btrfs: allocate raid type kobjects dynamically

We are currently allocating space_info objects in an array when we
allocate space_info. When a user does something like:

# btrfs balance start -mconvert=raid1 -dconvert=raid1 /mnt
# btrfs balance start -mconvert=single -dconvert=single /mnt -f
# btrfs balance start -mconvert=raid1 -dconvert=raid1 /

We can end up with memory corruption since the kobject hasn't
been reinitialized properly and the name pointer was left set.

The rationale behind allocating them statically was to avoid
creating a separate kobject container that just contained the
raid type. It used the index in the array to determine the index.

Ultimately, though, this wastes more memory than it saves in all
but the most complex scenarios and introduces kobject lifetime
questions.

This patch allocates the kobjects dynamically instead. Note that
we also remove the kobject_get/put of the parent kobject since
kobject_add and kobject_del do that internally.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Reported-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>

1 files changed, 26 insertions, 13 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 6caddd5970e4..fafb3e53ecde 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3497,10 +3497,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 		return ret;
 	}
 
-	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
+	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++)
 		INIT_LIST_HEAD(&found->block_groups[i]);
-		kobject_init(&found->block_group_kobjs[i], &btrfs_raid_ktype);
-	}
 	init_rwsem(&found->groups_sem);
 	spin_lock_init(&found->lock);
 	found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
@@ -8586,8 +8584,9 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		list_del(&space_info->list);
 		for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
 			struct kobject *kobj;
-			kobj = &space_info->block_group_kobjs[i];
-			if (kobj->parent) {
+			kobj = space_info->block_group_kobjs[i];
+			space_info->block_group_kobjs[i] = NULL;
+			if (kobj) {
 				kobject_del(kobj);
 				kobject_put(kobj);
 			}
@@ -8611,17 +8610,26 @@ static void __link_block_group(struct btrfs_space_info *space_info,
 	up_write(&space_info->groups_sem);
 
 	if (first) {
-		struct kobject *kobj = &space_info->block_group_kobjs[index];
+		struct raid_kobject *rkobj;
 		int ret;
 
-		kobject_get(&space_info->kobj); /* put in release */
-		ret = kobject_add(kobj, &space_info->kobj, "%s",
-				  get_raid_name(index));
+		rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS);
+		if (!rkobj)
+			goto out_err;
+		rkobj->raid_type = index;
+		kobject_init(&rkobj->kobj, &btrfs_raid_ktype);
+		ret = kobject_add(&rkobj->kobj, &space_info->kobj,
+				  "%s", get_raid_name(index));
 		if (ret) {
-			pr_warn("BTRFS: failed to add kobject for block cache. ignoring.\n");
-			kobject_put(&space_info->kobj);
+			kobject_put(&rkobj->kobj);
+			goto out_err;
 		}
+		space_info->block_group_kobjs[index] = &rkobj->kobj;
 	}
+
+	return;
+out_err:
+	pr_warn("BTRFS: failed to add kobject for block cache. ignoring.\n");
 }
 
 static struct btrfs_block_group_cache *
@@ -8956,6 +8964,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	struct btrfs_root *tree_root = root->fs_info->tree_root;
 	struct btrfs_key key;
 	struct inode *inode;
+	struct kobject *kobj = NULL;
 	int ret;
 	int index;
 	int factor;
@@ -9055,11 +9064,15 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 */
 	list_del_init(&block_group->list);
 	if (list_empty(&block_group->space_info->block_groups[index])) {
-		kobject_del(&block_group->space_info->block_group_kobjs[index]);
-		kobject_put(&block_group->space_info->block_group_kobjs[index]);
+		kobj = block_group->space_info->block_group_kobjs[index];
+		block_group->space_info->block_group_kobjs[index] = NULL;
 		clear_avail_alloc_bits(root->fs_info, block_group->flags);
 	}
 	up_write(&block_group->space_info->groups_sem);
+	if (kobj) {
+		kobject_del(kobj);
+		kobject_put(kobj);
+	}
 
 	if (block_group->cached == BTRFS_CACHE_STARTED)
 		wait_block_group_cache_done(block_group);