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

…ux/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,
-				 const struct ext4_sb_encodings **encoding,
-				 __u16 *flags)
+static const struct ext4_sb_encodings *
+ext4_sb_read_encoding(const struct ext4_super_block *es)
 {
 	__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;
-
-	if (i >= ARRAY_SIZE(ext4_sb_encoding_map))
-		return -EINVAL;
+			return &ext4_sb_encoding_map[i];
 
-	*encoding = &ext4_sb_encoding_map[i];
-	*flags = le16_to_cpu(es->s_encoding_flags);
-
-	return 0;
+	return NULL;
 }
 #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_flags)) {
+		encoding_info = ext4_sb_read_encoding(es);
+		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,
-			 encoding_info->version?:"\b", encoding_flags);
+			 "%s-%u.%u.%u with flags 0x%hx", encoding_info->name,
+			 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,
-				 const struct f2fs_sb_encodings **encoding,
-				 __u16 *flags)
+static const struct f2fs_sb_encodings *
+f2fs_sb_read_encoding(const struct f2fs_super_block *sb)
 {
 	__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;
-
-	if (i >= ARRAY_SIZE(f2fs_sb_encoding_map))
-		return -EINVAL;
+			return &f2fs_sb_encoding_map[i];
 
-	*encoding = &f2fs_sb_encoding_map[i];
-	*flags = le16_to_cpu(sb->s_encoding_flags);
-
-	return 0;
+	return NULL;
 }
 
 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_flags)) {
+		encoding_info = f2fs_sb_read_encoding(sbi->raw_super);
+		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,
-			 encoding_info->version?:"\b", encoding_flags);
+			 "%s-%u.%u.%u with flags 0x%hx", encoding_info->name,
+			 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",
-			sb->s_encoding->charset,
+		return sysfs_emit(buf, "UTF-8 (%d.%d.%d)\n",
 			(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
-	default n
+	depends on UNICODE_UTF8_DATA

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",
-		unicode_maxage);
+	fprintf(file, "#include <linux/module.h>\n");
+	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);
 }