[AIX] Support per global code model.

Exploit the per global code model attribute on AIX. On AIX we need to
update both the code sequence used to access the global (either 1 or
2 instructions for small and large code model respectively) and the
storage mapping class that we emit the toc entry.

Author: mandlebug

llvm/include/llvm/MC/MCSymbolXCOFF.h

@@ -26,6 +26,8 @@ class MCSymbolXCOFF : public MCSymbol {
 
   static bool classof(const MCSymbol *S) { return S->isXCOFF(); }
 
+  enum CodeModel : uint8_t { CM_Small, CM_Large };
+
   static StringRef getUnqualifiedName(StringRef Name) {
     if (Name.back() == ']') {
       StringRef Lhs, Rhs;
@@ -72,8 +74,22 @@ class MCSymbolXCOFF : public MCSymbol {
 
   void setEHInfo() const { modifyFlags(SF_EHInfo, SF_EHInfo); }
 
+  bool hasPerSymbolCodeModel() const { return PerSymbolCodeModel.has_value(); }
+
+  CodeModel getPerSymbolCodeModel() const {
+    assert(hasPerSymbolCodeModel() &&
+           "Requested codemodel for symbol with out one");
+    return *PerSymbolCodeModel;
+  }
+
+  void setPerSymbolCodeModel(MCSymbolXCOFF::CodeModel Model) {
+    PerSymbolCodeModel = Model;
+  }
+
 private:
   std::optional<XCOFF::StorageClass> StorageClass;
+  std::optional<CodeModel> PerSymbolCodeModel;
+
   MCSectionXCOFF *RepresentedCsect = nullptr;
   XCOFF::VisibilityType VisibilityType = XCOFF::SYM_V_UNSPECIFIED;
   StringRef SymbolTableName;

llvm/lib/CodeGen/TargetLoweringObjectFileImpl.cpp

@@ -2680,21 +2680,35 @@ MCSection *TargetLoweringObjectFileXCOFF::getSectionForFunctionDescriptor(
 
 MCSection *TargetLoweringObjectFileXCOFF::getSectionForTOCEntry(
     const MCSymbol *Sym, const TargetMachine &TM) const {
-  // Use TE storage-mapping class when large code model is enabled so that
-  // the chance of needing -bbigtoc is decreased. Also, the toc-entry for
-  // EH info is never referenced directly using instructions so it can be
-  // allocated with TE storage-mapping class.
-  // The "_$TLSML" symbol for TLS local-dynamic mode requires XMC_TC, otherwise
-  // the AIX assembler will complain.
+  const XCOFF::StorageMappingClass SMC = [](const MCSymbol *Sym,
+                                            const TargetMachine &TM) {
+
+    const MCSymbolXCOFF *XSym = cast<MCSymbolXCOFF>(Sym);
+
+    // The "_$TLSML" symbol for TLS local-dynamic mode requires XMC_TC, otherwise
+    // the AIX assembler will complain.
+    if (XSym->getSymbolTableName() == "_$TLSML")
+      return XCOFF::XMC_TC;
+
+    // Use large code model toc entries for ehinfo symbols as they are
+    // never refrenced directly. The runtime loads their TOC entries
+    // address from the trace-back table.
+    if (XSym->isEHInfo())
+      return XCOFF::XMC_TE;
+
+    // If the symbol does not have a code model specified use the module value.
+    if (!XSym->hasPerSymbolCodeModel())
+      return TM.getCodeModel() == CodeModel::Large ? XCOFF::XMC_TE
+                                                   : XCOFF::XMC_TC;
+
+    return XSym->getPerSymbolCodeModel() == MCSymbolXCOFF::CM_Large
+               ? XCOFF::XMC_TE
+               : XCOFF::XMC_TC;
+  }(Sym, TM);
+
   return getContext().getXCOFFSection(
       cast<MCSymbolXCOFF>(Sym)->getSymbolTableName(), SectionKind::getData(),
-      XCOFF::CsectProperties(
-          ((TM.getCodeModel() == CodeModel::Large &&
-            cast<MCSymbolXCOFF>(Sym)->getSymbolTableName() != "_$TLSML") ||
-           cast<MCSymbolXCOFF>(Sym)->isEHInfo())
-              ? XCOFF::XMC_TE
-              : XCOFF::XMC_TC,
-          XCOFF::XTY_SD));
+      XCOFF::CsectProperties(SMC, XCOFF::XTY_SD));
 }
 
 MCSection *TargetLoweringObjectFileXCOFF::getSectionForLSDA(

llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp

@@ -474,6 +474,63 @@ static void collectTOCStats(PPCAsmPrinter::TOCEntryType Type) {
   }
 }
 
+static CodeModel::Model getCodeModel(const PPCSubtarget &S,
+                                     const TargetMachine &TM,
+                                     const MachineOperand &MO) {
+  assert(S.isAIXABI() && "ELF per global code model not supported yet");
+
+  CodeModel::Model ModuleModel = TM.getCodeModel();
+
+  // If the operand is not a global address then there is no
+  // global variable to carry an attribute.
+  if (!(MO.getType() == MachineOperand::MO_GlobalAddress))
+    return ModuleModel;
+
+  const GlobalValue *GV = MO.getGlobal();
+  assert(GV && "expected global for MO_GlobalAddress");
+
+  if (!isa<GlobalVariable>(GV))
+    return ModuleModel;
+
+  std::optional<CodeModel::Model> MaybeCodeModel =
+      dyn_cast<GlobalVariable>(GV)->getCodeModel();
+  if (MaybeCodeModel)
+    return *MaybeCodeModel;
+
+  return ModuleModel;
+}
+
+static void checkPerGlobalCodeModel(const GlobalValue *GV, MCSymbol *Sym) {
+  // ELF per global code model not supported yet.
+  if (!isa<MCSymbolXCOFF>(Sym))
+    return;
+
+  // Symbols that aren't global variables cannot have the attribute.
+  if (!isa<GlobalVariable>(GV))
+    return;
+
+  const GlobalVariable *GVar = cast<GlobalVariable>(GV);
+  std::optional<CodeModel::Model> MaybeCM = GVar->getCodeModel();
+
+  // No overriding atribute.
+  if (!MaybeCM)
+    return;
+
+  CodeModel::Model CM = *MaybeCM;
+
+  MCSymbolXCOFF *XSym = cast<MCSymbolXCOFF>(Sym);
+  switch (CM) {
+  case CodeModel::Large:
+    XSym->setPerSymbolCodeModel(MCSymbolXCOFF::CM_Large);
+    return;
+  case CodeModel::Small:
+    XSym->setPerSymbolCodeModel(MCSymbolXCOFF::CM_Small);
+    return;
+  default:
+    report_fatal_error("Invlaid code model for AIX");
+  }
+}
+
 /// lookUpOrCreateTOCEntry -- Given a symbol, look up whether a TOC entry
 /// exists for it.  If not, create one.  Then return a symbol that references
 /// the TOC entry.
@@ -723,8 +780,12 @@ void PPCAsmPrinter::EmitTlsCall(const MachineInstr *MI,
 static MCSymbol *getMCSymbolForTOCPseudoMO(const MachineOperand &MO,
                                            AsmPrinter &AP) {
   switch (MO.getType()) {
-  case MachineOperand::MO_GlobalAddress:
-    return AP.getSymbol(MO.getGlobal());
+  case MachineOperand::MO_GlobalAddress: {
+    const GlobalValue *GV = MO.getGlobal();
+    MCSymbol *Sym = AP.getSymbol(GV);
+    checkPerGlobalCodeModel(GV, Sym);
+    return Sym;
+  }
   case MachineOperand::MO_ConstantPoolIndex:
     return AP.GetCPISymbol(MO.getIndex());
   case MachineOperand::MO_JumpTableIndex:
@@ -1014,7 +1075,7 @@ void PPCAsmPrinter::emitInstruction(const MachineInstr *MI) {
     // relative to the toc-base.
     if (IsAIX) {
       assert(
-          TM.getCodeModel() == CodeModel::Small &&
+          getCodeModel(*Subtarget, TM, MO) == CodeModel::Small &&
           "This pseudo should only be selected for 32-bit small code model.");
       Exp = getTOCEntryLoadingExprForXCOFF(MOSymbol, Exp, VK);
       TmpInst.getOperand(1) = MCOperand::createExpr(Exp);
@@ -1098,7 +1159,12 @@ void PPCAsmPrinter::emitInstruction(const MachineInstr *MI) {
     return;
   }
   case PPC::ADDIStocHA: {
-    assert((IsAIX && !IsPPC64 && TM.getCodeModel() == CodeModel::Large) &&
+    const MachineOperand &MO = MI->getOperand(2);
+
+    assert((MO.isGlobal() || MO.isCPI() || MO.isJTI() || MO.isBlockAddress()) &&
+           "Invalid operand for ADDIStocHA.");
+    assert((IsAIX && !IsPPC64 &&
+            getCodeModel(*Subtarget, TM, MO) == CodeModel::Large) &&
            "This pseudo should only be selected for 32-bit large code model on"
            " AIX.");
 
@@ -1108,10 +1174,6 @@ void PPCAsmPrinter::emitInstruction(const MachineInstr *MI) {
     // Change the opcode to ADDIS.
     TmpInst.setOpcode(PPC::ADDIS);
 
-    const MachineOperand &MO = MI->getOperand(2);
-    assert((MO.isGlobal() || MO.isCPI() || MO.isJTI() || MO.isBlockAddress()) &&
-           "Invalid operand for ADDIStocHA.");
-
     // Map the machine operand to its corresponding MCSymbol.
     MCSymbol *MOSymbol = getMCSymbolForTOCPseudoMO(MO, *this);
 
@@ -1131,7 +1193,12 @@ void PPCAsmPrinter::emitInstruction(const MachineInstr *MI) {
     return;
   }
   case PPC::LWZtocL: {
-    assert(IsAIX && !IsPPC64 && TM.getCodeModel() == CodeModel::Large &&
+    const MachineOperand &MO = MI->getOperand(1);
+
+    assert((MO.isGlobal() || MO.isCPI() || MO.isJTI() || MO.isBlockAddress()) &&
+           "Invalid operand for LWZtocL.");
+    assert(IsAIX && !IsPPC64 &&
+           getCodeModel(*Subtarget, TM, MO) == CodeModel::Large &&
            "This pseudo should only be selected for 32-bit large code model on"
            " AIX.");
 
@@ -1141,10 +1208,6 @@ void PPCAsmPrinter::emitInstruction(const MachineInstr *MI) {
     // Change the opcode to lwz.
     TmpInst.setOpcode(PPC::LWZ);
 
-    const MachineOperand &MO = MI->getOperand(1);
-    assert((MO.isGlobal() || MO.isCPI() || MO.isJTI() || MO.isBlockAddress()) &&
-           "Invalid operand for LWZtocL.");
-
     // Map the machine operand to its corresponding MCSymbol.
     MCSymbol *MOSymbol = getMCSymbolForTOCPseudoMO(MO, *this);
 
@@ -1183,8 +1246,12 @@ void PPCAsmPrinter::emitInstruction(const MachineInstr *MI) {
 
     const bool GlobalToc =
         MO.isGlobal() && Subtarget->isGVIndirectSymbol(MO.getGlobal());
+
+    const CodeModel::Model CM =
+        IsAIX ? getCodeModel(*Subtarget, TM, MO) : TM.getCodeModel();
+
     if (GlobalToc || MO.isJTI() || MO.isBlockAddress() ||
-        (MO.isCPI() && TM.getCodeModel() == CodeModel::Large))
+        (MO.isCPI() && CM == CodeModel::Large))
       MOSymbol = lookUpOrCreateTOCEntry(MOSymbol, getTOCEntryTypeForMO(MO), VK);
 
     VK = IsAIX ? MCSymbolRefExpr::VK_PPC_U : MCSymbolRefExpr::VK_PPC_TOC_HA;
@@ -1225,8 +1292,9 @@ void PPCAsmPrinter::emitInstruction(const MachineInstr *MI) {
     const MCSymbol *MOSymbol = getMCSymbolForTOCPseudoMO(MO, *this);
 
     MCSymbolRefExpr::VariantKind VK = GetVKForMO(MO);
-
-    if (!MO.isCPI() || TM.getCodeModel() == CodeModel::Large)
+    CodeModel::Model CM =
+        IsAIX ? getCodeModel(*Subtarget, TM, MO) : TM.getCodeModel();
+    if (!MO.isCPI() || CM == CodeModel::Large)
       MOSymbol = lookUpOrCreateTOCEntry(MOSymbol, getTOCEntryTypeForMO(MO), VK);
 
     VK = IsAIX ? MCSymbolRefExpr::VK_PPC_L : MCSymbolRefExpr::VK_PPC_TOC_LO;

llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp

@@ -558,6 +558,43 @@ static bool hasTocDataAttr(SDValue Val, unsigned PointerSize) {
   return true;
 }
 
+static CodeModel::Model getCodeModel(const PPCSubtarget &Subtarget,
+                                     const TargetMachine &TM,
+                                     const SDNode *Node) {
+  // If there isn't an attribute to override the module code model
+  // this will be the effective code model.
+  CodeModel::Model ModuleModel = TM.getCodeModel();
+
+  // Initially support per global code model for AIX only.
+  if (!Subtarget.isAIXABI())
+    return ModuleModel;
+
+  // If the operand is not a global address there is no
+  // GlobalVariable to query for an attribute.
+  SDValue Operand = Node->getOperand(0);
+  if (!isa<GlobalAddressSDNode>(Operand))
+    return ModuleModel;
+
+  GlobalAddressSDNode *GA = cast<GlobalAddressSDNode>(Operand);
+  if (!GA)
+    return ModuleModel;
+
+  const GlobalValue *GV = GA->getGlobal();
+  if (!GV || !isa<GlobalVariable>(GV))
+    return ModuleModel;
+
+  std::optional<CodeModel::Model> MaybeCodeModel =
+      dyn_cast<GlobalVariable>(GV)->getCodeModel();
+  if (MaybeCodeModel) {
+    CodeModel::Model CM = *MaybeCodeModel;
+    assert((CM == CodeModel::Small || CM == CodeModel::Large) &&
+           "invalid code model for AIX");
+    return CM;
+  }
+
+  return ModuleModel;
+}
+
 /// isInt32Immediate - This method tests to see if the node is a 32-bit constant
 /// operand. If so Imm will receive the 32-bit value.
 static bool isInt32Immediate(SDNode *N, unsigned &Imm) {
@@ -6093,7 +6130,8 @@ void PPCDAGToDAGISel::Select(SDNode *N) {
     const bool isAIXABI = Subtarget->isAIXABI();
 
     // PowerPC only support small, medium and large code model.
-    const CodeModel::Model CModel = TM.getCodeModel();
+    const CodeModel::Model CModel = getCodeModel(*Subtarget, TM, N);
+
     assert(!(CModel == CodeModel::Tiny || CModel == CodeModel::Kernel) &&
            "PowerPC doesn't support tiny or kernel code models.");
 

llvm/lib/Target/PowerPC/PPCSubtarget.cpp

@@ -189,6 +189,15 @@ bool PPCSubtarget::isGVIndirectSymbol(const GlobalValue *GV) const {
   // Large code model always uses the TOC even for local symbols.
   if (TM.getCodeModel() == CodeModel::Large)
     return true;
+
+  // AIX may have a per global code model attribute.
+  if (isAIXABI() && isa<GlobalVariable>(GV)) {
+    const GlobalVariable *GVar = cast<GlobalVariable>(GV);
+    std::optional<CodeModel::Model> OptionalCM = GVar->getCodeModel();
+    if (OptionalCM && *OptionalCM == CodeModel::Large)
+      return true;
+  }
+
   if (TM.shouldAssumeDSOLocal(*GV->getParent(), GV))
     return false;
   return true;