Merge branch 'block-dir' of git://brick.kernel.dk/data/git/linux-2.6-block

12 files changed, 11454 insertions, 0 deletions

diff --git a/block/Kconfig b/block/Kconfig
new file mode 100644
index 000000000000..eb48edb80c1d
--- /dev/null
+++ b/block/Kconfig
@@ -0,0 +1,14 @@
+#
+# Block layer core configuration
+#
+#XXX - it makes sense to enable this only for 32-bit subarch's, not for x86_64
+#for instance.
+config LBD
+	bool "Support for Large Block Devices"
+	depends on X86 || (MIPS && 32BIT) || PPC32 || ARCH_S390_31 || SUPERH || UML
+	help
+	  Say Y here if you want to attach large (bigger than 2TB) discs to
+	  your machine, or if you want to have a raid or loopback device
+	  bigger than 2TB.  Otherwise say N.
+
+source block/Kconfig.iosched
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
new file mode 100644
index 000000000000..f3b7753aac99
--- /dev/null
+++ b/block/Kconfig.iosched
@@ -0,0 +1,69 @@
+
+menu "IO Schedulers"
+
+config IOSCHED_NOOP
+	bool
+	default y
+	---help---
+	  The no-op I/O scheduler is a minimal scheduler that does basic merging
+	  and sorting. Its main uses include non-disk based block devices like
+	  memory devices, and specialised software or hardware environments
+	  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 the default disk scheduler. It 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.
+
+config IOSCHED_CFQ
+	tristate "CFQ I/O scheduler"
+	default y
+	---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.
+
+choice
+	prompt "Default I/O scheduler"
+	default DEFAULT_AS
+	help
+	  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
+
+	config DEFAULT_CFQ
+		bool "CFQ" if IOSCHED_CFQ=y
+
+	config DEFAULT_NOOP
+		bool "No-op"
+
+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
+
+endmenu
diff --git a/block/Makefile b/block/Makefile
new file mode 100644
index 000000000000..7e4f93e2b44e
--- /dev/null
+++ b/block/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for the kernel block layer
+#
+
+obj-y	:= elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.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
new file mode 100644
index 000000000000..a78e160b59a3
--- /dev/null
+++ b/block/as-iosched.c
@@ -0,0 +1,2005 @@
+/*
+ *  linux/drivers/block/as-iosched.c
+ *
+ *  Anticipatory & deadline i/o scheduler.
+ *
+ *  Copyright (C) 2002 Jens Axboe <axboe@suse.de>
+ *                     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/config.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/hash.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 as_rq *next_arq[2];	/* next in sort order */
+	sector_t last_sector[2];	/* last REQ_SYNC & REQ_ASYNC sectors */
+	struct list_head *hash;		/* request hash */
+
+	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? */
+	mempool_t *arq_pool;
+
+	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;
+};
+
+#define list_entry_fifo(ptr)	list_entry((ptr), struct as_rq, fifo)
+
+/*
+ * 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 */
+};
+
+struct as_rq {
+	/*
+	 * rbtree index, key is the starting offset
+	 */
+	struct rb_node rb_node;
+	sector_t rb_key;
+
+	struct request *request;
+
+	struct io_context *io_context;	/* The submitting task */
+
+	/*
+	 * request hash, key is the ending offset (for back merge lookup)
+	 */
+	struct list_head hash;
+	unsigned int on_hash;
+
+	/*
+	 * expire fifo
+	 */
+	struct list_head fifo;
+	unsigned long expires;
+
+	unsigned int is_sync;
+	enum arq_state state;
+};
+
+#define RQ_DATA(rq)	((struct as_rq *) (rq)->elevator_private)
+
+static kmem_cache_t *arq_pool;
+
+/*
+ * IO Context helper functions
+ */
+
+/* Called to deallocate the as_io_context */
+static void free_as_io_context(struct as_io_context *aic)
+{
+	kfree(aic);
+}
+
+/* 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;
+	}
+
+	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(void)
+{
+	struct io_context *ioc = get_io_context(GFP_ATOMIC);
+	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 as_rq *arq)
+{
+	struct as_io_context *aic;
+
+	if (unlikely(!arq->io_context))
+		return;
+
+	aic = arq->io_context->aic;
+
+	if (arq->is_sync == REQ_SYNC && aic) {
+		spin_lock(&aic->lock);
+		set_bit(AS_TASK_IORUNNING, &aic->state);
+		aic->last_end_request = jiffies;
+		spin_unlock(&aic->lock);
+	}
+
+	put_io_context(arq->io_context);
+}
+
+/*
+ * the back merge hash support functions
+ */
+static const int as_hash_shift = 6;
+#define AS_HASH_BLOCK(sec)	((sec) >> 3)
+#define AS_HASH_FN(sec)		(hash_long(AS_HASH_BLOCK((sec)), as_hash_shift))
+#define AS_HASH_ENTRIES		(1 << as_hash_shift)
+#define rq_hash_key(rq)		((rq)->sector + (rq)->nr_sectors)
+#define list_entry_hash(ptr)	list_entry((ptr), struct as_rq, hash)
+
+static inline void __as_del_arq_hash(struct as_rq *arq)
+{
+	arq->on_hash = 0;
+	list_del_init(&arq->hash);
+}
+
+static inline void as_del_arq_hash(struct as_rq *arq)
+{
+	if (arq->on_hash)
+		__as_del_arq_hash(arq);
+}
+
+static void as_add_arq_hash(struct as_data *ad, struct as_rq *arq)
+{
+	struct request *rq = arq->request;
+
+	BUG_ON(arq->on_hash);
+
+	arq->on_hash = 1;
+	list_add(&arq->hash, &ad->hash[AS_HASH_FN(rq_hash_key(rq))]);
+}
+
+/*
+ * move hot entry to front of chain
+ */
+static inline void as_hot_arq_hash(struct as_data *ad, struct as_rq *arq)
+{
+	struct request *rq = arq->request;
+	struct list_head *head = &ad->hash[AS_HASH_FN(rq_hash_key(rq))];
+
+	if (!arq->on_hash) {
+		WARN_ON(1);
+		return;
+	}
+
+	if (arq->hash.prev != head) {
+		list_del(&arq->hash);
+		list_add(&arq->hash, head);
+	}
+}
+
+static struct request *as_find_arq_hash(struct as_data *ad, sector_t offset)
+{
+	struct list_head *hash_list = &ad->hash[AS_HASH_FN(offset)];
+	struct list_head *entry, *next = hash_list->next;
+
+	while ((entry = next) != hash_list) {
+		struct as_rq *arq = list_entry_hash(entry);
+		struct request *__rq = arq->request;
+
+		next = entry->next;
+
+		BUG_ON(!arq->on_hash);
+
+		if (!rq_mergeable(__rq)) {
+			as_del_arq_hash(arq);
+			continue;
+		}
+
+		if (rq_hash_key(__rq) == offset)
+			return __rq;
+	}
+
+	return NULL;
+}
+
+/*
+ * rb tree support functions
+ */
+#define RB_NONE		(2)
+#define RB_EMPTY(root)	((root)->rb_node == NULL)
+#define ON_RB(node)	((node)->rb_color != RB_NONE)
+#define RB_CLEAR(node)	((node)->rb_color = RB_NONE)
+#define rb_entry_arq(node)	rb_entry((node), struct as_rq, rb_node)
+#define ARQ_RB_ROOT(ad, arq)	(&(ad)->sort_list[(arq)->is_sync])
+#define rq_rb_key(rq)		(rq)->sector
+
+/*
+ * as_find_first_arq finds the first (lowest sector numbered) request
+ * for the specified data_dir. Used to sweep back to the start of the disk
+ * (1-way elevator) after we process the last (highest sector) request.
+ */
+static struct as_rq *as_find_first_arq(struct as_data *ad, int data_dir)
+{
+	struct rb_node *n = ad->sort_list[data_dir].rb_node;
+
+	if (n == NULL)
+		return NULL;
+
+	for (;;) {
+		if (n->rb_left == NULL)
+			return rb_entry_arq(n);
+
+		n = n->rb_left;
+	}
+}
+
+/*
+ * Add the request to the rb tree if it is unique.  If there is an alias (an
+ * existing request against the same sector), which can happen when using
+ * direct IO, then return the alias.
+ */
+static struct as_rq *as_add_arq_rb(struct as_data *ad, struct as_rq *arq)
+{
+	struct rb_node **p = &ARQ_RB_ROOT(ad, arq)->rb_node;
+	struct rb_node *parent = NULL;
+	struct as_rq *__arq;
+	struct request *rq = arq->request;
+
+	arq->rb_key = rq_rb_key(rq);
+
+	while (*p) {
+		parent = *p;
+		__arq = rb_entry_arq(parent);
+
+		if (arq->rb_key < __arq->rb_key)
+			p = &(*p)->rb_left;
+		else if (arq->rb_key > __arq->rb_key)
+			p = &(*p)->rb_right;
+		else
+			return __arq;
+	}
+
+	rb_link_node(&arq->rb_node, parent, p);
+	rb_insert_color(&arq->rb_node, ARQ_RB_ROOT(ad, arq));
+
+	return NULL;
+}
+
+static inline void as_del_arq_rb(struct as_data *ad, struct as_rq *arq)
+{
+	if (!ON_RB(&arq->rb_node)) {
+		WARN_ON(1);
+		return;
+	}
+
+	rb_erase(&arq->rb_node, ARQ_RB_ROOT(ad, arq));
+	RB_CLEAR(&arq->rb_node);
+}
+
+static struct request *
+as_find_arq_rb(struct as_data *ad, sector_t sector, int data_dir)
+{
+	struct rb_node *n = ad->sort_list[data_dir].rb_node;
+	struct as_rq *arq;
+
+	while (n) {
+		arq = rb_entry_arq(n);
+
+		if (sector < arq->rb_key)
+			n = n->rb_left;
+		else if (sector > arq->rb_key)
+			n = n->rb_right;
+		else
+			return arq->request;
+	}
+
+	return NULL;
+}
+
+/*
+ * 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 as_rq *
+as_choose_req(struct as_data *ad, struct as_rq *arq1, struct as_rq *arq2)
+{
+	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 (arq1 == NULL || arq1 == arq2)
+		return arq2;
+	if (arq2 == NULL)
+		return arq1;
+
+	data_dir = arq1->is_sync;
+
+	last = ad->last_sector[data_dir];
+	s1 = arq1->request->sector;
+	s2 = arq2->request->sector;
+
+	BUG_ON(data_dir != arq2->is_sync);
+
+	/*
+	 * 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 arq1;
+	else if (!r2_wrap && r1_wrap)
+		return arq2;
+	else if (r1_wrap && r2_wrap) {
+		/* both behind the head */
+		if (s1 <= s2)
+			return arq1;
+		else
+			return arq2;
+	}
+
+	/* Both requests in front of the head */
+	if (d1 < d2)
+		return arq1;
+	else if (d2 < d1)
+		return arq2;
+	else {
+		if (s1 >= s2)
+			return arq1;
+		else
+			return arq2;
+	}
+}
+
+/*
+ * as_find_next_arq 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 as_rq *as_find_next_arq(struct as_data *ad, struct as_rq *last)
+{
+	const int data_dir = last->is_sync;
+	struct as_rq *ret;
+	struct rb_node *rbnext = rb_next(&last->rb_node);
+	struct rb_node *rbprev = rb_prev(&last->rb_node);
+	struct as_rq *arq_next, *arq_prev;
+
+	BUG_ON(!ON_RB(&last->rb_node));
+
+	if (rbprev)
+		arq_prev = rb_entry_arq(rbprev);
+	else
+		arq_prev = NULL;
+
+	if (rbnext)
+		arq_next = rb_entry_arq(rbnext);
+	else {
+		arq_next = as_find_first_arq(ad, data_dir);
+		if (arq_next == last)
+			arq_next = NULL;
+	}
+
+	ret = as_choose_req(ad,	arq_next, arq_prev);
+
+	return ret;
+}
+
+/*
+ * 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->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 = ad->io_context->aic;
+
+		ad->antic_status = ANTIC_FINISHED;
+		kblockd_schedule_work(&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_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)
+{
+	struct as_rq *arq = RQ_DATA(rq);
+	int data_dir = arq->is_sync;
+	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 as_rq *arq)
+{
+	unsigned long delay;	/* milliseconds */
+	sector_t last = ad->last_sector[ad->batch_data_dir];
+	sector_t next = arq->request->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) * 1000) / HZ;
+
+	if (delay == 0)
+		delta = 8192;
+	else if (delay <= 20 && 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 as_rq *arq)
+{
+	struct io_context *ioc;
+	struct as_io_context *aic;
+
+	ioc = ad->io_context;
+	BUG_ON(!ioc);
+
+	if (arq && ioc == arq->io_context) {
+		/* request from same process */
+		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.
+		 */
+		return 1;
+	}
+
+	aic = ioc->aic;
+	if (!aic)
+		return 0;
+
+	if (atomic_read(&aic->nr_queued) > 0) {
+		/* process has more requests queued */
+		return 1;
+	}
+
+	if (atomic_read(&aic->nr_dispatched) > 0) {
+		/* process has more requests dispatched */
+		return 1;
+	}
+
+	if (arq && arq->is_sync == REQ_SYNC && as_close_req(ad, aic, arq)) {
+		/*
+		 * 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, arq->request);
+		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)
+			return 1;
+	}
+
+	if (aic->ttime_samples == 0) {
+		if (ad->new_ttime_mean > ad->antic_expire)
+			return 1;
+		if (ad->exit_prob * ad->exit_no_coop > 128*256)
+			return 1;
+	} else if (aic->ttime_mean > ad->antic_expire) {
+		/* the process thinks too much between requests */
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * as_can_anticipate indicates weather we should either run arq
+ * or keep anticipating a better request.
+ */
+static int as_can_anticipate(struct as_data *ad, struct as_rq *arq)
+{
+	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, arq))
+		/*
+		 * 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_arq must be called whenever a request (arq) 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_arq(struct as_data *ad, struct as_rq *arq)
+{
+	const int data_dir = arq->is_sync;
+
+	/* keep the next_arq cache up to date */
+	ad->next_arq[data_dir] = as_choose_req(ad, arq, ad->next_arq[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, arq))
+			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[REQ_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(request_queue_t *q, struct request *rq)
+{
+	struct as_data *ad = q->elevator->elevator_data;
+	struct as_rq *arq = RQ_DATA(rq);
+
+	WARN_ON(!list_empty(&rq->queuelist));
+
+	if (arq->state != AS_RQ_REMOVED) {
+		printk("arq->state %d\n", arq->state);
+		WARN_ON(1);
+		goto out;
+	}
+
+	if (ad->changed_batch && ad->nr_dispatched == 1) {
+		kblockd_schedule_work(&ad->antic_work);