping = mapping;
-	hlist_add_head(&abe->list, &batch_hash[bucket]);
-	return;
-}
-
-static void aio_batch_free(struct hlist_head *batch_hash)
-{
-	struct aio_batch_entry *abe;
-	struct hlist_node *pos, *n;
-	int i;
-
-	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 int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
-			 struct iocb *iocb, struct hlist_head *batch_hash,
+			 struct iocb *iocb, bool compat)
-			 bool compat)
 {
 	struct kiocb *req;
 	struct file *file;
@@ -1666,11 +1606,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			;
 	}
 	spin_unlock_irq(&ctx->ctx_lock);
-	if (req->ki_opcode == IOCB_CMD_PREAD ||
-	    req->ki_opcode == IOCB_CMD_PREADV ||
-	    req->ki_opcode == IOCB_CMD_PWRITE ||
-	    req->ki_opcode == IOCB_CMD_PWRITEV)
-		aio_batch_add(file->f_mapping, batch_hash);
 
 	aio_put_req(req);	/* drop extra ref to req */
 	return 0;
@@ -1687,7 +1622,7 @@ long do_io_submit(aio_context_t ctx_id, long nr,
 	struct kioctx *ctx;
 	long ret = 0;
 	int i;
-	struct hlist_head batch_hash[AIO_BATCH_HASH_SIZE] = { { 0, }, };
+	struct blk_plug plug;
 
 	if (unlikely(nr < 0))
 		return -EINVAL;
@@ -1704,6 +1639,8 @@ long do_io_submit(aio_context_t ctx_id, long nr,
 		return -EINVAL;
 	}
 
+	blk_start_plug(&plug);
+
 	/*
 	 * AKPM: should this return a partial result if some of the IOs were
 	 * successfully submitted?
@@ -1722,11 +1659,11 @@ long do_io_submit(aio_context_t ctx_id, long nr,
 			break;
 		}
 
-		ret = io_submit_one(ctx, user_iocb, &tmp, batch_hash, compat);
+		ret = io_submit_one(ctx, user_iocb, &tmp, compat);
 		if (ret)
 			break;
 	}
-	aio_batch_free(batch_hash);
+	blk_finish_plug(&plug);
 
 	put_ioctx(ctx);
 	return i ? i : ret;

fs/befs/linuxvfs.c

@@ -75,7 +75,6 @@ static const struct inode_operations befs_dir_inode_operations = {
 
 static const struct address_space_operations befs_aops = {
 	.readpage	= befs_readpage,
-	.sync_page	= block_sync_page,
 	.bmap		= befs_bmap,
 };
 

fs/bfs/file.c

@@ -186,7 +186,6 @@ static sector_t bfs_bmap(struct address_space *mapping, sector_t block)
 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,

fs/block_dev.c

@@ -1529,7 +1529,6 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
 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,

fs/btrfs/disk-io.c

@@ -847,7 +847,6 @@ static const struct address_space_operations btree_aops = {
 	.writepages	= btree_writepages,
 	.releasepage	= btree_releasepage,
 	.invalidatepage = btree_invalidatepage,
-	.sync_page	= block_sync_page,
 #ifdef CONFIG_MIGRATION
 	.migratepage	= btree_migratepage,
 #endif
@@ -1330,82 +1329,6 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 	return ret;
 }
 
-/*
- * 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.
@@ -1420,8 +1343,6 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 		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;

fs/btrfs/extent_io.c

@@ -2188,7 +2188,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	unsigned long nr_written = 0;
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
-		write_flags = WRITE_SYNC_PLUG;
+		write_flags = WRITE_SYNC;
 	else
 		write_flags = WRITE;
 

fs/btrfs/inode.c

@@ -7340,7 +7340,6 @@ static const struct address_space_operations btrfs_aops = {
 	.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,

fs/btrfs/volumes.c

@@ -162,7 +162,6 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
 	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;
@@ -173,11 +172,6 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
 	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);
 
@@ -223,15 +217,6 @@ loop_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();
@@ -259,19 +244,11 @@ loop_lock:
 
 		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 (need_resched())
-			if (num_sync_run) {
-				blk_run_backing_dev(bdi, NULL);
-				num_sync_run = 0;
-			}
 			cond_resched();
-		}
 
 		/*
 		 * we made progress, there is more work to do and the bdi
@@ -304,13 +281,8 @@ loop_lock:
 				 * against it before looping
 				 */
 				last_waited = ioc->last_waited;
-				if (need_resched()) {
+				if (need_resched())
-					if (num_sync_run) {
-						blk_run_backing_dev(bdi, NULL);
-						num_sync_run = 0;
-					}
 					cond_resched();
-				}
 				continue;
 			}
 			spin_lock(&device->io_lock);
@@ -323,22 +295,6 @@ loop_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;
@@ -2955,7 +2911,7 @@ static int find_live_mirror(struct map_lookup *map, int first, int num,
 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;
@@ -2987,11 +2943,6 @@ again:
 	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,
@@ -3047,13 +2998,13 @@ again:
 		*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;
@@ -3075,7 +3026,7 @@ again:
 		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;
@@ -3095,22 +3046,10 @@ again:
 	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;
-		}
 		stripe_index++;
 	}
 	if (multi_ret) {
@@ -3128,7 +3067,7 @@ int btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
 		      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,
@@ -3196,14 +3135,6 @@ 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;

fs/buffer.c

@@ -54,23 +54,15 @@ init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *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);
@@ -90,7 +82,7 @@ EXPORT_SYMBOL(unlock_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);
 
@@ -749,7 +741,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 {
 	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);
@@ -775,7 +767,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 				 * still in flight on potentially older
 				 * contents.
 				 */
-				write_dirty_buffer(bh, WRITE_SYNC_PLUG);
+				write_dirty_buffer(bh, WRITE_SYNC);
 
 				/*
 				 * Kick off IO for the previous mapping. Note
@@ -783,10 +775,6 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 				 * 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);
 			}
@@ -1614,14 +1602,8 @@ EXPORT_SYMBOL(unmap_underlying_metadata);
  * prevents this contention from occurring.
  *
  * If block_write_full_page() is called with wbc->sync_mode ==
- * WB_SYNC_ALL, the writes are posted using WRITE_SYNC_PLUG; this
+ * WB_SYNC_ALL, the writes are posted using WRITE_SYNC; this
- * causes the writes to be flagged as synchronous writes, but the
+ * causes the writes to be flagged as synchronous writes.
- * block device queue will NOT be unplugged, since usually many pages
- * will be pushed to the out before the higher-level caller actually
- * waits for the writes to be completed.  The various wait functions,
- * such as wait_on_writeback_range() will ultimately call sync_page()
- * which will ultimately call blk_run_backing_dev(), which will end up
- * unplugging the device queue.
  */
 static int __block_write_full_page(struct inode *inode, struct page *page,
 			get_block_t *get_block, struct writeback_control *wbc,
@@ -1634,7 +1616,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	const unsigned blocksize = 1 << inode->i_blkbits;
 	int nr_underway = 0;
 	int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
-			WRITE_SYNC_PLUG : WRITE);
+			WRITE_SYNC : WRITE);
 
 	BUG_ON(!PageLocked(page));
 
@@ -3138,17 +3120,6 @@ out:
 }
 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.

fs/cifs/file.c

@@ -1569,34 +1569,6 @@ int cifs_fsync(struct file *file, int datasync)
 	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.
@@ -2510,7 +2482,6 @@ const struct address_space_operations cifs_addr_ops = {
 	.set_page_dirty = __set_page_dirty_nobuffers,
 	.releasepage = cifs_release_page,
 	.invalidatepage = cifs_invalidate_page,
-	/* .sync_page = cifs_sync_page, */
 	/* .direct_IO = */
 };
 
@@ -2528,6 +2499,5 @@ const struct address_space_operations cifs_addr_ops_smallbuf = {
 	.set_page_dirty = __set_page_dirty_nobuffers,
 	.releasepage = cifs_release_page,
 	.invalidatepage = cifs_invalidate_page,
-	/* .sync_page = cifs_sync_page, */
 	/* .direct_IO = */
 };

fs/direct-io.c

@@ -1110,11 +1110,8 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
 	    ((rw & READ) || (dio->result == dio->size)))
 		ret = -EIOCBQUEUED;
 
-	if (ret != -EIOCBQUEUED) {
+	if (ret != -EIOCBQUEUED)
-		/* All IO is now issued, send it on its way */
-		blk_run_address_space(inode->i_mapping);
 		dio_await_completion(dio);
-	}
 
 	/*
 	 * Sync will always be dropping the final ref and completing the
@@ -1176,7 +1173,7 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	struct dio *dio;
 
 	if (rw & WRITE)
-		rw = WRITE_ODIRECT_PLUG;
+		rw = WRITE_ODIRECT;
 
 	if (bdev)
 		bdev_blkbits = blksize_bits(bdev_logical_block_size(bdev));

fs/efs/inode.c

@@ -23,7 +23,6 @@ static sector_t _efs_bmap(struct address_space *mapping, sector_t block)
 }
 static const struct address_space_operations efs_aops = {
 	.readpage = efs_readpage,
-	.sync_page = block_sync_page,
 	.bmap = _efs_bmap
 };
 

fs/exofs/inode.c

@@ -795,7 +795,6 @@ const struct address_space_operations exofs_aops = {
 	.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,

fs/ext2/inode.c

@@ -860,7 +860,6 @@ const struct address_space_operations ext2_aops = {
 	.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,
@@ -880,7 +879,6 @@ const struct address_space_operations ext2_nobh_aops = {
 	.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,

fs/ext3/inode.c

@@ -1894,7 +1894,6 @@ static const struct address_space_operations ext3_ordered_aops = {
 	.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,
@@ -1910,7 +1909,6 @@ static const struct address_space_operations ext3_writeback_aops = {
 	.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,
@@ -1926,7 +1924,6 @@ static const struct address_space_operations ext3_journalled_aops = {
 	.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,

fs/ext4/inode.c

@@ -3903,7 +3903,6 @@ static const struct address_space_operations ext4_ordered_aops = {
 	.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,
@@ -3919,7 +3918,6 @@ static const struct address_space_operations ext4_writeback_aops = {
 	.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,
@@ -3935,7 +3933,6 @@ static const struct address_space_operations ext4_journalled_aops = {
 	.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,
@@ -3951,7 +3948,6 @@ static const struct address_space_operations ext4_da_aops = {
 	.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,

fs/ext4/page-io.c

@@ -310,8 +310,7 @@ static int io_submit_init(struct ext4_io_submit *io,
 	io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
 
 	io->io_bio = bio;
-	io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?
+	io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
-			WRITE_SYNC_PLUG : WRITE);
 	io->io_next_block = bh->b_blocknr;
 	return 0;
 }

fs/fat/inode.c

@@ -236,7 +236,6 @@ static const struct address_space_operations fat_aops = {
 	.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,

fs/freevxfs/vxfs_subr.c

@@ -44,7 +44,6 @@ static sector_t		vxfs_bmap(struct address_space *, sector_t);
 const struct address_space_operations vxfs_aops = {
 	.readpage =		vxfs_readpage,
 	.bmap =			vxfs_bmap,
-	.sync_page =		block_sync_page,
 };
 
 inline void

fs/fuse/inode.c

@@ -868,7 +868,6 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 
 	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;
 

fs/gfs2/aops.c

@@ -1116,7 +1116,6 @@ static const struct address_space_operations gfs2_writeback_aops = {
 	.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,
@@ -1132,7 +1131,6 @@ static const struct address_space_operations gfs2_ordered_aops = {
 	.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,
@@ -1150,7 +1148,6 @@ static const struct address_space_operations gfs2_jdata_aops = {
 	.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,

fs/gfs2/log.c

@@ -121,7 +121,7 @@ __acquires(&sdp->sd_log_lock)
 			lock_buffer(bh);
 			if (test_clear_buffer_dirty(bh)) {
 				bh->b_end_io = end_buffer_write_sync;
-				submit_bh(WRITE_SYNC_PLUG, bh);
+				submit_bh(WRITE_SYNC, bh);
 			} else {
 				unlock_buffer(bh);
 				brelse(bh);
@@ -647,7 +647,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 		lock_buffer(bh);
 		if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) {
 			bh->b_end_io = end_buffer_write_sync;
-			submit_bh(WRITE_SYNC_PLUG, bh);
+			submit_bh(WRITE_SYNC, bh);
 		} else {
 			unlock_buffer(bh);
 			brelse(bh);

fs/gfs2/lops.c

@@ -200,7 +200,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 		}
 
 		gfs2_log_unlock(sdp);
-		submit_bh(WRITE_SYNC_PLUG, bh);
+		submit_bh(WRITE_SYNC, bh);
 		gfs2_log_lock(sdp);
 
 		n = 0;
@@ -210,7 +210,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 			gfs2_log_unlock(sdp);
 			lock_buffer(bd2->bd_bh);
 			bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
-			submit_bh(WRITE_SYNC_PLUG, bh);
+			submit_bh(WRITE_SYNC, bh);
 			gfs2_log_lock(sdp);
 			if (++n >= num)
 				break;
@@ -352,7 +352,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 		sdp->sd_log_num_revoke--;
 
 		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
-			submit_bh(WRITE_SYNC_PLUG, bh);
+			submit_bh(WRITE_SYNC, bh);
 
 			bh = gfs2_log_get_buf(sdp);
 			mh = (struct gfs2_meta_header *)bh->b_data;
@@ -369,7 +369,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 	}
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
 
-	submit_bh(WRITE_SYNC_PLUG, bh);
+	submit_bh(WRITE_SYNC, bh);
 }
 
 static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
@@ -571,7 +571,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
 	ptr = bh_log_ptr(bh);
 	
 	get_bh(bh);
-	submit_bh(WRITE_SYNC_PLUG, bh);
+	submit_bh(WRITE_SYNC, bh);
 	gfs2_log_lock(sdp);
 	while(!list_empty(list)) {
 		bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list);
@@ -597,7 +597,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
 		} else {
 			bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh);
 		}
-		submit_bh(WRITE_SYNC_PLUG, bh1);
+		submit_bh(WRITE_SYNC, bh1);
 		gfs2_log_lock(sdp);
 		ptr += 2;
 	}

fs/gfs2/meta_io.c

@@ -37,7 +37,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb
 	struct buffer_head *bh, *head;
 	int nr_underway = 0;
 	int write_op = REQ_META |
-		(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC_PLUG : WRITE);
+		(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(!page_has_buffers(page));
@@ -94,7 +94,6 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb
 const struct address_space_operations gfs2_meta_aops = {
 	.writepage = gfs2_aspace_writepage,
 	.releasepage = gfs2_releasepage,
-	.sync_page = block_sync_page,
 };
 
 /**

fs/hfs/inode.c

@@ -150,7 +150,6 @@ static int hfs_writepages(struct address_space *mapping,
 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,
@@ -160,7 +159,6 @@ const struct address_space_operations hfs_btree_aops = {
 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,

fs/hfsplus/inode.c

@@ -146,7 +146,6 @@ static int hfsplus_writepages(struct address_space *mapping,
 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,
@@ -156,7 +155,6 @@ const struct address_space_operations hfsplus_btree_aops = {
 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,

fs/hpfs/file.c

@@ -120,7 +120,6 @@ static sector_t _hpfs_bmap(struct address_space *mapping, sector_t block)
 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

fs/isofs/inode.c

@@ -1158,7 +1158,6 @@ static sector_t _isofs_bmap(struct address_space *mapping, sector_t block)
 
 static const struct address_space_operations isofs_aops = {
 	.readpage = isofs_readpage,
-	.sync_page = block_sync_page,
 	.bmap = _isofs_bmap
 };
 

fs/jbd/commit.c

@@ -333,7 +333,7 @@ void journal_commit_transaction(journal_t *journal)
 	 * instead we rely on sync_buffer() doing the unplug for us.
 	 */
 	if (commit_transaction->t_synchronous_commit)
-		write_op = WRITE_SYNC_PLUG;
+		write_op = WRITE_SYNC;
 	spin_lock(&commit_transaction->t_handle_lock);
 	while (commit_transaction->t_updates) {
 		DEFINE_WAIT(wait);

fs/jbd2/commit.c

@@ -137,9 +137,9 @@ static int journal_submit_commit_record(journal_t *journal,
 	if (journal->j_flags & JBD2_BARRIER &&
 	    !JBD2_HAS_INCOMPAT_FEATURE(journal,
 				       JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT))
-		ret = submit_bh(WRITE_SYNC_PLUG | WRITE_FLUSH_FUA, bh);
+		ret = submit_bh(WRITE_SYNC | WRITE_FLUSH_FUA, bh);
 	else
-		ret = submit_bh(WRITE_SYNC_PLUG, bh);
+		ret = submit_bh(WRITE_SYNC, bh);
 
 	*cbh = bh;
 	return ret;
@@ -369,7 +369,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	 * instead we rely on sync_buffer() doing the unplug for us.
 	 */
 	if (commit_transaction->t_synchronous_commit)
-		write_op = WRITE_SYNC_PLUG;
+		write_op = WRITE_SYNC;
 	trace_jbd2_commit_locking(journal, commit_transaction);
 	stats.run.rs_wait = commit_transaction->t_max_wait;
 	stats.run.rs_locked = jiffies;

fs/jfs/inode.c

@@ -352,7 +352,6 @@ const struct address_space_operations jfs_aops = {
 	.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,

fs/jfs/jfs_metapage.c

@@ -583,7 +583,6 @@ static void metapage_invalidatepage(struct page *page, unsigned long offset)
 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,

fs/logfs/dev_bdev.c

@@ -39,7 +39,6 @@ static int sync_request(struct page *page, struct block_device *bdev, int rw)
 	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;
 }
@@ -168,7 +167,6 @@ static void bdev_writeseg(struct super_block *sb, u64 ofs, size_t len)
 	}
 	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));
 }
 
 

fs/minix/inode.c

@@ -399,7 +399,6 @@ static sector_t minix_bmap(struct address_space *mapping, sector_t block)
 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

fs/mpage.c

@@ -364,6 +364,9 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	sector_t last_block_in_bio = 0;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
+	struct blk_plug plug;
+
+	blk_start_plug(&plug);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
@@ -385,6 +388,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	BUG_ON(!list_empty(pages));
 	if (bio)
 		mpage_bio_submit(READ, bio);
+	blk_finish_plug(&plug);
 	return 0;
 }
 EXPORT_SYMBOL(mpage_readpages);
@@ -666,8 +670,11 @@ int
 mpage_writepages(struct address_space *mapping,
 		struct writeback_control *wbc, get_block_t get_block)
 {
+	struct blk_plug plug;
 	int ret;
 
+	blk_start_plug(&plug);
+
 	if (!get_block)
 		ret = generic_writepages(mapping, wbc);
 	else {
@@ -682,6 +689,7 @@ mpage_writepages(struct address_space *mapping,
 		if (mpd.bio)
 			mpage_bio_submit(WRITE, mpd.bio);
 	}
+	blk_finish_plug(&plug);
 	return ret;
 }
 EXPORT_SYMBOL(mpage_writepages);

fs/nilfs2/btnode.c

@@ -34,15 +34,10 @@
 #include "page.h"
 #include "btnode.h"
 
-
-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)

fs/nilfs2/gcinode.c

@@ -49,7 +49,6 @@
 #include "ifile.h"
 
 static const struct address_space_operations def_gcinode_aops = {
-	.sync_page		= block_sync_page,
 };
 
 /*

fs/nilfs2/inode.c

@@ -262,7 +262,6 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 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,

fs/nilfs2/mdt.c

@@ -399,7 +399,6 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
 
 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;
@@ -438,10 +437,6 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned entry_size,
 	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
@@ -455,9 +450,9 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode,
 
 	INIT_LIST_HEAD(&shadow->frozen_buffers);
 	address_space_init_once(&shadow->frozen_data);
-	nilfs_mapping_init(&shadow->frozen_data, bdi, &shadow_map_aops);
+	nilfs_mapping_init(&shadow->frozen_data, bdi);
 	address_space_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;
 }

fs/nilfs2/page.c

@@ -493,15 +493,14 @@ unsigned nilfs_page_count_clean_buffers(struct page *page,
 }
 
 void nilfs_mapping_init(struct address_space *mapping,
-			struct backing_dev_info *bdi,
+			struct backing_dev_info *bdi)
-			const struct address_space_operations *aops)
 {
 	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;
 }
 
 /*

fs/nilfs2/page.h

@@ -62,8 +62,7 @@ int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
 void nilfs_copy_back_pages(struct address_space *, struct address_space *);
 void nilfs_clear_dirty_pages(struct address_space *);
 void nilfs_mapping_init(struct address_space *mapping,
-			struct backing_dev_info *bdi,
+			struct backing_dev_info *bdi);
-			const struct address_space_operations *aops);
 unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);
 unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
 					    sector_t start_blk,

fs/nilfs2/segbuf.c

@@ -509,7 +509,7 @@ static int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf,
 		 * Last BIO is always sent through the following
 		 * submission.
 		 */
-		rw |= REQ_SYNC | REQ_UNPLUG;
+		rw |= REQ_SYNC;
 		res = nilfs_segbuf_submit_bio(segbuf, &wi, rw);
 	}
 

fs/ntfs/aops.c

@@ -1543,8 +1543,6 @@ err_out:
  */
 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 */
@@ -1560,8 +1558,6 @@ const struct address_space_operations ntfs_aops = {
  */
 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

fs/ntfs/compress.c

@@ -698,8 +698,7 @@ lock_retry_remap:
 					"uptodate! Unplugging the disk queue "
 					"and rescheduling.");
 			get_bh(tbh);
-			blk_run_address_space(mapping);
+			io_schedule();
-			schedule();
 			put_bh(tbh);
 			if (unlikely(!buffer_uptodate(tbh)))
 				goto read_err;

fs/ocfs2/aops.c

@@ -2043,7 +2043,6 @@ const struct address_space_operations ocfs2_aops = {
 	.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,