Revision b645af2d5905c4e32399005b867987919cbfc3ae authored by Andy Lutomirski on 23 November 2014, 02:00:33 UTC, committed by Linus Torvalds on 23 November 2014, 21:56:19 UTC
It's possible for iretq to userspace to fail.  This can happen because
of a bad CS, SS, or RIP.

Historically, we've handled it by fixing up an exception from iretq to
land at bad_iret, which pretends that the failed iret frame was really
the hardware part of #GP(0) from userspace.  To make this work, there's
an extra fixup to fudge the gs base into a usable state.

This is suboptimal because it loses the original exception.  It's also
buggy because there's no guarantee that we were on the kernel stack to
begin with.  For example, if the failing iret happened on return from an
NMI, then we'll end up executing general_protection on the NMI stack.
This is bad for several reasons, the most immediate of which is that
general_protection, as a non-paranoid idtentry, will try to deliver
signals and/or schedule from the wrong stack.

This patch throws out bad_iret entirely.  As a replacement, it augments
the existing swapgs fudge into a full-blown iret fixup, mostly written
in C.  It's should be clearer and more correct.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 6f442be
Raw File
attr.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(!mutex_is_locked(&inode->i_mutex));

	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;

	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);
back to top