2019-06-01 11:08:42 +03:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0-only */
|
2013-11-28 23:54:31 +04:00
|
|
|
/*
|
|
|
|
* fs/kernfs/kernfs-internal.h - kernfs internal header file
|
|
|
|
*
|
|
|
|
* Copyright (c) 2001-3 Patrick Mochel
|
|
|
|
* Copyright (c) 2007 SUSE Linux Products GmbH
|
|
|
|
* Copyright (c) 2007, 2013 Tejun Heo <teheo@suse.de>
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef __KERNFS_INTERNAL_H
|
|
|
|
#define __KERNFS_INTERNAL_H
|
|
|
|
|
|
|
|
#include <linux/lockdep.h>
|
|
|
|
#include <linux/fs.h>
|
2013-11-28 23:54:33 +04:00
|
|
|
#include <linux/mutex.h>
|
2021-07-16 12:28:29 +03:00
|
|
|
#include <linux/rwsem.h>
|
2013-11-24 02:40:02 +04:00
|
|
|
#include <linux/xattr.h>
|
2013-11-28 23:54:31 +04:00
|
|
|
|
|
|
|
#include <linux/kernfs.h>
|
kernfs, sysfs, cgroup, intel_rdt: Support fs_context
Make kernfs support superblock creation/mount/remount with fs_context.
This requires that sysfs, cgroup and intel_rdt, which are built on kernfs,
be made to support fs_context also.
Notes:
(1) A kernfs_fs_context struct is created to wrap fs_context and the
kernfs mount parameters are moved in here (or are in fs_context).
(2) kernfs_mount{,_ns}() are made into kernfs_get_tree(). The extra
namespace tag parameter is passed in the context if desired
(3) kernfs_free_fs_context() is provided as a destructor for the
kernfs_fs_context struct, but for the moment it does nothing except
get called in the right places.
(4) sysfs doesn't wrap kernfs_fs_context since it has no parameters to
pass, but possibly this should be done anyway in case someone wants to
add a parameter in future.
(5) A cgroup_fs_context struct is created to wrap kernfs_fs_context and
the cgroup v1 and v2 mount parameters are all moved there.
(6) cgroup1 parameter parsing error messages are now handled by invalf(),
which allows userspace to collect them directly.
(7) cgroup1 parameter cleanup is now done in the context destructor rather
than in the mount/get_tree and remount functions.
Weirdies:
(*) cgroup_do_get_tree() calls cset_cgroup_from_root() with locks held,
but then uses the resulting pointer after dropping the locks. I'm
told this is okay and needs commenting.
(*) The cgroup refcount web. This really needs documenting.
(*) cgroup2 only has one root?
Add a suggestion from Thomas Gleixner in which the RDT enablement code is
placed into its own function.
[folded a leak fix from Andrey Vagin]
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cc: Tejun Heo <tj@kernel.org>
cc: Li Zefan <lizefan@huawei.com>
cc: Johannes Weiner <hannes@cmpxchg.org>
cc: cgroups@vger.kernel.org
cc: fenghua.yu@intel.com
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-02 02:07:26 +03:00
|
|
|
#include <linux/fs_context.h>
|
2013-11-28 23:54:31 +04:00
|
|
|
|
2013-12-11 23:11:55 +04:00
|
|
|
struct kernfs_iattrs {
|
2019-02-22 17:57:12 +03:00
|
|
|
kuid_t ia_uid;
|
|
|
|
kgid_t ia_gid;
|
|
|
|
struct timespec64 ia_atime;
|
|
|
|
struct timespec64 ia_mtime;
|
|
|
|
struct timespec64 ia_ctime;
|
2013-11-24 02:40:02 +04:00
|
|
|
|
|
|
|
struct simple_xattrs xattrs;
|
2020-03-12 23:03:16 +03:00
|
|
|
atomic_t nr_user_xattrs;
|
|
|
|
atomic_t user_xattr_size;
|
2013-11-28 23:54:31 +04:00
|
|
|
};
|
|
|
|
|
2014-02-03 23:03:00 +04:00
|
|
|
/* +1 to avoid triggering overflow warning when negating it */
|
|
|
|
#define KN_DEACTIVATED_BIAS (INT_MIN + 1)
|
2013-11-28 23:54:31 +04:00
|
|
|
|
2013-12-11 23:11:56 +04:00
|
|
|
/* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */
|
2013-11-28 23:54:31 +04:00
|
|
|
|
2013-11-28 23:54:40 +04:00
|
|
|
/**
|
2013-12-11 23:11:53 +04:00
|
|
|
* kernfs_root - find out the kernfs_root a kernfs_node belongs to
|
|
|
|
* @kn: kernfs_node of interest
|
2013-11-28 23:54:40 +04:00
|
|
|
*
|
2013-12-11 23:11:53 +04:00
|
|
|
* Return the kernfs_root @kn belongs to.
|
2013-11-28 23:54:40 +04:00
|
|
|
*/
|
2013-12-11 23:11:53 +04:00
|
|
|
static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn)
|
2013-11-28 23:54:40 +04:00
|
|
|
{
|
|
|
|
/* if parent exists, it's always a dir; otherwise, @sd is a dir */
|
2013-12-11 23:11:54 +04:00
|
|
|
if (kn->parent)
|
|
|
|
kn = kn->parent;
|
|
|
|
return kn->dir.root;
|
2013-11-28 23:54:40 +04:00
|
|
|
}
|
|
|
|
|
2013-11-28 23:54:44 +04:00
|
|
|
/*
|
|
|
|
* mount.c
|
|
|
|
*/
|
2013-12-11 23:11:55 +04:00
|
|
|
struct kernfs_super_info {
|
2014-04-09 19:07:30 +04:00
|
|
|
struct super_block *sb;
|
|
|
|
|
2013-11-28 23:54:44 +04:00
|
|
|
/*
|
|
|
|
* The root associated with this super_block. Each super_block is
|
|
|
|
* identified by the root and ns it's associated with.
|
|
|
|
*/
|
|
|
|
struct kernfs_root *root;
|
|
|
|
|
|
|
|
/*
|
2013-12-11 23:11:53 +04:00
|
|
|
* Each sb is associated with one namespace tag, currently the
|
2013-12-11 23:11:55 +04:00
|
|
|
* network namespace of the task which mounted this kernfs
|
|
|
|
* instance. If multiple tags become necessary, make the following
|
|
|
|
* an array and compare kernfs_node tag against every entry.
|
2013-11-28 23:54:44 +04:00
|
|
|
*/
|
|
|
|
const void *ns;
|
2014-04-09 19:07:30 +04:00
|
|
|
|
2021-07-16 12:28:29 +03:00
|
|
|
/* anchored at kernfs_root->supers, protected by kernfs_rwsem */
|
2014-04-09 19:07:30 +04:00
|
|
|
struct list_head node;
|
2013-11-28 23:54:44 +04:00
|
|
|
};
|
2013-12-11 23:11:55 +04:00
|
|
|
#define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info))
|
2013-11-28 23:54:44 +04:00
|
|
|
|
2017-07-12 21:49:49 +03:00
|
|
|
static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
if (d_really_is_negative(dentry))
|
|
|
|
return NULL;
|
|
|
|
return d_inode(dentry)->i_private;
|
|
|
|
}
|
|
|
|
|
2021-07-16 12:28:18 +03:00
|
|
|
static inline void kernfs_set_rev(struct kernfs_node *parent,
|
|
|
|
struct dentry *dentry)
|
|
|
|
{
|
|
|
|
dentry->d_time = parent->dir.rev;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void kernfs_inc_rev(struct kernfs_node *parent)
|
|
|
|
{
|
|
|
|
parent->dir.rev++;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool kernfs_dir_changed(struct kernfs_node *parent,
|
|
|
|
struct dentry *dentry)
|
|
|
|
{
|
|
|
|
if (parent->dir.rev != dentry->d_time)
|
|
|
|
return true;
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2014-02-14 12:57:27 +04:00
|
|
|
extern const struct super_operations kernfs_sops;
|
2019-02-06 07:55:42 +03:00
|
|
|
extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache;
|
2013-11-28 23:54:44 +04:00
|
|
|
|
2013-11-28 23:54:32 +04:00
|
|
|
/*
|
|
|
|
* inode.c
|
|
|
|
*/
|
2016-09-29 18:48:33 +03:00
|
|
|
extern const struct xattr_handler *kernfs_xattr_handlers[];
|
2013-12-11 23:11:58 +04:00
|
|
|
void kernfs_evict_inode(struct inode *inode);
|
2021-01-21 16:19:43 +03:00
|
|
|
int kernfs_iop_permission(struct user_namespace *mnt_userns,
|
|
|
|
struct inode *inode, int mask);
|
|
|
|
int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
|
|
|
|
struct iattr *iattr);
|
|
|
|
int kernfs_iop_getattr(struct user_namespace *mnt_userns,
|
|
|
|
const struct path *path, struct kstat *stat,
|
statx: Add a system call to make enhanced file info available
Add a system call to make extended file information available, including
file creation and some attribute flags where available through the
underlying filesystem.
The getattr inode operation is altered to take two additional arguments: a
u32 request_mask and an unsigned int flags that indicate the
synchronisation mode. This change is propagated to the vfs_getattr*()
function.
Functions like vfs_stat() are now inline wrappers around new functions
vfs_statx() and vfs_statx_fd() to reduce stack usage.
========
OVERVIEW
========
The idea was initially proposed as a set of xattrs that could be retrieved
with getxattr(), but the general preference proved to be for a new syscall
with an extended stat structure.
A number of requests were gathered for features to be included. The
following have been included:
(1) Make the fields a consistent size on all arches and make them large.
(2) Spare space, request flags and information flags are provided for
future expansion.
(3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an
__s64).
(4) Creation time: The SMB protocol carries the creation time, which could
be exported by Samba, which will in turn help CIFS make use of
FS-Cache as that can be used for coherency data (stx_btime).
This is also specified in NFSv4 as a recommended attribute and could
be exported by NFSD [Steve French].
(5) Lightweight stat: Ask for just those details of interest, and allow a
netfs (such as NFS) to approximate anything not of interest, possibly
without going to the server [Trond Myklebust, Ulrich Drepper, Andreas
Dilger] (AT_STATX_DONT_SYNC).
(6) Heavyweight stat: Force a netfs to go to the server, even if it thinks
its cached attributes are up to date [Trond Myklebust]
(AT_STATX_FORCE_SYNC).
And the following have been left out for future extension:
(7) Data version number: Could be used by userspace NFS servers [Aneesh
Kumar].
Can also be used to modify fill_post_wcc() in NFSD which retrieves
i_version directly, but has just called vfs_getattr(). It could get
it from the kstat struct if it used vfs_xgetattr() instead.
(There's disagreement on the exact semantics of a single field, since
not all filesystems do this the same way).
(8) BSD stat compatibility: Including more fields from the BSD stat such
as creation time (st_btime) and inode generation number (st_gen)
[Jeremy Allison, Bernd Schubert].
(9) Inode generation number: Useful for FUSE and userspace NFS servers
[Bernd Schubert].
(This was asked for but later deemed unnecessary with the
open-by-handle capability available and caused disagreement as to
whether it's a security hole or not).
(10) Extra coherency data may be useful in making backups [Andreas Dilger].
(No particular data were offered, but things like last backup
timestamp, the data version number and the DOS archive bit would come
into this category).
(11) Allow the filesystem to indicate what it can/cannot provide: A
filesystem can now say it doesn't support a standard stat feature if
that isn't available, so if, for instance, inode numbers or UIDs don't
exist or are fabricated locally...
(This requires a separate system call - I have an fsinfo() call idea
for this).
(12) Store a 16-byte volume ID in the superblock that can be returned in
struct xstat [Steve French].
(Deferred to fsinfo).
(13) Include granularity fields in the time data to indicate the
granularity of each of the times (NFSv4 time_delta) [Steve French].
(Deferred to fsinfo).
(14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags.
Note that the Linux IOC flags are a mess and filesystems such as Ext4
define flags that aren't in linux/fs.h, so translation in the kernel
may be a necessity (or, possibly, we provide the filesystem type too).
(Some attributes are made available in stx_attributes, but the general
feeling was that the IOC flags were to ext[234]-specific and shouldn't
be exposed through statx this way).
(15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer,
Michael Kerrisk].
(Deferred, probably to fsinfo. Finding out if there's an ACL or
seclabal might require extra filesystem operations).
(16) Femtosecond-resolution timestamps [Dave Chinner].
(A __reserved field has been left in the statx_timestamp struct for
this - if there proves to be a need).
(17) A set multiple attributes syscall to go with this.
===============
NEW SYSTEM CALL
===============
The new system call is:
int ret = statx(int dfd,
const char *filename,
unsigned int flags,
unsigned int mask,
struct statx *buffer);
The dfd, filename and flags parameters indicate the file to query, in a
similar way to fstatat(). There is no equivalent of lstat() as that can be
emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is
also no equivalent of fstat() as that can be emulated by passing a NULL
filename to statx() with the fd of interest in dfd.
Whether or not statx() synchronises the attributes with the backing store
can be controlled by OR'ing a value into the flags argument (this typically
only affects network filesystems):
(1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this
respect.
(2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise
its attributes with the server - which might require data writeback to
occur to get the timestamps correct.
(3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a
network filesystem. The resulting values should be considered
approximate.
mask is a bitmask indicating the fields in struct statx that are of
interest to the caller. The user should set this to STATX_BASIC_STATS to
get the basic set returned by stat(). It should be noted that asking for
more information may entail extra I/O operations.
buffer points to the destination for the data. This must be 256 bytes in
size.
======================
MAIN ATTRIBUTES RECORD
======================
The following structures are defined in which to return the main attribute
set:
struct statx_timestamp {
__s64 tv_sec;
__s32 tv_nsec;
__s32 __reserved;
};
struct statx {
__u32 stx_mask;
__u32 stx_blksize;
__u64 stx_attributes;
__u32 stx_nlink;
__u32 stx_uid;
__u32 stx_gid;
__u16 stx_mode;
__u16 __spare0[1];
__u64 stx_ino;
__u64 stx_size;
__u64 stx_blocks;
__u64 __spare1[1];
struct statx_timestamp stx_atime;
struct statx_timestamp stx_btime;
struct statx_timestamp stx_ctime;
struct statx_timestamp stx_mtime;
__u32 stx_rdev_major;
__u32 stx_rdev_minor;
__u32 stx_dev_major;
__u32 stx_dev_minor;
__u64 __spare2[14];
};
The defined bits in request_mask and stx_mask are:
STATX_TYPE Want/got stx_mode & S_IFMT
STATX_MODE Want/got stx_mode & ~S_IFMT
STATX_NLINK Want/got stx_nlink
STATX_UID Want/got stx_uid
STATX_GID Want/got stx_gid
STATX_ATIME Want/got stx_atime{,_ns}
STATX_MTIME Want/got stx_mtime{,_ns}
STATX_CTIME Want/got stx_ctime{,_ns}
STATX_INO Want/got stx_ino
STATX_SIZE Want/got stx_size
STATX_BLOCKS Want/got stx_blocks
STATX_BASIC_STATS [The stuff in the normal stat struct]
STATX_BTIME Want/got stx_btime{,_ns}
STATX_ALL [All currently available stuff]
stx_btime is the file creation time, stx_mask is a bitmask indicating the
data provided and __spares*[] are where as-yet undefined fields can be
placed.
Time fields are structures with separate seconds and nanoseconds fields
plus a reserved field in case we want to add even finer resolution. Note
that times will be negative if before 1970; in such a case, the nanosecond
fields will also be negative if not zero.
The bits defined in the stx_attributes field convey information about a
file, how it is accessed, where it is and what it does. The following
attributes map to FS_*_FL flags and are the same numerical value:
STATX_ATTR_COMPRESSED File is compressed by the fs
STATX_ATTR_IMMUTABLE File is marked immutable
STATX_ATTR_APPEND File is append-only
STATX_ATTR_NODUMP File is not to be dumped
STATX_ATTR_ENCRYPTED File requires key to decrypt in fs
Within the kernel, the supported flags are listed by:
KSTAT_ATTR_FS_IOC_FLAGS
[Are any other IOC flags of sufficient general interest to be exposed
through this interface?]
New flags include:
STATX_ATTR_AUTOMOUNT Object is an automount trigger
These are for the use of GUI tools that might want to mark files specially,
depending on what they are.
Fields in struct statx come in a number of classes:
(0) stx_dev_*, stx_blksize.
These are local system information and are always available.
(1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino,
stx_size, stx_blocks.
These will be returned whether the caller asks for them or not. The
corresponding bits in stx_mask will be set to indicate whether they
actually have valid values.
If the caller didn't ask for them, then they may be approximated. For
example, NFS won't waste any time updating them from the server,
unless as a byproduct of updating something requested.
If the values don't actually exist for the underlying object (such as
UID or GID on a DOS file), then the bit won't be set in the stx_mask,
even if the caller asked for the value. In such a case, the returned
value will be a fabrication.
Note that there are instances where the type might not be valid, for
instance Windows reparse points.
(2) stx_rdev_*.
This will be set only if stx_mode indicates we're looking at a
blockdev or a chardev, otherwise will be 0.
(3) stx_btime.
Similar to (1), except this will be set to 0 if it doesn't exist.
=======
TESTING
=======
The following test program can be used to test the statx system call:
samples/statx/test-statx.c
Just compile and run, passing it paths to the files you want to examine.
The file is built automatically if CONFIG_SAMPLES is enabled.
Here's some example output. Firstly, an NFS directory that crosses to
another FSID. Note that the AUTOMOUNT attribute is set because transiting
this directory will cause d_automount to be invoked by the VFS.
[root@andromeda ~]# /tmp/test-statx -A /warthog/data
statx(/warthog/data) = 0
results=7ff
Size: 4096 Blocks: 8 IO Block: 1048576 directory
Device: 00:26 Inode: 1703937 Links: 125
Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041
Access: 2016-11-24 09:02:12.219699527+0000
Modify: 2016-11-17 10:44:36.225653653+0000
Change: 2016-11-17 10:44:36.225653653+0000
Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------)
Secondly, the result of automounting on that directory.
[root@andromeda ~]# /tmp/test-statx /warthog/data
statx(/warthog/data) = 0
results=7ff
Size: 4096 Blocks: 8 IO Block: 1048576 directory
Device: 00:27 Inode: 2 Links: 125
Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041
Access: 2016-11-24 09:02:12.219699527+0000
Modify: 2016-11-17 10:44:36.225653653+0000
Change: 2016-11-17 10:44:36.225653653+0000
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-01-31 19:46:22 +03:00
|
|
|
u32 request_mask, unsigned int query_flags);
|
2013-12-11 23:11:58 +04:00
|
|
|
ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
|
2018-07-21 00:56:47 +03:00
|
|
|
int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
|
2013-11-28 23:54:32 +04:00
|
|
|
|
2013-11-28 23:54:33 +04:00
|
|
|
/*
|
|
|
|
* dir.c
|
|
|
|
*/
|
2021-07-16 12:28:29 +03:00
|
|
|
extern struct rw_semaphore kernfs_rwsem;
|
2013-12-11 23:11:57 +04:00
|
|
|
extern const struct dentry_operations kernfs_dops;
|
|
|
|
extern const struct file_operations kernfs_dir_fops;
|
|
|
|
extern const struct inode_operations kernfs_dir_iops;
|
2013-11-28 23:54:33 +04:00
|
|
|
|
2013-12-11 23:11:58 +04:00
|
|
|
struct kernfs_node *kernfs_get_active(struct kernfs_node *kn);
|
|
|
|
void kernfs_put_active(struct kernfs_node *kn);
|
2014-02-03 23:02:58 +04:00
|
|
|
int kernfs_add_one(struct kernfs_node *kn);
|
2014-01-17 18:58:25 +04:00
|
|
|
struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
|
|
|
|
const char *name, umode_t mode,
|
2018-07-21 00:56:47 +03:00
|
|
|
kuid_t uid, kgid_t gid,
|
2014-01-17 18:58:25 +04:00
|
|
|
unsigned flags);
|
2013-11-28 23:54:33 +04:00
|
|
|
|
2013-11-28 23:54:34 +04:00
|
|
|
/*
|
|
|
|
* file.c
|
|
|
|
*/
|
2013-12-11 23:11:57 +04:00
|
|
|
extern const struct file_operations kernfs_file_fops;
|
2013-11-28 23:54:34 +04:00
|
|
|
|
2016-12-27 22:49:03 +03:00
|
|
|
void kernfs_drain_open_files(struct kernfs_node *kn);
|
2013-11-28 23:54:34 +04:00
|
|
|
|
2013-11-28 23:54:35 +04:00
|
|
|
/*
|
|
|
|
* symlink.c
|
|
|
|
*/
|
2013-12-11 23:11:57 +04:00
|
|
|
extern const struct inode_operations kernfs_symlink_iops;
|
2013-11-28 23:54:35 +04:00
|
|
|
|
2013-11-28 23:54:31 +04:00
|
|
|
#endif /* __KERNFS_INTERNAL_H */
|