Merge commit 'v2.6.34-rc1' into for-2.6.35

10 files changed, 167 insertions, 262 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1fa2654db0a..c85d74cae20 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -23,20 +23,6 @@ static LIST_HEAD(blkio_list);
 struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
 EXPORT_SYMBOL_GPL(blkio_root_cgroup);
 
-bool blkiocg_css_tryget(struct blkio_cgroup *blkcg)
-{
-	if (!css_tryget(&blkcg->css))
-		return false;
-	return true;
-}
-EXPORT_SYMBOL_GPL(blkiocg_css_tryget);
-
-void blkiocg_css_put(struct blkio_cgroup *blkcg)
-{
-	css_put(&blkcg->css);
-}
-EXPORT_SYMBOL_GPL(blkiocg_css_put);
-
 struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 {
 	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
@@ -147,16 +133,16 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
 		return -EINVAL;
 
 	blkcg = cgroup_to_blkio_cgroup(cgroup);
+	spin_lock(&blkio_list_lock);
 	spin_lock_irq(&blkcg->lock);
 	blkcg->weight = (unsigned int)val;
 	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
-		spin_lock(&blkio_list_lock);
 		list_for_each_entry(blkiop, &blkio_list, list)
 			blkiop->ops.blkio_update_group_weight_fn(blkg,
 					blkcg->weight);
-		spin_unlock(&blkio_list_lock);
 	}
 	spin_unlock_irq(&blkcg->lock);
+	spin_unlock(&blkio_list_lock);
 	return 0;
 }
 
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 4d316df863b..84bf745fa77 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -43,9 +43,6 @@ struct blkio_group {
 	unsigned long sectors;
 };
 
-extern bool blkiocg_css_tryget(struct blkio_cgroup *blkcg);
-extern void blkiocg_css_put(struct blkio_cgroup *blkcg);
-
 typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg);
 typedef void (blkio_update_group_weight_fn) (struct blkio_group *blkg,
 						unsigned int weight);
diff --git a/block/blk-core.c b/block/blk-core.c
index 718897e6d37..9fe174dc74d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1147,7 +1147,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
  */
 static inline bool queue_should_plug(struct request_queue *q)
 {
-	return !(blk_queue_nonrot(q) && blk_queue_queuing(q));
+	return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
 }
 
 static int __make_request(struct request_queue *q, struct bio *bio)
@@ -1490,9 +1490,9 @@ end_io:
 /*
  * We only want one ->make_request_fn to be active at a time,
  * else stack usage with stacked devices could be a problem.
- * So use current->bio_{list,tail} to keep a list of requests
+ * So use current->bio_list to keep a list of requests
  * submited by a make_request_fn function.
- * current->bio_tail is also used as a flag to say if
+ * current->bio_list is also used as a flag to say if
  * generic_make_request is currently active in this task or not.
  * If it is NULL, then no make_request is active.  If it is non-NULL,
  * then a make_request is active, and new requests should be added
@@ -1500,11 +1500,11 @@ end_io:
  */
 void generic_make_request(struct bio *bio)
 {
-	if (current->bio_tail) {
+	struct bio_list bio_list_on_stack;
+
+	if (current->bio_list) {
 		/* make_request is active */
-		*(current->bio_tail) = bio;
-		bio->bi_next = NULL;
-		current->bio_tail = &bio->bi_next;
+		bio_list_add(current->bio_list, bio);
 		return;
 	}
 	/* following loop may be a bit non-obvious, and so deserves some
@@ -1512,30 +1512,27 @@ void generic_make_request(struct bio *bio)
 	 * Before entering the loop, bio->bi_next is NULL (as all callers
 	 * ensure that) so we have a list with a single bio.
 	 * We pretend that we have just taken it off a longer list, so
-	 * we assign bio_list to the next (which is NULL) and bio_tail
-	 * to &bio_list, thus initialising the bio_list of new bios to be
+	 * we assign bio_list to a pointer to the bio_list_on_stack,
+	 * thus initialising the bio_list of new bios to be
 	 * added.  __generic_make_request may indeed add some more bios
 	 * through a recursive call to generic_make_request.  If it
 	 * did, we find a non-NULL value in bio_list and re-enter the loop
 	 * from the top.  In this case we really did just take the bio
-	 * of the top of the list (no pretending) and so fixup bio_list and
-	 * bio_tail or bi_next, and call into __generic_make_request again.
+	 * of the top of the list (no pretending) and so remove it from
+	 * bio_list, and call into __generic_make_request again.
 	 *
 	 * The loop was structured like this to make only one call to
 	 * __generic_make_request (which is important as it is large and
 	 * inlined) and to keep the structure simple.
 	 */
 	BUG_ON(bio->bi_next);
+	bio_list_init(&bio_list_on_stack);
+	current->bio_list = &bio_list_on_stack;
 	do {
-		current->bio_list = bio->bi_next;
-		if (bio->bi_next == NULL)
-			current->bio_tail = &current->bio_list;
-		else
-			bio->bi_next = NULL;
 		__generic_make_request(bio);
-		bio = current->bio_list;
+		bio = bio_list_pop(current->bio_list);
 	} while (bio);
-	current->bio_tail = NULL; /* deactivate */
+	current->bio_list = NULL; /* deactivate */
 }
 EXPORT_SYMBOL(generic_make_request);
 
@@ -1617,8 +1614,7 @@ int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 	 * limitation.
 	 */
 	blk_recalc_rq_segments(rq);
-	if (rq->nr_phys_segments > queue_max_phys_segments(q) ||
-	    rq->nr_phys_segments > queue_max_hw_segments(q)) {
+	if (rq->nr_phys_segments > queue_max_segments(q)) {
 		printk(KERN_ERR "%s: over max segments limit.\n", __func__);
 		return -EIO;
 	}
@@ -1859,15 +1855,8 @@ void blk_dequeue_request(struct request *rq)
 	 * and to it is freed is accounted as io that is in progress at
 	 * the driver side.
 	 */
-	if (blk_account_rq(rq)) {
+	if (blk_account_rq(rq))
 		q->in_flight[rq_is_sync(rq)]++;
-		/*
-		 * Mark this device as supporting hardware queuing, if
-		 * we have more IOs in flight than 4.
-		 */
-		if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
-			set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
-	}
 }
 
 /**
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 15c630813b1..96e83c2bdb9 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -278,7 +278,7 @@ static struct attribute *integrity_attrs[] = {
 	NULL,
 };
 
-static struct sysfs_ops integrity_ops = {
+static const struct sysfs_ops integrity_ops = {
 	.show	= &integrity_attr_show,
 	.store	= &integrity_attr_store,
 };
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 98e6bf61b0a..3f65c8aadb2 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -91,7 +91,7 @@ struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
 		spin_lock_init(&ret->lock);
 		ret->ioprio_changed = 0;
 		ret->ioprio = 0;
-		ret->last_waited = jiffies; /* doesn't matter... */
+		ret->last_waited = 0; /* doesn't matter... */
 		ret->nr_batch_requests = 0; /* because this is 0 */
 		INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
 		INIT_HLIST_HEAD(&ret->cic_list);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 99cb5cf1f44..5e7dc997345 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -206,8 +206,7 @@ static inline int ll_new_hw_segment(struct request_queue *q,
 {
 	int nr_phys_segs = bio_phys_segments(q, bio);
 
-	if (req->nr_phys_segments + nr_phys_segs > queue_max_hw_segments(q) ||
-	    req->nr_phys_segments + nr_phys_segs > queue_max_phys_segments(q)) {
+	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q)) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -300,10 +299,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		total_phys_segments--;
 	}
 
-	if (total_phys_segments > queue_max_phys_segments(q))
-		return 0;
-
-	if (total_phys_segments > queue_max_hw_segments(q))
+	if (total_phys_segments > queue_max_segments(q))
 		return 0;
 
 	/* Merge is OK... */
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5eeb9e0d256..31e7a9375c1 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -91,10 +91,9 @@ EXPORT_SYMBOL_GPL(blk_queue_lld_busy);
  */
 void blk_set_default_limits(struct queue_limits *lim)
 {
-	lim->max_phys_segments = MAX_PHYS_SEGMENTS;
-	lim->max_hw_segments = MAX_HW_SEGMENTS;
+	lim->max_segments = BLK_MAX_SEGMENTS;
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
-	lim->max_segment_size = MAX_SEGMENT_SIZE;
+	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
 	lim->max_sectors = BLK_DEF_MAX_SECTORS;
 	lim->max_hw_sectors = INT_MAX;
 	lim->max_discard_sectors = 0;
@@ -154,7 +153,7 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 	q->unplug_timer.data = (unsigned long)q;
 
 	blk_set_default_limits(&q->limits);
-	blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
+	blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS);
 
 	/*
 	 * If the caller didn't supply a lock, fall back to our embedded
@@ -210,37 +209,32 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask)
 EXPORT_SYMBOL(blk_queue_bounce_limit);
 
 /**
- * blk_queue_max_sectors - set max sectors for a request for this queue
+ * blk_queue_max_hw_sectors - set max sectors for a request for this queue
  * @q:  the request queue for the device
- * @max_sectors:  max sectors in the usual 512b unit
+ * @max_hw_sectors:  max hardware sectors in the usual 512b unit
  *
  * Description:
- *    Enables a low level driver to set an upper limit on the size of
- *    received requests.
+ *    Enables a low level driver to set a hard upper limit,
+ *    max_hw_sectors, on the size of requests.  max_hw_sectors is set by
+ *    the device driver based upon the combined capabilities of I/O
+ *    controller and storage device.
+ *
+ *    max_sectors is a soft limit imposed by the block layer for
+ *    filesystem type requests.  This value can be overridden on a
+ *    per-device basis in /sys/block/<device>/queue/max_sectors_kb.
+ *    The soft limit can not exceed max_hw_sectors.
  **/
-void blk_queue_max_sectors(struct request_queue *q, unsigned int max_sectors)
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
 {
-	if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
-		max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
+	if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) {
+		max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
 		printk(KERN_INFO "%s: set to minimum %d\n",
-		       __func__, max_sectors);
+		       __func__, max_hw_sectors);
 	}
 
-	if (BLK_DEF_MAX_SECTORS > max_sectors)
-		q->limits.max_hw_sectors = q->limits.max_sectors = max_sectors;
-	else {
-		q->limits.max_sectors = BLK_DEF_MAX_SECTORS;
-		q->limits.max_hw_sectors = max_sectors;
-	}
-}
-EXPORT_SYMBOL(blk_queue_max_sectors);
-
-void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors)
-{
-	if (BLK_DEF_MAX_SECTORS > max_sectors)
-		q->limits.max_hw_sectors = BLK_DEF_MAX_SECTORS;
-	else
-		q->limits.max_hw_sectors = max_sectors;
+	q->limits.max_hw_sectors = max_hw_sectors;
+	q->limits.max_sectors = min_t(unsigned int, max_hw_sectors,
+				      BLK_DEF_MAX_SECTORS);
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
@@ -257,17 +251,15 @@ void blk_queue_max_discard_sectors(struct request_queue *q,
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
 /**
- * blk_queue_max_phys_segments - set max phys segments for a request for this queue
+ * blk_queue_max_segments - set max hw segments for a request for this queue
  * @q:  the request queue for the device
  * @max_segments:  max number of segments
  *
  * Description:
  *    Enables a low level driver to set an upper limit on the number of
- *    physical data segments in a request.  This would be the largest sized
- *    scatter list the driver could handle.
+ *    hw data segments in a request.
  **/
-void blk_queue_max_phys_segments(struct request_queue *q,
-				 unsigned short max_segments)
+void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments)
 {
 	if (!max_segments) {
 		max_segments = 1;
@@ -275,33 +267,9 @@ void blk_queue_max_phys_segments(struct request_queue *q,
 		       __func__, max_segments);
 	}
 
-	q->limits.max_phys_segments = max_segments;
+	q->limits.max_segments = max_segments;
 }
-EXPORT_SYMBOL(blk_queue_max_phys_segments);
-
-/**
- * blk_queue_max_hw_segments - set max hw segments for a request for this queue
- * @q:  the request queue for the device
- * @max_segments:  max number of segments
- *
- * Description:
- *    Enables a low level driver to set an upper limit on the number of
- *    hw data segments in a request.  This would be the largest number of
- *    address/length pairs the host adapter can actually give at once
- *    to the device.
- **/
-void blk_queue_max_hw_segments(struct request_queue *q,
-			       unsigned short max_segments)
-{
-	if (!max_segments) {
-		max_segments = 1;
-		printk(KERN_INFO "%s: set to minimum %d\n",
-		       __func__, max_segments);
-	}
-
-	q->limits.max_hw_segments = max_segments;
-}
-EXPORT_SYMBOL(blk_queue_max_hw_segments);
+EXPORT_SYMBOL(blk_queue_max_segments);
 
 /**
  * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
@@ -507,7 +475,7 @@ static unsigned int lcm(unsigned int a, unsigned int b)
  * blk_stack_limits - adjust queue_limits for stacked devices
  * @t:	the stacking driver limits (top device)
  * @b:  the underlying queue limits (bottom, component device)
- * @offset:  offset to beginning of data within component device
+ * @start:  first data sector within component device
  *
  * Description:
  *    This function is used by stacking drivers like MD and DM to ensure
@@ -525,10 +493,9 @@ static unsigned int lcm(unsigned int a, unsigned int b)
  *    the alignment_offset is undefined.
  */
 int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
-		     sector_t offset)
+		     sector_t start)
 {
-	sector_t alignment;
-	unsigned int top, bottom, ret = 0;
+	unsigned int top, bottom, alignment, ret = 0;
 
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
 	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
@@ -537,18 +504,14 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
 					    b->seg_boundary_mask);
 
-	t->max_phys_segments = min_not_zero(t->max_phys_segments,
-					    b->max_phys_segments);
-
-	t->max_hw_segments = min_not_zero(t->max_hw_segments,
-					  b->max_hw_segments);
+	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
 
 	t->max_segment_size = min_not_zero(t->max_segment_size,
 					   b->max_segment_size);
 
 	t->misaligned |= b->misaligned;
 
-	alignment = queue_limit_alignment_offset(b, offset);
+	alignment = queue_limit_alignment_offset(b, start);
 
 	/* Bottom device has different alignment.  Check that it is
 	 * compatible with the current top alignment.
@@ -611,11 +574,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	/* Discard alignment and granularity */
 	if (b->discard_granularity) {
-		unsigned int granularity = b->discard_granularity;
-		offset &= granularity - 1;
-
-		alignment = (granularity + b->discard_alignment - offset)
-			& (granularity - 1);
+		alignment = queue_limit_discard_alignment(b, start);
 
 		if (t->discard_granularity != 0 &&
 		    t->discard_alignment != alignment) {
@@ -657,7 +616,7 @@ int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
 
 	start += get_start_sect(bdev);
 
-	return blk_stack_limits(t, &bq->limits, start << 9);
+	return blk_stack_limits(t, &bq->limits, start);
 }
 EXPORT_SYMBOL(bdev_stack_limits);
 
@@ -668,9 +627,8 @@ EXPORT_SYMBOL(bdev_stack_limits);
  * @offset:  offset to beginning of data within component device
  *
  * Description:
- *    Merges the limits for two queues.  Returns 0 if alignment
- *    didn't change.  Returns -1 if adding the bottom device caused
- *    misalignment.
+ *    Merges the limits for a top level gendisk and a bottom level
+ *    block_device.
  */
 void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		       sector_t offset)
@@ -678,9 +636,7 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 	struct request_queue *t = disk->queue;
 	struct request_queue *b = bdev_get_queue(bdev);
 
-	offset += get_start_sect(bdev) << 9;
-
-	if (blk_stack_limits(&t->limits, &b->limits, offset) < 0) {
+	if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) {
 		char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
 
 		disk_name(disk, 0, top);
@@ -752,22 +708,19 @@ EXPORT_SYMBOL(blk_queue_update_dma_pad);
  * does is adjust the queue so that the buf is always appended
  * silently to the scatterlist.
  *
- * Note: This routine adjusts max_hw_segments to make room for
- * appending the drain buffer.  If you call
- * blk_queue_max_hw_segments() or blk_queue_max_phys_segments() after
- * calling this routine, you must set the limit to one fewer than your
- * device can support otherwise there won't be room for the drain
- * buffer.
+ * Note: This routine adjusts max_hw_segments to make room for appending
+ * the drain buffer.  If you call blk_queue_max_segments() after calling
+ * this routine, you must set the limit to one fewer than your device
+ * can support otherwise there won't be room for the drain buffer.
  */
 int blk_queue_dma_drain(struct request_queue *q,
 			       dma_drain_needed_fn *dma_drain_needed,
 			       void *buf, unsigned int size)
 {
-	if (queue_max_hw_segments(q) < 2 || queue_max_phys_segments(q) < 2)
+	if (queue_max_segments(q) < 2)
 		return -EINVAL;
 	/* make room for appending the drain */
-	blk_queue_max_hw_segments(q, queue_max_hw_segments(q) - 1);
-	blk_queue_max_phys_segments(q, queue_max_phys_segments(q) - 1);
+	blk_queue_max_segments(q, queue_max_segments(q) - 1);
 	q->dma_drain_needed = dma_drain_needed;
 	q->dma_drain_buffer = buf;
 	q->dma_drain_size = size;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 8606c9543fd..2ae2cb3f362 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -189,7 +189,8 @@ static ssize_t queue_nonrot_store(struct request_queue *q, const char *page,
 
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(blk_queue_nomerges(q), page);
+	return queue_var_show((blk_queue_nomerges(q) << 1) |
+			       blk_queue_noxmerges(q), page);
 }
 
 static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
@@ -199,10 +200,12 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
 	ssize_t ret = queue_var_store(&nm, page, count);
 
 	spin_lock_irq(q->queue_lock);
-	if (nm)
+	queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
+	queue_flag_clear(QUEUE_FLAG_NOXMERGES, q);
+	if (nm == 2)
 		queue_flag_set(QUEUE_FLAG_NOMERGES, q);
-	else
-		queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
+	else if (nm)
+		queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
@@ -447,7 +450,7 @@ static void blk_release_queue(struct kobject *kobj)
 	kmem_cache_free(blk_requestq_cachep, q);
 }
 
-static struct sysfs_ops queue_sysfs_ops = {
+static const struct sysfs_ops queue_sysfs_ops = {
 	.show	= queue_attr_show,
 	.store	= queue_attr_store,
 };
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index ee130f14d1f..dee9d9378fe 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -19,7 +19,7 @@
  * tunables
  */
 /* max queue in one round of service */
-static const int cfq_quantum = 4;
+static const int cfq_quantum = 8;
 static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
 /* maximum backwards seek, in KiB */
 static const int cfq_back_max = 16 * 1024;
@@ -42,16 +42,14 @@ static const int cfq_hist_divisor = 4;
  */
 #define CFQ_MIN_TT		(2)
 
-/*
- * Allow merged cfqqs to perform this amount of seeky I/O before
- * deciding to break the queues up again.
- */
-#define CFQQ_COOP_TOUT		(HZ)
-
 #define CFQ_SLICE_SCALE		(5)
 #define CFQ_HW_QUEUE_MIN	(5)
 #define CFQ_SERVICE_SHIFT       12
 
+#define CFQQ_SEEK_THR		(sector_t)(8 * 100)
+#define CFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
+#define CFQQ_SEEKY(cfqq)	(hweight32(cfqq->seek_history) > 32/8)
+
 #define RQ_CIC(rq)		\
 	((struct cfq_io_context *) (rq)->elevator_private)
 #define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private2)
@@ -80,11 +78,12 @@ struct cfq_rb_root {
 	struct rb_root rb;
 	struct rb_node *left;
 	unsigned count;
+	unsigned total_weight;
 	u64 min_vdisktime;
 	struct rb_node *active;
-	unsigned total_weight;
 };
-#define CFQ_RB_ROOT	(struct cfq_rb_root) { RB_ROOT, NULL, 0, 0, }
+#define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, .left = NULL, \
+			.count = 0, .min_vdisktime = 0, }
 
 /*
  * Per process-grouping structure
@@ -118,11 +117,11 @@ struct cfq_queue {
 	/* time when queue got scheduled in to dispatch first request. */
 	unsigned long dispatch_start;
 	unsigned int allocated_slice;
+	unsigned int slice_dispatch;
 	/* time when first request from queue completed and slice started. */
 	unsigned long slice_start;
 	unsigned long slice_end;
 	long slice_resid;
-	unsigned int slice_dispatch;
 
 	/* pending metadata requests */
 	int meta_pending;
@@ -133,14 +132,11 @@ struct cfq_queue {
 	unsigned short ioprio, org_ioprio;
 	unsigned short ioprio_class, org_ioprio_class;
 
-	unsigned int seek_samples;
-	u64 seek_total;
-	sector_t seek_mean;
-	sector_t last_request_pos;
-	unsigned long seeky_start;
-
 	pid_t pid;
 
+	u32 seek_history;
+	sector_t last_request_pos;
+
 	struct cfq_rb_root *service_tree;
 	struct cfq_queue *new_cfqq;
 	struct cfq_group *cfqg;
@@ -227,8 +223,8 @@ struct cfq_data {
 
 	unsigned int busy_queues;
 
-	int rq_in_driver[2];
-	int sync_flight;
+	int rq_in_driver;
+	int rq_in_flight[2];
 
 	/*
 	 * queue-depth detection
@@ -314,6 +310,7 @@ enum cfqq_state_flags {
 	CFQ_CFQQ_FLAG_slice_new,	/* no requests dispatched in slice */
 	CFQ_CFQQ_FLAG_sync,		/* synchronous queue */
 	CFQ_CFQQ_FLAG_coop,		/* cfqq is shared */
+	CFQ_CFQQ_FLAG_split_coop,	/* shared cfqq will be splitted */
 	CFQ_CFQQ_FLAG_deep,		/* sync cfqq experienced large depth */
 	CFQ_CFQQ_FLAG_wait_busy,	/* Waiting for next request */
 };
@@ -342,6 +339,7 @@ CFQ_CFQQ_FNS(prio_changed);
 CFQ_CFQQ_FNS(slice_new);
 CFQ_CFQQ_FNS(sync);
 CFQ_CFQQ_FNS(coop);
+CFQ_CFQQ_FNS(split_coop);
 CFQ_CFQQ_FNS(deep);
 CFQ_CFQQ_FNS(wait_busy);
 #undef CFQ_CFQQ_FNS
@@ -419,11 +417,6 @@ static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,
 static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
 						struct io_context *);
 
-static inline int rq_in_driver(struct cfq_data *cfqd)
-{
-	return cfqd->rq_in_driver[0] + cfqd->rq_in_driver[1];
-}
-
 static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
 					    bool is_sync)
 {
@@ -953,10 +946,6 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
 	unsigned int major, minor;
 
-	/* Do we need to take this reference */
-	if (!blkiocg_css_tryget(blkcg))
-		return NULL;;
-
 	cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
 	if (cfqg || !create)
 		goto done;
@@ -987,7 +976,6 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
 
 done:
-	blkiocg_css_put(blkcg);
 	return cfqg;
 }
 
@@ -1422,9 +1410,9 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 
-	cfqd->rq_in_driver[rq_is_sync(rq)]++;
+	cfqd->rq_in_driver++;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
-						rq_in_driver(cfqd));
+						cfqd->rq_in_driver);
 
 	cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
 }
@@ -1432,12 +1420,11 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
-	const int sync = rq_is_sync(rq);
 
-	WARN_ON(!cfqd->rq_in_driver[sync]);
-	cfqd->rq_in_driver[sync]--;
+	WARN_ON(!cfqd->rq_in_driver);
+	cfqd->rq_in_driver--;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
-						rq_in_driver(cfqd));
+						cfqd->rq_in_driver);
 }
 
 static void cfq_remove_request(struct request *rq)
@@ -1566,6 +1553,15 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	cfq_clear_cfqq_wait_busy(cfqq);
 
 	/*
+	 * If this cfqq is shared between multiple processes, check to
+	 * make sure that those processes are still issuing I/Os within
+	 * the mean seek distance.  If not, it may be time to break the
+	 * queues apart again.
+	 */
+	if (cfq_cfqq_coop(cfqq) && CFQQ_SEEKY(cfqq))
+		cfq_mark_cfqq_split_coop(cfqq);
+
+	/*
 	 * store what was left of this slice, if the queue idled/timed out
 	 */
 	if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
@@ -1663,22 +1659,10 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 		return cfqd->last_position - blk_rq_pos(rq);
 }
 
-#define CFQQ_SEEK_THR		8 * 1024
-#define CFQQ_SEEKY(cfqq)	((cfqq)->seek_mean > CFQQ_SEEK_THR)
-
 static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			       struct request *rq, bool for_preempt)
 {
-	sector_t sdist = cfqq->seek_mean;
-
-	if (!sample_valid(cfqq->seek_samples))
-		sdist = CFQQ_SEEK_THR;
-
-	/* if seek_mean is big, using it as close criteria is meaningless */
-	if (sdist > CFQQ_SEEK_THR && !for_preempt)
-		sdist = CFQQ_SEEK_THR;
-
-	return cfq_dist_from_last(cfqd, rq) <= sdist;
+	return cfq_dist_from_last(cfqd, rq) <= CFQQ_SEEK_THR;
 }
 
 static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
@@ -1803,7 +1787,7 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * Otherwise, we do only if they are the last ones
 	 * in their service tree.
 	 */
-	return service_tree->count == 1;
+	return service_tree->count == 1 && cfq_cfqq_sync(cfqq);
 }
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
@@ -1874,8 +1858,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
 	cfqq->dispatched++;
 	elv_dispatch_sort(q, rq);
 
-	if (cfq_cfqq_sync(cfqq))
-		cfqd->sync_flight++;
+	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
 	cfqq->nr_sectors += blk_rq_sectors(rq);
 }
 
@@ -2215,6 +2198,19 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 	return dispatched;
 }
 
+static inline bool cfq_slice_used_soon(struct cfq_data *cfqd,
+	struct cfq_queue *cfqq)
+{
+	/* the queue hasn't finished any request, can't estimate */
+	if (cfq_cfqq_slice_new(cfqq))
+		return 1;
+	if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
+		cfqq->slice_end))
+		return 1;
+
+	return 0;
+}
+
 static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	unsigned int max_dispatch;
@@ -2222,16 +2218,16 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	/*
 	 * Drain async requests before we start sync IO
 	 */
-	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC])
+	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_flight[BLK_RW_ASYNC])
 		return false;
 
 	/*
 	 * If this is an async queue and we have sync IO in flight, let it wait
 	 */
-	if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
+	if (cfqd->rq_in_flight[BLK_RW_SYNC] && !cfq_cfqq_sync(cfqq))
 		return false;
 
-	max_dispatch = cfqd->cfq_quantum;
+	max_dispatch = max_t(unsigned int, cfqd->cfq_quantum / 2, 1);
 	if (cfq_class_idle(cfqq))
 		max_dispatch = 1;
 
@@ -2248,13 +2244,22 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		/*
 		 * We have other queues, don't allow more IO from this one
 		 */
-		if (cfqd->busy_queues > 1)
+		if (cfqd->busy_queues > 1 && cfq_slice_used_soon(cfqd, cfqq))
 			return false;
 
 		/*
 		 * Sole queue user, no limit
 		 */
-		max_dispatch = -1;
+		if (cfqd->busy_queues == 1)
+			max_dispatch = -1;
+		else
+			/*
+			 * Normally we start throttling cfqq when cfq_quantum/2
+			 * requests have been dispatched. But we can drive
+			 * deeper queue depths at the beginning of slice
+			 * subjected to upper limit of cfq_quantum.
+			 * */
+			max_dispatch = cfqd->cfq_quantum;
 	}
 
 	/*
@@ -2976,43 +2981,20 @@ static void
 cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		       struct request *rq)
 {
-	sector_t sdist;
-	u64 total;
-
-	if (!cfqq->last_request_pos)
-		sdist = 0;
-	else if (cfqq->last_request_pos < blk_rq_pos(rq))
-		sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
-	else
-		sdist = cfqq->last_request_pos - blk_rq_pos(rq);
+	sector_t sdist = 0;
+	sector_t n_sec = blk_rq_sectors(rq);
+	if (cfqq->last_request_pos) {
+		if (cfqq->last_request_pos < blk_rq_pos(rq))
+			sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
+		else
+			sdist = cfqq->last_request_pos - blk_rq_pos(rq);
+	}
 
-	/*
-	 * Don't allow the seek distance to get too large from the
-	 * odd fragment, pagein, etc
-	 */
-	if (cfqq->seek_samples <= 60) /* second&third seek */
-		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*1024);
+	cfqq->seek_history <<= 1;
+	if (blk_queue_nonrot(cfqd->queue))
+		cfqq->seek_history |= (n_sec < CFQQ_SECT_THR_NONROT);
 	else
-		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*64);
-
-	cfqq->seek_samples = (7*cfqq->seek_samples + 256) / 8;
-	cfqq->seek_total = (7*cfqq->seek_total + (u64)256*sdist) / 8;
-	total = cfqq->seek_total + (cfqq->seek_samples/2);
-	do_div(total, cfqq->seek_samples);
-	cfqq->seek_mean = (sector_t)total;
-
-	/*
-	 * If this cfqq is shared between multiple processes, check to
-	 * make sure that those processes are still issuing I/Os within
-	 * the mean seek distance.  If not, it may be time to break the
-	 * queues apart again.
-	 */
-	if (cfq_cfqq_coop(cfqq)) {
-		if (CFQQ_SEEKY(cfqq) && !cfqq->seeky_start)
-			cfqq->seeky_start = jiffies;
-		else if (!CFQQ_SEEKY(cfqq))
-			cfqq->seeky_start = 0;
-	}
+		cfqq->seek_history |= (sdist > CFQQ_SEEK_THR);
 }
 
 /*
@@ -3037,8 +3019,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		cfq_mark_cfqq_deep(cfqq);
 
 	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
-	    (!cfq_cfqq_deep(cfqq) && sample_valid(cfqq->seek_samples)
-	     && CFQQ_SEEKY(cfqq)))
+	    (!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq)))
 		enable_idle = 0;
 	else if (sample_valid(cic->ttime_samples)) {
 		if (cic->ttime_mean > cfqd->cfq_slice_idle)
@@ -3224,14 +3205,14 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 
-	if (rq_in_driver(cfqd) > cfqd->hw_tag_est_depth)
-		cfqd->hw_tag_est_depth = rq_in_driver(cfqd);
+	if (cfqd->rq_in_driver > cfqd->hw_tag_est_depth)
+		cfqd->hw_tag_est_depth = cfqd->rq_in_driver;
 
 	if (cfqd->hw_tag == 1)
 		return;
 
 	if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
-	    rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
+	    cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
 		return;
 
 	/*
@@ -3241,7 +3222,7 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 	 */
 	if (cfqq && cfq_cfqq_idle_window(cfqq) &&
 	    cfqq->dispatched + cfqq->queued[0] + cfqq->queued[1] <
-	    CFQ_HW_QUEUE_MIN && rq_in_driver(cfqd) < CFQ_HW_QUEUE_MIN)
+	    CFQ_HW_QUEUE_MIN && cfqd->rq_in_driver < CFQ_HW_QUEUE_MIN)
 		return;
 
 	if (cfqd->hw_tag_samples++ < 50)
@@ -3294,13 +3275,12 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 
 	cfq_update_hw_tag(cfqd);
 
-	WARN_ON(!cfqd->rq_in_driver[sync]);
+	WARN_ON(!cfqd->rq_in_driver);
 	WARN_ON(!cfqq->dispatched);
-	cfqd->rq_in_driver[sync]--;
+	cfqd->rq_in_driver--;
 	cfqq->dispatched--;
 
-	if (cfq_cfqq_sync(cfqq))
-		cfqd->sync_flight--;
+	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 
 	if (sync) {
 		RQ_CIC(rq)->last_end_request = now;
@@ -3354,7 +3334,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		}
 	}
 
-	if (!rq_in_driver(cfqd))
+	if (!cfqd->rq_in_driver)
 		cfq_schedule_dispatch(cfqd);
 }
 
@@ -3453,14 +3433,6 @@ cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic,
 	return cic_to_cfqq(cic, 1);
 }
 
-static int should_split_cfqq(struct cfq_queue *cfqq)
-{
-	if (cfqq->seeky_start &&
-	    time_after(jiffies, cfqq->seeky_start + CFQQ_COOP_TOUT))
-		return 1;
-	return 0;
-}
-
 /*
  * Returns NULL if a new cfqq should be allocated, or the old cfqq if this
  * was the last process referring to said cfqq.
@@ -3469,9 +3441,9 @@ static struct cfq_queue *
 split_cfqq(struct cfq_io_context *cic, struct cfq_queue *cfqq)
 {
 	if (cfqq_process_refs(cfqq) == 1) {
-		cfqq->seeky_start = 0;
 		cfqq->pid = current->pid;
 		cfq_clear_cfqq_coop(cfqq);
+		cfq_clear_cfqq_split_coop(cfqq);
 		return cfqq;
 	}
 
@@ -3510,7 +3482,7 @@ new_queue:
 		/*
 		 * If the queue was seeky for too long, break it apart.
 		 */
-		if (cfq_cfqq_coop(cfqq) && should_split_cfqq(cfqq)) {
+		if (cfq_cfqq_coop(cfqq) && cfq_cfqq_split_coop(cfqq)) {
 			cfq_log_cfqq(cfqd, cfqq, "breaking apart cfqq");
 			cfqq = split_cfqq(cic, cfqq);
 			if (!cfqq)
diff --git a/block/elevator.c b/block/elevator.c
index 9ad5ccc4c5e..df75676f667 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -474,6 +474,15 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	int ret;
 
 	/*
+	 * Levels of merges:
+	 * 	nomerges:  No merges at all attempted
+	 * 	noxmerges: Only simple one-hit cache try
+	 * 	merges:	   All merge tries attempted
+	 */
+	if (blk_queue_nomerges(q))
+		return ELEVATOR_NO_MERGE;
+
+	/*
 	 * First try one-hit cache.
 	 */
 	if (q->last_merge) {
@@ -484,7 +493,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		}
 	}
 
-	if (blk_queue_nomerges(q))
+	if (blk_queue_noxmerges(q))
 		return ELEVATOR_NO_MERGE;
 
 	/*
@@ -883,7 +892,7 @@ elv_attr_store(struct kobject *kobj, struct attribute *attr,
 	return error;
 }
 
-static struct sysfs_ops elv_sysfs_ops = {
+static const struct sysfs_ops elv_sysfs_ops = {
 	.show	= elv_attr_show,
 	.store	= elv_attr_store,
 };