linux/fs/overlayfs/inode.c

/*
 *
 * Copyright (C) 2011 Novell Inc.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published by
 * the Free Software Foundation.
 */

#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/ratelimit.h>
#include "overlayfs.h"


static dev_t ovl_get_pseudo_dev(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	return oe->lowerstack[0].layer->pseudo_dev;
}

int ovl_setattr(struct dentry *dentry, struct iattr *attr)
{
	int err;
	struct dentry *upperdentry;
	const struct cred *old_cred;

	/*
	 * Check for permissions before trying to copy-up.  This is redundant
	 * since it will be rechecked later by ->setattr() on upper dentry.  But
	 * without this, copy-up can be triggered by just about anybody.
	 *
	 * We don't initialize inode->size, which just means that
	 * inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not
	 * check for a swapfile (which this won't be anyway).
	 */
	err = setattr_prepare(dentry, attr);
	if (err)
		return err;

	err = ovl_want_write(dentry);
	if (err)
		goto out;

	err = ovl_copy_up(dentry);
	if (!err) {
		upperdentry = ovl_dentry_upper(dentry);

		if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
			attr->ia_valid &= ~ATTR_MODE;

		inode_lock(upperdentry->d_inode);
		old_cred = ovl_override_creds(dentry->d_sb);
		err = notify_change(upperdentry, attr, NULL);
		revert_creds(old_cred);
		if (!err)
			ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
		inode_unlock(upperdentry->d_inode);
	}
	ovl_drop_write(dentry);
out:
	return err;
}

int ovl_getattr(const struct path *path, struct kstat *stat,
		u32 request_mask, unsigned int flags)
{
	struct dentry *dentry = path->dentry;
	enum ovl_path_type type;
	struct path realpath;
	const struct cred *old_cred;
	bool is_dir = S_ISDIR(dentry->d_inode->i_mode);
	bool samefs = ovl_same_sb(dentry->d_sb);
	int err;

	type = ovl_path_real(dentry, &realpath);
	old_cred = ovl_override_creds(dentry->d_sb);
	err = vfs_getattr(&realpath, stat, request_mask, flags);
	if (err)
		goto out;

	/*
	 * For non-dir or same fs, we use st_ino of the copy up origin, if we
	 * know it. This guaranties constant st_dev/st_ino across copy up.
	 *
	 * If filesystem supports NFS export ops, this also guaranties
	 * persistent st_ino across mount cycle.
	 */
	if (!is_dir || samefs) {
		if (OVL_TYPE_ORIGIN(type)) {
			struct kstat lowerstat;
			u32 lowermask = STATX_INO | (!is_dir ? STATX_NLINK : 0);

			ovl_path_lower(dentry, &realpath);
			err = vfs_getattr(&realpath, &lowerstat,
					  lowermask, flags);
			if (err)
				goto out;

			/*
			 * Lower hardlinks may be broken on copy up to different
			 * upper files, so we cannot use the lower origin st_ino
			 * for those different files, even for the same fs case.
			 * With inodes index enabled, it is safe to use st_ino
			 * of an indexed hardlinked origin. The index validates
			 * that the upper hardlink is not broken.
			 */
			if (is_dir || lowerstat.nlink == 1 ||
			    ovl_test_flag(OVL_INDEX, d_inode(dentry)))
				stat->ino = lowerstat.ino;

			if (samefs)
				WARN_ON_ONCE(stat->dev != lowerstat.dev);
			else
				stat->dev = ovl_get_pseudo_dev(dentry);
		}
		if (samefs) {
			/*
			 * When all layers are on the same fs, all real inode
			 * number are unique, so we use the overlay st_dev,
			 * which is friendly to du -x.
			 */
			stat->dev = dentry->d_sb->s_dev;
		} else if (!OVL_TYPE_UPPER(type)) {
			/*
			 * For non-samefs setup, to make sure that st_dev/st_ino
			 * pair is unique across the system, we use a unique
			 * anonymous st_dev for lower layer inode.
			 */
			stat->dev = ovl_get_pseudo_dev(dentry);
		}
	} else {
		/*
		 * Always use the overlay st_dev for directories, so 'find
		 * -xdev' will scan the entire overlay mount and won't cross the
		 * overlay mount boundaries.
		 *
		 * If not all layers are on the same fs the pair {real st_ino;
		 * overlay st_dev} is not unique, so use the non persistent
		 * overlay st_ino for directories.
		 */
		stat->dev = dentry->d_sb->s_dev;
		stat->ino = dentry->d_inode->i_ino;
	}

	/*
	 * It's probably not worth it to count subdirs to get the
	 * correct link count.  nlink=1 seems to pacify 'find' and
	 * other utilities.
	 */
	if (is_dir && OVL_TYPE_MERGE(type))
		stat->nlink = 1;

	/*
	 * Return the overlay inode nlinks for indexed upper inodes.
	 * Overlay inode nlink counts the union of the upper hardlinks
	 * and non-covered lower hardlinks. It does not include the upper
	 * index hardlink.
	 */
	if (!is_dir && ovl_test_flag(OVL_INDEX, d_inode(dentry)))
		stat->nlink = dentry->d_inode->i_nlink;

out:
	revert_creds(old_cred);

	return err;
}

int ovl_permission(struct inode *inode, int mask)
{
	struct inode *upperinode = ovl_inode_upper(inode);
	struct inode *realinode = upperinode ?: ovl_inode_lower(inode);
	const struct cred *old_cred;
	int err;

	/* Careful in RCU walk mode */
	if (!realinode) {
		WARN_ON(!(mask & MAY_NOT_BLOCK));
		return -ECHILD;
	}

	/*
	 * Check overlay inode with the creds of task and underlying inode
	 * with creds of mounter
	 */
	err = generic_permission(inode, mask);
	if (err)
		return err;

	old_cred = ovl_override_creds(inode->i_sb);
	if (!upperinode &&
	    !special_file(realinode->i_mode) && mask & MAY_WRITE) {
		mask &= ~(MAY_WRITE | MAY_APPEND);
		/* Make sure mounter can read file for copy up later */
		mask |= MAY_READ;
	}
	err = inode_permission(realinode, mask);
	revert_creds(old_cred);

	return err;
}

static const char *ovl_get_link(struct dentry *dentry,
				struct inode *inode,
				struct delayed_call *done)
{
	const struct cred *old_cred;
	const char *p;

	if (!dentry)
		return ERR_PTR(-ECHILD);

	old_cred = ovl_override_creds(dentry->d_sb);
	p = vfs_get_link(ovl_dentry_real(dentry), done);
	revert_creds(old_cred);
	return p;
}

bool ovl_is_private_xattr(const char *name)
{
	return strncmp(name, OVL_XATTR_PREFIX,
		       sizeof(OVL_XATTR_PREFIX) - 1) == 0;
}

int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
		  const void *value, size_t size, int flags)
{
	int err;
	struct dentry *upperdentry = ovl_i_dentry_upper(inode);
	struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry);
	const struct cred *old_cred;

	err = ovl_want_write(dentry);
	if (err)
		goto out;

	if (!value && !upperdentry) {
		err = vfs_getxattr(realdentry, name, NULL, 0);
		if (err < 0)
			goto out_drop_write;
	}

	if (!upperdentry) {
		err = ovl_copy_up(dentry);
		if (err)
			goto out_drop_write;

		realdentry = ovl_dentry_upper(dentry);
	}

	old_cred = ovl_override_creds(dentry->d_sb);
	if (value)
		err = vfs_setxattr(realdentry, name, value, size, flags);
	else {
		WARN_ON(flags != XATTR_REPLACE);
		err = vfs_removexattr(realdentry, name);
	}
	revert_creds(old_cred);

out_drop_write:
	ovl_drop_write(dentry);
out:
	return err;
}

int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
		  void *value, size_t size)
{
	ssize_t res;
	const struct cred *old_cred;
	struct dentry *realdentry =
		ovl_i_dentry_upper(inode) ?: ovl_dentry_lower(dentry);

	old_cred = ovl_override_creds(dentry->d_sb);
	res = vfs_getxattr(realdentry, name, value, size);
	revert_creds(old_cred);
	return res;
}

static bool ovl_can_list(const char *s)
{
	/* List all non-trusted xatts */
	if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0)
		return true;

	/* Never list trusted.overlay, list other trusted for superuser only */
	return !ovl_is_private_xattr(s) && capable(CAP_SYS_ADMIN);
}

ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
{
	struct dentry *realdentry = ovl_dentry_real(dentry);
	ssize_t res;
	size_t len;
	char *s;
	const struct cred *old_cred;

	old_cred = ovl_override_creds(dentry->d_sb);
	res = vfs_listxattr(realdentry, list, size);
	revert_creds(old_cred);
	if (res <= 0 || size == 0)
		return res;

	/* filter out private xattrs */
	for (s = list, len = res; len;) {
		size_t slen = strnlen(s, len) + 1;

		/* underlying fs providing us with an broken xattr list? */
		if (WARN_ON(slen > len))
			return -EIO;

		len -= slen;
		if (!ovl_can_list(s)) {
			res -= slen;
			memmove(s, s + slen, len);
		} else {
			s += slen;
		}
	}

	return res;
}

struct posix_acl *ovl_get_acl(struct inode *inode, int type)
{
	struct inode *realinode = ovl_inode_real(inode);
	const struct cred *old_cred;
	struct posix_acl *acl;

	if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
		return NULL;

	old_cred = ovl_override_creds(inode->i_sb);
	acl = get_acl(realinode, type);
	revert_creds(old_cred);

	return acl;
}

static bool ovl_open_need_copy_up(struct dentry *dentry, int flags)
{
	if (ovl_dentry_upper(dentry) &&
	    ovl_dentry_has_upper_alias(dentry))
		return false;

	if (special_file(d_inode(dentry)->i_mode))
		return false;

	if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC))
		return false;

	return true;
}

int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags)
{
	int err = 0;

	if (ovl_open_need_copy_up(dentry, file_flags)) {
		err = ovl_want_write(dentry);
		if (!err) {
			err = ovl_copy_up_flags(dentry, file_flags);
			ovl_drop_write(dentry);
		}
	}

	return err;
}

int ovl_update_time(struct inode *inode, struct timespec *ts, int flags)
{
	struct dentry *alias;
	struct path upperpath;

	if (!(flags & S_ATIME))
		return 0;

	alias = d_find_any_alias(inode);
	if (!alias)
		return 0;

	ovl_path_upper(alias, &upperpath);
	if (upperpath.dentry) {
		touch_atime(&upperpath);
		inode->i_atime = d_inode(upperpath.dentry)->i_atime;
	}

	dput(alias);

	return 0;
}

static const struct inode_operations ovl_file_inode_operations = {
	.setattr	= ovl_setattr,
	.permission	= ovl_permission,
	.getattr	= ovl_getattr,
	.listxattr	= ovl_listxattr,
	.get_acl	= ovl_get_acl,
	.update_time	= ovl_update_time,
};

static const struct inode_operations ovl_symlink_inode_operations = {
	.setattr	= ovl_setattr,
	.get_link	= ovl_get_link,
	.getattr	= ovl_getattr,
	.listxattr	= ovl_listxattr,
	.update_time	= ovl_update_time,
};

/*
 * It is possible to stack overlayfs instance on top of another
 * overlayfs instance as lower layer. We need to annonate the
 * stackable i_mutex locks according to stack level of the super
 * block instance. An overlayfs instance can never be in stack
 * depth 0 (there is always a real fs below it).  An overlayfs
 * inode lock will use the lockdep annotaion ovl_i_mutex_key[depth].
 *
 * For example, here is a snip from /proc/lockdep_chains after
 * dir_iterate of nested overlayfs:
 *
 * [...] &ovl_i_mutex_dir_key[depth]   (stack_depth=2)
 * [...] &ovl_i_mutex_dir_key[depth]#2 (stack_depth=1)
 * [...] &type->i_mutex_dir_key        (stack_depth=0)
 */
#define OVL_MAX_NESTING FILESYSTEM_MAX_STACK_DEPTH

static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode)
{
#ifdef CONFIG_LOCKDEP
	static struct lock_class_key ovl_i_mutex_key[OVL_MAX_NESTING];
	static struct lock_class_key ovl_i_mutex_dir_key[OVL_MAX_NESTING];
	static struct lock_class_key ovl_i_lock_key[OVL_MAX_NESTING];

	int depth = inode->i_sb->s_stack_depth - 1;

	if (WARN_ON_ONCE(depth < 0 || depth >= OVL_MAX_NESTING))
		depth = 0;

	if (S_ISDIR(inode->i_mode))
		lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_dir_key[depth]);
	else
		lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_key[depth]);

	lockdep_set_class(&OVL_I(inode)->lock, &ovl_i_lock_key[depth]);
#endif
}

static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
{
	inode->i_ino = get_next_ino();
	inode->i_mode = mode;
	inode->i_flags |= S_NOCMTIME;
#ifdef CONFIG_FS_POSIX_ACL
	inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
#endif

	ovl_lockdep_annotate_inode_mutex_key(inode);

	switch (mode & S_IFMT) {
	case S_IFREG:
		inode->i_op = &ovl_file_inode_operations;
		break;

	case S_IFDIR:
		inode->i_op = &ovl_dir_inode_operations;
		inode->i_fop = &ovl_dir_operations;
		break;

	case S_IFLNK:
		inode->i_op = &ovl_symlink_inode_operations;
		break;

	default:
		inode->i_op = &ovl_file_inode_operations;
		init_special_inode(inode, mode, rdev);
		break;
	}
}

/*
 * With inodes index enabled, an overlay inode nlink counts the union of upper
 * hardlinks and non-covered lower hardlinks. During the lifetime of a non-pure
 * upper inode, the following nlink modifying operations can happen:
 *
 * 1. Lower hardlink copy up
 * 2. Upper hardlink created, unlinked or renamed over
 * 3. Lower hardlink whiteout or renamed over
 *
 * For the first, copy up case, the union nlink does not change, whether the
 * operation succeeds or fails, but the upper inode nlink may change.
 * Therefore, before copy up, we store the union nlink value relative to the
 * lower inode nlink in the index inode xattr trusted.overlay.nlink.
 *
 * For the second, upper hardlink case, the union nlink should be incremented
 * or decremented IFF the operation succeeds, aligned with nlink change of the
 * upper inode. Therefore, before link/unlink/rename, we store the union nlink
 * value relative to the upper inode nlink in the index inode.
 *
 * For the last, lower cover up case, we simplify things by preceding the
 * whiteout or cover up with copy up. This makes sure that there is an index
 * upper inode where the nlink xattr can be stored before the copied up upper
 * entry is unlink.
 */
#define OVL_NLINK_ADD_UPPER	(1 << 0)

/*
 * On-disk format for indexed nlink:
 *
 * nlink relative to the upper inode - "U[+-]NUM"
 * nlink relative to the lower inode - "L[+-]NUM"
 */

static int ovl_set_nlink_common(struct dentry *dentry,
				struct dentry *realdentry, const char *format)
{
	struct inode *inode = d_inode(dentry);
	struct inode *realinode = d_inode(realdentry);
	char buf[13];
	int len;

	len = snprintf(buf, sizeof(buf), format,
		       (int) (inode->i_nlink - realinode->i_nlink));

	if (WARN_ON(len >= sizeof(buf)))
		return -EIO;

	return ovl_do_setxattr(ovl_dentry_upper(dentry),
			       OVL_XATTR_NLINK, buf, len, 0);
}

int ovl_set_nlink_upper(struct dentry *dentry)
{
	return ovl_set_nlink_common(dentry, ovl_dentry_upper(dentry), "U%+i");
}

int ovl_set_nlink_lower(struct dentry *dentry)
{
	return ovl_set_nlink_common(dentry, ovl_dentry_lower(dentry), "L%+i");
}

unsigned int ovl_get_nlink(struct dentry *lowerdentry,
			   struct dentry *upperdentry,
			   unsigned int fallback)
{
	int nlink_diff;
	int nlink;
	char buf[13];
	int err;

	if (!lowerdentry || !upperdentry || d_inode(lowerdentry)->i_nlink == 1)
		return fallback;

	err = vfs_getxattr(upperdentry, OVL_XATTR_NLINK, &buf, sizeof(buf) - 1);
	if (err < 0)
		goto fail;

	buf[err] = '\0';
	if ((buf[0] != 'L' && buf[0] != 'U') ||
	    (buf[1] != '+' && buf[1] != '-'))
		goto fail;

	err = kstrtoint(buf + 1, 10, &nlink_diff);
	if (err < 0)
		goto fail;

	nlink = d_inode(buf[0] == 'L' ? lowerdentry : upperdentry)->i_nlink;
	nlink += nlink_diff;

	if (nlink <= 0)
		goto fail;

	return nlink;

fail:
	pr_warn_ratelimited("overlayfs: failed to get index nlink (%pd2, err=%i)\n",
			    upperdentry, err);
	return fallback;
}

struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev)
{
	struct inode *inode;

	inode = new_inode(sb);
	if (inode)
		ovl_fill_inode(inode, mode, rdev);

	return inode;
}

static int ovl_inode_test(struct inode *inode, void *data)
{
	return inode->i_private == data;
}

static int ovl_inode_set(struct inode *inode, void *data)
{
	inode->i_private = data;
	return 0;
}

static bool ovl_verify_inode(struct inode *inode, struct dentry *lowerdentry,
			     struct dentry *upperdentry)
{
	/*
	 * Allow non-NULL lower inode in ovl_inode even if lowerdentry is NULL.
	 * This happens when finding a copied up overlay inode for a renamed
	 * or hardlinked overlay dentry and lower dentry cannot be followed
	 * by origin because lower fs does not support file handles.
	 */
	if (lowerdentry && ovl_inode_lower(inode) != d_inode(lowerdentry))
		return false;

	/*
	 * Allow non-NULL __upperdentry in inode even if upperdentry is NULL.
	 * This happens when finding a lower alias for a copied up hard link.
	 */
	if (upperdentry && ovl_inode_upper(inode) != d_inode(upperdentry))
		return false;

	return true;
}

struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry,
			    struct dentry *index)
{
	struct dentry *lowerdentry = ovl_dentry_lower(dentry);
	struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL;
	struct inode *inode;
	/* Already indexed or could be indexed on copy up? */
	bool indexed = (index || (ovl_indexdir(dentry->d_sb) && !upperdentry));

	if (WARN_ON(upperdentry && indexed && !lowerdentry))
		return ERR_PTR(-EIO);

	if (!realinode)
		realinode = d_inode(lowerdentry);

	/*
	 * Copy up origin (lower) may exist for non-indexed upper, but we must
	 * not use lower as hash key in that case.
	 * Hash inodes that are or could be indexed by origin inode and
	 * non-indexed upper inodes that could be hard linked by upper inode.
	 */
	if (!S_ISDIR(realinode->i_mode) && (upperdentry || indexed)) {
		struct inode *key = d_inode(indexed ? lowerdentry :
						      upperdentry);
		unsigned int nlink;

		inode = iget5_locked(dentry->d_sb, (unsigned long) key,
				     ovl_inode_test, ovl_inode_set, key);
		if (!inode)
			goto out_nomem;
		if (!(inode->i_state & I_NEW)) {
			/*
			 * Verify that the underlying files stored in the inode
			 * match those in the dentry.
			 */
			if (!ovl_verify_inode(inode, lowerdentry, upperdentry)) {
				iput(inode);
				inode = ERR_PTR(-ESTALE);
				goto out;
			}

			dput(upperdentry);
			goto out;
		}

		nlink = ovl_get_nlink(lowerdentry, upperdentry,
				      realinode->i_nlink);
		set_nlink(inode, nlink);
	} else {
		inode = new_inode(dentry->d_sb);
		if (!inode)
			goto out_nomem;
	}
	ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev);
	ovl_inode_init(inode, upperdentry, lowerdentry);

	if (upperdentry && ovl_is_impuredir(upperdentry))
		ovl_set_flag(OVL_IMPURE, inode);

	/* Check for non-merge dir that may have whiteouts */
	if (S_ISDIR(realinode->i_mode)) {
		struct ovl_entry *oe = dentry->d_fsdata;

		if (((upperdentry && lowerdentry) || oe->numlower > 1) ||
		    ovl_check_origin_xattr(upperdentry ?: lowerdentry)) {
			ovl_set_flag(OVL_WHITEOUTS, inode);
		}
	}

	if (inode->i_state & I_NEW)
		unlock_new_inode(inode);
out:
	return inode;

out_nomem:
	inode = ERR_PTR(-ENOMEM);
	goto out;
}