ThreadSanitizer.cpp 29.3 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736
//===-- ThreadSanitizer.cpp - race detector -------------------------------===//
//
// 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 is a part of ThreadSanitizer, a race detector.
//
// The tool is under development, for the details about previous versions see
// http://code.google.com/p/data-race-test
//
// The instrumentation phase is quite simple:
//   - Insert calls to run-time library before every memory access.
//      - Optimizations may apply to avoid instrumenting some of the accesses.
//   - Insert calls at function entry/exit.
// The rest is handled by the run-time library.
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Instrumentation/ThreadSanitizer.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/CaptureTracking.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Type.h"
#include "llvm/InitializePasses.h"
#include "llvm/ProfileData/InstrProf.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Instrumentation.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/EscapeEnumerator.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Transforms/Utils/ModuleUtils.h"

using namespace llvm;

#define DEBUG_TYPE "tsan"

static cl::opt<bool>  ClInstrumentMemoryAccesses(
    "tsan-instrument-memory-accesses", cl::init(true),
    cl::desc("Instrument memory accesses"), cl::Hidden);
static cl::opt<bool>  ClInstrumentFuncEntryExit(
    "tsan-instrument-func-entry-exit", cl::init(true),
    cl::desc("Instrument function entry and exit"), cl::Hidden);
static cl::opt<bool>  ClHandleCxxExceptions(
    "tsan-handle-cxx-exceptions", cl::init(true),
    cl::desc("Handle C++ exceptions (insert cleanup blocks for unwinding)"),
    cl::Hidden);
static cl::opt<bool>  ClInstrumentAtomics(
    "tsan-instrument-atomics", cl::init(true),
    cl::desc("Instrument atomics"), cl::Hidden);
static cl::opt<bool>  ClInstrumentMemIntrinsics(
    "tsan-instrument-memintrinsics", cl::init(true),
    cl::desc("Instrument memintrinsics (memset/memcpy/memmove)"), cl::Hidden);

STATISTIC(NumInstrumentedReads, "Number of instrumented reads");
STATISTIC(NumInstrumentedWrites, "Number of instrumented writes");
STATISTIC(NumOmittedReadsBeforeWrite,
          "Number of reads ignored due to following writes");
STATISTIC(NumAccessesWithBadSize, "Number of accesses with bad size");
STATISTIC(NumInstrumentedVtableWrites, "Number of vtable ptr writes");
STATISTIC(NumInstrumentedVtableReads, "Number of vtable ptr reads");
STATISTIC(NumOmittedReadsFromConstantGlobals,
          "Number of reads from constant globals");
STATISTIC(NumOmittedReadsFromVtable, "Number of vtable reads");
STATISTIC(NumOmittedNonCaptured, "Number of accesses ignored due to capturing");

static const char *const kTsanModuleCtorName = "tsan.module_ctor";
static const char *const kTsanInitName = "__tsan_init";

namespace {

/// ThreadSanitizer: instrument the code in module to find races.
///
/// Instantiating ThreadSanitizer inserts the tsan runtime library API function
/// declarations into the module if they don't exist already. Instantiating
/// ensures the __tsan_init function is in the list of global constructors for
/// the module.
struct ThreadSanitizer {
  bool sanitizeFunction(Function &F, const TargetLibraryInfo &TLI);

private:
  void initialize(Module &M);
  bool instrumentLoadOrStore(Instruction *I, const DataLayout &DL);
  bool instrumentAtomic(Instruction *I, const DataLayout &DL);
  bool instrumentMemIntrinsic(Instruction *I);
  void chooseInstructionsToInstrument(SmallVectorImpl<Instruction *> &Local,
                                      SmallVectorImpl<Instruction *> &All,
                                      const DataLayout &DL);
  bool addrPointsToConstantData(Value *Addr);
  int getMemoryAccessFuncIndex(Value *Addr, const DataLayout &DL);
  void InsertRuntimeIgnores(Function &F);

  Type *IntptrTy;
  FunctionCallee TsanFuncEntry;
  FunctionCallee TsanFuncExit;
  FunctionCallee TsanIgnoreBegin;
  FunctionCallee TsanIgnoreEnd;
  // Accesses sizes are powers of two: 1, 2, 4, 8, 16.
  static const size_t kNumberOfAccessSizes = 5;
  FunctionCallee TsanRead[kNumberOfAccessSizes];
  FunctionCallee TsanWrite[kNumberOfAccessSizes];
  FunctionCallee TsanUnalignedRead[kNumberOfAccessSizes];
  FunctionCallee TsanUnalignedWrite[kNumberOfAccessSizes];
  FunctionCallee TsanAtomicLoad[kNumberOfAccessSizes];
  FunctionCallee TsanAtomicStore[kNumberOfAccessSizes];
  FunctionCallee TsanAtomicRMW[AtomicRMWInst::LAST_BINOP + 1]
                              [kNumberOfAccessSizes];
  FunctionCallee TsanAtomicCAS[kNumberOfAccessSizes];
  FunctionCallee TsanAtomicThreadFence;
  FunctionCallee TsanAtomicSignalFence;
  FunctionCallee TsanVptrUpdate;
  FunctionCallee TsanVptrLoad;
  FunctionCallee MemmoveFn, MemcpyFn, MemsetFn;
};

struct ThreadSanitizerLegacyPass : FunctionPass {
  ThreadSanitizerLegacyPass() : FunctionPass(ID) {}
  StringRef getPassName() const override;
  void getAnalysisUsage(AnalysisUsage &AU) const override;
  bool runOnFunction(Function &F) override;
  bool doInitialization(Module &M) override;
  static char ID; // Pass identification, replacement for typeid.
private:
  Optional<ThreadSanitizer> TSan;
};

void insertModuleCtor(Module &M) {
  getOrCreateSanitizerCtorAndInitFunctions(
      M, kTsanModuleCtorName, kTsanInitName, /*InitArgTypes=*/{},
      /*InitArgs=*/{},
      // This callback is invoked when the functions are created the first
      // time. Hook them into the global ctors list in that case:
      [&](Function *Ctor, FunctionCallee) { appendToGlobalCtors(M, Ctor, 0); });
}

}  // namespace

PreservedAnalyses ThreadSanitizerPass::run(Function &F,
                                           FunctionAnalysisManager &FAM) {
  ThreadSanitizer TSan;
  if (TSan.sanitizeFunction(F, FAM.getResult<TargetLibraryAnalysis>(F)))
    return PreservedAnalyses::none();
  return PreservedAnalyses::all();
}

PreservedAnalyses ThreadSanitizerPass::run(Module &M,
                                           ModuleAnalysisManager &MAM) {
  insertModuleCtor(M);
  return PreservedAnalyses::none();
}

char ThreadSanitizerLegacyPass::ID = 0;
INITIALIZE_PASS_BEGIN(ThreadSanitizerLegacyPass, "tsan",
                      "ThreadSanitizer: detects data races.", false, false)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_END(ThreadSanitizerLegacyPass, "tsan",
                    "ThreadSanitizer: detects data races.", false, false)

StringRef ThreadSanitizerLegacyPass::getPassName() const {
  return "ThreadSanitizerLegacyPass";
}

void ThreadSanitizerLegacyPass::getAnalysisUsage(AnalysisUsage &AU) const {
  AU.addRequired<TargetLibraryInfoWrapperPass>();
}

bool ThreadSanitizerLegacyPass::doInitialization(Module &M) {
  insertModuleCtor(M);
  TSan.emplace();
  return true;
}

bool ThreadSanitizerLegacyPass::runOnFunction(Function &F) {
  auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
  TSan->sanitizeFunction(F, TLI);
  return true;
}

FunctionPass *llvm::createThreadSanitizerLegacyPassPass() {
  return new ThreadSanitizerLegacyPass();
}

void ThreadSanitizer::initialize(Module &M) {
  const DataLayout &DL = M.getDataLayout();
  IntptrTy = DL.getIntPtrType(M.getContext());

  IRBuilder<> IRB(M.getContext());
  AttributeList Attr;
  Attr = Attr.addAttribute(M.getContext(), AttributeList::FunctionIndex,
                           Attribute::NoUnwind);
  // Initialize the callbacks.
  TsanFuncEntry = M.getOrInsertFunction("__tsan_func_entry", Attr,
                                        IRB.getVoidTy(), IRB.getInt8PtrTy());
  TsanFuncExit =
      M.getOrInsertFunction("__tsan_func_exit", Attr, IRB.getVoidTy());
  TsanIgnoreBegin = M.getOrInsertFunction("__tsan_ignore_thread_begin", Attr,
                                          IRB.getVoidTy());
  TsanIgnoreEnd =
      M.getOrInsertFunction("__tsan_ignore_thread_end", Attr, IRB.getVoidTy());
  IntegerType *OrdTy = IRB.getInt32Ty();
  for (size_t i = 0; i < kNumberOfAccessSizes; ++i) {
    const unsigned ByteSize = 1U << i;
    const unsigned BitSize = ByteSize * 8;
    std::string ByteSizeStr = utostr(ByteSize);
    std::string BitSizeStr = utostr(BitSize);
    SmallString<32> ReadName("__tsan_read" + ByteSizeStr);
    TsanRead[i] = M.getOrInsertFunction(ReadName, Attr, IRB.getVoidTy(),
                                        IRB.getInt8PtrTy());

    SmallString<32> WriteName("__tsan_write" + ByteSizeStr);
    TsanWrite[i] = M.getOrInsertFunction(WriteName, Attr, IRB.getVoidTy(),
                                         IRB.getInt8PtrTy());

    SmallString<64> UnalignedReadName("__tsan_unaligned_read" + ByteSizeStr);
    TsanUnalignedRead[i] = M.getOrInsertFunction(
        UnalignedReadName, Attr, IRB.getVoidTy(), IRB.getInt8PtrTy());

    SmallString<64> UnalignedWriteName("__tsan_unaligned_write" + ByteSizeStr);
    TsanUnalignedWrite[i] = M.getOrInsertFunction(
        UnalignedWriteName, Attr, IRB.getVoidTy(), IRB.getInt8PtrTy());

    Type *Ty = Type::getIntNTy(M.getContext(), BitSize);
    Type *PtrTy = Ty->getPointerTo();
    SmallString<32> AtomicLoadName("__tsan_atomic" + BitSizeStr + "_load");
    TsanAtomicLoad[i] =
        M.getOrInsertFunction(AtomicLoadName, Attr, Ty, PtrTy, OrdTy);

    SmallString<32> AtomicStoreName("__tsan_atomic" + BitSizeStr + "_store");
    TsanAtomicStore[i] = M.getOrInsertFunction(
        AtomicStoreName, Attr, IRB.getVoidTy(), PtrTy, Ty, OrdTy);

    for (int op = AtomicRMWInst::FIRST_BINOP;
        op <= AtomicRMWInst::LAST_BINOP; ++op) {
      TsanAtomicRMW[op][i] = nullptr;
      const char *NamePart = nullptr;
      if (op == AtomicRMWInst::Xchg)
        NamePart = "_exchange";
      else if (op == AtomicRMWInst::Add)
        NamePart = "_fetch_add";
      else if (op == AtomicRMWInst::Sub)
        NamePart = "_fetch_sub";
      else if (op == AtomicRMWInst::And)
        NamePart = "_fetch_and";
      else if (op == AtomicRMWInst::Or)
        NamePart = "_fetch_or";
      else if (op == AtomicRMWInst::Xor)
        NamePart = "_fetch_xor";
      else if (op == AtomicRMWInst::Nand)
        NamePart = "_fetch_nand";
      else
        continue;
      SmallString<32> RMWName("__tsan_atomic" + itostr(BitSize) + NamePart);
      TsanAtomicRMW[op][i] =
          M.getOrInsertFunction(RMWName, Attr, Ty, PtrTy, Ty, OrdTy);
    }

    SmallString<32> AtomicCASName("__tsan_atomic" + BitSizeStr +
                                  "_compare_exchange_val");
    TsanAtomicCAS[i] = M.getOrInsertFunction(AtomicCASName, Attr, Ty, PtrTy, Ty,
                                             Ty, OrdTy, OrdTy);
  }
  TsanVptrUpdate =
      M.getOrInsertFunction("__tsan_vptr_update", Attr, IRB.getVoidTy(),
                            IRB.getInt8PtrTy(), IRB.getInt8PtrTy());
  TsanVptrLoad = M.getOrInsertFunction("__tsan_vptr_read", Attr,
                                       IRB.getVoidTy(), IRB.getInt8PtrTy());
  TsanAtomicThreadFence = M.getOrInsertFunction("__tsan_atomic_thread_fence",
                                                Attr, IRB.getVoidTy(), OrdTy);
  TsanAtomicSignalFence = M.getOrInsertFunction("__tsan_atomic_signal_fence",
                                                Attr, IRB.getVoidTy(), OrdTy);

  MemmoveFn =
      M.getOrInsertFunction("memmove", Attr, IRB.getInt8PtrTy(),
                            IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), IntptrTy);
  MemcpyFn =
      M.getOrInsertFunction("memcpy", Attr, IRB.getInt8PtrTy(),
                            IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), IntptrTy);
  MemsetFn =
      M.getOrInsertFunction("memset", Attr, IRB.getInt8PtrTy(),
                            IRB.getInt8PtrTy(), IRB.getInt32Ty(), IntptrTy);
}

static bool isVtableAccess(Instruction *I) {
  if (MDNode *Tag = I->getMetadata(LLVMContext::MD_tbaa))
    return Tag->isTBAAVtableAccess();
  return false;
}

// Do not instrument known races/"benign races" that come from compiler
// instrumentatin. The user has no way of suppressing them.
static bool shouldInstrumentReadWriteFromAddress(const Module *M, Value *Addr) {
  // Peel off GEPs and BitCasts.
  Addr = Addr->stripInBoundsOffsets();

  if (GlobalVariable *GV = dyn_cast<GlobalVariable>(Addr)) {
    if (GV->hasSection()) {
      StringRef SectionName = GV->getSection();
      // Check if the global is in the PGO counters section.
      auto OF = Triple(M->getTargetTriple()).getObjectFormat();
      if (SectionName.endswith(
              getInstrProfSectionName(IPSK_cnts, OF, /*AddSegmentInfo=*/false)))
        return false;
    }

    // Check if the global is private gcov data.
    if (GV->getName().startswith("__llvm_gcov") ||
        GV->getName().startswith("__llvm_gcda"))
      return false;
  }

  // Do not instrument acesses from different address spaces; we cannot deal
  // with them.
  if (Addr) {
    Type *PtrTy = cast<PointerType>(Addr->getType()->getScalarType());
    if (PtrTy->getPointerAddressSpace() != 0)
      return false;
  }

  return true;
}

bool ThreadSanitizer::addrPointsToConstantData(Value *Addr) {
  // If this is a GEP, just analyze its pointer operand.
  if (GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(Addr))
    Addr = GEP->getPointerOperand();

  if (GlobalVariable *GV = dyn_cast<GlobalVariable>(Addr)) {
    if (GV->isConstant()) {
      // Reads from constant globals can not race with any writes.
      NumOmittedReadsFromConstantGlobals++;
      return true;
    }
  } else if (LoadInst *L = dyn_cast<LoadInst>(Addr)) {
    if (isVtableAccess(L)) {
      // Reads from a vtable pointer can not race with any writes.
      NumOmittedReadsFromVtable++;
      return true;
    }
  }
  return false;
}

// Instrumenting some of the accesses may be proven redundant.
// Currently handled:
//  - read-before-write (within same BB, no calls between)
//  - not captured variables
//
// We do not handle some of the patterns that should not survive
// after the classic compiler optimizations.
// E.g. two reads from the same temp should be eliminated by CSE,
// two writes should be eliminated by DSE, etc.
//
// 'Local' is a vector of insns within the same BB (no calls between).
// 'All' is a vector of insns that will be instrumented.
void ThreadSanitizer::chooseInstructionsToInstrument(
    SmallVectorImpl<Instruction *> &Local, SmallVectorImpl<Instruction *> &All,
    const DataLayout &DL) {
  SmallPtrSet<Value*, 8> WriteTargets;
  // Iterate from the end.
  for (Instruction *I : reverse(Local)) {
    if (StoreInst *Store = dyn_cast<StoreInst>(I)) {
      Value *Addr = Store->getPointerOperand();
      if (!shouldInstrumentReadWriteFromAddress(I->getModule(), Addr))
        continue;
      WriteTargets.insert(Addr);
    } else {
      LoadInst *Load = cast<LoadInst>(I);
      Value *Addr = Load->getPointerOperand();
      if (!shouldInstrumentReadWriteFromAddress(I->getModule(), Addr))
        continue;
      if (WriteTargets.count(Addr)) {
        // We will write to this temp, so no reason to analyze the read.
        NumOmittedReadsBeforeWrite++;
        continue;
      }
      if (addrPointsToConstantData(Addr)) {
        // Addr points to some constant data -- it can not race with any writes.
        continue;
      }
    }
    Value *Addr = isa<StoreInst>(*I)
        ? cast<StoreInst>(I)->getPointerOperand()
        : cast<LoadInst>(I)->getPointerOperand();
    if (isa<AllocaInst>(GetUnderlyingObject(Addr, DL)) &&
        !PointerMayBeCaptured(Addr, true, true)) {
      // The variable is addressable but not captured, so it cannot be
      // referenced from a different thread and participate in a data race
      // (see llvm/Analysis/CaptureTracking.h for details).
      NumOmittedNonCaptured++;
      continue;
    }
    All.push_back(I);
  }
  Local.clear();
}

static bool isAtomic(Instruction *I) {
  // TODO: Ask TTI whether synchronization scope is between threads.
  if (LoadInst *LI = dyn_cast<LoadInst>(I))
    return LI->isAtomic() && LI->getSyncScopeID() != SyncScope::SingleThread;
  if (StoreInst *SI = dyn_cast<StoreInst>(I))
    return SI->isAtomic() && SI->getSyncScopeID() != SyncScope::SingleThread;
  if (isa<AtomicRMWInst>(I))
    return true;
  if (isa<AtomicCmpXchgInst>(I))
    return true;
  if (isa<FenceInst>(I))
    return true;
  return false;
}

void ThreadSanitizer::InsertRuntimeIgnores(Function &F) {
  IRBuilder<> IRB(F.getEntryBlock().getFirstNonPHI());
  IRB.CreateCall(TsanIgnoreBegin);
  EscapeEnumerator EE(F, "tsan_ignore_cleanup", ClHandleCxxExceptions);
  while (IRBuilder<> *AtExit = EE.Next()) {
    AtExit->CreateCall(TsanIgnoreEnd);
  }
}

bool ThreadSanitizer::sanitizeFunction(Function &F,
                                       const TargetLibraryInfo &TLI) {
  // This is required to prevent instrumenting call to __tsan_init from within
  // the module constructor.
  if (F.getName() == kTsanModuleCtorName)
    return false;
  initialize(*F.getParent());
  SmallVector<Instruction*, 8> AllLoadsAndStores;
  SmallVector<Instruction*, 8> LocalLoadsAndStores;
  SmallVector<Instruction*, 8> AtomicAccesses;
  SmallVector<Instruction*, 8> MemIntrinCalls;
  bool Res = false;
  bool HasCalls = false;
  bool SanitizeFunction = F.hasFnAttribute(Attribute::SanitizeThread);
  const DataLayout &DL = F.getParent()->getDataLayout();

  // Traverse all instructions, collect loads/stores/returns, check for calls.
  for (auto &BB : F) {
    for (auto &Inst : BB) {
      if (isAtomic(&Inst))
        AtomicAccesses.push_back(&Inst);
      else if (isa<LoadInst>(Inst) || isa<StoreInst>(Inst))
        LocalLoadsAndStores.push_back(&Inst);
      else if (isa<CallInst>(Inst) || isa<InvokeInst>(Inst)) {
        if (CallInst *CI = dyn_cast<CallInst>(&Inst))
          maybeMarkSanitizerLibraryCallNoBuiltin(CI, &TLI);
        if (isa<MemIntrinsic>(Inst))
          MemIntrinCalls.push_back(&Inst);
        HasCalls = true;
        chooseInstructionsToInstrument(LocalLoadsAndStores, AllLoadsAndStores,
                                       DL);
      }
    }
    chooseInstructionsToInstrument(LocalLoadsAndStores, AllLoadsAndStores, DL);
  }

  // We have collected all loads and stores.
  // FIXME: many of these accesses do not need to be checked for races
  // (e.g. variables that do not escape, etc).

  // Instrument memory accesses only if we want to report bugs in the function.
  if (ClInstrumentMemoryAccesses && SanitizeFunction)
    for (auto Inst : AllLoadsAndStores) {
      Res |= instrumentLoadOrStore(Inst, DL);
    }

  // Instrument atomic memory accesses in any case (they can be used to
  // implement synchronization).
  if (ClInstrumentAtomics)
    for (auto Inst : AtomicAccesses) {
      Res |= instrumentAtomic(Inst, DL);
    }

  if (ClInstrumentMemIntrinsics && SanitizeFunction)
    for (auto Inst : MemIntrinCalls) {
      Res |= instrumentMemIntrinsic(Inst);
    }

  if (F.hasFnAttribute("sanitize_thread_no_checking_at_run_time")) {
    assert(!F.hasFnAttribute(Attribute::SanitizeThread));
    if (HasCalls)
      InsertRuntimeIgnores(F);
  }

  // Instrument function entry/exit points if there were instrumented accesses.
  if ((Res || HasCalls) && ClInstrumentFuncEntryExit) {
    IRBuilder<> IRB(F.getEntryBlock().getFirstNonPHI());
    Value *ReturnAddress = IRB.CreateCall(
        Intrinsic::getDeclaration(F.getParent(), Intrinsic::returnaddress),
        IRB.getInt32(0));
    IRB.CreateCall(TsanFuncEntry, ReturnAddress);

    EscapeEnumerator EE(F, "tsan_cleanup", ClHandleCxxExceptions);
    while (IRBuilder<> *AtExit = EE.Next()) {
      AtExit->CreateCall(TsanFuncExit, {});
    }
    Res = true;
  }
  return Res;
}

bool ThreadSanitizer::instrumentLoadOrStore(Instruction *I,
                                            const DataLayout &DL) {
  IRBuilder<> IRB(I);
  bool IsWrite = isa<StoreInst>(*I);
  Value *Addr = IsWrite
      ? cast<StoreInst>(I)->getPointerOperand()
      : cast<LoadInst>(I)->getPointerOperand();

  // swifterror memory addresses are mem2reg promoted by instruction selection.
  // As such they cannot have regular uses like an instrumentation function and
  // it makes no sense to track them as memory.
  if (Addr->isSwiftError())
    return false;

  int Idx = getMemoryAccessFuncIndex(Addr, DL);
  if (Idx < 0)
    return false;
  if (IsWrite && isVtableAccess(I)) {
    LLVM_DEBUG(dbgs() << "  VPTR : " << *I << "\n");
    Value *StoredValue = cast<StoreInst>(I)->getValueOperand();
    // StoredValue may be a vector type if we are storing several vptrs at once.
    // In this case, just take the first element of the vector since this is
    // enough to find vptr races.
    if (isa<VectorType>(StoredValue->getType()))
      StoredValue = IRB.CreateExtractElement(
          StoredValue, ConstantInt::get(IRB.getInt32Ty(), 0));
    if (StoredValue->getType()->isIntegerTy())
      StoredValue = IRB.CreateIntToPtr(StoredValue, IRB.getInt8PtrTy());
    // Call TsanVptrUpdate.
    IRB.CreateCall(TsanVptrUpdate,
                   {IRB.CreatePointerCast(Addr, IRB.getInt8PtrTy()),
                    IRB.CreatePointerCast(StoredValue, IRB.getInt8PtrTy())});
    NumInstrumentedVtableWrites++;
    return true;
  }
  if (!IsWrite && isVtableAccess(I)) {
    IRB.CreateCall(TsanVptrLoad,
                   IRB.CreatePointerCast(Addr, IRB.getInt8PtrTy()));
    NumInstrumentedVtableReads++;
    return true;
  }
  const unsigned Alignment = IsWrite
      ? cast<StoreInst>(I)->getAlignment()
      : cast<LoadInst>(I)->getAlignment();
  Type *OrigTy = cast<PointerType>(Addr->getType())->getElementType();
  const uint32_t TypeSize = DL.getTypeStoreSizeInBits(OrigTy);
  FunctionCallee OnAccessFunc = nullptr;
  if (Alignment == 0 || Alignment >= 8 || (Alignment % (TypeSize / 8)) == 0)
    OnAccessFunc = IsWrite ? TsanWrite[Idx] : TsanRead[Idx];
  else
    OnAccessFunc = IsWrite ? TsanUnalignedWrite[Idx] : TsanUnalignedRead[Idx];
  IRB.CreateCall(OnAccessFunc, IRB.CreatePointerCast(Addr, IRB.getInt8PtrTy()));
  if (IsWrite) NumInstrumentedWrites++;
  else         NumInstrumentedReads++;
  return true;
}

static ConstantInt *createOrdering(IRBuilder<> *IRB, AtomicOrdering ord) {
  uint32_t v = 0;
  switch (ord) {
    case AtomicOrdering::NotAtomic:
      llvm_unreachable("unexpected atomic ordering!");
    case AtomicOrdering::Unordered:              LLVM_FALLTHROUGH;
    case AtomicOrdering::Monotonic:              v = 0; break;
    // Not specified yet:
    // case AtomicOrdering::Consume:                v = 1; break;
    case AtomicOrdering::Acquire:                v = 2; break;
    case AtomicOrdering::Release:                v = 3; break;
    case AtomicOrdering::AcquireRelease:         v = 4; break;
    case AtomicOrdering::SequentiallyConsistent: v = 5; break;
  }
  return IRB->getInt32(v);
}

// If a memset intrinsic gets inlined by the code gen, we will miss races on it.
// So, we either need to ensure the intrinsic is not inlined, or instrument it.
// We do not instrument memset/memmove/memcpy intrinsics (too complicated),
// instead we simply replace them with regular function calls, which are then
// intercepted by the run-time.
// Since tsan is running after everyone else, the calls should not be
// replaced back with intrinsics. If that becomes wrong at some point,
// we will need to call e.g. __tsan_memset to avoid the intrinsics.
bool ThreadSanitizer::instrumentMemIntrinsic(Instruction *I) {
  IRBuilder<> IRB(I);
  if (MemSetInst *M = dyn_cast<MemSetInst>(I)) {
    IRB.CreateCall(
        MemsetFn,
        {IRB.CreatePointerCast(M->getArgOperand(0), IRB.getInt8PtrTy()),
         IRB.CreateIntCast(M->getArgOperand(1), IRB.getInt32Ty(), false),
         IRB.CreateIntCast(M->getArgOperand(2), IntptrTy, false)});
    I->eraseFromParent();
  } else if (MemTransferInst *M = dyn_cast<MemTransferInst>(I)) {
    IRB.CreateCall(
        isa<MemCpyInst>(M) ? MemcpyFn : MemmoveFn,
        {IRB.CreatePointerCast(M->getArgOperand(0), IRB.getInt8PtrTy()),
         IRB.CreatePointerCast(M->getArgOperand(1), IRB.getInt8PtrTy()),
         IRB.CreateIntCast(M->getArgOperand(2), IntptrTy, false)});
    I->eraseFromParent();
  }
  return false;
}

// Both llvm and ThreadSanitizer atomic operations are based on C++11/C1x
// standards.  For background see C++11 standard.  A slightly older, publicly
// available draft of the standard (not entirely up-to-date, but close enough
// for casual browsing) is available here:
// http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2011/n3242.pdf
// The following page contains more background information:
// http://www.hpl.hp.com/personal/Hans_Boehm/c++mm/

bool ThreadSanitizer::instrumentAtomic(Instruction *I, const DataLayout &DL) {
  IRBuilder<> IRB(I);
  if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
    Value *Addr = LI->getPointerOperand();
    int Idx = getMemoryAccessFuncIndex(Addr, DL);
    if (Idx < 0)
      return false;
    const unsigned ByteSize = 1U << Idx;
    const unsigned BitSize = ByteSize * 8;
    Type *Ty = Type::getIntNTy(IRB.getContext(), BitSize);
    Type *PtrTy = Ty->getPointerTo();
    Value *Args[] = {IRB.CreatePointerCast(Addr, PtrTy),
                     createOrdering(&IRB, LI->getOrdering())};
    Type *OrigTy = cast<PointerType>(Addr->getType())->getElementType();
    Value *C = IRB.CreateCall(TsanAtomicLoad[Idx], Args);
    Value *Cast = IRB.CreateBitOrPointerCast(C, OrigTy);
    I->replaceAllUsesWith(Cast);
  } else if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
    Value *Addr = SI->getPointerOperand();
    int Idx = getMemoryAccessFuncIndex(Addr, DL);
    if (Idx < 0)
      return false;
    const unsigned ByteSize = 1U << Idx;
    const unsigned BitSize = ByteSize * 8;
    Type *Ty = Type::getIntNTy(IRB.getContext(), BitSize);
    Type *PtrTy = Ty->getPointerTo();
    Value *Args[] = {IRB.CreatePointerCast(Addr, PtrTy),
                     IRB.CreateBitOrPointerCast(SI->getValueOperand(), Ty),
                     createOrdering(&IRB, SI->getOrdering())};
    CallInst *C = CallInst::Create(TsanAtomicStore[Idx], Args);
    ReplaceInstWithInst(I, C);
  } else if (AtomicRMWInst *RMWI = dyn_cast<AtomicRMWInst>(I)) {
    Value *Addr = RMWI->getPointerOperand();
    int Idx = getMemoryAccessFuncIndex(Addr, DL);
    if (Idx < 0)
      return false;
    FunctionCallee F = TsanAtomicRMW[RMWI->getOperation()][Idx];
    if (!F)
      return false;
    const unsigned ByteSize = 1U << Idx;
    const unsigned BitSize = ByteSize * 8;
    Type *Ty = Type::getIntNTy(IRB.getContext(), BitSize);
    Type *PtrTy = Ty->getPointerTo();
    Value *Args[] = {IRB.CreatePointerCast(Addr, PtrTy),
                     IRB.CreateIntCast(RMWI->getValOperand(), Ty, false),
                     createOrdering(&IRB, RMWI->getOrdering())};
    CallInst *C = CallInst::Create(F, Args);
    ReplaceInstWithInst(I, C);
  } else if (AtomicCmpXchgInst *CASI = dyn_cast<AtomicCmpXchgInst>(I)) {
    Value *Addr = CASI->getPointerOperand();
    int Idx = getMemoryAccessFuncIndex(Addr, DL);
    if (Idx < 0)
      return false;
    const unsigned ByteSize = 1U << Idx;
    const unsigned BitSize = ByteSize * 8;
    Type *Ty = Type::getIntNTy(IRB.getContext(), BitSize);
    Type *PtrTy = Ty->getPointerTo();
    Value *CmpOperand =
      IRB.CreateBitOrPointerCast(CASI->getCompareOperand(), Ty);
    Value *NewOperand =
      IRB.CreateBitOrPointerCast(CASI->getNewValOperand(), Ty);
    Value *Args[] = {IRB.CreatePointerCast(Addr, PtrTy),
                     CmpOperand,
                     NewOperand,
                     createOrdering(&IRB, CASI->getSuccessOrdering()),
                     createOrdering(&IRB, CASI->getFailureOrdering())};
    CallInst *C = IRB.CreateCall(TsanAtomicCAS[Idx], Args);
    Value *Success = IRB.CreateICmpEQ(C, CmpOperand);
    Value *OldVal = C;
    Type *OrigOldValTy = CASI->getNewValOperand()->getType();
    if (Ty != OrigOldValTy) {
      // The value is a pointer, so we need to cast the return value.
      OldVal = IRB.CreateIntToPtr(C, OrigOldValTy);
    }

    Value *Res =
      IRB.CreateInsertValue(UndefValue::get(CASI->getType()), OldVal, 0);
    Res = IRB.CreateInsertValue(Res, Success, 1);

    I->replaceAllUsesWith(Res);
    I->eraseFromParent();
  } else if (FenceInst *FI = dyn_cast<FenceInst>(I)) {
    Value *Args[] = {createOrdering(&IRB, FI->getOrdering())};
    FunctionCallee F = FI->getSyncScopeID() == SyncScope::SingleThread
                           ? TsanAtomicSignalFence
                           : TsanAtomicThreadFence;
    CallInst *C = CallInst::Create(F, Args);
    ReplaceInstWithInst(I, C);
  }
  return true;
}

int ThreadSanitizer::getMemoryAccessFuncIndex(Value *Addr,
                                              const DataLayout &DL) {
  Type *OrigPtrTy = Addr->getType();
  Type *OrigTy = cast<PointerType>(OrigPtrTy)->getElementType();
  assert(OrigTy->isSized());
  uint32_t TypeSize = DL.getTypeStoreSizeInBits(OrigTy);
  if (TypeSize != 8  && TypeSize != 16 &&
      TypeSize != 32 && TypeSize != 64 && TypeSize != 128) {
    NumAccessesWithBadSize++;
    // Ignore all unusual sizes.
    return -1;
  }
  size_t Idx = countTrailingZeros(TypeSize / 8);
  assert(Idx < kNumberOfAccessSizes);
  return Idx;
}