mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 16:29:59 +00:00
![David Howells](/assets/img/avatar_default.png)
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>
148 lines
6 KiB
C
148 lines
6 KiB
C
/*
|
|
* fs/cifs/cifsfs.h
|
|
*
|
|
* Copyright (c) International Business Machines Corp., 2002, 2007
|
|
* Author(s): Steve French (sfrench@us.ibm.com)
|
|
*
|
|
* This library is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU Lesser General Public License as published
|
|
* by the Free Software Foundation; either version 2.1 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This library is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
|
|
* the GNU Lesser General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU Lesser General Public License
|
|
* along with this library; if not, write to the Free Software
|
|
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
|
*/
|
|
|
|
#ifndef _CIFSFS_H
|
|
#define _CIFSFS_H
|
|
|
|
#include <linux/hash.h>
|
|
|
|
#define ROOT_I 2
|
|
|
|
/*
|
|
* ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
|
|
* so that it will fit. We use hash_64 to convert the value to 31 bits, and
|
|
* then add 1, to ensure that we don't end up with a 0 as the value.
|
|
*/
|
|
static inline ino_t
|
|
cifs_uniqueid_to_ino_t(u64 fileid)
|
|
{
|
|
if ((sizeof(ino_t)) < (sizeof(u64)))
|
|
return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
|
|
|
|
return (ino_t)fileid;
|
|
|
|
}
|
|
|
|
static inline void cifs_set_time(struct dentry *dentry, unsigned long time)
|
|
{
|
|
dentry->d_fsdata = (void *) time;
|
|
}
|
|
|
|
static inline unsigned long cifs_get_time(struct dentry *dentry)
|
|
{
|
|
return (unsigned long) dentry->d_fsdata;
|
|
}
|
|
|
|
extern struct file_system_type cifs_fs_type;
|
|
extern const struct address_space_operations cifs_addr_ops;
|
|
extern const struct address_space_operations cifs_addr_ops_smallbuf;
|
|
|
|
/* Functions related to super block operations */
|
|
extern void cifs_sb_active(struct super_block *sb);
|
|
extern void cifs_sb_deactive(struct super_block *sb);
|
|
|
|
/* Functions related to inodes */
|
|
extern const struct inode_operations cifs_dir_inode_ops;
|
|
extern struct inode *cifs_root_iget(struct super_block *);
|
|
extern int cifs_create(struct inode *, struct dentry *, umode_t,
|
|
bool excl);
|
|
extern int cifs_atomic_open(struct inode *, struct dentry *,
|
|
struct file *, unsigned, umode_t,
|
|
int *);
|
|
extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
|
|
unsigned int);
|
|
extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
|
|
extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *);
|
|
extern int cifs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
|
|
extern int cifs_mkdir(struct inode *, struct dentry *, umode_t);
|
|
extern int cifs_rmdir(struct inode *, struct dentry *);
|
|
extern int cifs_rename2(struct inode *, struct dentry *, struct inode *,
|
|
struct dentry *, unsigned int);
|
|
extern int cifs_revalidate_file_attr(struct file *filp);
|
|
extern int cifs_revalidate_dentry_attr(struct dentry *);
|
|
extern int cifs_revalidate_file(struct file *filp);
|
|
extern int cifs_revalidate_dentry(struct dentry *);
|
|
extern int cifs_invalidate_mapping(struct inode *inode);
|
|
extern int cifs_revalidate_mapping(struct inode *inode);
|
|
extern int cifs_zap_mapping(struct inode *inode);
|
|
extern int cifs_getattr(const struct path *, struct kstat *, u32, unsigned int);
|
|
extern int cifs_setattr(struct dentry *, struct iattr *);
|
|
|
|
extern const struct inode_operations cifs_file_inode_ops;
|
|
extern const struct inode_operations cifs_symlink_inode_ops;
|
|
extern const struct inode_operations cifs_dfs_referral_inode_operations;
|
|
|
|
|
|
/* Functions related to files and directories */
|
|
extern const struct file_operations cifs_file_ops;
|
|
extern const struct file_operations cifs_file_direct_ops; /* if directio mnt */
|
|
extern const struct file_operations cifs_file_strict_ops; /* if strictio mnt */
|
|
extern const struct file_operations cifs_file_nobrl_ops; /* no brlocks */
|
|
extern const struct file_operations cifs_file_direct_nobrl_ops;
|
|
extern const struct file_operations cifs_file_strict_nobrl_ops;
|
|
extern int cifs_open(struct inode *inode, struct file *file);
|
|
extern int cifs_close(struct inode *inode, struct file *file);
|
|
extern int cifs_closedir(struct inode *inode, struct file *file);
|
|
extern ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to);
|
|
extern ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to);
|
|
extern ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from);
|
|
extern ssize_t cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from);
|
|
extern int cifs_lock(struct file *, int, struct file_lock *);
|
|
extern int cifs_fsync(struct file *, loff_t, loff_t, int);
|
|
extern int cifs_strict_fsync(struct file *, loff_t, loff_t, int);
|
|
extern int cifs_flush(struct file *, fl_owner_t id);
|
|
extern int cifs_file_mmap(struct file * , struct vm_area_struct *);
|
|
extern int cifs_file_strict_mmap(struct file * , struct vm_area_struct *);
|
|
extern const struct file_operations cifs_dir_ops;
|
|
extern int cifs_dir_open(struct inode *inode, struct file *file);
|
|
extern int cifs_readdir(struct file *file, struct dir_context *ctx);
|
|
|
|
/* Functions related to dir entries */
|
|
extern const struct dentry_operations cifs_dentry_ops;
|
|
extern const struct dentry_operations cifs_ci_dentry_ops;
|
|
|
|
#ifdef CONFIG_CIFS_DFS_UPCALL
|
|
extern struct vfsmount *cifs_dfs_d_automount(struct path *path);
|
|
#else
|
|
#define cifs_dfs_d_automount NULL
|
|
#endif
|
|
|
|
/* Functions related to symlinks */
|
|
extern const char *cifs_get_link(struct dentry *, struct inode *,
|
|
struct delayed_call *);
|
|
extern int cifs_symlink(struct inode *inode, struct dentry *direntry,
|
|
const char *symname);
|
|
|
|
#ifdef CONFIG_CIFS_XATTR
|
|
extern const struct xattr_handler *cifs_xattr_handlers[];
|
|
extern ssize_t cifs_listxattr(struct dentry *, char *, size_t);
|
|
#else
|
|
# define cifs_xattr_handlers NULL
|
|
# define cifs_listxattr NULL
|
|
#endif
|
|
|
|
extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
|
|
#ifdef CONFIG_CIFS_NFSD_EXPORT
|
|
extern const struct export_operations cifs_export_ops;
|
|
#endif /* CONFIG_CIFS_NFSD_EXPORT */
|
|
|
|
#define CIFS_VERSION "2.09"
|
|
#endif /* _CIFSFS_H */
|