[lib] Add ZSTD_c_deterministicRefPrefix

This flag forces zstd to always load the prefix in ext-dict mode, even
if it happens to be contiguous, to force determinism. It also applies to
dictionaries that are re-processed.

A determinism test case is also added, which fails without
`ZSTD_c_deterministicRefPrefix` and passes with it set.

Question: Should this be the default behavior? It isn't in this PR.

diff --git a/lib/compress/zstd_compress.c b/lib/compress/zstd_compress.c
index 6e18b68e5be1f383d63c158b19d2293dd278c69b..6afc05b4637a658f7c29cf36b942dce548f34e40 100644 (file)
--- a/lib/compress/zstd_compress.c
+++ b/lib/compress/zstd_compress.c
@@ -559,6 +559,11 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
         bounds.upperBound = (int)ZSTD_urm_enableRowMatchFinder;
         return bounds;
 
+    case ZSTD_c_deterministicRefPrefix:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 1;
+        return bounds;
+
     default:
         bounds.error = ERROR(parameter_unsupported);
         return bounds;
@@ -622,6 +627,7 @@ static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param)
     case ZSTD_c_validateSequences:
     case ZSTD_c_splitBlocks:
     case ZSTD_c_useRowMatchFinder:
+    case ZSTD_c_deterministicRefPrefix:
     default:
         return 0;
     }
@@ -676,6 +682,7 @@ size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value)
     case ZSTD_c_validateSequences:
     case ZSTD_c_splitBlocks:
     case ZSTD_c_useRowMatchFinder:
+    case ZSTD_c_deterministicRefPrefix:
         break;
 
     default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
@@ -897,6 +904,11 @@ size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams,
         CCtxParams->useRowMatchFinder = (ZSTD_useRowMatchFinderMode_e)value;
         return CCtxParams->useRowMatchFinder;
 
+    case ZSTD_c_deterministicRefPrefix:
+        BOUNDCHECK(ZSTD_c_deterministicRefPrefix, value);
+        CCtxParams->deterministicRefPrefix = !!value;
+        return CCtxParams->deterministicRefPrefix;
+
     default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
     }
 }
@@ -1026,6 +1038,9 @@ size_t ZSTD_CCtxParams_getParameter(
     case ZSTD_c_useRowMatchFinder :
         *value = (int)CCtxParams->useRowMatchFinder;
         break;
+    case ZSTD_c_deterministicRefPrefix:
+        *value = (int)CCtxParams->deterministicRefPrefix;
+        break;
     default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
     }
     return 0;
@@ -4045,11 +4060,12 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,
 
     if (!srcSize) return fhSize;  /* do not generate an empty block if no input */
 
-    if (!ZSTD_window_update(&ms->window, src, srcSize)) {
+    if (!ZSTD_window_update(&ms->window, src, srcSize, ms->forceNonContiguous)) {
+        ms->forceNonContiguous = 0;
         ms->nextToUpdate = ms->window.dictLimit;
     }
     if (cctx->appliedParams.ldmParams.enableLdm) {
-        ZSTD_window_update(&cctx->ldmState.window, src, srcSize);
+        ZSTD_window_update(&cctx->ldmState.window, src, srcSize, /* forceNonContiguous */ 0);
     }
 
     if (!frame) {
@@ -4141,11 +4157,12 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms,
     }
 
     DEBUGLOG(4, "ZSTD_loadDictionaryContent(): useRowMatchFinder=%d", (int)params->useRowMatchFinder);
-    ZSTD_window_update(&ms->window, src, srcSize);
+    ZSTD_window_update(&ms->window, src, srcSize, /* forceNonContiguous */ 0);
     ms->loadedDictEnd = params->forceWindow ? 0 : (U32)(iend - ms->window.base);
+    ms->forceNonContiguous = params->deterministicRefPrefix;
 
     if (loadLdmDict) {
-        ZSTD_window_update(&ls->window, src, srcSize);
+        ZSTD_window_update(&ls->window, src, srcSize, /* forceNonContiguous */ 0);
         ls->loadedDictEnd = params->forceWindow ? 0 : (U32)(iend - ls->window.base);
     }
 

diff --git a/lib/compress/zstd_compress_internal.h b/lib/compress/zstd_compress_internal.h
index c0b01794876ade2d22da7a7a05d321ee5ea45539..18b0131ea6402a5f5e7c89d655733e51481a5895 100644 (file)
--- a/lib/compress/zstd_compress_internal.h
+++ b/lib/compress/zstd_compress_internal.h
@@ -219,6 +219,8 @@ struct ZSTD_matchState_t {
     U32* hashTable3;
     U32* chainTable;
 
+    U32 forceNonContiguous; /* Non-zero if we should force non-contiguous load for the next window update. */
+
     int dedicatedDictSearch;  /* Indicates whether this matchState is using the
                                * dedicated dictionary search structure.
                                */
@@ -317,6 +319,9 @@ struct ZSTD_CCtx_params_s {
     /* Param for deciding whether to use row-based matchfinder */
     ZSTD_useRowMatchFinderMode_e useRowMatchFinder;
 
+    /* Always load a dictionary in ext-dict mode (not prefix mode)? */
+    int deterministicRefPrefix;
+
     /* Internal use, for createCCtxParams() and freeCCtxParams() only */
     ZSTD_customMem customMem;
 };  /* typedef'd to ZSTD_CCtx_params within "zstd.h" */
@@ -1138,7 +1143,8 @@ MEM_STATIC void ZSTD_window_init(ZSTD_window_t* window) {
  * Returns non-zero if the segment is contiguous.
  */
 MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window,
-                                  void const* src, size_t srcSize)
+                                  void const* src, size_t srcSize,
+                                  int forceNonContiguous)
 {
     BYTE const* const ip = (BYTE const*)src;
     U32 contiguous = 1;
@@ -1148,7 +1154,7 @@ MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window,
     assert(window->base != NULL);
     assert(window->dictBase != NULL);
     /* Check if blocks follow each other */
-    if (src != window->nextSrc) {
+    if (src != window->nextSrc || forceNonContiguous) {
         /* not contiguous */
         size_t const distanceFromBase = (size_t)(window->nextSrc - window->base);
         DEBUGLOG(5, "Non contiguous blocks, new segment starts at %u", window->dictLimit);

diff --git a/lib/compress/zstdmt_compress.c b/lib/compress/zstdmt_compress.c
index cfd75cc4932cd3083fce9e9853481ec91909673d..22aa3e1245aca4f29820eeddda415e8b1b5455fc 100644 (file)
--- a/lib/compress/zstdmt_compress.c
+++ b/lib/compress/zstdmt_compress.c
@@ -512,7 +512,7 @@ ZSTDMT_serialState_reset(serialState_t* serialState,
         if (dictSize > 0) {
             if (dictContentType == ZSTD_dct_rawContent) {
                 BYTE const* const dictEnd = (const BYTE*)dict + dictSize;
-                ZSTD_window_update(&serialState->ldmState.window, dict, dictSize);
+                ZSTD_window_update(&serialState->ldmState.window, dict, dictSize, /* forceNonContiguous */ 0);
                 ZSTD_ldm_fillHashTable(&serialState->ldmState, (const BYTE*)dict, dictEnd, &params.ldmParams);
                 serialState->ldmState.loadedDictEnd = params.forceWindow ? 0 : (U32)(dictEnd - serialState->ldmState.window.base);
             } else {
@@ -569,7 +569,7 @@ static void ZSTDMT_serialState_update(serialState_t* serialState,
             assert(seqStore.seq != NULL && seqStore.pos == 0 &&
                    seqStore.size == 0 && seqStore.capacity > 0);
             assert(src.size <= serialState->params.jobSize);
-            ZSTD_window_update(&serialState->ldmState.window, src.start, src.size);
+            ZSTD_window_update(&serialState->ldmState.window, src.start, src.size, /* forceNonContiguous */ 0);
             error = ZSTD_ldm_generateSequences(
                 &serialState->ldmState, &seqStore,
                 &serialState->params.ldmParams, src.start, src.size);
@@ -695,6 +695,10 @@ static void ZSTDMT_compressionJob(void* jobDescription)
         {   size_t const forceWindowError = ZSTD_CCtxParams_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob);
             if (ZSTD_isError(forceWindowError)) JOB_ERROR(forceWindowError);
         }
+        if (!job->firstJob) {
+            size_t const err = ZSTD_CCtxParams_setParameter(&jobParams, ZSTD_c_deterministicRefPrefix, 0);
+            if (ZSTD_isError(err)) JOB_ERROR(err);
+        }
         {   size_t const initError = ZSTD_compressBegin_advanced_internal(cctx,
                                         job->prefix.start, job->prefix.size, ZSTD_dct_rawContent, /* load dictionary in "content-only" mode (no header analysis) */
                                         ZSTD_dtlm_fast,
@@ -750,6 +754,12 @@ static void ZSTDMT_compressionJob(void* jobDescription)
             if (ZSTD_isError(cSize)) JOB_ERROR(cSize);
             lastCBlockSize = cSize;
     }   }
+    if (!job->firstJob) {
+        /* Double check that we don't have an ext-dict, because then our
+         * repcode invalidation doesn't work.
+         */
+        assert(!ZSTD_window_hasExtDict(cctx->blockState.matchState.window));
+    }
     ZSTD_CCtx_trace(cctx, 0);
 
 _endJob:

diff --git a/lib/zstd.h b/lib/zstd.h
index 8f0ba268dc854a4b07a83a0f1dc6c29606ab01f0..a285e26b04aeaff8c95894cd4eb201a5d717e027 100644 (file)
--- a/lib/zstd.h
+++ b/lib/zstd.h
@@ -449,7 +449,8 @@ typedef enum {
      ZSTD_c_experimentalParam11=1008,
      ZSTD_c_experimentalParam12=1009,
      ZSTD_c_experimentalParam13=1010,
-     ZSTD_c_experimentalParam14=1011
+     ZSTD_c_experimentalParam14=1011,
+     ZSTD_c_experimentalParam15=1012
 } ZSTD_cParameter;
 
 typedef struct {
@@ -1859,6 +1860,26 @@ ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* pre
  */
 #define ZSTD_c_useRowMatchFinder ZSTD_c_experimentalParam14
 
+/* ZSTD_c_deterministicRefPrefix
+ * Default is 0 == disabled. Set to 1 to enable.
+ *
+ * Zstd produces different results for prefix compression when the prefix is
+ * directly adjacent to the data about to be compressed vs. when it isn't.
+ * This is because zstd detects that the two buffers are contiguous and it can
+ * use a more efficient match finding algorithm. However, this produces different
+ * results than when the two buffers are non-contiguous. This flag forces zstd
+ * to always load the prefix in non-contiguous mode, even if it happens to be
+ * adjacent to the data, to guarantee determinism.
+ *
+ * If you really care about determinism when using a dictionary or prefix,
+ * like when doing delta compression, you should select this option. It comes
+ * at a speed penalty of about ~2.5% if the dictionary and data happened to be
+ * contiguous, and is free if they weren't contiguous. We don't expect that
+ * intentionally making the dictionary and data contiguous will be worth the
+ * cost to memcpy() the data.
+ */
+#define ZSTD_c_deterministicRefPrefix ZSTD_c_experimentalParam15
+
 /*! ZSTD_CCtx_getParameter() :
  *  Get the requested compression parameter value, selected by enum ZSTD_cParameter,
  *  and store it into int* value.

diff --git a/tests/fuzz/zstd_helpers.c b/tests/fuzz/zstd_helpers.c
index 31bf4c20dad3c4844ac4a7ff561f493e0b8abd35..4d889deeb4550e13c0f5df3438909312428cb370 100644 (file)
--- a/tests/fuzz/zstd_helpers.c
+++ b/tests/fuzz/zstd_helpers.c
@@ -97,6 +97,7 @@ void FUZZ_setRandomParameters(ZSTD_CCtx *cctx, size_t srcSize, FUZZ_dataProducer
     setRand(cctx, ZSTD_c_literalCompressionMode, 0, 2, producer);
     setRand(cctx, ZSTD_c_forceAttachDict, 0, 2, producer);
     setRand(cctx, ZSTD_c_splitBlocks, 0, 1, producer);
+    setRand(cctx, ZSTD_c_deterministicRefPrefix, 0, 1, producer);
     if (FUZZ_dataProducer_uint32Range(producer, 0, 1) == 0) {
       setRand(cctx, ZSTD_c_srcSizeHint, ZSTD_SRCSIZEHINT_MIN, 2 * srcSize, producer);
     }

diff --git a/tests/fuzzer.c b/tests/fuzzer.c
index 2c6c60d3833372b44aecf7bc50974022b0c32e51..17193f23fd07743bc56a52abe780de730eabf134 100644 (file)
--- a/tests/fuzzer.c
+++ b/tests/fuzzer.c
@@ -766,6 +766,50 @@ static int basicUnitTests(U32 const seed, double compressibility)
     }
     DISPLAYLEVEL(3, "OK \n");
 
+    DISPLAYLEVEL(3, "test%3i : testing dict compression for determinism : ", testNb++);
+    {
+        size_t const testSize = 1024;
+        ZSTD_CCtx* const cctx = ZSTD_createCCtx();
+        ZSTD_DCtx* const dctx = ZSTD_createDCtx();
+        char* dict = (char*)malloc(2 * testSize);
+        int ldmEnabled, level;
+
+        RDG_genBuffer(dict, testSize, 0.5, 0.5, seed);
+        RDG_genBuffer(CNBuffer, testSize, 0.6, 0.6, seed);
+        memcpy(dict + testSize, CNBuffer, testSize);
+        for (level = 1; level <= 5; ++level) {
+            for (ldmEnabled = 0; ldmEnabled <= 1; ++ldmEnabled) {
+                size_t cSize0;
+                XXH64_hash_t compressedChecksum0;
+
+                CHECK_Z(ZSTD_CCtx_setParameter(cctx, ZSTD_c_checksumFlag, 1));
+                CHECK_Z(ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, level));
+                CHECK_Z(ZSTD_CCtx_setParameter(cctx, ZSTD_c_enableLongDistanceMatching, ldmEnabled));
+                CHECK_Z(ZSTD_CCtx_setParameter(cctx, ZSTD_c_deterministicRefPrefix, 1));
+
+                CHECK_Z(ZSTD_CCtx_refPrefix(cctx, dict, testSize));
+                cSize = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, testSize);
+                CHECK_Z(cSize);
+                CHECK_Z(ZSTD_decompress_usingDict(dctx, decodedBuffer, testSize, compressedBuffer, cSize, dict, testSize));
+
+                cSize0 = cSize;
+                compressedChecksum0 = XXH64(compressedBuffer, cSize, 0);
+
+                CHECK_Z(ZSTD_CCtx_refPrefix(cctx, dict, testSize));
+                cSize = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, dict + testSize, testSize);
+                CHECK_Z(cSize);
+
+                if (cSize != cSize0) goto _output_error;
+                if (XXH64(compressedBuffer, cSize, 0) != compressedChecksum0) goto _output_error;
+            }
+        }
+
+        ZSTD_freeCCtx(cctx);
+        ZSTD_freeDCtx(dctx);
+        free(dict);
+    }
+    DISPLAYLEVEL(3, "OK \n");
+
     DISPLAYLEVEL(3, "test%3i : LDM + opt parser with small uncompressible block ", testNb++);
     {   ZSTD_CCtx* cctx = ZSTD_createCCtx();
         ZSTD_DCtx* dctx = ZSTD_createDCtx();

diff --git a/tests/zstreamtest.c b/tests/zstreamtest.c
index f2b16db2c56419aa8c67659af01e193a6c414168..14af777cde5abe235b56e4720f1417879183c839 100644 (file)
--- a/tests/zstreamtest.c
+++ b/tests/zstreamtest.c
@@ -2215,6 +2215,7 @@ static int fuzzerTests_newAPI(U32 seed, int nbTests, int startTest,
                 }
 
                 if (FUZ_rand(&lseed) & 1) CHECK_Z( setCCtxParameter(zc, cctxParams, ZSTD_c_forceMaxWindow, FUZ_rand(&lseed) & 1, opaqueAPI) );
+                if (FUZ_rand(&lseed) & 1) CHECK_Z( setCCtxParameter(zc, cctxParams, ZSTD_c_deterministicRefPrefix, FUZ_rand(&lseed) & 1, opaqueAPI) );
 
                 /* Apply parameters */
                 if (opaqueAPI) {