unicode: cache the normalization tables in struct unicode_map

Instead of repeatedly looking up the version add pointers to the
NFD and NFD+CF tables to struct unicode_map, and pass a
unicode_map plus index to the functions using the normalization
tables.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>

1 files changed, 19 insertions, 0 deletions

diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 77bb915fd1f0..526ca8b8391a 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -5,6 +5,8 @@
 #include <linux/init.h>
 #include <linux/dcache.h>
 
+struct utf8data;
+
 #define UNICODE_MAJ_SHIFT		16
 #define UNICODE_MIN_SHIFT		8
 
@@ -28,8 +30,25 @@ 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 {
 	unsigned int version;
+	const struct utf8data *ntab[UTF8_NMAX];
 };
 
 int utf8_validate(const struct unicode_map *um, const struct qstr *str);