Orange Pi5 kernel

^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   1) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   2)  * unicode.c
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   3)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   4)  * PURPOSE
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   5)  *	Routines for converting between UTF-8 and OSTA Compressed Unicode.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   6)  *      Also handles filename mangling
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   7)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   8)  * DESCRIPTION
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   9)  *	OSTA Compressed Unicode is explained in the OSTA UDF specification.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  10)  *		http://www.osta.org/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  11)  *	UTF-8 is explained in the IETF RFC XXXX.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  12)  *		ftp://ftp.internic.net/rfc/rfcxxxx.txt
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  13)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  14)  * COPYRIGHT
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  15)  *	This file is distributed under the terms of the GNU General Public
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  16)  *	License (GPL). Copies of the GPL can be obtained from:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  17)  *		ftp://prep.ai.mit.edu/pub/gnu/GPL
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  18)  *	Each contributing author retains all rights to their own work.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  19)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  20) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  21) #include "udfdecl.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  22) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  23) #include <linux/kernel.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  24) #include <linux/string.h>	/* for memset */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  25) #include <linux/nls.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  26) #include <linux/crc-itu-t.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  27) #include <linux/slab.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  28) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  29) #include "udf_sb.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  30) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  31) #define PLANE_SIZE 0x10000
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  32) #define UNICODE_MAX 0x10ffff
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  33) #define SURROGATE_MASK 0xfffff800
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  34) #define SURROGATE_PAIR 0x0000d800
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  35) #define SURROGATE_LOW  0x00000400
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  36) #define SURROGATE_CHAR_BITS 10
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  37) #define SURROGATE_CHAR_MASK ((1 << SURROGATE_CHAR_BITS) - 1)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  38) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  39) #define ILLEGAL_CHAR_MARK	'_'
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  40) #define EXT_MARK		'.'
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  41) #define CRC_MARK		'#'
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  42) #define EXT_SIZE		5
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  43) /* Number of chars we need to store generated CRC to make filename unique */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  44) #define CRC_LEN			5
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  45) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  46) static unicode_t get_utf16_char(const uint8_t *str_i, int str_i_max_len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  47) 				int str_i_idx, int u_ch, unicode_t *ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  48) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  49) 	unicode_t c;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  50) 	int start_idx = str_i_idx;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  51) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  52) 	/* Expand OSTA compressed Unicode to Unicode */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  53) 	c = str_i[str_i_idx++];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  54) 	if (u_ch > 1)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  55) 		c = (c << 8) | str_i[str_i_idx++];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  56) 	if ((c & SURROGATE_MASK) == SURROGATE_PAIR) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  57) 		unicode_t next;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  58) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  59) 		/* Trailing surrogate char */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  60) 		if (str_i_idx >= str_i_max_len) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  61) 			c = UNICODE_MAX + 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  62) 			goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  63) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  64) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  65) 		/* Low surrogate must follow the high one... */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  66) 		if (c & SURROGATE_LOW) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  67) 			c = UNICODE_MAX + 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  68) 			goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  69) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  70) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  71) 		WARN_ON_ONCE(u_ch != 2);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  72) 		next = str_i[str_i_idx++] << 8;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  73) 		next |= str_i[str_i_idx++];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  74) 		if ((next & SURROGATE_MASK) != SURROGATE_PAIR ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  75) 		    !(next & SURROGATE_LOW)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  76) 			c = UNICODE_MAX + 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  77) 			goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  78) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  79) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  80) 		c = PLANE_SIZE +
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  81) 		    ((c & SURROGATE_CHAR_MASK) << SURROGATE_CHAR_BITS) +
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  82) 		    (next & SURROGATE_CHAR_MASK);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  83) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  84) out:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  85) 	*ret = c;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  86) 	return str_i_idx - start_idx;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  87) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  88) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  89) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  90) static int udf_name_conv_char(uint8_t *str_o, int str_o_max_len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  91) 			      int *str_o_idx,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  92) 			      const uint8_t *str_i, int str_i_max_len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  93) 			      int *str_i_idx,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  94) 			      int u_ch, int *needsCRC,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  95) 			      int (*conv_f)(wchar_t, unsigned char *, int),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  96) 			      int translate)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  97) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  98) 	unicode_t c;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  99) 	int illChar = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100) 	int len, gotch = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102) 	while (!gotch && *str_i_idx < str_i_max_len) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103) 		if (*str_o_idx >= str_o_max_len) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) 			*needsCRC = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105) 			return gotch;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108) 		len = get_utf16_char(str_i, str_i_max_len, *str_i_idx, u_ch,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109) 				     &c);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) 		/* These chars cannot be converted. Replace them. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111) 		if (c == 0 || c > UNICODE_MAX || (conv_f && c > MAX_WCHAR_T) ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112) 		    (translate && c == '/')) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113) 			illChar = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114) 			if (!translate)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115) 				gotch = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116) 		} else if (illChar)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117) 			break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118) 		else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119) 			gotch = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120) 		*str_i_idx += len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122) 	if (illChar) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123) 		*needsCRC = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124) 		c = ILLEGAL_CHAR_MARK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125) 		gotch = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127) 	if (gotch) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) 		if (conv_f) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129) 			len = conv_f(c, &str_o[*str_o_idx],
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130) 				     str_o_max_len - *str_o_idx);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131) 		} else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132) 			len = utf32_to_utf8(c, &str_o[*str_o_idx],
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133) 					    str_o_max_len - *str_o_idx);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134) 			if (len < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135) 				len = -ENAMETOOLONG;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137) 		/* Valid character? */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138) 		if (len >= 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139) 			*str_o_idx += len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140) 		else if (len == -ENAMETOOLONG) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141) 			*needsCRC = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142) 			gotch = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143) 		} else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144) 			str_o[(*str_o_idx)++] = ILLEGAL_CHAR_MARK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145) 			*needsCRC = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148) 	return gotch;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151) static int udf_name_from_CS0(struct super_block *sb,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152) 			     uint8_t *str_o, int str_max_len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153) 			     const uint8_t *ocu, int ocu_len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154) 			     int translate)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156) 	uint32_t c;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157) 	uint8_t cmp_id;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158) 	int idx, len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159) 	int u_ch;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) 	int needsCRC = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161) 	int ext_i_len, ext_max_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162) 	int str_o_len = 0;	/* Length of resulting output */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) 	int ext_o_len = 0;	/* Extension output length */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164) 	int ext_crc_len = 0;	/* Extension output length if used with CRC */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165) 	int i_ext = -1;		/* Extension position in input buffer */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166) 	int o_crc = 0;		/* Rightmost possible output pos for CRC+ext */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167) 	unsigned short valueCRC;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168) 	uint8_t ext[EXT_SIZE * NLS_MAX_CHARSET_SIZE + 1];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169) 	uint8_t crc[CRC_LEN];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 170) 	int (*conv_f)(wchar_t, unsigned char *, int);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 171) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 172) 	if (str_max_len <= 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 173) 		return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 174) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 175) 	if (ocu_len == 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 176) 		memset(str_o, 0, str_max_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 177) 		return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 178) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 179) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 180) 	if (UDF_SB(sb)->s_nls_map)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 181) 		conv_f = UDF_SB(sb)->s_nls_map->uni2char;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 182) 	else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 183) 		conv_f = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 184) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 185) 	cmp_id = ocu[0];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 186) 	if (cmp_id != 8 && cmp_id != 16) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 187) 		memset(str_o, 0, str_max_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 188) 		pr_err("unknown compression code (%u)\n", cmp_id);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 189) 		return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 190) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 191) 	u_ch = cmp_id >> 3;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 192) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 193) 	ocu++;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 194) 	ocu_len--;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 195) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 196) 	if (ocu_len % u_ch) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 197) 		pr_err("incorrect filename length (%d)\n", ocu_len + 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 198) 		return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 199) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 200) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 201) 	if (translate) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 202) 		/* Look for extension */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 203) 		for (idx = ocu_len - u_ch, ext_i_len = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 204) 		     (idx >= 0) && (ext_i_len < EXT_SIZE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 205) 		     idx -= u_ch, ext_i_len++) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 206) 			c = ocu[idx];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 207) 			if (u_ch > 1)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 208) 				c = (c << 8) | ocu[idx + 1];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 209) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 210) 			if (c == EXT_MARK) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 211) 				if (ext_i_len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 212) 					i_ext = idx;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 213) 				break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 214) 			}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 215) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 216) 		if (i_ext >= 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 217) 			/* Convert extension */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 218) 			ext_max_len = min_t(int, sizeof(ext), str_max_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 219) 			ext[ext_o_len++] = EXT_MARK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 220) 			idx = i_ext + u_ch;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 221) 			while (udf_name_conv_char(ext, ext_max_len, &ext_o_len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 222) 						  ocu, ocu_len, &idx,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 223) 						  u_ch, &needsCRC,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 224) 						  conv_f, translate)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 225) 				if ((ext_o_len + CRC_LEN) < str_max_len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 226) 					ext_crc_len = ext_o_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 227) 			}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 228) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 229) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 230) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 231) 	idx = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 232) 	while (1) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 233) 		if (translate && (idx == i_ext)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 234) 			if (str_o_len > (str_max_len - ext_o_len))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 235) 				needsCRC = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 236) 			break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 237) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 238) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 239) 		if (!udf_name_conv_char(str_o, str_max_len, &str_o_len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 240) 					ocu, ocu_len, &idx,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 241) 					u_ch, &needsCRC, conv_f, translate))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 242) 			break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 243) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 244) 		if (translate &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 245) 		    (str_o_len <= (str_max_len - ext_o_len - CRC_LEN)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 246) 			o_crc = str_o_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 247) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 248) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 249) 	if (translate) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 250) 		if (str_o_len <= 2 && str_o[0] == '.' &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 251) 		    (str_o_len == 1 || str_o[1] == '.'))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 252) 			needsCRC = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 253) 		if (needsCRC) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 254) 			str_o_len = o_crc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 255) 			valueCRC = crc_itu_t(0, ocu, ocu_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 256) 			crc[0] = CRC_MARK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 257) 			crc[1] = hex_asc_upper_hi(valueCRC >> 8);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 258) 			crc[2] = hex_asc_upper_lo(valueCRC >> 8);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 259) 			crc[3] = hex_asc_upper_hi(valueCRC);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 260) 			crc[4] = hex_asc_upper_lo(valueCRC);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 261) 			len = min_t(int, CRC_LEN, str_max_len - str_o_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 262) 			memcpy(&str_o[str_o_len], crc, len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 263) 			str_o_len += len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 264) 			ext_o_len = ext_crc_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 265) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 266) 		if (ext_o_len > 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 267) 			memcpy(&str_o[str_o_len], ext, ext_o_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 268) 			str_o_len += ext_o_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 269) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 270) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 271) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 272) 	return str_o_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 273) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 274) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 275) static int udf_name_to_CS0(struct super_block *sb,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 276) 			   uint8_t *ocu, int ocu_max_len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 277) 			   const uint8_t *str_i, int str_len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 278) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 279) 	int i, len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 280) 	unsigned int max_val;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 281) 	int u_len, u_ch;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 282) 	unicode_t uni_char;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 283) 	int (*conv_f)(const unsigned char *, int, wchar_t *);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 284) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 285) 	if (ocu_max_len <= 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 286) 		return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 287) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 288) 	if (UDF_SB(sb)->s_nls_map)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 289) 		conv_f = UDF_SB(sb)->s_nls_map->char2uni;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 290) 	else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 291) 		conv_f = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 292) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 293) 	memset(ocu, 0, ocu_max_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 294) 	ocu[0] = 8;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 295) 	max_val = 0xff;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 296) 	u_ch = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 297) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 298) try_again:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 299) 	u_len = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 300) 	for (i = 0; i < str_len; i += len) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 301) 		/* Name didn't fit? */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 302) 		if (u_len + u_ch > ocu_max_len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 303) 			return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 304) 		if (conv_f) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 305) 			wchar_t wchar;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 306) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 307) 			len = conv_f(&str_i[i], str_len - i, &wchar);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 308) 			if (len > 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 309) 				uni_char = wchar;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 310) 		} else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 311) 			len = utf8_to_utf32(&str_i[i], str_len - i,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 312) 					    &uni_char);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 313) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 314) 		/* Invalid character, deal with it */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 315) 		if (len <= 0 || uni_char > UNICODE_MAX) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 316) 			len = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 317) 			uni_char = '?';
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 318) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 319) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 320) 		if (uni_char > max_val) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 321) 			unicode_t c;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 322) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 323) 			if (max_val == 0xff) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 324) 				max_val = 0xffff;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 325) 				ocu[0] = 0x10;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 326) 				u_ch = 2;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 327) 				goto try_again;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 328) 			}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 329) 			/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 330) 			 * Use UTF-16 encoding for chars outside we
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 331) 			 * cannot encode directly.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 332) 			 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 333) 			if (u_len + 2 * u_ch > ocu_max_len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 334) 				return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 335) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 336) 			uni_char -= PLANE_SIZE;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 337) 			c = SURROGATE_PAIR |
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 338) 			    ((uni_char >> SURROGATE_CHAR_BITS) &
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 339) 			     SURROGATE_CHAR_MASK);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 340) 			ocu[u_len++] = (uint8_t)(c >> 8);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 341) 			ocu[u_len++] = (uint8_t)(c & 0xff);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 342) 			uni_char = SURROGATE_PAIR | SURROGATE_LOW |
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 343) 					(uni_char & SURROGATE_CHAR_MASK);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 344) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 345) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 346) 		if (max_val == 0xffff)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 347) 			ocu[u_len++] = (uint8_t)(uni_char >> 8);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 348) 		ocu[u_len++] = (uint8_t)(uni_char & 0xff);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 349) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 350) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 351) 	return u_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 352) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 353) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 354) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 355)  * Convert CS0 dstring to output charset. Warning: This function may truncate
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 356)  * input string if it is too long as it is used for informational strings only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 357)  * and it is better to truncate the string than to refuse mounting a media.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 358)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 359) int udf_dstrCS0toChar(struct super_block *sb, uint8_t *utf_o, int o_len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 360) 		      const uint8_t *ocu_i, int i_len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 361) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 362) 	int s_len = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 363) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 364) 	if (i_len > 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 365) 		s_len = ocu_i[i_len - 1];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 366) 		if (s_len >= i_len) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 367) 			pr_warn("incorrect dstring lengths (%d/%d),"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 368) 				" truncating\n", s_len, i_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 369) 			s_len = i_len - 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 370) 			/* 2-byte encoding? Need to round properly... */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 371) 			if (ocu_i[0] == 16)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 372) 				s_len -= (s_len - 1) & 2;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 373) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 374) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 375) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 376) 	return udf_name_from_CS0(sb, utf_o, o_len, ocu_i, s_len, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 377) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 378) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 379) int udf_get_filename(struct super_block *sb, const uint8_t *sname, int slen,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 380) 		     uint8_t *dname, int dlen)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 381) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 382) 	int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 383) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 384) 	if (!slen)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 385) 		return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 386) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 387) 	if (dlen <= 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 388) 		return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 389) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 390) 	ret = udf_name_from_CS0(sb, dname, dlen, sname, slen, 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 391) 	/* Zero length filename isn't valid... */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 392) 	if (ret == 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 393) 		ret = -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 394) 	return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 395) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 396) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 397) int udf_put_filename(struct super_block *sb, const uint8_t *sname, int slen,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 398) 		     uint8_t *dname, int dlen)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 399) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 400) 	return udf_name_to_CS0(sb, dname, dlen, sname, slen);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 401) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 402)