ddidderr/zstd-rs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Guard against invalid sequences from external matchfinders (#3465)

Browse Source
This commit is contained in:
Elliot Gorokhovsky
2023-01-31 13:55:48 -05:00
committed by GitHub
parent 4794bbfe00
commit 64052ef57d
5 changed files with 96 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/zstd_compress.c
+31 -13
View File
@@ -277,14 +277,8 @@ static ZSTD_paramSwitch_e ZSTD_resolveEnableLdm(ZSTD_paramSwitch_e mode,
return (cParams->strategy >= ZSTD_btopt && cParams->windowLog >= 27) ? ZSTD_ps_enable : ZSTD_ps_disable;
}
/* Enables validation for external sequences in debug builds. */
static int ZSTD_resolveExternalSequenceValidation(int mode) {
#if defined(DEBUGLEVEL) && (DEBUGLEVEL>=2)
(void)mode;
return 1;
#else
return mode;
#endif
}
/* Resolves maxBlockSize to the default if no value is present. */
@@ -3050,6 +3044,23 @@ static size_t ZSTD_postProcessExternalMatchFinderResult(
}
}
/* ZSTD_fastSequenceLengthSum() :
* Returns sum(litLen) + sum(matchLen) + lastLits for *seqBuf*.
* Similar to another function in zstd_compress.c (determine_blockSize),
* except it doesn't check for a block delimiter to end summation.
* Removing the early exit allows the compiler to auto-vectorize (https://godbolt.org/z/cY1cajz9P).
* This function can be deleted and replaced by determine_blockSize after we resolve issue #3456. */
static size_t ZSTD_fastSequenceLengthSum(ZSTD_Sequence const* seqBuf, size_t seqBufSize) {
size_t matchLenSum, litLenSum, i;
matchLenSum = 0;
litLenSum = 0;
for (i = 0; i < seqBufSize; i++) {
litLenSum += seqBuf[i].litLength;
matchLenSum += seqBuf[i].matchLength;
}
return litLenSum + matchLenSum;
}
typedef enum { ZSTDbss_compress, ZSTDbss_noCompress } ZSTD_buildSeqStore_e;
static size_t ZSTD_buildSeqStore(ZSTD_CCtx* zc, const void* src, size_t srcSize)
@@ -3167,8 +3178,15 @@ static size_t ZSTD_buildSeqStore(ZSTD_CCtx* zc, const void* src, size_t srcSize)
/* Return early if there is no error, since we don't need to worry about last literals */
if (!ZSTD_isError(nbPostProcessedSeqs)) {
ZSTD_sequencePosition seqPos = {0,0,0};
ZSTD_copySequencesToSeqStoreExplicitBlockDelim(
zc, &seqPos, zc->externalMatchCtx.seqBuffer, nbPostProcessedSeqs, src, srcSize
size_t const seqLenSum = ZSTD_fastSequenceLengthSum(zc->externalMatchCtx.seqBuffer, nbPostProcessedSeqs);
RETURN_ERROR_IF(seqLenSum > srcSize, externalSequences_invalid, "External sequences imply too large a block!");
FORWARD_IF_ERROR(
ZSTD_copySequencesToSeqStoreExplicitBlockDelim(
zc, &seqPos,
zc->externalMatchCtx.seqBuffer, nbPostProcessedSeqs,
src, srcSize
),
"Failed to copy external sequences to seqStore!"
);
ms->ldmSeqStore = NULL;
DEBUGLOG(5, "Copied %lu sequences from external matchfinder to internal seqStore.", (unsigned long)nbExternalSeqs);
@@ -6286,7 +6304,7 @@ ZSTD_copySequencesToSeqStoreExplicitBlockDelim(ZSTD_CCtx* cctx,
ip += inSeqs[idx].litLength;
seqPos->posInSrc += inSeqs[idx].litLength;
}
RETURN_ERROR_IF(ip != iend, corruption_detected, "Blocksize doesn't agree with block delimiter!");
RETURN_ERROR_IF(ip != iend, externalSequences_invalid, "Blocksize doesn't agree with block delimiter!");
seqPos->idx = idx+1;
return 0;
}
@@ -6444,13 +6462,13 @@ blockSize_explicitDelimiter(const ZSTD_Sequence* inSeqs, size_t inSeqsSize, ZSTD
blockSize += inSeqs[spos].litLength + inSeqs[spos].matchLength;
if (end) {
if (inSeqs[spos].matchLength != 0)
RETURN_ERROR(corruption_detected, "delimiter format error : both matchlength and offset must be == 0");
RETURN_ERROR(externalSequences_invalid, "delimiter format error : both matchlength and offset must be == 0");
break;
}
spos++;
}
if (!end)
RETURN_ERROR(corruption_detected, "Reached end of sequences without finding a block delimiter");
RETURN_ERROR(externalSequences_invalid, "Reached end of sequences without finding a block delimiter");
return blockSize;
}
@@ -6471,9 +6489,9 @@ static size_t determine_blockSize(ZSTD_sequenceFormat_e mode,
{ size_t const explicitBlockSize = blockSize_explicitDelimiter(inSeqs, inSeqsSize, seqPos);
FORWARD_IF_ERROR(explicitBlockSize, "Error while determining block size with explicit delimiters");
if (explicitBlockSize > blockSize)
RETURN_ERROR(corruption_detected, "sequences incorrectly define a too large block");
RETURN_ERROR(externalSequences_invalid, "sequences incorrectly define a too large block");
if (explicitBlockSize > remaining)
RETURN_ERROR(srcSize_wrong, "sequences define a frame longer than source");
RETURN_ERROR(externalSequences_invalid, "sequences define a frame longer than source");
return explicitBlockSize;
}
}