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

1 files changed, 46 insertions, 3 deletions

diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 74484d44c755..4d39e6e11a95 100644
--- a/include/linux/unicode.h
+++ b/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;
-	int version;
+	unsigned 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 */