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);
 	}
 }
@@ -264,15 +283,14 @@ 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);
 			if (mbox->err_notify)
 				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

@@ -451,31 +451,13 @@ 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. */
 /* Called without dev->lock held, and only in interrupt context. */
 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)"