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

Documentation/ABI/testing/sysfs-block

@@ -60,3 +60,62 @@ Description:
 		Indicates whether the block layer should automatically
 		generate checksums for write requests bound for
 		devices that support receiving integrity metadata.
+
+What:		/sys/block/<disk>/alignment_offset
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a physical block size that is
+		bigger than the logical block size (for instance a drive
+		with 4KB physical sectors exposing 512-byte logical
+		blocks to the operating system).  This parameter
+		indicates how many bytes the beginning of the device is
+		offset from the disk's natural alignment.
+
+What:		/sys/block/<disk>/<partition>/alignment_offset
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a physical block size that is
+		bigger than the logical block size (for instance a drive
+		with 4KB physical sectors exposing 512-byte logical
+		blocks to the operating system).  This parameter
+		indicates how many bytes the beginning of the partition
+		is offset from the disk's natural alignment.
+
+What:		/sys/block/<disk>/queue/logical_block_size
+Date:		May 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		This is the smallest unit the storage device can
+		address.  It is typically 512 bytes.
+
+What:		/sys/block/<disk>/queue/physical_block_size
+Date:		May 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		This is the smallest unit the storage device can write
+		without resorting to read-modify-write operation.  It is
+		usually the same as the logical block size but may be
+		bigger.  One example is SATA drives with 4KB sectors
+		that expose a 512-byte logical block size to the
+		operating system.
+
+What:		/sys/block/<disk>/queue/minimum_io_size
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a preferred minimum I/O size,
+		which is the smallest request the device can perform
+		without incurring a read-modify-write penalty.  For disk
+		drives this is often the physical block size.  For RAID
+		arrays it is often the stripe chunk size.
+
+What:		/sys/block/<disk>/queue/optimal_io_size
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report an optimal I/O size, which is
+		the device's preferred unit of receiving I/O.  This is
+		rarely reported for disk drives.  For RAID devices it is
+		usually the stripe width or the internal block size.

Documentation/ABI/testing/sysfs-bus-pci-devices-cciss

@@ -0,0 +1,33 @@
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/model
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 0 model for logical drive
+		Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/rev
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 0 revision for logical
+		drive Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/unique_id
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 83 serial number for logical
+		drive Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/vendor
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 0 vendor for logical drive
+		Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/block:cciss!cXdY
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	A symbolic link to /sys/block/cciss!cXdY

Documentation/block/biodoc.txt

@@ -186,7 +186,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address
 do not have a corresponding kernel virtual address space mapping) and
 low-memory pages.
 
-Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion
+Note: Please refer to Documentation/DMA-mapping.txt for a discussion
 on PCI high mem DMA aspects and mapping of scatter gather lists, and support
 for 64 bit PCI.
 

arch/arm/plat-omap/mailbox.c

@@ -147,24 +147,40 @@ static int __mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg, void *arg)
 	return ret;
 }
 
+struct omap_msg_tx_data {
+	mbox_msg_t	msg;
+	void		*arg;
+};
+
+static void omap_msg_tx_end_io(struct request *rq, int error)
+{
+	kfree(rq->special);
+	__blk_put_request(rq->q, rq);
+}
+
 int omap_mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg, void* arg)
 {
+	struct omap_msg_tx_data *tx_data;
 	struct request *rq;
 	struct request_queue *q = mbox->txq->queue;
-	int ret = 0;
+
+	tx_data = kmalloc(sizeof(*tx_data), GFP_ATOMIC);
+	if (unlikely(!tx_data))
+		return -ENOMEM;
 
 	rq = blk_get_request(q, WRITE, GFP_ATOMIC);
 	if (unlikely(!rq)) {
-		ret = -ENOMEM;
-		goto fail;
+		kfree(tx_data);
+		return -ENOMEM;
 	}
 
-	rq->data = (void *)msg;
-	blk_insert_request(q, rq, 0, arg);
+	tx_data->msg = msg;
+	tx_data->arg = arg;
+	rq->end_io = omap_msg_tx_end_io;
+	blk_insert_request(q, rq, 0, tx_data);
 
 	schedule_work(&mbox->txq->work);
- fail:
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(omap_mbox_msg_send);
 
@@ -178,22 +194,28 @@ static void mbox_tx_work(struct work_struct *work)
 	struct request_queue *q = mbox->txq->queue;
 
 	while (1) {
+		struct omap_msg_tx_data *tx_data;
+
 		spin_lock(q->queue_lock);
-		rq = elv_next_request(q);
+		rq = blk_fetch_request(q);
 		spin_unlock(q->queue_lock);
 
 		if (!rq)
 			break;
 
-		ret = __mbox_msg_send(mbox, (mbox_msg_t) rq->data, rq->special);
+		tx_data = rq->special;
+
+		ret = __mbox_msg_send(mbox, tx_data->msg, tx_data->arg);
 		if (ret) {
 			enable_mbox_irq(mbox, IRQ_TX);
+			spin_lock(q->queue_lock);
+			blk_requeue_request(q, rq);
+			spin_unlock(q->queue_lock);
 			return;
 		}
 
 		spin_lock(q->queue_lock);
-		if (__blk_end_request(rq, 0, 0))
-			BUG();
+		__blk_end_request_all(rq, 0);
 		spin_unlock(q->queue_lock);
 	}
 }
@@ -218,16 +240,13 @@ static void mbox_rx_work(struct work_struct *work)
 
 	while (1) {
 		spin_lock_irqsave(q->queue_lock, flags);
-		rq = elv_next_request(q);
+		rq = blk_fetch_request(q);
 		spin_unlock_irqrestore(q->queue_lock, flags);
 		if (!rq)
 			break;
 
-		msg = (mbox_msg_t) rq->data;
-
-		if (blk_end_request(rq, 0, 0))
-			BUG();
-
+		msg = (mbox_msg_t)rq->special;
+		blk_end_request_all(rq, 0);
 		mbox->rxq->callback((void *)msg);
 	}
 }
@@ -264,7 +283,6 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox)
 			goto nomem;
 
 		msg = mbox_fifo_read(mbox);
-		rq->data = (void *)msg;
 
 		if (unlikely(mbox_seq_test(mbox, msg))) {
 			pr_info("mbox: Illegal seq bit!(%08x)\n", msg);
@@ -272,7 +290,7 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox)
 				mbox->err_notify();
 		}
 
-		blk_insert_request(q, rq, 0, NULL);
+		blk_insert_request(q, rq, 0, (void *)msg);
 		if (mbox->ops->type == OMAP_MBOX_TYPE1)
 			break;
 	}
@@ -329,16 +347,15 @@ omap_mbox_read(struct device *dev, struct device_attribute *attr, char *buf)
 
 	while (1) {
 		spin_lock_irqsave(q->queue_lock, flags);
-		rq = elv_next_request(q);
+		rq = blk_fetch_request(q);
 		spin_unlock_irqrestore(q->queue_lock, flags);
 
 		if (!rq)
 			break;
 
-		*p = (mbox_msg_t) rq->data;
+		*p = (mbox_msg_t)rq->special;
 
-		if (blk_end_request(rq, 0, 0))
-			BUG();
+		blk_end_request_all(rq, 0);
 
 		if (unlikely(mbox_seq_test(mbox, *p))) {
 			pr_info("mbox: Illegal seq bit!(%08x) ignored\n", *p);

arch/powerpc/sysdev/axonram.c

@@ -250,7 +250,7 @@ axon_ram_probe(struct of_device *device, const struct of_device_id *device_id)
 
 	set_capacity(bank->disk, bank->size >> AXON_RAM_SECTOR_SHIFT);
 	blk_queue_make_request(bank->disk->queue, axon_ram_make_request);
-	blk_queue_hardsect_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE);
+	blk_queue_logical_block_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE);
 	add_disk(bank->disk);
 
 	bank->irq_id = irq_of_parse_and_map(device->node, 0);

arch/um/drivers/ubd_kern.c

@@ -451,23 +451,6 @@ static void do_ubd_request(struct request_queue * q);
 
 /* Only changed by ubd_init, which is an initcall. */
 static int thread_fd = -1;
-
-static void ubd_end_request(struct request *req, int bytes, int error)
-{
-	blk_end_request(req, error, bytes);
-}
-
-/* Callable only from interrupt context - otherwise you need to do
- * spin_lock_irq()/spin_lock_irqsave() */
-static inline void ubd_finish(struct request *req, int bytes)
-{
-	if(bytes < 0){
-		ubd_end_request(req, 0, -EIO);
-		return;
-	}
-	ubd_end_request(req, bytes, 0);
-}
-
 static LIST_HEAD(restart);
 
 /* XXX - move this inside ubd_intr. */
@@ -475,7 +458,6 @@ static LIST_HEAD(restart);
 static void ubd_handler(void)
 {
 	struct io_thread_req *req;
-	struct request *rq;
 	struct ubd *ubd;
 	struct list_head *list, *next_ele;
 	unsigned long flags;
@@ -492,10 +474,7 @@ static void ubd_handler(void)
 			return;
 		}
 
-		rq = req->req;
-		rq->nr_sectors -= req->length >> 9;
-		if(rq->nr_sectors == 0)
-			ubd_finish(rq, rq->hard_nr_sectors << 9);
+		blk_end_request(req->req, 0, req->length);
 		kfree(req);
 	}
 	reactivate_fd(thread_fd, UBD_IRQ);
@@ -1243,27 +1222,26 @@ static void do_ubd_request(struct request_queue *q)
 {
 	struct io_thread_req *io_req;
 	struct request *req;
-	int n, last_sectors;
+	sector_t sector;
+	int n;
 
 	while(1){
 		struct ubd *dev = q->queuedata;
 		if(dev->end_sg == 0){
-			struct request *req = elv_next_request(q);
+			struct request *req = blk_fetch_request(q);
 			if(req == NULL)
 				return;
 
 			dev->request = req;
-			blkdev_dequeue_request(req);
 			dev->start_sg = 0;
 			dev->end_sg = blk_rq_map_sg(q, req, dev->sg);
 		}
 
 		req = dev->request;
-		last_sectors = 0;
+		sector = blk_rq_pos(req);
 		while(dev->start_sg < dev->end_sg){
 			struct scatterlist *sg = &dev->sg[dev->start_sg];
 
-			req->sector += last_sectors;
 			io_req = kmalloc(sizeof(struct io_thread_req),
 					 GFP_ATOMIC);
 			if(io_req == NULL){
@@ -1272,10 +1250,10 @@ static void do_ubd_request(struct request_queue *q)
 				return;
 			}
 			prepare_request(req, io_req,
-					(unsigned long long) req->sector << 9,
+					(unsigned long long)sector << 9,
 					sg->offset, sg->length, sg_page(sg));
 
-			last_sectors = sg->length >> 9;
+			sector += sg->length >> 9;
 			n = os_write_file(thread_fd, &io_req,
 					  sizeof(struct io_thread_req *));
 			if(n != sizeof(struct io_thread_req *)){

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)"

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)

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;

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");

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);

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;

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;
 	}

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);

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);
 

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)) {
@@ -336,6 +442,109 @@ 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
@@ -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);
 

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);

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;
 }

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);
 
 	/*

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

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

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);
 }
 

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))

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;

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))

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

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))

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;

drivers/ata/libata-scsi.c

@@ -1084,7 +1084,7 @@ static int atapi_drain_needed(struct request *rq)
 	if (likely(!blk_pc_request(rq)))
 		return 0;
 
-	if (!rq->data_len || (rq->cmd_flags & REQ_RW))
+	if (!blk_rq_bytes(rq) || (rq->cmd_flags & REQ_RW))
 		return 0;
 
 	return atapi_cmd_type(rq->cmd[0]) == ATAPI_MISC;

drivers/block/DAC960.c

@@ -3321,7 +3321,7 @@ static int DAC960_process_queue(DAC960_Controller_T *Controller, struct request_
 	DAC960_Command_T *Command;
 
    while(1) {
-	Request = elv_next_request(req_q);
+	Request = blk_peek_request(req_q);
 	if (!Request)
 		return 1;
 
@@ -3338,10 +3338,10 @@ static int DAC960_process_queue(DAC960_Controller_T *Controller, struct request_
 	}
 	Command->Completion = Request->end_io_data;
 	Command->LogicalDriveNumber = (long)Request->rq_disk->private_data;
-	Command->BlockNumber = Request->sector;
-	Command->BlockCount = Request->nr_sectors;
+	Command->BlockNumber = blk_rq_pos(Request);
+	Command->BlockCount = blk_rq_sectors(Request);
 	Command->Request = Request;
-	blkdev_dequeue_request(Request);
+	blk_start_request(Request);
 	Command->SegmentCount = blk_rq_map_sg(req_q,
 		  Command->Request, Command->cmd_sglist);
 	/* pci_map_sg MAY change the value of SegCount */
@@ -3431,7 +3431,7 @@ static void DAC960_queue_partial_rw(DAC960_Command_T *Command)
    * successfully as possible.
    */
   Command->SegmentCount = 1;
-  Command->BlockNumber = Request->sector;
+  Command->BlockNumber = blk_rq_pos(Request);
   Command->BlockCount = 1;
   DAC960_QueueReadWriteCommand(Command);
   return;

drivers/block/Kconfig

@@ -412,7 +412,7 @@ config ATA_OVER_ETH
 
 config MG_DISK
 	tristate "mGine mflash, gflash support"
-	depends on ARM && ATA && GPIOLIB
+	depends on ARM && GPIOLIB
 	help
 	  mGine mFlash(gFlash) block device driver
 

drivers/block/amiflop.c

@@ -112,8 +112,6 @@ module_param(fd_def_df0, ulong, 0);
 MODULE_LICENSE("GPL");
 
 static struct request_queue *floppy_queue;
-#define QUEUE (floppy_queue)
-#define CURRENT elv_next_request(floppy_queue)
 
 /*
  *  Macros
@@ -1335,64 +1333,60 @@ static int get_track(int drive, int track)
 
 static void redo_fd_request(void)
 {
+	struct request *rq;
 	unsigned int cnt, block, track, sector;
 	int drive;
 	struct amiga_floppy_struct *floppy;
 	char *data;
 	unsigned long flags;
+	int err;
 
- repeat:
-	if (!CURRENT) {
+next_req:
+	rq = blk_fetch_request(floppy_queue);
+	if (!rq) {
 		/* Nothing left to do */
 		return;
 	}
 
-	floppy = CURRENT->rq_disk->private_data;
+	floppy = rq->rq_disk->private_data;
 	drive = floppy - unit;
 
+next_segment:
 	/* Here someone could investigate to be more efficient */
-	for (cnt = 0; cnt < CURRENT->current_nr_sectors; cnt++) { 
+	for (cnt = 0, err = 0; cnt < blk_rq_cur_sectors(rq); cnt++) {
 #ifdef DEBUG
 		printk("fd: sector %ld + %d requested for %s\n",
-		       CURRENT->sector,cnt,
-		       (rq_data_dir(CURRENT) == READ) ? "read" : "write");
+		       blk_rq_pos(rq), cnt,
+		       (rq_data_dir(rq) == READ) ? "read" : "write");
 #endif
-		block = CURRENT->sector + cnt;
+		block = blk_rq_pos(rq) + cnt;
 		if ((int)block > floppy->blocks) {
-			end_request(CURRENT, 0);
-			goto repeat;
+			err = -EIO;
+			break;
 		}
 
 		track = block / (floppy->dtype->sects * floppy->type->sect_mult);
 		sector = block % (floppy->dtype->sects * floppy->type->sect_mult);
-		data = CURRENT->buffer + 512 * cnt;
+		data = rq->buffer + 512 * cnt;
 #ifdef DEBUG
 		printk("access to track %d, sector %d, with buffer at "
 		       "0x%08lx\n", track, sector, data);
 #endif
 
-		if ((rq_data_dir(CURRENT) != READ) && (rq_data_dir(CURRENT) != WRITE)) {
-			printk(KERN_WARNING "do_fd_request: unknown command\n");
-			end_request(CURRENT, 0);
-			goto repeat;
-		}
 		if (get_track(drive, track) == -1) {
-			end_request(CURRENT, 0);
-			goto repeat;
+			err = -EIO;
+			break;
 		}
 
-		switch (rq_data_dir(CURRENT)) {
-		case READ:
+		if (rq_data_dir(rq) == READ) {
 			memcpy(data, floppy->trackbuf + sector * 512, 512);
-			break;
-
-		case WRITE:
+		} else {
 			memcpy(floppy->trackbuf + sector * 512, data, 512);
 
 			/* keep the drive spinning while writes are scheduled */
 			if (!fd_motor_on(drive)) {
-				end_request(CURRENT, 0);
-				goto repeat;
+				err = -EIO;
+				break;
 			}
 			/*
 			 * setup a callback to write the track buffer
@@ -1404,14 +1398,12 @@ static void redo_fd_request(void)
 		        /* reset the timer */
 			mod_timer (flush_track_timer + drive, jiffies + 1);
 			local_irq_restore(flags);
-			break;
 		}
 	}
-	CURRENT->nr_sectors -= CURRENT->current_nr_sectors;
-	CURRENT->sector += CURRENT->current_nr_sectors;
 
-	end_request(CURRENT, 1);
-	goto repeat;
+	if (__blk_end_request_cur(rq, err))
+		goto next_segment;
+	goto next_req;
 }
 
 static void do_fd_request(struct request_queue * q)

drivers/block/ataflop.c

@@ -79,9 +79,7 @@
 #undef DEBUG
 
 static struct request_queue *floppy_queue;
-
-#define QUEUE (floppy_queue)
-#define CURRENT elv_next_request(floppy_queue)
+static struct request *fd_request;
 
 /* Disk types: DD, HD, ED */
 static struct atari_disk_type {
@@ -376,6 +374,12 @@ static DEFINE_TIMER(readtrack_timer, fd_readtrack_check, 0, 0);
 static DEFINE_TIMER(timeout_timer, fd_times_out, 0, 0);
 static DEFINE_TIMER(fd_timer, check_change, 0, 0);
 	
+static void fd_end_request_cur(int err)
+{
+	if (!__blk_end_request_cur(fd_request, err))
+		fd_request = NULL;
+}
+
 static inline void start_motor_off_timer(void)
 {
 	mod_timer(&motor_off_timer, jiffies + FD_MOTOR_OFF_DELAY);
@@ -606,15 +610,15 @@ static void fd_error( void )
 		return;
 	}
 
-	if (!CURRENT)
+	if (!fd_request)
 		return;
 
-	CURRENT->errors++;
-	if (CURRENT->errors >= MAX_ERRORS) {
+	fd_request->errors++;
+	if (fd_request->errors >= MAX_ERRORS) {
 		printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive );
-		end_request(CURRENT, 0);
+		fd_end_request_cur(-EIO);
 	}
-	else if (CURRENT->errors == RECALIBRATE_ERRORS) {
+	else if (fd_request->errors == RECALIBRATE_ERRORS) {
 		printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive );
 		if (SelectedDrive != -1)
 			SUD.track = -1;
@@ -725,16 +729,14 @@ static void do_fd_action( int drive )
 	    if (IS_BUFFERED( drive, ReqSide, ReqTrack )) {
 		if (ReqCmd == READ) {
 		    copy_buffer( SECTOR_BUFFER(ReqSector), ReqData );
-		    if (++ReqCnt < CURRENT->current_nr_sectors) {
+		    if (++ReqCnt < blk_rq_cur_sectors(fd_request)) {
 			/* read next sector */
 			setup_req_params( drive );
 			goto repeat;
 		    }
 		    else {
 			/* all sectors finished */
-			CURRENT->nr_sectors -= CURRENT->current_nr_sectors;
-			CURRENT->sector += CURRENT->current_nr_sectors;
-			end_request(CURRENT, 1);
+			fd_end_request_cur(0);
 			redo_fd_request();
 			return;
 		    }
@@ -1132,16 +1134,14 @@ static void fd_rwsec_done1(int status)
 		}
 	}
   
-	if (++ReqCnt < CURRENT->current_nr_sectors) {
+	if (++ReqCnt < blk_rq_cur_sectors(fd_request)) {
 		/* read next sector */
 		setup_req_params( SelectedDrive );
 		do_fd_action( SelectedDrive );
 	}
 	else {
 		/* all sectors finished */
-		CURRENT->nr_sectors -= CURRENT->current_nr_sectors;
-		CURRENT->sector += CURRENT->current_nr_sectors;
-		end_request(CURRENT, 1);
+		fd_end_request_cur(0);
 		redo_fd_request();
 	}
 	return;
@@ -1382,7 +1382,7 @@ static void setup_req_params( int drive )
 	ReqData = ReqBuffer + 512 * ReqCnt;
 
 	if (UseTrackbuffer)
-		read_track = (ReqCmd == READ && CURRENT->errors == 0);
+		read_track = (ReqCmd == READ && fd_request->errors == 0);
 	else
 		read_track = 0;
 
@@ -1396,25 +1396,27 @@ static void redo_fd_request(void)
 	int drive, type;
 	struct atari_floppy_struct *floppy;
 
-	DPRINT(("redo_fd_request: CURRENT=%p dev=%s CURRENT->sector=%ld\n",
-		CURRENT, CURRENT ? CURRENT->rq_disk->disk_name : "",
-		CURRENT ? CURRENT->sector : 0 ));
+	DPRINT(("redo_fd_request: fd_request=%p dev=%s fd_request->sector=%ld\n",
+		fd_request, fd_request ? fd_request->rq_disk->disk_name : "",
+		fd_request ? blk_rq_pos(fd_request) : 0 ));
 
 	IsFormatting = 0;
 
 repeat:
+	if (!fd_request) {
+		fd_request = blk_fetch_request(floppy_queue);
+		if (!fd_request)
+			goto the_end;
+	}
 
-	if (!CURRENT)
-		goto the_end;
-
-	floppy = CURRENT->rq_disk->private_data;
+	floppy = fd_request->rq_disk->private_data;
 	drive = floppy - unit;
 	type = floppy->type;
 	
 	if (!UD.connected) {
 		/* drive not connected */
 		printk(KERN_ERR "Unknown Device: fd%d\n", drive );
-		end_request(CURRENT, 0);
+		fd_end_request_cur(-EIO);
 		goto repeat;
 	}
 		
@@ -1430,12 +1432,12 @@ repeat:
 		/* user supplied disk type */
 		if (--type >= NUM_DISK_MINORS) {
 			printk(KERN_WARNING "fd%d: invalid disk format", drive );
-			end_request(CURRENT, 0);
+			fd_end_request_cur(-EIO);
 			goto repeat;
 		}
 		if (minor2disktype[type].drive_types > DriveType)  {
 			printk(KERN_WARNING "fd%d: unsupported disk format", drive );
-			end_request(CURRENT, 0);
+			fd_end_request_cur(-EIO);
 			goto repeat;
 		}
 		type = minor2disktype[type].index;
@@ -1444,8 +1446,8 @@ repeat:
 		UD.autoprobe = 0;
 	}
 	
-	if (CURRENT->sector + 1 > UDT->blocks) {
-		end_request(CURRENT, 0);
+	if (blk_rq_pos(fd_request) + 1 > UDT->blocks) {
+		fd_end_request_cur(-EIO);
 		goto repeat;
 	}
 
@@ -1453,9 +1455,9 @@ repeat:
 	del_timer( &motor_off_timer );
 		
 	ReqCnt = 0;
-	ReqCmd = rq_data_dir(CURRENT);
-	ReqBlock = CURRENT->sector;
-	ReqBuffer = CURRENT->buffer;
+	ReqCmd = rq_data_dir(fd_request);
+	ReqBlock = blk_rq_pos(fd_request);
+	ReqBuffer = fd_request->buffer;
 	setup_req_params( drive );
 	do_fd_action( drive );
 

drivers/block/brd.c

@@ -407,12 +407,7 @@ static int __init ramdisk_size(char *str)
 	rd_size = simple_strtol(str, NULL, 0);
 	return 1;
 }
-static int __init ramdisk_size2(char *str)
-{
-	return ramdisk_size(str);
-}
-__setup("ramdisk=", ramdisk_size);
-__setup("ramdisk_size=", ramdisk_size2);
+__setup("ramdisk_size=", ramdisk_size);
 #endif
 
 /*

drivers/block/cciss.c

@@ -180,11 +180,13 @@ static void __devinit cciss_interrupt_mode(ctlr_info_t *, struct pci_dev *,
 					   __u32);
 static void start_io(ctlr_info_t *h);
 static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size,
-		   unsigned int use_unit_num, unsigned int log_unit,
 		   __u8 page_code, unsigned char *scsi3addr, int cmd_type);
 static int sendcmd_withirq(__u8 cmd, int ctlr, void *buff, size_t size,
-			   unsigned int use_unit_num, unsigned int log_unit,
-			   __u8 page_code, int cmd_type);
+			__u8 page_code, unsigned char scsi3addr[],
+			int cmd_type);
+static int sendcmd_withirq_core(ctlr_info_t *h, CommandList_struct *c,
+	int attempt_retry);
+static int process_sendcmd_error(ctlr_info_t *h, CommandList_struct *c);
 
 static void fail_all_cmds(unsigned long ctlr);
 static int scan_thread(void *data);
@@ -437,6 +439,194 @@ static void __devinit cciss_procinit(int i)
 }
 #endif				/* CONFIG_PROC_FS */
 
+#define MAX_PRODUCT_NAME_LEN 19
+
+#define to_hba(n) container_of(n, struct ctlr_info, dev)
+#define to_drv(n) container_of(n, drive_info_struct, dev)
+
+static struct device_type cciss_host_type = {
+	.name		= "cciss_host",
+};
+
+static ssize_t dev_show_unique_id(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	drive_info_struct *drv = to_drv(dev);
+	struct ctlr_info *h = to_hba(drv->dev.parent);
+	__u8 sn[16];
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
+	if (h->busy_configuring)
+		ret = -EBUSY;
+	else
+		memcpy(sn, drv->serial_no, sizeof(sn));
+	spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
+
+	if (ret)
+		return ret;
+	else
+		return snprintf(buf, 16 * 2 + 2,
+				"%02X%02X%02X%02X%02X%02X%02X%02X"
+				"%02X%02X%02X%02X%02X%02X%02X%02X\n",
+				sn[0], sn[1], sn[2], sn[3],
+				sn[4], sn[5], sn[6], sn[7],
+				sn[8], sn[9], sn[10], sn[11],
+				sn[12], sn[13], sn[14], sn[15]);
+}
+DEVICE_ATTR(unique_id, S_IRUGO, dev_show_unique_id, NULL);
+
+static ssize_t dev_show_vendor(struct device *dev,
+			       struct device_attribute *attr,
+			       char *buf)
+{
+	drive_info_struct *drv = to_drv(dev);
+	struct ctlr_info *h = to_hba(drv->dev.parent);
+	char vendor[VENDOR_LEN + 1];
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
+	if (h->busy_configuring)
+		ret = -EBUSY;
+	else
+		memcpy(vendor, drv->vendor, VENDOR_LEN + 1);
+	spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
+
+	if (ret)
+		return ret;
+	else
+		return snprintf(buf, sizeof(vendor) + 1, "%s\n", drv->vendor);
+}
+DEVICE_ATTR(vendor, S_IRUGO, dev_show_vendor, NULL);
+
+static ssize_t dev_show_model(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	drive_info_struct *drv = to_drv(dev);
+	struct ctlr_info *h = to_hba(drv->dev.parent);
+	char model[MODEL_LEN + 1];
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
+	if (h->busy_configuring)
+		ret = -EBUSY;
+	else
+		memcpy(model, drv->model, MODEL_LEN + 1);
+	spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
+
+	if (ret)
+		return ret;
+	else
+		return snprintf(buf, sizeof(model) + 1, "%s\n", drv->model);
+}
+DEVICE_ATTR(model, S_IRUGO, dev_show_model, NULL);
+
+static ssize_t dev_show_rev(struct device *dev,
+			    struct device_attribute *attr,
+			    char *buf)
+{
+	drive_info_struct *drv = to_drv(dev);
+	struct ctlr_info *h = to_hba(drv->dev.parent);
+	char rev[REV_LEN + 1];
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
+	if (h->busy_configuring)
+		ret = -EBUSY;
+	else
+		memcpy(rev, drv->rev, REV_LEN + 1);
+	spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
+
+	if (ret)
+		return ret;
+	else
+		return snprintf(buf, sizeof(rev) + 1, "%s\n", drv->rev);
+}
+DEVICE_ATTR(rev, S_IRUGO, dev_show_rev, NULL);
+
+static struct attribute *cciss_dev_attrs[] = {
+	&dev_attr_unique_id.attr,
+	&dev_attr_model.attr,
+	&dev_attr_vendor.attr,
+	&dev_attr_rev.attr,
+	NULL
+};
+
+static struct attribute_group cciss_dev_attr_group = {
+	.attrs = cciss_dev_attrs,
+};
+
+static struct attribute_group *cciss_dev_attr_groups[] = {
+	&cciss_dev_attr_group,
+	NULL
+};
+
+static struct device_type cciss_dev_type = {
+	.name		= "cciss_device",
+	.groups		= cciss_dev_attr_groups,
+};
+
+static struct bus_type cciss_bus_type = {
+	.name		= "cciss",
+};
+
+
+/*
+ * Initialize sysfs entry for each controller.  This sets up and registers
+ * the 'cciss#' directory for each individual controller under
+ * /sys/bus/pci/devices/<dev>/.
+ */
+static int cciss_create_hba_sysfs_entry(struct ctlr_info *h)
+{
+	device_initialize(&h->dev);
+	h->dev.type = &cciss_host_type;
+	h->dev.bus = &cciss_bus_type;
+	dev_set_name(&h->dev, "%s", h->devname);
+	h->dev.parent = &h->pdev->dev;
+
+	return device_add(&h->dev);
+}
+
+/*
+ * Remove sysfs entries for an hba.
+ */
+static void cciss_destroy_hba_sysfs_entry(struct ctlr_info *h)
+{
+	device_del(&h->dev);
+}
+
+/*
+ * Initialize sysfs for each logical drive.  This sets up and registers
+ * the 'c#d#' directory for each individual logical drive under
+ * /sys/bus/pci/devices/<dev/ccis#/. We also create a link from
+ * /sys/block/cciss!c#d# to this entry.
+ */
+static int cciss_create_ld_sysfs_entry(struct ctlr_info *h,
+				       drive_info_struct *drv,
+				       int drv_index)
+{
+	device_initialize(&drv->dev);
+	drv->dev.type = &cciss_dev_type;
+	drv->dev.bus = &cciss_bus_type;
+	dev_set_name(&drv->dev, "c%dd%d", h->ctlr, drv_index);
+	drv->dev.parent = &h->dev;
+	return device_add(&drv->dev);
+}
+
+/*
+ * Remove sysfs entries for a logical drive.
+ */
+static void cciss_destroy_ld_sysfs_entry(drive_info_struct *drv)
+{
+	device_del(&drv->dev);
+}
+
 /*
  * For operations that cannot sleep, a command block is allocated at init,
  * and managed by cmd_alloc() and cmd_free() using a simple bitmap to track
@@ -1299,7 +1489,6 @@ static void cciss_softirq_done(struct request *rq)
 {
 	CommandList_struct *cmd = rq->completion_data;
 	ctlr_info_t *h = hba[cmd->ctlr];
-	unsigned int nr_bytes;
 	unsigned long flags;
 	u64bit temp64;
 	int i, ddir;
@@ -1321,15 +1510,11 @@ static void cciss_softirq_done(struct request *rq)
 	printk("Done with %p\n", rq);
 #endif				/* CCISS_DEBUG */
 
-	/*
-	 * Store the full size and set the residual count for pc requests
-	 */
-	nr_bytes = blk_rq_bytes(rq);
+	/* set the residual count for pc requests */
 	if (blk_pc_request(rq))
-		rq->data_len = cmd->err_info->ResidualCnt;
+		rq->resid_len = cmd->err_info->ResidualCnt;
 
-	if (blk_end_request(rq, (rq->errors == 0) ? 0 : -EIO, nr_bytes))
-		BUG();
+	blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO);
 
 	spin_lock_irqsave(&h->lock, flags);
 	cmd_free(h, cmd, 1);
@@ -1337,6 +1522,56 @@ static void cciss_softirq_done(struct request *rq)
 	spin_unlock_irqrestore(&h->lock, flags);
 }
 
+static void log_unit_to_scsi3addr(ctlr_info_t *h, unsigned char scsi3addr[],
+	uint32_t log_unit)
+{
+	log_unit = h->drv[log_unit].LunID & 0x03fff;
+	memset(&scsi3addr[4], 0, 4);
+	memcpy(&scsi3addr[0], &log_unit, 4);
+	scsi3addr[3] |= 0x40;
+}
+
+/* This function gets the SCSI vendor, model, and revision of a logical drive
+ * via the inquiry page 0.  Model, vendor, and rev are set to empty strings if
+ * they cannot be read.
+ */
+static void cciss_get_device_descr(int ctlr, int logvol, int withirq,
+				   char *vendor, char *model, char *rev)
+{
+	int rc;
+	InquiryData_struct *inq_buf;
+	unsigned char scsi3addr[8];
+
+	*vendor = '\0';
+	*model = '\0';
+	*rev = '\0';
+
+	inq_buf = kzalloc(sizeof(InquiryData_struct), GFP_KERNEL);
+	if (!inq_buf)
+		return;
+
+	log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol);
+	if (withirq)
+		rc = sendcmd_withirq(CISS_INQUIRY, ctlr, inq_buf,
+			     sizeof(InquiryData_struct), 0,
+				scsi3addr, TYPE_CMD);
+	else
+		rc = sendcmd(CISS_INQUIRY, ctlr, inq_buf,
+			     sizeof(InquiryData_struct), 0,
+				scsi3addr, TYPE_CMD);
+	if (rc == IO_OK) {
+		memcpy(vendor, &inq_buf->data_byte[8], VENDOR_LEN);
+		vendor[VENDOR_LEN] = '\0';
+		memcpy(model, &inq_buf->data_byte[16], MODEL_LEN);
+		model[MODEL_LEN] = '\0';
+		memcpy(rev, &inq_buf->data_byte[32], REV_LEN);
+		rev[REV_LEN] = '\0';
+	}
+
+	kfree(inq_buf);
+	return;
+}
+
 /* This function gets the serial number of a logical drive via
  * inquiry page 0x83.  Serial no. is 16 bytes.  If the serial
  * number cannot be had, for whatever reason, 16 bytes of 0xff
@@ -1348,6 +1583,7 @@ static void cciss_get_serial_no(int ctlr, int logvol, int withirq,
 #define PAGE_83_INQ_BYTES 64
 	int rc;
 	unsigned char *buf;
+	unsigned char scsi3addr[8];
 
 	if (buflen > 16)
 		buflen = 16;
@@ -1356,12 +1592,13 @@ static void cciss_get_serial_no(int ctlr, int logvol, int withirq,
 	if (!buf)
 		return;
 	memset(serial_no, 0, buflen);
+	log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol);
 	if (withirq)
 		rc = sendcmd_withirq(CISS_INQUIRY, ctlr, buf,
-			PAGE_83_INQ_BYTES, 1, logvol, 0x83, TYPE_CMD);
+			PAGE_83_INQ_BYTES, 0x83, scsi3addr, TYPE_CMD);
 	else
 		rc = sendcmd(CISS_INQUIRY, ctlr, buf,
-			PAGE_83_INQ_BYTES, 1, logvol, 0x83, NULL, TYPE_CMD);
+			PAGE_83_INQ_BYTES, 0x83, scsi3addr, TYPE_CMD);
 	if (rc == IO_OK)
 		memcpy(serial_no, &buf[8], buflen);
 	kfree(buf);
@@ -1377,7 +1614,7 @@ static void cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
 	disk->first_minor = drv_index << NWD_SHIFT;
 	disk->fops = &cciss_fops;
 	disk->private_data = &h->drv[drv_index];
-	disk->driverfs_dev = &h->pdev->dev;
+	disk->driverfs_dev = &h->drv[drv_index].dev;
 
 	/* Set up queue information */
 	blk_queue_bounce_limit(disk->queue, h->pdev->dma_mask);
@@ -1394,8 +1631,8 @@ static void cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
 
 	disk->queue->queuedata = h;
 
-	blk_queue_hardsect_size(disk->queue,
-				h->drv[drv_index].block_size);
+	blk_queue_logical_block_size(disk->queue,
+				     h->drv[drv_index].block_size);
 
 	/* Make sure all queue data is written out before */
 	/* setting h->drv[drv_index].queue, as setting this */
@@ -1468,6 +1705,8 @@ static void cciss_update_drive_info(int ctlr, int drv_index, int first_time)
 	drvinfo->block_size = block_size;
 	drvinfo->nr_blocks = total_size + 1;
 
+	cciss_get_device_descr(ctlr, drv_index, 1, drvinfo->vendor,
+				drvinfo->model, drvinfo->rev);
 	cciss_get_serial_no(ctlr, drv_index, 1, drvinfo->serial_no,
 			sizeof(drvinfo->serial_no));
 
@@ -1517,6 +1756,9 @@ static void cciss_update_drive_info(int ctlr, int drv_index, int first_time)
 	h->drv[drv_index].cylinders = drvinfo->cylinders;
 	h->drv[drv_index].raid_level = drvinfo->raid_level;
 	memcpy(h->drv[drv_index].serial_no, drvinfo->serial_no, 16);
+	memcpy(h->drv[drv_index].vendor, drvinfo->vendor, VENDOR_LEN + 1);
+	memcpy(h->drv[drv_index].model, drvinfo->model, MODEL_LEN + 1);
+	memcpy(h->drv[drv_index].rev, drvinfo->rev, REV_LEN + 1);
 
 	++h->num_luns;
 	disk = h->gendisk[drv_index];
@@ -1591,6 +1833,8 @@ static int cciss_add_gendisk(ctlr_info_t *h, __u32 lunid, int controller_node)
 		}
 	}
 	h->drv[drv_index].LunID = lunid;
+	if (cciss_create_ld_sysfs_entry(h, &h->drv[drv_index], drv_index))
+		goto err_free_disk;
 
 	/* Don't need to mark this busy because nobody */
 	/* else knows about this disk yet to contend */
@@ -1598,6 +1842,11 @@ static int cciss_add_gendisk(ctlr_info_t *h, __u32 lunid, int controller_node)
 	h->drv[drv_index].busy_configuring = 0;
 	wmb();
 	return drv_index;
+
+err_free_disk:
+	put_disk(h->gendisk[drv_index]);
+	h->gendisk[drv_index] = NULL;
+	return -1;
 }
 
 /* This is for the special case of a controller which
@@ -1668,8 +1917,8 @@ static int rebuild_lun_table(ctlr_info_t *h, int first_time)
 		goto mem_msg;
 
 	return_code = sendcmd_withirq(CISS_REPORT_LOG, ctlr, ld_buff,
-				      sizeof(ReportLunData_struct), 0,
-				      0, 0, TYPE_CMD);
+				      sizeof(ReportLunData_struct),
+				      0, CTLR_LUNID, TYPE_CMD);
 
 	if (return_code == IO_OK)
 		listlength = be32_to_cpu(*(__be32 *) ld_buff->LUNListLength);
@@ -1718,6 +1967,7 @@ static int rebuild_lun_table(ctlr_info_t *h, int first_time)
 			h->drv[i].busy_configuring = 1;
 			spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
 			return_code = deregister_disk(h, i, 1);
+			cciss_destroy_ld_sysfs_entry(&h->drv[i]);
 			h->drv[i].busy_configuring = 0;
 		}
 	}
@@ -1877,11 +2127,9 @@ static int deregister_disk(ctlr_info_t *h, int drv_index,
 	return 0;
 }
 
-static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_t size, unsigned int use_unit_num,	/* 0: address the controller,
-															   1: address logical volume log_unit,
-															   2: periph device address is scsi3addr */
-		    unsigned int log_unit, __u8 page_code,
-		    unsigned char *scsi3addr, int cmd_type)
+static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff,
+		size_t size, __u8 page_code, unsigned char *scsi3addr,
+		int cmd_type)
 {
 	ctlr_info_t *h = hba[ctlr];
 	u64bit buff_dma_handle;
@@ -1897,27 +2145,12 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 		c->Header.SGTotal = 0;
 	}
 	c->Header.Tag.lower = c->busaddr;
+	memcpy(c->Header.LUN.LunAddrBytes, scsi3addr, 8);
 
 	c->Request.Type.Type = cmd_type;
 	if (cmd_type == TYPE_CMD) {
 		switch (cmd) {
 		case CISS_INQUIRY:
-			/* If the logical unit number is 0 then, this is going
-			   to controller so It's a physical command
-			   mode = 0 target = 0.  So we have nothing to write.
-			   otherwise, if use_unit_num == 1,
-			   mode = 1(volume set addressing) target = LUNID
-			   otherwise, if use_unit_num == 2,
-			   mode = 0(periph dev addr) target = scsi3addr */
-			if (use_unit_num == 1) {
-				c->Header.LUN.LogDev.VolId =
-				    h->drv[log_unit].LunID;
-				c->Header.LUN.LogDev.Mode = 1;
-			} else if (use_unit_num == 2) {
-				memcpy(c->Header.LUN.LunAddrBytes, scsi3addr,
-				       8);
-				c->Header.LUN.LogDev.Mode = 0;
-			}
 			/* are we trying to read a vital product page */
 			if (page_code != 0) {
 				c->Request.CDB[1] = 0x01;
@@ -1947,8 +2180,6 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 			break;
 
 		case CCISS_READ_CAPACITY:
-			c->Header.LUN.LogDev.VolId = h->drv[log_unit].LunID;
-			c->Header.LUN.LogDev.Mode = 1;
 			c->Request.CDBLen = 10;
 			c->Request.Type.Attribute = ATTR_SIMPLE;
 			c->Request.Type.Direction = XFER_READ;
@@ -1956,8 +2187,6 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 			c->Request.CDB[0] = cmd;
 			break;
 		case CCISS_READ_CAPACITY_16:
-			c->Header.LUN.LogDev.VolId = h->drv[log_unit].LunID;
-			c->Header.LUN.LogDev.Mode = 1;
 			c->Request.CDBLen = 16;
 			c->Request.Type.Attribute = ATTR_SIMPLE;
 			c->Request.Type.Direction = XFER_READ;
@@ -1979,6 +2208,12 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 			c->Request.CDB[0] = BMIC_WRITE;
 			c->Request.CDB[6] = BMIC_CACHE_FLUSH;
 			break;
+		case TEST_UNIT_READY:
+			c->Request.CDBLen = 6;
+			c->Request.Type.Attribute = ATTR_SIMPLE;
+			c->Request.Type.Direction = XFER_NONE;
+			c->Request.Timeout = 0;
+			break;
 		default:
 			printk(KERN_WARNING
 			       "cciss%d:  Unknown Command 0x%c\n", ctlr, cmd);
@@ -1997,13 +2232,13 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 			memcpy(&c->Request.CDB[4], buff, 8);
 			break;
 		case 1:	/* RESET message */
-			c->Request.CDBLen = 12;
+			c->Request.CDBLen = 16;
 			c->Request.Type.Attribute = ATTR_SIMPLE;
-			c->Request.Type.Direction = XFER_WRITE;
+			c->Request.Type.Direction = XFER_NONE;
 			c->Request.Timeout = 0;
 			memset(&c->Request.CDB[0], 0, sizeof(c->Request.CDB));
 			c->Request.CDB[0] = cmd;	/* reset */
-			c->Request.CDB[1] = 0x04;	/* reset a LUN */
+			c->Request.CDB[1] = 0x03;	/* reset a target */
 			break;
 		case 3:	/* No-Op message */
 			c->Request.CDBLen = 1;
@@ -2035,114 +2270,152 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 	return status;
 }
 
-static int sendcmd_withirq(__u8 cmd,
-			   int ctlr,
-			   void *buff,
-			   size_t size,
-			   unsigned int use_unit_num,
-			   unsigned int log_unit, __u8 page_code, int cmd_type)
+static int check_target_status(ctlr_info_t *h, CommandList_struct *c)
 {
-	ctlr_info_t *h = hba[ctlr];
-	CommandList_struct *c;
+	switch (c->err_info->ScsiStatus) {
+	case SAM_STAT_GOOD:
+		return IO_OK;
+	case SAM_STAT_CHECK_CONDITION:
+		switch (0xf & c->err_info->SenseInfo[2]) {
+		case 0: return IO_OK; /* no sense */
+		case 1: return IO_OK; /* recovered error */
+		default:
+			printk(KERN_WARNING "cciss%d: cmd 0x%02x "
+				"check condition, sense key = 0x%02x\n",
+				h->ctlr, c->Request.CDB[0],
+				c->err_info->SenseInfo[2]);
+		}
+		break;
+	default:
+		printk(KERN_WARNING "cciss%d: cmd 0x%02x"
+			"scsi status = 0x%02x\n", h->ctlr,
+			c->Request.CDB[0], c->err_info->ScsiStatus);
+		break;
+	}
+	return IO_ERROR;
+}
+
+static int process_sendcmd_error(ctlr_info_t *h, CommandList_struct *c)
+{
+	int return_status = IO_OK;
+
+	if (c->err_info->CommandStatus == CMD_SUCCESS)
+		return IO_OK;
+
+	switch (c->err_info->CommandStatus) {
+	case CMD_TARGET_STATUS:
+		return_status = check_target_status(h, c);
+		break;
+	case CMD_DATA_UNDERRUN:
+	case CMD_DATA_OVERRUN:
+		/* expected for inquiry and report lun commands */
+		break;
+	case CMD_INVALID:
+		printk(KERN_WARNING "cciss: cmd 0x%02x is "
+		       "reported invalid\n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_PROTOCOL_ERR:
+		printk(KERN_WARNING "cciss: cmd 0x%02x has "
+		       "protocol error \n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_HARDWARE_ERR:
+		printk(KERN_WARNING "cciss: cmd 0x%02x had "
+		       " hardware error\n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_CONNECTION_LOST:
+		printk(KERN_WARNING "cciss: cmd 0x%02x had "
+		       "connection lost\n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_ABORTED:
+		printk(KERN_WARNING "cciss: cmd 0x%02x was "
+		       "aborted\n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_ABORT_FAILED:
+		printk(KERN_WARNING "cciss: cmd 0x%02x reports "
+		       "abort failed\n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_UNSOLICITED_ABORT:
+		printk(KERN_WARNING
+		       "cciss%d: unsolicited abort 0x%02x\n", h->ctlr,
+			c->Request.CDB[0]);
+		return_status = IO_NEEDS_RETRY;
+		break;
+	default:
+		printk(KERN_WARNING "cciss: cmd 0x%02x returned "
+		       "unknown status %x\n", c->Request.CDB[0],
+		       c->err_info->CommandStatus);
+		return_status = IO_ERROR;
+	}
+	return return_status;
+}
+
+static int sendcmd_withirq_core(ctlr_info_t *h, CommandList_struct *c,
+	int attempt_retry)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
 	u64bit buff_dma_handle;
 	unsigned long flags;
-	int return_status;
-	DECLARE_COMPLETION_ONSTACK(wait);
+	int return_status = IO_OK;
 
-	if ((c = cmd_alloc(h, 0)) == NULL)
-		return -ENOMEM;
-	return_status = fill_cmd(c, cmd, ctlr, buff, size, use_unit_num,
-				 log_unit, page_code, NULL, cmd_type);
-	if (return_status != IO_OK) {
-		cmd_free(h, c, 0);
-		return return_status;
-	}
-      resend_cmd2:
+resend_cmd2:
 	c->waiting = &wait;
-
 	/* Put the request on the tail of the queue and send it */
-	spin_lock_irqsave(CCISS_LOCK(ctlr), flags);
+	spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
 	addQ(&h->reqQ, c);
 	h->Qdepth++;
 	start_io(h);
-	spin_unlock_irqrestore(CCISS_LOCK(ctlr), flags);
+	spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
 
 	wait_for_completion(&wait);
 
-	if (c->err_info->CommandStatus != 0) {	/* an error has occurred */
-		switch (c->err_info->CommandStatus) {
-		case CMD_TARGET_STATUS:
-			printk(KERN_WARNING "cciss: cmd %p has "
-			       " completed with errors\n", c);
-			if (c->err_info->ScsiStatus) {
-				printk(KERN_WARNING "cciss: cmd %p "
-				       "has SCSI Status = %x\n",
-				       c, c->err_info->ScsiStatus);
-			}
+	if (c->err_info->CommandStatus == 0 || !attempt_retry)
+		goto command_done;
 
-			break;
-		case CMD_DATA_UNDERRUN:
-		case CMD_DATA_OVERRUN:
-			/* expected for inquire and report lun commands */
-			break;
-		case CMD_INVALID:
-			printk(KERN_WARNING "cciss: Cmd %p is "
-			       "reported invalid\n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_PROTOCOL_ERR:
-			printk(KERN_WARNING "cciss: cmd %p has "
-			       "protocol error \n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_HARDWARE_ERR:
-			printk(KERN_WARNING "cciss: cmd %p had "
-			       " hardware error\n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_CONNECTION_LOST:
-			printk(KERN_WARNING "cciss: cmd %p had "
-			       "connection lost\n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_ABORTED:
-			printk(KERN_WARNING "cciss: cmd %p was "
-			       "aborted\n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_ABORT_FAILED:
-			printk(KERN_WARNING "cciss: cmd %p reports "
-			       "abort failed\n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_UNSOLICITED_ABORT:
-			printk(KERN_WARNING
-			       "cciss%d: unsolicited abort %p\n", ctlr, c);
-			if (c->retry_count < MAX_CMD_RETRIES) {
-				printk(KERN_WARNING
-				       "cciss%d: retrying %p\n", ctlr, c);
-				c->retry_count++;
-				/* erase the old error information */
-				memset(c->err_info, 0,
-				       sizeof(ErrorInfo_struct));
-				return_status = IO_OK;
-				INIT_COMPLETION(wait);
-				goto resend_cmd2;
-			}
-			return_status = IO_ERROR;
-			break;
-		default:
-			printk(KERN_WARNING "cciss: cmd %p returned "
-			       "unknown status %x\n", c,
-			       c->err_info->CommandStatus);
-			return_status = IO_ERROR;
-		}
+	return_status = process_sendcmd_error(h, c);
+
+	if (return_status == IO_NEEDS_RETRY &&
+		c->retry_count < MAX_CMD_RETRIES) {
+		printk(KERN_WARNING "cciss%d: retrying 0x%02x\n", h->ctlr,
+			c->Request.CDB[0]);
+		c->retry_count++;
+		/* erase the old error information */
+		memset(c->err_info, 0, sizeof(ErrorInfo_struct));
+		return_status = IO_OK;
+		INIT_COMPLETION(wait);
+		goto resend_cmd2;
 	}
+
+command_done:
 	/* unlock the buffers from DMA */
 	buff_dma_handle.val32.lower = c->SG[0].Addr.lower;
 	buff_dma_handle.val32.upper = c->SG[0].Addr.upper;
 	pci_unmap_single(h->pdev, (dma_addr_t) buff_dma_handle.val,
 			 c->SG[0].Len, PCI_DMA_BIDIRECTIONAL);
+	return return_status;
+}
+
+static int sendcmd_withirq(__u8 cmd, int ctlr, void *buff, size_t size,
+			   __u8 page_code, unsigned char scsi3addr[],
+			int cmd_type)
+{
+	ctlr_info_t *h = hba[ctlr];
+	CommandList_struct *c;
+	int return_status;
+
+	c = cmd_alloc(h, 0);
+	if (!c)
+		return -ENOMEM;
+	return_status = fill_cmd(c, cmd, ctlr, buff, size, page_code,
+		scsi3addr, cmd_type);
+	if (return_status == IO_OK)
+		return_status = sendcmd_withirq_core(h, c, 1);
+
 	cmd_free(h, c, 0);
 	return return_status;
 }
@@ -2155,15 +2428,17 @@ static void cciss_geometry_inquiry(int ctlr, int logvol,
 {
 	int return_code;
 	unsigned long t;
+	unsigned char scsi3addr[8];
 
 	memset(inq_buff, 0, sizeof(InquiryData_struct));
+	log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol);
 	if (withirq)
 		return_code = sendcmd_withirq(CISS_INQUIRY, ctlr,
-					      inq_buff, sizeof(*inq_buff), 1,
-					      logvol, 0xC1, TYPE_CMD);
+					      inq_buff, sizeof(*inq_buff),
+					      0xC1, scsi3addr, TYPE_CMD);
 	else
 		return_code = sendcmd(CISS_INQUIRY, ctlr, inq_buff,
-				      sizeof(*inq_buff), 1, logvol, 0xC1, NULL,
+				      sizeof(*inq_buff), 0xC1, scsi3addr,
 				      TYPE_CMD);
 	if (return_code == IO_OK) {
 		if (inq_buff->data_byte[8] == 0xFF) {
@@ -2204,6 +2479,7 @@ cciss_read_capacity(int ctlr, int logvol, int withirq, sector_t *total_size,
 {
 	ReadCapdata_struct *buf;
 	int return_code;
+	unsigned char scsi3addr[8];
 
 	buf = kzalloc(sizeof(ReadCapdata_struct), GFP_KERNEL);
 	if (!buf) {
@@ -2211,14 +2487,15 @@ cciss_read_capacity(int ctlr, int logvol, int withirq, sector_t *total_size,
 		return;
 	}
 
+	log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol);
 	if (withirq)
 		return_code = sendcmd_withirq(CCISS_READ_CAPACITY,
 				ctlr, buf, sizeof(ReadCapdata_struct),
-					1, logvol, 0, TYPE_CMD);
+					0, scsi3addr, TYPE_CMD);
 	else
 		return_code = sendcmd(CCISS_READ_CAPACITY,
 				ctlr, buf, sizeof(ReadCapdata_struct),
-					1, logvol, 0, NULL, TYPE_CMD);
+					0, scsi3addr, TYPE_CMD);
 	if (return_code == IO_OK) {
 		*total_size = be32_to_cpu(*(__be32 *) buf->total_size);
 		*block_size = be32_to_cpu(*(__be32 *) buf->block_size);
@@ -2238,6 +2515,7 @@ cciss_read_capacity_16(int ctlr, int logvol, int withirq, sector_t *total_size,
 {
 	ReadCapdata_struct_16 *buf;
 	int return_code;
+	unsigned char scsi3addr[8];
 
 	buf = kzalloc(sizeof(ReadCapdata_struct_16), GFP_KERNEL);
 	if (!buf) {
@@ -2245,15 +2523,16 @@ cciss_read_capacity_16(int ctlr, int logvol, int withirq, sector_t *total_size,
 		return;
 	}
 
+	log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol);
 	if (withirq) {
 		return_code = sendcmd_withirq(CCISS_READ_CAPACITY_16,
 			ctlr, buf, sizeof(ReadCapdata_struct_16),
-				1, logvol, 0, TYPE_CMD);
+				0, scsi3addr, TYPE_CMD);
 	}
 	else {
 		return_code = sendcmd(CCISS_READ_CAPACITY_16,
 			ctlr, buf, sizeof(ReadCapdata_struct_16),
-				1, logvol, 0, NULL, TYPE_CMD);
+				0, scsi3addr, TYPE_CMD);
 	}
 	if (return_code == IO_OK) {
 		*total_size = be64_to_cpu(*(__be64 *) buf->total_size);
@@ -2303,7 +2582,7 @@ static int cciss_revalidate(struct gendisk *disk)
 	cciss_geometry_inquiry(h->ctlr, logvol, 1, total_size, block_size,
 			       inq_buff, drv);
 
-	blk_queue_hardsect_size(drv->queue, drv->block_size);
+	blk_queue_logical_block_size(drv->queue, drv->block_size);
 	set_capacity(disk, drv->nr_blocks);
 
 	kfree(inq_buff);
@@ -2333,86 +2612,21 @@ static unsigned long pollcomplete(int ctlr)
 	return 1;
 }
 
-static int add_sendcmd_reject(__u8 cmd, int ctlr, unsigned long complete)
-{
-	/* We get in here if sendcmd() is polling for completions
-	   and gets some command back that it wasn't expecting --
-	   something other than that which it just sent down.
-	   Ordinarily, that shouldn't happen, but it can happen when
-	   the scsi tape stuff gets into error handling mode, and
-	   starts using sendcmd() to try to abort commands and
-	   reset tape drives.  In that case, sendcmd may pick up
-	   completions of commands that were sent to logical drives
-	   through the block i/o system, or cciss ioctls completing, etc.
-	   In that case, we need to save those completions for later
-	   processing by the interrupt handler.
-	 */
-
-#ifdef CONFIG_CISS_SCSI_TAPE
-	struct sendcmd_reject_list *srl = &hba[ctlr]->scsi_rejects;
-
-	/* If it's not the scsi tape stuff doing error handling, (abort */
-	/* or reset) then we don't expect anything weird. */
-	if (cmd != CCISS_RESET_MSG && cmd != CCISS_ABORT_MSG) {
-#endif
-		printk(KERN_WARNING "cciss cciss%d: SendCmd "
-		       "Invalid command list address returned! (%lx)\n",
-		       ctlr, complete);
-		/* not much we can do. */
-#ifdef CONFIG_CISS_SCSI_TAPE
-		return 1;
-	}
-
-	/* We've sent down an abort or reset, but something else
-	   has completed */
-	if (srl->ncompletions >= (hba[ctlr]->nr_cmds + 2)) {
-		/* Uh oh.  No room to save it for later... */
-		printk(KERN_WARNING "cciss%d: Sendcmd: Invalid command addr, "
-		       "reject list overflow, command lost!\n", ctlr);
-		return 1;
-	}
-	/* Save it for later */
-	srl->complete[srl->ncompletions] = complete;
-	srl->ncompletions++;
-#endif
-	return 0;
-}
-
-/*
- * Send a command to the controller, and wait for it to complete.
- * Only used at init time.
+/* Send command c to controller h and poll for it to complete.
+ * Turns interrupts off on the board.  Used at driver init time
+ * and during SCSI error recovery.
  */
-static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size, unsigned int use_unit_num,	/* 0: address the controller,
-												   1: address logical volume log_unit,
-												   2: periph device address is scsi3addr */
-		   unsigned int log_unit,
-		   __u8 page_code, unsigned char *scsi3addr, int cmd_type)
+static int sendcmd_core(ctlr_info_t *h, CommandList_struct *c)
 {
-	CommandList_struct *c;
 	int i;
 	unsigned long complete;
-	ctlr_info_t *info_p = hba[ctlr];
+	int status = IO_ERROR;
 	u64bit buff_dma_handle;
-	int status, done = 0;
 
-	if ((c = cmd_alloc(info_p, 1)) == NULL) {
-		printk(KERN_WARNING "cciss: unable to get memory");
-		return IO_ERROR;
-	}
-	status = fill_cmd(c, cmd, ctlr, buff, size, use_unit_num,
-			  log_unit, page_code, scsi3addr, cmd_type);
-	if (status != IO_OK) {
-		cmd_free(info_p, c, 1);
-		return status;
-	}
-      resend_cmd1:
-	/*
-	 * Disable interrupt
-	 */
-#ifdef CCISS_DEBUG
-	printk(KERN_DEBUG "cciss: turning intr off\n");
-#endif				/* CCISS_DEBUG */
-	info_p->access.set_intr_mask(info_p, CCISS_INTR_OFF);
+resend_cmd1:
+
+	/* Disable interrupt on the board. */
+	h->access.set_intr_mask(h, CCISS_INTR_OFF);
 
 	/* Make sure there is room in the command FIFO */
 	/* Actually it should be completely empty at this time */
@@ -2420,21 +2634,15 @@ static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size, unsigned int use
 	/* tape side of the driver. */
 	for (i = 200000; i > 0; i--) {
 		/* if fifo isn't full go */
-		if (!(info_p->access.fifo_full(info_p))) {
-
+		if (!(h->access.fifo_full(h)))
 			break;
-		}
 		udelay(10);
 		printk(KERN_WARNING "cciss cciss%d: SendCmd FIFO full,"
-		       " waiting!\n", ctlr);
+		       " waiting!\n", h->ctlr);
 	}
-	/*
-	 * Send the cmd
-	 */
-	info_p->access.submit_command(info_p, c);
-	done = 0;
+	h->access.submit_command(h, c); /* Send the cmd */
 	do {
-		complete = pollcomplete(ctlr);
+		complete = pollcomplete(h->ctlr);
 
 #ifdef CCISS_DEBUG
 		printk(KERN_DEBUG "cciss: command completed\n");
@@ -2443,97 +2651,102 @@ static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size, unsigned int use
 		if (complete == 1) {
 			printk(KERN_WARNING
 			       "cciss cciss%d: SendCmd Timeout out, "
-			       "No command list address returned!\n", ctlr);
+			       "No command list address returned!\n", h->ctlr);
 			status = IO_ERROR;
-			done = 1;
 			break;
 		}
 
-		/* This will need to change for direct lookup completions */
-		if ((complete & CISS_ERROR_BIT)
-		    && (complete & ~CISS_ERROR_BIT) == c->busaddr) {
-			/* if data overrun or underun on Report command
-			   ignore it
-			 */
-			if (((c->Request.CDB[0] == CISS_REPORT_LOG) ||
-			     (c->Request.CDB[0] == CISS_REPORT_PHYS) ||
-			     (c->Request.CDB[0] == CISS_INQUIRY)) &&
-			    ((c->err_info->CommandStatus ==
-			      CMD_DATA_OVERRUN) ||
-			     (c->err_info->CommandStatus == CMD_DATA_UNDERRUN)
-			    )) {
-				complete = c->busaddr;
-			} else {
-				if (c->err_info->CommandStatus ==
-				    CMD_UNSOLICITED_ABORT) {
-					printk(KERN_WARNING "cciss%d: "
-					       "unsolicited abort %p\n",
-					       ctlr, c);
-					if (c->retry_count < MAX_CMD_RETRIES) {
-						printk(KERN_WARNING
-						       "cciss%d: retrying %p\n",
-						       ctlr, c);
-						c->retry_count++;
-						/* erase the old error */
-						/* information */
-						memset(c->err_info, 0,
-						       sizeof
-						       (ErrorInfo_struct));
-						goto resend_cmd1;
-					} else {
-						printk(KERN_WARNING
-						       "cciss%d: retried %p too "
-						       "many times\n", ctlr, c);
-						status = IO_ERROR;
-						goto cleanup1;
-					}
-				} else if (c->err_info->CommandStatus ==
-					   CMD_UNABORTABLE) {
-					printk(KERN_WARNING
-					       "cciss%d: command could not be aborted.\n",
-					       ctlr);
-					status = IO_ERROR;
-					goto cleanup1;
-				}
-				printk(KERN_WARNING "ciss ciss%d: sendcmd"
-				       " Error %x \n", ctlr,
-				       c->err_info->CommandStatus);
-				printk(KERN_WARNING "ciss ciss%d: sendcmd"
-				       " offensive info\n"
-				       "  size %x\n   num %x   value %x\n",
-				       ctlr,
-				       c->err_info->MoreErrInfo.Invalid_Cmd.
-				       offense_size,
-				       c->err_info->MoreErrInfo.Invalid_Cmd.
-				       offense_num,
-				       c->err_info->MoreErrInfo.Invalid_Cmd.
-				       offense_value);
-				status = IO_ERROR;
-				goto cleanup1;
-			}
+		/* Make sure it's the command we're expecting. */
+		if ((complete & ~CISS_ERROR_BIT) != c->busaddr) {
+			printk(KERN_WARNING "cciss%d: Unexpected command "
+				"completion.\n", h->ctlr);
+			continue;
+		}
+
+		/* It is our command.  If no error, we're done. */
+		if (!(complete & CISS_ERROR_BIT)) {
+			status = IO_OK;
+			break;
 		}
-		/* This will need changing for direct lookup completions */
-		if (complete != c->busaddr) {
-			if (add_sendcmd_reject(cmd, ctlr, complete) != 0) {
-				BUG();	/* we are pretty much hosed if we get here. */
+
+		/* There is an error... */
+
+		/* if data overrun or underun on Report command ignore it */
+		if (((c->Request.CDB[0] == CISS_REPORT_LOG) ||
+		     (c->Request.CDB[0] == CISS_REPORT_PHYS) ||
+		     (c->Request.CDB[0] == CISS_INQUIRY)) &&
+			((c->err_info->CommandStatus == CMD_DATA_OVERRUN) ||
+			 (c->err_info->CommandStatus == CMD_DATA_UNDERRUN))) {
+			complete = c->busaddr;
+			status = IO_OK;
+			break;
+		}
+
+		if (c->err_info->CommandStatus == CMD_UNSOLICITED_ABORT) {
+			printk(KERN_WARNING "cciss%d: unsolicited abort %p\n",
+				h->ctlr, c);
+			if (c->retry_count < MAX_CMD_RETRIES) {
+				printk(KERN_WARNING "cciss%d: retrying %p\n",
+				   h->ctlr, c);
+				c->retry_count++;
+				/* erase the old error information */
+				memset(c->err_info, 0, sizeof(c->err_info));
+				goto resend_cmd1;
 			}
-			continue;
-		} else
-			done = 1;
-	} while (!done);
+			printk(KERN_WARNING "cciss%d: retried %p too many "
+				"times\n", h->ctlr, c);
+			status = IO_ERROR;
+			break;
+		}
+
+		if (c->err_info->CommandStatus == CMD_UNABORTABLE) {
+			printk(KERN_WARNING "cciss%d: command could not be "
+				"aborted.\n", h->ctlr);
+			status = IO_ERROR;
+			break;
+		}
+
+		if (c->err_info->CommandStatus == CMD_TARGET_STATUS) {
+			status = check_target_status(h, c);
+			break;
+		}
+
+		printk(KERN_WARNING "cciss%d: sendcmd error\n", h->ctlr);
+		printk(KERN_WARNING "cmd = 0x%02x, CommandStatus = 0x%02x\n",
+			c->Request.CDB[0], c->err_info->CommandStatus);
+		status = IO_ERROR;
+		break;
+
+	} while (1);
 
-      cleanup1:
 	/* unlock the data buffer from DMA */
 	buff_dma_handle.val32.lower = c->SG[0].Addr.lower;
 	buff_dma_handle.val32.upper = c->SG[0].Addr.upper;
-	pci_unmap_single(info_p->pdev, (dma_addr_t) buff_dma_handle.val,
+	pci_unmap_single(h->pdev, (dma_addr_t) buff_dma_handle.val,
 			 c->SG[0].Len, PCI_DMA_BIDIRECTIONAL);
-#ifdef CONFIG_CISS_SCSI_TAPE
-	/* if we saved some commands for later, process them now. */
-	if (info_p->scsi_rejects.ncompletions > 0)
-		do_cciss_intr(0, info_p);
-#endif
-	cmd_free(info_p, c, 1);
+	return status;
+}
+
+/*
+ * Send a command to the controller, and wait for it to complete.
+ * Used at init time, and during SCSI error recovery.
+ */
+static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size,
+	__u8 page_code, unsigned char *scsi3addr, int cmd_type)
+{
+	CommandList_struct *c;
+	int status;
+
+	c = cmd_alloc(hba[ctlr], 1);
+	if (!c) {
+		printk(KERN_WARNING "cciss: unable to get memory");
+		return IO_ERROR;
+	}
+	status = fill_cmd(c, cmd, ctlr, buff, size, page_code,
+		scsi3addr, cmd_type);
+	if (status == IO_OK)
+		status = sendcmd_core(hba[ctlr], c);
+	cmd_free(hba[ctlr], c, 1);
 	return status;
 }
 
@@ -2691,7 +2904,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 			printk(KERN_WARNING "cciss: cmd %p has"
 			       " completed with data underrun "
 			       "reported\n", cmd);
-			cmd->rq->data_len = cmd->err_info->ResidualCnt;
+			cmd->rq->resid_len = cmd->err_info->ResidualCnt;
 		}
 		break;
 	case CMD_DATA_OVERRUN:
@@ -2806,7 +3019,7 @@ static void do_cciss_request(struct request_queue *q)
 		goto startio;
 
       queue:
-	creq = elv_next_request(q);
+	creq = blk_peek_request(q);
 	if (!creq)
 		goto startio;
 
@@ -2815,7 +3028,7 @@ static void do_cciss_request(struct request_queue *q)
 	if ((c = cmd_alloc(h, 1)) == NULL)
 		goto full;
 
-	blkdev_dequeue_request(creq);
+	blk_start_request(creq);
 
 	spin_unlock_irq(q->queue_lock);
 
@@ -2840,10 +3053,10 @@ static void do_cciss_request(struct request_queue *q)
 	c->Request.Timeout = 0;	// Don't time out
 	c->Request.CDB[0] =
 	    (rq_data_dir(creq) == READ) ? h->cciss_read : h->cciss_write;
-	start_blk = creq->sector;
+	start_blk = blk_rq_pos(creq);
 #ifdef CCISS_DEBUG
-	printk(KERN_DEBUG "ciss: sector =%d nr_sectors=%d\n", (int)creq->sector,
-	       (int)creq->nr_sectors);
+	printk(KERN_DEBUG "ciss: sector =%d nr_sectors=%d\n",
+	       (int)blk_rq_pos(creq), (int)blk_rq_sectors(creq));
 #endif				/* CCISS_DEBUG */
 
 	sg_init_table(tmp_sg, MAXSGENTRIES);
@@ -2869,8 +3082,8 @@ static void do_cciss_request(struct request_queue *q)
 		h->maxSG = seg;
 
 #ifdef CCISS_DEBUG
-	printk(KERN_DEBUG "cciss: Submitting %lu sectors in %d segments\n",
-	       creq->nr_sectors, seg);
+	printk(KERN_DEBUG "cciss: Submitting %u sectors in %d segments\n",
+	       blk_rq_sectors(creq), seg);
 #endif				/* CCISS_DEBUG */
 
 	c->Header.SGList = c->Header.SGTotal = seg;
@@ -2882,8 +3095,8 @@ static void do_cciss_request(struct request_queue *q)
 			c->Request.CDB[4] = (start_blk >> 8) & 0xff;
 			c->Request.CDB[5] = start_blk & 0xff;
 			c->Request.CDB[6] = 0;	// (sect >> 24) & 0xff; MSB
-			c->Request.CDB[7] = (creq->nr_sectors >> 8) & 0xff;
-			c->Request.CDB[8] = creq->nr_sectors & 0xff;
+			c->Request.CDB[7] = (blk_rq_sectors(creq) >> 8) & 0xff;
+			c->Request.CDB[8] = blk_rq_sectors(creq) & 0xff;
 			c->Request.CDB[9] = c->Request.CDB[11] = c->Request.CDB[12] = 0;
 		} else {
 			u32 upper32 = upper_32_bits(start_blk);
@@ -2898,10 +3111,10 @@ static void do_cciss_request(struct request_queue *q)
 			c->Request.CDB[7]= (start_blk >> 16) & 0xff;
 			c->Request.CDB[8]= (start_blk >>  8) & 0xff;
 			c->Request.CDB[9]= start_blk & 0xff;
-			c->Request.CDB[10]= (creq->nr_sectors >>  24) & 0xff;
-			c->Request.CDB[11]= (creq->nr_sectors >>  16) & 0xff;
-			c->Request.CDB[12]= (creq->nr_sectors >>  8) & 0xff;
-			c->Request.CDB[13]= creq->nr_sectors & 0xff;
+			c->Request.CDB[10]= (blk_rq_sectors(creq) >> 24) & 0xff;
+			c->Request.CDB[11]= (blk_rq_sectors(creq) >> 16) & 0xff;
+			c->Request.CDB[12]= (blk_rq_sectors(creq) >>  8) & 0xff;
+			c->Request.CDB[13]= blk_rq_sectors(creq) & 0xff;
 			c->Request.CDB[14] = c->Request.CDB[15] = 0;
 		}
 	} else if (blk_pc_request(creq)) {
@@ -2931,44 +3144,18 @@ startio:
 
 static inline unsigned long get_next_completion(ctlr_info_t *h)
 {
-#ifdef CONFIG_CISS_SCSI_TAPE
-	/* Any rejects from sendcmd() lying around? Process them first */
-	if (h->scsi_rejects.ncompletions == 0)
-		return h->access.command_completed(h);
-	else {
-		struct sendcmd_reject_list *srl;
-		int n;
-		srl = &h->scsi_rejects;
-		n = --srl->ncompletions;
-		/* printk("cciss%d: processing saved reject\n", h->ctlr); */
-		printk("p");
-		return srl->complete[n];
-	}
-#else
 	return h->access.command_completed(h);
-#endif
 }
 
 static inline int interrupt_pending(ctlr_info_t *h)
 {
-#ifdef CONFIG_CISS_SCSI_TAPE
-	return (h->access.intr_pending(h)
-		|| (h->scsi_rejects.ncompletions > 0));
-#else
 	return h->access.intr_pending(h);
-#endif
 }
 
 static inline long interrupt_not_for_us(ctlr_info_t *h)
 {
-#ifdef CONFIG_CISS_SCSI_TAPE
-	return (((h->access.intr_pending(h) == 0) ||
-		 (h->interrupts_enabled == 0))
-		&& (h->scsi_rejects.ncompletions == 0));
-#else
 	return (((h->access.intr_pending(h) == 0) ||
 		 (h->interrupts_enabled == 0)));
-#endif
 }
 
 static irqreturn_t do_cciss_intr(int irq, void *dev_id)
@@ -3723,12 +3910,15 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 	INIT_HLIST_HEAD(&hba[i]->reqQ);
 
 	if (cciss_pci_init(hba[i], pdev) != 0)
-		goto clean1;
+		goto clean0;
 
 	sprintf(hba[i]->devname, "cciss%d", i);
 	hba[i]->ctlr = i;
 	hba[i]->pdev = pdev;
 
+	if (cciss_create_hba_sysfs_entry(hba[i]))
+		goto clean0;
+
 	/* configure PCI DMA stuff */
 	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64)))
 		dac = 1;
@@ -3787,15 +3977,6 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 		printk(KERN_ERR "cciss: out of memory");
 		goto clean4;
 	}
-#ifdef CONFIG_CISS_SCSI_TAPE
-	hba[i]->scsi_rejects.complete =
-	    kmalloc(sizeof(hba[i]->scsi_rejects.complete[0]) *
-		    (hba[i]->nr_cmds + 5), GFP_KERNEL);
-	if (hba[i]->scsi_rejects.complete == NULL) {
-		printk(KERN_ERR "cciss: out of memory");
-		goto clean4;
-	}
-#endif
 	spin_lock_init(&hba[i]->lock);
 
 	/* Initialize the pdev driver private data.
@@ -3828,7 +4009,7 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 	}
 
 	return_code = sendcmd_withirq(CISS_INQUIRY, i, inq_buff,
-		sizeof(InquiryData_struct), 0, 0 , 0, TYPE_CMD);
+		sizeof(InquiryData_struct), 0, CTLR_LUNID, TYPE_CMD);
 	if (return_code == IO_OK) {
 		hba[i]->firm_ver[0] = inq_buff->data_byte[32];
 		hba[i]->firm_ver[1] = inq_buff->data_byte[33];
@@ -3855,9 +4036,6 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 
 clean4:
 	kfree(inq_buff);
-#ifdef CONFIG_CISS_SCSI_TAPE
-	kfree(hba[i]->scsi_rejects.complete);
-#endif
 	kfree(hba[i]->cmd_pool_bits);
 	if (hba[i]->cmd_pool)
 		pci_free_consistent(hba[i]->pdev,
@@ -3872,6 +4050,8 @@ clean4:
 clean2:
 	unregister_blkdev(hba[i]->major, hba[i]->devname);
 clean1:
+	cciss_destroy_hba_sysfs_entry(hba[i]);
+clean0:
 	hba[i]->busy_initializing = 0;
 	/* cleanup any queues that may have been initialized */
 	for (j=0; j <= hba[i]->highest_lun; j++){
@@ -3907,8 +4087,8 @@ static void cciss_shutdown(struct pci_dev *pdev)
 	/* sendcmd will turn off interrupt, and send the flush...
 	 * To write all data in the battery backed cache to disks */
 	memset(flush_buf, 0, 4);
-	return_code = sendcmd(CCISS_CACHE_FLUSH, i, flush_buf, 4, 0, 0, 0, NULL,
-			      TYPE_CMD);
+	return_code = sendcmd(CCISS_CACHE_FLUSH, i, flush_buf, 4, 0,
+		CTLR_LUNID, TYPE_CMD);
 	if (return_code == IO_OK) {
 		printk(KERN_INFO "Completed flushing cache on controller %d\n", i);
 	} else {
@@ -3973,15 +4153,13 @@ static void __devexit cciss_remove_one(struct pci_dev *pdev)
 	pci_free_consistent(hba[i]->pdev, hba[i]->nr_cmds * sizeof(ErrorInfo_struct),
 			    hba[i]->errinfo_pool, hba[i]->errinfo_pool_dhandle);
 	kfree(hba[i]->cmd_pool_bits);
-#ifdef CONFIG_CISS_SCSI_TAPE
-	kfree(hba[i]->scsi_rejects.complete);
-#endif
 	/*
 	 * Deliberately omit pci_disable_device(): it does something nasty to
 	 * Smart Array controllers that pci_enable_device does not undo
 	 */
 	pci_release_regions(pdev);
 	pci_set_drvdata(pdev, NULL);
+	cciss_destroy_hba_sysfs_entry(hba[i]);
 	free_hba(i);
 }
 
@@ -3999,6 +4177,8 @@ static struct pci_driver cciss_pci_driver = {
  */
 static int __init cciss_init(void)
 {
+	int err;
+
 	/*
 	 * The hardware requires that commands are aligned on a 64-bit
 	 * boundary. Given that we use pci_alloc_consistent() to allocate an
@@ -4008,8 +4188,20 @@ static int __init cciss_init(void)
 
 	printk(KERN_INFO DRIVER_NAME "\n");
 
+	err = bus_register(&cciss_bus_type);
+	if (err)
+		return err;
+
 	/* Register for our PCI devices */
-	return pci_register_driver(&cciss_pci_driver);
+	err = pci_register_driver(&cciss_pci_driver);
+	if (err)
+		goto err_bus_register;
+
+	return 0;
+
+err_bus_register:
+	bus_unregister(&cciss_bus_type);
+	return err;
 }
 
 static void __exit cciss_cleanup(void)
@@ -4026,6 +4218,7 @@ static void __exit cciss_cleanup(void)
 		}
 	}
 	remove_proc_entry("driver/cciss", NULL);
+	bus_unregister(&cciss_bus_type);
 }
 
 static void fail_all_cmds(unsigned long ctlr)

drivers/block/cciss.h

@@ -11,6 +11,11 @@
 
 #define IO_OK		0
 #define IO_ERROR	1
+#define IO_NEEDS_RETRY  3
+
+#define VENDOR_LEN	8
+#define MODEL_LEN	16
+#define REV_LEN		4
 
 struct ctlr_info;
 typedef struct ctlr_info ctlr_info_t;
@@ -34,23 +39,20 @@ typedef struct _drive_info_struct
 	int 	cylinders;
 	int	raid_level; /* set to -1 to indicate that
 			     * the drive is not in use/configured
-			    */
-	int	busy_configuring; /*This is set when the drive is being removed
-				   *to prevent it from being opened or it's queue
-				   *from being started.
-				  */
-	__u8 serial_no[16]; /* from inquiry page 0x83, */
-			    /* not necc. null terminated. */
+			     */
+	int	busy_configuring; /* This is set when a drive is being removed
+				   * to prevent it from being opened or it's
+				   * queue from being started.
+				   */
+	struct	device dev;
+	__u8 serial_no[16]; /* from inquiry page 0x83,
+			     * not necc. null terminated.
+			     */
+	char vendor[VENDOR_LEN + 1]; /* SCSI vendor string */
+	char model[MODEL_LEN + 1];   /* SCSI model string */
+	char rev[REV_LEN + 1];       /* SCSI revision string */
 } drive_info_struct;
 
-#ifdef CONFIG_CISS_SCSI_TAPE
-
-struct sendcmd_reject_list {
-	int ncompletions;
-	unsigned long *complete; /* array of NR_CMDS tags */
-};
-
-#endif
 struct ctlr_info 
 {
 	int	ctlr;
@@ -118,11 +120,11 @@ struct ctlr_info
 	void *scsi_ctlr; /* ptr to structure containing scsi related stuff */
 	/* list of block side commands the scsi error handling sucked up */
 	/* and saved for later processing */
-	struct sendcmd_reject_list scsi_rejects;
 #endif
 	unsigned char alive;
 	struct completion *rescan_wait;
 	struct task_struct *cciss_scan_thread;
+	struct device dev;
 };
 
 /*  Defining the diffent access_menthods */

drivers/block/cciss_cmd.h

@@ -217,6 +217,8 @@ typedef union _LUNAddr_struct {
   LogDevAddr_struct  LogDev;
 } LUNAddr_struct;
 
+#define CTLR_LUNID "\0\0\0\0\0\0\0\0"
+
 typedef struct _CommandListHeader_struct {
   BYTE              ReplyQueue;
   BYTE              SGList;

drivers/block/cciss_scsi.c

@@ -44,20 +44,13 @@
 #define CCISS_ABORT_MSG 0x00
 #define CCISS_RESET_MSG 0x01
 
-/* some prototypes... */ 
-static int sendcmd(
-	__u8	cmd,
-	int	ctlr,
-	void	*buff,
-	size_t	size,
-	unsigned int use_unit_num, /* 0: address the controller,
-				      1: address logical volume log_unit, 
-				      2: address is in scsi3addr */
-	unsigned int log_unit,
-	__u8	page_code,
-	unsigned char *scsi3addr,
+static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff,
+	size_t size,
+	__u8 page_code, unsigned char *scsi3addr,
 	int cmd_type);
 
+static CommandList_struct *cmd_alloc(ctlr_info_t *h, int get_from_pool);
+static void cmd_free(ctlr_info_t *h, CommandList_struct *c, int got_from_pool);
 
 static int cciss_scsi_proc_info(
 		struct Scsi_Host *sh,
@@ -1575,6 +1568,75 @@ cciss_seq_tape_report(struct seq_file *seq, int ctlr)
 	CPQ_TAPE_UNLOCK(ctlr, flags);
 }
 
+static int wait_for_device_to_become_ready(ctlr_info_t *h,
+	unsigned char lunaddr[])
+{
+	int rc;
+	int count = 0;
+	int waittime = HZ;
+	CommandList_struct *c;
+
+	c = cmd_alloc(h, 1);
+	if (!c) {
+		printk(KERN_WARNING "cciss%d: out of memory in "
+			"wait_for_device_to_become_ready.\n", h->ctlr);
+		return IO_ERROR;
+	}
+
+	/* Send test unit ready until device ready, or give up. */
+	while (count < 20) {
+
+		/* Wait for a bit.  do this first, because if we send
+		 * the TUR right away, the reset will just abort it.
+		 */
+		schedule_timeout_uninterruptible(waittime);
+		count++;
+
+		/* Increase wait time with each try, up to a point. */
+		if (waittime < (HZ * 30))
+			waittime = waittime * 2;
+
+		/* Send the Test Unit Ready */
+		rc = fill_cmd(c, TEST_UNIT_READY, h->ctlr, NULL, 0, 0,
+			lunaddr, TYPE_CMD);
+		if (rc == 0)
+			rc = sendcmd_withirq_core(h, c, 0);
+
+		(void) process_sendcmd_error(h, c);
+
+		if (rc != 0)
+			goto retry_tur;
+
+		if (c->err_info->CommandStatus == CMD_SUCCESS)
+			break;
+
+		if (c->err_info->CommandStatus == CMD_TARGET_STATUS &&
+			c->err_info->ScsiStatus == SAM_STAT_CHECK_CONDITION) {
+			if (c->err_info->SenseInfo[2] == NO_SENSE)
+				break;
+			if (c->err_info->SenseInfo[2] == UNIT_ATTENTION) {
+				unsigned char asc;
+				asc = c->err_info->SenseInfo[12];
+				check_for_unit_attention(h, c);
+				if (asc == POWER_OR_RESET)
+					break;
+			}
+		}
+retry_tur:
+		printk(KERN_WARNING "cciss%d: Waiting %d secs "
+			"for device to become ready.\n",
+			h->ctlr, waittime / HZ);
+		rc = 1; /* device not ready. */
+	}
+
+	if (rc)
+		printk("cciss%d: giving up on device.\n", h->ctlr);
+	else
+		printk(KERN_WARNING "cciss%d: device is ready.\n", h->ctlr);
+
+	cmd_free(h, c, 1);
+	return rc;
+}
 
 /* Need at least one of these error handlers to keep ../scsi/hosts.c from 
  * complaining.  Doing a host- or bus-reset can't do anything good here. 
@@ -1591,6 +1653,7 @@ static int cciss_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 {
 	int rc;
 	CommandList_struct *cmd_in_trouble;
+	unsigned char lunaddr[8];
 	ctlr_info_t **c;
 	int ctlr;
 
@@ -1600,19 +1663,15 @@ static int cciss_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 		return FAILED;
 	ctlr = (*c)->ctlr;
 	printk(KERN_WARNING "cciss%d: resetting tape drive or medium changer.\n", ctlr);
-
 	/* find the command that's giving us trouble */
 	cmd_in_trouble = (CommandList_struct *) scsicmd->host_scribble;
-	if (cmd_in_trouble == NULL) { /* paranoia */
+	if (cmd_in_trouble == NULL) /* paranoia */
 		return FAILED;
-	}
+	memcpy(lunaddr, &cmd_in_trouble->Header.LUN.LunAddrBytes[0], 8);
 	/* send a reset to the SCSI LUN which the command was sent to */
-	rc = sendcmd(CCISS_RESET_MSG, ctlr, NULL, 0, 2, 0, 0, 
-		(unsigned char *) &cmd_in_trouble->Header.LUN.LunAddrBytes[0], 
+	rc = sendcmd_withirq(CCISS_RESET_MSG, ctlr, NULL, 0, 0, lunaddr,
 		TYPE_MSG);
-	/* sendcmd turned off interrupts on the board, turn 'em back on. */
-	(*c)->access.set_intr_mask(*c, CCISS_INTR_ON);
-	if (rc == 0)
+	if (rc == 0 && wait_for_device_to_become_ready(*c, lunaddr) == 0)
 		return SUCCESS;
 	printk(KERN_WARNING "cciss%d: resetting device failed.\n", ctlr);
 	return FAILED;
@@ -1622,6 +1681,7 @@ static int  cciss_eh_abort_handler(struct scsi_cmnd *scsicmd)
 {
 	int rc;
 	CommandList_struct *cmd_to_abort;
+	unsigned char lunaddr[8];
 	ctlr_info_t **c;
 	int ctlr;
 
@@ -1636,12 +1696,9 @@ static int  cciss_eh_abort_handler(struct scsi_cmnd *scsicmd)
 	cmd_to_abort = (CommandList_struct *) scsicmd->host_scribble;
 	if (cmd_to_abort == NULL) /* paranoia */
 		return FAILED;
-	rc = sendcmd(CCISS_ABORT_MSG, ctlr, &cmd_to_abort->Header.Tag, 
-		0, 2, 0, 0, 
-		(unsigned char *) &cmd_to_abort->Header.LUN.LunAddrBytes[0], 
-		TYPE_MSG);
-	/* sendcmd turned off interrupts on the board, turn 'em back on. */
-	(*c)->access.set_intr_mask(*c, CCISS_INTR_ON);
+	memcpy(lunaddr, &cmd_to_abort->Header.LUN.LunAddrBytes[0], 8);
+	rc = sendcmd_withirq(CCISS_ABORT_MSG, ctlr, &cmd_to_abort->Header.Tag,
+		0, 0, lunaddr, TYPE_MSG);
 	if (rc == 0)
 		return SUCCESS;
 	return FAILED;

drivers/block/cpqarray.c

@@ -474,7 +474,7 @@ static int __init cpqarray_register_ctlr( int i, struct pci_dev *pdev)
 		disk->fops = &ida_fops;
 		if (j && !drv->nr_blks)
 			continue;
-		blk_queue_hardsect_size(hba[i]->queue, drv->blk_size);
+		blk_queue_logical_block_size(hba[i]->queue, drv->blk_size);
 		set_capacity(disk, drv->nr_blks);
 		disk->queue = hba[i]->queue;
 		disk->private_data = drv;
@@ -903,7 +903,7 @@ static void do_ida_request(struct request_queue *q)
 		goto startio;
 
 queue_next:
-	creq = elv_next_request(q);
+	creq = blk_peek_request(q);
 	if (!creq)
 		goto startio;
 
@@ -912,17 +912,18 @@ queue_next:
 	if ((c = cmd_alloc(h,1)) == NULL)
 		goto startio;
 
-	blkdev_dequeue_request(creq);
+	blk_start_request(creq);
 
 	c->ctlr = h->ctlr;
 	c->hdr.unit = (drv_info_t *)(creq->rq_disk->private_data) - h->drv;
 	c->hdr.size = sizeof(rblk_t) >> 2;
 	c->size += sizeof(rblk_t);
 
-	c->req.hdr.blk = creq->sector;
+	c->req.hdr.blk = blk_rq_pos(creq);
 	c->rq = creq;
 DBGPX(
-	printk("sector=%d, nr_sectors=%d\n", creq->sector, creq->nr_sectors);
+	printk("sector=%d, nr_sectors=%u\n",
+	       blk_rq_pos(creq), blk_rq_sectors(creq));
 );
 	sg_init_table(tmp_sg, SG_MAX);
 	seg = blk_rq_map_sg(q, creq, tmp_sg);
@@ -940,9 +941,9 @@ DBGPX(
 						 tmp_sg[i].offset,
 						 tmp_sg[i].length, dir);
 	}
-DBGPX(	printk("Submitting %d sectors in %d segments\n", creq->nr_sectors, seg); );
+DBGPX(	printk("Submitting %u sectors in %d segments\n", blk_rq_sectors(creq), seg); );
 	c->req.hdr.sg_cnt = seg;
-	c->req.hdr.blk_cnt = creq->nr_sectors;
+	c->req.hdr.blk_cnt = blk_rq_sectors(creq);
 	c->req.hdr.cmd = (rq_data_dir(creq) == READ) ? IDA_READ : IDA_WRITE;
 	c->type = CMD_RWREQ;
 
@@ -1024,8 +1025,7 @@ static inline void complete_command(cmdlist_t *cmd, int timeout)
 				cmd->req.sg[i].size, ddir);
 
 	DBGPX(printk("Done with %p\n", rq););
-	if (__blk_end_request(rq, error, blk_rq_bytes(rq)))
-		BUG();
+	__blk_end_request_all(rq, error);
 }
 
 /*
@@ -1546,7 +1546,7 @@ static int revalidate_allvol(ctlr_info_t *host)
 		drv_info_t *drv = &host->drv[i];
 		if (i && !drv->nr_blks)
 			continue;
-		blk_queue_hardsect_size(host->queue, drv->blk_size);
+		blk_queue_logical_block_size(host->queue, drv->blk_size);
 		set_capacity(disk, drv->nr_blks);
 		disk->queue = host->queue;
 		disk->private_data = drv;

drivers/block/floppy.c

@@ -931,7 +931,7 @@ static inline void unlock_fdc(void)
 	del_timer(&fd_timeout);
 	cont = NULL;
 	clear_bit(0, &fdc_busy);
-	if (elv_next_request(floppy_queue))
+	if (current_req || blk_peek_request(floppy_queue))
 		do_fd_request(floppy_queue);
 	spin_unlock_irqrestore(&floppy_lock, flags);
 	wake_up(&fdc_wait);
@@ -2303,7 +2303,7 @@ static void floppy_end_request(struct request *req, int error)
 
 	/* current_count_sectors can be zero if transfer failed */
 	if (error)
-		nr_sectors = req->current_nr_sectors;
+		nr_sectors = blk_rq_cur_sectors(req);
 	if (__blk_end_request(req, error, nr_sectors << 9))
 		return;
 
@@ -2332,7 +2332,7 @@ static void request_done(int uptodate)
 	if (uptodate) {
 		/* maintain values for invalidation on geometry
 		 * change */
-		block = current_count_sectors + req->sector;
+		block = current_count_sectors + blk_rq_pos(req);
 		INFBOUND(DRS->maxblock, block);
 		if (block > _floppy->sect)
 			DRS->maxtrack = 1;
@@ -2346,10 +2346,10 @@ static void request_done(int uptodate)
 			/* record write error information */
 			DRWE->write_errors++;
 			if (DRWE->write_errors == 1) {
-				DRWE->first_error_sector = req->sector;
+				DRWE->first_error_sector = blk_rq_pos(req);
 				DRWE->first_error_generation = DRS->generation;
 			}
-			DRWE->last_error_sector = req->sector;
+			DRWE->last_error_sector = blk_rq_pos(req);
 			DRWE->last_error_generation = DRS->generation;
 		}
 		spin_lock_irqsave(q->queue_lock, flags);
@@ -2503,24 +2503,23 @@ static void copy_buffer(int ssize, int max_sector, int max_sector_2)
 
 	max_sector = transfer_size(ssize,
 				   min(max_sector, max_sector_2),
-				   current_req->nr_sectors);
+				   blk_rq_sectors(current_req));
 
 	if (current_count_sectors <= 0 && CT(COMMAND) == FD_WRITE &&
-	    buffer_max > fsector_t + current_req->nr_sectors)
+	    buffer_max > fsector_t + blk_rq_sectors(current_req))
 		current_count_sectors = min_t(int, buffer_max - fsector_t,
-					      current_req->nr_sectors);
+					      blk_rq_sectors(current_req));
 
 	remaining = current_count_sectors << 9;
 #ifdef FLOPPY_SANITY_CHECK
-	if ((remaining >> 9) > current_req->nr_sectors &&
-	    CT(COMMAND) == FD_WRITE) {
+	if (remaining > blk_rq_bytes(current_req) && CT(COMMAND) == FD_WRITE) {
 		DPRINT("in copy buffer\n");
 		printk("current_count_sectors=%ld\n", current_count_sectors);
 		printk("remaining=%d\n", remaining >> 9);
-		printk("current_req->nr_sectors=%ld\n",
-		       current_req->nr_sectors);
+		printk("current_req->nr_sectors=%u\n",
+		       blk_rq_sectors(current_req));
 		printk("current_req->current_nr_sectors=%u\n",
-		       current_req->current_nr_sectors);
+		       blk_rq_cur_sectors(current_req));
 		printk("max_sector=%d\n", max_sector);
 		printk("ssize=%d\n", ssize);
 	}
@@ -2530,7 +2529,7 @@ static void copy_buffer(int ssize, int max_sector, int max_sector_2)
 
 	dma_buffer = floppy_track_buffer + ((fsector_t - buffer_min) << 9);
 
-	size = current_req->current_nr_sectors << 9;
+	size = blk_rq_cur_bytes(current_req);
 
 	rq_for_each_segment(bv, current_req, iter) {
 		if (!remaining)
@@ -2648,10 +2647,10 @@ static int make_raw_rw_request(void)
 
 	max_sector = _floppy->sect * _floppy->head;
 
-	TRACK = (int)current_req->sector / max_sector;
-	fsector_t = (int)current_req->sector % max_sector;
+	TRACK = (int)blk_rq_pos(current_req) / max_sector;
+	fsector_t = (int)blk_rq_pos(current_req) % max_sector;
 	if (_floppy->track && TRACK >= _floppy->track) {
-		if (current_req->current_nr_sectors & 1) {
+		if (blk_rq_cur_sectors(current_req) & 1) {
 			current_count_sectors = 1;
 			return 1;
 		} else
@@ -2669,7 +2668,7 @@ static int make_raw_rw_request(void)
 		if (fsector_t >= max_sector) {
 			current_count_sectors =
 			    min_t(int, _floppy->sect - fsector_t,
-				  current_req->nr_sectors);
+				  blk_rq_sectors(current_req));
 			return 1;
 		}
 		SIZECODE = 2;
@@ -2720,7 +2719,7 @@ static int make_raw_rw_request(void)
 
 	in_sector_offset = (fsector_t % _floppy->sect) % ssize;
 	aligned_sector_t = fsector_t - in_sector_offset;
-	max_size = current_req->nr_sectors;
+	max_size = blk_rq_sectors(current_req);
 	if ((raw_cmd->track == buffer_track) &&
 	    (current_drive == buffer_drive) &&
 	    (fsector_t >= buffer_min) && (fsector_t < buffer_max)) {
@@ -2729,10 +2728,10 @@ static int make_raw_rw_request(void)
 			copy_buffer(1, max_sector, buffer_max);
 			return 1;
 		}
-	} else if (in_sector_offset || current_req->nr_sectors < ssize) {
+	} else if (in_sector_offset || blk_rq_sectors(current_req) < ssize) {
 		if (CT(COMMAND) == FD_WRITE) {
-			if (fsector_t + current_req->nr_sectors > ssize &&
-			    fsector_t + current_req->nr_sectors < ssize + ssize)
+			if (fsector_t + blk_rq_sectors(current_req) > ssize &&
+			    fsector_t + blk_rq_sectors(current_req) < ssize + ssize)
 				max_size = ssize + ssize;
 			else
 				max_size = ssize;
@@ -2776,7 +2775,7 @@ static int make_raw_rw_request(void)
 		    (indirect * 2 > direct * 3 &&
 		     *errors < DP->max_errors.read_track && ((!probing
 		       || (DP->read_track & (1 << DRS->probed_format)))))) {
-			max_size = current_req->nr_sectors;
+			max_size = blk_rq_sectors(current_req);
 		} else {
 			raw_cmd->kernel_data = current_req->buffer;
 			raw_cmd->length = current_count_sectors << 9;
@@ -2801,7 +2800,7 @@ static int make_raw_rw_request(void)
 	    fsector_t > buffer_max ||
 	    fsector_t < buffer_min ||
 	    ((CT(COMMAND) == FD_READ ||
-	      (!in_sector_offset && current_req->nr_sectors >= ssize)) &&
+	      (!in_sector_offset && blk_rq_sectors(current_req) >= ssize)) &&
 	     max_sector > 2 * max_buffer_sectors + buffer_min &&
 	     max_size + fsector_t > 2 * max_buffer_sectors + buffer_min)
 	    /* not enough space */
@@ -2879,8 +2878,8 @@ static int make_raw_rw_request(void)
 				printk("write\n");
 			return 0;
 		}
-	} else if (raw_cmd->length > current_req->nr_sectors << 9 ||
-		   current_count_sectors > current_req->nr_sectors) {
+	} else if (raw_cmd->length > blk_rq_bytes(current_req) ||
+		   current_count_sectors > blk_rq_sectors(current_req)) {
 		DPRINT("buffer overrun in direct transfer\n");
 		return 0;
 	} else if (raw_cmd->length < current_count_sectors << 9) {
@@ -2913,7 +2912,7 @@ static void redo_fd_request(void)
 			struct request *req;
 
 			spin_lock_irq(floppy_queue->queue_lock);
-			req = elv_next_request(floppy_queue);
+			req = blk_fetch_request(floppy_queue);
 			spin_unlock_irq(floppy_queue->queue_lock);
 			if (!req) {
 				do_floppy = NULL;
@@ -2990,8 +2989,9 @@ static void do_fd_request(struct request_queue * q)
 	if (usage_count == 0) {
 		printk("warning: usage count=0, current_req=%p exiting\n",
 		       current_req);
-		printk("sect=%ld type=%x flags=%x\n", (long)current_req->sector,
-		       current_req->cmd_type, current_req->cmd_flags);
+		printk("sect=%ld type=%x flags=%x\n",
+		       (long)blk_rq_pos(current_req), current_req->cmd_type,
+		       current_req->cmd_flags);
 		return;
 	}
 	if (test_bit(0, &fdc_busy)) {
@@ -4148,6 +4148,24 @@ static void floppy_device_release(struct device *dev)
 {
 }
 
+static int floppy_resume(struct platform_device *dev)
+{
+	int fdc;
+
+	for (fdc = 0; fdc < N_FDC; fdc++)
+		if (FDCS->address != -1)
+			user_reset_fdc(-1, FD_RESET_ALWAYS, 0);
+
+	return 0;
+}
+
+static struct platform_driver floppy_driver = {
+	.resume = floppy_resume,
+	.driver = {
+		.name = "floppy",
+	},
+};
+
 static struct platform_device floppy_device[N_DRIVE];
 
 static struct kobject *floppy_find(dev_t dev, int *part, void *data)
@@ -4196,10 +4214,14 @@ static int __init floppy_init(void)
 	if (err)
 		goto out_put_disk;
 
+	err = platform_driver_register(&floppy_driver);
+	if (err)
+		goto out_unreg_blkdev;
+
 	floppy_queue = blk_init_queue(do_fd_request, &floppy_lock);
 	if (!floppy_queue) {
 		err = -ENOMEM;
-		goto out_unreg_blkdev;
+		goto out_unreg_driver;
 	}
 	blk_queue_max_sectors(floppy_queue, 64);
 
@@ -4346,6 +4368,8 @@ out_flush_work:
 out_unreg_region:
 	blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256);
 	blk_cleanup_queue(floppy_queue);
+out_unreg_driver:
+	platform_driver_unregister(&floppy_driver);
 out_unreg_blkdev:
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 out_put_disk:
@@ -4566,6 +4590,7 @@ static void __exit floppy_module_exit(void)
 
 	blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256);
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
+	platform_driver_unregister(&floppy_driver);
 
 	for (drive = 0; drive < N_DRIVE; drive++) {
 		del_timer_sync(&motor_off_timer[drive]);

drivers/block/hd.c

@@ -98,10 +98,9 @@
 
 static DEFINE_SPINLOCK(hd_lock);
 static struct request_queue *hd_queue;
+static struct request *hd_req;
 
 #define MAJOR_NR HD_MAJOR
-#define QUEUE (hd_queue)
-#define CURRENT elv_next_request(hd_queue)
 
 #define TIMEOUT_VALUE	(6*HZ)
 #define	HD_DELAY	0
@@ -195,11 +194,24 @@ static void __init hd_setup(char *str, int *ints)
 	NR_HD = hdind+1;
 }
 
+static bool hd_end_request(int err, unsigned int bytes)
+{
+	if (__blk_end_request(hd_req, err, bytes))
+		return true;
+	hd_req = NULL;
+	return false;
+}
+
+static bool hd_end_request_cur(int err)
+{
+	return hd_end_request(err, blk_rq_cur_bytes(hd_req));
+}
+
 static void dump_status(const char *msg, unsigned int stat)
 {
 	char *name = "hd?";
-	if (CURRENT)
-		name = CURRENT->rq_disk->disk_name;
+	if (hd_req)
+		name = hd_req->rq_disk->disk_name;
 
 #ifdef VERBOSE_ERRORS
 	printk("%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
@@ -227,8 +239,8 @@ static void dump_status(const char *msg, unsigned int stat)
 		if (hd_error & (BBD_ERR|ECC_ERR|ID_ERR|MARK_ERR)) {
 			printk(", CHS=%d/%d/%d", (inb(HD_HCYL)<<8) + inb(HD_LCYL),
 				inb(HD_CURRENT) & 0xf, inb(HD_SECTOR));
-			if (CURRENT)
-				printk(", sector=%ld", CURRENT->sector);
+			if (hd_req)
+				printk(", sector=%ld", blk_rq_pos(hd_req));
 		}
 		printk("\n");
 	}
@@ -406,11 +418,12 @@ static void unexpected_hd_interrupt(void)
  */
 static void bad_rw_intr(void)
 {
-	struct request *req = CURRENT;
+	struct request *req = hd_req;
+
 	if (req != NULL) {
 		struct hd_i_struct *disk = req->rq_disk->private_data;
 		if (++req->errors >= MAX_ERRORS || (hd_error & BBD_ERR)) {
-			end_request(req, 0);
+			hd_end_request_cur(-EIO);
 			disk->special_op = disk->recalibrate = 1;
 		} else if (req->errors % RESET_FREQ == 0)
 			reset = 1;
@@ -452,37 +465,30 @@ static void read_intr(void)
 	bad_rw_intr();
 	hd_request();
 	return;
+
 ok_to_read:
-	req = CURRENT;
+	req = hd_req;
 	insw(HD_DATA, req->buffer, 256);
-	req->sector++;
-	req->buffer += 512;
-	req->errors = 0;
-	i = --req->nr_sectors;
-	--req->current_nr_sectors;
 #ifdef DEBUG
-	printk("%s: read: sector %ld, remaining = %ld, buffer=%p\n",
-		req->rq_disk->disk_name, req->sector, req->nr_sectors,
-		req->buffer+512);
+	printk("%s: read: sector %ld, remaining = %u, buffer=%p\n",
+	       req->rq_disk->disk_name, blk_rq_pos(req) + 1,
+	       blk_rq_sectors(req) - 1, req->buffer+512);
 #endif
-	if (req->current_nr_sectors <= 0)
-		end_request(req, 1);
-	if (i > 0) {
+	if (hd_end_request(0, 512)) {
 		SET_HANDLER(&read_intr);
 		return;
 	}
+
 	(void) inb_p(HD_STATUS);
 #if (HD_DELAY > 0)
 	last_req = read_timer();
 #endif
-	if (elv_next_request(QUEUE))
-		hd_request();
-	return;
+	hd_request();
 }
 
 static void write_intr(void)
 {
-	struct request *req = CURRENT;
+	struct request *req = hd_req;
 	int i;
 	int retries = 100000;
 
@@ -492,30 +498,25 @@ static void write_intr(void)
 			continue;
 		if (!OK_STATUS(i))
 			break;
-		if ((req->nr_sectors <= 1) || (i & DRQ_STAT))
+		if ((blk_rq_sectors(req) <= 1) || (i & DRQ_STAT))
 			goto ok_to_write;
 	} while (--retries > 0);
 	dump_status("write_intr", i);
 	bad_rw_intr();
 	hd_request();
 	return;
+
 ok_to_write:
-	req->sector++;
-	i = --req->nr_sectors;
-	--req->current_nr_sectors;
-	req->buffer += 512;
-	if (!i || (req->bio && req->current_nr_sectors <= 0))
-		end_request(req, 1);
-	if (i > 0) {
+	if (hd_end_request(0, 512)) {
 		SET_HANDLER(&write_intr);
 		outsw(HD_DATA, req->buffer, 256);
-	} else {
+		return;
+	}
+
 #if (HD_DELAY > 0)
-		last_req = read_timer();
+	last_req = read_timer();
 #endif
-		hd_request();
-	}
-	return;
+	hd_request();
 }
 
 static void recal_intr(void)
@@ -537,18 +538,18 @@ static void hd_times_out(unsigned long dummy)
 
 	do_hd = NULL;
 
-	if (!CURRENT)
+	if (!hd_req)
 		return;
 
 	spin_lock_irq(hd_queue->queue_lock);
 	reset = 1;
-	name = CURRENT->rq_disk->disk_name;
+	name = hd_req->rq_disk->disk_name;
 	printk("%s: timeout\n", name);
-	if (++CURRENT->errors >= MAX_ERRORS) {
+	if (++hd_req->errors >= MAX_ERRORS) {
 #ifdef DEBUG
 		printk("%s: too many errors\n", name);
 #endif
-		end_request(CURRENT, 0);
+		hd_end_request_cur(-EIO);
 	}
 	hd_request();
 	spin_unlock_irq(hd_queue->queue_lock);
@@ -563,7 +564,7 @@ static int do_special_op(struct hd_i_struct *disk, struct request *req)
 	}
 	if (disk->head > 16) {
 		printk("%s: cannot handle device with more than 16 heads - giving up\n", req->rq_disk->disk_name);
-		end_request(req, 0);
+		hd_end_request_cur(-EIO);
 	}
 	disk->special_op = 0;
 	return 1;
@@ -590,24 +591,27 @@ static void hd_request(void)
 repeat:
 	del_timer(&device_timer);
 
-	req = CURRENT;
-	if (!req) {
-		do_hd = NULL;
-		return;
+	if (!hd_req) {
+		hd_req = blk_fetch_request(hd_queue);
+		if (!hd_req) {
+			do_hd = NULL;
+			return;
+		}
 	}
+	req = hd_req;
 
 	if (reset) {
 		reset_hd();
 		return;
 	}
 	disk = req->rq_disk->private_data;
-	block = req->sector;
-	nsect = req->nr_sectors;
+	block = blk_rq_pos(req);
+	nsect = blk_rq_sectors(req);
 	if (block >= get_capacity(req->rq_disk) ||
 	    ((block+nsect) > get_capacity(req->rq_disk))) {
 		printk("%s: bad access: block=%d, count=%d\n",
 			req->rq_disk->disk_name, block, nsect);
-		end_request(req, 0);
+		hd_end_request_cur(-EIO);
 		goto repeat;
 	}
 
@@ -647,7 +651,7 @@ repeat:
 			break;
 		default:
 			printk("unknown hd-command\n");
-			end_request(req, 0);
+			hd_end_request_cur(-EIO);
 			break;
 		}
 	}
@@ -720,7 +724,7 @@ static int __init hd_init(void)
 	blk_queue_max_sectors(hd_queue, 255);
 	init_timer(&device_timer);
 	device_timer.function = hd_times_out;
-	blk_queue_hardsect_size(hd_queue, 512);
+	blk_queue_logical_block_size(hd_queue, 512);
 
 	if (!NR_HD) {
 		/*

drivers/block/loop.c

@@ -511,11 +511,7 @@ out:
  */
 static void loop_add_bio(struct loop_device *lo, struct bio *bio)
 {
-	if (lo->lo_biotail) {
-		lo->lo_biotail->bi_next = bio;
-		lo->lo_biotail = bio;
-	} else
-		lo->lo_bio = lo->lo_biotail = bio;
+	bio_list_add(&lo->lo_bio_list, bio);
 }
 
 /*
@@ -523,16 +519,7 @@ static void loop_add_bio(struct loop_device *lo, struct bio *bio)
  */
 static struct bio *loop_get_bio(struct loop_device *lo)
 {
-	struct bio *bio;
-
-	if ((bio = lo->lo_bio)) {
-		if (bio == lo->lo_biotail)
-			lo->lo_biotail = NULL;
-		lo->lo_bio = bio->bi_next;
-		bio->bi_next = NULL;
-	}
-
-	return bio;
+	return bio_list_pop(&lo->lo_bio_list);
 }
 
 static int loop_make_request(struct request_queue *q, struct bio *old_bio)
@@ -609,12 +596,13 @@ static int loop_thread(void *data)
 
 	set_user_nice(current, -20);
 
-	while (!kthread_should_stop() || lo->lo_bio) {
+	while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) {
 
 		wait_event_interruptible(lo->lo_event,
-				lo->lo_bio || kthread_should_stop());
+				!bio_list_empty(&lo->lo_bio_list) ||
+				kthread_should_stop());
 
-		if (!lo->lo_bio)
+		if (bio_list_empty(&lo->lo_bio_list))
 			continue;
 		spin_lock_irq(&lo->lo_lock);
 		bio = loop_get_bio(lo);
@@ -721,10 +709,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
 		goto out_putf;
 
-	/* new backing store needs to support loop (eg splice_read) */
-	if (!inode->i_fop->splice_read)
-		goto out_putf;
-
 	/* size of the new backing store needs to be the same */
 	if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
 		goto out_putf;
@@ -800,12 +784,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	error = -EINVAL;
 	if (S_ISREG(inode->i_mode) || S_ISBLK(inode->i_mode)) {
 		const struct address_space_operations *aops = mapping->a_ops;
-		/*
-		 * If we can't read - sorry. If we only can't write - well,
-		 * it's going to be read-only.
-		 */
-		if (!file->f_op->splice_read)
-			goto out_putf;
+
 		if (aops->write_begin)
 			lo_flags |= LO_FLAGS_USE_AOPS;
 		if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write)
@@ -841,7 +820,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
-	lo->lo_bio = lo->lo_biotail = NULL;
+	bio_list_init(&lo->lo_bio_list);
 
 	/*
 	 * set queue make_request_fn, and add limits based on lower level

drivers/block/mg_disk.c

@@ -17,71 +17,220 @@
 #include <linux/fs.h>
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
-#include <linux/libata.h>
+#include <linux/ata.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
-#include <linux/mg_disk.h>
 
 #define MG_RES_SEC (CONFIG_MG_DISK_RES << 1)
 
+/* name for block device */
+#define MG_DISK_NAME "mgd"
+/* name for platform device */
+#define MG_DEV_NAME "mg_disk"
+
+#define MG_DISK_MAJ 0
+#define MG_DISK_MAX_PART 16
+#define MG_SECTOR_SIZE 512
+#define MG_MAX_SECTS 256
+
+/* Register offsets */
+#define MG_BUFF_OFFSET			0x8000
+#define MG_STORAGE_BUFFER_SIZE		0x200
+#define MG_REG_OFFSET			0xC000
+#define MG_REG_FEATURE			(MG_REG_OFFSET + 2)	/* write case */
+#define MG_REG_ERROR			(MG_REG_OFFSET + 2)	/* read case */
+#define MG_REG_SECT_CNT			(MG_REG_OFFSET + 4)
+#define MG_REG_SECT_NUM			(MG_REG_OFFSET + 6)
+#define MG_REG_CYL_LOW			(MG_REG_OFFSET + 8)
+#define MG_REG_CYL_HIGH			(MG_REG_OFFSET + 0xA)
+#define MG_REG_DRV_HEAD			(MG_REG_OFFSET + 0xC)
+#define MG_REG_COMMAND			(MG_REG_OFFSET + 0xE)	/* write case */
+#define MG_REG_STATUS			(MG_REG_OFFSET + 0xE)	/* read  case */
+#define MG_REG_DRV_CTRL			(MG_REG_OFFSET + 0x10)
+#define MG_REG_BURST_CTRL		(MG_REG_OFFSET + 0x12)
+
+/* handy status */
+#define MG_STAT_READY	(ATA_DRDY | ATA_DSC)
+#define MG_READY_OK(s)	(((s) & (MG_STAT_READY | (ATA_BUSY | ATA_DF | \
+				 ATA_ERR))) == MG_STAT_READY)
+
+/* error code for others */
+#define MG_ERR_NONE		0
+#define MG_ERR_TIMEOUT		0x100
+#define MG_ERR_INIT_STAT	0x101
+#define MG_ERR_TRANSLATION	0x102
+#define MG_ERR_CTRL_RST		0x103
+#define MG_ERR_INV_STAT		0x104
+#define MG_ERR_RSTOUT		0x105
+
+#define MG_MAX_ERRORS	6	/* Max read/write errors */
+
+/* command */
+#define MG_CMD_RD 0x20
+#define MG_CMD_WR 0x30
+#define MG_CMD_SLEEP 0x99
+#define MG_CMD_WAKEUP 0xC3
+#define MG_CMD_ID 0xEC
+#define MG_CMD_WR_CONF 0x3C
+#define MG_CMD_RD_CONF 0x40
+
+/* operation mode */
+#define MG_OP_CASCADE (1 << 0)
+#define MG_OP_CASCADE_SYNC_RD (1 << 1)
+#define MG_OP_CASCADE_SYNC_WR (1 << 2)
+#define MG_OP_INTERLEAVE (1 << 3)
+
+/* synchronous */
+#define MG_BURST_LAT_4 (3 << 4)
+#define MG_BURST_LAT_5 (4 << 4)
+#define MG_BURST_LAT_6 (5 << 4)
+#define MG_BURST_LAT_7 (6 << 4)
+#define MG_BURST_LAT_8 (7 << 4)
+#define MG_BURST_LEN_4 (1 << 1)
+#define MG_BURST_LEN_8 (2 << 1)
+#define MG_BURST_LEN_16 (3 << 1)
+#define MG_BURST_LEN_32 (4 << 1)
+#define MG_BURST_LEN_CONT (0 << 1)
+
+/* timeout value (unit: ms) */
+#define MG_TMAX_CONF_TO_CMD	1
+#define MG_TMAX_WAIT_RD_DRQ	10
+#define MG_TMAX_WAIT_WR_DRQ	500
+#define MG_TMAX_RST_TO_BUSY	10
+#define MG_TMAX_HDRST_TO_RDY	500
+#define MG_TMAX_SWRST_TO_RDY	500
+#define MG_TMAX_RSTOUT		3000
+
+/* device attribution */
+/* use mflash as boot device */
+#define MG_BOOT_DEV		(1 << 0)
+/* use mflash as storage device */
+#define MG_STORAGE_DEV		(1 << 1)
+/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */
+#define MG_STORAGE_DEV_SKIP_RST	(1 << 2)
+
+#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST)
+
+/* names of GPIO resource */
+#define MG_RST_PIN	"mg_rst"
+/* except MG_BOOT_DEV, reset-out pin should be assigned */
+#define MG_RSTOUT_PIN	"mg_rstout"
+
+/* private driver data */
+struct mg_drv_data {
+	/* disk resource */
+	u32 use_polling;
+
+	/* device attribution */
+	u32 dev_attr;
+
+	/* internally used */
+	struct mg_host *host;
+};
+
+/* main structure for mflash driver */
+struct mg_host {
+	struct device *dev;
+
+	struct request_queue *breq;
+	struct request *req;
+	spinlock_t lock;
+	struct gendisk *gd;
+
+	struct timer_list timer;
+	void (*mg_do_intr) (struct mg_host *);
+
+	u16 id[ATA_ID_WORDS];
+
+	u16 cyls;
+	u16 heads;
+	u16 sectors;
+	u32 n_sectors;
+	u32 nres_sectors;
+
+	void __iomem *dev_base;
+	unsigned int irq;
+	unsigned int rst;
+	unsigned int rstout;
+
+	u32 major;
+	u32 error;
+};
+
+/*
+ * Debugging macro and defines
+ */
+#undef DO_MG_DEBUG
+#ifdef DO_MG_DEBUG
+#  define MG_DBG(fmt, args...) \
+	printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args)
+#else /* CONFIG_MG_DEBUG */
+#  define MG_DBG(fmt, args...) do { } while (0)
+#endif /* CONFIG_MG_DEBUG */
+
 static void mg_request(struct request_queue *);
 
+static bool mg_end_request(struct mg_host *host, int err, unsigned int nr_bytes)
+{
+	if (__blk_end_request(host->req, err, nr_bytes))
+		return true;
+
+	host->req = NULL;
+	return false;
+}
+
+static bool mg_end_request_cur(struct mg_host *host, int err)
+{
+	return mg_end_request(host, err, blk_rq_cur_bytes(host->req));
+}
+
 static void mg_dump_status(const char *msg, unsigned int stat,
 		struct mg_host *host)
 {
 	char *name = MG_DISK_NAME;
-	struct request *req;
 
-	if (host->breq) {
-		req = elv_next_request(host->breq);
-		if (req)
-			name = req->rq_disk->disk_name;
-	}
+	if (host->req)
+		name = host->req->rq_disk->disk_name;
 
 	printk(KERN_ERR "%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
-	if (stat & MG_REG_STATUS_BIT_BUSY)
+	if (stat & ATA_BUSY)
 		printk("Busy ");
-	if (stat & MG_REG_STATUS_BIT_READY)
+	if (stat & ATA_DRDY)
 		printk("DriveReady ");
-	if (stat & MG_REG_STATUS_BIT_WRITE_FAULT)
+	if (stat & ATA_DF)
 		printk("WriteFault ");
-	if (stat & MG_REG_STATUS_BIT_SEEK_DONE)
+	if (stat & ATA_DSC)
 		printk("SeekComplete ");
-	if (stat & MG_REG_STATUS_BIT_DATA_REQ)
+	if (stat & ATA_DRQ)
 		printk("DataRequest ");
-	if (stat & MG_REG_STATUS_BIT_CORRECTED_ERROR)
+	if (stat & ATA_CORR)
 		printk("CorrectedError ");
-	if (stat & MG_REG_STATUS_BIT_ERROR)
+	if (stat & ATA_ERR)
 		printk("Error ");
 	printk("}\n");
-	if ((stat & MG_REG_STATUS_BIT_ERROR) == 0) {
+	if ((stat & ATA_ERR) == 0) {
 		host->error = 0;
 	} else {
 		host->error = inb((unsigned long)host->dev_base + MG_REG_ERROR);
 		printk(KERN_ERR "%s: %s: error=0x%02x { ", name, msg,
 				host->error & 0xff);
-		if (host->error & MG_REG_ERR_BBK)
+		if (host->error & ATA_BBK)
 			printk("BadSector ");
-		if (host->error & MG_REG_ERR_UNC)
+		if (host->error & ATA_UNC)
 			printk("UncorrectableError ");
-		if (host->error & MG_REG_ERR_IDNF)
+		if (host->error & ATA_IDNF)
 			printk("SectorIdNotFound ");
-		if (host->error & MG_REG_ERR_ABRT)
+		if (host->error & ATA_ABORTED)
 			printk("DriveStatusError ");
-		if (host->error & MG_REG_ERR_AMNF)
+		if (host->error & ATA_AMNF)
 			printk("AddrMarkNotFound ");
 		printk("}");
-		if (host->error &
-				(MG_REG_ERR_BBK | MG_REG_ERR_UNC |
-				 MG_REG_ERR_IDNF | MG_REG_ERR_AMNF)) {
-			if (host->breq) {
-				req = elv_next_request(host->breq);
-				if (req)
-					printk(", sector=%u", (u32)req->sector);
-			}
-
+		if (host->error & (ATA_BBK | ATA_UNC | ATA_IDNF | ATA_AMNF)) {
+			if (host->req)
+				printk(", sector=%u",
+				       (unsigned int)blk_rq_pos(host->req));
 		}
 		printk("\n");
 	}
@@ -100,12 +249,12 @@ static unsigned int mg_wait(struct mg_host *host, u32 expect, u32 msec)
 
 	do {
 		cur_jiffies = jiffies;
-		if (status & MG_REG_STATUS_BIT_BUSY) {
-			if (expect == MG_REG_STATUS_BIT_BUSY)
+		if (status & ATA_BUSY) {
+			if (expect == ATA_BUSY)
 				break;
 		} else {
 			/* Check the error condition! */
-			if (status & MG_REG_STATUS_BIT_ERROR) {
+			if (status & ATA_ERR) {
 				mg_dump_status("mg_wait", status, host);
 				break;
 			}
@@ -114,8 +263,8 @@ static unsigned int mg_wait(struct mg_host *host, u32 expect, u32 msec)
 				if (MG_READY_OK(status))
 					break;
 
-			if (expect == MG_REG_STATUS_BIT_DATA_REQ)
-				if (status & MG_REG_STATUS_BIT_DATA_REQ)
+			if (expect == ATA_DRQ)
+				if (status & ATA_DRQ)
 					break;
 		}
 		if (!msec) {
@@ -173,6 +322,42 @@ static irqreturn_t mg_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+/* local copy of ata_id_string() */
+static void mg_id_string(const u16 *id, unsigned char *s,
+			 unsigned int ofs, unsigned int len)
+{
+	unsigned int c;
+
+	BUG_ON(len & 1);
+
+	while (len > 0) {
+		c = id[ofs] >> 8;
+		*s = c;
+		s++;
+
+		c = id[ofs] & 0xff;
+		*s = c;
+		s++;
+
+		ofs++;
+		len -= 2;
+	}
+}
+
+/* local copy of ata_id_c_string() */
+static void mg_id_c_string(const u16 *id, unsigned char *s,
+			   unsigned int ofs, unsigned int len)
+{
+	unsigned char *p;
+
+	mg_id_string(id, s, ofs, len - 1);
+
+	p = s + strnlen(s, len - 1);
+	while (p > s && p[-1] == ' ')
+		p--;
+	*p = '\0';
+}
+
 static int mg_get_disk_id(struct mg_host *host)
 {
 	u32 i;
@@ -184,12 +369,10 @@ static int mg_get_disk_id(struct mg_host *host)
 	char serial[ATA_ID_SERNO_LEN + 1];
 
 	if (!prv_data->use_polling)
-		outb(MG_REG_CTRL_INTR_DISABLE,
-				(unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 
 	outb(MG_CMD_ID, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	err = mg_wait(host, MG_REG_STATUS_BIT_DATA_REQ, MG_TMAX_WAIT_RD_DRQ);
+	err = mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_RD_DRQ);
 	if (err)
 		return err;
 
@@ -219,9 +402,9 @@ static int mg_get_disk_id(struct mg_host *host)
 		host->n_sectors -= host->nres_sectors;
 	}
 
-	ata_id_c_string(id, fwrev, ATA_ID_FW_REV, sizeof(fwrev));
-	ata_id_c_string(id, model, ATA_ID_PROD, sizeof(model));
-	ata_id_c_string(id, serial, ATA_ID_SERNO, sizeof(serial));
+	mg_id_c_string(id, fwrev, ATA_ID_FW_REV, sizeof(fwrev));
+	mg_id_c_string(id, model, ATA_ID_PROD, sizeof(model));
+	mg_id_c_string(id, serial, ATA_ID_SERNO, sizeof(serial));
 	printk(KERN_INFO "mg_disk: model: %s\n", model);
 	printk(KERN_INFO "mg_disk: firm: %.8s\n", fwrev);
 	printk(KERN_INFO "mg_disk: serial: %s\n", serial);
@@ -229,8 +412,7 @@ static int mg_get_disk_id(struct mg_host *host)
 			host->n_sectors, host->nres_sectors);
 
 	if (!prv_data->use_polling)
-		outb(MG_REG_CTRL_INTR_ENABLE, (unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 
 	return err;
 }
@@ -244,7 +426,7 @@ static int mg_disk_init(struct mg_host *host)
 
 	/* hdd rst low */
 	gpio_set_value(host->rst, 0);
-	err = mg_wait(host, MG_REG_STATUS_BIT_BUSY, MG_TMAX_RST_TO_BUSY);
+	err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
 	if (err)
 		return err;
 
@@ -255,17 +437,14 @@ static int mg_disk_init(struct mg_host *host)
 		return err;
 
 	/* soft reset on */
-	outb(MG_REG_CTRL_RESET |
-			(prv_data->use_polling ? MG_REG_CTRL_INTR_DISABLE :
-			 MG_REG_CTRL_INTR_ENABLE),
+	outb(ATA_SRST | (prv_data->use_polling ? ATA_NIEN : 0),
 			(unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-	err = mg_wait(host, MG_REG_STATUS_BIT_BUSY, MG_TMAX_RST_TO_BUSY);
+	err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
 	if (err)
 		return err;
 
 	/* soft reset off */
-	outb(prv_data->use_polling ? MG_REG_CTRL_INTR_DISABLE :
-			MG_REG_CTRL_INTR_ENABLE,
+	outb(prv_data->use_polling ? ATA_NIEN : 0,
 			(unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 	err = mg_wait(host, MG_STAT_READY, MG_TMAX_SWRST_TO_RDY);
 	if (err)
@@ -281,11 +460,10 @@ static int mg_disk_init(struct mg_host *host)
 
 static void mg_bad_rw_intr(struct mg_host *host)
 {
-	struct request *req = elv_next_request(host->breq);
-	if (req != NULL)
-		if (++req->errors >= MG_MAX_ERRORS ||
-				host->error == MG_ERR_TIMEOUT)
-			end_request(req, 0);
+	if (host->req)
+		if (++host->req->errors >= MG_MAX_ERRORS ||
+		    host->error == MG_ERR_TIMEOUT)
+			mg_end_request_cur(host, -EIO);
 }
 
 static unsigned int mg_out(struct mg_host *host,
@@ -311,7 +489,7 @@ static unsigned int mg_out(struct mg_host *host,
 			MG_REG_CYL_LOW);
 	outb((u8)(sect_num >> 16), (unsigned long)host->dev_base +
 			MG_REG_CYL_HIGH);
-	outb((u8)((sect_num >> 24) | MG_REG_HEAD_LBA_MODE),
+	outb((u8)((sect_num >> 24) | ATA_LBA | ATA_DEVICE_OBS),
 			(unsigned long)host->dev_base + MG_REG_DRV_HEAD);
 	outb(cmd, (unsigned long)host->dev_base + MG_REG_COMMAND);
 	return MG_ERR_NONE;
@@ -319,105 +497,77 @@ static unsigned int mg_out(struct mg_host *host,
 
 static void mg_read(struct request *req)
 {
-	u32 remains, j;
+	u32 j;
 	struct mg_host *host = req->rq_disk->private_data;
 
-	remains = req->nr_sectors;
-
-	if (mg_out(host, req->sector, req->nr_sectors, MG_CMD_RD, NULL) !=
-			MG_ERR_NONE)
+	if (mg_out(host, blk_rq_pos(req), blk_rq_sectors(req),
+		   MG_CMD_RD, NULL) != MG_ERR_NONE)
 		mg_bad_rw_intr(host);
 
 	MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
-			remains, req->sector, req->buffer);
+	       blk_rq_sectors(req), blk_rq_pos(req), req->buffer);
+
+	do {
+		u16 *buff = (u16 *)req->buffer;
 
-	while (remains) {
-		if (mg_wait(host, MG_REG_STATUS_BIT_DATA_REQ,
-					MG_TMAX_WAIT_RD_DRQ) != MG_ERR_NONE) {
+		if (mg_wait(host, ATA_DRQ,
+			    MG_TMAX_WAIT_RD_DRQ) != MG_ERR_NONE) {
 			mg_bad_rw_intr(host);
 			return;
 		}
-		for (j = 0; j < MG_SECTOR_SIZE >> 1; j++) {
-			*(u16 *)req->buffer =
-				inw((unsigned long)host->dev_base +
-						MG_BUFF_OFFSET + (j << 1));
-			req->buffer += 2;
-		}
-
-		req->sector++;
-		req->errors = 0;
-		remains = --req->nr_sectors;
-		--req->current_nr_sectors;
-
-		if (req->current_nr_sectors <= 0) {
-			MG_DBG("remain : %d sects\n", remains);
-			end_request(req, 1);
-			if (remains > 0)
-				req = elv_next_request(host->breq);
-		}
+		for (j = 0; j < MG_SECTOR_SIZE >> 1; j++)
+			*buff++ = inw((unsigned long)host->dev_base +
+				      MG_BUFF_OFFSET + (j << 1));
 
 		outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base +
 				MG_REG_COMMAND);
-	}
+	} while (mg_end_request(host, 0, MG_SECTOR_SIZE));
 }
 
 static void mg_write(struct request *req)
 {
-	u32 remains, j;
+	u32 j;
 	struct mg_host *host = req->rq_disk->private_data;
 
-	remains = req->nr_sectors;
-
-	if (mg_out(host, req->sector, req->nr_sectors, MG_CMD_WR, NULL) !=
-			MG_ERR_NONE) {
+	if (mg_out(host, blk_rq_pos(req), blk_rq_sectors(req),
+		   MG_CMD_WR, NULL) != MG_ERR_NONE) {
 		mg_bad_rw_intr(host);
 		return;
 	}
 
-
 	MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
-			remains, req->sector, req->buffer);
-	while (remains) {
-		if (mg_wait(host, MG_REG_STATUS_BIT_DATA_REQ,
-					MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
+	       blk_rq_sectors(req), blk_rq_pos(req), req->buffer);
+
+	do {
+		u16 *buff = (u16 *)req->buffer;
+
+	if (mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
 			mg_bad_rw_intr(host);
 			return;
 		}
-		for (j = 0; j < MG_SECTOR_SIZE >> 1; j++) {
-			outw(*(u16 *)req->buffer,
-					(unsigned long)host->dev_base +
-					MG_BUFF_OFFSET + (j << 1));
-			req->buffer += 2;
-		}
-		req->sector++;
-		remains = --req->nr_sectors;
-		--req->current_nr_sectors;
-
-		if (req->current_nr_sectors <= 0) {
-			MG_DBG("remain : %d sects\n", remains);
-			end_request(req, 1);
-			if (remains > 0)
-				req = elv_next_request(host->breq);
-		}
+		for (j = 0; j < MG_SECTOR_SIZE >> 1; j++)
+			outw(*buff++, (unsigned long)host->dev_base +
+				      MG_BUFF_OFFSET + (j << 1));
 
 		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
 				MG_REG_COMMAND);
-	}
+	} while (mg_end_request(host, 0, MG_SECTOR_SIZE));
 }
 
 static void mg_read_intr(struct mg_host *host)
 {
+	struct request *req = host->req;
 	u32 i;
-	struct request *req;
+	u16 *buff;
 
 	/* check status */
 	do {
 		i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-		if (i & MG_REG_STATUS_BIT_BUSY)
+		if (i & ATA_BUSY)
 			break;
 		if (!MG_READY_OK(i))
 			break;
-		if (i & MG_REG_STATUS_BIT_DATA_REQ)
+		if (i & ATA_DRQ)
 			goto ok_to_read;
 	} while (0);
 	mg_dump_status("mg_read_intr", i, host);
@@ -427,60 +577,42 @@ static void mg_read_intr(struct mg_host *host)
 
 ok_to_read:
 	/* get current segment of request */
-	req = elv_next_request(host->breq);
+	buff = (u16 *)req->buffer;
 
 	/* read 1 sector */
-	for (i = 0; i < MG_SECTOR_SIZE >> 1; i++) {
-		*(u16 *)req->buffer =
-			inw((unsigned long)host->dev_base + MG_BUFF_OFFSET +
-					(i << 1));
-		req->buffer += 2;
-	}
+	for (i = 0; i < MG_SECTOR_SIZE >> 1; i++)
+		*buff++ = inw((unsigned long)host->dev_base + MG_BUFF_OFFSET +
+			      (i << 1));
 
-	/* manipulate request */
 	MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
-			req->sector, req->nr_sectors - 1, req->buffer);
-
-	req->sector++;
-	req->errors = 0;
-	i = --req->nr_sectors;
-	--req->current_nr_sectors;
-
-	/* let know if current segment done */
-	if (req->current_nr_sectors <= 0)
-		end_request(req, 1);
-
-	/* set handler if read remains */
-	if (i > 0) {
-		host->mg_do_intr = mg_read_intr;
-		mod_timer(&host->timer, jiffies + 3 * HZ);
-	}
+	       blk_rq_pos(req), blk_rq_sectors(req) - 1, req->buffer);
 
 	/* send read confirm */
 	outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
 
-	/* goto next request */
-	if (!i)
+	if (mg_end_request(host, 0, MG_SECTOR_SIZE)) {
+		/* set handler if read remains */
+		host->mg_do_intr = mg_read_intr;
+		mod_timer(&host->timer, jiffies + 3 * HZ);
+	} else /* goto next request */
 		mg_request(host->breq);
 }
 
 static void mg_write_intr(struct mg_host *host)
 {
+	struct request *req = host->req;
 	u32 i, j;
 	u16 *buff;
-	struct request *req;
-
-	/* get current segment of request */
-	req = elv_next_request(host->breq);
+	bool rem;
 
 	/* check status */
 	do {
 		i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-		if (i & MG_REG_STATUS_BIT_BUSY)
+		if (i & ATA_BUSY)
 			break;
 		if (!MG_READY_OK(i))
 			break;
-		if ((req->nr_sectors <= 1) || (i & MG_REG_STATUS_BIT_DATA_REQ))
+		if ((blk_rq_sectors(req) <= 1) || (i & ATA_DRQ))
 			goto ok_to_write;
 	} while (0);
 	mg_dump_status("mg_write_intr", i, host);
@@ -489,18 +621,8 @@ static void mg_write_intr(struct mg_host *host)
 	return;
 
 ok_to_write:
-	/* manipulate request */
-	req->sector++;
-	i = --req->nr_sectors;
-	--req->current_nr_sectors;
-	req->buffer += MG_SECTOR_SIZE;
-
-	/* let know if current segment or all done */
-	if (!i || (req->bio && req->current_nr_sectors <= 0))
-		end_request(req, 1);
-
-	/* write 1 sector and set handler if remains */
-	if (i > 0) {
+	if ((rem = mg_end_request(host, 0, MG_SECTOR_SIZE))) {
+		/* write 1 sector and set handler if remains */
 		buff = (u16 *)req->buffer;
 		for (j = 0; j < MG_STORAGE_BUFFER_SIZE >> 1; j++) {
 			outw(*buff, (unsigned long)host->dev_base +
@@ -508,7 +630,7 @@ ok_to_write:
 			buff++;
 		}
 		MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
-				req->sector, req->nr_sectors, req->buffer);
+		       blk_rq_pos(req), blk_rq_sectors(req), req->buffer);
 		host->mg_do_intr = mg_write_intr;
 		mod_timer(&host->timer, jiffies + 3 * HZ);
 	}
@@ -516,7 +638,7 @@ ok_to_write:
 	/* send write confirm */
 	outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
 
-	if (!i)
+	if (!rem)
 		mg_request(host->breq);
 }
 
@@ -524,49 +646,45 @@ void mg_times_out(unsigned long data)
 {
 	struct mg_host *host = (struct mg_host *)data;
 	char *name;
-	struct request *req;
 
 	spin_lock_irq(&host->lock);
 
-	req = elv_next_request(host->breq);
-	if (!req)
+	if (!host->req)
 		goto out_unlock;
 
 	host->mg_do_intr = NULL;
 
-	name = req->rq_disk->disk_name;
+	name = host->req->rq_disk->disk_name;
 	printk(KERN_DEBUG "%s: timeout\n", name);
 
 	host->error = MG_ERR_TIMEOUT;
 	mg_bad_rw_intr(host);
 
-	mg_request(host->breq);
 out_unlock:
+	mg_request(host->breq);
 	spin_unlock_irq(&host->lock);
 }
 
 static void mg_request_poll(struct request_queue *q)
 {
-	struct request *req;
-	struct mg_host *host;
+	struct mg_host *host = q->queuedata;
 
-	while ((req = elv_next_request(q)) != NULL) {
-		host = req->rq_disk->private_data;
-		if (blk_fs_request(req)) {
-			switch (rq_data_dir(req)) {
-			case READ:
-				mg_read(req);
-				break;
-			case WRITE:
-				mg_write(req);
-				break;
-			default:
-				printk(KERN_WARNING "%s:%d unknown command\n",
-						__func__, __LINE__);
-				end_request(req, 0);
+	while (1) {
+		if (!host->req) {
+			host->req = blk_fetch_request(q);
+			if (!host->req)
 				break;
-			}
 		}
+
+		if (unlikely(!blk_fs_request(host->req))) {
+			mg_end_request_cur(host, -EIO);
+			continue;
+		}
+
+		if (rq_data_dir(host->req) == READ)
+			mg_read(host->req);
+		else
+			mg_write(host->req);
 	}
 }
 
@@ -588,18 +706,15 @@ static unsigned int mg_issue_req(struct request *req,
 		break;
 	case WRITE:
 		/* TODO : handler */
-		outb(MG_REG_CTRL_INTR_DISABLE,
-				(unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 		if (mg_out(host, sect_num, sect_cnt, MG_CMD_WR, &mg_write_intr)
 				!= MG_ERR_NONE) {
 			mg_bad_rw_intr(host);
 			return host->error;
 		}
 		del_timer(&host->timer);
-		mg_wait(host, MG_REG_STATUS_BIT_DATA_REQ, MG_TMAX_WAIT_WR_DRQ);
-		outb(MG_REG_CTRL_INTR_ENABLE, (unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_WR_DRQ);
+		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 		if (host->error) {
 			mg_bad_rw_intr(host);
 			return host->error;
@@ -614,11 +729,6 @@ static unsigned int mg_issue_req(struct request *req,
 		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
 				MG_REG_COMMAND);
 		break;
-	default:
-		printk(KERN_WARNING "%s:%d unknown command\n",
-				__func__, __LINE__);
-		end_request(req, 0);
-		break;
 	}
 	return MG_ERR_NONE;
 }
@@ -626,16 +736,17 @@ static unsigned int mg_issue_req(struct request *req,
 /* This function also called from IRQ context */
 static void mg_request(struct request_queue *q)
 {
+	struct mg_host *host = q->queuedata;
 	struct request *req;
-	struct mg_host *host;
 	u32 sect_num, sect_cnt;
 
 	while (1) {
-		req = elv_next_request(q);
-		if (!req)
-			return;
-
-		host = req->rq_disk->private_data;
+		if (!host->req) {
+			host->req = blk_fetch_request(q);
+			if (!host->req)
+				break;
+		}
+		req = host->req;
 
 		/* check unwanted request call */
 		if (host->mg_do_intr)
@@ -643,9 +754,9 @@ static void mg_request(struct request_queue *q)
 
 		del_timer(&host->timer);
 
-		sect_num = req->sector;
+		sect_num = blk_rq_pos(req);
 		/* deal whole segments */
-		sect_cnt = req->nr_sectors;
+		sect_cnt = blk_rq_sectors(req);
 
 		/* sanity check */
 		if (sect_num >= get_capacity(req->rq_disk) ||
@@ -655,12 +766,14 @@ static void mg_request(struct request_queue *q)
 					"%s: bad access: sector=%d, count=%d\n",
 					req->rq_disk->disk_name,
 					sect_num, sect_cnt);
-			end_request(req, 0);
+			mg_end_request_cur(host, -EIO);
 			continue;
 		}
 
-		if (!blk_fs_request(req))
-			return;
+		if (unlikely(!blk_fs_request(req))) {
+			mg_end_request_cur(host, -EIO);
+			continue;
+		}
 
 		if (!mg_issue_req(req, host, sect_num, sect_cnt))
 			return;
@@ -690,9 +803,7 @@ static int mg_suspend(struct platform_device *plat_dev, pm_message_t state)
 		return -EIO;
 
 	if (!prv_data->use_polling)
-		outb(MG_REG_CTRL_INTR_DISABLE,
-				(unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 
 	outb(MG_CMD_SLEEP, (unsigned long)host->dev_base + MG_REG_COMMAND);
 	/* wait until mflash deep sleep */
@@ -700,9 +811,7 @@ static int mg_suspend(struct platform_device *plat_dev, pm_message_t state)
 
 	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD)) {
 		if (!prv_data->use_polling)
-			outb(MG_REG_CTRL_INTR_ENABLE,
-					(unsigned long)host->dev_base +
-					MG_REG_DRV_CTRL);
+			outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 		return -EIO;
 	}
 
@@ -725,8 +834,7 @@ static int mg_resume(struct platform_device *plat_dev)
 		return -EIO;
 
 	if (!prv_data->use_polling)
-		outb(MG_REG_CTRL_INTR_ENABLE, (unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 
 	return 0;
 }
@@ -877,6 +985,7 @@ static int mg_probe(struct platform_device *plat_dev)
 				__func__, __LINE__);
 		goto probe_err_5;
 	}
+	host->breq->queuedata = host;
 
 	/* mflash is random device, thanx for the noop */
 	elevator_exit(host->breq->elevator);
@@ -887,7 +996,7 @@ static int mg_probe(struct platform_device *plat_dev)
 		goto probe_err_6;
 	}
 	blk_queue_max_sectors(host->breq, MG_MAX_SECTS);
-	blk_queue_hardsect_size(host->breq, MG_SECTOR_SIZE);
+	blk_queue_logical_block_size(host->breq, MG_SECTOR_SIZE);
 
 	init_timer(&host->timer);
 	host->timer.function = mg_times_out;

drivers/block/nbd.c

@@ -110,7 +110,7 @@ static void nbd_end_request(struct request *req)
 			req, error ? "failed" : "done");
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	__blk_end_request(req, error, req->nr_sectors << 9);
+	__blk_end_request_all(req, error);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
@@ -231,19 +231,19 @@ static int nbd_send_req(struct nbd_device *lo, struct request *req)
 {
 	int result, flags;
 	struct nbd_request request;
-	unsigned long size = req->nr_sectors << 9;
+	unsigned long size = blk_rq_bytes(req);
 
 	request.magic = htonl(NBD_REQUEST_MAGIC);
 	request.type = htonl(nbd_cmd(req));
-	request.from = cpu_to_be64((u64) req->sector << 9);
+	request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
 	request.len = htonl(size);
 	memcpy(request.handle, &req, sizeof(req));
 
-	dprintk(DBG_TX, "%s: request %p: sending control (%s@%llu,%luB)\n",
+	dprintk(DBG_TX, "%s: request %p: sending control (%s@%llu,%uB)\n",
 			lo->disk->disk_name, req,
 			nbdcmd_to_ascii(nbd_cmd(req)),
-			(unsigned long long)req->sector << 9,
-			req->nr_sectors << 9);
+			(unsigned long long)blk_rq_pos(req) << 9,
+			blk_rq_bytes(req));
 	result = sock_xmit(lo, 1, &request, sizeof(request),
 			(nbd_cmd(req) == NBD_CMD_WRITE) ? MSG_MORE : 0);
 	if (result <= 0) {
@@ -533,11 +533,9 @@ static void do_nbd_request(struct request_queue *q)
 {
 	struct request *req;
 	
-	while ((req = elv_next_request(q)) != NULL) {
+	while ((req = blk_fetch_request(q)) != NULL) {
 		struct nbd_device *lo;
 
-		blkdev_dequeue_request(req);
-
 		spin_unlock_irq(q->queue_lock);
 
 		dprintk(DBG_BLKDEV, "%s: request %p: dequeued (flags=%x)\n",
@@ -580,13 +578,6 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
 		blk_rq_init(NULL, &sreq);
 		sreq.cmd_type = REQ_TYPE_SPECIAL;
 		nbd_cmd(&sreq) = NBD_CMD_DISC;
-		/*
-		 * Set these to sane values in case server implementation
-		 * fails to check the request type first and also to keep
-		 * debugging output cleaner.
-		 */
-		sreq.sector = 0;
-		sreq.nr_sectors = 0;
 		if (!lo->sock)
 			return -EINVAL;
 		nbd_send_req(lo, &sreq);

drivers/block/paride/pcd.c

@@ -719,32 +719,37 @@ static void do_pcd_request(struct request_queue * q)
 	if (pcd_busy)
 		return;
 	while (1) {
-		pcd_req = elv_next_request(q);
-		if (!pcd_req)
-			return;
+		if (!pcd_req) {
+			pcd_req = blk_fetch_request(q);
+			if (!pcd_req)
+				return;
+		}
 
 		if (rq_data_dir(pcd_req) == READ) {
 			struct pcd_unit *cd = pcd_req->rq_disk->private_data;
 			if (cd != pcd_current)
 				pcd_bufblk = -1;
 			pcd_current = cd;
-			pcd_sector = pcd_req->sector;
-			pcd_count = pcd_req->current_nr_sectors;
+			pcd_sector = blk_rq_pos(pcd_req);
+			pcd_count = blk_rq_cur_sectors(pcd_req);
 			pcd_buf = pcd_req->buffer;
 			pcd_busy = 1;
 			ps_set_intr(do_pcd_read, NULL, 0, nice);
 			return;
-		} else
-			end_request(pcd_req, 0);
+		} else {
+			__blk_end_request_all(pcd_req, -EIO);
+			pcd_req = NULL;
+		}
 	}
 }
 
-static inline void next_request(int success)
+static inline void next_request(int err)
 {
 	unsigned long saved_flags;
 
 	spin_lock_irqsave(&pcd_lock, saved_flags);
-	end_request(pcd_req, success);
+	if (!__blk_end_request_cur(pcd_req, err))
+		pcd_req = NULL;
 	pcd_busy = 0;
 	do_pcd_request(pcd_queue);
 	spin_unlock_irqrestore(&pcd_lock, saved_flags);
@@ -781,7 +786,7 @@ static void pcd_start(void)
 
 	if (pcd_command(pcd_current, rd_cmd, 2048, "read block")) {
 		pcd_bufblk = -1;
-		next_request(0);
+		next_request(-EIO);
 		return;
 	}
 
@@ -796,7 +801,7 @@ static void do_pcd_read(void)
 	pcd_retries = 0;
 	pcd_transfer();
 	if (!pcd_count) {
-		next_request(1);
+		next_request(0);
 		return;
 	}
 
@@ -815,7 +820,7 @@ static void do_pcd_read_drq(void)
 			return;
 		}
 		pcd_bufblk = -1;
-		next_request(0);
+		next_request(-EIO);
 		return;
 	}
 

drivers/block/paride/pd.c

@@ -410,10 +410,12 @@ static void run_fsm(void)
 				pd_claimed = 0;
 				phase = NULL;
 				spin_lock_irqsave(&pd_lock, saved_flags);
-				end_request(pd_req, res);
-				pd_req = elv_next_request(pd_queue);
-				if (!pd_req)
-					stop = 1;
+				if (!__blk_end_request_cur(pd_req,
+						res == Ok ? 0 : -EIO)) {
+					pd_req = blk_fetch_request(pd_queue);
+					if (!pd_req)
+						stop = 1;
+				}
 				spin_unlock_irqrestore(&pd_lock, saved_flags);
 				if (stop)
 					return;
@@ -443,11 +445,11 @@ static enum action do_pd_io_start(void)
 
 	pd_cmd = rq_data_dir(pd_req);
 	if (pd_cmd == READ || pd_cmd == WRITE) {
-		pd_block = pd_req->sector;
-		pd_count = pd_req->current_nr_sectors;
+		pd_block = blk_rq_pos(pd_req);
+		pd_count = blk_rq_cur_sectors(pd_req);
 		if (pd_block + pd_count > get_capacity(pd_req->rq_disk))
 			return Fail;
-		pd_run = pd_req->nr_sectors;
+		pd_run = blk_rq_sectors(pd_req);
 		pd_buf = pd_req->buffer;
 		pd_retries = 0;
 		if (pd_cmd == READ)
@@ -477,8 +479,8 @@ static int pd_next_buf(void)
 	if (pd_count)
 		return 0;
 	spin_lock_irqsave(&pd_lock, saved_flags);
-	end_request(pd_req, 1);
-	pd_count = pd_req->current_nr_sectors;
+	__blk_end_request_cur(pd_req, 0);
+	pd_count = blk_rq_cur_sectors(pd_req);
 	pd_buf = pd_req->buffer;
 	spin_unlock_irqrestore(&pd_lock, saved_flags);
 	return 0;
@@ -702,7 +704,7 @@ static void do_pd_request(struct request_queue * q)
 {
 	if (pd_req)
 		return;
-	pd_req = elv_next_request(q);
+	pd_req = blk_fetch_request(q);
 	if (!pd_req)
 		return;
 

drivers/block/paride/pf.c

@@ -750,12 +750,10 @@ static int pf_ready(void)
 
 static struct request_queue *pf_queue;
 
-static void pf_end_request(int uptodate)
+static void pf_end_request(int err)
 {
-	if (pf_req) {
-		end_request(pf_req, uptodate);
+	if (pf_req && !__blk_end_request_cur(pf_req, err))
 		pf_req = NULL;
-	}
 }
 
 static void do_pf_request(struct request_queue * q)
@@ -763,17 +761,19 @@ static void do_pf_request(struct request_queue * q)
 	if (pf_busy)
 		return;
 repeat:
-	pf_req = elv_next_request(q);
-	if (!pf_req)
-		return;
+	if (!pf_req) {
+		pf_req = blk_fetch_request(q);
+		if (!pf_req)
+			return;
+	}
 
 	pf_current = pf_req->rq_disk->private_data;
-	pf_block = pf_req->sector;
-	pf_run = pf_req->nr_sectors;
-	pf_count = pf_req->current_nr_sectors;
+	pf_block = blk_rq_pos(pf_req);
+	pf_run = blk_rq_sectors(pf_req);
+	pf_count = blk_rq_cur_sectors(pf_req);
 
 	if (pf_block + pf_count > get_capacity(pf_req->rq_disk)) {
-		pf_end_request(0);
+		pf_end_request(-EIO);
 		goto repeat;
 	}
 
@@ -788,7 +788,7 @@ repeat:
 		pi_do_claimed(pf_current->pi, do_pf_write);
 	else {
 		pf_busy = 0;
-		pf_end_request(0);
+		pf_end_request(-EIO);
 		goto repeat;
 	}
 }
@@ -805,23 +805,22 @@ static int pf_next_buf(void)
 		return 1;
 	if (!pf_count) {
 		spin_lock_irqsave(&pf_spin_lock, saved_flags);
-		pf_end_request(1);
-		pf_req = elv_next_request(pf_queue);
+		pf_end_request(0);
 		spin_unlock_irqrestore(&pf_spin_lock, saved_flags);
 		if (!pf_req)
 			return 1;
-		pf_count = pf_req->current_nr_sectors;
+		pf_count = blk_rq_cur_sectors(pf_req);
 		pf_buf = pf_req->buffer;
 	}
 	return 0;
 }
 
-static inline void next_request(int success)
+static inline void next_request(int err)
 {
 	unsigned long saved_flags;
 
 	spin_lock_irqsave(&pf_spin_lock, saved_flags);
-	pf_end_request(success);
+	pf_end_request(err);
 	pf_busy = 0;
 	do_pf_request(pf_queue);
 	spin_unlock_irqrestore(&pf_spin_lock, saved_flags);
@@ -844,7 +843,7 @@ static void do_pf_read_start(void)
 			pi_do_claimed(pf_current->pi, do_pf_read_start);
 			return;
 		}
-		next_request(0);
+		next_request(-EIO);
 		return;
 	}
 	pf_mask = STAT_DRQ;
@@ -863,7 +862,7 @@ static void do_pf_read_drq(void)
 				pi_do_claimed(pf_current->pi, do_pf_read_start);
 				return;
 			}
-			next_request(0);
+			next_request(-EIO);
 			return;
 		}
 		pi_read_block(pf_current->pi, pf_buf, 512);
@@ -871,7 +870,7 @@ static void do_pf_read_drq(void)
 			break;
 	}
 	pi_disconnect(pf_current->pi);
-	next_request(1);
+	next_request(0);
 }
 
 static void do_pf_write(void)
@@ -890,7 +889,7 @@ static void do_pf_write_start(void)
 			pi_do_claimed(pf_current->pi, do_pf_write_start);
 			return;
 		}
-		next_request(0);
+		next_request(-EIO);
 		return;
 	}
 
@@ -903,7 +902,7 @@ static void do_pf_write_start(void)
 				pi_do_claimed(pf_current->pi, do_pf_write_start);
 				return;
 			}
-			next_request(0);
+			next_request(-EIO);
 			return;
 		}
 		pi_write_block(pf_current->pi, pf_buf, 512);
@@ -923,11 +922,11 @@ static void do_pf_write_done(void)
 			pi_do_claimed(pf_current->pi, do_pf_write_start);
 			return;
 		}
-		next_request(0);
+		next_request(-EIO);
 		return;
 	}
 	pi_disconnect(pf_current->pi);
-	next_request(1);
+	next_request(0);
 }
 
 static int __init pf_init(void)

drivers/block/pktcdvd.c

@@ -991,13 +991,15 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
  */
 static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q)
 {
-	if ((pd->settings.size << 9) / CD_FRAMESIZE <= q->max_phys_segments) {
+	if ((pd->settings.size << 9) / CD_FRAMESIZE
+	    <= queue_max_phys_segments(q)) {
 		/*
 		 * The cdrom device can handle one segment/frame
 		 */
 		clear_bit(PACKET_MERGE_SEGS, &pd->flags);
 		return 0;
-	} else if ((pd->settings.size << 9) / PAGE_SIZE <= q->max_phys_segments) {
+	} else if ((pd->settings.size << 9) / PAGE_SIZE
+		   <= queue_max_phys_segments(q)) {
 		/*
 		 * We can handle this case at the expense of some extra memory
 		 * copies during write operations
@@ -2657,7 +2659,7 @@ static void pkt_init_queue(struct pktcdvd_device *pd)
 	struct request_queue *q = pd->disk->queue;
 
 	blk_queue_make_request(q, pkt_make_request);
-	blk_queue_hardsect_size(q, CD_FRAMESIZE);
+	blk_queue_logical_block_size(q, CD_FRAMESIZE);
 	blk_queue_max_sectors(q, PACKET_MAX_SECTORS);
 	blk_queue_merge_bvec(q, pkt_merge_bvec);
 	q->queuedata = pd;

drivers/block/ps3disk.c

@@ -134,13 +134,12 @@ static int ps3disk_submit_request_sg(struct ps3_storage_device *dev,
 	rq_for_each_segment(bv, req, iter)
 		n++;
 	dev_dbg(&dev->sbd.core,
-		"%s:%u: %s req has %u bvecs for %lu sectors %lu hard sectors\n",
-		__func__, __LINE__, op, n, req->nr_sectors,
-		req->hard_nr_sectors);
+		"%s:%u: %s req has %u bvecs for %u sectors\n",
+		__func__, __LINE__, op, n, blk_rq_sectors(req));
 #endif
 
-	start_sector = req->sector * priv->blocking_factor;
-	sectors = req->nr_sectors * priv->blocking_factor;
+	start_sector = blk_rq_pos(req) * priv->blocking_factor;
+	sectors = blk_rq_sectors(req) * priv->blocking_factor;
 	dev_dbg(&dev->sbd.core, "%s:%u: %s %llu sectors starting at %llu\n",
 		__func__, __LINE__, op, sectors, start_sector);
 
@@ -158,7 +157,7 @@ static int ps3disk_submit_request_sg(struct ps3_storage_device *dev,
 	if (res) {
 		dev_err(&dev->sbd.core, "%s:%u: %s failed %d\n", __func__,
 			__LINE__, op, res);
-		end_request(req, 0);
+		__blk_end_request_all(req, -EIO);
 		return 0;
 	}
 
@@ -180,7 +179,7 @@ static int ps3disk_submit_flush_request(struct ps3_storage_device *dev,
 	if (res) {
 		dev_err(&dev->sbd.core, "%s:%u: sync cache failed 0x%llx\n",
 			__func__, __LINE__, res);
-		end_request(req, 0);
+		__blk_end_request_all(req, -EIO);
 		return 0;
 	}
 
@@ -195,7 +194,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev,
 
 	dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__);
 
-	while ((req = elv_next_request(q))) {
+	while ((req = blk_fetch_request(q))) {
 		if (blk_fs_request(req)) {
 			if (ps3disk_submit_request_sg(dev, req))
 				break;
@@ -205,7 +204,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev,
 				break;
 		} else {
 			blk_dump_rq_flags(req, DEVICE_NAME " bad request");
-			end_request(req, 0);
+			__blk_end_request_all(req, -EIO);
 			continue;
 		}
 	}
@@ -231,7 +230,6 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
 	struct request *req;
 	int res, read, error;
 	u64 tag, status;
-	unsigned long num_sectors;
 	const char *op;
 
 	res = lv1_storage_get_async_status(dev->sbd.dev_id, &tag, &status);
@@ -261,11 +259,9 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
 	if (req->cmd_type == REQ_TYPE_LINUX_BLOCK &&
 	    req->cmd[0] == REQ_LB_OP_FLUSH) {
 		read = 0;
-		num_sectors = req->hard_cur_sectors;
 		op = "flush";
 	} else {
 		read = !rq_data_dir(req);
-		num_sectors = req->nr_sectors;
 		op = read ? "read" : "write";
 	}
 	if (status) {
@@ -281,7 +277,7 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
 	}
 
 	spin_lock(&priv->lock);
-	__blk_end_request(req, error, num_sectors << 9);
+	__blk_end_request_all(req, error);
 	priv->req = NULL;
 	ps3disk_do_request(dev, priv->queue);
 	spin_unlock(&priv->lock);
@@ -481,7 +477,7 @@ static int __devinit ps3disk_probe(struct ps3_system_bus_device *_dev)
 	blk_queue_max_sectors(queue, dev->bounce_size >> 9);
 	blk_queue_segment_boundary(queue, -1UL);
 	blk_queue_dma_alignment(queue, dev->blk_size-1);
-	blk_queue_hardsect_size(queue, dev->blk_size);
+	blk_queue_logical_block_size(queue, dev->blk_size);
 
 	blk_queue_ordered(queue, QUEUE_ORDERED_DRAIN_FLUSH,
 			  ps3disk_prepare_flush);

drivers/block/sunvdc.c

@@ -212,11 +212,6 @@ static void vdc_end_special(struct vdc_port *port, struct vio_disk_desc *desc)
 	vdc_finish(&port->vio, -err, WAITING_FOR_GEN_CMD);
 }
 
-static void vdc_end_request(struct request *req, int error, int num_sectors)
-{
-	__blk_end_request(req, error, num_sectors << 9);
-}
-
 static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
 			unsigned int index)
 {
@@ -239,7 +234,7 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
 
 	rqe->req = NULL;
 
-	vdc_end_request(req, (desc->status ? -EIO : 0), desc->size >> 9);
+	__blk_end_request(req, (desc->status ? -EIO : 0), desc->size);
 
 	if (blk_queue_stopped(port->disk->queue))
 		blk_start_queue(port->disk->queue);
@@ -421,7 +416,7 @@ static int __send_request(struct request *req)
 		desc->slice = 0;
 	}
 	desc->status = ~0;
-	desc->offset = (req->sector << 9) / port->vdisk_block_size;
+	desc->offset = (blk_rq_pos(req) << 9) / port->vdisk_block_size;
 	desc->size = len;
 	desc->ncookies = err;
 
@@ -446,14 +441,13 @@ out:
 static void do_vdc_request(struct request_queue *q)
 {
 	while (1) {
-		struct request *req = elv_next_request(q);
+		struct request *req = blk_fetch_request(q);
 
 		if (!req)
 			break;
 
-		blkdev_dequeue_request(req);
 		if (__send_request(req) < 0)
-			vdc_end_request(req, -EIO, req->hard_nr_sectors);
+			__blk_end_request_all(req, -EIO);
 	}
 }
 

drivers/block/swim.c

@@ -514,7 +514,7 @@ static int floppy_read_sectors(struct floppy_state *fs,
 			ret = swim_read_sector(fs, side, track, sector,
 						buffer);
 			if (try-- == 0)
-				return -1;
+				return -EIO;
 		} while (ret != 512);
 
 		buffer += ret;
@@ -528,45 +528,31 @@ static void redo_fd_request(struct request_queue *q)
 	struct request *req;
 	struct floppy_state *fs;
 
-	while ((req = elv_next_request(q))) {
+	req = blk_fetch_request(q);
+	while (req) {
+		int err = -EIO;
 
 		fs = req->rq_disk->private_data;
-		if (req->sector < 0 || req->sector >= fs->total_secs) {
-			end_request(req, 0);
-			continue;
-		}
-		if (req->current_nr_sectors == 0) {
-			end_request(req, 1);
-			continue;
-		}
-		if (!fs->disk_in) {
-			end_request(req, 0);
-			continue;
-		}
-		if (rq_data_dir(req) == WRITE) {
-			if (fs->write_protected) {
-				end_request(req, 0);
-				continue;
-			}
-		}
+		if (blk_rq_pos(req) >= fs->total_secs)
+			goto done;
+		if (!fs->disk_in)
+			goto done;
+		if (rq_data_dir(req) == WRITE && fs->write_protected)
+			goto done;
+
 		switch (rq_data_dir(req)) {
 		case WRITE:
 			/* NOT IMPLEMENTED */
-			end_request(req, 0);
 			break;
 		case READ:
-			if (floppy_read_sectors(fs, req->sector,
-						req->current_nr_sectors,
-						req->buffer)) {
-				end_request(req, 0);
-				continue;
-			}
-			req->nr_sectors -= req->current_nr_sectors;
-			req->sector += req->current_nr_sectors;
-			req->buffer += req->current_nr_sectors * 512;
-			end_request(req, 1);
+			err = floppy_read_sectors(fs, blk_rq_pos(req),
+						  blk_rq_cur_sectors(req),
+						  req->buffer);
 			break;
 		}
+	done:
+		if (!__blk_end_request_cur(req, err))
+			req = blk_fetch_request(q);
 	}
 }
 

drivers/block/swim3.c

@@ -251,6 +251,20 @@ static int floppy_release(struct gendisk *disk, fmode_t mode);
 static int floppy_check_change(struct gendisk *disk);
 static int floppy_revalidate(struct gendisk *disk);
 
+static bool swim3_end_request(int err, unsigned int nr_bytes)
+{
+	if (__blk_end_request(fd_req, err, nr_bytes))
+		return true;
+
+	fd_req = NULL;
+	return false;
+}
+
+static bool swim3_end_request_cur(int err)
+{
+	return swim3_end_request(err, blk_rq_cur_bytes(fd_req));
+}
+
 static void swim3_select(struct floppy_state *fs, int sel)
 {
 	struct swim3 __iomem *sw = fs->swim3;
@@ -310,25 +324,27 @@ static void start_request(struct floppy_state *fs)
 		wake_up(&fs->wait);
 		return;
 	}
-	while (fs->state == idle && (req = elv_next_request(swim3_queue))) {
+	while (fs->state == idle) {
+		if (!fd_req) {
+			fd_req = blk_fetch_request(swim3_queue);
+			if (!fd_req)
+				break;
+		}
+		req = fd_req;
 #if 0
-		printk("do_fd_req: dev=%s cmd=%d sec=%ld nr_sec=%ld buf=%p\n",
+		printk("do_fd_req: dev=%s cmd=%d sec=%ld nr_sec=%u buf=%p\n",
 		       req->rq_disk->disk_name, req->cmd,
-		       (long)req->sector, req->nr_sectors, req->buffer);
-		printk("           errors=%d current_nr_sectors=%ld\n",
-		       req->errors, req->current_nr_sectors);
+		       (long)blk_rq_pos(req), blk_rq_sectors(req), req->buffer);
+		printk("           errors=%d current_nr_sectors=%u\n",
+		       req->errors, blk_rq_cur_sectors(req));
 #endif
 
-		if (req->sector < 0 || req->sector >= fs->total_secs) {
-			end_request(req, 0);
-			continue;
-		}
-		if (req->current_nr_sectors == 0) {
-			end_request(req, 1);
+		if (blk_rq_pos(req) >= fs->total_secs) {
+			swim3_end_request_cur(-EIO);
 			continue;
 		}
 		if (fs->ejected) {
-			end_request(req, 0);
+			swim3_end_request_cur(-EIO);
 			continue;
 		}
 
@@ -336,18 +352,19 @@ static void start_request(struct floppy_state *fs)
 			if (fs->write_prot < 0)
 				fs->write_prot = swim3_readbit(fs, WRITE_PROT);
 			if (fs->write_prot) {
-				end_request(req, 0);
+				swim3_end_request_cur(-EIO);
 				continue;
 			}
 		}
 
-		/* Do not remove the cast. req->sector is now a sector_t and
-		 * can be 64 bits, but it will never go past 32 bits for this
-		 * driver anyway, so we can safely cast it down and not have
-		 * to do a 64/32 division
+		/* Do not remove the cast. blk_rq_pos(req) is now a
+		 * sector_t and can be 64 bits, but it will never go
+		 * past 32 bits for this driver anyway, so we can
+		 * safely cast it down and not have to do a 64/32
+		 * division
 		 */
-		fs->req_cyl = ((long)req->sector) / fs->secpercyl;
-		x = ((long)req->sector) % fs->secpercyl;
+		fs->req_cyl = ((long)blk_rq_pos(req)) / fs->secpercyl;
+		x = ((long)blk_rq_pos(req)) % fs->secpercyl;
 		fs->head = x / fs->secpertrack;
 		fs->req_sector = x % fs->secpertrack + 1;
 		fd_req = req;
@@ -424,7 +441,7 @@ static inline void setup_transfer(struct floppy_state *fs)
 	struct dbdma_cmd *cp = fs->dma_cmd;
 	struct dbdma_regs __iomem *dr = fs->dma;
 
-	if (fd_req->current_nr_sectors <= 0) {
+	if (blk_rq_cur_sectors(fd_req) <= 0) {
 		printk(KERN_ERR "swim3: transfer 0 sectors?\n");
 		return;
 	}
@@ -432,8 +449,8 @@ static inline void setup_transfer(struct floppy_state *fs)
 		n = 1;
 	else {
 		n = fs->secpertrack - fs->req_sector + 1;
-		if (n > fd_req->current_nr_sectors)
-			n = fd_req->current_nr_sectors;
+		if (n > blk_rq_cur_sectors(fd_req))
+			n = blk_rq_cur_sectors(fd_req);
 	}
 	fs->scount = n;
 	swim3_select(fs, fs->head? READ_DATA_1: READ_DATA_0);
@@ -508,7 +525,7 @@ static void act(struct floppy_state *fs)
 		case do_transfer:
 			if (fs->cur_cyl != fs->req_cyl) {
 				if (fs->retries > 5) {
-					end_request(fd_req, 0);
+					swim3_end_request_cur(-EIO);
 					fs->state = idle;
 					return;
 				}
@@ -540,7 +557,7 @@ static void scan_timeout(unsigned long data)
 	out_8(&sw->intr_enable, 0);
 	fs->cur_cyl = -1;
 	if (fs->retries > 5) {
-		end_request(fd_req, 0);
+		swim3_end_request_cur(-EIO);
 		fs->state = idle;
 		start_request(fs);
 	} else {
@@ -559,7 +576,7 @@ static void seek_timeout(unsigned long data)
 	out_8(&sw->select, RELAX);
 	out_8(&sw->intr_enable, 0);
 	printk(KERN_ERR "swim3: seek timeout\n");
-	end_request(fd_req, 0);
+	swim3_end_request_cur(-EIO);
 	fs->state = idle;
 	start_request(fs);
 }
@@ -583,7 +600,7 @@ static void settle_timeout(unsigned long data)
 		return;
 	}
 	printk(KERN_ERR "swim3: seek settle timeout\n");
-	end_request(fd_req, 0);
+	swim3_end_request_cur(-EIO);
 	fs->state = idle;
 	start_request(fs);
 }
@@ -593,8 +610,6 @@ static void xfer_timeout(unsigned long data)
 	struct floppy_state *fs = (struct floppy_state *) data;
 	struct swim3 __iomem *sw = fs->swim3;
 	struct dbdma_regs __iomem *dr = fs->dma;
-	struct dbdma_cmd *cp = fs->dma_cmd;
-	unsigned long s;
 	int n;
 
 	fs->timeout_pending = 0;
@@ -605,17 +620,10 @@ static void xfer_timeout(unsigned long data)
 	out_8(&sw->intr_enable, 0);
 	out_8(&sw->control_bic, WRITE_SECTORS | DO_ACTION);
 	out_8(&sw->select, RELAX);
-	if (rq_data_dir(fd_req) == WRITE)
-		++cp;
-	if (ld_le16(&cp->xfer_status) != 0)
-		s = fs->scount - ((ld_le16(&cp->res_count) + 511) >> 9);
-	else
-		s = 0;
-	fd_req->sector += s;
-	fd_req->current_nr_sectors -= s;
 	printk(KERN_ERR "swim3: timeout %sing sector %ld\n",
-	       (rq_data_dir(fd_req)==WRITE? "writ": "read"), (long)fd_req->sector);
-	end_request(fd_req, 0);
+	       (rq_data_dir(fd_req)==WRITE? "writ": "read"),
+	       (long)blk_rq_pos(fd_req));
+	swim3_end_request_cur(-EIO);
 	fs->state = idle;
 	start_request(fs);
 }
@@ -646,7 +654,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 				printk(KERN_ERR "swim3: seen sector but cyl=ff?\n");
 				fs->cur_cyl = -1;
 				if (fs->retries > 5) {
-					end_request(fd_req, 0);
+					swim3_end_request_cur(-EIO);
 					fs->state = idle;
 					start_request(fs);
 				} else {
@@ -719,9 +727,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 		if (intr & ERROR_INTR) {
 			n = fs->scount - 1 - resid / 512;
 			if (n > 0) {
-				fd_req->sector += n;
-				fd_req->current_nr_sectors -= n;
-				fd_req->buffer += n * 512;
+				blk_update_request(fd_req, 0, n << 9);
 				fs->req_sector += n;
 			}
 			if (fs->retries < 5) {
@@ -730,8 +736,8 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 			} else {
 				printk("swim3: error %sing block %ld (err=%x)\n",
 				       rq_data_dir(fd_req) == WRITE? "writ": "read",
-				       (long)fd_req->sector, err);
-				end_request(fd_req, 0);
+				       (long)blk_rq_pos(fd_req), err);
+				swim3_end_request_cur(-EIO);
 				fs->state = idle;
 			}
 		} else {
@@ -740,18 +746,12 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 				printk(KERN_ERR "swim3: fd dma: stat=%x resid=%d\n", stat, resid);
 				printk(KERN_ERR "  state=%d, dir=%x, intr=%x, err=%x\n",
 				       fs->state, rq_data_dir(fd_req), intr, err);
-				end_request(fd_req, 0);
+				swim3_end_request_cur(-EIO);
 				fs->state = idle;
 				start_request(fs);
 				break;
 			}
-			fd_req->sector += fs->scount;
-			fd_req->current_nr_sectors -= fs->scount;
-			fd_req->buffer += fs->scount * 512;
-			if (fd_req->current_nr_sectors <= 0) {
-				end_request(fd_req, 1);
-				fs->state = idle;
-			} else {
+			if (swim3_end_request(0, fs->scount << 9)) {
 				fs->req_sector += fs->scount;
 				if (fs->req_sector > fs->secpertrack) {
 					fs->req_sector -= fs->secpertrack;
@@ -761,7 +761,8 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 					}
 				}
 				act(fs);
-			}
+			} else
+				fs->state = idle;
 		}
 		if (fs->state == idle)
 			start_request(fs);

drivers/block/sx8.c

@@ -749,8 +749,7 @@ static inline void carm_end_request_queued(struct carm_host *host,
 	struct request *req = crq->rq;
 	int rc;
 
-	rc = __blk_end_request(req, error, blk_rq_bytes(req));
-	assert(rc == 0);
+	__blk_end_request_all(req, error);
 
 	rc = carm_put_request(host, crq);
 	assert(rc == 0);
@@ -811,12 +810,10 @@ static void carm_oob_rq_fn(struct request_queue *q)
 
 	while (1) {
 		DPRINTK("get req\n");
-		rq = elv_next_request(q);
+		rq = blk_fetch_request(q);
 		if (!rq)
 			break;
 
-		blkdev_dequeue_request(rq);
-
 		crq = rq->special;
 		assert(crq != NULL);
 		assert(crq->rq == rq);
@@ -847,7 +844,7 @@ static void carm_rq_fn(struct request_queue *q)
 
 queue_one_request:
 	VPRINTK("get req\n");
-	rq = elv_next_request(q);
+	rq = blk_peek_request(q);
 	if (!rq)
 		return;
 
@@ -858,7 +855,7 @@ queue_one_request:
 	}
 	crq->rq = rq;
 
-	blkdev_dequeue_request(rq);
+	blk_start_request(rq);
 
 	if (rq_data_dir(rq) == WRITE) {
 		writing = 1;
@@ -904,10 +901,10 @@ queue_one_request:
 	msg->sg_count	= n_elem;
 	msg->sg_type	= SGT_32BIT;
 	msg->handle	= cpu_to_le32(TAG_ENCODE(crq->tag));
-	msg->lba	= cpu_to_le32(rq->sector & 0xffffffff);
-	tmp		= (rq->sector >> 16) >> 16;
+	msg->lba	= cpu_to_le32(blk_rq_pos(rq) & 0xffffffff);
+	tmp		= (blk_rq_pos(rq) >> 16) >> 16;
 	msg->lba_high	= cpu_to_le16( (u16) tmp );
-	msg->lba_count	= cpu_to_le16(rq->nr_sectors);
+	msg->lba_count	= cpu_to_le16(blk_rq_sectors(rq));
 
 	msg_size = sizeof(struct carm_msg_rw) - sizeof(msg->sg);
 	for (i = 0; i < n_elem; i++) {

drivers/block/ub.c

@@ -360,8 +360,7 @@ static void ub_cmd_build_block(struct ub_dev *sc, struct ub_lun *lun,
 static void ub_cmd_build_packet(struct ub_dev *sc, struct ub_lun *lun,
     struct ub_scsi_cmd *cmd, struct ub_request *urq);
 static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd);
-static void ub_end_rq(struct request *rq, unsigned int status,
-    unsigned int cmd_len);
+static void ub_end_rq(struct request *rq, unsigned int status);
 static int ub_rw_cmd_retry(struct ub_dev *sc, struct ub_lun *lun,
     struct ub_request *urq, struct ub_scsi_cmd *cmd);
 static int ub_submit_scsi(struct ub_dev *sc, struct ub_scsi_cmd *cmd);
@@ -627,7 +626,7 @@ static void ub_request_fn(struct request_queue *q)
 	struct ub_lun *lun = q->queuedata;
 	struct request *rq;
 
-	while ((rq = elv_next_request(q)) != NULL) {
+	while ((rq = blk_peek_request(q)) != NULL) {
 		if (ub_request_fn_1(lun, rq) != 0) {
 			blk_stop_queue(q);
 			break;
@@ -643,14 +642,14 @@ static int ub_request_fn_1(struct ub_lun *lun, struct request *rq)
 	int n_elem;
 
 	if (atomic_read(&sc->poison)) {
-		blkdev_dequeue_request(rq);
-		ub_end_rq(rq, DID_NO_CONNECT << 16, blk_rq_bytes(rq));
+		blk_start_request(rq);
+		ub_end_rq(rq, DID_NO_CONNECT << 16);
 		return 0;
 	}
 
 	if (lun->changed && !blk_pc_request(rq)) {
-		blkdev_dequeue_request(rq);
-		ub_end_rq(rq, SAM_STAT_CHECK_CONDITION, blk_rq_bytes(rq));
+		blk_start_request(rq);
+		ub_end_rq(rq, SAM_STAT_CHECK_CONDITION);
 		return 0;
 	}
 
@@ -660,7 +659,7 @@ static int ub_request_fn_1(struct ub_lun *lun, struct request *rq)
 		return -1;
 	memset(cmd, 0, sizeof(struct ub_scsi_cmd));
 
-	blkdev_dequeue_request(rq);
+	blk_start_request(rq);
 
 	urq = &lun->urq;
 	memset(urq, 0, sizeof(struct ub_request));
@@ -702,7 +701,7 @@ static int ub_request_fn_1(struct ub_lun *lun, struct request *rq)
 
 drop:
 	ub_put_cmd(lun, cmd);
-	ub_end_rq(rq, DID_ERROR << 16, blk_rq_bytes(rq));
+	ub_end_rq(rq, DID_ERROR << 16);
 	return 0;
 }
 
@@ -723,11 +722,11 @@ static void ub_cmd_build_block(struct ub_dev *sc, struct ub_lun *lun,
 	/*
 	 * build the command
 	 *
-	 * The call to blk_queue_hardsect_size() guarantees that request
+	 * The call to blk_queue_logical_block_size() guarantees that request
 	 * is aligned, but it is given in terms of 512 byte units, always.
 	 */
-	block = rq->sector >> lun->capacity.bshift;
-	nblks = rq->nr_sectors >> lun->capacity.bshift;
+	block = blk_rq_pos(rq) >> lun->capacity.bshift;
+	nblks = blk_rq_sectors(rq) >> lun->capacity.bshift;
 
 	cmd->cdb[0] = (cmd->dir == UB_DIR_READ)? READ_10: WRITE_10;
 	/* 10-byte uses 4 bytes of LBA: 2147483648KB, 2097152MB, 2048GB */
@@ -739,7 +738,7 @@ static void ub_cmd_build_block(struct ub_dev *sc, struct ub_lun *lun,
 	cmd->cdb[8] = nblks;
 	cmd->cdb_len = 10;
 
-	cmd->len = rq->nr_sectors * 512;
+	cmd->len = blk_rq_bytes(rq);
 }
 
 static void ub_cmd_build_packet(struct ub_dev *sc, struct ub_lun *lun,
@@ -747,7 +746,7 @@ static void ub_cmd_build_packet(struct ub_dev *sc, struct ub_lun *lun,
 {
 	struct request *rq = urq->rq;
 
-	if (rq->data_len == 0) {
+	if (blk_rq_bytes(rq) == 0) {
 		cmd->dir = UB_DIR_NONE;
 	} else {
 		if (rq_data_dir(rq) == WRITE)
@@ -762,7 +761,7 @@ static void ub_cmd_build_packet(struct ub_dev *sc, struct ub_lun *lun,
 	memcpy(&cmd->cdb, rq->cmd, rq->cmd_len);
 	cmd->cdb_len = rq->cmd_len;
 
-	cmd->len = rq->data_len;
+	cmd->len = blk_rq_bytes(rq);
 
 	/*
 	 * To reapply this to every URB is not as incorrect as it looks.
@@ -777,16 +776,15 @@ static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
 	struct ub_request *urq = cmd->back;
 	struct request *rq;
 	unsigned int scsi_status;
-	unsigned int cmd_len;
 
 	rq = urq->rq;
 
 	if (cmd->error == 0) {
 		if (blk_pc_request(rq)) {
-			if (cmd->act_len >= rq->data_len)
-				rq->data_len = 0;
+			if (cmd->act_len >= rq->resid_len)
+				rq->resid_len = 0;
 			else
-				rq->data_len -= cmd->act_len;
+				rq->resid_len -= cmd->act_len;
 			scsi_status = 0;
 		} else {
 			if (cmd->act_len != cmd->len) {
@@ -818,17 +816,14 @@ static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
 
 	urq->rq = NULL;
 
-	cmd_len = cmd->len;
 	ub_put_cmd(lun, cmd);
-	ub_end_rq(rq, scsi_status, cmd_len);
+	ub_end_rq(rq, scsi_status);
 	blk_start_queue(lun->disk->queue);
 }
 
-static void ub_end_rq(struct request *rq, unsigned int scsi_status,
-    unsigned int cmd_len)
+static void ub_end_rq(struct request *rq, unsigned int scsi_status)
 {
 	int error;
-	long rqlen;
 
 	if (scsi_status == 0) {
 		error = 0;
@@ -836,12 +831,7 @@ static void ub_end_rq(struct request *rq, unsigned int scsi_status,
 		error = -EIO;
 		rq->errors = scsi_status;
 	}
-	rqlen = blk_rq_bytes(rq);    /* Oddly enough, this is the residue. */
-	if (__blk_end_request(rq, error, cmd_len)) {
-		printk(KERN_WARNING DRV_NAME
-		    ": __blk_end_request blew, %s-cmd total %u rqlen %ld\n",
-		    blk_pc_request(rq)? "pc": "fs", cmd_len, rqlen);
-	}
+	__blk_end_request_all(rq, error);
 }
 
 static int ub_rw_cmd_retry(struct ub_dev *sc, struct ub_lun *lun,
@@ -1759,7 +1749,7 @@ static int ub_bd_revalidate(struct gendisk *disk)
 	ub_revalidate(lun->udev, lun);
 
 	/* XXX Support sector size switching like in sr.c */
-	blk_queue_hardsect_size(disk->queue, lun->capacity.bsize);
+	blk_queue_logical_block_size(disk->queue, lun->capacity.bsize);
 	set_capacity(disk, lun->capacity.nsec);
 	// set_disk_ro(sdkp->disk, lun->readonly);
 
@@ -2334,7 +2324,7 @@ static int ub_probe_lun(struct ub_dev *sc, int lnum)
 	blk_queue_max_phys_segments(q, UB_MAX_REQ_SG);
 	blk_queue_segment_boundary(q, 0xffffffff);	/* Dubious. */
 	blk_queue_max_sectors(q, UB_MAX_SECTORS);
-	blk_queue_hardsect_size(q, lun->capacity.bsize);
+	blk_queue_logical_block_size(q, lun->capacity.bsize);
 
 	lun->disk = disk;
 	q->queuedata = lun;

drivers/block/viodasd.c

@@ -252,7 +252,7 @@ static int send_request(struct request *req)
 	struct viodasd_device *d;
 	unsigned long flags;
 
-	start = (u64)req->sector << 9;
+	start = (u64)blk_rq_pos(req) << 9;
 
 	if (rq_data_dir(req) == READ) {
 		direction = DMA_FROM_DEVICE;
@@ -361,19 +361,17 @@ static void do_viodasd_request(struct request_queue *q)
 	 * back later.
 	 */
 	while (num_req_outstanding < VIOMAXREQ) {
-		req = elv_next_request(q);
+		req = blk_fetch_request(q);
 		if (req == NULL)
 			return;
-		/* dequeue the current request from the queue */
-		blkdev_dequeue_request(req);
 		/* check that request contains a valid command */
 		if (!blk_fs_request(req)) {
-			viodasd_end_request(req, -EIO, req->hard_nr_sectors);
+			viodasd_end_request(req, -EIO, blk_rq_sectors(req));
 			continue;
 		}
 		/* Try sending the request */
 		if (send_request(req) != 0)
-			viodasd_end_request(req, -EIO, req->hard_nr_sectors);
+			viodasd_end_request(req, -EIO, blk_rq_sectors(req));
 	}
 }
 
@@ -590,7 +588,7 @@ static int viodasd_handle_read_write(struct vioblocklpevent *bevent)
 		err = vio_lookup_rc(viodasd_err_table, bevent->sub_result);
 		printk(VIOD_KERN_WARNING "read/write error %d:0x%04x (%s)\n",
 				event->xRc, bevent->sub_result, err->msg);
-		num_sect = req->hard_nr_sectors;
+		num_sect = blk_rq_sectors(req);
 	}
 	qlock = req->q->queue_lock;
 	spin_lock_irqsave(qlock, irq_flags);

drivers/block/virtio_blk.c

@@ -37,6 +37,7 @@ struct virtblk_req
 	struct list_head list;
 	struct request *req;
 	struct virtio_blk_outhdr out_hdr;
+	struct virtio_scsi_inhdr in_hdr;
 	u8 status;
 };
 
@@ -50,6 +51,7 @@ static void blk_done(struct virtqueue *vq)
 	spin_lock_irqsave(&vblk->lock, flags);
 	while ((vbr = vblk->vq->vq_ops->get_buf(vblk->vq, &len)) != NULL) {
 		int error;
+
 		switch (vbr->status) {
 		case VIRTIO_BLK_S_OK:
 			error = 0;
@@ -62,7 +64,13 @@ static void blk_done(struct virtqueue *vq)
 			break;
 		}
 
-		__blk_end_request(vbr->req, error, blk_rq_bytes(vbr->req));
+		if (blk_pc_request(vbr->req)) {
+			vbr->req->resid_len = vbr->in_hdr.residual;
+			vbr->req->sense_len = vbr->in_hdr.sense_len;
+			vbr->req->errors = vbr->in_hdr.errors;
+		}
+
+		__blk_end_request_all(vbr->req, error);
 		list_del(&vbr->list);
 		mempool_free(vbr, vblk->pool);
 	}
@@ -74,7 +82,7 @@ static void blk_done(struct virtqueue *vq)
 static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 		   struct request *req)
 {
-	unsigned long num, out, in;
+	unsigned long num, out = 0, in = 0;
 	struct virtblk_req *vbr;
 
 	vbr = mempool_alloc(vblk->pool, GFP_ATOMIC);
@@ -85,7 +93,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 	vbr->req = req;
 	if (blk_fs_request(vbr->req)) {
 		vbr->out_hdr.type = 0;
-		vbr->out_hdr.sector = vbr->req->sector;
+		vbr->out_hdr.sector = blk_rq_pos(vbr->req);
 		vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
 	} else if (blk_pc_request(vbr->req)) {
 		vbr->out_hdr.type = VIRTIO_BLK_T_SCSI_CMD;
@@ -99,18 +107,36 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 	if (blk_barrier_rq(vbr->req))
 		vbr->out_hdr.type |= VIRTIO_BLK_T_BARRIER;
 
-	sg_set_buf(&vblk->sg[0], &vbr->out_hdr, sizeof(vbr->out_hdr));
-	num = blk_rq_map_sg(q, vbr->req, vblk->sg+1);
-	sg_set_buf(&vblk->sg[num+1], &vbr->status, sizeof(vbr->status));
+	sg_set_buf(&vblk->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr));
 
-	if (rq_data_dir(vbr->req) == WRITE) {
-		vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
-		out = 1 + num;
-		in = 1;
-	} else {
-		vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
-		out = 1;
-		in = 1 + num;
+	/*
+	 * If this is a packet command we need a couple of additional headers.
+	 * Behind the normal outhdr we put a segment with the scsi command
+	 * block, and before the normal inhdr we put the sense data and the
+	 * inhdr with additional status information before the normal inhdr.
+	 */
+	if (blk_pc_request(vbr->req))
+		sg_set_buf(&vblk->sg[out++], vbr->req->cmd, vbr->req->cmd_len);
+
+	num = blk_rq_map_sg(q, vbr->req, vblk->sg + out);
+
+	if (blk_pc_request(vbr->req)) {
+		sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96);
+		sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr,
+			   sizeof(vbr->in_hdr));
+	}
+
+	sg_set_buf(&vblk->sg[num + out + in++], &vbr->status,
+		   sizeof(vbr->status));
+
+	if (num) {
+		if (rq_data_dir(vbr->req) == WRITE) {
+			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
+			out += num;
+		} else {
+			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
+			in += num;
+		}
 	}
 
 	if (vblk->vq->vq_ops->add_buf(vblk->vq, vblk->sg, out, in, vbr)) {
@@ -124,12 +150,11 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 
 static void do_virtblk_request(struct request_queue *q)
 {
-	struct virtio_blk *vblk = NULL;
+	struct virtio_blk *vblk = q->queuedata;
 	struct request *req;
 	unsigned int issued = 0;
 
-	while ((req = elv_next_request(q)) != NULL) {
-		vblk = req->rq_disk->private_data;
+	while ((req = blk_peek_request(q)) != NULL) {
 		BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
 		/* If this request fails, stop queue and wait for something to
@@ -138,7 +163,7 @@ static void do_virtblk_request(struct request_queue *q)
 			blk_stop_queue(q);
 			break;
 		}
-		blkdev_dequeue_request(req);
+		blk_start_request(req);
 		issued++;
 	}
 
@@ -146,12 +171,51 @@ static void do_virtblk_request(struct request_queue *q)
 		vblk->vq->vq_ops->kick(vblk->vq);
 }
 
+/* return ATA identify data
+ */
+static int virtblk_identify(struct gendisk *disk, void *argp)
+{
+	struct virtio_blk *vblk = disk->private_data;
+	void *opaque;
+	int err = -ENOMEM;
+
+	opaque = kmalloc(VIRTIO_BLK_ID_BYTES, GFP_KERNEL);
+	if (!opaque)
+		goto out;
+
+	err = virtio_config_buf(vblk->vdev, VIRTIO_BLK_F_IDENTIFY,
+		offsetof(struct virtio_blk_config, identify), opaque,
+		VIRTIO_BLK_ID_BYTES);
+
+	if (err)
+		goto out_kfree;
+
+	if (copy_to_user(argp, opaque, VIRTIO_BLK_ID_BYTES))
+		err = -EFAULT;
+
+out_kfree:
+	kfree(opaque);
+out:
+	return err;
+}
+
 static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
 			 unsigned cmd, unsigned long data)
 {
-	return scsi_cmd_ioctl(bdev->bd_disk->queue,
-			      bdev->bd_disk, mode, cmd,
-			      (void __user *)data);
+	struct gendisk *disk = bdev->bd_disk;
+	struct virtio_blk *vblk = disk->private_data;
+	void __user *argp = (void __user *)data;
+
+	if (cmd == HDIO_GET_IDENTITY)
+		return virtblk_identify(disk, argp);
+
+	/*
+	 * Only allow the generic SCSI ioctls if the host can support it.
+	 */
+	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
+		return -ENOIOCTLCMD;
+
+	return scsi_cmd_ioctl(disk->queue, disk, mode, cmd, argp);
 }
 
 /* We provide getgeo only to please some old bootloader/partitioning tools */
@@ -249,6 +313,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 		goto out_put_disk;
 	}
 
+	vblk->disk->queue->queuedata = vblk;
 	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, vblk->disk->queue);
 
 	if (index < 26) {
@@ -313,7 +378,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 				offsetof(struct virtio_blk_config, blk_size),
 				&blk_size);
 	if (!err)
-		blk_queue_hardsect_size(vblk->disk->queue, blk_size);
+		blk_queue_logical_block_size(vblk->disk->queue, blk_size);
 
 	add_disk(vblk->disk);
 	return 0;
@@ -356,6 +421,7 @@ static struct virtio_device_id id_table[] = {
 static unsigned int features[] = {
 	VIRTIO_BLK_F_BARRIER, VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX,
 	VIRTIO_BLK_F_GEOMETRY, VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
+	VIRTIO_BLK_F_SCSI, VIRTIO_BLK_F_IDENTIFY
 };
 
 static struct virtio_driver virtio_blk = {

drivers/block/xd.c

@@ -305,30 +305,25 @@ static void do_xd_request (struct request_queue * q)
 	if (xdc_busy)
 		return;
 
-	while ((req = elv_next_request(q)) != NULL) {
-		unsigned block = req->sector;
-		unsigned count = req->nr_sectors;
-		int rw = rq_data_dir(req);
+	req = blk_fetch_request(q);
+	while (req) {
+		unsigned block = blk_rq_pos(req);
+		unsigned count = blk_rq_cur_sectors(req);
 		XD_INFO *disk = req->rq_disk->private_data;
-		int res = 0;
+		int res = -EIO;
 		int retry;
 
-		if (!blk_fs_request(req)) {
-			end_request(req, 0);
-			continue;
-		}
-		if (block + count > get_capacity(req->rq_disk)) {
-			end_request(req, 0);
-			continue;
-		}
-		if (rw != READ && rw != WRITE) {
-			printk("do_xd_request: unknown request\n");
-			end_request(req, 0);
-			continue;
-		}
+		if (!blk_fs_request(req))
+			goto done;
+		if (block + count > get_capacity(req->rq_disk))
+			goto done;
 		for (retry = 0; (retry < XD_RETRIES) && !res; retry++)
-			res = xd_readwrite(rw, disk, req->buffer, block, count);
-		end_request(req, res);	/* wrap up, 0 = fail, 1 = success */
+			res = xd_readwrite(rq_data_dir(req), disk, req->buffer,
+					   block, count);
+	done:
+		/* wrap up, 0 = success, -errno = fail */
+		if (!__blk_end_request_cur(req, res))
+			req = blk_fetch_request(q);
 	}
 }
 
@@ -418,7 +413,7 @@ static int xd_readwrite (u_char operation,XD_INFO *p,char *buffer,u_int block,u_
 				printk("xd%c: %s timeout, recalibrating drive\n",'a'+drive,(operation == READ ? "read" : "write"));
 				xd_recalibrate(drive);
 				spin_lock_irq(&xd_lock);
-				return (0);
+				return -EIO;
 			case 2:
 				if (sense[0] & 0x30) {
 					printk("xd%c: %s - ",'a'+drive,(operation == READ ? "reading" : "writing"));
@@ -439,7 +434,7 @@ static int xd_readwrite (u_char operation,XD_INFO *p,char *buffer,u_int block,u_
 				else
 					printk(" - no valid disk address\n");
 				spin_lock_irq(&xd_lock);
-				return (0);
+				return -EIO;
 		}
 		if (xd_dma_buffer)
 			for (i=0; i < (temp * 0x200); i++)
@@ -448,7 +443,7 @@ static int xd_readwrite (u_char operation,XD_INFO *p,char *buffer,u_int block,u_
 		count -= temp, buffer += temp * 0x200, block += temp;
 	}
 	spin_lock_irq(&xd_lock);
-	return (1);
+	return 0;
 }
 
 /* xd_recalibrate: recalibrate a given drive and reset controller if necessary */

drivers/block/xen-blkfront.c

@@ -122,7 +122,7 @@ static DEFINE_SPINLOCK(blkif_io_lock);
 static int get_id_from_freelist(struct blkfront_info *info)
 {
 	unsigned long free = info->shadow_free;
-	BUG_ON(free > BLK_RING_SIZE);
+	BUG_ON(free >= BLK_RING_SIZE);
 	info->shadow_free = info->shadow[free].req.id;
 	info->shadow[free].req.id = 0x0fffffee; /* debug */
 	return free;
@@ -231,7 +231,7 @@ static int blkif_queue_request(struct request *req)
 	info->shadow[id].request = (unsigned long)req;
 
 	ring_req->id = id;
-	ring_req->sector_number = (blkif_sector_t)req->sector;
+	ring_req->sector_number = (blkif_sector_t)blk_rq_pos(req);
 	ring_req->handle = info->handle;
 
 	ring_req->operation = rq_data_dir(req) ?
@@ -299,25 +299,25 @@ static void do_blkif_request(struct request_queue *rq)
 
 	queued = 0;
 
-	while ((req = elv_next_request(rq)) != NULL) {
+	while ((req = blk_peek_request(rq)) != NULL) {
 		info = req->rq_disk->private_data;
-		if (!blk_fs_request(req)) {
-			end_request(req, 0);
-			continue;
-		}
 
 		if (RING_FULL(&info->ring))
 			goto wait;
 
-		pr_debug("do_blk_req %p: cmd %p, sec %lx, "
-			 "(%u/%li) buffer:%p [%s]\n",
-			 req, req->cmd, (unsigned long)req->sector,
-			 req->current_nr_sectors,
-			 req->nr_sectors, req->buffer,
-			 rq_data_dir(req) ? "write" : "read");
+		blk_start_request(req);
 
+		if (!blk_fs_request(req)) {
+			__blk_end_request_all(req, -EIO);
+			continue;
+		}
+
+		pr_debug("do_blk_req %p: cmd %p, sec %lx, "
+			 "(%u/%u) buffer:%p [%s]\n",
+			 req, req->cmd, (unsigned long)blk_rq_pos(req),
+			 blk_rq_cur_sectors(req), blk_rq_sectors(req),
+			 req->buffer, rq_data_dir(req) ? "write" : "read");
 
-		blkdev_dequeue_request(req);
 		if (blkif_queue_request(req)) {
 			blk_requeue_request(rq, req);
 wait:
@@ -344,7 +344,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
 	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
-	blk_queue_hardsect_size(rq, sector_size);
+	blk_queue_logical_block_size(rq, sector_size);
 	blk_queue_max_sectors(rq, 512);
 
 	/* Each segment in a request is up to an aligned page in size. */
@@ -551,7 +551,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 
 	for (i = info->ring.rsp_cons; i != rp; i++) {
 		unsigned long id;
-		int ret;
 
 		bret = RING_GET_RESPONSE(&info->ring, i);
 		id   = bret->id;
@@ -578,8 +577,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
 					"request: %x\n", bret->status);
 
-			ret = __blk_end_request(req, error, blk_rq_bytes(req));
-			BUG_ON(ret);
+			__blk_end_request_all(req, error);
 			break;
 		default:
 			BUG();

drivers/block/xsysace.c

@@ -463,10 +463,11 @@ struct request *ace_get_next_request(struct request_queue * q)
 {
 	struct request *req;
 
-	while ((req = elv_next_request(q)) != NULL) {
+	while ((req = blk_peek_request(q)) != NULL) {
 		if (blk_fs_request(req))
 			break;
-		end_request(req, 0);
+		blk_start_request(req);
+		__blk_end_request_all(req, -EIO);
 	}
 	return req;
 }
@@ -492,9 +493,13 @@ static void ace_fsm_dostate(struct ace_device *ace)
 		set_capacity(ace->gd, 0);
 		dev_info(ace->dev, "No CF in slot\n");
 
-		/* Drop all pending requests */
-		while ((req = elv_next_request(ace->queue)) != NULL)
-			end_request(req, 0);
+		/* Drop all in-flight and pending requests */
+		if (ace->req) {
+			__blk_end_request_all(ace->req, -EIO);
+			ace->req = NULL;
+		}
+		while ((req = blk_fetch_request(ace->queue)) != NULL)
+			__blk_end_request_all(req, -EIO);
 
 		/* Drop back to IDLE state and notify waiters */
 		ace->fsm_state = ACE_FSM_STATE_IDLE;
@@ -642,19 +647,21 @@ static void ace_fsm_dostate(struct ace_device *ace)
 			ace->fsm_state = ACE_FSM_STATE_IDLE;
 			break;
 		}
+		blk_start_request(req);
 
 		/* Okay, it's a data request, set it up for transfer */
 		dev_dbg(ace->dev,
-			"request: sec=%llx hcnt=%lx, ccnt=%x, dir=%i\n",
-			(unsigned long long) req->sector, req->hard_nr_sectors,
-			req->current_nr_sectors, rq_data_dir(req));
+			"request: sec=%llx hcnt=%x, ccnt=%x, dir=%i\n",
+			(unsigned long long)blk_rq_pos(req),
+			blk_rq_sectors(req), blk_rq_cur_sectors(req),
+			rq_data_dir(req));
 
 		ace->req = req;
 		ace->data_ptr = req->buffer;
-		ace->data_count = req->current_nr_sectors * ACE_BUF_PER_SECTOR;
-		ace_out32(ace, ACE_MPULBA, req->sector & 0x0FFFFFFF);
+		ace->data_count = blk_rq_cur_sectors(req) * ACE_BUF_PER_SECTOR;
+		ace_out32(ace, ACE_MPULBA, blk_rq_pos(req) & 0x0FFFFFFF);
 
-		count = req->hard_nr_sectors;
+		count = blk_rq_sectors(req);
 		if (rq_data_dir(req)) {
 			/* Kick off write request */
 			dev_dbg(ace->dev, "write data\n");
@@ -688,7 +695,7 @@ static void ace_fsm_dostate(struct ace_device *ace)
 			dev_dbg(ace->dev,
 				"CFBSY set; t=%i iter=%i c=%i dc=%i irq=%i\n",
 				ace->fsm_task, ace->fsm_iter_num,
-				ace->req->current_nr_sectors * 16,
+				blk_rq_cur_sectors(ace->req) * 16,
 				ace->data_count, ace->in_irq);
 			ace_fsm_yield(ace);	/* need to poll CFBSY bit */
 			break;
@@ -697,7 +704,7 @@ static void ace_fsm_dostate(struct ace_device *ace)
 			dev_dbg(ace->dev,
 				"DATABUF not set; t=%i iter=%i c=%i dc=%i irq=%i\n",
 				ace->fsm_task, ace->fsm_iter_num,
-				ace->req->current_nr_sectors * 16,
+				blk_rq_cur_sectors(ace->req) * 16,
 				ace->data_count, ace->in_irq);
 			ace_fsm_yieldirq(ace);
 			break;
@@ -717,14 +724,13 @@ static void ace_fsm_dostate(struct ace_device *ace)
 		}
 
 		/* bio finished; is there another one? */
-		if (__blk_end_request(ace->req, 0,
-					blk_rq_cur_bytes(ace->req))) {
-			/* dev_dbg(ace->dev, "next block; h=%li c=%i\n",
-			 *      ace->req->hard_nr_sectors,
-			 *      ace->req->current_nr_sectors);
+		if (__blk_end_request_cur(ace->req, 0)) {
+			/* dev_dbg(ace->dev, "next block; h=%u c=%u\n",
+			 *      blk_rq_sectors(ace->req),
+			 *      blk_rq_cur_sectors(ace->req));
 			 */
 			ace->data_ptr = ace->req->buffer;
-			ace->data_count = ace->req->current_nr_sectors * 16;
+			ace->data_count = blk_rq_cur_sectors(ace->req) * 16;
 			ace_fsm_yieldirq(ace);
 			break;
 		}
@@ -978,7 +984,7 @@ static int __devinit ace_setup(struct ace_device *ace)
 	ace->queue = blk_init_queue(ace_request, &ace->lock);
 	if (ace->queue == NULL)
 		goto err_blk_initq;
-	blk_queue_hardsect_size(ace->queue, 512);
+	blk_queue_logical_block_size(ace->queue, 512);
 
 	/*
 	 * Allocate and initialize GD structure

drivers/block/z2ram.c

@@ -70,15 +70,18 @@ static struct gendisk *z2ram_gendisk;
 static void do_z2_request(struct request_queue *q)
 {
 	struct request *req;
-	while ((req = elv_next_request(q)) != NULL) {
-		unsigned long start = req->sector << 9;
-		unsigned long len  = req->current_nr_sectors << 9;
+
+	req = blk_fetch_request(q);
+	while (req) {
+		unsigned long start = blk_rq_pos(req) << 9;
+		unsigned long len  = blk_rq_cur_bytes(req);
+		int err = 0;
 
 		if (start + len > z2ram_size) {
 			printk( KERN_ERR DEVICE_NAME ": bad access: block=%lu, count=%u\n",
-				req->sector, req->current_nr_sectors);
-			end_request(req, 0);
-			continue;
+				blk_rq_pos(req), blk_rq_cur_sectors(req));
+			err = -EIO;
+			goto done;
 		}
 		while (len) {
 			unsigned long addr = start & Z2RAM_CHUNKMASK;
@@ -93,7 +96,9 @@ static void do_z2_request(struct request_queue *q)
 			start += size;
 			len -= size;
 		}
-		end_request(req, 1);
+	done:
+		if (!__blk_end_request_cur(req, err))
+			req = blk_fetch_request(q);
 	}
 }
 

drivers/cdrom/cdrom.c

@@ -2101,8 +2101,8 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 		nr = nframes;
 		if (cdi->cdda_method == CDDA_BPC_SINGLE)
 			nr = 1;
-		if (nr * CD_FRAMESIZE_RAW > (q->max_sectors << 9))
-			nr = (q->max_sectors << 9) / CD_FRAMESIZE_RAW;
+		if (nr * CD_FRAMESIZE_RAW > (queue_max_sectors(q) << 9))
+			nr = (queue_max_sectors(q) << 9) / CD_FRAMESIZE_RAW;
 
 		len = nr * CD_FRAMESIZE_RAW;
 

drivers/cdrom/gdrom.c

@@ -584,8 +584,8 @@ static void gdrom_readdisk_dma(struct work_struct *work)
 	list_for_each_safe(elem, next, &gdrom_deferred) {
 		req = list_entry(elem, struct request, queuelist);
 		spin_unlock(&gdrom_lock);
-		block = req->sector/GD_TO_BLK + GD_SESSION_OFFSET;
-		block_cnt = req->nr_sectors/GD_TO_BLK;
+		block = blk_rq_pos(req)/GD_TO_BLK + GD_SESSION_OFFSET;
+		block_cnt = blk_rq_sectors(req)/GD_TO_BLK;
 		ctrl_outl(PHYSADDR(req->buffer), GDROM_DMA_STARTADDR_REG);
 		ctrl_outl(block_cnt * GDROM_HARD_SECTOR, GDROM_DMA_LENGTH_REG);
 		ctrl_outl(1, GDROM_DMA_DIRECTION_REG);
@@ -632,39 +632,35 @@ static void gdrom_readdisk_dma(struct work_struct *work)
 		* before handling ending the request */
 		spin_lock(&gdrom_lock);
 		list_del_init(&req->queuelist);
-		__blk_end_request(req, err, blk_rq_bytes(req));
+		__blk_end_request_all(req, err);
 	}
 	spin_unlock(&gdrom_lock);
 	kfree(read_command);
 }
 
-static void gdrom_request_handler_dma(struct request *req)
-{
-	/* dequeue, add to list of deferred work
-	* and then schedule workqueue */
-	blkdev_dequeue_request(req);
-	list_add_tail(&req->queuelist, &gdrom_deferred);
-	schedule_work(&work);
-}
-
 static void gdrom_request(struct request_queue *rq)
 {
 	struct request *req;
 
-	while ((req = elv_next_request(rq)) != NULL) {
+	while ((req = blk_fetch_request(rq)) != NULL) {
 		if (!blk_fs_request(req)) {
 			printk(KERN_DEBUG "GDROM: Non-fs request ignored\n");
-			end_request(req, 0);
+			__blk_end_request_all(req, -EIO);
+			continue;
 		}
 		if (rq_data_dir(req) != READ) {
 			printk(KERN_NOTICE "GDROM: Read only device -");
 			printk(" write request ignored\n");
-			end_request(req, 0);
+			__blk_end_request_all(req, -EIO);
+			continue;
 		}
-		if (req->nr_sectors)
-			gdrom_request_handler_dma(req);
-		else
-			end_request(req, 0);
+
+		/*
+		 * Add to list of deferred work and then schedule
+		 * workqueue.
+		 */
+		list_add_tail(&req->queuelist, &gdrom_deferred);
+		schedule_work(&work);
 	}
 }
 
@@ -743,7 +739,7 @@ static void __devinit probe_gdrom_setupdisk(void)
 
 static int __devinit probe_gdrom_setupqueue(void)
 {
-	blk_queue_hardsect_size(gd.gdrom_rq, GDROM_HARD_SECTOR);
+	blk_queue_logical_block_size(gd.gdrom_rq, GDROM_HARD_SECTOR);
 	/* using DMA so memory will need to be contiguous */
 	blk_queue_max_hw_segments(gd.gdrom_rq, 1);
 	/* set a large max size to get most from DMA */

drivers/cdrom/viocd.c

@@ -282,7 +282,7 @@ static int send_request(struct request *req)
 			viopath_targetinst(viopath_hostLp),
 			(u64)req, VIOVERSION << 16,
 			((u64)DEVICE_NR(diskinfo) << 48) | dmaaddr,
-			(u64)req->sector * 512, len, 0);
+			(u64)blk_rq_pos(req) * 512, len, 0);
 	if (hvrc != HvLpEvent_Rc_Good) {
 		printk(VIOCD_KERN_WARNING "hv error on op %d\n", (int)hvrc);
 		return -1;
@@ -291,36 +291,19 @@ static int send_request(struct request *req)
 	return 0;
 }
 
-static void viocd_end_request(struct request *req, int error)
-{
-	int nsectors = req->hard_nr_sectors;
-
-	/*
-	 * Make sure it's fully ended, and ensure that we process
-	 * at least one sector.
-	 */
-	if (blk_pc_request(req))
-		nsectors = (req->data_len + 511) >> 9;
-	if (!nsectors)
-		nsectors = 1;
-
-	if (__blk_end_request(req, error, nsectors << 9))
-		BUG();
-}
-
 static int rwreq;
 
 static void do_viocd_request(struct request_queue *q)
 {
 	struct request *req;
 
-	while ((rwreq == 0) && ((req = elv_next_request(q)) != NULL)) {
+	while ((rwreq == 0) && ((req = blk_fetch_request(q)) != NULL)) {
 		if (!blk_fs_request(req))
-			viocd_end_request(req, -EIO);
+			__blk_end_request_all(req, -EIO);
 		else if (send_request(req) < 0) {
 			printk(VIOCD_KERN_WARNING
 					"unable to send message to OS/400!");
-			viocd_end_request(req, -EIO);
+			__blk_end_request_all(req, -EIO);
 		} else
 			rwreq++;
 	}
@@ -486,8 +469,8 @@ static void vio_handle_cd_event(struct HvLpEvent *event)
 	case viocdopen:
 		if (event->xRc == 0) {
 			di = &viocd_diskinfo[bevent->disk];
-			blk_queue_hardsect_size(di->viocd_disk->queue,
-					bevent->block_size);
+			blk_queue_logical_block_size(di->viocd_disk->queue,
+						     bevent->block_size);
 			set_capacity(di->viocd_disk,
 					bevent->media_size *
 					bevent->block_size / 512);
@@ -531,9 +514,9 @@ return_complete:
 					"with rc %d:0x%04X: %s\n",
 					req, event->xRc,
 					bevent->sub_result, err->msg);
-			viocd_end_request(req, -EIO);
+			__blk_end_request_all(req, -EIO);
 		} else
-			viocd_end_request(req, 0);
+			__blk_end_request_all(req, 0);
 
 		/* restart handling of incoming requests */
 		spin_unlock_irqrestore(&viocd_reqlock, flags);

drivers/char/raw.c

@@ -71,7 +71,7 @@ static int raw_open(struct inode *inode, struct file *filp)
 	err = bd_claim(bdev, raw_open);
 	if (err)
 		goto out1;
-	err = set_blocksize(bdev, bdev_hardsect_size(bdev));
+	err = set_blocksize(bdev, bdev_logical_block_size(bdev));
 	if (err)
 		goto out2;
 	filp->f_flags |= O_DIRECT;

drivers/ide/ide-atapi.c

@@ -246,6 +246,7 @@ EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
  */
 void ide_retry_pc(ide_drive_t *drive)
 {
+	struct request *failed_rq = drive->hwif->rq;
 	struct request *sense_rq = &drive->sense_rq;
 	struct ide_atapi_pc *pc = &drive->request_sense_pc;
 
@@ -255,13 +256,22 @@ void ide_retry_pc(ide_drive_t *drive)
 	ide_init_pc(pc);
 	memcpy(pc->c, sense_rq->cmd, 12);
 	pc->buf = bio_data(sense_rq->bio);	/* pointer to mapped address */
-	pc->req_xfer = sense_rq->data_len;
+	pc->req_xfer = blk_rq_bytes(sense_rq);
 
 	if (drive->media == ide_tape)
 		set_bit(IDE_AFLAG_IGNORE_DSC, &drive->atapi_flags);
 
-	if (ide_queue_sense_rq(drive, pc))
-		ide_complete_rq(drive, -EIO, blk_rq_bytes(drive->hwif->rq));
+	/*
+	 * Push back the failed request and put request sense on top
+	 * of it.  The failed command will be retried after sense data
+	 * is acquired.
+	 */
+	blk_requeue_request(failed_rq->q, failed_rq);
+	drive->hwif->rq = NULL;
+	if (ide_queue_sense_rq(drive, pc)) {
+		blk_start_request(failed_rq);
+		ide_complete_rq(drive, -EIO, blk_rq_bytes(failed_rq));
+	}
 }
 EXPORT_SYMBOL_GPL(ide_retry_pc);
 
@@ -303,7 +313,7 @@ int ide_cd_get_xferlen(struct request *rq)
 		return 32768;
 	else if (blk_sense_request(rq) || blk_pc_request(rq) ||
 			 rq->cmd_type == REQ_TYPE_ATA_PC)
-		return rq->data_len;
+		return blk_rq_bytes(rq);
 	else
 		return 0;
 }
@@ -367,7 +377,6 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 	/* No more interrupts */
 	if ((stat & ATA_DRQ) == 0) {
 		int uptodate, error;
-		unsigned int done;
 
 		debug_log("Packet command completed, %d bytes transferred\n",
 			  pc->xferred);
@@ -431,7 +440,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 			error = uptodate ? 0 : -EIO;
 		}
 
-		ide_complete_rq(drive, error, done);
+		ide_complete_rq(drive, error, blk_rq_bytes(rq));
 		return ide_stopped;
 	}
 

drivers/ide/ide-cd.c

@@ -182,7 +182,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 				 (sense->information[2] <<  8) |
 				 (sense->information[3]);
 
-			if (drive->queue->hardsect_size == 2048)
+			if (queue_logical_block_size(drive->queue) == 2048)
 				/* device sector size is 2K */
 				sector <<= 2;
 
@@ -404,15 +404,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 
 end_request:
 	if (stat & ATA_ERR) {
-		struct request_queue *q = drive->queue;
-		unsigned long flags;
-
-		spin_lock_irqsave(q->queue_lock, flags);
-		blkdev_dequeue_request(rq);
-		spin_unlock_irqrestore(q->queue_lock, flags);
-
 		hwif->rq = NULL;
-
 		return ide_queue_sense_rq(drive, rq) ? 2 : 1;
 	} else
 		return 2;
@@ -518,7 +510,7 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		error = blk_execute_rq(drive->queue, info->disk, rq, 0);
 
 		if (buffer)
-			*bufflen = rq->data_len;
+			*bufflen = rq->resid_len;
 
 		flags = rq->cmd_flags;
 		blk_put_request(rq);
@@ -576,7 +568,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 	struct request *rq = hwif->rq;
 	ide_expiry_t *expiry = NULL;
 	int dma_error = 0, dma, thislen, uptodate = 0;
-	int write = (rq_data_dir(rq) == WRITE) ? 1 : 0, rc = 0, nsectors;
+	int write = (rq_data_dir(rq) == WRITE) ? 1 : 0, rc = 0;
 	int sense = blk_sense_request(rq);
 	unsigned int timeout;
 	u16 len;
@@ -706,13 +698,8 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 
 out_end:
 	if (blk_pc_request(rq) && rc == 0) {
-		unsigned int dlen = rq->data_len;
-
-		rq->data_len = 0;
-
-		if (blk_end_request(rq, 0, dlen))
-			BUG();
-
+		rq->resid_len = 0;
+		blk_end_request_all(rq, 0);
 		hwif->rq = NULL;
 	} else {
 		if (sense && uptodate)
@@ -730,21 +717,13 @@ out_end:
 			ide_cd_error_cmd(drive, cmd);
 
 		/* make sure it's fully ended */
-		if (blk_pc_request(rq))
-			nsectors = (rq->data_len + 511) >> 9;
-		else
-			nsectors = rq->hard_nr_sectors;
-
-		if (nsectors == 0)
-			nsectors = 1;
-
 		if (blk_fs_request(rq) == 0) {
-			rq->data_len -= (cmd->nbytes - cmd->nleft);
+			rq->resid_len -= cmd->nbytes - cmd->nleft;
 			if (uptodate == 0 && (cmd->tf_flags & IDE_TFLAG_WRITE))
-				rq->data_len += cmd->last_xfer_len;
+				rq->resid_len += cmd->last_xfer_len;
 		}
 
-		ide_complete_rq(drive, uptodate ? 0 : -EIO, nsectors << 9);
+		ide_complete_rq(drive, uptodate ? 0 : -EIO, blk_rq_bytes(rq));
 
 		if (sense && rc == 2)
 			ide_error(drive, "request sense failure", stat);
@@ -758,7 +737,7 @@ static ide_startstop_t cdrom_start_rw(ide_drive_t *drive, struct request *rq)
 	struct request_queue *q = drive->queue;
 	int write = rq_data_dir(rq) == WRITE;
 	unsigned short sectors_per_frame =
-		queue_hardsect_size(q) >> SECTOR_BITS;
+		queue_logical_block_size(q) >> SECTOR_BITS;
 
 	ide_debug_log(IDE_DBG_RQ, "rq->cmd[0]: 0x%x, rq->cmd_flags: 0x%x, "
 				  "secs_per_frame: %u",
@@ -777,8 +756,8 @@ static ide_startstop_t cdrom_start_rw(ide_drive_t *drive, struct request *rq)
 	}
 
 	/* fs requests *must* be hardware frame aligned */
-	if ((rq->nr_sectors & (sectors_per_frame - 1)) ||
-	    (rq->sector & (sectors_per_frame - 1)))
+	if ((blk_rq_sectors(rq) & (sectors_per_frame - 1)) ||
+	    (blk_rq_pos(rq) & (sectors_per_frame - 1)))
 		return ide_stopped;
 
 	/* use DMA, if possible */
@@ -821,7 +800,7 @@ static void cdrom_do_block_pc(ide_drive_t *drive, struct request *rq)
 		 */
 		alignment = queue_dma_alignment(q) | q->dma_pad_mask;
 		if ((unsigned long)buf & alignment
-		    || rq->data_len & q->dma_pad_mask
+		    || blk_rq_bytes(rq) & q->dma_pad_mask
 		    || object_is_on_stack(buf))
 			drive->dma = 0;
 	}
@@ -869,15 +848,14 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 
 	cmd.rq = rq;
 
-	if (blk_fs_request(rq) || rq->data_len) {
-		ide_init_sg_cmd(&cmd, blk_fs_request(rq) ? (rq->nr_sectors << 9)
-							 : rq->data_len);
+	if (blk_fs_request(rq) || blk_rq_bytes(rq)) {
+		ide_init_sg_cmd(&cmd, blk_rq_bytes(rq));
 		ide_map_sg(drive, &cmd);
 	}
 
 	return ide_issue_pc(drive, &cmd);
 out_end:
-	nsectors = rq->hard_nr_sectors;
+	nsectors = blk_rq_sectors(rq);
 
 	if (nsectors == 0)
 		nsectors = 1;
@@ -1043,8 +1021,8 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	/* save a private copy of the TOC capacity for error handling */
 	drive->probed_capacity = toc->capacity * sectors_per_frame;
 
-	blk_queue_hardsect_size(drive->queue,
-				sectors_per_frame << SECTOR_BITS);
+	blk_queue_logical_block_size(drive->queue,
+				     sectors_per_frame << SECTOR_BITS);
 
 	/* first read just the header, so we know how long the TOC is */
 	stat = cdrom_read_tocentry(drive, 0, 1, 0, (char *) &toc->hdr,
@@ -1360,9 +1338,9 @@ static int ide_cdrom_probe_capabilities(ide_drive_t *drive)
 /* standard prep_rq_fn that builds 10 byte cmds */
 static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
 {
-	int hard_sect = queue_hardsect_size(q);
-	long block = (long)rq->hard_sector / (hard_sect >> 9);
-	unsigned long blocks = rq->hard_nr_sectors / (hard_sect >> 9);
+	int hard_sect = queue_logical_block_size(q);
+	long block = (long)blk_rq_pos(rq) / (hard_sect >> 9);
+	unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9);
 
 	memset(rq->cmd, 0, BLK_MAX_CDB);
 
@@ -1565,7 +1543,7 @@ static int ide_cdrom_setup(ide_drive_t *drive)
 
 	nslots = ide_cdrom_probe_capabilities(drive);
 
-	blk_queue_hardsect_size(q, CD_FRAMESIZE);
+	blk_queue_logical_block_size(q, CD_FRAMESIZE);
 
 	if (ide_cdrom_register(drive, nslots)) {
 		printk(KERN_ERR PFX "%s: %s failed to register device with the"

drivers/ide/ide-disk.c

@@ -82,7 +82,7 @@ static ide_startstop_t __ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
 					sector_t block)
 {
 	ide_hwif_t *hwif	= drive->hwif;
-	u16 nsectors		= (u16)rq->nr_sectors;
+	u16 nsectors		= (u16)blk_rq_sectors(rq);
 	u8 lba48		= !!(drive->dev_flags & IDE_DFLAG_LBA48);
 	u8 dma			= !!(drive->dev_flags & IDE_DFLAG_USING_DMA);
 	struct ide_cmd		cmd;
@@ -90,7 +90,7 @@ static ide_startstop_t __ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
 	ide_startstop_t		rc;
 
 	if ((hwif->host_flags & IDE_HFLAG_NO_LBA48_DMA) && lba48 && dma) {
-		if (block + rq->nr_sectors > 1ULL << 28)
+		if (block + blk_rq_sectors(rq) > 1ULL << 28)
 			dma = 0;
 		else
 			lba48 = 0;
@@ -195,9 +195,9 @@ static ide_startstop_t ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
 
 	ledtrig_ide_activity();
 
-	pr_debug("%s: %sing: block=%llu, sectors=%lu, buffer=0x%08lx\n",
+	pr_debug("%s: %sing: block=%llu, sectors=%u, buffer=0x%08lx\n",
 		 drive->name, rq_data_dir(rq) == READ ? "read" : "writ",
-		 (unsigned long long)block, rq->nr_sectors,
+		 (unsigned long long)block, blk_rq_sectors(rq),
 		 (unsigned long)rq->buffer);
 
 	if (hwif->rw_disk)
@@ -639,7 +639,7 @@ static void ide_disk_setup(ide_drive_t *drive)
 	}
 
 	printk(KERN_INFO "%s: max request size: %dKiB\n", drive->name,
-		q->max_sectors / 2);
+	       queue_max_sectors(q) / 2);
 
 	if (ata_id_is_ssd(id))
 		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);

drivers/ide/ide-dma.c

@@ -103,7 +103,7 @@ ide_startstop_t ide_dma_intr(ide_drive_t *drive)
 				ide_finish_cmd(drive, cmd, stat);
 			else
 				ide_complete_rq(drive, 0,
-						cmd->rq->nr_sectors << 9);
+						blk_rq_sectors(cmd->rq) << 9);
 			return ide_stopped;
 		}
 		printk(KERN_ERR "%s: %s: bad DMA status (0x%02x)\n",

drivers/ide/ide-floppy.c

@@ -194,7 +194,7 @@ static void idefloppy_create_rw_cmd(ide_drive_t *drive,
 {
 	struct ide_disk_obj *floppy = drive->driver_data;
 	int block = sector / floppy->bs_factor;
-	int blocks = rq->nr_sectors / floppy->bs_factor;
+	int blocks = blk_rq_sectors(rq) / floppy->bs_factor;
 	int cmd = rq_data_dir(rq);
 
 	ide_debug_log(IDE_DBG_FUNC, "block: %d, blocks: %d", block, blocks);
@@ -220,14 +220,14 @@ static void idefloppy_blockpc_cmd(struct ide_disk_obj *floppy,
 	ide_init_pc(pc);
 	memcpy(pc->c, rq->cmd, sizeof(pc->c));
 	pc->rq = rq;
-	if (rq->data_len) {
+	if (blk_rq_bytes(rq)) {
 		pc->flags |= PC_FLAG_DMA_OK;
 		if (rq_data_dir(rq) == WRITE)
 			pc->flags |= PC_FLAG_WRITING;
 	}
 	/* pio will be performed by ide_pio_bytes() which handles sg fine */
 	pc->buf = NULL;
-	pc->req_xfer = pc->buf_size = rq->data_len;
+	pc->req_xfer = pc->buf_size = blk_rq_bytes(rq);
 }
 
 static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
@@ -259,8 +259,8 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 			goto out_end;
 	}
 	if (blk_fs_request(rq)) {
-		if (((long)rq->sector % floppy->bs_factor) ||
-		    (rq->nr_sectors % floppy->bs_factor)) {
+		if (((long)blk_rq_pos(rq) % floppy->bs_factor) ||
+		    (blk_rq_sectors(rq) % floppy->bs_factor)) {
 			printk(KERN_ERR PFX "%s: unsupported r/w rq size\n",
 				drive->name);
 			goto out_end;

drivers/ide/ide-io.c

@@ -116,9 +116,9 @@ void ide_complete_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat, u8 err)
 unsigned int ide_rq_bytes(struct request *rq)
 {
 	if (blk_pc_request(rq))
-		return rq->data_len;
+		return blk_rq_bytes(rq);
 	else
-		return rq->hard_cur_sectors << 9;
+		return blk_rq_cur_sectors(rq) << 9;
 }
 EXPORT_SYMBOL_GPL(ide_rq_bytes);
 
@@ -133,7 +133,7 @@ int ide_complete_rq(ide_drive_t *drive, int error, unsigned int nr_bytes)
 	 * and complete the whole request right now
 	 */
 	if (blk_noretry_request(rq) && error <= 0)
-		nr_bytes = rq->hard_nr_sectors << 9;
+		nr_bytes = blk_rq_sectors(rq) << 9;
 
 	rc = ide_end_rq(drive, rq, error, nr_bytes);
 	if (rc == 0)
@@ -279,7 +279,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
 
 	if (cmd) {
 		if (cmd->protocol == ATA_PROT_PIO) {
-			ide_init_sg_cmd(cmd, rq->nr_sectors << 9);
+			ide_init_sg_cmd(cmd, blk_rq_sectors(rq) << 9);
 			ide_map_sg(drive, cmd);
 		}
 
@@ -387,7 +387,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 
 		drv = *(struct ide_driver **)rq->rq_disk->private_data;
 
-		return drv->do_request(drive, rq, rq->sector);
+		return drv->do_request(drive, rq, blk_rq_pos(rq));
 	}
 	return do_special(drive);
 kill_rq:
@@ -487,10 +487,10 @@ void do_ide_request(struct request_queue *q)
 
 	if (!ide_lock_port(hwif)) {
 		ide_hwif_t *prev_port;
+
+		WARN_ON_ONCE(hwif->rq);
 repeat:
 		prev_port = hwif->host->cur_port;
-		hwif->rq = NULL;
-
 		if (drive->dev_flags & IDE_DFLAG_SLEEPING &&
 		    time_after(drive->sleep, jiffies)) {
 			ide_unlock_port(hwif);
@@ -519,7 +519,9 @@ repeat:
 		 * we know that the queue isn't empty, but this can happen
 		 * if the q->prep_rq_fn() decides to kill a request
 		 */
-		rq = elv_next_request(drive->queue);
+		if (!rq)
+			rq = blk_fetch_request(drive->queue);
+
 		spin_unlock_irq(q->queue_lock);
 		spin_lock_irq(&hwif->lock);
 
@@ -531,7 +533,7 @@ repeat:
 		/*
 		 * Sanity: don't accept a request that isn't a PM request
 		 * if we are currently power managed. This is very important as
-		 * blk_stop_queue() doesn't prevent the elv_next_request()
+		 * blk_stop_queue() doesn't prevent the blk_fetch_request()
 		 * above to return us whatever is in the queue. Since we call
 		 * ide_do_request() ourselves, we end up taking requests while
 		 * the queue is blocked...
@@ -555,8 +557,11 @@ repeat:
 		startstop = start_request(drive, rq);
 		spin_lock_irq(&hwif->lock);
 
-		if (startstop == ide_stopped)
+		if (startstop == ide_stopped) {
+			rq = hwif->rq;
+			hwif->rq = NULL;
 			goto repeat;
+		}
 	} else
 		goto plug_device;
 out:
@@ -572,18 +577,24 @@ plug_device:
 plug_device_2:
 	spin_lock_irq(q->queue_lock);
 
+	if (rq)
+		blk_requeue_request(q, rq);
 	if (!elv_queue_empty(q))
 		blk_plug_device(q);
 }
 
-static void ide_plug_device(ide_drive_t *drive)
+static void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq)
 {
 	struct request_queue *q = drive->queue;
 	unsigned long flags;
 
 	spin_lock_irqsave(q->queue_lock, flags);
+
+	if (rq)
+		blk_requeue_request(q, rq);
 	if (!elv_queue_empty(q))
 		blk_plug_device(q);
+
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
@@ -632,6 +643,7 @@ void ide_timer_expiry (unsigned long data)
 	unsigned long	flags;
 	int		wait = -1;
 	int		plug_device = 0;
+	struct request	*uninitialized_var(rq_in_flight);
 
 	spin_lock_irqsave(&hwif->lock, flags);
 
@@ -693,6 +705,8 @@ void ide_timer_expiry (unsigned long data)
 		spin_lock_irq(&hwif->lock);
 		enable_irq(hwif->irq);
 		if (startstop == ide_stopped && hwif->polling == 0) {
+			rq_in_flight = hwif->rq;
+			hwif->rq = NULL;
 			ide_unlock_port(hwif);
 			plug_device = 1;
 		}
@@ -701,7 +715,7 @@ void ide_timer_expiry (unsigned long data)
 
 	if (plug_device) {
 		ide_unlock_host(hwif->host);
-		ide_plug_device(drive);
+		ide_requeue_and_plug(drive, rq_in_flight);
 	}
 }
 
@@ -787,6 +801,7 @@ irqreturn_t ide_intr (int irq, void *dev_id)
 	ide_startstop_t startstop;
 	irqreturn_t irq_ret = IRQ_NONE;
 	int plug_device = 0;
+	struct request *uninitialized_var(rq_in_flight);
 
 	if (host->host_flags & IDE_HFLAG_SERIALIZE) {
 		if (hwif != host->cur_port)
@@ -866,6 +881,8 @@ irqreturn_t ide_intr (int irq, void *dev_id)
 	 */
 	if (startstop == ide_stopped && hwif->polling == 0) {
 		BUG_ON(hwif->handler);
+		rq_in_flight = hwif->rq;
+		hwif->rq = NULL;
 		ide_unlock_port(hwif);
 		plug_device = 1;
 	}
@@ -875,7 +892,7 @@ out:
 out_early:
 	if (plug_device) {
 		ide_unlock_host(hwif->host);
-		ide_plug_device(drive);
+		ide_requeue_and_plug(drive, rq_in_flight);
 	}
 
 	return irq_ret;

drivers/ide/ide-lib.c

@@ -96,7 +96,7 @@ static void ide_dump_ata_error(ide_drive_t *drive, u8 err)
 
 		if (rq)
 			printk(KERN_CONT ", sector=%llu",
-			       (unsigned long long)rq->sector);
+			       (unsigned long long)blk_rq_pos(rq));
 	}
 	printk(KERN_CONT "\n");
 }

drivers/ide/ide-tape.c

@@ -380,7 +380,7 @@ static int ide_tape_callback(ide_drive_t *drive, int dsc)
 		}
 
 		tape->first_frame += blocks;
-		rq->data_len -= blocks * tape->blk_size;
+		rq->resid_len -= blocks * tape->blk_size;
 
 		if (pc->error) {
 			uptodate = 0;
@@ -586,7 +586,7 @@ static void ide_tape_create_rw_cmd(idetape_tape_t *tape,
 				   struct ide_atapi_pc *pc, struct request *rq,
 				   u8 opcode)
 {
-	unsigned int length = rq->nr_sectors;
+	unsigned int length = blk_rq_sectors(rq);
 
 	ide_init_pc(pc);
 	put_unaligned(cpu_to_be32(length), (unsigned int *) &pc->c[1]);
@@ -617,8 +617,8 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 	struct ide_cmd cmd;
 	u8 stat;
 
-	debug_log(DBG_SENSE, "sector: %llu, nr_sectors: %lu\n",
-		  (unsigned long long)rq->sector, rq->nr_sectors);
+	debug_log(DBG_SENSE, "sector: %llu, nr_sectors: %u\n"
+		  (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq));
 
 	if (!(blk_special_request(rq) || blk_sense_request(rq))) {
 		/* We do not support buffer cache originated requests. */
@@ -892,7 +892,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	rq->cmd_type = REQ_TYPE_SPECIAL;
 	rq->cmd[13] = cmd;
 	rq->rq_disk = tape->disk;
-	rq->sector = tape->first_frame;
+	rq->__sector = tape->first_frame;
 
 	if (size) {
 		ret = blk_rq_map_kern(drive->queue, rq, tape->buf, size,
@@ -904,7 +904,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	blk_execute_rq(drive->queue, tape->disk, rq, 0);
 
 	/* calculate the number of transferred bytes and update buffer state */
-	size -= rq->data_len;
+	size -= rq->resid_len;
 	tape->cur = tape->buf;
 	if (cmd == REQ_IDETAPE_READ)
 		tape->valid = size;

drivers/ide/ide-taskfile.c

@@ -385,7 +385,7 @@ out_end:
 	if ((cmd->tf_flags & IDE_TFLAG_FS) == 0)
 		ide_finish_cmd(drive, cmd, stat);
 	else
-		ide_complete_rq(drive, 0, cmd->rq->nr_sectors << 9);
+		ide_complete_rq(drive, 0, blk_rq_sectors(cmd->rq) << 9);
 	return ide_stopped;
 out_err:
 	ide_error_cmd(drive, cmd);

drivers/ide/pdc202xx_old.c

@@ -177,7 +177,7 @@ static void pdc202xx_dma_start(ide_drive_t *drive)
 		u8 clock = inb(high_16 + 0x11);
 
 		outb(clock | (hwif->channel ? 0x08 : 0x02), high_16 + 0x11);
-		word_count = (rq->nr_sectors << 8);
+		word_count = (blk_rq_sectors(rq) << 8);
 		word_count = (rq_data_dir(rq) == READ) ?
 					word_count | 0x05000000 :
 					word_count | 0x06000000;

drivers/ide/tc86c001.c

@@ -112,7 +112,7 @@ static void tc86c001_dma_start(ide_drive_t *drive)
 	ide_hwif_t *hwif	= drive->hwif;
 	unsigned long sc_base	= hwif->config_data;
 	unsigned long twcr_port	= sc_base + (drive->dn ? 0x06 : 0x04);
-	unsigned long nsectors	= hwif->rq->nr_sectors;
+	unsigned long nsectors	= blk_rq_sectors(hwif->rq);
 
 	/*
 	 * We have to manually load the sector count and size into

drivers/ide/tx4939ide.c

@@ -307,7 +307,7 @@ static int tx4939ide_dma_setup(ide_drive_t *drive, struct ide_cmd *cmd)
 	tx4939ide_writew(SECTOR_SIZE / 2, base, drive->dn ?
 			 TX4939IDE_Xfer_Cnt_2 : TX4939IDE_Xfer_Cnt_1);
 
-	tx4939ide_writew(cmd->rq->nr_sectors, base, TX4939IDE_Sec_Cnt);
+	tx4939ide_writew(blk_rq_sectors(cmd->rq), base, TX4939IDE_Sec_Cnt);
 
 	return 0;
 }

drivers/md/bitmap.c

@@ -232,7 +232,7 @@ static struct page *read_sb_page(mddev_t *mddev, long offset,
 		target = rdev->sb_start + offset + index * (PAGE_SIZE/512);
 
 		if (sync_page_io(rdev->bdev, target,
-				 roundup(size, bdev_hardsect_size(rdev->bdev)),
+				 roundup(size, bdev_logical_block_size(rdev->bdev)),
 				 page, READ)) {
 			page->index = index;
 			attach_page_buffers(page, NULL); /* so that free_buffer will
@@ -287,7 +287,7 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 			int size = PAGE_SIZE;
 			if (page->index == bitmap->file_pages-1)
 				size = roundup(bitmap->last_page_size,
-					       bdev_hardsect_size(rdev->bdev));
+					       bdev_logical_block_size(rdev->bdev));
 			/* Just make sure we aren't corrupting data or
 			 * metadata
 			 */

drivers/md/dm-exception-store.c

@@ -178,7 +178,7 @@ static int set_chunk_size(struct dm_exception_store *store,
 	}
 
 	/* Validate the chunk size against the device block size */
-	if (chunk_size_ulong % (bdev_hardsect_size(store->cow->bdev) >> 9)) {
+	if (chunk_size_ulong % (bdev_logical_block_size(store->cow->bdev) >> 9)) {
 		*error = "Chunk size is not a multiple of device blocksize";
 		return -EINVAL;
 	}

drivers/md/dm-log.c

@@ -413,7 +413,8 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 		 * Buffer holds both header and bitset.
 		 */
 		buf_size = dm_round_up((LOG_OFFSET << SECTOR_SHIFT) +
-				       bitset_size, ti->limits.hardsect_size);
+				       bitset_size,
+				       ti->limits.logical_block_size);
 
 		if (buf_size > dev->bdev->bd_inode->i_size) {
 			DMWARN("log device %s too small: need %llu bytes",

drivers/md/dm-snap-persistent.c

@@ -282,7 +282,7 @@ static int read_header(struct pstore *ps, int *new_snapshot)
 	 */
 	if (!ps->store->chunk_size) {
 		ps->store->chunk_size = max(DM_CHUNK_SIZE_DEFAULT_SECTORS,
-		    bdev_hardsect_size(ps->store->cow->bdev) >> 9);
+		    bdev_logical_block_size(ps->store->cow->bdev) >> 9);
 		ps->store->chunk_mask = ps->store->chunk_size - 1;
 		ps->store->chunk_shift = ffs(ps->store->chunk_size) - 1;
 		chunk_size_supplied = 0;

drivers/md/dm-table.c

@@ -108,7 +108,8 @@ static void combine_restrictions_low(struct io_restrictions *lhs,
 	lhs->max_hw_segments =
 		min_not_zero(lhs->max_hw_segments, rhs->max_hw_segments);
 
-	lhs->hardsect_size = max(lhs->hardsect_size, rhs->hardsect_size);
+	lhs->logical_block_size = max(lhs->logical_block_size,
+				      rhs->logical_block_size);
 
 	lhs->max_segment_size =
 		min_not_zero(lhs->max_segment_size, rhs->max_segment_size);
@@ -509,7 +510,7 @@ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
 	 *        combine_restrictions_low()
 	 */
 	rs->max_sectors =
-		min_not_zero(rs->max_sectors, q->max_sectors);
+		min_not_zero(rs->max_sectors, queue_max_sectors(q));
 
 	/*
 	 * Check if merge fn is supported.
@@ -524,24 +525,25 @@ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
 
 	rs->max_phys_segments =
 		min_not_zero(rs->max_phys_segments,
-			     q->max_phys_segments);
+			     queue_max_phys_segments(q));
 
 	rs->max_hw_segments =
-		min_not_zero(rs->max_hw_segments, q->max_hw_segments);
+		min_not_zero(rs->max_hw_segments, queue_max_hw_segments(q));
 
-	rs->hardsect_size = max(rs->hardsect_size, q->hardsect_size);
+	rs->logical_block_size = max(rs->logical_block_size,
+				     queue_logical_block_size(q));
 
 	rs->max_segment_size =
-		min_not_zero(rs->max_segment_size, q->max_segment_size);
+		min_not_zero(rs->max_segment_size, queue_max_segment_size(q));
 
 	rs->max_hw_sectors =
-		min_not_zero(rs->max_hw_sectors, q->max_hw_sectors);
+		min_not_zero(rs->max_hw_sectors, queue_max_hw_sectors(q));
 
 	rs->seg_boundary_mask =
 		min_not_zero(rs->seg_boundary_mask,
-			     q->seg_boundary_mask);
+			     queue_segment_boundary(q));
 
-	rs->bounce_pfn = min_not_zero(rs->bounce_pfn, q->bounce_pfn);
+	rs->bounce_pfn = min_not_zero(rs->bounce_pfn, queue_bounce_pfn(q));
 
 	rs->no_cluster |= !test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
 }
@@ -683,8 +685,8 @@ static void check_for_valid_limits(struct io_restrictions *rs)
 		rs->max_phys_segments = MAX_PHYS_SEGMENTS;
 	if (!rs->max_hw_segments)
 		rs->max_hw_segments = MAX_HW_SEGMENTS;
-	if (!rs->hardsect_size)
-		rs->hardsect_size = 1 << SECTOR_SHIFT;
+	if (!rs->logical_block_size)
+		rs->logical_block_size = 1 << SECTOR_SHIFT;
 	if (!rs->max_segment_size)
 		rs->max_segment_size = MAX_SEGMENT_SIZE;
 	if (!rs->seg_boundary_mask)
@@ -912,13 +914,13 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q)
 	 * restrictions.
 	 */
 	blk_queue_max_sectors(q, t->limits.max_sectors);
-	q->max_phys_segments = t->limits.max_phys_segments;
-	q->max_hw_segments = t->limits.max_hw_segments;
-	q->hardsect_size = t->limits.hardsect_size;
-	q->max_segment_size = t->limits.max_segment_size;
-	q->max_hw_sectors = t->limits.max_hw_sectors;
-	q->seg_boundary_mask = t->limits.seg_boundary_mask;
-	q->bounce_pfn = t->limits.bounce_pfn;
+	blk_queue_max_phys_segments(q, t->limits.max_phys_segments);
+	blk_queue_max_hw_segments(q, t->limits.max_hw_segments);
+	blk_queue_logical_block_size(q, t->limits.logical_block_size);
+	blk_queue_max_segment_size(q, t->limits.max_segment_size);
+	blk_queue_max_hw_sectors(q, t->limits.max_hw_sectors);
+	blk_queue_segment_boundary(q, t->limits.seg_boundary_mask);
+	blk_queue_bounce_limit(q, t->limits.bounce_pfn);
 
 	if (t->limits.no_cluster)
 		queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);

drivers/md/linear.c

@@ -146,7 +146,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		 * a one page request is never in violation.
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->num_sectors = rdev->sectors;

drivers/md/md.c

@@ -1202,7 +1202,7 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 	atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read));
 
 	rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
-	bmask = queue_hardsect_size(rdev->bdev->bd_disk->queue)-1;
+	bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1;
 	if (rdev->sb_size & bmask)
 		rdev->sb_size = (rdev->sb_size | bmask) + 1;
 

drivers/md/multipath.c

@@ -303,7 +303,7 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 		 * merge_bvec_fn will be involved in multipath.)
 		 */
 			if (q->merge_bvec_fn &&
-			    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+			    queue_max_sectors(q) > (PAGE_SIZE>>9))
 				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			conf->working_disks++;
@@ -467,7 +467,7 @@ static int multipath_run (mddev_t *mddev)
 		 * violating it, not that we ever expect a device with
 		 * a merge_bvec_fn to be involved in multipath */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		if (!test_bit(Faulty, &rdev->flags))

drivers/md/raid0.c

@@ -144,7 +144,7 @@ static int create_strip_zones (mddev_t *mddev)
 		 */
 
 		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		if (!smallest || (rdev1->sectors < smallest->sectors))

drivers/md/raid1.c

@@ -1130,7 +1130,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 			 * a one page request is never in violation.
 			 */
 			if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-			    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+			    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			p->head_position = 0;
@@ -1996,7 +1996,7 @@ static int run(mddev_t *mddev)
 		 * a one page request is never in violation.
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->head_position = 0;

drivers/md/raid10.c

@@ -1158,8 +1158,8 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 			 * a one page request is never in violation.
 			 */
 			if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-			    mddev->queue->max_sectors > (PAGE_SIZE>>9))
-				mddev->queue->max_sectors = (PAGE_SIZE>>9);
+			    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
+				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
@@ -2145,8 +2145,8 @@ static int run(mddev_t *mddev)
 		 * a one page request is never in violation.
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
-			mddev->queue->max_sectors = (PAGE_SIZE>>9);
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
+			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->head_position = 0;
 	}

drivers/md/raid5.c

@@ -3463,10 +3463,10 @@ static int bio_fits_rdev(struct bio *bi)
 {
 	struct request_queue *q = bdev_get_queue(bi->bi_bdev);
 
-	if ((bi->bi_size>>9) > q->max_sectors)
+	if ((bi->bi_size>>9) > queue_max_sectors(q))
 		return 0;
 	blk_recount_segments(q, bi);
-	if (bi->bi_phys_segments > q->max_phys_segments)
+	if (bi->bi_phys_segments > queue_max_phys_segments(q))
 		return 0;
 
 	if (q->merge_bvec_fn)

drivers/memstick/core/mspro_block.c

@@ -672,15 +672,14 @@ try_again:
 					       msb->req_sg);
 
 		if (!msb->seg_count) {
-			chunk = __blk_end_request(msb->block_req, -ENOMEM,
-					blk_rq_cur_bytes(msb->block_req));
+			chunk = __blk_end_request_cur(msb->block_req, -ENOMEM);
 			continue;
 		}
 
-		t_sec = msb->block_req->sector << 9;
+		t_sec = blk_rq_pos(msb->block_req) << 9;
 		sector_div(t_sec, msb->page_size);
 
-		count = msb->block_req->nr_sectors << 9;
+		count = blk_rq_bytes(msb->block_req);
 		count /= msb->page_size;
 
 		param.system = msb->system;
@@ -705,8 +704,8 @@ try_again:
 		return 0;
 	}
 
-	dev_dbg(&card->dev, "elv_next\n");
-	msb->block_req = elv_next_request(msb->queue);
+	dev_dbg(&card->dev, "blk_fetch\n");
+	msb->block_req = blk_fetch_request(msb->queue);
 	if (!msb->block_req) {
 		dev_dbg(&card->dev, "issue end\n");
 		return -EAGAIN;
@@ -745,7 +744,7 @@ static int mspro_block_complete_req(struct memstick_dev *card, int error)
 					t_len *= msb->page_size;
 			}
 		} else
-			t_len = msb->block_req->nr_sectors << 9;
+			t_len = blk_rq_bytes(msb->block_req);
 
 		dev_dbg(&card->dev, "transferred %x (%d)\n", t_len, error);
 
@@ -825,8 +824,8 @@ static void mspro_block_submit_req(struct request_queue *q)
 		return;
 
 	if (msb->eject) {
-		while ((req = elv_next_request(q)) != NULL)
-			__blk_end_request(req, -ENODEV, blk_rq_bytes(req));
+		while ((req = blk_fetch_request(q)) != NULL)
+			__blk_end_request_all(req, -ENODEV);
 
 		return;
 	}
@@ -1243,7 +1242,7 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 
 	sprintf(msb->disk->disk_name, "mspblk%d", disk_id);
 
-	blk_queue_hardsect_size(msb->queue, msb->page_size);
+	blk_queue_logical_block_size(msb->queue, msb->page_size);
 
 	capacity = be16_to_cpu(sys_info->user_block_count);
 	capacity *= be16_to_cpu(sys_info->block_size);

drivers/message/fusion/mptsas.c

@@ -1277,8 +1277,8 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	/* do we need to support multiple segments? */
 	if (req->bio->bi_vcnt > 1 || rsp->bio->bi_vcnt > 1) {
 		printk(MYIOC_s_ERR_FMT "%s: multiple segments req %u %u, rsp %u %u\n",
-		    ioc->name, __func__, req->bio->bi_vcnt, req->data_len,
-		    rsp->bio->bi_vcnt, rsp->data_len);
+		    ioc->name, __func__, req->bio->bi_vcnt, blk_rq_bytes(req),
+		    rsp->bio->bi_vcnt, blk_rq_bytes(rsp));
 		return -EINVAL;
 	}
 
@@ -1295,7 +1295,7 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	smpreq = (SmpPassthroughRequest_t *)mf;
 	memset(smpreq, 0, sizeof(*smpreq));
 
-	smpreq->RequestDataLength = cpu_to_le16(req->data_len - 4);
+	smpreq->RequestDataLength = cpu_to_le16(blk_rq_bytes(req) - 4);
 	smpreq->Function = MPI_FUNCTION_SMP_PASSTHROUGH;
 
 	if (rphy)
@@ -1321,10 +1321,10 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 		       MPI_SGE_FLAGS_END_OF_BUFFER |
 		       MPI_SGE_FLAGS_DIRECTION |
 		       mpt_addr_size()) << MPI_SGE_FLAGS_SHIFT;
-	flagsLength |= (req->data_len - 4);
+	flagsLength |= (blk_rq_bytes(req) - 4);
 
 	dma_addr_out = pci_map_single(ioc->pcidev, bio_data(req->bio),
-				      req->data_len, PCI_DMA_BIDIRECTIONAL);
+				      blk_rq_bytes(req), PCI_DMA_BIDIRECTIONAL);
 	if (!dma_addr_out)
 		goto put_mf;
 	mpt_add_sge(psge, flagsLength, dma_addr_out);
@@ -1332,9 +1332,9 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 
 	/* response */
 	flagsLength = MPT_SGE_FLAGS_SSIMPLE_READ;
-	flagsLength |= rsp->data_len + 4;
+	flagsLength |= blk_rq_bytes(rsp) + 4;
 	dma_addr_in =  pci_map_single(ioc->pcidev, bio_data(rsp->bio),
-				      rsp->data_len, PCI_DMA_BIDIRECTIONAL);
+				      blk_rq_bytes(rsp), PCI_DMA_BIDIRECTIONAL);
 	if (!dma_addr_in)
 		goto unmap;
 	mpt_add_sge(psge, flagsLength, dma_addr_in);
@@ -1357,8 +1357,8 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 		smprep = (SmpPassthroughReply_t *)ioc->sas_mgmt.reply;
 		memcpy(req->sense, smprep, sizeof(*smprep));
 		req->sense_len = sizeof(*smprep);
-		req->data_len = 0;
-		rsp->data_len -= smprep->ResponseDataLength;
+		req->resid_len = 0;
+		rsp->resid_len -= smprep->ResponseDataLength;
 	} else {
 		printk(MYIOC_s_ERR_FMT "%s: smp passthru reply failed to be returned\n",
 		    ioc->name, __func__);
@@ -1366,10 +1366,10 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	}
 unmap:
 	if (dma_addr_out)
-		pci_unmap_single(ioc->pcidev, dma_addr_out, req->data_len,
+		pci_unmap_single(ioc->pcidev, dma_addr_out, blk_rq_bytes(req),
 				 PCI_DMA_BIDIRECTIONAL);
 	if (dma_addr_in)
-		pci_unmap_single(ioc->pcidev, dma_addr_in, rsp->data_len,
+		pci_unmap_single(ioc->pcidev, dma_addr_in, blk_rq_bytes(rsp),
 				 PCI_DMA_BIDIRECTIONAL);
 put_mf:
 	if (mf)

drivers/message/i2o/i2o_block.c

@@ -426,15 +426,9 @@ static void i2o_block_end_request(struct request *req, int error,
 	struct request_queue *q = req->q;
 	unsigned long flags;
 
-	if (blk_end_request(req, error, nr_bytes)) {
-		int leftover = (req->hard_nr_sectors << KERNEL_SECTOR_SHIFT);
-
-		if (blk_pc_request(req))
-			leftover = req->data_len;
-
+	if (blk_end_request(req, error, nr_bytes))
 		if (error)
-			blk_end_request(req, -EIO, leftover);
-	}
+			blk_end_request_all(req, -EIO);
 
 	spin_lock_irqsave(q->queue_lock, flags);
 
@@ -761,7 +755,7 @@ static int i2o_block_transfer(struct request *req)
 			break;
 
 		case CACHE_SMARTFETCH:
-			if (req->nr_sectors > 16)
+			if (blk_rq_sectors(req) > 16)
 				ctl_flags = 0x201F0008;
 			else
 				ctl_flags = 0x001F0000;
@@ -781,13 +775,13 @@ static int i2o_block_transfer(struct request *req)
 			ctl_flags = 0x001F0010;
 			break;
 		case CACHE_SMARTBACK:
-			if (req->nr_sectors > 16)
+			if (blk_rq_sectors(req) > 16)
 				ctl_flags = 0x001F0004;
 			else
 				ctl_flags = 0x001F0010;
 			break;
 		case CACHE_SMARTTHROUGH:
-			if (req->nr_sectors > 16)
+			if (blk_rq_sectors(req) > 16)
 				ctl_flags = 0x001F0004;
 			else
 				ctl_flags = 0x001F0010;
@@ -800,8 +794,9 @@ static int i2o_block_transfer(struct request *req)
 	if (c->adaptec) {
 		u8 cmd[10];
 		u32 scsi_flags;
-		u16 hwsec = queue_hardsect_size(req->q) >> KERNEL_SECTOR_SHIFT;
+		u16 hwsec;
 
+		hwsec = queue_logical_block_size(req->q) >> KERNEL_SECTOR_SHIFT;
 		memset(cmd, 0, 10);
 
 		sgl_offset = SGL_OFFSET_12;
@@ -827,22 +822,22 @@ static int i2o_block_transfer(struct request *req)
 
 		*mptr++ = cpu_to_le32(scsi_flags);
 
-		*((u32 *) & cmd[2]) = cpu_to_be32(req->sector * hwsec);
-		*((u16 *) & cmd[7]) = cpu_to_be16(req->nr_sectors * hwsec);
+		*((u32 *) & cmd[2]) = cpu_to_be32(blk_rq_pos(req) * hwsec);
+		*((u16 *) & cmd[7]) = cpu_to_be16(blk_rq_sectors(req) * hwsec);
 
 		memcpy(mptr, cmd, 10);
 		mptr += 4;
-		*mptr++ = cpu_to_le32(req->nr_sectors << KERNEL_SECTOR_SHIFT);
+		*mptr++ = cpu_to_le32(blk_rq_bytes(req));
 	} else
 #endif
 	{
 		msg->u.head[1] = cpu_to_le32(cmd | HOST_TID << 12 | tid);
 		*mptr++ = cpu_to_le32(ctl_flags);
-		*mptr++ = cpu_to_le32(req->nr_sectors << KERNEL_SECTOR_SHIFT);
+		*mptr++ = cpu_to_le32(blk_rq_bytes(req));
 		*mptr++ =
-		    cpu_to_le32((u32) (req->sector << KERNEL_SECTOR_SHIFT));
+		    cpu_to_le32((u32) (blk_rq_pos(req) << KERNEL_SECTOR_SHIFT));
 		*mptr++ =
-		    cpu_to_le32(req->sector >> (32 - KERNEL_SECTOR_SHIFT));
+		    cpu_to_le32(blk_rq_pos(req) >> (32 - KERNEL_SECTOR_SHIFT));
 	}
 
 	if (!i2o_block_sglist_alloc(c, ireq, &mptr)) {
@@ -883,7 +878,7 @@ static void i2o_block_request_fn(struct request_queue *q)
 	struct request *req;
 
 	while (!blk_queue_plugged(q)) {
-		req = elv_next_request(q);
+		req = blk_peek_request(q);
 		if (!req)
 			break;
 
@@ -896,7 +891,7 @@ static void i2o_block_request_fn(struct request_queue *q)
 
 			if (queue_depth < I2O_BLOCK_MAX_OPEN_REQUESTS) {
 				if (!i2o_block_transfer(req)) {
-					blkdev_dequeue_request(req);
+					blk_start_request(req);
 					continue;
 				} else
 					osm_info("transfer error\n");
@@ -922,8 +917,10 @@ static void i2o_block_request_fn(struct request_queue *q)
 				blk_stop_queue(q);
 				break;
 			}
-		} else
-			end_request(req, 0);
+		} else {
+			blk_start_request(req);
+			__blk_end_request_all(req, -EIO);
+		}
 	}
 };
 
@@ -1082,7 +1079,7 @@ static int i2o_block_probe(struct device *dev)
 	 */
 	if (!i2o_parm_field_get(i2o_dev, 0x0004, 1, &blocksize, 4) ||
 	    !i2o_parm_field_get(i2o_dev, 0x0000, 3, &blocksize, 4)) {
-		blk_queue_hardsect_size(queue, le32_to_cpu(blocksize));
+		blk_queue_logical_block_size(queue, le32_to_cpu(blocksize));
 	} else
 		osm_warn("unable to get blocksize of %s\n", gd->disk_name);
 

drivers/mmc/card/block.c

@@ -243,7 +243,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 		brq.mrq.cmd = &brq.cmd;
 		brq.mrq.data = &brq.data;
 
-		brq.cmd.arg = req->sector;
+		brq.cmd.arg = blk_rq_pos(req);
 		if (!mmc_card_blockaddr(card))
 			brq.cmd.arg <<= 9;
 		brq.cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC;
@@ -251,7 +251,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 		brq.stop.opcode = MMC_STOP_TRANSMISSION;
 		brq.stop.arg = 0;
 		brq.stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
-		brq.data.blocks = req->nr_sectors;
+		brq.data.blocks = blk_rq_sectors(req);
 
 		/*
 		 * The block layer doesn't support all sector count
@@ -301,7 +301,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 		 * Adjust the sg list so it is the same size as the
 		 * request.
 		 */
-		if (brq.data.blocks != req->nr_sectors) {
+		if (brq.data.blocks != blk_rq_sectors(req)) {
 			int i, data_size = brq.data.blocks << 9;
 			struct scatterlist *sg;
 
@@ -352,8 +352,8 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 			printk(KERN_ERR "%s: error %d transferring data,"
 			       " sector %u, nr %u, card status %#x\n",
 			       req->rq_disk->disk_name, brq.data.error,
-			       (unsigned)req->sector,
-			       (unsigned)req->nr_sectors, status);
+			       (unsigned)blk_rq_pos(req),
+			       (unsigned)blk_rq_sectors(req), status);
 		}
 
 		if (brq.stop.error) {
@@ -521,7 +521,7 @@ static struct mmc_blk_data *mmc_blk_alloc(struct mmc_card *card)
 
 	sprintf(md->disk->disk_name, "mmcblk%d", devidx);
 
-	blk_queue_hardsect_size(md->queue.queue, 512);
+	blk_queue_logical_block_size(md->queue.queue, 512);
 
 	if (!mmc_card_sd(card) && mmc_card_blockaddr(card)) {
 		/*

drivers/mmc/card/queue.c

@@ -55,7 +55,7 @@ static int mmc_queue_thread(void *d)
 		spin_lock_irq(q->queue_lock);
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (!blk_queue_plugged(q))
-			req = elv_next_request(q);
+			req = blk_fetch_request(q);
 		mq->req = req;
 		spin_unlock_irq(q->queue_lock);
 
@@ -88,16 +88,11 @@ static void mmc_request(struct request_queue *q)
 {
 	struct mmc_queue *mq = q->queuedata;
 	struct request *req;
-	int ret;
 
 	if (!mq) {
 		printk(KERN_ERR "MMC: killing requests for dead queue\n");
-		while ((req = elv_next_request(q)) != NULL) {
-			do {
-				ret = __blk_end_request(req, -EIO,
-							blk_rq_cur_bytes(req));
-			} while (ret);
-		}
+		while ((req = blk_fetch_request(q)) != NULL)
+			__blk_end_request_all(req, -EIO);
 		return;
 	}
 

drivers/mtd/mtd_blkdevs.c

@@ -47,40 +47,41 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 	unsigned long block, nsect;
 	char *buf;
 
-	block = req->sector << 9 >> tr->blkshift;
-	nsect = req->current_nr_sectors << 9 >> tr->blkshift;
+	block = blk_rq_pos(req) << 9 >> tr->blkshift;
+	nsect = blk_rq_cur_bytes(req) >> tr->blkshift;
 
 	buf = req->buffer;
 
 	if (req->cmd_type == REQ_TYPE_LINUX_BLOCK &&
 	    req->cmd[0] == REQ_LB_OP_DISCARD)
-		return !tr->discard(dev, block, nsect);
+		return tr->discard(dev, block, nsect);
 
 	if (!blk_fs_request(req))
-		return 0;
+		return -EIO;
 
-	if (req->sector + req->current_nr_sectors > get_capacity(req->rq_disk))
-		return 0;
+	if (blk_rq_pos(req) + blk_rq_cur_sectors(req) >
+	    get_capacity(req->rq_disk))
+		return -EIO;
 
 	switch(rq_data_dir(req)) {
 	case READ:
 		for (; nsect > 0; nsect--, block++, buf += tr->blksize)
 			if (tr->readsect(dev, block, buf))
-				return 0;
-		return 1;
+				return -EIO;
+		return 0;
 
 	case WRITE:
 		if (!tr->writesect)
-			return 0;
+			return -EIO;
 
 		for (; nsect > 0; nsect--, block++, buf += tr->blksize)
 			if (tr->writesect(dev, block, buf))
-				return 0;
-		return 1;
+				return -EIO;
+		return 0;
 
 	default:
 		printk(KERN_NOTICE "Unknown request %u\n", rq_data_dir(req));
-		return 0;
+		return -EIO;
 	}
 }
 
@@ -88,19 +89,18 @@ static int mtd_blktrans_thread(void *arg)
 {
 	struct mtd_blktrans_ops *tr = arg;
 	struct request_queue *rq = tr->blkcore_priv->rq;
+	struct request *req = NULL;
 
 	/* we might get involved when memory gets low, so use PF_MEMALLOC */
 	current->flags |= PF_MEMALLOC;
 
 	spin_lock_irq(rq->queue_lock);
+
 	while (!kthread_should_stop()) {
-		struct request *req;
 		struct mtd_blktrans_dev *dev;
-		int res = 0;
-
-		req = elv_next_request(rq);
+		int res;
 
-		if (!req) {
+		if (!req && !(req = blk_fetch_request(rq))) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			spin_unlock_irq(rq->queue_lock);
 			schedule();
@@ -119,8 +119,13 @@ static int mtd_blktrans_thread(void *arg)
 
 		spin_lock_irq(rq->queue_lock);
 
-		end_request(req, res);
+		if (!__blk_end_request_cur(req, res))
+			req = NULL;
 	}
+
+	if (req)
+		__blk_end_request_all(req, -EIO);
+
 	spin_unlock_irq(rq->queue_lock);
 
 	return 0;
@@ -373,7 +378,7 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr)
 	}
 
 	tr->blkcore_priv->rq->queuedata = tr;
-	blk_queue_hardsect_size(tr->blkcore_priv->rq, tr->blksize);
+	blk_queue_logical_block_size(tr->blkcore_priv->rq, tr->blksize);
 	if (tr->discard)
 		blk_queue_set_discard(tr->blkcore_priv->rq,
 				      blktrans_discard_request);

drivers/s390/block/dasd.c

@@ -603,7 +603,7 @@ static void dasd_profile_end(struct dasd_block *block,
 	if (dasd_profile_level != DASD_PROFILE_ON)
 		return;
 
-	sectors = req->nr_sectors;
+	sectors = blk_rq_sectors(req);
 	if (!cqr->buildclk || !cqr->startclk ||
 	    !cqr->stopclk || !cqr->endclk ||
 	    !sectors)
@@ -1613,15 +1613,6 @@ void dasd_block_clear_timer(struct dasd_block *block)
 	del_timer(&block->timer);
 }
 
-/*
- * posts the buffer_cache about a finalized request
- */
-static inline void dasd_end_request(struct request *req, int error)
-{
-	if (__blk_end_request(req, error, blk_rq_bytes(req)))
-		BUG();
-}
-
 /*
  * Process finished error recovery ccw.
  */
@@ -1665,18 +1656,14 @@ static void __dasd_process_request_queue(struct dasd_block *block)
 	if (basedev->state < DASD_STATE_READY)
 		return;
 	/* Now we try to fetch requests from the request queue */
-	while (!blk_queue_plugged(queue) &&
-	       elv_next_request(queue)) {
-
-		req = elv_next_request(queue);
-
+	while (!blk_queue_plugged(queue) && (req = blk_peek_request(queue))) {
 		if (basedev->features & DASD_FEATURE_READONLY &&
 		    rq_data_dir(req) == WRITE) {
 			DBF_DEV_EVENT(DBF_ERR, basedev,
 				      "Rejecting write request %p",
 				      req);
-			blkdev_dequeue_request(req);
-			dasd_end_request(req, -EIO);
+			blk_start_request(req);
+			__blk_end_request_all(req, -EIO);
 			continue;
 		}
 		cqr = basedev->discipline->build_cp(basedev, block, req);
@@ -1704,8 +1691,8 @@ static void __dasd_process_request_queue(struct dasd_block *block)
 				      "CCW creation failed (rc=%ld) "
 				      "on request %p",
 				      PTR_ERR(cqr), req);
-			blkdev_dequeue_request(req);
-			dasd_end_request(req, -EIO);
+			blk_start_request(req);
+			__blk_end_request_all(req, -EIO);
 			continue;
 		}
 		/*
@@ -1714,7 +1701,7 @@ static void __dasd_process_request_queue(struct dasd_block *block)
 		 */
 		cqr->callback_data = (void *) req;
 		cqr->status = DASD_CQR_FILLED;
-		blkdev_dequeue_request(req);
+		blk_start_request(req);
 		list_add_tail(&cqr->blocklist, &block->ccw_queue);
 		dasd_profile_start(block, cqr, req);
 	}
@@ -1731,7 +1718,7 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr)
 	status = cqr->block->base->discipline->free_cp(cqr, req);
 	if (status <= 0)
 		error = status ? status : -EIO;
-	dasd_end_request(req, error);
+	__blk_end_request_all(req, error);
 }
 
 /*
@@ -2003,7 +1990,7 @@ static void dasd_setup_queue(struct dasd_block *block)
 {
 	int max;
 
-	blk_queue_hardsect_size(block->request_queue, block->bp_block);
+	blk_queue_logical_block_size(block->request_queue, block->bp_block);
 	max = block->base->discipline->max_blocks << block->s2b_shift;
 	blk_queue_max_sectors(block->request_queue, max);
 	blk_queue_max_phys_segments(block->request_queue, -1L);
@@ -2038,10 +2025,8 @@ static void dasd_flush_request_queue(struct dasd_block *block)
 		return;
 
 	spin_lock_irq(&block->request_queue_lock);
-	while ((req = elv_next_request(block->request_queue))) {
-		blkdev_dequeue_request(req);
-		dasd_end_request(req, -EIO);
-	}
+	while ((req = blk_fetch_request(block->request_queue)))
+		__blk_end_request_all(req, -EIO);
 	spin_unlock_irq(&block->request_queue_lock);
 }
 

drivers/s390/block/dasd_diag.c

@@ -505,8 +505,9 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
 		return ERR_PTR(-EINVAL);
 	blksize = block->bp_block;
 	/* Calculate record id of first and last block. */
-	first_rec = req->sector >> block->s2b_shift;
-	last_rec = (req->sector + req->nr_sectors - 1) >> block->s2b_shift;
+	first_rec = blk_rq_pos(req) >> block->s2b_shift;
+	last_rec =
+		(blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift;
 	/* Check struct bio and count the number of blocks for the request. */
 	count = 0;
 	rq_for_each_segment(bv, req, iter) {

drivers/s390/block/dasd_eckd.c

@@ -2354,10 +2354,10 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev,
 	blksize = block->bp_block;
 	blk_per_trk = recs_per_track(&private->rdc_data, 0, blksize);
 	/* Calculate record id of first and last block. */
-	first_rec = first_trk = req->sector >> block->s2b_shift;
+	first_rec = first_trk = blk_rq_pos(req) >> block->s2b_shift;
 	first_offs = sector_div(first_trk, blk_per_trk);
 	last_rec = last_trk =
-		(req->sector + req->nr_sectors - 1) >> block->s2b_shift;
+		(blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift;
 	last_offs = sector_div(last_trk, blk_per_trk);
 	cdlspecial = (private->uses_cdl && first_rec < 2*blk_per_trk);
 
@@ -2420,7 +2420,7 @@ dasd_eckd_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 	private = (struct dasd_eckd_private *) cqr->block->base->private;
 	blksize = cqr->block->bp_block;
 	blk_per_trk = recs_per_track(&private->rdc_data, 0, blksize);
-	recid = req->sector >> cqr->block->s2b_shift;
+	recid = blk_rq_pos(req) >> cqr->block->s2b_shift;
 	ccw = cqr->cpaddr;
 	/* Skip over define extent & locate record. */
 	ccw++;

drivers/s390/block/dasd_fba.c

@@ -270,8 +270,9 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 		return ERR_PTR(-EINVAL);
 	blksize = block->bp_block;
 	/* Calculate record id of first and last block. */
-	first_rec = req->sector >> block->s2b_shift;
-	last_rec = (req->sector + req->nr_sectors - 1) >> block->s2b_shift;
+	first_rec = blk_rq_pos(req) >> block->s2b_shift;
+	last_rec =
+		(blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift;
 	/* Check struct bio and count the number of blocks for the request. */
 	count = 0;
 	cidaw = 0;
@@ -309,7 +310,7 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 	ccw = cqr->cpaddr;
 	/* First ccw is define extent. */
 	define_extent(ccw++, cqr->data, rq_data_dir(req),
-		      block->bp_block, req->sector, req->nr_sectors);
+		      block->bp_block, blk_rq_pos(req), blk_rq_sectors(req));
 	/* Build locate_record + read/write ccws. */
 	idaws = (unsigned long *) (cqr->data + sizeof(struct DE_fba_data));
 	LO_data = (struct LO_fba_data *) (idaws + cidaw);

drivers/s390/block/dcssblk.c

@@ -602,7 +602,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	dev_info->gd->private_data = dev_info;
 	dev_info->gd->driverfs_dev = &dev_info->dev;
 	blk_queue_make_request(dev_info->dcssblk_queue, dcssblk_make_request);
-	blk_queue_hardsect_size(dev_info->dcssblk_queue, 4096);
+	blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096);
 
 	seg_byte_size = (dev_info->end - dev_info->start + 1);
 	set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors

drivers/s390/block/xpram.c

@@ -343,7 +343,7 @@ static int __init xpram_setup_blkdev(void)
 			goto out;
 		}
 		blk_queue_make_request(xpram_queues[i], xpram_make_request);
-		blk_queue_hardsect_size(xpram_queues[i], 4096);
+		blk_queue_logical_block_size(xpram_queues[i], 4096);
 	}
 
 	/*