17 files changed, 9810 insertions, 0 deletions

diff --git a/libdde-linux26/contrib/block/as-iosched.c b/libdde-linux26/contrib/block/as-iosched.c
new file mode 100644
index 00000000..5b363ced
--- /dev/null
+++ b/libdde-linux26/contrib/block/as-iosched.c
@@ -0,0 +1,1526 @@
+/*
+ *  Anticipatory & deadline i/o scheduler.
+ *
+ *  Copyright (C) 2002 Jens Axboe <axboe@kernel.dk>
+ *                     Nick Piggin <nickpiggin@yahoo.com.au>
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+#include <linux/elevator.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <linux/interrupt.h>
+
+#include <ddekit/timer.h>
+
+#define REQ_SYNC	1
+#define REQ_ASYNC	0
+
+/*
+ * See Documentation/block/as-iosched.txt
+ */
+
+/*
+ * max time before a read is submitted.
+ */
+#define default_read_expire (HZ / 8)
+
+/*
+ * ditto for writes, these limits are not hard, even
+ * if the disk is capable of satisfying them.
+ */
+#define default_write_expire (HZ / 4)
+
+/*
+ * read_batch_expire describes how long we will allow a stream of reads to
+ * persist before looking to see whether it is time to switch over to writes.
+ */
+#define default_read_batch_expire (HZ / 2)
+
+/*
+ * write_batch_expire describes how long we want a stream of writes to run for.
+ * This is not a hard limit, but a target we set for the auto-tuning thingy.
+ * See, the problem is: we can send a lot of writes to disk cache / TCQ in
+ * a short amount of time...
+ */
+#define default_write_batch_expire (HZ / 8)
+
+/*
+ * max time we may wait to anticipate a read (default around 6ms)
+ */
+#define default_antic_expire ((HZ / 150) ? HZ / 150 : 1)
+
+/*
+ * Keep track of up to 20ms thinktimes. We can go as big as we like here,
+ * however huge values tend to interfere and not decay fast enough. A program
+ * might be in a non-io phase of operation. Waiting on user input for example,
+ * or doing a lengthy computation. A small penalty can be justified there, and
+ * will still catch out those processes that constantly have large thinktimes.
+ */
+#define MAX_THINKTIME (HZ/50UL)
+
+/* Bits in as_io_context.state */
+enum as_io_states {
+	AS_TASK_RUNNING=0,	/* Process has not exited */
+	AS_TASK_IOSTARTED,	/* Process has started some IO */
+	AS_TASK_IORUNNING,	/* Process has completed some IO */
+};
+
+enum anticipation_status {
+	ANTIC_OFF=0,		/* Not anticipating (normal operation)	*/
+	ANTIC_WAIT_REQ,		/* The last read has not yet completed  */
+	ANTIC_WAIT_NEXT,	/* Currently anticipating a request vs
+				   last read (which has completed) */
+	ANTIC_FINISHED,		/* Anticipating but have found a candidate
+				 * or timed out */
+};
+
+struct as_data {
+	/*
+	 * run time data
+	 */
+
+	struct request_queue *q;	/* the "owner" queue */
+
+	/*
+	 * requests (as_rq s) are present on both sort_list and fifo_list
+	 */
+	struct rb_root sort_list[2];
+	struct list_head fifo_list[2];
+
+	struct request *next_rq[2];	/* next in sort order */
+	sector_t last_sector[2];	/* last REQ_SYNC & REQ_ASYNC sectors */
+
+	unsigned long exit_prob;	/* probability a task will exit while
+					   being waited on */
+	unsigned long exit_no_coop;	/* probablility an exited task will
+					   not be part of a later cooperating
+					   request */
+	unsigned long new_ttime_total; 	/* mean thinktime on new proc */
+	unsigned long new_ttime_mean;
+	u64 new_seek_total;		/* mean seek on new proc */
+	sector_t new_seek_mean;
+
+	unsigned long current_batch_expires;
+	unsigned long last_check_fifo[2];
+	int changed_batch;		/* 1: waiting for old batch to end */
+	int new_batch;			/* 1: waiting on first read complete */
+	int batch_data_dir;		/* current batch REQ_SYNC / REQ_ASYNC */
+	int write_batch_count;		/* max # of reqs in a write batch */
+	int current_write_count;	/* how many requests left this batch */
+	int write_batch_idled;		/* has the write batch gone idle? */
+
+	enum anticipation_status antic_status;
+	unsigned long antic_start;	/* jiffies: when it started */
+	struct timer_list antic_timer;	/* anticipatory scheduling timer */
+	struct work_struct antic_work;	/* Deferred unplugging */
+	struct io_context *io_context;	/* Identify the expected process */
+	int ioc_finished; /* IO associated with io_context is finished */
+	int nr_dispatched;
+
+	/*
+	 * settings that change how the i/o scheduler behaves
+	 */
+	unsigned long fifo_expire[2];
+	unsigned long batch_expire[2];
+	unsigned long antic_expire;
+};
+
+/*
+ * per-request data.
+ */
+enum arq_state {
+	AS_RQ_NEW=0,		/* New - not referenced and not on any lists */
+	AS_RQ_QUEUED,		/* In the request queue. It belongs to the
+				   scheduler */
+	AS_RQ_DISPATCHED,	/* On the dispatch list. It belongs to the
+				   driver now */
+	AS_RQ_PRESCHED,		/* Debug poisoning for requests being used */
+	AS_RQ_REMOVED,
+	AS_RQ_MERGED,
+	AS_RQ_POSTSCHED,	/* when they shouldn't be */
+};
+
+#define RQ_IOC(rq)	((struct io_context *) (rq)->elevator_private)
+#define RQ_STATE(rq)	((enum arq_state)(rq)->elevator_private2)
+#define RQ_SET_STATE(rq, state)	((rq)->elevator_private2 = (void *) state)
+
+static DEFINE_PER_CPU(unsigned long, ioc_count);
+static struct completion *ioc_gone;
+static DEFINE_SPINLOCK(ioc_gone_lock);
+
+static void as_move_to_dispatch(struct as_data *ad, struct request *rq);
+static void as_antic_stop(struct as_data *ad);
+
+/*
+ * IO Context helper functions
+ */
+
+/* Called to deallocate the as_io_context */
+static void free_as_io_context(struct as_io_context *aic)
+{
+	kfree(aic);
+	elv_ioc_count_dec(ioc_count);
+	if (ioc_gone) {
+		/*
+		 * AS scheduler is exiting, grab exit lock and check
+		 * the pending io context count. If it hits zero,
+		 * complete ioc_gone and set it back to NULL.
+		 */
+		spin_lock(&ioc_gone_lock);
+		if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
+			complete(ioc_gone);
+			ioc_gone = NULL;
+		}
+		spin_unlock(&ioc_gone_lock);
+	}
+}
+
+static void as_trim(struct io_context *ioc)
+{
+	spin_lock_irq(&ioc->lock);
+	if (ioc->aic)
+		free_as_io_context(ioc->aic);
+	ioc->aic = NULL;
+	spin_unlock_irq(&ioc->lock);
+}
+
+/* Called when the task exits */
+static void exit_as_io_context(struct as_io_context *aic)
+{
+	WARN_ON(!test_bit(AS_TASK_RUNNING, &aic->state));
+	clear_bit(AS_TASK_RUNNING, &aic->state);
+}
+
+static struct as_io_context *alloc_as_io_context(void)
+{
+	struct as_io_context *ret;
+
+	ret = kmalloc(sizeof(*ret), GFP_ATOMIC);
+	if (ret) {
+		ret->dtor = free_as_io_context;
+		ret->exit = exit_as_io_context;
+		ret->state = 1 << AS_TASK_RUNNING;
+		atomic_set(&ret->nr_queued, 0);
+		atomic_set(&ret->nr_dispatched, 0);
+		spin_lock_init(&ret->lock);
+		ret->ttime_total = 0;
+		ret->ttime_samples = 0;
+		ret->ttime_mean = 0;
+		ret->seek_total = 0;
+		ret->seek_samples = 0;
+		ret->seek_mean = 0;
+		elv_ioc_count_inc(ioc_count);
+	}
+
+	return ret;
+}
+
+/*
+ * If the current task has no AS IO context then create one and initialise it.
+ * Then take a ref on the task's io context and return it.
+ */
+static struct io_context *as_get_io_context(int node)
+{
+	struct io_context *ioc = get_io_context(GFP_ATOMIC, node);
+	if (ioc && !ioc->aic) {
+		ioc->aic = alloc_as_io_context();
+		if (!ioc->aic) {
+			put_io_context(ioc);
+			ioc = NULL;
+		}
+	}
+	return ioc;
+}
+
+static void as_put_io_context(struct request *rq)
+{
+	struct as_io_context *aic;
+
+	if (unlikely(!RQ_IOC(rq)))
+		return;
+
+	aic = RQ_IOC(rq)->aic;
+
+	if (rq_is_sync(rq) && aic) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&aic->lock, flags);
+		set_bit(AS_TASK_IORUNNING, &aic->state);
+		aic->last_end_request = jiffies;
+		spin_unlock_irqrestore(&aic->lock, flags);
+	}
+
+	put_io_context(RQ_IOC(rq));
+}
+
+/*
+ * rb tree support functions
+ */
+#define RQ_RB_ROOT(ad, rq)	(&(ad)->sort_list[rq_is_sync((rq))])
+
+static void as_add_rq_rb(struct as_data *ad, struct request *rq)
+{
+	struct request *alias;
+
+	while ((unlikely(alias = elv_rb_add(RQ_RB_ROOT(ad, rq), rq)))) {
+		as_move_to_dispatch(ad, alias);
+		as_antic_stop(ad);
+	}
+}
+
+static inline void as_del_rq_rb(struct as_data *ad, struct request *rq)
+{
+	elv_rb_del(RQ_RB_ROOT(ad, rq), rq);
+}
+
+/*
+ * IO Scheduler proper
+ */
+
+#define MAXBACK (1024 * 1024)	/*
+				 * Maximum distance the disk will go backward
+				 * for a request.
+				 */
+
+#define BACK_PENALTY	2
+
+/*
+ * as_choose_req selects the preferred one of two requests of the same data_dir
+ * ignoring time - eg. timeouts, which is the job of as_dispatch_request
+ */
+static struct request *
+as_choose_req(struct as_data *ad, struct request *rq1, struct request *rq2)
+{
+	int data_dir;
+	sector_t last, s1, s2, d1, d2;
+	int r1_wrap=0, r2_wrap=0;	/* requests are behind the disk head */
+	const sector_t maxback = MAXBACK;
+
+	if (rq1 == NULL || rq1 == rq2)
+		return rq2;
+	if (rq2 == NULL)
+		return rq1;
+
+	data_dir = rq_is_sync(rq1);
+
+	last = ad->last_sector[data_dir];
+	s1 = rq1->sector;
+	s2 = rq2->sector;
+
+	BUG_ON(data_dir != rq_is_sync(rq2));
+
+	/*
+	 * Strict one way elevator _except_ in the case where we allow
+	 * short backward seeks which are biased as twice the cost of a
+	 * similar forward seek.
+	 */
+	if (s1 >= last)
+		d1 = s1 - last;
+	else if (s1+maxback >= last)
+		d1 = (last - s1)*BACK_PENALTY;
+	else {
+		r1_wrap = 1;
+		d1 = 0; /* shut up, gcc */
+	}
+
+	if (s2 >= last)
+		d2 = s2 - last;
+	else if (s2+maxback >= last)
+		d2 = (last - s2)*BACK_PENALTY;
+	else {
+		r2_wrap = 1;
+		d2 = 0;
+	}
+
+	/* Found required data */
+	if (!r1_wrap && r2_wrap)
+		return rq1;
+	else if (!r2_wrap && r1_wrap)
+		return rq2;
+	else if (r1_wrap && r2_wrap) {
+		/* both behind the head */
+		if (s1 <= s2)
+			return rq1;
+		else
+			return rq2;
+	}
+
+	/* Both requests in front of the head */
+	if (d1 < d2)
+		return rq1;
+	else if (d2 < d1)
+		return rq2;
+	else {
+		if (s1 >= s2)
+			return rq1;
+		else
+			return rq2;
+	}
+}
+
+/*
+ * as_find_next_rq finds the next request after @prev in elevator order.
+ * this with as_choose_req form the basis for how the scheduler chooses
+ * what request to process next. Anticipation works on top of this.
+ */
+static struct request *
+as_find_next_rq(struct as_data *ad, struct request *last)
+{
+	struct rb_node *rbnext = rb_next(&last->rb_node);
+	struct rb_node *rbprev = rb_prev(&last->rb_node);
+	struct request *next = NULL, *prev = NULL;
+
+	BUG_ON(RB_EMPTY_NODE(&last->rb_node));
+
+	if (rbprev)
+		prev = rb_entry_rq(rbprev);
+
+	if (rbnext)
+		next = rb_entry_rq(rbnext);
+	else {
+		const int data_dir = rq_is_sync(last);
+
+		rbnext = rb_first(&ad->sort_list[data_dir]);
+		if (rbnext && rbnext != &last->rb_node)
+			next = rb_entry_rq(rbnext);
+	}
+
+	return as_choose_req(ad, next, prev);
+}
+
+/*
+ * anticipatory scheduling functions follow
+ */
+
+/*
+ * as_antic_expired tells us when we have anticipated too long.
+ * The funny "absolute difference" math on the elapsed time is to handle
+ * jiffy wraps, and disks which have been idle for 0x80000000 jiffies.
+ */
+static int as_antic_expired(struct as_data *ad)
+{
+	long delta_jif;
+
+	delta_jif = jiffies - ad->antic_start;
+	if (unlikely(delta_jif < 0))
+		delta_jif = -delta_jif;
+	if (delta_jif < ad->antic_expire)
+		return 0;
+
+	return 1;
+}
+
+/*
+ * as_antic_waitnext starts anticipating that a nice request will soon be
+ * submitted. See also as_antic_waitreq
+ */
+static void as_antic_waitnext(struct as_data *ad)
+{
+	unsigned long timeout;
+
+	BUG_ON(ad->antic_status != ANTIC_OFF
+			&& ad->antic_status != ANTIC_WAIT_REQ);
+
+	timeout = ad->antic_start + ad->antic_expire;
+
+	mod_timer(&ad->antic_timer, timeout);
+
+	ad->antic_status = ANTIC_WAIT_NEXT;
+}
+
+/*
+ * as_antic_waitreq starts anticipating. We don't start timing the anticipation
+ * until the request that we're anticipating on has finished. This means we
+ * are timing from when the candidate process wakes up hopefully.
+ */
+static void as_antic_waitreq(struct as_data *ad)
+{
+	BUG_ON(ad->antic_status == ANTIC_FINISHED);
+	if (ad->antic_status == ANTIC_OFF) {
+		if (!ad->io_context || ad->ioc_finished)
+			as_antic_waitnext(ad);
+		else
+			ad->antic_status = ANTIC_WAIT_REQ;
+	}
+}
+
+/*
+ * This is called directly by the functions in this file to stop anticipation.
+ * We kill the timer and schedule a call to the request_fn asap.
+ */
+static void as_antic_stop(struct as_data *ad)
+{
+	int status = ad->antic_status;
+
+	if (status == ANTIC_WAIT_REQ || status == ANTIC_WAIT_NEXT) {
+		if (status == ANTIC_WAIT_NEXT)
+			del_timer(&ad->antic_timer);
+		ad->antic_status = ANTIC_FINISHED;
+		/* see as_work_handler */
+		kblockd_schedule_work(ad->q, &ad->antic_work);
+	}
+}
+
+/*
+ * as_antic_timeout is the timer function set by as_antic_waitnext.
+ */
+static void as_antic_timeout(unsigned long data)
+{
+	struct request_queue *q = (struct request_queue *)data;
+	struct as_data *ad = q->elevator->elevator_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	if (ad->antic_status == ANTIC_WAIT_REQ
+			|| ad->antic_status == ANTIC_WAIT_NEXT) {
+		struct as_io_context *aic;
+		spin_lock(&ad->io_context->lock);
+		aic = ad->io_context->aic;
+
+		ad->antic_status = ANTIC_FINISHED;
+		kblockd_schedule_work(q, &ad->antic_work);
+
+		if (aic->ttime_samples == 0) {
+			/* process anticipated on has exited or timed out*/
+			ad->exit_prob = (7*ad->exit_prob + 256)/8;
+		}
+		if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
+			/* process not "saved" by a cooperating request */
+			ad->exit_no_coop = (7*ad->exit_no_coop + 256)/8;
+		}
+		spin_unlock(&ad->io_context->lock);
+	}
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static void as_update_thinktime(struct as_data *ad, struct as_io_context *aic,
+				unsigned long ttime)
+{
+	/* fixed point: 1.0 == 1<<8 */
+	if (aic->ttime_samples == 0) {
+		ad->new_ttime_total = (7*ad->new_ttime_total + 256*ttime) / 8;
+		ad->new_ttime_mean = ad->new_ttime_total / 256;
+
+		ad->exit_prob = (7*ad->exit_prob)/8;
+	}
+	aic->ttime_samples = (7*aic->ttime_samples + 256) / 8;
+	aic->ttime_total = (7*aic->ttime_total + 256*ttime) / 8;
+	aic->ttime_mean = (aic->ttime_total + 128) / aic->ttime_samples;
+}
+
+static void as_update_seekdist(struct as_data *ad, struct as_io_context *aic,
+				sector_t sdist)
+{
+	u64 total;
+
+	if (aic->seek_samples == 0) {
+		ad->new_seek_total = (7*ad->new_seek_total + 256*(u64)sdist)/8;
+		ad->new_seek_mean = ad->new_seek_total / 256;
+	}
+
+	/*
+	 * Don't allow the seek distance to get too large from the
+	 * odd fragment, pagein, etc
+	 */
+	if (aic->seek_samples <= 60) /* second&third seek */
+		sdist = min(sdist, (aic->seek_mean * 4) + 2*1024*1024);
+	else
+		sdist = min(sdist, (aic->seek_mean * 4)	+ 2*1024*64);
+
+	aic->seek_samples = (7*aic->seek_samples + 256) / 8;
+	aic->seek_total = (7*aic->seek_total + (u64)256*sdist) / 8;
+	total = aic->seek_total + (aic->seek_samples/2);
+	do_div(total, aic->seek_samples);
+	aic->seek_mean = (sector_t)total;
+}
+
+/*
+ * as_update_iohist keeps a decaying histogram of IO thinktimes, and
+ * updates @aic->ttime_mean based on that. It is called when a new
+ * request is queued.
+ */
+static void as_update_iohist(struct as_data *ad, struct as_io_context *aic,
+				struct request *rq)
+{
+	int data_dir = rq_is_sync(rq);
+	unsigned long thinktime = 0;
+	sector_t seek_dist;
+
+	if (aic == NULL)
+		return;
+
+	if (data_dir == REQ_SYNC) {
+		unsigned long in_flight = atomic_read(&aic->nr_queued)
+					+ atomic_read(&aic->nr_dispatched);
+		spin_lock(&aic->lock);
+		if (test_bit(AS_TASK_IORUNNING, &aic->state) ||
+			test_bit(AS_TASK_IOSTARTED, &aic->state)) {
+			/* Calculate read -> read thinktime */
+			if (test_bit(AS_TASK_IORUNNING, &aic->state)
+							&& in_flight == 0) {
+				thinktime = jiffies - aic->last_end_request;
+				thinktime = min(thinktime, MAX_THINKTIME-1);
+			}
+			as_update_thinktime(ad, aic, thinktime);
+
+			/* Calculate read -> read seek distance */
+			if (aic->last_request_pos < rq->sector)
+				seek_dist = rq->sector - aic->last_request_pos;
+			else
+				seek_dist = aic->last_request_pos - rq->sector;
+			as_update_seekdist(ad, aic, seek_dist);
+		}
+		aic->last_request_pos = rq->sector + rq->nr_sectors;
+		set_bit(AS_TASK_IOSTARTED, &aic->state);
+		spin_unlock(&aic->lock);
+	}
+}
+
+/*
+ * as_close_req decides if one request is considered "close" to the
+ * previous one issued.
+ */
+static int as_close_req(struct as_data *ad, struct as_io_context *aic,
+			struct request *rq)
+{
+	unsigned long delay;	/* jiffies */
+	sector_t last = ad->last_sector[ad->batch_data_dir];
+	sector_t next = rq->sector;
+	sector_t delta; /* acceptable close offset (in sectors) */
+	sector_t s;
+
+	if (ad->antic_status == ANTIC_OFF || !ad->ioc_finished)
+		delay = 0;
+	else
+		delay = jiffies - ad->antic_start;
+
+	if (delay == 0)
+		delta = 8192;
+	else if (delay <= (20 * HZ / 1000) && delay <= ad->antic_expire)
+		delta = 8192 << delay;
+	else
+		return 1;
+
+	if ((last <= next + (delta>>1)) && (next <= last + delta))
+		return 1;
+
+	if (last < next)
+		s = next - last;
+	else
+		s = last - next;
+
+	if (aic->seek_samples == 0) {
+		/*
+		 * Process has just started IO. Use past statistics to
+		 * gauge success possibility
+		 */
+		if (ad->new_seek_mean > s) {
+			/* this request is better than what we're expecting */
+			return 1;
+		}
+
+	} else {
+		if (aic->seek_mean > s) {
+			/* this request is better than what we're expecting */
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * as_can_break_anticipation returns true if we have been anticipating this
+ * request.
+ *
+ * It also returns true if the process against which we are anticipating
+ * submits a write - that's presumably an fsync, O_SYNC write, etc. We want to
+ * dispatch it ASAP, because we know that application will not be submitting
+ * any new reads.
+ *
+ * If the task which has submitted the request has exited, break anticipation.
+ *
+ * If this task has queued some other IO, do not enter enticipation.
+ */
+static int as_can_break_anticipation(struct as_data *ad, struct request *rq)
+{
+	struct io_context *ioc;
+	struct as_io_context *aic;
+
+	ioc = ad->io_context;
+	BUG_ON(!ioc);
+	spin_lock(&ioc->lock);
+
+	if (rq && ioc == RQ_IOC(rq)) {
+		/* request from same process */
+		spin_unlock(&ioc->lock);
+		return 1;
+	}
+
+	if (ad->ioc_finished && as_antic_expired(ad)) {
+		/*
+		 * In this situation status should really be FINISHED,
+		 * however the timer hasn't had the chance to run yet.
+		 */
+		spin_unlock(&ioc->lock);
+		return 1;
+	}
+
+	aic = ioc->aic;
+	if (!aic) {
+		spin_unlock(&ioc->lock);
+		return 0;
+	}
+
+	if (atomic_read(&aic->nr_queued) > 0) {
+		/* process has more requests queued */
+		spin_unlock(&ioc->lock);
+		return 1;
+	}
+
+	if (atomic_read(&aic->nr_dispatched) > 0) {
+		/* process has more requests dispatched */
+		spin_unlock(&ioc->lock);
+		return 1;
+	}
+
+	if (rq && rq_is_sync(rq) && as_close_req(ad, aic, rq)) {
+		/*
+		 * Found a close request that is not one of ours.
+		 *
+		 * This makes close requests from another process update
+		 * our IO history. Is generally useful when there are
+		 * two or more cooperating processes working in the same
+		 * area.
+		 */
+		if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
+			if (aic->ttime_samples == 0)
+				ad->exit_prob = (7*ad->exit_prob + 256)/8;
+
+			ad->exit_no_coop = (7*ad->exit_no_coop)/8;
+		}
+
+		as_update_iohist(ad, aic, rq);
+		spin_unlock(&ioc->lock);
+		return 1;
+	}
+
+	if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
+		/* process anticipated on has exited */
+		if (aic->ttime_samples == 0)
+			ad->exit_prob = (7*ad->exit_prob + 256)/8;
+
+		if (ad->exit_no_coop > 128) {
+			spin_unlock(&ioc->lock);
+			return 1;
+		}
+	}
+
+	if (aic->ttime_samples == 0) {
+		if (ad->new_ttime_mean > ad->antic_expire) {
+			spin_unlock(&ioc->lock);
+			return 1;
+		}
+		if (ad->exit_prob * ad->exit_no_coop > 128*256) {
+			spin_unlock(&ioc->lock);
+			return 1;
+		}
+	} else if (aic->ttime_mean > ad->antic_expire) {
+		/* the process thinks too much between requests */
+		spin_unlock(&ioc->lock);
+		return 1;
+	}
+	spin_unlock(&ioc->lock);
+	return 0;
+}
+
+/*
+ * as_can_anticipate indicates whether we should either run rq
+ * or keep anticipating a better request.
+ */
+static int as_can_anticipate(struct as_data *ad, struct request *rq)
+{
+#if 0 /* disable for now, we need to check tag level as well */
+	/*
+	 * SSD device without seek penalty, disable idling
+	 */
+	if (blk_queue_nonrot(ad->q)) axman
+		return 0;
+#endif
+
+	if (!ad->io_context)
+		/*
+		 * Last request submitted was a write
+		 */
+		return 0;
+
+	if (ad->antic_status == ANTIC_FINISHED)
+		/*
+		 * Don't restart if we have just finished. Run the next request
+		 */
+		return 0;
+
+	if (as_can_break_anticipation(ad, rq))
+		/*
+		 * This request is a good candidate. Don't keep anticipating,
+		 * run it.
+		 */
+		return 0;
+
+	/*
+	 * OK from here, we haven't finished, and don't have a decent request!
+	 * Status is either ANTIC_OFF so start waiting,
+	 * ANTIC_WAIT_REQ so continue waiting for request to finish
+	 * or ANTIC_WAIT_NEXT so continue waiting for an acceptable request.
+	 */
+
+	return 1;
+}
+
+/*
+ * as_update_rq must be called whenever a request (rq) is added to
+ * the sort_list. This function keeps caches up to date, and checks if the
+ * request might be one we are "anticipating"
+ */
+static void as_update_rq(struct as_data *ad, struct request *rq)
+{
+	const int data_dir = rq_is_sync(rq);
+
+	/* keep the next_rq cache up to date */
+	ad->next_rq[data_dir] = as_choose_req(ad, rq, ad->next_rq[data_dir]);
+
+	/*
+	 * have we been anticipating this request?
+	 * or does it come from the same process as the one we are anticipating
+	 * for?
+	 */
+	if (ad->antic_status == ANTIC_WAIT_REQ
+			|| ad->antic_status == ANTIC_WAIT_NEXT) {
+		if (as_can_break_anticipation(ad, rq))
+			as_antic_stop(ad);
+	}
+}
+
+/*
+ * Gathers timings and resizes the write batch automatically
+ */
+static void update_write_batch(struct as_data *ad)
+{
+	unsigned long batch = ad->batch_expire[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(struct request_queue *q, struct request *rq)
+{
+	struct as_data *ad = q->elevator->elevator_data;
+
+	WARN_ON(!list_empty(&rq->queuelist));
+
+	if (RQ_STATE(rq) != AS_RQ_REMOVED) {
+		WARN(1, "rq->state %d\n", RQ_STATE(rq));
+		goto out;
+	}
+
+	if (ad->changed_batch && ad->nr_dispatched == 1) {
+		ad->current_batch_expires = jiffies +
+					ad->batch_expire[ad->batch_data_dir];
+		kblockd_schedule_work(q, &ad->antic_work);
+		ad->changed_batch = 0;
+
+		if (ad->batch_data_dir == 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 == rq_is_sync(rq)) {
+		update_write_batch(ad);
+		ad->current_batch_expires = jiffies +
+				ad->batch_expire[REQ_SYNC];
+		ad->new_batch = 0;
+	}
+
+	if (ad->io_context == RQ_IOC(rq) && ad->io_context) {
+		ad->antic_start = jiffies;
+		ad->ioc_finished = 1;
+		if (ad->antic_status == ANTIC_WAIT_REQ) {
+			/*
+			 * We were waiting on this request, now anticipate
+			 * the next one
+			 */
+			as_antic_waitnext(ad);
+		}
+	}
+
+	as_put_io_context(rq);
+out:
+	RQ_SET_STATE(rq, AS_RQ_POSTSCHED);
+}
+
+/*
+ * as_remove_queued_request removes a request from the pre dispatch queue
+ * without updating refcounts. It is expected the caller will drop the
+ * reference unless it replaces the request at somepart of the elevator
+ * (ie. the dispatch queue)
+ */
+static void as_remove_queued_request(struct request_queue *q,
+				     struct request *rq)
+{
+	const int data_dir = rq_is_sync(rq);
+	struct as_data *ad = q->elevator->elevator_data;
+	struct io_context *ioc;
+
+	WARN_ON(RQ_STATE(rq) != AS_RQ_QUEUED);
+
+	ioc = RQ_IOC(rq);
+	if (ioc && ioc->aic) {
+		BUG_ON(!atomic_read(&ioc->aic->nr_queued));
+		atomic_dec(&ioc->aic->nr_queued);
+	}
+
+	/*
+	 * Update the "next_rq" cache if we are about to remove its
+	 * entry
+	 */
+	if (ad->next_rq[data_dir] == rq)
+		ad->next_rq[data_dir] = as_find_next_rq(ad, rq);
+
+	rq_fifo_clear(rq);
+	as_del_rq_rb(ad, rq);
+}
+
+/*
+ * as_fifo_expired returns 0 if there are no expired requests on the fifo,
+ * 1 otherwise.  It is ratelimited so that we only perform the check once per
+ * `fifo_expire' interval.  Otherwise a large number of expired requests
+ * would create a hopeless seekstorm.
+ *
+ * See as_antic_expired comment.
+ */
+static int as_fifo_expired(struct as_data *ad, int adir)
+{
+	struct request *rq;
+	long delta_jif;
+
+	delta_jif = jiffies - ad->last_check_fifo[adir];
+	if (unlikely(delta_jif < 0))
+		delta_jif = -delta_jif;
+	if (delta_jif < ad->fifo_expire[adir])
+		return 0;
+
+	ad->last_check_fifo[adir] = jiffies;
+
+	if (list_empty(&ad->fifo_list[adir]))
+		return 0;
+
+	rq = rq_entry_fifo(ad->fifo_list[adir].next);
+
+	return time_after(jiffies, rq_fifo_time(rq));
+}
+
+/*
+ * as_batch_expired returns true if the current batch has expired. A batch
+ * is a set of reads or a set of writes.
+ */
+static inline int as_batch_expired(struct as_data *ad)
+{
+	if (ad->changed_batch || ad->new_batch)
+		return 0;
+
+	if (ad->batch_data_dir == 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 request *rq)
+{
+	const int data_dir = rq_is_sync(rq);
+
+	BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
+
+	as_antic_stop(ad);
+	ad->antic_status = ANTIC_OFF;
+
+	/*
+	 * This has to be set in order to be correctly updated by
+	 * as_find_next_rq
+	 */
+	ad->last_sector[data_dir] = rq->sector + rq->nr_sectors;
+
+	if (data_dir == REQ_SYNC) {
+		struct io_context *ioc = RQ_IOC(rq);
+		/* In case we have to anticipate after this */
+		copy_io_context(&ad->io_context, &ioc);
+	} else {
+		if (ad->io_context) {
+			put_io_context(ad->io_context);
+			ad->io_context = NULL;
+		}
+
+		if (ad->current_write_count != 0)
+			ad->current_write_count--;
+	}
+	ad->ioc_finished = 0;
+
+	ad->next_rq[data_dir] = as_find_next_rq(ad, rq);
+
+	/*
+	 * take it off the sort and fifo list, add to dispatch queue
+	 */
+	as_remove_queued_request(ad->q, rq);
+	WARN_ON(RQ_STATE(rq) != AS_RQ_QUEUED);
+
+	elv_dispatch_sort(ad->q, rq);
+
+	RQ_SET_STATE(rq, AS_RQ_DISPATCHED);
+	if (RQ_IOC(rq) && RQ_IOC(rq)->aic)
+		atomic_inc(&RQ_IOC(rq)->aic->nr_dispatched);
+	ad->nr_dispatched++;
+}
+
+/*
+ * as_dispatch_request selects the best request according to
+ * read/write expire, batch expire, etc, and moves it to the dispatch
+ * queue. Returns 1 if a request was found, 0 otherwise.
+ */
+static int as_dispatch_request(struct request_queue *q, int force)
+{
+	struct as_data *ad = q->elevator->elevator_data;
+	const int reads = !list_empty(&ad->fifo_list[REQ_SYNC]);
+	const int writes = !list_empty(&ad->fifo_list[REQ_ASYNC]);
+	struct request *rq;
+
+	if (unlikely(force)) {
+		/*
+		 * Forced dispatch, accounting is useless.  Reset
+		 * accounting states and dump fifo_lists.  Note that
+		 * batch_data_dir is reset to 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_rq[REQ_SYNC]) {
+			as_move_to_dispatch(ad, ad->next_rq[REQ_SYNC]);
+			dispatched++;
+		}
+		ad->last_check_fifo[REQ_SYNC] = jiffies;
+
+		while (ad->next_rq[REQ_ASYNC]) {
+			as_move_to_dispatch(ad, ad->next_rq[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
+		 */
+		rq = ad->next_rq[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, rq)) {
+				as_antic_waitreq(ad);
+				return 0;
+			}
+		}
+
+		if (rq) {
+			/* we have a "next request" */
+			if (reads && !writes)
+				ad->current_batch_expires =
+					jiffies + ad->batch_expire[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_ROOT(&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;
+		rq = rq_entry_fifo(ad->fifo_list[REQ_SYNC].next);
+		ad->last_check_fifo[ad->batch_data_dir] = jiffies;
+		goto dispatch_request;
+	}
+
+	/*
+	 * the last batch was a read
+	 */
+
+	if (writes) {
+dispatch_writes:
+		BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[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;
+		rq = rq_entry_fifo(ad->fifo_list[REQ_ASYNC].next);
+		ad->last_check_fifo[REQ_ASYNC] = jiffies;
+		goto dispatch_request;
+	}
+
+	BUG();
+	return 0;
+
+dispatch_request:
+	/*
+	 * If a request has expired, service it.
+	 */
+
+	if (as_fifo_expired(ad, ad->batch_data_dir)) {
+fifo_expired:
+		rq = rq_entry_fifo(ad->fifo_list[ad->batch_data_dir].next);
+	}
+
+	if (ad->changed_batch) {
+		WARN_ON(ad->new_batch);
+
+		if (ad->nr_dispatched)
+			return 0;
+
+		if (ad->batch_data_dir == REQ_ASYNC)
+			ad->current_batch_expires = jiffies +
+					ad->batch_expire[REQ_ASYNC];
+		else
+			ad->new_batch = 1;
+
+		ad->changed_batch = 0;
+	}
+
+	/*
+	 * rq is the selected appropriate request.
+	 */
+	as_move_to_dispatch(ad, rq);
+
+	return 1;
+}
+
+/*
+ * add rq to rbtree and fifo
+ */
+static void as_add_request(struct request_queue *q, struct request *rq)
+{
+	struct as_data *ad = q->elevator->elevator_data;
+	int data_dir;
+
+	RQ_SET_STATE(rq, AS_RQ_NEW);
+
+	data_dir = rq_is_sync(rq);
+
+	rq->elevator_private = as_get_io_context(q->node);
+
+	if (RQ_IOC(rq)) {
+		as_update_iohist(ad, RQ_IOC(rq)->aic, rq);
+		atomic_inc(&RQ_IOC(rq)->aic->nr_queued);
+	}
+
+	as_add_rq_rb(ad, rq);
+
+	/*
+	 * set expire time and add to fifo list
+	 */
+	rq_set_fifo_time(rq, jiffies + ad->fifo_expire[data_dir]);
+	list_add_tail(&rq->queuelist, &ad->fifo_list[data_dir]);
+
+	as_update_rq(ad, rq); /* keep state machine up to date */
+	RQ_SET_STATE(rq, AS_RQ_QUEUED);
+}
+
+static void as_activate_request(struct request_queue *q, struct request *rq)
+{
+	WARN_ON(RQ_STATE(rq) != AS_RQ_DISPATCHED);
+	RQ_SET_STATE(rq, AS_RQ_REMOVED);
+	if (RQ_IOC(rq) && RQ_IOC(rq)->aic)
+		atomic_dec(&RQ_IOC(rq)->aic->nr_dispatched);
+}
+
+static void as_deactivate_request(struct request_queue *q, struct request *rq)
+{
+	WARN_ON(RQ_STATE(rq) != AS_RQ_REMOVED);
+	RQ_SET_STATE(rq, AS_RQ_DISPATCHED);
+	if (RQ_IOC(rq) && RQ_IOC(rq)->aic)
+		atomic_inc(&RQ_IOC(rq)->aic->nr_dispatched);
+}
+
+/*
+ * as_queue_empty tells us if there are requests left in the device. It may
+ * not be the case that a driver can get the next request even if the queue
+ * is not empty - it is used in the block layer to check for plugging and
+ * merging opportunities
+ */
+static int as_queue_empty(struct request_queue *q)
+{
+	struct as_data *ad = q->elevator->elevator_data;
+
+	return list_empty(&ad->fifo_list[REQ_ASYNC])
+		&& list_empty(&ad->fifo_list[REQ_SYNC]);
+}
+
+static int
+as_merge(struct request_queue *q, struct request **req, struct bio *bio)
+{
+	struct as_data *ad = q->elevator->elevator_data;
+	sector_t rb_key = bio->bi_sector + bio_sectors(bio);
+	struct request *__rq;
+
+	/*
+	 * check for front merge
+	 */
+	__rq = elv_rb_find(&ad->sort_list[bio_data_dir(bio)], rb_key);
+	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+		*req = __rq;
+		return ELEVATOR_FRONT_MERGE;
+	}
+
+	return ELEVATOR_NO_MERGE;
+}
+
+static void as_merged_request(struct request_queue *q, struct request *req,
+			      int type)
+{
+	struct as_data *ad = q->elevator->elevator_data;
+
+	/*
+	 * if the merge was a front merge, we need to reposition request
+	 */
+	if (type == ELEVATOR_FRONT_MERGE) {
+		as_del_rq_rb(ad, req);
+		as_add_rq_rb(ad, req);
+		/*
+		 * Note! At this stage of this and the next function, our next
+		 * request may not be optimal - eg the request may have "grown"
+		 * behind the disk head. We currently don't bother adjusting.
+		 */
+	}
+}
+
+static void as_merged_requests(struct request_queue *q, struct request *req,
+			 	struct request *next)
+{
+	/*
+	 * if next expires before rq, assign its expire time to arq
+	 * and move into next position (next will be deleted) in fifo
+	 */
+	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
+		if (time_before(rq_fifo_time(next), rq_fifo_time(req))) {
+			list_move(&req->queuelist, &next->queuelist);
+			rq_set_fifo_time(req, rq_fifo_time(next));
+		}
+	}
+
+	/*
+	 * kill knowledge of next, this one is a goner
+	 */
+	as_remove_queued_request(q, next);
+	as_put_io_context(next);
+
+	RQ_SET_STATE(next, AS_RQ_MERGED);
+}
+
+/*
+ * This is executed in a "deferred" process context, by kblockd. It calls the
+ * driver's request_fn so the driver can submit that request.
+ *
+ * IMPORTANT! This guy will reenter the elevator, so set up all queue global
+ * state before calling, and don't rely on any state over calls.
+ *
+ * FIXME! dispatch queue is not a queue at all!
+ */
+static void as_work_handler(struct work_struct *work)
+{
+	struct as_data *ad = container_of(work, struct as_data, antic_work);
+	struct request_queue *q = ad->q;
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	blk_start_queueing(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static int as_may_queue(struct request_queue *q, int rw)
+{
+	int ret = ELV_MQUEUE_MAY;
+	struct as_data *ad = q->elevator->elevator_data;
+	struct io_context *ioc;
+	if (ad->antic_status == ANTIC_WAIT_REQ ||
+			ad->antic_status == ANTIC_WAIT_NEXT) {
+		ioc = as_get_io_context(q->node);
+		if (ad->io_context == ioc)
+			ret = ELV_MQUEUE_MUST;
+		put_io_context(ioc);
+	}
+
+	return ret;
+}
+
+static void as_exit_queue(struct elevator_queue *e)
+{
+	struct as_data *ad = e->elevator_data;
+
+	del_timer_sync(&ad->antic_timer);
+	cancel_work_sync(&ad->antic_work);
+
+	BUG_ON(!list_empty(&ad->fifo_list[REQ_SYNC]));
+	BUG_ON(!list_empty(&ad->fifo_list[REQ_ASYNC]));
+
+	put_io_context(ad->io_context);
+	kfree(ad);
+}
+
+/*
+ * initialize elevator private data (as_data).
+ */
+static void *as_init_queue(struct request_queue *q)
+{
+	struct as_data *ad;
+
+	ad = kmalloc_node(sizeof(*ad), GFP_KERNEL | __GFP_ZERO, q->node);
+	if (!ad)
+		return NULL;
+
+	ad->q = q; /* Identify what queue the data belongs to */
+
+	/* anticipatory scheduling helpers */
+	ad->antic_timer.function = as_antic_timeout;
+	ad->antic_timer.data = (unsigned long)q;
+	init_timer(&ad->antic_timer);
+	INIT_WORK(&ad->antic_work, as_work_handler);
+
+	INIT_LIST_HEAD(&ad->fifo_list[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;
+
+	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 ad;
+}
+
+/*
+ * sysfs parts below
+ */
+
+static ssize_t
+as_var_show(unsigned int var, char *page)
+{
+	return sprintf(page, "%d\n", var);
+}
+
+static ssize_t
+as_var_store(unsigned long *var, const char *page, size_t count)
+{
+	char *p = (char *) page;
+
+	*var = simple_strtoul(p, &p, 10);
+	return count;
+}
+
+static ssize_t est_time_show(struct elevator_queue *e, char *page)
+{
+	struct as_data *ad = e->elevator_data;
+	int pos = 0;
+
+	pos += sprintf(page+pos, "%lu %% exit probability\n",
+				100*ad->exit_prob/256);
+	pos += sprintf(page+pos, "%lu %% probability of exiting without a "
+				"cooperating process submitting IO\n",
+				100*ad->exit_no_coop/256);
+	pos += sprintf(page+pos, "%lu ms new thinktime\n", ad->new_ttime_mean);
+	pos += sprintf(page+pos, "%llu sectors new seek distance\n",
+				(unsigned long long)ad->new_seek_mean);
+
+	return pos;
+}
+
+#define SHOW_FUNCTION(__FUNC, __VAR)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)	\
+{								\
+	struct as_data *ad = e->elevator_data;			\
+	return as_var_show(jiffies_to_msecs((__VAR)), (page));	\
+}
+SHOW_FUNCTION(as_read_expire_show, ad->fifo_expire[REQ_SYNC]);
+SHOW_FUNCTION(as_write_expire_show, ad->fifo_expire[REQ_ASYNC]);
+SHOW_FUNCTION(as_antic_expire_show, ad->antic_expire);
+SHOW_FUNCTION(as_read_batch_expire_show, ad->batch_expire[REQ_SYNC]);
+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(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct as_data *ad = e->elevator_data;				\
+	int ret = as_var_store(__PTR, (page), count);			\
+	if (*(__PTR) < (MIN))						\
+		*(__PTR) = (MIN);					\
+	else if (*(__PTR) > (MAX))					\
+		*(__PTR) = (MAX);					\
+	*(__PTR) = msecs_to_jiffies(*(__PTR));				\
+	return ret;							\
+}
+STORE_FUNCTION(as_read_expire_store, &ad->fifo_expire[REQ_SYNC], 0, INT_MAX);
+STORE_FUNCTION(as_write_expire_store, &ad->fifo_expire[REQ_ASYNC], 0, INT_MAX);
+STORE_FUNCTION(as_antic_expire_store, &ad->antic_expire, 0, INT_MAX);
+STORE_FUNCTION(as_read_batch_expire_store,
+			&ad->batch_expire[REQ_SYNC], 0, INT_MAX);
+STORE_FUNCTION(as_write_batch_expire_store,
+			&ad->batch_expire[REQ_ASYNC], 0, INT_MAX);
+#undef STORE_FUNCTION
+
+#define AS_ATTR(name) \
+	__ATTR(name, S_IRUGO|S_IWUSR, as_##name##_show, as_##name##_store)
+
+static struct elv_fs_entry as_attrs[] = {
+	__ATTR_RO(est_time),
+	AS_ATTR(read_expire),
+	AS_ATTR(write_expire),
+	AS_ATTR(antic_expire),
+	AS_ATTR(read_batch_expire),
+	AS_ATTR(write_batch_expire),
+	__ATTR_NULL
+};
+
+static struct elevator_type iosched_as = {
+	.ops = {
+		.elevator_merge_fn = 		as_merge,
+		.elevator_merged_fn =		as_merged_request,
+		.elevator_merge_req_fn =	as_merged_requests,
+		.elevator_dispatch_fn =		as_dispatch_request,
+		.elevator_add_req_fn =		as_add_request,
+		.elevator_activate_req_fn =	as_activate_request,
+		.elevator_deactivate_req_fn = 	as_deactivate_request,
+		.elevator_queue_empty_fn =	as_queue_empty,
+		.elevator_completed_req_fn =	as_completed_request,
+		.elevator_former_req_fn =	elv_rb_former_request,
+		.elevator_latter_req_fn =	elv_rb_latter_request,
+		.elevator_may_queue_fn =	as_may_queue,
+		.elevator_init_fn =		as_init_queue,
+		.elevator_exit_fn =		as_exit_queue,
+		.trim =				as_trim,
+	},
+
+	.elevator_attrs = as_attrs,
+	.elevator_name = "anticipatory",
+	.elevator_owner = THIS_MODULE,
+};
+
+static int __init as_init(void)
+{
+	elv_register(&iosched_as);
+
+	return 0;
+}
+
+static void __exit as_exit(void)
+{
+	DECLARE_COMPLETION_ONSTACK(all_gone);
+	elv_unregister(&iosched_as);
+	ioc_gone = &all_gone;
+	/* ioc_gone's update must be visible before reading ioc_count */
+	smp_wmb();
+	if (elv_ioc_count_read(ioc_count))
+		wait_for_completion(&all_gone);
+	synchronize_rcu();
+}
+
+module_init(as_init);
+module_exit(as_exit);
+
+MODULE_AUTHOR("Nick Piggin");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("anticipatory IO scheduler");
diff --git a/libdde-linux26/contrib/block/blk-barrier.c b/libdde-linux26/contrib/block/blk-barrier.c
new file mode 100644
index 00000000..f7dae57e
--- /dev/null
+++ b/libdde-linux26/contrib/block/blk-barrier.c
@@ -0,0 +1,419 @@
+/*
+ * Functions related to barrier IO handling
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+
+#include "blk.h"
+
+/**
+ * blk_queue_ordered - does this queue support ordered writes
+ * @q:        the request queue
+ * @ordered:  one of QUEUE_ORDERED_*
+ * @prepare_flush_fn: rq setup helper for cache flush ordered writes
+ *
+ * Description:
+ *   For journalled file systems, doing ordered writes on a commit
+ *   block instead of explicitly doing wait_on_buffer (which is bad
+ *   for performance) can be a big win. Block drivers supporting this
+ *   feature should call this function and indicate so.
+ *
+ **/
+int blk_queue_ordered(struct request_queue *q, unsigned ordered,
+		      prepare_flush_fn *prepare_flush_fn)
+{
+	if (!prepare_flush_fn && (ordered & (QUEUE_ORDERED_DO_PREFLUSH |
+					     QUEUE_ORDERED_DO_POSTFLUSH))) {
+		printk(KERN_ERR "%s: prepare_flush_fn required\n", __func__);
+		return -EINVAL;
+	}
+
+	if (ordered != QUEUE_ORDERED_NONE &&
+	    ordered != QUEUE_ORDERED_DRAIN &&
+	    ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
+	    ordered != QUEUE_ORDERED_DRAIN_FUA &&
+	    ordered != QUEUE_ORDERED_TAG &&
+	    ordered != QUEUE_ORDERED_TAG_FLUSH &&
+	    ordered != QUEUE_ORDERED_TAG_FUA) {
+		printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
+		return -EINVAL;
+	}
+
+	q->ordered = ordered;
+	q->next_ordered = ordered;
+	q->prepare_flush_fn = prepare_flush_fn;
+
+	return 0;
+}
+EXPORT_SYMBOL(blk_queue_ordered);
+
+/*
+ * Cache flushing for ordered writes handling
+ */
+unsigned blk_ordered_cur_seq(struct request_queue *q)
+{
+	if (!q->ordseq)
+		return 0;
+	return 1 << ffz(q->ordseq);
+}
+
+unsigned blk_ordered_req_seq(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	BUG_ON(q->ordseq == 0);
+
+	if (rq == &q->pre_flush_rq)
+		return QUEUE_ORDSEQ_PREFLUSH;
+	if (rq == &q->bar_rq)
+		return QUEUE_ORDSEQ_BAR;
+	if (rq == &q->post_flush_rq)
+		return QUEUE_ORDSEQ_POSTFLUSH;
+
+	/*
+	 * !fs requests don't need to follow barrier ordering.  Always
+	 * put them at the front.  This fixes the following deadlock.
+	 *
+	 * http://thread.gmane.org/gmane.linux.kernel/537473
+	 */
+	if (!blk_fs_request(rq))
+		return QUEUE_ORDSEQ_DRAIN;
+
+	if ((rq->cmd_flags & REQ_ORDERED_COLOR) ==
+	    (q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR))
+		return QUEUE_ORDSEQ_DRAIN;
+	else
+		return QUEUE_ORDSEQ_DONE;
+}
+
+bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
+{
+	struct request *rq;
+
+	if (error && !q->orderr)
+		q->orderr = error;
+
+	BUG_ON(q->ordseq & seq);
+	q->ordseq |= seq;
+
+	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
+		return false;
+
+	/*
+	 * Okay, sequence complete.
+	 */
+	q->ordseq = 0;
+	rq = q->orig_bar_rq;
+
+	if (__blk_end_request(rq, q->orderr, blk_rq_bytes(rq)))
+		BUG();
+
+	return true;
+}
+
+static void pre_flush_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_PREFLUSH, error);
+}
+
+static void bar_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_BAR, error);
+}
+
+static void post_flush_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
+}
+
+static void queue_flush(struct request_queue *q, unsigned which)
+{
+	struct request *rq;
+	rq_end_io_fn *end_io;
+
+	if (which == QUEUE_ORDERED_DO_PREFLUSH) {
+		rq = &q->pre_flush_rq;
+		end_io = pre_flush_end_io;
+	} else {
+		rq = &q->post_flush_rq;
+		end_io = post_flush_end_io;
+	}
+
+	blk_rq_init(q, rq);
+	rq->cmd_flags = REQ_HARDBARRIER;
+	rq->rq_disk = q->bar_rq.rq_disk;
+	rq->end_io = end_io;
+	q->prepare_flush_fn(q, rq);
+
+	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
+}
+
+static inline bool start_ordered(struct request_queue *q, struct request **rqp)
+{
+	struct request *rq = *rqp;
+	unsigned skip = 0;
+
+	q->orderr = 0;
+	q->ordered = q->next_ordered;
+	q->ordseq |= QUEUE_ORDSEQ_STARTED;
+
+	/*
+	 * For an empty barrier, there's no actual BAR request, which
+	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
+	 */
+	if (!rq->hard_nr_sectors) {
+		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
+				QUEUE_ORDERED_DO_POSTFLUSH);
+		/*
+		 * Empty barrier on a write-through device w/ ordered
+		 * tag has no command to issue and without any command
+		 * to issue, ordering by tag can't be used.  Drain
+		 * instead.
+		 */
+		if ((q->ordered & QUEUE_ORDERED_BY_TAG) &&
+		    !(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) {
+			q->ordered &= ~QUEUE_ORDERED_BY_TAG;
+			q->ordered |= QUEUE_ORDERED_BY_DRAIN;
+		}
+	}
+
+	/* stash away the original request */
+	elv_dequeue_request(q, rq);
+	q->orig_bar_rq = rq;
+	rq = NULL;
+
+	/*
+	 * Queue ordered sequence.  As we stack them at the head, we
+	 * need to queue in reverse order.  Note that we rely on that
+	 * no fs request uses ELEVATOR_INSERT_FRONT and thus no fs
+	 * request gets inbetween ordered sequence.
+	 */
+	if (q->ordered & QUEUE_ORDERED_DO_POSTFLUSH) {
+		queue_flush(q, QUEUE_ORDERED_DO_POSTFLUSH);
+		rq = &q->post_flush_rq;
+	} else
+		skip |= QUEUE_ORDSEQ_POSTFLUSH;
+
+	if (q->ordered & QUEUE_ORDERED_DO_BAR) {
+		rq = &q->bar_rq;
+
+		/* initialize proxy request and queue it */
+		blk_rq_init(q, rq);
+		if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
+			rq->cmd_flags |= REQ_RW;
+		if (q->ordered & QUEUE_ORDERED_DO_FUA)
+			rq->cmd_flags |= REQ_FUA;
+		init_request_from_bio(rq, q->orig_bar_rq->bio);
+		rq->end_io = bar_end_io;
+
+		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
+	} else
+		skip |= QUEUE_ORDSEQ_BAR;
+
+	if (q->ordered & QUEUE_ORDERED_DO_PREFLUSH) {
+		queue_flush(q, QUEUE_ORDERED_DO_PREFLUSH);
+		rq = &q->pre_flush_rq;
+	} else
+		skip |= QUEUE_ORDSEQ_PREFLUSH;
+
+	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && q->in_flight)
+		rq = NULL;
+	else
+		skip |= QUEUE_ORDSEQ_DRAIN;
+
+	*rqp = rq;
+
+	/*
+	 * Complete skipped sequences.  If whole sequence is complete,
+	 * return false to tell elevator that this request is gone.
+	 */
+	return !blk_ordered_complete_seq(q, skip, 0);
+}
+
+bool blk_do_ordered(struct request_queue *q, struct request **rqp)
+{
+	struct request *rq = *rqp;
+	const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
+
+	if (!q->ordseq) {
+		if (!is_barrier)
+			return true;
+
+		if (q->next_ordered != QUEUE_ORDERED_NONE)
+			return start_ordered(q, rqp);
+		else {
+			/*
+			 * Queue ordering not supported.  Terminate
+			 * with prejudice.
+			 */
+			elv_dequeue_request(q, rq);
+			if (__blk_end_request(rq, -EOPNOTSUPP,
+					      blk_rq_bytes(rq)))
+				BUG();
+			*rqp = NULL;
+			return false;
+		}
+	}
+
+	/*
+	 * Ordered sequence in progress
+	 */
+
+	/* Special requests are not subject to ordering rules. */
+	if (!blk_fs_request(rq) &&
+	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
+		return true;
+
+	if (q->ordered & QUEUE_ORDERED_BY_TAG) {
+		/* Ordered by tag.  Blocking the next barrier is enough. */
+		if (is_barrier && rq != &q->bar_rq)
+			*rqp = NULL;
+	} else {
+		/* Ordered by draining.  Wait for turn. */
+		WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
+		if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
+			*rqp = NULL;
+	}
+
+	return true;
+}
+
+static void bio_end_empty_barrier(struct bio *bio, int err)
+{
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	}
+
+	complete(bio->bi_private);
+}
+
+/**
+ * blkdev_issue_flush - queue a flush
+ * @bdev:	blockdev to issue flush for
+ * @error_sector:	error sector
+ *
+ * Description:
+ *    Issue a flush for the block device in question. Caller can supply
+ *    room for storing the error offset in case of a flush error, if they
+ *    wish to.
+ */
+int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+	struct request_queue *q;
+	struct bio *bio;
+	int ret;
+
+	if (bdev->bd_disk == NULL)
+		return -ENXIO;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	bio = bio_alloc(GFP_KERNEL, 0);
+	if (!bio)
+		return -ENOMEM;
+
+	bio->bi_end_io = bio_end_empty_barrier;
+	bio->bi_private = &wait;
+	bio->bi_bdev = bdev;
+	submit_bio(WRITE_BARRIER, bio);
+
+	wait_for_completion(&wait);
+
+	/*
+	 * The driver must store the error location in ->bi_sector, if
+	 * it supports it. For non-stacked drivers, this should be copied
+	 * from rq->sector.
+	 */
+	if (error_sector)
+		*error_sector = bio->bi_sector;
+
+	ret = 0;
+	if (bio_flagged(bio, BIO_EOPNOTSUPP))
+		ret = -EOPNOTSUPP;
+	else if (!bio_flagged(bio, BIO_UPTODATE))
+		ret = -EIO;
+
+	bio_put(bio);
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_flush);
+
+static void blkdev_discard_end_io(struct bio *bio, int err)
+{
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	}
+
+	bio_put(bio);
+}
+
+/**
+ * blkdev_issue_discard - queue a discard
+ * @bdev:	blockdev to issue discard for
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to discard
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *    Issue a discard request for the sectors in question. Does not wait.
+ */
+int blkdev_issue_discard(struct block_device *bdev,
+			 sector_t sector, sector_t nr_sects, gfp_t gfp_mask)
+{
+	struct request_queue *q;
+	struct bio *bio;
+	int ret = 0;
+
+	if (bdev->bd_disk == NULL)
+		return -ENXIO;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	if (!q->prepare_discard_fn)
+		return -EOPNOTSUPP;
+
+	while (nr_sects && !ret) {
+		bio = bio_alloc(gfp_mask, 0);
+		if (!bio)
+			return -ENOMEM;
+
+		bio->bi_end_io = blkdev_discard_end_io;
+		bio->bi_bdev = bdev;
+
+		bio->bi_sector = sector;
+
+		if (nr_sects > q->max_hw_sectors) {
+			bio->bi_size = q->max_hw_sectors << 9;
+			nr_sects -= q->max_hw_sectors;
+			sector += q->max_hw_sectors;
+		} else {
+			bio->bi_size = nr_sects << 9;
+			nr_sects = 0;
+		}
+		bio_get(bio);
+		submit_bio(DISCARD_BARRIER, bio);
+
+		/* Check if it failed immediately */
+		if (bio_flagged(bio, BIO_EOPNOTSUPP))
+			ret = -EOPNOTSUPP;
+		else if (!bio_flagged(bio, BIO_UPTODATE))
+			ret = -EIO;
+		bio_put(bio);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_discard);
diff --git a/libdde-linux26/contrib/block/blk-exec.c b/libdde-linux26/contrib/block/blk-exec.c
new file mode 100644
index 00000000..6af716d1
--- /dev/null
+++ b/libdde-linux26/contrib/block/blk-exec.c
@@ -0,0 +1,106 @@
+/*
+ * Functions related to setting various queue properties from drivers
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+
+#include "blk.h"
+
+/*
+ * for max sense size
+ */
+#include <scsi/scsi_cmnd.h>
+
+/**
+ * blk_end_sync_rq - executes a completion event on a request
+ * @rq: request to complete
+ * @error: end I/O status of the request
+ */
+static void blk_end_sync_rq(struct request *rq, int error)
+{
+	struct completion *waiting = rq->end_io_data;
+
+	rq->end_io_data = NULL;
+	__blk_put_request(rq->q, rq);
+
+	/*
+	 * complete last, if this is a stack request the process (and thus
+	 * the rq pointer) could be invalid right after this complete()
+	 */
+	complete(waiting);
+}
+
+/**
+ * blk_execute_rq_nowait - insert a request into queue for execution
+ * @q:		queue to insert the request in
+ * @bd_disk:	matching gendisk
+ * @rq:		request to insert
+ * @at_head:    insert request at head or tail of queue
+ * @done:	I/O completion handler
+ *
+ * Description:
+ *    Insert a fully prepared request at the back of the I/O scheduler queue
+ *    for execution.  Don't wait for completion.
+ */
+void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
+			   struct request *rq, int at_head,
+			   rq_end_io_fn *done)
+{
+	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
+
+	rq->rq_disk = bd_disk;
+	rq->cmd_flags |= REQ_NOMERGE;
+	rq->end_io = done;
+	WARN_ON(irqs_disabled());
+	spin_lock_irq(q->queue_lock);
+	__elv_add_request(q, rq, where, 1);
+	__generic_unplug_device(q);
+	/* the queue is stopped so it won't be plugged+unplugged */
+	if (blk_pm_resume_request(rq))
+		q->request_fn(q);
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
+
+/**
+ * blk_execute_rq - insert a request into queue for execution
+ * @q:		queue to insert the request in
+ * @bd_disk:	matching gendisk
+ * @rq:		request to insert
+ * @at_head:    insert request at head or tail of queue
+ *
+ * Description:
+ *    Insert a fully prepared request at the back of the I/O scheduler queue
+ *    for execution and wait for completion.
+ */
+int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
+		   struct request *rq, int at_head)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+	char sense[SCSI_SENSE_BUFFERSIZE];
+	int err = 0;
+
+	/*
+	 * we need an extra reference to the request, so we can look at
+	 * it after io completion
+	 */
+	rq->ref_count++;
+
+	if (!rq->sense) {
+		memset(sense, 0, sizeof(sense));
+		rq->sense = sense;
+		rq->sense_len = 0;
+	}
+
+	rq->end_io_data = &wait;
+	blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
+	wait_for_completion(&wait);
+
+	if (rq->errors)
+		err = -EIO;
+
+	return err;
+}
+EXPORT_SYMBOL(blk_execute_rq);
diff --git a/libdde-linux26/contrib/block/blk-ioc.c b/libdde-linux26/contrib/block/blk-ioc.c
new file mode 100644
index 00000000..e7235861
--- /dev/null
+++ b/libdde-linux26/contrib/block/blk-ioc.c
@@ -0,0 +1,182 @@
+/*
+ * Functions related to io context handling
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
+
+#include "blk.h"
+
+#include <ddekit/timer.h>
+
+/*
+ * For io context allocations
+ */
+static struct kmem_cache *iocontext_cachep;
+
+static void cfq_dtor(struct io_context *ioc)
+{
+	if (!hlist_empty(&ioc->cic_list)) {
+		struct cfq_io_context *cic;
+
+		cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+								cic_list);
+		cic->dtor(ioc);
+	}
+}
+
+/*
+ * IO Context helper functions. put_io_context() returns 1 if there are no
+ * more users of this io context, 0 otherwise.
+ */
+int put_io_context(struct io_context *ioc)
+{
+	if (ioc == NULL)
+		return 1;
+
+	BUG_ON(atomic_read(&ioc->refcount) == 0);
+
+	if (atomic_dec_and_test(&ioc->refcount)) {
+		rcu_read_lock();
+		if (ioc->aic && ioc->aic->dtor)
+			ioc->aic->dtor(ioc->aic);
+		cfq_dtor(ioc);
+		rcu_read_unlock();
+
+		kmem_cache_free(iocontext_cachep, ioc);
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(put_io_context);
+
+static void cfq_exit(struct io_context *ioc)
+{
+	rcu_read_lock();
+
+	if (!hlist_empty(&ioc->cic_list)) {
+		struct cfq_io_context *cic;
+
+		cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+								cic_list);
+		cic->exit(ioc);
+	}
+	rcu_read_unlock();
+}
+
+/* Called by the exitting task */
+void exit_io_context(void)
+{
+	struct io_context *ioc;
+
+	task_lock(current);
+	ioc = current->io_context;
+	current->io_context = NULL;
+	task_unlock(current);
+
+	if (atomic_dec_and_test(&ioc->nr_tasks)) {
+		if (ioc->aic && ioc->aic->exit)
+			ioc->aic->exit(ioc->aic);
+		cfq_exit(ioc);
+
+		put_io_context(ioc);
+	}
+}
+
+struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
+{
+	struct io_context *ret;
+
+	ret = kmem_cache_alloc_node(iocontext_cachep, gfp_flags, node);
+	if (ret) {
+		atomic_set(&ret->refcount, 1);
+		atomic_set(&ret->nr_tasks, 1);
+		spin_lock_init(&ret->lock);
+		ret->ioprio_changed = 0;
+		ret->ioprio = 0;
+		ret->last_waited = jiffies; /* doesn't matter... */
+		ret->nr_batch_requests = 0; /* because this is 0 */
+		ret->aic = NULL;
+		INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
+		INIT_HLIST_HEAD(&ret->cic_list);
+		ret->ioc_data = NULL;
+	}
+
+	return ret;
+}
+
+/*
+ * If the current task has no IO context then create one and initialise it.
+ * Otherwise, return its existing IO context.
+ *
+ * This returned IO context doesn't have a specifically elevated refcount,
+ * but since the current task itself holds a reference, the context can be
+ * used in general code, so long as it stays within `current` context.
+ */
+struct io_context *current_io_context(gfp_t gfp_flags, int node)
+{
+	struct task_struct *tsk = current;
+	struct io_context *ret;
+
+	ret = tsk->io_context;
+	if (likely(ret))
+		return ret;
+
+	ret = alloc_io_context(gfp_flags, node);
+	if (ret) {
+		/* make sure set_task_ioprio() sees the settings above */
+		smp_wmb();
+		tsk->io_context = ret;
+	}
+
+	return ret;
+}
+
+/*
+ * If the current task has no IO context then create one and initialise it.
+ * If it does have a context, take a ref on it.
+ *
+ * This is always called in the context of the task which submitted the I/O.
+ */
+struct io_context *get_io_context(gfp_t gfp_flags, int node)
+{
+	struct io_context *ret = NULL;
+
+	/*
+	 * Check for unlikely race with exiting task. ioc ref count is
+	 * zero when ioc is being detached.
+	 */
+	do {
+		ret = current_io_context(gfp_flags, node);
+		if (unlikely(!ret))
+			break;
+	} while (!atomic_inc_not_zero(&ret->refcount));
+
+	return ret;
+}
+EXPORT_SYMBOL(get_io_context);
+
+void copy_io_context(struct io_context **pdst, struct io_context **psrc)
+{
+	struct io_context *src = *psrc;
+	struct io_context *dst = *pdst;
+
+	if (src) {
+		BUG_ON(atomic_read(&src->refcount) == 0);
+		atomic_inc(&src->refcount);
+		put_io_context(dst);
+		*pdst = src;
+	}
+}
+EXPORT_SYMBOL(copy_io_context);
+
+static int __init blk_ioc_init(void)
+{
+	iocontext_cachep = kmem_cache_create("blkdev_ioc",
+			sizeof(struct io_context), 0, SLAB_PANIC, NULL);
+	return 0;
+}
+subsys_initcall(blk_ioc_init);
diff --git a/libdde-linux26/contrib/block/blk-merge.c b/libdde-linux26/contrib/block/blk-merge.c
new file mode 100644
index 00000000..5a244f05
--- /dev/null
+++ b/libdde-linux26/contrib/block/blk-merge.c
@@ -0,0 +1,428 @@
+/*
+ * Functions related to segment and merge handling
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/scatterlist.h>
+
+#include "blk.h"
+
+void blk_recalc_rq_sectors(struct request *rq, int nsect)
+{
+	if (blk_fs_request(rq) || blk_discard_rq(rq)) {
+		rq->hard_sector += nsect;
+		rq->hard_nr_sectors -= nsect;
+
+		/*
+		 * Move the I/O submission pointers ahead if required.
+		 */
+		if ((rq->nr_sectors >= rq->hard_nr_sectors) &&
+		    (rq->sector <= rq->hard_sector)) {
+			rq->sector = rq->hard_sector;
+			rq->nr_sectors = rq->hard_nr_sectors;
+			rq->hard_cur_sectors = bio_cur_sectors(rq->bio);
+			rq->current_nr_sectors = rq->hard_cur_sectors;
+			rq->buffer = bio_data(rq->bio);
+		}
+
+		/*
+		 * if total number of sectors is less than the first segment
+		 * size, something has gone terribly wrong
+		 */
+		if (rq->nr_sectors < rq->current_nr_sectors) {
+			printk(KERN_ERR "blk: request botched\n");
+			rq->nr_sectors = rq->current_nr_sectors;
+		}
+	}
+}
+
+static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
+					     struct bio *bio)
+{
+	unsigned int phys_size;
+	struct bio_vec *bv, *bvprv = NULL;
+	int cluster, i, high, highprv = 1;
+	unsigned int seg_size, nr_phys_segs;
+	struct bio *fbio, *bbio;
+
+	if (!bio)
+		return 0;
+
+	fbio = bio;
+	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+	seg_size = 0;
+	phys_size = nr_phys_segs = 0;
+	for_each_bio(bio) {
+		bio_for_each_segment(bv, bio, i) {
+			/*
+			 * the trick here is making sure that a high page is
+			 * never considered part of another segment, since that
+			 * might change with the bounce page.
+			 */
+			high = page_to_pfn(bv->bv_page) > q->bounce_pfn;
+			if (high || highprv)
+				goto new_segment;
+			if (cluster) {
+				if (seg_size + bv->bv_len > q->max_segment_size)
+					goto new_segment;
+				if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
+					goto new_segment;
+				if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
+					goto new_segment;
+
+				seg_size += bv->bv_len;
+				bvprv = bv;
+				continue;
+			}
+new_segment:
+			if (nr_phys_segs == 1 && seg_size >
+			    fbio->bi_seg_front_size)
+				fbio->bi_seg_front_size = seg_size;
+
+			nr_phys_segs++;
+			bvprv = bv;
+			seg_size = bv->bv_len;
+			highprv = high;
+		}
+		bbio = bio;
+	}
+
+	if (nr_phys_segs == 1 && seg_size > fbio->bi_seg_front_size)
+		fbio->bi_seg_front_size = seg_size;
+	if (seg_size > bbio->bi_seg_back_size)
+		bbio->bi_seg_back_size = seg_size;
+
+	return nr_phys_segs;
+}
+
+void blk_recalc_rq_segments(struct request *rq)
+{
+	rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio);
+}
+
+void blk_recount_segments(struct request_queue *q, struct bio *bio)
+{
+	struct bio *nxt = bio->bi_next;
+
+	bio->bi_next = NULL;
+	bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio);
+	bio->bi_next = nxt;
+	bio->bi_flags |= (1 << BIO_SEG_VALID);
+}
+EXPORT_SYMBOL(blk_recount_segments);
+
+static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
+				   struct bio *nxt)
+{
+	if (!test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+		return 0;
+
+	if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
+	    q->max_segment_size)
+		return 0;
+
+	if (!bio_has_data(bio))
+		return 1;
+
+	if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
+		return 0;
+
+	/*
+	 * bio and nxt are contiguous in memory; check if the queue allows
+	 * these two to be merged into one
+	 */
+	if (BIO_SEG_BOUNDARY(q, bio, nxt))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * map a request to scatterlist, return number of sg entries setup. Caller
+ * must make sure sg can hold rq->nr_phys_segments entries
+ */
+int blk_rq_map_sg(struct request_queue *q, struct request *rq,
+		  struct scatterlist *sglist)
+{
+	struct bio_vec *bvec, *bvprv;
+	struct req_iterator iter;
+	struct scatterlist *sg;
+	int nsegs, cluster;
+
+	nsegs = 0;
+	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+
+	/*
+	 * for each bio in rq
+	 */
+	bvprv = NULL;
+	sg = NULL;
+	rq_for_each_segment(bvec, rq, iter) {
+		int nbytes = bvec->bv_len;
+
+		if (bvprv && cluster) {
+			if (sg->length + nbytes > q->max_segment_size)
+				goto new_segment;
+
+			if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
+				goto new_segment;
+			if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
+				goto new_segment;
+
+			sg->length += nbytes;
+		} else {
+new_segment:
+			if (!sg)
+				sg = sglist;
+			else {
+				/*
+				 * If the driver previously mapped a shorter
+				 * list, we could see a termination bit
+				 * prematurely unless it fully inits the sg
+				 * table on each mapping. We KNOW that there
+				 * must be more entries here or the driver
+				 * would be buggy, so force clear the
+				 * termination bit to avoid doing a full
+				 * sg_init_table() in drivers for each command.
+				 */
+				sg->page_link &= ~0x02;
+				sg = sg_next(sg);
+			}
+
+			sg_set_page(sg, bvec->bv_page, nbytes, bvec->bv_offset);
+			nsegs++;
+		}
+		bvprv = bvec;
+	} /* segments in rq */
+
+
+	if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
+	    (rq->data_len & q->dma_pad_mask)) {
+		unsigned int pad_len = (q->dma_pad_mask & ~rq->data_len) + 1;
+
+		sg->length += pad_len;
+		rq->extra_len += pad_len;
+	}
+
+	if (q->dma_drain_size && q->dma_drain_needed(rq)) {
+		if (rq->cmd_flags & REQ_RW)
+			memset(q->dma_drain_buffer, 0, q->dma_drain_size);
+
+		sg->page_link &= ~0x02;
+		sg = sg_next(sg);
+		sg_set_page(sg, virt_to_page(q->dma_drain_buffer),
+			    q->dma_drain_size,
+			    ((unsigned long)q->dma_drain_buffer) &
+			    (PAGE_SIZE - 1));
+		nsegs++;
+		rq->extra_len += q->dma_drain_size;
+	}
+
+	if (sg)
+		sg_mark_end(sg);
+
+	return nsegs;
+}
+EXPORT_SYMBOL(blk_rq_map_sg);
+
+static inline int ll_new_hw_segment(struct request_queue *q,
+				    struct request *req,
+				    struct bio *bio)
+{
+	int nr_phys_segs = bio_phys_segments(q, bio);
+
+	if (req->nr_phys_segments + nr_phys_segs > q->max_hw_segments
+	    || req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
+		req->cmd_flags |= REQ_NOMERGE;
+		if (req == q->last_merge)
+			q->last_merge = NULL;
+		return 0;
+	}
+
+	/*
+	 * This will form the start of a new hw segment.  Bump both
+	 * counters.
+	 */
+	req->nr_phys_segments += nr_phys_segs;
+	return 1;
+}
+
+int ll_back_merge_fn(struct request_queue *q, struct request *req,
+		     struct bio *bio)
+{
+	unsigned short max_sectors;
+
+	if (unlikely(blk_pc_request(req)))
+		max_sectors = q->max_hw_sectors;
+	else
+		max_sectors = q->max_sectors;
+
+	if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
+		req->cmd_flags |= REQ_NOMERGE;
+		if (req == q->last_merge)
+			q->last_merge = NULL;
+		return 0;
+	}
+	if (!bio_flagged(req->biotail, BIO_SEG_VALID))
+		blk_recount_segments(q, req->biotail);
+	if (!bio_flagged(bio, BIO_SEG_VALID))
+		blk_recount_segments(q, bio);
+
+	return ll_new_hw_segment(q, req, bio);
+}
+
+int ll_front_merge_fn(struct request_queue *q, struct request *req,
+		      struct bio *bio)
+{
+	unsigned short max_sectors;
+
+	if (unlikely(blk_pc_request(req)))
+		max_sectors = q->max_hw_sectors;
+	else
+		max_sectors = q->max_sectors;
+
+
+	if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
+		req->cmd_flags |= REQ_NOMERGE;
+		if (req == q->last_merge)
+			q->last_merge = NULL;
+		return 0;
+	}
+	if (!bio_flagged(bio, BIO_SEG_VALID))
+		blk_recount_segments(q, bio);
+	if (!bio_flagged(req->bio, BIO_SEG_VALID))
+		blk_recount_segments(q, req->bio);
+
+	return ll_new_hw_segment(q, req, bio);
+}
+
+static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
+				struct request *next)
+{
+	int total_phys_segments;
+	unsigned int seg_size =
+		req->biotail->bi_seg_back_size + next->bio->bi_seg_front_size;
+
+	/*
+	 * First check if the either of the requests are re-queued
+	 * requests.  Can't merge them if they are.
+	 */
+	if (req->special || next->special)
+		return 0;
+
+	/*
+	 * Will it become too large?
+	 */
+	if ((req->nr_sectors + next->nr_sectors) > q->max_sectors)
+		return 0;
+
+	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
+	if (blk_phys_contig_segment(q, req->biotail, next->bio)) {
+		if (req->nr_phys_segments == 1)
+			req->bio->bi_seg_front_size = seg_size;
+		if (next->nr_phys_segments == 1)
+			next->biotail->bi_seg_back_size = seg_size;
+		total_phys_segments--;
+	}
+
+	if (total_phys_segments > q->max_phys_segments)
+		return 0;
+
+	if (total_phys_segments > q->max_hw_segments)
+		return 0;
+
+	/* Merge is OK... */
+	req->nr_phys_segments = total_phys_segments;
+	return 1;
+}
+
+/*
+ * Has to be called with the request spinlock acquired
+ */
+static int attempt_merge(struct request_queue *q, struct request *req,
+			  struct request *next)
+{
+	if (!rq_mergeable(req) || !rq_mergeable(next))
+		return 0;
+
+	/*
+	 * not contiguous
+	 */
+	if (req->sector + req->nr_sectors != next->sector)
+		return 0;
+
+	if (rq_data_dir(req) != rq_data_dir(next)
+	    || req->rq_disk != next->rq_disk
+	    || next->special)
+		return 0;
+
+	if (blk_integrity_rq(req) != blk_integrity_rq(next))
+		return 0;
+
+	/*
+	 * If we are allowed to merge, then append bio list
+	 * from next to rq and release next. merge_requests_fn
+	 * will have updated segment counts, update sector
+	 * counts here.
+	 */
+	if (!ll_merge_requests_fn(q, req, next))
+		return 0;
+
+	/*
+	 * At this point we have either done a back merge
+	 * or front merge. We need the smaller start_time of
+	 * the merged requests to be the current request
+	 * for accounting purposes.
+	 */
+	if (time_after(req->start_time, next->start_time))
+		req->start_time = next->start_time;
+
+	req->biotail->bi_next = next->bio;
+	req->biotail = next->biotail;
+
+	req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;
+
+	elv_merge_requests(q, req, next);
+
+	if (req->rq_disk) {
+		struct hd_struct *part;
+		int cpu;
+
+		cpu = part_stat_lock();
+		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+
+		part_round_stats(cpu, part);
+		part_dec_in_flight(part);
+
+		part_stat_unlock();
+	}
+
+	req->ioprio = ioprio_best(req->ioprio, next->ioprio);
+	if (blk_rq_cpu_valid(next))
+		req->cpu = next->cpu;
+
+	__blk_put_request(q, next);
+	return 1;
+}
+
+int attempt_back_merge(struct request_queue *q, struct request *rq)
+{
+	struct request *next = elv_latter_request(q, rq);
+
+	if (next)
+		return attempt_merge(q, rq, next);
+
+	return 0;
+}
+
+int attempt_front_merge(struct request_queue *q, struct request *rq)
+{
+	struct request *prev = elv_former_request(q, rq);
+
+	if (prev)
+		return attempt_merge(q, prev, rq);
+
+	return 0;
+}
diff --git a/libdde-linux26/contrib/block/blk-settings.c b/libdde-linux26/contrib/block/blk-settings.c
new file mode 100644
index 00000000..61510191
--- /dev/null
+++ b/libdde-linux26/contrib/block/blk-settings.c
@@ -0,0 +1,474 @@
+/*
+ * Functions related to setting various queue properties from drivers
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
+
+#include "blk.h"
+
+#include <ddekit/timer.h>
+
+unsigned long blk_max_low_pfn;
+EXPORT_SYMBOL(blk_max_low_pfn);
+
+unsigned long blk_max_pfn;
+
+/**
+ * blk_queue_prep_rq - set a prepare_request function for queue
+ * @q:		queue
+ * @pfn:	prepare_request function
+ *
+ * It's possible for a queue to register a prepare_request callback which
+ * is invoked before the request is handed to the request_fn. The goal of
+ * the function is to prepare a request for I/O, it can be used to build a
+ * cdb from the request data for instance.
+ *
+ */
+void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn)
+{
+	q->prep_rq_fn = pfn;
+}
+EXPORT_SYMBOL(blk_queue_prep_rq);
+
+/**
+ * blk_queue_set_discard - set a discard_sectors function for queue
+ * @q:		queue
+ * @dfn:	prepare_discard function
+ *
+ * It's possible for a queue to register a discard callback which is used
+ * to transform a discard request into the appropriate type for the
+ * hardware. If none is registered, then discard requests are failed
+ * with %EOPNOTSUPP.
+ *
+ */
+void blk_queue_set_discard(struct request_queue *q, prepare_discard_fn *dfn)
+{
+	q->prepare_discard_fn = dfn;
+}
+EXPORT_SYMBOL(blk_queue_set_discard);
+
+/**
+ * blk_queue_merge_bvec - set a merge_bvec function for queue
+ * @q:		queue
+ * @mbfn:	merge_bvec_fn
+ *
+ * Usually queues have static limitations on the max sectors or segments that
+ * we can put in a request. Stacking drivers may have some settings that
+ * are dynamic, and thus we have to query the queue whether it is ok to
+ * add a new bio_vec to a bio at a given offset or not. If the block device
+ * has such limitations, it needs to register a merge_bvec_fn to control
+ * the size of bio's sent to it. Note that a block device *must* allow a
+ * single page to be added to an empty bio. The block device driver may want
+ * to use the bio_split() function to deal with these bio's. By default
+ * no merge_bvec_fn is defined for a queue, and only the fixed limits are
+ * honored.
+ */
+void blk_queue_merge_bvec(struct request_queue *q, merge_bvec_fn *mbfn)
+{
+	q->merge_bvec_fn = mbfn;
+}
+EXPORT_SYMBOL(blk_queue_merge_bvec);
+
+void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
+{
+	q->softirq_done_fn = fn;
+}
+EXPORT_SYMBOL(blk_queue_softirq_done);
+
+void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout)
+{
+	q->rq_timeout = timeout;
+}
+EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);
+
+void blk_queue_rq_timed_out(struct request_queue *q, rq_timed_out_fn *fn)
+{
+	q->rq_timed_out_fn = fn;
+}
+EXPORT_SYMBOL_GPL(blk_queue_rq_timed_out);
+
+void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn)
+{
+	q->lld_busy_fn = fn;
+}
+EXPORT_SYMBOL_GPL(blk_queue_lld_busy);
+
+/**
+ * blk_queue_make_request - define an alternate make_request function for a device
+ * @q:  the request queue for the device to be affected
+ * @mfn: the alternate make_request function
+ *
+ * Description:
+ *    The normal way for &struct bios to be passed to a device
+ *    driver is for them to be collected into requests on a request
+ *    queue, and then to allow the device driver to select requests
+ *    off that queue when it is ready.  This works well for many block
+ *    devices. However some block devices (typically virtual devices
+ *    such as md or lvm) do not benefit from the processing on the
+ *    request queue, and are served best by having the requests passed
+ *    directly to them.  This can be achieved by providing a function
+ *    to blk_queue_make_request().
+ *
+ * Caveat:
+ *    The driver that does this *must* be able to deal appropriately
+ *    with buffers in "highmemory". This can be accomplished by either calling
+ *    __bio_kmap_atomic() to get a temporary kernel mapping, or by calling
+ *    blk_queue_bounce() to create a buffer in normal memory.
+ **/
+void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
+{
+	/*
+	 * set defaults
+	 */
+	q->nr_requests = BLKDEV_MAX_RQ;
+	blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
+	blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
+	blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
+	blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
+
+	q->make_request_fn = mfn;
+	q->backing_dev_info.ra_pages =
+			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+	q->backing_dev_info.state = 0;
+	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+	blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
+	blk_queue_hardsect_size(q, 512);
+	blk_queue_dma_alignment(q, 511);
+	blk_queue_congestion_threshold(q);
+	q->nr_batching = BLK_BATCH_REQ;
+
+	q->unplug_thresh = 4;		/* hmm */
+	q->unplug_delay = (3 * HZ) / 1000;	/* 3 milliseconds */
+	if (q->unplug_delay == 0)
+		q->unplug_delay = 1;
+
+	q->unplug_timer.function = blk_unplug_timeout;
+	q->unplug_timer.data = (unsigned long)q;
+
+	/*
+	 * by default assume old behaviour and bounce for any highmem page
+	 */
+	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
+}
+EXPORT_SYMBOL(blk_queue_make_request);
+
+/**
+ * blk_queue_bounce_limit - set bounce buffer limit for queue
+ * @q:  the request queue for the device
+ * @dma_addr:   bus address limit
+ *
+ * Description:
+ *    Different hardware can have different requirements as to what pages
+ *    it can do I/O directly to. A low level driver can call
+ *    blk_queue_bounce_limit to have lower memory pages allocated as bounce
+ *    buffers for doing I/O to pages residing above @dma_addr.
+ **/
+void blk_queue_bounce_limit(struct request_queue *q, u64 dma_addr)
+{
+	unsigned long b_pfn = dma_addr >> PAGE_SHIFT;
+	int dma = 0;
+
+	q->bounce_gfp = GFP_NOIO;
+#if BITS_PER_LONG == 64
+	/* Assume anything <= 4GB can be handled by IOMMU.
+	   Actually some IOMMUs can handle everything, but I don't
+	   know of a way to test this here. */
+	if (b_pfn < (min_t(u64, 0x100000000UL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
+		dma = 1;
+	q->bounce_pfn = max_low_pfn;
+#else
+	if (b_pfn < blk_max_low_pfn)
+		dma = 1;
+	q->bounce_pfn = b_pfn;
+#endif
+	if (dma) {
+		init_emergency_isa_pool();
+		q->bounce_gfp = GFP_NOIO | GFP_DMA;
+		q->bounce_pfn = b_pfn;
+	}
+}
+EXPORT_SYMBOL(blk_queue_bounce_limit);
+
+/**
+ * blk_queue_max_sectors - set max sectors for a request for this queue
+ * @q:  the request queue for the device
+ * @max_sectors:  max sectors in the usual 512b unit
+ *
+ * Description:
+ *    Enables a low level driver to set an upper limit on the size of
+ *    received requests.
+ **/
+void blk_queue_max_sectors(struct request_queue *q, unsigned int max_sectors)
+{
+	if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
+		max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
+		printk(KERN_INFO "%s: set to minimum %d\n",
+		       __func__, max_sectors);
+	}
+
+	if (BLK_DEF_MAX_SECTORS > max_sectors)
+		q->max_hw_sectors = q->max_sectors = max_sectors;
+	else {
+		q->max_sectors = BLK_DEF_MAX_SECTORS;
+		q->max_hw_sectors = max_sectors;
+	}
+}
+EXPORT_SYMBOL(blk_queue_max_sectors);
+
+/**
+ * blk_queue_max_phys_segments - set max phys segments for a request for this queue
+ * @q:  the request queue for the device
+ * @max_segments:  max number of segments
+ *
+ * Description:
+ *    Enables a low level driver to set an upper limit on the number of
+ *    physical data segments in a request.  This would be the largest sized
+ *    scatter list the driver could handle.
+ **/
+void blk_queue_max_phys_segments(struct request_queue *q,
+				 unsigned short max_segments)
+{
+	if (!max_segments) {
+		max_segments = 1;
+		printk(KERN_INFO "%s: set to minimum %d\n",
+		       __func__, max_segments);
+	}
+
+	q->max_phys_segments = max_segments;
+}
+EXPORT_SYMBOL(blk_queue_max_phys_segments);
+
+/**
+ * blk_queue_max_hw_segments - set max hw segments for a request for this queue
+ * @q:  the request queue for the device
+ * @max_segments:  max number of segments
+ *
+ * Description:
+ *    Enables a low level driver to set an upper limit on the number of
+ *    hw data segments in a request.  This would be the largest number of
+ *    address/length pairs the host adapter can actually give at once
+ *    to the device.
+ **/
+void blk_queue_max_hw_segments(struct request_queue *q,
+			       unsigned short max_segments)
+{
+	if (!max_segments) {
+		max_segments = 1;
+		printk(KERN_INFO "%s: set to minimum %d\n",
+		       __func__, max_segments);
+	}
+
+	q->max_hw_segments = max_segments;
+}
+EXPORT_SYMBOL(blk_queue_max_hw_segments);
+
+/**
+ * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
+ * @q:  the request queue for the device
+ * @max_size:  max size of segment in bytes
+ *
+ * Description:
+ *    Enables a low level driver to set an upper limit on the size of a
+ *    coalesced segment
+ **/
+void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
+{
+	if (max_size < PAGE_CACHE_SIZE) {
+		max_size = PAGE_CACHE_SIZE;
+		printk(KERN_INFO "%s: set to minimum %d\n",
+		       __func__, max_size);
+	}
+
+	q->max_segment_size = max_size;
+}
+EXPORT_SYMBOL(blk_queue_max_segment_size);
+
+/**
+ * blk_queue_hardsect_size - set hardware sector size for the queue
+ * @q:  the request queue for the device
+ * @size:  the hardware sector size, in bytes
+ *
+ * Description:
+ *   This should typically be set to the lowest possible sector size
+ *   that the hardware can operate on (possible without reverting to
+ *   even internal read-modify-write operations). Usually the default
+ *   of 512 covers most hardware.
+ **/
+void blk_queue_hardsect_size(struct request_queue *q, unsigned short size)
+{
+	q->hardsect_size = size;
+}
+EXPORT_SYMBOL(blk_queue_hardsect_size);
+
+/*
+ * Returns the minimum that is _not_ zero, unless both are zero.
+ */
+#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))
+
+/**
+ * blk_queue_stack_limits - inherit underlying queue limits for stacked drivers
+ * @t:	the stacking driver (top)
+ * @b:  the underlying device (bottom)
+ **/
+void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
+{
+	/* zero is "infinity" */
+	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
+	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
+	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, b->seg_boundary_mask);
+
+	t->max_phys_segments = min_not_zero(t->max_phys_segments, b->max_phys_segments);
+	t->max_hw_segments = min_not_zero(t->max_hw_segments, b->max_hw_segments);
+	t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size);
+	t->hardsect_size = max(t->hardsect_size, b->hardsect_size);
+	if (!t->queue_lock)
+		WARN_ON_ONCE(1);
+	else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
+		unsigned long flags;
+		spin_lock_irqsave(t->queue_lock, flags);
+		queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
+		spin_unlock_irqrestore(t->queue_lock, flags);
+	}
+}
+EXPORT_SYMBOL(blk_queue_stack_limits);
+
+/**
+ * blk_queue_dma_pad - set pad mask
+ * @q:     the request queue for the device
+ * @mask:  pad mask
+ *
+ * Set dma pad mask.
+ *
+ * Appending pad buffer to a request modifies the last entry of a
+ * scatter list such that it includes the pad buffer.
+ **/
+void blk_queue_dma_pad(struct request_queue *q, unsigned int mask)
+{
+	q->dma_pad_mask = mask;
+}
+EXPORT_SYMBOL(blk_queue_dma_pad);
+
+/**
+ * blk_queue_update_dma_pad - update pad mask
+ * @q:     the request queue for the device
+ * @mask:  pad mask
+ *
+ * Update dma pad mask.
+ *
+ * Appending pad buffer to a request modifies the last entry of a
+ * scatter list such that it includes the pad buffer.
+ **/
+void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask)
+{
+	if (mask > q->dma_pad_mask)
+		q->dma_pad_mask = mask;
+}
+EXPORT_SYMBOL(blk_queue_update_dma_pad);
+
+/**
+ * blk_queue_dma_drain - Set up a drain buffer for excess dma.
+ * @q:  the request queue for the device
+ * @dma_drain_needed: fn which returns non-zero if drain is necessary
+ * @buf:	physically contiguous buffer
+ * @size:	size of the buffer in bytes
+ *
+ * Some devices have excess DMA problems and can't simply discard (or
+ * zero fill) the unwanted piece of the transfer.  They have to have a
+ * real area of memory to transfer it into.  The use case for this is
+ * ATAPI devices in DMA mode.  If the packet command causes a transfer
+ * bigger than the transfer size some HBAs will lock up if there
+ * aren't DMA elements to contain the excess transfer.  What this API
+ * does is adjust the queue so that the buf is always appended
+ * silently to the scatterlist.
+ *
+ * Note: This routine adjusts max_hw_segments to make room for
+ * appending the drain buffer.  If you call
+ * blk_queue_max_hw_segments() or blk_queue_max_phys_segments() after
+ * calling this routine, you must set the limit to one fewer than your
+ * device can support otherwise there won't be room for the drain
+ * buffer.
+ */
+int blk_queue_dma_drain(struct request_queue *q,
+			       dma_drain_needed_fn *dma_drain_needed,
+			       void *buf, unsigned int size)
+{
+	if (q->max_hw_segments < 2 || q->max_phys_segments < 2)
+		return -EINVAL;
+	/* make room for appending the drain */
+	--q->max_hw_segments;
+	--q->max_phys_segments;
+	q->dma_drain_needed = dma_drain_needed;
+	q->dma_drain_buffer = buf;
+	q->dma_drain_size = size;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blk_queue_dma_drain);
+
+/**
+ * blk_queue_segment_boundary - set boundary rules for segment merging
+ * @q:  the request queue for the device
+ * @mask:  the memory boundary mask
+ **/
+void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
+{
+	if (mask < PAGE_CACHE_SIZE - 1) {
+		mask = PAGE_CACHE_SIZE - 1;
+		printk(KERN_INFO "%s: set to minimum %lx\n",
+		       __func__, mask);
+	}
+
+	q->seg_boundary_mask = mask;
+}
+EXPORT_SYMBOL(blk_queue_segment_boundary);
+
+/**
+ * blk_queue_dma_alignment - set dma length and memory alignment
+ * @q:     the request queue for the device
+ * @mask:  alignment mask
+ *
+ * description:
+ *    set required memory and length alignment for direct dma transactions.
+ *    this is used when buiding direct io requests for the queue.
+ *
+ **/
+void blk_queue_dma_alignment(struct request_queue *q, int mask)
+{
+	q->dma_alignment = mask;
+}
+EXPORT_SYMBOL(blk_queue_dma_alignment);
+
+/**
+ * blk_queue_update_dma_alignment - update dma length and memory alignment
+ * @q:     the request queue for the device
+ * @mask:  alignment mask
+ *
+ * description:
+ *    update required memory and length alignment for direct dma transactions.
+ *    If the requested alignment is larger than the current alignment, then
+ *    the current queue alignment is updated to the new value, otherwise it
+ *    is left alone.  The design of this is to allow multiple objects
+ *    (driver, device, transport etc) to set their respective
+ *    alignments without having them interfere.
+ *
+ **/
+void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
+{
+	BUG_ON(mask > PAGE_SIZE);
+
+	if (mask > q->dma_alignment)
+		q->dma_alignment = mask;
+}
+EXPORT_SYMBOL(blk_queue_update_dma_alignment);
+
+static int __init blk_settings_init(void)
+{
+	blk_max_low_pfn = max_low_pfn - 1;
+	blk_max_pfn = max_pfn - 1;
+	return 0;
+}
+subsys_initcall(blk_settings_init);
diff --git a/libdde-linux26/contrib/block/blk-softirq.c b/libdde-linux26/contrib/block/blk-softirq.c
new file mode 100644
index 00000000..ce0efc6b
--- /dev/null
+++ b/libdde-linux26/contrib/block/blk-softirq.c
@@ -0,0 +1,175 @@
+/*
+ * Functions related to softirq rq completions
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+
+#include "blk.h"
+
+static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
+
+/*
+ * Softirq action handler - move entries to local list and loop over them
+ * while passing them to the queue registered handler.
+ */
+static void blk_done_softirq(struct softirq_action *h)
+{
+	struct list_head *cpu_list, local_list;
+
+	local_irq_disable();
+	cpu_list = &__get_cpu_var(blk_cpu_done);
+	list_replace_init(cpu_list, &local_list);
+	local_irq_enable();
+
+	while (!list_empty(&local_list)) {
+		struct request *rq;
+
+		rq = list_entry(local_list.next, struct request, csd.list);
+		list_del_init(&rq->csd.list);
+		rq->q->softirq_done_fn(rq);
+	}
+}
+
+#if defined(CONFIG_SMP) && defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+static void trigger_softirq(void *data)
+{
+	struct request *rq = data;
+	unsigned long flags;
+	struct list_head *list;
+
+	local_irq_save(flags);
+	list = &__get_cpu_var(blk_cpu_done);
+	list_add_tail(&rq->csd.list, list);
+
+	if (list->next == &rq->csd.list)
+		raise_softirq_irqoff(BLOCK_SOFTIRQ);
+
+	local_irq_restore(flags);
+}
+
+/*
+ * Setup and invoke a run of 'trigger_softirq' on the given cpu.
+ */
+static int raise_blk_irq(int cpu, struct request *rq)
+{
+	if (cpu_online(cpu)) {
+		struct call_single_data *data = &rq->csd;
+
+		data->func = trigger_softirq;
+		data->info = rq;
+		data->flags = 0;
+
+		__smp_call_function_single(cpu, data);
+		return 0;
+	}
+
+	return 1;
+}
+#else /* CONFIG_SMP && CONFIG_USE_GENERIC_SMP_HELPERS */
+static int raise_blk_irq(int cpu, struct request *rq)
+{
+	return 1;
+}
+#endif
+
+static int __cpuinit blk_cpu_notify(struct notifier_block *self,
+				    unsigned long action, void *hcpu)
+{
+	/*
+	 * If a CPU goes away, splice its entries to the current CPU
+	 * and trigger a run of the softirq
+	 */
+	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+		int cpu = (unsigned long) hcpu;
+
+		local_irq_disable();
+		list_splice_init(&per_cpu(blk_cpu_done, cpu),
+				 &__get_cpu_var(blk_cpu_done));
+		raise_softirq_irqoff(BLOCK_SOFTIRQ);
+		local_irq_enable();
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata blk_cpu_notifier = {
+	.notifier_call	= blk_cpu_notify,
+};
+
+void __blk_complete_request(struct request *req)
+{
+	struct request_queue *q = req->q;
+	unsigned long flags;
+	int ccpu, cpu, group_cpu;
+
+	BUG_ON(!q->softirq_done_fn);
+
+	local_irq_save(flags);
+	cpu = smp_processor_id();
+	group_cpu = blk_cpu_to_group(cpu);
+
+	/*
+	 * Select completion CPU
+	 */
+	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && req->cpu != -1)
+		ccpu = req->cpu;
+	else
+		ccpu = cpu;
+
+	if (ccpu == cpu || ccpu == group_cpu) {
+		struct list_head *list;
+do_local:
+		list = &__get_cpu_var(blk_cpu_done);
+		list_add_tail(&req->csd.list, list);
+
+		/*
+		 * if the list only contains our just added request,
+		 * signal a raise of the softirq. If there are already
+		 * entries there, someone already raised the irq but it
+		 * hasn't run yet.
+		 */
+		if (list->next == &req->csd.list)
+			raise_softirq_irqoff(BLOCK_SOFTIRQ);
+	} else if (raise_blk_irq(ccpu, req))
+		goto do_local;
+
+	local_irq_restore(flags);
+}
+
+/**
+ * blk_complete_request - end I/O on a request
+ * @req:      the request being processed
+ *
+ * Description:
+ *     Ends all I/O on a request. It does not handle partial completions,
+ *     unless the driver actually implements this in its completion callback
+ *     through requeueing. The actual completion happens out-of-order,
+ *     through a softirq handler. The user must have registered a completion
+ *     callback through blk_queue_softirq_done().
+ **/
+void blk_complete_request(struct request *req)
+{
+	if (unlikely(blk_should_fake_timeout(req->q)))
+		return;
+	if (!blk_mark_rq_complete(req))
+		__blk_complete_request(req);
+}
+EXPORT_SYMBOL(blk_complete_request);
+
+static __init int blk_softirq_init(void)
+{
+	int i;
+
+	for_each_possible_cpu(i)
+		INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
+
+	open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
+	register_hotcpu_notifier(&blk_cpu_notifier);
+	return 0;
+}
+subsys_initcall(blk_softirq_init);
diff --git a/libdde-linux26/contrib/block/blk-sysfs.c b/libdde-linux26/contrib/block/blk-sysfs.c
new file mode 100644
index 00000000..e29ddfc7
--- /dev/null
+++ b/libdde-linux26/contrib/block/blk-sysfs.c
@@ -0,0 +1,426 @@
+/*
+ * Functions related to sysfs handling
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/blktrace_api.h>
+
+#include "blk.h"
+
+struct queue_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(struct request_queue *, char *);
+	ssize_t (*store)(struct request_queue *, const char *, size_t);
+};
+
+static ssize_t
+queue_var_show(unsigned int var, char *page)
+{
+	return sprintf(page, "%d\n", var);
+}
+
+static ssize_t
+queue_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 queue_requests_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(q->nr_requests, (page));
+}
+
+static ssize_t
+queue_requests_store(struct request_queue *q, const char *page, size_t count)
+{
+	struct request_list *rl = &q->rq;
+	unsigned long nr;
+	int ret = queue_var_store(&nr, page, count);
+	if (nr < BLKDEV_MIN_RQ)
+		nr = BLKDEV_MIN_RQ;
+
+	spin_lock_irq(q->queue_lock);
+	q->nr_requests = nr;
+	blk_queue_congestion_threshold(q);
+
+	if (rl->count[READ] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, READ);
+	else if (rl->count[READ] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, READ);
+
+	if (rl->count[WRITE] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, WRITE);
+	else if (rl->count[WRITE] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, WRITE);
+
+	if (rl->count[READ] >= q->nr_requests) {
+		blk_set_queue_full(q, READ);
+	} else if (rl->count[READ]+1 <= q->nr_requests) {
+		blk_clear_queue_full(q, READ);
+		wake_up(&rl->wait[READ]);
+	}
+
+	if (rl->count[WRITE] >= q->nr_requests) {
+		blk_set_queue_full(q, WRITE);
+	} else if (rl->count[WRITE]+1 <= q->nr_requests) {
+		blk_clear_queue_full(q, WRITE);
+		wake_up(&rl->wait[WRITE]);
+	}
+	spin_unlock_irq(q->queue_lock);
+	return ret;
+}
+
+static ssize_t queue_ra_show(struct request_queue *q, char *page)
+{
+	int ra_kb = q->backing_dev_info.ra_pages << (PAGE_CACHE_SHIFT - 10);
+
+	return queue_var_show(ra_kb, (page));
+}
+
+static ssize_t
+queue_ra_store(struct request_queue *q, const char *page, size_t count)
+{
+	unsigned long ra_kb;
+	ssize_t ret = queue_var_store(&ra_kb, page, count);
+
+	q->backing_dev_info.ra_pages = ra_kb >> (PAGE_CACHE_SHIFT - 10);
+
+	return ret;
+}
+
+static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
+{
+	int max_sectors_kb = q->max_sectors >> 1;
+
+	return queue_var_show(max_sectors_kb, (page));
+}
+
+static ssize_t queue_hw_sector_size_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(q->hardsect_size, page);
+}
+
+static ssize_t
+queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
+{
+	unsigned long max_sectors_kb,
+			max_hw_sectors_kb = q->max_hw_sectors >> 1,
+			page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
+	ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
+
+	if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
+		return -EINVAL;
+
+	spin_lock_irq(q->queue_lock);
+	q->max_sectors = max_sectors_kb << 1;
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
+static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
+{
+	int max_hw_sectors_kb = q->max_hw_sectors >> 1;
+
+	return queue_var_show(max_hw_sectors_kb, (page));
+}
+
+static ssize_t queue_nonrot_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(!blk_queue_nonrot(q), page);
+}
+
+static ssize_t queue_nonrot_store(struct request_queue *q, const char *page,
+				  size_t count)
+{
+	unsigned long nm;
+	ssize_t ret = queue_var_store(&nm, page, count);
+
+	spin_lock_irq(q->queue_lock);
+	if (nm)
+		queue_flag_clear(QUEUE_FLAG_NONROT, q);
+	else
+		queue_flag_set(QUEUE_FLAG_NONROT, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
+static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_nomerges(q), page);
+}
+
+static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
+				    size_t count)
+{
+	unsigned long nm;
+	ssize_t ret = queue_var_store(&nm, page, count);
+
+	spin_lock_irq(q->queue_lock);
+	if (nm)
+		queue_flag_set(QUEUE_FLAG_NOMERGES, q);
+	else
+		queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
+static ssize_t queue_rq_affinity_show(struct request_queue *q, char *page)
+{
+	unsigned int set = test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags);
+
+	return queue_var_show(set != 0, page);
+}
+
+static ssize_t
+queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
+{
+	ssize_t ret = -EINVAL;
+#if defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+	unsigned long val;
+
+	ret = queue_var_store(&val, page, count);
+	spin_lock_irq(q->queue_lock);
+	if (val)
+		queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
+	else
+		queue_flag_clear(QUEUE_FLAG_SAME_COMP,  q);
+	spin_unlock_irq(q->queue_lock);
+#endif
+	return ret;
+}
+
+static ssize_t queue_iostats_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_io_stat(q), page);
+}
+
+static ssize_t queue_iostats_store(struct request_queue *q, const char *page,
+				   size_t count)
+{
+	unsigned long stats;
+	ssize_t ret = queue_var_store(&stats, page, count);
+
+	spin_lock_irq(q->queue_lock);
+	if (stats)
+		queue_flag_set(QUEUE_FLAG_IO_STAT, q);
+	else
+		queue_flag_clear(QUEUE_FLAG_IO_STAT, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
+static struct queue_sysfs_entry queue_requests_entry = {
+	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_requests_show,
+	.store = queue_requests_store,
+};
+
+static struct queue_sysfs_entry queue_ra_entry = {
+	.attr = {.name = "read_ahead_kb", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_ra_show,
+	.store = queue_ra_store,
+};
+
+static struct queue_sysfs_entry queue_max_sectors_entry = {
+	.attr = {.name = "max_sectors_kb", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_max_sectors_show,
+	.store = queue_max_sectors_store,
+};
+
+static struct queue_sysfs_entry queue_max_hw_sectors_entry = {
+	.attr = {.name = "max_hw_sectors_kb", .mode = S_IRUGO },
+	.show = queue_max_hw_sectors_show,
+};
+
+static struct queue_sysfs_entry queue_iosched_entry = {
+	.attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
+	.show = elv_iosched_show,
+	.store = elv_iosched_store,
+};
+
+static struct queue_sysfs_entry queue_hw_sector_size_entry = {
+	.attr = {.name = "hw_sector_size", .mode = S_IRUGO },
+	.show = queue_hw_sector_size_show,
+};
+
+static struct queue_sysfs_entry queue_nonrot_entry = {
+	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_nonrot_show,
+	.store = queue_nonrot_store,
+};
+
+static struct queue_sysfs_entry queue_nomerges_entry = {
+	.attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_nomerges_show,
+	.store = queue_nomerges_store,
+};
+
+static struct queue_sysfs_entry queue_rq_affinity_entry = {
+	.attr = {.name = "rq_affinity", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_rq_affinity_show,
+	.store = queue_rq_affinity_store,
+};
+
+static struct queue_sysfs_entry queue_iostats_entry = {
+	.attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_iostats_show,
+	.store = queue_iostats_store,
+};
+
+static struct attribute *default_attrs[] = {
+	&queue_requests_entry.attr,
+	&queue_ra_entry.attr,
+	&queue_max_hw_sectors_entry.attr,
+	&queue_max_sectors_entry.attr,
+	&queue_iosched_entry.attr,
+	&queue_hw_sector_size_entry.attr,
+	&queue_nonrot_entry.attr,
+	&queue_nomerges_entry.attr,
+	&queue_rq_affinity_entry.attr,
+	&queue_iostats_entry.attr,
+	NULL,
+};
+
+#define to_queue(atr) container_of((atr), struct queue_sysfs_entry, attr)
+
+static ssize_t
+queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+{
+	struct queue_sysfs_entry *entry = to_queue(attr);
+	struct request_queue *q =
+		container_of(kobj, struct request_queue, kobj);
+	ssize_t res;
+
+	if (!entry->show)
+		return -EIO;
+	mutex_lock(&q->sysfs_lock);
+	if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)) {
+		mutex_unlock(&q->sysfs_lock);
+		return -ENOENT;
+	}
+	res = entry->show(q, page);
+	mutex_unlock(&q->sysfs_lock);
+	return res;
+}
+
+static ssize_t
+queue_attr_store(struct kobject *kobj, struct attribute *attr,
+		    const char *page, size_t length)
+{
+	struct queue_sysfs_entry *entry = to_queue(attr);
+	struct request_queue *q;
+	ssize_t res;
+
+	if (!entry->store)
+		return -EIO;
+
+	q = container_of(kobj, struct request_queue, kobj);
+	mutex_lock(&q->sysfs_lock);
+	if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)) {
+		mutex_unlock(&q->sysfs_lock);
+		return -ENOENT;
+	}
+	res = entry->store(q, page, length);
+	mutex_unlock(&q->sysfs_lock);
+	return res;
+}
+
+/**
+ * blk_cleanup_queue: - release a &struct request_queue when it is no longer needed
+ * @kobj:    the kobj belonging of the request queue to be released
+ *
+ * Description:
+ *     blk_cleanup_queue is the pair to blk_init_queue() or
+ *     blk_queue_make_request().  It should be called when a request queue is
+ *     being released; typically when a block device is being de-registered.
+ *     Currently, its primary task it to free all the &struct request
+ *     structures that were allocated to the queue and the queue itself.
+ *
+ * Caveat:
+ *     Hopefully the low level driver will have finished any
+ *     outstanding requests first...
+ **/
+static void blk_release_queue(struct kobject *kobj)
+{
+	struct request_queue *q =
+		container_of(kobj, struct request_queue, kobj);
+	struct request_list *rl = &q->rq;
+
+	blk_sync_queue(q);
+
+	if (rl->rq_pool)
+		mempool_destroy(rl->rq_pool);
+
+	if (q->queue_tags)
+		__blk_queue_free_tags(q);
+
+	blk_trace_shutdown(q);
+
+	bdi_destroy(&q->backing_dev_info);
+	kmem_cache_free(blk_requestq_cachep, q);
+}
+
+static struct sysfs_ops queue_sysfs_ops = {
+	.show	= queue_attr_show,
+	.store	= queue_attr_store,
+};
+
+struct kobj_type blk_queue_ktype = {
+	.sysfs_ops	= &queue_sysfs_ops,
+	.default_attrs	= default_attrs,
+	.release	= blk_release_queue,
+};
+
+int blk_register_queue(struct gendisk *disk)
+{
+	int ret;
+
+	struct request_queue *q = disk->queue;
+
+	if (WARN_ON(!q))
+		return -ENXIO;
+
+	if (!q->request_fn)
+		return 0;
+
+	ret = kobject_add(&q->kobj, kobject_get(&disk_to_dev(disk)->kobj),
+			  "%s", "queue");
+	if (ret < 0)
+		return ret;
+
+	kobject_uevent(&q->kobj, KOBJ_ADD);
+
+	ret = elv_register_queue(q);
+	if (ret) {
+		kobject_uevent(&q->kobj, KOBJ_REMOVE);
+		kobject_del(&q->kobj);
+		return ret;
+	}
+
+	return 0;
+}
+
+void blk_unregister_queue(struct gendisk *disk)
+{
+	struct request_queue *q = disk->queue;
+
+	if (WARN_ON(!q))
+		return;
+
+	if (q->request_fn) {
+		elv_unregister_queue(q);
+
+		kobject_uevent(&q->kobj, KOBJ_REMOVE);
+		kobject_del(&q->kobj);
+		kobject_put(&disk_to_dev(disk)->kobj);
+	}
+}
diff --git a/libdde-linux26/contrib/block/blk-tag.c b/libdde-linux26/contrib/block/blk-tag.c
new file mode 100644
index 00000000..3c518e33
--- /dev/null
+++ b/libdde-linux26/contrib/block/blk-tag.c
@@ -0,0 +1,402 @@
+/*
+ * Functions related to tagged command queuing
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+
+#include "blk.h"
+
+/**
+ * blk_queue_find_tag - find a request by its tag and queue
+ * @q:	 The request queue for the device
+ * @tag: The tag of the request
+ *
+ * Notes:
+ *    Should be used when a device returns a tag and you want to match
+ *    it with a request.
+ *
+ *    no locks need be held.
+ **/
+struct request *blk_queue_find_tag(struct request_queue *q, int tag)
+{
+	return blk_map_queue_find_tag(q->queue_tags, tag);
+}
+EXPORT_SYMBOL(blk_queue_find_tag);
+
+/**
+ * __blk_free_tags - release a given set of tag maintenance info
+ * @bqt:	the tag map to free
+ *
+ * Tries to free the specified @bqt.  Returns true if it was
+ * actually freed and false if there are still references using it
+ */
+static int __blk_free_tags(struct blk_queue_tag *bqt)
+{
+	int retval;
+
+	retval = atomic_dec_and_test(&bqt->refcnt);
+	if (retval) {
+		BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) <
+							bqt->max_depth);
+
+		kfree(bqt->tag_index);
+		bqt->tag_index = NULL;
+
+		kfree(bqt->tag_map);
+		bqt->tag_map = NULL;
+
+		kfree(bqt);
+	}
+
+	return retval;
+}
+
+/**
+ * __blk_queue_free_tags - release tag maintenance info
+ * @q:  the request queue for the device
+ *
+ *  Notes:
+ *    blk_cleanup_queue() will take care of calling this function, if tagging
+ *    has been used. So there's no need to call this directly.
+ **/
+void __blk_queue_free_tags(struct request_queue *q)
+{
+	struct blk_queue_tag *bqt = q->queue_tags;
+
+	if (!bqt)
+		return;
+
+	__blk_free_tags(bqt);
+
+	q->queue_tags = NULL;
+	queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
+}
+
+/**
+ * blk_free_tags - release a given set of tag maintenance info
+ * @bqt:	the tag map to free
+ *
+ * For externally managed @bqt frees the map.  Callers of this
+ * function must guarantee to have released all the queues that
+ * might have been using this tag map.
+ */
+void blk_free_tags(struct blk_queue_tag *bqt)
+{
+	if (unlikely(!__blk_free_tags(bqt)))
+		BUG();
+}
+EXPORT_SYMBOL(blk_free_tags);
+
+/**
+ * blk_queue_free_tags - release tag maintenance info
+ * @q:  the request queue for the device
+ *
+ *  Notes:
+ *	This is used to disable tagged queuing to a device, yet leave
+ *	queue in function.
+ **/
+void blk_queue_free_tags(struct request_queue *q)
+{
+	queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
+}
+EXPORT_SYMBOL(blk_queue_free_tags);
+
+static int
+init_tag_map(struct request_queue *q, struct blk_queue_tag *tags, int depth)
+{
+	struct request **tag_index;
+	unsigned long *tag_map;
+	int nr_ulongs;
+
+	if (q && depth > q->nr_requests * 2) {
+		depth = q->nr_requests * 2;
+		printk(KERN_ERR "%s: adjusted depth to %d\n",
+		       __func__, depth);
+	}
+
+	tag_index = kzalloc(depth * sizeof(struct request *), GFP_ATOMIC);
+	if (!tag_index)
+		goto fail;
+
+	nr_ulongs = ALIGN(depth, BITS_PER_LONG) / BITS_PER_LONG;
+	tag_map = kzalloc(nr_ulongs * sizeof(unsigned long), GFP_ATOMIC);
+	if (!tag_map)
+		goto fail;
+
+	tags->real_max_depth = depth;
+	tags->max_depth = depth;
+	tags->tag_index = tag_index;
+	tags->tag_map = tag_map;
+
+	return 0;
+fail:
+	kfree(tag_index);
+	return -ENOMEM;
+}
+
+static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
+						   int depth)
+{
+	struct blk_queue_tag *tags;
+
+	tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC);
+	if (!tags)
+		goto fail;
+
+	if (init_tag_map(q, tags, depth))
+		goto fail;
+
+	atomic_set(&tags->refcnt, 1);
+	return tags;
+fail:
+	kfree(tags);
+	return NULL;
+}
+
+/**
+ * blk_init_tags - initialize the tag info for an external tag map
+ * @depth:	the maximum queue depth supported
+ **/
+struct blk_queue_tag *blk_init_tags(int depth)
+{
+	return __blk_queue_init_tags(NULL, depth);
+}
+EXPORT_SYMBOL(blk_init_tags);
+
+/**
+ * blk_queue_init_tags - initialize the queue tag info
+ * @q:  the request queue for the device
+ * @depth:  the maximum queue depth supported
+ * @tags: the tag to use
+ *
+ * Queue lock must be held here if the function is called to resize an
+ * existing map.
+ **/
+int blk_queue_init_tags(struct request_queue *q, int depth,
+			struct blk_queue_tag *tags)
+{
+	int rc;
+
+	BUG_ON(tags && q->queue_tags && tags != q->queue_tags);
+
+	if (!tags && !q->queue_tags) {
+		tags = __blk_queue_init_tags(q, depth);
+
+		if (!tags)
+			goto fail;
+	} else if (q->queue_tags) {
+		rc = blk_queue_resize_tags(q, depth);
+		if (rc)
+			return rc;
+		queue_flag_set(QUEUE_FLAG_QUEUED, q);
+		return 0;
+	} else
+		atomic_inc(&tags->refcnt);
+
+	/*
+	 * assign it, all done
+	 */
+	q->queue_tags = tags;
+	queue_flag_set_unlocked(QUEUE_FLAG_QUEUED, q);
+	INIT_LIST_HEAD(&q->tag_busy_list);
+	return 0;
+fail:
+	kfree(tags);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(blk_queue_init_tags);
+
+/**
+ * blk_queue_resize_tags - change the queueing depth
+ * @q:  the request queue for the device
+ * @new_depth: the new max command queueing depth
+ *
+ *  Notes:
+ *    Must be called with the queue lock held.
+ **/
+int blk_queue_resize_tags(struct request_queue *q, int new_depth)
+{
+	struct blk_queue_tag *bqt = q->queue_tags;
+	struct request **tag_index;
+	unsigned long *tag_map;
+	int max_depth, nr_ulongs;
+
+	if (!bqt)
+		return -ENXIO;
+
+	/*
+	 * if we already have large enough real_max_depth.  just
+	 * adjust max_depth.  *NOTE* as requests with tag value
+	 * between new_depth and real_max_depth can be in-flight, tag
+	 * map can not be shrunk blindly here.
+	 */
+	if (new_depth <= bqt->real_max_depth) {
+		bqt->max_depth = new_depth;
+		return 0;
+	}
+
+	/*
+	 * Currently cannot replace a shared tag map with a new
+	 * one, so error out if this is the case
+	 */
+	if (atomic_read(&bqt->refcnt) != 1)
+		return -EBUSY;
+
+	/*
+	 * save the old state info, so we can copy it back
+	 */
+	tag_index = bqt->tag_index;
+	tag_map = bqt->tag_map;
+	max_depth = bqt->real_max_depth;
+
+	if (init_tag_map(q, bqt, new_depth))
+		return -ENOMEM;
+
+	memcpy(bqt->tag_index, tag_index, max_depth * sizeof(struct request *));
+	nr_ulongs = ALIGN(max_depth, BITS_PER_LONG) / BITS_PER_LONG;
+	memcpy(bqt->tag_map, tag_map, nr_ulongs * sizeof(unsigned long));
+
+	kfree(tag_index);
+	kfree(tag_map);
+	return 0;
+}
+EXPORT_SYMBOL(blk_queue_resize_tags);
+
+/**
+ * blk_queue_end_tag - end tag operations for a request
+ * @q:  the request queue for the device
+ * @rq: the request that has completed
+ *
+ *  Description:
+ *    Typically called when end_that_request_first() returns %0, meaning
+ *    all transfers have been done for a request. It's important to call
+ *    this function before end_that_request_last(), as that will put the
+ *    request back on the free list thus corrupting the internal tag list.
+ *
+ *  Notes:
+ *   queue lock must be held.
+ **/
+void blk_queue_end_tag(struct request_queue *q, struct request *rq)
+{
+	struct blk_queue_tag *bqt = q->queue_tags;
+	int tag = rq->tag;
+
+	BUG_ON(tag == -1);
+
+	if (unlikely(tag >= bqt->real_max_depth))
+		/*
+		 * This can happen after tag depth has been reduced.
+		 * FIXME: how about a warning or info message here?
+		 */
+		return;
+
+	list_del_init(&rq->queuelist);
+	rq->cmd_flags &= ~REQ_QUEUED;
+	rq->tag = -1;
+
+	if (unlikely(bqt->tag_index[tag] == NULL))
+		printk(KERN_ERR "%s: tag %d is missing\n",
+		       __func__, tag);
+
+	bqt->tag_index[tag] = NULL;
+
+	if (unlikely(!test_bit(tag, bqt->tag_map))) {
+		printk(KERN_ERR "%s: attempt to clear non-busy tag (%d)\n",
+		       __func__, tag);
+		return;
+	}
+	/*
+	 * The tag_map bit acts as a lock for tag_index[bit], so we need
+	 * unlock memory barrier semantics.
+	 */
+	clear_bit_unlock(tag, bqt->tag_map);
+}
+EXPORT_SYMBOL(blk_queue_end_tag);
+
+/**
+ * blk_queue_start_tag - find a free tag and assign it
+ * @q:  the request queue for the device
+ * @rq:  the block request that needs tagging
+ *
+ *  Description:
+ *    This can either be used as a stand-alone helper, or possibly be
+ *    assigned as the queue &prep_rq_fn (in which case &struct request
+ *    automagically gets a tag assigned). Note that this function
+ *    assumes that any type of request can be queued! if this is not
+ *    true for your device, you must check the request type before
+ *    calling this function.  The request will also be removed from
+ *    the request queue, so it's the drivers responsibility to readd
+ *    it if it should need to be restarted for some reason.
+ *
+ *  Notes:
+ *   queue lock must be held.
+ **/
+int blk_queue_start_tag(struct request_queue *q, struct request *rq)
+{
+	struct blk_queue_tag *bqt = q->queue_tags;
+	unsigned max_depth, offset;
+	int tag;
+
+	if (unlikely((rq->cmd_flags & REQ_QUEUED))) {
+		printk(KERN_ERR
+		       "%s: request %p for device [%s] already tagged %d",
+		       __func__, rq,
+		       rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->tag);
+		BUG();
+	}
+
+	/*
+	 * Protect against shared tag maps, as we may not have exclusive
+	 * access to the tag map.
+	 *
+	 * We reserve a few tags just for sync IO, since we don't want
+	 * to starve sync IO on behalf of flooding async IO.
+	 */
+	max_depth = bqt->max_depth;
+	if (rq_is_sync(rq))
+		offset = 0;
+	else
+		offset = max_depth >> 2;
+
+	do {
+		tag = find_next_zero_bit(bqt->tag_map, max_depth, offset);
+		if (tag >= max_depth)
+			return 1;
+
+	} while (test_and_set_bit_lock(tag, bqt->tag_map));
+	/*
+	 * We need lock ordering semantics given by test_and_set_bit_lock.
+	 * See blk_queue_end_tag for details.
+	 */
+
+	rq->cmd_flags |= REQ_QUEUED;
+	rq->tag = tag;
+	bqt->tag_index[tag] = rq;
+	blkdev_dequeue_request(rq);
+	list_add(&rq->queuelist, &q->tag_busy_list);
+	return 0;
+}
+EXPORT_SYMBOL(blk_queue_start_tag);
+
+/**
+ * blk_queue_invalidate_tags - invalidate all pending tags
+ * @q:  the request queue for the device
+ *
+ *  Description:
+ *   Hardware conditions may dictate a need to stop all pending requests.
+ *   In this case, we will safely clear the block side of the tag queue and
+ *   readd all requests to the request queue in the right order.
+ *
+ *  Notes:
+ *   queue lock must be held.
+ **/
+void blk_queue_invalidate_tags(struct request_queue *q)
+{
+	struct list_head *tmp, *n;
+
+	list_for_each_safe(tmp, n, &q->tag_busy_list)
+		blk_requeue_request(q, list_entry_rq(tmp));
+}
+EXPORT_SYMBOL(blk_queue_invalidate_tags);
diff --git a/libdde-linux26/contrib/block/blk-timeout.c b/libdde-linux26/contrib/block/blk-timeout.c
new file mode 100644
index 00000000..19da232b
--- /dev/null
+++ b/libdde-linux26/contrib/block/blk-timeout.c
@@ -0,0 +1,232 @@
+/*
+ * Functions related to generic timeout handling of requests.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/fault-inject.h>
+
+#include "blk.h"
+
+#include <ddekit/timer.h>
+
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+
+static DECLARE_FAULT_ATTR(fail_io_timeout);
+
+static int __init setup_fail_io_timeout(char *str)
+{
+	return setup_fault_attr(&fail_io_timeout, str);
+}
+__setup("fail_io_timeout=", setup_fail_io_timeout);
+
+int blk_should_fake_timeout(struct request_queue *q)
+{
+	if (!test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
+		return 0;
+
+	return should_fail(&fail_io_timeout, 1);
+}
+
+static int __init fail_io_timeout_debugfs(void)
+{
+	return init_fault_attr_dentries(&fail_io_timeout, "fail_io_timeout");
+}
+
+late_initcall(fail_io_timeout_debugfs);
+
+ssize_t part_timeout_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	int set = test_bit(QUEUE_FLAG_FAIL_IO, &disk->queue->queue_flags);
+
+	return sprintf(buf, "%d\n", set != 0);
+}
+
+ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t count)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	int val;
+
+	if (count) {
+		struct request_queue *q = disk->queue;
+		char *p = (char *) buf;
+
+		val = simple_strtoul(p, &p, 10);
+		spin_lock_irq(q->queue_lock);
+		if (val)
+			queue_flag_set(QUEUE_FLAG_FAIL_IO, q);
+		else
+			queue_flag_clear(QUEUE_FLAG_FAIL_IO, q);
+		spin_unlock_irq(q->queue_lock);
+	}
+
+	return count;
+}
+
+#endif /* CONFIG_FAIL_IO_TIMEOUT */
+
+/*
+ * blk_delete_timer - Delete/cancel timer for a given function.
+ * @req:	request that we are canceling timer for
+ *
+ */
+void blk_delete_timer(struct request *req)
+{
+	list_del_init(&req->timeout_list);
+}
+
+static void blk_rq_timed_out(struct request *req)
+{
+	struct request_queue *q = req->q;
+	enum blk_eh_timer_return ret;
+
+	ret = q->rq_timed_out_fn(req);
+	switch (ret) {
+	case BLK_EH_HANDLED:
+		__blk_complete_request(req);
+		break;
+	case BLK_EH_RESET_TIMER:
+		blk_clear_rq_complete(req);
+		blk_add_timer(req);
+		break;
+	case BLK_EH_NOT_HANDLED:
+		/*
+		 * LLD handles this for now but in the future
+		 * we can send a request msg to abort the command
+		 * and we can move more of the generic scsi eh code to
+		 * the blk layer.
+		 */
+		break;
+	default:
+		printk(KERN_ERR "block: bad eh return: %d\n", ret);
+		break;
+	}
+}
+
+void blk_rq_timed_out_timer(unsigned long data)
+{
+	struct request_queue *q = (struct request_queue *) data;
+	unsigned long flags, next = 0;
+	struct request *rq, *tmp;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list) {
+		if (time_after_eq(jiffies, rq->deadline)) {
+			list_del_init(&rq->timeout_list);
+
+			/*
+			 * Check if we raced with end io completion
+			 */
+			if (blk_mark_rq_complete(rq))
+				continue;
+			blk_rq_timed_out(rq);
+		} else {
+			if (!next || time_after(next, rq->deadline))
+				next = rq->deadline;
+		}
+	}
+
+	/*
+	 * next can never be 0 here with the list non-empty, since we always
+	 * bump ->deadline to 1 so we can detect if the timer was ever added
+	 * or not. See comment in blk_add_timer()
+	 */
+	if (next)
+		mod_timer(&q->timeout, round_jiffies_up(next));
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+/**
+ * blk_abort_request -- Request request recovery for the specified command
+ * @req:	pointer to the request of interest
+ *
+ * This function requests that the block layer start recovery for the
+ * request by deleting the timer and calling the q's timeout function.
+ * LLDDs who implement their own error recovery MAY ignore the timeout
+ * event if they generated blk_abort_req. Must hold queue lock.
+ */
+void blk_abort_request(struct request *req)
+{
+	if (blk_mark_rq_complete(req))
+		return;
+	blk_delete_timer(req);
+	blk_rq_timed_out(req);
+}
+EXPORT_SYMBOL_GPL(blk_abort_request);
+
+/**
+ * blk_add_timer - Start timeout timer for a single request
+ * @req:	request that is about to start running.
+ *
+ * Notes:
+ *    Each request has its own timer, and as it is added to the queue, we
+ *    set up the timer. When the request completes, we cancel the timer.
+ */
+void blk_add_timer(struct request *req)
+{
+	struct request_queue *q = req->q;
+	unsigned long expiry;
+
+	if (!q->rq_timed_out_fn)
+		return;
+
+	BUG_ON(!list_empty(&req->timeout_list));
+	BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
+
+	if (req->timeout)
+		req->deadline = jiffies + req->timeout;
+	else {
+		req->deadline = jiffies + q->rq_timeout;
+		/*
+		 * Some LLDs, like scsi, peek at the timeout to prevent
+		 * a command from being retried forever.
+		 */
+		req->timeout = q->rq_timeout;
+	}
+	list_add_tail(&req->timeout_list, &q->timeout_list);
+
+	/*
+	 * If the timer isn't already pending or this timeout is earlier
+	 * than an existing one, modify the timer. Round up to next nearest
+	 * second.
+	 */
+	expiry = round_jiffies_up(req->deadline);
+
+	if (!timer_pending(&q->timeout) ||
+	    time_before(expiry, q->timeout.expires))
+		mod_timer(&q->timeout, expiry);
+}
+
+/**
+ * blk_abort_queue -- Abort all request on given queue
+ * @queue:	pointer to queue
+ *
+ */
+void blk_abort_queue(struct request_queue *q)
+{
+	unsigned long flags;
+	struct request *rq, *tmp;
+	LIST_HEAD(list);
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	elv_abort_queue(q);
+
+	/*
+	 * Splice entries to local list, to avoid deadlocking if entries
+	 * get readded to the timeout list by error handling
+	 */
+	list_splice_init(&q->timeout_list, &list);
+
+	list_for_each_entry_safe(rq, tmp, &list, timeout_list)
+		blk_abort_request(rq);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+}
+EXPORT_SYMBOL_GPL(blk_abort_queue);
diff --git a/libdde-linux26/contrib/block/blk.h b/libdde-linux26/contrib/block/blk.h
new file mode 100644
index 00000000..0dce92c3
--- /dev/null
+++ b/libdde-linux26/contrib/block/blk.h
@@ -0,0 +1,119 @@
+#ifndef BLK_INTERNAL_H
+#define BLK_INTERNAL_H
+
+/* Amount of time in which a process may batch requests */
+#define BLK_BATCH_TIME	(HZ/50UL)
+
+/* Number of requests a "batching" process may submit */
+#define BLK_BATCH_REQ	32
+
+extern struct kmem_cache *blk_requestq_cachep;
+extern struct kobj_type blk_queue_ktype;
+
+void init_request_from_bio(struct request *req, struct bio *bio);
+void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
+			struct bio *bio);
+void __blk_queue_free_tags(struct request_queue *q);
+
+void blk_unplug_work(struct work_struct *work);
+void blk_unplug_timeout(unsigned long data);
+void blk_rq_timed_out_timer(unsigned long data);
+void blk_delete_timer(struct request *);
+void blk_add_timer(struct request *);
+void __generic_unplug_device(struct request_queue *);
+
+/*
+ * Internal atomic flags for request handling
+ */
+enum rq_atomic_flags {
+	REQ_ATOM_COMPLETE = 0,
+};
+
+/*
+ * EH timer and IO completion will both attempt to 'grab' the request, make
+ * sure that only one of them suceeds
+ */
+static inline int blk_mark_rq_complete(struct request *rq)
+{
+	return test_and_set_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
+}
+
+static inline void blk_clear_rq_complete(struct request *rq)
+{
+	clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
+}
+
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+int blk_should_fake_timeout(struct request_queue *);
+ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
+ssize_t part_timeout_store(struct device *, struct device_attribute *,
+				const char *, size_t);
+#else
+static inline int blk_should_fake_timeout(struct request_queue *q)
+{
+	return 0;
+}
+#endif
+
+struct io_context *current_io_context(gfp_t gfp_flags, int node);
+
+int ll_back_merge_fn(struct request_queue *q, struct request *req,
+		     struct bio *bio);
+int ll_front_merge_fn(struct request_queue *q, struct request *req, 
+		      struct bio *bio);
+int attempt_back_merge(struct request_queue *q, struct request *rq);
+int attempt_front_merge(struct request_queue *q, struct request *rq);
+void blk_recalc_rq_segments(struct request *rq);
+void blk_recalc_rq_sectors(struct request *rq, int nsect);
+
+void blk_queue_congestion_threshold(struct request_queue *q);
+
+int blk_dev_init(void);
+
+/*
+ * Return the threshold (number of used requests) at which the queue is
+ * considered to be congested.  It include a little hysteresis to keep the
+ * context switch rate down.
+ */
+static inline int queue_congestion_on_threshold(struct request_queue *q)
+{
+	return q->nr_congestion_on;
+}
+
+/*
+ * The threshold at which a queue is considered to be uncongested
+ */
+static inline int queue_congestion_off_threshold(struct request_queue *q)
+{
+	return q->nr_congestion_off;
+}
+
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+#define rq_for_each_integrity_segment(bvl, _rq, _iter)		\
+	__rq_for_each_bio(_iter.bio, _rq)			\
+		bip_for_each_vec(bvl, _iter.bio->bi_integrity, _iter.i)
+
+#endif /* BLK_DEV_INTEGRITY */
+
+static inline int blk_cpu_to_group(int cpu)
+{
+#ifdef CONFIG_SCHED_MC
+	const struct cpumask *mask = cpu_coregroup_mask(cpu);
+	return cpumask_first(mask);
+#elif defined(CONFIG_SCHED_SMT)
+	return first_cpu(per_cpu(cpu_sibling_map, cpu));
+#else
+	return cpu;
+#endif
+}
+
+static inline int blk_do_io_stat(struct request_queue *q)
+{
+	if (q)
+		return blk_queue_io_stat(q);
+
+	return 0;
+}
+
+#endif
diff --git a/libdde-linux26/contrib/block/cfq-iosched.c b/libdde-linux26/contrib/block/cfq-iosched.c
new file mode 100644
index 00000000..37c1fca9
--- /dev/null
+++ b/libdde-linux26/contrib/block/cfq-iosched.c
@@ -0,0 +1,2465 @@
+/*
+ *  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@kernel.dk>
+ */
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/elevator.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include <linux/blktrace_api.h>
+#include <ddekit/timer.h>
+
+/*
+ * tunables
+ */
+/* max queue in one round of service */
+static const int cfq_quantum = 4;
+static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
+/* maximum backwards seek, in KiB */
+static const int cfq_back_max = 16 * 1024;
+/* penalty of a backwards seek */
+static const int cfq_back_penalty = 2;
+static const int cfq_slice_sync = HZ / 10;
+static int cfq_slice_async = HZ / 25;
+static const int cfq_slice_async_rq = 2;
+static int cfq_slice_idle = HZ / 125;
+
+/*
+ * offset from end of service tree
+ */
+#define CFQ_IDLE_DELAY		(HZ / 5)
+
+/*
+ * below this threshold, we consider thinktime immediate
+ */
+#define CFQ_MIN_TT		(2)
+
+#define CFQ_SLICE_SCALE		(5)
+#define CFQ_HW_QUEUE_MIN	(5)
+
+#define RQ_CIC(rq)		\
+	((struct cfq_io_context *) (rq)->elevator_private)
+#define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private2)
+
+static struct kmem_cache *cfq_pool;
+static struct kmem_cache *cfq_ioc_pool;
+
+static DEFINE_PER_CPU(unsigned long, ioc_count);
+static struct completion *ioc_gone;
+static DEFINE_SPINLOCK(ioc_gone_lock);
+
+#define CFQ_PRIO_LISTS		IOPRIO_BE_NR
+#define cfq_class_idle(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
+#define cfq_class_rt(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
+
+#define ASYNC			(0)
+#define SYNC			(1)
+
+#define sample_valid(samples)	((samples) > 80)
+
+/*
+ * Most of our rbtree usage is for sorting with min extraction, so
+ * if we cache the leftmost node we don't have to walk down the tree
+ * to find it. Idea borrowed from Ingo Molnars CFS scheduler. We should
+ * move this into the elevator for the rq sorting as well.
+ */
+struct cfq_rb_root {
+	struct rb_root rb;
+	struct rb_node *left;
+};
+#define CFQ_RB_ROOT	(struct cfq_rb_root) { RB_ROOT, NULL, }
+
+/*
+ * Per block device queue structure
+ */
+struct cfq_data {
+	struct request_queue *queue;
+
+	/*
+	 * rr list of queues with requests and the count of them
+	 */
+	struct cfq_rb_root service_tree;
+	unsigned int busy_queues;
+	/*
+	 * Used to track any pending rt requests so we can pre-empt current
+	 * non-RT cfqq in service when this value is non-zero.
+	 */
+	unsigned int busy_rt_queues;
+
+	int rq_in_driver;
+	int sync_flight;
+
+	/*
+	 * queue-depth detection
+	 */
+	int rq_queued;
+	int hw_tag;
+	int hw_tag_samples;
+	int rq_in_driver_peak;
+
+	/*
+	 * 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;
+
+	/*
+	 * async queue for each priority case
+	 */
+	struct cfq_queue *async_cfqq[2][IOPRIO_BE_NR];
+	struct cfq_queue *async_idle_cfqq;
+
+	sector_t last_position;
+	unsigned long last_end_request;
+
+	/*
+	 * tunables, see top of file
+	 */
+	unsigned int cfq_quantum;
+	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;
+
+	struct list_head cic_list;
+};
+
+/*
+ * Per process-grouping structure
+ */
+struct cfq_queue {
+	/* reference count */
+	atomic_t ref;
+	/* various state flags, see below */
+	unsigned int flags;
+	/* parent cfq_data */
+	struct cfq_data *cfqd;
+	/* service_tree member */
+	struct rb_node rb_node;
+	/* service_tree key */
+	unsigned long rb_key;
+	/* sorted list of pending requests */
+	struct rb_root sort_list;
+	/* if fifo isn't expired, next request to serve */
+	struct request *next_rq;
+	/* 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_end;
+	long slice_resid;
+
+	/* pending metadata requests */
+	int meta_pending;
+	/* number of requests that are on the dispatch list or inside driver */
+	int dispatched;
+
+	/* io prio of this group */
+	unsigned short ioprio, org_ioprio;
+	unsigned short ioprio_class, org_ioprio_class;
+
+	pid_t pid;
+};
+
+enum cfqq_state_flags {
+	CFQ_CFQQ_FLAG_on_rr = 0,	/* on round-robin busy list */
+	CFQ_CFQQ_FLAG_wait_request,	/* waiting for a request */
+	CFQ_CFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
+	CFQ_CFQQ_FLAG_must_alloc_slice,	/* per-slice must_alloc flag */
+	CFQ_CFQQ_FLAG_must_dispatch,	/* must dispatch, even if expired */
+	CFQ_CFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
+	CFQ_CFQQ_FLAG_idle_window,	/* slice idling enabled */
+	CFQ_CFQQ_FLAG_prio_changed,	/* task priority has changed */
+	CFQ_CFQQ_FLAG_queue_new,	/* queue never been serviced */
+	CFQ_CFQQ_FLAG_slice_new,	/* no requests dispatched in slice */
+	CFQ_CFQQ_FLAG_sync,		/* synchronous queue */
+};
+
+#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);
+CFQ_CFQQ_FNS(queue_new);
+CFQ_CFQQ_FNS(slice_new);
+CFQ_CFQQ_FNS(sync);
+#undef CFQ_CFQQ_FNS
+
+#define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
+	blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
+#define cfq_log(cfqd, fmt, args...)	\
+	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
+
+static void cfq_dispatch_insert(struct request_queue *, struct request *);
+static struct cfq_queue *cfq_get_queue(struct cfq_data *, int,
+				       struct io_context *, gfp_t);
+static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
+						struct io_context *);
+
+static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
+					    int is_sync)
+{
+	return cic->cfqq[!!is_sync];
+}
+
+static inline void cic_set_cfqq(struct cfq_io_context *cic,
+				struct cfq_queue *cfqq, int is_sync)
+{
+	cic->cfqq[!!is_sync] = cfqq;
+}
+
+/*
+ * We regard a request as SYNC, if it's either a read or has the SYNC bit
+ * set (in which case it could also be direct WRITE).
+ */
+static inline int cfq_bio_sync(struct bio *bio)
+{
+	if (bio_data_dir(bio) == READ || bio_sync(bio))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * 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) {
+		cfq_log(cfqd, "schedule dispatch");
+		kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work);
+	}
+}
+
+static int cfq_queue_empty(struct request_queue *q)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+
+	return !cfqd->busy_queues;
+}
+
+/*
+ * 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_slice(struct cfq_data *cfqd, int sync,
+				 unsigned short prio)
+{
+	const int base_slice = cfqd->cfq_slice[sync];
+
+	WARN_ON(prio >= IOPRIO_BE_NR);
+
+	return base_slice + (base_slice/CFQ_SLICE_SCALE * (4 - prio));
+}
+
+static inline int
+cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
+}
+
+static inline void
+cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies;
+	cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
+}
+
+/*
+ * We need to wrap this check in cfq_cfqq_slice_new(), since ->slice_end
+ * isn't valid until the first request from the dispatch is activated
+ * and the slice time set.
+ */
+static inline int cfq_slice_used(struct cfq_queue *cfqq)
+{
+	if (cfq_cfqq_slice_new(cfqq))
+		return 0;
+	if (time_before(jiffies, cfqq->slice_end))
+		return 0;
+
+	return 1;
+}
+
+/*
+ * Lifted from AS - choose which of rq1 and rq2 that is best served now.
+ * We choose the request that is closest to the head right now. Distance
+ * behind the head is penalized and only allowed to a certain extent.
+ */
+static struct request *
+cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
+{
+	sector_t last, s1, s2, d1 = 0, d2 = 0;
+	unsigned long back_max;
+#define CFQ_RQ1_WRAP	0x01 /* request 1 wraps */
+#define CFQ_RQ2_WRAP	0x02 /* request 2 wraps */
+	unsigned wrap = 0; /* bit mask: requests behind the disk head? */
+
+	if (rq1 == NULL || rq1 == rq2)
+		return rq2;
+	if (rq2 == NULL)
+		return rq1;
+
+	if (rq_is_sync(rq1) && !rq_is_sync(rq2))
+		return rq1;
+	else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
+		return rq2;
+	if (rq_is_meta(rq1) && !rq_is_meta(rq2))
+		return rq1;
+	else if (rq_is_meta(rq2) && !rq_is_meta(rq1))
+		return rq2;
+
+	s1 = rq1->sector;
+	s2 = rq2->sector;
+
+	last = cfqd->last_position;
+
+	/*
+	 * 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
+		wrap |= CFQ_RQ1_WRAP;
+
+	if (s2 >= last)
+		d2 = s2 - last;
+	else if (s2 + back_max >= last)
+		d2 = (last - s2) * cfqd->cfq_back_penalty;
+	else
+		wrap |= CFQ_RQ2_WRAP;
+
+	/* Found required data */
+
+	/*
+	 * By doing switch() on the bit mask "wrap" we avoid having to
+	 * check two variables for all permutations: --> faster!
+	 */
+	switch (wrap) {
+	case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
+		if (d1 < d2)
+			return rq1;
+		else if (d2 < d1)
+			return rq2;
+		else {
+			if (s1 >= s2)
+				return rq1;
+			else
+				return rq2;
+		}
+
+	case CFQ_RQ2_WRAP:
+		return rq1;
+	case CFQ_RQ1_WRAP:
+		return rq2;
+	case (CFQ_RQ1_WRAP|CFQ_RQ2_WRAP): /* both rqs wrapped */
+	default:
+		/*
+		 * Since both rqs are wrapped,
+		 * start with the one that's further behind head
+		 * (--> only *one* back seek required),
+		 * since back seek takes more time than forward.
+		 */
+		if (s1 <= s2)
+			return rq1;
+		else
+			return rq2;
+	}
+}
+
+/*
+ * The below is leftmost cache rbtree addon
+ */
+static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
+{
+	if (!root->left)
+		root->left = rb_first(&root->rb);
+
+	if (root->left)
+		return rb_entry(root->left, struct cfq_queue, rb_node);
+
+	return NULL;
+}
+
+static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root)
+{
+	if (root->left == n)
+		root->left = NULL;
+
+	rb_erase(n, &root->rb);
+	RB_CLEAR_NODE(n);
+}
+
+/*
+ * would be nice to take fifo expire time into account as well
+ */
+static struct request *
+cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+		  struct request *last)
+{
+	struct rb_node *rbnext = rb_next(&last->rb_node);
+	struct rb_node *rbprev = rb_prev(&last->rb_node);
+	struct request *next = NULL, *prev = NULL;
+
+	BUG_ON(RB_EMPTY_NODE(&last->rb_node));
+
+	if (rbprev)
+		prev = rb_entry_rq(rbprev);
+
+	if (rbnext)
+		next = rb_entry_rq(rbnext);
+	else {
+		rbnext = rb_first(&cfqq->sort_list);
+		if (rbnext && rbnext != &last->rb_node)
+			next = rb_entry_rq(rbnext);
+	}
+
+	return cfq_choose_req(cfqd, next, prev);
+}
+
+static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
+				      struct cfq_queue *cfqq)
+{
+	/*
+	 * just an approximation, should be ok.
+	 */
+	return (cfqd->busy_queues - 1) * (cfq_prio_slice(cfqd, 1, 0) -
+		       cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
+}
+
+/*
+ * The cfqd->service_tree holds all pending cfq_queue's that have
+ * requests waiting to be processed. It is sorted in the order that
+ * we will service the queues.
+ */
+static void cfq_service_tree_add(struct cfq_data *cfqd,
+				    struct cfq_queue *cfqq, int add_front)
+{
+	struct rb_node **p, *parent;
+	struct cfq_queue *__cfqq;
+	unsigned long rb_key;
+	int left;
+
+	if (cfq_class_idle(cfqq)) {
+		rb_key = CFQ_IDLE_DELAY;
+		parent = rb_last(&cfqd->service_tree.rb);
+		if (parent && parent != &cfqq->rb_node) {
+			__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
+			rb_key += __cfqq->rb_key;
+		} else
+			rb_key += jiffies;
+	} else if (!add_front) {
+		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
+		rb_key += cfqq->slice_resid;
+		cfqq->slice_resid = 0;
+	} else
+		rb_key = 0;
+
+	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
+		/*
+		 * same position, nothing more to do
+		 */
+		if (rb_key == cfqq->rb_key)
+			return;
+
+		cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
+	}
+
+	left = 1;
+	parent = NULL;
+	p = &cfqd->service_tree.rb.rb_node;
+	while (*p) {
+		struct rb_node **n;
+
+		parent = *p;
+		__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
+
+		/*
+		 * sort RT queues first, we always want to give
+		 * preference to them. IDLE queues goes to the back.
+		 * after that, sort on the next service time.
+		 */
+		if (cfq_class_rt(cfqq) > cfq_class_rt(__cfqq))
+			n = &(*p)->rb_left;
+		else if (cfq_class_rt(cfqq) < cfq_class_rt(__cfqq))
+			n = &(*p)->rb_right;
+		else if (cfq_class_idle(cfqq) < cfq_class_idle(__cfqq))
+			n = &(*p)->rb_left;
+		else if (cfq_class_idle(cfqq) > cfq_class_idle(__cfqq))
+			n = &(*p)->rb_right;
+		else if (rb_key < __cfqq->rb_key)
+			n = &(*p)->rb_left;
+		else
+			n = &(*p)->rb_right;
+
+		if (n == &(*p)->rb_right)
+			left = 0;
+
+		p = n;
+	}
+
+	if (left)
+		cfqd->service_tree.left = &cfqq->rb_node;
+
+	cfqq->rb_key = rb_key;
+	rb_link_node(&cfqq->rb_node, parent, p);
+	rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb);
+}
+
+/*
+ * Update cfqq's position in the service tree.
+ */
+static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	/*
+	 * Resorting requires the cfqq to be on the RR list already.
+	 */
+	if (cfq_cfqq_on_rr(cfqq))
+		cfq_service_tree_add(cfqd, cfqq, 0);
+}
+
+/*
+ * add to busy list of queues for service, trying to be fair in ordering
+ * the pending list according to last request service
+ */
+static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	cfq_log_cfqq(cfqd, cfqq, "add_to_rr");
+	BUG_ON(cfq_cfqq_on_rr(cfqq));
+	cfq_mark_cfqq_on_rr(cfqq);
+	cfqd->busy_queues++;
+	if (cfq_class_rt(cfqq))
+		cfqd->busy_rt_queues++;
+
+	cfq_resort_rr_list(cfqd, cfqq);
+}
+
+/*
+ * Called when the cfqq no longer has requests pending, remove it from
+ * the service tree.
+ */
+static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
+	BUG_ON(!cfq_cfqq_on_rr(cfqq));
+	cfq_clear_cfqq_on_rr(cfqq);
+
+	if (!RB_EMPTY_NODE(&cfqq->rb_node))
+		cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
+
+	BUG_ON(!cfqd->busy_queues);
+	cfqd->busy_queues--;
+	if (cfq_class_rt(cfqq))
+		cfqd->busy_rt_queues--;
+}
+
+/*
+ * rb tree support functions
+ */
+static void cfq_del_rq_rb(struct request *rq)
+{
+	struct cfq_queue *cfqq = RQ_CFQQ(rq);
+	struct cfq_data *cfqd = cfqq->cfqd;
+	const int sync = rq_is_sync(rq);
+
+	BUG_ON(!cfqq->queued[sync]);
+	cfqq->queued[sync]--;
+
+	elv_rb_del(&cfqq->sort_list, rq);
+
+	if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list))
+		cfq_del_cfqq_rr(cfqd, cfqq);
+}
+
+static void cfq_add_rq_rb(struct request *rq)
+{
+	struct cfq_queue *cfqq = RQ_CFQQ(rq);
+	struct cfq_data *cfqd = cfqq->cfqd;
+	struct request *__alias;
+
+	cfqq->queued[rq_is_sync(rq)]++;
+
+	/*
+	 * looks a little odd, but the first insert might return an alias.
+	 * if that happens, put the alias on the dispatch list
+	 */
+	while ((__alias = elv_rb_add(&cfqq->sort_list, rq)) != NULL)
+		cfq_dispatch_insert(cfqd->queue, __alias);
+
+	if (!cfq_cfqq_on_rr(cfqq))
+		cfq_add_cfqq_rr(cfqd, cfqq);
+
+	/*
+	 * check if this request is a better next-serve candidate
+	 */
+	cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq);
+	BUG_ON(!cfqq->next_rq);
+}
+
+static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
+{
+	elv_rb_del(&cfqq->sort_list, rq);
+	cfqq->queued[rq_is_sync(rq)]--;
+	cfq_add_rq_rb(rq);
+}
+
+static struct request *
+cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio)
+{
+	struct task_struct *tsk = current;
+	struct cfq_io_context *cic;
+	struct cfq_queue *cfqq;
+
+	cic = cfq_cic_lookup(cfqd, tsk->io_context);
+	if (!cic)
+		return NULL;
+
+	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
+	if (cfqq) {
+		sector_t sector = bio->bi_sector + bio_sectors(bio);
+
+		return elv_rb_find(&cfqq->sort_list, sector);
+	}
+
+	return NULL;
+}
+
+static void cfq_activate_request(struct request_queue *q, struct request *rq)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+
+	cfqd->rq_in_driver++;
+	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
+						cfqd->rq_in_driver);
+
+	cfqd->last_position = rq->hard_sector + rq->hard_nr_sectors;
+}
+
+static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+
+	WARN_ON(!cfqd->rq_in_driver);
+	cfqd->rq_in_driver--;
+	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
+						cfqd->rq_in_driver);
+}
+
+static void cfq_remove_request(struct request *rq)
+{
+	struct cfq_queue *cfqq = RQ_CFQQ(rq);
+
+	if (cfqq->next_rq == rq)
+		cfqq->next_rq = cfq_find_next_rq(cfqq->cfqd, cfqq, rq);
+
+	list_del_init(&rq->queuelist);
+	cfq_del_rq_rb(rq);
+
+	cfqq->cfqd->rq_queued--;
+	if (rq_is_meta(rq)) {
+		WARN_ON(!cfqq->meta_pending);
+		cfqq->meta_pending--;
+	}
+}
+
+static int cfq_merge(struct request_queue *q, struct request **req,
+		     struct bio *bio)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+	struct request *__rq;
+
+	__rq = cfq_find_rq_fmerge(cfqd, bio);
+	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+		*req = __rq;
+		return ELEVATOR_FRONT_MERGE;
+	}
+
+	return ELEVATOR_NO_MERGE;
+}
+
+static void cfq_merged_request(struct request_queue *q, struct request *req,
+			       int type)
+{
+	if (type == ELEVATOR_FRONT_MERGE) {
+		struct cfq_queue *cfqq = RQ_CFQQ(req);
+
+		cfq_reposition_rq_rb(cfqq, req);
+	}
+}
+
+static void
+cfq_merged_requests(struct request_queue *q, struct request *rq,
+		    struct request *next)
+{
+	/*
+	 * 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 int cfq_allow_merge(struct request_queue *q, struct request *rq,
+			   struct bio *bio)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+	struct cfq_io_context *cic;
+	struct cfq_queue *cfqq;
+
+	/*
+	 * Disallow merge of a sync bio into an async request.
+	 */
+	if (cfq_bio_sync(bio) && !rq_is_sync(rq))
+		return 0;
+
+	/*
+	 * Lookup the cfqq that this bio will be queued with. Allow
+	 * merge only if rq is queued there.
+	 */
+	cic = cfq_cic_lookup(cfqd, current->io_context);
+	if (!cic)
+		return 0;
+
+	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
+	if (cfqq == RQ_CFQQ(rq))
+		return 1;
+
+	return 0;
+}
+
+static void __cfq_set_active_queue(struct cfq_data *cfqd,
+				   struct cfq_queue *cfqq)
+{
+	if (cfqq) {
+		cfq_log_cfqq(cfqd, cfqq, "set_active");
+		cfqq->slice_end = 0;
+		cfq_clear_cfqq_must_alloc_slice(cfqq);
+		cfq_clear_cfqq_fifo_expire(cfqq);
+		cfq_mark_cfqq_slice_new(cfqq);
+		cfq_clear_cfqq_queue_new(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 timed_out)
+{
+	cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
+
+	if (cfq_cfqq_wait_request(cfqq))
+		del_timer(&cfqd->idle_slice_timer);
+
+	cfq_clear_cfqq_must_dispatch(cfqq);
+	cfq_clear_cfqq_wait_request(cfqq);
+
+	/*
+	 * store what was left of this slice, if the queue idled/timed out
+	 */
+	if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
+		cfqq->slice_resid = cfqq->slice_end - jiffies;
+		cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
+	}
+
+	cfq_resort_rr_list(cfqd, cfqq);
+
+	if (cfqq == cfqd->active_queue)
+		cfqd->active_queue = NULL;
+
+	if (cfqd->active_cic) {
+		put_io_context(cfqd->active_cic->ioc);
+		cfqd->active_cic = NULL;
+	}
+}
+
+static inline void cfq_slice_expired(struct cfq_data *cfqd, int timed_out)
+{
+	struct cfq_queue *cfqq = cfqd->active_queue;
+
+	if (cfqq)
+		__cfq_slice_expired(cfqd, cfqq, timed_out);
+}
+
+/*
+ * Get next queue for service. Unless we have a queue preemption,
+ * we'll simply select the first cfqq in the service tree.
+ */
+static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
+{
+	if (RB_EMPTY_ROOT(&cfqd->service_tree.rb))
+		return NULL;
+
+	return cfq_rb_first(&cfqd->service_tree);
+}
+
+/*
+ * Get and set a new active queue for service.
+ */
+static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd)
+{
+	struct cfq_queue *cfqq;
+
+	cfqq = cfq_get_next_queue(cfqd);
+	__cfq_set_active_queue(cfqd, cfqq);
+	return cfqq;
+}
+
+static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
+					  struct request *rq)
+{
+	if (rq->sector >= cfqd->last_position)
+		return rq->sector - cfqd->last_position;
+	else
+		return cfqd->last_position - rq->sector;
+}
+
+static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq)
+{
+	struct cfq_io_context *cic = cfqd->active_cic;
+
+	if (!sample_valid(cic->seek_samples))
+		return 0;
+
+	return cfq_dist_from_last(cfqd, rq) <= cic->seek_mean;
+}
+
+static int cfq_close_cooperator(struct cfq_data *cfq_data,
+				struct cfq_queue *cfqq)
+{
+	/*
+	 * We should notice if some of the queues are cooperating, eg
+	 * working closely on the same area of the disk. In that case,
+	 * we can group them together and don't waste time idling.
+	 */
+	return 0;
+}
+
+#define CIC_SEEKY(cic) ((cic)->seek_mean > (8 * 1024))
+
+static void cfq_arm_slice_timer(struct cfq_data *cfqd)
+{
+	struct cfq_queue *cfqq = cfqd->active_queue;
+	struct cfq_io_context *cic;
+	unsigned long sl;
+
+	/*
+	 * SSD device without seek penalty, disable idling. But only do so
+	 * for devices that support queuing, otherwise we still have a problem
+	 * with sync vs async workloads.
+	 */
+	if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag)
+		return;
+
+	WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list));
+	WARN_ON(cfq_cfqq_slice_new(cfqq));
+
+	/*
+	 * idle is disabled, either manually or by past process history
+	 */
+	if (!cfqd->cfq_slice_idle || !cfq_cfqq_idle_window(cfqq))
+		return;
+
+	/*
+	 * still requests with the driver, don't idle
+	 */
+	if (cfqd->rq_in_driver)
+		return;
+
+	/*
+	 * task has exited, don't wait
+	 */
+	cic = cfqd->active_cic;
+	if (!cic || !atomic_read(&cic->ioc->nr_tasks))
+		return;
+
+	/*
+	 * See if this prio level has a good candidate
+	 */
+	if (cfq_close_cooperator(cfqd, cfqq) &&
+	    (sample_valid(cic->ttime_samples) && cic->ttime_mean > 2))
+		return;
+
+	cfq_mark_cfqq_must_dispatch(cfqq);
+	cfq_mark_cfqq_wait_request(cfqq);
+
+	/*
+	 * we don't want to idle for seeks, but we do want to allow
+	 * fair distribution of slice time for a process doing back-to-back
+	 * seeks. so allow a little bit of time for him to submit a new rq
+	 */
+	sl = cfqd->cfq_slice_idle;
+	if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic))
+		sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT));
+
+	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
+	cfq_log(cfqd, "arm_idle: %lu", sl);
+}
+
+/*
+ * Move request from internal lists to the request queue dispatch list.
+ */
+static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+	struct cfq_queue *cfqq = RQ_CFQQ(rq);
+
+	cfq_log_cfqq(cfqd, cfqq, "dispatch_insert");
+
+	cfq_remove_request(rq);
+	cfqq->dispatched++;
+	elv_dispatch_sort(q, rq);
+
+	if (cfq_cfqq_sync(cfqq))
+		cfqd->sync_flight++;
+}
+
+/*
+ * return expired entry, or NULL to just start from scratch in rbtree
+ */
+static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
+{
+	struct cfq_data *cfqd = cfqq->cfqd;
+	struct request *rq;
+	int fifo;
+
+	if (cfq_cfqq_fifo_expire(cfqq))
+		return NULL;
+
+	cfq_mark_cfqq_fifo_expire(cfqq);
+
+	if (list_empty(&cfqq->fifo))
+		return NULL;
+
+	fifo = cfq_cfqq_sync(cfqq);
+	rq = rq_entry_fifo(cfqq->fifo.next);
+
+	if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo]))
+		rq = NULL;
+
+	cfq_log_cfqq(cfqd, cfqq, "fifo=%p", rq);
+	return rq;
+}
+
+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));
+}
+
+/*
+ * Select a queue for service. If we have a current active queue,
+ * check whether to continue servicing it, or retrieve and set a new one.
+ */
+static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
+{
+	struct cfq_queue *cfqq;
+
+	cfqq = cfqd->active_queue;
+	if (!cfqq)
+		goto new_queue;
+
+	/*
+	 * The active queue has run out of time, expire it and select new.
+	 */
+	if (cfq_slice_used(cfqq))
+		goto expire;
+
+	/*
+	 * If we have a RT cfqq waiting, then we pre-empt the current non-rt
+	 * cfqq.
+	 */
+	if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues) {
+		/*
+		 * We simulate this as cfqq timed out so that it gets to bank
+		 * the remaining of its time slice.
+		 */
+		cfq_log_cfqq(cfqd, cfqq, "preempt");
+		cfq_slice_expired(cfqd, 1);
+		goto new_queue;
+	}
+
+	/*
+	 * The active queue has requests and isn't expired, allow it to
+	 * dispatch.
+	 */
+	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
+		goto keep_queue;
+
+	/*
+	 * No requests pending. If the active queue still has requests in
+	 * flight or is idling for a new request, allow either of these
+	 * conditions to happen (or time out) before selecting a new queue.
+	 */
+	if (timer_pending(&cfqd->idle_slice_timer) ||
+	    (cfqq->dispatched && cfq_cfqq_idle_window(cfqq))) {
+		cfqq = NULL;
+		goto keep_queue;
+	}
+
+expire:
+	cfq_slice_expired(cfqd, 0);
+new_queue:
+	cfqq = cfq_set_active_queue(cfqd);
+keep_queue:
+	return cfqq;
+}
+
+/*
+ * Dispatch some requests from cfqq, moving them to the request queue
+ * dispatch list.
+ */
+static int
+__cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+			int max_dispatch)
+{
+	int dispatched = 0;
+
+	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
+
+	do {
+		struct request *rq;
+
+		/*
+		 * follow expired path, else get first next available
+		 */
+		rq = cfq_check_fifo(cfqq);
+		if (rq == NULL)
+			rq = cfqq->next_rq;
+
+		/*
+		 * finally, insert request into driver dispatch list
+		 */
+		cfq_dispatch_insert(cfqd->queue, rq);
+
+		dispatched++;
+
+		if (!cfqd->active_cic) {
+			atomic_inc(&RQ_CIC(rq)->ioc->refcount);
+			cfqd->active_cic = RQ_CIC(rq);
+		}
+
+		if (RB_EMPTY_ROOT(&cfqq->sort_list))
+			break;
+
+		/*
+		 * If there is a non-empty RT cfqq waiting for current
+		 * cfqq's timeslice to complete, pre-empt this cfqq
+		 */
+		if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues)
+			break;
+
+	} while (dispatched < max_dispatch);
+
+	/*
+	 * expire an async queue immediately if it has used up its slice. idle
+	 * queue always expire after 1 dispatch round.
+	 */
+	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
+	    dispatched >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
+	    cfq_class_idle(cfqq))) {
+		cfqq->slice_end = jiffies + 1;
+		cfq_slice_expired(cfqd, 0);
+	}
+
+	return dispatched;
+}
+
+static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq)
+{
+	int dispatched = 0;
+
+	while (cfqq->next_rq) {
+		cfq_dispatch_insert(cfqq->cfqd->queue, cfqq->next_rq);
+		dispatched++;
+	}
+
+	BUG_ON(!list_empty(&cfqq->fifo));
+	return dispatched;
+}
+
+/*
+ * Drain our current requests. Used for barriers and when switching
+ * io schedulers on-the-fly.
+ */
+static int cfq_forced_dispatch(struct cfq_data *cfqd)
+{
+	struct cfq_queue *cfqq;
+	int dispatched = 0;
+
+	while ((cfqq = cfq_rb_first(&cfqd->service_tree)) != NULL)
+		dispatched += __cfq_forced_dispatch_cfqq(cfqq);
+
+	cfq_slice_expired(cfqd, 0);
+
+	BUG_ON(cfqd->busy_queues);
+
+	cfq_log(cfqd, "forced_dispatch=%d\n", dispatched);
+	return dispatched;
+}
+
+static int cfq_dispatch_requests(struct request_queue *q, int force)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+	struct cfq_queue *cfqq;
+	int dispatched;
+
+	if (!cfqd->busy_queues)
+		return 0;
+
+	if (unlikely(force))
+		return cfq_forced_dispatch(cfqd);
+
+	dispatched = 0;
+	while ((cfqq = cfq_select_queue(cfqd)) != NULL) {
+		int max_dispatch;
+
+		max_dispatch = cfqd->cfq_quantum;
+		if (cfq_class_idle(cfqq))
+			max_dispatch = 1;
+
+		if (cfqq->dispatched >= max_dispatch && cfqd->busy_queues > 1)
+			break;
+
+		if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
+			break;
+
+		cfq_clear_cfqq_must_dispatch(cfqq);
+		cfq_clear_cfqq_wait_request(cfqq);
+		del_timer(&cfqd->idle_slice_timer);
+
+		dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);
+	}
+
+	cfq_log(cfqd, "dispatched=%d", dispatched);
+	return dispatched;
+}
+
+/*
+ * task holds one reference to the queue, dropped when task exits. each rq
+ * in-flight on this queue also holds a reference, dropped when rq is freed.
+ *
+ * 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;
+
+	cfq_log_cfqq(cfqd, cfqq, "put_queue");
+	BUG_ON(rb_first(&cfqq->sort_list));
+	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
+	BUG_ON(cfq_cfqq_on_rr(cfqq));
+
+	if (unlikely(cfqd->active_queue == cfqq)) {
+		__cfq_slice_expired(cfqd, cfqq, 0);
+		cfq_schedule_dispatch(cfqd);
+	}
+
+	kmem_cache_free(cfq_pool, cfqq);
+}
+
+/*
+ * Must always be called with the rcu_read_lock() held
+ */
+static void
+__call_for_each_cic(struct io_context *ioc,
+		    void (*func)(struct io_context *, struct cfq_io_context *))
+{
+	struct cfq_io_context *cic;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_rcu(cic, n, &ioc->cic_list, cic_list)
+		func(ioc, cic);
+}
+
+/*
+ * Call func for each cic attached to this ioc.
+ */
+static void
+call_for_each_cic(struct io_context *ioc,
+		  void (*func)(struct io_context *, struct cfq_io_context *))
+{
+	rcu_read_lock();
+	__call_for_each_cic(ioc, func);
+	rcu_read_unlock();
+}
+
+static void cfq_cic_free_rcu(struct rcu_head *head)
+{
+	struct cfq_io_context *cic;
+
+	cic = container_of(head, struct cfq_io_context, rcu_head);
+
+	kmem_cache_free(cfq_ioc_pool, cic);
+	elv_ioc_count_dec(ioc_count);
+
+	if (ioc_gone) {
+		/*
+		 * CFQ scheduler is exiting, grab exit lock and check
+		 * the pending io context count. If it hits zero,
+		 * complete ioc_gone and set it back to NULL
+		 */
+		spin_lock(&ioc_gone_lock);
+		if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
+			complete(ioc_gone);
+			ioc_gone = NULL;
+		}
+		spin_unlock(&ioc_gone_lock);
+	}
+}
+
+static void cfq_cic_free(struct cfq_io_context *cic)
+{
+	call_rcu(&cic->rcu_head, cfq_cic_free_rcu);
+}
+
+static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic)
+{
+	unsigned long flags;
+
+	BUG_ON(!cic->dead_key);
+
+	spin_lock_irqsave(&ioc->lock, flags);
+	radix_tree_delete(&ioc->radix_root, cic->dead_key);
+	hlist_del_rcu(&cic->cic_list);
+	spin_unlock_irqrestore(&ioc->lock, flags);
+
+	cfq_cic_free(cic);
+}
+
+/*
+ * Must be called with rcu_read_lock() held or preemption otherwise disabled.
+ * Only two callers of this - ->dtor() which is called with the rcu_read_lock(),
+ * and ->trim() which is called with the task lock held
+ */
+static void cfq_free_io_context(struct io_context *ioc)
+{
+	/*
+	 * ioc->refcount is zero here, or we are called from elv_unregister(),
+	 * so no more cic's are allowed to be linked into this ioc.  So it
+	 * should be ok to iterate over the known list, we will see all cic's
+	 * since no new ones are added.
+	 */
+	__call_for_each_cic(ioc, cic_free_func);
+}
+
+static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	if (unlikely(cfqq == cfqd->active_queue)) {
+		__cfq_slice_expired(cfqd, cfqq, 0);
+		cfq_schedule_dispatch(cfqd);
+	}
+
+	cfq_put_queue(cfqq);
+}
+
+static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
+					 struct cfq_io_context *cic)
+{
+	struct io_context *ioc = cic->ioc;
+
+	list_del_init(&cic->queue_list);
+
+	/*
+	 * Make sure key == NULL is seen for dead queues
+	 */
+	smp_wmb();
+	cic->dead_key = (unsigned long) cic->key;
+	cic->key = NULL;
+
+	if (ioc->ioc_data == cic)
+		rcu_assign_pointer(ioc->ioc_data, NULL);
+
+	if (cic->cfqq[ASYNC]) {
+		cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]);
+		cic->cfqq[ASYNC] = NULL;
+	}
+
+	if (cic->cfqq[SYNC]) {
+		cfq_exit_cfqq(cfqd, cic->cfqq[SYNC]);
+		cic->cfqq[SYNC] = NULL;
+	}
+}
+
+static void cfq_exit_single_io_context(struct io_context *ioc,
+				       struct cfq_io_context *cic)
+{
+	struct cfq_data *cfqd = cic->key;
+
+	if (cfqd) {
+		struct request_queue *q = cfqd->queue;
+		unsigned long flags;
+
+		spin_lock_irqsave(q->queue_lock, flags);
+
+		/*
+		 * Ensure we get a fresh copy of the ->key to prevent
+		 * race between exiting task and queue
+		 */
+		smp_read_barrier_depends();
+		if (cic->key)
+			__cfq_exit_single_io_context(cfqd, cic);
+
+		spin_unlock_irqrestore(q->queue_lock, flags);
+	}
+}
+
+/*
+ * The process that ioc belongs to has exited, we need to clean up
+ * and put the internal structures we have that belongs to that process.
+ */
+static void cfq_exit_io_context(struct io_context *ioc)
+{
+	call_for_each_cic(ioc, cfq_exit_single_io_context);
+}
+
+static struct cfq_io_context *
+cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
+{
+	struct cfq_io_context *cic;
+
+	cic = kmem_cache_alloc_node(cfq_ioc_pool, gfp_mask | __GFP_ZERO,
+							cfqd->queue->node);
+	if (cic) {
+		cic->last_end_request = jiffies;
+		INIT_LIST_HEAD(&cic->queue_list);
+		INIT_HLIST_NODE(&cic->cic_list);
+		cic->dtor = cfq_free_io_context;
+		cic->exit = cfq_exit_io_context;
+		elv_ioc_count_inc(ioc_count);
+	}
+
+	return cic;
+}
+
+static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc)
+{
+	struct task_struct *tsk = current;
+	int ioprio_class;
+
+	if (!cfq_cfqq_prio_changed(cfqq))
+		return;
+
+	ioprio_class = IOPRIO_PRIO_CLASS(ioc->ioprio);
+	switch (ioprio_class) {
+	default:
+		printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
+	case IOPRIO_CLASS_NONE:
+		/*
+		 * no prio set, inherit CPU scheduling settings
+		 */
+		cfqq->ioprio = task_nice_ioprio(tsk);
+		cfqq->ioprio_class = task_nice_ioclass(tsk);
+		break;
+	case IOPRIO_CLASS_RT:
+		cfqq->ioprio = task_ioprio(ioc);
+		cfqq->ioprio_class = IOPRIO_CLASS_RT;
+		break;
+	case IOPRIO_CLASS_BE:
+		cfqq->ioprio = task_ioprio(ioc);
+		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;
+	cfq_clear_cfqq_prio_changed(cfqq);
+}
+
+static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic)
+{
+	struct cfq_data *cfqd = cic->key;
+	struct cfq_queue *cfqq;
+	unsigned long flags;
+
+	if (unlikely(!cfqd))
+		return;
+
+	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+
+	cfqq = cic->cfqq[ASYNC];
+	if (cfqq) {
+		struct cfq_queue *new_cfqq;
+		new_cfqq = cfq_get_queue(cfqd, ASYNC, cic->ioc, 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);
+
+	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+}
+
+static void cfq_ioc_set_ioprio(struct io_context *ioc)
+{
+	call_for_each_cic(ioc, changed_ioprio);
+	ioc->ioprio_changed = 0;
+}
+
+static struct cfq_queue *
+cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync,
+		     struct io_context *ioc, gfp_t gfp_mask)
+{
+	struct cfq_queue *cfqq, *new_cfqq = NULL;
+	struct cfq_io_context *cic;
+
+retry:
+	cic = cfq_cic_lookup(cfqd, ioc);
+	/* cic always exists here */
+	cfqq = cic_to_cfqq(cic, is_sync);
+
+	if (!cfqq) {
+		if (new_cfqq) {
+			cfqq = new_cfqq;
+			new_cfqq = NULL;
+		} else if (gfp_mask & __GFP_WAIT) {
+			/*
+			 * Inform the allocator of the fact that we will
+			 * just repeat this allocation if it fails, to allow
+			 * the allocator to do whatever it needs to attempt to
+			 * free memory.
+			 */
+			spin_unlock_irq(cfqd->queue->queue_lock);
+			new_cfqq = kmem_cache_alloc_node(cfq_pool,
+					gfp_mask | __GFP_NOFAIL | __GFP_ZERO,
+					cfqd->queue->node);
+			spin_lock_irq(cfqd->queue->queue_lock);
+			goto retry;
+		} else {
+			cfqq = kmem_cache_alloc_node(cfq_pool,
+					gfp_mask | __GFP_ZERO,
+					cfqd->queue->node);
+			if (!cfqq)
+				goto out;
+		}
+
+		RB_CLEAR_NODE(&cfqq->rb_node);
+		INIT_LIST_HEAD(&cfqq->fifo);
+
+		atomic_set(&cfqq->ref, 0);
+		cfqq->cfqd = cfqd;
+
+		cfq_mark_cfqq_prio_changed(cfqq);
+		cfq_mark_cfqq_queue_new(cfqq);
+
+		cfq_init_prio_data(cfqq, ioc);
+
+		if (is_sync) {
+			if (!cfq_class_idle(cfqq))
+				cfq_mark_cfqq_idle_window(cfqq);
+			cfq_mark_cfqq_sync(cfqq);
+		}
+		cfqq->pid = current->pid;
+		cfq_log_cfqq(cfqd, cfqq, "alloced");
+	}
+
+	if (new_cfqq)
+		kmem_cache_free(cfq_pool, new_cfqq);
+
+out:
+	WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq);
+	return cfqq;
+}
+
+static struct cfq_queue **
+cfq_async_queue_prio(struct cfq_data *cfqd, int ioprio_class, int ioprio)
+{
+	switch (ioprio_class) {
+	case IOPRIO_CLASS_RT:
+		return &cfqd->async_cfqq[0][ioprio];
+	case IOPRIO_CLASS_BE:
+		return &cfqd->async_cfqq[1][ioprio];
+	case IOPRIO_CLASS_IDLE:
+		return &cfqd->async_idle_cfqq;
+	default:
+		BUG();
+	}
+}
+
+static struct cfq_queue *
+cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc,
+	      gfp_t gfp_mask)
+{
+	const int ioprio = task_ioprio(ioc);
+	const int ioprio_class = task_ioprio_class(ioc);
+	struct cfq_queue **async_cfqq = NULL;
+	struct cfq_queue *cfqq = NULL;
+
+	if (!is_sync) {
+		async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio);
+		cfqq = *async_cfqq;
+	}
+
+	if (!cfqq) {
+		cfqq = cfq_find_alloc_queue(cfqd, is_sync, ioc, gfp_mask);
+		if (!cfqq)
+			return NULL;
+	}
+
+	/*
+	 * pin the queue now that it's allocated, scheduler exit will prune it
+	 */
+	if (!is_sync && !(*async_cfqq)) {
+		atomic_inc(&cfqq->ref);
+		*async_cfqq = cfqq;
+	}
+
+	atomic_inc(&cfqq->ref);
+	return cfqq;
+}
+
+/*
+ * We drop cfq io contexts lazily, so we may find a dead one.
+ */
+static void
+cfq_drop_dead_cic(struct cfq_data *cfqd, struct io_context *ioc,
+		  struct cfq_io_context *cic)
+{
+	unsigned long flags;
+
+	WARN_ON(!list_empty(&cic->queue_list));
+
+	spin_lock_irqsave(&ioc->lock, flags);
+
+	BUG_ON(ioc->ioc_data == cic);
+
+	radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd);
+	hlist_del_rcu(&cic->cic_list);
+	spin_unlock_irqrestore(&ioc->lock, flags);
+
+	cfq_cic_free(cic);
+}
+
+static struct cfq_io_context *
+cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc)
+{
+	struct cfq_io_context *cic;
+	unsigned long flags;
+	void *k;
+
+	if (unlikely(!ioc))
+		return NULL;
+
+	rcu_read_lock();
+
+	/*
+	 * we maintain a last-hit cache, to avoid browsing over the tree
+	 */
+	cic = rcu_dereference(ioc->ioc_data);
+	if (cic && cic->key == cfqd) {
+		rcu_read_unlock();
+		return cic;
+	}
+
+	do {
+		cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd);
+		rcu_read_unlock();
+		if (!cic)
+			break;
+		/* ->key must be copied to avoid race with cfq_exit_queue() */
+		k = cic->key;
+		if (unlikely(!k)) {
+			cfq_drop_dead_cic(cfqd, ioc, cic);
+			rcu_read_lock();
+			continue;
+		}
+
+		spin_lock_irqsave(&ioc->lock, flags);
+		rcu_assign_pointer(ioc->ioc_data, cic);
+		spin_unlock_irqrestore(&ioc->lock, flags);
+		break;
+	} while (1);
+
+	return cic;
+}
+
+/*
+ * Add cic into ioc, using cfqd as the search key. This enables us to lookup
+ * the process specific cfq io context when entered from the block layer.
+ * Also adds the cic to a per-cfqd list, used when this queue is removed.
+ */
+static int cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc,
+			struct cfq_io_context *cic, gfp_t gfp_mask)
+{
+	unsigned long flags;
+	int ret;
+
+	ret = radix_tree_preload(gfp_mask);
+	if (!ret) {
+		cic->ioc = ioc;
+		cic->key = cfqd;
+
+		spin_lock_irqsave(&ioc->lock, flags);
+		ret = radix_tree_insert(&ioc->radix_root,
+						(unsigned long) cfqd, cic);
+		if (!ret)
+			hlist_add_head_rcu(&cic->cic_list, &ioc->cic_list);
+		spin_unlock_irqrestore(&ioc->lock, flags);
+
+		radix_tree_preload_end();
+
+		if (!ret) {
+			spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+			list_add(&cic->queue_list, &cfqd->cic_list);
+			spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+		}
+	}
+
+	if (ret)
+		printk(KERN_ERR "cfq: cic link failed!\n");
+
+	return ret;
+}
+
+/*
+ * 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.
+ */
+static struct cfq_io_context *
+cfq_get_io_context(struct cfq_data *cfqd, 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, cfqd->queue->node);
+	if (!ioc)
+		return NULL;
+
+	cic = cfq_cic_lookup(cfqd, ioc);
+	if (cic)
+		goto out;
+
+	cic = cfq_alloc_io_context(cfqd, gfp_mask);
+	if (cic == NULL)
+		goto err;
+
+	if (cfq_cic_link(cfqd, ioc, cic, gfp_mask))
+		goto err_free;
+
+out:
+	smp_read_barrier_depends();
+	if (unlikely(ioc->ioprio_changed))
+		cfq_ioc_set_ioprio(ioc);
+
+	return cic;
+err_free:
+	cfq_cic_free(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 = jiffies - cic->last_end_request;
+	unsigned long 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;
+}
+
+static void
+cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,
+		       struct request *rq)
+{
+	sector_t sdist;
+	u64 total;
+
+	if (cic->last_request_pos < rq->sector)
+		sdist = rq->sector - cic->last_request_pos;
+	else
+		sdist = cic->last_request_pos - rq->sector;
+
+	/*
+	 * Don't allow the seek distance to get too large from the
+	 * odd fragment, pagein, etc
+	 */
+	if (cic->seek_samples <= 60) /* second&third seek */
+		sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*1024);
+	else
+		sdist = min(sdist, (cic->seek_mean * 4)	+ 2*1024*64);
+
+	cic->seek_samples = (7*cic->seek_samples + 256) / 8;
+	cic->seek_total = (7*cic->seek_total + (u64)256*sdist) / 8;
+	total = cic->seek_total + (cic->seek_samples/2);
+	do_div(total, cic->seek_samples);
+	cic->seek_mean = (sector_t)total;
+}
+
+/*
+ * 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 old_idle, enable_idle;
+
+	/*
+	 * Don't idle for async or idle io prio class
+	 */
+	if (!cfq_cfqq_sync(cfqq) || cfq_class_idle(cfqq))
+		return;
+
+	enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);
+
+	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
+	    (cfqd->hw_tag && CIC_SEEKY(cic)))
+		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 (old_idle != enable_idle) {
+		cfq_log_cfqq(cfqd, cfqq, "idle=%d", enable_idle);
+		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 request *rq)
+{
+	struct cfq_queue *cfqq;
+
+	cfqq = cfqd->active_queue;
+	if (!cfqq)
+		return 0;
+
+	if (cfq_slice_used(cfqq))
+		return 1;
+
+	if (cfq_class_idle(new_cfqq))
+		return 0;
+
+	if (cfq_class_idle(cfqq))
+		return 1;
+
+	/*
+	 * if the new request is sync, but the currently running queue is
+	 * not, let the sync request have priority.
+	 */
+	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
+		return 1;
+
+	/*
+	 * So both queues are sync. Let the new request get disk time if
+	 * it's a metadata request and the current queue is doing regular IO.
+	 */
+	if (rq_is_meta(rq) && !cfqq->meta_pending)
+		return 1;
+
+	/*
+	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
+	 */
+	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
+		return 1;
+
+	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
+		return 0;
+
+	/*
+	 * if this request is as-good as one we would expect from the
+	 * current cfqq, let it preempt
+	 */
+	if (cfq_rq_close(cfqd, rq))
+		return 1;
+
+	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)
+{
+	cfq_log_cfqq(cfqd, cfqq, "preempt");
+	cfq_slice_expired(cfqd, 1);
+
+	/*
+	 * Put the new queue at the front of the of the current list,
+	 * so we know that it will be selected next.
+	 */
+	BUG_ON(!cfq_cfqq_on_rr(cfqq));
+
+	cfq_service_tree_add(cfqd, cfqq, 1);
+
+	cfqq->slice_end = 0;
+	cfq_mark_cfqq_slice_new(cfqq);
+}
+
+/*
+ * Called when a new fs request (rq) is added (to cfqq). Check if there's
+ * something we should do about it
+ */
+static void
+cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+		struct request *rq)
+{
+	struct cfq_io_context *cic = RQ_CIC(rq);
+
+	cfqd->rq_queued++;
+	if (rq_is_meta(rq))
+		cfqq->meta_pending++;
+
+	cfq_update_io_thinktime(cfqd, cic);
+	cfq_update_io_seektime(cfqd, cic, rq);
+	cfq_update_idle_window(cfqd, cfqq, cic);
+
+	cic->last_request_pos = rq->sector + rq->nr_sectors;
+
+	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);
+			blk_start_queueing(cfqd->queue);
+		}
+	} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
+		/*
+		 * 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 or
+		 * this new queue is RT and the current one is BE
+		 */
+		cfq_preempt_queue(cfqd, cfqq);
+		cfq_mark_cfqq_must_dispatch(cfqq);
+		blk_start_queueing(cfqd->queue);
+	}
+}
+
+static void cfq_insert_request(struct request_queue *q, struct request *rq)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+	struct cfq_queue *cfqq = RQ_CFQQ(rq);
+
+	cfq_log_cfqq(cfqd, cfqq, "insert_request");
+	cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc);
+
+	cfq_add_rq_rb(rq);
+
+	list_add_tail(&rq->queuelist, &cfqq->fifo);
+
+	cfq_rq_enqueued(cfqd, cfqq, rq);
+}
+
+/*
+ * Update hw_tag based on peak queue depth over 50 samples under
+ * sufficient load.
+ */
+static void cfq_update_hw_tag(struct cfq_data *cfqd)
+{
+	if (cfqd->rq_in_driver > cfqd->rq_in_driver_peak)
+		cfqd->rq_in_driver_peak = cfqd->rq_in_driver;
+
+	if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
+	    cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
+		return;
+
+	if (cfqd->hw_tag_samples++ < 50)
+		return;
+
+	if (cfqd->rq_in_driver_peak >= CFQ_HW_QUEUE_MIN)
+		cfqd->hw_tag = 1;
+	else
+		cfqd->hw_tag = 0;
+
+	cfqd->hw_tag_samples = 0;
+	cfqd->rq_in_driver_peak = 0;
+}
+
+static void cfq_completed_request(struct request_queue *q, struct request *rq)
+{
+	struct cfq_queue *cfqq = RQ_CFQQ(rq);
+	struct cfq_data *cfqd = cfqq->cfqd;
+	const int sync = rq_is_sync(rq);
+	unsigned long now;
+
+	now = jiffies;
+	cfq_log_cfqq(cfqd, cfqq, "complete");
+
+	cfq_update_hw_tag(cfqd);
+
+	WARN_ON(!cfqd->rq_in_driver);
+	WARN_ON(!cfqq->dispatched);
+	cfqd->rq_in_driver--;
+	cfqq->dispatched--;
+
+	if (cfq_cfqq_sync(cfqq))
+		cfqd->sync_flight--;
+
+	if (!cfq_class_idle(cfqq))
+		cfqd->last_end_request = now;
+
+	if (sync)
+		RQ_CIC(rq)->last_end_request = now;
+
+	/*
+	 * If this is the active queue, check if it needs to be expired,
+	 * or if we want to idle in case it has no pending requests.
+	 */
+	if (cfqd->active_queue == cfqq) {
+		if (cfq_cfqq_slice_new(cfqq)) {
+			cfq_set_prio_slice(cfqd, cfqq);
+			cfq_clear_cfqq_slice_new(cfqq);
+		}
+		if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
+			cfq_slice_expired(cfqd, 1);
+		else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list))
+			cfq_arm_slice_timer(cfqd);
+	}
+
+	if (!cfqd->rq_in_driver)
+		cfq_schedule_dispatch(cfqd);
+}
+
+/*
+ * 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)
+{
+	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;
+	}
+}
+
+static inline int __cfq_may_queue(struct cfq_queue *cfqq)
+{
+	if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) &&
+	    !cfq_cfqq_must_alloc_slice(cfqq)) {
+		cfq_mark_cfqq_must_alloc_slice(cfqq);
+		return ELV_MQUEUE_MUST;
+	}
+
+	return ELV_MQUEUE_MAY;
+}
+
+static int cfq_may_queue(struct request_queue *q, int rw)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+	struct task_struct *tsk = current;
+	struct cfq_io_context *cic;
+	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
+	 */
+	cic = cfq_cic_lookup(cfqd, tsk->io_context);
+	if (!cic)
+		return ELV_MQUEUE_MAY;
+
+	cfqq = cic_to_cfqq(cic, rw & REQ_RW_SYNC);
+	if (cfqq) {
+		cfq_init_prio_data(cfqq, cic->ioc);
+		cfq_prio_boost(cfqq);
+
+		return __cfq_may_queue(cfqq);
+	}
+
+	return ELV_MQUEUE_MAY;
+}
+
+/*
+ * queue lock held here
+ */
+static void cfq_put_request(struct request *rq)
+{
+	struct cfq_queue *cfqq = RQ_CFQQ(rq);
+
+	if (cfqq) {
+		const int rw = rq_data_dir(rq);
+
+		BUG_ON(!cfqq->allocated[rw]);
+		cfqq->allocated[rw]--;
+
+		put_io_context(RQ_CIC(rq)->ioc);
+
+		rq->elevator_private = NULL;
+		rq->elevator_private2 = NULL;
+
+		cfq_put_queue(cfqq);
+	}
+}
+
+/*
+ * Allocate cfq data structures associated with this request.
+ */
+static int
+cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+	struct cfq_io_context *cic;
+	const int rw = rq_data_dir(rq);
+	const int is_sync = rq_is_sync(rq);
+	struct cfq_queue *cfqq;
+	unsigned long flags;
+
+	might_sleep_if(gfp_mask & __GFP_WAIT);
+
+	cic = cfq_get_io_context(cfqd, gfp_mask);
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	if (!cic)
+		goto queue_fail;
+
+	cfqq = cic_to_cfqq(cic, is_sync);
+	if (!cfqq) {
+		cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask);
+
+		if (!cfqq)
+			goto queue_fail;
+
+		cic_set_cfqq(cic, cfqq, is_sync);
+	}
+
+	cfqq->allocated[rw]++;
+	cfq_clear_cfqq_must_alloc(cfqq);
+	atomic_inc(&cfqq->ref);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	rq->elevator_private = cic;
+	rq->elevator_private2 = cfqq;
+	return 0;
+
+queue_fail:
+	if (cic)
+		put_io_context(cic->ioc);
+
+	cfq_schedule_dispatch(cfqd);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+	cfq_log(cfqd, "set_request fail");
+	return 1;
+}
+
+static void cfq_kick_queue(struct work_struct *work)
+{
+	struct cfq_data *cfqd =
+		container_of(work, struct cfq_data, unplug_work);
+	struct request_queue *q = cfqd->queue;
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	blk_start_queueing(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;
+	int timed_out = 1;
+
+	cfq_log(cfqd, "idle timer fired");
+
+	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+
+	cfqq = cfqd->active_queue;
+	if (cfqq) {
+		timed_out = 0;
+
+		/*
+		 * expired
+		 */
+		if (cfq_slice_used(cfqq))
+			goto expire;
+
+		/*
+		 * only expire and reinvoke request handler, if there are
+		 * other queues with pending requests
+		 */
+		if (!cfqd->busy_queues)
+			goto out_cont;
+
+		/*
+		 * not expired and it has a request pending, let it dispatch
+		 */
+		if (!RB_EMPTY_ROOT(&cfqq->sort_list)) {
+			cfq_mark_cfqq_must_dispatch(cfqq);
+			goto out_kick;
+		}
+	}
+expire:
+	cfq_slice_expired(cfqd, timed_out);
+out_kick:
+	cfq_schedule_dispatch(cfqd);
+out_cont:
+	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);
+	cancel_work_sync(&cfqd->unplug_work);
+}
+
+static void cfq_put_async_queues(struct cfq_data *cfqd)
+{
+	int i;
+
+	for (i = 0; i < IOPRIO_BE_NR; i++) {
+		if (cfqd->async_cfqq[0][i])
+			cfq_put_queue(cfqd->async_cfqq[0][i]);
+		if (cfqd->async_cfqq[1][i])
+			cfq_put_queue(cfqd->async_cfqq[1][i]);
+	}
+
+	if (cfqd->async_idle_cfqq)
+		cfq_put_queue(cfqd->async_idle_cfqq);
+}
+
+static void cfq_exit_queue(struct elevator_queue *e)
+{
+	struct cfq_data *cfqd = e->elevator_data;
+	struct request_queue *q = cfqd->queue;
+
+	cfq_shutdown_timer_wq(cfqd);
+
+	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);
+
+		__cfq_exit_single_io_context(cfqd, cic);
+	}
+
+	cfq_put_async_queues(cfqd);
+
+	spin_unlock_irq(q->queue_lock);
+
+	cfq_shutdown_timer_wq(cfqd);
+
+	kfree(cfqd);
+}
+
+static void *cfq_init_queue(struct request_queue *q)
+{
+	struct cfq_data *cfqd;
+
+	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
+	if (!cfqd)
+		return NULL;
+
+	cfqd->service_tree = CFQ_RB_ROOT;
+	INIT_LIST_HEAD(&cfqd->cic_list);
+
+	cfqd->queue = q;
+
+	init_timer(&cfqd->idle_slice_timer);
+	cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
+	cfqd->idle_slice_timer.data = (unsigned long) cfqd;
+
+	INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);
+
+	cfqd->last_end_request = jiffies;
+	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->hw_tag = 1;
+
+	return cfqd;
+}
+
+static void cfq_slab_kill(void)
+{
+	/*
+	 * Caller already ensured that pending RCU callbacks are completed,
+	 * so we should have no busy allocations at this point.
+	 */
+	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)
+{
+	cfq_pool = KMEM_CACHE(cfq_queue, 0);
+	if (!cfq_pool)
+		goto fail;
+
+	cfq_ioc_pool = KMEM_CACHE(cfq_io_context, 0);
+	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(struct elevator_queue *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_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_seek_max_show, cfqd->cfq_back_max, 0);
+SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0);
+SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
+SHOW_FUNCTION(cfq_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);
+#undef SHOW_FUNCTION
+
+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
+static ssize_t __FUNC(struct elevator_queue *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_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_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
+STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1,
+		UINT_MAX, 0);
+STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
+STORE_FUNCTION(cfq_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);
+#undef STORE_FUNCTION
+
+#define CFQ_ATTR(name) \
+	__ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store)
+
+static struct elv_fs_entry cfq_attrs[] = {
+	CFQ_ATTR(quantum),
+	CFQ_ATTR(fifo_expire_sync),
+	CFQ_ATTR(fifo_expire_async),
+	CFQ_ATTR(back_seek_max),
+	CFQ_ATTR(back_seek_penalty),
+	CFQ_ATTR(slice_sync),
+	CFQ_ATTR(slice_async),
+	CFQ_ATTR(slice_async_rq),
+	CFQ_ATTR(slice_idle),
+	__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_allow_merge_fn =	cfq_allow_merge,
+		.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 =	elv_rb_former_request,
+		.elevator_latter_req_fn =	elv_rb_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_free_io_context,
+	},
+	.elevator_attrs =	cfq_attrs,
+	.elevator_name =	"cfq",
+	.elevator_owner =	THIS_MODULE,
+};
+
+static int __init cfq_init(void)
+{
+	/*
+	 * 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;
+
+	elv_register(&iosched_cfq);
+
+	return 0;
+}
+
+static void __exit cfq_exit(void)
+{
+	DECLARE_COMPLETION_ONSTACK(all_gone);
+	elv_unregister(&iosched_cfq);
+	ioc_gone = &all_gone;
+	/* ioc_gone's update must be visible before reading ioc_count */
+	smp_wmb();
+
+	/*
+	 * this also protects us from entering cfq_slab_kill() with
+	 * pending RCU callbacks
+	 */
+	if (elv_ioc_count_read(ioc_count))
+		wait_for_completion(&all_gone);
+	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");
diff --git a/libdde-linux26/contrib/block/deadline-iosched.c b/libdde-linux26/contrib/block/deadline-iosched.c
new file mode 100644
index 00000000..9bb6f050
--- /dev/null
+++ b/libdde-linux26/contrib/block/deadline-iosched.c
@@ -0,0 +1,478 @@
+/*
+ *  Deadline i/o scheduler.
+ *
+ *  Copyright (C) 2002 Jens Axboe <axboe@kernel.dk>
+ */
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+#include <linux/elevator.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <ddekit/timer.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. */
+
+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 request *next_rq[2];
+	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;
+};
+
+static void deadline_move_request(struct deadline_data *, struct request *);
+
+static inline struct rb_root *
+deadline_rb_root(struct deadline_data *dd, struct request *rq)
+{
+	return &dd->sort_list[rq_data_dir(rq)];
+}
+
+/*
+ * get the request after `rq' in sector-sorted order
+ */
+static inline struct request *
+deadline_latter_request(struct request *rq)
+{
+	struct rb_node *node = rb_next(&rq->rb_node);
+
+	if (node)
+		return rb_entry_rq(node);
+
+	return NULL;
+}
+
+static void
+deadline_add_rq_rb(struct deadline_data *dd, struct request *rq)
+{
+	struct rb_root *root = deadline_rb_root(dd, rq);
+	struct request *__alias;
+
+	while (unlikely(__alias = elv_rb_add(root, rq)))
+		deadline_move_request(dd, __alias);
+}
+
+static inline void
+deadline_del_rq_rb(struct deadline_data *dd, struct request *rq)
+{
+	const int data_dir = rq_data_dir(rq);
+
+	if (dd->next_rq[data_dir] == rq)
+		dd->next_rq[data_dir] = deadline_latter_request(rq);
+
+	elv_rb_del(deadline_rb_root(dd, rq), rq);
+}
+
+/*
+ * add rq to rbtree and fifo
+ */
+static void
+deadline_add_request(struct request_queue *q, struct request *rq)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+	const int data_dir = rq_data_dir(rq);
+
+	deadline_add_rq_rb(dd, rq);
+
+	/*
+	 * set expire time and add to fifo list
+	 */
+	rq_set_fifo_time(rq, jiffies + dd->fifo_expire[data_dir]);
+	list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]);
+}
+
+/*
+ * remove rq from rbtree and fifo.
+ */
+static void deadline_remove_request(struct request_queue *q, struct request *rq)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	rq_fifo_clear(rq);
+	deadline_del_rq_rb(dd, rq);
+}
+
+static int
+deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+	struct request *__rq;
+	int ret;
+
+	/*
+	 * check for front merge
+	 */
+	if (dd->front_merges) {
+		sector_t sector = bio->bi_sector + bio_sectors(bio);
+
+		__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
+		if (__rq) {
+			BUG_ON(sector != __rq->sector);
+
+			if (elv_rq_merge_ok(__rq, bio)) {
+				ret = ELEVATOR_FRONT_MERGE;
+				goto out;
+			}
+		}
+	}
+
+	return ELEVATOR_NO_MERGE;
+out:
+	*req = __rq;
+	return ret;
+}
+
+static void deadline_merged_request(struct request_queue *q,
+				    struct request *req, int type)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	/*
+	 * if the merge was a front merge, we need to reposition request
+	 */
+	if (type == ELEVATOR_FRONT_MERGE) {
+		elv_rb_del(deadline_rb_root(dd, req), req);
+		deadline_add_rq_rb(dd, req);
+	}
+}
+
+static void
+deadline_merged_requests(struct request_queue *q, struct request *req,
+			 struct request *next)
+{
+	/*
+	 * if next expires before rq, assign its expire time to rq
+	 * and move into next position (next will be deleted) in fifo
+	 */
+	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
+		if (time_before(rq_fifo_time(next), rq_fifo_time(req))) {
+			list_move(&req->queuelist, &next->queuelist);
+			rq_set_fifo_time(req, rq_fifo_time(next));
+		}
+	}
+
+	/*
+	 * kill knowledge of next, this one is a goner
+	 */
+	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 request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	deadline_remove_request(q, rq);
+	elv_dispatch_add_tail(q, rq);
+}
+
+/*
+ * move an entry to dispatch queue
+ */
+static void
+deadline_move_request(struct deadline_data *dd, struct request *rq)
+{
+	const int data_dir = rq_data_dir(rq);
+
+	dd->next_rq[READ] = NULL;
+	dd->next_rq[WRITE] = NULL;
+	dd->next_rq[data_dir] = deadline_latter_request(rq);
+
+	dd->last_sector = rq_end_sector(rq);
+
+	/*
+	 * take it off the sort and fifo list, move
+	 * to dispatch queue
+	 */
+	deadline_move_to_dispatch(dd, rq);
+}
+
+/*
+ * deadline_check_fifo returns 0 if there are no expired requests 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 request *rq = rq_entry_fifo(dd->fifo_list[ddir].next);
+
+	/*
+	 * rq is expired!
+	 */
+	if (time_after(jiffies, rq_fifo_time(rq)))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * deadline_dispatch_requests selects the best request according to
+ * read/write expire, fifo_batch, etc
+ */
+static int deadline_dispatch_requests(struct request_queue *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 request *rq;
+	int data_dir;
+
+	/*
+	 * batches are currently reads XOR writes
+	 */
+	if (dd->next_rq[WRITE])
+		rq = dd->next_rq[WRITE];
+	else
+		rq = dd->next_rq[READ];
+
+	if (rq && dd->batching < dd->fifo_batch)
+		/* we have a next request 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_ROOT(&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_ROOT(&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) || !dd->next_rq[data_dir]) {
+		/*
+		 * A deadline has expired, the last request was in the other
+		 * direction, or we have run out of higher-sectored requests.
+		 * Start again from the request with the earliest expiry time.
+		 */
+		rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+	} else {
+		/*
+		 * The last req was the same dir and we have a next request in
+		 * sort order. No expired requests so continue on from here.
+		 */
+		rq = dd->next_rq[data_dir];
+	}
+
+	dd->batching = 0;
+
+dispatch_request:
+	/*
+	 * rq is the selected appropriate request.
+	 */
+	dd->batching++;
+	deadline_move_request(dd, rq);
+
+	return 1;
+}
+
+static int deadline_queue_empty(struct request_queue *q)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	return list_empty(&dd->fifo_list[WRITE])
+		&& list_empty(&dd->fifo_list[READ]);
+}
+
+static void deadline_exit_queue(struct elevator_queue *e)
+{
+	struct deadline_data *dd = e->elevator_data;
+
+	BUG_ON(!list_empty(&dd->fifo_list[READ]));
+	BUG_ON(!list_empty(&dd->fifo_list[WRITE]));
+
+	kfree(dd);
+}
+
+/*
+ * initialize elevator private data (deadline_data).
+ */
+static void *deadline_init_queue(struct request_queue *q)
+{
+	struct deadline_data *dd;
+
+	dd = kmalloc_node(sizeof(*dd), GFP_KERNEL | __GFP_ZERO, q->node);
+	if (!dd)
+		return NULL;
+
+	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;
+	return dd;
+}
+
+/*
+ * 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(struct elevator_queue *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_read_expire_show, dd->fifo_expire[READ], 1);
+SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1);
+SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0);
+SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 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(struct elevator_queue *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_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0);
+STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0);
+STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
+#undef STORE_FUNCTION
+
+#define DD_ATTR(name) \
+	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
+				      deadline_##name##_store)
+
+static struct elv_fs_entry deadline_attrs[] = {
+	DD_ATTR(read_expire),
+	DD_ATTR(write_expire),
+	DD_ATTR(writes_starved),
+	DD_ATTR(front_merges),
+	DD_ATTR(fifo_batch),
+	__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 =	elv_rb_former_request,
+		.elevator_latter_req_fn =	elv_rb_latter_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)
+{
+	elv_register(&iosched_deadline);
+
+	return 0;
+}
+
+static void __exit deadline_exit(void)
+{
+	elv_unregister(&iosched_deadline);
+}
+
+module_init(deadline_init);
+module_exit(deadline_exit);
+
+MODULE_AUTHOR("Jens Axboe");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("deadline IO scheduler");
diff --git a/libdde-linux26/contrib/block/elevator.c b/libdde-linux26/contrib/block/elevator.c
new file mode 100644
index 00000000..0287fafd
--- /dev/null
+++ b/libdde-linux26/contrib/block/elevator.c
@@ -0,0 +1,1231 @@
+/*
+ *  Block device elevator/IO-scheduler.
+ *
+ *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
+ *
+ * 30042000 Jens Axboe <axboe@kernel.dk> :
+ *
+ * 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/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/delay.h>
+#include <linux/blktrace_api.h>
+#include <trace/block.h>
+#include <linux/hash.h>
+#include <linux/uaccess.h>
+
+#include "blk.h"
+#include "local.h"
+
+static DEFINE_SPINLOCK(elv_list_lock);
+static LIST_HEAD(elv_list);
+
+DEFINE_TRACE(block_rq_abort);
+
+/*
+ * Merge hash stuff.
+ */
+static const int elv_hash_shift = 6;
+#define ELV_HASH_BLOCK(sec)	((sec) >> 3)
+#define ELV_HASH_FN(sec)	\
+		(hash_long(ELV_HASH_BLOCK((sec)), elv_hash_shift))
+#define ELV_HASH_ENTRIES	(1 << elv_hash_shift)
+#define rq_hash_key(rq)		((rq)->sector + (rq)->nr_sectors)
+#define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
+
+DEFINE_TRACE(block_rq_insert);
+DEFINE_TRACE(block_rq_issue);
+
+/*
+ * Query io scheduler to see if the current process issuing bio may be
+ * merged with rq.
+ */
+static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_allow_merge_fn)
+		return e->ops->elevator_allow_merge_fn(q, rq, bio);
+
+	return 1;
+}
+
+/*
+ * can we safely merge with this request?
+ */
+int elv_rq_merge_ok(struct request *rq, struct bio *bio)
+{
+	if (!rq_mergeable(rq))
+		return 0;
+
+	/*
+	 * Don't merge file system requests and discard requests
+	 */
+	if (bio_discard(bio) != bio_discard(rq->bio))
+		return 0;
+
+	/*
+	 * different data direction or already started, don't merge
+	 */
+	if (bio_data_dir(bio) != rq_data_dir(rq))
+		return 0;
+
+	/*
+	 * must be same device and not a special request
+	 */
+	if (rq->rq_disk != bio->bi_bdev->bd_disk || rq->special)
+		return 0;
+
+	/*
+	 * only merge integrity protected bio into ditto rq
+	 */
+	if (bio_integrity(bio) != blk_integrity_rq(rq))
+		return 0;
+
+	if (!elv_iosched_allow_merge(rq, bio))
+		return 0;
+
+	return 1;
+}
+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;
+
+	list_for_each_entry(e, &elv_list, list) {
+		if (!strcmp(e->elevator_name, name))
+			return e;
+	}
+
+	return NULL;
+}
+
+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(&elv_list_lock);
+
+	e = elevator_find(name);
+	if (!e) {
+		char elv[ELV_NAME_MAX + strlen("-iosched")];
+
+		spin_unlock(&elv_list_lock);
+
+		if (!strcmp(name, "anticipatory"))
+			sprintf(elv, "as-iosched");
+		else
+			sprintf(elv, "%s-iosched", name);
+
+		request_module("%s", elv);
+		spin_lock(&elv_list_lock);
+		e = elevator_find(name);
+	}
+
+	if (e && !try_module_get(e->elevator_owner))
+		e = NULL;
+
+	spin_unlock(&elv_list_lock);
+
+	return e;
+}
+
+static void *elevator_init_queue(struct request_queue *q,
+				 struct elevator_queue *eq)
+{
+	return eq->ops->elevator_init_fn(q);
+}
+
+static void elevator_attach(struct request_queue *q, struct elevator_queue *eq,
+			   void *data)
+{
+	q->elevator = eq;
+	eq->elevator_data = data;
+}
+
+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 1;
+}
+
+__setup("elevator=", elevator_setup);
+
+static struct kobj_type elv_ktype;
+
+static struct elevator_queue *elevator_alloc(struct request_queue *q,
+				  struct elevator_type *e)
+{
+	struct elevator_queue *eq;
+	int i;
+
+	eq = kmalloc_node(sizeof(*eq), GFP_KERNEL | __GFP_ZERO, q->node);
+	if (unlikely(!eq))
+		goto err;
+
+	eq->ops = &e->ops;
+	eq->elevator_type = e;
+	kobject_init(&eq->kobj, &elv_ktype);
+	mutex_init(&eq->sysfs_lock);
+
+	eq->hash = kmalloc_node(sizeof(struct hlist_head) * ELV_HASH_ENTRIES,
+					GFP_KERNEL, q->node);
+	if (!eq->hash)
+		goto err;
+
+	for (i = 0; i < ELV_HASH_ENTRIES; i++)
+		INIT_HLIST_HEAD(&eq->hash[i]);
+
+	return eq;
+err:
+	kfree(eq);
+	elevator_put(e);
+	return NULL;
+}
+
+static void elevator_release(struct kobject *kobj)
+{
+	struct elevator_queue *e;
+
+	e = container_of(kobj, struct elevator_queue, kobj);
+	elevator_put(e->elevator_type);
+	kfree(e->hash);
+	kfree(e);
+}
+
+int elevator_init(struct request_queue *q, char *name)
+{
+	struct elevator_type *e = NULL;
+	struct elevator_queue *eq;
+	int ret = 0;
+	void *data;
+
+	INIT_LIST_HEAD(&q->queue_head);
+	q->last_merge = NULL;
+	q->end_sector = 0;
+	q->boundary_rq = NULL;
+
+	if (name) {
+		e = elevator_get(name);
+		if (!e)
+			return -EINVAL;
+	}
+
+	if (!e && *chosen_elevator) {
+		e = elevator_get(chosen_elevator);
+		if (!e)
+			printk(KERN_ERR "I/O scheduler %s not found\n",
+							chosen_elevator);
+	}
+
+	if (!e) {
+		e = elevator_get(CONFIG_DEFAULT_IOSCHED);
+		if (!e) {
+			printk(KERN_ERR
+				"Default I/O scheduler not found. " \
+				"Using noop.\n");
+			e = elevator_get("noop");
+		}
+	}
+
+	eq = elevator_alloc(q, e);
+	if (!eq)
+		return -ENOMEM;
+
+	data = elevator_init_queue(q, eq);
+	if (!data) {
+		kobject_put(&eq->kobj);
+		return -ENOMEM;
+	}
+
+	elevator_attach(q, eq, data);
+	return ret;
+}
+EXPORT_SYMBOL(elevator_init);
+
+void elevator_exit(struct elevator_queue *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);
+}
+EXPORT_SYMBOL(elevator_exit);
+
+static void elv_activate_rq(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_activate_req_fn)
+		e->ops->elevator_activate_req_fn(q, rq);
+}
+
+static void elv_deactivate_rq(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_deactivate_req_fn)
+		e->ops->elevator_deactivate_req_fn(q, rq);
+}
+
+static inline void __elv_rqhash_del(struct request *rq)
+{
+	hlist_del_init(&rq->hash);
+}
+
+static void elv_rqhash_del(struct request_queue *q, struct request *rq)
+{
+	if (ELV_ON_HASH(rq))
+		__elv_rqhash_del(rq);
+}
+
+static void elv_rqhash_add(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	BUG_ON(ELV_ON_HASH(rq));
+	hlist_add_head(&rq->hash, &e->hash[ELV_HASH_FN(rq_hash_key(rq))]);
+}
+
+static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
+{
+	__elv_rqhash_del(rq);
+	elv_rqhash_add(q, rq);
+}
+
+static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
+{
+	struct elevator_queue *e = q->elevator;
+	struct hlist_head *hash_list = &e->hash[ELV_HASH_FN(offset)];
+	struct hlist_node *entry, *next;
+	struct request *rq;
+
+	hlist_for_each_entry_safe(rq, entry, next, hash_list, hash) {
+		BUG_ON(!ELV_ON_HASH(rq));
+
+		if (unlikely(!rq_mergeable(rq))) {
+			__elv_rqhash_del(rq);
+			continue;
+		}
+
+		if (rq_hash_key(rq) == offset)
+			return rq;
+	}
+
+	return NULL;
+}
+
+/*
+ * RB-tree support functions for inserting/lookup/removal of requests
+ * in a sorted RB tree.
+ */
+struct request *elv_rb_add(struct rb_root *root, struct request *rq)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct request *__rq;
+
+	while (*p) {
+		parent = *p;
+		__rq = rb_entry(parent, struct request, rb_node);
+
+		if (rq->sector < __rq->sector)
+			p = &(*p)->rb_left;
+		else if (rq->sector > __rq->sector)
+			p = &(*p)->rb_right;
+		else
+			return __rq;
+	}
+
+	rb_link_node(&rq->rb_node, parent, p);
+	rb_insert_color(&rq->rb_node, root);
+	return NULL;
+}
+EXPORT_SYMBOL(elv_rb_add);
+
+void elv_rb_del(struct rb_root *root, struct request *rq)
+{
+	BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
+	rb_erase(&rq->rb_node, root);
+	RB_CLEAR_NODE(&rq->rb_node);
+}
+EXPORT_SYMBOL(elv_rb_del);
+
+struct request *elv_rb_find(struct rb_root *root, sector_t sector)
+{
+	struct rb_node *n = root->rb_node;
+	struct request *rq;
+
+	while (n) {
+		rq = rb_entry(n, struct request, rb_node);
+
+		if (sector < rq->sector)
+			n = n->rb_left;
+		else if (sector > rq->sector)
+			n = n->rb_right;
+		else
+			return rq;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(elv_rb_find);
+
+/*
+ * Insert rq into dispatch queue of q.  Queue lock must be held on
+ * entry.  rq is sort instead into the dispatch queue. To be used by
+ * specific elevators.
+ */
+void elv_dispatch_sort(struct request_queue *q, struct request *rq)
+{
+	sector_t boundary;
+	struct list_head *entry;
+	int stop_flags;
+
+	if (q->last_merge == rq)
+		q->last_merge = NULL;
+
+	elv_rqhash_del(q, rq);
+
+	q->nr_sorted--;
+
+	boundary = q->end_sector;
+	stop_flags = REQ_SOFTBARRIER | REQ_HARDBARRIER | REQ_STARTED;
+	list_for_each_prev(entry, &q->queue_head) {
+		struct request *pos = list_entry_rq(entry);
+
+		if (blk_discard_rq(rq) != blk_discard_rq(pos))
+			break;
+		if (rq_data_dir(rq) != rq_data_dir(pos))
+			break;
+		if (pos->cmd_flags & stop_flags)
+			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);
+}
+EXPORT_SYMBOL(elv_dispatch_sort);
+
+/*
+ * Insert rq into dispatch queue of q.  Queue lock must be held on
+ * entry.  rq is added to the back of the dispatch queue. To be used by
+ * specific elevators.
+ */
+void elv_dispatch_add_tail(struct request_queue *q, struct request *rq)
+{
+	if (q->last_merge == rq)
+		q->last_merge = NULL;
+
+	elv_rqhash_del(q, rq);
+
+	q->nr_sorted--;
+
+	q->end_sector = rq_end_sector(rq);
+	q->boundary_rq = rq;
+	list_add_tail(&rq->queuelist, &q->queue_head);
+}
+EXPORT_SYMBOL(elv_dispatch_add_tail);
+
+int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+	struct request *__rq;
+	int ret;
+
+	/*
+	 * First try one-hit cache.
+	 */
+	if (q->last_merge) {
+		ret = elv_try_merge(q->last_merge, bio);
+		if (ret != ELEVATOR_NO_MERGE) {
+			*req = q->last_merge;
+			return ret;
+		}
+	}
+
+	if (blk_queue_nomerges(q))
+		return ELEVATOR_NO_MERGE;
+
+	/*
+	 * See if our hash lookup can find a potential backmerge.
+	 */
+	__rq = elv_rqhash_find(q, bio->bi_sector);
+	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+		*req = __rq;
+		return ELEVATOR_BACK_MERGE;
+	}
+
+	if (e->ops->elevator_merge_fn)
+		return e->ops->elevator_merge_fn(q, req, bio);
+
+	return ELEVATOR_NO_MERGE;
+}
+
+void elv_merged_request(struct request_queue *q, struct request *rq, int type)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_merged_fn)
+		e->ops->elevator_merged_fn(q, rq, type);
+
+	if (type == ELEVATOR_BACK_MERGE)
+		elv_rqhash_reposition(q, rq);
+
+	q->last_merge = rq;
+}
+
+void elv_merge_requests(struct request_queue *q, struct request *rq,
+			     struct request *next)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_merge_req_fn)
+		e->ops->elevator_merge_req_fn(q, rq, next);
+
+	elv_rqhash_reposition(q, rq);
+	elv_rqhash_del(q, next);
+
+	q->nr_sorted--;
+	q->last_merge = rq;
+}
+
+void elv_requeue_request(struct request_queue *q, struct request *rq)
+{
+	/*
+	 * 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))
+			elv_deactivate_rq(q, rq);
+	}
+
+	rq->cmd_flags &= ~REQ_STARTED;
+
+	elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE);
+}
+
+static void elv_drain_elevator(struct request_queue *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(struct request_queue *q, struct request *rq, int where)
+{
+	struct list_head *pos;
+	unsigned ordseq;
+	int unplug_it = 1;
+
+	trace_block_rq_insert(q, rq);
+
+	rq->q = q;
+
+	switch (where) {
+	case ELEVATOR_INSERT_FRONT:
+		rq->cmd_flags |= REQ_SOFTBARRIER;
+
+		list_add(&rq->queuelist, &q->queue_head);
+		break;
+
+	case ELEVATOR_INSERT_BACK:
+		rq->cmd_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);
+		blk_start_queueing(q);
+		break;
+
+	case ELEVATOR_INSERT_SORT:
+		BUG_ON(!blk_fs_request(rq) && !blk_discard_rq(rq));
+		rq->cmd_flags |= REQ_SORTED;
+		q->nr_sorted++;
+		if (rq_mergeable(rq)) {
+			elv_rqhash_add(q, rq);
+			if (!q->last_merge)
+				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->cmd_flags |= REQ_SOFTBARRIER;
+
+		/*
+		 * Most requeues happen because of a busy condition,
+		 * don't force unplug of the queue for that case.
+		 */
+		unplug_it = 0;
+
+		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",
+		       __func__, where);
+		BUG();
+	}
+
+	if (unplug_it && 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(struct request_queue *q, struct request *rq, int where,
+		       int plug)
+{
+	if (q->ordcolor)
+		rq->cmd_flags |= REQ_ORDERED_COLOR;
+
+	if (rq->cmd_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) || blk_discard_rq(rq)) {
+			q->end_sector = rq_end_sector(rq);
+			q->boundary_rq = rq;
+		}
+	} else if (!(rq->cmd_flags & REQ_ELVPRIV) &&
+		    where == ELEVATOR_INSERT_SORT)
+		where = ELEVATOR_INSERT_BACK;
+
+	if (plug)
+		blk_plug_device(q);
+
+	elv_insert(q, rq, where);
+}
+EXPORT_SYMBOL(__elv_add_request);
+
+void elv_add_request(struct request_queue *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);
+}
+EXPORT_SYMBOL(elv_add_request);
+
+static inline struct request *__elv_next_request(struct request_queue *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(struct request_queue *q)
+{
+	struct request *rq;
+	int ret;
+
+	while ((rq = __elv_next_request(q)) != NULL) {
+		if (!(rq->cmd_flags & REQ_STARTED)) {
+			/*
+			 * This is the first time the device driver
+			 * sees this request (possibly after
+			 * requeueing).  Notify IO scheduler.
+			 */
+			if (blk_sorted_rq(rq))
+				elv_activate_rq(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->cmd_flags |= REQ_STARTED;
+			trace_block_rq_issue(q, rq);
+		}
+
+		if (!q->boundary_rq || q->boundary_rq == rq) {
+			q->end_sector = rq_end_sector(rq);
+			q->boundary_rq = NULL;
+		}
+
+		if (rq->cmd_flags & REQ_DONTPREP)
+			break;
+
+		if (q->dma_drain_size && rq->data_len) {
+			/*
+			 * make sure space for the drain appears we
+			 * know we can do this because max_hw_segments
+			 * has been adjusted to be one fewer than the
+			 * device can handle
+			 */
+			rq->nr_phys_segments++;
+		}
+
+		if (!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.
+			 */
+			if (q->dma_drain_size && rq->data_len &&
+			    !(rq->cmd_flags & REQ_DONTPREP)) {
+				/*
+				 * remove the space for the drain we added
+				 * so that we don't add it again
+				 */
+				--rq->nr_phys_segments;
+			}
+
+			rq = NULL;
+			break;
+		} else if (ret == BLKPREP_KILL) {
+			rq->cmd_flags |= REQ_QUIET;
+			__blk_end_request(rq, -EIO, blk_rq_bytes(rq));
+		} else {
+			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
+			break;
+		}
+	}
+
+	return rq;
+}
+EXPORT_SYMBOL(elv_next_request);
+
+void elv_dequeue_request(struct request_queue *q, struct request *rq)
+{
+	BUG_ON(list_empty(&rq->queuelist));
+	BUG_ON(ELV_ON_HASH(rq));
+
+	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(struct request_queue *q)
+{
+	struct elevator_queue *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;
+}
+EXPORT_SYMBOL(elv_queue_empty);
+
+struct request *elv_latter_request(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *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(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *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(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_set_req_fn)
+		return e->ops->elevator_set_req_fn(q, rq, gfp_mask);
+
+	rq->elevator_private = NULL;
+	return 0;
+}
+
+void elv_put_request(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_put_req_fn)
+		e->ops->elevator_put_req_fn(rq);
+}
+
+int elv_may_queue(struct request_queue *q, int rw)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_may_queue_fn)
+		return e->ops->elevator_may_queue_fn(q, rw);
+
+	return ELV_MQUEUE_MAY;
+}
+
+void elv_abort_queue(struct request_queue *q)
+{
+	struct request *rq;
+
+	while (!list_empty(&q->queue_head)) {
+		rq = list_entry_rq(q->queue_head.next);
+		rq->cmd_flags |= REQ_QUIET;
+		trace_block_rq_abort(q, rq);
+		__blk_end_request(rq, -EIO, blk_rq_bytes(rq));
+	}
+}
+EXPORT_SYMBOL(elv_abort_queue);
+
+void elv_completed_request(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *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 *next = NULL;
+
+		if (!list_empty(&q->queue_head))
+			next = list_entry_rq(q->queue_head.next);
+
+		if (!q->in_flight &&
+		    blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
+		    (!next || blk_ordered_req_seq(next) > QUEUE_ORDSEQ_DRAIN)) {
+			blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
+			blk_start_queueing(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)
+{
+	struct elv_fs_entry *entry = to_elv(attr);
+	struct elevator_queue *e;
+	ssize_t error;
+
+	if (!entry->show)
+		return -EIO;
+
+	e = container_of(kobj, struct elevator_queue, kobj);
+	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)
+{
+	struct elv_fs_entry *entry = to_elv(attr);
+	struct elevator_queue *e;
+	ssize_t error;
+
+	if (!entry->store)
+		return -EIO;
+
+	e = container_of(kobj, struct elevator_queue, kobj);
+	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)
+{
+	struct elevator_queue *e = q->elevator;
+	int error;
+
+	error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
+	if (!error) {
+		struct elv_fs_entry *attr = e->elevator_type->elevator_attrs;
+		if (attr) {
+			while (attr->attr.name) {
+				if (sysfs_create_file(&e->kobj, &attr->attr))
+					break;
+				attr++;
+			}
+		}
+		kobject_uevent(&e->kobj, KOBJ_ADD);
+	}
+	return error;
+}
+
+static void __elv_unregister_queue(struct elevator_queue *e)
+{
+	kobject_uevent(&e->kobj, KOBJ_REMOVE);
+	kobject_del(&e->kobj);
+}
+
+void elv_unregister_queue(struct request_queue *q)
+{
+	if (q)
+		__elv_unregister_queue(q->elevator);
+}
+
+void elv_register(struct elevator_type *e)
+{
+	char *def = "";
+
+	spin_lock(&elv_list_lock);
+	BUG_ON(elevator_find(e->elevator_name));
+	list_add_tail(&e->list, &elv_list);
+	spin_unlock(&elv_list_lock);
+
+	if (!strcmp(e->elevator_name, chosen_elevator) ||
+			(!*chosen_elevator &&
+			 !strcmp(e->elevator_name, CONFIG_DEFAULT_IOSCHED)))
+				def = " (default)";
+
+	printk(KERN_INFO "io scheduler %s registered%s\n", e->elevator_name,
+								def);
+}
+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);
+			if (p->io_context)
+				e->ops.trim(p->io_context);
+			task_unlock(p);
+		} while_each_thread(g, p);
+		read_unlock(&tasklist_lock);
+	}
+
+	spin_lock(&elv_list_lock);
+	list_del_init(&e->list);
+	spin_unlock(&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(struct request_queue *q, struct elevator_type *new_e)
+{
+	struct elevator_queue *old_elevator, *e;
+	void *data;
+
+	/*
+	 * Allocate new elevator
+	 */
+	e = elevator_alloc(q, new_e);
+	if (!e)
+		return 0;
+
+	data = elevator_init_queue(q, e);
+	if (!data) {
+		kobject_put(&e->kobj);
+		return 0;
+	}
+
+	/*
+	 * Turn on BYPASS and drain all requests w/ elevator private data
+	 */
+	spin_lock_irq(q->queue_lock);
+
+	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
+
+	elv_drain_elevator(q);
+
+	while (q->rq.elvpriv) {
+		blk_start_queueing(q);
+		spin_unlock_irq(q->queue_lock);
+		msleep(10);
+		spin_lock_irq(q->queue_lock);
+		elv_drain_elevator(q);
+	}
+
+	/*
+	 * Remember old elevator.
+	 */
+	old_elevator = q->elevator;
+
+	/*
+	 * attach and start new elevator
+	 */
+	elevator_attach(q, e, data);
+
+	spin_unlock_irq(q->queue_lock);
+
+	__elv_unregister_queue(old_elevator);
+
+	if (elv_register_queue(q))
+		goto fail_register;
+
+	/*
+	 * finally exit old elevator and turn off BYPASS.
+	 */
+	elevator_exit(old_elevator);
+	spin_lock_irq(q->queue_lock);
+	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+	spin_unlock_irq(q->queue_lock);
+
+	blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name);
+
+	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);
+	q->elevator = old_elevator;
+	elv_register_queue(q);
+
+	spin_lock_irq(q->queue_lock);
+	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return 0;
+}
+
+ssize_t elv_iosched_store(struct request_queue *q, const char *name,
+			  size_t count)
+{
+	char elevator_name[ELV_NAME_MAX];
+	struct elevator_type *e;
+
+	strlcpy(elevator_name, name, sizeof(elevator_name));
+	strstrip(elevator_name);
+
+	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(struct request_queue *q, char *name)
+{
+	struct elevator_queue *e = q->elevator;
+	struct elevator_type *elv = e->elevator_type;
+	struct elevator_type *__e;
+	int len = 0;
+
+	spin_lock(&elv_list_lock);
+	list_for_each_entry(__e, &elv_list, 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(&elv_list_lock);
+
+	len += sprintf(len+name, "\n");
+	return len;
+}
+
+struct request *elv_rb_former_request(struct request_queue *q,
+				      struct request *rq)
+{
+	struct rb_node *rbprev = rb_prev(&rq->rb_node);
+
+	if (rbprev)
+		return rb_entry_rq(rbprev);
+
+	return NULL;
+}
+EXPORT_SYMBOL(elv_rb_former_request);
+
+struct request *elv_rb_latter_request(struct request_queue *q,
+				      struct request *rq)
+{
+	struct rb_node *rbnext = rb_next(&rq->rb_node);
+
+	if (rbnext)
+		return rb_entry_rq(rbnext);
+
+	return NULL;
+}
+EXPORT_SYMBOL(elv_rb_latter_request);
diff --git a/libdde-linux26/contrib/block/ioctl.c b/libdde-linux26/contrib/block/ioctl.c
new file mode 100644
index 00000000..0f22e629
--- /dev/null
+++ b/libdde-linux26/contrib/block/ioctl.c
@@ -0,0 +1,372 @@
+#include <linux/capability.h>
+#include <linux/blkdev.h>
+#include <linux/blkpg.h>
+#include <linux/hdreg.h>
+#include <linux/backing-dev.h>
+#include <linux/buffer_head.h>
+#include <linux/smp_lock.h>
+#include <linux/blktrace_api.h>
+#include <asm/uaccess.h>
+
+static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg)
+{
+	struct block_device *bdevp;
+	struct gendisk *disk;
+	struct hd_struct *part;
+	struct blkpg_ioctl_arg a;
+	struct blkpg_partition p;
+	struct disk_part_iter piter;
+	long long start, length;
+	int partno;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (copy_from_user(&a, arg, sizeof(struct blkpg_ioctl_arg)))
+		return -EFAULT;
+	if (copy_from_user(&p, a.data, sizeof(struct blkpg_partition)))
+		return -EFAULT;
+	disk = bdev->bd_disk;
+	if (bdev != bdev->bd_contains)
+		return -EINVAL;
+	partno = p.pno;
+	if (partno <= 0)
+		return -EINVAL;
+	switch (a.op) {
+		case BLKPG_ADD_PARTITION:
+			start = p.start >> 9;
+			length = p.length >> 9;
+			/* check for fit in a hd_struct */ 
+			if (sizeof(sector_t) == sizeof(long) && 
+			    sizeof(long long) > sizeof(long)) {
+				long pstart = start, plength = length;
+				if (pstart != start || plength != length
+				    || pstart < 0 || plength < 0)
+					return -EINVAL;
+			}
+
+			mutex_lock(&bdev->bd_mutex);
+
+			/* overlap? */
+			disk_part_iter_init(&piter, disk,
+					    DISK_PITER_INCL_EMPTY);
+			while ((part = disk_part_iter_next(&piter))) {
+				if (!(start + length <= part->start_sect ||
+				      start >= part->start_sect + part->nr_sects)) {
+					disk_part_iter_exit(&piter);
+					mutex_unlock(&bdev->bd_mutex);
+					return -EBUSY;
+				}
+			}
+			disk_part_iter_exit(&piter);
+
+			/* all seems OK */
+			part = add_partition(disk, partno, start, length,
+					     ADDPART_FLAG_NONE);
+			mutex_unlock(&bdev->bd_mutex);
+			return IS_ERR(part) ? PTR_ERR(part) : 0;
+		case BLKPG_DEL_PARTITION:
+			part = disk_get_part(disk, partno);
+			if (!part)
+				return -ENXIO;
+
+			bdevp = bdget(part_devt(part));
+			disk_put_part(part);
+			if (!bdevp)
+				return -ENOMEM;
+
+			mutex_lock(&bdevp->bd_mutex);
+			if (bdevp->bd_openers) {
+				mutex_unlock(&bdevp->bd_mutex);
+				bdput(bdevp);
+				return -EBUSY;
+			}
+			/* all seems OK */
+			fsync_bdev(bdevp);
+			invalidate_bdev(bdevp);
+
+			mutex_lock_nested(&bdev->bd_mutex, 1);
+			delete_partition(disk, partno);
+			mutex_unlock(&bdev->bd_mutex);
+			mutex_unlock(&bdevp->bd_mutex);
+			bdput(bdevp);
+
+			return 0;
+		default:
+			return -EINVAL;
+	}
+}
+
+static int blkdev_reread_part(struct block_device *bdev)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	int res;
+
+	if (!disk_partitionable(disk) || bdev != bdev->bd_contains)
+		return -EINVAL;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (!mutex_trylock(&bdev->bd_mutex))
+		return -EBUSY;
+	res = rescan_partitions(disk, bdev);
+	mutex_unlock(&bdev->bd_mutex);
+	return res;
+}
+
+static void blk_ioc_discard_endio(struct bio *bio, int err)
+{
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	}
+	complete(bio->bi_private);
+}
+
+static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
+			     uint64_t len)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	int ret = 0;
+
+	if (start & 511)
+		return -EINVAL;
+	if (len & 511)
+		return -EINVAL;
+	start >>= 9;
+	len >>= 9;
+
+	if (start + len > (bdev->bd_inode->i_size >> 9))
+		return -EINVAL;
+
+	if (!q->prepare_discard_fn)
+		return -EOPNOTSUPP;
+
+	while (len && !ret) {
+		DECLARE_COMPLETION_ONSTACK(wait);
+		struct bio *bio;
+
+		bio = bio_alloc(GFP_KERNEL, 0);
+		if (!bio)
+			return -ENOMEM;
+
+		bio->bi_end_io = blk_ioc_discard_endio;
+		bio->bi_bdev = bdev;
+		bio->bi_private = &wait;
+		bio->bi_sector = start;
+
+		if (len > q->max_hw_sectors) {
+			bio->bi_size = q->max_hw_sectors << 9;
+			len -= q->max_hw_sectors;
+			start += q->max_hw_sectors;
+		} else {
+			bio->bi_size = len << 9;
+			len = 0;
+		}
+		submit_bio(DISCARD_NOBARRIER, bio);
+
+		wait_for_completion(&wait);
+
+		if (bio_flagged(bio, BIO_EOPNOTSUPP))
+			ret = -EOPNOTSUPP;
+		else if (!bio_flagged(bio, BIO_UPTODATE))
+			ret = -EIO;
+		bio_put(bio);
+	}
+	return ret;
+}
+
+static int put_ushort(unsigned long arg, unsigned short val)
+{
+	return put_user(val, (unsigned short __user *)arg);
+}
+
+static int put_int(unsigned long arg, int val)
+{
+	return put_user(val, (int __user *)arg);
+}
+
+static int put_long(unsigned long arg, long val)
+{
+	return put_user(val, (long __user *)arg);
+}
+
+static int put_ulong(unsigned long arg, unsigned long val)
+{
+	return put_user(val, (unsigned long __user *)arg);
+}
+
+static int put_u64(unsigned long arg, u64 val)
+{
+	return put_user(val, (u64 __user *)arg);
+}
+
+int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
+			unsigned cmd, unsigned long arg)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	int ret;
+
+	if (disk->fops->ioctl)
+		return disk->fops->ioctl(bdev, mode, cmd, arg);
+
+	if (disk->fops->locked_ioctl) {
+		lock_kernel();
+		ret = disk->fops->locked_ioctl(bdev, mode, cmd, arg);
+		unlock_kernel();
+		return ret;
+	}
+
+	return -ENOTTY;
+}
+/*
+ * For the record: _GPL here is only because somebody decided to slap it
+ * on the previous export.  Sheer idiocy, since it wasn't copyrightable
+ * at all and could be open-coded without any exports by anybody who cares.
+ */
+EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
+
+/*
+ * always keep this in sync with compat_blkdev_ioctl() and
+ * compat_blkdev_locked_ioctl()
+ */
+int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
+			unsigned long arg)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	struct backing_dev_info *bdi;
+	loff_t size;
+	int ret, n;
+
+	switch(cmd) {
+	case BLKFLSBUF:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+
+		ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+		/* -EINVAL to handle old uncorrected drivers */
+		if (ret != -EINVAL && ret != -ENOTTY)
+			return ret;
+
+		lock_kernel();
+		fsync_bdev(bdev);
+		invalidate_bdev(bdev);
+		unlock_kernel();
+		return 0;
+
+	case BLKROSET:
+		ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+		/* -EINVAL to handle old uncorrected drivers */
+		if (ret != -EINVAL && ret != -ENOTTY)
+			return ret;
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		if (get_user(n, (int __user *)(arg)))
+			return -EFAULT;
+		lock_kernel();
+		set_device_ro(bdev, n);
+		unlock_kernel();
+		return 0;
+
+	case BLKDISCARD: {
+		uint64_t range[2];
+
+		if (!(mode & FMODE_WRITE))
+			return -EBADF;
+
+		if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+			return -EFAULT;
+
+		return blk_ioctl_discard(bdev, range[0], range[1]);
+	}
+
+	case HDIO_GETGEO: {
+		struct hd_geometry geo;
+
+		if (!arg)
+			return -EINVAL;
+		if (!disk->fops->getgeo)
+			return -ENOTTY;
+
+		/*
+		 * We need to set the startsect first, the driver may
+		 * want to override it.
+		 */
+		geo.start = get_start_sect(bdev);
+		ret = disk->fops->getgeo(bdev, &geo);
+		if (ret)
+			return ret;
+		if (copy_to_user((struct hd_geometry __user *)arg, &geo,
+					sizeof(geo)))
+			return -EFAULT;
+		return 0;
+	}
+	case BLKRAGET:
+	case BLKFRAGET:
+		if (!arg)
+			return -EINVAL;
+		bdi = blk_get_backing_dev_info(bdev);
+		if (bdi == NULL)
+			return -ENOTTY;
+		return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
+	case BLKROGET:
+		return put_int(arg, bdev_read_only(bdev) != 0);
+	case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */
+		return put_int(arg, block_size(bdev));
+	case BLKSSZGET: /* get block device hardware sector size */
+		return put_int(arg, bdev_hardsect_size(bdev));
+	case BLKSECTGET:
+		return put_ushort(arg, bdev_get_queue(bdev)->max_sectors);
+	case BLKRASET:
+	case BLKFRASET:
+		if(!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		bdi = blk_get_backing_dev_info(bdev);
+		if (bdi == NULL)
+			return -ENOTTY;
+		bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
+		return 0;
+	case BLKBSZSET:
+		/* set the logical block size */
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		if (!arg)
+			return -EINVAL;
+		if (get_user(n, (int __user *) arg))
+			return -EFAULT;
+		if (!(mode & FMODE_EXCL) && bd_claim(bdev, &bdev) < 0)
+			return -EBUSY;
+		ret = set_blocksize(bdev, n);
+		if (!(mode & FMODE_EXCL))
+			bd_release(bdev);
+		return ret;
+	case BLKPG:
+		lock_kernel();
+		ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
+		unlock_kernel();
+		break;
+	case BLKRRPART:
+		lock_kernel();
+		ret = blkdev_reread_part(bdev);
+		unlock_kernel();
+		break;
+	case BLKGETSIZE:
+		size = bdev->bd_inode->i_size;
+		if ((size >> 9) > ~0UL)
+			return -EFBIG;
+		return put_ulong(arg, size >> 9);
+	case BLKGETSIZE64:
+		return put_u64(arg, bdev->bd_inode->i_size);
+	case BLKTRACESTART:
+	case BLKTRACESTOP:
+	case BLKTRACESETUP:
+	case BLKTRACETEARDOWN:
+		lock_kernel();
+		ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg);
+		unlock_kernel();
+		break;
+	default:
+		ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_ioctl);
diff --git a/libdde-linux26/contrib/block/noop-iosched.c b/libdde-linux26/contrib/block/noop-iosched.c
new file mode 100644
index 00000000..075cb108
--- /dev/null
+++ b/libdde-linux26/contrib/block/noop-iosched.c
@@ -0,0 +1,123 @@
+/*
+ * elevator noop
+ */
+#include <linux/blkdev.h>
+#include <linux/elevator.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include "local.h"
+
+struct noop_data {
+	struct list_head queue;
+};
+
+static void noop_merged_requests(struct request_queue *q, struct request *rq,
+				 struct request *next)
+{
+	list_del_init(&next->queuelist);
+}
+
+static int noop_dispatch(struct request_queue *q, int force)
+{
+	struct noop_data *nd = q->elevator->elevator_data;
+
+	if (!list_empty(&nd->queue)) {
+		struct request *rq;
+		rq = list_entry(nd->queue.next, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		elv_dispatch_sort(q, rq);
+		return 1;
+	}
+	return 0;
+}
+
+static void noop_add_request(struct request_queue *q, struct request *rq)
+{
+	struct noop_data *nd = q->elevator->elevator_data;
+
+	list_add_tail(&rq->queuelist, &nd->queue);
+}
+
+static int noop_queue_empty(struct request_queue *q)
+{
+	struct noop_data *nd = q->elevator->elevator_data;
+
+	return list_empty(&nd->queue);
+}
+
+static struct request *
+noop_former_request(struct request_queue *q, struct request *rq)
+{
+	struct noop_data *nd = q->elevator->elevator_data;
+
+	if (rq->queuelist.prev == &nd->queue)
+		return NULL;
+	return list_entry(rq->queuelist.prev, struct request, queuelist);
+}
+
+static struct request *
+noop_latter_request(struct request_queue *q, struct request *rq)
+{
+	struct noop_data *nd = q->elevator->elevator_data;
+
+	if (rq->queuelist.next == &nd->queue)
+		return NULL;
+	return list_entry(rq->queuelist.next, struct request, queuelist);
+}
+
+static void *noop_init_queue(struct request_queue *q)
+{
+	struct noop_data *nd;
+
+	nd = kmalloc_node(sizeof(*nd), GFP_KERNEL, q->node);
+	if (!nd)
+		return NULL;
+	INIT_LIST_HEAD(&nd->queue);
+	return nd;
+}
+
+static void noop_exit_queue(struct elevator_queue *e)
+{
+	struct noop_data *nd = e->elevator_data;
+
+	BUG_ON(!list_empty(&nd->queue));
+	kfree(nd);
+}
+
+static struct elevator_type elevator_noop = {
+	.ops = {
+		.elevator_merge_req_fn		= noop_merged_requests,
+		.elevator_dispatch_fn		= noop_dispatch,
+		.elevator_add_req_fn		= noop_add_request,
+		.elevator_queue_empty_fn	= noop_queue_empty,
+		.elevator_former_req_fn		= noop_former_request,
+		.elevator_latter_req_fn		= noop_latter_request,
+		.elevator_init_fn		= noop_init_queue,
+		.elevator_exit_fn		= noop_exit_queue,
+	},
+	.elevator_name = "noop",
+	.elevator_owner = THIS_MODULE,
+};
+
+static int __init noop_init(void)
+{
+	DEBUG_MSG("here!");
+	elv_register(&elevator_noop);
+
+	return 0;
+}
+
+static void __exit noop_exit(void)
+{
+	elv_unregister(&elevator_noop);
+}
+
+subsys_initcall(noop_init);
+module_exit(noop_exit);
+
+
+MODULE_AUTHOR("Jens Axboe");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("No-op IO scheduler");
diff --git a/libdde-linux26/contrib/block/scsi_ioctl.c b/libdde-linux26/contrib/block/scsi_ioctl.c
new file mode 100644
index 00000000..ee9c67d7
--- /dev/null
+++ b/libdde-linux26/contrib/block/scsi_ioctl.c
@@ -0,0 +1,652 @@
+/*
+ * Copyright (C) 2001 Jens Axboe <axboe@suse.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public Licens
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/capability.h>
+#include <linux/completion.h>
+#include <linux/cdrom.h>
+#include <linux/slab.h>
+#include <linux/times.h>
+#include <asm/uaccess.h>
+
+#include <scsi/scsi.h>
+#include <scsi/scsi_ioctl.h>
+#include <scsi/scsi_cmnd.h>
+
+/* Command group 3 is reserved and should never be used.  */
+const unsigned char scsi_command_size_tbl[8] =
+{
+	6, 10, 10, 12,
+	16, 12, 10, 10
+};
+EXPORT_SYMBOL(scsi_command_size_tbl);
+
+#include <scsi/sg.h>
+
+static int sg_get_version(int __user *p)
+{
+	static const int sg_version_num = 30527;
+	return put_user(sg_version_num, p);
+}
+
+static int scsi_get_idlun(struct request_queue *q, int __user *p)
+{
+	return put_user(0, p);
+}
+
+static int scsi_get_bus(struct request_queue *q, int __user *p)
+{
+	return put_user(0, p);
+}
+
+static int sg_get_timeout(struct request_queue *q)
+{
+	return jiffies_to_clock_t(q->sg_timeout);
+}
+
+static int sg_set_timeout(struct request_queue *q, int __user *p)
+{
+	int timeout, err = get_user(timeout, p);
+
+	if (!err)
+		q->sg_timeout = clock_t_to_jiffies(timeout);
+
+	return err;
+}
+
+static int sg_get_reserved_size(struct request_queue *q, int __user *p)
+{
+	unsigned val = min(q->sg_reserved_size, q->max_sectors << 9);
+
+	return put_user(val, p);
+}
+
+static int sg_set_reserved_size(struct request_queue *q, int __user *p)
+{
+	int size, err = get_user(size, p);
+
+	if (err)
+		return err;
+
+	if (size < 0)
+		return -EINVAL;
+	if (size > (q->max_sectors << 9))
+		size = q->max_sectors << 9;
+
+	q->sg_reserved_size = size;
+	return 0;
+}
+
+/*
+ * will always return that we are ATAPI even for a real SCSI drive, I'm not
+ * so sure this is worth doing anything about (why would you care??)
+ */
+static int sg_emulated_host(struct request_queue *q, int __user *p)
+{
+	return put_user(1, p);
+}
+
+void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
+{
+	/* Basic read-only commands */
+	__set_bit(TEST_UNIT_READY, filter->read_ok);
+	__set_bit(REQUEST_SENSE, filter->read_ok);
+	__set_bit(READ_6, filter->read_ok);
+	__set_bit(READ_10, filter->read_ok);
+	__set_bit(READ_12, filter->read_ok);
+	__set_bit(READ_16, filter->read_ok);
+	__set_bit(READ_BUFFER, filter->read_ok);
+	__set_bit(READ_DEFECT_DATA, filter->read_ok);
+	__set_bit(READ_CAPACITY, filter->read_ok);
+	__set_bit(READ_LONG, filter->read_ok);
+	__set_bit(INQUIRY, filter->read_ok);
+	__set_bit(MODE_SENSE, filter->read_ok);
+	__set_bit(MODE_SENSE_10, filter->read_ok);
+	__set_bit(LOG_SENSE, filter->read_ok);
+	__set_bit(START_STOP, filter->read_ok);
+	__set_bit(GPCMD_VERIFY_10, filter->read_ok);
+	__set_bit(VERIFY_16, filter->read_ok);
+	__set_bit(REPORT_LUNS, filter->read_ok);
+	__set_bit(SERVICE_ACTION_IN, filter->read_ok);
+	__set_bit(RECEIVE_DIAGNOSTIC, filter->read_ok);
+	__set_bit(MAINTENANCE_IN, filter->read_ok);
+	__set_bit(GPCMD_READ_BUFFER_CAPACITY, filter->read_ok);
+
+	/* Audio CD commands */
+	__set_bit(GPCMD_PLAY_CD, filter->read_ok);
+	__set_bit(GPCMD_PLAY_AUDIO_10, filter->read_ok);
+	__set_bit(GPCMD_PLAY_AUDIO_MSF, filter->read_ok);
+	__set_bit(GPCMD_PLAY_AUDIO_TI, filter->read_ok);
+	__set_bit(GPCMD_PAUSE_RESUME, filter->read_ok);
+
+	/* CD/DVD data reading */
+	__set_bit(GPCMD_READ_CD, filter->read_ok);
+	__set_bit(GPCMD_READ_CD_MSF, filter->read_ok);
+	__set_bit(GPCMD_READ_DISC_INFO, filter->read_ok);
+	__set_bit(GPCMD_READ_CDVD_CAPACITY, filter->read_ok);
+	__set_bit(GPCMD_READ_DVD_STRUCTURE, filter->read_ok);
+	__set_bit(GPCMD_READ_HEADER, filter->read_ok);
+	__set_bit(GPCMD_READ_TRACK_RZONE_INFO, filter->read_ok);
+	__set_bit(GPCMD_READ_SUBCHANNEL, filter->read_ok);
+	__set_bit(GPCMD_READ_TOC_PMA_ATIP, filter->read_ok);
+	__set_bit(GPCMD_REPORT_KEY, filter->read_ok);
+	__set_bit(GPCMD_SCAN, filter->read_ok);
+	__set_bit(GPCMD_GET_CONFIGURATION, filter->read_ok);
+	__set_bit(GPCMD_READ_FORMAT_CAPACITIES, filter->read_ok);
+	__set_bit(GPCMD_GET_EVENT_STATUS_NOTIFICATION, filter->read_ok);
+	__set_bit(GPCMD_GET_PERFORMANCE, filter->read_ok);
+	__set_bit(GPCMD_SEEK, filter->read_ok);
+	__set_bit(GPCMD_STOP_PLAY_SCAN, filter->read_ok);
+
+	/* Basic writing commands */
+	__set_bit(WRITE_6, filter->write_ok);
+	__set_bit(WRITE_10, filter->write_ok);
+	__set_bit(WRITE_VERIFY, filter->write_ok);
+	__set_bit(WRITE_12, filter->write_ok);
+	__set_bit(WRITE_VERIFY_12, filter->write_ok);
+	__set_bit(WRITE_16, filter->write_ok);
+	__set_bit(WRITE_LONG, filter->write_ok);
+	__set_bit(WRITE_LONG_2, filter->write_ok);
+	__set_bit(ERASE, filter->write_ok);
+	__set_bit(GPCMD_MODE_SELECT_10, filter->write_ok);
+	__set_bit(MODE_SELECT, filter->write_ok);
+	__set_bit(LOG_SELECT, filter->write_ok);
+	__set_bit(GPCMD_BLANK, filter->write_ok);
+	__set_bit(GPCMD_CLOSE_TRACK, filter->write_ok);
+	__set_bit(GPCMD_FLUSH_CACHE, filter->write_ok);
+	__set_bit(GPCMD_FORMAT_UNIT, filter->write_ok);
+	__set_bit(GPCMD_REPAIR_RZONE_TRACK, filter->write_ok);
+	__set_bit(GPCMD_RESERVE_RZONE_TRACK, filter->write_ok);
+	__set_bit(GPCMD_SEND_DVD_STRUCTURE, filter->write_ok);
+	__set_bit(GPCMD_SEND_EVENT, filter->write_ok);
+	__set_bit(GPCMD_SEND_KEY, filter->write_ok);
+	__set_bit(GPCMD_SEND_OPC, filter->write_ok);
+	__set_bit(GPCMD_SEND_CUE_SHEET, filter->write_ok);
+	__set_bit(GPCMD_SET_SPEED, filter->write_ok);
+	__set_bit(GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL, filter->write_ok);
+	__set_bit(GPCMD_LOAD_UNLOAD, filter->write_ok);
+	__set_bit(GPCMD_SET_STREAMING, filter->write_ok);
+	__set_bit(GPCMD_SET_READ_AHEAD, filter->write_ok);
+}
+EXPORT_SYMBOL_GPL(blk_set_cmd_filter_defaults);
+
+static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
+			     struct sg_io_hdr *hdr, fmode_t mode)
+{
+	if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
+		return -EFAULT;
+	if (blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE))
+		return -EPERM;
+
+	/*
+	 * fill in request structure
+	 */
+	rq->cmd_len = hdr->cmd_len;
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+
+	rq->timeout = msecs_to_jiffies(hdr->timeout);
+	if (!rq->timeout)
+		rq->timeout = q->sg_timeout;
+	if (!rq->timeout)
+		rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
+	if (rq->timeout < BLK_MIN_SG_TIMEOUT)
+		rq->timeout = BLK_MIN_SG_TIMEOUT;
+
+	return 0;
+}
+
+/*
+ * unmap a request that was previously mapped to this sg_io_hdr. handles
+ * both sg and non-sg sg_io_hdr.
+ */
+static int blk_unmap_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr)
+{
+	blk_rq_unmap_user(rq->bio);
+	blk_put_request(rq);
+	return 0;
+}
+
+static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
+				 struct bio *bio)
+{
+	int r, ret = 0;
+
+	/*
+	 * fill in all the output members
+	 */
+	hdr->status = rq->errors & 0xff;
+	hdr->masked_status = status_byte(rq->errors);
+	hdr->msg_status = msg_byte(rq->errors);
+	hdr->host_status = host_byte(rq->errors);
+	hdr->driver_status = driver_byte(rq->errors);
+	hdr->info = 0;
+	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
+		hdr->info |= SG_INFO_CHECK;
+	hdr->resid = rq->data_len;
+	hdr->sb_len_wr = 0;
+
+	if (rq->sense_len && hdr->sbp) {
+		int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len);
+
+		if (!copy_to_user(hdr->sbp, rq->sense, len))
+			hdr->sb_len_wr = len;
+		else
+			ret = -EFAULT;
+	}
+
+	rq->bio = bio;
+	r = blk_unmap_sghdr_rq(rq, hdr);
+	if (ret)
+		r = ret;
+
+	return r;
+}
+
+static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
+		struct sg_io_hdr *hdr, fmode_t mode)
+{
+	unsigned long start_time;
+	int writing = 0, ret = 0;
+	struct request *rq;
+	char sense[SCSI_SENSE_BUFFERSIZE];
+	struct bio *bio;
+
+	if (hdr->interface_id != 'S')
+		return -EINVAL;
+	if (hdr->cmd_len > BLK_MAX_CDB)
+		return -EINVAL;
+
+	if (hdr->dxfer_len > (q->max_hw_sectors << 9))
+		return -EIO;
+
+	if (hdr->dxfer_len)
+		switch (hdr->dxfer_direction) {
+		default:
+			return -EINVAL;
+		case SG_DXFER_TO_DEV:
+			writing = 1;
+			break;
+		case SG_DXFER_TO_FROM_DEV:
+		case SG_DXFER_FROM_DEV:
+			break;
+		}
+
+	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
+	if (!rq)
+		return -ENOMEM;
+
+	if (blk_fill_sghdr_rq(q, rq, hdr, mode)) {
+		blk_put_request(rq);
+		return -EFAULT;
+	}
+
+	if (hdr->iovec_count) {
+		const int size = sizeof(struct sg_iovec) * hdr->iovec_count;
+		struct sg_iovec *iov;
+
+		iov = kmalloc(size, GFP_KERNEL);
+		if (!iov) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		if (copy_from_user(iov, hdr->dxferp, size)) {
+			kfree(iov);
+			ret = -EFAULT;
+			goto out;
+		}
+
+		ret = blk_rq_map_user_iov(q, rq, NULL, iov, hdr->iovec_count,
+					  hdr->dxfer_len, GFP_KERNEL);
+		kfree(iov);
+	} else if (hdr->dxfer_len)
+		ret = blk_rq_map_user(q, rq, NULL, hdr->dxferp, hdr->dxfer_len,
+				      GFP_KERNEL);
+
+	if (ret)
+		goto out;
+
+	bio = rq->bio;
+	memset(sense, 0, sizeof(sense));
+	rq->sense = sense;
+	rq->sense_len = 0;
+	rq->retries = 0;
+
+	start_time = jiffies;
+
+	/* ignore return value. All information is passed back to caller
+	 * (if he doesn't check that is his problem).
+	 * N.B. a non-zero SCSI status is _not_ necessarily an error.
+	 */
+	blk_execute_rq(q, bd_disk, rq, 0);
+
+	hdr->duration = jiffies_to_msecs(jiffies - start_time);
+
+	return blk_complete_sghdr_rq(rq, hdr, bio);
+out:
+	blk_put_request(rq);
+	return ret;
+}
+
+/**
+ * sg_scsi_ioctl  --  handle deprecated SCSI_IOCTL_SEND_COMMAND ioctl
+ * @file:	file this ioctl operates on (optional)
+ * @q:		request queue to send scsi commands down
+ * @disk:	gendisk to operate on (option)
+ * @sic:	userspace structure describing the command to perform
+ *
+ * Send down the scsi command described by @sic to the device below
+ * the request queue @q.  If @file is non-NULL it's used to perform
+ * fine-grained permission checks that allow users to send down
+ * non-destructive SCSI commands.  If the caller has a struct gendisk
+ * available it should be passed in as @disk to allow the low level
+ * driver to use the information contained in it.  A non-NULL @disk
+ * is only allowed if the caller knows that the low level driver doesn't
+ * need it (e.g. in the scsi subsystem).
+ *
+ * Notes:
+ *   -  This interface is deprecated - users should use the SG_IO
+ *      interface instead, as this is a more flexible approach to
+ *      performing SCSI commands on a device.
+ *   -  The SCSI command length is determined by examining the 1st byte
+ *      of the given command. There is no way to override this.
+ *   -  Data transfers are limited to PAGE_SIZE
+ *   -  The length (x + y) must be at least OMAX_SB_LEN bytes long to
+ *      accommodate the sense buffer when an error occurs.
+ *      The sense buffer is truncated to OMAX_SB_LEN (16) bytes so that
+ *      old code will not be surprised.
+ *   -  If a Unix error occurs (e.g. ENOMEM) then the user will receive
+ *      a negative return and the Unix error code in 'errno'.
+ *      If the SCSI command succeeds then 0 is returned.
+ *      Positive numbers returned are the compacted SCSI error codes (4
+ *      bytes in one int) where the lowest byte is the SCSI status.
+ */
+#define OMAX_SB_LEN 16          /* For backward compatibility */
+int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
+		struct scsi_ioctl_command __user *sic)
+{
+	struct request *rq;
+	int err;
+	unsigned int in_len, out_len, bytes, opcode, cmdlen;
+	char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE];
+
+	if (!sic)
+		return -EINVAL;
+
+	/*
+	 * get in an out lengths, verify they don't exceed a page worth of data
+	 */
+	if (get_user(in_len, &sic->inlen))
+		return -EFAULT;
+	if (get_user(out_len, &sic->outlen))
+		return -EFAULT;
+	if (in_len > PAGE_SIZE || out_len > PAGE_SIZE)
+		return -EINVAL;
+	if (get_user(opcode, sic->data))
+		return -EFAULT;
+
+	bytes = max(in_len, out_len);
+	if (bytes) {
+		buffer = kzalloc(bytes, q->bounce_gfp | GFP_USER| __GFP_NOWARN);
+		if (!buffer)
+			return -ENOMEM;
+
+	}
+
+	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT);
+
+	cmdlen = COMMAND_SIZE(opcode);
+
+	/*
+	 * get command and data to send to device, if any
+	 */
+	err = -EFAULT;
+	rq->cmd_len = cmdlen;
+	if (copy_from_user(rq->cmd, sic->data, cmdlen))
+		goto error;
+
+	if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
+		goto error;
+
+	err = blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE);
+	if (err)
+		goto error;
+
+	/* default.  possible overriden later */
+	rq->retries = 5;
+
+	switch (opcode) {
+	case SEND_DIAGNOSTIC:
+	case FORMAT_UNIT:
+		rq->timeout = FORMAT_UNIT_TIMEOUT;
+		rq->retries = 1;
+		break;
+	case START_STOP:
+		rq->timeout = START_STOP_TIMEOUT;
+		break;
+	case MOVE_MEDIUM:
+		rq->timeout = MOVE_MEDIUM_TIMEOUT;
+		break;
+	case READ_ELEMENT_STATUS:
+		rq->timeout = READ_ELEMENT_STATUS_TIMEOUT;
+		break;
+	case READ_DEFECT_DATA:
+		rq->timeout = READ_DEFECT_DATA_TIMEOUT;
+		rq->retries = 1;
+		break;
+	default:
+		rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
+		break;
+	}
+
+	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) {
+		err = DRIVER_ERROR << 24;
+		goto out;
+	}
+
+	memset(sense, 0, sizeof(sense));
+	rq->sense = sense;
+	rq->sense_len = 0;
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+
+	blk_execute_rq(q, disk, rq, 0);
+
+out:
+	err = rq->errors & 0xff;	/* only 8 bit SCSI status */
+	if (err) {
+		if (rq->sense_len && rq->sense) {
+			bytes = (OMAX_SB_LEN > rq->sense_len) ?
+				rq->sense_len : OMAX_SB_LEN;
+			if (copy_to_user(sic->data, rq->sense, bytes))
+				err = -EFAULT;
+		}
+	} else {
+		if (copy_to_user(sic->data, buffer, out_len))
+			err = -EFAULT;
+	}
+	
+error:
+	kfree(buffer);
+	blk_put_request(rq);
+	return err;
+}
+EXPORT_SYMBOL_GPL(sg_scsi_ioctl);
+
+/* Send basic block requests */
+static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
+			      int cmd, int data)
+{
+	struct request *rq;
+	int err;
+
+	rq = blk_get_request(q, WRITE, __GFP_WAIT);
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	rq->data = NULL;
+	rq->data_len = 0;
+	rq->extra_len = 0;
+	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
+	rq->cmd[0] = cmd;
+	rq->cmd[4] = data;
+	rq->cmd_len = 6;
+	err = blk_execute_rq(q, bd_disk, rq, 0);
+	blk_put_request(rq);
+
+	return err;
+}
+
+static inline int blk_send_start_stop(struct request_queue *q,
+				      struct gendisk *bd_disk, int data)
+{
+	return __blk_send_generic(q, bd_disk, GPCMD_START_STOP_UNIT, data);
+}
+
+int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mode,
+		   unsigned int cmd, void __user *arg)
+{
+	int err;
+
+	if (!q || blk_get_queue(q))
+		return -ENXIO;
+
+	switch (cmd) {
+		/*
+		 * new sgv3 interface
+		 */
+		case SG_GET_VERSION_NUM:
+			err = sg_get_version(arg);
+			break;
+		case SCSI_IOCTL_GET_IDLUN:
+			err = scsi_get_idlun(q, arg);
+			break;
+		case SCSI_IOCTL_GET_BUS_NUMBER:
+			err = scsi_get_bus(q, arg);
+			break;
+		case SG_SET_TIMEOUT:
+			err = sg_set_timeout(q, arg);
+			break;
+		case SG_GET_TIMEOUT:
+			err = sg_get_timeout(q);
+			break;
+		case SG_GET_RESERVED_SIZE:
+			err = sg_get_reserved_size(q, arg);
+			break;
+		case SG_SET_RESERVED_SIZE:
+			err = sg_set_reserved_size(q, arg);
+			break;
+		case SG_EMULATED_HOST:
+			err = sg_emulated_host(q, arg);
+			break;
+		case SG_IO: {
+			struct sg_io_hdr hdr;
+
+			err = -EFAULT;
+			if (copy_from_user(&hdr, arg, sizeof(hdr)))
+				break;
+			err = sg_io(q, bd_disk, &hdr, mode);
+			if (err == -EFAULT)
+				break;
+
+			if (copy_to_user(arg, &hdr, sizeof(hdr)))
+				err = -EFAULT;
+			break;
+		}
+		case CDROM_SEND_PACKET: {
+			struct cdrom_generic_command cgc;
+			struct sg_io_hdr hdr;
+
+			err = -EFAULT;
+			if (copy_from_user(&cgc, arg, sizeof(cgc)))
+				break;
+			cgc.timeout = clock_t_to_jiffies(cgc.timeout);
+			memset(&hdr, 0, sizeof(hdr));
+			hdr.interface_id = 'S';
+			hdr.cmd_len = sizeof(cgc.cmd);
+			hdr.dxfer_len = cgc.buflen;
+			err = 0;
+			switch (cgc.data_direction) {
+				case CGC_DATA_UNKNOWN:
+					hdr.dxfer_direction = SG_DXFER_UNKNOWN;
+					break;
+				case CGC_DATA_WRITE:
+					hdr.dxfer_direction = SG_DXFER_TO_DEV;
+					break;
+				case CGC_DATA_READ:
+					hdr.dxfer_direction = SG_DXFER_FROM_DEV;
+					break;
+				case CGC_DATA_NONE:
+					hdr.dxfer_direction = SG_DXFER_NONE;
+					break;
+				default:
+					err = -EINVAL;
+			}
+			if (err)
+				break;
+
+			hdr.dxferp = cgc.buffer;
+			hdr.sbp = cgc.sense;
+			if (hdr.sbp)
+				hdr.mx_sb_len = sizeof(struct request_sense);
+			hdr.timeout = jiffies_to_msecs(cgc.timeout);
+			hdr.cmdp = ((struct cdrom_generic_command __user*) arg)->cmd;
+			hdr.cmd_len = sizeof(cgc.cmd);
+
+			err = sg_io(q, bd_disk, &hdr, mode);
+			if (err == -EFAULT)
+				break;
+
+			if (hdr.status)
+				err = -EIO;
+
+			cgc.stat = err;
+			cgc.buflen = hdr.resid;
+			if (copy_to_user(arg, &cgc, sizeof(cgc)))
+				err = -EFAULT;
+
+			break;
+		}
+
+		/*
+		 * old junk scsi send command ioctl
+		 */
+		case SCSI_IOCTL_SEND_COMMAND:
+			printk(KERN_WARNING "program %s is using a deprecated SCSI ioctl, please convert it to SG_IO\n", current->comm);
+			err = -EINVAL;
+			if (!arg)
+				break;
+
+			err = sg_scsi_ioctl(q, bd_disk, mode, arg);
+			break;
+		case CDROMCLOSETRAY:
+			err = blk_send_start_stop(q, bd_disk, 0x03);
+			break;
+		case CDROMEJECT:
+			err = blk_send_start_stop(q, bd_disk, 0x02);
+			break;
+		default:
+			err = -ENOTTY;
+	}
+
+	blk_put_queue(q);
+	return err;
+}
+
+EXPORT_SYMBOL(scsi_cmd_ioctl);