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-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, 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,
-		       int plug)
+void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 {
+	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,
-		     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;

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 */
-		/* plugging on a queue, that actually has no requests! */
-	q->unplug_fn = drbd_unplug_fn;
+	q->queue_lock = &mdev->req_lock;
 
 	mdev->md_io_page = alloc_page(GFP_KERNEL);
 	if (!mdev->md_io_page)

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);
-		schedule();
+		io_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);