OpenCloudOS-Kernel/fs/attr.c

235 lines
6.0 KiB
C
Raw Normal View History

/*
* 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>
#include <linux/capability.h>
#include <linux/fsnotify.h>
#include <linux/fcntl.h>
#include <linux/quotaops.h>
#include <linux/security.h>
/* Taken over from the old code... */
/* POSIX UID/GID verification for setting inode attributes. */
int inode_change_ok(const struct inode *inode, struct iattr *attr)
{
int retval = -EPERM;
unsigned int ia_valid = attr->ia_valid;
/* If force is set do it anyway. */
if (ia_valid & ATTR_FORCE)
goto fine;
/* Make sure a caller can chown. */
if ((ia_valid & ATTR_UID) &&
(current_fsuid() != inode->i_uid ||
attr->ia_uid != inode->i_uid) && !capable(CAP_CHOWN))
goto error;
/* Make sure caller can chgrp. */
if ((ia_valid & ATTR_GID) &&
(current_fsuid() != inode->i_uid ||
(!in_group_p(attr->ia_gid) && attr->ia_gid != inode->i_gid)) &&
!capable(CAP_CHOWN))
goto error;
/* Make sure a caller can chmod. */
if (ia_valid & ATTR_MODE) {
if (!is_owner_or_cap(inode))
goto error;
/* 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. */
if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) {
if (!is_owner_or_cap(inode))
goto error;
}
fine:
retval = 0;
error:
return retval;
}
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 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).
*
* inode_newsize_ok must be called with i_mutex held.
*/
int inode_newsize_ok(const struct inode *inode, loff_t offset)
{
if (inode->i_size < offset) {
unsigned long limit;
limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
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);
int inode_setattr(struct inode * inode, struct iattr * attr)
{
unsigned int ia_valid = attr->ia_valid;
if (ia_valid & ATTR_SIZE &&
attr->ia_size != i_size_read(inode)) {
int error = vmtruncate(inode, attr->ia_size);
if (error)
return error;
}
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;
}
mark_inode_dirty(inode);
return 0;
}
EXPORT_SYMBOL(inode_setattr);
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;
int error;
struct timespec now;
unsigned int ia_valid = attr->ia_valid;
if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
}
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;
error = security_inode_setattr(dentry, attr);
if (error)
return error;
if (ia_valid & ATTR_SIZE)
down_write(&dentry->d_inode->i_alloc_sem);
if (inode->i_op && inode->i_op->setattr) {
error = inode->i_op->setattr(dentry, attr);
} else {
error = inode_change_ok(inode, attr);
if (!error) {
if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid))
error = vfs_dq_transfer(inode, attr) ?
-EDQUOT : 0;
if (!error)
error = inode_setattr(inode, attr);
}
}
if (ia_valid & ATTR_SIZE)
up_write(&dentry->d_inode->i_alloc_sem);
if (!error)
fsnotify_change(dentry, ia_valid);
return error;
}
EXPORT_SYMBOL(notify_change);