[44/64] cachefiles: Implement key to filename encoding

Implement a function to encode a binary cookie key as something that can be
used as a filename.  Four options are considered:

 (1) All printable chars with no '/' characters.  Prepend a 'D' to indicate
     the encoding but otherwise use as-is.

 (2) Appears to be an array of __be32.  Encode as 'S' plus a list of
     hex-encoded 32-bit ints separated by commas.  If a number is 0, it is
     rendered as "" instead of "0".

 (3) Appears to be an array of __le32.  Encoded as (2) but with a 'T'
     encoding prefix.

 (4) Encoded as base64 with an 'E' prefix plus a second char indicating how
     much padding is involved.  A non-standard base64 encoding is used
     because '/' cannot be used in the encoded form.

If (1) is not possible, whichever of (2), (3) or (4) produces the shortest
string is selected (hex-encoding a number may be less dense than base64
encoding it).

Note that the prefix characters have to be selected from the set [DEIJST@]
lest cachefilesd remove the files because it recognise the name.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-cachefs@redhat.com
---

 fs/cachefiles/Makefile   |    1 
 fs/cachefiles/internal.h |    5 ++
 fs/cachefiles/key.c      |  139 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 145 insertions(+)
 create mode 100644 fs/cachefiles/key.c

On 11/29/21 10:33 PM, David Howells wrote:

> +/*
> + * turn the raw key into something cooked
> + * - the key may be up to NAME_MAX in length (including the length word)
> + *   - "base64" encode the strange keys, mapping 3 bytes of raw to four of
> + *     cooked
> + *   - need to cut the cooked key into 252 char lengths (189 raw bytes)
> + */
> +bool cachefiles_cook_key(struct cachefiles_object *object)
> +{
> +	const u8 *key = fscache_get_key(object->cookie), *kend;
> +	unsigned char ch;
> +	unsigned int acc, i, n, nle, nbe, keylen = object->cookie->key_len;
> +	unsigned int b64len, len, print, pad;
> +	char *name, sep;
> +
> +	_enter(",%u,%*phN", keylen, keylen, key);
> +
> +	BUG_ON(keylen > NAME_MAX - 3);
> +
> +	print = 1;
> +	for (i = 0; i < keylen; i++) {
> +		ch = key[i];
> +		print &= cachefiles_filecharmap[ch];
> +	}
> +
> +	/* If the path is usable ASCII, then we render it directly */
> +	if (print) {
> +		len = 1 + keylen + 1;
> +		name = kmalloc(len, GFP_KERNEL);
> +		if (!name)
> +			return false;
> +
> +		name[0] = 'D'; /* Data object type, string encoding */
> +		name[1 + keylen] = 0;
> +		memcpy(name + 1, key, keylen);
> +		goto success;
			^
If we goto success from here,

> +	}
> +
> +	/* See if it makes sense to encode it as "hex,hex,hex" for each 32-bit
> +	 * chunk.  We rely on the key having been padded out to a whole number
> +	 * of 32-bit words.
> +	 */
> +	n = round_up(keylen, 4);
> +	nbe = nle = 0;
> +	for (i = 0; i < n; i += 4) {
> +		u32 be = be32_to_cpu(*(__be32 *)(key + i));
> +		u32 le = le32_to_cpu(*(__le32 *)(key + i));
> +
> +		nbe += 1 + how_many_hex_digits(be);
> +		nle += 1 + how_many_hex_digits(le);
> +	}
> +
> +	b64len = DIV_ROUND_UP(keylen, 3);
> +	pad = b64len * 3 - keylen;
> +	b64len = 2 + b64len * 4; /* Length if we base64-encode it */
> +	_debug("len=%u nbe=%u nle=%u b64=%u", keylen, nbe, nle, b64len);
> +	if (nbe < b64len || nle < b64len) {
> +		unsigned int nlen = min(nbe, nle) + 1;
> +		name = kmalloc(nlen, GFP_KERNEL);
> +		if (!name)
> +			return false;
> +		sep = (nbe <= nle) ? 'S' : 'T'; /* Encoding indicator */
> +		len = 0;
> +		for (i = 0; i < n; i += 4) {
> +			u32 x;
> +			if (nbe <= nle)
> +				x = be32_to_cpu(*(__be32 *)(key + i));
> +			else
> +				x = le32_to_cpu(*(__le32 *)(key + i));
> +			name[len++] = sep;
> +			if (x != 0)
> +				len += snprintf(name + len, nlen - len, "%x", x);
> +			sep = ',';
> +		}
> +		goto success;
> +	}
> +
> +	/* We need to base64-encode it */
> +	name = kmalloc(b64len + 1, GFP_KERNEL);
> +	if (!name)
> +		return false;
> +
> +	name[0] = 'E';
> +	name[1] = '0' + pad;
> +	len = 2;
> +	kend = key + keylen;
> +	do {
> +		acc  = *key++;
> +		if (key < kend) {
> +			acc |= *key++ << 8;
> +			if (key < kend)
> +				acc |= *key++ << 16;
> +		}
> +
> +		name[len++] = cachefiles_charmap[acc & 63];
> +		acc >>= 6;
> +		name[len++] = cachefiles_charmap[acc & 63];
> +		acc >>= 6;
> +		name[len++] = cachefiles_charmap[acc & 63];
> +		acc >>= 6;
> +		name[len++] = cachefiles_charmap[acc & 63];
> +	} while (key < kend);
> +
> +success:
> +	name[len] = 0;
	     ^
then it seems that this will cause an out-of-boundary access.


> +	object->d_name = name;
> +	object->d_name_len = len;
> +	_leave(" = %s", object->d_name);
> +	return true;
> +}
>

JeffleXu <jefflexu@linux.alibaba.com> wrote:

> > +	/* If the path is usable ASCII, then we render it directly */
> > +	if (print) {
> > +		len = 1 + keylen + 1;
> > +		name = kmalloc(len, GFP_KERNEL);
> > +		if (!name)
> > +			return false;
> > +
> > +		name[0] = 'D'; /* Data object type, string encoding */
> > +		name[1 + keylen] = 0;
> > +		memcpy(name + 1, key, keylen);
> > +		goto success;
> 			^
> If we goto success from here,
> ...
> > +
> > +success:
> > +	name[len] = 0;
> 	     ^
> then it seems that this will cause an out-of-boundary access.

You're right.  I'll change that to:

		len = 1 + keylen;
		name = kmalloc(len + 1, GFP_KERNEL);

and I shouldn't need:

		name[1 + keylen] = 0;

as that's also done after the success label.

David