Merge branch 'for-2.6.26' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.26' of git://git.kernel.dk/linux-2.6-block:
  block: fix blk_register_queue() return value
  block: fix memory hotplug and bouncing in block layer
  block: replace remaining __FUNCTION__ occurrences
  Kconfig: clean up block/Kconfig help descriptions
  cciss: fix warning oops on rmmod of driver
  cciss: Fix race between disk-adding code and interrupt handler
  block: move the padding adjustment to blk_rq_map_sg
  block: add bio_copy_user_iov support to blk_rq_map_user_iov
  block: convert bio_copy_user to bio_copy_user_iov
  loop: manage partitions in disk image
  cdrom: use kmalloced buffers instead of buffers on stack
  cdrom: make unregister_cdrom() return void
  cdrom: use list_head for cdrom_device_info list
  cdrom: protect cdrom_device_info list by mutex
  cdrom: cleanup hardcoded error-code
  cdrom: remove ifdef CONFIG_SYSCTL

Documentation/cdrom/cdrom-standard.tex

@@ -777,7 +777,7 @@ Note that a driver must have one static structure, $<device>_dops$, while
 it may have as many structures $<device>_info$ as there are minor devices
 active. $Register_cdrom()$ builds a linked list from these. 
 
-\subsection{$Int\ unregister_cdrom(struct\ cdrom_device_info * cdi)$}
+\subsection{$Void\ unregister_cdrom(struct\ cdrom_device_info * cdi)$}
 
 Unregistering device $cdi$ with minor number $MINOR(cdi\to dev)$ removes
 the minor device from the list. If it was the last registered minor for

block/Kconfig

@@ -5,14 +5,18 @@ menuconfig BLOCK
        bool "Enable the block layer" if EMBEDDED
        default y
        help
-	 This permits the block layer to be removed from the kernel if it's not
-	 needed (on some embedded devices for example).  If this option is
-	 disabled, then blockdev files will become unusable and some
-	 filesystems (such as ext3) will become unavailable.
+	 Provide block layer support for the kernel.
 
-	 This option will also disable SCSI character devices and USB storage
-	 since they make use of various block layer definitions and
-	 facilities.
+	 Disable this option to remove the block layer support from the
+	 kernel. This may be useful for embedded devices.
+
+	 If this option is disabled:
+
+	   - block device files will become unusable
+	   - some filesystems (such as ext3) will become unavailable.
+
+	 Also, SCSI character devices and USB storage will be disabled since
+	 they make use of various block layer definitions and facilities.
 
 	 Say Y here unless you know you really don't want to mount disks and
 	 suchlike.
@@ -23,9 +27,20 @@ config LBD
 	bool "Support for Large Block Devices"
 	depends on !64BIT
 	help
-	  Say Y here if you want to attach large (bigger than 2TB) discs to
-	  your machine, or if you want to have a raid or loopback device
-	  bigger than 2TB.  Otherwise say N.
+	  Enable block devices of size 2TB and larger.
+
+	  This option is required to support the full capacity of large
+	  (2TB+) block devices, including RAID, disk, Network Block Device,
+	  Logical Volume Manager (LVM) and loopback.
+
+	  For example, RAID devices are frequently bigger than the capacity
+	  of the largest individual hard drive.
+
+	  This option is not required if you have individual disk drives
+	  which total 2TB+ and you are not aggregating the capacity into
+	  a large block device (e.g. using RAID or LVM).
+
+	  If unsure, say N.
 
 config BLK_DEV_IO_TRACE
 	bool "Support for tracing block io actions"
@@ -33,19 +48,21 @@ config BLK_DEV_IO_TRACE
 	select RELAY
 	select DEBUG_FS
 	help
-	  Say Y here, if you want to be able to trace the block layer actions
+	  Say Y here if you want to be able to trace the block layer actions
 	  on a given queue. Tracing allows you to see any traffic happening
-	  on a block device queue. For more information (and the user space
-	  support tools needed), fetch the blktrace app from:
+	  on a block device queue. For more information (and the userspace
+	  support tools needed), fetch the blktrace tools from:
 
 	  git://git.kernel.dk/blktrace.git
 
+	  If unsure, say N.
+
 config LSF
 	bool "Support for Large Single Files"
 	depends on !64BIT
 	help
-	  Say Y here if you want to be able to handle very large files (bigger
-	  than 2TB), otherwise say N.
+	  Say Y here if you want to be able to handle very large files (2TB
+	  and larger), otherwise say N.
 
 	  If unsure, say Y.
 
@@ -62,6 +79,8 @@ config BLK_DEV_BSG
 	  protocols (e.g. Task Management Functions and SMP in Serial
 	  Attached SCSI).
 
+	  If unsure, say N.
+
 endif # BLOCK
 
 config BLOCK_COMPAT

block/blk-map.c

@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <scsi/sg.h>		/* for struct sg_iovec */
 
 #include "blk.h"
 
@@ -140,25 +141,8 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 		ubuf += ret;
 	}
 
-	/*
-	 * __blk_rq_map_user() copies the buffers if starting address
-	 * or length isn't aligned to dma_pad_mask.  As the copied
-	 * buffer is always page aligned, we know that there's enough
-	 * room for padding.  Extend the last bio and update
-	 * rq->data_len accordingly.
-	 *
-	 * On unmap, bio_uncopy_user() will use unmodified
-	 * bio_map_data pointed to by bio->bi_private.
-	 */
-	if (len & q->dma_pad_mask) {
-		unsigned int pad_len = (q->dma_pad_mask & ~len) + 1;
-		struct bio *tail = rq->biotail;
-
-		tail->bi_io_vec[tail->bi_vcnt - 1].bv_len += pad_len;
-		tail->bi_size += pad_len;
-
-		rq->extra_len += pad_len;
-	}
+	if (!bio_flagged(bio, BIO_USER_MAPPED))
+		rq->cmd_flags |= REQ_COPY_USER;
 
 	rq->buffer = rq->data = NULL;
 	return 0;
@@ -194,15 +178,26 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			struct sg_iovec *iov, int iov_count, unsigned int len)
 {
 	struct bio *bio;
+	int i, read = rq_data_dir(rq) == READ;
+	int unaligned = 0;
 
 	if (!iov || iov_count <= 0)
 		return -EINVAL;
 
-	/* we don't allow misaligned data like bio_map_user() does.  If the
-	 * user is using sg, they're expected to know the alignment constraints
-	 * and respect them accordingly */
-	bio = bio_map_user_iov(q, NULL, iov, iov_count,
-				rq_data_dir(rq) == READ);
+	for (i = 0; i < iov_count; i++) {
+		unsigned long uaddr = (unsigned long)iov[i].iov_base;
+
+		if (uaddr & queue_dma_alignment(q)) {
+			unaligned = 1;
+			break;
+		}
+	}
+
+	if (unaligned || (q->dma_pad_mask & len))
+		bio = bio_copy_user_iov(q, iov, iov_count, read);
+	else
+		bio = bio_map_user_iov(q, NULL, iov, iov_count, read);
+
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
@@ -212,6 +207,9 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 		return -EINVAL;
 	}
 
+	if (!bio_flagged(bio, BIO_USER_MAPPED))
+		rq->cmd_flags |= REQ_COPY_USER;
+
 	bio_get(bio);
 	blk_rq_bio_prep(q, rq, bio);
 	rq->buffer = rq->data = NULL;

block/blk-merge.c

@@ -220,6 +220,15 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 		bvprv = bvec;
 	} /* segments in 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;
+
+		sg->length += pad_len;
+		rq->extra_len += pad_len;
+	}
+
 	if (q->dma_drain_size && q->dma_drain_needed(rq)) {
 		if (rq->cmd_flags & REQ_RW)
 			memset(q->dma_drain_buffer, 0, q->dma_drain_size);

block/blk-sysfs.c

@@ -276,9 +276,12 @@ int blk_register_queue(struct gendisk *disk)
 
 	struct request_queue *q = disk->queue;
 
-	if (!q || !q->request_fn)
+	if (WARN_ON(!q))
 		return -ENXIO;
 
+	if (!q->request_fn)
+		return 0;
+
 	ret = kobject_add(&q->kobj, kobject_get(&disk->dev.kobj),
 			  "%s", "queue");
 	if (ret < 0)
@@ -300,7 +303,10 @@ void blk_unregister_queue(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 
-	if (q && q->request_fn) {
+	if (WARN_ON(!q))
+		return;
+
+	if (q->request_fn) {
 		elv_unregister_queue(q);
 
 		kobject_uevent(&q->kobj, KOBJ_REMOVE);

drivers/block/cciss.c

@@ -1349,6 +1349,10 @@ static void cciss_update_drive_info(int ctlr, int drv_index)
 		spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
 		h->drv[drv_index].busy_configuring = 1;
 		spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
+
+		/* deregister_disk sets h->drv[drv_index].queue = NULL */
+		/* which keeps the interrupt handler from starting */
+		/* the queue. */
 		ret = deregister_disk(h->gendisk[drv_index],
 				      &h->drv[drv_index], 0);
 		h->drv[drv_index].busy_configuring = 0;
@@ -1419,6 +1423,10 @@ static void cciss_update_drive_info(int ctlr, int drv_index)
 		blk_queue_hardsect_size(disk->queue,
 					hba[ctlr]->drv[drv_index].block_size);
 
+		/* Make sure all queue data is written out before */
+		/* setting h->drv[drv_index].queue, as setting this */
+		/* allows the interrupt handler to start the queue */
+		wmb();
 		h->drv[drv_index].queue = disk->queue;
 		add_disk(disk);
 	}
@@ -3520,10 +3528,17 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 			continue;
 		blk_queue_hardsect_size(q, drv->block_size);
 		set_capacity(disk, drv->nr_blocks);
-		add_disk(disk);
 		j++;
 	} while (j <= hba[i]->highest_lun);
 
+	/* Make sure all queue data is written out before */
+	/* interrupt handler, triggered by add_disk,  */
+	/* is allowed to start them. */
+	wmb();
+
+	for (j = 0; j <= hba[i]->highest_lun; j++)
+		add_disk(hba[i]->gendisk[j]);
+
 	return 1;
 
       clean4:

drivers/block/cciss_scsi.c

@@ -1349,9 +1349,9 @@ cciss_unregister_scsi(int ctlr)
 	/* set scsi_host to NULL so our detect routine will 
 	   find us on register */
 	sa->scsi_host = NULL;
+	spin_unlock_irqrestore(CCISS_LOCK(ctlr), flags);
 	scsi_cmd_stack_free(ctlr);
 	kfree(sa);
-	spin_unlock_irqrestore(CCISS_LOCK(ctlr), flags);
 }
 
 static int 

drivers/block/loop.c

@@ -82,6 +82,9 @@
 static LIST_HEAD(loop_devices);
 static DEFINE_MUTEX(loop_devices_mutex);
 
+static int max_part;
+static int part_shift;
+
 /*
  * Transfer functions
  */
@@ -692,6 +695,8 @@ static int loop_change_fd(struct loop_device *lo, struct file *lo_file,
 		goto out_putf;
 
 	fput(old_file);
+	if (max_part > 0)
+		ioctl_by_bdev(bdev, BLKRRPART, 0);
 	return 0;
 
  out_putf:
@@ -819,6 +824,8 @@ static int loop_set_fd(struct loop_device *lo, struct file *lo_file,
 	}
 	lo->lo_state = Lo_bound;
 	wake_up_process(lo->lo_thread);
+	if (max_part > 0)
+		ioctl_by_bdev(bdev, BLKRRPART, 0);
 	return 0;
 
 out_clr:
@@ -919,6 +926,8 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
 	fput(filp);
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
+	if (max_part > 0)
+		ioctl_by_bdev(bdev, BLKRRPART, 0);
 	return 0;
 }
 
@@ -1360,6 +1369,8 @@ static struct block_device_operations lo_fops = {
 static int max_loop;
 module_param(max_loop, int, 0);
 MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
+module_param(max_part, int, 0);
+MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
 
@@ -1412,7 +1423,7 @@ static struct loop_device *loop_alloc(int i)
 	if (!lo->lo_queue)
 		goto out_free_dev;
 
-	disk = lo->lo_disk = alloc_disk(1);
+	disk = lo->lo_disk = alloc_disk(1 << part_shift);
 	if (!disk)
 		goto out_free_queue;
 
@@ -1422,7 +1433,7 @@ static struct loop_device *loop_alloc(int i)
 	init_waitqueue_head(&lo->lo_event);
 	spin_lock_init(&lo->lo_lock);
 	disk->major		= LOOP_MAJOR;
-	disk->first_minor	= i;
+	disk->first_minor	= i << part_shift;
 	disk->fops		= &lo_fops;
 	disk->private_data	= lo;
 	disk->queue		= lo->lo_queue;
@@ -1502,7 +1513,12 @@ static int __init loop_init(void)
 	 *     themselves and have kernel automatically instantiate actual
 	 *     device on-demand.
 	 */
-	if (max_loop > 1UL << MINORBITS)
+
+	part_shift = 0;
+	if (max_part > 0)
+		part_shift = fls(max_part);
+
+	if (max_loop > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
 
 	if (max_loop) {
@@ -1510,7 +1526,7 @@ static int __init loop_init(void)
 		range = max_loop;
 	} else {
 		nr = 8;
-		range = 1UL << MINORBITS;
+		range = 1UL << (MINORBITS - part_shift);
 	}
 
 	if (register_blkdev(LOOP_MAJOR, "loop"))
@@ -1549,7 +1565,7 @@ static void __exit loop_exit(void)
 	unsigned long range;
 	struct loop_device *lo, *next;
 
-	range = max_loop ? max_loop :  1UL << MINORBITS;
+	range = max_loop ? max_loop :  1UL << (MINORBITS - part_shift);
 
 	list_for_each_entry_safe(lo, next, &loop_devices, lo_list)
 		loop_del_one(lo);

drivers/block/sx8.c

@@ -79,9 +79,9 @@ MODULE_PARM_DESC(max_queue, "Maximum number of queued commands. (min==1, max==30
 
 /* note: prints function name for you */
 #ifdef CARM_DEBUG
-#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __FUNCTION__, ## args)
+#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args)
 #ifdef CARM_VERBOSE_DEBUG
-#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __FUNCTION__, ## args)
+#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args)
 #else
 #define VPRINTK(fmt, args...)
 #endif	/* CARM_VERBOSE_DEBUG */
@@ -96,7 +96,7 @@ MODULE_PARM_DESC(max_queue, "Maximum number of queued commands. (min==1, max==30
 #define assert(expr) \
         if(unlikely(!(expr))) {                                   \
         printk(KERN_ERR "Assertion failed! %s,%s,%s,line=%d\n", \
-        #expr,__FILE__,__FUNCTION__,__LINE__);          \
+	#expr, __FILE__, __func__, __LINE__);          \
         }
 #endif
 

drivers/cdrom/gdrom.c

@@ -827,7 +827,9 @@ static int __devexit remove_gdrom(struct platform_device *devptr)
 	del_gendisk(gd.disk);
 	if (gdrom_major)
 		unregister_blkdev(gdrom_major, GDROM_DEV_NAME);
-	return unregister_cdrom(gd.cd_info);
+	unregister_cdrom(gd.cd_info);
+
+	return 0;
 }
 
 static struct platform_driver gdrom_driver = {

drivers/cdrom/viocd.c

@@ -650,10 +650,7 @@ static int viocd_remove(struct vio_dev *vdev)
 {
 	struct disk_info *d = &viocd_diskinfo[vdev->unit_address];
 
-	if (unregister_cdrom(&d->viocd_info) != 0)
-		printk(VIOCD_KERN_WARNING
-				"Cannot unregister viocd CD-ROM %s!\n",
-				d->viocd_info.name);
+	unregister_cdrom(&d->viocd_info);
 	del_gendisk(d->viocd_disk);
 	blk_cleanup_queue(d->viocd_disk->queue);
 	put_disk(d->viocd_disk);

drivers/ide/ide-cd.c

@@ -2032,9 +2032,8 @@ static void ide_cd_release(struct kref *kref)
 
 	kfree(info->buffer);
 	kfree(info->toc);
-	if (devinfo->handle == drive && unregister_cdrom(devinfo))
-		printk(KERN_ERR "%s: %s failed to unregister device from the cdrom "
-				"driver.\n", __FUNCTION__, drive->name);
+	if (devinfo->handle == drive)
+		unregister_cdrom(devinfo);
 	drive->dsc_overlap = 0;
 	drive->driver_data = NULL;
 	blk_queue_prep_rq(drive->queue, NULL);

drivers/scsi/scsi.c

@@ -852,7 +852,7 @@ void scsi_finish_command(struct scsi_cmnd *cmd)
 				"Notifying upper driver of completion "
 				"(result %x)\n", cmd->result));
 
-	good_bytes = scsi_bufflen(cmd) + cmd->request->extra_len;
+	good_bytes = scsi_bufflen(cmd);
         if (cmd->request->cmd_type != REQ_TYPE_BLOCK_PC) {
 		drv = scsi_cmd_to_driver(cmd);
 		if (drv->done)

fs/bio.c

@@ -444,22 +444,27 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
 
 struct bio_map_data {
 	struct bio_vec *iovecs;
-	void __user *userptr;
+	int nr_sgvecs;
+	struct sg_iovec *sgvecs;
 };
 
-static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio)
+static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
+			     struct sg_iovec *iov, int iov_count)
 {
 	memcpy(bmd->iovecs, bio->bi_io_vec, sizeof(struct bio_vec) * bio->bi_vcnt);
+	memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
+	bmd->nr_sgvecs = iov_count;
 	bio->bi_private = bmd;
 }
 
 static void bio_free_map_data(struct bio_map_data *bmd)
 {
 	kfree(bmd->iovecs);
+	kfree(bmd->sgvecs);
 	kfree(bmd);
 }
 
-static struct bio_map_data *bio_alloc_map_data(int nr_segs)
+static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count)
 {
 	struct bio_map_data *bmd = kmalloc(sizeof(*bmd), GFP_KERNEL);
 
@@ -467,13 +472,71 @@ static struct bio_map_data *bio_alloc_map_data(int nr_segs)
 		return NULL;
 
 	bmd->iovecs = kmalloc(sizeof(struct bio_vec) * nr_segs, GFP_KERNEL);
-	if (bmd->iovecs)
+	if (!bmd->iovecs) {
+		kfree(bmd);
+		return NULL;
+	}
+
+	bmd->sgvecs = kmalloc(sizeof(struct sg_iovec) * iov_count, GFP_KERNEL);
+	if (bmd->sgvecs)
 		return bmd;
 
+	kfree(bmd->iovecs);
 	kfree(bmd);
 	return NULL;
 }
 
+static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
+			  int uncopy)
+{
+	int ret = 0, i;
+	struct bio_vec *bvec;
+	int iov_idx = 0;
+	unsigned int iov_off = 0;
+	int read = bio_data_dir(bio) == READ;
+
+	__bio_for_each_segment(bvec, bio, i, 0) {
+		char *bv_addr = page_address(bvec->bv_page);
+		unsigned int bv_len = bvec->bv_len;
+
+		while (bv_len && iov_idx < iov_count) {
+			unsigned int bytes;
+			char *iov_addr;
+
+			bytes = min_t(unsigned int,
+				      iov[iov_idx].iov_len - iov_off, bv_len);
+			iov_addr = iov[iov_idx].iov_base + iov_off;
+
+			if (!ret) {
+				if (!read && !uncopy)
+					ret = copy_from_user(bv_addr, iov_addr,
+							     bytes);
+				if (read && uncopy)
+					ret = copy_to_user(iov_addr, bv_addr,
+							   bytes);
+
+				if (ret)
+					ret = -EFAULT;
+			}
+
+			bv_len -= bytes;
+			bv_addr += bytes;
+			iov_addr += bytes;
+			iov_off += bytes;
+
+			if (iov[iov_idx].iov_len == iov_off) {
+				iov_idx++;
+				iov_off = 0;
+			}
+		}
+
+		if (uncopy)
+			__free_page(bvec->bv_page);
+	}
+
+	return ret;
+}
+
 /**
  *	bio_uncopy_user	-	finish previously mapped bio
  *	@bio: bio being terminated
@@ -484,55 +547,56 @@ static struct bio_map_data *bio_alloc_map_data(int nr_segs)
 int bio_uncopy_user(struct bio *bio)
 {
 	struct bio_map_data *bmd = bio->bi_private;
-	const int read = bio_data_dir(bio) == READ;
-	struct bio_vec *bvec;
-	int i, ret = 0;
-
-	__bio_for_each_segment(bvec, bio, i, 0) {
-		char *addr = page_address(bvec->bv_page);
-		unsigned int len = bmd->iovecs[i].bv_len;
+	int ret;
 
-		if (read && !ret && copy_to_user(bmd->userptr, addr, len))
-			ret = -EFAULT;
+	ret = __bio_copy_iov(bio, bmd->sgvecs, bmd->nr_sgvecs, 1);
 
-		__free_page(bvec->bv_page);
-		bmd->userptr += len;
-	}
 	bio_free_map_data(bmd);
 	bio_put(bio);
 	return ret;
 }
 
 /**
- *	bio_copy_user	-	copy user data to bio
+ *	bio_copy_user_iov	-	copy user data to bio
  *	@q: destination block queue
- *	@uaddr: start of user address
- *	@len: length in bytes
+ *	@iov:	the iovec.
+ *	@iov_count: number of elements in the iovec
  *	@write_to_vm: bool indicating writing to pages or not
  *
  *	Prepares and returns a bio for indirect user io, bouncing data
  *	to/from kernel pages as necessary. Must be paired with
  *	call bio_uncopy_user() on io completion.
  */
-struct bio *bio_copy_user(struct request_queue *q, unsigned long uaddr,
-			  unsigned int len, int write_to_vm)
+struct bio *bio_copy_user_iov(struct request_queue *q, struct sg_iovec *iov,
+			      int iov_count, int write_to_vm)
 {
-	unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	unsigned long start = uaddr >> PAGE_SHIFT;
 	struct bio_map_data *bmd;
 	struct bio_vec *bvec;
 	struct page *page;
 	struct bio *bio;
 	int i, ret;
+	int nr_pages = 0;
+	unsigned int len = 0;
+
+	for (i = 0; i < iov_count; i++) {
+		unsigned long uaddr;
+		unsigned long end;
+		unsigned long start;
 
-	bmd = bio_alloc_map_data(end - start);
+		uaddr = (unsigned long)iov[i].iov_base;
+		end = (uaddr + iov[i].iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		start = uaddr >> PAGE_SHIFT;
+
+		nr_pages += end - start;
+		len += iov[i].iov_len;
+	}
+
+	bmd = bio_alloc_map_data(nr_pages, iov_count);
 	if (!bmd)
 		return ERR_PTR(-ENOMEM);
 
-	bmd->userptr = (void __user *) uaddr;
-
 	ret = -ENOMEM;
-	bio = bio_alloc(GFP_KERNEL, end - start);
+	bio = bio_alloc(GFP_KERNEL, nr_pages);
 	if (!bio)
 		goto out_bmd;
 
@@ -564,22 +628,12 @@ struct bio *bio_copy_user(struct request_queue *q, unsigned long uaddr,
 	 * success
 	 */
 	if (!write_to_vm) {
-		char __user *p = (char __user *) uaddr;
-
-		/*
-		 * for a write, copy in data to kernel pages
-		 */
-		ret = -EFAULT;
-		bio_for_each_segment(bvec, bio, i) {
-			char *addr = page_address(bvec->bv_page);
-
-			if (copy_from_user(addr, p, bvec->bv_len))
+		ret = __bio_copy_iov(bio, iov, iov_count, 0);
+		if (ret)
 			goto cleanup;
-			p += bvec->bv_len;
-		}
 	}
 
-	bio_set_map_data(bmd, bio);
+	bio_set_map_data(bmd, bio, iov, iov_count);
 	return bio;
 cleanup:
 	bio_for_each_segment(bvec, bio, i)
@@ -591,6 +645,28 @@ struct bio *bio_copy_user(struct request_queue *q, unsigned long uaddr,
 	return ERR_PTR(ret);
 }
 
+/**
+ *	bio_copy_user	-	copy user data to bio
+ *	@q: destination block queue
+ *	@uaddr: start of user address
+ *	@len: length in bytes
+ *	@write_to_vm: bool indicating writing to pages or not
+ *
+ *	Prepares and returns a bio for indirect user io, bouncing data
+ *	to/from kernel pages as necessary. Must be paired with
+ *	call bio_uncopy_user() on io completion.
+ */
+struct bio *bio_copy_user(struct request_queue *q, unsigned long uaddr,
+			  unsigned int len, int write_to_vm)
+{
+	struct sg_iovec iov;
+
+	iov.iov_base = (void __user *)uaddr;
+	iov.iov_len = len;
+
+	return bio_copy_user_iov(q, &iov, 1, write_to_vm);
+}
+
 static struct bio *__bio_map_user_iov(struct request_queue *q,
 				      struct block_device *bdev,
 				      struct sg_iovec *iov, int iov_count,

include/linux/bio.h

@@ -327,6 +327,8 @@ extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 extern struct bio *bio_copy_user(struct request_queue *, unsigned long, unsigned int, int);
+extern struct bio *bio_copy_user_iov(struct request_queue *, struct sg_iovec *,
+				     int, int);
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
 

include/linux/blkdev.h

@@ -112,6 +112,7 @@ enum rq_flag_bits {
 	__REQ_RW_SYNC,		/* request is sync (O_DIRECT) */
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_RW_META,		/* metadata io request */
+	__REQ_COPY_USER,	/* contains copies of user pages */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -133,6 +134,7 @@ enum rq_flag_bits {
 #define REQ_RW_SYNC	(1 << __REQ_RW_SYNC)
 #define REQ_ALLOCED	(1 << __REQ_ALLOCED)
 #define REQ_RW_META	(1 << __REQ_RW_META)
+#define REQ_COPY_USER	(1 << __REQ_COPY_USER)
 
 #define BLK_MAX_CDB	16
 
@@ -533,8 +535,13 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn;
  * BLK_BOUNCE_ANY	: don't bounce anything
  * BLK_BOUNCE_ISA	: bounce pages above ISA DMA boundary
  */
+
+#if BITS_PER_LONG == 32
 #define BLK_BOUNCE_HIGH		((u64)blk_max_low_pfn << PAGE_SHIFT)
-#define BLK_BOUNCE_ANY		((u64)blk_max_pfn << PAGE_SHIFT)
+#else
+#define BLK_BOUNCE_HIGH		-1ULL
+#endif
+#define BLK_BOUNCE_ANY		(-1ULL)
 #define BLK_BOUNCE_ISA		(ISA_DMA_THRESHOLD)
 
 /*

include/linux/cdrom.h

@@ -910,6 +910,7 @@ struct mode_page_header {
 #ifdef __KERNEL__
 #include <linux/fs.h>		/* not really needed, later.. */
 #include <linux/device.h>
+#include <linux/list.h>
 
 struct packet_command
 {
@@ -934,7 +935,7 @@ struct packet_command
 /* Uniform cdrom data structures for cdrom.c */
 struct cdrom_device_info {
 	struct cdrom_device_ops  *ops;  /* link to device_ops */
-	struct cdrom_device_info *next; /* next device_info for this major */
+	struct list_head list;		/* linked list of all device_info */
 	struct gendisk *disk;		/* matching block layer disk */
 	void *handle;		        /* driver-dependent data */
 /* specifications */
@@ -994,7 +995,7 @@ extern int cdrom_ioctl(struct file *file, struct cdrom_device_info *cdi,
 extern int cdrom_media_changed(struct cdrom_device_info *);
 
 extern int register_cdrom(struct cdrom_device_info *cdi);
-extern int unregister_cdrom(struct cdrom_device_info *cdi);
+extern void unregister_cdrom(struct cdrom_device_info *cdi);
 
 typedef struct {
     int data;