Adding upstream version 6.6.15.upstream/6.6.15

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

11 files changed, 2140 insertions, 0 deletions

diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig
new file mode 100644
index 0000000000..e1036e5353
--- /dev/null
+++ b/fs/verity/Kconfig
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+
+config FS_VERITY
+	bool "FS Verity (read-only file-based authenticity protection)"
+	select CRYPTO
+	select CRYPTO_HASH_INFO
+	# SHA-256 is implied as it's intended to be the default hash algorithm.
+	# To avoid bloat, other wanted algorithms must be selected explicitly.
+	# Note that CRYPTO_SHA256 denotes the generic C implementation, but
+	# some architectures provided optimized implementations of the same
+	# algorithm that may be used instead. In this case, CRYPTO_SHA256 may
+	# be omitted even if SHA-256 is being used.
+	imply CRYPTO_SHA256
+	help
+	  This option enables fs-verity.  fs-verity is the dm-verity
+	  mechanism implemented at the file level.  On supported
+	  filesystems (currently ext4, f2fs, and btrfs), userspace can
+	  use an ioctl to enable verity for a file, which causes the
+	  filesystem to build a Merkle tree for the file.  The filesystem
+	  will then transparently verify any data read from the file
+	  against the Merkle tree.  The file is also made read-only.
+
+	  This serves as an integrity check, but the availability of the
+	  Merkle tree root hash also allows efficiently supporting
+	  various use cases where normally the whole file would need to
+	  be hashed at once, such as: (a) auditing (logging the file's
+	  hash), or (b) authenticity verification (comparing the hash
+	  against a known good value, e.g. from a digital signature).
+
+	  fs-verity is especially useful on large files where not all
+	  the contents may actually be needed.  Also, fs-verity verifies
+	  data each time it is paged back in, which provides better
+	  protection against malicious disks vs. an ahead-of-time hash.
+
+	  If unsure, say N.
+
+config FS_VERITY_BUILTIN_SIGNATURES
+	bool "FS Verity builtin signature support"
+	depends on FS_VERITY
+	select SYSTEM_DATA_VERIFICATION
+	help
+	  This option adds support for in-kernel verification of
+	  fs-verity builtin signatures.
+
+	  Please take great care before using this feature.  It is not
+	  the only way to do signatures with fs-verity, and the
+	  alternatives (such as userspace signature verification, and
+	  IMA appraisal) can be much better.  For details about the
+	  limitations of this feature, see
+	  Documentation/filesystems/fsverity.rst.
+
+	  If unsure, say N.
diff --git a/fs/verity/Makefile b/fs/verity/Makefile
new file mode 100644
index 0000000000..435559a4fa
--- /dev/null
+++ b/fs/verity/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_FS_VERITY) += enable.o \
+			   hash_algs.o \
+			   init.o \
+			   measure.o \
+			   open.o \
+			   read_metadata.o \
+			   verify.o
+
+obj-$(CONFIG_FS_VERITY_BUILTIN_SIGNATURES) += signature.o
diff --git a/fs/verity/enable.c b/fs/verity/enable.c
new file mode 100644
index 0000000000..c284f46d1b
--- /dev/null
+++ b/fs/verity/enable.c
@@ -0,0 +1,405 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ioctl to enable verity on a file
+ *
+ * Copyright 2019 Google LLC
+ */
+
+#include "fsverity_private.h"
+
+#include <crypto/hash.h>
+#include <linux/mount.h>
+#include <linux/sched/signal.h>
+#include <linux/uaccess.h>
+
+struct block_buffer {
+	u32 filled;
+	bool is_root_hash;
+	u8 *data;
+};
+
+/* Hash a block, writing the result to the next level's pending block buffer. */
+static int hash_one_block(struct inode *inode,
+			  const struct merkle_tree_params *params,
+			  struct block_buffer *cur)
+{
+	struct block_buffer *next = cur + 1;
+	int err;
+
+	/*
+	 * Safety check to prevent a buffer overflow in case of a filesystem bug
+	 * that allows the file size to change despite deny_write_access(), or a
+	 * bug in the Merkle tree logic itself
+	 */
+	if (WARN_ON_ONCE(next->is_root_hash && next->filled != 0))
+		return -EINVAL;
+
+	/* Zero-pad the block if it's shorter than the block size. */
+	memset(&cur->data[cur->filled], 0, params->block_size - cur->filled);
+
+	err = fsverity_hash_block(params, inode, cur->data,
+				  &next->data[next->filled]);
+	if (err)
+		return err;
+	next->filled += params->digest_size;
+	cur->filled = 0;
+	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.
+ *
+ * The tree is written to a filesystem-specific location as determined by the
+ * ->write_merkle_tree_block() method.  However, the blocks that comprise the
+ * tree are the same for all filesystems.
+ */
+static int build_merkle_tree(struct file *filp,
+			     const struct merkle_tree_params *params,
+			     u8 *root_hash)
+{
+	struct inode *inode = file_inode(filp);
+	const u64 data_size = inode->i_size;
+	const int num_levels = params->num_levels;
+	struct block_buffer _buffers[1 + FS_VERITY_MAX_LEVELS + 1] = {};
+	struct block_buffer *buffers = &_buffers[1];
+	unsigned long level_offset[FS_VERITY_MAX_LEVELS];
+	int level;
+	u64 offset;
+	int err;
+
+	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;
+	}
+
+	/*
+	 * Allocate the block buffers.  Buffer "-1" is for data blocks.
+	 * Buffers 0 <= level < num_levels are for the actual tree levels.
+	 * Buffer 'num_levels' is for the root hash.
+	 */
+	for (level = -1; level < num_levels; level++) {
+		buffers[level].data = kzalloc(params->block_size, GFP_KERNEL);
+		if (!buffers[level].data) {
+			err = -ENOMEM;
+			goto out;
+		}
+	}
+	buffers[num_levels].data = root_hash;
+	buffers[num_levels].is_root_hash = true;
+
+	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, &buffers[-1]);
+		if (err)
+			goto out;
+		for (level = 0; level < num_levels; level++) {
+			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, &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, &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_ONCE(buffers[num_levels].filled != params->digest_size)) {
+		err = -EINVAL;
+		goto out;
+	}
+	err = 0;
+out:
+	for (level = -1; level < num_levels; level++)
+		kfree(buffers[level].data);
+	return err;
+}
+
+static int enable_verity(struct file *filp,
+			 const struct fsverity_enable_arg *arg)
+{
+	struct inode *inode = file_inode(filp);
+	const struct fsverity_operations *vops = inode->i_sb->s_vop;
+	struct merkle_tree_params params = { };
+	struct fsverity_descriptor *desc;
+	size_t desc_size = struct_size(desc, signature, arg->sig_size);
+	struct fsverity_info *vi;
+	int err;
+
+	/* Start initializing the fsverity_descriptor */
+	desc = kzalloc(desc_size, GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+	desc->version = 1;
+	desc->hash_algorithm = arg->hash_algorithm;
+	desc->log_blocksize = ilog2(arg->block_size);
+
+	/* Get the salt if the user provided one */
+	if (arg->salt_size &&
+	    copy_from_user(desc->salt, u64_to_user_ptr(arg->salt_ptr),
+			   arg->salt_size)) {
+		err = -EFAULT;
+		goto out;
+	}
+	desc->salt_size = arg->salt_size;
+
+	/* Get the builtin signature if the user provided one */
+	if (arg->sig_size &&
+	    copy_from_user(desc->signature, u64_to_user_ptr(arg->sig_ptr),
+			   arg->sig_size)) {
+		err = -EFAULT;
+		goto out;
+	}
+	desc->sig_size = cpu_to_le32(arg->sig_size);
+
+	desc->data_size = cpu_to_le64(inode->i_size);
+
+	/* Prepare the Merkle tree parameters */
+	err = fsverity_init_merkle_tree_params(&params, inode,
+					       arg->hash_algorithm,
+					       desc->log_blocksize,
+					       desc->salt, desc->salt_size);
+	if (err)
+		goto out;
+
+	/*
+	 * Start enabling verity on this file, serialized by the inode lock.
+	 * Fail if verity is already enabled or is already being enabled.
+	 */
+	inode_lock(inode);
+	if (IS_VERITY(inode))
+		err = -EEXIST;
+	else
+		err = vops->begin_enable_verity(filp);
+	inode_unlock(inode);
+	if (err)
+		goto out;
+
+	/*
+	 * Build the Merkle tree.  Don't hold the inode lock during this, since
+	 * on huge files this may take a very long time and we don't want to
+	 * force unrelated syscalls like chown() to block forever.  We don't
+	 * need the inode lock here because deny_write_access() already prevents
+	 * the file from being written to or truncated, and we still serialize
+	 * ->begin_enable_verity() and ->end_enable_verity() using the inode
+	 * lock and only allow one process to be here at a time on a given file.
+	 */
+	BUILD_BUG_ON(sizeof(desc->root_hash) < FS_VERITY_MAX_DIGEST_SIZE);
+	err = build_merkle_tree(filp, &params, desc->root_hash);
+	if (err) {
+		fsverity_err(inode, "Error %d building Merkle tree", err);
+		goto rollback;
+	}
+
+	/*
+	 * Create the fsverity_info.  Don't bother trying to save work by
+	 * reusing the merkle_tree_params from above.  Instead, just create the
+	 * fsverity_info from the fsverity_descriptor as if it were just loaded
+	 * from disk.  This is simpler, and it serves as an extra check that the
+	 * metadata we're writing is valid before actually enabling verity.
+	 */
+	vi = fsverity_create_info(inode, desc);
+	if (IS_ERR(vi)) {
+		err = PTR_ERR(vi);
+		goto rollback;
+	}
+
+	/*
+	 * Tell the filesystem to finish enabling verity on the file.
+	 * Serialized with ->begin_enable_verity() by the inode lock.
+	 */
+	inode_lock(inode);
+	err = vops->end_enable_verity(filp, desc, desc_size, params.tree_size);
+	inode_unlock(inode);
+	if (err) {
+		fsverity_err(inode, "%ps() failed with err %d",
+			     vops->end_enable_verity, err);
+		fsverity_free_info(vi);
+	} else if (WARN_ON_ONCE(!IS_VERITY(inode))) {
+		err = -EINVAL;
+		fsverity_free_info(vi);
+	} else {
+		/* Successfully enabled verity */
+
+		/*
+		 * Readers can start using ->i_verity_info immediately, so it
+		 * can't be rolled back once set.  So don't set it until just
+		 * after the filesystem has successfully enabled verity.
+		 */
+		fsverity_set_info(inode, vi);
+	}
+out:
+	kfree(params.hashstate);
+	kfree(desc);
+	return err;
+
+rollback:
+	inode_lock(inode);
+	(void)vops->end_enable_verity(filp, NULL, 0, params.tree_size);
+	inode_unlock(inode);
+	goto out;
+}
+
+/**
+ * fsverity_ioctl_enable() - enable verity on a file
+ * @filp: file to enable verity on
+ * @uarg: user pointer to fsverity_enable_arg
+ *
+ * Enable fs-verity on a file.  See the "FS_IOC_ENABLE_VERITY" section of
+ * Documentation/filesystems/fsverity.rst for the documentation.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fsverity_ioctl_enable(struct file *filp, const void __user *uarg)
+{
+	struct inode *inode = file_inode(filp);
+	struct fsverity_enable_arg arg;
+	int err;
+
+	if (copy_from_user(&arg, uarg, sizeof(arg)))
+		return -EFAULT;
+
+	if (arg.version != 1)
+		return -EINVAL;
+
+	if (arg.__reserved1 ||
+	    memchr_inv(arg.__reserved2, 0, sizeof(arg.__reserved2)))
+		return -EINVAL;
+
+	if (!is_power_of_2(arg.block_size))
+		return -EINVAL;
+
+	if (arg.salt_size > sizeof_field(struct fsverity_descriptor, salt))
+		return -EMSGSIZE;
+
+	if (arg.sig_size > FS_VERITY_MAX_SIGNATURE_SIZE)
+		return -EMSGSIZE;
+
+	/*
+	 * Require a regular file with write access.  But the actual fd must
+	 * still be readonly so that we can lock out all writers.  This is
+	 * needed to guarantee that no writable fds exist to the file once it
+	 * has verity enabled, and to stabilize the data being hashed.
+	 */
+
+	err = file_permission(filp, MAY_WRITE);
+	if (err)
+		return err;
+	/*
+	 * __kernel_read() is used while building the Merkle tree.  So, we can't
+	 * allow file descriptors that were opened for ioctl access only, using
+	 * the special nonstandard access mode 3.  O_RDONLY only, please!
+	 */
+	if (!(filp->f_mode & FMODE_READ))
+		return -EBADF;
+
+	if (IS_APPEND(inode))
+		return -EPERM;
+
+	if (S_ISDIR(inode->i_mode))
+		return -EISDIR;
+
+	if (!S_ISREG(inode->i_mode))
+		return -EINVAL;
+
+	err = mnt_want_write_file(filp);
+	if (err) /* -EROFS */
+		return err;
+
+	err = deny_write_access(filp);
+	if (err) /* -ETXTBSY */
+		goto out_drop_write;
+
+	err = enable_verity(filp, &arg);
+
+	/*
+	 * We no longer drop the inode's pagecache after enabling verity.  This
+	 * used to be done to try to avoid a race condition where pages could be
+	 * evicted after being used in the Merkle tree construction, then
+	 * re-instantiated by a concurrent read.  Such pages are unverified, and
+	 * the backing storage could have filled them with different content, so
+	 * they shouldn't be used to fulfill reads once verity is enabled.
+	 *
+	 * But, dropping the pagecache has a big performance impact, and it
+	 * doesn't fully solve the race condition anyway.  So for those reasons,
+	 * and also because this race condition isn't very important relatively
+	 * speaking (especially for small-ish files, where the chance of a page
+	 * being used, evicted, *and* re-instantiated all while enabling verity
+	 * is quite small), we no longer drop the inode's pagecache.
+	 */
+
+	/*
+	 * allow_write_access() is needed to pair with deny_write_access().
+	 * Regardless, the filesystem won't allow writing to verity files.
+	 */
+	allow_write_access(filp);
+out_drop_write:
+	mnt_drop_write_file(filp);
+	return err;
+}
+EXPORT_SYMBOL_GPL(fsverity_ioctl_enable);
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
new file mode 100644
index 0000000000..d071a6e325
--- /dev/null
+++ b/fs/verity/fsverity_private.h
@@ -0,0 +1,148 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * fs-verity: read-only file-based authenticity protection
+ *
+ * Copyright 2019 Google LLC
+ */
+
+#ifndef _FSVERITY_PRIVATE_H
+#define _FSVERITY_PRIVATE_H
+
+#define pr_fmt(fmt) "fs-verity: " fmt
+
+#include <linux/fsverity.h>
+
+/*
+ * Implementation limit: maximum depth of the Merkle tree.  For now 8 is plenty;
+ * it's enough for over U64_MAX bytes of data using SHA-256 and 4K blocks.
+ */
+#define FS_VERITY_MAX_LEVELS		8
+
+/* A hash algorithm supported by fs-verity */
+struct fsverity_hash_alg {
+	struct crypto_shash *tfm; /* hash tfm, allocated on demand */
+	const char *name;	  /* crypto API name, e.g. sha256 */
+	unsigned int digest_size; /* digest size in bytes, e.g. 32 for SHA-256 */
+	unsigned int block_size;  /* block size in bytes, e.g. 64 for SHA-256 */
+	/*
+	 * The HASH_ALGO_* constant for this algorithm.  This is different from
+	 * FS_VERITY_HASH_ALG_*, which uses a different numbering scheme.
+	 */
+	enum hash_algo algo_id;
+};
+
+/* Merkle tree parameters: hash algorithm, initial hash state, and topology */
+struct merkle_tree_params {
+	const struct fsverity_hash_alg *hash_alg; /* the hash algorithm */
+	const u8 *hashstate;		/* initial hash state or NULL */
+	unsigned int digest_size;	/* same as hash_alg->digest_size */
+	unsigned int block_size;	/* size of data and tree blocks */
+	unsigned int hashes_per_block;	/* number of hashes per tree block */
+	unsigned int blocks_per_page;	/* PAGE_SIZE / block_size */
+	u8 log_digestsize;		/* log2(digest_size) */
+	u8 log_blocksize;		/* log2(block_size) */
+	u8 log_arity;			/* log2(hashes_per_block) */
+	u8 log_blocks_per_page;		/* log2(blocks_per_page) */
+	unsigned int num_levels;	/* number of levels in Merkle tree */
+	u64 tree_size;			/* Merkle tree size in bytes */
+	unsigned long tree_pages;	/* Merkle tree size in pages */
+
+	/*
+	 * Starting block index for each tree level, ordered from leaf level (0)
+	 * to root level ('num_levels - 1')
+	 */
+	unsigned long level_start[FS_VERITY_MAX_LEVELS];
+};
+
+/*
+ * fsverity_info - cached verity metadata for an inode
+ *
+ * When a verity file is first opened, an instance of this struct is allocated
+ * and stored in ->i_verity_info; it remains until the inode is evicted.  It
+ * caches information about the Merkle tree that's needed to efficiently verify
+ * data read from the file.  It also caches the file digest.  The Merkle tree
+ * pages themselves are not cached here, but the filesystem may cache them.
+ */
+struct fsverity_info {
+	struct merkle_tree_params tree_params;
+	u8 root_hash[FS_VERITY_MAX_DIGEST_SIZE];
+	u8 file_digest[FS_VERITY_MAX_DIGEST_SIZE];
+	const struct inode *inode;
+	unsigned long *hash_block_verified;
+	spinlock_t hash_page_init_lock;
+};
+
+#define FS_VERITY_MAX_SIGNATURE_SIZE	(FS_VERITY_MAX_DESCRIPTOR_SIZE - \
+					 sizeof(struct fsverity_descriptor))
+
+/* hash_algs.c */
+
+extern struct fsverity_hash_alg fsverity_hash_algs[];
+
+const struct fsverity_hash_alg *fsverity_get_hash_alg(const struct inode *inode,
+						      unsigned int num);
+const u8 *fsverity_prepare_hash_state(const struct fsverity_hash_alg *alg,
+				      const u8 *salt, size_t salt_size);
+int fsverity_hash_block(const struct merkle_tree_params *params,
+			const struct inode *inode, const void *data, u8 *out);
+int fsverity_hash_buffer(const struct fsverity_hash_alg *alg,
+			 const void *data, size_t size, u8 *out);
+void __init fsverity_check_hash_algs(void);
+
+/* init.c */
+
+void __printf(3, 4) __cold
+fsverity_msg(const struct inode *inode, const char *level,
+	     const char *fmt, ...);
+
+#define fsverity_warn(inode, fmt, ...)		\
+	fsverity_msg((inode), KERN_WARNING, fmt, ##__VA_ARGS__)
+#define fsverity_err(inode, fmt, ...)		\
+	fsverity_msg((inode), KERN_ERR, fmt, ##__VA_ARGS__)
+
+/* open.c */
+
+int fsverity_init_merkle_tree_params(struct merkle_tree_params *params,
+				     const struct inode *inode,
+				     unsigned int hash_algorithm,
+				     unsigned int log_blocksize,
+				     const u8 *salt, size_t salt_size);
+
+struct fsverity_info *fsverity_create_info(const struct inode *inode,
+					   struct fsverity_descriptor *desc);
+
+void fsverity_set_info(struct inode *inode, struct fsverity_info *vi);
+
+void fsverity_free_info(struct fsverity_info *vi);
+
+int fsverity_get_descriptor(struct inode *inode,
+			    struct fsverity_descriptor **desc_ret);
+
+void __init fsverity_init_info_cache(void);
+
+/* signature.c */
+
+#ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES
+extern int fsverity_require_signatures;
+int fsverity_verify_signature(const struct fsverity_info *vi,
+			      const u8 *signature, size_t sig_size);
+
+void __init fsverity_init_signature(void);
+#else /* !CONFIG_FS_VERITY_BUILTIN_SIGNATURES */
+static inline int
+fsverity_verify_signature(const struct fsverity_info *vi,
+			  const u8 *signature, size_t sig_size)
+{
+	return 0;
+}
+
+static inline void fsverity_init_signature(void)
+{
+}
+#endif /* !CONFIG_FS_VERITY_BUILTIN_SIGNATURES */
+
+/* verify.c */
+
+void __init fsverity_init_workqueue(void);
+
+#endif /* _FSVERITY_PRIVATE_H */
diff --git a/fs/verity/hash_algs.c b/fs/verity/hash_algs.c
new file mode 100644
index 0000000000..6b08b1d9a7
--- /dev/null
+++ b/fs/verity/hash_algs.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs-verity hash algorithms
+ *
+ * Copyright 2019 Google LLC
+ */
+
+#include "fsverity_private.h"
+
+#include <crypto/hash.h>
+
+/* The hash algorithms supported by fs-verity */
+struct fsverity_hash_alg fsverity_hash_algs[] = {
+	[FS_VERITY_HASH_ALG_SHA256] = {
+		.name = "sha256",
+		.digest_size = SHA256_DIGEST_SIZE,
+		.block_size = SHA256_BLOCK_SIZE,
+		.algo_id = HASH_ALGO_SHA256,
+	},
+	[FS_VERITY_HASH_ALG_SHA512] = {
+		.name = "sha512",
+		.digest_size = SHA512_DIGEST_SIZE,
+		.block_size = SHA512_BLOCK_SIZE,
+		.algo_id = HASH_ALGO_SHA512,
+	},
+};
+
+static DEFINE_MUTEX(fsverity_hash_alg_init_mutex);
+
+/**
+ * fsverity_get_hash_alg() - validate and prepare a hash algorithm
+ * @inode: optional inode for logging purposes
+ * @num: the hash algorithm number
+ *
+ * Get the struct fsverity_hash_alg for the given hash algorithm number, and
+ * ensure it has a hash transform ready to go.  The hash transforms are
+ * allocated on-demand so that we don't waste resources unnecessarily, and
+ * because the crypto modules may be initialized later than fs/verity/.
+ *
+ * Return: pointer to the hash alg on success, else an ERR_PTR()
+ */
+const struct fsverity_hash_alg *fsverity_get_hash_alg(const struct inode *inode,
+						      unsigned int num)
+{
+	struct fsverity_hash_alg *alg;
+	struct crypto_shash *tfm;
+	int err;
+
+	if (num >= ARRAY_SIZE(fsverity_hash_algs) ||
+	    !fsverity_hash_algs[num].name) {
+		fsverity_warn(inode, "Unknown hash algorithm number: %u", num);
+		return ERR_PTR(-EINVAL);
+	}
+	alg = &fsverity_hash_algs[num];
+
+	/* pairs with smp_store_release() below */
+	if (likely(smp_load_acquire(&alg->tfm) != NULL))
+		return alg;
+
+	mutex_lock(&fsverity_hash_alg_init_mutex);
+
+	if (alg->tfm != NULL)
+		goto out_unlock;
+
+	tfm = crypto_alloc_shash(alg->name, 0, 0);
+	if (IS_ERR(tfm)) {
+		if (PTR_ERR(tfm) == -ENOENT) {
+			fsverity_warn(inode,
+				      "Missing crypto API support for hash algorithm \"%s\"",
+				      alg->name);
+			alg = ERR_PTR(-ENOPKG);
+			goto out_unlock;
+		}
+		fsverity_err(inode,
+			     "Error allocating hash algorithm \"%s\": %ld",
+			     alg->name, PTR_ERR(tfm));
+		alg = ERR_CAST(tfm);
+		goto out_unlock;
+	}
+
+	err = -EINVAL;
+	if (WARN_ON_ONCE(alg->digest_size != crypto_shash_digestsize(tfm)))
+		goto err_free_tfm;
+	if (WARN_ON_ONCE(alg->block_size != crypto_shash_blocksize(tfm)))
+		goto err_free_tfm;
+
+	pr_info("%s using implementation \"%s\"\n",
+		alg->name, crypto_shash_driver_name(tfm));
+
+	/* pairs with smp_load_acquire() above */
+	smp_store_release(&alg->tfm, tfm);
+	goto out_unlock;
+
+err_free_tfm:
+	crypto_free_shash(tfm);
+	alg = ERR_PTR(err);
+out_unlock:
+	mutex_unlock(&fsverity_hash_alg_init_mutex);
+	return alg;
+}
+
+/**
+ * fsverity_prepare_hash_state() - precompute the initial hash state
+ * @alg: hash algorithm
+ * @salt: a salt which is to be prepended to all data to be hashed
+ * @salt_size: salt size in bytes, possibly 0
+ *
+ * Return: NULL if the salt is empty, otherwise the kmalloc()'ed precomputed
+ *	   initial hash state on success or an ERR_PTR() on failure.
+ */
+const u8 *fsverity_prepare_hash_state(const struct fsverity_hash_alg *alg,
+				      const u8 *salt, size_t salt_size)
+{
+	u8 *hashstate = NULL;
+	SHASH_DESC_ON_STACK(desc, alg->tfm);
+	u8 *padded_salt = NULL;
+	size_t padded_salt_size;
+	int err;
+
+	desc->tfm = alg->tfm;
+
+	if (salt_size == 0)
+		return NULL;
+
+	hashstate = kmalloc(crypto_shash_statesize(alg->tfm), GFP_KERNEL);
+	if (!hashstate)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * Zero-pad the salt to the next multiple of the input size of the hash
+	 * algorithm's compression function, e.g. 64 bytes for SHA-256 or 128
+	 * bytes for SHA-512.  This ensures that the hash algorithm won't have
+	 * any bytes buffered internally after processing the salt, thus making
+	 * salted hashing just as fast as unsalted hashing.
+	 */
+	padded_salt_size = round_up(salt_size, alg->block_size);
+	padded_salt = kzalloc(padded_salt_size, GFP_KERNEL);
+	if (!padded_salt) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+	memcpy(padded_salt, salt, salt_size);
+	err = crypto_shash_init(desc);
+	if (err)
+		goto err_free;
+
+	err = crypto_shash_update(desc, padded_salt, padded_salt_size);
+	if (err)
+		goto err_free;
+
+	err = crypto_shash_export(desc, hashstate);
+	if (err)
+		goto err_free;
+out:
+	kfree(padded_salt);
+	return hashstate;
+
+err_free:
+	kfree(hashstate);
+	hashstate = ERR_PTR(err);
+	goto out;
+}
+
+/**
+ * fsverity_hash_block() - hash a single data or hash block
+ * @params: the Merkle tree's parameters
+ * @inode: inode for which the hashing is being done
+ * @data: virtual address of a buffer containing the block to hash
+ * @out: output digest, size 'params->digest_size' bytes
+ *
+ * Hash a single data or hash block.  The hash is salted if a salt is specified
+ * in the Merkle tree parameters.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fsverity_hash_block(const struct merkle_tree_params *params,
+			const struct inode *inode, const void *data, u8 *out)
+{
+	SHASH_DESC_ON_STACK(desc, params->hash_alg->tfm);
+	int err;
+
+	desc->tfm = params->hash_alg->tfm;
+
+	if (params->hashstate) {
+		err = crypto_shash_import(desc, params->hashstate);
+		if (err) {
+			fsverity_err(inode,
+				     "Error %d importing hash state", err);
+			return err;
+		}
+		err = crypto_shash_finup(desc, data, params->block_size, out);
+	} else {
+		err = crypto_shash_digest(desc, data, params->block_size, out);
+	}
+	if (err)
+		fsverity_err(inode, "Error %d computing block hash", err);
+	return err;
+}
+
+/**
+ * fsverity_hash_buffer() - hash some data
+ * @alg: the hash algorithm to use
+ * @data: the data to hash
+ * @size: size of data to hash, in bytes
+ * @out: output digest, size 'alg->digest_size' bytes
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fsverity_hash_buffer(const struct fsverity_hash_alg *alg,
+			 const void *data, size_t size, u8 *out)
+{
+	return crypto_shash_tfm_digest(alg->tfm, data, size, out);
+}
+
+void __init fsverity_check_hash_algs(void)
+{
+	size_t i;
+
+	/*
+	 * Sanity check the hash algorithms (could be a build-time check, but
+	 * they're in an array)
+	 */
+	for (i = 0; i < ARRAY_SIZE(fsverity_hash_algs); i++) {
+		const struct fsverity_hash_alg *alg = &fsverity_hash_algs[i];
+
+		if (!alg->name)
+			continue;
+
+		/*
+		 * 0 must never be allocated as an FS_VERITY_HASH_ALG_* value,
+		 * as it is reserved for users that use 0 to mean unspecified or
+		 * a default value.  fs/verity/ itself doesn't care and doesn't
+		 * have a default algorithm, but some users make use of this.
+		 */
+		BUG_ON(i == 0);
+
+		BUG_ON(alg->digest_size > FS_VERITY_MAX_DIGEST_SIZE);
+
+		/*
+		 * For efficiency, the implementation currently assumes the
+		 * digest and block sizes are powers of 2.  This limitation can
+		 * be lifted if the code is updated to handle other values.
+		 */
+		BUG_ON(!is_power_of_2(alg->digest_size));
+		BUG_ON(!is_power_of_2(alg->block_size));
+
+		/* Verify that there is a valid mapping to HASH_ALGO_*. */
+		BUG_ON(alg->algo_id == 0);
+		BUG_ON(alg->digest_size != hash_digest_size[alg->algo_id]);
+	}
+}
diff --git a/fs/verity/init.c b/fs/verity/init.c
new file mode 100644
index 0000000000..a29f062f60
--- /dev/null
+++ b/fs/verity/init.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs-verity module initialization and logging
+ *
+ * Copyright 2019 Google LLC
+ */
+
+#include "fsverity_private.h"
+
+#include <linux/ratelimit.h>
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table_header *fsverity_sysctl_header;
+
+static struct ctl_table fsverity_sysctl_table[] = {
+#ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES
+	{
+		.procname       = "require_signatures",
+		.data           = &fsverity_require_signatures,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+#endif
+	{ }
+};
+
+static void __init fsverity_init_sysctl(void)
+{
+	fsverity_sysctl_header = register_sysctl("fs/verity",
+						 fsverity_sysctl_table);
+	if (!fsverity_sysctl_header)
+		panic("fsverity sysctl registration failed");
+}
+#else /* CONFIG_SYSCTL */
+static inline void fsverity_init_sysctl(void)
+{
+}
+#endif /* !CONFIG_SYSCTL */
+
+void fsverity_msg(const struct inode *inode, const char *level,
+		  const char *fmt, ...)
+{
+	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+	struct va_format vaf;
+	va_list args;
+
+	if (!__ratelimit(&rs))
+		return;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	if (inode)
+		printk("%sfs-verity (%s, inode %lu): %pV\n",
+		       level, inode->i_sb->s_id, inode->i_ino, &vaf);
+	else
+		printk("%sfs-verity: %pV\n", level, &vaf);
+	va_end(args);
+}
+
+static int __init fsverity_init(void)
+{
+	fsverity_check_hash_algs();
+	fsverity_init_info_cache();
+	fsverity_init_workqueue();
+	fsverity_init_sysctl();
+	fsverity_init_signature();
+	return 0;
+}
+late_initcall(fsverity_init)
diff --git a/fs/verity/measure.c b/fs/verity/measure.c
new file mode 100644
index 0000000000..eec5956141
--- /dev/null
+++ b/fs/verity/measure.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ioctl to get a verity file's digest
+ *
+ * Copyright 2019 Google LLC
+ */
+
+#include "fsverity_private.h"
+
+#include <linux/uaccess.h>
+
+/**
+ * fsverity_ioctl_measure() - get a verity file's digest
+ * @filp: file to get digest of
+ * @_uarg: user pointer to fsverity_digest
+ *
+ * Retrieve the file digest that the kernel is enforcing for reads from a verity
+ * file.  See the "FS_IOC_MEASURE_VERITY" section of
+ * Documentation/filesystems/fsverity.rst for the documentation.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fsverity_ioctl_measure(struct file *filp, void __user *_uarg)
+{
+	const struct inode *inode = file_inode(filp);
+	struct fsverity_digest __user *uarg = _uarg;
+	const struct fsverity_info *vi;
+	const struct fsverity_hash_alg *hash_alg;
+	struct fsverity_digest arg;
+
+	vi = fsverity_get_info(inode);
+	if (!vi)
+		return -ENODATA; /* not a verity file */
+	hash_alg = vi->tree_params.hash_alg;
+
+	/*
+	 * The user specifies the digest_size their buffer has space for; we can
+	 * return the digest if it fits in the available space.  We write back
+	 * the actual size, which may be shorter than the user-specified size.
+	 */
+
+	if (get_user(arg.digest_size, &uarg->digest_size))
+		return -EFAULT;
+	if (arg.digest_size < hash_alg->digest_size)
+		return -EOVERFLOW;
+
+	memset(&arg, 0, sizeof(arg));
+	arg.digest_algorithm = hash_alg - fsverity_hash_algs;
+	arg.digest_size = hash_alg->digest_size;
+
+	if (copy_to_user(uarg, &arg, sizeof(arg)))
+		return -EFAULT;
+
+	if (copy_to_user(uarg->digest, vi->file_digest, hash_alg->digest_size))
+		return -EFAULT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fsverity_ioctl_measure);
+
+/**
+ * fsverity_get_digest() - get a verity file's digest
+ * @inode: inode to get digest of
+ * @raw_digest: (out) the raw file digest
+ * @alg: (out) the digest's algorithm, as a FS_VERITY_HASH_ALG_* value
+ * @halg: (out) the digest's algorithm, as a HASH_ALGO_* value
+ *
+ * Retrieves the fsverity digest of the given file.  The file must have been
+ * opened at least once since the inode was last loaded into the inode cache;
+ * otherwise this function will not recognize when fsverity is enabled.
+ *
+ * The file's fsverity digest consists of @raw_digest in combination with either
+ * @alg or @halg.  (The caller can choose which one of @alg or @halg to use.)
+ *
+ * IMPORTANT: Callers *must* make use of one of the two algorithm IDs, since
+ * @raw_digest is meaningless without knowing which algorithm it uses!  fsverity
+ * provides no security guarantee for users who ignore the algorithm ID, even if
+ * they use the digest size (since algorithms can share the same digest size).
+ *
+ * Return: The size of the raw digest in bytes, or 0 if the file doesn't have
+ *	   fsverity enabled.
+ */
+int fsverity_get_digest(struct inode *inode,
+			u8 raw_digest[FS_VERITY_MAX_DIGEST_SIZE],
+			u8 *alg, enum hash_algo *halg)
+{
+	const struct fsverity_info *vi;
+	const struct fsverity_hash_alg *hash_alg;
+
+	vi = fsverity_get_info(inode);
+	if (!vi)
+		return 0; /* not a verity file */
+
+	hash_alg = vi->tree_params.hash_alg;
+	memcpy(raw_digest, vi->file_digest, hash_alg->digest_size);
+	if (alg)
+		*alg = hash_alg - fsverity_hash_algs;
+	if (halg)
+		*halg = hash_alg->algo_id;
+	return hash_alg->digest_size;
+}
+EXPORT_SYMBOL_GPL(fsverity_get_digest);
diff --git a/fs/verity/open.c b/fs/verity/open.c
new file mode 100644
index 0000000000..6c31a871b8
--- /dev/null
+++ b/fs/verity/open.c
@@ -0,0 +1,417 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Opening fs-verity files
+ *
+ * Copyright 2019 Google LLC
+ */
+
+#include "fsverity_private.h"
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+static struct kmem_cache *fsverity_info_cachep;
+
+/**
+ * fsverity_init_merkle_tree_params() - initialize Merkle tree parameters
+ * @params: the parameters struct to initialize
+ * @inode: the inode for which the Merkle tree is being built
+ * @hash_algorithm: number of hash algorithm to use
+ * @log_blocksize: log base 2 of block size to use
+ * @salt: pointer to salt (optional)
+ * @salt_size: size of salt, possibly 0
+ *
+ * Validate the hash algorithm and block size, then compute the tree topology
+ * (num levels, num blocks in each level, etc.) and initialize @params.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fsverity_init_merkle_tree_params(struct merkle_tree_params *params,
+				     const struct inode *inode,
+				     unsigned int hash_algorithm,
+				     unsigned int log_blocksize,
+				     const u8 *salt, size_t salt_size)
+{
+	const struct fsverity_hash_alg *hash_alg;
+	int err;
+	u64 blocks;
+	u64 blocks_in_level[FS_VERITY_MAX_LEVELS];
+	u64 offset;
+	int level;
+
+	memset(params, 0, sizeof(*params));
+
+	hash_alg = fsverity_get_hash_alg(inode, hash_algorithm);
+	if (IS_ERR(hash_alg))
+		return PTR_ERR(hash_alg);
+	params->hash_alg = hash_alg;
+	params->digest_size = hash_alg->digest_size;
+
+	params->hashstate = fsverity_prepare_hash_state(hash_alg, salt,
+							salt_size);
+	if (IS_ERR(params->hashstate)) {
+		err = PTR_ERR(params->hashstate);
+		params->hashstate = NULL;
+		fsverity_err(inode, "Error %d preparing hash state", err);
+		goto out_err;
+	}
+
+	/*
+	 * fs/verity/ directly assumes that the Merkle tree block size is a
+	 * power of 2 less than or equal to PAGE_SIZE.  Another restriction
+	 * arises from the interaction between fs/verity/ and the filesystems
+	 * themselves: filesystems expect to be able to verify a single
+	 * filesystem block of data at a time.  Therefore, the Merkle tree block
+	 * size must also be less than or equal to the filesystem block size.
+	 *
+	 * The above are the only hard limitations, so in theory the Merkle tree
+	 * block size could be as small as twice the digest size.  However,
+	 * that's not useful, and it would result in some unusually deep and
+	 * large Merkle trees.  So we currently require that the Merkle tree
+	 * block size be at least 1024 bytes.  That's small enough to test the
+	 * sub-page block case on systems with 4K pages, but not too small.
+	 */
+	if (log_blocksize < 10 || log_blocksize > PAGE_SHIFT ||
+	    log_blocksize > inode->i_blkbits) {
+		fsverity_warn(inode, "Unsupported log_blocksize: %u",
+			      log_blocksize);
+		err = -EINVAL;
+		goto out_err;
+	}
+	params->log_blocksize = log_blocksize;
+	params->block_size = 1 << log_blocksize;
+	params->log_blocks_per_page = PAGE_SHIFT - log_blocksize;
+	params->blocks_per_page = 1 << params->log_blocks_per_page;
+
+	if (WARN_ON_ONCE(!is_power_of_2(params->digest_size))) {
+		err = -EINVAL;
+		goto out_err;
+	}
+	if (params->block_size < 2 * params->digest_size) {
+		fsverity_warn(inode,
+			      "Merkle tree block size (%u) too small for hash algorithm \"%s\"",
+			      params->block_size, hash_alg->name);
+		err = -EINVAL;
+		goto out_err;
+	}
+	params->log_digestsize = ilog2(params->digest_size);
+	params->log_arity = log_blocksize - params->log_digestsize;
+	params->hashes_per_block = 1 << params->log_arity;
+
+	/*
+	 * Compute the number of levels in the Merkle tree and create a map from
+	 * level to the starting block of that level.  Level 'num_levels - 1' is
+	 * the root and is stored first.  Level 0 is the level directly "above"
+	 * the data blocks and is stored last.
+	 */
+
+	/* Compute number of levels and the number of blocks in each level */
+	blocks = ((u64)inode->i_size + params->block_size - 1) >> log_blocksize;
+	while (blocks > 1) {
+		if (params->num_levels >= FS_VERITY_MAX_LEVELS) {
+			fsverity_err(inode, "Too many levels in Merkle tree");
+			err = -EFBIG;
+			goto out_err;
+		}
+		blocks = (blocks + params->hashes_per_block - 1) >>
+			 params->log_arity;
+		blocks_in_level[params->num_levels++] = blocks;
+	}
+
+	/* Compute the starting block of each level */
+	offset = 0;
+	for (level = (int)params->num_levels - 1; level >= 0; level--) {
+		params->level_start[level] = offset;
+		offset += blocks_in_level[level];
+	}
+
+	/*
+	 * With block_size != PAGE_SIZE, an in-memory bitmap will need to be
+	 * allocated to track the "verified" status of hash blocks.  Don't allow
+	 * this bitmap to get too large.  For now, limit it to 1 MiB, which
+	 * limits the file size to about 4.4 TB with SHA-256 and 4K blocks.
+	 *
+	 * Together with the fact that the data, and thus also the Merkle tree,
+	 * cannot have more than ULONG_MAX pages, this implies that hash block
+	 * indices can always fit in an 'unsigned long'.  But to be safe, we
+	 * explicitly check for that too.  Note, this is only for hash block
+	 * indices; data block indices might not fit in an 'unsigned long'.
+	 */
+	if ((params->block_size != PAGE_SIZE && offset > 1 << 23) ||
+	    offset > ULONG_MAX) {
+		fsverity_err(inode, "Too many blocks in Merkle tree");
+		err = -EFBIG;
+		goto out_err;
+	}
+
+	params->tree_size = offset << log_blocksize;
+	params->tree_pages = PAGE_ALIGN(params->tree_size) >> PAGE_SHIFT;
+	return 0;
+
+out_err:
+	kfree(params->hashstate);
+	memset(params, 0, sizeof(*params));
+	return err;
+}
+
+/*
+ * Compute the file digest by hashing the fsverity_descriptor excluding the
+ * builtin signature and with the sig_size field set to 0.
+ */
+static int compute_file_digest(const struct fsverity_hash_alg *hash_alg,
+			       struct fsverity_descriptor *desc,
+			       u8 *file_digest)
+{
+	__le32 sig_size = desc->sig_size;
+	int err;
+
+	desc->sig_size = 0;
+	err = fsverity_hash_buffer(hash_alg, desc, sizeof(*desc), file_digest);
+	desc->sig_size = sig_size;
+
+	return err;
+}
+
+/*
+ * Create a new fsverity_info from the given fsverity_descriptor (with optional
+ * appended builtin signature), and check the signature if present.  The
+ * fsverity_descriptor must have already undergone basic validation.
+ */
+struct fsverity_info *fsverity_create_info(const struct inode *inode,
+					   struct fsverity_descriptor *desc)
+{
+	struct fsverity_info *vi;
+	int err;
+
+	vi = kmem_cache_zalloc(fsverity_info_cachep, GFP_KERNEL);
+	if (!vi)
+		return ERR_PTR(-ENOMEM);
+	vi->inode = inode;
+
+	err = fsverity_init_merkle_tree_params(&vi->tree_params, inode,
+					       desc->hash_algorithm,
+					       desc->log_blocksize,
+					       desc->salt, desc->salt_size);
+	if (err) {
+		fsverity_err(inode,
+			     "Error %d initializing Merkle tree parameters",
+			     err);
+		goto fail;
+	}
+
+	memcpy(vi->root_hash, desc->root_hash, vi->tree_params.digest_size);
+
+	err = compute_file_digest(vi->tree_params.hash_alg, desc,
+				  vi->file_digest);
+	if (err) {
+		fsverity_err(inode, "Error %d computing file digest", err);
+		goto fail;
+	}
+
+	err = fsverity_verify_signature(vi, desc->signature,
+					le32_to_cpu(desc->sig_size));
+	if (err)
+		goto fail;
+
+	if (vi->tree_params.block_size != PAGE_SIZE) {
+		/*
+		 * When the Merkle tree block size and page size differ, we use
+		 * a bitmap to keep track of which hash blocks have been
+		 * verified.  This bitmap must contain one bit per hash block,
+		 * including alignment to a page boundary at the end.
+		 *
+		 * Eventually, to support extremely large files in an efficient
+		 * way, it might be necessary to make pages of this bitmap
+		 * reclaimable.  But for now, simply allocating the whole bitmap
+		 * is a simple solution that works well on the files on which
+		 * fsverity is realistically used.  E.g., with SHA-256 and 4K
+		 * blocks, a 100MB file only needs a 24-byte bitmap, and the
+		 * bitmap for any file under 17GB fits in a 4K page.
+		 */
+		unsigned long num_bits =
+			vi->tree_params.tree_pages <<
+			vi->tree_params.log_blocks_per_page;
+
+		vi->hash_block_verified = kvcalloc(BITS_TO_LONGS(num_bits),
+						   sizeof(unsigned long),
+						   GFP_KERNEL);
+		if (!vi->hash_block_verified) {
+			err = -ENOMEM;
+			goto fail;
+		}
+		spin_lock_init(&vi->hash_page_init_lock);
+	}
+
+	return vi;
+
+fail:
+	fsverity_free_info(vi);
+	return ERR_PTR(err);
+}
+
+void fsverity_set_info(struct inode *inode, struct fsverity_info *vi)
+{
+	/*
+	 * Multiple tasks may race to set ->i_verity_info, so use
+	 * cmpxchg_release().  This pairs with the smp_load_acquire() in
+	 * fsverity_get_info().  I.e., here we publish ->i_verity_info with a
+	 * RELEASE barrier so that other tasks can ACQUIRE it.
+	 */
+	if (cmpxchg_release(&inode->i_verity_info, NULL, vi) != NULL) {
+		/* Lost the race, so free the fsverity_info we allocated. */
+		fsverity_free_info(vi);
+		/*
+		 * Afterwards, the caller may access ->i_verity_info directly,
+		 * so make sure to ACQUIRE the winning fsverity_info.
+		 */
+		(void)fsverity_get_info(inode);
+	}
+}
+
+void fsverity_free_info(struct fsverity_info *vi)
+{
+	if (!vi)
+		return;
+	kfree(vi->tree_params.hashstate);
+	kvfree(vi->hash_block_verified);
+	kmem_cache_free(fsverity_info_cachep, vi);
+}
+
+static bool validate_fsverity_descriptor(struct inode *inode,
+					 const struct fsverity_descriptor *desc,
+					 size_t desc_size)
+{
+	if (desc_size < sizeof(*desc)) {
+		fsverity_err(inode, "Unrecognized descriptor size: %zu bytes",
+			     desc_size);
+		return false;
+	}
+
+	if (desc->version != 1) {
+		fsverity_err(inode, "Unrecognized descriptor version: %u",
+			     desc->version);
+		return false;
+	}
+
+	if (memchr_inv(desc->__reserved, 0, sizeof(desc->__reserved))) {
+		fsverity_err(inode, "Reserved bits set in descriptor");
+		return false;
+	}
+
+	if (desc->salt_size > sizeof(desc->salt)) {
+		fsverity_err(inode, "Invalid salt_size: %u", desc->salt_size);
+		return false;
+	}
+
+	if (le64_to_cpu(desc->data_size) != inode->i_size) {
+		fsverity_err(inode,
+			     "Wrong data_size: %llu (desc) != %lld (inode)",
+			     le64_to_cpu(desc->data_size), inode->i_size);
+		return false;
+	}
+
+	if (le32_to_cpu(desc->sig_size) > desc_size - sizeof(*desc)) {
+		fsverity_err(inode, "Signature overflows verity descriptor");
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * Read the inode's fsverity_descriptor (with optional appended builtin
+ * signature) from the filesystem, and do basic validation of it.
+ */
+int fsverity_get_descriptor(struct inode *inode,
+			    struct fsverity_descriptor **desc_ret)
+{
+	int res;
+	struct fsverity_descriptor *desc;
+
+	res = inode->i_sb->s_vop->get_verity_descriptor(inode, NULL, 0);
+	if (res < 0) {
+		fsverity_err(inode,
+			     "Error %d getting verity descriptor size", res);
+		return res;
+	}
+	if (res > FS_VERITY_MAX_DESCRIPTOR_SIZE) {
+		fsverity_err(inode, "Verity descriptor is too large (%d bytes)",
+			     res);
+		return -EMSGSIZE;
+	}
+	desc = kmalloc(res, GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+	res = inode->i_sb->s_vop->get_verity_descriptor(inode, desc, res);
+	if (res < 0) {
+		fsverity_err(inode, "Error %d reading verity descriptor", res);
+		kfree(desc);
+		return res;
+	}
+
+	if (!validate_fsverity_descriptor(inode, desc, res)) {
+		kfree(desc);
+		return -EINVAL;
+	}
+
+	*desc_ret = desc;
+	return 0;
+}
+
+/* Ensure the inode has an ->i_verity_info */
+static int ensure_verity_info(struct inode *inode)
+{
+	struct fsverity_info *vi = fsverity_get_info(inode);
+	struct fsverity_descriptor *desc;
+	int err;
+
+	if (vi)
+		return 0;
+
+	err = fsverity_get_descriptor(inode, &desc);
+	if (err)
+		return err;
+
+	vi = fsverity_create_info(inode, desc);
+	if (IS_ERR(vi)) {
+		err = PTR_ERR(vi);
+		goto out_free_desc;
+	}
+
+	fsverity_set_info(inode, vi);
+	err = 0;
+out_free_desc:
+	kfree(desc);
+	return err;
+}
+
+int __fsverity_file_open(struct inode *inode, struct file *filp)
+{
+	if (filp->f_mode & FMODE_WRITE)
+		return -EPERM;
+	return ensure_verity_info(inode);
+}
+EXPORT_SYMBOL_GPL(__fsverity_file_open);
+
+int __fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	if (attr->ia_valid & ATTR_SIZE)
+		return -EPERM;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__fsverity_prepare_setattr);
+
+void __fsverity_cleanup_inode(struct inode *inode)
+{
+	fsverity_free_info(inode->i_verity_info);
+	inode->i_verity_info = NULL;
+}
+EXPORT_SYMBOL_GPL(__fsverity_cleanup_inode);
+
+void __init fsverity_init_info_cache(void)
+{
+	fsverity_info_cachep = KMEM_CACHE_USERCOPY(
+					fsverity_info,
+					SLAB_RECLAIM_ACCOUNT | SLAB_PANIC,
+					file_digest);
+}
diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c
new file mode 100644
index 0000000000..f58432772d
--- /dev/null
+++ b/fs/verity/read_metadata.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Ioctl to read verity metadata
+ *
+ * Copyright 2021 Google LLC
+ */
+
+#include "fsverity_private.h"
+
+#include <linux/backing-dev.h>
+#include <linux/highmem.h>
+#include <linux/sched/signal.h>
+#include <linux/uaccess.h>
+
+static int fsverity_read_merkle_tree(struct inode *inode,
+				     const struct fsverity_info *vi,
+				     void __user *buf, u64 offset, int length)
+{
+	const struct fsverity_operations *vops = inode->i_sb->s_vop;
+	u64 end_offset;
+	unsigned int offs_in_page;
+	pgoff_t index, last_index;
+	int retval = 0;
+	int err = 0;
+
+	end_offset = min(offset + length, vi->tree_params.tree_size);
+	if (offset >= end_offset)
+		return 0;
+	offs_in_page = offset_in_page(offset);
+	last_index = (end_offset - 1) >> PAGE_SHIFT;
+
+	/*
+	 * Iterate through each Merkle tree page in the requested range and copy
+	 * the requested portion to userspace.  Note that the Merkle tree block
+	 * size isn't important here, as we are returning a byte stream; i.e.,
+	 * we can just work with pages even if the tree block size != PAGE_SIZE.
+	 */
+	for (index = offset >> PAGE_SHIFT; index <= last_index; index++) {
+		unsigned long num_ra_pages =
+			min_t(unsigned long, last_index - index + 1,
+			      inode->i_sb->s_bdi->io_pages);
+		unsigned int bytes_to_copy = min_t(u64, end_offset - offset,
+						   PAGE_SIZE - offs_in_page);
+		struct page *page;
+		const void *virt;
+
+		page = vops->read_merkle_tree_page(inode, index, num_ra_pages);
+		if (IS_ERR(page)) {
+			err = PTR_ERR(page);
+			fsverity_err(inode,
+				     "Error %d reading Merkle tree page %lu",
+				     err, index);
+			break;
+		}
+
+		virt = kmap_local_page(page);
+		if (copy_to_user(buf, virt + offs_in_page, bytes_to_copy)) {
+			kunmap_local(virt);
+			put_page(page);
+			err = -EFAULT;
+			break;
+		}
+		kunmap_local(virt);
+		put_page(page);
+
+		retval += bytes_to_copy;
+		buf += bytes_to_copy;
+		offset += bytes_to_copy;
+
+		if (fatal_signal_pending(current))  {
+			err = -EINTR;
+			break;
+		}
+		cond_resched();
+		offs_in_page = 0;
+	}
+	return retval ? retval : err;
+}
+
+/* Copy the requested portion of the buffer to userspace. */
+static int fsverity_read_buffer(void __user *dst, u64 offset, int length,
+				const void *src, size_t src_length)
+{
+	if (offset >= src_length)
+		return 0;
+	src += offset;
+	src_length -= offset;
+
+	length = min_t(size_t, length, src_length);
+
+	if (copy_to_user(dst, src, length))
+		return -EFAULT;
+
+	return length;
+}
+
+static int fsverity_read_descriptor(struct inode *inode,
+				    void __user *buf, u64 offset, int length)
+{
+	struct fsverity_descriptor *desc;
+	size_t desc_size;
+	int res;
+
+	res = fsverity_get_descriptor(inode, &desc);
+	if (res)
+		return res;
+
+	/* don't include the builtin signature */
+	desc_size = offsetof(struct fsverity_descriptor, signature);
+	desc->sig_size = 0;
+
+	res = fsverity_read_buffer(buf, offset, length, desc, desc_size);
+
+	kfree(desc);
+	return res;
+}
+
+static int fsverity_read_signature(struct inode *inode,
+				   void __user *buf, u64 offset, int length)
+{
+	struct fsverity_descriptor *desc;
+	int res;
+
+	res = fsverity_get_descriptor(inode, &desc);
+	if (res)
+		return res;
+
+	if (desc->sig_size == 0) {
+		res = -ENODATA;
+		goto out;
+	}
+
+	/*
+	 * Include only the builtin signature.  fsverity_get_descriptor()
+	 * already verified that sig_size is in-bounds.
+	 */
+	res = fsverity_read_buffer(buf, offset, length, desc->signature,
+				   le32_to_cpu(desc->sig_size));
+out:
+	kfree(desc);
+	return res;
+}
+
+/**
+ * fsverity_ioctl_read_metadata() - read verity metadata from a file
+ * @filp: file to read the metadata from
+ * @uarg: user pointer to fsverity_read_metadata_arg
+ *
+ * Return: length read on success, 0 on EOF, -errno on failure
+ */
+int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg)
+{
+	struct inode *inode = file_inode(filp);
+	const struct fsverity_info *vi;
+	struct fsverity_read_metadata_arg arg;
+	int length;
+	void __user *buf;
+
+	vi = fsverity_get_info(inode);
+	if (!vi)
+		return -ENODATA; /* not a verity file */
+	/*
+	 * Note that we don't have to explicitly check that the file is open for
+	 * reading, since verity files can only be opened for reading.
+	 */
+
+	if (copy_from_user(&arg, uarg, sizeof(arg)))
+		return -EFAULT;
+
+	if (arg.__reserved)
+		return -EINVAL;
+
+	/* offset + length must not overflow. */
+	if (arg.offset + arg.length < arg.offset)
+		return -EINVAL;
+
+	/* Ensure that the return value will fit in INT_MAX. */
+	length = min_t(u64, arg.length, INT_MAX);
+
+	buf = u64_to_user_ptr(arg.buf_ptr);
+
+	switch (arg.metadata_type) {
+	case FS_VERITY_METADATA_TYPE_MERKLE_TREE:
+		return fsverity_read_merkle_tree(inode, vi, buf, arg.offset,
+						 length);
+	case FS_VERITY_METADATA_TYPE_DESCRIPTOR:
+		return fsverity_read_descriptor(inode, buf, arg.offset, length);
+	case FS_VERITY_METADATA_TYPE_SIGNATURE:
+		return fsverity_read_signature(inode, buf, arg.offset, length);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL_GPL(fsverity_ioctl_read_metadata);
diff --git a/fs/verity/signature.c b/fs/verity/signature.c
new file mode 100644
index 0000000000..90c07573dd
--- /dev/null
+++ b/fs/verity/signature.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Verification of builtin signatures
+ *
+ * Copyright 2019 Google LLC
+ */
+
+/*
+ * This file implements verification of fs-verity builtin signatures.  Please
+ * take great care before using this feature.  It is not the only way to do
+ * signatures with fs-verity, and the alternatives (such as userspace signature
+ * verification, and IMA appraisal) can be much better.  For details about the
+ * limitations of this feature, see Documentation/filesystems/fsverity.rst.
+ */
+
+#include "fsverity_private.h"
+
+#include <linux/cred.h>
+#include <linux/key.h>
+#include <linux/slab.h>
+#include <linux/verification.h>
+
+/*
+ * /proc/sys/fs/verity/require_signatures
+ * If 1, all verity files must have a valid builtin signature.
+ */
+int fsverity_require_signatures;
+
+/*
+ * Keyring that contains the trusted X.509 certificates.
+ *
+ * Only root (kuid=0) can modify this.  Also, root may use
+ * keyctl_restrict_keyring() to prevent any more additions.
+ */
+static struct key *fsverity_keyring;
+
+/**
+ * fsverity_verify_signature() - check a verity file's signature
+ * @vi: the file's fsverity_info
+ * @signature: the file's built-in signature
+ * @sig_size: size of signature in bytes, or 0 if no signature
+ *
+ * If the file includes a signature of its fs-verity file digest, verify it
+ * against the certificates in the fs-verity keyring.
+ *
+ * Return: 0 on success (signature valid or not required); -errno on failure
+ */
+int fsverity_verify_signature(const struct fsverity_info *vi,
+			      const u8 *signature, size_t sig_size)
+{
+	const struct inode *inode = vi->inode;
+	const struct fsverity_hash_alg *hash_alg = vi->tree_params.hash_alg;
+	struct fsverity_formatted_digest *d;
+	int err;
+
+	if (sig_size == 0) {
+		if (fsverity_require_signatures) {
+			fsverity_err(inode,
+				     "require_signatures=1, rejecting unsigned file!");
+			return -EPERM;
+		}
+		return 0;
+	}
+
+	if (fsverity_keyring->keys.nr_leaves_on_tree == 0) {
+		/*
+		 * The ".fs-verity" keyring is empty, due to builtin signatures
+		 * being supported by the kernel but not actually being used.
+		 * In this case, verify_pkcs7_signature() would always return an
+		 * error, usually ENOKEY.  It could also be EBADMSG if the
+		 * PKCS#7 is malformed, but that isn't very important to
+		 * distinguish.  So, just skip to ENOKEY to avoid the attack
+		 * surface of the PKCS#7 parser, which would otherwise be
+		 * reachable by any task able to execute FS_IOC_ENABLE_VERITY.
+		 */
+		fsverity_err(inode,
+			     "fs-verity keyring is empty, rejecting signed file!");
+		return -ENOKEY;
+	}
+
+	d = kzalloc(sizeof(*d) + hash_alg->digest_size, GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+	memcpy(d->magic, "FSVerity", 8);
+	d->digest_algorithm = cpu_to_le16(hash_alg - fsverity_hash_algs);
+	d->digest_size = cpu_to_le16(hash_alg->digest_size);
+	memcpy(d->digest, vi->file_digest, hash_alg->digest_size);
+
+	err = verify_pkcs7_signature(d, sizeof(*d) + hash_alg->digest_size,
+				     signature, sig_size, fsverity_keyring,
+				     VERIFYING_UNSPECIFIED_SIGNATURE,
+				     NULL, NULL);
+	kfree(d);
+
+	if (err) {
+		if (err == -ENOKEY)
+			fsverity_err(inode,
+				     "File's signing cert isn't in the fs-verity keyring");
+		else if (err == -EKEYREJECTED)
+			fsverity_err(inode, "Incorrect file signature");
+		else if (err == -EBADMSG)
+			fsverity_err(inode, "Malformed file signature");
+		else
+			fsverity_err(inode, "Error %d verifying file signature",
+				     err);
+		return err;
+	}
+
+	return 0;
+}
+
+void __init fsverity_init_signature(void)
+{
+	fsverity_keyring =
+		keyring_alloc(".fs-verity", KUIDT_INIT(0), KGIDT_INIT(0),
+			      current_cred(), KEY_POS_SEARCH |
+				KEY_USR_VIEW | KEY_USR_READ | KEY_USR_WRITE |
+				KEY_USR_SEARCH | KEY_USR_SETATTR,
+			      KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
+	if (IS_ERR(fsverity_keyring))
+		panic("failed to allocate \".fs-verity\" keyring");
+}
diff --git a/fs/verity/verify.c b/fs/verity/verify.c
new file mode 100644
index 0000000000..904ccd7e8e
--- /dev/null
+++ b/fs/verity/verify.c
@@ -0,0 +1,364 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Data verification functions, i.e. hooks for ->readahead()
+ *
+ * Copyright 2019 Google LLC
+ */
+
+#include "fsverity_private.h"
+
+#include <crypto/hash.h>
+#include <linux/bio.h>
+
+static struct workqueue_struct *fsverity_read_workqueue;
+
+/*
+ * Returns true if the hash block with index @hblock_idx in the tree, located in
+ * @hpage, has already been verified.
+ */
+static bool is_hash_block_verified(struct fsverity_info *vi, struct page *hpage,
+				   unsigned long hblock_idx)
+{
+	bool verified;
+	unsigned int blocks_per_page;
+	unsigned int i;
+
+	/*
+	 * When the Merkle tree block size and page size are the same, then the
+	 * ->hash_block_verified bitmap isn't allocated, and we use PG_checked
+	 * to directly indicate whether the page's block has been verified.
+	 *
+	 * Using PG_checked also guarantees that we re-verify hash pages that
+	 * get evicted and re-instantiated from the backing storage, as new
+	 * pages always start out with PG_checked cleared.
+	 */
+	if (!vi->hash_block_verified)
+		return PageChecked(hpage);
+
+	/*
+	 * When the Merkle tree block size and page size differ, we use a bitmap
+	 * to indicate whether each hash block has been verified.
+	 *
+	 * However, we still need to ensure that hash pages that get evicted and
+	 * re-instantiated from the backing storage are re-verified.  To do
+	 * this, we use PG_checked again, but now it doesn't really mean
+	 * "checked".  Instead, now it just serves as an indicator for whether
+	 * the hash page is newly instantiated or not.
+	 *
+	 * The first thread that sees PG_checked=0 must clear the corresponding
+	 * bitmap bits, then set PG_checked=1.  This requires a spinlock.  To
+	 * avoid having to take this spinlock in the common case of
+	 * PG_checked=1, we start with an opportunistic lockless read.
+	 */
+	if (PageChecked(hpage)) {
+		/*
+		 * A read memory barrier is needed here to give ACQUIRE
+		 * semantics to the above PageChecked() test.
+		 */
+		smp_rmb();
+		return test_bit(hblock_idx, vi->hash_block_verified);
+	}
+	spin_lock(&vi->hash_page_init_lock);
+	if (PageChecked(hpage)) {
+		verified = test_bit(hblock_idx, vi->hash_block_verified);
+	} else {
+		blocks_per_page = vi->tree_params.blocks_per_page;
+		hblock_idx = round_down(hblock_idx, blocks_per_page);
+		for (i = 0; i < blocks_per_page; i++)
+			clear_bit(hblock_idx + i, vi->hash_block_verified);
+		/*
+		 * A write memory barrier is needed here to give RELEASE
+		 * semantics to the below SetPageChecked() operation.
+		 */
+		smp_wmb();
+		SetPageChecked(hpage);
+		verified = false;
+	}
+	spin_unlock(&vi->hash_page_init_lock);
+	return verified;
+}
+
+/*
+ * Verify a single data block against the file's Merkle tree.
+ *
+ * In principle, we need to verify the entire path to the root node.  However,
+ * for efficiency the filesystem may cache the hash blocks.  Therefore we need
+ * only ascend the tree until an already-verified hash block is seen, and then
+ * verify the path to that block.
+ *
+ * Return: %true if the data block is valid, else %false.
+ */
+static bool
+verify_data_block(struct inode *inode, struct fsverity_info *vi,
+		  const void *data, u64 data_pos, unsigned long max_ra_pages)
+{
+	const struct merkle_tree_params *params = &vi->tree_params;
+	const unsigned int hsize = params->digest_size;
+	int level;
+	u8 _want_hash[FS_VERITY_MAX_DIGEST_SIZE];
+	const u8 *want_hash;
+	u8 real_hash[FS_VERITY_MAX_DIGEST_SIZE];
+	/* The hash blocks that are traversed, indexed by level */
+	struct {
+		/* Page containing the hash block */
+		struct page *page;
+		/* Mapped address of the hash block (will be within @page) */
+		const void *addr;
+		/* Index of the hash block in the tree overall */
+		unsigned long index;
+		/* Byte offset of the wanted hash relative to @addr */
+		unsigned int hoffset;
+	} hblocks[FS_VERITY_MAX_LEVELS];
+	/*
+	 * The index of the previous level's block within that level; also the
+	 * index of that block's hash within the current level.
+	 */
+	u64 hidx = data_pos >> params->log_blocksize;
+
+	/* Up to 1 + FS_VERITY_MAX_LEVELS pages may be mapped at once */
+	BUILD_BUG_ON(1 + FS_VERITY_MAX_LEVELS > KM_MAX_IDX);
+
+	if (unlikely(data_pos >= inode->i_size)) {
+		/*
+		 * This can happen in the data page spanning EOF when the Merkle
+		 * tree block size is less than the page size.  The Merkle tree
+		 * doesn't cover data blocks fully past EOF.  But the entire
+		 * page spanning EOF can be visible to userspace via a mmap, and
+		 * any part past EOF should be all zeroes.  Therefore, we need
+		 * to verify that any data blocks fully past EOF are all zeroes.
+		 */
+		if (memchr_inv(data, 0, params->block_size)) {
+			fsverity_err(inode,
+				     "FILE CORRUPTED!  Data past EOF is not zeroed");
+			return false;
+		}
+		return true;
+	}
+
+	/*
+	 * Starting at the leaf level, ascend the tree saving hash blocks along
+	 * the way until we find a hash block that has already been verified, or
+	 * until we reach the root.
+	 */
+	for (level = 0; level < params->num_levels; level++) {
+		unsigned long next_hidx;
+		unsigned long hblock_idx;
+		pgoff_t hpage_idx;
+		unsigned int hblock_offset_in_page;
+		unsigned int hoffset;
+		struct page *hpage;
+		const void *haddr;
+
+		/*
+		 * The index of the block in the current level; also the index
+		 * of that block's hash within the next level.
+		 */
+		next_hidx = hidx >> params->log_arity;
+
+		/* Index of the hash block in the tree overall */
+		hblock_idx = params->level_start[level] + next_hidx;
+
+		/* Index of the hash page in the tree overall */
+		hpage_idx = hblock_idx >> params->log_blocks_per_page;
+
+		/* Byte offset of the hash block within the page */
+		hblock_offset_in_page =
+			(hblock_idx << params->log_blocksize) & ~PAGE_MASK;
+
+		/* Byte offset of the hash within the block */
+		hoffset = (hidx << params->log_digestsize) &
+			  (params->block_size - 1);
+
+		hpage = inode->i_sb->s_vop->read_merkle_tree_page(inode,
+				hpage_idx, level == 0 ? min(max_ra_pages,
+					params->tree_pages - hpage_idx) : 0);
+		if (IS_ERR(hpage)) {
+			fsverity_err(inode,
+				     "Error %ld reading Merkle tree page %lu",
+				     PTR_ERR(hpage), hpage_idx);
+			goto error;
+		}
+		haddr = kmap_local_page(hpage) + hblock_offset_in_page;
+		if (is_hash_block_verified(vi, hpage, hblock_idx)) {
+			memcpy(_want_hash, haddr + hoffset, hsize);
+			want_hash = _want_hash;
+			kunmap_local(haddr);
+			put_page(hpage);
+			goto descend;
+		}
+		hblocks[level].page = hpage;
+		hblocks[level].addr = haddr;
+		hblocks[level].index = hblock_idx;
+		hblocks[level].hoffset = hoffset;
+		hidx = next_hidx;
+	}
+
+	want_hash = vi->root_hash;
+descend:
+	/* Descend the tree verifying hash blocks. */
+	for (; level > 0; level--) {
+		struct page *hpage = hblocks[level - 1].page;
+		const void *haddr = hblocks[level - 1].addr;
+		unsigned long hblock_idx = hblocks[level - 1].index;
+		unsigned int hoffset = hblocks[level - 1].hoffset;
+
+		if (fsverity_hash_block(params, inode, haddr, real_hash) != 0)
+			goto error;
+		if (memcmp(want_hash, real_hash, hsize) != 0)
+			goto corrupted;
+		/*
+		 * Mark the hash block as verified.  This must be atomic and
+		 * idempotent, as the same hash block might be verified by
+		 * multiple threads concurrently.
+		 */
+		if (vi->hash_block_verified)
+			set_bit(hblock_idx, vi->hash_block_verified);
+		else
+			SetPageChecked(hpage);
+		memcpy(_want_hash, haddr + hoffset, hsize);
+		want_hash = _want_hash;
+		kunmap_local(haddr);
+		put_page(hpage);
+	}
+
+	/* Finally, verify the data block. */
+	if (fsverity_hash_block(params, inode, data, real_hash) != 0)
+		goto error;
+	if (memcmp(want_hash, real_hash, hsize) != 0)
+		goto corrupted;
+	return true;
+
+corrupted:
+	fsverity_err(inode,
+		     "FILE CORRUPTED! pos=%llu, level=%d, want_hash=%s:%*phN, real_hash=%s:%*phN",
+		     data_pos, level - 1,
+		     params->hash_alg->name, hsize, want_hash,
+		     params->hash_alg->name, hsize, real_hash);
+error:
+	for (; level > 0; level--) {
+		kunmap_local(hblocks[level - 1].addr);
+		put_page(hblocks[level - 1].page);
+	}
+	return false;
+}
+
+static bool
+verify_data_blocks(struct folio *data_folio, size_t len, size_t offset,
+		   unsigned long max_ra_pages)
+{
+	struct inode *inode = data_folio->mapping->host;
+	struct fsverity_info *vi = inode->i_verity_info;
+	const unsigned int block_size = vi->tree_params.block_size;
+	u64 pos = (u64)data_folio->index << PAGE_SHIFT;
+
+	if (WARN_ON_ONCE(len <= 0 || !IS_ALIGNED(len | offset, block_size)))
+		return false;
+	if (WARN_ON_ONCE(!folio_test_locked(data_folio) ||
+			 folio_test_uptodate(data_folio)))
+		return false;
+	do {
+		void *data;
+		bool valid;
+
+		data = kmap_local_folio(data_folio, offset);
+		valid = verify_data_block(inode, vi, data, pos + offset,
+					  max_ra_pages);
+		kunmap_local(data);
+		if (!valid)
+			return false;
+		offset += block_size;
+		len -= block_size;
+	} while (len);
+	return true;
+}
+
+/**
+ * fsverity_verify_blocks() - verify data in a folio
+ * @folio: the folio containing the data to verify
+ * @len: the length of the data to verify in the folio
+ * @offset: the offset of the data to verify in the folio
+ *
+ * Verify data that has just been read from a verity file.  The data must be
+ * located in a pagecache folio that is still locked and not yet uptodate.  The
+ * length and offset of the data must be Merkle tree block size aligned.
+ *
+ * Return: %true if the data is valid, else %false.
+ */
+bool fsverity_verify_blocks(struct folio *folio, size_t len, size_t offset)
+{
+	return verify_data_blocks(folio, len, offset, 0);
+}
+EXPORT_SYMBOL_GPL(fsverity_verify_blocks);
+
+#ifdef CONFIG_BLOCK
+/**
+ * fsverity_verify_bio() - verify a 'read' bio that has just completed
+ * @bio: the bio to verify
+ *
+ * Verify the bio's data against the file's Merkle tree.  All bio data segments
+ * must be aligned to the file's Merkle tree block size.  If any data fails
+ * verification, then bio->bi_status is set to an error status.
+ *
+ * This is a helper function for use by the ->readahead() method of filesystems
+ * that issue bios to read data directly into the page cache.  Filesystems that
+ * populate the page cache without issuing bios (e.g. non block-based
+ * filesystems) must instead call fsverity_verify_page() directly on each page.
+ * All filesystems must also call fsverity_verify_page() on holes.
+ */
+void fsverity_verify_bio(struct bio *bio)
+{
+	struct folio_iter fi;
+	unsigned long max_ra_pages = 0;
+
+	if (bio->bi_opf & REQ_RAHEAD) {
+		/*
+		 * If this bio is for data readahead, then we also do readahead
+		 * of the first (largest) level of the Merkle tree.  Namely,
+		 * when a Merkle tree page is read, we also try to piggy-back on
+		 * some additional pages -- up to 1/4 the number of data pages.
+		 *
+		 * This improves sequential read performance, as it greatly
+		 * reduces the number of I/O requests made to the Merkle tree.
+		 */
+		max_ra_pages = bio->bi_iter.bi_size >> (PAGE_SHIFT + 2);
+	}
+
+	bio_for_each_folio_all(fi, bio) {
+		if (!verify_data_blocks(fi.folio, fi.length, fi.offset,
+					max_ra_pages)) {
+			bio->bi_status = BLK_STS_IOERR;
+			break;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(fsverity_verify_bio);
+#endif /* CONFIG_BLOCK */
+
+/**
+ * fsverity_enqueue_verify_work() - enqueue work on the fs-verity workqueue
+ * @work: the work to enqueue
+ *
+ * Enqueue verification work for asynchronous processing.
+ */
+void fsverity_enqueue_verify_work(struct work_struct *work)
+{
+	queue_work(fsverity_read_workqueue, work);
+}
+EXPORT_SYMBOL_GPL(fsverity_enqueue_verify_work);
+
+void __init fsverity_init_workqueue(void)
+{
+	/*
+	 * Use a high-priority workqueue to prioritize verification work, which
+	 * blocks reads from completing, over regular application tasks.
+	 *
+	 * For performance reasons, don't use an unbound workqueue.  Using an
+	 * unbound workqueue for crypto operations causes excessive scheduler
+	 * latency on ARM64.
+	 */
+	fsverity_read_workqueue = alloc_workqueue("fsverity_read_queue",
+						  WQ_HIGHPRI,
+						  num_online_cpus());
+	if (!fsverity_read_workqueue)
+		panic("failed to allocate fsverity_read_queue");
+}