From 3cca6dc1c81e2407928dc4c6105252146fd3924f Mon Sep 17 00:00:00 2001
From: Jens Axboe <jaxboe@fusionio.com>
Date: Wed, 2 Mar 2011 11:08:00 -0500
Subject: block: add API for delaying work/request_fn a little bit

Currently we use plugging for that, but as plugging is going away,
we need an alternative mechanism.

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-core.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'block')

diff --git a/block/blk-core.c b/block/blk-core.c
index 3cc17e60..e958c7a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -197,6 +197,32 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 }
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
+static void blk_delay_work(struct work_struct *work)
+{
+	struct request_queue *q;
+
+	q = container_of(work, struct request_queue, delay_work.work);
+	spin_lock_irq(q->queue_lock);
+	q->request_fn(q);
+	spin_unlock_irq(q->queue_lock);
+}
+
+/**
+ * blk_delay_queue - restart queueing after defined interval
+ * @q:		The &struct request_queue in question
+ * @msecs:	Delay in msecs
+ *
+ * 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
+ *   restarted around the specified time.
+ */
+void blk_delay_queue(struct request_queue *q, unsigned long msecs)
+{
+	schedule_delayed_work(&q->delay_work, msecs_to_jiffies(msecs));
+}
+EXPORT_SYMBOL(blk_delay_queue);
+
 /*
  * "plug" the device if there are no outstanding requests: this will
  * force the transfer to start only after we have put all the requests
@@ -363,6 +389,7 @@ 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);
@@ -387,6 +414,7 @@ void blk_sync_queue(struct request_queue *q)
 	del_timer_sync(&q->timeout);
 	cancel_work_sync(&q->unplug_work);
 	throtl_shutdown_timer_wq(q);
+	cancel_delayed_work_sync(&q->delay_work);
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
@@ -534,6 +562,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	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);
 
-- 
cgit v1.1


From 73c101011926c5832e6e141682180c4debe2cf45 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jaxboe@fusionio.com>
Date: Tue, 8 Mar 2011 13:19:51 +0100
Subject: block: initial patch for on-stack per-task plugging

This patch adds support for creating a queuing context outside
of the queue itself. This enables us to batch up pieces of IO
before grabbing the block device queue lock and submitting them to
the IO scheduler.

The context is created on the stack of the process and assigned in
the task structure, so that we can auto-unplug it if we hit a schedule
event.

The current queue plugging happens implicitly if IO is submitted to
an empty device, yet callers have to remember to unplug that IO when
they are going to wait for it. This is an ugly API and has caused bugs
in the past. Additionally, it requires hacks in the vm (->sync_page()
callback) to handle that logic. By switching to an explicit plugging
scheme we make the API a lot nicer and can get rid of the ->sync_page()
hack in the vm.

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-core.c  | 369 +++++++++++++++++++++++++++++++++++++++---------------
 block/blk-flush.c |   3 +-
 block/elevator.c  |   6 +-
 3 files changed, 277 insertions(+), 101 deletions(-)

(limited to 'block')

diff --git a/block/blk-core.c b/block/blk-core.c
index e958c7a..6efb55c 100644
--- a/block/blk-core.c
+++ b/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>
@@ -203,7 +204,7 @@ static void blk_delay_work(struct work_struct *work)
 
 	q = container_of(work, struct request_queue, delay_work.work);
 	spin_lock_irq(q->queue_lock);
-	q->request_fn(q);
+	__blk_run_queue(q);
 	spin_unlock_irq(q->queue_lock);
 }
 
@@ -686,6 +687,8 @@ 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);
@@ -1051,6 +1054,13 @@ 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, 0);
+}
+
 /**
  * blk_insert_request - insert a special request into a request queue
  * @q:		request queue where request should be inserted
@@ -1093,8 +1103,7 @@ 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);
-	__elv_add_request(q, rq, where, 0);
+	add_acct_request(q, rq, where);
 	__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
@@ -1215,6 +1224,113 @@ 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;
@@ -1230,26 +1346,12 @@ 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);
-	const unsigned long ff = bio->bi_rw & REQ_FAILFAST_MASK;
-	int where = ELEVATOR_INSERT_SORT;
-	int rw_flags;
+	struct blk_plug *plug;
+	int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
+	struct request *req;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
@@ -1258,78 +1360,36 @@ 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;
-
-	el_ret = elv_merge(q, &req, bio);
-	switch (el_ret) {
-	case ELEVATOR_BACK_MERGE:
-		BUG_ON(!rq_mergeable(req));
-
-		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);
+	/*
+	 * Check if we can merge with the plugged list before grabbing
+	 * any locks.
+	 */
+	if (attempt_plug_merge(current, q, bio))
 		goto out;
 
-	case ELEVATOR_FRONT_MERGE:
-		BUG_ON(!rq_mergeable(req));
-
-		if (!ll_front_merge_fn(q, req, bio))
-			break;
-
-		trace_block_bio_frontmerge(q, bio);
+	spin_lock_irq(q->queue_lock);
 
-		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
-			blk_rq_set_mixed_merge(req);
-			req->cmd_flags &= ~REQ_FAILFAST_MASK;
-			req->cmd_flags |= ff;
+	el_ret = elv_merge(q, &req, bio);
+	if (el_ret == ELEVATOR_BACK_MERGE) {
+		BUG_ON(req->cmd_flags & REQ_ON_PLUG);
+		if (bio_attempt_back_merge(q, req, bio)) {
+			if (!attempt_back_merge(q, req))
+				elv_merged_request(q, req, el_ret);
+			goto out_unlock;
+		}
+	} else if (el_ret == ELEVATOR_FRONT_MERGE) {
+		BUG_ON(req->cmd_flags & REQ_ON_PLUG);
+		if (bio_attempt_front_merge(q, req, bio)) {
+			if (!attempt_front_merge(q, req))
+				elv_merged_request(q, req, el_ret);
+			goto out_unlock;
 		}
-
-		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 += 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;
-
-	/* ELV_NO_MERGE: elevator says don't/can't merge. */
-	default:
-		;
 	}
 
 get_rq:
@@ -1356,20 +1416,35 @@ 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))
-		req->cpu = blk_cpu_to_group(smp_processor_id());
-	if (queue_should_plug(q) && elv_queue_empty(q))
-		blk_plug_device(q);
-
-	/* insert the request into the elevator */
-	drive_stat_acct(req, 1);
-	__elv_add_request(q, req, where, 0);
+	    bio_flagged(bio, BIO_CPU_AFFINE)) {
+		req->cpu = blk_cpu_to_group(get_cpu());
+		put_cpu();
+	}
+
+	plug = current->plug;
+	if (plug && !sync) {
+		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);
+	} else {
+		spin_lock_irq(q->queue_lock);
+		add_acct_request(q, req, where);
+		__blk_run_queue(q);
+out_unlock:
+		spin_unlock_irq(q->queue_lock);
+	}
 out:
-	if (unplug || !queue_should_plug(q))
-		__generic_unplug_device(q);
-	spin_unlock_irq(q->queue_lock);
 	return 0;
 }
 
@@ -1772,9 +1847,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	drive_stat_acct(rq, 1);
-	__elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 0);
-
+	add_acct_request(q, rq, ELEVATOR_INSERT_BACK);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
 	return 0;
@@ -2659,6 +2732,106 @@ int kblockd_schedule_delayed_work(struct request_queue *q,
 }
 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);
+				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, 0);
+	}
+
+	if (q) {
+		__blk_run_queue(q);
+		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 *
diff --git a/block/blk-flush.c b/block/blk-flush.c
index a867e3f..1e2aa8a 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -264,10 +264,9 @@ 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 */
-	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);
 }
 
diff --git a/block/elevator.c b/block/elevator.c
index f98e92e..2571392 100644
--- a/block/elevator.c
+++ b/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;
 
@@ -696,6 +698,8 @@ void elv_insert(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 ||
-- 
cgit v1.1


From 7eaceaccab5f40bbfda044629a6298616aeaed50 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jaxboe@fusionio.com>
Date: Thu, 10 Mar 2011 08:52:07 +0100
Subject: block: remove per-queue plugging

Code has been converted over to the new explicit on-stack plugging,
and delay users have been converted to use the new API for that.
So lets kill off the old plugging along with aops->sync_page().

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-core.c         | 173 ++++++-----------------------------------------
 block/blk-exec.c         |   4 +-
 block/blk-flush.c        |   3 +-
 block/blk-settings.c     |   8 ---
 block/blk-throttle.c     |   1 -
 block/blk.h              |   2 -
 block/cfq-iosched.c      |   8 ---
 block/deadline-iosched.c |   9 ---
 block/elevator.c         |  43 +-----------
 block/noop-iosched.c     |   8 ---
 10 files changed, 26 insertions(+), 233 deletions(-)

(limited to 'block')

diff --git a/block/blk-core.c b/block/blk-core.c
index 6efb55c..82a4589 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -198,6 +198,19 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 }
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
+/*
+ * Make sure that plugs that were pending when this function was entered,
+ * are now complete and requests pushed to the queue.
+*/
+static inline void queue_sync_plugs(struct request_queue *q)
+{
+	/*
+	 * If the current process is plugged and has barriers submitted,
+	 * we will livelock if we don't unplug first.
+	 */
+	blk_flush_plug(current);
+}
+
 static void blk_delay_work(struct work_struct *work)
 {
 	struct request_queue *q;
@@ -224,137 +237,6 @@ void blk_delay_queue(struct request_queue *q, unsigned long msecs)
 }
 EXPORT_SYMBOL(blk_delay_queue);
 
-/*
- * "plug" the device if there are no outstanding requests: this will
- * force the transfer to start only after we have put all the requests
- * on the list.
- *
- * This is called with interrupts off and no requests on the queue and
- * with the queue lock held.
- */
-void blk_plug_device(struct request_queue *q)
-{
-	WARN_ON(!irqs_disabled());
-
-	/*
-	 * don't plug a stopped queue, it must be paired with blk_start_queue()
-	 * which will restart the queueing
-	 */
-	if (blk_queue_stopped(q))
-		return;
-
-	if (!queue_flag_test_and_set(QUEUE_FLAG_PLUGGED, q)) {
-		mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
-		trace_block_plug(q);
-	}
-}
-EXPORT_SYMBOL(blk_plug_device);
-
-/**
- * blk_plug_device_unlocked - plug a device without queue lock held
- * @q:    The &struct request_queue to plug
- *
- * Description:
- *   Like @blk_plug_device(), but grabs the queue lock and disables
- *   interrupts.
- **/
-void blk_plug_device_unlocked(struct request_queue *q)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	blk_plug_device(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-EXPORT_SYMBOL(blk_plug_device_unlocked);
-
-/*
- * remove the queue from the plugged list, if present. called with
- * queue lock held and interrupts disabled.
- */
-int blk_remove_plug(struct request_queue *q)
-{
-	WARN_ON(!irqs_disabled());
-
-	if (!queue_flag_test_and_clear(QUEUE_FLAG_PLUGGED, q))
-		return 0;
-
-	del_timer(&q->unplug_timer);
-	return 1;
-}
-EXPORT_SYMBOL(blk_remove_plug);
-
-/*
- * remove the plug and let it rip..
- */
-void __generic_unplug_device(struct request_queue *q)
-{
-	if (unlikely(blk_queue_stopped(q)))
-		return;
-	if (!blk_remove_plug(q) && !blk_queue_nonrot(q))
-		return;
-
-	q->request_fn(q);
-}
-
-/**
- * generic_unplug_device - fire a request queue
- * @q:    The &struct request_queue in question
- *
- * Description:
- *   Linux uses plugging to build bigger requests queues before letting
- *   the device have at them. If a queue is plugged, the I/O scheduler
- *   is still adding and merging requests on the queue. Once the queue
- *   gets unplugged, the request_fn defined for the queue is invoked and
- *   transfers started.
- **/
-void generic_unplug_device(struct request_queue *q)
-{
-	if (blk_queue_plugged(q)) {
-		spin_lock_irq(q->queue_lock);
-		__generic_unplug_device(q);
-		spin_unlock_irq(q->queue_lock);
-	}
-}
-EXPORT_SYMBOL(generic_unplug_device);
-
-static void blk_backing_dev_unplug(struct backing_dev_info *bdi,
-				   struct page *page)
-{
-	struct request_queue *q = bdi->unplug_io_data;
-
-	blk_unplug(q);
-}
-
-void blk_unplug_work(struct work_struct *work)
-{
-	struct request_queue *q =
-		container_of(work, struct request_queue, unplug_work);
-
-	trace_block_unplug_io(q);
-	q->unplug_fn(q);
-}
-
-void blk_unplug_timeout(unsigned long data)
-{
-	struct request_queue *q = (struct request_queue *)data;
-
-	trace_block_unplug_timer(q);
-	kblockd_schedule_work(q, &q->unplug_work);
-}
-
-void blk_unplug(struct request_queue *q)
-{
-	/*
-	 * devices don't necessarily have an ->unplug_fn defined
-	 */
-	if (q->unplug_fn) {
-		trace_block_unplug_io(q);
-		q->unplug_fn(q);
-	}
-}
-EXPORT_SYMBOL(blk_unplug);
-
 /**
  * blk_start_queue - restart a previously stopped queue
  * @q:    The &struct request_queue in question
@@ -389,7 +271,6 @@ 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);
 }
@@ -411,11 +292,10 @@ 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);
 	throtl_shutdown_timer_wq(q);
 	cancel_delayed_work_sync(&q->delay_work);
+	queue_sync_plugs(q);
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
@@ -430,14 +310,9 @@ EXPORT_SYMBOL(blk_sync_queue);
  */
 void __blk_run_queue(struct request_queue *q)
 {
-	blk_remove_plug(q);
-
 	if (unlikely(blk_queue_stopped(q)))
 		return;
 
-	if (elv_queue_empty(q))
-		return;
-
 	/*
 	 * Only recurse once to avoid overrunning the stack, let the unplug
 	 * handling reinvoke the handler shortly if we already got there.
@@ -445,10 +320,8 @@ void __blk_run_queue(struct request_queue *q)
 	if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
 		q->request_fn(q);
 		queue_flag_clear(QUEUE_FLAG_REENTER, q);
-	} else {
-		queue_flag_set(QUEUE_FLAG_PLUGGED, q);
-		kblockd_schedule_work(q, &q->unplug_work);
-	}
+	} else
+		queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
 }
 EXPORT_SYMBOL(__blk_run_queue);
 
@@ -535,8 +408,6 @@ 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;
@@ -556,13 +427,11 @@ 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);
@@ -652,7 +521,6 @@ 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;
 	q->queue_lock		= lock;
 
@@ -910,8 +778,8 @@ out:
 }
 
 /*
- * No available requests for this queue, unplug the device and wait for some
- * requests to become available.
+ * No available requests for this queue, wait for some requests to become
+ * available.
  *
  * Called with q->queue_lock held, and returns with it unlocked.
  */
@@ -932,7 +800,6 @@ 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();
 
@@ -1058,7 +925,7 @@ 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, 0);
+	__elv_add_request(q, rq, where);
 }
 
 /**
@@ -2798,7 +2665,7 @@ static void flush_plug_list(struct blk_plug *plug)
 		/*
 		 * rq is already accounted, so use raw insert
 		 */
-		__elv_add_request(q, rq, ELEVATOR_INSERT_SORT, 0);
+		__elv_add_request(q, rq, ELEVATOR_INSERT_SORT);
 	}
 
 	if (q) {
diff --git a/block/blk-exec.c b/block/blk-exec.c
index cf1456a..81e3181 100644
--- a/block/blk-exec.c
+++ b/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);
-	__generic_unplug_device(q);
+	__elv_add_request(q, rq, where);
+	__blk_run_queue(q);
 	/* the queue is stopped so it won't be plugged+unplugged */
 	if (rq->cmd_type == REQ_TYPE_PM_RESUME)
 		q->request_fn(q);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 1e2aa8a..671fa9d 100644
--- a/block/blk-flush.c
+++ b/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;
 
@@ -213,7 +212,7 @@ static void flush_end_io(struct request *flush_rq, int error)
 	}
 
 	/* after populating an empty queue, kick it to avoid stall */
-	if (queued && was_empty)
+	if (queued)
 		__blk_run_queue(q);
 }
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 36c8c1f..c8d6892 100644
--- a/block/blk-settings.c
+++ b/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);
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index a89043a..b8dcdc2 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -800,7 +800,6 @@ out:
 	if (nr_disp) {
 		while((bio = bio_list_pop(&bio_list_on_stack)))
 			generic_make_request(bio);
-		blk_unplug(q);
 	}
 	return nr_disp;
 }
diff --git a/block/blk.h b/block/blk.h
index 284b500..49d21af 100644
--- a/block/blk.h
+++ b/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 *);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 3202c7e..ef63153 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -499,13 +499,6 @@ 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
@@ -4061,7 +4054,6 @@ 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,
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index b547cbc..5139c0e 100644
--- a/block/deadline-iosched.c
+++ b/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,
diff --git a/block/elevator.c b/block/elevator.c
index 2571392..3ea2082 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -619,21 +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);
@@ -679,24 +670,14 @@ 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,
-		       int plug)
+void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 {
 	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
 
@@ -711,38 +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,
-		     int plug)
+void elv_add_request(struct request_queue *q, struct request *rq, int where)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	__elv_add_request(q, rq, where, plug);
+	__elv_add_request(q, rq, where);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(elv_add_request);
 
-int elv_queue_empty(struct request_queue *q)
-{
-	struct elevator_queue *e = q->elevator;
-
-	if (!list_empty(&q->queue_head))
-		return 0;
-
-	if (e->ops->elevator_queue_empty_fn)
-		return e->ops->elevator_queue_empty_fn(q);
-
-	return 1;
-}
-EXPORT_SYMBOL(elv_queue_empty);
-
 struct request *elv_latter_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index 232c4b3..06389e9 100644
--- a/block/noop-iosched.c
+++ b/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,
-- 
cgit v1.1


From 721a9602e6607417c6bc15b18e97a2f35266c690 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jaxboe@fusionio.com>
Date: Wed, 9 Mar 2011 11:56:30 +0100
Subject: block: kill off REQ_UNPLUG

With the plugging now being explicitly controlled by the
submitter, callers need not pass down unplugging hints
to the block layer. If they want to unplug, it's because they
manually plugged on their own - in which case, they should just
unplug at will.

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'block')

diff --git a/block/blk-core.c b/block/blk-core.c
index 82a4589..7e9715a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1290,7 +1290,7 @@ get_rq:
 	}
 
 	plug = current->plug;
-	if (plug && !sync) {
+	if (plug) {
 		if (!plug->should_sort && !list_empty(&plug->list)) {
 			struct request *__rq;
 
-- 
cgit v1.1


From 69d60eb96ae8a73cf9b79cf28051caf973006011 Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@redhat.com>
Date: Wed, 9 Mar 2011 08:27:37 +0100
Subject: blk-throttle: Use blk_plug in throttle dispatch

Use plug in throttle dispatch also as we are dispatching a bunch of
bios in throttle context and some of them might merge.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-throttle.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'block')

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index b8dcdc2..658ee50 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -770,6 +770,7 @@ 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);
 
@@ -798,8 +799,10 @@ out:
 	 * immediate dispatch
 	 */
 	if (nr_disp) {
+		blk_start_plug(&plug);
 		while((bio = bio_list_pop(&bio_list_on_stack)))
 			generic_make_request(bio);
+		blk_finish_plug(&plug);
 	}
 	return nr_disp;
 }
-- 
cgit v1.1