linux/fs/kernfs/inode.c

447 lines
11 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/kernfs/inode.c - kernfs inode implementation
*
* Copyright (c) 2001-3 Patrick Mochel
* Copyright (c) 2007 SUSE Linux Products GmbH
* Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
*/
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include "kernfs-internal.h"
static const struct inode_operations kernfs_iops = {
.permission = kernfs_iop_permission,
.setattr = kernfs_iop_setattr,
.getattr = kernfs_iop_getattr,
.listxattr = kernfs_iop_listxattr,
};
static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, int alloc)
{
static DEFINE_MUTEX(iattr_mutex);
struct kernfs_iattrs *ret;
mutex_lock(&iattr_mutex);
if (kn->iattr || !alloc)
goto out_unlock;
kn->iattr = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL);
if (!kn->iattr)
goto out_unlock;
/* assign default attributes */
kn->iattr->ia_uid = GLOBAL_ROOT_UID;
kn->iattr->ia_gid = GLOBAL_ROOT_GID;
ktime_get_real_ts64(&kn->iattr->ia_atime);
kn->iattr->ia_mtime = kn->iattr->ia_atime;
kn->iattr->ia_ctime = kn->iattr->ia_atime;
simple_xattrs_init(&kn->iattr->xattrs);
atomic_set(&kn->iattr->nr_user_xattrs, 0);
atomic_set(&kn->iattr->user_xattr_size, 0);
out_unlock:
ret = kn->iattr;
mutex_unlock(&iattr_mutex);
return ret;
}
static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
{
return __kernfs_iattrs(kn, 1);
}
static struct kernfs_iattrs *kernfs_iattrs_noalloc(struct kernfs_node *kn)
{
return __kernfs_iattrs(kn, 0);
}
int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
{
struct kernfs_iattrs *attrs;
unsigned int ia_valid = iattr->ia_valid;
attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
if (ia_valid & ATTR_UID)
attrs->ia_uid = iattr->ia_uid;
if (ia_valid & ATTR_GID)
attrs->ia_gid = iattr->ia_gid;
if (ia_valid & ATTR_ATIME)
attrs->ia_atime = iattr->ia_atime;
if (ia_valid & ATTR_MTIME)
attrs->ia_mtime = iattr->ia_mtime;
if (ia_valid & ATTR_CTIME)
attrs->ia_ctime = iattr->ia_ctime;
if (ia_valid & ATTR_MODE)
kn->mode = iattr->ia_mode;
return 0;
}
/**
* kernfs_setattr - set iattr on a node
* @kn: target node
* @iattr: iattr to set
*
* Returns 0 on success, -errno on failure.
*/
int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
{
int ret;
struct kernfs_root *root = kernfs_root(kn);
down_write(&root->kernfs_rwsem);
ret = __kernfs_setattr(kn, iattr);
up_write(&root->kernfs_rwsem);
return ret;
}
int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
struct kernfs_node *kn = inode->i_private;
struct kernfs_root *root;
int error;
if (!kn)
return -EINVAL;
root = kernfs_root(kn);
down_write(&root->kernfs_rwsem);
error = setattr_prepare(&init_user_ns, dentry, iattr);
if (error)
goto out;
error = __kernfs_setattr(kn, iattr);
if (error)
goto out;
/* this ignores size changes */
setattr_copy(&init_user_ns, inode, iattr);
out:
up_write(&root->kernfs_rwsem);
return error;
}
ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
{
struct kernfs_node *kn = kernfs_dentry_node(dentry);
struct kernfs_iattrs *attrs;
attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size);
}
static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
{
inode->i_mode = mode;
inode->i_atime = inode->i_mtime =
inode->i_ctime = current_time(inode);
}
static inline void set_inode_attr(struct inode *inode,
struct kernfs_iattrs *attrs)
{
inode->i_uid = attrs->ia_uid;
inode->i_gid = attrs->ia_gid;
inode->i_atime = attrs->ia_atime;
inode->i_mtime = attrs->ia_mtime;
inode->i_ctime = attrs->ia_ctime;
}
static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
{
struct kernfs_iattrs *attrs = kn->iattr;
inode->i_mode = kn->mode;
if (attrs)
/*
* kernfs_node has non-default attributes get them from
* persistent copy in kernfs_node.
*/
set_inode_attr(inode, attrs);
if (kernfs_type(kn) == KERNFS_DIR)
set_nlink(inode, kn->dir.subdirs + 2);
}
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>
2017-02-01 00:46:22 +08:00
u32 request_mask, unsigned int query_flags)
{
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>
2017-02-01 00:46:22 +08:00
struct inode *inode = d_inode(path->dentry);
struct kernfs_node *kn = inode->i_private;
struct kernfs_root *root = kernfs_root(kn);
down_read(&root->kernfs_rwsem);
spin_lock(&inode->i_lock);
kernfs_refresh_inode(kn, inode);
generic_fillattr(&init_user_ns, inode, stat);
spin_unlock(&inode->i_lock);
up_read(&root->kernfs_rwsem);
return 0;
}
static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
{
kernfs_get(kn);
inode->i_private = kn;
inode->i_mapping->a_ops = &ram_aops;
inode->i_op = &kernfs_iops;
inode->i_generation = kernfs_gen(kn);
set_default_inode_attr(inode, kn->mode);
kernfs_refresh_inode(kn, inode);
/* initialize inode according to type */
switch (kernfs_type(kn)) {
case KERNFS_DIR:
inode->i_op = &kernfs_dir_iops;
inode->i_fop = &kernfs_dir_fops;
if (kn->flags & KERNFS_EMPTY_DIR)
make_empty_dir_inode(inode);
break;
case KERNFS_FILE:
inode->i_size = kn->attr.size;
inode->i_fop = &kernfs_file_fops;
break;
case KERNFS_LINK:
inode->i_op = &kernfs_symlink_iops;
break;
default:
BUG();
}
unlock_new_inode(inode);
}
/**
* kernfs_get_inode - get inode for kernfs_node
* @sb: super block
* @kn: kernfs_node to allocate inode for
*
* Get inode for @kn. If such inode doesn't exist, a new inode is
* allocated and basics are initialized. New inode is returned
* locked.
*
* LOCKING:
* Kernel thread context (may sleep).
*
* RETURNS:
* Pointer to allocated inode on success, NULL on failure.
*/
struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
{
struct inode *inode;
inode = iget_locked(sb, kernfs_ino(kn));
if (inode && (inode->i_state & I_NEW))
kernfs_init_inode(kn, inode);
return inode;
}
/*
* The kernfs_node serves as both an inode and a directory entry for
* kernfs. To prevent the kernfs inode numbers from being freed
* prematurely we take a reference to kernfs_node from the kernfs inode. A
* super_operations.evict_inode() implementation is needed to drop that
* reference upon inode destruction.
*/
void kernfs_evict_inode(struct inode *inode)
{
struct kernfs_node *kn = inode->i_private;
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-04 05:47:49 +08:00
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
kernfs_put(kn);
}
int kernfs_iop_permission(struct user_namespace *mnt_userns,
struct inode *inode, int mask)
{
struct kernfs_node *kn;
struct kernfs_root *root;
int ret;
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
kn = inode->i_private;
root = kernfs_root(kn);
down_read(&root->kernfs_rwsem);
spin_lock(&inode->i_lock);
kernfs_refresh_inode(kn, inode);
ret = generic_permission(&init_user_ns, inode, mask);
spin_unlock(&inode->i_lock);
up_read(&root->kernfs_rwsem);
return ret;
}
int kernfs_xattr_get(struct kernfs_node *kn, const char *name,
void *value, size_t size)
{
struct kernfs_iattrs *attrs = kernfs_iattrs_noalloc(kn);
if (!attrs)
return -ENODATA;
return simple_xattr_get(&attrs->xattrs, name, value, size);
}
int kernfs_xattr_set(struct kernfs_node *kn, const char *name,
const void *value, size_t size, int flags)
{
struct kernfs_iattrs *attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
return simple_xattr_set(&attrs->xattrs, name, value, size, flags, NULL);
}
static int kernfs_vfs_xattr_get(const struct xattr_handler *handler,
struct dentry *unused, struct inode *inode,
const char *suffix, void *value, size_t size)
{
const char *name = xattr_full_name(handler, suffix);
struct kernfs_node *kn = inode->i_private;
return kernfs_xattr_get(kn, name, value, size);
}
static int kernfs_vfs_xattr_set(const struct xattr_handler *handler,
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *suffix, const void *value,
size_t size, int flags)
{
const char *name = xattr_full_name(handler, suffix);
struct kernfs_node *kn = inode->i_private;
return kernfs_xattr_set(kn, name, value, size, flags);
}
static int kernfs_vfs_user_xattr_add(struct kernfs_node *kn,
const char *full_name,
struct simple_xattrs *xattrs,
const void *value, size_t size, int flags)
{
atomic_t *sz = &kn->iattr->user_xattr_size;
atomic_t *nr = &kn->iattr->nr_user_xattrs;
ssize_t removed_size;
int ret;
if (atomic_inc_return(nr) > KERNFS_MAX_USER_XATTRS) {
ret = -ENOSPC;
goto dec_count_out;
}
if (atomic_add_return(size, sz) > KERNFS_USER_XATTR_SIZE_LIMIT) {
ret = -ENOSPC;
goto dec_size_out;
}
ret = simple_xattr_set(xattrs, full_name, value, size, flags,
&removed_size);
if (!ret && removed_size >= 0)
size = removed_size;
else if (!ret)
return 0;
dec_size_out:
atomic_sub(size, sz);
dec_count_out:
atomic_dec(nr);
return ret;
}
static int kernfs_vfs_user_xattr_rm(struct kernfs_node *kn,
const char *full_name,
struct simple_xattrs *xattrs,
const void *value, size_t size, int flags)
{
atomic_t *sz = &kn->iattr->user_xattr_size;
atomic_t *nr = &kn->iattr->nr_user_xattrs;
ssize_t removed_size;
int ret;
ret = simple_xattr_set(xattrs, full_name, value, size, flags,
&removed_size);
if (removed_size >= 0) {
atomic_sub(removed_size, sz);
atomic_dec(nr);
}
return ret;
}
static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler,
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *suffix, const void *value,
size_t size, int flags)
{
const char *full_name = xattr_full_name(handler, suffix);
struct kernfs_node *kn = inode->i_private;
struct kernfs_iattrs *attrs;
if (!(kernfs_root(kn)->flags & KERNFS_ROOT_SUPPORT_USER_XATTR))
return -EOPNOTSUPP;
attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
if (value)
return kernfs_vfs_user_xattr_add(kn, full_name, &attrs->xattrs,
value, size, flags);
else
return kernfs_vfs_user_xattr_rm(kn, full_name, &attrs->xattrs,
value, size, flags);
}
static const struct xattr_handler kernfs_trusted_xattr_handler = {
.prefix = XATTR_TRUSTED_PREFIX,
.get = kernfs_vfs_xattr_get,
.set = kernfs_vfs_xattr_set,
};
static const struct xattr_handler kernfs_security_xattr_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.get = kernfs_vfs_xattr_get,
.set = kernfs_vfs_xattr_set,
};
static const struct xattr_handler kernfs_user_xattr_handler = {
.prefix = XATTR_USER_PREFIX,
.get = kernfs_vfs_xattr_get,
.set = kernfs_vfs_user_xattr_set,
};
const struct xattr_handler *kernfs_xattr_handlers[] = {
&kernfs_trusted_xattr_handler,
&kernfs_security_xattr_handler,
&kernfs_user_xattr_handler,
NULL
};