Merge branch 'master' into next

17 files changed, 592 insertions, 1202 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 0cbb3b88b59..e7d12782bcf 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -44,22 +44,6 @@ config LBD
 
 	  If unsure, say N.
 
-config BLK_DEV_IO_TRACE
-	bool "Support for tracing block io actions"
-	depends on SYSFS
-	select RELAY
-	select DEBUG_FS
-	select TRACEPOINTS
-	help
-	  Say Y here if you want to be able to trace the block layer actions
-	  on a given queue. Tracing allows you to see any traffic happening
-	  on a block device queue. For more information (and the userspace
-	  support tools needed), fetch the blktrace tools from:
-
-	  git://git.kernel.dk/blktrace.git
-
-	  If unsure, say N.
-
 config BLK_DEV_BSG
 	bool "Block layer SG support v4 (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
diff --git a/block/Makefile b/block/Makefile
index bfe73049f93..e9fa4dd690f 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -13,6 +13,5 @@ obj-$(CONFIG_IOSCHED_AS)	+= as-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 
-obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY)	+= blk-integrity.o
diff --git a/block/as-iosched.c b/block/as-iosched.c
index 631f6f44460..c48fa670d22 100644
--- a/block/as-iosched.c
+++ b/block/as-iosched.c
@@ -17,9 +17,6 @@
 #include <linux/rbtree.h>
 #include <linux/interrupt.h>
 
-#define REQ_SYNC	1
-#define REQ_ASYNC	0
-
 /*
  * See Documentation/block/as-iosched.txt
  */
@@ -93,7 +90,7 @@ struct as_data {
 	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 */
+	sector_t last_sector[2];	/* last SYNC & ASYNC sectors */
 
 	unsigned long exit_prob;	/* probability a task will exit while
 					   being waited on */
@@ -109,7 +106,7 @@ struct as_data {
 	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 batch_data_dir;		/* current batch SYNC / ASYNC */
 	int write_batch_count;		/* max # of reqs in a write batch */
 	int current_write_count;	/* how many requests left this batch */
 	int write_batch_idled;		/* has the write batch gone idle? */
@@ -554,7 +551,7 @@ static void as_update_iohist(struct as_data *ad, struct as_io_context *aic,
 	if (aic == NULL)
 		return;
 
-	if (data_dir == REQ_SYNC) {
+	if (data_dir == BLK_RW_SYNC) {
 		unsigned long in_flight = atomic_read(&aic->nr_queued)
 					+ atomic_read(&aic->nr_dispatched);
 		spin_lock(&aic->lock);
@@ -811,7 +808,7 @@ static void as_update_rq(struct as_data *ad, struct request *rq)
  */
 static void update_write_batch(struct as_data *ad)
 {
-	unsigned long batch = ad->batch_expire[REQ_ASYNC];
+	unsigned long batch = ad->batch_expire[BLK_RW_ASYNC];
 	long write_time;
 
 	write_time = (jiffies - ad->current_batch_expires) + batch;
@@ -855,7 +852,7 @@ static void as_completed_request(struct request_queue *q, struct request *rq)
 		kblockd_schedule_work(q, &ad->antic_work);
 		ad->changed_batch = 0;
 
-		if (ad->batch_data_dir == REQ_SYNC)
+		if (ad->batch_data_dir == BLK_RW_SYNC)
 			ad->new_batch = 1;
 	}
 	WARN_ON(ad->nr_dispatched == 0);
@@ -869,7 +866,7 @@ static void as_completed_request(struct request_queue *q, struct request *rq)
 	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->batch_expire[BLK_RW_SYNC];
 		ad->new_batch = 0;
 	}
 
@@ -960,7 +957,7 @@ 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)
+	if (ad->batch_data_dir == BLK_RW_SYNC)
 		/* TODO! add a check so a complete fifo gets written? */
 		return time_after(jiffies, ad->current_batch_expires);
 
@@ -986,7 +983,7 @@ static void as_move_to_dispatch(struct as_data *ad, struct request *rq)
 	 */
 	ad->last_sector[data_dir] = rq->sector + rq->nr_sectors;
 
-	if (data_dir == REQ_SYNC) {
+	if (data_dir == BLK_RW_SYNC) {
 		struct io_context *ioc = RQ_IOC(rq);
 		/* In case we have to anticipate after this */
 		copy_io_context(&ad->io_context, &ioc);
@@ -1025,41 +1022,41 @@ static void as_move_to_dispatch(struct as_data *ad, struct request *rq)
 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]);
+	const int reads = !list_empty(&ad->fifo_list[BLK_RW_SYNC]);
+	const int writes = !list_empty(&ad->fifo_list[BLK_RW_ASYNC]);
 	struct request *rq;
 
 	if (unlikely(force)) {
 		/*
 		 * Forced dispatch, accounting is useless.  Reset
 		 * accounting states and dump fifo_lists.  Note that
-		 * batch_data_dir is reset to REQ_SYNC to avoid
+		 * batch_data_dir is reset to BLK_RW_SYNC to avoid
 		 * screwing write batch accounting as write batch
 		 * accounting occurs on W->R transition.
 		 */
 		int dispatched = 0;
 
-		ad->batch_data_dir = REQ_SYNC;
+		ad->batch_data_dir = BLK_RW_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]);
+		while (ad->next_rq[BLK_RW_SYNC]) {
+			as_move_to_dispatch(ad, ad->next_rq[BLK_RW_SYNC]);
 			dispatched++;
 		}
-		ad->last_check_fifo[REQ_SYNC] = jiffies;
+		ad->last_check_fifo[BLK_RW_SYNC] = jiffies;
 
-		while (ad->next_rq[REQ_ASYNC]) {
-			as_move_to_dispatch(ad, ad->next_rq[REQ_ASYNC]);
+		while (ad->next_rq[BLK_RW_ASYNC]) {
+			as_move_to_dispatch(ad, ad->next_rq[BLK_RW_ASYNC]);
 			dispatched++;
 		}
-		ad->last_check_fifo[REQ_ASYNC] = jiffies;
+		ad->last_check_fifo[BLK_RW_ASYNC] = jiffies;
 
 		return dispatched;
 	}
 
 	/* Signal that the write batch was uncontended, so we can't time it */
-	if (ad->batch_data_dir == REQ_ASYNC && !reads) {
+	if (ad->batch_data_dir == BLK_RW_ASYNC && !reads) {
 		if (ad->current_write_count == 0 || !writes)
 			ad->write_batch_idled = 1;
 	}
@@ -1076,8 +1073,8 @@ static int as_dispatch_request(struct request_queue *q, int force)
 		 */
 		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))
+		if (ad->batch_data_dir == BLK_RW_SYNC && ad->antic_expire) {
+			if (as_fifo_expired(ad, BLK_RW_SYNC))
 				goto fifo_expired;
 
 			if (as_can_anticipate(ad, rq)) {
@@ -1090,7 +1087,7 @@ static int as_dispatch_request(struct request_queue *q, int force)
 			/* we have a "next request" */
 			if (reads && !writes)
 				ad->current_batch_expires =
-					jiffies + ad->batch_expire[REQ_SYNC];
+					jiffies + ad->batch_expire[BLK_RW_SYNC];
 			goto dispatch_request;
 		}
 	}
@@ -1101,20 +1098,20 @@ static int as_dispatch_request(struct request_queue *q, int force)
 	 */
 
 	if (reads) {
-		BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[REQ_SYNC]));
+		BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[BLK_RW_SYNC]));
 
-		if (writes && ad->batch_data_dir == REQ_SYNC)
+		if (writes && ad->batch_data_dir == BLK_RW_SYNC)
 			/*
 			 * Last batch was a read, switch to writes
 			 */
 			goto dispatch_writes;
 
-		if (ad->batch_data_dir == REQ_ASYNC) {
+		if (ad->batch_data_dir == BLK_RW_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->batch_data_dir = BLK_RW_SYNC;
+		rq = rq_entry_fifo(ad->fifo_list[BLK_RW_SYNC].next);
 		ad->last_check_fifo[ad->batch_data_dir] = jiffies;
 		goto dispatch_request;
 	}
@@ -1125,9 +1122,9 @@ static int as_dispatch_request(struct request_queue *q, int force)
 
 	if (writes) {
 dispatch_writes:
-		BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[REQ_ASYNC]));
+		BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[BLK_RW_ASYNC]));
 
-		if (ad->batch_data_dir == REQ_SYNC) {
+		if (ad->batch_data_dir == BLK_RW_SYNC) {
 			ad->changed_batch = 1;
 
 			/*
@@ -1137,11 +1134,11 @@ dispatch_writes:
 			 */
 			ad->new_batch = 0;
 		}
-		ad->batch_data_dir = REQ_ASYNC;
+		ad->batch_data_dir = BLK_RW_ASYNC;
 		ad->current_write_count = ad->write_batch_count;
 		ad->write_batch_idled = 0;
-		rq = rq_entry_fifo(ad->fifo_list[REQ_ASYNC].next);
-		ad->last_check_fifo[REQ_ASYNC] = jiffies;
+		rq = rq_entry_fifo(ad->fifo_list[BLK_RW_ASYNC].next);
+		ad->last_check_fifo[BLK_RW_ASYNC] = jiffies;
 		goto dispatch_request;
 	}
 
@@ -1164,9 +1161,9 @@ fifo_expired:
 		if (ad->nr_dispatched)
 			return 0;
 
-		if (ad->batch_data_dir == REQ_ASYNC)
+		if (ad->batch_data_dir == BLK_RW_ASYNC)
 			ad->current_batch_expires = jiffies +
-					ad->batch_expire[REQ_ASYNC];
+					ad->batch_expire[BLK_RW_ASYNC];
 		else
 			ad->new_batch = 1;
 
@@ -1238,8 +1235,8 @@ 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]);
+	return list_empty(&ad->fifo_list[BLK_RW_ASYNC])
+		&& list_empty(&ad->fifo_list[BLK_RW_SYNC]);
 }
 
 static int
@@ -1346,8 +1343,8 @@ static void as_exit_queue(struct elevator_queue *e)
 	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]));
+	BUG_ON(!list_empty(&ad->fifo_list[BLK_RW_SYNC]));
+	BUG_ON(!list_empty(&ad->fifo_list[BLK_RW_ASYNC]));
 
 	put_io_context(ad->io_context);
 	kfree(ad);
@@ -1372,18 +1369,18 @@ static void *as_init_queue(struct request_queue *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;
+	INIT_LIST_HEAD(&ad->fifo_list[BLK_RW_SYNC]);
+	INIT_LIST_HEAD(&ad->fifo_list[BLK_RW_ASYNC]);
+	ad->sort_list[BLK_RW_SYNC] = RB_ROOT;
+	ad->sort_list[BLK_RW_ASYNC] = RB_ROOT;
+	ad->fifo_expire[BLK_RW_SYNC] = default_read_expire;
+	ad->fifo_expire[BLK_RW_ASYNC] = default_write_expire;
 	ad->antic_expire = default_antic_expire;
-	ad->batch_expire[REQ_SYNC] = default_read_batch_expire;
-	ad->batch_expire[REQ_ASYNC] = default_write_batch_expire;
+	ad->batch_expire[BLK_RW_SYNC] = default_read_batch_expire;
+	ad->batch_expire[BLK_RW_ASYNC] = default_write_batch_expire;
 
-	ad->current_batch_expires = jiffies + ad->batch_expire[REQ_SYNC];
-	ad->write_batch_count = ad->batch_expire[REQ_ASYNC] / 10;
+	ad->current_batch_expires = jiffies + ad->batch_expire[BLK_RW_SYNC];
+	ad->write_batch_count = ad->batch_expire[BLK_RW_ASYNC] / 10;
 	if (ad->write_batch_count < 2)
 		ad->write_batch_count = 2;
 
@@ -1432,11 +1429,11 @@ 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_read_expire_show, ad->fifo_expire[BLK_RW_SYNC]);
+SHOW_FUNCTION(as_write_expire_show, ad->fifo_expire[BLK_RW_ASYNC]);
 SHOW_FUNCTION(as_antic_expire_show, ad->antic_expire);
-SHOW_FUNCTION(as_read_batch_expire_show, ad->batch_expire[REQ_SYNC]);
-SHOW_FUNCTION(as_write_batch_expire_show, ad->batch_expire[REQ_ASYNC]);
+SHOW_FUNCTION(as_read_batch_expire_show, ad->batch_expire[BLK_RW_SYNC]);
+SHOW_FUNCTION(as_write_batch_expire_show, ad->batch_expire[BLK_RW_ASYNC]);
 #undef SHOW_FUNCTION
 
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)				\
@@ -1451,13 +1448,14 @@ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)
 	*(__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_read_expire_store, &ad->fifo_expire[BLK_RW_SYNC], 0, INT_MAX);
+STORE_FUNCTION(as_write_expire_store,
+			&ad->fifo_expire[BLK_RW_ASYNC], 0, INT_MAX);
 STORE_FUNCTION(as_antic_expire_store, &ad->antic_expire, 0, INT_MAX);
 STORE_FUNCTION(as_read_batch_expire_store,
-			&ad->batch_expire[REQ_SYNC], 0, INT_MAX);
+			&ad->batch_expire[BLK_RW_SYNC], 0, INT_MAX);
 STORE_FUNCTION(as_write_batch_expire_store,
-			&ad->batch_expire[REQ_ASYNC], 0, INT_MAX);
+			&ad->batch_expire[BLK_RW_ASYNC], 0, INT_MAX);
 #undef STORE_FUNCTION
 
 #define AS_ATTR(name) \
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index f7dae57e6ca..20b4111fa05 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -319,9 +319,6 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 		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;
diff --git a/block/blk-core.c b/block/blk-core.c
index 996ed906d8c..2998fe3a237 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -64,12 +64,11 @@ static struct workqueue_struct *kblockd_workqueue;
 
 static void drive_stat_acct(struct request *rq, int new_io)
 {
-	struct gendisk *disk = rq->rq_disk;
 	struct hd_struct *part;
 	int rw = rq_data_dir(rq);
 	int cpu;
 
-	if (!blk_fs_request(rq) || !disk || !blk_do_io_stat(disk->queue))
+	if (!blk_fs_request(rq) || !blk_do_io_stat(rq))
 		return;
 
 	cpu = part_stat_lock();
@@ -132,6 +131,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	INIT_HLIST_NODE(&rq->hash);
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->cmd = rq->__cmd;
+	rq->cmd_len = BLK_MAX_CDB;
 	rq->tag = -1;
 	rq->ref_count = 1;
 }
@@ -484,11 +484,11 @@ static int blk_init_free_list(struct request_queue *q)
 {
 	struct request_list *rl = &q->rq;
 
-	rl->count[READ] = rl->count[WRITE] = 0;
-	rl->starved[READ] = rl->starved[WRITE] = 0;
+	rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
+	rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
 	rl->elvpriv = 0;
-	init_waitqueue_head(&rl->wait[READ]);
-	init_waitqueue_head(&rl->wait[WRITE]);
+	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
+	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
 
 	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
 				mempool_free_slab, request_cachep, q->node);
@@ -643,7 +643,7 @@ static inline void blk_free_request(struct request_queue *q, struct request *rq)
 }
 
 static struct request *
-blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask)
+blk_alloc_request(struct request_queue *q, int flags, int priv, gfp_t gfp_mask)
 {
 	struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);
 
@@ -652,7 +652,7 @@ blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask)
 
 	blk_rq_init(q, rq);
 
-	rq->cmd_flags = rw | REQ_ALLOCED;
+	rq->cmd_flags = flags | REQ_ALLOCED;
 
 	if (priv) {
 		if (unlikely(elv_set_request(q, rq, gfp_mask))) {
@@ -699,18 +699,18 @@ static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)
 	ioc->last_waited = jiffies;
 }
 
-static void __freed_request(struct request_queue *q, int rw)
+static void __freed_request(struct request_queue *q, int sync)
 {
 	struct request_list *rl = &q->rq;
 
-	if (rl->count[rw] < queue_congestion_off_threshold(q))
-		blk_clear_queue_congested(q, rw);
+	if (rl->count[sync] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, sync);
 
-	if (rl->count[rw] + 1 <= q->nr_requests) {
-		if (waitqueue_active(&rl->wait[rw]))
-			wake_up(&rl->wait[rw]);
+	if (rl->count[sync] + 1 <= q->nr_requests) {
+		if (waitqueue_active(&rl->wait[sync]))
+			wake_up(&rl->wait[sync]);
 
-		blk_clear_queue_full(q, rw);
+		blk_clear_queue_full(q, sync);
 	}
 }
 
@@ -718,18 +718,18 @@ static void __freed_request(struct request_queue *q, int rw)
  * A request has just been released.  Account for it, update the full and
  * congestion status, wake up any waiters.   Called under q->queue_lock.
  */
-static void freed_request(struct request_queue *q, int rw, int priv)
+static void freed_request(struct request_queue *q, int sync, int priv)
 {
 	struct request_list *rl = &q->rq;
 
-	rl->count[rw]--;
+	rl->count[sync]--;
 	if (priv)
 		rl->elvpriv--;
 
-	__freed_request(q, rw);
+	__freed_request(q, sync);
 
-	if (unlikely(rl->starved[rw ^ 1]))
-		__freed_request(q, rw ^ 1);
+	if (unlikely(rl->starved[sync ^ 1]))
+		__freed_request(q, sync ^ 1);
 }
 
 /*
@@ -743,15 +743,15 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	struct request *rq = NULL;
 	struct request_list *rl = &q->rq;
 	struct io_context *ioc = NULL;
-	const int rw = rw_flags & 0x01;
+	const bool is_sync = rw_is_sync(rw_flags) != 0;
 	int may_queue, priv;
 
 	may_queue = elv_may_queue(q, rw_flags);
 	if (may_queue == ELV_MQUEUE_NO)
 		goto rq_starved;
 
-	if (rl->count[rw]+1 >= queue_congestion_on_threshold(q)) {
-		if (rl->count[rw]+1 >= q->nr_requests) {
+	if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) {
+		if (rl->count[is_sync]+1 >= q->nr_requests) {
 			ioc = current_io_context(GFP_ATOMIC, q->node);
 			/*
 			 * The queue will fill after this allocation, so set
@@ -759,9 +759,9 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 			 * This process will be allowed to complete a batch of
 			 * requests, others will be blocked.
 			 */
-			if (!blk_queue_full(q, rw)) {
+			if (!blk_queue_full(q, is_sync)) {
 				ioc_set_batching(q, ioc);
-				blk_set_queue_full(q, rw);
+				blk_set_queue_full(q, is_sync);
 			} else {
 				if (may_queue != ELV_MQUEUE_MUST
 						&& !ioc_batching(q, ioc)) {
@@ -774,7 +774,7 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 				}
 			}
 		}
-		blk_set_queue_congested(q, rw);
+		blk_set_queue_congested(q, is_sync);
 	}
 
 	/*
@@ -782,16 +782,18 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	 * limit of requests, otherwise we could have thousands of requests
 	 * allocated with any setting of ->nr_requests
 	 */
-	if (rl->count[rw] >= (3 * q->nr_requests / 2))
+	if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
 		goto out;
 
-	rl->count[rw]++;
-	rl->starved[rw] = 0;
+	rl->count[is_sync]++;
+	rl->starved[is_sync] = 0;
 
 	priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
 	if (priv)
 		rl->elvpriv++;
 
+	if (blk_queue_io_stat(q))
+		rw_flags |= REQ_IO_STAT;
 	spin_unlock_irq(q->queue_lock);
 
 	rq = blk_alloc_request(q, rw_flags, priv, gfp_mask);
@@ -804,7 +806,7 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 		 * wait queue, but this is pretty rare.
 		 */
 		spin_lock_irq(q->queue_lock);
-		freed_request(q, rw, priv);
+		freed_request(q, is_sync, priv);
 
 		/*
 		 * in the very unlikely event that allocation failed and no
@@ -814,8 +816,8 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 		 * rq mempool into READ and WRITE
 		 */
 rq_starved:
-		if (unlikely(rl->count[rw] == 0))
-			rl->starved[rw] = 1;
+		if (unlikely(rl->count[is_sync] == 0))
+			rl->starved[is_sync] = 1;
 
 		goto out;
 	}
@@ -829,7 +831,7 @@ rq_starved:
 	if (ioc_batching(q, ioc))
 		ioc->nr_batch_requests--;
 
-	trace_block_getrq(q, bio, rw);
+	trace_block_getrq(q, bio, rw_flags & 1);
 out:
 	return rq;
 }
@@ -843,7 +845,7 @@ out:
 static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 					struct bio *bio)
 {
-	const int rw = rw_flags & 0x01;
+	const bool is_sync = rw_is_sync(rw_flags) != 0;
 	struct request *rq;
 
 	rq = get_request(q, rw_flags, bio, GFP_NOIO);
@@ -852,10 +854,10 @@ static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 		struct io_context *ioc;
 		struct request_list *rl = &q->rq;
 
-		prepare_to_wait_exclusive(&rl->wait[rw], &wait,
+		prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
 				TASK_UNINTERRUPTIBLE);
 
-		trace_block_sleeprq(q, bio, rw);
+		trace_block_sleeprq(q, bio, rw_flags & 1);
 
 		__generic_unplug_device(q);
 		spin_unlock_irq(q->queue_lock);
@@ -871,7 +873,7 @@ static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 		ioc_set_batching(q, ioc);
 
 		spin_lock_irq(q->queue_lock);
-		finish_wait(&rl->wait[rw], &wait);
+		finish_wait(&rl->wait[is_sync], &wait);
 
 		rq = get_request(q, rw_flags, bio, GFP_NOIO);
 	};
@@ -1070,14 +1072,14 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	 * it didn't come out of our reserved rq pools
 	 */
 	if (req->cmd_flags & REQ_ALLOCED) {
-		int rw = rq_data_dir(req);
+		int is_sync = rq_is_sync(req) != 0;
 		int priv = req->cmd_flags & REQ_ELVPRIV;
 
 		BUG_ON(!list_empty(&req->queuelist));
 		BUG_ON(!hlist_unhashed(&req->hash));
 
 		blk_free_request(q, req);
-		freed_request(q, rw, priv);
+		freed_request(q, is_sync, priv);
 	}
 }
 EXPORT_SYMBOL_GPL(__blk_put_request);
@@ -1124,10 +1126,10 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 
 	if (bio_sync(bio))
 		req->cmd_flags |= REQ_RW_SYNC;
-	if (bio_unplug(bio))
-		req->cmd_flags |= REQ_UNPLUG;
 	if (bio_rw_meta(bio))
 		req->cmd_flags |= REQ_RW_META;
+	if (bio_noidle(bio))
+		req->cmd_flags |= REQ_NOIDLE;
 
 	req->errors = 0;
 	req->hard_sector = req->sector = bio->bi_sector;
@@ -1136,6 +1138,15 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	blk_rq_bio_prep(req->q, req, bio);
 }
 
+/*
+ * Only disabling plugging for non-rotational devices if it does tagging
+ * as well, otherwise we do need the proper merging
+ */
+static inline bool queue_should_plug(struct request_queue *q)
+{
+	return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
+}
+
 static int __make_request(struct request_queue *q, struct bio *bio)
 {
 	struct request *req;
@@ -1242,11 +1253,11 @@ get_rq:
 	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) ||
 	    bio_flagged(bio, BIO_CPU_AFFINE))
 		req->cpu = blk_cpu_to_group(smp_processor_id());
-	if (!blk_queue_nonrot(q) && elv_queue_empty(q))
+	if (queue_should_plug(q) && elv_queue_empty(q))
 		blk_plug_device(q);
 	add_request(q, req);
 out:
-	if (unplug || blk_queue_nonrot(q))
+	if (unplug || !queue_should_plug(q))
 		__generic_unplug_device(q);
 	spin_unlock_irq(q->queue_lock);
 	return 0;
@@ -1664,9 +1675,7 @@ EXPORT_SYMBOL(blkdev_dequeue_request);
 
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
-	struct gendisk *disk = req->rq_disk;
-
-	if (!disk || !blk_do_io_stat(disk->queue))
+	if (!blk_do_io_stat(req))
 		return;
 
 	if (blk_fs_request(req)) {
@@ -1683,9 +1692,7 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 
 static void blk_account_io_done(struct request *req)
 {
-	struct gendisk *disk = req->rq_disk;
-
-	if (!disk || !blk_do_io_stat(disk->queue))
+	if (!blk_do_io_stat(req))
 		return;
 
 	/*
@@ -1700,7 +1707,7 @@ static void blk_account_io_done(struct request *req)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(disk, req->sector);
+		part = disk_map_sector_rcu(req->rq_disk, req->sector);
 
 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index e39cb24b767..23d2a6fe34a 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -338,6 +338,22 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	return 1;
 }
 
+static void blk_account_io_merge(struct request *req)
+{
+	if (blk_do_io_stat(req)) {
+		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();
+	}
+}
+
 /*
  * Has to be called with the request spinlock acquired
  */
@@ -386,18 +402,10 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 
 	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();
-	}
+	/*
+	 * 'next' is going away, so update stats accordingly
+	 */
+	blk_account_io_merge(next);
 
 	req->ioprio = ioprio_best(req->ioprio, next->ioprio);
 	if (blk_rq_cpu_valid(next))
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 59fd05d9f1d..57af728d94b 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -156,26 +156,28 @@ 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
+ * @q: the request queue for the device
+ * @dma_mask: the maximum address the device can handle
  *
  * 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.
+ *    buffers for doing I/O to pages residing above @dma_mask.
  **/
-void blk_queue_bounce_limit(struct request_queue *q, u64 dma_addr)
+void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask)
 {
-	unsigned long b_pfn = dma_addr >> PAGE_SHIFT;
+	unsigned long b_pfn = dma_mask >> 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))
+	/*
+	 * 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, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
 		dma = 1;
 	q->bounce_pfn = max_low_pfn;
 #else
@@ -431,7 +433,7 @@ EXPORT_SYMBOL(blk_queue_segment_boundary);
  *
  * description:
  *    set required memory and length alignment for direct dma transactions.
- *    this is used when buiding direct io requests for the queue.
+ *    this is used when building direct io requests for the queue.
  *
  **/
 void blk_queue_dma_alignment(struct request_queue *q, int mask)
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index ce0efc6b26d..ee9c2160222 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -64,7 +64,7 @@ static int raise_blk_irq(int cpu, struct request *rq)
 		data->info = rq;
 		data->flags = 0;
 
-		__smp_call_function_single(cpu, data);
+		__smp_call_function_single(cpu, data, 0);
 		return 0;
 	}
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index e29ddfc73cf..3ff9bba3379 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -48,28 +48,28 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 	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[BLK_RW_SYNC] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, BLK_RW_SYNC);
+	else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, BLK_RW_SYNC);
+
+	if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, BLK_RW_ASYNC);
+	else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, BLK_RW_ASYNC);
+
+	if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
+		blk_set_queue_full(q, BLK_RW_SYNC);
+	} else if (rl->count[BLK_RW_SYNC]+1 <= q->nr_requests) {
+		blk_clear_queue_full(q, BLK_RW_SYNC);
+		wake_up(&rl->wait[BLK_RW_SYNC]);
 	}
 
-	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]);
+	if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
+		blk_set_queue_full(q, BLK_RW_ASYNC);
+	} else if (rl->count[BLK_RW_ASYNC]+1 <= q->nr_requests) {
+		blk_clear_queue_full(q, BLK_RW_ASYNC);
+		wake_up(&rl->wait[BLK_RW_ASYNC]);
 	}
 	spin_unlock_irq(q->queue_lock);
 	return ret;
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index bbbdc4b8ccf..1ec0d503cac 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -211,6 +211,12 @@ void blk_abort_queue(struct request_queue *q)
 	struct request *rq, *tmp;
 	LIST_HEAD(list);
 
+	/*
+	 * Not a request based block device, nothing to abort
+	 */
+	if (!q->request_fn)
+		return;
+
 	spin_lock_irqsave(q->queue_lock, flags);
 
 	elv_abort_queue(q);
@@ -224,6 +230,13 @@ void blk_abort_queue(struct request_queue *q)
 	list_for_each_entry_safe(rq, tmp, &list, timeout_list)
 		blk_abort_request(rq);
 
+	/*
+	 * Occasionally, blk_abort_request() will return without
+	 * deleting the element from the list. Make sure we add those back
+	 * instead of leaving them on the local stack list.
+	 */
+	list_splice(&list, &q->timeout_list);
+
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
 }
diff --git a/block/blk.h b/block/blk.h
index 0dce92c3749..79c85f7c9ff 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -70,6 +70,10 @@ void blk_queue_congestion_threshold(struct request_queue *q);
 
 int blk_dev_init(void);
 
+void elv_quiesce_start(struct request_queue *q);
+void elv_quiesce_end(struct request_queue *q);
+
+
 /*
  * Return the threshold (number of used requests) at which the queue is
  * considered to be congested.  It include a little hysteresis to keep the
@@ -102,18 +106,15 @@ static inline int blk_cpu_to_group(int cpu)
 	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));
+	return cpumask_first(topology_thread_cpumask(cpu));
 #else
 	return cpu;
 #endif
 }
 
-static inline int blk_do_io_stat(struct request_queue *q)
+static inline int blk_do_io_stat(struct request *rq)
 {
-	if (q)
-		return blk_queue_io_stat(q);
-
-	return 0;
+	return rq->rq_disk && blk_rq_io_stat(rq);
 }
 
 #endif
diff --git a/block/blktrace.c b/block/blktrace.c
deleted file mode 100644
index 028120a0965..00000000000
--- a/block/blktrace.c
+++ /dev/null
@@ -1,860 +0,0 @@
-/*
- * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
- *
- * 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 License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
- */
-#include <linux/kernel.h>
-#include <linux/blkdev.h>
-#include <linux/blktrace_api.h>
-#include <linux/percpu.h>
-#include <linux/init.h>
-#include <linux/mutex.h>
-#include <linux/debugfs.h>
-#include <linux/time.h>
-#include <trace/block.h>
-#include <asm/uaccess.h>
-
-static unsigned int blktrace_seq __read_mostly = 1;
-
-/* Global reference count of probes */
-static DEFINE_MUTEX(blk_probe_mutex);
-static atomic_t blk_probes_ref = ATOMIC_INIT(0);
-
-static int blk_register_tracepoints(void);
-static void blk_unregister_tracepoints(void);
-
-/*
- * Send out a notify message.
- */
-static void trace_note(struct blk_trace *bt, pid_t pid, int action,
-		       const void *data, size_t len)
-{
-	struct blk_io_trace *t;
-
-	t = relay_reserve(bt->rchan, sizeof(*t) + len);
-	if (t) {
-		const int cpu = smp_processor_id();
-
-		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
-		t->time = ktime_to_ns(ktime_get());
-		t->device = bt->dev;
-		t->action = action;
-		t->pid = pid;
-		t->cpu = cpu;
-		t->pdu_len = len;
-		memcpy((void *) t + sizeof(*t), data, len);
-	}
-}
-
-/*
- * Send out a notify for this process, if we haven't done so since a trace
- * started
- */
-static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk)
-{
-	tsk->btrace_seq = blktrace_seq;
-	trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm));
-}
-
-static void trace_note_time(struct blk_trace *bt)
-{
-	struct timespec now;
-	unsigned long flags;
-	u32 words[2];
-
-	getnstimeofday(&now);
-	words[0] = now.tv_sec;
-	words[1] = now.tv_nsec;
-
-	local_irq_save(flags);
-	trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words));
-	local_irq_restore(flags);
-}
-
-void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
-{
-	int n;
-	va_list args;
-	unsigned long flags;
-	char *buf;
-
-	local_irq_save(flags);
-	buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
-	va_start(args, fmt);
-	n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
-	va_end(args);
-
-	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(__trace_note_message);
-
-static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
-			 pid_t pid)
-{
-	if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
-		return 1;
-	if (sector < bt->start_lba || sector > bt->end_lba)
-		return 1;
-	if (bt->pid && pid != bt->pid)
-		return 1;
-
-	return 0;
-}
-
-/*
- * Data direction bit lookup
- */
-static u32 ddir_act[2] __read_mostly = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) };
-
-/* The ilog2() calls fall out because they're constant */
-#define MASK_TC_BIT(rw, __name) ( (rw & (1 << BIO_RW_ ## __name)) << \
-	  (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - BIO_RW_ ## __name) )
-
-/*
- * The worker for the various blk_add_trace*() types. Fills out a
- * blk_io_trace structure and places it in a per-cpu subbuffer.
- */
-static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
-		     int rw, u32 what, int error, int pdu_len, void *pdu_data)
-{
-	struct task_struct *tsk = current;
-	struct blk_io_trace *t;
-	unsigned long flags;
-	unsigned long *sequence;
-	pid_t pid;
-	int cpu;
-
-	if (unlikely(bt->trace_state != Blktrace_running))
-		return;
-
-	what |= ddir_act[rw & WRITE];
-	what |= MASK_TC_BIT(rw, BARRIER);
-	what |= MASK_TC_BIT(rw, SYNCIO);
-	what |= MASK_TC_BIT(rw, AHEAD);
-	what |= MASK_TC_BIT(rw, META);
-	what |= MASK_TC_BIT(rw, DISCARD);
-
-	pid = tsk->pid;
-	if (unlikely(act_log_check(bt, what, sector, pid)))
-		return;
-
-	/*
-	 * A word about the locking here - we disable interrupts to reserve
-	 * some space in the relay per-cpu buffer, to prevent an irq
-	 * from coming in and stepping on our toes.
-	 */
-	local_irq_save(flags);
-
-	if (unlikely(tsk->btrace_seq != blktrace_seq))
-		trace_note_tsk(bt, tsk);
-
-	t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len);
-	if (t) {
-		cpu = smp_processor_id();
-		sequence = per_cpu_ptr(bt->sequence, cpu);
-
-		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
-		t->sequence = ++(*sequence);
-		t->time = ktime_to_ns(ktime_get());
-		t->sector = sector;
-		t->bytes = bytes;
-		t->action = what;
-		t->pid = pid;
-		t->device = bt->dev;
-		t->cpu = cpu;
-		t->error = error;
-		t->pdu_len = pdu_len;
-
-		if (pdu_len)
-			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
-	}
-
-	local_irq_restore(flags);
-}
-
-static struct dentry *blk_tree_root;
-static DEFINE_MUTEX(blk_tree_mutex);
-
-static void blk_trace_cleanup(struct blk_trace *bt)
-{
-	debugfs_remove(bt->msg_file);
-	debugfs_remove(bt->dropped_file);
-	relay_close(bt->rchan);
-	free_percpu(bt->sequence);
-	free_percpu(bt->msg_data);
-	kfree(bt);
-	mutex_lock(&blk_probe_mutex);
-	if (atomic_dec_and_test(&blk_probes_ref))
-		blk_unregister_tracepoints();
-	mutex_unlock(&blk_probe_mutex);
-}
-
-int blk_trace_remove(struct request_queue *q)
-{
-	struct blk_trace *bt;
-
-	bt = xchg(&q->blk_trace, NULL);
-	if (!bt)
-		return -EINVAL;
-
-	if (bt->trace_state == Blktrace_setup ||
-	    bt->trace_state == Blktrace_stopped)
-		blk_trace_cleanup(bt);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blk_trace_remove);
-
-static int blk_dropped_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-
-	return 0;
-}
-
-static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	struct blk_trace *bt = filp->private_data;
-	char buf[16];
-
-	snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped));
-
-	return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
-}
-
-static const struct file_operations blk_dropped_fops = {
-	.owner =	THIS_MODULE,
-	.open =		blk_dropped_open,
-	.read =		blk_dropped_read,
-};
-
-static int blk_msg_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-
-	return 0;
-}
-
-static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	char *msg;
-	struct blk_trace *bt;
-
-	if (count > BLK_TN_MAX_MSG)
-		return -EINVAL;
-
-	msg = kmalloc(count, GFP_KERNEL);
-	if (msg == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(msg, buffer, count)) {
-		kfree(msg);
-		return -EFAULT;
-	}
-
-	bt = filp->private_data;
-	__trace_note_message(bt, "%s", msg);
-	kfree(msg);
-
-	return count;
-}
-
-static const struct file_operations blk_msg_fops = {
-	.owner =	THIS_MODULE,
-	.open =		blk_msg_open,
-	.write =	blk_msg_write,
-};
-
-/*
- * Keep track of how many times we encountered a full subbuffer, to aid
- * the user space app in telling how many lost events there were.
- */
-static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
-				     void *prev_subbuf, size_t prev_padding)
-{
-	struct blk_trace *bt;
-
-	if (!relay_buf_full(buf))
-		return 1;
-
-	bt = buf->chan->private_data;
-	atomic_inc(&bt->dropped);
-	return 0;
-}
-
-static int blk_remove_buf_file_callback(struct dentry *dentry)
-{
-	struct dentry *parent = dentry->d_parent;
-	debugfs_remove(dentry);
-
-	/*
-	* this will fail for all but the last file, but that is ok. what we
-	* care about is the top level buts->name directory going away, when
-	* the last trace file is gone. Then we don't have to rmdir() that
-	* manually on trace stop, so it nicely solves the issue with
-	* force killing of running traces.
-	*/
-
-	debugfs_remove(parent);
-	return 0;
-}
-
-static struct dentry *blk_create_buf_file_callback(const char *filename,
-						   struct dentry *parent,
-						   int mode,
-						   struct rchan_buf *buf,
-						   int *is_global)
-{
-	return debugfs_create_file(filename, mode, parent, buf,
-					&relay_file_operations);
-}
-
-static struct rchan_callbacks blk_relay_callbacks = {
-	.subbuf_start		= blk_subbuf_start_callback,
-	.create_buf_file	= blk_create_buf_file_callback,
-	.remove_buf_file	= blk_remove_buf_file_callback,
-};
-
-/*
- * Setup everything required to start tracing
- */
-int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
-			struct blk_user_trace_setup *buts)
-{
-	struct blk_trace *old_bt, *bt = NULL;
-	struct dentry *dir = NULL;
-	int ret, i;
-
-	if (!buts->buf_size || !buts->buf_nr)
-		return -EINVAL;
-
-	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
-	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
-
-	/*
-	 * some device names have larger paths - convert the slashes
-	 * to underscores for this to work as expected
-	 */
-	for (i = 0; i < strlen(buts->name); i++)
-		if (buts->name[i] == '/')
-			buts->name[i] = '_';
-
-	ret = -ENOMEM;
-	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
-	if (!bt)
-		goto err;
-
-	bt->sequence = alloc_percpu(unsigned long);
-	if (!bt->sequence)
-		goto err;
-
-	bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
-	if (!bt->msg_data)
-		goto err;
-
-	ret = -ENOENT;
-
-	if (!blk_tree_root) {
-		blk_tree_root = debugfs_create_dir("block", NULL);
-		if (!blk_tree_root)
-			return -ENOMEM;
-	}
-
-	dir = debugfs_create_dir(buts->name, blk_tree_root);
-
-	if (!dir)
-		goto err;
-
-	bt->dir = dir;
-	bt->dev = dev;
-	atomic_set(&bt->dropped, 0);
-
-	ret = -EIO;
-	bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops);
-	if (!bt->dropped_file)
-		goto err;
-
-	bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
-	if (!bt->msg_file)
-		goto err;
-
-	bt->rchan = relay_open("trace", dir, buts->buf_size,
-				buts->buf_nr, &blk_relay_callbacks, bt);
-	if (!bt->rchan)
-		goto err;
-
-	bt->act_mask = buts->act_mask;
-	if (!bt->act_mask)
-		bt->act_mask = (u16) -1;
-
-	bt->start_lba = buts->start_lba;
-	bt->end_lba = buts->end_lba;
-	if (!bt->end_lba)
-		bt->end_lba = -1ULL;
-
-	bt->pid = buts->pid;
-	bt->trace_state = Blktrace_setup;
-
-	mutex_lock(&blk_probe_mutex);
-	if (atomic_add_return(1, &blk_probes_ref) == 1) {
-		ret = blk_register_tracepoints();
-		if (ret)
-			goto probe_err;
-	}
-	mutex_unlock(&blk_probe_mutex);
-
-	ret = -EBUSY;
-	old_bt = xchg(&q->blk_trace, bt);
-	if (old_bt) {
-		(void) xchg(&q->blk_trace, old_bt);
-		goto err;
-	}
-
-	return 0;
-probe_err:
-	atomic_dec(&blk_probes_ref);
-	mutex_unlock(&blk_probe_mutex);
-err:
-	if (bt) {
-		if (bt->msg_file)
-			debugfs_remove(bt->msg_file);
-		if (bt->dropped_file)
-			debugfs_remove(bt->dropped_file);
-		free_percpu(bt->sequence);
-		free_percpu(bt->msg_data);
-		if (bt->rchan)
-			relay_close(bt->rchan);
-		kfree(bt);
-	}
-	return ret;
-}
-
-int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
-		    char __user *arg)
-{
-	struct blk_user_trace_setup buts;
-	int ret;
-
-	ret = copy_from_user(&buts, arg, sizeof(buts));
-	if (ret)
-		return -EFAULT;
-
-	ret = do_blk_trace_setup(q, name, dev, &buts);
-	if (ret)
-		return ret;
-
-	if (copy_to_user(arg, &buts, sizeof(buts)))
-		return -EFAULT;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blk_trace_setup);
-
-int blk_trace_startstop(struct request_queue *q, int start)
-{
-	struct blk_trace *bt;
-	int ret;
-
-	if ((bt = q->blk_trace) == NULL)
-		return -EINVAL;
-
-	/*
-	 * For starting a trace, we can transition from a setup or stopped
-	 * trace. For stopping a trace, the state must be running
-	 */
-	ret = -EINVAL;
-	if (start) {
-		if (bt->trace_state == Blktrace_setup ||
-		    bt->trace_state == Blktrace_stopped) {
-			blktrace_seq++;
-			smp_mb();
-			bt->trace_state = Blktrace_running;
-
-			trace_note_time(bt);
-			ret = 0;
-		}
-	} else {
-		if (bt->trace_state == Blktrace_running) {
-			bt->trace_state = Blktrace_stopped;
-			relay_flush(bt->rchan);
-			ret = 0;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(blk_trace_startstop);
-
-/**
- * blk_trace_ioctl: - handle the ioctls associated with tracing
- * @bdev:	the block device
- * @cmd: 	the ioctl cmd
- * @arg:	the argument data, if any
- *
- **/
-int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
-{
-	struct request_queue *q;
-	int ret, start = 0;
-	char b[BDEVNAME_SIZE];
-
-	q = bdev_get_queue(bdev);
-	if (!q)
-		return -ENXIO;
-
-	mutex_lock(&bdev->bd_mutex);
-
-	switch (cmd) {
-	case BLKTRACESETUP:
-		bdevname(bdev, b);
-		ret = blk_trace_setup(q, b, bdev->bd_dev, arg);
-		break;
-	case BLKTRACESTART:
-		start = 1;
-	case BLKTRACESTOP:
-		ret = blk_trace_startstop(q, start);
-		break;
-	case BLKTRACETEARDOWN:
-		ret = blk_trace_remove(q);
-		break;
-	default:
-		ret = -ENOTTY;
-		break;
-	}
-
-	mutex_unlock(&bdev->bd_mutex);
-	return ret;
-}
-
-/**
- * blk_trace_shutdown: - stop and cleanup trace structures
- * @q:    the request queue associated with the device
- *
- **/
-void blk_trace_shutdown(struct request_queue *q)
-{
-	if (q->blk_trace) {
-		blk_trace_startstop(q, 0);
-		blk_trace_remove(q);
-	}
-}
-
-/*
- * blktrace probes
- */
-
-/**
- * blk_add_trace_rq - Add a trace for a request oriented action
- * @q:		queue the io is for
- * @rq:		the source request
- * @what:	the action
- *
- * Description:
- *     Records an action against a request. Will log the bio offset + size.
- *
- **/
-static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
-				    u32 what)
-{
-	struct blk_trace *bt = q->blk_trace;
-	int rw = rq->cmd_flags & 0x03;
-
-	if (likely(!bt))
-		return;
-
-	if (blk_discard_rq(rq))
-		rw |= (1 << BIO_RW_DISCARD);
-
-	if (blk_pc_request(rq)) {
-		what |= BLK_TC_ACT(BLK_TC_PC);
-		__blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors,
-				sizeof(rq->cmd), rq->cmd);
-	} else  {
-		what |= BLK_TC_ACT(BLK_TC_FS);
-		__blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
-				rw, what, rq->errors, 0, NULL);
-	}
-}
-
-static void blk_add_trace_rq_abort(struct request_queue *q, struct request *rq)
-{
-	blk_add_trace_rq(q, rq, BLK_TA_ABORT);
-}
-
-static void blk_add_trace_rq_insert(struct request_queue *q, struct request *rq)
-{
-	blk_add_trace_rq(q, rq, BLK_TA_INSERT);
-}
-
-static void blk_add_trace_rq_issue(struct request_queue *q, struct request *rq)
-{
-	blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
-}
-
-static void blk_add_trace_rq_requeue(struct request_queue *q, struct request *rq)
-{
-	blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
-}
-
-static void blk_add_trace_rq_complete(struct request_queue *q, struct request *rq)
-{
-	blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
-}
-
-/**
- * blk_add_trace_bio - Add a trace for a bio oriented action
- * @q:		queue the io is for
- * @bio:	the source bio
- * @what:	the action
- *
- * Description:
- *     Records an action against a bio. Will log the bio offset + size.
- *
- **/
-static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
-				     u32 what)
-{
-	struct blk_trace *bt = q->blk_trace;
-
-	if (likely(!bt))
-		return;
-
-	__blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what,
-			!bio_flagged(bio, BIO_UPTODATE), 0, NULL);
-}
-
-static void blk_add_trace_bio_bounce(struct request_queue *q, struct bio *bio)
-{
-	blk_add_trace_bio(q, bio, BLK_TA_BOUNCE);
-}
-
-static void blk_add_trace_bio_complete(struct request_queue *q, struct bio *bio)
-{
-	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE);
-}
-
-static void blk_add_trace_bio_backmerge(struct request_queue *q, struct bio *bio)
-{
-	blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
-}
-
-static void blk_add_trace_bio_frontmerge(struct request_queue *q, struct bio *bio)
-{
-	blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
-}
-
-static void blk_add_trace_bio_queue(struct request_queue *q, struct bio *bio)
-{
-	blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
-}
-
-static void blk_add_trace_getrq(struct request_queue *q, struct bio *bio, int rw)
-{
-	if (bio)
-		blk_add_trace_bio(q, bio, BLK_TA_GETRQ);
-	else {
-		struct blk_trace *bt = q->blk_trace;
-
-		if (bt)
-			__blk_add_trace(bt, 0, 0, rw, BLK_TA_GETRQ, 0, 0, NULL);
-	}
-}
-
-
-static void blk_add_trace_sleeprq(struct request_queue *q, struct bio *bio, int rw)
-{
-	if (bio)
-		blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ);
-	else {
-		struct blk_trace *bt = q->blk_trace;
-
-		if (bt)
-			__blk_add_trace(bt, 0, 0, rw, BLK_TA_SLEEPRQ, 0, 0, NULL);
-	}
-}
-
-static void blk_add_trace_plug(struct request_queue *q)
-{
-	struct blk_trace *bt = q->blk_trace;
-
-	if (bt)
-		__blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
-}
-
-static void blk_add_trace_unplug_io(struct request_queue *q)
-{
-	struct blk_trace *bt = q->blk_trace;
-
-	if (bt) {
-		unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE];
-		__be64 rpdu = cpu_to_be64(pdu);
-
-		__blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_IO, 0,
-				sizeof(rpdu), &rpdu);
-	}
-}
-
-static void blk_add_trace_unplug_timer(struct request_queue *q)
-{
-	struct blk_trace *bt = q->blk_trace;
-
-	if (bt) {
-		unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE];
-		__be64 rpdu = cpu_to_be64(pdu);
-
-		__blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_TIMER, 0,
-				sizeof(rpdu), &rpdu);
-	}
-}
-
-static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
-				unsigned int pdu)
-{
-	struct blk_trace *bt = q->blk_trace;
-
-	if (bt) {
-		__be64 rpdu = cpu_to_be64(pdu);
-
-		__blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
-				BLK_TA_SPLIT, !bio_flagged(bio, BIO_UPTODATE),
-				sizeof(rpdu), &rpdu);
-	}
-}
-
-/**
- * blk_add_trace_remap - Add a trace for a remap operation
- * @q:		queue the io is for
- * @bio:	the source bio
- * @dev:	target device
- * @from:	source sector
- * @to:		target sector
- *
- * Description:
- *     Device mapper or raid target sometimes need to split a bio because
- *     it spans a stripe (or similar). Add a trace for that action.
- *
- **/
-static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
-				       dev_t dev, sector_t from, sector_t to)
-{
-	struct blk_trace *bt = q->blk_trace;
-	struct blk_io_trace_remap r;
-
-	if (likely(!bt))
-		return;
-
-	r.device = cpu_to_be32(dev);
-	r.device_from = cpu_to_be32(bio->bi_bdev->bd_dev);
-	r.sector = cpu_to_be64(to);
-
-	__blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP,
-			!bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
-}
-
-/**
- * blk_add_driver_data - Add binary message with driver-specific data
- * @q:		queue the io is for
- * @rq:		io request
- * @data:	driver-specific data
- * @len:	length of driver-specific data
- *
- * Description:
- *     Some drivers might want to write driver-specific data per request.
- *
- **/
-void blk_add_driver_data(struct request_queue *q,
-			 struct request *rq,
-			 void *data, size_t len)
-{
-	struct blk_trace *bt = q->blk_trace;
-
-	if (likely(!bt))
-		return;
-
-	if (blk_pc_request(rq))
-		__blk_add_trace(bt, 0, rq->data_len, 0, BLK_TA_DRV_DATA,
-				rq->errors, len, data);
-	else
-		__blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
-				0, BLK_TA_DRV_DATA, rq->errors, len, data);
-}
-EXPORT_SYMBOL_GPL(blk_add_driver_data);
-
-static int blk_register_tracepoints(void)
-{
-	int ret;
-
-	ret = register_trace_block_rq_abort(blk_add_trace_rq_abort);
-	WARN_ON(ret);
-	ret = register_trace_block_rq_insert(blk_add_trace_rq_insert);
-	WARN_ON(ret);
-	ret = register_trace_block_rq_issue(blk_add_trace_rq_issue);
-	WARN_ON(ret);
-	ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue);
-	WARN_ON(ret);
-	ret = register_trace_block_rq_complete(blk_add_trace_rq_complete);
-	WARN_ON(ret);
-	ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce);
-	WARN_ON(ret);
-	ret = register_trace_block_bio_complete(blk_add_trace_bio_complete);
-	WARN_ON(ret);
-	ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
-	WARN_ON(ret);
-	ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
-	WARN_ON(ret);
-	ret = register_trace_block_bio_queue(blk_add_trace_bio_queue);
-	WARN_ON(ret);
-	ret = register_trace_block_getrq(blk_add_trace_getrq);
-	WARN_ON(ret);
-	ret = register_trace_block_sleeprq(blk_add_trace_sleeprq);
-	WARN_ON(ret);
-	ret = register_trace_block_plug(blk_add_trace_plug);
-	WARN_ON(ret);
-	ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer);
-	WARN_ON(ret);
-	ret = register_trace_block_unplug_io(blk_add_trace_unplug_io);
-	WARN_ON(ret);
-	ret = register_trace_block_split(blk_add_trace_split);
-	WARN_ON(ret);
-	ret = register_trace_block_remap(blk_add_trace_remap);
-	WARN_ON(ret);
-	return 0;
-}
-
-static void blk_unregister_tracepoints(void)
-{
-	unregister_trace_block_remap(blk_add_trace_remap);
-	unregister_trace_block_split(blk_add_trace_split);
-	unregister_trace_block_unplug_io(blk_add_trace_unplug_io);
-	unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer);
-	unregister_trace_block_plug(blk_add_trace_plug);
-	unregister_trace_block_sleeprq(blk_add_trace_sleeprq);
-	unregister_trace_block_getrq(blk_add_trace_getrq);
-	unregister_trace_block_bio_queue(blk_add_trace_bio_queue);
-	unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
-	unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
-	unregister_trace_block_bio_complete(blk_add_trace_bio_complete);
-	unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce);
-	unregister_trace_block_rq_complete(blk_add_trace_rq_complete);
-	unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue);
-	unregister_trace_block_rq_issue(blk_add_trace_rq_issue);
-	unregister_trace_block_rq_insert(blk_add_trace_rq_insert);
-	unregister_trace_block_rq_abort(blk_add_trace_rq_abort);
-
-	tracepoint_synchronize_unregister();
-}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 664ebfd092e..a55a9bd75bd 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -56,9 +56,6 @@ static DEFINE_SPINLOCK(ioc_gone_lock);
 #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)
 
 /*
@@ -83,6 +80,14 @@ struct cfq_data {
 	 * rr list of queues with requests and the count of them
 	 */
 	struct cfq_rb_root service_tree;
+
+	/*
+	 * Each priority tree is sorted by next_request position.  These
+	 * trees are used when determining if two or more queues are
+	 * interleaving requests (see cfq_close_cooperator).
+	 */
+	struct rb_root prio_trees[CFQ_PRIO_LISTS];
+
 	unsigned int busy_queues;
 	/*
 	 * Used to track any pending rt requests so we can pre-empt current
@@ -147,6 +152,10 @@ struct cfq_queue {
 	struct rb_node rb_node;
 	/* service_tree key */
 	unsigned long rb_key;
+	/* prio tree member */
+	struct rb_node p_node;
+	/* prio tree root we belong to, if any */
+	struct rb_root *p_root;
 	/* sorted list of pending requests */
 	struct rb_root sort_list;
 	/* if fifo isn't expired, next request to serve */
@@ -160,6 +169,7 @@ struct cfq_queue {
 
 	unsigned long slice_end;
 	long slice_resid;
+	unsigned int slice_dispatch;
 
 	/* pending metadata requests */
 	int meta_pending;
@@ -176,15 +186,15 @@ struct cfq_queue {
 enum cfqq_state_flags {
 	CFQ_CFQQ_FLAG_on_rr = 0,	/* on round-robin busy list */
 	CFQ_CFQQ_FLAG_wait_request,	/* waiting for a request */
+	CFQ_CFQQ_FLAG_must_dispatch,	/* must be allowed a dispatch */
 	CFQ_CFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
 	CFQ_CFQQ_FLAG_must_alloc_slice,	/* per-slice must_alloc flag */
-	CFQ_CFQQ_FLAG_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 */
+	CFQ_CFQQ_FLAG_coop,		/* has done a coop jump of the queue */
 };
 
 #define CFQ_CFQQ_FNS(name)						\
@@ -203,15 +213,15 @@ static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq)		\
 
 CFQ_CFQQ_FNS(on_rr);
 CFQ_CFQQ_FNS(wait_request);
+CFQ_CFQQ_FNS(must_dispatch);
 CFQ_CFQQ_FNS(must_alloc);
 CFQ_CFQQ_FNS(must_alloc_slice);
-CFQ_CFQQ_FNS(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);
+CFQ_CFQQ_FNS(coop);
 #undef CFQ_CFQQ_FNS
 
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
@@ -420,13 +430,17 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
 	return NULL;
 }
 
+static void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+
 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);
+	rb_erase_init(n, &root->rb);
 }
 
 /*
@@ -471,8 +485,8 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
  * 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)
+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;
@@ -545,6 +559,67 @@ static void cfq_service_tree_add(struct cfq_data *cfqd,
 	rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb);
 }
 
+static struct cfq_queue *
+cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root,
+		     sector_t sector, struct rb_node **ret_parent,
+		     struct rb_node ***rb_link)
+{
+	struct rb_node **p, *parent;
+	struct cfq_queue *cfqq = NULL;
+
+	parent = NULL;
+	p = &root->rb_node;
+	while (*p) {
+		struct rb_node **n;
+
+		parent = *p;
+		cfqq = rb_entry(parent, struct cfq_queue, p_node);
+
+		/*
+		 * Sort strictly based on sector.  Smallest to the left,
+		 * largest to the right.
+		 */
+		if (sector > cfqq->next_rq->sector)
+			n = &(*p)->rb_right;
+		else if (sector < cfqq->next_rq->sector)
+			n = &(*p)->rb_left;
+		else
+			break;
+		p = n;
+		cfqq = NULL;
+	}
+
+	*ret_parent = parent;
+	if (rb_link)
+		*rb_link = p;
+	return cfqq;
+}
+
+static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	struct rb_node **p, *parent;
+	struct cfq_queue *__cfqq;
+
+	if (cfqq->p_root) {
+		rb_erase(&cfqq->p_node, cfqq->p_root);
+		cfqq->p_root = NULL;
+	}
+
+	if (cfq_class_idle(cfqq))
+		return;
+	if (!cfqq->next_rq)
+		return;
+
+	cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio];
+	__cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root, cfqq->next_rq->sector,
+					 &parent, &p);
+	if (!__cfqq) {
+		rb_link_node(&cfqq->p_node, parent, p);
+		rb_insert_color(&cfqq->p_node, cfqq->p_root);
+	} else
+		cfqq->p_root = NULL;
+}
+
 /*
  * Update cfqq's position in the service tree.
  */
@@ -553,8 +628,10 @@ 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))
+	if (cfq_cfqq_on_rr(cfqq)) {
 		cfq_service_tree_add(cfqd, cfqq, 0);
+		cfq_prio_tree_add(cfqd, cfqq);
+	}
 }
 
 /*
@@ -585,6 +662,10 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
 	if (!RB_EMPTY_NODE(&cfqq->rb_node))
 		cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
+	if (cfqq->p_root) {
+		rb_erase(&cfqq->p_node, cfqq->p_root);
+		cfqq->p_root = NULL;
+	}
 
 	BUG_ON(!cfqd->busy_queues);
 	cfqd->busy_queues--;
@@ -614,7 +695,7 @@ 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;
+	struct request *__alias, *prev;
 
 	cfqq->queued[rq_is_sync(rq)]++;
 
@@ -631,7 +712,15 @@ static void cfq_add_rq_rb(struct request *rq)
 	/*
 	 * check if this request is a better next-serve candidate
 	 */
+	prev = cfqq->next_rq;
 	cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq);
+
+	/*
+	 * adjust priority tree position, if ->next_rq changes
+	 */
+	if (prev != cfqq->next_rq)
+		cfq_prio_tree_add(cfqd, cfqq);
+
 	BUG_ON(!cfqq->next_rq);
 }
 
@@ -774,10 +863,15 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 	if (cfqq) {
 		cfq_log_cfqq(cfqd, cfqq, "set_active");
 		cfqq->slice_end = 0;
+		cfqq->slice_dispatch = 0;
+
+		cfq_clear_cfqq_wait_request(cfqq);
+		cfq_clear_cfqq_must_dispatch(cfqq);
 		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);
+
+		del_timer(&cfqd->idle_slice_timer);
 	}
 
 	cfqd->active_queue = cfqq;
@@ -795,7 +889,6 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	if (cfq_cfqq_wait_request(cfqq))
 		del_timer(&cfqd->idle_slice_timer);
 
-	cfq_clear_cfqq_must_dispatch(cfqq);
 	cfq_clear_cfqq_wait_request(cfqq);
 
 	/*
@@ -840,11 +933,15 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
 /*
  * Get and set a new active queue for service.
  */
-static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd)
+static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
+					      struct cfq_queue *cfqq)
 {
-	struct cfq_queue *cfqq;
+	if (!cfqq) {
+		cfqq = cfq_get_next_queue(cfqd);
+		if (cfqq)
+			cfq_clear_cfqq_coop(cfqq);
+	}
 
-	cfqq = cfq_get_next_queue(cfqd);
 	__cfq_set_active_queue(cfqd, cfqq);
 	return cfqq;
 }
@@ -858,28 +955,100 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 		return cfqd->last_position - rq->sector;
 }
 
+#define CIC_SEEK_THR	8 * 1024
+#define CIC_SEEKY(cic)	((cic)->seek_mean > CIC_SEEK_THR)
+
 static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq)
 {
 	struct cfq_io_context *cic = cfqd->active_cic;
+	sector_t sdist = cic->seek_mean;
 
 	if (!sample_valid(cic->seek_samples))
-		return 0;
+		sdist = CIC_SEEK_THR;
 
-	return cfq_dist_from_last(cfqd, rq) <= cic->seek_mean;
+	return cfq_dist_from_last(cfqd, rq) <= sdist;
 }
 
-static int cfq_close_cooperator(struct cfq_data *cfq_data,
-				struct cfq_queue *cfqq)
+static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
+				    struct cfq_queue *cur_cfqq)
 {
+	struct rb_root *root = &cfqd->prio_trees[cur_cfqq->org_ioprio];
+	struct rb_node *parent, *node;
+	struct cfq_queue *__cfqq;
+	sector_t sector = cfqd->last_position;
+
+	if (RB_EMPTY_ROOT(root))
+		return NULL;
+
+	/*
+	 * First, if we find a request starting at the end of the last
+	 * request, choose it.
+	 */
+	__cfqq = cfq_prio_tree_lookup(cfqd, root, sector, &parent, NULL);
+	if (__cfqq)
+		return __cfqq;
+
+	/*
+	 * If the exact sector wasn't found, the parent of the NULL leaf
+	 * will contain the closest sector.
+	 */
+	__cfqq = rb_entry(parent, struct cfq_queue, p_node);
+	if (cfq_rq_close(cfqd, __cfqq->next_rq))
+		return __cfqq;
+
+	if (__cfqq->next_rq->sector < sector)
+		node = rb_next(&__cfqq->p_node);
+	else
+		node = rb_prev(&__cfqq->p_node);
+	if (!node)
+		return NULL;
+
+	__cfqq = rb_entry(node, struct cfq_queue, p_node);
+	if (cfq_rq_close(cfqd, __cfqq->next_rq))
+		return __cfqq;
+
+	return NULL;
+}
+
+/*
+ * cfqd - obvious
+ * cur_cfqq - passed in so that we don't decide that the current queue is
+ * 	      closely cooperating with itself.
+ *
+ * So, basically we're assuming that that cur_cfqq has dispatched at least
+ * one request, and that cfqd->last_position reflects a position on the disk
+ * associated with the I/O issued by cur_cfqq.  I'm not sure this is a valid
+ * assumption.
+ */
+static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
+					      struct cfq_queue *cur_cfqq,
+					      int probe)
+{
+	struct cfq_queue *cfqq;
+
+	/*
+	 * A valid cfq_io_context is necessary to compare requests against
+	 * the seek_mean of the current cfqq.
+	 */
+	if (!cfqd->active_cic)
+		return NULL;
+
 	/*
 	 * 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;
-}
+	cfqq = cfqq_close(cfqd, cur_cfqq);
+	if (!cfqq)
+		return NULL;
 
-#define CIC_SEEKY(cic) ((cic)->seek_mean > (8 * 1024))
+	if (cfq_cfqq_coop(cfqq))
+		return NULL;
+
+	if (!probe)
+		cfq_mark_cfqq_coop(cfqq);
+	return cfqq;
+}
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 {
@@ -917,14 +1086,6 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	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);
 
 	/*
@@ -937,7 +1098,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 		sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT));
 
 	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
-	cfq_log(cfqd, "arm_idle: %lu", sl);
+	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
 }
 
 /*
@@ -1001,7 +1162,7 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  */
 static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 {
-	struct cfq_queue *cfqq;
+	struct cfq_queue *cfqq, *new_cfqq = NULL;
 
 	cfqq = cfqd->active_queue;
 	if (!cfqq)
@@ -1010,7 +1171,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	/*
 	 * The active queue has run out of time, expire it and select new.
 	 */
-	if (cfq_slice_used(cfqq))
+	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
 		goto expire;
 
 	/*
@@ -1035,6 +1196,16 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 		goto keep_queue;
 
 	/*
+	 * If another queue has a request waiting within our mean seek
+	 * distance, let it run.  The expire code will check for close
+	 * cooperators and put the close queue at the front of the service
+	 * tree.
+	 */
+	new_cfqq = cfq_close_cooperator(cfqd, cfqq, 0);
+	if (new_cfqq)
+		goto expire;
+
+	/*
 	 * 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.
@@ -1048,71 +1219,11 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 expire:
 	cfq_slice_expired(cfqd, 0);
 new_queue:
-	cfqq = cfq_set_active_queue(cfqd);
+	cfqq = cfq_set_active_queue(cfqd, new_cfqq);
 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;
@@ -1146,11 +1257,45 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 	return dispatched;
 }
 
+/*
+ * Dispatch a request from cfqq, moving them to the request queue
+ * dispatch list.
+ */
+static void cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	struct request *rq;
+
+	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
+
+	/*
+	 * follow expired path, else get first next available
+	 */
+	rq = cfq_check_fifo(cfqq);
+	if (!rq)
+		rq = cfqq->next_rq;
+
+	/*
+	 * insert request into driver dispatch list
+	 */
+	cfq_dispatch_insert(cfqd->queue, rq);
+
+	if (!cfqd->active_cic) {
+		struct cfq_io_context *cic = RQ_CIC(rq);
+
+		atomic_inc(&cic->ioc->refcount);
+		cfqd->active_cic = cic;
+	}
+}
+
+/*
+ * Find the cfqq that we need to service and move a request from that to the
+ * dispatch list
+ */
 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;
+	unsigned int max_dispatch;
 
 	if (!cfqd->busy_queues)
 		return 0;
@@ -1158,29 +1303,63 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 	if (unlikely(force))
 		return cfq_forced_dispatch(cfqd);
 
-	dispatched = 0;
-	while ((cfqq = cfq_select_queue(cfqd)) != NULL) {
-		int max_dispatch;
+	cfqq = cfq_select_queue(cfqd);
+	if (!cfqq)
+		return 0;
 
-		max_dispatch = cfqd->cfq_quantum;
+	/*
+	 * If this is an async queue and we have sync IO in flight, let it wait
+	 */
+	if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
+		return 0;
+
+	max_dispatch = cfqd->cfq_quantum;
+	if (cfq_class_idle(cfqq))
+		max_dispatch = 1;
+
+	/*
+	 * Does this cfqq already have too much IO in flight?
+	 */
+	if (cfqq->dispatched >= max_dispatch) {
+		/*
+		 * idle queue must always only have a single IO in flight
+		 */
 		if (cfq_class_idle(cfqq))
-			max_dispatch = 1;
+			return 0;
 
-		if (cfqq->dispatched >= max_dispatch && cfqd->busy_queues > 1)
-			break;
+		/*
+		 * We have other queues, don't allow more IO from this one
+		 */
+		if (cfqd->busy_queues > 1)
+			return 0;
 
-		if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
-			break;
+		/*
+		 * we are the only queue, allow up to 4 times of 'quantum'
+		 */
+		if (cfqq->dispatched >= 4 * max_dispatch)
+			return 0;
+	}
 
-		cfq_clear_cfqq_must_dispatch(cfqq);
-		cfq_clear_cfqq_wait_request(cfqq);
-		del_timer(&cfqd->idle_slice_timer);
+	/*
+	 * Dispatch a request from this cfqq
+	 */
+	cfq_dispatch_request(cfqd, cfqq);
+	cfqq->slice_dispatch++;
+	cfq_clear_cfqq_must_dispatch(cfqq);
 
-		dispatched += __cfq_dispatch_requests(cfqd, cfqq, 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) &&
+	    cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
+	    cfq_class_idle(cfqq))) {
+		cfqq->slice_end = jiffies + 1;
+		cfq_slice_expired(cfqd, 0);
 	}
 
-	cfq_log(cfqd, "dispatched=%d", dispatched);
-	return dispatched;
+	cfq_log(cfqd, "dispatched a request");
+	return 1;
 }
 
 /*
@@ -1323,14 +1502,14 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
 	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[BLK_RW_ASYNC]) {
+		cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]);
+		cic->cfqq[BLK_RW_ASYNC] = NULL;
 	}
 
-	if (cic->cfqq[SYNC]) {
-		cfq_exit_cfqq(cfqd, cic->cfqq[SYNC]);
-		cic->cfqq[SYNC] = NULL;
+	if (cic->cfqq[BLK_RW_SYNC]) {
+		cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_SYNC]);
+		cic->cfqq[BLK_RW_SYNC] = NULL;
 	}
 }
 
@@ -1439,17 +1618,18 @@ static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic)
 
 	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
 
-	cfqq = cic->cfqq[ASYNC];
+	cfqq = cic->cfqq[BLK_RW_ASYNC];
 	if (cfqq) {
 		struct cfq_queue *new_cfqq;
-		new_cfqq = cfq_get_queue(cfqd, ASYNC, cic->ioc, GFP_ATOMIC);
+		new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic->ioc,
+						GFP_ATOMIC);
 		if (new_cfqq) {
-			cic->cfqq[ASYNC] = new_cfqq;
+			cic->cfqq[BLK_RW_ASYNC] = new_cfqq;
 			cfq_put_queue(cfqq);
 		}
 	}
 
-	cfqq = cic->cfqq[SYNC];
+	cfqq = cic->cfqq[BLK_RW_SYNC];
 	if (cfqq)
 		cfq_mark_cfqq_prio_changed(cfqq);
 
@@ -1500,13 +1680,13 @@ retry:
 		}
 
 		RB_CLEAR_NODE(&cfqq->rb_node);
+		RB_CLEAR_NODE(&cfqq->p_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);
 
@@ -1736,7 +1916,9 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,
 	sector_t sdist;
 	u64 total;
 
-	if (cic->last_request_pos < rq->sector)
+	if (!cic->last_request_pos)
+		sdist = 0;
+	else if (cic->last_request_pos < rq->sector)
 		sdist = rq->sector - cic->last_request_pos;
 	else
 		sdist = cic->last_request_pos - rq->sector;
@@ -1893,14 +2075,22 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 
 	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
+		 * Remember that we saw a request from this process, but
+		 * don't start queuing just yet. Otherwise we risk seeing lots
+		 * of tiny requests, because we disrupt the normal plugging
+		 * and merging. If the request is already larger than a single
+		 * page, let it rip immediately. For that case we assume that
+		 * merging is already done. Ditto for a busy system that
+		 * has other work pending, don't risk delaying until the
+		 * idle timer unplug to continue working.
 		 */
 		if (cfq_cfqq_wait_request(cfqq)) {
+			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
+			    cfqd->busy_queues > 1) {
+				del_timer(&cfqd->idle_slice_timer);
+				blk_start_queueing(cfqd->queue);
+			}
 			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)) {
 		/*
@@ -1910,7 +2100,6 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 * 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);
 	}
 }
@@ -1986,13 +2175,23 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	 * or if we want to idle in case it has no pending requests.
 	 */
 	if (cfqd->active_queue == cfqq) {
+		const bool cfqq_empty = RB_EMPTY_ROOT(&cfqq->sort_list);
+
 		if (cfq_cfqq_slice_new(cfqq)) {
 			cfq_set_prio_slice(cfqd, cfqq);
 			cfq_clear_cfqq_slice_new(cfqq);
 		}
+		/*
+		 * If there are no requests waiting in this queue, and
+		 * there are other queues ready to issue requests, AND
+		 * those other queues are issuing requests within our
+		 * mean seek distance, give them a chance to run instead
+		 * of idling.
+		 */
 		if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
 			cfq_slice_expired(cfqd, 1);
-		else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list))
+		else if (cfqq_empty && !cfq_close_cooperator(cfqd, cfqq, 1) &&
+			 sync && !rq_noidle(rq))
 			cfq_arm_slice_timer(cfqd);
 	}
 
@@ -2054,7 +2253,7 @@ static int cfq_may_queue(struct request_queue *q, int rw)
 	if (!cic)
 		return ELV_MQUEUE_MAY;
 
-	cfqq = cic_to_cfqq(cic, rw & REQ_RW_SYNC);
+	cfqq = cic_to_cfqq(cic, rw_is_sync(rw));
 	if (cfqq) {
 		cfq_init_prio_data(cfqq, cic->ioc);
 		cfq_prio_boost(cfqq);
@@ -2144,11 +2343,10 @@ 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);
+	spin_lock_irq(q->queue_lock);
 	blk_start_queueing(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	spin_unlock_irq(q->queue_lock);
 }
 
 /*
@@ -2170,6 +2368,12 @@ static void cfq_idle_slice_timer(unsigned long data)
 		timed_out = 0;
 
 		/*
+		 * We saw a request before the queue expired, let it through
+		 */
+		if (cfq_cfqq_must_dispatch(cfqq))
+			goto out_kick;
+
+		/*
 		 * expired
 		 */
 		if (cfq_slice_used(cfqq))
@@ -2185,10 +2389,8 @@ static void cfq_idle_slice_timer(unsigned long data)
 		/*
 		 * not expired and it has a request pending, let it dispatch
 		 */
-		if (!RB_EMPTY_ROOT(&cfqq->sort_list)) {
-			cfq_mark_cfqq_must_dispatch(cfqq);
+		if (!RB_EMPTY_ROOT(&cfqq->sort_list))
 			goto out_kick;
-		}
 	}
 expire:
 	cfq_slice_expired(cfqd, timed_out);
@@ -2251,12 +2453,22 @@ static void cfq_exit_queue(struct elevator_queue *e)
 static void *cfq_init_queue(struct request_queue *q)
 {
 	struct cfq_data *cfqd;
+	int i;
 
 	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
 	if (!cfqd)
 		return NULL;
 
 	cfqd->service_tree = CFQ_RB_ROOT;
+
+	/*
+	 * Not strictly needed (since RB_ROOT just clears the node and we
+	 * zeroed cfqd on alloc), but better be safe in case someone decides
+	 * to add magic to the rb code
+	 */
+	for (i = 0; i < CFQ_PRIO_LISTS; i++)
+		cfqd->prio_trees[i] = RB_ROOT;
+
 	INIT_LIST_HEAD(&cfqd->cic_list);
 
 	cfqd->queue = q;
diff --git a/block/elevator.c b/block/elevator.c
index 98259eda0ef..7073a907257 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -573,7 +573,7 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
 	elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE);
 }
 
-static void elv_drain_elevator(struct request_queue *q)
+void elv_drain_elevator(struct request_queue *q)
 {
 	static int printed;
 	while (q->elevator->ops->elevator_dispatch_fn(q, 1))
@@ -587,6 +587,31 @@ static void elv_drain_elevator(struct request_queue *q)
 	}
 }
 
+/*
+ * Call with queue lock held, interrupts disabled
+ */
+void elv_quiesce_start(struct request_queue *q)
+{
+	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
+
+	/*
+	 * make sure we don't have any requests in flight
+	 */
+	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);
+	}
+}
+
+void elv_quiesce_end(struct request_queue *q)
+{
+	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+}
+
 void elv_insert(struct request_queue *q, struct request *rq, int where)
 {
 	struct list_head *pos;
@@ -677,7 +702,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 	}
 
 	if (unplug_it && blk_queue_plugged(q)) {
-		int nrq = q->rq.count[READ] + q->rq.count[WRITE]
+		int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC]
 			- q->in_flight;
 
 		if (nrq >= q->unplug_thresh)
@@ -1101,18 +1126,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 * 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);
-	}
+	elv_quiesce_start(q);
 
 	/*
 	 * Remember old elevator.
@@ -1136,7 +1150,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 */
 	elevator_exit(old_elevator);
 	spin_lock_irq(q->queue_lock);
-	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+	elv_quiesce_end(q);
 	spin_unlock_irq(q->queue_lock);
 
 	blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name);
diff --git a/block/genhd.c b/block/genhd.c
index a9ec910974c..1a4916e0173 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -98,7 +98,7 @@ void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk,
 
 	if (flags & DISK_PITER_REVERSE)
 		piter->idx = ptbl->len - 1;
-	else if (flags & DISK_PITER_INCL_PART0)
+	else if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0))
 		piter->idx = 0;
 	else
 		piter->idx = 1;
@@ -134,7 +134,8 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 	/* determine iteration parameters */
 	if (piter->flags & DISK_PITER_REVERSE) {
 		inc = -1;
-		if (piter->flags & DISK_PITER_INCL_PART0)
+		if (piter->flags & (DISK_PITER_INCL_PART0 |
+				    DISK_PITER_INCL_EMPTY_PART0))
 			end = -1;
 		else
 			end = 0;
@@ -150,7 +151,10 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
-		if (!(piter->flags & DISK_PITER_INCL_EMPTY) && !part->nr_sects)
+		if (!part->nr_sects &&
+		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
+		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
+		      piter->idx == 0))
 			continue;
 
 		get_device(part_to_dev(part));
@@ -1011,7 +1015,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 				"\n\n");
 	*/
  
-	disk_part_iter_init(&piter, gp, DISK_PITER_INCL_PART0);
+	disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
 	while ((hd = disk_part_iter_next(&piter))) {
 		cpu = part_stat_lock();
 		part_round_stats(cpu, hd);
diff --git a/block/ioctl.c b/block/ioctl.c
index 0f22e629b13..ad474d4bbcc 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -146,8 +146,6 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 		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;
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 626ee274c5c..82a0ca2f672 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -217,7 +217,7 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 				 struct bio *bio)
 {
-	int ret = 0;
+	int r, ret = 0;
 
 	/*
 	 * fill in all the output members
@@ -242,7 +242,9 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 			ret = -EFAULT;
 	}
 
-	blk_rq_unmap_user(bio);
+	r = blk_rq_unmap_user(bio);
+	if (!ret)
+		ret = r;
 	blk_put_request(rq);
 
 	return ret;
@@ -288,6 +290,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 
 	if (hdr->iovec_count) {
 		const int size = sizeof(struct sg_iovec) * hdr->iovec_count;
+		size_t iov_data_len;
 		struct sg_iovec *iov;
 
 		iov = kmalloc(size, GFP_KERNEL);
@@ -302,8 +305,18 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 			goto out;
 		}
 
+		/* SG_IO howto says that the shorter of the two wins */
+		iov_data_len = iov_length((struct iovec *)iov,
+					  hdr->iovec_count);
+		if (hdr->dxfer_len < iov_data_len) {
+			hdr->iovec_count = iov_shorten((struct iovec *)iov,
+						       hdr->iovec_count,
+						       hdr->dxfer_len);
+			iov_data_len = hdr->dxfer_len;
+		}
+
 		ret = blk_rq_map_user_iov(q, rq, NULL, iov, hdr->iovec_count,
-					  hdr->dxfer_len, GFP_KERNEL);
+					  iov_data_len, GFP_KERNEL);
 		kfree(iov);
 	} else if (hdr->dxfer_len)
 		ret = blk_rq_map_user(q, rq, NULL, hdr->dxferp, hdr->dxfer_len,