Revert "Codegen: Tail-duplicate during placement."

This reverts commit 71c312652c10f1855b28d06697c08d47e7a243e4.

llvm-svn: 283647

3 files changed, 41 insertions, 326 deletions

diff --git a/llvm/lib/CodeGen/MachineBlockPlacement.cpp b/llvm/lib/CodeGen/MachineBlockPlacement.cpp
index 6adab3290a0..90a576a6621 100644
--- a/llvm/lib/CodeGen/MachineBlockPlacement.cpp
+++ b/llvm/lib/CodeGen/MachineBlockPlacement.cpp
@@ -40,7 +40,6 @@
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
-#include "llvm/CodeGen/TailDuplicator.h"
 #include "llvm/Support/Allocator.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
@@ -122,12 +121,6 @@ static cl::opt<unsigned> MisfetchCost(
 static cl::opt<unsigned> JumpInstCost("jump-inst-cost",
                                       cl::desc("Cost of jump instructions."),
                                       cl::init(1), cl::Hidden);
-static cl::opt<bool>
-TailDupPlacement("tail-dup-placement",
-              cl::desc("Perform tail duplication during placement. "
-                       "Creates more fallthrough opportunites in "
-                       "outline branches."),
-              cl::init(true), cl::Hidden);
 
 static cl::opt<bool>
 BranchFoldPlacement("branch-fold-placement",
@@ -135,14 +128,6 @@ BranchFoldPlacement("branch-fold-placement",
                        "Reduces code size."),
               cl::init(true), cl::Hidden);
 
-// Heuristic for tail duplication.
-static cl::opt<unsigned> TailDuplicatePlacementThreshold(
-    "tail-dup-placement-threshold",
-    cl::desc("Instruction cutoff for tail duplication during layout. "
-             "Tail merging during layout is forced to have a threshold "
-             "that won't conflict."), cl::init(2),
-    cl::Hidden);
-
 extern cl::opt<unsigned> StaticLikelyProb;
 extern cl::opt<unsigned> ProfileLikelyProb;
 
@@ -200,16 +185,6 @@ public:
   /// \brief End of blocks within the chain.
   iterator end() { return Blocks.end(); }
 
-  bool remove(MachineBasicBlock* BB) {
-    for(iterator i = begin(); i != end(); ++i) {
-      if (*i == BB) {
-        Blocks.erase(i);
-        return true;
-      }
-    }
-    return false;
-  }
-
   /// \brief Merge a block chain into this one.
   ///
   /// This routine merges a block chain into this one. It takes care of forming
@@ -291,13 +266,6 @@ class MachineBlockPlacement : public MachineFunctionPass {
   /// \brief A handle to the post dominator tree.
   MachineDominatorTree *MDT;
 
-  /// \brief Duplicator used to duplicate tails during placement.
-  ///
-  /// Placement decisions can open up new tail duplication opportunities, but
-  /// since tail duplication affects placement decisions of later blocks, it
-  /// must be done inline.
-  TailDuplicator TailDup;
-
   /// \brief A set of blocks that are unavoidably execute, i.e. they dominate
   /// all terminators of the MachineFunction.
   SmallPtrSet<MachineBasicBlock *, 4> UnavoidableBlocks;
@@ -319,18 +287,8 @@ class MachineBlockPlacement : public MachineFunctionPass {
   /// between basic blocks.
   DenseMap<MachineBasicBlock *, BlockChain *> BlockToChain;
 
-  /// Decrease the UnscheduledPredecessors count for all blocks in chain, and
-  /// if the count goes to 0, add them to the appropriate work list.
   void markChainSuccessors(BlockChain &Chain, MachineBasicBlock *LoopHeaderBB,
                            const BlockFilterSet *BlockFilter = nullptr);
-
-  /// Decrease the UnscheduledPredecessors count for a single block, and
-  /// if the count goes to 0, add them to the appropriate work list.
-  void markBlockSuccessors(
-      BlockChain &Chain, MachineBasicBlock *BB, MachineBasicBlock *LoopHeaderBB,
-      const BlockFilterSet *BlockFilter = nullptr);
-
-
   BranchProbability
   collectViableSuccessors(MachineBasicBlock *BB, BlockChain &Chain,
                           const BlockFilterSet *BlockFilter,
@@ -340,16 +298,6 @@ class MachineBlockPlacement : public MachineFunctionPass {
                                  const BlockFilterSet *BlockFilter,
                                  BranchProbability SuccProb,
                                  BranchProbability HotProb);
-  bool repeatedlyTailDuplicateBlock(
-      MachineBasicBlock *BB, MachineBasicBlock *&LPred,
-      MachineBasicBlock *LoopHeaderBB,
-      BlockChain &Chain, BlockFilterSet *BlockFilter,
-      MachineFunction::iterator &PrevUnplacedBlockIt);
-  bool maybeTailDuplicateBlock(MachineBasicBlock *BB, MachineBasicBlock *LPred,
-                               const BlockChain &Chain,
-                               BlockFilterSet *BlockFilter,
-                               MachineFunction::iterator &PrevUnplacedBlockIt,
-                               bool &DuplicatedToPred);
   bool
   hasBetterLayoutPredecessor(MachineBasicBlock *BB, MachineBasicBlock *Succ,
                              BlockChain &SuccChain, BranchProbability SuccProb,
@@ -375,7 +323,7 @@ class MachineBlockPlacement : public MachineFunctionPass {
                      SmallPtrSetImpl<BlockChain *> &UpdatedPreds,
                      const BlockFilterSet *BlockFilter);
   void buildChain(MachineBasicBlock *BB, BlockChain &Chain,
-                  BlockFilterSet *BlockFilter = nullptr);
+                  const BlockFilterSet *BlockFilter = nullptr);
   MachineBasicBlock *findBestLoopTop(MachineLoop &L,
                                      const BlockFilterSet &LoopBlockSet);
   MachineBasicBlock *findBestLoopExit(MachineLoop &L,
@@ -440,49 +388,37 @@ static std::string getBlockName(MachineBasicBlock *BB) {
 /// When a chain is being merged into the "placed" chain, this routine will
 /// quickly walk the successors of each block in the chain and mark them as
 /// having one fewer active predecessor. It also adds any successors of this
-/// chain which reach the zero-predecessor state to the appropriate worklist.
+/// chain which reach the zero-predecessor state to the worklist passed in.
 void MachineBlockPlacement::markChainSuccessors(
     BlockChain &Chain, MachineBasicBlock *LoopHeaderBB,
     const BlockFilterSet *BlockFilter) {
   // Walk all the blocks in this chain, marking their successors as having
   // a predecessor placed.
   for (MachineBasicBlock *MBB : Chain) {
-    markBlockSuccessors(Chain, MBB, LoopHeaderBB, BlockFilter);
-  }
-}
-
-/// \brief Mark a single block's successors as having one fewer preds.
-///
-/// Under normal circumstances, this is only called by markChainSuccessors,
-/// but if a block that was to be placed is completely tail-duplicated away,
-/// and was duplicated into the chain end, we need to redo markBlockSuccessors
-/// for just that block.
-void MachineBlockPlacement::markBlockSuccessors(
-    BlockChain &Chain, MachineBasicBlock *MBB, MachineBasicBlock *LoopHeaderBB,
-    const BlockFilterSet *BlockFilter) {
-  // Add any successors for which this is the only un-placed in-loop
-  // predecessor to the worklist as a viable candidate for CFG-neutral
-  // placement. No subsequent placement of this block will violate the CFG
-  // shape, so we get to use heuristics to choose a favorable placement.
-  for (MachineBasicBlock *Succ : MBB->successors()) {
-    if (BlockFilter && !BlockFilter->count(Succ))
-      continue;
-    BlockChain &SuccChain = *BlockToChain[Succ];
-    // Disregard edges within a fixed chain, or edges to the loop header.
-    if (&Chain == &SuccChain || Succ == LoopHeaderBB)
-      continue;
+    // Add any successors for which this is the only un-placed in-loop
+    // predecessor to the worklist as a viable candidate for CFG-neutral
+    // placement. No subsequent placement of this block will violate the CFG
+    // shape, so we get to use heuristics to choose a favorable placement.
+    for (MachineBasicBlock *Succ : MBB->successors()) {
+      if (BlockFilter && !BlockFilter->count(Succ))
+        continue;
+      BlockChain &SuccChain = *BlockToChain[Succ];
+      // Disregard edges within a fixed chain, or edges to the loop header.
+      if (&Chain == &SuccChain || Succ == LoopHeaderBB)
+        continue;
 
-    // This is a cross-chain edge that is within the loop, so decrement the
-    // loop predecessor count of the destination chain.
-    if (SuccChain.UnscheduledPredecessors == 0 ||
-        --SuccChain.UnscheduledPredecessors > 0)
-      continue;
+      // This is a cross-chain edge that is within the loop, so decrement the
+      // loop predecessor count of the destination chain.
+      if (SuccChain.UnscheduledPredecessors == 0 ||
+          --SuccChain.UnscheduledPredecessors > 0)
+        continue;
 
-    auto *NewBB = *SuccChain.begin();
-    if (NewBB->isEHPad())
-      EHPadWorkList.push_back(NewBB);
-    else
-      BlockWorkList.push_back(NewBB);
+      auto *MBB = *SuccChain.begin();
+      if (MBB->isEHPad())
+        EHPadWorkList.push_back(MBB);
+      else
+        BlockWorkList.push_back(MBB);
+    }
   }
 }
 
@@ -966,7 +902,7 @@ void MachineBlockPlacement::fillWorkLists(
 
 void MachineBlockPlacement::buildChain(
     MachineBasicBlock *BB, BlockChain &Chain,
-    BlockFilterSet *BlockFilter) {
+    const BlockFilterSet *BlockFilter) {
   assert(BB && "BB must not be null.\n");
   assert(BlockToChain[BB] == &Chain && "BlockToChainMap mis-match.\n");
   MachineFunction::iterator PrevUnplacedBlockIt = F->begin();
@@ -1001,17 +937,6 @@ void MachineBlockPlacement::buildChain(
                       "layout successor until the CFG reduces\n");
     }
 
-    // Placement may have changed tail duplication opportunities.
-    // Check for that now.
-    if (TailDupPlacement && BestSucc) {
-      // If the chosen successor was duplicated into all its predecessors,
-      // don't bother laying it out, just go round the loop again with BB as
-      // the chain end.
-      if (repeatedlyTailDuplicateBlock(BestSucc, BB, LoopHeaderBB, Chain,
-                                       BlockFilter, PrevUnplacedBlockIt))
-        continue;
-    }
-
     // Place this block, updating the datastructures to reflect its placement.
     BlockChain &SuccChain = *BlockToChain[BestSucc];
     // Zero out UnscheduledPredecessors for the successor we're about to merge in case
@@ -1793,175 +1718,6 @@ void MachineBlockPlacement::alignBlocks() {
   }
 }
 
-/// Tail duplicate \p BB into (some) predecessors if profitable, repeating if
-/// it was duplicated into its chain predecessor and removed.
-/// \p BB    - Basic block that may be duplicated.
-///
-/// \p LPred - Chosen layout predecessor of \p BB.
-///            Updated to be the chain end if LPred is removed.
-/// \p Chain - Chain to which \p LPred belongs, and \p BB will belong.
-/// \p BlockFilter - Set of blocks that belong to the loop being laid out.
-///                  Used to identify which blocks to update predecessor
-///                  counts.
-/// \p PrevUnplacedBlockIt - Iterator pointing to the last block that was
-///                          chosen in the given order due to unnatural CFG
-///                          only needed if \p BB is removed and
-///                          \p PrevUnplacedBlockIt pointed to \p BB.
-/// @return true if \p BB was removed.
-bool MachineBlockPlacement::repeatedlyTailDuplicateBlock(
-    MachineBasicBlock *BB, MachineBasicBlock *&LPred,
-    MachineBasicBlock *LoopHeaderBB,
-    BlockChain &Chain, BlockFilterSet *BlockFilter,
-    MachineFunction::iterator &PrevUnplacedBlockIt) {
-  bool Removed, DuplicatedToLPred;
-  bool DuplicatedToOriginalLPred;
-  Removed = maybeTailDuplicateBlock(BB, LPred, Chain, BlockFilter,
-                                    PrevUnplacedBlockIt,
-                                    DuplicatedToLPred);
-  if (!Removed)
-    return false;
-  DuplicatedToOriginalLPred = DuplicatedToLPred;
-  // Iteratively try to duplicate again. It can happen that a block that is
-  // duplicated into is still small enough to be duplicated again.
-  // No need to call markBlockSuccessors in this case, as the blocks being
-  // duplicated from here on are already scheduled.
-  // Note that DuplicatedToLPred always implies Removed.
-  while (DuplicatedToLPred) {
-    assert (Removed && "Block must have been removed to be duplicated into its "
-            "layout predecessor.");
-    MachineBasicBlock *DupBB, *DupPred;
-    // The removal callback causes Chain.end() to be updated when a block is
-    // removed. On the first pass through the loop, the chain end should be the
-    // same as it was on function entry. On subsequent passes, because we are
-    // duplicating the block at the end of the chain, if it is removed the
-    // chain will have shrunk by one block.
-    BlockChain::iterator ChainEnd = Chain.end();
-    DupBB = *(--ChainEnd);
-    // Now try to duplicate again.
-    if (ChainEnd == Chain.begin())
-      break;
-    DupPred = *std::prev(ChainEnd);
-    Removed = maybeTailDuplicateBlock(DupBB, DupPred, Chain, BlockFilter,
-                                      PrevUnplacedBlockIt,
-                                      DuplicatedToLPred);
-  }
-  // If BB was duplicated into LPred, it is now scheduled. But because it was
-  // removed, markChainSuccessors won't be called for its chain. Instead we
-  // call markBlockSuccessors for LPred to achieve the same effect. This must go
-  // at the end because repeating the tail duplication can increase the number
-  // of unscheduled predecessors.
-  if (DuplicatedToOriginalLPred)
-    markBlockSuccessors(Chain, LPred, LoopHeaderBB, BlockFilter);
-
-  LPred = *std::prev(Chain.end());
-  return true;
-}
-
-/// Tail duplicate \p BB into (some) predecessors if profitable.
-/// \p BB    - Basic block that may be duplicated
-/// \p LPred - Chosen layout predecessor of \p BB
-/// \p Chain - Chain to which \p LPred belongs, and \p BB will belong.
-/// \p BlockFilter - Set of blocks that belong to the loop being laid out.
-///                  Used to identify which blocks to update predecessor
-///                  counts.
-/// \p PrevUnplacedBlockIt - Iterator pointing to the last block that was
-///                          chosen in the given order due to unnatural CFG
-///                          only needed if \p BB is removed and
-///                          \p PrevUnplacedBlockIt pointed to \p BB.
-/// \p DuplicatedToLPred - True if the block was duplicated into LPred. Will
-///                        only be true if the block was removed.
-/// \return  - True if the block was duplicated into all preds and removed.
-bool MachineBlockPlacement::maybeTailDuplicateBlock(
-    MachineBasicBlock *BB, MachineBasicBlock *LPred,
-    const BlockChain &Chain, BlockFilterSet *BlockFilter,
-    MachineFunction::iterator &PrevUnplacedBlockIt,
-    bool &DuplicatedToLPred) {
-
-  DuplicatedToLPred = false;
-  DEBUG(dbgs() << "Redoing tail duplication for Succ#"
-        << BB->getNumber() << "\n");
-  bool IsSimple = TailDup.isSimpleBB(BB);
-  // Blocks with single successors don't create additional fallthrough
-  // opportunities. Don't duplicate them. TODO: When conditional exits are
-  // analyzable, allow them to be duplicated.
-  if (!IsSimple && BB->succ_size() == 1)
-    return false;
-  if (!TailDup.shouldTailDuplicate(IsSimple, *BB))
-    return false;
-  // This has to be a callback because none of it can be done after
-  // BB is deleted.
-  bool Removed = false;
-  auto RemovalCallback =
-      [&](MachineBasicBlock *RemBB) {
-        // Signal to outer function
-        Removed = true;
-
-        // Conservative default.
-        bool InWorkList = true;
-        // Remove from the Chain and Chain Map
-        if (BlockToChain.count(RemBB)) {
-          BlockChain *Chain = BlockToChain[RemBB];
-          InWorkList = Chain->UnscheduledPredecessors == 0;
-          Chain->remove(RemBB);
-          BlockToChain.erase(RemBB);
-        }
-
-        // Handle the unplaced block iterator
-        if (&(*PrevUnplacedBlockIt) == RemBB) {
-          PrevUnplacedBlockIt++;
-        }
-
-        // Handle the Work Lists
-        if (InWorkList) {
-          SmallVectorImpl<MachineBasicBlock *> &RemoveList = BlockWorkList;
-          if (RemBB->isEHPad())
-            RemoveList = EHPadWorkList;
-          RemoveList.erase(
-              remove_if(RemoveList,
-                        [RemBB](MachineBasicBlock *BB) {return BB == RemBB;}),
-              RemoveList.end());
-        }
-
-        // Handle the filter set
-        if (BlockFilter) {
-          BlockFilter->erase(RemBB);
-        }
-
-        // Remove the block from loop info.
-        MLI->removeBlock(RemBB);
-
-        // TailDuplicator handles removing it from loops.
-        DEBUG(dbgs() << "TailDuplicator deleted block: "
-              << getBlockName(RemBB) << "\n");
-      };
-  auto RemovalCallbackRef =
-      llvm::function_ref<void(MachineBasicBlock*)>(RemovalCallback);
-
-  SmallVector<MachineBasicBlock *, 8> DuplicatedPreds;
-  TailDup.tailDuplicateAndUpdate(IsSimple, BB, LPred,
-                                 &DuplicatedPreds, &RemovalCallbackRef);
-
-  // Update UnscheduledPredecessors to reflect tail-duplication.
-  DuplicatedToLPred = false;
-  for (MachineBasicBlock *Pred : DuplicatedPreds) {
-    // We're only looking for unscheduled predecessors that match the filter.
-    BlockChain* PredChain = BlockToChain[Pred];
-    if (Pred == LPred)
-      DuplicatedToLPred = true;
-    if (Pred == LPred || (BlockFilter && !BlockFilter->count(Pred))
-        || PredChain == &Chain)
-      continue;
-    for (MachineBasicBlock *NewSucc : Pred->successors()) {
-      if (BlockFilter && !BlockFilter->count(NewSucc))
-        continue;
-      BlockChain *NewChain = BlockToChain[NewSucc];
-      if (NewChain != &Chain && NewChain != PredChain)
-        NewChain->UnscheduledPredecessors++;
-    }
-  }
-  return Removed;
-}
-
 bool MachineBlockPlacement::runOnMachineFunction(MachineFunction &MF) {
   if (skipFunction(*MF.getFunction()))
     return false;
@@ -1978,13 +1734,6 @@ bool MachineBlockPlacement::runOnMachineFunction(MachineFunction &MF) {
   TII = MF.getSubtarget().getInstrInfo();
   TLI = MF.getSubtarget().getTargetLowering();
   MDT = &getAnalysis<MachineDominatorTree>();
-  if (TailDupPlacement) {
-    unsigned TailDupSize = TailDuplicatePlacementThreshold;
-    if (MF.getFunction()->optForSize())
-      TailDupSize = 1;
-    TailDup.initMF(MF, MBPI, /* LayoutMode */ true, TailDupSize);
-  }
-
   assert(BlockToChain.empty());
 
   buildCFGChains();
@@ -1998,7 +1747,8 @@ bool MachineBlockPlacement::runOnMachineFunction(MachineFunction &MF) {
                          BranchFoldPlacement;
   // No tail merging opportunities if the block number is less than four.
   if (MF.size() > 3 && EnableTailMerge) {
-    unsigned TailMergeSize = TailDuplicatePlacementThreshold + 1;
+    // Default to the standard tail-merge-size option.
+    unsigned TailMergeSize = 0;
     BranchFolder BF(/*EnableTailMerge=*/true, /*CommonHoist=*/false, *MBFI,
                     *MBPI, TailMergeSize);
 
@@ -2007,8 +1757,6 @@ bool MachineBlockPlacement::runOnMachineFunction(MachineFunction &MF) {
                             /*AfterBlockPlacement=*/true)) {
       // Redo the layout if tail merging creates/removes/moves blocks.
       BlockToChain.clear();
-      // Must redo the dominator tree if blocks were changed.
-      MDT->runOnMachineFunction(MF);
       ChainAllocator.DestroyAll();
       buildCFGChains();
     }
diff --git a/llvm/lib/CodeGen/TailDuplication.cpp b/llvm/lib/CodeGen/TailDuplication.cpp
index e2377d89497..6e8ee9e2634 100644
--- a/llvm/lib/CodeGen/TailDuplication.cpp
+++ b/llvm/lib/CodeGen/TailDuplication.cpp
@@ -49,7 +49,7 @@ bool TailDuplicatePass::runOnMachineFunction(MachineFunction &MF) {
 
   auto MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
 
-  Duplicator.initMF(MF, MBPI, /* LayoutMode */ false);
+  Duplicator.initMF(MF, MBPI);
 
   bool MadeChange = false;
   while (Duplicator.tailDuplicateBlocks())
diff --git a/llvm/lib/CodeGen/TailDuplicator.cpp b/llvm/lib/CodeGen/TailDuplicator.cpp
index 5b93b88405e..26b9b074ede 100644
--- a/llvm/lib/CodeGen/TailDuplicator.cpp
+++ b/llvm/lib/CodeGen/TailDuplicator.cpp
@@ -20,7 +20,6 @@
 #include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/IR/Function.h"
@@ -65,7 +64,7 @@ static cl::opt<unsigned> TailDupLimit("tail-dup-limit", cl::init(~0U),
 
 void TailDuplicator::initMF(MachineFunction &MFin,
                             const MachineBranchProbabilityInfo *MBPIin,
-                            bool LayoutModeIn, unsigned TailDupSizeIn) {
+                            unsigned TailDupSizeIn) {
   MF = &MFin;
   TII = MF->getSubtarget().getInstrInfo();
   TRI = MF->getSubtarget().getRegisterInfo();
@@ -76,7 +75,6 @@ void TailDuplicator::initMF(MachineFunction &MFin,
 
   assert(MBPI != nullptr && "Machine Branch Probability Info required");
 
-  LayoutMode = LayoutModeIn;
   PreRegAlloc = MRI->isSSA();
 }
 
@@ -129,23 +127,18 @@ static void VerifyPHIs(MachineFunction &MF, bool CheckExtra) {
 /// Tail duplicate the block and cleanup.
 /// \p IsSimple - return value of isSimpleBB
 /// \p MBB - block to be duplicated
-/// \p ForcedLayoutPred - If non-null, treat this block as the layout
-///     predecessor, instead of using the ordering in MF
 /// \p DuplicatedPreds - if non-null, \p DuplicatedPreds will contain a list of
 ///     all Preds that received a copy of \p MBB.
-/// \p RemovalCallback - if non-null, called just before MBB is deleted.
 bool TailDuplicator::tailDuplicateAndUpdate(
     bool IsSimple, MachineBasicBlock *MBB,
-    MachineBasicBlock *ForcedLayoutPred,
-    SmallVectorImpl<MachineBasicBlock*> *DuplicatedPreds,
-    llvm::function_ref<void(MachineBasicBlock *)> *RemovalCallback) {
+    SmallVectorImpl<MachineBasicBlock*> *DuplicatedPreds) {
   // Save the successors list.
   SmallSetVector<MachineBasicBlock *, 8> Succs(MBB->succ_begin(),
                                                MBB->succ_end());
 
   SmallVector<MachineBasicBlock *, 8> TDBBs;
   SmallVector<MachineInstr *, 16> Copies;
-  if (!tailDuplicate(IsSimple, MBB, ForcedLayoutPred, TDBBs, Copies))
+  if (!tailDuplicate(IsSimple, MBB, TDBBs, Copies))
     return false;
 
   ++NumTails;
@@ -163,7 +156,7 @@ bool TailDuplicator::tailDuplicateAndUpdate(
   // If it is dead, remove it.
   if (isDead) {
     NumTailDupRemoved += MBB->size();
-    removeDeadBlock(MBB, RemovalCallback);
+    removeDeadBlock(MBB);
     ++NumDeadBlocks;
   }
 
@@ -262,7 +255,7 @@ bool TailDuplicator::tailDuplicateBlocks() {
     if (!shouldTailDuplicate(IsSimple, *MBB))
       continue;
 
-    MadeChange |= tailDuplicateAndUpdate(IsSimple, MBB, nullptr);
+    MadeChange |= tailDuplicateAndUpdate(IsSimple, MBB);
   }
 
   if (PreRegAlloc && TailDupVerify)
@@ -521,10 +514,8 @@ void TailDuplicator::updateSuccessorsPHIs(
 /// Determine if it is profitable to duplicate this block.
 bool TailDuplicator::shouldTailDuplicate(bool IsSimple,
                                          MachineBasicBlock &TailBB) {
-  // When doing tail-duplication during layout, the block ordering is in flux,
-  // so canFallThrough returns a result based on incorrect information and
-  // should just be ignored.
-  if (!LayoutMode && TailBB.canFallThrough())
+  // Only duplicate blocks that end with unconditional branches.
+  if (TailBB.canFallThrough())
     return false;
 
   // Don't try to tail-duplicate single-block loops.
@@ -744,7 +735,7 @@ bool TailDuplicator::duplicateSimpleBB(
 
 bool TailDuplicator::canTailDuplicate(MachineBasicBlock *TailBB,
                                       MachineBasicBlock *PredBB) {
-  // EH edges are ignored by analyzeBranch.
+  // EH edges are ignored by AnalyzeBranch.
   if (PredBB->succ_size() > 1)
     return false;
 
@@ -759,16 +750,7 @@ bool TailDuplicator::canTailDuplicate(MachineBasicBlock *TailBB,
 
 /// If it is profitable, duplicate TailBB's contents in each
 /// of its predecessors.
-/// \p IsSimple result of isSimpleBB
-/// \p TailBB   Block to be duplicated.
-/// \p ForcedLayoutPred  When non-null, use this block as the layout predecessor
-///                      instead of the previous block in MF's order.
-/// \p TDBBs             A vector to keep track of all blocks tail-duplicated
-///                      into.
-/// \p Copies            A vector of copy instructions inserted. Used later to
-///                      walk all the inserted copies and remove redundant ones.
 bool TailDuplicator::tailDuplicate(bool IsSimple, MachineBasicBlock *TailBB,
-                                   MachineBasicBlock *ForcedLayoutPred,
                                    SmallVectorImpl<MachineBasicBlock *> &TDBBs,
                                    SmallVectorImpl<MachineInstr *> &Copies) {
   DEBUG(dbgs() << "\n*** Tail-duplicating BB#" << TailBB->getNumber() << '\n');
@@ -793,12 +775,7 @@ bool TailDuplicator::tailDuplicate(bool IsSimple, MachineBasicBlock *TailBB,
       continue;
 
     // Don't duplicate into a fall-through predecessor (at least for now).
-    bool IsLayoutSuccessor = false;
-    if (ForcedLayoutPred)
-      IsLayoutSuccessor = (ForcedLayoutPred == PredBB);
-    else if (PredBB->isLayoutSuccessor(TailBB) && PredBB->canFallThrough())
-      IsLayoutSuccessor = true;
-    if (IsLayoutSuccessor)
+    if (PredBB->isLayoutSuccessor(TailBB) && PredBB->canFallThrough())
       continue;
 
     DEBUG(dbgs() << "\nTail-duplicating into PredBB: " << *PredBB
@@ -851,20 +828,16 @@ bool TailDuplicator::tailDuplicate(bool IsSimple, MachineBasicBlock *TailBB,
   // If TailBB was duplicated into all its predecessors except for the prior
   // block, which falls through unconditionally, move the contents of this
   // block into the prior block.
-  MachineBasicBlock *PrevBB = ForcedLayoutPred;
-  if (!PrevBB)
-    PrevBB = &*std::prev(TailBB->getIterator());
+  MachineBasicBlock *PrevBB = &*std::prev(TailBB->getIterator());
   MachineBasicBlock *PriorTBB = nullptr, *PriorFBB = nullptr;
   SmallVector<MachineOperand, 4> PriorCond;
   // This has to check PrevBB->succ_size() because EH edges are ignored by
-  // analyzeBranch.
+  // AnalyzeBranch.
   if (PrevBB->succ_size() == 1 &&
       // Layout preds are not always CFG preds. Check.
       *PrevBB->succ_begin() == TailBB &&
       !TII->analyzeBranch(*PrevBB, PriorTBB, PriorFBB, PriorCond, true) &&
-      PriorCond.empty() &&
-      (!PriorTBB || PriorTBB == TailBB) &&
-      TailBB->pred_size() == 1 &&
+      PriorCond.empty() && !PriorTBB && TailBB->pred_size() == 1 &&
       !TailBB->hasAddressTaken()) {
     DEBUG(dbgs() << "\nMerging into block: " << *PrevBB
                  << "From MBB: " << *TailBB);
@@ -891,7 +864,6 @@ bool TailDuplicator::tailDuplicate(bool IsSimple, MachineBasicBlock *TailBB,
       }
       appendCopies(PrevBB, CopyInfos, Copies);
     } else {
-      TII->removeBranch(*PrevBB);
       // No PHIs to worry about, just splice the instructions over.
       PrevBB->splice(PrevBB->end(), TailBB, TailBB->begin(), TailBB->end());
     }
@@ -964,15 +936,10 @@ void TailDuplicator::appendCopies(MachineBasicBlock *MBB,
 
 /// Remove the specified dead machine basic block from the function, updating
 /// the CFG.
-void TailDuplicator::removeDeadBlock(
-    MachineBasicBlock *MBB,
-    llvm::function_ref<void(MachineBasicBlock *)> *RemovalCallback) {
+void TailDuplicator::removeDeadBlock(MachineBasicBlock *MBB) {
   assert(MBB->pred_empty() && "MBB must be dead!");
   DEBUG(dbgs() << "\nRemoving MBB: " << *MBB);
 
-  if (RemovalCallback)
-    (*RemovalCallback)(MBB);
-
   // Remove all successors.
   while (!MBB->succ_empty())
     MBB->removeSuccessor(MBB->succ_end() - 1);