summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDaniel Rosenberg <drosen@google.com>2020-07-08 02:12:34 -0700
committerJaegeuk Kim <jaegeuk@kernel.org>2020-09-10 14:03:31 -0700
commit3d7bfea8b8378277a25b42b28fe5a2a5ca76a7cf (patch)
tree70947df66e566caf2bd0bc776c4ca85417fc7747
parente6c3948de2f8213010e584009d47e9bc0934b32c (diff)
unicode: Add utf8_casefold_hash
This adds a case insensitive hash function to allow taking the hash without needing to allocate a casefolded copy of the string. The existing d_hash implementations for casefolding allocate memory within rcu-walk, by avoiding it we can be more efficient and avoid worrying about a failed allocation. Signed-off-by: Daniel Rosenberg <drosen@google.com> Reviewed-by: Gabriel Krisman Bertazi <krisman@collabora.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
-rw-r--r--fs/unicode/utf8-core.c23
-rw-r--r--include/linux/unicode.h3
2 files changed, 25 insertions, 1 deletions
diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index 2a878b739115..dc25823bfed9 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -6,6 +6,7 @@
#include <linux/parser.h>
#include <linux/errno.h>
#include <linux/unicode.h>
+#include <linux/stringhash.h>
#include "utf8n.h"
@@ -122,9 +123,29 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
}
return -EINVAL;
}
-
EXPORT_SYMBOL(utf8_casefold);
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+ struct qstr *str)
+{
+ const struct utf8data *data = utf8nfdicf(um->version);
+ struct utf8cursor cur;
+ int c;
+ unsigned long hash = init_name_hash(salt);
+
+ if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+ return -EINVAL;
+
+ while ((c = utf8byte(&cur))) {
+ if (c < 0)
+ return -EINVAL;
+ hash = partial_name_hash((unsigned char)c, hash);
+ }
+ str->hash = end_name_hash(hash);
+ return 0;
+}
+EXPORT_SYMBOL(utf8_casefold_hash);
+
int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
unsigned char *dest, size_t dlen)
{
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 990aa97d8049..74484d44c755 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -27,6 +27,9 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
unsigned char *dest, size_t dlen);
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+ struct qstr *str);
+
struct unicode_map *utf8_load(const char *version);
void utf8_unload(struct unicode_map *um);