btrfs: initial fsverity support

Add support for fsverity in btrfs. To support the generic interface in
fs/verity, we add two new item types in the fs tree for inodes with
verity enabled. One stores the per-file verity descriptor and btrfs
verity item and the other stores the Merkle tree data itself.

Verity checking is done in end_page_read just before a page is marked
uptodate. This naturally handles a variety of edge cases like holes,
preallocated extents, and inline extents. Some care needs to be taken to
not try to verity pages past the end of the file, which are accessed by
the generic buffered file reading code under some circumstances like
reading to the end of the last page and trying to read again. Direct IO
on a verity file falls back to buffered reads.

Verity relies on PageChecked for the Merkle tree data itself to avoid
re-walking up shared paths in the tree. For this reason, we need to
cache the Merkle tree data. Since the file is immutable after verity is
turned on, we can cache it at an index past EOF.

Use the new inode ro_flags to store verity on the inode item, so that we
can enable verity on a file, then rollback to an older kernel and still
mount the file system and read the file. Since we can't safely write the
file anymore without ruining the invariants of the Merkle tree, we mark
a ro_compat flag on the file system when a file has verity enabled.

Acked-by: Eric Biggers <ebiggers@google.com>
Co-developed-by: Chris Mason <clm@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 35 insertions, 0 deletions

diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index ccdb40fe40dc..e1c4c732aaba 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -118,6 +118,29 @@
 #define BTRFS_INODE_REF_KEY		12
 #define BTRFS_INODE_EXTREF_KEY		13
 #define BTRFS_XATTR_ITEM_KEY		24
+
+/*
+ * fs verity items are stored under two different key types on disk.
+ * The descriptor items:
+ * [ inode objectid, BTRFS_VERITY_DESC_ITEM_KEY, offset ]
+ *
+ * At offset 0, we store a btrfs_verity_descriptor_item which tracks the size
+ * of the descriptor item and some extra data for encryption.
+ * Starting at offset 1, these hold the generic fs verity descriptor.  The
+ * latter are opaque to btrfs, we just read and write them as a blob for the
+ * higher level verity code.  The most common descriptor size is 256 bytes.
+ *
+ * The merkle tree items:
+ * [ inode objectid, BTRFS_VERITY_MERKLE_ITEM_KEY, offset ]
+ *
+ * These also start at offset 0, and correspond to the merkle tree bytes.  When
+ * fsverity asks for page 0 of the merkle tree, we pull up one page starting at
+ * offset 0 for this key type.  These are also opaque to btrfs, we're blindly
+ * storing whatever fsverity sends down.
+ */
+#define BTRFS_VERITY_DESC_ITEM_KEY	36
+#define BTRFS_VERITY_MERKLE_ITEM_KEY	37
+
 #define BTRFS_ORPHAN_ITEM_KEY		48
 /* reserve 2-15 close to the inode for later flexibility */
 
@@ -991,4 +1014,16 @@ struct btrfs_qgroup_limit_item {
 	__le64 rsv_excl;
 } __attribute__ ((__packed__));
 
+struct btrfs_verity_descriptor_item {
+	/* Size of the verity descriptor in bytes */
+	__le64 size;
+	/*
+	 * When we implement support for fscrypt, we will need to encrypt the
+	 * Merkle tree for encrypted verity files. These 128 bits are for the
+	 * eventual storage of an fscrypt initialization vector.
+	 */
+	__le64 reserved[2];
+	__u8 encryption;
+} __attribute__ ((__packed__));
+
 #endif /* _BTRFS_CTREE_H_ */