aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/usb/gadget/usbstring.c
blob: 58c4d37d312a4ce40e487abeb36e45c34c3002fc (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
/*
 * Copyright (C) 2003 David Brownell
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU Lesser General Public License as published
 * by the Free Software Foundation; either version 2.1 of the License, or
 * (at your option) any later version.
 */

#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/string.h>
#include <linux/device.h>
#include <linux/init.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 (unlikely(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;

	/* 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];
}