[1] unix2doschr()

 If a character cannot be converted to DOS code page,
 unix2doschr() returned `0'. As a result, unix2dosfn()
 was forced to return `0', so we saw a file which was
 composed of these characters as `Invalid argument'.
 To correct this, if a character can be converted to
 Unicode, unix2doschr() now returns `1' which is a magic
 number to make unix2dosfn() know that the character
 must be converted to `_'.

[2] unix2dosfn()
 The above-mentioned solution only works if a file
 has both of Unicode name and DOS code page name.
 Unicode name would not be recorded if file name
 can be settled within 11 bytes (DOS short name)
 and if no conversion from Unix charset to DOS code
 page has occurred. Thus, FreeBSD can create a file
 which has only short name, but there is no guarantee
 that the short name contains allways valid characters
 because we leave it to people by using mount_msdosfs(8)
 to select which conversion is used between DOS code
 page and unix charset.
 To avoid this, Unicode file name should be recorded
 unless a character is an ascii character. This is
 the way Windows XP do.

PR:		77074 [1]
MFC after:	1 week

1 files changed, 27 insertions, 10 deletions

diff --git a/sys/fs/msdosfs/msdosfs_conv.c b/sys/fs/msdosfs/msdosfs_conv.c
index 8010457..2da7723 100644
--- a/sys/fs/msdosfs/msdosfs_conv.c
+++ b/sys/fs/msdosfs/msdosfs_conv.c
@@ -560,7 +560,9 @@ unix2dosfn(un, dn, unlen, gen, pmp)
 	}
 
 	/*
-	 * Now convert it (this part is for extension)
+	 * Now convert it (this part is for extension).
+	 * As Windows XP do, if it's not ascii char,
+	 * this function should return 2 or 3, so that checkng out Unicode name.
 	 */
 	if (dp) {
 		if (dp1)
@@ -573,6 +575,8 @@ unix2dosfn(un, dn, unlen, gen, pmp)
 				dn[j] = c >> 8;
 				if (++j < 11) {
 					dn[j] = c;
+					if (conv != 3)
+						conv = 2;
 					continue;
 				} else {
 					conv = 3;
@@ -582,7 +586,7 @@ unix2dosfn(un, dn, unlen, gen, pmp)
 			} else {
 				dn[j] = c;
 			}
-			if (*(cp - 1) != dn[j] && conv != 3)
+			if (((dn[j] & 0x80) || *(cp - 1) != dn[j]) && conv != 3)
 				conv = 2;
 			if (dn[j] == 1) {
 				conv = 3;
@@ -610,6 +614,8 @@ unix2dosfn(un, dn, unlen, gen, pmp)
 			dn[j] = c >> 8;
 			if (++j < 8) {
 				dn[j] = c;
+				if (conv != 3)
+					conv = 2;
 				continue;
 			} else {
 				conv = 3;
@@ -619,7 +625,7 @@ unix2dosfn(un, dn, unlen, gen, pmp)
 		} else {
 			dn[j] = c;
 		}
-		if (*(un - 1) != dn[j] && conv != 3)
+		if (((dn[j] & 0x80) || *(un - 1) != dn[j]) && conv != 3)
 			conv = 2;
 		if (dn[j] == 1) {
 			conv = 3;
@@ -1048,22 +1054,23 @@ unix2doschr(const u_char **instr, size_t *ilen, struct msdosfsmount *pmp)
 	u_char c;
 	char *up, *outp, unicode[3], outbuf[3];
 	u_int16_t wc;
-	size_t len, ulen, olen;
+	size_t len, ucslen, unixlen, olen;
 
 	if (pmp->pm_flags & MSDOSFSMNT_KICONV && msdosfs_iconv) {
 		/*
 		 * to hide an invisible character, using a unicode filter
 		 */
-		ulen = 2;
+		ucslen = 2;
 		len = *ilen;
 		up = unicode;
 		msdosfs_iconv->convchr(pmp->pm_u2w, (const char **)instr,
-				     ilen, &up, &ulen);
+				     ilen, &up, &ucslen);
+		unixlen = len - *ilen;
 
 		/*
 		 * cannot be converted
 		 */
-		if (ulen == 2) {
+		if (unixlen == 0) {
 			(*ilen)--;
 			(*instr)++;
 			return (0);
@@ -1072,7 +1079,7 @@ unix2doschr(const u_char **instr, size_t *ilen, struct msdosfsmount *pmp)
 		/*
 		 * return magic number for ascii char
 		 */
-		if ((len - *ilen) == 1) {
+		if (unixlen == 1) {
 			c = *(*instr -1);
 			if (! (c & 0x80)) {
 				c = unix2dos[c];
@@ -1084,14 +1091,24 @@ unix2doschr(const u_char **instr, size_t *ilen, struct msdosfsmount *pmp)
 		/*
 		 * now convert using libiconv
 		 */
-		*instr -= len - *ilen;
-		*ilen = (int)len;
+		*instr -= unixlen;
+		*ilen = len;
 
 		olen = len = 2;
 		outp = outbuf;
 		msdosfs_iconv->convchr_case(pmp->pm_u2d, (const char **)instr,
 					  ilen, &outp, &olen, KICONV_FROM_UPPER);
 		len -= olen;
+
+		/*
+		 * cannot be converted, but has unicode char, should return magic number
+		 */
+		if (len == 0) {
+			(*ilen) -= unixlen;
+			(*instr) += unixlen;
+			return (1);
+		}
+
 		wc = 0;
 		while(len--)
 			wc |= (*(outp - len - 1) & 0xff) << (len << 3);