Merge branch 'for-2.6.31' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.31' of git://git.kernel.dk/linux-2.6-block: (153 commits)
  block: add request clone interface (v2)
  floppy: fix hibernation
  ramdisk: remove long-deprecated "ramdisk=" boot-time parameter
  fs/bio.c: add missing __user annotation
  block: prevent possible io_context->refcount overflow
  Add serial number support for virtio_blk, V4a
  block: Add missing bounce_pfn stacking and fix comments
  Revert "block: Fix bounce limit setting in DM"
  cciss: decode unit attention in SCSI error handling code
  cciss: Remove no longer needed sendcmd reject processing code
  cciss: change SCSI error handling routines to work with interrupts enabled.
  cciss: separate error processing and command retrying code in sendcmd_withirq_core()
  cciss: factor out fix target status processing code from sendcmd functions
  cciss: simplify interface of sendcmd() and sendcmd_withirq()
  cciss: factor out core of sendcmd_withirq() for use by SCSI error handling code
  cciss: Use schedule_timeout_uninterruptible in SCSI error handling code
  block: needs to set the residual length of a bidi request
  Revert "block: implement blkdev_readpages"
  block: Fix bounce limit setting in DM
  Removed reference to non-existing file Documentation/PCI/PCI-DMA-mapping.txt
  ...

Manually fix conflicts with tracing updates in:
	block/blk-sysfs.c
	drivers/ide/ide-atapi.c
	drivers/ide/ide-cd.c
	drivers/ide/ide-floppy.c
	drivers/ide/ide-tape.c
	include/trace/events/block.h
	kernel/trace/blktrace.c

22 files changed, 1061 insertions, 654 deletions

diff --git a/block/Kconfig b/block/Kconfig
index e7d12782bcfb..2c39527aa7db 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -26,6 +26,7 @@ if BLOCK
 config LBD
 	bool "Support for large block devices and files"
 	depends on !64BIT
+	default y
 	help
 	  Enable block devices or files of size 2TB and larger.
 
@@ -38,11 +39,13 @@ config LBD
 
 	  The ext4 filesystem requires that this feature be enabled in
 	  order to support filesystems that have the huge_file feature
-	  enabled.    Otherwise, it will refuse to mount any filesystems
-	  that use the huge_file feature, which is enabled by default
-	  by mke2fs.ext4.   The GFS2 filesystem also requires this feature.
+	  enabled.  Otherwise, it will refuse to mount in the read-write
+	  mode any filesystems that use the huge_file feature, which is
+	  enabled by default by mke2fs.ext4.
 
-	  If unsure, say N.
+	  The GFS2 filesystem also requires this feature.
+
+	  If unsure, say Y.
 
 config BLK_DEV_BSG
 	bool "Block layer SG support v4 (EXPERIMENTAL)"
diff --git a/block/as-iosched.c b/block/as-iosched.c
index c48fa670d221..7a12cf6ee1d3 100644
--- a/block/as-iosched.c
+++ b/block/as-iosched.c
@@ -306,8 +306,8 @@ as_choose_req(struct as_data *ad, struct request *rq1, struct request *rq2)
 	data_dir = rq_is_sync(rq1);
 
 	last = ad->last_sector[data_dir];
-	s1 = rq1->sector;
-	s2 = rq2->sector;
+	s1 = blk_rq_pos(rq1);
+	s2 = blk_rq_pos(rq2);
 
 	BUG_ON(data_dir != rq_is_sync(rq2));
 
@@ -566,13 +566,15 @@ static void as_update_iohist(struct as_data *ad, struct as_io_context *aic,
 			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;
+			if (aic->last_request_pos < blk_rq_pos(rq))
+				seek_dist = blk_rq_pos(rq) -
+					    aic->last_request_pos;
 			else
-				seek_dist = aic->last_request_pos - rq->sector;
+				seek_dist = aic->last_request_pos -
+					    blk_rq_pos(rq);
 			as_update_seekdist(ad, aic, seek_dist);
 		}
-		aic->last_request_pos = rq->sector + rq->nr_sectors;
+		aic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
 		set_bit(AS_TASK_IOSTARTED, &aic->state);
 		spin_unlock(&aic->lock);
 	}
@@ -587,7 +589,7 @@ static int as_close_req(struct as_data *ad, struct as_io_context *aic,
 {
 	unsigned long delay;	/* jiffies */
 	sector_t last = ad->last_sector[ad->batch_data_dir];
-	sector_t next = rq->sector;
+	sector_t next = blk_rq_pos(rq);
 	sector_t delta; /* acceptable close offset (in sectors) */
 	sector_t s;
 
@@ -981,7 +983,7 @@ static void as_move_to_dispatch(struct as_data *ad, struct request *rq)
 	 * 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;
+	ad->last_sector[data_dir] = blk_rq_pos(rq) + blk_rq_sectors(rq);
 
 	if (data_dir == BLK_RW_SYNC) {
 		struct io_context *ioc = RQ_IOC(rq);
@@ -1312,12 +1314,8 @@ static void as_merged_requests(struct request_queue *q, struct request *req,
 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);
+	blk_run_queue(ad->q);
 }
 
 static int as_may_queue(struct request_queue *q, int rw)
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 20b4111fa050..30022b4e2f63 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -106,10 +106,7 @@ bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
 	 */
 	q->ordseq = 0;
 	rq = q->orig_bar_rq;
-
-	if (__blk_end_request(rq, q->orderr, blk_rq_bytes(rq)))
-		BUG();
-
+	__blk_end_request_all(rq, q->orderr);
 	return true;
 }
 
@@ -166,7 +163,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	 * For an empty barrier, there's no actual BAR request, which
 	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
 	 */
-	if (!rq->hard_nr_sectors) {
+	if (!blk_rq_sectors(rq)) {
 		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
 				QUEUE_ORDERED_DO_POSTFLUSH);
 		/*
@@ -183,7 +180,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	}
 
 	/* stash away the original request */
-	elv_dequeue_request(q, rq);
+	blk_dequeue_request(rq);
 	q->orig_bar_rq = rq;
 	rq = NULL;
 
@@ -221,7 +218,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	} else
 		skip |= QUEUE_ORDSEQ_PREFLUSH;
 
-	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && q->in_flight)
+	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && queue_in_flight(q))
 		rq = NULL;
 	else
 		skip |= QUEUE_ORDSEQ_DRAIN;
@@ -251,10 +248,8 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp)
 			 * Queue ordering not supported.  Terminate
 			 * with prejudice.
 			 */
-			elv_dequeue_request(q, rq);
-			if (__blk_end_request(rq, -EOPNOTSUPP,
-					      blk_rq_bytes(rq)))
-				BUG();
+			blk_dequeue_request(rq);
+			__blk_end_request_all(rq, -EOPNOTSUPP);
 			*rqp = NULL;
 			return false;
 		}
@@ -329,7 +324,7 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 	/*
 	 * 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.
+	 * from blk_rq_pos(rq).
 	 */
 	if (error_sector)
 		*error_sector = bio->bi_sector;
@@ -393,10 +388,10 @@ int blkdev_issue_discard(struct block_device *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;
+		if (nr_sects > queue_max_hw_sectors(q)) {
+			bio->bi_size = queue_max_hw_sectors(q) << 9;
+			nr_sects -= queue_max_hw_sectors(q);
+			sector += queue_max_hw_sectors(q);
 		} else {
 			bio->bi_size = nr_sects << 9;
 			nr_sects = 0;
diff --git a/block/blk-core.c b/block/blk-core.c
index 648f15cb41f1..d17d71c71d4f 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -60,11 +60,11 @@ static void drive_stat_acct(struct request *rq, int new_io)
 	int rw = rq_data_dir(rq);
 	int cpu;
 
-	if (!blk_fs_request(rq) || !blk_do_io_stat(rq))
+	if (!blk_do_io_stat(rq))
 		return;
 
 	cpu = part_stat_lock();
-	part = disk_map_sector_rcu(rq->rq_disk, rq->sector);
+	part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
 
 	if (!new_io)
 		part_stat_inc(cpu, part, merges[rw]);
@@ -119,13 +119,14 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	INIT_LIST_HEAD(&rq->timeout_list);
 	rq->cpu = -1;
 	rq->q = q;
-	rq->sector = rq->hard_sector = (sector_t) -1;
+	rq->__sector = (sector_t) -1;
 	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;
+	rq->start_time = jiffies;
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -176,14 +177,11 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
 		rq->cmd_flags);
 
-	printk(KERN_INFO "  sector %llu, nr/cnr %lu/%u\n",
-						(unsigned long long)rq->sector,
-						rq->nr_sectors,
-						rq->current_nr_sectors);
-	printk(KERN_INFO "  bio %p, biotail %p, buffer %p, data %p, len %u\n",
-						rq->bio, rq->biotail,
-						rq->buffer, rq->data,
-						rq->data_len);
+	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
+	       (unsigned long long)blk_rq_pos(rq),
+	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
+	printk(KERN_INFO "  bio %p, biotail %p, buffer %p, len %u\n",
+	       rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));
 
 	if (blk_pc_request(rq)) {
 		printk(KERN_INFO "  cdb: ");
@@ -325,24 +323,6 @@ void blk_unplug(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_unplug);
 
-static void blk_invoke_request_fn(struct request_queue *q)
-{
-	if (unlikely(blk_queue_stopped(q)))
-		return;
-
-	/*
-	 * one level of recursion is ok and is much faster than kicking
-	 * the unplug handling
-	 */
-	if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
-		q->request_fn(q);
-		queue_flag_clear(QUEUE_FLAG_REENTER, q);
-	} else {
-		queue_flag_set(QUEUE_FLAG_PLUGGED, q);
-		kblockd_schedule_work(q, &q->unplug_work);
-	}
-}
-
 /**
  * blk_start_queue - restart a previously stopped queue
  * @q:    The &struct request_queue in question
@@ -357,7 +337,7 @@ void blk_start_queue(struct request_queue *q)
 	WARN_ON(!irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
-	blk_invoke_request_fn(q);
+	__blk_run_queue(q);
 }
 EXPORT_SYMBOL(blk_start_queue);
 
@@ -417,12 +397,23 @@ void __blk_run_queue(struct request_queue *q)
 {
 	blk_remove_plug(q);
 
+	if (unlikely(blk_queue_stopped(q)))
+		return;
+
+	if (elv_queue_empty(q))
+		return;
+
 	/*
 	 * Only recurse once to avoid overrunning the stack, let the unplug
 	 * handling reinvoke the handler shortly if we already got there.
 	 */
-	if (!elv_queue_empty(q))
-		blk_invoke_request_fn(q);
+	if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
+		q->request_fn(q);
+		queue_flag_clear(QUEUE_FLAG_REENTER, q);
+	} else {
+		queue_flag_set(QUEUE_FLAG_PLUGGED, q);
+		kblockd_schedule_work(q, &q->unplug_work);
+	}
 }
 EXPORT_SYMBOL(__blk_run_queue);
 
@@ -432,9 +423,7 @@ EXPORT_SYMBOL(__blk_run_queue);
  *
  * Description:
  *    Invoke request handling on this queue, if it has pending work to do.
- *    May be used to restart queueing when a request has completed. Also
- *    See @blk_start_queueing.
- *
+ *    May be used to restart queueing when a request has completed.
  */
 void blk_run_queue(struct request_queue *q)
 {
@@ -894,26 +883,58 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 EXPORT_SYMBOL(blk_get_request);
 
 /**
- * blk_start_queueing - initiate dispatch of requests to device
- * @q:		request queue to kick into gear
+ * blk_make_request - given a bio, allocate a corresponding struct request.
+ *
+ * @bio:  The bio describing the memory mappings that will be submitted for IO.
+ *        It may be a chained-bio properly constructed by block/bio layer.
  *
- * This is basically a helper to remove the need to know whether a queue
- * is plugged or not if someone just wants to initiate dispatch of requests
- * for this queue. Should be used to start queueing on a device outside
- * of ->request_fn() context. Also see @blk_run_queue.
+ * blk_make_request is the parallel of generic_make_request for BLOCK_PC
+ * type commands. Where the struct request needs to be farther initialized by
+ * the caller. It is passed a &struct bio, which describes the memory info of
+ * the I/O transfer.
  *
- * The queue lock must be held with interrupts disabled.
+ * The caller of blk_make_request must make sure that bi_io_vec
+ * are set to describe the memory buffers. That bio_data_dir() will return
+ * the needed direction of the request. (And all bio's in the passed bio-chain
+ * are properly set accordingly)
+ *
+ * If called under none-sleepable conditions, mapped bio buffers must not
+ * need bouncing, by calling the appropriate masked or flagged allocator,
+ * suitable for the target device. Otherwise the call to blk_queue_bounce will
+ * BUG.
+ *
+ * WARNING: When allocating/cloning a bio-chain, careful consideration should be
+ * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for
+ * anything but the first bio in the chain. Otherwise you risk waiting for IO
+ * completion of a bio that hasn't been submitted yet, thus resulting in a
+ * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead
+ * of bio_alloc(), as that avoids the mempool deadlock.
+ * If possible a big IO should be split into smaller parts when allocation
+ * fails. Partial allocation should not be an error, or you risk a live-lock.
  */
-void blk_start_queueing(struct request_queue *q)
+struct request *blk_make_request(struct request_queue *q, struct bio *bio,
+				 gfp_t gfp_mask)
 {
-	if (!blk_queue_plugged(q)) {
-		if (unlikely(blk_queue_stopped(q)))
-			return;
-		q->request_fn(q);
-	} else
-		__generic_unplug_device(q);
+	struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);
+
+	if (unlikely(!rq))
+		return ERR_PTR(-ENOMEM);
+
+	for_each_bio(bio) {
+		struct bio *bounce_bio = bio;
+		int ret;
+
+		blk_queue_bounce(q, &bounce_bio);
+		ret = blk_rq_append_bio(q, rq, bounce_bio);
+		if (unlikely(ret)) {
+			blk_put_request(rq);
+			return ERR_PTR(ret);
+		}
+	}
+
+	return rq;
 }
-EXPORT_SYMBOL(blk_start_queueing);
+EXPORT_SYMBOL(blk_make_request);
 
 /**
  * blk_requeue_request - put a request back on queue
@@ -934,6 +955,8 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 	if (blk_rq_tagged(rq))
 		blk_queue_end_tag(q, rq);
 
+	BUG_ON(blk_queued_rq(rq));
+
 	elv_requeue_request(q, rq);
 }
 EXPORT_SYMBOL(blk_requeue_request);
@@ -969,7 +992,6 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 	 * barrier
 	 */
 	rq->cmd_type = REQ_TYPE_SPECIAL;
-	rq->cmd_flags |= REQ_SOFTBARRIER;
 
 	rq->special = data;
 
@@ -983,7 +1005,7 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 
 	drive_stat_acct(rq, 1);
 	__elv_add_request(q, rq, where, 0);
-	blk_start_queueing(q);
+	__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_insert_request);
@@ -1105,16 +1127,13 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	if (bio_failfast_driver(bio))
 		req->cmd_flags |= REQ_FAILFAST_DRIVER;
 
-	/*
-	 * REQ_BARRIER implies no merging, but lets make it explicit
-	 */
 	if (unlikely(bio_discard(bio))) {
 		req->cmd_flags |= REQ_DISCARD;
 		if (bio_barrier(bio))
 			req->cmd_flags |= REQ_SOFTBARRIER;
 		req->q->prepare_discard_fn(req->q, req);
 	} else if (unlikely(bio_barrier(bio)))
-		req->cmd_flags |= (REQ_HARDBARRIER | REQ_NOMERGE);
+		req->cmd_flags |= REQ_HARDBARRIER;
 
 	if (bio_sync(bio))
 		req->cmd_flags |= REQ_RW_SYNC;
@@ -1124,9 +1143,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 		req->cmd_flags |= REQ_NOIDLE;
 
 	req->errors = 0;
-	req->hard_sector = req->sector = bio->bi_sector;
+	req->__sector = bio->bi_sector;
 	req->ioprio = bio_prio(bio);
-	req->start_time = jiffies;
 	blk_rq_bio_prep(req->q, req, bio);
 }
 
@@ -1142,14 +1160,13 @@ static inline bool queue_should_plug(struct request_queue *q)
 static int __make_request(struct request_queue *q, struct bio *bio)
 {
 	struct request *req;
-	int el_ret, nr_sectors;
+	int el_ret;
+	unsigned int bytes = bio->bi_size;
 	const unsigned short prio = bio_prio(bio);
 	const int sync = bio_sync(bio);
 	const int unplug = bio_unplug(bio);
 	int rw_flags;
 
-	nr_sectors = bio_sectors(bio);
-
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even
@@ -1174,7 +1191,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 		req->biotail->bi_next = bio;
 		req->biotail = bio;
-		req->nr_sectors = req->hard_nr_sectors += nr_sectors;
+		req->__data_len += bytes;
 		req->ioprio = ioprio_best(req->ioprio, prio);
 		if (!blk_rq_cpu_valid(req))
 			req->cpu = bio->bi_comp_cpu;
@@ -1200,10 +1217,8 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 		 * not touch req->buffer either...
 		 */
 		req->buffer = bio_data(bio);
-		req->current_nr_sectors = bio_cur_sectors(bio);
-		req->hard_cur_sectors = req->current_nr_sectors;
-		req->sector = req->hard_sector = bio->bi_sector;
-		req->nr_sectors = req->hard_nr_sectors += nr_sectors;
+		req->__sector = bio->bi_sector;
+		req->__data_len += bytes;
 		req->ioprio = ioprio_best(req->ioprio, prio);
 		if (!blk_rq_cpu_valid(req))
 			req->cpu = bio->bi_comp_cpu;
@@ -1414,11 +1429,11 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 		}
 
-		if (unlikely(nr_sectors > q->max_hw_sectors)) {
+		if (unlikely(nr_sectors > queue_max_hw_sectors(q))) {
 			printk(KERN_ERR "bio too big device %s (%u > %u)\n",
-				bdevname(bio->bi_bdev, b),
-				bio_sectors(bio),
-				q->max_hw_sectors);
+			       bdevname(bio->bi_bdev, b),
+			       bio_sectors(bio),
+			       queue_max_hw_sectors(q));
 			goto end_io;
 		}
 
@@ -1584,8 +1599,8 @@ EXPORT_SYMBOL(submit_bio);
  */
 int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 {
-	if (rq->nr_sectors > q->max_sectors ||
-	    rq->data_len > q->max_hw_sectors << 9) {
+	if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
+	    blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
 		return -EIO;
 	}
@@ -1597,8 +1612,8 @@ int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 	 * limitation.
 	 */
 	blk_recalc_rq_segments(rq);
-	if (rq->nr_phys_segments > q->max_phys_segments ||
-	    rq->nr_phys_segments > q->max_hw_segments) {
+	if (rq->nr_phys_segments > queue_max_phys_segments(q) ||
+	    rq->nr_phys_segments > queue_max_hw_segments(q)) {
 		printk(KERN_ERR "%s: over max segments limit.\n", __func__);
 		return -EIO;
 	}
@@ -1642,40 +1657,15 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
 
-/**
- * blkdev_dequeue_request - dequeue request and start timeout timer
- * @req: request to dequeue
- *
- * Dequeue @req and start timeout timer on it.  This hands off the
- * request to the driver.
- *
- * Block internal functions which don't want to start timer should
- * call elv_dequeue_request().
- */
-void blkdev_dequeue_request(struct request *req)
-{
-	elv_dequeue_request(req->q, req);
-
-	/*
-	 * We are now handing the request to the hardware, add the
-	 * timeout handler.
-	 */
-	blk_add_timer(req);
-}
-EXPORT_SYMBOL(blkdev_dequeue_request);
-
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
-	if (!blk_do_io_stat(req))
-		return;
-
-	if (blk_fs_request(req)) {
+	if (blk_do_io_stat(req)) {
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
 		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
 		part_stat_unlock();
 	}
@@ -1683,22 +1673,19 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 
 static void blk_account_io_done(struct request *req)
 {
-	if (!blk_do_io_stat(req))
-		return;
-
 	/*
 	 * Account IO completion.  bar_rq isn't accounted as a normal
 	 * IO on queueing nor completion.  Accounting the containing
 	 * request is enough.
 	 */
-	if (blk_fs_request(req) && req != &req->q->bar_rq) {
+	if (blk_do_io_stat(req) && req != &req->q->bar_rq) {
 		unsigned long duration = jiffies - req->start_time;
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
 
 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);
@@ -1710,25 +1697,209 @@ static void blk_account_io_done(struct request *req)
 }
 
 /**
- * __end_that_request_first - end I/O on a request
- * @req:      the request being processed
+ * blk_peek_request - peek at the top of a request queue
+ * @q: request queue to peek at
+ *
+ * Description:
+ *     Return the request at the top of @q.  The returned request
+ *     should be started using blk_start_request() before LLD starts
+ *     processing it.
+ *
+ * Return:
+ *     Pointer to the request at the top of @q if available.  Null
+ *     otherwise.
+ *
+ * Context:
+ *     queue_lock must be held.
+ */
+struct request *blk_peek_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 && blk_rq_bytes(rq)) {
+			/*
+			 * 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 && blk_rq_bytes(rq) &&
+			    !(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;
+			/*
+			 * Mark this request as started so we don't trigger
+			 * any debug logic in the end I/O path.
+			 */
+			blk_start_request(rq);
+			__blk_end_request_all(rq, -EIO);
+		} else {
+			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
+			break;
+		}
+	}
+
+	return rq;
+}
+EXPORT_SYMBOL(blk_peek_request);
+
+void blk_dequeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	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[rq_is_sync(rq)]++;
+}
+
+/**
+ * blk_start_request - start request processing on the driver
+ * @req: request to dequeue
+ *
+ * Description:
+ *     Dequeue @req and start timeout timer on it.  This hands off the
+ *     request to the driver.
+ *
+ *     Block internal functions which don't want to start timer should
+ *     call blk_dequeue_request().
+ *
+ * Context:
+ *     queue_lock must be held.
+ */
+void blk_start_request(struct request *req)
+{
+	blk_dequeue_request(req);
+
+	/*
+	 * We are now handing the request to the hardware, initialize
+	 * resid_len to full count and add the timeout handler.
+	 */
+	req->resid_len = blk_rq_bytes(req);
+	if (unlikely(blk_bidi_rq(req)))
+		req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
+
+	blk_add_timer(req);
+}
+EXPORT_SYMBOL(blk_start_request);
+
+/**
+ * blk_fetch_request - fetch a request from a request queue
+ * @q: request queue to fetch a request from
+ *
+ * Description:
+ *     Return the request at the top of @q.  The request is started on
+ *     return and LLD can start processing it immediately.
+ *
+ * Return:
+ *     Pointer to the request at the top of @q if available.  Null
+ *     otherwise.
+ *
+ * Context:
+ *     queue_lock must be held.
+ */
+struct request *blk_fetch_request(struct request_queue *q)
+{
+	struct request *rq;
+
+	rq = blk_peek_request(q);
+	if (rq)
+		blk_start_request(rq);
+	return rq;
+}
+EXPORT_SYMBOL(blk_fetch_request);
+
+/**
+ * blk_update_request - Special helper function for request stacking drivers
+ * @rq:	      the request being processed
  * @error:    %0 for success, < %0 for error
- * @nr_bytes: number of bytes to complete
+ * @nr_bytes: number of bytes to complete @rq
  *
  * Description:
- *     Ends I/O on a number of bytes attached to @req, and sets it up
- *     for the next range of segments (if any) in the cluster.
+ *     Ends I/O on a number of bytes attached to @rq, but doesn't complete
+ *     the request structure even if @rq doesn't have leftover.
+ *     If @rq has leftover, sets it up for the next range of segments.
+ *
+ *     This special helper function is only for request stacking drivers
+ *     (e.g. request-based dm) so that they can handle partial completion.
+ *     Actual device drivers should use blk_end_request instead.
+ *
+ *     Passing the result of blk_rq_bytes() as @nr_bytes guarantees
+ *     %false return from this function.
  *
  * Return:
- *     %0 - we are done with this request, call end_that_request_last()
- *     %1 - still buffers pending for this request
+ *     %false - this request doesn't have any more data
+ *     %true  - this request has more data
  **/
-static int __end_that_request_first(struct request *req, int error,
-				    int nr_bytes)
+bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 {
 	int total_bytes, bio_nbytes, next_idx = 0;
 	struct bio *bio;
 
+	if (!req->bio)
+		return false;
+
 	trace_block_rq_complete(req->q, req);
 
 	/*
@@ -1745,7 +1916,7 @@ static int __end_that_request_first(struct request *req, int error,
 	if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) {
 		printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n",
 				req->rq_disk ? req->rq_disk->disk_name : "?",
-				(unsigned long long)req->sector);
+				(unsigned long long)blk_rq_pos(req));
 	}
 
 	blk_account_io_completion(req, nr_bytes);
@@ -1805,8 +1976,15 @@ static int __end_that_request_first(struct request *req, int error,
 	/*
 	 * completely done
 	 */
-	if (!req->bio)
-		return 0;
+	if (!req->bio) {
+		/*
+		 * Reset counters so that the request stacking driver
+		 * can find how many bytes remain in the request
+		 * later.
+		 */
+		req->__data_len = 0;
+		return false;
+	}
 
 	/*
 	 * if the request wasn't completed, update state
@@ -1818,21 +1996,55 @@ static int __end_that_request_first(struct request *req, int error,
 		bio_iovec(bio)->bv_len -= nr_bytes;
 	}
 
-	blk_recalc_rq_sectors(req, total_bytes >> 9);
+	req->__data_len -= total_bytes;
+	req->buffer = bio_data(req->bio);
+
+	/* update sector only for requests with clear definition of sector */
+	if (blk_fs_request(req) || blk_discard_rq(req))
+		req->__sector += total_bytes >> 9;
+
+	/*
+	 * If total number of sectors is less than the first segment
+	 * size, something has gone terribly wrong.
+	 */
+	if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
+		printk(KERN_ERR "blk: request botched\n");
+		req->__data_len = blk_rq_cur_bytes(req);
+	}
+
+	/* recalculate the number of segments */
 	blk_recalc_rq_segments(req);
-	return 1;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(blk_update_request);
+
+static bool blk_update_bidi_request(struct request *rq, int error,
+				    unsigned int nr_bytes,
+				    unsigned int bidi_bytes)
+{
+	if (blk_update_request(rq, error, nr_bytes))
+		return true;
+
+	/* Bidi request must be completed as a whole */
+	if (unlikely(blk_bidi_rq(rq)) &&
+	    blk_update_request(rq->next_rq, error, bidi_bytes))
+		return true;
+
+	add_disk_randomness(rq->rq_disk);
+
+	return false;
 }
 
 /*
  * queue lock must be held
  */
-static void end_that_request_last(struct request *req, int error)
+static void blk_finish_request(struct request *req, int error)
 {
 	if (blk_rq_tagged(req))
 		blk_queue_end_tag(req->q, req);
 
-	if (blk_queued_rq(req))
-		elv_dequeue_request(req->q, req);
+	BUG_ON(blk_queued_rq(req));
 
 	if (unlikely(laptop_mode) && blk_fs_request(req))
 		laptop_io_completion();
@@ -1852,117 +2064,62 @@ static void end_that_request_last(struct request *req, int error)
 }
 
 /**
- * blk_rq_bytes - Returns bytes left to complete in the entire request
- * @rq: the request being processed
- **/
-unsigned int blk_rq_bytes(struct request *rq)
-{
-	if (blk_fs_request(rq))
-		return rq->hard_nr_sectors << 9;
-
-	return rq->data_len;
-}
-EXPORT_SYMBOL_GPL(blk_rq_bytes);
-
-/**
- * blk_rq_cur_bytes - Returns bytes left to complete in the current segment
- * @rq: the request being processed
- **/
-unsigned int blk_rq_cur_bytes(struct request *rq)
-{
-	if (blk_fs_request(rq))
-		return rq->current_nr_sectors << 9;
-
-	if (rq->bio)
-		return rq->bio->bi_size;
-
-	return rq->data_len;
-}
-EXPORT_SYMBOL_GPL(blk_rq_cur_bytes);
-
-/**
- * end_request - end I/O on the current segment of the request
- * @req:	the request being processed
- * @uptodate:	error value or %0/%1 uptodate flag
+ * blk_end_bidi_request - Complete a bidi request
+ * @rq:         the request to complete
+ * @error:      %0 for success, < %0 for error
+ * @nr_bytes:   number of bytes to complete @rq
+ * @bidi_bytes: number of bytes to complete @rq->next_rq
  *
  * Description:
- *     Ends I/O on the current segment of a request. If that is the only
- *     remaining segment, the request is also completed and freed.
- *
- *     This is a remnant of how older block drivers handled I/O completions.
- *     Modern drivers typically end I/O on the full request in one go, unless
- *     they have a residual value to account for. For that case this function
- *     isn't really useful, unless the residual just happens to be the
- *     full current segment. In other words, don't use this function in new
- *     code. Use blk_end_request() or __blk_end_request() to end a request.
+ *     Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
+ *     Drivers that supports bidi can safely call this member for any
+ *     type of request, bidi or uni.  In the later case @bidi_bytes is
+ *     just ignored.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
  **/
-void end_request(struct request *req, int uptodate)
-{
-	int error = 0;
-
-	if (uptodate <= 0)
-		error = uptodate ? uptodate : -EIO;
-
-	__blk_end_request(req, error, req->hard_cur_sectors << 9);
-}
-EXPORT_SYMBOL(end_request);
-
-static int end_that_request_data(struct request *rq, int error,
+static bool blk_end_bidi_request(struct request *rq, int error,
 				 unsigned int nr_bytes, unsigned int bidi_bytes)
 {
-	if (rq->bio) {
-		if (__end_that_request_first(rq, error, nr_bytes))
-			return 1;
+	struct request_queue *q = rq->q;
+	unsigned long flags;
 
-		/* Bidi request must be completed as a whole */
-		if (blk_bidi_rq(rq) &&
-		    __end_that_request_first(rq->next_rq, error, bidi_bytes))
-			return 1;
-	}
+	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
+		return true;
 
-	return 0;
+	spin_lock_irqsave(q->queue_lock, flags);
+	blk_finish_request(rq, error);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return false;
 }
 
 /**
- * blk_end_io - Generic end_io function to complete a request.
- * @rq:           the request being processed
- * @error:        %0 for success, < %0 for error
- * @nr_bytes:     number of bytes to complete @rq
- * @bidi_bytes:   number of bytes to complete @rq->next_rq
- * @drv_callback: function called between completion of bios in the request
- *                and completion of the request.
- *                If the callback returns non %0, this helper returns without
- *                completion of the request.
+ * __blk_end_bidi_request - Complete a bidi request with queue lock held
+ * @rq:         the request to complete
+ * @error:      %0 for success, < %0 for error
+ * @nr_bytes:   number of bytes to complete @rq
+ * @bidi_bytes: number of bytes to complete @rq->next_rq
  *
  * Description:
- *     Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
- *     If @rq has leftover, sets it up for the next range of segments.
+ *     Identical to blk_end_bidi_request() except that queue lock is
+ *     assumed to be locked on entry and remains so on return.
  *
  * Return:
- *     %0 - we are done with this request
- *     %1 - this request is not freed yet, it still has pending buffers.
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
  **/
-static int blk_end_io(struct request *rq, int error, unsigned int nr_bytes,
-		      unsigned int bidi_bytes,
-		      int (drv_callback)(struct request *))
+static bool __blk_end_bidi_request(struct request *rq, int error,
+				   unsigned int nr_bytes, unsigned int bidi_bytes)
 {
-	struct request_queue *q = rq->q;
-	unsigned long flags = 0UL;
-
-	if (end_that_request_data(rq, error, nr_bytes, bidi_bytes))
-		return 1;
-
-	/* Special feature for tricky drivers */
-	if (drv_callback && drv_callback(rq))
-		return 1;
-
-	add_disk_randomness(rq->rq_disk);
+	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
+		return true;
 
-	spin_lock_irqsave(q->queue_lock, flags);
-	end_that_request_last(rq, error);
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	blk_finish_request(rq, error);
 
-	return 0;
+	return false;
 }
 
 /**
@@ -1976,124 +2133,112 @@ static int blk_end_io(struct request *rq, int error, unsigned int nr_bytes,
  *     If @rq has leftover, sets it up for the next range of segments.
  *
  * Return:
- *     %0 - we are done with this request
- *     %1 - still buffers pending for this request
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
  **/
-int blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
+bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
 {
-	return blk_end_io(rq, error, nr_bytes, 0, NULL);
+	return blk_end_bidi_request(rq, error, nr_bytes, 0);
 }
 EXPORT_SYMBOL_GPL(blk_end_request);
 
 /**
- * __blk_end_request - Helper function for drivers to complete the request.
- * @rq:       the request being processed
- * @error:    %0 for success, < %0 for error
- * @nr_bytes: number of bytes to complete
+ * blk_end_request_all - Helper function for drives to finish the request.
+ * @rq: the request to finish
+ * @err: %0 for success, < %0 for error
  *
  * Description:
- *     Must be called with queue lock held unlike blk_end_request().
- *
- * Return:
- *     %0 - we are done with this request
- *     %1 - still buffers pending for this request
- **/
-int __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
+ *     Completely finish @rq.
+ */
+void blk_end_request_all(struct request *rq, int error)
 {
-	if (rq->bio && __end_that_request_first(rq, error, nr_bytes))
-		return 1;
+	bool pending;
+	unsigned int bidi_bytes = 0;
 
-	add_disk_randomness(rq->rq_disk);
+	if (unlikely(blk_bidi_rq(rq)))
+		bidi_bytes = blk_rq_bytes(rq->next_rq);
 
-	end_that_request_last(rq, error);
+	pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
+	BUG_ON(pending);
+}
+EXPORT_SYMBOL_GPL(blk_end_request_all);
 
-	return 0;
+/**
+ * blk_end_request_cur - Helper function to finish the current request chunk.
+ * @rq: the request to finish the current chunk for
+ * @err: %0 for success, < %0 for error
+ *
+ * Description:
+ *     Complete the current consecutively mapped chunk from @rq.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool blk_end_request_cur(struct request *rq, int error)
+{
+	return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
 }
-EXPORT_SYMBOL_GPL(__blk_end_request);
+EXPORT_SYMBOL_GPL(blk_end_request_cur);
 
 /**
- * blk_end_bidi_request - Helper function for drivers to complete bidi request.
- * @rq:         the bidi request being processed
- * @error:      %0 for success, < %0 for error
- * @nr_bytes:   number of bytes to complete @rq
- * @bidi_bytes: number of bytes to complete @rq->next_rq
+ * __blk_end_request - Helper function for drivers to complete the request.
+ * @rq:       the request being processed
+ * @error:    %0 for success, < %0 for error
+ * @nr_bytes: number of bytes to complete
  *
  * Description:
- *     Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
+ *     Must be called with queue lock held unlike blk_end_request().
  *
  * Return:
- *     %0 - we are done with this request
- *     %1 - still buffers pending for this request
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
  **/
-int blk_end_bidi_request(struct request *rq, int error, unsigned int nr_bytes,
-			 unsigned int bidi_bytes)
+bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
 {
-	return blk_end_io(rq, error, nr_bytes, bidi_bytes, NULL);
+	return __blk_end_bidi_request(rq, error, nr_bytes, 0);
 }
-EXPORT_SYMBOL_GPL(blk_end_bidi_request);
+EXPORT_SYMBOL_GPL(__blk_end_request);
 
 /**
- * blk_update_request - Special helper function for request stacking drivers
- * @rq:           the request being processed
- * @error:        %0 for success, < %0 for error
- * @nr_bytes:     number of bytes to complete @rq
+ * __blk_end_request_all - Helper function for drives to finish the request.
+ * @rq: the request to finish
+ * @err: %0 for success, < %0 for error
  *
  * Description:
- *     Ends I/O on a number of bytes attached to @rq, but doesn't complete
- *     the request structure even if @rq doesn't have leftover.
- *     If @rq has leftover, sets it up for the next range of segments.
- *
- *     This special helper function is only for request stacking drivers
- *     (e.g. request-based dm) so that they can handle partial completion.
- *     Actual device drivers should use blk_end_request instead.
+ *     Completely finish @rq.  Must be called with queue lock held.
  */
-void blk_update_request(struct request *rq, int error, unsigned int nr_bytes)
+void __blk_end_request_all(struct request *rq, int error)
 {
-	if (!end_that_request_data(rq, error, nr_bytes, 0)) {
-		/*
-		 * These members are not updated in end_that_request_data()
-		 * when all bios are completed.
-		 * Update them so that the request stacking driver can find
-		 * how many bytes remain in the request later.
-		 */
-		rq->nr_sectors = rq->hard_nr_sectors = 0;
-		rq->current_nr_sectors = rq->hard_cur_sectors = 0;
-	}
+	bool pending;
+	unsigned int bidi_bytes = 0;
+
+	if (unlikely(blk_bidi_rq(rq)))
+		bidi_bytes = blk_rq_bytes(rq->next_rq);
+
+	pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
+	BUG_ON(pending);
 }
-EXPORT_SYMBOL_GPL(blk_update_request);
+EXPORT_SYMBOL_GPL(__blk_end_request_all);
 
 /**
- * blk_end_request_callback - Special helper function for tricky drivers
- * @rq:           the request being processed
- * @error:        %0 for success, < %0 for error
- * @nr_bytes:     number of bytes to complete
- * @drv_callback: function called between completion of bios in the request
- *                and completion of the request.
- *                If the callback returns non %0, this helper returns without
- *                completion of the request.
+ * __blk_end_request_cur - Helper function to finish the current request chunk.
+ * @rq: the request to finish the current chunk for
+ * @err: %0 for success, < %0 for error
  *
  * Description:
- *     Ends I/O on a number of bytes attached to @rq.
- *     If @rq has leftover, sets it up for the next range of segments.
- *
- *     This special helper function is used only for existing tricky drivers.
- *     (e.g. cdrom_newpc_intr() of ide-cd)
- *     This interface will be removed when such drivers are rewritten.
- *     Don't use this interface in other places anymore.
+ *     Complete the current consecutively mapped chunk from @rq.  Must
+ *     be called with queue lock held.
  *
  * Return:
- *     %0 - we are done with this request
- *     %1 - this request is not freed yet.
- *          this request still has pending buffers or
- *          the driver doesn't want to finish this request yet.
- **/
-int blk_end_request_callback(struct request *rq, int error,
-			     unsigned int nr_bytes,
-			     int (drv_callback)(struct request *))
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool __blk_end_request_cur(struct request *rq, int error)
 {
-	return blk_end_io(rq, error, nr_bytes, 0, drv_callback);
+	return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
 }
-EXPORT_SYMBOL_GPL(blk_end_request_callback);
+EXPORT_SYMBOL_GPL(__blk_end_request_cur);
 
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
@@ -2106,11 +2251,7 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
 		rq->buffer = bio_data(bio);
 	}
-	rq->current_nr_sectors = bio_cur_sectors(bio);
-	rq->hard_cur_sectors = rq->current_nr_sectors;
-	rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio);
-	rq->data_len = bio->bi_size;
-
+	rq->__data_len = bio->bi_size;
 	rq->bio = rq->biotail = bio;
 
 	if (bio->bi_bdev)
@@ -2145,6 +2286,106 @@ int blk_lld_busy(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_lld_busy);
 
+/**
+ * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
+ * @rq: the clone request to be cleaned up
+ *
+ * Description:
+ *     Free all bios in @rq for a cloned request.
+ */
+void blk_rq_unprep_clone(struct request *rq)
+{
+	struct bio *bio;
+
+	while ((bio = rq->bio) != NULL) {
+		rq->bio = bio->bi_next;
+
+		bio_put(bio);
+	}
+}
+EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
+
+/*
+ * Copy attributes of the original request to the clone request.
+ * The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied.
+ */
+static void __blk_rq_prep_clone(struct request *dst, struct request *src)
+{
+	dst->cpu = src->cpu;
+	dst->cmd_flags = (rq_data_dir(src) | REQ_NOMERGE);
+	dst->cmd_type = src->cmd_type;
+	dst->__sector = blk_rq_pos(src);
+	dst->__data_len = blk_rq_bytes(src);
+	dst->nr_phys_segments = src->nr_phys_segments;
+	dst->ioprio = src->ioprio;
+	dst->extra_len = src->extra_len;
+}
+
+/**
+ * blk_rq_prep_clone - Helper function to setup clone request
+ * @rq: the request to be setup
+ * @rq_src: original request to be cloned
+ * @bs: bio_set that bios for clone are allocated from
+ * @gfp_mask: memory allocation mask for bio
+ * @bio_ctr: setup function to be called for each clone bio.
+ *           Returns %0 for success, non %0 for failure.
+ * @data: private data to be passed to @bio_ctr
+ *
+ * Description:
+ *     Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
+ *     The actual data parts of @rq_src (e.g. ->cmd, ->buffer, ->sense)
+ *     are not copied, and copying such parts is the caller's responsibility.
+ *     Also, pages which the original bios are pointing to are not copied
+ *     and the cloned bios just point same pages.
+ *     So cloned bios must be completed before original bios, which means
+ *     the caller must complete @rq before @rq_src.
+ */
+int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
+		      struct bio_set *bs, gfp_t gfp_mask,
+		      int (*bio_ctr)(struct bio *, struct bio *, void *),
+		      void *data)
+{
+	struct bio *bio, *bio_src;
+
+	if (!bs)
+		bs = fs_bio_set;
+
+	blk_rq_init(NULL, rq);
+
+	__rq_for_each_bio(bio_src, rq_src) {
+		bio = bio_alloc_bioset(gfp_mask, bio_src->bi_max_vecs, bs);
+		if (!bio)
+			goto free_and_out;
+
+		__bio_clone(bio, bio_src);
+
+		if (bio_integrity(bio_src) &&
+		    bio_integrity_clone(bio, bio_src, gfp_mask))
+			goto free_and_out;
+
+		if (bio_ctr && bio_ctr(bio, bio_src, data))
+			goto free_and_out;
+
+		if (rq->bio) {
+			rq->biotail->bi_next = bio;
+			rq->biotail = bio;
+		} else
+			rq->bio = rq->biotail = bio;
+	}
+
+	__blk_rq_prep_clone(rq, rq_src);
+
+	return 0;
+
+free_and_out:
+	if (bio)
+		bio_free(bio, bs);
+	blk_rq_unprep_clone(rq);
+
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
+
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
 {
 	return queue_work(kblockd_workqueue, work);
@@ -2153,6 +2394,9 @@ EXPORT_SYMBOL(kblockd_schedule_work);
 
 int __init blk_dev_init(void)
 {
+	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
+			sizeof(((struct request *)0)->cmd_flags));
+
 	kblockd_workqueue = create_workqueue("kblockd");
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 6af716d1e54e..49557e91f0da 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -51,7 +51,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	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);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 91fa8e06b6a5..73e28d355688 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -340,7 +340,7 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 		kobject_uevent(&bi->kobj, KOBJ_ADD);
 
 		bi->flags |= INTEGRITY_FLAG_READ | INTEGRITY_FLAG_WRITE;
-		bi->sector_size = disk->queue->hardsect_size;
+		bi->sector_size = queue_logical_block_size(disk->queue);
 		disk->integrity = bi;
 	} else
 		bi = disk->integrity;
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 012f065ac8e2..d4ed6000147d 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -35,9 +35,9 @@ int put_io_context(struct io_context *ioc)
 	if (ioc == NULL)
 		return 1;
 
-	BUG_ON(atomic_read(&ioc->refcount) == 0);
+	BUG_ON(atomic_long_read(&ioc->refcount) == 0);
 
-	if (atomic_dec_and_test(&ioc->refcount)) {
+	if (atomic_long_dec_and_test(&ioc->refcount)) {
 		rcu_read_lock();
 		if (ioc->aic && ioc->aic->dtor)
 			ioc->aic->dtor(ioc->aic);
@@ -90,7 +90,7 @@ struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
 
 	ret = kmem_cache_alloc_node(iocontext_cachep, gfp_flags, node);
 	if (ret) {
-		atomic_set(&ret->refcount, 1);
+		atomic_long_set(&ret->refcount, 1);
 		atomic_set(&ret->nr_tasks, 1);
 		spin_lock_init(&ret->lock);
 		ret->ioprio_changed = 0;
@@ -151,7 +151,7 @@ struct io_context *get_io_context(gfp_t gfp_flags, int node)
 		ret = current_io_context(gfp_flags, node);
 		if (unlikely(!ret))
 			break;
-	} while (!atomic_inc_not_zero(&ret->refcount));
+	} while (!atomic_long_inc_not_zero(&ret->refcount));
 
 	return ret;
 }
@@ -163,8 +163,8 @@ void copy_io_context(struct io_context **pdst, struct io_context **psrc)
 	struct io_context *dst = *pdst;
 
 	if (src) {
-		BUG_ON(atomic_read(&src->refcount) == 0);
-		atomic_inc(&src->refcount);
+		BUG_ON(atomic_long_read(&src->refcount) == 0);
+		atomic_long_inc(&src->refcount);
 		put_io_context(dst);
 		*pdst = src;
 	}
diff --git a/block/blk-map.c b/block/blk-map.c
index f103729b462f..9083cf0180cc 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -20,11 +20,10 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
 
-		rq->data_len += bio->bi_size;
+		rq->__data_len += bio->bi_size;
 	}
 	return 0;
 }
-EXPORT_SYMBOL(blk_rq_append_bio);
 
 static int __blk_rq_unmap_user(struct bio *bio)
 {
@@ -116,7 +115,7 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 	struct bio *bio = NULL;
 	int ret;
 
-	if (len > (q->max_hw_sectors << 9))
+	if (len > (queue_max_hw_sectors(q) << 9))
 		return -EINVAL;
 	if (!len)
 		return -EINVAL;
@@ -156,7 +155,7 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 	if (!bio_flagged(bio, BIO_USER_MAPPED))
 		rq->cmd_flags |= REQ_COPY_USER;
 
-	rq->buffer = rq->data = NULL;
+	rq->buffer = NULL;
 	return 0;
 unmap_rq:
 	blk_rq_unmap_user(bio);
@@ -235,7 +234,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	blk_queue_bounce(q, &bio);
 	bio_get(bio);
 	blk_rq_bio_prep(q, rq, bio);
-	rq->buffer = rq->data = NULL;
+	rq->buffer = NULL;
 	return 0;
 }
 EXPORT_SYMBOL(blk_rq_map_user_iov);
@@ -282,7 +281,8 @@ EXPORT_SYMBOL(blk_rq_unmap_user);
  *
  * Description:
  *    Data will be mapped directly if possible. Otherwise a bounce
- *    buffer is used.
+ *    buffer is used. Can be called multple times to append multple
+ *    buffers.
  */
 int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		    unsigned int len, gfp_t gfp_mask)
@@ -290,8 +290,9 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	int reading = rq_data_dir(rq) == READ;
 	int do_copy = 0;
 	struct bio *bio;
+	int ret;
 
-	if (len > (q->max_hw_sectors << 9))
+	if (len > (queue_max_hw_sectors(q) << 9))
 		return -EINVAL;
 	if (!len || !kbuf)
 		return -EINVAL;
@@ -311,9 +312,15 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (do_copy)
 		rq->cmd_flags |= REQ_COPY_USER;
 
-	blk_rq_bio_prep(q, rq, bio);
+	ret = blk_rq_append_bio(q, rq, bio);
+	if (unlikely(ret)) {
+		/* request is too big */
+		bio_put(bio);
+		return ret;
+	}
+
 	blk_queue_bounce(q, &rq->bio);
-	rq->buffer = rq->data = NULL;
+	rq->buffer = NULL;
 	return 0;
 }
 EXPORT_SYMBOL(blk_rq_map_kern);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 23d2a6fe34a3..39ce64432ba6 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,35 +9,6 @@
 
 #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)
 {
@@ -61,11 +32,12 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 			 * never considered part of another segment, since that
 			 * might change with the bounce page.
 			 */
-			high = page_to_pfn(bv->bv_page) > q->bounce_pfn;
+			high = page_to_pfn(bv->bv_page) > queue_bounce_pfn(q);
 			if (high || highprv)
 				goto new_segment;
 			if (cluster) {
-				if (seg_size + bv->bv_len > q->max_segment_size)
+				if (seg_size + bv->bv_len
+				    > queue_max_segment_size(q))
 					goto new_segment;
 				if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
 					goto new_segment;
@@ -120,7 +92,7 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 		return 0;
 
 	if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
-	    q->max_segment_size)
+	    queue_max_segment_size(q))
 		return 0;
 
 	if (!bio_has_data(bio))
@@ -163,7 +135,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 		int nbytes = bvec->bv_len;
 
 		if (bvprv && cluster) {
-			if (sg->length + nbytes > q->max_segment_size)
+			if (sg->length + nbytes > queue_max_segment_size(q))
 				goto new_segment;
 
 			if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
@@ -199,8 +171,9 @@ new_segment:
 
 
 	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;
+	    (blk_rq_bytes(rq) & q->dma_pad_mask)) {
+		unsigned int pad_len =
+			(q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1;
 
 		sg->length += pad_len;
 		rq->extra_len += pad_len;
@@ -233,8 +206,8 @@ static inline int ll_new_hw_segment(struct request_queue *q,
 {
 	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) {
+	if (req->nr_phys_segments + nr_phys_segs > queue_max_hw_segments(q) ||
+	    req->nr_phys_segments + nr_phys_segs > queue_max_phys_segments(q)) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -255,11 +228,11 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 	unsigned short max_sectors;
 
 	if (unlikely(blk_pc_request(req)))
-		max_sectors = q->max_hw_sectors;
+		max_sectors = queue_max_hw_sectors(q);
 	else
-		max_sectors = q->max_sectors;
+		max_sectors = queue_max_sectors(q);
 
-	if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
+	if (blk_rq_sectors(req) + bio_sectors(bio) > max_sectors) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -279,12 +252,12 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 	unsigned short max_sectors;
 
 	if (unlikely(blk_pc_request(req)))
-		max_sectors = q->max_hw_sectors;
+		max_sectors = queue_max_hw_sectors(q);
 	else
-		max_sectors = q->max_sectors;
+		max_sectors = queue_max_sectors(q);
 
 
-	if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
+	if (blk_rq_sectors(req) + bio_sectors(bio) > max_sectors) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -315,7 +288,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	/*
 	 * Will it become too large?
 	 */
-	if ((req->nr_sectors + next->nr_sectors) > q->max_sectors)
+	if ((blk_rq_sectors(req) + blk_rq_sectors(next)) > queue_max_sectors(q))
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
@@ -327,10 +300,10 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		total_phys_segments--;
 	}
 
-	if (total_phys_segments > q->max_phys_segments)
+	if (total_phys_segments > queue_max_phys_segments(q))
 		return 0;
 
-	if (total_phys_segments > q->max_hw_segments)
+	if (total_phys_segments > queue_max_hw_segments(q))
 		return 0;
 
 	/* Merge is OK... */
@@ -345,7 +318,7 @@ static void blk_account_io_merge(struct request *req)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
 
 		part_round_stats(cpu, part);
 		part_dec_in_flight(part);
@@ -366,7 +339,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	/*
 	 * not contiguous
 	 */
-	if (req->sector + req->nr_sectors != next->sector)
+	if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
 		return 0;
 
 	if (rq_data_dir(req) != rq_data_dir(next)
@@ -398,7 +371,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	req->biotail->bi_next = next->bio;
 	req->biotail = next->biotail;
 
-	req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;
+	req->__data_len += blk_rq_bytes(next);
 
 	elv_merge_requests(q, req, next);
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 57af728d94bb..1c4df9bf6813 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -134,7 +134,7 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 	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_logical_block_size(q, 512);
 	blk_queue_dma_alignment(q, 511);
 	blk_queue_congestion_threshold(q);
 	q->nr_batching = BLK_BATCH_REQ;
@@ -179,16 +179,16 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask)
 	 */
 	if (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
 		dma = 1;
-	q->bounce_pfn = max_low_pfn;
+	q->limits.bounce_pfn = max_low_pfn;
 #else
 	if (b_pfn < blk_max_low_pfn)
 		dma = 1;
-	q->bounce_pfn = b_pfn;
+	q->limits.bounce_pfn = b_pfn;
 #endif
 	if (dma) {
 		init_emergency_isa_pool();
 		q->bounce_gfp = GFP_NOIO | GFP_DMA;
-		q->bounce_pfn = b_pfn;
+		q->limits.bounce_pfn = b_pfn;
 	}
 }
 EXPORT_SYMBOL(blk_queue_bounce_limit);
@@ -211,14 +211,23 @@ void blk_queue_max_sectors(struct request_queue *q, unsigned int max_sectors)
 	}
 
 	if (BLK_DEF_MAX_SECTORS > max_sectors)
-		q->max_hw_sectors = q->max_sectors = max_sectors;
+		q->limits.max_hw_sectors = q->limits.max_sectors = max_sectors;
 	else {
-		q->max_sectors = BLK_DEF_MAX_SECTORS;
-		q->max_hw_sectors = max_sectors;
+		q->limits.max_sectors = BLK_DEF_MAX_SECTORS;
+		q->limits.max_hw_sectors = max_sectors;
 	}
 }
 EXPORT_SYMBOL(blk_queue_max_sectors);
 
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors)
+{
+	if (BLK_DEF_MAX_SECTORS > max_sectors)
+		q->limits.max_hw_sectors = BLK_DEF_MAX_SECTORS;
+	else
+		q->limits.max_hw_sectors = max_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_hw_sectors);
+
 /**
  * blk_queue_max_phys_segments - set max phys segments for a request for this queue
  * @q:  the request queue for the device
@@ -238,7 +247,7 @@ void blk_queue_max_phys_segments(struct request_queue *q,
 		       __func__, max_segments);
 	}
 
-	q->max_phys_segments = max_segments;
+	q->limits.max_phys_segments = max_segments;
 }
 EXPORT_SYMBOL(blk_queue_max_phys_segments);
 
@@ -262,7 +271,7 @@ void blk_queue_max_hw_segments(struct request_queue *q,
 		       __func__, max_segments);
 	}
 
-	q->max_hw_segments = max_segments;
+	q->limits.max_hw_segments = max_segments;
 }
 EXPORT_SYMBOL(blk_queue_max_hw_segments);
 
@@ -283,26 +292,110 @@ void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
 		       __func__, max_size);
 	}
 
-	q->max_segment_size = max_size;
+	q->limits.max_segment_size = max_size;
 }
 EXPORT_SYMBOL(blk_queue_max_segment_size);
 
 /**
- * blk_queue_hardsect_size - set hardware sector size for the queue
+ * blk_queue_logical_block_size - set logical block size for the queue
  * @q:  the request queue for the device
- * @size:  the hardware sector size, in bytes
+ * @size:  the logical block 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.
+ *   This should be set to the lowest possible block size that the
+ *   storage device can address.  The default of 512 covers most
+ *   hardware.
  **/
-void blk_queue_hardsect_size(struct request_queue *q, unsigned short size)
+void blk_queue_logical_block_size(struct request_queue *q, unsigned short size)
+{
+	q->limits.logical_block_size = size;
+
+	if (q->limits.physical_block_size < size)
+		q->limits.physical_block_size = size;
+
+	if (q->limits.io_min < q->limits.physical_block_size)
+		q->limits.io_min = q->limits.physical_block_size;
+}
+EXPORT_SYMBOL(blk_queue_logical_block_size);
+
+/**
+ * blk_queue_physical_block_size - set physical block size for the queue
+ * @q:  the request queue for the device
+ * @size:  the physical block size, in bytes
+ *
+ * Description:
+ *   This should be set to the lowest possible sector size that the
+ *   hardware can operate on without reverting to read-modify-write
+ *   operations.
+ */
+void blk_queue_physical_block_size(struct request_queue *q, unsigned short size)
+{
+	q->limits.physical_block_size = size;
+
+	if (q->limits.physical_block_size < q->limits.logical_block_size)
+		q->limits.physical_block_size = q->limits.logical_block_size;
+
+	if (q->limits.io_min < q->limits.physical_block_size)
+		q->limits.io_min = q->limits.physical_block_size;
+}
+EXPORT_SYMBOL(blk_queue_physical_block_size);
+
+/**
+ * blk_queue_alignment_offset - set physical block alignment offset
+ * @q:	the request queue for the device
+ * @alignment:	alignment offset in bytes
+ *
+ * Description:
+ *   Some devices are naturally misaligned to compensate for things like
+ *   the legacy DOS partition table 63-sector offset.  Low-level drivers
+ *   should call this function for devices whose first sector is not
+ *   naturally aligned.
+ */
+void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
 {
-	q->hardsect_size = size;
+	q->limits.alignment_offset =
+		offset & (q->limits.physical_block_size - 1);
+	q->limits.misaligned = 0;
 }
-EXPORT_SYMBOL(blk_queue_hardsect_size);
+EXPORT_SYMBOL(blk_queue_alignment_offset);
+
+/**
+ * blk_queue_io_min - set minimum request size for the queue
+ * @q:	the request queue for the device
+ * @io_min:  smallest I/O size in bytes
+ *
+ * Description:
+ *   Some devices have an internal block size bigger than the reported
+ *   hardware sector size.  This function can be used to signal the
+ *   smallest I/O the device can perform without incurring a performance
+ *   penalty.
+ */
+void blk_queue_io_min(struct request_queue *q, unsigned int min)
+{
+	q->limits.io_min = min;
+
+	if (q->limits.io_min < q->limits.logical_block_size)
+		q->limits.io_min = q->limits.logical_block_size;
+
+	if (q->limits.io_min < q->limits.physical_block_size)
+		q->limits.io_min = q->limits.physical_block_size;
+}
+EXPORT_SYMBOL(blk_queue_io_min);
+
+/**
+ * blk_queue_io_opt - set optimal request size for the queue
+ * @q:	the request queue for the device
+ * @io_opt:  optimal request size in bytes
+ *
+ * Description:
+ *   Drivers can call this function to set the preferred I/O request
+ *   size for devices that report such a value.
+ */
+void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
+{
+	q->limits.io_opt = opt;
+}
+EXPORT_SYMBOL(blk_queue_io_opt);
 
 /*
  * Returns the minimum that is _not_ zero, unless both are zero.
@@ -317,14 +410,27 @@ EXPORT_SYMBOL(blk_queue_hardsect_size);
 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->limits.max_sectors = min_not_zero(queue_max_sectors(t),
+					     queue_max_sectors(b));
+
+	t->limits.max_hw_sectors = min_not_zero(queue_max_hw_sectors(t),
+						queue_max_hw_sectors(b));
+
+	t->limits.seg_boundary_mask = min_not_zero(queue_segment_boundary(t),
+						   queue_segment_boundary(b));
+
+	t->limits.max_phys_segments = min_not_zero(queue_max_phys_segments(t),
+						   queue_max_phys_segments(b));
+
+	t->limits.max_hw_segments = min_not_zero(queue_max_hw_segments(t),
+						 queue_max_hw_segments(b));
+
+	t->limits.max_segment_size = min_not_zero(queue_max_segment_size(t),
+						  queue_max_segment_size(b));
+
+	t->limits.logical_block_size = max(queue_logical_block_size(t),
+					   queue_logical_block_size(b));
 
-	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)) {
@@ -337,6 +443,109 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
 /**
+ * blk_stack_limits - adjust queue_limits for stacked devices
+ * @t:	the stacking driver limits (top)
+ * @b:  the underlying queue limits (bottom)
+ * @offset:  offset to beginning of data within component device
+ *
+ * Description:
+ *    Merges two queue_limit structs.  Returns 0 if alignment didn't
+ *    change.  Returns -1 if adding the bottom device caused
+ *    misalignment.
+ */
+int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
+		     sector_t offset)
+{
+	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->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
+
+	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->logical_block_size = max(t->logical_block_size,
+				    b->logical_block_size);
+
+	t->physical_block_size = max(t->physical_block_size,
+				     b->physical_block_size);
+
+	t->io_min = max(t->io_min, b->io_min);
+	t->no_cluster |= b->no_cluster;
+
+	/* Bottom device offset aligned? */
+	if (offset &&
+	    (offset & (b->physical_block_size - 1)) != b->alignment_offset) {
+		t->misaligned = 1;
+		return -1;
+	}
+
+	/* If top has no alignment offset, inherit from bottom */
+	if (!t->alignment_offset)
+		t->alignment_offset =
+			b->alignment_offset & (b->physical_block_size - 1);
+
+	/* Top device aligned on logical block boundary? */
+	if (t->alignment_offset & (t->logical_block_size - 1)) {
+		t->misaligned = 1;
+		return -1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(blk_stack_limits);
+
+/**
+ * disk_stack_limits - adjust queue limits for stacked drivers
+ * @disk:  MD/DM gendisk (top)
+ * @bdev:  the underlying block device (bottom)
+ * @offset:  offset to beginning of data within component device
+ *
+ * Description:
+ *    Merges the limits for two queues.  Returns 0 if alignment
+ *    didn't change.  Returns -1 if adding the bottom device caused
+ *    misalignment.
+ */
+void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
+		       sector_t offset)
+{
+	struct request_queue *t = disk->queue;
+	struct request_queue *b = bdev_get_queue(bdev);
+
+	offset += get_start_sect(bdev) << 9;
+
+	if (blk_stack_limits(&t->limits, &b->limits, offset) < 0) {
+		char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
+
+		disk_name(disk, 0, top);
+		bdevname(bdev, bottom);
+
+		printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
+		       top, bottom);
+	}
+
+	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);
+		if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
+			queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
+		spin_unlock_irqrestore(t->queue_lock, flags);
+	}
+}
+EXPORT_SYMBOL(disk_stack_limits);
+
+/**
  * blk_queue_dma_pad - set pad mask
  * @q:     the request queue for the device
  * @mask:  pad mask
@@ -396,11 +605,11 @@ 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)
+	if (queue_max_hw_segments(q) < 2 || queue_max_phys_segments(q) < 2)
 		return -EINVAL;
 	/* make room for appending the drain */
-	--q->max_hw_segments;
-	--q->max_phys_segments;
+	blk_queue_max_hw_segments(q, queue_max_hw_segments(q) - 1);
+	blk_queue_max_phys_segments(q, queue_max_phys_segments(q) - 1);
 	q->dma_drain_needed = dma_drain_needed;
 	q->dma_drain_buffer = buf;
 	q->dma_drain_size = size;
@@ -422,7 +631,7 @@ void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
 		       __func__, mask);
 	}
 
-	q->seg_boundary_mask = mask;
+	q->limits.seg_boundary_mask = mask;
 }
 EXPORT_SYMBOL(blk_queue_segment_boundary);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 26f9ec28f56c..b1cd04087d6a 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -95,21 +95,36 @@ queue_ra_store(struct request_queue *q, const char *page, size_t count)
 
 static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
 {
-	int max_sectors_kb = q->max_sectors >> 1;
+	int max_sectors_kb = queue_max_sectors(q) >> 1;
 
 	return queue_var_show(max_sectors_kb, (page));
 }
 
-static ssize_t queue_hw_sector_size_show(struct request_queue *q, char *page)
+static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(q->hardsect_size, page);
+	return queue_var_show(queue_logical_block_size(q), page);
+}
+
+static ssize_t queue_physical_block_size_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_physical_block_size(q), page);
+}
+
+static ssize_t queue_io_min_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_io_min(q), page);
+}
+
+static ssize_t queue_io_opt_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_io_opt(q), 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,
+		max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1,
 			page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
 	ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
 
@@ -117,7 +132,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 		return -EINVAL;
 
 	spin_lock_irq(q->queue_lock);
-	q->max_sectors = max_sectors_kb << 1;
+	blk_queue_max_sectors(q, max_sectors_kb << 1);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
@@ -125,7 +140,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 
 static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
 {
-	int max_hw_sectors_kb = q->max_hw_sectors >> 1;
+	int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1;
 
 	return queue_var_show(max_hw_sectors_kb, (page));
 }
@@ -249,7 +264,27 @@ static struct queue_sysfs_entry queue_iosched_entry = {
 
 static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.attr = {.name = "hw_sector_size", .mode = S_IRUGO },
-	.show = queue_hw_sector_size_show,
+	.show = queue_logical_block_size_show,
+};
+
+static struct queue_sysfs_entry queue_logical_block_size_entry = {
+	.attr = {.name = "logical_block_size", .mode = S_IRUGO },
+	.show = queue_logical_block_size_show,
+};
+
+static struct queue_sysfs_entry queue_physical_block_size_entry = {
+	.attr = {.name = "physical_block_size", .mode = S_IRUGO },
+	.show = queue_physical_block_size_show,
+};
+
+static struct queue_sysfs_entry queue_io_min_entry = {
+	.attr = {.name = "minimum_io_size", .mode = S_IRUGO },
+	.show = queue_io_min_show,
+};
+
+static struct queue_sysfs_entry queue_io_opt_entry = {
+	.attr = {.name = "optimal_io_size", .mode = S_IRUGO },
+	.show = queue_io_opt_show,
 };
 
 static struct queue_sysfs_entry queue_nonrot_entry = {
@@ -283,6 +318,10 @@ static struct attribute *default_attrs[] = {
 	&queue_max_sectors_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
+	&queue_logical_block_size_entry.attr,
+	&queue_physical_block_size_entry.attr,
+	&queue_io_min_entry.attr,
+	&queue_io_opt_entry.attr,
 	&queue_nonrot_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
@@ -394,16 +433,15 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret)
 		return ret;
 
-	if (!q->request_fn)
-		return 0;
-
-	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj),
-			  "%s", "queue");
+	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
 	if (ret < 0)
 		return ret;
 
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 
+	if (!q->request_fn)
+		return 0;
+
 	ret = elv_register_queue(q);
 	if (ret) {
 		kobject_uevent(&q->kobj, KOBJ_REMOVE);
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 3c518e3303ae..2e5cfeb59333 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -336,7 +336,7 @@ EXPORT_SYMBOL(blk_queue_end_tag);
 int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 {
 	struct blk_queue_tag *bqt = q->queue_tags;
-	unsigned max_depth, offset;
+	unsigned max_depth;
 	int tag;
 
 	if (unlikely((rq->cmd_flags & REQ_QUEUED))) {
@@ -355,13 +355,16 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	 * 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;
+	if (!rq_is_sync(rq) && max_depth > 1) {
+		max_depth -= 2;
+		if (!max_depth)
+			max_depth = 1;
+		if (q->in_flight[0] > max_depth)
+			return 1;
+	}
 
 	do {
-		tag = find_next_zero_bit(bqt->tag_map, max_depth, offset);
+		tag = find_first_zero_bit(bqt->tag_map, max_depth);
 		if (tag >= max_depth)
 			return 1;
 
@@ -374,7 +377,7 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	rq->cmd_flags |= REQ_QUEUED;
 	rq->tag = tag;
 	bqt->tag_index[tag] = rq;
-	blkdev_dequeue_request(rq);
+	blk_start_request(rq);
 	list_add(&rq->queuelist, &q->tag_busy_list);
 	return 0;
 }
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 1ec0d503cacd..1ba7e0aca878 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -122,10 +122,8 @@ void blk_rq_timed_out_timer(unsigned long data)
 			if (blk_mark_rq_complete(rq))
 				continue;
 			blk_rq_timed_out(rq);
-		} else {
-			if (!next || time_after(next, rq->deadline))
-				next = rq->deadline;
-		}
+		} else if (!next || time_after(next, rq->deadline))
+			next = rq->deadline;
 	}
 
 	/*
@@ -176,16 +174,14 @@ void blk_add_timer(struct request *req)
 	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.
-		 */
+	/*
+	 * Some LLDs, like scsi, peek at the timeout to prevent a
+	 * command from being retried forever.
+	 */
+	if (!req->timeout)
 		req->timeout = q->rq_timeout;
-	}
+
+	req->deadline = jiffies + req->timeout;
 	list_add_tail(&req->timeout_list, &q->timeout_list);
 
 	/*
diff --git a/block/blk.h b/block/blk.h
index 79c85f7c9ff5..3fae6add5430 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -13,6 +13,9 @@ 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);
+int blk_rq_append_bio(struct request_queue *q, struct request *rq,
+		      struct bio *bio);
+void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
 
 void blk_unplug_work(struct work_struct *work);
@@ -43,6 +46,43 @@ static inline void blk_clear_rq_complete(struct request *rq)
 	clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
 }
 
+/*
+ * Internal elevator interface
+ */
+#define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
+
+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;
+	}
+}
+
+static inline 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 inline 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);
+}
+
 #ifdef CONFIG_FAIL_IO_TIMEOUT
 int blk_should_fake_timeout(struct request_queue *);
 ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
@@ -64,7 +104,6 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 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);
 
@@ -112,9 +151,17 @@ static inline int blk_cpu_to_group(int cpu)
 #endif
 }
 
+/*
+ * Contribute to IO statistics IFF:
+ *
+ *	a) it's attached to a gendisk, and
+ *	b) the queue had IO stats enabled when this request was started, and
+ *	c) it's a file system request or a discard request
+ */
 static inline int blk_do_io_stat(struct request *rq)
 {
-	return rq->rq_disk && blk_rq_io_stat(rq);
+	return rq->rq_disk && blk_rq_io_stat(rq) &&
+	       (blk_fs_request(rq) || blk_discard_rq(rq));
 }
 
 #endif
diff --git a/block/bsg.c b/block/bsg.c
index dd81be455e00..5358f9ae13c1 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -446,15 +446,15 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	}
 
 	if (rq->next_rq) {
-		hdr->dout_resid = rq->data_len;
-		hdr->din_resid = rq->next_rq->data_len;
+		hdr->dout_resid = rq->resid_len;
+		hdr->din_resid = rq->next_rq->resid_len;
 		blk_rq_unmap_user(bidi_bio);
 		rq->next_rq->bio = NULL;
 		blk_put_request(rq->next_rq);
 	} else if (rq_data_dir(rq) == READ)
-		hdr->din_resid = rq->data_len;
+		hdr->din_resid = rq->resid_len;
 	else
-		hdr->dout_resid = rq->data_len;
+		hdr->dout_resid = rq->resid_len;
 
 	/*
 	 * If the request generated a negative error number, return it
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index a55a9bd75bd1..ef2f72d42434 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -349,8 +349,8 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
 	else if (rq_is_meta(rq2) && !rq_is_meta(rq1))
 		return rq2;
 
-	s1 = rq1->sector;
-	s2 = rq2->sector;
+	s1 = blk_rq_pos(rq1);
+	s2 = blk_rq_pos(rq2);
 
 	last = cfqd->last_position;
 
@@ -579,9 +579,9 @@ cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root,
 		 * Sort strictly based on sector.  Smallest to the left,
 		 * largest to the right.
 		 */
-		if (sector > cfqq->next_rq->sector)
+		if (sector > blk_rq_pos(cfqq->next_rq))
 			n = &(*p)->rb_right;
-		else if (sector < cfqq->next_rq->sector)
+		else if (sector < blk_rq_pos(cfqq->next_rq))
 			n = &(*p)->rb_left;
 		else
 			break;
@@ -611,8 +611,8 @@ static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		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);
+	__cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root,
+				      blk_rq_pos(cfqq->next_rq), &parent, &p);
 	if (!__cfqq) {
 		rb_link_node(&cfqq->p_node, parent, p);
 		rb_insert_color(&cfqq->p_node, cfqq->p_root);
@@ -760,7 +760,7 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 	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;
+	cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
 }
 
 static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
@@ -949,10 +949,10 @@ static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
 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;
+	if (blk_rq_pos(rq) >= cfqd->last_position)
+		return blk_rq_pos(rq) - cfqd->last_position;
 	else
-		return cfqd->last_position - rq->sector;
+		return cfqd->last_position - blk_rq_pos(rq);
 }
 
 #define CIC_SEEK_THR	8 * 1024
@@ -996,7 +996,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
 	if (cfq_rq_close(cfqd, __cfqq->next_rq))
 		return __cfqq;
 
-	if (__cfqq->next_rq->sector < sector)
+	if (blk_rq_pos(__cfqq->next_rq) < sector)
 		node = rb_next(&__cfqq->p_node);
 	else
 		node = rb_prev(&__cfqq->p_node);
@@ -1282,7 +1282,7 @@ static void cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	if (!cfqd->active_cic) {
 		struct cfq_io_context *cic = RQ_CIC(rq);
 
-		atomic_inc(&cic->ioc->refcount);
+		atomic_long_inc(&cic->ioc->refcount);
 		cfqd->active_cic = cic;
 	}
 }
@@ -1918,10 +1918,10 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,
 
 	if (!cic->last_request_pos)
 		sdist = 0;
-	else if (cic->last_request_pos < rq->sector)
-		sdist = rq->sector - cic->last_request_pos;
+	else if (cic->last_request_pos < blk_rq_pos(rq))
+		sdist = blk_rq_pos(rq) - cic->last_request_pos;
 	else
-		sdist = cic->last_request_pos - rq->sector;
+		sdist = cic->last_request_pos - blk_rq_pos(rq);
 
 	/*
 	 * Don't allow the seek distance to get too large from the
@@ -2071,7 +2071,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	cfq_update_io_seektime(cfqd, cic, rq);
 	cfq_update_idle_window(cfqd, cfqq, cic);
 
-	cic->last_request_pos = rq->sector + rq->nr_sectors;
+	cic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
 
 	if (cfqq == cfqd->active_queue) {
 		/*
@@ -2088,7 +2088,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
 			    cfqd->busy_queues > 1) {
 				del_timer(&cfqd->idle_slice_timer);
-				blk_start_queueing(cfqd->queue);
+			__blk_run_queue(cfqd->queue);
 			}
 			cfq_mark_cfqq_must_dispatch(cfqq);
 		}
@@ -2100,7 +2100,7 @@ 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);
-		blk_start_queueing(cfqd->queue);
+		__blk_run_queue(cfqd->queue);
 	}
 }
 
@@ -2345,7 +2345,7 @@ static void cfq_kick_queue(struct work_struct *work)
 	struct request_queue *q = cfqd->queue;
 
 	spin_lock_irq(q->queue_lock);
-	blk_start_queueing(q);
+	__blk_run_queue(cfqd->queue);
 	spin_unlock_irq(q->queue_lock);
 }
 
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index f8c218cd08e1..7865a34e0faa 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -763,10 +763,10 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
 		return compat_put_int(arg, block_size(bdev));
 	case BLKSSZGET: /* get block device hardware sector size */
-		return compat_put_int(arg, bdev_hardsect_size(bdev));
+		return compat_put_int(arg, bdev_logical_block_size(bdev));
 	case BLKSECTGET:
 		return compat_put_ushort(arg,
-					 bdev_get_queue(bdev)->max_sectors);
+					 queue_max_sectors(bdev_get_queue(bdev)));
 	case BLKRASET: /* compatible, but no compat_ptr (!) */
 	case BLKFRASET:
 		if (!capable(CAP_SYS_ADMIN))
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index c4d991d4adef..b547cbca7b23 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -138,7 +138,7 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 
 		__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
 		if (__rq) {
-			BUG_ON(sector != __rq->sector);
+			BUG_ON(sector != blk_rq_pos(__rq));
 
 			if (elv_rq_merge_ok(__rq, bio)) {
 				ret = ELEVATOR_FRONT_MERGE;
diff --git a/block/elevator.c b/block/elevator.c
index e220f0c543e3..ca861927ba41 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -51,8 +51,7 @@ static const int elv_hash_shift = 6;
 #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 rq_hash_key(rq)		(blk_rq_pos(rq) + blk_rq_sectors(rq))
 
 /*
  * Query io scheduler to see if the current process issuing bio may be
@@ -116,9 +115,9 @@ static inline int elv_try_merge(struct request *__rq, struct bio *bio)
 	 * 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)
+		if (blk_rq_pos(__rq) + blk_rq_sectors(__rq) == bio->bi_sector)
 			ret = ELEVATOR_BACK_MERGE;
-		else if (__rq->sector - bio_sectors(bio) == bio->bi_sector)
+		else if (blk_rq_pos(__rq) - bio_sectors(bio) == bio->bi_sector)
 			ret = ELEVATOR_FRONT_MERGE;
 	}
 
@@ -306,22 +305,6 @@ void elevator_exit(struct elevator_queue *e)
 }
 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);
@@ -383,9 +366,9 @@ struct request *elv_rb_add(struct rb_root *root, struct request *rq)
 		parent = *p;
 		__rq = rb_entry(parent, struct request, rb_node);
 
-		if (rq->sector < __rq->sector)
+		if (blk_rq_pos(rq) < blk_rq_pos(__rq))
 			p = &(*p)->rb_left;
-		else if (rq->sector > __rq->sector)
+		else if (blk_rq_pos(rq) > blk_rq_pos(__rq))
 			p = &(*p)->rb_right;
 		else
 			return __rq;
@@ -413,9 +396,9 @@ struct request *elv_rb_find(struct rb_root *root, sector_t sector)
 	while (n) {
 		rq = rb_entry(n, struct request, rb_node);
 
-		if (sector < rq->sector)
+		if (sector < blk_rq_pos(rq))
 			n = n->rb_left;
-		else if (sector > rq->sector)
+		else if (sector > blk_rq_pos(rq))
 			n = n->rb_right;
 		else
 			return rq;
@@ -454,14 +437,14 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 			break;
 		if (pos->cmd_flags & stop_flags)
 			break;
-		if (rq->sector >= boundary) {
-			if (pos->sector < boundary)
+		if (blk_rq_pos(rq) >= boundary) {
+			if (blk_rq_pos(pos) < boundary)
 				continue;
 		} else {
-			if (pos->sector >= boundary)
+			if (blk_rq_pos(pos) >= boundary)
 				break;
 		}
-		if (rq->sector >= pos->sector)
+		if (blk_rq_pos(rq) >= blk_rq_pos(pos))
 			break;
 	}
 
@@ -559,7 +542,7 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
 	 * in_flight count again
 	 */
 	if (blk_account_rq(rq)) {
-		q->in_flight--;
+		q->in_flight[rq_is_sync(rq)]--;
 		if (blk_sorted_rq(rq))
 			elv_deactivate_rq(q, rq);
 	}
@@ -588,6 +571,9 @@ void elv_drain_elevator(struct request_queue *q)
  */
 void elv_quiesce_start(struct request_queue *q)
 {
+	if (!q->elevator)
+		return;
+
 	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
 
 	/*
@@ -595,7 +581,7 @@ void elv_quiesce_start(struct request_queue *q)
 	 */
 	elv_drain_elevator(q);
 	while (q->rq.elvpriv) {
-		blk_start_queueing(q);
+		__blk_run_queue(q);
 		spin_unlock_irq(q->queue_lock);
 		msleep(10);
 		spin_lock_irq(q->queue_lock);
@@ -639,8 +625,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		 *   with anything.  There's no point in delaying queue
 		 *   processing.
 		 */
-		blk_remove_plug(q);
-		blk_start_queueing(q);
+		__blk_run_queue(q);
 		break;
 
 	case ELEVATOR_INSERT_SORT:
@@ -699,7 +684,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 
 	if (unplug_it && blk_queue_plugged(q)) {
 		int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC]
-			- q->in_flight;
+				- queue_in_flight(q);
 
 		if (nrq >= q->unplug_thresh)
 			__generic_unplug_device(q);
@@ -755,117 +740,6 @@ void elv_add_request(struct request_queue *q, struct request *rq, int where,
 }
 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;
@@ -935,7 +809,12 @@ void elv_abort_queue(struct request_queue *q)
 		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));
+		/*
+		 * Mark this request as started so we don't trigger
+		 * any debug logic in the end I/O path.
+		 */
+		blk_start_request(rq);
+		__blk_end_request_all(rq, -EIO);
 	}
 }
 EXPORT_SYMBOL(elv_abort_queue);
@@ -948,7 +827,7 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 	 * request is released from the driver, io must be done
 	 */
 	if (blk_account_rq(rq)) {
-		q->in_flight--;
+		q->in_flight[rq_is_sync(rq)]--;
 		if (blk_sorted_rq(rq) && e->ops->elevator_completed_req_fn)
 			e->ops->elevator_completed_req_fn(q, rq);
 	}
@@ -963,11 +842,11 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 		if (!list_empty(&q->queue_head))
 			next = list_entry_rq(q->queue_head.next);
 
-		if (!q->in_flight &&
+		if (!queue_in_flight(q) &&
 		    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);
+			__blk_run_queue(q);
 		}
 	}
 }
@@ -1175,6 +1054,9 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 	char elevator_name[ELV_NAME_MAX];
 	struct elevator_type *e;
 
+	if (!q->elevator)
+		return count;
+
 	strlcpy(elevator_name, name, sizeof(elevator_name));
 	strstrip(elevator_name);
 
@@ -1198,10 +1080,15 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 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 *elv;
 	struct elevator_type *__e;
 	int len = 0;
 
+	if (!q->elevator)
+		return sprintf(name, "none\n");
+
+	elv = e->elevator_type;
+
 	spin_lock(&elv_list_lock);
 	list_for_each_entry(__e, &elv_list, list) {
 		if (!strcmp(elv->elevator_name, __e->elevator_name))
diff --git a/block/genhd.c b/block/genhd.c
index 1a4916e01732..fe7ccc0a618f 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -852,11 +852,21 @@ static ssize_t disk_capability_show(struct device *dev,
 	return sprintf(buf, "%x\n", disk->flags);
 }
 
+static ssize_t disk_alignment_offset_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue));
+}
+
 static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
 static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
 static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
 static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
+static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL);
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -875,6 +885,7 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_removable.attr,
 	&dev_attr_ro.attr,
 	&dev_attr_size.attr,
+	&dev_attr_alignment_offset.attr,
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
diff --git a/block/ioctl.c b/block/ioctl.c
index ad474d4bbcce..500e4c73cc52 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -152,10 +152,10 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 		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;
+		if (len > queue_max_hw_sectors(q)) {
+			bio->bi_size = queue_max_hw_sectors(q) << 9;
+			len -= queue_max_hw_sectors(q);
+			start += queue_max_hw_sectors(q);
 		} else {
 			bio->bi_size = len << 9;
 			len = 0;
@@ -311,9 +311,9 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	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));
+		return put_int(arg, bdev_logical_block_size(bdev));
 	case BLKSECTGET:
-		return put_ushort(arg, bdev_get_queue(bdev)->max_sectors);
+		return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev)));
 	case BLKRASET:
 	case BLKFRASET:
 		if(!capable(CAP_SYS_ADMIN))
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 82a0ca2f6729..5f8e798ede4e 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -75,7 +75,7 @@ static int sg_set_timeout(struct request_queue *q, int __user *p)
 
 static int sg_get_reserved_size(struct request_queue *q, int __user *p)
 {
-	unsigned val = min(q->sg_reserved_size, q->max_sectors << 9);
+	unsigned val = min(q->sg_reserved_size, queue_max_sectors(q) << 9);
 
 	return put_user(val, p);
 }
@@ -89,8 +89,8 @@ static int sg_set_reserved_size(struct request_queue *q, int __user *p)
 
 	if (size < 0)
 		return -EINVAL;
-	if (size > (q->max_sectors << 9))
-		size = q->max_sectors << 9;
+	if (size > (queue_max_sectors(q) << 9))
+		size = queue_max_sectors(q) << 9;
 
 	q->sg_reserved_size = size;
 	return 0;
@@ -230,7 +230,7 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 	hdr->info = 0;
 	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
 		hdr->info |= SG_INFO_CHECK;
-	hdr->resid = rq->data_len;
+	hdr->resid = rq->resid_len;
 	hdr->sb_len_wr = 0;
 
 	if (rq->sense_len && hdr->sbp) {
@@ -264,7 +264,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	if (hdr->cmd_len > BLK_MAX_CDB)
 		return -EINVAL;
 
-	if (hdr->dxfer_len > (q->max_hw_sectors << 9))
+	if (hdr->dxfer_len > (queue_max_hw_sectors(q) << 9))
 		return -EIO;
 
 	if (hdr->dxfer_len)
@@ -500,9 +500,6 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 
 	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;