genhd.c

/*
 *  gendisk handling
 */

#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/backing-dev.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/mutex.h>
#include <linux/idr.h>
#include <linux/log2.h>
#include <linux/pm_runtime.h>
#include <linux/badblocks.h>

#include "blk.h"

static DEFINE_MUTEX(block_class_lock);
struct kobject *block_depr;

/* for extended dynamic devt allocation, currently only one major is used */
#define NR_EXT_DEVT		(1 << MINORBITS)

/* For extended devt allocation.  ext_devt_lock prevents look up
 * results from going away underneath its user.
 */
static DEFINE_SPINLOCK(ext_devt_lock);
static DEFINE_IDR(ext_devt_idr);

static const struct device_type disk_type;

static void disk_check_events(struct disk_events *ev,
			      unsigned int *clearing_ptr);
static void disk_alloc_events(struct gendisk *disk);
static void disk_add_events(struct gendisk *disk);
static void disk_del_events(struct gendisk *disk);
static void disk_release_events(struct gendisk *disk);

void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
{
	if (queue_is_mq(q))
		return;

	part_stat_local_inc(part, in_flight[rw]);
	if (part->partno)
		part_stat_local_inc(&part_to_disk(part)->part0, in_flight[rw]);
}

void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
{
	if (queue_is_mq(q))
		return;

	part_stat_local_dec(part, in_flight[rw]);
	if (part->partno)
		part_stat_local_dec(&part_to_disk(part)->part0, in_flight[rw]);
}

unsigned int part_in_flight(struct request_queue *q, struct hd_struct *part)
{
	int cpu;
	unsigned int inflight;

	if (queue_is_mq(q)) {
		return blk_mq_in_flight(q, part);
	}

	inflight = 0;
	for_each_possible_cpu(cpu) {
		inflight += part_stat_local_read_cpu(part, in_flight[0], cpu) +
			    part_stat_local_read_cpu(part, in_flight[1], cpu);
	}
	if ((int)inflight < 0)
		inflight = 0;

	return inflight;
}

void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
		       unsigned int inflight[2])
{
	int cpu;

	if (queue_is_mq(q)) {
		blk_mq_in_flight_rw(q, part, inflight);
		return;
	}

	inflight[0] = 0;
	inflight[1] = 0;
	for_each_possible_cpu(cpu) {
		inflight[0] += part_stat_local_read_cpu(part, in_flight[0], cpu);
		inflight[1] += part_stat_local_read_cpu(part, in_flight[1], cpu);
	}
	if ((int)inflight[0] < 0)
		inflight[0] = 0;
	if ((int)inflight[1] < 0)
		inflight[1] = 0;
}

struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
{
	struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl);

	if (unlikely(partno < 0 || partno >= ptbl->len))
		return NULL;
	return rcu_dereference(ptbl->part[partno]);
}

/**
 * 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;

	rcu_read_lock();
	part = __disk_get_part(disk, 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_read(part) &&
		    !(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_read(part);
}

/**
 * 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.
 *
 */
#define BLKDEV_MAJOR_HASH_SIZE 255
static struct blk_major_name {
	struct blk_major_name *next;
	int major;
	char name[16];
} *major_names[BLKDEV_MAJOR_HASH_SIZE];

/* index in the above - for now: assume no multimajor ranges */
static inline int major_to_index(unsigned major)
{
	return major % BLKDEV_MAJOR_HASH_SIZE;
}

#ifdef CONFIG_PROC_FS
void blkdev_show(struct seq_file *seqf, off_t offset)
{
	struct blk_major_name *dp;

	mutex_lock(&block_class_lock);
	for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next)
		if (dp->major == offset)
			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..BLKDEV_MAJOR_MAX-1]. 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..BLKDEV_MAJOR_MAX-1]
 *    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..BLKDEV_MAJOR_MAX-1] or a negative error code otherwise
 *
 * See Documentation/admin-guide/devices.txt for the list of allocated
 * major numbers.
 */
int register_blkdev(unsigned int major, const char *name)
{
	struct blk_major_name **n, *p;
	int index, ret = 0;

	mutex_lock(&block_class_lock);

	/* temporary */
	if (major == 0) {
		for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) {
			if (major_names[index] == NULL)
				break;
		}

		if (index == 0) {
			printk("register_blkdev: failed to get major for %s\n",
			       name);
			ret = -EBUSY;
			goto out;
		}
		major = index;
		ret = major;
	}

	if (major >= BLKDEV_MAJOR_MAX) {
		pr_err("register_blkdev: major requested (%u) is greater than the maximum (%u) for %s\n",
		       major, BLKDEV_MAJOR_MAX-1, name);

		ret = -EINVAL;
		goto out;
	}

	p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL);
	if (p == NULL) {
		ret = -ENOMEM;
		goto out;
	}

	p->major = major;
	strlcpy(p->name, name, sizeof(p->name));
	p->next = NULL;
	index = major_to_index(major);

	for (n = &major_names[index]; *n; n = &(*n)->next) {
		if ((*n)->major == major)
			break;
	}
	if (!*n)
		*n = p;
	else
		ret = -EBUSY;

	if (ret < 0) {
		printk("register_blkdev: cannot get major %u for %s\n",
		       major, name);
		kfree(p);
	}
out:
	mutex_unlock(&block_class_lock);
	return ret;
}

EXPORT_SYMBOL(register_blkdev);

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);

	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)) {
		WARN_ON(1);
	} else {
		p = *n;
		*n = p->next;
	}
	mutex_unlock(&block_class_lock);
	kfree(p);
}

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;

	/* in consecutive minor range? */
	if (part->partno < disk->minors) {
		*devt = MKDEV(disk->major, disk->first_minor + part->partno);
		return 0;
	}

	/* allocate ext devt */
	idr_preload(GFP_KERNEL);

	spin_lock_bh(&ext_devt_lock);
	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
	spin_unlock_bh(&ext_devt_lock);

	idr_preload_end();
	if (idx < 0)
		return idx == -ENOSPC ? -EBUSY : idx;

	*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)
{
	if (devt == MKDEV(0, 0))
		return;

	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
		spin_lock_bh(&ext_devt_lock);
		idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
		spin_unlock_bh(&ext_devt_lock);
	}
}

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 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, devt, range, module, probe, lock, data);
}

EXPORT_SYMBOL(blk_register_region);

void blk_unregister_region(dev_t devt, unsigned long range)
{
	kobj_unmap(bdev_map, devt, range);
}

EXPORT_SYMBOL(blk_unregister_region);

static struct kobject *exact_match(dev_t devt, int *partno, void *data)
{
	struct gendisk *p = data;

	return &disk_to_dev(p)->kobj;
}

static int exact_lock(dev_t devt, void *data)
{
	struct gendisk *p = data;

	if (!get_disk_and_module(p))
		return -1;
	return 0;
}

static void register_disk(struct device *parent, struct gendisk *disk,
			  const struct attribute_group **groups)
{
	struct device *ddev = disk_to_dev(disk);
	struct block_device *bdev;
	struct disk_part_iter piter;
	struct hd_struct *part;
	int err;

	ddev->parent = parent;

	dev_set_name(ddev, "%s", disk->disk_name);

	/* delay uevents, until we scanned partition table */
	dev_set_uevent_suppress(ddev, 1);

	if (groups) {
		WARN_ON(ddev->groups);
		ddev->groups = groups;
	}
	if (device_add(ddev))
		return;
	if (!sysfs_deprecated) {
		err = sysfs_create_link(block_depr, &ddev->kobj,
					kobject_name(&ddev->kobj));
		if (err) {
			device_del(ddev);
			return;
		}
	}

	/*
	 * avoid probable deadlock caused by allocating memory with
	 * GFP_KERNEL in runtime_resume callback of its all ancestor
	 * devices
	 */
	pm_runtime_set_memalloc_noio(ddev, true);

	disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);

	if (disk->flags & GENHD_FL_HIDDEN) {
		dev_set_uevent_suppress(ddev, 0);
		return;
	}

	/* No minors to use for partitions */
	if (!disk_part_scan_enabled(disk))
		goto exit;

	/* No such device (e.g., media were just removed) */
	if (!get_capacity(disk))
		goto exit;

	bdev = bdget_disk(disk, 0);
	if (!bdev)
		goto exit;

	bdev->bd_invalidated = 1;
	err = blkdev_get(bdev, FMODE_READ, NULL);
	if (err < 0)
		goto exit;
	blkdev_put(bdev, FMODE_READ);

exit:
	/* announce disk after possible partitions are created */
	dev_set_uevent_suppress(ddev, 0);
	kobject_uevent(&ddev->kobj, KOBJ_ADD);

	/* announce possible partitions */
	disk_part_iter_init(&piter, disk, 0);
	while ((part = disk_part_iter_next(&piter)))
		kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD);
	disk_part_iter_exit(&piter);

	err = sysfs_create_link(&ddev->kobj,
				&disk->queue->backing_dev_info->dev->kobj,
				"bdi");
	WARN_ON(err);
}

/**
 * __device_add_disk - add disk information to kernel list
 * @parent: parent device for the disk
 * @disk: per-device partitioning information
 * @groups: Additional per-device sysfs groups
 * @register_queue: register the queue if set to true
 *
 * This function registers the partitioning information in @disk
 * with the kernel.
 *
 * FIXME: error handling
 */
static void __device_add_disk(struct device *parent, struct gendisk *disk,
			      const struct attribute_group **groups,
			      bool register_queue)
{
	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 | GENHD_FL_HIDDEN)));

	disk->flags |= GENHD_FL_UP;

	retval = blk_alloc_devt(&disk->part0, &devt);
	if (retval) {
		WARN_ON(1);
		return;
	}
	disk->major = MAJOR(devt);
	disk->first_minor = MINOR(devt);

	disk_alloc_events(disk);

	if (disk->flags & GENHD_FL_HIDDEN) {
		/*
		 * Don't let hidden disks show up in /proc/partitions,
		 * and don't bother scanning for partitions either.
		 */
		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
		disk->flags |= GENHD_FL_NO_PART_SCAN;
	} else {
		int ret;

		/* Register BDI before referencing it from bdev */
		disk_to_dev(disk)->devt = devt;
		ret = bdi_register_owner(disk->queue->backing_dev_info,
						disk_to_dev(disk));
		WARN_ON(ret);
		blk_register_region(disk_devt(disk), disk->minors, NULL,
				    exact_match, exact_lock, disk);
	}
	register_disk(parent, disk, groups);
	if (register_queue)
		blk_register_queue(disk);

	/*
	 * Take an extra ref on queue which will be put on disk_release()
	 * so that it sticks around as long as @disk is there.
	 */
	WARN_ON_ONCE(!blk_get_queue(disk->queue));

	disk_add_events(disk);
	blk_integrity_add(disk);
}

void device_add_disk(struct device *parent, struct gendisk *disk,
		     const struct attribute_group **groups)

{
	__device_add_disk(parent, disk, groups, true);
}
EXPORT_SYMBOL(device_add_disk);

void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk)
{
	__device_add_disk(parent, disk, NULL, false);
}
EXPORT_SYMBOL(device_add_disk_no_queue_reg);

void del_gendisk(struct gendisk *disk)
{
	struct disk_part_iter piter;
	struct hd_struct *part;

	blk_integrity_del(disk);
	disk_del_events(disk);

	/*
	 * Block lookups of the disk until all bdevs are unhashed and the
	 * disk is marked as dead (GENHD_FL_UP cleared).
	 */
	down_write(&disk->lookup_sem);
	/* invalidate stuff */
	disk_part_iter_init(&piter, disk,
			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
	while ((part = disk_part_iter_next(&piter))) {
		invalidate_partition(disk, part->partno);
		bdev_unhash_inode(part_devt(part));
		delete_partition(disk, part->partno);
	}
	disk_part_iter_exit(&piter);

	invalidate_partition(disk, 0);
	bdev_unhash_inode(disk_devt(disk));
	set_capacity(disk, 0);
	disk->flags &= ~GENHD_FL_UP;
	up_write(&disk->lookup_sem);

	if (!(disk->flags & GENHD_FL_HIDDEN))
		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
	if (disk->queue) {
		/*
		 * Unregister bdi before releasing device numbers (as they can
		 * get reused and we'd get clashes in sysfs).
		 */
		if (!(disk->flags & GENHD_FL_HIDDEN))
			bdi_unregister(disk->queue->backing_dev_info);
		blk_unregister_queue(disk);
	} else {
		WARN_ON(1);
	}

	if (!(disk->flags & GENHD_FL_HIDDEN))
		blk_unregister_region(disk_devt(disk), disk->minors);

	kobject_put(disk->part0.holder_dir);
	kobject_put(disk->slave_dir);

	part_stat_set_all(&disk->part0, 0);
	disk->part0.stamp = 0;
	if (!sysfs_deprecated)
		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
	device_del(disk_to_dev(disk));
}
EXPORT_SYMBOL(del_gendisk);

/* sysfs access to bad-blocks list. */
static ssize_t disk_badblocks_show(struct device *dev,
					struct device_attribute *attr,
					char *page)
{
	struct gendisk *disk = dev_to_disk(dev);

	if (!disk->bb)
		return sprintf(page, "\n");

	return badblocks_show(disk->bb, page, 0);
}

static ssize_t disk_badblocks_store(struct device *dev,
					struct device_attribute *attr,
					const char *page, size_t len)
{
	struct gendisk *disk = dev_to_disk(dev);

	if (!disk->bb)
		return -ENXIO;

	return badblocks_store(disk->bb, page, len, 0);
}

/**
 * get_gendisk - get partitioning information for a given device
 * @devt: device to get partitioning information for
 * @partno: returned partition index
 *
 * This function gets the structure containing partitioning
 * information for the given device @devt.
 */
struct gendisk *get_gendisk(dev_t devt, int *partno)
{
	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;

		spin_lock_bh(&ext_devt_lock);
		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
		if (part && get_disk_and_module(part_to_disk(part))) {
			*partno = part->partno;
			disk = part_to_disk(part);
		}
		spin_unlock_bh(&ext_devt_lock);
	}

	if (!disk)
		return NULL;

	/*
	 * Synchronize with del_gendisk() to not return disk that is being
	 * destroyed.
	 */
	down_read(&disk->lookup_sem);
	if (unlikely((disk->flags & GENHD_FL_HIDDEN) ||
		     !(disk->flags & GENHD_FL_UP))) {
		up_read(&disk->lookup_sem);
		put_disk_and_module(disk);
		disk = NULL;
	} else {
		up_read(&disk->lookup_sem);
	}
	return disk;
}
EXPORT_SYMBOL(get_gendisk);

/**
 * 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
		 * suppressed
		 */
		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 %s", is_part0 ? "" : "  ",
			       bdevt_str(part_devt(part), devt_buf),
			       (unsigned long long)part_nr_sects_read(part) >> 1
			       , disk_name(disk, part->partno, name_buf),
			       part->info ? part->info->uuid : "");
			if (is_part0) {
				if (dev->parent && dev->parent->driver)
					printk(" driver: %s\n",
					      dev->parent->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 *disk_seqf_start(struct seq_file *seqf, loff_t *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);

	return NULL;
}

static void disk_seqf_stop(struct seq_file *seqf, void *v)
{
	struct class_dev_iter *iter = seqf->private;