hfsplus: fix decomposition of Hangul characters

Files created under macOS cannot be opened under linux if their names
contain Korean characters, and vice versa.

The Korean alphabet is special because its normalization is done without a
table. The module deals with it correctly when composing, but forgets
about it for the decomposition.

Fix this using the Hangul decomposition function provided in the Unicode
Standard. The code fits a bit awkwardly because it requires a buffer,
while all the other normalizations are returned as pointers to the
decomposition table. This is actually also a bug because reordering may
still be needed, but for now leave it as it is.

The patch will cause trouble for Hangul filenames already created by the
module in the past. This shouldn't really be concern because its main
purpose was always sharing with macOS. If a user actually needs to access
such a file the nodecompose mount option should be enough.

Link: http://lkml.kernel.org/r/20180717220951.p6qqrgautc4pxvzu@eaf
Signed-off-by: Ernesto A. Fernández <[e-mail]>
Reported-by: Ting-Chang Hou <[e-mail]>
Tested-by: Ting-Chang Hou <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

fs/hfsplus/unicode.c

···
 	return size;
 }
 
-/* Decomposes a single unicode character. */
-static inline u16 *decompose_unichar(wchar_t uc, int *size)
+/* Decomposes a non-Hangul unicode character. */
+static u16 *hfsplus_decompose_nonhangul(wchar_t uc, int *size)
 {
 	int off;
 
···
 	return hfsplus_decompose_table + (off / 4);
 }
 
+/*
+ * Try to decompose a unicode character as Hangul. Return 0 if @uc is not
+ * precomposed Hangul, otherwise return the length of the decomposition.
+ *
+ * This function was adapted from sample code from the Unicode Standard
+ * Annex #15: Unicode Normalization Forms, version 3.2.0.
+ *
+ * Copyright (C) 1991-2018 Unicode, Inc.  All rights reserved.  Distributed
+ * under the Terms of Use in http://www.unicode.org/copyright.html.
+ */
+static int hfsplus_try_decompose_hangul(wchar_t uc, u16 *result)
+{
+	int index;
+	int l, v, t;
+
+	index = uc - Hangul_SBase;
+	if (index < 0 || index >= Hangul_SCount)
+		return 0;
+
+	l = Hangul_LBase + index / Hangul_NCount;
+	v = Hangul_VBase + (index % Hangul_NCount) / Hangul_TCount;
+	t = Hangul_TBase + index % Hangul_TCount;
+
+	result[0] = l;
+	result[1] = v;
+	if (t != Hangul_TBase) {
+		result[2] = t;
+		return 3;
+	}
+	return 2;
+}
+
+/* Decomposes a single unicode character. */
+static u16 *decompose_unichar(wchar_t uc, int *size, u16 *hangul_buffer)
+{
+	u16 *result;
+
+	/* Hangul is handled separately */
+	result = hangul_buffer;
+	*size = hfsplus_try_decompose_hangul(uc, result);
+	if (*size == 0)
+		result = hfsplus_decompose_nonhangul(uc, size);
+	return result;
+}
+
 int hfsplus_asc2uni(struct super_block *sb,
 		    struct hfsplus_unistr *ustr, int max_unistr_len,
 		    const char *astr, int len)
···
 	int size, dsize, decompose;
 	u16 *dstr, outlen = 0;
 	wchar_t c;
+	u16 dhangul[3];
 
 	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
 	while (outlen < max_unistr_len && len > 0) {
 		size = asc2unichar(sb, astr, len, &c);
 
 		if (decompose)
-			dstr = decompose_unichar(c, &dsize);
+			dstr = decompose_unichar(c, &dsize, dhangul);
 		else
 			dstr = NULL;
 		if (dstr) {
···
 	unsigned long hash;
 	wchar_t c;
 	u16 c2;
+	u16 dhangul[3];
 
 	casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
 	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
···
 		len -= size;
 
 		if (decompose)
-			dstr = decompose_unichar(c, &dsize);
+			dstr = decompose_unichar(c, &dsize, dhangul);
 		else
 			dstr = NULL;
 		if (dstr) {
···
 	const char *astr1, *astr2;
 	u16 c1, c2;
 	wchar_t c;
+	u16 dhangul_1[3], dhangul_2[3];
 
 	casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
 	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
···
 			len1 -= size;
 
 			if (decompose)
-				dstr1 = decompose_unichar(c, &dsize1);
+				dstr1 = decompose_unichar(c, &dsize1,
+							  dhangul_1);
 			if (!decompose || !dstr1) {
 				c1 = c;
 				dstr1 = &c1;
···
 			len2 -= size;
 
 			if (decompose)
-				dstr2 = decompose_unichar(c, &dsize2);
+				dstr2 = decompose_unichar(c, &dsize2,
+							  dhangul_2);
 			if (!decompose || !dstr2) {
 				c2 = c;
 				dstr2 = &c2;