1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
|
//===- Delta.cpp - Delta Debugging Algorithm Implementation ---------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file contains the implementation for the Delta Debugging Algorithm:
// it splits a given set of Targets (i.e. Functions, Instructions, BBs, etc.)
// into chunks and tries to reduce the number chunks that are interesting.
//
//===----------------------------------------------------------------------===//
#include "Delta.h"
#include "ReducerWorkItem.h"
#include "TestRunner.h"
#include "Utils.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/Analysis/ModuleSummaryAnalysis.h"
#include "llvm/Analysis/ProfileSummaryInfo.h"
#include "llvm/Bitcode/BitcodeReader.h"
#include "llvm/Bitcode/BitcodeWriter.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Verifier.h"
#include "llvm/MC/TargetRegistry.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/MemoryBufferRef.h"
#include "llvm/Support/ThreadPool.h"
#include <fstream>
using namespace llvm;
extern cl::OptionCategory LLVMReduceOptions;
static cl::opt<bool> AbortOnInvalidReduction(
"abort-on-invalid-reduction",
cl::desc("Abort if any reduction results in invalid IR"),
cl::cat(LLVMReduceOptions));
static cl::opt<unsigned int> StartingGranularityLevel(
"starting-granularity-level",
cl::desc("Number of times to divide chunks prior to first test"),
cl::cat(LLVMReduceOptions));
#ifdef LLVM_ENABLE_THREADS
static cl::opt<unsigned> NumJobs(
"j",
cl::desc("Maximum number of threads to use to process chunks. Set to 1 to "
"disable parallelism."),
cl::init(1), cl::cat(LLVMReduceOptions));
#else
unsigned NumJobs = 1;
#endif
/// Splits Chunks in half and prints them.
/// If unable to split (when chunk size is 1) returns false.
static bool increaseGranularity(std::vector<Chunk> &Chunks) {
if (Verbose)
errs() << "Increasing granularity...";
std::vector<Chunk> NewChunks;
bool SplitAny = false;
for (Chunk C : Chunks) {
if (C.End - C.Begin == 0)
NewChunks.push_back(C);
else {
int Half = (C.Begin + C.End) / 2;
NewChunks.push_back({C.Begin, Half});
NewChunks.push_back({Half + 1, C.End});
SplitAny = true;
}
}
if (SplitAny) {
Chunks = NewChunks;
if (Verbose) {
errs() << "Success! " << NewChunks.size() << " New Chunks:\n";
for (auto C : Chunks) {
errs() << '\t';
C.print();
errs() << '\n';
}
}
}
return SplitAny;
}
// Check if \p ChunkToCheckForUninterestingness is interesting. Returns the
// modified module if the chunk resulted in a reduction.
static std::unique_ptr<ReducerWorkItem>
CheckChunk(const Chunk ChunkToCheckForUninterestingness,
std::unique_ptr<ReducerWorkItem> Clone, const TestRunner &Test,
ReductionFunc ExtractChunksFromModule,
const DenseSet<Chunk> &UninterestingChunks,
const std::vector<Chunk> &ChunksStillConsideredInteresting) {
// Take all of ChunksStillConsideredInteresting chunks, except those we've
// already deemed uninteresting (UninterestingChunks) but didn't remove
// from ChunksStillConsideredInteresting yet, and additionally ignore
// ChunkToCheckForUninterestingness chunk.
std::vector<Chunk> CurrentChunks;
CurrentChunks.reserve(ChunksStillConsideredInteresting.size() -
UninterestingChunks.size() - 1);
copy_if(ChunksStillConsideredInteresting, std::back_inserter(CurrentChunks),
[&](const Chunk &C) {
return C != ChunkToCheckForUninterestingness &&
!UninterestingChunks.count(C);
});
// Generate Module with only Targets inside Current Chunks
Oracle O(CurrentChunks);
ExtractChunksFromModule(O, *Clone);
// Some reductions may result in invalid IR. Skip such reductions.
if (Clone->verify(&errs())) {
if (AbortOnInvalidReduction) {
errs() << "Invalid reduction, aborting.\n";
Clone->print(errs());
exit(1);
}
if (Verbose) {
errs() << " **** WARNING | reduction resulted in invalid module, "
"skipping\n";
}
return nullptr;
}
if (Verbose) {
errs() << "Ignoring: ";
ChunkToCheckForUninterestingness.print();
for (const Chunk &C : UninterestingChunks)
C.print();
errs() << "\n";
}
if (!Clone->isReduced(Test)) {
// Program became non-reduced, so this chunk appears to be interesting.
if (Verbose)
errs() << "\n";
return nullptr;
}
return Clone;
}
static SmallString<0> ProcessChunkFromSerializedBitcode(
const Chunk ChunkToCheckForUninterestingness, const TestRunner &Test,
ReductionFunc ExtractChunksFromModule,
const DenseSet<Chunk> &UninterestingChunks,
ArrayRef<Chunk> ChunksStillConsideredInteresting, StringRef OriginalBC,
std::atomic<bool> &AnyReduced) {
LLVMContext Ctx;
auto CloneMMM = std::make_unique<ReducerWorkItem>();
MemoryBufferRef Data(OriginalBC, "<bc file>");
CloneMMM->readBitcode(Data, Ctx, Test.getToolName());
SmallString<0> Result;
if (std::unique_ptr<ReducerWorkItem> ChunkResult =
CheckChunk(ChunkToCheckForUninterestingness, std::move(CloneMMM),
Test, ExtractChunksFromModule, UninterestingChunks,
ChunksStillConsideredInteresting)) {
raw_svector_ostream BCOS(Result);
ChunkResult->writeBitcode(BCOS);
// Communicate that the task reduced a chunk.
AnyReduced = true;
}
return Result;
}
using SharedTaskQueue = std::deque<std::shared_future<SmallString<0>>>;
/// Runs the Delta Debugging algorithm, splits the code into chunks and
/// reduces the amount of chunks that are considered interesting by the
/// given test. The number of chunks is determined by a preliminary run of the
/// reduction pass where no change must be made to the module.
void llvm::runDeltaPass(TestRunner &Test, ReductionFunc ExtractChunksFromModule,
StringRef Message) {
assert(!Test.getProgram().verify(&errs()) &&
"input module is broken before making changes");
errs() << "*** " << Message << "...\n";
int Targets;
{
// Count the number of chunks by counting the number of calls to
// Oracle::shouldKeep() but always returning true so no changes are
// made.
std::vector<Chunk> AllChunks = {{0, INT_MAX}};
Oracle Counter(AllChunks);
ExtractChunksFromModule(Counter, Test.getProgram());
Targets = Counter.count();
assert(!Test.getProgram().verify(&errs()) &&
"input module is broken after counting chunks");
assert(Test.getProgram().isReduced(Test) &&
"input module no longer interesting after counting chunks");
#ifndef NDEBUG
// Make sure that the number of chunks does not change as we reduce.
std::vector<Chunk> NoChunks = {{0, INT_MAX}};
Oracle NoChunksCounter(NoChunks);
std::unique_ptr<ReducerWorkItem> Clone =
Test.getProgram().clone(Test.getTargetMachine());
ExtractChunksFromModule(NoChunksCounter, *Clone);
assert(Targets == NoChunksCounter.count() &&
"number of chunks changes when reducing");
#endif
}
if (!Targets) {
if (Verbose)
errs() << "\nNothing to reduce\n";
errs() << "----------------------------\n";
return;
}
std::vector<Chunk> ChunksStillConsideredInteresting = {{0, Targets - 1}};
std::unique_ptr<ReducerWorkItem> ReducedProgram;
for (unsigned int Level = 0; Level < StartingGranularityLevel; Level++) {
increaseGranularity(ChunksStillConsideredInteresting);
}
std::atomic<bool> AnyReduced;
std::unique_ptr<ThreadPoolInterface> ChunkThreadPoolPtr;
if (NumJobs > 1)
ChunkThreadPoolPtr =
std::make_unique<ThreadPool>(hardware_concurrency(NumJobs));
bool FoundAtLeastOneNewUninterestingChunkWithCurrentGranularity;
do {
FoundAtLeastOneNewUninterestingChunkWithCurrentGranularity = false;
DenseSet<Chunk> UninterestingChunks;
// When running with more than one thread, serialize the original bitcode
// to OriginalBC.
SmallString<0> OriginalBC;
if (NumJobs > 1) {
raw_svector_ostream BCOS(OriginalBC);
Test.getProgram().writeBitcode(BCOS);
}
SharedTaskQueue TaskQueue;
for (auto I = ChunksStillConsideredInteresting.rbegin(),
E = ChunksStillConsideredInteresting.rend();
I != E; ++I) {
std::unique_ptr<ReducerWorkItem> Result = nullptr;
unsigned WorkLeft = std::distance(I, E);
// Run in parallel mode, if the user requested more than one thread and
// there are at least a few chunks to process.
if (NumJobs > 1 && WorkLeft > 1) {
unsigned NumInitialTasks = std::min(WorkLeft, unsigned(NumJobs));
unsigned NumChunksProcessed = 0;
ThreadPoolInterface &ChunkThreadPool = *ChunkThreadPoolPtr;
assert(TaskQueue.empty());
AnyReduced = false;
// Queue jobs to process NumInitialTasks chunks in parallel using
// ChunkThreadPool. When the tasks are added to the pool, parse the
// original module from OriginalBC with a fresh LLVMContext object. This
// ensures that the cloned module of each task uses an independent
// LLVMContext object. If a task reduces the input, serialize the result
// back in the corresponding Result element.
for (unsigned J = 0; J < NumInitialTasks; ++J) {
Chunk ChunkToCheck = *(I + J);
TaskQueue.emplace_back(ChunkThreadPool.async(
ProcessChunkFromSerializedBitcode, ChunkToCheck, std::ref(Test),
ExtractChunksFromModule, UninterestingChunks,
ChunksStillConsideredInteresting, OriginalBC,
std::ref(AnyReduced)));
}
// Start processing results of the queued tasks. We wait for the first
// task in the queue to finish. If it reduced a chunk, we parse the
// result and exit the loop.
// Otherwise we will try to schedule a new task, if
// * no other pending job reduced a chunk and
// * we have not reached the end of the chunk.
while (!TaskQueue.empty()) {
auto &Future = TaskQueue.front();
Future.wait();
NumChunksProcessed++;
SmallString<0> Res = Future.get();
TaskQueue.pop_front();
if (Res.empty()) {
unsigned NumScheduledTasks = NumChunksProcessed + TaskQueue.size();
if (!AnyReduced && I + NumScheduledTasks != E) {
Chunk ChunkToCheck = *(I + NumScheduledTasks);
TaskQueue.emplace_back(ChunkThreadPool.async(
ProcessChunkFromSerializedBitcode, ChunkToCheck,
std::ref(Test), ExtractChunksFromModule, UninterestingChunks,
ChunksStillConsideredInteresting, OriginalBC,
std::ref(AnyReduced)));
}
continue;
}
Result = std::make_unique<ReducerWorkItem>();
MemoryBufferRef Data(StringRef(Res), "<bc file>");
Result->readBitcode(Data, Test.getProgram().M->getContext(),
Test.getToolName());
break;
}
// If we broke out of the loop, we still need to wait for everything to
// avoid race access to the chunk set.
//
// TODO: Create a way to kill remaining items we're ignoring; they could
// take a long time.
ChunkThreadPoolPtr->wait();
TaskQueue.clear();
// Forward I to the last chunk processed in parallel.
I += NumChunksProcessed - 1;
} else {
Result =
CheckChunk(*I, Test.getProgram().clone(Test.getTargetMachine()),
Test, ExtractChunksFromModule, UninterestingChunks,
ChunksStillConsideredInteresting);
}
if (!Result)
continue;
const Chunk ChunkToCheckForUninterestingness = *I;
FoundAtLeastOneNewUninterestingChunkWithCurrentGranularity = true;
UninterestingChunks.insert(ChunkToCheckForUninterestingness);
ReducedProgram = std::move(Result);
}
// Delete uninteresting chunks
erase_if(ChunksStillConsideredInteresting,
[&UninterestingChunks](const Chunk &C) {
return UninterestingChunks.count(C);
});
} while (!ChunksStillConsideredInteresting.empty() &&
(FoundAtLeastOneNewUninterestingChunkWithCurrentGranularity ||
increaseGranularity(ChunksStillConsideredInteresting)));
// If we reduced the testcase replace it
if (ReducedProgram) {
Test.setProgram(std::move(ReducedProgram));
// FIXME: Report meaningful progress info
Test.writeOutput(" **** SUCCESS | Saved new best reduction to ");
}
if (Verbose)
errs() << "Couldn't increase anymore.\n";
errs() << "----------------------------\n";
}
|