mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 19:00:25 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCYCegywAKCRCRxhvAZXjc
ouJ6AQDlf+7jCQlQdeKKoN9QDFfMzG1ooemat36EpRRTONaGuAD8D9A4sUsG4+5f
4IU5Lj9oY4DEmF8HenbWK2ZHsesL2Qg=
=yPaw
-----END PGP SIGNATURE-----
Merge tag 'idmapped-mounts-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux
Pull idmapped mounts from Christian Brauner:
"This introduces idmapped mounts which has been in the making for some
time. Simply put, different mounts can expose the same file or
directory with different ownership. This initial implementation comes
with ports for fat, ext4 and with Christoph's port for xfs with more
filesystems being actively worked on by independent people and
maintainers.
Idmapping mounts handle a wide range of long standing use-cases. Here
are just a few:
- Idmapped mounts make it possible to easily share files between
multiple users or multiple machines especially in complex
scenarios. For example, idmapped mounts will be used in the
implementation of portable home directories in
systemd-homed.service(8) where they allow users to move their home
directory to an external storage device and use it on multiple
computers where they are assigned different uids and gids. This
effectively makes it possible to assign random uids and gids at
login time.
- It is possible to share files from the host with unprivileged
containers without having to change ownership permanently through
chown(2).
- It is possible to idmap a container's rootfs and without having to
mangle every file. For example, Chromebooks use it to share the
user's Download folder with their unprivileged containers in their
Linux subsystem.
- It is possible to share files between containers with
non-overlapping idmappings.
- Filesystem that lack a proper concept of ownership such as fat can
use idmapped mounts to implement discretionary access (DAC)
permission checking.
- They allow users to efficiently changing ownership on a per-mount
basis without having to (recursively) chown(2) all files. In
contrast to chown (2) changing ownership of large sets of files is
instantenous with idmapped mounts. This is especially useful when
ownership of a whole root filesystem of a virtual machine or
container is changed. With idmapped mounts a single syscall
mount_setattr syscall will be sufficient to change the ownership of
all files.
- Idmapped mounts always take the current ownership into account as
idmappings specify what a given uid or gid is supposed to be mapped
to. This contrasts with the chown(2) syscall which cannot by itself
take the current ownership of the files it changes into account. It
simply changes the ownership to the specified uid and gid. This is
especially problematic when recursively chown(2)ing a large set of
files which is commong with the aforementioned portable home
directory and container and vm scenario.
- Idmapped mounts allow to change ownership locally, restricting it
to specific mounts, and temporarily as the ownership changes only
apply as long as the mount exists.
Several userspace projects have either already put up patches and
pull-requests for this feature or will do so should you decide to pull
this:
- systemd: In a wide variety of scenarios but especially right away
in their implementation of portable home directories.
https://systemd.io/HOME_DIRECTORY/
- container runtimes: containerd, runC, LXD:To share data between
host and unprivileged containers, unprivileged and privileged
containers, etc. The pull request for idmapped mounts support in
containerd, the default Kubernetes runtime is already up for quite
a while now: https://github.com/containerd/containerd/pull/4734
- The virtio-fs developers and several users have expressed interest
in using this feature with virtual machines once virtio-fs is
ported.
- ChromeOS: Sharing host-directories with unprivileged containers.
I've tightly synced with all those projects and all of those listed
here have also expressed their need/desire for this feature on the
mailing list. For more info on how people use this there's a bunch of
talks about this too. Here's just two recent ones:
https://www.cncf.io/wp-content/uploads/2020/12/Rootless-Containers-in-Gitpod.pdf
https://fosdem.org/2021/schedule/event/containers_idmap/
This comes with an extensive xfstests suite covering both ext4 and
xfs:
https://git.kernel.org/brauner/xfstests-dev/h/idmapped_mounts
It covers truncation, creation, opening, xattrs, vfscaps, setid
execution, setgid inheritance and more both with idmapped and
non-idmapped mounts. It already helped to discover an unrelated xfs
setgid inheritance bug which has since been fixed in mainline. It will
be sent for inclusion with the xfstests project should you decide to
merge this.
In order to support per-mount idmappings vfsmounts are marked with
user namespaces. The idmapping of the user namespace will be used to
map the ids of vfs objects when they are accessed through that mount.
By default all vfsmounts are marked with the initial user namespace.
The initial user namespace is used to indicate that a mount is not
idmapped. All operations behave as before and this is verified in the
testsuite.
Based on prior discussions we want to attach the whole user namespace
and not just a dedicated idmapping struct. This allows us to reuse all
the helpers that already exist for dealing with idmappings instead of
introducing a whole new range of helpers. In addition, if we decide in
the future that we are confident enough to enable unprivileged users
to setup idmapped mounts the permission checking can take into account
whether the caller is privileged in the user namespace the mount is
currently marked with.
The user namespace the mount will be marked with can be specified by
passing a file descriptor refering to the user namespace as an
argument to the new mount_setattr() syscall together with the new
MOUNT_ATTR_IDMAP flag. The system call follows the openat2() pattern
of extensibility.
The following conditions must be met in order to create an idmapped
mount:
- The caller must currently have the CAP_SYS_ADMIN capability in the
user namespace the underlying filesystem has been mounted in.
- The underlying filesystem must support idmapped mounts.
- The mount must not already be idmapped. This also implies that the
idmapping of a mount cannot be altered once it has been idmapped.
- The mount must be a detached/anonymous mount, i.e. it must have
been created by calling open_tree() with the OPEN_TREE_CLONE flag
and it must not already have been visible in the filesystem.
The last two points guarantee easier semantics for userspace and the
kernel and make the implementation significantly simpler.
By default vfsmounts are marked with the initial user namespace and no
behavioral or performance changes are observed.
The manpage with a detailed description can be found here:
1d7b902e28
In order to support idmapped mounts, filesystems need to be changed
and mark themselves with the FS_ALLOW_IDMAP flag in fs_flags. The
patches to convert individual filesystem are not very large or
complicated overall as can be seen from the included fat, ext4, and
xfs ports. Patches for other filesystems are actively worked on and
will be sent out separately. The xfstestsuite can be used to verify
that port has been done correctly.
The mount_setattr() syscall is motivated independent of the idmapped
mounts patches and it's been around since July 2019. One of the most
valuable features of the new mount api is the ability to perform
mounts based on file descriptors only.
Together with the lookup restrictions available in the openat2()
RESOLVE_* flag namespace which we added in v5.6 this is the first time
we are close to hardened and race-free (e.g. symlinks) mounting and
path resolution.
While userspace has started porting to the new mount api to mount
proper filesystems and create new bind-mounts it is currently not
possible to change mount options of an already existing bind mount in
the new mount api since the mount_setattr() syscall is missing.
With the addition of the mount_setattr() syscall we remove this last
restriction and userspace can now fully port to the new mount api,
covering every use-case the old mount api could. We also add the
crucial ability to recursively change mount options for a whole mount
tree, both removing and adding mount options at the same time. This
syscall has been requested multiple times by various people and
projects.
There is a simple tool available at
https://github.com/brauner/mount-idmapped
that allows to create idmapped mounts so people can play with this
patch series. I'll add support for the regular mount binary should you
decide to pull this in the following weeks:
Here's an example to a simple idmapped mount of another user's home
directory:
u1001@f2-vm:/$ sudo ./mount --idmap both:1000:1001:1 /home/ubuntu/ /mnt
u1001@f2-vm:/$ ls -al /home/ubuntu/
total 28
drwxr-xr-x 2 ubuntu ubuntu 4096 Oct 28 22:07 .
drwxr-xr-x 4 root root 4096 Oct 28 04:00 ..
-rw------- 1 ubuntu ubuntu 3154 Oct 28 22:12 .bash_history
-rw-r--r-- 1 ubuntu ubuntu 220 Feb 25 2020 .bash_logout
-rw-r--r-- 1 ubuntu ubuntu 3771 Feb 25 2020 .bashrc
-rw-r--r-- 1 ubuntu ubuntu 807 Feb 25 2020 .profile
-rw-r--r-- 1 ubuntu ubuntu 0 Oct 16 16:11 .sudo_as_admin_successful
-rw------- 1 ubuntu ubuntu 1144 Oct 28 00:43 .viminfo
u1001@f2-vm:/$ ls -al /mnt/
total 28
drwxr-xr-x 2 u1001 u1001 4096 Oct 28 22:07 .
drwxr-xr-x 29 root root 4096 Oct 28 22:01 ..
-rw------- 1 u1001 u1001 3154 Oct 28 22:12 .bash_history
-rw-r--r-- 1 u1001 u1001 220 Feb 25 2020 .bash_logout
-rw-r--r-- 1 u1001 u1001 3771 Feb 25 2020 .bashrc
-rw-r--r-- 1 u1001 u1001 807 Feb 25 2020 .profile
-rw-r--r-- 1 u1001 u1001 0 Oct 16 16:11 .sudo_as_admin_successful
-rw------- 1 u1001 u1001 1144 Oct 28 00:43 .viminfo
u1001@f2-vm:/$ touch /mnt/my-file
u1001@f2-vm:/$ setfacl -m u:1001:rwx /mnt/my-file
u1001@f2-vm:/$ sudo setcap -n 1001 cap_net_raw+ep /mnt/my-file
u1001@f2-vm:/$ ls -al /mnt/my-file
-rw-rwxr--+ 1 u1001 u1001 0 Oct 28 22:14 /mnt/my-file
u1001@f2-vm:/$ ls -al /home/ubuntu/my-file
-rw-rwxr--+ 1 ubuntu ubuntu 0 Oct 28 22:14 /home/ubuntu/my-file
u1001@f2-vm:/$ getfacl /mnt/my-file
getfacl: Removing leading '/' from absolute path names
# file: mnt/my-file
# owner: u1001
# group: u1001
user::rw-
user:u1001:rwx
group::rw-
mask::rwx
other::r--
u1001@f2-vm:/$ getfacl /home/ubuntu/my-file
getfacl: Removing leading '/' from absolute path names
# file: home/ubuntu/my-file
# owner: ubuntu
# group: ubuntu
user::rw-
user:ubuntu:rwx
group::rw-
mask::rwx
other::r--"
* tag 'idmapped-mounts-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux: (41 commits)
xfs: remove the possibly unused mp variable in xfs_file_compat_ioctl
xfs: support idmapped mounts
ext4: support idmapped mounts
fat: handle idmapped mounts
tests: add mount_setattr() selftests
fs: introduce MOUNT_ATTR_IDMAP
fs: add mount_setattr()
fs: add attr_flags_to_mnt_flags helper
fs: split out functions to hold writers
namespace: only take read lock in do_reconfigure_mnt()
mount: make {lock,unlock}_mount_hash() static
namespace: take lock_mount_hash() directly when changing flags
nfs: do not export idmapped mounts
overlayfs: do not mount on top of idmapped mounts
ecryptfs: do not mount on top of idmapped mounts
ima: handle idmapped mounts
apparmor: handle idmapped mounts
fs: make helpers idmap mount aware
exec: handle idmapped mounts
would_dump: handle idmapped mounts
...
1345 lines
31 KiB
C
1345 lines
31 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* fs/f2fs/namei.c
|
|
*
|
|
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
|
|
* http://www.samsung.com/
|
|
*/
|
|
#include <linux/fs.h>
|
|
#include <linux/f2fs_fs.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/ctype.h>
|
|
#include <linux/random.h>
|
|
#include <linux/dcache.h>
|
|
#include <linux/namei.h>
|
|
#include <linux/quotaops.h>
|
|
|
|
#include "f2fs.h"
|
|
#include "node.h"
|
|
#include "segment.h"
|
|
#include "xattr.h"
|
|
#include "acl.h"
|
|
#include <trace/events/f2fs.h>
|
|
|
|
static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
nid_t ino;
|
|
struct inode *inode;
|
|
bool nid_free = false;
|
|
bool encrypt = false;
|
|
int xattr_size = 0;
|
|
int err;
|
|
|
|
inode = new_inode(dir->i_sb);
|
|
if (!inode)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
f2fs_lock_op(sbi);
|
|
if (!f2fs_alloc_nid(sbi, &ino)) {
|
|
f2fs_unlock_op(sbi);
|
|
err = -ENOSPC;
|
|
goto fail;
|
|
}
|
|
f2fs_unlock_op(sbi);
|
|
|
|
nid_free = true;
|
|
|
|
inode_init_owner(&init_user_ns, inode, dir, mode);
|
|
|
|
inode->i_ino = ino;
|
|
inode->i_blocks = 0;
|
|
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
|
|
F2FS_I(inode)->i_crtime = inode->i_mtime;
|
|
inode->i_generation = prandom_u32();
|
|
|
|
if (S_ISDIR(inode->i_mode))
|
|
F2FS_I(inode)->i_current_depth = 1;
|
|
|
|
err = insert_inode_locked(inode);
|
|
if (err) {
|
|
err = -EINVAL;
|
|
goto fail;
|
|
}
|
|
|
|
if (f2fs_sb_has_project_quota(sbi) &&
|
|
(F2FS_I(dir)->i_flags & F2FS_PROJINHERIT_FL))
|
|
F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid;
|
|
else
|
|
F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns,
|
|
F2FS_DEF_PROJID);
|
|
|
|
err = fscrypt_prepare_new_inode(dir, inode, &encrypt);
|
|
if (err)
|
|
goto fail_drop;
|
|
|
|
err = dquot_initialize(inode);
|
|
if (err)
|
|
goto fail_drop;
|
|
|
|
set_inode_flag(inode, FI_NEW_INODE);
|
|
|
|
if (encrypt)
|
|
f2fs_set_encrypted_inode(inode);
|
|
|
|
if (f2fs_sb_has_extra_attr(sbi)) {
|
|
set_inode_flag(inode, FI_EXTRA_ATTR);
|
|
F2FS_I(inode)->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE;
|
|
}
|
|
|
|
if (test_opt(sbi, INLINE_XATTR))
|
|
set_inode_flag(inode, FI_INLINE_XATTR);
|
|
|
|
if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
|
|
set_inode_flag(inode, FI_INLINE_DATA);
|
|
if (f2fs_may_inline_dentry(inode))
|
|
set_inode_flag(inode, FI_INLINE_DENTRY);
|
|
|
|
if (f2fs_sb_has_flexible_inline_xattr(sbi)) {
|
|
f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode));
|
|
if (f2fs_has_inline_xattr(inode))
|
|
xattr_size = F2FS_OPTION(sbi).inline_xattr_size;
|
|
/* Otherwise, will be 0 */
|
|
} else if (f2fs_has_inline_xattr(inode) ||
|
|
f2fs_has_inline_dentry(inode)) {
|
|
xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
|
|
}
|
|
F2FS_I(inode)->i_inline_xattr_size = xattr_size;
|
|
|
|
f2fs_init_extent_tree(inode, NULL);
|
|
|
|
stat_inc_inline_xattr(inode);
|
|
stat_inc_inline_inode(inode);
|
|
stat_inc_inline_dir(inode);
|
|
|
|
F2FS_I(inode)->i_flags =
|
|
f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED);
|
|
|
|
if (S_ISDIR(inode->i_mode))
|
|
F2FS_I(inode)->i_flags |= F2FS_INDEX_FL;
|
|
|
|
if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL)
|
|
set_inode_flag(inode, FI_PROJ_INHERIT);
|
|
|
|
if (f2fs_sb_has_compression(sbi)) {
|
|
/* Inherit the compression flag in directory */
|
|
if ((F2FS_I(dir)->i_flags & F2FS_COMPR_FL) &&
|
|
f2fs_may_compress(inode))
|
|
set_compress_context(inode);
|
|
}
|
|
|
|
f2fs_set_inode_flags(inode);
|
|
|
|
trace_f2fs_new_inode(inode, 0);
|
|
return inode;
|
|
|
|
fail:
|
|
trace_f2fs_new_inode(inode, err);
|
|
make_bad_inode(inode);
|
|
if (nid_free)
|
|
set_inode_flag(inode, FI_FREE_NID);
|
|
iput(inode);
|
|
return ERR_PTR(err);
|
|
fail_drop:
|
|
trace_f2fs_new_inode(inode, err);
|
|
dquot_drop(inode);
|
|
inode->i_flags |= S_NOQUOTA;
|
|
if (nid_free)
|
|
set_inode_flag(inode, FI_FREE_NID);
|
|
clear_nlink(inode);
|
|
unlock_new_inode(inode);
|
|
iput(inode);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
static inline int is_extension_exist(const unsigned char *s, const char *sub)
|
|
{
|
|
size_t slen = strlen(s);
|
|
size_t sublen = strlen(sub);
|
|
int i;
|
|
|
|
if (sublen == 1 && *sub == '*')
|
|
return 1;
|
|
|
|
/*
|
|
* filename format of multimedia file should be defined as:
|
|
* "filename + '.' + extension + (optional: '.' + temp extension)".
|
|
*/
|
|
if (slen < sublen + 2)
|
|
return 0;
|
|
|
|
for (i = 1; i < slen - sublen; i++) {
|
|
if (s[i] != '.')
|
|
continue;
|
|
if (!strncasecmp(s + i + 1, sub, sublen))
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Set file's temperature for hot/cold data separation
|
|
*/
|
|
static inline void set_file_temperature(struct f2fs_sb_info *sbi, struct inode *inode,
|
|
const unsigned char *name)
|
|
{
|
|
__u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list;
|
|
int i, cold_count, hot_count;
|
|
|
|
down_read(&sbi->sb_lock);
|
|
|
|
cold_count = le32_to_cpu(sbi->raw_super->extension_count);
|
|
hot_count = sbi->raw_super->hot_ext_count;
|
|
|
|
for (i = 0; i < cold_count + hot_count; i++) {
|
|
if (is_extension_exist(name, extlist[i]))
|
|
break;
|
|
}
|
|
|
|
up_read(&sbi->sb_lock);
|
|
|
|
if (i == cold_count + hot_count)
|
|
return;
|
|
|
|
if (i < cold_count)
|
|
file_set_cold(inode);
|
|
else
|
|
file_set_hot(inode);
|
|
}
|
|
|
|
int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
|
|
bool hot, bool set)
|
|
{
|
|
__u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list;
|
|
int cold_count = le32_to_cpu(sbi->raw_super->extension_count);
|
|
int hot_count = sbi->raw_super->hot_ext_count;
|
|
int total_count = cold_count + hot_count;
|
|
int start, count;
|
|
int i;
|
|
|
|
if (set) {
|
|
if (total_count == F2FS_MAX_EXTENSION)
|
|
return -EINVAL;
|
|
} else {
|
|
if (!hot && !cold_count)
|
|
return -EINVAL;
|
|
if (hot && !hot_count)
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (hot) {
|
|
start = cold_count;
|
|
count = total_count;
|
|
} else {
|
|
start = 0;
|
|
count = cold_count;
|
|
}
|
|
|
|
for (i = start; i < count; i++) {
|
|
if (strcmp(name, extlist[i]))
|
|
continue;
|
|
|
|
if (set)
|
|
return -EINVAL;
|
|
|
|
memcpy(extlist[i], extlist[i + 1],
|
|
F2FS_EXTENSION_LEN * (total_count - i - 1));
|
|
memset(extlist[total_count - 1], 0, F2FS_EXTENSION_LEN);
|
|
if (hot)
|
|
sbi->raw_super->hot_ext_count = hot_count - 1;
|
|
else
|
|
sbi->raw_super->extension_count =
|
|
cpu_to_le32(cold_count - 1);
|
|
return 0;
|
|
}
|
|
|
|
if (!set)
|
|
return -EINVAL;
|
|
|
|
if (hot) {
|
|
memcpy(extlist[count], name, strlen(name));
|
|
sbi->raw_super->hot_ext_count = hot_count + 1;
|
|
} else {
|
|
char buf[F2FS_MAX_EXTENSION][F2FS_EXTENSION_LEN];
|
|
|
|
memcpy(buf, &extlist[cold_count],
|
|
F2FS_EXTENSION_LEN * hot_count);
|
|
memset(extlist[cold_count], 0, F2FS_EXTENSION_LEN);
|
|
memcpy(extlist[cold_count], name, strlen(name));
|
|
memcpy(&extlist[cold_count + 1], buf,
|
|
F2FS_EXTENSION_LEN * hot_count);
|
|
sbi->raw_super->extension_count = cpu_to_le32(cold_count + 1);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static void set_compress_inode(struct f2fs_sb_info *sbi, struct inode *inode,
|
|
const unsigned char *name)
|
|
{
|
|
__u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list;
|
|
unsigned char (*ext)[F2FS_EXTENSION_LEN];
|
|
unsigned int ext_cnt = F2FS_OPTION(sbi).compress_ext_cnt;
|
|
int i, cold_count, hot_count;
|
|
|
|
if (!f2fs_sb_has_compression(sbi) ||
|
|
is_inode_flag_set(inode, FI_COMPRESSED_FILE) ||
|
|
F2FS_I(inode)->i_flags & F2FS_NOCOMP_FL ||
|
|
!f2fs_may_compress(inode))
|
|
return;
|
|
|
|
down_read(&sbi->sb_lock);
|
|
|
|
cold_count = le32_to_cpu(sbi->raw_super->extension_count);
|
|
hot_count = sbi->raw_super->hot_ext_count;
|
|
|
|
for (i = cold_count; i < cold_count + hot_count; i++) {
|
|
if (is_extension_exist(name, extlist[i])) {
|
|
up_read(&sbi->sb_lock);
|
|
return;
|
|
}
|
|
}
|
|
|
|
up_read(&sbi->sb_lock);
|
|
|
|
ext = F2FS_OPTION(sbi).extensions;
|
|
|
|
for (i = 0; i < ext_cnt; i++) {
|
|
if (!is_extension_exist(name, ext[i]))
|
|
continue;
|
|
|
|
set_compress_context(inode);
|
|
return;
|
|
}
|
|
}
|
|
|
|
static int f2fs_create(struct user_namespace *mnt_userns, struct inode *dir,
|
|
struct dentry *dentry, umode_t mode, bool excl)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
struct inode *inode;
|
|
nid_t ino = 0;
|
|
int err;
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
return -EIO;
|
|
if (!f2fs_is_checkpoint_ready(sbi))
|
|
return -ENOSPC;
|
|
|
|
err = dquot_initialize(dir);
|
|
if (err)
|
|
return err;
|
|
|
|
inode = f2fs_new_inode(dir, mode);
|
|
if (IS_ERR(inode))
|
|
return PTR_ERR(inode);
|
|
|
|
if (!test_opt(sbi, DISABLE_EXT_IDENTIFY))
|
|
set_file_temperature(sbi, inode, dentry->d_name.name);
|
|
|
|
set_compress_inode(sbi, inode, dentry->d_name.name);
|
|
|
|
inode->i_op = &f2fs_file_inode_operations;
|
|
inode->i_fop = &f2fs_file_operations;
|
|
inode->i_mapping->a_ops = &f2fs_dblock_aops;
|
|
ino = inode->i_ino;
|
|
|
|
f2fs_lock_op(sbi);
|
|
err = f2fs_add_link(dentry, inode);
|
|
if (err)
|
|
goto out;
|
|
f2fs_unlock_op(sbi);
|
|
|
|
f2fs_alloc_nid_done(sbi, ino);
|
|
|
|
d_instantiate_new(dentry, inode);
|
|
|
|
if (IS_DIRSYNC(dir))
|
|
f2fs_sync_fs(sbi->sb, 1);
|
|
|
|
f2fs_balance_fs(sbi, true);
|
|
return 0;
|
|
out:
|
|
f2fs_handle_failed_inode(inode);
|
|
return err;
|
|
}
|
|
|
|
static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
|
|
struct dentry *dentry)
|
|
{
|
|
struct inode *inode = d_inode(old_dentry);
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
int err;
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
return -EIO;
|
|
if (!f2fs_is_checkpoint_ready(sbi))
|
|
return -ENOSPC;
|
|
|
|
err = fscrypt_prepare_link(old_dentry, dir, dentry);
|
|
if (err)
|
|
return err;
|
|
|
|
if (is_inode_flag_set(dir, FI_PROJ_INHERIT) &&
|
|
(!projid_eq(F2FS_I(dir)->i_projid,
|
|
F2FS_I(old_dentry->d_inode)->i_projid)))
|
|
return -EXDEV;
|
|
|
|
err = dquot_initialize(dir);
|
|
if (err)
|
|
return err;
|
|
|
|
f2fs_balance_fs(sbi, true);
|
|
|
|
inode->i_ctime = current_time(inode);
|
|
ihold(inode);
|
|
|
|
set_inode_flag(inode, FI_INC_LINK);
|
|
f2fs_lock_op(sbi);
|
|
err = f2fs_add_link(dentry, inode);
|
|
if (err)
|
|
goto out;
|
|
f2fs_unlock_op(sbi);
|
|
|
|
d_instantiate(dentry, inode);
|
|
|
|
if (IS_DIRSYNC(dir))
|
|
f2fs_sync_fs(sbi->sb, 1);
|
|
return 0;
|
|
out:
|
|
clear_inode_flag(inode, FI_INC_LINK);
|
|
iput(inode);
|
|
f2fs_unlock_op(sbi);
|
|
return err;
|
|
}
|
|
|
|
struct dentry *f2fs_get_parent(struct dentry *child)
|
|
{
|
|
struct qstr dotdot = QSTR_INIT("..", 2);
|
|
struct page *page;
|
|
unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot, &page);
|
|
if (!ino) {
|
|
if (IS_ERR(page))
|
|
return ERR_CAST(page);
|
|
return ERR_PTR(-ENOENT);
|
|
}
|
|
return d_obtain_alias(f2fs_iget(child->d_sb, ino));
|
|
}
|
|
|
|
static int __recover_dot_dentries(struct inode *dir, nid_t pino)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
struct qstr dot = QSTR_INIT(".", 1);
|
|
struct qstr dotdot = QSTR_INIT("..", 2);
|
|
struct f2fs_dir_entry *de;
|
|
struct page *page;
|
|
int err = 0;
|
|
|
|
if (f2fs_readonly(sbi->sb)) {
|
|
f2fs_info(sbi, "skip recovering inline_dots inode (ino:%lu, pino:%u) in readonly mountpoint",
|
|
dir->i_ino, pino);
|
|
return 0;
|
|
}
|
|
|
|
err = dquot_initialize(dir);
|
|
if (err)
|
|
return err;
|
|
|
|
f2fs_balance_fs(sbi, true);
|
|
|
|
f2fs_lock_op(sbi);
|
|
|
|
de = f2fs_find_entry(dir, &dot, &page);
|
|
if (de) {
|
|
f2fs_put_page(page, 0);
|
|
} else if (IS_ERR(page)) {
|
|
err = PTR_ERR(page);
|
|
goto out;
|
|
} else {
|
|
err = f2fs_do_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
|
|
if (err)
|
|
goto out;
|
|
}
|
|
|
|
de = f2fs_find_entry(dir, &dotdot, &page);
|
|
if (de)
|
|
f2fs_put_page(page, 0);
|
|
else if (IS_ERR(page))
|
|
err = PTR_ERR(page);
|
|
else
|
|
err = f2fs_do_add_link(dir, &dotdot, NULL, pino, S_IFDIR);
|
|
out:
|
|
if (!err)
|
|
clear_inode_flag(dir, FI_INLINE_DOTS);
|
|
|
|
f2fs_unlock_op(sbi);
|
|
return err;
|
|
}
|
|
|
|
static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
|
|
unsigned int flags)
|
|
{
|
|
struct inode *inode = NULL;
|
|
struct f2fs_dir_entry *de;
|
|
struct page *page;
|
|
struct dentry *new;
|
|
nid_t ino = -1;
|
|
int err = 0;
|
|
unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
|
|
struct f2fs_filename fname;
|
|
|
|
trace_f2fs_lookup_start(dir, dentry, flags);
|
|
|
|
if (dentry->d_name.len > F2FS_NAME_LEN) {
|
|
err = -ENAMETOOLONG;
|
|
goto out;
|
|
}
|
|
|
|
err = f2fs_prepare_lookup(dir, dentry, &fname);
|
|
generic_set_encrypted_ci_d_ops(dentry);
|
|
if (err == -ENOENT)
|
|
goto out_splice;
|
|
if (err)
|
|
goto out;
|
|
de = __f2fs_find_entry(dir, &fname, &page);
|
|
f2fs_free_filename(&fname);
|
|
|
|
if (!de) {
|
|
if (IS_ERR(page)) {
|
|
err = PTR_ERR(page);
|
|
goto out;
|
|
}
|
|
err = -ENOENT;
|
|
goto out_splice;
|
|
}
|
|
|
|
ino = le32_to_cpu(de->ino);
|
|
f2fs_put_page(page, 0);
|
|
|
|
inode = f2fs_iget(dir->i_sb, ino);
|
|
if (IS_ERR(inode)) {
|
|
err = PTR_ERR(inode);
|
|
goto out;
|
|
}
|
|
|
|
if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) {
|
|
err = __recover_dot_dentries(dir, root_ino);
|
|
if (err)
|
|
goto out_iput;
|
|
}
|
|
|
|
if (f2fs_has_inline_dots(inode)) {
|
|
err = __recover_dot_dentries(inode, dir->i_ino);
|
|
if (err)
|
|
goto out_iput;
|
|
}
|
|
if (IS_ENCRYPTED(dir) &&
|
|
(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
|
|
!fscrypt_has_permitted_context(dir, inode)) {
|
|
f2fs_warn(F2FS_I_SB(inode), "Inconsistent encryption contexts: %lu/%lu",
|
|
dir->i_ino, inode->i_ino);
|
|
err = -EPERM;
|
|
goto out_iput;
|
|
}
|
|
out_splice:
|
|
#ifdef CONFIG_UNICODE
|
|
if (!inode && IS_CASEFOLDED(dir)) {
|
|
/* Eventually we want to call d_add_ci(dentry, NULL)
|
|
* for negative dentries in the encoding case as
|
|
* well. For now, prevent the negative dentry
|
|
* from being cached.
|
|
*/
|
|
trace_f2fs_lookup_end(dir, dentry, ino, err);
|
|
return NULL;
|
|
}
|
|
#endif
|
|
new = d_splice_alias(inode, dentry);
|
|
err = PTR_ERR_OR_ZERO(new);
|
|
trace_f2fs_lookup_end(dir, dentry, ino, !new ? -ENOENT : err);
|
|
return new;
|
|
out_iput:
|
|
iput(inode);
|
|
out:
|
|
trace_f2fs_lookup_end(dir, dentry, ino, err);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
struct inode *inode = d_inode(dentry);
|
|
struct f2fs_dir_entry *de;
|
|
struct page *page;
|
|
int err;
|
|
|
|
trace_f2fs_unlink_enter(dir, dentry);
|
|
|
|
if (unlikely(f2fs_cp_error(sbi))) {
|
|
err = -EIO;
|
|
goto fail;
|
|
}
|
|
|
|
err = dquot_initialize(dir);
|
|
if (err)
|
|
goto fail;
|
|
err = dquot_initialize(inode);
|
|
if (err)
|
|
goto fail;
|
|
|
|
de = f2fs_find_entry(dir, &dentry->d_name, &page);
|
|
if (!de) {
|
|
if (IS_ERR(page))
|
|
err = PTR_ERR(page);
|
|
goto fail;
|
|
}
|
|
|
|
f2fs_balance_fs(sbi, true);
|
|
|
|
f2fs_lock_op(sbi);
|
|
err = f2fs_acquire_orphan_inode(sbi);
|
|
if (err) {
|
|
f2fs_unlock_op(sbi);
|
|
f2fs_put_page(page, 0);
|
|
goto fail;
|
|
}
|
|
f2fs_delete_entry(de, page, dir, inode);
|
|
#ifdef CONFIG_UNICODE
|
|
/* VFS negative dentries are incompatible with Encoding and
|
|
* Case-insensitiveness. Eventually we'll want avoid
|
|
* invalidating the dentries here, alongside with returning the
|
|
* negative dentries at f2fs_lookup(), when it is better
|
|
* supported by the VFS for the CI case.
|
|
*/
|
|
if (IS_CASEFOLDED(dir))
|
|
d_invalidate(dentry);
|
|
#endif
|
|
f2fs_unlock_op(sbi);
|
|
|
|
if (IS_DIRSYNC(dir))
|
|
f2fs_sync_fs(sbi->sb, 1);
|
|
fail:
|
|
trace_f2fs_unlink_exit(inode, err);
|
|
return err;
|
|
}
|
|
|
|
static const char *f2fs_get_link(struct dentry *dentry,
|
|
struct inode *inode,
|
|
struct delayed_call *done)
|
|
{
|
|
const char *link = page_get_link(dentry, inode, done);
|
|
if (!IS_ERR(link) && !*link) {
|
|
/* this is broken symlink case */
|
|
do_delayed_call(done);
|
|
clear_delayed_call(done);
|
|
link = ERR_PTR(-ENOENT);
|
|
}
|
|
return link;
|
|
}
|
|
|
|
static int f2fs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
|
|
struct dentry *dentry, const char *symname)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
struct inode *inode;
|
|
size_t len = strlen(symname);
|
|
struct fscrypt_str disk_link;
|
|
int err;
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
return -EIO;
|
|
if (!f2fs_is_checkpoint_ready(sbi))
|
|
return -ENOSPC;
|
|
|
|
err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize,
|
|
&disk_link);
|
|
if (err)
|
|
return err;
|
|
|
|
err = dquot_initialize(dir);
|
|
if (err)
|
|
return err;
|
|
|
|
inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
|
|
if (IS_ERR(inode))
|
|
return PTR_ERR(inode);
|
|
|
|
if (IS_ENCRYPTED(inode))
|
|
inode->i_op = &f2fs_encrypted_symlink_inode_operations;
|
|
else
|
|
inode->i_op = &f2fs_symlink_inode_operations;
|
|
inode_nohighmem(inode);
|
|
inode->i_mapping->a_ops = &f2fs_dblock_aops;
|
|
|
|
f2fs_lock_op(sbi);
|
|
err = f2fs_add_link(dentry, inode);
|
|
if (err)
|
|
goto out_f2fs_handle_failed_inode;
|
|
f2fs_unlock_op(sbi);
|
|
f2fs_alloc_nid_done(sbi, inode->i_ino);
|
|
|
|
err = fscrypt_encrypt_symlink(inode, symname, len, &disk_link);
|
|
if (err)
|
|
goto err_out;
|
|
|
|
err = page_symlink(inode, disk_link.name, disk_link.len);
|
|
|
|
err_out:
|
|
d_instantiate_new(dentry, inode);
|
|
|
|
/*
|
|
* Let's flush symlink data in order to avoid broken symlink as much as
|
|
* possible. Nevertheless, fsyncing is the best way, but there is no
|
|
* way to get a file descriptor in order to flush that.
|
|
*
|
|
* Note that, it needs to do dir->fsync to make this recoverable.
|
|
* If the symlink path is stored into inline_data, there is no
|
|
* performance regression.
|
|
*/
|
|
if (!err) {
|
|
filemap_write_and_wait_range(inode->i_mapping, 0,
|
|
disk_link.len - 1);
|
|
|
|
if (IS_DIRSYNC(dir))
|
|
f2fs_sync_fs(sbi->sb, 1);
|
|
} else {
|
|
f2fs_unlink(dir, dentry);
|
|
}
|
|
|
|
f2fs_balance_fs(sbi, true);
|
|
goto out_free_encrypted_link;
|
|
|
|
out_f2fs_handle_failed_inode:
|
|
f2fs_handle_failed_inode(inode);
|
|
out_free_encrypted_link:
|
|
if (disk_link.name != (unsigned char *)symname)
|
|
kfree(disk_link.name);
|
|
return err;
|
|
}
|
|
|
|
static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
|
|
struct dentry *dentry, umode_t mode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
struct inode *inode;
|
|
int err;
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
return -EIO;
|
|
|
|
err = dquot_initialize(dir);
|
|
if (err)
|
|
return err;
|
|
|
|
inode = f2fs_new_inode(dir, S_IFDIR | mode);
|
|
if (IS_ERR(inode))
|
|
return PTR_ERR(inode);
|
|
|
|
inode->i_op = &f2fs_dir_inode_operations;
|
|
inode->i_fop = &f2fs_dir_operations;
|
|
inode->i_mapping->a_ops = &f2fs_dblock_aops;
|
|
inode_nohighmem(inode);
|
|
|
|
set_inode_flag(inode, FI_INC_LINK);
|
|
f2fs_lock_op(sbi);
|
|
err = f2fs_add_link(dentry, inode);
|
|
if (err)
|
|
goto out_fail;
|
|
f2fs_unlock_op(sbi);
|
|
|
|
f2fs_alloc_nid_done(sbi, inode->i_ino);
|
|
|
|
d_instantiate_new(dentry, inode);
|
|
|
|
if (IS_DIRSYNC(dir))
|
|
f2fs_sync_fs(sbi->sb, 1);
|
|
|
|
f2fs_balance_fs(sbi, true);
|
|
return 0;
|
|
|
|
out_fail:
|
|
clear_inode_flag(inode, FI_INC_LINK);
|
|
f2fs_handle_failed_inode(inode);
|
|
return err;
|
|
}
|
|
|
|
static int f2fs_rmdir(struct inode *dir, struct dentry *dentry)
|
|
{
|
|
struct inode *inode = d_inode(dentry);
|
|
if (f2fs_empty_dir(inode))
|
|
return f2fs_unlink(dir, dentry);
|
|
return -ENOTEMPTY;
|
|
}
|
|
|
|
static int f2fs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
|
|
struct dentry *dentry, umode_t mode, dev_t rdev)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
struct inode *inode;
|
|
int err = 0;
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
return -EIO;
|
|
if (!f2fs_is_checkpoint_ready(sbi))
|
|
return -ENOSPC;
|
|
|
|
err = dquot_initialize(dir);
|
|
if (err)
|
|
return err;
|
|
|
|
inode = f2fs_new_inode(dir, mode);
|
|
if (IS_ERR(inode))
|
|
return PTR_ERR(inode);
|
|
|
|
init_special_inode(inode, inode->i_mode, rdev);
|
|
inode->i_op = &f2fs_special_inode_operations;
|
|
|
|
f2fs_lock_op(sbi);
|
|
err = f2fs_add_link(dentry, inode);
|
|
if (err)
|
|
goto out;
|
|
f2fs_unlock_op(sbi);
|
|
|
|
f2fs_alloc_nid_done(sbi, inode->i_ino);
|
|
|
|
d_instantiate_new(dentry, inode);
|
|
|
|
if (IS_DIRSYNC(dir))
|
|
f2fs_sync_fs(sbi->sb, 1);
|
|
|
|
f2fs_balance_fs(sbi, true);
|
|
return 0;
|
|
out:
|
|
f2fs_handle_failed_inode(inode);
|
|
return err;
|
|
}
|
|
|
|
static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
|
|
umode_t mode, struct inode **whiteout)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
struct inode *inode;
|
|
int err;
|
|
|
|
err = dquot_initialize(dir);
|
|
if (err)
|
|
return err;
|
|
|
|
inode = f2fs_new_inode(dir, mode);
|
|
if (IS_ERR(inode))
|
|
return PTR_ERR(inode);
|
|
|
|
if (whiteout) {
|
|
init_special_inode(inode, inode->i_mode, WHITEOUT_DEV);
|
|
inode->i_op = &f2fs_special_inode_operations;
|
|
} else {
|
|
inode->i_op = &f2fs_file_inode_operations;
|
|
inode->i_fop = &f2fs_file_operations;
|
|
inode->i_mapping->a_ops = &f2fs_dblock_aops;
|
|
}
|
|
|
|
f2fs_lock_op(sbi);
|
|
err = f2fs_acquire_orphan_inode(sbi);
|
|
if (err)
|
|
goto out;
|
|
|
|
err = f2fs_do_tmpfile(inode, dir);
|
|
if (err)
|
|
goto release_out;
|
|
|
|
/*
|
|
* add this non-linked tmpfile to orphan list, in this way we could
|
|
* remove all unused data of tmpfile after abnormal power-off.
|
|
*/
|
|
f2fs_add_orphan_inode(inode);
|
|
f2fs_alloc_nid_done(sbi, inode->i_ino);
|
|
|
|
if (whiteout) {
|
|
f2fs_i_links_write(inode, false);
|
|
|
|
spin_lock(&inode->i_lock);
|
|
inode->i_state |= I_LINKABLE;
|
|
spin_unlock(&inode->i_lock);
|
|
|
|
*whiteout = inode;
|
|
} else {
|
|
d_tmpfile(dentry, inode);
|
|
}
|
|
/* link_count was changed by d_tmpfile as well. */
|
|
f2fs_unlock_op(sbi);
|
|
unlock_new_inode(inode);
|
|
|
|
f2fs_balance_fs(sbi, true);
|
|
return 0;
|
|
|
|
release_out:
|
|
f2fs_release_orphan_inode(sbi);
|
|
out:
|
|
f2fs_handle_failed_inode(inode);
|
|
return err;
|
|
}
|
|
|
|
static int f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
|
|
struct dentry *dentry, umode_t mode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
return -EIO;
|
|
if (!f2fs_is_checkpoint_ready(sbi))
|
|
return -ENOSPC;
|
|
|
|
return __f2fs_tmpfile(dir, dentry, mode, NULL);
|
|
}
|
|
|
|
static int f2fs_create_whiteout(struct inode *dir, struct inode **whiteout)
|
|
{
|
|
if (unlikely(f2fs_cp_error(F2FS_I_SB(dir))))
|
|
return -EIO;
|
|
|
|
return __f2fs_tmpfile(dir, NULL, S_IFCHR | WHITEOUT_MODE, whiteout);
|
|
}
|
|
|
|
static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
|
|
struct inode *new_dir, struct dentry *new_dentry,
|
|
unsigned int flags)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir);
|
|
struct inode *old_inode = d_inode(old_dentry);
|
|
struct inode *new_inode = d_inode(new_dentry);
|
|
struct inode *whiteout = NULL;
|
|
struct page *old_dir_page = NULL;
|
|
struct page *old_page, *new_page = NULL;
|
|
struct f2fs_dir_entry *old_dir_entry = NULL;
|
|
struct f2fs_dir_entry *old_entry;
|
|
struct f2fs_dir_entry *new_entry;
|
|
int err;
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
return -EIO;
|
|
if (!f2fs_is_checkpoint_ready(sbi))
|
|
return -ENOSPC;
|
|
|
|
if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
|
|
(!projid_eq(F2FS_I(new_dir)->i_projid,
|
|
F2FS_I(old_dentry->d_inode)->i_projid)))
|
|
return -EXDEV;
|
|
|
|
/*
|
|
* If new_inode is null, the below renaming flow will
|
|
* add a link in old_dir which can conver inline_dir.
|
|
* After then, if we failed to get the entry due to other
|
|
* reasons like ENOMEM, we had to remove the new entry.
|
|
* Instead of adding such the error handling routine, let's
|
|
* simply convert first here.
|
|
*/
|
|
if (old_dir == new_dir && !new_inode) {
|
|
err = f2fs_try_convert_inline_dir(old_dir, new_dentry);
|
|
if (err)
|
|
return err;
|
|
}
|
|
|
|
if (flags & RENAME_WHITEOUT) {
|
|
err = f2fs_create_whiteout(old_dir, &whiteout);
|
|
if (err)
|
|
return err;
|
|
}
|
|
|
|
err = dquot_initialize(old_dir);
|
|
if (err)
|
|
goto out;
|
|
|
|
err = dquot_initialize(new_dir);
|
|
if (err)
|
|
goto out;
|
|
|
|
if (new_inode) {
|
|
err = dquot_initialize(new_inode);
|
|
if (err)
|
|
goto out;
|
|
}
|
|
|
|
err = -ENOENT;
|
|
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
|
|
if (!old_entry) {
|
|
if (IS_ERR(old_page))
|
|
err = PTR_ERR(old_page);
|
|
goto out;
|
|
}
|
|
|
|
if (S_ISDIR(old_inode->i_mode)) {
|
|
old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page);
|
|
if (!old_dir_entry) {
|
|
if (IS_ERR(old_dir_page))
|
|
err = PTR_ERR(old_dir_page);
|
|
goto out_old;
|
|
}
|
|
}
|
|
|
|
if (new_inode) {
|
|
|
|
err = -ENOTEMPTY;
|
|
if (old_dir_entry && !f2fs_empty_dir(new_inode))
|
|
goto out_dir;
|
|
|
|
err = -ENOENT;
|
|
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
|
|
&new_page);
|
|
if (!new_entry) {
|
|
if (IS_ERR(new_page))
|
|
err = PTR_ERR(new_page);
|
|
goto out_dir;
|
|
}
|
|
|
|
f2fs_balance_fs(sbi, true);
|
|
|
|
f2fs_lock_op(sbi);
|
|
|
|
err = f2fs_acquire_orphan_inode(sbi);
|
|
if (err)
|
|
goto put_out_dir;
|
|
|
|
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
|
|
new_page = NULL;
|
|
|
|
new_inode->i_ctime = current_time(new_inode);
|
|
down_write(&F2FS_I(new_inode)->i_sem);
|
|
if (old_dir_entry)
|
|
f2fs_i_links_write(new_inode, false);
|
|
f2fs_i_links_write(new_inode, false);
|
|
up_write(&F2FS_I(new_inode)->i_sem);
|
|
|
|
if (!new_inode->i_nlink)
|
|
f2fs_add_orphan_inode(new_inode);
|
|
else
|
|
f2fs_release_orphan_inode(sbi);
|
|
} else {
|
|
f2fs_balance_fs(sbi, true);
|
|
|
|
f2fs_lock_op(sbi);
|
|
|
|
err = f2fs_add_link(new_dentry, old_inode);
|
|
if (err) {
|
|
f2fs_unlock_op(sbi);
|
|
goto out_dir;
|
|
}
|
|
|
|
if (old_dir_entry)
|
|
f2fs_i_links_write(new_dir, true);
|
|
}
|
|
|
|
down_write(&F2FS_I(old_inode)->i_sem);
|
|
if (!old_dir_entry || whiteout)
|
|
file_lost_pino(old_inode);
|
|
else
|
|
/* adjust dir's i_pino to pass fsck check */
|
|
f2fs_i_pino_write(old_inode, new_dir->i_ino);
|
|
up_write(&F2FS_I(old_inode)->i_sem);
|
|
|
|
old_inode->i_ctime = current_time(old_inode);
|
|
f2fs_mark_inode_dirty_sync(old_inode, false);
|
|
|
|
f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
|
|
old_page = NULL;
|
|
|
|
if (whiteout) {
|
|
set_inode_flag(whiteout, FI_INC_LINK);
|
|
err = f2fs_add_link(old_dentry, whiteout);
|
|
if (err)
|
|
goto put_out_dir;
|
|
|
|
spin_lock(&whiteout->i_lock);
|
|
whiteout->i_state &= ~I_LINKABLE;
|
|
spin_unlock(&whiteout->i_lock);
|
|
|
|
iput(whiteout);
|
|
}
|
|
|
|
if (old_dir_entry) {
|
|
if (old_dir != new_dir && !whiteout)
|
|
f2fs_set_link(old_inode, old_dir_entry,
|
|
old_dir_page, new_dir);
|
|
else
|
|
f2fs_put_page(old_dir_page, 0);
|
|
f2fs_i_links_write(old_dir, false);
|
|
}
|
|
if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) {
|
|
f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
|
|
if (S_ISDIR(old_inode->i_mode))
|
|
f2fs_add_ino_entry(sbi, old_inode->i_ino,
|
|
TRANS_DIR_INO);
|
|
}
|
|
|
|
f2fs_unlock_op(sbi);
|
|
|
|
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
|
|
f2fs_sync_fs(sbi->sb, 1);
|
|
|
|
f2fs_update_time(sbi, REQ_TIME);
|
|
return 0;
|
|
|
|
put_out_dir:
|
|
f2fs_unlock_op(sbi);
|
|
f2fs_put_page(new_page, 0);
|
|
out_dir:
|
|
if (old_dir_entry)
|
|
f2fs_put_page(old_dir_page, 0);
|
|
out_old:
|
|
f2fs_put_page(old_page, 0);
|
|
out:
|
|
if (whiteout)
|
|
iput(whiteout);
|
|
return err;
|
|
}
|
|
|
|
static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
|
|
struct inode *new_dir, struct dentry *new_dentry)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir);
|
|
struct inode *old_inode = d_inode(old_dentry);
|
|
struct inode *new_inode = d_inode(new_dentry);
|
|
struct page *old_dir_page, *new_dir_page;
|
|
struct page *old_page, *new_page;
|
|
struct f2fs_dir_entry *old_dir_entry = NULL, *new_dir_entry = NULL;
|
|
struct f2fs_dir_entry *old_entry, *new_entry;
|
|
int old_nlink = 0, new_nlink = 0;
|
|
int err;
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
return -EIO;
|
|
if (!f2fs_is_checkpoint_ready(sbi))
|
|
return -ENOSPC;
|
|
|
|
if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
|
|
!projid_eq(F2FS_I(new_dir)->i_projid,
|
|
F2FS_I(old_dentry->d_inode)->i_projid)) ||
|
|
(is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
|
|
!projid_eq(F2FS_I(old_dir)->i_projid,
|
|
F2FS_I(new_dentry->d_inode)->i_projid)))
|
|
return -EXDEV;
|
|
|
|
err = dquot_initialize(old_dir);
|
|
if (err)
|
|
goto out;
|
|
|
|
err = dquot_initialize(new_dir);
|
|
if (err)
|
|
goto out;
|
|
|
|
err = -ENOENT;
|
|
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
|
|
if (!old_entry) {
|
|
if (IS_ERR(old_page))
|
|
err = PTR_ERR(old_page);
|
|
goto out;
|
|
}
|
|
|
|
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page);
|
|
if (!new_entry) {
|
|
if (IS_ERR(new_page))
|
|
err = PTR_ERR(new_page);
|
|
goto out_old;
|
|
}
|
|
|
|
/* prepare for updating ".." directory entry info later */
|
|
if (old_dir != new_dir) {
|
|
if (S_ISDIR(old_inode->i_mode)) {
|
|
old_dir_entry = f2fs_parent_dir(old_inode,
|
|
&old_dir_page);
|
|
if (!old_dir_entry) {
|
|
if (IS_ERR(old_dir_page))
|
|
err = PTR_ERR(old_dir_page);
|
|
goto out_new;
|
|
}
|
|
}
|
|
|
|
if (S_ISDIR(new_inode->i_mode)) {
|
|
new_dir_entry = f2fs_parent_dir(new_inode,
|
|
&new_dir_page);
|
|
if (!new_dir_entry) {
|
|
if (IS_ERR(new_dir_page))
|
|
err = PTR_ERR(new_dir_page);
|
|
goto out_old_dir;
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* If cross rename between file and directory those are not
|
|
* in the same directory, we will inc nlink of file's parent
|
|
* later, so we should check upper boundary of its nlink.
|
|
*/
|
|
if ((!old_dir_entry || !new_dir_entry) &&
|
|
old_dir_entry != new_dir_entry) {
|
|
old_nlink = old_dir_entry ? -1 : 1;
|
|
new_nlink = -old_nlink;
|
|
err = -EMLINK;
|
|
if ((old_nlink > 0 && old_dir->i_nlink >= F2FS_LINK_MAX) ||
|
|
(new_nlink > 0 && new_dir->i_nlink >= F2FS_LINK_MAX))
|
|
goto out_new_dir;
|
|
}
|
|
|
|
f2fs_balance_fs(sbi, true);
|
|
|
|
f2fs_lock_op(sbi);
|
|
|
|
/* update ".." directory entry info of old dentry */
|
|
if (old_dir_entry)
|
|
f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir);
|
|
|
|
/* update ".." directory entry info of new dentry */
|
|
if (new_dir_entry)
|
|
f2fs_set_link(new_inode, new_dir_entry, new_dir_page, old_dir);
|
|
|
|
/* update directory entry info of old dir inode */
|
|
f2fs_set_link(old_dir, old_entry, old_page, new_inode);
|
|
|
|
down_write(&F2FS_I(old_inode)->i_sem);
|
|
if (!old_dir_entry)
|
|
file_lost_pino(old_inode);
|
|
else
|
|
/* adjust dir's i_pino to pass fsck check */
|
|
f2fs_i_pino_write(old_inode, new_dir->i_ino);
|
|
up_write(&F2FS_I(old_inode)->i_sem);
|
|
|
|
old_dir->i_ctime = current_time(old_dir);
|
|
if (old_nlink) {
|
|
down_write(&F2FS_I(old_dir)->i_sem);
|
|
f2fs_i_links_write(old_dir, old_nlink > 0);
|
|
up_write(&F2FS_I(old_dir)->i_sem);
|
|
}
|
|
f2fs_mark_inode_dirty_sync(old_dir, false);
|
|
|
|
/* update directory entry info of new dir inode */
|
|
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
|
|
|
|
down_write(&F2FS_I(new_inode)->i_sem);
|
|
if (!new_dir_entry)
|
|
file_lost_pino(new_inode);
|
|
else
|
|
/* adjust dir's i_pino to pass fsck check */
|
|
f2fs_i_pino_write(new_inode, old_dir->i_ino);
|
|
up_write(&F2FS_I(new_inode)->i_sem);
|
|
|
|
new_dir->i_ctime = current_time(new_dir);
|
|
if (new_nlink) {
|
|
down_write(&F2FS_I(new_dir)->i_sem);
|
|
f2fs_i_links_write(new_dir, new_nlink > 0);
|
|
up_write(&F2FS_I(new_dir)->i_sem);
|
|
}
|
|
f2fs_mark_inode_dirty_sync(new_dir, false);
|
|
|
|
if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) {
|
|
f2fs_add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO);
|
|
f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
|
|
}
|
|
|
|
f2fs_unlock_op(sbi);
|
|
|
|
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
|
|
f2fs_sync_fs(sbi->sb, 1);
|
|
|
|
f2fs_update_time(sbi, REQ_TIME);
|
|
return 0;
|
|
out_new_dir:
|
|
if (new_dir_entry) {
|
|
f2fs_put_page(new_dir_page, 0);
|
|
}
|
|
out_old_dir:
|
|
if (old_dir_entry) {
|
|
f2fs_put_page(old_dir_page, 0);
|
|
}
|
|
out_new:
|
|
f2fs_put_page(new_page, 0);
|
|
out_old:
|
|
f2fs_put_page(old_page, 0);
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
static int f2fs_rename2(struct user_namespace *mnt_userns,
|
|
struct inode *old_dir, struct dentry *old_dentry,
|
|
struct inode *new_dir, struct dentry *new_dentry,
|
|
unsigned int flags)
|
|
{
|
|
int err;
|
|
|
|
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
|
|
return -EINVAL;
|
|
|
|
err = fscrypt_prepare_rename(old_dir, old_dentry, new_dir, new_dentry,
|
|
flags);
|
|
if (err)
|
|
return err;
|
|
|
|
if (flags & RENAME_EXCHANGE) {
|
|
return f2fs_cross_rename(old_dir, old_dentry,
|
|
new_dir, new_dentry);
|
|
}
|
|
/*
|
|
* VFS has already handled the new dentry existence case,
|
|
* here, we just deal with "RENAME_NOREPLACE" as regular rename.
|
|
*/
|
|
return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
|
|
}
|
|
|
|
static const char *f2fs_encrypted_get_link(struct dentry *dentry,
|
|
struct inode *inode,
|
|
struct delayed_call *done)
|
|
{
|
|
struct page *page;
|
|
const char *target;
|
|
|
|
if (!dentry)
|
|
return ERR_PTR(-ECHILD);
|
|
|
|
page = read_mapping_page(inode->i_mapping, 0, NULL);
|
|
if (IS_ERR(page))
|
|
return ERR_CAST(page);
|
|
|
|
target = fscrypt_get_symlink(inode, page_address(page),
|
|
inode->i_sb->s_blocksize, done);
|
|
put_page(page);
|
|
return target;
|
|
}
|
|
|
|
const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
|
|
.get_link = f2fs_encrypted_get_link,
|
|
.getattr = f2fs_getattr,
|
|
.setattr = f2fs_setattr,
|
|
.listxattr = f2fs_listxattr,
|
|
};
|
|
|
|
const struct inode_operations f2fs_dir_inode_operations = {
|
|
.create = f2fs_create,
|
|
.lookup = f2fs_lookup,
|
|
.link = f2fs_link,
|
|
.unlink = f2fs_unlink,
|
|
.symlink = f2fs_symlink,
|
|
.mkdir = f2fs_mkdir,
|
|
.rmdir = f2fs_rmdir,
|
|
.mknod = f2fs_mknod,
|
|
.rename = f2fs_rename2,
|
|
.tmpfile = f2fs_tmpfile,
|
|
.getattr = f2fs_getattr,
|
|
.setattr = f2fs_setattr,
|
|
.get_acl = f2fs_get_acl,
|
|
.set_acl = f2fs_set_acl,
|
|
.listxattr = f2fs_listxattr,
|
|
.fiemap = f2fs_fiemap,
|
|
};
|
|
|
|
const struct inode_operations f2fs_symlink_inode_operations = {
|
|
.get_link = f2fs_get_link,
|
|
.getattr = f2fs_getattr,
|
|
.setattr = f2fs_setattr,
|
|
.listxattr = f2fs_listxattr,
|
|
};
|
|
|
|
const struct inode_operations f2fs_special_inode_operations = {
|
|
.getattr = f2fs_getattr,
|
|
.setattr = f2fs_setattr,
|
|
.get_acl = f2fs_get_acl,
|
|
.set_acl = f2fs_set_acl,
|
|
.listxattr = f2fs_listxattr,
|
|
};
|