diff --git a/llvm/include/llvm/CodeGen/AsmPrinter.h b/llvm/include/llvm/CodeGen/AsmPrinter.h
--- a/llvm/include/llvm/CodeGen/AsmPrinter.h
+++ b/llvm/include/llvm/CodeGen/AsmPrinter.h
@@ -48,6 +48,7 @@
 class GlobalValue;
 class GlobalVariable;
 class MachineBasicBlock;
+class MachineBlockFrequencyInfo;
 class MachineConstantPoolValue;
 class MachineDominatorTree;
 class MachineFunction;
@@ -69,6 +70,7 @@
 class MCTargetOptions;
 class MDNode;
 class Module;
+class ProfileSummaryInfo;
 class raw_ostream;
 class RemarkStreamer;
 class StackMaps;
@@ -108,6 +110,10 @@
   /// Optimization remark emitter.
   MachineOptimizationRemarkEmitter *ORE;
 
+  MachineBlockFrequencyInfo *MBFI;
+
+  ProfileSummaryInfo *PSI;
+
   /// The symbol for the current function. This is recalculated at the beginning
   /// of each call to runOnMachineFunction().
   MCSymbol *CurrentFnSym = nullptr;
diff --git a/llvm/include/llvm/CodeGen/MachineOptimizationRemarkEmitter.h b/llvm/include/llvm/CodeGen/MachineOptimizationRemarkEmitter.h
--- a/llvm/include/llvm/CodeGen/MachineOptimizationRemarkEmitter.h
+++ b/llvm/include/llvm/CodeGen/MachineOptimizationRemarkEmitter.h
@@ -182,6 +182,10 @@
     }
   }
 
+  MachineBlockFrequencyInfo *getBFI() {
+    return MBFI;
+  }
+
 private:
   MachineFunction &MF;
 
diff --git a/llvm/include/llvm/CodeGen/TailDuplicator.h b/llvm/include/llvm/CodeGen/TailDuplicator.h
--- a/llvm/include/llvm/CodeGen/TailDuplicator.h
+++ b/llvm/include/llvm/CodeGen/TailDuplicator.h
@@ -25,11 +25,13 @@
 namespace llvm {
 
 class MachineBasicBlock;
+class MachineBlockFrequencyInfo;
 class MachineBranchProbabilityInfo;
 class MachineFunction;
 class MachineInstr;
 class MachineModuleInfo;
 class MachineRegisterInfo;
+class ProfileSummaryInfo;
 class TargetRegisterInfo;
 
 /// Utility class to perform tail duplication.
@@ -40,6 +42,8 @@
   const MachineModuleInfo *MMI;
   MachineRegisterInfo *MRI;
   MachineFunction *MF;
+  const MachineBlockFrequencyInfo *MBFI;
+  ProfileSummaryInfo *PSI;
   bool PreRegAlloc;
   bool LayoutMode;
   unsigned TailDupSize;
@@ -65,6 +69,8 @@
   ///     default implies using the command line value TailDupSize.
   void initMF(MachineFunction &MF, bool PreRegAlloc,
               const MachineBranchProbabilityInfo *MBPI,
+              const MachineBlockFrequencyInfo *MBFI,
+              ProfileSummaryInfo *PSI,
               bool LayoutMode, unsigned TailDupSize = 0);
 
   bool tailDuplicateBlocks();
diff --git a/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp b/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
--- a/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
@@ -31,13 +31,16 @@
 #include "llvm/Analysis/ConstantFolding.h"
 #include "llvm/Analysis/EHPersonalities.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/BinaryFormat/COFF.h"
 #include "llvm/BinaryFormat/Dwarf.h"
 #include "llvm/BinaryFormat/ELF.h"
 #include "llvm/CodeGen/GCMetadata.h"
 #include "llvm/CodeGen/GCMetadataPrinter.h"
 #include "llvm/CodeGen/GCStrategy.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
+#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineConstantPool.h"
 #include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
@@ -52,6 +55,7 @@
 #include "llvm/CodeGen/MachineModuleInfoImpls.h"
 #include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachineOptimizationRemarkEmitter.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/StackMaps.h"
 #include "llvm/CodeGen/TargetFrameLowering.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
@@ -248,6 +252,8 @@
   AU.addRequired<MachineModuleInfoWrapperPass>();
   AU.addRequired<MachineOptimizationRemarkEmitterPass>();
   AU.addRequired<GCModuleInfo>();
+  AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
+  AU.addRequired<ProfileSummaryInfoWrapperPass>();
 }
 
 bool AsmPrinter::doInitialization(Module &M) {
@@ -1684,6 +1690,13 @@
   }
 
   ORE = &getAnalysis<MachineOptimizationRemarkEmitterPass>().getORE();
+  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  MBFI = (PSI && PSI->hasProfileSummary()) ?
+         // ORE conditionally computes MBFI. If available, use it, otherwise
+         // request it.
+         (ORE->getBFI() ? ORE->getBFI() :
+          &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI()) :
+         nullptr;
 }
 
 namespace {
@@ -2913,8 +2926,10 @@
 void AsmPrinter::setupCodePaddingContext(const MachineBasicBlock &MBB,
                                          MCCodePaddingContext &Context) const {
   assert(MF != nullptr && "Machine function must be valid");
+  bool OptForSize = MF->getFunction().hasOptSize() ||
+                    llvm::shouldOptimizeForSize(&MBB, PSI, MBFI);
   Context.IsPaddingActive = !MF->hasInlineAsm() &&
-                            !MF->getFunction().hasOptSize() &&
+                            !OptForSize &&
                             TM.getOptLevel() != CodeGenOpt::None;
   Context.IsBasicBlockReachableViaFallthrough =
       std::find(MBB.pred_begin(), MBB.pred_end(), MBB.getPrevNode()) !=
diff --git a/llvm/lib/CodeGen/BranchFolding.h b/llvm/lib/CodeGen/BranchFolding.h
--- a/llvm/lib/CodeGen/BranchFolding.h
+++ b/llvm/lib/CodeGen/BranchFolding.h
@@ -27,6 +27,7 @@
 class MachineLoopInfo;
 class MachineModuleInfo;
 class MachineRegisterInfo;
+class ProfileSummaryInfo;
 class raw_ostream;
 class TargetInstrInfo;
 class TargetRegisterInfo;
@@ -39,6 +40,7 @@
                           bool CommonHoist,
                           MBFIWrapper &FreqInfo,
                           const MachineBranchProbabilityInfo &ProbInfo,
+                          ProfileSummaryInfo *PSI,
                           // Min tail length to merge. Defaults to commandline
                           // flag. Ignored for optsize.
                           unsigned MinTailLength = 0);
@@ -145,6 +147,7 @@
                                   const BlockFrequency Freq) const;
       void view(const Twine &Name, bool isSimple = true);
       uint64_t getEntryFreq() const;
+      const MachineBlockFrequencyInfo &getMBFI() { return MBFI; }
 
     private:
       const MachineBlockFrequencyInfo &MBFI;
@@ -154,6 +157,7 @@
   private:
     MBFIWrapper &MBBFreqInfo;
     const MachineBranchProbabilityInfo &MBPI;
+    ProfileSummaryInfo *PSI;
 
     bool TailMergeBlocks(MachineFunction &MF);
     bool TryTailMergeBlocks(MachineBasicBlock* SuccBB,
diff --git a/llvm/lib/CodeGen/BranchFolding.cpp b/llvm/lib/CodeGen/BranchFolding.cpp
--- a/llvm/lib/CodeGen/BranchFolding.cpp
+++ b/llvm/lib/CodeGen/BranchFolding.cpp
@@ -24,6 +24,7 @@
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/CodeGen/Analysis.h"
 #include "llvm/CodeGen/LivePhysRegs.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
@@ -38,6 +39,7 @@
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/CodeGen/TargetOpcodes.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
@@ -103,6 +105,7 @@
     void getAnalysisUsage(AnalysisUsage &AU) const override {
       AU.addRequired<MachineBlockFrequencyInfo>();
       AU.addRequired<MachineBranchProbabilityInfo>();
+      AU.addRequired<ProfileSummaryInfoWrapperPass>();
       AU.addRequired<TargetPassConfig>();
       MachineFunctionPass::getAnalysisUsage(AU);
     }
@@ -129,7 +132,8 @@
   BranchFolder::MBFIWrapper MBBFreqInfo(
       getAnalysis<MachineBlockFrequencyInfo>());
   BranchFolder Folder(EnableTailMerge, /*CommonHoist=*/true, MBBFreqInfo,
-                      getAnalysis<MachineBranchProbabilityInfo>());
+                      getAnalysis<MachineBranchProbabilityInfo>(),
+                      &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI());
   auto *MMIWP = getAnalysisIfAvailable<MachineModuleInfoWrapperPass>();
   return Folder.OptimizeFunction(
       MF, MF.getSubtarget().getInstrInfo(), MF.getSubtarget().getRegisterInfo(),
@@ -139,9 +143,10 @@
 BranchFolder::BranchFolder(bool defaultEnableTailMerge, bool CommonHoist,
                            MBFIWrapper &FreqInfo,
                            const MachineBranchProbabilityInfo &ProbInfo,
+                           ProfileSummaryInfo *PSI,
                            unsigned MinTailLength)
     : EnableHoistCommonCode(CommonHoist), MinCommonTailLength(MinTailLength),
-      MBBFreqInfo(FreqInfo), MBPI(ProbInfo) {
+      MBBFreqInfo(FreqInfo), MBPI(ProbInfo), PSI(PSI) {
   if (MinCommonTailLength == 0)
     MinCommonTailLength = TailMergeSize;
   switch (FlagEnableTailMerge) {
@@ -585,7 +590,9 @@
                   MachineBasicBlock::iterator &I2, MachineBasicBlock *SuccBB,
                   MachineBasicBlock *PredBB,
                   DenseMap<const MachineBasicBlock *, int> &EHScopeMembership,
-                  bool AfterPlacement) {
+                  bool AfterPlacement,
+                  BranchFolder::MBFIWrapper &MBBFreqInfo,
+                  ProfileSummaryInfo *PSI) {
   // It is never profitable to tail-merge blocks from two different EH scopes.
   if (!EHScopeMembership.empty()) {
     auto EHScope1 = EHScopeMembership.find(MBB1);
@@ -682,7 +689,11 @@
   // branch instruction, which is likely to be smaller than the 2
   // instructions that would be deleted in the merge.
   MachineFunction *MF = MBB1->getParent();
-  return EffectiveTailLen >= 2 && MF->getFunction().hasOptSize() &&
+  bool OptForSize =
+      MF->getFunction().hasOptSize() ||
+      (llvm::shouldOptimizeForSize(MBB1, PSI, &MBBFreqInfo.getMBFI()) &&
+       llvm::shouldOptimizeForSize(MBB2, PSI, &MBBFreqInfo.getMBFI()));
+  return EffectiveTailLen >= 2 && OptForSize &&
          (FullBlockTail1 || FullBlockTail2);
 }
 
@@ -704,7 +715,7 @@
                             CommonTailLen, TrialBBI1, TrialBBI2,
                             SuccBB, PredBB,
                             EHScopeMembership,
-                            AfterBlockPlacement)) {
+                            AfterBlockPlacement, MBBFreqInfo, PSI)) {
         if (CommonTailLen > maxCommonTailLength) {
           SameTails.clear();
           maxCommonTailLength = CommonTailLen;
@@ -1534,8 +1545,10 @@
     }
   }
 
-  if (!IsEmptyBlock(MBB) && MBB->pred_size() == 1 &&
-      MF.getFunction().hasOptSize()) {
+  bool OptForSize =
+      MF.getFunction().hasOptSize() ||
+      llvm::shouldOptimizeForSize(MBB, PSI, &MBBFreqInfo.getMBFI());
+  if (!IsEmptyBlock(MBB) && MBB->pred_size() == 1 && OptForSize) {
     // Changing "Jcc foo; foo: jmp bar;" into "Jcc bar;" might change the branch
     // direction, thereby defeating careful block placement and regressing
     // performance. Therefore, only consider this for optsize functions.
diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp
--- a/llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ b/llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -90,6 +90,7 @@
 #include "llvm/Transforms/Utils/BypassSlowDivision.h"
 #include "llvm/Transforms/Utils/Local.h"
 #include "llvm/Transforms/Utils/SimplifyLibCalls.h"
+#include "llvm/Transforms/Utils/SizeOpts.h"
 #include <algorithm>
 #include <cassert>
 #include <cstdint>
@@ -256,6 +257,7 @@
     const LoopInfo *LI;
     std::unique_ptr<BlockFrequencyInfo> BFI;
     std::unique_ptr<BranchProbabilityInfo> BPI;
+    ProfileSummaryInfo *PSI;
 
     /// As we scan instructions optimizing them, this is the next instruction
     /// to optimize. Transforms that can invalidate this should update it.
@@ -298,7 +300,7 @@
     /// Keep track of SExt promoted.
     ValueToSExts ValToSExtendedUses;
 
-    /// True if optimizing for size.
+    /// True if the function has the OptSize attribute.
     bool OptSize;
 
     /// DataLayout for the Function being processed.
@@ -435,10 +437,8 @@
   LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
   BPI.reset(new BranchProbabilityInfo(F, *LI));
   BFI.reset(new BlockFrequencyInfo(F, *BPI, *LI));
+  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
   OptSize = F.hasOptSize();
-
-  ProfileSummaryInfo *PSI =
-      &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
   if (ProfileGuidedSectionPrefix) {
     if (PSI->isFunctionHotInCallGraph(&F, *BFI))
       F.setSectionPrefix(".hot");
@@ -457,7 +457,9 @@
       // bypassSlowDivision may create new BBs, but we don't want to reapply the
       // optimization to those blocks.
       BasicBlock* Next = BB->getNextNode();
-      EverMadeChange |= bypassSlowDivision(BB, BypassWidths);
+      // F.hasOptSize is already checked in the outer if statement.
+      if (!llvm::shouldOptimizeForSize(BB, PSI, BFI.get()))
+        EverMadeChange |= bypassSlowDivision(BB, BypassWidths);
       BB = Next;
     }
   }
@@ -1938,7 +1940,8 @@
   // cold block.  This interacts with our handling for loads and stores to
   // ensure that we can fold all uses of a potential addressing computation
   // into their uses.  TODO: generalize this to work over profiling data
-  if (!OptSize && CI->hasFnAttr(Attribute::Cold))
+  bool OptForSize = OptSize || llvm::shouldOptimizeForSize(BB, PSI, BFI.get());
+  if (!OptForSize && CI->hasFnAttr(Attribute::Cold))
     for (auto &Arg : CI->arg_operands()) {
       if (!Arg->getType()->isPointerTy())
         continue;
@@ -2875,16 +2878,24 @@
   /// When true, IsProfitableToFoldIntoAddressingMode always returns true.
   bool IgnoreProfitability;
 
+  /// True if we are optimizing for size.
+  bool OptSize;
+
+  ProfileSummaryInfo *PSI;
+  BlockFrequencyInfo *BFI;
+
   AddressingModeMatcher(
       SmallVectorImpl<Instruction *> &AMI, const TargetLowering &TLI,
       const TargetRegisterInfo &TRI, Type *AT, unsigned AS, Instruction *MI,
       ExtAddrMode &AM, const SetOfInstrs &InsertedInsts,
       InstrToOrigTy &PromotedInsts, TypePromotionTransaction &TPT,
-      std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP)
+      std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP,
+      bool OptSize, ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI)
       : AddrModeInsts(AMI), TLI(TLI), TRI(TRI),
         DL(MI->getModule()->getDataLayout()), AccessTy(AT), AddrSpace(AS),
         MemoryInst(MI), AddrMode(AM), InsertedInsts(InsertedInsts),
-        PromotedInsts(PromotedInsts), TPT(TPT), LargeOffsetGEP(LargeOffsetGEP) {
+        PromotedInsts(PromotedInsts), TPT(TPT), LargeOffsetGEP(LargeOffsetGEP),
+        OptSize(OptSize), PSI(PSI), BFI(BFI) {
     IgnoreProfitability = false;
   }
 
@@ -2902,12 +2913,14 @@
         const TargetLowering &TLI, const TargetRegisterInfo &TRI,
         const SetOfInstrs &InsertedInsts, InstrToOrigTy &PromotedInsts,
         TypePromotionTransaction &TPT,
-        std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP) {
+        std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP,
+        bool OptSize, ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI) {
     ExtAddrMode Result;
 
     bool Success = AddressingModeMatcher(AddrModeInsts, TLI, TRI, AccessTy, AS,
                                          MemoryInst, Result, InsertedInsts,
-                                         PromotedInsts, TPT, LargeOffsetGEP)
+                                         PromotedInsts, TPT, LargeOffsetGEP,
+                                         OptSize, PSI, BFI)
                        .matchAddr(V, 0);
     (void)Success; assert(Success && "Couldn't select *anything*?");
     return Result;
@@ -4518,7 +4531,8 @@
     Instruction *I,
     SmallVectorImpl<std::pair<Instruction *, unsigned>> &MemoryUses,
     SmallPtrSetImpl<Instruction *> &ConsideredInsts, const TargetLowering &TLI,
-    const TargetRegisterInfo &TRI, int SeenInsts = 0) {
+    const TargetRegisterInfo &TRI, bool OptSize, ProfileSummaryInfo *PSI,
+    BlockFrequencyInfo *BFI, int SeenInsts = 0) {
   // If we already considered this instruction, we're done.
   if (!ConsideredInsts.insert(I).second)
     return false;
@@ -4527,8 +4541,6 @@
   if (!MightBeFoldableInst(I))
     return true;
 
-  const bool OptSize = I->getFunction()->hasOptSize();
-
   // Loop over all the uses, recursively processing them.
   for (Use &U : I->uses()) {
     // Conservatively return true if we're seeing a large number or a deep chain
@@ -4569,7 +4581,9 @@
     if (CallInst *CI = dyn_cast<CallInst>(UserI)) {
       // If this is a cold call, we can sink the addressing calculation into
       // the cold path.  See optimizeCallInst
-      if (!OptSize && CI->hasFnAttr(Attribute::Cold))
+      bool OptForSize = OptSize ||
+          llvm::shouldOptimizeForSize(CI->getParent(), PSI, BFI);
+      if (!OptForSize && CI->hasFnAttr(Attribute::Cold))
         continue;
 
       InlineAsm *IA = dyn_cast<InlineAsm>(CI->getCalledValue());
@@ -4581,8 +4595,8 @@
       continue;
     }
 
-    if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TLI, TRI,
-                          SeenInsts))
+    if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TLI, TRI, OptSize,
+                          PSI, BFI, SeenInsts))
       return true;
   }
 
@@ -4670,7 +4684,8 @@
   // the use is just a particularly nice way of sinking it.
   SmallVector<std::pair<Instruction*,unsigned>, 16> MemoryUses;
   SmallPtrSet<Instruction*, 16> ConsideredInsts;
-  if (FindAllMemoryUses(I, MemoryUses, ConsideredInsts, TLI, TRI))
+  if (FindAllMemoryUses(I, MemoryUses, ConsideredInsts, TLI, TRI, OptSize,
+                        PSI, BFI))
     return false;  // Has a non-memory, non-foldable use!
 
   // Now that we know that all uses of this instruction are part of a chain of
@@ -4706,7 +4721,7 @@
         TPT.getRestorationPoint();
     AddressingModeMatcher Matcher(
         MatchedAddrModeInsts, TLI, TRI, AddressAccessTy, AS, MemoryInst, Result,
-        InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP);
+        InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP, OptSize, PSI, BFI);
     Matcher.IgnoreProfitability = true;
     bool Success = Matcher.matchAddr(Address, 0);
     (void)Success; assert(Success && "Couldn't select *anything*?");
@@ -4812,7 +4827,8 @@
                                                                       0);
     ExtAddrMode NewAddrMode = AddressingModeMatcher::Match(
         V, AccessTy, AddrSpace, MemoryInst, AddrModeInsts, *TLI, *TRI,
-        InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP);
+        InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP, OptSize, PSI,
+        BFI.get());
 
     GetElementPtrInst *GEP = LargeOffsetGEP.first;
     if (GEP && !NewGEPBases.count(GEP)) {
@@ -6030,7 +6046,9 @@
 /// turn it into a branch.
 bool CodeGenPrepare::optimizeSelectInst(SelectInst *SI) {
   // If branch conversion isn't desirable, exit early.
-  if (DisableSelectToBranch || OptSize || !TLI)
+  if (DisableSelectToBranch ||
+      OptSize || llvm::shouldOptimizeForSize(SI->getParent(), PSI, BFI.get()) ||
+      !TLI)
     return false;
 
   // Find all consecutive select instructions that share the same condition.
diff --git a/llvm/lib/CodeGen/ExpandMemCmp.cpp b/llvm/lib/CodeGen/ExpandMemCmp.cpp
--- a/llvm/lib/CodeGen/ExpandMemCmp.cpp
+++ b/llvm/lib/CodeGen/ExpandMemCmp.cpp
@@ -13,6 +13,8 @@
 
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/ConstantFolding.h"
+#include "llvm/Analysis/LazyBlockFrequencyInfo.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
@@ -21,6 +23,7 @@
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/InitializePasses.h"
+#include "llvm/Transforms/Utils/SizeOpts.h"
 
 using namespace llvm;
 
@@ -721,7 +724,8 @@
 ///  %phi.res = phi i32 [ %48, %loadbb3 ], [ %11, %res_block ]
 ///  ret i32 %phi.res
 static bool expandMemCmp(CallInst *CI, const TargetTransformInfo *TTI,
-                         const TargetLowering *TLI, const DataLayout *DL) {
+                         const TargetLowering *TLI, const DataLayout *DL,
+                         ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI) {
   NumMemCmpCalls++;
 
   // Early exit from expansion if -Oz.
@@ -742,18 +746,20 @@
   // TTI call to check if target would like to expand memcmp. Also, get the
   // available load sizes.
   const bool IsUsedForZeroCmp = isOnlyUsedInZeroEqualityComparison(CI);
-  auto Options = TTI->enableMemCmpExpansion(CI->getFunction()->hasOptSize(),
+  bool OptForSize = CI->getFunction()->hasOptSize() ||
+                    llvm::shouldOptimizeForSize(CI->getParent(), PSI, BFI);
+  auto Options = TTI->enableMemCmpExpansion(OptForSize,
                                             IsUsedForZeroCmp);
   if (!Options) return false;
 
   if (MemCmpEqZeroNumLoadsPerBlock.getNumOccurrences())
     Options.NumLoadsPerBlock = MemCmpEqZeroNumLoadsPerBlock;
 
-  if (CI->getFunction()->hasOptSize() &&
+  if (OptForSize &&
       MaxLoadsPerMemcmpOptSize.getNumOccurrences())
     Options.MaxNumLoads = MaxLoadsPerMemcmpOptSize;
 
-  if (!CI->getFunction()->hasOptSize() && MaxLoadsPerMemcmp.getNumOccurrences())
+  if (!OptForSize && MaxLoadsPerMemcmp.getNumOccurrences())
     Options.MaxNumLoads = MaxLoadsPerMemcmp;
 
   MemCmpExpansion Expansion(CI, SizeVal, Options, IsUsedForZeroCmp, *DL);
@@ -799,7 +805,11 @@
         &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
     const TargetTransformInfo *TTI =
         &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
-    auto PA = runImpl(F, TLI, TTI, TL);
+    auto *PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+    auto *BFI = (PSI && PSI->hasProfileSummary()) ?
+           &getAnalysis<LazyBlockFrequencyInfoPass>().getBFI() :
+           nullptr;
+    auto PA = runImpl(F, TLI, TTI, TL, PSI, BFI);
     return !PA.areAllPreserved();
   }
 
@@ -807,22 +817,26 @@
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<TargetLibraryInfoWrapperPass>();
     AU.addRequired<TargetTransformInfoWrapperPass>();
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
+    LazyBlockFrequencyInfoPass::getLazyBFIAnalysisUsage(AU);
     FunctionPass::getAnalysisUsage(AU);
   }
 
   PreservedAnalyses runImpl(Function &F, const TargetLibraryInfo *TLI,
                             const TargetTransformInfo *TTI,
-                            const TargetLowering* TL);
+                            const TargetLowering* TL,
+                            ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI);
   // Returns true if a change was made.
   bool runOnBlock(BasicBlock &BB, const TargetLibraryInfo *TLI,
                   const TargetTransformInfo *TTI, const TargetLowering* TL,
-                  const DataLayout& DL);
+                  const DataLayout& DL, ProfileSummaryInfo *PSI,
+                  BlockFrequencyInfo *BFI);
 };
 
 bool ExpandMemCmpPass::runOnBlock(
     BasicBlock &BB, const TargetLibraryInfo *TLI,
     const TargetTransformInfo *TTI, const TargetLowering* TL,
-    const DataLayout& DL) {
+    const DataLayout& DL, ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI) {
   for (Instruction& I : BB) {
     CallInst *CI = dyn_cast<CallInst>(&I);
     if (!CI) {
@@ -831,7 +845,7 @@
     LibFunc Func;
     if (TLI->getLibFunc(ImmutableCallSite(CI), Func) &&
         (Func == LibFunc_memcmp || Func == LibFunc_bcmp) &&
-        expandMemCmp(CI, TTI, TL, &DL)) {
+        expandMemCmp(CI, TTI, TL, &DL, PSI, BFI)) {
       return true;
     }
   }
@@ -841,11 +855,12 @@
 
 PreservedAnalyses ExpandMemCmpPass::runImpl(
     Function &F, const TargetLibraryInfo *TLI, const TargetTransformInfo *TTI,
-    const TargetLowering* TL) {
+    const TargetLowering* TL, ProfileSummaryInfo *PSI,
+    BlockFrequencyInfo *BFI) {
   const DataLayout& DL = F.getParent()->getDataLayout();
   bool MadeChanges = false;
   for (auto BBIt = F.begin(); BBIt != F.end();) {
-    if (runOnBlock(*BBIt, TLI, TTI, TL, DL)) {
+    if (runOnBlock(*BBIt, TLI, TTI, TL, DL, PSI, BFI)) {
       MadeChanges = true;
       // If changes were made, restart the function from the beginning, since
       // the structure of the function was changed.
@@ -864,6 +879,8 @@
                       "Expand memcmp() to load/stores", false, false)
 INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(LazyBlockFrequencyInfoPass)
+INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)
 INITIALIZE_PASS_END(ExpandMemCmpPass, "expandmemcmp",
                     "Expand memcmp() to load/stores", false, false)
 
diff --git a/llvm/lib/CodeGen/IfConversion.cpp b/llvm/lib/CodeGen/IfConversion.cpp
--- a/llvm/lib/CodeGen/IfConversion.cpp
+++ b/llvm/lib/CodeGen/IfConversion.cpp
@@ -19,6 +19,7 @@
 #include "llvm/ADT/SparseSet.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/iterator_range.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/CodeGen/LivePhysRegs.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
@@ -213,6 +214,7 @@
     void getAnalysisUsage(AnalysisUsage &AU) const override {
       AU.addRequired<MachineBlockFrequencyInfo>();
       AU.addRequired<MachineBranchProbabilityInfo>();
+      AU.addRequired<ProfileSummaryInfoWrapperPass>();
       MachineFunctionPass::getAnalysisUsage(AU);
     }
 
@@ -434,6 +436,7 @@
 
 INITIALIZE_PASS_BEGIN(IfConverter, DEBUG_TYPE, "If Converter", false, false)
 INITIALIZE_PASS_DEPENDENCY(MachineBranchProbabilityInfo)
+INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)
 INITIALIZE_PASS_END(IfConverter, DEBUG_TYPE, "If Converter", false, false)
 
 bool IfConverter::runOnMachineFunction(MachineFunction &MF) {
@@ -446,6 +449,8 @@
   TRI = ST.getRegisterInfo();
   BranchFolder::MBFIWrapper MBFI(getAnalysis<MachineBlockFrequencyInfo>());
   MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
+  ProfileSummaryInfo *PSI =
+      &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
   MRI = &MF.getRegInfo();
   SchedModel.init(&ST);
 
@@ -456,7 +461,7 @@
   bool BFChange = false;
   if (!PreRegAlloc) {
     // Tail merge tend to expose more if-conversion opportunities.
-    BranchFolder BF(true, false, MBFI, *MBPI);
+    BranchFolder BF(true, false, MBFI, *MBPI, PSI);
     auto *MMIWP = getAnalysisIfAvailable<MachineModuleInfoWrapperPass>();
     BFChange = BF.OptimizeFunction(
         MF, TII, ST.getRegisterInfo(),
@@ -598,7 +603,7 @@
   BBAnalysis.clear();
 
   if (MadeChange && IfCvtBranchFold) {
-    BranchFolder BF(false, false, MBFI, *MBPI);
+    BranchFolder BF(false, false, MBFI, *MBPI, PSI);
     auto *MMIWP = getAnalysisIfAvailable<MachineModuleInfoWrapperPass>();
     BF.OptimizeFunction(
         MF, TII, MF.getSubtarget().getRegisterInfo(),
diff --git a/llvm/lib/CodeGen/MachineBlockPlacement.cpp b/llvm/lib/CodeGen/MachineBlockPlacement.cpp
--- a/llvm/lib/CodeGen/MachineBlockPlacement.cpp
+++ b/llvm/lib/CodeGen/MachineBlockPlacement.cpp
@@ -33,6 +33,7 @@
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/BlockFrequencyInfoImpl.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
@@ -41,6 +42,7 @@
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachinePostDominators.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/TailDuplicator.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/CodeGen/TargetLowering.h"
@@ -363,6 +365,8 @@
   /// A handle to the post dominator tree.
   MachinePostDominatorTree *MPDT;
 
+  ProfileSummaryInfo *PSI;
+
   /// Duplicator used to duplicate tails during placement.
   ///
   /// Placement decisions can open up new tail duplication opportunities, but
@@ -538,6 +542,7 @@
     if (TailDupPlacement)
       AU.addRequired<MachinePostDominatorTree>();
     AU.addRequired<MachineLoopInfo>();
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
     AU.addRequired<TargetPassConfig>();
     MachineFunctionPass::getAnalysisUsage(AU);
   }
@@ -555,6 +560,7 @@
 INITIALIZE_PASS_DEPENDENCY(MachineBlockFrequencyInfo)
 INITIALIZE_PASS_DEPENDENCY(MachinePostDominatorTree)
 INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
+INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)
 INITIALIZE_PASS_END(MachineBlockPlacement, DEBUG_TYPE,
                     "Branch Probability Basic Block Placement", false, false)
 
@@ -2075,7 +2081,10 @@
   // i.e. when the layout predecessor does not fallthrough to the loop header.
   // In practice this never happens though: there always seems to be a preheader
   // that can fallthrough and that is also placed before the header.
-  if (F->getFunction().hasOptSize())
+  bool OptForSize = F->getFunction().hasOptSize() ||
+                    llvm::shouldOptimizeForSize(L.getHeader(), PSI,
+                                                &MBFI->getMBFI());
+  if (OptForSize)
     return L.getHeader();
 
   MachineBasicBlock *OldTop = nullptr;
@@ -2831,6 +2840,11 @@
     if (Freq < (LoopHeaderFreq * ColdProb))
       continue;
 
+    // If the global profiles indicates so, don't align it.
+    if (llvm::shouldOptimizeForSize(ChainBB, PSI, &MBFI->getMBFI()) &&
+        !TLI->alignLoopsWithOptSize())
+      continue;
+
     // Check for the existence of a non-layout predecessor which would benefit
     // from aligning this block.
     MachineBasicBlock *LayoutPred =
@@ -3038,6 +3052,7 @@
   TII = MF.getSubtarget().getInstrInfo();
   TLI = MF.getSubtarget().getTargetLowering();
   MPDT = nullptr;
+  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
 
   // Initialize PreferredLoopExit to nullptr here since it may never be set if
   // there are no MachineLoops.
@@ -3068,10 +3083,13 @@
 
   if (allowTailDupPlacement()) {
     MPDT = &getAnalysis<MachinePostDominatorTree>();
-    if (MF.getFunction().hasOptSize())
+    bool OptForSize = MF.getFunction().hasOptSize() ||
+                      llvm::shouldOptimizeForSize(&MF, PSI, &MBFI->getMBFI());
+    if (OptForSize)
       TailDupSize = 1;
     bool PreRegAlloc = false;
-    TailDup.initMF(MF, PreRegAlloc, MBPI, /* LayoutMode */ true, TailDupSize);
+    TailDup.initMF(MF, PreRegAlloc, MBPI, &MBFI->getMBFI(), PSI,
+                   /* LayoutMode */ true, TailDupSize);
     precomputeTriangleChains();
   }
 
@@ -3087,7 +3105,7 @@
   if (MF.size() > 3 && EnableTailMerge) {
     unsigned TailMergeSize = TailDupSize + 1;
     BranchFolder BF(/*EnableTailMerge=*/true, /*CommonHoist=*/false, *MBFI,
-                    *MBPI, TailMergeSize);
+                    *MBPI, PSI, TailMergeSize);
 
     auto *MMIWP = getAnalysisIfAvailable<MachineModuleInfoWrapperPass>();
     if (BF.OptimizeFunction(MF, TII, MF.getSubtarget().getRegisterInfo(),
diff --git a/llvm/lib/CodeGen/MachineCombiner.cpp b/llvm/lib/CodeGen/MachineCombiner.cpp
--- a/llvm/lib/CodeGen/MachineCombiner.cpp
+++ b/llvm/lib/CodeGen/MachineCombiner.cpp
@@ -12,11 +12,14 @@
 
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/MachineTraceMetrics.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
@@ -67,6 +70,8 @@
   MachineLoopInfo *MLI; // Current MachineLoopInfo
   MachineTraceMetrics *Traces;
   MachineTraceMetrics::Ensemble *MinInstr;
+  MachineBlockFrequencyInfo *MBFI;
+  ProfileSummaryInfo *PSI;
 
   TargetSchedModel TSchedModel;
 
@@ -83,7 +88,7 @@
   StringRef getPassName() const override { return "Machine InstCombiner"; }
 
 private:
-  bool doSubstitute(unsigned NewSize, unsigned OldSize);
+  bool doSubstitute(unsigned NewSize, unsigned OldSize, bool OptForSize);
   bool combineInstructions(MachineBasicBlock *);
   MachineInstr *getOperandDef(const MachineOperand &MO);
   unsigned getDepth(SmallVectorImpl<MachineInstr *> &InsInstrs,
@@ -132,6 +137,8 @@
   AU.addPreserved<MachineLoopInfo>();
   AU.addRequired<MachineTraceMetrics>();
   AU.addPreserved<MachineTraceMetrics>();
+  AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
+  AU.addRequired<ProfileSummaryInfoWrapperPass>();
   MachineFunctionPass::getAnalysisUsage(AU);
 }
 
@@ -409,8 +416,9 @@
 
 /// \returns true when new instruction sequence should be generated
 /// independent if it lengthens critical path or not
-bool MachineCombiner::doSubstitute(unsigned NewSize, unsigned OldSize) {
-  if (OptSize && (NewSize < OldSize))
+bool MachineCombiner::doSubstitute(unsigned NewSize, unsigned OldSize,
+                                   bool OptForSize) {
+  if (OptForSize && (NewSize < OldSize))
     return true;
   if (!TSchedModel.hasInstrSchedModelOrItineraries())
     return true;
@@ -508,6 +516,8 @@
   SparseSet<LiveRegUnit> RegUnits;
   RegUnits.setUniverse(TRI->getNumRegUnits());
 
+  bool OptForSize = OptSize || llvm::shouldOptimizeForSize(MBB, PSI, MBFI);
+
   while (BlockIter != MBB->end()) {
     auto &MI = *BlockIter++;
     SmallVector<MachineCombinerPattern, 16> Patterns;
@@ -584,7 +594,8 @@
       // fewer instructions OR
       // the new sequence neither lengthens the critical path nor increases
       // resource pressure.
-      if (SubstituteAlways || doSubstitute(NewInstCount, OldInstCount)) {
+      if (SubstituteAlways ||
+          doSubstitute(NewInstCount, OldInstCount, OptForSize)) {
         insertDeleteInstructions(MBB, MI, InsInstrs, DelInstrs, MinInstr,
                                  RegUnits, IncrementalUpdate);
         // Eagerly stop after the first pattern fires.
@@ -639,6 +650,10 @@
   MRI = &MF.getRegInfo();
   MLI = &getAnalysis<MachineLoopInfo>();
   Traces = &getAnalysis<MachineTraceMetrics>();
+  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  MBFI = (PSI && PSI->hasProfileSummary()) ?
+         &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+         nullptr;
   MinInstr = nullptr;
   OptSize = MF.getFunction().hasOptSize();
 
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
@@ -27,8 +27,10 @@
 #include "llvm/Analysis/BranchProbabilityInfo.h"
 #include "llvm/Analysis/CFG.h"
 #include "llvm/Analysis/EHPersonalities.h"
+#include "llvm/Analysis/LazyBlockFrequencyInfo.h"
 #include "llvm/Analysis/LegacyDivergenceAnalysis.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/CodeGen/FastISel.h"
@@ -334,6 +336,8 @@
   AU.addRequired<TargetTransformInfoWrapperPass>();
   if (UseMBPI && OptLevel != CodeGenOpt::None)
     AU.addRequired<BranchProbabilityInfoWrapperPass>();
+  AU.addRequired<ProfileSummaryInfoWrapperPass>();
+  LazyBlockFrequencyInfoPass::getLazyBFIAnalysisUsage(AU);
   MachineFunctionPass::getAnalysisUsage(AU);
 }
 
@@ -436,14 +440,17 @@
   DominatorTree *DT = DTWP ? &DTWP->getDomTree() : nullptr;
   auto *LIWP = getAnalysisIfAvailable<LoopInfoWrapperPass>();
   LoopInfo *LI = LIWP ? &LIWP->getLoopInfo() : nullptr;
+  auto *PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  auto *BFI = (PSI && PSI->hasProfileSummary()) ?
+              &getAnalysis<LazyBlockFrequencyInfoPass>().getBFI() :
+              nullptr;
 
   LLVM_DEBUG(dbgs() << "\n\n\n=== " << Fn.getName() << "\n");
 
   SplitCriticalSideEffectEdges(const_cast<Function &>(Fn), DT, LI);
 
   CurDAG->init(*MF, *ORE, this, LibInfo,
-               getAnalysisIfAvailable<LegacyDivergenceAnalysis>(),
-               nullptr, nullptr);
+               getAnalysisIfAvailable<LegacyDivergenceAnalysis>(), PSI, BFI);
   FuncInfo->set(Fn, *MF, CurDAG);
   SwiftError->setFunction(*MF);
 
diff --git a/llvm/lib/CodeGen/TailDuplication.cpp b/llvm/lib/CodeGen/TailDuplication.cpp
--- a/llvm/lib/CodeGen/TailDuplication.cpp
+++ b/llvm/lib/CodeGen/TailDuplication.cpp
@@ -12,6 +12,8 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
@@ -38,6 +40,8 @@
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<MachineBranchProbabilityInfo>();
+    AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
     MachineFunctionPass::getAnalysisUsage(AU);
   }
 };
@@ -75,7 +79,11 @@
     return false;
 
   auto MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
-  Duplicator.initMF(MF, PreRegAlloc, MBPI, /*LayoutMode=*/false);
+  auto *PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  auto *MBFI = (PSI && PSI->hasProfileSummary()) ?
+               &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+               nullptr;
+  Duplicator.initMF(MF, PreRegAlloc, MBPI, MBFI, PSI, /*LayoutMode=*/false);
 
   bool MadeChange = false;
   while (Duplicator.tailDuplicateBlocks())
diff --git a/llvm/lib/CodeGen/TailDuplicator.cpp b/llvm/lib/CodeGen/TailDuplicator.cpp
--- a/llvm/lib/CodeGen/TailDuplicator.cpp
+++ b/llvm/lib/CodeGen/TailDuplicator.cpp
@@ -19,13 +19,16 @@
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
+#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/MachineSSAUpdater.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/CodeGen/TargetRegisterInfo.h"
@@ -77,6 +80,8 @@
 
 void TailDuplicator::initMF(MachineFunction &MFin, bool PreRegAlloc,
                             const MachineBranchProbabilityInfo *MBPIin,
+                            const MachineBlockFrequencyInfo *MBFIin,
+                            ProfileSummaryInfo *PSIin,
                             bool LayoutModeIn, unsigned TailDupSizeIn) {
   MF = &MFin;
   TII = MF->getSubtarget().getInstrInfo();
@@ -84,6 +89,8 @@
   MRI = &MF->getRegInfo();
   MMI = &MF->getMMI();
   MBPI = MBPIin;
+  MBFI = MBFIin;
+  PSI = PSIin;
   TailDupSize = TailDupSizeIn;
 
   assert(MBPI != nullptr && "Machine Branch Probability Info required");
@@ -555,14 +562,14 @@
   // duplicate only one, because one branch instruction can be eliminated to
   // compensate for the duplication.
   unsigned MaxDuplicateCount;
-  if (TailDupSize == 0 &&
-      TailDuplicateSize.getNumOccurrences() == 0 &&
-      MF->getFunction().hasOptSize())
-    MaxDuplicateCount = 1;
-  else if (TailDupSize == 0)
+  bool OptForSize = MF->getFunction().hasOptSize() ||
+                    llvm::shouldOptimizeForSize(&TailBB, PSI, MBFI);
+  if (TailDupSize == 0)
     MaxDuplicateCount = TailDuplicateSize;
   else
     MaxDuplicateCount = TailDupSize;
+  if (OptForSize)
+    MaxDuplicateCount = 1;
 
   // If the block to be duplicated ends in an unanalyzable fallthrough, don't
   // duplicate it.
diff --git a/llvm/lib/Target/X86/X86FixupBWInsts.cpp b/llvm/lib/Target/X86/X86FixupBWInsts.cpp
--- a/llvm/lib/Target/X86/X86FixupBWInsts.cpp
+++ b/llvm/lib/Target/X86/X86FixupBWInsts.cpp
@@ -48,11 +48,14 @@
 #include "X86InstrInfo.h"
 #include "X86Subtarget.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/LivePhysRegs.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/Support/Debug.h"
@@ -113,6 +116,8 @@
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<MachineLoopInfo>(); // Machine loop info is used to
                                        // guide some heuristics.
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
+    AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
     MachineFunctionPass::getAnalysisUsage(AU);
   }
 
@@ -140,6 +145,9 @@
 
   /// Register Liveness information after the current instruction.
   LivePhysRegs LiveRegs;
+
+  ProfileSummaryInfo *PSI;
+  MachineBlockFrequencyInfo *MBFI;
 };
 char FixupBWInstPass::ID = 0;
 }
@@ -154,8 +162,11 @@
 
   this->MF = &MF;
   TII = MF.getSubtarget<X86Subtarget>().getInstrInfo();
-  OptForSize = MF.getFunction().hasOptSize();
   MLI = &getAnalysis<MachineLoopInfo>();
+  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  MBFI = (PSI && PSI->hasProfileSummary()) ?
+         &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+         nullptr;
   LiveRegs.init(TII->getRegisterInfo());
 
   LLVM_DEBUG(dbgs() << "Start X86FixupBWInsts\n";);
@@ -426,6 +437,9 @@
   // We run after PEI, so we need to AddPristinesAndCSRs.
   LiveRegs.addLiveOuts(MBB);
 
+  OptForSize = MF.getFunction().hasOptSize() ||
+               llvm::shouldOptimizeForSize(&MBB, PSI, MBFI);
+
   for (auto I = MBB.rbegin(); I != MBB.rend(); ++I) {
     MachineInstr *MI = &*I;
 
diff --git a/llvm/lib/Target/X86/X86OptimizeLEAs.cpp b/llvm/lib/Target/X86/X86OptimizeLEAs.cpp
--- a/llvm/lib/Target/X86/X86OptimizeLEAs.cpp
+++ b/llvm/lib/Target/X86/X86OptimizeLEAs.cpp
@@ -25,6 +25,8 @@
 #include "llvm/ADT/Hashing.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
@@ -32,6 +34,7 @@
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/TargetOpcodes.h"
 #include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/IR/DebugInfoMetadata.h"
@@ -247,6 +250,12 @@
 
   static char ID;
 
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
+    AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
+    MachineFunctionPass::getAnalysisUsage(AU);
+  }
+
 private:
   using MemOpMap = DenseMap<MemOpKey, SmallVector<MachineInstr *, 16>>;
 
@@ -681,6 +690,11 @@
   MRI = &MF.getRegInfo();
   TII = MF.getSubtarget<X86Subtarget>().getInstrInfo();
   TRI = MF.getSubtarget<X86Subtarget>().getRegisterInfo();
+  auto *PSI =
+      &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  auto *MBFI = (PSI && PSI->hasProfileSummary()) ?
+               &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+               nullptr;
 
   // Process all basic blocks.
   for (auto &MBB : MF) {
@@ -699,7 +713,9 @@
 
     // Remove redundant address calculations. Do it only for -Os/-Oz since only
     // a code size gain is expected from this part of the pass.
-    if (MF.getFunction().hasOptSize())
+    bool OptForSize = MF.getFunction().hasOptSize() ||
+                      llvm::shouldOptimizeForSize(&MBB, PSI, MBFI);
+    if (OptForSize)
       Changed |= removeRedundantAddrCalc(LEAs);
   }
 
diff --git a/llvm/lib/Target/X86/X86PadShortFunction.cpp b/llvm/lib/Target/X86/X86PadShortFunction.cpp
--- a/llvm/lib/Target/X86/X86PadShortFunction.cpp
+++ b/llvm/lib/Target/X86/X86PadShortFunction.cpp
@@ -17,8 +17,11 @@
 #include "X86InstrInfo.h"
 #include "X86Subtarget.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetSchedule.h"
 #include "llvm/IR/Function.h"
@@ -52,6 +55,12 @@
 
     bool runOnMachineFunction(MachineFunction &MF) override;
 
+    void getAnalysisUsage(AnalysisUsage &AU) const override {
+      AU.addRequired<ProfileSummaryInfoWrapperPass>();
+      AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
+      MachineFunctionPass::getAnalysisUsage(AU);
+    }
+
     MachineFunctionProperties getRequiredProperties() const override {
       return MachineFunctionProperties().set(
           MachineFunctionProperties::Property::NoVRegs);
@@ -105,6 +114,12 @@
 
   TSM.init(&MF.getSubtarget());
 
+  auto *PSI =
+      &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  auto *MBFI = (PSI && PSI->hasProfileSummary()) ?
+               &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+               nullptr;
+
   // Search through basic blocks and mark the ones that have early returns
   ReturnBBs.clear();
   VisitedBBs.clear();
@@ -118,6 +133,11 @@
     MachineBasicBlock *MBB = I->first;
     unsigned Cycles = I->second;
 
+    // Function::hasOptSize is already checked above.
+    bool OptForSize = llvm::shouldOptimizeForSize(MBB, PSI, MBFI);
+    if (OptForSize)
+      continue;
+
     if (Cycles < Threshold) {
       // BB ends in a return. Skip over any DBG_VALUE instructions
       // trailing the terminator.
diff --git a/llvm/test/CodeGen/AArch64/O0-pipeline.ll b/llvm/test/CodeGen/AArch64/O0-pipeline.ll
--- a/llvm/test/CodeGen/AArch64/O0-pipeline.ll
+++ b/llvm/test/CodeGen/AArch64/O0-pipeline.ll
@@ -11,6 +11,7 @@
 ; CHECK-NEXT: Scoped NoAlias Alias Analysis
 ; CHECK-NEXT: Assumption Cache Tracker
 ; CHECK-NEXT: Create Garbage Collector Module Metadata
+; CHECK-NEXT: Profile summary info
 ; CHECK-NEXT: Machine Branch Probability Analysis
 ; CHECK-NEXT:   ModulePass Manager
 ; CHECK-NEXT:     Pre-ISel Intrinsic Lowering
@@ -45,6 +46,10 @@
 ; CHECK-NEXT:       Analysis for ComputingKnownBits
 ; CHECK-NEXT:       InstructionSelect
 ; CHECK-NEXT:       ResetMachineFunction
+; CHECK-NEXT:       Dominator Tree Construction
+; CHECK-NEXT:       Natural Loop Information
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       AArch64 Instruction Selection
 ; CHECK-NEXT:       Finalize ISel and expand pseudo-instructions
 ; CHECK-NEXT:       Local Stack Slot Allocation
diff --git a/llvm/test/CodeGen/AArch64/O3-pipeline.ll b/llvm/test/CodeGen/AArch64/O3-pipeline.ll
--- a/llvm/test/CodeGen/AArch64/O3-pipeline.ll
+++ b/llvm/test/CodeGen/AArch64/O3-pipeline.ll
@@ -10,8 +10,8 @@
 ; CHECK-NEXT: Assumption Cache Tracker
 ; CHECK-NEXT: Type-Based Alias Analysis
 ; CHECK-NEXT: Scoped NoAlias Alias Analysis
-; CHECK-NEXT: Create Garbage Collector Module Metadata
 ; CHECK-NEXT: Profile summary info
+; CHECK-NEXT: Create Garbage Collector Module Metadata
 ; CHECK-NEXT: Machine Branch Probability Analysis
 ; CHECK-NEXT:   ModulePass Manager
 ; CHECK-NEXT:     Pre-ISel Intrinsic Lowering
@@ -35,6 +35,9 @@
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:       Merge contiguous icmps into a memcmp
+; CHECK-NEXT:       Natural Loop Information
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       Expand memcmp() to load/stores
 ; CHECK-NEXT:       Lower Garbage Collection Instructions
 ; CHECK-NEXT:       Shadow Stack GC Lowering
@@ -78,10 +81,13 @@
 ; CHECK-NEXT:       Function Alias Analysis Results
 ; CHECK-NEXT:       Natural Loop Information
 ; CHECK-NEXT:       Branch Probability Analysis
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       AArch64 Instruction Selection
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       AArch64 Local Dynamic TLS Access Clean-up
 ; CHECK-NEXT:       Finalize ISel and expand pseudo-instructions
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Early Tail Duplication
 ; CHECK-NEXT:       Optimize machine instruction PHIs
 ; CHECK-NEXT:       Slot index numbering
@@ -93,6 +99,7 @@
 ; CHECK-NEXT:       Machine Natural Loop Construction
 ; CHECK-NEXT:       Machine Trace Metrics
 ; CHECK-NEXT:       AArch64 Conditional Compares
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine InstCombiner
 ; CHECK-NEXT:       AArch64 Conditional Branch Tuning
 ; CHECK-NEXT:       Machine Trace Metrics
@@ -149,6 +156,7 @@
 ; CHECK-NEXT:       Shrink Wrapping analysis
 ; CHECK-NEXT:       Prologue/Epilogue Insertion & Frame Finalization
 ; CHECK-NEXT:       Control Flow Optimizer
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Tail Duplication
 ; CHECK-NEXT:       Machine Copy Propagation Pass
 ; CHECK-NEXT:       Post-RA pseudo instruction expansion pass
diff --git a/llvm/test/CodeGen/ARM/O3-pipeline.ll b/llvm/test/CodeGen/ARM/O3-pipeline.ll
--- a/llvm/test/CodeGen/ARM/O3-pipeline.ll
+++ b/llvm/test/CodeGen/ARM/O3-pipeline.ll
@@ -19,6 +19,9 @@
 ; CHECK-NEXT:      Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:      Function Alias Analysis Results
 ; CHECK-NEXT:      Merge contiguous icmps into a memcmp
+; CHECK-NEXT:      Natural Loop Information
+; CHECK-NEXT:      Lazy Branch Probability Analysis
+; CHECK-NEXT:      Lazy Block Frequency Analysis
 ; CHECK-NEXT:      Expand memcmp() to load/stores
 ; CHECK-NEXT:      Lower Garbage Collection Instructions
 ; CHECK-NEXT:      Shadow Stack GC Lowering
@@ -67,8 +70,11 @@
 ; CHECK-NEXT:      Function Alias Analysis Results
 ; CHECK-NEXT:      Natural Loop Information
 ; CHECK-NEXT:      Branch Probability Analysis
+; CHECK-NEXT:      Lazy Branch Probability Analysis
+; CHECK-NEXT:      Lazy Block Frequency Analysis
 ; CHECK-NEXT:      ARM Instruction Selection
 ; CHECK-NEXT:      Finalize ISel and expand pseudo-instructions
+; CHECK-NEXT:      Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:      Early Tail Duplication
 ; CHECK-NEXT:      Optimize machine instruction PHIs
 ; CHECK-NEXT:      Slot index numbering
@@ -124,6 +130,7 @@
 ; CHECK-NEXT:      Shrink Wrapping analysis
 ; CHECK-NEXT:      Prologue/Epilogue Insertion & Frame Finalization
 ; CHECK-NEXT:      Control Flow Optimizer
+; CHECK-NEXT:      Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:      Tail Duplication
 ; CHECK-NEXT:      Machine Copy Propagation Pass
 ; CHECK-NEXT:      Post-RA pseudo instruction expansion pass
diff --git a/llvm/test/CodeGen/X86/O0-pipeline.ll b/llvm/test/CodeGen/X86/O0-pipeline.ll
--- a/llvm/test/CodeGen/X86/O0-pipeline.ll
+++ b/llvm/test/CodeGen/X86/O0-pipeline.ll
@@ -14,6 +14,7 @@
 ; CHECK-NEXT: Scoped NoAlias Alias Analysis
 ; CHECK-NEXT: Assumption Cache Tracker
 ; CHECK-NEXT: Create Garbage Collector Module Metadata
+; CHECK-NEXT: Profile summary info
 ; CHECK-NEXT: Machine Branch Probability Analysis
 ; CHECK-NEXT:   ModulePass Manager
 ; CHECK-NEXT:     Pre-ISel Intrinsic Lowering
@@ -37,6 +38,10 @@
 ; CHECK-NEXT:       Safe Stack instrumentation pass
 ; CHECK-NEXT:       Insert stack protectors
 ; CHECK-NEXT:       Module Verifier
+; CHECK-NEXT:       Dominator Tree Construction
+; CHECK-NEXT:       Natural Loop Information
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       X86 DAG->DAG Instruction Selection
 ; CHECK-NEXT:       X86 PIC Global Base Reg Initialization
 ; CHECK-NEXT:       Finalize ISel and expand pseudo-instructions
diff --git a/llvm/test/CodeGen/X86/O3-pipeline.ll b/llvm/test/CodeGen/X86/O3-pipeline.ll
--- a/llvm/test/CodeGen/X86/O3-pipeline.ll
+++ b/llvm/test/CodeGen/X86/O3-pipeline.ll
@@ -13,8 +13,8 @@
 ; CHECK-NEXT: Type-Based Alias Analysis
 ; CHECK-NEXT: Scoped NoAlias Alias Analysis
 ; CHECK-NEXT: Assumption Cache Tracker
-; CHECK-NEXT: Create Garbage Collector Module Metadata
 ; CHECK-NEXT: Profile summary info
+; CHECK-NEXT: Create Garbage Collector Module Metadata
 ; CHECK-NEXT: Machine Branch Probability Analysis
 ; CHECK-NEXT:   ModulePass Manager
 ; CHECK-NEXT:     Pre-ISel Intrinsic Lowering
@@ -32,6 +32,9 @@
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:       Merge contiguous icmps into a memcmp
+; CHECK-NEXT:       Natural Loop Information
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       Expand memcmp() to load/stores
 ; CHECK-NEXT:       Lower Garbage Collection Instructions
 ; CHECK-NEXT:       Shadow Stack GC Lowering
@@ -64,12 +67,15 @@
 ; CHECK-NEXT:       Function Alias Analysis Results
 ; CHECK-NEXT:       Natural Loop Information
 ; CHECK-NEXT:       Branch Probability Analysis
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       X86 DAG->DAG Instruction Selection
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Local Dynamic TLS Access Clean-up
 ; CHECK-NEXT:       X86 PIC Global Base Reg Initialization
 ; CHECK-NEXT:        Finalize ISel and expand pseudo-instructions
 ; CHECK-NEXT:       X86 Domain Reassignment Pass
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Early Tail Duplication
 ; CHECK-NEXT:       Optimize machine instruction PHIs
 ; CHECK-NEXT:       Slot index numbering
@@ -80,6 +86,7 @@
 ; CHECK-NEXT:       Machine Natural Loop Construction
 ; CHECK-NEXT:       Machine Trace Metrics
 ; CHECK-NEXT:       Early If-Conversion
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine InstCombiner
 ; CHECK-NEXT:       X86 cmov Conversion
 ; CHECK-NEXT:       MachineDominator Tree Construction
@@ -94,6 +101,7 @@
 ; CHECK-NEXT:       Remove dead machine instructions
 ; CHECK-NEXT:       Live Range Shrink
 ; CHECK-NEXT:       X86 Fixup SetCC
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       X86 LEA Optimize
 ; CHECK-NEXT:       X86 Optimize Call Frame
 ; CHECK-NEXT:       X86 Avoid Store Forwarding Block
@@ -139,6 +147,7 @@
 ; CHECK-NEXT:       Shrink Wrapping analysis
 ; CHECK-NEXT:       Prologue/Epilogue Insertion & Frame Finalization
 ; CHECK-NEXT:       Control Flow Optimizer
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Tail Duplication
 ; CHECK-NEXT:       Machine Copy Propagation Pass
 ; CHECK-NEXT:       Post-RA pseudo instruction expansion pass
@@ -157,7 +166,9 @@
 ; CHECK-NEXT:       X86 vzeroupper inserter
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Natural Loop Construction
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       X86 Byte/Word Instruction Fixup
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       X86 Atom pad short functions
 ; CHECK-NEXT:       X86 LEA Fixup
 ; CHECK-NEXT:       Compressing EVEX instrs to VEX encoding when possible