mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 17:30:02 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCY+5NlQAKCRCRxhvAZXjc
orOaAP9i2h3OJy95nO2Fpde0Bt2UT+oulKCCcGlvXJ8/+TQpyQD/ZQq47gFQ0EAz
Br5NxeyGeecAb0lHpFz+CpLGsxMrMwQ=
=+BG5
-----END PGP SIGNATURE-----
Merge tag 'fs.idmapped.v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping
Pull vfs idmapping updates from Christian Brauner:
- Last cycle we introduced the dedicated struct mnt_idmap type for
mount idmapping and the required infrastucture in 256c8aed2b
("fs:
introduce dedicated idmap type for mounts"). As promised in last
cycle's pull request message this converts everything to rely on
struct mnt_idmap.
Currently we still pass around the plain namespace that was attached
to a mount. This is in general pretty convenient but it makes it easy
to conflate namespaces that are relevant on the filesystem with
namespaces that are relevant on the mount level. Especially for
non-vfs developers without detailed knowledge in this area this was a
potential source for bugs.
This finishes the conversion. Instead of passing the plain namespace
around this updates all places that currently take a pointer to a
mnt_userns with a pointer to struct mnt_idmap.
Now that the conversion is done all helpers down to the really
low-level helpers only accept a struct mnt_idmap argument instead of
two namespace arguments.
Conflating mount and other idmappings will now cause the compiler to
complain loudly thus eliminating the possibility of any bugs. This
makes it impossible for filesystem developers to mix up mount and
filesystem idmappings as they are two distinct types and require
distinct helpers that cannot be used interchangeably.
Everything associated with struct mnt_idmap is moved into a single
separate file. With that change no code can poke around in struct
mnt_idmap. It can only be interacted with through dedicated helpers.
That means all filesystems are and all of the vfs is completely
oblivious to the actual implementation of idmappings.
We are now also able to extend struct mnt_idmap as we see fit. For
example, we can decouple it completely from namespaces for users that
don't require or don't want to use them at all. We can also extend
the concept of idmappings so we can cover filesystem specific
requirements.
In combination with the vfs{g,u}id_t work we finished in v6.2 this
makes this feature substantially more robust and thus difficult to
implement wrong by a given filesystem and also protects the vfs.
- Enable idmapped mounts for tmpfs and fulfill a longstanding request.
A long-standing request from users had been to make it possible to
create idmapped mounts for tmpfs. For example, to share the host's
tmpfs mount between multiple sandboxes. This is a prerequisite for
some advanced Kubernetes cases. Systemd also has a range of use-cases
to increase service isolation. And there are more users of this.
However, with all of the other work going on this was way down on the
priority list but luckily someone other than ourselves picked this
up.
As usual the patch is tiny as all the infrastructure work had been
done multiple kernel releases ago. In addition to all the tests that
we already have I requested that Rodrigo add a dedicated tmpfs
testsuite for idmapped mounts to xfstests. It is to be included into
xfstests during the v6.3 development cycle. This should add a slew of
additional tests.
* tag 'fs.idmapped.v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping: (26 commits)
shmem: support idmapped mounts for tmpfs
fs: move mnt_idmap
fs: port vfs{g,u}id helpers to mnt_idmap
fs: port fs{g,u}id helpers to mnt_idmap
fs: port i_{g,u}id_into_vfs{g,u}id() to mnt_idmap
fs: port i_{g,u}id_{needs_}update() to mnt_idmap
quota: port to mnt_idmap
fs: port privilege checking helpers to mnt_idmap
fs: port inode_owner_or_capable() to mnt_idmap
fs: port inode_init_owner() to mnt_idmap
fs: port acl to mnt_idmap
fs: port xattr to mnt_idmap
fs: port ->permission() to pass mnt_idmap
fs: port ->fileattr_set() to pass mnt_idmap
fs: port ->set_acl() to pass mnt_idmap
fs: port ->get_acl() to pass mnt_idmap
fs: port ->tmpfile() to pass mnt_idmap
fs: port ->rename() to pass mnt_idmap
fs: port ->mknod() to pass mnt_idmap
fs: port ->mkdir() to pass mnt_idmap
...
843 lines
23 KiB
C
843 lines
23 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* linux/fs/stat.c
|
|
*
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
*/
|
|
|
|
#include <linux/blkdev.h>
|
|
#include <linux/export.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/file.h>
|
|
#include <linux/highuid.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/namei.h>
|
|
#include <linux/security.h>
|
|
#include <linux/cred.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/compat.h>
|
|
#include <linux/iversion.h>
|
|
|
|
#include <linux/uaccess.h>
|
|
#include <asm/unistd.h>
|
|
|
|
#include "internal.h"
|
|
#include "mount.h"
|
|
|
|
/**
|
|
* generic_fillattr - Fill in the basic attributes from the inode struct
|
|
* @idmap: idmap of the mount the inode was found from
|
|
* @inode: Inode to use as the source
|
|
* @stat: Where to fill in the attributes
|
|
*
|
|
* Fill in the basic attributes in the kstat structure from data that's to be
|
|
* found on the VFS inode structure. This is the default if no getattr inode
|
|
* operation is supplied.
|
|
*
|
|
* If the inode has been found through an idmapped mount the idmap of
|
|
* the vfsmount must be passed through @idmap. This function will then
|
|
* take care to map the inode according to @idmap before filling in the
|
|
* uid and gid filds. On non-idmapped mounts or if permission checking is to be
|
|
* performed on the raw inode simply passs @nop_mnt_idmap.
|
|
*/
|
|
void generic_fillattr(struct mnt_idmap *idmap, struct inode *inode,
|
|
struct kstat *stat)
|
|
{
|
|
vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode);
|
|
vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode);
|
|
|
|
stat->dev = inode->i_sb->s_dev;
|
|
stat->ino = inode->i_ino;
|
|
stat->mode = inode->i_mode;
|
|
stat->nlink = inode->i_nlink;
|
|
stat->uid = vfsuid_into_kuid(vfsuid);
|
|
stat->gid = vfsgid_into_kgid(vfsgid);
|
|
stat->rdev = inode->i_rdev;
|
|
stat->size = i_size_read(inode);
|
|
stat->atime = inode->i_atime;
|
|
stat->mtime = inode->i_mtime;
|
|
stat->ctime = inode->i_ctime;
|
|
stat->blksize = i_blocksize(inode);
|
|
stat->blocks = inode->i_blocks;
|
|
}
|
|
EXPORT_SYMBOL(generic_fillattr);
|
|
|
|
/**
|
|
* generic_fill_statx_attr - Fill in the statx attributes from the inode flags
|
|
* @inode: Inode to use as the source
|
|
* @stat: Where to fill in the attribute flags
|
|
*
|
|
* Fill in the STATX_ATTR_* flags in the kstat structure for properties of the
|
|
* inode that are published on i_flags and enforced by the VFS.
|
|
*/
|
|
void generic_fill_statx_attr(struct inode *inode, struct kstat *stat)
|
|
{
|
|
if (inode->i_flags & S_IMMUTABLE)
|
|
stat->attributes |= STATX_ATTR_IMMUTABLE;
|
|
if (inode->i_flags & S_APPEND)
|
|
stat->attributes |= STATX_ATTR_APPEND;
|
|
stat->attributes_mask |= KSTAT_ATTR_VFS_FLAGS;
|
|
}
|
|
EXPORT_SYMBOL(generic_fill_statx_attr);
|
|
|
|
/**
|
|
* vfs_getattr_nosec - getattr without security checks
|
|
* @path: file to get attributes from
|
|
* @stat: structure to return attributes in
|
|
* @request_mask: STATX_xxx flags indicating what the caller wants
|
|
* @query_flags: Query mode (AT_STATX_SYNC_TYPE)
|
|
*
|
|
* Get attributes without calling security_inode_getattr.
|
|
*
|
|
* Currently the only caller other than vfs_getattr is internal to the
|
|
* filehandle lookup code, which uses only the inode number and returns no
|
|
* attributes to any user. Any other code probably wants vfs_getattr.
|
|
*/
|
|
int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
|
|
u32 request_mask, unsigned int query_flags)
|
|
{
|
|
struct mnt_idmap *idmap;
|
|
struct inode *inode = d_backing_inode(path->dentry);
|
|
|
|
memset(stat, 0, sizeof(*stat));
|
|
stat->result_mask |= STATX_BASIC_STATS;
|
|
query_flags &= AT_STATX_SYNC_TYPE;
|
|
|
|
/* allow the fs to override these if it really wants to */
|
|
/* SB_NOATIME means filesystem supplies dummy atime value */
|
|
if (inode->i_sb->s_flags & SB_NOATIME)
|
|
stat->result_mask &= ~STATX_ATIME;
|
|
|
|
/*
|
|
* Note: If you add another clause to set an attribute flag, please
|
|
* update attributes_mask below.
|
|
*/
|
|
if (IS_AUTOMOUNT(inode))
|
|
stat->attributes |= STATX_ATTR_AUTOMOUNT;
|
|
|
|
if (IS_DAX(inode))
|
|
stat->attributes |= STATX_ATTR_DAX;
|
|
|
|
stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT |
|
|
STATX_ATTR_DAX);
|
|
|
|
if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) {
|
|
stat->result_mask |= STATX_CHANGE_COOKIE;
|
|
stat->change_cookie = inode_query_iversion(inode);
|
|
}
|
|
|
|
idmap = mnt_idmap(path->mnt);
|
|
if (inode->i_op->getattr)
|
|
return inode->i_op->getattr(idmap, path, stat,
|
|
request_mask, query_flags);
|
|
|
|
generic_fillattr(idmap, inode, stat);
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(vfs_getattr_nosec);
|
|
|
|
/*
|
|
* vfs_getattr - Get the enhanced basic attributes of a file
|
|
* @path: The file of interest
|
|
* @stat: Where to return the statistics
|
|
* @request_mask: STATX_xxx flags indicating what the caller wants
|
|
* @query_flags: Query mode (AT_STATX_SYNC_TYPE)
|
|
*
|
|
* Ask the filesystem for a file's attributes. The caller must indicate in
|
|
* request_mask and query_flags to indicate what they want.
|
|
*
|
|
* If the file is remote, the filesystem can be forced to update the attributes
|
|
* from the backing store by passing AT_STATX_FORCE_SYNC in query_flags or can
|
|
* suppress the update by passing AT_STATX_DONT_SYNC.
|
|
*
|
|
* Bits must have been set in request_mask to indicate which attributes the
|
|
* caller wants retrieving. Any such attribute not requested may be returned
|
|
* anyway, but the value may be approximate, and, if remote, may not have been
|
|
* synchronised with the server.
|
|
*
|
|
* 0 will be returned on success, and a -ve error code if unsuccessful.
|
|
*/
|
|
int vfs_getattr(const struct path *path, struct kstat *stat,
|
|
u32 request_mask, unsigned int query_flags)
|
|
{
|
|
int retval;
|
|
|
|
retval = security_inode_getattr(path);
|
|
if (retval)
|
|
return retval;
|
|
return vfs_getattr_nosec(path, stat, request_mask, query_flags);
|
|
}
|
|
EXPORT_SYMBOL(vfs_getattr);
|
|
|
|
/**
|
|
* vfs_fstat - Get the basic attributes by file descriptor
|
|
* @fd: The file descriptor referring to the file of interest
|
|
* @stat: The result structure to fill in.
|
|
*
|
|
* This function is a wrapper around vfs_getattr(). The main difference is
|
|
* that it uses a file descriptor to determine the file location.
|
|
*
|
|
* 0 will be returned on success, and a -ve error code if unsuccessful.
|
|
*/
|
|
int vfs_fstat(int fd, struct kstat *stat)
|
|
{
|
|
struct fd f;
|
|
int error;
|
|
|
|
f = fdget_raw(fd);
|
|
if (!f.file)
|
|
return -EBADF;
|
|
error = vfs_getattr(&f.file->f_path, stat, STATX_BASIC_STATS, 0);
|
|
fdput(f);
|
|
return error;
|
|
}
|
|
|
|
int getname_statx_lookup_flags(int flags)
|
|
{
|
|
int lookup_flags = 0;
|
|
|
|
if (!(flags & AT_SYMLINK_NOFOLLOW))
|
|
lookup_flags |= LOOKUP_FOLLOW;
|
|
if (!(flags & AT_NO_AUTOMOUNT))
|
|
lookup_flags |= LOOKUP_AUTOMOUNT;
|
|
if (flags & AT_EMPTY_PATH)
|
|
lookup_flags |= LOOKUP_EMPTY;
|
|
|
|
return lookup_flags;
|
|
}
|
|
|
|
/**
|
|
* vfs_statx - Get basic and extra attributes by filename
|
|
* @dfd: A file descriptor representing the base dir for a relative filename
|
|
* @filename: The name of the file of interest
|
|
* @flags: Flags to control the query
|
|
* @stat: The result structure to fill in.
|
|
* @request_mask: STATX_xxx flags indicating what the caller wants
|
|
*
|
|
* This function is a wrapper around vfs_getattr(). The main difference is
|
|
* that it uses a filename and base directory to determine the file location.
|
|
* Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink
|
|
* at the given name from being referenced.
|
|
*
|
|
* 0 will be returned on success, and a -ve error code if unsuccessful.
|
|
*/
|
|
static int vfs_statx(int dfd, struct filename *filename, int flags,
|
|
struct kstat *stat, u32 request_mask)
|
|
{
|
|
struct path path;
|
|
unsigned int lookup_flags = getname_statx_lookup_flags(flags);
|
|
int error;
|
|
|
|
if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH |
|
|
AT_STATX_SYNC_TYPE))
|
|
return -EINVAL;
|
|
|
|
retry:
|
|
error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
|
|
if (error)
|
|
goto out;
|
|
|
|
error = vfs_getattr(&path, stat, request_mask, flags);
|
|
|
|
stat->mnt_id = real_mount(path.mnt)->mnt_id;
|
|
stat->result_mask |= STATX_MNT_ID;
|
|
|
|
if (path.mnt->mnt_root == path.dentry)
|
|
stat->attributes |= STATX_ATTR_MOUNT_ROOT;
|
|
stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;
|
|
|
|
/* Handle STATX_DIOALIGN for block devices. */
|
|
if (request_mask & STATX_DIOALIGN) {
|
|
struct inode *inode = d_backing_inode(path.dentry);
|
|
|
|
if (S_ISBLK(inode->i_mode))
|
|
bdev_statx_dioalign(inode, stat);
|
|
}
|
|
|
|
path_put(&path);
|
|
if (retry_estale(error, lookup_flags)) {
|
|
lookup_flags |= LOOKUP_REVAL;
|
|
goto retry;
|
|
}
|
|
out:
|
|
return error;
|
|
}
|
|
|
|
int vfs_fstatat(int dfd, const char __user *filename,
|
|
struct kstat *stat, int flags)
|
|
{
|
|
int ret;
|
|
int statx_flags = flags | AT_NO_AUTOMOUNT;
|
|
struct filename *name;
|
|
|
|
name = getname_flags(filename, getname_statx_lookup_flags(statx_flags), NULL);
|
|
ret = vfs_statx(dfd, name, statx_flags, stat, STATX_BASIC_STATS);
|
|
putname(name);
|
|
|
|
return ret;
|
|
}
|
|
|
|
#ifdef __ARCH_WANT_OLD_STAT
|
|
|
|
/*
|
|
* For backward compatibility? Maybe this should be moved
|
|
* into arch/i386 instead?
|
|
*/
|
|
static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * statbuf)
|
|
{
|
|
static int warncount = 5;
|
|
struct __old_kernel_stat tmp;
|
|
|
|
if (warncount > 0) {
|
|
warncount--;
|
|
printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n",
|
|
current->comm);
|
|
} else if (warncount < 0) {
|
|
/* it's laughable, but... */
|
|
warncount = 0;
|
|
}
|
|
|
|
memset(&tmp, 0, sizeof(struct __old_kernel_stat));
|
|
tmp.st_dev = old_encode_dev(stat->dev);
|
|
tmp.st_ino = stat->ino;
|
|
if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
|
|
return -EOVERFLOW;
|
|
tmp.st_mode = stat->mode;
|
|
tmp.st_nlink = stat->nlink;
|
|
if (tmp.st_nlink != stat->nlink)
|
|
return -EOVERFLOW;
|
|
SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
|
|
SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
|
|
tmp.st_rdev = old_encode_dev(stat->rdev);
|
|
#if BITS_PER_LONG == 32
|
|
if (stat->size > MAX_NON_LFS)
|
|
return -EOVERFLOW;
|
|
#endif
|
|
tmp.st_size = stat->size;
|
|
tmp.st_atime = stat->atime.tv_sec;
|
|
tmp.st_mtime = stat->mtime.tv_sec;
|
|
tmp.st_ctime = stat->ctime.tv_sec;
|
|
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
|
|
}
|
|
|
|
SYSCALL_DEFINE2(stat, const char __user *, filename,
|
|
struct __old_kernel_stat __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error;
|
|
|
|
error = vfs_stat(filename, &stat);
|
|
if (error)
|
|
return error;
|
|
|
|
return cp_old_stat(&stat, statbuf);
|
|
}
|
|
|
|
SYSCALL_DEFINE2(lstat, const char __user *, filename,
|
|
struct __old_kernel_stat __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error;
|
|
|
|
error = vfs_lstat(filename, &stat);
|
|
if (error)
|
|
return error;
|
|
|
|
return cp_old_stat(&stat, statbuf);
|
|
}
|
|
|
|
SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error = vfs_fstat(fd, &stat);
|
|
|
|
if (!error)
|
|
error = cp_old_stat(&stat, statbuf);
|
|
|
|
return error;
|
|
}
|
|
|
|
#endif /* __ARCH_WANT_OLD_STAT */
|
|
|
|
#ifdef __ARCH_WANT_NEW_STAT
|
|
|
|
#if BITS_PER_LONG == 32
|
|
# define choose_32_64(a,b) a
|
|
#else
|
|
# define choose_32_64(a,b) b
|
|
#endif
|
|
|
|
#ifndef INIT_STRUCT_STAT_PADDING
|
|
# define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st))
|
|
#endif
|
|
|
|
static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
|
|
{
|
|
struct stat tmp;
|
|
|
|
if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev))
|
|
return -EOVERFLOW;
|
|
if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev))
|
|
return -EOVERFLOW;
|
|
#if BITS_PER_LONG == 32
|
|
if (stat->size > MAX_NON_LFS)
|
|
return -EOVERFLOW;
|
|
#endif
|
|
|
|
INIT_STRUCT_STAT_PADDING(tmp);
|
|
tmp.st_dev = new_encode_dev(stat->dev);
|
|
tmp.st_ino = stat->ino;
|
|
if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
|
|
return -EOVERFLOW;
|
|
tmp.st_mode = stat->mode;
|
|
tmp.st_nlink = stat->nlink;
|
|
if (tmp.st_nlink != stat->nlink)
|
|
return -EOVERFLOW;
|
|
SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
|
|
SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
|
|
tmp.st_rdev = new_encode_dev(stat->rdev);
|
|
tmp.st_size = stat->size;
|
|
tmp.st_atime = stat->atime.tv_sec;
|
|
tmp.st_mtime = stat->mtime.tv_sec;
|
|
tmp.st_ctime = stat->ctime.tv_sec;
|
|
#ifdef STAT_HAVE_NSEC
|
|
tmp.st_atime_nsec = stat->atime.tv_nsec;
|
|
tmp.st_mtime_nsec = stat->mtime.tv_nsec;
|
|
tmp.st_ctime_nsec = stat->ctime.tv_nsec;
|
|
#endif
|
|
tmp.st_blocks = stat->blocks;
|
|
tmp.st_blksize = stat->blksize;
|
|
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
|
|
}
|
|
|
|
SYSCALL_DEFINE2(newstat, const char __user *, filename,
|
|
struct stat __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error = vfs_stat(filename, &stat);
|
|
|
|
if (error)
|
|
return error;
|
|
return cp_new_stat(&stat, statbuf);
|
|
}
|
|
|
|
SYSCALL_DEFINE2(newlstat, const char __user *, filename,
|
|
struct stat __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error;
|
|
|
|
error = vfs_lstat(filename, &stat);
|
|
if (error)
|
|
return error;
|
|
|
|
return cp_new_stat(&stat, statbuf);
|
|
}
|
|
|
|
#if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT)
|
|
SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename,
|
|
struct stat __user *, statbuf, int, flag)
|
|
{
|
|
struct kstat stat;
|
|
int error;
|
|
|
|
error = vfs_fstatat(dfd, filename, &stat, flag);
|
|
if (error)
|
|
return error;
|
|
return cp_new_stat(&stat, statbuf);
|
|
}
|
|
#endif
|
|
|
|
SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error = vfs_fstat(fd, &stat);
|
|
|
|
if (!error)
|
|
error = cp_new_stat(&stat, statbuf);
|
|
|
|
return error;
|
|
}
|
|
#endif
|
|
|
|
static int do_readlinkat(int dfd, const char __user *pathname,
|
|
char __user *buf, int bufsiz)
|
|
{
|
|
struct path path;
|
|
int error;
|
|
int empty = 0;
|
|
unsigned int lookup_flags = LOOKUP_EMPTY;
|
|
|
|
if (bufsiz <= 0)
|
|
return -EINVAL;
|
|
|
|
retry:
|
|
error = user_path_at_empty(dfd, pathname, lookup_flags, &path, &empty);
|
|
if (!error) {
|
|
struct inode *inode = d_backing_inode(path.dentry);
|
|
|
|
error = empty ? -ENOENT : -EINVAL;
|
|
/*
|
|
* AFS mountpoints allow readlink(2) but are not symlinks
|
|
*/
|
|
if (d_is_symlink(path.dentry) || inode->i_op->readlink) {
|
|
error = security_inode_readlink(path.dentry);
|
|
if (!error) {
|
|
touch_atime(&path);
|
|
error = vfs_readlink(path.dentry, buf, bufsiz);
|
|
}
|
|
}
|
|
path_put(&path);
|
|
if (retry_estale(error, lookup_flags)) {
|
|
lookup_flags |= LOOKUP_REVAL;
|
|
goto retry;
|
|
}
|
|
}
|
|
return error;
|
|
}
|
|
|
|
SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
|
|
char __user *, buf, int, bufsiz)
|
|
{
|
|
return do_readlinkat(dfd, pathname, buf, bufsiz);
|
|
}
|
|
|
|
SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf,
|
|
int, bufsiz)
|
|
{
|
|
return do_readlinkat(AT_FDCWD, path, buf, bufsiz);
|
|
}
|
|
|
|
|
|
/* ---------- LFS-64 ----------- */
|
|
#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64)
|
|
|
|
#ifndef INIT_STRUCT_STAT64_PADDING
|
|
# define INIT_STRUCT_STAT64_PADDING(st) memset(&st, 0, sizeof(st))
|
|
#endif
|
|
|
|
static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf)
|
|
{
|
|
struct stat64 tmp;
|
|
|
|
INIT_STRUCT_STAT64_PADDING(tmp);
|
|
#ifdef CONFIG_MIPS
|
|
/* mips has weird padding, so we don't get 64 bits there */
|
|
tmp.st_dev = new_encode_dev(stat->dev);
|
|
tmp.st_rdev = new_encode_dev(stat->rdev);
|
|
#else
|
|
tmp.st_dev = huge_encode_dev(stat->dev);
|
|
tmp.st_rdev = huge_encode_dev(stat->rdev);
|
|
#endif
|
|
tmp.st_ino = stat->ino;
|
|
if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
|
|
return -EOVERFLOW;
|
|
#ifdef STAT64_HAS_BROKEN_ST_INO
|
|
tmp.__st_ino = stat->ino;
|
|
#endif
|
|
tmp.st_mode = stat->mode;
|
|
tmp.st_nlink = stat->nlink;
|
|
tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid);
|
|
tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid);
|
|
tmp.st_atime = stat->atime.tv_sec;
|
|
tmp.st_atime_nsec = stat->atime.tv_nsec;
|
|
tmp.st_mtime = stat->mtime.tv_sec;
|
|
tmp.st_mtime_nsec = stat->mtime.tv_nsec;
|
|
tmp.st_ctime = stat->ctime.tv_sec;
|
|
tmp.st_ctime_nsec = stat->ctime.tv_nsec;
|
|
tmp.st_size = stat->size;
|
|
tmp.st_blocks = stat->blocks;
|
|
tmp.st_blksize = stat->blksize;
|
|
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
|
|
}
|
|
|
|
SYSCALL_DEFINE2(stat64, const char __user *, filename,
|
|
struct stat64 __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error = vfs_stat(filename, &stat);
|
|
|
|
if (!error)
|
|
error = cp_new_stat64(&stat, statbuf);
|
|
|
|
return error;
|
|
}
|
|
|
|
SYSCALL_DEFINE2(lstat64, const char __user *, filename,
|
|
struct stat64 __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error = vfs_lstat(filename, &stat);
|
|
|
|
if (!error)
|
|
error = cp_new_stat64(&stat, statbuf);
|
|
|
|
return error;
|
|
}
|
|
|
|
SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error = vfs_fstat(fd, &stat);
|
|
|
|
if (!error)
|
|
error = cp_new_stat64(&stat, statbuf);
|
|
|
|
return error;
|
|
}
|
|
|
|
SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
|
|
struct stat64 __user *, statbuf, int, flag)
|
|
{
|
|
struct kstat stat;
|
|
int error;
|
|
|
|
error = vfs_fstatat(dfd, filename, &stat, flag);
|
|
if (error)
|
|
return error;
|
|
return cp_new_stat64(&stat, statbuf);
|
|
}
|
|
#endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
|
|
|
|
static noinline_for_stack int
|
|
cp_statx(const struct kstat *stat, struct statx __user *buffer)
|
|
{
|
|
struct statx tmp;
|
|
|
|
memset(&tmp, 0, sizeof(tmp));
|
|
|
|
/* STATX_CHANGE_COOKIE is kernel-only for now */
|
|
tmp.stx_mask = stat->result_mask & ~STATX_CHANGE_COOKIE;
|
|
tmp.stx_blksize = stat->blksize;
|
|
/* STATX_ATTR_CHANGE_MONOTONIC is kernel-only for now */
|
|
tmp.stx_attributes = stat->attributes & ~STATX_ATTR_CHANGE_MONOTONIC;
|
|
tmp.stx_nlink = stat->nlink;
|
|
tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid);
|
|
tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid);
|
|
tmp.stx_mode = stat->mode;
|
|
tmp.stx_ino = stat->ino;
|
|
tmp.stx_size = stat->size;
|
|
tmp.stx_blocks = stat->blocks;
|
|
tmp.stx_attributes_mask = stat->attributes_mask;
|
|
tmp.stx_atime.tv_sec = stat->atime.tv_sec;
|
|
tmp.stx_atime.tv_nsec = stat->atime.tv_nsec;
|
|
tmp.stx_btime.tv_sec = stat->btime.tv_sec;
|
|
tmp.stx_btime.tv_nsec = stat->btime.tv_nsec;
|
|
tmp.stx_ctime.tv_sec = stat->ctime.tv_sec;
|
|
tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec;
|
|
tmp.stx_mtime.tv_sec = stat->mtime.tv_sec;
|
|
tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec;
|
|
tmp.stx_rdev_major = MAJOR(stat->rdev);
|
|
tmp.stx_rdev_minor = MINOR(stat->rdev);
|
|
tmp.stx_dev_major = MAJOR(stat->dev);
|
|
tmp.stx_dev_minor = MINOR(stat->dev);
|
|
tmp.stx_mnt_id = stat->mnt_id;
|
|
tmp.stx_dio_mem_align = stat->dio_mem_align;
|
|
tmp.stx_dio_offset_align = stat->dio_offset_align;
|
|
|
|
return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
|
|
}
|
|
|
|
int do_statx(int dfd, struct filename *filename, unsigned int flags,
|
|
unsigned int mask, struct statx __user *buffer)
|
|
{
|
|
struct kstat stat;
|
|
int error;
|
|
|
|
if (mask & STATX__RESERVED)
|
|
return -EINVAL;
|
|
if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
|
|
return -EINVAL;
|
|
|
|
/* STATX_CHANGE_COOKIE is kernel-only for now. Ignore requests
|
|
* from userland.
|
|
*/
|
|
mask &= ~STATX_CHANGE_COOKIE;
|
|
|
|
error = vfs_statx(dfd, filename, flags, &stat, mask);
|
|
if (error)
|
|
return error;
|
|
|
|
return cp_statx(&stat, buffer);
|
|
}
|
|
|
|
/**
|
|
* sys_statx - System call to get enhanced stats
|
|
* @dfd: Base directory to pathwalk from *or* fd to stat.
|
|
* @filename: File to stat or "" with AT_EMPTY_PATH
|
|
* @flags: AT_* flags to control pathwalk.
|
|
* @mask: Parts of statx struct actually required.
|
|
* @buffer: Result buffer.
|
|
*
|
|
* Note that fstat() can be emulated by setting dfd to the fd of interest,
|
|
* supplying "" as the filename and setting AT_EMPTY_PATH in the flags.
|
|
*/
|
|
SYSCALL_DEFINE5(statx,
|
|
int, dfd, const char __user *, filename, unsigned, flags,
|
|
unsigned int, mask,
|
|
struct statx __user *, buffer)
|
|
{
|
|
int ret;
|
|
struct filename *name;
|
|
|
|
name = getname_flags(filename, getname_statx_lookup_flags(flags), NULL);
|
|
ret = do_statx(dfd, name, flags, mask, buffer);
|
|
putname(name);
|
|
|
|
return ret;
|
|
}
|
|
|
|
#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_STAT)
|
|
static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
|
|
{
|
|
struct compat_stat tmp;
|
|
|
|
if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev))
|
|
return -EOVERFLOW;
|
|
if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev))
|
|
return -EOVERFLOW;
|
|
|
|
memset(&tmp, 0, sizeof(tmp));
|
|
tmp.st_dev = new_encode_dev(stat->dev);
|
|
tmp.st_ino = stat->ino;
|
|
if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
|
|
return -EOVERFLOW;
|
|
tmp.st_mode = stat->mode;
|
|
tmp.st_nlink = stat->nlink;
|
|
if (tmp.st_nlink != stat->nlink)
|
|
return -EOVERFLOW;
|
|
SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
|
|
SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
|
|
tmp.st_rdev = new_encode_dev(stat->rdev);
|
|
if ((u64) stat->size > MAX_NON_LFS)
|
|
return -EOVERFLOW;
|
|
tmp.st_size = stat->size;
|
|
tmp.st_atime = stat->atime.tv_sec;
|
|
tmp.st_atime_nsec = stat->atime.tv_nsec;
|
|
tmp.st_mtime = stat->mtime.tv_sec;
|
|
tmp.st_mtime_nsec = stat->mtime.tv_nsec;
|
|
tmp.st_ctime = stat->ctime.tv_sec;
|
|
tmp.st_ctime_nsec = stat->ctime.tv_nsec;
|
|
tmp.st_blocks = stat->blocks;
|
|
tmp.st_blksize = stat->blksize;
|
|
return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
|
|
}
|
|
|
|
COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename,
|
|
struct compat_stat __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error;
|
|
|
|
error = vfs_stat(filename, &stat);
|
|
if (error)
|
|
return error;
|
|
return cp_compat_stat(&stat, statbuf);
|
|
}
|
|
|
|
COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename,
|
|
struct compat_stat __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error;
|
|
|
|
error = vfs_lstat(filename, &stat);
|
|
if (error)
|
|
return error;
|
|
return cp_compat_stat(&stat, statbuf);
|
|
}
|
|
|
|
#ifndef __ARCH_WANT_STAT64
|
|
COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd,
|
|
const char __user *, filename,
|
|
struct compat_stat __user *, statbuf, int, flag)
|
|
{
|
|
struct kstat stat;
|
|
int error;
|
|
|
|
error = vfs_fstatat(dfd, filename, &stat, flag);
|
|
if (error)
|
|
return error;
|
|
return cp_compat_stat(&stat, statbuf);
|
|
}
|
|
#endif
|
|
|
|
COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd,
|
|
struct compat_stat __user *, statbuf)
|
|
{
|
|
struct kstat stat;
|
|
int error = vfs_fstat(fd, &stat);
|
|
|
|
if (!error)
|
|
error = cp_compat_stat(&stat, statbuf);
|
|
return error;
|
|
}
|
|
#endif
|
|
|
|
/* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
|
|
void __inode_add_bytes(struct inode *inode, loff_t bytes)
|
|
{
|
|
inode->i_blocks += bytes >> 9;
|
|
bytes &= 511;
|
|
inode->i_bytes += bytes;
|
|
if (inode->i_bytes >= 512) {
|
|
inode->i_blocks++;
|
|
inode->i_bytes -= 512;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(__inode_add_bytes);
|
|
|
|
void inode_add_bytes(struct inode *inode, loff_t bytes)
|
|
{
|
|
spin_lock(&inode->i_lock);
|
|
__inode_add_bytes(inode, bytes);
|
|
spin_unlock(&inode->i_lock);
|
|
}
|
|
|
|
EXPORT_SYMBOL(inode_add_bytes);
|
|
|
|
void __inode_sub_bytes(struct inode *inode, loff_t bytes)
|
|
{
|
|
inode->i_blocks -= bytes >> 9;
|
|
bytes &= 511;
|
|
if (inode->i_bytes < bytes) {
|
|
inode->i_blocks--;
|
|
inode->i_bytes += 512;
|
|
}
|
|
inode->i_bytes -= bytes;
|
|
}
|
|
|
|
EXPORT_SYMBOL(__inode_sub_bytes);
|
|
|
|
void inode_sub_bytes(struct inode *inode, loff_t bytes)
|
|
{
|
|
spin_lock(&inode->i_lock);
|
|
__inode_sub_bytes(inode, bytes);
|
|
spin_unlock(&inode->i_lock);
|
|
}
|
|
|
|
EXPORT_SYMBOL(inode_sub_bytes);
|
|
|
|
loff_t inode_get_bytes(struct inode *inode)
|
|
{
|
|
loff_t ret;
|
|
|
|
spin_lock(&inode->i_lock);
|
|
ret = __inode_get_bytes(inode);
|
|
spin_unlock(&inode->i_lock);
|
|
return ret;
|
|
}
|
|
|
|
EXPORT_SYMBOL(inode_get_bytes);
|
|
|
|
void inode_set_bytes(struct inode *inode, loff_t bytes)
|
|
{
|
|
/* Caller is here responsible for sufficient locking
|
|
* (ie. inode->i_lock) */
|
|
inode->i_blocks = bytes >> 9;
|
|
inode->i_bytes = bytes & 511;
|
|
}
|
|
|
|
EXPORT_SYMBOL(inode_set_bytes);
|