diff --git a/llvm/include/llvm/MC/MCAsmBackend.h b/llvm/include/llvm/MC/MCAsmBackend.h
index 20525a65b7e3..a7d7db834b50 100644
--- a/llvm/include/llvm/MC/MCAsmBackend.h
+++ b/llvm/include/llvm/MC/MCAsmBackend.h
@@ -1,186 +1,189 @@
 //===- llvm/MC/MCAsmBackend.h - MC Asm Backend ------------------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_MC_MCASMBACKEND_H
 #define LLVM_MC_MCASMBACKEND_H
 
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/Optional.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/MC/MCDirectives.h"
 #include "llvm/MC/MCFixup.h"
 #include "llvm/MC/MCFragment.h"
 #include "llvm/Support/Endian.h"
 #include <cstdint>
 
 namespace llvm {
 
 class MCAsmLayout;
 class MCAssembler;
 class MCCFIInstruction;
 struct MCFixupKindInfo;
 class MCFragment;
 class MCInst;
 class MCObjectStreamer;
 class MCObjectTargetWriter;
 class MCObjectWriter;
 class MCRelaxableFragment;
 class MCSubtargetInfo;
 class MCValue;
 class raw_pwrite_stream;
 
 /// Generic interface to target specific assembler backends.
 class MCAsmBackend {
 protected: // Can only create subclasses.
   MCAsmBackend(support::endianness Endian);
 
 public:
   MCAsmBackend(const MCAsmBackend &) = delete;
   MCAsmBackend &operator=(const MCAsmBackend &) = delete;
   virtual ~MCAsmBackend();
 
   const support::endianness Endian;
 
+  virtual void alignBranchesBegin(MCObjectStreamer &OS, const MCInst &Inst) {}
+  virtual void alignBranchesEnd(MCObjectStreamer &OS, const MCInst &Inst) {}
+
   /// lifetime management
   virtual void reset() {}
 
   /// Create a new MCObjectWriter instance for use by the assembler backend to
   /// emit the final object file.
   std::unique_ptr<MCObjectWriter>
   createObjectWriter(raw_pwrite_stream &OS) const;
 
   /// Create an MCObjectWriter that writes two object files: a .o file which is
   /// linked into the final program and a .dwo file which is used by debuggers.
   /// This function is only supported with ELF targets.
   std::unique_ptr<MCObjectWriter>
   createDwoObjectWriter(raw_pwrite_stream &OS, raw_pwrite_stream &DwoOS) const;
 
   virtual std::unique_ptr<MCObjectTargetWriter>
   createObjectTargetWriter() const = 0;
 
   /// \name Target Fixup Interfaces
   /// @{
 
   /// Get the number of target specific fixup kinds.
   virtual unsigned getNumFixupKinds() const = 0;
 
   /// Map a relocation name used in .reloc to a fixup kind.
   virtual Optional<MCFixupKind> getFixupKind(StringRef Name) const;
 
   /// Get information on a fixup kind.
   virtual const MCFixupKindInfo &getFixupKindInfo(MCFixupKind Kind) const;
 
   /// Hook to check if a relocation is needed for some target specific reason.
   virtual bool shouldForceRelocation(const MCAssembler &Asm,
                                      const MCFixup &Fixup,
                                      const MCValue &Target) {
     return false;
   }
 
   /// Hook to check if extra nop bytes must be inserted for alignment directive.
   /// For some targets this may be necessary in order to support linker
   /// relaxation. The number of bytes to insert are returned in Size.
   virtual bool shouldInsertExtraNopBytesForCodeAlign(const MCAlignFragment &AF,
                                                      unsigned &Size) {
     return false;
   }
 
   /// Hook which indicates if the target requires a fixup to be generated when
   /// handling an align directive in an executable section
   virtual bool shouldInsertFixupForCodeAlign(MCAssembler &Asm,
                                              const MCAsmLayout &Layout,
                                              MCAlignFragment &AF) {
     return false;
   }
 
   /// Apply the \p Value for given \p Fixup into the provided data fragment, at
   /// the offset specified by the fixup and following the fixup kind as
   /// appropriate. Errors (such as an out of range fixup value) should be
   /// reported via \p Ctx.
   /// The  \p STI is present only for fragments of type MCRelaxableFragment and
   /// MCDataFragment with hasInstructions() == true.
   virtual void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                           const MCValue &Target, MutableArrayRef<char> Data,
                           uint64_t Value, bool IsResolved,
                           const MCSubtargetInfo *STI) const = 0;
 
   /// Check whether the given target requires emitting differences of two
   /// symbols as a set of relocations.
   virtual bool requiresDiffExpressionRelocations() const { return false; }
 
   /// @}
 
   /// \name Target Relaxation Interfaces
   /// @{
 
   /// Check whether the given instruction may need relaxation.
   ///
   /// \param Inst - The instruction to test.
   /// \param STI - The MCSubtargetInfo in effect when the instruction was
   /// encoded.
   virtual bool mayNeedRelaxation(const MCInst &Inst,
                                  const MCSubtargetInfo &STI) const = 0;
 
   /// Target specific predicate for whether a given fixup requires the
   /// associated instruction to be relaxed.
   virtual bool fixupNeedsRelaxationAdvanced(const MCFixup &Fixup, bool Resolved,
                                             uint64_t Value,
                                             const MCRelaxableFragment *DF,
                                             const MCAsmLayout &Layout,
                                             const bool WasForced) const;
 
   /// Simple predicate for targets where !Resolved implies requiring relaxation
   virtual bool fixupNeedsRelaxation(const MCFixup &Fixup, uint64_t Value,
                                     const MCRelaxableFragment *DF,
                                     const MCAsmLayout &Layout) const = 0;
 
   /// Relax the instruction in the given fragment to the next wider instruction.
   ///
   /// \param Inst The instruction to relax, which may be the same as the
   /// output.
   /// \param STI the subtarget information for the associated instruction.
   /// \param [out] Res On return, the relaxed instruction.
   virtual void relaxInstruction(const MCInst &Inst, const MCSubtargetInfo &STI,
                                 MCInst &Res) const = 0;
 
   /// @}
 
   /// Returns the minimum size of a nop in bytes on this target. The assembler
   /// will use this to emit excess padding in situations where the padding
   /// required for simple alignment would be less than the minimum nop size.
   ///
   virtual unsigned getMinimumNopSize() const { return 1; }
 
   /// Write an (optimal) nop sequence of Count bytes to the given output. If the
   /// target cannot generate such a sequence, it should return an error.
   ///
   /// \return - True on success.
   virtual bool writeNopData(raw_ostream &OS, uint64_t Count) const = 0;
 
   /// Give backend an opportunity to finish layout after relaxation
   virtual void finishLayout(MCAssembler const &Asm,
                             MCAsmLayout &Layout) const {}
 
   /// Handle any target-specific assembler flags. By default, do nothing.
   virtual void handleAssemblerFlag(MCAssemblerFlag Flag) {}
 
   /// Generate the compact unwind encoding for the CFI instructions.
   virtual uint32_t
       generateCompactUnwindEncoding(ArrayRef<MCCFIInstruction>) const {
     return 0;
   }
 
   /// Check whether a given symbol has been flagged with MICROMIPS flag.
   virtual bool isMicroMips(const MCSymbol *Sym) const {
     return false;
   }
 };
 
 } // end namespace llvm
 
 #endif // LLVM_MC_MCASMBACKEND_H
diff --git a/llvm/include/llvm/MC/MCAssembler.h b/llvm/include/llvm/MC/MCAssembler.h
index 3fbeb62c7f8f..8c76f30222e5 100644
--- a/llvm/include/llvm/MC/MCAssembler.h
+++ b/llvm/include/llvm/MC/MCAssembler.h
@@ -1,466 +1,465 @@
 //===- MCAssembler.h - Object File Generation -------------------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_MC_MCASSEMBLER_H
 #define LLVM_MC_MCASSEMBLER_H
 
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/iterator.h"
 #include "llvm/ADT/iterator_range.h"
 #include "llvm/BinaryFormat/MachO.h"
 #include "llvm/MC/MCDirectives.h"
 #include "llvm/MC/MCDwarf.h"
 #include "llvm/MC/MCFixup.h"
 #include "llvm/MC/MCFragment.h"
 #include "llvm/MC/MCLinkerOptimizationHint.h"
 #include "llvm/MC/MCSymbol.h"
 #include "llvm/Support/VersionTuple.h"
 #include <cassert>
 #include <cstddef>
 #include <cstdint>
 #include <string>
 #include <utility>
 #include <vector>
 
 namespace llvm {
 
 class MCAsmBackend;
 class MCAsmLayout;
 class MCContext;
 class MCCodeEmitter;
 class MCFragment;
 class MCObjectWriter;
 class MCSection;
 class MCValue;
 
 // FIXME: This really doesn't belong here. See comments below.
 struct IndirectSymbolData {
   MCSymbol *Symbol;
   MCSection *Section;
 };
 
 // FIXME: Ditto this. Purely so the Streamer and the ObjectWriter can talk
 // to one another.
 struct DataRegionData {
   // This enum should be kept in sync w/ the mach-o definition in
   // llvm/Object/MachOFormat.h.
   enum KindTy { Data = 1, JumpTable8, JumpTable16, JumpTable32 } Kind;
   MCSymbol *Start;
   MCSymbol *End;
 };
 
 class MCAssembler {
   friend class MCAsmLayout;
 
 public:
   using SectionListType = std::vector<MCSection *>;
   using SymbolDataListType = std::vector<const MCSymbol *>;
 
   using const_iterator = pointee_iterator<SectionListType::const_iterator>;
   using iterator = pointee_iterator<SectionListType::iterator>;
 
   using const_symbol_iterator =
       pointee_iterator<SymbolDataListType::const_iterator>;
   using symbol_iterator = pointee_iterator<SymbolDataListType::iterator>;
 
   using symbol_range = iterator_range<symbol_iterator>;
   using const_symbol_range = iterator_range<const_symbol_iterator>;
 
   using const_indirect_symbol_iterator =
       std::vector<IndirectSymbolData>::const_iterator;
   using indirect_symbol_iterator = std::vector<IndirectSymbolData>::iterator;
 
   using const_data_region_iterator =
       std::vector<DataRegionData>::const_iterator;
   using data_region_iterator = std::vector<DataRegionData>::iterator;
 
   /// MachO specific deployment target version info.
   // A Major version of 0 indicates that no version information was supplied
   // and so the corresponding load command should not be emitted.
   using VersionInfoType = struct {
     bool EmitBuildVersion;
     union {
       MCVersionMinType Type;          ///< Used when EmitBuildVersion==false.
       MachO::PlatformType Platform;   ///< Used when EmitBuildVersion==true.
     } TypeOrPlatform;
     unsigned Major;
     unsigned Minor;
     unsigned Update;
     /// An optional version of the SDK that was used to build the source.
     VersionTuple SDKVersion;
   };
 
 private:
   MCContext &Context;
 
   std::unique_ptr<MCAsmBackend> Backend;
 
   std::unique_ptr<MCCodeEmitter> Emitter;
 
   std::unique_ptr<MCObjectWriter> Writer;
 
   SectionListType Sections;
 
   SymbolDataListType Symbols;
 
   std::vector<IndirectSymbolData> IndirectSymbols;
 
   std::vector<DataRegionData> DataRegions;
 
   /// The list of linker options to propagate into the object file.
   std::vector<std::vector<std::string>> LinkerOptions;
 
   /// List of declared file names
   std::vector<std::string> FileNames;
 
   MCDwarfLineTableParams LTParams;
 
   /// The set of function symbols for which a .thumb_func directive has
   /// been seen.
   //
   // FIXME: We really would like this in target specific code rather than
   // here. Maybe when the relocation stuff moves to target specific,
   // this can go with it? The streamer would need some target specific
   // refactoring too.
   mutable SmallPtrSet<const MCSymbol *, 32> ThumbFuncs;
 
   /// The bundle alignment size currently set in the assembler.
   ///
   /// By default it's 0, which means bundling is disabled.
   unsigned BundleAlignSize;
 
   bool RelaxAll : 1;
   bool SubsectionsViaSymbols : 1;
   bool IncrementalLinkerCompatible : 1;
 
   /// ELF specific e_header flags
   // It would be good if there were an MCELFAssembler class to hold this.
   // ELF header flags are used both by the integrated and standalone assemblers.
   // Access to the flags is necessary in cases where assembler directives affect
   // which flags to be set.
   unsigned ELFHeaderEFlags;
 
   /// Used to communicate Linker Optimization Hint information between
   /// the Streamer and the .o writer
   MCLOHContainer LOHContainer;
 
   VersionInfoType VersionInfo;
 
   /// Evaluate a fixup to a relocatable expression and the value which should be
   /// placed into the fixup.
   ///
   /// \param Layout The layout to use for evaluation.
   /// \param Fixup The fixup to evaluate.
   /// \param DF The fragment the fixup is inside.
   /// \param Target [out] On return, the relocatable expression the fixup
   /// evaluates to.
   /// \param Value [out] On return, the value of the fixup as currently laid
   /// out.
   /// \param WasForced [out] On return, the value in the fixup is set to the
   /// correct value if WasForced is true, even if evaluateFixup returns false.
   /// \return Whether the fixup value was fully resolved. This is true if the
   /// \p Value result is fixed, otherwise the value may change due to
   /// relocation.
   bool evaluateFixup(const MCAsmLayout &Layout, const MCFixup &Fixup,
                      const MCFragment *DF, MCValue &Target,
                      uint64_t &Value, bool &WasForced) const;
 
   /// Check whether a fixup can be satisfied, or whether it needs to be relaxed
   /// (increased in size, in order to hold its value correctly).
   bool fixupNeedsRelaxation(const MCFixup &Fixup, const MCRelaxableFragment *DF,
                             const MCAsmLayout &Layout) const;
 
   /// Check whether the given fragment needs relaxation.
   bool fragmentNeedsRelaxation(const MCRelaxableFragment *IF,
                                const MCAsmLayout &Layout) const;
 
   /// Perform one layout iteration and return true if any offsets
   /// were adjusted.
   bool layoutOnce(MCAsmLayout &Layout);
 
   /// Perform one layout iteration of the given section and return true
   /// if any offsets were adjusted.
   bool layoutSectionOnce(MCAsmLayout &Layout, MCSection &Sec);
 
   bool relaxInstruction(MCAsmLayout &Layout, MCRelaxableFragment &IF);
-
   bool relaxLEB(MCAsmLayout &Layout, MCLEBFragment &IF);
-
+  bool relaxBoundaryAlign(MCAsmLayout &Layout, MCBoundaryAlignFragment &BF);
   bool relaxDwarfLineAddr(MCAsmLayout &Layout, MCDwarfLineAddrFragment &DF);
   bool relaxDwarfCallFrameFragment(MCAsmLayout &Layout,
                                    MCDwarfCallFrameFragment &DF);
   bool relaxCVInlineLineTable(MCAsmLayout &Layout,
                               MCCVInlineLineTableFragment &DF);
   bool relaxCVDefRange(MCAsmLayout &Layout, MCCVDefRangeFragment &DF);
 
   /// finishLayout - Finalize a layout, including fragment lowering.
   void finishLayout(MCAsmLayout &Layout);
 
   std::tuple<MCValue, uint64_t, bool>
   handleFixup(const MCAsmLayout &Layout, MCFragment &F, const MCFixup &Fixup);
 
 public:
   std::vector<std::pair<StringRef, const MCSymbol *>> Symvers;
 
   /// Construct a new assembler instance.
   //
   // FIXME: How are we going to parameterize this? Two obvious options are stay
   // concrete and require clients to pass in a target like object. The other
   // option is to make this abstract, and have targets provide concrete
   // implementations as we do with AsmParser.
   MCAssembler(MCContext &Context, std::unique_ptr<MCAsmBackend> Backend,
               std::unique_ptr<MCCodeEmitter> Emitter,
               std::unique_ptr<MCObjectWriter> Writer);
   MCAssembler(const MCAssembler &) = delete;
   MCAssembler &operator=(const MCAssembler &) = delete;
   ~MCAssembler();
 
   /// Compute the effective fragment size assuming it is laid out at the given
   /// \p SectionAddress and \p FragmentOffset.
   uint64_t computeFragmentSize(const MCAsmLayout &Layout,
                                const MCFragment &F) const;
 
   /// Find the symbol which defines the atom containing the given symbol, or
   /// null if there is no such symbol.
   const MCSymbol *getAtom(const MCSymbol &S) const;
 
   /// Check whether a particular symbol is visible to the linker and is required
   /// in the symbol table, or whether it can be discarded by the assembler. This
   /// also effects whether the assembler treats the label as potentially
   /// defining a separate atom.
   bool isSymbolLinkerVisible(const MCSymbol &SD) const;
 
   /// Emit the section contents to \p OS.
   void writeSectionData(raw_ostream &OS, const MCSection *Section,
                         const MCAsmLayout &Layout) const;
 
   /// Check whether a given symbol has been flagged with .thumb_func.
   bool isThumbFunc(const MCSymbol *Func) const;
 
   /// Flag a function symbol as the target of a .thumb_func directive.
   void setIsThumbFunc(const MCSymbol *Func) { ThumbFuncs.insert(Func); }
 
   /// ELF e_header flags
   unsigned getELFHeaderEFlags() const { return ELFHeaderEFlags; }
   void setELFHeaderEFlags(unsigned Flags) { ELFHeaderEFlags = Flags; }
 
   /// MachO deployment target version information.
   const VersionInfoType &getVersionInfo() const { return VersionInfo; }
   void setVersionMin(MCVersionMinType Type, unsigned Major, unsigned Minor,
                      unsigned Update,
                      VersionTuple SDKVersion = VersionTuple()) {
     VersionInfo.EmitBuildVersion = false;
     VersionInfo.TypeOrPlatform.Type = Type;
     VersionInfo.Major = Major;
     VersionInfo.Minor = Minor;
     VersionInfo.Update = Update;
     VersionInfo.SDKVersion = SDKVersion;
   }
   void setBuildVersion(MachO::PlatformType Platform, unsigned Major,
                        unsigned Minor, unsigned Update,
                        VersionTuple SDKVersion = VersionTuple()) {
     VersionInfo.EmitBuildVersion = true;
     VersionInfo.TypeOrPlatform.Platform = Platform;
     VersionInfo.Major = Major;
     VersionInfo.Minor = Minor;
     VersionInfo.Update = Update;
     VersionInfo.SDKVersion = SDKVersion;
   }
 
   /// Reuse an assembler instance
   ///
   void reset();
 
   MCContext &getContext() const { return Context; }
 
   MCAsmBackend *getBackendPtr() const { return Backend.get(); }
 
   MCCodeEmitter *getEmitterPtr() const { return Emitter.get(); }
 
   MCObjectWriter *getWriterPtr() const { return Writer.get(); }
 
   MCAsmBackend &getBackend() const { return *Backend; }
 
   MCCodeEmitter &getEmitter() const { return *Emitter; }
 
   MCObjectWriter &getWriter() const { return *Writer; }
 
   MCDwarfLineTableParams getDWARFLinetableParams() const { return LTParams; }
   void setDWARFLinetableParams(MCDwarfLineTableParams P) { LTParams = P; }
 
   /// Finish - Do final processing and write the object to the output stream.
   /// \p Writer is used for custom object writer (as the MCJIT does),
   /// if not specified it is automatically created from backend.
   void Finish();
 
   // Layout all section and prepare them for emission.
   void layout(MCAsmLayout &Layout);
 
   // FIXME: This does not belong here.
   bool getSubsectionsViaSymbols() const { return SubsectionsViaSymbols; }
   void setSubsectionsViaSymbols(bool Value) { SubsectionsViaSymbols = Value; }
 
   bool isIncrementalLinkerCompatible() const {
     return IncrementalLinkerCompatible;
   }
   void setIncrementalLinkerCompatible(bool Value) {
     IncrementalLinkerCompatible = Value;
   }
 
   bool getRelaxAll() const { return RelaxAll; }
   void setRelaxAll(bool Value) { RelaxAll = Value; }
 
   bool isBundlingEnabled() const { return BundleAlignSize != 0; }
 
   unsigned getBundleAlignSize() const { return BundleAlignSize; }
 
   void setBundleAlignSize(unsigned Size) {
     assert((Size == 0 || !(Size & (Size - 1))) &&
            "Expect a power-of-two bundle align size");
     BundleAlignSize = Size;
   }
 
   /// \name Section List Access
   /// @{
 
   iterator begin() { return Sections.begin(); }
   const_iterator begin() const { return Sections.begin(); }
 
   iterator end() { return Sections.end(); }
   const_iterator end() const { return Sections.end(); }
 
   size_t size() const { return Sections.size(); }
 
   /// @}
   /// \name Symbol List Access
   /// @{
   symbol_iterator symbol_begin() { return Symbols.begin(); }
   const_symbol_iterator symbol_begin() const { return Symbols.begin(); }
 
   symbol_iterator symbol_end() { return Symbols.end(); }
   const_symbol_iterator symbol_end() const { return Symbols.end(); }
 
   symbol_range symbols() { return make_range(symbol_begin(), symbol_end()); }
   const_symbol_range symbols() const {
     return make_range(symbol_begin(), symbol_end());
   }
 
   size_t symbol_size() const { return Symbols.size(); }
 
   /// @}
   /// \name Indirect Symbol List Access
   /// @{
 
   // FIXME: This is a total hack, this should not be here. Once things are
   // factored so that the streamer has direct access to the .o writer, it can
   // disappear.
   std::vector<IndirectSymbolData> &getIndirectSymbols() {
     return IndirectSymbols;
   }
 
   indirect_symbol_iterator indirect_symbol_begin() {
     return IndirectSymbols.begin();
   }
   const_indirect_symbol_iterator indirect_symbol_begin() const {
     return IndirectSymbols.begin();
   }
 
   indirect_symbol_iterator indirect_symbol_end() {
     return IndirectSymbols.end();
   }
   const_indirect_symbol_iterator indirect_symbol_end() const {
     return IndirectSymbols.end();
   }
 
   size_t indirect_symbol_size() const { return IndirectSymbols.size(); }
 
   /// @}
   /// \name Linker Option List Access
   /// @{
 
   std::vector<std::vector<std::string>> &getLinkerOptions() {
     return LinkerOptions;
   }
 
   /// @}
   /// \name Data Region List Access
   /// @{
 
   // FIXME: This is a total hack, this should not be here. Once things are
   // factored so that the streamer has direct access to the .o writer, it can
   // disappear.
   std::vector<DataRegionData> &getDataRegions() { return DataRegions; }
 
   data_region_iterator data_region_begin() { return DataRegions.begin(); }
   const_data_region_iterator data_region_begin() const {
     return DataRegions.begin();
   }
 
   data_region_iterator data_region_end() { return DataRegions.end(); }
   const_data_region_iterator data_region_end() const {
     return DataRegions.end();
   }
 
   size_t data_region_size() const { return DataRegions.size(); }
 
   /// @}
   /// \name Data Region List Access
   /// @{
 
   // FIXME: This is a total hack, this should not be here. Once things are
   // factored so that the streamer has direct access to the .o writer, it can
   // disappear.
   MCLOHContainer &getLOHContainer() { return LOHContainer; }
   const MCLOHContainer &getLOHContainer() const {
     return const_cast<MCAssembler *>(this)->getLOHContainer();
   }
 
   struct CGProfileEntry {
     const MCSymbolRefExpr *From;
     const MCSymbolRefExpr *To;
     uint64_t Count;
   };
   std::vector<CGProfileEntry> CGProfile;
   /// @}
   /// \name Backend Data Access
   /// @{
 
   bool registerSection(MCSection &Section);
 
   void registerSymbol(const MCSymbol &Symbol, bool *Created = nullptr);
 
   ArrayRef<std::string> getFileNames() { return FileNames; }
 
   void addFileName(StringRef FileName) {
     if (!is_contained(FileNames, FileName))
       FileNames.push_back(FileName);
   }
 
   /// Write the necessary bundle padding to \p OS.
   /// Expects a fragment \p F containing instructions and its size \p FSize.
   void writeFragmentPadding(raw_ostream &OS, const MCEncodedFragment &F,
                             uint64_t FSize) const;
 
   /// @}
 
   void dump() const;
 };
 
 /// Compute the amount of padding required before the fragment \p F to
 /// obey bundling restrictions, where \p FOffset is the fragment's offset in
 /// its section and \p FSize is the fragment's size.
 uint64_t computeBundlePadding(const MCAssembler &Assembler,
                               const MCEncodedFragment *F, uint64_t FOffset,
                               uint64_t FSize);
 
 } // end namespace llvm
 
 #endif // LLVM_MC_MCASSEMBLER_H
diff --git a/llvm/include/llvm/MC/MCFragment.h b/llvm/include/llvm/MC/MCFragment.h
index 46f40ae7aba3..5e3d5b783365 100644
--- a/llvm/include/llvm/MC/MCFragment.h
+++ b/llvm/include/llvm/MC/MCFragment.h
@@ -1,568 +1,613 @@
 //===- MCFragment.h - Fragment type hierarchy -------------------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_MC_MCFRAGMENT_H
 #define LLVM_MC_MCFRAGMENT_H
 
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/ilist_node.h"
 #include "llvm/MC/MCFixup.h"
 #include "llvm/MC/MCInst.h"
+#include "llvm/Support/Alignment.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/SMLoc.h"
 #include <cstdint>
 #include <utility>
 
 namespace llvm {
 
 class MCSection;
 class MCSubtargetInfo;
 class MCSymbol;
 
 class MCFragment : public ilist_node_with_parent<MCFragment, MCSection> {
   friend class MCAsmLayout;
 
 public:
   enum FragmentType : uint8_t {
     FT_Align,
     FT_Data,
     FT_CompactEncodedInst,
     FT_Fill,
     FT_Relaxable,
     FT_Org,
     FT_Dwarf,
     FT_DwarfFrame,
     FT_LEB,
+    FT_BoundaryAlign,
     FT_SymbolId,
     FT_CVInlineLines,
     FT_CVDefRange,
     FT_Dummy
   };
 
 private:
   FragmentType Kind;
 
 protected:
   bool HasInstructions;
 
 private:
   /// LayoutOrder - The layout order of this fragment.
   unsigned LayoutOrder;
 
   /// The data for the section this fragment is in.
   MCSection *Parent;
 
   /// Atom - The atom this fragment is in, as represented by its defining
   /// symbol.
   const MCSymbol *Atom;
 
   /// \name Assembler Backend Data
   /// @{
   //
   // FIXME: This could all be kept private to the assembler implementation.
 
   /// Offset - The offset of this fragment in its section. This is ~0 until
   /// initialized.
   uint64_t Offset;
 
   /// @}
 
 protected:
   MCFragment(FragmentType Kind, bool HasInstructions,
              MCSection *Parent = nullptr);
 
 public:
   MCFragment() = delete;
   MCFragment(const MCFragment &) = delete;
   MCFragment &operator=(const MCFragment &) = delete;
 
   /// Destroys the current fragment.
   ///
   /// This must be used instead of delete as MCFragment is non-virtual.
   /// This method will dispatch to the appropriate subclass.
   void destroy();
 
   FragmentType getKind() const { return Kind; }
 
   MCSection *getParent() const { return Parent; }
   void setParent(MCSection *Value) { Parent = Value; }
 
   const MCSymbol *getAtom() const { return Atom; }
   void setAtom(const MCSymbol *Value) { Atom = Value; }
 
   unsigned getLayoutOrder() const { return LayoutOrder; }
   void setLayoutOrder(unsigned Value) { LayoutOrder = Value; }
 
   /// Does this fragment have instructions emitted into it? By default
   /// this is false, but specific fragment types may set it to true.
   bool hasInstructions() const { return HasInstructions; }
 
   /// Return true if given frgment has FT_Dummy type.
   bool isDummy() const { return Kind == FT_Dummy; }
 
   void dump() const;
 };
 
 class MCDummyFragment : public MCFragment {
 public:
   explicit MCDummyFragment(MCSection *Sec) : MCFragment(FT_Dummy, false, Sec) {}
 
   static bool classof(const MCFragment *F) { return F->getKind() == FT_Dummy; }
 };
 
 /// Interface implemented by fragments that contain encoded instructions and/or
 /// data.
 ///
 class MCEncodedFragment : public MCFragment {
   /// Should this fragment be aligned to the end of a bundle?
   bool AlignToBundleEnd = false;
 
   uint8_t BundlePadding = 0;
 
 protected:
   MCEncodedFragment(MCFragment::FragmentType FType, bool HasInstructions,
                     MCSection *Sec)
       : MCFragment(FType, HasInstructions, Sec) {}
 
   /// STI - The MCSubtargetInfo in effect when the instruction was encoded.
   /// must be non-null for instructions.
   const MCSubtargetInfo *STI = nullptr;
 
 public:
   static bool classof(const MCFragment *F) {
     MCFragment::FragmentType Kind = F->getKind();
     switch (Kind) {
     default:
       return false;
     case MCFragment::FT_Relaxable:
     case MCFragment::FT_CompactEncodedInst:
     case MCFragment::FT_Data:
     case MCFragment::FT_Dwarf:
     case MCFragment::FT_DwarfFrame:
       return true;
     }
   }
 
   /// Should this fragment be placed at the end of an aligned bundle?
   bool alignToBundleEnd() const { return AlignToBundleEnd; }
   void setAlignToBundleEnd(bool V) { AlignToBundleEnd = V; }
 
   /// Get the padding size that must be inserted before this fragment.
   /// Used for bundling. By default, no padding is inserted.
   /// Note that padding size is restricted to 8 bits. This is an optimization
   /// to reduce the amount of space used for each fragment. In practice, larger
   /// padding should never be required.
   uint8_t getBundlePadding() const { return BundlePadding; }
 
   /// Set the padding size for this fragment. By default it's a no-op,
   /// and only some fragments have a meaningful implementation.
   void setBundlePadding(uint8_t N) { BundlePadding = N; }
 
   /// Retrieve the MCSubTargetInfo in effect when the instruction was encoded.
   /// Guaranteed to be non-null if hasInstructions() == true
   const MCSubtargetInfo *getSubtargetInfo() const { return STI; }
 
   /// Record that the fragment contains instructions with the MCSubtargetInfo in
   /// effect when the instruction was encoded.
   void setHasInstructions(const MCSubtargetInfo &STI) {
     HasInstructions = true;
     this->STI = &STI;
   }
 };
 
 /// Interface implemented by fragments that contain encoded instructions and/or
 /// data.
 ///
 template<unsigned ContentsSize>
 class MCEncodedFragmentWithContents : public MCEncodedFragment {
   SmallVector<char, ContentsSize> Contents;
 
 protected:
   MCEncodedFragmentWithContents(MCFragment::FragmentType FType,
                                 bool HasInstructions,
                                 MCSection *Sec)
       : MCEncodedFragment(FType, HasInstructions, Sec) {}
 
 public:
   SmallVectorImpl<char> &getContents() { return Contents; }
   const SmallVectorImpl<char> &getContents() const { return Contents; }
 };
 
 /// Interface implemented by fragments that contain encoded instructions and/or
 /// data and also have fixups registered.
 ///
 template<unsigned ContentsSize, unsigned FixupsSize>
 class MCEncodedFragmentWithFixups :
   public MCEncodedFragmentWithContents<ContentsSize> {
 
   /// Fixups - The list of fixups in this fragment.
   SmallVector<MCFixup, FixupsSize> Fixups;
 
 protected:
   MCEncodedFragmentWithFixups(MCFragment::FragmentType FType,
                               bool HasInstructions,
                               MCSection *Sec)
       : MCEncodedFragmentWithContents<ContentsSize>(FType, HasInstructions,
                                                     Sec) {}
 
 public:
 
   using const_fixup_iterator = SmallVectorImpl<MCFixup>::const_iterator;
   using fixup_iterator = SmallVectorImpl<MCFixup>::iterator;
 
   SmallVectorImpl<MCFixup> &getFixups() { return Fixups; }
   const SmallVectorImpl<MCFixup> &getFixups() const { return Fixups; }
 
   fixup_iterator fixup_begin() { return Fixups.begin(); }
   const_fixup_iterator fixup_begin() const { return Fixups.begin(); }
 
   fixup_iterator fixup_end() { return Fixups.end(); }
   const_fixup_iterator fixup_end() const { return Fixups.end(); }
 
   static bool classof(const MCFragment *F) {
     MCFragment::FragmentType Kind = F->getKind();
     return Kind == MCFragment::FT_Relaxable || Kind == MCFragment::FT_Data ||
            Kind == MCFragment::FT_CVDefRange || Kind == MCFragment::FT_Dwarf ||
            Kind == MCFragment::FT_DwarfFrame;
   }
 };
 
 /// Fragment for data and encoded instructions.
 ///
 class MCDataFragment : public MCEncodedFragmentWithFixups<32, 4> {
 public:
   MCDataFragment(MCSection *Sec = nullptr)
       : MCEncodedFragmentWithFixups<32, 4>(FT_Data, false, Sec) {}
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_Data;
   }
 };
 
 /// This is a compact (memory-size-wise) fragment for holding an encoded
 /// instruction (non-relaxable) that has no fixups registered. When applicable,
 /// it can be used instead of MCDataFragment and lead to lower memory
 /// consumption.
 ///
 class MCCompactEncodedInstFragment : public MCEncodedFragmentWithContents<4> {
 public:
   MCCompactEncodedInstFragment(MCSection *Sec = nullptr)
       : MCEncodedFragmentWithContents(FT_CompactEncodedInst, true, Sec) {
   }
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_CompactEncodedInst;
   }
 };
 
 /// A relaxable fragment holds on to its MCInst, since it may need to be
 /// relaxed during the assembler layout and relaxation stage.
 ///
 class MCRelaxableFragment : public MCEncodedFragmentWithFixups<8, 1> {
 
   /// Inst - The instruction this is a fragment for.
   MCInst Inst;
 
 public:
   MCRelaxableFragment(const MCInst &Inst, const MCSubtargetInfo &STI,
                       MCSection *Sec = nullptr)
       : MCEncodedFragmentWithFixups(FT_Relaxable, true, Sec),
         Inst(Inst) { this->STI = &STI; }
 
   const MCInst &getInst() const { return Inst; }
   void setInst(const MCInst &Value) { Inst = Value; }
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_Relaxable;
   }
 };
 
 class MCAlignFragment : public MCFragment {
   /// Alignment - The alignment to ensure, in bytes.
   unsigned Alignment;
 
   /// EmitNops - Flag to indicate that (optimal) NOPs should be emitted instead
   /// of using the provided value. The exact interpretation of this flag is
   /// target dependent.
   bool EmitNops : 1;
 
   /// Value - Value to use for filling padding bytes.
   int64_t Value;
 
   /// ValueSize - The size of the integer (in bytes) of \p Value.
   unsigned ValueSize;
 
   /// MaxBytesToEmit - The maximum number of bytes to emit; if the alignment
   /// cannot be satisfied in this width then this fragment is ignored.
   unsigned MaxBytesToEmit;
 
 public:
   MCAlignFragment(unsigned Alignment, int64_t Value, unsigned ValueSize,
                   unsigned MaxBytesToEmit, MCSection *Sec = nullptr)
       : MCFragment(FT_Align, false, Sec), Alignment(Alignment), EmitNops(false),
         Value(Value), ValueSize(ValueSize), MaxBytesToEmit(MaxBytesToEmit) {}
 
   /// \name Accessors
   /// @{
 
   unsigned getAlignment() const { return Alignment; }
 
   int64_t getValue() const { return Value; }
 
   unsigned getValueSize() const { return ValueSize; }
 
   unsigned getMaxBytesToEmit() const { return MaxBytesToEmit; }
 
   bool hasEmitNops() const { return EmitNops; }
   void setEmitNops(bool Value) { EmitNops = Value; }
 
   /// @}
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_Align;
   }
 };
 
 class MCFillFragment : public MCFragment {
   /// Value to use for filling bytes.
   uint64_t Value;
   uint8_t ValueSize;
   /// The number of bytes to insert.
   const MCExpr &NumValues;
 
   /// Source location of the directive that this fragment was created for.
   SMLoc Loc;
 
 public:
   MCFillFragment(uint64_t Value, uint8_t VSize, const MCExpr &NumValues,
                  SMLoc Loc, MCSection *Sec = nullptr)
       : MCFragment(FT_Fill, false, Sec), Value(Value), ValueSize(VSize),
         NumValues(NumValues), Loc(Loc) {}
 
   uint64_t getValue() const { return Value; }
   uint8_t getValueSize() const { return ValueSize; }
   const MCExpr &getNumValues() const { return NumValues; }
 
   SMLoc getLoc() const { return Loc; }
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_Fill;
   }
 };
 
 class MCOrgFragment : public MCFragment {
   /// The offset this fragment should start at.
   const MCExpr *Offset;
 
   /// Value to use for filling bytes.
   int8_t Value;
 
   /// Source location of the directive that this fragment was created for.
   SMLoc Loc;
 
 public:
   MCOrgFragment(const MCExpr &Offset, int8_t Value, SMLoc Loc,
                 MCSection *Sec = nullptr)
       : MCFragment(FT_Org, false, Sec), Offset(&Offset), Value(Value), Loc(Loc) {}
 
   /// \name Accessors
   /// @{
 
   const MCExpr &getOffset() const { return *Offset; }
 
   uint8_t getValue() const { return Value; }
 
   SMLoc getLoc() const { return Loc; }
 
   /// @}
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_Org;
   }
 };
 
 class MCLEBFragment : public MCFragment {
   /// Value - The value this fragment should contain.
   const MCExpr *Value;
 
   /// IsSigned - True if this is a sleb128, false if uleb128.
   bool IsSigned;
 
   SmallString<8> Contents;
 
 public:
   MCLEBFragment(const MCExpr &Value_, bool IsSigned_, MCSection *Sec = nullptr)
       : MCFragment(FT_LEB, false, Sec), Value(&Value_), IsSigned(IsSigned_) {
     Contents.push_back(0);
   }
 
   /// \name Accessors
   /// @{
 
   const MCExpr &getValue() const { return *Value; }
 
   bool isSigned() const { return IsSigned; }
 
   SmallString<8> &getContents() { return Contents; }
   const SmallString<8> &getContents() const { return Contents; }
 
   /// @}
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_LEB;
   }
 };
 
 class MCDwarfLineAddrFragment : public MCEncodedFragmentWithFixups<8, 1> {
   /// LineDelta - the value of the difference between the two line numbers
   /// between two .loc dwarf directives.
   int64_t LineDelta;
 
   /// AddrDelta - The expression for the difference of the two symbols that
   /// make up the address delta between two .loc dwarf directives.
   const MCExpr *AddrDelta;
 
 public:
   MCDwarfLineAddrFragment(int64_t LineDelta, const MCExpr &AddrDelta,
                           MCSection *Sec = nullptr)
       : MCEncodedFragmentWithFixups<8, 1>(FT_Dwarf, false, Sec),
         LineDelta(LineDelta), AddrDelta(&AddrDelta) {}
 
   /// \name Accessors
   /// @{
 
   int64_t getLineDelta() const { return LineDelta; }
 
   const MCExpr &getAddrDelta() const { return *AddrDelta; }
 
   /// @}
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_Dwarf;
   }
 };
 
 class MCDwarfCallFrameFragment : public MCEncodedFragmentWithFixups<8, 1> {
   /// AddrDelta - The expression for the difference of the two symbols that
   /// make up the address delta between two .cfi_* dwarf directives.
   const MCExpr *AddrDelta;
 
 public:
   MCDwarfCallFrameFragment(const MCExpr &AddrDelta, MCSection *Sec = nullptr)
       : MCEncodedFragmentWithFixups<8, 1>(FT_DwarfFrame, false, Sec),
         AddrDelta(&AddrDelta) {}
 
   /// \name Accessors
   /// @{
 
   const MCExpr &getAddrDelta() const { return *AddrDelta; }
 
   /// @}
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_DwarfFrame;
   }
 };
 
 /// Represents a symbol table index fragment.
 class MCSymbolIdFragment : public MCFragment {
   const MCSymbol *Sym;
 
 public:
   MCSymbolIdFragment(const MCSymbol *Sym, MCSection *Sec = nullptr)
       : MCFragment(FT_SymbolId, false, Sec), Sym(Sym) {}
 
   /// \name Accessors
   /// @{
 
   const MCSymbol *getSymbol() { return Sym; }
   const MCSymbol *getSymbol() const { return Sym; }
 
   /// @}
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_SymbolId;
   }
 };
 
 /// Fragment representing the binary annotations produced by the
 /// .cv_inline_linetable directive.
 class MCCVInlineLineTableFragment : public MCFragment {
   unsigned SiteFuncId;
   unsigned StartFileId;
   unsigned StartLineNum;
   const MCSymbol *FnStartSym;
   const MCSymbol *FnEndSym;
   SmallString<8> Contents;
 
   /// CodeViewContext has the real knowledge about this format, so let it access
   /// our members.
   friend class CodeViewContext;
 
 public:
   MCCVInlineLineTableFragment(unsigned SiteFuncId, unsigned StartFileId,
                               unsigned StartLineNum, const MCSymbol *FnStartSym,
                               const MCSymbol *FnEndSym,
                               MCSection *Sec = nullptr)
       : MCFragment(FT_CVInlineLines, false, Sec), SiteFuncId(SiteFuncId),
         StartFileId(StartFileId), StartLineNum(StartLineNum),
         FnStartSym(FnStartSym), FnEndSym(FnEndSym) {}
 
   /// \name Accessors
   /// @{
 
   const MCSymbol *getFnStartSym() const { return FnStartSym; }
   const MCSymbol *getFnEndSym() const { return FnEndSym; }
 
   SmallString<8> &getContents() { return Contents; }
   const SmallString<8> &getContents() const { return Contents; }
 
   /// @}
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_CVInlineLines;
   }
 };
 
 /// Fragment representing the .cv_def_range directive.
 class MCCVDefRangeFragment : public MCEncodedFragmentWithFixups<32, 4> {
   SmallVector<std::pair<const MCSymbol *, const MCSymbol *>, 2> Ranges;
   SmallString<32> FixedSizePortion;
 
   /// CodeViewContext has the real knowledge about this format, so let it access
   /// our members.
   friend class CodeViewContext;
 
 public:
   MCCVDefRangeFragment(
       ArrayRef<std::pair<const MCSymbol *, const MCSymbol *>> Ranges,
       StringRef FixedSizePortion, MCSection *Sec = nullptr)
       : MCEncodedFragmentWithFixups<32, 4>(FT_CVDefRange, false, Sec),
         Ranges(Ranges.begin(), Ranges.end()),
         FixedSizePortion(FixedSizePortion) {}
 
   /// \name Accessors
   /// @{
   ArrayRef<std::pair<const MCSymbol *, const MCSymbol *>> getRanges() const {
     return Ranges;
   }
 
   StringRef getFixedSizePortion() const { return FixedSizePortion; }
   /// @}
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_CVDefRange;
   }
 };
 
+class MCBoundaryAlignFragment : public MCFragment {
+private:
+  /// The size of the MCBoundaryAlignFragment.
+  /// Note: The size is lazily set during relaxation, and is not meaningful
+  /// before that.
+  uint64_t Size = 0;
+  /// The alignment requirement of the branch to be aligned.
+  Align AlignBoundary;
+  /// Flag to indicate whether the branch is fused.
+  bool Fused : 1;
+  /// Flag to indicate whether NOPs should be emitted.
+  bool EmitNops : 1;
+
+public:
+  MCBoundaryAlignFragment(Align AlignBoundary, bool Fused = false,
+                          bool EmitNops = false, MCSection *Sec = nullptr)
+      : MCFragment(FT_BoundaryAlign, false, Sec), AlignBoundary(AlignBoundary),
+        Fused(Fused), EmitNops(EmitNops) {}
+
+  /// \name Accessors
+  /// @{
+
+  Align getAlignment() const { return AlignBoundary; }
+
+  uint64_t getSize() const { return Size; }
+
+  bool canEmitNops() const { return EmitNops; }
+
+  bool isFused() const { return Fused; }
+
+  void setFused(bool Value) { Fused = Value; }
+
+  void setEmitNops(bool Value) { EmitNops = Value; }
+
+  void setSize(uint64_t Value) { Size = Value; }
+
+  /// @}
+  //
+
+  static bool classof(const MCFragment *F) {
+    return F->getKind() == MCFragment::FT_BoundaryAlign;
+  }
+};
 } // end namespace llvm
 
 #endif // LLVM_MC_MCFRAGMENT_H
diff --git a/llvm/include/llvm/MC/MCObjectStreamer.h b/llvm/include/llvm/MC/MCObjectStreamer.h
index d8ea75a0ee7c..9e3f87565e26 100644
--- a/llvm/include/llvm/MC/MCObjectStreamer.h
+++ b/llvm/include/llvm/MC/MCObjectStreamer.h
@@ -1,208 +1,209 @@
 //===- MCObjectStreamer.h - MCStreamer Object File Interface ----*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_MC_MCOBJECTSTREAMER_H
 #define LLVM_MC_MCOBJECTSTREAMER_H
 
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCSection.h"
 #include "llvm/MC/MCStreamer.h"
 
 namespace llvm {
 class MCAssembler;
 class MCCodeEmitter;
 class MCSubtargetInfo;
 class MCExpr;
 class MCFragment;
 class MCDataFragment;
 class MCAsmBackend;
 class raw_ostream;
 class raw_pwrite_stream;
 
 /// Streaming object file generation interface.
 ///
 /// This class provides an implementation of the MCStreamer interface which is
 /// suitable for use with the assembler backend. Specific object file formats
 /// are expected to subclass this interface to implement directives specific
 /// to that file format or custom semantics expected by the object writer
 /// implementation.
 class MCObjectStreamer : public MCStreamer {
   std::unique_ptr<MCAssembler> Assembler;
   MCSection::iterator CurInsertionPoint;
   bool EmitEHFrame;
   bool EmitDebugFrame;
   SmallVector<MCSymbol *, 2> PendingLabels;
   SmallVector<MCSection*, 2> PendingLabelSections;
   unsigned CurSubsectionIdx;
   struct PendingMCFixup {
     const MCSymbol *Sym;
     MCFixup Fixup;
     MCDataFragment *DF;
     PendingMCFixup(const MCSymbol *McSym, MCDataFragment *F, MCFixup McFixup)
         : Sym(McSym), Fixup(McFixup), DF(F) {}
   };
   SmallVector<PendingMCFixup, 2> PendingFixups;
 
   virtual void EmitInstToData(const MCInst &Inst, const MCSubtargetInfo&) = 0;
   void EmitCFIStartProcImpl(MCDwarfFrameInfo &Frame) override;
   void EmitCFIEndProcImpl(MCDwarfFrameInfo &Frame) override;
   MCSymbol *EmitCFILabel() override;
+  void EmitInstructionImpl(const MCInst &Inst, const MCSubtargetInfo &STI);
   void resolvePendingFixups();
 
 protected:
   MCObjectStreamer(MCContext &Context, std::unique_ptr<MCAsmBackend> TAB,
                    std::unique_ptr<MCObjectWriter> OW,
                    std::unique_ptr<MCCodeEmitter> Emitter);
   ~MCObjectStreamer();
 
 public:
   /// state management
   void reset() override;
 
   /// Object streamers require the integrated assembler.
   bool isIntegratedAssemblerRequired() const override { return true; }
 
   void EmitFrames(MCAsmBackend *MAB);
   void EmitCFISections(bool EH, bool Debug) override;
 
   MCFragment *getCurrentFragment() const;
 
   void insert(MCFragment *F) {
     flushPendingLabels(F);
     MCSection *CurSection = getCurrentSectionOnly();
     CurSection->getFragmentList().insert(CurInsertionPoint, F);
     F->setParent(CurSection);
   }
 
   /// Get a data fragment to write into, creating a new one if the current
   /// fragment is not a data fragment.
   /// Optionally a \p STI can be passed in so that a new fragment is created
   /// if the Subtarget differs from the current fragment.
   MCDataFragment *getOrCreateDataFragment(const MCSubtargetInfo* STI = nullptr);
 
 protected:
   bool changeSectionImpl(MCSection *Section, const MCExpr *Subsection);
 
   /// Assign a label to the current Section and Subsection even though a
   /// fragment is not yet present. Use flushPendingLabels(F) to associate
   /// a fragment with this label.
   void addPendingLabel(MCSymbol* label);
 
   /// If any labels have been emitted but not assigned fragments in the current
   /// Section and Subsection, ensure that they get assigned, either to fragment
   /// F if possible or to a new data fragment. Optionally, one can provide an
   /// offset \p FOffset as a symbol offset within the fragment.
   void flushPendingLabels(MCFragment *F, uint64_t FOffset = 0);
 
 public:
   void visitUsedSymbol(const MCSymbol &Sym) override;
 
   /// Create a data fragment for any pending labels across all Sections
   /// and Subsections.
   void flushPendingLabels();
 
   MCAssembler &getAssembler() { return *Assembler; }
   MCAssembler *getAssemblerPtr() override;
   /// \name MCStreamer Interface
   /// @{
 
   void EmitLabel(MCSymbol *Symbol, SMLoc Loc = SMLoc()) override;
   virtual void EmitLabelAtPos(MCSymbol *Symbol, SMLoc Loc, MCFragment *F,
                               uint64_t Offset);
   void EmitAssignment(MCSymbol *Symbol, const MCExpr *Value) override;
   void EmitValueImpl(const MCExpr *Value, unsigned Size,
                      SMLoc Loc = SMLoc()) override;
   void EmitULEB128Value(const MCExpr *Value) override;
   void EmitSLEB128Value(const MCExpr *Value) override;
   void EmitWeakReference(MCSymbol *Alias, const MCSymbol *Symbol) override;
   void ChangeSection(MCSection *Section, const MCExpr *Subsection) override;
   void EmitInstruction(const MCInst &Inst, const MCSubtargetInfo &STI) override;
 
   /// Emit an instruction to a special fragment, because this instruction
   /// can change its size during relaxation.
   virtual void EmitInstToFragment(const MCInst &Inst, const MCSubtargetInfo &);
 
   void EmitBundleAlignMode(unsigned AlignPow2) override;
   void EmitBundleLock(bool AlignToEnd) override;
   void EmitBundleUnlock() override;
   void EmitBytes(StringRef Data) override;
   void EmitValueToAlignment(unsigned ByteAlignment, int64_t Value = 0,
                             unsigned ValueSize = 1,
                             unsigned MaxBytesToEmit = 0) override;
   void EmitCodeAlignment(unsigned ByteAlignment,
                          unsigned MaxBytesToEmit = 0) override;
   void emitValueToOffset(const MCExpr *Offset, unsigned char Value,
                          SMLoc Loc) override;
   void EmitDwarfLocDirective(unsigned FileNo, unsigned Line,
                              unsigned Column, unsigned Flags,
                              unsigned Isa, unsigned Discriminator,
                              StringRef FileName) override;
   void EmitDwarfAdvanceLineAddr(int64_t LineDelta, const MCSymbol *LastLabel,
                                 const MCSymbol *Label,
                                 unsigned PointerSize);
   void EmitDwarfAdvanceFrameAddr(const MCSymbol *LastLabel,
                                  const MCSymbol *Label);
   void EmitCVLocDirective(unsigned FunctionId, unsigned FileNo, unsigned Line,
                           unsigned Column, bool PrologueEnd, bool IsStmt,
                           StringRef FileName, SMLoc Loc) override;
   void EmitCVLinetableDirective(unsigned FunctionId, const MCSymbol *Begin,
                                 const MCSymbol *End) override;
   void EmitCVInlineLinetableDirective(unsigned PrimaryFunctionId,
                                       unsigned SourceFileId,
                                       unsigned SourceLineNum,
                                       const MCSymbol *FnStartSym,
                                       const MCSymbol *FnEndSym) override;
   void EmitCVDefRangeDirective(
       ArrayRef<std::pair<const MCSymbol *, const MCSymbol *>> Ranges,
       StringRef FixedSizePortion) override;
   void EmitCVStringTableDirective() override;
   void EmitCVFileChecksumsDirective() override;
   void EmitCVFileChecksumOffsetDirective(unsigned FileNo) override;
   void EmitDTPRel32Value(const MCExpr *Value) override;
   void EmitDTPRel64Value(const MCExpr *Value) override;
   void EmitTPRel32Value(const MCExpr *Value) override;
   void EmitTPRel64Value(const MCExpr *Value) override;
   void EmitGPRel32Value(const MCExpr *Value) override;
   void EmitGPRel64Value(const MCExpr *Value) override;
   bool EmitRelocDirective(const MCExpr &Offset, StringRef Name,
                           const MCExpr *Expr, SMLoc Loc,
                           const MCSubtargetInfo &STI) override;
   using MCStreamer::emitFill;
   void emitFill(const MCExpr &NumBytes, uint64_t FillValue,
                 SMLoc Loc = SMLoc()) override;
   void emitFill(const MCExpr &NumValues, int64_t Size, int64_t Expr,
                 SMLoc Loc = SMLoc()) override;
   void EmitFileDirective(StringRef Filename) override;
 
   void EmitAddrsig() override;
   void EmitAddrsigSym(const MCSymbol *Sym) override;
 
   void FinishImpl() override;
 
   /// Emit the absolute difference between two symbols if possible.
   ///
   /// Emit the absolute difference between \c Hi and \c Lo, as long as we can
   /// compute it.  Currently, that requires that both symbols are in the same
   /// data fragment and that the target has not specified that diff expressions
   /// require relocations to be emitted. Otherwise, do nothing and return
   /// \c false.
   ///
   /// \pre Offset of \c Hi is greater than the offset \c Lo.
   void emitAbsoluteSymbolDiff(const MCSymbol *Hi, const MCSymbol *Lo,
                               unsigned Size) override;
 
   void emitAbsoluteSymbolDiffAsULEB128(const MCSymbol *Hi,
                                        const MCSymbol *Lo) override;
 
   bool mayHaveInstructions(MCSection &Sec) const override;
 };
 
 } // end namespace llvm
 
 #endif
diff --git a/llvm/lib/MC/MCAssembler.cpp b/llvm/lib/MC/MCAssembler.cpp
index 2e9cfc73cf47..df1c49b2a06a 100644
--- a/llvm/lib/MC/MCAssembler.cpp
+++ b/llvm/lib/MC/MCAssembler.cpp
@@ -1,1124 +1,1204 @@
 //===- lib/MC/MCAssembler.cpp - Assembler Backend Implementation ----------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/MC/MCAsmBackend.h"
 #include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCAsmLayout.h"
 #include "llvm/MC/MCCodeEmitter.h"
 #include "llvm/MC/MCCodeView.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCDwarf.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCFixup.h"
 #include "llvm/MC/MCFixupKindInfo.h"
 #include "llvm/MC/MCFragment.h"
 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCObjectWriter.h"
 #include "llvm/MC/MCSection.h"
 #include "llvm/MC/MCSectionELF.h"
 #include "llvm/MC/MCSymbol.h"
 #include "llvm/MC/MCValue.h"
 #include "llvm/Support/Alignment.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/LEB128.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/raw_ostream.h"
 #include <cassert>
 #include <cstdint>
 #include <cstring>
 #include <tuple>
 #include <utility>
 
 using namespace llvm;
 
 #define DEBUG_TYPE "assembler"
 
 namespace {
 namespace stats {
 
 STATISTIC(EmittedFragments, "Number of emitted assembler fragments - total");
 STATISTIC(EmittedRelaxableFragments,
           "Number of emitted assembler fragments - relaxable");
 STATISTIC(EmittedDataFragments,
           "Number of emitted assembler fragments - data");
 STATISTIC(EmittedCompactEncodedInstFragments,
           "Number of emitted assembler fragments - compact encoded inst");
 STATISTIC(EmittedAlignFragments,
           "Number of emitted assembler fragments - align");
 STATISTIC(EmittedFillFragments,
           "Number of emitted assembler fragments - fill");
 STATISTIC(EmittedOrgFragments,
           "Number of emitted assembler fragments - org");
 STATISTIC(evaluateFixup, "Number of evaluated fixups");
 STATISTIC(FragmentLayouts, "Number of fragment layouts");
 STATISTIC(ObjectBytes, "Number of emitted object file bytes");
 STATISTIC(RelaxationSteps, "Number of assembler layout and relaxation steps");
 STATISTIC(RelaxedInstructions, "Number of relaxed instructions");
 
 } // end namespace stats
 } // end anonymous namespace
 
 // FIXME FIXME FIXME: There are number of places in this file where we convert
 // what is a 64-bit assembler value used for computation into a value in the
 // object file, which may truncate it. We should detect that truncation where
 // invalid and report errors back.
 
 /* *** */
 
 MCAssembler::MCAssembler(MCContext &Context,
                          std::unique_ptr<MCAsmBackend> Backend,
                          std::unique_ptr<MCCodeEmitter> Emitter,
                          std::unique_ptr<MCObjectWriter> Writer)
     : Context(Context), Backend(std::move(Backend)),
       Emitter(std::move(Emitter)), Writer(std::move(Writer)),
       BundleAlignSize(0), RelaxAll(false), SubsectionsViaSymbols(false),
       IncrementalLinkerCompatible(false), ELFHeaderEFlags(0) {
   VersionInfo.Major = 0; // Major version == 0 for "none specified"
 }
 
 MCAssembler::~MCAssembler() = default;
 
 void MCAssembler::reset() {
   Sections.clear();
   Symbols.clear();
   IndirectSymbols.clear();
   DataRegions.clear();
   LinkerOptions.clear();
   FileNames.clear();
   ThumbFuncs.clear();
   BundleAlignSize = 0;
   RelaxAll = false;
   SubsectionsViaSymbols = false;
   IncrementalLinkerCompatible = false;
   ELFHeaderEFlags = 0;
   LOHContainer.reset();
   VersionInfo.Major = 0;
   VersionInfo.SDKVersion = VersionTuple();
 
   // reset objects owned by us
   if (getBackendPtr())
     getBackendPtr()->reset();
   if (getEmitterPtr())
     getEmitterPtr()->reset();
   if (getWriterPtr())
     getWriterPtr()->reset();
   getLOHContainer().reset();
 }
 
 bool MCAssembler::registerSection(MCSection &Section) {
   if (Section.isRegistered())
     return false;
   Sections.push_back(&Section);
   Section.setIsRegistered(true);
   return true;
 }
 
 bool MCAssembler::isThumbFunc(const MCSymbol *Symbol) const {
   if (ThumbFuncs.count(Symbol))
     return true;
 
   if (!Symbol->isVariable())
     return false;
 
   const MCExpr *Expr = Symbol->getVariableValue();
 
   MCValue V;
   if (!Expr->evaluateAsRelocatable(V, nullptr, nullptr))
     return false;
 
   if (V.getSymB() || V.getRefKind() != MCSymbolRefExpr::VK_None)
     return false;
 
   const MCSymbolRefExpr *Ref = V.getSymA();
   if (!Ref)
     return false;
 
   if (Ref->getKind() != MCSymbolRefExpr::VK_None)
     return false;
 
   const MCSymbol &Sym = Ref->getSymbol();
   if (!isThumbFunc(&Sym))
     return false;
 
   ThumbFuncs.insert(Symbol); // Cache it.
   return true;
 }
 
 bool MCAssembler::isSymbolLinkerVisible(const MCSymbol &Symbol) const {
   // Non-temporary labels should always be visible to the linker.
   if (!Symbol.isTemporary())
     return true;
 
   // Absolute temporary labels are never visible.
   if (!Symbol.isInSection())
     return false;
 
   if (Symbol.isUsedInReloc())
     return true;
 
   return false;
 }
 
 const MCSymbol *MCAssembler::getAtom(const MCSymbol &S) const {
   // Linker visible symbols define atoms.
   if (isSymbolLinkerVisible(S))
     return &S;
 
   // Absolute and undefined symbols have no defining atom.
   if (!S.isInSection())
     return nullptr;
 
   // Non-linker visible symbols in sections which can't be atomized have no
   // defining atom.
   if (!getContext().getAsmInfo()->isSectionAtomizableBySymbols(
           *S.getFragment()->getParent()))
     return nullptr;
 
   // Otherwise, return the atom for the containing fragment.
   return S.getFragment()->getAtom();
 }
 
 bool MCAssembler::evaluateFixup(const MCAsmLayout &Layout,
                                 const MCFixup &Fixup, const MCFragment *DF,
                                 MCValue &Target, uint64_t &Value,
                                 bool &WasForced) const {
   ++stats::evaluateFixup;
 
   // FIXME: This code has some duplication with recordRelocation. We should
   // probably merge the two into a single callback that tries to evaluate a
   // fixup and records a relocation if one is needed.
 
   // On error claim to have completely evaluated the fixup, to prevent any
   // further processing from being done.
   const MCExpr *Expr = Fixup.getValue();
   MCContext &Ctx = getContext();
   Value = 0;
   WasForced = false;
   if (!Expr->evaluateAsRelocatable(Target, &Layout, &Fixup)) {
     Ctx.reportError(Fixup.getLoc(), "expected relocatable expression");
     return true;
   }
   if (const MCSymbolRefExpr *RefB = Target.getSymB()) {
     if (RefB->getKind() != MCSymbolRefExpr::VK_None) {
       Ctx.reportError(Fixup.getLoc(),
                       "unsupported subtraction of qualified symbol");
       return true;
     }
   }
 
   assert(getBackendPtr() && "Expected assembler backend");
   bool IsPCRel = getBackendPtr()->getFixupKindInfo(Fixup.getKind()).Flags &
                  MCFixupKindInfo::FKF_IsPCRel;
 
   bool IsResolved = false;
   if (IsPCRel) {
     if (Target.getSymB()) {
       IsResolved = false;
     } else if (!Target.getSymA()) {
       IsResolved = false;
     } else {
       const MCSymbolRefExpr *A = Target.getSymA();
       const MCSymbol &SA = A->getSymbol();
       if (A->getKind() != MCSymbolRefExpr::VK_None || SA.isUndefined()) {
         IsResolved = false;
       } else if (auto *Writer = getWriterPtr()) {
         IsResolved = Writer->isSymbolRefDifferenceFullyResolvedImpl(
             *this, SA, *DF, false, true);
       }
     }
   } else {
     IsResolved = Target.isAbsolute();
   }
 
   Value = Target.getConstant();
 
   if (const MCSymbolRefExpr *A = Target.getSymA()) {
     const MCSymbol &Sym = A->getSymbol();
     if (Sym.isDefined())
       Value += Layout.getSymbolOffset(Sym);
   }
   if (const MCSymbolRefExpr *B = Target.getSymB()) {
     const MCSymbol &Sym = B->getSymbol();
     if (Sym.isDefined())
       Value -= Layout.getSymbolOffset(Sym);
   }
 
   bool ShouldAlignPC = getBackend().getFixupKindInfo(Fixup.getKind()).Flags &
                        MCFixupKindInfo::FKF_IsAlignedDownTo32Bits;
   assert((ShouldAlignPC ? IsPCRel : true) &&
     "FKF_IsAlignedDownTo32Bits is only allowed on PC-relative fixups!");
 
   if (IsPCRel) {
     uint32_t Offset = Layout.getFragmentOffset(DF) + Fixup.getOffset();
 
     // A number of ARM fixups in Thumb mode require that the effective PC
     // address be determined as the 32-bit aligned version of the actual offset.
     if (ShouldAlignPC) Offset &= ~0x3;
     Value -= Offset;
   }
 
   // Let the backend force a relocation if needed.
   if (IsResolved && getBackend().shouldForceRelocation(*this, Fixup, Target)) {
     IsResolved = false;
     WasForced = true;
   }
 
   return IsResolved;
 }
 
 uint64_t MCAssembler::computeFragmentSize(const MCAsmLayout &Layout,
                                           const MCFragment &F) const {
   assert(getBackendPtr() && "Requires assembler backend");
   switch (F.getKind()) {
   case MCFragment::FT_Data:
     return cast<MCDataFragment>(F).getContents().size();
   case MCFragment::FT_Relaxable:
     return cast<MCRelaxableFragment>(F).getContents().size();
   case MCFragment::FT_CompactEncodedInst:
     return cast<MCCompactEncodedInstFragment>(F).getContents().size();
   case MCFragment::FT_Fill: {
     auto &FF = cast<MCFillFragment>(F);
     int64_t NumValues = 0;
     if (!FF.getNumValues().evaluateAsAbsolute(NumValues, Layout)) {
       getContext().reportError(FF.getLoc(),
                                "expected assembly-time absolute expression");
       return 0;
     }
     int64_t Size = NumValues * FF.getValueSize();
     if (Size < 0) {
       getContext().reportError(FF.getLoc(), "invalid number of bytes");
       return 0;
     }
     return Size;
   }
 
   case MCFragment::FT_LEB:
     return cast<MCLEBFragment>(F).getContents().size();
 
+  case MCFragment::FT_BoundaryAlign:
+    return cast<MCBoundaryAlignFragment>(F).getSize();
+
   case MCFragment::FT_SymbolId:
     return 4;
 
   case MCFragment::FT_Align: {
     const MCAlignFragment &AF = cast<MCAlignFragment>(F);
     unsigned Offset = Layout.getFragmentOffset(&AF);
     unsigned Size = offsetToAlignment(Offset, Align(AF.getAlignment()));
 
     // Insert extra Nops for code alignment if the target define
     // shouldInsertExtraNopBytesForCodeAlign target hook.
     if (AF.getParent()->UseCodeAlign() && AF.hasEmitNops() &&
         getBackend().shouldInsertExtraNopBytesForCodeAlign(AF, Size))
       return Size;
 
     // If we are padding with nops, force the padding to be larger than the
     // minimum nop size.
     if (Size > 0 && AF.hasEmitNops()) {
       while (Size % getBackend().getMinimumNopSize())
         Size += AF.getAlignment();
     }
     if (Size > AF.getMaxBytesToEmit())
       return 0;
     return Size;
   }
 
   case MCFragment::FT_Org: {
     const MCOrgFragment &OF = cast<MCOrgFragment>(F);
     MCValue Value;
     if (!OF.getOffset().evaluateAsValue(Value, Layout)) {
       getContext().reportError(OF.getLoc(),
                                "expected assembly-time absolute expression");
         return 0;
     }
 
     uint64_t FragmentOffset = Layout.getFragmentOffset(&OF);
     int64_t TargetLocation = Value.getConstant();
     if (const MCSymbolRefExpr *A = Value.getSymA()) {
       uint64_t Val;
       if (!Layout.getSymbolOffset(A->getSymbol(), Val)) {
         getContext().reportError(OF.getLoc(), "expected absolute expression");
         return 0;
       }
       TargetLocation += Val;
     }
     int64_t Size = TargetLocation - FragmentOffset;
     if (Size < 0 || Size >= 0x40000000) {
       getContext().reportError(
           OF.getLoc(), "invalid .org offset '" + Twine(TargetLocation) +
                            "' (at offset '" + Twine(FragmentOffset) + "')");
       return 0;
     }
     return Size;
   }
 
   case MCFragment::FT_Dwarf:
     return cast<MCDwarfLineAddrFragment>(F).getContents().size();
   case MCFragment::FT_DwarfFrame:
     return cast<MCDwarfCallFrameFragment>(F).getContents().size();
   case MCFragment::FT_CVInlineLines:
     return cast<MCCVInlineLineTableFragment>(F).getContents().size();
   case MCFragment::FT_CVDefRange:
     return cast<MCCVDefRangeFragment>(F).getContents().size();
   case MCFragment::FT_Dummy:
     llvm_unreachable("Should not have been added");
   }
 
   llvm_unreachable("invalid fragment kind");
 }
 
 void MCAsmLayout::layoutFragment(MCFragment *F) {
   MCFragment *Prev = F->getPrevNode();
 
   // We should never try to recompute something which is valid.
   assert(!isFragmentValid(F) && "Attempt to recompute a valid fragment!");
   // We should never try to compute the fragment layout if its predecessor
   // isn't valid.
   assert((!Prev || isFragmentValid(Prev)) &&
          "Attempt to compute fragment before its predecessor!");
 
   ++stats::FragmentLayouts;
 
   // Compute fragment offset and size.
   if (Prev)
     F->Offset = Prev->Offset + getAssembler().computeFragmentSize(*this, *Prev);
   else
     F->Offset = 0;
   LastValidFragment[F->getParent()] = F;
 
   // If bundling is enabled and this fragment has instructions in it, it has to
   // obey the bundling restrictions. With padding, we'll have:
   //
   //
   //        BundlePadding
   //             |||
   // -------------------------------------
   //   Prev  |##########|       F        |
   // -------------------------------------
   //                    ^
   //                    |
   //                    F->Offset
   //
   // The fragment's offset will point to after the padding, and its computed
   // size won't include the padding.
   //
   // When the -mc-relax-all flag is used, we optimize bundling by writting the
   // padding directly into fragments when the instructions are emitted inside
   // the streamer. When the fragment is larger than the bundle size, we need to
   // ensure that it's bundle aligned. This means that if we end up with
   // multiple fragments, we must emit bundle padding between fragments.
   //
   // ".align N" is an example of a directive that introduces multiple
   // fragments. We could add a special case to handle ".align N" by emitting
   // within-fragment padding (which would produce less padding when N is less
   // than the bundle size), but for now we don't.
   //
   if (Assembler.isBundlingEnabled() && F->hasInstructions()) {
     assert(isa<MCEncodedFragment>(F) &&
            "Only MCEncodedFragment implementations have instructions");
     MCEncodedFragment *EF = cast<MCEncodedFragment>(F);
     uint64_t FSize = Assembler.computeFragmentSize(*this, *EF);
 
     if (!Assembler.getRelaxAll() && FSize > Assembler.getBundleAlignSize())
       report_fatal_error("Fragment can't be larger than a bundle size");
 
     uint64_t RequiredBundlePadding =
         computeBundlePadding(Assembler, EF, EF->Offset, FSize);
     if (RequiredBundlePadding > UINT8_MAX)
       report_fatal_error("Padding cannot exceed 255 bytes");
     EF->setBundlePadding(static_cast<uint8_t>(RequiredBundlePadding));
     EF->Offset += RequiredBundlePadding;
   }
 }
 
 void MCAssembler::registerSymbol(const MCSymbol &Symbol, bool *Created) {
   bool New = !Symbol.isRegistered();
   if (Created)
     *Created = New;
   if (New) {
     Symbol.setIsRegistered(true);
     Symbols.push_back(&Symbol);
   }
 }
 
 void MCAssembler::writeFragmentPadding(raw_ostream &OS,
                                        const MCEncodedFragment &EF,
                                        uint64_t FSize) const {
   assert(getBackendPtr() && "Expected assembler backend");
   // Should NOP padding be written out before this fragment?
   unsigned BundlePadding = EF.getBundlePadding();
   if (BundlePadding > 0) {
     assert(isBundlingEnabled() &&
            "Writing bundle padding with disabled bundling");
     assert(EF.hasInstructions() &&
            "Writing bundle padding for a fragment without instructions");
 
     unsigned TotalLength = BundlePadding + static_cast<unsigned>(FSize);
     if (EF.alignToBundleEnd() && TotalLength > getBundleAlignSize()) {
       // If the padding itself crosses a bundle boundary, it must be emitted
       // in 2 pieces, since even nop instructions must not cross boundaries.
       //             v--------------v   <- BundleAlignSize
       //        v---------v             <- BundlePadding
       // ----------------------------
       // | Prev |####|####|    F    |
       // ----------------------------
       //        ^-------------------^   <- TotalLength
       unsigned DistanceToBoundary = TotalLength - getBundleAlignSize();
       if (!getBackend().writeNopData(OS, DistanceToBoundary))
         report_fatal_error("unable to write NOP sequence of " +
                            Twine(DistanceToBoundary) + " bytes");
       BundlePadding -= DistanceToBoundary;
     }
     if (!getBackend().writeNopData(OS, BundlePadding))
       report_fatal_error("unable to write NOP sequence of " +
                          Twine(BundlePadding) + " bytes");
   }
 }
 
 /// Write the fragment \p F to the output file.
 static void writeFragment(raw_ostream &OS, const MCAssembler &Asm,
                           const MCAsmLayout &Layout, const MCFragment &F) {
   // FIXME: Embed in fragments instead?
   uint64_t FragmentSize = Asm.computeFragmentSize(Layout, F);
 
   support::endianness Endian = Asm.getBackend().Endian;
 
   if (const MCEncodedFragment *EF = dyn_cast<MCEncodedFragment>(&F))
     Asm.writeFragmentPadding(OS, *EF, FragmentSize);
 
   // This variable (and its dummy usage) is to participate in the assert at
   // the end of the function.
   uint64_t Start = OS.tell();
   (void) Start;
 
   ++stats::EmittedFragments;
 
   switch (F.getKind()) {
   case MCFragment::FT_Align: {
     ++stats::EmittedAlignFragments;
     const MCAlignFragment &AF = cast<MCAlignFragment>(F);
     assert(AF.getValueSize() && "Invalid virtual align in concrete fragment!");
 
     uint64_t Count = FragmentSize / AF.getValueSize();
 
     // FIXME: This error shouldn't actually occur (the front end should emit
     // multiple .align directives to enforce the semantics it wants), but is
     // severe enough that we want to report it. How to handle this?
     if (Count * AF.getValueSize() != FragmentSize)
       report_fatal_error("undefined .align directive, value size '" +
                         Twine(AF.getValueSize()) +
                         "' is not a divisor of padding size '" +
                         Twine(FragmentSize) + "'");
 
     // See if we are aligning with nops, and if so do that first to try to fill
     // the Count bytes.  Then if that did not fill any bytes or there are any
     // bytes left to fill use the Value and ValueSize to fill the rest.
     // If we are aligning with nops, ask that target to emit the right data.
     if (AF.hasEmitNops()) {
       if (!Asm.getBackend().writeNopData(OS, Count))
         report_fatal_error("unable to write nop sequence of " +
                           Twine(Count) + " bytes");
       break;
     }
 
     // Otherwise, write out in multiples of the value size.
     for (uint64_t i = 0; i != Count; ++i) {
       switch (AF.getValueSize()) {
       default: llvm_unreachable("Invalid size!");
       case 1: OS << char(AF.getValue()); break;
       case 2:
         support::endian::write<uint16_t>(OS, AF.getValue(), Endian);
         break;
       case 4:
         support::endian::write<uint32_t>(OS, AF.getValue(), Endian);
         break;
       case 8:
         support::endian::write<uint64_t>(OS, AF.getValue(), Endian);
         break;
       }
     }
     break;
   }
 
   case MCFragment::FT_Data:
     ++stats::EmittedDataFragments;
     OS << cast<MCDataFragment>(F).getContents();
     break;
 
   case MCFragment::FT_Relaxable:
     ++stats::EmittedRelaxableFragments;
     OS << cast<MCRelaxableFragment>(F).getContents();
     break;
 
   case MCFragment::FT_CompactEncodedInst:
     ++stats::EmittedCompactEncodedInstFragments;
     OS << cast<MCCompactEncodedInstFragment>(F).getContents();
     break;
 
   case MCFragment::FT_Fill: {
     ++stats::EmittedFillFragments;
     const MCFillFragment &FF = cast<MCFillFragment>(F);
     uint64_t V = FF.getValue();
     unsigned VSize = FF.getValueSize();
     const unsigned MaxChunkSize = 16;
     char Data[MaxChunkSize];
     // Duplicate V into Data as byte vector to reduce number of
     // writes done. As such, do endian conversion here.
     for (unsigned I = 0; I != VSize; ++I) {
       unsigned index = Endian == support::little ? I : (VSize - I - 1);
       Data[I] = uint8_t(V >> (index * 8));
     }
     for (unsigned I = VSize; I < MaxChunkSize; ++I)
       Data[I] = Data[I - VSize];
 
     // Set to largest multiple of VSize in Data.
     const unsigned NumPerChunk = MaxChunkSize / VSize;
     // Set ChunkSize to largest multiple of VSize in Data
     const unsigned ChunkSize = VSize * NumPerChunk;
 
     // Do copies by chunk.
     StringRef Ref(Data, ChunkSize);
     for (uint64_t I = 0, E = FragmentSize / ChunkSize; I != E; ++I)
       OS << Ref;
 
     // do remainder if needed.
     unsigned TrailingCount = FragmentSize % ChunkSize;
     if (TrailingCount)
       OS.write(Data, TrailingCount);
     break;
   }
 
   case MCFragment::FT_LEB: {
     const MCLEBFragment &LF = cast<MCLEBFragment>(F);
     OS << LF.getContents();
     break;
   }
 
+  case MCFragment::FT_BoundaryAlign: {
+    if (!Asm.getBackend().writeNopData(OS, FragmentSize))
+      report_fatal_error("unable to write nop sequence of " +
+                         Twine(FragmentSize) + " bytes");
+    break;
+  }
+
   case MCFragment::FT_SymbolId: {
     const MCSymbolIdFragment &SF = cast<MCSymbolIdFragment>(F);
     support::endian::write<uint32_t>(OS, SF.getSymbol()->getIndex(), Endian);
     break;
   }
 
   case MCFragment::FT_Org: {
     ++stats::EmittedOrgFragments;
     const MCOrgFragment &OF = cast<MCOrgFragment>(F);
 
     for (uint64_t i = 0, e = FragmentSize; i != e; ++i)
       OS << char(OF.getValue());
 
     break;
   }
 
   case MCFragment::FT_Dwarf: {
     const MCDwarfLineAddrFragment &OF = cast<MCDwarfLineAddrFragment>(F);
     OS << OF.getContents();
     break;
   }
   case MCFragment::FT_DwarfFrame: {
     const MCDwarfCallFrameFragment &CF = cast<MCDwarfCallFrameFragment>(F);
     OS << CF.getContents();
     break;
   }
   case MCFragment::FT_CVInlineLines: {
     const auto &OF = cast<MCCVInlineLineTableFragment>(F);
     OS << OF.getContents();
     break;
   }
   case MCFragment::FT_CVDefRange: {
     const auto &DRF = cast<MCCVDefRangeFragment>(F);
     OS << DRF.getContents();
     break;
   }
   case MCFragment::FT_Dummy:
     llvm_unreachable("Should not have been added");
   }
 
   assert(OS.tell() - Start == FragmentSize &&
          "The stream should advance by fragment size");
 }
 
 void MCAssembler::writeSectionData(raw_ostream &OS, const MCSection *Sec,
                                    const MCAsmLayout &Layout) const {
   assert(getBackendPtr() && "Expected assembler backend");
 
   // Ignore virtual sections.
   if (Sec->isVirtualSection()) {
     assert(Layout.getSectionFileSize(Sec) == 0 && "Invalid size for section!");
 
     // Check that contents are only things legal inside a virtual section.
     for (const MCFragment &F : *Sec) {
       switch (F.getKind()) {
       default: llvm_unreachable("Invalid fragment in virtual section!");
       case MCFragment::FT_Data: {
         // Check that we aren't trying to write a non-zero contents (or fixups)
         // into a virtual section. This is to support clients which use standard
         // directives to fill the contents of virtual sections.
         const MCDataFragment &DF = cast<MCDataFragment>(F);
         if (DF.fixup_begin() != DF.fixup_end())
           report_fatal_error("cannot have fixups in virtual section!");
         for (unsigned i = 0, e = DF.getContents().size(); i != e; ++i)
           if (DF.getContents()[i]) {
             if (auto *ELFSec = dyn_cast<const MCSectionELF>(Sec))
               report_fatal_error("non-zero initializer found in section '" +
                   ELFSec->getSectionName() + "'");
             else
               report_fatal_error("non-zero initializer found in virtual section");
           }
         break;
       }
       case MCFragment::FT_Align:
         // Check that we aren't trying to write a non-zero value into a virtual
         // section.
         assert((cast<MCAlignFragment>(F).getValueSize() == 0 ||
                 cast<MCAlignFragment>(F).getValue() == 0) &&
                "Invalid align in virtual section!");
         break;
       case MCFragment::FT_Fill:
         assert((cast<MCFillFragment>(F).getValue() == 0) &&
                "Invalid fill in virtual section!");
         break;
       }
     }
 
     return;
   }
 
   uint64_t Start = OS.tell();
   (void)Start;
 
   for (const MCFragment &F : *Sec)
     writeFragment(OS, *this, Layout, F);
 
   assert(OS.tell() - Start == Layout.getSectionAddressSize(Sec));
 }
 
 std::tuple<MCValue, uint64_t, bool>
 MCAssembler::handleFixup(const MCAsmLayout &Layout, MCFragment &F,
                          const MCFixup &Fixup) {
   // Evaluate the fixup.
   MCValue Target;
   uint64_t FixedValue;
   bool WasForced;
   bool IsResolved = evaluateFixup(Layout, Fixup, &F, Target, FixedValue,
                                   WasForced);
   if (!IsResolved) {
     // The fixup was unresolved, we need a relocation. Inform the object
     // writer of the relocation, and give it an opportunity to adjust the
     // fixup value if need be.
     if (Target.getSymA() && Target.getSymB() &&
         getBackend().requiresDiffExpressionRelocations()) {
       // The fixup represents the difference between two symbols, which the
       // backend has indicated must be resolved at link time. Split up the fixup
       // into two relocations, one for the add, and one for the sub, and emit
       // both of these. The constant will be associated with the add half of the
       // expression.
       MCFixup FixupAdd = MCFixup::createAddFor(Fixup);
       MCValue TargetAdd =
           MCValue::get(Target.getSymA(), nullptr, Target.getConstant());
       getWriter().recordRelocation(*this, Layout, &F, FixupAdd, TargetAdd,
                                    FixedValue);
       MCFixup FixupSub = MCFixup::createSubFor(Fixup);
       MCValue TargetSub = MCValue::get(Target.getSymB());
       getWriter().recordRelocation(*this, Layout, &F, FixupSub, TargetSub,
                                    FixedValue);
     } else {
       getWriter().recordRelocation(*this, Layout, &F, Fixup, Target,
                                    FixedValue);
     }
   }
   return std::make_tuple(Target, FixedValue, IsResolved);
 }
 
 void MCAssembler::layout(MCAsmLayout &Layout) {
   assert(getBackendPtr() && "Expected assembler backend");
   DEBUG_WITH_TYPE("mc-dump", {
       errs() << "assembler backend - pre-layout\n--\n";
       dump(); });
 
   // Create dummy fragments and assign section ordinals.
   unsigned SectionIndex = 0;
   for (MCSection &Sec : *this) {
     // Create dummy fragments to eliminate any empty sections, this simplifies
     // layout.
     if (Sec.getFragmentList().empty())
       new MCDataFragment(&Sec);
 
     Sec.setOrdinal(SectionIndex++);
   }
 
   // Assign layout order indices to sections and fragments.
   for (unsigned i = 0, e = Layout.getSectionOrder().size(); i != e; ++i) {
     MCSection *Sec = Layout.getSectionOrder()[i];
     Sec->setLayoutOrder(i);
 
     unsigned FragmentIndex = 0;
     for (MCFragment &Frag : *Sec)
       Frag.setLayoutOrder(FragmentIndex++);
   }
 
   // Layout until everything fits.
   while (layoutOnce(Layout))
     if (getContext().hadError())
       return;
 
   DEBUG_WITH_TYPE("mc-dump", {
       errs() << "assembler backend - post-relaxation\n--\n";
       dump(); });
 
   // Finalize the layout, including fragment lowering.
   finishLayout(Layout);
 
   DEBUG_WITH_TYPE("mc-dump", {
       errs() << "assembler backend - final-layout\n--\n";
       dump(); });
 
   // Allow the object writer a chance to perform post-layout binding (for
   // example, to set the index fields in the symbol data).
   getWriter().executePostLayoutBinding(*this, Layout);
 
   // Evaluate and apply the fixups, generating relocation entries as necessary.
   for (MCSection &Sec : *this) {
     for (MCFragment &Frag : Sec) {
       // Data and relaxable fragments both have fixups.  So only process
       // those here.
       // FIXME: Is there a better way to do this?  MCEncodedFragmentWithFixups
       // being templated makes this tricky.
       if (isa<MCEncodedFragment>(&Frag) &&
           isa<MCCompactEncodedInstFragment>(&Frag))
         continue;
       if (!isa<MCEncodedFragment>(&Frag) && !isa<MCCVDefRangeFragment>(&Frag) &&
           !isa<MCAlignFragment>(&Frag))
         continue;
       ArrayRef<MCFixup> Fixups;
       MutableArrayRef<char> Contents;
       const MCSubtargetInfo *STI = nullptr;
       if (auto *FragWithFixups = dyn_cast<MCDataFragment>(&Frag)) {
         Fixups = FragWithFixups->getFixups();
         Contents = FragWithFixups->getContents();
         STI = FragWithFixups->getSubtargetInfo();
         assert(!FragWithFixups->hasInstructions() || STI != nullptr);
       } else if (auto *FragWithFixups = dyn_cast<MCRelaxableFragment>(&Frag)) {
         Fixups = FragWithFixups->getFixups();
         Contents = FragWithFixups->getContents();
         STI = FragWithFixups->getSubtargetInfo();
         assert(!FragWithFixups->hasInstructions() || STI != nullptr);
       } else if (auto *FragWithFixups = dyn_cast<MCCVDefRangeFragment>(&Frag)) {
         Fixups = FragWithFixups->getFixups();
         Contents = FragWithFixups->getContents();
       } else if (auto *FragWithFixups = dyn_cast<MCDwarfLineAddrFragment>(&Frag)) {
         Fixups = FragWithFixups->getFixups();
         Contents = FragWithFixups->getContents();
       } else if (auto *AF = dyn_cast<MCAlignFragment>(&Frag)) {
         // Insert fixup type for code alignment if the target define
         // shouldInsertFixupForCodeAlign target hook.
         if (Sec.UseCodeAlign() && AF->hasEmitNops()) {
           getBackend().shouldInsertFixupForCodeAlign(*this, Layout, *AF);
         }
         continue;
       } else if (auto *FragWithFixups =
                      dyn_cast<MCDwarfCallFrameFragment>(&Frag)) {
         Fixups = FragWithFixups->getFixups();
         Contents = FragWithFixups->getContents();
       } else
         llvm_unreachable("Unknown fragment with fixups!");
       for (const MCFixup &Fixup : Fixups) {
         uint64_t FixedValue;
         bool IsResolved;
         MCValue Target;
         std::tie(Target, FixedValue, IsResolved) =
             handleFixup(Layout, Frag, Fixup);
         getBackend().applyFixup(*this, Fixup, Target, Contents, FixedValue,
                                 IsResolved, STI);
       }
     }
   }
 }
 
 void MCAssembler::Finish() {
   // Create the layout object.
   MCAsmLayout Layout(*this);
   layout(Layout);
 
   // Write the object file.
   stats::ObjectBytes += getWriter().writeObject(*this, Layout);
 }
 
 bool MCAssembler::fixupNeedsRelaxation(const MCFixup &Fixup,
                                        const MCRelaxableFragment *DF,
                                        const MCAsmLayout &Layout) const {
   assert(getBackendPtr() && "Expected assembler backend");
   MCValue Target;
   uint64_t Value;
   bool WasForced;
   bool Resolved = evaluateFixup(Layout, Fixup, DF, Target, Value, WasForced);
   if (Target.getSymA() &&
       Target.getSymA()->getKind() == MCSymbolRefExpr::VK_X86_ABS8 &&
       Fixup.getKind() == FK_Data_1)
     return false;
   return getBackend().fixupNeedsRelaxationAdvanced(Fixup, Resolved, Value, DF,
                                                    Layout, WasForced);
 }
 
 bool MCAssembler::fragmentNeedsRelaxation(const MCRelaxableFragment *F,
                                           const MCAsmLayout &Layout) const {
   assert(getBackendPtr() && "Expected assembler backend");
   // If this inst doesn't ever need relaxation, ignore it. This occurs when we
   // are intentionally pushing out inst fragments, or because we relaxed a
   // previous instruction to one that doesn't need relaxation.
   if (!getBackend().mayNeedRelaxation(F->getInst(), *F->getSubtargetInfo()))
     return false;
 
   for (const MCFixup &Fixup : F->getFixups())
     if (fixupNeedsRelaxation(Fixup, F, Layout))
       return true;
 
   return false;
 }
 
 bool MCAssembler::relaxInstruction(MCAsmLayout &Layout,
                                    MCRelaxableFragment &F) {
   assert(getEmitterPtr() &&
          "Expected CodeEmitter defined for relaxInstruction");
   if (!fragmentNeedsRelaxation(&F, Layout))
     return false;
 
   ++stats::RelaxedInstructions;
 
   // FIXME-PERF: We could immediately lower out instructions if we can tell
   // they are fully resolved, to avoid retesting on later passes.
 
   // Relax the fragment.
 
   MCInst Relaxed;
   getBackend().relaxInstruction(F.getInst(), *F.getSubtargetInfo(), Relaxed);
 
   // Encode the new instruction.
   //
   // FIXME-PERF: If it matters, we could let the target do this. It can
   // probably do so more efficiently in many cases.
   SmallVector<MCFixup, 4> Fixups;
   SmallString<256> Code;
   raw_svector_ostream VecOS(Code);
   getEmitter().encodeInstruction(Relaxed, VecOS, Fixups, *F.getSubtargetInfo());
 
   // Update the fragment.
   F.setInst(Relaxed);
   F.getContents() = Code;
   F.getFixups() = Fixups;
 
   return true;
 }
 
 bool MCAssembler::relaxLEB(MCAsmLayout &Layout, MCLEBFragment &LF) {
   uint64_t OldSize = LF.getContents().size();
   int64_t Value;
   bool Abs = LF.getValue().evaluateKnownAbsolute(Value, Layout);
   if (!Abs)
     report_fatal_error("sleb128 and uleb128 expressions must be absolute");
   SmallString<8> &Data = LF.getContents();
   Data.clear();
   raw_svector_ostream OSE(Data);
   // The compiler can generate EH table assembly that is impossible to assemble
   // without either adding padding to an LEB fragment or adding extra padding
   // to a later alignment fragment. To accommodate such tables, relaxation can
   // only increase an LEB fragment size here, not decrease it. See PR35809.
   if (LF.isSigned())
     encodeSLEB128(Value, OSE, OldSize);
   else
     encodeULEB128(Value, OSE, OldSize);
   return OldSize != LF.getContents().size();
 }
 
+/// Check if the branch crosses the boundary.
+///
+/// \param StartAddr start address of the fused/unfused branch.
+/// \param Size size of the fused/unfused branch.
+/// \param BoundaryAlignment aligment requirement of the branch.
+/// \returns true if the branch cross the boundary.
+static bool mayCrossBoundary(uint64_t StartAddr, uint64_t Size,
+                             Align BoundaryAlignment) {
+  uint64_t EndAddr = StartAddr + Size;
+  return (StartAddr >> Log2(BoundaryAlignment)) !=
+         ((EndAddr - 1) >> Log2(BoundaryAlignment));
+}
+
+/// Check if the branch is against the boundary.
+///
+/// \param StartAddr start address of the fused/unfused branch.
+/// \param Size size of the fused/unfused branch.
+/// \param BoundaryAlignment aligment requirement of the branch.
+/// \returns true if the branch is against the boundary.
+static bool isAgainstBoundary(uint64_t StartAddr, uint64_t Size,
+                              Align BoundaryAlignment) {
+  uint64_t EndAddr = StartAddr + Size;
+  return (EndAddr & (BoundaryAlignment.value() - 1)) == 0;
+}
+
+/// Check if the branch needs padding.
+///
+/// \param StartAddr start address of the fused/unfused branch.
+/// \param Size size of the fused/unfused branch.
+/// \param BoundaryAlignment aligment requirement of the branch.
+/// \returns true if the branch needs padding.
+static bool needPadding(uint64_t StartAddr, uint64_t Size,
+                        Align BoundaryAlignment) {
+  return mayCrossBoundary(StartAddr, Size, BoundaryAlignment) ||
+         isAgainstBoundary(StartAddr, Size, BoundaryAlignment);
+}
+
+bool MCAssembler::relaxBoundaryAlign(MCAsmLayout &Layout,
+                                     MCBoundaryAlignFragment &BF) {
+  // The MCBoundaryAlignFragment that doesn't emit NOP should not be relaxed.
+  if (!BF.canEmitNops())
+    return false;
+
+  uint64_t AlignedOffset = Layout.getFragmentOffset(BF.getNextNode());
+  uint64_t AlignedSize = 0;
+  const MCFragment *F = BF.getNextNode();
+  // If the branch is unfused, it is emitted into one fragment, otherwise it is
+  // emitted into two fragments at most, the next MCBoundaryAlignFragment(if
+  // exists) also marks the end of the branch.
+  for (auto i = 0, N = BF.isFused() ? 2 : 1;
+       i != N && !isa<MCBoundaryAlignFragment>(F); ++i, F = F->getNextNode()) {
+    AlignedSize += computeFragmentSize(Layout, *F);
+  }
+  uint64_t OldSize = BF.getSize();
+  AlignedOffset -= OldSize;
+  Align BoundaryAlignment = BF.getAlignment();
+  uint64_t NewSize = needPadding(AlignedOffset, AlignedSize, BoundaryAlignment)
+                         ? offsetToAlignment(AlignedOffset, BoundaryAlignment)
+                         : 0U;
+  if (NewSize == OldSize)
+    return false;
+  BF.setSize(NewSize);
+  Layout.invalidateFragmentsFrom(&BF);
+  return true;
+}
+
 bool MCAssembler::relaxDwarfLineAddr(MCAsmLayout &Layout,
                                      MCDwarfLineAddrFragment &DF) {
   MCContext &Context = Layout.getAssembler().getContext();
   uint64_t OldSize = DF.getContents().size();
   int64_t AddrDelta;
   bool Abs = DF.getAddrDelta().evaluateKnownAbsolute(AddrDelta, Layout);
   assert(Abs && "We created a line delta with an invalid expression");
   (void)Abs;
   int64_t LineDelta;
   LineDelta = DF.getLineDelta();
   SmallVectorImpl<char> &Data = DF.getContents();
   Data.clear();
   raw_svector_ostream OSE(Data);
   DF.getFixups().clear();
 
   if (!getBackend().requiresDiffExpressionRelocations()) {
     MCDwarfLineAddr::Encode(Context, getDWARFLinetableParams(), LineDelta,
                             AddrDelta, OSE);
   } else {
     uint32_t Offset;
     uint32_t Size;
     bool SetDelta = MCDwarfLineAddr::FixedEncode(Context,
                                                  getDWARFLinetableParams(),
                                                  LineDelta, AddrDelta,
                                                  OSE, &Offset, &Size);
     // Add Fixups for address delta or new address.
     const MCExpr *FixupExpr;
     if (SetDelta) {
       FixupExpr = &DF.getAddrDelta();
     } else {
       const MCBinaryExpr *ABE = cast<MCBinaryExpr>(&DF.getAddrDelta());
       FixupExpr = ABE->getLHS();
     }
     DF.getFixups().push_back(
         MCFixup::create(Offset, FixupExpr,
                         MCFixup::getKindForSize(Size, false /*isPCRel*/)));
   }
 
   return OldSize != Data.size();
 }
 
 bool MCAssembler::relaxDwarfCallFrameFragment(MCAsmLayout &Layout,
                                               MCDwarfCallFrameFragment &DF) {
   MCContext &Context = Layout.getAssembler().getContext();
   uint64_t OldSize = DF.getContents().size();
   int64_t AddrDelta;
   bool Abs = DF.getAddrDelta().evaluateKnownAbsolute(AddrDelta, Layout);
   assert(Abs && "We created call frame with an invalid expression");
   (void) Abs;
   SmallVectorImpl<char> &Data = DF.getContents();
   Data.clear();
   raw_svector_ostream OSE(Data);
   DF.getFixups().clear();
 
   if (getBackend().requiresDiffExpressionRelocations()) {
     uint32_t Offset;
     uint32_t Size;
     MCDwarfFrameEmitter::EncodeAdvanceLoc(Context, AddrDelta, OSE, &Offset,
                                           &Size);
     if (Size) {
       DF.getFixups().push_back(MCFixup::create(
           Offset, &DF.getAddrDelta(),
           MCFixup::getKindForSizeInBits(Size /*In bits.*/, false /*isPCRel*/)));
     }
   } else {
     MCDwarfFrameEmitter::EncodeAdvanceLoc(Context, AddrDelta, OSE);
   }
 
   return OldSize != Data.size();
 }
 
 bool MCAssembler::relaxCVInlineLineTable(MCAsmLayout &Layout,
                                          MCCVInlineLineTableFragment &F) {
   unsigned OldSize = F.getContents().size();
   getContext().getCVContext().encodeInlineLineTable(Layout, F);
   return OldSize != F.getContents().size();
 }
 
 bool MCAssembler::relaxCVDefRange(MCAsmLayout &Layout,
                                   MCCVDefRangeFragment &F) {
   unsigned OldSize = F.getContents().size();
   getContext().getCVContext().encodeDefRange(Layout, F);
   return OldSize != F.getContents().size();
 }
 
 bool MCAssembler::layoutSectionOnce(MCAsmLayout &Layout, MCSection &Sec) {
   // Holds the first fragment which needed relaxing during this layout. It will
   // remain NULL if none were relaxed.
   // When a fragment is relaxed, all the fragments following it should get
   // invalidated because their offset is going to change.
   MCFragment *FirstRelaxedFragment = nullptr;
 
   // Attempt to relax all the fragments in the section.
   for (MCSection::iterator I = Sec.begin(), IE = Sec.end(); I != IE; ++I) {
     // Check if this is a fragment that needs relaxation.
     bool RelaxedFrag = false;
     switch(I->getKind()) {
     default:
       break;
     case MCFragment::FT_Relaxable:
       assert(!getRelaxAll() &&
              "Did not expect a MCRelaxableFragment in RelaxAll mode");
       RelaxedFrag = relaxInstruction(Layout, *cast<MCRelaxableFragment>(I));
       break;
     case MCFragment::FT_Dwarf:
       RelaxedFrag = relaxDwarfLineAddr(Layout,
                                        *cast<MCDwarfLineAddrFragment>(I));
       break;
     case MCFragment::FT_DwarfFrame:
       RelaxedFrag =
         relaxDwarfCallFrameFragment(Layout,
                                     *cast<MCDwarfCallFrameFragment>(I));
       break;
     case MCFragment::FT_LEB:
       RelaxedFrag = relaxLEB(Layout, *cast<MCLEBFragment>(I));
       break;
+    case MCFragment::FT_BoundaryAlign:
+      RelaxedFrag =
+          relaxBoundaryAlign(Layout, *cast<MCBoundaryAlignFragment>(I));
+      break;
     case MCFragment::FT_CVInlineLines:
       RelaxedFrag =
           relaxCVInlineLineTable(Layout, *cast<MCCVInlineLineTableFragment>(I));
       break;
     case MCFragment::FT_CVDefRange:
       RelaxedFrag = relaxCVDefRange(Layout, *cast<MCCVDefRangeFragment>(I));
       break;
     }
     if (RelaxedFrag && !FirstRelaxedFragment)
       FirstRelaxedFragment = &*I;
   }
   if (FirstRelaxedFragment) {
     Layout.invalidateFragmentsFrom(FirstRelaxedFragment);
     return true;
   }
   return false;
 }
 
 bool MCAssembler::layoutOnce(MCAsmLayout &Layout) {
   ++stats::RelaxationSteps;
 
   bool WasRelaxed = false;
   for (iterator it = begin(), ie = end(); it != ie; ++it) {
     MCSection &Sec = *it;
     while (layoutSectionOnce(Layout, Sec))
       WasRelaxed = true;
   }
 
   return WasRelaxed;
 }
 
 void MCAssembler::finishLayout(MCAsmLayout &Layout) {
   assert(getBackendPtr() && "Expected assembler backend");
   // The layout is done. Mark every fragment as valid.
   for (unsigned int i = 0, n = Layout.getSectionOrder().size(); i != n; ++i) {
     MCSection &Section = *Layout.getSectionOrder()[i];
     Layout.getFragmentOffset(&*Section.rbegin());
     computeFragmentSize(Layout, *Section.rbegin());
   }
   getBackend().finishLayout(*this, Layout);
 }
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
 LLVM_DUMP_METHOD void MCAssembler::dump() const{
   raw_ostream &OS = errs();
 
   OS << "<MCAssembler\n";
   OS << "  Sections:[\n    ";
   for (const_iterator it = begin(), ie = end(); it != ie; ++it) {
     if (it != begin()) OS << ",\n    ";
     it->dump();
   }
   OS << "],\n";
   OS << "  Symbols:[";
 
   for (const_symbol_iterator it = symbol_begin(), ie = symbol_end(); it != ie; ++it) {
     if (it != symbol_begin()) OS << ",\n           ";
     OS << "(";
     it->dump();
     OS << ", Index:" << it->getIndex() << ", ";
     OS << ")";
   }
   OS << "]>\n";
 }
 #endif
diff --git a/llvm/lib/MC/MCFragment.cpp b/llvm/lib/MC/MCFragment.cpp
index 98017a9bfa6f..1f0615c2bb02 100644
--- a/llvm/lib/MC/MCFragment.cpp
+++ b/llvm/lib/MC/MCFragment.cpp
@@ -1,448 +1,465 @@
 //===- lib/MC/MCFragment.cpp - Assembler Fragment Implementation ----------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/MC/MCFragment.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/Config/llvm-config.h"
 #include "llvm/MC/MCAsmLayout.h"
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCFixup.h"
 #include "llvm/MC/MCSection.h"
 #include "llvm/MC/MCSymbol.h"
 #include "llvm/MC/MCValue.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/raw_ostream.h"
 #include <cassert>
 #include <cstdint>
 #include <utility>
 
 using namespace llvm;
 
 MCAsmLayout::MCAsmLayout(MCAssembler &Asm) : Assembler(Asm) {
   // Compute the section layout order. Virtual sections must go last.
   for (MCSection &Sec : Asm)
     if (!Sec.isVirtualSection())
       SectionOrder.push_back(&Sec);
   for (MCSection &Sec : Asm)
     if (Sec.isVirtualSection())
       SectionOrder.push_back(&Sec);
 }
 
 bool MCAsmLayout::isFragmentValid(const MCFragment *F) const {
   const MCSection *Sec = F->getParent();
   const MCFragment *LastValid = LastValidFragment.lookup(Sec);
   if (!LastValid)
     return false;
   assert(LastValid->getParent() == Sec);
   return F->getLayoutOrder() <= LastValid->getLayoutOrder();
 }
 
 void MCAsmLayout::invalidateFragmentsFrom(MCFragment *F) {
   // If this fragment wasn't already valid, we don't need to do anything.
   if (!isFragmentValid(F))
     return;
 
   // Otherwise, reset the last valid fragment to the previous fragment
   // (if this is the first fragment, it will be NULL).
   LastValidFragment[F->getParent()] = F->getPrevNode();
 }
 
 void MCAsmLayout::ensureValid(const MCFragment *F) const {
   MCSection *Sec = F->getParent();
   MCSection::iterator I;
   if (MCFragment *Cur = LastValidFragment[Sec])
     I = ++MCSection::iterator(Cur);
   else
     I = Sec->begin();
 
   // Advance the layout position until the fragment is valid.
   while (!isFragmentValid(F)) {
     assert(I != Sec->end() && "Layout bookkeeping error");
     const_cast<MCAsmLayout *>(this)->layoutFragment(&*I);
     ++I;
   }
 }
 
 uint64_t MCAsmLayout::getFragmentOffset(const MCFragment *F) const {
   ensureValid(F);
   assert(F->Offset != ~UINT64_C(0) && "Address not set!");
   return F->Offset;
 }
 
 // Simple getSymbolOffset helper for the non-variable case.
 static bool getLabelOffset(const MCAsmLayout &Layout, const MCSymbol &S,
                            bool ReportError, uint64_t &Val) {
   if (!S.getFragment()) {
     if (ReportError)
       report_fatal_error("unable to evaluate offset to undefined symbol '" +
                          S.getName() + "'");
     return false;
   }
   Val = Layout.getFragmentOffset(S.getFragment()) + S.getOffset();
   return true;
 }
 
 static bool getSymbolOffsetImpl(const MCAsmLayout &Layout, const MCSymbol &S,
                                 bool ReportError, uint64_t &Val) {
   if (!S.isVariable())
     return getLabelOffset(Layout, S, ReportError, Val);
 
   // If SD is a variable, evaluate it.
   MCValue Target;
   if (!S.getVariableValue()->evaluateAsValue(Target, Layout))
     report_fatal_error("unable to evaluate offset for variable '" +
                        S.getName() + "'");
 
   uint64_t Offset = Target.getConstant();
 
   const MCSymbolRefExpr *A = Target.getSymA();
   if (A) {
     uint64_t ValA;
     if (!getLabelOffset(Layout, A->getSymbol(), ReportError, ValA))
       return false;
     Offset += ValA;
   }
 
   const MCSymbolRefExpr *B = Target.getSymB();
   if (B) {
     uint64_t ValB;
     if (!getLabelOffset(Layout, B->getSymbol(), ReportError, ValB))
       return false;
     Offset -= ValB;
   }
 
   Val = Offset;
   return true;
 }
 
 bool MCAsmLayout::getSymbolOffset(const MCSymbol &S, uint64_t &Val) const {
   return getSymbolOffsetImpl(*this, S, false, Val);
 }
 
 uint64_t MCAsmLayout::getSymbolOffset(const MCSymbol &S) const {
   uint64_t Val;
   getSymbolOffsetImpl(*this, S, true, Val);
   return Val;
 }
 
 const MCSymbol *MCAsmLayout::getBaseSymbol(const MCSymbol &Symbol) const {
   if (!Symbol.isVariable())
     return &Symbol;
 
   const MCExpr *Expr = Symbol.getVariableValue();
   MCValue Value;
   if (!Expr->evaluateAsValue(Value, *this)) {
     Assembler.getContext().reportError(
         Expr->getLoc(), "expression could not be evaluated");
     return nullptr;
   }
 
   const MCSymbolRefExpr *RefB = Value.getSymB();
   if (RefB) {
     Assembler.getContext().reportError(
         Expr->getLoc(), Twine("symbol '") + RefB->getSymbol().getName() +
                      "' could not be evaluated in a subtraction expression");
     return nullptr;
   }
 
   const MCSymbolRefExpr *A = Value.getSymA();
   if (!A)
     return nullptr;
 
   const MCSymbol &ASym = A->getSymbol();
   const MCAssembler &Asm = getAssembler();
   if (ASym.isCommon()) {
     Asm.getContext().reportError(Expr->getLoc(),
                                  "Common symbol '" + ASym.getName() +
                                      "' cannot be used in assignment expr");
     return nullptr;
   }
 
   return &ASym;
 }
 
 uint64_t MCAsmLayout::getSectionAddressSize(const MCSection *Sec) const {
   // The size is the last fragment's end offset.
   const MCFragment &F = Sec->getFragmentList().back();
   return getFragmentOffset(&F) + getAssembler().computeFragmentSize(*this, F);
 }
 
 uint64_t MCAsmLayout::getSectionFileSize(const MCSection *Sec) const {
   // Virtual sections have no file size.
   if (Sec->isVirtualSection())
     return 0;
 
   // Otherwise, the file size is the same as the address space size.
   return getSectionAddressSize(Sec);
 }
 
 uint64_t llvm::computeBundlePadding(const MCAssembler &Assembler,
                                     const MCEncodedFragment *F,
                                     uint64_t FOffset, uint64_t FSize) {
   uint64_t BundleSize = Assembler.getBundleAlignSize();
   assert(BundleSize > 0 &&
          "computeBundlePadding should only be called if bundling is enabled");
   uint64_t BundleMask = BundleSize - 1;
   uint64_t OffsetInBundle = FOffset & BundleMask;
   uint64_t EndOfFragment = OffsetInBundle + FSize;
 
   // There are two kinds of bundling restrictions:
   //
   // 1) For alignToBundleEnd(), add padding to ensure that the fragment will
   //    *end* on a bundle boundary.
   // 2) Otherwise, check if the fragment would cross a bundle boundary. If it
   //    would, add padding until the end of the bundle so that the fragment
   //    will start in a new one.
   if (F->alignToBundleEnd()) {
     // Three possibilities here:
     //
     // A) The fragment just happens to end at a bundle boundary, so we're good.
     // B) The fragment ends before the current bundle boundary: pad it just
     //    enough to reach the boundary.
     // C) The fragment ends after the current bundle boundary: pad it until it
     //    reaches the end of the next bundle boundary.
     //
     // Note: this code could be made shorter with some modulo trickery, but it's
     // intentionally kept in its more explicit form for simplicity.
     if (EndOfFragment == BundleSize)
       return 0;
     else if (EndOfFragment < BundleSize)
       return BundleSize - EndOfFragment;
     else { // EndOfFragment > BundleSize
       return 2 * BundleSize - EndOfFragment;
     }
   } else if (OffsetInBundle > 0 && EndOfFragment > BundleSize)
     return BundleSize - OffsetInBundle;
   else
     return 0;
 }
 
 /* *** */
 
 void ilist_alloc_traits<MCFragment>::deleteNode(MCFragment *V) { V->destroy(); }
 
 MCFragment::MCFragment(FragmentType Kind, bool HasInstructions,
                        MCSection *Parent)
     : Kind(Kind), HasInstructions(HasInstructions), LayoutOrder(0),
       Parent(Parent), Atom(nullptr), Offset(~UINT64_C(0)) {
   if (Parent && !isDummy())
     Parent->getFragmentList().push_back(this);
 }
 
 void MCFragment::destroy() {
   // First check if we are the sentinal.
   if (Kind == FragmentType(~0)) {
     delete this;
     return;
   }
 
   switch (Kind) {
     case FT_Align:
       delete cast<MCAlignFragment>(this);
       return;
     case FT_Data:
       delete cast<MCDataFragment>(this);
       return;
     case FT_CompactEncodedInst:
       delete cast<MCCompactEncodedInstFragment>(this);
       return;
     case FT_Fill:
       delete cast<MCFillFragment>(this);
       return;
     case FT_Relaxable:
       delete cast<MCRelaxableFragment>(this);
       return;
     case FT_Org:
       delete cast<MCOrgFragment>(this);
       return;
     case FT_Dwarf:
       delete cast<MCDwarfLineAddrFragment>(this);
       return;
     case FT_DwarfFrame:
       delete cast<MCDwarfCallFrameFragment>(this);
       return;
     case FT_LEB:
       delete cast<MCLEBFragment>(this);
       return;
+    case FT_BoundaryAlign:
+      delete cast<MCBoundaryAlignFragment>(this);
+      return;
     case FT_SymbolId:
       delete cast<MCSymbolIdFragment>(this);
       return;
     case FT_CVInlineLines:
       delete cast<MCCVInlineLineTableFragment>(this);
       return;
     case FT_CVDefRange:
       delete cast<MCCVDefRangeFragment>(this);
       return;
     case FT_Dummy:
       delete cast<MCDummyFragment>(this);
       return;
   }
 }
 
 // Debugging methods
 
 namespace llvm {
 
 raw_ostream &operator<<(raw_ostream &OS, const MCFixup &AF) {
   OS << "<MCFixup" << " Offset:" << AF.getOffset()
      << " Value:" << *AF.getValue()
      << " Kind:" << AF.getKind() << ">";
   return OS;
 }
 
 } // end namespace llvm
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
 LLVM_DUMP_METHOD void MCFragment::dump() const {
   raw_ostream &OS = errs();
 
   OS << "<";
   switch (getKind()) {
   case MCFragment::FT_Align: OS << "MCAlignFragment"; break;
   case MCFragment::FT_Data:  OS << "MCDataFragment"; break;
   case MCFragment::FT_CompactEncodedInst:
     OS << "MCCompactEncodedInstFragment"; break;
   case MCFragment::FT_Fill:  OS << "MCFillFragment"; break;
   case MCFragment::FT_Relaxable:  OS << "MCRelaxableFragment"; break;
   case MCFragment::FT_Org:   OS << "MCOrgFragment"; break;
   case MCFragment::FT_Dwarf: OS << "MCDwarfFragment"; break;
   case MCFragment::FT_DwarfFrame: OS << "MCDwarfCallFrameFragment"; break;
   case MCFragment::FT_LEB:   OS << "MCLEBFragment"; break;
+  case MCFragment::FT_BoundaryAlign: OS<<"MCBoundaryAlignFragment"; break;
   case MCFragment::FT_SymbolId:    OS << "MCSymbolIdFragment"; break;
   case MCFragment::FT_CVInlineLines: OS << "MCCVInlineLineTableFragment"; break;
   case MCFragment::FT_CVDefRange: OS << "MCCVDefRangeTableFragment"; break;
   case MCFragment::FT_Dummy: OS << "MCDummyFragment"; break;
   }
 
   OS << "<MCFragment " << (const void *)this << " LayoutOrder:" << LayoutOrder
      << " Offset:" << Offset << " HasInstructions:" << hasInstructions();
   if (const MCEncodedFragment *EF = dyn_cast<MCEncodedFragment>(this))
     OS << " BundlePadding:" << static_cast<unsigned>(EF->getBundlePadding());
   OS << ">";
 
   switch (getKind()) {
   case MCFragment::FT_Align: {
     const MCAlignFragment *AF = cast<MCAlignFragment>(this);
     if (AF->hasEmitNops())
       OS << " (emit nops)";
     OS << "\n       ";
     OS << " Alignment:" << AF->getAlignment()
        << " Value:" << AF->getValue() << " ValueSize:" << AF->getValueSize()
        << " MaxBytesToEmit:" << AF->getMaxBytesToEmit() << ">";
     break;
   }
   case MCFragment::FT_Data:  {
     const MCDataFragment *DF = cast<MCDataFragment>(this);
     OS << "\n       ";
     OS << " Contents:[";
     const SmallVectorImpl<char> &Contents = DF->getContents();
     for (unsigned i = 0, e = Contents.size(); i != e; ++i) {
       if (i) OS << ",";
       OS << hexdigit((Contents[i] >> 4) & 0xF) << hexdigit(Contents[i] & 0xF);
     }
     OS << "] (" << Contents.size() << " bytes)";
 
     if (DF->fixup_begin() != DF->fixup_end()) {
       OS << ",\n       ";
       OS << " Fixups:[";
       for (MCDataFragment::const_fixup_iterator it = DF->fixup_begin(),
              ie = DF->fixup_end(); it != ie; ++it) {
         if (it != DF->fixup_begin()) OS << ",\n                ";
         OS << *it;
       }
       OS << "]";
     }
     break;
   }
   case MCFragment::FT_CompactEncodedInst: {
     const MCCompactEncodedInstFragment *CEIF =
       cast<MCCompactEncodedInstFragment>(this);
     OS << "\n       ";
     OS << " Contents:[";
     const SmallVectorImpl<char> &Contents = CEIF->getContents();
     for (unsigned i = 0, e = Contents.size(); i != e; ++i) {
       if (i) OS << ",";
       OS << hexdigit((Contents[i] >> 4) & 0xF) << hexdigit(Contents[i] & 0xF);
     }
     OS << "] (" << Contents.size() << " bytes)";
     break;
   }
   case MCFragment::FT_Fill:  {
     const MCFillFragment *FF = cast<MCFillFragment>(this);
     OS << " Value:" << static_cast<unsigned>(FF->getValue())
        << " ValueSize:" << static_cast<unsigned>(FF->getValueSize())
        << " NumValues:" << FF->getNumValues();
     break;
   }
   case MCFragment::FT_Relaxable:  {
     const MCRelaxableFragment *F = cast<MCRelaxableFragment>(this);
     OS << "\n       ";
     OS << " Inst:";
     F->getInst().dump_pretty(OS);
     break;
   }
   case MCFragment::FT_Org:  {
     const MCOrgFragment *OF = cast<MCOrgFragment>(this);
     OS << "\n       ";
     OS << " Offset:" << OF->getOffset()
        << " Value:" << static_cast<unsigned>(OF->getValue());
     break;
   }
   case MCFragment::FT_Dwarf:  {
     const MCDwarfLineAddrFragment *OF = cast<MCDwarfLineAddrFragment>(this);
     OS << "\n       ";
     OS << " AddrDelta:" << OF->getAddrDelta()
        << " LineDelta:" << OF->getLineDelta();
     break;
   }
   case MCFragment::FT_DwarfFrame:  {
     const MCDwarfCallFrameFragment *CF = cast<MCDwarfCallFrameFragment>(this);
     OS << "\n       ";
     OS << " AddrDelta:" << CF->getAddrDelta();
     break;
   }
   case MCFragment::FT_LEB: {
     const MCLEBFragment *LF = cast<MCLEBFragment>(this);
     OS << "\n       ";
     OS << " Value:" << LF->getValue() << " Signed:" << LF->isSigned();
     break;
   }
+  case MCFragment::FT_BoundaryAlign: {
+    const auto *BF = cast<MCBoundaryAlignFragment>(this);
+    if (BF->canEmitNops())
+      OS << " (can emit nops to align";
+    if (BF->isFused())
+      OS << " fused branch)";
+    else
+      OS << " unfused branch)";
+    OS << "\n       ";
+    OS << " BoundarySize:" << BF->getAlignment().value()
+       << " Size:" << BF->getSize();
+    break;
+  }
   case MCFragment::FT_SymbolId: {
     const MCSymbolIdFragment *F = cast<MCSymbolIdFragment>(this);
     OS << "\n       ";
     OS << " Sym:" << F->getSymbol();
     break;
   }
   case MCFragment::FT_CVInlineLines: {
     const auto *F = cast<MCCVInlineLineTableFragment>(this);
     OS << "\n       ";
     OS << " Sym:" << *F->getFnStartSym();
     break;
   }
   case MCFragment::FT_CVDefRange: {
     const auto *F = cast<MCCVDefRangeFragment>(this);
     OS << "\n       ";
     for (std::pair<const MCSymbol *, const MCSymbol *> RangeStartEnd :
          F->getRanges()) {
       OS << " RangeStart:" << RangeStartEnd.first;
       OS << " RangeEnd:" << RangeStartEnd.second;
     }
     break;
   }
   case MCFragment::FT_Dummy:
     break;
   }
   OS << ">";
 }
 #endif
diff --git a/llvm/lib/MC/MCObjectStreamer.cpp b/llvm/lib/MC/MCObjectStreamer.cpp
index 1ed6ec1015b2..5c42667f9910 100644
--- a/llvm/lib/MC/MCObjectStreamer.cpp
+++ b/llvm/lib/MC/MCObjectStreamer.cpp
@@ -1,765 +1,772 @@
 //===- lib/MC/MCObjectStreamer.cpp - Object File MCStreamer Interface -----===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/MC/MCObjectStreamer.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/MC/MCAsmBackend.h"
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCCodeEmitter.h"
 #include "llvm/MC/MCCodeView.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCDwarf.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCObjectWriter.h"
 #include "llvm/MC/MCSection.h"
 #include "llvm/MC/MCSymbol.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/SourceMgr.h"
 using namespace llvm;
 
 MCObjectStreamer::MCObjectStreamer(MCContext &Context,
                                    std::unique_ptr<MCAsmBackend> TAB,
                                    std::unique_ptr<MCObjectWriter> OW,
                                    std::unique_ptr<MCCodeEmitter> Emitter)
     : MCStreamer(Context),
       Assembler(std::make_unique<MCAssembler>(
           Context, std::move(TAB), std::move(Emitter), std::move(OW))),
       EmitEHFrame(true), EmitDebugFrame(false) {}
 
 MCObjectStreamer::~MCObjectStreamer() {}
 
 // AssemblerPtr is used for evaluation of expressions and causes
 // difference between asm and object outputs. Return nullptr to in
 // inline asm mode to limit divergence to assembly inputs.
 MCAssembler *MCObjectStreamer::getAssemblerPtr() {
   if (getUseAssemblerInfoForParsing())
     return Assembler.get();
   return nullptr;
 }
 
 void MCObjectStreamer::addPendingLabel(MCSymbol* S) {
   MCSection *CurSection = getCurrentSectionOnly();
   if (CurSection) {
     // Register labels that have not yet been assigned to a Section.
     if (!PendingLabels.empty()) {
       for (MCSymbol* Sym : PendingLabels)
         CurSection->addPendingLabel(Sym);
       PendingLabels.clear();
     }
 
     // Add this label to the current Section / Subsection.
     CurSection->addPendingLabel(S, CurSubsectionIdx);
 
     // Add this Section to the list of PendingLabelSections.
     auto SecIt = std::find(PendingLabelSections.begin(),
                            PendingLabelSections.end(), CurSection);
     if (SecIt == PendingLabelSections.end())
       PendingLabelSections.push_back(CurSection);
   }
   else
     // There is no Section / Subsection for this label yet.
     PendingLabels.push_back(S);
 }
 
 void MCObjectStreamer::flushPendingLabels(MCFragment *F, uint64_t FOffset) {
   MCSection *CurSection = getCurrentSectionOnly();
   if (!CurSection) {
     assert(PendingLabels.empty());
     return;
   }
   // Register labels that have not yet been assigned to a Section.
   if (!PendingLabels.empty()) {
     for (MCSymbol* Sym : PendingLabels)
       CurSection->addPendingLabel(Sym, CurSubsectionIdx);
     PendingLabels.clear();
   }
 
   // Associate a fragment with this label, either the supplied fragment
   // or an empty data fragment.
   if (F)
     CurSection->flushPendingLabels(F, FOffset, CurSubsectionIdx);
   else
     CurSection->flushPendingLabels(nullptr, 0, CurSubsectionIdx);
 }
 
 void MCObjectStreamer::flushPendingLabels() {
   // Register labels that have not yet been assigned to a Section.
   if (!PendingLabels.empty()) {
     MCSection *CurSection = getCurrentSectionOnly();
     assert(CurSection);
     for (MCSymbol* Sym : PendingLabels)
       CurSection->addPendingLabel(Sym, CurSubsectionIdx);
     PendingLabels.clear();
   }
 
   // Assign an empty data fragment to all remaining pending labels.
   for (MCSection* Section : PendingLabelSections)
     Section->flushPendingLabels();
 }
 
 // When fixup's offset is a forward declared label, e.g.:
 //
 //   .reloc 1f, R_MIPS_JALR, foo
 // 1: nop
 //
 // postpone adding it to Fixups vector until the label is defined and its offset
 // is known.
 void MCObjectStreamer::resolvePendingFixups() {
   for (PendingMCFixup &PendingFixup : PendingFixups) {
     if (!PendingFixup.Sym || PendingFixup.Sym->isUndefined ()) {
       getContext().reportError(PendingFixup.Fixup.getLoc(),
                                "unresolved relocation offset");
       continue;
     }
     flushPendingLabels(PendingFixup.DF, PendingFixup.DF->getContents().size());
     PendingFixup.Fixup.setOffset(PendingFixup.Sym->getOffset());
     PendingFixup.DF->getFixups().push_back(PendingFixup.Fixup);
   }
   PendingFixups.clear();
 }
 
 // As a compile-time optimization, avoid allocating and evaluating an MCExpr
 // tree for (Hi - Lo) when Hi and Lo are offsets into the same fragment.
 static Optional<uint64_t>
 absoluteSymbolDiff(MCAssembler &Asm, const MCSymbol *Hi, const MCSymbol *Lo) {
   assert(Hi && Lo);
   if (Asm.getBackendPtr()->requiresDiffExpressionRelocations())
     return None;
 
   if (!Hi->getFragment() || Hi->getFragment() != Lo->getFragment() ||
       Hi->isVariable() || Lo->isVariable())
     return None;
 
   return Hi->getOffset() - Lo->getOffset();
 }
 
 void MCObjectStreamer::emitAbsoluteSymbolDiff(const MCSymbol *Hi,
                                               const MCSymbol *Lo,
                                               unsigned Size) {
   if (Optional<uint64_t> Diff = absoluteSymbolDiff(getAssembler(), Hi, Lo)) {
     EmitIntValue(*Diff, Size);
     return;
   }
   MCStreamer::emitAbsoluteSymbolDiff(Hi, Lo, Size);
 }
 
 void MCObjectStreamer::emitAbsoluteSymbolDiffAsULEB128(const MCSymbol *Hi,
                                                        const MCSymbol *Lo) {
   if (Optional<uint64_t> Diff = absoluteSymbolDiff(getAssembler(), Hi, Lo)) {
     EmitULEB128IntValue(*Diff);
     return;
   }
   MCStreamer::emitAbsoluteSymbolDiffAsULEB128(Hi, Lo);
 }
 
 void MCObjectStreamer::reset() {
   if (Assembler)
     Assembler->reset();
   CurInsertionPoint = MCSection::iterator();
   EmitEHFrame = true;
   EmitDebugFrame = false;
   PendingLabels.clear();
   PendingLabelSections.clear();
   MCStreamer::reset();
 }
 
 void MCObjectStreamer::EmitFrames(MCAsmBackend *MAB) {
   if (!getNumFrameInfos())
     return;
 
   if (EmitEHFrame)
     MCDwarfFrameEmitter::Emit(*this, MAB, true);
 
   if (EmitDebugFrame)
     MCDwarfFrameEmitter::Emit(*this, MAB, false);
 }
 
 MCFragment *MCObjectStreamer::getCurrentFragment() const {
   assert(getCurrentSectionOnly() && "No current section!");
 
   if (CurInsertionPoint != getCurrentSectionOnly()->getFragmentList().begin())
     return &*std::prev(CurInsertionPoint);
 
   return nullptr;
 }
 
 static bool CanReuseDataFragment(const MCDataFragment &F,
                                  const MCAssembler &Assembler,
                                  const MCSubtargetInfo *STI) {
   if (!F.hasInstructions())
     return true;
   // When bundling is enabled, we don't want to add data to a fragment that
   // already has instructions (see MCELFStreamer::EmitInstToData for details)
   if (Assembler.isBundlingEnabled())
     return Assembler.getRelaxAll();
   // If the subtarget is changed mid fragment we start a new fragment to record
   // the new STI.
   return !STI || F.getSubtargetInfo() == STI;
 }
 
 MCDataFragment *
 MCObjectStreamer::getOrCreateDataFragment(const MCSubtargetInfo *STI) {
   MCDataFragment *F = dyn_cast_or_null<MCDataFragment>(getCurrentFragment());
   if (!F || !CanReuseDataFragment(*F, *Assembler, STI)) {
     F = new MCDataFragment();
     insert(F);
   }
   return F;
 }
 
 void MCObjectStreamer::visitUsedSymbol(const MCSymbol &Sym) {
   Assembler->registerSymbol(Sym);
 }
 
 void MCObjectStreamer::EmitCFISections(bool EH, bool Debug) {
   MCStreamer::EmitCFISections(EH, Debug);
   EmitEHFrame = EH;
   EmitDebugFrame = Debug;
 }
 
 void MCObjectStreamer::EmitValueImpl(const MCExpr *Value, unsigned Size,
                                      SMLoc Loc) {
   MCStreamer::EmitValueImpl(Value, Size, Loc);
   MCDataFragment *DF = getOrCreateDataFragment();
   flushPendingLabels(DF, DF->getContents().size());
 
   MCDwarfLineEntry::Make(this, getCurrentSectionOnly());
 
   // Avoid fixups when possible.
   int64_t AbsValue;
   if (Value->evaluateAsAbsolute(AbsValue, getAssemblerPtr())) {
     if (!isUIntN(8 * Size, AbsValue) && !isIntN(8 * Size, AbsValue)) {
       getContext().reportError(
           Loc, "value evaluated as " + Twine(AbsValue) + " is out of range.");
       return;
     }
     EmitIntValue(AbsValue, Size);
     return;
   }
   DF->getFixups().push_back(
       MCFixup::create(DF->getContents().size(), Value,
                       MCFixup::getKindForSize(Size, false), Loc));
   DF->getContents().resize(DF->getContents().size() + Size, 0);
 }
 
 MCSymbol *MCObjectStreamer::EmitCFILabel() {
   MCSymbol *Label = getContext().createTempSymbol("cfi", true);
   EmitLabel(Label);
   return Label;
 }
 
 void MCObjectStreamer::EmitCFIStartProcImpl(MCDwarfFrameInfo &Frame) {
   // We need to create a local symbol to avoid relocations.
   Frame.Begin = getContext().createTempSymbol();
   EmitLabel(Frame.Begin);
 }
 
 void MCObjectStreamer::EmitCFIEndProcImpl(MCDwarfFrameInfo &Frame) {
   Frame.End = getContext().createTempSymbol();
   EmitLabel(Frame.End);
 }
 
 void MCObjectStreamer::EmitLabel(MCSymbol *Symbol, SMLoc Loc) {
   MCStreamer::EmitLabel(Symbol, Loc);
 
   getAssembler().registerSymbol(*Symbol);
 
   // If there is a current fragment, mark the symbol as pointing into it.
   // Otherwise queue the label and set its fragment pointer when we emit the
   // next fragment.
   auto *F = dyn_cast_or_null<MCDataFragment>(getCurrentFragment());
   if (F && !(getAssembler().isBundlingEnabled() &&
              getAssembler().getRelaxAll())) {
     Symbol->setFragment(F);
     Symbol->setOffset(F->getContents().size());
   } else {
     // Assign all pending labels to offset 0 within the dummy "pending"
     // fragment. (They will all be reassigned to a real fragment in
     // flushPendingLabels())
     Symbol->setOffset(0);
     addPendingLabel(Symbol);
   }
 }
 
 // Emit a label at a previously emitted fragment/offset position. This must be
 // within the currently-active section.
 void MCObjectStreamer::EmitLabelAtPos(MCSymbol *Symbol, SMLoc Loc,
                                       MCFragment *F, uint64_t Offset) {
   assert(F->getParent() == getCurrentSectionOnly());
 
   MCStreamer::EmitLabel(Symbol, Loc);
   getAssembler().registerSymbol(*Symbol);
   auto *DF = dyn_cast_or_null<MCDataFragment>(F);
   Symbol->setOffset(Offset);
   if (DF) {
     Symbol->setFragment(F);
   } else {
     assert(isa<MCDummyFragment>(F) &&
            "F must either be an MCDataFragment or the pending MCDummyFragment");
     assert(Offset == 0);
     addPendingLabel(Symbol);
   }
 }
 
 void MCObjectStreamer::EmitULEB128Value(const MCExpr *Value) {
   int64_t IntValue;
   if (Value->evaluateAsAbsolute(IntValue, getAssemblerPtr())) {
     EmitULEB128IntValue(IntValue);
     return;
   }
   insert(new MCLEBFragment(*Value, false));
 }
 
 void MCObjectStreamer::EmitSLEB128Value(const MCExpr *Value) {
   int64_t IntValue;
   if (Value->evaluateAsAbsolute(IntValue, getAssemblerPtr())) {
     EmitSLEB128IntValue(IntValue);
     return;
   }
   insert(new MCLEBFragment(*Value, true));
 }
 
 void MCObjectStreamer::EmitWeakReference(MCSymbol *Alias,
                                          const MCSymbol *Symbol) {
   report_fatal_error("This file format doesn't support weak aliases.");
 }
 
 void MCObjectStreamer::ChangeSection(MCSection *Section,
                                      const MCExpr *Subsection) {
   changeSectionImpl(Section, Subsection);
 }
 
 bool MCObjectStreamer::changeSectionImpl(MCSection *Section,
                                          const MCExpr *Subsection) {
   assert(Section && "Cannot switch to a null section!");
   getContext().clearDwarfLocSeen();
 
   bool Created = getAssembler().registerSection(*Section);
 
   int64_t IntSubsection = 0;
   if (Subsection &&
       !Subsection->evaluateAsAbsolute(IntSubsection, getAssemblerPtr()))
     report_fatal_error("Cannot evaluate subsection number");
   if (IntSubsection < 0 || IntSubsection > 8192)
     report_fatal_error("Subsection number out of range");
   CurSubsectionIdx = unsigned(IntSubsection);
   CurInsertionPoint =
       Section->getSubsectionInsertionPoint(CurSubsectionIdx);
   return Created;
 }
 
 void MCObjectStreamer::EmitAssignment(MCSymbol *Symbol, const MCExpr *Value) {
   getAssembler().registerSymbol(*Symbol);
   MCStreamer::EmitAssignment(Symbol, Value);
 }
 
 bool MCObjectStreamer::mayHaveInstructions(MCSection &Sec) const {
   return Sec.hasInstructions();
 }
 
 void MCObjectStreamer::EmitInstruction(const MCInst &Inst,
                                        const MCSubtargetInfo &STI) {
+  getAssembler().getBackend().alignBranchesBegin(*this, Inst);
+  EmitInstructionImpl(Inst, STI);
+  getAssembler().getBackend().alignBranchesEnd(*this, Inst);
+}
+
+void MCObjectStreamer::EmitInstructionImpl(const MCInst &Inst,
+                                           const MCSubtargetInfo &STI) {
   MCStreamer::EmitInstruction(Inst, STI);
 
   MCSection *Sec = getCurrentSectionOnly();
   Sec->setHasInstructions(true);
 
   // Now that a machine instruction has been assembled into this section, make
   // a line entry for any .loc directive that has been seen.
   MCDwarfLineEntry::Make(this, getCurrentSectionOnly());
 
   // If this instruction doesn't need relaxation, just emit it as data.
   MCAssembler &Assembler = getAssembler();
   if (!Assembler.getBackend().mayNeedRelaxation(Inst, STI)) {
     EmitInstToData(Inst, STI);
     return;
   }
 
   // Otherwise, relax and emit it as data if either:
   // - The RelaxAll flag was passed
   // - Bundling is enabled and this instruction is inside a bundle-locked
   //   group. We want to emit all such instructions into the same data
   //   fragment.
   if (Assembler.getRelaxAll() ||
       (Assembler.isBundlingEnabled() && Sec->isBundleLocked())) {
     MCInst Relaxed;
     getAssembler().getBackend().relaxInstruction(Inst, STI, Relaxed);
     while (getAssembler().getBackend().mayNeedRelaxation(Relaxed, STI))
       getAssembler().getBackend().relaxInstruction(Relaxed, STI, Relaxed);
     EmitInstToData(Relaxed, STI);
     return;
   }
 
   // Otherwise emit to a separate fragment.
   EmitInstToFragment(Inst, STI);
 }
 
 void MCObjectStreamer::EmitInstToFragment(const MCInst &Inst,
                                           const MCSubtargetInfo &STI) {
   if (getAssembler().getRelaxAll() && getAssembler().isBundlingEnabled())
     llvm_unreachable("All instructions should have already been relaxed");
 
   // Always create a new, separate fragment here, because its size can change
   // during relaxation.
   MCRelaxableFragment *IF = new MCRelaxableFragment(Inst, STI);
   insert(IF);
 
   SmallString<128> Code;
   raw_svector_ostream VecOS(Code);
   getAssembler().getEmitter().encodeInstruction(Inst, VecOS, IF->getFixups(),
                                                 STI);
   IF->getContents().append(Code.begin(), Code.end());
 }
 
 #ifndef NDEBUG
 static const char *const BundlingNotImplementedMsg =
   "Aligned bundling is not implemented for this object format";
 #endif
 
 void MCObjectStreamer::EmitBundleAlignMode(unsigned AlignPow2) {
   llvm_unreachable(BundlingNotImplementedMsg);
 }
 
 void MCObjectStreamer::EmitBundleLock(bool AlignToEnd) {
   llvm_unreachable(BundlingNotImplementedMsg);
 }
 
 void MCObjectStreamer::EmitBundleUnlock() {
   llvm_unreachable(BundlingNotImplementedMsg);
 }
 
 void MCObjectStreamer::EmitDwarfLocDirective(unsigned FileNo, unsigned Line,
                                              unsigned Column, unsigned Flags,
                                              unsigned Isa,
                                              unsigned Discriminator,
                                              StringRef FileName) {
   // In case we see two .loc directives in a row, make sure the
   // first one gets a line entry.
   MCDwarfLineEntry::Make(this, getCurrentSectionOnly());
 
   this->MCStreamer::EmitDwarfLocDirective(FileNo, Line, Column, Flags,
                                           Isa, Discriminator, FileName);
 }
 
 static const MCExpr *buildSymbolDiff(MCObjectStreamer &OS, const MCSymbol *A,
                                      const MCSymbol *B) {
   MCContext &Context = OS.getContext();
   MCSymbolRefExpr::VariantKind Variant = MCSymbolRefExpr::VK_None;
   const MCExpr *ARef = MCSymbolRefExpr::create(A, Variant, Context);
   const MCExpr *BRef = MCSymbolRefExpr::create(B, Variant, Context);
   const MCExpr *AddrDelta =
       MCBinaryExpr::create(MCBinaryExpr::Sub, ARef, BRef, Context);
   return AddrDelta;
 }
 
 static void emitDwarfSetLineAddr(MCObjectStreamer &OS,
                                  MCDwarfLineTableParams Params,
                                  int64_t LineDelta, const MCSymbol *Label,
                                  int PointerSize) {
   // emit the sequence to set the address
   OS.EmitIntValue(dwarf::DW_LNS_extended_op, 1);
   OS.EmitULEB128IntValue(PointerSize + 1);
   OS.EmitIntValue(dwarf::DW_LNE_set_address, 1);
   OS.EmitSymbolValue(Label, PointerSize);
 
   // emit the sequence for the LineDelta (from 1) and a zero address delta.
   MCDwarfLineAddr::Emit(&OS, Params, LineDelta, 0);
 }
 
 void MCObjectStreamer::EmitDwarfAdvanceLineAddr(int64_t LineDelta,
                                                 const MCSymbol *LastLabel,
                                                 const MCSymbol *Label,
                                                 unsigned PointerSize) {
   if (!LastLabel) {
     emitDwarfSetLineAddr(*this, Assembler->getDWARFLinetableParams(), LineDelta,
                          Label, PointerSize);
     return;
   }
   const MCExpr *AddrDelta = buildSymbolDiff(*this, Label, LastLabel);
   int64_t Res;
   if (AddrDelta->evaluateAsAbsolute(Res, getAssemblerPtr())) {
     MCDwarfLineAddr::Emit(this, Assembler->getDWARFLinetableParams(), LineDelta,
                           Res);
     return;
   }
   insert(new MCDwarfLineAddrFragment(LineDelta, *AddrDelta));
 }
 
 void MCObjectStreamer::EmitDwarfAdvanceFrameAddr(const MCSymbol *LastLabel,
                                                  const MCSymbol *Label) {
   const MCExpr *AddrDelta = buildSymbolDiff(*this, Label, LastLabel);
   int64_t Res;
   if (AddrDelta->evaluateAsAbsolute(Res, getAssemblerPtr())) {
     MCDwarfFrameEmitter::EmitAdvanceLoc(*this, Res);
     return;
   }
   insert(new MCDwarfCallFrameFragment(*AddrDelta));
 }
 
 void MCObjectStreamer::EmitCVLocDirective(unsigned FunctionId, unsigned FileNo,
                                           unsigned Line, unsigned Column,
                                           bool PrologueEnd, bool IsStmt,
                                           StringRef FileName, SMLoc Loc) {
   // Validate the directive.
   if (!checkCVLocSection(FunctionId, FileNo, Loc))
     return;
 
   // Emit a label at the current position and record it in the CodeViewContext.
   MCSymbol *LineSym = getContext().createTempSymbol();
   EmitLabel(LineSym);
   getContext().getCVContext().recordCVLoc(getContext(), LineSym, FunctionId,
                                           FileNo, Line, Column, PrologueEnd,
                                           IsStmt);
 }
 
 void MCObjectStreamer::EmitCVLinetableDirective(unsigned FunctionId,
                                                 const MCSymbol *Begin,
                                                 const MCSymbol *End) {
   getContext().getCVContext().emitLineTableForFunction(*this, FunctionId, Begin,
                                                        End);
   this->MCStreamer::EmitCVLinetableDirective(FunctionId, Begin, End);
 }
 
 void MCObjectStreamer::EmitCVInlineLinetableDirective(
     unsigned PrimaryFunctionId, unsigned SourceFileId, unsigned SourceLineNum,
     const MCSymbol *FnStartSym, const MCSymbol *FnEndSym) {
   getContext().getCVContext().emitInlineLineTableForFunction(
       *this, PrimaryFunctionId, SourceFileId, SourceLineNum, FnStartSym,
       FnEndSym);
   this->MCStreamer::EmitCVInlineLinetableDirective(
       PrimaryFunctionId, SourceFileId, SourceLineNum, FnStartSym, FnEndSym);
 }
 
 void MCObjectStreamer::EmitCVDefRangeDirective(
     ArrayRef<std::pair<const MCSymbol *, const MCSymbol *>> Ranges,
     StringRef FixedSizePortion) {
   MCFragment *Frag =
       getContext().getCVContext().emitDefRange(*this, Ranges, FixedSizePortion);
   // Attach labels that were pending before we created the defrange fragment to
   // the beginning of the new fragment.
   flushPendingLabels(Frag, 0);
   this->MCStreamer::EmitCVDefRangeDirective(Ranges, FixedSizePortion);
 }
 
 void MCObjectStreamer::EmitCVStringTableDirective() {
   getContext().getCVContext().emitStringTable(*this);
 }
 void MCObjectStreamer::EmitCVFileChecksumsDirective() {
   getContext().getCVContext().emitFileChecksums(*this);
 }
 
 void MCObjectStreamer::EmitCVFileChecksumOffsetDirective(unsigned FileNo) {
   getContext().getCVContext().emitFileChecksumOffset(*this, FileNo);
 }
 
 void MCObjectStreamer::EmitBytes(StringRef Data) {
   MCDwarfLineEntry::Make(this, getCurrentSectionOnly());
   MCDataFragment *DF = getOrCreateDataFragment();
   flushPendingLabels(DF, DF->getContents().size());
   DF->getContents().append(Data.begin(), Data.end());
 
   // EmitBytes might not cover all possible ways we emit data (or could be used
   // to emit executable code in some cases), but is the best method we have
   // right now for checking this.
   MCSection *Sec = getCurrentSectionOnly();
   Sec->setHasData(true);
 }
 
 void MCObjectStreamer::EmitValueToAlignment(unsigned ByteAlignment,
                                             int64_t Value,
                                             unsigned ValueSize,
                                             unsigned MaxBytesToEmit) {
   if (MaxBytesToEmit == 0)
     MaxBytesToEmit = ByteAlignment;
   insert(new MCAlignFragment(ByteAlignment, Value, ValueSize, MaxBytesToEmit));
 
   // Update the maximum alignment on the current section if necessary.
   MCSection *CurSec = getCurrentSectionOnly();
   if (ByteAlignment > CurSec->getAlignment())
     CurSec->setAlignment(Align(ByteAlignment));
 }
 
 void MCObjectStreamer::EmitCodeAlignment(unsigned ByteAlignment,
                                          unsigned MaxBytesToEmit) {
   EmitValueToAlignment(ByteAlignment, 0, 1, MaxBytesToEmit);
   cast<MCAlignFragment>(getCurrentFragment())->setEmitNops(true);
 }
 
 void MCObjectStreamer::emitValueToOffset(const MCExpr *Offset,
                                          unsigned char Value,
                                          SMLoc Loc) {
   insert(new MCOrgFragment(*Offset, Value, Loc));
 }
 
 // Associate DTPRel32 fixup with data and resize data area
 void MCObjectStreamer::EmitDTPRel32Value(const MCExpr *Value) {
   MCDataFragment *DF = getOrCreateDataFragment();
   flushPendingLabels(DF, DF->getContents().size());
 
   DF->getFixups().push_back(MCFixup::create(DF->getContents().size(),
                                             Value, FK_DTPRel_4));
   DF->getContents().resize(DF->getContents().size() + 4, 0);
 }
 
 // Associate DTPRel64 fixup with data and resize data area
 void MCObjectStreamer::EmitDTPRel64Value(const MCExpr *Value) {
   MCDataFragment *DF = getOrCreateDataFragment();
   flushPendingLabels(DF, DF->getContents().size());
 
   DF->getFixups().push_back(MCFixup::create(DF->getContents().size(),
                                             Value, FK_DTPRel_8));
   DF->getContents().resize(DF->getContents().size() + 8, 0);
 }
 
 // Associate TPRel32 fixup with data and resize data area
 void MCObjectStreamer::EmitTPRel32Value(const MCExpr *Value) {
   MCDataFragment *DF = getOrCreateDataFragment();
   flushPendingLabels(DF, DF->getContents().size());
 
   DF->getFixups().push_back(MCFixup::create(DF->getContents().size(),
                                             Value, FK_TPRel_4));
   DF->getContents().resize(DF->getContents().size() + 4, 0);
 }
 
 // Associate TPRel64 fixup with data and resize data area
 void MCObjectStreamer::EmitTPRel64Value(const MCExpr *Value) {
   MCDataFragment *DF = getOrCreateDataFragment();
   flushPendingLabels(DF, DF->getContents().size());
 
   DF->getFixups().push_back(MCFixup::create(DF->getContents().size(),
                                             Value, FK_TPRel_8));
   DF->getContents().resize(DF->getContents().size() + 8, 0);
 }
 
 // Associate GPRel32 fixup with data and resize data area
 void MCObjectStreamer::EmitGPRel32Value(const MCExpr *Value) {
   MCDataFragment *DF = getOrCreateDataFragment();
   flushPendingLabels(DF, DF->getContents().size());
 
   DF->getFixups().push_back(
       MCFixup::create(DF->getContents().size(), Value, FK_GPRel_4));
   DF->getContents().resize(DF->getContents().size() + 4, 0);
 }
 
 // Associate GPRel64 fixup with data and resize data area
 void MCObjectStreamer::EmitGPRel64Value(const MCExpr *Value) {
   MCDataFragment *DF = getOrCreateDataFragment();
   flushPendingLabels(DF, DF->getContents().size());
 
   DF->getFixups().push_back(
       MCFixup::create(DF->getContents().size(), Value, FK_GPRel_4));
   DF->getContents().resize(DF->getContents().size() + 8, 0);
 }
 
 bool MCObjectStreamer::EmitRelocDirective(const MCExpr &Offset, StringRef Name,
                                           const MCExpr *Expr, SMLoc Loc,
                                           const MCSubtargetInfo &STI) {
   Optional<MCFixupKind> MaybeKind = Assembler->getBackend().getFixupKind(Name);
   if (!MaybeKind.hasValue())
     return true;
 
   MCFixupKind Kind = *MaybeKind;
 
   if (Expr == nullptr)
     Expr =
         MCSymbolRefExpr::create(getContext().createTempSymbol(), getContext());
 
   MCDataFragment *DF = getOrCreateDataFragment(&STI);
   flushPendingLabels(DF, DF->getContents().size());
 
   int64_t OffsetValue;
   if (Offset.evaluateAsAbsolute(OffsetValue)) {
     if (OffsetValue < 0)
       llvm_unreachable(".reloc offset is negative");
     DF->getFixups().push_back(MCFixup::create(OffsetValue, Expr, Kind, Loc));
     return false;
   }
 
   if (Offset.getKind() != llvm::MCExpr::SymbolRef)
     llvm_unreachable(".reloc offset is not absolute nor a label");
 
   const MCSymbolRefExpr &SRE = cast<MCSymbolRefExpr>(Offset);
   if (SRE.getSymbol().isDefined()) {
     DF->getFixups().push_back(MCFixup::create(SRE.getSymbol().getOffset(),
                                               Expr, Kind, Loc));
     return false;
   }
 
   PendingFixups.emplace_back(&SRE.getSymbol(), DF,
                                          MCFixup::create(-1, Expr, Kind, Loc));
   return false;
 }
 
 void MCObjectStreamer::emitFill(const MCExpr &NumBytes, uint64_t FillValue,
                                 SMLoc Loc) {
   MCDataFragment *DF = getOrCreateDataFragment();
   flushPendingLabels(DF, DF->getContents().size());
 
   assert(getCurrentSectionOnly() && "need a section");
   insert(new MCFillFragment(FillValue, 1, NumBytes, Loc));
 }
 
 void MCObjectStreamer::emitFill(const MCExpr &NumValues, int64_t Size,
                                 int64_t Expr, SMLoc Loc) {
   int64_t IntNumValues;
   // Do additional checking now if we can resolve the value.
   if (NumValues.evaluateAsAbsolute(IntNumValues, getAssemblerPtr())) {
     if (IntNumValues < 0) {
       getContext().getSourceManager()->PrintMessage(
           Loc, SourceMgr::DK_Warning,
           "'.fill' directive with negative repeat count has no effect");
       return;
     }
     // Emit now if we can for better errors.
     int64_t NonZeroSize = Size > 4 ? 4 : Size;
     Expr &= ~0ULL >> (64 - NonZeroSize * 8);
     for (uint64_t i = 0, e = IntNumValues; i != e; ++i) {
       EmitIntValue(Expr, NonZeroSize);
       if (NonZeroSize < Size)
         EmitIntValue(0, Size - NonZeroSize);
     }
     return;
   }
 
   // Otherwise emit as fragment.
   MCDataFragment *DF = getOrCreateDataFragment();
   flushPendingLabels(DF, DF->getContents().size());
 
   assert(getCurrentSectionOnly() && "need a section");
   insert(new MCFillFragment(Expr, Size, NumValues, Loc));
 }
 
 void MCObjectStreamer::EmitFileDirective(StringRef Filename) {
   getAssembler().addFileName(Filename);
 }
 
 void MCObjectStreamer::EmitAddrsig() {
   getAssembler().getWriter().emitAddrsigSection();
 }
 
 void MCObjectStreamer::EmitAddrsigSym(const MCSymbol *Sym) {
   getAssembler().registerSymbol(*Sym);
   getAssembler().getWriter().addAddrsigSymbol(Sym);
 }
 
 void MCObjectStreamer::FinishImpl() {
   getContext().RemapDebugPaths();
 
   // If we are generating dwarf for assembly source files dump out the sections.
   if (getContext().getGenDwarfForAssembly())
     MCGenDwarfInfo::Emit(this);
 
   // Dump out the dwarf file & directory tables and line tables.
   MCDwarfLineTable::Emit(this, getAssembler().getDWARFLinetableParams());
 
   // Update any remaining pending labels with empty data fragments.
   flushPendingLabels();
 
   resolvePendingFixups();
   getAssembler().Finish();
 }
diff --git a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
index 1ccb9b7cbf74..afcd244b1441 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
@@ -1,894 +1,1179 @@
 //===-- X86AsmBackend.cpp - X86 Assembler Backend -------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "MCTargetDesc/X86BaseInfo.h"
 #include "MCTargetDesc/X86FixupKinds.h"
 #include "llvm/ADT/StringSwitch.h"
 #include "llvm/BinaryFormat/ELF.h"
 #include "llvm/BinaryFormat/MachO.h"
 #include "llvm/MC/MCAsmBackend.h"
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCDwarf.h"
 #include "llvm/MC/MCELFObjectWriter.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCFixupKindInfo.h"
 #include "llvm/MC/MCInst.h"
+#include "llvm/MC/MCInstrInfo.h"
 #include "llvm/MC/MCMachObjectWriter.h"
+#include "llvm/MC/MCObjectStreamer.h"
 #include "llvm/MC/MCObjectWriter.h"
 #include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCSectionMachO.h"
 #include "llvm/MC/MCSubtargetInfo.h"
 #include "llvm/MC/MCValue.h"
+#include "llvm/Support/CommandLine.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/raw_ostream.h"
+#include "llvm/Support/TargetRegistry.h"
+
 using namespace llvm;
 
 static unsigned getFixupKindSize(unsigned Kind) {
   switch (Kind) {
   default:
     llvm_unreachable("invalid fixup kind!");
   case FK_NONE:
     return 0;
   case FK_PCRel_1:
   case FK_SecRel_1:
   case FK_Data_1:
     return 1;
   case FK_PCRel_2:
   case FK_SecRel_2:
   case FK_Data_2:
     return 2;
   case FK_PCRel_4:
   case X86::reloc_riprel_4byte:
   case X86::reloc_riprel_4byte_relax:
   case X86::reloc_riprel_4byte_relax_rex:
   case X86::reloc_riprel_4byte_movq_load:
   case X86::reloc_signed_4byte:
   case X86::reloc_signed_4byte_relax:
   case X86::reloc_global_offset_table:
   case X86::reloc_branch_4byte_pcrel:
   case FK_SecRel_4:
   case FK_Data_4:
     return 4;
   case FK_PCRel_8:
   case FK_SecRel_8:
   case FK_Data_8:
   case X86::reloc_global_offset_table8:
     return 8;
   }
 }
 
 namespace {
+class X86AlignBranchKind {
+private:
+  uint8_t AlignBranchKind = 0;
+
+public:
+  enum Flag : uint8_t {
+    AlignBranchNone = 0,
+    AlignBranchFused = 1U << 0,
+    AlignBranchJcc = 1U << 1,
+    AlignBranchJmp = 1U << 2,
+    AlignBranchCall = 1U << 3,
+    AlignBranchRet = 1U << 4,
+    AlignBranchIndirect = 1U << 5
+  };
+
+  void operator=(const std::string &Val) {
+    if (Val.empty())
+      return;
+    SmallVector<StringRef, 6> BranchTypes;
+    StringRef(Val).split(BranchTypes, '+', -1, false);
+    for (auto BranchType : BranchTypes) {
+      if (BranchType == "fused")
+        addKind(AlignBranchFused);
+      else if (BranchType == "jcc")
+        addKind(AlignBranchJcc);
+      else if (BranchType == "jmp")
+        addKind(AlignBranchJmp);
+      else if (BranchType == "call")
+        addKind(AlignBranchCall);
+      else if (BranchType == "ret")
+        addKind(AlignBranchRet);
+      else if (BranchType == "indirect")
+        addKind(AlignBranchIndirect);
+      else {
+        report_fatal_error(
+            "'-x86-align-branch 'The branches's type is combination of jcc, "
+            "fused, jmp, call, ret, indirect.(plus separated)",
+            false);
+      }
+    }
+  }
+
+  operator uint8_t() const { return AlignBranchKind; }
+  void addKind(Flag Value) { AlignBranchKind |= Value; }
+};
+
+X86AlignBranchKind X86AlignBranchKindLoc;
+
+cl::opt<uint64_t> X86AlignBranchBoundary(
+    "x86-align-branch-boundary", cl::init(0),
+    cl::desc(
+        "Control how the assembler should align branches with NOP. If the "
+        "boundary's size is not 0, it should be a power of 2 and no less "
+        "than 32. Branches will be aligned within the boundary of specified "
+        "size. -x86-align-branch-boundary=0 doesn't align branches."));
+
+cl::opt<X86AlignBranchKind, true, cl::parser<std::string>> X86AlignBranch(
+    "x86-align-branch",
+    cl::desc("Specify types of branches to align (plus separated list of "
+             "types). The branches's type is combination of jcc, fused, "
+             "jmp, call, ret, indirect."),
+    cl::value_desc("jcc(conditional jump), fused(fused conditional jump), "
+                   "jmp(unconditional jump); call(call); ret(ret), "
+                   "indirect(indirect jump)."),
+    cl::location(X86AlignBranchKindLoc));
 
 class X86ELFObjectWriter : public MCELFObjectTargetWriter {
 public:
   X86ELFObjectWriter(bool is64Bit, uint8_t OSABI, uint16_t EMachine,
                      bool HasRelocationAddend, bool foobar)
     : MCELFObjectTargetWriter(is64Bit, OSABI, EMachine, HasRelocationAddend) {}
 };
 
 class X86AsmBackend : public MCAsmBackend {
   const MCSubtargetInfo &STI;
+  const MCInstrInfo &MCII;
+  X86AlignBranchKind AlignBranchType;
+  Align AlignBoundary;
+
+  bool isFirstMacroFusibleInst(const MCInst &Inst) const;
+  bool isMacroFused(const MCInst &Cmp, const MCInst &Jcc) const;
+  bool isRIPRelative(const MCInst &MI) const;
+  bool hasVariantSymbol(const MCInst &MI) const;
+
+  bool needAlign(MCObjectStreamer &OS) const;
+  bool needAlignInst(const MCInst &Inst) const;
+  MCBoundaryAlignFragment *
+  getOrCreateBoundaryAlignFragment(MCObjectStreamer &OS) const;
+  MCInst PrevInst;
+
 public:
   X86AsmBackend(const Target &T, const MCSubtargetInfo &STI)
-      : MCAsmBackend(support::little), STI(STI) {}
+      : MCAsmBackend(support::little), STI(STI),
+        MCII(*(T.createMCInstrInfo())) {
+    AlignBoundary = assumeAligned(X86AlignBranchBoundary);
+    AlignBranchType = X86AlignBranchKindLoc;
+  }
+
+  void alignBranchesBegin(MCObjectStreamer &OS, const MCInst &Inst) override;
+  void alignBranchesEnd(MCObjectStreamer &OS, const MCInst &Inst) override;
 
   unsigned getNumFixupKinds() const override {
     return X86::NumTargetFixupKinds;
   }
 
   Optional<MCFixupKind> getFixupKind(StringRef Name) const override;
 
   const MCFixupKindInfo &getFixupKindInfo(MCFixupKind Kind) const override {
     const static MCFixupKindInfo Infos[X86::NumTargetFixupKinds] = {
         {"reloc_riprel_4byte", 0, 32, MCFixupKindInfo::FKF_IsPCRel},
         {"reloc_riprel_4byte_movq_load", 0, 32, MCFixupKindInfo::FKF_IsPCRel},
         {"reloc_riprel_4byte_relax", 0, 32, MCFixupKindInfo::FKF_IsPCRel},
         {"reloc_riprel_4byte_relax_rex", 0, 32, MCFixupKindInfo::FKF_IsPCRel},
         {"reloc_signed_4byte", 0, 32, 0},
         {"reloc_signed_4byte_relax", 0, 32, 0},
         {"reloc_global_offset_table", 0, 32, 0},
         {"reloc_global_offset_table8", 0, 64, 0},
         {"reloc_branch_4byte_pcrel", 0, 32, MCFixupKindInfo::FKF_IsPCRel},
     };
 
     if (Kind < FirstTargetFixupKind)
       return MCAsmBackend::getFixupKindInfo(Kind);
 
     assert(unsigned(Kind - FirstTargetFixupKind) < getNumFixupKinds() &&
            "Invalid kind!");
     assert(Infos[Kind - FirstTargetFixupKind].Name && "Empty fixup name!");
     return Infos[Kind - FirstTargetFixupKind];
   }
 
   bool shouldForceRelocation(const MCAssembler &Asm, const MCFixup &Fixup,
                              const MCValue &Target) override;
 
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
                   uint64_t Value, bool IsResolved,
                   const MCSubtargetInfo *STI) const override {
     unsigned Size = getFixupKindSize(Fixup.getKind());
 
     assert(Fixup.getOffset() + Size <= Data.size() && "Invalid fixup offset!");
 
     int64_t SignedValue = static_cast<int64_t>(Value);
     if ((Target.isAbsolute() || IsResolved) &&
         getFixupKindInfo(Fixup.getKind()).Flags &
             MCFixupKindInfo::FKF_IsPCRel) {
       // check that PC relative fixup fits into the fixup size.
       if (Size > 0 && !isIntN(Size * 8, SignedValue))
         Asm.getContext().reportError(
             Fixup.getLoc(), "value of " + Twine(SignedValue) +
                                 " is too large for field of " + Twine(Size) +
                                 ((Size == 1) ? " byte." : " bytes."));
     } else {
       // Check that uppper bits are either all zeros or all ones.
       // Specifically ignore overflow/underflow as long as the leakage is
       // limited to the lower bits. This is to remain compatible with
       // other assemblers.
       assert((Size == 0 || isIntN(Size * 8 + 1, SignedValue)) &&
              "Value does not fit in the Fixup field");
     }
 
     for (unsigned i = 0; i != Size; ++i)
       Data[Fixup.getOffset() + i] = uint8_t(Value >> (i * 8));
   }
 
   bool mayNeedRelaxation(const MCInst &Inst,
                          const MCSubtargetInfo &STI) const override;
 
   bool fixupNeedsRelaxation(const MCFixup &Fixup, uint64_t Value,
                             const MCRelaxableFragment *DF,
                             const MCAsmLayout &Layout) const override;
 
   void relaxInstruction(const MCInst &Inst, const MCSubtargetInfo &STI,
                         MCInst &Res) const override;
 
   bool writeNopData(raw_ostream &OS, uint64_t Count) const override;
 };
 } // end anonymous namespace
 
 static unsigned getRelaxedOpcodeBranch(const MCInst &Inst, bool is16BitMode) {
   unsigned Op = Inst.getOpcode();
   switch (Op) {
   default:
     return Op;
   case X86::JCC_1:
     return (is16BitMode) ? X86::JCC_2 : X86::JCC_4;
   case X86::JMP_1:
     return (is16BitMode) ? X86::JMP_2 : X86::JMP_4;
   }
 }
 
 static unsigned getRelaxedOpcodeArith(const MCInst &Inst) {
   unsigned Op = Inst.getOpcode();
   switch (Op) {
   default:
     return Op;
 
     // IMUL
   case X86::IMUL16rri8: return X86::IMUL16rri;
   case X86::IMUL16rmi8: return X86::IMUL16rmi;
   case X86::IMUL32rri8: return X86::IMUL32rri;
   case X86::IMUL32rmi8: return X86::IMUL32rmi;
   case X86::IMUL64rri8: return X86::IMUL64rri32;
   case X86::IMUL64rmi8: return X86::IMUL64rmi32;
 
     // AND
   case X86::AND16ri8: return X86::AND16ri;
   case X86::AND16mi8: return X86::AND16mi;
   case X86::AND32ri8: return X86::AND32ri;
   case X86::AND32mi8: return X86::AND32mi;
   case X86::AND64ri8: return X86::AND64ri32;
   case X86::AND64mi8: return X86::AND64mi32;
 
     // OR
   case X86::OR16ri8: return X86::OR16ri;
   case X86::OR16mi8: return X86::OR16mi;
   case X86::OR32ri8: return X86::OR32ri;
   case X86::OR32mi8: return X86::OR32mi;
   case X86::OR64ri8: return X86::OR64ri32;
   case X86::OR64mi8: return X86::OR64mi32;
 
     // XOR
   case X86::XOR16ri8: return X86::XOR16ri;
   case X86::XOR16mi8: return X86::XOR16mi;
   case X86::XOR32ri8: return X86::XOR32ri;
   case X86::XOR32mi8: return X86::XOR32mi;
   case X86::XOR64ri8: return X86::XOR64ri32;
   case X86::XOR64mi8: return X86::XOR64mi32;
 
     // ADD
   case X86::ADD16ri8: return X86::ADD16ri;
   case X86::ADD16mi8: return X86::ADD16mi;
   case X86::ADD32ri8: return X86::ADD32ri;
   case X86::ADD32mi8: return X86::ADD32mi;
   case X86::ADD64ri8: return X86::ADD64ri32;
   case X86::ADD64mi8: return X86::ADD64mi32;
 
    // ADC
   case X86::ADC16ri8: return X86::ADC16ri;
   case X86::ADC16mi8: return X86::ADC16mi;
   case X86::ADC32ri8: return X86::ADC32ri;
   case X86::ADC32mi8: return X86::ADC32mi;
   case X86::ADC64ri8: return X86::ADC64ri32;
   case X86::ADC64mi8: return X86::ADC64mi32;
 
     // SUB
   case X86::SUB16ri8: return X86::SUB16ri;
   case X86::SUB16mi8: return X86::SUB16mi;
   case X86::SUB32ri8: return X86::SUB32ri;
   case X86::SUB32mi8: return X86::SUB32mi;
   case X86::SUB64ri8: return X86::SUB64ri32;
   case X86::SUB64mi8: return X86::SUB64mi32;
 
    // SBB
   case X86::SBB16ri8: return X86::SBB16ri;
   case X86::SBB16mi8: return X86::SBB16mi;
   case X86::SBB32ri8: return X86::SBB32ri;
   case X86::SBB32mi8: return X86::SBB32mi;
   case X86::SBB64ri8: return X86::SBB64ri32;
   case X86::SBB64mi8: return X86::SBB64mi32;
 
     // CMP
   case X86::CMP16ri8: return X86::CMP16ri;
   case X86::CMP16mi8: return X86::CMP16mi;
   case X86::CMP32ri8: return X86::CMP32ri;
   case X86::CMP32mi8: return X86::CMP32mi;
   case X86::CMP64ri8: return X86::CMP64ri32;
   case X86::CMP64mi8: return X86::CMP64mi32;
 
     // PUSH
   case X86::PUSH32i8:  return X86::PUSHi32;
   case X86::PUSH16i8:  return X86::PUSHi16;
   case X86::PUSH64i8:  return X86::PUSH64i32;
   }
 }
 
 static unsigned getRelaxedOpcode(const MCInst &Inst, bool is16BitMode) {
   unsigned R = getRelaxedOpcodeArith(Inst);
   if (R != Inst.getOpcode())
     return R;
   return getRelaxedOpcodeBranch(Inst, is16BitMode);
 }
 
+static X86::CondCode getCondFromBranch(const MCInst &MI,
+                                       const MCInstrInfo &MCII) {
+  unsigned Opcode = MI.getOpcode();
+  switch (Opcode) {
+  default:
+    return X86::COND_INVALID;
+  case X86::JCC_1: {
+    const MCInstrDesc &Desc = MCII.get(Opcode);
+    return static_cast<X86::CondCode>(
+        MI.getOperand(Desc.getNumOperands() - 1).getImm());
+  }
+  }
+}
+
+static X86::SecondMacroFusionInstKind
+classifySecondInstInMacroFusion(const MCInst &MI, const MCInstrInfo &MCII) {
+  X86::CondCode CC = getCondFromBranch(MI, MCII);
+  return classifySecondCondCodeInMacroFusion(CC);
+}
+
+/// Check if the instruction is valid as the first instruction in macro fusion.
+bool X86AsmBackend::isFirstMacroFusibleInst(const MCInst &Inst) const {
+  // An Intel instruction with RIP relative addressing is not macro fusible.
+  if (isRIPRelative(Inst))
+    return false;
+  X86::FirstMacroFusionInstKind FIK =
+      X86::classifyFirstOpcodeInMacroFusion(Inst.getOpcode());
+  return FIK != X86::FirstMacroFusionInstKind::Invalid;
+}
+
+/// Check if the two instructions are macro-fused.
+bool X86AsmBackend::isMacroFused(const MCInst &Cmp, const MCInst &Jcc) const {
+  const MCInstrDesc &InstDesc = MCII.get(Jcc.getOpcode());
+  if (!InstDesc.isConditionalBranch())
+    return false;
+  if (!isFirstMacroFusibleInst(Cmp))
+    return false;
+  const X86::FirstMacroFusionInstKind CmpKind =
+      X86::classifyFirstOpcodeInMacroFusion(Cmp.getOpcode());
+  const X86::SecondMacroFusionInstKind BranchKind =
+      classifySecondInstInMacroFusion(Jcc, MCII);
+  return X86::isMacroFused(CmpKind, BranchKind);
+}
+
+/// Check if the instruction is RIP relative addressing.
+bool X86AsmBackend::isRIPRelative(const MCInst &MI) const {
+  unsigned Opcode = MI.getOpcode();
+  const MCInstrDesc &Desc = MCII.get(Opcode);
+  uint64_t TSFlags = Desc.TSFlags;
+  unsigned CurOp = X86II::getOperandBias(Desc);
+  int MemoryOperand = X86II::getMemoryOperandNo(TSFlags);
+  if (MemoryOperand >= 0) {
+    unsigned BaseRegNum = MemoryOperand + CurOp + X86::AddrBaseReg;
+    unsigned BaseReg = MI.getOperand(BaseRegNum).getReg();
+    if (BaseReg == X86::RIP)
+      return true;
+  }
+  return false;
+}
+
+/// Check if the instruction has variant symbol operand.
+bool X86AsmBackend::hasVariantSymbol(const MCInst &MI) const {
+
+  for (auto &Operand : MI) {
+    if (Operand.isExpr()) {
+      const MCExpr &Expr = *Operand.getExpr();
+      if (Expr.getKind() == MCExpr::SymbolRef &&
+          cast<MCSymbolRefExpr>(*Operand.getExpr()).getKind() !=
+              MCSymbolRefExpr::VK_None)
+        return true;
+    }
+  }
+  return false;
+}
+
+bool X86AsmBackend::needAlign(MCObjectStreamer &OS) const {
+  if (AlignBoundary == Align::None() ||
+      AlignBranchType == X86AlignBranchKind::AlignBranchNone)
+    return false;
+
+  MCAssembler &Assembler = OS.getAssembler();
+  MCSection *Sec = OS.getCurrentSectionOnly();
+  // To be Done: Currently don't deal with Bundle cases.
+  if (Assembler.isBundlingEnabled() && Sec->isBundleLocked())
+    return false;
+
+  // Branches only need to be aligned in 32-bit or 64-bit mode.
+  if (!(STI.getFeatureBits()[X86::Mode64Bit] ||
+        STI.getFeatureBits()[X86::Mode32Bit]))
+    return false;
+
+  return true;
+}
+
+/// Check if the instruction operand needs to be aligned. Padding is disabled
+/// before intruction which may be rewritten by linker(e.g. TLSCALL).
+bool X86AsmBackend::needAlignInst(const MCInst &Inst) const {
+  // Linker may rewrite the instruction with variant symbol operand.
+  if (hasVariantSymbol(Inst))
+    return false;
+
+  const MCInstrDesc &InstDesc = MCII.get(Inst.getOpcode());
+  return (InstDesc.isConditionalBranch() &&
+          (AlignBranchType & X86AlignBranchKind::AlignBranchJcc)) ||
+         (InstDesc.isUnconditionalBranch() &&
+          (AlignBranchType & X86AlignBranchKind::AlignBranchJmp)) ||
+         (InstDesc.isCall() &&
+          (AlignBranchType & X86AlignBranchKind::AlignBranchCall)) ||
+         (InstDesc.isReturn() &&
+          (AlignBranchType & X86AlignBranchKind::AlignBranchRet)) ||
+         (InstDesc.isIndirectBranch() &&
+          (AlignBranchType & X86AlignBranchKind::AlignBranchIndirect));
+}
+
+static bool canReuseBoundaryAlignFragment(const MCBoundaryAlignFragment &F) {
+  // If a MCBoundaryAlignFragment has not been used to emit NOP,we can reuse it.
+  return !F.canEmitNops();
+}
+
+MCBoundaryAlignFragment *
+X86AsmBackend::getOrCreateBoundaryAlignFragment(MCObjectStreamer &OS) const {
+  auto *F = dyn_cast_or_null<MCBoundaryAlignFragment>(OS.getCurrentFragment());
+  if (!F || !canReuseBoundaryAlignFragment(*F)) {
+    F = new MCBoundaryAlignFragment(AlignBoundary);
+    OS.insert(F);
+  }
+  return F;
+}
+
+/// Insert MCBoundaryAlignFragment before instructions to align branches.
+void X86AsmBackend::alignBranchesBegin(MCObjectStreamer &OS,
+                                       const MCInst &Inst) {
+  if (!needAlign(OS))
+    return;
+
+  MCFragment *CF = OS.getCurrentFragment();
+  bool NeedAlignFused = AlignBranchType & X86AlignBranchKind::AlignBranchFused;
+  if (NeedAlignFused && isMacroFused(PrevInst, Inst) && CF) {
+    // Macro fusion actually happens and there is no other fragment inserted
+    // after the previous instruction. NOP can be emitted in PF to align fused
+    // jcc.
+    if (auto *PF =
+            dyn_cast_or_null<MCBoundaryAlignFragment>(CF->getPrevNode())) {
+      const_cast<MCBoundaryAlignFragment *>(PF)->setEmitNops(true);
+      const_cast<MCBoundaryAlignFragment *>(PF)->setFused(true);
+    }
+  } else if (needAlignInst(Inst)) {
+    // Note: When there is at least one fragment, such as MCAlignFragment,
+    // inserted after the previous instruction, e.g.
+    //
+    // \code
+    //   cmp %rax %rcx
+    //   .align 16
+    //   je .Label0
+    // \ endcode
+    //
+    // We will treat the JCC as a unfused branch although it may be fused
+    // with the CMP.
+    auto *F = getOrCreateBoundaryAlignFragment(OS);
+    F->setEmitNops(true);
+    F->setFused(false);
+  } else if (NeedAlignFused && isFirstMacroFusibleInst(Inst)) {
+    // We don't know if macro fusion happens until the reaching the next
+    // instruction, so a place holder is put here if necessary.
+    getOrCreateBoundaryAlignFragment(OS);
+  }
+
+  PrevInst = Inst;
+}
+
+/// Insert a MCBoundaryAlignFragment to mark the end of the branch to be aligned
+/// if necessary.
+void X86AsmBackend::alignBranchesEnd(MCObjectStreamer &OS, const MCInst &Inst) {
+  if (!needAlign(OS))
+    return;
+  // If the branch is emitted into a MCRelaxableFragment, we can determine the
+  // size of the branch easily in MCAssembler::relaxBoundaryAlign. When the
+  // branch is fused, the fused branch(macro fusion pair) must be emitted into
+  // two fragments. Or when the branch is unfused, the branch must be emitted
+  // into one fragment. The MCRelaxableFragment naturally marks the end of the
+  // fused or unfused branch.
+  // Otherwise, we need to insert a MCBoundaryAlignFragment to mark the end of
+  // the branch. This MCBoundaryAlignFragment may be reused to emit NOP to align
+  // other branch.
+  if (needAlignInst(Inst) && !isa<MCRelaxableFragment>(OS.getCurrentFragment()))
+    OS.insert(new MCBoundaryAlignFragment(AlignBoundary));
+
+  // Update the maximum alignment on the current section if necessary.
+  MCSection *Sec = OS.getCurrentSectionOnly();
+  if (AlignBoundary.value() > Sec->getAlignment())
+    Sec->setAlignment(AlignBoundary);
+}
+
 Optional<MCFixupKind> X86AsmBackend::getFixupKind(StringRef Name) const {
   if (STI.getTargetTriple().isOSBinFormatELF()) {
     if (STI.getTargetTriple().getArch() == Triple::x86_64) {
       if (Name == "R_X86_64_NONE")
         return FK_NONE;
     } else {
       if (Name == "R_386_NONE")
         return FK_NONE;
     }
   }
   return MCAsmBackend::getFixupKind(Name);
 }
 
 bool X86AsmBackend::shouldForceRelocation(const MCAssembler &,
                                           const MCFixup &Fixup,
                                           const MCValue &) {
   return Fixup.getKind() == FK_NONE;
 }
 
 bool X86AsmBackend::mayNeedRelaxation(const MCInst &Inst,
                                       const MCSubtargetInfo &STI) const {
   // Branches can always be relaxed in either mode.
   if (getRelaxedOpcodeBranch(Inst, false) != Inst.getOpcode())
     return true;
 
   // Check if this instruction is ever relaxable.
   if (getRelaxedOpcodeArith(Inst) == Inst.getOpcode())
     return false;
 
 
   // Check if the relaxable operand has an expression. For the current set of
   // relaxable instructions, the relaxable operand is always the last operand.
   unsigned RelaxableOp = Inst.getNumOperands() - 1;
   if (Inst.getOperand(RelaxableOp).isExpr())
     return true;
 
   return false;
 }
 
 bool X86AsmBackend::fixupNeedsRelaxation(const MCFixup &Fixup,
                                          uint64_t Value,
                                          const MCRelaxableFragment *DF,
                                          const MCAsmLayout &Layout) const {
   // Relax if the value is too big for a (signed) i8.
   return !isInt<8>(Value);
 }
 
 // FIXME: Can tblgen help at all here to verify there aren't other instructions
 // we can relax?
 void X86AsmBackend::relaxInstruction(const MCInst &Inst,
                                      const MCSubtargetInfo &STI,
                                      MCInst &Res) const {
   // The only relaxations X86 does is from a 1byte pcrel to a 4byte pcrel.
   bool is16BitMode = STI.getFeatureBits()[X86::Mode16Bit];
   unsigned RelaxedOp = getRelaxedOpcode(Inst, is16BitMode);
 
   if (RelaxedOp == Inst.getOpcode()) {
     SmallString<256> Tmp;
     raw_svector_ostream OS(Tmp);
     Inst.dump_pretty(OS);
     OS << "\n";
     report_fatal_error("unexpected instruction to relax: " + OS.str());
   }
 
   Res = Inst;
   Res.setOpcode(RelaxedOp);
 }
 
 /// Write a sequence of optimal nops to the output, covering \p Count
 /// bytes.
 /// \return - true on success, false on failure
 bool X86AsmBackend::writeNopData(raw_ostream &OS, uint64_t Count) const {
   static const char Nops[10][11] = {
     // nop
     "\x90",
     // xchg %ax,%ax
     "\x66\x90",
     // nopl (%[re]ax)
     "\x0f\x1f\x00",
     // nopl 0(%[re]ax)
     "\x0f\x1f\x40\x00",
     // nopl 0(%[re]ax,%[re]ax,1)
     "\x0f\x1f\x44\x00\x00",
     // nopw 0(%[re]ax,%[re]ax,1)
     "\x66\x0f\x1f\x44\x00\x00",
     // nopl 0L(%[re]ax)
     "\x0f\x1f\x80\x00\x00\x00\x00",
     // nopl 0L(%[re]ax,%[re]ax,1)
     "\x0f\x1f\x84\x00\x00\x00\x00\x00",
     // nopw 0L(%[re]ax,%[re]ax,1)
     "\x66\x0f\x1f\x84\x00\x00\x00\x00\x00",
     // nopw %cs:0L(%[re]ax,%[re]ax,1)
     "\x66\x2e\x0f\x1f\x84\x00\x00\x00\x00\x00",
   };
 
   // This CPU doesn't support long nops. If needed add more.
   // FIXME: We could generated something better than plain 0x90.
   if (!STI.getFeatureBits()[X86::FeatureNOPL]) {
     for (uint64_t i = 0; i < Count; ++i)
       OS << '\x90';
     return true;
   }
 
   // 15-bytes is the longest single NOP instruction, but 10-bytes is
   // commonly the longest that can be efficiently decoded.
   uint64_t MaxNopLength = 10;
   if (STI.getFeatureBits()[X86::ProcIntelSLM])
     MaxNopLength = 7;
   else if (STI.getFeatureBits()[X86::FeatureFast15ByteNOP])
     MaxNopLength = 15;
   else if (STI.getFeatureBits()[X86::FeatureFast11ByteNOP])
     MaxNopLength = 11;
 
   // Emit as many MaxNopLength NOPs as needed, then emit a NOP of the remaining
   // length.
   do {
     const uint8_t ThisNopLength = (uint8_t) std::min(Count, MaxNopLength);
     const uint8_t Prefixes = ThisNopLength <= 10 ? 0 : ThisNopLength - 10;
     for (uint8_t i = 0; i < Prefixes; i++)
       OS << '\x66';
     const uint8_t Rest = ThisNopLength - Prefixes;
     if (Rest != 0)
       OS.write(Nops[Rest - 1], Rest);
     Count -= ThisNopLength;
   } while (Count != 0);
 
   return true;
 }
 
 /* *** */
 
 namespace {
 
 class ELFX86AsmBackend : public X86AsmBackend {
 public:
   uint8_t OSABI;
   ELFX86AsmBackend(const Target &T, uint8_t OSABI, const MCSubtargetInfo &STI)
       : X86AsmBackend(T, STI), OSABI(OSABI) {}
 };
 
 class ELFX86_32AsmBackend : public ELFX86AsmBackend {
 public:
   ELFX86_32AsmBackend(const Target &T, uint8_t OSABI,
                       const MCSubtargetInfo &STI)
     : ELFX86AsmBackend(T, OSABI, STI) {}
 
   std::unique_ptr<MCObjectTargetWriter>
   createObjectTargetWriter() const override {
     return createX86ELFObjectWriter(/*IsELF64*/ false, OSABI, ELF::EM_386);
   }
 };
 
 class ELFX86_X32AsmBackend : public ELFX86AsmBackend {
 public:
   ELFX86_X32AsmBackend(const Target &T, uint8_t OSABI,
                        const MCSubtargetInfo &STI)
       : ELFX86AsmBackend(T, OSABI, STI) {}
 
   std::unique_ptr<MCObjectTargetWriter>
   createObjectTargetWriter() const override {
     return createX86ELFObjectWriter(/*IsELF64*/ false, OSABI,
                                     ELF::EM_X86_64);
   }
 };
 
 class ELFX86_IAMCUAsmBackend : public ELFX86AsmBackend {
 public:
   ELFX86_IAMCUAsmBackend(const Target &T, uint8_t OSABI,
                          const MCSubtargetInfo &STI)
       : ELFX86AsmBackend(T, OSABI, STI) {}
 
   std::unique_ptr<MCObjectTargetWriter>
   createObjectTargetWriter() const override {
     return createX86ELFObjectWriter(/*IsELF64*/ false, OSABI,
                                     ELF::EM_IAMCU);
   }
 };
 
 class ELFX86_64AsmBackend : public ELFX86AsmBackend {
 public:
   ELFX86_64AsmBackend(const Target &T, uint8_t OSABI,
                       const MCSubtargetInfo &STI)
     : ELFX86AsmBackend(T, OSABI, STI) {}
 
   std::unique_ptr<MCObjectTargetWriter>
   createObjectTargetWriter() const override {
     return createX86ELFObjectWriter(/*IsELF64*/ true, OSABI, ELF::EM_X86_64);
   }
 };
 
 class WindowsX86AsmBackend : public X86AsmBackend {
   bool Is64Bit;
 
 public:
   WindowsX86AsmBackend(const Target &T, bool is64Bit,
                        const MCSubtargetInfo &STI)
     : X86AsmBackend(T, STI)
     , Is64Bit(is64Bit) {
   }
 
   Optional<MCFixupKind> getFixupKind(StringRef Name) const override {
     return StringSwitch<Optional<MCFixupKind>>(Name)
         .Case("dir32", FK_Data_4)
         .Case("secrel32", FK_SecRel_4)
         .Case("secidx", FK_SecRel_2)
         .Default(MCAsmBackend::getFixupKind(Name));
   }
 
   std::unique_ptr<MCObjectTargetWriter>
   createObjectTargetWriter() const override {
     return createX86WinCOFFObjectWriter(Is64Bit);
   }
 };
 
 namespace CU {
 
   /// Compact unwind encoding values.
   enum CompactUnwindEncodings {
     /// [RE]BP based frame where [RE]BP is pused on the stack immediately after
     /// the return address, then [RE]SP is moved to [RE]BP.
     UNWIND_MODE_BP_FRAME                   = 0x01000000,
 
     /// A frameless function with a small constant stack size.
     UNWIND_MODE_STACK_IMMD                 = 0x02000000,
 
     /// A frameless function with a large constant stack size.
     UNWIND_MODE_STACK_IND                  = 0x03000000,
 
     /// No compact unwind encoding is available.
     UNWIND_MODE_DWARF                      = 0x04000000,
 
     /// Mask for encoding the frame registers.
     UNWIND_BP_FRAME_REGISTERS              = 0x00007FFF,
 
     /// Mask for encoding the frameless registers.
     UNWIND_FRAMELESS_STACK_REG_PERMUTATION = 0x000003FF
   };
 
 } // end CU namespace
 
 class DarwinX86AsmBackend : public X86AsmBackend {
   const MCRegisterInfo &MRI;
 
   /// Number of registers that can be saved in a compact unwind encoding.
   enum { CU_NUM_SAVED_REGS = 6 };
 
   mutable unsigned SavedRegs[CU_NUM_SAVED_REGS];
   bool Is64Bit;
 
   unsigned OffsetSize;                   ///< Offset of a "push" instruction.
   unsigned MoveInstrSize;                ///< Size of a "move" instruction.
   unsigned StackDivide;                  ///< Amount to adjust stack size by.
 protected:
   /// Size of a "push" instruction for the given register.
   unsigned PushInstrSize(unsigned Reg) const {
     switch (Reg) {
       case X86::EBX:
       case X86::ECX:
       case X86::EDX:
       case X86::EDI:
       case X86::ESI:
       case X86::EBP:
       case X86::RBX:
       case X86::RBP:
         return 1;
       case X86::R12:
       case X86::R13:
       case X86::R14:
       case X86::R15:
         return 2;
     }
     return 1;
   }
 
   /// Implementation of algorithm to generate the compact unwind encoding
   /// for the CFI instructions.
   uint32_t
   generateCompactUnwindEncodingImpl(ArrayRef<MCCFIInstruction> Instrs) const {
     if (Instrs.empty()) return 0;
 
     // Reset the saved registers.
     unsigned SavedRegIdx = 0;
     memset(SavedRegs, 0, sizeof(SavedRegs));
 
     bool HasFP = false;
 
     // Encode that we are using EBP/RBP as the frame pointer.
     uint32_t CompactUnwindEncoding = 0;
 
     unsigned SubtractInstrIdx = Is64Bit ? 3 : 2;
     unsigned InstrOffset = 0;
     unsigned StackAdjust = 0;
     unsigned StackSize = 0;
     unsigned NumDefCFAOffsets = 0;
 
     for (unsigned i = 0, e = Instrs.size(); i != e; ++i) {
       const MCCFIInstruction &Inst = Instrs[i];
 
       switch (Inst.getOperation()) {
       default:
         // Any other CFI directives indicate a frame that we aren't prepared
         // to represent via compact unwind, so just bail out.
         return 0;
       case MCCFIInstruction::OpDefCfaRegister: {
         // Defines a frame pointer. E.g.
         //
         //     movq %rsp, %rbp
         //  L0:
         //     .cfi_def_cfa_register %rbp
         //
         HasFP = true;
 
         // If the frame pointer is other than esp/rsp, we do not have a way to
         // generate a compact unwinding representation, so bail out.
         if (*MRI.getLLVMRegNum(Inst.getRegister(), true) !=
             (Is64Bit ? X86::RBP : X86::EBP))
           return 0;
 
         // Reset the counts.
         memset(SavedRegs, 0, sizeof(SavedRegs));
         StackAdjust = 0;
         SavedRegIdx = 0;
         InstrOffset += MoveInstrSize;
         break;
       }
       case MCCFIInstruction::OpDefCfaOffset: {
         // Defines a new offset for the CFA. E.g.
         //
         //  With frame:
         //
         //     pushq %rbp
         //  L0:
         //     .cfi_def_cfa_offset 16
         //
         //  Without frame:
         //
         //     subq $72, %rsp
         //  L0:
         //     .cfi_def_cfa_offset 80
         //
         StackSize = std::abs(Inst.getOffset()) / StackDivide;
         ++NumDefCFAOffsets;
         break;
       }
       case MCCFIInstruction::OpOffset: {
         // Defines a "push" of a callee-saved register. E.g.
         //
         //     pushq %r15
         //     pushq %r14
         //     pushq %rbx
         //  L0:
         //     subq $120, %rsp
         //  L1:
         //     .cfi_offset %rbx, -40
         //     .cfi_offset %r14, -32
         //     .cfi_offset %r15, -24
         //
         if (SavedRegIdx == CU_NUM_SAVED_REGS)
           // If there are too many saved registers, we cannot use a compact
           // unwind encoding.
           return CU::UNWIND_MODE_DWARF;
 
         unsigned Reg = *MRI.getLLVMRegNum(Inst.getRegister(), true);
         SavedRegs[SavedRegIdx++] = Reg;
         StackAdjust += OffsetSize;
         InstrOffset += PushInstrSize(Reg);
         break;
       }
       }
     }
 
     StackAdjust /= StackDivide;
 
     if (HasFP) {
       if ((StackAdjust & 0xFF) != StackAdjust)
         // Offset was too big for a compact unwind encoding.
         return CU::UNWIND_MODE_DWARF;
 
       // Get the encoding of the saved registers when we have a frame pointer.
       uint32_t RegEnc = encodeCompactUnwindRegistersWithFrame();
       if (RegEnc == ~0U) return CU::UNWIND_MODE_DWARF;
 
       CompactUnwindEncoding |= CU::UNWIND_MODE_BP_FRAME;
       CompactUnwindEncoding |= (StackAdjust & 0xFF) << 16;
       CompactUnwindEncoding |= RegEnc & CU::UNWIND_BP_FRAME_REGISTERS;
     } else {
       SubtractInstrIdx += InstrOffset;
       ++StackAdjust;
 
       if ((StackSize & 0xFF) == StackSize) {
         // Frameless stack with a small stack size.
         CompactUnwindEncoding |= CU::UNWIND_MODE_STACK_IMMD;
 
         // Encode the stack size.
         CompactUnwindEncoding |= (StackSize & 0xFF) << 16;
       } else {
         if ((StackAdjust & 0x7) != StackAdjust)
           // The extra stack adjustments are too big for us to handle.
           return CU::UNWIND_MODE_DWARF;
 
         // Frameless stack with an offset too large for us to encode compactly.
         CompactUnwindEncoding |= CU::UNWIND_MODE_STACK_IND;
 
         // Encode the offset to the nnnnnn value in the 'subl $nnnnnn, ESP'
         // instruction.
         CompactUnwindEncoding |= (SubtractInstrIdx & 0xFF) << 16;
 
         // Encode any extra stack adjustments (done via push instructions).
         CompactUnwindEncoding |= (StackAdjust & 0x7) << 13;
       }
 
       // Encode the number of registers saved. (Reverse the list first.)
       std::reverse(&SavedRegs[0], &SavedRegs[SavedRegIdx]);
       CompactUnwindEncoding |= (SavedRegIdx & 0x7) << 10;
 
       // Get the encoding of the saved registers when we don't have a frame
       // pointer.
       uint32_t RegEnc = encodeCompactUnwindRegistersWithoutFrame(SavedRegIdx);
       if (RegEnc == ~0U) return CU::UNWIND_MODE_DWARF;
 
       // Encode the register encoding.
       CompactUnwindEncoding |=
         RegEnc & CU::UNWIND_FRAMELESS_STACK_REG_PERMUTATION;
     }
 
     return CompactUnwindEncoding;
   }
 
 private:
   /// Get the compact unwind number for a given register. The number
   /// corresponds to the enum lists in compact_unwind_encoding.h.
   int getCompactUnwindRegNum(unsigned Reg) const {
     static const MCPhysReg CU32BitRegs[7] = {
       X86::EBX, X86::ECX, X86::EDX, X86::EDI, X86::ESI, X86::EBP, 0
     };
     static const MCPhysReg CU64BitRegs[] = {
       X86::RBX, X86::R12, X86::R13, X86::R14, X86::R15, X86::RBP, 0
     };
     const MCPhysReg *CURegs = Is64Bit ? CU64BitRegs : CU32BitRegs;
     for (int Idx = 1; *CURegs; ++CURegs, ++Idx)
       if (*CURegs == Reg)
         return Idx;
 
     return -1;
   }
 
   /// Return the registers encoded for a compact encoding with a frame
   /// pointer.
   uint32_t encodeCompactUnwindRegistersWithFrame() const {
     // Encode the registers in the order they were saved --- 3-bits per
     // register. The list of saved registers is assumed to be in reverse
     // order. The registers are numbered from 1 to CU_NUM_SAVED_REGS.
     uint32_t RegEnc = 0;
     for (int i = 0, Idx = 0; i != CU_NUM_SAVED_REGS; ++i) {
       unsigned Reg = SavedRegs[i];
       if (Reg == 0) break;
 
       int CURegNum = getCompactUnwindRegNum(Reg);
       if (CURegNum == -1) return ~0U;
 
       // Encode the 3-bit register number in order, skipping over 3-bits for
       // each register.
       RegEnc |= (CURegNum & 0x7) << (Idx++ * 3);
     }
 
     assert((RegEnc & 0x3FFFF) == RegEnc &&
            "Invalid compact register encoding!");
     return RegEnc;
   }
 
   /// Create the permutation encoding used with frameless stacks. It is
   /// passed the number of registers to be saved and an array of the registers
   /// saved.
   uint32_t encodeCompactUnwindRegistersWithoutFrame(unsigned RegCount) const {
     // The saved registers are numbered from 1 to 6. In order to encode the
     // order in which they were saved, we re-number them according to their
     // place in the register order. The re-numbering is relative to the last
     // re-numbered register. E.g., if we have registers {6, 2, 4, 5} saved in
     // that order:
     //
     //    Orig  Re-Num
     //    ----  ------
     //     6       6
     //     2       2
     //     4       3
     //     5       3
     //
     for (unsigned i = 0; i < RegCount; ++i) {
       int CUReg = getCompactUnwindRegNum(SavedRegs[i]);
       if (CUReg == -1) return ~0U;
       SavedRegs[i] = CUReg;
     }
 
     // Reverse the list.
     std::reverse(&SavedRegs[0], &SavedRegs[CU_NUM_SAVED_REGS]);
 
     uint32_t RenumRegs[CU_NUM_SAVED_REGS];
     for (unsigned i = CU_NUM_SAVED_REGS - RegCount; i < CU_NUM_SAVED_REGS; ++i){
       unsigned Countless = 0;
       for (unsigned j = CU_NUM_SAVED_REGS - RegCount; j < i; ++j)
         if (SavedRegs[j] < SavedRegs[i])
           ++Countless;
 
       RenumRegs[i] = SavedRegs[i] - Countless - 1;
     }
 
     // Take the renumbered values and encode them into a 10-bit number.
     uint32_t permutationEncoding = 0;
     switch (RegCount) {
     case 6:
       permutationEncoding |= 120 * RenumRegs[0] + 24 * RenumRegs[1]
                              + 6 * RenumRegs[2] +  2 * RenumRegs[3]
                              +     RenumRegs[4];
       break;
     case 5:
       permutationEncoding |= 120 * RenumRegs[1] + 24 * RenumRegs[2]
                              + 6 * RenumRegs[3] +  2 * RenumRegs[4]
                              +     RenumRegs[5];
       break;
     case 4:
       permutationEncoding |=  60 * RenumRegs[2] + 12 * RenumRegs[3]
                              + 3 * RenumRegs[4] +      RenumRegs[5];
       break;
     case 3:
       permutationEncoding |=  20 * RenumRegs[3] +  4 * RenumRegs[4]
                              +     RenumRegs[5];
       break;
     case 2:
       permutationEncoding |=   5 * RenumRegs[4] +      RenumRegs[5];
       break;
     case 1:
       permutationEncoding |=       RenumRegs[5];
       break;
     }
 
     assert((permutationEncoding & 0x3FF) == permutationEncoding &&
            "Invalid compact register encoding!");
     return permutationEncoding;
   }
 
 public:
   DarwinX86AsmBackend(const Target &T, const MCRegisterInfo &MRI,
                       const MCSubtargetInfo &STI, bool Is64Bit)
     : X86AsmBackend(T, STI), MRI(MRI), Is64Bit(Is64Bit) {
     memset(SavedRegs, 0, sizeof(SavedRegs));
     OffsetSize = Is64Bit ? 8 : 4;
     MoveInstrSize = Is64Bit ? 3 : 2;
     StackDivide = Is64Bit ? 8 : 4;
   }
 };
 
 class DarwinX86_32AsmBackend : public DarwinX86AsmBackend {
 public:
   DarwinX86_32AsmBackend(const Target &T, const MCRegisterInfo &MRI,
                          const MCSubtargetInfo &STI)
       : DarwinX86AsmBackend(T, MRI, STI, false) {}
 
   std::unique_ptr<MCObjectTargetWriter>
   createObjectTargetWriter() const override {
     return createX86MachObjectWriter(/*Is64Bit=*/false,
                                      MachO::CPU_TYPE_I386,
                                      MachO::CPU_SUBTYPE_I386_ALL);
   }
 
   /// Generate the compact unwind encoding for the CFI instructions.
   uint32_t generateCompactUnwindEncoding(
                              ArrayRef<MCCFIInstruction> Instrs) const override {
     return generateCompactUnwindEncodingImpl(Instrs);
   }
 };
 
 class DarwinX86_64AsmBackend : public DarwinX86AsmBackend {
   const MachO::CPUSubTypeX86 Subtype;
 public:
   DarwinX86_64AsmBackend(const Target &T, const MCRegisterInfo &MRI,
                          const MCSubtargetInfo &STI, MachO::CPUSubTypeX86 st)
       : DarwinX86AsmBackend(T, MRI, STI, true), Subtype(st) {}
 
   std::unique_ptr<MCObjectTargetWriter>
   createObjectTargetWriter() const override {
     return createX86MachObjectWriter(/*Is64Bit=*/true, MachO::CPU_TYPE_X86_64,
                                      Subtype);
   }
 
   /// Generate the compact unwind encoding for the CFI instructions.
   uint32_t generateCompactUnwindEncoding(
                              ArrayRef<MCCFIInstruction> Instrs) const override {
     return generateCompactUnwindEncodingImpl(Instrs);
   }
 };
 
 } // end anonymous namespace
 
 MCAsmBackend *llvm::createX86_32AsmBackend(const Target &T,
                                            const MCSubtargetInfo &STI,
                                            const MCRegisterInfo &MRI,
                                            const MCTargetOptions &Options) {
   const Triple &TheTriple = STI.getTargetTriple();
   if (TheTriple.isOSBinFormatMachO())
     return new DarwinX86_32AsmBackend(T, MRI, STI);
 
   if (TheTriple.isOSWindows() && TheTriple.isOSBinFormatCOFF())
     return new WindowsX86AsmBackend(T, false, STI);
 
   uint8_t OSABI = MCELFObjectTargetWriter::getOSABI(TheTriple.getOS());
 
   if (TheTriple.isOSIAMCU())
     return new ELFX86_IAMCUAsmBackend(T, OSABI, STI);
 
   return new ELFX86_32AsmBackend(T, OSABI, STI);
 }
 
 MCAsmBackend *llvm::createX86_64AsmBackend(const Target &T,
                                            const MCSubtargetInfo &STI,
                                            const MCRegisterInfo &MRI,
                                            const MCTargetOptions &Options) {
   const Triple &TheTriple = STI.getTargetTriple();
   if (TheTriple.isOSBinFormatMachO()) {
     MachO::CPUSubTypeX86 CS =
         StringSwitch<MachO::CPUSubTypeX86>(TheTriple.getArchName())
             .Case("x86_64h", MachO::CPU_SUBTYPE_X86_64_H)
             .Default(MachO::CPU_SUBTYPE_X86_64_ALL);
     return new DarwinX86_64AsmBackend(T, MRI, STI, CS);
   }
 
   if (TheTriple.isOSWindows() && TheTriple.isOSBinFormatCOFF())
     return new WindowsX86AsmBackend(T, true, STI);
 
   uint8_t OSABI = MCELFObjectTargetWriter::getOSABI(TheTriple.getOS());
 
   if (TheTriple.getEnvironment() == Triple::GNUX32)
     return new ELFX86_X32AsmBackend(T, OSABI, STI);
   return new ELFX86_64AsmBackend(T, OSABI, STI);
 }
diff --git a/llvm/test/MC/X86/align-branch-32-1a.s b/llvm/test/MC/X86/align-branch-32-1a.s
new file mode 100644
index 000000000000..646024e71e93
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-32-1a.s
@@ -0,0 +1,38 @@
+# Check NOP padding is disabled before instruction that has variant symbol operand.
+# RUN: llvm-mc -filetype=obj -triple i386-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=call %s | llvm-objdump -d  - | FileCheck %s
+
+# CHECK: 00000000 foo:
+# CHECK-COUNT-5:      : 64 a3 01 00 00 00                movl    %eax, %fs:1
+# CHECK:            1e: e8 fc ff ff ff                   calll   {{.*}}
+# CHECK-COUNT-4:      : 64 a3 01 00 00 00                movl    %eax, %fs:1
+# CHECK:            3b: 55                               pushl   %ebp
+# CHECK-NEXT:       3c: ff 91 00 00 00 00                calll   *(%ecx)
+# CHECK-COUNT-4:      : 64 a3 01 00 00 00                movl    %eax, %fs:1
+# CHECK:            5a: c1 e9 02                         shrl    $2, %ecx
+# CHECK-NEXT:       5d: 55                               pushl   %ebp
+# CHECK-NEXT:       5e: ff 10                            calll   *(%eax)
+# CHECK-COUNT-5:      : 64 a3 01 00 00 00                movl    %eax, %fs:1
+# CHECK-NEXT:       7e: ff 20                            jmpl    *(%eax)
+  .text
+  .globl  foo
+  .p2align  4
+foo:
+  .rept 5
+  movl  %eax, %fs:0x1
+  .endr
+  call    ___tls_get_addr@PLT
+  .rept 4
+  movl  %eax, %fs:0x1
+  .endr
+  pushl  %ebp
+  call *___tls_get_addr@GOT(%ecx)
+  .rept 4
+  movl  %eax, %fs:0x1
+  .endr
+  shrl  $2, %ecx
+  pushl %ebp
+  call *foo@tlscall(%eax)
+  .rept 5
+  movl  %eax, %fs:0x1
+  .endr
+  jmp  *foo@tlscall(%eax)
diff --git a/llvm/test/MC/X86/align-branch-64-1a.s b/llvm/test/MC/X86/align-branch-64-1a.s
new file mode 100644
index 000000000000..c2187f9e73aa
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-1a.s
@@ -0,0 +1,83 @@
+# Check only fused conditional jumps, conditional jumps and unconditional jumps are aligned with option --x86-align-branch-boundary=32 --x86-align-branch=fused+jcc+jmp
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=fused+jcc+jmp %s | llvm-objdump -d  - > %t1
+# RUN: FileCheck --input-file=%t1 %s
+
+# Check no branches is aligned with option --x86-align-branch-boundary=0
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=0 --x86-align-branch=fused+jcc+jmp %s | llvm-objdump -d  - > %t2
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %s | llvm-objdump -d  - > %t3
+# RUN: cmp %t2 %t3
+
+# CHECK: 0000000000000000 foo:
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            18: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       1b: 31 c0                            xorl    %eax, %eax
+# CHECK-COUNT-3:      : 90                               nop
+# CHECK:            20: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       23: 74 5d                            je      {{.*}}
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            3d: 31 c0                            xorl    %eax, %eax
+# CHECK-NEXT:       3f: 90                               nop
+# CHECK-NEXT:       40: 74 40                            je      {{.*}}
+# CHECK-NEXT:       42: 5d                               popq    %rbp
+# CHECK-NEXT:       43: 74 3d                            je      {{.*}}
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            5d: 31 c0                            xorl    %eax, %eax
+# CHECK-NEXT:       5f: 90                               nop
+# CHECK-NEXT:       60: eb 26                            jmp     {{.*}}
+# CHECK-NEXT:       62: eb 24                            jmp     {{.*}}
+# CHECK-NEXT:       64: eb 22                            jmp     {{.*}}
+# CHECK-COUNT-2:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            76: 89 45 fc                         movl    %eax, -4(%rbp)
+# CHECK-NEXT:       79: 5d                               popq    %rbp
+# CHECK-NEXT:       7a: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       7d: 74 03                            je      {{.*}}
+# CHECK-NEXT:       7f: 90                               nop
+# CHECK-NEXT:       80: eb 06                            jmp     {{.*}}
+# CHECK-NEXT:       82: 8b 45 f4                         movl    -12(%rbp), %eax
+# CHECK-NEXT:       85: 89 45 fc                         movl    %eax, -4(%rbp)
+# CHECK-COUNT-10:     : 89 b5 50 fb ff ff                movl    %esi, -1200(%rbp)
+# CHECK:            c4: eb c2                            jmp     {{.*}}
+# CHECK-NEXT:       c6: c3                               retq
+
+  .text
+  .globl  foo
+  .p2align  4
+foo:
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  cmp  %rax, %rbp
+  xorl %eax, %eax
+  cmp  %rax, %rbp
+  je  .L_2
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  xorl %eax, %eax
+  je  .L_2
+  popq  %rbp
+  je  .L_2
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  xorl %eax, %eax
+  jmp  .L_3
+  jmp  .L_3
+  jmp  .L_3
+  .rept 2
+  movl  %eax, %fs:0x1
+  .endr
+  movl  %eax, -4(%rbp)
+  popq  %rbp
+  cmp  %rax, %rbp
+  je  .L_2
+  jmp  .L_3
+.L_2:
+  movl  -12(%rbp), %eax
+  movl  %eax, -4(%rbp)
+.L_3:
+  .rept 10
+  movl  %esi, -1200(%rbp)
+  .endr
+  jmp  .L_3
+  retq
diff --git a/llvm/test/MC/X86/align-branch-64-1b.s b/llvm/test/MC/X86/align-branch-64-1b.s
new file mode 100644
index 000000000000..3647e4e85be3
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-1b.s
@@ -0,0 +1,32 @@
+# Check only fused conditional jumps and conditional jumps are aligned with option --x86-align-branch-boundary=32 --x86-align-branch=fused+jcc
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=fused+jcc %S/align-branch-64-1a.s | llvm-objdump -d  - | FileCheck %s
+
+# CHECK: 0000000000000000 foo:
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:       18: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       1b: 31 c0                            xorl    %eax, %eax
+# CHECK-COUNT-3:      : 90                               nop
+# CHECK-NEXT:       20: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       23: 74 5b                            je      {{.*}}
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            3d: 31 c0                            xorl    %eax, %eax
+# CHECK-NEXT:       3f: 90                               nop
+# CHECK-NEXT:       40: 74 3e                            je      {{.*}}
+# CHECK-NEXT:       42: 5d                               popq    %rbp
+# CHECK-NEXT:       43: 74 3b                            je      {{.*}}
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            5d: 31 c0                            xorl    %eax, %eax
+# CHECK-NEXT:       5f: eb 25                            jmp     {{.*}}
+# CHECK-NEXT:       61: eb 23                            jmp     {{.*}}
+# CHECK-NEXT:       63: eb 21                            jmp     {{.*}}
+# CHECK-COUNT-2:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:       75: 89 45 fc                         movl    %eax, -4(%rbp)
+# CHECK:            78: 5d                               popq    %rbp
+# CHECK-NEXT:       79: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       7c: 74 02                            je      {{.*}}
+# CHECK-NEXT:       7e: eb 06                            jmp     {{.*}}
+# CHECK-NEXT:       80: 8b 45 f4                         movl    -12(%rbp), %eax
+# CHECK-NEXT:       83: 89 45 fc                         movl    %eax, -4(%rbp)
+# CHECK-COUNT-10:     : 89 b5 50 fb ff ff                movl    %esi, -1200(%rbp)
+# CHECK:            c2: eb c2                            jmp     {{.*}}
+# CHECK-NEXT:       c4: c3                               retq
diff --git a/llvm/test/MC/X86/align-branch-64-1c.s b/llvm/test/MC/X86/align-branch-64-1c.s
new file mode 100644
index 000000000000..11e0f2be0064
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-1c.s
@@ -0,0 +1,31 @@
+# Check only conditional jumps are aligned with option --x86-align-branch-boundary=32 --x86-align-branch=jcc
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=jcc %S/align-branch-64-1a.s | llvm-objdump -d  - | FileCheck %s
+
+# CHECK: 0000000000000000 foo:
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            18: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       1b: 31 c0                            xorl    %eax, %eax
+# CHECK-NEXT:       1d: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       20: 74 5b                            je      {{.*}}
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            3a: 31 c0                            xorl    %eax, %eax
+# CHECK-NEXT:       3c: 74 3f                            je      {{.*}}
+# CHECK-NEXT:       3e: 5d                               popq    %rbp
+# CHECK-NEXT:       3f: 90                               nop
+# CHECK-NEXT:       40: 74 3b                            je      {{.*}}
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            5a: 31 c0                            xorl    %eax, %eax
+# CHECK-NEXT:       5c: eb 25                            jmp     {{.*}}
+# CHECK-NEXT:       5e: eb 23                            jmp     {{.*}}
+# CHECK-NEXT:       60: eb 21                            jmp     {{.*}}
+# CHECK-COUNT-2:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            72: 89 45 fc                         movl    %eax, -4(%rbp)
+# CHECK-NEXT:       75: 5d                               popq    %rbp
+# CHECK-NEXT:       76: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       79: 74 02                            je      {{.*}}
+# CHECK-NEXT:       7b: eb 06                            jmp     {{.*}}
+# CHECK-NEXT:       7d: 8b 45 f4                         movl    -12(%rbp), %eax
+# CHECK-NEXT:       80: 89 45 fc                         movl    %eax, -4(%rbp)
+# CHECK-COUNT-10:     : 89 b5 50 fb ff ff                movl    %esi, -1200(%rbp)
+# CHECK:            bf: eb c2                            jmp     {{.*}}
+# CHECK-NEXT:       c1: c3                               retq
diff --git a/llvm/test/MC/X86/align-branch-64-1d.s b/llvm/test/MC/X86/align-branch-64-1d.s
new file mode 100644
index 000000000000..be6b5cf94719
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-1d.s
@@ -0,0 +1,38 @@
+# Check only conditional jumps and unconditional jumps are aligned with option --x86-align-branch-boundary=32 --x86-align-branch=jcc+jmp
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=jcc+jmp %S/align-branch-64-1a.s | llvm-objdump -d  - > %t1
+# RUN: FileCheck --input-file=%t1 %s --check-prefixes=CHECK,SHORT-NOP
+
+# Check long NOP can be emitted to align branch if the target cpu support long nop.
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 -mcpu=x86-64 --x86-align-branch=jcc+jmp %S/align-branch-64-1a.s | llvm-objdump -d  - >%t2
+# RUN: FileCheck --input-file=%t2 %s --check-prefixes=CHECK,LONG-NOP
+
+# CHECK: 0000000000000000 foo:
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            18: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       1b: 31 c0                            xorl    %eax, %eax
+# CHECK-NEXT:       1d: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       20: 74 5d                            je      {{.*}}
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            3a: 31 c0                            xorl    %eax, %eax
+# CHECK-NEXT:       3c: 74 41                            je      {{.*}}
+# CHECK-NEXT:       3e: 5d                               popq    %rbp
+# CHECK-NEXT:       3f: 90                               nop
+# CHECK-NEXT:       40: 74 3d                            je      {{.*}}
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            5a: 31 c0                            xorl    %eax, %eax
+# CHECK-NEXT:       5c: eb 27                            jmp     {{.*}}
+# SHORT-NOP-COUNT-2:  : 90                               nop
+# LONG-NOP:         5e: 66 90                            nop
+# CHECK-NEXT:       60: eb 23                            jmp     {{.*}}
+# CHECK-NEXT:       62: eb 21                            jmp     {{.*}}
+# CHECK-COUNT-2:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            74: 89 45 fc                         movl    %eax, -4(%rbp)
+# CHECK-NEXT:       77: 5d                               popq    %rbp
+# CHECK-NEXT:       78: 48 39 c5                         cmpq    %rax, %rbp
+# CHECK-NEXT:       7b: 74 02                            je      {{.*}}
+# CHECK-NEXT:       7d: eb 06                            jmp     {{.*}}
+# CHECK-NEXT:       7f: 8b 45 f4                         movl    -12(%rbp), %eax
+# CHECK-NEXT:       82: 89 45 fc                         movl    %eax, -4(%rbp)
+# CHECK-COUNT-10:     : 89 b5 50 fb ff ff                movl    %esi, -1200(%rbp)
+# CHECK:            c1: eb c2                            jmp     {{.*}}
+# CHECK-NEXT:       c3: c3                               retq
diff --git a/llvm/test/MC/X86/align-branch-64-2a.s b/llvm/test/MC/X86/align-branch-64-2a.s
new file mode 100644
index 000000000000..fe38f71c0692
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-2a.s
@@ -0,0 +1,44 @@
+# Check only indirect jumps are aligned with option --x86-align-branch-boundary=32 --x86-align-branch=indirect
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=indirect %s | llvm-objdump -d  - | FileCheck %s
+
+# CHECK: 0000000000000000 foo:
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-COUNT-2:      : 89 75 f4                         movl    %esi, -12(%rbp)
+# CHECK-COUNT-2:      : 90                               nop
+# CHECK:            20: ff e0                            jmpq    *%rax
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            3a: 89 75 f4                         movl    %esi, -12(%rbp)
+# CHECK-NEXT:       3d: 55                               pushq   %rbp
+# CHECK-NEXT:       3e: ff d0                            callq   *%rax
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:       58: 55                               pushq   %rbp
+# CHECK-NEXT:       59: e8 a2 ff ff ff                   callq   {{.*}}
+# CHECK-COUNT-4:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            7e: ff 14 25 00 00 00 00             callq   *0
+
+  .text
+  .globl  foo
+  .p2align  4
+foo:
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  .rept 2
+  movl  %esi, -12(%rbp)
+  .endr
+  jmp  *%rax
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  movl  %esi, -12(%rbp)
+  pushq  %rbp
+  call *%rax
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  pushq  %rbp
+  call  foo
+  .rept 4
+  movl  %eax, %fs:0x1
+  .endr
+  call  *foo
diff --git a/llvm/test/MC/X86/align-branch-64-2b.s b/llvm/test/MC/X86/align-branch-64-2b.s
new file mode 100644
index 000000000000..c7ffa16922f2
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-2b.s
@@ -0,0 +1,17 @@
+# Check only calls are aligned with option --x86-align-branch-boundary=32 --x86-align-branch=call
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=call %S/align-branch-64-2a.s| llvm-objdump -d  - | FileCheck %s
+
+# CHECK: 0000000000000000 foo:
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-COUNT-2:      : 89 75 f4                         movl    %esi, -12(%rbp)
+# CHECK:            1e: ff e0                            jmpq    *%rax
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            38: 89 75 f4                         movl    %esi, -12(%rbp)
+# CHECK-NEXT:       3b: 55                               pushq    %rbp
+# CHECK-NEXT:       3c: ff d0                            callq    *%rax
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl     %eax, %fs:1
+# CHECK:            56: 55                               pushq    %rbp
+# CHECK-NEXT:       57: e8 a4 ff ff ff                   callq    {{.*}}
+# CHECK-COUNT-4:      : 64 89 04 25 01 00 00 00          movl     %eax, %fs:1
+# CHECK-COUNT-4:      : 90                               nop
+# CHECK:            80: ff 14 25 00 00 00 00             callq    *0
diff --git a/llvm/test/MC/X86/align-branch-64-2c.s b/llvm/test/MC/X86/align-branch-64-2c.s
new file mode 100644
index 000000000000..71b84e587d8a
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-2c.s
@@ -0,0 +1,19 @@
+# Check only indirect jumps and calls are aligned with option --x86-align-branch-boundary=32 --x86-align-branch=indirect+call
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=indirect+call %S/align-branch-64-2a.s  | llvm-objdump -d  - | FileCheck %s
+
+# CHECK: 0000000000000000 foo:
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-COUNT-2:      : 89 75 f4                         movl    %esi, -12(%rbp)
+# CHECK-COUNT-2:      : 90                               nop
+# CHECK:            20: ff e0                            jmpq    *%rax
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            3a: 89 75 f4                         movl    %esi, -12(%rbp)
+# CHECK-NEXT:       3d: 55                               pushq    %rbp
+# CHECK-COUNT-2:      : 90                               nop
+# CHECK:            40: ff d0                            callq    *%rax
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            5a: 55                               pushq    %rbp
+# CHECK-COUNT-5:      : 90                               nop
+# CHECK:            60: e8 9b ff ff ff                   callq   {{.*}}
+# CHECK-COUNT-4:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            85: ff 14 25 00 00 00 00             callq    *0
diff --git a/llvm/test/MC/X86/align-branch-64-3a.s b/llvm/test/MC/X86/align-branch-64-3a.s
new file mode 100644
index 000000000000..47cdd10102f8
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-3a.s
@@ -0,0 +1,41 @@
+# Check NOP padding is disabled before instruction that has variant symbol operand.
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=jmp+call %s | llvm-objdump -d  - | FileCheck %s
+
+# CHECK: 0000000000000000 foo:
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-COUNT-2:      : 48 89 e5                         movq    %rsp, %rbp
+# CHECK:            1e: e8 00 00 00 00                   callq   {{.*}}
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            3b: 55                               pushq   %rbp
+# CHECK-NEXT:       3c: 89 75 f4                         movl    %esi, -12(%rbp)
+# CHECK-NEXT:       3f: ff 15 00 00 00 00                callq   *(%rip)
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            5d: ff 15 00 00 00 00                callq   *(%rip)
+# CHECK-NEXT-3:       : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            7b: ff 25 00 00 00 00                jmpq    *(%rip)
+
+  .text
+  .globl  foo
+  .p2align  4
+foo:
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  .rept 2
+  movq  %rsp, %rbp
+  .endr
+  call    __tls_get_addr@PLT
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  pushq  %rbp
+  movl  %esi, -12(%rbp)
+  call    *__tls_get_addr@GOTPCREL(%rip)
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  call *foo@GOTPCREL(%rip)
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  jmp  *foo@GOTPCREL(%rip)
diff --git a/llvm/test/MC/X86/align-branch-64-4a.s b/llvm/test/MC/X86/align-branch-64-4a.s
new file mode 100644
index 000000000000..a1db0e56b2b9
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-4a.s
@@ -0,0 +1,33 @@
+# Check only rets are aligned with option --x86-align-branch-boundary=32 --x86-align-branch=ret
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=ret %s | llvm-objdump -d  - | FileCheck %s
+
+# CHECK: 0000000000000000 foo:
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-COUNT-2:      : 48 89 e5                         movq    %rsp, %rbp
+# CHECK:            1e: 5a                               popq    %rdx
+# CHECK-NEXT:       1f: 90                               nop
+# CHECK-NEXT:       20: c3                               retq
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            39: 89 75 f4                         movl    %esi, -12(%rbp)
+# CHECK-NEXT:       3c: 31 c0                            xorl    %eax, %eax
+# CHECK-COUNT-2:      : 90                               nop
+# CHECK:            40: c2 1e 00                         retq    $30
+
+  .text
+  .globl  foo
+  .p2align  4
+foo:
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  .rept 2
+  movq  %rsp, %rbp
+  .endr
+  popq  %rdx
+  ret
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  movl  %esi, -12(%rbp)
+  xorl %eax, %eax
+  ret $30
diff --git a/llvm/test/MC/X86/align-branch-64-5a.s b/llvm/test/MC/X86/align-branch-64-5a.s
new file mode 100644
index 000000000000..1d4dbd5300ca
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-5a.s
@@ -0,0 +1,43 @@
+# Check no nop is inserted if no branch cross or is against the boundary
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=fused+jcc+jmp+indirect+call+ret  %s | llvm-objdump -d  - > %t1
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %s | llvm-objdump -d  - > %t2
+# RUN: cmp %t1 %t2
+# RUN: FileCheck --input-file=%t1 %s
+
+# CHECK: 0000000000000000 foo:
+# CHECK-COUNT-3:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            18: c1 e9 02                         shrl    $2, %ecx
+# CHECK-NEXT:       1b: 89 d1                            movl    %edx, %ecx
+# CHECK-NEXT:       1d: 75 fc                            jne     {{.*}}
+# CHECK-NEXT:       1f: 55                               pushq   %rbp
+# CHECK-NEXT:       20: f6 c2 02                         testb   $2, %dl
+# CHECK-NEXT:       23: 75 fa                            jne     {{.*}}
+# CHECK-COUNT-2:      : 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK:            35: c1 e9 02                         shrl    $2, %ecx
+# CHECK-NEXT:       38: e8 c3 ff ff ff                   callq   {{.*}}
+# CHECK-NEXT:       3d: ff e0                            jmpq    *%rax
+# CHECK-NEXT:       3f: 55                               pushq   %rbp
+# CHECK-NEXT:       40: c2 63 00                         retq    $99
+
+    .text
+    .p2align 4
+foo:
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  shrl  $2, %ecx
+.L1:
+  movl  %edx, %ecx
+  jne   .L1
+.L2:
+  push  %rbp
+  testb $2, %dl
+  jne    .L2
+  .rept 2
+  movl  %eax, %fs:0x1
+  .endr
+  shrl  $2, %ecx
+  call  foo
+  jmp   *%rax
+  push  %rbp
+  ret   $99
diff --git a/llvm/test/MC/X86/align-branch-64-5b.s b/llvm/test/MC/X86/align-branch-64-5b.s
new file mode 100644
index 000000000000..4a046f8e0640
--- /dev/null
+++ b/llvm/test/MC/X86/align-branch-64-5b.s
@@ -0,0 +1,50 @@
+# Check option --x86-align-branch-boundary=32 --x86-align-branch=fused+jcc+jmp+indirect+call+ret can cowork with option --mc-relax-all
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=32 --x86-align-branch=fused+jcc+jmp+indirect+call+ret --mc-relax-all %s | llvm-objdump -d  - > %t1
+# RUN: FileCheck --input-file=%t1 %s
+
+# CHECK: 0000000000000000 foo:
+# CHECK-NEXT:        0: 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:        8: 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:       10: 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:       18: c1 e9 02                         shrl    $2, %ecx
+# CHECK-NEXT:       1b: 89 d1                            movl    %edx, %ecx
+# CHECK-NEXT:       1d: 90                               nop
+# CHECK-NEXT:       1e: 90                               nop
+# CHECK-NEXT:       1f: 90                               nop
+# CHECK-NEXT:       20: 0f 85 f5 ff ff ff                jne     {{.*}}
+# CHECK-NEXT:       26: 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:       2e: 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:       36: f6 c2 02                         testb   $2, %dl
+# CHECK-NEXT:       39: 0f 85 e7 ff ff ff                jne     {{.*}}
+# CHECK-NEXT:       3f: 90                               nop
+# CHECK-NEXT:       40: e9 d6 ff ff ff                   jmp     {{.*}}
+# CHECK-NEXT:       45: 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:       4d: 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:       55: 64 89 04 25 01 00 00 00          movl    %eax, %fs:1
+# CHECK-NEXT:       5d: 90                               nop
+# CHECK-NEXT:       5e: 90                               nop
+# CHECK-NEXT:       5f: 90                               nop
+# CHECK-NEXT:       60: e8 9b ff ff ff                   callq   {{.*}}
+# CHECK-NEXT:       65: e9 bc ff ff ff                   jmp     {{.*}}
+    .text
+    .p2align 4
+foo:
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  shrl  $2, %ecx
+.L1:
+  movl  %edx, %ecx
+  jne   .L1
+.L2:
+  .rept 2
+  movl  %eax, %fs:0x1
+  .endr
+  testb $2, %dl
+  jne   .L2
+  jmp   .L1
+  .rept 3
+  movl  %eax, %fs:0x1
+  .endr
+  call  foo
+  jmp   .L2