[PATCH v17 19/71] ceph: add base64 endcoding routines for encrypted names

From: xiubli@redhat.com
To: idryomov@gmail.com, ceph-devel@vger.kernel.org
Cc: jlayton@kernel.org, vshankar@redhat.com, mchangir@redhat.com,
	lhenriques@suse.de, Xiubo Li <xiubli@redhat.com>
Subject: [PATCH v17 19/71] ceph: add base64 endcoding routines for encrypted names
Date: Thu, 23 Mar 2023 14:54:33 +0800	[thread overview]
Message-ID: <20230323065525.201322-20-xiubli@redhat.com> (raw)
In-Reply-To: <20230323065525.201322-1-xiubli@redhat.com>

From: Luís Henriques <lhenriques@suse.de>

The base64url encoding used by fscrypt includes the '_' character, which
may cause problems in snapshot names (if the name starts with '_').
Thus, use the base64 encoding defined for IMAP mailbox names (RFC 3501),
which uses '+' and ',' instead of '-' and '_'.

Signed-off-by: Luís Henriques <lhenriques@suse.de>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/ceph/crypto.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/crypto.h | 32 ++++++++++++++++++++++++++
 2 files changed, 92 insertions(+)

diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index fd3192917e8d..947ac98119aa 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -1,4 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
+/*
+ * The base64 encode/decode code was copied from fscrypt:
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ * Written by Uday Savagaonkar, 2014.
+ * Modified by Jaegeuk Kim, 2015.
+ */
 #include <linux/ceph/ceph_debug.h>
 #include <linux/xattr.h>
 #include <linux/fscrypt.h>
@@ -7,6 +14,59 @@
 #include "mds_client.h"
 #include "crypto.h"
 
+/*
+ * The base64url encoding used by fscrypt includes the '_' character, which may
+ * cause problems in snapshot names (which can not starts with '_').  Thus, we
+ * used the base64 encoding defined for IMAP mailbox names (RFC 3501) instead,
+ * which replaces '-' and '_' by '+' and ','.
+ */
+static const char base64_table[65] =
+        "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
+
+int ceph_base64_encode(const u8 *src, int srclen, char *dst)
+{
+	u32 ac = 0;
+	int bits = 0;
+	int i;
+	char *cp = dst;
+
+	for (i = 0; i < srclen; i++) {
+		ac = (ac << 8) | src[i];
+		bits += 8;
+		do {
+			bits -= 6;
+			*cp++ = base64_table[(ac >> bits) & 0x3f];
+		} while (bits >= 6);
+	}
+	if (bits)
+		*cp++ = base64_table[(ac << (6 - bits)) & 0x3f];
+	return cp - dst;
+}
+
+int ceph_base64_decode(const char *src, int srclen, u8 *dst)
+{
+	u32 ac = 0;
+	int bits = 0;
+	int i;
+	u8 *bp = dst;
+
+	for (i = 0; i < srclen; i++) {
+		const char *p = strchr(base64_table, src[i]);
+
+		if (p == NULL || src[i] == 0)
+			return -1;
+		ac = (ac << 6) | (p - base64_table);
+		bits += 6;
+		if (bits >= 8) {
+			bits -= 8;
+			*bp++ = (u8)(ac >> bits);
+		}
+	}
+	if (ac & ((1 << bits) - 1))
+		return -1;
+	return bp - dst;
+}
+
 static int ceph_crypt_get_context(struct inode *inode, void *ctx, size_t len)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index cb00fe42d5b7..f5d38d8a1995 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -27,6 +27,38 @@ static inline u32 ceph_fscrypt_auth_len(struct ceph_fscrypt_auth *fa)
 }
 
 #ifdef CONFIG_FS_ENCRYPTION
+/*
+ * We want to encrypt filenames when creating them, but the encrypted
+ * versions of those names may have illegal characters in them. To mitigate
+ * that, we base64 encode them, but that gives us a result that can exceed
+ * NAME_MAX.
+ *
+ * Follow a similar scheme to fscrypt itself, and cap the filename to a
+ * smaller size. If the ciphertext name is longer than the value below, then
+ * sha256 hash the remaining bytes.
+ *
+ * For the fscrypt_nokey_name struct the dirhash[2] member is useless in ceph
+ * so the corresponding struct will be:
+ *
+ * struct fscrypt_ceph_nokey_name {
+ *	u8 bytes[157];
+ *	u8 sha256[SHA256_DIGEST_SIZE];
+ * }; // 180 bytes => 240 bytes base64-encoded, which is <= NAME_MAX (255)
+ *
+ * (240 bytes is the maximum size allowed for snapshot names to take into
+ *  account the format: '_<SNAPSHOT-NAME>_<INODE-NUMBER>'.)
+ *
+ * Note that for long names that end up having their tail portion hashed, we
+ * must also store the full encrypted name (in the dentry's alternate_name
+ * field).
+ */
+#define CEPH_NOHASH_NAME_MAX (180 - SHA256_DIGEST_SIZE)
+
+#define CEPH_BASE64_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3)
+
+int ceph_base64_encode(const u8 *src, int srclen, char *dst);
+int ceph_base64_decode(const char *src, int srclen, u8 *dst);
+
 void ceph_fscrypt_set_ops(struct super_block *sb);
 
 void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc);
-- 
2.31.1

