Eric Lee / linux-smarc-t335x-v3.2

Browse Code »

Commit e572ec7e4e432de7ecf7bd2e62117646fa64e518

Authored by Al Viro 2006-03-19 11:27:18 +0800

1 parent 3d1ab40f4c

Exists in master and in 4 other branches

[PATCH] fix rmmod problems with elevator attributes, clean them up

Showing 5 changed files with 74 additions and 175 deletions Inline Diff

block/as-iosched.c
block/cfq-iosched.c
block/deadline-iosched.c
block/elevator.c
include/linux/elevator.h

block/as-iosched.c

Diff comments View file @ e572ec7

 /*
  *  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;
 static atomic_t ioc_count = ATOMIC_INIT(0);
 static struct completion *ioc_gone;
 static void as_move_to_dispatch(struct as_data *ad, struct as_rq *arq);
 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);
 	if (atomic_dec_and_test(&ioc_count) && ioc_gone)
 		complete(ioc_gone);
 }
 static void as_trim(struct io_context *ioc)
 {
 	if (ioc->aic)
 		free_as_io_context(ioc->aic);
 	ioc->aic = NULL;
 }
 /* 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;
 		atomic_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(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 void as_add_arq_rb(struct as_data *ad, struct as_rq *arq)
 {
 	struct as_rq *alias;
 	while ((unlikely(alias = __as_add_arq_rb(ad, arq)))) {
 		as_move_to_dispatch(ad, alias);
 		as_antic_stop(ad);
 	}
 }
 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);
 		ad->changed_batch = 0;
 		if (ad->batch_data_dir == REQ_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 == arq->is_sync) {
 		update_write_batch(ad);
 		ad->current_batch_expires = jiffies +
 				ad->batch_expire[REQ_SYNC];
 		ad->new_batch = 0;
 	}
 	if (ad->io_context == arq->io_context && 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(arq);
 out:
 	arq->state = 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(request_queue_t *q, struct request *rq)
 {
 	struct as_rq *arq = RQ_DATA(rq);
 	const int data_dir = arq->is_sync;
 	struct as_data *ad = q->elevator->elevator_data;
 	WARN_ON(arq->state != AS_RQ_QUEUED);
 	if (arq->io_context && arq->io_context->aic) {
 		BUG_ON(!atomic_read(&arq->io_context->aic->nr_queued));
 		atomic_dec(&arq->io_context->aic->nr_queued);
 	}
 	/*
 	 * Update the "next_arq" cache if we are about to remove its
 	 * entry
 	 */
 	if (ad->next_arq[data_dir] == arq)
 		ad->next_arq[data_dir] = as_find_next_arq(ad, arq);
 	list_del_init(&arq->fifo);
 	as_del_arq_hash(arq);
 	as_del_arq_rb(ad, arq);
 }
 /*
  * as_fifo_expired returns 0 if there are no expired reads 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 as_rq *arq;
 	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;
 	arq = list_entry_fifo(ad->fifo_list[adir].next);
 	return time_after(jiffies, arq->expires);
 }
 /*
  * 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 == REQ_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 as_rq *arq)
 {
 	struct request *rq = arq->request;
 	const int data_dir = arq->is_sync;
 	BUG_ON(!ON_RB(&arq->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_arq
 	 */
 	ad->last_sector[data_dir] = rq->sector + rq->nr_sectors;
 	if (data_dir == REQ_SYNC) {
 		/* In case we have to anticipate after this */
 		copy_io_context(&ad->io_context, &arq->io_context);
 	} 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_arq[data_dir] = as_find_next_arq(ad, arq);
 	/*
 	 * take it off the sort and fifo list, add to dispatch queue
 	 */
 	as_remove_queued_request(ad->q, rq);
 	WARN_ON(arq->state != AS_RQ_QUEUED);
 	elv_dispatch_sort(ad->q, rq);
 	arq->state = AS_RQ_DISPATCHED;
 	if (arq->io_context && arq->io_context->aic)
 		atomic_inc(&arq->io_context->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(request_queue_t *q, int force)
 {
 	struct as_data *ad = q->elevator->elevator_data;
 	struct as_rq *arq;
 	const int reads = !list_empty(&ad->fifo_list[REQ_SYNC]);
 	const int writes = !list_empty(&ad->fifo_list[REQ_ASYNC]);
 	if (unlikely(force)) {
 		/*
 		 * Forced dispatch, accounting is useless.  Reset
 		 * accounting states and dump fifo_lists.  Note that
 		 * batch_data_dir is reset to REQ_SYNC to avoid
 		 * screwing write batch accounting as write batch
 		 * accounting occurs on W->R transition.
 		 */
 		int dispatched = 0;
 		ad->batch_data_dir = REQ_SYNC;
 		ad->changed_batch = 0;
 		ad->new_batch = 0;
 		while (ad->next_arq[REQ_SYNC]) {
 			as_move_to_dispatch(ad, ad->next_arq[REQ_SYNC]);
 			dispatched++;
 		}
 		ad->last_check_fifo[REQ_SYNC] = jiffies;
 		while (ad->next_arq[REQ_ASYNC]) {
 			as_move_to_dispatch(ad, ad->next_arq[REQ_ASYNC]);
 			dispatched++;
 		}
 		ad->last_check_fifo[REQ_ASYNC] = jiffies;
 		return dispatched;
 	}
 	/* Signal that the write batch was uncontended, so we can't time it */
 	if (ad->batch_data_dir == REQ_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
 		 */
 		arq = ad->next_arq[ad->batch_data_dir];
 		if (ad->batch_data_dir == REQ_SYNC && ad->antic_expire) {
 			if (as_fifo_expired(ad, REQ_SYNC))
 				goto fifo_expired;
 			if (as_can_anticipate(ad, arq)) {
 				as_antic_waitreq(ad);
 				return 0;
 			}
 		}
 		if (arq) {
 			/* we have a "next request" */
 			if (reads && !writes)
 				ad->current_batch_expires =
 					jiffies + ad->batch_expire[REQ_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(&ad->sort_list[REQ_SYNC]));
 		if (writes && ad->batch_data_dir == REQ_SYNC)
 			/*
 			 * Last batch was a read, switch to writes
 			 */
 			goto dispatch_writes;
 		if (ad->batch_data_dir == REQ_ASYNC) {
 			WARN_ON(ad->new_batch);
 			ad->changed_batch = 1;
 		}
 		ad->batch_data_dir = REQ_SYNC;
 		arq = list_entry_fifo(ad->fifo_list[ad->batch_data_dir].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(&ad->sort_list[REQ_ASYNC]));
 		if (ad->batch_data_dir == REQ_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 = REQ_ASYNC;
 		ad->current_write_count = ad->write_batch_count;
 		ad->write_batch_idled = 0;
 		arq = ad->next_arq[ad->batch_data_dir];
 		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:
 		arq = list_entry_fifo(ad->fifo_list[ad->batch_data_dir].next);
 		BUG_ON(arq == NULL);
 	}
 	if (ad->changed_batch) {
 		WARN_ON(ad->new_batch);
 		if (ad->nr_dispatched)
 			return 0;
 		if (ad->batch_data_dir == REQ_ASYNC)
 			ad->current_batch_expires = jiffies +
 					ad->batch_expire[REQ_ASYNC];
 		else
 			ad->new_batch = 1;
 		ad->changed_batch = 0;
 	}
 	/*
 	 * arq is the selected appropriate request.
 	 */
 	as_move_to_dispatch(ad, arq);
 	return 1;
 }
 /*
  * add arq to rbtree and fifo
  */
 static void as_add_request(request_queue_t *q, struct request *rq)
 {
 	struct as_data *ad = q->elevator->elevator_data;
 	struct as_rq *arq = RQ_DATA(rq);
 	int data_dir;
 	arq->state = AS_RQ_NEW;
 	if (rq_data_dir(arq->request) == READ
 			|| current->flags&PF_SYNCWRITE)
 		arq->is_sync = 1;
 	else
 		arq->is_sync = 0;
 	data_dir = arq->is_sync;
 	arq->io_context = as_get_io_context();
 	if (arq->io_context) {
 		as_update_iohist(ad, arq->io_context->aic, arq->request);
 		atomic_inc(&arq->io_context->aic->nr_queued);
 	}
 	as_add_arq_rb(ad, arq);
 	if (rq_mergeable(arq->request))
 		as_add_arq_hash(ad, arq);
 	/*
 	 * set expire time (only used for reads) and add to fifo list
 	 */
 	arq->expires = jiffies + ad->fifo_expire[data_dir];
 	list_add_tail(&arq->fifo, &ad->fifo_list[data_dir]);
 	as_update_arq(ad, arq); /* keep state machine up to date */
 	arq->state = AS_RQ_QUEUED;
 }
 static void as_activate_request(request_queue_t *q, struct request *rq)
 {
 	struct as_rq *arq = RQ_DATA(rq);
 	WARN_ON(arq->state != AS_RQ_DISPATCHED);
 	arq->state = AS_RQ_REMOVED;
 	if (arq->io_context && arq->io_context->aic)
 		atomic_dec(&arq->io_context->aic->nr_dispatched);
 }
 static void as_deactivate_request(request_queue_t *q, struct request *rq)
 {
 	struct as_rq *arq = RQ_DATA(rq);
 	WARN_ON(arq->state != AS_RQ_REMOVED);
 	arq->state = AS_RQ_DISPATCHED;
 	if (arq->io_context && arq->io_context->aic)
 		atomic_inc(&arq->io_context->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(request_queue_t *q)
 {
 	struct as_data *ad = q->elevator->elevator_data;
 	return list_empty(&ad->fifo_list[REQ_ASYNC])
 		&& list_empty(&ad->fifo_list[REQ_SYNC]);
 }
 static struct request *as_former_request(request_queue_t *q,
 					struct request *rq)
 {
 	struct as_rq *arq = RQ_DATA(rq);
 	struct rb_node *rbprev = rb_prev(&arq->rb_node);
 	struct request *ret = NULL;
 	if (rbprev)
 		ret = rb_entry_arq(rbprev)->request;
 	return ret;
 }
 static struct request *as_latter_request(request_queue_t *q,
 					struct request *rq)
 {
 	struct as_rq *arq = RQ_DATA(rq);
 	struct rb_node *rbnext = rb_next(&arq->rb_node);
 	struct request *ret = NULL;
 	if (rbnext)
 		ret = rb_entry_arq(rbnext)->request;
 	return ret;
 }
 static int
 as_merge(request_queue_t *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;
 	int ret;
 	/*
 	 * see if the merge hash can satisfy a back merge
 	 */
 	__rq = as_find_arq_hash(ad, bio->bi_sector);
 	if (__rq) {
 		BUG_ON(__rq->sector + __rq->nr_sectors != bio->bi_sector);
 		if (elv_rq_merge_ok(__rq, bio)) {
 			ret = ELEVATOR_BACK_MERGE;
 			goto out;
 		}
 	}
 	/*
 	 * check for front merge
 	 */
 	__rq = as_find_arq_rb(ad, rb_key, bio_data_dir(bio));
 	if (__rq) {
 		BUG_ON(rb_key != rq_rb_key(__rq));
 		if (elv_rq_merge_ok(__rq, bio)) {
 			ret = ELEVATOR_FRONT_MERGE;
 			goto out;
 		}
 	}
 	return ELEVATOR_NO_MERGE;
 out:
 	if (ret) {
 		if (rq_mergeable(__rq))
 			as_hot_arq_hash(ad, RQ_DATA(__rq));
 	}
 	*req = __rq;
 	return ret;
 }
 static void as_merged_request(request_queue_t *q, struct request *req)
 {
 	struct as_data *ad = q->elevator->elevator_data;
 	struct as_rq *arq = RQ_DATA(req);
 	/*
 	 * hash always needs to be repositioned, key is end sector
 	 */
 	as_del_arq_hash(arq);
 	as_add_arq_hash(ad, arq);
 	/*
 	 * if the merge was a front merge, we need to reposition request
 	 */
 	if (rq_rb_key(req) != arq->rb_key) {
 		as_del_arq_rb(ad, arq);
 		as_add_arq_rb(ad, arq);
 		/*
 		 * 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(request_queue_t *q, struct request *req,
 			 	struct request *next)
 {
 	struct as_data *ad = q->elevator->elevator_data;
 	struct as_rq *arq = RQ_DATA(req);
 	struct as_rq *anext = RQ_DATA(next);
 	BUG_ON(!arq);
 	BUG_ON(!anext);
 	/*
 	 * reposition arq (this is the merged request) in hash, and in rbtree
 	 * in case of a front merge
 	 */
 	as_del_arq_hash(arq);
 	as_add_arq_hash(ad, arq);
 	if (rq_rb_key(req) != arq->rb_key) {
 		as_del_arq_rb(ad, arq);
 		as_add_arq_rb(ad, arq);
 	}
 	/*
 	 * if anext expires before arq, assign its expire time to arq
 	 * and move into anext position (anext will be deleted) in fifo
 	 */
 	if (!list_empty(&arq->fifo) && !list_empty(&anext->fifo)) {
 		if (time_before(anext->expires, arq->expires)) {
 			list_move(&arq->fifo, &anext->fifo);
 			arq->expires = anext->expires;
 			/*
 			 * Don't copy here but swap, because when anext is
 			 * removed below, it must contain the unused context
 			 */
 			swap_io_context(&arq->io_context, &anext->io_context);
 		}
 	}
 	/*
 	 * kill knowledge of next, this one is a goner
 	 */
 	as_remove_queued_request(q, next);
 	as_put_io_context(anext);
 	anext->state = 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(void *data)
 {
 	struct request_queue *q = data;
 	unsigned long flags;
 	spin_lock_irqsave(q->queue_lock, flags);
 	if (!as_queue_empty(q))
 		q->request_fn(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 static void as_put_request(request_queue_t *q, struct request *rq)
 {
 	struct as_data *ad = q->elevator->elevator_data;
 	struct as_rq *arq = RQ_DATA(rq);
 	if (!arq) {
 		WARN_ON(1);
 		return;
 	}
 	if (unlikely(arq->state != AS_RQ_POSTSCHED &&
 		     arq->state != AS_RQ_PRESCHED &&
 		     arq->state != AS_RQ_MERGED)) {
 		printk("arq->state %d\n", arq->state);
 		WARN_ON(1);
 	}
 	mempool_free(arq, ad->arq_pool);
 	rq->elevator_private = NULL;
 }
 static int as_set_request(request_queue_t *q, struct request *rq,
 			  struct bio *bio, gfp_t gfp_mask)
 {
 	struct as_data *ad = q->elevator->elevator_data;
 	struct as_rq *arq = mempool_alloc(ad->arq_pool, gfp_mask);
 	if (arq) {
 		memset(arq, 0, sizeof(*arq));
 		RB_CLEAR(&arq->rb_node);
 		arq->request = rq;
 		arq->state = AS_RQ_PRESCHED;
 		arq->io_context = NULL;
 		INIT_LIST_HEAD(&arq->hash);
 		arq->on_hash = 0;
 		INIT_LIST_HEAD(&arq->fifo);
 		rq->elevator_private = arq;
 		return 0;
 	}
 	return 1;
 }
 static int as_may_queue(request_queue_t *q, int rw, struct bio *bio)
 {
 	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();
 		if (ad->io_context == ioc)
 			ret = ELV_MQUEUE_MUST;
 		put_io_context(ioc);
 	}
 	return ret;
 }
 static void as_exit_queue(elevator_t *e)
 {
 	struct as_data *ad = e->elevator_data;
 	del_timer_sync(&ad->antic_timer);
 	kblockd_flush();
 	BUG_ON(!list_empty(&ad->fifo_list[REQ_SYNC]));
 	BUG_ON(!list_empty(&ad->fifo_list[REQ_ASYNC]));
 	mempool_destroy(ad->arq_pool);
 	put_io_context(ad->io_context);
 	kfree(ad->hash);
 	kfree(ad);
 }
 /*
  * initialize elevator private data (as_data), and alloc a arq for
  * each request on the free lists
  */
 static int as_init_queue(request_queue_t *q, elevator_t *e)
 {
 	struct as_data *ad;
 	int i;
 	if (!arq_pool)
 		return -ENOMEM;
 	ad = kmalloc_node(sizeof(*ad), GFP_KERNEL, q->node);
 	if (!ad)
 		return -ENOMEM;
 	memset(ad, 0, sizeof(*ad));
 	ad->q = q; /* Identify what queue the data belongs to */
 	ad->hash = kmalloc_node(sizeof(struct list_head)*AS_HASH_ENTRIES,
 				GFP_KERNEL, q->node);
 	if (!ad->hash) {
 		kfree(ad);
 		return -ENOMEM;
 	}
 	ad->arq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
 				mempool_free_slab, arq_pool, q->node);
 	if (!ad->arq_pool) {
 		kfree(ad->hash);
 		kfree(ad);
 		return -ENOMEM;
 	}
 	/* 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, q);
 	for (i = 0; i < AS_HASH_ENTRIES; i++)
 		INIT_LIST_HEAD(&ad->hash[i]);
 	INIT_LIST_HEAD(&ad->fifo_list[REQ_SYNC]);
 	INIT_LIST_HEAD(&ad->fifo_list[REQ_ASYNC]);
 	ad->sort_list[REQ_SYNC] = RB_ROOT;
 	ad->sort_list[REQ_ASYNC] = RB_ROOT;
 	ad->fifo_expire[REQ_SYNC] = default_read_expire;
 	ad->fifo_expire[REQ_ASYNC] = default_write_expire;
 	ad->antic_expire = default_antic_expire;
 	ad->batch_expire[REQ_SYNC] = default_read_batch_expire;
 	ad->batch_expire[REQ_ASYNC] = default_write_batch_expire;
 	e->elevator_data = ad;
 	ad->current_batch_expires = jiffies + ad->batch_expire[REQ_SYNC];
 	ad->write_batch_count = ad->batch_expire[REQ_ASYNC] / 10;
 	if (ad->write_batch_count < 2)
 		ad->write_batch_count = 2;
 	return 0;
 }
 /*
  * 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 as_est_show(elevator_t *e, char *page)
+static ssize_t est_time_show(elevator_t *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(elevator_t *e, char *page)		\
 {								\
 	struct as_data *ad = e->elevator_data;			\
 	return as_var_show(jiffies_to_msecs((__VAR)), (page));	\
 }
-SHOW_FUNCTION(as_readexpire_show, ad->fifo_expire[REQ_SYNC]);
+SHOW_FUNCTION(as_read_expire_show, ad->fifo_expire[REQ_SYNC]);
-SHOW_FUNCTION(as_writeexpire_show, ad->fifo_expire[REQ_ASYNC]);
+SHOW_FUNCTION(as_write_expire_show, ad->fifo_expire[REQ_ASYNC]);
-SHOW_FUNCTION(as_anticexpire_show, ad->antic_expire);
+SHOW_FUNCTION(as_antic_expire_show, ad->antic_expire);
-SHOW_FUNCTION(as_read_batchexpire_show, ad->batch_expire[REQ_SYNC]);
+SHOW_FUNCTION(as_read_batch_expire_show, ad->batch_expire[REQ_SYNC]);
-SHOW_FUNCTION(as_write_batchexpire_show, ad->batch_expire[REQ_ASYNC]);
+SHOW_FUNCTION(as_write_batch_expire_show, ad->batch_expire[REQ_ASYNC]);
 #undef SHOW_FUNCTION
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)				\
 static ssize_t __FUNC(elevator_t *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_readexpire_store, &ad->fifo_expire[REQ_SYNC], 0, INT_MAX);
+STORE_FUNCTION(as_read_expire_store, &ad->fifo_expire[REQ_SYNC], 0, INT_MAX);
-STORE_FUNCTION(as_writeexpire_store, &ad->fifo_expire[REQ_ASYNC], 0, INT_MAX);
+STORE_FUNCTION(as_write_expire_store, &ad->fifo_expire[REQ_ASYNC], 0, INT_MAX);
-STORE_FUNCTION(as_anticexpire_store, &ad->antic_expire, 0, INT_MAX);
+STORE_FUNCTION(as_antic_expire_store, &ad->antic_expire, 0, INT_MAX);
-STORE_FUNCTION(as_read_batchexpire_store,
+STORE_FUNCTION(as_read_batch_expire_store,
 			&ad->batch_expire[REQ_SYNC], 0, INT_MAX);
-STORE_FUNCTION(as_write_batchexpire_store,
+STORE_FUNCTION(as_write_batch_expire_store,
 			&ad->batch_expire[REQ_ASYNC], 0, INT_MAX);
 #undef STORE_FUNCTION
-static struct elv_fs_entry as_est_entry = {
+#define AS_ATTR(name) \
-	.attr = {.name = "est_time", .mode = S_IRUGO },
+	__ATTR(name, S_IRUGO|S_IWUSR, as_##name##_show, as_##name##_store)
-	.show = as_est_show,
-};
-static struct elv_fs_entry as_readexpire_entry = {
-	.attr = {.name = "read_expire", .mode = S_IRUGO | S_IWUSR },
-	.show = as_readexpire_show,
-	.store = as_readexpire_store,
-};
-static struct elv_fs_entry as_writeexpire_entry = {
-	.attr = {.name = "write_expire", .mode = S_IRUGO | S_IWUSR },
-	.show = as_writeexpire_show,
-	.store = as_writeexpire_store,
-};
-static struct elv_fs_entry as_anticexpire_entry = {
-	.attr = {.name = "antic_expire", .mode = S_IRUGO | S_IWUSR },
-	.show = as_anticexpire_show,
-	.store = as_anticexpire_store,
-};
-static struct elv_fs_entry as_read_batchexpire_entry = {
-	.attr = {.name = "read_batch_expire", .mode = S_IRUGO | S_IWUSR },
-	.show = as_read_batchexpire_show,
-	.store = as_read_batchexpire_store,
-};
-static struct elv_fs_entry as_write_batchexpire_entry = {
-	.attr = {.name = "write_batch_expire", .mode = S_IRUGO | S_IWUSR },
-	.show = as_write_batchexpire_show,
-	.store = as_write_batchexpire_store,
-};
-static struct attribute *as_attrs[] = {
+static struct elv_fs_entry as_attrs[] = {
-	&as_est_entry.attr,
+	__ATTR_RO(est_time),
-	&as_readexpire_entry.attr,
+	AS_ATTR(read_expire),
-	&as_writeexpire_entry.attr,
+	AS_ATTR(write_expire),
-	&as_anticexpire_entry.attr,
+	AS_ATTR(antic_expire),
-	&as_read_batchexpire_entry.attr,
+	AS_ATTR(read_batch_expire),
-	&as_write_batchexpire_entry.attr,
+	AS_ATTR(write_batch_expire),
-	NULL,
+	__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 =	as_former_request,
 		.elevator_latter_req_fn =	as_latter_request,
 		.elevator_set_req_fn =		as_set_request,
 		.elevator_put_req_fn =		as_put_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)
 {
 	int ret;
 	arq_pool = kmem_cache_create("as_arq", sizeof(struct as_rq),
 				     0, 0, NULL, NULL);
 	if (!arq_pool)
 		return -ENOMEM;
 	ret = elv_register(&iosched_as);
 	if (!ret) {
 		/*
 		 * don't allow AS to get unregistered, since we would have
 		 * to browse all tasks in the system and release their
 		 * as_io_context first
 		 */
 		__module_get(THIS_MODULE);
 		return 0;
 	}
 	kmem_cache_destroy(arq_pool);
 	return ret;
 }
 static void __exit as_exit(void)
 {
 	DECLARE_COMPLETION(all_gone);
 	elv_unregister(&iosched_as);
 	ioc_gone = &all_gone;
 	barrier();
 	if (atomic_read(&ioc_count))
 		complete(ioc_gone);
 	synchronize_rcu();
 	kmem_cache_destroy(arq_pool);
 }
 module_init(as_init);
 module_exit(as_exit);
 MODULE_AUTHOR("Nick Piggin");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("anticipatory IO scheduler");

block/cfq-iosched.c

Diff comments View file @ e572ec7

 /*
  *  CFQ, or complete fairness queueing, disk scheduler.
  *
  *  Based on ideas from a previously unfinished io
  *  scheduler (round robin per-process disk scheduling) and Andrea Arcangeli.
  *
  *  Copyright (C) 2003 Jens Axboe <axboe@suse.de>
  */
 #include <linux/config.h>
 #include <linux/module.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
 #include <linux/hash.h>
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
 /*
  * tunables
  */
 static const int cfq_quantum = 4;		/* max queue in one round of service */
 static const int cfq_queued = 8;		/* minimum rq allocate limit per-queue*/
 static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
 static const int cfq_back_max = 16 * 1024;	/* maximum backwards seek, in KiB */
 static const int cfq_back_penalty = 2;		/* penalty of a backwards seek */
 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 / 100;
 #define CFQ_IDLE_GRACE		(HZ / 10)
 #define CFQ_SLICE_SCALE		(5)
 #define CFQ_KEY_ASYNC		(0)
 #define CFQ_KEY_ANY		(0xffff)
 /*
  * disable queueing at the driver/hardware level
  */
 static const int cfq_max_depth = 2;
 static DEFINE_RWLOCK(cfq_exit_lock);
 /*
  * for the hash of cfqq inside the cfqd
  */
 #define CFQ_QHASH_SHIFT		6
 #define CFQ_QHASH_ENTRIES	(1 << CFQ_QHASH_SHIFT)
 #define list_entry_qhash(entry)	hlist_entry((entry), struct cfq_queue, cfq_hash)
 /*
  * for the hash of crq inside the cfqq
  */
 #define CFQ_MHASH_SHIFT		6
 #define CFQ_MHASH_BLOCK(sec)	((sec) >> 3)
 #define CFQ_MHASH_ENTRIES	(1 << CFQ_MHASH_SHIFT)
 #define CFQ_MHASH_FN(sec)	hash_long(CFQ_MHASH_BLOCK(sec), CFQ_MHASH_SHIFT)
 #define rq_hash_key(rq)		((rq)->sector + (rq)->nr_sectors)
 #define list_entry_hash(ptr)	hlist_entry((ptr), struct cfq_rq, hash)
 #define list_entry_cfqq(ptr)	list_entry((ptr), struct cfq_queue, cfq_list)
 #define list_entry_fifo(ptr)	list_entry((ptr), struct request, queuelist)
 #define RQ_DATA(rq)		(rq)->elevator_private
 /*
  * rb-tree defines
  */
 #define RB_NONE			(2)
 #define RB_EMPTY(node)		((node)->rb_node == NULL)
 #define RB_CLEAR_COLOR(node)	(node)->rb_color = RB_NONE
 #define RB_CLEAR(node)		do {	\
 	(node)->rb_parent = NULL;	\
 	RB_CLEAR_COLOR((node));		\
 	(node)->rb_right = NULL;	\
 	(node)->rb_left = NULL;		\
 } while (0)
 #define RB_CLEAR_ROOT(root)	((root)->rb_node = NULL)
 #define rb_entry_crq(node)	rb_entry((node), struct cfq_rq, rb_node)
 #define rq_rb_key(rq)		(rq)->sector
 static kmem_cache_t *crq_pool;
 static kmem_cache_t *cfq_pool;
 static kmem_cache_t *cfq_ioc_pool;
 static atomic_t ioc_count = ATOMIC_INIT(0);
 static struct completion *ioc_gone;
 #define CFQ_PRIO_LISTS		IOPRIO_BE_NR
 #define cfq_class_idle(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
 #define cfq_class_be(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_BE)
 #define cfq_class_rt(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
 #define ASYNC			(0)
 #define SYNC			(1)
 #define cfq_cfqq_dispatched(cfqq)	\
 	((cfqq)->on_dispatch[ASYNC] + (cfqq)->on_dispatch[SYNC])
 #define cfq_cfqq_class_sync(cfqq)	((cfqq)->key != CFQ_KEY_ASYNC)
 #define cfq_cfqq_sync(cfqq)		\
 	(cfq_cfqq_class_sync(cfqq) || (cfqq)->on_dispatch[SYNC])
 /*
  * Per block device queue structure
  */
 struct cfq_data {
 	request_queue_t *queue;
 	/*
 	 * rr list of queues with requests and the count of them
 	 */
 	struct list_head rr_list[CFQ_PRIO_LISTS];
 	struct list_head busy_rr;
 	struct list_head cur_rr;
 	struct list_head idle_rr;
 	unsigned int busy_queues;
 	/*
 	 * non-ordered list of empty cfqq's
 	 */
 	struct list_head empty_list;
 	/*
 	 * cfqq lookup hash
 	 */
 	struct hlist_head *cfq_hash;
 	/*
 	 * global crq hash for all queues
 	 */
 	struct hlist_head *crq_hash;
 	unsigned int max_queued;
 	mempool_t *crq_pool;
 	int rq_in_driver;
 	/*
 	 * schedule slice state info
 	 */
 	/*
 	 * idle window management
 	 */
 	struct timer_list idle_slice_timer;
 	struct work_struct unplug_work;
 	struct cfq_queue *active_queue;
 	struct cfq_io_context *active_cic;
 	int cur_prio, cur_end_prio;
 	unsigned int dispatch_slice;
 	struct timer_list idle_class_timer;
 	sector_t last_sector;
 	unsigned long last_end_request;
 	unsigned int rq_starved;
 	/*
 	 * tunables, see top of file
 	 */
 	unsigned int cfq_quantum;
 	unsigned int cfq_queued;
 	unsigned int cfq_fifo_expire[2];
 	unsigned int cfq_back_penalty;
 	unsigned int cfq_back_max;
 	unsigned int cfq_slice[2];
 	unsigned int cfq_slice_async_rq;
 	unsigned int cfq_slice_idle;
 	unsigned int cfq_max_depth;
 	struct list_head cic_list;
 };
 /*
  * Per process-grouping structure
  */
 struct cfq_queue {
 	/* reference count */
 	atomic_t ref;
 	/* parent cfq_data */
 	struct cfq_data *cfqd;
 	/* cfqq lookup hash */
 	struct hlist_node cfq_hash;
 	/* hash key */
 	unsigned int key;
 	/* on either rr or empty list of cfqd */
 	struct list_head cfq_list;
 	/* sorted list of pending requests */
 	struct rb_root sort_list;
 	/* if fifo isn't expired, next request to serve */
 	struct cfq_rq *next_crq;
 	/* requests queued in sort_list */
 	int queued[2];
 	/* currently allocated requests */
 	int allocated[2];
 	/* fifo list of requests in sort_list */
 	struct list_head fifo;
 	unsigned long slice_start;
 	unsigned long slice_end;
 	unsigned long slice_left;
 	unsigned long service_last;
 	/* number of requests that are on the dispatch list */
 	int on_dispatch[2];
 	/* io prio of this group */
 	unsigned short ioprio, org_ioprio;
 	unsigned short ioprio_class, org_ioprio_class;
 	/* various state flags, see below */
 	unsigned int flags;
 };
 struct cfq_rq {
 	struct rb_node rb_node;
 	sector_t rb_key;
 	struct request *request;
 	struct hlist_node hash;
 	struct cfq_queue *cfq_queue;
 	struct cfq_io_context *io_context;
 	unsigned int crq_flags;
 };
 enum cfqq_state_flags {
 	CFQ_CFQQ_FLAG_on_rr = 0,
 	CFQ_CFQQ_FLAG_wait_request,
 	CFQ_CFQQ_FLAG_must_alloc,
 	CFQ_CFQQ_FLAG_must_alloc_slice,
 	CFQ_CFQQ_FLAG_must_dispatch,
 	CFQ_CFQQ_FLAG_fifo_expire,
 	CFQ_CFQQ_FLAG_idle_window,
 	CFQ_CFQQ_FLAG_prio_changed,
 };
 #define CFQ_CFQQ_FNS(name)						\
 static inline void cfq_mark_cfqq_##name(struct cfq_queue *cfqq)		\
 {									\
 	cfqq->flags |= (1 << CFQ_CFQQ_FLAG_##name);			\
 }									\
 static inline void cfq_clear_cfqq_##name(struct cfq_queue *cfqq)	\
 {									\
 	cfqq->flags &= ~(1 << CFQ_CFQQ_FLAG_##name);			\
 }									\
 static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq)		\
 {									\
 	return (cfqq->flags & (1 << CFQ_CFQQ_FLAG_##name)) != 0;	\
 }
 CFQ_CFQQ_FNS(on_rr);
 CFQ_CFQQ_FNS(wait_request);
 CFQ_CFQQ_FNS(must_alloc);
 CFQ_CFQQ_FNS(must_alloc_slice);
 CFQ_CFQQ_FNS(must_dispatch);
 CFQ_CFQQ_FNS(fifo_expire);
 CFQ_CFQQ_FNS(idle_window);
 CFQ_CFQQ_FNS(prio_changed);
 #undef CFQ_CFQQ_FNS
 enum cfq_rq_state_flags {
 	CFQ_CRQ_FLAG_is_sync = 0,
 };
 #define CFQ_CRQ_FNS(name)						\
 static inline void cfq_mark_crq_##name(struct cfq_rq *crq)		\
 {									\
 	crq->crq_flags |= (1 << CFQ_CRQ_FLAG_##name);			\
 }									\
 static inline void cfq_clear_crq_##name(struct cfq_rq *crq)		\
 {									\
 	crq->crq_flags &= ~(1 << CFQ_CRQ_FLAG_##name);			\
 }									\
 static inline int cfq_crq_##name(const struct cfq_rq *crq)		\
 {									\
 	return (crq->crq_flags & (1 << CFQ_CRQ_FLAG_##name)) != 0;	\
 }
 CFQ_CRQ_FNS(is_sync);
 #undef CFQ_CRQ_FNS
 static struct cfq_queue *cfq_find_cfq_hash(struct cfq_data *, unsigned int, unsigned short);
 static void cfq_dispatch_insert(request_queue_t *, struct cfq_rq *);
 static struct cfq_queue *cfq_get_queue(struct cfq_data *cfqd, unsigned int key, struct task_struct *tsk, gfp_t gfp_mask);
 #define process_sync(tsk)	((tsk)->flags & PF_SYNCWRITE)
 /*
  * lots of deadline iosched dupes, can be abstracted later...
  */
 static inline void cfq_del_crq_hash(struct cfq_rq *crq)
 {
 	hlist_del_init(&crq->hash);
 }
 static inline void cfq_add_crq_hash(struct cfq_data *cfqd, struct cfq_rq *crq)
 {
 	const int hash_idx = CFQ_MHASH_FN(rq_hash_key(crq->request));
 	hlist_add_head(&crq->hash, &cfqd->crq_hash[hash_idx]);
 }
 static struct request *cfq_find_rq_hash(struct cfq_data *cfqd, sector_t offset)
 {
 	struct hlist_head *hash_list = &cfqd->crq_hash[CFQ_MHASH_FN(offset)];
 	struct hlist_node *entry, *next;
 	hlist_for_each_safe(entry, next, hash_list) {
 		struct cfq_rq *crq = list_entry_hash(entry);
 		struct request *__rq = crq->request;
 		if (!rq_mergeable(__rq)) {
 			cfq_del_crq_hash(crq);
 			continue;
 		}
 		if (rq_hash_key(__rq) == offset)
 			return __rq;
 	}
 	return NULL;
 }
 /*
  * scheduler run of queue, if there are requests pending and no one in the
  * driver that will restart queueing
  */
 static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
 {
 	if (cfqd->busy_queues)
 		kblockd_schedule_work(&cfqd->unplug_work);
 }
 static int cfq_queue_empty(request_queue_t *q)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	return !cfqd->busy_queues;
 }
 /*
  * Lifted from AS - choose which of crq1 and crq2 that is best served now.
  * We choose the request that is closest to the head right now. Distance
  * behind the head are penalized and only allowed to a certain extent.
  */
 static struct cfq_rq *
 cfq_choose_req(struct cfq_data *cfqd, struct cfq_rq *crq1, struct cfq_rq *crq2)
 {
 	sector_t last, s1, s2, d1 = 0, d2 = 0;
 	int r1_wrap = 0, r2_wrap = 0;	/* requests are behind the disk head */
 	unsigned long back_max;
 	if (crq1 == NULL || crq1 == crq2)
 		return crq2;
 	if (crq2 == NULL)
 		return crq1;
 	if (cfq_crq_is_sync(crq1) && !cfq_crq_is_sync(crq2))
 		return crq1;
 	else if (cfq_crq_is_sync(crq2) && !cfq_crq_is_sync(crq1))
 		return crq2;
 	s1 = crq1->request->sector;
 	s2 = crq2->request->sector;
 	last = cfqd->last_sector;
 	/*
 	 * by definition, 1KiB is 2 sectors
 	 */
 	back_max = cfqd->cfq_back_max * 2;
 	/*
 	 * 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 + back_max >= last)
 		d1 = (last - s1) * cfqd->cfq_back_penalty;
 	else
 		r1_wrap = 1;
 	if (s2 >= last)
 		d2 = s2 - last;
 	else if (s2 + back_max >= last)
 		d2 = (last - s2) * cfqd->cfq_back_penalty;
 	else
 		r2_wrap = 1;
 	/* Found required data */
 	if (!r1_wrap && r2_wrap)
 		return crq1;
 	else if (!r2_wrap && r1_wrap)
 		return crq2;
 	else if (r1_wrap && r2_wrap) {
 		/* both behind the head */
 		if (s1 <= s2)
 			return crq1;
 		else
 			return crq2;
 	}
 	/* Both requests in front of the head */
 	if (d1 < d2)
 		return crq1;
 	else if (d2 < d1)
 		return crq2;
 	else {
 		if (s1 >= s2)
 			return crq1;
 		else
 			return crq2;
 	}
 }
 /*
  * would be nice to take fifo expire time into account as well
  */
 static struct cfq_rq *
 cfq_find_next_crq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		  struct cfq_rq *last)
 {
 	struct cfq_rq *crq_next = NULL, *crq_prev = NULL;
 	struct rb_node *rbnext, *rbprev;
 	if (!(rbnext = rb_next(&last->rb_node))) {
 		rbnext = rb_first(&cfqq->sort_list);
 		if (rbnext == &last->rb_node)
 			rbnext = NULL;
 	}
 	rbprev = rb_prev(&last->rb_node);
 	if (rbprev)
 		crq_prev = rb_entry_crq(rbprev);
 	if (rbnext)
 		crq_next = rb_entry_crq(rbnext);
 	return cfq_choose_req(cfqd, crq_next, crq_prev);
 }
 static void cfq_update_next_crq(struct cfq_rq *crq)
 {
 	struct cfq_queue *cfqq = crq->cfq_queue;
 	if (cfqq->next_crq == crq)
 		cfqq->next_crq = cfq_find_next_crq(cfqq->cfqd, cfqq, crq);
 }
 static void cfq_resort_rr_list(struct cfq_queue *cfqq, int preempted)
 {
 	struct cfq_data *cfqd = cfqq->cfqd;
 	struct list_head *list, *entry;
 	BUG_ON(!cfq_cfqq_on_rr(cfqq));
 	list_del(&cfqq->cfq_list);
 	if (cfq_class_rt(cfqq))
 		list = &cfqd->cur_rr;
 	else if (cfq_class_idle(cfqq))
 		list = &cfqd->idle_rr;
 	else {
 		/*
 		 * if cfqq has requests in flight, don't allow it to be
 		 * found in cfq_set_active_queue before it has finished them.
 		 * this is done to increase fairness between a process that
 		 * has lots of io pending vs one that only generates one
 		 * sporadically or synchronously
 		 */
 		if (cfq_cfqq_dispatched(cfqq))
 			list = &cfqd->busy_rr;
 		else
 			list = &cfqd->rr_list[cfqq->ioprio];
 	}
 	/*
 	 * if queue was preempted, just add to front to be fair. busy_rr
 	 * isn't sorted.
 	 */
 	if (preempted || list == &cfqd->busy_rr) {
 		list_add(&cfqq->cfq_list, list);
 		return;
 	}
 	/*
 	 * sort by when queue was last serviced
 	 */
 	entry = list;
 	while ((entry = entry->prev) != list) {
 		struct cfq_queue *__cfqq = list_entry_cfqq(entry);
 		if (!__cfqq->service_last)
 			break;
 		if (time_before(__cfqq->service_last, cfqq->service_last))
 			break;
 	}
 	list_add(&cfqq->cfq_list, entry);
 }
 /*
  * add to busy list of queues for service, trying to be fair in ordering
  * the pending list according to last request service
  */
 static inline 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++;
 	cfq_resort_rr_list(cfqq, 0);
 }
 static inline 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);
 	list_move(&cfqq->cfq_list, &cfqd->empty_list);
 	BUG_ON(!cfqd->busy_queues);
 	cfqd->busy_queues--;
 }
 /*
  * rb tree support functions
  */
 static inline void cfq_del_crq_rb(struct cfq_rq *crq)
 {
 	struct cfq_queue *cfqq = crq->cfq_queue;
 	struct cfq_data *cfqd = cfqq->cfqd;
 	const int sync = cfq_crq_is_sync(crq);
 	BUG_ON(!cfqq->queued[sync]);
 	cfqq->queued[sync]--;
 	cfq_update_next_crq(crq);
 	rb_erase(&crq->rb_node, &cfqq->sort_list);
 	RB_CLEAR_COLOR(&crq->rb_node);
 	if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY(&cfqq->sort_list))
 		cfq_del_cfqq_rr(cfqd, cfqq);
 }
 static struct cfq_rq *
 __cfq_add_crq_rb(struct cfq_rq *crq)
 {
 	struct rb_node **p = &crq->cfq_queue->sort_list.rb_node;
 	struct rb_node *parent = NULL;
 	struct cfq_rq *__crq;
 	while (*p) {
 		parent = *p;
 		__crq = rb_entry_crq(parent);
 		if (crq->rb_key < __crq->rb_key)
 			p = &(*p)->rb_left;
 		else if (crq->rb_key > __crq->rb_key)
 			p = &(*p)->rb_right;
 		else
 			return __crq;
 	}
 	rb_link_node(&crq->rb_node, parent, p);
 	return NULL;
 }
 static void cfq_add_crq_rb(struct cfq_rq *crq)
 {
 	struct cfq_queue *cfqq = crq->cfq_queue;
 	struct cfq_data *cfqd = cfqq->cfqd;
 	struct request *rq = crq->request;
 	struct cfq_rq *__alias;
 	crq->rb_key = rq_rb_key(rq);
 	cfqq->queued[cfq_crq_is_sync(crq)]++;
 	/*
 	 * looks a little odd, but the first insert might return an alias.
 	 * if that happens, put the alias on the dispatch list
 	 */
 	while ((__alias = __cfq_add_crq_rb(crq)) != NULL)
 		cfq_dispatch_insert(cfqd->queue, __alias);
 	rb_insert_color(&crq->rb_node, &cfqq->sort_list);
 	if (!cfq_cfqq_on_rr(cfqq))
 		cfq_add_cfqq_rr(cfqd, cfqq);
 	/*
 	 * check if this request is a better next-serve candidate
 	 */
 	cfqq->next_crq = cfq_choose_req(cfqd, cfqq->next_crq, crq);
 }
 static inline void
 cfq_reposition_crq_rb(struct cfq_queue *cfqq, struct cfq_rq *crq)
 {
 	rb_erase(&crq->rb_node, &cfqq->sort_list);
 	cfqq->queued[cfq_crq_is_sync(crq)]--;
 	cfq_add_crq_rb(crq);
 }
 static struct request *cfq_find_rq_rb(struct cfq_data *cfqd, sector_t sector)
 {
 	struct cfq_queue *cfqq = cfq_find_cfq_hash(cfqd, current->pid, CFQ_KEY_ANY);
 	struct rb_node *n;
 	if (!cfqq)
 		goto out;
 	n = cfqq->sort_list.rb_node;
 	while (n) {
 		struct cfq_rq *crq = rb_entry_crq(n);
 		if (sector < crq->rb_key)
 			n = n->rb_left;
 		else if (sector > crq->rb_key)
 			n = n->rb_right;
 		else
 			return crq->request;
 	}
 out:
 	return NULL;
 }
 static void cfq_activate_request(request_queue_t *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	cfqd->rq_in_driver++;
 }
 static void cfq_deactivate_request(request_queue_t *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	WARN_ON(!cfqd->rq_in_driver);
 	cfqd->rq_in_driver--;
 }
 static void cfq_remove_request(struct request *rq)
 {
 	struct cfq_rq *crq = RQ_DATA(rq);
 	list_del_init(&rq->queuelist);
 	cfq_del_crq_rb(crq);
 	cfq_del_crq_hash(crq);
 }
 static int
 cfq_merge(request_queue_t *q, struct request **req, struct bio *bio)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct request *__rq;
 	int ret;
 	__rq = cfq_find_rq_hash(cfqd, bio->bi_sector);
 	if (__rq && elv_rq_merge_ok(__rq, bio)) {
 		ret = ELEVATOR_BACK_MERGE;
 		goto out;
 	}
 	__rq = cfq_find_rq_rb(cfqd, bio->bi_sector + bio_sectors(bio));
 	if (__rq && elv_rq_merge_ok(__rq, bio)) {
 		ret = ELEVATOR_FRONT_MERGE;
 		goto out;
 	}
 	return ELEVATOR_NO_MERGE;
 out:
 	*req = __rq;
 	return ret;
 }
 static void cfq_merged_request(request_queue_t *q, struct request *req)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_rq *crq = RQ_DATA(req);
 	cfq_del_crq_hash(crq);
 	cfq_add_crq_hash(cfqd, crq);
 	if (rq_rb_key(req) != crq->rb_key) {
 		struct cfq_queue *cfqq = crq->cfq_queue;
 		cfq_update_next_crq(crq);
 		cfq_reposition_crq_rb(cfqq, crq);
 	}
 }
 static void
 cfq_merged_requests(request_queue_t *q, struct request *rq,
 		    struct request *next)
 {
 	cfq_merged_request(q, 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))
 		list_move(&rq->queuelist, &next->queuelist);
 	cfq_remove_request(next);
 }
 static inline void
 __cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	if (cfqq) {
 		/*
 		 * stop potential idle class queues waiting service
 		 */
 		del_timer(&cfqd->idle_class_timer);
 		cfqq->slice_start = jiffies;
 		cfqq->slice_end = 0;
 		cfqq->slice_left = 0;
 		cfq_clear_cfqq_must_alloc_slice(cfqq);
 		cfq_clear_cfqq_fifo_expire(cfqq);
 	}
 	cfqd->active_queue = cfqq;
 }
 /*
  * current cfqq expired its slice (or was too idle), select new one
  */
 static void
 __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		    int preempted)
 {
 	unsigned long now = jiffies;
 	if (cfq_cfqq_wait_request(cfqq))
 		del_timer(&cfqd->idle_slice_timer);
 	if (!preempted && !cfq_cfqq_dispatched(cfqq)) {
 		cfqq->service_last = now;
 		cfq_schedule_dispatch(cfqd);
 	}
 	cfq_clear_cfqq_must_dispatch(cfqq);
 	cfq_clear_cfqq_wait_request(cfqq);
 	/*
 	 * store what was left of this slice, if the queue idled out
 	 * or was preempted
 	 */
 	if (time_after(cfqq->slice_end, now))
 		cfqq->slice_left = cfqq->slice_end - now;
 	else
 		cfqq->slice_left = 0;
 	if (cfq_cfqq_on_rr(cfqq))
 		cfq_resort_rr_list(cfqq, preempted);
 	if (cfqq == cfqd->active_queue)
 		cfqd->active_queue = NULL;
 	if (cfqd->active_cic) {
 		put_io_context(cfqd->active_cic->ioc);
 		cfqd->active_cic = NULL;
 	}
 	cfqd->dispatch_slice = 0;
 }
 static inline void cfq_slice_expired(struct cfq_data *cfqd, int preempted)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 	if (cfqq)
 		__cfq_slice_expired(cfqd, cfqq, preempted);
 }
 /*
  * 0
  * 0,1
  * 0,1,2
  * 0,1,2,3
  * 0,1,2,3,4
  * 0,1,2,3,4,5
  * 0,1,2,3,4,5,6
  * 0,1,2,3,4,5,6,7
  */
 static int cfq_get_next_prio_level(struct cfq_data *cfqd)
 {
 	int prio, wrap;
 	prio = -1;
 	wrap = 0;
 	do {
 		int p;
 		for (p = cfqd->cur_prio; p <= cfqd->cur_end_prio; p++) {
 			if (!list_empty(&cfqd->rr_list[p])) {
 				prio = p;
 				break;
 			}
 		}
 		if (prio != -1)
 			break;
 		cfqd->cur_prio = 0;
 		if (++cfqd->cur_end_prio == CFQ_PRIO_LISTS) {
 			cfqd->cur_end_prio = 0;
 			if (wrap)
 				break;
 			wrap = 1;
 		}
 	} while (1);
 	if (unlikely(prio == -1))
 		return -1;
 	BUG_ON(prio >= CFQ_PRIO_LISTS);
 	list_splice_init(&cfqd->rr_list[prio], &cfqd->cur_rr);
 	cfqd->cur_prio = prio + 1;
 	if (cfqd->cur_prio > cfqd->cur_end_prio) {
 		cfqd->cur_end_prio = cfqd->cur_prio;
 		cfqd->cur_prio = 0;
 	}
 	if (cfqd->cur_end_prio == CFQ_PRIO_LISTS) {
 		cfqd->cur_prio = 0;
 		cfqd->cur_end_prio = 0;
 	}
 	return prio;
 }
 static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq = NULL;
 	/*
 	 * if current list is non-empty, grab first entry. if it is empty,
 	 * get next prio level and grab first entry then if any are spliced
 	 */
 	if (!list_empty(&cfqd->cur_rr) || cfq_get_next_prio_level(cfqd) != -1)
 		cfqq = list_entry_cfqq(cfqd->cur_rr.next);
 	/*
 	 * if we have idle queues and no rt or be queues had pending
 	 * requests, either allow immediate service if the grace period
 	 * has passed or arm the idle grace timer
 	 */
 	if (!cfqq && !list_empty(&cfqd->idle_rr)) {
 		unsigned long end = cfqd->last_end_request + CFQ_IDLE_GRACE;
 		if (time_after_eq(jiffies, end))
 			cfqq = list_entry_cfqq(cfqd->idle_rr.next);
 		else
 			mod_timer(&cfqd->idle_class_timer, end);
 	}
 	__cfq_set_active_queue(cfqd, cfqq);
 	return cfqq;
 }
 static int cfq_arm_slice_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	unsigned long sl;
 	WARN_ON(!RB_EMPTY(&cfqq->sort_list));
 	WARN_ON(cfqq != cfqd->active_queue);
 	/*
 	 * idle is disabled, either manually or by past process history
 	 */
 	if (!cfqd->cfq_slice_idle)
 		return 0;
 	if (!cfq_cfqq_idle_window(cfqq))
 		return 0;
 	/*
 	 * task has exited, don't wait
 	 */
 	if (cfqd->active_cic && !cfqd->active_cic->ioc->task)
 		return 0;
 	cfq_mark_cfqq_must_dispatch(cfqq);
 	cfq_mark_cfqq_wait_request(cfqq);
 	sl = min(cfqq->slice_end - 1, (unsigned long) cfqd->cfq_slice_idle);
 	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
 	return 1;
 }
 static void cfq_dispatch_insert(request_queue_t *q, struct cfq_rq *crq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_queue *cfqq = crq->cfq_queue;
 	cfqq->next_crq = cfq_find_next_crq(cfqd, cfqq, crq);
 	cfq_remove_request(crq->request);
 	cfqq->on_dispatch[cfq_crq_is_sync(crq)]++;
 	elv_dispatch_sort(q, crq->request);
 }
 /*
  * return expired entry, or NULL to just start from scratch in rbtree
  */
 static inline struct cfq_rq *cfq_check_fifo(struct cfq_queue *cfqq)
 {
 	struct cfq_data *cfqd = cfqq->cfqd;
 	struct request *rq;
 	struct cfq_rq *crq;
 	if (cfq_cfqq_fifo_expire(cfqq))
 		return NULL;
 	if (!list_empty(&cfqq->fifo)) {
 		int fifo = cfq_cfqq_class_sync(cfqq);
 		crq = RQ_DATA(list_entry_fifo(cfqq->fifo.next));
 		rq = crq->request;
 		if (time_after(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo])) {
 			cfq_mark_cfqq_fifo_expire(cfqq);
 			return crq;
 		}
 	}
 	return NULL;
 }
 /*
  * Scale schedule slice based on io priority. Use the sync time slice only
  * 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_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	const int base_slice = cfqd->cfq_slice[cfq_cfqq_sync(cfqq)];
 	WARN_ON(cfqq->ioprio >= IOPRIO_BE_NR);
 	return base_slice + (base_slice/CFQ_SLICE_SCALE * (4 - cfqq->ioprio));
 }
 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;
 }
 static inline int
 cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	const int base_rq = cfqd->cfq_slice_async_rq;
 	WARN_ON(cfqq->ioprio >= IOPRIO_BE_NR);
 	return 2 * (base_rq + base_rq * (CFQ_PRIO_LISTS - 1 - cfqq->ioprio));
 }
 /*
  * get next queue for service
  */
 static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 {
 	unsigned long now = jiffies;
 	struct cfq_queue *cfqq;
 	cfqq = cfqd->active_queue;
 	if (!cfqq)
 		goto new_queue;
 	/*
 	 * slice has expired
 	 */
 	if (!cfq_cfqq_must_dispatch(cfqq) && time_after(now, cfqq->slice_end))
 		goto expire;
 	/*
 	 * if queue has requests, dispatch one. if not, check if
 	 * enough slice is left to wait for one
 	 */
 	if (!RB_EMPTY(&cfqq->sort_list))
 		goto keep_queue;
 	else if (cfq_cfqq_class_sync(cfqq) &&
 		 time_before(now, cfqq->slice_end)) {
 		if (cfq_arm_slice_timer(cfqd, cfqq))
 			return NULL;
 	}
 expire:
 	cfq_slice_expired(cfqd, 0);
 new_queue:
 	cfqq = cfq_set_active_queue(cfqd);
 keep_queue:
 	return cfqq;
 }
 static int
 __cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			int max_dispatch)
 {
 	int dispatched = 0;
 	BUG_ON(RB_EMPTY(&cfqq->sort_list));
 	do {
 		struct cfq_rq *crq;
 		/*
 		 * follow expired path, else get first next available
 		 */
 		if ((crq = cfq_check_fifo(cfqq)) == NULL)
 			crq = cfqq->next_crq;
 		/*
 		 * finally, insert request into driver dispatch list
 		 */
 		cfq_dispatch_insert(cfqd->queue, crq);
 		cfqd->dispatch_slice++;
 		dispatched++;
 		if (!cfqd->active_cic) {
 			atomic_inc(&crq->io_context->ioc->refcount);
 			cfqd->active_cic = crq->io_context;
 		}
 		if (RB_EMPTY(&cfqq->sort_list))
 			break;
 	} while (dispatched < max_dispatch);
 	/*
 	 * if slice end isn't set yet, set it. if at least one request was
 	 * sync, use the sync time slice value
 	 */
 	if (!cfqq->slice_end)
 		cfq_set_prio_slice(cfqd, cfqq);
 	/*
 	 * expire an async queue immediately if it has used up its slice. idle
 	 * queue always expire after 1 dispatch round.
 	 */
 	if ((!cfq_cfqq_sync(cfqq) &&
 	    cfqd->dispatch_slice >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
 	    cfq_class_idle(cfqq))
 		cfq_slice_expired(cfqd, 0);
 	return dispatched;
 }
 static int
 cfq_forced_dispatch_cfqqs(struct list_head *list)
 {
 	int dispatched = 0;
 	struct cfq_queue *cfqq, *next;
 	struct cfq_rq *crq;
 	list_for_each_entry_safe(cfqq, next, list, cfq_list) {
 		while ((crq = cfqq->next_crq)) {
 			cfq_dispatch_insert(cfqq->cfqd->queue, crq);
 			dispatched++;
 		}
 		BUG_ON(!list_empty(&cfqq->fifo));
 	}
 	return dispatched;
 }
 static int
 cfq_forced_dispatch(struct cfq_data *cfqd)
 {
 	int i, dispatched = 0;
 	for (i = 0; i < CFQ_PRIO_LISTS; i++)
 		dispatched += cfq_forced_dispatch_cfqqs(&cfqd->rr_list[i]);
 	dispatched += cfq_forced_dispatch_cfqqs(&cfqd->busy_rr);
 	dispatched += cfq_forced_dispatch_cfqqs(&cfqd->cur_rr);
 	dispatched += cfq_forced_dispatch_cfqqs(&cfqd->idle_rr);
 	cfq_slice_expired(cfqd, 0);
 	BUG_ON(cfqd->busy_queues);
 	return dispatched;
 }
 static int
 cfq_dispatch_requests(request_queue_t *q, int force)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_queue *cfqq;
 	if (!cfqd->busy_queues)
 		return 0;
 	if (unlikely(force))
 		return cfq_forced_dispatch(cfqd);
 	cfqq = cfq_select_queue(cfqd);
 	if (cfqq) {
 		int max_dispatch;
 		/*
 		 * if idle window is disabled, allow queue buildup
 		 */
 		if (!cfq_cfqq_idle_window(cfqq) &&
 		    cfqd->rq_in_driver >= cfqd->cfq_max_depth)
 			return 0;
 		cfq_clear_cfqq_must_dispatch(cfqq);
 		cfq_clear_cfqq_wait_request(cfqq);
 		del_timer(&cfqd->idle_slice_timer);
 		max_dispatch = cfqd->cfq_quantum;
 		if (cfq_class_idle(cfqq))
 			max_dispatch = 1;
 		return __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);
 	}
 	return 0;
 }
 /*
  * task holds one reference to the queue, dropped when task exits. each crq
  * in-flight on this queue also holds a reference, dropped when crq is freed.
  *
  * queue lock must be held here.
  */
 static void cfq_put_queue(struct cfq_queue *cfqq)
 {
 	struct cfq_data *cfqd = cfqq->cfqd;
 	BUG_ON(atomic_read(&cfqq->ref) <= 0);
 	if (!atomic_dec_and_test(&cfqq->ref))
 		return;
 	BUG_ON(rb_first(&cfqq->sort_list));
 	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	if (unlikely(cfqd->active_queue == cfqq))
 		__cfq_slice_expired(cfqd, cfqq, 0);
 	/*
 	 * it's on the empty list and still hashed
 	 */
 	list_del(&cfqq->cfq_list);
 	hlist_del(&cfqq->cfq_hash);
 	kmem_cache_free(cfq_pool, cfqq);
 }
 static inline struct cfq_queue *
 __cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned int key, unsigned int prio,
 		    const int hashval)
 {
 	struct hlist_head *hash_list = &cfqd->cfq_hash[hashval];
 	struct hlist_node *entry, *next;
 	hlist_for_each_safe(entry, next, hash_list) {
 		struct cfq_queue *__cfqq = list_entry_qhash(entry);
 		const unsigned short __p = IOPRIO_PRIO_VALUE(__cfqq->org_ioprio_class, __cfqq->org_ioprio);
 		if (__cfqq->key == key && (__p == prio || prio == CFQ_KEY_ANY))
 			return __cfqq;
 	}
 	return NULL;
 }
 static struct cfq_queue *
 cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned int key, unsigned short prio)
 {
 	return __cfq_find_cfq_hash(cfqd, key, prio, hash_long(key, CFQ_QHASH_SHIFT));
 }
 static void cfq_free_io_context(struct cfq_io_context *cic)
 {
 	struct cfq_io_context *__cic;
 	struct list_head *entry, *next;
 	int freed = 1;
 	list_for_each_safe(entry, next, &cic->list) {
 		__cic = list_entry(entry, struct cfq_io_context, list);
 		kmem_cache_free(cfq_ioc_pool, __cic);
 		freed++;
 	}
 	kmem_cache_free(cfq_ioc_pool, cic);
 	if (atomic_sub_and_test(freed, &ioc_count) && ioc_gone)
 		complete(ioc_gone);
 }
 static void cfq_trim(struct io_context *ioc)
 {
 	ioc->set_ioprio = NULL;
 	if (ioc->cic)
 		cfq_free_io_context(ioc->cic);
 }
 /*
  * Called with interrupts disabled
  */
 static void cfq_exit_single_io_context(struct cfq_io_context *cic)
 {
 	struct cfq_data *cfqd = cic->key;
 	request_queue_t *q;
 	if (!cfqd)
 		return;
 	q = cfqd->queue;
 	WARN_ON(!irqs_disabled());
 	spin_lock(q->queue_lock);
 	if (cic->cfqq[ASYNC]) {
 		if (unlikely(cic->cfqq[ASYNC] == cfqd->active_queue))
 			__cfq_slice_expired(cfqd, cic->cfqq[ASYNC], 0);
 		cfq_put_queue(cic->cfqq[ASYNC]);
 		cic->cfqq[ASYNC] = NULL;
 	}
 	if (cic->cfqq[SYNC]) {
 		if (unlikely(cic->cfqq[SYNC] == cfqd->active_queue))
 			__cfq_slice_expired(cfqd, cic->cfqq[SYNC], 0);
 		cfq_put_queue(cic->cfqq[SYNC]);
 		cic->cfqq[SYNC] = NULL;
 	}
 	cic->key = NULL;
 	list_del_init(&cic->queue_list);
 	spin_unlock(q->queue_lock);
 }
 static void cfq_exit_io_context(struct cfq_io_context *cic)
 {
 	struct cfq_io_context *__cic;
 	struct list_head *entry;
 	unsigned long flags;
 	local_irq_save(flags);
 	/*
 	 * put the reference this task is holding to the various queues
 	 */
 	read_lock(&cfq_exit_lock);
 	list_for_each(entry, &cic->list) {
 		__cic = list_entry(entry, struct cfq_io_context, list);
 		cfq_exit_single_io_context(__cic);
 	}
 	cfq_exit_single_io_context(cic);
 	read_unlock(&cfq_exit_lock);
 	local_irq_restore(flags);
 }
 static struct cfq_io_context *
 cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
 {
 	struct cfq_io_context *cic = kmem_cache_alloc(cfq_ioc_pool, gfp_mask);
 	if (cic) {
 		INIT_LIST_HEAD(&cic->list);
 		cic->cfqq[ASYNC] = NULL;
 		cic->cfqq[SYNC] = NULL;
 		cic->key = NULL;
 		cic->last_end_request = jiffies;
 		cic->ttime_total = 0;
 		cic->ttime_samples = 0;
 		cic->ttime_mean = 0;
 		cic->dtor = cfq_free_io_context;
 		cic->exit = cfq_exit_io_context;
 		INIT_LIST_HEAD(&cic->queue_list);
 		atomic_inc(&ioc_count);
 	}
 	return cic;
 }
 static void cfq_init_prio_data(struct cfq_queue *cfqq)
 {
 	struct task_struct *tsk = current;
 	int ioprio_class;
 	if (!cfq_cfqq_prio_changed(cfqq))
 		return;
 	ioprio_class = IOPRIO_PRIO_CLASS(tsk->ioprio);
 	switch (ioprio_class) {
 		default:
 			printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
 		case IOPRIO_CLASS_NONE:
 			/*
 			 * no prio set, place us in the middle of the BE classes
 			 */
 			cfqq->ioprio = task_nice_ioprio(tsk);
 			cfqq->ioprio_class = IOPRIO_CLASS_BE;
 			break;
 		case IOPRIO_CLASS_RT:
 			cfqq->ioprio = task_ioprio(tsk);
 			cfqq->ioprio_class = IOPRIO_CLASS_RT;
 			break;
 		case IOPRIO_CLASS_BE:
 			cfqq->ioprio = task_ioprio(tsk);
 			cfqq->ioprio_class = IOPRIO_CLASS_BE;
 			break;
 		case IOPRIO_CLASS_IDLE:
 			cfqq->ioprio_class = IOPRIO_CLASS_IDLE;
 			cfqq->ioprio = 7;
 			cfq_clear_cfqq_idle_window(cfqq);
 			break;
 	}
 	/*
 	 * keep track of original prio settings in case we have to temporarily
 	 * elevate the priority of this queue
 	 */
 	cfqq->org_ioprio = cfqq->ioprio;
 	cfqq->org_ioprio_class = cfqq->ioprio_class;
 	if (cfq_cfqq_on_rr(cfqq))
 		cfq_resort_rr_list(cfqq, 0);
 	cfq_clear_cfqq_prio_changed(cfqq);
 }
 static inline void changed_ioprio(struct cfq_io_context *cic)
 {
 	struct cfq_data *cfqd = cic->key;
 	struct cfq_queue *cfqq;
 	if (cfqd) {
 		spin_lock(cfqd->queue->queue_lock);
 		cfqq = cic->cfqq[ASYNC];
 		if (cfqq) {
 			struct cfq_queue *new_cfqq;
 			new_cfqq = cfq_get_queue(cfqd, CFQ_KEY_ASYNC,
 						cic->ioc->task, GFP_ATOMIC);
 			if (new_cfqq) {
 				cic->cfqq[ASYNC] = new_cfqq;
 				cfq_put_queue(cfqq);
 			}
 		}
 		cfqq = cic->cfqq[SYNC];
 		if (cfqq) {
 			cfq_mark_cfqq_prio_changed(cfqq);
 			cfq_init_prio_data(cfqq);
 		}
 		spin_unlock(cfqd->queue->queue_lock);
 	}
 }
 /*
  * callback from sys_ioprio_set, irqs are disabled
  */
 static int cfq_ioc_set_ioprio(struct io_context *ioc, unsigned int ioprio)
 {
 	struct cfq_io_context *cic;
 	write_lock(&cfq_exit_lock);
 	cic = ioc->cic;
 	changed_ioprio(cic);
 	list_for_each_entry(cic, &cic->list, list)
 		changed_ioprio(cic);
 	write_unlock(&cfq_exit_lock);
 	return 0;
 }
 static struct cfq_queue *
 cfq_get_queue(struct cfq_data *cfqd, unsigned int key, struct task_struct *tsk,
 	      gfp_t gfp_mask)
 {
 	const int hashval = hash_long(key, CFQ_QHASH_SHIFT);
 	struct cfq_queue *cfqq, *new_cfqq = NULL;
 	unsigned short ioprio;
 retry:
 	ioprio = tsk->ioprio;
 	cfqq = __cfq_find_cfq_hash(cfqd, key, ioprio, hashval);
 	if (!cfqq) {
 		if (new_cfqq) {
 			cfqq = new_cfqq;
 			new_cfqq = NULL;
 		} else if (gfp_mask & __GFP_WAIT) {
 			spin_unlock_irq(cfqd->queue->queue_lock);
 			new_cfqq = kmem_cache_alloc(cfq_pool, gfp_mask);
 			spin_lock_irq(cfqd->queue->queue_lock);
 			goto retry;
 		} else {
 			cfqq = kmem_cache_alloc(cfq_pool, gfp_mask);
 			if (!cfqq)
 				goto out;
 		}
 		memset(cfqq, 0, sizeof(*cfqq));
 		INIT_HLIST_NODE(&cfqq->cfq_hash);
 		INIT_LIST_HEAD(&cfqq->cfq_list);
 		RB_CLEAR_ROOT(&cfqq->sort_list);
 		INIT_LIST_HEAD(&cfqq->fifo);
 		cfqq->key = key;
 		hlist_add_head(&cfqq->cfq_hash, &cfqd->cfq_hash[hashval]);
 		atomic_set(&cfqq->ref, 0);
 		cfqq->cfqd = cfqd;
 		cfqq->service_last = 0;
 		/*
 		 * set ->slice_left to allow preemption for a new process
 		 */
 		cfqq->slice_left = 2 * cfqd->cfq_slice_idle;
 		cfq_mark_cfqq_idle_window(cfqq);
 		cfq_mark_cfqq_prio_changed(cfqq);
 		cfq_init_prio_data(cfqq);
 	}
 	if (new_cfqq)
 		kmem_cache_free(cfq_pool, new_cfqq);
 	atomic_inc(&cfqq->ref);
 out:
 	WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq);
 	return cfqq;
 }
 /*
  * Setup general io context and cfq io context. There can be several cfq
  * io contexts per general io context, if this process is doing io to more
  * than one device managed by cfq. Note that caller is holding a reference to
  * cfqq, so we don't need to worry about it disappearing
  */
 static struct cfq_io_context *
 cfq_get_io_context(struct cfq_data *cfqd, pid_t pid, gfp_t gfp_mask)
 {
 	struct io_context *ioc = NULL;
 	struct cfq_io_context *cic;
 	might_sleep_if(gfp_mask & __GFP_WAIT);
 	ioc = get_io_context(gfp_mask);
 	if (!ioc)
 		return NULL;
 restart:
 	if ((cic = ioc->cic) == NULL) {
 		cic = cfq_alloc_io_context(cfqd, gfp_mask);
 		if (cic == NULL)
 			goto err;
 		/*
 		 * manually increment generic io_context usage count, it
 		 * cannot go away since we are already holding one ref to it
 		 */
 		cic->ioc = ioc;
 		cic->key = cfqd;
 		read_lock(&cfq_exit_lock);
 		ioc->set_ioprio = cfq_ioc_set_ioprio;
 		ioc->cic = cic;
 		list_add(&cic->queue_list, &cfqd->cic_list);
 		read_unlock(&cfq_exit_lock);
 	} else {
 		struct cfq_io_context *__cic;
 		/*
 		 * the first cic on the list is actually the head itself
 		 */
 		if (cic->key == cfqd)
 			goto out;
 		if (unlikely(!cic->key)) {
 			read_lock(&cfq_exit_lock);
 			if (list_empty(&cic->list))
 				ioc->cic = NULL;
 			else
 				ioc->cic = list_entry(cic->list.next,
 						      struct cfq_io_context,
 						      list);
 			read_unlock(&cfq_exit_lock);
 			kmem_cache_free(cfq_ioc_pool, cic);
 			atomic_dec(&ioc_count);
 			goto restart;
 		}
 		/*
 		 * cic exists, check if we already are there. linear search
 		 * should be ok here, the list will usually not be more than
 		 * 1 or a few entries long
 		 */
 		list_for_each_entry(__cic, &cic->list, list) {
 			/*
 			 * this process is already holding a reference to
 			 * this queue, so no need to get one more
 			 */
 			if (__cic->key == cfqd) {
 				cic = __cic;
 				goto out;
 			}
 			if (unlikely(!__cic->key)) {
 				read_lock(&cfq_exit_lock);
 				list_del(&__cic->list);
 				read_unlock(&cfq_exit_lock);
 				kmem_cache_free(cfq_ioc_pool, __cic);
 				atomic_dec(&ioc_count);
 				goto restart;
 			}
 		}
 		/*
 		 * nope, process doesn't have a cic assoicated with this
 		 * cfqq yet. get a new one and add to list
 		 */
 		__cic = cfq_alloc_io_context(cfqd, gfp_mask);
 		if (__cic == NULL)
 			goto err;
 		__cic->ioc = ioc;
 		__cic->key = cfqd;
 		read_lock(&cfq_exit_lock);
 		list_add(&__cic->list, &cic->list);
 		list_add(&__cic->queue_list, &cfqd->cic_list);
 		read_unlock(&cfq_exit_lock);
 		cic = __cic;
 	}
 out:
 	return cic;
 err:
 	put_io_context(ioc);
 	return NULL;
 }
 static void
 cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_io_context *cic)
 {
 	unsigned long elapsed, ttime;
 	/*
 	 * if this context already has stuff queued, thinktime is from
 	 * last queue not last end
 	 */
 #if 0
 	if (time_after(cic->last_end_request, cic->last_queue))
 		elapsed = jiffies - cic->last_end_request;
 	else
 		elapsed = jiffies - cic->last_queue;
 #else
 		elapsed = jiffies - cic->last_end_request;
 #endif
 	ttime = min(elapsed, 2UL * cfqd->cfq_slice_idle);
 	cic->ttime_samples = (7*cic->ttime_samples + 256) / 8;
 	cic->ttime_total = (7*cic->ttime_total + 256*ttime) / 8;
 	cic->ttime_mean = (cic->ttime_total + 128) / cic->ttime_samples;
 }
 #define sample_valid(samples)	((samples) > 80)
 /*
  * Disable idle window if the process thinks too long or seeks so much that
  * it doesn't matter
  */
 static void
 cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		       struct cfq_io_context *cic)
 {
 	int enable_idle = cfq_cfqq_idle_window(cfqq);
 	if (!cic->ioc->task || !cfqd->cfq_slice_idle)
 		enable_idle = 0;
 	else if (sample_valid(cic->ttime_samples)) {
 		if (cic->ttime_mean > cfqd->cfq_slice_idle)
 			enable_idle = 0;
 		else
 			enable_idle = 1;
 	}
 	if (enable_idle)
 		cfq_mark_cfqq_idle_window(cfqq);
 	else
 		cfq_clear_cfqq_idle_window(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
 cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 		   struct cfq_rq *crq)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 	if (cfq_class_idle(new_cfqq))
 		return 0;
 	if (!cfqq)
 		return 1;
 	if (cfq_class_idle(cfqq))
 		return 1;
 	if (!cfq_cfqq_wait_request(new_cfqq))
 		return 0;
 	/*
 	 * if it doesn't have slice left, forget it
 	 */
 	if (new_cfqq->slice_left < cfqd->cfq_slice_idle)
 		return 0;
 	if (cfq_crq_is_sync(crq) && !cfq_cfqq_sync(cfqq))
 		return 1;
 	return 0;
 }
 /*
  * cfqq preempts the active queue. if we allowed preempt with no slice left,
  * let it have half of its nominal slice.
  */
 static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	struct cfq_queue *__cfqq, *next;
 	list_for_each_entry_safe(__cfqq, next, &cfqd->cur_rr, cfq_list)
 		cfq_resort_rr_list(__cfqq, 1);
 	if (!cfqq->slice_left)
 		cfqq->slice_left = cfq_prio_to_slice(cfqd, cfqq) / 2;
 	cfqq->slice_end = cfqq->slice_left + jiffies;
 	__cfq_slice_expired(cfqd, cfqq, 1);
 	__cfq_set_active_queue(cfqd, cfqq);
 }
 /*
  * should really be a ll_rw_blk.c helper
  */
 static void cfq_start_queueing(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	request_queue_t *q = cfqd->queue;
 	if (!blk_queue_plugged(q))
 		q->request_fn(q);
 	else
 		__generic_unplug_device(q);
 }
 /*
  * Called when a new fs request (crq) is added (to cfqq). Check if there's
  * something we should do about it
  */
 static void
 cfq_crq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 struct cfq_rq *crq)
 {
 	struct cfq_io_context *cic;
 	cfqq->next_crq = cfq_choose_req(cfqd, cfqq->next_crq, crq);
 	/*
 	 * we never wait for an async request and we don't allow preemption
 	 * of an async request. so just return early
 	 */
 	if (!cfq_crq_is_sync(crq))
 		return;
 	cic = crq->io_context;
 	cfq_update_io_thinktime(cfqd, cic);
 	cfq_update_idle_window(cfqd, cfqq, cic);
 	cic->last_queue = jiffies;
 	if (cfqq == cfqd->active_queue) {
 		/*
 		 * if we are waiting for a request for this queue, let it rip
 		 * immediately and flag that we must not expire this queue
 		 * just now
 		 */
 		if (cfq_cfqq_wait_request(cfqq)) {
 			cfq_mark_cfqq_must_dispatch(cfqq);
 			del_timer(&cfqd->idle_slice_timer);
 			cfq_start_queueing(cfqd, cfqq);
 		}
 	} else if (cfq_should_preempt(cfqd, cfqq, crq)) {
 		/*
 		 * not the active queue - expire current slice if it is
 		 * idle and has expired it's mean thinktime or this new queue
 		 * has some old slice time left and is of higher priority
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
 		cfq_mark_cfqq_must_dispatch(cfqq);
 		cfq_start_queueing(cfqd, cfqq);
 	}
 }
 static void cfq_insert_request(request_queue_t *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_rq *crq = RQ_DATA(rq);
 	struct cfq_queue *cfqq = crq->cfq_queue;
 	cfq_init_prio_data(cfqq);
 	cfq_add_crq_rb(crq);
 	list_add_tail(&rq->queuelist, &cfqq->fifo);
 	if (rq_mergeable(rq))
 		cfq_add_crq_hash(cfqd, crq);
 	cfq_crq_enqueued(cfqd, cfqq, crq);
 }
 static void cfq_completed_request(request_queue_t *q, struct request *rq)
 {
 	struct cfq_rq *crq = RQ_DATA(rq);
 	struct cfq_queue *cfqq = crq->cfq_queue;
 	struct cfq_data *cfqd = cfqq->cfqd;
 	const int sync = cfq_crq_is_sync(crq);
 	unsigned long now;
 	now = jiffies;
 	WARN_ON(!cfqd->rq_in_driver);
 	WARN_ON(!cfqq->on_dispatch[sync]);
 	cfqd->rq_in_driver--;
 	cfqq->on_dispatch[sync]--;
 	if (!cfq_class_idle(cfqq))
 		cfqd->last_end_request = now;
 	if (!cfq_cfqq_dispatched(cfqq)) {
 		if (cfq_cfqq_on_rr(cfqq)) {
 			cfqq->service_last = now;
 			cfq_resort_rr_list(cfqq, 0);
 		}
 		cfq_schedule_dispatch(cfqd);
 	}
 	if (cfq_crq_is_sync(crq))
 		crq->io_context->last_end_request = now;
 }
 static struct request *
 cfq_former_request(request_queue_t *q, struct request *rq)
 {
 	struct cfq_rq *crq = RQ_DATA(rq);
 	struct rb_node *rbprev = rb_prev(&crq->rb_node);
 	if (rbprev)
 		return rb_entry_crq(rbprev)->request;
 	return NULL;
 }
 static struct request *
 cfq_latter_request(request_queue_t *q, struct request *rq)
 {
 	struct cfq_rq *crq = RQ_DATA(rq);
 	struct rb_node *rbnext = rb_next(&crq->rb_node);
 	if (rbnext)
 		return rb_entry_crq(rbnext)->request;
 	return NULL;
 }
 /*
  * we temporarily boost lower priority queues if they are holding fs exclusive
  * resources. they are boosted to normal prio (CLASS_BE/4)
  */
 static void cfq_prio_boost(struct cfq_queue *cfqq)
 {
 	const int ioprio_class = cfqq->ioprio_class;
 	const int ioprio = cfqq->ioprio;
 	if (has_fs_excl()) {
 		/*
 		 * boost idle prio on transactions that would lock out other
 		 * users of the filesystem
 		 */
 		if (cfq_class_idle(cfqq))
 			cfqq->ioprio_class = IOPRIO_CLASS_BE;
 		if (cfqq->ioprio > IOPRIO_NORM)
 			cfqq->ioprio = IOPRIO_NORM;
 	} else {
 		/*
 		 * check if we need to unboost the queue
 		 */
 		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;
 	}
 	/*
 	 * refile between round-robin lists if we moved the priority class
 	 */
 	if ((ioprio_class != cfqq->ioprio_class || ioprio != cfqq->ioprio) &&
 	    cfq_cfqq_on_rr(cfqq))
 		cfq_resort_rr_list(cfqq, 0);
 }
 static inline pid_t cfq_queue_pid(struct task_struct *task, int rw)
 {
 	if (rw == READ || process_sync(task))
 		return task->pid;
 	return CFQ_KEY_ASYNC;
 }
 static inline int
 __cfq_may_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		struct task_struct *task, int rw)
 {
 #if 1
 	if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) &&
 	    !cfq_cfqq_must_alloc_slice(cfqq)) {
 		cfq_mark_cfqq_must_alloc_slice(cfqq);
 		return ELV_MQUEUE_MUST;
 	}
 	return ELV_MQUEUE_MAY;
 #else
 	if (!cfqq || task->flags & PF_MEMALLOC)
 		return ELV_MQUEUE_MAY;
 	if (!cfqq->allocated[rw] || cfq_cfqq_must_alloc(cfqq)) {
 		if (cfq_cfqq_wait_request(cfqq))
 			return ELV_MQUEUE_MUST;
 		/*
 		 * only allow 1 ELV_MQUEUE_MUST per slice, otherwise we
 		 * can quickly flood the queue with writes from a single task
 		 */
 		if (rw == READ || !cfq_cfqq_must_alloc_slice(cfqq)) {
 			cfq_mark_cfqq_must_alloc_slice(cfqq);
 			return ELV_MQUEUE_MUST;
 		}
 		return ELV_MQUEUE_MAY;
 	}
 	if (cfq_class_idle(cfqq))
 		return ELV_MQUEUE_NO;
 	if (cfqq->allocated[rw] >= cfqd->max_queued) {
 		struct io_context *ioc = get_io_context(GFP_ATOMIC);
 		int ret = ELV_MQUEUE_NO;
 		if (ioc && ioc->nr_batch_requests)
 			ret = ELV_MQUEUE_MAY;
 		put_io_context(ioc);
 		return ret;
 	}
 	return ELV_MQUEUE_MAY;
 #endif
 }
 static int cfq_may_queue(request_queue_t *q, int rw, struct bio *bio)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct task_struct *tsk = current;
 	struct cfq_queue *cfqq;
 	/*
 	 * don't force setup of a queue from here, as a call to may_queue
 	 * does not necessarily imply that a request actually will be queued.
 	 * so just lookup a possibly existing queue, or return 'may queue'
 	 * if that fails
 	 */
 	cfqq = cfq_find_cfq_hash(cfqd, cfq_queue_pid(tsk, rw), tsk->ioprio);
 	if (cfqq) {
 		cfq_init_prio_data(cfqq);
 		cfq_prio_boost(cfqq);
 		return __cfq_may_queue(cfqd, cfqq, tsk, rw);
 	}
 	return ELV_MQUEUE_MAY;
 }
 static void cfq_check_waiters(request_queue_t *q, struct cfq_queue *cfqq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct request_list *rl = &q->rq;
 	if (cfqq->allocated[READ] <= cfqd->max_queued || cfqd->rq_starved) {
 		smp_mb();
 		if (waitqueue_active(&rl->wait[READ]))
 			wake_up(&rl->wait[READ]);
 	}
 	if (cfqq->allocated[WRITE] <= cfqd->max_queued || cfqd->rq_starved) {
 		smp_mb();
 		if (waitqueue_active(&rl->wait[WRITE]))
 			wake_up(&rl->wait[WRITE]);
 	}
 }
 /*
  * queue lock held here
  */
 static void cfq_put_request(request_queue_t *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_rq *crq = RQ_DATA(rq);
 	if (crq) {
 		struct cfq_queue *cfqq = crq->cfq_queue;
 		const int rw = rq_data_dir(rq);
 		BUG_ON(!cfqq->allocated[rw]);
 		cfqq->allocated[rw]--;
 		put_io_context(crq->io_context->ioc);
 		mempool_free(crq, cfqd->crq_pool);
 		rq->elevator_private = NULL;
 		cfq_check_waiters(q, cfqq);
 		cfq_put_queue(cfqq);
 	}
 }
 /*
  * Allocate cfq data structures associated with this request.
  */
 static int
 cfq_set_request(request_queue_t *q, struct request *rq, struct bio *bio,
 		gfp_t gfp_mask)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct task_struct *tsk = current;
 	struct cfq_io_context *cic;
 	const int rw = rq_data_dir(rq);
 	pid_t key = cfq_queue_pid(tsk, rw);
 	struct cfq_queue *cfqq;
 	struct cfq_rq *crq;
 	unsigned long flags;
 	int is_sync = key != CFQ_KEY_ASYNC;
 	might_sleep_if(gfp_mask & __GFP_WAIT);
 	cic = cfq_get_io_context(cfqd, key, gfp_mask);
 	spin_lock_irqsave(q->queue_lock, flags);
 	if (!cic)
 		goto queue_fail;
 	if (!cic->cfqq[is_sync]) {
 		cfqq = cfq_get_queue(cfqd, key, tsk, gfp_mask);
 		if (!cfqq)
 			goto queue_fail;
 		cic->cfqq[is_sync] = cfqq;
 	} else
 		cfqq = cic->cfqq[is_sync];
 	cfqq->allocated[rw]++;
 	cfq_clear_cfqq_must_alloc(cfqq);
 	cfqd->rq_starved = 0;
 	atomic_inc(&cfqq->ref);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 	crq = mempool_alloc(cfqd->crq_pool, gfp_mask);
 	if (crq) {
 		RB_CLEAR(&crq->rb_node);
 		crq->rb_key = 0;
 		crq->request = rq;
 		INIT_HLIST_NODE(&crq->hash);
 		crq->cfq_queue = cfqq;
 		crq->io_context = cic;
 		if (is_sync)
 			cfq_mark_crq_is_sync(crq);
 		else
 			cfq_clear_crq_is_sync(crq);
 		rq->elevator_private = crq;
 		return 0;
 	}
 	spin_lock_irqsave(q->queue_lock, flags);
 	cfqq->allocated[rw]--;
 	if (!(cfqq->allocated[0] + cfqq->allocated[1]))
 		cfq_mark_cfqq_must_alloc(cfqq);
 	cfq_put_queue(cfqq);
 queue_fail:
 	if (cic)
 		put_io_context(cic->ioc);
 	/*
 	 * mark us rq allocation starved. we need to kickstart the process
 	 * ourselves if there are no pending requests that can do it for us.
 	 * that would be an extremely rare OOM situation
 	 */
 	cfqd->rq_starved = 1;
 	cfq_schedule_dispatch(cfqd);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 	return 1;
 }
 static void cfq_kick_queue(void *data)
 {
 	request_queue_t *q = data;
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	unsigned long flags;
 	spin_lock_irqsave(q->queue_lock, flags);
 	if (cfqd->rq_starved) {
 		struct request_list *rl = &q->rq;
 		/*
 		 * we aren't guaranteed to get a request after this, but we
 		 * have to be opportunistic
 		 */
 		smp_mb();
 		if (waitqueue_active(&rl->wait[READ]))
 			wake_up(&rl->wait[READ]);
 		if (waitqueue_active(&rl->wait[WRITE]))
 			wake_up(&rl->wait[WRITE]);
 	}
 	blk_remove_plug(q);
 	q->request_fn(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 /*
  * Timer running if the active_queue is currently idling inside its time slice
  */
 static void cfq_idle_slice_timer(unsigned long data)
 {
 	struct cfq_data *cfqd = (struct cfq_data *) data;
 	struct cfq_queue *cfqq;
 	unsigned long flags;
 	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
 	if ((cfqq = cfqd->active_queue) != NULL) {
 		unsigned long now = jiffies;
 		/*
 		 * expired
 		 */
 		if (time_after(now, cfqq->slice_end))
 			goto expire;
 		/*
 		 * only expire and reinvoke request handler, if there are
 		 * other queues with pending requests
 		 */
 		if (!cfqd->busy_queues) {
 			cfqd->idle_slice_timer.expires = min(now + cfqd->cfq_slice_idle, cfqq->slice_end);
 			add_timer(&cfqd->idle_slice_timer);
 			goto out_cont;
 		}
 		/*
 		 * not expired and it has a request pending, let it dispatch
 		 */
 		if (!RB_EMPTY(&cfqq->sort_list)) {
 			cfq_mark_cfqq_must_dispatch(cfqq);
 			goto out_kick;
 		}
 	}
 expire:
 	cfq_slice_expired(cfqd, 0);
 out_kick:
 	cfq_schedule_dispatch(cfqd);
 out_cont:
 	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
 }
 /*
  * Timer running if an idle class queue is waiting for service
  */
 static void cfq_idle_class_timer(unsigned long data)
 {
 	struct cfq_data *cfqd = (struct cfq_data *) data;
 	unsigned long flags, end;
 	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
 	/*
 	 * race with a non-idle queue, reset timer
 	 */
 	end = cfqd->last_end_request + CFQ_IDLE_GRACE;
 	if (!time_after_eq(jiffies, end)) {
 		cfqd->idle_class_timer.expires = end;
 		add_timer(&cfqd->idle_class_timer);
 	} else
 		cfq_schedule_dispatch(cfqd);
 	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
 }
 static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
 {
 	del_timer_sync(&cfqd->idle_slice_timer);
 	del_timer_sync(&cfqd->idle_class_timer);
 	blk_sync_queue(cfqd->queue);
 }
 static void cfq_exit_queue(elevator_t *e)
 {
 	struct cfq_data *cfqd = e->elevator_data;
 	request_queue_t *q = cfqd->queue;
 	cfq_shutdown_timer_wq(cfqd);
 	write_lock(&cfq_exit_lock);
 	spin_lock_irq(q->queue_lock);
 	if (cfqd->active_queue)
 		__cfq_slice_expired(cfqd, cfqd->active_queue, 0);
 	while(!list_empty(&cfqd->cic_list)) {
 		struct cfq_io_context *cic = list_entry(cfqd->cic_list.next,
 							struct cfq_io_context,
 							queue_list);
 		if (cic->cfqq[ASYNC]) {
 			cfq_put_queue(cic->cfqq[ASYNC]);
 			cic->cfqq[ASYNC] = NULL;
 		}
 		if (cic->cfqq[SYNC]) {
 			cfq_put_queue(cic->cfqq[SYNC]);
 			cic->cfqq[SYNC] = NULL;
 		}
 		cic->key = NULL;
 		list_del_init(&cic->queue_list);
 	}
 	spin_unlock_irq(q->queue_lock);
 	write_unlock(&cfq_exit_lock);
 	cfq_shutdown_timer_wq(cfqd);
 	mempool_destroy(cfqd->crq_pool);
 	kfree(cfqd->crq_hash);
 	kfree(cfqd->cfq_hash);
 	kfree(cfqd);
 }
 static int cfq_init_queue(request_queue_t *q, elevator_t *e)
 {
 	struct cfq_data *cfqd;
 	int i;
 	cfqd = kmalloc(sizeof(*cfqd), GFP_KERNEL);
 	if (!cfqd)
 		return -ENOMEM;
 	memset(cfqd, 0, sizeof(*cfqd));
 	for (i = 0; i < CFQ_PRIO_LISTS; i++)
 		INIT_LIST_HEAD(&cfqd->rr_list[i]);
 	INIT_LIST_HEAD(&cfqd->busy_rr);
 	INIT_LIST_HEAD(&cfqd->cur_rr);
 	INIT_LIST_HEAD(&cfqd->idle_rr);
 	INIT_LIST_HEAD(&cfqd->empty_list);
 	INIT_LIST_HEAD(&cfqd->cic_list);
 	cfqd->crq_hash = kmalloc(sizeof(struct hlist_head) * CFQ_MHASH_ENTRIES, GFP_KERNEL);
 	if (!cfqd->crq_hash)
 		goto out_crqhash;
 	cfqd->cfq_hash = kmalloc(sizeof(struct hlist_head) * CFQ_QHASH_ENTRIES, GFP_KERNEL);
 	if (!cfqd->cfq_hash)
 		goto out_cfqhash;
 	cfqd->crq_pool = mempool_create(BLKDEV_MIN_RQ, mempool_alloc_slab, mempool_free_slab, crq_pool);
 	if (!cfqd->crq_pool)
 		goto out_crqpool;
 	for (i = 0; i < CFQ_MHASH_ENTRIES; i++)
 		INIT_HLIST_HEAD(&cfqd->crq_hash[i]);
 	for (i = 0; i < CFQ_QHASH_ENTRIES; i++)
 		INIT_HLIST_HEAD(&cfqd->cfq_hash[i]);
 	e->elevator_data = cfqd;
 	cfqd->queue = q;
 	cfqd->max_queued = q->nr_requests / 4;
 	q->nr_batching = cfq_queued;
 	init_timer(&cfqd->idle_slice_timer);
 	cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
 	cfqd->idle_slice_timer.data = (unsigned long) cfqd;
 	init_timer(&cfqd->idle_class_timer);
 	cfqd->idle_class_timer.function = cfq_idle_class_timer;
 	cfqd->idle_class_timer.data = (unsigned long) cfqd;
 	INIT_WORK(&cfqd->unplug_work, cfq_kick_queue, q);
 	cfqd->cfq_queued = cfq_queued;
 	cfqd->cfq_quantum = cfq_quantum;
 	cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0];
 	cfqd->cfq_fifo_expire[1] = cfq_fifo_expire[1];
 	cfqd->cfq_back_max = cfq_back_max;
 	cfqd->cfq_back_penalty = cfq_back_penalty;
 	cfqd->cfq_slice[0] = cfq_slice_async;
 	cfqd->cfq_slice[1] = cfq_slice_sync;
 	cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
 	cfqd->cfq_slice_idle = cfq_slice_idle;
 	cfqd->cfq_max_depth = cfq_max_depth;
 	return 0;
 out_crqpool:
 	kfree(cfqd->cfq_hash);
 out_cfqhash:
 	kfree(cfqd->crq_hash);
 out_crqhash:
 	kfree(cfqd);
 	return -ENOMEM;
 }
 static void cfq_slab_kill(void)
 {
 	if (crq_pool)
 		kmem_cache_destroy(crq_pool);
 	if (cfq_pool)
 		kmem_cache_destroy(cfq_pool);
 	if (cfq_ioc_pool)
 		kmem_cache_destroy(cfq_ioc_pool);
 }
 static int __init cfq_slab_setup(void)
 {
 	crq_pool = kmem_cache_create("crq_pool", sizeof(struct cfq_rq), 0, 0,
 					NULL, NULL);
 	if (!crq_pool)
 		goto fail;
 	cfq_pool = kmem_cache_create("cfq_pool", sizeof(struct cfq_queue), 0, 0,
 					NULL, NULL);
 	if (!cfq_pool)
 		goto fail;
 	cfq_ioc_pool = kmem_cache_create("cfq_ioc_pool",
 			sizeof(struct cfq_io_context), 0, 0, NULL, NULL);
 	if (!cfq_ioc_pool)
 		goto fail;
 	return 0;
 fail:
 	cfq_slab_kill();
 	return -ENOMEM;
 }
 /*
  * sysfs parts below -->
  */
 static ssize_t
 cfq_var_show(unsigned int var, char *page)
 {
 	return sprintf(page, "%d\n", var);
 }
 static ssize_t
 cfq_var_store(unsigned int *var, const char *page, size_t count)
 {
 	char *p = (char *) page;
 	*var = simple_strtoul(p, &p, 10);
 	return count;
 }
 #define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
 static ssize_t __FUNC(elevator_t *e, char *page)			\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
 	unsigned int __data = __VAR;					\
 	if (__CONV)							\
 		__data = jiffies_to_msecs(__data);			\
 	return cfq_var_show(__data, (page));				\
 }
 SHOW_FUNCTION(cfq_quantum_show, cfqd->cfq_quantum, 0);
 SHOW_FUNCTION(cfq_queued_show, cfqd->cfq_queued, 0);
 SHOW_FUNCTION(cfq_fifo_expire_sync_show, cfqd->cfq_fifo_expire[1], 1);
 SHOW_FUNCTION(cfq_fifo_expire_async_show, cfqd->cfq_fifo_expire[0], 1);
-SHOW_FUNCTION(cfq_back_max_show, cfqd->cfq_back_max, 0);
+SHOW_FUNCTION(cfq_back_seek_max_show, cfqd->cfq_back_max, 0);
-SHOW_FUNCTION(cfq_back_penalty_show, cfqd->cfq_back_penalty, 0);
+SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0);
 SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
 SHOW_FUNCTION(cfq_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_max_depth_show, cfqd->cfq_max_depth, 0);
 #undef SHOW_FUNCTION
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
 static ssize_t __FUNC(elevator_t *e, const char *page, size_t count)	\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
 	unsigned int __data;						\
 	int ret = cfq_var_store(&__data, (page), count);		\
 	if (__data < (MIN))						\
 		__data = (MIN);						\
 	else if (__data > (MAX))					\
 		__data = (MAX);						\
 	if (__CONV)							\
 		*(__PTR) = msecs_to_jiffies(__data);			\
 	else								\
 		*(__PTR) = __data;					\
 	return ret;							\
 }
 STORE_FUNCTION(cfq_quantum_store, &cfqd->cfq_quantum, 1, UINT_MAX, 0);
 STORE_FUNCTION(cfq_queued_store, &cfqd->cfq_queued, 1, UINT_MAX, 0);
 STORE_FUNCTION(cfq_fifo_expire_sync_store, &cfqd->cfq_fifo_expire[1], 1, UINT_MAX, 1);
 STORE_FUNCTION(cfq_fifo_expire_async_store, &cfqd->cfq_fifo_expire[0], 1, UINT_MAX, 1);
-STORE_FUNCTION(cfq_back_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
+STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
-STORE_FUNCTION(cfq_back_penalty_store, &cfqd->cfq_back_penalty, 1, UINT_MAX, 0);
+STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1, UINT_MAX, 0);
 STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
 STORE_FUNCTION(cfq_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_max_depth_store, &cfqd->cfq_max_depth, 1, UINT_MAX, 0);
 #undef STORE_FUNCTION
-static struct elv_fs_entry cfq_quantum_entry = {
+#define CFQ_ATTR(name) \
-	.attr = {.name = "quantum", .mode = S_IRUGO | S_IWUSR },
+	__ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store)
-	.show = cfq_quantum_show,
-	.store = cfq_quantum_store,
-};
-static struct elv_fs_entry cfq_queued_entry = {
-	.attr = {.name = "queued", .mode = S_IRUGO | S_IWUSR },
-	.show = cfq_queued_show,
-	.store = cfq_queued_store,
-};
-static struct elv_fs_entry cfq_fifo_expire_sync_entry = {
-	.attr = {.name = "fifo_expire_sync", .mode = S_IRUGO | S_IWUSR },
-	.show = cfq_fifo_expire_sync_show,
-	.store = cfq_fifo_expire_sync_store,
-};
-static struct elv_fs_entry cfq_fifo_expire_async_entry = {
-	.attr = {.name = "fifo_expire_async", .mode = S_IRUGO | S_IWUSR },
-	.show = cfq_fifo_expire_async_show,
-	.store = cfq_fifo_expire_async_store,
-};
-static struct elv_fs_entry cfq_back_max_entry = {
-	.attr = {.name = "back_seek_max", .mode = S_IRUGO | S_IWUSR },
-	.show = cfq_back_max_show,
-	.store = cfq_back_max_store,
-};
-static struct elv_fs_entry cfq_back_penalty_entry = {
-	.attr = {.name = "back_seek_penalty", .mode = S_IRUGO | S_IWUSR },
-	.show = cfq_back_penalty_show,
-	.store = cfq_back_penalty_store,
-};
-static struct elv_fs_entry cfq_slice_sync_entry = {
-	.attr = {.name = "slice_sync", .mode = S_IRUGO | S_IWUSR },
-	.show = cfq_slice_sync_show,
-	.store = cfq_slice_sync_store,
-};
-static struct elv_fs_entry cfq_slice_async_entry = {
-	.attr = {.name = "slice_async", .mode = S_IRUGO | S_IWUSR },
-	.show = cfq_slice_async_show,
-	.store = cfq_slice_async_store,
-};
-static struct elv_fs_entry cfq_slice_async_rq_entry = {
-	.attr = {.name = "slice_async_rq", .mode = S_IRUGO | S_IWUSR },
-	.show = cfq_slice_async_rq_show,
-	.store = cfq_slice_async_rq_store,
-};
-static struct elv_fs_entry cfq_slice_idle_entry = {
-	.attr = {.name = "slice_idle", .mode = S_IRUGO | S_IWUSR },
-	.show = cfq_slice_idle_show,
-	.store = cfq_slice_idle_store,
-};
-static struct elv_fs_entry cfq_max_depth_entry = {
-	.attr = {.name = "max_depth", .mode = S_IRUGO | S_IWUSR },
-	.show = cfq_max_depth_show,
-	.store = cfq_max_depth_store,
-};
-static struct attribute *cfq_attrs[] = {
+static struct elv_fs_entry cfq_attrs[] = {
-	&cfq_quantum_entry.attr,
+	CFQ_ATTR(quantum),
-	&cfq_queued_entry.attr,
+	CFQ_ATTR(queued),
-	&cfq_fifo_expire_sync_entry.attr,
+	CFQ_ATTR(fifo_expire_sync),
-	&cfq_fifo_expire_async_entry.attr,
+	CFQ_ATTR(fifo_expire_async),
-	&cfq_back_max_entry.attr,
+	CFQ_ATTR(back_seek_max),
-	&cfq_back_penalty_entry.attr,
+	CFQ_ATTR(back_seek_penalty),
-	&cfq_slice_sync_entry.attr,
+	CFQ_ATTR(slice_sync),
-	&cfq_slice_async_entry.attr,
+	CFQ_ATTR(slice_async),
-	&cfq_slice_async_rq_entry.attr,
+	CFQ_ATTR(slice_async_rq),
-	&cfq_slice_idle_entry.attr,
+	CFQ_ATTR(slice_idle),
-	&cfq_max_depth_entry.attr,
+	CFQ_ATTR(max_depth),
-	NULL,
+	__ATTR_NULL
 };
 static struct elevator_type iosched_cfq = {
 	.ops = {
 		.elevator_merge_fn = 		cfq_merge,
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,
 		.elevator_dispatch_fn =		cfq_dispatch_requests,
 		.elevator_add_req_fn =		cfq_insert_request,
 		.elevator_activate_req_fn =	cfq_activate_request,
 		.elevator_deactivate_req_fn =	cfq_deactivate_request,
 		.elevator_queue_empty_fn =	cfq_queue_empty,
 		.elevator_completed_req_fn =	cfq_completed_request,
 		.elevator_former_req_fn =	cfq_former_request,
 		.elevator_latter_req_fn =	cfq_latter_request,
 		.elevator_set_req_fn =		cfq_set_request,
 		.elevator_put_req_fn =		cfq_put_request,
 		.elevator_may_queue_fn =	cfq_may_queue,
 		.elevator_init_fn =		cfq_init_queue,
 		.elevator_exit_fn =		cfq_exit_queue,
 		.trim =				cfq_trim,
 	},
 	.elevator_attrs =	cfq_attrs,
 	.elevator_name =	"cfq",
 	.elevator_owner =	THIS_MODULE,
 };
 static int __init cfq_init(void)
 {
 	int ret;
 	/*
 	 * could be 0 on HZ < 1000 setups
 	 */
 	if (!cfq_slice_async)
 		cfq_slice_async = 1;
 	if (!cfq_slice_idle)
 		cfq_slice_idle = 1;
 	if (cfq_slab_setup())
 		return -ENOMEM;
 	ret = elv_register(&iosched_cfq);
 	if (ret)
 		cfq_slab_kill();
 	return ret;
 }
 static void __exit cfq_exit(void)
 {
 	DECLARE_COMPLETION(all_gone);
 	elv_unregister(&iosched_cfq);
 	ioc_gone = &all_gone;
 	barrier();
 	if (atomic_read(&ioc_count))
 		complete(ioc_gone);
 	synchronize_rcu();
 	cfq_slab_kill();
 }
 module_init(cfq_init);
 module_exit(cfq_exit);
 MODULE_AUTHOR("Jens Axboe");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Completely Fair Queueing IO scheduler");

block/deadline-iosched.c

Diff comments View file @ e572ec7

 /*
  *  Deadline i/o scheduler.
  *
  *  Copyright (C) 2002 Jens Axboe <axboe@suse.de>
  */
 #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>
 /*
  * See Documentation/block/deadline-iosched.txt
  */
 static const int read_expire = HZ / 2;  /* max time before a read is submitted. */
 static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
 static const int writes_starved = 2;    /* max times reads can starve a write */
 static const int fifo_batch = 16;       /* # of sequential requests treated as one
 				     by the above parameters. For throughput. */
 static const int deadline_hash_shift = 5;
 #define DL_HASH_BLOCK(sec)	((sec) >> 3)
 #define DL_HASH_FN(sec)		(hash_long(DL_HASH_BLOCK((sec)), deadline_hash_shift))
 #define DL_HASH_ENTRIES		(1 << deadline_hash_shift)
 #define rq_hash_key(rq)		((rq)->sector + (rq)->nr_sectors)
 #define list_entry_hash(ptr)	list_entry((ptr), struct deadline_rq, hash)
 #define ON_HASH(drq)		(drq)->on_hash
 struct deadline_data {
 	/*
 	 * run time data
 	 */
 	/*
 	 * requests (deadline_rq s) are present on both sort_list and fifo_list
 	 */
 	struct rb_root sort_list[2];
 	struct list_head fifo_list[2];
 	/*
 	 * next in sort order. read, write or both are NULL
 	 */
 	struct deadline_rq *next_drq[2];
 	struct list_head *hash;		/* request hash */
 	unsigned int batching;		/* number of sequential requests made */
 	sector_t last_sector;		/* head position */
 	unsigned int starved;		/* times reads have starved writes */
 	/*
 	 * settings that change how the i/o scheduler behaves
 	 */
 	int fifo_expire[2];
 	int fifo_batch;
 	int writes_starved;
 	int front_merges;
 	mempool_t *drq_pool;
 };
 /*
  * pre-request data.
  */
 struct deadline_rq {
 	/*
 	 * rbtree index, key is the starting offset
 	 */
 	struct rb_node rb_node;
 	sector_t rb_key;
 	struct request *request;
 	/*
 	 * request hash, key is the ending offset (for back merge lookup)
 	 */
 	struct list_head hash;
 	char on_hash;
 	/*
 	 * expire fifo
 	 */
 	struct list_head fifo;
 	unsigned long expires;
 };
 static void deadline_move_request(struct deadline_data *dd, struct deadline_rq *drq);
 static kmem_cache_t *drq_pool;
 #define RQ_DATA(rq)	((struct deadline_rq *) (rq)->elevator_private)
 /*
  * the back merge hash support functions
  */
 static inline void __deadline_del_drq_hash(struct deadline_rq *drq)
 {
 	drq->on_hash = 0;
 	list_del_init(&drq->hash);
 }
 static inline void deadline_del_drq_hash(struct deadline_rq *drq)
 {
 	if (ON_HASH(drq))
 		__deadline_del_drq_hash(drq);
 }
 static inline void
 deadline_add_drq_hash(struct deadline_data *dd, struct deadline_rq *drq)
 {
 	struct request *rq = drq->request;
 	BUG_ON(ON_HASH(drq));
 	drq->on_hash = 1;
 	list_add(&drq->hash, &dd->hash[DL_HASH_FN(rq_hash_key(rq))]);
 }
 /*
  * move hot entry to front of chain
  */
 static inline void
 deadline_hot_drq_hash(struct deadline_data *dd, struct deadline_rq *drq)
 {
 	struct request *rq = drq->request;
 	struct list_head *head = &dd->hash[DL_HASH_FN(rq_hash_key(rq))];
 	if (ON_HASH(drq) && drq->hash.prev != head) {
 		list_del(&drq->hash);
 		list_add(&drq->hash, head);
 	}
 }
 static struct request *
 deadline_find_drq_hash(struct deadline_data *dd, sector_t offset)
 {
 	struct list_head *hash_list = &dd->hash[DL_HASH_FN(offset)];
 	struct list_head *entry, *next = hash_list->next;
 	while ((entry = next) != hash_list) {
 		struct deadline_rq *drq = list_entry_hash(entry);
 		struct request *__rq = drq->request;
 		next = entry->next;
 		BUG_ON(!ON_HASH(drq));
 		if (!rq_mergeable(__rq)) {
 			__deadline_del_drq_hash(drq);
 			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_drq(node)	rb_entry((node), struct deadline_rq, rb_node)
 #define DRQ_RB_ROOT(dd, drq)	(&(dd)->sort_list[rq_data_dir((drq)->request)])
 #define rq_rb_key(rq)		(rq)->sector
 static struct deadline_rq *
 __deadline_add_drq_rb(struct deadline_data *dd, struct deadline_rq *drq)
 {
 	struct rb_node **p = &DRQ_RB_ROOT(dd, drq)->rb_node;
 	struct rb_node *parent = NULL;
 	struct deadline_rq *__drq;
 	while (*p) {
 		parent = *p;
 		__drq = rb_entry_drq(parent);
 		if (drq->rb_key < __drq->rb_key)
 			p = &(*p)->rb_left;
 		else if (drq->rb_key > __drq->rb_key)
 			p = &(*p)->rb_right;
 		else
 			return __drq;
 	}
 	rb_link_node(&drq->rb_node, parent, p);
 	return NULL;
 }
 static void
 deadline_add_drq_rb(struct deadline_data *dd, struct deadline_rq *drq)
 {
 	struct deadline_rq *__alias;
 	drq->rb_key = rq_rb_key(drq->request);
 retry:
 	__alias = __deadline_add_drq_rb(dd, drq);
 	if (!__alias) {
 		rb_insert_color(&drq->rb_node, DRQ_RB_ROOT(dd, drq));
 		return;
 	}
 	deadline_move_request(dd, __alias);
 	goto retry;
 }
 static inline void
 deadline_del_drq_rb(struct deadline_data *dd, struct deadline_rq *drq)
 {
 	const int data_dir = rq_data_dir(drq->request);
 	if (dd->next_drq[data_dir] == drq) {
 		struct rb_node *rbnext = rb_next(&drq->rb_node);
 		dd->next_drq[data_dir] = NULL;
 		if (rbnext)
 			dd->next_drq[data_dir] = rb_entry_drq(rbnext);
 	}
 	BUG_ON(!ON_RB(&drq->rb_node));
 	rb_erase(&drq->rb_node, DRQ_RB_ROOT(dd, drq));
 	RB_CLEAR(&drq->rb_node);
 }
 static struct request *
 deadline_find_drq_rb(struct deadline_data *dd, sector_t sector, int data_dir)
 {
 	struct rb_node *n = dd->sort_list[data_dir].rb_node;
 	struct deadline_rq *drq;
 	while (n) {
 		drq = rb_entry_drq(n);
 		if (sector < drq->rb_key)
 			n = n->rb_left;
 		else if (sector > drq->rb_key)
 			n = n->rb_right;
 		else
 			return drq->request;
 	}
 	return NULL;
 }
 /*
  * deadline_find_first_drq 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 deadline_rq *
 deadline_find_first_drq(struct deadline_data *dd, int data_dir)
 {
 	struct rb_node *n = dd->sort_list[data_dir].rb_node;
 	for (;;) {
 		if (n->rb_left == NULL)
 			return rb_entry_drq(n);
 		n = n->rb_left;
 	}
 }
 /*
  * add drq to rbtree and fifo
  */
 static void
 deadline_add_request(struct request_queue *q, struct request *rq)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct deadline_rq *drq = RQ_DATA(rq);
 	const int data_dir = rq_data_dir(drq->request);
 	deadline_add_drq_rb(dd, drq);
 	/*
 	 * set expire time (only used for reads) and add to fifo list
 	 */
 	drq->expires = jiffies + dd->fifo_expire[data_dir];
 	list_add_tail(&drq->fifo, &dd->fifo_list[data_dir]);
 	if (rq_mergeable(rq))
 		deadline_add_drq_hash(dd, drq);
 }
 /*
  * remove rq from rbtree, fifo, and hash
  */
 static void deadline_remove_request(request_queue_t *q, struct request *rq)
 {
 	struct deadline_rq *drq = RQ_DATA(rq);
 	struct deadline_data *dd = q->elevator->elevator_data;
 	list_del_init(&drq->fifo);
 	deadline_del_drq_rb(dd, drq);
 	deadline_del_drq_hash(drq);
 }
 static int
 deadline_merge(request_queue_t *q, struct request **req, struct bio *bio)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct request *__rq;
 	int ret;
 	/*
 	 * see if the merge hash can satisfy a back merge
 	 */
 	__rq = deadline_find_drq_hash(dd, bio->bi_sector);
 	if (__rq) {
 		BUG_ON(__rq->sector + __rq->nr_sectors != bio->bi_sector);
 		if (elv_rq_merge_ok(__rq, bio)) {
 			ret = ELEVATOR_BACK_MERGE;
 			goto out;
 		}
 	}
 	/*
 	 * check for front merge
 	 */
 	if (dd->front_merges) {
 		sector_t rb_key = bio->bi_sector + bio_sectors(bio);
 		__rq = deadline_find_drq_rb(dd, rb_key, bio_data_dir(bio));
 		if (__rq) {
 			BUG_ON(rb_key != rq_rb_key(__rq));
 			if (elv_rq_merge_ok(__rq, bio)) {
 				ret = ELEVATOR_FRONT_MERGE;
 				goto out;
 			}
 		}
 	}
 	return ELEVATOR_NO_MERGE;
 out:
 	if (ret)
 		deadline_hot_drq_hash(dd, RQ_DATA(__rq));
 	*req = __rq;
 	return ret;
 }
 static void deadline_merged_request(request_queue_t *q, struct request *req)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct deadline_rq *drq = RQ_DATA(req);
 	/*
 	 * hash always needs to be repositioned, key is end sector
 	 */
 	deadline_del_drq_hash(drq);
 	deadline_add_drq_hash(dd, drq);
 	/*
 	 * if the merge was a front merge, we need to reposition request
 	 */
 	if (rq_rb_key(req) != drq->rb_key) {
 		deadline_del_drq_rb(dd, drq);
 		deadline_add_drq_rb(dd, drq);
 	}
 }
 static void
 deadline_merged_requests(request_queue_t *q, struct request *req,
 			 struct request *next)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct deadline_rq *drq = RQ_DATA(req);
 	struct deadline_rq *dnext = RQ_DATA(next);
 	BUG_ON(!drq);
 	BUG_ON(!dnext);
 	/*
 	 * reposition drq (this is the merged request) in hash, and in rbtree
 	 * in case of a front merge
 	 */
 	deadline_del_drq_hash(drq);
 	deadline_add_drq_hash(dd, drq);
 	if (rq_rb_key(req) != drq->rb_key) {
 		deadline_del_drq_rb(dd, drq);
 		deadline_add_drq_rb(dd, drq);
 	}
 	/*
 	 * if dnext expires before drq, assign its expire time to drq
 	 * and move into dnext position (dnext will be deleted) in fifo
 	 */
 	if (!list_empty(&drq->fifo) && !list_empty(&dnext->fifo)) {
 		if (time_before(dnext->expires, drq->expires)) {
 			list_move(&drq->fifo, &dnext->fifo);
 			drq->expires = dnext->expires;
 		}
 	}
 	/*
 	 * kill knowledge of next, this one is a goner
 	 */
 	deadline_remove_request(q, next);
 }
 /*
  * move request from sort list to dispatch queue.
  */
 static inline void
 deadline_move_to_dispatch(struct deadline_data *dd, struct deadline_rq *drq)
 {
 	request_queue_t *q = drq->request->q;
 	deadline_remove_request(q, drq->request);
 	elv_dispatch_add_tail(q, drq->request);
 }
 /*
  * move an entry to dispatch queue
  */
 static void
 deadline_move_request(struct deadline_data *dd, struct deadline_rq *drq)
 {
 	const int data_dir = rq_data_dir(drq->request);
 	struct rb_node *rbnext = rb_next(&drq->rb_node);
 	dd->next_drq[READ] = NULL;
 	dd->next_drq[WRITE] = NULL;
 	if (rbnext)
 		dd->next_drq[data_dir] = rb_entry_drq(rbnext);
 	dd->last_sector = drq->request->sector + drq->request->nr_sectors;
 	/*
 	 * take it off the sort and fifo list, move
 	 * to dispatch queue
 	 */
 	deadline_move_to_dispatch(dd, drq);
 }
 #define list_entry_fifo(ptr)	list_entry((ptr), struct deadline_rq, fifo)
 /*
  * deadline_check_fifo returns 0 if there are no expired reads on the fifo,
  * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
  */
 static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 {
 	struct deadline_rq *drq = list_entry_fifo(dd->fifo_list[ddir].next);
 	/*
 	 * drq is expired!
 	 */
 	if (time_after(jiffies, drq->expires))
 		return 1;
 	return 0;
 }
 /*
  * deadline_dispatch_requests selects the best request according to
  * read/write expire, fifo_batch, etc
  */
 static int deadline_dispatch_requests(request_queue_t *q, int force)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	const int reads = !list_empty(&dd->fifo_list[READ]);
 	const int writes = !list_empty(&dd->fifo_list[WRITE]);
 	struct deadline_rq *drq;
 	int data_dir;
 	/*
 	 * batches are currently reads XOR writes
 	 */
 	if (dd->next_drq[WRITE])
 		drq = dd->next_drq[WRITE];
 	else
 		drq = dd->next_drq[READ];
 	if (drq) {
 		/* we have a "next request" */
 		if (dd->last_sector != drq->request->sector)
 			/* end the batch on a non sequential request */
 			dd->batching += dd->fifo_batch;
 		if (dd->batching < dd->fifo_batch)
 			/* we are still entitled to batch */
 			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(&dd->sort_list[READ]));
 		if (writes && (dd->starved++ >= dd->writes_starved))
 			goto dispatch_writes;
 		data_dir = READ;
 		goto dispatch_find_request;
 	}
 	/*
 	 * there are either no reads or writes have been starved
 	 */
 	if (writes) {
 dispatch_writes:
 		BUG_ON(RB_EMPTY(&dd->sort_list[WRITE]));
 		dd->starved = 0;
 		data_dir = WRITE;
 		goto dispatch_find_request;
 	}
 	return 0;
 dispatch_find_request:
 	/*
 	 * we are not running a batch, find best request for selected data_dir
 	 */
 	if (deadline_check_fifo(dd, data_dir)) {
 		/* An expired request exists - satisfy it */
 		dd->batching = 0;
 		drq = list_entry_fifo(dd->fifo_list[data_dir].next);
 	} else if (dd->next_drq[data_dir]) {
 		/*
 		 * The last req was the same dir and we have a next request in
 		 * sort order. No expired requests so continue on from here.
 		 */
 		drq = dd->next_drq[data_dir];
 	} else {
 		/*
 		 * The last req was the other direction or we have run out of
 		 * higher-sectored requests. Go back to the lowest sectored
 		 * request (1 way elevator) and start a new batch.
 		 */
 		dd->batching = 0;
 		drq = deadline_find_first_drq(dd, data_dir);
 	}
 dispatch_request:
 	/*
 	 * drq is the selected appropriate request.
 	 */
 	dd->batching++;
 	deadline_move_request(dd, drq);
 	return 1;
 }
 static int deadline_queue_empty(request_queue_t *q)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	return list_empty(&dd->fifo_list[WRITE])
 		&& list_empty(&dd->fifo_list[READ]);
 }
 static struct request *
 deadline_former_request(request_queue_t *q, struct request *rq)
 {
 	struct deadline_rq *drq = RQ_DATA(rq);
 	struct rb_node *rbprev = rb_prev(&drq->rb_node);
 	if (rbprev)
 		return rb_entry_drq(rbprev)->request;
 	return NULL;
 }
 static struct request *
 deadline_latter_request(request_queue_t *q, struct request *rq)
 {
 	struct deadline_rq *drq = RQ_DATA(rq);
 	struct rb_node *rbnext = rb_next(&drq->rb_node);
 	if (rbnext)
 		return rb_entry_drq(rbnext)->request;
 	return NULL;
 }
 static void deadline_exit_queue(elevator_t *e)
 {
 	struct deadline_data *dd = e->elevator_data;
 	BUG_ON(!list_empty(&dd->fifo_list[READ]));
 	BUG_ON(!list_empty(&dd->fifo_list[WRITE]));
 	mempool_destroy(dd->drq_pool);
 	kfree(dd->hash);
 	kfree(dd);
 }
 /*
  * initialize elevator private data (deadline_data), and alloc a drq for
  * each request on the free lists
  */
 static int deadline_init_queue(request_queue_t *q, elevator_t *e)
 {
 	struct deadline_data *dd;
 	int i;
 	if (!drq_pool)
 		return -ENOMEM;
 	dd = kmalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
 	if (!dd)
 		return -ENOMEM;
 	memset(dd, 0, sizeof(*dd));
 	dd->hash = kmalloc_node(sizeof(struct list_head)*DL_HASH_ENTRIES,
 				GFP_KERNEL, q->node);
 	if (!dd->hash) {
 		kfree(dd);
 		return -ENOMEM;
 	}
 	dd->drq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
 					mempool_free_slab, drq_pool, q->node);
 	if (!dd->drq_pool) {
 		kfree(dd->hash);
 		kfree(dd);
 		return -ENOMEM;
 	}
 	for (i = 0; i < DL_HASH_ENTRIES; i++)
 		INIT_LIST_HEAD(&dd->hash[i]);
 	INIT_LIST_HEAD(&dd->fifo_list[READ]);
 	INIT_LIST_HEAD(&dd->fifo_list[WRITE]);
 	dd->sort_list[READ] = RB_ROOT;
 	dd->sort_list[WRITE] = RB_ROOT;
 	dd->fifo_expire[READ] = read_expire;
 	dd->fifo_expire[WRITE] = write_expire;
 	dd->writes_starved = writes_starved;
 	dd->front_merges = 1;
 	dd->fifo_batch = fifo_batch;
 	e->elevator_data = dd;
 	return 0;
 }
 static void deadline_put_request(request_queue_t *q, struct request *rq)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct deadline_rq *drq = RQ_DATA(rq);
 	mempool_free(drq, dd->drq_pool);
 	rq->elevator_private = NULL;
 }
 static int
 deadline_set_request(request_queue_t *q, struct request *rq, struct bio *bio,
 		     gfp_t gfp_mask)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct deadline_rq *drq;
 	drq = mempool_alloc(dd->drq_pool, gfp_mask);
 	if (drq) {
 		memset(drq, 0, sizeof(*drq));
 		RB_CLEAR(&drq->rb_node);
 		drq->request = rq;
 		INIT_LIST_HEAD(&drq->hash);
 		drq->on_hash = 0;
 		INIT_LIST_HEAD(&drq->fifo);
 		rq->elevator_private = drq;
 		return 0;
 	}
 	return 1;
 }
 /*
  * sysfs parts below
  */
 static ssize_t
 deadline_var_show(int var, char *page)
 {
 	return sprintf(page, "%d\n", var);
 }
 static ssize_t
 deadline_var_store(int *var, const char *page, size_t count)
 {
 	char *p = (char *) page;
 	*var = simple_strtol(p, &p, 10);
 	return count;
 }
 #define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
 static ssize_t __FUNC(elevator_t *e, char *page)			\
 {									\
 	struct deadline_data *dd = e->elevator_data;			\
 	int __data = __VAR;						\
 	if (__CONV)							\
 		__data = jiffies_to_msecs(__data);			\
 	return deadline_var_show(__data, (page));			\
 }
-SHOW_FUNCTION(deadline_readexpire_show, dd->fifo_expire[READ], 1);
+SHOW_FUNCTION(deadline_read_expire_show, dd->fifo_expire[READ], 1);
-SHOW_FUNCTION(deadline_writeexpire_show, dd->fifo_expire[WRITE], 1);
+SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1);
-SHOW_FUNCTION(deadline_writesstarved_show, dd->writes_starved, 0);
+SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0);
-SHOW_FUNCTION(deadline_frontmerges_show, dd->front_merges, 0);
+SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 0);
-SHOW_FUNCTION(deadline_fifobatch_show, dd->fifo_batch, 0);
+SHOW_FUNCTION(deadline_fifo_batch_show, dd->fifo_batch, 0);
 #undef SHOW_FUNCTION
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
 static ssize_t __FUNC(elevator_t *e, const char *page, size_t count)	\
 {									\
 	struct deadline_data *dd = e->elevator_data;			\
 	int __data;							\
 	int ret = deadline_var_store(&__data, (page), count);		\
 	if (__data < (MIN))						\
 		__data = (MIN);						\
 	else if (__data > (MAX))					\
 		__data = (MAX);						\
 	if (__CONV)							\
 		*(__PTR) = msecs_to_jiffies(__data);			\
 	else								\
 		*(__PTR) = __data;					\
 	return ret;							\
 }
-STORE_FUNCTION(deadline_readexpire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1);
-STORE_FUNCTION(deadline_writeexpire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1);
-STORE_FUNCTION(deadline_writesstarved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0);
+STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0);
-STORE_FUNCTION(deadline_frontmerges_store, &dd->front_merges, 0, 1, 0);
+STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0);
-STORE_FUNCTION(deadline_fifobatch_store, &dd->fifo_batch, 0, INT_MAX, 0);
+STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
 #undef STORE_FUNCTION
-static struct elv_fs_entry deadline_readexpire_entry = {
+#define DD_ATTR(name) \
-	.attr = {.name = "read_expire", .mode = S_IRUGO | S_IWUSR },
+	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
-	.show = deadline_readexpire_show,
+				      deadline_##name##_store)
-	.store = deadline_readexpire_store,
-};
-static struct elv_fs_entry deadline_writeexpire_entry = {
-	.attr = {.name = "write_expire", .mode = S_IRUGO | S_IWUSR },
-	.show = deadline_writeexpire_show,
-	.store = deadline_writeexpire_store,
-};
-static struct elv_fs_entry deadline_writesstarved_entry = {
-	.attr = {.name = "writes_starved", .mode = S_IRUGO | S_IWUSR },
-	.show = deadline_writesstarved_show,
-	.store = deadline_writesstarved_store,
-};
-static struct elv_fs_entry deadline_frontmerges_entry = {
-	.attr = {.name = "front_merges", .mode = S_IRUGO | S_IWUSR },
-	.show = deadline_frontmerges_show,
-	.store = deadline_frontmerges_store,
-};
-static struct elv_fs_entry deadline_fifobatch_entry = {
-	.attr = {.name = "fifo_batch", .mode = S_IRUGO | S_IWUSR },
-	.show = deadline_fifobatch_show,
-	.store = deadline_fifobatch_store,
-};
-static struct attribute *deadline_attrs[] = {
+static struct elv_fs_entry deadline_attrs[] = {
-	&deadline_readexpire_entry.attr,
+	DD_ATTR(read_expire),
-	&deadline_writeexpire_entry.attr,
+	DD_ATTR(write_expire),
-	&deadline_writesstarved_entry.attr,
+	DD_ATTR(writes_starved),
-	&deadline_frontmerges_entry.attr,
+	DD_ATTR(front_merges),
-	&deadline_fifobatch_entry.attr,
+	DD_ATTR(fifo_batch),
-	NULL,
+	__ATTR_NULL
 };
 static struct elevator_type iosched_deadline = {
 	.ops = {
 		.elevator_merge_fn = 		deadline_merge,
 		.elevator_merged_fn =		deadline_merged_request,
 		.elevator_merge_req_fn =	deadline_merged_requests,
 		.elevator_dispatch_fn =		deadline_dispatch_requests,
 		.elevator_add_req_fn =		deadline_add_request,
 		.elevator_queue_empty_fn =	deadline_queue_empty,
 		.elevator_former_req_fn =	deadline_former_request,
 		.elevator_latter_req_fn =	deadline_latter_request,
 		.elevator_set_req_fn =		deadline_set_request,
 		.elevator_put_req_fn = 		deadline_put_request,
 		.elevator_init_fn =		deadline_init_queue,
 		.elevator_exit_fn =		deadline_exit_queue,
 	},
 	.elevator_attrs = deadline_attrs,
 	.elevator_name = "deadline",
 	.elevator_owner = THIS_MODULE,
 };
 static int __init deadline_init(void)
 {
 	int ret;
 	drq_pool = kmem_cache_create("deadline_drq", sizeof(struct deadline_rq),
 				     0, 0, NULL, NULL);
 	if (!drq_pool)
 		return -ENOMEM;
 	ret = elv_register(&iosched_deadline);
 	if (ret)
 		kmem_cache_destroy(drq_pool);
 	return ret;
 }
 static void __exit deadline_exit(void)
 {
 	kmem_cache_destroy(drq_pool);
 	elv_unregister(&iosched_deadline);
 }
 module_init(deadline_init);
 module_exit(deadline_exit);
 MODULE_AUTHOR("Jens Axboe");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("deadline IO scheduler");

block/elevator.c

Diff comments View file @ e572ec7

 /*
  *  Block device elevator/IO-scheduler.
  *
  *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
  *
  * 30042000 Jens Axboe <axboe@suse.de> :
  *
  * Split the elevator a bit so that it is possible to choose a different
  * one or even write a new "plug in". There are three pieces:
  * - elevator_fn, inserts a new request in the queue list
  * - elevator_merge_fn, decides whether a new buffer can be merged with
  *   an existing request
  * - elevator_dequeue_fn, called when a request is taken off the active list
  *
  * 20082000 Dave Jones <davej@suse.de> :
  * Removed tests for max-bomb-segments, which was breaking elvtune
  *  when run without -bN
  *
  * Jens:
  * - Rework again to work with bio instead of buffer_heads
  * - loose bi_dev comparisons, partition handling is right now
  * - completely modularize elevator setup and teardown
  *
  */
 #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/delay.h>
 #include <asm/uaccess.h>
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
 /*
  * can we safely merge with this request?
  */
 inline int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 {
 	if (!rq_mergeable(rq))
 		return 0;
 	/*
 	 * different data direction or already started, don't merge
 	 */
 	if (bio_data_dir(bio) != rq_data_dir(rq))
 		return 0;
 	/*
 	 * same device and no special stuff set, merge is ok
 	 */
 	if (rq->rq_disk == bio->bi_bdev->bd_disk &&
 	    !rq->waiting && !rq->special)
 		return 1;
 	return 0;
 }
 EXPORT_SYMBOL(elv_rq_merge_ok);
 static inline int elv_try_merge(struct request *__rq, struct bio *bio)
 {
 	int ret = ELEVATOR_NO_MERGE;
 	/*
 	 * we can merge and sequence is ok, check if it's possible
 	 */
 	if (elv_rq_merge_ok(__rq, bio)) {
 		if (__rq->sector + __rq->nr_sectors == bio->bi_sector)
 			ret = ELEVATOR_BACK_MERGE;
 		else if (__rq->sector - bio_sectors(bio) == bio->bi_sector)
 			ret = ELEVATOR_FRONT_MERGE;
 	}
 	return ret;
 }
 static struct elevator_type *elevator_find(const char *name)
 {
 	struct elevator_type *e = NULL;
 	struct list_head *entry;
 	list_for_each(entry, &elv_list) {
 		struct elevator_type *__e;
 		__e = list_entry(entry, struct elevator_type, list);
 		if (!strcmp(__e->elevator_name, name)) {
 			e = __e;
 			break;
 		}
 	}
 	return e;
 }
 static void elevator_put(struct elevator_type *e)
 {
 	module_put(e->elevator_owner);
 }
 static struct elevator_type *elevator_get(const char *name)
 {
 	struct elevator_type *e;
 	spin_lock_irq(&elv_list_lock);
 	e = elevator_find(name);
 	if (e && !try_module_get(e->elevator_owner))
 		e = NULL;
 	spin_unlock_irq(&elv_list_lock);
 	return e;
 }
 static int elevator_attach(request_queue_t *q, struct elevator_queue *eq)
 {
 	int ret = 0;
 	q->elevator = eq;
 	if (eq->ops->elevator_init_fn)
 		ret = eq->ops->elevator_init_fn(q, eq);
 	return ret;
 }
 static char chosen_elevator[16];
 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);
 	return 0;
 }
 __setup("elevator=", elevator_setup);
 static struct kobj_type elv_ktype;
 static elevator_t *elevator_alloc(struct elevator_type *e)
 {
 	elevator_t *eq = kmalloc(sizeof(elevator_t), GFP_KERNEL);
 	if (eq) {
 		memset(eq, 0, sizeof(*eq));
 		eq->ops = &e->ops;
 		eq->elevator_type = e;
 		kobject_init(&eq->kobj);
 		snprintf(eq->kobj.name, KOBJ_NAME_LEN, "%s", "iosched");
 		eq->kobj.ktype = &elv_ktype;
 		mutex_init(&eq->sysfs_lock);
 	} else {
 		elevator_put(e);
 	}
 	return eq;
 }
 static void elevator_release(struct kobject *kobj)
 {
 	elevator_t *e = container_of(kobj, elevator_t, kobj);
 	elevator_put(e->elevator_type);
 	kfree(e);
 }
 int elevator_init(request_queue_t *q, char *name)
 {
 	struct elevator_type *e = NULL;
 	struct elevator_queue *eq;
 	int ret = 0;
 	INIT_LIST_HEAD(&q->queue_head);
 	q->last_merge = NULL;
 	q->end_sector = 0;
 	q->boundary_rq = NULL;
 	if (name && !(e = elevator_get(name)))
 		return -EINVAL;
 	if (!e && *chosen_elevator && !(e = elevator_get(chosen_elevator)))
 		printk("I/O scheduler %s not found\n", chosen_elevator);
 	if (!e && !(e = elevator_get(CONFIG_DEFAULT_IOSCHED))) {
 		printk("Default I/O scheduler not found, using no-op\n");
 		e = elevator_get("noop");
 	}
 	eq = elevator_alloc(e);
 	if (!eq)
 		return -ENOMEM;
 	ret = elevator_attach(q, eq);
 	if (ret)
 		kobject_put(&eq->kobj);
 	return ret;
 }
 void elevator_exit(elevator_t *e)
 {
 	mutex_lock(&e->sysfs_lock);
 	if (e->ops->elevator_exit_fn)
 		e->ops->elevator_exit_fn(e);
 	e->ops = NULL;
 	mutex_unlock(&e->sysfs_lock);
 	kobject_put(&e->kobj);
 }
 /*
  * Insert rq into dispatch queue of q.  Queue lock must be held on
  * entry.  If sort != 0, rq is sort-inserted; otherwise, rq will be
  * appended to the dispatch queue.  To be used by specific elevators.
  */
 void elv_dispatch_sort(request_queue_t *q, struct request *rq)
 {
 	sector_t boundary;
 	struct list_head *entry;
 	if (q->last_merge == rq)
 		q->last_merge = NULL;
 	q->nr_sorted--;
 	boundary = q->end_sector;
 	list_for_each_prev(entry, &q->queue_head) {
 		struct request *pos = list_entry_rq(entry);
 		if (pos->flags & (REQ_SOFTBARRIER|REQ_HARDBARRIER|REQ_STARTED))
 			break;
 		if (rq->sector >= boundary) {
 			if (pos->sector < boundary)
 				continue;
 		} else {
 			if (pos->sector >= boundary)
 				break;
 		}
 		if (rq->sector >= pos->sector)
 			break;
 	}
 	list_add(&rq->queuelist, entry);
 }
 int elv_merge(request_queue_t *q, struct request **req, struct bio *bio)
 {
 	elevator_t *e = q->elevator;
 	int ret;
 	if (q->last_merge) {
 		ret = elv_try_merge(q->last_merge, bio);
 		if (ret != ELEVATOR_NO_MERGE) {
 			*req = q->last_merge;
 			return ret;
 		}
 	}
 	if (e->ops->elevator_merge_fn)
 		return e->ops->elevator_merge_fn(q, req, bio);
 	return ELEVATOR_NO_MERGE;
 }
 void elv_merged_request(request_queue_t *q, struct request *rq)
 {
 	elevator_t *e = q->elevator;
 	if (e->ops->elevator_merged_fn)
 		e->ops->elevator_merged_fn(q, rq);
 	q->last_merge = rq;
 }
 void elv_merge_requests(request_queue_t *q, struct request *rq,
 			     struct request *next)
 {
 	elevator_t *e = q->elevator;
 	if (e->ops->elevator_merge_req_fn)
 		e->ops->elevator_merge_req_fn(q, rq, next);
 	q->nr_sorted--;
 	q->last_merge = rq;
 }
 void elv_requeue_request(request_queue_t *q, struct request *rq)
 {
 	elevator_t *e = q->elevator;
 	/*
 	 * it already went through dequeue, we need to decrement the
 	 * in_flight count again
 	 */
 	if (blk_account_rq(rq)) {
 		q->in_flight--;
 		if (blk_sorted_rq(rq) && e->ops->elevator_deactivate_req_fn)
 			e->ops->elevator_deactivate_req_fn(q, rq);
 	}
 	rq->flags &= ~REQ_STARTED;
 	elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE);
 }
 static void elv_drain_elevator(request_queue_t *q)
 {
 	static int printed;
 	while (q->elevator->ops->elevator_dispatch_fn(q, 1))
 		;
 	if (q->nr_sorted == 0)
 		return;
 	if (printed++ < 10) {
 		printk(KERN_ERR "%s: forced dispatching is broken "
 		       "(nr_sorted=%u), please report this\n",
 		       q->elevator->elevator_type->elevator_name, q->nr_sorted);
 	}
 }
 void elv_insert(request_queue_t *q, struct request *rq, int where)
 {
 	struct list_head *pos;
 	unsigned ordseq;
 	rq->q = q;
 	switch (where) {
 	case ELEVATOR_INSERT_FRONT:
 		rq->flags |= REQ_SOFTBARRIER;
 		list_add(&rq->queuelist, &q->queue_head);
 		break;
 	case ELEVATOR_INSERT_BACK:
 		rq->flags |= REQ_SOFTBARRIER;
 		elv_drain_elevator(q);
 		list_add_tail(&rq->queuelist, &q->queue_head);
 		/*
 		 * We kick the queue here for the following reasons.
 		 * - The elevator might have returned NULL previously
 		 *   to delay requests and returned them now.  As the
 		 *   queue wasn't empty before this request, ll_rw_blk
 		 *   won't run the queue on return, resulting in hang.
 		 * - Usually, back inserted requests won't be merged
 		 *   with anything.  There's no point in delaying queue
 		 *   processing.
 		 */
 		blk_remove_plug(q);
 		q->request_fn(q);
 		break;
 	case ELEVATOR_INSERT_SORT:
 		BUG_ON(!blk_fs_request(rq));
 		rq->flags |= REQ_SORTED;
 		q->nr_sorted++;
 		if (q->last_merge == NULL && rq_mergeable(rq))
 			q->last_merge = rq;
 		/*
 		 * Some ioscheds (cfq) run q->request_fn directly, so
 		 * rq cannot be accessed after calling
 		 * elevator_add_req_fn.
 		 */
 		q->elevator->ops->elevator_add_req_fn(q, rq);
 		break;
 	case ELEVATOR_INSERT_REQUEUE:
 		/*
 		 * If ordered flush isn't in progress, we do front
 		 * insertion; otherwise, requests should be requeued
 		 * in ordseq order.
 		 */
 		rq->flags |= REQ_SOFTBARRIER;
 		if (q->ordseq == 0) {
 			list_add(&rq->queuelist, &q->queue_head);
 			break;
 		}
 		ordseq = blk_ordered_req_seq(rq);
 		list_for_each(pos, &q->queue_head) {
 			struct request *pos_rq = list_entry_rq(pos);
 			if (ordseq <= blk_ordered_req_seq(pos_rq))
 				break;
 		}
 		list_add_tail(&rq->queuelist, pos);
 		break;
 	default:
 		printk(KERN_ERR "%s: bad insertion point %d\n",
 		       __FUNCTION__, where);
 		BUG();
 	}
 	if (blk_queue_plugged(q)) {
 		int nrq = q->rq.count[READ] + q->rq.count[WRITE]
 			- q->in_flight;
 		if (nrq >= q->unplug_thresh)
 			__generic_unplug_device(q);
 	}
 }
 void __elv_add_request(request_queue_t *q, struct request *rq, int where,
 		       int plug)
 {
 	if (q->ordcolor)
 		rq->flags |= REQ_ORDERED_COLOR;
 	if (rq->flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) {
 		/*
 		 * toggle ordered color
 		 */
 		if (blk_barrier_rq(rq))
 			q->ordcolor ^= 1;
 		/*
 		 * barriers implicitly indicate back insertion
 		 */
 		if (where == ELEVATOR_INSERT_SORT)
 			where = ELEVATOR_INSERT_BACK;
 		/*
 		 * this request is scheduling boundary, update
 		 * end_sector
 		 */
 		if (blk_fs_request(rq)) {
 			q->end_sector = rq_end_sector(rq);
 			q->boundary_rq = rq;
 		}
 	} else if (!(rq->flags & REQ_ELVPRIV) && where == ELEVATOR_INSERT_SORT)
 		where = ELEVATOR_INSERT_BACK;
 	if (plug)
 		blk_plug_device(q);
 	elv_insert(q, rq, where);
 }
 void elv_add_request(request_queue_t *q, struct request *rq, int where,
 		     int plug)
 {
 	unsigned long flags;
 	spin_lock_irqsave(q->queue_lock, flags);
 	__elv_add_request(q, rq, where, plug);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 static inline struct request *__elv_next_request(request_queue_t *q)
 {
 	struct request *rq;
 	while (1) {
 		while (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
 			if (blk_do_ordered(q, &rq))
 				return rq;
 		}
 		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
 }
 struct request *elv_next_request(request_queue_t *q)
 {
 	struct request *rq;
 	int ret;
 	while ((rq = __elv_next_request(q)) != NULL) {
 		if (!(rq->flags & REQ_STARTED)) {
 			elevator_t *e = q->elevator;
 			/*
 			 * This is the first time the device driver
 			 * sees this request (possibly after
 			 * requeueing).  Notify IO scheduler.
 			 */
 			if (blk_sorted_rq(rq) &&
 			    e->ops->elevator_activate_req_fn)
 				e->ops->elevator_activate_req_fn(q, rq);
 			/*
 			 * just mark as started even if we don't start
 			 * it, a request that has been delayed should
 			 * not be passed by new incoming requests
 			 */
 			rq->flags |= REQ_STARTED;
 		}
 		if (!q->boundary_rq || q->boundary_rq == rq) {
 			q->end_sector = rq_end_sector(rq);
 			q->boundary_rq = NULL;
 		}
 		if ((rq->flags & REQ_DONTPREP) || !q->prep_rq_fn)
 			break;
 		ret = q->prep_rq_fn(q, rq);
 		if (ret == BLKPREP_OK) {
 			break;
 		} else if (ret == BLKPREP_DEFER) {
 			/*
 			 * the request may have been (partially) prepped.
 			 * we need to keep this request in the front to
 			 * avoid resource deadlock.  REQ_STARTED will
 			 * prevent other fs requests from passing this one.
 			 */
 			rq = NULL;
 			break;
 		} else if (ret == BLKPREP_KILL) {
 			int nr_bytes = rq->hard_nr_sectors << 9;
 			if (!nr_bytes)
 				nr_bytes = rq->data_len;
 			blkdev_dequeue_request(rq);
 			rq->flags |= REQ_QUIET;
 			end_that_request_chunk(rq, 0, nr_bytes);
 			end_that_request_last(rq, 0);
 		} else {
 			printk(KERN_ERR "%s: bad return=%d\n", __FUNCTION__,
 								ret);
 			break;
 		}
 	}
 	return rq;
 }
 void elv_dequeue_request(request_queue_t *q, struct request *rq)
 {
 	BUG_ON(list_empty(&rq->queuelist));
 	list_del_init(&rq->queuelist);
 	/*
 	 * the time frame between a request being removed from the lists
 	 * and to it is freed is accounted as io that is in progress at
 	 * the driver side.
 	 */
 	if (blk_account_rq(rq))
 		q->in_flight++;
 }
 int elv_queue_empty(request_queue_t *q)
 {
 	elevator_t *e = q->elevator;
 	if (!list_empty(&q->queue_head))
 		return 0;
 	if (e->ops->elevator_queue_empty_fn)
 		return e->ops->elevator_queue_empty_fn(q);
 	return 1;
 }
 struct request *elv_latter_request(request_queue_t *q, struct request *rq)
 {
 	elevator_t *e = q->elevator;
 	if (e->ops->elevator_latter_req_fn)
 		return e->ops->elevator_latter_req_fn(q, rq);
 	return NULL;
 }
 struct request *elv_former_request(request_queue_t *q, struct request *rq)
 {
 	elevator_t *e = q->elevator;
 	if (e->ops->elevator_former_req_fn)
 		return e->ops->elevator_former_req_fn(q, rq);
 	return NULL;
 }
 int elv_set_request(request_queue_t *q, struct request *rq, struct bio *bio,
 		    gfp_t gfp_mask)
 {
 	elevator_t *e = q->elevator;
 	if (e->ops->elevator_set_req_fn)
 		return e->ops->elevator_set_req_fn(q, rq, bio, gfp_mask);
 	rq->elevator_private = NULL;
 	return 0;
 }
 void elv_put_request(request_queue_t *q, struct request *rq)
 {
 	elevator_t *e = q->elevator;
 	if (e->ops->elevator_put_req_fn)
 		e->ops->elevator_put_req_fn(q, rq);
 }
 int elv_may_queue(request_queue_t *q, int rw, struct bio *bio)
 {
 	elevator_t *e = q->elevator;
 	if (e->ops->elevator_may_queue_fn)
 		return e->ops->elevator_may_queue_fn(q, rw, bio);
 	return ELV_MQUEUE_MAY;
 }
 void elv_completed_request(request_queue_t *q, struct request *rq)
 {
 	elevator_t *e = q->elevator;
 	/*
 	 * request is released from the driver, io must be done
 	 */
 	if (blk_account_rq(rq)) {
 		q->in_flight--;
 		if (blk_sorted_rq(rq) && e->ops->elevator_completed_req_fn)
 			e->ops->elevator_completed_req_fn(q, rq);
 	}
 	/*
 	 * Check if the queue is waiting for fs requests to be
 	 * drained for flush sequence.
 	 */
 	if (unlikely(q->ordseq)) {
 		struct request *first_rq = list_entry_rq(q->queue_head.next);
 		if (q->in_flight == 0 &&
 		    blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
 		    blk_ordered_req_seq(first_rq) > QUEUE_ORDSEQ_DRAIN) {
 			blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
 			q->request_fn(q);
 		}
 	}
 }
 #define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)
 static ssize_t
 elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 {
 	elevator_t *e = container_of(kobj, elevator_t, kobj);
 	struct elv_fs_entry *entry = to_elv(attr);
 	ssize_t error;
 	if (!entry->show)
 		return -EIO;
 	mutex_lock(&e->sysfs_lock);
 	error = e->ops ? entry->show(e, page) : -ENOENT;
 	mutex_unlock(&e->sysfs_lock);
 	return error;
 }
 static ssize_t
 elv_attr_store(struct kobject *kobj, struct attribute *attr,
 	       const char *page, size_t length)
 {
 	elevator_t *e = container_of(kobj, elevator_t, kobj);
 	struct elv_fs_entry *entry = to_elv(attr);
 	ssize_t error;
 	if (!entry->store)
 		return -EIO;
 	mutex_lock(&e->sysfs_lock);
 	error = e->ops ? entry->store(e, page, length) : -ENOENT;
 	mutex_unlock(&e->sysfs_lock);
 	return error;
 }
 static struct sysfs_ops elv_sysfs_ops = {
 	.show	= elv_attr_show,
 	.store	= elv_attr_store,
 };
 static struct kobj_type elv_ktype = {
 	.sysfs_ops	= &elv_sysfs_ops,
 	.release	= elevator_release,
 };
 int elv_register_queue(struct request_queue *q)
 {
 	elevator_t *e = q->elevator;
 	int error;
 	e->kobj.parent = &q->kobj;
 	error = kobject_add(&e->kobj);
 	if (!error) {
-		struct attribute **attr = e->elevator_type->elevator_attrs;
+		struct elv_fs_entry *attr = e->elevator_type->elevator_attrs;
 		if (attr) {
-			while (*attr) {
+			while (attr->attr.name) {
-				if (sysfs_create_file(&e->kobj,*attr++))
+				if (sysfs_create_file(&e->kobj, &attr->attr))
 					break;
+				attr++;
 			}
 		}
 		kobject_uevent(&e->kobj, KOBJ_ADD);
 	}
 	return error;
 }
 void elv_unregister_queue(struct request_queue *q)
 {
 	if (q) {
 		elevator_t *e = q->elevator;
 		kobject_uevent(&e->kobj, KOBJ_REMOVE);
 		kobject_del(&e->kobj);
 	}
 }
 int elv_register(struct elevator_type *e)
 {
 	spin_lock_irq(&elv_list_lock);
 	if (elevator_find(e->elevator_name))
 		BUG();
 	list_add_tail(&e->list, &elv_list);
 	spin_unlock_irq(&elv_list_lock);
 	printk(KERN_INFO "io scheduler %s registered", e->elevator_name);
 	if (!strcmp(e->elevator_name, chosen_elevator) ||
 			(!*chosen_elevator &&
 			 !strcmp(e->elevator_name, CONFIG_DEFAULT_IOSCHED)))
 				printk(" (default)");
 	printk("\n");
 	return 0;
 }
 EXPORT_SYMBOL_GPL(elv_register);
 void elv_unregister(struct elevator_type *e)
 {
 	struct task_struct *g, *p;
 	/*
 	 * Iterate every thread in the process to remove the io contexts.
 	 */
 	if (e->ops.trim) {
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
 			task_lock(p);
 			e->ops.trim(p->io_context);
 			task_unlock(p);
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);
 	}
 	spin_lock_irq(&elv_list_lock);
 	list_del_init(&e->list);
 	spin_unlock_irq(&elv_list_lock);
 }
 EXPORT_SYMBOL_GPL(elv_unregister);
 /*
  * switch to new_e io scheduler. be careful not to introduce deadlocks -
  * we don't free the old io scheduler, before we have allocated what we
  * need for the new one. this way we have a chance of going back to the old
  * one, if the new one fails init for some reason.
  */
 static int elevator_switch(request_queue_t *q, struct elevator_type *new_e)
 {
 	elevator_t *old_elevator, *e;
 	/*
 	 * Allocate new elevator
 	 */
 	e = elevator_alloc(new_e);
 	if (!e)
 		return 0;
 	/*
 	 * Turn on BYPASS and drain all requests w/ elevator private data
 	 */
 	spin_lock_irq(q->queue_lock);
 	set_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
 	elv_drain_elevator(q);
 	while (q->rq.elvpriv) {
 		blk_remove_plug(q);
 		q->request_fn(q);
 		spin_unlock_irq(q->queue_lock);
 		msleep(10);
 		spin_lock_irq(q->queue_lock);
 		elv_drain_elevator(q);
 	}
 	spin_unlock_irq(q->queue_lock);
 	/*
 	 * unregister old elevator data
 	 */
 	elv_unregister_queue(q);
 	old_elevator = q->elevator;
 	/*
 	 * attach and start new elevator
 	 */
 	if (elevator_attach(q, e))
 		goto fail;
 	if (elv_register_queue(q))
 		goto fail_register;
 	/*
 	 * finally exit old elevator and turn off BYPASS.
 	 */
 	elevator_exit(old_elevator);
 	clear_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
 	return 1;
 fail_register:
 	/*
 	 * switch failed, exit the new io scheduler and reattach the old
 	 * one again (along with re-adding the sysfs dir)
 	 */
 	elevator_exit(e);
 	e = NULL;
 fail:
 	q->elevator = old_elevator;
 	elv_register_queue(q);
 	clear_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
 	if (e)
 		kobject_put(&e->kobj);
 	return 0;
 }
 ssize_t elv_iosched_store(request_queue_t *q, const char *name, size_t count)
 {
 	char elevator_name[ELV_NAME_MAX];
 	size_t len;
 	struct elevator_type *e;
 	elevator_name[sizeof(elevator_name) - 1] = '\0';
 	strncpy(elevator_name, name, sizeof(elevator_name) - 1);
 	len = strlen(elevator_name);
 	if (len && elevator_name[len - 1] == '\n')
 		elevator_name[len - 1] = '\0';
 	e = elevator_get(elevator_name);
 	if (!e) {
 		printk(KERN_ERR "elevator: type %s not found\n", elevator_name);
 		return -EINVAL;
 	}
 	if (!strcmp(elevator_name, q->elevator->elevator_type->elevator_name)) {
 		elevator_put(e);
 		return count;
 	}
 	if (!elevator_switch(q, e))
 		printk(KERN_ERR "elevator: switch to %s failed\n",elevator_name);
 	return count;
 }
 ssize_t elv_iosched_show(request_queue_t *q, char *name)
 {
 	elevator_t *e = q->elevator;
 	struct elevator_type *elv = e->elevator_type;
 	struct list_head *entry;
 	int len = 0;
 	spin_lock_irq(q->queue_lock);
 	list_for_each(entry, &elv_list) {
 		struct elevator_type *__e;
 		__e = list_entry(entry, struct elevator_type, list);
 		if (!strcmp(elv->elevator_name, __e->elevator_name))
 			len += sprintf(name+len, "[%s] ", elv->elevator_name);
 		else
 			len += sprintf(name+len, "%s ", __e->elevator_name);
 	}
 	spin_unlock_irq(q->queue_lock);
 	len += sprintf(len+name, "\n");
 	return len;
 }
 EXPORT_SYMBOL(elv_dispatch_sort);
 EXPORT_SYMBOL(elv_add_request);
 EXPORT_SYMBOL(__elv_add_request);
 EXPORT_SYMBOL(elv_requeue_request);
 EXPORT_SYMBOL(elv_next_request);
 EXPORT_SYMBOL(elv_dequeue_request);
 EXPORT_SYMBOL(elv_queue_empty);
 EXPORT_SYMBOL(elv_completed_request);
 EXPORT_SYMBOL(elevator_exit);
 EXPORT_SYMBOL(elevator_init);

include/linux/elevator.h

Diff comments View file @ e572ec7

 #ifndef _LINUX_ELEVATOR_H
 #define _LINUX_ELEVATOR_H
 typedef int (elevator_merge_fn) (request_queue_t *, struct request **,
 				 struct bio *);
 typedef void (elevator_merge_req_fn) (request_queue_t *, struct request *, struct request *);
 typedef void (elevator_merged_fn) (request_queue_t *, struct request *);
 typedef int (elevator_dispatch_fn) (request_queue_t *, int);
 typedef void (elevator_add_req_fn) (request_queue_t *, struct request *);
 typedef int (elevator_queue_empty_fn) (request_queue_t *);
 typedef struct request *(elevator_request_list_fn) (request_queue_t *, struct request *);
 typedef void (elevator_completed_req_fn) (request_queue_t *, struct request *);
 typedef int (elevator_may_queue_fn) (request_queue_t *, int, struct bio *);
 typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, struct bio *, gfp_t);
 typedef void (elevator_put_req_fn) (request_queue_t *, struct request *);
 typedef void (elevator_activate_req_fn) (request_queue_t *, struct request *);
 typedef void (elevator_deactivate_req_fn) (request_queue_t *, struct request *);
 typedef int (elevator_init_fn) (request_queue_t *, elevator_t *);
 typedef void (elevator_exit_fn) (elevator_t *);
 struct elevator_ops
 {
 	elevator_merge_fn *elevator_merge_fn;
 	elevator_merged_fn *elevator_merged_fn;
 	elevator_merge_req_fn *elevator_merge_req_fn;
 	elevator_dispatch_fn *elevator_dispatch_fn;
 	elevator_add_req_fn *elevator_add_req_fn;
 	elevator_activate_req_fn *elevator_activate_req_fn;
 	elevator_deactivate_req_fn *elevator_deactivate_req_fn;
 	elevator_queue_empty_fn *elevator_queue_empty_fn;
 	elevator_completed_req_fn *elevator_completed_req_fn;
 	elevator_request_list_fn *elevator_former_req_fn;
 	elevator_request_list_fn *elevator_latter_req_fn;
 	elevator_set_req_fn *elevator_set_req_fn;
 	elevator_put_req_fn *elevator_put_req_fn;
 	elevator_may_queue_fn *elevator_may_queue_fn;
 	elevator_init_fn *elevator_init_fn;
 	elevator_exit_fn *elevator_exit_fn;
 	void (*trim)(struct io_context *);
 };
 #define ELV_NAME_MAX	(16)
+struct elv_fs_entry {
+	struct attribute attr;
+	ssize_t (*show)(elevator_t *, char *);
+	ssize_t (*store)(elevator_t *, const char *, size_t);
+};
 /*
  * identifies an elevator type, such as AS or deadline
  */
 struct elevator_type
 {
 	struct list_head list;
 	struct elevator_ops ops;
 	struct elevator_type *elevator_type;
-	struct attribute **elevator_attrs;
+	struct elv_fs_entry *elevator_attrs;
 	char elevator_name[ELV_NAME_MAX];
 	struct module *elevator_owner;
 };
 /*
  * each queue has an elevator_queue associated with it
  */
 struct elevator_queue
 {
 	struct elevator_ops *ops;
 	void *elevator_data;
 	struct kobject kobj;
 	struct elevator_type *elevator_type;
 	struct mutex sysfs_lock;
 };
 /*
  * block elevator interface
  */
 extern void elv_dispatch_sort(request_queue_t *, struct request *);
 extern void elv_add_request(request_queue_t *, struct request *, int, int);
 extern void __elv_add_request(request_queue_t *, struct request *, int, int);
 extern void elv_insert(request_queue_t *, struct request *, int);
 extern int elv_merge(request_queue_t *, struct request **, struct bio *);
 extern void elv_merge_requests(request_queue_t *, struct request *,
 			       struct request *);
 extern void elv_merged_request(request_queue_t *, struct request *);
 extern void elv_dequeue_request(request_queue_t *, struct request *);
 extern void elv_requeue_request(request_queue_t *, struct request *);
 extern int elv_queue_empty(request_queue_t *);
 extern struct request *elv_next_request(struct request_queue *q);
 extern struct request *elv_former_request(request_queue_t *, struct request *);
 extern struct request *elv_latter_request(request_queue_t *, struct request *);
 extern int elv_register_queue(request_queue_t *q);
 extern void elv_unregister_queue(request_queue_t *q);
 extern int elv_may_queue(request_queue_t *, int, struct bio *);
 extern void elv_completed_request(request_queue_t *, struct request *);
 extern int elv_set_request(request_queue_t *, struct request *, struct bio *, gfp_t);
 extern void elv_put_request(request_queue_t *, struct request *);
 /*
  * io scheduler registration
  */
 extern int elv_register(struct elevator_type *);
 extern void elv_unregister(struct elevator_type *);
 /*
  * io scheduler sysfs switching
  */
 extern ssize_t elv_iosched_show(request_queue_t *, char *);
 extern ssize_t elv_iosched_store(request_queue_t *, const char *, size_t);
 extern int elevator_init(request_queue_t *, char *);
 extern void elevator_exit(elevator_t *);
 extern int elv_rq_merge_ok(struct request *, struct bio *);
 /*
  * Return values from elevator merger
  */
 #define ELEVATOR_NO_MERGE	0
 #define ELEVATOR_FRONT_MERGE	1
 #define ELEVATOR_BACK_MERGE	2
 /*
  * Insertion selection
  */
 #define ELEVATOR_INSERT_FRONT	1
 #define ELEVATOR_INSERT_BACK	2
 #define ELEVATOR_INSERT_SORT	3
 #define ELEVATOR_INSERT_REQUEUE	4
 /*
  * return values from elevator_may_queue_fn
  */
 enum {
 	ELV_MQUEUE_MAY,
 	ELV_MQUEUE_NO,
 	ELV_MQUEUE_MUST,
-};
-struct elv_fs_entry {
-	struct attribute attr;
-	ssize_t (*show)(elevator_t *, char *);
-	ssize_t (*store)(elevator_t *, const char *, size_t);