f2fs: rework filename handling

Rework f2fs's handling of filenames to use a new 'struct f2fs_filename'.
Similar to 'struct ext4_filename', this stores the usr_fname, disk_name,
dirhash, crypto_buf, and casefolded name.  Some of these names can be
NULL in some cases.  'struct f2fs_filename' differs from
'struct fscrypt_name' mainly in that the casefolded name is included.

For user-initiated directory operations like lookup() and create(),
initialize the f2fs_filename by translating the corresponding
fscrypt_name, then computing the dirhash and casefolded name if needed.

This makes the dirhash and casefolded name be cached for each syscall,
so we don't have to recompute them repeatedly.  (Previously, f2fs
computed the dirhash once per directory level, and the casefolded name
once per directory block.)  This improves performance.

This rework also makes it much easier to correctly handle all
combinations of normal, encrypted, casefolded, and encrypted+casefolded
directories.  (The fourth isn't supported yet but is being worked on.)

The only other cases where an f2fs_filename gets initialized are for two
filesystem-internal operations: (1) when converting an inline directory
to a regular one, we grab the needed disk_name and hash from an existing
f2fs_dir_entry; and (2) when roll-forward recovering a new dentry, we
grab the needed disk_name from f2fs_inode::i_name and compute the hash.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

1 files changed, 32 insertions, 44 deletions

diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index 5bc4dcd8fc03..e5997919472d 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -68,22 +68,9 @@ static void str2hashbuf(const unsigned char *msg, size_t len,
 		*buf++ = pad;
 }
 
-static f2fs_hash_t __f2fs_dentry_hash(const struct qstr *name_info,
-				struct fscrypt_name *fname)
+static u32 TEA_hash_name(const u8 *p, size_t len)
 {
-	__u32 hash;
-	f2fs_hash_t f2fs_hash;
-	const unsigned char *p;
 	__u32 in[8], buf[4];
-	const unsigned char *name = name_info->name;
-	size_t len = name_info->len;
-
-	/* encrypted bigname case */
-	if (fname && !fname->disk_name.name)
-		return cpu_to_le32(fname->hash);
-
-	if (is_dot_dotdot(name_info))
-		return 0;
 
 	/* Initialize the default seed for the hash checksum functions */
 	buf[0] = 0x67452301;
@@ -91,7 +78,6 @@ static f2fs_hash_t __f2fs_dentry_hash(const struct qstr *name_info,
 	buf[2] = 0x98badcfe;
 	buf[3] = 0x10325476;
 
-	p = name;
 	while (1) {
 		str2hashbuf(p, len, in, 4);
 		TEA_transform(buf, in);
@@ -100,41 +86,43 @@ static f2fs_hash_t __f2fs_dentry_hash(const struct qstr *name_info,
 			break;
 		len -= 16;
 	}
-	hash = buf[0];
-	f2fs_hash = cpu_to_le32(hash & ~F2FS_HASH_COL_BIT);
-	return f2fs_hash;
+	return buf[0] & ~F2FS_HASH_COL_BIT;
 }
 
-f2fs_hash_t f2fs_dentry_hash(const struct inode *dir,
-		const struct qstr *name_info, struct fscrypt_name *fname)
+/*
+ * Compute @fname->hash.  For all directories, @fname->disk_name must be set.
+ * For casefolded directories, @fname->usr_fname must be set, and also
+ * @fname->cf_name if the filename is valid Unicode.
+ */
+void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
 {
-#ifdef CONFIG_UNICODE
-	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
-	const struct unicode_map *um = sbi->s_encoding;
-	int r, dlen;
-	unsigned char *buff;
-	struct qstr folded;
+	const u8 *name = fname->disk_name.name;
+	size_t len = fname->disk_name.len;
 
-	if (!name_info->len || !IS_CASEFOLDED(dir))
-		goto opaque_seq;
+	WARN_ON_ONCE(!name);
 
-	buff = f2fs_kzalloc(sbi, sizeof(char) * PATH_MAX, GFP_KERNEL);
-	if (!buff)
-		return -ENOMEM;
-
-	dlen = utf8_casefold(um, name_info, buff, PATH_MAX);
-	if (dlen < 0) {
-		kvfree(buff);
-		goto opaque_seq;
+	if (is_dot_dotdot(name, len)) {
+		fname->hash = 0;
+		return;
 	}
-	folded.name = buff;
-	folded.len = dlen;
-	r = __f2fs_dentry_hash(&folded, fname);
-
-	kvfree(buff);
-	return r;
 
-opaque_seq:
+#ifdef CONFIG_UNICODE
+	if (IS_CASEFOLDED(dir)) {
+		/*
+		 * If the casefolded name is provided, hash it instead of the
+		 * on-disk name.  If the casefolded name is *not* provided, that
+		 * should only be because the name wasn't valid Unicode, so fall
+		 * back to treating the name as an opaque byte sequence.
+		 */
+		WARN_ON_ONCE(!fname->usr_fname->name);
+		if (fname->cf_name.name) {
+			name = fname->cf_name.name;
+			len = fname->cf_name.len;
+		} else {
+			name = fname->usr_fname->name;
+			len = fname->usr_fname->len;
+		}
+	}
 #endif
-	return __f2fs_dentry_hash(name_info, fname);
+	fname->hash = cpu_to_le32(TEA_hash_name(name, len));
 }