@@ -3419,7 +3419,9 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
/*
* If we have an inode with links, there are a couple of
- * possibilities. Old kernels (before v3.12) used to create an
+ * possibilities:
+ *
+ * 1. Old kernels (before v3.12) used to create an
* orphan item for truncate indicating that there were possibly
* extent items past i_size that needed to be deleted. In v3.12,
* truncate was changed to update i_size in sync with the extent
@@ -3432,13 +3434,22 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
* slim, and it's a pain to do the truncate now, so just delete
* the orphan item.
*
+ * 2. We were halfway through creating fsverity metadata for the
+ * file. In that case, the orphan item represents incomplete
+ * fsverity metadata which must be cleaned up with
+ * btrfs_drop_verity_items.
+ *
* It's also possible that this orphan item was supposed to be
* deleted but wasn't. The inode number may have been reused,
* but either way, we can delete the orphan item.
*/
if (ret == -ENOENT || inode->i_nlink) {
- if (!ret)
+ if (!ret) {
+ ret = btrfs_drop_verity_items(BTRFS_I(inode));
iput(inode);
+ if (ret)
+ goto out;
+ }
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
@@ -378,6 +378,69 @@ static ssize_t read_key_bytes(struct btrfs_inode *inode, u8 key_type, u64 offset
return ret;
}
+static int add_orphan(struct btrfs_inode *inode)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = inode->root;
+ int ret = 0;
+
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+ ret = btrfs_orphan_add(trans, inode);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+ btrfs_end_transaction(trans);
+
+out:
+ return ret;
+}
+
+static int del_orphan(struct btrfs_inode *inode)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = inode->root;
+ int ret;
+
+ if (!inode->vfs_inode.i_nlink)
+ return 0;
+
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode));
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ return ret;
+ }
+
+ btrfs_end_transaction(trans);
+ return ret;
+}
+
+int btrfs_drop_verity_items(struct btrfs_inode *inode)
+{
+ int ret;
+ struct inode *ino = &inode->vfs_inode;
+ pgoff_t index;
+
+ ret = get_verity_mapping_index(ino, 0, &index);
+ if (ret)
+ return ret;
+ truncate_inode_pages(inode->vfs_inode.i_mapping, index << PAGE_SHIFT);
+
+ ret = drop_verity_items(inode, BTRFS_VERITY_DESC_ITEM_KEY);
+ if (ret)
+ return ret;
+
+ return drop_verity_items(inode, BTRFS_VERITY_MERKLE_ITEM_KEY);
+}
+
/*
* fsverity op that begins enabling verity.
* fsverity calls this to ask us to setup the inode for enabling. We
@@ -391,17 +454,13 @@ static int btrfs_begin_enable_verity(struct file *filp)
if (test_bit(BTRFS_INODE_VERITY_IN_PROGRESS, &BTRFS_I(inode)->runtime_flags))
return -EBUSY;
- /*
- * ext4 adds the inode to the orphan list here, presumably because the
- * truncate done at orphan processing time will delete partial
- * measurements. TODO: setup orphans
- */
set_bit(BTRFS_INODE_VERITY_IN_PROGRESS, &BTRFS_I(inode)->runtime_flags);
- ret = drop_verity_items(BTRFS_I(inode), BTRFS_VERITY_DESC_ITEM_KEY);
+
+ ret = btrfs_drop_verity_items(BTRFS_I(inode));
if (ret)
goto err;
- ret = drop_verity_items(BTRFS_I(inode), BTRFS_VERITY_MERKLE_ITEM_KEY);
+ ret = add_orphan(BTRFS_I(inode));
if (ret)
goto err;
@@ -428,6 +487,7 @@ static int btrfs_end_enable_verity(struct file *filp, const void *desc,
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_verity_descriptor_item item;
int ret;
+ int keep_orphan = 0;
if (desc != NULL) {
/* write out the descriptor item */
@@ -459,11 +519,20 @@ static int btrfs_end_enable_verity(struct file *filp, const void *desc,
out:
if (desc == NULL || ret) {
- /* If we failed, drop all the verity items */
- drop_verity_items(BTRFS_I(inode), BTRFS_VERITY_DESC_ITEM_KEY);
- drop_verity_items(BTRFS_I(inode), BTRFS_VERITY_MERKLE_ITEM_KEY);
+ /*
+ * If verity failed (here or in the generic code), drop all the
+ * verity items.
+ */
+ keep_orphan = btrfs_drop_verity_items(BTRFS_I(inode));
} else
btrfs_set_fs_compat_ro(root->fs_info, VERITY);
+ /*
+ * If we are handling an error, but failed to drop the verity items,
+ * we still need the orphan.
+ */
+ if (!keep_orphan)
+ del_orphan(BTRFS_I(inode));
+
clear_bit(BTRFS_INODE_VERITY_IN_PROGRESS, &BTRFS_I(inode)->runtime_flags);
return ret;
}
If we don't finish creating fsverity metadata for a file, or fail to clean up already created metadata after a failure, we could leak the verity items. To address this issue, we use the orphan mechanism. When we start enabling verity on a file, we also add an orphan item for that inode. When we are finished, we delete the orphan. However, if we are interrupted midway, the orphan will be present at mount and we can cleanup the half-formed verity state. There is a possible race with a normal unlink operation: if unlink and verity run on the same file in parallel, it is possible for verity to succeed and delete the still legitimate orphan added by unlink. Then, if we are interrupted and mount in that state, we will never clean up the inode properly. This is also possible for a file created with O_TMPFILE. Check nlink==0 before deleting to avoid this race. A final thing to note is that this is a resurrection of using orphans to signal orphaned metadata that isn't the inode itself. This makes the comment discussing deprecating that concept a bit messy in full context. Signed-off-by: Boris Burkov <boris@bur.io> --- fs/btrfs/inode.c | 15 ++++++-- fs/btrfs/verity.c | 89 +++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 92 insertions(+), 12 deletions(-)