introduce LZ4_decoderRingBufferSize()

fuzzer : fix and robustify ring buffer tests
This commit is contained in:
Yann Collet 2018-05-02 12:56:37 -07:00
parent 1a191b3f8d
commit 93cf628a08
3 changed files with 115 additions and 61 deletions

View File

@ -1431,7 +1431,7 @@ LZ4_FORCE_INLINE int LZ4_decompress_generic(
/* strictly "less than" on input, to re-enter the loop with at least one byte */
likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend)))
{
/* Copy the literals. */
/* Copy the literals */
memcpy(op, ip, endOnInput ? 16 : 8);
op += length; ip += length;
@ -1688,12 +1688,11 @@ int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
return 0;
}
/*!
* LZ4_setStreamDecode() :
* Use this function to instruct where to find the dictionary.
* This function is not necessary if previous data is still available where it was decoded.
* Loading a size of 0 is allowed (same effect as no dictionary).
* Return : 1 if OK, 0 if error
/*! LZ4_setStreamDecode() :
* Use this function to instruct where to find the dictionary.
* This function is not necessary if previous data is still available where it was decoded.
* Loading a size of 0 is allowed (same effect as no dictionary).
* @return : 1 if OK, 0 if error
*/
int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
{
@ -1705,6 +1704,26 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti
return 1;
}
/*! LZ4_decoderRingBufferSize() :
* when setting a ring buffer for streaming decompression (optional scenario),
* provides the minimum size of this ring buffer
* to be compatible with any source respecting maxBlockSize condition.
* Note : in a ring buffer scenario,
* blocks are presumed decompressed next to each other
* up to the moment there is not enough remaining space for next block (remainingSize < maxBlockSize),
* at which stage it resumes from beginning of ring buffer.
* @return : minimum ring buffer size,
* or 0 if there is an error (invalid maxBlockSize).
*/
int LZ4_decoderRingBufferSize(int maxBlockSize)
{
if (maxBlockSize < 0) return 0;
if (maxBlockSize > LZ4_MAX_INPUT_SIZE) return 0;
if (maxBlockSize < 16) maxBlockSize = 16;
return LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize);
}
/*
*_continue() :
These decoding functions allow decompression of multiple blocks in "streaming" mode.

View File

@ -293,45 +293,62 @@ LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int maxD
* Streaming Decompression Functions
* Bufferless synchronous API
************************************************/
typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* incomplete type (defined later) */
typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* tracking context */
/*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() :
* creation / destruction of streaming decompression tracking structure.
* A tracking structure can be re-used multiple times sequentially. */
* creation / destruction of streaming decompression tracking context.
* A tracking context can be re-used multiple times.
*/
LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void);
LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream);
/*! LZ4_setStreamDecode() :
* An LZ4_streamDecode_t structure can be allocated once and re-used multiple times.
* An LZ4_streamDecode_t context can be allocated once and re-used multiple times.
* Use this function to start decompression of a new stream of blocks.
* A dictionary can optionnally be set. Use NULL or size 0 for a reset order.
* Dictionary is presumed stable : it must remain accessible and unmodified during next decompression.
* @return : 1 if OK, 0 if error
*/
LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize);
/*! LZ4_decoderRingBufferSize() : v1.8.2
* Note : in a ring buffer scenario (optional),
* blocks are presumed decompressed next to each other
* up to the moment there is not enough remaining space for next block (remainingSize < maxBlockSize),
* at which stage it resumes from beginning of ring buffer.
* When setting such a ring buffer for streaming decompression,
* provides the minimum size of this ring buffer
* to be compatible with any source respecting maxBlockSize condition.
* @return : minimum ring buffer size,
* or 0 if there is an error (invalid maxBlockSize).
*/
LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize);
#define LZ4_DECODER_RING_BUFFER_SIZE(mbs) (65536 + 14 + (mbs)) /* for static allocation; mbs presumed valid */
/*! LZ4_decompress_*_continue() :
* These decoding functions allow decompression of consecutive blocks in "streaming" mode.
* A block is an unsplittable entity, it must be presented entirely to a decompression function.
* Decompression functions only accept one block at a time.
* Decompression functions only accepts one block at a time.
* The last 64KB of previously decoded data *must* remain available and unmodified at the memory position where they were decoded.
* If less than 64KB of data has been decoded all the data must be present.
* If less than 64KB of data has been decoded, all the data must be present.
*
* Special : if application sets a ring buffer for decompression, it must respect one of the following conditions :
* Special : if decompression side sets a ring buffer, it must respect one of the following conditions :
* - Decompression buffer size is _at least_ LZ4_decoderRingBufferSize(maxBlockSize).
* maxBlockSize is the maximum size of any single block. It can have any value > 16 bytes.
* In which case, encoding and decoding buffers do not need to be synchronized.
* Actually, data can be produced by any source compliant with LZ4 format specification, and respecting maxBlockSize.
* - Synchronized mode :
* Decompression buffer size is _exactly_ the same as compression buffer size,
* and follows exactly same update rule (block boundaries at same positions),
* and decoding function is provided with exact decompressed size of each block (exception for last block of the stream),
* _then_ decoding & encoding ring buffer can have any size, including small ones ( < 64 KB).
* - Decompression buffer is larger than encoding buffer, by a minimum of maxBlockSize more bytes.
* maxBlockSize is the maximum size of any single block. It is implementation dependent, and can have any value (presumed > 16 bytes).
* In which case, encoding and decoding buffers do not need to be synchronized,
* and encoding ring buffer can have any size, including small ones ( < 64 KB).
* - Decompression buffer size is _at least_ 64 KB + 8 bytes + maxBlockSize.
* In which case, encoding and decoding buffers do not need to be synchronized,
* and encoding ring buffer can have any size, including larger than decoding buffer.
* - Decompression buffer size is exactly the same as compression buffer size,
* and follows exactly same update rule (block boundaries at same positions).
* If the decoding function is provided with the exact decompressed size of each block,
* then decoding & encoding ring buffer can have any size, including very small ones ( < 64 KB).
* If the decoding function only knows the compressed size,
* then buffer size must be a minimum of 64 KB + 8 bytes + maxBlockSize.
* Whenever these conditions are not possible, save the last 64KB of decoded data into a safe buffer,
* and indicate where it is saved using LZ4_setStreamDecode() before decompressing next block.
*
* Whenever these conditions are not possible,
* save the last 64KB of decoded data into a safe buffer where it can't be modified during decompression,
* then indicate where this data is saved using LZ4_setStreamDecode(), before decompressing next block.
*/
LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int srcSize, int dstCapacity);
LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize);
@ -341,6 +358,7 @@ LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecod
* These decoding functions work the same as
* a combination of LZ4_setStreamDecode() followed by LZ4_decompress_*_continue()
* They are stand-alone, and don't need an LZ4_streamDecode_t structure.
* Dictionary is presumed stable : it must remain accessible and unmodified during next decompression.
*/
LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize);
LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize);

View File

@ -47,6 +47,7 @@
#include <stdio.h> /* fgets, sscanf */
#include <string.h> /* strcmp */
#include <time.h> /* clock_t, clock, CLOCKS_PER_SEC */
#include <assert.h>
#define LZ4_STATIC_LINKING_ONLY
#define LZ4_HC_STATIC_LINKING_ONLY
#include "lz4hc.h"
@ -953,6 +954,7 @@ static void FUZ_unitTests(int compressionLevel)
const unsigned cycleNb= 0;
char testInput[testInputSize];
char testCompressed[testCompressedSize];
size_t const testVerifySize = testInputSize;
char testVerify[testInputSize];
char ringBuffer[ringBufferSize];
U32 randState = 1;
@ -1197,19 +1199,28 @@ static void FUZ_unitTests(int compressionLevel)
}
}
/* small decoder-side ring buffer test */
/* Ring buffer test : Non synchronized decoder */
/* This test uses minimum amount of memory required to setup a decoding ring buffer
* while being unsynchronized with encoder
* (no assumption done on how the data is encoded, it just follows LZ4 format specification).
* This size is documented in lz4.h, and is LZ4_decoderRingBufferSize(maxBlockSize).
*/
{ XXH64_state_t xxhOrig;
XXH64_state_t xxhNewSafe, xxhNewFast;
LZ4_streamDecode_t decodeStateSafe, decodeStateFast;
const U32 maxMessageSizeLog = 12;
const U32 maxMessageSizeMask = (1<<maxMessageSizeLog) - 1;
U32 messageSize;
const int maxMessageSizeLog = 12;
const int maxMessageSize = 1 << maxMessageSizeLog;
const int maxMessageSizeMask = maxMessageSize - 1;
int messageSize;
U32 totalMessageSize = 0;
U32 iNext = 0;
U32 dNext = 0;
const U32 dBufferSize = 64 KB;
const int dBufferSize = LZ4_decoderRingBufferSize(maxMessageSize);
char* const ringBufferSafe = testVerify;
char* const ringBufferFast = testVerify + dBufferSize + 1; /* used by LZ4_decompress_fast_continue */
int iNext = 0;
int dNext = 0;
int compressedSize;
assert((size_t)(dBufferSize + 1 + dBufferSize) < testVerifySize); /* space used by ringBufferSafe and ringBufferFast */
XXH64_reset(&xxhOrig, 0);
XXH64_reset(&xxhNewSafe, 0);
XXH64_reset(&xxhNewFast, 0);
@ -1217,38 +1228,40 @@ static void FUZ_unitTests(int compressionLevel)
LZ4_setStreamDecode(&decodeStateSafe, NULL, 0);
LZ4_setStreamDecode(&decodeStateFast, NULL, 0);
#define BSIZE1 65537
#define BSIZE2 16435
#define BSIZE1 (dBufferSize - (maxMessageSize-1))
/* first block */
messageSize = BSIZE1;
messageSize = BSIZE1; /* note : we cheat a bit here, in theory no message should be > maxMessageSize. We just want to fill the decoding ring buffer once. */
assert(messageSize < dBufferSize);
XXH64_update(&xxhOrig, testInput + iNext, messageSize);
crcOrig = XXH64_digest(&xxhOrig);
compressedSize = LZ4_compress_HC_continue(&sHC, testInput + iNext, testCompressed, messageSize, testCompressedSize-ringBufferSize);
FUZ_CHECKTEST(compressedSize==0, "LZ4_compress_HC_continue() compression failed");
result = LZ4_decompress_safe_continue(&decodeStateSafe, testCompressed, testVerify + dNext, compressedSize, messageSize);
FUZ_CHECKTEST(result!=(int)messageSize, "64K D.ringBuffer : LZ4_decompress_safe_continue() test failed");
result = LZ4_decompress_safe_continue(&decodeStateSafe, testCompressed, ringBufferSafe + dNext, compressedSize, messageSize);
FUZ_CHECKTEST(result!=messageSize, "64K D.ringBuffer : LZ4_decompress_safe_continue() test failed");
XXH64_update(&xxhNewSafe, testVerify + dNext, messageSize);
XXH64_update(&xxhNewSafe, ringBufferSafe + dNext, messageSize);
{ U64 const crcNew = XXH64_digest(&xxhNewSafe);
FUZ_CHECKTEST(crcOrig!=crcNew, "LZ4_decompress_safe_continue() decompression corruption"); }
result = LZ4_decompress_fast_continue(&decodeStateFast, testCompressed, testVerify + dNext, messageSize);
result = LZ4_decompress_fast_continue(&decodeStateFast, testCompressed, ringBufferFast + dNext, messageSize);
FUZ_CHECKTEST(result!=compressedSize, "64K D.ringBuffer : LZ4_decompress_fast_continue() test failed");
XXH64_update(&xxhNewFast, testVerify + dNext, messageSize);
XXH64_update(&xxhNewFast, ringBufferFast + dNext, messageSize);
{ U64 const crcNew = XXH64_digest(&xxhNewFast);
FUZ_CHECKTEST(crcOrig!=crcNew, "LZ4_decompress_fast_continue() decompression corruption"); }
/* prepare next message */
/* prepare second message */
dNext += messageSize;
totalMessageSize += messageSize;
messageSize = BSIZE2;
iNext = 132000;
memcpy(testInput + iNext, testInput + 8, messageSize);
if (dNext > dBufferSize) dNext = 0;
messageSize = maxMessageSize;
iNext = BSIZE1+1;
assert(BSIZE1 >= 65535);
memcpy(testInput + iNext, testInput + (BSIZE1-65535), messageSize); /* will generate a match at max distance == 65535 */
FUZ_CHECKTEST(dNext+messageSize <= dBufferSize, "Ring buffer test : second message should require restarting from beginning");
dNext = 0;
while (totalMessageSize < 9 MB) {
XXH64_update(&xxhOrig, testInput + iNext, messageSize);
@ -1256,32 +1269,36 @@ static void FUZ_unitTests(int compressionLevel)
compressedSize = LZ4_compress_HC_continue(&sHC, testInput + iNext, testCompressed, messageSize, testCompressedSize-ringBufferSize);
FUZ_CHECKTEST(compressedSize==0, "LZ4_compress_HC_continue() compression failed");
DISPLAYLEVEL(5, "compressed %i bytes to %i bytes \n", messageSize, compressedSize);
#if 1 /* Because the ring buffer is small, decompression overwrites part of the output which
* is first used as dictionary. Hence only one decompression function can be tested. */
result = LZ4_decompress_safe_continue(&decodeStateSafe, testCompressed, testVerify + dNext, compressedSize, messageSize);
FUZ_CHECKTEST(result!=(int)messageSize, "64K D.ringBuffer : LZ4_decompress_safe_continue() test failed");
XXH64_update(&xxhNewSafe, testVerify + dNext, messageSize);
/* test LZ4_decompress_safe_continue */
assert(dNext < dBufferSize);
assert(dBufferSize - dNext >= maxMessageSize);
result = LZ4_decompress_safe_continue(&decodeStateSafe,
testCompressed, ringBufferSafe + dNext,
compressedSize, dBufferSize - dNext); /* works without knowing messageSize, but under assumption that messageSize < maxMessageSize */
FUZ_CHECKTEST(result!=messageSize, "D.ringBuffer : LZ4_decompress_safe_continue() test failed");
XXH64_update(&xxhNewSafe, ringBufferSafe + dNext, messageSize);
{ U64 const crcNew = XXH64_digest(&xxhNewSafe);
if (crcOrig != crcNew) FUZ_findDiff(testInput + iNext, testVerify + dNext);
FUZ_CHECKTEST(crcOrig!=crcNew, "LZ4_decompress_safe_continue() decompression corruption during small decoder-side ring buffer test");
if (crcOrig != crcNew) FUZ_findDiff(testInput + iNext, ringBufferSafe + dNext);
FUZ_CHECKTEST(crcOrig!=crcNew, "LZ4_decompress_safe_continue() decompression corruption during D.ringBuffer test");
}
#else
result = LZ4_decompress_fast_continue(&decodeStateFast, testCompressed, testVerify + dNext, messageSize);
FUZ_CHECKTEST(result!=compressedSize, "64K D.ringBuffer : LZ4_decompress_fast_continue() test failed");
XXH64_update(&xxhNewFast, testVerify + dNext, messageSize);
/* test LZ4_decompress_fast_continue in its own buffer ringBufferFast */
result = LZ4_decompress_fast_continue(&decodeStateFast, testCompressed, ringBufferFast + dNext, messageSize);
FUZ_CHECKTEST(result!=compressedSize, "D.ringBuffer : LZ4_decompress_fast_continue() test failed");
XXH64_update(&xxhNewFast, ringBufferFast + dNext, messageSize);
{ U64 const crcNew = XXH64_digest(&xxhNewFast);
if (crcOrig != crcNew) FUZ_findDiff(testInput + iNext, testVerify + dNext);
FUZ_CHECKTEST(crcOrig!=crcNew, "LZ4_decompress_fast_continue() decompression corruption during small decoder-side ring buffer test");
if (crcOrig != crcNew) FUZ_findDiff(testInput + iNext, ringBufferFast + dNext);
FUZ_CHECKTEST(crcOrig!=crcNew, "LZ4_decompress_fast_continue() decompression corruption during D.ringBuffer test");
}
#endif
/* prepare next message */
dNext += messageSize;
totalMessageSize += messageSize;
messageSize = (FUZ_rand(&randState) & maxMessageSizeMask) + 1;
iNext = (FUZ_rand(&randState) & 65535);
if (dNext > dBufferSize) dNext = 0;
if (dNext + maxMessageSize > dBufferSize) dNext = 0;
}
}
}