30 files changed, 4399 insertions, 3991 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 0cbb3b88b59..e20fbde0875 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -23,9 +23,10 @@ menuconfig BLOCK
 
 if BLOCK
 
-config LBD
-	bool "Support for large block devices and files"
+config LBDAF
+	bool "Support for large (2TB+) block devices and files"
 	depends on !64BIT
+	default y
 	help
 	  Enable block devices or files of size 2TB and larger.
 
@@ -38,32 +39,18 @@ config LBD
 
 	  The ext4 filesystem requires that this feature be enabled in
 	  order to support filesystems that have the huge_file feature
-	  enabled.    Otherwise, it will refuse to mount any filesystems
-	  that use the huge_file feature, which is enabled by default
-	  by mke2fs.ext4.   The GFS2 filesystem also requires this feature.
-
-	  If unsure, say N.
-
-config BLK_DEV_IO_TRACE
-	bool "Support for tracing block io actions"
-	depends on SYSFS
-	select RELAY
-	select DEBUG_FS
-	select TRACEPOINTS
-	help
-	  Say Y here if you want to be able to trace the block layer actions
-	  on a given queue. Tracing allows you to see any traffic happening
-	  on a block device queue. For more information (and the userspace
-	  support tools needed), fetch the blktrace tools from:
+	  enabled.  Otherwise, it will refuse to mount in the read-write
+	  mode any filesystems that use the huge_file feature, which is
+	  enabled by default by mke2fs.ext4.
 
-	  git://git.kernel.dk/blktrace.git
+	  The GFS2 filesystem also requires this feature.
 
-	  If unsure, say N.
+	  If unsure, say Y.
 
 config BLK_DEV_BSG
-	bool "Block layer SG support v4 (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
-	---help---
+	bool "Block layer SG support v4"
+	default y
+	help
 	  Saying Y here will enable generic SG (SCSI generic) v4 support
 	  for any block device.
 
@@ -73,7 +60,10 @@ config BLK_DEV_BSG
 	  protocols (e.g. Task Management Functions and SMP in Serial
 	  Attached SCSI).
 
-	  If unsure, say N.
+	  This option is required by recent UDEV versions to properly
+	  access device serial numbers, etc.
+
+	  If unsure, say Y.
 
 config BLK_DEV_INTEGRITY
 	bool "Block layer data integrity support"
@@ -87,6 +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 7e803fc8877..b71abfb0d72 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 bfe73049f93..cb2d515ebd6 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,14 +5,13 @@
 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 cmd-filter.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
 
-obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY)	+= blk-integrity.o
diff --git a/block/as-iosched.c b/block/as-iosched.c
deleted file mode 100644
index 631f6f44460..00000000000
--- a/block/as-iosched.c
+++ /dev/null
@@ -1,1524 +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>
-
-#define REQ_SYNC	1
-#define REQ_ASYNC	0
-
-/*
- * 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 REQ_SYNC & REQ_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 REQ_SYNC / REQ_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 = rq1->sector;
-	s2 = rq2->sector;
-
-	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 == REQ_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 < rq->sector)
-				seek_dist = rq->sector - aic->last_request_pos;
-			else
-				seek_dist = aic->last_request_pos - rq->sector;
-			as_update_seekdist(ad, aic, seek_dist);
-		}
-		aic->last_request_pos = rq->sector + rq->nr_sectors;
-		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 = rq->sector;
-	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_RUNN