From: Neil Brown Currently md devices are created when first opened and remain in existence until the module is unloaded. This isn't a major problem, but it somewhat ugly. This patch changes the lifetime rules so that an md device will disappear on the last close if it has no state. Locking rules depend on bd_mutex being held in do_open and __blkdev_put, and on setting bd_disk->private_data to 'mddev'. There is room for a race because md_probe is called early in do_open (get_gendisk) to create the mddev. As this isn't protected by bd_mutex, a concurrent call to md_close can destroy that mddev before do_open calls md_open to get a reference on it. md_open and md_close are serialised by md_mutex so the worst that can happen is that md_open finds that the mddev structure doesn't exist after all. In this case bd_disk->private_data will be NULL, and md_open chooses to exit with -EBUSY in this case, which is arguable and appropriate result. The new 'dead' field in mddev is used to track whether it is time to destroy the mddev (if a last-close happens). It is cleared when any state is create (set_array_info) and set when the array is stopped (do_md_stop). mddev_put becomes simpler. It just destroys the mddev when the refcount hits zero. This will normally be the reference held in bd_disk->private_data. Signed-off-by: Neil Brown Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton --- drivers/md/md.c | 32 +++++++++++++++++++++++--------- include/linux/raid/md_k.h | 3 +++ 2 files changed, 26 insertions(+), 9 deletions(-) diff -puN drivers/md/md.c~md-change-lifetime-rules-for-md-devices drivers/md/md.c --- a/drivers/md/md.c~md-change-lifetime-rules-for-md-devices +++ a/drivers/md/md.c @@ -226,13 +226,14 @@ static void mddev_put(mddev_t *mddev) { if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock)) return; - if (!mddev->raid_disks && list_empty(&mddev->disks)) { - list_del(&mddev->all_mddevs); - spin_unlock(&all_mddevs_lock); - blk_cleanup_queue(mddev->queue); - kobject_unregister(&mddev->kobj); - } else - spin_unlock(&all_mddevs_lock); + list_del(&mddev->all_mddevs); + spin_unlock(&all_mddevs_lock); + + del_gendisk(mddev->gendisk); + mddev->gendisk = NULL; + blk_cleanup_queue(mddev->queue); + mddev->queue = NULL; + kobject_unregister(&mddev->kobj); } static mddev_t * mddev_find(dev_t unit) @@ -273,6 +274,7 @@ static mddev_t * mddev_find(dev_t unit) atomic_set(&new->active, 1); spin_lock_init(&new->write_lock); init_waitqueue_head(&new->sb_wait); + new->dead = 1; new->queue = blk_alloc_queue(GFP_KERNEL); if (!new->queue) { @@ -1384,6 +1386,7 @@ static int bind_rdev_to_array(mdk_rdev_t ko = &rdev->bdev->bd_disk->kobj; sysfs_create_link(&rdev->kobj, ko, "block"); bd_claim_by_disk(rdev->bdev, rdev, mddev->gendisk); + mddev->dead = 0; return 0; } @@ -3360,6 +3363,8 @@ static int do_md_stop(mddev_t * mddev, i mddev->array_size = 0; mddev->size = 0; mddev->raid_disks = 0; + mddev->dead = 1; + mddev->recovery_cp = 0; } else if (mddev->pers) @@ -4023,6 +4028,7 @@ static int set_array_info(mddev_t * mdde mddev->new_layout = mddev->layout; mddev->delta_disks = 0; + mddev->dead = 0; return 0; } @@ -4423,8 +4429,12 @@ static int md_open(struct inode *inode, * Succeed if we can lock the mddev, which confirms that * it isn't being stopped right now. */ - mddev_t *mddev = inode->i_bdev->bd_disk->private_data; - int err; + mddev_t *mddev; + int err = -EBUSY; + + mddev = inode->i_bdev->bd_disk->private_data; + if (!mddev) + goto out; if ((err = mutex_lock_interruptible_nested(&mddev->reconfig_mutex, 1))) goto out; @@ -4443,6 +4453,10 @@ static int md_release(struct inode *inod mddev_t *mddev = inode->i_bdev->bd_disk->private_data; BUG_ON(!mddev); + if (inode->i_bdev->bd_openers == 0 && mddev->dead) { + inode->i_bdev->bd_disk->private_data = NULL; + mddev_put(mddev); + } mddev_put(mddev); return 0; diff -puN include/linux/raid/md_k.h~md-change-lifetime-rules-for-md-devices include/linux/raid/md_k.h --- a/include/linux/raid/md_k.h~md-change-lifetime-rules-for-md-devices +++ a/include/linux/raid/md_k.h @@ -119,6 +119,9 @@ struct mddev_s #define MD_CHANGE_PENDING 2 /* superblock update in progress */ int ro; + int dead; /* array should be discarded on + * last close + */ struct gendisk *gendisk; _