ARM/ELF: Better codegen for global variable addresses.

In PIC mode we were previously computing global variable addresses (or GOT
entry addresses) by adding the PC, the PC-relative GOT displacement and
the GOT-relative symbol/GOT entry displacement. Because the latter two
displacements are fixed, we ended up performing one more addition than
necessary.

This change causes us to compute addresses using a single PC-relative
displacement, resulting in a shorter code sequence. This reduces code size
by about 4% in a recent build of Chromium for Android.

As a result of this change we no longer need to compute the GOT base address
in the ARM backend, which allows us to remove the Global Base Reg pass and
SDAG lowering for the GOT.

We also now no longer use the GOT when addressing a symbol which is known
to be defined in the same linkage unit. Specifically, the symbol must have
either hidden visibility or a strong definition in the current module in
order to not use the the GOT.

This is a change from the previous behaviour where we would use the GOT to
address externally visible symbols defined in the same module. I think the
only cases where this could matter are cases involving symbol interposition,
but we don't really support that well anyway.

Differential Revision: http://reviews.llvm.org/D13650

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@251322 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/MC/MCExpr.h b/include/llvm/MC/MCExpr.h
index 76da86c..1d6bdef 100644 (file)
--- a/include/llvm/MC/MCExpr.h
+++ b/include/llvm/MC/MCExpr.h
@@ -188,6 +188,7 @@ public:
     VK_WEAKREF,   // The link between the symbols in .weakref foo, bar
 
     VK_ARM_NONE,
+    VK_ARM_GOT_PREL,
     VK_ARM_TARGET1,
     VK_ARM_TARGET2,
     VK_ARM_PREL31,

diff --git a/lib/MC/MCExpr.cpp b/lib/MC/MCExpr.cpp
index 9d01e13..caa5020 100644 (file)
--- a/lib/MC/MCExpr.cpp
+++ b/lib/MC/MCExpr.cpp
@@ -202,6 +202,7 @@ StringRef MCSymbolRefExpr::getVariantKindName(VariantKind Kind) {
   case VK_SIZE: return "SIZE";
   case VK_WEAKREF: return "WEAKREF";
   case VK_ARM_NONE: return "none";
+  case VK_ARM_GOT_PREL: return "GOT_PREL";
   case VK_ARM_TARGET1: return "target1";
   case VK_ARM_TARGET2: return "target2";
   case VK_ARM_PREL31: return "prel31";
@@ -311,7 +312,6 @@ MCSymbolRefExpr::getVariantKindForName(StringRef Name) {
     .Case("got", VK_GOT)
     .Case("gotoff", VK_GOTOFF)
     .Case("gotpcrel", VK_GOTPCREL)
-    .Case("got_prel", VK_GOTPCREL)
     .Case("gottpoff", VK_GOTTPOFF)
     .Case("indntpoff", VK_INDNTPOFF)
     .Case("ntpoff", VK_NTPOFF)
@@ -383,6 +383,7 @@ MCSymbolRefExpr::getVariantKindForName(StringRef Name) {
     .Case("got@tlsld@h", VK_PPC_GOT_TLSLD_HI)
     .Case("got@tlsld@ha", VK_PPC_GOT_TLSLD_HA)
     .Case("none", VK_ARM_NONE)
+    .Case("got_prel", VK_ARM_GOT_PREL)
     .Case("target1", VK_ARM_TARGET1)
     .Case("target2", VK_ARM_TARGET2)
     .Case("prel31", VK_ARM_PREL31)

diff --git a/lib/Target/ARM/ARM.h b/lib/Target/ARM/ARM.h
index 9550a3a..cd7540e 100644 (file)
--- a/lib/Target/ARM/ARM.h
+++ b/lib/Target/ARM/ARM.h
@@ -35,7 +35,6 @@ FunctionPass *createARMISelDag(ARMBaseTargetMachine &TM,
 FunctionPass *createA15SDOptimizerPass();
 FunctionPass *createARMLoadStoreOptimizationPass(bool PreAlloc = false);
 FunctionPass *createARMExpandPseudoPass();
-FunctionPass *createARMGlobalBaseRegPass();
 FunctionPass *createARMConstantIslandPass();
 FunctionPass *createMLxExpansionPass();
 FunctionPass *createThumb2ITBlockPass();

diff --git a/lib/Target/ARM/ARMAsmPrinter.cpp b/lib/Target/ARM/ARMAsmPrinter.cpp
index 9e2dc45..ef56a01 100644 (file)
--- a/lib/Target/ARM/ARMAsmPrinter.cpp
+++ b/lib/Target/ARM/ARMAsmPrinter.cpp
@@ -819,8 +819,7 @@ getModifierVariantKind(ARMCP::ARMCPModifier Modifier) {
   case ARMCP::TLSGD:       return MCSymbolRefExpr::VK_TLSGD;
   case ARMCP::TPOFF:       return MCSymbolRefExpr::VK_TPOFF;
   case ARMCP::GOTTPOFF:    return MCSymbolRefExpr::VK_GOTTPOFF;
-  case ARMCP::GOT:         return MCSymbolRefExpr::VK_GOT;
-  case ARMCP::GOTOFF:      return MCSymbolRefExpr::VK_GOTOFF;
+  case ARMCP::GOT_PREL:    return MCSymbolRefExpr::VK_ARM_GOT_PREL;
   }
   llvm_unreachable("Invalid ARMCPModifier!");
 }

diff --git a/lib/Target/ARM/ARMBaseInstrInfo.cpp b/lib/Target/ARM/ARMBaseInstrInfo.cpp
index a32af35..62f1dae 100644 (file)
--- a/lib/Target/ARM/ARMBaseInstrInfo.cpp
+++ b/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -1379,9 +1379,9 @@ static unsigned duplicateCPV(MachineFunction &MF, unsigned &CPI) {
   // instructions, so that's probably OK, but is PIC always correct when
   // we get here?
   if (ACPV->isGlobalValue())
-    NewCPV = ARMConstantPoolConstant::
-      Create(cast<ARMConstantPoolConstant>(ACPV)->getGV(), PCLabelId,
-             ARMCP::CPValue, 4);
+    NewCPV = ARMConstantPoolConstant::Create(
+        cast<ARMConstantPoolConstant>(ACPV)->getGV(), PCLabelId, ARMCP::CPValue,
+        4, ACPV->getModifier(), ACPV->mustAddCurrentAddress());
   else if (ACPV->isExtSymbol())
     NewCPV = ARMConstantPoolSymbol::
       Create(MF.getFunction()->getContext(),

diff --git a/lib/Target/ARM/ARMConstantPoolValue.cpp b/lib/Target/ARM/ARMConstantPoolValue.cpp
index 7d41c69..c9849b2 100644 (file)
--- a/lib/Target/ARM/ARMConstantPoolValue.cpp
+++ b/lib/Target/ARM/ARMConstantPoolValue.cpp
@@ -52,8 +52,7 @@ const char *ARMConstantPoolValue::getModifierText() const {
     // strings if that's legal.
   case ARMCP::no_modifier: return "none";
   case ARMCP::TLSGD:       return "tlsgd";
-  case ARMCP::GOT:         return "GOT";
-  case ARMCP::GOTOFF:      return "GOTOFF";
+  case ARMCP::GOT_PREL:    return "GOT_PREL";
   case ARMCP::GOTTPOFF:    return "gottpoff";
   case ARMCP::TPOFF:       return "tpoff";
   }

diff --git a/lib/Target/ARM/ARMConstantPoolValue.h b/lib/Target/ARM/ARMConstantPoolValue.h
index 36f63e2..21ad07d 100644 (file)
--- a/lib/Target/ARM/ARMConstantPoolValue.h
+++ b/lib/Target/ARM/ARMConstantPoolValue.h
@@ -39,8 +39,7 @@ namespace ARMCP {
   enum ARMCPModifier {
     no_modifier,
     TLSGD,
-    GOT,
-    GOTOFF,
+    GOT_PREL,
     GOTTPOFF,
     TPOFF
   };

diff --git a/lib/Target/ARM/ARMFastISel.cpp b/lib/Target/ARM/ARMFastISel.cpp
index 113f1f1..a2093eb 100644 (file)
--- a/lib/Target/ARM/ARMFastISel.cpp
+++ b/lib/Target/ARM/ARMFastISel.cpp
@@ -2939,48 +2939,51 @@ bool ARMFastISel::tryToFoldLoadIntoMI(MachineInstr *MI, unsigned OpNo,
 
 unsigned ARMFastISel::ARMLowerPICELF(const GlobalValue *GV,
                                      unsigned Align, MVT VT) {
-  bool UseGOTOFF = GV->hasLocalLinkage() || GV->hasHiddenVisibility();
-  ARMConstantPoolConstant *CPV =
-    ARMConstantPoolConstant::Create(GV, UseGOTOFF ? ARMCP::GOTOFF : ARMCP::GOT);
-  unsigned Idx = MCP.getConstantPoolIndex(CPV, Align);
+  bool UseGOT_PREL =
+      !(GV->hasHiddenVisibility() || GV->isStrongDefinitionForLinker());
+
+  LLVMContext *Context = &MF->getFunction()->getContext();
+  unsigned ARMPCLabelIndex = AFI->createPICLabelUId();
+  unsigned PCAdj = Subtarget->isThumb() ? 4 : 8;
+  ARMConstantPoolValue *CPV = ARMConstantPoolConstant::Create(
+      GV, ARMPCLabelIndex, ARMCP::CPValue, PCAdj,
+      UseGOT_PREL ? ARMCP::GOT_PREL : ARMCP::no_modifier,
+      /*AddCurrentAddress=*/UseGOT_PREL);
+
+  unsigned ConstAlign =
+      MF->getDataLayout().getPrefTypeAlignment(Type::getInt32PtrTy(*Context));
+  unsigned Idx = MF->getConstantPool()->getConstantPoolIndex(CPV, ConstAlign);
+
+  unsigned TempReg = MF->getRegInfo().createVirtualRegister(&ARM::rGPRRegClass);
+  unsigned Opc = isThumb2 ? ARM::t2LDRpci : ARM::LDRcp;
+  MachineInstrBuilder MIB =
+      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), TempReg)
+          .addConstantPoolIndex(Idx);
+  if (Opc == ARM::LDRcp)
+    MIB.addImm(0);
+  AddDefaultPred(MIB);
 
-  unsigned Opc;
-  unsigned DestReg1 = createResultReg(TLI.getRegClassFor(VT));
-  // Load value.
-  if (isThumb2) {
-    DestReg1 = constrainOperandRegClass(TII.get(ARM::t2LDRpci), DestReg1, 0);
-    AddOptionalDefs(BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
-                            TII.get(ARM::t2LDRpci), DestReg1)
-                    .addConstantPoolIndex(Idx));
-    Opc = UseGOTOFF ? ARM::t2ADDrr : ARM::t2LDRs;
-  } else {
-    // The extra immediate is for addrmode2.
-    DestReg1 = constrainOperandRegClass(TII.get(ARM::LDRcp), DestReg1, 0);
-    AddOptionalDefs(BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt,
-                            DbgLoc, TII.get(ARM::LDRcp), DestReg1)
-                    .addConstantPoolIndex(Idx).addImm(0));
-    Opc = UseGOTOFF ? ARM::ADDrr : ARM::LDRrs;
-  }
+  // Fix the address by adding pc.
+  unsigned DestReg = createResultReg(TLI.getRegClassFor(VT));
+  Opc = Subtarget->isThumb() ? ARM::tPICADD : UseGOT_PREL ? ARM::PICLDR
+                                                          : ARM::PICADD;
+  DestReg = constrainOperandRegClass(TII.get(Opc), DestReg, 0);
+  MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), DestReg)
+            .addReg(TempReg)
+            .addImm(ARMPCLabelIndex);
+  if (!Subtarget->isThumb())
+    AddDefaultPred(MIB);
 
-  unsigned GlobalBaseReg = AFI->getGlobalBaseReg();
-  if (GlobalBaseReg == 0) {
-    GlobalBaseReg = MRI.createVirtualRegister(TLI.getRegClassFor(VT));
-    AFI->setGlobalBaseReg(GlobalBaseReg);
+  if (UseGOT_PREL && Subtarget->isThumb()) {
+    unsigned NewDestReg = createResultReg(TLI.getRegClassFor(VT));
+    MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
+                  TII.get(ARM::t2LDRi12), NewDestReg)
+              .addReg(DestReg)
+              .addImm(0);
+    DestReg = NewDestReg;
+    AddOptionalDefs(MIB);
   }
-
-  unsigned DestReg2 = createResultReg(TLI.getRegClassFor(VT));
-  DestReg2 = constrainOperandRegClass(TII.get(Opc), DestReg2, 0);
-  DestReg1 = constrainOperandRegClass(TII.get(Opc), DestReg1, 1);
-  GlobalBaseReg = constrainOperandRegClass(TII.get(Opc), GlobalBaseReg, 2);
-  MachineInstrBuilder MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt,
-                                    DbgLoc, TII.get(Opc), DestReg2)
-                            .addReg(DestReg1)
-                            .addReg(GlobalBaseReg);
-  if (!UseGOTOFF)
-    MIB.addImm(0);
-  AddOptionalDefs(MIB);
-
-  return DestReg2;
+  return DestReg;
 }
 
 bool ARMFastISel::fastLowerArguments() {

diff --git a/lib/Target/ARM/ARMISelLowering.cpp b/lib/Target/ARM/ARMISelLowering.cpp
index 857c85c..36f8886 100644 (file)
--- a/lib/Target/ARM/ARMISelLowering.cpp
+++ b/lib/Target/ARM/ARMISelLowering.cpp
@@ -788,7 +788,6 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
 
   setOperationAction(ISD::GlobalAddress, MVT::i32,   Custom);
   setOperationAction(ISD::ConstantPool,  MVT::i32,   Custom);
-  setOperationAction(ISD::GLOBAL_OFFSET_TABLE, MVT::i32, Custom);
   setOperationAction(ISD::GlobalTLSAddress, MVT::i32, Custom);
   setOperationAction(ISD::BlockAddress, MVT::i32, Custom);
 
@@ -2637,10 +2636,19 @@ SDValue ARMTargetLowering::LowerGlobalAddressELF(SDValue Op,
   SDLoc dl(Op);
   const GlobalValue *GV = cast<GlobalAddressSDNode>(Op)->getGlobal();
   if (getTargetMachine().getRelocationModel() == Reloc::PIC_) {
-    bool UseGOTOFF = GV->hasLocalLinkage() || GV->hasHiddenVisibility();
-    ARMConstantPoolValue *CPV =
-      ARMConstantPoolConstant::Create(GV,
-                                      UseGOTOFF ? ARMCP::GOTOFF : ARMCP::GOT);
+    bool UseGOT_PREL =
+        !(GV->hasHiddenVisibility() || GV->isStrongDefinitionForLinker());
+
+    MachineFunction &MF = DAG.getMachineFunction();
+    ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
+    unsigned ARMPCLabelIndex = AFI->createPICLabelUId();
+    EVT PtrVT = getPointerTy(DAG.getDataLayout());
+    SDLoc dl(Op);
+    unsigned PCAdj = Subtarget->isThumb() ? 4 : 8;
+    ARMConstantPoolValue *CPV = ARMConstantPoolConstant::Create(
+        GV, ARMPCLabelIndex, ARMCP::CPValue, PCAdj,
+        UseGOT_PREL ? ARMCP::GOT_PREL : ARMCP::no_modifier,
+        /*AddCurrentAddress=*/UseGOT_PREL);
     SDValue CPAddr = DAG.getTargetConstantPool(CPV, PtrVT, 4);
     CPAddr = DAG.getNode(ARMISD::Wrapper, dl, MVT::i32, CPAddr);
     SDValue Result = DAG.getLoad(
@@ -2648,9 +2656,9 @@ SDValue ARMTargetLowering::LowerGlobalAddressELF(SDValue Op,
         MachinePointerInfo::getConstantPool(DAG.getMachineFunction()), false,
         false, false, 0);
     SDValue Chain = Result.getValue(1);
-    SDValue GOT = DAG.getGLOBAL_OFFSET_TABLE(PtrVT);
-    Result = DAG.getNode(ISD::ADD, dl, PtrVT, Result, GOT);
-    if (!UseGOTOFF)
+    SDValue PICLabel = DAG.getConstant(ARMPCLabelIndex, dl, MVT::i32);
+    Result = DAG.getNode(ARMISD::PIC_ADD, dl, PtrVT, Result, PICLabel);
+    if (UseGOT_PREL)
       Result = DAG.getLoad(PtrVT, dl, Chain, Result,
                            MachinePointerInfo::getGOT(DAG.getMachineFunction()),
                            false, false, false, 0);
@@ -2727,29 +2735,6 @@ SDValue ARMTargetLowering::LowerGlobalAddressWindows(SDValue Op,
   return Result;
 }
 
-SDValue ARMTargetLowering::LowerGLOBAL_OFFSET_TABLE(SDValue Op,
-                                                    SelectionDAG &DAG) const {
-  assert(Subtarget->isTargetELF() &&
-         "GLOBAL OFFSET TABLE not implemented for non-ELF targets");
-  MachineFunction &MF = DAG.getMachineFunction();
-  ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
-  unsigned ARMPCLabelIndex = AFI->createPICLabelUId();
-  EVT PtrVT = getPointerTy(DAG.getDataLayout());
-  SDLoc dl(Op);
-  unsigned PCAdj = Subtarget->isThumb() ? 4 : 8;
-  ARMConstantPoolValue *CPV =
-    ARMConstantPoolSymbol::Create(*DAG.getContext(), "_GLOBAL_OFFSET_TABLE_",
-                                  ARMPCLabelIndex, PCAdj);
-  SDValue CPAddr = DAG.getTargetConstantPool(CPV, PtrVT, 4);
-  CPAddr = DAG.getNode(ARMISD::Wrapper, dl, MVT::i32, CPAddr);
-  SDValue Result =
-      DAG.getLoad(PtrVT, dl, DAG.getEntryNode(), CPAddr,
-                  MachinePointerInfo::getConstantPool(DAG.getMachineFunction()),
-                  false, false, false, 0);
-  SDValue PICLabel = DAG.getConstant(ARMPCLabelIndex, dl, MVT::i32);
-  return DAG.getNode(ARMISD::PIC_ADD, dl, PtrVT, Result, PICLabel);
-}
-
 SDValue
 ARMTargetLowering::LowerEH_SJLJ_SETJMP(SDValue Op, SelectionDAG &DAG) const {
   SDLoc dl(Op);
@@ -6783,7 +6768,6 @@ SDValue ARMTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   case ISD::FCOPYSIGN:     return LowerFCOPYSIGN(Op, DAG);
   case ISD::RETURNADDR:    return LowerRETURNADDR(Op, DAG);
   case ISD::FRAMEADDR:     return LowerFRAMEADDR(Op, DAG);
-  case ISD::GLOBAL_OFFSET_TABLE: return LowerGLOBAL_OFFSET_TABLE(Op, DAG);
   case ISD::EH_SJLJ_SETJMP: return LowerEH_SJLJ_SETJMP(Op, DAG);
   case ISD::EH_SJLJ_LONGJMP: return LowerEH_SJLJ_LONGJMP(Op, DAG);
   case ISD::EH_SJLJ_SETUP_DISPATCH: return LowerEH_SJLJ_SETUP_DISPATCH(Op, DAG);

diff --git a/lib/Target/ARM/ARMISelLowering.h b/lib/Target/ARM/ARMISelLowering.h
index e4b8891..99a18f0 100644 (file)
--- a/lib/Target/ARM/ARMISelLowering.h
+++ b/lib/Target/ARM/ARMISelLowering.h
@@ -514,7 +514,6 @@ namespace llvm {
     SDValue LowerToTLSExecModels(GlobalAddressSDNode *GA,
                                  SelectionDAG &DAG,
                                  TLSModel::Model model) const;
-    SDValue LowerGLOBAL_OFFSET_TABLE(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerBR_JT(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerXALUO(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerSELECT(SDValue Op, SelectionDAG &DAG) const;

diff --git a/lib/Target/ARM/ARMInstrInfo.cpp b/lib/Target/ARM/ARMInstrInfo.cpp
index 39715aa..cf973d6 100644 (file)
--- a/lib/Target/ARM/ARMInstrInfo.cpp
+++ b/lib/Target/ARM/ARMInstrInfo.cpp
@@ -132,73 +132,3 @@ void ARMInstrInfo::expandLoadStackGuard(MachineBasicBlock::iterator MI,
   MIB.setMemRefs(MI->memoperands_begin(), MI->memoperands_end());
   AddDefaultPred(MIB);
 }
-
-namespace {
-/// ARMCGBR - Create Global Base Reg pass. This initializes the PIC
-/// global base register for ARM ELF.
-struct ARMCGBR : public MachineFunctionPass {
-  static char ID;
-  ARMCGBR() : MachineFunctionPass(ID) {}
-
-  bool runOnMachineFunction(MachineFunction &MF) override {
-    ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
-    if (AFI->getGlobalBaseReg() == 0)
-      return false;
-    const ARMSubtarget &STI =
-        static_cast<const ARMSubtarget &>(MF.getSubtarget());
-    // Don't do this for Thumb1.
-    if (STI.isThumb1Only())
-      return false;
-
-    const TargetMachine &TM = MF.getTarget();
-    if (TM.getRelocationModel() != Reloc::PIC_)
-      return false;
-
-    LLVMContext *Context = &MF.getFunction()->getContext();
-    unsigned ARMPCLabelIndex = AFI->createPICLabelUId();
-    unsigned PCAdj = STI.isThumb() ? 4 : 8;
-    ARMConstantPoolValue *CPV = ARMConstantPoolSymbol::Create(
-        *Context, "_GLOBAL_OFFSET_TABLE_", ARMPCLabelIndex, PCAdj);
-
-    unsigned Align =
-        MF.getDataLayout().getPrefTypeAlignment(Type::getInt32PtrTy(*Context));
-    unsigned Idx = MF.getConstantPool()->getConstantPoolIndex(CPV, Align);
-
-    MachineBasicBlock &FirstMBB = MF.front();
-    MachineBasicBlock::iterator MBBI = FirstMBB.begin();
-    DebugLoc DL = FirstMBB.findDebugLoc(MBBI);
-    unsigned TempReg =
-        MF.getRegInfo().createVirtualRegister(&ARM::rGPRRegClass);
-    unsigned Opc = STI.isThumb2() ? ARM::t2LDRpci : ARM::LDRcp;
-    const TargetInstrInfo &TII = *STI.getInstrInfo();
-    MachineInstrBuilder MIB = BuildMI(FirstMBB, MBBI, DL, TII.get(Opc), TempReg)
-                                  .addConstantPoolIndex(Idx);
-    if (Opc == ARM::LDRcp)
-      MIB.addImm(0);
-    AddDefaultPred(MIB);
-
-    // Fix the GOT address by adding pc.
-    unsigned GlobalBaseReg = AFI->getGlobalBaseReg();
-    Opc = STI.isThumb2() ? ARM::tPICADD : ARM::PICADD;
-    MIB = BuildMI(FirstMBB, MBBI, DL, TII.get(Opc), GlobalBaseReg)
-              .addReg(TempReg)
-              .addImm(ARMPCLabelIndex);
-    if (Opc == ARM::PICADD)
-      AddDefaultPred(MIB);
-
-    return true;
-  }
-
-  const char *getPassName() const override {
-    return "ARM PIC Global Base Reg Initialization";
-  }
-
-  void getAnalysisUsage(AnalysisUsage &AU) const override {
-    AU.setPreservesCFG();
-    MachineFunctionPass::getAnalysisUsage(AU);
-  }
-};
-}
-
-char ARMCGBR::ID = 0;
-FunctionPass *llvm::createARMGlobalBaseRegPass() { return new ARMCGBR(); }

diff --git a/lib/Target/ARM/ARMMachineFunctionInfo.cpp b/lib/Target/ARM/ARMMachineFunctionInfo.cpp
index 8ca4be7..ac0330f 100644 (file)
--- a/lib/Target/ARM/ARMMachineFunctionInfo.cpp
+++ b/lib/Target/ARM/ARMMachineFunctionInfo.cpp
@@ -20,5 +20,4 @@ ARMFunctionInfo::ARMFunctionInfo(MachineFunction &MF)
       RestoreSPFromFP(false), LRSpilledForFarJump(false),
       FramePtrSpillOffset(0), GPRCS1Offset(0), GPRCS2Offset(0), DPRCSOffset(0),
       GPRCS1Size(0), GPRCS2Size(0), DPRCSSize(0),
-      PICLabelUId(0), VarArgsFrameIndex(0), HasITBlocks(false),
-      GlobalBaseReg(0) {}
+      PICLabelUId(0), VarArgsFrameIndex(0), HasITBlocks(false) {}

diff --git a/lib/Target/ARM/ARMMachineFunctionInfo.h b/lib/Target/ARM/ARMMachineFunctionInfo.h
index 40ace69..d644797 100644 (file)
--- a/lib/Target/ARM/ARMMachineFunctionInfo.h
+++ b/lib/Target/ARM/ARMMachineFunctionInfo.h
@@ -110,11 +110,6 @@ class ARMFunctionInfo : public MachineFunctionInfo {
   /// pass.
   DenseMap<unsigned, unsigned> CPEClones;
 
-  /// GlobalBaseReg - keeps track of the virtual register initialized for
-  /// use as the global base register. This is used for PIC in some PIC
-  /// relocation models.
-  unsigned GlobalBaseReg;
-
   /// ArgumentStackSize - amount of bytes on stack consumed by the arguments
   /// being passed on the stack
   unsigned ArgumentStackSize;
@@ -133,7 +128,7 @@ public:
     FramePtrSpillOffset(0), GPRCS1Offset(0), GPRCS2Offset(0), DPRCSOffset(0),
     GPRCS1Size(0), GPRCS2Size(0), DPRCSAlignGapSize(0), DPRCSSize(0),
     NumAlignedDPRCS2Regs(0), PICLabelUId(0),
-    VarArgsFrameIndex(0), HasITBlocks(false), GlobalBaseReg(0) {}
+    VarArgsFrameIndex(0), HasITBlocks(false) {}
 
   explicit ARMFunctionInfo(MachineFunction &MF);
 
@@ -204,9 +199,6 @@ public:
   bool hasITBlocks() const { return HasITBlocks; }
   void setHasITBlocks(bool h) { HasITBlocks = h; }
 
-  unsigned getGlobalBaseReg() const { return GlobalBaseReg; }
-  void setGlobalBaseReg(unsigned Reg) { GlobalBaseReg = Reg; }
-
   void recordCPEClone(unsigned CPIdx, unsigned CPCloneIdx) {
     if (!CPEClones.insert(std::make_pair(CPCloneIdx, CPIdx)).second)
       llvm_unreachable("Duplicate entries!");

diff --git a/lib/Target/ARM/ARMTargetMachine.cpp b/lib/Target/ARM/ARMTargetMachine.cpp
index b581509..3e3c864 100644 (file)
--- a/lib/Target/ARM/ARMTargetMachine.cpp
+++ b/lib/Target/ARM/ARMTargetMachine.cpp
@@ -362,9 +362,6 @@ bool ARMPassConfig::addPreISel() {
 
 bool ARMPassConfig::addInstSelector() {
   addPass(createARMISelDag(getARMTargetMachine(), getOptLevel()));
-
-  if (TM->getTargetTriple().isOSBinFormatELF() && TM->Options.EnableFastISel)
-    addPass(createARMGlobalBaseRegPass());
   return false;
 }
 

diff --git a/lib/Target/ARM/MCTargetDesc/ARMELFObjectWriter.cpp b/lib/Target/ARM/MCTargetDesc/ARMELFObjectWriter.cpp
index 804d353..52eba8b 100644 (file)
--- a/lib/Target/ARM/MCTargetDesc/ARMELFObjectWriter.cpp
+++ b/lib/Target/ARM/MCTargetDesc/ARMELFObjectWriter.cpp
@@ -95,7 +95,7 @@ unsigned ARMELFObjectWriter::GetRelocTypeInner(const MCValue &Target,
       case MCSymbolRefExpr::VK_GOTTPOFF:
         Type = ELF::R_ARM_TLS_IE32;
         break;
-      case MCSymbolRefExpr::VK_GOTPCREL:
+      case MCSymbolRefExpr::VK_ARM_GOT_PREL:
         Type = ELF::R_ARM_GOT_PREL;
         break;
       }
@@ -192,7 +192,7 @@ unsigned ARMELFObjectWriter::GetRelocTypeInner(const MCValue &Target,
       case MCSymbolRefExpr::VK_GOTOFF:
         Type = ELF::R_ARM_GOTOFF32;
         break;
-      case MCSymbolRefExpr::VK_GOTPCREL:
+      case MCSymbolRefExpr::VK_ARM_GOT_PREL:
         Type = ELF::R_ARM_GOT_PREL;
         break;
       case MCSymbolRefExpr::VK_ARM_TARGET1:

diff --git a/test/CodeGen/ARM/emutls.ll b/test/CodeGen/ARM/emutls.ll
index a313b8c..7ba50dd 100644 (file)
--- a/test/CodeGen/ARM/emutls.ll
+++ b/test/CodeGen/ARM/emutls.ll
@@ -10,9 +10,7 @@ declare i8* @my_emutls_get_address(i8*)
 define i32 @my_get_xyz() {
 ; ARM32-LABEL: my_get_xyz:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl my_emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
 
@@ -34,9 +32,7 @@ entry:
 define i32 @f1() {
 ; ARM32-LABEL: f1:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
 
@@ -48,9 +44,7 @@ entry:
 define i32* @f2() {
 ; ARM32-LABEL: f2:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
 
@@ -61,9 +55,7 @@ entry:
 define i32 @f3() nounwind {
 ; ARM32-LABEL: f3:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
 
@@ -75,9 +67,7 @@ entry:
 define i32* @f4() {
 ; ARM32-LABEL: f4:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
 
@@ -88,9 +78,7 @@ entry:
 define i32 @f5() nounwind {
 ; ARM32-LABEL: f5:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
 
@@ -102,9 +90,7 @@ entry:
 define i32* @f6() {
 ; ARM32-LABEL: f6:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
 
@@ -115,9 +101,7 @@ entry:
 define i32 @f7() {
 ; ARM32-LABEL: f7:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
 
@@ -129,9 +113,7 @@ entry:
 define i32* @f8() {
 ; ARM32-LABEL: f8:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
 
@@ -142,9 +124,7 @@ entry:
 define i32 @f9() {
 ; ARM32-LABEL: f9:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
 
@@ -156,9 +136,7 @@ entry:
 define i32* @f10() {
 ; ARM32-LABEL: f10:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
 
@@ -169,9 +147,7 @@ entry:
 define i16 @f11() {
 ; ARM32-LABEL: f11:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldrh r0, [r0]
 
@@ -183,9 +159,7 @@ entry:
 define i32 @f12() {
 ; ARM32-LABEL: f12:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldrsh r0, [r0]
 
@@ -198,9 +172,7 @@ entry:
 define i8 @f13() {
 ; ARM32-LABEL: f13:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldrb r0, [r0]
 ; ARM32-NEXT: pop
@@ -213,9 +185,7 @@ entry:
 define i32 @f14() {
 ; ARM32-LABEL: f14:
 ; ARM32:        ldr r0,
-; ARM32-NEXT:   ldr r1,
-; ARM32:        add r0, pc, r0
-; ARM32-NEXT:   ldr r0, [r1, r0]
+; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldrsb r0, [r0]
 ; ARM32-NEXT: pop

diff --git a/test/CodeGen/ARM/fast-isel-pic.ll b/test/CodeGen/ARM/fast-isel-pic.ll
index 75b82e8..a4494ee 100644 (file)
--- a/test/CodeGen/ARM/fast-isel-pic.ll
+++ b/test/CodeGen/ARM/fast-isel-pic.ll
@@ -1,7 +1,7 @@
 ; RUN: llc < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=pic -mtriple=thumbv7-apple-ios | FileCheck %s --check-prefix=THUMB
 ; RUN: llc < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=pic -mtriple=armv7-apple-ios | FileCheck %s --check-prefix=ARMv7
-; RUN: llc < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=pic -mtriple=thumbv7-none-linux-gnueabi | FileCheck %s --check-prefix=THUMB-ELF
-; RUN: llc < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=pic -mtriple=armv7-none-linux-gnueabi | FileCheck %s --check-prefix=ARMv7-ELF
+; RUN: llc < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -arm-force-fast-isel -relocation-model=pic -mtriple=thumbv7-none-linux-gnueabi | FileCheck %s --check-prefix=THUMB-ELF
+; RUN: llc < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -arm-force-fast-isel -relocation-model=pic -mtriple=armv7-none-linux-gnueabi | FileCheck %s --check-prefix=ARMv7-ELF
 
 @g = global i32 0, align 4
 
@@ -13,8 +13,8 @@ entry:
 ; THUMB: add  [[reg0]], pc
 ; THUMB-ELF: LoadGV
 ; THUMB-ELF: ldr r[[reg0:[0-9]+]],
-; THUMB-ELF: ldr r[[reg1:[0-9]+]],
-; THUMB-ELF: ldr r[[reg0]], [r[[reg0]], r[[reg1]]]
+; THUMB-ELF: add r[[reg0]], pc
+; THUMB-ELF: ldr r[[reg0]], [r[[reg0]]]
 ; ARM: LoadGV
 ; ARM: ldr [[reg1:r[0-9]+]],
 ; ARM: add [[reg1]], pc, [[reg1]]
@@ -26,8 +26,7 @@ entry:
 ; ARMv7-ELF: ldr r[[reg2:[0-9]+]],
 ; ARMv7-ELF: .LPC
 ; ARMv7-ELF-NEXT: add r[[reg2]], pc
-; ARMv7-ELF: ldr r[[reg3:[0-9]+]],
-; ARMv7-ELF: ldr r[[reg2]], [r[[reg3]], r[[reg2]]]
+; ARMv7-ELF: ldr r[[reg2]], [r[[reg2]]]
   %tmp = load i32, i32* @g
   ret i32 %tmp
 }
@@ -43,8 +42,8 @@ entry:
 ; THUMB: ldr  r[[reg3]], [r[[reg3]]]
 ; THUMB-ELF: LoadIndirectSymbol
 ; THUMB-ELF: ldr r[[reg3:[0-9]+]],
-; THUMB-ELF: ldr r[[reg4:[0-9]+]],
-; THUMB-ELF: ldr r[[reg3]], [r[[reg3]], r[[reg4]]]
+; THUMB-ELF: ldr r[[reg4:[0-9]+]], [r[[reg3]]]
+; THUMB-ELF: ldr r0, [r[[reg4]]]
 ; ARM: LoadIndirectSymbol
 ; ARM: ldr [[reg4:r[0-9]+]],
 ; ARM: ldr [[reg4]], [pc, [[reg4]]]
@@ -56,9 +55,8 @@ entry:
 ; ARMv7-ELF: LoadIndirectSymbol
 ; ARMv7-ELF: ldr r[[reg5:[0-9]+]],
 ; ARMv7-ELF: .LPC
-; ARMv7-ELF-NEXT: add r[[reg5]], pc
-; ARMv7-ELF: ldr r[[reg6:[0-9]+]],
-; ARMv7-ELF: ldr r[[reg5]], [r[[reg6]], r[[reg5]]]
+; ARMv7-ELF: ldr r[[reg6:[0-9]+]], [pc, r[[reg5]]]
+; ARMv7-ELF: ldr r0, [r[[reg5]]]
   %tmp = load i32, i32* @i
   ret i32 %tmp
 }

diff --git a/test/CodeGen/ARM/globals.ll b/test/CodeGen/ARM/globals.ll
index bab96da..e6aa2db 100644 (file)
--- a/test/CodeGen/ARM/globals.ll
+++ b/test/CodeGen/ARM/globals.ll
@@ -60,16 +60,13 @@ define i32 @test1() {
 
 ; LinuxPIC-LABEL: test1:
 ; LinuxPIC:    ldr r0, .LCPI0_0
-; LinuxPIC:    ldr r1, .LCPI0_1
        
 ; LinuxPIC: .LPC0_0:
-; LinuxPIC:    add r0, pc, r0
-; LinuxPIC:    ldr r0, [r1, r0]
+; LinuxPIC:    ldr r0, [pc, r0]
 ; LinuxPIC:    ldr r0, [r0]
 ; LinuxPIC:    bx lr
 
 ; LinuxPIC: .align 2
 ; LinuxPIC: .LCPI0_0:
-; LinuxPIC:     .long _GLOBAL_OFFSET_TABLE_-(.LPC0_0+8)
-; LinuxPIC: .LCPI0_1:
-; LinuxPIC:     .long  G(GOT)
+; LinuxPIC: .Ltmp0:
+; LinuxPIC:     .long   G(GOT_PREL)-((.LPC0_0+8)-.Ltmp0)

diff --git a/test/CodeGen/ARM/load-global.ll b/test/CodeGen/ARM/load-global.ll
index 34748bc..eade2fd 100644 (file)
--- a/test/CodeGen/ARM/load-global.ll
+++ b/test/CodeGen/ARM/load-global.ll
@@ -4,6 +4,7 @@
 ; RUN: llc < %s -mtriple=thumbv6-apple-darwin -relocation-model=pic | FileCheck %s -check-prefix=PIC_T
 ; RUN: llc < %s -mtriple=armv7-apple-darwin -relocation-model=pic | FileCheck %s -check-prefix=PIC_V7
 ; RUN: llc < %s -mtriple=armv6-linux-gnueabi -relocation-model=pic | FileCheck %s -check-prefix=LINUX
+; RUN: llc < %s -mtriple=thumbv6-linux-gnueabi -relocation-model=pic | FileCheck %s -check-prefix=LINUX_T
 
 @G = external global i32
 
@@ -40,11 +41,14 @@ define i32 @test1() {
 
 ; LINUX: test1
 ; LINUX: ldr r0, .LCPI0_0
-; LINUX: ldr r1, .LCPI0_1
-; LINUX: add r0, pc, r0
-; LINUX: ldr r0, [r1, r0]
+; LINUX: ldr r0, [pc, r0]
 ; LINUX: ldr r0, [r0]
-; LINUX: .long G(GOT)
+; LINUX: .long G(GOT_PREL)-((.LPC0_0+8)-.Ltmp0)
+
+; LINUX_T: ldr r0, .LCPI0_0
+; LINUX_T: add r0, pc
+; LINUX_T: ldr r0, [r0]
+; LINUX_T: ldr r0, [r0]
        %tmp = load i32, i32* @G
        ret i32 %tmp
 }