/*
 *  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/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>

#include "blk.h"

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)
		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)
			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 (!(piter->flags & DISK_PITER_INCL_EMPTY) && !part->nr_sects)
			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.
 *
 */
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(int 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;

	if (offset < BLKDEV_MAJOR_HASH_SIZE) {
		mutex_lock(&block_class_lock);
		for (dp = major_names[offset]; dp; dp = dp->next)
			seq_printf(seqf, "%3d %s\n", dp->major, dp->name);
		mutex_unlock(&block_class_lock);
	}
}
#endif /* CONFIG_PROC_FS */

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;
	}

	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 %d 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, 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 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(p))
		return -1;
	return 0;
}

/**
 * add_disk - add partitioning information to kernel list
 * @disk: per-device partitioning information
 *
 * 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;

	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);
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(disk_devt(disk), disk->minors);
}

/**
 * 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;

		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;