lib/lzo: fix bugs for very short or empty input

For very short input data (0 - 1 bytes), lzo-rle was not behaving
correctly.  Fix this behaviour and update documentation accordingly.

For zero-length input, lzo v0 outputs an end-of-stream marker only,
which was misinterpreted by lzo-rle as a bitstream version number.
Ensure bitstream versions > 0 require a minimum stream length of 5.

Also fixes a bug in handling the tail for very short inputs when a
bitstream version is present.

Link: http://lkml.kernel.org/r/20190326165857.34613-1-dave.rodgman@arm.comSigned-off-by: NDave Rodgman <dave.rodgman@arm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Documentation/lzo.txt

@@ -102,9 +102,11 @@ Byte sequences
                 dictionary which is empty, and that it will always be
                 invalid at this place.
 
-      17      : bitstream version. If the first byte is 17, the next byte
-                gives the bitstream version (version 1 only). If the first byte
-                is not 17, the bitstream version is 0.
+      17      : bitstream version. If the first byte is 17, and compressed
+                stream length is at least 5 bytes (length of shortest possible
+                versioned bitstream), the next byte gives the bitstream version
+                (version 1 only).
+                Otherwise, the bitstream version is 0.
 
       18..21  : copy 0..3 literals
                 state = (byte - 17) = 0..3  [ copy <state> literals ]

lib/lzo/lzo1x_compress.c

@@ -291,13 +291,14 @@ int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len,
 {
 	const unsigned char *ip = in;
 	unsigned char *op = out;
+	unsigned char *data_start;
 	size_t l = in_len;
 	size_t t = 0;
 	signed char state_offset = -2;
 	unsigned int m4_max_offset;
 
-	// LZO v0 will never write 17 as first byte,
-	// so this is used to version the bitstream
+	// LZO v0 will never write 17 as first byte (except for zero-length
+	// input), so this is used to version the bitstream
 	if (bitstream_version > 0) {
 		*op++ = 17;
 		*op++ = bitstream_version;
@@ -306,6 +307,8 @@ int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len,
 		m4_max_offset = M4_MAX_OFFSET_V0;
 	}
 
+	data_start = op;
+
 	while (l > 20) {
 		size_t ll = l <= (m4_max_offset + 1) ? l : (m4_max_offset + 1);
 		uintptr_t ll_end = (uintptr_t) ip + ll;
@@ -324,7 +327,7 @@ int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len,
 	if (t > 0) {
 		const unsigned char *ii = in + in_len - t;
 
-		if (op == out && t <= 238) {
+		if (op == data_start && t <= 238) {
 			*op++ = (17 + t);
 		} else if (t <= 3) {
 			op[state_offset] |= t;

lib/lzo/lzo1x_decompress_safe.c

@@ -54,11 +54,9 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 	if (unlikely(in_len < 3))
 		goto input_overrun;
 
-	if (likely(*ip == 17)) {
+	if (likely(in_len >= 5) && likely(*ip == 17)) {
 		bitstream_version = ip[1];
 		ip += 2;
-		if (unlikely(in_len < 5))
-			goto input_overrun;
 	} else {
 		bitstream_version = 0;
 	}