[libFuzzer] simplify the DFT trace collection using the new faster DFSan mode that traces up to 16 labels at a time and never runs out of labels. Second attempt. This time with a fix for windows (putenv instead of setenv))

llvm-svn: 363445
This commit is contained in:
Kostya Serebryany 2019-06-14 19:54:32 +00:00
parent 1b091540d2
commit 3f39123d15
6 changed files with 172 additions and 184 deletions

View File

@ -120,12 +120,6 @@ static Vector<uint8_t> DFTStringToVector(const std::string &DFTString) {
return DFT;
}
static std::ostream &operator<<(std::ostream &OS, const Vector<uint8_t> &DFT) {
for (auto B : DFT)
OS << (B ? "1" : "0");
return OS;
}
static bool ParseError(const char *Err, const std::string &Line) {
Printf("DataFlowTrace: parse error: %s: Line: %s\n", Err, Line.c_str());
return false;
@ -246,74 +240,25 @@ int CollectDataFlow(const std::string &DFTBinary, const std::string &DirPath,
const Vector<SizedFile> &CorporaFiles) {
Printf("INFO: collecting data flow: bin: %s dir: %s files: %zd\n",
DFTBinary.c_str(), DirPath.c_str(), CorporaFiles.size());
static char DFSanEnv[] = "DFSAN_OPTIONS=fast16labels=1:warn_unimplemented=0";
putenv(DFSanEnv);
MkDir(DirPath);
auto Temp = TempPath(".dft");
for (auto &F : CorporaFiles) {
// For every input F we need to collect the data flow and the coverage.
// Data flow collection may fail if we request too many DFSan tags at once.
// So, we start from requesting all tags in range [0,Size) and if that fails
// we then request tags in [0,Size/2) and [Size/2, Size), and so on.
// Function number => DFT.
auto OutPath = DirPlusFile(DirPath, Hash(FileToVector(F.File)));
std::unordered_map<size_t, Vector<uint8_t>> DFTMap;
std::unordered_set<std::string> Cov;
std::queue<std::pair<size_t, size_t>> Q;
Q.push({0, F.Size});
while (!Q.empty()) {
auto R = Q.front();
Printf("\n\n\n********* Trying: [%zd, %zd)\n", R.first, R.second);
Q.pop();
Command Cmd;
Cmd.addArgument(DFTBinary);
Cmd.addArgument(std::to_string(R.first));
Cmd.addArgument(std::to_string(R.second));
Cmd.addArgument(F.File);
Cmd.addArgument(Temp);
Printf("CMD: %s\n", Cmd.toString().c_str());
if (ExecuteCommand(Cmd)) {
// DFSan has failed, collect tags for two subsets.
if (R.second - R.first >= 2) {
size_t Mid = (R.second + R.first) / 2;
Q.push({R.first, Mid});
Q.push({Mid, R.second});
}
} else {
Printf("********* Success: [%zd, %zd)\n", R.first, R.second);
std::ifstream IF(Temp);
std::string L;
while (std::getline(IF, L, '\n')) {
// Data flow collection has succeeded.
// Merge the results with the other runs.
if (L.empty()) continue;
if (L[0] == 'C') {
// Take coverage lines as is, they will be the same in all attempts.
Cov.insert(L);
} else if (L[0] == 'F') {
size_t FunctionNum = 0;
std::string DFTString;
if (ParseDFTLine(L, &FunctionNum, &DFTString)) {
auto &DFT = DFTMap[FunctionNum];
if (DFT.empty()) {
// Haven't seen this function before, take DFT as is.
DFT = DFTStringToVector(DFTString);
} else if (DFT.size() == DFTString.size()) {
// Have seen this function already, merge DFTs.
DFTStringAppendToVector(&DFT, DFTString);
}
}
}
}
}
}
auto OutPath = DirPlusFile(DirPath, Hash(FileToVector(F.File)));
// Dump combined DFT to disk.
Printf("Producing DFT for %s\n", OutPath.c_str());
std::ofstream OF(OutPath);
for (auto &DFT: DFTMap)
OF << "F" << DFT.first << " " << DFT.second << std::endl;
for (auto &C : Cov)
OF << C << std::endl;
Command Cmd;
Cmd.addArgument(DFTBinary);
Cmd.addArgument(F.File);
Cmd.addArgument(OutPath);
Printf("CMD: %s\n", Cmd.toString().c_str());
ExecuteCommand(Cmd);
}
RemoveFile(Temp);
// Write functions.txt if it's currently empty or doesn't exist.
auto FunctionsTxtPath = DirPlusFile(DirPath, kFunctionsTxt);
if (FileToString(FunctionsTxtPath).empty()) {

View File

@ -89,6 +89,7 @@ struct GlobalEnv {
std::string DFTDir;
std::string DataFlowBinary;
Set<uint32_t> Features, Cov;
Set<std::string> FilesWithDFT;
Vector<std::string> Files;
Random *Rand;
std::chrono::system_clock::time_point ProcessStartTime;
@ -126,10 +127,13 @@ struct GlobalEnv {
auto Job = new FuzzJob;
std::string Seeds;
if (size_t CorpusSubsetSize =
std::min(Files.size(), (size_t)sqrt(Files.size() + 2)))
for (size_t i = 0; i < CorpusSubsetSize; i++)
Seeds += (Seeds.empty() ? "" : ",") +
Files[Rand->SkewTowardsLast(Files.size())];
std::min(Files.size(), (size_t)sqrt(Files.size() + 2))) {
for (size_t i = 0; i < CorpusSubsetSize; i++) {
auto &SF = Files[Rand->SkewTowardsLast(Files.size())];
Seeds += (Seeds.empty() ? "" : ",") + SF;
CollectDFT(SF);
}
}
if (!Seeds.empty()) {
Job->SeedListPath =
DirPlusFile(TempDir, std::to_string(JobId) + ".seeds");
@ -196,7 +200,6 @@ struct GlobalEnv {
auto NewPath = DirPlusFile(MainCorpusDir, Hash(U));
WriteToFile(U, NewPath);
Files.push_back(NewPath);
CollectDFT(NewPath);
}
Features.insert(NewFeatures.begin(), NewFeatures.end());
Cov.insert(NewCov.begin(), NewCov.end());
@ -217,6 +220,7 @@ struct GlobalEnv {
void CollectDFT(const std::string &InputPath) {
if (DataFlowBinary.empty()) return;
if (!FilesWithDFT.insert(InputPath).second) return;
Command Cmd(Args);
Cmd.removeFlag("fork");
Cmd.removeFlag("runs");
@ -226,7 +230,7 @@ struct GlobalEnv {
Cmd.removeArgument(C);
Cmd.setOutputFile(DirPlusFile(TempDir, "dft.log"));
Cmd.combineOutAndErr();
// Printf("CollectDFT: %s %s\n", InputPath.c_str(), Cmd.toString().c_str());
// Printf("CollectDFT: %s\n", Cmd.toString().c_str());
ExecuteCommand(Cmd);
}
@ -296,9 +300,6 @@ void FuzzWithFork(Random &Rand, const FuzzingOptions &Options,
CrashResistantMerge(Env.Args, {}, SeedFiles, &Env.Files, {}, &Env.Features,
{}, &Env.Cov,
CFPath, false);
for (auto &F : Env.Files)
Env.CollectDFT(F);
RemoveFile(CFPath);
Printf("INFO: -fork=%d: %zd seed inputs, starting to fuzz in %s\n", NumJobs,
Env.Files.size(), Env.TempDir.c_str());

View File

@ -35,7 +35,8 @@
// Run:
// # Collect data flow and coverage for INPUT_FILE
// # write to OUTPUT_FILE (default: stdout)
// ./a.out FIRST_LABEL LAST_LABEL INPUT_FILE [OUTPUT_FILE]
// export DFSAN_OPTIONS=fast16labels=1:warn_unimplemented=0
// ./a.out INPUT_FILE [OUTPUT_FILE]
//
// # Print all instrumented functions. llvm-symbolizer must be present in PATH
// ./a.out
@ -48,8 +49,6 @@
// C1 8
// ===============
// "FN xxxxxxxxxx": tells what bytes of the input does the function N depend on.
// The byte string is LEN+1 bytes. The last byte is set if the function
// depends on the input length.
// "CN X Y Z T": tells that a function N has basic blocks X, Y, and Z covered
// in addition to the function's entry block, out of T total instrumented
// blocks.
@ -72,22 +71,20 @@ __attribute__((weak)) extern int LLVMFuzzerInitialize(int *argc, char ***argv);
} // extern "C"
static size_t InputLen;
static size_t InputLabelBeg;
static size_t InputLabelEnd;
static size_t InputSizeLabel;
static size_t NumIterations;
static size_t NumFuncs, NumGuards;
static uint32_t *GuardsBeg, *GuardsEnd;
static const uintptr_t *PCsBeg, *PCsEnd;
static __thread size_t CurrentFunc;
static dfsan_label *FuncLabels; // Array of NumFuncs elements.
static __thread size_t CurrentFunc, CurrentIteration;
static dfsan_label **FuncLabels; // NumFuncs x NumIterations.
static bool *BBExecuted; // Array of NumGuards elements.
static char *PrintableStringForLabel; // InputLen + 2 bytes.
static bool LabelSeen[1 << 8 * sizeof(dfsan_label)];
enum {
PCFLAG_FUNC_ENTRY = 1,
};
const int kNumLabels = 16;
static inline bool BlockIsEntry(size_t BlockIdx) {
return PCsBeg[BlockIdx * 2 + 1] & PCFLAG_FUNC_ENTRY;
}
@ -112,35 +109,32 @@ static int PrintFunctions() {
return 0;
}
extern "C"
void SetBytesForLabel(dfsan_label L, char *Bytes) {
if (LabelSeen[L])
return;
LabelSeen[L] = true;
assert(L);
if (L < InputSizeLabel) {
Bytes[L + InputLabelBeg - 1] = '1';
} else if (L == InputSizeLabel) {
Bytes[InputLen] = '1';
} else {
auto *DLI = dfsan_get_label_info(L);
SetBytesForLabel(DLI->l1, Bytes);
SetBytesForLabel(DLI->l2, Bytes);
}
}
static char *GetPrintableStringForLabel(dfsan_label L) {
memset(PrintableStringForLabel, '0', InputLen + 1);
PrintableStringForLabel[InputLen + 1] = 0;
memset(LabelSeen, 0, sizeof(LabelSeen));
SetBytesForLabel(L, PrintableStringForLabel);
return PrintableStringForLabel;
static void PrintBinary(FILE *Out, dfsan_label L, size_t Len) {
char buf[kNumLabels + 1];
assert(Len <= kNumLabels);
for (int i = 0; i < kNumLabels; i++)
buf[i] = (L & (1 << i)) ? '1' : '0';
buf[Len] = 0;
fprintf(Out, "%s", buf);
}
static void PrintDataFlow(FILE *Out) {
for (size_t I = 0; I < NumFuncs; I++)
if (FuncLabels[I])
fprintf(Out, "F%zd %s\n", I, GetPrintableStringForLabel(FuncLabels[I]));
for (size_t Func = 0; Func < NumFuncs; Func++) {
bool HasAny = false;
for (size_t Iter = 0; Iter < NumIterations; Iter++)
if (FuncLabels[Func][Iter])
HasAny = true;
if (!HasAny)
continue;
fprintf(Out, "F%zd ", Func);
size_t LenOfLastIteration = kNumLabels;
if (auto Tail = InputLen % kNumLabels)
LenOfLastIteration = Tail;
for (size_t Iter = 0; Iter < NumIterations; Iter++)
PrintBinary(Out, FuncLabels[Func][Iter],
Iter == NumIterations - 1 ? LenOfLastIteration : kNumLabels);
fprintf(Out, "\n");
}
}
static void PrintCoverage(FILE *Out) {
@ -169,12 +163,9 @@ int main(int argc, char **argv) {
LLVMFuzzerInitialize(&argc, &argv);
if (argc == 1)
return PrintFunctions();
assert(argc == 4 || argc == 5);
InputLabelBeg = atoi(argv[1]);
InputLabelEnd = atoi(argv[2]);
assert(InputLabelBeg < InputLabelEnd);
assert(argc == 2 || argc == 3);
const char *Input = argv[3];
const char *Input = argv[1];
fprintf(stderr, "INFO: reading '%s'\n", Input);
FILE *In = fopen(Input, "r");
assert(In);
@ -184,30 +175,35 @@ int main(int argc, char **argv) {
unsigned char *Buf = (unsigned char*)malloc(InputLen);
size_t NumBytesRead = fread(Buf, 1, InputLen, In);
assert(NumBytesRead == InputLen);
PrintableStringForLabel = (char*)malloc(InputLen + 2);
fclose(In);
fprintf(stderr, "INFO: running '%s'\n", Input);
for (size_t I = 1; I <= InputLen; I++) {
size_t Idx = I - 1;
if (Idx >= InputLabelBeg && Idx < InputLabelEnd) {
dfsan_label L = dfsan_create_label("", nullptr);
assert(L == I - InputLabelBeg);
dfsan_set_label(L, Buf + Idx, 1);
}
}
dfsan_label SizeL = dfsan_create_label("", nullptr);
InputSizeLabel = SizeL;
assert(InputSizeLabel == InputLabelEnd - InputLabelBeg + 1);
dfsan_set_label(SizeL, &InputLen, sizeof(InputLen));
NumIterations = (NumBytesRead + kNumLabels - 1) / kNumLabels;
FuncLabels = (dfsan_label**)calloc(NumFuncs, sizeof(dfsan_label*));
for (size_t Func = 0; Func < NumFuncs; Func++)
FuncLabels[Func] =
(dfsan_label *)calloc(NumIterations, sizeof(dfsan_label));
LLVMFuzzerTestOneInput(Buf, InputLen);
for (CurrentIteration = 0; CurrentIteration < NumIterations;
CurrentIteration++) {
fprintf(stderr, "INFO: running '%s' %zd/%zd\n", Input, CurrentIteration,
NumIterations);
dfsan_flush();
dfsan_set_label(0, Buf, InputLen);
size_t BaseIdx = CurrentIteration * kNumLabels;
size_t LastIdx = BaseIdx + kNumLabels < NumBytesRead ? BaseIdx + kNumLabels
: NumBytesRead;
assert(BaseIdx < LastIdx);
for (size_t Idx = BaseIdx; Idx < LastIdx; Idx++)
dfsan_set_label(1 << (Idx - BaseIdx), Buf + Idx, 1);
LLVMFuzzerTestOneInput(Buf, InputLen);
}
free(Buf);
bool OutIsStdout = argc == 4;
bool OutIsStdout = argc == 2;
fprintf(stderr, "INFO: writing dataflow to %s\n",
OutIsStdout ? "<stdout>" : argv[4]);
FILE *Out = OutIsStdout ? stdout : fopen(argv[4], "w");
OutIsStdout ? "<stdout>" : argv[2]);
FILE *Out = OutIsStdout ? stdout : fopen(argv[2], "w");
PrintDataFlow(Out);
PrintCoverage(Out);
if (!OutIsStdout) fclose(Out);
@ -237,7 +233,6 @@ void __sanitizer_cov_pcs_init(const uintptr_t *pcs_beg,
GuardsBeg[i] = NumFuncs;
}
}
FuncLabels = (dfsan_label*)calloc(NumFuncs, sizeof(dfsan_label));
BBExecuted = (bool*)calloc(NumGuards, sizeof(bool));
fprintf(stderr, "INFO: %zd instrumented function(s) observed "
"and %zd basic blocks\n", NumFuncs, NumGuards);
@ -258,14 +253,13 @@ void __sanitizer_cov_trace_pc_guard(uint32_t *guard) {
void __dfsw___sanitizer_cov_trace_switch(uint64_t Val, uint64_t *Cases,
dfsan_label L1, dfsan_label UnusedL) {
assert(CurrentFunc < NumFuncs);
FuncLabels[CurrentFunc] = dfsan_union(FuncLabels[CurrentFunc], L1);
FuncLabels[CurrentFunc][CurrentIteration] |= L1;
}
#define HOOK(Name, Type) \
void Name(Type Arg1, Type Arg2, dfsan_label L1, dfsan_label L2) { \
assert(CurrentFunc < NumFuncs); \
FuncLabels[CurrentFunc] = \
dfsan_union(FuncLabels[CurrentFunc], dfsan_union(L1, L2)); \
FuncLabels[CurrentFunc][CurrentIteration] |= L1 | L2; \
}
HOOK(__dfsw___sanitizer_cov_trace_const_cmp1, uint8_t)

View File

@ -0,0 +1,41 @@
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
// Simple test for a fuzzer.
// Needs to find a string "FUZZxxxxxxxxxxxxMxxE", where 'x' is any byte.
#include <assert.h>
#include <cstddef>
#include <cstdint>
#include <cstdlib>
#include <cstdio>
extern "C" bool Func1(const uint8_t *Data, size_t Size);
extern "C" bool Func2(const uint8_t *Data, size_t Size);
extern "C" int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size) {
if (Size >= 20
&& Data[0] == 'F'
&& Data[1] == 'U'
&& Data[2] == 'Z'
&& Data[3] == 'Z'
&& Func1(Data, Size)
&& Func2(Data, Size)) {
fprintf(stderr, "BINGO\n");
abort();
}
return 0;
}
extern "C"
__attribute__((noinline))
bool Func1(const uint8_t *Data, size_t Size) {
// assumes Size >= 5, doesn't check it.
return Data[16] == 'M';
}
extern "C"
__attribute__((noinline))
bool Func2(const uint8_t *Data, size_t Size) {
return Size >= 20 && Data[19] == 'E';
}

View File

@ -36,7 +36,8 @@ __attribute__((noinline)) void f0(IN in) {
}
}
__attribute__((noinline)) void fC(IN in) { if (in[2] == 'C') f0(in); }
__attribute__((noinline)) void fD(IN in) { f0(in); }
__attribute__((noinline)) void fC(IN in) { if (in[2] == 'C') fD(in); }
__attribute__((noinline)) void fB(IN in) { if (in[1] == 'B') fC(in); }
__attribute__((noinline)) void fA(IN in) { if (in[0] == 'A') fB(in); }

View File

@ -4,7 +4,7 @@ REQUIRES: linux, x86_64
# Build the tracer and the test.
RUN: %no_fuzzer_cpp_compiler -c -fno-sanitize=all -fsanitize=dataflow %S/../../lib/fuzzer/dataflow/DataFlow.cpp -o %t-DataFlow.o
RUN: %no_fuzzer_cpp_compiler -fno-sanitize=all -fsanitize=dataflow -fsanitize-coverage=trace-pc-guard,pc-table,bb,trace-cmp %S/ThreeFunctionsTest.cpp %t-DataFlow.o -o %t-ThreeFunctionsTestDF
RUN: %no_fuzzer_cpp_compiler -fno-sanitize=all -fsanitize=dataflow -fsanitize-coverage=trace-pc-guard,pc-table,bb,trace-cmp %S/ExplodeDFSanLabelsTest.cpp %t-DataFlow.o -o %t-ExplodeDFSanLabelsTestDF
RUN: %no_fuzzer_cpp_compiler -fno-sanitize=all -fsanitize=dataflow -fsanitize-coverage=trace-pc-guard,pc-table,bb,trace-cmp %S/Labels20Test.cpp %t-DataFlow.o -o %t-Labels20TestDF
RUN: %cpp_compiler %S/ThreeFunctionsTest.cpp -o %t-ThreeFunctionsTest
# Dump the function list.
@ -14,8 +14,8 @@ FUNC_LIST-DAG: Func1
FUNC_LIST-DAG: Func2
# Prepare the inputs.
RUN: rm -rf %t/IN
RUN: mkdir -p %t/IN
RUN: rm -rf %t/IN %t/IN20
RUN: mkdir -p %t/IN %t/IN20
RUN: echo -n ABC > %t/IN/ABC
RUN: echo -n FUABC > %t/IN/FUABC
RUN: echo -n FUZZR > %t/IN/FUZZR
@ -23,71 +23,83 @@ RUN: echo -n FUZZM > %t/IN/FUZZM
RUN: echo -n FUZZMU > %t/IN/FUZZMU
RUN: echo -n 1234567890123456 > %t/IN/1234567890123456
RUN: echo -n FUZZxxxxxxxxxxxxxxxx > %t/IN20/FUZZxxxxxxxxxxxxxxxx
RUN: echo -n FUZZxxxxxxxxxxxxMxxx > %t/IN20/FUZZxxxxxxxxxxxxMxxx
RUN: echo -n FUZxxxxxxxxxxxxxxxxx > %t/IN20/FUZxxxxxxxxxxxxxxxxx
RUN: echo -n FUxxxxxxxxxxxxxxxxxx > %t/IN20/FUxxxxxxxxxxxxxxxxxx
RUN: export DFSAN_OPTIONS=fast16labels=1:warn_unimplemented=0
# This test assumes that the functions in ThreeFunctionsTestDF are instrumented
# in a specific order:
# LLVMFuzzerTestOneInput: F0
# Func1: F1
# Func2: F2
# ABC: No data is used, the only used label is 4 (corresponds to the size)
RUN:%t-ThreeFunctionsTestDF 0 3 %t/IN/ABC | FileCheck %s --check-prefix=IN_ABC
IN_ABC: F0 0001
IN_ABC-NOT: F
IN_ABC-NEXT: C0
# ABC: No data is used
RUN:%t-ThreeFunctionsTestDF %t/IN/ABC | FileCheck %s --check-prefix=IN_ABC
IN_ABC-NOT: F0
IN_ABC: C0
IN_ABC-NOT: C
# FUABC: First 3 bytes are checked, Func1/Func2 are not called.
RUN:%t-ThreeFunctionsTestDF 0 5 %t/IN/FUABC | FileCheck %s --check-prefix=IN_FUABC
IN_FUABC: F0 111001
RUN:%t-ThreeFunctionsTestDF %t/IN/FUABC | FileCheck %s --check-prefix=IN_FUABC
IN_FUABC: F0 11100{{$}}
IN_FUABC-NOT: F
IN_FUABC-NEXT: C0
IN_FUABC-NOT: C
# FUZZR: 5 bytes are used (4 in one function, 5-th in the other), Func2 is not called.
RUN:%t-ThreeFunctionsTestDF 0 5 %t/IN/FUZZR | FileCheck %s --check-prefix=IN_FUZZR
IN_FUZZR: F0 111101
IN_FUZZR: F1 000010
RUN:%t-ThreeFunctionsTestDF %t/IN/FUZZR | FileCheck %s --check-prefix=IN_FUZZR
IN_FUZZR: F0 11110
IN_FUZZR: F1 00001
IN_FUZZR-NOT: F
IN_FUZZR: C0
IN_FUZZR: C1
IN_FUZZR-NOT: C
# FUZZM: 5 bytes are used, both Func1 and Func2 are called, Func2 depends only on size (label 6).
RUN:%t-ThreeFunctionsTestDF 0 5 %t/IN/FUZZM | FileCheck %s --check-prefix=IN_FUZZM
IN_FUZZM: F0 111101
IN_FUZZM: F1 000010
IN_FUZZM: F2 000001
# FUZZM: 5 bytes are used, both Func1 and Func2 are called, Func2 depends only on size.
RUN:%t-ThreeFunctionsTestDF %t/IN/FUZZM | FileCheck %s --check-prefix=IN_FUZZM
IN_FUZZM: F0 11110
IN_FUZZM: F1 00001
IN_FUZZM-NOT: F2
IN_FUZZM: C0
IN_FUZZM: C1
IN_FUZZM: C2
# FUZZMU: 6 bytes are used, both Func1 and Func2 are called, Func2 depends on byte 6 and size (label 7)
RUN:%t-ThreeFunctionsTestDF 0 6 %t/IN/FUZZMU | FileCheck %s --check-prefix=IN_FUZZMU
# FUZZMU: 6 bytes are used, both Func1 and Func2 are called, Func2 depends on byte 6 and size.
RUN:%t-ThreeFunctionsTestDF %t/IN/FUZZMU | FileCheck %s --check-prefix=IN_FUZZMU
# Test merge_data_flow
RUN:rm -f %t-merge-*
RUN:%t-ThreeFunctionsTestDF 0 2 %t/IN/FUZZMU > %t-merge-1
RUN:%t-ThreeFunctionsTestDF 2 4 %t/IN/FUZZMU > %t-merge-2
RUN:%t-ThreeFunctionsTestDF 4 6 %t/IN/FUZZMU > %t-merge-3
# Test Labels20TestDF
RUN:%t-Labels20TestDF %t/IN20/FUxxxxxxxxxxxxxxxxxx | FileCheck %s --check-prefix=L20_FU
L20_FU: F0 11100000000000000000{{$}}
L20_FU-NOT: F
RUN:%t-Labels20TestDF %t/IN20/FUZxxxxxxxxxxxxxxxxx | FileCheck %s --check-prefix=L20_FUZ
L20_FUZ: F0 11110000000000000000{{$}}
L20_FUZ-NOT: F
RUN:%t-Labels20TestDF %t/IN20/FUZZxxxxxxxxxxxxxxxx | FileCheck %s --check-prefix=L20_FUZZ
L20_FUZZ: F0 11110000000000000000{{$}}
L20_FUZZ-NEXT: F1 00000000000000001000{{$}}
L20_FUZZ-NOT: F
RUN:%t-Labels20TestDF %t/IN20/FUZZxxxxxxxxxxxxMxxx | FileCheck %s --check-prefix=L20_FUZZM
L20_FUZZM: F0 11110000000000000000{{$}}
L20_FUZZM-NEXT: F1 00000000000000001000{{$}}
L20_FUZZM-NEXT: F2 00000000000000000001{{$}}
L20_FUZZM-NOT: F
# Test libFuzzer's built in DFT collection.
RUN: rm -rf %t-DFT
RUN: %t-ThreeFunctionsTest -collect_data_flow=%t-ThreeFunctionsTestDF -data_flow_trace=%t-DFT %t/IN/FUZZMU
RUN: cat %t-DFT/* | sort | FileCheck %s --check-prefix=IN_FUZZMU
IN_FUZZMU: F0 1111001
IN_FUZZMU: F1 0000100
IN_FUZZMU: F2 0000011
# A very simple test will cause DFSan to die with "out of labels"
RUN: not %t-ExplodeDFSanLabelsTestDF 0 16 %t/IN/1234567890123456 2>&1 | FileCheck %s --check-prefix=OUT_OF_LABELS
OUT_OF_LABELS: ==FATAL: DataFlowSanitizer: out of labels
# However we can run the same test piece by piece.
RUN: %t-ExplodeDFSanLabelsTestDF 0 2 %t/IN/1234567890123456
RUN: %t-ExplodeDFSanLabelsTestDF 2 4 %t/IN/1234567890123456
RUN: %t-ExplodeDFSanLabelsTestDF 4 6 %t/IN/1234567890123456
# Test libFuzzer's builtin collect_data_flow.
RUN: %t-ThreeFunctionsTest -collect_data_flow=%t-ThreeFunctionsTestDF -data_flow_trace=%t-DFT %t/IN/1234567890123456
IN_FUZZMU: F0 111100
IN_FUZZMU: F1 000010
IN_FUZZMU: F2 000001
# Test that we can run collect_data_flow on the entire corpus dir
RUN: rm -rf %t/OUT
@ -96,18 +108,12 @@ RUN: %t-ThreeFunctionsTest -data_flow_trace=%t/OUT -runs=0 -focus_function=Func2
USE_DATA_FLOW_TRACE: INFO: DataFlowTrace: reading from {{.*}}/OUT
USE_DATA_FLOW_TRACE-DAG: ca8eefe2fd5d6b32028f355fafa3e739a6bf5edc => |000001|
USE_DATA_FLOW_TRACE-DAG: d28cb407e8e1a702c72d25473f0553d3ec172262 => |0000011|
USE_DATA_FLOW_TRACE: INFO: DataFlowTrace: 6 trace files, 3 functions, 2 traces with focus function
USE_DATA_FLOW_TRACE: d28cb407e8e1a702c72d25473f0553d3ec172262 => |000001|
USE_DATA_FLOW_TRACE: INFO: DataFlowTrace: 6 trace files, 3 functions, 1 traces with focus function
USE_DATA_FLOW_TRACE: INFO: Focus function is set to 'Func2'
# Test that we can run collect_data_flow on a long input (>2**16 bytes)
RUN: printf "%0.sA" {1..150001} > %t/IN/very_long_input
RUN: rm -rf %t/OUT
RUN: %t-ThreeFunctionsTest -collect_data_flow=%t-ThreeFunctionsTestDF -data_flow_trace=%t/OUT %t/IN/very_long_input 2>&1 | FileCheck %s --check-prefix=COLLECT_TRACE_FOR_LONG_INPUT
RUN: %t-ThreeFunctionsTest -collect_data_flow=%t-ThreeFunctionsTestDF -data_flow_trace=%t/OUT %t/IN/very_long_input
RUN: rm %t/IN/very_long_input
COLLECT_TRACE_FOR_LONG_INPUT: ******* Trying:{{[ ]+}}[0, 150001
COLLECT_TRACE_FOR_LONG_INPUT-DAG: ******* Trying:{{[ ]+}}[75000, 150001
COLLECT_TRACE_FOR_LONG_INPUT-DAG: ******* Trying:{{[ ]+}}[112500, 150001
COLLECT_TRACE_FOR_LONG_INPUT-DAG: ******* Success:{{[ ]+}}[{{[0123456789]+}}, 150001
COLLECT_TRACE_FOR_LONG_INPUT-DAG: ******* Success:{{[ ]+}}[0, {{[0123456789]+}}