dm.c

linux 内核源代码

static void unlock_fs(struct mapped_device *md);

static void free_dev(struct mapped_device *md)
{
	int minor = md->disk->first_minor;

	if (md->suspended_bdev) {
		unlock_fs(md);
		bdput(md->suspended_bdev);
	}
	mempool_destroy(md->tio_pool);
	mempool_destroy(md->io_pool);
	bioset_free(md->bs);
	del_gendisk(md->disk);
	free_minor(minor);

	spin_lock(&_minor_lock);
	md->disk->private_data = NULL;
	spin_unlock(&_minor_lock);

	put_disk(md->disk);
	blk_cleanup_queue(md->queue);
	module_put(THIS_MODULE);
	kfree(md);
}

/*
 * Bind a table to the device.
 */
static void event_callback(void *context)
{
	unsigned long flags;
	LIST_HEAD(uevents);
	struct mapped_device *md = (struct mapped_device *) context;

	spin_lock_irqsave(&md->uevent_lock, flags);
	list_splice_init(&md->uevent_list, &uevents);
	spin_unlock_irqrestore(&md->uevent_lock, flags);

	dm_send_uevents(&uevents, &md->disk->kobj);

	atomic_inc(&md->event_nr);
	wake_up(&md->eventq);
}

static void __set_size(struct mapped_device *md, sector_t size)
{
	set_capacity(md->disk, size);

	mutex_lock(&md->suspended_bdev->bd_inode->i_mutex);
	i_size_write(md->suspended_bdev->bd_inode, (loff_t)size << SECTOR_SHIFT);
	mutex_unlock(&md->suspended_bdev->bd_inode->i_mutex);
}

static int __bind(struct mapped_device *md, struct dm_table *t)
{
	struct request_queue *q = md->queue;
	sector_t size;

	size = dm_table_get_size(t);

	/*
	 * Wipe any geometry if the size of the table changed.
	 */
	if (size != get_capacity(md->disk))
		memset(&md->geometry, 0, sizeof(md->geometry));

	if (md->suspended_bdev)
		__set_size(md, size);
	if (size == 0)
		return 0;

	dm_table_get(t);
	dm_table_event_callback(t, event_callback, md);

	write_lock(&md->map_lock);
	md->map = t;
	dm_table_set_restrictions(t, q);
	write_unlock(&md->map_lock);

	return 0;
}

static void __unbind(struct mapped_device *md)
{
	struct dm_table *map = md->map;

	if (!map)
		return;

	dm_table_event_callback(map, NULL, NULL);
	write_lock(&md->map_lock);
	md->map = NULL;
	write_unlock(&md->map_lock);
	dm_table_put(map);
}

/*
 * Constructor for a new device.
 */
int dm_create(int minor, struct mapped_device **result)
{
	struct mapped_device *md;

	md = alloc_dev(minor);
	if (!md)
		return -ENXIO;

	*result = md;
	return 0;
}

static struct mapped_device *dm_find_md(dev_t dev)
{
	struct mapped_device *md;
	unsigned minor = MINOR(dev);

	if (MAJOR(dev) != _major || minor >= (1 << MINORBITS))
		return NULL;

	spin_lock(&_minor_lock);

	md = idr_find(&_minor_idr, minor);
	if (md && (md == MINOR_ALLOCED ||
		   (dm_disk(md)->first_minor != minor) ||
		   test_bit(DMF_FREEING, &md->flags))) {
		md = NULL;
		goto out;
	}

out:
	spin_unlock(&_minor_lock);

	return md;
}

struct mapped_device *dm_get_md(dev_t dev)
{
	struct mapped_device *md = dm_find_md(dev);

	if (md)
		dm_get(md);

	return md;
}

void *dm_get_mdptr(struct mapped_device *md)
{
	return md->interface_ptr;
}

void dm_set_mdptr(struct mapped_device *md, void *ptr)
{
	md->interface_ptr = ptr;
}

void dm_get(struct mapped_device *md)
{
	atomic_inc(&md->holders);
}

const char *dm_device_name(struct mapped_device *md)
{
	return md->name;
}
EXPORT_SYMBOL_GPL(dm_device_name);

void dm_put(struct mapped_device *md)
{
	struct dm_table *map;

	BUG_ON(test_bit(DMF_FREEING, &md->flags));

	if (atomic_dec_and_lock(&md->holders, &_minor_lock)) {
		map = dm_get_table(md);
		idr_replace(&_minor_idr, MINOR_ALLOCED, dm_disk(md)->first_minor);
		set_bit(DMF_FREEING, &md->flags);
		spin_unlock(&_minor_lock);
		if (!dm_suspended(md)) {
			dm_table_presuspend_targets(map);
			dm_table_postsuspend_targets(map);
		}
		__unbind(md);
		dm_table_put(map);
		free_dev(md);
	}
}
EXPORT_SYMBOL_GPL(dm_put);

/*
 * Process the deferred bios
 */
static void __flush_deferred_io(struct mapped_device *md, struct bio *c)
{
	struct bio *n;

	while (c) {
		n = c->bi_next;
		c->bi_next = NULL;
		if (__split_bio(md, c))
			bio_io_error(c);
		c = n;
	}
}

/*
 * Swap in a new table (destroying old one).
 */
int dm_swap_table(struct mapped_device *md, struct dm_table *table)
{
	int r = -EINVAL;

	down(&md->suspend_lock);

	/* device must be suspended */
	if (!dm_suspended(md))
		goto out;

	/* without bdev, the device size cannot be changed */
	if (!md->suspended_bdev)
		if (get_capacity(md->disk) != dm_table_get_size(table))
			goto out;

	__unbind(md);
	r = __bind(md, table);

out:
	up(&md->suspend_lock);
	return r;
}

/*
 * Functions to lock and unlock any filesystem running on the
 * device.
 */
static int lock_fs(struct mapped_device *md)
{
	int r;

	WARN_ON(md->frozen_sb);

	md->frozen_sb = freeze_bdev(md->suspended_bdev);
	if (IS_ERR(md->frozen_sb)) {
		r = PTR_ERR(md->frozen_sb);
		md->frozen_sb = NULL;
		return r;
	}

	set_bit(DMF_FROZEN, &md->flags);

	/* don't bdput right now, we don't want the bdev
	 * to go away while it is locked.
	 */
	return 0;
}

static void unlock_fs(struct mapped_device *md)
{
	if (!test_bit(DMF_FROZEN, &md->flags))
		return;

	thaw_bdev(md->suspended_bdev, md->frozen_sb);
	md->frozen_sb = NULL;
	clear_bit(DMF_FROZEN, &md->flags);
}

/*
 * We need to be able to change a mapping table under a mounted
 * filesystem.  For example we might want to move some data in
 * the background.  Before the table can be swapped with
 * dm_bind_table, dm_suspend must be called to flush any in
 * flight bios and ensure that any further io gets deferred.
 */
int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
{
	struct dm_table *map = NULL;
	unsigned long flags;
	DECLARE_WAITQUEUE(wait, current);
	struct bio *def;
	int r = -EINVAL;
	int do_lockfs = suspend_flags & DM_SUSPEND_LOCKFS_FLAG ? 1 : 0;
	int noflush = suspend_flags & DM_SUSPEND_NOFLUSH_FLAG ? 1 : 0;

	down(&md->suspend_lock);

	if (dm_suspended(md))
		goto out_unlock;

	map = dm_get_table(md);

	/*
	 * DMF_NOFLUSH_SUSPENDING must be set before presuspend.
	 * This flag is cleared before dm_suspend returns.
	 */
	if (noflush)
		set_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);

	/* This does not get reverted if there's an error later. */
	dm_table_presuspend_targets(map);

	/* bdget() can stall if the pending I/Os are not flushed */
	if (!noflush) {
		md->suspended_bdev = bdget_disk(md->disk, 0);
		if (!md->suspended_bdev) {
			DMWARN("bdget failed in dm_suspend");
			r = -ENOMEM;
			goto flush_and_out;
		}
	}

	/*
	 * Flush I/O to the device.
	 * noflush supersedes do_lockfs, because lock_fs() needs to flush I/Os.
	 */
	if (do_lockfs && !noflush) {
		r = lock_fs(md);
		if (r)
			goto out;
	}

	/*
	 * First we set the BLOCK_IO flag so no more ios will be mapped.
	 */
	down_write(&md->io_lock);
	set_bit(DMF_BLOCK_IO, &md->flags);

	add_wait_queue(&md->wait, &wait);
	up_write(&md->io_lock);

	/* unplug */
	if (map)
		dm_table_unplug_all(map);

	/*
	 * Then we wait for the already mapped ios to
	 * complete.
	 */
	while (1) {
		set_current_state(TASK_INTERRUPTIBLE);

		if (!atomic_read(&md->pending) || signal_pending(current))
			break;

		io_schedule();
	}
	set_current_state(TASK_RUNNING);

	down_write(&md->io_lock);
	remove_wait_queue(&md->wait, &wait);

	if (noflush) {
		spin_lock_irqsave(&md->pushback_lock, flags);
		clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
		bio_list_merge_head(&md->deferred, &md->pushback);
		bio_list_init(&md->pushback);
		spin_unlock_irqrestore(&md->pushback_lock, flags);
	}

	/* were we interrupted ? */
	r = -EINTR;
	if (atomic_read(&md->pending)) {
		clear_bit(DMF_BLOCK_IO, &md->flags);
		def = bio_list_get(&md->deferred);
		__flush_deferred_io(md, def);
		up_write(&md->io_lock);
		unlock_fs(md);
		goto out; /* pushback list is already flushed, so skip flush */
	}
	up_write(&md->io_lock);

	dm_table_postsuspend_targets(map);

	set_bit(DMF_SUSPENDED, &md->flags);

	r = 0;

flush_and_out:
	if (r && noflush) {
		/*
		 * Because there may be already I/Os in the pushback list,
		 * flush them before return.
		 */
		down_write(&md->io_lock);

		spin_lock_irqsave(&md->pushback_lock, flags);
		clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
		bio_list_merge_head(&md->deferred, &md->pushback);
		bio_list_init(&md->pushback);
		spin_unlock_irqrestore(&md->pushback_lock, flags);

		def = bio_list_get(&md->deferred);
		__flush_deferred_io(md, def);
		up_write(&md->io_lock);
	}

out:
	if (r && md->suspended_bdev) {
		bdput(md->suspended_bdev);
		md->suspended_bdev = NULL;
	}

	dm_table_put(map);

out_unlock:
	up(&md->suspend_lock);
	return r;
}

int dm_resume(struct mapped_device *md)
{
	int r = -EINVAL;
	struct bio *def;
	struct dm_table *map = NULL;

	down(&md->suspend_lock);
	if (!dm_suspended(md))
		goto out;

	map = dm_get_table(md);
	if (!map || !dm_table_get_size(map))
		goto out;

	r = dm_table_resume_targets(map);
	if (r)
		goto out;

	down_write(&md->io_lock);
	clear_bit(DMF_BLOCK_IO, &md->flags);

	def = bio_list_get(&md->deferred);
	__flush_deferred_io(md, def);
	up_write(&md->io_lock);

	unlock_fs(md);

	if (md->suspended_bdev) {
		bdput(md->suspended_bdev);
		md->suspended_bdev = NULL;
	}

	clear_bit(DMF_SUSPENDED, &md->flags);

	dm_table_unplug_all(map);

	dm_kobject_uevent(md);

	r = 0;

out:
	dm_table_put(map);
	up(&md->suspend_lock);

	return r;
}

/*-----------------------------------------------------------------
 * Event notification.
 *---------------------------------------------------------------*/
void dm_kobject_uevent(struct mapped_device *md)
{
	kobject_uevent(&md->disk->kobj, KOBJ_CHANGE);
}

uint32_t dm_next_uevent_seq(struct mapped_device *md)
{
	return atomic_add_return(1, &md->uevent_seq);
}

uint32_t dm_get_event_nr(struct mapped_device *md)
{
	return atomic_read(&md->event_nr);
}

int dm_wait_event(struct mapped_device *md, int event_nr)
{
	return wait_event_interruptible(md->eventq,
			(event_nr != atomic_read(&md->event_nr)));
}

void dm_uevent_add(struct mapped_device *md, struct list_head *elist)
{
	unsigned long flags;

	spin_lock_irqsave(&md->uevent_lock, flags);
	list_add(elist, &md->uevent_list);
	spin_unlock_irqrestore(&md->uevent_lock, flags);
}

/*
 * The gendisk is only valid as long as you have a reference
 * count on 'md'.
 */
struct gendisk *dm_disk(struct mapped_device *md)
{
	return md->disk;
}

int dm_suspended(struct mapped_device *md)
{
	return test_bit(DMF_SUSPENDED, &md->flags);
}

int dm_noflush_suspending(struct dm_target *ti)
{
	struct mapped_device *md = dm_table_get_md(ti->table);
	int r = __noflush_suspending(md);

	dm_put(md);

	return r;
}
EXPORT_SYMBOL_GPL(dm_noflush_suspending);

static struct block_device_operations dm_blk_dops = {
	.open = dm_blk_open,
	.release = dm_blk_close,
	.ioctl = dm_blk_ioctl,
	.getgeo = dm_blk_getgeo,
	.owner = THIS_MODULE
};

EXPORT_SYMBOL(dm_get_mapinfo);

/*
 * module hooks
 */
module_init(dm_init);
module_exit(dm_exit);

module_param(major, uint, 0);
MODULE_PARM_DESC(major, "The major number of the device mapper");
MODULE_DESCRIPTION(DM_NAME " driver");
MODULE_AUTHOR("Joe Thornber <[e-mail]>");
MODULE_LICENSE("GPL");