path: root/drivers/md/dm.c

/*
 * Copyright (C) 2001, 2002 Sistina Software (UK) Limited.
 * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
 *
 * This file is released under the GPL.
 */

#include "dm.h"
#include "dm-bio-list.h"
#include "dm-uevent.h"

#include <linux/init.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/moduleparam.h>
#include <linux/blkpg.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/mempool.h>
#include <linux/slab.h>
#include <linux/idr.h>
#include <linux/hdreg.h>
#include <linux/blktrace_api.h>
#include <linux/smp_lock.h>

#define DM_MSG_PREFIX "core"

static const char *_name = DM_NAME;

static unsigned int major = 0;
static unsigned int _major = 0;

static DEFINE_SPINLOCK(_minor_lock);
/*
 * One of these is allocated per bio.
 */
struct dm_io {
	struct mapped_device *md;
	int error;
	struct bio *bio;
	atomic_t io_count;
	unsigned long start_time;
};

/*
 * One of these is allocated per target within a bio.  Hopefully
 * this will be simplified out one day.
 */
struct dm_target_io {
	struct dm_io *io;
	struct dm_target *ti;
	union map_info info;
};

union map_info *dm_get_mapinfo(struct bio *bio)
{
	if (bio && bio->bi_private)
		return &((struct dm_target_io *)bio->bi_private)->info;
	return NULL;
}

#define MINOR_ALLOCED ((void *)-1)

/*
 * Bits for the md->flags field.
 */
#define DMF_BLOCK_IO 0
#define DMF_SUSPENDED 1
#define DMF_FROZEN 2
#define DMF_FREEING 3
#define DMF_DELETING 4
#define DMF_NOFLUSH_SUSPENDING 5

struct mapped_device {
	struct rw_semaphore io_lock;
	struct semaphore suspend_lock;
	spinlock_t pushback_lock;
	rwlock_t map_lock;
	atomic_t holders;
	atomic_t open_count;

	unsigned long flags;

	struct request_queue *queue;
	struct gendisk *disk;
	char name[16];

	void *interface_ptr;

	/*
	 * A list of ios that arrived while we were suspended.
	 */
	atomic_t pending;
	wait_queue_head_t wait;
	struct bio_list deferred;
	struct bio_list pushback;

	/*
	 * The current mapping.
	 */
	struct dm_table *map;

	/*
	 * io objects are allocated from here.
	 */
	mempool_t *io_pool;
	mempool_t *tio_pool;

	struct bio_set *bs;

	/*
	 * Event handling.
	 */
	atomic_t event_nr;
	wait_queue_head_t eventq;
	atomic_t uevent_seq;
	struct list_head uevent_list;
	spinlock_t uevent_lock; /* Protect access to uevent_list */

	/*
	 * freeze/thaw support require holding onto a super block
	 */
	struct super_block *frozen_sb;
	struct block_device *suspended_bdev;

	/* forced geometry settings */
	struct hd_geometry geometry;
};

#define MIN_IOS 256
static struct kmem_cache *_io_cache;
static struct kmem_cache *_tio_cache;

static int __init local_init(void)
{
	int r;

	/* allocate a slab for the dm_ios */
	_io_cache = KMEM_CACHE(dm_io, 0);
	if (!_io_cache)
		return -ENOMEM;

	/* allocate a slab for the target ios */
	_tio_cache = KMEM_CACHE(dm_target_io, 0);
	if (!_tio_cache) {
		kmem_cache_destroy(_io_cache);
		return -ENOMEM;
	}

	r = dm_uevent_init();
	if (r) {
		kmem_cache_destroy(_tio_cache);
		kmem_cache_destroy(_io_cache);
		return r;
	}

	_major = major;
	r = register_blkdev(_major, _name);
	if (r < 0) {
		kmem_cache_destroy(_tio_cache);
		kmem_cache_destroy(_io_cache);
		dm_uevent_exit();
		return r;
	}

	if (!_major)
		_major = r;

	return 0;
}

static void local_exit(void)
{
	kmem_cache_destroy(_tio_cache);
	kmem_cache_destroy(_io_cache);
	unregister_blkdev(_major, _name);
	dm_uevent_exit();

	_major = 0;

	DMINFO("cleaned up");
}

int (*_inits[])(void) __initdata = {
	local_init,
	dm_target_init,
	dm_linear_init,
	dm_stripe_init,
	dm_interface_init,
};

void (*_exits[])(void) = {
	local_exit,
	dm_target_exit,
	dm_linear_exit,
	dm_stripe_exit,
	dm_interface_exit,
};

static int __init dm_init(void)
{
	const int count = ARRAY_SIZE(_inits);

	int r, i;

	for (i = 0; i < count; i++) {
		r = _inits[i]();
		if (r)
			goto bad;
	}

	return 0;

      bad:
	while (i--)
		_exits[i]();

	return r;
}

static void __exit dm_exit(void)
{
	int i = ARRAY_SIZE(_exits);

	while (i--)
		_exits[i]();
}

/*
 * Block device functions
 */
static int dm_blk_open(struct inode *inode, struct file *file)
{
	struct mapped_device *md;

	spin_lock(&_minor_lock);

	md = inode->i_bdev->bd_disk->private_data;
	if (!md)
		goto out;

	if (test_bit(DMF_FREEING, &md->flags) ||
	    test_bit(DMF_DELETING, &md->flags)) {
		md = NULL;
		goto out;
	}

	dm_get(md);
	atomic_inc(&md->open_count);

out:
	spin_unlock(&_minor_lock);

	return md ? 0 : -ENXIO;
}

static int dm_blk_close(struct inode *inode, struct file *file)
{
	struct mapped_device *md;

	md = inode->i_bdev->bd_disk->private_data;
	atomic_dec(&md->open_count);
	dm_put(md);
	return 0;
}

int dm_open_count(struct mapped_device *md)
{
	return atomic_read(&md->open_count);
}

/*
 * Guarantees nothing is using the device before it's deleted.
 */
int dm_lock_for_deletion(struct mapped_device *md)
{
	int r = 0;

	spin_lock(&_minor_lock);

	if (dm_open_count(md))
		r = -EBUSY;
	else
		set_bit(DMF_DELETING, &md->flags);

	spin_unlock(&_minor_lock);

	return r;
}

static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
	struct mapped_device *md = bdev->bd_disk->private_data;

	return dm_get_geometry(md, geo);
}

static int dm_blk_ioctl(struct inode *inode, struct file *file,
			unsigned int cmd, unsigned long arg)
{
	struct mapped_device *md;
	struct dm_table *map;
	struct dm_target *tgt;
	int r = -ENOTTY;

	/* We don't really need this lock, but we do need 'inode'. */
	unlock_kernel();

	md = inode->i_bdev->bd_disk->private_data;

	map = dm_get_table(md);

	if (!map || !dm_table_get_size(map))
		goto out;

	/* We only support devices that have a single target */
	if (dm_table_get_num_targets(map) != 1)
		goto out;

	tgt = dm_table_get