Date:   Wed, 16 Mar 2022 11:00:42 +0000
From:   Luís Henriques <lhenriques@...e.de>
To:     Xiubo Li <xiubli@...hat.com>
Cc:     Jeff Layton <jlayton@...nel.org>,
        Ilya Dryomov <idryomov@...il.com>, ceph-devel@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: Re: [RFC PATCH v2 2/3] ceph: add support for handling encrypted
 snapshot names

Xiubo Li <xiubli@...hat.com> writes:

> On 3/16/22 12:19 AM, Luís Henriques wrote:
>> When creating a snapshot, the .snap directories for every subdirectory will
>> show the snapshot name in the "long format":
>>
>>    # mkdir .snap/my-snap
>>    # ls my-dir/.snap/
>>    _my-snap_1099511627782
>>
>> Encrypted snapshots will need to be able to handle these snapshot names by
>> encrypting/decrypting only the snapshot part of the string ('my-snap').
>>
>> Also, since the MDS prevents snapshot names to be bigger than 240 characters
>> it is necessary to adapt CEPH_NOHASH_NAME_MAX to accommodate this extra
>> limitation.
>>
>> Signed-off-by: Luís Henriques <lhenriques@...e.de>
>> ---
>>   fs/ceph/crypto.c | 158 +++++++++++++++++++++++++++++++++++++++++------
>>   fs/ceph/crypto.h |  11 ++--
>>   2 files changed, 145 insertions(+), 24 deletions(-)
>>
>> diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
>> index c125a79019b3..06a4b918201c 100644
>> --- a/fs/ceph/crypto.c
>> +++ b/fs/ceph/crypto.c
>> @@ -128,18 +128,95 @@ void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_se
>>   	swap(req->r_fscrypt_auth, as->fscrypt_auth);
>>   }
>>   -int ceph_encode_encrypted_dname(const struct inode *parent, struct qstr
>> *d_name, char *buf)
>> +/*
>> + * User-created snapshots can't start with '_'.  Snapshots that start with this
>> + * character are special (hint: there aren't real snapshots) and use the
>> + * following format:
>> + *
>> + *   _<SNAPSHOT-NAME>_<INODE-NUMBER>
>> + *
>> + * where:
>> + *  - <SNAPSHOT-NAME> - the real snapshot name that may need to be decrypted,
>> + *  - <INODE-NUMBER> - the inode number for the actual snapshot
>> + *
>> + * This function parses these snapshot names and returns the inode
>> + * <INODE-NUMBER>.  'name_len' will also bet set with the <SNAPSHOT-NAME>
>> + * length.
>> + */
>> +static struct inode *parse_longname(const struct inode *parent, const char *name,
>> +				    int *name_len)
>>   {
>> +	struct inode *dir = NULL;
>> +	struct ceph_vino vino = { .snap = CEPH_NOSNAP };
>> +	char *inode_number;
>> +	char *name_end;
>> +	int orig_len = *name_len;
>> +	int ret = -EIO;
>> +
>> +	/* Skip initial '_' */
>> +	name++;
>> +	name_end = strrchr(name, '_');
>> +	if (!name_end) {
>> +		dout("Failed to parse long snapshot name: %s\n", name);
>> +		return ERR_PTR(-EIO);
>> +	}
>> +	*name_len = (name_end - name);
>> +	if (*name_len <= 0) {
>> +		pr_err("Failed to parse long snapshot name\n");
>> +		return ERR_PTR(-EIO);
>> +	}
>> +
>> +	/* Get the inode number */
>> +	inode_number = kmemdup_nul(name_end + 1,
>> +				   orig_len - *name_len - 2,
>> +				   GFP_KERNEL);
>> +	if (!inode_number)
>> +		return ERR_PTR(-ENOMEM);
>> +	ret = kstrtou64(inode_number, 0, &vino.ino);
>> +	if (ret) {
>> +		dout("Failed to parse inode number: %s\n", name);
>> +		dir = ERR_PTR(ret);
>> +		goto out;
>> +	}
>> +
>> +	/* And finally the inode */
>> +	dir = ceph_get_inode(parent->i_sb, vino, NULL);
>
> Maybe you should use ceph_find_inode() here ? We shouldn't insert a new one
> here. And IMO the parent dir inode must be in the cache...

Right, that makes sense.  I'll swap it for the ceph_find_inode().

>> +	if (IS_ERR(dir))
>> +		dout("Can't find inode %s (%s)\n", inode_number, name);
>> +
>> +out:
>> +	kfree(inode_number);
>> +	return dir;
>> +}
>
> Here I think you have missed one case, not all the long snap names are needed to
> be dencrypted if they are from the parent snap realms, who are not encrypted,
> for example:
>
> mkdir dir1
>
> fscrypt encrypt dir1
>
> mkdir dir1/dir2
>
> mkdir .snap/root_snap
>
> mkdir dir1/.snap/dir1_snap
>
> ls dir1/dir2/.snap/
>
> _root_snap_1  _dir1_snap_1099511628283
>
> You shouldn't encrypt the "_root_snap_1" long name.

Ah!  Good catch!  Yes, this case isn't being covered.  I'll fix it with by
following your suggestion bellow.

>> +
>> +int ceph_encode_encrypted_dname(struct inode *parent, struct qstr *d_name, char *buf)
>> +{
>> +	struct inode *dir = parent;
>> +	struct qstr iname;
>>   	u32 len;
>> +	int name_len;
>>   	int elen;
>>   	int ret;
>> -	u8 *cryptbuf;
>> +	u8 *cryptbuf = NULL;
>>     	if (!fscrypt_has_encryption_key(parent)) {
>>   		memcpy(buf, d_name->name, d_name->len);
>>   		return d_name->len;
>>   	}
>>   +	iname.name = d_name->name;
>> +	name_len = d_name->len;
>> +
>> +	/* Handle the special case of snapshot names that start with '_' */
>> +	if ((ceph_snap(dir) == CEPH_SNAPDIR) && (name_len > 0) &&
>> +	    (iname.name[0] == '_')) {
>> +		dir = parse_longname(parent, iname.name, &name_len);
>> +		if (IS_ERR(dir))
>> +			return PTR_ERR(dir);
>> +		iname.name++; /* skip initial '_' */
>> +	}
>> +	iname.len = name_len;
>> +
>
> Maybe you can do this just before checking the fscrypt_has_encryption_key() to
> fix the issue mentioned above ?
>
>
>>   	/*
>>   	 * convert cleartext d_name to ciphertext
>>   	 * if result is longer than CEPH_NOKEY_NAME_MAX,
>> @@ -147,18 +224,22 @@ int ceph_encode_encrypted_dname(const struct inode *parent, struct qstr *d_name,
>>   	 *
>>   	 * See: fscrypt_setup_filename
>>   	 */
>> -	if (!fscrypt_fname_encrypted_size(parent, d_name->len, NAME_MAX, &len))
>> -		return -ENAMETOOLONG;
>> +	if (!fscrypt_fname_encrypted_size(dir, iname.len, NAME_MAX, &len)) {
>> +		elen = -ENAMETOOLONG;
>> +		goto out;
>> +	}
>>     	/* Allocate a buffer appropriate to hold the result */
>>   	cryptbuf = kmalloc(len > CEPH_NOHASH_NAME_MAX ? NAME_MAX : len, GFP_KERNEL);
>> -	if (!cryptbuf)
>> -		return -ENOMEM;
>> +	if (!cryptbuf) {
>> +		elen = -ENOMEM;
>> +		goto out;
>> +	}
>>   -	ret = fscrypt_fname_encrypt(parent, d_name, cryptbuf, len);
>> +	ret = fscrypt_fname_encrypt(dir, &iname, cryptbuf, len);
>>   	if (ret) {
>> -		kfree(cryptbuf);
>> -		return ret;
>> +		elen = ret;
>> +		goto out;
>>   	}
>>     	/* hash the end if the name is long enough */
>> @@ -174,12 +255,24 @@ int ceph_encode_encrypted_dname(const struct inode *parent, struct qstr *d_name,
>>     	/* base64 encode the encrypted name */
>>   	elen = fscrypt_base64url_encode(cryptbuf, len, buf);
>> -	kfree(cryptbuf);
>>   	dout("base64-encoded ciphertext name = %.*s\n", elen, buf);
>> +
>> +	if ((elen > 0) && (dir != parent)) {
>> +		char tmp_buf[FSCRYPT_BASE64URL_CHARS(NAME_MAX)];
>> +
>
> Do we really need FSCRYPT_BASE64URL_CHARS(NAME_MAX) ? Since you have fix the
> 189->180 code, then the encrypted long snap name shouldn't exceed 255.
>
> I think the NAME_MAX is enough.

Yes, correct.  I'll change that too.

> And also you should check the elen here it shouldn't exceed 240 after encrypted,
> or should we fail it here directly with a warning log ?

Right, that should probably be logged.  I'll had that check.

Thanks a lot for your review, Xiubo.

Cheers,
-- 
Luís

>> +		elen = snprintf(tmp_buf, sizeof(tmp_buf), "_%.*s_%ld",
>> +				elen, buf, dir->i_ino);
>> +		memcpy(buf, tmp_buf, elen);
>> +	}
>> +
>> +out:
>> +	kfree(cryptbuf);
>> +	if (dir != parent)
>> +		iput(dir);
>>   	return elen;
>>   }
>>   -int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry
>> *dentry, char *buf)
>> +int ceph_encode_encrypted_fname(struct inode *parent, struct dentry *dentry, char *buf)
>>   {
>>   	WARN_ON_ONCE(!fscrypt_has_encryption_key(parent));
>>   @@ -204,11 +297,14 @@ int ceph_encode_encrypted_fname(const struct inode
>> *parent, struct dentry *dentr
>>   int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
>>   		      struct fscrypt_str *oname, bool *is_nokey)
>>   {
>> -	int ret;
>> +	struct inode *dir = fname->dir;
>>   	struct fscrypt_str _tname = FSTR_INIT(NULL, 0);
>>   	struct fscrypt_str iname;
>> +	char *name = fname->name;
>> +	int name_len = fname->name_len;
>> +	int ret;
>>   -	if (!IS_ENCRYPTED(fname->dir)) {
>> +	if (!IS_ENCRYPTED(dir)) {
>>   		oname->name = fname->name;
>>   		oname->len = fname->name_len;
>>   		return 0;
>> @@ -218,15 +314,24 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
>>   	if (fname->name_len > NAME_MAX || fname->ctext_len > NAME_MAX)
>>   		return -EIO;
>>   -	ret = __fscrypt_prepare_readdir(fname->dir);
>> +	/* Handle the special case of snapshot names that start with '_' */
>> +	if ((ceph_snap(dir) == CEPH_SNAPDIR) && (name_len > 0) &&
>> +	    (name[0] == '_')) {
>> +		dir = parse_longname(dir, name, &name_len);
>> +		if (IS_ERR(dir))
>> +			return PTR_ERR(dir);
>> +		name++; /* skip initial '_' */
>> +	}
>> +
>> +	ret = __fscrypt_prepare_readdir(dir);
>>   	if (ret)
>> -		return ret;
>> +		goto out_inode;
>>     	/*
>>   	 * Use the raw dentry name as sent by the MDS instead of
>>   	 * generating a nokey name via fscrypt.
>>   	 */
>> -	if (!fscrypt_has_encryption_key(fname->dir)) {
>> +	if (!fscrypt_has_encryption_key(dir)) {
>>   		if (fname->no_copy)
>>   			oname->name = fname->name;
>>   		else
>> @@ -234,7 +339,8 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
>>   		oname->len = fname->name_len;
>>   		if (is_nokey)
>>   			*is_nokey = true;
>> -		return 0;
>> +		ret = 0;
>> +		goto out_inode;
>>   	}
>>     	if (fname->ctext_len == 0) {
>> @@ -243,11 +349,11 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
>>   		if (!tname) {
>>   			ret = fscrypt_fname_alloc_buffer(NAME_MAX, &_tname);
>>   			if (ret)
>> -				return ret;
>> +				goto out_inode;
>>   			tname = &_tname;
>>   		}
>>   -		declen = fscrypt_base64url_decode(fname->name, fname->name_len,
>> tname->name);
>> +		declen = fscrypt_base64url_decode(name, name_len, tname->name);
>>   		if (declen <= 0) {
>>   			ret = -EIO;
>>   			goto out;
>> @@ -259,9 +365,21 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
>>   		iname.len = fname->ctext_len;
>>   	}
>>   -	ret = fscrypt_fname_disk_to_usr(fname->dir, 0, 0, &iname, oname);
>> +	ret = fscrypt_fname_disk_to_usr(dir, 0, 0, &iname, oname);
>> +	if (!ret && (dir != fname->dir)) {
>> +		char tmp_buf[FSCRYPT_BASE64URL_CHARS(NAME_MAX)];
>> +
>> +		name_len = snprintf(tmp_buf, sizeof(tmp_buf), "_%.*s_%ld",
>> +				    oname->len, oname->name, dir->i_ino);
>> +		memcpy(oname->name, tmp_buf, name_len);
>> +		oname->len = name_len;
>> +	}
>> +
>>   out:
>>   	fscrypt_fname_free_buffer(&_tname);
>> +out_inode:
>> +	if ((dir != fname->dir) && !IS_ERR(dir))
>> +		iput(dir);
>>   	return ret;
>>   }
>>   diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
>> index 185fb4799a6d..e38a842e02a6 100644
>> --- a/fs/ceph/crypto.h
>> +++ b/fs/ceph/crypto.h
>> @@ -76,13 +76,16 @@ static inline u32 ceph_fscrypt_auth_len(struct ceph_fscrypt_auth *fa)
>>    * smaller size. If the ciphertext name is longer than the value below, then
>>    * sha256 hash the remaining bytes.
>>    *
>> - * 189 bytes => 252 bytes base64-encoded, which is <= NAME_MAX (255)
>> + * 180 bytes => 240 bytes base64-encoded, which is <= NAME_MAX (255)
>> + *
>> + * (Note: 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 (189 - SHA256_DIGEST_SIZE)
>> +#define CEPH_NOHASH_NAME_MAX (180 - SHA256_DIGEST_SIZE)
>>     void ceph_fscrypt_set_ops(struct super_block *sb);
>>   @@ -91,8 +94,8 @@ void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client
>> *fsc);
>>   int ceph_fscrypt_prepare_context(struct inode *dir, struct inode *inode,
>>   				 struct ceph_acl_sec_ctx *as);
>>   void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_sec_ctx *as);
>> -int ceph_encode_encrypted_dname(const struct inode *parent, struct qstr *d_name, char *buf);
>> -int ceph_encode_encrypted_fname(const struct inode *parent, struct dentry *dentry, char *buf);
>> +int ceph_encode_encrypted_dname(struct inode *parent, struct qstr *d_name, char *buf);
>> +int ceph_encode_encrypted_fname(struct inode *parent, struct dentry *dentry, char *buf);
>>     static inline int ceph_fname_alloc_buffer(struct inode *parent, struct
>> fscrypt_str *fname)
>>   {
>>
>

Powered by blists - more mailing lists