Index: include/llvm/MC/MCAsmBackend.h
===================================================================
--- include/llvm/MC/MCAsmBackend.h
+++ include/llvm/MC/MCAsmBackend.h
@@ -80,9 +80,12 @@
   /// 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 = 0;
+                          uint64_t Value, bool IsResolved,
+                          const MCSubtargetInfo *STI) const = 0;
 
   /// @}
 
@@ -92,7 +95,10 @@
   /// Check whether the given instruction may need relaxation.
   ///
   /// \param Inst - The instruction to test.
-  virtual bool mayNeedRelaxation(const MCInst &Inst) const = 0;
+  /// \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.
Index: include/llvm/MC/MCFragment.h
===================================================================
--- include/llvm/MC/MCFragment.h
+++ include/llvm/MC/MCFragment.h
@@ -201,7 +201,16 @@
       : MCEncodedFragmentWithContents<ContentsSize>(FType, HasInstructions,
                                                     Sec) {}
 
+  /// STI - The MCSubtargetInfo in effect when the instruction was encoded.
+  /// must be non-null for instructions.
+  const MCSubtargetInfo *STI = nullptr;
+
 public:
+
+  /// Retrieve the MCSubTargetInfo in effect when the instruction was encoded.
+  /// Guaranteed to be non-null if hasInstructions() == true
+  const MCSubtargetInfo *getSubtargetInfo() const { return STI; }
+
   using const_fixup_iterator = SmallVectorImpl<MCFixup>::const_iterator;
   using fixup_iterator = SmallVectorImpl<MCFixup>::iterator;
 
@@ -228,7 +237,12 @@
   MCDataFragment(MCSection *Sec = nullptr)
       : MCEncodedFragmentWithFixups<32, 4>(FT_Data, false, Sec) {}
 
-  void setHasInstructions(bool V) { HasInstructions = V; }
+  /// 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;
+  }
 
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_Data;
@@ -259,20 +273,15 @@
   /// Inst - The instruction this is a fragment for.
   MCInst Inst;
 
-  /// STI - The MCSubtargetInfo in effect when the instruction was encoded.
-  const MCSubtargetInfo &STI;
-
 public:
   MCRelaxableFragment(const MCInst &Inst, const MCSubtargetInfo &STI,
                       MCSection *Sec = nullptr)
       : MCEncodedFragmentWithFixups(FT_Relaxable, true, Sec),
-        Inst(Inst), STI(STI) {}
+        Inst(Inst) { this->STI = &STI; }
 
   const MCInst &getInst() const { return Inst; }
   void setInst(const MCInst &Value) { Inst = Value; }
 
-  const MCSubtargetInfo &getSubtargetInfo() { return STI; }
-
   static bool classof(const MCFragment *F) {
     return F->getKind() == MCFragment::FT_Relaxable;
   }
Index: include/llvm/MC/MCObjectStreamer.h
===================================================================
--- include/llvm/MC/MCObjectStreamer.h
+++ include/llvm/MC/MCObjectStreamer.h
@@ -73,7 +73,9 @@
 
   /// Get a data fragment to write into, creating a new one if the current
   /// fragment is not a data fragment.
-  MCDataFragment *getOrCreateDataFragment();
+  /// 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);
   MCPaddingFragment *getOrCreatePaddingFragment();
 
 protected:
@@ -158,7 +160,8 @@
   void EmitGPRel32Value(const MCExpr *Value) override;
   void EmitGPRel64Value(const MCExpr *Value) override;
   bool EmitRelocDirective(const MCExpr &Offset, StringRef Name,
-                          const MCExpr *Expr, SMLoc Loc) override;
+                          const MCExpr *Expr, SMLoc Loc,
+                          const MCSubtargetInfo &STI) override;
   using MCStreamer::emitFill;
   void emitFill(const MCExpr &NumBytes, uint64_t FillValue,
                 SMLoc Loc = SMLoc()) override;
Index: include/llvm/MC/MCStreamer.h
===================================================================
--- include/llvm/MC/MCStreamer.h
+++ include/llvm/MC/MCStreamer.h
@@ -915,7 +915,8 @@
   /// Returns true if the relocation could not be emitted because Name is not
   /// known.
   virtual bool EmitRelocDirective(const MCExpr &Offset, StringRef Name,
-                                  const MCExpr *Expr, SMLoc Loc) {
+                                  const MCExpr *Expr, SMLoc Loc,
+                                  const MCSubtargetInfo &STI) {
     return true;
   }
 
Index: lib/MC/MCAsmStreamer.cpp
===================================================================
--- lib/MC/MCAsmStreamer.cpp
+++ lib/MC/MCAsmStreamer.cpp
@@ -312,7 +312,8 @@
   void EmitBundleUnlock() override;
 
   bool EmitRelocDirective(const MCExpr &Offset, StringRef Name,
-                          const MCExpr *Expr, SMLoc Loc) override;
+                          const MCExpr *Expr, SMLoc Loc,
+                          const MCSubtargetInfo &STI) override;
 
   /// If this file is backed by an assembly streamer, this dumps the specified
   /// string in the output .s file. This capability is indicated by the
@@ -1799,7 +1800,8 @@
 }
 
 bool MCAsmStreamer::EmitRelocDirective(const MCExpr &Offset, StringRef Name,
-                                       const MCExpr *Expr, SMLoc) {
+                                       const MCExpr *Expr, SMLoc,
+                                       const MCSubtargetInfo &STI) {
   OS << "\t.reloc ";
   Offset.print(OS, MAI);
   OS << ", " << Name;
Index: lib/MC/MCAssembler.cpp
===================================================================
--- lib/MC/MCAssembler.cpp
+++ lib/MC/MCAssembler.cpp
@@ -760,12 +760,17 @@
         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();
@@ -778,7 +783,7 @@
         std::tie(Target, FixedValue, IsResolved) =
             handleFixup(Layout, Frag, Fixup);
         getBackend().applyFixup(*this, Fixup, Target, Contents, FixedValue,
-                                IsResolved);
+                                IsResolved, STI);
       }
     }
   }
@@ -819,7 +824,7 @@
   // 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()))
+  if (!getBackend().mayNeedRelaxation(F->getInst(), *F->getSubtargetInfo()))
     return false;
 
   for (const MCFixup &Fixup : F->getFixups())
@@ -844,7 +849,7 @@
   // Relax the fragment.
 
   MCInst Relaxed;
-  getBackend().relaxInstruction(F.getInst(), F.getSubtargetInfo(), Relaxed);
+  getBackend().relaxInstruction(F.getInst(), *F.getSubtargetInfo(), Relaxed);
 
   // Encode the new instruction.
   //
@@ -853,7 +858,7 @@
   SmallVector<MCFixup, 4> Fixups;
   SmallString<256> Code;
   raw_svector_ostream VecOS(Code);
-  getEmitter().encodeInstruction(Relaxed, VecOS, Fixups, F.getSubtargetInfo());
+  getEmitter().encodeInstruction(Relaxed, VecOS, Fixups, *F.getSubtargetInfo());
 
   // Update the fragment.
   F.setInst(Relaxed);
Index: lib/MC/MCELFStreamer.cpp
===================================================================
--- lib/MC/MCELFStreamer.cpp
+++ lib/MC/MCELFStreamer.cpp
@@ -87,7 +87,8 @@
                                  DF->getContents().size());
     DF->getFixups().push_back(EF->getFixups()[i]);
   }
-  DF->setHasInstructions(true);
+  if (DF->getSubtargetInfo() == nullptr && EF->getSubtargetInfo())
+    DF->setHasInstructions(*EF->getSubtargetInfo());
   DF->getContents().append(EF->getContents().begin(), EF->getContents().end());
 }
 
@@ -471,6 +472,15 @@
     fixSymbolsInTLSFixups(F.getFixups()[i].getValue());
 }
 
+// A fragment can only have one Subtarget, and when bundling is enabled we
+// sometimes need to use the same fragment. We give an error if there
+// are conflicting Subtargets.
+static void CheckBundleSubtargets(const MCSubtargetInfo *OldSTI,
+                                  const MCSubtargetInfo *NewSTI) {
+  if (OldSTI && NewSTI && OldSTI != NewSTI)
+    report_fatal_error("A Bundle can only have one Subtarget.");
+}
+
 void MCELFStreamer::EmitInstToData(const MCInst &Inst,
                                    const MCSubtargetInfo &STI) {
   MCAssembler &Assembler = getAssembler();
@@ -486,7 +496,7 @@
   //
   // If bundling is disabled, append the encoded instruction to the current data
   // fragment (or create a new such fragment if the current fragment is not a
-  // data fragment).
+  // data fragment, or the Subtarget has changed).
   //
   // If bundling is enabled:
   // - If we're not in a bundle-locked group, emit the instruction into a
@@ -501,19 +511,23 @@
 
   if (Assembler.isBundlingEnabled()) {
     MCSection &Sec = *getCurrentSectionOnly();
-    if (Assembler.getRelaxAll() && isBundleLocked())
+    if (Assembler.getRelaxAll() && isBundleLocked()) {
       // If the -mc-relax-all flag is used and we are bundle-locked, we re-use
       // the current bundle group.
       DF = BundleGroups.back();
+      CheckBundleSubtargets(DF->getSubtargetInfo(), &STI);
+    }
     else if (Assembler.getRelaxAll() && !isBundleLocked())
       // When not in a bundle-locked group and the -mc-relax-all flag is used,
       // we create a new temporary fragment which will be later merged into
       // the current fragment.
       DF = new MCDataFragment();
-    else if (isBundleLocked() && !Sec.isBundleGroupBeforeFirstInst())
+    else if (isBundleLocked() && !Sec.isBundleGroupBeforeFirstInst()) {
       // If we are bundle-locked, we re-use the current fragment.
       // The bundle-locking directive ensures this is a new data fragment.
       DF = cast<MCDataFragment>(getCurrentFragment());
+      CheckBundleSubtargets(DF->getSubtargetInfo(), &STI);
+    }
     else if (!isBundleLocked() && Fixups.size() == 0) {
       // Optimize memory usage by emitting the instruction to a
       // MCCompactEncodedInstFragment when not in a bundle-locked group and
@@ -538,7 +552,7 @@
     // to be turned off.
     Sec.setBundleGroupBeforeFirstInst(false);
   } else {
-    DF = getOrCreateDataFragment();
+    DF = getOrCreateDataFragment(&STI);
   }
 
   // Add the fixups and data.
@@ -546,12 +560,12 @@
     Fixups[i].setOffset(Fixups[i].getOffset() + DF->getContents().size());
     DF->getFixups().push_back(Fixups[i]);
   }
-  DF->setHasInstructions(true);
+  DF->setHasInstructions(STI);
   DF->getContents().append(Code.begin(), Code.end());
 
   if (Assembler.isBundlingEnabled() && Assembler.getRelaxAll()) {
     if (!isBundleLocked()) {
-      mergeFragment(getOrCreateDataFragment(), DF);
+      mergeFragment(getOrCreateDataFragment(&STI), DF);
       delete DF;
     }
   }
@@ -611,7 +625,7 @@
 
     // FIXME: Use more separate fragments for nested groups.
     if (!isBundleLocked()) {
-      mergeFragment(getOrCreateDataFragment(), DF);
+      mergeFragment(getOrCreateDataFragment(DF->getSubtargetInfo()), DF);
       BundleGroups.pop_back();
       delete DF;
     }
Index: lib/MC/MCMachOStreamer.cpp
===================================================================
--- lib/MC/MCMachOStreamer.cpp
+++ lib/MC/MCMachOStreamer.cpp
@@ -447,6 +447,7 @@
     Fixup.setOffset(Fixup.getOffset() + DF->getContents().size());
     DF->getFixups().push_back(Fixup);
   }
+  DF->setHasInstructions(STI);
   DF->getContents().append(Code.begin(), Code.end());
 }
 
Index: lib/MC/MCObjectStreamer.cpp
===================================================================
--- lib/MC/MCObjectStreamer.cpp
+++ lib/MC/MCObjectStreamer.cpp
@@ -147,12 +147,24 @@
   return nullptr;
 }
 
-MCDataFragment *MCObjectStreamer::getOrCreateDataFragment() {
-  MCDataFragment *F = dyn_cast_or_null<MCDataFragment>(getCurrentFragment());
+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 (!F || (Assembler->isBundlingEnabled() && !Assembler->getRelaxAll() &&
-             F->hasInstructions())) {
+  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);
   }
@@ -328,7 +340,7 @@
 
   // If this instruction doesn't need relaxation, just emit it as data.
   MCAssembler &Assembler = getAssembler();
-  if (!Assembler.getBackend().mayNeedRelaxation(Inst)) {
+  if (!Assembler.getBackend().mayNeedRelaxation(Inst, STI)) {
     EmitInstToData(Inst, STI);
     return;
   }
@@ -342,7 +354,7 @@
       (Assembler.isBundlingEnabled() && Sec->isBundleLocked())) {
     MCInst Relaxed;
     getAssembler().getBackend().relaxInstruction(Inst, STI, Relaxed);
-    while (getAssembler().getBackend().mayNeedRelaxation(Relaxed))
+    while (getAssembler().getBackend().mayNeedRelaxation(Relaxed, STI))
       getAssembler().getBackend().relaxInstruction(Relaxed, STI, Relaxed);
     EmitInstToData(Relaxed, STI);
     return;
@@ -607,7 +619,8 @@
 }
 
 bool MCObjectStreamer::EmitRelocDirective(const MCExpr &Offset, StringRef Name,
-                                          const MCExpr *Expr, SMLoc Loc) {
+                                          const MCExpr *Expr, SMLoc Loc,
+                                          const MCSubtargetInfo &STI) {
   int64_t OffsetValue;
   if (!Offset.evaluateAsAbsolute(OffsetValue))
     llvm_unreachable("Offset is not absolute");
@@ -615,7 +628,7 @@
   if (OffsetValue < 0)
     llvm_unreachable("Offset is negative");
 
-  MCDataFragment *DF = getOrCreateDataFragment();
+  MCDataFragment *DF = getOrCreateDataFragment(&STI);
   flushPendingLabels(DF, DF->getContents().size());
 
   Optional<MCFixupKind> MaybeKind = Assembler->getBackend().getFixupKind(Name);
Index: lib/MC/MCParser/AsmParser.cpp
===================================================================
--- lib/MC/MCParser/AsmParser.cpp
+++ lib/MC/MCParser/AsmParser.cpp
@@ -2945,7 +2945,9 @@
                  "unexpected token in .reloc directive"))
       return true;
 
-  if (getStreamer().EmitRelocDirective(*Offset, Name, Expr, DirectiveLoc))
+  const MCTargetAsmParser &MCT = getTargetParser();
+  const MCSubtargetInfo &STI = MCT.getSTI();
+  if (getStreamer().EmitRelocDirective(*Offset, Name, Expr, DirectiveLoc, STI))
     return Error(NameLoc, "unknown relocation name");
 
   return false;
Index: lib/MC/MCWasmStreamer.cpp
===================================================================
--- lib/MC/MCWasmStreamer.cpp
+++ lib/MC/MCWasmStreamer.cpp
@@ -45,7 +45,8 @@
                                  DF->getContents().size());
     DF->getFixups().push_back(EF->getFixups()[i]);
   }
-  DF->setHasInstructions(true);
+  if (DF->getSubtargetInfo() == nullptr && EF->getSubtargetInfo())
+    DF->setHasInstructions(*EF->getSubtargetInfo());
   DF->getContents().append(EF->getContents().begin(), EF->getContents().end());
 }
 
@@ -183,7 +184,7 @@
     Fixups[i].setOffset(Fixups[i].getOffset() + DF->getContents().size());
     DF->getFixups().push_back(Fixups[i]);
   }
-  DF->setHasInstructions(true);
+  DF->setHasInstructions(STI);
   DF->getContents().append(Code.begin(), Code.end());
 }
 
Index: lib/MC/MCWinCOFFStreamer.cpp
===================================================================
--- lib/MC/MCWinCOFFStreamer.cpp
+++ lib/MC/MCWinCOFFStreamer.cpp
@@ -62,7 +62,7 @@
     Fixups[i].setOffset(Fixups[i].getOffset() + DF->getContents().size());
     DF->getFixups().push_back(Fixups[i]);
   }
-
+  DF->setHasInstructions(STI);
   DF->getContents().append(Code.begin(), Code.end());
 }
 
Index: lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp
===================================================================
--- lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp
+++ lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp
@@ -75,9 +75,11 @@
 
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
-                  uint64_t Value, bool IsResolved) const override;
+                  uint64_t Value, bool IsResolved,
+                  const MCSubtargetInfo *STI) const override;
 
-  bool mayNeedRelaxation(const MCInst &Inst) const override;
+  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;
@@ -287,7 +289,8 @@
 void AArch64AsmBackend::applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                                    const MCValue &Target,
                                    MutableArrayRef<char> Data, uint64_t Value,
-                                   bool IsResolved) const {
+                                   bool IsResolved,
+                                   const MCSubtargetInfo *STI) const {
   unsigned NumBytes = getFixupKindNumBytes(Fixup.getKind());
   if (!Value)
     return; // Doesn't change encoding.
@@ -323,7 +326,8 @@
   }
 }
 
-bool AArch64AsmBackend::mayNeedRelaxation(const MCInst &Inst) const {
+bool AArch64AsmBackend::mayNeedRelaxation(const MCInst &Inst,
+                                          const MCSubtargetInfo &STI) const {
   return false;
 }
 
Index: lib/Target/AMDGPU/MCTargetDesc/AMDGPUAsmBackend.cpp
===================================================================
--- lib/Target/AMDGPU/MCTargetDesc/AMDGPUAsmBackend.cpp
+++ lib/Target/AMDGPU/MCTargetDesc/AMDGPUAsmBackend.cpp
@@ -33,7 +33,8 @@
 
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
-                  uint64_t Value, bool IsResolved) const override;
+                  uint64_t Value, bool IsResolved,
+                  const MCSubtargetInfo *STI) const override;
   bool fixupNeedsRelaxation(const MCFixup &Fixup, uint64_t Value,
                             const MCRelaxableFragment *DF,
                             const MCAsmLayout &Layout) const override {
@@ -43,7 +44,10 @@
                         MCInst &Res) const override {
     llvm_unreachable("Not implemented");
   }
-  bool mayNeedRelaxation(const MCInst &Inst) const override { return false; }
+  bool mayNeedRelaxation(const MCInst &Inst,
+                         const MCSubtargetInfo &STI) const override {
+    return false;
+  }
 
   unsigned getMinimumNopSize() const override;
   bool writeNopData(uint64_t Count, MCObjectWriter *OW) const override;
@@ -103,7 +107,8 @@
 void AMDGPUAsmBackend::applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                                   const MCValue &Target,
                                   MutableArrayRef<char> Data, uint64_t Value,
-                                  bool IsResolved) const {
+                                  bool IsResolved,
+                                  const MCSubtargetInfo *STI) const {
   Value = adjustFixupValue(Fixup, Value, &Asm.getContext());
   if (!Value)
     return; // Doesn't change encoding.
Index: lib/Target/ARM/MCTargetDesc/ARMAsmBackend.h
===================================================================
--- lib/Target/ARM/MCTargetDesc/ARMAsmBackend.h
+++ lib/Target/ARM/MCTargetDesc/ARMAsmBackend.h
@@ -19,6 +19,9 @@
 namespace llvm {
 
 class ARMAsmBackend : public MCAsmBackend {
+  // The STI from the target triple the MCAsmBackend was instantiated with
+  // note that MCFragments may have a different local STI that should be
+  // used in preference.
   const MCSubtargetInfo &STI;
   bool isThumbMode;    // Currently emitting Thumb code.
   bool IsLittleEndian; // Big or little endian.
@@ -32,6 +35,8 @@
     return ARM::NumTargetFixupKinds;
   }
 
+  // FIXME: this should be calculated per fragment as the STI may be
+  // different.
   bool hasNOP() const { return STI.getFeatureBits()[ARM::HasV6T2Ops]; }
 
   const MCFixupKindInfo &getFixupKindInfo(MCFixupKind Kind) const override;
@@ -41,15 +46,18 @@
 
   unsigned adjustFixupValue(const MCAssembler &Asm, const MCFixup &Fixup,
                             const MCValue &Target, uint64_t Value,
-                            bool IsResolved, MCContext &Ctx) const;
+                            bool IsResolved, MCContext &Ctx,
+                            const MCSubtargetInfo *STI) const;
 
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
-                  uint64_t Value, bool IsResolved) const override;
+                  uint64_t Value, bool IsResolved,
+                  const MCSubtargetInfo *STI) const override;
 
-  unsigned getRelaxedOpcode(unsigned Op) const;
+  unsigned getRelaxedOpcode(unsigned Op, const MCSubtargetInfo &STI) const;
 
-  bool mayNeedRelaxation(const MCInst &Inst) const override;
+  bool mayNeedRelaxation(const MCInst &Inst,
+                         const MCSubtargetInfo &STI) const override;
 
   const char *reasonForFixupRelaxation(const MCFixup &Fixup,
                                        uint64_t Value) const;
Index: lib/Target/ARM/MCTargetDesc/ARMAsmBackend.cpp
===================================================================
--- lib/Target/ARM/MCTargetDesc/ARMAsmBackend.cpp
+++ lib/Target/ARM/MCTargetDesc/ARMAsmBackend.cpp
@@ -171,7 +171,8 @@
   }
 }
 
-unsigned ARMAsmBackend::getRelaxedOpcode(unsigned Op) const {
+unsigned ARMAsmBackend::getRelaxedOpcode(unsigned Op,
+                                         const MCSubtargetInfo &STI) const {
   bool HasThumb2 = STI.getFeatureBits()[ARM::FeatureThumb2];
   bool HasV8MBaselineOps = STI.getFeatureBits()[ARM::HasV8MBaselineOps];
 
@@ -193,8 +194,9 @@
   }
 }
 
-bool ARMAsmBackend::mayNeedRelaxation(const MCInst &Inst) const {
-  if (getRelaxedOpcode(Inst.getOpcode()) != Inst.getOpcode())
+bool ARMAsmBackend::mayNeedRelaxation(const MCInst &Inst,
+                                      const MCSubtargetInfo &STI) const {
+  if (getRelaxedOpcode(Inst.getOpcode(), STI) != Inst.getOpcode())
     return true;
   return false;
 }
@@ -261,7 +263,7 @@
 void ARMAsmBackend::relaxInstruction(const MCInst &Inst,
                                      const MCSubtargetInfo &STI,
                                      MCInst &Res) const {
-  unsigned RelaxedOp = getRelaxedOpcode(Inst.getOpcode());
+  unsigned RelaxedOp = getRelaxedOpcode(Inst.getOpcode(), STI);
 
   // Sanity check w/ diagnostic if we get here w/ a bogus instruction.
   if (RelaxedOp == Inst.getOpcode()) {
@@ -359,7 +361,8 @@
 unsigned ARMAsmBackend::adjustFixupValue(const MCAssembler &Asm,
                                          const MCFixup &Fixup,
                                          const MCValue &Target, uint64_t Value,
-                                         bool IsResolved, MCContext &Ctx) const {
+                                         bool IsResolved, MCContext &Ctx,
+                                         const MCSubtargetInfo* STI) const {
   unsigned Kind = Fixup.getKind();
 
   // MachO tries to make .o files that look vaguely pre-linked, so for MOVW/MOVT
@@ -388,7 +391,8 @@
   case FK_SecRel_4:
     return Value;
   case ARM::fixup_arm_movt_hi16:
-    if (IsResolved || !STI.getTargetTriple().isOSBinFormatELF())
+    assert(STI != nullptr);
+    if (IsResolved || !STI->getTargetTriple().isOSBinFormatELF())
       Value >>= 16;
     LLVM_FALLTHROUGH;
   case ARM::fixup_arm_movw_lo16: {
@@ -400,7 +404,8 @@
     return Value;
   }
   case ARM::fixup_t2_movt_hi16:
-    if (IsResolved || !STI.getTargetTriple().isOSBinFormatELF())
+    assert(STI != nullptr);
+    if (IsResolved || !STI->getTargetTriple().isOSBinFormatELF())
       Value >>= 16;
     LLVM_FALLTHROUGH;
   case ARM::fixup_t2_movw_lo16: {
@@ -590,7 +595,8 @@
   case ARM::fixup_arm_thumb_cp:
     // On CPUs supporting Thumb2, this will be relaxed to an ldr.w, otherwise we
     // could have an error on our hands.
-    if (!STI.getFeatureBits()[ARM::FeatureThumb2] && IsResolved) {
+    assert(STI != nullptr);
+    if (!STI->getFeatureBits()[ARM::FeatureThumb2] && IsResolved) {
       const char *FixupDiagnostic = reasonForFixupRelaxation(Fixup, Value);
       if (FixupDiagnostic) {
         Ctx.reportError(Fixup.getLoc(), FixupDiagnostic);
@@ -614,8 +620,9 @@
   }
   case ARM::fixup_arm_thumb_br:
     // Offset by 4 and don't encode the lower bit, which is always 0.
-    if (!STI.getFeatureBits()[ARM::FeatureThumb2] &&
-        !STI.getFeatureBits()[ARM::HasV8MBaselineOps]) {
+    assert(STI != nullptr);
+    if (!STI->getFeatureBits()[ARM::FeatureThumb2] &&
+        !STI->getFeatureBits()[ARM::HasV8MBaselineOps]) {
       const char *FixupDiagnostic = reasonForFixupRelaxation(Fixup, Value);
       if (FixupDiagnostic) {
         Ctx.reportError(Fixup.getLoc(), FixupDiagnostic);
@@ -625,7 +632,8 @@
     return ((Value - 4) >> 1) & 0x7ff;
   case ARM::fixup_arm_thumb_bcc:
     // Offset by 4 and don't encode the lower bit, which is always 0.
-    if (!STI.getFeatureBits()[ARM::FeatureThumb2]) {
+    assert(STI != nullptr);
+    if (!STI->getFeatureBits()[ARM::FeatureThumb2]) {
       const char *FixupDiagnostic = reasonForFixupRelaxation(Fixup, Value);
       if (FixupDiagnostic) {
         Ctx.reportError(Fixup.getLoc(), FixupDiagnostic);
@@ -881,10 +889,11 @@
 void ARMAsmBackend::applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                                const MCValue &Target,
                                MutableArrayRef<char> Data, uint64_t Value,
-                               bool IsResolved) const {
+                               bool IsResolved,
+                               const MCSubtargetInfo* STI) const {
   unsigned NumBytes = getFixupKindNumBytes(Fixup.getKind());
   MCContext &Ctx = Asm.getContext();
-  Value = adjustFixupValue(Asm, Fixup, Target, Value, IsResolved, Ctx);
+  Value = adjustFixupValue(Asm, Fixup, Target, Value, IsResolved, Ctx, STI);
   if (!Value)
     return; // Doesn't change encoding.
 
Index: lib/Target/BPF/MCTargetDesc/BPFAsmBackend.cpp
===================================================================
--- lib/Target/BPF/MCTargetDesc/BPFAsmBackend.cpp
+++ lib/Target/BPF/MCTargetDesc/BPFAsmBackend.cpp
@@ -29,7 +29,8 @@
 
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
-                  uint64_t Value, bool IsResolved) const override;
+                  uint64_t Value, bool IsResolved,
+                  const MCSubtargetInfo *STI) const override;
 
   std::unique_ptr<MCObjectWriter>
   createObjectWriter(raw_pwrite_stream &OS) const override;
@@ -43,7 +44,10 @@
 
   unsigned getNumFixupKinds() const override { return 1; }
 
-  bool mayNeedRelaxation(const MCInst &Inst) const override { return false; }
+  bool mayNeedRelaxation(const MCInst &Inst,
+                         const MCSubtargetInfo &STI) const override {
+    return false;
+  }
 
   void relaxInstruction(const MCInst &Inst, const MCSubtargetInfo &STI,
                         MCInst &Res) const override {}
@@ -66,7 +70,8 @@
 void BPFAsmBackend::applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                                const MCValue &Target,
                                MutableArrayRef<char> Data, uint64_t Value,
-                               bool IsResolved) const {
+                               bool IsResolved,
+                               const MCSubtargetInfo *STI) const {
   if (Fixup.getKind() == FK_SecRel_4 || Fixup.getKind() == FK_SecRel_8) {
     assert(Value == 0);
   } else if (Fixup.getKind() == FK_Data_4 || Fixup.getKind() == FK_Data_8) {
Index: lib/Target/Hexagon/MCTargetDesc/HexagonAsmBackend.cpp
===================================================================
--- lib/Target/Hexagon/MCTargetDesc/HexagonAsmBackend.cpp
+++ lib/Target/Hexagon/MCTargetDesc/HexagonAsmBackend.cpp
@@ -51,7 +51,7 @@
     SmallVector<MCFixup, 4> Fixups;
     SmallString<256> Code;
     raw_svector_ostream VecOS(Code);
-    E.encodeInstruction(HMB, VecOS, Fixups, RF.getSubtargetInfo());
+    E.encodeInstruction(HMB, VecOS, Fixups, *RF.getSubtargetInfo());
 
     // Update the fragment.
     RF.setInst(HMB);
@@ -413,7 +413,8 @@
   /// fixup kind as appropriate.
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
-                  uint64_t FixupValue, bool IsResolved) const override {
+                  uint64_t FixupValue, bool IsResolved,
+                  const MCSubtargetInfo *STI) const override {
 
     // When FixupValue is 0 the relocation is external and there
     // is nothing for us to do.
@@ -560,7 +561,8 @@
   /// relaxation.
   ///
   /// \param Inst - The instruction to test.
-  bool mayNeedRelaxation(MCInst const &Inst) const override {
+  bool mayNeedRelaxation(MCInst const &Inst,
+                         const MCSubtargetInfo &STI) const override {
     return true;
   }
 
@@ -735,7 +737,7 @@
                 Inst.addOperand(MCOperand::createInst(Nop));
                 Size -= 4;
                 if (!HexagonMCChecker(
-                         Context, *MCII, RF.getSubtargetInfo(), Inst,
+                         Context, *MCII, *RF.getSubtargetInfo(), Inst,
                          *Context.getRegisterInfo(), false)
                          .check()) {
                   Inst.erase(Inst.end() - 1);
@@ -743,7 +745,7 @@
                 }
               }
               bool Error = HexagonMCShuffle(Context, true, *MCII,
-                                            RF.getSubtargetInfo(), Inst);
+                                            *RF.getSubtargetInfo(), Inst);
               //assert(!Error);
               (void)Error;
               ReplaceInstruction(Asm.getEmitter(), RF, Inst);
Index: lib/Target/Lanai/MCTargetDesc/LanaiAsmBackend.cpp
===================================================================
--- lib/Target/Lanai/MCTargetDesc/LanaiAsmBackend.cpp
+++ lib/Target/Lanai/MCTargetDesc/LanaiAsmBackend.cpp
@@ -51,7 +51,8 @@
 
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
-                  uint64_t Value, bool IsResolved) const override;
+                  uint64_t Value, bool IsResolved,
+                  const MCSubtargetInfo *STI) const override;
 
   std::unique_ptr<MCObjectWriter>
   createObjectWriter(raw_pwrite_stream &OS) const override;
@@ -69,7 +70,8 @@
     return Lanai::NumTargetFixupKinds;
   }
 
-  bool mayNeedRelaxation(const MCInst & /*Inst*/) const override {
+  bool mayNeedRelaxation(const MCInst & /*Inst*/,
+                         const MCSubtargetInfo &STI) const override {
     return false;
   }
 
@@ -93,7 +95,8 @@
 void LanaiAsmBackend::applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                                  const MCValue &Target,
                                  MutableArrayRef<char> Data, uint64_t Value,
-                                 bool /*IsResolved*/) const {
+                                 bool /*IsResolved*/,
+                                 const MCSubtargetInfo */*STI*/) const {
   MCFixupKind Kind = Fixup.getKind();
   Value = adjustFixupValue(static_cast<unsigned>(Kind), Value);
 
Index: lib/Target/Mips/MCTargetDesc/MipsAsmBackend.h
===================================================================
--- lib/Target/Mips/MCTargetDesc/MipsAsmBackend.h
+++ lib/Target/Mips/MCTargetDesc/MipsAsmBackend.h
@@ -42,7 +42,8 @@
 
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
-                  uint64_t Value, bool IsResolved) const override;
+                  uint64_t Value, bool IsResolved,
+                  const MCSubtargetInfo *STI) const override;
 
   Optional<MCFixupKind> getFixupKind(StringRef Name) const override;
   const MCFixupKindInfo &getFixupKindInfo(MCFixupKind Kind) const override;
@@ -58,7 +59,8 @@
   /// relaxation.
   ///
   /// \param Inst - The instruction to test.
-  bool mayNeedRelaxation(const MCInst &Inst) const override {
+  bool mayNeedRelaxation(const MCInst &Inst,
+                         const MCSubtargetInfo &STI) const override {
     return false;
   }
 
Index: lib/Target/Mips/MCTargetDesc/MipsAsmBackend.cpp
===================================================================
--- lib/Target/Mips/MCTargetDesc/MipsAsmBackend.cpp
+++ lib/Target/Mips/MCTargetDesc/MipsAsmBackend.cpp
@@ -239,7 +239,8 @@
 void MipsAsmBackend::applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                                 const MCValue &Target,
                                 MutableArrayRef<char> Data, uint64_t Value,
-                                bool IsResolved) const {
+                                bool IsResolved,
+                                const MCSubtargetInfo *STI) const {
   MCFixupKind Kind = Fixup.getKind();
   MCContext &Ctx = Asm.getContext();
   Value = adjustFixupValue(Fixup, Value, Ctx);
Index: lib/Target/PowerPC/MCTargetDesc/PPCAsmBackend.cpp
===================================================================
--- lib/Target/PowerPC/MCTargetDesc/PPCAsmBackend.cpp
+++ lib/Target/PowerPC/MCTargetDesc/PPCAsmBackend.cpp
@@ -116,7 +116,8 @@
 
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
-                  uint64_t Value, bool IsResolved) const override {
+                  uint64_t Value, bool IsResolved,
+                  const MCSubtargetInfo *STI) const override {
     Value = adjustFixupValue(Fixup.getKind(), Value);
     if (!Value) return;           // Doesn't change encoding.
 
@@ -156,7 +157,8 @@
     }
   }
 
-  bool mayNeedRelaxation(const MCInst &Inst) const override {
+  bool mayNeedRelaxation(const MCInst &Inst,
+                         const MCSubtargetInfo &STI) const override {
     // FIXME.
     return false;
   }
Index: lib/Target/Sparc/MCTargetDesc/SparcAsmBackend.cpp
===================================================================
--- lib/Target/Sparc/MCTargetDesc/SparcAsmBackend.cpp
+++ lib/Target/Sparc/MCTargetDesc/SparcAsmBackend.cpp
@@ -234,7 +234,8 @@
       }
     }
 
-    bool mayNeedRelaxation(const MCInst &Inst) const override {
+    bool mayNeedRelaxation(const MCInst &Inst,
+                           const MCSubtargetInfo &STI) const override {
       // FIXME.
       return false;
     }
@@ -276,7 +277,8 @@
 
     void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                     const MCValue &Target, MutableArrayRef<char> Data,
-                    uint64_t Value, bool IsResolved) const override {
+                    uint64_t Value, bool IsResolved,
+                    const MCSubtargetInfo *STI) const override {
 
       Value = adjustFixupValue(Fixup.getKind(), Value);
       if (!Value) return;           // Doesn't change encoding.
Index: lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmBackend.cpp
===================================================================
--- lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmBackend.cpp
+++ lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmBackend.cpp
@@ -53,8 +53,10 @@
   const MCFixupKindInfo &getFixupKindInfo(MCFixupKind Kind) const override;
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
-                  uint64_t Value, bool IsResolved) const override;
-  bool mayNeedRelaxation(const MCInst &Inst) const override {
+                  uint64_t Value, bool IsResolved,
+                  const MCSubtargetInfo *STI) const override;
+  bool mayNeedRelaxation(const MCInst &Inst,
+                         const MCSubtargetInfo &STI) const override {
     return false;
   }
   bool fixupNeedsRelaxation(const MCFixup &Fixup, uint64_t Value,
@@ -96,7 +98,8 @@
                                      const MCFixup &Fixup,
                                      const MCValue &Target,
                                      MutableArrayRef<char> Data, uint64_t Value,
-                                     bool IsResolved) const {
+                                     bool IsResolved,
+                                     const MCSubtargetInfo *STI) const {
   MCFixupKind Kind = Fixup.getKind();
   unsigned Offset = Fixup.getOffset();
   unsigned BitSize = getFixupKindInfo(Kind).TargetSize;
Index: lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
===================================================================
--- lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
+++ lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
@@ -101,7 +101,8 @@
 
   void applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                   const MCValue &Target, MutableArrayRef<char> Data,
-                  uint64_t Value, bool IsResolved) const override {
+                  uint64_t Value, bool IsResolved,
+                  const MCSubtargetInfo *STI) const override {
     unsigned Size = 1 << getFixupKindLog2Size(Fixup.getKind());
 
     assert(Fixup.getOffset() + Size <= Data.size() && "Invalid fixup offset!");
@@ -117,7 +118,8 @@
       Data[Fixup.getOffset() + i] = uint8_t(Value >> (i * 8));
   }
 
-  bool mayNeedRelaxation(const MCInst &Inst) const override;
+  bool mayNeedRelaxation(const MCInst &Inst,
+                         const MCSubtargetInfo &STI) const override;
 
   bool fixupNeedsRelaxation(const MCFixup &Fixup, uint64_t Value,
                             const MCRelaxableFragment *DF,
@@ -264,7 +266,8 @@
   return getRelaxedOpcodeBranch(Inst, is16BitMode);
 }
 
-bool X86AsmBackend::mayNeedRelaxation(const MCInst &Inst) const {
+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;
Index: test/CodeGen/ARM/relax-per-target-feature.ll
===================================================================
--- /dev/null
+++ test/CodeGen/ARM/relax-per-target-feature.ll
@@ -0,0 +1,34 @@
+; RUN: llc -mtriple=thumbv4t-linux-gnueabi -o - %s | FileCheck %s
+
+; Functions may have more features than the base triple; code generation and
+; instruction selection may be performed based on this information. This test
+; makes sure that the MC layer performs instruction relaxation based on the
+; target-features of the function. The relaxation for tail call is particularly
+; important on Thumb2 as the 16-bit Thumb branch instruction has an extremely
+; short range.
+
+declare dso_local void @g(...) local_unnamed_addr #2
+
+define dso_local void @f() local_unnamed_addr #0 {
+entry:
+  tail call void bitcast (void (...)* @g to void ()*)() #3
+  ret void
+}
+; Function has thumb2 target-feature, tail call is allowed and must be widened.
+; CHECK: f:
+; CHECK: b g
+
+define dso_local void @h() local_unnamed_addr #2 {
+entry:
+  tail call void bitcast (void (...)* @g to void ()*)() #3
+  ret void
+}
+; Function does not have thumb2 target-feature, tail call should not be
+; generated as it cannot be widened.
+; CHECK: h:
+; CHECK: bl g
+
+attributes #0 = { nounwind  "disable-tail-calls"="false" "target-cpu"="cortex-a53" "target-features"="+crypto,+fp-armv8,+neon,+soft-float-abi,+strict-align,+thumb-mode,-crc,-dotprod,-dsp,-hwdiv,-hwdiv-arm,-ras" "use-soft-float"="true" }
+
+attributes #2 = { nounwind  "disable-tail-calls"="false" "target-cpu"="arm7tdmi" "target-features"="+strict-align,+thumb-mode,-crc,-dotprod,-dsp,-hwdiv,-hwdiv-arm,-ras" "unsafe-fp-math"="false" "use-soft-float"="true" }
+attributes #3 = { nounwind }
Index: test/MC/ARM/AlignedBundling/illegal-subtarget-change.s
===================================================================
--- /dev/null
+++ test/MC/ARM/AlignedBundling/illegal-subtarget-change.s
@@ -0,0 +1,16 @@
+# RUN: not llvm-mc -filetype=obj -triple armv7-linux-gnueabi %s -o - 2>&1 | FileCheck %s
+
+        # We cannot switch subtargets mid-bundle
+        .syntax unified
+        .text
+        .bundle_align_mode 4
+        .arch armv4t
+        bx lr
+        .bundle_lock
+        bx lr
+        .arch armv7a
+        movt r0, #0xffff
+        movw r0, #0xffff
+        .bundle_unlock
+        bx lr
+# CHECK: LLVM ERROR: A Bundle can only have one Subtarget.
Index: test/MC/ARM/AlignedBundling/subtarget-change.s
===================================================================
--- /dev/null
+++ test/MC/ARM/AlignedBundling/subtarget-change.s
@@ -0,0 +1,33 @@
+# RUN: llvm-mc -filetype=obj -triple armv7-linux-gnueabi %s -o - \
+# RUN:   | llvm-objdump -no-show-raw-insn -triple armv7 -disassemble - | FileCheck %s
+
+        # We can switch subtargets with .arch outside of a bundle
+        .syntax unified
+        .text
+        .bundle_align_mode 4
+        .arch armv4t
+        bx lr
+        .bundle_lock
+        and r1, r1, r1
+        and r1, r1, r1
+        .bundle_unlock
+        bx lr
+
+        # We can switch subtargets at the start of a bundle
+        bx lr
+        .bundle_lock align_to_end
+        .arch armv7a
+        movt r0, #0xffff
+        movw r0, #0xffff
+        .bundle_unlock
+        bx lr
+
+# CHECK:      0: bx    lr
+# CHECK-NEXT: 4: and   r1, r1, r1
+# CHECK-NEXT: 8: and   r1, r1, r1
+# CHECK-NEXT: c: bx    lr
+# CHECK-NEXT: 10: bx    lr
+# CHECK-NEXT: 14: nop
+# CHECK-NEXT: 18: movt  r0, #65535
+# CHECK-NEXT: 1c: movw  r0, #65535
+# CHECK-NEXT: 20: bx    lr
Index: test/MC/ARM/fixup-per-fragment.s
===================================================================
--- /dev/null
+++ test/MC/ARM/fixup-per-fragment.s
@@ -0,0 +1,20 @@
+@ RUN: not llvm-mc -triple armv7a-linux-gnueabihf %s -filetype=obj -o %s.o 2>&1 | FileCheck %s
+
+@ The relaxations should be applied using the subtarget from the fragment
+@ containing the fixup and not the per module subtarget.
+
+        .syntax unified
+        .thumb
+        @ Place a literal pool out of range of the 16-bit ldr but within
+        @ range of the 32-bit ldr.w
+        .text
+        @ Relaxation to ldr.w as target triple supports Thumb2
+        ldr r0,=0x12345678
+        .arch armv4t
+        @ No relaxation as v4t does not support Thumb
+        @ expect out of range error message
+        ldr r0,=0x87654321
+        .space 1024
+
+@ CHECK: error: out of range pc-relative fixup value
+@ CHECK-NEXT: ldr r0,=0x87654321
Index: test/MC/X86/AlignedBundling/bundle-subtarget-change-error.s
===================================================================
--- /dev/null
+++ test/MC/X86/AlignedBundling/bundle-subtarget-change-error.s
@@ -0,0 +1,16 @@
+# RUN: not llvm-mc -filetype=obj -triple x86_64-pc-linux-gnu -mcpu=pentiumpro %s -o - 2>&1 | FileCheck %s
+# RUN: not llvm-mc -filetype=obj -triple x86_64-pc-linux-gnu -mcpu=pentiumpro -mc-relax-all %s -o - 2>&1 | FileCheck %s
+
+# Switching mode will change subtarget, which we can't do within a bundle
+  .text
+  .code64
+  .bundle_align_mode 4
+foo:
+  pushq   %rbp
+  .bundle_lock
+  addl    %ebp, %eax
+  .code32
+  movb  $0x0, (%si)
+  .bundle_unlock
+
+CHECK:  LLVM ERROR: A Bundle can only have one Subtarget.