2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* linux/fs/attr.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
|
|
* changes by Thomas Schoebel-Theuer
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/time.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/string.h>
|
2006-01-12 04:17:46 +08:00
|
|
|
#include <linux/capability.h>
|
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 05:06:03 +08:00
|
|
|
#include <linux/fsnotify.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/fcntl.h>
|
|
|
|
#include <linux/security.h>
|
2011-03-10 03:39:57 +08:00
|
|
|
#include <linux/evm.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-06-04 17:30:04 +08:00
|
|
|
/**
|
|
|
|
* inode_change_ok - check if attribute changes to an inode are allowed
|
|
|
|
* @inode: inode to check
|
|
|
|
* @attr: attributes to change
|
|
|
|
*
|
|
|
|
* Check if we are allowed to change the attributes contained in @attr
|
|
|
|
* in the given inode. This includes the normal unix access permission
|
|
|
|
* checks, as well as checks for rlimits and others.
|
|
|
|
*
|
|
|
|
* Should be called as the first thing in ->setattr implementations,
|
|
|
|
* possibly after taking additional locks.
|
|
|
|
*/
|
2009-08-21 00:35:05 +08:00
|
|
|
int inode_change_ok(const struct inode *inode, struct iattr *attr)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
unsigned int ia_valid = attr->ia_valid;
|
|
|
|
|
2010-06-04 17:30:04 +08:00
|
|
|
/*
|
|
|
|
* First check size constraints. These can't be overriden using
|
|
|
|
* ATTR_FORCE.
|
|
|
|
*/
|
|
|
|
if (ia_valid & ATTR_SIZE) {
|
|
|
|
int error = inode_newsize_ok(inode, attr->ia_size);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* If force is set do it anyway. */
|
|
|
|
if (ia_valid & ATTR_FORCE)
|
2010-06-04 17:30:04 +08:00
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Make sure a caller can chown. */
|
|
|
|
if ((ia_valid & ATTR_UID) &&
|
2008-11-14 07:39:05 +08:00
|
|
|
(current_fsuid() != inode->i_uid ||
|
2005-04-17 06:20:36 +08:00
|
|
|
attr->ia_uid != inode->i_uid) && !capable(CAP_CHOWN))
|
2010-06-04 17:30:04 +08:00
|
|
|
return -EPERM;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Make sure caller can chgrp. */
|
|
|
|
if ((ia_valid & ATTR_GID) &&
|
2008-11-14 07:39:05 +08:00
|
|
|
(current_fsuid() != inode->i_uid ||
|
2005-04-17 06:20:36 +08:00
|
|
|
(!in_group_p(attr->ia_gid) && attr->ia_gid != inode->i_gid)) &&
|
|
|
|
!capable(CAP_CHOWN))
|
2010-06-04 17:30:04 +08:00
|
|
|
return -EPERM;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Make sure a caller can chmod. */
|
|
|
|
if (ia_valid & ATTR_MODE) {
|
2011-03-24 07:43:26 +08:00
|
|
|
if (!inode_owner_or_capable(inode))
|
2010-06-04 17:30:04 +08:00
|
|
|
return -EPERM;
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Also check the setgid bit! */
|
|
|
|
if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
|
|
|
|
inode->i_gid) && !capable(CAP_FSETID))
|
|
|
|
attr->ia_mode &= ~S_ISGID;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Check for setting the inode time. */
|
2008-07-01 21:01:26 +08:00
|
|
|
if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) {
|
2011-03-24 07:43:26 +08:00
|
|
|
if (!inode_owner_or_capable(inode))
|
2010-06-04 17:30:04 +08:00
|
|
|
return -EPERM;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2010-06-04 17:30:04 +08:00
|
|
|
|
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(inode_change_ok);
|
|
|
|
|
2009-08-21 00:35:05 +08:00
|
|
|
/**
|
|
|
|
* inode_newsize_ok - may this inode be truncated to a given size
|
|
|
|
* @inode: the inode to be truncated
|
|
|
|
* @offset: the new size to assign to the inode
|
|
|
|
* @Returns: 0 on success, -ve errno on failure
|
|
|
|
*
|
fs: introduce new truncate sequence
Introduce a new truncate calling sequence into fs/mm subsystems. Rather than
setattr > vmtruncate > truncate, have filesystems call their truncate sequence
from ->setattr if filesystem specific operations are required. vmtruncate is
deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced
previously should be used.
simple_setattr is introduced for simple in-ram filesystems to implement
the new truncate sequence. Eventually all filesystems should be converted
to implement a setattr, and the default code in notify_change should go
away.
simple_setsize is also introduced to perform just the ATTR_SIZE portion
of simple_setattr (ie. changing i_size and trimming pagecache).
To implement the new truncate sequence:
- filesystem specific manipulations (eg freeing blocks) must be done in
the setattr method rather than ->truncate.
- vmtruncate can not be used by core code to trim blocks past i_size in
the event of write failure after allocation, so this must be performed
in the fs code.
- convert usage of helpers block_write_begin, nobh_write_begin,
cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed
variants. These avoid calling vmtruncate to trim blocks (see previous).
- inode_setattr should not be used. generic_setattr is a new function
to be used to copy simple attributes into the generic inode.
- make use of the better opportunity to handle errors with the new sequence.
Big problem with the previous calling sequence: the filesystem is not called
until i_size has already changed. This means it is not allowed to fail the
call, and also it does not know what the previous i_size was. Also, generic
code calling vmtruncate to truncate allocated blocks in case of error had
no good way to return a meaningful error (or, for example, atomically handle
block deallocation).
Cc: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-05-26 23:05:33 +08:00
|
|
|
* inode_newsize_ok must be called with i_mutex held.
|
|
|
|
*
|
2009-08-21 00:35:05 +08:00
|
|
|
* inode_newsize_ok will check filesystem limits and ulimits to check that the
|
|
|
|
* new inode size is within limits. inode_newsize_ok will also send SIGXFSZ
|
|
|
|
* when necessary. Caller must not proceed with inode size change if failure is
|
|
|
|
* returned. @inode must be a file (not directory), with appropriate
|
|
|
|
* permissions to allow truncate (inode_newsize_ok does NOT check these
|
|
|
|
* conditions).
|
|
|
|
*/
|
|
|
|
int inode_newsize_ok(const struct inode *inode, loff_t offset)
|
|
|
|
{
|
|
|
|
if (inode->i_size < offset) {
|
|
|
|
unsigned long limit;
|
|
|
|
|
2010-03-06 05:42:42 +08:00
|
|
|
limit = rlimit(RLIMIT_FSIZE);
|
2009-08-21 00:35:05 +08:00
|
|
|
if (limit != RLIM_INFINITY && offset > limit)
|
|
|
|
goto out_sig;
|
|
|
|
if (offset > inode->i_sb->s_maxbytes)
|
|
|
|
goto out_big;
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* truncation of in-use swapfiles is disallowed - it would
|
|
|
|
* cause subsequent swapout to scribble on the now-freed
|
|
|
|
* blocks.
|
|
|
|
*/
|
|
|
|
if (IS_SWAPFILE(inode))
|
|
|
|
return -ETXTBSY;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
out_sig:
|
|
|
|
send_sig(SIGXFSZ, current, 0);
|
|
|
|
out_big:
|
|
|
|
return -EFBIG;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(inode_newsize_ok);
|
|
|
|
|
fs: introduce new truncate sequence
Introduce a new truncate calling sequence into fs/mm subsystems. Rather than
setattr > vmtruncate > truncate, have filesystems call their truncate sequence
from ->setattr if filesystem specific operations are required. vmtruncate is
deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced
previously should be used.
simple_setattr is introduced for simple in-ram filesystems to implement
the new truncate sequence. Eventually all filesystems should be converted
to implement a setattr, and the default code in notify_change should go
away.
simple_setsize is also introduced to perform just the ATTR_SIZE portion
of simple_setattr (ie. changing i_size and trimming pagecache).
To implement the new truncate sequence:
- filesystem specific manipulations (eg freeing blocks) must be done in
the setattr method rather than ->truncate.
- vmtruncate can not be used by core code to trim blocks past i_size in
the event of write failure after allocation, so this must be performed
in the fs code.
- convert usage of helpers block_write_begin, nobh_write_begin,
cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed
variants. These avoid calling vmtruncate to trim blocks (see previous).
- inode_setattr should not be used. generic_setattr is a new function
to be used to copy simple attributes into the generic inode.
- make use of the better opportunity to handle errors with the new sequence.
Big problem with the previous calling sequence: the filesystem is not called
until i_size has already changed. This means it is not allowed to fail the
call, and also it does not know what the previous i_size was. Also, generic
code calling vmtruncate to truncate allocated blocks in case of error had
no good way to return a meaningful error (or, for example, atomically handle
block deallocation).
Cc: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-05-26 23:05:33 +08:00
|
|
|
/**
|
2010-06-04 17:30:00 +08:00
|
|
|
* setattr_copy - copy simple metadata updates into the generic inode
|
fs: introduce new truncate sequence
Introduce a new truncate calling sequence into fs/mm subsystems. Rather than
setattr > vmtruncate > truncate, have filesystems call their truncate sequence
from ->setattr if filesystem specific operations are required. vmtruncate is
deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced
previously should be used.
simple_setattr is introduced for simple in-ram filesystems to implement
the new truncate sequence. Eventually all filesystems should be converted
to implement a setattr, and the default code in notify_change should go
away.
simple_setsize is also introduced to perform just the ATTR_SIZE portion
of simple_setattr (ie. changing i_size and trimming pagecache).
To implement the new truncate sequence:
- filesystem specific manipulations (eg freeing blocks) must be done in
the setattr method rather than ->truncate.
- vmtruncate can not be used by core code to trim blocks past i_size in
the event of write failure after allocation, so this must be performed
in the fs code.
- convert usage of helpers block_write_begin, nobh_write_begin,
cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed
variants. These avoid calling vmtruncate to trim blocks (see previous).
- inode_setattr should not be used. generic_setattr is a new function
to be used to copy simple attributes into the generic inode.
- make use of the better opportunity to handle errors with the new sequence.
Big problem with the previous calling sequence: the filesystem is not called
until i_size has already changed. This means it is not allowed to fail the
call, and also it does not know what the previous i_size was. Also, generic
code calling vmtruncate to truncate allocated blocks in case of error had
no good way to return a meaningful error (or, for example, atomically handle
block deallocation).
Cc: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-05-26 23:05:33 +08:00
|
|
|
* @inode: the inode to be updated
|
|
|
|
* @attr: the new attributes
|
|
|
|
*
|
2010-06-04 17:30:00 +08:00
|
|
|
* setattr_copy must be called with i_mutex held.
|
fs: introduce new truncate sequence
Introduce a new truncate calling sequence into fs/mm subsystems. Rather than
setattr > vmtruncate > truncate, have filesystems call their truncate sequence
from ->setattr if filesystem specific operations are required. vmtruncate is
deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced
previously should be used.
simple_setattr is introduced for simple in-ram filesystems to implement
the new truncate sequence. Eventually all filesystems should be converted
to implement a setattr, and the default code in notify_change should go
away.
simple_setsize is also introduced to perform just the ATTR_SIZE portion
of simple_setattr (ie. changing i_size and trimming pagecache).
To implement the new truncate sequence:
- filesystem specific manipulations (eg freeing blocks) must be done in
the setattr method rather than ->truncate.
- vmtruncate can not be used by core code to trim blocks past i_size in
the event of write failure after allocation, so this must be performed
in the fs code.
- convert usage of helpers block_write_begin, nobh_write_begin,
cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed
variants. These avoid calling vmtruncate to trim blocks (see previous).
- inode_setattr should not be used. generic_setattr is a new function
to be used to copy simple attributes into the generic inode.
- make use of the better opportunity to handle errors with the new sequence.
Big problem with the previous calling sequence: the filesystem is not called
until i_size has already changed. This means it is not allowed to fail the
call, and also it does not know what the previous i_size was. Also, generic
code calling vmtruncate to truncate allocated blocks in case of error had
no good way to return a meaningful error (or, for example, atomically handle
block deallocation).
Cc: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-05-26 23:05:33 +08:00
|
|
|
*
|
2010-06-04 17:30:00 +08:00
|
|
|
* setattr_copy updates the inode's metadata with that specified
|
2011-03-31 09:57:33 +08:00
|
|
|
* in attr. Noticeably missing is inode size update, which is more complex
|
2010-06-04 17:30:04 +08:00
|
|
|
* as it requires pagecache updates.
|
fs: introduce new truncate sequence
Introduce a new truncate calling sequence into fs/mm subsystems. Rather than
setattr > vmtruncate > truncate, have filesystems call their truncate sequence
from ->setattr if filesystem specific operations are required. vmtruncate is
deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced
previously should be used.
simple_setattr is introduced for simple in-ram filesystems to implement
the new truncate sequence. Eventually all filesystems should be converted
to implement a setattr, and the default code in notify_change should go
away.
simple_setsize is also introduced to perform just the ATTR_SIZE portion
of simple_setattr (ie. changing i_size and trimming pagecache).
To implement the new truncate sequence:
- filesystem specific manipulations (eg freeing blocks) must be done in
the setattr method rather than ->truncate.
- vmtruncate can not be used by core code to trim blocks past i_size in
the event of write failure after allocation, so this must be performed
in the fs code.
- convert usage of helpers block_write_begin, nobh_write_begin,
cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed
variants. These avoid calling vmtruncate to trim blocks (see previous).
- inode_setattr should not be used. generic_setattr is a new function
to be used to copy simple attributes into the generic inode.
- make use of the better opportunity to handle errors with the new sequence.
Big problem with the previous calling sequence: the filesystem is not called
until i_size has already changed. This means it is not allowed to fail the
call, and also it does not know what the previous i_size was. Also, generic
code calling vmtruncate to truncate allocated blocks in case of error had
no good way to return a meaningful error (or, for example, atomically handle
block deallocation).
Cc: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-05-26 23:05:33 +08:00
|
|
|
*
|
|
|
|
* The inode is not marked as dirty after this operation. The rationale is
|
|
|
|
* that for "simple" filesystems, the struct inode is the inode storage.
|
|
|
|
* The caller is free to mark the inode dirty afterwards if needed.
|
|
|
|
*/
|
2010-06-04 17:30:00 +08:00
|
|
|
void setattr_copy(struct inode *inode, const struct iattr *attr)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
unsigned int ia_valid = attr->ia_valid;
|
2006-01-08 17:02:39 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (ia_valid & ATTR_UID)
|
|
|
|
inode->i_uid = attr->ia_uid;
|
|
|
|
if (ia_valid & ATTR_GID)
|
|
|
|
inode->i_gid = attr->ia_gid;
|
|
|
|
if (ia_valid & ATTR_ATIME)
|
|
|
|
inode->i_atime = timespec_trunc(attr->ia_atime,
|
|
|
|
inode->i_sb->s_time_gran);
|
|
|
|
if (ia_valid & ATTR_MTIME)
|
|
|
|
inode->i_mtime = timespec_trunc(attr->ia_mtime,
|
|
|
|
inode->i_sb->s_time_gran);
|
|
|
|
if (ia_valid & ATTR_CTIME)
|
|
|
|
inode->i_ctime = timespec_trunc(attr->ia_ctime,
|
|
|
|
inode->i_sb->s_time_gran);
|
|
|
|
if (ia_valid & ATTR_MODE) {
|
|
|
|
umode_t mode = attr->ia_mode;
|
|
|
|
|
|
|
|
if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
|
|
|
|
mode &= ~S_ISGID;
|
|
|
|
inode->i_mode = mode;
|
|
|
|
}
|
fs: introduce new truncate sequence
Introduce a new truncate calling sequence into fs/mm subsystems. Rather than
setattr > vmtruncate > truncate, have filesystems call their truncate sequence
from ->setattr if filesystem specific operations are required. vmtruncate is
deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced
previously should be used.
simple_setattr is introduced for simple in-ram filesystems to implement
the new truncate sequence. Eventually all filesystems should be converted
to implement a setattr, and the default code in notify_change should go
away.
simple_setsize is also introduced to perform just the ATTR_SIZE portion
of simple_setattr (ie. changing i_size and trimming pagecache).
To implement the new truncate sequence:
- filesystem specific manipulations (eg freeing blocks) must be done in
the setattr method rather than ->truncate.
- vmtruncate can not be used by core code to trim blocks past i_size in
the event of write failure after allocation, so this must be performed
in the fs code.
- convert usage of helpers block_write_begin, nobh_write_begin,
cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed
variants. These avoid calling vmtruncate to trim blocks (see previous).
- inode_setattr should not be used. generic_setattr is a new function
to be used to copy simple attributes into the generic inode.
- make use of the better opportunity to handle errors with the new sequence.
Big problem with the previous calling sequence: the filesystem is not called
until i_size has already changed. This means it is not allowed to fail the
call, and also it does not know what the previous i_size was. Also, generic
code calling vmtruncate to truncate allocated blocks in case of error had
no good way to return a meaningful error (or, for example, atomically handle
block deallocation).
Cc: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-05-26 23:05:33 +08:00
|
|
|
}
|
2010-06-04 17:30:00 +08:00
|
|
|
EXPORT_SYMBOL(setattr_copy);
|
fs: introduce new truncate sequence
Introduce a new truncate calling sequence into fs/mm subsystems. Rather than
setattr > vmtruncate > truncate, have filesystems call their truncate sequence
from ->setattr if filesystem specific operations are required. vmtruncate is
deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced
previously should be used.
simple_setattr is introduced for simple in-ram filesystems to implement
the new truncate sequence. Eventually all filesystems should be converted
to implement a setattr, and the default code in notify_change should go
away.
simple_setsize is also introduced to perform just the ATTR_SIZE portion
of simple_setattr (ie. changing i_size and trimming pagecache).
To implement the new truncate sequence:
- filesystem specific manipulations (eg freeing blocks) must be done in
the setattr method rather than ->truncate.
- vmtruncate can not be used by core code to trim blocks past i_size in
the event of write failure after allocation, so this must be performed
in the fs code.
- convert usage of helpers block_write_begin, nobh_write_begin,
cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed
variants. These avoid calling vmtruncate to trim blocks (see previous).
- inode_setattr should not be used. generic_setattr is a new function
to be used to copy simple attributes into the generic inode.
- make use of the better opportunity to handle errors with the new sequence.
Big problem with the previous calling sequence: the filesystem is not called
until i_size has already changed. This means it is not allowed to fail the
call, and also it does not know what the previous i_size was. Also, generic
code calling vmtruncate to truncate allocated blocks in case of error had
no good way to return a meaningful error (or, for example, atomically handle
block deallocation).
Cc: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-05-26 23:05:33 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
int notify_change(struct dentry * dentry, struct iattr * attr)
|
|
|
|
{
|
|
|
|
struct inode *inode = dentry->d_inode;
|
VFS: make notify_change pass ATTR_KILL_S*ID to setattr operations
When an unprivileged process attempts to modify a file that has the setuid or
setgid bits set, the VFS will attempt to clear these bits. The VFS will set
the ATTR_KILL_SUID or ATTR_KILL_SGID bits in the ia_valid mask, and then call
notify_change to clear these bits and set the mode accordingly.
With a networked filesystem (NFS and CIFS in particular but likely others),
the client machine or process may not have credentials that allow for setting
the mode. In some situations, this can lead to file corruption, an operation
failing outright because the setattr fails, or to races that lead to a mode
change being reverted.
In this situation, we'd like to just leave the handling of this to the server
and ignore these bits. The problem is that by the time the setattr op is
called, the VFS has already reinterpreted the ATTR_KILL_* bits into a mode
change. The setattr operation has no way to know its intent.
The following patch fixes this by making notify_change no longer clear the
ATTR_KILL_SUID and ATTR_KILL_SGID bits in the ia_valid before handing it off
to the setattr inode op. setattr can then check for the presence of these
bits, and if they're set it can assume that the mode change was only for the
purposes of clearing these bits.
This means that we now have an implicit assumption that notify_change is never
called with ATTR_MODE and either ATTR_KILL_S*ID bit set. Nothing currently
enforces that, so this patch also adds a BUG() if that occurs.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Cc: Michael Halcrow <mhalcrow@us.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Neil Brown <neilb@suse.de>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: "Vladimir V. Saveliev" <vs@namesys.com>
Cc: Josef 'Jeff' Sipek <jsipek@cs.sunysb.edu>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Steven French <sfrench@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-18 18:05:20 +08:00
|
|
|
mode_t mode = inode->i_mode;
|
2005-04-17 06:20:36 +08:00
|
|
|
int error;
|
|
|
|
struct timespec now;
|
|
|
|
unsigned int ia_valid = attr->ia_valid;
|
|
|
|
|
2008-07-01 21:01:29 +08:00
|
|
|
if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
|
|
|
|
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
|
|
|
|
return -EPERM;
|
|
|
|
}
|
|
|
|
|
2011-05-28 23:25:51 +08:00
|
|
|
if ((ia_valid & ATTR_MODE)) {
|
|
|
|
mode_t amode = attr->ia_mode;
|
|
|
|
/* Flag setting protected by i_mutex */
|
|
|
|
if (is_sxid(amode))
|
|
|
|
inode->i_flags &= ~S_NOSEC;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
now = current_fs_time(inode->i_sb);
|
|
|
|
|
|
|
|
attr->ia_ctime = now;
|
|
|
|
if (!(ia_valid & ATTR_ATIME_SET))
|
|
|
|
attr->ia_atime = now;
|
|
|
|
if (!(ia_valid & ATTR_MTIME_SET))
|
|
|
|
attr->ia_mtime = now;
|
Implement file posix capabilities
Implement file posix capabilities. This allows programs to be given a
subset of root's powers regardless of who runs them, without having to use
setuid and giving the binary all of root's powers.
This version works with Kaigai Kohei's userspace tools, found at
http://www.kaigai.gr.jp/index.php. For more information on how to use this
patch, Chris Friedhoff has posted a nice page at
http://www.friedhoff.org/fscaps.html.
Changelog:
Nov 27:
Incorporate fixes from Andrew Morton
(security-introduce-file-caps-tweaks and
security-introduce-file-caps-warning-fix)
Fix Kconfig dependency.
Fix change signaling behavior when file caps are not compiled in.
Nov 13:
Integrate comments from Alexey: Remove CONFIG_ ifdef from
capability.h, and use %zd for printing a size_t.
Nov 13:
Fix endianness warnings by sparse as suggested by Alexey
Dobriyan.
Nov 09:
Address warnings of unused variables at cap_bprm_set_security
when file capabilities are disabled, and simultaneously clean
up the code a little, by pulling the new code into a helper
function.
Nov 08:
For pointers to required userspace tools and how to use
them, see http://www.friedhoff.org/fscaps.html.
Nov 07:
Fix the calculation of the highest bit checked in
check_cap_sanity().
Nov 07:
Allow file caps to be enabled without CONFIG_SECURITY, since
capabilities are the default.
Hook cap_task_setscheduler when !CONFIG_SECURITY.
Move capable(TASK_KILL) to end of cap_task_kill to reduce
audit messages.
Nov 05:
Add secondary calls in selinux/hooks.c to task_setioprio and
task_setscheduler so that selinux and capabilities with file
cap support can be stacked.
Sep 05:
As Seth Arnold points out, uid checks are out of place
for capability code.
Sep 01:
Define task_setscheduler, task_setioprio, cap_task_kill, and
task_setnice to make sure a user cannot affect a process in which
they called a program with some fscaps.
One remaining question is the note under task_setscheduler: are we
ok with CAP_SYS_NICE being sufficient to confine a process to a
cpuset?
It is a semantic change, as without fsccaps, attach_task doesn't
allow CAP_SYS_NICE to override the uid equivalence check. But since
it uses security_task_setscheduler, which elsewhere is used where
CAP_SYS_NICE can be used to override the uid equivalence check,
fixing it might be tough.
task_setscheduler
note: this also controls cpuset:attach_task. Are we ok with
CAP_SYS_NICE being used to confine to a cpuset?
task_setioprio
task_setnice
sys_setpriority uses this (through set_one_prio) for another
process. Need same checks as setrlimit
Aug 21:
Updated secureexec implementation to reflect the fact that
euid and uid might be the same and nonzero, but the process
might still have elevated caps.
Aug 15:
Handle endianness of xattrs.
Enforce capability version match between kernel and disk.
Enforce that no bits beyond the known max capability are
set, else return -EPERM.
With this extra processing, it may be worth reconsidering
doing all the work at bprm_set_security rather than
d_instantiate.
Aug 10:
Always call getxattr at bprm_set_security, rather than
caching it at d_instantiate.
[morgan@kernel.org: file-caps clean up for linux/capability.h]
[bunk@kernel.org: unexport cap_inode_killpriv]
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Cc: James Morris <jmorris@namei.org>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Andrew Morgan <morgan@kernel.org>
Signed-off-by: Andrew Morgan <morgan@kernel.org>
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:31:36 +08:00
|
|
|
if (ia_valid & ATTR_KILL_PRIV) {
|
|
|
|
attr->ia_valid &= ~ATTR_KILL_PRIV;
|
|
|
|
ia_valid &= ~ATTR_KILL_PRIV;
|
|
|
|
error = security_inode_need_killpriv(dentry);
|
|
|
|
if (error > 0)
|
|
|
|
error = security_inode_killpriv(dentry);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
}
|
VFS: make notify_change pass ATTR_KILL_S*ID to setattr operations
When an unprivileged process attempts to modify a file that has the setuid or
setgid bits set, the VFS will attempt to clear these bits. The VFS will set
the ATTR_KILL_SUID or ATTR_KILL_SGID bits in the ia_valid mask, and then call
notify_change to clear these bits and set the mode accordingly.
With a networked filesystem (NFS and CIFS in particular but likely others),
the client machine or process may not have credentials that allow for setting
the mode. In some situations, this can lead to file corruption, an operation
failing outright because the setattr fails, or to races that lead to a mode
change being reverted.
In this situation, we'd like to just leave the handling of this to the server
and ignore these bits. The problem is that by the time the setattr op is
called, the VFS has already reinterpreted the ATTR_KILL_* bits into a mode
change. The setattr operation has no way to know its intent.
The following patch fixes this by making notify_change no longer clear the
ATTR_KILL_SUID and ATTR_KILL_SGID bits in the ia_valid before handing it off
to the setattr inode op. setattr can then check for the presence of these
bits, and if they're set it can assume that the mode change was only for the
purposes of clearing these bits.
This means that we now have an implicit assumption that notify_change is never
called with ATTR_MODE and either ATTR_KILL_S*ID bit set. Nothing currently
enforces that, so this patch also adds a BUG() if that occurs.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Cc: Michael Halcrow <mhalcrow@us.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Neil Brown <neilb@suse.de>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: "Vladimir V. Saveliev" <vs@namesys.com>
Cc: Josef 'Jeff' Sipek <jsipek@cs.sunysb.edu>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Steven French <sfrench@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-18 18:05:20 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We now pass ATTR_KILL_S*ID to the lower level setattr function so
|
|
|
|
* that the function has the ability to reinterpret a mode change
|
|
|
|
* that's due to these bits. This adds an implicit restriction that
|
|
|
|
* no function will ever call notify_change with both ATTR_MODE and
|
|
|
|
* ATTR_KILL_S*ID set.
|
|
|
|
*/
|
|
|
|
if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) &&
|
|
|
|
(ia_valid & ATTR_MODE))
|
|
|
|
BUG();
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (ia_valid & ATTR_KILL_SUID) {
|
|
|
|
if (mode & S_ISUID) {
|
VFS: make notify_change pass ATTR_KILL_S*ID to setattr operations
When an unprivileged process attempts to modify a file that has the setuid or
setgid bits set, the VFS will attempt to clear these bits. The VFS will set
the ATTR_KILL_SUID or ATTR_KILL_SGID bits in the ia_valid mask, and then call
notify_change to clear these bits and set the mode accordingly.
With a networked filesystem (NFS and CIFS in particular but likely others),
the client machine or process may not have credentials that allow for setting
the mode. In some situations, this can lead to file corruption, an operation
failing outright because the setattr fails, or to races that lead to a mode
change being reverted.
In this situation, we'd like to just leave the handling of this to the server
and ignore these bits. The problem is that by the time the setattr op is
called, the VFS has already reinterpreted the ATTR_KILL_* bits into a mode
change. The setattr operation has no way to know its intent.
The following patch fixes this by making notify_change no longer clear the
ATTR_KILL_SUID and ATTR_KILL_SGID bits in the ia_valid before handing it off
to the setattr inode op. setattr can then check for the presence of these
bits, and if they're set it can assume that the mode change was only for the
purposes of clearing these bits.
This means that we now have an implicit assumption that notify_change is never
called with ATTR_MODE and either ATTR_KILL_S*ID bit set. Nothing currently
enforces that, so this patch also adds a BUG() if that occurs.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Cc: Michael Halcrow <mhalcrow@us.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Neil Brown <neilb@suse.de>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: "Vladimir V. Saveliev" <vs@namesys.com>
Cc: Josef 'Jeff' Sipek <jsipek@cs.sunysb.edu>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Steven French <sfrench@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-18 18:05:20 +08:00
|
|
|
ia_valid = attr->ia_valid |= ATTR_MODE;
|
|
|
|
attr->ia_mode = (inode->i_mode & ~S_ISUID);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
if (ia_valid & ATTR_KILL_SGID) {
|
|
|
|
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
|
|
|
|
if (!(ia_valid & ATTR_MODE)) {
|
|
|
|
ia_valid = attr->ia_valid |= ATTR_MODE;
|
|
|
|
attr->ia_mode = inode->i_mode;
|
|
|
|
}
|
|
|
|
attr->ia_mode &= ~S_ISGID;
|
|
|
|
}
|
|
|
|
}
|
VFS: make notify_change pass ATTR_KILL_S*ID to setattr operations
When an unprivileged process attempts to modify a file that has the setuid or
setgid bits set, the VFS will attempt to clear these bits. The VFS will set
the ATTR_KILL_SUID or ATTR_KILL_SGID bits in the ia_valid mask, and then call
notify_change to clear these bits and set the mode accordingly.
With a networked filesystem (NFS and CIFS in particular but likely others),
the client machine or process may not have credentials that allow for setting
the mode. In some situations, this can lead to file corruption, an operation
failing outright because the setattr fails, or to races that lead to a mode
change being reverted.
In this situation, we'd like to just leave the handling of this to the server
and ignore these bits. The problem is that by the time the setattr op is
called, the VFS has already reinterpreted the ATTR_KILL_* bits into a mode
change. The setattr operation has no way to know its intent.
The following patch fixes this by making notify_change no longer clear the
ATTR_KILL_SUID and ATTR_KILL_SGID bits in the ia_valid before handing it off
to the setattr inode op. setattr can then check for the presence of these
bits, and if they're set it can assume that the mode change was only for the
purposes of clearing these bits.
This means that we now have an implicit assumption that notify_change is never
called with ATTR_MODE and either ATTR_KILL_S*ID bit set. Nothing currently
enforces that, so this patch also adds a BUG() if that occurs.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Cc: Michael Halcrow <mhalcrow@us.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Neil Brown <neilb@suse.de>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: "Vladimir V. Saveliev" <vs@namesys.com>
Cc: Josef 'Jeff' Sipek <jsipek@cs.sunysb.edu>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Steven French <sfrench@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-18 18:05:20 +08:00
|
|
|
if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID)))
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
|
2008-07-30 20:06:22 +08:00
|
|
|
error = security_inode_setattr(dentry, attr);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
2010-06-04 17:30:01 +08:00
|
|
|
if (inode->i_op->setattr)
|
2008-07-30 20:06:22 +08:00
|
|
|
error = inode->i_op->setattr(dentry, attr);
|
2010-06-04 17:30:01 +08:00
|
|
|
else
|
|
|
|
error = simple_setattr(dentry, attr);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-03-10 03:39:57 +08:00
|
|
|
if (!error) {
|
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 05:06:03 +08:00
|
|
|
fsnotify_change(dentry, ia_valid);
|
2011-03-10 03:39:57 +08:00
|
|
|
evm_inode_post_setattr(dentry, ia_valid);
|
|
|
|
}
|
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 05:06:03 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(notify_change);
|