[DebugInfo] Convert intrinsic llvm.dbg.label to MachineInstr.

In order to convert LLVM IR to MachineInstr, we need a new TargetOpcode,
DBG_LABEL, to ‘lower’ intrinsic llvm.dbg.label. The patch
creates this new TargetOpcode and convert intrinsic llvm.dbg.label to
MachineInstr through SelectionDAG.

In SelectionDAG, debug information is stored in SDDbgInfo. We create a
new data member of SDDbgInfo for labels and use the new data member,
SDDbgLabel, to create DBG_LABEL MachineInstr.

The new DBG_LABEL MachineInstr uses label metadata from LLVM IR as its
parameter. So, the backend could get metadata information of labels from
DBG_LABEL MachineInstr.

Differential Revision: https://reviews.llvm.org/D45341

Patch by Hsiangkai Wang.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@331842 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/CodeGen/MachineInstr.h

@@ -292,6 +292,10 @@ class MachineInstr
   /// this DBG_VALUE instruction.
   const DIExpression *getDebugExpression() const;
 
+  /// Return the debug label referenced by
+  /// this DBG_LABEL instruction.
+  const DILabel *getDebugLabel() const;
+
   /// Emit an error referring to the source location of this instruction.
   /// This should only be used for inline assembly that is somehow
   /// impossible to compile. Other errors should have been handled much
@@ -831,6 +835,8 @@ class MachineInstr
   bool isPosition() const { return isLabel() || isCFIInstruction(); }
 
   bool isDebugValue() const { return getOpcode() == TargetOpcode::DBG_VALUE; }
+  bool isDebugLabel() const { return getOpcode() == TargetOpcode::DBG_LABEL; }
+  bool isDebugInstr() const { return isDebugValue() || isDebugLabel(); }
 
   /// A DBG_VALUE is indirect iff the first operand is a register and
   /// the second operand is an immediate.
@@ -907,6 +913,7 @@ class MachineInstr
     case TargetOpcode::EH_LABEL:
     case TargetOpcode::GC_LABEL:
     case TargetOpcode::DBG_VALUE:
+    case TargetOpcode::DBG_LABEL:
     case TargetOpcode::LIFETIME_START:
     case TargetOpcode::LIFETIME_END:
       return true;

include/llvm/CodeGen/SelectionDAG.h

@@ -73,6 +73,7 @@ class MachineConstantPoolValue;
 class MCSymbol;
 class OptimizationRemarkEmitter;
 class SDDbgValue;
+class SDDbgLabel;
 class SelectionDAG;
 class SelectionDAGTargetInfo;
 class TargetLibraryInfo;
@@ -148,6 +149,7 @@ class SDDbgInfo {
   BumpPtrAllocator Alloc;
   SmallVector<SDDbgValue*, 32> DbgValues;
   SmallVector<SDDbgValue*, 32> ByvalParmDbgValues;
+  SmallVector<SDDbgLabel*, 4> DbgLabels;
   using DbgValMapType = DenseMap<const SDNode *, SmallVector<SDDbgValue *, 2>>;
   DbgValMapType DbgValMap;
 
@@ -164,6 +166,10 @@ class SDDbgInfo {
       DbgValMap[Node].push_back(V);
   }
 
+  void add(SDDbgLabel *L) {
+    DbgLabels.push_back(L);
+  }
+
   /// Invalidate all DbgValues attached to the node and remove
   /// it from the Node-to-DbgValues map.
   void erase(const SDNode *Node);
@@ -172,13 +178,14 @@ class SDDbgInfo {
     DbgValMap.clear();
     DbgValues.clear();
     ByvalParmDbgValues.clear();
+    DbgLabels.clear();
     Alloc.Reset();
   }
 
   BumpPtrAllocator &getAlloc() { return Alloc; }
 
   bool empty() const {
-    return DbgValues.empty() && ByvalParmDbgValues.empty();
+    return DbgValues.empty() && ByvalParmDbgValues.empty() && DbgLabels.empty();
   }
 
   ArrayRef<SDDbgValue*> getSDDbgValues(const SDNode *Node) {
@@ -189,11 +196,14 @@ class SDDbgInfo {
   }
 
   using DbgIterator = SmallVectorImpl<SDDbgValue*>::iterator;
+  using DbgLabelIterator = SmallVectorImpl<SDDbgLabel*>::iterator;
 
   DbgIterator DbgBegin() { return DbgValues.begin(); }
   DbgIterator DbgEnd()   { return DbgValues.end(); }
   DbgIterator ByvalParmDbgBegin() { return ByvalParmDbgValues.begin(); }
   DbgIterator ByvalParmDbgEnd()   { return ByvalParmDbgValues.end(); }
+  DbgLabelIterator DbgLabelBegin() { return DbgLabels.begin(); }
+  DbgLabelIterator DbgLabelEnd()   { return DbgLabels.end(); }
 };
 
 void checkForCycles(const SelectionDAG *DAG, bool force = false);
@@ -255,7 +265,7 @@ class SelectionDAG {
   /// Pool allocation for misc. objects that are created once per SelectionDAG.
   BumpPtrAllocator Allocator;
 
-  /// Tracks dbg_value information through SDISel.
+  /// Tracks dbg_value and dbg_label information through SDISel.
   SDDbgInfo *DbgInfo;
 
   uint16_t NextPersistentId = 0;
@@ -1247,6 +1257,9 @@ class SelectionDAG {
                               unsigned VReg, bool IsIndirect,
                               const DebugLoc &DL, unsigned O);
 
+  /// Creates a SDDbgLabel node.
+  SDDbgLabel *getDbgLabel(DILabel *Label, const DebugLoc &DL, unsigned O);
+
   /// Transfer debug values from one node to another, while optionally
   /// generating fragment expressions for split-up values. If \p InvalidateDbg
   /// is set, debug values are invalidated after they are transferred.
@@ -1328,6 +1341,9 @@ class SelectionDAG {
   /// value is produced by SD.
   void AddDbgValue(SDDbgValue *DB, SDNode *SD, bool isParameter);
 
+  /// Add a dbg_label SDNode.
+  void AddDbgLabel(SDDbgLabel *DB);
+
   /// Get the debug values which reference the given SDNode.
   ArrayRef<SDDbgValue*> GetDbgValues(const SDNode* SD) {
     return DbgInfo->getSDDbgValues(SD);
@@ -1349,6 +1365,13 @@ class SelectionDAG {
     return DbgInfo->ByvalParmDbgEnd();
   }
 
+  SDDbgInfo::DbgLabelIterator DbgLabelBegin() {
+    return DbgInfo->DbgLabelBegin();
+  }
+  SDDbgInfo::DbgLabelIterator DbgLabelEnd() {
+    return DbgInfo->DbgLabelEnd();
+  }
+
   /// To be invoked on an SDNode that is slated to be erased. This
   /// function mirrors \c llvm::salvageDebugInfo.
   void salvageDebugInfo(SDNode &N);

include/llvm/Support/TargetOpcodes.def

@@ -77,6 +77,9 @@ HANDLE_TARGET_OPCODE(SUBREG_TO_REG)
 /// DBG_VALUE - a mapping of the llvm.dbg.value intrinsic
 HANDLE_TARGET_OPCODE(DBG_VALUE)
 
+/// DBG_LABEL - a mapping of the llvm.dbg.label intrinsic
+HANDLE_TARGET_OPCODE(DBG_LABEL)
+
 /// REG_SEQUENCE - This variadic instruction is used to form a register that
 /// represents a consecutive sequence of sub-registers. It's used as a
 /// register coalescing / allocation aid and must be eliminated before code

include/llvm/Target/Target.td

@@ -997,6 +997,12 @@ def DBG_VALUE : StandardPseudoInstruction {
   let AsmString = "DBG_VALUE";
   let hasSideEffects = 0;
 }
+def DBG_LABEL : StandardPseudoInstruction {
+  let OutOperandList = (outs);
+  let InOperandList = (ins unknown:$label);
+  let AsmString = "DBG_LABEL";
+  let hasSideEffects = 0;
+}
 def REG_SEQUENCE : StandardPseudoInstruction {
   let OutOperandList = (outs unknown:$dst);
   let InOperandList = (ins unknown:$supersrc, variable_ops);

lib/CodeGen/AsmPrinter/AsmPrinter.cpp

@@ -911,6 +911,30 @@ static bool emitDebugValueComment(const MachineInstr *MI, AsmPrinter &AP) {
   return true;
 }
 
+/// This method handles the target-independent form of DBG_LABEL, returning
+/// true if it was able to do so.  A false return means the target will need
+/// to handle MI in EmitInstruction.
+static bool emitDebugLabelComment(const MachineInstr *MI, AsmPrinter &AP) {
+  if (MI->getNumOperands() != 1)
+    return false;
+
+  SmallString<128> Str;
+  raw_svector_ostream OS(Str);
+  OS << "DEBUG_LABEL: ";
+
+  const DILabel *V = MI->getDebugLabel();
+  if (auto *SP = dyn_cast<DISubprogram>(V->getScope())) {
+    StringRef Name = SP->getName();
+    if (!Name.empty())
+      OS << Name << ":";
+  }
+  OS << V->getName();
+
+  // NOTE: Want this comment at start of line, don't emit with AddComment.
+  AP.OutStreamer->emitRawComment(OS.str());
+  return true;
+}
+
 AsmPrinter::CFIMoveType AsmPrinter::needsCFIMoves() const {
   if (MAI->getExceptionHandlingType() == ExceptionHandling::DwarfCFI &&
       MF->getFunction().needsUnwindTableEntry())
@@ -1074,6 +1098,12 @@ void AsmPrinter::EmitFunctionBody() {
             EmitInstruction(&MI);
         }
         break;
+      case TargetOpcode::DBG_LABEL:
+        if (isVerbose()) {
+          if (!emitDebugLabelComment(&MI, *this))
+            EmitInstruction(&MI);
+        }
+        break;
       case TargetOpcode::IMPLICIT_DEF:
         if (isVerbose()) emitImplicitDef(&MI);
         break;

lib/CodeGen/MachineInstr.cpp

@@ -613,6 +613,11 @@ int MachineInstr::findInlineAsmFlagIdx(unsigned OpIdx,
   return -1;
 }
 
+const DILabel *MachineInstr::getDebugLabel() const {
+  assert(isDebugLabel() && "not a DBG_LABEL");
+  return cast<DILabel>(getOperand(0).getMetadata());
+}
+
 const DILocalVariable *MachineInstr::getDebugVariable() const {
   assert(isDebugValue() && "not a DBG_VALUE");
   return cast<DILocalVariable>(getOperand(2).getMetadata());
@@ -1383,6 +1388,17 @@ void MachineInstr::print(raw_ostream &OS, ModuleSlotTracker &MST,
         MO.print(OS, MST, TypeToPrint, /*PrintDef=*/true, IsStandalone,
                  ShouldPrintRegisterTies, TiedOperandIdx, TRI, IntrinsicInfo);
       }
+    } else if (isDebugLabel() && MO.isMetadata()) {
+      // Pretty print DBG_LABEL instructions.
+      auto *DIL = dyn_cast<DILabel>(MO.getMetadata());
+      if (DIL && !DIL->getName().empty())
+        OS << "\"" << DIL->getName() << '\"';
+      else {
+        LLT TypeToPrint = MRI ? getTypeToPrint(i, PrintedTypes, *MRI) : LLT{};
+        unsigned TiedOperandIdx = getTiedOperandIdx(i);
+        MO.print(OS, MST, TypeToPrint, /*PrintDef=*/true, IsStandalone,
+                 ShouldPrintRegisterTies, TiedOperandIdx, TRI, IntrinsicInfo);
+      }
     } else if (i == AsmDescOp && MO.isImm()) {
       // Pretty print the inline asm operand descriptor.
       OS << '$' << AsmOpCount++;

lib/CodeGen/PatchableFunction.cpp

@@ -49,6 +49,7 @@ static bool doesNotGeneratecode(const MachineInstr &MI) {
   case TargetOpcode::EH_LABEL:
   case TargetOpcode::GC_LABEL:
   case TargetOpcode::DBG_VALUE:
+  case TargetOpcode::DBG_LABEL:
     return true;
   }
 }

lib/CodeGen/SelectionDAG/InstrEmitter.cpp

@@ -753,6 +753,20 @@ InstrEmitter::EmitDbgValue(SDDbgValue *SD,
   return &*MIB;
 }
 
+MachineInstr *
+InstrEmitter::EmitDbgLabel(SDDbgLabel *SD) {
+  MDNode *Label = SD->getLabel();
+  DebugLoc DL = SD->getDebugLoc();
+  assert(cast<DILabel>(Label)->isValidLocationForIntrinsic(DL) &&
+         "Expected inlined-at fields to agree");
+
+  const MCInstrDesc &II = TII->get(TargetOpcode::DBG_LABEL);
+  MachineInstrBuilder MIB = BuildMI(*MF, DL, II);
+  MIB.addMetadata(Label);
+
+  return &*MIB;
+}
+
 /// EmitMachineNode - Generate machine code for a target-specific node and
 /// needed dependencies.
 ///

lib/CodeGen/SelectionDAG/InstrEmitter.h

@@ -113,6 +113,9 @@ class LLVM_LIBRARY_VISIBILITY InstrEmitter {
   MachineInstr *EmitDbgValue(SDDbgValue *SD,
                              DenseMap<SDValue, unsigned> &VRBaseMap);
 
+  /// Generate machine instruction for a dbg_label node.
+  MachineInstr *EmitDbgLabel(SDDbgLabel *SD);
+
   /// EmitNode - Generate machine code for a node and needed dependencies.
   ///
   void EmitNode(SDNode *Node, bool IsClone, bool IsCloned,

lib/CodeGen/SelectionDAG/SDNodeDbgValue.h

@@ -128,6 +128,28 @@ class SDDbgValue {
   bool isInvalidated() const { return Invalid; }
 };
 
+/// Holds the information from a dbg_label node through SDISel.
+/// We do not use SDValue here to avoid including its header.
+class SDDbgLabel {
+  MDNode *Label;
+  DebugLoc DL;
+  unsigned Order;
+
+public:
+  SDDbgLabel(MDNode *Label, DebugLoc dl, unsigned O)
+      : Label(Label), DL(std::move(dl)), Order(O) {}
+
+  /// Returns the MDNode pointer for the label.
+  MDNode *getLabel() const { return Label; }
+
+  /// Returns the DebugLoc.
+  DebugLoc getDebugLoc() const { return DL; }
+
+  /// Returns the SDNodeOrder.  This is the order of the preceding node in the
+  /// input.
+  unsigned getOrder() const { return Order; }
+};
+
 } // end llvm namespace
 
 #endif

lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp

@@ -911,6 +911,39 @@ EmitSchedule(MachineBasicBlock::iterator &InsertPos) {
     MachineBasicBlock *InsertBB = Emitter.getBlock();
     MachineBasicBlock::iterator Pos = InsertBB->getFirstTerminator();
     InsertBB->insert(Pos, DbgMIs.begin(), DbgMIs.end());
+
+    SDDbgInfo::DbgLabelIterator DLI = DAG->DbgLabelBegin();
+    SDDbgInfo::DbgLabelIterator DLE = DAG->DbgLabelEnd();
+    // Now emit the rest according to source order.
+    LastOrder = 0;
+    for (const auto &InstrOrder : Orders) {
+      unsigned Order = InstrOrder.first;
+      MachineInstr *MI = InstrOrder.second;
+      if (!MI)
+        continue;
+
+      // Insert all SDDbgLabel's whose order(s) are before "Order".
+      for (; DLI != DLE &&
+             (*DLI)->getOrder() >= LastOrder && (*DLI)->getOrder() < Order;
+             ++DLI) {
+        MachineInstr *DbgMI = Emitter.EmitDbgLabel(*DLI);
+        if (DbgMI) {
+          if (!LastOrder)
+            // Insert to start of the BB (after PHIs).
+            BB->insert(BBBegin, DbgMI);
+          else {
+            // Insert at the instruction, which may be in a different
+            // block, if the block was split by a custom inserter.
+            MachineBasicBlock::iterator Pos = MI;
+            MI->getParent()->insert(Pos, DbgMI);
+          }
+        }
+      }
+      if (DLI == DLE)
+        break;
+
+      LastOrder = Order;
+    }
   }
 
   InsertPos = Emitter.getInsertPos();

lib/CodeGen/SelectionDAG/SelectionDAG.cpp

@@ -7420,6 +7420,14 @@ void SelectionDAG::salvageDebugInfo(SDNode &N) {
     AddDbgValue(Dbg, Dbg->getSDNode(), false);
 }
 
+/// Creates a SDDbgLabel node.
+SDDbgLabel *SelectionDAG::getDbgLabel(DILabel *Label,
+                                      const DebugLoc &DL, unsigned O) {
+  assert(cast<DILabel>(Label)->isValidLocationForIntrinsic(DL) &&
+         "Expected inlined-at fields to agree");
+  return new (DbgInfo->getAlloc()) SDDbgLabel(Label, DL, O);
+}
+
 namespace {
 
 /// RAUWUpdateListener - Helper for ReplaceAllUsesWith - When the node
@@ -7905,6 +7913,10 @@ void SelectionDAG::AddDbgValue(SDDbgValue *DB, SDNode *SD, bool isParameter) {
   DbgInfo->add(DB, SD, isParameter);
 }
 
+void SelectionDAG::AddDbgLabel(SDDbgLabel *DB) {
+  DbgInfo->add(DB);
+}
+
 SDValue SelectionDAG::makeEquivalentMemoryOrdering(LoadSDNode *OldLoad,
                                                    SDValue NewMemOp) {
   assert(isa<MemSDNode>(NewMemOp.getNode()) && "Expected a memop node");

lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

@@ -5230,6 +5230,16 @@ SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I, unsigned Intrinsic) {
     }
     return nullptr;
   }
+  case Intrinsic::dbg_label: {
+    const DbgLabelInst &DI = cast<DbgLabelInst>(I);
+    DILabel *Label = DI.getLabel();
+    assert(Label && "Missing label");
+
+    SDDbgLabel *SDV;
+    SDV = DAG.getDbgLabel(Label, dl, SDNodeOrder);
+    DAG.AddDbgLabel(SDV);
+    return nullptr;
+  }
   case Intrinsic::dbg_value: {
     const DbgValueInst &DI = cast<DbgValueInst>(I);
     assert(DI.getVariable() && "Missing variable");