[PATCH v2 07/15] nls: Add new interface for string comparisons

From: Gabriel Krisman Bertazi
Date: Mon May 21 2018 - 12:44:04 EST


The existing stricmp() interface is limited by not accepting separated
length parameters for each string being compared. This is a problem for
charsets doing normalization or full casefold comparison, since
different sized strings can still be matched. To resolve this problem,
this patch implements a new interface, allowing charsets to do the
comparison, if needed.

The original stricmp is left in the code, while all callers are not
converted, but was rewritten the new interface.

Signed-off-by: Gabriel Krisman Bertazi <krisman@xxxxxxxxxxxxxxx>
---
include/linux/nls.h | 42 +++++++++++++++++++++++++++++++++++++++---
1 file changed, 39 insertions(+), 3 deletions(-)

diff --git a/include/linux/nls.h b/include/linux/nls.h
index 3766fbe6efc3..1a653b866a64 100644
--- a/include/linux/nls.h
+++ b/include/linux/nls.h
@@ -3,6 +3,7 @@
#define _LINUX_NLS_H

#include <linux/init.h>
+#include <linux/string.h>

/* Unicode has changed over the years. Unicode code points no longer
* fit into 16 bits; as of Unicode 5 valid code points range from 0
@@ -21,11 +22,18 @@ typedef u16 wchar_t;

/* Arbitrary Unicode character */
typedef u32 unicode_t;
+struct nls_table;

struct nls_ops {
int (*uni2char) (wchar_t uni, unsigned char *out, int boundlen);
int (*char2uni) (const unsigned char *rawstring, int boundlen,
wchar_t *uni);
+ int (*strncmp)(const struct nls_table *charset,
+ const unsigned char *str1, size_t len1,
+ const unsigned char *str2, size_t len2);
+ int (*strncasecmp)(const struct nls_table *charset,
+ const unsigned char *str1, size_t len1,
+ const unsigned char *str2, size_t len2);
};

struct nls_table {
@@ -105,10 +113,17 @@ static inline unsigned char nls_toupper(struct nls_table *t, unsigned char c)
return nc ? nc : c;
}

-static inline int nls_strnicmp(struct nls_table *t, const unsigned char *s1,
- const unsigned char *s2, int len)
+static inline int nls_strncasecmp(struct nls_table *t,
+ const unsigned char *s1, size_t len1,
+ const unsigned char *s2, size_t len2)
{
- while (len--) {
+ if (t->ops->strncasecmp)
+ return t->ops->strncasecmp(t, s1, len1, s2, len2);
+
+ if (len1 != len2)
+ return 1;
+
+ while (len1--) {
if (nls_tolower(t, *s1++) != nls_tolower(t, *s2++))
return 1;
}
@@ -116,6 +131,27 @@ static inline int nls_strnicmp(struct nls_table *t, const unsigned char *s1,
return 0;
}

+static inline int nls_strncmp(struct nls_table *t,
+ const unsigned char *s1, size_t len1,
+ const unsigned char *s2, size_t len2)
+{
+ if (t->ops->strncmp)
+ return t->ops->strncmp(t, s1, len1, s2, len2);
+
+ if (len1 != len2)
+ return 1;
+
+ /* strnicmp did not return negative values. So let's keep the
+ * abi for now */
+ return !!memcmp(s1, s2, len1);
+}
+
+static inline int nls_strnicmp(struct nls_table *t, const unsigned char *s1,
+ const unsigned char *s2, int len)
+{
+ return nls_strncasecmp(t, s1, len, s2, len);
+}
+
/*
* nls_nullsize - return length of null character for codepage
* @codepage - codepage for which to return length of NULL terminator
--
2.17.0