USB: remove homegrown UTF conversion routine for gadgets

This patch (as1502) removes the UTF8-to-UTF16 conversion routine in
the USB gadget library and replaces it with a call to the equivalent
function in the NLS library.

The only downside worth noting is that the NLS library routine
requires the output buffer to be 16-bit aligned.  This is always true
in the gadget code, because the output buffer is always a
usb_request buffer being used to send a string descriptor.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

2 files changed, 5 insertions, 69 deletions

diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index b21cd376c11a..a11dbc85d08b 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -15,6 +15,7 @@
 
 menuconfig USB_GADGET
         tristate "USB Gadget Support"
+        select NLS
         help
            USB is a master/slave protocol, organized with one master
            host (such as a PC) controlling up to 127 peripheral devices.
diff --git a/drivers/usb/gadget/usbstring.c b/drivers/usb/gadget/usbstring.c
index 58c4d37d312a..4d25b9009edf 100644
--- a/drivers/usb/gadget/usbstring.c
+++ b/drivers/usb/gadget/usbstring.c
@@ -13,82 +13,17 @@
 #include <linux/string.h>
 #include <linux/device.h>
 #include <linux/init.h>
+#include <linux/nls.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
+ * @buf: at least 256 bytes, must be 16-bit aligned
  *
  * Finds the UTF-8 string matching the ID, and converts it into a
  * string descriptor in utf16-le.
@@ -125,8 +60,8 @@ usb_gadget_get_string (struct usb_gadget_strings *table, int id, u8 *buf)
 
         /* 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);
+        len = utf8s_to_utf16s(s->s, len, UTF16_LITTLE_ENDIAN,
+                        (wchar_t *) &buf[2], 126);
         if (len < 0)
                 return -EINVAL;
         buf [0] = (len + 1) * 2;