Merge commit 'v2.6.36' into kbuild/misc

Update to be able to fix a recent change to scripts/basic/docproc.c
(commit eda603f).

26 files changed, 2129 insertions, 836 deletions

diff --git a/block/Kconfig b/block/Kconfig
index e20fbde0875c..9be0b56eaee1 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -77,28 +77,6 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
-config BLK_CGROUP
-	bool
-	depends on CGROUPS
-	default n
-	---help---
-	Generic block IO controller cgroup interface. This is the common
-	cgroup interface which should be used by various IO controlling
-	policies.
-
-	Currently, CFQ IO scheduler uses it to recognize task groups and
-	control disk bandwidth allocation (proportional time slice allocation)
-	to such task groups.
-
-config DEBUG_BLK_CGROUP
-	bool
-	depends on BLK_CGROUP
-	default n
-	---help---
-	Enable some debugging help. Currently it stores the cgroup path
-	in the blk group which can be used by cfq for tracing various
-	group related activity.
-
 endif # BLOCK
 
 config BLOCK_COMPAT
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index b71abfb0d726..3199b76f795d 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -23,6 +23,8 @@ config IOSCHED_DEADLINE
 
 config IOSCHED_CFQ
 	tristate "CFQ I/O scheduler"
+	# If BLK_CGROUP is a module, CFQ has to be built as module.
+	depends on (BLK_CGROUP=m && m) || !BLK_CGROUP || BLK_CGROUP=y
 	default y
 	---help---
 	  The CFQ I/O scheduler tries to distribute bandwidth equally
@@ -32,23 +34,15 @@ config IOSCHED_CFQ
 
 	  This is the default I/O scheduler.
 
+	  Note: If BLK_CGROUP=m, then CFQ can be built only as module.
+
 config CFQ_GROUP_IOSCHED
 	bool "CFQ Group Scheduling support"
-	depends on IOSCHED_CFQ && CGROUPS
-	select BLK_CGROUP
+	depends on IOSCHED_CFQ && BLK_CGROUP
 	default n
 	---help---
 	  Enable group IO scheduling in CFQ.
 
-config DEBUG_CFQ_IOSCHED
-	bool "Debug CFQ Scheduling"
-	depends on CFQ_GROUP_IOSCHED
-	select DEBUG_BLK_CGROUP
-	default n
-	---help---
-	  Enable CFQ IO scheduling debugging in CFQ. Currently it makes
-	  blktrace output more verbose.
-
 choice
 	prompt "Default I/O scheduler"
 	default DEFAULT_CFQ
diff --git a/block/Makefile b/block/Makefile
index cb2d515ebd6e..0bb499a739cd 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
-			blk-iopoll.o ioctl.o genhd.o scsi_ioctl.o
+			blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 8618d8996fea..f0faefca032f 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/gfp.h>
 
 #include "blk.h"
 
@@ -12,7 +13,6 @@
  * blk_queue_ordered - does this queue support ordered writes
  * @q:        the request queue
  * @ordered:  one of QUEUE_ORDERED_*
- * @prepare_flush_fn: rq setup helper for cache flush ordered writes
  *
  * Description:
  *   For journalled file systems, doing ordered writes on a commit
@@ -21,15 +21,8 @@
  *   feature should call this function and indicate so.
  *
  **/
-int blk_queue_ordered(struct request_queue *q, unsigned ordered,
-		      prepare_flush_fn *prepare_flush_fn)
+int blk_queue_ordered(struct request_queue *q, unsigned ordered)
 {
-	if (!prepare_flush_fn && (ordered & (QUEUE_ORDERED_DO_PREFLUSH |
-					     QUEUE_ORDERED_DO_POSTFLUSH))) {
-		printk(KERN_ERR "%s: prepare_flush_fn required\n", __func__);
-		return -EINVAL;
-	}
-
 	if (ordered != QUEUE_ORDERED_NONE &&
 	    ordered != QUEUE_ORDERED_DRAIN &&
 	    ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
@@ -43,7 +36,6 @@ int blk_queue_ordered(struct request_queue *q, unsigned ordered,
 
 	q->ordered = ordered;
 	q->next_ordered = ordered;
-	q->prepare_flush_fn = prepare_flush_fn;
 
 	return 0;
 }
@@ -78,7 +70,7 @@ unsigned blk_ordered_req_seq(struct request *rq)
 	 *
 	 * http://thread.gmane.org/gmane.linux.kernel/537473
 	 */
-	if (!blk_fs_request(rq))
+	if (rq->cmd_type != REQ_TYPE_FS)
 		return QUEUE_ORDSEQ_DRAIN;
 
 	if ((rq->cmd_flags & REQ_ORDERED_COLOR) ==
@@ -142,10 +134,10 @@ static void queue_flush(struct request_queue *q, unsigned which)
 	}
 
 	blk_rq_init(q, rq);
-	rq->cmd_flags = REQ_HARDBARRIER;
-	rq->rq_disk = q->bar_rq.rq_disk;
+	rq->cmd_type = REQ_TYPE_FS;
+	rq->cmd_flags = REQ_HARDBARRIER | REQ_FLUSH;
+	rq->rq_disk = q->orig_bar_rq->rq_disk;
 	rq->end_io = end_io;
-	q->prepare_flush_fn(q, rq);
 
 	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
 }
@@ -202,7 +194,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 		/* initialize proxy request and queue it */
 		blk_rq_init(q, rq);
 		if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
-			rq->cmd_flags |= REQ_RW;
+			rq->cmd_flags |= REQ_WRITE;
 		if (q->ordered & QUEUE_ORDERED_DO_FUA)
 			rq->cmd_flags |= REQ_FUA;
 		init_request_from_bio(rq, q->orig_bar_rq->bio);
@@ -235,7 +227,8 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 bool blk_do_ordered(struct request_queue *q, struct request **rqp)
 {
 	struct request *rq = *rqp;
-	const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
+	const int is_barrier = rq->cmd_type == REQ_TYPE_FS &&
+				(rq->cmd_flags & REQ_HARDBARRIER);
 
 	if (!q->ordseq) {
 		if (!is_barrier)
@@ -260,7 +253,7 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp)
 	 */
 
 	/* Special requests are not subject to ordering rules. */
-	if (!blk_fs_request(rq) &&
+	if (rq->cmd_type != REQ_TYPE_FS &&
 	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
 		return true;
 
@@ -285,26 +278,31 @@ static void bio_end_empty_barrier(struct bio *bio, int err)
 			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
 	}
-
-	complete(bio->bi_private);
+	if (bio->bi_private)
+		complete(bio->bi_private);
+	bio_put(bio);
 }
 
 /**
  * blkdev_issue_flush - queue a flush
  * @bdev:	blockdev to issue flush for
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
  * @error_sector:	error sector
+ * @flags:	BLKDEV_IFL_* flags to control behaviour
  *
  * Description:
  *    Issue a flush for the block device in question. Caller can supply
  *    room for storing the error offset in case of a flush error, if they
- *    wish to.
+ *    wish to. If WAIT flag is not passed then caller may check only what
+ *    request was pushed in some internal queue for later handling.
  */
-int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
+int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
+		sector_t *error_sector, unsigned long flags)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
 	struct request_queue *q;
 	struct bio *bio;
-	int ret;
+	int ret = 0;
 
 	if (bdev->bd_disk == NULL)
 		return -ENXIO;
@@ -313,23 +311,34 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 	if (!q)
 		return -ENXIO;
 
-	bio = bio_alloc(GFP_KERNEL, 0);
+	/*
+	 * some block devices may not have their queue correctly set up here
+	 * (e.g. loop device without a backing file) and so issuing a flush
+	 * here will panic. Ensure there is a request function before issuing
+	 * the barrier.
+	 */
+	if (!q->make_request_fn)
+		return -ENXIO;
+
+	bio = bio_alloc(gfp_mask, 0);
 	bio->bi_end_io = bio_end_empty_barrier;
-	bio->bi_private = &wait;
 	bio->bi_bdev = bdev;
-	submit_bio(WRITE_BARRIER, bio);
+	if (test_bit(BLKDEV_WAIT, &flags))
+		bio->bi_private = &wait;
 
-	wait_for_completion(&wait);
-
-	/*
-	 * The driver must store the error location in ->bi_sector, if
-	 * it supports it. For non-stacked drivers, this should be copied
-	 * from blk_rq_pos(rq).
-	 */
-	if (error_sector)
-		*error_sector = bio->bi_sector;
+	bio_get(bio);
+	submit_bio(WRITE_BARRIER, bio);
+	if (test_bit(BLKDEV_WAIT, &flags)) {
+		wait_for_completion(&wait);
+		/*
+		 * The driver must store the error location in ->bi_sector, if
+		 * it supports it. For non-stacked drivers, this should be
+		 * copied from blk_rq_pos(rq).
+		 */
+		if (error_sector)
+			*error_sector = bio->bi_sector;
+	}
 
-	ret = 0;
 	if (bio_flagged(bio, BIO_EOPNOTSUPP))
 		ret = -EOPNOTSUPP;
 	else if (!bio_flagged(bio, BIO_UPTODATE))
@@ -339,107 +348,3 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_flush);
-
-static void blkdev_discard_end_io(struct bio *bio, int err)
-{
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	}
-
-	if (bio->bi_private)
-		complete(bio->bi_private);
-	__free_page(bio_page(bio));
-
-	bio_put(bio);
-}
-
-/**
- * blkdev_issue_discard - queue a discard
- * @bdev:	blockdev to issue discard for
- * @sector:	start sector
- * @nr_sects:	number of sectors to discard
- * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @flags:	DISCARD_FL_* flags to control behaviour
- *
- * Description:
- *    Issue a discard request for the sectors in question.
- */
-int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, int flags)
-{
-	DECLARE_COMPLETION_ONSTACK(wait);
-	struct request_queue *q = bdev_get_queue(bdev);
-	int type = flags & DISCARD_FL_BARRIER ?
-		DISCARD_BARRIER : DISCARD_NOBARRIER;
-	struct bio *bio;
-	struct page *page;
-	int ret = 0;
-
-	if (!q)
-		return -ENXIO;
-
-	if (!blk_queue_discard(q))
-		return -EOPNOTSUPP;
-
-	while (nr_sects && !ret) {
-		unsigned int sector_size = q->limits.logical_block_size;
-		unsigned int max_discard_sectors =
-			min(q->limits.max_discard_sectors, UINT_MAX >> 9);
-
-		bio = bio_alloc(gfp_mask, 1);
-		if (!bio)
-			goto out;
-		bio->bi_sector = sector;
-		bio->bi_end_io = blkdev_discard_end_io;
-		bio->bi_bdev = bdev;
-		if (flags & DISCARD_FL_WAIT)
-			bio->bi_private = &wait;
-
-		/*
-		 * Add a zeroed one-sector payload as that's what
-		 * our current implementations need.  If we'll ever need
-		 * more the interface will need revisiting.
-		 */
-		page = alloc_page(gfp_mask | __GFP_ZERO);
-		if (!page)
-			goto out_free_bio;
-		if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size)
-			goto out_free_page;
-
-		/*
-		 * And override the bio size - the way discard works we
-		 * touch many more blocks on disk than the actual payload
-		 * length.
-		 */
-		if (nr_sects > max_discard_sectors) {
-			bio->bi_size = max_discard_sectors << 9;
-			nr_sects -= max_discard_sectors;
-			sector += max_discard_sectors;
-		} else {
-			bio->bi_size = nr_sects << 9;
-			nr_sects = 0;
-		}
-
-		bio_get(bio);
-		submit_bio(type, bio);
-
-		if (flags & DISCARD_FL_WAIT)
-			wait_for_completion(&wait);
-
-		if (bio_flagged(bio, BIO_EOPNOTSUPP))
-			ret = -EOPNOTSUPP;
-		else if (!bio_flagged(bio, BIO_UPTODATE))
-			ret = -EIO;
-		bio_put(bio);
-	}
-	return ret;
-out_free_page:
-	__free_page(page);
-out_free_bio:
-	bio_put(bio);
-out:
-	return -ENOMEM;
-}
-EXPORT_SYMBOL(blkdev_issue_discard);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1fa2654db0a6..2fef1ef931a0 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -15,7 +15,12 @@
 #include <linux/kdev_t.h>
 #include <linux/module.h>
 #include <linux/err.h>
+#include <linux/blkdev.h>
+#include <linux/slab.h>
 #include "blk-cgroup.h"
+#include <linux/genhd.h>
+
+#define MAX_KEY_LEN 100
 
 static DEFINE_SPINLOCK(blkio_list_lock);
 static LIST_HEAD(blkio_list);
@@ -23,19 +28,56 @@ 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)
+static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,
+						  struct cgroup *);
+static int blkiocg_can_attach(struct cgroup_subsys *, struct cgroup *,
+			      struct task_struct *, bool);
+static void blkiocg_attach(struct cgroup_subsys *, struct cgroup *,
+			   struct cgroup *, struct task_struct *, bool);
+static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *);
+static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
+
+struct cgroup_subsys blkio_subsys = {
+	.name = "blkio",
+	.create = blkiocg_create,
+	.can_attach = blkiocg_can_attach,
+	.attach = blkiocg_attach,
+	.destroy = blkiocg_destroy,
+	.populate = blkiocg_populate,
+#ifdef CONFIG_BLK_CGROUP
+	/* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */
+	.subsys_id = blkio_subsys_id,
+#endif
+	.use_id = 1,
+	.module = THIS_MODULE,
+};
+EXPORT_SYMBOL_GPL(blkio_subsys);
+
+static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg,
+					    struct blkio_policy_node *pn)
 {
-	if (!css_tryget(&blkcg->css))
-		return false;
-	return true;
+	list_add(&pn->node, &blkcg->policy_list);
 }
-EXPORT_SYMBOL_GPL(blkiocg_css_tryget);
 
-void blkiocg_css_put(struct blkio_cgroup *blkcg)
+/* Must be called with blkcg->lock held */
+static inline void blkio_policy_delete_node(struct blkio_policy_node *pn)
 {
-	css_put(&blkcg->css);
+	list_del(&pn->node);
+}
+
+/* Must be called with blkcg->lock held */
+static struct blkio_policy_node *
+blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev)
+{
+	struct blkio_policy_node *pn;
+
+	list_for_each_entry(pn, &blkcg->policy_list, node) {
+		if (pn->dev == dev)
+			return pn;
+	}
+
+	return NULL;
 }
-EXPORT_SYMBOL_GPL(blkiocg_css_put);
 
 struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 {
@@ -44,13 +86,259 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 }
 EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
 
-void blkiocg_update_blkio_group_stats(struct blkio_group *blkg,
-			unsigned long time, unsigned long sectors)
+/*
+ * Add to the appropriate stat variable depending on the request type.
+ * This should be called with the blkg->stats_lock held.
+ */
+static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction,
+				bool sync)
+{
+	if (direction)
+		stat[BLKIO_STAT_WRITE] += add;
+	else
+		stat[BLKIO_STAT_READ] += add;
+	if (sync)
+		stat[BLKIO_STAT_SYNC] += add;
+	else
+		stat[BLKIO_STAT_ASYNC] += add;
+}
+
+/*
+ * Decrements the appropriate stat variable if non-zero depending on the
+ * request type. Panics on value being zero.
+ * This should be called with the blkg->stats_lock held.
+ */
+static void blkio_check_and_dec_stat(uint64_t *stat, bool direction, bool sync)
+{
+	if (direction) {
+		BUG_ON(stat[BLKIO_STAT_WRITE] == 0);
+		stat[BLKIO_STAT_WRITE]--;
+	} else {
+		BUG_ON(stat[BLKIO_STAT_READ] == 0);
+		stat[BLKIO_STAT_READ]--;
+	}
+	if (sync) {
+		BUG_ON(stat[BLKIO_STAT_SYNC] == 0);
+		stat[BLKIO_STAT_SYNC]--;
+	} else {
+		BUG_ON(stat[BLKIO_STAT_ASYNC] == 0);
+		stat[BLKIO_STAT_ASYNC]--;
+	}
+}
+
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+/* This should be called with the blkg->stats_lock held. */
+static void blkio_set_start_group_wait_time(struct blkio_group *blkg,
+						struct blkio_group *curr_blkg)
+{
+	if (blkio_blkg_waiting(&blkg->stats))
+		return;
+	if (blkg == curr_blkg)
+		return;
+	blkg->stats.start_group_wait_time = sched_clock();
+	blkio_mark_blkg_waiting(&blkg->stats);
+}
+
+/* This should be called with the blkg->stats_lock held. */
+static void blkio_update_group_wait_time(struct blkio_group_stats *stats)
+{
+	unsigned long long now;
+
+	if (!blkio_blkg_waiting(stats))
+		return;
+
+	now = sched_clock();
+	if (time_after64(now, stats->start_group_wait_time))
+		stats->group_wait_time += now - stats->start_group_wait_time;
+	blkio_clear_blkg_waiting(stats);
+}
+
+/* This should be called with the blkg->stats_lock held. */
+static void blkio_end_empty_time(struct blkio_group_stats *stats)
+{
+	unsigned long long now;
+
+	if (!blkio_blkg_empty(stats))
+		return;
+
+	now = sched_clock();
+	if (time_after64(now, stats->start_empty_time))
+		stats->empty_time += now - stats->start_empty_time;
+	blkio_clear_blkg_empty(stats);
+}
+
+void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	BUG_ON(blkio_blkg_idling(&blkg->stats));
+	blkg->stats.start_idle_time = sched_clock();
+	blkio_mark_blkg_idling(&blkg->stats);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_set_idle_time_stats);
+
+void blkiocg_update_idle_time_stats(struct blkio_group *blkg)
+{
+	unsigned long flags;
+	unsigned long long now;
+	struct blkio_group_stats *stats;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	stats = &blkg->stats;
+	if (blkio_blkg_idling(stats)) {
+		now = sched_clock();
+		if (time_after64(now, stats->start_idle_time))
+			stats->idle_time += now - stats->start_idle_time;
+		blkio_clear_blkg_idling(stats);
+	}
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_idle_time_stats);
+
+void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg)
+{
+	unsigned long flags;
+	struct blkio_group_stats *stats;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	stats = &blkg->stats;
+	stats->avg_queue_size_sum +=
+			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] +
+			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE];
+	stats->avg_queue_size_samples++;
+	blkio_update_group_wait_time(stats);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_avg_queue_size_stats);
+
+void blkiocg_set_start_empty_time(struct blkio_group *blkg)
+{
+	unsigned long flags;
+	struct blkio_group_stats *stats;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	stats = &blkg->stats;
+
+	if (stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] ||
+			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]) {
+		spin_unlock_irqrestore(&blkg->stats_lock, flags);
+		return;
+	}
+
+	/*
+	 * group is already marked empty. This can happen if cfqq got new
+	 * request in parent group and moved to this group while being added
+	 * to service tree. Just ignore the event and move on.
+	 */
+	if(blkio_blkg_empty(stats)) {
+		spin_unlock_irqrestore(&blkg->stats_lock, flags);
+		return;
+	}
+
+	stats->start_empty_time = sched_clock();
+	blkio_mark_blkg_empty(stats);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_set_start_empty_time);
+
+void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
+			unsigned long dequeue)
+{
+	blkg->stats.dequeue += dequeue;
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats);
+#else
+static inline void blkio_set_start_group_wait_time(struct blkio_group *blkg,
+					struct blkio_group *curr_blkg) {}
+static inline void blkio_end_empty_time(struct blkio_group_stats *stats) {}
+#endif
+
+void blkiocg_update_io_add_stats(struct blkio_group *blkg,
+			struct blkio_group *curr_blkg, bool direction,
+			bool sync)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED], 1, direction,
+			sync);
+	blkio_end_empty_time(&blkg->stats);
+	blkio_set_start_group_wait_time(blkg, curr_blkg);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_io_add_stats);
+
+void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
+						bool direction, bool sync)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	blkio_check_and_dec_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED],
+					direction, sync);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_io_remove_stats);
+
+void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	blkg->stats.time += time;
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);
+
+void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
+				uint64_t bytes, bool direction, bool sync)
+{
+	struct blkio_group_stats *stats;
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	stats = &blkg->stats;
+	stats->sectors += bytes >> 9;
+	blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICED], 1, direction,
+			sync);
+	blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_BYTES], bytes,
+			direction, sync);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats);
+
+void blkiocg_update_completion_stats(struct blkio_group *blkg,
+	uint64_t start_time, uint64_t io_start_time, bool direction, bool sync)
 {
-	blkg->time += time;
-	blkg->sectors += sectors;
+	struct blkio_group_stats *stats;
+	unsigned long flags;
+	unsigned long long now = sched_clock();
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	stats = &blkg->stats;
+	if (time_after64(now, io_start_time))
+		blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_TIME],
+				now - io_start_time, direction, sync);
+	if (time_after64(io_start_time, start_time))
+		blkio_add_stat(stats->stat_arr[BLKIO_STAT_WAIT_TIME],
+				io_start_time - start_time, direction, sync);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
 }
-EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_stats);
+EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats);
+
+void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
+					bool sync)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_MERGED], 1, direction,
+			sync);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
 
 void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 			struct blkio_group *blkg, void *key, dev_t dev)
@@ -58,14 +346,13 @@ void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 	unsigned long flags;
 
 	spin_lock_irqsave(&blkcg->lock, flags);
+	spin_lock_init(&blkg->stats_lock);
 	rcu_assign_pointer(blkg->key, key);
 	blkg->blkcg_id = css_id(&blkcg->css);
 	hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
 	spin_unlock_irqrestore(&blkcg->lock, flags);
-#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* Need to take css reference ? */
 	cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
-#endif
 	blkg->dev = dev;
 }
 EXPORT_SYMBOL_GPL(blkiocg_add_blkio_group);
@@ -89,17 +376,16 @@ int blkiocg_del_blkio_group(struct blkio_group *blkg)
 
 	rcu_read_lock();
 	css = css_lookup(&blkio_subsys, blkg->blkcg_id);
-	if (!css)
-		goto out;
-
-	blkcg = container_of(css, struct blkio_cgroup, css);
-	spin_lock_irqsave(&blkcg->lock, flags);
-	if (!hlist_unhashed(&blkg->blkcg_node)) {
-		__blkiocg_del_blkio_group(blkg);
-		ret = 0;
+	if (css) {
+		blkcg = container_of(css, struct blkio_cgroup, css);
+		spin_lock_irqsave(&blkcg->lock, flags);
+		if (!hlist_unhashed(&blkg->blkcg_node)) {
+			__blkiocg_del_blkio_group(blkg);
+			ret = 0;
+		}
+		spin_unlock_irqrestore(&blkcg->lock, flags);
 	}
-	spin_unlock_irqrestore(&blkcg->lock, flags);
-out:
+
 	rcu_read_unlock();
 	return ret;
 }
@@ -142,31 +428,179 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
 	struct blkio_group *blkg;
 	struct hlist_node *n;
 	struct blkio_policy_type *blkiop;
+	struct blkio_policy_node *pn;
 
 	if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
 		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);
+		pn = blkio_policy_search_node(blkcg, blkg->dev);
+
+		if (pn)
+			continue;
+
 		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;
 }
 
-#define SHOW_FUNCTION_PER_GROUP(__VAR)					\
+static int
+blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
+{
+	struct blkio_cgroup *blkcg;
+	struct blkio_group *blkg;
+	struct blkio_group_stats *stats;
+	struct hlist_node *n;
+	uint64_t queued[BLKIO_STAT_TOTAL];
+	int i;
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	bool idling, waiting, empty;
+	unsigned long long now = sched_clock();
+#endif
+
+	blkcg = cgroup_to_blkio_cgroup(cgroup);
+	spin_lock_irq(&blkcg->lock);
+	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
+		spin_lock(&blkg->stats_lock);
+		stats = &blkg->stats;
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+		idling = blkio_blkg_idling(stats);
+		waiting = blkio_blkg_waiting(stats);
+		empty = blkio_blkg_empty(stats);
+#endif
+		for (i = 0; i < BLKIO_STAT_TOTAL; i++)
+			queued[i] = stats->stat_arr[BLKIO_STAT_QUEUED][i];
+		memset(stats, 0, sizeof(struct blkio_group_stats));
+		for (i = 0; i < BLKIO_STAT_TOTAL; i++)
+			stats->stat_arr[BLKIO_STAT_QUEUED][i] = queued[i];
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+		if (idling) {
+			blkio_mark_blkg_idling(stats);
+			stats->start_idle_time = now;
+		}
+		if (waiting) {
+			blkio_mark_blkg_waiting(stats);
+			stats->start_group_wait_time = now;
+		}
+		if (empty) {
+			blkio_mark_blkg_empty(stats);
+			stats->start_empty_time = now;
+		}
+#endif
+		spin_unlock(&blkg->stats_lock);
+	}
+	spin_unlock_irq(&blkcg->lock);
+	return 0;
+}
+
+static void blkio_get_key_name(enum stat_sub_type type, dev_t dev, char *str,
+				int chars_left, bool diskname_only)
+{
+	snprintf(str, chars_left, "%d:%d", MAJOR(dev), MINOR(dev));
+	chars_left -= strlen(str);
+	if (chars_left <= 0) {
+		printk(KERN_WARNING
+			"Possibly incorrect cgroup stat display format");
+		return;
+	}
+	if (diskname_only)
+		return;
+	switch (type) {
+	case BLKIO_STAT_READ:
+		strlcat(str, " Read", chars_left);
+		break;
+	case BLKIO_STAT_WRITE:
+		strlcat(str, " Write", chars_left);
+		break;
+	case BLKIO_STAT_SYNC:
+		strlcat(str, " Sync", chars_left);
+		break;
+	case BLKIO_STAT_ASYNC:
+		strlcat(str, " Async", chars_left);
+		break;
+	case BLKIO_STAT_TOTAL:
+		strlcat(str, " Total", chars_left);
+		break;
+	default:
+		strlcat(str, " Invalid", chars_left);
+	}
+}
+
+static uint64_t blkio_fill_stat(char *str, int chars_left, uint64_t val,
+				struct cgroup_map_cb *cb, dev_t dev)
+{
+	blkio_get_key_name(0, dev, str, chars_left, true);
+	cb->fill(cb, str, val);
+	return val;
+}
+
+/* This should be called with blkg->stats_lock held */
+static uint64_t blkio_get_stat(struct blkio_group *blkg,
+		struct cgroup_map_cb *cb, dev_t dev, enum stat_type type)
+{
+	uint64_t disk_total;
+	char key_str[MAX_KEY_LEN];
+	enum stat_sub_type sub_type;
+
+	if (type == BLKIO_STAT_TIME)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.time, cb, dev);
+	if (type == BLKIO_STAT_SECTORS)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.sectors, cb, dev);
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	if (type == BLKIO_STAT_AVG_QUEUE_SIZE) {
+		uint64_t sum = blkg->stats.avg_queue_size_sum;
+		uint64_t samples = blkg->stats.avg_queue_size_samples;
+		if (samples)
+			do_div(sum, samples);
+		else
+			sum = 0;
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, sum, cb, dev);
+	}
+	if (type == BLKIO_STAT_GROUP_WAIT_TIME)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.group_wait_time, cb, dev);
+	if (type == BLKIO_STAT_IDLE_TIME)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.idle_time, cb, dev);
+	if (type == BLKIO_STAT_EMPTY_TIME)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.empty_time, cb, dev);
+	if (type == BLKIO_STAT_DEQUEUE)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.dequeue, cb, dev);
+#endif
+
+	for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL;
+			sub_type++) {
+		blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false);
+		cb->fill(cb, key_str, blkg->stats.stat_arr[type][sub_type]);
+	}
+	disk_total = blkg->stats.stat_arr[type][BLKIO_STAT_READ] +
+			blkg->stats.stat_arr[type][BLKIO_STAT_WRITE];
+	blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false);
+	cb->fill(cb, key_str, disk_total);
+	return disk_total;
+}
+
+#define SHOW_FUNCTION_PER_GROUP(__VAR, type, show_total)		\
 static int blkiocg_##__VAR##_read(struct cgroup *cgroup,		\
-			struct cftype *cftype, struct seq_file *m)	\
+		struct cftype *cftype, struct cgroup_map_cb *cb)	\
 {									\
 	struct blkio_cgroup *blkcg;					\
 	struct blkio_group *blkg;					\
 	struct hlist_node *n;						\
+	uint64_t cgroup_total = 0;					\
 									\
 	if (!cgroup_lock_live_group(cgroup))				\
 		return -ENODEV;						\
@@ -174,50 +608,293 @@ static int blkiocg_##__VAR##_read(struct cgroup *cgroup,		\
 	blkcg = cgroup_to_blkio_cgroup(cgroup);				\
 	rcu_read_lock();						\
 	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {\
-		if (blkg->dev)						\
-			seq_printf(m, "%u:%u %lu\n", MAJOR(blkg->dev),	\
-				 MINOR(blkg->dev), blkg->__VAR);	\
+		if (blkg->dev) {					\
+			spin_lock_irq(&blkg->stats_lock);		\
+			cgroup_total += blkio_get_stat(blkg, cb,	\
+						blkg->dev, type);	\
+			spin_unlock_irq(&blkg->stats_lock);		\
+		}							\
 	}								\
+	if (show_total)							\
+		cb->fill(cb, "Total", cgroup_total);			\
 	rcu_read_unlock();						\
 	cgroup_unlock();						\
 	return 0;							\
 }
 
-SHOW_FUNCTION_PER_GROUP(time);
-SHOW_FUNCTION_PER_GROUP(sectors);
+SHOW_FUNCTION_PER_GROUP(time, BLKIO_STAT_TIME, 0);
+SHOW_FUNCTION_PER_GROUP(sectors, BLKIO_STAT_SECTORS, 0);
+SHOW_FUNCTION_PER_GROUP(io_service_bytes, BLKIO_STAT_SERVICE_BYTES, 1);
+SHOW_FUNCTION_PER_GROUP(io_serviced, BLKIO_STAT_SERVICED, 1);
+SHOW_FUNCTION_PER_GROUP(io_service_time, BLKIO_STAT_SERVICE_TIME, 1);
+SHOW_FUNCTION_PER_GROUP(io_wait_time, BLKIO_STAT_WAIT_TIME, 1);
+SHOW_FUNCTION_PER_GROUP(io_merged, BLKIO_STAT_MERGED, 1);
+SHOW_FUNCTION_PER_GROUP(io_queued, BLKIO_STAT_QUEUED, 1);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
-SHOW_FUNCTION_PER_GROUP(dequeue);
+SHOW_FUNCTION_PER_GROUP(dequeue, BLKIO_STAT_DEQUEUE, 0);
+SHOW_FUNCTION_PER_GROUP(avg_queue_size, BLKIO_STAT_AVG_QUEUE_SIZE, 0);
+SHOW_FUNCTION_PER_GROUP(group_wait_time, BLKIO_STAT_GROUP_WAIT_TIME, 0);
+SHOW_FUNCTION_PER_GROUP(idle_time, BLKIO_STAT_IDLE_TIME, 0);
+SHOW_FUNCTION_PER_GROUP(empty_time, BLKIO_STAT_EMPTY_TIME, 0);
 #endif
 #undef SHOW_FUNCTION_PER_GROUP
 
-#ifdef CONFIG_DEBUG_BLK_CGROUP
-void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg,
-			unsigned long dequeue)
+static int blkio_check_dev_num(dev_t dev)
 {
-	blkg->dequeue += dequeue;
+	int part = 0;
+	struct gendisk *disk;
+
+	disk = get_gendisk(dev, &part);
+	if (!disk || part)
+		return -ENODEV;
+
+	return 0;
+}
+
+static int blkio_policy_parse_and_set(char *buf,
+				      struct blkio_policy_node *newpn)
+{
+	char *s[4], *p, *major_s = NULL, *minor_s = NULL;
+	int ret;
+	unsigned long major, minor, temp;
+	int i = 0;
+	dev_t dev;
+
+	memset(s, 0, sizeof(s));
+
+	while ((p = strsep(&buf, " ")) != NULL) {
+		if (!*p)
+			continue;
+
+		s[i++] = p;
+
+		/* Prevent from inputing too many things */
+		if (i == 3)
+			break;
+	}
+
+	if (i != 2)
+		return -EINVAL;
+
+	p = strsep(&s[0], ":");
+	if (p != NULL)
+		major_s = p;
+	else
+		return -EINVAL;
+
+	minor_s = s[0];
+	if (!minor_s)
+		return -EINVAL;
+
+	ret = strict_strtoul(major_s, 10, &major);
+	if (ret)
+		return -EINVAL;
+
+	ret = strict_strtoul(minor_s, 10, &minor);
+	if (ret)
+		return -EINVAL;
+
+	dev = MKDEV(major, minor);
+
+	ret = blkio_check_dev_num(dev);
+	if (ret)
+		return ret;
+
+	newpn->dev = dev;
+
+	if (s[1] == NULL)
+		return -EINVAL;
+
+	ret = strict_strtoul(s[1], 10, &temp);
+	if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) ||
+	    temp > BLKIO_WEIGHT_MAX)
+		return -EINVAL;
+
+	newpn->weight =  temp;
+
+	return 0;
+}
+
+unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
+			      dev_t dev)
+{
+	struct blkio_policy_node *pn;
+
+	pn = blkio_policy_search_node(blkcg, dev);
+	if (pn)
+		return pn->weight;
+	else
+		return blkcg->weight;
+}
+EXPORT_SYMBOL_GPL(blkcg_get_weight);
+
+
+static int blkiocg_weight_device_write(struct cgroup *cgrp, struct cftype *cft,
+				       const char *buffer)
+{
+	int ret = 0;
+	char *buf;
+	struct blkio_policy_node *newpn, *pn;
+	struct blkio_cgroup *blkcg;
+	struct blkio_group *blkg;
+	int keep_newpn = 0;
+	struct hlist_node *n;
+	struct blkio_policy_type *blkiop;
+
+	buf = kstrdup(buffer, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	newpn = kzalloc(sizeof(*newpn), GFP_KERNEL);
+	if (!newpn) {
+		ret = -ENOMEM;
+		goto free_buf;
+	}
+
+	ret = blkio_policy_parse_and_set(buf, newpn);
+	if (ret)
+		goto free_newpn;
+
+	blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+	spin_lock_irq(&blkcg->lock);
+
+	pn = blkio_policy_search_node(blkcg, newpn->dev);
+	if (!pn) {
+		if (newpn->weight != 0) {
+			blkio_policy_insert_node(blkcg, newpn);
+			keep_newpn = 1;
+		}
+		spin_unlock_irq(&blkcg->lock);
+		goto update_io_group;
+	}
+
+	if (newpn->weight == 0) {
+		/* weight == 0 means deleteing a specific weight */
+		blkio_policy_delete_node(pn);
+		spin_unlock_irq(&blkcg->lock);
+		goto update_io_group;
+	}
+	spin_unlock_irq(&blkcg->lock);
+
+	pn->weight = newpn->weight;
+
+update_io_group:
+	/* update weight for each cfqg */
+	spin_lock(&blkio_list_lock);
+	spin_lock_irq(&blkcg->lock);
+
+	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
+		if (newpn->dev == blkg->dev) {
+			list_for_each_entry(blkiop, &blkio_list, list)
+				blkiop->ops.blkio_update_group_weight_fn(blkg,
+							 newpn->weight ?
+							 newpn->weight :
+							 blkcg->weight);
+		}
+	}
+
+	spin_unlock_irq(&blkcg->lock);
+	spin_unlock(&blkio_list_lock);
+
+free_newpn:
+	if (!keep_newpn)
+		kfree(newpn);
+free_buf:
+	kfree(buf);
+	return ret;
+}
+
+static int blkiocg_weight_device_read(struct cgroup *cgrp, struct cftype *cft,
+				      struct seq_file *m)
+{
+	struct blkio_cgroup *blkcg;
+	struct blkio_policy_node *pn;
+
+	seq_printf(m, "dev\tweight\n");
+
+	blkcg = cgroup_to_blkio_cgroup(cgrp);
+	if (!list_empty(&blkcg->policy_list)) {
+		spin_lock_irq(&blkcg->lock);
+		list_for_each_entry(pn, &blkcg->policy_list, node) {
+			seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
+				   MINOR(pn->dev), pn->weight);
+		}
+		spin_unlock_irq(&blkcg->lock);
+	}
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_dequeue_stats);
-#endif
 
 struct cftype blkio_files[] = {
 	{
+		.name = "weight_device",
+		.read_seq_string = blkiocg_weight_device_read,
+		.write_string = blkiocg_weight_device_write,
+		.max_write_len = 256,
+	},
+	{
 		.name = "weight",
 		.read_u64 = blkiocg_weight_read,
 		.write_u64 = blkiocg_weight_write,
 	},
 	{
 		.name = "time",
-		.read_seq_string = blkiocg_time_read,
+		.read_map = blkiocg_time_read,
 	},
 	{
 		.name = "sectors",
-		.read_seq_string = blkiocg_sectors_read,
+		.read_map = blkiocg_sectors_read,
+	},
+	{
+		.name = "io_service_bytes",
+		.read_map = blkiocg_io_service_bytes_read,
+	},
+	{
+		.name = "io_serviced",
+		.read_map = blkiocg_io_serviced_read,
+	},
+	{
+		.name = "io_service_time",
+		.read_map = blkiocg_io_service_time_read,
+	},
+	{
+		.name = "io_wait_time",
+		.read_map = blkiocg_io_wait_time_read,
+	},
+	{
+		.name = "io_merged",
+		.read_map = blkiocg_io_merged_read,
+	},
+	{
+		.name = "io_queued",
+		.read_map = blkiocg_io_queued_read,
+	},
+	{
+		.name = "reset_stats",
+		.write_u64 = blkiocg_reset_stats,
 	},
 #ifdef CONFIG_DEBUG_BLK_CGROUP
-       {
+	{
+		.name = "avg_queue_size",
+		.read_map = blkiocg_avg_queue_size_read,
+	},
+	{
+		.name = "group_wait_time",
+		.read_map = blkiocg_group_wait_time_read,
+	},
+	{
+		.name = "idle_time",
+		.read_map = blkiocg_idle_time_read,
+	},
+	{
+		.name = "empty_time",
+		.read_map = blkiocg_empty_time_read,
+	},
+	{
 		.name = "dequeue",
-		.read_seq_string = blkiocg_dequeue_read,
-       },
+		.read_map = blkiocg_dequeue_read,
+	},
 #endif
 };
 
@@ -234,56 +911,62 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 	struct blkio_group *blkg;
 	void *key;
 	struct blkio_policy_type *blkiop;
+	struct blkio_policy_node *pn, *pntmp;
 
 	rcu_read_lock();
-remove_entry:
-	spin_lock_irqsave(&blkcg->lock, flags);
+	do {
+		spin_lock_irqsave(&blkcg->lock, flags);
+
+		if (hlist_empty(&blkcg->blkg_list)) {
+			spin_unlock_irqrestore(&blkcg->lock, flags);
+			break;
+		}
+
+		blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group,
+					blkcg_node);
+		key = rcu_dereference(blkg->key);
+		__blkiocg_del_blkio_group(blkg);
 
-	if (hlist_empty(&blkcg->blkg_list)) {
 		spin_unlock_irqrestore(&blkcg->lock, flags);
-		goto done;
-	}
 
-	blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group,
-				blkcg_node);
-	key = rcu_dereference(blkg->key);
-	__blkiocg_del_blkio_group(blkg);
+		/*
+		 * This blkio_group is being unlinked as associated cgroup is
+		 * going away. Let all the IO controlling policies know about
+		 * this event. Currently this is static call to one io
+		 * controlling policy. Once we have more policies in place, we
+		 * need some dynamic registration of callback function.
+		 */
+		spin_lock(&blkio_list_lock);
+		list_for_each_entry(blkiop, &blkio_list, list)
+			blkiop->ops.blkio_unlink_group_fn(key, blkg);
+		spin_unlock(&blkio_list_lock);
+	} while (1);
 
-	spin_unlock_irqrestore(&blkcg->lock, flags);
+	list_for_each_entry_safe(pn, pntmp, &blkcg->policy_list, node) {
+		blkio_policy_delete_node(pn);
+		kfree(pn);
+	}
 
-	/*
-	 * This blkio_group is being unlinked as associated cgroup is going
-	 * away. Let all the IO controlling policies know about this event.
-	 *
-	 * Currently this is static call to one io controlling policy. Once
-	 * we have more policies in place, we need some dynamic registration
-	 * of callback function.
-	 */
-	spin_lock(&blkio_list_lock);
-	list_for_each_entry(blkiop, &blkio_list, list)
-		blkiop->ops.blkio_unlink_group_fn(key, blkg);
-	spin_unlock(&blkio_list_lock);
-	goto remove_entry;
-done:
 	free_css_id(&blkio_subsys, &blkcg->css);
 	rcu_read_unlock();
-	kfree(blkcg);
+	if (blkcg != &blkio_root_cgroup)
+		kfree(blkcg);
 }
 
 static struct cgroup_subsys_state *
 blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 {
-	struct blkio_cgroup *blkcg, *parent_blkcg;
+	struct blkio_cgroup *blkcg;
+	struct cgroup *parent = cgroup->parent;
 
-	if (!cgroup->parent) {
+	if (!parent) {
 		blkcg = &blkio_root_cgroup;
 		goto done;
 	}
 
 	/* Currently we do not support hierarchy deeper than two level (0,1) */
-	parent_blkcg = cgroup_to_blkio_cgroup(cgroup->parent);
-	if (css_depth(&parent_blkcg->css) > 0)
-		return ERR_PTR(-EINVAL);
+	if (parent != cgroup->top_cgroup)
+		return ERR_PTR(-EPERM);
 
 	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
 	if (!blkcg)
@@ -294,6 +977,7 @@ done:
 	spin_lock_init(&blkcg->lock);
 	INIT_HLIST_HEAD(&blkcg->blkg_list);
 
+	INIT_LIST_HEAD(&blkcg->policy_list);
 	return &blkcg->css;
 }
 
@@ -333,17 +1017,6 @@ static void blkiocg_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup,
 	task_unlock(tsk);
 }
 
-struct cgroup_subsys blkio_subsys = {
-	.name = "blkio",
-	.create = blkiocg_create,
-	.can_attach = blkiocg_can_attach,
-	.attach = blkiocg_attach,
-	.destroy = blkiocg_destroy,
-	.populate = blkiocg_populate,
-	.subsys_id = blkio_subsys_id,
-	.use_id = 1,
-};
-
 void blkio_policy_register(struct blkio_policy_type *blkiop)
 {
 	spin_lock(&blkio_list_lock);
@@ -359,3 +1032,17 @@ void blkio_policy_unregister(struct blkio_policy_type *blkiop)
 	spin_unlock(&blkio_list_lock);
 }
 EXPORT_SYMBOL_GPL(blkio_policy_unregister);
+
+static int __init init_cgroup_blkio(void)
+{
+	return cgroup_load_subsys(&blkio_subsys);
+}
+
+static void __exit exit_cgroup_blkio(void)
+{
+	cgroup_unload_subsys(&blkio_subsys);
+}
+
+module_init(init_cgroup_blkio);
+module_exit(exit_cgroup_blkio);
+MODULE_LICENSE("GPL");
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 4d316df863b4..2b866ec1dcea 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -15,13 +15,92 @@
 
 #include <linux/cgroup.h>
 
-#ifdef CONFIG_BLK_CGROUP
+#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
+
+#ifndef CONFIG_BLK_CGROUP
+/* When blk-cgroup is a module, its subsys_id isn't a compile-time constant */
+extern struct cgroup_subsys blkio_subsys;
+#define blkio_subsys_id blkio_subsys.subsys_id
+#endif
+
+enum stat_type {
+	/* Total time spent (in ns) between request dispatch to the driver and
+	 * request completion for IOs doen by this cgroup. This may not be
+	 * accurate when NCQ is turned on. */
+	BLKIO_STAT_SERVICE_TIME = 0,
+	/* Total bytes transferred */
+	BLKIO_STAT_SERVICE_BYTES,
+	/* Total IOs serviced, post merge */
+	BLKIO_STAT_SERVICED,
+	/* Total time spent waiting in scheduler queue in ns */
+	BLKIO_STAT_WAIT_TIME,
+	/* Number of IOs merged */
+	BLKIO_STAT_MERGED,
+	/* Number of IOs queued up */
+	BLKIO_STAT_QUEUED,
+	/* All the single valued stats go below this */
+	BLKIO_STAT_TIME,
+	BLKIO_STAT_SECTORS,
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	BLKIO_STAT_AVG_QUEUE_SIZE,
+	BLKIO_STAT_IDLE_TIME,
+	BLKIO_STAT_EMPTY_TIME,
+	BLKIO_STAT_GROUP_WAIT_TIME,
+	BLKIO_STAT_DEQUEUE
+#endif
+};
+
+enum stat_sub_type {
+	BLKIO_STAT_READ = 0,
+	BLKIO_STAT_WRITE,
+	BLKIO_STAT_SYNC,
+	BLKIO_STAT_ASYNC,
+	BLKIO_STAT_TOTAL
+};
+
+/* blkg state flags */
+enum blkg_state_flags {
+	BLKG_waiting = 0,
+	BLKG_idling,
+	BLKG_empty,
+};
 
 struct blkio_cgroup {
 	struct cgroup_subsys_state css;
 	unsigned int weight;
 	spinlock_t lock;
 	struct hlist_head blkg_list;
+	struct list_head policy_list; /* list of blkio_policy_node */
+};
+
+struct blkio_group_stats {
+	/* total disk time and nr sectors dispatched by this group */
+	uint64_t time;
+	uint64_t sectors;
+	uint64_t stat_arr[BLKIO_STAT_QUEUED + 1][BLKIO_STAT_TOTAL];
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	/* Sum of number of IOs queued across all samples */
+	uint64_t avg_queue_size_sum;
+	/* Count of samples taken for average */
+	uint64_t avg_queue_size_samples;
+	/* How many times this group has been removed from service tree */
+	unsigned long dequeue;
+
+	/* Total time spent waiting for it to be assigned a timeslice. */
+	uint64_t group_wait_time;
+	uint64_t start_group_wait_time;
+
+	/* Time spent idling for this blkio_group */
+	uint64_t idle_time;
+	uint64_t start_idle_time;
+	/*
+	 * Total time when we have requests queued and do not contain the
+	 * current active queue.
+	 */
+	uint64_t empty_time;
+	uint64_t start_empty_time;
+	uint16_t flags;
+#endif
 };
 
 struct blkio_group {
@@ -29,22 +108,24 @@ struct blkio_group {
 	void *key;
 	struct hlist_node blkcg_node;
 	unsigned short blkcg_id;
-#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* Store cgroup path */
 	char path[128];
-	/* How many times this group has been removed from service tree */
-	unsigned long dequeue;
-#endif
 	/* The device MKDEV(major, minor), this group has been created for */
-	dev_t   dev;
+	dev_t dev;
 
-	/* total disk time and nr sectors dispatched by this group */
-	unsigned long time;
-	unsigned long sectors;
+	/* Need to serialize the stats in the case of reset/update */
+	spinlock_t stats_lock;
+	struct blkio_group_stats stats;
+};
+
+struct blkio_policy_node {
+	struct list_head node;
+	dev_t dev;
+	unsigned int weight;
 };
 
-extern bool blkiocg_css_tryget(struct blkio_cgroup *blkcg);
-extern void blkiocg_css_put(struct blkio_cgroup *blkcg);
+extern unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
+				     dev_t dev);
 
 typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg);
 typedef void (blkio_update_group_weight_fn) (struct blkio_group *blkg,
@@ -64,6 +145,11 @@ struct blkio_policy_type {
 extern void blkio_policy_register(struct blkio_policy_type *);
 extern void blkio_policy_unregister(struct blkio_policy_type *);
 
+static inline char *blkg_path(struct blkio_group *blkg)
+{
+	return blkg->path;
+}
+
 #else
 
 struct blkio_group {
@@ -75,6 +161,8 @@ struct blkio_policy_type {
 static inline void blkio_policy_register(struct blkio_policy_type *blkiop) { }
 static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { }
 
+static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }
+
 #endif
 
 #define BLKIO_WEIGHT_MIN	100
@@ -82,19 +170,45 @@ static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { }
 #define BLKIO_WEIGHT_DEFAULT	500
 
 #ifdef CONFIG_DEBUG_BLK_CGROUP
-static inline char *blkg_path(struct blkio_group *blkg)
-{
-	return blkg->path;
-}
-void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg,
+void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg);
+void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
 				unsigned long dequeue);
+void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg);
+void blkiocg_update_idle_time_stats(struct blkio_group *blkg);
+void blkiocg_set_start_empty_time(struct blkio_group *blkg);
+
+#define BLKG_FLAG_FNS(name)						\
+static inline void blkio_mark_blkg_##name(				\
+		struct blkio_group_stats *stats)			\
+{									\
+	stats->flags |= (1 << BLKG_##name);				\
+}									\
+static inline void blkio_clear_blkg_##name(				\
+		struct blkio_group_stats *stats)			\
+{									\
+	stats->flags &= ~(1 << BLKG_##name);				\
+}									\
+static inline int blkio_blkg_##name(struct blkio_group_stats *stats)	\
+{									\
+	return (stats->flags & (1 << BLKG_##name)) != 0;		\
+}									\
+
+BLKG_FLAG_FNS(waiting)
+BLKG_FLAG_FNS(idling)
+BLKG_FLAG_FNS(empty)
+#undef BLKG_FLAG_FNS
 #else
-static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }
-static inline void blkiocg_update_blkio_group_dequeue_stats(
-			struct blkio_group *blkg, unsigned long dequeue) {}
+static inline void blkiocg_update_avg_queue_size_stats(
+						struct blkio_group *blkg) {}
+static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
+						unsigned long dequeue) {}
+static inline void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg)
+{}
+static inline void blkiocg_update_idle_time_stats(struct blkio_group *blkg) {}
+static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {}
 #endif
 
-#ifdef CONFIG_BLK_CGROUP
+#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
 extern struct blkio_cgroup blkio_root_cgroup;
 extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
 extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
@@ -102,26 +216,43 @@ extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
 extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
 						void *key);
-void blkiocg_update_blkio_group_stats(struct blkio_group *blkg,
-			unsigned long time, unsigned long sectors);
+void blkiocg_update_timeslice_used(struct blkio_group *blkg,
+					unsigned long time);
+void blkiocg_update_dispatch_stats(struct blkio_group *blkg, uint64_t bytes,
+						bool direction, bool sync);
+void blkiocg_update_completion_stats(struct blkio_group *blkg,
+	uint64_t start_time, uint64_t io_start_time, bool direction, bool sync);
+void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
+					bool sync);
+void blkiocg_update_io_add_stats(struct blkio_group *blkg,
+		struct blkio_group *curr_blkg, bool direction, bool sync);
+void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
+					bool direction, bool sync);
 #else
 struct cgroup;
 static inline struct blkio_cgroup *
 cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
 
 static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-			struct blkio_group *blkg, void *key, dev_t dev)
-{
-}
+			struct blkio_group *blkg, void *key, dev_t dev) {}
 
 static inline int
 blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
 
 static inline struct blkio_group *
 blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; }
-static inline void blkiocg_update_blkio_group_stats(struct blkio_group *blkg,
-			unsigned long time, unsigned long sectors)
-{
-}
+static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg,
+						unsigned long time) {}
+static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
+				uint64_t bytes, bool direction, bool sync) {}
+static inline void blkiocg_update_completion_stats(struct blkio_group *blkg,
+		uint64_t start_time, uint64_t io_start_time, bool direction,
+		bool sync) {}
+static inline void blkiocg_update_io_merged_stats(struct blkio_group *blkg,
+						bool direction, bool sync) {}
+static inline void blkiocg_update_io_add_stats(struct blkio_group *blkg,
+		struct blkio_group *curr_blkg, bool direction, bool sync) {}
+static inline void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
+						bool direction, bool sync) {}
 #endif
 #endif /* _BLK_CGROUP_H */
diff --git a/block/blk-core.c b/block/blk-core.c
index 718897e6d37f..32a1c123dfb3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -127,6 +127,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->tag = -1;
 	rq->ref_count = 1;
 	rq->start_time = jiffies;
+	set_start_time_ns(rq);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -183,7 +184,7 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 	printk(KERN_INFO "  bio %p, biotail %p, buffer %p, len %u\n",
 	       rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));
 
-	if (blk_pc_request(rq)) {
+	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		printk(KERN_INFO "  cdb: ");
 		for (bit = 0; bit < BLK_MAX_CDB; bit++)
 			printk("%02x ", rq->cmd[bit]);
@@ -450,6 +451,7 @@ void blk_cleanup_queue(struct request_queue *q)
 	 */
 	blk_sync_queue(q);
 
+	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
 	mutex_lock(&q->sysfs_lock);
 	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
 	mutex_unlock(&q->sysfs_lock);
@@ -465,6 +467,9 @@ static int blk_init_free_list(struct request_queue *q)
 {
 	struct request_list *rl = &q->rq;
 
+	if (unlikely(rl->rq_pool))
+		return 0;
+
 	rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
 	rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
 	rl->elvpriv = 0;
@@ -510,6 +515,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 		return NULL;
 	}
 
+	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);
@@ -566,19 +573,42 @@ EXPORT_SYMBOL(blk_init_queue);
 struct request_queue *
 blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 {
-	struct request_queue *q = blk_alloc_queue_node(GFP_KERNEL, node_id);
+	struct request_queue *uninit_q, *q;
+
+	uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id);
+	if (!uninit_q)
+		return NULL;
+
+	q = blk_init_allocated_queue_node(uninit_q, rfn, lock, node_id);
+	if (!q)
+		blk_cleanup_queue(uninit_q);
+
+	return q;
+}
+EXPORT_SYMBOL(blk_init_queue_node);
+
+struct request_queue *
+blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
+			 spinlock_t *lock)
+{
+	return blk_init_allocated_queue_node(q, rfn, lock, -1);
+}
+EXPORT_SYMBOL(blk_init_allocated_queue);
 
+struct request_queue *
+blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn,
+			      spinlock_t *lock, int node_id)
+{
 	if (!q)
 		return NULL;
 
 	q->node = node_id;
-	if (blk_init_free_list(q)) {
-		kmem_cache_free(blk_requestq_cachep, q);
+	if (blk_init_free_list(q))
 		return NULL;
-	}
 
 	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;
@@ -598,10 +628,9 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 		return q;
 	}
 
-	blk_put_queue(q);
 	return NULL;
 }
-EXPORT_SYMBOL(blk_init_queue_node);
+EXPORT_SYMBOL(blk_init_allocated_queue_node);
 
 int blk_get_queue(struct request_queue *q)
 {
@@ -1107,33 +1136,46 @@ void blk_put_request(struct request *req)
 }
 EXPORT_SYMBOL(blk_put_request);
 
+/**
+ * blk_add_request_payload - add a payload to a request
+ * @rq: request to update
+ * @page: page backing the payload
+ * @len: length of the payload.
+ *
+ * This allows to later add a payload to an already submitted request by
+ * a block driver.  The driver needs to take care of freeing the payload
+ * itself.
+ *
+ * Note that this is a quite horrible hack and nothing but handling of
+ * discard requests should ever use it.
+ */
+void blk_add_request_payload(struct request *rq, struct page *page,
+		unsigned int len)
+{
+	struct bio *bio = rq->bio;
+
+	bio->bi_io_vec->bv_page = page;
+	bio->bi_io_vec->bv_offset = 0;
+	bio->bi_io_vec->bv_len = len;
+
+	bio->bi_size = len;
+	bio->bi_vcnt = 1;
+	bio->bi_phys_segments = 1;
+
+	rq->__data_len = rq->resid_len = len;
+	rq->nr_phys_segments = 1;
+	rq->buffer = bio_data(bio);
+}
+EXPORT_SYMBOL_GPL(blk_add_request_payload);
+
 void init_request_from_bio(struct request *req, struct bio *bio)
 {
 	req->cpu = bio->bi_comp_cpu;
 	req->cmd_type = REQ_TYPE_FS;
 
-	/*
-	 * Inherit FAILFAST from bio (for read-ahead, and explicit
-	 * FAILFAST).  FAILFAST flags are identical for req and bio.
-	 */
-	if (bio_rw_flagged(bio, BIO_RW_AHEAD))
+	req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK;
+	if (bio->bi_rw & REQ_RAHEAD)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
-	else
-		req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK;
-
-	if (unlikely(bio_rw_flagged(bio, BIO_RW_DISCARD))) {
-		req->cmd_flags |= REQ_DISCARD;
-		if (bio_rw_flagged(bio, BIO_RW_BARRIER))
-			req->cmd_flags |= REQ_SOFTBARRIER;
-	} else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)))
-		req->cmd_flags |= REQ_HARDBARRIER;
-
-	if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
-		req->cmd_flags |= REQ_RW_SYNC;
-	if (bio_rw_flagged(bio, BIO_RW_META))
-		req->cmd_flags |= REQ_RW_META;
-	if (bio_rw_flagged(bio, BIO_RW_NOIDLE))
-		req->cmd_flags |= REQ_NOIDLE;
 
 	req->errors = 0;
 	req->__sector = bio->bi_sector;
@@ -1147,7 +1189,7 @@ 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)
@@ -1156,12 +1198,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	int el_ret;
 	unsigned int bytes = bio->bi_size;
 	const unsigned short prio = bio_prio(bio);
-	const bool sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
-	const bool unplug = bio_rw_flagged(bio, BIO_RW_UNPLUG);
-	const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	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 rw_flags;
 
-	if (bio_rw_flagged(bio, BIO_RW_BARRIER) &&
+	if ((bio->bi_rw & REQ_HARDBARRIER) &&
 	    (q->next_ordered == QUEUE_ORDERED_NONE)) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
@@ -1175,7 +1217,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)) || elv_queue_empty(q))
+	if (unlikely((bio->bi_rw & REQ_HARDBARRIER)) || elv_queue_empty(q))
 		goto get_rq;
 
 	el_ret = elv_merge(q, &req, bio);
@@ -1198,6 +1240,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 		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;
@@ -1231,6 +1274,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 		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;
@@ -1248,7 +1292,7 @@ get_rq:
 	 */
 	rw_flags = bio_data_dir(bio);
 	if (sync)
-		rw_flags |= REQ_RW_SYNC;
+		rw_flags |= REQ_SYNC;
 
 	/*
 	 * Grab a free request. This is might sleep but can not fail.
@@ -1437,7 +1481,7 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 		}
 
-		if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+		if (unlikely(!(bio->bi_rw & REQ_DISCARD) &&
 			     nr_sectors > queue_max_hw_sectors(q))) {
 			printk(KERN_ERR "bio too big device %s (%u > %u)\n",
 			       bdevname(bio->bi_bdev, b),
@@ -1470,8 +1514,10 @@ static inline void __generic_make_request(struct bio *bio)
 		if (bio_check_eod(bio, nr_sectors))
 			goto end_io;
 
-		if (bio_rw_flagged(bio, BIO_RW_DISCARD) &&
-		    !blk_queue_discard(q)) {
+		if ((bio->bi_rw & REQ_DISCARD) &&
+		    (!blk_queue_discard(q) ||
+		     ((bio->bi_rw & REQ_SECURE) &&
+		      !blk_queue_secdiscard(q)))) {
 			err = -EOPNOTSUPP;
 			goto end_io;
 		}
@@ -1490,9 +1536,9 @@ 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 +1546,11 @@ 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 +1558,27 @@ 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);
 
@@ -1559,7 +1602,7 @@ void submit_bio(int rw, struct bio *bio)
 	 * If it's a regular read/write or a barrier with data attached,
 	 * go through the normal accounting stuff before submission.
 	 */
-	if (bio_has_data(bio)) {
+	if (bio_has_data(bio) && !(rw & REQ_DISCARD)) {
 		if (rw & WRITE) {
 			count_vm_events(PGPGOUT, count);
 		} else {
@@ -1604,6 +1647,9 @@ EXPORT_SYMBOL(submit_bio);
  */
 int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 {
+	if (rq->cmd_flags & REQ_DISCARD)
+		return 0;
+
 	if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
 	    blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
@@ -1617,8 +1663,7 @@ 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;
 	}
@@ -1773,7 +1818,7 @@ struct request *blk_peek_request(struct request_queue *q)
 			 * sees this request (possibly after
 			 * requeueing).  Notify IO scheduler.
 			 */
-			if (blk_sorted_rq(rq))
+			if (rq->cmd_flags & REQ_SORTED)
 				elv_activate_rq(q, rq);
 
 			/*
@@ -1861,12 +1906,7 @@ void blk_dequeue_request(struct request *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);
+		set_io_start_time_ns(rq);
 	}
 }
 
@@ -1966,10 +2006,11 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	 * TODO: tj: This is too subtle.  It would be better to let
 	 * low level drivers do what they see fit.
 	 */
-	if (blk_fs_request(req))
+	if (req->cmd_type == REQ_TYPE_FS)
 		req->errors = 0;
 
-	if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) {
+	if (error && req->cmd_type == REQ_TYPE_FS &&
+	    !(req->cmd_flags & REQ_QUIET)) {
 		printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n",
 				req->rq_disk ? req->rq_disk->disk_name : "?",
 				(unsigned long long)blk_rq_pos(req));
@@ -2056,7 +2097,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	req->buffer = bio_data(req->bio);
 
 	/* update sector only for requests with clear definition of sector */
-	if (blk_fs_request(req) || blk_discard_rq(req))
+	if (req->cmd_type == REQ_TYPE_FS || (req->cmd_flags & REQ_DISCARD))
 		req->__sector += total_bytes >> 9;
 
 	/* mixed attributes always follow the first bio */
@@ -2093,11 +2134,32 @@ static bool blk_update_bidi_request(struct request *rq, int error,
 	    blk_update_request(rq->next_rq, error, bidi_bytes))
 		return true;
 
-	add_disk_randomness(rq->rq_disk);
+	if (blk_queue_add_random(rq->q))
+		add_disk_randomness(rq->rq_disk);
 
 	return false;
 }
 
+/**
+ * blk_unprep_request - unprepare a request
+ * @req:	the request
+ *
+ * This function makes a request ready for complete resubmission (or
+ * completion).  It happens only after all error handling is complete,
+ * so represents the appropriate moment to deallocate any resources
+ * that were allocated to the request in the prep_rq_fn.  The queue
+ * lock is held when calling this.
+ */
+void blk_unprep_request(struct request *req)
+{
+	struct request_queue *q = req->q;
+
+	req->cmd_flags &= ~REQ_DONTPREP;
+	if (q->unprep_rq_fn)
+		q->unprep_rq_fn(q, req);
+}
+EXPORT_SYMBOL_GPL(blk_unprep_request);
+
 /*
  * queue lock must be held
  */
@@ -2108,11 +2170,15 @@ static void blk_finish_request(struct request *req, int error)
 
 	BUG_ON(blk_queued_rq(req));
 
-	if (unlikely(laptop_mode) && blk_fs_request(req))
-		laptop_io_completion();
+	if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS)
+		laptop_io_completion(&req->q->backing_dev_info);
 
 	blk_delete_timer(req);
 
+	if (req->cmd_flags & REQ_DONTPREP)
+		blk_unprep_request(req);
+
+
 	blk_account_io_done(req);
 
 	if (req->end_io)
@@ -2345,7 +2411,7 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
 	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
-	rq->cmd_flags |= bio->bi_rw & REQ_RW;
+	rq->cmd_flags |= bio->bi_rw & REQ_WRITE;
 
 	if (bio_has_data(bio)) {
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
@@ -2432,6 +2498,8 @@ static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
 	dst->cmd_flags = (rq_data_dir(src) | REQ_NOMERGE);
+	if (src->cmd_flags & REQ_DISCARD)
+		dst->cmd_flags |= REQ_DISCARD;
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
@@ -2528,4 +2596,3 @@ int __init blk_dev_init(void)
 
 	return 0;
 }
-
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 49557e91f0da..e1672f14840e 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -57,7 +57,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	__elv_add_request(q, rq, where, 1);
 	__generic_unplug_device(q);
 	/* the queue is stopped so it won't be plugged+unplugged */
-	if (blk_pm_resume_request(rq))
+	if (rq->cmd_type == REQ_TYPE_PM_RESUME)
 		q->request_fn(q);
 	spin_unlock_irq(q->queue_lock);
 }
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 15c630813b1c..edce1ef7933d 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -24,6 +24,7 @@
 #include <linux/mempool.h>
 #include <linux/bio.h>
 #include <linux/scatterlist.h>
+#include <linux/slab.h>
 
 #include "blk.h"
 
@@ -278,7 +279,7 @@ 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 98e6bf61b0ac..d22c4c55c406 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -7,6 +7,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
+#include <linux/slab.h>
 
 #include "blk.h"
 
@@ -91,7 +92,7 @@ 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-lib.c b/block/blk-lib.c
new file mode 100644
index 000000000000..c392029a104e
--- /dev/null
+++ b/block/blk-lib.c
@@ -0,0 +1,231 @@
+/*
+ * Functions related to generic helpers functions
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/scatterlist.h>
+
+#include "blk.h"
+
+static void blkdev_discard_end_io(struct bio *bio, int err)
+{
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	}
+
+	if (bio->bi_private)
+		complete(bio->bi_private);
+
+	bio_put(bio);
+}
+
+/**
+ * blkdev_issue_discard - queue a discard
+ * @bdev:	blockdev to issue discard for
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to discard
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @flags:	BLKDEV_IFL_* flags to control behaviour
+ *
+ * Description:
+ *    Issue a discard request for the sectors in question.
+ */
+int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+	struct request_queue *q = bdev_get_queue(bdev);
+	int type = flags & BLKDEV_IFL_BARRIER ?
+		DISCARD_BARRIER : DISCARD_NOBARRIER;
+	unsigned int max_discard_sectors;
+	struct bio *bio;
+	int ret = 0;
+
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_discard(q))
+		return -EOPNOTSUPP;
+
+	/*
+	 * Ensure that max_discard_sectors is of the proper
+	 * granularity
+	 */
+	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+	if (q->limits.discard_granularity) {
+		unsigned int disc_sects = q->limits.discard_granularity >> 9;
+
+		max_discard_sectors &= ~(disc_sects - 1);
+	}
+
+	if (flags & BLKDEV_IFL_SECURE) {
+		if (!blk_queue_secdiscard(q))
+			return -EOPNOTSUPP;
+		type |= DISCARD_SECURE;
+	}
+
+	while (nr_sects && !ret) {
+		bio = bio_alloc(gfp_mask, 1);
+		if (!bio) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		bio->bi_sector = sector;
+		bio->bi_end_io = blkdev_discard_end_io;
+		bio->bi_bdev = bdev;
+		if (flags & BLKDEV_IFL_WAIT)
+			bio->bi_private = &wait;
+
+		if (nr_sects > max_discard_sectors) {
+			bio->bi_size = max_discard_sectors << 9;
+			nr_sects -= max_discard_sectors;
+			sector += max_discard_sectors;
+		} else {
+			bio->bi_size = nr_sects << 9;
+			nr_sects = 0;
+		}
+
+		bio_get(bio);
+		submit_bio(type, bio);
+
+		if (flags & BLKDEV_IFL_WAIT)
+			wait_for_completion(&wait);
+
+		if (bio_flagged(bio, BIO_EOPNOTSUPP))
+			ret = -EOPNOTSUPP;
+		else if (!bio_flagged(bio, BIO_UPTODATE))
+			ret = -EIO;
+		bio_put(bio);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_discard);
+
+struct bio_batch
+{
+	atomic_t 		done;
+	unsigned long 		flags;
+	struct completion 	*wait;
+	bio_end_io_t		*end_io;
+};
+
+static void bio_batch_end_io(struct bio *bio, int err)
+{
+	struct bio_batch *bb = bio->bi_private;
+
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			set_bit(BIO_EOPNOTSUPP, &bb->flags);
+		else
+			clear_bit(BIO_UPTODATE, &bb->flags);
+	}
+	if (bb) {
+		if (bb->end_io)
+			bb->end_io(bio, err);
+		atomic_inc(&bb->done);
+		complete(bb->wait);
+	}
+	bio_put(bio);
+}
+
+/**
+ * blkdev_issue_zeroout generate number of zero filed write bios
+ * @bdev:	blockdev to issue
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to write
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @flags:	BLKDEV_IFL_* flags to control behaviour
+ *
+ * Description:
+ *  Generate and issue number of bios with zerofiled pages.
+ *  Send barrier at the beginning and at the end if requested. This guarantie
+ *  correct request ordering. Empty barrier allow us to avoid post queue flush.
+ */
+
+int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+			sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+{
+	int ret;
+	struct bio *bio;
+	struct bio_batch bb;
+	unsigned int sz, issued = 0;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	atomic_set(&bb.done, 0);
+	bb.flags = 1 << BIO_UPTODATE;
+	bb.wait = &wait;
+	bb.end_io = NULL;
+
+	if (flags & BLKDEV_IFL_BARRIER) {
+		/* issue async barrier before the data */
+		ret = blkdev_issue_flush(bdev, gfp_mask, NULL, 0);
+		if (ret)
+			return ret;
+	}
+submit:
+	ret = 0;
+	while (nr_sects != 0) {
+		bio = bio_alloc(gfp_mask,
+				min(nr_sects, (sector_t)BIO_MAX_PAGES));
+		if (!bio) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		bio->bi_sector = sector;
+		bio->bi_bdev   = bdev;
+		bio->bi_end_io = bio_batch_end_io;
+		if (flags & BLKDEV_IFL_WAIT)
+			bio->bi_private = &bb;
+
+		while (nr_sects != 0) {
+			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
+			if (sz == 0)
+				/* bio has maximum size possible */
+				break;
+			ret = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0);
+			nr_sects -= ret >> 9;
+			sector += ret >> 9;
+			if (ret < (sz << 9))
+				break;
+		}
+		ret = 0;
+		issued++;
+		submit_bio(WRITE, bio);
+	}
+	/*
+	 * When all data bios are in flight. Send final barrier if requeted.
+	 */
+	if (nr_sects == 0 && flags & BLKDEV_IFL_BARRIER)
+		ret = blkdev_issue_flush(bdev, gfp_mask, NULL,
+					flags & BLKDEV_IFL_WAIT);
+
+
+	if (flags & BLKDEV_IFL_WAIT)
+		/* Wait for bios in-flight */
+		while ( issued != atomic_read(&bb.done))
+			wait_for_completion(&wait);
+
+	if (!test_bit(BIO_UPTODATE, &bb.flags))
+		/* One of bios in the batch was completed with error.*/
+		ret = -EIO;
+
+	if (ret)
+		goto out;
+
+	if (test_bit(BIO_EOPNOTSUPP, &bb.flags)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+	if (nr_sects != 0)
+		goto submit;
+out:
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_zeroout);
diff --git a/block/blk-map.c b/block/blk-map.c
index 9083cf0180cc..ade0a08c9099 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -307,7 +307,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		return PTR_ERR(bio);
 
 	if (rq_data_dir(rq) == WRITE)
-		bio->bi_rw |= (1 << BIO_RW);
+		bio->bi_rw |= REQ_WRITE;
 
 	if (do_copy)
 		rq->cmd_flags |= REQ_COPY_USER;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 99cb5cf1f447..eafc94f68d79 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -12,7 +12,6 @@
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					     struct bio *bio)
 {
-	unsigned int phys_size;
 	struct bio_vec *bv, *bvprv = NULL;
 	int cluster, i, high, highprv = 1;
 	unsigned int seg_size, nr_phys_segs;
@@ -24,7 +23,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	fbio = bio;
 	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
 	seg_size = 0;
-	phys_size = nr_phys_segs = 0;
+	nr_phys_segs = 0;
 	for_each_bio(bio) {
 		bio_for_each_segment(bv, bio, i) {
 			/*
@@ -180,7 +179,7 @@ new_segment:
 	}
 
 	if (q->dma_drain_size && q->dma_drain_needed(rq)) {
-		if (rq->cmd_flags & REQ_RW)
+		if (rq->cmd_flags & REQ_WRITE)
 			memset(q->dma_drain_buffer, 0, q->dma_drain_size);
 
 		sg->page_link &= ~0x02;
@@ -206,8 +205,7 @@ 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;
@@ -227,7 +225,7 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 {
 	unsigned short max_sectors;
 
-	if (unlikely(blk_pc_request(req)))
+	if (unlikely(req->cmd_type == REQ_TYPE_BLOCK_PC))
 		max_sectors = queue_max_hw_sectors(q);
 	else
 		max_sectors = queue_max_sectors(q);
@@ -251,7 +249,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 {
 	unsigned short max_sectors;
 
-	if (unlikely(blk_pc_request(req)))
+	if (unlikely(req->cmd_type == REQ_TYPE_BLOCK_PC))
 		max_sectors = queue_max_hw_sectors(q);
 	else
 		max_sectors = queue_max_sectors(q);
@@ -300,10 +298,7 @@ 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... */
@@ -367,6 +362,18 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 		return 0;
 
 	/*
+	 * Don't merge file system requests and discard requests
+	 */
+	if ((req->cmd_flags & REQ_DISCARD) != (next->cmd_flags & REQ_DISCARD))
+		return 0;
+
+	/*
+	 * Don't merge discard requests and secure discard requests
+	 */
+	if ((req->cmd_flags & REQ_SECURE) != (next->cmd_flags & REQ_SECURE))
+		return 0;
+
+	/*
 	 * not contiguous
 	 */
 	if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5eeb9e0d256e..a234f4bf1d6f 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -8,7 +8,9 @@
 #include <linux/blkdev.h>
 #include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
 #include <linux/gcd.h>
+#include <linux/lcm.h>
 #include <linux/jiffies.h>
+#include <linux/gfp.h>
 
 #include "blk.h"
 
@@ -35,6 +37,23 @@ void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn)
 EXPORT_SYMBOL(blk_queue_prep_rq);
 
 /**
+ * blk_queue_unprep_rq - set an unprepare_request function for queue
+ * @q:		queue
+ * @ufn:	unprepare_request function
+ *
+ * It's possible for a queue to register an unprepare_request callback
+ * which is invoked before the request is finally completed. The goal
+ * of the function is to deallocate any data that was allocated in the
+ * prepare_request callback.
+ *
+ */
+void blk_queue_unprep_rq(struct request_queue *q, unprep_rq_fn *ufn)
+{
+	q->unprep_rq_fn = ufn;
+}
+EXPORT_SYMBOL(blk_queue_unprep_rq);
+
+/**
  * blk_queue_merge_bvec - set a merge_bvec function for queue
  * @q:		queue
  * @mbfn:	merge_bvec_fn
@@ -91,10 +110,9 @@ 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 +172,7 @@ 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 +228,32 @@ 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 +270,15 @@ 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 +286,9 @@ 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
@@ -493,21 +480,11 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
-static unsigned int lcm(unsigned int a, unsigned int b)
-{
-	if (a && b)
-		return (a * b) / gcd(a, b);
-	else if (b)
-		return b;
-
-	return a;
-}
-
 /**
  * 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 +502,9 @@ 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 +513,14 @@ 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 +583,7 @@ 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 +625,7 @@ 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 +636,8 @@ 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 +645,7 @@ 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 +717,19 @@ 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 8606c9543fdd..0749b89c6885 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -2,6 +2,7 @@
  * Functions related to sysfs handling
  */
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
@@ -106,6 +107,19 @@ static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_sectors_kb, (page));
 }
 
+static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_max_segments(q), (page));
+}
+
+static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
+{
+	if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+		return queue_var_show(queue_max_segment_size(q), (page));
+
+	return queue_var_show(PAGE_CACHE_SIZE, (page));
+}
+
 static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(queue_logical_block_size(q), page);
@@ -166,30 +180,41 @@ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_hw_sectors_kb, (page));
 }
 
-static ssize_t queue_nonrot_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(!blk_queue_nonrot(q), page);
+#define QUEUE_SYSFS_BIT_FNS(name, flag, neg)				\
+static ssize_t								\
+queue_show_##name(struct request_queue *q, char *page)			\
+{									\
+	int bit;							\
+	bit = test_bit(QUEUE_FLAG_##flag, &q->queue_flags);		\
+	return queue_var_show(neg ? !bit : bit, page);			\
+}									\
+static ssize_t								\
+queue_store_##name(struct request_queue *q, const char *page, size_t count) \
+{									\
+	unsigned long val;						\
+	ssize_t ret;							\
+	ret = queue_var_store(&val, page, count);			\
+	if (neg)							\
+		val = !val;						\
+									\
+	spin_lock_irq(q->queue_lock);					\
+	if (val)							\
+		queue_flag_set(QUEUE_FLAG_##flag, q);			\
+	else								\
+		queue_flag_clear(QUEUE_FLAG_##flag, q);			\
+	spin_unlock_irq(q->queue_lock);					\
+	return ret;							\
 }
 
-static ssize_t queue_nonrot_store(struct request_queue *q, const char *page,
-				  size_t count)
-{
-	unsigned long nm;
-	ssize_t ret = queue_var_store(&nm, page, count);
-
-	spin_lock_irq(q->queue_lock);
-	if (nm)
-		queue_flag_clear(QUEUE_FLAG_NONROT, q);
-	else
-		queue_flag_set(QUEUE_FLAG_NONROT, q);
-	spin_unlock_irq(q->queue_lock);
-
-	return ret;
-}
+QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1);
+QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0);
+QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0);
+#undef QUEUE_SYSFS_BIT_FNS
 
 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 +224,12 @@ 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;
@@ -233,27 +260,6 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 	return ret;
 }
 
-static ssize_t queue_iostats_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(blk_queue_io_stat(q), page);
-}
-
-static ssize_t queue_iostats_store(struct request_queue *q, const char *page,
-				   size_t count)
-{
-	unsigned long stats;
-	ssize_t ret = queue_var_store(&stats, page, count);
-
-	spin_lock_irq(q->queue_lock);
-	if (stats)
-		queue_flag_set(QUEUE_FLAG_IO_STAT, q);
-	else
-		queue_flag_clear(QUEUE_FLAG_IO_STAT, q);
-	spin_unlock_irq(q->queue_lock);
-
-	return ret;
-}
-
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -277,6 +283,16 @@ static struct queue_sysfs_entry queue_max_hw_sectors_entry = {
 	.show = queue_max_hw_sectors_show,
 };
 
+static struct queue_sysfs_entry queue_max_segments_entry = {
+	.attr = {.name = "max_segments", .mode = S_IRUGO },
+	.show = queue_max_segments_show,
+};
+
+static struct queue_sysfs_entry queue_max_segment_size_entry = {
+	.attr = {.name = "max_segment_size", .mode = S_IRUGO },
+	.show = queue_max_segment_size_show,
+};
+
 static struct queue_sysfs_entry queue_iosched_entry = {
 	.attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
 	.show = elv_iosched_show,
@@ -325,8 +341,8 @@ static struct queue_sysfs_entry queue_discard_zeroes_data_entry = {
 
 static struct queue_sysfs_entry queue_nonrot_entry = {
 	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
-	.show = queue_nonrot_show,
-	.store = queue_nonrot_store,
+	.show = queue_show_nonrot,
+	.store = queue_store_nonrot,
 };
 
 static struct queue_sysfs_entry queue_nomerges_entry = {
@@ -343,8 +359,14 @@ static struct queue_sysfs_entry queue_rq_affinity_entry = {
 
 static struct queue_sysfs_entry queue_iostats_entry = {
 	.attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR },
-	.show = queue_iostats_show,
-	.store = queue_iostats_store,
+	.show = queue_show_iostats,
+	.store = queue_store_iostats,
+};
+
+static struct queue_sysfs_entry queue_random_entry = {
+	.attr = {.name = "add_random", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_show_random,
+	.store = queue_store_random,
 };
 
 static struct attribute *default_attrs[] = {
@@ -352,6 +374,8 @@ static struct attribute *default_attrs[] = {
 	&queue_ra_entry.attr,
 	&queue_max_hw_sectors_entry.attr,
 	&queue_max_sectors_entry.attr,
+	&queue_max_segments_entry.attr,
+	&queue_max_segment_size_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
 	&queue_logical_block_size_entry.attr,
@@ -365,6 +389,7 @@ static struct attribute *default_attrs[] = {
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
 	&queue_iostats_entry.attr,
+	&queue_random_entry.attr,
 	NULL,
 };
 
@@ -447,7 +472,7 @@ 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,
 };
@@ -486,6 +511,7 @@ int blk_register_queue(struct gendisk *disk)
 		kobject_uevent(&q->kobj, KOBJ_REMOVE);
 		kobject_del(&q->kobj);
 		blk_trace_remove_sysfs(disk_to_dev(disk));
+		kobject_put(&dev->kobj);
 		return ret;
 	}
 
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 6b0f52c20964..ece65fc4c79b 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/slab.h>
 
 #include "blk.h"
 
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 1ba7e0aca878..4f0c06c7a338 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -109,6 +109,7 @@ void blk_rq_timed_out_timer(unsigned long data)
 	struct request_queue *q = (struct request_queue *) data;
 	unsigned long flags, next = 0;
 	struct request *rq, *tmp;
+	int next_set = 0;
 
 	spin_lock_irqsave(q->queue_lock, flags);
 
@@ -122,16 +123,13 @@ void blk_rq_timed_out_timer(unsigned long data)
 			if (blk_mark_rq_complete(rq))
 				continue;
 			blk_rq_timed_out(rq);
-		} else if (!next || time_after(next, rq->deadline))
+		} else if (!next_set || time_after(next, rq->deadline)) {
 			next = rq->deadline;
+			next_set = 1;
+		}
 	}
 
-	/*
-	 * next can never be 0 here with the list non-empty, since we always
-	 * bump ->deadline to 1 so we can detect if the timer was ever added
-	 * or not. See comment in blk_add_timer()
-	 */
-	if (next)
+	if (next_set)
 		mod_timer(&q->timeout, round_jiffies_up(next));
 
 	spin_unlock_irqrestore(q->queue_lock, flags);
diff --git a/block/blk.h b/block/blk.h
index 5ee3d7e72feb..d6b911ac002c 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -142,14 +142,18 @@ static inline int queue_congestion_off_threshold(struct request_queue *q)
 
 static inline int blk_cpu_to_group(int cpu)
 {
+	int group = NR_CPUS;
 #ifdef CONFIG_SCHED_MC
 	const struct cpumask *mask = cpu_coregroup_mask(cpu);
-	return cpumask_first(mask);
+	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	return cpumask_first(topology_thread_cpumask(cpu));
+	group = cpumask_first(topology_thread_cpumask(cpu));
 #else
 	return cpu;
 #endif
+	if (likely(group < NR_CPUS))
+		return group;
+	return cpu;
 }
 
 /*
@@ -161,8 +165,10 @@ static inline int blk_cpu_to_group(int cpu)
  */
 static inline int blk_do_io_stat(struct request *rq)
 {
-	return rq->rq_disk && blk_rq_io_stat(rq) &&
-	       (blk_fs_request(rq) || blk_discard_rq(rq));
+	return rq->rq_disk &&
+	       (rq->cmd_flags & REQ_IO_STAT) &&
+	       (rq->cmd_type == REQ_TYPE_FS ||
+	        (rq->cmd_flags & REQ_DISCARD));
 }
 
 #endif
diff --git a/block/bsg.c b/block/bsg.c
index a9fd2d84b53a..0c00870553a3 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -21,6 +21,7 @@
 #include <linux/idr.h>
 #include <linux/bsg.h>
 #include <linux/smp_lock.h>
+#include <linux/slab.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_ioctl.h>
@@ -260,7 +261,7 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 		return ERR_PTR(ret);
 
 	/*
-	 * map scatter-gather elements seperately and string them to request
+	 * map scatter-gather elements separately and string them to request
 	 */
 	rq = blk_get_request(q, rw, GFP_KERNEL);
 	if (!rq)
@@ -425,7 +426,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	/*
 	 * fill in all the output members
 	 */
-	hdr->device_status = status_byte(rq->errors);
+	hdr->device_status = rq->errors & 0xff;
 	hdr->transport_status = host_byte(rq->errors);
 	hdr->driver_status = driver_byte(rq->errors);
 	hdr->info = 0;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index ee130f14d1fc..9eba291eb6fd 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -7,19 +7,20 @@
  *  Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
  */
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
 #include <linux/jiffies.h>
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
 #include <linux/blktrace_api.h>
-#include "blk-cgroup.h"
+#include "cfq.h"
 
 /*
  * 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;
@@ -29,6 +30,7 @@ static const int cfq_slice_sync = HZ / 10;
 static int cfq_slice_async = HZ / 25;
 static const int cfq_slice_async_rq = 2;
 static int cfq_slice_idle = HZ / 125;
+static int cfq_group_idle = HZ / 125;
 static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
 static const int cfq_hist_divisor = 4;
 
@@ -42,19 +44,19 @@ 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_CLOSE_THR		(sector_t)(8 * 1024)
+#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)
+#define RQ_CFQG(rq)		(struct cfq_group *) ((rq)->elevator_private3)
 
 static struct kmem_cache *cfq_pool;
 static struct kmem_cache *cfq_ioc_pool;
@@ -63,6 +65,9 @@ static DEFINE_PER_CPU(unsigned long, cfq_ioc_count);
 static struct completion *ioc_gone;
 static DEFINE_SPINLOCK(ioc_gone_lock);
 
+static DEFINE_SPINLOCK(cic_index_lock);
+static DEFINE_IDA(cic_index_ida);
+
 #define CFQ_PRIO_LISTS		IOPRIO_BE_NR
 #define cfq_class_idle(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
 #define cfq_class_rt(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
@@ -80,11 +85,12 @@ 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 +124,11 @@ 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;
@@ -133,19 +139,16 @@ 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;
 	struct cfq_group *orig_cfqg;
-	/* Sectors dispatched in current dispatch round */
+	/* Number of sectors dispatched from queue in single dispatch round */
 	unsigned long nr_sectors;
 };
 
@@ -198,6 +201,8 @@ struct cfq_group {
 	struct hlist_node cfqd_node;
 	atomic_t ref;
 #endif
+	/* number of requests that are on the dispatch list or inside driver */
+	int dispatched;
 };
 
 /*
@@ -227,8 +232,8 @@ 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
@@ -271,9 +276,11 @@ struct cfq_data {
 	unsigned int cfq_slice[2];
 	unsigned int cfq_slice_async_rq;
 	unsigned int cfq_slice_idle;
+	unsigned int cfq_group_idle;
 	unsigned int cfq_latency;
 	unsigned int cfq_group_isolation;
 
+	unsigned int cic_index;
 	struct list_head cic_list;
 
 	/*
@@ -314,6 +321,7 @@ 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 */
 };
@@ -342,11 +350,12 @@ 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
 
-#ifdef CONFIG_DEBUG_CFQ_IOSCHED
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
 			cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \
@@ -375,6 +384,21 @@ CFQ_CFQQ_FNS(wait_busy);
 			&cfqg->service_trees[i][j]: NULL) \
 
 
+static inline bool iops_mode(struct cfq_data *cfqd)
+{
+	/*
+	 * If we are not idling on queues and it is a NCQ drive, parallel
+	 * execution of requests is on and measuring time is not possible
+	 * in most of the cases until and unless we drive shallower queue
+	 * depths and that becomes a performance bottleneck. In such cases
+	 * switch to start providing fairness in terms of number of IOs.
+	 */
+	if (!cfqd->cfq_slice_idle && cfqd->hw_tag)
+		return true;
+	else
+		return false;
+}
+
 static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq)
 {
 	if (cfq_class_idle(cfqq))
@@ -419,11 +443,6 @@ 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)
 {
@@ -436,13 +455,31 @@ static inline void cic_set_cfqq(struct cfq_io_context *cic,
 	cic->cfqq[is_sync] = cfqq;
 }
 
+#define CIC_DEAD_KEY	1ul
+#define CIC_DEAD_INDEX_SHIFT	1
+
+static inline void *cfqd_dead_key(struct cfq_data *cfqd)
+{
+	return (void *)(cfqd->cic_index << CIC_DEAD_INDEX_SHIFT | CIC_DEAD_KEY);
+}
+
+static inline struct cfq_data *cic_to_cfqd(struct cfq_io_context *cic)
+{
+	struct cfq_data *cfqd = cic->key;
+
+	if (unlikely((unsigned long) cfqd & CIC_DEAD_KEY))
+		return NULL;
+
+	return cfqd;
+}
+
 /*
  * We regard a request as SYNC, if it's either a read or has the SYNC bit
  * set (in which case it could also be direct WRITE).
  */
 static inline bool cfq_bio_sync(struct bio *bio)
 {
-	return bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO);
+	return bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC);
 }
 
 /*
@@ -630,9 +667,10 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2,
 		return rq1;
 	else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
 		return rq2;
-	if (rq_is_meta(rq1) && !rq_is_meta(rq2))
+	if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
 		return rq1;
-	else if (rq_is_meta(rq2) && !rq_is_meta(rq1))
+	else if ((rq2->cmd_flags & REQ_META) &&
+		 !(rq1->cmd_flags & REQ_META))
 		return rq2;
 
 	s1 = blk_rq_pos(rq1);
@@ -863,7 +901,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	if (!RB_EMPTY_NODE(&cfqg->rb_node))
 		cfq_rb_erase(&cfqg->rb_node, st);
 	cfqg->saved_workload_slice = 0;
-	blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1);
+	cfq_blkiocg_update_dequeue_stats(&cfqg->blkg, 1);
 }
 
 static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
@@ -889,8 +927,6 @@ static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
 			slice_used = cfqq->allocated_slice;
 	}
 
-	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u sect=%lu", slice_used,
-				cfqq->nr_sectors);
 	return slice_used;
 }
 
@@ -898,19 +934,21 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 				struct cfq_queue *cfqq)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
-	unsigned int used_sl, charge_sl;
+	unsigned int used_sl, charge;
 	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
 			- cfqg->service_tree_idle.count;
 
 	BUG_ON(nr_sync < 0);
-	used_sl = charge_sl = cfq_cfqq_slice_usage(cfqq);
+	used_sl = charge = cfq_cfqq_slice_usage(cfqq);
 
-	if (!cfq_cfqq_sync(cfqq) && !nr_sync)
-		charge_sl = cfqq->allocated_slice;
+	if (iops_mode(cfqd))
+		charge = cfqq->slice_dispatch;
+	else if (!cfq_cfqq_sync(cfqq) && !nr_sync)
+		charge = cfqq->allocated_slice;
 
 	/* Can't update vdisktime while group is on service tree */
 	cfq_rb_erase(&cfqg->rb_node, st);
-	cfqg->vdisktime += cfq_scale_slice(charge_sl, cfqg);
+	cfqg->vdisktime += cfq_scale_slice(charge, cfqg);
 	__cfq_group_service_tree_add(st, cfqg);
 
 	/* This group is being expired. Save the context */
@@ -924,8 +962,11 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 
 	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
 					st->min_vdisktime);
-	blkiocg_update_blkio_group_stats(&cfqg->blkg, used_sl,
-						cfqq->nr_sectors);
+	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u"
+			" sect=%u", used_sl, cfqq->slice_dispatch, charge,
+			iops_mode(cfqd), cfqq->nr_sectors);
+	cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl);
+	cfq_blkiocg_set_start_empty_time(&cfqg->blkg);
 }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
@@ -953,11 +994,12 @@ 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 && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+		cfqg->blkg.dev = MKDEV(major, minor);
+		goto done;
+	}
 	if (cfqg || !create)
 		goto done;
 
@@ -965,7 +1007,6 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	if (!cfqg)
 		goto done;
 
-	cfqg->weight = blkcg->weight;
 	for_each_cfqg_st(cfqg, i, j, st)
 		*st = CFQ_RB_ROOT;
 	RB_CLEAR_NODE(&cfqg->rb_node);
@@ -978,16 +1019,26 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	 */
 	atomic_set(&cfqg->ref, 1);
 
-	/* Add group onto cgroup list */
-	sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
-	blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
+	/*
+	 * Add group onto cgroup list. It might happen that bdi->dev is
+	 * not initiliazed yet. Initialize this new group without major
+	 * and minor info and this info will be filled in once a new thread
+	 * comes for IO. See code above.
+	 */
+	if (bdi->dev) {
+		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
 					MKDEV(major, minor));
+	} else
+		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
+					0);
+
+	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
 
 	/* Add group on cfqd list */
 	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
 
 done:
-	blkiocg_css_put(blkcg);
 	return cfqg;
 }
 
@@ -1009,6 +1060,12 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
 	return cfqg;
 }
 
+static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg)
+{
+	atomic_inc(&cfqg->ref);
+	return cfqg;
+}
+
 static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
 {
 	/* Currently, all async queues are mapped to root group */
@@ -1058,7 +1115,7 @@ static void cfq_release_cfq_groups(struct cfq_data *cfqd)
 		 * it from cgroup list, then it will take care of destroying
 		 * cfqg also.
 		 */
-		if (!blkiocg_del_blkio_group(&cfqg->blkg))
+		if (!cfq_blkiocg_del_blkio_group(&cfqg->blkg))
 			cfq_destroy_cfqg(cfqd, cfqg);
 	}
 }
@@ -1092,6 +1149,12 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
 {
 	return &cfqd->root_group;
 }
+
+static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg)
+{
+	return cfqg;
+}
+
 static inline void
 cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) {
 	cfqq->cfqg = cfqg;
@@ -1394,7 +1457,12 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
 {
 	elv_rb_del(&cfqq->sort_list, rq);
 	cfqq->queued[rq_is_sync(rq)]--;
+	cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg,
+					rq_data_dir(rq), rq_is_sync(rq));
 	cfq_add_rq_rb(rq);
+	cfq_blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg,
+			&cfqq->cfqd->serving_group->blkg, rq_data_dir(rq),
+			rq_is_sync(rq));
 }
 
 static struct request *
@@ -1422,9 +1490,9 @@ 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 +1500,11 @@ 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)
@@ -1451,7 +1518,9 @@ static void cfq_remove_request(struct request *rq)
 	cfq_del_rq_rb(rq);
 
 	cfqq->cfqd->rq_queued--;
-	if (rq_is_meta(rq)) {
+	cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg,
+					rq_data_dir(rq), rq_is_sync(rq));
+	if (rq->cmd_flags & REQ_META) {
 		WARN_ON(!cfqq->meta_pending);
 		cfqq->meta_pending--;
 	}
@@ -1482,6 +1551,13 @@ static void cfq_merged_request(struct request_queue *q, struct request *req,
 	}
 }
 
+static void cfq_bio_merged(struct request_queue *q, struct request *req,
+				struct bio *bio)
+{
+	cfq_blkiocg_update_io_merged_stats(&(RQ_CFQG(req))->blkg,
+					bio_data_dir(bio), cfq_bio_sync(bio));
+}
+
 static void
 cfq_merged_requests(struct request_queue *q, struct request *rq,
 		    struct request *next)
@@ -1499,6 +1575,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	if (cfqq->next_rq == next)
 		cfqq->next_rq = rq;
 	cfq_remove_request(next);
+	cfq_blkiocg_update_io_merged_stats(&(RQ_CFQG(rq))->blkg,
+					rq_data_dir(next), rq_is_sync(next));
 }
 
 static int cfq_allow_merge(struct request_queue *q, struct request *rq,
@@ -1526,11 +1604,19 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	return cfqq == RQ_CFQQ(rq);
 }
 
+static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	del_timer(&cfqd->idle_slice_timer);
+	cfq_blkiocg_update_idle_time_stats(&cfqq->cfqg->blkg);
+}
+
 static void __cfq_set_active_queue(struct cfq_data *cfqd,
 				   struct cfq_queue *cfqq)
 {
 	if (cfqq) {
-		cfq_log_cfqq(cfqd, cfqq, "set_active");
+		cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d",
+				cfqd->serving_prio, cfqd->serving_type);
+		cfq_blkiocg_update_avg_queue_size_stats(&cfqq->cfqg->blkg);
 		cfqq->slice_start = 0;
 		cfqq->dispatch_start = jiffies;
 		cfqq->allocated_slice = 0;
@@ -1544,7 +1630,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 		cfq_clear_cfqq_fifo_expire(cfqq);
 		cfq_mark_cfqq_slice_new(cfqq);
 
-		del_timer(&cfqd->idle_slice_timer);
+		cfq_del_timer(cfqd, cfqq);
 	}
 
 	cfqd->active_queue = cfqq;
@@ -1560,12 +1646,21 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
 
 	if (cfq_cfqq_wait_request(cfqq))
-		del_timer(&cfqd->idle_slice_timer);
+		cfq_del_timer(cfqd, cfqq);
 
 	cfq_clear_cfqq_wait_request(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 +1758,10 @@ 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)
+			       struct request *rq)
 {
-	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_CLOSE_THR;
 }
 
 static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
@@ -1705,7 +1788,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
 	 * will contain the closest sector.
 	 */
 	__cfqq = rb_entry(parent, struct cfq_queue, p_node);
-	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
 		return __cfqq;
 
 	if (blk_rq_pos(__cfqq->next_rq) < sector)
@@ -1716,7 +1799,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
 		return NULL;
 
 	__cfqq = rb_entry(node, struct cfq_queue, p_node);
-	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
 		return __cfqq;
 
 	return NULL;
@@ -1737,6 +1820,8 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 {
 	struct cfq_queue *cfqq;
 
+	if (cfq_class_idle(cur_cfqq))
+		return NULL;
 	if (!cfq_cfqq_sync(cur_cfqq))
 		return NULL;
 	if (CFQQ_SEEKY(cur_cfqq))
@@ -1790,6 +1875,9 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	BUG_ON(!service_tree);
 	BUG_ON(!service_tree->count);
 
+	if (!cfqd->cfq_slice_idle)
+		return false;
+
 	/* We never do for idle class queues. */
 	if (prio == IDLE_WORKLOAD)
 		return false;
@@ -1803,14 +1891,18 @@ 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;
+	if (service_tree->count == 1 && cfq_cfqq_sync(cfqq))
+		return 1;
+	cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d",
+			service_tree->count);
+	return 0;
 }
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 	struct cfq_io_context *cic;
-	unsigned long sl;
+	unsigned long sl, group_idle = 0;
 
 	/*
 	 * SSD device without seek penalty, disable idling. But only do so
@@ -1826,8 +1918,13 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	/*
 	 * idle is disabled, either manually or by past process history
 	 */
-	if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq))
-		return;
+	if (!cfq_should_idle(cfqd, cfqq)) {
+		/* no queue idling. Check for group idling */
+		if (cfqd->cfq_group_idle)
+			group_idle = cfqd->cfq_group_idle;
+		else
+			return;
+	}
 
 	/*
 	 * still active requests from this queue, don't idle
@@ -1848,15 +1945,27 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	 * time slice.
 	 */
 	if (sample_valid(cic->ttime_samples) &&
-	    (cfqq->slice_end - jiffies < cic->ttime_mean))
+	    (cfqq->slice_end - jiffies < cic->ttime_mean)) {
+		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%d",
+				cic->ttime_mean);
+		return;
+	}
+
+	/* There are other queues in the group, don't do group idle */
+	if (group_idle && cfqq->cfqg->nr_cfqq > 1)
 		return;
 
 	cfq_mark_cfqq_wait_request(cfqq);
 
-	sl = cfqd->cfq_slice_idle;
+	if (group_idle)
+		sl = cfqd->cfq_group_idle;
+	else
+		sl = cfqd->cfq_slice_idle;
 
 	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
-	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
+	cfq_blkiocg_update_set_idle_time_stats(&cfqq->cfqg->blkg);
+	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl,
+			group_idle ? 1 : 0);
 }
 
 /*
@@ -1872,11 +1981,13 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
 	cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
 	cfq_remove_request(rq);
 	cfqq->dispatched++;
+	(RQ_CFQG(rq))->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);
+	cfq_blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq),
+					rq_data_dir(rq), rq_is_sync(rq));
 }
 
 /*
@@ -1930,6 +2041,15 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
 	int process_refs, new_process_refs;
 	struct cfq_queue *__cfqq;
 
+	/*
+	 * If there are no process references on the new_cfqq, then it is
+	 * unsafe to follow the ->new_cfqq chain as other cfqq's in the
+	 * chain may have dropped their last reference (not just their
+	 * last process reference).
+	 */
+	if (!cfqq_process_refs(new_cfqq))
+		return;
+
 	/* Avoid a circular list and skip interim queue merges */
 	while ((__cfqq = new_cfqq->new_cfqq)) {
 		if (__cfqq == cfqq)
@@ -1938,17 +2058,17 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
 	}
 
 	process_refs = cfqq_process_refs(cfqq);
+	new_process_refs = cfqq_process_refs(new_cfqq);
 	/*
 	 * If the process for the cfqq has gone away, there is no
 	 * sense in merging the queues.
 	 */
-	if (process_refs == 0)
+	if (process_refs == 0 || new_process_refs == 0)
 		return;
 
 	/*
 	 * Merge in the direction of the lesser amount of work.
 	 */
-	new_process_refs = cfqq_process_refs(new_cfqq);
 	if (new_process_refs >= process_refs) {
 		cfqq->new_cfqq = new_cfqq;
 		atomic_add(process_refs, &new_cfqq->ref);
@@ -2058,6 +2178,7 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		slice = max(slice, 2 * cfqd->cfq_slice_idle);
 
 	slice = max_t(unsigned, slice, CFQ_MIN_TT);
+	cfq_log(cfqd, "workload slice:%d", slice);
 	cfqd->workload_expires = jiffies + slice;
 	cfqd->noidle_tree_requires_idle = false;
 }
@@ -2131,7 +2252,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 			cfqq = NULL;
 			goto keep_queue;
 		} else
-			goto expire;
+			goto check_group_idle;
 	}
 
 	/*
@@ -2159,8 +2280,23 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	 * flight or is idling for a new request, allow either of these
 	 * conditions to happen (or time out) before selecting a new queue.
 	 */
-	if (timer_pending(&cfqd->idle_slice_timer) ||
-	    (cfqq->dispatched && cfq_should_idle(cfqd, cfqq))) {
+	if (timer_pending(&cfqd->idle_slice_timer)) {
+		cfqq = NULL;
+		goto keep_queue;
+	}
+
+	if (cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
+		cfqq = NULL;
+		goto keep_queue;
+	}
+
+	/*
+	 * If group idle is enabled and there are requests dispatched from
+	 * this group, wait for requests to complete.
+	 */
+check_group_idle:
+	if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1
+	    && cfqq->cfqg->dispatched) {
 		cfqq = NULL;
 		goto keep_queue;
 	}
@@ -2205,16 +2341,32 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 	struct cfq_queue *cfqq;
 	int dispatched = 0;
 
-	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL)
+	/* Expire the timeslice of the current active queue first */
+	cfq_slice_expired(cfqd, 0);
+	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL) {
+		__cfq_set_active_queue(cfqd, cfqq);
 		dispatched += __cfq_forced_dispatch_cfqq(cfqq);
+	}
 
-	cfq_slice_expired(cfqd, 0);
 	BUG_ON(cfqd->busy_queues);
 
 	cfq_log(cfqd, "forced_dispatch=%d", dispatched);
 	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 +2374,16 @@ 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 +2400,22 @@ 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;
 	}
 
 	/*
@@ -2450,11 +2611,12 @@ static void cfq_cic_free(struct cfq_io_context *cic)
 static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic)
 {
 	unsigned long flags;
+	unsigned long dead_key = (unsigned long) cic->key;
 
-	BUG_ON(!cic->dead_key);
+	BUG_ON(!(dead_key & CIC_DEAD_KEY));
 
 	spin_lock_irqsave(&ioc->lock, flags);
-	radix_tree_delete(&ioc->radix_root, cic->dead_key);
+	radix_tree_delete(&ioc->radix_root, dead_key >> CIC_DEAD_INDEX_SHIFT);
 	hlist_del_rcu(&cic->cic_list);
 	spin_unlock_irqrestore(&ioc->lock, flags);
 
@@ -2477,15 +2639,10 @@ static void cfq_free_io_context(struct io_context *ioc)
 	__call_for_each_cic(ioc, cic_free_func);
 }
 
-static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+static void cfq_put_cooperator(struct cfq_queue *cfqq)
 {
 	struct cfq_queue *__cfqq, *next;
 
-	if (unlikely(cfqq == cfqd->active_queue)) {
-		__cfq_slice_expired(cfqd, cfqq, 0);
-		cfq_schedule_dispatch(cfqd);
-	}
-
 	/*
 	 * If this queue was scheduled to merge with another queue, be
 	 * sure to drop the reference taken on that queue (and others in
@@ -2501,6 +2658,16 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		cfq_put_queue(__cfqq);
 		__cfqq = next;
 	}
+}
+
+static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	if (unlikely(cfqq == cfqd->active_queue)) {
+		__cfq_slice_expired(cfqd, cfqq, 0);
+		cfq_schedule_dispatch(cfqd);
+	}
+
+	cfq_put_cooperator(cfqq);
 
 	cfq_put_queue(cfqq);
 }
@@ -2513,11 +2680,10 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
 	list_del_init(&cic->queue_list);
 
 	/*
-	 * Make sure key == NULL is seen for dead queues
+	 * Make sure dead mark is seen for dead queues
 	 */
 	smp_wmb();
-	cic->dead_key = (unsigned long) cic->key;
-	cic->key = NULL;
+	cic->key = cfqd_dead_key(cfqd);
 
 	if (ioc->ioc_data == cic)
 		rcu_assign_pointer(ioc->ioc_data, NULL);
@@ -2536,7 +2702,7 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
 static void cfq_exit_single_io_context(struct io_context *ioc,
 				       struct cfq_io_context *cic)
 {
-	struct cfq_data *cfqd = cic->key;
+	struct cfq_data *cfqd = cic_to_cfqd(cic);
 
 	if (cfqd) {
 		struct request_queue *q = cfqd->queue;
@@ -2549,7 +2715,7 @@ static void cfq_exit_single_io_context(struct io_context *ioc,
 		 * race between exiting task and queue
 		 */
 		smp_read_barrier_depends();
-		if (cic->key)
+		if (cic->key == cfqd)
 			__cfq_exit_single_io_context(cfqd, cic);
 
 		spin_unlock_irqrestore(q->queue_lock, flags);
@@ -2629,7 +2795,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc)
 
 static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic)
 {
-	struct cfq_data *cfqd = cic->key;
+	struct cfq_data *cfqd = cic_to_cfqd(cic);
 	struct cfq_queue *cfqq;
 	unsigned long flags;
 
@@ -2686,7 +2852,7 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 static void changed_cgroup(struct io_context *ioc, struct cfq_io_context *cic)
 {
 	struct cfq_queue *sync_cfqq = cic_to_cfqq(cic, 1);
-	struct cfq_data *cfqd = cic->key;
+	struct cfq_data *cfqd = cic_to_cfqd(cic);
 	unsigned long flags;
 	struct request_queue *q;
 
@@ -2823,12 +2989,13 @@ cfq_drop_dead_cic(struct cfq_data *cfqd, struct io_context *ioc,
 	unsigned long flags;
 
 	WARN_ON(!list_empty(&cic->queue_list));
+	BUG_ON(cic->key != cfqd_dead_key(cfqd));
 
 	spin_lock_irqsave(&ioc->lock, flags);
 
 	BUG_ON(ioc->ioc_data == cic);
 
-	radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd);
+	radix_tree_delete(&ioc->radix_root, cfqd->cic_index);
 	hlist_del_rcu(&cic->cic_list);
 	spin_unlock_irqrestore(&ioc->lock, flags);
 
@@ -2840,7 +3007,6 @@ cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc)
 {
 	struct cfq_io_context *cic;
 	unsigned long flags;
-	void *k;
 
 	if (unlikely(!ioc))
 		return NULL;
@@ -2857,13 +3023,11 @@ cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc)
 	}
 
 	do {
-		cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd);
+		cic = radix_tree_lookup(&ioc->radix_root, cfqd->cic_index);
 		rcu_read_unlock();
 		if (!cic)
 			break;
-		/* ->key must be copied to avoid race with cfq_exit_queue() */
-		k = cic->key;
-		if (unlikely(!k)) {
+		if (unlikely(cic->key != cfqd)) {
 			cfq_drop_dead_cic(cfqd, ioc, cic);
 			rcu_read_lock();
 			continue;
@@ -2896,7 +3060,7 @@ static int cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc,
 
 		spin_lock_irqsave(&ioc->lock, flags);
 		ret = radix_tree_insert(&ioc->radix_root,
-						(unsigned long) cfqd, cic);
+						cfqd->cic_index, cic);
 		if (!ret)
 			hlist_add_head_rcu(&cic->cic_list, &ioc->cic_list);
 		spin_unlock_irqrestore(&ioc->lock, flags);
@@ -2976,43 +3140,20 @@ 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 +3178,7 @@ 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)
@@ -3106,7 +3246,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	 * So both queues are sync. Let the new request get disk time if
 	 * it's a metadata request and the current queue is doing regular IO.
 	 */
-	if (rq_is_meta(rq) && !cfqq->meta_pending)
+	if ((rq->cmd_flags & REQ_META) && !cfqq->meta_pending)
 		return true;
 
 	/*
@@ -3122,7 +3262,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	 * if this request is as-good as one we would expect from the
 	 * current cfqq, let it preempt
 	 */
-	if (cfq_rq_close(cfqd, cfqq, rq, true))
+	if (cfq_rq_close(cfqd, cfqq, rq))
 		return true;
 
 	return false;
@@ -3160,7 +3300,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	struct cfq_io_context *cic = RQ_CIC(rq);
 
 	cfqd->rq_queued++;
-	if (rq_is_meta(rq))
+	if (rq->cmd_flags & REQ_META)
 		cfqq->meta_pending++;
 
 	cfq_update_io_thinktime(cfqd, cic);
@@ -3183,11 +3323,14 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		if (cfq_cfqq_wait_request(cfqq)) {
 			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
 			    cfqd->busy_queues > 1) {
-				del_timer(&cfqd->idle_slice_timer);
+				cfq_del_timer(cfqd, cfqq);
 				cfq_clear_cfqq_wait_request(cfqq);
 				__blk_run_queue(cfqd->queue);
-			} else
+			} else {
+				cfq_blkiocg_update_idle_time_stats(
+						&cfqq->cfqg->blkg);
 				cfq_mark_cfqq_must_dispatch(cfqq);
+			}
 		}
 	} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
 		/*
@@ -3212,7 +3355,9 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]);
 	list_add_tail(&rq->queuelist, &cfqq->fifo);
 	cfq_add_rq_rb(rq);
-
+	cfq_blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg,
+			&cfqd->serving_group->blkg, rq_data_dir(rq),
+			rq_is_sync(rq));
 	cfq_rq_enqueued(cfqd, cfqq, rq);
 }
 
@@ -3224,14 +3369,14 @@ 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 +3386,7 @@ 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)
@@ -3290,17 +3435,21 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	unsigned long now;
 
 	now = jiffies;
-	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", !!rq_noidle(rq));
+	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d",
+		     !!(rq->cmd_flags & REQ_NOIDLE));
 
 	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--;
+	(RQ_CFQG(rq))->dispatched--;
+	cfq_blkiocg_update_completion_stats(&cfqq->cfqg->blkg,
+			rq_start_time_ns(rq), rq_io_start_time_ns(rq),
+			rq_data_dir(rq), rq_is_sync(rq));
 
-	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;
@@ -3325,8 +3474,12 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		 * the queue.
 		 */
 		if (cfq_should_wait_busy(cfqd, cfqq)) {
-			cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
+			unsigned long extend_sl = cfqd->cfq_slice_idle;
+			if (!cfqd->cfq_slice_idle)
+				extend_sl = cfqd->cfq_group_idle;
+			cfqq->slice_end = jiffies + extend_sl;
 			cfq_mark_cfqq_wait_busy(cfqq);
+			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
 		}
 
 		/*
@@ -3341,11 +3494,12 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 			cfq_slice_expired(cfqd, 1);
 		else if (sync && cfqq_empty &&
 			 !cfq_close_cooperator(cfqd, cfqq)) {
-			cfqd->noidle_tree_requires_idle |= !rq_noidle(rq);
+			cfqd->noidle_tree_requires_idle |=
+				!(rq->cmd_flags & REQ_NOIDLE);
 			/*
 			 * Idling is enabled for SYNC_WORKLOAD.
 			 * SYNC_NOIDLE_WORKLOAD idles at the end of the tree
-			 * only if we processed at least one !rq_noidle request
+			 * only if we processed at least one !REQ_NOIDLE request
 			 */
 			if (cfqd->serving_type == SYNC_WORKLOAD
 			    || cfqd->noidle_tree_requires_idle
@@ -3354,7 +3508,7 @@ 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);
 }
 
@@ -3438,6 +3592,10 @@ static void cfq_put_request(struct request *rq)
 		rq->elevator_private = NULL;
 		rq->elevator_private2 = NULL;
 
+		/* Put down rq reference on cfqg */
+		cfq_put_cfqg(RQ_CFQG(rq));
+		rq->elevator_private3 = NULL;
+
 		cfq_put_queue(cfqq);
 	}
 }
@@ -3453,14 +3611,6 @@ 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.
@@ -3469,13 +3619,16 @@ 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;
 	}
 
 	cic_set_cfqq(cic, NULL, 1);
+
+	cfq_put_cooperator(cfqq);
+
 	cfq_put_queue(cfqq);
 	return NULL;
 }
@@ -3510,7 +3663,7 @@ 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)
@@ -3534,6 +3687,7 @@ new_queue:
 
 	rq->elevator_private = cic;
 	rq->elevator_private2 = cfqq;
+	rq->elevator_private3 = cfq_ref_get_cfqg(cfqq->cfqg);
 	return 0;
 
 queue_fail:
@@ -3661,16 +3815,38 @@ static void cfq_exit_queue(struct elevator_queue *e)
 
 	cfq_put_async_queues(cfqd);
 	cfq_release_cfq_groups(cfqd);
-	blkiocg_del_blkio_group(&cfqd->root_group.blkg);
+	cfq_blkiocg_del_blkio_group(&cfqd->root_group.blkg);
 
 	spin_unlock_irq(q->queue_lock);
 
 	cfq_shutdown_timer_wq(cfqd);
 
+	spin_lock(&cic_index_lock);
+	ida_remove(&cic_index_ida, cfqd->cic_index);
+	spin_unlock(&cic_index_lock);
+
 	/* Wait for cfqg->blkg->key accessors to exit their grace periods. */
 	call_rcu(&cfqd->rcu, cfq_cfqd_free);
 }
 
+static int cfq_alloc_cic_index(void)
+{
+	int index, error;
+
+	do {
+		if (!ida_pre_get(&cic_index_ida, GFP_KERNEL))
+			return -ENOMEM;
+
+		spin_lock(&cic_index_lock);
+		error = ida_get_new(&cic_index_ida, &index);
+		spin_unlock(&cic_index_lock);
+		if (error && error != -EAGAIN)
+			return error;
+	} while (error);
+
+	return index;
+}
+
 static void *cfq_init_queue(struct request_queue *q)
 {
 	struct cfq_data *cfqd;
@@ -3678,10 +3854,16 @@ static void *cfq_init_queue(struct request_queue *q)
 	struct cfq_group *cfqg;
 	struct cfq_rb_root *st;
 
+	i = cfq_alloc_cic_index();
+	if (i < 0)
+		return NULL;
+
 	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
 	if (!cfqd)
 		return NULL;
 
+	cfqd->cic_index = i;
+
 	/* Init root service tree */
 	cfqd->grp_service_tree = CFQ_RB_ROOT;
 
@@ -3700,8 +3882,10 @@ static void *cfq_init_queue(struct request_queue *q)
 	 * to make sure that cfq_put_cfqg() does not try to kfree root group
 	 */
 	atomic_set(&cfqg->ref, 1);
-	blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd,
-					0);
+	rcu_read_lock();
+	cfq_blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg,
+					(void *)cfqd, 0);
+	rcu_read_unlock();
 #endif
 	/*
 	 * Not strictly needed (since RB_ROOT just clears the node and we
@@ -3739,6 +3923,7 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqd->cfq_slice[1] = cfq_slice_sync;
 	cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
 	cfqd->cfq_slice_idle = cfq_slice_idle;
+	cfqd->cfq_group_idle = cfq_group_idle;
 	cfqd->cfq_latency = 1;
 	cfqd->cfq_group_isolation = 0;
 	cfqd->hw_tag = -1;
@@ -3747,7 +3932,6 @@ static void *cfq_init_queue(struct request_queue *q)
 	 * second, in order to have larger depth for async operations.
 	 */
 	cfqd->last_delayed_sync = jiffies - HZ;
-	INIT_RCU_HEAD(&cfqd->rcu);
 	return cfqd;
 }
 
@@ -3812,6 +3996,7 @@ SHOW_FUNCTION(cfq_fifo_expire_async_show, cfqd->cfq_fifo_expire[0], 1);
 SHOW_FUNCTION(cfq_back_seek_max_show, cfqd->cfq_back_max, 0);
 SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0);
 SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
+SHOW_FUNCTION(cfq_group_idle_show, cfqd->cfq_group_idle, 1);
 SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1);
 SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
 SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
@@ -3844,6 +4029,7 @@ STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
 STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1,
 		UINT_MAX, 0);
 STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
+STORE_FUNCTION(cfq_group_idle_store, &cfqd->cfq_group_idle, 0, UINT_MAX, 1);
 STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1);
 STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1);
 STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1,
@@ -3865,6 +4051,7 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(slice_async),
 	CFQ_ATTR(slice_async_rq),
 	CFQ_ATTR(slice_idle),
+	CFQ_ATTR(group_idle),
 	CFQ_ATTR(low_latency),
 	CFQ_ATTR(group_isolation),
 	__ATTR_NULL
@@ -3876,6 +4063,7 @@ static struct elevator_type iosched_cfq = {
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,
 		.elevator_allow_merge_fn =	cfq_allow_merge,
+		.elevator_bio_merged_fn =	cfq_bio_merged,
 		.elevator_dispatch_fn =		cfq_dispatch_requests,
 		.elevator_add_req_fn =		cfq_insert_request,
 		.elevator_activate_req_fn =	cfq_activate_request,
@@ -3917,6 +4105,12 @@ static int __init cfq_init(void)
 	if (!cfq_slice_idle)
 		cfq_slice_idle = 1;
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	if (!cfq_group_idle)
+		cfq_group_idle = 1;
+#else
+		cfq_group_idle = 0;
+#endif
 	if (cfq_slab_setup())
 		return -ENOMEM;
 
@@ -3941,6 +4135,7 @@ static void __exit cfq_exit(void)
 	 */
 	if (elv_ioc_count_read(cfq_ioc_count))
 		wait_for_completion(&all_gone);
+	ida_destroy(&cic_index_ida);
 	cfq_slab_kill();
 }
 
diff --git a/block/cfq.h b/block/cfq.h
new file mode 100644
index 000000000000..93448e5a2e41
--- /dev/null
+++ b/block/cfq.h
@@ -0,0 +1,115 @@
+#ifndef _CFQ_H
+#define _CFQ_H
+#include "blk-cgroup.h"
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static inline void cfq_blkiocg_update_io_add_stats(struct blkio_group *blkg,
+	struct blkio_group *curr_blkg, bool direction, bool sync)
+{
+	blkiocg_update_io_add_stats(blkg, curr_blkg, direction, sync);
+}
+
+static inline void cfq_blkiocg_update_dequeue_stats(struct blkio_group *blkg,
+			unsigned long dequeue)
+{
+	blkiocg_update_dequeue_stats(blkg, dequeue);
+}
+
+static inline void cfq_blkiocg_update_timeslice_used(struct blkio_group *blkg,
+			unsigned long time)
+{
+	blkiocg_update_timeslice_used(blkg, time);
+}
+
+static inline void cfq_blkiocg_set_start_empty_time(struct blkio_group *blkg)
+{
+	blkiocg_set_start_empty_time(blkg);
+}
+
+static inline void cfq_blkiocg_update_io_remove_stats(struct blkio_group *blkg,
+				bool direction, bool sync)
+{
+	blkiocg_update_io_remove_stats(blkg, direction, sync);
+}
+
+static inline void cfq_blkiocg_update_io_merged_stats(struct blkio_group *blkg,
+		bool direction, bool sync)
+{
+	blkiocg_update_io_merged_stats(blkg, direction, sync);
+}
+
+static inline void cfq_blkiocg_update_idle_time_stats(struct blkio_group *blkg)
+{
+	blkiocg_update_idle_time_stats(blkg);
+}
+
+static inline void
+cfq_blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg)
+{
+	blkiocg_update_avg_queue_size_stats(blkg);
+}
+
+static inline void
+cfq_blkiocg_update_set_idle_time_stats(struct blkio_group *blkg)
+{
+	blkiocg_update_set_idle_time_stats(blkg);
+}
+
+static inline void cfq_blkiocg_update_dispatch_stats(struct blkio_group *blkg,
+				uint64_t bytes, bool direction, bool sync)
+{
+	blkiocg_update_dispatch_stats(blkg, bytes, direction, sync);
+}
+
+static inline void cfq_blkiocg_update_completion_stats(struct blkio_group *blkg, uint64_t start_time, uint64_t io_start_time, bool direction, bool sync)
+{
+	blkiocg_update_completion_stats(blkg, start_time, io_start_time,
+				direction, sync);
+}
+
+static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
+			struct blkio_group *blkg, void *key, dev_t dev) {
+	blkiocg_add_blkio_group(blkcg, blkg, key, dev);
+}
+
+static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
+{
+	return blkiocg_del_blkio_group(blkg);
+}
+
+#else /* CFQ_GROUP_IOSCHED */
+static inline void cfq_blkiocg_update_io_add_stats(struct blkio_group *blkg,
+	struct blkio_group *curr_blkg, bool direction, bool sync) {}
+
+static inline void cfq_blkiocg_update_dequeue_stats(struct blkio_group *blkg,
+			unsigned long dequeue) {}
+
+static inline void cfq_blkiocg_update_timeslice_used(struct blkio_group *blkg,
+			unsigned long time) {}
+static inline void cfq_blkiocg_set_start_empty_time(struct blkio_group *blkg) {}
+static inline void cfq_blkiocg_update_io_remove_stats(struct blkio_group *blkg,
+				bool direction, bool sync) {}
+static inline void cfq_blkiocg_update_io_merged_stats(struct blkio_group *blkg,
+		bool direction, bool sync) {}
+static inline void cfq_blkiocg_update_idle_time_stats(struct blkio_group *blkg)
+{
+}
+static inline void
+cfq_blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg) {}
+
+static inline void
+cfq_blkiocg_update_set_idle_time_stats(struct blkio_group *blkg) {}
+
+static inline void cfq_blkiocg_update_dispatch_stats(struct blkio_group *blkg,
+				uint64_t bytes, bool direction, bool sync) {}
+static inline void cfq_blkiocg_update_completion_stats(struct blkio_group *blkg, uint64_t start_time, uint64_t io_start_time, bool direction, bool sync) {}
+
+static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
+			struct blkio_group *blkg, void *key, dev_t dev) {}
+static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
+{
+	return 0;
+}
+
+#endif /* CFQ_GROUP_IOSCHED */
+#endif
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 4eb8e9ea4af5..119f07b74dc0 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -6,6 +6,7 @@
 #include <linux/elevator.h>
 #include <linux/fd.h>
 #include <linux/hdreg.h>
+#include <linux/slab.h>
 #include <linux/syscalls.h>
 #include <linux/smp_lock.h>
 #include <linux/types.h>
@@ -534,56 +535,6 @@ out:
 	return err;
 }
 
-struct compat_blk_user_trace_setup {
-	char name[32];
-	u16 act_mask;
-	u32 buf_size;
-	u32 buf_nr;
-	compat_u64 start_lba;
-	compat_u64 end_lba;
-	u32 pid;
-};
-#define BLKTRACESETUP32 _IOWR(0x12, 115, struct compat_blk_user_trace_setup)
-
-static int compat_blk_trace_setup(struct block_device *bdev, char __user *arg)
-{
-	struct blk_user_trace_setup buts;
-	struct compat_blk_user_trace_setup cbuts;
-	struct request_queue *q;
-	char b[BDEVNAME_SIZE];
-	int ret;
-
-	q = bdev_get_queue(bdev);
-	if (!q)
-		return -ENXIO;
-
-	if (copy_from_user(&cbuts, arg, sizeof(cbuts)))
-		return -EFAULT;
-
-	bdevname(bdev, b);
-
-	buts = (struct blk_user_trace_setup) {
-		.act_mask = cbuts.act_mask,
-		.buf_size = cbuts.buf_size,
-		.buf_nr = cbuts.buf_nr,
-		.start_lba = cbuts.start_lba,
-		.end_lba = cbuts.end_lba,
-		.pid = cbuts.pid,
-	};
-	memcpy(&buts.name, &cbuts.name, 32);
-
-	mutex_lock(&bdev->bd_mutex);
-	ret = do_blk_trace_setup(q, b, bdev->bd_dev, bdev, &buts);
-	mutex_unlock(&bdev->bd_mutex);
-	if (ret)
-		return ret;
-
-	if (copy_to_user(arg, &buts.name, 32))
-		return -EFAULT;
-
-	return 0;
-}
-
 static int compat_blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
 			unsigned cmd, unsigned long arg)
 {
@@ -752,6 +703,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKFLSBUF:
 	case BLKROSET:
 	case BLKDISCARD:
+	case BLKSECDISCARD:
 	/*
 	 * the ones below are implemented in blkdev_locked_ioctl,
 	 * but we call blkdev_ioctl, which gets the lock for us
@@ -801,16 +753,10 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		return compat_put_u64(arg, bdev->bd_inode->i_size);
 
 	case BLKTRACESETUP32:
-		lock_kernel();
-		ret = compat_blk_trace_setup(bdev, compat_ptr(arg));
-		unlock_kernel();
-		return ret;
 	case BLKTRACESTART: /* compatible */
 	case BLKTRACESTOP:  /* compatible */
 	case BLKTRACETEARDOWN: /* compatible */
-		lock_kernel();
 		ret = blk_trace_ioctl(bdev, cmd, compat_ptr(arg));
-		unlock_kernel();
 		return ret;
 	default:
 		if (disk->fops->compat_ioctl)
diff --git a/block/elevator.c b/block/elevator.c
index 9ad5ccc4c5ee..4e11559aa2b0 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -79,8 +79,13 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 	/*
 	 * Don't merge file system requests and discard requests
 	 */
-	if (bio_rw_flagged(bio, BIO_RW_DISCARD) !=
-	    bio_rw_flagged(rq->bio, BIO_RW_DISCARD))
+	if ((bio->bi_rw & REQ_DISCARD) != (rq->bio->bi_rw & REQ_DISCARD))
+		return 0;
+
+	/*
+	 * Don't merge discard requests and secure discard requests
+	 */
+	if ((bio->bi_rw & REQ_SECURE) != (rq->bio->bi_rw & REQ_SECURE))
 		return 0;
 
 	/*
@@ -154,7 +159,7 @@ static struct elevator_type *elevator_get(const char *name)
 
 		spin_unlock(&elv_list_lock);
 
-		sprintf(elv, "%s-iosched", name);
+		snprintf(elv, sizeof(elv), "%s-iosched", name);
 
 		request_module("%s", elv);
 		spin_lock(&elv_list_lock);
@@ -242,9 +247,11 @@ int elevator_init(struct request_queue *q, char *name)
 {
 	struct elevator_type *e = NULL;
 	struct elevator_queue *eq;
-	int ret = 0;
 	void *data;
 
+	if (unlikely(q->elevator))
+		return 0;
+
 	INIT_LIST_HEAD(&q->queue_head);
 	q->last_merge = NULL;
 	q->end_sector = 0;
@@ -284,7 +291,7 @@ int elevator_init(struct request_queue *q, char *name)
 	}
 
 	elevator_attach(q, eq, data);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(elevator_init);
 
@@ -426,7 +433,8 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	list_for_each_prev(entry, &q->queue_head) {
 		struct request *pos = list_entry_rq(entry);
 
-		if (blk_discard_rq(rq) != blk_discard_rq(pos))
+		if ((rq->cmd_flags & REQ_DISCARD) !=
+		    (pos->cmd_flags & REQ_DISCARD))
 			break;
 		if (rq_data_dir(rq) != rq_data_dir(pos))
 			break;
@@ -474,6 +482,15 @@ 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 +501,7 @@ 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;
 
 	/*
@@ -530,6 +547,15 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
 	q->last_merge = rq;
 }
 
+void elv_bio_merged(struct request_queue *q, struct request *rq,
+			struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_bio_merged_fn)
+		e->ops->elevator_bio_merged_fn(q, rq, bio);
+}
+
 void elv_requeue_request(struct request_queue *q, struct request *rq)
 {
 	/*
@@ -538,7 +564,7 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
 	 */
 	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]--;
-		if (blk_sorted_rq(rq))
+		if (rq->cmd_flags & REQ_SORTED)
 			elv_deactivate_rq(q, rq);
 	}
 
@@ -624,7 +650,8 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		break;
 
 	case ELEVATOR_INSERT_SORT:
-		BUG_ON(!blk_fs_request(rq) && !blk_discard_rq(rq));
+		BUG_ON(rq->cmd_type != REQ_TYPE_FS &&
+		       !(rq->cmd_flags & REQ_DISCARD));
 		rq->cmd_flags |= REQ_SORTED;
 		q->nr_sorted++;
 		if (rq_mergeable(rq)) {
@@ -696,7 +723,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where,
 		/*
 		 * toggle ordered color
 		 */
-		if (blk_barrier_rq(rq))
+		if (rq->cmd_flags & REQ_HARDBARRIER)
 			q->ordcolor ^= 1;
 
 		/*
@@ -709,7 +736,8 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where,
 		 * this request is scheduling boundary, update
 		 * end_sector
 		 */
-		if (blk_fs_request(rq) || blk_discard_rq(rq)) {
+		if (rq->cmd_type == REQ_TYPE_FS ||
+		    (rq->cmd_flags & REQ_DISCARD)) {
 			q->end_sector = rq_end_sector(rq);
 			q->boundary_rq = rq;
 		}
@@ -823,7 +851,8 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 	 */
 	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]--;
-		if (blk_sorted_rq(rq) && e->ops->elevator_completed_req_fn)
+		if ((rq->cmd_flags & REQ_SORTED) &&
+		    e->ops->elevator_completed_req_fn)
 			e->ops->elevator_completed_req_fn(q, rq);
 	}
 
@@ -883,7 +912,7 @@ 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,
 };
@@ -909,14 +938,17 @@ int elv_register_queue(struct request_queue *q)
 			}
 		}
 		kobject_uevent(&e->kobj, KOBJ_ADD);
+		e->registered = 1;
 	}
 	return error;
 }
+EXPORT_SYMBOL(elv_register_queue);
 
 static void __elv_unregister_queue(struct elevator_queue *e)
 {
 	kobject_uevent(&e->kobj, KOBJ_REMOVE);
 	kobject_del(&e->kobj);
+	e->registered = 0;
 }
 
 void elv_unregister_queue(struct request_queue *q)
@@ -924,6 +956,7 @@ void elv_unregister_queue(struct request_queue *q)
 	if (q)
 		__elv_unregister_queue(q->elevator);
 }
+EXPORT_SYMBOL(elv_unregister_queue);
 
 void elv_register(struct elevator_type *e)
 {
@@ -978,18 +1011,19 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 {
 	struct elevator_queue *old_elevator, *e;
 	void *data;
+	int err;
 
 	/*
 	 * Allocate new elevator
 	 */
 	e = elevator_alloc(q, new_e);
 	if (!e)
-		return 0;
+		return -ENOMEM;
 
 	data = elevator_init_queue(q, e);
 	if (!data) {
 		kobject_put(&e->kobj);
-		return 0;
+		return -ENOMEM;
 	}
 
 	/*
@@ -1010,10 +1044,13 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 
 	spin_unlock_irq(q->queue_lock);
 
-	__elv_unregister_queue(old_elevator);
+	if (old_elevator->registered) {
+		__elv_unregister_queue(old_elevator);
 
-	if (elv_register_queue(q))
-		goto fail_register;
+		err = elv_register_queue(q);
+		if (err)
+			goto fail_register;
+	}
 
 	/*
 	 * finally exit old elevator and turn off BYPASS.
@@ -1025,7 +1062,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 
 	blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name);
 
-	return 1;
+	return 0;
 
 fail_register:
 	/*
@@ -1040,17 +1077,19 @@ fail_register:
 	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
 	spin_unlock_irq(q->queue_lock);
 
-	return 0;
+	return err;
 }
 
-ssize_t elv_iosched_store(struct request_queue *q, const char *name,
-			  size_t count)
+/*
+ * Switch this queue to the given IO scheduler.
+ */
+int elevator_change(struct request_queue *q, const char *name)
 {
 	char elevator_name[ELV_NAME_MAX];
 	struct elevator_type *e;
 
 	if (!q->elevator)
-		return count;
+		return -ENXIO;
 
 	strlcpy(elevator_name, name, sizeof(elevator_name));
 	e = elevator_get(strstrip(elevator_name));
@@ -1061,13 +1100,27 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 
 	if (!strcmp(elevator_name, q->elevator->elevator_type->elevator_name)) {
 		elevator_put(e);
-		return count;
+		return 0;
 	}
 
-	if (!elevator_switch(q, e))
-		printk(KERN_ERR "elevator: switch to %s failed\n",
-							elevator_name);
-	return count;
+	return elevator_switch(q, e);
+}
+EXPORT_SYMBOL(elevator_change);
+
+ssize_t elv_iosched_store(struct request_queue *q, const char *name,
+			  size_t count)
+{
+	int ret;
+
+	if (!q->elevator)
+		return count;
+
+	ret = elevator_change(q, name);
+	if (!ret)
+		return count;
+
+	printk(KERN_ERR "elevator: switch to %s failed\n", name);
+	return ret;
 }
 
 ssize_t elv_iosched_show(struct request_queue *q, char *name)
@@ -1077,7 +1130,7 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name)
 	struct elevator_type *__e;
 	int len = 0;
 
-	if (!q->elevator)
+	if (!q->elevator || !blk_queue_stackable(q))
 		return sprintf(name, "none\n");
 
 	elv = e->elevator_type;
diff --git a/block/genhd.c b/block/genhd.c
index d13ba76a169c..59a2db6fecef 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -596,6 +596,7 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 
 	return disk;
 }
+EXPORT_SYMBOL(get_gendisk);
 
 /**
  * bdget_disk - do bdget() by gendisk and partition number
@@ -987,7 +988,6 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
 	if (!new_ptbl)
 		return -ENOMEM;
 
-	INIT_RCU_HEAD(&new_ptbl->rcu_head);
 	new_ptbl->len = target;
 
 	for (i = 0; i < len; i++)
diff --git a/block/ioctl.c b/block/ioctl.c
index be48ea51faee..d8052f0dabd3 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -1,5 +1,6 @@
 #include <linux/capability.h>
 #include <linux/blkdev.h>
+#include <linux/gfp.h>
 #include <linux/blkpg.h>
 #include <linux/hdreg.h>
 #include <linux/backing-dev.h>
@@ -113,8 +114,10 @@ static int blkdev_reread_part(struct block_device *bdev)
 }
 
 static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
-			     uint64_t len)
+			     uint64_t len, int secure)
 {
+	unsigned long flags = BLKDEV_IFL_WAIT;
+
 	if (start & 511)
 		return -EINVAL;
 	if (len & 511)
@@ -124,8 +127,9 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 
 	if (start + len > (bdev->bd_inode->i_size >> 9))
 		return -EINVAL;
-	return blkdev_issue_discard(bdev, start, len, GFP_KERNEL,
-				    DISCARD_FL_WAIT);
+	if (secure)
+		flags |= BLKDEV_IFL_SECURE;
+	return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags);
 }
 
 static int put_ushort(unsigned long arg, unsigned short val)
@@ -162,18 +166,10 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
 			unsigned cmd, unsigned long arg)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	int ret;
 
 	if (disk->fops->ioctl)
 		return disk->fops->ioctl(bdev, mode, cmd, arg);
 
-	if (disk->fops->locked_ioctl) {
-		lock_kernel();
-		ret = disk->fops->locked_ioctl(bdev, mode, cmd, arg);
-		unlock_kernel();
-		return ret;
-	}
-
 	return -ENOTTY;
 }
 /*
@@ -184,8 +180,7 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
 EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
 
 /*
- * always keep this in sync with compat_blkdev_ioctl() and
- * compat_blkdev_locked_ioctl()
+ * always keep this in sync with compat_blkdev_ioctl()
  */
 int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 			unsigned long arg)
@@ -205,10 +200,8 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		if (ret != -EINVAL && ret != -ENOTTY)
 			return ret;
 
-		lock_kernel();
 		fsync_bdev(bdev);
 		invalidate_bdev(bdev);
-		unlock_kernel();
 		return 0;
 
 	case BLKROSET:
@@ -220,12 +213,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 			return -EACCES;
 		if (get_user(n, (int __user *)(arg)))
 			return -EFAULT;
-		lock_kernel();
 		set_device_ro(bdev, n);
-		unlock_kernel();
 		return 0;
 
-	case BLKDISCARD: {
+	case BLKDISCARD:
+	case BLKSECDISCARD: {
 		uint64_t range[2];
 
 		if (!(mode & FMODE_WRITE))
@@ -234,7 +226,8 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		if (copy_from_user(range, (void __user *)arg, sizeof(range)))
 			return -EFAULT;
 
-		return blk_ioctl_discard(bdev, range[0], range[1]);
+		return blk_ioctl_discard(bdev, range[0], range[1],
+					 cmd == BLKSECDISCARD);
 	}
 
 	case HDIO_GETGEO: {
@@ -308,14 +301,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 			bd_release(bdev);
 		return ret;
 	case BLKPG:
-		lock_kernel();
 		ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
-		unlock_kernel();
 		break;
 	case BLKRRPART:
-		lock_kernel();
 		ret = blkdev_reread_part(bdev);
-		unlock_kernel();
 		break;
 	case BLKGETSIZE:
 		size = bdev->bd_inode->i_size;
@@ -328,9 +317,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKTRACESTOP:
 	case BLKTRACESETUP:
 	case BLKTRACETEARDOWN:
-		lock_kernel();
 		ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg);
-		unlock_kernel();
 		break;
 	default:
 		ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index 3a0d369d08c7..232c4b38cd37 100644
--- a/block/noop-iosched.c
+++ b/block/noop-iosched.c
@@ -5,6 +5,7 @@
 #include <linux/elevator.h>
 #include <linux/bio.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 
 struct noop_data {