/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp

Bug Summary

File:	lib/Transforms/Utils/CodeExtractor.cpp
Warning:	line 782, column 32 1st function call argument is an uninitialized value
Annotated Source Code

Press '?' to see keyboard shortcuts
Show analyzer invocation
clang -cc1 -triple x86_64-pc-linux-gnu -analyze -disable-free -disable-llvm-verifier -discard-value-names -main-file-name CodeExtractor.cpp -analyzer-store=region -analyzer-opt-analyze-nested-blocks -analyzer-eagerly-assume -analyzer-checker=core -analyzer-checker=apiModeling -analyzer-checker=unix -analyzer-checker=deadcode -analyzer-checker=cplusplus -analyzer-checker=security.insecureAPI.UncheckedReturn -analyzer-checker=security.insecureAPI.getpw -analyzer-checker=security.insecureAPI.gets -analyzer-checker=security.insecureAPI.mktemp -analyzer-checker=security.insecureAPI.mkstemp -analyzer-checker=security.insecureAPI.vfork -analyzer-checker=nullability.NullPassedToNonnull -analyzer-checker=nullability.NullReturnedFromNonnull -analyzer-output plist -w -mrelocation-model pic -pic-level 2 -mthread-model posix -fmath-errno -masm-verbose -mconstructor-aliases -munwind-tables -fuse-init-array -target-cpu x86-64 -dwarf-column-info -debugger-tuning=gdb -momit-leaf-frame-pointer -ffunction-sections -fdata-sections -resource-dir /usr/lib/llvm-7/lib/clang/7.0.0 -D _DEBUG -D _GNU_SOURCE -D __STDC_CONSTANT_MACROS -D __STDC_FORMAT_MACROS -D __STDC_LIMIT_MACROS -I /build/llvm-toolchain-snapshot-7~svn338205/build-llvm/lib/Transforms/Utils -I /build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils -I /build/llvm-toolchain-snapshot-7~svn338205/build-llvm/include -I /build/llvm-toolchain-snapshot-7~svn338205/include -U NDEBUG -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/8/../../../../include/c++/8 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/8/../../../../include/x86_64-linux-gnu/c++/8 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/8/../../../../include/x86_64-linux-gnu/c++/8 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/8/../../../../include/c++/8/backward -internal-isystem /usr/include/clang/7.0.0/include/ -internal-isystem /usr/local/include -internal-isystem /usr/lib/llvm-7/lib/clang/7.0.0/include -internal-externc-isystem /usr/lib/gcc/x86_64-linux-gnu/8/include -internal-externc-isystem /usr/include/x86_64-linux-gnu -internal-externc-isystem /include -internal-externc-isystem /usr/include -O2 -Wno-unused-parameter -Wwrite-strings -Wno-missing-field-initializers -Wno-long-long -Wno-maybe-uninitialized -Wno-class-memaccess -Wno-comment -std=c++11 -fdeprecated-macro -fdebug-compilation-dir /build/llvm-toolchain-snapshot-7~svn338205/build-llvm/lib/Transforms/Utils -ferror-limit 19 -fmessage-length 0 -fvisibility-inlines-hidden -fobjc-runtime=gcc -fdiagnostics-show-option -vectorize-loops -vectorize-slp -analyzer-output=html -analyzer-config stable-report-filename=true -o /tmp/scan-build-2018-07-29-043837-17923-1 -x c++ /build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp -faddrsig
1//===- CodeExtractor.cpp - Pull code region into a new function -----------===//
2//
3//                     The LLVM Compiler Infrastructure
4//
5// This file is distributed under the University of Illinois Open Source
6// License. See LICENSE.TXT for details.
7//
8//===----------------------------------------------------------------------===//
9//
10// This file implements the interface to tear out a code region, such as an
11// individual loop or a parallel section, into a new function, replacing it with
12// a call to the new function.
13//
14//===----------------------------------------------------------------------===//

16#include "llvm/Transforms/Utils/CodeExtractor.h"
17#include "llvm/ADT/ArrayRef.h"
18#include "llvm/ADT/DenseMap.h"
19#include "llvm/ADT/Optional.h"
20#include "llvm/ADT/STLExtras.h"
21#include "llvm/ADT/SetVector.h"
22#include "llvm/ADT/SmallPtrSet.h"
23#include "llvm/ADT/SmallVector.h"
24#include "llvm/Analysis/BlockFrequencyInfo.h"
25#include "llvm/Analysis/BlockFrequencyInfoImpl.h"
26#include "llvm/Analysis/BranchProbabilityInfo.h"
27#include "llvm/Analysis/LoopInfo.h"
28#include "llvm/IR/Argument.h"
29#include "llvm/IR/Attributes.h"
30#include "llvm/IR/BasicBlock.h"
31#include "llvm/IR/CFG.h"
32#include "llvm/IR/Constant.h"
33#include "llvm/IR/Constants.h"
34#include "llvm/IR/DataLayout.h"
35#include "llvm/IR/DerivedTypes.h"
36#include "llvm/IR/Dominators.h"
37#include "llvm/IR/Function.h"
38#include "llvm/IR/GlobalValue.h"
39#include "llvm/IR/InstrTypes.h"
40#include "llvm/IR/Instruction.h"
41#include "llvm/IR/Instructions.h"
42#include "llvm/IR/IntrinsicInst.h"
43#include "llvm/IR/Intrinsics.h"
44#include "llvm/IR/LLVMContext.h"
45#include "llvm/IR/MDBuilder.h"
46#include "llvm/IR/Module.h"
47#include "llvm/IR/Type.h"
48#include "llvm/IR/User.h"
49#include "llvm/IR/Value.h"
50#include "llvm/IR/Verifier.h"
51#include "llvm/Pass.h"
52#include "llvm/Support/BlockFrequency.h"
53#include "llvm/Support/BranchProbability.h"
54#include "llvm/Support/Casting.h"
55#include "llvm/Support/CommandLine.h"
56#include "llvm/Support/Debug.h"
57#include "llvm/Support/ErrorHandling.h"
58#include "llvm/Support/raw_ostream.h"
59#include "llvm/Transforms/Utils/BasicBlockUtils.h"
60#include <cassert>
61#include <cstdint>
62#include <iterator>
63#include <map>
64#include <set>
65#include <utility>
66#include <vector>

68using namespace llvm;
69using ProfileCount = Function::ProfileCount;

71#define DEBUG_TYPE"code-extractor" "code-extractor"

73// Provide a command-line option to aggregate function arguments into a struct
74// for functions produced by the code extractor. This is useful when converting
75// extracted functions to pthread-based code, as only one argument (void*) can
76// be passed in to pthread_create().
77static cl::opt<bool>
78AggregateArgsOpt("aggregate-extracted-args", cl::Hidden,
               cl::desc("Aggregate arguments to code-extracted functions"));

81/// Test whether a block is valid for extraction.
82static bool isBlockValidForExtraction(const BasicBlock &BB,
                                    const SetVector<BasicBlock *> &Result,
                                    bool AllowVarArgs, bool AllowAlloca) {
// taking the address of a basic block moved to another function is illegal
if (BB.hasAddressTaken())
  return false;

// don't hoist code that uses another basicblock address, as it's likely to
// lead to unexpected behavior, like cross-function jumps
SmallPtrSet<User const *, 16> Visited;
SmallVector<User const *, 16> ToVisit;

for (Instruction const &Inst : BB)
  ToVisit.push_back(&Inst);

while (!ToVisit.empty()) {
  User const *Curr = ToVisit.pop_back_val();
  if (!Visited.insert(Curr).second)
    continue;
  if (isa<BlockAddress const>(Curr))
    return false; // even a reference to self is likely to be not compatible

  if (isa<Instruction>(Curr) && cast<Instruction>(Curr)->getParent() != &BB)
    continue;

  for (auto const &U : Curr->operands()) {
    if (auto *UU = dyn_cast<User>(U))
      ToVisit.push_back(UU);
  }
}

// If explicitly requested, allow vastart and alloca. For invoke instructions
// verify that extraction is valid.
for (BasicBlock::const_iterator I = BB.begin(), E = BB.end(); I != E; ++I) {
  if (isa<AllocaInst>(I)) {
     if (!AllowAlloca)
       return false;
     continue;
  }

  if (const auto *II = dyn_cast<InvokeInst>(I)) {
    // Unwind destination (either a landingpad, catchswitch, or cleanuppad)
    // must be a part of the subgraph which is being extracted.
    if (auto *UBB = II->getUnwindDest())
      if (!Result.count(UBB))
        return false;
    continue;
  }

  // All catch handlers of a catchswitch instruction as well as the unwind
  // destination must be in the subgraph.
  if (const auto *CSI = dyn_cast<CatchSwitchInst>(I)) {
    if (auto *UBB = CSI->getUnwindDest())
      if (!Result.count(UBB))
        return false;
    for (auto *HBB : CSI->handlers())
      if (!Result.count(const_cast<BasicBlock*>(HBB)))
        return false;
    continue;
  }

  // Make sure that entire catch handler is within subgraph. It is sufficient
  // to check that catch return's block is in the list.
  if (const auto *CPI = dyn_cast<CatchPadInst>(I)) {
    for (const auto *U : CPI->users())
      if (const auto *CRI = dyn_cast<CatchReturnInst>(U))
        if (!Result.count(const_cast<BasicBlock*>(CRI->getParent())))
          return false;
    continue;
  }

  // And do similar checks for cleanup handler - the entire handler must be
  // in subgraph which is going to be extracted. For cleanup return should
  // additionally check that the unwind destination is also in the subgraph.
  if (const auto *CPI = dyn_cast<CleanupPadInst>(I)) {
    for (const auto *U : CPI->users())
      if (const auto *CRI = dyn_cast<CleanupReturnInst>(U))
        if (!Result.count(const_cast<BasicBlock*>(CRI->getParent())))
          return false;
    continue;
  }
  if (const auto *CRI = dyn_cast<CleanupReturnInst>(I)) {
    if (auto *UBB = CRI->getUnwindDest())
      if (!Result.count(UBB))
        return false;
    continue;
  }

  if (const CallInst *CI = dyn_cast<CallInst>(I))
    if (const Function *F = CI->getCalledFunction())
      if (F->getIntrinsicID() == Intrinsic::vastart) {
        if (AllowVarArgs)
          continue;
        else
          return false;
      }
}

return true;
181}

183/// Build a set of blocks to extract if the input blocks are viable.
184static SetVector<BasicBlock *>
185buildExtractionBlockSet(ArrayRef<BasicBlock *> BBs, DominatorTree *DT,
                      bool AllowVarArgs, bool AllowAlloca) {
assert(!BBs.empty() && "The set of blocks to extract must be non-empty")(static_cast <bool> (!BBs.empty() && "The set of blocks to extract must be non-empty"
) ? void (0) : __assert_fail ("!BBs.empty() && \"The set of blocks to extract must be non-empty\""
, "/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp"
, 187, __extension__ __PRETTY_FUNCTION__));
SetVector<BasicBlock *> Result;

// Loop over the blocks, adding them to our set-vector, and aborting with an
// empty set if we encounter invalid blocks.
for (BasicBlock *BB : BBs) {
  // If this block is dead, don't process it.
  if (DT && !DT->isReachableFromEntry(BB))
    continue;

  if (!Result.insert(BB))
    llvm_unreachable("Repeated basic blocks in extraction input")::llvm::llvm_unreachable_internal("Repeated basic blocks in extraction input"
, "/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp"
, 198);
}

for (auto *BB : Result) {
  if (!isBlockValidForExtraction(*BB, Result, AllowVarArgs, AllowAlloca))
    return {};

  // Make sure that the first block is not a landing pad.
  if (BB == Result.front()) {
    if (BB->isEHPad()) {
      LLVM_DEBUG(dbgs() << "The first block cannot be an unwind block\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { dbgs() << "The first block cannot be an unwind block\n"
; } } while (false);
      return {};
    }
    continue;
  }

  // All blocks other than the first must not have predecessors outside of
  // the subgraph which is being extracted.
  for (auto *PBB : predecessors(BB))
    if (!Result.count(PBB)) {
      LLVM_DEBUG(do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { dbgs() << "No blocks in this region may have entries from "
 "outside the region except for the first block!\n"; } } while
 (false)
          dbgs() << "No blocks in this region may have entries from "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { dbgs() << "No blocks in this region may have entries from "
 "outside the region except for the first block!\n"; } } while
 (false)
                    "outside the region except for the first block!\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { dbgs() << "No blocks in this region may have entries from "
 "outside the region except for the first block!\n"; } } while
 (false);
      return {};
    }
}

return Result;
226}

228CodeExtractor::CodeExtractor(ArrayRef<BasicBlock *> BBs, DominatorTree *DT,
                           bool AggregateArgs, BlockFrequencyInfo *BFI,
                           BranchProbabilityInfo *BPI, bool AllowVarArgs,
                           bool AllowAlloca)
  : DT(DT), AggregateArgs(AggregateArgs || AggregateArgsOpt), BFI(BFI),
    BPI(BPI), AllowVarArgs(AllowVarArgs),
    Blocks(buildExtractionBlockSet(BBs, DT, AllowVarArgs, AllowAlloca)) {}

236CodeExtractor::CodeExtractor(DominatorTree &DT, Loop &L, bool AggregateArgs,
                           BlockFrequencyInfo *BFI,
                           BranchProbabilityInfo *BPI)
  : DT(&DT), AggregateArgs(AggregateArgs || AggregateArgsOpt), BFI(BFI),
    BPI(BPI), AllowVarArgs(false),
    Blocks(buildExtractionBlockSet(L.getBlocks(), &DT,
                                   /* AllowVarArgs */ false,
                                   /* AllowAlloca */ false)) {}

245/// definedInRegion - Return true if the specified value is defined in the
246/// extracted region.
247static bool definedInRegion(const SetVector<BasicBlock *> &Blocks, Value *V) {
if (Instruction *I = dyn_cast<Instruction>(V))
  if (Blocks.count(I->getParent()))
    return true;
return false;
252}

254/// definedInCaller - Return true if the specified value is defined in the
255/// function being code extracted, but not in the region being extracted.
256/// These values must be passed in as live-ins to the function.
257static bool definedInCaller(const SetVector<BasicBlock *> &Blocks, Value *V) {
if (isa<Argument>(V)) return true;
if (Instruction *I = dyn_cast<Instruction>(V))
  if (!Blocks.count(I->getParent()))
    return true;
return false;
263}

265static BasicBlock *getCommonExitBlock(const SetVector<BasicBlock *> &Blocks) {
BasicBlock *CommonExitBlock = nullptr;
auto hasNonCommonExitSucc = [&](BasicBlock *Block) {
  for (auto *Succ : successors(Block)) {
    // Internal edges, ok.
    if (Blocks.count(Succ))
      continue;
    if (!CommonExitBlock) {
      CommonExitBlock = Succ;
      continue;
    }
    if (CommonExitBlock == Succ)
      continue;

    return true;
  }
  return false;
};

if (any_of(Blocks, hasNonCommonExitSucc))
  return nullptr;

return CommonExitBlock;
288}

290bool CodeExtractor::isLegalToShrinkwrapLifetimeMarkers(
  Instruction *Addr) const {
AllocaInst *AI = cast<AllocaInst>(Addr->stripInBoundsConstantOffsets());
Function *Func = (*Blocks.begin())->getParent();
for (BasicBlock &BB : *Func) {
  if (Blocks.count(&BB))
    continue;
  for (Instruction &II : BB) {
    if (isa<DbgInfoIntrinsic>(II))
      continue;

    unsigned Opcode = II.getOpcode();
    Value *MemAddr = nullptr;
    switch (Opcode) {
    case Instruction::Store:
    case Instruction::Load: {
      if (Opcode == Instruction::Store) {
        StoreInst *SI = cast<StoreInst>(&II);
        MemAddr = SI->getPointerOperand();
      } else {
        LoadInst *LI = cast<LoadInst>(&II);
        MemAddr = LI->getPointerOperand();
      }
      // Global variable can not be aliased with locals.
      if (dyn_cast<Constant>(MemAddr))
        break;
      Value *Base = MemAddr->stripInBoundsConstantOffsets();
      if (!dyn_cast<AllocaInst>(Base) || Base == AI)
        return false;
      break;
    }
    default: {
      IntrinsicInst *IntrInst = dyn_cast<IntrinsicInst>(&II);
      if (IntrInst) {
        if (IntrInst->getIntrinsicID() == Intrinsic::lifetime_start ||
            IntrInst->getIntrinsicID() == Intrinsic::lifetime_end)
          break;
        return false;
      }
      // Treat all the other cases conservatively if it has side effects.
      if (II.mayHaveSideEffects())
        return false;
    }
    }
  }
}

return true;
338}

340BasicBlock *
341CodeExtractor::findOrCreateBlockForHoisting(BasicBlock *CommonExitBlock) {
BasicBlock *SinglePredFromOutlineRegion = nullptr;
assert(!Blocks.count(CommonExitBlock) &&(static_cast <bool> (!Blocks.count(CommonExitBlock) &&
 "Expect a block outside the region!") ? void (0) : __assert_fail
 ("!Blocks.count(CommonExitBlock) && \"Expect a block outside the region!\""
, "/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp"
, 344, __extension__ __PRETTY_FUNCTION__))
       "Expect a block outside the region!")(static_cast <bool> (!Blocks.count(CommonExitBlock) &&
 "Expect a block outside the region!") ? void (0) : __assert_fail
 ("!Blocks.count(CommonExitBlock) && \"Expect a block outside the region!\""
, "/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp"
, 344, __extension__ __PRETTY_FUNCTION__));
for (auto *Pred : predecessors(CommonExitBlock)) {
  if (!Blocks.count(Pred))
    continue;
  if (!SinglePredFromOutlineRegion) {
    SinglePredFromOutlineRegion = Pred;
  } else if (SinglePredFromOutlineRegion != Pred) {
    SinglePredFromOutlineRegion = nullptr;
    break;
  }
}

if (SinglePredFromOutlineRegion)
  return SinglePredFromOutlineRegion;

359#ifndef NDEBUG
auto getFirstPHI = [](BasicBlock *BB) {
  BasicBlock::iterator I = BB->begin();
  PHINode *FirstPhi = nullptr;
  while (I != BB->end()) {
    PHINode *Phi = dyn_cast<PHINode>(I);
    if (!Phi)
      break;
    if (!FirstPhi) {
      FirstPhi = Phi;
      break;
    }
  }
  return FirstPhi;
};
// If there are any phi nodes, the single pred either exists or has already
// be created before code extraction.
assert(!getFirstPHI(CommonExitBlock) && "Phi not expected")(static_cast <bool> (!getFirstPHI(CommonExitBlock) &&
 "Phi not expected") ? void (0) : __assert_fail ("!getFirstPHI(CommonExitBlock) && \"Phi not expected\""
, "/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp"
, 376, __extension__ __PRETTY_FUNCTION__));
377#endif

BasicBlock *NewExitBlock = CommonExitBlock->splitBasicBlock(
    CommonExitBlock->getFirstNonPHI()->getIterator());

for (auto PI = pred_begin(CommonExitBlock), PE = pred_end(CommonExitBlock);
     PI != PE;) {
  BasicBlock *Pred = *PI++;
  if (Blocks.count(Pred))
    continue;
  Pred->getTerminator()->replaceUsesOfWith(CommonExitBlock, NewExitBlock);
}
// Now add the old exit block to the outline region.
Blocks.insert(CommonExitBlock);
return CommonExitBlock;
392}

394void CodeExtractor::findAllocas(ValueSet &SinkCands, ValueSet &HoistCands,
                              BasicBlock *&ExitBlock) const {
Function *Func = (*Blocks.begin())->getParent();
ExitBlock = getCommonExitBlock(Blocks);

for (BasicBlock &BB : *Func) {
  if (Blocks.count(&BB))
    continue;
  for (Instruction &II : BB) {
    auto *AI = dyn_cast<AllocaInst>(&II);
    if (!AI)
      continue;

    // Find the pair of life time markers for address 'Addr' that are either
    // defined inside the outline region or can legally be shrinkwrapped into
    // the outline region. If there are not other untracked uses of the
    // address, return the pair of markers if found; otherwise return a pair
    // of nullptr.
    auto GetLifeTimeMarkers =
        [&](Instruction *Addr, bool &SinkLifeStart,
            bool &HoistLifeEnd) -> std::pair<Instruction *, Instruction *> {
      Instruction *LifeStart = nullptr, *LifeEnd = nullptr;

      for (User *U : Addr->users()) {
        IntrinsicInst *IntrInst = dyn_cast<IntrinsicInst>(U);
        if (IntrInst) {
          if (IntrInst->getIntrinsicID() == Intrinsic::lifetime_start) {
            // Do not handle the case where AI has multiple start markers.
            if (LifeStart)
              return std::make_pair<Instruction *>(nullptr, nullptr);
            LifeStart = IntrInst;
          }
          if (IntrInst->getIntrinsicID() == Intrinsic::lifetime_end) {
            if (LifeEnd)
              return std::make_pair<Instruction *>(nullptr, nullptr);
            LifeEnd = IntrInst;
          }
          continue;
        }
        // Find untracked uses of the address, bail.
        if (!definedInRegion(Blocks, U))
          return std::make_pair<Instruction *>(nullptr, nullptr);
      }

      if (!LifeStart || !LifeEnd)
        return std::make_pair<Instruction *>(nullptr, nullptr);

      SinkLifeStart = !definedInRegion(Blocks, LifeStart);
      HoistLifeEnd = !definedInRegion(Blocks, LifeEnd);
      // Do legality Check.
      if ((SinkLifeStart || HoistLifeEnd) &&
          !isLegalToShrinkwrapLifetimeMarkers(Addr))
        return std::make_pair<Instruction *>(nullptr, nullptr);

      // Check to see if we have a place to do hoisting, if not, bail.
      if (HoistLifeEnd && !ExitBlock)
        return std::make_pair<Instruction *>(nullptr, nullptr);

      return std::make_pair(LifeStart, LifeEnd);
    };

    bool SinkLifeStart = false, HoistLifeEnd = false;
    auto Markers = GetLifeTimeMarkers(AI, SinkLifeStart, HoistLifeEnd);

    if (Markers.first) {
      if (SinkLifeStart)
        SinkCands.insert(Markers.first);
      SinkCands.insert(AI);
      if (HoistLifeEnd)
        HoistCands.insert(Markers.second);
      continue;
    }

    // Follow the bitcast.
    Instruction *MarkerAddr = nullptr;
    for (User *U : AI->users()) {
      if (U->stripInBoundsConstantOffsets() == AI) {
        SinkLifeStart = false;
        HoistLifeEnd = false;
        Instruction *Bitcast = cast<Instruction>(U);
        Markers = GetLifeTimeMarkers(Bitcast, SinkLifeStart, HoistLifeEnd);
        if (Markers.first) {
          MarkerAddr = Bitcast;
          continue;
        }
      }

      // Found unknown use of AI.
      if (!definedInRegion(Blocks, U)) {
        MarkerAddr = nullptr;
        break;
      }
    }

    if (MarkerAddr) {
      if (SinkLifeStart)
        SinkCands.insert(Markers.first);
      if (!definedInRegion(Blocks, MarkerAddr))
        SinkCands.insert(MarkerAddr);
      SinkCands.insert(AI);
      if (HoistLifeEnd)
        HoistCands.insert(Markers.second);
    }
  }
}
499}

501void CodeExtractor::findInputsOutputs(ValueSet &Inputs, ValueSet &Outputs,
                                    const ValueSet &SinkCands) const {
for (BasicBlock *BB : Blocks) {
  // If a used value is defined outside the region, it's an input.  If an
  // instruction is used outside the region, it's an output.
  for (Instruction &II : *BB) {
    for (User::op_iterator OI = II.op_begin(), OE = II.op_end(); OI != OE;
         ++OI) {
      Value *V = *OI;
      if (!SinkCands.count(V) && definedInCaller(Blocks, V))
        Inputs.insert(V);
    }

    for (User *U : II.users())
      if (!definedInRegion(Blocks, U)) {
        Outputs.insert(&II);
        break;
      }
  }
}
521}

523/// severSplitPHINodes - If a PHI node has multiple inputs from outside of the
524/// region, we need to split the entry block of the region so that the PHI node
525/// is easier to deal with.
526void CodeExtractor::severSplitPHINodes(BasicBlock *&Header) {
unsigned NumPredsFromRegion = 0;
unsigned NumPredsOutsideRegion = 0;

if (Header != &Header->getParent()->getEntryBlock()) {
  PHINode *PN = dyn_cast<PHINode>(Header->begin());
  if (!PN) return;  // No PHI nodes.

  // If the header node contains any PHI nodes, check to see if there is more
  // than one entry from outside the region.  If so, we need to sever the
  // header block into two.
  for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i)
    if (Blocks.count(PN->getIncomingBlock(i)))
      ++NumPredsFromRegion;
    else
      ++NumPredsOutsideRegion;

  // If there is one (or fewer) predecessor from outside the region, we don't
  // need to do anything special.
  if (NumPredsOutsideRegion <= 1) return;
}

// Otherwise, we need to split the header block into two pieces: one
// containing PHI nodes merging values from outside of the region, and a
// second that contains all of the code for the block and merges back any
// incoming values from inside of the region.
BasicBlock *NewBB = SplitBlock(Header, Header->getFirstNonPHI(), DT);

// We only want to code extract the second block now, and it becomes the new
// header of the region.
BasicBlock *OldPred = Header;
Blocks.remove(OldPred);
Blocks.insert(NewBB);
Header = NewBB;

// Okay, now we need to adjust the PHI nodes and any branches from within the
// region to go to the new header block instead of the old header block.
if (NumPredsFromRegion) {
  PHINode *PN = cast<PHINode>(OldPred->begin());
  // Loop over all of the predecessors of OldPred that are in the region,
  // changing them to branch to NewBB instead.
  for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i)
    if (Blocks.count(PN->getIncomingBlock(i))) {
      TerminatorInst *TI = PN->getIncomingBlock(i)->getTerminator();
      TI->replaceUsesOfWith(OldPred, NewBB);
    }

  // Okay, everything within the region is now branching to the right block, we
  // just have to update the PHI nodes now, inserting PHI nodes into NewBB.
  BasicBlock::iterator AfterPHIs;
  for (AfterPHIs = OldPred->begin(); isa<PHINode>(AfterPHIs); ++AfterPHIs) {
    PHINode *PN = cast<PHINode>(AfterPHIs);
    // Create a new PHI node in the new region, which has an incoming value
    // from OldPred of PN.
    PHINode *NewPN = PHINode::Create(PN->getType(), 1 + NumPredsFromRegion,
                                     PN->getName() + ".ce", &NewBB->front());
    PN->replaceAllUsesWith(NewPN);
    NewPN->addIncoming(PN, OldPred);

    // Loop over all of the incoming value in PN, moving them to NewPN if they
    // are from the extracted region.
    for (unsigned i = 0; i != PN->getNumIncomingValues(); ++i) {
      if (Blocks.count(PN->getIncomingBlock(i))) {
        NewPN->addIncoming(PN->getIncomingValue(i), PN->getIncomingBlock(i));
        PN->removeIncomingValue(i);
        --i;
      }
    }
  }
}
596}

598void CodeExtractor::splitReturnBlocks() {
for (BasicBlock *Block : Blocks)
  if (ReturnInst *RI = dyn_cast<ReturnInst>(Block->getTerminator())) {
    BasicBlock *New =
        Block->splitBasicBlock(RI->getIterator(), Block->getName() + ".ret");
    if (DT) {
      // Old dominates New. New node dominates all other nodes dominated
      // by Old.
      DomTreeNode *OldNode = DT->getNode(Block);
      SmallVector<DomTreeNode *, 8> Children(OldNode->begin(),
                                             OldNode->end());

      DomTreeNode *NewNode = DT->addNewBlock(New, Block);

      for (DomTreeNode *I : Children)
        DT->changeImmediateDominator(I, NewNode);
    }
  }
616}

618/// constructFunction - make a function based on inputs and outputs, as follows:
619/// f(in0, ..., inN, out0, ..., outN)
620Function *CodeExtractor::constructFunction(const ValueSet &inputs,
                                         const ValueSet &outputs,
                                         BasicBlock *header,
                                         BasicBlock *newRootNode,
                                         BasicBlock *newHeader,
                                         Function *oldFunction,
                                         Module *M) {
LLVM_DEBUG(dbgs() << "inputs: " << inputs.size() << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { dbgs() << "inputs: " << inputs
.size() << "\n"; } } while (false);
LLVM_DEBUG(dbgs() << "outputs: " << outputs.size() << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { dbgs() << "outputs: " << outputs
.size() << "\n"; } } while (false);

// This function returns unsigned, outputs will go back by reference.
switch (NumExitBlocks) {
1
Control jumps to the 'default' case at line 635→
case 0:
case 1: RetTy = Type::getVoidTy(header->getContext()); break;
case 2: RetTy = Type::getInt1Ty(header->getContext()); break;
default: RetTy = Type::getInt16Ty(header->getContext()); break;
2
←
 Execution continues on line 638→
}

std::vector<Type *> paramTy;

// Add the types of the input values to the function's argument list
for (Value *value : inputs) {
  LLVM_DEBUG(dbgs() << "value used in func: " << *value << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { dbgs() << "value used in func: " <<
 *value << "\n"; } } while (false);
  paramTy.push_back(value->getType());
}

// Add the types of the output values to the function's argument list.
for (Value *output : outputs) {
  LLVM_DEBUG(dbgs() << "instr used in func: " << *output << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { dbgs() << "instr used in func: " <<
 *output << "\n"; } } while (false);
  if (AggregateArgs)
    paramTy.push_back(output->getType());
  else
    paramTy.push_back(PointerType::getUnqual(output->getType()));
}

LLVM_DEBUG({do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { { dbgs() << "Function type: " <<
 *RetTy << " f("; for (Type *i : paramTy) dbgs() <<
 *i << ", "; dbgs() << ")\n"; }; } } while (false
)
  dbgs() << "Function type: " << *RetTy << " f(";do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { { dbgs() << "Function type: " <<
 *RetTy << " f("; for (Type *i : paramTy) dbgs() <<
 *i << ", "; dbgs() << ")\n"; }; } } while (false
)
  for (Type *i : paramTy)do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { { dbgs() << "Function type: " <<
 *RetTy << " f("; for (Type *i : paramTy) dbgs() <<
 *i << ", "; dbgs() << ")\n"; }; } } while (false
)
    dbgs() << *i << ", ";do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { { dbgs() << "Function type: " <<
 *RetTy << " f("; for (Type *i : paramTy) dbgs() <<
 *i << ", "; dbgs() << ")\n"; }; } } while (false
)
  dbgs() << ")\n";do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { { dbgs() << "Function type: " <<
 *RetTy << " f("; for (Type *i : paramTy) dbgs() <<
 *i << ", "; dbgs() << ")\n"; }; } } while (false
)
})do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { { dbgs() << "Function type: " <<
 *RetTy << " f("; for (Type *i : paramTy) dbgs() <<
 *i << ", "; dbgs() << ")\n"; }; } } while (false
);

StructType *StructTy;
3
←
'StructTy' declared without an initial value→
if (AggregateArgs && (inputs.size() + outputs.size() > 0)) {
4
←
Assuming the condition is true→
5
←
Assuming the condition is false→
6
←
Taking false branch→
  StructTy = StructType::get(M->getContext(), paramTy);
  paramTy.clear();
  paramTy.push_back(PointerType::getUnqual(StructTy));
}
FunctionType *funcType =
                FunctionType::get(RetTy, paramTy,
                                  AllowVarArgs && oldFunction->isVarArg());
7
←
Assuming the condition is false→

// Create the new function
Function *newFunction = Function::Create(funcType,
                                         GlobalValue::InternalLinkage,
                                         oldFunction->getName() + "_" +
                                         header->getName(), M);
// If the old function is no-throw, so is the new one.
if (oldFunction->doesNotThrow())
8
←
Assuming the condition is false→
9
←
Taking false branch→
  newFunction->setDoesNotThrow();

// Inherit the uwtable attribute if we need to.
if (oldFunction->hasUWTable())
10
←
Assuming the condition is false→
11
←
Taking false branch→
  newFunction->setHasUWTable();

// Inherit all of the target dependent attributes and white-listed
// target independent attributes.
//  (e.g. If the extracted region contains a call to an x86.sse
//  instruction we need to make sure that the extracted region has the
//  "target-features" attribute allowing it to be lowered.
// FIXME: This should be changed to check to see if a specific
//           attribute can not be inherited.
for (const auto &Attr : oldFunction->getAttributes().getFnAttributes()) {
12
←
Assuming '__begin1' is equal to '__end1'→
  if (Attr.isStringAttribute()) {
    if (Attr.getKindAsString() == "thunk")
      continue;
  } else
    switch (Attr.getKindAsEnum()) {
    // Those attributes cannot be propagated safely. Explicitly list them
    // here so we get a warning if new attributes are added. This list also
    // includes non-function attributes.
    case Attribute::Alignment:
    case Attribute::AllocSize:
    case Attribute::ArgMemOnly:
    case Attribute::Builtin:
    case Attribute::ByVal:
    case Attribute::Convergent:
    case Attribute::Dereferenceable:
    case Attribute::DereferenceableOrNull:
    case Attribute::InAlloca:
    case Attribute::InReg:
    case Attribute::InaccessibleMemOnly:
    case Attribute::InaccessibleMemOrArgMemOnly:
    case Attribute::JumpTable:
    case Attribute::Naked:
    case Attribute::Nest:
    case Attribute::NoAlias:
    case Attribute::NoBuiltin:
    case Attribute::NoCapture:
    case Attribute::NoReturn:
    case Attribute::None:
    case Attribute::NonNull:
    case Attribute::ReadNone:
    case Attribute::ReadOnly:
    case Attribute::Returned:
    case Attribute::ReturnsTwice:
    case Attribute::SExt:
    case Attribute::Speculatable:
    case Attribute::StackAlignment:
    case Attribute::StructRet:
    case Attribute::SwiftError:
    case Attribute::SwiftSelf:
    case Attribute::WriteOnly:
    case Attribute::ZExt:
    case Attribute::EndAttrKinds:
      continue;
    // Those attributes should be safe to propagate to the extracted function.
    case Attribute::AlwaysInline:
    case Attribute::Cold:
    case Attribute::NoRecurse:
    case Attribute::InlineHint:
    case Attribute::MinSize:
    case Attribute::NoDuplicate:
    case Attribute::NoImplicitFloat:
    case Attribute::NoInline:
    case Attribute::NonLazyBind:
    case Attribute::NoRedZone:
    case Attribute::NoUnwind:
    case Attribute::OptForFuzzing:
    case Attribute::OptimizeNone:
    case Attribute::OptimizeForSize:
    case Attribute::SafeStack:
    case Attribute::ShadowCallStack:
    case Attribute::SanitizeAddress:
    case Attribute::SanitizeMemory:
    case Attribute::SanitizeThread:
    case Attribute::SanitizeHWAddress:
    case Attribute::StackProtect:
    case Attribute::StackProtectReq:
    case Attribute::StackProtectStrong:
    case Attribute::StrictFP:
    case Attribute::UWTable:
    case Attribute::NoCfCheck:
      break;
    }

  newFunction->addFnAttr(Attr);
}
newFunction->getBasicBlockList().push_back(newRootNode);

// Create an iterator to name all of the arguments we inserted.
Function::arg_iterator AI = newFunction->arg_begin();

// Rewrite all users of the inputs in the extracted region to use the
// arguments (or appropriate addressing into struct) instead.
for (unsigned i = 0, e = inputs.size(); i != e; ++i) {
13
←
Assuming 'i' is not equal to 'e'→
14
←
Loop condition is true.  Entering loop body→
  Value *RewriteVal;
  if (AggregateArgs) {
15
←
Taking true branch→
    Value *Idx[2];
    Idx[0] = Constant::getNullValue(Type::getInt32Ty(header->getContext()));
    Idx[1] = ConstantInt::get(Type::getInt32Ty(header->getContext()), i);
    TerminatorInst *TI = newFunction->begin()->getTerminator();
    GetElementPtrInst *GEP = GetElementPtrInst::Create(
16
←
1st function call argument is an uninitialized value
        StructTy, &*AI, Idx, "gep_" + inputs[i]->getName(), TI);
    RewriteVal = new LoadInst(GEP, "loadgep_" + inputs[i]->getName(), TI);
  } else
    RewriteVal = &*AI++;

  std::vector<User *> Users(inputs[i]->user_begin(), inputs[i]->user_end());
  for (User *use : Users)
    if (Instruction *inst = dyn_cast<Instruction>(use))
      if (Blocks.count(inst->getParent()))
        inst->replaceUsesOfWith(inputs[i], RewriteVal);
}

// Set names for input and output arguments.
if (!AggregateArgs) {
  AI = newFunction->arg_begin();
  for (unsigned i = 0, e = inputs.size(); i != e; ++i, ++AI)
    AI->setName(inputs[i]->getName());
  for (unsigned i = 0, e = outputs.size(); i != e; ++i, ++AI)
    AI->setName(outputs[i]->getName()+".out");
}

// Rewrite branches to basic blocks outside of the loop to new dummy blocks
// within the new function. This must be done before we lose track of which
// blocks were originally in the code region.
std::vector<User *> Users(header->user_begin(), header->user_end());
for (unsigned i = 0, e = Users.size(); i != e; ++i)
  // The BasicBlock which contains the branch is not in the region
  // modify the branch target to a new block
  if (TerminatorInst *TI = dyn_cast<TerminatorInst>(Users[i]))
    if (!Blocks.count(TI->getParent()) &&
        TI->getParent()->getParent() == oldFunction)
      TI->replaceUsesOfWith(header, newHeader);

return newFunction;
817}

819/// emitCallAndSwitchStatement - This method sets up the caller side by adding
820/// the call instruction, splitting any PHI nodes in the header block as
821/// necessary.
822void CodeExtractor::
823emitCallAndSwitchStatement(Function *newFunction, BasicBlock *codeReplacer,
                         ValueSet &inputs, ValueSet &outputs) {
// Emit a call to the new function, passing in: *pointer to struct (if
// aggregating parameters), or plan inputs and allocated memory for outputs
std::vector<Value *> params, StructValues, ReloadOutputs, Reloads;

Module *M = newFunction->getParent();
LLVMContext &Context = M->getContext();
const DataLayout &DL = M->getDataLayout();

// Add inputs as params, or to be filled into the struct
for (Value *input : inputs)
  if (AggregateArgs)
    StructValues.push_back(input);
  else
    params.push_back(input);

// Create allocas for the outputs
for (Value *output : outputs) {
  if (AggregateArgs) {
    StructValues.push_back(output);
  } else {
    AllocaInst *alloca =
      new AllocaInst(output->getType(), DL.getAllocaAddrSpace(),
                     nullptr, output->getName() + ".loc",
                     &codeReplacer->getParent()->front().front());
    ReloadOutputs.push_back(alloca);
    params.push_back(alloca);
  }
}

StructType *StructArgTy = nullptr;
AllocaInst *Struct = nullptr;
if (AggregateArgs && (inputs.size() + outputs.size() > 0)) {
  std::vector<Type *> ArgTypes;
  for (ValueSet::iterator v = StructValues.begin(),
         ve = StructValues.end(); v != ve; ++v)
    ArgTypes.push_back((*v)->getType());

  // Allocate a struct at the beginning of this function
  StructArgTy = StructType::get(newFunction->getContext(), ArgTypes);
  Struct = new AllocaInst(StructArgTy, DL.getAllocaAddrSpace(), nullptr,
                          "structArg",
                          &codeReplacer->getParent()->front().front());
  params.push_back(Struct);

  for (unsigned i = 0, e = inputs.size(); i != e; ++i) {
    Value *Idx[2];
    Idx[0] = Constant::getNullValue(Type::getInt32Ty(Context));
    Idx[1] = ConstantInt::get(Type::getInt32Ty(Context), i);
    GetElementPtrInst *GEP = GetElementPtrInst::Create(
        StructArgTy, Struct, Idx, "gep_" + StructValues[i]->getName());
    codeReplacer->getInstList().push_back(GEP);
    StoreInst *SI = new StoreInst(StructValues[i], GEP);
    codeReplacer->getInstList().push_back(SI);
  }
}

// Emit the call to the function
CallInst *call = CallInst::Create(newFunction, params,
                                  NumExitBlocks > 1 ? "targetBlock" : "");
// Add debug location to the new call, if the original function has debug
// info. In that case, the terminator of the entry block of the extracted
// function contains the first debug location of the extracted function,
// set in extractCodeRegion.
if (codeReplacer->getParent()->getSubprogram()) {
  if (auto DL = newFunction->getEntryBlock().getTerminator()->getDebugLoc())
    call->setDebugLoc(DL);
}
codeReplacer->getInstList().push_back(call);

Function::arg_iterator OutputArgBegin = newFunction->arg_begin();
unsigned FirstOut = inputs.size();
if (!AggregateArgs)
  std::advance(OutputArgBegin, inputs.size());

// Reload the outputs passed in by reference.
Function::arg_iterator OAI = OutputArgBegin;
for (unsigned i = 0, e = outputs.size(); i != e; ++i) {
  Value *Output = nullptr;
  if (AggregateArgs) {
    Value *Idx[2];
    Idx[0] = Constant::getNullValue(Type::getInt32Ty(Context));
    Idx[1] = ConstantInt::get(Type::getInt32Ty(Context), FirstOut + i);
    GetElementPtrInst *GEP = GetElementPtrInst::Create(
        StructArgTy, Struct, Idx, "gep_reload_" + outputs[i]->getName());
    codeReplacer->getInstList().push_back(GEP);
    Output = GEP;
  } else {
    Output = ReloadOutputs[i];
  }
  LoadInst *load = new LoadInst(Output, outputs[i]->getName()+".reload");
  Reloads.push_back(load);
  codeReplacer->getInstList().push_back(load);
  std::vector<User *> Users(outputs[i]->user_begin(), outputs[i]->user_end());
  for (unsigned u = 0, e = Users.size(); u != e; ++u) {
    Instruction *inst = cast<Instruction>(Users[u]);
    if (!Blocks.count(inst->getParent()))
      inst->replaceUsesOfWith(outputs[i], load);
  }

  // Store to argument right after the definition of output value.
  auto *OutI = dyn_cast<Instruction>(outputs[i]);
  if (!OutI)
    continue;
  // Find proper insertion point.
  Instruction *InsertPt = OutI->getNextNode();
  // Let's assume that there is no other guy interleave non-PHI in PHIs.
  if (isa<PHINode>(InsertPt))
    InsertPt = InsertPt->getParent()->getFirstNonPHI();

  assert(OAI != newFunction->arg_end() &&(static_cast <bool> (OAI != newFunction->arg_end() &&
 "Number of output arguments should match " "the amount of defined values"
) ? void (0) : __assert_fail ("OAI != newFunction->arg_end() && \"Number of output arguments should match \" \"the amount of defined values\""
, "/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp"
, 936, __extension__ __PRETTY_FUNCTION__))
         "Number of output arguments should match "(static_cast <bool> (OAI != newFunction->arg_end() &&
 "Number of output arguments should match " "the amount of defined values"
) ? void (0) : __assert_fail ("OAI != newFunction->arg_end() && \"Number of output arguments should match \" \"the amount of defined values\""
, "/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp"
, 936, __extension__ __PRETTY_FUNCTION__))
         "the amount of defined values")(static_cast <bool> (OAI != newFunction->arg_end() &&
 "Number of output arguments should match " "the amount of defined values"
) ? void (0) : __assert_fail ("OAI != newFunction->arg_end() && \"Number of output arguments should match \" \"the amount of defined values\""
, "/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp"
, 936, __extension__ __PRETTY_FUNCTION__));
  if (AggregateArgs) {
    Value *Idx[2];
    Idx[0] = Constant::getNullValue(Type::getInt32Ty(Context));
    Idx[1] = ConstantInt::get(Type::getInt32Ty(Context), FirstOut + i);
    GetElementPtrInst *GEP = GetElementPtrInst::Create(
        StructArgTy, &*OAI, Idx, "gep_" + outputs[i]->getName(), InsertPt);
    new StoreInst(outputs[i], GEP, InsertPt);
    // Since there should be only one struct argument aggregating
    // all the output values, we shouldn't increment OAI, which always
    // points to the struct argument, in this case.
  } else {
    new StoreInst(outputs[i], &*OAI, InsertPt);
    ++OAI;
  }
}

// Now we can emit a switch statement using the call as a value.
SwitchInst *TheSwitch =
    SwitchInst::Create(Constant::getNullValue(Type::getInt16Ty(Context)),
                       codeReplacer, 0, codeReplacer);

// Since there may be multiple exits from the original region, make the new
// function return an unsigned, switch on that number.  This loop iterates
// over all of the blocks in the extracted region, updating any terminator
// instructions in the to-be-extracted region that branch to blocks that are
// not in the region to be extracted.
std::map<BasicBlock *, BasicBlock *> ExitBlockMap;

unsigned switchVal = 0;
for (BasicBlock *Block : Blocks) {
  TerminatorInst *TI = Block->getTerminator();
  for (unsigned i = 0, e = TI->getNumSuccessors(); i != e; ++i)
    if (!Blocks.count(TI->getSuccessor(i))) {
      BasicBlock *OldTarget = TI->getSuccessor(i);
      // add a new basic block which returns the appropriate value
      BasicBlock *&NewTarget = ExitBlockMap[OldTarget];
      if (!NewTarget) {
        // If we don't already have an exit stub for this non-extracted
        // destination, create one now!
        NewTarget = BasicBlock::Create(Context,
                                       OldTarget->getName() + ".exitStub",
                                       newFunction);
        unsigned SuccNum = switchVal++;

        Value *brVal = nullptr;
        switch (NumExitBlocks) {
        case 0:
        case 1: break;  // No value needed.
        case 2:         // Conditional branch, return a bool
          brVal = ConstantInt::get(Type::getInt1Ty(Context), !SuccNum);
          break;
        default:
          brVal = ConstantInt::get(Type::getInt16Ty(Context), SuccNum);
          break;
        }

        ReturnInst::Create(Context, brVal, NewTarget);

        // Update the switch instruction.
        TheSwitch->addCase(ConstantInt::get(Type::getInt16Ty(Context),
                                            SuccNum),
                           OldTarget);
      }

      // rewrite the original branch instruction with this new target
      TI->setSuccessor(i, NewTarget);
    }
}

// Now that we've done the deed, simplify the switch instruction.
Type *OldFnRetTy = TheSwitch->getParent()->getParent()->getReturnType();
switch (NumExitBlocks) {
case 0:
  // There are no successors (the block containing the switch itself), which
  // means that previously this was the last part of the function, and hence
  // this should be rewritten as a `ret'

  // Check if the function should return a value
  if (OldFnRetTy->isVoidTy()) {
    ReturnInst::Create(Context, nullptr, TheSwitch);  // Return void
  } else if (OldFnRetTy == TheSwitch->getCondition()->getType()) {
    // return what we have
    ReturnInst::Create(Context, TheSwitch->getCondition(), TheSwitch);
  } else {
    // Otherwise we must have code extracted an unwind or something, just
    // return whatever we want.
    ReturnInst::Create(Context, 
                       Constant::getNullValue(OldFnRetTy), TheSwitch);
  }

  TheSwitch->eraseFromParent();
  break;
case 1:
  // Only a single destination, change the switch into an unconditional
  // branch.
  BranchInst::Create(TheSwitch->getSuccessor(1), TheSwitch);
  TheSwitch->eraseFromParent();
  break;
case 2:
  BranchInst::Create(TheSwitch->getSuccessor(1), TheSwitch->getSuccessor(2),
                     call, TheSwitch);
  TheSwitch->eraseFromParent();
  break;
default:
  // Otherwise, make the default destination of the switch instruction be one
  // of the other successors.
  TheSwitch->setCondition(call);
  TheSwitch->setDefaultDest(TheSwitch->getSuccessor(NumExitBlocks));
  // Remove redundant case
  TheSwitch->removeCase(SwitchInst::CaseIt(TheSwitch, NumExitBlocks-1));
  break;
}
1049}

1051void CodeExtractor::moveCodeToFunction(Function *newFunction) {
Function *oldFunc = (*Blocks.begin())->getParent();
Function::BasicBlockListType &oldBlocks = oldFunc->getBasicBlockList();
Function::BasicBlockListType &newBlocks = newFunction->getBasicBlockList();

for (BasicBlock *Block : Blocks) {
  // Delete the basic block from the old function, and the list of blocks
  oldBlocks.remove(Block);

  // Insert this basic block into the new function
  newBlocks.push_back(Block);
}
1063}

1065void CodeExtractor::calculateNewCallTerminatorWeights(
  BasicBlock *CodeReplacer,
  DenseMap<BasicBlock *, BlockFrequency> &ExitWeights,
  BranchProbabilityInfo *BPI) {
using Distribution = BlockFrequencyInfoImplBase::Distribution;
using BlockNode = BlockFrequencyInfoImplBase::BlockNode;

// Update the branch weights for the exit block.
TerminatorInst *TI = CodeReplacer->getTerminator();
SmallVector<unsigned, 8> BranchWeights(TI->getNumSuccessors(), 0);

// Block Frequency distribution with dummy node.
Distribution BranchDist;

// Add each of the frequencies of the successors.
for (unsigned i = 0, e = TI->getNumSuccessors(); i < e; ++i) {
  BlockNode ExitNode(i);
  uint64_t ExitFreq = ExitWeights[TI->getSuccessor(i)].getFrequency();
  if (ExitFreq != 0)
    BranchDist.addExit(ExitNode, ExitFreq);
  else
    BPI->setEdgeProbability(CodeReplacer, i, BranchProbability::getZero());
}

// Check for no total weight.
if (BranchDist.Total == 0)
  return;

// Normalize the distribution so that they can fit in unsigned.
BranchDist.normalize();

// Create normalized branch weights and set the metadata.
for (unsigned I = 0, E = BranchDist.Weights.size(); I < E; ++I) {
  const auto &Weight = BranchDist.Weights[I];

  // Get the weight and update the current BFI.
  BranchWeights[Weight.TargetNode.Index] = Weight.Amount;
  BranchProbability BP(Weight.Amount, BranchDist.Total);
  BPI->setEdgeProbability(CodeReplacer, Weight.TargetNode.Index, BP);
}
TI->setMetadata(
    LLVMContext::MD_prof,
    MDBuilder(TI->getContext()).createBranchWeights(BranchWeights));
1108}

1110Function *CodeExtractor::extractCodeRegion() {
if (!isEligible())
  return nullptr;

// Assumption: this is a single-entry code region, and the header is the first
// block in the region.
BasicBlock *header = *Blocks.begin();
Function *oldFunction = header->getParent();

// For functions with varargs, check that varargs handling is only done in the
// outlined function, i.e vastart and vaend are only used in outlined blocks.
if (AllowVarArgs && oldFunction->getFunctionType()->isVarArg()) {
  auto containsVarArgIntrinsic = [](Instruction &I) {
    if (const CallInst *CI = dyn_cast<CallInst>(&I))
      if (const Function *F = CI->getCalledFunction())
        return F->getIntrinsicID() == Intrinsic::vastart ||
               F->getIntrinsicID() == Intrinsic::vaend;
    return false;
  };

  for (auto &BB : *oldFunction) {
    if (Blocks.count(&BB))
      continue;
    if (llvm::any_of(BB, containsVarArgIntrinsic))
      return nullptr;
  }
}
ValueSet inputs, outputs, SinkingCands, HoistingCands;
BasicBlock *CommonExit = nullptr;

// Calculate the entry frequency of the new function before we change the root
//   block.
BlockFrequency EntryFreq;
if (BFI) {
  assert(BPI && "Both BPI and BFI are required to preserve profile info")(static_cast <bool> (BPI && "Both BPI and BFI are required to preserve profile info"
) ? void (0) : __assert_fail ("BPI && \"Both BPI and BFI are required to preserve profile info\""
, "/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp"
, 1144, __extension__ __PRETTY_FUNCTION__));
  for (BasicBlock *Pred : predecessors(header)) {
    if (Blocks.count(Pred))
      continue;
    EntryFreq +=
        BFI->getBlockFreq(Pred) * BPI->getEdgeProbability(Pred, header);
  }
}

// If we have to split PHI nodes or the entry block, do so now.
severSplitPHINodes(header);

// If we have any return instructions in the region, split those blocks so
// that the return is not in the region.
splitReturnBlocks();

// This takes place of the original loop
BasicBlock *codeReplacer = BasicBlock::Create(header->getContext(), 
                                              "codeRepl", oldFunction,
                                              header);

// The new function needs a root node because other nodes can branch to the
// head of the region, but the entry node of a function cannot have preds.
BasicBlock *newFuncRoot = BasicBlock::Create(header->getContext(), 
                                             "newFuncRoot");
auto *BranchI = BranchInst::Create(header);
// If the original function has debug info, we have to add a debug location
// to the new branch instruction from the artificial entry block.
// We use the debug location of the first instruction in the extracted
// blocks, as there is no other equivalent line in the source code.
if (oldFunction->getSubprogram()) {
  any_of(Blocks, [&BranchI](const BasicBlock *BB) {
    return any_of(*BB, [&BranchI](const Instruction &I) {
      if (!I.getDebugLoc())
        return false;
      BranchI->setDebugLoc(I.getDebugLoc());
      return true;
    });
  });
}
newFuncRoot->getInstList().push_back(BranchI);

findAllocas(SinkingCands, HoistingCands, CommonExit);
assert(HoistingCands.empty() || CommonExit)(static_cast <bool> (HoistingCands.empty() || CommonExit
) ? void (0) : __assert_fail ("HoistingCands.empty() || CommonExit"
, "/build/llvm-toolchain-snapshot-7~svn338205/lib/Transforms/Utils/CodeExtractor.cpp"
, 1187, __extension__ __PRETTY_FUNCTION__));

// Find inputs to, outputs from the code region.
findInputsOutputs(inputs, outputs, SinkingCands);

// Now sink all instructions which only have non-phi uses inside the region
for (auto *II : SinkingCands)
  cast<Instruction>(II)->moveBefore(*newFuncRoot,
                                    newFuncRoot->getFirstInsertionPt());

if (!HoistingCands.empty()) {
  auto *HoistToBlock = findOrCreateBlockForHoisting(CommonExit);
  Instruction *TI = HoistToBlock->getTerminator();
  for (auto *II : HoistingCands)
    cast<Instruction>(II)->moveBefore(TI);
}

// Calculate the exit blocks for the extracted region and the total exit
// weights for each of those blocks.
DenseMap<BasicBlock *, BlockFrequency> ExitWeights;
SmallPtrSet<BasicBlock *, 1> ExitBlocks;
for (BasicBlock *Block : Blocks) {
  for (succ_iterator SI = succ_begin(Block), SE = succ_end(Block); SI != SE;
       ++SI) {
    if (!Blocks.count(*SI)) {
      // Update the branch weight for this successor.
      if (BFI) {
        BlockFrequency &BF = ExitWeights[*SI];
        BF += BFI->getBlockFreq(Block) * BPI->getEdgeProbability(Block, *SI);
      }
      ExitBlocks.insert(*SI);
    }
  }
}
NumExitBlocks = ExitBlocks.size();

// Construct new function based on inputs/outputs & add allocas for all defs.
Function *newFunction = constructFunction(inputs, outputs, header,
                                          newFuncRoot,
                                          codeReplacer, oldFunction,
                                          oldFunction->getParent());

// Update the entry count of the function.
if (BFI) {
  auto Count = BFI->getProfileCountFromFreq(EntryFreq.getFrequency());
  if (Count.hasValue())
    newFunction->setEntryCount(
        ProfileCount(Count.getValue(), Function::PCT_Real)); // FIXME
  BFI->setBlockFreq(codeReplacer, EntryFreq.getFrequency());
}

emitCallAndSwitchStatement(newFunction, codeReplacer, inputs, outputs);

moveCodeToFunction(newFunction);

// Propagate personality info to the new function if there is one.
if (oldFunction->hasPersonalityFn())
  newFunction->setPersonalityFn(oldFunction->getPersonalityFn());

// Update the branch weights for the exit block.
if (BFI && NumExitBlocks > 1)
  calculateNewCallTerminatorWeights(codeReplacer, ExitWeights, BPI);

// Loop over all of the PHI nodes in the header block, and change any
// references to the old incoming edge to be the new incoming edge.
for (BasicBlock::iterator I = header->begin(); isa<PHINode>(I); ++I) {
  PHINode *PN = cast<PHINode>(I);
  for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i)
    if (!Blocks.count(PN->getIncomingBlock(i)))
      PN->setIncomingBlock(i, newFuncRoot);
}

// Look at all successors of the codeReplacer block.  If any of these blocks
// had PHI nodes in them, we need to update the "from" block to be the code
// replacer, not the original block in the extracted region.
std::vector<BasicBlock *> Succs(succ_begin(codeReplacer),
                                succ_end(codeReplacer));
for (unsigned i = 0, e = Succs.size(); i != e; ++i)
  for (BasicBlock::iterator I = Succs[i]->begin(); isa<PHINode>(I); ++I) {
    PHINode *PN = cast<PHINode>(I);
    std::set<BasicBlock*> ProcessedPreds;
    for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i)
      if (Blocks.count(PN->getIncomingBlock(i))) {
        if (ProcessedPreds.insert(PN->getIncomingBlock(i)).second)
          PN->setIncomingBlock(i, codeReplacer);
        else {
          // There were multiple entries in the PHI for this block, now there
          // is only one, so remove the duplicated entries.
          PN->removeIncomingValue(i, false);
          --i; --e;
        }
      }
  }

LLVM_DEBUG(if (verifyFunction(*newFunction))do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { if (verifyFunction(*newFunction)) report_fatal_error
("verifyFunction failed!"); } } while (false)
               report_fatal_error("verifyFunction failed!"))do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("code-extractor")) { if (verifyFunction(*newFunction)) report_fatal_error
("verifyFunction failed!"); } } while (false);
return newFunction;
1284}