mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-24 03:24:55 +08:00
ff49c86f27
In this round, we've made more work into per-file compression support. For example, F2FS_IOC_GET|SET_COMPRESS_OPTION provides a way to change the algorithm or cluster size per file. F2FS_IOC_COMPRESS|DECOMPRESS_FILE provides a way to compress and decompress the existing normal files manually along with a new mount option, compress_mode=fs|user, which can control who compresses the data. Chao also added a checksum feature with a mount option so that we are able to detect any corrupted cluster. In addition, Daniel contributed casefolding with encryption patch, which will be used for Android devices. Enhancement: - add ioctls and mount option to manage per-file compression feature - support casefolding with encryption - support checksum for compressed cluster - avoid IO starvation by replacing mutex with rwsem - add sysfs, max_io_bytes, to control max bio size Bug fix: - fix use-after-free issue when compression and fsverity are enabled - fix consistency corruption during fault injection test - fix data offset for lseek - get rid of buffer_head which has 32bits limit in fiemap - fix some bugs in multi-partitions support - fix nat entry count calculation in shrinker - fix some stat information And, we've refactored some logics and fix minor bugs as well. -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEE00UqedjCtOrGVvQiQBSofoJIUNIFAl/a8ywACgkQQBSofoJI UNLa2RAAjK+6tOs+NuYx2w9SegghKxwCg4Mb362BMdaAGx6GzMqAkCiVdujuoz/r +wy8sdqO9QE7723ZDNsebNMLRnkNPHnpneSL2p6OsSLJrD3ORTELVRrzNlkemvnK rRHZyYnNJvQQnD4uU7ABvROKsIDw/nCfcFvzHmLIgEw8EHO0W4n6fTtBdTwXv1qi N3qXhGuQldonR9XICuGjzj7wh17n9ua6Mr12XX3Ok38giMcZb9KFBwgvlhl35cxt htEmUpxWD3NTSw6zJmV4VAiajpiIkW6QRQuVA1nzdLZK644gaJMhM1EUsOnZhfDl wX0ZtKoNkXxb0glD34O3aYqeHJ3tHWgPmmpVm9TECJP9A/X7kmEHgQYpH/eJ9I7d tk51Uz28Mz1RShXU4i5RyKZeeoNTLiVlqiC95E2cnq4C1tLOJyI00N9AinrLzvR+ fqUrAwCrBpiYX63mWKYwq7GWxWwp4+PY09kyIZxxJiWhTE/St0bRx2bQL8zA8C6J Rtxl+QWyQhkFbNu8fAukLFAhC6mqX/FKpXvUqRehBnHRvMWBiVZG0//eOPQLk71u qsdCgYuEVcg3itDQrZvmsjxi4Pb5E9mNr0s5oC4I2WvBPMheD4esSyG7cKDN0qfS 3FFHlRYLOvnjPMLnKTmZXjFvFyHR8mwsD4Z83MeSrqYnWC14tFY= =KneU -----END PGP SIGNATURE----- Merge tag 'f2fs-for-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs Pull f2fs updates from Jaegeuk Kim: "In this round, we've made more work into per-file compression support. For example, F2FS_IOC_GET | SET_COMPRESS_OPTION provides a way to change the algorithm or cluster size per file. F2FS_IOC_COMPRESS | DECOMPRESS_FILE provides a way to compress and decompress the existing normal files manually. There is also a new mount option, compress_mode=fs|user, which can control who compresses the data. Chao also added a checksum feature with a mount option so that we are able to detect any corrupted cluster. In addition, Daniel contributed casefolding with encryption patch, which will be used for Android devices. Summary: Enhancements: - add ioctls and mount option to manage per-file compression feature - support casefolding with encryption - support checksum for compressed cluster - avoid IO starvation by replacing mutex with rwsem - add sysfs, max_io_bytes, to control max bio size Bug fixes: - fix use-after-free issue when compression and fsverity are enabled - fix consistency corruption during fault injection test - fix data offset for lseek - get rid of buffer_head which has 32bits limit in fiemap - fix some bugs in multi-partitions support - fix nat entry count calculation in shrinker - fix some stat information And, we've refactored some logics and fix minor bugs as well" * tag 'f2fs-for-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (36 commits) f2fs: compress: fix compression chksum f2fs: fix shift-out-of-bounds in sanity_check_raw_super() f2fs: fix race of pending_pages in decompression f2fs: fix to account inline xattr correctly during recovery f2fs: inline: fix wrong inline inode stat f2fs: inline: correct comment in f2fs_recover_inline_data f2fs: don't check PAGE_SIZE again in sanity_check_raw_super() f2fs: convert to F2FS_*_INO macro f2fs: introduce max_io_bytes, a sysfs entry, to limit bio size f2fs: don't allow any writes on readonly mount f2fs: avoid race condition for shrinker count f2fs: add F2FS_IOC_DECOMPRESS_FILE and F2FS_IOC_COMPRESS_FILE f2fs: add compress_mode mount option f2fs: Remove unnecessary unlikely() f2fs: init dirty_secmap incorrectly f2fs: remove buffer_head which has 32bits limit f2fs: fix wrong block count instead of bytes f2fs: use new conversion functions between blks and bytes f2fs: rename logical_to_blk and blk_to_logical f2fs: fix kbytes written stat for multi-device case ...
387 lines
12 KiB
C
387 lines
12 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* fs/crypto/hooks.c
|
|
*
|
|
* Encryption hooks for higher-level filesystem operations.
|
|
*/
|
|
|
|
#include <linux/key.h>
|
|
|
|
#include "fscrypt_private.h"
|
|
|
|
/**
|
|
* fscrypt_file_open() - prepare to open a possibly-encrypted regular file
|
|
* @inode: the inode being opened
|
|
* @filp: the struct file being set up
|
|
*
|
|
* Currently, an encrypted regular file can only be opened if its encryption key
|
|
* is available; access to the raw encrypted contents is not supported.
|
|
* Therefore, we first set up the inode's encryption key (if not already done)
|
|
* and return an error if it's unavailable.
|
|
*
|
|
* We also verify that if the parent directory (from the path via which the file
|
|
* is being opened) is encrypted, then the inode being opened uses the same
|
|
* encryption policy. This is needed as part of the enforcement that all files
|
|
* in an encrypted directory tree use the same encryption policy, as a
|
|
* protection against certain types of offline attacks. Note that this check is
|
|
* needed even when opening an *unencrypted* file, since it's forbidden to have
|
|
* an unencrypted file in an encrypted directory.
|
|
*
|
|
* Return: 0 on success, -ENOKEY if the key is missing, or another -errno code
|
|
*/
|
|
int fscrypt_file_open(struct inode *inode, struct file *filp)
|
|
{
|
|
int err;
|
|
struct dentry *dir;
|
|
|
|
err = fscrypt_require_key(inode);
|
|
if (err)
|
|
return err;
|
|
|
|
dir = dget_parent(file_dentry(filp));
|
|
if (IS_ENCRYPTED(d_inode(dir)) &&
|
|
!fscrypt_has_permitted_context(d_inode(dir), inode)) {
|
|
fscrypt_warn(inode,
|
|
"Inconsistent encryption context (parent directory: %lu)",
|
|
d_inode(dir)->i_ino);
|
|
err = -EPERM;
|
|
}
|
|
dput(dir);
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(fscrypt_file_open);
|
|
|
|
int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
|
|
struct dentry *dentry)
|
|
{
|
|
if (fscrypt_is_nokey_name(dentry))
|
|
return -ENOKEY;
|
|
/*
|
|
* We don't need to separately check that the directory inode's key is
|
|
* available, as it's implied by the dentry not being a no-key name.
|
|
*/
|
|
|
|
if (!fscrypt_has_permitted_context(dir, inode))
|
|
return -EXDEV;
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__fscrypt_prepare_link);
|
|
|
|
int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
|
|
struct inode *new_dir, struct dentry *new_dentry,
|
|
unsigned int flags)
|
|
{
|
|
if (fscrypt_is_nokey_name(old_dentry) ||
|
|
fscrypt_is_nokey_name(new_dentry))
|
|
return -ENOKEY;
|
|
/*
|
|
* We don't need to separately check that the directory inodes' keys are
|
|
* available, as it's implied by the dentries not being no-key names.
|
|
*/
|
|
|
|
if (old_dir != new_dir) {
|
|
if (IS_ENCRYPTED(new_dir) &&
|
|
!fscrypt_has_permitted_context(new_dir,
|
|
d_inode(old_dentry)))
|
|
return -EXDEV;
|
|
|
|
if ((flags & RENAME_EXCHANGE) &&
|
|
IS_ENCRYPTED(old_dir) &&
|
|
!fscrypt_has_permitted_context(old_dir,
|
|
d_inode(new_dentry)))
|
|
return -EXDEV;
|
|
}
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__fscrypt_prepare_rename);
|
|
|
|
int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
|
|
struct fscrypt_name *fname)
|
|
{
|
|
int err = fscrypt_setup_filename(dir, &dentry->d_name, 1, fname);
|
|
|
|
if (err && err != -ENOENT)
|
|
return err;
|
|
|
|
if (fname->is_nokey_name) {
|
|
spin_lock(&dentry->d_lock);
|
|
dentry->d_flags |= DCACHE_NOKEY_NAME;
|
|
spin_unlock(&dentry->d_lock);
|
|
}
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup);
|
|
|
|
int __fscrypt_prepare_readdir(struct inode *dir)
|
|
{
|
|
return fscrypt_get_encryption_info(dir, true);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__fscrypt_prepare_readdir);
|
|
|
|
int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr)
|
|
{
|
|
if (attr->ia_valid & ATTR_SIZE)
|
|
return fscrypt_require_key(d_inode(dentry));
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__fscrypt_prepare_setattr);
|
|
|
|
/**
|
|
* fscrypt_prepare_setflags() - prepare to change flags with FS_IOC_SETFLAGS
|
|
* @inode: the inode on which flags are being changed
|
|
* @oldflags: the old flags
|
|
* @flags: the new flags
|
|
*
|
|
* The caller should be holding i_rwsem for write.
|
|
*
|
|
* Return: 0 on success; -errno if the flags change isn't allowed or if
|
|
* another error occurs.
|
|
*/
|
|
int fscrypt_prepare_setflags(struct inode *inode,
|
|
unsigned int oldflags, unsigned int flags)
|
|
{
|
|
struct fscrypt_info *ci;
|
|
struct key *key;
|
|
struct fscrypt_master_key *mk;
|
|
int err;
|
|
|
|
/*
|
|
* When the CASEFOLD flag is set on an encrypted directory, we must
|
|
* derive the secret key needed for the dirhash. This is only possible
|
|
* if the directory uses a v2 encryption policy.
|
|
*/
|
|
if (IS_ENCRYPTED(inode) && (flags & ~oldflags & FS_CASEFOLD_FL)) {
|
|
err = fscrypt_require_key(inode);
|
|
if (err)
|
|
return err;
|
|
ci = inode->i_crypt_info;
|
|
if (ci->ci_policy.version != FSCRYPT_POLICY_V2)
|
|
return -EINVAL;
|
|
key = ci->ci_master_key;
|
|
mk = key->payload.data[0];
|
|
down_read(&key->sem);
|
|
if (is_master_key_secret_present(&mk->mk_secret))
|
|
err = fscrypt_derive_dirhash_key(ci, mk);
|
|
else
|
|
err = -ENOKEY;
|
|
up_read(&key->sem);
|
|
return err;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink
|
|
* @dir: directory in which the symlink is being created
|
|
* @target: plaintext symlink target
|
|
* @len: length of @target excluding null terminator
|
|
* @max_len: space the filesystem has available to store the symlink target
|
|
* @disk_link: (out) the on-disk symlink target being prepared
|
|
*
|
|
* This function computes the size the symlink target will require on-disk,
|
|
* stores it in @disk_link->len, and validates it against @max_len. An
|
|
* encrypted symlink may be longer than the original.
|
|
*
|
|
* Additionally, @disk_link->name is set to @target if the symlink will be
|
|
* unencrypted, but left NULL if the symlink will be encrypted. For encrypted
|
|
* symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the
|
|
* on-disk target later. (The reason for the two-step process is that some
|
|
* filesystems need to know the size of the symlink target before creating the
|
|
* inode, e.g. to determine whether it will be a "fast" or "slow" symlink.)
|
|
*
|
|
* Return: 0 on success, -ENAMETOOLONG if the symlink target is too long,
|
|
* -ENOKEY if the encryption key is missing, or another -errno code if a problem
|
|
* occurred while setting up the encryption key.
|
|
*/
|
|
int fscrypt_prepare_symlink(struct inode *dir, const char *target,
|
|
unsigned int len, unsigned int max_len,
|
|
struct fscrypt_str *disk_link)
|
|
{
|
|
const union fscrypt_policy *policy;
|
|
|
|
/*
|
|
* To calculate the size of the encrypted symlink target we need to know
|
|
* the amount of NUL padding, which is determined by the flags set in
|
|
* the encryption policy which will be inherited from the directory.
|
|
*/
|
|
policy = fscrypt_policy_to_inherit(dir);
|
|
if (policy == NULL) {
|
|
/* Not encrypted */
|
|
disk_link->name = (unsigned char *)target;
|
|
disk_link->len = len + 1;
|
|
if (disk_link->len > max_len)
|
|
return -ENAMETOOLONG;
|
|
return 0;
|
|
}
|
|
if (IS_ERR(policy))
|
|
return PTR_ERR(policy);
|
|
|
|
/*
|
|
* Calculate the size of the encrypted symlink and verify it won't
|
|
* exceed max_len. Note that for historical reasons, encrypted symlink
|
|
* targets are prefixed with the ciphertext length, despite this
|
|
* actually being redundant with i_size. This decreases by 2 bytes the
|
|
* longest symlink target we can accept.
|
|
*
|
|
* We could recover 1 byte by not counting a null terminator, but
|
|
* counting it (even though it is meaningless for ciphertext) is simpler
|
|
* for now since filesystems will assume it is there and subtract it.
|
|
*/
|
|
if (!fscrypt_fname_encrypted_size(policy, len,
|
|
max_len - sizeof(struct fscrypt_symlink_data),
|
|
&disk_link->len))
|
|
return -ENAMETOOLONG;
|
|
disk_link->len += sizeof(struct fscrypt_symlink_data);
|
|
|
|
disk_link->name = NULL;
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(fscrypt_prepare_symlink);
|
|
|
|
int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
|
|
unsigned int len, struct fscrypt_str *disk_link)
|
|
{
|
|
int err;
|
|
struct qstr iname = QSTR_INIT(target, len);
|
|
struct fscrypt_symlink_data *sd;
|
|
unsigned int ciphertext_len;
|
|
|
|
/*
|
|
* fscrypt_prepare_new_inode() should have already set up the new
|
|
* symlink inode's encryption key. We don't wait until now to do it,
|
|
* since we may be in a filesystem transaction now.
|
|
*/
|
|
if (WARN_ON_ONCE(!fscrypt_has_encryption_key(inode)))
|
|
return -ENOKEY;
|
|
|
|
if (disk_link->name) {
|
|
/* filesystem-provided buffer */
|
|
sd = (struct fscrypt_symlink_data *)disk_link->name;
|
|
} else {
|
|
sd = kmalloc(disk_link->len, GFP_NOFS);
|
|
if (!sd)
|
|
return -ENOMEM;
|
|
}
|
|
ciphertext_len = disk_link->len - sizeof(*sd);
|
|
sd->len = cpu_to_le16(ciphertext_len);
|
|
|
|
err = fscrypt_fname_encrypt(inode, &iname, sd->encrypted_path,
|
|
ciphertext_len);
|
|
if (err)
|
|
goto err_free_sd;
|
|
|
|
/*
|
|
* Null-terminating the ciphertext doesn't make sense, but we still
|
|
* count the null terminator in the length, so we might as well
|
|
* initialize it just in case the filesystem writes it out.
|
|
*/
|
|
sd->encrypted_path[ciphertext_len] = '\0';
|
|
|
|
/* Cache the plaintext symlink target for later use by get_link() */
|
|
err = -ENOMEM;
|
|
inode->i_link = kmemdup(target, len + 1, GFP_NOFS);
|
|
if (!inode->i_link)
|
|
goto err_free_sd;
|
|
|
|
if (!disk_link->name)
|
|
disk_link->name = (unsigned char *)sd;
|
|
return 0;
|
|
|
|
err_free_sd:
|
|
if (!disk_link->name)
|
|
kfree(sd);
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink);
|
|
|
|
/**
|
|
* fscrypt_get_symlink() - get the target of an encrypted symlink
|
|
* @inode: the symlink inode
|
|
* @caddr: the on-disk contents of the symlink
|
|
* @max_size: size of @caddr buffer
|
|
* @done: if successful, will be set up to free the returned target if needed
|
|
*
|
|
* If the symlink's encryption key is available, we decrypt its target.
|
|
* Otherwise, we encode its target for presentation.
|
|
*
|
|
* This may sleep, so the filesystem must have dropped out of RCU mode already.
|
|
*
|
|
* Return: the presentable symlink target or an ERR_PTR()
|
|
*/
|
|
const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
|
|
unsigned int max_size,
|
|
struct delayed_call *done)
|
|
{
|
|
const struct fscrypt_symlink_data *sd;
|
|
struct fscrypt_str cstr, pstr;
|
|
bool has_key;
|
|
int err;
|
|
|
|
/* This is for encrypted symlinks only */
|
|
if (WARN_ON(!IS_ENCRYPTED(inode)))
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
/* If the decrypted target is already cached, just return it. */
|
|
pstr.name = READ_ONCE(inode->i_link);
|
|
if (pstr.name)
|
|
return pstr.name;
|
|
|
|
/*
|
|
* Try to set up the symlink's encryption key, but we can continue
|
|
* regardless of whether the key is available or not.
|
|
*/
|
|
err = fscrypt_get_encryption_info(inode, false);
|
|
if (err)
|
|
return ERR_PTR(err);
|
|
has_key = fscrypt_has_encryption_key(inode);
|
|
|
|
/*
|
|
* For historical reasons, encrypted symlink targets are prefixed with
|
|
* the ciphertext length, even though this is redundant with i_size.
|
|
*/
|
|
|
|
if (max_size < sizeof(*sd))
|
|
return ERR_PTR(-EUCLEAN);
|
|
sd = caddr;
|
|
cstr.name = (unsigned char *)sd->encrypted_path;
|
|
cstr.len = le16_to_cpu(sd->len);
|
|
|
|
if (cstr.len == 0)
|
|
return ERR_PTR(-EUCLEAN);
|
|
|
|
if (cstr.len + sizeof(*sd) - 1 > max_size)
|
|
return ERR_PTR(-EUCLEAN);
|
|
|
|
err = fscrypt_fname_alloc_buffer(cstr.len, &pstr);
|
|
if (err)
|
|
return ERR_PTR(err);
|
|
|
|
err = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
|
|
if (err)
|
|
goto err_kfree;
|
|
|
|
err = -EUCLEAN;
|
|
if (pstr.name[0] == '\0')
|
|
goto err_kfree;
|
|
|
|
pstr.name[pstr.len] = '\0';
|
|
|
|
/*
|
|
* Cache decrypted symlink targets in i_link for later use. Don't cache
|
|
* symlink targets encoded without the key, since those become outdated
|
|
* once the key is added. This pairs with the READ_ONCE() above and in
|
|
* the VFS path lookup code.
|
|
*/
|
|
if (!has_key ||
|
|
cmpxchg_release(&inode->i_link, NULL, pstr.name) != NULL)
|
|
set_delayed_call(done, kfree_link, pstr.name);
|
|
|
|
return pstr.name;
|
|
|
|
err_kfree:
|
|
kfree(pstr.name);
|
|
return ERR_PTR(err);
|
|
}
|
|
EXPORT_SYMBOL_GPL(fscrypt_get_symlink);
|