mirror of
https://github.com/torvalds/linux.git
synced 2024-12-04 18:13:04 +00:00
0bd23d09b8
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>
298 lines
8.5 KiB
C
298 lines
8.5 KiB
C
/*
|
|
* 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
|
|
*
|
|
* 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);
|
|
|
|
/**
|
|
* setattr_copy - copy simple metadata updates into the generic inode
|
|
* @inode: the inode to be updated
|
|
* @attr: the new attributes
|
|
*
|
|
* setattr_copy must be called with i_mutex held.
|
|
*
|
|
* 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.
|
|
*
|
|
* 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;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(setattr_copy);
|
|
|
|
/**
|
|
* 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;
|
|
}
|
|
|
|
if ((ia_valid & ATTR_MODE)) {
|
|
umode_t amode = attr->ia_mode;
|
|
/* 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;
|
|
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;
|
|
}
|
|
|
|
/*
|
|
* 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) {
|
|
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;
|
|
}
|
|
}
|
|
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;
|
|
|
|
/* 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);
|