Add support for pc-relative addressing on 64-bit RISC-V

llvm/include/llvm/CodeGen/MachineBasicBlock.h

@@ -115,6 +115,10 @@ class MachineBasicBlock
   /// branch.
   bool AddressTaken = false;
 
+  /// Indicate that this basic block needs its symbol be emitted regardless of
+  /// whether the flow just falls-through to it.
+  bool LabelMustBeEmitted = false;
+
   /// Indicate that this basic block is the entry block of an EH scope, i.e.,
   /// the block that used to have a catchpad or cleanuppad instruction in the
   /// LLVM IR.
@@ -159,6 +163,13 @@ class MachineBasicBlock
   /// branch.
   void setHasAddressTaken() { AddressTaken = true; }
 
+  /// Test whether this block must have its label emitted.
+  bool hasLabelMustBeEmitted() const { return LabelMustBeEmitted; }
+
+  /// Set this block to reflect that, regardless how we flow to it, we need
+  /// its label be emitted.
+  void setLabelMustBeEmitted() { LabelMustBeEmitted = true; }
+
   /// Return the MachineFunction containing this basic block.
   const MachineFunction *getParent() const { return xParent; }
   MachineFunction *getParent() { return xParent; }

llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp

@@ -2922,13 +2922,16 @@ void AsmPrinter::EmitBasicBlockStart(const MachineBasicBlock &MBB) const {
 
   // Print the main label for the block.
   if (MBB.pred_empty() ||
-      (isBlockOnlyReachableByFallthrough(&MBB) && !MBB.isEHFuncletEntry())) {
+      (isBlockOnlyReachableByFallthrough(&MBB) && !MBB.isEHFuncletEntry() &&
+       !MBB.hasLabelMustBeEmitted())) {
     if (isVerbose()) {
       // NOTE: Want this comment at start of line, don't emit with AddComment.
       OutStreamer->emitRawComment(" %bb." + Twine(MBB.getNumber()) + ":",
                                   false);
     }
   } else {
+    if (isVerbose() && MBB.hasLabelMustBeEmitted())
+      OutStreamer->AddComment("Label of block must be emitted");
     OutStreamer->EmitLabel(MBB.getSymbol());
   }
 }

llvm/lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp

@@ -21,6 +21,7 @@
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCInstBuilder.h"
+#include "llvm/MC/MCObjectFileInfo.h"
 #include "llvm/MC/MCParser/MCAsmLexer.h"
 #include "llvm/MC/MCParser/MCParsedAsmOperand.h"
 #include "llvm/MC/MCParser/MCTargetAsmParser.h"
@@ -79,9 +80,18 @@ class RISCVAsmParser : public MCTargetAsmParser {
   // synthesize the desired immedate value into the destination register.
   void emitLoadImm(unsigned DestReg, int64_t Value, MCStreamer &Out);
 
+  // Helper to emit a combination of AUIPC and SecondOpcode. Used to implement
+  // helpers such as emitLoadLocalAddress and emitLoadAddress.
+  void emitAuipcInstPair(MCOperand DestReg, MCOperand TmpReg,
+                         const MCExpr *Symbol, RISCVMCExpr::VariantKind VKHi,
+                         unsigned SecondOpcode, SMLoc IDLoc, MCStreamer &Out);
+
   // Helper to emit pseudo instruction "lla" used in PC-rel addressing.
   void emitLoadLocalAddress(MCInst &Inst, SMLoc IDLoc, MCStreamer &Out);
 
+  // Helper to emit pseudo instruction "la" used in GOT/PC-rel addressing.
+  void emitLoadAddress(MCInst &Inst, SMLoc IDLoc, MCStreamer &Out);
+
   /// Helper for processing MC instructions that have been successfully matched
   /// by MatchAndEmitInstruction. Modifications to the emitted instructions,
   /// like the expansion of pseudo instructions (e.g., "li"), can be performed
@@ -505,10 +515,12 @@ struct RISCVOperand : public MCParsedAsmOperand {
     bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK);
     if (!IsConstantImm) {
       IsValid = RISCVAsmParser::classifySymbolRef(getImm(), VK, Imm);
-      return IsValid && VK == RISCVMCExpr::VK_RISCV_PCREL_HI;
+      return IsValid && (VK == RISCVMCExpr::VK_RISCV_PCREL_HI ||
+                         VK == RISCVMCExpr::VK_RISCV_GOT_HI);
     } else {
       return isUInt<20>(Imm) && (VK == RISCVMCExpr::VK_RISCV_None ||
-                                 VK == RISCVMCExpr::VK_RISCV_PCREL_HI);
+                                 VK == RISCVMCExpr::VK_RISCV_PCREL_HI ||
+                                 VK == RISCVMCExpr::VK_RISCV_GOT_HI);
     }
   }
 
@@ -861,8 +873,8 @@ bool RISCVAsmParser::MatchAndEmitInstruction(SMLoc IDLoc, unsigned &Opcode,
   case Match_InvalidUImm20AUIPC:
     return generateImmOutOfRangeError(
         Operands, ErrorInfo, 0, (1 << 20) - 1,
-        "operand must be a symbol with %pcrel_hi() modifier or an integer in "
-        "the range");
+        "operand must be a symbol with a %pcrel_hi/%got_pcrel_hi modifier "
+        "or an integer in the range");
   case Match_InvalidSImm21Lsb0JAL:
     return generateImmOutOfRangeError(
         Operands, ErrorInfo, -(1 << 20), (1 << 20) - 2,
@@ -1408,42 +1420,82 @@ void RISCVAsmParser::emitLoadImm(unsigned DestReg, int64_t Value,
   }
 }
 
-void RISCVAsmParser::emitLoadLocalAddress(MCInst &Inst, SMLoc IDLoc,
-                                          MCStreamer &Out) {
-  // The local load address pseudo-instruction "lla" is used in PC-relative
-  // addressing of symbols:
-  //   lla rdest, symbol
-  // expands to
-  //   TmpLabel: AUIPC rdest, %pcrel_hi(symbol)
-  //             ADDI rdest, %pcrel_lo(TmpLabel)
+void RISCVAsmParser::emitAuipcInstPair(MCOperand DestReg, MCOperand TmpReg,
+                                       const MCExpr *Symbol,
+                                       RISCVMCExpr::VariantKind VKHi,
+                                       unsigned SecondOpcode, SMLoc IDLoc,
+                                       MCStreamer &Out) {
+  // A pair of instructions for PC-relative addressing; expands to
+  //   TmpLabel: AUIPC TmpReg, VKHi(symbol)
+  //             OP DestReg, TmpReg, %pcrel_lo(TmpLabel)
   MCContext &Ctx = getContext();
 
   MCSymbol *TmpLabel = Ctx.createTempSymbol(
       "pcrel_hi", /* AlwaysAddSuffix */ true, /* CanBeUnnamed */ false);
   Out.EmitLabel(TmpLabel);
 
-  MCOperand DestReg = Inst.getOperand(0);
-  const RISCVMCExpr *Symbol = RISCVMCExpr::create(
-      Inst.getOperand(1).getExpr(), RISCVMCExpr::VK_RISCV_PCREL_HI, Ctx);
-
+  const RISCVMCExpr *SymbolHi = RISCVMCExpr::create(Symbol, VKHi, Ctx);
   emitToStreamer(
-      Out, MCInstBuilder(RISCV::AUIPC).addOperand(DestReg).addExpr(Symbol));
+      Out, MCInstBuilder(RISCV::AUIPC).addOperand(TmpReg).addExpr(SymbolHi));
 
   const MCExpr *RefToLinkTmpLabel =
       RISCVMCExpr::create(MCSymbolRefExpr::create(TmpLabel, Ctx),
                           RISCVMCExpr::VK_RISCV_PCREL_LO, Ctx);
 
-  emitToStreamer(Out, MCInstBuilder(RISCV::ADDI)
-                          .addOperand(DestReg)
+  emitToStreamer(Out, MCInstBuilder(SecondOpcode)
                           .addOperand(DestReg)
+                          .addOperand(TmpReg)
                           .addExpr(RefToLinkTmpLabel));
 }
 
+void RISCVAsmParser::emitLoadLocalAddress(MCInst &Inst, SMLoc IDLoc,
+                                          MCStreamer &Out) {
+  // The load local address pseudo-instruction "lla" is used in PC-relative
+  // addressing of local symbols:
+  //   lla rdest, symbol
+  // expands to
+  //   TmpLabel: AUIPC rdest, %pcrel_hi(symbol)
+  //             ADDI rdest, rdest, %pcrel_lo(TmpLabel)
+  MCOperand DestReg = Inst.getOperand(0);
+  const MCExpr *Symbol = Inst.getOperand(1).getExpr();
+  emitAuipcInstPair(DestReg, DestReg, Symbol, RISCVMCExpr::VK_RISCV_PCREL_HI,
+                    RISCV::ADDI, IDLoc, Out);
+}
+
+void RISCVAsmParser::emitLoadAddress(MCInst &Inst, SMLoc IDLoc,
+                                     MCStreamer &Out) {
+  // The load address pseudo-instruction "la" is used in PC-relative and
+  // GOT-indirect addressing of global symbols:
+  //   la rdest, symbol
+  // expands to either (for non-PIC)
+  //   TmpLabel: AUIPC rdest, %pcrel_hi(symbol)
+  //             ADDI rdest, rdest, %pcrel_lo(TmpLabel)
+  // or (for PIC)
+  //   TmpLabel: AUIPC rdest, %got_pcrel_hi(symbol)
+  //             Lx rdest, %pcrel_lo(TmpLabel)(rdest)
+  MCOperand DestReg = Inst.getOperand(0);
+  const MCExpr *Symbol = Inst.getOperand(1).getExpr();
+  unsigned SecondOpcode;
+  RISCVMCExpr::VariantKind VKHi;
+  // FIXME: Should check .option (no)pic when implemented
+  if (getContext().getObjectFileInfo()->isPositionIndependent()) {
+    SecondOpcode = isRV64() ? RISCV::LD : RISCV::LW;
+    VKHi = RISCVMCExpr::VK_RISCV_GOT_HI;
+  } else {
+    SecondOpcode = RISCV::ADDI;
+    VKHi = RISCVMCExpr::VK_RISCV_PCREL_HI;
+  }
+  emitAuipcInstPair(DestReg, DestReg, Symbol, VKHi, SecondOpcode, IDLoc, Out);
+}
+
 bool RISCVAsmParser::processInstruction(MCInst &Inst, SMLoc IDLoc,
                                         MCStreamer &Out) {
   Inst.setLoc(IDLoc);
 
-  if (Inst.getOpcode() == RISCV::PseudoLI) {
+  switch (Inst.getOpcode()) {
+  default:
+    break;
+  case RISCV::PseudoLI: {
     unsigned Reg = Inst.getOperand(0).getReg();
     const MCOperand &Op1 = Inst.getOperand(1);
     if (Op1.isExpr()) {
@@ -1463,9 +1515,13 @@ bool RISCVAsmParser::processInstruction(MCInst &Inst, SMLoc IDLoc,
       Imm = SignExtend64<32>(Imm);
     emitLoadImm(Reg, Imm, Out);
     return false;
-  } else if (Inst.getOpcode() == RISCV::PseudoLLA) {
+  }
+  case RISCV::PseudoLLA:
     emitLoadLocalAddress(Inst, IDLoc, Out);
     return false;
+  case RISCV::PseudoLA:
+    emitLoadAddress(Inst, IDLoc, Out);
+    return false;
   }
 
   emitToStreamer(Out, Inst);

llvm/lib/Target/RISCV/MCTargetDesc/RISCVAsmBackend.cpp

@@ -33,6 +33,8 @@ bool RISCVAsmBackend::shouldForceRelocation(const MCAssembler &Asm,
   switch ((unsigned)Fixup.getKind()) {
   default:
     break;
+  case RISCV::fixup_riscv_got_hi20:
+    return true;
   case RISCV::fixup_riscv_pcrel_lo12_i:
   case RISCV::fixup_riscv_pcrel_lo12_s:
     // For pcrel_lo12, force a relocation if the target of the corresponding
@@ -48,6 +50,9 @@ bool RISCVAsmBackend::shouldForceRelocation(const MCAssembler &Asm,
     default:
       llvm_unreachable("Unexpected fixup kind for pcrel_lo12");
       break;
+    case RISCV::fixup_riscv_got_hi20:
+      ShouldForce = true;
+      break;
     case RISCV::fixup_riscv_pcrel_hi20:
       ShouldForce = T->getValue()->findAssociatedFragment() !=
                     Fixup.getValue()->findAssociatedFragment();
@@ -173,6 +178,8 @@ static uint64_t adjustFixupValue(const MCFixup &Fixup, uint64_t Value,
   switch (Kind) {
   default:
     llvm_unreachable("Unknown fixup kind!");
+  case RISCV::fixup_riscv_got_hi20:
+    llvm_unreachable("Relocation should be unconditionally forced\n");
   case FK_Data_1:
   case FK_Data_2:
   case FK_Data_4:

llvm/lib/Target/RISCV/MCTargetDesc/RISCVAsmBackend.h

@@ -80,6 +80,7 @@ class RISCVAsmBackend : public MCAsmBackend {
       { "fixup_riscv_pcrel_hi20",   12,     20,  MCFixupKindInfo::FKF_IsPCRel },
       { "fixup_riscv_pcrel_lo12_i", 20,     12,  MCFixupKindInfo::FKF_IsPCRel },
       { "fixup_riscv_pcrel_lo12_s",  0,     32,  MCFixupKindInfo::FKF_IsPCRel },
+      { "fixup_riscv_got_hi20",     12,     20,  MCFixupKindInfo::FKF_IsPCRel },
       { "fixup_riscv_jal",          12,     20,  MCFixupKindInfo::FKF_IsPCRel },
       { "fixup_riscv_branch",        0,     32,  MCFixupKindInfo::FKF_IsPCRel },
       { "fixup_riscv_rvc_jump",      2,     11,  MCFixupKindInfo::FKF_IsPCRel },

llvm/lib/Target/RISCV/MCTargetDesc/RISCVELFObjectWriter.cpp

@@ -84,6 +84,8 @@ unsigned RISCVELFObjectWriter::getRelocType(MCContext &Ctx,
     return ELF::R_RISCV_PCREL_LO12_I;
   case RISCV::fixup_riscv_pcrel_lo12_s:
     return ELF::R_RISCV_PCREL_LO12_S;
+  case RISCV::fixup_riscv_got_hi20:
+    return ELF::R_RISCV_GOT_HI20;
   case RISCV::fixup_riscv_jal:
     return ELF::R_RISCV_JAL;
   case RISCV::fixup_riscv_branch:

llvm/lib/Target/RISCV/MCTargetDesc/RISCVFixupKinds.h

@@ -35,6 +35,9 @@ enum Fixups {
   // fixup_riscv_pcrel_lo12_s - 12-bit fixup corresponding to pcrel_lo(foo) for
   // the S-type store instructions
   fixup_riscv_pcrel_lo12_s,
+  // fixup_riscv_got_hi20 - 20-bit fixup corresponding to got_pcrel_hi(foo) for
+  // instructions like auipc
+  fixup_riscv_got_hi20,
   // fixup_riscv_jal - 20-bit fixup for symbol references in the jal
   // instruction
   fixup_riscv_jal,

llvm/lib/Target/RISCV/MCTargetDesc/RISCVMCCodeEmitter.cpp

@@ -235,6 +235,9 @@ unsigned RISCVMCCodeEmitter::getImmOpValue(const MCInst &MI, unsigned OpNo,
     case RISCVMCExpr::VK_RISCV_PCREL_HI:
       FixupKind = RISCV::fixup_riscv_pcrel_hi20;
       break;
+    case RISCVMCExpr::VK_RISCV_GOT_HI:
+      FixupKind = RISCV::fixup_riscv_got_hi20;
+      break;
     case RISCVMCExpr::VK_RISCV_CALL:
       FixupKind = RISCV::fixup_riscv_call;
       break;

llvm/lib/Target/RISCV/MCTargetDesc/RISCVMCExpr.cpp

@@ -63,6 +63,7 @@ const MCFixup *RISCVMCExpr::getPCRelHiFixup() const {
     switch ((unsigned)F.getKind()) {
     default:
       continue;
+    case RISCV::fixup_riscv_got_hi20:
     case RISCV::fixup_riscv_pcrel_hi20:
       return &F;
     }
@@ -137,6 +138,7 @@ bool RISCVMCExpr::evaluateAsRelocatableImpl(MCValue &Res,
     case VK_RISCV_HI:
     case VK_RISCV_PCREL_LO:
     case VK_RISCV_PCREL_HI:
+    case VK_RISCV_GOT_HI:
       return false;
     }
   }
@@ -154,6 +156,7 @@ RISCVMCExpr::VariantKind RISCVMCExpr::getVariantKindForName(StringRef name) {
       .Case("hi", VK_RISCV_HI)
       .Case("pcrel_lo", VK_RISCV_PCREL_LO)
       .Case("pcrel_hi", VK_RISCV_PCREL_HI)
+      .Case("got_pcrel_hi", VK_RISCV_GOT_HI)
       .Default(VK_RISCV_Invalid);
 }
 
@@ -169,14 +172,16 @@ StringRef RISCVMCExpr::getVariantKindName(VariantKind Kind) {
     return "pcrel_lo";
   case VK_RISCV_PCREL_HI:
     return "pcrel_hi";
+  case VK_RISCV_GOT_HI:
+    return "got_pcrel_hi";
   }
 }
 
 bool RISCVMCExpr::evaluateAsConstant(int64_t &Res) const {
   MCValue Value;
 
   if (Kind == VK_RISCV_PCREL_HI || Kind == VK_RISCV_PCREL_LO ||
-      Kind == VK_RISCV_CALL)
+      Kind == VK_RISCV_GOT_HI || Kind == VK_RISCV_CALL)
     return false;
 
   if (!getSubExpr()->evaluateAsRelocatable(Value, nullptr, nullptr))

llvm/lib/Target/RISCV/MCTargetDesc/RISCVMCExpr.h

@@ -29,6 +29,7 @@ class RISCVMCExpr : public MCTargetExpr {
     VK_RISCV_HI,
     VK_RISCV_PCREL_LO,
     VK_RISCV_PCREL_HI,
+    VK_RISCV_GOT_HI,
     VK_RISCV_CALL,
     VK_RISCV_Invalid
   };
@@ -53,11 +54,11 @@ class RISCVMCExpr : public MCTargetExpr {
 
   const MCExpr *getSubExpr() const { return Expr; }
 
-  /// Get the MCExpr of the VK_RISCV_PCREL_HI Fixup that the
-  /// VK_RISCV_PCREL_LO points to.
+  /// Get the corresponding PC-relative HI fixup that a VK_RISCV_PCREL_LO
+  /// points to.
   ///
   /// \returns nullptr if this isn't a VK_RISCV_PCREL_LO pointing to a
-  /// VK_RISCV_PCREL_HI.
+  /// known PC-relative HI fixup.
   const MCFixup *getPCRelHiFixup() const;
 
   void printImpl(raw_ostream &OS, const MCAsmInfo *MAI) const override;