summaryrefslogtreecommitdiff
path: root/fs/ksmbd/unicode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ksmbd/unicode.c')
-rw-r--r--fs/ksmbd/unicode.c193
1 files changed, 132 insertions, 61 deletions
diff --git a/fs/ksmbd/unicode.c b/fs/ksmbd/unicode.c
index a0db699ddafd..33fc6d45c0f3 100644
--- a/fs/ksmbd/unicode.c
+++ b/fs/ksmbd/unicode.c
@@ -15,45 +15,9 @@
#include "smb_common.h"
/*
- * smb_utf16_bytes() - how long will a string be after conversion?
- * @from: pointer to input string
- * @maxbytes: don't go past this many bytes of input string
- * @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)
-{
- int i;
- int charlen, outlen = 0;
- int maxwords = maxbytes / 2;
- char tmp[NLS_MAX_CHARSET_SIZE];
- __u16 ftmp;
-
- for (i = 0; i < maxwords; i++) {
- ftmp = get_unaligned_le16(&from[i]);
- if (ftmp == 0)
- break;
-
- charlen = codepage->uni2char(ftmp, tmp, NLS_MAX_CHARSET_SIZE);
- if (charlen > 0)
- outlen += charlen;
- else
- outlen++;
- }
-
- return outlen;
-}
-
-/*
* cifs_mapchar() - convert a host-endian char to proper char in codepage
* @target: where converted character should be copied
- * @src_char: 2 byte host-endian source character
+ * @from: host-endian source string
* @cp: codepage to which character should be converted
* @mapchar: should character be mapped according to mapchars mount option?
*
@@ -64,10 +28,13 @@ static int smb_utf16_bytes(const __le16 *from, int maxbytes,
* Return: string length after conversion
*/
static int
-cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp,
+cifs_mapchar(char *target, const __u16 *from, const struct nls_table *cp,
bool mapchar)
{
int len = 1;
+ __u16 src_char;
+
+ src_char = *from;
if (!mapchar)
goto cp_convert;
@@ -105,30 +72,66 @@ out:
cp_convert:
len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE);
- if (len <= 0) {
- *target = '?';
- len = 1;
- }
+ if (len <= 0)
+ goto surrogate_pair;
+
+ goto out;
+
+surrogate_pair:
+ /* convert SURROGATE_PAIR and IVS */
+ if (strcmp(cp->charset, "utf8"))
+ goto unknown;
+ len = utf16s_to_utf8s(from, 3, UTF16_LITTLE_ENDIAN, target, 6);
+ if (len <= 0)
+ goto unknown;
+ return len;
+unknown:
+ *target = '?';
+ len = 1;
goto out;
}
/*
- * is_char_allowed() - check for valid character
- * @ch: input character to be checked
+ * 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: 1 if char is allowed, otherwise 0
+ * Return: string length after conversion
*/
-static inline int is_char_allowed(char *ch)
+static int smb_utf16_bytes(const __le16 *from, int maxbytes,
+ const struct nls_table *codepage)
{
- /* check for control chars, wildcards etc. */
- if (!(*ch & 0x80) &&
- (*ch <= 0x1f ||
- *ch == '?' || *ch == '"' || *ch == '<' ||
- *ch == '>' || *ch == '|'))
- return 0;
-
- return 1;
+ int i, j;
+ int charlen, outlen = 0;
+ int maxwords = maxbytes / 2;
+ char tmp[NLS_MAX_CHARSET_SIZE];
+ __u16 ftmp[3];
+
+ for (i = 0; i < maxwords; i++) {
+ ftmp[0] = get_unaligned_le16(&from[i]);
+ if (ftmp[0] == 0)
+ break;
+ for (j = 1; j <= 2; j++) {
+ if (i + j < maxwords)
+ ftmp[j] = get_unaligned_le16(&from[i + j]);
+ else
+ ftmp[j] = 0;
+ }
+
+ charlen = cifs_mapchar(tmp, ftmp, codepage, 0);
+ if (charlen > 0)
+ outlen += charlen;
+ else
+ outlen++;
+ }
+
+ return outlen;
}
/*
@@ -158,12 +161,12 @@ static inline int is_char_allowed(char *ch)
static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
const struct nls_table *codepage, bool mapchar)
{
- int i, charlen, safelen;
+ int i, j, charlen, safelen;
int outlen = 0;
int nullsize = nls_nullsize(codepage);
int fromwords = fromlen / 2;
char tmp[NLS_MAX_CHARSET_SIZE];
- __u16 ftmp;
+ __u16 ftmp[3]; /* ftmp[3] = 3array x 2bytes = 6bytes UTF-16 */
/*
* because the chars can be of varying widths, we need to take care
@@ -174,9 +177,15 @@ static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize);
for (i = 0; i < fromwords; i++) {
- ftmp = get_unaligned_le16(&from[i]);
- if (ftmp == 0)
+ ftmp[0] = get_unaligned_le16(&from[i]);
+ if (ftmp[0] == 0)
break;
+ for (j = 1; j <= 2; j++) {
+ if (i + j < fromwords)
+ ftmp[j] = get_unaligned_le16(&from[i + j]);
+ else
+ ftmp[j] = 0;
+ }
/*
* check to see if converting this character might make the
@@ -191,6 +200,19 @@ static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
/* put converted char into 'to' buffer */
charlen = cifs_mapchar(&to[outlen], ftmp, codepage, mapchar);
outlen += charlen;
+
+ /*
+ * charlen (=bytes of UTF-8 for 1 character)
+ * 4bytes UTF-8(surrogate pair) is charlen=4
+ * (4bytes UTF-16 code)
+ * 7-8bytes UTF-8(IVS) is charlen=3+4 or 4+4
+ * (2 UTF-8 pairs divided to 2 UTF-16 pairs)
+ */
+ if (charlen == 4)
+ i++;
+ else if (charlen >= 5)
+ /* 5-6bytes UTF-8 */
+ i += 2;
}
/* properly null-terminate string */
@@ -325,6 +347,9 @@ int smbConvertToUTF16(__le16 *target, const char *source, int srclen,
char src_char;
__le16 dst_char;
wchar_t tmp;
+ wchar_t wchar_to[6]; /* UTF-16 */
+ int ret;
+ unicode_t u;
if (!mapchars)
return smb_strtoUTF16(target, source, srclen, cp);
@@ -367,11 +392,57 @@ int smbConvertToUTF16(__le16 *target, const char *source, int srclen,
* if no match, use question mark, which at least in
* some cases serves as wild card
*/
- if (charlen < 1) {
- dst_char = cpu_to_le16(0x003f);
- charlen = 1;
+ if (charlen > 0)
+ goto ctoUTF16;
+
+ /* convert SURROGATE_PAIR */
+ if (strcmp(cp->charset, "utf8"))
+ goto unknown;
+ if (*(source + i) & 0x80) {
+ charlen = utf8_to_utf32(source + i, 6, &u);
+ if (charlen < 0)
+ goto unknown;
+ } else
+ goto unknown;
+ ret = utf8s_to_utf16s(source + i, charlen,
+ UTF16_LITTLE_ENDIAN,
+ wchar_to, 6);
+ if (ret < 0)
+ goto unknown;
+
+ i += charlen;
+ dst_char = cpu_to_le16(*wchar_to);
+ if (charlen <= 3)
+ /* 1-3bytes UTF-8 to 2bytes UTF-16 */
+ put_unaligned(dst_char, &target[j]);
+ else if (charlen == 4) {
+ /*
+ * 4bytes UTF-8(surrogate pair) to 4bytes UTF-16
+ * 7-8bytes UTF-8(IVS) divided to 2 UTF-16
+ * (charlen=3+4 or 4+4)
+ */
+ put_unaligned(dst_char, &target[j]);
+ dst_char = cpu_to_le16(*(wchar_to + 1));
+ j++;
+ put_unaligned(dst_char, &target[j]);
+ } else if (charlen >= 5) {
+ /* 5-6bytes UTF-8 to 6bytes UTF-16 */
+ put_unaligned(dst_char, &target[j]);
+ dst_char = cpu_to_le16(*(wchar_to + 1));
+ j++;
+ put_unaligned(dst_char, &target[j]);
+ dst_char = cpu_to_le16(*(wchar_to + 2));
+ j++;
+ put_unaligned(dst_char, &target[j]);
}
+ continue;
+
+unknown:
+ dst_char = cpu_to_le16(0x003f);
+ charlen = 1;
}
+
+ctoUTF16:
/*
* character may take more than one byte in the source string,
* but will take exactly two bytes in the target string
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-28 06:14:57 +0000