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

+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-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 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 
 
 	if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
-	    (rq->data_len & q->dma_pad_mask)) {
-		unsigned int pad_len = (q->dma_pad_mask & ~rq->data_len) + 1;
+	    (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 @@ static void redo_fd_request(void)
 		/* 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 @@ static void redo_fd_request(void)
 		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 @@ static void redo_fd_request(void)
 	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.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/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);