fsverity: support enabling with tree block size < PAGE_SIZE

Make FS_IOC_ENABLE_VERITY support values of
fsverity_enable_arg::block_size other than PAGE_SIZE.

To make this possible, rework build_merkle_tree(), which was reading
data and hash pages from the file and assuming that they were the same
thing as "blocks".

For reading the data blocks, just replace the direct pagecache access
with __kernel_read(), to naturally read one block at a time.

(A disadvantage of the above is that we lose the two optimizations of
hashing the pagecache pages in-place and forcing the maximum readahead.
That shouldn't be very important, though.)

The hash block reads are a bit more difficult to handle, as the only way
to do them is through fsverity_operations::read_merkle_tree_page().

Instead, let's switch to the single-pass tree construction algorithm
that fsverity-utils uses.  This eliminates the need to read back any
hash blocks while the tree is being built, at the small cost of an extra
block-sized memory buffer per Merkle tree level.  This is probably what
I should have done originally.

Taken together, the above two changes result in page-size independent
code that is also a bit simpler than what we had before.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Andrey Albershteyn <aalbersh@redhat.com>
Tested-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Link: https://lore.kernel.org/r/20221223203638.41293-8-ebiggers@kernel.org

Documentation/filesystems/fsverity.rst

@@ -118,10 +118,11 @@ as follows:
 - ``hash_algorithm`` must be the identifier for the hash algorithm to
   use for the Merkle tree, such as FS_VERITY_HASH_ALG_SHA256.  See
   ``include/uapi/linux/fsverity.h`` for the list of possible values.
-- ``block_size`` must be the Merkle tree block size.  Currently, this
+- ``block_size`` is the Merkle tree block size, in bytes.  In Linux
-  must be equal to the system page size, which is usually 4096 bytes.
+  v6.3 and later, this can be any power of 2 between (inclusively)
-  Other sizes may be supported in the future.  This value is not
+  1024 and the minimum of the system page size and the filesystem
-  necessarily the same as the filesystem block size.
+  block size.  In earlier versions, the page size was the only allowed
+  value.
 - ``salt_size`` is the size of the salt in bytes, or 0 if no salt is
   provided.  The salt is a value that is prepended to every hashed
   block; it can be used to personalize the hashing for a particular
@@ -519,9 +520,7 @@ 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.
 
-Currently, ext4 verity only supports the case where the Merkle tree
+ext4 only allows verity on extent-based files.
-block size, filesystem block size, and page size are all the same.  It
-also only supports extent-based files.
 
 f2fs
 ----
@@ -539,11 +538,10 @@ Like ext4, f2fs stores the verity metadata (Merkle tree and
 fsverity_descriptor) past the end of the file, starting at the first
 64K boundary beyond i_size.  See explanation for ext4 above.
 Moreover, f2fs supports at most 4096 bytes of xattr entries per inode
-which wouldn't be enough for even a single Merkle tree block.
+which usually wouldn't be enough for even a single Merkle tree block.
 
-Currently, f2fs verity only supports a Merkle tree block size of 4096.
+f2fs doesn't support enabling verity on files that currently have
-Also, f2fs doesn't support enabling verity on files that currently
+atomic or volatile writes pending.
-have atomic or volatile writes pending.
 
 btrfs
 -----

fs/verity/enable.c

@@ -7,134 +7,52 @@
 
 #include "fsverity_private.h"
 
-#include <crypto/hash.h>
-#include <linux/backing-dev.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 
-/*
+struct block_buffer {
- * Read a file data page for Merkle tree construction.  Do aggressive readahead,
+	u32 filled;
- * since we're sequentially reading the entire file.
+	u8 *data;
- */
+};
-static struct page *read_file_data_page(struct file *file, pgoff_t index,
-					struct file_ra_state *ra,
-					unsigned long remaining_pages)
-{
-	DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, index);
-	struct folio *folio;
 
-	folio = __filemap_get_folio(ractl.mapping, index, FGP_ACCESSED, 0);
+/* Hash a block, writing the result to the next level's pending block buffer. */
-	if (!folio || !folio_test_uptodate(folio)) {
+static int hash_one_block(struct inode *inode,
-		if (folio)
+			  const struct merkle_tree_params *params,
-			folio_put(folio);
+			  struct ahash_request *req, struct block_buffer *cur)
-		else
-			page_cache_sync_ra(&ractl, remaining_pages);
-		folio = read_cache_folio(ractl.mapping, index, NULL, file);
-		if (IS_ERR(folio))
-			return &folio->page;
-	}
-	if (folio_test_readahead(folio))
-		page_cache_async_ra(&ractl, folio, remaining_pages);
-	return folio_file_page(folio, index);
-}
-
-static int build_merkle_tree_level(struct file *filp, unsigned int level,
-				   u64 num_blocks_to_hash,
-				   const struct merkle_tree_params *params,
-				   u8 *pending_hashes,
-				   struct ahash_request *req)
 {
-	struct inode *inode = file_inode(filp);
+	struct block_buffer *next = cur + 1;
-	const struct fsverity_operations *vops = inode->i_sb->s_vop;
-	struct file_ra_state ra = { 0 };
-	unsigned int pending_size = 0;
-	u64 dst_block_num;
-	u64 i;
 	int err;
 
-	if (WARN_ON(params->block_size != PAGE_SIZE)) /* checked earlier too */
+	/* Zero-pad the block if it's shorter than the block size. */
-		return -EINVAL;
+	memset(&cur->data[cur->filled], 0, params->block_size - cur->filled);
 
-	if (level < params->num_levels) {
+	err = fsverity_hash_block(params, inode, req, virt_to_page(cur->data),
-		dst_block_num = params->level_start[level];
+				  offset_in_page(cur->data),
-	} else {
+				  &next->data[next->filled]);
-		if (WARN_ON(num_blocks_to_hash != 1))
+	if (err)
-			return -EINVAL;
+		return err;
-		dst_block_num = 0; /* unused */
+	next->filled += params->digest_size;
-	}
+	cur->filled = 0;
-
-	file_ra_state_init(&ra, filp->f_mapping);
-
-	for (i = 0; i < num_blocks_to_hash; i++) {
-		struct page *src_page;
-
-		if (level == 0) {
-			/* Leaf: hashing a data block */
-			src_page = read_file_data_page(filp, i, &ra,
-						       num_blocks_to_hash - i);
-			if (IS_ERR(src_page)) {
-				err = PTR_ERR(src_page);
-				fsverity_err(inode,
-					     "Error %d reading data page %llu",
-					     err, i);
-				return err;
-			}
-		} else {
-			unsigned long num_ra_pages =
-				min_t(unsigned long, num_blocks_to_hash - i,
-				      inode->i_sb->s_bdi->io_pages);
-
-			/* Non-leaf: hashing hash block from level below */
-			src_page = vops->read_merkle_tree_page(inode,
-					params->level_start[level - 1] + i,
-					num_ra_pages);
-			if (IS_ERR(src_page)) {
-				err = PTR_ERR(src_page);
-				fsverity_err(inode,
-					     "Error %d reading Merkle tree page %llu",
-					     err, params->level_start[level - 1] + i);
-				return err;
-			}
-		}
-
-		err = fsverity_hash_block(params, inode, req, src_page, 0,
-					  &pending_hashes[pending_size]);
-		put_page(src_page);
-		if (err)
-			return err;
-		pending_size += params->digest_size;
-
-		if (level == params->num_levels) /* Root hash? */
-			return 0;
-
-		if (pending_size + params->digest_size > params->block_size ||
-		    i + 1 == num_blocks_to_hash) {
-			/* Flush the pending hash block */
-			memset(&pending_hashes[pending_size], 0,
-			       params->block_size - pending_size);
-			err = vops->write_merkle_tree_block(inode,
-					pending_hashes,
-					dst_block_num << params->log_blocksize,
-					params->block_size);
-			if (err) {
-				fsverity_err(inode,
-					     "Error %d writing Merkle tree block %llu",
-					     err, dst_block_num);
-				return err;
-			}
-			dst_block_num++;
-			pending_size = 0;
-		}
-
-		if (fatal_signal_pending(current))
-			return -EINTR;
-		cond_resched();
-	}
 	return 0;
 }
 
+static int write_merkle_tree_block(struct inode *inode, const u8 *buf,
+				   unsigned long index,
+				   const struct merkle_tree_params *params)
+{
+	u64 pos = (u64)index << params->log_blocksize;
+	int err;
+
+	err = inode->i_sb->s_vop->write_merkle_tree_block(inode, buf, pos,
+							  params->block_size);
+	if (err)
+		fsverity_err(inode, "Error %d writing Merkle tree block %lu",
+			     err, index);
+	return err;
+}
+
 /*
  * Build the Merkle tree for the given file using the given parameters, and
  * return the root hash in @root_hash.
@@ -148,13 +66,17 @@ static int build_merkle_tree(struct file *filp,
 			     u8 *root_hash)
 {
 	struct inode *inode = file_inode(filp);
-	u8 *pending_hashes;
+	const u64 data_size = inode->i_size;
+	const int num_levels = params->num_levels;
 	struct ahash_request *req;
-	u64 blocks;
+	struct block_buffer _buffers[1 + FS_VERITY_MAX_LEVELS + 1] = {};
-	unsigned int level;
+	struct block_buffer *buffers = &_buffers[1];
-	int err = -ENOMEM;
+	unsigned long level_offset[FS_VERITY_MAX_LEVELS];
+	int level;
+	u64 offset;
+	int err;
 
-	if (inode->i_size == 0) {
+	if (data_size == 0) {
 		/* Empty file is a special case; root hash is all 0's */
 		memset(root_hash, 0, params->digest_size);
 		return 0;
@@ -163,29 +85,95 @@ static int build_merkle_tree(struct file *filp,
 	/* This allocation never fails, since it's mempool-backed. */
 	req = fsverity_alloc_hash_request(params->hash_alg, GFP_KERNEL);
 
-	pending_hashes = kmalloc(params->block_size, GFP_KERNEL);
-	if (!pending_hashes)
-		goto out;
-
 	/*
-	 * Build each level of the Merkle tree, starting at the leaf level
+	 * Allocate the block buffers.  Buffer "-1" is for data blocks.
-	 * (level 0) and ascending to the root node (level 'num_levels - 1').
+	 * Buffers 0 <= level < num_levels are for the actual tree levels.
-	 * Then at the end (level 'num_levels'), calculate the root hash.
+	 * Buffer 'num_levels' is for the root hash.
 	 */
-	blocks = ((u64)inode->i_size + params->block_size - 1) >>
+	for (level = -1; level < num_levels; level++) {
-		 params->log_blocksize;
+		buffers[level].data = kzalloc(params->block_size, GFP_KERNEL);
-	for (level = 0; level <= params->num_levels; level++) {
+		if (!buffers[level].data) {
-		err = build_merkle_tree_level(filp, level, blocks, params,
+			err = -ENOMEM;
-					      pending_hashes, req);
+			goto out;
+		}
+	}
+	buffers[num_levels].data = root_hash;
+
+	BUILD_BUG_ON(sizeof(level_offset) != sizeof(params->level_start));
+	memcpy(level_offset, params->level_start, sizeof(level_offset));
+
+	/* Hash each data block, also hashing the tree blocks as they fill up */
+	for (offset = 0; offset < data_size; offset += params->block_size) {
+		ssize_t bytes_read;
+		loff_t pos = offset;
+
+		buffers[-1].filled = min_t(u64, params->block_size,
+					   data_size - offset);
+		bytes_read = __kernel_read(filp, buffers[-1].data,
+					   buffers[-1].filled, &pos);
+		if (bytes_read < 0) {
+			err = bytes_read;
+			fsverity_err(inode, "Error %d reading file data", err);
+			goto out;
+		}
+		if (bytes_read != buffers[-1].filled) {
+			err = -EINVAL;
+			fsverity_err(inode, "Short read of file data");
+			goto out;
+		}
+		err = hash_one_block(inode, params, req, &buffers[-1]);
 		if (err)
 			goto out;
-		blocks = (blocks + params->hashes_per_block - 1) >>
+		for (level = 0; level < num_levels; level++) {
-			 params->log_arity;
+			if (buffers[level].filled + params->digest_size <=
+			    params->block_size) {
+				/* Next block at @level isn't full yet */
+				break;
+			}
+			/* Next block at @level is full */
+
+			err = hash_one_block(inode, params, req,
+					     &buffers[level]);
+			if (err)
+				goto out;
+			err = write_merkle_tree_block(inode,
+						      buffers[level].data,
+						      level_offset[level],
+						      params);
+			if (err)
+				goto out;
+			level_offset[level]++;
+		}
+		if (fatal_signal_pending(current)) {
+			err = -EINTR;
+			goto out;
+		}
+		cond_resched();
+	}
+	/* Finish all nonempty pending tree blocks. */
+	for (level = 0; level < num_levels; level++) {
+		if (buffers[level].filled != 0) {
+			err = hash_one_block(inode, params, req,
+					     &buffers[level]);
+			if (err)
+				goto out;
+			err = write_merkle_tree_block(inode,
+						      buffers[level].data,
+						      level_offset[level],
+						      params);
+			if (err)
+				goto out;
+		}
+	}
+	/* The root hash was filled by the last call to hash_one_block(). */
+	if (WARN_ON(buffers[num_levels].filled != params->digest_size)) {
+		err = -EINVAL;
+		goto out;
 	}
-	memcpy(root_hash, pending_hashes, params->digest_size);
 	err = 0;
 out:
-	kfree(pending_hashes);
+	for (level = -1; level < num_levels; level++)
+		kfree(buffers[level].data);
 	fsverity_free_hash_request(params->hash_alg, req);
 	return err;
 }
@@ -341,7 +329,7 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *uarg)
 	    memchr_inv(arg.__reserved2, 0, sizeof(arg.__reserved2)))
 		return -EINVAL;
 
-	if (arg.block_size != PAGE_SIZE)
+	if (!is_power_of_2(arg.block_size))
 		return -EINVAL;
 
 	if (arg.salt_size > sizeof_field(struct fsverity_descriptor, salt))

include/linux/fsverity.h

@@ -93,8 +93,7 @@ struct fsverity_operations {
 	 *		  isn't already cached.  Implementations may ignore this
 	 *		  argument; it's only a performance optimization.
 	 *
-	 * This can be called at any time on an open verity file, as well as
+	 * This can be called at any time on an open verity file.  It may be
-	 * between ->begin_enable_verity() and ->end_enable_verity().  It may be
 	 * called by multiple processes concurrently, even with the same page.
 	 *
 	 * Note that this must retrieve a *page*, not necessarily a *block*.