linux/fs/smb/server/unicode.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *   Some of the source code in this file came from fs/cifs/cifs_unicode.c
 *
 *   Copyright (c) International Business Machines  Corp., 2000,2009
 *   Modified by Steve French ([email protected])
 *   Modified by Namjae Jeon ([email protected])
 */
#include <linux/fs.h>
#include <linux/slab.h>
#include <asm/unaligned.h>
#include "glob.h"
#include "unicode.h"
#include "smb_common.h"

/*
 * cifs_mapchar() - convert a host-endian char to proper char in codepage
 * @target:	where converted character should be copied
 * @from:	host-endian source string
 * @cp:		codepage to which character should be converted
 * @mapchar:	should character be mapped according to mapchars mount option?
 *
 * This function handles the conversion of a single character. It is the
 * responsibility of the caller to ensure that the target buffer is large
 * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
 *
 * Return:	string length after conversion
 */
static int
cifs_mapchar(char *target, const __u16 *from, const struct nls_table *cp,
	     bool mapchar)
{ … }

/*
 * smb_utf16_bytes() - compute converted string length
 * @from:	pointer to input string
 * @maxbytes:	input string length
 * @codepage:	destination codepage
 *
 * Walk a utf16le string and return the number of bytes that the string will
 * be after being converted to the given charset, not including any null
 * termination required. Don't walk past maxbytes in the source buffer.
 *
 * Return:	string length after conversion
 */
static int smb_utf16_bytes(const __le16 *from, int maxbytes,
			   const struct nls_table *codepage)
{ … }

/*
 * smb_from_utf16() - convert utf16le string to local charset
 * @to:		destination buffer
 * @from:	source buffer
 * @tolen:	destination buffer size (in bytes)
 * @fromlen:	source buffer size (in bytes)
 * @codepage:	codepage to which characters should be converted
 * @mapchar:	should characters be remapped according to the mapchars option?
 *
 * Convert a little-endian utf16le string (as sent by the server) to a string
 * in the provided codepage. The tolen and fromlen parameters are to ensure
 * that the code doesn't walk off of the end of the buffer (which is always
 * a danger if the alignment of the source buffer is off). The destination
 * string is always properly null terminated and fits in the destination
 * buffer. Returns the length of the destination string in bytes (including
 * null terminator).
 *
 * Note that some windows versions actually send multiword UTF-16 characters
 * instead of straight UTF16-2. The linux nls routines however aren't able to
 * deal with those characters properly. In the event that we get some of
 * those characters, they won't be translated properly.
 *
 * Return:	string length after conversion
 */
static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
			  const struct nls_table *codepage, bool mapchar)
{ … }

/*
 * smb_strtoUTF16() - Convert character string to unicode string
 * @to:		destination buffer
 * @from:	source buffer
 * @len:	destination buffer size (in bytes)
 * @codepage:	codepage to which characters should be converted
 *
 * Return:	string length after conversion
 */
int smb_strtoUTF16(__le16 *to, const char *from, int len,
		   const struct nls_table *codepage)
{ … }

/*
 * smb_strndup_from_utf16() - copy a string from wire format to the local
 *		codepage
 * @src:	source string
 * @maxlen:	don't walk past this many bytes in the source string
 * @is_unicode:	is this a unicode string?
 * @codepage:	destination codepage
 *
 * Take a string given by the server, convert it to the local codepage and
 * put it in a new buffer. Returns a pointer to the new string or NULL on
 * error.
 *
 * Return:	destination string buffer or error ptr
 */
char *smb_strndup_from_utf16(const char *src, const int maxlen,
			     const bool is_unicode,
			     const struct nls_table *codepage)
{ … }

/*
 * Convert 16 bit Unicode pathname to wire format from string in current code
 * page. Conversion may involve remapping up the six characters that are
 * only legal in POSIX-like OS (if they are present in the string). Path
 * names are little endian 16 bit Unicode on the wire
 */
/*
 * smbConvertToUTF16() - convert string from local charset to utf16
 * @target:	destination buffer
 * @source:	source buffer
 * @srclen:	source buffer size (in bytes)
 * @cp:		codepage to which characters should be converted
 * @mapchar:	should characters be remapped according to the mapchars option?
 *
 * Convert 16 bit Unicode pathname to wire format from string in current code
 * page. Conversion may involve remapping up the six characters that are
 * only legal in POSIX-like OS (if they are present in the string). Path
 * names are little endian 16 bit Unicode on the wire
 *
 * Return:	char length after conversion
 */
int smbConvertToUTF16(__le16 *target, const char *source, int srclen,
		      const struct nls_table *cp, int mapchars)
{ … }