fs/fat/namei_vfat.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 *  linux/fs/vfat/namei.c
 *
 *  Written 1992,1993 by Werner Almesberger
 *
 *  Windows95/Windows NT compatible extended MSDOS filesystem
 *    by Gordon Chaffee Copyright (C) 1995.  Send bug reports for the
 *    VFAT filesystem to <chaffee@cs.berkeley.edu>.  Specify
 *    what file operation caused you trouble and if you can duplicate
 *    the problem, send a script that demonstrates it.
 *
 *  Short name translation 1999, 2001 by Wolfram Pienkoss <wp@bszh.de>
 *
 *  Support Multibyte characters and cleanup by
 *				OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
 */

#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/slab.h>
#include <linux/namei.h>
#include <linux/hex.h>
#include <linux/kernel.h>
#include <linux/iversion.h>
#include "fat.h"

static inline unsigned long vfat_d_version(struct dentry *dentry)
{
	return (unsigned long) dentry->d_fsdata;
}

static inline void vfat_d_version_set(struct dentry *dentry,
				      unsigned long version)
{
	dentry->d_fsdata = (void *) version;
}

/*
 * If new entry was created in the parent, it could create the 8.3
 * alias (the shortname of logname).  So, the parent may have the
 * negative-dentry which matches the created 8.3 alias.
 *
 * If it happened, the negative dentry isn't actually negative
 * anymore.  So, drop it.
 */
static bool vfat_revalidate_shortname(struct dentry *dentry, struct inode *dir)
{
	return inode_eq_iversion(dir, vfat_d_version(dentry));
}

static int vfat_revalidate(struct inode *dir, const struct qstr *name,
			   struct dentry *dentry, unsigned int flags)
{
	if (flags & LOOKUP_RCU)
		return -ECHILD;

	/* This is not negative dentry. Always valid. */
	if (d_really_is_positive(dentry))
		return 1;
	return vfat_revalidate_shortname(dentry, dir);
}

static int vfat_revalidate_ci(struct inode *dir, const struct qstr *name,
			      struct dentry *dentry, unsigned int flags)
{
	if (flags & LOOKUP_RCU)
		return -ECHILD;

	/*
	 * This is not negative dentry. Always valid.
	 *
	 * Note, rename() to existing directory entry will have ->d_inode,
	 * and will use existing name which isn't specified name by user.
	 *
	 * We may be able to drop this positive dentry here. But dropping
	 * positive dentry isn't good idea. So it's unsupported like
	 * rename("filename", "FILENAME") for now.
	 */
	if (d_really_is_positive(dentry))
		return 1;

	/*
	 * This may be nfsd (or something), anyway, we can't see the
	 * intent of this. So, since this can be for creation, drop it.
	 */
	if (!flags)
		return 0;

	/*
	 * Drop the negative dentry, in order to make sure to use the
	 * case sensitive name which is specified by user if this is
	 * for creation.
	 */
	if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
		return 0;

	return vfat_revalidate_shortname(dentry, dir);
}

/* returns the length of a struct qstr, ignoring trailing dots */
static unsigned int __vfat_striptail_len(unsigned int len, const char *name)
{
	while (len && name[len - 1] == '.')
		len--;
	return len;
}

static unsigned int vfat_striptail_len(const struct qstr *qstr)
{
	return __vfat_striptail_len(qstr->len, qstr->name);
}

/*
 * Compute the hash for the vfat name corresponding to the dentry.
 * Note: if the name is invalid, we leave the hash code unchanged so
 * that the existing dentry can be used. The vfat fs routines will
 * return ENOENT or EINVAL as appropriate.
 */
static int vfat_hash(const struct dentry *dentry, struct qstr *qstr)
{
	qstr->hash = full_name_hash(dentry, qstr->name, vfat_striptail_len(qstr));
	return 0;
}

/*
 * Compute the hash for the vfat name corresponding to the dentry.
 * Note: if the name is invalid, we leave the hash code unchanged so
 * that the existing dentry can be used. The vfat fs routines will
 * return ENOENT or EINVAL as appropriate.
 */
static int vfat_hashi(const struct dentry *dentry, struct qstr *qstr)
{
	struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io;
	const unsigned char *name;
	unsigned int len;
	unsigned long hash;

	name = qstr->name;
	len = vfat_striptail_len(qstr);

	hash = init_name_hash(dentry);
	while (len--)
		hash = partial_name_hash(nls_tolower(t, *name++), hash);
	qstr->hash = end_name_hash(hash);

	return 0;
}

/*
 * Case insensitive compare of two vfat names.
 */
static int vfat_cmpi(const struct dentry *dentry,
		unsigned int len, const char *str, const struct qstr *name)
{
	struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io;
	unsigned int alen, blen;

	/* A filename cannot end in '.' or we treat it like it has none */
	alen = vfat_striptail_len(name);
	blen = __vfat_striptail_len(len, str);
	if (alen == blen) {
		if (nls_strnicmp(t, name->name, str, alen) == 0)
			return 0;
	}
	return 1;
}

/*
 * Case sensitive compare of two vfat names.
 */
static int vfat_cmp(const struct dentry *dentry,
		unsigned int len, const char *str, const struct qstr *name)
{
	unsigned int alen, blen;

	/* A filename cannot end in '.' or we treat it like it has none */
	alen = vfat_striptail_len(name);
	blen = __vfat_striptail_len(len, str);
	if (alen == blen) {
		if (strncmp(name->name, str, alen) == 0)
			return 0;
	}
	return 1;
}

static const struct dentry_operations vfat_ci_dentry_ops = {
	.d_revalidate	= vfat_revalidate_ci,
	.d_hash		= vfat_hashi,
	.d_compare	= vfat_cmpi,
};

static const struct dentry_operations vfat_dentry_ops = {
	.d_revalidate	= vfat_revalidate,
	.d_hash		= vfat_hash,
	.d_compare	= vfat_cmp,
};

/* Characters that are undesirable in an MS-DOS file name */

static inline bool vfat_bad_char(wchar_t w)
{
	return (w < 0x0020)
	    || (w == '*') || (w == '?') || (w == '<') || (w == '>')
	    || (w == '|') || (w == '"') || (w == ':') || (w == '/')
	    || (w == '\\');
}

static inline bool vfat_replace_char(wchar_t w)
{
	return (w == '[') || (w == ']') || (w == ';') || (w == ',')
	    || (w == '+') || (w == '=');
}

static wchar_t vfat_skip_char(wchar_t w)
{
	return (w == '.') || (w == ' ');
}

static inline int vfat_is_used_badchars(const wchar_t *s, int len)
{
	int i;

	for (i = 0; i < len; i++)
		if (vfat_bad_char(s[i]))
			return -EINVAL;

	if (s[i - 1] == ' ') /* last character cannot be space */
		return -EINVAL;

	return 0;
}

static int vfat_find_form(struct inode *dir, unsigned char *name)
{
	struct fat_slot_info sinfo;
	int err = fat_scan(dir, name, &sinfo);
	if (err)
		return -ENOENT;
	brelse(sinfo.bh);
	return 0;
}

/*
 * 1) Valid characters for the 8.3 format alias are any combination of
 * letters, uppercase alphabets, digits, any of the
 * following special characters:
 *     $ % ' ` - @ { } ~ ! # ( ) & _ ^
 * In this case Longfilename is not stored in disk.
 *
 * WinNT's Extension:
 * File name and extension name is contain uppercase/lowercase
 * only. And it is expressed by CASE_LOWER_BASE and CASE_LOWER_EXT.
 *
 * 2) File name is 8.3 format, but it contain the uppercase and
 * lowercase char, muliti bytes char, etc. In this case numtail is not
 * added, but Longfilename is stored.
 *
 * 3) When the one except for the above, or the following special
 * character are contained:
 *        .   [ ] ; , + =
 * numtail is added, and Longfilename must be stored in disk .
 */
struct shortname_info {
	unsigned char lower:1,
		      upper:1,
		      valid:1;
};
#define INIT_SHORTNAME_INFO(x)	do {		\
	(x)->lower = 1;				\
	(x)->upper = 1;				\
	(x)->valid = 1;				\
} while (0)

static inline int to_shortname_char(struct nls_table *nls,
				    unsigned char *buf, int buf_size,
				    wchar_t *src, struct shortname_info *info)
{
	int len;

	if (vfat_skip_char(*src)) {
		info->valid = 0;
		return 0;
	}
	if (vfat_replace_char(*src)) {
		info->valid = 0;
		buf[0] = '_';
		return 1;
	}

	len = nls->uni2char(*src, buf, buf_size);
	if (len <= 0) {
		info->valid = 0;
		buf[0] = '_';
		len = 1;
	} else if (len == 1) {
		unsigned char prev = buf[0];

		if (buf[0] >= 0x7F) {
			info->lower = 0;
			info->upper = 0;
		}

		buf[0] = nls_toupper(nls, buf[0]);
		if (isalpha(buf[0])) {
			if (buf[0] == prev)
				info->lower = 0;
			else
				info->upper = 0;
		}
	} else {
		info->lower = 0;
		info->upper = 0;
	}

	return len;
}

/*
 * Given a valid longname, create a unique shortname.  Make sure the
 * shortname does not exist
 * Returns negative number on error, 0 for a normal
 * return, and 1 for valid shortname
 */
static int vfat_create_shortname(struct inode *dir, struct nls_table *nls,
				 wchar_t *uname, int ulen,
				 unsigned char *name_res, unsigned char *lcase)
{
	struct fat_mount_options *opts = &MSDOS_SB(dir->i_sb)->options;
	wchar_t *ip, *ext_start, *end, *name_start;
	unsigned char base[9], ext[4], buf[5], *p;
	unsigned char charbuf[NLS_MAX_CHARSET_SIZE];
	int chl, chi;
	int sz = 0, extlen, baselen, i, numtail_baselen, numtail2_baselen;
	int is_shortname;
	struct shortname_info base_info, ext_info;

	is_shortname = 1;
	INIT_SHORTNAME_INFO(&base_info);
	INIT_SHORTNAME_INFO(&ext_info);

	/* Now, we need to create a shortname from the long name */
	ext_start = end = &uname[ulen];
	while (--ext_start >= uname) {
		if (*ext_start == 0x002E) {	/* is `.' */
			if (ext_start == end - 1) {
				sz = ulen;
				ext_start = NULL;
			}
			break;
		}
	}

	if (ext_start == uname - 1) {
		sz = ulen;
		ext_start = NULL;
	} else if (ext_start) {
		/*
		 * Names which start with a dot could be just
		 * an extension eg. "...test".  In this case Win95
		 * uses the extension as the name and sets no extension.
		 */
		name_start = &uname[0];
		while (name_start < ext_start) {
			if (!vfat_skip_char(*name_start))
				break;
			name_start++;
		}
		if (name_start != ext_start) {
			sz = ext_start - uname;
			ext_start++;
		} else {
			sz = ulen;
			ext_start = NULL;
		}
	}

	numtail_baselen = 6;
	numtail2_baselen = 2;
	for (baselen = i = 0, p = base, ip = uname; i < sz; i++, ip++) {
		chl = to_shortname_char(nls, charbuf, sizeof(charbuf),
					ip, &base_info);
		if (chl == 0)
			continue;

		if (baselen < 2 && (baselen + chl) > 2)
			numtail2_baselen = baselen;
		if (baselen < 6 && (baselen + chl) > 6)
			numtail_baselen = baselen;
		for (chi = 0; chi < chl; chi++) {
			*p++ = charbuf[chi];
			baselen++;
			if (baselen >= 8)
				break;
		}
		if (baselen >= 8) {
			if ((chi < chl - 1) || (ip + 1) - uname < sz)
				is_shortname = 0;
			break;
		}
	}
	if (baselen == 0) {
		return -EINVAL;
	}

	extlen = 0;
	if (ext_start) {
		for (p = ext, ip = ext_start; extlen < 3 && ip < end; ip++) {
			chl = to_shortname_char(nls, charbuf, sizeof(charbuf),
						ip, &ext_info);
			if (chl == 0)
				continue;

			if ((extlen + chl) > 3) {
				is_shortname = 0;
				break;
			}
			for (chi = 0; chi < chl; chi++) {
				*p++ = charbuf[chi];
				extlen++;
			}
			if (extlen >= 3) {
				if (ip + 1 != end)
					is_shortname = 0;
				break;
			}
		}
	}
	ext[extlen] = '\0';
	base[baselen] = '\0';

	/* Yes, it can happen. ".\xe5" would do it. */
	if (base[0] == DELETED_FLAG)
		base[0] = 0x05;

	/* OK, at this point we know that base is not longer than 8 symbols,
	 * ext is not longer than 3, base is nonempty, both don't contain
	 * any bad symbols (lowercase transformed to uppercase).
	 */

	memset(name_res, ' ', MSDOS_NAME);
	memcpy(name_res, base, baselen);
	memcpy(name_res + 8, ext, extlen);
	*lcase = 0;
	if (is_shortname && base_info.valid && ext_info.valid) {
		if (vfat_find_form(dir, name_res) == 0)
			return -EEXIST;

		if (opts->shortname & VFAT_SFN_CREATE_WIN95) {
			return (base_info.upper && ext_info.upper);
		} else if (opts->shortname & VFAT_SFN_CREATE_WINNT) {
			if ((base_info.upper || base_info.lower) &&
			    (ext_info.upper || ext_info.lower)) {
				if (!base_info.upper && base_info.lower)
					*lcase |= CASE_LOWER_BASE;
				if (!ext_info.upper && ext_info.lower)
					*lcase |= CASE_LOWER_EXT;
				return 1;
			}
			return 0;
		} else {
			BUG();
		}
	}

	if (opts->numtail == 0)
		if (vfat_find_form(dir, name_res) < 0)
			return 0;

	/*
	 * Try to find a unique extension.  This used to
	 * iterate through all possibilities sequentially,
	 * but that gave extremely bad performance.  Windows
	 * only tries a few cases before using random
	 * values for part of the base.
	 */

	if (baselen > 6) {
		baselen = numtail_baselen;
		name_res[7] = ' ';
	}
	name_res[baselen] = '~';
	for (i = 1; i < 10; i++) {
		name_res[baselen + 1] = i + '0';
		if (vfat_find_form(dir, name_res) < 0)
			return 0;
	}

	i = jiffies;
	sz = (jiffies >> 16) & 0x7;
	if (baselen > 2) {
		baselen = numtail2_baselen;
		name_res[7] = ' ';
	}
	name_res[baselen + 4] = '~';
	name_res[baselen + 5] = '1' + sz;
	while (1) {
		snprintf(buf, sizeof(buf), "%04X", i & 0xffff);
		memcpy(&name_res[baselen], buf, 4);
		if (vfat_find_form(dir, name_res) < 0)
			break;
		i -= 11;
	}
	return 0;
}

/* Translate a string, including coded sequences into Unicode */
static int
xlate_to_uni(const unsigned char *name, int len, unsigned char *outname,
	     int *longlen, int *outlen, int escape, int utf8,
	     struct nls_table *nls)
{
	const unsigned char *ip;
	unsigned char *op;
	int i, fill;
	int charlen;

	if (utf8) {
		*outlen = utf8s_to_utf16s(name, len, UTF16_HOST_ENDIAN,
				(wchar_t *) outname, FAT_LFN_LEN + 2);
		if (*outlen < 0)
			return *outlen;
		else if (*outlen > FAT_LFN_LEN)
			return -ENAMETOOLONG;

		op = &outname[*outlen * sizeof(wchar_t)];
	} else {
		for (i = 0, ip = name, op = outname, *outlen = 0;
			 i < len && *outlen < FAT_LFN_LEN;
			 *outlen += 1) {
			if (escape && (*ip == ':')) {
				u8 uc[2];

				if (i > len - 5)
					return -EINVAL;

				if (hex2bin(uc, ip + 1, 2) < 0)
					return -EINVAL;

				*(wchar_t *)op = uc[0] << 8 | uc[1];

				op += 2;
				ip += 5;
				i += 5;
			} else {
				charlen = nls->char2uni(ip, len - i,
							(wchar_t *)op);
				if (charlen < 0)
					return -EINVAL;
				ip += charlen;
				i += charlen;
				op += 2;
			}
		}
		if (i < len)
			return -ENAMETOOLONG;
	}

	*longlen = *outlen;
	if (*outlen % 13) {
		*op++ = 0;
		*op++ = 0;
		*outlen += 1;
		if (*outlen % 13) {
			fill = 13 - (*outlen % 13);
			for (i = 0; i < fill; i++) {
				*op++ = 0xff;
				*op++ = 0xff;
			}
			*outlen += fill;
		}
	}

	return 0;
}

static int vfat_build_slots(struct inode *dir, const unsigned char *name,
			    int len, int is_dir, int cluster,
			    struct timespec64 *ts,
			    struct msdos_dir_slot *slots, int *nr_slots)
{
	struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb);
	struct fat_mount_options *opts = &sbi->options;
	struct msdos_dir_slot *ps;
	struct msdos_dir_entry *de;
	unsigned char cksum, lcase;
	unsigned char msdos_name[MSDOS_NAME];
	wchar_t *uname;
	__le16 time, date;
	u8 time_cs;
	int err, ulen, usize, i;
	loff_t offset;

	*nr_slots = 0;

	uname = __getname();
	if (!uname)
		return -ENOMEM;

	err = xlate_to_uni(name, len, (unsigned char *)uname, &ulen, &usize,
			   opts->unicode_xlate, opts->utf8, sbi->nls_io);
	if (err)
		goto out_free;

	err = vfat_is_used_badchars(uname, ulen);
	if (err)
		goto out_free;

	err = vfat_create_shortname(dir, sbi->nls_disk, uname, ulen,
				    msdos_name, &lcase);
	if (err < 0)
		goto out_free;
	else if (err == 1) {
		de = (struct msdos_dir_entry *)slots;
		err = 0;
		goto shortname;
	}

	/* build the entry of long file name */
	cksum = fat_checksum(msdos_name);

	*nr_slots = usize / 13;
	for (ps = slots, i = *nr_slots; i > 0; i--, ps++) {
		ps->id = i;
		ps->attr = ATTR_EXT;
		ps->reserved = 0;
		ps->alias_checksum = cksum;
		ps->start = 0;
		offset = (i - 1) * 13;
		fatwchar_to16(ps->name0_4, uname + offset, 5);
		fatwchar_to16(ps->name5_10, uname + offset + 5, 6);
		fatwchar_to16(ps->name11_12, uname + offset + 11, 2);
	}
	slots[0].id |= 0x40;
	de = (struct msdos_dir_entry *)ps;

shortname:
	/* build the entry of 8.3 alias name */
	(*nr_slots)++;
	memcpy(de->name, msdos_name, MSDOS_NAME);
	de->attr = is_dir ? ATTR_DIR : ATTR_ARCH;
	de->lcase = lcase;
	fat_time_unix2fat(sbi, ts, &time, &date, &time_cs);
	de->time = de->ctime = time;
	de->date = de->cdate = de->adate = date;
	de->ctime_cs = time_cs;
	fat_set_start(de, cluster);
	de->size = 0;
out_free:
	__putname(uname);
	return err;
}

static int vfat_add_entry(struct inode *dir, const struct qstr *qname,
			  int is_dir, int cluster, struct timespec64 *ts,
			  struct fat_slot_info *sinfo)
{
	struct msdos_dir_slot *slots;
	unsigned int len;
	int err, nr_slots;

	len = vfat_striptail_len(qname);
	if (len == 0)
		return -ENOENT;

	slots = kmalloc_objs(*slots, MSDOS_SLOTS, GFP_NOFS);
	if (slots == NULL)
		return -ENOMEM;

	err = vfat_build_slots(dir, qname->name, len, is_dir, cluster, ts,
			       slots, &nr_slots);
	if (err)
		goto cleanup;

	err = fat_add_entries(dir, slots, nr_slots, sinfo);
	if (err)
		goto cleanup;

	/* update timestamp */
	fat_truncate_time(dir, ts, FAT_UPDATE_CMTIME);
	mark_inode_dirty(dir);
	if (IS_DIRSYNC(dir))
		(void)sync_inode_metadata(dir, 1);
cleanup:
	kfree(slots);
	return err;
}

static int vfat_find(struct inode *dir, const struct qstr *qname,
		     struct fat_slot_info *sinfo)
{
	unsigned int len = vfat_striptail_len(qname);
	if (len == 0)
		return -ENOENT;
	return fat_search_long(dir, qname->name, len, sinfo);
}

static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
				  unsigned int flags)
{
	struct super_block *sb = dir->i_sb;
	struct fat_slot_info sinfo;
	struct inode *inode;
	struct dentry *alias;
	int err;

	mutex_lock(&MSDOS_SB(sb)->s_lock);

	err = vfat_find(dir, &dentry->d_name, &sinfo);
	if (err) {
		if (err == -ENOENT) {
			inode = NULL;
			goto out;
		}
		goto error;
	}

	inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
	brelse(sinfo.bh);
	if (IS_ERR(inode)) {
		err = PTR_ERR(inode);
		goto error;
	}

	alias = d_find_alias(inode);
	/*
	 * Checking "alias->d_parent == dentry->d_parent" to make sure
	 * FS is not corrupted (especially double linked dir).
	 */
	if (alias && alias->d_parent == dentry->d_parent) {
		/*
		 * This inode has non anonymous-DCACHE_DISCONNECTED
		 * dentry. This means, the user did ->lookup() by an
		 * another name (longname vs 8.3 alias of it) in past.
		 *
		 * Switch to new one for reason of locality if possible.
		 */
		if (!S_ISDIR(inode->i_mode))
			d_move(alias, dentry);
		iput(inode);
		mutex_unlock(&MSDOS_SB(sb)->s_lock);
		return alias;
	} else
		dput(alias);

out:
	mutex_unlock(&MSDOS_SB(sb)->s_lock);
	if (!inode)
		vfat_d_version_set(dentry, inode_query_iversion(dir));
	return d_splice_alias(inode, dentry);
error:
	mutex_unlock(&MSDOS_SB(sb)->s_lock);
	return ERR_PTR(err);
}

static int vfat_create(struct mnt_idmap *idmap, struct inode *dir,
		       struct dentry *dentry, umode_t mode)
{
	struct super_block *sb = dir->i_sb;
	struct inode *inode;
	struct fat_slot_info sinfo;
	struct timespec64 ts;
	int err;

	mutex_lock(&MSDOS_SB(sb)->s_lock);

	ts = current_time(dir);
	err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &ts, &sinfo);
	if (err)
		goto out;
	inode_inc_iversion(dir);

	inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
	brelse(sinfo.bh);
	if (IS_ERR(inode)) {
		err = PTR_ERR(inode);
		goto out;
	}
	inode_inc_iversion(inode);

	d_instantiate(dentry, inode);
out:
	mutex_unlock(&MSDOS_SB(sb)->s_lock);
	return err;
}

static int vfat_rmdir(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);
	struct super_block *sb = dir->i_sb;
	struct fat_slot_info sinfo;
	int err;

	mutex_lock(&MSDOS_SB(sb)->s_lock);

	err = fat_dir_empty(inode);
	if (err)
		goto out;
	err = vfat_find(dir, &dentry->d_name, &sinfo);
	if (err)
		goto out;

	err = fat_remove_entries(dir, &sinfo);	/* and releases bh */
	if (err)
		goto out;
	if (dir->i_nlink >= 3)
		drop_nlink(dir);
	else {
		fat_fs_error(sb, "parent dir link count too low (%u)",
			dir->i_nlink);
	}

	clear_nlink(inode);
	fat_truncate_time(inode, NULL, FAT_UPDATE_ATIME | FAT_UPDATE_CMTIME);
	fat_detach(inode);
	vfat_d_version_set(dentry, inode_query_iversion(dir));
out:
	mutex_unlock(&MSDOS_SB(sb)->s_lock);

	return err;
}

static int vfat_unlink(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);
	struct super_block *sb = dir->i_sb;
	struct fat_slot_info sinfo;
	int err;

	mutex_lock(&MSDOS_SB(sb)->s_lock);

	err = vfat_find(dir, &dentry->d_name, &sinfo);
	if (err)
		goto out;

	err = fat_remove_entries(dir, &sinfo);	/* and releases bh */
	if (err)
		goto out;
	clear_nlink(inode);
	fat_truncate_time(inode, NULL, FAT_UPDATE_ATIME | FAT_UPDATE_CMTIME);
	fat_detach(inode);
	vfat_d_version_set(dentry, inode_query_iversion(dir));
out:
	mutex_unlock(&MSDOS_SB(sb)->s_lock);

	return err;
}

static struct dentry *vfat_mkdir(struct mnt_idmap *idmap, struct inode *dir,
				  struct dentry *dentry, umode_t mode)
{
	struct super_block *sb = dir->i_sb;
	struct inode *inode;
	struct fat_slot_info sinfo;
	struct timespec64 ts;
	int err, cluster;

	mutex_lock(&MSDOS_SB(sb)->s_lock);

	ts = current_time(dir);
	cluster = fat_alloc_new_dir(dir, &ts);
	if (cluster < 0) {
		err = cluster;
		goto out;
	}
	err = vfat_add_entry(dir, &dentry->d_name, 1, cluster, &ts, &sinfo);
	if (err)
		goto out_free;
	inode_inc_iversion(dir);
	inc_nlink(dir);

	inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
	brelse(sinfo.bh);
	if (IS_ERR(inode)) {
		err = PTR_ERR(inode);
		/* the directory was completed, just return a error */
		goto out;
	}
	inode_inc_iversion(inode);
	set_nlink(inode, 2);

	d_instantiate(dentry, inode);

	mutex_unlock(&MSDOS_SB(sb)->s_lock);
	return NULL;

out_free:
	fat_free_clusters(dir, cluster);
out:
	mutex_unlock(&MSDOS_SB(sb)->s_lock);
	return ERR_PTR(err);
}

static int vfat_get_dotdot_de(struct inode *inode, struct buffer_head **bh,
			      struct msdos_dir_entry **de)
{
	if (S_ISDIR(inode->i_mode)) {
		if (fat_get_dotdot_entry(inode, bh, de))
			return -EIO;
	}
	return 0;
}

static int vfat_sync_ipos(struct inode *dir, struct inode *inode)
{
	mark_inode_dirty(inode);
	if (IS_DIRSYNC(dir))
		return sync_inode_metadata(inode, 1);
	return 0;
}

static int vfat_update_dotdot_de(struct inode *dir, struct inode *inode,
				 struct buffer_head *dotdot_bh,
				 struct msdos_dir_entry *dotdot_de)
{
	fat_set_start(dotdot_de, MSDOS_I(dir)->i_logstart);
	mmb_mark_buffer_dirty(dotdot_bh, &MSDOS_I(inode)->i_metadata_bhs);
	if (IS_DIRSYNC(dir))
		return sync_dirty_buffer(dotdot_bh);
	return 0;
}

static void vfat_update_dir_metadata(struct inode *dir, struct timespec64 *ts)
{
	inode_inc_iversion(dir);
	fat_truncate_time(dir, ts, FAT_UPDATE_CMTIME);
	mark_inode_dirty(dir);
	if (IS_DIRSYNC(dir))
		(void)sync_inode_metadata(dir, 1);
}

static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
		       struct inode *new_dir, struct dentry *new_dentry)
{
	struct buffer_head *dotdot_bh;
	struct msdos_dir_entry *dotdot_de = NULL;
	struct inode *old_inode, *new_inode;
	struct fat_slot_info old_sinfo, sinfo;
	struct timespec64 ts;
	loff_t new_i_pos;
	int err, is_dir, corrupt = 0;
	struct super_block *sb = old_dir->i_sb;

	old_sinfo.bh = sinfo.bh = dotdot_bh = NULL;
	old_inode = d_inode(old_dentry);
	new_inode = d_inode(new_dentry);
	mutex_lock(&MSDOS_SB(sb)->s_lock);
	err = vfat_find(old_dir, &old_dentry->d_name, &old_sinfo);
	if (err)
		goto out;

	if (old_dir != new_dir) {
		err = vfat_get_dotdot_de(old_inode, &dotdot_bh, &dotdot_de);
		if (err)
			goto out;
	}

	is_dir = S_ISDIR(old_inode->i_mode);
	ts = current_time(old_dir);
	if (new_inode) {
		if (is_dir) {
			err = fat_dir_empty(new_inode);
			if (err)
				goto out;
		}
		new_i_pos = MSDOS_I(new_inode)->i_pos;
		fat_detach(new_inode);
	} else {
		err = vfat_add_entry(new_dir, &new_dentry->d_name, is_dir, 0,
				     &ts, &sinfo);
		if (err)
			goto out;
		new_i_pos = sinfo.i_pos;
	}
	inode_inc_iversion(new_dir);

	fat_detach(old_inode);
	fat_attach(old_inode, new_i_pos);
	err = vfat_sync_ipos(new_dir, old_inode);
	if (err)
		goto error_inode;

	if (dotdot_de) {
		err = vfat_update_dotdot_de(new_dir, old_inode, dotdot_bh,
					    dotdot_de);
		if (err)
			goto error_dotdot;
		drop_nlink(old_dir);
		if (!new_inode)
 			inc_nlink(new_dir);
	}

	err = fat_remove_entries(old_dir, &old_sinfo);	/* and releases bh */
	old_sinfo.bh = NULL;
	if (err)
		goto error_dotdot;
	vfat_update_dir_metadata(old_dir, &ts);

	if (new_inode) {
		drop_nlink(new_inode);
		if (is_dir)
			drop_nlink(new_inode);
	}
out:
	brelse(sinfo.bh);
	brelse(dotdot_bh);
	brelse(old_sinfo.bh);
	mutex_unlock(&MSDOS_SB(sb)->s_lock);

	return err;

error_dotdot:
	/* data cluster is shared, serious corruption */
	corrupt = 1;

	if (dotdot_de) {
		corrupt |= vfat_update_dotdot_de(old_dir, old_inode, dotdot_bh,
						 dotdot_de);
	}
error_inode:
	fat_detach(old_inode);
	fat_attach(old_inode, old_sinfo.i_pos);
	if (new_inode) {
		fat_attach(new_inode, new_i_pos);
		if (corrupt) {
			mark_inode_dirty(new_inode);
			corrupt |= sync_inode_metadata(new_inode, 1);
		}
	} else {
		/*
		 * If new entry was not sharing the data cluster, it
		 * shouldn't be serious corruption.
		 */
		int err2 = fat_remove_entries(new_dir, &sinfo);
		if (corrupt)
			corrupt |= err2;
		sinfo.bh = NULL;
	}
	if (corrupt < 0) {
		fat_fs_error(new_dir->i_sb,
			     "%s: Filesystem corrupted (i_pos %lld)",
			     __func__, new_i_pos);
	}
	goto out;
}

static void vfat_exchange_ipos(struct inode *old_inode, struct inode *new_inode,
			       loff_t old_i_pos, loff_t new_i_pos)
{
	fat_detach(old_inode);
	fat_detach(new_inode);
	fat_attach(old_inode, new_i_pos);
	fat_attach(new_inode, old_i_pos);
}

static void vfat_move_nlink(struct inode *src, struct inode *dst)
{
	drop_nlink(src);
	inc_nlink(dst);
}

static int vfat_rename_exchange(struct inode *old_dir, struct dentry *old_dentry,
				struct inode *new_dir, struct dentry *new_dentry)
{
	struct buffer_head *old_dotdot_bh = NULL, *new_dotdot_bh = NULL;
	struct msdos_dir_entry *old_dotdot_de = NULL, *new_dotdot_de = NULL;
	struct inode *old_inode, *new_inode;
	struct timespec64 ts = current_time(old_dir);
	loff_t old_i_pos, new_i_pos;
	int err, corrupt = 0;
	struct super_block *sb = old_dir->i_sb;

	old_inode = d_inode(old_dentry);
	new_inode = d_inode(new_dentry);

	/* Acquire super block lock for the operation to be atomic */
	mutex_lock(&MSDOS_SB(sb)->s_lock);

	/* if directories are not the same, get ".." info to update */
	if (old_dir != new_dir) {
		err = vfat_get_dotdot_de(old_inode, &old_dotdot_bh,
					 &old_dotdot_de);
		if (err)
			goto out;

		err = vfat_get_dotdot_de(new_inode, &new_dotdot_bh,
					 &new_dotdot_de);
		if (err)
			goto out;
	}

	old_i_pos = MSDOS_I(old_inode)->i_pos;
	new_i_pos = MSDOS_I(new_inode)->i_pos;

	vfat_exchange_ipos(old_inode, new_inode, old_i_pos, new_i_pos);

	err = vfat_sync_ipos(old_dir, new_inode);
	if (err)
		goto error_exchange;
	err = vfat_sync_ipos(new_dir, old_inode);
	if (err)
		goto error_exchange;

	/* update ".." directory entry info */
	if (old_dotdot_de) {
		err = vfat_update_dotdot_de(new_dir, old_inode, old_dotdot_bh,
					    old_dotdot_de);
		if (err)
			goto error_old_dotdot;
	}
	if (new_dotdot_de) {
		err = vfat_update_dotdot_de(old_dir, new_inode, new_dotdot_bh,
					    new_dotdot_de);
		if (err)
			goto error_new_dotdot;
	}

	/* if cross directory and only one is a directory, adjust nlink */
	if (!old_dotdot_de != !new_dotdot_de) {
		if (old_dotdot_de)
			vfat_move_nlink(old_dir, new_dir);
		else
			vfat_move_nlink(new_dir, old_dir);
	}

	vfat_update_dir_metadata(old_dir, &ts);
	/* if directories are not the same, update new_dir as well */
	if (old_dir != new_dir)
		vfat_update_dir_metadata(new_dir, &ts);

out:
	brelse(old_dotdot_bh);
	brelse(new_dotdot_bh);
	mutex_unlock(&MSDOS_SB(sb)->s_lock);

	return err;

error_new_dotdot:
	if (new_dotdot_de) {
		corrupt |= vfat_update_dotdot_de(new_dir, new_inode,
						 new_dotdot_bh, new_dotdot_de);
	}

error_old_dotdot:
	if (old_dotdot_de) {
		corrupt |= vfat_update_dotdot_de(old_dir, old_inode,
						 old_dotdot_bh, old_dotdot_de);
	}

error_exchange:
	vfat_exchange_ipos(old_inode, new_inode, new_i_pos, old_i_pos);
	corrupt |= vfat_sync_ipos(new_dir, new_inode);
	corrupt |= vfat_sync_ipos(old_dir, old_inode);

	if (corrupt < 0) {
		fat_fs_error(new_dir->i_sb,
			     "%s: Filesystem corrupted (i_pos %lld, %lld)",
			     __func__, old_i_pos, new_i_pos);
	}
	goto out;
}

static int vfat_rename2(struct mnt_idmap *idmap, struct inode *old_dir,
			struct dentry *old_dentry, struct inode *new_dir,
			struct dentry *new_dentry, unsigned int flags)
{
	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
		return -EINVAL;

	if (flags & RENAME_EXCHANGE) {
		return vfat_rename_exchange(old_dir, old_dentry,
					    new_dir, new_dentry);
	}

	/* VFS already handled RENAME_NOREPLACE, handle it as a normal rename */
	return vfat_rename(old_dir, old_dentry, new_dir, new_dentry);
}

static const struct inode_operations vfat_dir_inode_operations = {
	.create		= vfat_create,
	.lookup		= vfat_lookup,
	.unlink		= vfat_unlink,
	.mkdir		= vfat_mkdir,
	.rmdir		= vfat_rmdir,
	.rename		= vfat_rename2,
	.setattr	= fat_setattr,
	.getattr	= fat_getattr,
	.fileattr_get	= fat_fileattr_get,
	.update_time	= fat_update_time,
};

static void setup(struct super_block *sb)
{
	MSDOS_SB(sb)->dir_ops = &vfat_dir_inode_operations;
	if (MSDOS_SB(sb)->options.name_check != 's')
		set_default_d_op(sb, &vfat_ci_dentry_ops);
	else
		set_default_d_op(sb, &vfat_dentry_ops);
}

static int vfat_fill_super(struct super_block *sb, struct fs_context *fc)
{
	return fat_fill_super(sb, fc, setup);
}

static int vfat_get_tree(struct fs_context *fc)
{
	return get_tree_bdev(fc, vfat_fill_super);
}

static int vfat_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
	return fat_parse_param(fc, param, true);
}

static const struct fs_context_operations vfat_context_ops = {
	.parse_param	= vfat_parse_param,
	.get_tree	= vfat_get_tree,
	.reconfigure	= fat_reconfigure,
	.free		= fat_free_fc,
};

static int vfat_init_fs_context(struct fs_context *fc)
{
	int err;

	/* Initialize with is_vfat == true */
	err = fat_init_fs_context(fc, true);
	if (err)
		return err;

	fc->ops = &vfat_context_ops;
	return 0;
}

static struct file_system_type vfat_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "vfat",
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
	.init_fs_context = vfat_init_fs_context,
	.parameters     = fat_param_spec,
};
MODULE_ALIAS_FS("vfat");

static int __init init_vfat_fs(void)
{
	return register_filesystem(&vfat_fs_type);
}

static void __exit exit_vfat_fs(void)
{
	unregister_filesystem(&vfat_fs_type);
}

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("VFAT filesystem support");
MODULE_AUTHOR("Gordon Chaffee");

module_init(init_vfat_fs)
module_exit(exit_vfat_fs)