[WIP] Encode WebAssembly specific locations in DBG_VALUEs and DW_AT_frame_base

include/llvm/BinaryFormat/Dwarf.def

@@ -627,6 +627,8 @@ HANDLE_DW_OP(0xfb, GNU_addr_index, 0, GNU)
 HANDLE_DW_OP(0xfc, GNU_const_index, 0, GNU)
 
 // DWARF languages.
+// Extensions for WebAssembly.
+HANDLE_DW_OP(0xed, WASM_location, 0, WASM)
 HANDLE_DW_LANG(0x0001, C89, 2, DWARF)
 HANDLE_DW_LANG(0x0002, C, 2, DWARF)
 HANDLE_DW_LANG(0x0003, Ada83, 2, DWARF)

include/llvm/BinaryFormat/Dwarf.h

@@ -58,7 +58,8 @@ enum LLVMConstants : uint32_t {
   DWARF_VENDOR_GNU = 3,
   DWARF_VENDOR_GOOGLE = 4,
   DWARF_VENDOR_LLVM = 5,
-  DWARF_VENDOR_MIPS = 6
+  DWARF_VENDOR_MIPS = 6,
+  DWARF_VENDOR_WASM = 7
 };
 
 /// Constants that define the DWARF format as 32 or 64 bit.

include/llvm/CodeGen/TargetRegisterInfo.h

@@ -211,6 +211,22 @@ struct RegClassWeight {
   unsigned WeightLimit;
 };
 
+struct FrameBaseLocation {
+  enum LocationKind {
+    Register,
+    CFA,
+    TargetIndex
+  } Kind;
+  struct TargetIndexInfo {
+    unsigned Index;
+    signed Offset;
+  };
+  union {
+    unsigned Reg;
+    TargetIndexInfo TI;
+  };
+};
+
 /// TargetRegisterInfo base class - We assume that the target defines a static
 /// array of TargetRegisterDesc objects that represent all of the machine
 /// registers that the target has.  As such, we simply have to track a pointer
@@ -988,6 +1004,13 @@ class TargetRegisterInfo : public MCRegisterInfo {
   /// for values allocated in the current stack frame.
   virtual unsigned getFrameRegister(const MachineFunction &MF) const = 0;
 
+  virtual FrameBaseLocation getFrameBaseLocation(const MachineFunction &MF) const {
+    FrameBaseLocation Loc;
+    Loc.Kind = FrameBaseLocation::Register;
+    Loc.Reg = getFrameRegister(MF);
+    return Loc;
+  }
+
   /// Mark a register and all its aliases as reserved in the given set.
   void markSuperRegs(BitVector &RegisterSet, unsigned Reg) const;
 

lib/CodeGen/AsmPrinter/AsmPrinter.cpp

@@ -895,6 +895,10 @@ static bool emitDebugValueComment(const MachineInstr *MI, AsmPrinter &AP) {
     OS << MI->getOperand(0).getImm();
   } else if (MI->getOperand(0).isCImm()) {
     MI->getOperand(0).getCImm()->getValue().print(OS, false /*isSigned*/);
+  } else if (MI->getOperand(0).isTargetIndex()) {
+    auto Op = MI->getOperand(0);
+    OS << "!target-index(" << Op.getIndex() << "," << Op.getOffset() << ")";
+    return true;
   } else {
     unsigned Reg;
     if (MI->getOperand(0).isReg()) {

lib/CodeGen/AsmPrinter/DebugLocEntry.h

@@ -21,6 +21,19 @@
 namespace llvm {
 class AsmPrinter;
 
+struct TargetIndexLocation {
+  int Index;
+  int Offset;
+
+  TargetIndexLocation() = default;
+  TargetIndexLocation(unsigned Idx, int64_t Offset)
+      : Index(Idx), Offset(Offset) {}
+
+  bool operator==(const TargetIndexLocation &Other) const {
+    return Index == Other.Index && Offset == Other.Offset;
+  }
+};
+
 /// This struct describes location entries emitted in the .debug_loc
 /// section.
 class DebugLocEntry {
@@ -47,12 +60,20 @@ class DebugLocEntry {
         : Expression(Expr), EntryKind(E_Location), Loc(Loc) {
       assert(cast<DIExpression>(Expr)->isValid());
     }
+    Value(const DIExpression *Expr, TargetIndexLocation Loc)
+        : Expression(Expr), EntryKind(E_TargetIndexLocation), TIL(Loc) {}
 
     /// Any complex address location expression for this Value.
     const DIExpression *Expression;
 
     /// Type of entry that this represents.
-    enum EntryType { E_Location, E_Integer, E_ConstantFP, E_ConstantInt };
+    enum EntryType {
+      E_Location,
+      E_Integer,
+      E_ConstantFP,
+      E_ConstantInt,
+      E_TargetIndexLocation
+    };
     enum EntryType EntryKind;
 
     /// Either a constant,
@@ -62,17 +83,25 @@ class DebugLocEntry {
       const ConstantInt *CIP;
     } Constant;
 
-    // Or a location in the machine frame.
-    MachineLocation Loc;
+    union {
+      // Or a location in the machine frame.
+      MachineLocation Loc;
+      // Or a location from target specific location.
+      TargetIndexLocation TIL;
+    };
 
     bool isLocation() const { return EntryKind == E_Location; }
+    bool isTargetIndexLocation() const {
+      return EntryKind == E_TargetIndexLocation;
+    }
     bool isInt() const { return EntryKind == E_Integer; }
     bool isConstantFP() const { return EntryKind == E_ConstantFP; }
     bool isConstantInt() const { return EntryKind == E_ConstantInt; }
     int64_t getInt() const { return Constant.Int; }
     const ConstantFP *getConstantFP() const { return Constant.CFP; }
     const ConstantInt *getConstantInt() const { return Constant.CIP; }
     MachineLocation getLoc() const { return Loc; }
+    TargetIndexLocation getTargetIndexLocation() const { return TIL; }
     bool isFragment() const { return getExpression()->isFragment(); }
     const DIExpression *getExpression() const { return Expression; }
     friend bool operator==(const Value &, const Value &);
@@ -165,6 +194,8 @@ inline bool operator==(const DebugLocEntry::Value &A,
   switch (A.EntryKind) {
   case DebugLocEntry::Value::E_Location:
     return A.Loc == B.Loc;
+  case DebugLocEntry::Value::E_TargetIndexLocation:
+    return A.TIL == B.TIL;
   case DebugLocEntry::Value::E_Integer:
     return A.Constant.Int == B.Constant.Int;
   case DebugLocEntry::Value::E_ConstantFP:

lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp

@@ -340,13 +340,24 @@ DIE &DwarfCompileUnit::updateSubprogramScopeDIE(const DISubprogram *SP) {
 
   // Only include DW_AT_frame_base in full debug info
   if (!includeMinimalInlineScopes()) {
-    if (Asm->MF->getTarget().getTargetTriple().isNVPTX()) {
+    const TargetRegisterInfo *RI = Asm->MF->getSubtarget().getRegisterInfo();
+    auto FBL = RI->getFrameBaseLocation(*Asm->MF);
+    if (FBL.Kind == FrameBaseLocation::CFA) {
       DIELoc *Loc = new (DIEValueAllocator) DIELoc;
       addUInt(*Loc, dwarf::DW_FORM_data1, dwarf::DW_OP_call_frame_cfa);
       addBlock(*SPDie, dwarf::DW_AT_frame_base, Loc);
+    } else if (FBL.Kind == FrameBaseLocation::TargetIndex) {
+      if (FBL.TI.Offset >= 0) {
+        DIELoc *Loc = new (DIEValueAllocator) DIELoc;
+        DIEDwarfExpression DwarfExpr(*Asm, *this, *Loc);
+        DIExpressionCursor Cursor({});
+        DwarfExpr.addTargetIndexLocation(FBL.TI.Index, FBL.TI.Offset);
+        DwarfExpr.addExpression(std::move(Cursor));
+        addBlock(*SPDie, dwarf::DW_AT_frame_base, DwarfExpr.finalize());
+      }
     } else {
-      const TargetRegisterInfo *RI = Asm->MF->getSubtarget().getRegisterInfo();
-      MachineLocation Location(RI->getFrameRegister(*Asm->MF));
+      assert(FBL.Kind == FrameBaseLocation::Register);
+      MachineLocation Location(FBL.Reg);
       if (RI->isPhysicalRegister(Location.getReg()))
         addAddress(*SPDie, dwarf::DW_AT_frame_base, Location);
     }
@@ -1023,7 +1034,7 @@ void DwarfCompileUnit::addVariableAddress(const DbgVariable &DV, DIE &Die,
 
 /// Add an address attribute to a die based on the location provided.
 void DwarfCompileUnit::addAddress(DIE &Die, dwarf::Attribute Attribute,
-                                  const MachineLocation &Location) {
+				  const MachineLocation &Location) {
   DIELoc *Loc = new (DIEValueAllocator) DIELoc;
   DIEDwarfExpression DwarfExpr(*Asm, *this, *Loc);
   if (Location.isIndirect())

lib/CodeGen/AsmPrinter/DwarfDebug.cpp

@@ -1060,6 +1060,11 @@ static DebugLocEntry::Value getDebugLocValue(const MachineInstr *MI) {
     MachineLocation MLoc(RegOp.getReg(), Op1.isImm());
     return DebugLocEntry::Value(Expr, MLoc);
   }
+  if (MI->getOperand(0).isTargetIndex()) {
+    auto Op = MI->getOperand(0);
+    return DebugLocEntry::Value(
+        Expr, TargetIndexLocation(Op.getIndex(), Op.getOffset()));
+  }
   if (MI->getOperand(0).isImm())
     return DebugLocEntry::Value(Expr, MI->getOperand(0).getImm());
   if (MI->getOperand(0).isFPImm())
@@ -1899,6 +1904,9 @@ static void emitDebugLocValue(const AsmPrinter &AP, const DIBasicType *BT,
   } else if (Value.isConstantFP()) {
     APInt RawBytes = Value.getConstantFP()->getValueAPF().bitcastToAPInt();
     DwarfExpr.addUnsignedConstant(RawBytes);
+  } else if (Value.isTargetIndexLocation()) {
+    TargetIndexLocation Loc = Value.getTargetIndexLocation();
+    DwarfExpr.addTargetIndexLocation(Loc.Index, Loc.Offset);
   }
   DwarfExpr.addExpression(std::move(ExprCursor));
 }

lib/CodeGen/AsmPrinter/DwarfExpression.cpp

@@ -437,3 +437,11 @@ void DwarfExpression::addFragmentOffset(const DIExpression *Expr) {
     addOpPiece(FragmentOffset - OffsetInBits);
   OffsetInBits = FragmentOffset;
 }
+
+void DwarfExpression::addTargetIndexLocation(unsigned Index, int64_t Offset) {
+  assert(LocationKind == Implicit || LocationKind == Unknown);
+  LocationKind = Implicit;
+  emitOp(dwarf::DW_OP_WASM_location);
+  emitUnsigned(Index);
+  emitSigned(Offset);
+}

lib/CodeGen/AsmPrinter/DwarfExpression.h

@@ -248,6 +248,10 @@ class DwarfExpression {
   /// If applicable, emit an empty DW_OP_piece / DW_OP_bit_piece to advance to
   /// the fragment described by \c Expr.
   void addFragmentOffset(const DIExpression *Expr);
+
+  /// Emit location information expressed via target's index + offset
+  /// It is an extension for WebAssembly locals, globals and operand stack.
+  void addTargetIndexLocation(unsigned Index, int64_t Offset);
 };
 
 /// DwarfExpression implementation for .debug_loc entries.

lib/DebugInfo/DWARF/DWARFExpression.cpp

@@ -93,6 +93,8 @@ static DescVector getDescriptions() {
   Descriptions[DW_OP_implicit_value] =
       Desc(Op::Dwarf3, Op::SizeLEB, Op::SizeBlock);
   Descriptions[DW_OP_stack_value] = Desc(Op::Dwarf3);
+  Descriptions[DW_OP_WASM_location] =
+      Desc(Op::Dwarf4, Op::SizeLEB, Op::SignedSizeLEB);
   Descriptions[DW_OP_GNU_push_tls_address] = Desc(Op::Dwarf3);
   Descriptions[DW_OP_addrx] = Desc(Op::Dwarf4, Op::SizeLEB);
   Descriptions[DW_OP_GNU_addr_index] = Desc(Op::Dwarf4, Op::SizeLEB);

lib/Target/NVPTX/NVPTXRegisterInfo.h

@@ -45,6 +45,12 @@ class NVPTXRegisterInfo : public NVPTXGenRegisterInfo {
 
   unsigned getFrameRegister(const MachineFunction &MF) const override;
 
+  FrameBaseLocation getFrameBaseLocation(const MachineFunction &MF) const override {
+    FrameBaseLocation Loc;
+    Loc.Kind = FrameBaseLocation::CFA;
+    return Loc;
+  }
+
   ManagedStringPool *getStrPool() const {
     return const_cast<ManagedStringPool *>(&ManagedStrPool);
   }

lib/Target/WebAssembly/WebAssembly.h

@@ -82,6 +82,14 @@ void initializeWebAssemblyRegNumberingPass(PassRegistry &);
 void initializeWebAssemblyPeepholePass(PassRegistry &);
 void initializeWebAssemblyCallIndirectFixupPass(PassRegistry &);
 
+namespace WebAssembly {
+enum TargetIndex { TI_LOCAL_START, TI_GLOBAL_START, TI_OPERAND_STACK_START };
+} // end namespace WebAssembly
+
+namespace WebAssembly {
+enum TargetIndex { TI_LOCAL_START, TI_GLOBAL_START, TI_OPERAND_STACK_START };
+} // end namespace WebAssembly
+
 } // end namespace llvm
 
 #endif

lib/Target/WebAssembly/WebAssemblyExplicitLocals.cpp

@@ -164,6 +164,45 @@ static MVT typeForRegClass(const TargetRegisterClass *RC) {
   llvm_unreachable("unrecognized register class");
 }
 
+static void fixupFollowingDebugValues(DenseMap<unsigned, unsigned> &Reg2Local,
+                                      MachineRegisterInfo &MRI,
+                                      MachineBasicBlock::iterator B,
+                                      MachineBasicBlock::iterator E) {
+  // Scan DBG_VALUE and modify virtual registers with known locals.
+  // Stop at first non-DBG_VALUE instruction.
+  for (auto I = B; I != E && I->isDebugInstr();) {
+    MachineInstr &MI = *I++;
+    for (MachineOperand &MO : reverse(MI.uses())) {
+      if (!MO.isReg())
+        continue;
+
+      unsigned OldReg = MO.getReg();
+      auto I = Reg2Local.find(OldReg);
+      if (I == Reg2Local.end())
+        continue;
+
+      unsigned LocalId = I->second;
+      MO.ChangeToTargetIndex(llvm::WebAssembly::TI_LOCAL_START, LocalId);
+    }
+  }
+}
+
+static void fixupFollowingDebugValues(unsigned Reg, unsigned LocalId,
+                                      MachineRegisterInfo &MRI,
+                                      MachineBasicBlock::iterator B,
+                                      MachineBasicBlock::iterator E) {
+  // Scan DBG_VALUE and modify the specified virtual registers with the local.
+  // Stop at first non-DBG_VALUE instruction.
+  for (auto I = B; I != E && I->isDebugInstr();) {
+    MachineInstr &MI = *I++;
+    for (MachineOperand &MO : reverse(MI.uses())) {
+      if (!MO.isReg() || MO.getReg() != Reg)
+        continue;
+      MO.ChangeToTargetIndex(llvm::WebAssembly::TI_LOCAL_START, LocalId);
+    }
+  }
+}
+
 /// Given a MachineOperand of a stackified vreg, return the instruction at the
 /// start of the expression tree.
 static MachineInstr *findStartOfTree(MachineOperand &MO,
@@ -262,6 +301,11 @@ bool WebAssemblyExplicitLocals::runOnMachineFunction(MachineFunction &MF) {
             .addImm(LocalId)
             .addReg(MI.getOperand(2).getReg());
 
+        auto Next = std::next(MachineBasicBlock::iterator(&MI));
+        fixupFollowingDebugValues(Reg2Local, MRI, Next, MBB.end());
+        fixupFollowingDebugValues(MI.getOperand(0).getReg(), LocalId, MRI, Next,
+                                  MBB.end());
+
         MI.eraseFromParent();
         Changed = true;
         continue;
@@ -294,13 +338,18 @@ bool WebAssemblyExplicitLocals::runOnMachineFunction(MachineFunction &MF) {
             BuildMI(MBB, InsertPt, MI.getDebugLoc(), TII->get(Opc))
                 .addImm(LocalId)
                 .addReg(NewReg);
+            fixupFollowingDebugValues(NewReg, LocalId, MRI, InsertPt,
+                                      MBB.end());
           }
           MI.getOperand(0).setReg(NewReg);
           // This register operand is now being used by the inserted drop
           // instruction, so make it undead.
           MI.getOperand(0).setIsDead(false);
           MFI.stackifyVReg(NewReg);
           Changed = true;
+
+          fixupFollowingDebugValues(Reg2Local, MRI, InsertPt, MBB.end());
+
         }
       }
 
@@ -353,6 +402,8 @@ bool WebAssemblyExplicitLocals::runOnMachineFunction(MachineFunction &MF) {
         MO.setReg(NewReg);
         MFI.stackifyVReg(NewReg);
         Changed = true;
+
+        fixupFollowingDebugValues(OldReg, LocalId, MRI, InsertPt, MBB.end());
       }
 
       // Coalesce and eliminate COPY instructions.
@@ -379,6 +430,13 @@ bool WebAssemblyExplicitLocals::runOnMachineFunction(MachineFunction &MF) {
     Changed = true;
   }
 
+  {
+    auto RL = Reg2Local.find(MFI.SPVReg);
+    if (RL != Reg2Local.end()) {
+      MFI.SPLocal = RL->second;
+    }
+  }
+
 #ifndef NDEBUG
   // Assert that all registers have been stackified at this point.
   for (const MachineBasicBlock &MBB : MF) {

lib/Target/WebAssembly/WebAssemblyInstrInfo.cpp

@@ -198,3 +198,12 @@ bool WebAssemblyInstrInfo::reverseBranchCondition(
   Cond.front() = MachineOperand::CreateImm(!Cond.front().getImm());
   return false;
 }
+
+ArrayRef<std::pair<int, const char *>>
+WebAssemblyInstrInfo::getSerializableTargetIndices() const {
+  static const std::pair<int, const char *> TargetIndices[] = {
+      {WebAssembly::TI_LOCAL_START, "wasm-local-start"},
+      {WebAssembly::TI_GLOBAL_START, "wasm-global-start"},
+      {WebAssembly::TI_OPERAND_STACK_START, "wasm-operator-stack-start"}};
+  return makeArrayRef(TargetIndices);
+}

lib/Target/WebAssembly/WebAssemblyInstrInfo.h

@@ -16,7 +16,9 @@
 #ifndef LLVM_LIB_TARGET_WEBASSEMBLY_WEBASSEMBLYINSTRINFO_H
 #define LLVM_LIB_TARGET_WEBASSEMBLY_WEBASSEMBLYINSTRINFO_H
 
+#include "WebAssembly.h"
 #include "WebAssemblyRegisterInfo.h"
+#include "llvm/ADT/ArrayRef.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 
 #define GET_INSTRINFO_HEADER
@@ -56,6 +58,9 @@ class WebAssemblyInstrInfo final : public WebAssemblyGenInstrInfo {
                         int *BytesAdded = nullptr) const override;
   bool
   reverseBranchCondition(SmallVectorImpl<MachineOperand> &Cond) const override;
+
+  ArrayRef<std::pair<int, const char *>>
+  getSerializableTargetIndices() const override;
 };
 
 } // end namespace llvm