[RISCV] Support the large code model. (#70308)

Implement large code model for GlobalAddressSDNode and ExternalSymbolSDNode.

See discussion on
riscv-non-isa/riscv-elf-psabi-doc#388.

---------

Co-authored-by: Kuan-Lin Chen <rufus@andestech.com>

llvm/lib/Target/RISCV/CMakeLists.txt

@@ -31,6 +31,7 @@ add_llvm_target(RISCVCodeGen
   RISCVAsmPrinter.cpp
   RISCVCallingConv.cpp
   RISCVCodeGenPrepare.cpp
+  RISCVConstantPoolValue.cpp
   RISCVDeadRegisterDefinitions.cpp
   RISCVMakeCompressible.cpp
   RISCVExpandAtomicPseudoInsts.cpp

llvm/lib/Target/RISCV/RISCVAsmPrinter.cpp

@@ -17,6 +17,7 @@
 #include "MCTargetDesc/RISCVMatInt.h"
 #include "MCTargetDesc/RISCVTargetStreamer.h"
 #include "RISCV.h"
+#include "RISCVConstantPoolValue.h"
 #include "RISCVMachineFunctionInfo.h"
 #include "RISCVTargetMachine.h"
 #include "TargetInfo/RISCVTargetInfo.h"
@@ -77,6 +78,8 @@ class RISCVAsmPrinter : public AsmPrinter {
 
   void emitInstruction(const MachineInstr *MI) override;
 
+  void emitMachineConstantPoolValue(MachineConstantPoolValue *MCPV) override;
+
   bool PrintAsmOperand(const MachineInstr *MI, unsigned OpNo,
                        const char *ExtraCode, raw_ostream &OS) override;
   bool PrintAsmMemoryOperand(const MachineInstr *MI, unsigned OpNo,
@@ -1080,3 +1083,23 @@ bool RISCVAsmPrinter::lowerToMCInst(const MachineInstr *MI, MCInst &OutMI) {
   }
   return false;
 }
+
+void RISCVAsmPrinter::emitMachineConstantPoolValue(
+    MachineConstantPoolValue *MCPV) {
+  auto *RCPV = static_cast<RISCVConstantPoolValue *>(MCPV);
+  MCSymbol *MCSym;
+
+  if (RCPV->isGlobalValue()) {
+    auto *GV = RCPV->getGlobalValue();
+    MCSym = getSymbol(GV);
+  } else {
+    assert(RCPV->isExtSymbol() && "unrecognized constant pool type");
+    auto Sym = RCPV->getSymbol();
+    MCSym = GetExternalSymbolSymbol(Sym);
+  }
+
+  const MCExpr *Expr =
+      MCSymbolRefExpr::create(MCSym, MCSymbolRefExpr::VK_None, OutContext);
+  uint64_t Size = getDataLayout().getTypeAllocSize(RCPV->getType());
+  OutStreamer->emitValue(Expr, Size);
+}

llvm/lib/Target/RISCV/RISCVConstantPoolValue.cpp

@@ -0,0 +1,81 @@
+//===------- RISCVConstantPoolValue.cpp - RISC-V constantpool value -------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the RISC-V specific constantpool value class.
+//
+//===----------------------------------------------------------------------===//
+
+#include "RISCVConstantPoolValue.h"
+#include "llvm/ADT/FoldingSet.h"
+#include "llvm/IR/Constants.h"
+#include "llvm/IR/DerivedTypes.h"
+#include "llvm/IR/GlobalValue.h"
+#include "llvm/IR/Type.h"
+#include "llvm/Support/Casting.h"
+#include "llvm/Support/raw_ostream.h"
+
+using namespace llvm;
+
+RISCVConstantPoolValue::RISCVConstantPoolValue(Type *Ty, const GlobalValue *GV)
+    : MachineConstantPoolValue(Ty), GV(GV), Kind(RISCVCPKind::GlobalValue) {}
+
+RISCVConstantPoolValue::RISCVConstantPoolValue(LLVMContext &C, StringRef S)
+    : MachineConstantPoolValue(Type::getInt64Ty(C)), S(S),
+      Kind(RISCVCPKind::ExtSymbol) {}
+
+RISCVConstantPoolValue *RISCVConstantPoolValue::Create(const GlobalValue *GV) {
+  return new RISCVConstantPoolValue(GV->getType(), GV);
+}
+
+RISCVConstantPoolValue *RISCVConstantPoolValue::Create(LLVMContext &C,
+                                                       StringRef S) {
+  return new RISCVConstantPoolValue(C, S);
+}
+
+int RISCVConstantPoolValue::getExistingMachineCPValue(MachineConstantPool *CP,
+                                                      Align Alignment) {
+  const std::vector<MachineConstantPoolEntry> &Constants = CP->getConstants();
+  for (unsigned i = 0, e = Constants.size(); i != e; ++i) {
+    if (Constants[i].isMachineConstantPoolEntry() &&
+        Constants[i].getAlign() >= Alignment) {
+      auto *CPV =
+          static_cast<RISCVConstantPoolValue *>(Constants[i].Val.MachineCPVal);
+      if (equals(CPV))
+        return i;
+    }
+  }
+
+  return -1;
+}
+
+void RISCVConstantPoolValue::addSelectionDAGCSEId(FoldingSetNodeID &ID) {
+  if (isGlobalValue())
+    ID.AddPointer(GV);
+  else {
+    assert(isExtSymbol() && "unrecognized constant pool type");
+    ID.AddString(S);
+  }
+}
+
+void RISCVConstantPoolValue::print(raw_ostream &O) const {
+  if (isGlobalValue())
+    O << GV->getName();
+  else {
+    assert(isExtSymbol() && "unrecognized constant pool type");
+    O << S;
+  }
+}
+
+bool RISCVConstantPoolValue::equals(const RISCVConstantPoolValue *A) const {
+  if (isGlobalValue() && A->isGlobalValue())
+    return GV == A->GV;
+  if (isExtSymbol() && A->isExtSymbol())
+    return S == A->S;
+
+  return false;
+}

llvm/lib/Target/RISCV/RISCVConstantPoolValue.h

@@ -0,0 +1,63 @@
+//===--- RISCVConstantPoolValue.h - RISC-V constantpool value ---*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the RISC-V specific constantpool value class.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_TARGET_RISCV_RISCVCONSTANTPOOLVALUE_H
+#define LLVM_LIB_TARGET_RISCV_RISCVCONSTANTPOOLVALUE_H
+
+#include "llvm/ADT/StringRef.h"
+#include "llvm/CodeGen/MachineConstantPool.h"
+#include "llvm/Support/Casting.h"
+#include "llvm/Support/ErrorHandling.h"
+
+namespace llvm {
+
+class BlockAddress;
+class GlobalValue;
+class LLVMContext;
+
+/// A RISCV-specific constant pool value.
+class RISCVConstantPoolValue : public MachineConstantPoolValue {
+  const GlobalValue *GV;
+  const StringRef S;
+
+  RISCVConstantPoolValue(Type *Ty, const GlobalValue *GV);
+  RISCVConstantPoolValue(LLVMContext &C, StringRef S);
+
+private:
+  enum class RISCVCPKind { ExtSymbol, GlobalValue };
+  RISCVCPKind Kind;
+
+public:
+  ~RISCVConstantPoolValue() = default;
+
+  static RISCVConstantPoolValue *Create(const GlobalValue *GV);
+  static RISCVConstantPoolValue *Create(LLVMContext &C, StringRef S);
+
+  bool isGlobalValue() const { return Kind == RISCVCPKind::GlobalValue; }
+  bool isExtSymbol() const { return Kind == RISCVCPKind::ExtSymbol; }
+
+  const GlobalValue *getGlobalValue() const { return GV; }
+  StringRef getSymbol() const { return S; }
+
+  int getExistingMachineCPValue(MachineConstantPool *CP,
+                                Align Alignment) override;
+
+  void addSelectionDAGCSEId(FoldingSetNodeID &ID) override;
+
+  void print(raw_ostream &O) const override;
+
+  bool equals(const RISCVConstantPoolValue *A) const;
+};
+
+} // end namespace llvm
+
+#endif

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -14,6 +14,7 @@
 #include "RISCVISelLowering.h"
 #include "MCTargetDesc/RISCVMatInt.h"
 #include "RISCV.h"
+#include "RISCVConstantPoolValue.h"
 #include "RISCVMachineFunctionInfo.h"
 #include "RISCVRegisterInfo.h"
 #include "RISCVSubtarget.h"
@@ -7518,6 +7519,27 @@ static SDValue getTargetNode(JumpTableSDNode *N, const SDLoc &DL, EVT Ty,
   return DAG.getTargetJumpTable(N->getIndex(), Ty, Flags);
 }
 
+static SDValue getLargeGlobalAddress(GlobalAddressSDNode *N, const SDLoc &DL,
+                                     EVT Ty, SelectionDAG &DAG) {
+  RISCVConstantPoolValue *CPV = RISCVConstantPoolValue::Create(N->getGlobal());
+  SDValue CPAddr = DAG.getTargetConstantPool(CPV, Ty, Align(8));
+  SDValue LC = DAG.getNode(RISCVISD::LLA, DL, Ty, CPAddr);
+  return DAG.getLoad(
+      Ty, DL, DAG.getEntryNode(), LC,
+      MachinePointerInfo::getConstantPool(DAG.getMachineFunction()));
+}
+
+static SDValue getLargeExternalSymbol(ExternalSymbolSDNode *N, const SDLoc &DL,
+                                      EVT Ty, SelectionDAG &DAG) {
+  RISCVConstantPoolValue *CPV =
+      RISCVConstantPoolValue::Create(*DAG.getContext(), N->getSymbol());
+  SDValue CPAddr = DAG.getTargetConstantPool(CPV, Ty, Align(8));
+  SDValue LC = DAG.getNode(RISCVISD::LLA, DL, Ty, CPAddr);
+  return DAG.getLoad(
+      Ty, DL, DAG.getEntryNode(), LC,
+      MachinePointerInfo::getConstantPool(DAG.getMachineFunction()));
+}
+
 template <class NodeTy>
 SDValue RISCVTargetLowering::getAddr(NodeTy *N, SelectionDAG &DAG,
                                      bool IsLocal, bool IsExternWeak) const {
@@ -7586,6 +7608,14 @@ SDValue RISCVTargetLowering::getAddr(NodeTy *N, SelectionDAG &DAG,
     // expands to (addi (auipc %pcrel_hi(sym)) %pcrel_lo(auipc)).
     return DAG.getNode(RISCVISD::LLA, DL, Ty, Addr);
   }
+  case CodeModel::Large: {
+    if (GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(N))
+      return getLargeGlobalAddress(G, DL, Ty, DAG);
+
+    // Using pc-relative mode for other node type.
+    SDValue Addr = getTargetNode(N, DL, Ty, DAG, 0);
+    return DAG.getNode(RISCVISD::LLA, DL, Ty, Addr);
+  }
   }
 }
 
@@ -19590,7 +19620,12 @@ SDValue RISCVTargetLowering::LowerCall(CallLoweringInfo &CLI,
   // If the callee is a GlobalAddress/ExternalSymbol node, turn it into a
   // TargetGlobalAddress/TargetExternalSymbol node so that legalize won't
   // split it and then direct call can be matched by PseudoCALL.
-  if (GlobalAddressSDNode *S = dyn_cast<GlobalAddressSDNode>(Callee)) {
+  if (getTargetMachine().getCodeModel() == CodeModel::Large) {
+    if (auto *S = dyn_cast<GlobalAddressSDNode>(Callee))
+      Callee = getLargeGlobalAddress(S, DL, PtrVT, DAG);
+    else if (auto *S = dyn_cast<ExternalSymbolSDNode>(Callee))
+      Callee = getLargeExternalSymbol(S, DL, PtrVT, DAG);
+  } else if (GlobalAddressSDNode *S = dyn_cast<GlobalAddressSDNode>(Callee)) {
     const GlobalValue *GV = S->getGlobal();
     Callee = DAG.getTargetGlobalAddress(GV, DL, PtrVT, 0, RISCVII::MO_CALL);
   } else if (ExternalSymbolSDNode *S = dyn_cast<ExternalSymbolSDNode>(Callee)) {

llvm/lib/Target/RISCV/RISCVTargetObjectFile.cpp

@@ -161,7 +161,7 @@ bool RISCVELFTargetObjectFile::isConstantInSmallSection(
 MCSection *RISCVELFTargetObjectFile::getSectionForConstant(
     const DataLayout &DL, SectionKind Kind, const Constant *C,
     Align &Alignment) const {
-  if (isConstantInSmallSection(DL, C)) {
+  if (C && isConstantInSmallSection(DL, C)) {
     if (Kind.isMergeableConst4())
       return SmallROData4Section;
     if (Kind.isMergeableConst8())