ext4: add basic fs-verity support

Add most of fs-verity support to ext4.  fs-verity is a filesystem
feature that enables transparent integrity protection and authentication
of read-only files.  It uses a dm-verity like mechanism at the file
level: a Merkle tree is used to verify any block in the file in
log(filesize) time.  It is implemented mainly by helper functions in
fs/verity/.  See Documentation/filesystems/fsverity.rst for the full
documentation.

This commit adds all of ext4 fs-verity support except for the actual
data verification, including:

- Adding a filesystem feature flag and an inode flag for fs-verity.

- Implementing the fsverity_operations to support enabling verity on an
  inode and reading/writing the verity metadata.

- Updating ->write_begin(), ->write_end(), and ->writepages() to support
  writing verity metadata pages.

- Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl().

ext4 stores the verity metadata (Merkle tree and fsverity_descriptor)
past the end of the file, starting at the first 64K boundary beyond
i_size.  This approach works because (a) verity files are readonly, and
(b) pages fully beyond i_size aren't visible to userspace but can be
read/written internally by ext4 with only some relatively small changes
to ext4.  This approach avoids having to depend on the EA_INODE feature
and on rearchitecturing ext4's xattr support to support paging
multi-gigabyte xattrs into memory, and to support encrypting xattrs.
Note that the verity metadata *must* be encrypted when the file is,
since it contains hashes of the plaintext data.

This patch incorporates work by Theodore Ts'o and Chandan Rajendra.

Reviewed-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Eric Biggers <ebiggers@google.com>

1 files changed, 38 insertions, 15 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 420fe3deed39..6de3d4ba28f3 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1340,6 +1340,9 @@ retry_journal:
 	}
 
 	if (ret) {
+		bool extended = (pos + len > inode->i_size) &&
+				!ext4_verity_in_progress(inode);
+
 		unlock_page(page);
 		/*
 		 * __block_write_begin may have instantiated a few blocks
@@ -1349,11 +1352,11 @@ retry_journal:
 		 * Add inode to orphan list in case we crash before
 		 * truncate finishes
 		 */
-		if (pos + len > inode->i_size && ext4_can_truncate(inode))
+		if (extended && ext4_can_truncate(inode))
 			ext4_orphan_add(handle, inode);
 
 		ext4_journal_stop(handle);
-		if (pos + len > inode->i_size) {
+		if (extended) {
 			ext4_truncate_failed_write(inode);
 			/*
 			 * If truncate failed early the inode might
@@ -1406,6 +1409,7 @@ static int ext4_write_end(struct file *file,
 	int ret = 0, ret2;
 	int i_size_changed = 0;
 	int inline_data = ext4_has_inline_data(inode);
+	bool verity = ext4_verity_in_progress(inode);
 
 	trace_ext4_write_end(inode, pos, len, copied);
 	if (inline_data) {
@@ -1423,12 +1427,16 @@ static int ext4_write_end(struct file *file,
 	/*
 	 * it's important to update i_size while still holding page lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
+	 *
+	 * If FS_IOC_ENABLE_VERITY is running on this inode, then Merkle tree
+	 * blocks are being written past EOF, so skip the i_size update.
 	 */
-	i_size_changed = ext4_update_inode_size(inode, pos + copied);
+	if (!verity)
+		i_size_changed = ext4_update_inode_size(inode, pos + copied);
 	unlock_page(page);
 	put_page(page);
 
-	if (old_size < pos)
+	if (old_size < pos && !verity)
 		pagecache_isize_extended(inode, old_size, pos);
 	/*
 	 * Don't mark the inode dirty under page lock. First, it unnecessarily
@@ -1439,7 +1447,7 @@ static int ext4_write_end(struct file *file,
 	if (i_size_changed || inline_data)
 		ext4_mark_inode_dirty(handle, inode);
 
-	if (pos + len > inode->i_size && ext4_can_truncate(inode))
+	if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
 		 * inode->i_size. So truncate them
@@ -1450,7 +1458,7 @@ errout:
 	if (!ret)
 		ret = ret2;
 
-	if (pos + len > inode->i_size) {
+	if (pos + len > inode->i_size && !verity) {
 		ext4_truncate_failed_write(inode);
 		/*
 		 * If truncate failed early the inode might still be
@@ -1511,6 +1519,7 @@ static int ext4_journalled_write_end(struct file *file,
 	unsigned from, to;
 	int size_changed = 0;
 	int inline_data = ext4_has_inline_data(inode);
+	bool verity = ext4_verity_in_progress(inode);
 
 	trace_ext4_journalled_write_end(inode, pos, len, copied);
 	from = pos & (PAGE_SIZE - 1);
@@ -1540,13 +1549,14 @@ static int ext4_journalled_write_end(struct file *file,
 		if (!partial)
 			SetPageUptodate(page);
 	}
-	size_changed = ext4_update_inode_size(inode, pos + copied);
+	if (!verity)
+		size_changed = ext4_update_inode_size(inode, pos + copied);
 	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 	EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
 	unlock_page(page);
 	put_page(page);
 
-	if (old_size < pos)
+	if (old_size < pos && !verity)
 		pagecache_isize_extended(inode, old_size, pos);
 
 	if (size_changed || inline_data) {
@@ -1555,7 +1565,7 @@ static int ext4_journalled_write_end(struct file *file,
 			ret = ret2;
 	}
 
-	if (pos + len > inode->i_size && ext4_can_truncate(inode))
+	if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
 		 * inode->i_size. So truncate them
@@ -1566,7 +1576,7 @@ errout:
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
-	if (pos + len > inode->i_size) {
+	if (pos + len > inode->i_size && !verity) {
 		ext4_truncate_failed_write(inode);
 		/*
 		 * If truncate failed early the inode might still be
@@ -2162,7 +2172,8 @@ static int ext4_writepage(struct page *page,
 
 	trace_ext4_writepage(page);
 	size = i_size_read(inode);
-	if (page->index == size >> PAGE_SHIFT)
+	if (page->index == size >> PAGE_SHIFT &&
+	    !ext4_verity_in_progress(inode))
 		len = size & ~PAGE_MASK;
 	else
 		len = PAGE_SIZE;
@@ -2246,7 +2257,8 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 	 * after page tables are updated.
 	 */
 	size = i_size_read(mpd->inode);
-	if (page->index == size >> PAGE_SHIFT)
+	if (page->index == size >> PAGE_SHIFT &&
+	    !ext4_verity_in_progress(mpd->inode))
 		len = size & ~PAGE_MASK;
 	else
 		len = PAGE_SIZE;
@@ -2345,6 +2357,9 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 	ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1)
 							>> inode->i_blkbits;
 
+	if (ext4_verity_in_progress(inode))
+		blocks = EXT_MAX_BLOCKS;
+
 	do {
 		BUG_ON(buffer_locked(bh));
 
@@ -3061,8 +3076,8 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 
 	index = pos >> PAGE_SHIFT;
 
-	if (ext4_nonda_switch(inode->i_sb) ||
-	    S_ISLNK(inode->i_mode)) {
+	if (ext4_nonda_switch(inode->i_sb) || S_ISLNK(inode->i_mode) ||
+	    ext4_verity_in_progress(inode)) {
 		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
 		return ext4_write_begin(file, mapping, pos,
 					len, flags, pagep, fsdata);
@@ -4739,6 +4754,8 @@ static bool ext4_should_use_dax(struct inode *inode)
 		return false;
 	if (ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT))
 		return false;
+	if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY))
+		return false;
 	return true;
 }
 
@@ -4763,9 +4780,11 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_ENCRYPTED;
 	if (flags & EXT4_CASEFOLD_FL)
 		new_fl |= S_CASEFOLD;
+	if (flags & EXT4_VERITY_FL)
+		new_fl |= S_VERITY;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX|
-			S_ENCRYPTED|S_CASEFOLD);
+			S_ENCRYPTED|S_CASEFOLD|S_VERITY);
 }
 
 static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
@@ -5555,6 +5574,10 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	if (error)
 		return error;
 
+	error = fsverity_prepare_setattr(dentry, attr);
+	if (error)
+		return error;
+
 	if (is_quota_modification(inode, attr)) {
 		error = dquot_initialize(inode);
 		if (error)