md: only delete entries from all_mddevs when the disk is freed

This ensures device names don't get prematurely reused.  Instead add a
deleted flag to skip already deleted devices in mddev_get and other
places that only want to see live mddevs.

Reported-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Christoph Hellwig 2022-07-19 11:18:23 +02:00 committed by Jens Axboe
parent 16648bac86
commit 12a6caf273
2 changed files with 40 additions and 18 deletions

View File

@ -625,6 +625,10 @@ EXPORT_SYMBOL(md_flush_request);
static inline struct mddev *mddev_get(struct mddev *mddev)
{
lockdep_assert_held(&all_mddevs_lock);
if (test_bit(MD_DELETED, &mddev->flags))
return NULL;
atomic_inc(&mddev->active);
return mddev;
}
@ -639,7 +643,7 @@ static void mddev_put(struct mddev *mddev)
mddev->ctime == 0 && !mddev->hold_active) {
/* Array is not configured at all, and not held active,
* so destroy it */
list_del_init(&mddev->all_mddevs);
set_bit(MD_DELETED, &mddev->flags);
/*
* Call queue_work inside the spinlock so that
@ -719,8 +723,8 @@ static struct mddev *mddev_find(dev_t unit)
spin_lock(&all_mddevs_lock);
mddev = mddev_find_locked(unit);
if (mddev)
mddev_get(mddev);
if (mddev && !mddev_get(mddev))
mddev = NULL;
spin_unlock(&all_mddevs_lock);
return mddev;
@ -3338,6 +3342,8 @@ static bool md_rdev_overlaps(struct md_rdev *rdev)
spin_lock(&all_mddevs_lock);
list_for_each_entry(mddev, &all_mddevs, all_mddevs) {
if (test_bit(MD_DELETED, &mddev->flags))
continue;
rdev_for_each(rdev2, mddev) {
if (rdev != rdev2 && rdev->bdev == rdev2->bdev &&
md_rdevs_overlap(rdev, rdev2)) {
@ -5525,11 +5531,10 @@ md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
if (!entry->show)
return -EIO;
spin_lock(&all_mddevs_lock);
if (list_empty(&mddev->all_mddevs)) {
if (!mddev_get(mddev)) {
spin_unlock(&all_mddevs_lock);
return -EBUSY;
}
mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
rv = entry->show(mddev, page);
@ -5550,11 +5555,10 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
spin_lock(&all_mddevs_lock);
if (list_empty(&mddev->all_mddevs)) {
if (!mddev_get(mddev)) {
spin_unlock(&all_mddevs_lock);
return -EBUSY;
}
mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
rv = entry->store(mddev, page, length);
mddev_put(mddev);
@ -7849,7 +7853,7 @@ static void md_free_disk(struct gendisk *disk)
bioset_exit(&mddev->bio_set);
bioset_exit(&mddev->sync_set);
kfree(mddev);
mddev_free(mddev);
}
const struct block_device_operations md_fops =
@ -8171,6 +8175,8 @@ static void *md_seq_start(struct seq_file *seq, loff_t *pos)
if (!l--) {
mddev = list_entry(tmp, struct mddev, all_mddevs);
mddev_get(mddev);
if (!mddev_get(mddev))
continue;
spin_unlock(&all_mddevs_lock);
return mddev;
}
@ -8184,25 +8190,35 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct list_head *tmp;
struct mddev *next_mddev, *mddev = v;
struct mddev *to_put = NULL;
++*pos;
if (v == (void*)2)
return NULL;
spin_lock(&all_mddevs_lock);
if (v == (void*)1)
if (v == (void*)1) {
tmp = all_mddevs.next;
else
} else {
to_put = mddev;
tmp = mddev->all_mddevs.next;
if (tmp != &all_mddevs)
next_mddev = mddev_get(list_entry(tmp,struct mddev,all_mddevs));
else {
next_mddev = (void*)2;
*pos = 0x10000;
}
for (;;) {
if (tmp == &all_mddevs) {
next_mddev = (void*)2;
*pos = 0x10000;
break;
}
next_mddev = list_entry(tmp, struct mddev, all_mddevs);
if (mddev_get(next_mddev))
break;
mddev = next_mddev;
tmp = mddev->all_mddevs.next;
};
spin_unlock(&all_mddevs_lock);
if (v != (void*)1)
if (to_put)
mddev_put(mddev);
return next_mddev;
@ -8766,6 +8782,8 @@ void md_do_sync(struct md_thread *thread)
goto skip;
spin_lock(&all_mddevs_lock);
list_for_each_entry(mddev2, &all_mddevs, all_mddevs) {
if (test_bit(MD_DELETED, &mddev2->flags))
continue;
if (mddev2 == mddev)
continue;
if (!mddev->parallel_resync
@ -9568,7 +9586,8 @@ static int md_notify_reboot(struct notifier_block *this,
spin_lock(&all_mddevs_lock);
list_for_each_entry_safe(mddev, n, &all_mddevs, all_mddevs) {
mddev_get(mddev);
if (!mddev_get(mddev))
continue;
spin_unlock(&all_mddevs_lock);
if (mddev_trylock(mddev)) {
if (mddev->pers)
@ -9923,7 +9942,8 @@ static __exit void md_exit(void)
spin_lock(&all_mddevs_lock);
list_for_each_entry_safe(mddev, n, &all_mddevs, all_mddevs) {
mddev_get(mddev);
if (!mddev_get(mddev))
continue;
spin_unlock(&all_mddevs_lock);
export_array(mddev);
mddev->ctime = 0;

View File

@ -254,6 +254,7 @@ struct md_cluster_info;
* @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that
* array is ready yet.
* @MD_BROKEN: This is used to stop writes and mark array as failed.
* @MD_DELETED: This device is being deleted
*
* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added
*/
@ -270,6 +271,7 @@ enum mddev_flags {
MD_UPDATING_SB,
MD_NOT_READY,
MD_BROKEN,
MD_DELETED,
};
enum mddev_sb_flags {