Forward to 2.6.33-rc8

Merge branch 'linus' into rt/head with a pile of conflicts.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

22 files changed, 2827 insertions, 2007 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 9be0b56eaee1..e20fbde0875c 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -77,6 +77,28 @@ 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 7e803fc88770..b71abfb0d726 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -12,24 +12,14 @@ config IOSCHED_NOOP
 	  that do their own scheduling and require only minimal assistance from
 	  the kernel.
 
-config IOSCHED_AS
-	tristate "Anticipatory I/O scheduler"
-	default y
-	---help---
-	  The anticipatory I/O scheduler is generally a good choice for most
-	  environments, but is quite large and complex when compared to the
-	  deadline I/O scheduler, it can also be slower in some cases
-	  especially some database loads.
-
 config IOSCHED_DEADLINE
 	tristate "Deadline I/O scheduler"
 	default y
 	---help---
-	  The deadline I/O scheduler is simple and compact, and is often as
-	  good as the anticipatory I/O scheduler, and in some database
-	  workloads, better. In the case of a single process performing I/O to
-	  a disk at any one time, its behaviour is almost identical to the
-	  anticipatory I/O scheduler and so is a good choice.
+	  The deadline I/O scheduler is simple and compact. It will provide
+	  CSCAN service with FIFO expiration of requests, switching to
+	  a new point in the service tree and doing a batch of IO from there
+	  in case of expiry.
 
 config IOSCHED_CFQ
 	tristate "CFQ I/O scheduler"
@@ -37,9 +27,28 @@ config IOSCHED_CFQ
 	---help---
 	  The CFQ I/O scheduler tries to distribute bandwidth equally
 	  among all processes in the system. It should provide a fair
-	  working environment, suitable for desktop systems.
+	  and low latency working environment, suitable for both desktop
+	  and server systems.
+
 	  This is the default I/O scheduler.
 
+config CFQ_GROUP_IOSCHED
+	bool "CFQ Group Scheduling support"
+	depends on IOSCHED_CFQ && CGROUPS
+	select 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
@@ -47,9 +56,6 @@ choice
 	  Select the I/O scheduler which will be used by default for all
 	  block devices.
 
-	config DEFAULT_AS
-		bool "Anticipatory" if IOSCHED_AS=y
-
 	config DEFAULT_DEADLINE
 		bool "Deadline" if IOSCHED_DEADLINE=y
 
@@ -63,7 +69,6 @@ endchoice
 
 config DEFAULT_IOSCHED
 	string
-	default "anticipatory" if DEFAULT_AS
 	default "deadline" if DEFAULT_DEADLINE
 	default "cfq" if DEFAULT_CFQ
 	default "noop" if DEFAULT_NOOP
diff --git a/block/Makefile b/block/Makefile
index 6c54ed0ff755..cb2d515ebd6e 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,11 +5,11 @@
 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 \
-			ioctl.o genhd.o scsi_ioctl.o
+			blk-iopoll.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
+obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
-obj-$(CONFIG_IOSCHED_AS)	+= as-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 
diff --git a/block/as-iosched.c b/block/as-iosched.c
deleted file mode 100644
index 7a12cf6ee1d3..000000000000
--- a/block/as-iosched.c
+++ /dev/null
@@ -1,1520 +0,0 @@
-/*
- *  Anticipatory & deadline i/o scheduler.
- *
- *  Copyright (C) 2002 Jens Axboe <axboe@kernel.dk>
- *                     Nick Piggin <nickpiggin@yahoo.com.au>
- *
- */
-#include <linux/kernel.h>
-#include <linux/fs.h>
-#include <linux/blkdev.h>
-#include <linux/elevator.h>
-#include <linux/bio.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/compiler.h>
-#include <linux/rbtree.h>
-#include <linux/interrupt.h>
-
-/*
- * See Documentation/block/as-iosched.txt
- */
-
-/*
- * max time before a read is submitted.
- */
-#define default_read_expire (HZ / 8)
-
-/*
- * ditto for writes, these limits are not hard, even
- * if the disk is capable of satisfying them.
- */
-#define default_write_expire (HZ / 4)
-
-/*
- * read_batch_expire describes how long we will allow a stream of reads to
- * persist before looking to see whether it is time to switch over to writes.
- */
-#define default_read_batch_expire (HZ / 2)
-
-/*
- * write_batch_expire describes how long we want a stream of writes to run for.
- * This is not a hard limit, but a target we set for the auto-tuning thingy.
- * See, the problem is: we can send a lot of writes to disk cache / TCQ in
- * a short amount of time...
- */
-#define default_write_batch_expire (HZ / 8)
-
-/*
- * max time we may wait to anticipate a read (default around 6ms)
- */
-#define default_antic_expire ((HZ / 150) ? HZ / 150 : 1)
-
-/*
- * Keep track of up to 20ms thinktimes. We can go as big as we like here,
- * however huge values tend to interfere and not decay fast enough. A program
- * might be in a non-io phase of operation. Waiting on user input for example,
- * or doing a lengthy computation. A small penalty can be justified there, and
- * will still catch out those processes that constantly have large thinktimes.
- */
-#define MAX_THINKTIME (HZ/50UL)
-
-/* Bits in as_io_context.state */
-enum as_io_states {
-	AS_TASK_RUNNING=0,	/* Process has not exited */
-	AS_TASK_IOSTARTED,	/* Process has started some IO */
-	AS_TASK_IORUNNING,	/* Process has completed some IO */
-};
-
-enum anticipation_status {
-	ANTIC_OFF=0,		/* Not anticipating (normal operation)	*/
-	ANTIC_WAIT_REQ,		/* The last read has not yet completed  */
-	ANTIC_WAIT_NEXT,	/* Currently anticipating a request vs
-				   last read (which has completed) */
-	ANTIC_FINISHED,		/* Anticipating but have found a candidate
-				 * or timed out */
-};
-
-struct as_data {
-	/*
-	 * run time data
-	 */
-
-	struct request_queue *q;	/* the "owner" queue */
-
-	/*
-	 * requests (as_rq s) are present on both sort_list and fifo_list
-	 */
-	struct rb_root sort_list[2];
-	struct list_head fifo_list[2];
-
-	struct request *next_rq[2];	/* next in sort order */
-	sector_t last_sector[2];	/* last SYNC & ASYNC sectors */
-
-	unsigned long exit_prob;	/* probability a task will exit while
-					   being waited on */
-	unsigned long exit_no_coop;	/* probablility an exited task will
-					   not be part of a later cooperating
-					   request */
-	unsigned long new_ttime_total; 	/* mean thinktime on new proc */
-	unsigned long new_ttime_mean;
-	u64 new_seek_total;		/* mean seek on new proc */
-	sector_t new_seek_mean;
-
-	unsigned long current_batch_expires;
-	unsigned long last_check_fifo[2];
-	int changed_batch;		/* 1: waiting for old batch to end */
-	int new_batch;			/* 1: waiting on first read complete */
-	int batch_data_dir;		/* current batch SYNC / ASYNC */
-	int write_batch_count;		/* max # of reqs in a write batch */
-	int current_write_count;	/* how many requests left this batch */
-	int write_batch_idled;		/* has the write batch gone idle? */
-
-	enum anticipation_status antic_status;
-	unsigned long antic_start;	/* jiffies: when it started */
-	struct timer_list antic_timer;	/* anticipatory scheduling timer */
-	struct work_struct antic_work;	/* Deferred unplugging */
-	struct io_context *io_context;	/* Identify the expected process */
-	int ioc_finished; /* IO associated with io_context is finished */
-	int nr_dispatched;
-
-	/*
-	 * settings that change how the i/o scheduler behaves
-	 */
-	unsigned long fifo_expire[2];
-	unsigned long batch_expire[2];
-	unsigned long antic_expire;
-};
-
-/*
- * per-request data.
- */
-enum arq_state {
-	AS_RQ_NEW=0,		/* New - not referenced and not on any lists */
-	AS_RQ_QUEUED,		/* In the request queue. It belongs to the
-				   scheduler */
-	AS_RQ_DISPATCHED,	/* On the dispatch list. It belongs to the
-				   driver now */
-	AS_RQ_PRESCHED,		/* Debug poisoning for requests being used */
-	AS_RQ_REMOVED,
-	AS_RQ_MERGED,
-	AS_RQ_POSTSCHED,	/* when they shouldn't be */
-};
-
-#define RQ_IOC(rq)	((struct io_context *) (rq)->elevator_private)
-#define RQ_STATE(rq)	((enum arq_state)(rq)->elevator_private2)
-#define RQ_SET_STATE(rq, state)	((rq)->elevator_private2 = (void *) state)
-
-static DEFINE_PER_CPU(unsigned long, ioc_count);
-static struct completion *ioc_gone;
-static DEFINE_SPINLOCK(ioc_gone_lock);
-
-static void as_move_to_dispatch(struct as_data *ad, struct request *rq);
-static void as_antic_stop(struct as_data *ad);
-
-/*
- * IO Context helper functions
- */
-
-/* Called to deallocate the as_io_context */
-static void free_as_io_context(struct as_io_context *aic)
-{
-	kfree(aic);
-	elv_ioc_count_dec(ioc_count);
-	if (ioc_gone) {
-		/*
-		 * AS scheduler is exiting, grab exit lock and check
-		 * the pending io context count. If it hits zero,
-		 * complete ioc_gone and set it back to NULL.
-		 */
-		spin_lock(&ioc_gone_lock);
-		if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
-			complete(ioc_gone);
-			ioc_gone = NULL;
-		}
-		spin_unlock(&ioc_gone_lock);
-	}
-}
-
-static void as_trim(struct io_context *ioc)
-{
-	spin_lock_irq(&ioc->lock);
-	if (ioc->aic)
-		free_as_io_context(ioc->aic);
-	ioc->aic = NULL;
-	spin_unlock_irq(&ioc->lock);
-}
-
-/* Called when the task exits */
-static void exit_as_io_context(struct as_io_context *aic)
-{
-	WARN_ON(!test_bit(AS_TASK_RUNNING, &aic->state));
-	clear_bit(AS_TASK_RUNNING, &aic->state);
-}
-
-static struct as_io_context *alloc_as_io_context(void)
-{
-	struct as_io_context *ret;
-
-	ret = kmalloc(sizeof(*ret), GFP_ATOMIC);
-	if (ret) {
-		ret->dtor = free_as_io_context;
-		ret->exit = exit_as_io_context;
-		ret->state = 1 << AS_TASK_RUNNING;
-		atomic_set(&ret->nr_queued, 0);
-		atomic_set(&ret->nr_dispatched, 0);
-		spin_lock_init(&ret->lock);
-		ret->ttime_total = 0;
-		ret->ttime_samples = 0;
-		ret->ttime_mean = 0;
-		ret->seek_total = 0;
-		ret->seek_samples = 0;
-		ret->seek_mean = 0;
-		elv_ioc_count_inc(ioc_count);
-	}
-
-	return ret;
-}
-
-/*
- * If the current task has no AS IO context then create one and initialise it.
- * Then take a ref on the task's io context and return it.
- */
-static struct io_context *as_get_io_context(int node)
-{
-	struct io_context *ioc = get_io_context(GFP_ATOMIC, node);
-	if (ioc && !ioc->aic) {
-		ioc->aic = alloc_as_io_context();
-		if (!ioc->aic) {
-			put_io_context(ioc);
-			ioc = NULL;
-		}
-	}
-	return ioc;
-}
-
-static void as_put_io_context(struct request *rq)
-{
-	struct as_io_context *aic;
-
-	if (unlikely(!RQ_IOC(rq)))
-		return;
-
-	aic = RQ_IOC(rq)->aic;
-
-	if (rq_is_sync(rq) && aic) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&aic->lock, flags);
-		set_bit(AS_TASK_IORUNNING, &aic->state);
-		aic->last_end_request = jiffies;
-		spin_unlock_irqrestore(&aic->lock, flags);
-	}
-
-	put_io_context(RQ_IOC(rq));
-}
-
-/*
- * rb tree support functions
- */
-#define RQ_RB_ROOT(ad, rq)	(&(ad)->sort_list[rq_is_sync((rq))])
-
-static void as_add_rq_rb(struct as_data *ad, struct request *rq)
-{
-	struct request *alias;
-
-	while ((unlikely(alias = elv_rb_add(RQ_RB_ROOT(ad, rq), rq)))) {
-		as_move_to_dispatch(ad, alias);
-		as_antic_stop(ad);
-	}
-}
-
-static inline void as_del_rq_rb(struct as_data *ad, struct request *rq)
-{
-	elv_rb_del(RQ_RB_ROOT(ad, rq), rq);
-}
-
-/*
- * IO Scheduler proper
- */
-
-#define MAXBACK (1024 * 1024)	/*
-				 * Maximum distance the disk will go backward
-				 * for a request.
-				 */
-
-#define BACK_PENALTY	2
-
-/*
- * as_choose_req selects the preferred one of two requests of the same data_dir
- * ignoring time - eg. timeouts, which is the job of as_dispatch_request
- */
-static struct request *
-as_choose_req(struct as_data *ad, struct request *rq1, struct request *rq2)
-{
-	int data_dir;
-	sector_t last, s1, s2, d1, d2;
-	int r1_wrap=0, r2_wrap=0;	/* requests are behind the disk head */
-	const sector_t maxback = MAXBACK;
-
-	if (rq1 == NULL || rq1 == rq2)
-		return rq2;
-	if (rq2 == NULL)
-		return rq1;
-
-	data_dir = rq_is_sync(rq1);
-
-	last = ad->last_sector[data_dir];
-	s1 = blk_rq_pos(rq1);
-	s2 = blk_rq_pos(rq2);
-
-	BUG_ON(data_dir != rq_is_sync(rq2));
-
-	/*
-	 * Strict one way elevator _except_ in the case where we allow
-	 * short backward seeks which are biased as twice the cost of a
-	 * similar forward seek.
-	 */
-	if (s1 >= last)
-		d1 = s1 - last;
-	else if (s1+maxback >= last)
-		d1 = (last - s1)*BACK_PENALTY;
-	else {
-		r1_wrap = 1;
-		d1 = 0; /* shut up, gcc */
-	}
-
-	if (s2 >= last)
-		d2 = s2 - last;
-	else if (s2+maxback >= last)
-		d2 = (last - s2)*BACK_PENALTY;
-	else {
-		r2_wrap = 1;
-		d2 = 0;
-	}
-
-	/* Found required data */
-	if (!r1_wrap && r2_wrap)
-		return rq1;
-	else if (!r2_wrap && r1_wrap)
-		return rq2;
-	else if (r1_wrap && r2_wrap) {
-		/* both behind the head */
-		if (s1 <= s2)
-			return rq1;
-		else
-			return rq2;
-	}
-
-	/* Both requests in front of the head */
-	if (d1 < d2)
-		return rq1;
-	else if (d2 < d1)
-		return rq2;
-	else {
-		if (s1 >= s2)
-			return rq1;
-		else
-			return rq2;
-	}
-}
-
-/*
- * as_find_next_rq finds the next request after @prev in elevator order.
- * this with as_choose_req form the basis for how the scheduler chooses
- * what request to process next. Anticipation works on top of this.
- */
-static struct request *
-as_find_next_rq(struct as_data *ad, struct request *last)
-{
-	struct rb_node *rbnext = rb_next(&last->rb_node);
-	struct rb_node *rbprev = rb_prev(&last->rb_node);
-	struct request *next = NULL, *prev = NULL;
-
-	BUG_ON(RB_EMPTY_NODE(&last->rb_node));
-
-	if (rbprev)
-		prev = rb_entry_rq(rbprev);
-
-	if (rbnext)
-		next = rb_entry_rq(rbnext);
-	else {
-		const int data_dir = rq_is_sync(last);
-
-		rbnext = rb_first(&ad->sort_list[data_dir]);
-		if (rbnext && rbnext != &last->rb_node)
-			next = rb_entry_rq(rbnext);
-	}
-
-	return as_choose_req(ad, next, prev);
-}
-
-/*
- * anticipatory scheduling functions follow
- */
-
-/*
- * as_antic_expired tells us when we have anticipated too long.
- * The funny "absolute difference" math on the elapsed time is to handle
- * jiffy wraps, and disks which have been idle for 0x80000000 jiffies.
- */
-static int as_antic_expired(struct as_data *ad)
-{
-	long delta_jif;
-
-	delta_jif = jiffies - ad->antic_start;
-	if (unlikely(delta_jif < 0))
-		delta_jif = -delta_jif;
-	if (delta_jif < ad->antic_expire)
-		return 0;
-
-	return 1;
-}
-
-/*
- * as_antic_waitnext starts anticipating that a nice request will soon be
- * submitted. See also as_antic_waitreq
- */
-static void as_antic_waitnext(struct as_data *ad)
-{
-	unsigned long timeout;
-
-	BUG_ON(ad->antic_status != ANTIC_OFF
-			&& ad->antic_status != ANTIC_WAIT_REQ);
-
-	timeout = ad->antic_start + ad->antic_expire;
-
-	mod_timer(&ad->antic_timer, timeout);
-
-	ad->antic_status = ANTIC_WAIT_NEXT;
-}
-
-/*
- * as_antic_waitreq starts anticipating. We don't start timing the anticipation
- * until the request that we're anticipating on has finished. This means we
- * are timing from when the candidate process wakes up hopefully.
- */
-static void as_antic_waitreq(struct as_data *ad)
-{
-	BUG_ON(ad->antic_status == ANTIC_FINISHED);
-	if (ad->antic_status == ANTIC_OFF) {
-		if (!ad->io_context || ad->ioc_finished)
-			as_antic_waitnext(ad);
-		else
-			ad->antic_status = ANTIC_WAIT_REQ;
-	}
-}
-
-/*
- * This is called directly by the functions in this file to stop anticipation.
- * We kill the timer and schedule a call to the request_fn asap.
- */
-static void as_antic_stop(struct as_data *ad)
-{
-	int status = ad->antic_status;
-
-	if (status == ANTIC_WAIT_REQ || status == ANTIC_WAIT_NEXT) {
-		if (status == ANTIC_WAIT_NEXT)
-			del_timer(&ad->antic_timer);
-		ad->antic_status = ANTIC_FINISHED;
-		/* see as_work_handler */
-		kblockd_schedule_work(ad->q, &ad->antic_work);
-	}
-}
-
-/*
- * as_antic_timeout is the timer function set by as_antic_waitnext.
- */
-static void as_antic_timeout(unsigned long data)
-{
-	struct request_queue *q = (struct request_queue *)data;
-	struct as_data *ad = q->elevator->elevator_data;
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	if (ad->antic_status == ANTIC_WAIT_REQ
-			|| ad->antic_status == ANTIC_WAIT_NEXT) {
-		struct as_io_context *aic;
-		spin_lock(&ad->io_context->lock);
-		aic = ad->io_context->aic;
-
-		ad->antic_status = ANTIC_FINISHED;
-		kblockd_schedule_work(q, &ad->antic_work);
-
-		if (aic->ttime_samples == 0) {
-			/* process anticipated on has exited or timed out*/
-			ad->exit_prob = (7*ad->exit_prob + 256)/8;
-		}
-		if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
-			/* process not "saved" by a cooperating request */
-			ad->exit_no_coop = (7*ad->exit_no_coop + 256)/8;
-		}
-		spin_unlock(&ad->io_context->lock);
-	}
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void as_update_thinktime(struct as_data *ad, struct as_io_context *aic,
-				unsigned long ttime)
-{
-	/* fixed point: 1.0 == 1<<8 */
-	if (aic->ttime_samples == 0) {
-		ad->new_ttime_total = (7*ad->new_ttime_total + 256*ttime) / 8;
-		ad->new_ttime_mean = ad->new_ttime_total / 256;
-
-		ad->exit_prob = (7*ad->exit_prob)/8;
-	}
-	aic->ttime_samples = (7*aic->ttime_samples + 256) / 8;
-	aic->ttime_total = (7*aic->ttime_total + 256*ttime) / 8;
-	aic->ttime_mean = (aic->ttime_total + 128) / aic->ttime_samples;
-}
-
-static void as_update_seekdist(struct as_data *ad, struct as_io_context *aic,
-				sector_t sdist)
-{
-	u64 total;
-
-	if (aic->seek_samples == 0) {
-		ad->new_seek_total = (7*ad->new_seek_total + 256*(u64)sdist)/8;
-		ad->new_seek_mean = ad->new_seek_total / 256;
-	}
-
-	/*
-	 * Don't allow the seek distance to get too large from the
-	 * odd fragment, pagein, etc
-	 */
-	if (aic->seek_samples <= 60) /* second&third seek */
-		sdist = min(sdist, (aic->seek_mean * 4) + 2*1024*1024);
-	else
-		sdist = min(sdist, (aic->seek_mean * 4)	+ 2*1024*64);
-
-	aic->seek_samples = (7*aic->seek_samples + 256) / 8;
-	aic->seek_total = (7*aic->seek_total + (u64)256*sdist) / 8;
-	total = aic->seek_total + (aic->seek_samples/2);
-	do_div(total, aic->seek_samples);
-	aic->seek_mean = (sector_t)total;
-}
-
-/*
- * as_update_iohist keeps a decaying histogram of IO thinktimes, and
- * updates @aic->ttime_mean based on that. It is called when a new
- * request is queued.
- */
-static void as_update_iohist(struct as_data *ad, struct as_io_context *aic,
-				struct request *rq)
-{
-	int data_dir = rq_is_sync(rq);
-	unsigned long thinktime = 0;
-	sector_t seek_dist;
-
-	if (aic == NULL)
-		return;
-
-	if (data_dir == BLK_RW_SYNC) {
-		unsigned long in_flight = atomic_read(&aic->nr_queued)
-					+ atomic_read(&aic->nr_dispatched);
-		spin_lock(&aic->lock);
-		if (test_bit(AS_TASK_IORUNNING, &aic->state) ||
-			test_bit(AS_TASK_IOSTARTED, &aic->state)) {
-			/* Calculate read -> read thinktime */
-			if (test_bit(AS_TASK_IORUNNING, &aic->state)
-							&& in_flight == 0) {
-				thinktime = jiffies - aic->last_end_request;
-				thinktime = min(thinktime, MAX_THINKTIME-1);
-			}
-			as_update_thinktime(ad, aic, thinktime);
-
-			/* Calculate read -> read seek distance */
-			if (aic->last_request_pos < blk_rq_pos(rq))
-				seek_dist = blk_rq_pos(rq) -
-					    aic->last_request_pos;
-			else
-				seek_dist = aic->last_request_pos -
-					    blk_rq_pos(rq);
-			as_update_seekdist(ad, aic, seek_dist);
-		}
-		aic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
-		set_bit(AS_TASK_IOSTARTED, &aic->state);
-		spin_unlock(&aic->lock);
-	}
-}
-
-/*
- * as_close_req decides if one request is considered "close" to the
- * previous one issued.
- */
-static int as_close_req(struct as_data *ad, struct as_io_context *aic,
-			struct request *rq)
-{
-	unsigned long delay;	/* jiffies */
-	sector_t last = ad->last_sector[ad->batch_data_dir];
-	sector_t next = blk_rq_pos(rq);
-	sector_t delta; /* acceptable close offset (in sectors) */
-	sector_t s;
-
-	if (ad->antic_status == ANTIC_OFF || !ad->ioc_finished)
-		delay = 0;
-	else
-		delay = jiffies - ad->antic_start;
-
-	if (delay == 0)
-		delta = 8192;
-	else if (delay <= (20 * HZ / 1000) && delay <= ad->antic_expire)
-		delta = 8192 << delay;
-	else
-		return 1;
-
-	if ((last <= next + (delta>>1)) && (next <= last + delta))
-		return 1;
-
-	if (last < next)
-		s = next - last;
-	else
-		s = last - next;
-
-	if (aic->seek_samples == 0) {
-		/*
-		 * Process has just started IO. Use past statistics to
-		 * gauge success possibility
-		 */
-		if (ad->new_seek_mean > s) {
-			/* this request is better than what we're expecting */
-			return 1;
-		}
-
-	} else {
-		if (aic->seek_mean > s) {
-			/* this request is better than what we're expecting */
-			return 1;
-		}
-	}
-
-	return 0;
-}
-
-/*
- * as_can_break_anticipation returns true if we have been anticipating this
- * request.
- *
- * It also returns true if the process against which we are anticipating
- * submits a write - that's presumably an fsync, O_SYNC write, etc. We want to
- * dispatch it ASAP, because we know that application will not be submitting
- * any new reads.
- *
- * If the task which has submitted the request has exited, break anticipation.
- *
- * If this task has queued some other IO, do not enter enticipation.
- */
-static int as_can_break_anticipation(struct as_data *ad, struct request *rq)
-{
-	struct io_context *ioc;
-	struct as_io_context *aic;
-
-	ioc = ad->io_context;
-	BUG_ON(!ioc);
-	spin_lock(&ioc->lock);
-
-	if (rq && ioc == RQ_IOC(rq)) {
-		/* request from same process */
-		spin_unlock(&ioc->lock);
-		return 1;
-	}
-
-	if (ad->ioc_finished && as_antic_expired(ad)) {
-		/*
-		 * In this situation status should really be FINISHED,
-		 * however the timer hasn't had the chance to run yet.
-		 */
-		spin_unlock(&ioc->lock);
-		return 1;
-	}
-
-	aic = ioc->aic;
-	if (!aic) {
-		spin_unlock(&ioc->lock);
-		return 0;
-	}
-
-	if (atomic_read(&aic->nr_queued) > 0) {
-		/* process has more requests queued */
-		spin_unlock(&ioc->lock);
-		return 1;
-	}
-
-	if (atomic_read(&aic->nr_dispatched) > 0) {
-		/* process has more requests dispatched */
-		spin_unlock(&ioc->lock);
-		return 1;
-	}
-
-	if (rq && rq_is_sync(rq) && as_close_req(ad, aic, rq)) {
-		/*
-		 * Found a close request that is not one of ours.
-		 *
-		 * This makes close requests from another process update
-		 * our IO history. Is generally useful when there are
-		 * two or more cooperating processes working in the same
-		 * area.
-		 */
-		if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
-			if (aic->ttime_samples == 0)
-				ad->exit_prob = (7*ad->exit_prob + 256)/8;
-
-			ad->exit_no_coop = (7*ad->exit_no_coop)/8;
-		}
-
-		as_update_iohist(ad, aic, rq);
-		spin_unlock(&ioc->lock);
-		return 1;
-	}
-
-	if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
-		/* process anticipated on has exited */
-		if (aic->ttime_samples == 0)
-			ad->exit_prob = (7*ad->exit_prob + 256)/8;
-
-		if (ad->exit_no_coop > 128) {
-			spin_unlock(&ioc->lock);
-			return 1;
-		}
-	}
-
-	if (aic->ttime_samples == 0) {
-		if (ad->new_ttime_mean > ad->antic_expire) {
-			spin_unlock(&ioc->lock);
-			return 1;
-		}
-		if (ad->exit_prob * ad->exit_no_coop > 128*256) {
-			spin_unlock(&ioc->lock);
-			return 1;
-		}
-	} else if (aic->ttime_mean > ad->antic_expire) {
-		/* the process thinks too much between requests */
-		spin_unlock(&ioc->lock);
-		return 1;
-	}
-	spin_unlock(&ioc->lock);
-	return 0;
-}
-
-/*
- * as_can_anticipate indicates whether we should either run rq
- * or keep anticipating a better request.
- */
-static int as_can_anticipate(struct as_data *ad, struct request *rq)
-{
-#if 0 /* disable for now, we need to check tag level as well */
-	/*
-	 * SSD device without seek penalty, disable idling
-	 */
-	if (blk_queue_nonrot(ad->q)) axman
-		return 0;
-#endif
-
-	if (!ad->io_context)
-		/*
-		 * Last request submitted was a write
-		 */
-		return 0;
-
-	if (ad->antic_status == ANTIC_FINISHED)
-		/*
-		 * Don't restart if we have just finished. Run the next request
-		 */
-		return 0;
-
-	if (as_can_break_anticipation(ad, rq))
-		/*
-		 * This request is a good candidate. Don't keep anticipating,
-		 * run it.
-		 */
-		return 0;
-
-	/*
-	 * OK from here, we haven't finished, and don't have a decent request!
-	 * Status is either ANTIC_OFF so start waiting,
-	 * ANTIC_WAIT_REQ so continue waiting for request to finish
-	 * or ANTIC_WAIT_NEXT so continue waiting for an acceptable request.
-	 */
-
-	return 1;
-}
-
-/*
- * as_update_rq must be called whenever a request (rq) is added to
- * the sort_list. This function keeps caches up to date, and checks if the
- * request might be one we are "anticipating"
- */
-static void as_update_rq(struct as_data *ad, struct request *rq)
-{
-	const int data_dir = rq_is_sync(rq);
-
-	/* keep the next_rq cache up to date */
-	ad->next_rq[data_dir] = as_choose_req(ad, rq, ad->next_rq[data_dir]);
-
-	/*
-	 * have we been anticipating this request?
-	 * or does it come from the same process as the one we are anticipating
-	 * for?
-	 */
-	if (ad->antic_status == ANTIC_WAIT_REQ
-			|| ad->antic_status == ANTIC_WAIT_NEXT) {
-		if (as_can_break_anticipation(ad, rq))
-			as_antic_stop(ad);
-	}
-}
-
-/*
- * Gathers timings and resizes the write batch automatically
- */
-static void update_write_batch(struct as_data *ad)
-{
-	unsigned long batch = ad->batch_expire[BLK_RW_ASYNC];
-	long write_time;
-
-	write_time = (jiffies - ad->current_batch_expires) + batch;
-	if (write_time < 0)
-		write_time = 0;
-
-	if (write_time > batch && !ad->write_batch_idled) {
-		if (write_time > batch * 3)
-			ad->write_batch_count /= 2;
-		else
-			ad->write_batch_count--;
-	} else if (write_time < batch && ad->current_write_count == 0) {
-		if (batch > write_time * 3)
-			ad->write_batch_count *= 2;
-		else
-			ad->write_batch_count++;
-	}
-
-	if (ad->write_batch_count < 1)
-		ad->write_batch_count = 1;
-}
-
-/*
- * as_completed_request is to be called when a request has completed and
- * returned something to the requesting process, be it an error or data.
- */
-static void as_completed_request(struct request_queue *q, struct request *rq)
-{
-	struct as_data *ad = q->elevator->elevator_data;
-
-	WARN_ON(!list_empty(&rq->queuelist));
-
-	if (RQ_STATE(rq) != AS_RQ_REMOVED) {
-		WARN(1, "rq->state %d\n", RQ_STATE(rq));
-		goto out;
-	}
-
-	if (ad->changed_batch && ad->nr_dispatched == 1) {
-		ad->current_batch_expires = jiffies +
-					ad->batch_expire[ad->batch_data_dir];
-		kblockd_schedule_work(q, &ad->antic_work);
-		ad->changed_batch = 0;
-
-		if (ad->batch_data_dir == BLK_RW_SYNC)
-			ad->new_batch = 1;
-	}
-	WARN_ON(ad->nr_dispatched == 0);
-	ad->nr_dispatched--;
-
-	/*
-	 * Start counting the batch from when a request of that direction is
-	 * actually serviced. This should help devices with big TCQ windows
-	 * and writeback caches
-	 */
-	if (ad->new_batch && ad->batch_data_dir == rq_is_sync(rq)) {
-		update_write_batch(ad);
-		ad->current_batch_expires = jiffies +
-				ad->batch_expire[BLK_RW_SYNC];
-		ad->new_batch = 0;
-	}
-
-	if (ad->io_context == RQ_IOC(rq) && ad->io_context) {
-		ad->antic_start = jiffies;
-		ad->ioc_finished = 1;
-		if (ad->antic_status == ANTIC_WAIT_REQ) {
-			/*
-			 * We were waiting on this request, now anticipate
-			 * the next one
-			 */
-			as_antic_waitnext(ad);
-		}
-	}
-
-	as_put_io_context(rq);
-out:
-	RQ_SET_STATE(rq, AS_RQ_POSTSCHED);
-}
-
-/*
- * as_remove_queued_request removes a request from the pre dispatch queue
- * without updating refcounts. It is expected the caller will drop the
- * reference unless it replaces the request at somepart of the elevator
- * (ie. the dispatch queue)
- */
-static void as_remove_queued_request(struct request_queue *q,
-				     struct request *rq)
-{
-	const int data_dir = rq_is_sync(rq);
-	struct as_data *ad = q->elevator->elevator_data;
-	struct io_context *ioc;
-
-	WARN_ON(RQ_STATE(rq) != AS_RQ_QUEUED);
-
-	ioc = RQ_IOC(rq);
-	if (ioc && ioc->aic) {
-		BUG_ON(!atomic_read(&ioc->aic->nr_queued));
-		atomic_dec(&ioc->aic->nr_queued);
-	}
-
-	/*
-	 * Update the "next_rq" cache if we are about to remove its
-	 * entry
-	 */
-	if (ad->next_rq[data_dir] == rq)
-		ad->next_rq[data_dir] = as_find_next_rq(ad, rq);
-
-	rq_fifo_clear(rq);
-	as_del_rq_rb(ad, rq);
-}
-
-/*
- * as_fifo_expired returns 0 if there are no expired requests on the fifo,
- * 1 otherwise.  It is ratelimited so that we only perform the check once per
- * `fifo_expire' interval.  Otherwise a large number of expired requests
- * would create a hopeless seekstorm.
- *
- * See as_antic_expired comment.
- */
-static int as_fifo_expired(struct as_data *ad, int adir)
-{
-	struct request *rq;
-	long delta_jif;
-
-	delta_jif = jiffies - ad->last_check_fifo[adir];
-	if (unlikely(delta_jif < 0))
-		delta_jif = -delta_jif;
-	if (delta_jif < ad->fifo_expire[adir])
-		return 0;
-
-	ad->last_check_fifo[adir] = jiffies;
-
-	if (list_empty(&ad->fifo_list[adir]))
-		return 0;
-
-	rq = rq_entry_fifo(ad->fifo_list[adir].next);
-
-	return time_after(jiffies, rq_fifo_time(rq));
-}
-
-/*
- * as_batch_expired returns true if the current batch has expired. A batch
- * is a set of reads or a set of writes.
- */
-static inline int as_batch_expired(struct as_data *ad)
-{
-	if (ad->changed_batch || ad->new_batch)
-		return 0;
-
-	if (ad->batch_data_dir == BLK_RW_SYNC)
-		/* TODO! add a check so a complete fifo gets written? */
-		return time_after(jiffies, ad->current_batch_expires);
-
-	return time_after(jiffies, ad->current_batch_expires)
-		|| ad->current_write_count == 0;
-}
-
-/*
- * move an entry to dispatch queue
- */
-static void as_move_to_dispatch(struct as_data *ad, struct request *rq)
-{
-	const int data_dir = rq_is_sync(rq);
-
-	BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
-
-	as_antic_stop(ad);
-	ad->antic_status = ANTIC_OFF;
-
-	/*
-	 * This has to be set in order to be correctly updated by
-	 * as_find_next_rq
-	 */
-	ad->last_sector[data_dir] = blk_rq_pos(rq) + blk_rq_sectors(rq);
-
-	if (data_dir == BLK_RW_SYNC) {
-		struct io_context *ioc = RQ_IOC(rq);
-		/* In case we have to anticipate after this */
-		copy_io_context(&ad->io_context, &ioc);
-	} else {
-		if (ad->io_context) {
-			put_io_context(ad->io_context);
-			ad->io_context = NULL;
-		}
-
-		if (ad->current_write_count != 0)
-			ad->current_write_count--;
-	}
-	ad->ioc_finished = 0;
-
-	ad->next_rq[data_dir] = as_find_next_rq(ad, rq);
-
-	/*
-	 * take it off the sort and fifo list, add to dispatch queue
-	 */
-	as_remove_queued_request(ad->q, rq);
-	WARN_ON(RQ_STATE(rq) != AS_RQ_QUEUED);
-
-	elv_dispatch_sort(ad->q, rq);
-
-	RQ_SET_STATE(rq, AS_RQ_DISPATCHED);
-	if (RQ_IOC(rq) && RQ_IOC(rq)->aic)
-		atomic_inc(&RQ_IOC(rq)->aic->nr_dispatched);
-	ad->nr_dispatched++;
-}
-
-/*
- * as_dispatch_request selects the best request according to
- * read/write expire, batch expire, etc, and moves it to the dispatch
- * queue. Returns 1 if a request was found, 0 otherwise.
- */
-static int as_dispatch_request(struct request_queue *q, int force)
-{
-	struct as_data *ad = q->elevator->elevator_data;
-	const int reads = !list_empty(&ad->fifo_list[BLK_RW_SYNC]);
-	const int writes = !list_empty(&ad->fifo_list[BLK_RW_ASYNC]);
-	struct request *rq;
-
-	if (unlikely(force)) {
-		/*
-		 * Forced dispatch, accounting is useless.  Reset
-		 * accounting states and dump fifo_lists.  Note that
-		 * batch_data_dir is reset to BLK_RW_SYNC to avoid
-		 * screwing write batch accounting as write batch
-		 * accounting occurs on W->R transition.
-		 */
-		int dispatched = 0;
-
-		ad->batch_data_dir = BLK_RW_SYNC;
-		ad->changed_batch = 0;
-		ad->new_batch = 0;
-
-		while (ad->next_rq[BLK_RW_SYNC]) {
-			as_move_to_dispatch(ad, ad->next_rq[BLK_RW_SYNC]);
-			dispatched++;
-		}
-		ad->last_check_fifo[BLK_RW_SYNC] = jiffies;
-
-		while (ad->next_rq[BLK_RW_ASYNC]) {
-			as_move_to_dispatch(ad, ad->next_rq[BLK_RW_ASYNC]);
-			dispatched++;
-		}
-		ad->last_check_fifo[BLK_RW_ASYNC] = jiffies;
-
-		return dispatched;
-	}
-
-	/* Signal that the write batch was uncontended, so we can't time it */
-	if (ad->batch_data_dir == BLK_RW_ASYNC && !reads) {
-		if (ad->current_write_count == 0 || !writes)
-			ad->write_batch_idled = 1;
-	}
-
-	if (!(reads || writes)
-		|| ad->antic_status == ANTIC_WAIT_REQ
-		|| ad->antic_status == ANTIC_WAIT_NEXT
-		|| ad->changed_batch)
-		return 0;
-
-	if (!(reads && writes && as_batch_expired(ad))) {
-		/*
-		 * batch is still running or no reads or no writes
-		 */
-		rq = ad->next_rq[ad->batch_data_dir];
-
-		if (ad->batch_data_dir == BLK_RW_SYNC && ad->antic_expire) {
-			if (as_fifo_expired(ad, BLK_RW_SYNC))
-				goto fifo_expired;
-
-			if (as_can_anticipate(ad, rq)) {
-				as_antic_waitreq(ad);
-				return 0;
-			}
-		}
-
-		if (rq) {
-			/* we have a "next request" */
-			if (reads && !writes)
-				ad->current_batch_expires =
-					jiffies + ad->batch_expire[BLK_RW_SYNC];
-			goto dispatch_request;
-		}
-	}
-
-	/*
-	 * at this point we are not running a batch. select the appropriate
-	 * data direction (read / write)
-	 */
-
-	if (reads) {
-		BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[BLK_RW_SYNC]));
-
-		if (writes && ad->batch_data_dir == BLK_RW_SYNC)
-			/*
-			 * Last batch was a read, switch to writes
-			 */
-			goto dispatch_writes;
-
-		if (ad->batch_data_dir == BLK_RW_ASYNC) {
-			WARN_ON(ad->new_batch);
-			ad->changed_batch = 1;
-		}
-		ad->batch_data_dir = BLK_RW_SYNC;
-		rq = rq_entry_fifo(ad->fifo_list[BLK_RW_SYNC].next);
-		ad->last_check_fifo[ad->batch_data_dir] = jiffies;
-		goto dispatch_request;
-	}
-
-	/*
-	 * the last batch was a read
-	 */
-
-	if (writes) {
-dispatch_writes:
-		BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[BLK_RW_ASYNC]));
-
-		if (ad->batch_data_dir == BLK_RW_SYNC) {
-			ad->changed_batch = 1;
-
-			/*
-			 * new_batch might be 1 when the queue runs out of
-			 * reads. A subsequent submission of a write might
-			 * cause a change of batch before the read is finished.
-			 */
-			ad->new_batch = 0;
-		}
-		ad->batch_data_dir = BLK_RW_ASYNC;
-		ad->current_write_count = ad->write_batch_count;
-		ad->write_batch_idled = 0;
-		rq = rq_entry_fifo(ad->fifo_list[BLK_RW_ASYNC].next);
-		ad->last_check_fifo[BLK_RW_ASYNC] = jiffies;
-		goto dispatch_request;
-	}
-
-	BUG();
-	return 0;
-
-dispatch_request:
-	/*
-	 * If a request has expired, service it.
-	 */
-
-	if (as_fifo_expired(ad, ad->batch_data_dir)) {
-fifo_expired:
-		rq = rq_entry_fifo(ad->fifo_list[ad->batch_data_dir].next);
-	}
-
-	if (ad->changed_batch) {
-		WARN_ON(ad->new_batch);
-
-		if (ad->nr_dispatched)
-			return 0;
-
-		if (ad->batch_data_dir == BLK_RW_ASYNC)
-			ad->current_batch_expires = jiffies +
-					ad->batch_expire[BLK_RW_ASYNC];
-		else
-			ad->new_batch = 1;
-
-		ad->changed_batch = 0;
-	}
-
-	/*
-	 * rq is the selected appropriate request.
-	 */
-	as_move_to_dispatch(ad, rq);
-
-	return 1;
-}
-
-/*
- * add rq to rbtree and fifo
- */
-static void as_add_request(struct request_queue *q, struct request *rq)
-{
-	struct as_data *ad = q->elevator->elevator_data;
-	int data_dir;
-
-	RQ_SET_STATE(rq, AS_RQ_NEW);
-
-	data_dir = rq_is_sync(rq);
-
-	rq->elevator_private = as_get_io_context(q->node);
-
-	if (RQ_IOC(rq)) {
-		as_update_iohist(ad, RQ_IOC(rq)->aic, rq);
-		atomic_inc(&RQ_IOC(rq)->aic->nr_queued);
-	}
-
-	as_add_rq_rb(ad, rq);
-
-	/*
-	 * set expire time and add to fifo list
-	 */
-	rq_set_fifo_time(rq, jiffies + ad->fifo_expire[data_dir]);
-	list_add_tail(&rq->queuelist, &ad->fifo_list[data_dir]);
-
-	as_update_rq(ad, rq); /* keep state machine up to date */
-	RQ_SET_STATE(rq, AS_RQ_QUEUED);
-}
-
-static void as_activate_request(struct request_queue *q, struct request *rq)
-{
-	WARN_ON(RQ_STATE(rq) != AS_RQ_DISPATCHED);
-	RQ_SET_STATE(rq, AS_RQ_REMOVED);
-	if (RQ_IOC(rq) && RQ_IOC(rq)->aic)
-		atomic_dec(&RQ_IOC(rq)->aic->nr_dispatched);
-}
-
-static void as_deactivate_request(struct request_queue *q, struct request *rq)
-{
-	WARN_ON(RQ_STATE(rq) != AS_RQ_REMOVED);
-	RQ_SET_STATE(rq, AS_RQ_DISPATCHED);
-	if (RQ_IOC(rq) && RQ_IOC(rq)->aic)
-		atomic_inc(&RQ_IOC(rq)->aic->nr_dispatched);
-}
-
-/*
- * as_queue_empty tells us if there are requests left in the device. It may
- * not be the case that a driver can get the next request even if the queue
- * is not empty - it is used in the block layer to check for plugging and
- * merging opportunities
- */
-static int as_queue_empty(struct request_queue *q)
-{
-	struct as_data *ad = q->elevator->elevator_data;
-
-	return list_empty(&ad->fifo_list[BLK_RW_ASYNC])
-		&& list_empty(&ad->fifo_list[BLK_RW_SYNC]);
-}
-
-static int
-as_merge(struct request_queue *q, struct request **req, struct bio *bio)
-{
-	struct as_data *ad = q->elevator->elevator_data;
-	sector_t rb_key = bio->bi_sector + bio_sectors(bio);
-	struct request *__rq;
-
-	/*
-	 * check for front merge
-	 */
-	__rq = elv_rb_find(&ad->sort_list[bio_data_dir(bio)], rb_key);
-	if (__rq && elv_rq_merge_ok(__rq, bio)) {
-		*req = __rq;
-		return ELEVATOR_FRONT_MERGE;
-	}
-
-	return ELEVATOR_NO_MERGE;
-}
-
-static void as_merged_request(struct request_queue *q, struct request *req,
-			      int type)
-{
-	struct as_data *ad = q->elevator->elevator_data;
-
-	/*
-	 * if the merge was a front merge, we need to reposition request
-	 */
-	if (type == ELEVATOR_FRONT_MERGE) {
-		as_del_rq_rb(ad, req);
-		as_add_rq_rb(ad, req);
-		/*
-		 * Note! At this stage of this and the next function, our next
-		 * request may not be optimal - eg the request may have "grown"
-		 * behind the disk head. We currently don't bother adjusting.
-		 */
-	}
-}
-
-static void as_merged_requests(struct request_queue *q, struct request *req,
-			 	struct request *next)
-{
-	/*
-	 * if next expires before rq, assign its expire time to arq
-	 * and move into next position (next will be deleted) in fifo
-	 */
-	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
-		if (time_before(rq_fifo_time(next), rq_fifo_time(req))) {
-			list_move(&req->queuelist, &next->queuelist);
-			rq_set_fifo_time(req, rq_fifo_time(next));
-		}
-	}
-
-	/*
-	 * kill knowledge of next, this one is a goner
-	 */
-	as_remove_queued_request(q, next);
-	as_put_io_context(next);
-
-	RQ_SET_STATE(next, AS_RQ_MERGED);
-}
-
-/*
- * This is executed in a "deferred" process context, by kblockd. It calls the
- * driver's request_fn so the driver can submit that request.
- *
- * IMPORTANT! This guy will reenter the elevator, so set up all queue global
- * state before calling, and don't rely on any state over calls.
- *
- * FIXME! dispatch queue is not a queue at all!
- */
-static void as_work_handler(struct work_struct *work)
-{
-	struct as_data *ad = container_of(work, struct as_data, antic_work);
-
-	blk_run_queue(ad->q);
-}
-
-static int as_may_queue(struct request_queue *q, int rw)
-{
-	int ret = ELV_MQUEUE_MAY;
-	struct as_data *ad = q->elevator->elevator_data;
-	struct io_context *ioc;
-	if (ad->antic_status == ANTIC_WAIT_REQ ||
-			ad->antic_status == ANTIC_WAIT_NEXT) {
-		ioc = as_get_io_context(q->node);
-		if (ad->io_context == ioc)
-			ret = ELV_MQUEUE_MUST;
-		put_io_context(ioc);
-	}
-
-	return ret;
-}
-
-static void as_exit_queue(struct elevator_queue *e)
-{
-	struct as_data *ad = e->elevator_data;
-
-	del_timer_sync(&ad->antic_timer);
-	cancel_work_sync(&ad->antic_work);
-
-	BUG_ON(!list_empty(&ad->fifo_list[BLK_RW_SYNC]));
-	BUG_ON(!list_empty(&ad->fifo_list[BLK_RW_ASYNC]));
-
-	put_io_context(ad->io_context);
-	kfree(ad);
-}
-
-/*
- * initialize elevator private data (as_data).
- */
-static void *as_init_queue(struct request_queue *q)
-{
-	struct as_data *ad;
-
-	ad = kmalloc_node(sizeof(*ad), GFP_KERNEL | __GFP_ZERO, q->node);
-	if (!ad)
-		return NULL;
-
-	ad->q = q; /* Identify what queue the data belongs to */
-
-	/* anticipatory scheduling helpers */
-	ad->antic_timer.function = as_antic_timeout;
-	ad->antic_timer.data = (unsigned long)q;
-	init_timer(&ad->antic_timer);
-	INIT_WORK(&ad->antic_work, as_work_handler);
-
-	INIT_LIST_HEAD(&ad->fifo_list[BLK_RW_SYNC]);
-	INIT_LIST_HEAD(&ad->fifo_list[BLK_RW_ASYNC]);
-	ad->sort_list[BLK_RW_SYNC] = RB_ROOT;
-	ad->sort_list[BLK_RW_ASYNC] = RB_ROOT;
-	ad->fifo_expire[BLK_RW_SYNC] = default_read_expire;
-	ad->fifo_expire[BLK_RW_ASYNC] = default_write_expire;
-	ad->antic_expire = default_antic_expire;
-	ad->batch_expire[BLK_RW_SYNC] = default_read_batch_expire;
-	ad->batch_expire[BLK_RW_ASYNC] = default_write_batch_expire;
-
-	ad->current_batch_expires = jiffies + ad->batch_expire[BLK_RW_SYNC];
-	ad->write_batch_count = ad->batch_expire[BLK_RW_ASYNC] / 10;
-	if (ad->write_batch_count < 2)
-		ad->write_batch_count = 2;
-
-	return ad;
-}
-
-/*
- * sysfs parts below
- */
-
-static ssize_t
-as_var_show(unsigned int var, char *page)
-{
-	return sprintf(page, "%d\n", var);
-}
-
-static ssize_t
-as_var_store(unsigned long *var, const char *page, size_t count)
-{
-	char *p = (char *) page;
-
-	*var = simple_strtoul(p, &p, 10);
-	return count;
-}
-
-static ssize_t est_time_show(struct elevator_queue *e, char *page)
-{
-	struct as_data *ad = e->elevator_data;
-	int pos = 0;
-
-	pos += sprintf(page+pos, "%lu %% exit probability\n",
-				100*ad->exit_prob/256);
-	pos += sprintf(page+pos, "%lu %% probability of exiting without a "
-				"cooperating process submitting IO\n",
-				100*ad->exit_no_coop/256);
-	pos += sprintf(page+pos, "%lu ms new thinktime\n", ad->new_ttime_mean);
-	pos += sprintf(page+pos, "%llu sectors new seek distance\n",
-				(unsigned long long)ad->new_seek_mean);
-
-	return pos;
-}
-
-#define SHOW_FUNCTION(__FUNC, __VAR)				\
-static ssize_t __FUNC(struct elevator_queue *e, char *page)	\
-{								\
-	struct as_data *ad = e->elevator_data;			\
-	return as_var_show(jiffies_to_msecs((__VAR)), (page));	\
-}
-SHOW_FUNCTION(as_read_expire_show, ad->fifo_expire[BLK_RW_SYNC]);
-SHOW_FUNCTION(as_write_expire_show, ad->fifo_expire[BLK_RW_ASYNC]);
-SHOW_FUNCTION(as_antic_expire_show, ad->antic_expire);
-SHOW_FUNCTION(as_read_batch_expire_show, ad->batch_expire[BLK_RW_SYNC]);
-SHOW_FUNCTION(as_write_batch_expire_show, ad->batch_expire[BLK_RW_ASYNC]);
-#undef SHOW_FUNCTION
-
-#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)				\
-static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
-{									\
-	struct as_data *ad = e->elevator_data;				\
-	int ret = as_var_store(__PTR, (page), count);			\
-	if (*(__PTR) < (MIN))						\
-		*(__PTR) = (MIN);					\
-	else if (*(__PTR) > (MAX))					\
-		*(__PTR) = (MAX);					\
-	*(__PTR) = msecs_to_jiffies(*(__PTR));				\
-	return ret;							\
-}
-STORE_FUNCTION(as_read_expire_store, &ad->fifo_expire[BLK_RW_SYNC], 0, INT_MAX);
-STORE_FUNCTION(as_write_expire_store,
-			&ad->fifo_expire[BLK_RW_ASYNC], 0, INT_MAX);
-STORE_FUNCTION(as_antic_expire_store, &ad->antic_expire, 0, INT_MAX);
-STORE_FUNCTION(as_read_batch_expire_store,
-			&ad->batch_expire[BLK_RW_SYNC], 0, INT_MAX);
-STORE_FUNCTION(as_write_batch_expire_store,
-			&ad->batch_expire[BLK_RW_ASYNC], 0, INT_MAX);
-#undef STORE_FUNCTION
-
-#define AS_ATTR(name) \
-	__ATTR(name, S_IRUGO|S_IWUSR, as_##name##_show, as_##name##_store)
-
-static struct elv_fs_entry as_attrs[] = {
-	__ATTR_RO(est_time),
-	AS_ATTR(read_expire),
-	AS_ATTR(write_expire),
-	AS_ATTR(antic_expire),
-	AS_ATTR(read_batch_expire),
-	AS_ATTR(write_batch_expire),
-	__ATTR_NULL
-};
-
-static struct elevator_type iosched_as = {
-	.ops = {
-		.elevator_merge_fn = 		as_merge,
-		.elevator_merged_fn =		as_merged_request,
-		.elevator_merge_req_fn =	as_merged_requests,
-		.elevator_dispatch_fn =		as_dispatch_request,
-		.elevator_add_req_fn =		as_add_request,
-		.elevator_activate_req_fn =	as_activate_request,
-		.elevator_deactivate_req_fn = 	as_deactivate_request,
-		.elevator_queue_empty_fn =	as_queue_empty,
-		.elevator_completed_req_fn =	as_completed_request,
-		.elevator_former_req_fn =	elv_rb_former_request,
-		.elevator_latter_req_fn =	elv_rb_latter_request,
-		.elevator_may_queue_fn =	as_may_queue,
-		.elevator_init_fn =		as_init_queue,
-		.elevator_exit_fn =		as_exit_queue,
-		.trim =				as_trim,
-	},
-
-	.elevator_attrs = as_attrs,
-	.elevator_name = "anticipatory",
-	.elevator_owner = THIS_MODULE,
-};
-
-static int __init as_init(void)
-{
-	elv_register(&iosched_as);
-
-	return 0;
-}
-
-static void __exit as_exit(void)
-{
-	DECLARE_COMPLETION_ONSTACK(all_gone);
-	elv_unregister(&iosched_as);
-	ioc_gone = &all_gone;
-	/* ioc_gone's update must be visible before reading ioc_count */
-	smp_wmb();
-	if (elv_ioc_count_read(ioc_count))
-		wait_for_completion(&all_gone);
-	synchronize_rcu();
-}
-
-module_init(as_init);
-module_exit(as_exit);
-
-MODULE_AUTHOR("Nick Piggin");
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("anticipatory IO scheduler");
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 30022b4e2f63..8618d8996fea 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -348,6 +348,10 @@ static void blkdev_discard_end_io(struct bio *bio, int err)
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
 	}
 
+	if (bio->bi_private)
+		complete(bio->bi_private);
+	__free_page(bio_page(bio));
+
 	bio_put(bio);
 }
 
@@ -357,49 +361,73 @@ static void blkdev_discard_end_io(struct bio *bio, int err)
  * @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. Does not wait.
+ *    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 blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, int flags)
 {
-	struct request_queue *q;
+	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 (bdev->bd_disk == NULL)
-		return -ENXIO;
-
-	q = bdev_get_queue(bdev);
 	if (!q)
 		return -ENXIO;
 
-	if (!q->prepare_discard_fn)
+	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
 
 	while (nr_sects && !ret) {
-		bio = bio_alloc(gfp_mask, 0);
-		if (!bio)
-			return -ENOMEM;
+		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;
 
-		bio->bi_sector = sector;
+		/*
+		 * 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;
 
-		if (nr_sects > queue_max_hw_sectors(q)) {
-			bio->bi_size = queue_max_hw_sectors(q) << 9;
-			nr_sects -= queue_max_hw_sectors(q);
-			sector += queue_max_hw_sectors(q);
+		/*
+		 * 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(DISCARD_BARRIER, bio);
+		submit_bio(type, bio);
+
+		if (flags & DISCARD_FL_WAIT)
+			wait_for_completion(&wait);
 
-		/* Check if it failed immediately */
 		if (bio_flagged(bio, BIO_EOPNOTSUPP))
 			ret = -EOPNOTSUPP;
 		else if (!bio_flagged(bio, BIO_UPTODATE))
@@ -407,5 +435,11 @@ int blkdev_issue_discard(struct block_device *bdev,
 		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
new file mode 100644
index 000000000000..e7dbbaf5fb3e
--- /dev/null
+++ b/block/blk-cgroup.c
@@ -0,0 +1,361 @@
+/*
+ * Common Block IO controller cgroup interface
+ *
+ * Based on ideas and code from CFQ, CFS and BFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ *		      Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
+ * 	              Nauman Rafique <nauman@google.com>
+ */
+#include <linux/ioprio.h>
+#include <linux/seq_file.h>
+#include <linux/kdev_t.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include "blk-cgroup.h"
+
+static DEFINE_SPINLOCK(blkio_list_lock);
+static LIST_HEAD(blkio_list);
+
+struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
+EXPORT_SYMBOL_GPL(blkio_root_cgroup);
+
+bool blkiocg_css_tryget(struct blkio_cgroup *blkcg)
+{
+	if (!css_tryget(&blkcg->css))
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(blkiocg_css_tryget);
+
+void blkiocg_css_put(struct blkio_cgroup *blkcg)
+{
+	css_put(&blkcg->css);
+}
+EXPORT_SYMBOL_GPL(blkiocg_css_put);
+
+struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
+{
+	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
+			    struct blkio_cgroup, css);
+}
+EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
+
+void blkiocg_update_blkio_group_stats(struct blkio_group *blkg,
+			unsigned long time, unsigned long sectors)
+{
+	blkg->time += time;
+	blkg->sectors += sectors;
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_stats);
+
+void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
+			struct blkio_group *blkg, void *key, dev_t dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkcg->lock, flags);
+	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);
+
+static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
+{
+	hlist_del_init_rcu(&blkg->blkcg_node);
+	blkg->blkcg_id = 0;
+}
+
+/*
+ * returns 0 if blkio_group was still on cgroup list. Otherwise returns 1
+ * indicating that blk_group was unhashed by the time we got to it.
+ */
+int blkiocg_del_blkio_group(struct blkio_group *blkg)
+{
+	struct blkio_cgroup *blkcg;
+	unsigned long flags;
+	struct cgroup_subsys_state *css;
+	int ret = 1;
+
+	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;
+	}
+	spin_unlock_irqrestore(&blkcg->lock, flags);
+out:
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkiocg_del_blkio_group);
+
+/* called under rcu_read_lock(). */
+struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
+{
+	struct blkio_group *blkg;
+	struct hlist_node *n;
+	void *__key;
+
+	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
+		__key = blkg->key;
+		if (__key == key)
+			return blkg;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
+
+#define SHOW_FUNCTION(__VAR)						\
+static u64 blkiocg_##__VAR##_read(struct cgroup *cgroup,		\
+				       struct cftype *cftype)		\
+{									\
+	struct blkio_cgroup *blkcg;					\
+									\
+	blkcg = cgroup_to_blkio_cgroup(cgroup);				\
+	return (u64)blkcg->__VAR;					\
+}
+
+SHOW_FUNCTION(weight);
+#undef SHOW_FUNCTION
+
+static int
+blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
+{
+	struct blkio_cgroup *blkcg;
+	struct blkio_group *blkg;
+	struct hlist_node *n;
+	struct blkio_policy_type *blkiop;
+
+	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) {
+		list_for_each_entry(blkiop, &blkio_list, list)
+			blkiop->ops.blkio_update_group_weight_fn(blkg,
+					blkcg->weight);
+	}
+	spin_unlock_irq(&blkcg->lock);
+	spin_unlock(&blkio_list_lock);
+	return 0;
+}
+
+#define SHOW_FUNCTION_PER_GROUP(__VAR)					\
+static int blkiocg_##__VAR##_read(struct cgroup *cgroup,		\
+			struct cftype *cftype, struct seq_file *m)	\
+{									\
+	struct blkio_cgroup *blkcg;					\
+	struct blkio_group *blkg;					\
+	struct hlist_node *n;						\
+									\
+	if (!cgroup_lock_live_group(cgroup))				\
+		return -ENODEV;						\
+									\
+	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);	\
+	}								\
+	rcu_read_unlock();						\
+	cgroup_unlock();						\
+	return 0;							\
+}
+
+SHOW_FUNCTION_PER_GROUP(time);
+SHOW_FUNCTION_PER_GROUP(sectors);
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+SHOW_FUNCTION_PER_GROUP(dequeue);
+#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)
+{
+	blkg->dequeue += dequeue;
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_dequeue_stats);
+#endif
+
+struct cftype blkio_files[] = {
+	{
+		.name = "weight",
+		.read_u64 = blkiocg_weight_read,
+		.write_u64 = blkiocg_weight_write,
+	},
+	{
+		.name = "time",
+		.read_seq_string = blkiocg_time_read,
+	},
+	{
+		.name = "sectors",
+		.read_seq_string = blkiocg_sectors_read,
+	},
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+       {
+		.name = "dequeue",
+		.read_seq_string = blkiocg_dequeue_read,
+       },
+#endif
+};
+
+static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+	return cgroup_add_files(cgroup, subsys, blkio_files,
+				ARRAY_SIZE(blkio_files));
+}
+
+static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
+	unsigned long flags;
+	struct blkio_group *blkg;
+	void *key;
+	struct blkio_policy_type *blkiop;
+
+	rcu_read_lock();
+remove_entry:
+	spin_lock_irqsave(&blkcg->lock, flags);
+
+	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);
+
+	spin_unlock_irqrestore(&blkcg->lock, flags);
+
+	/*
+	 * 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);
+}
+
+static struct cgroup_subsys_state *
+blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+	struct blkio_cgroup *blkcg, *parent_blkcg;
+
+	if (!cgroup->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);
+
+	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
+	if (!blkcg)
+		return ERR_PTR(-ENOMEM);
+
+	blkcg->weight = BLKIO_WEIGHT_DEFAULT;
+done:
+	spin_lock_init(&blkcg->lock);
+	INIT_HLIST_HEAD(&blkcg->blkg_list);
+
+	return &blkcg->css;
+}
+
+/*
+ * We cannot support shared io contexts, as we have no mean to support
+ * two tasks with the same ioc in two different groups without major rework
+ * of the main cic data structures.  For now we allow a task to change
+ * its cgroup only if it's the only owner of its ioc.
+ */
+static int blkiocg_can_attach(struct cgroup_subsys *subsys,
+				struct cgroup *cgroup, struct task_struct *tsk,
+				bool threadgroup)
+{
+	struct io_context *ioc;
+	int ret = 0;
+
+	/* task_lock() is needed to avoid races with exit_io_context() */
+	task_lock(tsk);
+	ioc = tsk->io_context;
+	if (ioc && atomic_read(&ioc->nr_tasks) > 1)
+		ret = -EINVAL;
+	task_unlock(tsk);
+
+	return ret;
+}
+
+static void blkiocg_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup,
+				struct cgroup *prev, struct task_struct *tsk,
+				bool threadgroup)
+{
+	struct io_context *ioc;
+
+	task_lock(tsk);
+	ioc = tsk->io_context;
+	if (ioc)
+		ioc->cgroup_changed = 1;
+	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);
+	list_add_tail(&blkiop->list, &blkio_list);
+	spin_unlock(&blkio_list_lock);
+}
+EXPORT_SYMBOL_GPL(blkio_policy_register);
+
+void blkio_policy_unregister(struct blkio_policy_type *blkiop)
+{
+	spin_lock(&blkio_list_lock);
+	list_del_init(&blkiop->list);
+	spin_unlock(&blkio_list_lock);
+}
+EXPORT_SYMBOL_GPL(blkio_policy_unregister);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
new file mode 100644
index 000000000000..4d316df863b4
--- /dev/null
+++ b/block/blk-cgroup.h
@@ -0,0 +1,127 @@
+#ifndef _BLK_CGROUP_H
+#define _BLK_CGROUP_H
+/*
+ * Common Block IO controller cgroup interface
+ *
+ * Based on ideas and code from CFQ, CFS and BFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ *		      Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
+ * 	              Nauman Rafique <nauman@google.com>
+ */
+
+#include <linux/cgroup.h>
+
+#ifdef CONFIG_BLK_CGROUP
+
+struct blkio_cgroup {
+	struct cgroup_subsys_state css;
+	unsigned int weight;
+	spinlock_t lock;
+	struct hlist_head blkg_list;
+};
+
+struct blkio_group {
+	/* An rcu protected unique identifier for the 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;
+
+	/* total disk time and nr sectors dispatched by this group */
+	unsigned long time;
+	unsigned long sectors;
+};
+
+extern bool blkiocg_css_tryget(struct blkio_cgroup *blkcg);
+extern void blkiocg_css_put(struct blkio_cgroup *blkcg);
+
+typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg);
+typedef void (blkio_update_group_weight_fn) (struct blkio_group *blkg,
+						unsigned int weight);
+
+struct blkio_policy_ops {
+	blkio_unlink_group_fn *blkio_unlink_group_fn;
+	blkio_update_group_weight_fn *blkio_update_group_weight_fn;
+};
+
+struct blkio_policy_type {
+	struct list_head list;
+	struct blkio_policy_ops ops;
+};
+
+/* Blkio controller policy registration */
+extern void blkio_policy_register(struct blkio_policy_type *);
+extern void blkio_policy_unregister(struct blkio_policy_type *);
+
+#else
+
+struct blkio_group {
+};
+
+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) { }
+
+#endif
+
+#define BLKIO_WEIGHT_MIN	100
+#define BLKIO_WEIGHT_MAX	1000
+#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,
+				unsigned long dequeue);
+#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) {}
+#endif
+
+#ifdef CONFIG_BLK_CGROUP
+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,
+			struct blkio_group *blkg, void *key, dev_t dev);
+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);
+#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)
+{
+}
+
+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)
+{
+}
+#endif
+#endif /* _BLK_CGROUP_H */
diff --git a/block/blk-core.c b/block/blk-core.c
index 620579e0ff7b..800d396f8924 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -34,6 +34,7 @@
 #include "blk.h"
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
 
 static int __make_request(struct request_queue *q, struct bio *bio);
@@ -69,7 +70,7 @@ static void drive_stat_acct(struct request *rq, int new_io)
 		part_stat_inc(cpu, part, merges[rw]);
 	else {
 		part_round_stats(cpu, part);
-		part_inc_in_flight(part);
+		part_inc_in_flight(part, rw);
 	}
 
 	part_stat_unlock();
@@ -501,6 +502,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 	q->backing_dev_info.state = 0;
 	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+	q->backing_dev_info.name = "block";
 
 	err = bdi_init(&q->backing_dev_info);
 	if (err) {
@@ -1028,9 +1030,9 @@ static void part_round_stats_single(int cpu, struct hd_struct *part,
 	if (now == part->stamp)
 		return;
 
-	if (part->in_flight) {
+	if (part_in_flight(part)) {
 		__part_stat_add(cpu, part, time_in_queue,
-				part->in_flight * (now - part->stamp));
+				part_in_flight(part) * (now - part->stamp));
 		__part_stat_add(cpu, part, io_ticks, (now - part->stamp));
 	}
 	part->stamp = now;
@@ -1111,31 +1113,26 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	req->cmd_type = REQ_TYPE_FS;
 
 	/*
-	 * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
+	 * Inherit FAILFAST from bio (for read-ahead, and explicit
+	 * FAILFAST).  FAILFAST flags are identical for req and bio.
 	 */
-	if (bio_rw_ahead(bio))
-		req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
-				   REQ_FAILFAST_DRIVER);
-	if (bio_failfast_dev(bio))
-		req->cmd_flags |= REQ_FAILFAST_DEV;
-	if (bio_failfast_transport(bio))
-		req->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-	if (bio_failfast_driver(bio))
-		req->cmd_flags |= REQ_FAILFAST_DRIVER;
-
-	if (unlikely(bio_discard(bio))) {
+	if (bio_rw_flagged(bio, BIO_RW_AHEAD))
+		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_barrier(bio))
+		if (bio_rw_flagged(bio, BIO_RW_BARRIER))
 			req->cmd_flags |= REQ_SOFTBARRIER;
-		req->q->prepare_discard_fn(req->q, req);
-	} else if (unlikely(bio_barrier(bio)))
+	} else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)))
 		req->cmd_flags |= REQ_HARDBARRIER;
 
-	if (bio_sync(bio))
+	if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
 		req->cmd_flags |= REQ_RW_SYNC;
-	if (bio_rw_meta(bio))
+	if (bio_rw_flagged(bio, BIO_RW_META))
 		req->cmd_flags |= REQ_RW_META;
-	if (bio_noidle(bio))
+	if (bio_rw_flagged(bio, BIO_RW_NOIDLE))
 		req->cmd_flags |= REQ_NOIDLE;
 
 	req->errors = 0;
@@ -1150,7 +1147,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
  */
 static inline bool queue_should_plug(struct request_queue *q)
 {
-	return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
+	return !(blk_queue_nonrot(q) && blk_queue_queuing(q));
 }
 
 static int __make_request(struct request_queue *q, struct bio *bio)
@@ -1159,11 +1156,12 @@ 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 int sync = bio_sync(bio);
-	const int unplug = bio_unplug(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;
 	int rw_flags;
 
-	if (bio_barrier(bio) && bio_has_data(bio) &&
+	if (bio_rw_flagged(bio, BIO_RW_BARRIER) &&
 	    (q->next_ordered == QUEUE_ORDERED_NONE)) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
@@ -1177,7 +1175,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (unlikely(bio_barrier(bio)) || elv_queue_empty(q))
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)) || elv_queue_empty(q))
 		goto get_rq;
 
 	el_ret = elv_merge(q, &req, bio);
@@ -1190,6 +1188,9 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 		trace_block_bio_backmerge(q, bio);
 
+		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+			blk_rq_set_mixed_merge(req);
+
 		req->biotail->bi_next = bio;
 		req->biotail = bio;
 		req->__data_len += bytes;
@@ -1209,6 +1210,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 		trace_block_bio_frontmerge(q, bio);
 
+		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
+			blk_rq_set_mixed_merge(req);
+			req->cmd_flags &= ~REQ_FAILFAST_MASK;
+			req->cmd_flags |= ff;
+		}
+
 		bio->bi_next = req->bio;
 		req->bio = bio;
 
@@ -1260,7 +1267,7 @@ get_rq:
 	spin_lock_irq(q->queue_lock);
 	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) ||
 	    bio_flagged(bio, BIO_CPU_AFFINE))
-		req->cpu = blk_cpu_to_group(smp_processor_id());
+		req->cpu = blk_cpu_to_group(raw_smp_processor_id());
 	if (queue_should_plug(q) && elv_queue_empty(q))
 		blk_plug_device(q);
 	add_request(q, req);
@@ -1430,7 +1437,8 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 		}
 
-		if (unlikely(nr_sectors > queue_max_hw_sectors(q))) {
+		if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+			     nr_sectors > queue_max_hw_sectors(q))) {
 			printk(KERN_ERR "bio too big device %s (%u > %u)\n",
 			       bdevname(bio->bi_bdev, b),
 			       bio_sectors(bio),
@@ -1456,19 +1464,20 @@ static inline void __generic_make_request(struct bio *bio)
 		if (old_sector != -1)
 			trace_block_remap(q, bio, old_dev, old_sector);
 
-		trace_block_bio_queue(q, bio);
-
 		old_sector = bio->bi_sector;
 		old_dev = bio->bi_bdev->bd_dev;
 
 		if (bio_check_eod(bio, nr_sectors))
 			goto end_io;
 
-		if (bio_discard(bio) && !q->prepare_discard_fn) {
+		if (bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+		    !blk_queue_discard(q)) {
 			err = -EOPNOTSUPP;
 			goto end_io;
 		}
 
+		trace_block_bio_queue(q, bio);
+
 		ret = q->make_request_fn(q, bio);
 	} while (ret);
 
@@ -1653,6 +1662,50 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
 
+/**
+ * blk_rq_err_bytes - determine number of bytes till the next failure boundary
+ * @rq: request to examine
+ *
+ * Description:
+ *     A request could be merge of IOs which require different failure
+ *     handling.  This function determines the number of bytes which
+ *     can be failed from the beginning of the request without
+ *     crossing into area which need to be retried further.
+ *
+ * Return:
+ *     The number of bytes to fail.
+ *
+ * Context:
+ *     queue_lock must be held.
+ */
+unsigned int blk_rq_err_bytes(const struct request *rq)
+{
+	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	unsigned int bytes = 0;
+	struct bio *bio;
+
+	if (!(rq->cmd_flags & REQ_MIXED_MERGE))
+		return blk_rq_bytes(rq);
+
+	/*
+	 * Currently the only 'mixing' which can happen is between
+	 * different fastfail types.  We can safely fail portions
+	 * which have all the failfast bits that the first one has -
+	 * the ones which are at least as eager to fail as the first
+	 * one.
+	 */
+	for (bio = rq->bio; bio; bio = bio->bi_next) {
+		if ((bio->bi_rw & ff) != ff)
+			break;
+		bytes += bio->bi_size;
+	}
+
+	/* this could lead to infinite loop */
+	BUG_ON(blk_rq_bytes(rq) && !bytes);
+	return bytes;
+}
+EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
+
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (blk_do_io_stat(req)) {
@@ -1686,7 +1739,7 @@ static void blk_account_io_done(struct request *req)
 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);
 		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
+		part_dec_in_flight(part, rw);
 
 		part_stat_unlock();
 	}
@@ -1806,8 +1859,15 @@ void blk_dequeue_request(struct request *rq)
 	 * and to it is freed is accounted as io that is in progress at
 	 * the driver side.
 	 */
-	if (blk_account_rq(rq))
+	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]++;
+		/*
+		 * Mark this device as supporting hardware queuing, if
+		 * we have more IOs in flight than 4.
+		 */
+		if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
+			set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
+	}
 }
 
 /**
@@ -1999,6 +2059,12 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	if (blk_fs_request(req) || blk_discard_rq(req))
 		req->__sector += total_bytes >> 9;
 
+	/* mixed attributes always follow the first bio */
+	if (req->cmd_flags & REQ_MIXED_MERGE) {
+		req->cmd_flags &= ~REQ_FAILFAST_MASK;
+		req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
+	}
+
 	/*
 	 * If total number of sectors is less than the first segment
 	 * size, something has gone terribly wrong.
@@ -2178,6 +2244,25 @@ bool blk_end_request_cur(struct request *rq, int error)
 EXPORT_SYMBOL(blk_end_request_cur);
 
 /**
+ * blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ *     Complete @rq till the next failure boundary.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool blk_end_request_err(struct request *rq, int error)
+{
+	WARN_ON(error >= 0);
+	return blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(blk_end_request_err);
+
+/**
  * __blk_end_request - Helper function for drivers to complete the request.
  * @rq:       the request being processed
  * @error:    %0 for success, < %0 for error
@@ -2236,12 +2321,31 @@ bool __blk_end_request_cur(struct request *rq, int error)
 }
 EXPORT_SYMBOL(__blk_end_request_cur);
 
+/**
+ * __blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ *     Complete @rq till the next failure boundary.  Must be called
+ *     with queue lock held.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool __blk_end_request_err(struct request *rq, int error)
+{
+	WARN_ON(error >= 0);
+	return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(__blk_end_request_err);
+
 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, and
-	   we want BIO_RW_AHEAD (bit 1) to imply REQ_FAILFAST (bit 1). */
-	rq->cmd_flags |= (bio->bi_rw & 3);
+	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
+	rq->cmd_flags |= bio->bi_rw & REQ_RW;
 
 	if (bio_has_data(bio)) {
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
@@ -2254,6 +2358,25 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		rq->rq_disk = bio->bi_bdev->bd_disk;
 }
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+/**
+ * rq_flush_dcache_pages - Helper function to flush all pages in a request
+ * @rq: the request to be flushed
+ *
+ * Description:
+ *     Flush all pages in @rq.
+ */
+void rq_flush_dcache_pages(struct request *rq)
+{
+	struct req_iterator iter;
+	struct bio_vec *bvec;
+
+	rq_for_each_segment(bvec, rq, iter)
+		flush_dcache_page(bvec->bv_page);
+}
+EXPORT_SYMBOL_GPL(rq_flush_dcache_pages);
+#endif
+
 /**
  * blk_lld_busy - Check if underlying low-level drivers of a device are busy
  * @q : the queue of the device being checked
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index d4ed6000147d..98e6bf61b0ac 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -39,8 +39,6 @@ int put_io_context(struct io_context *ioc)
 
 	if (atomic_long_dec_and_test(&ioc->refcount)) {
 		rcu_read_lock();
-		if (ioc->aic && ioc->aic->dtor)
-			ioc->aic->dtor(ioc->aic);
 		cfq_dtor(ioc);
 		rcu_read_unlock();
 
@@ -66,22 +64,20 @@ static void cfq_exit(struct io_context *ioc)
 }
 
 /* Called by the exitting task */
-void exit_io_context(void)
+void exit_io_context(struct task_struct *task)
 {
 	struct io_context *ioc;
 
-	task_lock(current);
-	ioc = current->io_context;
-	current->io_context = NULL;
-	task_unlock(current);
+	task_lock(task);
+	ioc = task->io_context;
+	task->io_context = NULL;
+	task_unlock(task);
 
 	if (atomic_dec_and_test(&ioc->nr_tasks)) {
-		if (ioc->aic && ioc->aic->exit)
-			ioc->aic->exit(ioc->aic);
 		cfq_exit(ioc);
 
-		put_io_context(ioc);
 	}
+	put_io_context(ioc);
 }
 
 struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
@@ -97,7 +93,6 @@ struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
 		ret->ioprio = 0;
 		ret->last_waited = jiffies; /* doesn't matter... */
 		ret->nr_batch_requests = 0; /* because this is 0 */
-		ret->aic = NULL;
 		INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
 		INIT_HLIST_HEAD(&ret->cic_list);
 		ret->ioc_data = NULL;
diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c
new file mode 100644
index 000000000000..58916afbbda5
--- /dev/null
+++ b/block/blk-iopoll.c
@@ -0,0 +1,227 @@
+/*
+ * Functions related to interrupt-poll handling in the block layer. This
+ * is similar to NAPI for network devices.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/blk-iopoll.h>
+#include <linux/delay.h>
+
+#include "blk.h"
+
+int blk_iopoll_enabled = 1;
+EXPORT_SYMBOL(blk_iopoll_enabled);
+
+static unsigned int blk_iopoll_budget __read_mostly = 256;
+
+static DEFINE_PER_CPU(struct list_head, blk_cpu_iopoll);
+
+/**
+ * blk_iopoll_sched - Schedule a run of the iopoll handler
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     Add this blk_iopoll structure to the pending poll list and trigger the
+ *     raise of the blk iopoll softirq. The driver must already have gotten a
+ *     successful return from blk_iopoll_sched_prep() before calling this.
+ **/
+void blk_iopoll_sched(struct blk_iopoll *iop)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	list_add_tail(&iop->list, &__get_cpu_var(blk_cpu_iopoll));
+	__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(blk_iopoll_sched);
+
+/**
+ * __blk_iopoll_complete - Mark this @iop as un-polled again
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     See blk_iopoll_complete(). This function must be called with interrupts
+ *     disabled.
+ **/
+void __blk_iopoll_complete(struct blk_iopoll *iop)
+{
+	list_del(&iop->list);
+	smp_mb__before_clear_bit();
+	clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
+}
+EXPORT_SYMBOL(__blk_iopoll_complete);
+
+/**
+ * blk_iopoll_complete - Mark this @iop as un-polled again
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     If a driver consumes less than the assigned budget in its run of the
+ *     iopoll handler, it'll end the polled mode by calling this function. The
+ *     iopoll handler will not be invoked again before blk_iopoll_sched_prep()
+ *     is called.
+ **/
+void blk_iopoll_complete(struct blk_iopoll *iopoll)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__blk_iopoll_complete(iopoll);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(blk_iopoll_complete);
+
+static void blk_iopoll_softirq(struct softirq_action *h)
+{
+	struct list_head *list = &__get_cpu_var(blk_cpu_iopoll);
+	int rearm = 0, budget = blk_iopoll_budget;
+	unsigned long start_time = jiffies;
+
+	local_irq_disable();
+
+	while (!list_empty(list)) {
+		struct blk_iopoll *iop;
+		int work, weight;
+
+		/*
+		 * If softirq window is exhausted then punt.
+		 */
+		if (budget <= 0 || time_after(jiffies, start_time)) {
+			rearm = 1;
+			break;
+		}
+
+		local_irq_enable();
+
+		/* Even though interrupts have been re-enabled, this
+		 * access is safe because interrupts can only add new
+		 * entries to the tail of this list, and only ->poll()
+		 * calls can remove this head entry from the list.
+		 */
+		iop = list_entry(list->next, struct blk_iopoll, list);
+
+		weight = iop->weight;
+		work = 0;
+		if (test_bit(IOPOLL_F_SCHED, &iop->state))
+			work = iop->poll(iop, weight);
+
+		budget -= work;
+
+		local_irq_disable();
+
+		/*
+		 * Drivers must not modify the iopoll state, if they
+		 * consume their assigned weight (or more, some drivers can't
+		 * easily just stop processing, they have to complete an
+		 * entire mask of commands).In such cases this code
+		 * still "owns" the iopoll instance and therefore can
+		 * move the instance around on the list at-will.
+		 */
+		if (work >= weight) {
+			if (blk_iopoll_disable_pending(iop))
+				__blk_iopoll_complete(iop);
+			else
+				list_move_tail(&iop->list, list);
+		}
+	}
+
+	if (rearm)
+		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
+
+	local_irq_enable();
+}
+
+/**
+ * blk_iopoll_disable - Disable iopoll on this @iop
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     Disable io polling and wait for any pending callbacks to have completed.
+ **/
+void blk_iopoll_disable(struct blk_iopoll *iop)
+{
+	set_bit(IOPOLL_F_DISABLE, &iop->state);
+	while (test_and_set_bit(IOPOLL_F_SCHED, &iop->state))
+		msleep(1);
+	clear_bit(IOPOLL_F_DISABLE, &iop->state);
+}
+EXPORT_SYMBOL(blk_iopoll_disable);
+
+/**
+ * blk_iopoll_enable - Enable iopoll on this @iop
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     Enable iopoll on this @iop. Note that the handler run will not be
+ *     scheduled, it will only mark it as active.
+ **/
+void blk_iopoll_enable(struct blk_iopoll *iop)
+{
+	BUG_ON(!test_bit(IOPOLL_F_SCHED, &iop->state));
+	smp_mb__before_clear_bit();
+	clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
+}
+EXPORT_SYMBOL(blk_iopoll_enable);
+
+/**
+ * blk_iopoll_init - Initialize this @iop
+ * @iop:      The parent iopoll structure
+ * @weight:   The default weight (or command completion budget)
+ * @poll_fn:  The handler to invoke
+ *
+ * Description:
+ *     Initialize this blk_iopoll structure. Before being actively used, the
+ *     driver must call blk_iopoll_enable().
+ **/
+void blk_iopoll_init(struct blk_iopoll *iop, int weight, blk_iopoll_fn *poll_fn)
+{
+	memset(iop, 0, sizeof(*iop));
+	INIT_LIST_HEAD(&iop->list);
+	iop->weight = weight;
+	iop->poll = poll_fn;
+	set_bit(IOPOLL_F_SCHED, &iop->state);
+}
+EXPORT_SYMBOL(blk_iopoll_init);
+
+static int __cpuinit blk_iopoll_cpu_notify(struct notifier_block *self,
+					  unsigned long action, void *hcpu)
+{
+	/*
+	 * If a CPU goes away, splice its entries to the current CPU
+	 * and trigger a run of the softirq
+	 */
+	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+		int cpu = (unsigned long) hcpu;
+
+		local_irq_disable();
+		list_splice_init(&per_cpu(blk_cpu_iopoll, cpu),
+				 &__get_cpu_var(blk_cpu_iopoll));
+		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
+		local_irq_enable();
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata blk_iopoll_cpu_notifier = {
+	.notifier_call	= blk_iopoll_cpu_notify,
+};
+
+static __init int blk_iopoll_setup(void)
+{
+	int i;
+
+	for_each_possible_cpu(i)
+		INIT_LIST_HEAD(&per_cpu(blk_cpu_iopoll, i));
+
+	open_softirq(BLOCK_IOPOLL_SOFTIRQ, blk_iopoll_softirq);
+	register_hotcpu_notifier(&blk_iopoll_cpu_notifier);
+	return 0;
+}
+subsys_initcall(blk_iopoll_setup);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index e1999679a4d5..99cb5cf1f447 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -311,6 +311,36 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	return 1;
 }
 
+/**
+ * blk_rq_set_mixed_merge - mark a request as mixed merge
+ * @rq: request to mark as mixed merge
+ *
+ * Description:
+ *     @rq is about to be mixed merged.  Make sure the attributes
+ *     which can be mixed are set in each bio and mark @rq as mixed
+ *     merged.
+ */
+void blk_rq_set_mixed_merge(struct request *rq)
+{
+	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	struct bio *bio;
+
+	if (rq->cmd_flags & REQ_MIXED_MERGE)
+		return;
+
+	/*
+	 * @rq will no longer represent mixable attributes for all the
+	 * contained bios.  It will just track those of the first one.
+	 * Distributes the attributs to each bio.
+	 */
+	for (bio = rq->bio; bio; bio = bio->bi_next) {
+		WARN_ON_ONCE((bio->bi_rw & REQ_FAILFAST_MASK) &&
+			     (bio->bi_rw & REQ_FAILFAST_MASK) != ff);
+		bio->bi_rw |= ff;
+	}
+	rq->cmd_flags |= REQ_MIXED_MERGE;
+}
+
 static void blk_account_io_merge(struct request *req)
 {
 	if (blk_do_io_stat(req)) {
@@ -321,7 +351,7 @@ static void blk_account_io_merge(struct request *req)
 		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
 
 		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
+		part_dec_in_flight(part, rq_data_dir(req));
 
 		part_stat_unlock();
 	}
@@ -350,12 +380,6 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (blk_integrity_rq(req) != blk_integrity_rq(next))
 		return 0;
 
-	/* don't merge requests of different failfast settings */
-	if (blk_failfast_dev(req)	!= blk_failfast_dev(next)	||
-	    blk_failfast_transport(req)	!= blk_failfast_transport(next)	||
-	    blk_failfast_driver(req)	!= blk_failfast_driver(next))
-		return 0;
-
 	/*
 	 * If we are allowed to merge, then append bio list
 	 * from next to rq and release next. merge_requests_fn
@@ -366,6 +390,19 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 		return 0;
 
 	/*
+	 * If failfast settings disagree or any of the two is already
+	 * a mixed merge, mark both as mixed before proceeding.  This
+	 * makes sure that all involved bios have mixable attributes
+	 * set properly.
+	 */
+	if ((req->cmd_flags | next->cmd_flags) & REQ_MIXED_MERGE ||
+	    (req->cmd_flags & REQ_FAILFAST_MASK) !=
+	    (next->cmd_flags & REQ_FAILFAST_MASK)) {
+		blk_rq_set_mixed_merge(req);
+		blk_rq_set_mixed_merge(next);
+	}
+
+	/*
 	 * At this point we have either done a back merge
 	 * or front merge. We need the smaller start_time of
 	 * the merged requests to be the current request
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 476d87065073..5eeb9e0d256e 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -8,6 +8,7 @@
 #include <linux/blkdev.h>
 #include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
 #include <linux/gcd.h>
+#include <linux/jiffies.h>
 
 #include "blk.h"
 
@@ -34,23 +35,6 @@ void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn)
 EXPORT_SYMBOL(blk_queue_prep_rq);
 
 /**
- * blk_queue_set_discard - set a discard_sectors function for queue
- * @q:		queue
- * @dfn:	prepare_discard function
- *
- * It's possible for a queue to register a discard callback which is used
- * to transform a discard request into the appropriate type for the
- * hardware. If none is registered, then discard requests are failed
- * with %EOPNOTSUPP.
- *
- */
-void blk_queue_set_discard(struct request_queue *q, prepare_discard_fn *dfn)
-{
-	q->prepare_discard_fn = dfn;
-}
-EXPORT_SYMBOL(blk_queue_set_discard);
-
-/**
  * blk_queue_merge_bvec - set a merge_bvec function for queue
  * @q:		queue
  * @mbfn:	merge_bvec_fn
@@ -111,7 +95,13 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->max_hw_segments = MAX_HW_SEGMENTS;
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->max_segment_size = MAX_SEGMENT_SIZE;
-	lim->max_sectors = lim->max_hw_sectors = SAFE_MAX_SECTORS;
+	lim->max_sectors = BLK_DEF_MAX_SECTORS;
+	lim->max_hw_sectors = INT_MAX;
+	lim->max_discard_sectors = 0;
+	lim->discard_granularity = 0;
+	lim->discard_alignment = 0;
+	lim->discard_misaligned = 0;
+	lim->discard_zeroes_data = -1;
 	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
 	lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
 	lim->alignment_offset = 0;
@@ -156,7 +146,7 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 	q->nr_batching = BLK_BATCH_REQ;
 
 	q->unplug_thresh = 4;		/* hmm */
-	q->unplug_delay = (3 * HZ) / 1000;	/* 3 milliseconds */
+	q->unplug_delay = msecs_to_jiffies(3);	/* 3 milliseconds */
 	if (q->unplug_delay == 0)
 		q->unplug_delay = 1;
 
@@ -164,6 +154,7 @@ 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);
 
 	/*
 	 * If the caller didn't supply a lock, fall back to our embedded
@@ -254,6 +245,18 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors)
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
 /**
+ * blk_queue_max_discard_sectors - set max sectors for a single discard
+ * @q:  the request queue for the device
+ * @max_discard_sectors: maximum number of sectors to discard
+ **/
+void blk_queue_max_discard_sectors(struct request_queue *q,
+		unsigned int max_discard_sectors)
+{
+	q->limits.max_discard_sectors = max_discard_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_discard_sectors);
+
+/**
  * blk_queue_max_phys_segments - set max phys segments for a request for this queue
  * @q:  the request queue for the device
  * @max_segments:  max number of segments
@@ -428,6 +431,25 @@ void blk_queue_io_min(struct request_queue *q, unsigned int min)
 EXPORT_SYMBOL(blk_queue_io_min);
 
 /**
+ * blk_limits_io_opt - set optimal request size for a device
+ * @limits: the queue limits
+ * @opt:  smallest I/O size in bytes
+ *
+ * Description:
+ *   Storage devices may report an optimal I/O size, which is the
+ *   device's preferred unit for sustained I/O.  This is rarely reported
+ *   for disk drives.  For RAID arrays it is usually the stripe width or
+ *   the internal track size.  A properly aligned multiple of
+ *   optimal_io_size is the preferred request size for workloads where
+ *   sustained throughput is desired.
+ */
+void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt)
+{
+	limits->io_opt = opt;
+}
+EXPORT_SYMBOL(blk_limits_io_opt);
+
+/**
  * blk_queue_io_opt - set optimal request size for the queue
  * @q:	the request queue for the device
  * @opt:  optimal request size in bytes
@@ -442,7 +464,7 @@ EXPORT_SYMBOL(blk_queue_io_min);
  */
 void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
 {
-	q->limits.io_opt = opt;
+	blk_limits_io_opt(&q->limits, opt);
 }
 EXPORT_SYMBOL(blk_queue_io_opt);
 
@@ -471,20 +493,43 @@ 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)
- * @b:  the underlying queue limits (bottom)
+ * @t:	the stacking driver limits (top device)
+ * @b:  the underlying queue limits (bottom, component device)
  * @offset:  offset to beginning of data within component device
  *
  * Description:
- *    Merges two queue_limit structs.  Returns 0 if alignment didn't
- *    change.  Returns -1 if adding the bottom device caused
- *    misalignment.
+ *    This function is used by stacking drivers like MD and DM to ensure
+ *    that all component devices have compatible block sizes and
+ *    alignments.  The stacking driver must provide a queue_limits
+ *    struct (top) and then iteratively call the stacking function for
+ *    all component (bottom) devices.  The stacking function will
+ *    attempt to combine the values and ensure proper alignment.
+ *
+ *    Returns 0 if the top and bottom queue_limits are compatible.  The
+ *    top device's block sizes and alignment offsets may be adjusted to
+ *    ensure alignment with the bottom device. If no compatible sizes
+ *    and alignments exist, -1 is returned and the resulting top
+ *    queue_limits will have the misaligned flag set to indicate that
+ *    the alignment_offset is undefined.
  */
 int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		     sector_t offset)
 {
+	sector_t alignment;
+	unsigned int top, bottom, 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);
 	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
@@ -501,6 +546,26 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	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);
+
+	/* Bottom device has different alignment.  Check that it is
+	 * compatible with the current top alignment.
+	 */
+	if (t->alignment_offset != alignment) {
+
+		top = max(t->physical_block_size, t->io_min)
+			+ t->alignment_offset;
+		bottom = max(b->physical_block_size, b->io_min) + alignment;
+
+		/* Verify that top and bottom intervals line up */
+		if (max(top, bottom) & (min(top, bottom) - 1)) {
+			t->misaligned = 1;
+			ret = -1;
+		}
+	}
+
 	t->logical_block_size = max(t->logical_block_size,
 				    b->logical_block_size);
 
@@ -508,41 +573,95 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 				     b->physical_block_size);
 
 	t->io_min = max(t->io_min, b->io_min);
+	t->io_opt = lcm(t->io_opt, b->io_opt);
+
 	t->no_cluster |= b->no_cluster;
+	t->discard_zeroes_data &= b->discard_zeroes_data;
 
-	/* Bottom device offset aligned? */
-	if (offset &&
-	    (offset & (b->physical_block_size - 1)) != b->alignment_offset) {
+	/* Physical block size a multiple of the logical block size? */
+	if (t->physical_block_size & (t->logical_block_size - 1)) {
+		t->physical_block_size = t->logical_block_size;
 		t->misaligned = 1;
-		return -1;
+		ret = -1;
 	}
 
-	/* If top has no alignment offset, inherit from bottom */
-	if (!t->alignment_offset)
-		t->alignment_offset =
-			b->alignment_offset & (b->physical_block_size - 1);
+	/* Minimum I/O a multiple of the physical block size? */
+	if (t->io_min & (t->physical_block_size - 1)) {
+		t->io_min = t->physical_block_size;
+		t->misaligned = 1;
+		ret = -1;
+	}
 
-	/* Top device aligned on logical block boundary? */
-	if (t->alignment_offset & (t->logical_block_size - 1)) {
+	/* Optimal I/O a multiple of the physical block size? */
+	if (t->io_opt & (t->physical_block_size - 1)) {
+		t->io_opt = 0;
 		t->misaligned = 1;
-		return -1;
+		ret = -1;
 	}
 
-	/* Find lcm() of optimal I/O size */
-	if (t->io_opt && b->io_opt)
-		t->io_opt = (t->io_opt * b->io_opt) / gcd(t->io_opt, b->io_opt);
-	else if (b->io_opt)
-		t->io_opt = b->io_opt;
+	/* Find lowest common alignment_offset */
+	t->alignment_offset = lcm(t->alignment_offset, alignment)
+		& (max(t->physical_block_size, t->io_min) - 1);
 
-	/* Verify that optimal I/O size is a multiple of io_min */
-	if (t->io_min && t->io_opt % t->io_min)
-		return -1;
+	/* Verify that new alignment_offset is on a logical block boundary */
+	if (t->alignment_offset & (t->logical_block_size - 1)) {
+		t->misaligned = 1;
+		ret = -1;
+	}
 
-	return 0;
+	/* 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);
+
+		if (t->discard_granularity != 0 &&
+		    t->discard_alignment != alignment) {
+			top = t->discard_granularity + t->discard_alignment;
+			bottom = b->discard_granularity + alignment;
+
+			/* Verify that top and bottom intervals line up */
+			if (max(top, bottom) & (min(top, bottom) - 1))
+				t->discard_misaligned = 1;
+		}
+
+		t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
+						      b->max_discard_sectors);
+		t->discard_granularity = max(t->discard_granularity,
+					     b->discard_granularity);
+		t->discard_alignment = lcm(t->discard_alignment, alignment) &
+			(t->discard_granularity - 1);
+	}
+
+	return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);
 
 /**
+ * bdev_stack_limits - adjust queue limits for stacked drivers
+ * @t:	the stacking driver limits (top device)
+ * @bdev:  the component block_device (bottom)
+ * @start:  first data sector within component device
+ *
+ * Description:
+ *    Merges queue limits for a top device and a block_device.  Returns
+ *    0 if alignment didn't change.  Returns -1 if adding the bottom
+ *    device caused misalignment.
+ */
+int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
+		      sector_t start)
+{
+	struct request_queue *bq = bdev_get_queue(bdev);
+
+	start += get_start_sect(bdev);
+
+	return blk_stack_limits(t, &bq->limits, start << 9);
+}
+EXPORT_SYMBOL(bdev_stack_limits);
+
+/**
  * disk_stack_limits - adjust queue limits for stacked drivers
  * @disk:  MD/DM gendisk (top)
  * @bdev:  the underlying block device (bottom)
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index d3aa2aadb3e0..8606c9543fdd 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -40,7 +40,12 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 {
 	struct request_list *rl = &q->rq;
 	unsigned long nr;
-	int ret = queue_var_store(&nr, page, count);
+	int ret;
+
+	if (!q->request_fn)
+		return -EINVAL;
+
+	ret = queue_var_store(&nr, page, count);
 	if (nr < BLKDEV_MIN_RQ)
 		nr = BLKDEV_MIN_RQ;
 
@@ -121,6 +126,21 @@ static ssize_t queue_io_opt_show(struct request_queue *q, char *page)
 	return queue_var_show(queue_io_opt(q), page);
 }
 
+static ssize_t queue_discard_granularity_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(q->limits.discard_granularity, page);
+}
+
+static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(q->limits.max_discard_sectors << 9, page);
+}
+
+static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_discard_zeroes_data(q), page);
+}
+
 static ssize_t
 queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 {
@@ -288,6 +308,21 @@ static struct queue_sysfs_entry queue_io_opt_entry = {
 	.show = queue_io_opt_show,
 };
 
+static struct queue_sysfs_entry queue_discard_granularity_entry = {
+	.attr = {.name = "discard_granularity", .mode = S_IRUGO },
+	.show = queue_discard_granularity_show,
+};
+
+static struct queue_sysfs_entry queue_discard_max_entry = {
+	.attr = {.name = "discard_max_bytes", .mode = S_IRUGO },
+	.show = queue_discard_max_show,
+};
+
+static struct queue_sysfs_entry queue_discard_zeroes_data_entry = {
+	.attr = {.name = "discard_zeroes_data", .mode = S_IRUGO },
+	.show = queue_discard_zeroes_data_show,
+};
+
 static struct queue_sysfs_entry queue_nonrot_entry = {
 	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_nonrot_show,
@@ -323,6 +358,9 @@ static struct attribute *default_attrs[] = {
 	&queue_physical_block_size_entry.attr,
 	&queue_io_min_entry.attr,
 	&queue_io_opt_entry.attr,
+	&queue_discard_granularity_entry.attr,
+	&queue_discard_max_entry.attr,
+	&queue_discard_zeroes_data_entry.attr,
 	&queue_nonrot_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
@@ -447,6 +485,7 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret) {
 		kobject_uevent(&q->kobj, KOBJ_REMOVE);
 		kobject_del(&q->kobj);
+		blk_trace_remove_sysfs(disk_to_dev(disk));
 		return ret;
 	}
 
@@ -460,11 +499,11 @@ void blk_unregister_queue(struct gendisk *disk)
 	if (WARN_ON(!q))
 		return;
 
-	if (q->request_fn) {
+	if (q->request_fn)
 		elv_unregister_queue(q);
 
-		kobject_uevent(&q->kobj, KOBJ_REMOVE);
-		kobject_del(&q->kobj);
-		kobject_put(&disk_to_dev(disk)->kobj);
-	}
+	kobject_uevent(&q->kobj, KOBJ_REMOVE);
+	kobject_del(&q->kobj);
+	blk_trace_remove_sysfs(disk_to_dev(disk));
+	kobject_put(&disk_to_dev(disk)->kobj);
 }
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 2e5cfeb59333..6b0f52c20964 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -359,7 +359,7 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 		max_depth -= 2;
 		if (!max_depth)
 			max_depth = 1;
-		if (q->in_flight[0] > max_depth)
+		if (q->in_flight[BLK_RW_ASYNC] > max_depth)
 			return 1;
 	}
 
diff --git a/block/blk.h b/block/blk.h
index 3fae6add5430..5ee3d7e72feb 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -104,6 +104,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 int attempt_back_merge(struct request_queue *q, struct request *rq);
 int attempt_front_merge(struct request_queue *q, struct request *rq);
 void blk_recalc_rq_segments(struct request *rq);
+void blk_rq_set_mixed_merge(struct request *rq);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
diff --git a/block/bsg.c b/block/bsg.c
index 5f184bb3ff9e..a9fd2d84b53a 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -15,6 +15,7 @@
 #include <linux/blkdev.h>
 #include <linux/poll.h>
 #include <linux/cdev.h>
+#include <linux/jiffies.h>
 #include <linux/percpu.h>
 #include <linux/uio.h>
 #include <linux/idr.h>
@@ -197,7 +198,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 	rq->cmd_len = hdr->request_len;
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 
-	rq->timeout = (hdr->timeout * HZ) / 1000;
+	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
 		rq->timeout = q->sg_timeout;
 	if (!rq->timeout)
@@ -1062,7 +1063,7 @@ EXPORT_SYMBOL_GPL(bsg_register_queue);
 
 static struct cdev bsg_cdev;
 
-static char *bsg_nodename(struct device *dev)
+static char *bsg_devnode(struct device *dev, mode_t *mode)
 {
 	return kasprintf(GFP_KERNEL, "bsg/%s", dev_name(dev));
 }
@@ -1087,7 +1088,7 @@ static int __init bsg_init(void)
 		ret = PTR_ERR(bsg_class);
 		goto destroy_kmemcache;
 	}
-	bsg_class->nodename = bsg_nodename;
+	bsg_class->devnode = bsg_devnode;
 
 	ret = alloc_chrdev_region(&devid, 0, BSG_MAX_DEVS, "bsg");
 	if (ret)
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index fd7080ed7935..023f4e69a337 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -9,9 +9,11 @@
 #include <linux/module.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"
 
 /*
  * tunables
@@ -27,6 +29,8 @@ 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 const int cfq_target_latency = HZ * 3/10; /* 300 ms */
+static const int cfq_hist_divisor = 4;
 
 /*
  * offset from end of service tree
@@ -40,6 +44,10 @@ static int cfq_slice_idle = HZ / 125;
 
 #define CFQ_SLICE_SCALE		(5)
 #define CFQ_HW_QUEUE_MIN	(5)
+#define CFQ_SERVICE_SHIFT       12
+
+#define CFQQ_SEEK_THR		8 * 1024
+#define CFQQ_SEEKY(cfqq)	((cfqq)->seek_mean > CFQQ_SEEK_THR)
 
 #define RQ_CIC(rq)		\
 	((struct cfq_io_context *) (rq)->elevator_private)
@@ -48,7 +56,7 @@ static int cfq_slice_idle = HZ / 125;
 static struct kmem_cache *cfq_pool;
 static struct kmem_cache *cfq_ioc_pool;
 
-static DEFINE_PER_CPU(unsigned long, ioc_count);
+static DEFINE_PER_CPU(unsigned long, cfq_ioc_count);
 static struct completion *ioc_gone;
 static DEFINE_SPINLOCK(ioc_gone_lock);
 
@@ -57,6 +65,7 @@ static DEFINE_SPINLOCK(ioc_gone_lock);
 #define cfq_class_rt(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
 
 #define sample_valid(samples)	((samples) > 80)
+#define rb_entry_cfqg(node)	rb_entry((node), struct cfq_group, rb_node)
 
 /*
  * Most of our rbtree usage is for sorting with min extraction, so
@@ -67,8 +76,12 @@ static DEFINE_SPINLOCK(ioc_gone_lock);
 struct cfq_rb_root {
 	struct rb_root rb;
 	struct rb_node *left;
+	unsigned count;
+	u64 min_vdisktime;
+	struct rb_node *active;
+	unsigned total_weight;
 };
-#define CFQ_RB_ROOT	(struct cfq_rb_root) { RB_ROOT, NULL, }
+#define CFQ_RB_ROOT	(struct cfq_rb_root) { RB_ROOT, NULL, 0, 0, }
 
 /*
  * Per process-grouping structure
@@ -99,6 +112,11 @@ struct cfq_queue {
 	/* fifo list of requests in sort_list */
 	struct list_head fifo;
 
+	/* time when queue got scheduled in to dispatch first request. */
+	unsigned long dispatch_start;
+	unsigned int allocated_slice;
+	/* 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;
@@ -112,7 +130,70 @@ 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;
+
 	pid_t pid;
+
+	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 */
+	unsigned long nr_sectors;
+};
+
+/*
+ * First index in the service_trees.
+ * IDLE is handled separately, so it has negative index
+ */
+enum wl_prio_t {
+	BE_WORKLOAD = 0,
+	RT_WORKLOAD = 1,
+	IDLE_WORKLOAD = 2,
+};
+
+/*
+ * Second index in the service_trees.
+ */
+enum wl_type_t {
+	ASYNC_WORKLOAD = 0,
+	SYNC_NOIDLE_WORKLOAD = 1,
+	SYNC_WORKLOAD = 2
+};
+
+/* This is per cgroup per device grouping structure */
+struct cfq_group {
+	/* group service_tree member */
+	struct rb_node rb_node;
+
+	/* group service_tree key */
+	u64 vdisktime;
+	unsigned int weight;
+	bool on_st;
+
+	/* number of cfqq currently on this group */
+	int nr_cfqq;
+
+	/* Per group busy queus average. Useful for workload slice calc. */
+	unsigned int busy_queues_avg[2];
+	/*
+	 * rr lists of queues with requests, onle rr for each priority class.
+	 * Counts are embedded in the cfq_rb_root
+	 */
+	struct cfq_rb_root service_trees[2][3];
+	struct cfq_rb_root service_tree_idle;
+
+	unsigned long saved_workload_slice;
+	enum wl_type_t saved_workload;
+	enum wl_prio_t saved_serving_prio;
+	struct blkio_group blkg;
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	struct hlist_node cfqd_node;
+	atomic_t ref;
+#endif
 };
 
 /*
@@ -120,11 +201,18 @@ struct cfq_queue {
  */
 struct cfq_data {
 	struct request_queue *queue;
+	/* Root service tree for cfq_groups */
+	struct cfq_rb_root grp_service_tree;
+	struct cfq_group root_group;
 
 	/*
-	 * rr list of queues with requests and the count of them
+	 * The priority currently being served
 	 */
-	struct cfq_rb_root service_tree;
+	enum wl_prio_t serving_prio;
+	enum wl_type_t serving_type;
+	unsigned long workload_expires;
+	struct cfq_group *serving_group;
+	bool noidle_tree_requires_idle;
 
 	/*
 	 * Each priority tree is sorted by next_request position.  These
@@ -134,13 +222,8 @@ struct cfq_data {
 	struct rb_root prio_trees[CFQ_PRIO_LISTS];
 
 	unsigned int busy_queues;
-	/*
-	 * Used to track any pending rt requests so we can pre-empt current
-	 * non-RT cfqq in service when this value is non-zero.
-	 */
-	unsigned int busy_rt_queues;
 
-	int rq_in_driver;
+	int rq_in_driver[2];
 	int sync_flight;
 
 	/*
@@ -148,8 +231,14 @@ struct cfq_data {
 	 */
 	int rq_queued;
 	int hw_tag;
-	int hw_tag_samples;
-	int rq_in_driver_peak;
+	/*
+	 * hw_tag can be
+	 * -1 => indeterminate, (cfq will behave as if NCQ is present, to allow better detection)
+	 *  1 => NCQ is present (hw_tag_est_depth is the estimated max depth)
+	 *  0 => no NCQ
+	 */
+	int hw_tag_est_depth;
+	unsigned int hw_tag_samples;
 
 	/*
 	 * idle window management
@@ -178,6 +267,8 @@ struct cfq_data {
 	unsigned int cfq_slice[2];
 	unsigned int cfq_slice_async_rq;
 	unsigned int cfq_slice_idle;
+	unsigned int cfq_latency;
+	unsigned int cfq_group_isolation;
 
 	struct list_head cic_list;
 
@@ -185,20 +276,43 @@ struct cfq_data {
 	 * Fallback dummy cfqq for extreme OOM conditions
 	 */
 	struct cfq_queue oom_cfqq;
+
+	unsigned long last_delayed_sync;
+
+	/* List of cfq groups being managed on this device*/
+	struct hlist_head cfqg_list;
+	struct rcu_head rcu;
 };
 
+static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
+
+static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,
+					    enum wl_prio_t prio,
+					    enum wl_type_t type)
+{
+	if (!cfqg)
+		return NULL;
+
+	if (prio == IDLE_WORKLOAD)
+		return &cfqg->service_tree_idle;
+
+	return &cfqg->service_trees[prio][type];
+}
+
 enum cfqq_state_flags {
 	CFQ_CFQQ_FLAG_on_rr = 0,	/* on round-robin busy list */
 	CFQ_CFQQ_FLAG_wait_request,	/* waiting for a request */
 	CFQ_CFQQ_FLAG_must_dispatch,	/* must be allowed a dispatch */
-	CFQ_CFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
 	CFQ_CFQQ_FLAG_must_alloc_slice,	/* per-slice must_alloc flag */
 	CFQ_CFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
 	CFQ_CFQQ_FLAG_idle_window,	/* slice idling enabled */
 	CFQ_CFQQ_FLAG_prio_changed,	/* task priority has changed */
 	CFQ_CFQQ_FLAG_slice_new,	/* no requests dispatched in slice */
 	CFQ_CFQQ_FLAG_sync,		/* synchronous queue */
-	CFQ_CFQQ_FLAG_coop,		/* has done a coop jump of the 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 */
 };
 
 #define CFQ_CFQQ_FNS(name)						\
@@ -218,7 +332,6 @@ static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq)		\
 CFQ_CFQQ_FNS(on_rr);
 CFQ_CFQQ_FNS(wait_request);
 CFQ_CFQQ_FNS(must_dispatch);
-CFQ_CFQQ_FNS(must_alloc);
 CFQ_CFQQ_FNS(must_alloc_slice);
 CFQ_CFQQ_FNS(fifo_expire);
 CFQ_CFQQ_FNS(idle_window);
@@ -226,41 +339,108 @@ 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
+#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', \
+			blkg_path(&(cfqq)->cfqg->blkg), ##args);
+
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)				\
+	blk_add_trace_msg((cfqd)->queue, "%s " fmt,			\
+				blkg_path(&(cfqg)->blkg), ##args);      \
+
+#else
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0);
+#endif
 #define cfq_log(cfqd, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
 
+/* Traverses through cfq group service trees */
+#define for_each_cfqg_st(cfqg, i, j, st) \
+	for (i = 0; i <= IDLE_WORKLOAD; i++) \
+		for (j = 0, st = i < IDLE_WORKLOAD ? &cfqg->service_trees[i][j]\
+			: &cfqg->service_tree_idle; \
+			(i < IDLE_WORKLOAD && j <= SYNC_WORKLOAD) || \
+			(i == IDLE_WORKLOAD && j == 0); \
+			j++, st = i < IDLE_WORKLOAD ? \
+			&cfqg->service_trees[i][j]: NULL) \
+
+
+static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq)
+{
+	if (cfq_class_idle(cfqq))
+		return IDLE_WORKLOAD;
+	if (cfq_class_rt(cfqq))
+		return RT_WORKLOAD;
+	return BE_WORKLOAD;
+}
+
+
+static enum wl_type_t cfqq_type(struct cfq_queue *cfqq)
+{
+	if (!cfq_cfqq_sync(cfqq))
+		return ASYNC_WORKLOAD;
+	if (!cfq_cfqq_idle_window(cfqq))
+		return SYNC_NOIDLE_WORKLOAD;
+	return SYNC_WORKLOAD;
+}
+
+static inline int cfq_group_busy_queues_wl(enum wl_prio_t wl,
+					struct cfq_data *cfqd,
+					struct cfq_group *cfqg)
+{
+	if (wl == IDLE_WORKLOAD)
+		return cfqg->service_tree_idle.count;
+
+	return cfqg->service_trees[wl][ASYNC_WORKLOAD].count
+		+ cfqg->service_trees[wl][SYNC_NOIDLE_WORKLOAD].count
+		+ cfqg->service_trees[wl][SYNC_WORKLOAD].count;
+}
+
+static inline int cfqg_busy_async_queues(struct cfq_data *cfqd,
+					struct cfq_group *cfqg)
+{
+	return cfqg->service_trees[RT_WORKLOAD][ASYNC_WORKLOAD].count
+		+ cfqg->service_trees[BE_WORKLOAD][ASYNC_WORKLOAD].count;
+}
+
 static void cfq_dispatch_insert(struct request_queue *, struct request *);
-static struct cfq_queue *cfq_get_queue(struct cfq_data *, int,
+static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,
 				       struct io_context *, gfp_t);
 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,
-					    int is_sync)
+					    bool is_sync)
 {
-	return cic->cfqq[!!is_sync];
+	return cic->cfqq[is_sync];
 }
 
 static inline void cic_set_cfqq(struct cfq_io_context *cic,
-				struct cfq_queue *cfqq, int is_sync)
+				struct cfq_queue *cfqq, bool is_sync)
 {
-	cic->cfqq[!!is_sync] = cfqq;
+	cic->cfqq[is_sync] = cfqq;
 }
 
 /*
  * 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 int cfq_bio_sync(struct bio *bio)
+static inline bool cfq_bio_sync(struct bio *bio)
 {
-	if (bio_data_dir(bio) == READ || bio_sync(bio))
-		return 1;
-
-	return 0;
+	return bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO);
 }
 
 /*
@@ -279,7 +459,7 @@ static int cfq_queue_empty(struct request_queue *q)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 
-	return !cfqd->busy_queues;
+	return !cfqd->rq_queued;
 }
 
 /*
@@ -287,7 +467,7 @@ static int cfq_queue_empty(struct request_queue *q)
  * if a queue is marked sync and has sync io queued. A sync queue with async
  * io only, should not get full sync slice length.
  */
-static inline int cfq_prio_slice(struct cfq_data *cfqd, int sync,
+static inline int cfq_prio_slice(struct cfq_data *cfqd, bool sync,
 				 unsigned short prio)
 {
 	const int base_slice = cfqd->cfq_slice[sync];
@@ -303,10 +483,110 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
 }
 
+static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_group *cfqg)
+{
+	u64 d = delta << CFQ_SERVICE_SHIFT;
+
+	d = d * BLKIO_WEIGHT_DEFAULT;
+	do_div(d, cfqg->weight);
+	return d;
+}
+
+static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
+{
+	s64 delta = (s64)(vdisktime - min_vdisktime);
+	if (delta > 0)
+		min_vdisktime = vdisktime;
+
+	return min_vdisktime;
+}
+
+static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
+{
+	s64 delta = (s64)(vdisktime - min_vdisktime);
+	if (delta < 0)
+		min_vdisktime = vdisktime;
+
+	return min_vdisktime;
+}
+
+static void update_min_vdisktime(struct cfq_rb_root *st)
+{
+	u64 vdisktime = st->min_vdisktime;
+	struct cfq_group *cfqg;
+
+	if (st->active) {
+		cfqg = rb_entry_cfqg(st->active);
+		vdisktime = cfqg->vdisktime;
+	}
+
+	if (st->left) {
+		cfqg = rb_entry_cfqg(st->left);
+		vdisktime = min_vdisktime(vdisktime, cfqg->vdisktime);
+	}
+
+	st->min_vdisktime = max_vdisktime(st->min_vdisktime, vdisktime);
+}
+
+/*
+ * get averaged number of queues of RT/BE priority.
+ * average is updated, with a formula that gives more weight to higher numbers,
+ * to quickly follows sudden increases and decrease slowly
+ */
+
+static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd,
+					struct cfq_group *cfqg, bool rt)
+{
+	unsigned min_q, max_q;
+	unsigned mult  = cfq_hist_divisor - 1;
+	unsigned round = cfq_hist_divisor / 2;
+	unsigned busy = cfq_group_busy_queues_wl(rt, cfqd, cfqg);
+
+	min_q = min(cfqg->busy_queues_avg[rt], busy);
+	max_q = max(cfqg->busy_queues_avg[rt], busy);
+	cfqg->busy_queues_avg[rt] = (mult * max_q + min_q + round) /
+		cfq_hist_divisor;
+	return cfqg->busy_queues_avg[rt];
+}
+
+static inline unsigned
+cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+	struct cfq_rb_root *st = &cfqd->grp_service_tree;
+
+	return cfq_target_latency * cfqg->weight / st->total_weight;
+}
+
 static inline void
 cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies;
+	unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
+	if (cfqd->cfq_latency) {
+		/*
+		 * interested queues (we consider only the ones with the same
+		 * priority class in the cfq group)
+		 */
+		unsigned iq = cfq_group_get_avg_queues(cfqd, cfqq->cfqg,
+						cfq_class_rt(cfqq));
+		unsigned sync_slice = cfqd->cfq_slice[1];
+		unsigned expect_latency = sync_slice * iq;
+		unsigned group_slice = cfq_group_slice(cfqd, cfqq->cfqg);
+
+		if (expect_latency > group_slice) {
+			unsigned base_low_slice = 2 * cfqd->cfq_slice_idle;
+			/* scale low_slice according to IO priority
+			 * and sync vs async */
+			unsigned low_slice =
+				min(slice, base_low_slice * slice / sync_slice);
+			/* the adapted slice value is scaled to fit all iqs
+			 * into the target latency */
+			slice = max(slice * group_slice / expect_latency,
+				    low_slice);
+		}
+	}
+	cfqq->slice_start = jiffies;
+	cfqq->slice_end = jiffies + slice;
+	cfqq->allocated_slice = slice;
 	cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
 }
 
@@ -315,7 +595,7 @@ cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  * isn't valid until the first request from the dispatch is activated
  * and the slice time set.
  */
-static inline int cfq_slice_used(struct cfq_queue *cfqq)
+static inline bool cfq_slice_used(struct cfq_queue *cfqq)
 {
 	if (cfq_cfqq_slice_new(cfqq))
 		return 0;
@@ -331,9 +611,9 @@ static inline int cfq_slice_used(struct cfq_queue *cfqq)
  * behind the head is penalized and only allowed to a certain extent.
  */
 static struct request *
-cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
+cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, sector_t last)
 {
-	sector_t last, s1, s2, d1 = 0, d2 = 0;
+	sector_t s1, s2, d1 = 0, d2 = 0;
 	unsigned long back_max;
 #define CFQ_RQ1_WRAP	0x01 /* request 1 wraps */
 #define CFQ_RQ2_WRAP	0x02 /* request 2 wraps */
@@ -356,8 +636,6 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
 	s1 = blk_rq_pos(rq1);
 	s2 = blk_rq_pos(rq2);
 
-	last = cfqd->last_position;
-
 	/*
 	 * by definition, 1KiB is 2 sectors
 	 */
@@ -425,6 +703,10 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
  */
 static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
 {
+	/* Service tree is empty */
+	if (!root->count)
+		return NULL;
+
 	if (!root->left)
 		root->left = rb_first(&root->rb);
 
@@ -434,6 +716,17 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
 	return NULL;
 }
 
+static struct cfq_group *cfq_rb_first_group(struct cfq_rb_root *root)
+{
+	if (!root->left)
+		root->left = rb_first(&root->rb);
+
+	if (root->left)
+		return rb_entry_cfqg(root->left);
+
+	return NULL;
+}
+
 static void rb_erase_init(struct rb_node *n, struct rb_root *root)
 {
 	rb_erase(n, root);
@@ -445,6 +738,7 @@ static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root)
 	if (root->left == n)
 		root->left = NULL;
 	rb_erase_init(n, &root->rb);
+	--root->count;
 }
 
 /*
@@ -471,7 +765,7 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			next = rb_entry_rq(rbnext);
 	}
 
-	return cfq_choose_req(cfqd, next, prev);
+	return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
 }
 
 static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
@@ -480,51 +774,417 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
 	/*
 	 * just an approximation, should be ok.
 	 */
-	return (cfqd->busy_queues - 1) * (cfq_prio_slice(cfqd, 1, 0) -
+	return (cfqq->cfqg->nr_cfqq - 1) * (cfq_prio_slice(cfqd, 1, 0) -
 		       cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
 }
 
+static inline s64
+cfqg_key(struct cfq_rb_root *st, struct cfq_group *cfqg)
+{
+	return cfqg->vdisktime - st->min_vdisktime;
+}
+
+static void
+__cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
+{
+	struct rb_node **node = &st->rb.rb_node;
+	struct rb_node *parent = NULL;
+	struct cfq_group *__cfqg;
+	s64 key = cfqg_key(st, cfqg);
+	int left = 1;
+
+	while (*node != NULL) {
+		parent = *node;
+		__cfqg = rb_entry_cfqg(parent);
+
+		if (key < cfqg_key(st, __cfqg))
+			node = &parent->rb_left;
+		else {
+			node = &parent->rb_right;
+			left = 0;
+		}
+	}
+
+	if (left)
+		st->left = &cfqg->rb_node;
+
+	rb_link_node(&cfqg->rb_node, parent, node);
+	rb_insert_color(&cfqg->rb_node, &st->rb);
+}
+
+static void
+cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+	struct cfq_rb_root *st = &cfqd->grp_service_tree;
+	struct cfq_group *__cfqg;
+	struct rb_node *n;
+
+	cfqg->nr_cfqq++;
+	if (cfqg->on_st)
+		return;
+
+	/*
+	 * Currently put the group at the end. Later implement something
+	 * so that groups get lesser vtime based on their weights, so that
+	 * if group does not loose all if it was not continously backlogged.
+	 */
+	n = rb_last(&st->rb);
+	if (n) {
+		__cfqg = rb_entry_cfqg(n);
+		cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+	} else
+		cfqg->vdisktime = st->min_vdisktime;
+
+	__cfq_group_service_tree_add(st, cfqg);
+	cfqg->on_st = true;
+	st->total_weight += cfqg->weight;
+}
+
+static void
+cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+	struct cfq_rb_root *st = &cfqd->grp_service_tree;
+
+	if (st->active == &cfqg->rb_node)
+		st->active = NULL;
+
+	BUG_ON(cfqg->nr_cfqq < 1);
+	cfqg->nr_cfqq--;
+
+	/* If there are other cfq queues under this group, don't delete it */
+	if (cfqg->nr_cfqq)
+		return;
+
+	cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
+	cfqg->on_st = false;
+	st->total_weight -= cfqg->weight;
+	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);
+}
+
+static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
+{
+	unsigned int slice_used;
+
+	/*
+	 * Queue got expired before even a single request completed or
+	 * got expired immediately after first request completion.
+	 */
+	if (!cfqq->slice_start || cfqq->slice_start == jiffies) {
+		/*
+		 * Also charge the seek time incurred to the group, otherwise
+		 * if there are mutiple queues in the group, each can dispatch
+		 * a single request on seeky media and cause lots of seek time
+		 * and group will never know it.
+		 */
+		slice_used = max_t(unsigned, (jiffies - cfqq->dispatch_start),
+					1);
+	} else {
+		slice_used = jiffies - cfqq->slice_start;
+		if (slice_used > cfqq->allocated_slice)
+			slice_used = cfqq->allocated_slice;
+	}
+
+	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u sect=%lu", slice_used,
+				cfqq->nr_sectors);
+	return slice_used;
+}
+
+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;
+	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);
+
+	if (!cfq_cfqq_sync(cfqq) && !nr_sync)
+		charge_sl = 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);
+	__cfq_group_service_tree_add(st, cfqg);
+
+	/* This group is being expired. Save the context */
+	if (time_after(cfqd->workload_expires, jiffies)) {
+		cfqg->saved_workload_slice = cfqd->workload_expires
+						- jiffies;
+		cfqg->saved_workload = cfqd->serving_type;
+		cfqg->saved_serving_prio = cfqd->serving_prio;
+	} else
+		cfqg->saved_workload_slice = 0;
+
+	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);
+}
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg)
+{
+	if (blkg)
+		return container_of(blkg, struct cfq_group, blkg);
+	return NULL;
+}
+
+void
+cfq_update_blkio_group_weight(struct blkio_group *blkg, unsigned int weight)
+{
+	cfqg_of_blkg(blkg)->weight = weight;
+}
+
+static struct cfq_group *
+cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
+{
+	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
+	struct cfq_group *cfqg = NULL;
+	void *key = cfqd;
+	int i, j;
+	struct cfq_rb_root *st;
+	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
+	unsigned int major, minor;
+
+	/* Do we need to take this reference */
+	if (!blkiocg_css_tryget(blkcg))
+		return NULL;;
+
+	cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
+	if (cfqg || !create)
+		goto done;
+
+	cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, cfqd->queue->node);
+	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);
+
+	/*
+	 * Take the initial reference that will be released on destroy
+	 * This can be thought of a joint reference by cgroup and
+	 * elevator which will be dropped by either elevator exit
+	 * or cgroup deletion path depending on who is exiting first.
+	 */
+	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,
+					MKDEV(major, minor));
+
+	/* Add group on cfqd list */
+	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
+
+done:
+	blkiocg_css_put(blkcg);
+	return cfqg;
+}
+
+/*
+ * Search for the cfq group current task belongs to. If create = 1, then also
+ * create the cfq group if it does not exist. request_queue lock must be held.
+ */
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+{
+	struct cgroup *cgroup;
+	struct cfq_group *cfqg = NULL;
+
+	rcu_read_lock();
+	cgroup = task_cgroup(current, blkio_subsys_id);
+	cfqg = cfq_find_alloc_cfqg(cfqd, cgroup, create);
+	if (!cfqg && create)
+		cfqg = &cfqd->root_group;
+	rcu_read_unlock();
+	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 */
+	if (!cfq_cfqq_sync(cfqq))
+		cfqg = &cfqq->cfqd->root_group;
+
+	cfqq->cfqg = cfqg;
+	/* cfqq reference on cfqg */
+	atomic_inc(&cfqq->cfqg->ref);
+}
+
+static void cfq_put_cfqg(struct cfq_group *cfqg)
+{
+	struct cfq_rb_root *st;
+	int i, j;
+
+	BUG_ON(atomic_read(&cfqg->ref) <= 0);
+	if (!atomic_dec_and_test(&cfqg->ref))
+		return;
+	for_each_cfqg_st(cfqg, i, j, st)
+		BUG_ON(!RB_EMPTY_ROOT(&st->rb) || st->active != NULL);
+	kfree(cfqg);
+}
+
+static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+	/* Something wrong if we are trying to remove same group twice */
+	BUG_ON(hlist_unhashed(&cfqg->cfqd_node));
+
+	hlist_del_init(&cfqg->cfqd_node);
+
+	/*
+	 * Put the reference taken at the time of creation so that when all
+	 * queues are gone, group can be destroyed.
+	 */
+	cfq_put_cfqg(cfqg);
+}
+
+static void cfq_release_cfq_groups(struct cfq_data *cfqd)
+{
+	struct hlist_node *pos, *n;
+	struct cfq_group *cfqg;
+
+	hlist_for_each_entry_safe(cfqg, pos, n, &cfqd->cfqg_list, cfqd_node) {
+		/*
+		 * If cgroup removal path got to blk_group first and removed
+		 * it from cgroup list, then it will take care of destroying
+		 * cfqg also.
+		 */
+		if (!blkiocg_del_blkio_group(&cfqg->blkg))
+			cfq_destroy_cfqg(cfqd, cfqg);
+	}
+}
+
 /*
- * The cfqd->service_tree holds all pending cfq_queue's that have
+ * Blk cgroup controller notification saying that blkio_group object is being
+ * delinked as associated cgroup object is going away. That also means that
+ * no new IO will come in this group. So get rid of this group as soon as
+ * any pending IO in the group is finished.
+ *
+ * This function is called under rcu_read_lock(). key is the rcu protected
+ * pointer. That means "key" is a valid cfq_data pointer as long as we are rcu
+ * read lock.
+ *
+ * "key" was fetched from blkio_group under blkio_cgroup->lock. That means
+ * it should not be NULL as even if elevator was exiting, cgroup deltion
+ * path got to it first.
+ */
+void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
+{
+	unsigned long  flags;
+	struct cfq_data *cfqd = key;
+
+	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+	cfq_destroy_cfqg(cfqd, cfqg_of_blkg(blkg));
+	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+}
+
+#else /* GROUP_IOSCHED */
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+{
+	return &cfqd->root_group;
+}
+static inline void
+cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) {
+	cfqq->cfqg = cfqg;
+}
+
+static void cfq_release_cfq_groups(struct cfq_data *cfqd) {}
+static inline void cfq_put_cfqg(struct cfq_group *cfqg) {}
+
+#endif /* GROUP_IOSCHED */
+
+/*
+ * The cfqd->service_trees holds all pending cfq_queue's that have
  * requests waiting to be processed. It is sorted in the order that
  * we will service the queues.
  */
 static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-				 int add_front)
+				 bool add_front)
 {
 	struct rb_node **p, *parent;
 	struct cfq_queue *__cfqq;
 	unsigned long rb_key;
+	struct cfq_rb_root *service_tree;
 	int left;
+	int new_cfqq = 1;
+	int group_changed = 0;
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	if (!cfqd->cfq_group_isolation
+	    && cfqq_type(cfqq) == SYNC_NOIDLE_WORKLOAD
+	    && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) {
+		/* Move this cfq to root group */
+		cfq_log_cfqq(cfqd, cfqq, "moving to root group");
+		if (!RB_EMPTY_NODE(&cfqq->rb_node))
+			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+		cfqq->orig_cfqg = cfqq->cfqg;
+		cfqq->cfqg = &cfqd->root_group;
+		atomic_inc(&cfqd->root_group.ref);
+		group_changed = 1;
+	} else if (!cfqd->cfq_group_isolation
+		   && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
+		/* cfqq is sequential now needs to go to its original group */
+		BUG_ON(cfqq->cfqg != &cfqd->root_group);
+		if (!RB_EMPTY_NODE(&cfqq->rb_node))
+			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+		cfq_put_cfqg(cfqq->cfqg);
+		cfqq->cfqg = cfqq->orig_cfqg;
+		cfqq->orig_cfqg = NULL;
+		group_changed = 1;
+		cfq_log_cfqq(cfqd, cfqq, "moved to origin group");
+	}
+#endif
 
+	service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
+						cfqq_type(cfqq));
 	if (cfq_class_idle(cfqq)) {
 		rb_key = CFQ_IDLE_DELAY;
-		parent = rb_last(&cfqd->service_tree.rb);
+		parent = rb_last(&service_tree->rb);
 		if (parent && parent != &cfqq->rb_node) {
 			__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
 			rb_key += __cfqq->rb_key;
 		} else
 			rb_key += jiffies;
 	} else if (!add_front) {
+		/*
+		 * Get our rb key offset. Subtract any residual slice
+		 * value carried from last service. A negative resid
+		 * count indicates slice overrun, and this should position
+		 * the next service time further away in the tree.
+		 */
 		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
-		rb_key += cfqq->slice_resid;
+		rb_key -= cfqq->slice_resid;
 		cfqq->slice_resid = 0;
-	} else
-		rb_key = 0;
+	} else {
+		rb_key = -HZ;
+		__cfqq = cfq_rb_first(service_tree);
+		rb_key += __cfqq ? __cfqq->rb_key : jiffies;
+	}
 
 	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
+		new_cfqq = 0;
 		/*
 		 * same position, nothing more to do
 		 */
-		if (rb_key == cfqq->rb_key)
+		if (rb_key == cfqq->rb_key &&
+		    cfqq->service_tree == service_tree)
 			return;
 
-		cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
+		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
+		cfqq->service_tree = NULL;
 	}
 
 	left = 1;
 	parent = NULL;
-	p = &cfqd->service_tree.rb.rb_node;
+	cfqq->service_tree = service_tree;
+	p = &service_tree->rb.rb_node;
 	while (*p) {
 		struct rb_node **n;
 
@@ -532,35 +1192,28 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
 
 		/*
-		 * sort RT queues first, we always want to give
-		 * preference to them. IDLE queues goes to the back.
-		 * after that, sort on the next service time.
+		 * sort by key, that represents service time.
 		 */
-		if (cfq_class_rt(cfqq) > cfq_class_rt(__cfqq))
+		if (time_before(rb_key, __cfqq->rb_key))
 			n = &(*p)->rb_left;
-		else if (cfq_class_rt(cfqq) < cfq_class_rt(__cfqq))
-			n = &(*p)->rb_right;
-		else if (cfq_class_idle(cfqq) < cfq_class_idle(__cfqq))
-			n = &(*p)->rb_left;
-		else if (cfq_class_idle(cfqq) > cfq_class_idle(__cfqq))
-			n = &(*p)->rb_right;
-		else if (rb_key < __cfqq->rb_key)
-			n = &(*p)->rb_left;
-		else
+		else {
 			n = &(*p)->rb_right;
-
-		if (n == &(*p)->rb_right)
 			left = 0;
+		}
 
 		p = n;
 	}
 
 	if (left)
-		cfqd->service_tree.left = &cfqq->rb_node;
+		service_tree->left = &cfqq->rb_node;
 
 	cfqq->rb_key = rb_key;
 	rb_link_node(&cfqq->rb_node, parent, p);
-	rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb);
+	rb_insert_color(&cfqq->rb_node, &service_tree->rb);
+	service_tree->count++;
+	if ((add_front || !new_cfqq) && !group_changed)
+		return;
+	cfq_group_service_tree_add(cfqd, cfqq->cfqg);
 }
 
 static struct cfq_queue *
@@ -648,8 +1301,6 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	cfq_mark_cfqq_on_rr(cfqq);
 	cfqd->busy_queues++;
-	if (cfq_class_rt(cfqq))
-		cfqd->busy_rt_queues++;
 
 	cfq_resort_rr_list(cfqd, cfqq);
 }
@@ -664,17 +1315,18 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	BUG_ON(!cfq_cfqq_on_rr(cfqq));
 	cfq_clear_cfqq_on_rr(cfqq);
 
-	if (!RB_EMPTY_NODE(&cfqq->rb_node))
-		cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
+	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
+		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
+		cfqq->service_tree = NULL;
+	}
 	if (cfqq->p_root) {
 		rb_erase(&cfqq->p_node, cfqq->p_root);
 		cfqq->p_root = NULL;
 	}
 
+	cfq_group_service_tree_del(cfqd, cfqq->cfqg);
 	BUG_ON(!cfqd->busy_queues);
 	cfqd->busy_queues--;
-	if (cfq_class_rt(cfqq))
-		cfqd->busy_rt_queues--;
 }
 
 /*
@@ -683,7 +1335,6 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static void cfq_del_rq_rb(struct request *rq)
 {
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
-	struct cfq_data *cfqd = cfqq->cfqd;
 	const int sync = rq_is_sync(rq);
 
 	BUG_ON(!cfqq->queued[sync]);
@@ -691,8 +1342,17 @@ static void cfq_del_rq_rb(struct request *rq)
 
 	elv_rb_del(&cfqq->sort_list, rq);
 
-	if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list))
-		cfq_del_cfqq_rr(cfqd, cfqq);
+	if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) {
+		/*
+		 * Queue will be deleted from service tree when we actually
+		 * expire it later. Right now just remove it from prio tree
+		 * as it is empty.
+		 */
+		if (cfqq->p_root) {
+			rb_erase(&cfqq->p_node, cfqq->p_root);
+			cfqq->p_root = NULL;
+		}
+	}
 }
 
 static void cfq_add_rq_rb(struct request *rq)
@@ -717,7 +1377,7 @@ static void cfq_add_rq_rb(struct request *rq)
 	 * check if this request is a better next-serve candidate
 	 */
 	prev = cfqq->next_rq;
-	cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq);
+	cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq, cfqd->last_position);
 
 	/*
 	 * adjust priority tree position, if ->next_rq changes
@@ -760,9 +1420,9 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 
-	cfqd->rq_in_driver++;
+	cfqd->rq_in_driver[rq_is_sync(rq)]++;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
-						cfqd->rq_in_driver);
+						rq_in_driver(cfqd));
 
 	cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
 }
@@ -770,11 +1430,12 @@ 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);
-	cfqd->rq_in_driver--;
+	WARN_ON(!cfqd->rq_in_driver[sync]);
+	cfqd->rq_in_driver[sync]--;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
-						cfqd->rq_in_driver);
+						rq_in_driver(cfqd));
 }
 
 static void cfq_remove_request(struct request *rq)
@@ -823,13 +1484,18 @@ static void
 cfq_merged_requests(struct request_queue *q, struct request *rq,
 		    struct request *next)
 {
+	struct cfq_queue *cfqq = RQ_CFQQ(rq);
 	/*
 	 * reposition in fifo if next is older than rq
 	 */
 	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
-	    time_before(next->start_time, rq->start_time))
+	    time_before(rq_fifo_time(next), rq_fifo_time(rq))) {
 		list_move(&rq->queuelist, &next->queuelist);
+		rq_set_fifo_time(rq, rq_fifo_time(next));
+	}
 
+	if (cfqq->next_rq == next)
+		cfqq->next_rq = rq;
 	cfq_remove_request(next);
 }
 
@@ -844,7 +1510,7 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	 * Disallow merge of a sync bio into an async request.
 	 */
 	if (cfq_bio_sync(bio) && !rq_is_sync(rq))
-		return 0;
+		return false;
 
 	/*
 	 * Lookup the cfqq that this bio will be queued with. Allow
@@ -852,13 +1518,10 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	 */
 	cic = cfq_cic_lookup(cfqd, current->io_context);
 	if (!cic)
-		return 0;
+		return false;
 
 	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
-	if (cfqq == RQ_CFQQ(rq))
-		return 1;
-
-	return 0;
+	return cfqq == RQ_CFQQ(rq);
 }
 
 static void __cfq_set_active_queue(struct cfq_data *cfqd,
@@ -866,8 +1529,12 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 {
 	if (cfqq) {
 		cfq_log_cfqq(cfqd, cfqq, "set_active");
+		cfqq->slice_start = 0;
+		cfqq->dispatch_start = jiffies;
+		cfqq->allocated_slice = 0;
 		cfqq->slice_end = 0;
 		cfqq->slice_dispatch = 0;
+		cfqq->nr_sectors = 0;
 
 		cfq_clear_cfqq_wait_request(cfqq);
 		cfq_clear_cfqq_must_dispatch(cfqq);
@@ -886,7 +1553,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
  */
 static void
 __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-		    int timed_out)
+		    bool timed_out)
 {
 	cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
 
@@ -894,6 +1561,16 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		del_timer(&cfqd->idle_slice_timer);
 
 	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
@@ -903,18 +1580,26 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
 	}
 
+	cfq_group_served(cfqd, cfqq->cfqg, cfqq);
+
+	if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list))
+		cfq_del_cfqq_rr(cfqd, cfqq);
+
 	cfq_resort_rr_list(cfqd, cfqq);
 
 	if (cfqq == cfqd->active_queue)
 		cfqd->active_queue = NULL;
 
+	if (&cfqq->cfqg->rb_node == cfqd->grp_service_tree.active)
+		cfqd->grp_service_tree.active = NULL;
+
 	if (cfqd->active_cic) {
 		put_io_context(cfqd->active_cic->ioc);
 		cfqd->active_cic = NULL;
 	}
 }
 
-static inline void cfq_slice_expired(struct cfq_data *cfqd, int timed_out)
+static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 
@@ -928,10 +1613,39 @@ static inline void cfq_slice_expired(struct cfq_data *cfqd, int timed_out)
  */
 static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
 {
-	if (RB_EMPTY_ROOT(&cfqd->service_tree.rb))
+	struct cfq_rb_root *service_tree =
+		service_tree_for(cfqd->serving_group, cfqd->serving_prio,
+					cfqd->serving_type);
+
+	if (!cfqd->rq_queued)
+		return NULL;
+
+	/* There is nothing to dispatch */
+	if (!service_tree)
+		return NULL;
+	if (RB_EMPTY_ROOT(&service_tree->rb))
+		return NULL;
+	return cfq_rb_first(service_tree);
+}
+
+static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
+{
+	struct cfq_group *cfqg;
+	struct cfq_queue *cfqq;
+	int i, j;
+	struct cfq_rb_root *st;
+
+	if (!cfqd->rq_queued)
 		return NULL;
 
-	return cfq_rb_first(&cfqd->service_tree);
+	cfqg = cfq_get_next_cfqg(cfqd);
+	if (!cfqg)
+		return NULL;
+
+	for_each_cfqg_st(cfqg, i, j, st)
+		if ((cfqq = cfq_rb_first(st)) != NULL)
+			return cfqq;
+	return NULL;
 }
 
 /*
@@ -940,11 +1654,8 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
 static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
 					      struct cfq_queue *cfqq)
 {
-	if (!cfqq) {
+	if (!cfqq)
 		cfqq = cfq_get_next_queue(cfqd);
-		if (cfqq)
-			cfq_clear_cfqq_coop(cfqq);
-	}
 
 	__cfq_set_active_queue(cfqd, cfqq);
 	return cfqq;
@@ -959,16 +1670,17 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 		return cfqd->last_position - blk_rq_pos(rq);
 }
 
-#define CIC_SEEK_THR	8 * 1024
-#define CIC_SEEKY(cic)	((cic)->seek_mean > CIC_SEEK_THR)
-
-static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq)
+static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+			       struct request *rq, bool for_preempt)
 {
-	struct cfq_io_context *cic = cfqd->active_cic;
-	sector_t sdist = cic->seek_mean;
+	sector_t sdist = cfqq->seek_mean;
+
+	if (!sample_valid(cfqq->seek_samples))
+		sdist = CFQQ_SEEK_THR;
 
-	if (!sample_valid(cic->seek_samples))
-		sdist = CIC_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;
 }
@@ -997,7 +1709,7 @@ 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, __cfqq->next_rq))
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
 		return __cfqq;
 
 	if (blk_rq_pos(__cfqq->next_rq) < sector)
@@ -1008,7 +1720,7 @@ 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, __cfqq->next_rq))
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
 		return __cfqq;
 
 	return NULL;
@@ -1025,16 +1737,19 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
  * assumption.
  */
 static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
-					      struct cfq_queue *cur_cfqq,
-					      int probe)
+					      struct cfq_queue *cur_cfqq)
 {
 	struct cfq_queue *cfqq;
 
+	if (!cfq_cfqq_sync(cur_cfqq))
+		return NULL;
+	if (CFQQ_SEEKY(cur_cfqq))
+		return NULL;
+
 	/*
-	 * A valid cfq_io_context is necessary to compare requests against
-	 * the seek_mean of the current cfqq.
+	 * Don't search priority tree if it's the only queue in the group.
 	 */
-	if (!cfqd->active_cic)
+	if (cur_cfqq->cfqg->nr_cfqq == 1)
 		return NULL;
 
 	/*
@@ -1046,14 +1761,55 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 	if (!cfqq)
 		return NULL;
 
-	if (cfq_cfqq_coop(cfqq))
+	/* If new queue belongs to different cfq_group, don't choose it */
+	if (cur_cfqq->cfqg != cfqq->cfqg)
+		return NULL;
+
+	/*
+	 * It only makes sense to merge sync queues.
+	 */
+	if (!cfq_cfqq_sync(cfqq))
+		return NULL;
+	if (CFQQ_SEEKY(cfqq))
+		return NULL;
+
+	/*
+	 * Do not merge queues of different priority classes
+	 */
+	if (cfq_class_rt(cfqq) != cfq_class_rt(cur_cfqq))
 		return NULL;
 
-	if (!probe)
-		cfq_mark_cfqq_coop(cfqq);
 	return cfqq;
 }
 
+/*
+ * Determine whether we should enforce idle window for this queue.
+ */
+
+static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	enum wl_prio_t prio = cfqq_prio(cfqq);
+	struct cfq_rb_root *service_tree = cfqq->service_tree;
+
+	BUG_ON(!service_tree);
+	BUG_ON(!service_tree->count);
+
+	/* We never do for idle class queues. */
+	if (prio == IDLE_WORKLOAD)
+		return false;
+
+	/* We do for queues that were marked with idle window flag. */
+	if (cfq_cfqq_idle_window(cfqq) &&
+	   !(blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag))
+		return true;
+
+	/*
+	 * Otherwise, we do only if they are the last ones
+	 * in their service tree.
+	 */
+	return service_tree->count == 1 && cfq_cfqq_sync(cfqq);
+}
+
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
@@ -1074,13 +1830,13 @@ 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_cfqq_idle_window(cfqq))
+	if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq))
 		return;
 
 	/*
-	 * still requests with the driver, don't idle
+	 * still active requests from this queue, don't idle
 	 */
-	if (cfqd->rq_in_driver)
+	if (cfqq->dispatched)
 		return;
 
 	/*
@@ -1090,16 +1846,18 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	if (!cic || !atomic_read(&cic->ioc->nr_tasks))
 		return;
 
-	cfq_mark_cfqq_wait_request(cfqq);
-
 	/*
-	 * we don't want to idle for seeks, but we do want to allow
-	 * fair distribution of slice time for a process doing back-to-back
-	 * seeks. so allow a little bit of time for him to submit a new rq
+	 * If our average think time is larger than the remaining time
+	 * slice, then don't idle. This avoids overrunning the allotted
+	 * time slice.
 	 */
+	if (sample_valid(cic->ttime_samples) &&
+	    (cfqq->slice_end - jiffies < cic->ttime_mean))
+		return;
+
+	cfq_mark_cfqq_wait_request(cfqq);
+
 	sl = cfqd->cfq_slice_idle;
-	if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic))
-		sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT));
 
 	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
 	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
@@ -1115,12 +1873,14 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
 
 	cfq_log_cfqq(cfqd, cfqq, "dispatch_insert");
 
+	cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
 	cfq_remove_request(rq);
 	cfqq->dispatched++;
 	elv_dispatch_sort(q, rq);
 
 	if (cfq_cfqq_sync(cfqq))
 		cfqd->sync_flight++;
+	cfqq->nr_sectors += blk_rq_sectors(rq);
 }
 
 /*
@@ -1128,9 +1888,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
  */
 static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 {
-	struct cfq_data *cfqd = cfqq->cfqd;
-	struct request *rq;
-	int fifo;
+	struct request *rq = NULL;
 
 	if (cfq_cfqq_fifo_expire(cfqq))
 		return NULL;
@@ -1140,13 +1898,11 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 	if (list_empty(&cfqq->fifo))
 		return NULL;
 
-	fifo = cfq_cfqq_sync(cfqq);
 	rq = rq_entry_fifo(cfqq->fifo.next);
-
-	if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo]))
+	if (time_before(jiffies, rq_fifo_time(rq)))
 		rq = NULL;
 
-	cfq_log_cfqq(cfqd, cfqq, "fifo=%p", rq);
+	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
 	return rq;
 }
 
@@ -1161,6 +1917,186 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 }
 
 /*
+ * Must be called with the queue_lock held.
+ */
+static int cfqq_process_refs(struct cfq_queue *cfqq)
+{
+	int process_refs, io_refs;
+
+	io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE];
+	process_refs = atomic_read(&cfqq->ref) - io_refs;
+	BUG_ON(process_refs < 0);
+	return process_refs;
+}
+
+static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
+{
+	int process_refs, new_process_refs;
+	struct cfq_queue *__cfqq;
+
+	/* Avoid a circular list and skip interim queue merges */
+	while ((__cfqq = new_cfqq->new_cfqq)) {
+		if (__cfqq == cfqq)
+			return;
+		new_cfqq = __cfqq;
+	}
+
+	process_refs = cfqq_process_refs(cfqq);
+	/*
+	 * If the process for the cfqq has gone away, there is no
+	 * sense in merging the queues.
+	 */
+	if (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);
+	} else {
+		new_cfqq->new_cfqq = cfqq;
+		atomic_add(new_process_refs, &cfqq->ref);
+	}
+}
+
+static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
+				struct cfq_group *cfqg, enum wl_prio_t prio)
+{
+	struct cfq_queue *queue;
+	int i;
+	bool key_valid = false;
+	unsigned long lowest_key = 0;
+	enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;
+
+	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
+		/* select the one with lowest rb_key */
+		queue = cfq_rb_first(service_tree_for(cfqg, prio, i));
+		if (queue &&
+		    (!key_valid || time_before(queue->rb_key, lowest_key))) {
+			lowest_key = queue->rb_key;
+			cur_best = i;
+			key_valid = true;
+		}
+	}
+
+	return cur_best;
+}
+
+static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+	unsigned slice;
+	unsigned count;
+	struct cfq_rb_root *st;
+	unsigned group_slice;
+
+	if (!cfqg) {
+		cfqd->serving_prio = IDLE_WORKLOAD;
+		cfqd->workload_expires = jiffies + 1;
+		return;
+	}
+
+	/* Choose next priority. RT > BE > IDLE */
+	if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
+		cfqd->serving_prio = RT_WORKLOAD;
+	else if (cfq_group_busy_queues_wl(BE_WORKLOAD, cfqd, cfqg))
+		cfqd->serving_prio = BE_WORKLOAD;
+	else {
+		cfqd->serving_prio = IDLE_WORKLOAD;
+		cfqd->workload_expires = jiffies + 1;
+		return;
+	}
+
+	/*
+	 * For RT and BE, we have to choose also the type
+	 * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
+	 * expiration time
+	 */
+	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
+	count = st->count;
+
+	/*
+	 * check workload expiration, and that we still have other queues ready
+	 */
+	if (count && !time_after(jiffies, cfqd->workload_expires))
+		return;
+
+	/* otherwise select new workload type */
+	cfqd->serving_type =
+		cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
+	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
+	count = st->count;
+
+	/*
+	 * the workload slice is computed as a fraction of target latency
+	 * proportional to the number of queues in that workload, over
+	 * all the queues in the same priority class
+	 */
+	group_slice = cfq_group_slice(cfqd, cfqg);
+
+	slice = group_slice * count /
+		max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_prio],
+		      cfq_group_busy_queues_wl(cfqd->serving_prio, cfqd, cfqg));
+
+	if (cfqd->serving_type == ASYNC_WORKLOAD) {
+		unsigned int tmp;
+
+		/*
+		 * Async queues are currently system wide. Just taking
+		 * proportion of queues with-in same group will lead to higher
+		 * async ratio system wide as generally root group is going
+		 * to have higher weight. A more accurate thing would be to
+		 * calculate system wide asnc/sync ratio.
+		 */
+		tmp = cfq_target_latency * cfqg_busy_async_queues(cfqd, cfqg);
+		tmp = tmp/cfqd->busy_queues;
+		slice = min_t(unsigned, slice, tmp);
+
+		/* async workload slice is scaled down according to
+		 * the sync/async slice ratio. */
+		slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
+	} else
+		/* sync workload slice is at least 2 * cfq_slice_idle */
+		slice = max(slice, 2 * cfqd->cfq_slice_idle);
+
+	slice = max_t(unsigned, slice, CFQ_MIN_TT);
+	cfqd->workload_expires = jiffies + slice;
+	cfqd->noidle_tree_requires_idle = false;
+}
+
+static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
+{
+	struct cfq_rb_root *st = &cfqd->grp_service_tree;
+	struct cfq_group *cfqg;
+
+	if (RB_EMPTY_ROOT(&st->rb))
+		return NULL;
+	cfqg = cfq_rb_first_group(st);
+	st->active = &cfqg->rb_node;
+	update_min_vdisktime(st);
+	return cfqg;
+}
+
+static void cfq_choose_cfqg(struct cfq_data *cfqd)
+{
+	struct cfq_group *cfqg = cfq_get_next_cfqg(cfqd);
+
+	cfqd->serving_group = cfqg;
+
+	/* Restore the workload type data */
+	if (cfqg->saved_workload_slice) {
+		cfqd->workload_expires = jiffies + cfqg->saved_workload_slice;
+		cfqd->serving_type = cfqg->saved_workload;
+		cfqd->serving_prio = cfqg->saved_serving_prio;
+	} else
+		cfqd->workload_expires = jiffies - 1;
+
+	choose_service_tree(cfqd, cfqg);
+}
+
+/*
  * Select a queue for service. If we have a current active queue,
  * check whether to continue servicing it, or retrieve and set a new one.
  */
@@ -1172,24 +2108,34 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	if (!cfqq)
 		goto new_queue;
 
+	if (!cfqd->rq_queued)
+		return NULL;
+
 	/*
-	 * The active queue has run out of time, expire it and select new.
+	 * We were waiting for group to get backlogged. Expire the queue
 	 */
-	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
+	if (cfq_cfqq_wait_busy(cfqq) && !RB_EMPTY_ROOT(&cfqq->sort_list))
 		goto expire;
 
 	/*
-	 * If we have a RT cfqq waiting, then we pre-empt the current non-rt
-	 * cfqq.
+	 * The active queue has run out of time, expire it and select new.
 	 */
-	if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues) {
+	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) {
 		/*
-		 * We simulate this as cfqq timed out so that it gets to bank
-		 * the remaining of its time slice.
+		 * If slice had not expired at the completion of last request
+		 * we might not have turned on wait_busy flag. Don't expire
+		 * the queue yet. Allow the group to get backlogged.
+		 *
+		 * The very fact that we have used the slice, that means we
+		 * have been idling all along on this queue and it should be
+		 * ok to wait for this request to complete.
 		 */
-		cfq_log_cfqq(cfqd, cfqq, "preempt");
-		cfq_slice_expired(cfqd, 1);
-		goto new_queue;
+		if (cfqq->cfqg->nr_cfqq == 1 && RB_EMPTY_ROOT(&cfqq->sort_list)
+		    && cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
+			cfqq = NULL;
+			goto keep_queue;
+		} else
+			goto expire;
 	}
 
 	/*
@@ -1203,11 +2149,14 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	 * If another queue has a request waiting within our mean seek
 	 * distance, let it run.  The expire code will check for close
 	 * cooperators and put the close queue at the front of the service
-	 * tree.
+	 * tree.  If possible, merge the expiring queue with the new cfqq.
 	 */
-	new_cfqq = cfq_close_cooperator(cfqd, cfqq, 0);
-	if (new_cfqq)
+	new_cfqq = cfq_close_cooperator(cfqd, cfqq);
+	if (new_cfqq) {
+		if (!cfqq->new_cfqq)
+			cfq_setup_merge(cfqq, new_cfqq);
 		goto expire;
+	}
 
 	/*
 	 * No requests pending. If the active queue still has requests in
@@ -1215,7 +2164,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	 * conditions to happen (or time out) before selecting a new queue.
 	 */
 	if (timer_pending(&cfqd->idle_slice_timer) ||
-	    (cfqq->dispatched && cfq_cfqq_idle_window(cfqq))) {
+	    (cfqq->dispatched && cfq_should_idle(cfqd, cfqq))) {
 		cfqq = NULL;
 		goto keep_queue;
 	}
@@ -1223,6 +2172,13 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 expire:
 	cfq_slice_expired(cfqd, 0);
 new_queue:
+	/*
+	 * Current queue expired. Check if we have to switch to a new
+	 * service tree
+	 */
+	if (!new_cfqq)
+		cfq_choose_cfqg(cfqd);
+
 	cfqq = cfq_set_active_queue(cfqd, new_cfqq);
 keep_queue:
 	return cfqq;
@@ -1238,6 +2194,9 @@ static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq)
 	}
 
 	BUG_ON(!list_empty(&cfqq->fifo));
+
+	/* By default cfqq is not expired if it is empty. Do it explicitly */
+	__cfq_slice_expired(cfqq->cfqd, cfqq, 0);
 	return dispatched;
 }
 
@@ -1250,27 +2209,93 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 	struct cfq_queue *cfqq;
 	int dispatched = 0;
 
-	while ((cfqq = cfq_rb_first(&cfqd->service_tree)) != NULL)
+	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL)
 		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 bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	unsigned int max_dispatch;
+
+	/*
+	 * Drain async requests before we start sync IO
+	 */
+	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_driver[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))
+		return false;
+
+	max_dispatch = cfqd->cfq_quantum;
+	if (cfq_class_idle(cfqq))
+		max_dispatch = 1;
+
+	/*
+	 * Does this cfqq already have too much IO in flight?
+	 */
+	if (cfqq->dispatched >= max_dispatch) {
+		/*
+		 * idle queue must always only have a single IO in flight
+		 */
+		if (cfq_class_idle(cfqq))
+			return false;
+
+		/*
+		 * We have other queues, don't allow more IO from this one
+		 */
+		if (cfqd->busy_queues > 1)
+			return false;
+
+		/*
+		 * Sole queue user, no limit
+		 */
+		max_dispatch = -1;
+	}
+
+	/*
+	 * Async queues must wait a bit before being allowed dispatch.
+	 * We also ramp up the dispatch depth gradually for async IO,
+	 * based on the last sync IO we serviced
+	 */
+	if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
+		unsigned long last_sync = jiffies - cfqd->last_delayed_sync;
+		unsigned int depth;
+
+		depth = last_sync / cfqd->cfq_slice[1];
+		if (!depth && !cfqq->dispatched)
+			depth = 1;
+		if (depth < max_dispatch)
+			max_dispatch = depth;
+	}
+
+	/*
+	 * If we're below the current max, allow a dispatch
+	 */
+	return cfqq->dispatched < max_dispatch;
+}
+
 /*
  * Dispatch a request from cfqq, moving them to the request queue
  * dispatch list.
  */
-static void cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+static bool cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	struct request *rq;
 
 	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
 
+	if (!cfq_may_dispatch(cfqd, cfqq))
+		return false;
+
 	/*
 	 * follow expired path, else get first next available
 	 */
@@ -1289,6 +2314,8 @@ static void cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		atomic_long_inc(&cic->ioc->refcount);
 		cfqd->active_cic = cic;
 	}
+
+	return true;
 }
 
 /*
@@ -1299,7 +2326,6 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_queue *cfqq;
-	unsigned int max_dispatch;
 
 	if (!cfqd->busy_queues)
 		return 0;
@@ -1312,42 +2338,11 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 		return 0;
 
 	/*
-	 * If this is an async queue and we have sync IO in flight, let it wait
+	 * Dispatch a request from this cfqq, if it is allowed
 	 */
-	if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
+	if (!cfq_dispatch_request(cfqd, cfqq))
 		return 0;
 
-	max_dispatch = cfqd->cfq_quantum;
-	if (cfq_class_idle(cfqq))
-		max_dispatch = 1;
-
-	/*
-	 * Does this cfqq already have too much IO in flight?
-	 */
-	if (cfqq->dispatched >= max_dispatch) {
-		/*
-		 * idle queue must always only have a single IO in flight
-		 */
-		if (cfq_class_idle(cfqq))
-			return 0;
-
-		/*
-		 * We have other queues, don't allow more IO from this one
-		 */
-		if (cfqd->busy_queues > 1)
-			return 0;
-
-		/*
-		 * we are the only queue, allow up to 4 times of 'quantum'
-		 */
-		if (cfqq->dispatched >= 4 * max_dispatch)
-			return 0;
-	}
-
-	/*
-	 * Dispatch a request from this cfqq
-	 */
-	cfq_dispatch_request(cfqd, cfqq);
 	cfqq->slice_dispatch++;
 	cfq_clear_cfqq_must_dispatch(cfqq);
 
@@ -1362,7 +2357,7 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 		cfq_slice_expired(cfqd, 0);
 	}
 
-	cfq_log(cfqd, "dispatched a request");
+	cfq_log_cfqq(cfqd, cfqq, "dispatched a request");
 	return 1;
 }
 
@@ -1370,11 +2365,13 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
  * task holds one reference to the queue, dropped when task exits. each rq
  * in-flight on this queue also holds a reference, dropped when rq is freed.
  *
+ * Each cfq queue took a reference on the parent group. Drop it now.
  * queue lock must be held here.
  */
 static void cfq_put_queue(struct cfq_queue *cfqq)
 {
 	struct cfq_data *cfqd = cfqq->cfqd;
+	struct cfq_group *cfqg, *orig_cfqg;
 
 	BUG_ON(atomic_read(&cfqq->ref) <= 0);
 
@@ -1384,14 +2381,19 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 	cfq_log_cfqq(cfqd, cfqq, "put_queue");
 	BUG_ON(rb_first(&cfqq->sort_list));
 	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
-	BUG_ON(cfq_cfqq_on_rr(cfqq));
+	cfqg = cfqq->cfqg;
+	orig_cfqg = cfqq->orig_cfqg;
 
 	if (unlikely(cfqd->active_queue == cfqq)) {
 		__cfq_slice_expired(cfqd, cfqq, 0);
 		cfq_schedule_dispatch(cfqd);
 	}
 
+	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	kmem_cache_free(cfq_pool, cfqq);
+	cfq_put_cfqg(cfqg);
+	if (orig_cfqg)
+		cfq_put_cfqg(orig_cfqg);
 }
 
 /*
@@ -1427,7 +2429,7 @@ static void cfq_cic_free_rcu(struct rcu_head *head)
 	cic = container_of(head, struct cfq_io_context, rcu_head);
 
 	kmem_cache_free(cfq_ioc_pool, cic);
-	elv_ioc_count_dec(ioc_count);
+	elv_ioc_count_dec(cfq_ioc_count);
 
 	if (ioc_gone) {
 		/*
@@ -1436,7 +2438,7 @@ static void cfq_cic_free_rcu(struct rcu_head *head)
 		 * complete ioc_gone and set it back to NULL
 		 */
 		spin_lock(&ioc_gone_lock);
-		if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
+		if (ioc_gone && !elv_ioc_count_read(cfq_ioc_count)) {
 			complete(ioc_gone);
 			ioc_gone = NULL;
 		}
@@ -1481,11 +2483,29 @@ static void cfq_free_io_context(struct io_context *ioc)
 
 static void cfq_exit_cfqq(struct cfq_data *cfqd, 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
+	 * the merge chain).  See cfq_setup_merge and cfq_merge_cfqqs.
+	 */
+	__cfqq = cfqq->new_cfqq;
+	while (__cfqq) {
+		if (__cfqq == cfqq) {
+			WARN(1, "cfqq->new_cfqq loop detected\n");
+			break;
+		}
+		next = __cfqq->new_cfqq;
+		cfq_put_queue(__cfqq);
+		__cfqq = next;
+	}
+
 	cfq_put_queue(cfqq);
 }
 
@@ -1562,7 +2582,7 @@ cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
 		INIT_HLIST_NODE(&cic->cic_list);
 		cic->dtor = cfq_free_io_context;
 		cic->exit = cfq_exit_io_context;
-		elv_ioc_count_inc(ioc_count);
+		elv_ioc_count_inc(cfq_ioc_count);
 	}
 
 	return cic;
@@ -1647,7 +2667,7 @@ static void cfq_ioc_set_ioprio(struct io_context *ioc)
 }
 
 static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-			  pid_t pid, int is_sync)
+			  pid_t pid, bool is_sync)
 {
 	RB_CLEAR_NODE(&cfqq->rb_node);
 	RB_CLEAR_NODE(&cfqq->p_node);
@@ -1666,14 +2686,51 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	cfqq->pid = pid;
 }
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+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;
+	unsigned long flags;
+	struct request_queue *q;
+
+	if (unlikely(!cfqd))
+		return;
+
+	q = cfqd->queue;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	if (sync_cfqq) {
+		/*
+		 * Drop reference to sync queue. A new sync queue will be
+		 * assigned in new group upon arrival of a fresh request.
+		 */
+		cfq_log_cfqq(cfqd, sync_cfqq, "changed cgroup");
+		cic_set_cfqq(cic, NULL, 1);
+		cfq_put_queue(sync_cfqq);
+	}
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static void cfq_ioc_set_cgroup(struct io_context *ioc)
+{
+	call_for_each_cic(ioc, changed_cgroup);
+	ioc->cgroup_changed = 0;
+}
+#endif  /* CONFIG_CFQ_GROUP_IOSCHED */
+
 static struct cfq_queue *
-cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync,
+cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
 		     struct io_context *ioc, gfp_t gfp_mask)
 {
 	struct cfq_queue *cfqq, *new_cfqq = NULL;
 	struct cfq_io_context *cic;
+	struct cfq_group *cfqg;
 
 retry:
+	cfqg = cfq_get_cfqg(cfqd, 1);
 	cic = cfq_cic_lookup(cfqd, ioc);
 	/* cic always exists here */
 	cfqq = cic_to_cfqq(cic, is_sync);
@@ -1704,6 +2761,7 @@ retry:
 		if (cfqq) {
 			cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync);
 			cfq_init_prio_data(cfqq, ioc);
+			cfq_link_cfqq_cfqg(cfqq, cfqg);
 			cfq_log_cfqq(cfqd, cfqq, "alloced");
 		} else
 			cfqq = &cfqd->oom_cfqq;
@@ -1731,7 +2789,7 @@ cfq_async_queue_prio(struct cfq_data *cfqd, int ioprio_class, int ioprio)
 }
 
 static struct cfq_queue *
-cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc,
+cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct io_context *ioc,
 	      gfp_t gfp_mask)
 {
 	const int ioprio = task_ioprio(ioc);
@@ -1895,6 +2953,10 @@ out:
 	if (unlikely(ioc->ioprio_changed))
 		cfq_ioc_set_ioprio(ioc);
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	if (unlikely(ioc->cgroup_changed))
+		cfq_ioc_set_cgroup(ioc);
+#endif
 	return cic;
 err_free:
 	cfq_cic_free(cic);
@@ -1915,33 +2977,33 @@ cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_io_context *cic)
 }
 
 static void
-cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,
+cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		       struct request *rq)
 {
 	sector_t sdist;
 	u64 total;
 
-	if (!cic->last_request_pos)
+	if (!cfqq->last_request_pos)
 		sdist = 0;
-	else if (cic->last_request_pos < blk_rq_pos(rq))
-		sdist = blk_rq_pos(rq) - cic->last_request_pos;
+	else if (cfqq->last_request_pos < blk_rq_pos(rq))
+		sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
 	else
-		sdist = cic->last_request_pos - blk_rq_pos(rq);
+		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 (cic->seek_samples <= 60) /* second&third seek */
-		sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*1024);
+	if (cfqq->seek_samples <= 60) /* second&third seek */
+		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*1024);
 	else
-		sdist = min(sdist, (cic->seek_mean * 4)	+ 2*1024*64);
+		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*64);
 
-	cic->seek_samples = (7*cic->seek_samples + 256) / 8;
-	cic->seek_total = (7*cic->seek_total + (u64)256*sdist) / 8;
-	total = cic->seek_total + (cic->seek_samples/2);
-	do_div(total, cic->seek_samples);
-	cic->seek_mean = (sector_t)total;
+	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;
 }
 
 /*
@@ -1962,8 +3024,12 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 
 	enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);
 
+	if (cfqq->queued[0] + cfqq->queued[1] >= 4)
+		cfq_mark_cfqq_deep(cfqq);
+
 	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
-	    (cfqd->hw_tag && CIC_SEEKY(cic)))
+	    (!cfq_cfqq_deep(cfqq) && sample_valid(cfqq->seek_samples)
+	     && CFQQ_SEEKY(cfqq)))
 		enable_idle = 0;
 	else if (sample_valid(cic->ttime_samples)) {
 		if (cic->ttime_mean > cfqd->cfq_slice_idle)
@@ -1985,7 +3051,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
  * Check if new_cfqq should preempt the currently active queue. Return 0 for
  * no or if we aren't sure, a 1 will cause a preempt.
  */
-static int
+static bool
 cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 		   struct request *rq)
 {
@@ -1993,48 +3059,64 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 
 	cfqq = cfqd->active_queue;
 	if (!cfqq)
-		return 0;
-
-	if (cfq_slice_used(cfqq))
-		return 1;
+		return false;
 
 	if (cfq_class_idle(new_cfqq))
-		return 0;
+		return false;
 
 	if (cfq_class_idle(cfqq))
-		return 1;
+		return true;
+
+	/*
+	 * Don't allow a non-RT request to preempt an ongoing RT cfqq timeslice.
+	 */
+	if (cfq_class_rt(cfqq) && !cfq_class_rt(new_cfqq))
+		return false;
 
 	/*
 	 * if the new request is sync, but the currently running queue is
 	 * not, let the sync request have priority.
 	 */
 	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
-		return 1;
+		return true;
+
+	if (new_cfqq->cfqg != cfqq->cfqg)
+		return false;
+
+	if (cfq_slice_used(cfqq))
+		return true;
+
+	/* Allow preemption only if we are idling on sync-noidle tree */
+	if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD &&
+	    cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
+	    new_cfqq->service_tree->count == 2 &&
+	    RB_EMPTY_ROOT(&cfqq->sort_list))
+		return true;
 
 	/*
 	 * 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)
-		return 1;
+		return true;
 
 	/*
 	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
 	 */
 	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
-		return 1;
+		return true;
 
 	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
-		return 0;
+		return false;
 
 	/*
 	 * if this request is as-good as one we would expect from the
 	 * current cfqq, let it preempt
 	 */
-	if (cfq_rq_close(cfqd, rq))
-		return 1;
+	if (cfq_rq_close(cfqd, cfqq, rq, true))
+		return true;
 
-	return 0;
+	return false;
 }
 
 /*
@@ -2073,10 +3155,10 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		cfqq->meta_pending++;
 
 	cfq_update_io_thinktime(cfqd, cic);
-	cfq_update_io_seektime(cfqd, cic, rq);
+	cfq_update_io_seektime(cfqd, cfqq, rq);
 	cfq_update_idle_window(cfqd, cfqq, cic);
 
-	cic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
+	cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
 
 	if (cfqq == cfqd->active_queue) {
 		/*
@@ -2093,9 +3175,10 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
 			    cfqd->busy_queues > 1) {
 				del_timer(&cfqd->idle_slice_timer);
-			__blk_run_queue(cfqd->queue);
-			}
-			cfq_mark_cfqq_must_dispatch(cfqq);
+				cfq_clear_cfqq_wait_request(cfqq);
+				__blk_run_queue(cfqd->queue);
+			} else
+				cfq_mark_cfqq_must_dispatch(cfqq);
 		}
 	} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
 		/*
@@ -2117,9 +3200,9 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	cfq_log_cfqq(cfqd, cfqq, "insert_request");
 	cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc);
 
-	cfq_add_rq_rb(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_rq_enqueued(cfqd, cfqq, rq);
 }
@@ -2130,23 +3213,64 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
  */
 static void cfq_update_hw_tag(struct cfq_data *cfqd)
 {
-	if (cfqd->rq_in_driver > cfqd->rq_in_driver_peak)
-		cfqd->rq_in_driver_peak = cfqd->rq_in_driver;
+	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->hw_tag == 1)
+		return;
 
 	if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
-	    cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
+	    rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
+		return;
+
+	/*
+	 * If active queue hasn't enough requests and can idle, cfq might not
+	 * dispatch sufficient requests to hardware. Don't zero hw_tag in this
+	 * case
+	 */
+	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)
 		return;
 
 	if (cfqd->hw_tag_samples++ < 50)
 		return;
 
-	if (cfqd->rq_in_driver_peak >= CFQ_HW_QUEUE_MIN)
+	if (cfqd->hw_tag_est_depth >= CFQ_HW_QUEUE_MIN)
 		cfqd->hw_tag = 1;
 	else
 		cfqd->hw_tag = 0;
+}
+
+static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	struct cfq_io_context *cic = cfqd->active_cic;
 
-	cfqd->hw_tag_samples = 0;
-	cfqd->rq_in_driver_peak = 0;
+	/* If there are other queues in the group, don't wait */
+	if (cfqq->cfqg->nr_cfqq > 1)
+		return false;
+
+	if (cfq_slice_used(cfqq))
+		return true;
+
+	/* if slice left is less than think time, wait busy */
+	if (cic && sample_valid(cic->ttime_samples)
+	    && (cfqq->slice_end - jiffies < cic->ttime_mean))
+		return true;
+
+	/*
+	 * If think times is less than a jiffy than ttime_mean=0 and above
+	 * will not be true. It might happen that slice has not expired yet
+	 * but will expire soon (4-5 ns) during select_queue(). To cover the
+	 * case where think time is less than a jiffy, mark the queue wait
+	 * busy if only 1 jiffy is left in the slice.
+	 */
+	if (cfqq->slice_end - jiffies == 1)
+		return true;
+
+	return false;
 }
 
 static void cfq_completed_request(struct request_queue *q, struct request *rq)
@@ -2157,20 +3281,23 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	unsigned long now;
 
 	now = jiffies;
-	cfq_log_cfqq(cfqd, cfqq, "complete");
+	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", !!rq_noidle(rq));
 
 	cfq_update_hw_tag(cfqd);
 
-	WARN_ON(!cfqd->rq_in_driver);
+	WARN_ON(!cfqd->rq_in_driver[sync]);
 	WARN_ON(!cfqq->dispatched);
-	cfqd->rq_in_driver--;
+	cfqd->rq_in_driver[sync]--;
 	cfqq->dispatched--;
 
 	if (cfq_cfqq_sync(cfqq))
 		cfqd->sync_flight--;
 
-	if (sync)
+	if (sync) {
 		RQ_CIC(rq)->last_end_request = now;
+		if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now))
+			cfqd->last_delayed_sync = now;
+	}
 
 	/*
 	 * If this is the active queue, check if it needs to be expired,
@@ -2183,21 +3310,42 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 			cfq_set_prio_slice(cfqd, cfqq);
 			cfq_clear_cfqq_slice_new(cfqq);
 		}
+
+		/*
+		 * Should we wait for next request to come in before we expire
+		 * the queue.
+		 */
+		if (cfq_should_wait_busy(cfqd, cfqq)) {
+			cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
+			cfq_mark_cfqq_wait_busy(cfqq);
+		}
+
 		/*
-		 * If there are no requests waiting in this queue, and
-		 * there are other queues ready to issue requests, AND
-		 * those other queues are issuing requests within our
-		 * mean seek distance, give them a chance to run instead
-		 * of idling.
+		 * Idling is not enabled on:
+		 * - expired queues
+		 * - idle-priority queues
+		 * - async queues
+		 * - queues with still some requests queued
+		 * - when there is a close cooperator
 		 */
 		if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
 			cfq_slice_expired(cfqd, 1);
-		else if (cfqq_empty && !cfq_close_cooperator(cfqd, cfqq, 1) &&
-			 sync && !rq_noidle(rq))
-			cfq_arm_slice_timer(cfqd);
+		else if (sync && cfqq_empty &&
+			 !cfq_close_cooperator(cfqd, cfqq)) {
+			cfqd->noidle_tree_requires_idle |= !rq_noidle(rq);
+			/*
+			 * 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
+			 */
+			if (cfqd->serving_type == SYNC_WORKLOAD
+			    || cfqd->noidle_tree_requires_idle
+			    || cfqq->cfqg->nr_cfqq == 1)
+				cfq_arm_slice_timer(cfqd);
+		}
 	}
 
-	if (!cfqd->rq_in_driver)
+	if (!rq_in_driver(cfqd))
 		cfq_schedule_dispatch(cfqd);
 }
 
@@ -2218,19 +3366,16 @@ static void cfq_prio_boost(struct cfq_queue *cfqq)
 			cfqq->ioprio = IOPRIO_NORM;
 	} else {
 		/*
-		 * check if we need to unboost the queue
+		 * unboost the queue (if needed)
 		 */
-		if (cfqq->ioprio_class != cfqq->org_ioprio_class)
-			cfqq->ioprio_class = cfqq->org_ioprio_class;
-		if (cfqq->ioprio != cfqq->org_ioprio)
-			cfqq->ioprio = cfqq->org_ioprio;
+		cfqq->ioprio_class = cfqq->org_ioprio_class;
+		cfqq->ioprio = cfqq->org_ioprio;
 	}
 }
 
 static inline int __cfq_may_queue(struct cfq_queue *cfqq)
 {
-	if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) &&
-	    !cfq_cfqq_must_alloc_slice(cfqq)) {
+	if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) {
 		cfq_mark_cfqq_must_alloc_slice(cfqq);
 		return ELV_MQUEUE_MUST;
 	}
@@ -2288,6 +3433,35 @@ static void cfq_put_request(struct request *rq)
 	}
 }
 
+static struct cfq_queue *
+cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic,
+		struct cfq_queue *cfqq)
+{
+	cfq_log_cfqq(cfqd, cfqq, "merging with queue %p", cfqq->new_cfqq);
+	cic_set_cfqq(cic, cfqq->new_cfqq, 1);
+	cfq_mark_cfqq_coop(cfqq->new_cfqq);
+	cfq_put_queue(cfqq);
+	return cic_to_cfqq(cic, 1);
+}
+
+/*
+ * Returns NULL if a new cfqq should be allocated, or the old cfqq if this
+ * was the last process referring to said cfqq.
+ */
+static struct cfq_queue *
+split_cfqq(struct cfq_io_context *cic, struct cfq_queue *cfqq)
+{
+	if (cfqq_process_refs(cfqq) == 1) {
+		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_queue(cfqq);
+	return NULL;
+}
 /*
  * Allocate cfq data structures associated with this request.
  */
@@ -2297,7 +3471,7 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_io_context *cic;
 	const int rw = rq_data_dir(rq);
-	const int is_sync = rq_is_sync(rq);
+	const bool is_sync = rq_is_sync(rq);
 	struct cfq_queue *cfqq;
 	unsigned long flags;
 
@@ -2310,14 +3484,33 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
 	if (!cic)
 		goto queue_fail;
 
+new_queue:
 	cfqq = cic_to_cfqq(cic, is_sync);
 	if (!cfqq || cfqq == &cfqd->oom_cfqq) {
 		cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask);
 		cic_set_cfqq(cic, cfqq, is_sync);
+	} else {
+		/*
+		 * If the queue was seeky for too long, break it apart.
+		 */
+		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)
+				goto new_queue;
+		}
+
+		/*
+		 * Check to see if this queue is scheduled to merge with
+		 * another, closely cooperating queue.  The merging of
+		 * queues happens here as it must be done in process context.
+		 * The reference on new_cfqq was taken in merge_cfqqs.
+		 */
+		if (cfqq->new_cfqq)
+			cfqq = cfq_merge_cfqqs(cfqd, cic, cfqq);
 	}
 
 	cfqq->allocated[rw]++;
-	cfq_clear_cfqq_must_alloc(cfqq);
 	atomic_inc(&cfqq->ref);
 
 	spin_unlock_irqrestore(q->queue_lock, flags);
@@ -2389,6 +3582,11 @@ static void cfq_idle_slice_timer(unsigned long data)
 		 */
 		if (!RB_EMPTY_ROOT(&cfqq->sort_list))
 			goto out_kick;
+
+		/*
+		 * Queue depth flag is reset only when the idle didn't succeed
+		 */
+		cfq_clear_cfqq_deep(cfqq);
 	}
 expire:
 	cfq_slice_expired(cfqd, timed_out);
@@ -2419,6 +3617,11 @@ static void cfq_put_async_queues(struct cfq_data *cfqd)
 		cfq_put_queue(cfqd->async_idle_cfqq);
 }
 
+static void cfq_cfqd_free(struct rcu_head *head)
+{
+	kfree(container_of(head, struct cfq_data, rcu));
+}
+
 static void cfq_exit_queue(struct elevator_queue *e)
 {
 	struct cfq_data *cfqd = e->elevator_data;
@@ -2440,25 +3643,49 @@ 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);
 
 	spin_unlock_irq(q->queue_lock);
 
 	cfq_shutdown_timer_wq(cfqd);
 
-	kfree(cfqd);
+	/* Wait for cfqg->blkg->key accessors to exit their grace periods. */
+	call_rcu(&cfqd->rcu, cfq_cfqd_free);
 }
 
 static void *cfq_init_queue(struct request_queue *q)
 {
 	struct cfq_data *cfqd;
-	int i;
+	int i, j;
+	struct cfq_group *cfqg;
+	struct cfq_rb_root *st;
 
 	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
 	if (!cfqd)
 		return NULL;
 
-	cfqd->service_tree = CFQ_RB_ROOT;
+	/* Init root service tree */
+	cfqd->grp_service_tree = CFQ_RB_ROOT;
+
+	/* Init root group */
+	cfqg = &cfqd->root_group;
+	for_each_cfqg_st(cfqg, i, j, st)
+		*st = CFQ_RB_ROOT;
+	RB_CLEAR_NODE(&cfqg->rb_node);
+
+	/* Give preference to root group over other groups */
+	cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT;
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	/*
+	 * Take a reference to root group which we never drop. This is just
+	 * 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);
+#endif
 	/*
 	 * Not strictly needed (since RB_ROOT just clears the node and we
 	 * zeroed cfqd on alloc), but better be safe in case someone decides
@@ -2474,6 +3701,7 @@ static void *cfq_init_queue(struct request_queue *q)
 	 */
 	cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0);
 	atomic_inc(&cfqd->oom_cfqq.ref);
+	cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, &cfqd->root_group);
 
 	INIT_LIST_HEAD(&cfqd->cic_list);
 
@@ -2494,8 +3722,15 @@ 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->hw_tag = 1;
-
+	cfqd->cfq_latency = 1;
+	cfqd->cfq_group_isolation = 0;
+	cfqd->hw_tag = -1;
+	/*
+	 * we optimistically start assuming sync ops weren't delayed in last
+	 * second, in order to have larger depth for async operations.
+	 */
+	cfqd->last_delayed_sync = jiffies - HZ;
+	INIT_RCU_HEAD(&cfqd->rcu);
 	return cfqd;
 }
 
@@ -2563,6 +3798,8 @@ SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_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);
+SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0);
+SHOW_FUNCTION(cfq_group_isolation_show, cfqd->cfq_group_isolation, 0);
 #undef SHOW_FUNCTION
 
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
@@ -2594,6 +3831,8 @@ 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,
 		UINT_MAX, 0);
+STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
+STORE_FUNCTION(cfq_group_isolation_store, &cfqd->cfq_group_isolation, 0, 1, 0);
 #undef STORE_FUNCTION
 
 #define CFQ_ATTR(name) \
@@ -2609,6 +3848,8 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(slice_async),
 	CFQ_ATTR(slice_async_rq),
 	CFQ_ATTR(slice_idle),
+	CFQ_ATTR(low_latency),
+	CFQ_ATTR(group_isolation),
 	__ATTR_NULL
 };
 
@@ -2638,6 +3879,17 @@ static struct elevator_type iosched_cfq = {
 	.elevator_owner =	THIS_MODULE,
 };
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static struct blkio_policy_type blkio_policy_cfq = {
+	.ops = {
+		.blkio_unlink_group_fn =	cfq_unlink_blkio_group,
+		.blkio_update_group_weight_fn =	cfq_update_blkio_group_weight,
+	},
+};
+#else
+static struct blkio_policy_type blkio_policy_cfq;
+#endif
+
 static int __init cfq_init(void)
 {
 	/*
@@ -2652,6 +3904,7 @@ static int __init cfq_init(void)
 		return -ENOMEM;
 
 	elv_register(&iosched_cfq);
+	blkio_policy_register(&blkio_policy_cfq);
 
 	return 0;
 }
@@ -2659,6 +3912,7 @@ static int __init cfq_init(void)
 static void __exit cfq_exit(void)
 {
 	DECLARE_COMPLETION_ONSTACK(all_gone);
+	blkio_policy_unregister(&blkio_policy_cfq);
 	elv_unregister(&iosched_cfq);
 	ioc_gone = &all_gone;
 	/* ioc_gone's update must be visible before reading ioc_count */
@@ -2668,7 +3922,7 @@ static void __exit cfq_exit(void)
 	 * this also protects us from entering cfq_slab_kill() with
 	 * pending RCU callbacks
 	 */
-	if (elv_ioc_count_read(ioc_count))
+	if (elv_ioc_count_read(cfq_ioc_count))
 		wait_for_completion(&all_gone);
 	cfq_slab_kill();
 }
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 7865a34e0faa..4eb8e9ea4af5 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -21,6 +21,11 @@ static int compat_put_int(unsigned long arg, int val)
 	return put_user(val, (compat_int_t __user *)compat_ptr(arg));
 }
 
+static int compat_put_uint(unsigned long arg, unsigned int val)
+{
+	return put_user(val, (compat_uint_t __user *)compat_ptr(arg));
+}
+
 static int compat_put_long(unsigned long arg, long val)
 {
 	return put_user(val, (compat_long_t __user *)compat_ptr(arg));
@@ -734,6 +739,16 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	switch (cmd) {
 	case HDIO_GETGEO:
 		return compat_hdio_getgeo(disk, bdev, compat_ptr(arg));
+	case BLKPBSZGET:
+		return compat_put_uint(arg, bdev_physical_block_size(bdev));
+	case BLKIOMIN:
+		return compat_put_uint(arg, bdev_io_min(bdev));
+	case BLKIOOPT:
+		return compat_put_uint(arg, bdev_io_opt(bdev));
+	case BLKALIGNOFF:
+		return compat_put_int(arg, bdev_alignment_offset(bdev));
+	case BLKDISCARDZEROES:
+		return compat_put_uint(arg, bdev_discard_zeroes_data(bdev));
 	case BLKFLSBUF:
 	case BLKROSET:
 	case BLKDISCARD:
diff --git a/block/elevator.c b/block/elevator.c
index 2d511f9105e1..9ad5ccc4c5ee 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -79,7 +79,8 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 	/*
 	 * Don't merge file system requests and discard requests
 	 */
-	if (bio_discard(bio) != bio_discard(rq->bio))
+	if (bio_rw_flagged(bio, BIO_RW_DISCARD) !=
+	    bio_rw_flagged(rq->bio, BIO_RW_DISCARD))
 		return 0;
 
 	/*
@@ -100,19 +101,6 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (bio_integrity(bio) != blk_integrity_rq(rq))
 		return 0;
 
-	/*
-	 * Don't merge if failfast settings don't match.
-	 *
-	 * FIXME: The negation in front of each condition is necessary
-	 * because bio and request flags use different bit positions
-	 * and the accessors return those bits directly.  This
-	 * ugliness will soon go away.
-	 */
-	if (!bio_failfast_dev(bio)	 != !blk_failfast_dev(rq)	||
-	    !bio_failfast_transport(bio) != !blk_failfast_transport(rq)	||
-	    !bio_failfast_driver(bio)	 != !blk_failfast_driver(rq))
-		return 0;
-
 	if (!elv_iosched_allow_merge(rq, bio))
 		return 0;
 
@@ -166,10 +154,7 @@ static struct elevator_type *elevator_get(const char *name)
 
 		spin_unlock(&elv_list_lock);
 
-		if (!strcmp(name, "anticipatory"))
-			sprintf(elv, "as-iosched");
-		else
-			sprintf(elv, "%s-iosched", name);
+		sprintf(elv, "%s-iosched", name);
 
 		request_module("%s", elv);
 		spin_lock(&elv_list_lock);
@@ -205,10 +190,7 @@ static int __init elevator_setup(char *str)
 	 * Be backwards-compatible with previous kernels, so users
 	 * won't get the wrong elevator.
 	 */
-	if (!strcmp(str, "as"))
-		strcpy(chosen_elevator, "anticipatory");
-	else
-		strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
+	strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
 	return 1;
 }
 
@@ -1071,9 +1053,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 		return count;
 
 	strlcpy(elevator_name, name, sizeof(elevator_name));
-	strstrip(elevator_name);
-
-	e = elevator_get(elevator_name);
+	e = elevator_get(strstrip(elevator_name));
 	if (!e) {
 		printk(KERN_ERR "elevator: type %s not found\n", elevator_name);
 		return -EINVAL;
diff --git a/block/genhd.c b/block/genhd.c
index f4c64c2b303a..d13ba76a169c 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -861,14 +861,26 @@ static ssize_t disk_alignment_offset_show(struct device *dev,
 	return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue));
 }
 
+static ssize_t disk_discard_alignment_show(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue));
+}
+
 static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
 static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
 static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
 static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
 static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL);
+static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show,
+		   NULL);
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
@@ -886,8 +898,10 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_ro.attr,
 	&dev_attr_size.attr,
 	&dev_attr_alignment_offset.attr,
+	&dev_attr_discard_alignment.attr,
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
+	&dev_attr_inflight.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif
@@ -901,7 +915,7 @@ static struct attribute_group disk_attr_group = {
 	.attrs = disk_attrs,
 };
 
-static struct attribute_group *disk_attr_groups[] = {
+static const struct attribute_group *disk_attr_groups[] = {
 	&disk_attr_group,
 	NULL
 };
@@ -996,12 +1010,12 @@ struct class block_class = {
 	.name		= "block",
 };
 
-static char *block_nodename(struct device *dev)
+static char *block_devnode(struct device *dev, mode_t *mode)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	if (disk->nodename)
-		return disk->nodename(disk);
+	if (disk->devnode)
+		return disk->devnode(disk, mode);
 	return NULL;
 }
 
@@ -1009,7 +1023,7 @@ static struct device_type disk_type = {
 	.name		= "disk",
 	.groups		= disk_attr_groups,
 	.release	= disk_release,
-	.nodename	= block_nodename,
+	.devnode	= block_devnode,
 };
 
 #ifdef CONFIG_PROC_FS
@@ -1053,7 +1067,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   part_stat_read(hd, merges[1]),
 			   (unsigned long long)part_stat_read(hd, sectors[1]),
 			   jiffies_to_msecs(part_stat_read(hd, ticks[1])),
-			   hd->in_flight,
+			   part_in_flight(hd),
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
 			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
 			);
@@ -1215,6 +1229,16 @@ void put_disk(struct gendisk *disk)
 
 EXPORT_SYMBOL(put_disk);
 
+static void set_disk_ro_uevent(struct gendisk *gd, int ro)
+{
+	char event[] = "DISK_RO=1";
+	char *envp[] = { event, NULL };
+
+	if (!ro)
+		event[8] = '0';
+	kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp);
+}
+
 void set_device_ro(struct block_device *bdev, int flag)
 {
 	bdev->bd_part->policy = flag;
@@ -1227,8 +1251,12 @@ void set_disk_ro(struct gendisk *disk, int flag)
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 
-	disk_part_iter_init(&piter, disk,
-			    DISK_PITER_INCL_EMPTY | DISK_PITER_INCL_PART0);
+	if (disk->part0.policy != flag) {
+		set_disk_ro_uevent(disk, flag);
+		disk->part0.policy = flag;
+	}
+
+	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter)))
 		part->policy = flag;
 	disk_part_iter_exit(&piter);
diff --git a/block/ioctl.c b/block/ioctl.c
index 500e4c73cc52..be48ea51faee 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -112,22 +112,9 @@ static int blkdev_reread_part(struct block_device *bdev)
 	return res;
 }
 
-static void blk_ioc_discard_endio(struct bio *bio, int err)
-{
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	}
-	complete(bio->bi_private);
-}
-
 static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 			     uint64_t len)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-	int ret = 0;
-
 	if (start & 511)
 		return -EINVAL;
 	if (len & 511)
@@ -137,40 +124,8 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 
 	if (start + len > (bdev->bd_inode->i_size >> 9))
 		return -EINVAL;
-
-	if (!q->prepare_discard_fn)
-		return -EOPNOTSUPP;
-
-	while (len && !ret) {
-		DECLARE_COMPLETION_ONSTACK(wait);
-		struct bio *bio;
-
-		bio = bio_alloc(GFP_KERNEL, 0);
-
-		bio->bi_end_io = blk_ioc_discard_endio;
-		bio->bi_bdev = bdev;
-		bio->bi_private = &wait;
-		bio->bi_sector = start;
-
-		if (len > queue_max_hw_sectors(q)) {
-			bio->bi_size = queue_max_hw_sectors(q) << 9;
-			len -= queue_max_hw_sectors(q);
-			start += queue_max_hw_sectors(q);
-		} else {
-			bio->bi_size = len << 9;
-			len = 0;
-		}
-		submit_bio(DISCARD_NOBARRIER, bio);
-
-		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;
+	return blkdev_issue_discard(bdev, start, len, GFP_KERNEL,
+				    DISCARD_FL_WAIT);
 }
 
 static int put_ushort(unsigned long arg, unsigned short val)
@@ -183,6 +138,11 @@ static int put_int(unsigned long arg, int val)
 	return put_user(val, (int __user *)arg);
 }
 
+static int put_uint(unsigned long arg, unsigned int val)
+{
+	return put_user(val, (unsigned int __user *)arg);
+}
+
 static int put_long(unsigned long arg, long val)
 {
 	return put_user(val, (long __user *)arg);
@@ -308,10 +268,20 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
 	case BLKROGET:
 		return put_int(arg, bdev_read_only(bdev) != 0);
-	case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */
+	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
 		return put_int(arg, block_size(bdev));
-	case BLKSSZGET: /* get block device hardware sector size */
+	case BLKSSZGET: /* get block device logical block size */
 		return put_int(arg, bdev_logical_block_size(bdev));
+	case BLKPBSZGET: /* get block device physical block size */
+		return put_uint(arg, bdev_physical_block_size(bdev));
+	case BLKIOMIN:
+		return put_uint(arg, bdev_io_min(bdev));
+	case BLKIOOPT:
+		return put_uint(arg, bdev_io_opt(bdev));
+	case BLKALIGNOFF:
+		return put_int(arg, bdev_alignment_offset(bdev));
+	case BLKDISCARDZEROES:
+		return put_uint(arg, bdev_discard_zeroes_data(bdev));
 	case BLKSECTGET:
 		return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev)));
 	case BLKRASET:
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index e5b10017a50b..a8b5a10eb5b0 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -35,7 +35,9 @@
 struct blk_cmd_filter {
 	unsigned long read_ok[BLK_SCSI_CMD_PER_LONG];
 	unsigned long write_ok[BLK_SCSI_CMD_PER_LONG];
-} blk_default_cmd_filter;
+};
+
+static struct blk_cmd_filter blk_default_cmd_filter;
 
 /* Command group 3 is reserved and should never be used.  */
 const unsigned char scsi_command_size_tbl[8] =
@@ -675,7 +677,7 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod
 }
 EXPORT_SYMBOL(scsi_cmd_ioctl);
 
-int __init blk_scsi_ioctl_init(void)
+static int __init blk_scsi_ioctl_init(void)
 {
 	blk_set_cmd_filter_defaults(&blk_default_cmd_filter);
 	return 0;