ext2fs: implement faster CI comparison of strings

Instead of calling casefold two times and memcmp the result, which
require allocating a temporary buffer for the casefolded version, add a
strcasecmp-like method to perform the comparison of each code-point
during the casefold itself.

This method is exposed because it needs to be used directly by fsck.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Arnaud Ferraris <arnaud.ferraris@collabora.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

3 files changed, 40 insertions, 0 deletions

diff --git a/lib/ext2fs/ext2fs.h b/lib/ext2fs/ext2fs.h
index 68f6b0292..6a26abc4c 100644
--- a/lib/ext2fs/ext2fs.h
+++ b/lib/ext2fs/ext2fs.h
@@ -1635,6 +1635,9 @@ extern errcode_t ext2fs_new_dir_inline_data(ext2_filsys fs, ext2_ino_t dir_ino,
 extern const struct ext2fs_nls_table *ext2fs_load_nls_table(int encoding);
 extern int ext2fs_check_encoded_name(const struct ext2fs_nls_table *table,
 				     char *s, size_t len, char **pos);
+extern int ext2fs_casefold_cmp(const struct ext2fs_nls_table *table,
+			       const unsigned char *str1, size_t len1,
+			       const unsigned char *str2, size_t len2);
 
 /* mkdir.c */
 extern errcode_t ext2fs_mkdir(ext2_filsys fs, ext2_ino_t parent, ext2_ino_t inum,
diff --git a/lib/ext2fs/ext2fsP.h b/lib/ext2fs/ext2fsP.h
index 30564ded1..a20a05029 100644
--- a/lib/ext2fs/ext2fsP.h
+++ b/lib/ext2fs/ext2fsP.h
@@ -106,6 +106,9 @@ struct ext2fs_nls_ops {
 			unsigned char *dest, size_t dlen);
 	int (*validate)(const struct ext2fs_nls_table *table,
 			char *s, size_t len, char **pos);
+	int (*casefold_cmp)(const struct ext2fs_nls_table *table,
+			    const unsigned char *str1, size_t len1,
+			    const unsigned char *str2, size_t len2);
 };
 
 /* Function prototypes */
diff --git a/lib/ext2fs/nls_utf8.c b/lib/ext2fs/nls_utf8.c
index 7d2cf4214..43bab9a3e 100644
--- a/lib/ext2fs/nls_utf8.c
+++ b/lib/ext2fs/nls_utf8.c
@@ -941,9 +941,36 @@ static int utf8_validate(const struct ext2fs_nls_table *table,
 	return 0;
 }
 
+static int utf8_casefold_cmp(const struct ext2fs_nls_table *table,
+			     const unsigned char *str1, size_t len1,
+			     const unsigned char *str2, size_t len2)
+{
+	const struct utf8data *data = utf8nfdicf(table->version);
+	int c1, c2;
+	struct utf8cursor cur1, cur2;
+
+	if (utf8ncursor(&cur1, data, (const char *) str1, len1) < 0)
+		return -1;
+	if (utf8ncursor(&cur2, data, (const char *) str2, len2) < 0)
+		return -1;
+
+	do {
+		c1 = utf8byte(&cur1);
+		c2 = utf8byte(&cur2);
+
+		if (c1 < 0 || c2 < 0)
+			return -1;
+		if (c1 != c2)
+			return c1 - c2;
+	} while (c1);
+
+	return 0;
+}
+
 static const struct ext2fs_nls_ops utf8_ops = {
 	.casefold = utf8_casefold,
 	.validate = utf8_validate,
+	.casefold_cmp = utf8_casefold_cmp,
 };
 
 static const struct ext2fs_nls_table nls_utf8 = {
@@ -964,3 +991,10 @@ int ext2fs_check_encoded_name(const struct ext2fs_nls_table *table,
 {
 	return table->ops->validate(table, name, len, pos);
 }
+
+int ext2fs_casefold_cmp(const struct ext2fs_nls_table *table,
+			const unsigned char *str1, size_t len1,
+			const unsigned char *str2, size_t len2)
+{
+	return table->ops->casefold_cmp(table, str1, len1, str2, len2);
+}