Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Tue,  7 Jul 2020 20:05:49 -0700
In-Reply-To: <20200708030552.3829094-1-drosen@google.com>
Message-Id: <20200708030552.3829094-2-drosen@google.com>
Mime-Version: 1.0
References: <20200708030552.3829094-1-drosen@google.com>
Subject: [PATCH v11 1/4] unicode: Add utf8_casefold_hash
From:   Daniel Rosenberg <drosen@google.com>
To:     "Theodore Ts'o" <tytso@mit.edu>, linux-ext4@vger.kernel.org,
        Jaegeuk Kim <jaegeuk@kernel.org>, Chao Yu <chao@kernel.org>,
        linux-f2fs-devel@lists.sourceforge.net,
        Eric Biggers <ebiggers@kernel.org>,
        linux-fscrypt@vger.kernel.org,
        Alexander Viro <viro@zeniv.linux.org.uk>
Cc:     Andreas Dilger <adilger.kernel@dilger.ca>,
        linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        Gabriel Krisman Bertazi <krisman@collabora.com>,
        kernel-team@android.com, Daniel Rosenberg <drosen@google.com>,
        Eric Biggers <ebiggers@google.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

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>
---
 fs/unicode/utf8-core.c  | 23 ++++++++++++++++++++++-
 include/linux/unicode.h |  3 +++
 2 files changed, 25 insertions(+), 1 deletion(-)

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);
 
-- 
2.27.0.383.g050319c2ae-goog