OpenCloudOS-Kernel/fs/attr.c

298 lines
8.5 KiB
C
Raw Normal View History

/*
* linux/fs/attr.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
* changes by Thomas Schoebel-Theuer
*/
#include <linux/export.h>
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/capability.h>
#include <linux/fsnotify.h>
#include <linux/fcntl.h>
#include <linux/security.h>
#include <linux/evm.h>
#include <linux/ima.h>
/**
* 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.
*/
int inode_change_ok(const struct inode *inode, struct iattr *attr)
{
unsigned int ia_valid = attr->ia_valid;
/*
* 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;
}
/* If force is set do it anyway. */
if (ia_valid & ATTR_FORCE)
return 0;
/* Make sure a caller can chown. */
if ((ia_valid & ATTR_UID) &&
(!uid_eq(current_fsuid(), inode->i_uid) ||
!uid_eq(attr->ia_uid, inode->i_uid)) &&
!capable_wrt_inode_uidgid(inode, CAP_CHOWN))
return -EPERM;
/* Make sure caller can chgrp. */
if ((ia_valid & ATTR_GID) &&
(!uid_eq(current_fsuid(), inode->i_uid) ||
(!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) &&
!capable_wrt_inode_uidgid(inode, CAP_CHOWN))
return -EPERM;
/* Make sure a caller can chmod. */
if (ia_valid & ATTR_MODE) {
if (!inode_owner_or_capable(inode))
return -EPERM;
/* Also check the setgid bit! */
if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
inode->i_gid) &&
!capable_wrt_inode_uidgid(inode, CAP_FSETID))
attr->ia_mode &= ~S_ISGID;
}
/* Check for setting the inode time. */
if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) {
if (!inode_owner_or_capable(inode))
return -EPERM;
}
return 0;
}
EXPORT_SYMBOL(inode_change_ok);
/**
* 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.
*
* 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;
limit = rlimit(RLIMIT_FSIZE);
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
/**
* 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
*
* 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
*
* setattr_copy updates the inode's metadata with that specified
* in attr. Noticeably missing is inode size update, which is more complex
* 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.
*/
void setattr_copy(struct inode *inode, const struct iattr *attr)
{
unsigned int ia_valid = attr->ia_valid;
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_wrt_inode_uidgid(inode, 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
}
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
/**
* notify_change - modify attributes of a filesytem object
* @dentry: object affected
* @iattr: new attributes
* @delegated_inode: returns inode, if the inode is delegated
*
* The caller must hold the i_mutex on the affected object.
*
* If notify_change discovers a delegation in need of breaking,
* it will return -EWOULDBLOCK and return a reference to the inode in
* delegated_inode. The caller should then break the delegation and
* retry. Because breaking a delegation may take a long time, the
* caller should drop the i_mutex before doing so.
*
* Alternatively, a caller may pass NULL for delegated_inode. This may
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported. Also, passing NULL is fine for callers holding
* the file open for write, as there can be no conflicting delegation in
* that case.
*/
int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
umode_t mode = inode->i_mode;
int error;
struct timespec now;
unsigned int ia_valid = attr->ia_valid;
WARN_ON_ONCE(!inode_is_locked(inode));
if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
}
Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-28 23:25:51 +08:00
if ((ia_valid & ATTR_MODE)) {
umode_t amode = attr->ia_mode;
Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-28 23:25:51 +08:00
/* Flag setting protected by i_mutex */
if (is_sxid(amode))
inode->i_flags &= ~S_NOSEC;
}
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();
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);
}
}
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)))
return 0;
/*
* Verify that uid/gid changes are valid in the target
* namespace of the superblock.
*/
if (ia_valid & ATTR_UID &&
!kuid_has_mapping(inode->i_sb->s_user_ns, attr->ia_uid))
return -EOVERFLOW;
if (ia_valid & ATTR_GID &&
!kgid_has_mapping(inode->i_sb->s_user_ns, attr->ia_gid))
return -EOVERFLOW;
vfs: Don't modify inodes with a uid or gid unknown to the vfs When a filesystem outside of init_user_ns is mounted it could have uids and gids stored in it that do not map to init_user_ns. The plan is to allow those filesystems to set i_uid to INVALID_UID and i_gid to INVALID_GID for unmapped uids and gids and then to handle that strange case in the vfs to ensure there is consistent robust handling of the weirdness. Upon a careful review of the vfs and filesystems about the only case where there is any possibility of confusion or trouble is when the inode is written back to disk. In that case filesystems typically read the inode->i_uid and inode->i_gid and write them to disk even when just an inode timestamp is being updated. Which leads to a rule that is very simple to implement and understand inodes whose i_uid or i_gid is not valid may not be written. In dealing with access times this means treat those inodes as if the inode flag S_NOATIME was set. Reads of the inodes appear safe and useful, but any write or modification is disallowed. The only inode write that is allowed is a chown that sets the uid and gid on the inode to valid values. After such a chown the inode is normal and may be treated as such. Denying all writes to inodes with uids or gids unknown to the vfs also prevents several oddball cases where corruption would have occurred because the vfs does not have complete information. One problem case that is prevented is attempting to use the gid of a directory for new inodes where the directories sgid bit is set but the directories gid is not mapped. Another problem case avoided is attempting to update the evm hash after setxattr, removexattr, and setattr. As the evm hash includeds the inode->i_uid or inode->i_gid not knowning the uid or gid prevents a correct evm hash from being computed. evm hash verification also fails when i_uid or i_gid is unknown but that is essentially harmless as it does not cause filesystem corruption. Acked-by: Seth Forshee <seth.forshee@canonical.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2016-06-30 03:54:46 +08:00
/* Don't allow modifications of files with invalid uids or
* gids unless those uids & gids are being made valid.
*/
if (!(ia_valid & ATTR_UID) && !uid_valid(inode->i_uid))
return -EOVERFLOW;
if (!(ia_valid & ATTR_GID) && !gid_valid(inode->i_gid))
return -EOVERFLOW;
error = security_inode_setattr(dentry, attr);
if (error)
return error;
error = try_break_deleg(inode, delegated_inode);
if (error)
return error;
if (inode->i_op->setattr)
error = inode->i_op->setattr(dentry, attr);
else
error = simple_setattr(dentry, attr);
if (!error) {
fsnotify_change(dentry, ia_valid);
ima_inode_post_setattr(dentry);
evm_inode_post_setattr(dentry, ia_valid);
}
return error;
}
EXPORT_SYMBOL(notify_change);