/*
* Copyright (C) 2001, 2002 Sistina Software (UK) Limited.
- * Copyright (C) 2004 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
*
* This file is released under the GPL.
*/
#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;
union map_info *dm_get_mapinfo(struct bio *bio)
{
- if (bio && bio->bi_private)
- return &((struct target_io *)bio->bi_private)->info;
- return NULL;
+ if (bio && bio->bi_private)
+ return &((struct target_io *)bio->bi_private)->info;
+ return NULL;
}
#define MINOR_ALLOCED ((void *)-1)
#define DMF_SUSPENDED 1
#define DMF_FROZEN 2
#define DMF_FREEING 3
+#define DMF_DELETING 4
struct mapped_device {
struct rw_semaphore io_lock;
struct semaphore suspend_lock;
rwlock_t map_lock;
atomic_t holders;
+ atomic_t open_count;
unsigned long flags;
mempool_t *io_pool;
mempool_t *tio_pool;
+ struct bio_set *bs;
+
/*
* Event handling.
*/
static kmem_cache_t *_io_cache;
static kmem_cache_t *_tio_cache;
-static struct bio_set *dm_set;
-
static int __init local_init(void)
{
int r;
- dm_set = bioset_create(16, 16, 4);
- if (!dm_set)
- return -ENOMEM;
-
/* allocate a slab for the dm_ios */
_io_cache = kmem_cache_create("dm_io",
sizeof(struct dm_io), 0, 0, NULL, NULL);
kmem_cache_destroy(_tio_cache);
kmem_cache_destroy(_io_cache);
- bioset_free(dm_set);
-
if (unregister_blkdev(_major, _name) < 0)
- DMERR("devfs_unregister_blkdev failed");
+ DMERR("unregister_blkdev failed");
_major = 0;
if (!md)
goto out;
- if (test_bit(DMF_FREEING, &md->flags)) {
+ 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);
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_target(map, 0);
+
+ if (dm_suspended(md)) {
+ r = -EAGAIN;
+ goto out;
+ }
+
+ if (tgt->type->ioctl)
+ r = tgt->type->ioctl(tgt, inode, file, cmd, arg);
+
+out:
+ dm_table_put(map);
+
+ lock_kernel();
+ return r;
+}
+
static inline struct dm_io *alloc_io(struct mapped_device *md)
{
return mempool_alloc(md->io_pool, GFP_NOIO);
{
int r = 0;
struct target_io *tio = bio->bi_private;
- struct dm_io *io = tio->io;
+ struct mapped_device *md = tio->io->md;
dm_endio_fn endio = tio->ti->type->end_io;
if (bio->bi_size)
return 1;
}
- free_tio(io->md, tio);
- dec_pending(io, error);
+ dec_pending(tio->io, error);
+
+ /*
+ * Store md for cleanup instead of tio which is about to get freed.
+ */
+ bio->bi_private = md->bs;
+
bio_put(bio);
+ free_tio(md, tio);
return r;
}
{
int r;
sector_t sector;
+ struct mapped_device *md;
/*
* Sanity checks.
if (r > 0) {
/* the bio has been remapped so dispatch it */
- blk_add_trace_remap(bdev_get_queue(clone->bi_bdev), clone,
- tio->io->bio->bi_bdev->bd_dev, sector,
+ blk_add_trace_remap(bdev_get_queue(clone->bi_bdev), clone,
+ tio->io->bio->bi_bdev->bd_dev, sector,
clone->bi_sector);
generic_make_request(clone);
else if (r < 0) {
/* error the io and bail out */
- struct dm_io *io = tio->io;
- free_tio(tio->io->md, tio);
- dec_pending(io, r);
+ md = tio->io->md;
+ dec_pending(tio->io, r);
+ /*
+ * Store bio_set for cleanup.
+ */
+ clone->bi_private = md->bs;
bio_put(clone);
+ free_tio(md, tio);
}
}
static void dm_bio_destructor(struct bio *bio)
{
- bio_free(bio, dm_set);
+ struct bio_set *bs = bio->bi_private;
+
+ bio_free(bio, bs);
}
/*
*/
static struct bio *split_bvec(struct bio *bio, sector_t sector,
unsigned short idx, unsigned int offset,
- unsigned int len)
+ unsigned int len, struct bio_set *bs)
{
struct bio *clone;
struct bio_vec *bv = bio->bi_io_vec + idx;
- clone = bio_alloc_bioset(GFP_NOIO, 1, dm_set);
+ clone = bio_alloc_bioset(GFP_NOIO, 1, bs);
clone->bi_destructor = dm_bio_destructor;
*clone->bi_io_vec = *bv;
*/
static struct bio *clone_bio(struct bio *bio, sector_t sector,
unsigned short idx, unsigned short bv_count,
- unsigned int len)
+ unsigned int len, struct bio_set *bs)
{
struct bio *clone;
- clone = bio_clone(bio, GFP_NOIO);
+ clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs);
+ __bio_clone(clone, bio);
+ clone->bi_destructor = dm_bio_destructor;
clone->bi_sector = sector;
clone->bi_idx = idx;
clone->bi_vcnt = idx + bv_count;
* the remaining io with a single clone.
*/
clone = clone_bio(bio, ci->sector, ci->idx,
- bio->bi_vcnt - ci->idx, ci->sector_count);
+ bio->bi_vcnt - ci->idx, ci->sector_count,
+ ci->md->bs);
__map_bio(ti, clone, tio);
ci->sector_count = 0;
len += bv_len;
}
- clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len);
+ clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len,
+ ci->md->bs);
__map_bio(ti, clone, tio);
ci->sector += len;
len = min(remaining, max);
clone = split_bvec(bio, ci->sector, ci->idx,
- bv->bv_offset + offset, len);
+ bv->bv_offset + offset, len,
+ ci->md->bs);
__map_bio(ti, clone, tio);
*---------------------------------------------------------------*/
static DEFINE_IDR(_minor_idr);
-static void free_minor(unsigned int minor)
+static void free_minor(int minor)
{
spin_lock(&_minor_lock);
idr_remove(&_minor_idr, minor);
/*
* See if the device with a specific minor # is free.
*/
-static int specific_minor(struct mapped_device *md, unsigned int minor)
+static int specific_minor(struct mapped_device *md, int minor)
{
int r, m;
return r;
}
-static int next_free_minor(struct mapped_device *md, unsigned int *minor)
+static int next_free_minor(struct mapped_device *md, int *minor)
{
- int r;
- unsigned int m;
+ int r, m;
r = idr_pre_get(&_minor_idr, GFP_KERNEL);
if (!r)
/*
* Allocate and initialise a blank device with a given minor.
*/
-static struct mapped_device *alloc_dev(unsigned int minor, int persistent)
+static struct mapped_device *alloc_dev(int minor)
{
int r;
struct mapped_device *md = kmalloc(sizeof(*md), GFP_KERNEL);
goto bad0;
/* get a minor number for the dev */
- r = persistent ? specific_minor(md, minor) : next_free_minor(md, &minor);
+ if (minor == DM_ANY_MINOR)
+ r = next_free_minor(md, &minor);
+ else
+ r = specific_minor(md, minor);
if (r < 0)
goto bad1;
init_MUTEX(&md->suspend_lock);
rwlock_init(&md->map_lock);
atomic_set(&md->holders, 1);
+ atomic_set(&md->open_count, 0);
atomic_set(&md->event_nr, 0);
md->queue = blk_alloc_queue(GFP_KERNEL);
if (!md->queue)
- goto bad1;
+ goto bad1_free_minor;
md->queue->queuedata = md;
md->queue->backing_dev_info.congested_fn = dm_any_congested;
if (!md->tio_pool)
goto bad3;
+ md->bs = bioset_create(16, 16, 4);
+ if (!md->bs)
+ goto bad_no_bioset;
+
md->disk = alloc_disk(1);
if (!md->disk)
goto bad4;
+ atomic_set(&md->pending, 0);
+ init_waitqueue_head(&md->wait);
+ init_waitqueue_head(&md->eventq);
+
md->disk->major = _major;
md->disk->first_minor = minor;
md->disk->fops = &dm_blk_dops;
add_disk(md->disk);
format_dev_t(md->name, MKDEV(_major, minor));
- atomic_set(&md->pending, 0);
- init_waitqueue_head(&md->wait);
- init_waitqueue_head(&md->eventq);
-
/* Populate the mapping, nobody knows we exist yet */
spin_lock(&_minor_lock);
old_md = idr_replace(&_minor_idr, md, minor);
return md;
bad4:
+ bioset_free(md->bs);
+ bad_no_bioset:
mempool_destroy(md->tio_pool);
bad3:
mempool_destroy(md->io_pool);
bad2:
blk_cleanup_queue(md->queue);
+ bad1_free_minor:
free_minor(minor);
bad1:
module_put(THIS_MODULE);
static void free_dev(struct mapped_device *md)
{
- unsigned int minor = md->disk->first_minor;
+ int minor = md->disk->first_minor;
if (md->suspended_bdev) {
thaw_bdev(md->suspended_bdev, NULL);
}
mempool_destroy(md->tio_pool);
mempool_destroy(md->io_pool);
+ bioset_free(md->bs);
del_gendisk(md->disk);
free_minor(minor);
/*
* Constructor for a new device.
*/
-static int create_aux(unsigned int minor, int persistent,
- struct mapped_device **result)
+int dm_create(int minor, struct mapped_device **result)
{
struct mapped_device *md;
- md = alloc_dev(minor, persistent);
+ md = alloc_dev(minor);
if (!md)
return -ENXIO;
return 0;
}
-int dm_create(struct mapped_device **result)
-{
- return create_aux(0, 0, result);
-}
-
-int dm_create_with_minor(unsigned int minor, struct mapped_device **result)
-{
- return create_aux(minor, 1, result);
-}
-
static struct mapped_device *dm_find_md(dev_t dev)
{
struct mapped_device *md;
md = idr_find(&_minor_idr, minor);
if (md && (md == MINOR_ALLOCED ||
(dm_disk(md)->first_minor != minor) ||
- test_bit(DMF_FREEING, &md->flags))) {
+ test_bit(DMF_FREEING, &md->flags))) {
md = NULL;
goto out;
}
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;
if (!map || !dm_table_get_size(map))
goto out;
- dm_table_resume_targets(map);
+ r = dm_table_resume_targets(map);
+ if (r)
+ goto out;
down_write(&md->io_lock);
clear_bit(DMF_BLOCK_IO, &md->flags);
dm_table_unplug_all(map);
+ kobject_uevent(&md->disk->kobj, KOBJ_CHANGE);
+
r = 0;
out:
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
};