[DebugInfo] DW_OP_deref_size in PrologEpilogInserter.

The PrologEpilogInserter need to insert a DW_OP_deref_size before
prepending a memory location expression to an already implicit
expression to avoid having the existing expression act on the memory
address instead of the value behind it.

The reason for using DW_OP_deref_size and not plain DW_OP_deref is that
big-endian targets need to read the right size as simply truncating a
larger read would yield the wrong result (LSB bytes are not at the lower
address).

This re-commit fixes issues reported in the first one. Namely deref was
inserted under wrong conditions and additionally the deref_size argument
was incorrectly encoded.

Differential Revision: https://reviews.llvm.org/D59687

llvm-svn: 359535

llvm/include/llvm/IR/DebugInfoMetadata.h

@@ -2510,6 +2510,9 @@ public:
   /// Return whether this is a piece of an aggregate variable.
   bool isFragment() const { return getFragmentInfo().hasValue(); }
 
+  /// Return whether this is an implicit location description.
+  bool isImplicit() const;
+
   /// Append \p Ops with operations to apply the \p Offset.
   static void appendOffset(SmallVectorImpl<uint64_t> &Ops, int64_t Offset);
 

llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp

@@ -179,6 +179,10 @@ void DebugLocDwarfExpression::emitUnsigned(uint64_t Value) {
   BS.EmitULEB128(Value, Twine(Value));
 }
 
+void DebugLocDwarfExpression::emitData1(uint8_t Value) {
+  BS.EmitInt8(Value, Twine(Value));
+}
+
 void DebugLocDwarfExpression::emitBaseTypeRef(uint64_t Idx) {
   assert(Idx < (1ULL << (ULEB128PadSize * 7)) && "Idx wont fit");
   BS.EmitULEB128(Idx, Twine(Idx), ULEB128PadSize);

llvm/lib/CodeGen/AsmPrinter/DwarfExpression.cpp

@@ -434,6 +434,10 @@ void DwarfExpression::addExpression(DIExpressionCursor &&ExprCursor,
       assert(LocationKind != Register);
       emitOp(dwarf::DW_OP_xderef);
       break;
+    case dwarf::DW_OP_deref_size:
+      emitOp(dwarf::DW_OP_deref_size);
+      emitData1(Op->getArg(0));
+      break;
     default:
       llvm_unreachable("unhandled opcode found in expression");
     }

llvm/lib/CodeGen/AsmPrinter/DwarfExpression.h

@@ -139,6 +139,8 @@ protected:
   /// Emit a raw unsigned value.
   virtual void emitUnsigned(uint64_t Value) = 0;
 
+  virtual void emitData1(uint8_t Value) = 0;
+
   virtual void emitBaseTypeRef(uint64_t Idx) = 0;
 
   /// Emit a normalized unsigned constant.
@@ -264,6 +266,7 @@ class DebugLocDwarfExpression final : public DwarfExpression {
   void emitOp(uint8_t Op, const char *Comment = nullptr) override;
   void emitSigned(int64_t Value) override;
   void emitUnsigned(uint64_t Value) override;
+  void emitData1(uint8_t Value) override;
   void emitBaseTypeRef(uint64_t Idx) override;
   bool isFrameRegister(const TargetRegisterInfo &TRI,
                        unsigned MachineReg) override;
@@ -281,6 +284,7 @@ const AsmPrinter ≈
   void emitOp(uint8_t Op, const char *Comment = nullptr) override;
   void emitSigned(int64_t Value) override;
   void emitUnsigned(uint64_t Value) override;
+  void emitData1(uint8_t Value) override;
   void emitBaseTypeRef(uint64_t Idx) override;
   bool isFrameRegister(const TargetRegisterInfo &TRI,
                        unsigned MachineReg) override;

llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp

@@ -64,6 +64,10 @@ void DIEDwarfExpression::emitUnsigned(uint64_t Value) {
   CU.addUInt(DIE, dwarf::DW_FORM_udata, Value);
 }
 
+void DIEDwarfExpression::emitData1(uint8_t Value) {
+  CU.addUInt(DIE, dwarf::DW_FORM_data1, Value);
+}
+
 void DIEDwarfExpression::emitBaseTypeRef(uint64_t Idx) {
   CU.addBaseTypeRef(DIE, Idx);
 }

llvm/lib/CodeGen/MIRParser/MIParser.cpp

@@ -1854,6 +1854,11 @@ bool MIParser::parseDIExpression(MDNode *&Expr) {
           Elements.push_back(Op);
           continue;
         }
+        if (unsigned Enc = dwarf::getAttributeEncoding(Token.stringValue())) {
+          lex();
+          Elements.push_back(Enc);
+          continue;
+        }
         return error(Twine("invalid DWARF op '") + Token.stringValue() + "'");
       }
 

llvm/lib/CodeGen/PrologEpilogInserter.cpp

@@ -1172,12 +1172,26 @@ void PEI::replaceFrameIndices(MachineBasicBlock *BB, MachineFunction &MF,
         assert(i == 0 && "Frame indices can only appear as the first "
                          "operand of a DBG_VALUE machine instruction");
         unsigned Reg;
+        unsigned FrameIdx = MI.getOperand(0).getIndex();
+        unsigned Size = MF.getFrameInfo().getObjectSize(FrameIdx);
+
         int64_t Offset =
-            TFI->getFrameIndexReference(MF, MI.getOperand(0).getIndex(), Reg);
+            TFI->getFrameIndexReference(MF, FrameIdx, Reg);
         MI.getOperand(0).ChangeToRegister(Reg, false /*isDef*/);
         MI.getOperand(0).setIsDebug();
-        auto *DIExpr = DIExpression::prepend(MI.getDebugExpression(),
-                                             DIExpression::NoDeref, Offset);
+
+        const DIExpression *DIExpr = MI.getDebugExpression();
+        // If we have DBG_VALUE that is indirect and has a Implicit location
+        // expression need to insert a deref before prepending a Memory
+        // location expression. Also after doing this we change the DBG_VALUE
+        // to be direct.
+        if (MI.isIndirectDebugValue() && DIExpr->isImplicit()) {
+          SmallVector<uint64_t, 2> Ops = {dwarf::DW_OP_deref_size, Size};
+          DIExpr = DIExpression::prependOpcodes(DIExpr, Ops, DIExpression::WithStackValue);
+          // Make the DBG_VALUE direct.
+          MI.getOperand(1).ChangeToRegister(0, false);
+        }
+        DIExpr = DIExpression::prepend(DIExpr, DIExpression::NoDeref, Offset);
         MI.getOperand(3).setMetadata(DIExpr);
         continue;
       }

llvm/lib/IR/DebugInfoMetadata.cpp

@@ -833,6 +833,7 @@ unsigned DIExpression::ExprOperand::getSize() const {
   case dwarf::DW_OP_LLVM_fragment:
     return 3;
   case dwarf::DW_OP_constu:
+  case dwarf::DW_OP_deref_size:
   case dwarf::DW_OP_plus_uconst:
     return 2;
   default:
@@ -889,6 +890,7 @@ bool DIExpression::isValid() const {
     case dwarf::DW_OP_shr:
     case dwarf::DW_OP_shra:
     case dwarf::DW_OP_deref:
+    case dwarf::DW_OP_deref_size:
     case dwarf::DW_OP_xderef:
     case dwarf::DW_OP_lit0:
     case dwarf::DW_OP_not:
@@ -899,6 +901,19 @@ bool DIExpression::isValid() const {
   return true;
 }
 
+bool DIExpression::isImplicit() const {
+  unsigned N = getNumElements();
+  if (isValid() && N > 0) {
+    switch (getElement(N-1)) {
+      case dwarf::DW_OP_stack_value: return true;
+      case dwarf::DW_OP_LLVM_fragment:
+        return N > 1 && getElement(N-2) == dwarf::DW_OP_stack_value;
+      default: break;
+    }
+  }
+  return false;
+}
+
 Optional<DIExpression::FragmentInfo>
 DIExpression::getFragmentInfo(expr_op_iterator Start, expr_op_iterator End) {
   for (auto I = Start; I != End; ++I)

llvm/test/CodeGen/X86/prologepilog_deref_size.mir

@@ -0,0 +1,59 @@
+# RUN: llc -run-pass=prologepilog -o - %s | FileCheck %s
+--- |
+  ; ModuleID = 'dbg.opt.ll'
+  source_filename = "dbg.c"
+  target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+  target triple = "x86_64-unknown-linux-gnu"
+
+  ; Function Attrs: noinline nounwind uwtable
+  define dso_local zeroext i16 @foo(i16 zeroext %d0, i16 zeroext %d1, i16 zeroext %d2, i16 zeroext %d3, i16 zeroext %d4, i16 zeroext %d5, i16 zeroext %d6, i16 zeroext %d7, i16 zeroext %d8, i16 signext %x) #0 !dbg !7 {
+  entry:
+    call void @llvm.dbg.value(metadata i16 %x, metadata !32, metadata !DIExpression(DW_OP_LLVM_convert, 16, DW_ATE_signed, DW_OP_LLVM_convert, 32, DW_ATE_signed, DW_OP_stack_value)), !dbg !34
+    ret i16 %x
+  }
+
+  ; Function Attrs: nounwind readnone speculatable
+  declare void @llvm.dbg.value(metadata, metadata, metadata) #1
+
+  attributes #0 = { noinline nounwind uwtable }
+  attributes #1 = { nounwind readnone speculatable }
+
+  !llvm.dbg.cu = !{!0}
+  !llvm.module.flags = !{!3, !4, !5}
+  !llvm.ident = !{!6}
+
+  !0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 9.0.0", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, nameTableKind: None)
+  !1 = !DIFile(filename: "dbg.c", directory: "/tmp")
+  !2 = !{}
+  !3 = !{i32 2, !"Dwarf Version", i32 4}
+  !4 = !{i32 2, !"Debug Info Version", i32 3}
+  !5 = !{i32 1, !"wchar_size", i32 4}
+  !6 = !{!"clang version 9.0.0"}
+  !7 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 2, type: !8, scopeLine: 2, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition, unit: !0, retainedNodes: !2)
+  !8 = !DISubroutineType(types: !9)
+  !9 = !{!10, !10, !10, !10, !10, !10, !10, !10, !10, !10, !10}
+  !10 = !DIDerivedType(tag: DW_TAG_typedef, name: "T", file: !1, line: 1, baseType: !11)
+  !11 = !DIBasicType(name: "signed short", size: 16, encoding: DW_ATE_signed)
+  !32 = !DILocalVariable(name: "y", scope: !7, file: !1, line: 3, type: !33)
+  !33 = !DIBasicType(name: "signed int", size: 32, encoding: DW_ATE_signed)
+  !34 = !DILocation(line: 3, column: 20, scope: !7)
+
+...
+---
+name:            foo
+tracksRegLiveness: true
+fixedStack:
+  - { id: 0, type: default, offset: 24, size: 2, alignment: 8, stack-id: 0,
+      isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+stack:           []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  bb.0.entry:
+    renamable $ax = MOV16rm %fixed-stack.0, 1, $noreg, 0, $noreg :: (load 2 from %fixed-stack.0, align 8)
+    DBG_VALUE %fixed-stack.0, 0, !32, !DIExpression(DW_OP_LLVM_convert, 16, DW_ATE_signed, DW_OP_LLVM_convert, 32, DW_ATE_signed, DW_OP_stack_value), debug-location !34
+    RET 0, $ax
+...
+# CHECK: machineFunctionInfo
+# CHECK: DBG_VALUE $rsp, $noreg, !12, !DIExpression(DW_OP_plus_uconst, {{[0-9]+}}, DW_OP_deref_size, 2, DW_OP_LLVM_convert, 16, DW_ATE_signed, DW_OP_LLVM_convert, 32, DW_ATE_signed, DW_OP_stack_value), debug-location !14