[MCAsmInfo] Support UsesCFIForDebug for targets with no exception handling

[RamNalamothu]

Summary

This change enables emitting CFI unwind information for debugging purpose
for targets with MCAsmInfo::ExceptionsType == ExceptionHandling::None.

Enable this option for AMDGPU to prepare for future patches which add
complete CFI support.

Currently generating CFI unwind information is entangled with supporting
the exceptions, even when AsmPrinter explicitly recognizes that the unwind
tables are being generated as debug information.

In fact, the unwind information is not generated even if we specify
--force-dwarf-frame-section, unless exceptions are enabled. The LIT test
llvm/test/CodeGen/AMDGPU/debug_frame.ll demonstrates this behavior.

[RamNalamothu]

Abandoning this draft revision as this is not meant for review and the indented purpose is over.

llvm/include/llvm/CodeGen/AsmPrinter.h

public:
   /// Get the CFISection type for a function.
   CFISection getFunctionCFISectionType(const MachineFunction &MF) const;
 
   /// Get the CFISection type for the module.
   CFISection getModuleCFISectionType() const { return ModuleCFISection; }
 
   bool needsSEHMoves();
 
+  /// Since emitting CFI unwind information is entangled with supporting the
+  /// exceptions, this returns true for platforms which use CFI unwind
+  /// information for debugging purpose when
+  /// `MCAsmInfo::ExceptionsType == ExceptionHandling::None`.
+  bool needsCFIForDebug() const;
+
   /// Print to the current output stream assembly representations of the
   /// constants in the constant pool MCP. This is used to print out constants
   /// which have been "spilled to memory" by the code generator.
   virtual void emitConstantPool();
 
   /// Print assembly representations of the jump tables used by the current
   /// function to the current output stream.
   virtual void emitJumpTableInfo();

llvm/include/llvm/MC/MCAsmInfo.h

protected:
 
   /// True if target supports emission of debugging information.  Defaults to
   /// false.
   bool SupportsDebugInformation = false;
 
   /// Exception handling format for the target.  Defaults to None.
   ExceptionHandling ExceptionsType = ExceptionHandling::None;
 
+  /// True if target uses CFI unwind information for debugging purpose when
+  /// `ExceptionsType == ExceptionHandling::None`.
+  bool UsesCFIForDebug = false;
+
   /// Windows exception handling data (.pdata) encoding.  Defaults to Invalid.
   WinEH::EncodingType WinEHEncodingType = WinEH::EncodingType::Invalid;
 
   /// True if Dwarf2 output generally uses relocations for references to other
   /// .debug_* sections.
   bool DwarfUsesRelocationsAcrossSections = true;
 
   /// True if DWARF FDE symbol reference relocations should be replaced by an
public:
 
   ExceptionHandling getExceptionHandlingType() const { return ExceptionsType; }
   WinEH::EncodingType getWinEHEncodingType() const { return WinEHEncodingType; }
 
   void setExceptionsType(ExceptionHandling EH) {
     ExceptionsType = EH;
   }
 
+  bool doesUseCFIForDebug() const {
+    return UsesCFIForDebug;
+  }
+
   /// Returns true if the exception handling method for the platform uses call
   /// frame information to unwind.
   bool usesCFIForEH() const {
     return (ExceptionsType == ExceptionHandling::DwarfCFI ||
             ExceptionsType == ExceptionHandling::ARM || usesWindowsCFI());
   }
 
   bool usesWindowsCFI() const {

llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp

bool AsmPrinter::doInitialization(Module &M) {
 
   if (M.getNamedMetadata(PseudoProbeDescMetadataName)) {
     PP = new PseudoProbeHandler(this, &M);
     Handlers.emplace_back(std::unique_ptr<PseudoProbeHandler>(PP), PPTimerName,
                           PPTimerDescription, PPGroupName, PPGroupDescription);
   }
 
   switch (MAI->getExceptionHandlingType()) {
+  case ExceptionHandling::None:
+    // We may want to emit CFI for debug.
+    LLVM_FALLTHROUGH;
   case ExceptionHandling::SjLj:
   case ExceptionHandling::DwarfCFI:
   case ExceptionHandling::ARM:
     for (auto &F : M.getFunctionList()) {
       if (getFunctionCFISectionType(F) != CFISection::None)
         ModuleCFISection = getFunctionCFISectionType(F);
       // If any function needsUnwindTableEntry(), it needs .eh_frame and hence
       // the module needs .eh_frame. If we have found that case, we are done.
       if (ModuleCFISection == CFISection::EH)
         break;
     }
     assert(MAI->getExceptionHandlingType() == ExceptionHandling::DwarfCFI ||
            ModuleCFISection != CFISection::EH);
     break;
   default:
     break;
   }
 
   EHStreamer *ES = nullptr;
   switch (MAI->getExceptionHandlingType()) {
   case ExceptionHandling::None:
+    if (!needsCFIForDebug())
       break;
+    LLVM_FALLTHROUGH;
   case ExceptionHandling::SjLj:
   case ExceptionHandling::DwarfCFI:
     ES = new DwarfCFIException(this);
     break;
   case ExceptionHandling::ARM:
     ES = new ARMException(this);
     break;
   case ExceptionHandling::WinEH:

 AsmPrinter::getFunctionCFISectionType(const MachineFunction &MF) const {
   return getFunctionCFISectionType(MF.getFunction());
 }
 
 bool AsmPrinter::needsSEHMoves() {
   return MAI->usesWindowsCFI() && MF->getFunction().needsUnwindTableEntry();
 }
 
+bool AsmPrinter::needsCFIForDebug() const {
+  return MAI->getExceptionHandlingType() == ExceptionHandling::None &&
+         MAI->doesUseCFIForDebug() && ModuleCFISection == CFISection::Debug;
+}
+
 void AsmPrinter::emitCFIInstruction(const MachineInstr &MI) {
   ExceptionHandling ExceptionHandlingType = MAI->getExceptionHandlingType();
-  if (ExceptionHandlingType != ExceptionHandling::DwarfCFI &&
+  if (!needsCFIForDebug() &&
+      ExceptionHandlingType != ExceptionHandling::DwarfCFI &&
       ExceptionHandlingType != ExceptionHandling::ARM)
     return;
 
   if (getFunctionCFISectionType(*MF) == CFISection::None)
     return;
 
   // If there is no "real" instruction following this CFI instruction, skip
   // emitting it; it would be beyond the end of the function's FDE range.

llvm/lib/CodeGen/AsmPrinter/DwarfCFIException.cpp

shouldEmitPersonality =
       (forceEmitPersonality ||
        (hasLandingPads && PerEncoding != dwarf::DW_EH_PE_omit)) &&
       Per;
 
   unsigned LSDAEncoding = TLOF.getLSDAEncoding();
   shouldEmitLSDA = shouldEmitPersonality &&
     LSDAEncoding != dwarf::DW_EH_PE_omit;
 
-  shouldEmitCFI = MF->getMMI().getContext().getAsmInfo()->usesCFIForEH() &&
-                  (shouldEmitPersonality || shouldEmitMoves);
+  const MCAsmInfo &MAI = *MF->getMMI().getContext().getAsmInfo();
+  if (MAI.getExceptionHandlingType() != ExceptionHandling::None)
+    shouldEmitCFI =
+        MAI.usesCFIForEH() && (shouldEmitPersonality || shouldEmitMoves);
+  else
+    shouldEmitCFI = Asm->needsCFIForDebug() && shouldEmitMoves;
+
   beginFragment(&*MF->begin(), getExceptionSym);
 }
 
 void DwarfCFIException::beginFragment(const MachineBasicBlock *MBB,
                                       ExceptionSymbolProvider ESP) {
   if (!shouldEmitCFI)
     return;
 

llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCAsmInfo.cpp

AMDGPUMCAsmInfo::AMDGPUMCAsmInfo(const Triple &TT,
   UsesELFSectionDirectiveForBSS = true;
 
   //===--- Global Variable Emission Directives --------------------------===//
   HasAggressiveSymbolFolding = true;
   COMMDirectiveAlignmentIsInBytes = false;
   HasNoDeadStrip = true;
   //===--- Dwarf Emission Directives -----------------------------------===//
   SupportsDebugInformation = true;
+  UsesCFIForDebug = true;
   DwarfRegNumForCFI = true;
 
   UseIntegratedAssembler = false;
 }
 
 bool AMDGPUMCAsmInfo::shouldOmitSectionDirective(StringRef SectionName) const {
   return SectionName == ".hsatext" || SectionName == ".hsadata_global_agent" ||
          SectionName == ".hsadata_global_program" ||

llvm/test/CodeGen/AMDGPU/debug_frame.ll

 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -filetype=obj -o - < %s | llvm-readelf -S - | FileCheck --check-prefixes=NOEXCEPTIONS_NOFORCE-DEBUG %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -filetype=obj --force-dwarf-frame-section -o - < %s | llvm-readelf -S - | FileCheck --check-prefixes=NOEXCEPTIONS_FORCE-DEBUG %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -filetype=obj --exception-model=dwarf -o - < %s | llvm-readelf -S - | FileCheck --check-prefixes=EXCEPTIONS_NOFORCE-DEBUG %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -filetype=obj --force-dwarf-frame-section --exception-model=dwarf -o - < %s | llvm-readelf -S - | FileCheck --check-prefixes=EXCEPTIONS_FORCE-DEBUG %s
 
-; Test that demonstrates we produce a .debug_frame only when exceptions are enabled even if --force-dwarf-frame-section is enabled
-
-; NOEXCEPTIONS_NOFORCE-DEBUG-NOT: .debug_frame
-; NOEXCEPTIONS_FORCE-DEBUG-NOT: .debug_frame
+; NOEXCEPTIONS_NOFORCE-DEBUG: .debug_frame
+; NOEXCEPTIONS_FORCE-DEBUG: .debug_frame
 ; EXCEPTIONS_NOFORCE-DEBUG: .debug_frame
 ; EXCEPTIONS_FORCE-DEBUG: .debug_frame
 
 define void @f() nounwind !dbg !0 {
 entry:
   ret void
 }
 

llvm/test/CodeGen/AMDGPU/split-arg-dbg-value.ll

 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
 ; Make sure dbg_value reports something for argument registers when they are split into multiple registers
 
 define hidden <4 x float> @split_v4f32_arg(<4 x float> returned %arg) local_unnamed_addr #0 !dbg !7 {
 ; GCN-LABEL: split_v4f32_arg:
 ; GCN:       .Lfunc_begin0:
 ; GCN-NEXT:    .file 0
 ; GCN-NEXT:    .loc 0 3 0 ; /tmp/dbg.cl:3:0
+; GCN-NEXT:    .cfi_sections .debug_frame
+; GCN-NEXT:    .cfi_startproc
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 96 32] $vgpr3
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 64 32] $vgpr2
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp0:
 ; GCN-NEXT:    .loc 0 4 5 prologue_end ; /tmp/dbg.cl:4:5
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
 ; GCN-NEXT:  .Ltmp1:
+; GCN:    .cfi_endproc
   call void @llvm.dbg.value(metadata <4 x float> %arg, metadata !18, metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !19
   ret <4 x float> %arg, !dbg !20
 }
 
 define hidden <4 x float> @split_v4f32_multi_arg(<4 x float> %arg0, <2 x float> %arg1) local_unnamed_addr #0 !dbg !21 {
 ; GCN-LABEL: split_v4f32_multi_arg:
 ; GCN:       .Lfunc_begin1:
 ; GCN-NEXT:    .loc 0 7 0 ; /tmp/dbg.cl:7:0
+; GCN-NEXT:    .cfi_startproc
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_multi_arg:arg1 <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr5
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_multi_arg:arg1 <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr4
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_multi_arg:arg0 <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 96 32] $vgpr3
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_multi_arg:arg0 <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 64 32] $vgpr2
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_multi_arg:arg0 <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_multi_arg:arg0 <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp2:
 ; GCN-NEXT:    .loc 0 8 17 prologue_end ; /tmp/dbg.cl:8:17
 ; GCN-NEXT:    v_add_f32_e32 v0, v4, v0
 ; GCN-NEXT:  .Ltmp3:
 ; GCN-NEXT:    v_add_f32_e32 v1, v5, v1
 ; GCN-NEXT:  .Ltmp4:
 ; GCN-NEXT:    v_add_f32_e32 v2, v4, v2
 ; GCN-NEXT:  .Ltmp5:
 ; GCN-NEXT:    v_add_f32_e32 v3, v5, v3
 ; GCN-NEXT:  .Ltmp6:
 ; GCN-NEXT:    .loc 0 8 5 is_stmt 0 ; /tmp/dbg.cl:8:5
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
 ; GCN-NEXT:  .Ltmp7:
+; GCN:    .cfi_endproc
   call void @llvm.dbg.value(metadata <4 x float> %arg0, metadata !29, metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !31
   call void @llvm.dbg.value(metadata <2 x float> %arg1, metadata !30, metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !31
   %tmp = shufflevector <2 x float> %arg1, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>, !dbg !32
   %add = fadd <4 x float> %tmp, %arg0, !dbg !33
   ret <4 x float> %add, !dbg !34
 }
 
 define hidden <4 x half> @split_v4f16_arg(<4 x half> returned %arg) local_unnamed_addr #0 !dbg !35 {
 ; GCN-LABEL: split_v4f16_arg:
 ; GCN:       .Lfunc_begin2:
 ; GCN-NEXT:    .loc 0 11 0 is_stmt 1 ; /tmp/dbg.cl:11:0
+; GCN-NEXT:    .cfi_startproc
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f16_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f16_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp8:
 ; GCN-NEXT:    .loc 0 12 5 prologue_end ; /tmp/dbg.cl:12:5
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
 ; GCN-NEXT:  .Ltmp9:
+; GCN:    .cfi_endproc
   call void @llvm.dbg.value(metadata <4 x half> %arg, metadata !42, metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !43
   ret <4 x half> %arg, !dbg !44
 }
 
 define hidden double @split_f64_arg(double returned %arg) local_unnamed_addr #0 !dbg !45 {
 ; GCN-LABEL: split_f64_arg:
 ; GCN:       .Lfunc_begin3:
 ; GCN-NEXT:    .loc 0 15 0 ; /tmp/dbg.cl:15:0
+; GCN-NEXT:    .cfi_startproc
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp10:
 ; GCN-NEXT:    .loc 0 16 5 prologue_end ; /tmp/dbg.cl:16:5
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
 ; GCN-NEXT:  .Ltmp11:
+; GCN:    .cfi_endproc
   call void @llvm.dbg.value(metadata double %arg, metadata !50, metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !51
   ret double %arg, !dbg !52
 }
 
 define hidden <2 x double> @split_v2f64_arg(<2 x double> returned %arg) local_unnamed_addr #0 !dbg !53 {
 ; GCN-LABEL: split_v2f64_arg:
 ; GCN:       .Lfunc_begin4:
 ; GCN-NEXT:    .loc 0 19 0 ; /tmp/dbg.cl:19:0
+; GCN-NEXT:    .cfi_startproc
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v2f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 96 32] $vgpr3
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v2f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 64 32] $vgpr2
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v2f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v2f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp12:
 ; GCN-NEXT:    .loc 0 20 5 prologue_end ; /tmp/dbg.cl:20:5
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
 ; GCN-NEXT:  .Ltmp13:
+; GCN:    .cfi_endproc
   call void @llvm.dbg.value(metadata <2 x double> %arg, metadata !59, metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !60
   ret <2 x double> %arg, !dbg !61
 }
 
 define hidden i64 @split_i64_arg(i64 returned %arg) local_unnamed_addr #0 !dbg !62 {
 ; GCN-LABEL: split_i64_arg:
 ; GCN:       .Lfunc_begin5:
 ; GCN-NEXT:    .loc 0 23 0 ; /tmp/dbg.cl:23:0
+; GCN-NEXT:    .cfi_startproc
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_i64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_i64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp14:
 ; GCN-NEXT:    .loc 0 24 5 prologue_end ; /tmp/dbg.cl:24:5
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
 ; GCN-NEXT:  .Ltmp15:
+; GCN:    .cfi_endproc
   call void @llvm.dbg.value(metadata i64 %arg, metadata !67, metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !68
   ret i64 %arg, !dbg !69
 }
 
 define hidden i8 addrspace(1)* @split_ptr_arg(i8 addrspace(1)* readnone returned %arg) local_unnamed_addr #0 !dbg !70 {
 ; GCN-LABEL: split_ptr_arg:
 ; GCN:       .Lfunc_begin6:
 ; GCN-NEXT:    .loc 0 27 0 ; /tmp/dbg.cl:27:0
+; GCN-NEXT:    .cfi_startproc
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_ptr_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_ptr_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp16:
 ; GCN-NEXT:    .loc 0 28 5 prologue_end ; /tmp/dbg.cl:28:5
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
 ; GCN-NEXT:  .Ltmp17:
+; GCN:    .cfi_endproc
   call void @llvm.dbg.value(metadata i8 addrspace(1)* %arg, metadata !76, metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !77
   ret i8 addrspace(1)* %arg, !dbg !78
 }
 
 declare void @llvm.dbg.value(metadata, metadata, metadata) #1
 
 attributes #0 = { norecurse nounwind readnone }
 attributes #1 = { nounwind readnone speculatable }

llvm/test/DebugInfo/AMDGPU/cfi.ll

+; RUN: llc -mcpu=gfx900 -mtriple=amdgcn-amd-amdhsa -filetype=obj -o - %s | llvm-dwarfdump -debug-frame - | FileCheck %s
+
+; CHECK: .debug_frame contents:
+; CHECK: 00000000 0000000c ffffffff CIE
+; CHECK-NEXT:   Format:                DWARF32
+; CHECK-NEXT:   Version:               4
+; CHECK-NEXT:   Augmentation:          ""
+; CHECK-NEXT:   Address size:          8
+; CHECK-NEXT:   Segment desc size:     0
+; CHECK-NEXT:   Code alignment factor: 4
+; CHECK-NEXT:   Data alignment factor: 4
+; CHECK-NEXT:   Return address column: 16
+; CHECK-EMPTY:
+; CHECK:   DW_CFA_nop:
+; CHECK-EMPTY:
+; CHECK: 00000010 {{[0-9]+}} 00000000 FDE cie=00000000 pc=00000000...{{[0-9]+}}
+; CHECK-NEXT: Format:       DWARF32
+; CHECK-EMPTY:
+; CHECK: .eh_frame contents:
+; CHECK-NOT: CIE
+
+define void @func() #0 {
+  ret void
+}
+
+attributes #0 = { nounwind }
+
+!llvm.module.flags = !{!0, !1}
+!llvm.dbg.cu = !{!2}
+
+!0 = !{i32 7, !"Dwarf Version", i32 5}
+!1 = !{i32 2, !"Debug Info Version", i32 3}
+!2 = distinct !DICompileUnit(language: DW_LANG_C99, file: !3, emissionKind: FullDebug)
+!3 = !DIFile(filename: "file", directory: "dir")

llvm/test/MC/ELF/AMDGPU/cfi.s

+# RUN: llvm-mc -filetype=asm -mcpu=gfx900 -triple amdgcn-amd-amdhsa %s -o - | FileCheck --check-prefix=ASM %s
+# RUN: llvm-mc -filetype=obj -mcpu=gfx900 -triple amdgcn-amd-amdhsa %s -o %t
+# RUN: llvm-readelf -S -r -x .debug_frame %t | FileCheck --check-prefix=READELF %s
+
+f:
+  .cfi_sections .debug_frame
+  .cfi_startproc
+  s_nop 0
+  .cfi_endproc
+
+# ASM: f:
+# ASM-NEXT: .cfi_sections .debug_frame
+# ASM-NEXT: .cfi_startproc
+# ASM-NEXT: s_nop 0
+# ASM-NEXT: .cfi_endproc
+
+# READELF: Section Headers:
+# READELF: Name              Type            Address          Off    Size   ES Flg Lk Inf Al
+# READELF: .debug_frame      PROGBITS        0000000000000000 000048 000028 00      0   0  8
+
+# READELF: Relocation section '.rela.debug_frame' at offset 0xd0 contains 2 entries:
+# READELF-NEXT:     Offset             Info             Type               Symbol's Value  Symbol's Name + Addend
+# READELF-NEXT: 0000000000000014  0000000300000006 R_AMDGPU_ABS32         0000000000000000 .debug_frame + 0
+# READELF-NEXT: 0000000000000018  0000000100000003 R_AMDGPU_ABS64         0000000000000000 .text + 0
+
+# READELF: Hex dump of section '.debug_frame':
+# READELF-NEXT: 0x00000000 0c000000 ffffffff 04000800 04041000 ................
+# READELF-NEXT: 0x00000010 14000000 00000000 00000000 00000000 ................
+# READELF-NEXT: 0x00000020 04000000 00000000                   ........

llvm/test/MC/ELF/AMDGPU/lit.local.cfg

+# We have to reset config.unsupported here because the parent directory is
+# predicated on 'X86'.
+config.unsupported = 'AMDGPU' not in config.root.targets