unicode patches for 5.17

This includes patches from Christoph Hellwig to split the large data
 tables of the unicode subsystem into a loadable module, which allow
 users to not have them around if case-insensitive filesystems are not to
 be used.  It also includes minor code fixes to unicode and its users,
 from the same author.
 
 There is a trivial conflict in the function encoding_show in
 fs/f2fs/sysfs.c reported by linux-next between commit
 
 84eab2a899 ("f2fs: replace snprintf in show functions with sysfs_emit")
 
 and commit a440943e68 ("unicode: remove the charset field from struct
 unicode_map").  from my tree.
 
 All the patches here have been on linux-next releases for the past
 months.
 
 Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE8jAUPq50yNjPBCi4QEuZqsMcppQFAmHeLp0ACgkQQEuZqsMc
 ppRWdhAAstuibIlhUj1Vae070P92oaxM/Azz3IgyVFWensJyQV1PvbtFQDhyKM4w
 M3tQ45eK49vVHn+JpLHbiAdZV66rD/sMSsruCVIf/8KNVDisOBQtFar5yxVr0Ion
 AOMoG6/Xrk8BZlZH62fhtJGtu/EFmeFoGVdC81NdTSroe9G+26we3IULwHSE1lNH
 XMJFCgU6otuLDOna16U7kL77Tu7GXRJcQe1+2nRJ+u6Agxy2xTo/s4FHuxzRK0/e
 GsgO1scY6unWM23O6z+qJYazng2Zt3EOZtSGqU4TsvZwjUi2UtAYW1/vAQGc/q3Y
 hGxPYGgKC1VrXLfIcuyng7j0vFPtADbdHMbsJPoyy+Nz4znDJ81IAKAHMO1in3C8
 CHKjW+6InmXNye/uwdRt8Tx49jxUHmWUbQRT5FwMDpzC7MAL+DVdPpVVQgpLVM/H
 gW3YpBEk5qQvVdh8DWZVW3rT3SnMX/v0+u+76FsMHKYNJMNrCnP6vXpCPQl/Gyut
 ycgK7qVF3o/bgNBf072H3ZBZajTv7ePvacP4Wth7m9I2ykk+p4IjQLpTC5rJK0By
 VC1xS4im2VqiIWE9eE5y9cXU1oa/AfOcOF+7FZcxT13IL6hKTtd4+H4yKgdcNsyk
 7RjpGgjp+SU51/EilhEqMFgEe07CURxwGwhApizBSiTIOgZS96U=
 =4q9x
 -----END PGP SIGNATURE-----

Merge tag 'unicode-for-next-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/krisman/unicode

Pull unicode updates from Gabriel Krisman Bertazi:
 "This includes patches from Christoph Hellwig to split the large data
  tables of the unicode subsystem into a loadable module, which allow
  users to not have them around if case-insensitive filesystems are not
  to be used. It also includes minor code fixes to unicode and its
  users, from the same author.

  All the patches here have been on linux-next releases for the past
  months"

* tag 'unicode-for-next-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/krisman/unicode:
  unicode: only export internal symbols for the selftests
  unicode: Add utf8-data module
  unicode: cache the normalization tables in struct unicode_map
  unicode: move utf8cursor to utf8-selftest.c
  unicode: simplify utf8len
  unicode: remove the unused utf8{,n}age{min,max} functions
  unicode: pass a UNICODE_AGE() tripple to utf8_load
  unicode: mark the version field in struct unicode_map unsigned
  unicode: remove the charset field from struct unicode_map
  f2fs: simplify f2fs_sb_read_encoding
  ext4: simplify ext4_sb_read_encoding

fs/ext4/super.c

@@ -1966,29 +1966,22 @@ static const struct mount_opts {
 static const struct ext4_sb_encodings {
 	__u16 magic;
 	char *name;
-	char *version;
+	unsigned int version;
 } ext4_sb_encoding_map[] = {
-	{EXT4_ENC_UTF8_12_1, "utf8", "12.1.0"},
+	{EXT4_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)},
 };
 
-static int ext4_sb_read_encoding(const struct ext4_super_block *es,
+static const struct ext4_sb_encodings *
-				 const struct ext4_sb_encodings **encoding,
+ext4_sb_read_encoding(const struct ext4_super_block *es)
-				 __u16 *flags)
 {
 	__u16 magic = le16_to_cpu(es->s_encoding);
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(ext4_sb_encoding_map); i++)
 		if (magic == ext4_sb_encoding_map[i].magic)
-			break;
+			return &ext4_sb_encoding_map[i];
 
-	if (i >= ARRAY_SIZE(ext4_sb_encoding_map))
+	return NULL;
-		return -EINVAL;
-
-	*encoding = &ext4_sb_encoding_map[i];
-	*flags = le16_to_cpu(es->s_encoding_flags);
-
-	return 0;
 }
 #endif
 
@@ -4624,10 +4617,10 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	if (ext4_has_feature_casefold(sb) && !sb->s_encoding) {
 		const struct ext4_sb_encodings *encoding_info;
 		struct unicode_map *encoding;
-		__u16 encoding_flags;
+		__u16 encoding_flags = le16_to_cpu(es->s_encoding_flags);
 
-		if (ext4_sb_read_encoding(es, &encoding_info,
+		encoding_info = ext4_sb_read_encoding(es);
-					  &encoding_flags)) {
+		if (!encoding_info) {
 			ext4_msg(sb, KERN_ERR,
 				 "Encoding requested by superblock is unknown");
 			goto failed_mount;
@@ -4636,15 +4629,21 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		encoding = utf8_load(encoding_info->version);
 		if (IS_ERR(encoding)) {
 			ext4_msg(sb, KERN_ERR,
-				 "can't mount with superblock charset: %s-%s "
+				 "can't mount with superblock charset: %s-%u.%u.%u "
 				 "not supported by the kernel. flags: 0x%x.",
-				 encoding_info->name, encoding_info->version,
+				 encoding_info->name,
+				 unicode_major(encoding_info->version),
+				 unicode_minor(encoding_info->version),
+				 unicode_rev(encoding_info->version),
 				 encoding_flags);
 			goto failed_mount;
 		}
 		ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: "
-			 "%s-%s with flags 0x%hx", encoding_info->name,
+			 "%s-%u.%u.%u with flags 0x%hx", encoding_info->name,
-			 encoding_info->version?:"\b", encoding_flags);
+			 unicode_major(encoding_info->version),
+			 unicode_minor(encoding_info->version),
+			 unicode_rev(encoding_info->version),
+			 encoding_flags);
 
 		sb->s_encoding = encoding;
 		sb->s_encoding_flags = encoding_flags;

fs/f2fs/super.c

@@ -260,29 +260,22 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...)
 static const struct f2fs_sb_encodings {
 	__u16 magic;
 	char *name;
-	char *version;
+	unsigned int version;
 } f2fs_sb_encoding_map[] = {
-	{F2FS_ENC_UTF8_12_1, "utf8", "12.1.0"},
+	{F2FS_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)},
 };
 
-static int f2fs_sb_read_encoding(const struct f2fs_super_block *sb,
+static const struct f2fs_sb_encodings *
-				 const struct f2fs_sb_encodings **encoding,
+f2fs_sb_read_encoding(const struct f2fs_super_block *sb)
-				 __u16 *flags)
 {
 	__u16 magic = le16_to_cpu(sb->s_encoding);
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(f2fs_sb_encoding_map); i++)
 		if (magic == f2fs_sb_encoding_map[i].magic)
-			break;
+			return &f2fs_sb_encoding_map[i];
 
-	if (i >= ARRAY_SIZE(f2fs_sb_encoding_map))
+	return NULL;
-		return -EINVAL;
-
-	*encoding = &f2fs_sb_encoding_map[i];
-	*flags = le16_to_cpu(sb->s_encoding_flags);
-
-	return 0;
 }
 
 struct kmem_cache *f2fs_cf_name_slab;
@@ -3874,25 +3867,32 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 		struct unicode_map *encoding;
 		__u16 encoding_flags;
 
-		if (f2fs_sb_read_encoding(sbi->raw_super, &encoding_info,
+		encoding_info = f2fs_sb_read_encoding(sbi->raw_super);
-					  &encoding_flags)) {
+		if (!encoding_info) {
 			f2fs_err(sbi,
 				 "Encoding requested by superblock is unknown");
 			return -EINVAL;
 		}
 
+		encoding_flags = le16_to_cpu(sbi->raw_super->s_encoding_flags);
 		encoding = utf8_load(encoding_info->version);
 		if (IS_ERR(encoding)) {
 			f2fs_err(sbi,
-				 "can't mount with superblock charset: %s-%s "
+				 "can't mount with superblock charset: %s-%u.%u.%u "
 				 "not supported by the kernel. flags: 0x%x.",
-				 encoding_info->name, encoding_info->version,
+				 encoding_info->name,
+				 unicode_major(encoding_info->version),
+				 unicode_minor(encoding_info->version),
+				 unicode_rev(encoding_info->version),
 				 encoding_flags);
 			return PTR_ERR(encoding);
 		}
 		f2fs_info(sbi, "Using encoding defined by superblock: "
-			 "%s-%s with flags 0x%hx", encoding_info->name,
+			 "%s-%u.%u.%u with flags 0x%hx", encoding_info->name,
-			 encoding_info->version?:"\b", encoding_flags);
+			 unicode_major(encoding_info->version),
+			 unicode_minor(encoding_info->version),
+			 unicode_rev(encoding_info->version),
+			 encoding_flags);
 
 		sbi->sb->s_encoding = encoding;
 		sbi->sb->s_encoding_flags = encoding_flags;

fs/f2fs/sysfs.c

@@ -196,8 +196,7 @@ static ssize_t encoding_show(struct f2fs_attr *a,
 	struct super_block *sb = sbi->sb;
 
 	if (f2fs_sb_has_casefold(sbi))
-		return sysfs_emit(buf, "%s (%d.%d.%d)\n",
+		return sysfs_emit(buf, "UTF-8 (%d.%d.%d)\n",
-			sb->s_encoding->charset,
 			(sb->s_encoding->version >> 16) & 0xff,
 			(sb->s_encoding->version >> 8) & 0xff,
 			sb->s_encoding->version & 0xff);

fs/unicode/Kconfig

@@ -8,7 +8,16 @@ config UNICODE
 	  Say Y here to enable UTF-8 NFD normalization and NFD+CF casefolding
 	  support.
 
+config UNICODE_UTF8_DATA
+	tristate "UTF-8 normalization and casefolding tables"
+	depends on UNICODE
+	default UNICODE
+	help
+	  This contains a large table of case foldings, which can be loaded as
+	  a separate module if you say M here.  To be on the safe side stick
+	  to the default of Y.  Saying N here makes no sense, if you do not want
+	  utf8 casefolding support, disable CONFIG_UNICODE instead.
+
 config UNICODE_NORMALIZATION_SELFTEST
 	tristate "Test UTF-8 normalization support"
-	depends on UNICODE
+	depends on UNICODE_UTF8_DATA
-	default n

fs/unicode/Makefile

@@ -2,14 +2,15 @@
 
 obj-$(CONFIG_UNICODE) += unicode.o
 obj-$(CONFIG_UNICODE_NORMALIZATION_SELFTEST) += utf8-selftest.o
+obj-$(CONFIG_UNICODE_UTF8_DATA) += utf8data.o
 
 unicode-y := utf8-norm.o utf8-core.o
 
-$(obj)/utf8-norm.o: $(obj)/utf8data.h
+$(obj)/utf8-data.o: $(obj)/utf8data.c
 
-# In the normal build, the checked-in utf8data.h is just shipped.
+# In the normal build, the checked-in utf8data.c is just shipped.
 #
-# To generate utf8data.h from UCD, put *.txt files in this directory
+# To generate utf8data.c from UCD, put *.txt files in this directory
 # and pass REGENERATE_UTF8DATA=1 from the command line.
 ifdef REGENERATE_UTF8DATA
 
@@ -24,15 +25,15 @@ quiet_cmd_utf8data = GEN     $@
 		-t $(srctree)/$(src)/NormalizationTest.txt \
 		-o $@
 
-$(obj)/utf8data.h: $(obj)/mkutf8data $(filter %.txt, $(cmd_utf8data)) FORCE
+$(obj)/utf8data.c: $(obj)/mkutf8data $(filter %.txt, $(cmd_utf8data)) FORCE
 	$(call if_changed,utf8data)
 
 else
 
-$(obj)/utf8data.h: $(src)/utf8data.h_shipped FORCE
+$(obj)/utf8data.c: $(src)/utf8data.c_shipped FORCE
 	$(call if_changed,shipped)
 
 endif
 
-targets += utf8data.h
+targets += utf8data.c
 hostprogs += mkutf8data

fs/unicode/mkutf8data.c

@@ -3287,12 +3287,10 @@ static void write_file(void)
 		open_fail(utf8_name, errno);
 
 	fprintf(file, "/* This file is generated code, do not edit. */\n");
-	fprintf(file, "#ifndef __INCLUDED_FROM_UTF8NORM_C__\n");
-	fprintf(file, "#error Only nls_utf8-norm.c should include this file.\n");
-	fprintf(file, "#endif\n");
 	fprintf(file, "\n");
-	fprintf(file, "static const unsigned int utf8vers = %#x;\n",
+	fprintf(file, "#include <linux/module.h>\n");
-		unicode_maxage);
+	fprintf(file, "#include <linux/kernel.h>\n");
+	fprintf(file, "#include \"utf8n.h\"\n");
 	fprintf(file, "\n");
 	fprintf(file, "static const unsigned int utf8agetab[] = {\n");
 	for (i = 0; i != ages_count; i++)
@@ -3339,6 +3337,22 @@ static void write_file(void)
 		fprintf(file, "\n");
 	}
 	fprintf(file, "};\n");
+	fprintf(file, "\n");
+	fprintf(file, "struct utf8data_table utf8_data_table = {\n");
+	fprintf(file, "\t.utf8agetab = utf8agetab,\n");
+	fprintf(file, "\t.utf8agetab_size = ARRAY_SIZE(utf8agetab),\n");
+	fprintf(file, "\n");
+	fprintf(file, "\t.utf8nfdicfdata = utf8nfdicfdata,\n");
+	fprintf(file, "\t.utf8nfdicfdata_size = ARRAY_SIZE(utf8nfdicfdata),\n");
+	fprintf(file, "\n");
+	fprintf(file, "\t.utf8nfdidata = utf8nfdidata,\n");
+	fprintf(file, "\t.utf8nfdidata_size = ARRAY_SIZE(utf8nfdidata),\n");
+	fprintf(file, "\n");
+	fprintf(file, "\t.utf8data = utf8data,\n");
+	fprintf(file, "};\n");
+	fprintf(file, "EXPORT_SYMBOL_GPL(utf8_data_table);");
+	fprintf(file, "\n");
+	fprintf(file, "MODULE_LICENSE(\"GPL v2\");\n");
 	fclose(file);
 }
 

fs/unicode/utf8-core.c

@@ -5,16 +5,13 @@
 #include <linux/slab.h>
 #include <linux/parser.h>
 #include <linux/errno.h>
-#include <linux/unicode.h>
 #include <linux/stringhash.h>
 
 #include "utf8n.h"
 
 int utf8_validate(const struct unicode_map *um, const struct qstr *str)
 {
-	const struct utf8data *data = utf8nfdi(um->version);
+	if (utf8nlen(um, UTF8_NFDI, str->name, str->len) < 0)
-
-	if (utf8nlen(data, str->name, str->len) < 0)
 		return -1;
 	return 0;
 }
@@ -23,14 +20,13 @@ EXPORT_SYMBOL(utf8_validate);
 int utf8_strncmp(const struct unicode_map *um,
 		 const struct qstr *s1, const struct qstr *s2)
 {
-	const struct utf8data *data = utf8nfdi(um->version);
 	struct utf8cursor cur1, cur2;
 	int c1, c2;
 
-	if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0)
+	if (utf8ncursor(&cur1, um, UTF8_NFDI, s1->name, s1->len) < 0)
 		return -EINVAL;
 
-	if (utf8ncursor(&cur2, data, s2->name, s2->len) < 0)
+	if (utf8ncursor(&cur2, um, UTF8_NFDI, s2->name, s2->len) < 0)
 		return -EINVAL;
 
 	do {
@@ -50,14 +46,13 @@ EXPORT_SYMBOL(utf8_strncmp);
 int utf8_strncasecmp(const struct unicode_map *um,
 		     const struct qstr *s1, const struct qstr *s2)
 {
-	const struct utf8data *data = utf8nfdicf(um->version);
 	struct utf8cursor cur1, cur2;
 	int c1, c2;
 
-	if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0)
+	if (utf8ncursor(&cur1, um, UTF8_NFDICF, s1->name, s1->len) < 0)
 		return -EINVAL;
 
-	if (utf8ncursor(&cur2, data, s2->name, s2->len) < 0)
+	if (utf8ncursor(&cur2, um, UTF8_NFDICF, s2->name, s2->len) < 0)
 		return -EINVAL;
 
 	do {
@@ -81,12 +76,11 @@ int utf8_strncasecmp_folded(const struct unicode_map *um,
 			    const struct qstr *cf,
 			    const struct qstr *s1)
 {
-	const struct utf8data *data = utf8nfdicf(um->version);
 	struct utf8cursor cur1;
 	int c1, c2;
 	int i = 0;
 
-	if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0)
+	if (utf8ncursor(&cur1, um, UTF8_NFDICF, s1->name, s1->len) < 0)
 		return -EINVAL;
 
 	do {
@@ -105,11 +99,10 @@ EXPORT_SYMBOL(utf8_strncasecmp_folded);
 int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 		  unsigned char *dest, size_t dlen)
 {
-	const struct utf8data *data = utf8nfdicf(um->version);
 	struct utf8cursor cur;
 	size_t nlen = 0;
 
-	if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+	if (utf8ncursor(&cur, um, UTF8_NFDICF, str->name, str->len) < 0)
 		return -EINVAL;
 
 	for (nlen = 0; nlen < dlen; nlen++) {
@@ -128,12 +121,11 @@ EXPORT_SYMBOL(utf8_casefold);
 int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
 		       struct qstr *str)
 {
-	const struct utf8data *data = utf8nfdicf(um->version);
 	struct utf8cursor cur;
 	int c;
 	unsigned long hash = init_name_hash(salt);
 
-	if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+	if (utf8ncursor(&cur, um, UTF8_NFDICF, str->name, str->len) < 0)
 		return -EINVAL;
 
 	while ((c = utf8byte(&cur))) {
@@ -149,11 +141,10 @@ EXPORT_SYMBOL(utf8_casefold_hash);
 int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 		   unsigned char *dest, size_t dlen)
 {
-	const struct utf8data *data = utf8nfdi(um->version);
 	struct utf8cursor cur;
 	ssize_t nlen = 0;
 
-	if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+	if (utf8ncursor(&cur, um, UTF8_NFDI, str->name, str->len) < 0)
 		return -EINVAL;
 
 	for (nlen = 0; nlen < dlen; nlen++) {
@@ -167,69 +158,59 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 	}
 	return -EINVAL;
 }
-
 EXPORT_SYMBOL(utf8_normalize);
 
-static int utf8_parse_version(const char *version, unsigned int *maj,
+static const struct utf8data *find_table_version(const struct utf8data *table,
-			      unsigned int *min, unsigned int *rev)
+		size_t nr_entries, unsigned int version)
 {
-	substring_t args[3];
+	size_t i = nr_entries - 1;
-	char version_string[12];
-	static const struct match_token token[] = {
-		{1, "%d.%d.%d"},
-		{0, NULL}
-	};
 
-	strncpy(version_string, version, sizeof(version_string));
+	while (version < table[i].maxage)
-
+		i--;
-	if (match_token(version_string, token, args) != 1)
+	if (version > table[i].maxage)
-		return -EINVAL;
+		return NULL;
-
+	return &table[i];
-	if (match_int(&args[0], maj) || match_int(&args[1], min) ||
-	    match_int(&args[2], rev))
-		return -EINVAL;
-
-	return 0;
 }
 
-struct unicode_map *utf8_load(const char *version)
+struct unicode_map *utf8_load(unsigned int version)
 {
-	struct unicode_map *um = NULL;
+	struct unicode_map *um;
-	int unicode_version;
-
-	if (version) {
-		unsigned int maj, min, rev;
-
-		if (utf8_parse_version(version, &maj, &min, &rev) < 0)
-			return ERR_PTR(-EINVAL);
-
-		if (!utf8version_is_supported(maj, min, rev))
-			return ERR_PTR(-EINVAL);
-
-		unicode_version = UNICODE_AGE(maj, min, rev);
-	} else {
-		unicode_version = utf8version_latest();
-		printk(KERN_WARNING"UTF-8 version not specified. "
-		       "Assuming latest supported version (%d.%d.%d).",
-		       (unicode_version >> 16) & 0xff,
-		       (unicode_version >> 8) & 0xff,
-		       (unicode_version & 0xff));
-	}
 
 	um = kzalloc(sizeof(struct unicode_map), GFP_KERNEL);
 	if (!um)
 		return ERR_PTR(-ENOMEM);
+	um->version = version;
 
-	um->charset = "UTF-8";
+	um->tables = symbol_request(utf8_data_table);
-	um->version = unicode_version;
+	if (!um->tables)
+		goto out_free_um;
 
+	if (!utf8version_is_supported(um, version))
+		goto out_symbol_put;
+	um->ntab[UTF8_NFDI] = find_table_version(um->tables->utf8nfdidata,
+			um->tables->utf8nfdidata_size, um->version);
+	if (!um->ntab[UTF8_NFDI])
+		goto out_symbol_put;
+	um->ntab[UTF8_NFDICF] = find_table_version(um->tables->utf8nfdicfdata,
+			um->tables->utf8nfdicfdata_size, um->version);
+	if (!um->ntab[UTF8_NFDICF])
+		goto out_symbol_put;
 	return um;
+
+out_symbol_put:
+	symbol_put(um->tables);
+out_free_um:
+	kfree(um);
+	return ERR_PTR(-EINVAL);
 }
 EXPORT_SYMBOL(utf8_load);
 
 void utf8_unload(struct unicode_map *um)
 {
-	kfree(um);
+	if (um) {
+		symbol_put(utf8_data_table);
+		kfree(um);
+	}
 }
 EXPORT_SYMBOL(utf8_unload);
 

fs/unicode/utf8-norm.c

@@ -6,34 +6,17 @@
 
 #include "utf8n.h"
 
-struct utf8data {
+int utf8version_is_supported(const struct unicode_map *um, unsigned int version)
-	unsigned int maxage;
-	unsigned int offset;
-};
-
-#define __INCLUDED_FROM_UTF8NORM_C__
-#include "utf8data.h"
-#undef __INCLUDED_FROM_UTF8NORM_C__
-
-int utf8version_is_supported(u8 maj, u8 min, u8 rev)
 {
-	int i = ARRAY_SIZE(utf8agetab) - 1;
+	int i = um->tables->utf8agetab_size - 1;
-	unsigned int sb_utf8version = UNICODE_AGE(maj, min, rev);
 
-	while (i >= 0 && utf8agetab[i] != 0) {
+	while (i >= 0 && um->tables->utf8agetab[i] != 0) {
-		if (sb_utf8version == utf8agetab[i])
+		if (version == um->tables->utf8agetab[i])
 			return 1;
 		i--;
 	}
 	return 0;
 }
-EXPORT_SYMBOL(utf8version_is_supported);
-
-int utf8version_latest(void)
-{
-	return utf8vers;
-}
-EXPORT_SYMBOL(utf8version_latest);
 
 /*
  * UTF-8 valid ranges.
@@ -168,7 +151,7 @@ typedef const unsigned char utf8trie_t;
  * underlying datatype: unsigned char.
  *
  * leaf[0]: The unicode version, stored as a generation number that is
- *          an index into utf8agetab[].  With this we can filter code
+ *          an index into ->utf8agetab[].  With this we can filter code
  *          points based on the unicode version in which they were
  *          defined.  The CCC of a non-defined code point is 0.
  * leaf[1]: Canonical Combining Class. During normalization, we need
@@ -316,21 +299,19 @@ utf8hangul(const char *str, unsigned char *hangul)
  * is well-formed and corresponds to a known unicode code point.  The
  * shorthand for this will be "is valid UTF-8 unicode".
  */
-static utf8leaf_t *utf8nlookup(const struct utf8data *data,
+static utf8leaf_t *utf8nlookup(const struct unicode_map *um,
-			       unsigned char *hangul, const char *s, size_t len)
+		enum utf8_normalization n, unsigned char *hangul, const char *s,
+		size_t len)
 {
-	utf8trie_t	*trie = NULL;
+	utf8trie_t	*trie = um->tables->utf8data + um->ntab[n]->offset;
 	int		offlen;
 	int		offset;
 	int		mask;
 	int		node;
 
-	if (!data)
-		return NULL;
 	if (len == 0)
 		return NULL;
 
-	trie = utf8data + data->offset;
 	node = 1;
 	while (node) {
 		offlen = (*trie & OFFLEN) >> OFFLEN_SHIFT;
@@ -392,172 +373,29 @@ static utf8leaf_t *utf8nlookup(const struct utf8data *data,
  *
  * Forwards to utf8nlookup().
  */
-static utf8leaf_t *utf8lookup(const struct utf8data *data,
+static utf8leaf_t *utf8lookup(const struct unicode_map *um,
-			      unsigned char *hangul, const char *s)
+		enum utf8_normalization n, unsigned char *hangul, const char *s)
 {
-	return utf8nlookup(data, hangul, s, (size_t)-1);
+	return utf8nlookup(um, n, hangul, s, (size_t)-1);
 }
 
-/*
- * Maximum age of any character in s.
- * Return -1 if s is not valid UTF-8 unicode.
- * Return 0 if only non-assigned code points are used.
- */
-int utf8agemax(const struct utf8data *data, const char *s)
-{
-	utf8leaf_t	*leaf;
-	int		age = 0;
-	int		leaf_age;
-	unsigned char	hangul[UTF8HANGULLEAF];
-
-	if (!data)
-		return -1;
-
-	while (*s) {
-		leaf = utf8lookup(data, hangul, s);
-		if (!leaf)
-			return -1;
-
-		leaf_age = utf8agetab[LEAF_GEN(leaf)];
-		if (leaf_age <= data->maxage && leaf_age > age)
-			age = leaf_age;
-		s += utf8clen(s);
-	}
-	return age;
-}
-EXPORT_SYMBOL(utf8agemax);
-
-/*
- * Minimum age of any character in s.
- * Return -1 if s is not valid UTF-8 unicode.
- * Return 0 if non-assigned code points are used.
- */
-int utf8agemin(const struct utf8data *data, const char *s)
-{
-	utf8leaf_t	*leaf;
-	int		age;
-	int		leaf_age;
-	unsigned char	hangul[UTF8HANGULLEAF];
-
-	if (!data)
-		return -1;
-	age = data->maxage;
-	while (*s) {
-		leaf = utf8lookup(data, hangul, s);
-		if (!leaf)
-			return -1;
-		leaf_age = utf8agetab[LEAF_GEN(leaf)];
-		if (leaf_age <= data->maxage && leaf_age < age)
-			age = leaf_age;
-		s += utf8clen(s);
-	}
-	return age;
-}
-EXPORT_SYMBOL(utf8agemin);
-
-/*
- * Maximum age of any character in s, touch at most len bytes.
- * Return -1 if s is not valid UTF-8 unicode.
- */
-int utf8nagemax(const struct utf8data *data, const char *s, size_t len)
-{
-	utf8leaf_t	*leaf;
-	int		age = 0;
-	int		leaf_age;
-	unsigned char	hangul[UTF8HANGULLEAF];
-
-	if (!data)
-		return -1;
-
-	while (len && *s) {
-		leaf = utf8nlookup(data, hangul, s, len);
-		if (!leaf)
-			return -1;
-		leaf_age = utf8agetab[LEAF_GEN(leaf)];
-		if (leaf_age <= data->maxage && leaf_age > age)
-			age = leaf_age;
-		len -= utf8clen(s);
-		s += utf8clen(s);
-	}
-	return age;
-}
-EXPORT_SYMBOL(utf8nagemax);
-
-/*
- * Maximum age of any character in s, touch at most len bytes.
- * Return -1 if s is not valid UTF-8 unicode.
- */
-int utf8nagemin(const struct utf8data *data, const char *s, size_t len)
-{
-	utf8leaf_t	*leaf;
-	int		leaf_age;
-	int		age;
-	unsigned char	hangul[UTF8HANGULLEAF];
-
-	if (!data)
-		return -1;
-	age = data->maxage;
-	while (len && *s) {
-		leaf = utf8nlookup(data, hangul, s, len);
-		if (!leaf)
-			return -1;
-		leaf_age = utf8agetab[LEAF_GEN(leaf)];
-		if (leaf_age <= data->maxage && leaf_age < age)
-			age = leaf_age;
-		len -= utf8clen(s);
-		s += utf8clen(s);
-	}
-	return age;
-}
-EXPORT_SYMBOL(utf8nagemin);
-
-/*
- * Length of the normalization of s.
- * Return -1 if s is not valid UTF-8 unicode.
- *
- * A string of Default_Ignorable_Code_Point has length 0.
- */
-ssize_t utf8len(const struct utf8data *data, const char *s)
-{
-	utf8leaf_t	*leaf;
-	size_t		ret = 0;
-	unsigned char	hangul[UTF8HANGULLEAF];
-
-	if (!data)
-		return -1;
-	while (*s) {
-		leaf = utf8lookup(data, hangul, s);
-		if (!leaf)
-			return -1;
-		if (utf8agetab[LEAF_GEN(leaf)] > data->maxage)
-			ret += utf8clen(s);
-		else if (LEAF_CCC(leaf) == DECOMPOSE)
-			ret += strlen(LEAF_STR(leaf));
-		else
-			ret += utf8clen(s);
-		s += utf8clen(s);
-	}
-	return ret;
-}
-EXPORT_SYMBOL(utf8len);
-
 /*
  * Length of the normalization of s, touch at most len bytes.
  * Return -1 if s is not valid UTF-8 unicode.
  */
-ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len)
+ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n,
+		const char *s, size_t len)
 {
 	utf8leaf_t	*leaf;
 	size_t		ret = 0;
 	unsigned char	hangul[UTF8HANGULLEAF];
 
-	if (!data)
-		return -1;
 	while (len && *s) {
-		leaf = utf8nlookup(data, hangul, s, len);
+		leaf = utf8nlookup(um, n, hangul, s, len);
 		if (!leaf)
 			return -1;
-		if (utf8agetab[LEAF_GEN(leaf)] > data->maxage)
+		if (um->tables->utf8agetab[LEAF_GEN(leaf)] >
+		    um->ntab[n]->maxage)
 			ret += utf8clen(s);
 		else if (LEAF_CCC(leaf) == DECOMPOSE)
 			ret += strlen(LEAF_STR(leaf));
@@ -568,7 +406,6 @@ ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len)
 	}
 	return ret;
 }
-EXPORT_SYMBOL(utf8nlen);
 
 /*
  * Set up an utf8cursor for use by utf8byte().
@@ -580,14 +417,13 @@ EXPORT_SYMBOL(utf8nlen);
  *
  * Returns -1 on error, 0 on success.
  */
-int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
+int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um,
-		const char *s, size_t len)
+		enum utf8_normalization n, const char *s, size_t len)
 {
-	if (!data)
-		return -1;
 	if (!s)
 		return -1;
-	u8c->data = data;
+	u8c->um = um;
+	u8c->n = n;
 	u8c->s = s;
 	u8c->p = NULL;
 	u8c->ss = NULL;
@@ -604,23 +440,6 @@ int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
 		return -1;
 	return 0;
 }
-EXPORT_SYMBOL(utf8ncursor);
-
-/*
- * Set up an utf8cursor for use by utf8byte().
- *
- *   u8c    : pointer to cursor.
- *   data   : const struct utf8data to use for normalization.
- *   s      : NUL-terminated string.
- *
- * Returns -1 on error, 0 on success.
- */
-int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data,
-	       const char *s)
-{
-	return utf8ncursor(u8c, data, s, (unsigned int)-1);
-}
-EXPORT_SYMBOL(utf8cursor);
 
 /*
  * Get one byte from the normalized form of the string described by u8c.
@@ -678,9 +497,9 @@ int utf8byte(struct utf8cursor *u8c)
 
 		/* Look up the data for the current character. */
 		if (u8c->p) {
-			leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s);
+			leaf = utf8lookup(u8c->um, u8c->n, u8c->hangul, u8c->s);
 		} else {
-			leaf = utf8nlookup(u8c->data, u8c->hangul,
+			leaf = utf8nlookup(u8c->um, u8c->n, u8c->hangul,
 					   u8c->s, u8c->len);
 		}
 
@@ -690,7 +509,8 @@ int utf8byte(struct utf8cursor *u8c)
 
 		ccc = LEAF_CCC(leaf);
 		/* Characters that are too new have CCC 0. */
-		if (utf8agetab[LEAF_GEN(leaf)] > u8c->data->maxage) {
+		if (u8c->um->tables->utf8agetab[LEAF_GEN(leaf)] >
+		    u8c->um->ntab[u8c->n]->maxage) {
 			ccc = STOPPER;
 		} else if (ccc == DECOMPOSE) {
 			u8c->len -= utf8clen(u8c->s);
@@ -704,7 +524,7 @@ int utf8byte(struct utf8cursor *u8c)
 				goto ccc_mismatch;
 			}
 
-			leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s);
+			leaf = utf8lookup(u8c->um, u8c->n, u8c->hangul, u8c->s);
 			if (!leaf)
 				return -1;
 			ccc = LEAF_CCC(leaf);
@@ -765,28 +585,10 @@ ccc_mismatch:
 		}
 	}
 }
-EXPORT_SYMBOL(utf8byte);
 
-const struct utf8data *utf8nfdi(unsigned int maxage)
+#ifdef CONFIG_UNICODE_NORMALIZATION_SELFTEST_MODULE
-{
+EXPORT_SYMBOL_GPL(utf8version_is_supported);
-	int i = ARRAY_SIZE(utf8nfdidata) - 1;
+EXPORT_SYMBOL_GPL(utf8nlen);
-
+EXPORT_SYMBOL_GPL(utf8ncursor);
-	while (maxage < utf8nfdidata[i].maxage)
+EXPORT_SYMBOL_GPL(utf8byte);
-		i--;
+#endif
-	if (maxage > utf8nfdidata[i].maxage)
-		return NULL;
-	return &utf8nfdidata[i];
-}
-EXPORT_SYMBOL(utf8nfdi);
-
-const struct utf8data *utf8nfdicf(unsigned int maxage)
-{
-	int i = ARRAY_SIZE(utf8nfdicfdata) - 1;
-
-	while (maxage < utf8nfdicfdata[i].maxage)
-		i--;
-	if (maxage > utf8nfdicfdata[i].maxage)
-		return NULL;
-	return &utf8nfdicfdata[i];
-}
-EXPORT_SYMBOL(utf8nfdicf);

fs/unicode/utf8-selftest.c

@@ -18,9 +18,7 @@ unsigned int failed_tests;
 unsigned int total_tests;
 
 /* Tests will be based on this version. */
-#define latest_maj 12
+#define UTF8_LATEST	UNICODE_AGE(12, 1, 0)
-#define latest_min 1
-#define latest_rev 0
 
 #define _test(cond, func, line, fmt, ...) do {				\
 		total_tests++;						\
@@ -160,18 +158,22 @@ static const struct {
 	}
 };
 
-static void check_utf8_nfdi(void)
+static ssize_t utf8len(const struct unicode_map *um, enum utf8_normalization n,
+		const char *s)
+{
+	return utf8nlen(um, n, s, (size_t)-1);
+}
+
+static int utf8cursor(struct utf8cursor *u8c, const struct unicode_map *um,
+		enum utf8_normalization n, const char *s)
+{
+	return utf8ncursor(u8c, um, n, s, (unsigned int)-1);
+}
+
+static void check_utf8_nfdi(struct unicode_map *um)
 {
 	int i;
 	struct utf8cursor u8c;
-	const struct utf8data *data;
-
-	data = utf8nfdi(UNICODE_AGE(latest_maj, latest_min, latest_rev));
-	if (!data) {
-		pr_err("%s: Unable to load utf8-%d.%d.%d. Skipping.\n",
-		       __func__, latest_maj, latest_min, latest_rev);
-		return;
-	}
 
 	for (i = 0; i < ARRAY_SIZE(nfdi_test_data); i++) {
 		int len = strlen(nfdi_test_data[i].str);
@@ -179,10 +181,11 @@ static void check_utf8_nfdi(void)
 		int j = 0;
 		unsigned char c;
 
-		test((utf8len(data, nfdi_test_data[i].str) == nlen));
+		test((utf8len(um, UTF8_NFDI, nfdi_test_data[i].str) == nlen));
-		test((utf8nlen(data, nfdi_test_data[i].str, len) == nlen));
+		test((utf8nlen(um, UTF8_NFDI, nfdi_test_data[i].str, len) ==
+			nlen));
 
-		if (utf8cursor(&u8c, data, nfdi_test_data[i].str) < 0)
+		if (utf8cursor(&u8c, um, UTF8_NFDI, nfdi_test_data[i].str) < 0)
 			pr_err("can't create cursor\n");
 
 		while ((c = utf8byte(&u8c)) > 0) {
@@ -196,18 +199,10 @@ static void check_utf8_nfdi(void)
 	}
 }
 
-static void check_utf8_nfdicf(void)
+static void check_utf8_nfdicf(struct unicode_map *um)
 {
 	int i;
 	struct utf8cursor u8c;
-	const struct utf8data *data;
-
-	data = utf8nfdicf(UNICODE_AGE(latest_maj, latest_min, latest_rev));
-	if (!data) {
-		pr_err("%s: Unable to load utf8-%d.%d.%d. Skipping.\n",
-		       __func__, latest_maj, latest_min, latest_rev);
-		return;
-	}
 
 	for (i = 0; i < ARRAY_SIZE(nfdicf_test_data); i++) {
 		int len = strlen(nfdicf_test_data[i].str);
@@ -215,10 +210,13 @@ static void check_utf8_nfdicf(void)
 		int j = 0;
 		unsigned char c;
 
-		test((utf8len(data, nfdicf_test_data[i].str) == nlen));
+		test((utf8len(um, UTF8_NFDICF, nfdicf_test_data[i].str) ==
-		test((utf8nlen(data, nfdicf_test_data[i].str, len) == nlen));
+				nlen));
+		test((utf8nlen(um, UTF8_NFDICF, nfdicf_test_data[i].str, len) ==
+				nlen));
 
-		if (utf8cursor(&u8c, data, nfdicf_test_data[i].str) < 0)
+		if (utf8cursor(&u8c, um, UTF8_NFDICF,
+				nfdicf_test_data[i].str) < 0)
 			pr_err("can't create cursor\n");
 
 		while ((c = utf8byte(&u8c)) > 0) {
@@ -232,16 +230,9 @@ static void check_utf8_nfdicf(void)
 	}
 }
 
-static void check_utf8_comparisons(void)
+static void check_utf8_comparisons(struct unicode_map *table)
 {
 	int i;
-	struct unicode_map *table = utf8_load("12.1.0");
-
-	if (IS_ERR(table)) {
-		pr_err("%s: Unable to load utf8 %d.%d.%d. Skipping.\n",
-		       __func__, latest_maj, latest_min, latest_rev);
-		return;
-	}
 
 	for (i = 0; i < ARRAY_SIZE(nfdi_test_data); i++) {
 		const struct qstr s1 = {.name = nfdi_test_data[i].str,
@@ -262,42 +253,49 @@ static void check_utf8_comparisons(void)
 		test_f(!utf8_strncasecmp(table, &s1, &s2),
 		       "%s %s comparison mismatch\n", s1.name, s2.name);
 	}
-
-	utf8_unload(table);
 }
 
-static void check_supported_versions(void)
+static void check_supported_versions(struct unicode_map *um)
 {
 	/* Unicode 7.0.0 should be supported. */
-	test(utf8version_is_supported(7, 0, 0));
+	test(utf8version_is_supported(um, UNICODE_AGE(7, 0, 0)));
 
 	/* Unicode 9.0.0 should be supported. */
-	test(utf8version_is_supported(9, 0, 0));
+	test(utf8version_is_supported(um, UNICODE_AGE(9, 0, 0)));
 
 	/* Unicode 1x.0.0 (the latest version) should be supported. */
-	test(utf8version_is_supported(latest_maj, latest_min, latest_rev));
+	test(utf8version_is_supported(um, UTF8_LATEST));
 
 	/* Next versions don't exist. */
-	test(!utf8version_is_supported(13, 0, 0));
+	test(!utf8version_is_supported(um, UNICODE_AGE(13, 0, 0)));
-	test(!utf8version_is_supported(0, 0, 0));
+	test(!utf8version_is_supported(um, UNICODE_AGE(0, 0, 0)));
-	test(!utf8version_is_supported(-1, -1, -1));
+	test(!utf8version_is_supported(um, UNICODE_AGE(-1, -1, -1)));
 }
 
 static int __init init_test_ucd(void)
 {
+	struct unicode_map *um;
+
 	failed_tests = 0;
 	total_tests = 0;
 
-	check_supported_versions();
+	um = utf8_load(UTF8_LATEST);
-	check_utf8_nfdi();
+	if (IS_ERR(um)) {
-	check_utf8_nfdicf();
+		pr_err("%s: Unable to load utf8 table.\n", __func__);
-	check_utf8_comparisons();
+		return PTR_ERR(um);
+	}
+
+	check_supported_versions(um);
+	check_utf8_nfdi(um);
+	check_utf8_nfdicf(um);
+	check_utf8_comparisons(um);
 
 	if (!failed_tests)
 		pr_info("All %u tests passed\n", total_tests);
 	else
 		pr_err("%u out of %u tests failed\n", failed_tests,
 		       total_tests);
+	utf8_unload(um);
 	return 0;
 }
 

fs/unicode/utf8data.c_shipped

@@ -1,9 +1,8 @@
 /* This file is generated code, do not edit. */
-#ifndef __INCLUDED_FROM_UTF8NORM_C__
-#error Only nls_utf8-norm.c should include this file.
-#endif
 
-static const unsigned int utf8vers = 0xc0100;
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include "utf8n.h"
 
 static const unsigned int utf8agetab[] = {
 	0,
@@ -4107,3 +4106,18 @@ static const unsigned char utf8data[64256] = {
 	0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xcf,0x86,0xcf,0x06,0x02,0x00,
 	0x81,0x80,0xcf,0x86,0x85,0x84,0xcf,0x86,0xcf,0x06,0x02,0x00,0x00,0x00,0x00,0x00
 };
+
+struct utf8data_table utf8_data_table = {
+	.utf8agetab = utf8agetab,
+	.utf8agetab_size = ARRAY_SIZE(utf8agetab),
+
+	.utf8nfdicfdata = utf8nfdicfdata,
+	.utf8nfdicfdata_size = ARRAY_SIZE(utf8nfdicfdata),
+
+	.utf8nfdidata = utf8nfdidata,
+	.utf8nfdidata_size = ARRAY_SIZE(utf8nfdidata),
+
+	.utf8data = utf8data,
+};
+EXPORT_SYMBOL_GPL(utf8_data_table);
+MODULE_LICENSE("GPL v2");

fs/unicode/utf8n.h

@@ -11,53 +11,9 @@
 #include <linux/export.h>
 #include <linux/string.h>
 #include <linux/module.h>
+#include <linux/unicode.h>
 
-/* Encoding a unicode version number as a single unsigned int. */
+int utf8version_is_supported(const struct unicode_map *um, unsigned int version);
-#define UNICODE_MAJ_SHIFT		(16)
-#define UNICODE_MIN_SHIFT		(8)
-
-#define UNICODE_AGE(MAJ, MIN, REV)			\
-	(((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) |	\
-	 ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) |	\
-	 ((unsigned int)(REV)))
-
-/* Highest unicode version supported by the data tables. */
-extern int utf8version_is_supported(u8 maj, u8 min, u8 rev);
-extern int utf8version_latest(void);
-
-/*
- * Look for the correct const struct utf8data for a unicode version.
- * Returns NULL if the version requested is too new.
- *
- * Two normalization forms are supported: nfdi and nfdicf.
- *
- * nfdi:
- *  - Apply unicode normalization form NFD.
- *  - Remove any Default_Ignorable_Code_Point.
- *
- * nfdicf:
- *  - Apply unicode normalization form NFD.
- *  - Remove any Default_Ignorable_Code_Point.
- *  - Apply a full casefold (C + F).
- */
-extern const struct utf8data *utf8nfdi(unsigned int maxage);
-extern const struct utf8data *utf8nfdicf(unsigned int maxage);
-
-/*
- * Determine the maximum age of any unicode character in the string.
- * Returns 0 if only unassigned code points are present.
- * Returns -1 if the input is not valid UTF-8.
- */
-extern int utf8agemax(const struct utf8data *data, const char *s);
-extern int utf8nagemax(const struct utf8data *data, const char *s, size_t len);
-
-/*
- * Determine the minimum age of any unicode character in the string.
- * Returns 0 if any unassigned code points are present.
- * Returns -1 if the input is not valid UTF-8.
- */
-extern int utf8agemin(const struct utf8data *data, const char *s);
-extern int utf8nagemin(const struct utf8data *data, const char *s, size_t len);
 
 /*
  * Determine the length of the normalized from of the string,
@@ -65,8 +21,8 @@ extern int utf8nagemin(const struct utf8data *data, const char *s, size_t len);
  * Returns 0 if only ignorable code points are present.
  * Returns -1 if the input is not valid UTF-8.
  */
-extern ssize_t utf8len(const struct utf8data *data, const char *s);
+ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n,
-extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len);
+		const char *s, size_t len);
 
 /* Needed in struct utf8cursor below. */
 #define UTF8HANGULLEAF	(12)
@@ -75,7 +31,8 @@ extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len);
  * Cursor structure used by the normalizer.
  */
 struct utf8cursor {
-	const struct utf8data	*data;
+	const struct unicode_map *um;
+	enum utf8_normalization n;
 	const char	*s;
 	const char	*p;
 	const char	*ss;
@@ -92,10 +49,8 @@ struct utf8cursor {
  * Returns 0 on success.
  * Returns -1 on failure.
  */
-extern int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data,
+int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um,
-		      const char *s);
+		enum utf8_normalization n, const char *s, size_t len);
-extern int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
-		       const char *s, size_t len);
 
 /*
  * Get the next byte in the normalization.
@@ -105,4 +60,24 @@ extern int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
  */
 extern int utf8byte(struct utf8cursor *u8c);
 
+struct utf8data {
+	unsigned int maxage;
+	unsigned int offset;
+};
+
+struct utf8data_table {
+	const unsigned int *utf8agetab;
+	int utf8agetab_size;
+
+	const struct utf8data *utf8nfdicfdata;
+	int utf8nfdicfdata_size;
+
+	const struct utf8data *utf8nfdidata;
+	int utf8nfdidata_size;
+
+	const unsigned char *utf8data;
+};
+
+extern struct utf8data_table utf8_data_table;
+
 #endif /* UTF8NORM_H */

include/linux/unicode.h

@@ -5,9 +5,52 @@
 #include <linux/init.h>
 #include <linux/dcache.h>
 
+struct utf8data;
+struct utf8data_table;
+
+#define UNICODE_MAJ_SHIFT		16
+#define UNICODE_MIN_SHIFT		8
+
+#define UNICODE_AGE(MAJ, MIN, REV)			\
+	(((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) |	\
+	 ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) |	\
+	 ((unsigned int)(REV)))
+
+static inline u8 unicode_major(unsigned int age)
+{
+	return (age >> UNICODE_MAJ_SHIFT) & 0xff;
+}
+
+static inline u8 unicode_minor(unsigned int age)
+{
+	return (age >> UNICODE_MIN_SHIFT) & 0xff;
+}
+
+static inline u8 unicode_rev(unsigned int age)
+{
+	return age & 0xff;
+}
+
+/*
+ * Two normalization forms are supported:
+ * 1) NFDI
+ *   - Apply unicode normalization form NFD.
+ *   - Remove any Default_Ignorable_Code_Point.
+ * 2) NFDICF
+ *   - Apply unicode normalization form NFD.
+ *   - Remove any Default_Ignorable_Code_Point.
+ *   - Apply a full casefold (C + F).
+ */
+enum utf8_normalization {
+	UTF8_NFDI = 0,
+	UTF8_NFDICF,
+	UTF8_NMAX,
+};
+
 struct unicode_map {
-	const char *charset;
+	unsigned int version;
-	int version;
+	const struct utf8data *ntab[UTF8_NMAX];
+	const struct utf8data_table *tables;
 };
 
 int utf8_validate(const struct unicode_map *um, const struct qstr *str);
@@ -30,7 +73,7 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
 		       struct qstr *str);
 
-struct unicode_map *utf8_load(const char *version);
+struct unicode_map *utf8_load(unsigned int version);
 void utf8_unload(struct unicode_map *um);
 
 #endif /* _LINUX_UNICODE_H */