X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=block%2Fgenhd.c;h=1a4916e01732b68ebb9af5ff2fd831c78057d910;hb=c1d4c41f2fdfe66dea957b76d005affba3e56b26;hp=5a8d3bf02f1715702fe94515339f1cdfbfd3d088;hpb=68eef3b4791572ecb70249c7fb145bb3742dd899;p=safe%2Fjmp%2Flinux-2.6

diff --git a/block/genhd.c b/block/genhd.c
index 5a8d3bf..1a4916e 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -2,24 +2,233 @@
  *  gendisk handling
  */
 
-#include <linux/config.h>
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/genhd.h>
+#include <linux/kdev_t.h>
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/kobj_map.h>
 #include <linux/buffer_head.h>
 #include <linux/mutex.h>
+#include <linux/idr.h>
 
-static struct subsystem block_subsys;
+#include "blk.h"
 
-static DEFINE_MUTEX(block_subsys_lock);
+static DEFINE_MUTEX(block_class_lock);
+#ifndef CONFIG_SYSFS_DEPRECATED
+struct kobject *block_depr;
+#endif
+
+/* for extended dynamic devt allocation, currently only one major is used */
+#define MAX_EXT_DEVT		(1 << MINORBITS)
+
+/* For extended devt allocation.  ext_devt_mutex prevents look up
+ * results from going away underneath its user.
+ */
+static DEFINE_MUTEX(ext_devt_mutex);
+static DEFINE_IDR(ext_devt_idr);
+
+static struct device_type disk_type;
+
+/**
+ * disk_get_part - get partition
+ * @disk: disk to look partition from
+ * @partno: partition number
+ *
+ * Look for partition @partno from @disk.  If found, increment
+ * reference count and return it.
+ *
+ * CONTEXT:
+ * Don't care.
+ *
+ * RETURNS:
+ * Pointer to the found partition on success, NULL if not found.
+ */
+struct hd_struct *disk_get_part(struct gendisk *disk, int partno)
+{
+	struct hd_struct *part = NULL;
+	struct disk_part_tbl *ptbl;
+
+	if (unlikely(partno < 0))
+		return NULL;
+
+	rcu_read_lock();
+
+	ptbl = rcu_dereference(disk->part_tbl);
+	if (likely(partno < ptbl->len)) {
+		part = rcu_dereference(ptbl->part[partno]);
+		if (part)
+			get_device(part_to_dev(part));
+	}
+
+	rcu_read_unlock();
+
+	return part;
+}
+EXPORT_SYMBOL_GPL(disk_get_part);
+
+/**
+ * disk_part_iter_init - initialize partition iterator
+ * @piter: iterator to initialize
+ * @disk: disk to iterate over
+ * @flags: DISK_PITER_* flags
+ *
+ * Initialize @piter so that it iterates over partitions of @disk.
+ *
+ * CONTEXT:
+ * Don't care.
+ */
+void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk,
+			  unsigned int flags)
+{
+	struct disk_part_tbl *ptbl;
+
+	rcu_read_lock();
+	ptbl = rcu_dereference(disk->part_tbl);
+
+	piter->disk = disk;
+	piter->part = NULL;
+
+	if (flags & DISK_PITER_REVERSE)
+		piter->idx = ptbl->len - 1;
+	else if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0))
+		piter->idx = 0;
+	else
+		piter->idx = 1;
+
+	piter->flags = flags;
+
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(disk_part_iter_init);
+
+/**
+ * disk_part_iter_next - proceed iterator to the next partition and return it
+ * @piter: iterator of interest
+ *
+ * Proceed @piter to the next partition and return it.
+ *
+ * CONTEXT:
+ * Don't care.
+ */
+struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
+{
+	struct disk_part_tbl *ptbl;
+	int inc, end;
+
+	/* put the last partition */
+	disk_put_part(piter->part);
+	piter->part = NULL;
+
+	/* get part_tbl */
+	rcu_read_lock();
+	ptbl = rcu_dereference(piter->disk->part_tbl);
+
+	/* determine iteration parameters */
+	if (piter->flags & DISK_PITER_REVERSE) {
+		inc = -1;
+		if (piter->flags & (DISK_PITER_INCL_PART0 |
+				    DISK_PITER_INCL_EMPTY_PART0))
+			end = -1;
+		else
+			end = 0;
+	} else {
+		inc = 1;
+		end = ptbl->len;
+	}
+
+	/* iterate to the next partition */
+	for (; piter->idx != end; piter->idx += inc) {
+		struct hd_struct *part;
+
+		part = rcu_dereference(ptbl->part[piter->idx]);
+		if (!part)
+			continue;
+		if (!part->nr_sects &&
+		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
+		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
+		      piter->idx == 0))
+			continue;
+
+		get_device(part_to_dev(part));
+		piter->part = part;
+		piter->idx += inc;
+		break;
+	}
+
+	rcu_read_unlock();
+
+	return piter->part;
+}
+EXPORT_SYMBOL_GPL(disk_part_iter_next);
+
+/**
+ * disk_part_iter_exit - finish up partition iteration
+ * @piter: iter of interest
+ *
+ * Called when iteration is over.  Cleans up @piter.
+ *
+ * CONTEXT:
+ * Don't care.
+ */
+void disk_part_iter_exit(struct disk_part_iter *piter)
+{
+	disk_put_part(piter->part);
+	piter->part = NULL;
+}
+EXPORT_SYMBOL_GPL(disk_part_iter_exit);
+
+static inline int sector_in_part(struct hd_struct *part, sector_t sector)
+{
+	return part->start_sect <= sector &&
+		sector < part->start_sect + part->nr_sects;
+}
+
+/**
+ * disk_map_sector_rcu - map sector to partition
+ * @disk: gendisk of interest
+ * @sector: sector to map
+ *
+ * Find out which partition @sector maps to on @disk.  This is
+ * primarily used for stats accounting.
+ *
+ * CONTEXT:
+ * RCU read locked.  The returned partition pointer is valid only
+ * while preemption is disabled.
+ *
+ * RETURNS:
+ * Found partition on success, part0 is returned if no partition matches
+ */
+struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
+{
+	struct disk_part_tbl *ptbl;
+	struct hd_struct *part;
+	int i;
+
+	ptbl = rcu_dereference(disk->part_tbl);
+
+	part = rcu_dereference(ptbl->last_lookup);
+	if (part && sector_in_part(part, sector))
+		return part;
+
+	for (i = 1; i < ptbl->len; i++) {
+		part = rcu_dereference(ptbl->part[i]);
+
+		if (part && sector_in_part(part, sector)) {
+			rcu_assign_pointer(ptbl->last_lookup, part);
+			return part;
+		}
+	}
+	return &disk->part0;
+}
+EXPORT_SYMBOL_GPL(disk_map_sector_rcu);
 
 /*
  * Can be deleted altogether. Later.
@@ -38,27 +247,41 @@ static inline int major_to_index(int major)
 }
 
 #ifdef CONFIG_PROC_FS
-
-void blkdev_show(struct seq_file *f, off_t offset)
+void blkdev_show(struct seq_file *seqf, off_t offset)
 {
 	struct blk_major_name *dp;
 
 	if (offset < BLKDEV_MAJOR_HASH_SIZE) {
-		mutex_lock(&block_subsys_lock);
+		mutex_lock(&block_class_lock);
 		for (dp = major_names[offset]; dp; dp = dp->next)
-			seq_printf(f, "%3d %s\n", dp->major, dp->name);
-		mutex_unlock(&block_subsys_lock);
+			seq_printf(seqf, "%3d %s\n", dp->major, dp->name);
+		mutex_unlock(&block_class_lock);
 	}
 }
-
 #endif /* CONFIG_PROC_FS */
 
+/**
+ * register_blkdev - register a new block device
+ *
+ * @major: the requested major device number [1..255]. If @major=0, try to
+ *         allocate any unused major number.
+ * @name: the name of the new block device as a zero terminated string
+ *
+ * The @name must be unique within the system.
+ *
+ * The return value depends on the @major input parameter.
+ *  - if a major device number was requested in range [1..255] then the
+ *    function returns zero on success, or a negative error code
+ *  - if any unused major number was requested with @major=0 parameter
+ *    then the return value is the allocated major number in range
+ *    [1..255] or a negative error code otherwise
+ */
 int register_blkdev(unsigned int major, const char *name)
 {
 	struct blk_major_name **n, *p;
 	int index, ret = 0;
 
-	mutex_lock(&block_subsys_lock);
+	mutex_lock(&block_class_lock);
 
 	/* temporary */
 	if (major == 0) {
@@ -103,68 +326,176 @@ int register_blkdev(unsigned int major, const char *name)
 		kfree(p);
 	}
 out:
-	mutex_unlock(&block_subsys_lock);
+	mutex_unlock(&block_class_lock);
 	return ret;
 }
 
 EXPORT_SYMBOL(register_blkdev);
 
-/* todo: make void - error printk here */
-int unregister_blkdev(unsigned int major, const char *name)
+void unregister_blkdev(unsigned int major, const char *name)
 {
 	struct blk_major_name **n;
 	struct blk_major_name *p = NULL;
 	int index = major_to_index(major);
-	int ret = 0;
 
-	mutex_lock(&block_subsys_lock);
+	mutex_lock(&block_class_lock);
 	for (n = &major_names[index]; *n; n = &(*n)->next)
 		if ((*n)->major == major)
 			break;
-	if (!*n || strcmp((*n)->name, name))
-		ret = -EINVAL;
-	else {
+	if (!*n || strcmp((*n)->name, name)) {
+		WARN_ON(1);
+	} else {
 		p = *n;
 		*n = p->next;
 	}
-	mutex_unlock(&block_subsys_lock);
+	mutex_unlock(&block_class_lock);
 	kfree(p);
-
-	return ret;
 }
 
 EXPORT_SYMBOL(unregister_blkdev);
 
 static struct kobj_map *bdev_map;
 
+/**
+ * blk_mangle_minor - scatter minor numbers apart
+ * @minor: minor number to mangle
+ *
+ * Scatter consecutively allocated @minor number apart if MANGLE_DEVT
+ * is enabled.  Mangling twice gives the original value.
+ *
+ * RETURNS:
+ * Mangled value.
+ *
+ * CONTEXT:
+ * Don't care.
+ */
+static int blk_mangle_minor(int minor)
+{
+#ifdef CONFIG_DEBUG_BLOCK_EXT_DEVT
+	int i;
+
+	for (i = 0; i < MINORBITS / 2; i++) {
+		int low = minor & (1 << i);
+		int high = minor & (1 << (MINORBITS - 1 - i));
+		int distance = MINORBITS - 1 - 2 * i;
+
+		minor ^= low | high;	/* clear both bits */
+		low <<= distance;	/* swap the positions */
+		high >>= distance;
+		minor |= low | high;	/* and set */
+	}
+#endif
+	return minor;
+}
+
+/**
+ * blk_alloc_devt - allocate a dev_t for a partition
+ * @part: partition to allocate dev_t for
+ * @devt: out parameter for resulting dev_t
+ *
+ * Allocate a dev_t for block device.
+ *
+ * RETURNS:
+ * 0 on success, allocated dev_t is returned in *@devt.  -errno on
+ * failure.
+ *
+ * CONTEXT:
+ * Might sleep.
+ */
+int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
+{
+	struct gendisk *disk = part_to_disk(part);
+	int idx, rc;
+
+	/* in consecutive minor range? */
+	if (part->partno < disk->minors) {
+		*devt = MKDEV(disk->major, disk->first_minor + part->partno);
+		return 0;
+	}
+
+	/* allocate ext devt */
+	do {
+		if (!idr_pre_get(&ext_devt_idr, GFP_KERNEL))
+			return -ENOMEM;
+		rc = idr_get_new(&ext_devt_idr, part, &idx);
+	} while (rc == -EAGAIN);
+
+	if (rc)
+		return rc;
+
+	if (idx > MAX_EXT_DEVT) {
+		idr_remove(&ext_devt_idr, idx);
+		return -EBUSY;
+	}
+
+	*devt = MKDEV(BLOCK_EXT_MAJOR, blk_mangle_minor(idx));
+	return 0;
+}
+
+/**
+ * blk_free_devt - free a dev_t
+ * @devt: dev_t to free
+ *
+ * Free @devt which was allocated using blk_alloc_devt().
+ *
+ * CONTEXT:
+ * Might sleep.
+ */
+void blk_free_devt(dev_t devt)
+{
+	might_sleep();
+
+	if (devt == MKDEV(0, 0))
+		return;
+
+	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
+		mutex_lock(&ext_devt_mutex);
+		idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
+		mutex_unlock(&ext_devt_mutex);
+	}
+}
+
+static char *bdevt_str(dev_t devt, char *buf)
+{
+	if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) {
+		char tbuf[BDEVT_SIZE];
+		snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt));
+		snprintf(buf, BDEVT_SIZE, "%-9s", tbuf);
+	} else
+		snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt));
+
+	return buf;
+}
+
 /*
  * Register device numbers dev..(dev+range-1)
  * range must be nonzero
  * The hash chain is sorted on range, so that subranges can override.
  */
-void blk_register_region(dev_t dev, unsigned long range, struct module *module,
+void blk_register_region(dev_t devt, unsigned long range, struct module *module,
 			 struct kobject *(*probe)(dev_t, int *, void *),
 			 int (*lock)(dev_t, void *), void *data)
 {
-	kobj_map(bdev_map, dev, range, module, probe, lock, data);
+	kobj_map(bdev_map, devt, range, module, probe, lock, data);
 }
 
 EXPORT_SYMBOL(blk_register_region);
 
-void blk_unregister_region(dev_t dev, unsigned long range)
+void blk_unregister_region(dev_t devt, unsigned long range)
 {
-	kobj_unmap(bdev_map, dev, range);
+	kobj_unmap(bdev_map, devt, range);
 }
 
 EXPORT_SYMBOL(blk_unregister_region);
 
-static struct kobject *exact_match(dev_t dev, int *part, void *data)
+static struct kobject *exact_match(dev_t devt, int *partno, void *data)
 {
 	struct gendisk *p = data;
-	return &p->kobj;
+
+	return &disk_to_dev(p)->kobj;
 }
 
-static int exact_lock(dev_t dev, void *data)
+static int exact_lock(dev_t devt, void *data)
 {
 	struct gendisk *p = data;
 
@@ -179,14 +510,47 @@ static int exact_lock(dev_t dev, void *data)
  *
  * This function registers the partitioning information in @disk
  * with the kernel.
+ *
+ * FIXME: error handling
  */
 void add_disk(struct gendisk *disk)
 {
+	struct backing_dev_info *bdi;
+	dev_t devt;
+	int retval;
+
+	/* minors == 0 indicates to use ext devt from part0 and should
+	 * be accompanied with EXT_DEVT flag.  Make sure all
+	 * parameters make sense.
+	 */
+	WARN_ON(disk->minors && !(disk->major || disk->first_minor));
+	WARN_ON(!disk->minors && !(disk->flags & GENHD_FL_EXT_DEVT));
+
 	disk->flags |= GENHD_FL_UP;
-	blk_register_region(MKDEV(disk->major, disk->first_minor),
-			    disk->minors, NULL, exact_match, exact_lock, disk);
+
+	retval = blk_alloc_devt(&disk->part0, &devt);
+	if (retval) {
+		WARN_ON(1);
+		return;
+	}
+	disk_to_dev(disk)->devt = devt;
+
+	/* ->major and ->first_minor aren't supposed to be
+	 * dereferenced from here on, but set them just in case.
+	 */
+	disk->major = MAJOR(devt);
+	disk->first_minor = MINOR(devt);
+
+	blk_register_region(disk_devt(disk), disk->minors, NULL,
+			    exact_match, exact_lock, disk);
 	register_disk(disk);
 	blk_register_queue(disk);
+
+	bdi = &disk->queue->backing_dev_info;
+	bdi_register_dev(bdi, disk_devt(disk));
+	retval = sysfs_create_link(&disk_to_dev(disk)->kobj, &bdi->dev->kobj,
+				   "bdi");
+	WARN_ON(retval);
 }
 
 EXPORT_SYMBOL(add_disk);
@@ -194,448 +558,611 @@ EXPORT_SYMBOL(del_gendisk);	/* in partitions/check.c */
 
 void unlink_gendisk(struct gendisk *disk)
 {
+	sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
+	bdi_unregister(&disk->queue->backing_dev_info);
 	blk_unregister_queue(disk);
-	blk_unregister_region(MKDEV(disk->major, disk->first_minor),
-			      disk->minors);
+	blk_unregister_region(disk_devt(disk), disk->minors);
 }
 
-#define to_disk(obj) container_of(obj,struct gendisk,kobj)
-
 /**
  * get_gendisk - get partitioning information for a given device
- * @dev: device to get partitioning information for
+ * @devt: device to get partitioning information for
+ * @partno: returned partition index
  *
  * This function gets the structure containing partitioning
- * information for the given device @dev.
+ * information for the given device @devt.
  */
-struct gendisk *get_gendisk(dev_t dev, int *part)
+struct gendisk *get_gendisk(dev_t devt, int *partno)
 {
-	struct kobject *kobj = kobj_lookup(bdev_map, dev, part);
-	return  kobj ? to_disk(kobj) : NULL;
+	struct gendisk *disk = NULL;
+
+	if (MAJOR(devt) != BLOCK_EXT_MAJOR) {
+		struct kobject *kobj;
+
+		kobj = kobj_lookup(bdev_map, devt, partno);
+		if (kobj)
+			disk = dev_to_disk(kobj_to_dev(kobj));
+	} else {
+		struct hd_struct *part;
+
+		mutex_lock(&ext_devt_mutex);
+		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
+		if (part && get_disk(part_to_disk(part))) {
+			*partno = part->partno;
+			disk = part_to_disk(part);
+		}
+		mutex_unlock(&ext_devt_mutex);
+	}
+
+	return disk;
+}
+
+/**
+ * bdget_disk - do bdget() by gendisk and partition number
+ * @disk: gendisk of interest
+ * @partno: partition number
+ *
+ * Find partition @partno from @disk, do bdget() on it.
+ *
+ * CONTEXT:
+ * Don't care.
+ *
+ * RETURNS:
+ * Resulting block_device on success, NULL on failure.
+ */
+struct block_device *bdget_disk(struct gendisk *disk, int partno)
+{
+	struct hd_struct *part;
+	struct block_device *bdev = NULL;
+
+	part = disk_get_part(disk, partno);
+	if (part)
+		bdev = bdget(part_devt(part));
+	disk_put_part(part);
+
+	return bdev;
+}
+EXPORT_SYMBOL(bdget_disk);
+
+/*
+ * print a full list of all partitions - intended for places where the root
+ * filesystem can't be mounted and thus to give the victim some idea of what
+ * went wrong
+ */
+void __init printk_all_partitions(void)
+{
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
+	while ((dev = class_dev_iter_next(&iter))) {
+		struct gendisk *disk = dev_to_disk(dev);
+		struct disk_part_iter piter;
+		struct hd_struct *part;
+		char name_buf[BDEVNAME_SIZE];
+		char devt_buf[BDEVT_SIZE];
+
+		/*
+		 * Don't show empty devices or things that have been
+		 * surpressed
+		 */
+		if (get_capacity(disk) == 0 ||
+		    (disk->flags & GENHD_FL_SUPPRESS_PARTITION_INFO))
+			continue;
+
+		/*
+		 * Note, unlike /proc/partitions, I am showing the
+		 * numbers in hex - the same format as the root=
+		 * option takes.
+		 */
+		disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
+		while ((part = disk_part_iter_next(&piter))) {
+			bool is_part0 = part == &disk->part0;
+
+			printk("%s%s %10llu %s", is_part0 ? "" : "  ",
+			       bdevt_str(part_devt(part), devt_buf),
+			       (unsigned long long)part->nr_sects >> 1,
+			       disk_name(disk, part->partno, name_buf));
+			if (is_part0) {
+				if (disk->driverfs_dev != NULL &&
+				    disk->driverfs_dev->driver != NULL)
+					printk(" driver: %s\n",
+					      disk->driverfs_dev->driver->name);
+				else
+					printk(" (driver?)\n");
+			} else
+				printk("\n");
+		}
+		disk_part_iter_exit(&piter);
+	}
+	class_dev_iter_exit(&iter);
 }
 
 #ifdef CONFIG_PROC_FS
 /* iterator */
-static void *part_start(struct seq_file *part, loff_t *pos)
+static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos)
 {
-	struct list_head *p;
-	loff_t l = *pos;
+	loff_t skip = *pos;
+	struct class_dev_iter *iter;
+	struct device *dev;
+
+	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+	if (!iter)
+		return ERR_PTR(-ENOMEM);
+
+	seqf->private = iter;
+	class_dev_iter_init(iter, &block_class, NULL, &disk_type);
+	do {
+		dev = class_dev_iter_next(iter);
+		if (!dev)
+			return NULL;
+	} while (skip--);
+
+	return dev_to_disk(dev);
+}
+
+static void *disk_seqf_next(struct seq_file *seqf, void *v, loff_t *pos)
+{
+	struct device *dev;
+
+	(*pos)++;
+	dev = class_dev_iter_next(seqf->private);
+	if (dev)
+		return dev_to_disk(dev);
 
-	mutex_lock(&block_subsys_lock);
-	list_for_each(p, &block_subsys.kset.list)
-		if (!l--)
-			return list_entry(p, struct gendisk, kobj.entry);
 	return NULL;
 }
 
-static void *part_next(struct seq_file *part, void *v, loff_t *pos)
+static void disk_seqf_stop(struct seq_file *seqf, void *v)
 {
-	struct list_head *p = ((struct gendisk *)v)->kobj.entry.next;
-	++*pos;
-	return p==&block_subsys.kset.list ? NULL : 
-		list_entry(p, struct gendisk, kobj.entry);
+	struct class_dev_iter *iter = seqf->private;
+
+	/* stop is called even after start failed :-( */
+	if (iter) {
+		class_dev_iter_exit(iter);
+		kfree(iter);
+	}
 }
 
-static void part_stop(struct seq_file *part, void *v)
+static void *show_partition_start(struct seq_file *seqf, loff_t *pos)
 {
-	mutex_unlock(&block_subsys_lock);
+	static void *p;
+
+	p = disk_seqf_start(seqf, pos);
+	if (!IS_ERR(p) && p && !*pos)
+		seq_puts(seqf, "major minor  #blocks  name\n\n");
+	return p;
 }
 
-static int show_partition(struct seq_file *part, void *v)
+static int show_partition(struct seq_file *seqf, void *v)
 {
 	struct gendisk *sgp = v;
-	int n;
+	struct disk_part_iter piter;
+	struct hd_struct *part;
 	char buf[BDEVNAME_SIZE];
 
-	if (&sgp->kobj.entry == block_subsys.kset.list.next)
-		seq_puts(part, "major minor  #blocks  name\n\n");
-
 	/* Don't show non-partitionable removeable devices or empty devices */
-	if (!get_capacity(sgp) ||
-			(sgp->minors == 1 && (sgp->flags & GENHD_FL_REMOVABLE)))
+	if (!get_capacity(sgp) || (!disk_partitionable(sgp) &&
+				   (sgp->flags & GENHD_FL_REMOVABLE)))
 		return 0;
 	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
 		return 0;
 
 	/* show the full disk and all non-0 size partitions of it */
-	seq_printf(part, "%4d  %4d %10llu %s\n",
-		sgp->major, sgp->first_minor,
-		(unsigned long long)get_capacity(sgp) >> 1,
-		disk_name(sgp, 0, buf));
-	for (n = 0; n < sgp->minors - 1; n++) {
-		if (!sgp->part[n])
-			continue;
-		if (sgp->part[n]->nr_sects == 0)
-			continue;
-		seq_printf(part, "%4d  %4d %10llu %s\n",
-			sgp->major, n + 1 + sgp->first_minor,
-			(unsigned long long)sgp->part[n]->nr_sects >> 1 ,
-			disk_name(sgp, n + 1, buf));
-	}
+	disk_part_iter_init(&piter, sgp, DISK_PITER_INCL_PART0);
+	while ((part = disk_part_iter_next(&piter)))
+		seq_printf(seqf, "%4d  %7d %10llu %s\n",
+			   MAJOR(part_devt(part)), MINOR(part_devt(part)),
+			   (unsigned long long)part->nr_sects >> 1,
+			   disk_name(sgp, part->partno, buf));
+	disk_part_iter_exit(&piter);
 
 	return 0;
 }
 
-struct seq_operations partitions_op = {
-	.start =part_start,
-	.next =	part_next,
-	.stop =	part_stop,
-	.show =	show_partition
+static const struct seq_operations partitions_op = {
+	.start	= show_partition_start,
+	.next	= disk_seqf_next,
+	.stop	= disk_seqf_stop,
+	.show	= show_partition
 };
-#endif
 
+static int partitions_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &partitions_op);
+}
+
+static const struct file_operations proc_partitions_operations = {
+	.open		= partitions_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+#endif
 
-extern int blk_dev_init(void);
 
-static struct kobject *base_probe(dev_t dev, int *part, void *data)
+static struct kobject *base_probe(dev_t devt, int *partno, void *data)
 {
-	if (request_module("block-major-%d-%d", MAJOR(dev), MINOR(dev)) > 0)
+	if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0)
 		/* Make old-style 2.4 aliases work */
-		request_module("block-major-%d", MAJOR(dev));
+		request_module("block-major-%d", MAJOR(devt));
 	return NULL;
 }
 
 static int __init genhd_device_init(void)
 {
-	bdev_map = kobj_map_init(base_probe, &block_subsys_lock);
+	int error;
+
+	block_class.dev_kobj = sysfs_dev_block_kobj;
+	error = class_register(&block_class);
+	if (unlikely(error))
+		return error;
+	bdev_map = kobj_map_init(base_probe, &block_class_lock);
 	blk_dev_init();
-	subsystem_register(&block_subsys);
+
+	register_blkdev(BLOCK_EXT_MAJOR, "blkext");
+
+#ifndef CONFIG_SYSFS_DEPRECATED
+	/* create top-level block dir */
+	block_depr = kobject_create_and_add("block", NULL);
+#endif
 	return 0;
 }
 
 subsys_initcall(genhd_device_init);
 
-
-
-/*
- * kobject & sysfs bindings for block devices
- */
-static ssize_t disk_attr_show(struct kobject *kobj, struct attribute *attr,
-			      char *page)
+static ssize_t disk_range_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
-	struct gendisk *disk = to_disk(kobj);
-	struct disk_attribute *disk_attr =
-		container_of(attr,struct disk_attribute,attr);
-	ssize_t ret = -EIO;
+	struct gendisk *disk = dev_to_disk(dev);
 
-	if (disk_attr->show)
-		ret = disk_attr->show(disk,page);
-	return ret;
+	return sprintf(buf, "%d\n", disk->minors);
 }
 
-static ssize_t disk_attr_store(struct kobject * kobj, struct attribute * attr,
-			       const char *page, size_t count)
+static ssize_t disk_ext_range_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
 {
-	struct gendisk *disk = to_disk(kobj);
-	struct disk_attribute *disk_attr =
-		container_of(attr,struct disk_attribute,attr);
-	ssize_t ret = 0;
+	struct gendisk *disk = dev_to_disk(dev);
 
-	if (disk_attr->store)
-		ret = disk_attr->store(disk, page, count);
-	return ret;
+	return sprintf(buf, "%d\n", disk_max_parts(disk));
 }
 
-static struct sysfs_ops disk_sysfs_ops = {
-	.show	= &disk_attr_show,
-	.store	= &disk_attr_store,
-};
-
-static ssize_t disk_uevent_store(struct gendisk * disk,
-				 const char *buf, size_t count)
+static ssize_t disk_removable_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
 {
-	kobject_uevent(&disk->kobj, KOBJ_ADD);
-	return count;
-}
-static ssize_t disk_dev_read(struct gendisk * disk, char *page)
-{
-	dev_t base = MKDEV(disk->major, disk->first_minor); 
-	return print_dev_t(page, base);
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n",
+		       (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0));
 }
-static ssize_t disk_range_read(struct gendisk * disk, char *page)
+
+static ssize_t disk_ro_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
 {
-	return sprintf(page, "%d\n", disk->minors);
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", get_disk_ro(disk) ? 1 : 0);
 }
-static ssize_t disk_removable_read(struct gendisk * disk, char *page)
+
+static ssize_t disk_capability_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
 {
-	return sprintf(page, "%d\n",
-		       (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0));
+	struct gendisk *disk = dev_to_disk(dev);
 
+	return sprintf(buf, "%x\n", disk->flags);
 }
-static ssize_t disk_size_read(struct gendisk * disk, char *page)
-{
-	return sprintf(page, "%llu\n", (unsigned long long)get_capacity(disk));
-}
-
-static ssize_t disk_stats_read(struct gendisk * disk, char *page)
-{
-	preempt_disable();
-	disk_round_stats(disk);
-	preempt_enable();
-	return sprintf(page,
-		"%8lu %8lu %8llu %8u "
-		"%8lu %8lu %8llu %8u "
-		"%8u %8u %8u"
-		"\n",
-		disk_stat_read(disk, ios[READ]),
-		disk_stat_read(disk, merges[READ]),
-		(unsigned long long)disk_stat_read(disk, sectors[READ]),
-		jiffies_to_msecs(disk_stat_read(disk, ticks[READ])),
-		disk_stat_read(disk, ios[WRITE]),
-		disk_stat_read(disk, merges[WRITE]),
-		(unsigned long long)disk_stat_read(disk, sectors[WRITE]),
-		jiffies_to_msecs(disk_stat_read(disk, ticks[WRITE])),
-		disk->in_flight,
-		jiffies_to_msecs(disk_stat_read(disk, io_ticks)),
-		jiffies_to_msecs(disk_stat_read(disk, time_in_queue)));
-}
-static struct disk_attribute disk_attr_uevent = {
-	.attr = {.name = "uevent", .mode = S_IWUSR },
-	.store	= disk_uevent_store
-};
-static struct disk_attribute disk_attr_dev = {
-	.attr = {.name = "dev", .mode = S_IRUGO },
-	.show	= disk_dev_read
-};
-static struct disk_attribute disk_attr_range = {
-	.attr = {.name = "range", .mode = S_IRUGO },
-	.show	= disk_range_read
-};
-static struct disk_attribute disk_attr_removable = {
-	.attr = {.name = "removable", .mode = S_IRUGO },
-	.show	= disk_removable_read
-};
-static struct disk_attribute disk_attr_size = {
-	.attr = {.name = "size", .mode = S_IRUGO },
-	.show	= disk_size_read
+
+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(capability, S_IRUGO, disk_capability_show, NULL);
+static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+static struct device_attribute dev_attr_fail =
+	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
+#endif
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+static struct device_attribute dev_attr_fail_timeout =
+	__ATTR(io-timeout-fail,  S_IRUGO|S_IWUSR, part_timeout_show,
+		part_timeout_store);
+#endif
+
+static struct attribute *disk_attrs[] = {
+	&dev_attr_range.attr,
+	&dev_attr_ext_range.attr,
+	&dev_attr_removable.attr,
+	&dev_attr_ro.attr,
+	&dev_attr_size.attr,
+	&dev_attr_capability.attr,
+	&dev_attr_stat.attr,
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+	&dev_attr_fail.attr,
+#endif
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+	&dev_attr_fail_timeout.attr,
+#endif
+	NULL
 };
-static struct disk_attribute disk_attr_stat = {
-	.attr = {.name = "stat", .mode = S_IRUGO },
-	.show	= disk_stats_read
+
+static struct attribute_group disk_attr_group = {
+	.attrs = disk_attrs,
 };
 
-static struct attribute * default_attrs[] = {
-	&disk_attr_uevent.attr,
-	&disk_attr_dev.attr,
-	&disk_attr_range.attr,
-	&disk_attr_removable.attr,
-	&disk_attr_size.attr,
-	&disk_attr_stat.attr,
-	NULL,
+static struct attribute_group *disk_attr_groups[] = {
+	&disk_attr_group,
+	NULL
 };
 
-static void disk_release(struct kobject * kobj)
+static void disk_free_ptbl_rcu_cb(struct rcu_head *head)
 {
-	struct gendisk *disk = to_disk(kobj);
-	kfree(disk->random);
-	kfree(disk->part);
-	free_disk_stats(disk);
-	kfree(disk);
-}
+	struct disk_part_tbl *ptbl =
+		container_of(head, struct disk_part_tbl, rcu_head);
 
-static struct kobj_type ktype_block = {
-	.release	= disk_release,
-	.sysfs_ops	= &disk_sysfs_ops,
-	.default_attrs	= default_attrs,
-};
-
-extern struct kobj_type ktype_part;
+	kfree(ptbl);
+}
 
-static int block_uevent_filter(struct kset *kset, struct kobject *kobj)
+/**
+ * disk_replace_part_tbl - replace disk->part_tbl in RCU-safe way
+ * @disk: disk to replace part_tbl for
+ * @new_ptbl: new part_tbl to install
+ *
+ * Replace disk->part_tbl with @new_ptbl in RCU-safe way.  The
+ * original ptbl is freed using RCU callback.
+ *
+ * LOCKING:
+ * Matching bd_mutx locked.
+ */
+static void disk_replace_part_tbl(struct gendisk *disk,
+				  struct disk_part_tbl *new_ptbl)
 {
-	struct kobj_type *ktype = get_ktype(kobj);
+	struct disk_part_tbl *old_ptbl = disk->part_tbl;
+
+	rcu_assign_pointer(disk->part_tbl, new_ptbl);
 
-	return ((ktype == &ktype_block) || (ktype == &ktype_part));
+	if (old_ptbl) {
+		rcu_assign_pointer(old_ptbl->last_lookup, NULL);
+		call_rcu(&old_ptbl->rcu_head, disk_free_ptbl_rcu_cb);
+	}
 }
 
-static int block_uevent(struct kset *kset, struct kobject *kobj, char **envp,
-			 int num_envp, char *buffer, int buffer_size)
+/**
+ * disk_expand_part_tbl - expand disk->part_tbl
+ * @disk: disk to expand part_tbl for
+ * @partno: expand such that this partno can fit in
+ *
+ * Expand disk->part_tbl such that @partno can fit in.  disk->part_tbl
+ * uses RCU to allow unlocked dereferencing for stats and other stuff.
+ *
+ * LOCKING:
+ * Matching bd_mutex locked, might sleep.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int disk_expand_part_tbl(struct gendisk *disk, int partno)
 {
-	struct kobj_type *ktype = get_ktype(kobj);
-	struct device *physdev;
-	struct gendisk *disk;
-	struct hd_struct *part;
-	int length = 0;
-	int i = 0;
-
-	if (ktype == &ktype_block) {
-		disk = container_of(kobj, struct gendisk, kobj);
-		add_uevent_var(envp, num_envp, &i, buffer, buffer_size,
-			       &length, "MINOR=%u", disk->first_minor);
-	} else if (ktype == &ktype_part) {
-		disk = container_of(kobj->parent, struct gendisk, kobj);
-		part = container_of(kobj, struct hd_struct, kobj);
-		add_uevent_var(envp, num_envp, &i, buffer, buffer_size,
-			       &length, "MINOR=%u",
-			       disk->first_minor + part->partno);
-	} else
+	struct disk_part_tbl *old_ptbl = disk->part_tbl;
+	struct disk_part_tbl *new_ptbl;
+	int len = old_ptbl ? old_ptbl->len : 0;
+	int target = partno + 1;
+	size_t size;
+	int i;
+
+	/* disk_max_parts() is zero during initialization, ignore if so */
+	if (disk_max_parts(disk) && target > disk_max_parts(disk))
+		return -EINVAL;
+
+	if (target <= len)
 		return 0;
 
-	add_uevent_var(envp, num_envp, &i, buffer, buffer_size, &length,
-		       "MAJOR=%u", disk->major);
-
-	/* add physical device, backing this device  */
-	physdev = disk->driverfs_dev;
-	if (physdev) {
-		char *path = kobject_get_path(&physdev->kobj, GFP_KERNEL);
-
-		add_uevent_var(envp, num_envp, &i, buffer, buffer_size,
-			       &length, "PHYSDEVPATH=%s", path);
-		kfree(path);
-
-		if (physdev->bus)
-			add_uevent_var(envp, num_envp, &i,
-				       buffer, buffer_size, &length,
-				       "PHYSDEVBUS=%s",
-				       physdev->bus->name);
-
-		if (physdev->driver)
-			add_uevent_var(envp, num_envp, &i,
-				       buffer, buffer_size, &length,
-				       "PHYSDEVDRIVER=%s",
-				       physdev->driver->name);
-	}
+	size = sizeof(*new_ptbl) + target * sizeof(new_ptbl->part[0]);
+	new_ptbl = kzalloc_node(size, GFP_KERNEL, disk->node_id);
+	if (!new_ptbl)
+		return -ENOMEM;
+
+	INIT_RCU_HEAD(&new_ptbl->rcu_head);
+	new_ptbl->len = target;
 
-	/* terminate, set to next free slot, shrink available space */
-	envp[i] = NULL;
-	envp = &envp[i];
-	num_envp -= i;
-	buffer = &buffer[length];
-	buffer_size -= length;
+	for (i = 0; i < len; i++)
+		rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]);
 
+	disk_replace_part_tbl(disk, new_ptbl);
 	return 0;
 }
 
-static struct kset_uevent_ops block_uevent_ops = {
-	.filter		= block_uevent_filter,
-	.uevent		= block_uevent,
-};
+static void disk_release(struct device *dev)
+{
+	struct gendisk *disk = dev_to_disk(dev);
 
-/* declare block_subsys. */
-static decl_subsys(block, &ktype_block, &block_uevent_ops);
+	kfree(disk->random);
+	disk_replace_part_tbl(disk, NULL);
+	free_part_stats(&disk->part0);
+	kfree(disk);
+}
+struct class block_class = {
+	.name		= "block",
+};
 
+static struct device_type disk_type = {
+	.name		= "disk",
+	.groups		= disk_attr_groups,
+	.release	= disk_release,
+};
 
+#ifdef CONFIG_PROC_FS
 /*
  * aggregate disk stat collector.  Uses the same stats that the sysfs
  * entries do, above, but makes them available through one seq_file.
- * Watching a few disks may be efficient through sysfs, but watching
- * all of them will be more efficient through this interface.
  *
  * The output looks suspiciously like /proc/partitions with a bunch of
  * extra fields.
  */
-
-/* iterator */
-static void *diskstats_start(struct seq_file *part, loff_t *pos)
-{
-	loff_t k = *pos;
-	struct list_head *p;
-
-	mutex_lock(&block_subsys_lock);
-	list_for_each(p, &block_subsys.kset.list)
-		if (!k--)
-			return list_entry(p, struct gendisk, kobj.entry);
-	return NULL;
-}
-
-static void *diskstats_next(struct seq_file *part, void *v, loff_t *pos)
-{
-	struct list_head *p = ((struct gendisk *)v)->kobj.entry.next;
-	++*pos;
-	return p==&block_subsys.kset.list ? NULL :
-		list_entry(p, struct gendisk, kobj.entry);
-}
-
-static void diskstats_stop(struct seq_file *part, void *v)
-{
-	mutex_unlock(&block_subsys_lock);
-}
-
-static int diskstats_show(struct seq_file *s, void *v)
+static int diskstats_show(struct seq_file *seqf, void *v)
 {
 	struct gendisk *gp = v;
+	struct disk_part_iter piter;
+	struct hd_struct *hd;
 	char buf[BDEVNAME_SIZE];
-	int n = 0;
+	int cpu;
 
 	/*
-	if (&sgp->kobj.entry == block_subsys.kset.list.next)
-		seq_puts(s,	"major minor name"
+	if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next)
+		seq_puts(seqf,	"major minor name"
 				"     rio rmerge rsect ruse wio wmerge "
 				"wsect wuse running use aveq"
 				"\n\n");
 	*/
  
-	preempt_disable();
-	disk_round_stats(gp);
-	preempt_enable();
-	seq_printf(s, "%4d %4d %s %lu %lu %llu %u %lu %lu %llu %u %u %u %u\n",
-		gp->major, n + gp->first_minor, disk_name(gp, n, buf),
-		disk_stat_read(gp, ios[0]), disk_stat_read(gp, merges[0]),
-		(unsigned long long)disk_stat_read(gp, sectors[0]),
-		jiffies_to_msecs(disk_stat_read(gp, ticks[0])),
-		disk_stat_read(gp, ios[1]), disk_stat_read(gp, merges[1]),
-		(unsigned long long)disk_stat_read(gp, sectors[1]),
-		jiffies_to_msecs(disk_stat_read(gp, ticks[1])),
-		gp->in_flight,
-		jiffies_to_msecs(disk_stat_read(gp, io_ticks)),
-		jiffies_to_msecs(disk_stat_read(gp, time_in_queue)));
-
-	/* now show all non-0 size partitions of it */
-	for (n = 0; n < gp->minors - 1; n++) {
-		struct hd_struct *hd = gp->part[n];
-
-		if (hd && hd->nr_sects)
-			seq_printf(s, "%4d %4d %s %u %u %u %u\n",
-				gp->major, n + gp->first_minor + 1,
-				disk_name(gp, n + 1, buf),
-				hd->ios[0], hd->sectors[0],
-				hd->ios[1], hd->sectors[1]);
+	disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
+	while ((hd = disk_part_iter_next(&piter))) {
+		cpu = part_stat_lock();
+		part_round_stats(cpu, hd);
+		part_stat_unlock();
+		seq_printf(seqf, "%4d %7d %s %lu %lu %llu "
+			   "%u %lu %lu %llu %u %u %u %u\n",
+			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
+			   disk_name(gp, hd->partno, buf),
+			   part_stat_read(hd, ios[0]),
+			   part_stat_read(hd, merges[0]),
+			   (unsigned long long)part_stat_read(hd, sectors[0]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[0])),
+			   part_stat_read(hd, ios[1]),
+			   part_stat_read(hd, merges[1]),
+			   (unsigned long long)part_stat_read(hd, sectors[1]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[1])),
+			   hd->in_flight,
+			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
+			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
+			);
 	}
+	disk_part_iter_exit(&piter);
  
 	return 0;
 }
 
-struct seq_operations diskstats_op = {
-	.start	= diskstats_start,
-	.next	= diskstats_next,
-	.stop	= diskstats_stop,
+static const struct seq_operations diskstats_op = {
+	.start	= disk_seqf_start,
+	.next	= disk_seqf_next,
+	.stop	= disk_seqf_stop,
 	.show	= diskstats_show
 };
 
+static int diskstats_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &diskstats_op);
+}
+
+static const struct file_operations proc_diskstats_operations = {
+	.open		= diskstats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init proc_genhd_init(void)
+{
+	proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
+	proc_create("partitions", 0, NULL, &proc_partitions_operations);
+	return 0;
+}
+module_init(proc_genhd_init);
+#endif /* CONFIG_PROC_FS */
+
+static void media_change_notify_thread(struct work_struct *work)
+{
+	struct gendisk *gd = container_of(work, struct gendisk, async_notify);
+	char event[] = "MEDIA_CHANGE=1";
+	char *envp[] = { event, NULL };
+
+	/*
+	 * set enviroment vars to indicate which event this is for
+	 * so that user space will know to go check the media status.
+	 */
+	kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp);
+	put_device(gd->driverfs_dev);
+}
+
+#if 0
+void genhd_media_change_notify(struct gendisk *disk)
+{
+	get_device(disk->driverfs_dev);
+	schedule_work(&disk->async_notify);
+}
+EXPORT_SYMBOL_GPL(genhd_media_change_notify);
+#endif  /*  0  */
+
+dev_t blk_lookup_devt(const char *name, int partno)
+{
+	dev_t devt = MKDEV(0, 0);
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
+	while ((dev = class_dev_iter_next(&iter))) {
+		struct gendisk *disk = dev_to_disk(dev);
+		struct hd_struct *part;
+
+		if (strcmp(dev_name(dev), name))
+			continue;
+
+		if (partno < disk->minors) {
+			/* We need to return the right devno, even
+			 * if the partition doesn't exist yet.
+			 */
+			devt = MKDEV(MAJOR(dev->devt),
+				     MINOR(dev->devt) + partno);
+			break;
+		}
+		part = disk_get_part(disk, partno);
+		if (part) {
+			devt = part_devt(part);
+			disk_put_part(part);
+			break;
+		}
+		disk_put_part(part);
+	}
+	class_dev_iter_exit(&iter);
+	return devt;
+}
+EXPORT_SYMBOL(blk_lookup_devt);
+
 struct gendisk *alloc_disk(int minors)
 {
 	return alloc_disk_node(minors, -1);
 }
+EXPORT_SYMBOL(alloc_disk);
 
 struct gendisk *alloc_disk_node(int minors, int node_id)
 {
 	struct gendisk *disk;
 
-	disk = kmalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id);
+	disk = kmalloc_node(sizeof(struct gendisk),
+				GFP_KERNEL | __GFP_ZERO, node_id);
 	if (disk) {
-		memset(disk, 0, sizeof(struct gendisk));
-		if (!init_disk_stats(disk)) {
+		if (!init_part_stats(&disk->part0)) {
 			kfree(disk);
 			return NULL;
 		}
-		if (minors > 1) {
-			int size = (minors - 1) * sizeof(struct hd_struct *);
-			disk->part = kmalloc_node(size, GFP_KERNEL, node_id);
-			if (!disk->part) {
-				kfree(disk);
-				return NULL;
-			}
-			memset(disk->part, 0, size);
+		disk->node_id = node_id;
+		if (disk_expand_part_tbl(disk, 0)) {
+			free_part_stats(&disk->part0);
+			kfree(disk);
+			return NULL;
 		}
+		disk->part_tbl->part[0] = &disk->part0;
+
 		disk->minors = minors;
-		kobj_set_kset_s(disk,block_subsys);
-		kobject_init(&disk->kobj);
 		rand_initialize_disk(disk);
+		disk_to_dev(disk)->class = &block_class;
+		disk_to_dev(disk)->type = &disk_type;
+		device_initialize(disk_to_dev(disk));
+		INIT_WORK(&disk->async_notify,
+			media_change_notify_thread);
 	}
 	return disk;
 }
-
-EXPORT_SYMBOL(alloc_disk);
 EXPORT_SYMBOL(alloc_disk_node);
 
 struct kobject *get_disk(struct gendisk *disk)
@@ -648,7 +1175,7 @@ struct kobject *get_disk(struct gendisk *disk)
 	owner = disk->fops->owner;
 	if (owner && !try_module_get(owner))
 		return NULL;
-	kobj = kobject_get(&disk->kobj);
+	kobj = kobject_get(&disk_to_dev(disk)->kobj);
 	if (kobj == NULL) {
 		module_put(owner);
 		return NULL;
@@ -662,27 +1189,28 @@ EXPORT_SYMBOL(get_disk);
 void put_disk(struct gendisk *disk)
 {
 	if (disk)
-		kobject_put(&disk->kobj);
+		kobject_put(&disk_to_dev(disk)->kobj);
 }
 
 EXPORT_SYMBOL(put_disk);
 
 void set_device_ro(struct block_device *bdev, int flag)
 {
-	if (bdev->bd_contains != bdev)
-		bdev->bd_part->policy = flag;
-	else
-		bdev->bd_disk->policy = flag;
+	bdev->bd_part->policy = flag;
 }
 
 EXPORT_SYMBOL(set_device_ro);
 
 void set_disk_ro(struct gendisk *disk, int flag)
 {
-	int i;
-	disk->policy = flag;
-	for (i = 0; i < disk->minors - 1; i++)
-		if (disk->part[i]) disk->part[i]->policy = flag;
+	struct disk_part_iter piter;
+	struct hd_struct *part;
+
+	disk_part_iter_init(&piter, disk,
+			    DISK_PITER_INCL_EMPTY | DISK_PITER_INCL_PART0);
+	while ((part = disk_part_iter_next(&piter)))
+		part->policy = flag;
+	disk_part_iter_exit(&piter);
 }
 
 EXPORT_SYMBOL(set_disk_ro);
@@ -691,18 +1219,15 @@ int bdev_read_only(struct block_device *bdev)
 {
 	if (!bdev)
 		return 0;
-	else if (bdev->bd_contains != bdev)
-		return bdev->bd_part->policy;
-	else
-		return bdev->bd_disk->policy;
+	return bdev->bd_part->policy;
 }
 
 EXPORT_SYMBOL(bdev_read_only);
 
-int invalidate_partition(struct gendisk *disk, int index)
+int invalidate_partition(struct gendisk *disk, int partno)
 {
 	int res = 0;
-	struct block_device *bdev = bdget_disk(disk, index);
+	struct block_device *bdev = bdget_disk(disk, partno);
 	if (bdev) {
 		fsync_bdev(bdev);
 		res = __invalidate_device(bdev);