Correct dwarf unwind information in function epilogue for X86

This patch aims to provide correct dwarf unwind information in function
epilogue for X86.

It consists of two parts. The first part inserts CFI instructions that set
appropriate cfa offset and cfa register in emitEpilogue() in
X86FrameLowering. This part is X86 specific.

The second part is platform independent and ensures that:

- CFI instructions do not affect code generation
- Unwind information remains correct when a function is modified by
  different passes. This is done in a late pass by analyzing information
  about cfa offset and cfa register in BBs and inserting additional CFI
  directives where necessary.

Changed CFI instructions so that they:

- are duplicable
- are not counted as instructions when tail duplicating or tail merging
- can be compared as equal

Added CFIInstrInserter pass:

- analyzes each basic block to determine cfa offset and register valid at
  its entry and exit
- verifies that outgoing cfa offset and register of predecessor blocks match
  incoming values of their successors
- inserts additional CFI directives at basic block beginning to correct the
  rule for calculating CFA

Having CFI instructions in function epilogue can cause incorrect CFA
calculation rule for some basic blocks. This can happen if, due to basic
block reordering, or the existence of multiple epilogue blocks, some of the
blocks have wrong cfa offset and register values set by the epilogue block
above them.

CFIInstrInserter is currently run only on X86, but can be used by any target
that implements support for adding CFI instructions in epilogue.


Patch by Violeta Vukobrat.

Differential Revision: https://reviews.llvm.org/D35844


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317100 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/CodeGen/Passes.h

@@ -417,6 +417,9 @@ namespace llvm {
   /// shuffles.
   FunctionPass *createExpandReductionsPass();
 
+  /// Creates CFI Instruction Inserter pass. \see CFIInstrInserter.cpp
+  FunctionPass *createCFIInstrInserter();
+
 } // End llvm namespace
 
 #endif

include/llvm/InitializePasses.h

@@ -85,6 +85,7 @@ void initializeCFGOnlyViewerLegacyPassPass(PassRegistry&);
 void initializeCFGPrinterLegacyPassPass(PassRegistry&);
 void initializeCFGSimplifyPassPass(PassRegistry&);
 void initializeCFGViewerLegacyPassPass(PassRegistry&);
+void initializeCFIInstrInserterPass(PassRegistry&);
 void initializeCFLAndersAAWrapperPassPass(PassRegistry&);
 void initializeCFLSteensAAWrapperPassPass(PassRegistry&);
 void initializeCallGraphDOTPrinterPass(PassRegistry&);

include/llvm/Target/Target.td

@@ -902,7 +902,7 @@ def CFI_INSTRUCTION : Instruction {
   let InOperandList = (ins i32imm:$id);
   let AsmString = "";
   let hasCtrlDep = 1;
-  let isNotDuplicable = 1;
+  let isNotDuplicable = 0;
 }
 def EH_LABEL : Instruction {
   let OutOperandList = (outs);

include/llvm/Target/TargetFrameLowering.h

@@ -341,6 +341,14 @@ public:
           return false;
     return true;
   }
+
+  /// Return initial CFA offset value i.e. the one valid at the beginning of the
+  /// function (before any stack operations).
+  virtual int getInitialCFAOffset(const MachineFunction &MF) const;
+
+  /// Return initial CFA register value i.e. the one valid at the beginning of
+  /// the function (before any stack operations).
+  virtual unsigned getInitialCFARegister(const MachineFunction &MF) const;
 };
 
 } // End llvm namespace

lib/CodeGen/BranchFolding.cpp

@@ -296,6 +296,11 @@ static unsigned HashEndOfMBB(const MachineBasicBlock &MBB) {
   return HashMachineInstr(*I);
 }
 
+// Whether MI should be counted as an instruction when calculating common tail.
+static bool countsAsInstruction(const MachineInstr &MI) {
+  return !(MI.isDebugValue() || MI.isCFIInstruction());
+}
+
 /// ComputeCommonTailLength - Given two machine basic blocks, compute the number
 /// of instructions they actually have in common together at their end.  Return
 /// iterators for the first shared instruction in each block.
@@ -310,9 +315,9 @@ static unsigned ComputeCommonTailLength(MachineBasicBlock *MBB1,
   while (I1 != MBB1->begin() && I2 != MBB2->begin()) {
     --I1; --I2;
     // Skip debugging pseudos; necessary to avoid changing the code.
-    while (I1->isDebugValue()) {
+    while (!countsAsInstruction(*I1)) {
       if (I1==MBB1->begin()) {
-        while (I2->isDebugValue()) {
+        while (!countsAsInstruction(*I2)) {
           if (I2==MBB2->begin())
             // I1==DBG at begin; I2==DBG at begin
             return TailLen;
@@ -325,7 +330,7 @@ static unsigned ComputeCommonTailLength(MachineBasicBlock *MBB1,
       --I1;
     }
     // I1==first (untested) non-DBG preceding known match
-    while (I2->isDebugValue()) {
+    while (!countsAsInstruction(*I2)) {
       if (I2==MBB2->begin()) {
         ++I1;
         // I1==non-DBG, or first of DBGs not at begin; I2==DBG at begin
@@ -368,6 +373,35 @@ static unsigned ComputeCommonTailLength(MachineBasicBlock *MBB1,
     }
     ++I1;
   }
+
+  // Ensure that I1 and I2 do not point to a CFI_INSTRUCTION. This can happen if
+  // I1 and I2 are non-identical when compared and then one or both of them ends
+  // up pointing to a CFI instruction after being incremented. For example:
+  /*
+    BB1:
+    ...
+    INSTRUCTION_A
+    ADD32ri8  <- last common instruction
+    ...
+    BB2:
+    ...
+    INSTRUCTION_B
+    CFI_INSTRUCTION
+    ADD32ri8  <- last common instruction
+    ...
+  */
+  // When INSTRUCTION_A and INSTRUCTION_B are compared as not equal, after
+  // incrementing the iterators, I1 will point to ADD, however I2 will point to
+  // the CFI instruction. Later on, this leads to BB2 being 'hacked off' at the
+  // wrong place (in ReplaceTailWithBranchTo()) which results in losing this CFI
+  // instruction.
+  while (I1 != MBB1->end() && I1->isCFIInstruction()) {
+    ++I1;
+  }
+
+  while (I2 != MBB2->end() && I2->isCFIInstruction()) {
+    ++I2;
+  }
   return TailLen;
 }
 
@@ -454,7 +488,7 @@ static unsigned EstimateRuntime(MachineBasicBlock::iterator I,
                                 MachineBasicBlock::iterator E) {
   unsigned Time = 0;
   for (; I != E; ++I) {
-    if (I->isDebugValue())
+    if (!countsAsInstruction(*I))
       continue;
     if (I->isCall())
       Time += 10;
@@ -814,12 +848,12 @@ mergeOperations(MachineBasicBlock::iterator MBBIStartPos,
     assert(MBBI != MBBIE && "Reached BB end within common tail length!");
     (void)MBBIE;
 
-    if (MBBI->isDebugValue()) {
+    if (!countsAsInstruction(*MBBI)) {
       ++MBBI;
       continue;
     }
 
-    while ((MBBICommon != MBBIECommon) && MBBICommon->isDebugValue())
+    while ((MBBICommon != MBBIECommon) && !countsAsInstruction(*MBBICommon))
       ++MBBICommon;
 
     assert(MBBICommon != MBBIECommon &&
@@ -859,7 +893,7 @@ void BranchFolder::mergeCommonTails(unsigned commonTailIndex) {
   }
 
   for (auto &MI : *MBB) {
-    if (MI.isDebugValue())
+    if (!countsAsInstruction(MI))
       continue;
     DebugLoc DL = MI.getDebugLoc();
     for (unsigned int i = 0 ; i < NextCommonInsts.size() ; i++) {
@@ -869,7 +903,7 @@ void BranchFolder::mergeCommonTails(unsigned commonTailIndex) {
       auto &Pos = NextCommonInsts[i];
       assert(Pos != SameTails[i].getBlock()->end() &&
           "Reached BB end within common tail");
-      while (Pos->isDebugValue()) {
+      while (!countsAsInstruction(*Pos)) {
         ++Pos;
         assert(Pos != SameTails[i].getBlock()->end() &&
             "Reached BB end within common tail");

lib/CodeGen/CFIInstrInserter.cpp

@@ -0,0 +1,319 @@
+//===------ CFIInstrInserter.cpp - Insert additional CFI instructions -----===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+/// \file This pass verifies incoming and outgoing CFA information of basic
+/// blocks. CFA information is information about offset and register set by CFI
+/// directives, valid at the start and end of a basic block. This pass checks
+/// that outgoing information of predecessors matches incoming information of
+/// their successors. Then it checks if blocks have correct CFA calculation rule
+/// set and inserts additional CFI instruction at their beginnings if they
+/// don't. CFI instructions are inserted if basic blocks have incorrect offset
+/// or register set by previous blocks, as a result of a non-linear layout of
+/// blocks in a function.
+//===----------------------------------------------------------------------===//
+
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineModuleInfo.h"
+#include "llvm/CodeGen/Passes.h"
+#include "llvm/Target/TargetFrameLowering.h"
+#include "llvm/Target/TargetInstrInfo.h"
+#include "llvm/Target/TargetMachine.h"
+#include "llvm/Target/TargetSubtargetInfo.h"
+using namespace llvm;
+
+namespace {
+class CFIInstrInserter : public MachineFunctionPass {
+ public:
+  static char ID;
+
+  CFIInstrInserter() : MachineFunctionPass(ID) {
+    initializeCFIInstrInserterPass(*PassRegistry::getPassRegistry());
+  }
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.setPreservesAll();
+    MachineFunctionPass::getAnalysisUsage(AU);
+  }
+
+  bool runOnMachineFunction(MachineFunction &MF) override {
+
+    if (!MF.getMMI().hasDebugInfo() &&
+        !MF.getFunction()->needsUnwindTableEntry())
+      return false;
+
+    MBBVector.resize(MF.getNumBlockIDs());
+    calculateCFAInfo(MF);
+#ifndef NDEBUG
+    unsigned ErrorNum = verify(MF);
+    if (ErrorNum)
+      report_fatal_error("Found " + Twine(ErrorNum) +
+                         " in/out CFI information errors.");
+#endif
+    bool insertedCFI = insertCFIInstrs(MF);
+    MBBVector.clear();
+    return insertedCFI;
+  }
+
+ private:
+  struct MBBCFAInfo {
+    MachineBasicBlock *MBB;
+    /// Value of cfa offset valid at basic block entry.
+    int IncomingCFAOffset = -1;
+    /// Value of cfa offset valid at basic block exit.
+    int OutgoingCFAOffset = -1;
+    /// Value of cfa register valid at basic block entry.
+    unsigned IncomingCFARegister = 0;
+    /// Value of cfa register valid at basic block exit.
+    unsigned OutgoingCFARegister = 0;
+    /// If in/out cfa offset and register values for this block have already
+    /// been set or not.
+    bool Processed = false;
+  };
+
+  /// Contains cfa offset and register values valid at entry and exit of basic
+  /// blocks.
+  SmallVector<struct MBBCFAInfo, 4> MBBVector;
+
+  /// Calculate cfa offset and register values valid at entry and exit for all
+  /// basic blocks in a function.
+  void calculateCFAInfo(MachineFunction &MF);
+  /// Calculate cfa offset and register values valid at basic block exit by
+  /// checking the block for CFI instructions. Block's incoming CFA info remains
+  /// the same.
+  void calculateOutgoingCFAInfo(struct MBBCFAInfo &MBBInfo);
+  /// Update in/out cfa offset and register values for successors of the basic
+  /// block.
+  void updateSuccCFAInfo(struct MBBCFAInfo &MBBInfo);
+
+  /// Check if incoming CFA information of a basic block matches outgoing CFA
+  /// information of the previous block. If it doesn't, insert CFI instruction
+  /// at the beginning of the block that corrects the CFA calculation rule for
+  /// that block.
+  bool insertCFIInstrs(MachineFunction &MF);
+  /// Return the cfa offset value that should be set at the beginning of a MBB
+  /// if needed. The negated value is needed when creating CFI instructions that
+  /// set absolute offset.
+  int getCorrectCFAOffset(MachineBasicBlock *MBB) {
+    return -MBBVector[MBB->getNumber()].IncomingCFAOffset;
+  }
+
+  void report(const char *msg, MachineBasicBlock &MBB);
+  /// Go through each MBB in a function and check that outgoing offset and
+  /// register of its predecessors match incoming offset and register of that
+  /// MBB, as well as that incoming offset and register of its successors match
+  /// outgoing offset and register of the MBB.
+  unsigned verify(MachineFunction &MF);
+};
+}
+
+char CFIInstrInserter::ID = 0;
+INITIALIZE_PASS(CFIInstrInserter, "cfi-instr-inserter",
+                "Check CFA info and insert CFI instructions if needed", false,
+                false)
+FunctionPass *llvm::createCFIInstrInserter() { return new CFIInstrInserter(); }
+
+void CFIInstrInserter::calculateCFAInfo(MachineFunction &MF) {
+  // Initial CFA offset value i.e. the one valid at the beginning of the
+  // function.
+  int InitialOffset =
+      MF.getSubtarget().getFrameLowering()->getInitialCFAOffset(MF);
+  // Initial CFA register value i.e. the one valid at the beginning of the
+  // function.
+  unsigned InitialRegister =
+      MF.getSubtarget().getFrameLowering()->getInitialCFARegister(MF);
+
+  // Initialize MBBMap.
+  for (MachineBasicBlock &MBB : MF) {
+    struct MBBCFAInfo MBBInfo;
+    MBBInfo.MBB = &MBB;
+    MBBInfo.IncomingCFAOffset = InitialOffset;
+    MBBInfo.OutgoingCFAOffset = InitialOffset;
+    MBBInfo.IncomingCFARegister = InitialRegister;
+    MBBInfo.OutgoingCFARegister = InitialRegister;
+    MBBVector[MBB.getNumber()] = MBBInfo;
+  }
+
+  // Set in/out cfa info for all blocks in the function. This traversal is based
+  // on the assumption that the first block in the function is the entry block
+  // i.e. that it has initial cfa offset and register values as incoming CFA
+  // information.
+  for (MachineBasicBlock &MBB : MF) {
+    if (MBBVector[MBB.getNumber()].Processed) continue;
+    calculateOutgoingCFAInfo(MBBVector[MBB.getNumber()]);
+    updateSuccCFAInfo(MBBVector[MBB.getNumber()]);
+  }
+}
+
+void CFIInstrInserter::calculateOutgoingCFAInfo(struct MBBCFAInfo &MBBInfo) {
+  // Outgoing cfa offset set by the block.
+  int SetOffset = MBBInfo.IncomingCFAOffset;
+  // Outgoing cfa register set by the block.
+  unsigned SetRegister = MBBInfo.IncomingCFARegister;
+  const std::vector<MCCFIInstruction> &Instrs =
+      MBBInfo.MBB->getParent()->getFrameInstructions();
+
+  // Determine cfa offset and register set by the block.
+  for (MachineInstr &MI :
+       make_range(MBBInfo.MBB->instr_begin(), MBBInfo.MBB->instr_end())) {
+    if (MI.isCFIInstruction()) {
+      unsigned CFIIndex = MI.getOperand(0).getCFIIndex();
+      const MCCFIInstruction &CFI = Instrs[CFIIndex];
+      if (CFI.getOperation() == MCCFIInstruction::OpDefCfaRegister) {
+        SetRegister = CFI.getRegister();
+      } else if (CFI.getOperation() == MCCFIInstruction::OpDefCfaOffset) {
+        SetOffset = CFI.getOffset();
+      } else if (CFI.getOperation() == MCCFIInstruction::OpAdjustCfaOffset) {
+        SetOffset += CFI.getOffset();
+      } else if (CFI.getOperation() == MCCFIInstruction::OpDefCfa) {
+        SetRegister = CFI.getRegister();
+        SetOffset = CFI.getOffset();
+      }
+    }
+  }
+
+  MBBInfo.Processed = true;
+
+  // Update outgoing CFA info.
+  MBBInfo.OutgoingCFAOffset = SetOffset;
+  MBBInfo.OutgoingCFARegister = SetRegister;
+}
+
+void CFIInstrInserter::updateSuccCFAInfo(struct MBBCFAInfo &MBBInfo) {
+
+  for (MachineBasicBlock *Succ : MBBInfo.MBB->successors()) {
+    struct MBBCFAInfo &SuccInfo = MBBVector[Succ->getNumber()];
+    if (SuccInfo.Processed) continue;
+    SuccInfo.IncomingCFAOffset = MBBInfo.OutgoingCFAOffset;
+    SuccInfo.IncomingCFARegister = MBBInfo.OutgoingCFARegister;
+    calculateOutgoingCFAInfo(SuccInfo);
+    updateSuccCFAInfo(SuccInfo);
+  }
+}
+
+bool CFIInstrInserter::insertCFIInstrs(MachineFunction &MF) {
+
+  const struct MBBCFAInfo *PrevMBBInfo = &MBBVector[MF.front().getNumber()];
+  const TargetInstrInfo *TII = MF.getSubtarget().getInstrInfo();
+  bool InsertedCFIInstr = false;
+
+  for (MachineBasicBlock &MBB : MF) {
+    // Skip the first MBB in a function
+    if (MBB.getNumber() == MF.front().getNumber()) continue;
+
+    const struct MBBCFAInfo& MBBInfo = MBBVector[MBB.getNumber()];
+    auto MBBI = MBBInfo.MBB->begin();
+    DebugLoc DL = MBBInfo.MBB->findDebugLoc(MBBI);
+
+    if (PrevMBBInfo->OutgoingCFAOffset != MBBInfo.IncomingCFAOffset) {
+      // If both outgoing offset and register of a previous block don't match
+      // incoming offset and register of this block, add a def_cfa instruction
+      // with the correct offset and register for this block.
+      if (PrevMBBInfo->OutgoingCFARegister != MBBInfo.IncomingCFARegister) {
+        unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createDefCfa(
+            nullptr, MBBInfo.IncomingCFARegister, getCorrectCFAOffset(&MBB)));
+        BuildMI(*MBBInfo.MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
+            .addCFIIndex(CFIIndex);
+        // If outgoing offset of a previous block doesn't match incoming offset
+        // of this block, add a def_cfa_offset instruction with the correct
+        // offset for this block.
+      } else {
+        unsigned CFIIndex =
+            MF.addFrameInst(MCCFIInstruction::createDefCfaOffset(
+                nullptr, getCorrectCFAOffset(&MBB)));
+        BuildMI(*MBBInfo.MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
+            .addCFIIndex(CFIIndex);
+      }
+      InsertedCFIInstr = true;
+      // If outgoing register of a previous block doesn't match incoming
+      // register of this block, add a def_cfa_register instruction with the
+      // correct register for this block.
+    } else if (PrevMBBInfo->OutgoingCFARegister != MBBInfo.IncomingCFARegister) {
+      unsigned CFIIndex =
+          MF.addFrameInst(MCCFIInstruction::createDefCfaRegister(
+              nullptr, MBBInfo.IncomingCFARegister));
+      BuildMI(*MBBInfo.MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
+          .addCFIIndex(CFIIndex);
+      InsertedCFIInstr = true;
+    }
+    PrevMBBInfo = &MBBInfo;
+  }
+  return InsertedCFIInstr;
+}
+
+void CFIInstrInserter::report(const char *msg, MachineBasicBlock &MBB) {
+  errs() << '\n';
+  errs() << "*** " << msg << " ***\n"
+         << "- function:    " << MBB.getParent()->getName() << "\n";
+  errs() << "- basic block: BB#" << MBB.getNumber() << ' ' << MBB.getName()
+         << " (" << (const void *)&MBB << ')';
+  errs() << '\n';
+}
+
+unsigned CFIInstrInserter::verify(MachineFunction &MF) {
+  unsigned ErrorNum = 0;
+  for (MachineBasicBlock &CurrMBB : MF) {
+    const struct MBBCFAInfo& CurrMBBInfo = MBBVector[CurrMBB.getNumber()];
+    for (MachineBasicBlock *Pred : CurrMBB.predecessors()) {
+      const struct MBBCFAInfo& PredMBBInfo = MBBVector[Pred->getNumber()];
+      // Check that outgoing offset values of predecessors match the incoming
+      // offset value of CurrMBB
+      if (PredMBBInfo.OutgoingCFAOffset != CurrMBBInfo.IncomingCFAOffset) {
+        report("The outgoing offset of a predecessor is inconsistent.",
+               CurrMBB);
+        errs() << "Predecessor BB#" << Pred->getNumber()
+               << " has outgoing offset (" << PredMBBInfo.OutgoingCFAOffset
+               << "), while BB#" << CurrMBB.getNumber()
+               << " has incoming offset (" << CurrMBBInfo.IncomingCFAOffset
+               << ").\n";
+        ErrorNum++;
+      }
+      // Check that outgoing register values of predecessors match the incoming
+      // register value of CurrMBB
+      if (PredMBBInfo.OutgoingCFARegister != CurrMBBInfo.IncomingCFARegister) {
+        report("The outgoing register of a predecessor is inconsistent.",
+               CurrMBB);
+        errs() << "Predecessor BB#" << Pred->getNumber()
+               << " has outgoing register (" << PredMBBInfo.OutgoingCFARegister
+               << "), while BB#" << CurrMBB.getNumber()
+               << " has incoming register (" << CurrMBBInfo.IncomingCFARegister
+               << ").\n";
+        ErrorNum++;
+      }
+    }
+
+    for (MachineBasicBlock *Succ : CurrMBB.successors()) {
+      const struct MBBCFAInfo& SuccMBBInfo = MBBVector[Succ->getNumber()];
+      // Check that incoming offset values of successors match the outgoing
+      // offset value of CurrMBB
+      if (SuccMBBInfo.IncomingCFAOffset != CurrMBBInfo.OutgoingCFAOffset) {
+        report("The incoming offset of a successor is inconsistent.", CurrMBB);
+        errs() << "Successor BB#" << Succ->getNumber()
+               << " has incoming offset (" << SuccMBBInfo.IncomingCFAOffset
+               << "), while BB#" << CurrMBB.getNumber()
+               << " has outgoing offset (" << CurrMBBInfo.OutgoingCFAOffset
+               << ").\n";
+        ErrorNum++;
+      }
+      // Check that incoming register values of successors match the outgoing
+      // register value of CurrMBB
+      if (SuccMBBInfo.IncomingCFARegister != CurrMBBInfo.OutgoingCFARegister) {
+        report("The incoming register of a successor is inconsistent.",
+               CurrMBB);
+        errs() << "Successor BB#" << Succ->getNumber()
+               << " has incoming register (" << SuccMBBInfo.IncomingCFARegister
+               << "), while BB#" << CurrMBB.getNumber()
+               << " has outgoing register (" << CurrMBBInfo.OutgoingCFARegister
+               << ").\n";
+        ErrorNum++;
+      }
+    }
+  }
+  return ErrorNum;
+}

lib/CodeGen/CMakeLists.txt

@@ -9,6 +9,7 @@ add_llvm_library(LLVMCodeGen
   BuiltinGCs.cpp
   CalcSpillWeights.cpp
   CallingConvLower.cpp
+  CFIInstrInserter.cpp
   CodeGen.cpp
   CodeGenPrepare.cpp
   CountingFunctionInserter.cpp

lib/CodeGen/CodeGen.cpp

@@ -23,6 +23,7 @@ void llvm::initializeCodeGen(PassRegistry &Registry) {
   initializeAtomicExpandPass(Registry);
   initializeBranchFolderPassPass(Registry);
   initializeBranchRelaxationPass(Registry);
+  initializeCFIInstrInserterPass(Registry);
   initializeCodeGenPreparePass(Registry);
   initializeCountingFunctionInserterPass(Registry);
   initializeDeadMachineInstructionElimPass(Registry);

lib/CodeGen/MachineInstr.cpp

@@ -320,8 +320,45 @@ bool MachineOperand::isIdenticalTo(const MachineOperand &Other) const {
   }
   case MachineOperand::MO_MCSymbol:
     return getMCSymbol() == Other.getMCSymbol();
-  case MachineOperand::MO_CFIIndex:
-    return getCFIIndex() == Other.getCFIIndex();
+  case MachineOperand::MO_CFIIndex: {
+    const MachineFunction *MF = getParent()->getParent()->getParent();
+    const MachineFunction *OtherMF =
+        Other.getParent()->getParent()->getParent();
+    MCCFIInstruction Inst = MF->getFrameInstructions()[getCFIIndex()];
+    MCCFIInstruction OtherInst =
+        OtherMF->getFrameInstructions()[Other.getCFIIndex()];
+    MCCFIInstruction::OpType op = Inst.getOperation();
+    if (op != OtherInst.getOperation()) return false;
+    switch (op) {
+    case MCCFIInstruction::OpDefCfa:
+    case MCCFIInstruction::OpOffset:
+    case MCCFIInstruction::OpRelOffset:
+      if (Inst.getRegister() != OtherInst.getRegister()) return false;
+      if (Inst.getOffset() != OtherInst.getOffset()) return false;
+      break;
+    case MCCFIInstruction::OpRestore:
+    case MCCFIInstruction::OpUndefined:
+    case MCCFIInstruction::OpSameValue:
+    case MCCFIInstruction::OpDefCfaRegister:
+      if (Inst.getRegister() != OtherInst.getRegister()) return false;
+      break;
+    case MCCFIInstruction::OpRegister:
+      if (Inst.getRegister() != OtherInst.getRegister()) return false;
+      if (Inst.getRegister2() != OtherInst.getRegister2()) return false;
+      break;
+    case MCCFIInstruction::OpDefCfaOffset:
+    case MCCFIInstruction::OpAdjustCfaOffset:
+    case MCCFIInstruction::OpGnuArgsSize:
+      if (Inst.getOffset() != OtherInst.getOffset()) return false;
+      break;
+    case MCCFIInstruction::OpRememberState:
+    case MCCFIInstruction::OpRestoreState:
+    case MCCFIInstruction::OpEscape:
+    case MCCFIInstruction::OpWindowSave:
+      break;
+    }
+    return true;
+  }
   case MachineOperand::MO_Metadata:
     return getMetadata() == Other.getMetadata();
   case MachineOperand::MO_IntrinsicID:
@@ -370,8 +407,13 @@ hash_code llvm::hash_value(const MachineOperand &MO) {
     return hash_combine(MO.getType(), MO.getTargetFlags(), MO.getMetadata());
   case MachineOperand::MO_MCSymbol:
     return hash_combine(MO.getType(), MO.getTargetFlags(), MO.getMCSymbol());
-  case MachineOperand::MO_CFIIndex:
-    return hash_combine(MO.getType(), MO.getTargetFlags(), MO.getCFIIndex());
+  case MachineOperand::MO_CFIIndex: {
+    const MachineFunction *MF = MO.getParent()->getParent()->getParent();
+    MCCFIInstruction Inst = MF->getFrameInstructions()[MO.getCFIIndex()];
+    return hash_combine(MO.getType(), MO.getTargetFlags(), Inst.getOperation(),
+                        Inst.getRegister(), Inst.getRegister2(),
+                        Inst.getOffset());
+  }
   case MachineOperand::MO_IntrinsicID:
     return hash_combine(MO.getType(), MO.getTargetFlags(), MO.getIntrinsicID());
   case MachineOperand::MO_Predicate:

lib/CodeGen/TailDuplicator.cpp

@@ -603,8 +603,8 @@ bool TailDuplicator::shouldTailDuplicate(bool IsSimple,
     if (PreRegAlloc && MI.isCall())
       return false;
 
-    if (!MI.isPHI() && !MI.isDebugValue())
-      InstrCount += 1;
+    if (!MI.isPHI() && !MI.isMetaInstruction())
+        InstrCount += 1;
 
     if (InstrCount > MaxDuplicateCount)
       return false;

lib/CodeGen/TargetFrameLoweringImpl.cpp

@@ -104,3 +104,12 @@ unsigned TargetFrameLowering::getStackAlignmentSkew(
 
   return 0;
 }
+
+int TargetFrameLowering::getInitialCFAOffset(const MachineFunction &MF) const {
+  llvm_unreachable("getInitialCFAOffset() not implemented!");
+}
+
+unsigned TargetFrameLowering::getInitialCFARegister(const MachineFunction &MF)
+    const {
+  llvm_unreachable("getInitialCFARegister() not implemented!");
+}

lib/Target/X86/X86FrameLowering.cpp

@@ -1562,6 +1562,11 @@ void X86FrameLowering::emitEpilogue(MachineFunction &MF,
   bool HasFP = hasFP(MF);
   uint64_t NumBytes = 0;
 
+  bool NeedsDwarfCFI =
+      (!MF.getTarget().getTargetTriple().isOSDarwin() &&
+       !MF.getTarget().getTargetTriple().isOSWindows()) &&
+      (MF.getMMI().hasDebugInfo() || MF.getFunction()->needsUnwindTableEntry());
+
   if (IsFunclet) {
     assert(HasFP && "EH funclets without FP not yet implemented");
     NumBytes = getWinEHFuncletFrameSize(MF);
@@ -1584,6 +1589,13 @@ void X86FrameLowering::emitEpilogue(MachineFunction &MF,
     BuildMI(MBB, MBBI, DL, TII.get(Is64Bit ? X86::POP64r : X86::POP32r),
             MachineFramePtr)
         .setMIFlag(MachineInstr::FrameDestroy);
+    if (NeedsDwarfCFI) {
+      unsigned DwarfStackPtr =
+          TRI->getDwarfRegNum(Is64Bit ? X86::RSP : X86::ESP, true);
+      BuildCFI(MBB, MBBI, DL, MCCFIInstruction::createDefCfa(
+                                  nullptr, DwarfStackPtr, -SlotSize));
+      --MBBI;
+    }
   }
 
   MachineBasicBlock::iterator FirstCSPop = MBBI;
@@ -1647,6 +1659,11 @@ void X86FrameLowering::emitEpilogue(MachineFunction &MF,
   } else if (NumBytes) {
     // Adjust stack pointer back: ESP += numbytes.
     emitSPUpdate(MBB, MBBI, NumBytes, /*InEpilogue=*/true);
+    if (!hasFP(MF) && NeedsDwarfCFI) {
+      // Define the current CFA rule to use the provided offset.
+      BuildCFI(MBB, MBBI, DL, MCCFIInstruction::createDefCfaOffset(
+                                  nullptr, -CSSize - SlotSize));
+    }
     --MBBI;
   }
 
@@ -1659,6 +1676,23 @@ void X86FrameLowering::emitEpilogue(MachineFunction &MF,
   if (NeedsWin64CFI && MF.hasWinCFI())
     BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_Epilogue));
 
+  if (!hasFP(MF) && NeedsDwarfCFI) {
+    MBBI = FirstCSPop;
+    int64_t Offset = -CSSize - SlotSize;
+    // Mark callee-saved pop instruction.
+    // Define the current CFA rule to use the provided offset.
+    while (MBBI != MBB.end()) {
+      MachineBasicBlock::iterator PI = MBBI;
+      unsigned Opc = PI->getOpcode();
+      ++MBBI;
+      if (Opc == X86::POP32r || Opc == X86::POP64r) {
+        Offset += SlotSize;
+        BuildCFI(MBB, MBBI, DL,
+                 MCCFIInstruction::createDefCfaOffset(nullptr, Offset));
+      }
+    }
+  }
+
   if (Terminator == MBB.end() || !isTailCallOpcode(Terminator->getOpcode())) {
     // Add the return addr area delta back since we are not tail calling.
     int Offset = -1 * X86FI->getTCReturnAddrDelta();
@@ -2835,6 +2869,15 @@ MachineBasicBlock::iterator X86FrameLowering::restoreWin32EHStackPointers(
   return MBBI;
 }
 
+int X86FrameLowering::getInitialCFAOffset(const MachineFunction &MF) const {
+  return TRI->getSlotSize();
+}
+
+unsigned X86FrameLowering::getInitialCFARegister(const MachineFunction &MF)
+    const {
+  return TRI->getDwarfRegNum(StackPtr, true);
+}
+
 namespace {
 // Struct used by orderFrameObjects to help sort the stack objects.
 struct X86FrameSortingObject {

lib/Target/X86/X86FrameLowering.h

@@ -168,6 +168,10 @@ public:
                               MachineBasicBlock::iterator MBBI,
                               const DebugLoc &DL, bool RestoreSP = false) const;
 
+  int getInitialCFAOffset(const MachineFunction &MF) const override;
+
+  unsigned getInitialCFARegister(const MachineFunction &MF) const override;
+
 private:
   uint64_t calculateMaxStackAlign(const MachineFunction &MF) const;
 

lib/Target/X86/X86TargetMachine.cpp

@@ -436,4 +436,11 @@ void X86PassConfig::addPreEmitPass() {
     addPass(createX86FixupLEAs());
     addPass(createX86EvexToVexInsts());
   }
+
+  // Verify basic block incoming and outgoing cfa offset and register values and
+  // correct CFA calculation rule where needed by inserting appropriate CFI
+  // instructions.
+  const Triple &TT = TM->getTargetTriple();
+  if (!TT.isOSDarwin() && !TT.isOSWindows())
+    addPass(createCFIInstrInserter());
 }

test/CodeGen/X86/2009-03-16-PHIElimInLPad.ll

@@ -23,6 +23,7 @@ lpad:		; preds = %cont, %entry
 }
 
 ; CHECK: lpad
+; CHECK-NEXT: .cfi_def_cfa_offset 16
 ; CHECK-NEXT: Ltmp
 
 declare i32 @__gxx_personality_v0(...)

test/CodeGen/X86/2011-10-19-widen_vselect.ll

@@ -88,6 +88,7 @@ define void @full_test() {
 ; X32-NEXT:    movss %xmm4, {{[0-9]+}}(%esp)
 ; X32-NEXT:    movss %xmm0, {{[0-9]+}}(%esp)
 ; X32-NEXT:    addl $60, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: full_test:

test/CodeGen/X86/GlobalISel/add-scalar.ll

@@ -20,6 +20,7 @@ define i64 @test_add_i64(i64 %arg1, i64 %arg2) {
 ; X32-NEXT:    addl 8(%ebp), %eax
 ; X32-NEXT:    adcl 12(%ebp), %edx
 ; X32-NEXT:    popl %ebp
+; X32-NEXT:    .cfi_def_cfa %esp, 4
 ; X32-NEXT:    retl
   %ret = add i64 %arg1, %arg2
   ret i64 %ret

test/CodeGen/X86/GlobalISel/brcond.ll

@@ -36,6 +36,7 @@ define i32 @test_1(i32 %a, i32 %b, i32 %tValue, i32 %fValue) {
 ; X32-NEXT:    movl %eax, (%esp)
 ; X32-NEXT:    movl (%esp), %eax
 ; X32-NEXT:    popl %ecx
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 entry:
   %retval = alloca i32, align 4

test/CodeGen/X86/GlobalISel/callingconv.ll

@@ -117,6 +117,7 @@ define <8 x i32> @test_v8i32_args(<8 x i32> %arg1, <8 x i32> %arg2) {
 ; X32-NEXT:    movups 16(%esp), %xmm1
 ; X32-NEXT:    movaps %xmm2, %xmm0
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_v8i32_args:
@@ -135,6 +136,7 @@ define void @test_trivial_call() {
 ; X32-NEXT:    .cfi_def_cfa_offset 16
 ; X32-NEXT:    calll trivial_callee
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_trivial_call:
@@ -143,6 +145,7 @@ define void @test_trivial_call() {
 ; X64-NEXT:    .cfi_def_cfa_offset 16
 ; X64-NEXT:    callq trivial_callee
 ; X64-NEXT:    popq %rax
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
   call void @trivial_callee()
   ret void
@@ -160,6 +163,7 @@ define void @test_simple_arg_call(i32 %in0, i32 %in1) {
 ; X32-NEXT:    movl %eax, 4(%esp)
 ; X32-NEXT:    calll simple_arg_callee
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_simple_arg_call:
@@ -171,6 +175,7 @@ define void @test_simple_arg_call(i32 %in0, i32 %in1) {
 ; X64-NEXT:    movl %eax, %esi
 ; X64-NEXT:    callq simple_arg_callee
 ; X64-NEXT:    popq %rax
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
   call void @simple_arg_callee(i32 %in1, i32 %in0)
   ret void
@@ -193,6 +198,7 @@ define void @test_simple_arg8_call(i32 %in0) {
 ; X32-NEXT:    movl %eax, 28(%esp)
 ; X32-NEXT:    calll simple_arg8_callee
 ; X32-NEXT:    addl $44, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_simple_arg8_call:
@@ -208,6 +214,7 @@ define void @test_simple_arg8_call(i32 %in0) {
 ; X64-NEXT:    movl %edi, %r9d
 ; X64-NEXT:    callq simple_arg8_callee
 ; X64-NEXT:    addq $24, %rsp
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
   call void @simple_arg8_callee(i32 %in0, i32 %in0, i32 %in0, i32 %in0,i32 %in0, i32 %in0, i32 %in0, i32 %in0)
   ret void
@@ -224,6 +231,7 @@ define i32 @test_simple_return_callee() {
 ; X32-NEXT:    calll simple_return_callee
 ; X32-NEXT:    addl %eax, %eax
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_simple_return_callee:
@@ -234,6 +242,7 @@ define i32 @test_simple_return_callee() {
 ; X64-NEXT:    callq simple_return_callee
 ; X64-NEXT:    addl %eax, %eax
 ; X64-NEXT:    popq %rcx
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
   %call = call i32 @simple_return_callee(i32 5)
   %r = add i32 %call, %call
@@ -254,6 +263,7 @@ define <8 x i32> @test_split_return_callee(<8 x i32> %arg1, <8 x i32> %arg2) {
 ; X32-NEXT:    paddd (%esp), %xmm0 # 16-byte Folded Reload
 ; X32-NEXT:    paddd 16(%esp), %xmm1 # 16-byte Folded Reload
 ; X32-NEXT:    addl $44, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_split_return_callee:
@@ -268,6 +278,7 @@ define <8 x i32> @test_split_return_callee(<8 x i32> %arg1, <8 x i32> %arg2) {
 ; X64-NEXT:    paddd (%rsp), %xmm0 # 16-byte Folded Reload
 ; X64-NEXT:    paddd 16(%rsp), %xmm1 # 16-byte Folded Reload
 ; X64-NEXT:    addq $40, %rsp
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
   %call = call <8 x i32> @split_return_callee(<8 x i32> %arg2)
   %r = add <8 x i32> %arg1, %call
@@ -281,6 +292,7 @@ define void @test_indirect_call(void()* %func) {
 ; X32-NEXT:    .cfi_def_cfa_offset 16
 ; X32-NEXT:    calll *16(%esp)
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_indirect_call:
@@ -289,6 +301,7 @@ define void @test_indirect_call(void()* %func) {
 ; X64-NEXT:    .cfi_def_cfa_offset 16
 ; X64-NEXT:    callq *%rdi
 ; X64-NEXT:    popq %rax
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
   call void %func()
   ret void
@@ -317,8 +330,11 @@ define void @test_abi_exts_call(i8* %addr) {
 ; X32-NEXT:    movl %esi, (%esp)
 ; X32-NEXT:    calll take_char
 ; X32-NEXT:    addl $4, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 12
 ; X32-NEXT:    popl %esi
+; X32-NEXT:    .cfi_def_cfa_offset 8
 ; X32-NEXT:    popl %ebx
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_abi_exts_call:
@@ -335,6 +351,7 @@ define void @test_abi_exts_call(i8* %addr) {
 ; X64-NEXT:    movl %ebx, %edi
 ; X64-NEXT:    callq take_char
 ; X64-NEXT:    popq %rbx
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
   %val = load i8, i8* %addr
   call void @take_char(i8 %val)
@@ -357,6 +374,7 @@ define void @test_variadic_call_1(i8** %addr_ptr, i32* %val_ptr) {
 ; X32-NEXT:    movl %ecx, 4(%esp)
 ; X32-NEXT:    calll variadic_callee
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_variadic_call_1:
@@ -368,6 +386,7 @@ define void @test_variadic_call_1(i8** %addr_ptr, i32* %val_ptr) {
 ; X64-NEXT:    movb $0, %al
 ; X64-NEXT:    callq variadic_callee
 ; X64-NEXT:    popq %rax
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
 
   %addr = load i8*, i8** %addr_ptr
@@ -393,6 +412,7 @@ define void @test_variadic_call_2(i8** %addr_ptr, double* %val_ptr) {
 ; X32-NEXT:    movl %ecx, 4(%eax)
 ; X32-NEXT:    calll variadic_callee
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_variadic_call_2:
@@ -405,6 +425,7 @@ define void @test_variadic_call_2(i8** %addr_ptr, double* %val_ptr) {
 ; X64-NEXT:    movq %rcx, %xmm0
 ; X64-NEXT:    callq variadic_callee
 ; X64-NEXT:    popq %rax
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
 
   %addr = load i8*, i8** %addr_ptr

test/CodeGen/X86/GlobalISel/frameIndex.ll

@@ -18,6 +18,7 @@ define i32* @allocai32() {
 ; X32-NEXT:    .cfi_def_cfa_offset 8
 ; X32-NEXT:    movl %esp, %eax
 ; X32-NEXT:    popl %ecx
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X32ABI-LABEL: allocai32:

test/CodeGen/X86/O0-pipeline.ll

@@ -49,6 +49,7 @@
 ; CHECK-NEXT:       X86 pseudo instruction expansion pass
 ; CHECK-NEXT:       Analyze Machine Code For Garbage Collection
 ; CHECK-NEXT:       X86 vzeroupper inserter
+; CHECK-NEXT:       Check CFA info and insert CFI instructions if needed
 ; CHECK-NEXT:       Contiguously Lay Out Funclets
 ; CHECK-NEXT:       StackMap Liveness Analysis
 ; CHECK-NEXT:       Live DEBUG_VALUE analysis

test/CodeGen/X86/TruncAssertZext.ll

@@ -25,6 +25,7 @@ define i64 @main() {
 ; CHECK-NEXT:    subq %rcx, %rax
 ; CHECK-NEXT:    shrq $32, %rax
 ; CHECK-NEXT:    popq %rcx
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
   %b = call i64 @foo()
   %or = and i64 %b, 18446744069414584575 ; this is 0xffffffff000000ff

test/CodeGen/X86/avx512-mask-op.ll

@@ -699,11 +699,13 @@ define <16 x i8> @test8(<16 x i32>%a, <16 x i32>%b, i32 %a1, i32 %b1) {
 ; AVX512BW-NEXT:    jg LBB17_1
 ; AVX512BW-NEXT:  ## BB#2:
 ; AVX512BW-NEXT:    vpcmpltud %zmm2, %zmm1, %k0
-; AVX512BW-NEXT:    jmp LBB17_3
+; AVX512BW-NEXT:    vpmovm2b	%k0, %zmm0
+; AVX512BW-NEXT:    ## kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
 ; AVX512BW-NEXT:  LBB17_1:
-; AVX512BW-NEXT:    vpcmpgtd %zmm2, %zmm0, %k0
-; AVX512BW-NEXT:  LBB17_3:
-; AVX512BW-NEXT:    vpmovm2b %k0, %zmm0
+; AVX512BW-NEXT:    vpcmpgtd	%zmm2, %zmm0, %k0
+; AVX512BW-NEXT:    vpmovm2b	%k0, %zmm0
 ; AVX512BW-NEXT:    ## kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
 ; AVX512BW-NEXT:    vzeroupper
 ; AVX512BW-NEXT:    retq

test/CodeGen/X86/avx512-regcall-Mask.ll

@@ -209,12 +209,18 @@ define i64 @caller_argv64i1() #0 {
 ; LINUXOSX64-NEXT:    pushq %rax
 ; LINUXOSX64-NEXT:    .cfi_adjust_cfa_offset 8
 ; LINUXOSX64-NEXT:    callq test_argv64i1
-; LINUXOSX64-NEXT:    addq $24, %rsp
+; LINUXOSX64-NEXT:    addq $16, %rsp
 ; LINUXOSX64-NEXT:    .cfi_adjust_cfa_offset -16
+; LINUXOSX64-NEXT:    addq	$8, %rsp
+; LINUXOSX64-NEXT:    .cfi_def_cfa_offset 40
 ; LINUXOSX64-NEXT:    popq %r12
+; LINUXOSX64-NEXT:    .cfi_def_cfa_offset 32
 ; LINUXOSX64-NEXT:    popq %r13
+; LINUXOSX64-NEXT:    .cfi_def_cfa_offset 24
 ; LINUXOSX64-NEXT:    popq %r14
+; LINUXOSX64-NEXT:    .cfi_def_cfa_offset 16
 ; LINUXOSX64-NEXT:    popq %r15
+; LINUXOSX64-NEXT:    .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
 entry:
   %v0 = bitcast i64 4294967298 to <64 x i1>
@@ -287,6 +293,7 @@ define <64 x i1> @caller_retv64i1() #0 {
 ; LINUXOSX64-NEXT:    kmovq %rax, %k0
 ; LINUXOSX64-NEXT:    vpmovm2b %k0, %zmm0
 ; LINUXOSX64-NEXT:    popq %rax
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
 entry:
   %call = call x86_regcallcc <64 x i1> @test_retv64i1()
@@ -397,7 +404,9 @@ define x86_regcallcc i32 @test_argv32i1(<32 x i1> %x0, <32 x i1> %x1, <32 x i1>
 ; LINUXOSX64-NEXT:    vmovaps {{[0-9]+}}(%rsp), %xmm14 # 16-byte Reload
 ; LINUXOSX64-NEXT:    vmovaps {{[0-9]+}}(%rsp), %xmm15 # 16-byte Reload
 ; LINUXOSX64-NEXT:    addq $128, %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 16
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    vzeroupper
 ; LINUXOSX64-NEXT:    retq
 entry:
@@ -451,6 +460,7 @@ define i32 @caller_argv32i1() #0 {
 ; LINUXOSX64-NEXT:    movl $1, %edx
 ; LINUXOSX64-NEXT:    callq test_argv32i1
 ; LINUXOSX64-NEXT:    popq %rcx
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
 entry:
   %v0 = bitcast i32 1 to <32 x i1>
@@ -513,6 +523,7 @@ define i32 @caller_retv32i1() #0 {
 ; LINUXOSX64-NEXT:    callq test_retv32i1
 ; LINUXOSX64-NEXT:    incl %eax
 ; LINUXOSX64-NEXT:    popq %rcx
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
 entry:
   %call = call x86_regcallcc <32 x i1> @test_retv32i1()
@@ -626,7 +637,9 @@ define x86_regcallcc i16 @test_argv16i1(<16 x i1> %x0, <16 x i1> %x1, <16 x i1>
 ; LINUXOSX64-NEXT:    vmovaps {{[0-9]+}}(%rsp), %xmm14 # 16-byte Reload
 ; LINUXOSX64-NEXT:    vmovaps {{[0-9]+}}(%rsp), %xmm15 # 16-byte Reload
 ; LINUXOSX64-NEXT:    addq $128, %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 16
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %res = call i16 @test_argv16i1helper(<16 x i1> %x0, <16 x i1> %x1, <16 x i1> %x2)
   ret i16 %res
@@ -678,6 +691,7 @@ define i16 @caller_argv16i1() #0 {
 ; LINUXOSX64-NEXT:    movl $1, %edx
 ; LINUXOSX64-NEXT:    callq test_argv16i1
 ; LINUXOSX64-NEXT:    popq %rcx
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
 entry:
   %v0 = bitcast i16 1 to <16 x i1>
@@ -746,6 +760,7 @@ define i16 @caller_retv16i1() #0 {
 ; LINUXOSX64-NEXT:    incl %eax
 ; LINUXOSX64-NEXT:    # kill: %AX<def> %AX<kill> %EAX<kill>
 ; LINUXOSX64-NEXT:    popq %rcx
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
 entry:
   %call = call x86_regcallcc <16 x i1> @test_retv16i1()
@@ -859,7 +874,9 @@ define x86_regcallcc i8 @test_argv8i1(<8 x i1> %x0, <8 x i1> %x1, <8 x i1> %x2)
 ; LINUXOSX64-NEXT:    vmovaps {{[0-9]+}}(%rsp), %xmm14 # 16-byte Reload
 ; LINUXOSX64-NEXT:    vmovaps {{[0-9]+}}(%rsp), %xmm15 # 16-byte Reload
 ; LINUXOSX64-NEXT:    addq $128, %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 16
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %res = call i8 @test_argv8i1helper(<8 x i1> %x0, <8 x i1> %x1, <8 x i1> %x2)
   ret i8 %res
@@ -911,6 +928,7 @@ define i8 @caller_argv8i1() #0 {
 ; LINUXOSX64-NEXT:    movl $1, %edx
 ; LINUXOSX64-NEXT:    callq test_argv8i1
 ; LINUXOSX64-NEXT:    popq %rcx
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
 entry:
   %v0 = bitcast i8 1 to <8 x i1>
@@ -984,9 +1002,11 @@ define <8 x i1> @caller_retv8i1() #0 {
 ; LINUXOSX64-NEXT:    vpmovm2w %k0, %zmm0
 ; LINUXOSX64-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
 ; LINUXOSX64-NEXT:    popq %rax
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    vzeroupper
 ; LINUXOSX64-NEXT:    retq
 entry:
   %call = call x86_regcallcc <8 x i1> @test_retv8i1()
   ret <8 x i1> %call
 }
+

test/CodeGen/X86/avx512-regcall-NoMask.ll

@@ -63,6 +63,7 @@ define x86_regcallcc i1 @test_CallargReti1(i1 %a)  {
 ; LINUXOSX64-NEXT:    callq test_argReti1
 ; LINUXOSX64-NEXT:    incb %al
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = add i1 %a, 1
   %c = call x86_regcallcc i1 @test_argReti1(i1 %b)
@@ -130,6 +131,7 @@ define x86_regcallcc i8 @test_CallargReti8(i8 %a)  {
 ; LINUXOSX64-NEXT:    callq test_argReti8
 ; LINUXOSX64-NEXT:    incb %al
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = add i8 %a, 1
   %c = call x86_regcallcc i8 @test_argReti8(i8 %b)
@@ -200,6 +202,7 @@ define x86_regcallcc i16 @test_CallargReti16(i16 %a)  {
 ; LINUXOSX64-NEXT:    incl %eax
 ; LINUXOSX64-NEXT:    # kill: %AX<def> %AX<kill> %EAX<kill>
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = add i16 %a, 1
   %c = call x86_regcallcc i16 @test_argReti16(i16 %b)
@@ -261,6 +264,7 @@ define x86_regcallcc i32 @test_CallargReti32(i32 %a)  {
 ; LINUXOSX64-NEXT:    callq test_argReti32
 ; LINUXOSX64-NEXT:    incl %eax
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = add i32 %a, 1
   %c = call x86_regcallcc i32 @test_argReti32(i32 %b)
@@ -327,6 +331,7 @@ define x86_regcallcc i64 @test_CallargReti64(i64 %a)  {
 ; LINUXOSX64-NEXT:    callq test_argReti64
 ; LINUXOSX64-NEXT:    incq %rax
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = add i64 %a, 1
   %c = call x86_regcallcc i64 @test_argReti64(i64 %b)
@@ -406,7 +411,9 @@ define x86_regcallcc float @test_CallargRetFloat(float %a)  {
 ; LINUXOSX64-NEXT:    vaddss %xmm8, %xmm0, %xmm0
 ; LINUXOSX64-NEXT:    vmovaps (%rsp), %xmm8 # 16-byte Reload
 ; LINUXOSX64-NEXT:    addq $16, %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 16
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = fadd float 1.0, %a
   %c = call x86_regcallcc float @test_argRetFloat(float %b)
@@ -486,7 +493,9 @@ define x86_regcallcc double @test_CallargRetDouble(double %a)  {
 ; LINUXOSX64-NEXT:    vaddsd %xmm8, %xmm0, %xmm0
 ; LINUXOSX64-NEXT:    vmovaps (%rsp), %xmm8 # 16-byte Reload
 ; LINUXOSX64-NEXT:    addq $16, %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 16
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = fadd double 1.0, %a
   %c = call x86_regcallcc double @test_argRetDouble(double %b)
@@ -548,6 +557,7 @@ define x86_regcallcc x86_fp80 @test_CallargRetf80(x86_fp80 %a)  {
 ; LINUXOSX64-NEXT:    callq test_argRetf80
 ; LINUXOSX64-NEXT:    fadd %st(0), %st(0)
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = fadd x86_fp80 %a, %a
   %c = call x86_regcallcc x86_fp80 @test_argRetf80(x86_fp80 %b)
@@ -611,6 +621,7 @@ define x86_regcallcc [4 x i32]* @test_CallargRetPointer([4 x i32]* %a)  {
 ; LINUXOSX64-NEXT:    callq test_argRetPointer
 ; LINUXOSX64-NEXT:    incl %eax
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = ptrtoint [4 x i32]* %a to i32
   %c = add i32 %b, 1
@@ -694,7 +705,9 @@ define x86_regcallcc <4 x i32> @test_CallargRet128Vector(<4 x i32> %a)  {
 ; LINUXOSX64-NEXT:    vmovdqa32 %xmm8, %xmm0 {%k1}
 ; LINUXOSX64-NEXT:    vmovaps (%rsp), %xmm8 # 16-byte Reload
 ; LINUXOSX64-NEXT:    addq $16, %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 16
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = call x86_regcallcc <4 x i32> @test_argRet128Vector(<4 x i32> %a, <4 x i32> %a)
   %c = select <4 x i1> undef , <4 x i32> %a, <4 x i32> %b
@@ -768,7 +781,9 @@ define x86_regcallcc <8 x i32> @test_CallargRet256Vector(<8 x i32> %a)  {
 ; LINUXOSX64-NEXT:    vmovdqu (%rsp), %ymm1 # 32-byte Reload
 ; LINUXOSX64-NEXT:    vmovdqa32 %ymm1, %ymm0 {%k1}
 ; LINUXOSX64-NEXT:    addq $48, %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 16
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = call x86_regcallcc <8 x i32> @test_argRet256Vector(<8 x i32> %a, <8 x i32> %a)
   %c = select <8 x i1> undef , <8 x i32> %a, <8 x i32> %b
@@ -842,7 +857,9 @@ define x86_regcallcc <16 x i32> @test_CallargRet512Vector(<16 x i32> %a)  {
 ; LINUXOSX64-NEXT:    vmovdqu64 (%rsp), %zmm1 # 64-byte Reload
 ; LINUXOSX64-NEXT:    vmovdqa32 %zmm1, %zmm0 {%k1}
 ; LINUXOSX64-NEXT:    addq $112, %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 16
 ; LINUXOSX64-NEXT:    popq %rsp
+; LINUXOSX64-NEXT:   .cfi_def_cfa_offset 8
 ; LINUXOSX64-NEXT:    retq
   %b = call x86_regcallcc <16 x i32> @test_argRet512Vector(<16 x i32> %a, <16 x i32> %a)
   %c = select <16 x i1> undef , <16 x i32> %a, <16 x i32> %b

test/CodeGen/X86/avx512-schedule.ll

@@ -8839,6 +8839,7 @@ define <16 x float> @broadcast_ss_spill(float %x) {
 ; GENERIC-NEXT:    callq func_f32
 ; GENERIC-NEXT:    vbroadcastss (%rsp), %zmm0 # 16-byte Folded Reload
 ; GENERIC-NEXT:    addq $24, %rsp # sched: [1:0.33]
+; GENERIC-NEXT:    .cfi_def_cfa_offset 8
 ; GENERIC-NEXT:    retq # sched: [1:1.00]
 ;
 ; SKX-LABEL: broadcast_ss_spill:
@@ -8852,6 +8853,7 @@ define <16 x float> @broadcast_ss_spill(float %x) {
 ; SKX-NEXT:    vbroadcastss (%rsp), %zmm0 # 16-byte Folded Reload sched: [8:0.50]
 ; SKX-NEXT:    # sched: [8:0.50]
 ; SKX-NEXT:    addq $24, %rsp # sched: [1:0.25]
+; SKX-NEXT:    .cfi_def_cfa_offset 8
 ; SKX-NEXT:    retq # sched: [7:1.00]
   %a  = fadd float %x, %x
   call void @func_f32(float %a)
@@ -8872,6 +8874,7 @@ define <8 x double> @broadcast_sd_spill(double %x) {
 ; GENERIC-NEXT:    callq func_f64
 ; GENERIC-NEXT:    vbroadcastsd (%rsp), %zmm0 # 16-byte Folded Reload
 ; GENERIC-NEXT:    addq $24, %rsp # sched: [1:0.33]
+; GENERIC-NEXT:    .cfi_def_cfa_offset 8
 ; GENERIC-NEXT:    retq # sched: [1:1.00]
 ;
 ; SKX-LABEL: broadcast_sd_spill:
@@ -8885,6 +8888,7 @@ define <8 x double> @broadcast_sd_spill(double %x) {
 ; SKX-NEXT:    vbroadcastsd (%rsp), %zmm0 # 16-byte Folded Reload sched: [8:0.50]
 ; SKX-NEXT:    # sched: [8:0.50]
 ; SKX-NEXT:    addq $24, %rsp # sched: [1:0.25]
+; SKX-NEXT:    .cfi_def_cfa_offset 8
 ; SKX-NEXT:    retq # sched: [7:1.00]
   %a  = fadd double %x, %x
   call void @func_f64(double %a)

test/CodeGen/X86/avx512-select.ll

@@ -115,6 +115,7 @@ define <16 x double> @select04(<16 x double> %a, <16 x double> %b) {
 ; X86-NEXT:    vmovaps 8(%ebp), %zmm1
 ; X86-NEXT:    movl %ebp, %esp
 ; X86-NEXT:    popl %ebp
+; X86-NEXT:    	.cfi_def_cfa %esp, 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: select04:

test/CodeGen/X86/avx512-vbroadcast.ll

@@ -413,6 +413,7 @@ define <16 x float> @broadcast_ss_spill(float %x) {
 ; ALL-NEXT:    callq func_f32
 ; ALL-NEXT:    vbroadcastss (%rsp), %zmm0 # 16-byte Folded Reload
 ; ALL-NEXT:    addq $24, %rsp
+; ALL-NEXT:   .cfi_def_cfa_offset 8
 ; ALL-NEXT:    retq
   %a  = fadd float %x, %x
   call void @func_f32(float %a)
@@ -432,6 +433,7 @@ define <8 x double> @broadcast_sd_spill(double %x) {
 ; ALL-NEXT:    callq func_f64
 ; ALL-NEXT:    vbroadcastsd (%rsp), %zmm0 # 16-byte Folded Reload
 ; ALL-NEXT:    addq $24, %rsp
+; ALL-NEXT:   .cfi_def_cfa_offset 8
 ; ALL-NEXT:    retq
   %a  = fadd double %x, %x
   call void @func_f64(double %a)

test/CodeGen/X86/avx512bw-intrinsics-fast-isel.ll

@@ -717,6 +717,7 @@ define <8 x i64> @test_mm512_mask_set1_epi8(<8 x i64> %__O, i64 %__M, i8 signext
 ; X32-NEXT:    vpbroadcastb %eax, %zmm3 {%k1}
 ; X32-NEXT:    vmovdqa64 %zmm3, %zmm0
 ; X32-NEXT:    popl %ebx
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm512_mask_set1_epi8:
@@ -1444,6 +1445,7 @@ define <8 x i64> @test_mm512_maskz_set1_epi8(i64 %__M, i8 signext %__A)  {
 ; X32-NEXT:    korq %k0, %k1, %k1
 ; X32-NEXT:    vpbroadcastb %eax, %zmm0 {%k1} {z}
 ; X32-NEXT:    popl %ebx
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm512_maskz_set1_epi8:

test/CodeGen/X86/avx512bw-intrinsics-upgrade.ll

@@ -355,6 +355,7 @@ define i64 @test_pcmpeq_b(<64 x i8> %a, <64 x i8> %b) {
 ; AVX512F-32-NEXT:    movl (%esp), %eax
 ; AVX512F-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; AVX512F-32-NEXT:    addl $12, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    vzeroupper
 ; AVX512F-32-NEXT:    retl
   %res = call i64 @llvm.x86.avx512.mask.pcmpeq.b.512(<64 x i8> %a, <64 x i8> %b, i64 -1)
@@ -380,6 +381,7 @@ define i64 @test_mask_pcmpeq_b(<64 x i8> %a, <64 x i8> %b, i64 %mask) {
 ; AVX512F-32-NEXT:    movl (%esp), %eax
 ; AVX512F-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; AVX512F-32-NEXT:    addl $12, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    vzeroupper
 ; AVX512F-32-NEXT:    retl
   %res = call i64 @llvm.x86.avx512.mask.pcmpeq.b.512(<64 x i8> %a, <64 x i8> %b, i64 %mask)
@@ -445,6 +447,7 @@ define i64 @test_pcmpgt_b(<64 x i8> %a, <64 x i8> %b) {
 ; AVX512F-32-NEXT:    movl (%esp), %eax
 ; AVX512F-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; AVX512F-32-NEXT:    addl $12, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    vzeroupper
 ; AVX512F-32-NEXT:    retl
   %res = call i64 @llvm.x86.avx512.mask.pcmpgt.b.512(<64 x i8> %a, <64 x i8> %b, i64 -1)
@@ -470,6 +473,7 @@ define i64 @test_mask_pcmpgt_b(<64 x i8> %a, <64 x i8> %b, i64 %mask) {
 ; AVX512F-32-NEXT:    movl (%esp), %eax
 ; AVX512F-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; AVX512F-32-NEXT:    addl $12, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    vzeroupper
 ; AVX512F-32-NEXT:    retl
   %res = call i64 @llvm.x86.avx512.mask.pcmpgt.b.512(<64 x i8> %a, <64 x i8> %b, i64 %mask)
@@ -1702,6 +1706,7 @@ define i64 @test_cmp_b_512(<64 x i8> %a0, <64 x i8> %a1) {
 ; AVX512F-32-NEXT:    addl {{[0-9]+}}(%esp), %eax
 ; AVX512F-32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
 ; AVX512F-32-NEXT:    addl $60, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    vzeroupper
 ; AVX512F-32-NEXT:    retl
   %res0 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 0, i64 -1)
@@ -2503,8 +2508,11 @@ define i64 @test_mask_cmp_b_512(<64 x i8> %a0, <64 x i8> %a1, i64 %mask) {
 ; AVX512F-32-NEXT:    addl %esi, %eax
 ; AVX512F-32-NEXT:    adcl %ecx, %edx
 ; AVX512F-32-NEXT:    addl $60, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 12
 ; AVX512F-32-NEXT:    popl %esi
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 8
 ; AVX512F-32-NEXT:    popl %ebx
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    vzeroupper
 ; AVX512F-32-NEXT:    retl
   %res0 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 0, i64 %mask)
@@ -2586,6 +2594,7 @@ define i64 @test_ucmp_b_512(<64 x i8> %a0, <64 x i8> %a1) {
 ; AVX512F-32-NEXT:    addl {{[0-9]+}}(%esp), %eax
 ; AVX512F-32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
 ; AVX512F-32-NEXT:    addl $60, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    vzeroupper
 ; AVX512F-32-NEXT:    retl
   %res0 = call i64 @llvm.x86.avx512.mask.ucmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 0, i64 -1)
@@ -3387,8 +3396,11 @@ define i64 @test_mask_x86_avx512_ucmp_b_512(<64 x i8> %a0, <64 x i8> %a1, i64 %m
 ; AVX512F-32-NEXT:    addl %esi, %eax
 ; AVX512F-32-NEXT:    adcl %ecx, %edx
 ; AVX512F-32-NEXT:    addl $60, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 12
 ; AVX512F-32-NEXT:    popl %esi
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 8
 ; AVX512F-32-NEXT:    popl %ebx
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    vzeroupper
 ; AVX512F-32-NEXT:    retl
   %res0 = call i64 @llvm.x86.avx512.mask.ucmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 0, i64 %mask)

test/CodeGen/X86/avx512bw-intrinsics.ll

@@ -1499,6 +1499,7 @@ define i64@test_int_x86_avx512_kunpck_qd(i64 %x0, i64 %x1) {
 ; AVX512F-32-NEXT:    movl (%esp), %eax
 ; AVX512F-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; AVX512F-32-NEXT:    addl $12, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    retl
   %res = call i64 @llvm.x86.avx512.kunpck.dq(i64 %x0, i64 %x1)
   ret i64 %res
@@ -1522,6 +1523,7 @@ define i64@test_int_x86_avx512_cvtb2mask_512(<64 x i8> %x0) {
 ; AVX512F-32-NEXT:    movl (%esp), %eax
 ; AVX512F-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; AVX512F-32-NEXT:    addl $12, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    retl
     %res = call i64 @llvm.x86.avx512.cvtb2mask.512(<64 x i8> %x0)
     ret i64 %res
@@ -1712,6 +1714,7 @@ define i64@test_int_x86_avx512_ptestm_b_512(<64 x i8> %x0, <64 x i8> %x1, i64 %x
 ; AVX512F-32-NEXT:    addl {{[0-9]+}}(%esp), %eax
 ; AVX512F-32-NEXT:    adcxl {{[0-9]+}}(%esp), %edx
 ; AVX512F-32-NEXT:    addl $20, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    retl
   %res = call i64 @llvm.x86.avx512.ptestm.b.512(<64 x i8> %x0, <64 x i8> %x1, i64 %x2)
   %res1 = call i64 @llvm.x86.avx512.ptestm.b.512(<64 x i8> %x0, <64 x i8> %x1, i64-1)
@@ -1776,6 +1779,7 @@ define i64@test_int_x86_avx512_ptestnm_b_512(<64 x i8> %x0, <64 x i8> %x1, i64 %
 ; AVX512F-32-NEXT:    addl {{[0-9]+}}(%esp), %eax
 ; AVX512F-32-NEXT:    adcxl {{[0-9]+}}(%esp), %edx
 ; AVX512F-32-NEXT:    addl $20, %esp
+; AVX512F-32-NEXT:   .cfi_def_cfa_offset 4
 ; AVX512F-32-NEXT:    retl
   %res = call i64 @llvm.x86.avx512.ptestnm.b.512(<64 x i8> %x0, <64 x i8> %x1, i64 %x2)
   %res1 = call i64 @llvm.x86.avx512.ptestnm.b.512(<64 x i8> %x0, <64 x i8> %x1, i64-1)

test/CodeGen/X86/avx512vl-intrinsics-fast-isel.ll

@@ -233,6 +233,7 @@ define <2 x i64> @test_mm_mask_broadcastd_epi32(<2 x i64> %a0, i8 %a1, <2 x i64>
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vpbroadcastd %xmm1, %xmm0 {%k1}
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_mask_broadcastd_epi32:
@@ -265,6 +266,7 @@ define <2 x i64> @test_mm_maskz_broadcastd_epi32(i8 %a0, <2 x i64> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vpbroadcastd %xmm0, %xmm0 {%k1} {z}
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_maskz_broadcastd_epi32:
@@ -369,6 +371,7 @@ define <2 x i64> @test_mm_mask_broadcastq_epi64(<2 x i64> %a0, i8 %a1, <2 x i64>
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vpbroadcastq %xmm1, %xmm0 {%k1}
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_mask_broadcastq_epi64:
@@ -398,6 +401,7 @@ define <2 x i64> @test_mm_maskz_broadcastq_epi64(i8 %a0, <2 x i64> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vpbroadcastq %xmm0, %xmm0 {%k1} {z}
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_maskz_broadcastq_epi64:
@@ -441,6 +445,7 @@ define <4 x i64> @test_mm256_mask_broadcastq_epi64(<4 x i64> %a0, i8 %a1, <2 x i
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vpbroadcastq %xmm1, %ymm0 {%k1}
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_mask_broadcastq_epi64:
@@ -470,6 +475,7 @@ define <4 x i64> @test_mm256_maskz_broadcastq_epi64(i8 %a0, <2 x i64> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vpbroadcastq %xmm0, %ymm0 {%k1} {z}
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_maskz_broadcastq_epi64:
@@ -513,6 +519,7 @@ define <2 x double> @test_mm_mask_broadcastsd_pd(<2 x double> %a0, i8 %a1, <2 x
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} = xmm1[0,0]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_mask_broadcastsd_pd:
@@ -542,6 +549,7 @@ define <2 x double> @test_mm_maskz_broadcastsd_pd(i8 %a0, <2 x double> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} {z} = xmm0[0,0]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_maskz_broadcastsd_pd:
@@ -585,6 +593,7 @@ define <4 x double> @test_mm256_mask_broadcastsd_pd(<4 x double> %a0, i8 %a1, <2
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vbroadcastsd %xmm1, %ymm0 {%k1}
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_mask_broadcastsd_pd:
@@ -614,6 +623,7 @@ define <4 x double> @test_mm256_maskz_broadcastsd_pd(i8 %a0, <2 x double> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vbroadcastsd %xmm0, %ymm0 {%k1} {z}
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_maskz_broadcastsd_pd:
@@ -657,6 +667,7 @@ define <4 x float> @test_mm_mask_broadcastss_ps(<4 x float> %a0, i8 %a1, <4 x fl
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vbroadcastss %xmm1, %xmm0 {%k1}
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_mask_broadcastss_ps:
@@ -686,6 +697,7 @@ define <4 x float> @test_mm_maskz_broadcastss_ps(i8 %a0, <4 x float> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vbroadcastss %xmm0, %xmm0 {%k1} {z}
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_maskz_broadcastss_ps:
@@ -781,6 +793,7 @@ define <2 x double> @test_mm_mask_movddup_pd(<2 x double> %a0, i8 %a1, <2 x doub
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} = xmm1[0,0]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_mask_movddup_pd:
@@ -810,6 +823,7 @@ define <2 x double> @test_mm_maskz_movddup_pd(i8 %a0, <2 x double> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vmovddup {{.*#+}} xmm0 {%k1} {z} = xmm0[0,0]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_maskz_movddup_pd:
@@ -853,6 +867,7 @@ define <4 x double> @test_mm256_mask_movddup_pd(<4 x double> %a0, i8 %a1, <4 x d
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vmovddup {{.*#+}} ymm0 {%k1} = ymm1[0,0,2,2]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_mask_movddup_pd:
@@ -882,6 +897,7 @@ define <4 x double> @test_mm256_maskz_movddup_pd(i8 %a0, <4 x double> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vmovddup {{.*#+}} ymm0 {%k1} {z} = ymm0[0,0,2,2]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_maskz_movddup_pd:
@@ -925,6 +941,7 @@ define <4 x float> @test_mm_mask_movehdup_ps(<4 x float> %a0, i8 %a1, <4 x float
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vmovshdup {{.*#+}} xmm0 {%k1} = xmm1[1,1,3,3]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_mask_movehdup_ps:
@@ -954,6 +971,7 @@ define <4 x float> @test_mm_maskz_movehdup_ps(i8 %a0, <4 x float> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vmovshdup {{.*#+}} xmm0 {%k1} {z} = xmm0[1,1,3,3]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_maskz_movehdup_ps:
@@ -1049,6 +1067,7 @@ define <4 x float> @test_mm_mask_moveldup_ps(<4 x float> %a0, i8 %a1, <4 x float
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vmovsldup {{.*#+}} xmm0 {%k1} = xmm1[0,0,2,2]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_mask_moveldup_ps:
@@ -1078,6 +1097,7 @@ define <4 x float> @test_mm_maskz_moveldup_ps(i8 %a0, <4 x float> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vmovsldup {{.*#+}} xmm0 {%k1} {z} = xmm0[0,0,2,2]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_maskz_moveldup_ps:
@@ -1173,6 +1193,7 @@ define <4 x i64> @test_mm256_mask_permutex_epi64(<4 x i64> %a0, i8 %a1, <4 x i64
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vpermq {{.*#+}} ymm0 {%k1} = ymm1[1,0,0,0]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_mask_permutex_epi64:
@@ -1202,6 +1223,7 @@ define <4 x i64> @test_mm256_maskz_permutex_epi64(i8 %a0, <4 x i64> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vpermq {{.*#+}} ymm0 {%k1} {z} = ymm0[1,0,0,0]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_maskz_permutex_epi64:
@@ -1245,6 +1267,7 @@ define <4 x double> @test_mm256_mask_permutex_pd(<4 x double> %a0, i8 %a1, <4 x
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vpermpd {{.*#+}} ymm0 {%k1} = ymm1[1,0,0,0]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_mask_permutex_pd:
@@ -1274,6 +1297,7 @@ define <4 x double> @test_mm256_maskz_permutex_pd(i8 %a0, <4 x double> %a1) {
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vpermpd {{.*#+}} ymm0 {%k1} {z} = ymm0[1,0,0,0]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_maskz_permutex_pd:
@@ -1317,6 +1341,7 @@ define <2 x double> @test_mm_mask_shuffle_pd(<2 x double> %a0, i8 %a1, <2 x doub
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vunpckhpd {{.*#+}} xmm0 {%k1} = xmm1[1],xmm2[1]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_mask_shuffle_pd:
@@ -1346,6 +1371,7 @@ define <2 x double> @test_mm_maskz_shuffle_pd(i8 %a0, <2 x double> %a1, <2 x dou
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vunpckhpd {{.*#+}} xmm0 {%k1} {z} = xmm0[1],xmm1[1]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_maskz_shuffle_pd:
@@ -1389,6 +1415,7 @@ define <4 x double> @test_mm256_mask_shuffle_pd(<4 x double> %a0, i8 %a1, <4 x d
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vshufpd {{.*#+}} ymm0 {%k1} = ymm1[1],ymm2[1],ymm1[2],ymm2[2]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_mask_shuffle_pd:
@@ -1418,6 +1445,7 @@ define <4 x double> @test_mm256_maskz_shuffle_pd(i8 %a0, <4 x double> %a1, <4 x
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vshufpd {{.*#+}} ymm0 {%k1} {z} = ymm0[1],ymm1[1],ymm0[2],ymm1[2]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_maskz_shuffle_pd:
@@ -1461,6 +1489,7 @@ define <4 x float> @test_mm_mask_shuffle_ps(<4 x float> %a0, i8 %a1, <4 x float>
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vshufps {{.*#+}} xmm0 {%k1} = xmm1[0,1],xmm2[0,0]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_mask_shuffle_ps:
@@ -1490,6 +1519,7 @@ define <4 x float> @test_mm_maskz_shuffle_ps(i8 %a0, <4 x float> %a1, <4 x float
 ; X32-NEXT:    kmovw %eax, %k1
 ; X32-NEXT:    vshufps {{.*#+}} xmm0 {%k1} {z} = xmm0[0,1],xmm1[0,0]
 ; X32-NEXT:    popl %eax
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_maskz_shuffle_ps:

test/CodeGen/X86/avx512vl-vbroadcast.ll

@@ -12,6 +12,7 @@ define <8 x float> @_256_broadcast_ss_spill(float %x) {
 ; CHECK-NEXT:    callq func_f32
 ; CHECK-NEXT:    vbroadcastss (%rsp), %ymm0 # 16-byte Folded Reload
 ; CHECK-NEXT:    addq $24, %rsp
+; CHECK-NEXT:   .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
   %a  = fadd float %x, %x
   call void @func_f32(float %a)
@@ -30,6 +31,7 @@ define <4 x float> @_128_broadcast_ss_spill(float %x) {
 ; CHECK-NEXT:    callq func_f32
 ; CHECK-NEXT:    vbroadcastss (%rsp), %xmm0 # 16-byte Folded Reload
 ; CHECK-NEXT:    addq $24, %rsp
+; CHECK-NEXT:   .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
   %a  = fadd float %x, %x
   call void @func_f32(float %a)
@@ -49,6 +51,7 @@ define <4 x double> @_256_broadcast_sd_spill(double %x) {
 ; CHECK-NEXT:    callq func_f64
 ; CHECK-NEXT:    vbroadcastsd (%rsp), %ymm0 # 16-byte Folded Reload
 ; CHECK-NEXT:    addq $24, %rsp
+; CHECK-NEXT:   .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
   %a  = fadd double %x, %x
   call void @func_f64(double %a)

test/CodeGen/X86/bitcast-and-setcc-256.ll

@@ -439,6 +439,7 @@ define i32 @v32i8(<32 x i8> %a, <32 x i8> %b, <32 x i8> %c, <32 x i8> %d) {
 ; AVX512F-NEXT:    movl (%rsp), %eax
 ; AVX512F-NEXT:    movq %rbp, %rsp
 ; AVX512F-NEXT:    popq %rbp
+; AVX512F-NEXT:    .cfi_def_cfa %rsp, 8
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;

test/CodeGen/X86/bitcast-and-setcc-512.ll

@@ -594,6 +594,7 @@ define i32 @v32i16(<32 x i16> %a, <32 x i16> %b, <32 x i16> %c, <32 x i16> %d) {
 ; AVX512F-NEXT:    movl (%rsp), %eax
 ; AVX512F-NEXT:    movq %rbp, %rsp
 ; AVX512F-NEXT:    popq %rbp
+; AVX512F-NEXT:    .cfi_def_cfa %rsp, 8
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
@@ -1239,6 +1240,7 @@ define i64 @v64i8(<64 x i8> %a, <64 x i8> %b, <64 x i8> %c, <64 x i8> %d) {
 ; AVX1-NEXT:    orq %rcx, %rax
 ; AVX1-NEXT:    movq %rbp, %rsp
 ; AVX1-NEXT:    popq %rbp
+; AVX1-NEXT:   .cfi_def_cfa %rsp, 8
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
@@ -1457,6 +1459,7 @@ define i64 @v64i8(<64 x i8> %a, <64 x i8> %b, <64 x i8> %c, <64 x i8> %d) {
 ; AVX2-NEXT:    orq %rcx, %rax
 ; AVX2-NEXT:    movq %rbp, %rsp
 ; AVX2-NEXT:    popq %rbp
+; AVX2-NEXT:    .cfi_def_cfa %rsp, 8
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
@@ -1499,6 +1502,7 @@ define i64 @v64i8(<64 x i8> %a, <64 x i8> %b, <64 x i8> %c, <64 x i8> %d) {
 ; AVX512F-NEXT:    orq %rcx, %rax
 ; AVX512F-NEXT:    movq %rbp, %rsp
 ; AVX512F-NEXT:    popq %rbp
+; AVX512F-NEXT:    .cfi_def_cfa %rsp, 8
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;

test/CodeGen/X86/bitcast-int-to-vector-bool-zext.ll

@@ -321,11 +321,17 @@ define <16 x i8> @ext_i16_16i8(i16 %a0) {
 ; AVX512-NEXT:    vpinsrb $15, %r9d, %xmm0, %xmm0
 ; AVX512-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    popq %rbx
+; AVX512-NEXT:    .cfi_def_cfa_offset 48
 ; AVX512-NEXT:    popq %r12
+; AVX512-NEXT:    .cfi_def_cfa_offset 40
 ; AVX512-NEXT:    popq %r13
+; AVX512-NEXT:    .cfi_def_cfa_offset 32
 ; AVX512-NEXT:    popq %r14
+; AVX512-NEXT:    .cfi_def_cfa_offset 24
 ; AVX512-NEXT:    popq %r15
+; AVX512-NEXT:    .cfi_def_cfa_offset 16
 ; AVX512-NEXT:    popq %rbp
+; AVX512-NEXT:    .cfi_def_cfa_offset 8
 ; AVX512-NEXT:    retq
   %1 = bitcast i16 %a0 to <16 x i1>
   %2 = zext <16 x i1> %1 to <16 x i8>

test/CodeGen/X86/bitcast-setcc-256.ll

@@ -204,6 +204,7 @@ define i32 @v32i8(<32 x i8> %a, <32 x i8> %b) {
 ; AVX512F-NEXT:    movl (%rsp), %eax
 ; AVX512F-NEXT:    movq %rbp, %rsp
 ; AVX512F-NEXT:    popq %rbp
+; AVX512F-NEXT:    .cfi_def_cfa %rsp, 8
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;

test/CodeGen/X86/bitcast-setcc-512.ll

@@ -203,6 +203,7 @@ define i32 @v32i16(<32 x i16> %a, <32 x i16> %b) {
 ; AVX512F-NEXT:    movl (%rsp), %eax
 ; AVX512F-NEXT:    movq %rbp, %rsp
 ; AVX512F-NEXT:    popq %rbp
+; AVX512F-NEXT:    .cfi_def_cfa %rsp, 8
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
@@ -769,6 +770,7 @@ define i64 @v64i8(<64 x i8> %a, <64 x i8> %b) {
 ; AVX1-NEXT:    orq %rcx, %rax
 ; AVX1-NEXT:    movq %rbp, %rsp
 ; AVX1-NEXT:    popq %rbp
+; AVX1-NEXT:   .cfi_def_cfa %rsp, 8
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
@@ -983,6 +985,7 @@ define i64 @v64i8(<64 x i8> %a, <64 x i8> %b) {
 ; AVX2-NEXT:    orq %rcx, %rax
 ; AVX2-NEXT:    movq %rbp, %rsp
 ; AVX2-NEXT:    popq %rbp
+; AVX2-NEXT:    .cfi_def_cfa %rsp, 8
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
@@ -1021,6 +1024,7 @@ define i64 @v64i8(<64 x i8> %a, <64 x i8> %b) {
 ; AVX512F-NEXT:    orq %rcx, %rax
 ; AVX512F-NEXT:    movq %rbp, %rsp
 ; AVX512F-NEXT:    popq %rbp
+; AVX512F-NEXT:    .cfi_def_cfa %rsp, 8
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;

test/CodeGen/X86/bool-vector.ll

@@ -93,6 +93,7 @@ define i32 @PR15215_good(<4 x i32> %input) {
 ; X32-NEXT:    leal (%eax,%edx,4), %eax
 ; X32-NEXT:    leal (%eax,%esi,8), %eax
 ; X32-NEXT:    popl %esi
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X32-SSE2-LABEL: PR15215_good:
@@ -115,6 +116,7 @@ define i32 @PR15215_good(<4 x i32> %input) {
 ; X32-SSE2-NEXT:    leal (%eax,%edx,4), %eax
 ; X32-SSE2-NEXT:    leal (%eax,%esi,8), %eax
 ; X32-SSE2-NEXT:    popl %esi
+; X32-SSE2-NEXT:    .cfi_def_cfa_offset 4
 ; X32-SSE2-NEXT:    retl
 ;
 ; X32-AVX2-LABEL: PR15215_good:
@@ -134,6 +136,7 @@ define i32 @PR15215_good(<4 x i32> %input) {
 ; X32-AVX2-NEXT:    leal (%eax,%edx,4), %eax
 ; X32-AVX2-NEXT:    leal (%eax,%esi,8), %eax
 ; X32-AVX2-NEXT:    popl %esi
+; X32-AVX2-NEXT:    .cfi_def_cfa_offset 4
 ; X32-AVX2-NEXT:    retl
 ;
 ; X64-LABEL: PR15215_good:

test/CodeGen/X86/cmp.ll

@@ -247,10 +247,13 @@ define i32 @test12() ssp uwtable {
 ; CHECK-NEXT:  # BB#1: # %T
 ; CHECK-NEXT:    movl $1, %eax # encoding: [0xb8,0x01,0x00,0x00,0x00]
 ; CHECK-NEXT:    popq %rcx # encoding: [0x59]
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq # encoding: [0xc3]
 ; CHECK-NEXT:  .LBB12_2: # %F
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    movl $2, %eax # encoding: [0xb8,0x02,0x00,0x00,0x00]
 ; CHECK-NEXT:    popq %rcx # encoding: [0x59]
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq # encoding: [0xc3]
 entry:
   %tmp1 = call zeroext i1 @test12b()

test/CodeGen/X86/emutls-pie.ll

@@ -18,13 +18,16 @@ define i32 @my_get_xyz() {
 ; X32-NEXT: calll my_emutls_get_address@PLT
 ; X32-NEXT: movl (%eax), %eax
 ; X32-NEXT: addl $8, %esp
+; X32-NEXT: .cfi_def_cfa_offset 8
 ; X32-NEXT: popl %ebx
+; X32-NEXT: .cfi_def_cfa_offset 4
 ; X32-NEXT: retl
 ; X64-LABEL: my_get_xyz:
 ; X64:      movq my_emutls_v_xyz@GOTPCREL(%rip), %rdi
 ; X64-NEXT: callq my_emutls_get_address@PLT
 ; X64-NEXT: movl (%rax), %eax
 ; X64-NEXT: popq %rcx
+; X64-NEXT: .cfi_def_cfa_offset 8
 ; X64-NEXT: retq
 
 entry:
@@ -44,13 +47,16 @@ define i32 @f1() {
 ; X32-NEXT: calll __emutls_get_address@PLT
 ; X32-NEXT: movl (%eax), %eax
 ; X32-NEXT: addl $8, %esp
+; X32-NEXT: .cfi_def_cfa_offset 8
 ; X32-NEXT: popl %ebx
+; X32-NEXT: .cfi_def_cfa_offset 4
 ; X32-NEXT: retl
 ; X64-LABEL: f1:
 ; X64:      leaq __emutls_v.i(%rip), %rdi
 ; X64-NEXT: callq __emutls_get_address@PLT
 ; X64-NEXT: movl (%rax), %eax
 ; X64-NEXT: popq %rcx
+; X64-NEXT: .cfi_def_cfa_offset 8
 ; X64-NEXT: retq
 
 entry:

test/CodeGen/X86/emutls.ll

@@ -16,12 +16,14 @@ define i32 @my_get_xyz() {
 ; X32-NEXT:    calll my_emutls_get_address
 ; X32-NEXT:    movl (%eax), %eax
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ; X64-LABEL: my_get_xyz:
 ; X64:         movl $my_emutls_v_xyz, %edi
 ; X64-NEXT:    callq my_emutls_get_address
 ; X64-NEXT:    movl (%rax), %eax
 ; X64-NEXT:    popq %rcx
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
 
 entry:
@@ -45,12 +47,14 @@ define i32 @f1() {
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    movl (%eax), %eax
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ; X64-LABEL: f1:
 ; X64:         movl $__emutls_v.i1, %edi
 ; X64-NEXT:    callq __emutls_get_address
 ; X64-NEXT:    movl (%rax), %eax
 ; X64-NEXT:    popq %rcx
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
 
 entry:
@@ -63,11 +67,13 @@ define i32* @f2() {
 ; X32:         movl $__emutls_v.i1, (%esp)
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ; X64-LABEL: f2:
 ; X64:         movl $__emutls_v.i1, %edi
 ; X64-NEXT:    callq __emutls_get_address
 ; X64-NEXT:    popq %rcx
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
 
 entry:
@@ -92,6 +98,7 @@ define i32* @f4() {
 ; X32:         movl $__emutls_v.i2, (%esp)
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 
 entry:
@@ -116,6 +123,7 @@ define i32* @f6() {
 ; X32:         movl $__emutls_v.i3, (%esp)
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 
 entry:
@@ -128,6 +136,7 @@ define i32 @f7() {
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    movl (%eax), %eax
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 
 entry:
@@ -140,6 +149,7 @@ define i32* @f8() {
 ; X32:         movl $__emutls_v.i4, (%esp)
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 
 entry:
@@ -152,6 +162,7 @@ define i32 @f9() {
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    movl (%eax), %eax
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 
 entry:
@@ -164,6 +175,7 @@ define i32* @f10() {
 ; X32:         movl $__emutls_v.i5, (%esp)
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 
 entry:
@@ -176,6 +188,7 @@ define i16 @f11() {
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    movzwl (%eax), %eax
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 
 entry:
@@ -189,6 +202,7 @@ define i32 @f12() {
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    movswl (%eax), %eax
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 
 entry:
@@ -203,6 +217,7 @@ define i8 @f13() {
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    movb (%eax), %al
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 
 entry:
@@ -216,6 +231,7 @@ define i32 @f14() {
 ; X32-NEXT:    calll __emutls_get_address
 ; X32-NEXT:    movsbl (%eax), %eax
 ; X32-NEXT:    addl $12, %esp
+; X32-NEXT:    .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 
 entry:

test/CodeGen/X86/epilogue-cfi-fp.ll

@@ -0,0 +1,43 @@
+; RUN: llc -O0 %s -o - | FileCheck %s
+
+; ModuleID = 'epilogue-cfi-fp.c'
+source_filename = "epilogue-cfi-fp.c"
+target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
+target triple = "i686-pc-linux"
+
+; Function Attrs: noinline nounwind
+define i32 @foo(i32 %i, i32 %j, i32 %k, i32 %l, i32 %m) #0 {
+
+; CHECK-LABEL:   foo:
+; CHECK:         popl %ebp
+; CHECK-NEXT:    .cfi_def_cfa %esp, 4
+; CHECK-NEXT:    retl
+
+entry:
+  %i.addr = alloca i32, align 4
+  %j.addr = alloca i32, align 4
+  %k.addr = alloca i32, align 4
+  %l.addr = alloca i32, align 4
+  %m.addr = alloca i32, align 4
+  store i32 %i, i32* %i.addr, align 4
+  store i32 %j, i32* %j.addr, align 4
+  store i32 %k, i32* %k.addr, align 4
+  store i32 %l, i32* %l.addr, align 4
+  store i32 %m, i32* %m.addr, align 4
+  ret i32 0
+}
+
+attributes #0 = { "no-frame-pointer-elim"="true" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5, !6, !7}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 5.0.0 (http://llvm.org/git/clang.git 3f8116e6a2815b1d5f3491493938d0c63c9f42c9) (http://llvm.org/git/llvm.git 4fde77f8f1a8e4482e69b6a7484bc7d1b99b3c0a)", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !2)
+!1 = !DIFile(filename: "epilogue-cfi-fp.c", directory: "epilogue-dwarf/test")
+!2 = !{}
+!3 = !{i32 1, !"NumRegisterParameters", i32 0}
+!4 = !{i32 2, !"Dwarf Version", i32 4}
+!5 = !{i32 2, !"Debug Info Version", i32 3}
+!6 = !{i32 1, !"wchar_size", i32 4}
+!7 = !{i32 7, !"PIC Level", i32 2}
+

test/CodeGen/X86/epilogue-cfi-no-fp.ll

@@ -0,0 +1,46 @@
+; RUN: llc -O0 < %s | FileCheck %s
+
+; ModuleID = 'epilogue-cfi-no-fp.c'
+source_filename = "epilogue-cfi-no-fp.c"
+target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
+target triple = "i686-pc-linux"
+
+; Function Attrs: noinline nounwind
+define i32 @foo(i32 %i, i32 %j, i32 %k, i32 %l, i32 %m) {
+; CHECK-LABEL:   foo:
+; CHECK:         addl	$20, %esp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    popl	%esi
+; CHECK-NEXT:    .cfi_def_cfa_offset 12
+; CHECK-NEXT:    popl	%edi
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    popl	%ebx
+; CHECK-NEXT:    .cfi_def_cfa_offset 4
+; CHECK-NEXT:    retl
+entry:
+  %i.addr = alloca i32, align 4
+  %j.addr = alloca i32, align 4
+  %k.addr = alloca i32, align 4
+  %l.addr = alloca i32, align 4
+  %m.addr = alloca i32, align 4
+  store i32 %i, i32* %i.addr, align 4
+  store i32 %j, i32* %j.addr, align 4
+  store i32 %k, i32* %k.addr, align 4
+  store i32 %l, i32* %l.addr, align 4
+  store i32 %m, i32* %m.addr, align 4
+  ret i32 0
+}
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5, !6, !7}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 5.0.0 (http://llvm.org/git/clang.git 3f8116e6a2815b1d5f3491493938d0c63c9f42c9) (http://llvm.org/git/llvm.git 4fde77f8f1a8e4482e69b6a7484bc7d1b99b3c0a)", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !2)
+!1 = !DIFile(filename: "epilogue-cfi-no-fp.c", directory: "epilogue-dwarf/test")
+!2 = !{}
+!3 = !{i32 1, !"NumRegisterParameters", i32 0}
+!4 = !{i32 2, !"Dwarf Version", i32 4}
+!5 = !{i32 2, !"Debug Info Version", i32 3}
+!6 = !{i32 1, !"wchar_size", i32 4}
+!7 = !{i32 7, !"PIC Level", i32 2}
+
+

test/CodeGen/X86/fast-isel-store.ll

@@ -375,6 +375,7 @@ define <4 x double> @test_store_4xf64(<4 x double>* nocapture %addr, <4 x double
 ; SSE64-NEXT:    movupd %xmm0, (%eax)
 ; SSE64-NEXT:    movupd %xmm1, 16(%eax)
 ; SSE64-NEXT:    addl $12, %esp
+; SSE64-NEXT:   .cfi_def_cfa_offset 4
 ; SSE64-NEXT:    retl
 ;
 ; AVX32-LABEL: test_store_4xf64:
@@ -413,6 +414,7 @@ define <4 x double> @test_store_4xf64_aligned(<4 x double>* nocapture %addr, <4
 ; SSE64-NEXT:    movapd %xmm0, (%eax)
 ; SSE64-NEXT:    movapd %xmm1, 16(%eax)
 ; SSE64-NEXT:    addl $12, %esp
+; SSE64-NEXT:   .cfi_def_cfa_offset 4
 ; SSE64-NEXT:    retl
 ;
 ; AVX32-LABEL: test_store_4xf64_aligned:
@@ -452,6 +454,7 @@ define <16 x i32> @test_store_16xi32(<16 x i32>* nocapture %addr, <16 x i32> %va
 ; SSE64-NEXT:    movups %xmm2, 32(%eax)
 ; SSE64-NEXT:    movups %xmm3, 48(%eax)
 ; SSE64-NEXT:    addl $12, %esp
+; SSE64-NEXT:   .cfi_def_cfa_offset 4
 ; SSE64-NEXT:    retl
 ;
 ; AVXONLY32-LABEL: test_store_16xi32:
@@ -501,6 +504,7 @@ define <16 x i32> @test_store_16xi32_aligned(<16 x i32>* nocapture %addr, <16 x
 ; SSE64-NEXT:    movaps %xmm2, 32(%eax)
 ; SSE64-NEXT:    movaps %xmm3, 48(%eax)
 ; SSE64-NEXT:    addl $12, %esp
+; SSE64-NEXT:   .cfi_def_cfa_offset 4
 ; SSE64-NEXT:    retl
 ;
 ; AVXONLY32-LABEL: test_store_16xi32_aligned:
@@ -550,6 +554,7 @@ define <16 x float> @test_store_16xf32(<16 x float>* nocapture %addr, <16 x floa
 ; SSE64-NEXT:    movups %xmm2, 32(%eax)
 ; SSE64-NEXT:    movups %xmm3, 48(%eax)
 ; SSE64-NEXT:    addl $12, %esp
+; SSE64-NEXT:   .cfi_def_cfa_offset 4
 ; SSE64-NEXT:    retl
 ;
 ; AVXONLY32-LABEL: test_store_16xf32:
@@ -599,6 +604,7 @@ define <16 x float> @test_store_16xf32_aligned(<16 x float>* nocapture %addr, <1
 ; SSE64-NEXT:    movaps %xmm2, 32(%eax)
 ; SSE64-NEXT:    movaps %xmm3, 48(%eax)
 ; SSE64-NEXT:    addl $12, %esp
+; SSE64-NEXT:   .cfi_def_cfa_offset 4
 ; SSE64-NEXT:    retl
 ;
 ; AVXONLY32-LABEL: test_store_16xf32_aligned:
@@ -656,6 +662,7 @@ define <8 x double> @test_store_8xf64(<8 x double>* nocapture %addr, <8 x double
 ; SSE64-NEXT:    movupd %xmm2, 32(%eax)
 ; SSE64-NEXT:    movupd %xmm3, 48(%eax)
 ; SSE64-NEXT:    addl $12, %esp
+; SSE64-NEXT:   .cfi_def_cfa_offset 4
 ; SSE64-NEXT:    retl
 ;
 ; AVXONLY32-LABEL: test_store_8xf64:
@@ -682,6 +689,7 @@ define <8 x double> @test_store_8xf64(<8 x double>* nocapture %addr, <8 x double
 ; AVXONLY64-NEXT:    vmovupd %ymm1, 32(%eax)
 ; AVXONLY64-NEXT:    movl %ebp, %esp
 ; AVXONLY64-NEXT:    popl %ebp
+; AVXONLY64-NEXT:    .cfi_def_cfa %esp, 4
 ; AVXONLY64-NEXT:    retl
 ;
 ; AVX51232-LABEL: test_store_8xf64:
@@ -729,6 +737,7 @@ define <8 x double> @test_store_8xf64_aligned(<8 x double>* nocapture %addr, <8
 ; SSE64-NEXT:    movapd %xmm2, 32(%eax)
 ; SSE64-NEXT:    movapd %xmm3, 48(%eax)
 ; SSE64-NEXT:    addl $12, %esp
+; SSE64-NEXT:   .cfi_def_cfa_offset 4
 ; SSE64-NEXT:    retl
 ;
 ; AVXONLY32-LABEL: test_store_8xf64_aligned:
@@ -755,6 +764,7 @@ define <8 x double> @test_store_8xf64_aligned(<8 x double>* nocapture %addr, <8
 ; AVXONLY64-NEXT:    vmovapd %ymm1, 32(%eax)
 ; AVXONLY64-NEXT:    movl %ebp, %esp
 ; AVXONLY64-NEXT:    popl %ebp
+; AVXONLY64-NEXT:    .cfi_def_cfa %esp, 4
 ; AVXONLY64-NEXT:    retl
 ;
 ; AVX51232-LABEL: test_store_8xf64_aligned:

test/CodeGen/X86/frame-lowering-debug-intrinsic-2.ll

@@ -18,11 +18,15 @@ entry:
 }
 
 ; CHECK-LABEL: noDebug
-; CHECK:       addq  $24, %rsp
-; CHECK:       popq  %rbx
-; CHECK-NEXT:  popq  %r14
-; CHECK-NEXT:  retq
-
+; CHECK:        addq	$16, %rsp
+; CHECK-NEXT: 	  .cfi_adjust_cfa_offset -16
+; CHECK-NEXT: 	addq	$8, %rsp
+; CHECK-NEXT: 	  .cfi_def_cfa_offset 24
+; CHECK-NEXT: 	popq	%rbx
+; CHECK-NEXT: 	  .cfi_def_cfa_offset 16
+; CHECK-NEXT: 	popq	%r14
+; CHECK-NEXT: 	  .cfi_def_cfa_offset 8
+; CHECK-NEXT: 	retq
 
 define void @withDebug() !dbg !18 {
 entry:
@@ -42,9 +46,11 @@ entry:
 ; CHECK-LABEL: withDebug
 ; CHECK:       callq printf
 ; CHECK:       callq printf
-; CHECK-NEXT:  addq  $24, %rsp
+; CHECK-NEXT: addq $16, %rsp
 ; CHECK:       popq  %rbx
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:  popq  %r14
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:  retq
 
 declare { i64, i1 } @llvm.uadd.with.overflow.i64(i64, i64)

test/CodeGen/X86/frame-lowering-debug-intrinsic.ll

@@ -9,6 +9,7 @@ define i64 @fn1NoDebug(i64 %a) {
 
 ; CHECK-LABEL: fn1NoDebug
 ; CHECK: popq %rcx
+; CHECK-NEXT: .cfi_def_cfa_offset 8
 ; CHECK-NEXT: ret
 
 define i64 @fn1WithDebug(i64 %a) !dbg !4 {
@@ -19,6 +20,7 @@ define i64 @fn1WithDebug(i64 %a) !dbg !4 {
 
 ; CHECK-LABEL: fn1WithDebug
 ; CHECK: popq %rcx
+; CHECK-NEXT: .cfi_def_cfa_offset 8
 ; CHECK-NEXT: ret
 
 %struct.Buffer = type { i8, [63 x i8] }
@@ -33,6 +35,7 @@ define void @fn2NoDebug(%struct.Buffer* byval align 64 %p1) {
 ; CHECK-NOT: sub
 ; CHECK: mov
 ; CHECK-NEXT: pop
+; CHECK-NEXT: .cfi_def_cfa %rsp, 8
 ; CHECK-NEXT: ret
 
 define void @fn2WithDebug(%struct.Buffer* byval align 64 %p1) !dbg !8 {
@@ -46,6 +49,7 @@ define void @fn2WithDebug(%struct.Buffer* byval align 64 %p1) !dbg !8 {
 ; CHECK-NOT: sub
 ; CHECK: mov
 ; CHECK-NEXT: pop
+; CHECK-NEXT: .cfi_def_cfa %rsp, 8
 ; CHECK-NEXT: ret
 
 declare i64 @fn(i64, i64)

test/CodeGen/X86/haddsub-2.ll

@@ -724,11 +724,17 @@ define <16 x i16> @avx2_vphadd_w_test(<16 x i16> %a, <16 x i16> %b) {
 ; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm5[0]
 ; SSE3-NEXT:    popq %rbx
+; SSE3-NEXT:   .cfi_def_cfa_offset 48
 ; SSE3-NEXT:    popq %r12
+; SSE3-NEXT:   .cfi_def_cfa_offset 40
 ; SSE3-NEXT:    popq %r13
+; SSE3-NEXT:   .cfi_def_cfa_offset 32
 ; SSE3-NEXT:    popq %r14
+; SSE3-NEXT:   .cfi_def_cfa_offset 24
 ; SSE3-NEXT:    popq %r15
+; SSE3-NEXT:   .cfi_def_cfa_offset 16
 ; SSE3-NEXT:    popq %rbp
+; SSE3-NEXT:   .cfi_def_cfa_offset 8
 ; SSE3-NEXT:    retq
 ;
 ; SSSE3-LABEL: avx2_vphadd_w_test:
@@ -1351,11 +1357,17 @@ define <16 x i16> @avx2_hadd_w(<16 x i16> %a, <16 x i16> %b) {
 ; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm5[0]
 ; SSE3-NEXT:    popq %rbx
+; SSE3-NEXT:   .cfi_def_cfa_offset 48
 ; SSE3-NEXT:    popq %r12
+; SSE3-NEXT:   .cfi_def_cfa_offset 40
 ; SSE3-NEXT:    popq %r13
+; SSE3-NEXT:   .cfi_def_cfa_offset 32
 ; SSE3-NEXT:    popq %r14
+; SSE3-NEXT:   .cfi_def_cfa_offset 24
 ; SSE3-NEXT:    popq %r15
+; SSE3-NEXT:   .cfi_def_cfa_offset 16
 ; SSE3-NEXT:    popq %rbp
+; SSE3-NEXT:   .cfi_def_cfa_offset 8
 ; SSE3-NEXT:    retq
 ;
 ; SSSE3-LABEL: avx2_hadd_w:

test/CodeGen/X86/hipe-cc64.ll

@@ -87,6 +87,7 @@ define cc 11 { i64, i64, i64 } @tailcaller(i64 %hp, i64 %p) #0 {
   ; CHECK-NEXT: movl	$47, %ecx
   ; CHECK-NEXT: movl	$63, %r8d
   ; CHECK-NEXT: popq	%rax
+  ; CHECK-NEXT: .cfi_def_cfa_offset 16
   ; CHECK-NEXT: jmp	tailcallee
   %ret = tail call cc11 { i64, i64, i64 } @tailcallee(i64 %hp, i64 %p, i64 15,
      i64 31, i64 47, i64 63, i64 79) #1

test/CodeGen/X86/illegal-bitfield-loadstore.ll

@@ -81,6 +81,7 @@ define void @i24_insert_bit(i24* %a, i1 zeroext %bit) {
 ; X86-NEXT:    orl %edx, %eax
 ; X86-NEXT:    movw %ax, (%ecx)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:    .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: i24_insert_bit:

test/CodeGen/X86/imul.ll

@@ -307,6 +307,7 @@ define i64 @test5(i64 %a) {
 ; X86-NEXT:    subl %ecx, %edx
 ; X86-NEXT:    subl %esi, %edx
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 entry:
 	%tmp3 = mul i64 %a, -31
@@ -362,6 +363,7 @@ define i64 @test7(i64 %a) {
 ; X86-NEXT:    subl %ecx, %edx
 ; X86-NEXT:    subl %esi, %edx
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 entry:
 	%tmp3 = mul i64 %a, -33
@@ -390,6 +392,7 @@ define i64 @testOverflow(i64 %a) {
 ; X86-NEXT:    addl %esi, %edx
 ; X86-NEXT:    subl {{[0-9]+}}(%esp), %edx
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 entry:
 	%tmp3 = mul i64 %a, 9223372036854775807

test/CodeGen/X86/lea-opt-cse1.ll

@@ -30,6 +30,7 @@ define void @test_func(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr {
 ; X86-NEXT:    leal 1(%edx,%ecx), %ecx
 ; X86-NEXT:    movl %ecx, 16(%eax)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:    .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
  entry:
    %h0 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 0

test/CodeGen/X86/lea-opt-cse2.ll

@@ -46,7 +46,9 @@ define void @foo(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr #0 {
 ; X86-NEXT:    leal 1(%esi,%edx), %ecx
 ; X86-NEXT:    movl %ecx, 16(%eax)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:    .cfi_def_cfa_offset 8
 ; X86-NEXT:    popl %edi
+; X86-NEXT:    .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
  entry:
    br label %loop

test/CodeGen/X86/lea-opt-cse3.ll

@@ -91,6 +91,7 @@ define i32 @foo1_mult_basic_blocks(i32 %a, i32 %b) local_unnamed_addr #0 {
 ; X86-NEXT:    movl %ecx, %eax
 ; X86-NEXT:  .LBB2_2: # %exit
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 entry:
   %mul = shl i32 %b, 2
@@ -143,6 +144,7 @@ define i32 @foo1_mult_basic_blocks_illegal_scale(i32 %a, i32 %b) local_unnamed_a
 ; X86-NEXT:    movl %ecx, %eax
 ; X86-NEXT:  .LBB3_2: # %exit
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 entry:
   %mul = shl i32 %b, 1

test/CodeGen/X86/lea-opt-cse4.ll

@@ -36,6 +36,7 @@ define void @foo(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr #0 {
 ; X86-NEXT:    leal 1(%ecx,%edx), %ecx
 ; X86-NEXT:    movl %ecx, 16(%eax)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
  entry:
    %h0 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 0
@@ -110,7 +111,9 @@ define void @foo_loop(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr #0
 ; X86-NEXT:    addl %ecx, %edx
 ; X86-NEXT:    movl %edx, 16(%eax)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    popl %edi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
  entry:
    br label %loop

test/CodeGen/X86/legalize-shift-64.ll

@@ -117,9 +117,13 @@ define <2 x i64> @test5(<2 x i64> %A, <2 x i64> %B) {
 ; CHECK-NEXT:    movl %esi, 4(%eax)
 ; CHECK-NEXT:    movl %edi, (%eax)
 ; CHECK-NEXT:    popl %esi
+; CHECK-NEXT:   .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    popl %edi
+; CHECK-NEXT:   .cfi_def_cfa_offset 12
 ; CHECK-NEXT:    popl %ebx
+; CHECK-NEXT:   .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    popl %ebp
+; CHECK-NEXT:   .cfi_def_cfa_offset 4
 ; CHECK-NEXT:    retl $4
   %shl = shl <2 x i64> %A, %B
   ret <2 x i64> %shl
@@ -160,6 +164,7 @@ define i32 @test6() {
 ; CHECK-NEXT:  .LBB5_4: # %if.then
 ; CHECK-NEXT:    movl %ebp, %esp
 ; CHECK-NEXT:    popl %ebp
+; CHECK-NEXT:   .cfi_def_cfa %esp, 4
 ; CHECK-NEXT:    retl
   %x = alloca i32, align 4
   %t = alloca i64, align 8

test/CodeGen/X86/live-out-reg-info.ll

@@ -18,6 +18,7 @@ define void @foo(i32 %a) {
 ; CHECK-NEXT:    callq qux
 ; CHECK-NEXT:  .LBB0_2: # %false
 ; CHECK-NEXT:    popq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
   %t0 = lshr i32 %a, 23
   br label %next

test/CodeGen/X86/load-combine.ll

@@ -376,6 +376,7 @@ define i32 @load_i32_by_i8_bswap_uses(i32* %arg) {
 ; CHECK-NEXT:    orl %ecx, %eax
 ; CHECK-NEXT:    orl %edx, %eax
 ; CHECK-NEXT:    popl %esi
+; CHECK-NEXT:   .cfi_def_cfa_offset 4
 ; CHECK-NEXT:    retl
 ;
 ; CHECK64-LABEL: load_i32_by_i8_bswap_uses:
@@ -496,6 +497,7 @@ define i32 @load_i32_by_i8_bswap_store_in_between(i32* %arg, i32* %arg1) {
 ; CHECK-NEXT:    movzbl 3(%ecx), %eax
 ; CHECK-NEXT:    orl %edx, %eax
 ; CHECK-NEXT:    popl %esi
+; CHECK-NEXT:   .cfi_def_cfa_offset 4
 ; CHECK-NEXT:    retl
 ;
 ; CHECK64-LABEL: load_i32_by_i8_bswap_store_in_between:

test/CodeGen/X86/masked_gather_scatter.ll

@@ -1702,6 +1702,7 @@ define <16 x i64> @test_gather_16i64(<16 x i64*> %ptrs, <16 x i1> %mask, <16 x i
 ; KNL_32-NEXT:    vmovdqa64 %zmm2, %zmm0
 ; KNL_32-NEXT:    movl %ebp, %esp
 ; KNL_32-NEXT:    popl %ebp
+; KNL_32-NEXT:   .cfi_def_cfa %esp, 4
 ; KNL_32-NEXT:    retl
 ;
 ; SKX-LABEL: test_gather_16i64:
@@ -1736,6 +1737,7 @@ define <16 x i64> @test_gather_16i64(<16 x i64*> %ptrs, <16 x i1> %mask, <16 x i
 ; SKX_32-NEXT:    vmovdqa64 %zmm2, %zmm0
 ; SKX_32-NEXT:    movl %ebp, %esp
 ; SKX_32-NEXT:    popl %ebp
+; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
 ; SKX_32-NEXT:    retl
   %res = call <16 x i64> @llvm.masked.gather.v16i64.v16p0i64(<16 x i64*> %ptrs, i32 4, <16 x i1> %mask, <16 x i64> %src0)
   ret <16 x i64> %res
@@ -1819,6 +1821,7 @@ define <16 x double> @test_gather_16f64(<16 x double*> %ptrs, <16 x i1> %mask, <
 ; KNL_32-NEXT:    vmovapd %zmm2, %zmm0
 ; KNL_32-NEXT:    movl %ebp, %esp
 ; KNL_32-NEXT:    popl %ebp
+; KNL_32-NEXT:   .cfi_def_cfa %esp, 4
 ; KNL_32-NEXT:    retl
 ;
 ; SKX-LABEL: test_gather_16f64:
@@ -1853,6 +1856,7 @@ define <16 x double> @test_gather_16f64(<16 x double*> %ptrs, <16 x i1> %mask, <
 ; SKX_32-NEXT:    vmovapd %zmm2, %zmm0
 ; SKX_32-NEXT:    movl %ebp, %esp
 ; SKX_32-NEXT:    popl %ebp
+; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
 ; SKX_32-NEXT:    retl
   %res = call <16 x double> @llvm.masked.gather.v16f64.v16p0f64(<16 x double*> %ptrs, i32 4, <16 x i1> %mask, <16 x double> %src0)
   ret <16 x double> %res
@@ -1934,6 +1938,7 @@ define void @test_scatter_16i64(<16 x i64*> %ptrs, <16 x i1> %mask, <16 x i64> %
 ; KNL_32-NEXT:    vpscatterdq %zmm1, (,%ymm0) {%k2}
 ; KNL_32-NEXT:    movl %ebp, %esp
 ; KNL_32-NEXT:    popl %ebp
+; KNL_32-NEXT:   .cfi_def_cfa %esp, 4
 ; KNL_32-NEXT:    vzeroupper
 ; KNL_32-NEXT:    retl
 ;
@@ -1967,6 +1972,7 @@ define void @test_scatter_16i64(<16 x i64*> %ptrs, <16 x i1> %mask, <16 x i64> %
 ; SKX_32-NEXT:    vpscatterdq %zmm1, (,%ymm0) {%k2}
 ; SKX_32-NEXT:    movl %ebp, %esp
 ; SKX_32-NEXT:    popl %ebp
+; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
 ; SKX_32-NEXT:    vzeroupper
 ; SKX_32-NEXT:    retl
   call void @llvm.masked.scatter.v16i64.v16p0i64(<16 x i64> %src0, <16 x i64*> %ptrs, i32 4, <16 x i1> %mask)
@@ -2050,6 +2056,7 @@ define void @test_scatter_16f64(<16 x double*> %ptrs, <16 x i1> %mask, <16 x dou
 ; KNL_32-NEXT:    vscatterdpd %zmm1, (,%ymm0) {%k2}
 ; KNL_32-NEXT:    movl %ebp, %esp
 ; KNL_32-NEXT:    popl %ebp
+; KNL_32-NEXT:   .cfi_def_cfa %esp, 4
 ; KNL_32-NEXT:    vzeroupper
 ; KNL_32-NEXT:    retl
 ;
@@ -2083,6 +2090,7 @@ define void @test_scatter_16f64(<16 x double*> %ptrs, <16 x i1> %mask, <16 x dou
 ; SKX_32-NEXT:    vscatterdpd %zmm1, (,%ymm0) {%k2}
 ; SKX_32-NEXT:    movl %ebp, %esp
 ; SKX_32-NEXT:    popl %ebp
+; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
 ; SKX_32-NEXT:    vzeroupper
 ; SKX_32-NEXT:    retl
   call void @llvm.masked.scatter.v16f64.v16p0f64(<16 x double> %src0, <16 x double*> %ptrs, i32 4, <16 x i1> %mask)
@@ -2127,6 +2135,7 @@ define <4 x i64> @test_pr28312(<4 x i64*> %p1, <4 x i1> %k, <4 x i1> %k2,<4 x i6
 ; KNL_32-NEXT:    vpaddq %ymm0, %ymm1, %ymm0
 ; KNL_32-NEXT:    movl %ebp, %esp
 ; KNL_32-NEXT:    popl %ebp
+; KNL_32-NEXT:   .cfi_def_cfa %esp, 4
 ; KNL_32-NEXT:    retl
 ;
 ; SKX-LABEL: test_pr28312:
@@ -2154,6 +2163,7 @@ define <4 x i64> @test_pr28312(<4 x i64*> %p1, <4 x i1> %k, <4 x i1> %k2,<4 x i6
 ; SKX_32-NEXT:    vpaddq %ymm0, %ymm1, %ymm0
 ; SKX_32-NEXT:    movl %ebp, %esp
 ; SKX_32-NEXT:    popl %ebp
+; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
 ; SKX_32-NEXT:    retl
   %g1 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)
   %g2 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)

test/CodeGen/X86/memset-nonzero.ll

@@ -148,6 +148,7 @@ define void @memset_256_nonzero_bytes(i8* %x) {
 ; SSE-NEXT:    movl $256, %edx # imm = 0x100
 ; SSE-NEXT:    callq memset
 ; SSE-NEXT:    popq %rax
+; SSE-NEXT:    .cfi_def_cfa_offset 8
 ; SSE-NEXT:    retq
 ;
 ; SSE2FAST-LABEL: memset_256_nonzero_bytes:

test/CodeGen/X86/merge-consecutive-loads-128.ll

@@ -72,7 +72,9 @@ define <2 x i64> @merge_2i64_i64_12(i64* %ptr) nounwind uwtable noinline ssp {
 ; X32-SSE1-NEXT:    movl %esi, 4(%eax)
 ; X32-SSE1-NEXT:    movl %edx, (%eax)
 ; X32-SSE1-NEXT:    popl %esi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 8
 ; X32-SSE1-NEXT:    popl %edi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 4
 ; X32-SSE1-NEXT:    retl $4
 ;
 ; X32-SSE41-LABEL: merge_2i64_i64_12:
@@ -384,6 +386,7 @@ define <4 x i32> @merge_4i32_i32_23u5(i32* %ptr) nounwind uwtable noinline ssp {
 ; X32-SSE1-NEXT:    movl %edx, (%eax)
 ; X32-SSE1-NEXT:    movl %ecx, 12(%eax)
 ; X32-SSE1-NEXT:    popl %esi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 4
 ; X32-SSE1-NEXT:    retl $4
 ;
 ; X32-SSE41-LABEL: merge_4i32_i32_23u5:
@@ -435,7 +438,9 @@ define <4 x i32> @merge_4i32_i32_23u5_inc2(i32* %ptr) nounwind uwtable noinline
 ; X32-SSE1-NEXT:    movl %edx, (%eax)
 ; X32-SSE1-NEXT:    movl %ecx, 12(%eax)
 ; X32-SSE1-NEXT:    popl %esi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 8
 ; X32-SSE1-NEXT:    popl %edi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 4
 ; X32-SSE1-NEXT:    retl $4
 ;
 ; X32-SSE41-LABEL: merge_4i32_i32_23u5_inc2:
@@ -490,7 +495,9 @@ define <4 x i32> @merge_4i32_i32_23u5_inc3(i32* %ptr) nounwind uwtable noinline
 ; X32-SSE1-NEXT:    movl %edx, (%eax)
 ; X32-SSE1-NEXT:    movl %ecx, 12(%eax)
 ; X32-SSE1-NEXT:    popl %esi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 8
 ; X32-SSE1-NEXT:    popl %edi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 4
 ; X32-SSE1-NEXT:    retl $4
 ;
 ; X32-SSE41-LABEL: merge_4i32_i32_23u5_inc3:
@@ -649,7 +656,9 @@ define <4 x i32> @merge_4i32_i32_45zz_inc4(i32* %ptr) nounwind uwtable noinline
 ; X32-SSE1-NEXT:    movl $0, 12(%eax)
 ; X32-SSE1-NEXT:    movl $0, 8(%eax)
 ; X32-SSE1-NEXT:    popl %esi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 8
 ; X32-SSE1-NEXT:    popl %edi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 4
 ; X32-SSE1-NEXT:    retl $4
 ;
 ; X32-SSE41-LABEL: merge_4i32_i32_45zz_inc4:
@@ -701,7 +710,9 @@ define <4 x i32> @merge_4i32_i32_45zz_inc5(i32* %ptr) nounwind uwtable noinline
 ; X32-SSE1-NEXT:    movl $0, 12(%eax)
 ; X32-SSE1-NEXT:    movl $0, 8(%eax)
 ; X32-SSE1-NEXT:    popl %esi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 8
 ; X32-SSE1-NEXT:    popl %edi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 4
 ; X32-SSE1-NEXT:    retl $4
 ;
 ; X32-SSE41-LABEL: merge_4i32_i32_45zz_inc5:
@@ -751,7 +762,9 @@ define <8 x i16> @merge_8i16_i16_23u567u9(i16* %ptr) nounwind uwtable noinline s
 ; X32-SSE1-NEXT:    movl %esi, 6(%eax)
 ; X32-SSE1-NEXT:    movl %edx, (%eax)
 ; X32-SSE1-NEXT:    popl %esi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 8
 ; X32-SSE1-NEXT:    popl %edi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 4
 ; X32-SSE1-NEXT:    retl $4
 ;
 ; X32-SSE41-LABEL: merge_8i16_i16_23u567u9:
@@ -897,9 +910,13 @@ define <16 x i8> @merge_16i8_i8_01u3456789ABCDuF(i8* %ptr) nounwind uwtable noin
 ; X32-SSE1-NEXT:    movl %esi, 3(%eax)
 ; X32-SSE1-NEXT:    movw %bp, (%eax)
 ; X32-SSE1-NEXT:    popl %esi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 16
 ; X32-SSE1-NEXT:    popl %edi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 12
 ; X32-SSE1-NEXT:    popl %ebx
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 8
 ; X32-SSE1-NEXT:    popl %ebp
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 4
 ; X32-SSE1-NEXT:    retl $4
 ;
 ; X32-SSE41-LABEL: merge_16i8_i8_01u3456789ABCDuF:
@@ -1129,7 +1146,9 @@ define <2 x i64> @merge_2i64_i64_12_volatile(i64* %ptr) nounwind uwtable noinlin
 ; X32-SSE1-NEXT:    movl %esi, 4(%eax)
 ; X32-SSE1-NEXT:    movl %edx, (%eax)
 ; X32-SSE1-NEXT:    popl %esi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 8
 ; X32-SSE1-NEXT:    popl %edi
+; X32-SSE1-NEXT:   .cfi_def_cfa_offset 4
 ; X32-SSE1-NEXT:    retl $4
 ;
 ; X32-SSE41-LABEL: merge_2i64_i64_12_volatile:

test/CodeGen/X86/movtopush.ll

@@ -382,8 +382,10 @@ entry:
 ; LINUX: pushl   $1
 ; LINUX: .cfi_adjust_cfa_offset 4
 ; LINUX: calll   good
-; LINUX: addl    $28, %esp
+; LINUX: addl    $16, %esp
 ; LINUX: .cfi_adjust_cfa_offset -16
+; LINUX: addl    $12, %esp
+; LINUX: .cfi_def_cfa_offset 4
 ; LINUX-NOT: add
 ; LINUX: retl
 define void @pr27140() optsize {

test/CodeGen/X86/mul-constant-result.ll

@@ -34,84 +34,116 @@ define i32 @mult(i32, i32) local_unnamed_addr #0 {
 ; X86-NEXT:  .LBB0_6:
 ; X86-NEXT:    addl %eax, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_39:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    xorl %eax, %eax
 ; X86-NEXT:  .LBB0_40:
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_7:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,2), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_8:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    shll $2, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_9:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_10:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    addl %eax, %eax
 ; X86-NEXT:    leal (%eax,%eax,2), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_11:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (,%eax,8), %ecx
 ; X86-NEXT:    jmp .LBB0_12
 ; X86-NEXT:  .LBB0_13:
 ; X86-NEXT:    shll $3, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_14:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,8), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_15:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    addl %eax, %eax
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_16:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,4), %ecx
 ; X86-NEXT:    leal (%eax,%ecx,2), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_17:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    shll $2, %eax
 ; X86-NEXT:    leal (%eax,%eax,2), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_18:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,2), %ecx
 ; X86-NEXT:    leal (%eax,%ecx,4), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_19:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,2), %ecx
 ; X86-NEXT:    jmp .LBB0_20
 ; X86-NEXT:  .LBB0_21:
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    leal (%eax,%eax,2), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_22:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    shll $4, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_23:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    movl %eax, %ecx
 ; X86-NEXT:    shll $4, %ecx
 ; X86-NEXT:    addl %ecx, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_24:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    addl %eax, %eax
 ; X86-NEXT:    leal (%eax,%eax,8), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_25:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,4), %ecx
 ; X86-NEXT:    shll $2, %ecx
 ; X86-NEXT:    jmp .LBB0_12
@@ -119,20 +151,26 @@ define i32 @mult(i32, i32) local_unnamed_addr #0 {
 ; X86-NEXT:    shll $2, %eax
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_27:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,4), %ecx
 ; X86-NEXT:    leal (%eax,%ecx,4), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_28:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,4), %ecx
 ; X86-NEXT:  .LBB0_20:
 ; X86-NEXT:    leal (%eax,%ecx,4), %ecx
 ; X86-NEXT:    addl %ecx, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_29:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,2), %ecx
 ; X86-NEXT:    shll $3, %ecx
 ; X86-NEXT:    jmp .LBB0_12
@@ -140,13 +178,17 @@ define i32 @mult(i32, i32) local_unnamed_addr #0 {
 ; X86-NEXT:    shll $3, %eax
 ; X86-NEXT:    leal (%eax,%eax,2), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_31:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_32:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,8), %ecx
 ; X86-NEXT:    leal (%ecx,%ecx,2), %ecx
 ; X86-NEXT:    jmp .LBB0_12
@@ -154,21 +196,27 @@ define i32 @mult(i32, i32) local_unnamed_addr #0 {
 ; X86-NEXT:    leal (%eax,%eax,8), %eax
 ; X86-NEXT:    leal (%eax,%eax,2), %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_34:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,8), %ecx
 ; X86-NEXT:    leal (%ecx,%ecx,2), %ecx
 ; X86-NEXT:    addl %ecx, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_35:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    leal (%eax,%eax,8), %ecx
 ; X86-NEXT:    leal (%ecx,%ecx,2), %ecx
 ; X86-NEXT:    addl %eax, %ecx
 ; X86-NEXT:    addl %ecx, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_36:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    movl %eax, %ecx
 ; X86-NEXT:    shll $5, %ecx
 ; X86-NEXT:    subl %eax, %ecx
@@ -180,10 +228,13 @@ define i32 @mult(i32, i32) local_unnamed_addr #0 {
 ; X86-NEXT:    subl %eax, %ecx
 ; X86-NEXT:    movl %ecx, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_38:
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    shll $5, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-HSW-LABEL: mult:
@@ -857,8 +908,11 @@ define i32 @foo() local_unnamed_addr #0 {
 ; X86-NEXT:    negl %ecx
 ; X86-NEXT:    movl %ecx, %eax
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 12
 ; X86-NEXT:    popl %edi
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    popl %ebx
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-HSW-LABEL: foo:
@@ -1072,10 +1126,15 @@ define i32 @foo() local_unnamed_addr #0 {
 ; X64-HSW-NEXT:    negl %ecx
 ; X64-HSW-NEXT:    movl %ecx, %eax
 ; X64-HSW-NEXT:    addq $8, %rsp
+; X64-HSW-NEXT:    .cfi_def_cfa_offset 40
 ; X64-HSW-NEXT:    popq %rbx
+; X64-HSW-NEXT:    .cfi_def_cfa_offset 32
 ; X64-HSW-NEXT:    popq %r14
+; X64-HSW-NEXT:    .cfi_def_cfa_offset 24
 ; X64-HSW-NEXT:    popq %r15
+; X64-HSW-NEXT:    .cfi_def_cfa_offset 16
 ; X64-HSW-NEXT:    popq %rbp
+; X64-HSW-NEXT:    .cfi_def_cfa_offset 8
 ; X64-HSW-NEXT:    retq
   %1 = tail call i32 @mult(i32 1, i32 0)
   %2 = icmp ne i32 %1, 1

test/CodeGen/X86/mul-i256.ll

@@ -349,10 +349,15 @@ define void @test(i256* %a, i256* %b, i256* %out) #0 {
 ; X32-NEXT:    movl %eax, 24(%ecx)
 ; X32-NEXT:    movl %edx, 28(%ecx)
 ; X32-NEXT:    addl $88, %esp
+; X32-NEXT:   .cfi_def_cfa_offset 20
 ; X32-NEXT:    popl %esi
+; X32-NEXT:   .cfi_def_cfa_offset 16
 ; X32-NEXT:    popl %edi
+; X32-NEXT:   .cfi_def_cfa_offset 12
 ; X32-NEXT:    popl %ebx
+; X32-NEXT:   .cfi_def_cfa_offset 8
 ; X32-NEXT:    popl %ebp
+; X32-NEXT:   .cfi_def_cfa_offset 4
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test:
@@ -421,8 +426,11 @@ define void @test(i256* %a, i256* %b, i256* %out) #0 {
 ; X64-NEXT:    movq %rax, 16(%r9)
 ; X64-NEXT:    movq %rdx, 24(%r9)
 ; X64-NEXT:    popq %rbx
+; X64-NEXT:    .cfi_def_cfa_offset 24
 ; X64-NEXT:    popq %r14
+; X64-NEXT:    .cfi_def_cfa_offset 16
 ; X64-NEXT:    popq %r15
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
 entry:
   %av = load i256, i256* %a

test/CodeGen/X86/mul128.ll

@@ -86,10 +86,15 @@ define i128 @foo(i128 %t, i128 %u) {
 ; X86-NEXT:    movl %edx, 12(%ecx)
 ; X86-NEXT:    movl %ecx, %eax
 ; X86-NEXT:    addl $8, %esp
+; X86-NEXT:   .cfi_def_cfa_offset 20
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 16
 ; X86-NEXT:    popl %edi
+; X86-NEXT:   .cfi_def_cfa_offset 12
 ; X86-NEXT:    popl %ebx
+; X86-NEXT:   .cfi_def_cfa_offset 8
 ; X86-NEXT:    popl %ebp
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl $4
   %k = mul i128 %t, %u
   ret i128 %k

test/CodeGen/X86/pr21792.ll

@@ -28,6 +28,7 @@ define void @func(<4 x float> %vx) {
 ; CHECK-NEXT:    leaq stuff+8(%r9), %r9
 ; CHECK-NEXT:    callq toto
 ; CHECK-NEXT:    popq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
 entry:
   %tmp2 = bitcast <4 x float> %vx to <2 x i64>

test/CodeGen/X86/pr29061.ll

@@ -15,6 +15,7 @@ define void @t1(i8 signext %c) {
 ; CHECK-NEXT:    #APP
 ; CHECK-NEXT:    #NO_APP
 ; CHECK-NEXT:    popl %edi
+; CHECK-NEXT:   .cfi_def_cfa_offset 4
 ; CHECK-NEXT:    retl
 entry:
   tail call void asm sideeffect "", "{di},~{dirflag},~{fpsr},~{flags}"(i8 %c)
@@ -32,6 +33,7 @@ define void @t2(i8 signext %c) {
 ; CHECK-NEXT:    #APP
 ; CHECK-NEXT:    #NO_APP
 ; CHECK-NEXT:    popl %esi
+; CHECK-NEXT:   .cfi_def_cfa_offset 4
 ; CHECK-NEXT:    retl
 entry:
   tail call void asm sideeffect "", "{si},~{dirflag},~{fpsr},~{flags}"(i8 %c)

test/CodeGen/X86/pr29112.ll

@@ -65,6 +65,7 @@ define <4 x float> @bar(<4 x float>* %a1p, <4 x float>* %a2p, <4 x float> %a3, <
 ; CHECK-NEXT:    vaddps {{[0-9]+}}(%rsp), %xmm1, %xmm1 # 16-byte Folded Reload
 ; CHECK-NEXT:    vaddps %xmm0, %xmm1, %xmm0
 ; CHECK-NEXT:    addq $88, %rsp
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
   %a1 = shufflevector <16 x float>%c1, <16 x float>%c2, <4 x i32> <i32 4, i32 20, i32 1, i32 17>
 

test/CodeGen/X86/pr30430.ll

@@ -108,6 +108,7 @@ define <16 x float> @makefloat(float %f1, float %f2, float %f3, float %f4, float
 ; CHECK-NEXT:    vmovss %xmm14, (%rsp) # 4-byte Spill
 ; CHECK-NEXT:    movq %rbp, %rsp
 ; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
 ; CHECK-NEXT:    retq
 entry:
   %__A.addr.i = alloca float, align 4

test/CodeGen/X86/pr32241.ll

@@ -50,7 +50,9 @@ define i32 @_Z3foov() {
 ; CHECK-NEXT:    movw %dx, {{[0-9]+}}(%esp)
 ; CHECK-NEXT:    movzwl {{[0-9]+}}(%esp), %eax
 ; CHECK-NEXT:    addl $16, %esp
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    popl %esi
+; CHECK-NEXT:    .cfi_def_cfa_offset 4
 ; CHECK-NEXT:    retl
 entry:
   %aa = alloca i16, align 2

test/CodeGen/X86/pr32256.ll

@@ -27,6 +27,7 @@ define void @_Z1av() {
 ; CHECK-NEXT:    andb $1, %al
 ; CHECK-NEXT:    movb %al, {{[0-9]+}}(%esp)
 ; CHECK-NEXT:    addl $2, %esp
+; CHECK-NEXT:    .cfi_def_cfa_offset 4
 ; CHECK-NEXT:    retl
 entry:
   %b = alloca i8, align 1

test/CodeGen/X86/pr32282.ll

@@ -43,6 +43,7 @@ define void @foo() {
 ; X86-NEXT:    orl %eax, %edx
 ; X86-NEXT:    setne {{[0-9]+}}(%esp)
 ; X86-NEXT:    popl %eax
+; X86-NEXT:    .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: foo:

test/CodeGen/X86/pr32284.ll

@@ -71,6 +71,7 @@ define void @foo() {
 ; 686-O0-NEXT:    movzbl %al, %ecx
 ; 686-O0-NEXT:    movl %ecx, (%esp)
 ; 686-O0-NEXT:    addl $8, %esp
+; 686-O0-NEXT:    .cfi_def_cfa_offset 4
 ; 686-O0-NEXT:    retl
 ;
 ; 686-LABEL: foo:
@@ -88,6 +89,7 @@ define void @foo() {
 ; 686-NEXT:    setle %dl
 ; 686-NEXT:    movl %edx, {{[0-9]+}}(%esp)
 ; 686-NEXT:    addl $8, %esp
+; 686-NEXT:    .cfi_def_cfa_offset 4
 ; 686-NEXT:    retl
 entry:
   %a = alloca i8, align 1
@@ -232,10 +234,15 @@ define void @f1() {
 ; 686-O0-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
 ; 686-O0-NEXT:    movl %esi, (%esp) # 4-byte Spill
 ; 686-O0-NEXT:    addl $36, %esp
+; 686-O0-NEXT:    .cfi_def_cfa_offset 20
 ; 686-O0-NEXT:    popl %esi
+; 686-O0-NEXT:    .cfi_def_cfa_offset 16
 ; 686-O0-NEXT:    popl %edi
+; 686-O0-NEXT:    .cfi_def_cfa_offset 12
 ; 686-O0-NEXT:    popl %ebx
+; 686-O0-NEXT:    .cfi_def_cfa_offset 8
 ; 686-O0-NEXT:    popl %ebp
+; 686-O0-NEXT:    .cfi_def_cfa_offset 4
 ; 686-O0-NEXT:    retl
 ;
 ; 686-LABEL: f1:
@@ -277,8 +284,11 @@ define void @f1() {
 ; 686-NEXT:    movl %eax, _ZN8struct_210member_2_0E
 ; 686-NEXT:    movl $0, _ZN8struct_210member_2_0E+4
 ; 686-NEXT:    addl $1, %esp
+; 686-NEXT:    .cfi_def_cfa_offset 12
 ; 686-NEXT:    popl %esi
+; 686-NEXT:    .cfi_def_cfa_offset 8
 ; 686-NEXT:    popl %edi
+; 686-NEXT:    .cfi_def_cfa_offset 4
 ; 686-NEXT:    retl
 entry:
   %a = alloca i8, align 1
@@ -392,8 +402,11 @@ define void @f2() {
 ; 686-O0-NEXT:    movw %cx, %di
 ; 686-O0-NEXT:    movw %di, (%eax)
 ; 686-O0-NEXT:    addl $2, %esp
+; 686-O0-NEXT:    .cfi_def_cfa_offset 12
 ; 686-O0-NEXT:    popl %esi
+; 686-O0-NEXT:    .cfi_def_cfa_offset 8
 ; 686-O0-NEXT:    popl %edi
+; 686-O0-NEXT:    .cfi_def_cfa_offset 4
 ; 686-O0-NEXT:    retl
 ;
 ; 686-LABEL: f2:
@@ -414,6 +427,7 @@ define void @f2() {
 ; 686-NEXT:    sete %dl
 ; 686-NEXT:    movw %dx, (%eax)
 ; 686-NEXT:    addl $2, %esp
+; 686-NEXT:    .cfi_def_cfa_offset 4
 ; 686-NEXT:    retl
 entry:
   %a = alloca i16, align 2
@@ -532,6 +546,7 @@ define void @f3() #0 {
 ; 686-O0-NEXT:    popl %esi
 ; 686-O0-NEXT:    popl %edi
 ; 686-O0-NEXT:    popl %ebp
+; 686-O0-NEXT:    .cfi_def_cfa %esp, 4
 ; 686-O0-NEXT:    retl
 ;
 ; 686-LABEL: f3:
@@ -558,6 +573,7 @@ define void @f3() #0 {
 ; 686-NEXT:    movl %ecx, var_46
 ; 686-NEXT:    movl %ebp, %esp
 ; 686-NEXT:    popl %ebp
+; 686-NEXT:    .cfi_def_cfa %esp, 4
 ; 686-NEXT:    retl
 entry:
   %a = alloca i64, align 8

test/CodeGen/X86/pr32329.ll

@@ -57,9 +57,13 @@ define void @foo() local_unnamed_addr {
 ; X86-NEXT:    imull %eax, %ebx
 ; X86-NEXT:    movb %bl, var_218
 ; X86-NEXT:    popl %esi
+; X86-NEXT:    .cfi_def_cfa_offset 16
 ; X86-NEXT:    popl %edi
+; X86-NEXT:    .cfi_def_cfa_offset 12
 ; X86-NEXT:    popl %ebx
+; X86-NEXT:    .cfi_def_cfa_offset 8
 ; X86-NEXT:    popl %ebp
+; X86-NEXT:    .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: foo:

test/CodeGen/X86/pr32345.ll

@@ -84,6 +84,7 @@ define void @foo() {
 ; 6860-NEXT:    popl %edi
 ; 6860-NEXT:    popl %ebx
 ; 6860-NEXT:    popl %ebp
+; 6860-NEXT:    .cfi_def_cfa %esp, 4
 ; 6860-NEXT:    retl
 ;
 ; X64-LABEL: foo:
@@ -127,6 +128,7 @@ define void @foo() {
 ; 686-NEXT:    movb %dl, (%eax)
 ; 686-NEXT:    movl %ebp, %esp
 ; 686-NEXT:    popl %ebp
+; 686-NEXT:    .cfi_def_cfa %esp, 4
 ; 686-NEXT:    retl
 bb:
   %tmp = alloca i64, align 8

test/CodeGen/X86/pr32451.ll

@@ -30,7 +30,9 @@ define i8** @japi1_convert_690(i8**, i8***, i32) {
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
 ; CHECK-NEXT:    movl %eax, (%ecx)
 ; CHECK-NEXT:    addl $16, %esp
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    popl %ebx
+; CHECK-NEXT:    .cfi_def_cfa_offset 4
 ; CHECK-NEXT:    retl
 top:
   %3 = alloca i8***

test/CodeGen/X86/pr34088.ll

@@ -27,6 +27,7 @@ define i32 @pr34088() local_unnamed_addr {
 ; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%esp)
 ; CHECK-NEXT:    movl %ebp, %esp
 ; CHECK-NEXT:    popl %ebp
+; CHECK-NEXT:    .cfi_def_cfa %esp, 4
 ; CHECK-NEXT:    retl
 entry:
   %foo = alloca %struct.Foo, align 4

test/CodeGen/X86/pr9743.ll

@@ -11,4 +11,5 @@ define void @f() {
 ; CHECK-NEXT:  movq    %rsp, %rbp
 ; CHECK-NEXT:  .cfi_def_cfa_register %rbp
 ; CHECK-NEXT:  popq    %rbp
+; CHECK-NEXT:  .cfi_def_cfa %rsp, 8
 ; CHECK-NEXT:  ret

test/CodeGen/X86/push-cfi-debug.ll

@@ -23,8 +23,10 @@ declare x86_stdcallcc void @stdfoo(i32, i32) #0
 ; CHECK: .cfi_adjust_cfa_offset 4
 ; CHECK: calll stdfoo
 ; CHECK: .cfi_adjust_cfa_offset -8
-; CHECK: addl $20, %esp
+; CHECK: addl $8, %esp
 ; CHECK: .cfi_adjust_cfa_offset -8
+; CHECK: addl $12, %esp
+; CHECK: .cfi_def_cfa_offset 4
 define void @test1() #0 !dbg !4 {
 entry:
   tail call void @foo(i32 1, i32 2) #1, !dbg !10

test/CodeGen/X86/push-cfi-obj.ll

@@ -12,7 +12,7 @@
 ; LINUX-NEXT:    ]
 ; LINUX-NEXT:    Address: 0x0
 ; LINUX-NEXT:    Offset: 0x68
-; LINUX-NEXT:    Size: 64
+; LINUX-NEXT:    Size: 72
 ; LINUX-NEXT:    Link: 0
 ; LINUX-NEXT:    Info: 0
 ; LINUX-NEXT:    AddressAlignment: 4
@@ -22,8 +22,9 @@
 ; LINUX-NEXT:    SectionData (
 ; LINUX-NEXT:      0000: 1C000000 00000000 017A504C 5200017C  |.........zPLR..||
 ; LINUX-NEXT:      0010: 08070000 00000000 1B0C0404 88010000  |................|
-; LINUX-NEXT:      0020: 1C000000 24000000 00000000 1D000000  |....$...........|
+; LINUX-NEXT:      0020: 24000000 24000000 00000000 1D000000  |$...$...........|
 ; LINUX-NEXT:      0030: 04000000 00410E08 8502420D 05432E10  |.....A....B..C..|
+; LINUX-NEXT:      0040: 540C0404 410C0508                    |T...A...|
 ; LINUX-NEXT:    )
 
 declare i32 @__gxx_personality_v0(...)
@@ -35,7 +36,7 @@ entry:
           to label %continue unwind label %cleanup
 continue:
   ret void
-cleanup:  
+cleanup:
   landingpad { i8*, i32 }
      cleanup
   ret void

test/CodeGen/X86/push-cfi.ll

@@ -74,8 +74,9 @@ cleanup:
 ; LINUX-NEXT: pushl   $1
 ; LINUX-NEXT: .cfi_adjust_cfa_offset 4
 ; LINUX-NEXT: call
-; LINUX-NEXT: addl $28, %esp
+; LINUX-NEXT: addl $16, %esp
 ; LINUX: .cfi_adjust_cfa_offset -16
+; LINUX: addl $12, %esp
 ; DARWIN-NOT: .cfi_escape
 ; DARWIN-NOT: pushl
 define void @test2_nofp() #0 personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {

test/CodeGen/X86/return-ext.ll

@@ -106,6 +106,7 @@ entry:
 ; CHECK: call
 ; CHECK-NEXT: movzbl
 ; CHECK-NEXT: {{pop|add}}
+; CHECK-NEXT: .cfi_def_cfa_offset {{4|8}}
 ; CHECK-NEXT: ret
 }
 
@@ -120,6 +121,7 @@ entry:
 ; CHECK: call
 ; CHECK-NEXT: movzbl
 ; CHECK-NEXT: {{pop|add}}
+; CHECK-NEXT: .cfi_def_cfa_offset {{4|8}}
 ; CHECK-NEXT: ret
 }
 
@@ -134,5 +136,6 @@ entry:
 ; CHECK: call
 ; CHECK-NEXT: movzwl
 ; CHECK-NEXT: {{pop|add}}
+; CHECK-NEXT: .cfi_def_cfa_offset {{4|8}}
 ; CHECK-NEXT: ret
 }

test/CodeGen/X86/rtm.ll

@@ -75,6 +75,7 @@ define void @f2(i32 %x) nounwind uwtable {
 ; X64-NEXT:    xabort $1
 ; X64-NEXT:    callq f1
 ; X64-NEXT:    popq %rax
+; X64-NEXT:    .cfi_def_cfa_offset 8
 ; X64-NEXT:    retq
 entry:
   %x.addr = alloca i32, align 4

test/CodeGen/X86/select-mmx.ll

@@ -48,6 +48,7 @@ define i64 @test47(i64 %arg)  {
 ; I32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; I32-NEXT:    movl %ebp, %esp
 ; I32-NEXT:    popl %ebp
+; I32-NEXT:   .cfi_def_cfa %esp, 4
 ; I32-NEXT:    retl
   %cond = icmp eq i64 %arg, 0
   %slct = select i1 %cond, x86_mmx bitcast (i64 7 to x86_mmx), x86_mmx bitcast (i64 0 to x86_mmx)
@@ -100,6 +101,7 @@ define i64 @test49(i64 %arg, i64 %x, i64 %y) {
 ; I32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; I32-NEXT:    movl %ebp, %esp
 ; I32-NEXT:    popl %ebp
+; I32-NEXT:   .cfi_def_cfa %esp, 4
 ; I32-NEXT:    retl
   %cond = icmp eq i64 %arg, 0
   %xmmx = bitcast i64 %x to x86_mmx

test/CodeGen/X86/setcc-lowering.ll

@@ -90,6 +90,7 @@ define void @pr26232(i64 %a, <16 x i1> %b) {
 ; KNL-32-NEXT:    jne .LBB1_1
 ; KNL-32-NEXT:  # BB#2: # %for_exit600
 ; KNL-32-NEXT:    popl %esi
+; KNL-32-NEXT:    .cfi_def_cfa_offset 4
 ; KNL-32-NEXT:    retl
 allocas:
   br label %for_test11.preheader

test/CodeGen/X86/shrink_vmul.ll

@@ -31,6 +31,7 @@ define void @mul_2xi8(i8* nocapture readonly %a, i8* nocapture readonly %b, i64
 ; X86-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
 ; X86-NEXT:    movq %xmm1, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_2xi8:
@@ -89,6 +90,7 @@ define void @mul_4xi8(i8* nocapture readonly %a, i8* nocapture readonly %b, i64
 ; X86-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
 ; X86-NEXT:    movdqu %xmm1, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_4xi8:
@@ -148,6 +150,7 @@ define void @mul_8xi8(i8* nocapture readonly %a, i8* nocapture readonly %b, i64
 ; X86-NEXT:    movdqu %xmm1, 16(%esi,%ecx,4)
 ; X86-NEXT:    movdqu %xmm0, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_8xi8:
@@ -220,6 +223,7 @@ define void @mul_16xi8(i8* nocapture readonly %a, i8* nocapture readonly %b, i64
 ; X86-NEXT:    movdqu %xmm4, 16(%esi,%ecx,4)
 ; X86-NEXT:    movdqu %xmm3, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_16xi8:
@@ -288,6 +292,7 @@ define void @mul_2xi16(i8* nocapture readonly %a, i8* nocapture readonly %b, i64
 ; X86-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
 ; X86-NEXT:    movq %xmm1, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_2xi16:
@@ -342,6 +347,7 @@ define void @mul_4xi16(i8* nocapture readonly %a, i8* nocapture readonly %b, i64
 ; X86-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
 ; X86-NEXT:    movdqu %xmm1, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_4xi16:
@@ -399,6 +405,7 @@ define void @mul_8xi16(i8* nocapture readonly %a, i8* nocapture readonly %b, i64
 ; X86-NEXT:    movdqu %xmm1, 16(%esi,%ecx,4)
 ; X86-NEXT:    movdqu %xmm0, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_8xi16:
@@ -469,6 +476,7 @@ define void @mul_16xi16(i8* nocapture readonly %a, i8* nocapture readonly %b, i6
 ; X86-NEXT:    movdqu %xmm2, 16(%esi,%ecx,4)
 ; X86-NEXT:    movdqu %xmm0, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_16xi16:
@@ -541,6 +549,7 @@ define void @mul_2xi8_sext(i8* nocapture readonly %a, i8* nocapture readonly %b,
 ; X86-NEXT:    psrad $16, %xmm0
 ; X86-NEXT:    movq %xmm0, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_2xi8_sext:
@@ -606,6 +615,7 @@ define void @mul_2xi8_sext_zext(i8* nocapture readonly %a, i8* nocapture readonl
 ; X86-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
 ; X86-NEXT:    movq %xmm0, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_2xi8_sext_zext:
@@ -666,6 +676,7 @@ define void @mul_2xi16_sext(i8* nocapture readonly %a, i8* nocapture readonly %b
 ; X86-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
 ; X86-NEXT:    movq %xmm1, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_2xi16_sext:
@@ -733,6 +744,7 @@ define void @mul_2xi16_sext_zext(i8* nocapture readonly %a, i8* nocapture readon
 ; X86-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
 ; X86-NEXT:    movq %xmm0, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_2xi16_sext_zext:
@@ -813,6 +825,7 @@ define void @mul_16xi16_sext(i8* nocapture readonly %a, i8* nocapture readonly %
 ; X86-NEXT:    movdqu %xmm2, 16(%esi,%ecx,4)
 ; X86-NEXT:    movdqu %xmm0, (%esi,%ecx,4)
 ; X86-NEXT:    popl %esi
+; X86-NEXT:   .cfi_def_cfa_offset 4
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: mul_16xi16_sext:

test/CodeGen/X86/statepoint-call-lowering.ll

@@ -83,6 +83,7 @@ define i1 @test_relocate(i32 addrspace(1)* %a) gc "statepoint-example" {
 ; CHECK: callq return_i1
 ; CHECK-NEXT: .Ltmp5:
 ; CHECK-NEXT: popq %rcx
+; CHECK-NEXT: .cfi_def_cfa_offset 8
 ; CHECK-NEXT: retq
 entry:
   %safepoint_token = tail call token (i64, i32, i1 ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_i1f(i64 0, i32 0, i1 ()* @return_i1, i32 0, i32 0, i32 0, i32 0, i32 addrspace(1)* %a)

test/CodeGen/X86/statepoint-gctransition-call-lowering.ll

@@ -69,6 +69,7 @@ define i1 @test_relocate(i32 addrspace(1)* %a) gc "statepoint-example" {
 ; CHECK: callq return_i1
 ; CHECK-NEXT: .Ltmp4:
 ; CHECK-NEXT: popq %rcx
+; CHECK-NEXT: .cfi_def_cfa_offset 8
 ; CHECK-NEXT: retq
 entry:
   %safepoint_token = tail call token (i64, i32, i1 ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_i1f(i64 0, i32 0, i1 ()* @return_i1, i32 0, i32 1, i32 0, i32 0, i32 addrspace(1)* %a)

test/CodeGen/X86/statepoint-invoke.ll

@@ -142,6 +142,7 @@ normal_return:
   ; CHECK-LABEL: %normal_return
   ; CHECK: xorl %eax, %eax
   ; CHECK-NEXT: popq
+  ; CHECK-NEXT: .cfi_def_cfa_offset 8
   ; CHECK-NEXT: retq
   %null.relocated = call coldcc i64 addrspace(1)* @llvm.experimental.gc.relocate.p1i64(token %sp1, i32 13, i32 13)
   %undef.relocated = call coldcc i64 addrspace(1)* @llvm.experimental.gc.relocate.p1i64(token %sp1, i32 14, i32 14)
@@ -169,6 +170,7 @@ entry:
 normal_return:
   ; CHECK: leaq
   ; CHECK-NEXT: popq
+  ; CHECK-NEXT: .cfi_def_cfa_offset 8
   ; CHECK-NEXT: retq
   %aa.rel = call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %sp, i32 13, i32 13)
   %aa.converted = bitcast i32 addrspace(1)* %aa.rel to i64 addrspace(1)*
@@ -177,6 +179,7 @@ normal_return:
 exceptional_return:
   ; CHECK: movl	$15
   ; CHECK-NEXT: popq
+  ; CHECK-NEXT: .cfi_def_cfa_offset 8
   ; CHECK-NEXT: retq
   %landing_pad = landingpad token
           cleanup

test/CodeGen/X86/throws-cfi-fp.ll

@@ -0,0 +1,98 @@
+; RUN: llc %s -o - | FileCheck %s
+
+; ModuleID = 'throws-cfi-fp.cpp'
+source_filename = "throws-cfi-fp.cpp"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+$__clang_call_terminate = comdat any
+
+@_ZL11ShouldThrow = internal unnamed_addr global i1 false, align 1
+@_ZTIi = external constant i8*
+@str = private unnamed_addr constant [20 x i8] c"Threw an exception!\00"
+
+; Function Attrs: uwtable
+define void @_Z6throwsv() #0 personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+
+; CHECK-LABEL:   _Z6throwsv:
+; CHECK:         popq %rbp
+; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
+; CHECK-NEXT:    retq
+; CHECK-NEXT:    .LBB0_1:
+; CHECK-NEXT:    .cfi_def_cfa %rbp, 16
+
+entry:
+  %.b5 = load i1, i1* @_ZL11ShouldThrow, align 1
+  br i1 %.b5, label %if.then, label %try.cont
+
+if.then:                                          ; preds = %entry
+  %exception = tail call i8* @__cxa_allocate_exception(i64 4)
+  %0 = bitcast i8* %exception to i32*
+  store i32 1, i32* %0, align 16
+  invoke void @__cxa_throw(i8* %exception, i8* bitcast (i8** @_ZTIi to i8*), i8* null)
+          to label %unreachable unwind label %lpad
+
+lpad:                                             ; preds = %if.then
+  %1 = landingpad { i8*, i32 }
+          catch i8* null
+  %2 = extractvalue { i8*, i32 } %1, 0
+  %3 = tail call i8* @__cxa_begin_catch(i8* %2)
+  %puts = tail call i32 @puts(i8* getelementptr inbounds ([20 x i8], [20 x i8]* @str, i64 0, i64 0))
+  invoke void @__cxa_rethrow()
+          to label %unreachable unwind label %lpad1
+
+lpad1:                                            ; preds = %lpad
+  %4 = landingpad { i8*, i32 }
+          cleanup
+  invoke void @__cxa_end_catch()
+          to label %eh.resume unwind label %terminate.lpad
+
+try.cont:                                         ; preds = %entry
+  ret void
+
+eh.resume:                                        ; preds = %lpad1
+  resume { i8*, i32 } %4
+
+terminate.lpad:                                   ; preds = %lpad1
+  %5 = landingpad { i8*, i32 }
+          catch i8* null
+  %6 = extractvalue { i8*, i32 } %5, 0
+  tail call void @__clang_call_terminate(i8* %6)
+  unreachable
+
+unreachable:                                      ; preds = %lpad, %if.then
+  unreachable
+}
+
+declare i8* @__cxa_allocate_exception(i64)
+
+declare void @__cxa_throw(i8*, i8*, i8*)
+
+declare i32 @__gxx_personality_v0(...)
+
+declare i8* @__cxa_begin_catch(i8*)
+
+declare void @__cxa_rethrow()
+
+declare void @__cxa_end_catch()
+
+; Function Attrs: noinline noreturn nounwind
+declare void @__clang_call_terminate(i8*)
+
+declare void @_ZSt9terminatev()
+
+; Function Attrs: nounwind
+declare i32 @puts(i8* nocapture readonly)
+
+attributes #0 = { "no-frame-pointer-elim"="true" }
+
+!llvm.dbg.cu = !{!2}
+!llvm.module.flags = !{!8, !9, !10}
+
+!2 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !3, producer: "clang version 6.0.0 (https://github.com/llvm-mirror/clang.git 316ebefb7fff8ad324a08a694347500b6cd7c95f) (https://github.com/llvm-mirror/llvm.git dcae9be81fc17cdfbe989402354d3c8ecd0a2c79)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, globals: !5)
+!3 = !DIFile(filename: "throws-cfi-fp.cpp", directory: "epilogue-dwarf/test")
+!4 = !{}
+!5 = !{}
+!8 = !{i32 2, !"Dwarf Version", i32 4}
+!9 = !{i32 2, !"Debug Info Version", i32 3}
+!10 = !{i32 1, !"wchar_size", i32 4}

test/CodeGen/X86/throws-cfi-no-fp.ll

@@ -0,0 +1,97 @@
+; RUN: llc %s -o - | FileCheck %s
+
+; ModuleID = 'throws-cfi-no-fp.cpp'
+source_filename = "throws-cfi-no-fp.cpp"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+$__clang_call_terminate = comdat any
+
+@_ZL11ShouldThrow = internal unnamed_addr global i1 false, align 1
+@_ZTIi = external constant i8*
+@str = private unnamed_addr constant [20 x i8] c"Threw an exception!\00"
+
+; Function Attrs: uwtable
+define void @_Z6throwsv() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+
+; CHECK-LABEL:   _Z6throwsv:
+; CHECK:         popq	%rbx
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
+; CHECK-NEXT:    .LBB0_1:
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+
+entry:
+  %.b5 = load i1, i1* @_ZL11ShouldThrow, align 1
+  br i1 %.b5, label %if.then, label %try.cont
+
+if.then:                                          ; preds = %entry
+  %exception = tail call i8* @__cxa_allocate_exception(i64 4)
+  %0 = bitcast i8* %exception to i32*
+  store i32 1, i32* %0, align 16
+  invoke void @__cxa_throw(i8* %exception, i8* bitcast (i8** @_ZTIi to i8*), i8* null)
+          to label %unreachable unwind label %lpad
+
+lpad:                                             ; preds = %if.then
+  %1 = landingpad { i8*, i32 }
+          catch i8* null
+  %2 = extractvalue { i8*, i32 } %1, 0
+  %3 = tail call i8* @__cxa_begin_catch(i8* %2)
+  %puts = tail call i32 @puts(i8* getelementptr inbounds ([20 x i8], [20 x i8]* @str, i64 0, i64 0))
+  invoke void @__cxa_rethrow() #4
+          to label %unreachable unwind label %lpad1
+
+lpad1:                                            ; preds = %lpad
+  %4 = landingpad { i8*, i32 }
+          cleanup
+  invoke void @__cxa_end_catch()
+          to label %eh.resume unwind label %terminate.lpad
+
+try.cont:                                         ; preds = %entry
+  ret void
+
+eh.resume:                                        ; preds = %lpad1
+  resume { i8*, i32 } %4
+
+terminate.lpad:                                   ; preds = %lpad1
+  %5 = landingpad { i8*, i32 }
+          catch i8* null
+  %6 = extractvalue { i8*, i32 } %5, 0
+  tail call void @__clang_call_terminate(i8* %6)
+  unreachable
+
+unreachable:                                      ; preds = %lpad, %if.then
+  unreachable
+}
+
+declare i8* @__cxa_allocate_exception(i64)
+
+declare void @__cxa_throw(i8*, i8*, i8*)
+
+declare i32 @__gxx_personality_v0(...)
+
+declare i8* @__cxa_begin_catch(i8*)
+
+declare void @__cxa_rethrow()
+
+declare void @__cxa_end_catch()
+
+; Function Attrs: noinline noreturn nounwind
+declare void @__clang_call_terminate(i8*)
+
+declare void @_ZSt9terminatev()
+
+
+; Function Attrs: nounwind
+declare i32 @puts(i8* nocapture readonly)
+
+!llvm.dbg.cu = !{!2}
+!llvm.module.flags = !{!8, !9, !10}
+
+!2 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !3, producer: "clang version 6.0.0 (https://github.com/llvm-mirror/clang.git 316ebefb7fff8ad324a08a694347500b6cd7c95f) (https://github.com/llvm-mirror/llvm.git dcae9be81fc17cdfbe989402354d3c8ecd0a2c79)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, globals: !5)
+!3 = !DIFile(filename: "throws-cfi-no-fp.cpp", directory: "epilogue-dwarf/test")
+!4 = !{}
+!5 = !{}
+!8 = !{i32 2, !"Dwarf Version", i32 4}
+!9 = !{i32 2, !"Debug Info Version", i32 3}
+!10 = !{i32 1, !"wchar_size", i32 4}

test/CodeGen/X86/vector-sext.ll

@@ -3333,11 +3333,17 @@ define <16 x i16> @load_sext_16i1_to_16i16(<16 x i1> *%ptr) {
 ; AVX1-NEXT:    vpinsrw $7, %ebp, %xmm1, %xmm1
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    popq %rbx
+; AVX1-NEXT:    .cfi_def_cfa_offset 48
 ; AVX1-NEXT:    popq %r12
+; AVX1-NEXT:    .cfi_def_cfa_offset 40
 ; AVX1-NEXT:    popq %r13
+; AVX1-NEXT:    .cfi_def_cfa_offset 32
 ; AVX1-NEXT:    popq %r14
+; AVX1-NEXT:    .cfi_def_cfa_offset 24
 ; AVX1-NEXT:    popq %r15
+; AVX1-NEXT:    .cfi_def_cfa_offset 16
 ; AVX1-NEXT:    popq %rbp
+; AVX1-NEXT:    .cfi_def_cfa_offset 8
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: load_sext_16i1_to_16i16:
@@ -3424,11 +3430,17 @@ define <16 x i16> @load_sext_16i1_to_16i16(<16 x i1> *%ptr) {
 ; AVX2-NEXT:    vpinsrw $7, %ebp, %xmm1, %xmm1
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    popq %rbx
+; AVX2-NEXT:    .cfi_def_cfa_offset 48
 ; AVX2-NEXT:    popq %r12
+; AVX2-NEXT:    .cfi_def_cfa_offset 40
 ; AVX2-NEXT:    popq %r13
+; AVX2-NEXT:    .cfi_def_cfa_offset 32
 ; AVX2-NEXT:    popq %r14
+; AVX2-NEXT:    .cfi_def_cfa_offset 24
 ; AVX2-NEXT:    popq %r15
+; AVX2-NEXT:    .cfi_def_cfa_offset 16
 ; AVX2-NEXT:    popq %rbp
+; AVX2-NEXT:    .cfi_def_cfa_offset 8
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: load_sext_16i1_to_16i16:
@@ -4824,6 +4836,7 @@ define i32 @sext_2i8_to_i32(<16 x i8> %A) nounwind uwtable readnone ssp {
 ; X32-SSE41-NEXT:    pmovsxbw %xmm0, %xmm0
 ; X32-SSE41-NEXT:    movd %xmm0, %eax
 ; X32-SSE41-NEXT:    popl %ecx
+; X32-SSE41-NEXT:    .cfi_def_cfa_offset 4
 ; X32-SSE41-NEXT:    retl
 entry:
   %Shuf = shufflevector <16 x i8> %A, <16 x i8> undef, <2 x i32> <i32 0, i32 1>

test/CodeGen/X86/vector-shuffle-avx512.ll

@@ -619,6 +619,7 @@ define <64 x i8> @test_mm512_mask_blend_epi8(<64 x i8> %A, <64 x i8> %W){
 ; KNL32-NEXT:    vpblendvb %ymm3, 8(%ebp), %ymm1, %ymm1
 ; KNL32-NEXT:    movl %ebp, %esp
 ; KNL32-NEXT:    popl %ebp
+; KNL32-NEXT:   .cfi_def_cfa %esp, 4
 ; KNL32-NEXT:    retl
 entry:
   %0 = shufflevector <64 x i8> %A, <64 x i8> %W, <64 x i32>  <i32 64, i32 1, i32 66, i32 3, i32 68, i32 5, i32 70, i32 7, i32 72, i32 9, i32 74, i32 11, i32 76, i32 13, i32 78, i32 15, i32 80, i32 17, i32 82, i32 19, i32 84, i32 21, i32 86, i32 23, i32 88, i32 25, i32 90, i32 27, i32 92, i32 29, i32 94, i32 31, i32 96, i32 33, i32 98, i32 35, i32 100, i32 37, i32 102, i32 39, i32 104, i32 41, i32 106, i32 43, i32 108, i32 45, i32 110, i32 47, i32 112, i32 49, i32 114, i32 51, i32 116, i32 53, i32 118, i32 55, i32 120, i32 57, i32 122, i32 59, i32 124, i32 61, i32 126, i32 63>
@@ -659,6 +660,7 @@ define <32 x i16> @test_mm512_mask_blend_epi16(<32 x i16> %A, <32 x i16> %W){
 ; KNL32-NEXT:    vpblendw {{.*#+}} ymm1 = mem[0],ymm1[1],mem[2],ymm1[3],mem[4],ymm1[5],mem[6],ymm1[7],mem[8],ymm1[9],mem[10],ymm1[11],mem[12],ymm1[13],mem[14],ymm1[15]
 ; KNL32-NEXT:    movl %ebp, %esp
 ; KNL32-NEXT:    popl %ebp
+; KNL32-NEXT:   .cfi_def_cfa %esp, 4
 ; KNL32-NEXT:    retl
 entry:
   %0 = shufflevector <32 x i16> %A, <32 x i16> %W, <32 x i32>  <i32 32, i32 1, i32 34, i32 3, i32 36, i32 5, i32 38, i32 7, i32 40, i32 9, i32 42, i32 11, i32 44, i32 13, i32 46, i32 15, i32 48, i32 17, i32 50, i32 19, i32 52, i32 21, i32 54, i32 23, i32 56, i32 25, i32 58, i32 27, i32 60, i32 29, i32 62, i32 31>

test/CodeGen/X86/vector-shuffle-v1.ll

@@ -630,6 +630,7 @@ define i64 @shuf64i1_zero(i64 %a) {
 ; AVX512F-NEXT:    orq %rcx, %rax
 ; AVX512F-NEXT:    movq %rbp, %rsp
 ; AVX512F-NEXT:    popq %rbp
+; AVX512F-NEXT:    .cfi_def_cfa %rsp, 8
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
@@ -662,6 +663,7 @@ define i64 @shuf64i1_zero(i64 %a) {
 ; AVX512VL-NEXT:    orq %rcx, %rax
 ; AVX512VL-NEXT:    movq %rbp, %rsp
 ; AVX512VL-NEXT:    popq %rbp
+; AVX512VL-NEXT:    .cfi_def_cfa %rsp, 8
 ; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;

test/CodeGen/X86/wide-integer-cmp.ll

@@ -105,10 +105,13 @@ define i32 @test_wide(i128 %a, i128 %b) {
 ; CHECK-NEXT:  # BB#1: # %bb1
 ; CHECK-NEXT:    movl $1, %eax
 ; CHECK-NEXT:    popl %esi
+; CHECK-NEXT:    .cfi_def_cfa_offset 4
 ; CHECK-NEXT:    retl
 ; CHECK-NEXT:  .LBB4_2: # %bb2
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    movl $2, %eax
 ; CHECK-NEXT:    popl %esi
+; CHECK-NEXT:    .cfi_def_cfa_offset 4
 ; CHECK-NEXT:    retl
 entry:
   %cmp = icmp slt i128 %a, %b

test/CodeGen/X86/x86-framelowering-trap.ll

@@ -6,6 +6,7 @@ target triple = "x86_64-unknown-linux-gnu"
 ; CHECK: pushq
 ; CHECK: ud2
 ; CHECK-NEXT: popq
+; CHECK-NEXT: .cfi_def_cfa_offset 8
 ; CHECK-NEXT: retq
 define void @bar() {
 entry:

test/CodeGen/X86/x86-interleaved-access.ll

@@ -1816,6 +1816,7 @@ define void @interleaved_store_vf64_i8_stride4(<64 x i8> %a, <64 x i8> %b, <64 x
 ; AVX1-NEXT:    vmovaps %ymm9, 64(%rdi)
 ; AVX1-NEXT:    vmovaps %ymm8, (%rdi)
 ; AVX1-NEXT:    addq $24, %rsp
+; AVX1-NEXT:    .cfi_def_cfa_offset 8
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;

test/CodeGen/X86/x86-no_caller_saved_registers-preserve.ll

@@ -20,6 +20,7 @@ define x86_64_sysvcc i32 @bar(i32 %a0, i32 %a1, float %b0) #0 {
 ; CHECK-NEXT:    movl $4, %eax
 ; CHECK-NEXT:    movaps -{{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
 ; CHECK-NEXT:    popq %rdx
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
   call void asm sideeffect "", "~{rax},~{rdx},~{xmm1},~{rdi},~{rsi},~{xmm0}"()
   ret i32 4