path: root/drivers/md/md.c
diff options
authorNeilBrown <neilb@suse.de>2009-01-09 08:31:10 +1100
committerNeilBrown <neilb@suse.de>2009-01-09 08:31:10 +1100
commitd3374825ce57ba2214d375023979f6197ccc1385 (patch)
tree441ea927a7c702e4eadeafbac8be97d664bfb83b /drivers/md/md.c
parentmd: centralise all freeing of an 'mddev' in 'md_free' (diff)
md: make devices disappear when they are no longer needed.
Currently md devices, once created, never disappear until the module is unloaded. This is essentially because the gendisk holds a reference to the mddev, and the mddev holds a reference to the gendisk, this a circular reference. If we drop the reference from mddev to gendisk, then we need to ensure that the mddev is destroyed when the gendisk is destroyed. However it is not possible to hook into the gendisk destruction process to enable this. So we drop the reference from the gendisk to the mddev and destroy the gendisk when the mddev gets destroyed. However this has a complication. Between the call __blkdev_get->get_gendisk->kobj_lookup->md_probe and the call __blkdev_get->md_open there is no obvious way to hold a reference on the mddev any more, so unless something is done, it will disappear and gendisk will be destroyed prematurely. Also, once we decide to destroy the mddev, there will be an unlockable moment before the gendisk is unlinked (blk_unregister_region) during which a new reference to the gendisk can be created. We need to ensure that this reference can not be used. i.e. the ->open must fail. So: 1/ in md_probe we set a flag in the mddev (hold_active) which indicates that the array should be treated as active, even though there are no references, and no appearance of activity. This is cleared by md_release when the device is closed if it is no longer needed. This ensures that the gendisk will survive between md_probe and md_open. 2/ In md_open we check if the mddev we expect to open matches the gendisk that we did open. If there is a mismatch we return -ERESTARTSYS and modify __blkdev_get to retry from the top in that case. In the -ERESTARTSYS sys case we make sure to wait until the old gendisk (that we succeeded in opening) is really gone so we loop at most once. Some udev configurations will always open an md device when it first appears. If we allow an md device that was just created by an open to disappear on an immediate close, then this can race with such udev configurations and result in an infinite loop the device being opened and closed, then re-open due to the 'ADD' even from the first open, and then close and so on. So we make sure an md device, once created by an open, remains active at least until some md 'ioctl' has been made on it. This means that all normal usage of md devices will allow them to disappear promptly when not needed, but the worst that an incorrect usage will do it cause an inactive md device to be left in existence (it can easily be removed). As an array can be stopped by writing to a sysfs attribute echo clear > /sys/block/mdXXX/md/array_state we need to use scheduled work for deleting the gendisk and other kobjects. This allows us to wait for any pending gendisk deletion to complete by simply calling flush_scheduled_work(). Signed-off-by: NeilBrown <neilb@suse.de>
Diffstat (limited to 'drivers/md/md.c')
1 files changed, 49 insertions, 12 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 970a8c42ba92..38697283aaf4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -214,16 +214,33 @@ static inline mddev_t *mddev_get(mddev_t *mddev)
return mddev;
+static void mddev_delayed_delete(struct work_struct *ws)
+ mddev_t *mddev = container_of(ws, mddev_t, del_work);
+ kobject_del(&mddev->kobj);
+ kobject_put(&mddev->kobj);
static void mddev_put(mddev_t *mddev)
if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
- if (!mddev->raid_disks && list_empty(&mddev->disks)) {
+ if (!mddev->raid_disks && list_empty(&mddev->disks) &&
+ !mddev->hold_active) {
- spin_unlock(&all_mddevs_lock);
- kobject_put(&mddev->kobj);
- } else
- spin_unlock(&all_mddevs_lock);
+ if (mddev->gendisk) {
+ /* we did a probe so need to clean up.
+ * Call schedule_work inside the spinlock
+ * so that flush_scheduled_work() after
+ * mddev_find will succeed in waiting for the
+ * work to be done.
+ */
+ INIT_WORK(&mddev->del_work, mddev_delayed_delete);
+ schedule_work(&mddev->del_work);
+ } else
+ kfree(mddev);
+ }
+ spin_unlock(&all_mddevs_lock);
static mddev_t * mddev_find(dev_t unit)
@@ -242,6 +259,7 @@ static mddev_t * mddev_find(dev_t unit)
if (new) {
list_add(&new->all_mddevs, &all_mddevs);
+ mddev->hold_active = UNTIL_IOCTL;
return new;
@@ -3435,6 +3453,8 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
rv = mddev_lock(mddev);
+ if (mddev->hold_active == UNTIL_IOCTL)
+ mddev->hold_active = 0;
if (!rv) {
rv = entry->store(mddev, page, length);
@@ -3484,6 +3504,11 @@ static struct kobject *md_probe(dev_t dev, int *part, void *data)
if (!mddev)
return NULL;
+ /* wait for any previous instance if this device
+ * to be completed removed (mddev_delayed_delete).
+ */
+ flush_scheduled_work();
if (mddev->gendisk) {
@@ -3520,7 +3545,7 @@ static struct kobject *md_probe(dev_t dev, int *part, void *data)
disk->private_data = mddev;
disk->queue = mddev->queue;
/* Allow extended partitions. This makes the
- * 'mdp' device redundant, but we can really
+ * 'mdp' device redundant, but we can't really
* remove it now.
disk->flags |= GENHD_FL_EXT_DEVT;
@@ -3536,6 +3561,7 @@ static struct kobject *md_probe(dev_t dev, int *part, void *data)
kobject_uevent(&mddev->kobj, KOBJ_ADD);
mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, "array_state");
+ mddev_put(mddev);
return NULL;
@@ -5054,6 +5080,9 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
+ if (mddev->hold_active == UNTIL_IOCTL &&
+ err != -EINVAL)
+ mddev->hold_active = 0;
return err;
@@ -5070,14 +5099,25 @@ static int md_open(struct block_device *bdev, fmode_t mode)
* Succeed if we can lock the mddev, which confirms that
* it isn't being stopped right now.
- mddev_t *mddev = bdev->bd_disk->private_data;
+ mddev_t *mddev = mddev_find(bdev->bd_dev);
int err;
+ if (mddev->gendisk != bdev->bd_disk) {
+ /* we are racing with mddev_put which is discarding this
+ * bd_disk.
+ */
+ mddev_put(mddev);
+ /* Wait until bdev->bd_disk is definitely gone */
+ flush_scheduled_work();
+ /* Then retry the open from the top */
+ return -ERESTARTSYS;
+ }
+ BUG_ON(mddev != bdev->bd_disk->private_data);
if ((err = mutex_lock_interruptible_nested(&mddev->reconfig_mutex, 1)))
goto out;
err = 0;
- mddev_get(mddev);
@@ -6436,11 +6476,8 @@ static __exit void md_exit(void)
remove_proc_entry("mdstat", NULL);
for_each_mddev(mddev, tmp) {
- struct gendisk *disk = mddev->gendisk;
- if (!disk)
- continue;
- mddev_put(mddev);
+ mddev->hold_active = 0;