[people/ms/u-boot.git] / drivers / usb / gadget / usbstring.c

/*
 * Copyright (C) 2003 David Brownell
 *
 * SPDX-License-Identifier:	LGPL-2.1+
 *
 * Ported to U-boot by: Thomas Smits <ts.smits@gmail.com> and
 *                      Remy Bohmer <linux@bohmer.net>
 */

#include <common.h>
#include <asm/errno.h>
#include <linux/usb/ch9.h>
#include <linux/usb/gadget.h>

#include <asm/unaligned.h>


static int utf8_to_utf16le(const char *s, __le16 *cp, unsigned len)
{
	int	count = 0;
	u8	c;
	u16	uchar;

	/*
	 * this insists on correct encodings, though not minimal ones.
	 * BUT it currently rejects legit 4-byte UTF-8 code points,
	 * which need surrogate pairs.  (Unicode 3.1 can use them.)
	 */
	while (len != 0 && (c = (u8) *s++) != 0) {
		if ((c & 0x80)) {
			/*
			 * 2-byte sequence:
			 * 00000yyyyyxxxxxx = 110yyyyy 10xxxxxx
			 */
			if ((c & 0xe0) == 0xc0) {
				uchar = (c & 0x1f) << 6;

				c = (u8) *s++;
				if ((c & 0xc0) != 0x80)
					goto fail;
				c &= 0x3f;
				uchar |= c;

			/*
			 * 3-byte sequence (most CJKV characters):
			 * zzzzyyyyyyxxxxxx = 1110zzzz 10yyyyyy 10xxxxxx
			 */
			} else if ((c & 0xf0) == 0xe0) {
				uchar = (c & 0x0f) << 12;

				c = (u8) *s++;
				if ((c & 0xc0) != 0x80)
					goto fail;
				c &= 0x3f;
				uchar |= c << 6;

				c = (u8) *s++;
				if ((c & 0xc0) != 0x80)
					goto fail;
				c &= 0x3f;
				uchar |= c;

				/* no bogus surrogates */
				if (0xd800 <= uchar && uchar <= 0xdfff)
					goto fail;

			/*
			 * 4-byte sequence (surrogate pairs, currently rare):
			 * 11101110wwwwzzzzyy + 110111yyyyxxxxxx
			 *     = 11110uuu 10uuzzzz 10yyyyyy 10xxxxxx
			 * (uuuuu = wwww + 1)
			 * FIXME accept the surrogate code points (only)
			 */
			} else
				goto fail;
		} else
			uchar = c;
		put_unaligned_le16(uchar, cp++);
		count++;
		len--;
	}
	return count;
fail:
	return -1;
}


/**
 * usb_gadget_get_string - fill out a string descriptor
 * @table: of c strings encoded using UTF-8
 * @id: string id, from low byte of wValue in get string descriptor
 * @buf: at least 256 bytes
 *
 * Finds the UTF-8 string matching the ID, and converts it into a
 * string descriptor in utf16-le.
 * Returns length of descriptor (always even) or negative errno
 *
 * If your driver needs stings in multiple languages, you'll probably
 * "switch (wIndex) { ... }"  in your ep0 string descriptor logic,
 * using this routine after choosing which set of UTF-8 strings to use.
 * Note that US-ASCII is a strict subset of UTF-8; any string bytes with
 * the eighth bit set will be multibyte UTF-8 characters, not ISO-8859/1
 * characters (which are also widely used in C strings).
 */
int
usb_gadget_get_string(struct usb_gadget_strings *table, int id, u8 *buf)
{
	struct usb_string	*s;
	int			len;

	if (!table)
		return -EINVAL;

	/* descriptor 0 has the language id */
	if (id == 0) {
		buf[0] = 4;
		buf[1] = USB_DT_STRING;
		buf[2] = (u8) table->language;
		buf[3] = (u8) (table->language >> 8);
		return 4;
	}
	for (s = table->strings; s && s->s; s++)
		if (s->id == id)
			break;

	/* unrecognized: stall. */
	if (!s || !s->s)
		return -EINVAL;

	/* string descriptors have length, tag, then UTF16-LE text */
	len = min((size_t) 126, strlen(s->s));
	memset(buf + 2, 0, 2 * len);	/* zero all the bytes */
	len = utf8_to_utf16le(s->s, (__le16 *)&buf[2], len);
	if (len < 0)
		return -EINVAL;
	buf[0] = (len + 1) * 2;
	buf[1] = USB_DT_STRING;
	return buf[0];
}
Commit	Line	Data
23cd1385 RB	1	/*
	2	* Copyright (C) 2003 David Brownell
	3	*
eee479cf	4	* SPDX-License-Identifier: LGPL-2.1+
23cd1385 RB	5	*
	6	* Ported to U-boot by: Thomas Smits <ts.smits@gmail.com> and
	7	* Remy Bohmer <linux@bohmer.net>
	8	*/
	9
	10	#include <common.h>
	11	#include <asm/errno.h>
	12	#include <linux/usb/ch9.h>
	13	#include <linux/usb/gadget.h>
	14
	15	#include <asm/unaligned.h>
	16
	17
	18	static int utf8_to_utf16le(const char s, __le16 cp, unsigned len)
	19	{
	20	int count = 0;
	21	u8 c;
	22	u16 uchar;
	23
6142e0ae VK	24	/*
6142e0ae VK	25	* this insists on correct encodings, though not minimal ones.
23cd1385 RB	26	* BUT it currently rejects legit 4-byte UTF-8 code points,
	27	* which need surrogate pairs. (Unicode 3.1 can use them.)
	28	*/
	29	while (len != 0 && (c = (u8) *s++) != 0) {
	30	if ((c & 0x80)) {
6142e0ae VK	31	/*
	32	* 2-byte sequence:
	33	* 00000yyyyyxxxxxx = 110yyyyy 10xxxxxx
	34	*/
23cd1385 RB	35	if ((c & 0xe0) == 0xc0) {
	36	uchar = (c & 0x1f) << 6;
	37
	38	c = (u8) *s++;
	39	if ((c & 0xc0) != 0x80)
	40	goto fail;
	41	c &= 0x3f;
	42	uchar \|= c;
	43
6142e0ae VK	44	/*
	45	* 3-byte sequence (most CJKV characters):
	46	* zzzzyyyyyyxxxxxx = 1110zzzz 10yyyyyy 10xxxxxx
	47	*/
23cd1385 RB	48	} else if ((c & 0xf0) == 0xe0) {
	49	uchar = (c & 0x0f) << 12;
	50
	51	c = (u8) *s++;
	52	if ((c & 0xc0) != 0x80)
	53	goto fail;
	54	c &= 0x3f;
	55	uchar \|= c << 6;
	56
	57	c = (u8) *s++;
	58	if ((c & 0xc0) != 0x80)
	59	goto fail;
	60	c &= 0x3f;
	61	uchar \|= c;
	62
	63	/* no bogus surrogates */
	64	if (0xd800 <= uchar && uchar <= 0xdfff)
	65	goto fail;
	66
6142e0ae VK	67	/*
	68	* 4-byte sequence (surrogate pairs, currently rare):
	69	* 11101110wwwwzzzzyy + 110111yyyyxxxxxx
	70	* = 11110uuu 10uuzzzz 10yyyyyy 10xxxxxx
	71	* (uuuuu = wwww + 1)
	72	* FIXME accept the surrogate code points (only)
	73	*/
23cd1385 RB	74	} else
	75	goto fail;
	76	} else
	77	uchar = c;
	78	put_unaligned_le16(uchar, cp++);
	79	count++;
	80	len--;
	81	}
	82	return count;
	83	fail:
	84	return -1;
	85	}
	86
	87
	88	/**
	89	* usb_gadget_get_string - fill out a string descriptor
	90	* @table: of c strings encoded using UTF-8
	91	* @id: string id, from low byte of wValue in get string descriptor
	92	* @buf: at least 256 bytes
	93	*
	94	* Finds the UTF-8 string matching the ID, and converts it into a
	95	* string descriptor in utf16-le.
	96	* Returns length of descriptor (always even) or negative errno
	97	*
	98	* If your driver needs stings in multiple languages, you'll probably
	99	* "switch (wIndex) { ... }" in your ep0 string descriptor logic,
	100	* using this routine after choosing which set of UTF-8 strings to use.
	101	* Note that US-ASCII is a strict subset of UTF-8; any string bytes with
	102	* the eighth bit set will be multibyte UTF-8 characters, not ISO-8859/1
	103	* characters (which are also widely used in C strings).
	104	*/
	105	int
6142e0ae	106	usb_gadget_get_string(struct usb_gadget_strings table, int id, u8 buf)
23cd1385 RB	107	{
	108	struct usb_string *s;
	109	int len;
	110
52d45012 RH	111	if (!table)
	112	return -EINVAL;
	113
23cd1385 RB	114	/* descriptor 0 has the language id */
23cd1385 RB	115	if (id == 0) {
6142e0ae VK	116	buf[0] = 4;
	117	buf[1] = USB_DT_STRING;
	118	buf[2] = (u8) table->language;
	119	buf[3] = (u8) (table->language >> 8);
23cd1385 RB	120	return 4;
	121	}
	122	for (s = table->strings; s && s->s; s++)
	123	if (s->id == id)
	124	break;
	125
	126	/* unrecognized: stall. */
	127	if (!s \|\| !s->s)
	128	return -EINVAL;
	129
	130	/* string descriptors have length, tag, then UTF16-LE text */
6142e0ae VK	131	len = min((size_t) 126, strlen(s->s));
6142e0ae VK	132	memset(buf + 2, 0, 2 * len); /* zero all the bytes */
23cd1385 RB	133	len = utf8_to_utf16le(s->s, (__le16 *)&buf[2], len);
	134	if (len < 0)
	135	return -EINVAL;
6142e0ae VK	136	buf[0] = (len + 1) * 2;
	137	buf[1] = USB_DT_STRING;
	138	return buf[0];
23cd1385	139	}