Index: lib/CodeGen/BranchFolding.h
===================================================================
--- lib/CodeGen/BranchFolding.h
+++ lib/CodeGen/BranchFolding.h
@@ -33,10 +33,12 @@
                           MBFIWrapper &MBFI,
                           const MachineBranchProbabilityInfo &MBPI);
 
-    bool OptimizeFunction(MachineFunction &MF, const TargetInstrInfo *tii,
-                          const TargetRegisterInfo *tri, MachineModuleInfo *mmi,
-                          MachineLoopInfo *mli = nullptr,
-                          bool AfterPlacement = false);
+    bool OptimizeFunction(
+        MachineFunction &MF, const TargetInstrInfo *tii,
+        const TargetRegisterInfo *tri, MachineModuleInfo *mmi,
+        MachineLoopInfo *mli = nullptr,
+        SmallPtrSet<MachineBasicBlock *, 4> *unavoidables = nullptr,
+        bool AfterPlacement = false);
 
   private:
     class MergePotentialsElt {
@@ -102,6 +104,7 @@
     const TargetRegisterInfo *TRI;
     MachineModuleInfo *MMI;
     MachineLoopInfo *MLI;
+    SmallPtrSet<MachineBasicBlock *, 4> *UnavoidableBlocks;
     RegScavenger *RS;
 
   public:
Index: lib/CodeGen/BranchFolding.cpp
===================================================================
--- lib/CodeGen/BranchFolding.cpp
+++ lib/CodeGen/BranchFolding.cpp
@@ -140,6 +140,8 @@
   FuncletMembership.erase(MBB);
   if (MLI)
     MLI->removeBlock(MBB);
+  if (UnavoidableBlocks)
+    UnavoidableBlocks->erase(MBB);
 }
 
 /// OptimizeImpDefsBlock - If a basic block is just a bunch of implicit_def
@@ -198,11 +200,10 @@
 /// OptimizeFunction - Perhaps branch folding, tail merging and other
 /// CFG optimizations on the given function.  Block placement changes the layout
 /// and may create new tail merging opportunities.
-bool BranchFolder::OptimizeFunction(MachineFunction &MF,
-                                    const TargetInstrInfo *tii,
-                                    const TargetRegisterInfo *tri,
-                                    MachineModuleInfo *mmi,
-                                    MachineLoopInfo *mli, bool AfterPlacement) {
+bool BranchFolder::OptimizeFunction(
+    MachineFunction &MF, const TargetInstrInfo *tii,
+    const TargetRegisterInfo *tri, MachineModuleInfo *mmi, MachineLoopInfo *mli,
+    SmallPtrSet<MachineBasicBlock *, 4> *unavoidables, bool AfterPlacement) {
   if (!tii) return false;
 
   TriedMerging.clear();
@@ -212,6 +213,7 @@
   TRI = tri;
   MMI = mmi;
   MLI = mli;
+  UnavoidableBlocks = unavoidables;
   RS = nullptr;
 
   // Use a RegScavenger to help update liveness when required.
@@ -462,6 +464,9 @@
     if (MachineLoop *ML = MLI->getLoopFor(&CurMBB))
       ML->addBasicBlockToLoop(NewMBB, MLI->getBase());
 
+  if (UnavoidableBlocks)
+    UnavoidableBlocks->insert(NewMBB);
+
   // NewMBB inherits CurMBB's block frequency.
   MBBFreqInfo.setBlockFreq(NewMBB, MBBFreqInfo.getBlockFreq(&CurMBB));
 
Index: lib/CodeGen/MachineBlockPlacement.cpp
===================================================================
--- lib/CodeGen/MachineBlockPlacement.cpp
+++ lib/CodeGen/MachineBlockPlacement.cpp
@@ -262,6 +262,9 @@
   /// all terminators of the MachineFunction.
   SmallPtrSet<MachineBasicBlock *, 4> UnavoidableBlocks;
 
+  /// \brief A flag to show if UnavoidableBlocks is calculated.
+  bool HasUnavoidableBlocks;
+
   /// \brief Allocator and owner of BlockChain structures.
   ///
   /// We build BlockChains lazily while processing the loop structure of
@@ -1389,7 +1392,7 @@
 /// When OutlineOpitonalBranches is on, this method colects BBs that
 /// dominates all terminator blocks of the function \p F.
 void MachineBlockPlacement::collectMustExecuteBBs() {
-  if (OutlineOptionalBranches) {
+  if (OutlineOptionalBranches && !HasUnavoidableBlocks) {
     // Find the nearest common dominator of all of F's terminators.
     MachineBasicBlock *Terminator = nullptr;
     for (MachineBasicBlock &MBB : *F) {
@@ -1408,6 +1411,7 @@
         UnavoidableBlocks.insert(&MBB);
       }
     }
+    HasUnavoidableBlocks = true;
   }
 }
 
@@ -1657,6 +1661,7 @@
   TII = MF.getSubtarget().getInstrInfo();
   TLI = MF.getSubtarget().getTargetLowering();
   MDT = &getAnalysis<MachineDominatorTree>();
+  HasUnavoidableBlocks = false;
   assert(BlockToChain.empty());
 
   buildCFGChains();
@@ -1673,9 +1678,11 @@
     BranchFolder BF(/*EnableTailMerge=*/true, /*CommonHoist=*/false, *MBFI,
                     *MBPI);
 
-    if (BF.OptimizeFunction(MF, TII, MF.getSubtarget().getRegisterInfo(),
-                            getAnalysisIfAvailable<MachineModuleInfo>(), MLI,
-                            /*AfterBlockPlacement=*/true)) {
+    if (BF.OptimizeFunction(
+            MF, TII, MF.getSubtarget().getRegisterInfo(),
+            getAnalysisIfAvailable<MachineModuleInfo>(), MLI,
+            (OutlineOptionalBranches ? &UnavoidableBlocks : nullptr),
+            /*AfterBlockPlacement=*/true)) {
       // Redo the layout if tail merging creates/removes/moves blocks.
       BlockToChain.clear();
       ChainAllocator.DestroyAll();
Index: test/CodeGen/AArch64/tailmerging_in_mbp.ll
===================================================================
--- test/CodeGen/AArch64/tailmerging_in_mbp.ll
+++ test/CodeGen/AArch64/tailmerging_in_mbp.ll
@@ -1,4 +1,5 @@
-; RUN: llc <%s -march=aarch64 | FileCheck %s
+; RUN: llc < %s -march=aarch64 | FileCheck %s
+; RUN: llc < %s -march=aarch64 -outline-optional-branches | FileCheck %s --check-prefix=OUTLINE
 
 ; CHECK-LABEL: test:
 ; CHECK:       LBB0_7:
@@ -61,3 +62,14 @@
   %j.4 = add i64 %j.3, 10
   ret i64 %j.4 
 }
+; OUTLINE-LABEL: test:
+; OUTLINE:       entry
+; OUTLINE:       for.end
+; OUTLINE:       for.body.preheader
+; OUTLINE:       cond.false.i
+; OUTLINE:       cond.false6.i
+; OUTLINE:       cond.false11.i
+; OUTLINE:       cond.false12.i
+; OUTLINE:       if.end
+; OUTLINE:       LBB0_9:
+