[AArch64] Add Tiny Code Model for AArch64

This adds the plumbing for the Tiny code model for the AArch64 backend. This,
instead of loading addresses through the normal ADRP;ADD pair used in the Small
model, uses a single ADR. The 21 bit range of an ADR means that the code and
its statically defined symbols need to be within 1MB of each other.

This makes it mostly interesting for embedded applications where we want to fit
as much as we can in as small a space as possible.

Differential Revision: https://reviews.llvm.org/D49673

llvm-svn: 340397

llvm/bindings/go/llvm/target.go

@@ -62,6 +62,7 @@ const (
 const (
 	CodeModelDefault    CodeModel = C.LLVMCodeModelDefault
 	CodeModelJITDefault CodeModel = C.LLVMCodeModelJITDefault
+	CodeModelTiny       CodeModel = C.LLVMCodeModelTiny
 	CodeModelSmall      CodeModel = C.LLVMCodeModelSmall
 	CodeModelKernel     CodeModel = C.LLVMCodeModelKernel
 	CodeModelMedium     CodeModel = C.LLVMCodeModelMedium

llvm/docs/CommandGuide/lli.rst

@@ -125,6 +125,7 @@ CODE GENERATION OPTIONS
  .. code-block:: text
 
       default: Target default code model
+      tiny: Tiny code model
       small: Small code model
       kernel: Kernel code model
       medium: Medium code model

llvm/include/llvm-c/TargetMachine.h

@@ -45,6 +45,7 @@ typedef enum {
 typedef enum {
     LLVMCodeModelDefault,
     LLVMCodeModelJITDefault,
+    LLVMCodeModelTiny,
     LLVMCodeModelSmall,
     LLVMCodeModelKernel,
     LLVMCodeModelMedium,

llvm/include/llvm/CodeGen/CommandFlags.inc

@@ -74,7 +74,8 @@ static cl::opt<ThreadModel::Model> TMModel(
 
 static cl::opt<llvm::CodeModel::Model> CMModel(
     "code-model", cl::desc("Choose code model"),
-    cl::values(clEnumValN(CodeModel::Small, "small", "Small code model"),
+    cl::values(clEnumValN(CodeModel::Tiny, "tiny", "Tiny code model"),
+               clEnumValN(CodeModel::Small, "small", "Small code model"),
                clEnumValN(CodeModel::Kernel, "kernel", "Kernel code model"),
                clEnumValN(CodeModel::Medium, "medium", "Medium code model"),
                clEnumValN(CodeModel::Large, "large", "Large code model")));

llvm/include/llvm/Support/CodeGen.h

@@ -25,7 +25,7 @@ namespace llvm {
   // Code model types.
   namespace CodeModel {
     // Sync changes with CodeGenCWrappers.h.
-  enum Model { Small, Kernel, Medium, Large };
+  enum Model { Tiny, Small, Kernel, Medium, Large };
   }
 
   namespace PICLevel {

llvm/include/llvm/Target/CodeGenCWrappers.h

@@ -31,6 +31,8 @@ inline Optional<CodeModel::Model> unwrap(LLVMCodeModel Model, bool &JIT) {
     LLVM_FALLTHROUGH;
   case LLVMCodeModelDefault:
     return None;
+  case LLVMCodeModelTiny:
+    return CodeModel::Tiny;
   case LLVMCodeModelSmall:
     return CodeModel::Small;
   case LLVMCodeModelKernel:
@@ -45,6 +47,8 @@ inline Optional<CodeModel::Model> unwrap(LLVMCodeModel Model, bool &JIT) {
 
 inline LLVMCodeModel wrap(CodeModel::Model Model) {
   switch (Model) {
+  case CodeModel::Tiny:
+    return LLVMCodeModelTiny;
   case CodeModel::Small:
     return LLVMCodeModelSmall;
   case CodeModel::Kernel:

llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp

@@ -835,36 +835,55 @@ bool AArch64ExpandPseudo::expandMI(MachineBasicBlock &MBB,
   }
 
   case AArch64::LOADgot: {
-    // Expand into ADRP + LDR.
+    MachineFunction *MF = MBB.getParent();
     unsigned DstReg = MI.getOperand(0).getReg();
     const MachineOperand &MO1 = MI.getOperand(1);
     unsigned Flags = MO1.getTargetFlags();
-    MachineInstrBuilder MIB1 =
-        BuildMI(MBB, MBBI, MI.getDebugLoc(), TII->get(AArch64::ADRP), DstReg);
-    MachineInstrBuilder MIB2 =
-        BuildMI(MBB, MBBI, MI.getDebugLoc(), TII->get(AArch64::LDRXui))
-            .add(MI.getOperand(0))
-            .addReg(DstReg);
 
-    if (MO1.isGlobal()) {
+    if (MF->getTarget().getCodeModel() == CodeModel::Tiny) {
-      MIB1.addGlobalAddress(MO1.getGlobal(), 0, Flags | AArch64II::MO_PAGE);
+      // Tiny codemodel expand to LDR
-      MIB2.addGlobalAddress(MO1.getGlobal(), 0,
+      MachineInstrBuilder MIB = BuildMI(MBB, MBBI, MI.getDebugLoc(),
-                            Flags | AArch64II::MO_PAGEOFF | AArch64II::MO_NC);
+                                        TII->get(AArch64::LDRXl), DstReg);
-    } else if (MO1.isSymbol()) {
+
-      MIB1.addExternalSymbol(MO1.getSymbolName(), Flags | AArch64II::MO_PAGE);
+      if (MO1.isGlobal()) {
-      MIB2.addExternalSymbol(MO1.getSymbolName(),
+        MIB.addGlobalAddress(MO1.getGlobal(), 0, Flags);
-                             Flags | AArch64II::MO_PAGEOFF | AArch64II::MO_NC);
+      } else if (MO1.isSymbol()) {
+        MIB.addExternalSymbol(MO1.getSymbolName(), Flags);
+      } else {
+        assert(MO1.isCPI() &&
+               "Only expect globals, externalsymbols, or constant pools");
+        MIB.addConstantPoolIndex(MO1.getIndex(), MO1.getOffset(), Flags);
+      }
     } else {
-      assert(MO1.isCPI() &&
+      // Small codemodel expand into ADRP + LDR.
-             "Only expect globals, externalsymbols, or constant pools");
+      MachineInstrBuilder MIB1 =
-      MIB1.addConstantPoolIndex(MO1.getIndex(), MO1.getOffset(),
+          BuildMI(MBB, MBBI, MI.getDebugLoc(), TII->get(AArch64::ADRP), DstReg);
-                                Flags | AArch64II::MO_PAGE);
+      MachineInstrBuilder MIB2 =
-      MIB2.addConstantPoolIndex(MO1.getIndex(), MO1.getOffset(),
+          BuildMI(MBB, MBBI, MI.getDebugLoc(), TII->get(AArch64::LDRXui))
-                                Flags | AArch64II::MO_PAGEOFF |
+              .add(MI.getOperand(0))
-                                    AArch64II::MO_NC);
+              .addReg(DstReg);
-    }
 
-    transferImpOps(MI, MIB1, MIB2);
+      if (MO1.isGlobal()) {
+        MIB1.addGlobalAddress(MO1.getGlobal(), 0, Flags | AArch64II::MO_PAGE);
+        MIB2.addGlobalAddress(MO1.getGlobal(), 0,
+                              Flags | AArch64II::MO_PAGEOFF | AArch64II::MO_NC);
+      } else if (MO1.isSymbol()) {
+        MIB1.addExternalSymbol(MO1.getSymbolName(), Flags | AArch64II::MO_PAGE);
+        MIB2.addExternalSymbol(MO1.getSymbolName(), Flags |
+                                                        AArch64II::MO_PAGEOFF |
+                                                        AArch64II::MO_NC);
+      } else {
+        assert(MO1.isCPI() &&
+               "Only expect globals, externalsymbols, or constant pools");
+        MIB1.addConstantPoolIndex(MO1.getIndex(), MO1.getOffset(),
+                                  Flags | AArch64II::MO_PAGE);
+        MIB2.addConstantPoolIndex(MO1.getIndex(), MO1.getOffset(),
+                                  Flags | AArch64II::MO_PAGEOFF |
+                                      AArch64II::MO_NC);
+      }
+
+      transferImpOps(MI, MIB1, MIB2);
+    }
     MI.eraseFromParent();
     return true;
   }

llvm/lib/Target/AArch64/AArch64FrameLowering.cpp

@@ -686,6 +686,7 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
         .setMIFlags(MachineInstr::FrameSetup);
 
     switch (MF.getTarget().getCodeModel()) {
+    case CodeModel::Tiny:
     case CodeModel::Small:
     case CodeModel::Medium:
     case CodeModel::Kernel:

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -1086,6 +1086,7 @@ const char *AArch64TargetLowering::getTargetNodeName(unsigned Opcode) const {
   case AArch64ISD::FIRST_NUMBER:      break;
   case AArch64ISD::CALL:              return "AArch64ISD::CALL";
   case AArch64ISD::ADRP:              return "AArch64ISD::ADRP";
+  case AArch64ISD::ADR:               return "AArch64ISD::ADR";
   case AArch64ISD::ADDlow:            return "AArch64ISD::ADDlow";
   case AArch64ISD::LOADgot:           return "AArch64ISD::LOADgot";
   case AArch64ISD::RET_FLAG:          return "AArch64ISD::RET_FLAG";
@@ -3912,6 +3913,17 @@ SDValue AArch64TargetLowering::getAddr(NodeTy *N, SelectionDAG &DAG,
   return DAG.getNode(AArch64ISD::ADDlow, DL, Ty, ADRP, Lo);
 }
 
+// (adr sym)
+template <class NodeTy>
+SDValue AArch64TargetLowering::getAddrTiny(NodeTy *N, SelectionDAG &DAG,
+                                           unsigned Flags) const {
+  LLVM_DEBUG(dbgs() << "AArch64TargetLowering::getAddrTiny\n");
+  SDLoc DL(N);
+  EVT Ty = getPointerTy(DAG.getDataLayout());
+  SDValue Sym = getTargetNode(N, Ty, DAG, Flags);
+  return DAG.getNode(AArch64ISD::ADR, DL, Ty, Sym);
+}
+
 SDValue AArch64TargetLowering::LowerGlobalAddress(SDValue Op,
                                                   SelectionDAG &DAG) const {
   GlobalAddressSDNode *GN = cast<GlobalAddressSDNode>(Op);
@@ -3926,7 +3938,8 @@ SDValue AArch64TargetLowering::LowerGlobalAddress(SDValue Op,
     assert(cast<GlobalAddressSDNode>(Op)->getOffset() == 0 &&
            "unexpected offset in global node");
 
-  // This also catches the large code model case for Darwin.
+  // This also catches the large code model case for Darwin, and tiny code
+  // model with got relocations.
   if ((OpFlags & AArch64II::MO_GOT) != 0) {
     return getGOT(GN, DAG, TargetFlags);
   }
@@ -3934,6 +3947,8 @@ SDValue AArch64TargetLowering::LowerGlobalAddress(SDValue Op,
   SDValue Result;
   if (getTargetMachine().getCodeModel() == CodeModel::Large) {
     Result = getAddrLarge(GN, DAG, TargetFlags);
+  } else if (getTargetMachine().getCodeModel() == CodeModel::Tiny) {
+    Result = getAddrTiny(GN, DAG, TargetFlags);
   } else {
     Result = getAddr(GN, DAG, TargetFlags);
   }
@@ -4055,13 +4070,15 @@ SDValue
 AArch64TargetLowering::LowerELFGlobalTLSAddress(SDValue Op,
                                                 SelectionDAG &DAG) const {
   assert(Subtarget->isTargetELF() && "This function expects an ELF target");
-  assert(Subtarget->useSmallAddressing() &&
+  if (getTargetMachine().getCodeModel() == CodeModel::Large)
-         "ELF TLS only supported in small memory model");
+    report_fatal_error("ELF TLS only supported in small memory model");
   // Different choices can be made for the maximum size of the TLS area for a
   // module. For the small address model, the default TLS size is 16MiB and the
   // maximum TLS size is 4GiB.
   // FIXME: add -mtls-size command line option and make it control the 16MiB
   // vs. 4GiB code sequence generation.
+  // FIXME: add tiny codemodel support. We currently generate the same code as
+  // small, which may be larger than needed.
   const GlobalAddressSDNode *GA = cast<GlobalAddressSDNode>(Op);
 
   TLSModel::Model Model = getTargetMachine().getTLSModel(GA->getGlobal());
@@ -4779,6 +4796,8 @@ SDValue AArch64TargetLowering::LowerJumpTable(SDValue Op,
   if (getTargetMachine().getCodeModel() == CodeModel::Large &&
       !Subtarget->isTargetMachO()) {
     return getAddrLarge(JT, DAG);
+  } else if (getTargetMachine().getCodeModel() == CodeModel::Tiny) {
+    return getAddrTiny(JT, DAG);
   }
   return getAddr(JT, DAG);
 }
@@ -4793,6 +4812,8 @@ SDValue AArch64TargetLowering::LowerConstantPool(SDValue Op,
       return getGOT(CP, DAG);
     }
     return getAddrLarge(CP, DAG);
+  } else if (getTargetMachine().getCodeModel() == CodeModel::Tiny) {
+    return getAddrTiny(CP, DAG);
   } else {
     return getAddr(CP, DAG);
   }
@@ -4804,9 +4825,10 @@ SDValue AArch64TargetLowering::LowerBlockAddress(SDValue Op,
   if (getTargetMachine().getCodeModel() == CodeModel::Large &&
       !Subtarget->isTargetMachO()) {
     return getAddrLarge(BA, DAG);
-  } else {
+  } else if (getTargetMachine().getCodeModel() == CodeModel::Tiny) {
-    return getAddr(BA, DAG);
+    return getAddrTiny(BA, DAG);
   }
+  return getAddr(BA, DAG);
 }
 
 SDValue AArch64TargetLowering::LowerDarwin_VASTART(SDValue Op,

llvm/lib/Target/AArch64/AArch64ISelLowering.h

@@ -35,6 +35,7 @@ enum NodeType : unsigned {
   // offset of a variable into X0, using the TLSDesc model.
   TLSDESC_CALLSEQ,
   ADRP,     // Page address of a TargetGlobalAddress operand.
+  ADR,      // ADR
   ADDlow,   // Add the low 12 bits of a TargetGlobalAddress operand.
   LOADgot,  // Load from automatically generated descriptor (e.g. Global
             // Offset Table, TLS record).
@@ -587,6 +588,8 @@ private:
   SDValue getAddrLarge(NodeTy *N, SelectionDAG &DAG, unsigned Flags = 0) const;
   template <class NodeTy>
   SDValue getAddr(NodeTy *N, SelectionDAG &DAG, unsigned Flags = 0) const;
+  template <class NodeTy>
+  SDValue getAddrTiny(NodeTy *N, SelectionDAG &DAG, unsigned Flags = 0) const;
   SDValue LowerADDROFRETURNADDR(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerGlobalAddress(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;

llvm/lib/Target/AArch64/AArch64InstrInfo.cpp

@@ -1632,6 +1632,9 @@ bool AArch64InstrInfo::expandPostRAPseudo(MachineInstr &MI) const {
         .addReg(Reg, RegState::Kill)
         .addImm(0)
         .addMemOperand(*MI.memoperands_begin());
+  } else if (TM.getCodeModel() == CodeModel::Tiny) {
+    BuildMI(MBB, MI, DL, get(AArch64::ADR), Reg)
+        .addGlobalAddress(GV, 0, OpFlags);
   } else {
     BuildMI(MBB, MI, DL, get(AArch64::ADRP), Reg)
         .addGlobalAddress(GV, 0, OpFlags | AArch64II::MO_PAGE);

llvm/lib/Target/AArch64/AArch64InstrInfo.td

@@ -176,6 +176,7 @@ def SDT_AArch64WrapperLarge : SDTypeProfile<1, 4,
 
 // Node definitions.
 def AArch64adrp          : SDNode<"AArch64ISD::ADRP", SDTIntUnaryOp, []>;
+def AArch64adr           : SDNode<"AArch64ISD::ADR", SDTIntUnaryOp, []>;
 def AArch64addlow        : SDNode<"AArch64ISD::ADDlow", SDTIntBinOp, []>;
 def AArch64LOADgot       : SDNode<"AArch64ISD::LOADgot", SDTIntUnaryOp>;
 def AArch64callseq_start : SDNode<"ISD::CALLSEQ_START",
@@ -1385,7 +1386,8 @@ def : InstAlias<"cneg $dst, $src, $cc",
 //===----------------------------------------------------------------------===//
 let isReMaterializable = 1 in {
 let hasSideEffects = 0, mayStore = 0, mayLoad = 0 in {
-def ADR  : ADRI<0, "adr", adrlabel, []>;
+def ADR  : ADRI<0, "adr", adrlabel,
+                [(set GPR64:$Xd, (AArch64adr tglobaladdr:$label))]>;
 } // hasSideEffects = 0
 
 def ADRP : ADRI<1, "adrp", adrplabel,
@@ -1393,6 +1395,10 @@ def ADRP : ADRI<1, "adrp", adrplabel,
 } // isReMaterializable = 1
 
 // page address of a constant pool entry, block address
+def : Pat<(AArch64adr tconstpool:$cp), (ADR tconstpool:$cp)>;
+def : Pat<(AArch64adr tblockaddress:$cp), (ADR tblockaddress:$cp)>;
+def : Pat<(AArch64adr texternalsym:$sym), (ADR texternalsym:$sym)>;
+def : Pat<(AArch64adr tjumptable:$sym), (ADR tjumptable:$sym)>;
 def : Pat<(AArch64adrp tconstpool:$cp), (ADRP tconstpool:$cp)>;
 def : Pat<(AArch64adrp tblockaddress:$cp), (ADRP tblockaddress:$cp)>;
 def : Pat<(AArch64adrp texternalsym:$sym), (ADRP texternalsym:$sym)>;

llvm/lib/Target/AArch64/AArch64InstructionSelector.cpp

@@ -983,6 +983,9 @@ bool AArch64InstructionSelector::select(MachineInstr &I,
       materializeLargeCMVal(I, GV, OpFlags);
       I.eraseFromParent();
       return true;
+    } else if (TM.getCodeModel() == CodeModel::Tiny) {
+      I.setDesc(TII.get(AArch64::ADR));
+      I.getOperand(1).setTargetFlags(OpFlags);
     } else {
       I.setDesc(TII.get(AArch64::MOVaddr));
       I.getOperand(1).setTargetFlags(OpFlags | AArch64II::MO_PAGE);

llvm/lib/Target/AArch64/AArch64Subtarget.cpp

@@ -204,7 +204,9 @@ AArch64Subtarget::ClassifyGlobalReference(const GlobalValue *GV,
 
   // The small code model's direct accesses use ADRP, which cannot
   // necessarily produce the value 0 (if the code is above 4GB).
-  if (useSmallAddressing() && GV->hasExternalWeakLinkage())
+  // Same for the tiny code model, where we have a pc relative LDR.
+  if ((useSmallAddressing() || TM.getCodeModel() == CodeModel::Tiny) &&
+      GV->hasExternalWeakLinkage())
     return AArch64II::MO_GOT | Flags;
 
   return Flags;

llvm/lib/Target/AArch64/AArch64TargetMachine.cpp

@@ -210,14 +210,16 @@ static CodeModel::Model getEffectiveCodeModel(const Triple &TT,
                                               Optional<CodeModel::Model> CM,
                                               bool JIT) {
   if (CM) {
-    if (*CM != CodeModel::Small && *CM != CodeModel::Large) {
+    if (*CM != CodeModel::Small && *CM != CodeModel::Tiny &&
+        *CM != CodeModel::Large) {
       if (!TT.isOSFuchsia())
         report_fatal_error(
-            "Only small and large code models are allowed on AArch64");
+            "Only small, tiny and large code models are allowed on AArch64");
-      else if (CM != CodeModel::Kernel)
+      else if (*CM != CodeModel::Kernel)
-        report_fatal_error(
+        report_fatal_error("Only small, tiny, kernel, and large code models "
-            "Only small, kernel, and large code models are allowed on AArch64");
+                           "are allowed on AArch64");
-    }
+    } else if (*CM == CodeModel::Tiny && !TT.isOSBinFormatELF())
+      report_fatal_error("tiny code model is only supported on ELF");
     return *CM;
   }
   // The default MCJIT memory managers make no guarantees about where they can

llvm/lib/Target/AArch64/AsmParser/AArch64AsmParser.cpp

@@ -2453,17 +2453,34 @@ AArch64AsmParser::tryParseAdrLabel(OperandVector &Operands) {
   SMLoc S = getLoc();
   const MCExpr *Expr;
 
-  const AsmToken &Tok = getParser().getTok();
+  // Leave anything with a bracket to the default for SVE
-  if (parseOptionalToken(AsmToken::Hash) || Tok.is(AsmToken::Integer)) {
+  if (getParser().getTok().is(AsmToken::LBrac))
-    if (getParser().parseExpression(Expr))
+    return MatchOperand_NoMatch;
+
+  if (getParser().getTok().is(AsmToken::Hash))
+    getParser().Lex(); // Eat hash token.
+
+  if (parseSymbolicImmVal(Expr))
+    return MatchOperand_ParseFail;
+
+  AArch64MCExpr::VariantKind ELFRefKind;
+  MCSymbolRefExpr::VariantKind DarwinRefKind;
+  int64_t Addend;
+  if (classifySymbolRef(Expr, ELFRefKind, DarwinRefKind, Addend)) {
+    if (DarwinRefKind == MCSymbolRefExpr::VK_None &&
+        ELFRefKind == AArch64MCExpr::VK_INVALID) {
+      // No modifier was specified at all; this is the syntax for an ELF basic
+      // ADR relocation (unfortunately).
+      Expr = AArch64MCExpr::create(Expr, AArch64MCExpr::VK_ABS, getContext());
+    } else {
+      Error(S, "unexpected adr label");
       return MatchOperand_ParseFail;
-
+    }
-    SMLoc E = SMLoc::getFromPointer(getLoc().getPointer() - 1);
-    Operands.push_back(AArch64Operand::CreateImm(Expr, S, E, getContext()));
-
-    return MatchOperand_Success;
   }
-  return MatchOperand_NoMatch;
+
+  SMLoc E = SMLoc::getFromPointer(getLoc().getPointer() - 1);
+  Operands.push_back(AArch64Operand::CreateImm(Expr, S, E, getContext()));
+  return MatchOperand_Success;
 }
 
 /// tryParseFPImm - A floating point immediate expression operand.

llvm/lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp

@@ -10,6 +10,7 @@
 #include "AArch64.h"
 #include "AArch64RegisterInfo.h"
 #include "MCTargetDesc/AArch64FixupKinds.h"
+#include "MCTargetDesc/AArch64MCExpr.h"
 #include "llvm/ADT/Triple.h"
 #include "llvm/BinaryFormat/MachO.h"
 #include "llvm/MC/MCAsmBackend.h"
@@ -376,6 +377,14 @@ bool AArch64AsmBackend::shouldForceRelocation(const MCAssembler &Asm,
   // to the linker -- a relocation!
   if ((uint32_t)Fixup.getKind() == AArch64::fixup_aarch64_pcrel_adrp_imm21)
     return true;
+
+  AArch64MCExpr::VariantKind RefKind =
+      static_cast<AArch64MCExpr::VariantKind>(Target.getRefKind());
+  AArch64MCExpr::VariantKind SymLoc = AArch64MCExpr::getSymbolLoc(RefKind);
+  // LDR GOT relocations need a relocation
+  if ((uint32_t)Fixup.getKind() == AArch64::fixup_aarch64_ldr_pcrel_imm19 &&
+      SymLoc == AArch64MCExpr::VK_GOT)
+    return true;
   return false;
 }
 

llvm/lib/Target/AArch64/MCTargetDesc/AArch64ELFObjectWriter.cpp

@@ -138,7 +138,9 @@ unsigned AArch64ELFObjectWriter::getRelocType(MCContext &Ctx,
       } else
         return ELF::R_AARCH64_PREL64;
     case AArch64::fixup_aarch64_pcrel_adr_imm21:
-      assert(SymLoc == AArch64MCExpr::VK_NONE && "unexpected ADR relocation");
+      if (SymLoc != AArch64MCExpr::VK_ABS)
+        Ctx.reportError(Fixup.getLoc(),
+                        "invalid symbol kind for ADR relocation");
       return R_CLS(ADR_PREL_LO21);
     case AArch64::fixup_aarch64_pcrel_adrp_imm21:
       if (SymLoc == AArch64MCExpr::VK_ABS && !IsNC)

llvm/lib/Target/AArch64/MCTargetDesc/AArch64MCExpr.cpp

@@ -62,8 +62,10 @@ StringRef AArch64MCExpr::getVariantKindName() const {
   case VK_TLSDESC_LO12:        return ":tlsdesc_lo12:";
   case VK_ABS_PAGE:            return "";
   case VK_ABS_PAGE_NC:         return ":pg_hi21_nc:";
+  case VK_GOT:                 return ":got:";
   case VK_GOT_PAGE:            return ":got:";
   case VK_GOT_LO12:            return ":got_lo12:";
+  case VK_GOTTPREL:            return ":gottprel:";
   case VK_GOTTPREL_PAGE:       return ":gottprel:";
   case VK_GOTTPREL_LO12_NC:    return ":gottprel_lo12:";
   case VK_GOTTPREL_G1:         return ":gottprel_g1:";

llvm/lib/Target/ARM/ARMFrameLowering.cpp

@@ -526,6 +526,8 @@ void ARMFrameLowering::emitPrologue(MachineFunction &MF,
         .setMIFlags(MachineInstr::FrameSetup);
 
     switch (TM.getCodeModel()) {
+    case CodeModel::Tiny:
+      llvm_unreachable("Tiny code model not available on ARM.");
     case CodeModel::Small:
     case CodeModel::Medium:
     case CodeModel::Kernel:

llvm/lib/Target/ARM/ARMISelLowering.cpp

@@ -9207,6 +9207,8 @@ ARMTargetLowering::EmitLowered__chkstk(MachineInstr &MI,
   // IP.
 
   switch (TM.getCodeModel()) {
+  case CodeModel::Tiny:
+    llvm_unreachable("Tiny code model not available on ARM.");
   case CodeModel::Small:
   case CodeModel::Medium:
   case CodeModel::Kernel:

llvm/lib/Target/X86/X86Subtarget.cpp

@@ -77,6 +77,8 @@ X86Subtarget::classifyLocalReference(const GlobalValue *GV) const {
     if (isTargetELF()) {
       switch (TM.getCodeModel()) {
       // 64-bit small code model is simple: All rip-relative.
+      case CodeModel::Tiny:
+        llvm_unreachable("Tiny codesize model not supported on X86");
       case CodeModel::Small:
       case CodeModel::Kernel:
         return X86II::MO_NO_FLAG;

llvm/test/CodeGen/AArch64/GlobalISel/select-gv-cmodel-tiny.mir

@@ -0,0 +1,56 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=aarch64-none-eabi -code-model=tiny -run-pass=instruction-select -verify-machineinstrs -O0 %s -o - | FileCheck %s
+--- |
+  target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+
+  @foo1 = common global [1073741824 x i32] zeroinitializer, align 4
+  @foo2 = common global [1073741824 x i32] zeroinitializer, align 4
+
+  define i32 @gv_tiny() {
+  entry:
+    %retval = alloca i32, align 4
+    store i32 0, i32* %retval, align 4
+    %0 = load i32, i32* getelementptr inbounds ([1073741824 x i32], [1073741824 x i32]* @foo1, i64 0, i64 0), align 4
+    %1 = load i32, i32* getelementptr inbounds ([1073741824 x i32], [1073741824 x i32]* @foo2, i64 0, i64 0), align 4
+    %add = add nsw i32 %0, %1
+    ret i32 %add
+  }
+
+...
+---
+name:            gv_tiny
+legalized:       true
+regBankSelected: true
+stack:
+  - { id: 0, name: retval, type: default, offset: 0, size: 4, alignment: 4,
+      stack-id: 0, callee-saved-register: '', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '',
+      debug-info-location: '' }
+constants:
+body:             |
+  bb.1:
+    ; CHECK-LABEL: name: gv_tiny
+    ; CHECK: [[ADR:%[0-9]+]]:gpr64 = ADR @foo1
+    ; CHECK: [[COPY:%[0-9]+]]:gpr64sp = COPY [[ADR]]
+    ; CHECK: [[ADR1:%[0-9]+]]:gpr64 = ADR @foo2
+    ; CHECK: [[COPY1:%[0-9]+]]:gpr64sp = COPY [[ADR1]]
+    ; CHECK: STRWui $wzr, %stack.0.retval, 0 :: (store 4 into %ir.retval)
+    ; CHECK: [[LDRWui:%[0-9]+]]:gpr32 = LDRWui [[COPY]], 0 :: (load 4 from `i32* getelementptr inbounds ([1073741824 x i32], [1073741824 x i32]* @foo1, i64 0, i64 0)`)
+    ; CHECK: [[LDRWui1:%[0-9]+]]:gpr32 = LDRWui [[COPY1]], 0 :: (load 4 from `i32* getelementptr inbounds ([1073741824 x i32], [1073741824 x i32]* @foo2, i64 0, i64 0)`)
+    ; CHECK: [[ADDWrr:%[0-9]+]]:gpr32 = ADDWrr [[LDRWui]], [[LDRWui1]]
+    ; CHECK: $w0 = COPY [[ADDWrr]]
+    ; CHECK: RET_ReallyLR implicit $w0
+    %1:gpr(s32) = G_CONSTANT i32 0
+    %4:gpr(p0) = G_GLOBAL_VALUE @foo1
+    %3:gpr(p0) = COPY %4(p0)
+    %7:gpr(p0) = G_GLOBAL_VALUE @foo2
+    %6:gpr(p0) = COPY %7(p0)
+    %0:gpr(p0) = G_FRAME_INDEX %stack.0.retval
+    G_STORE %1(s32), %0(p0) :: (store 4 into %ir.retval)
+    %2:gpr(s32) = G_LOAD %3(p0) :: (load 4 from `i32* getelementptr inbounds ([1073741824 x i32], [1073741824 x i32]* @foo1, i64 0, i64 0)`)
+    %5:gpr(s32) = G_LOAD %6(p0) :: (load 4 from `i32* getelementptr inbounds ([1073741824 x i32], [1073741824 x i32]* @foo2, i64 0, i64 0)`)
+    %8:gpr(s32) = G_ADD %2, %5
+    $w0 = COPY %8(s32)
+    RET_ReallyLR implicit $w0
+
+...

llvm/test/CodeGen/AArch64/arm64-tls-dynamics.ll

@@ -2,6 +2,12 @@
 ; RUN: llc -mtriple=arm64-none-linux-gnu -relocation-model=pic -aarch64-elf-ldtls-generation=1 -filetype=obj < %s | llvm-objdump -r - | FileCheck --check-prefix=CHECK-RELOC %s
 ; RUN: llc -mtriple=arm64-none-linux-gnu -relocation-model=pic -verify-machineinstrs < %s | FileCheck --check-prefix=CHECK-NOLD %s
 ; RUN: llc -mtriple=arm64-none-linux-gnu -relocation-model=pic -filetype=obj < %s | llvm-objdump -r - | FileCheck --check-prefix=CHECK-NOLD-RELOC %s
+; FIXME: We currently produce "small" code for the tiny model
+; RUN: llc -mtriple=arm64-none-linux-gnu -relocation-model=pic -aarch64-elf-ldtls-generation=1 -code-model=tiny -verify-machineinstrs < %s | FileCheck %s
+; FIXME: We currently error for the large code model
+; RUN: not llc -mtriple=arm64-none-linux-gnu -relocation-model=pic -aarch64-elf-ldtls-generation=1 -code-model=large -verify-machineinstrs < %s 2>&1 | FileCheck %s --check-prefix=CHECK-LARGE
+
+; CHECK-LARGE: ELF TLS only supported in small memory model
 
 @general_dynamic_var = external thread_local global i32
 

llvm/test/CodeGen/AArch64/arm64-tls-execs.ll

@@ -1,5 +1,11 @@
 ; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding < %s | FileCheck %s
 ; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s | llvm-objdump -r - | FileCheck --check-prefix=CHECK-RELOC %s
+; RUN: llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -code-model=tiny < %s | FileCheck %s --check-prefix=CHECK-TINY
+; RUN: llc -mtriple=arm64-none-linux-gnu -filetype=obj < %s -code-model=tiny | llvm-objdump -r - | FileCheck --check-prefix=CHECK-TINY-RELOC %s
+; FIXME: We currently error for the large code model
+; RUN: not llc -mtriple=arm64-none-linux-gnu -verify-machineinstrs -show-mc-encoding -code-model=large < %s 2>&1 | FileCheck %s --check-prefix=CHECK-LARGE
+
+; CHECK-LARGE: ELF TLS only supported in small memory model
 
 @initial_exec_var = external thread_local(initialexec) global i32
 
@@ -15,6 +21,12 @@ define i32 @test_initial_exec() {
 ; CHECK-RELOC: R_AARCH64_TLSIE_ADR_GOTTPREL_PAGE21
 ; CHECK-RELOC: R_AARCH64_TLSIE_LD64_GOTTPREL_LO12_NC
 
+; CHECK-TINY: ldr x[[TP_OFFSET:[0-9]+]], :gottprel:initial_exec_var
+; CHECK-TINY: mrs x[[TP:[0-9]+]], TPIDR_EL0
+; CHECK-TINY: ldr w0, [x[[TP]], x[[TP_OFFSET]]]
+
+; CHECK-TINY-RELOC: R_AARCH64_TLSIE_LD_GOTTPREL_PREL19
+
   ret i32 %val
 }
 
@@ -30,6 +42,12 @@ define i32* @test_initial_exec_addr() {
 ; CHECK-RELOC: R_AARCH64_TLSIE_ADR_GOTTPREL_PAGE21
 ; CHECK-RELOC: R_AARCH64_TLSIE_LD64_GOTTPREL_LO12_NC
 
+; CHECK-TINY: ldr x[[TP_OFFSET:[0-9]+]], :gottprel:initial_exec_var
+; CHECK-TINY: mrs [[TP:x[0-9]+]], TPIDR_EL0
+; CHECK-TINY: add x0, [[TP]], x[[TP_OFFSET]]
+
+; CHECK-TINY-RELOC: R_AARCH64_TLSIE_LD_GOTTPREL_PREL19
+
 }
 
 @local_exec_var = thread_local(localexec) global i32 0
@@ -45,6 +63,14 @@ define i32 @test_local_exec() {
 
 ; CHECK-RELOC: R_AARCH64_TLSLE_ADD_TPREL_HI12
 ; CHECK-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
+
+; CHECK-TINY: mrs x[[R1:[0-9]+]], TPIDR_EL0
+; CHECK-TINY: add x[[R2:[0-9]+]], x[[R1]], :tprel_hi12:local_exec_var
+; CHECK-TINY: add x[[R3:[0-9]+]], x[[R2]], :tprel_lo12_nc:local_exec_var
+; CHECK-TINY: ldr w0, [x[[R3]]]
+
+; CHECK-TINY-RELOC: R_AARCH64_TLSLE_ADD_TPREL_HI12
+; CHECK-TINY-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
   ret i32 %val
 }
 
@@ -59,4 +85,12 @@ define i32* @test_local_exec_addr() {
 
 ; CHECK-RELOC: R_AARCH64_TLSLE_ADD_TPREL_HI12
 ; CHECK-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
+
+; CHECK-TINY: mrs x[[R1:[0-9]+]], TPIDR_EL0
+; CHECK-TINY: add x[[R2:[0-9]+]], x[[R1]], :tprel_hi12:local_exec_var
+; CHECK-TINY: add x0, x[[R2]], :tprel_lo12_nc:local_exec_var
+; CHECK-TINY: ret
+
+; CHECK-TINY-RELOC: R_AARCH64_TLSLE_ADD_TPREL_HI12
+; CHECK-TINY-RELOC: R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
 }

llvm/test/CodeGen/AArch64/blockaddress.ll

@@ -1,5 +1,6 @@
 ; RUN: llc -mtriple=aarch64-none-linux-gnu -aarch64-enable-atomic-cfg-tidy=0 -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -code-model=large -mtriple=aarch64-none-linux-gnu -aarch64-enable-atomic-cfg-tidy=0 -verify-machineinstrs < %s | FileCheck --check-prefix=CHECK-LARGE %s
+; RUN: llc -code-model=tiny -mtriple=aarch64-none-none-eabi -aarch64-enable-atomic-cfg-tidy=0 -verify-machineinstrs < %s | FileCheck --check-prefix=CHECK-TINY %s
 
 @addr = global i8* null
 
@@ -22,6 +23,11 @@ define void @test_blockaddress() {
 ; CHECK-LARGE: ldr [[NEWDEST:x[0-9]+]]
 ; CHECK-LARGE: br [[NEWDEST]]
 
+; CHECK-TINY: adr [[DEST:x[0-9]+]], {{.Ltmp[0-9]+}}
+; CHECK-TINY: str [[DEST]],
+; CHECK-TINY: ldr [[NEWDEST:x[0-9]+]]
+; CHECK-TINY: br [[NEWDEST]]
+
 block:
   ret void
 }

llvm/test/CodeGen/AArch64/code-model-tiny-abs.ll

@@ -0,0 +1,54 @@
+; RUN: llc -mtriple=aarch64-none-eabi -code-model=tiny < %s | FileCheck %s
+
+@var8 = global i8 0
+@var16 = global i16 0
+@var32 = global i32 0
+@var64 = global i64 0
+
+define i8* @global_addr() {
+; CHECK-LABEL: global_addr:
+  ret i8* @var8
+  ; The adr calculation should end up returned directly in x0.
+; CHECK: adr x0, var8
+; CHECK-NEXT: ret
+}
+
+define i8 @global_i8() {
+; CHECK-LABEL: global_i8:
+  %val = load i8, i8* @var8
+  ret i8 %val
+; CHECK: adr x[[ADDR_REG:[0-9]+]], var8
+; CHECK: ldrb w0, [x[[ADDR_REG]]]
+}
+
+define i16 @global_i16() {
+; CHECK-LABEL: global_i16:
+  %val = load i16, i16* @var16
+  ret i16 %val
+; CHECK: adr x[[ADDR_REG:[0-9]+]], var16
+; CHECK: ldrh w0, [x[[ADDR_REG]]]
+}
+
+define i32 @global_i32() {
+; CHECK-LABEL: global_i32:
+  %val = load i32, i32* @var32
+  ret i32 %val
+; CHECK: adr x[[ADDR_REG:[0-9]+]], var32
+; CHECK: ldr w0, [x[[ADDR_REG]]]
+}
+
+define i64 @global_i64() {
+; CHECK-LABEL: global_i64:
+  %val = load i64, i64* @var64
+  ret i64 %val
+; CHECK: adr x[[ADDR_REG:[0-9]+]], var64
+; CHECK: ldr x0, [x[[ADDR_REG]]]
+}
+
+define <2 x i64> @constpool() {
+; CHECK-LABEL: constpool:
+  ret <2 x i64> <i64 123456789, i64 987654321100>
+
+; CHECK: adr x[[ADDR_REG:[0-9]+]], {{.LCPI[0-9]+_[0-9]+}}
+; CHECK: ldr q0, [x[[ADDR_REG]]]
+}

llvm/test/CodeGen/AArch64/extern-weak.ll

@@ -1,6 +1,7 @@
 ; RUN: llc -mtriple=aarch64-none-linux-gnu -relocation-model=pic -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-none-linux-gnu -relocation-model=static -o - < %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-none-linux-gnu -code-model=large -o - %s | FileCheck --check-prefix=CHECK-LARGE %s
+; RUN: llc -mtriple=aarch64-none-none-eabi -code-model=tiny -o - %s | FileCheck --check-prefix=CHECK-TINY %s
 
 declare extern_weak i32 @var()
 
@@ -20,6 +21,9 @@ define i32()* @foo() {
 ; CHECK-LARGE: movk x0, #:abs_g1_nc:var
 ; CHECK-LARGE: movk x0, #:abs_g2_nc:var
 ; CHECK-LARGE: movk x0, #:abs_g3:var
+
+  ; In the tiny codemodel we us a got relocated LDR.
+; CHECK-TINY: ldr x0, :got:var
 }
 
 
@@ -41,6 +45,9 @@ define i32* @bar() {
 ; CHECK-LARGE: movk [[ADDR]], #:abs_g1_nc:arr_var
 ; CHECK-LARGE: movk [[ADDR]], #:abs_g2_nc:arr_var
 ; CHECK-LARGE: movk [[ADDR]], #:abs_g3:arr_var
+
+; CHECK-TINY: ldr [[BASE:x[0-9]+]], :got:arr_var
+; CHECK-TINY: add x0, [[BASE]], #20
 }
 
 @defined_weak_var = internal unnamed_addr global i32 0
@@ -55,4 +62,6 @@ define i32* @wibble() {
 ; CHECK-LARGE: movk x0, #:abs_g1_nc:defined_weak_var
 ; CHECK-LARGE: movk x0, #:abs_g2_nc:defined_weak_var
 ; CHECK-LARGE: movk x0, #:abs_g3:defined_weak_var
+
+; CHECK-TINY: adr x0, defined_weak_var
 }

llvm/test/CodeGen/AArch64/fpimm.ll

@@ -1,39 +1,48 @@
 ; RUN: llc -mtriple=aarch64-linux-gnu                                                  -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-apple-darwin -code-model=large                             -verify-machineinstrs < %s | FileCheck %s --check-prefix=LARGE
 ; RUN: llc -mtriple=aarch64-apple-darwin -code-model=large -fast-isel -fast-isel-abort=1 -verify-machineinstrs < %s | FileCheck %s --check-prefix=LARGE
+; RUN: llc -mtriple=aarch64-none-eabi    -code-model=tiny                              -verify-machineinstrs < %s | FileCheck %s --check-prefix=TINY
 
 @varf32 = global float 0.0
 @varf64 = global double 0.0
 
 define void @check_float() {
 ; CHECK-LABEL: check_float:
+; TINY-LABEL: check_float:
 
   %val = load float, float* @varf32
   %newval1 = fadd float %val, 8.5
   store volatile float %newval1, float* @varf32
-; CHECK-DAG: fmov [[EIGHT5:s[0-9]+]], #8.5
+; CHECK-DAG: fmov {{s[0-9]+}}, #8.5
+; TINY-DAG: fmov {{s[0-9]+}}, #8.5
 
   %newval2 = fadd float %val, 128.0
   store volatile float %newval2, float* @varf32
-; CHECK-DAG: ldr [[HARD:s[0-9]+]], [{{x[0-9]+}}, {{#?}}:lo12:.LCPI0_0
+; CHECK-DAG: ldr {{s[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.LCPI0_0
+; TINY-DAG: ldr {{s[0-9]+}}, [{{x[0-9]+}}]
 
 ; CHECK: ret
+; TINY: ret
   ret void
 }
 
 define void @check_double() {
 ; CHECK-LABEL: check_double:
+; TINY-LABEL: check_double:
 
   %val = load double, double* @varf64
   %newval1 = fadd double %val, 8.5
   store volatile double %newval1, double* @varf64
 ; CHECK-DAG: fmov {{d[0-9]+}}, #8.5
+; TINY-DAG: fmov {{d[0-9]+}}, #8.5
 
   %newval2 = fadd double %val, 128.0
   store volatile double %newval2, double* @varf64
 ; CHECK-DAG: ldr {{d[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.LCPI1_0
+; TINY-DAG: ldr {{d[0-9]+}}, [{{x[0-9]+}}]
 
 ; CHECK: ret
+; TINY: ret
   ret void
 }
 
@@ -41,6 +50,9 @@ define void @check_double() {
 ; LARGE:       mov [[REG:w[0-9]+]], #4059
 ; LARGE-NEXT:  movk [[REG]], #16457, lsl #16
 ; LARGE-NEXT:  fmov s0, [[REG]]
+; TINY-LABEL: check_float2
+; TINY:       adr     x[[REG:[0-9]+]], .LCPI2_0
+; TINY-NEXT:  ldr     s0, [x[[REG]]]
 define float @check_float2() {
   ret float 3.14159274101257324218750
 }
@@ -51,6 +63,9 @@ define float @check_float2() {
 ; LARGE-NEXT:  movk [[REG]], #8699, lsl #32
 ; LARGE-NEXT:  movk [[REG]], #16393, lsl #48
 ; LARGE-NEXT:  fmov d0, [[REG]]
+; TINY-LABEL: check_double2
+; TINY:       adr     x[[REG:[0-9]+]], .LCPI3_0
+; TINY-NEXT:  ldr     d0, [x[[REG]]]
 define double @check_double2() {
   ret double 3.1415926535897931159979634685441851615905761718750
 }

llvm/test/CodeGen/AArch64/jump-table.ll

@@ -1,6 +1,7 @@
 ; RUN: llc -verify-machineinstrs -o - %s -mtriple=aarch64-none-linux-gnu -aarch64-enable-atomic-cfg-tidy=0 | FileCheck %s
 ; RUN: llc -code-model=large -verify-machineinstrs -o - %s -mtriple=aarch64-none-linux-gnu -aarch64-enable-atomic-cfg-tidy=0 | FileCheck --check-prefix=CHECK-LARGE %s
 ; RUN: llc -mtriple=aarch64-none-linux-gnu -verify-machineinstrs -relocation-model=pic -aarch64-enable-atomic-cfg-tidy=0 -o - %s | FileCheck --check-prefix=CHECK-PIC %s
+; RUN: llc -code-model=tiny -verify-machineinstrs -o - %s -mtriple=aarch64-none-linux-gnu -aarch64-enable-atomic-cfg-tidy=0 | FileCheck --check-prefix=CHECK-TINY %s
 
 define i32 @test_jumptable(i32 %in) {
 ; CHECK: test_jumptable
@@ -29,6 +30,10 @@ define i32 @test_jumptable(i32 %in) {
 ; CHECK-PIC: add [[TABLE:x[0-9]+]], [[DEST]], x[[JT]]
 ; CHECK-PIC: br [[TABLE]]
 
+; CHECK-TINY: adr x[[JT:[0-9]+]], .LJTI0_0
+; CHECK-TINY: ldr [[DEST:x[0-9]+]], [x[[JT]], {{x[0-9]+}}, lsl #3]
+; CHECK-TINY: br [[DEST]]
+
 def:
   ret i32 0
 

llvm/test/CodeGen/AArch64/literal_pools_float.ll

@@ -1,7 +1,9 @@
 ; RUN: llc -verify-machineinstrs -o - %s -mtriple=aarch64-none-linux-gnu -mcpu=cyclone | FileCheck %s
 ; RUN: llc -verify-machineinstrs -o - %s -mtriple=aarch64-none-linux-gnu -code-model=large -mcpu=cyclone | FileCheck --check-prefix=CHECK-LARGE %s
+; RUN: llc -verify-machineinstrs -o - %s -mtriple=aarch64-none-none-eabi -code-model=tiny -mcpu=cyclone | FileCheck --check-prefix=CHECK-TINY %s
 ; RUN: llc -verify-machineinstrs < %s -mtriple=aarch64-none-linux-gnu -mattr=-fp-armv8 | FileCheck --check-prefix=CHECK-NOFP %s
 ; RUN: llc -verify-machineinstrs < %s -mtriple=aarch64-none-linux-gnu -code-model=large -mattr=-fp-armv8 | FileCheck --check-prefix=CHECK-NOFP-LARGE %s
+; RUN: llc -verify-machineinstrs < %s -mtriple=aarch64-none-none-eabi -code-model=tiny -mattr=-fp-armv8 | FileCheck --check-prefix=CHECK-NOFP-TINY %s
 
 @varfloat = global float 0.0
 @vardouble = global double 0.0
@@ -15,6 +17,10 @@ define void @floating_lits() {
 ; CHECK: ldr [[LIT128:s[0-9]+]], [x[[LITBASE]], {{#?}}:lo12:[[CURLIT]]]
 ; CHECK-NOFP-NOT: ldr {{s[0-9]+}},
 
+; CHECK-TINY: adr x[[LITBASE:[0-9]+]], [[CURLIT:.LCPI[0-9]+_[0-9]+]]
+; CHECK-TINY: ldr [[LIT128:s[0-9]+]], [x[[LITBASE]]]
+; CHECK-NOFP-TINY-NOT: ldr {{s[0-9]+}},
+
 ; CHECK-LARGE: movz x[[LITADDR:[0-9]+]], #:abs_g0_nc:[[CURLIT:.LCPI[0-9]+_[0-9]+]]
 ; CHECK-LARGE: movk x[[LITADDR]], #:abs_g1_nc:[[CURLIT]]
 ; CHECK-LARGE: movk x[[LITADDR]], #:abs_g2_nc:[[CURLIT]]
@@ -33,6 +39,11 @@ define void @floating_lits() {
 ; CHECK-NOFP-NOT: ldr {{d[0-9]+}},
 ; CHECK-NOFP-NOT: fadd
 
+; CHECK-TINY: adr x[[LITBASE:[0-9]+]], [[CURLIT:.LCPI[0-9]+_[0-9]+]]
+; CHECK-TINY: ldr [[LIT129:d[0-9]+]], [x[[LITBASE]]]
+; CHECK-NOFP-TINY-NOT: ldr {{d[0-9]+}},
+; CHECK-NOFP-TINY-NOT: fadd
+
 ; CHECK-LARGE: movz x[[LITADDR:[0-9]+]], #:abs_g0_nc:[[CURLIT:.LCPI[0-9]+_[0-9]+]]
 ; CHECK-LARGE: movk x[[LITADDR]], #:abs_g1_nc:[[CURLIT]]
 ; CHECK-LARGE: movk x[[LITADDR]], #:abs_g2_nc:[[CURLIT]]

llvm/test/CodeGen/AArch64/tiny_model.ll

@@ -0,0 +1,421 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -verify-machineinstrs -o - -mtriple=aarch64-none-linux-gnu -code-model=tiny < %s | FileCheck %s
+; RUN: llc -verify-machineinstrs -o - -mtriple=aarch64-none-linux-gnu -code-model=tiny -fast-isel < %s | FileCheck %s
+; RUN: llc -verify-machineinstrs -o - -mtriple=aarch64-none-linux-gnu -code-model=tiny -global-isel < %s | FileCheck %s --check-prefix=CHECK-GLOBISEL
+; RUN: llc -verify-machineinstrs -o - -mtriple=aarch64-none-linux-gnu -code-model=tiny -relocation-model=pic < %s | FileCheck %s --check-prefix=CHECK-PIC
+; RUN: llc -verify-machineinstrs -o - -mtriple=aarch64-none-linux-gnu -code-model=tiny -relocation-model=pic -fast-isel < %s | FileCheck %s --check-prefix=CHECK-PIC
+; RUN: llc -verify-machineinstrs -o - -mtriple=aarch64-none-linux-gnu -code-model=tiny -relocation-model=pic -global-isel < %s | FileCheck %s --check-prefix=CHECK-PIC-GLOBISEL
+
+; Note fast-isel tests here will fall back to isel
+
+@src = external local_unnamed_addr global [65536 x i8], align 1
+@dst = external global [65536 x i8], align 1
+@ptr = external local_unnamed_addr global i8*, align 8
+
+define void @foo1() {
+; CHECK-LABEL: foo1:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x8, src
+; CHECK-NEXT:    ldrb w8, [x8]
+; CHECK-NEXT:    adr x9, dst
+; CHECK-NEXT:    strb w8, [x9]
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: foo1:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x8, src
+; CHECK-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-GLOBISEL-NEXT:    adr x9, dst
+; CHECK-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: foo1:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    ldr x8, :got:src
+; CHECK-PIC-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-NEXT:    ldr x9, :got:dst
+; CHECK-PIC-NEXT:    strb w8, [x9]
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: foo1:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x8, :got:src
+; CHECK-PIC-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x9, :got:dst
+; CHECK-PIC-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+  %0 = load i8, i8* getelementptr inbounds ([65536 x i8], [65536 x i8]* @src, i64 0, i64 0), align 1
+  store i8 %0, i8* getelementptr inbounds ([65536 x i8], [65536 x i8]* @dst, i64 0, i64 0), align 1
+  ret void
+}
+
+define void @foo2() {
+; CHECK-LABEL: foo2:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x8, ptr
+; CHECK-NEXT:    adr x9, dst
+; CHECK-NEXT:    str x9, [x8]
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: foo2:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x8, dst
+; CHECK-GLOBISEL-NEXT:    adr x9, ptr
+; CHECK-GLOBISEL-NEXT:    str x8, [x9]
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: foo2:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    ldr x8, :got:ptr
+; CHECK-PIC-NEXT:    ldr x9, :got:dst
+; CHECK-PIC-NEXT:    str x9, [x8]
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: foo2:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x8, :got:dst
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x9, :got:ptr
+; CHECK-PIC-GLOBISEL-NEXT:    str x8, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+  store i8* getelementptr inbounds ([65536 x i8], [65536 x i8]* @dst, i64 0, i64 0), i8** @ptr, align 8
+  ret void
+}
+
+define void @foo3() {
+; FIXME: Needn't adr ptr
+;
+; CHECK-LABEL: foo3:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x8, src
+; CHECK-NEXT:    adr x9, ptr
+; CHECK-NEXT:    ldrb w8, [x8]
+; CHECK-NEXT:    ldr x9, [x9]
+; CHECK-NEXT:    strb w8, [x9]
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: foo3:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x8, src
+; CHECK-GLOBISEL-NEXT:    adr x9, ptr
+; CHECK-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-GLOBISEL-NEXT:    ldr x9, [x9]
+; CHECK-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: foo3:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    ldr x8, :got:src
+; CHECK-PIC-NEXT:    ldr x9, :got:ptr
+; CHECK-PIC-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-NEXT:    ldr x9, [x9]
+; CHECK-PIC-NEXT:    strb w8, [x9]
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: foo3:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x8, :got:src
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x9, :got:ptr
+; CHECK-PIC-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x9, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+  %0 = load i8, i8* getelementptr inbounds ([65536 x i8], [65536 x i8]* @src, i64 0, i64 0), align 1
+  %1 = load i8*, i8** @ptr, align 8
+  store i8 %0, i8* %1, align 1
+  ret void
+}
+
+@lsrc = internal global i8 0, align 4
+@ldst = internal global i8 0, align 4
+@lptr = internal global i8* null, align 8
+
+define void @bar1() {
+; CHECK-LABEL: bar1:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x8, lsrc
+; CHECK-NEXT:    ldrb w8, [x8]
+; CHECK-NEXT:    adr x9, ldst
+; CHECK-NEXT:    strb w8, [x9]
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: bar1:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x8, lsrc
+; CHECK-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-GLOBISEL-NEXT:    adr x9, ldst
+; CHECK-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: bar1:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    adr x8, lsrc
+; CHECK-PIC-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-NEXT:    adr x9, ldst
+; CHECK-PIC-NEXT:    strb w8, [x9]
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: bar1:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    adr x8, lsrc
+; CHECK-PIC-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-GLOBISEL-NEXT:    adr x9, ldst
+; CHECK-PIC-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+  %0 = load i8, i8* @lsrc, align 4
+  store i8 %0, i8* @ldst, align 4
+  ret void
+}
+
+define void @bar2() {
+; CHECK-LABEL: bar2:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x8, lptr
+; CHECK-NEXT:    adr x9, ldst
+; CHECK-NEXT:    str x9, [x8]
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: bar2:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x8, ldst
+; CHECK-GLOBISEL-NEXT:    adr x9, lptr
+; CHECK-GLOBISEL-NEXT:    str x8, [x9]
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: bar2:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    adr x8, lptr
+; CHECK-PIC-NEXT:    adr x9, ldst
+; CHECK-PIC-NEXT:    str x9, [x8]
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: bar2:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    adr x8, ldst
+; CHECK-PIC-GLOBISEL-NEXT:    adr x9, lptr
+; CHECK-PIC-GLOBISEL-NEXT:    str x8, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+  store i8* @ldst, i8** @lptr, align 8
+  ret void
+}
+
+define void @bar3() {
+; FIXME: Needn't adr lptr
+;
+; CHECK-LABEL: bar3:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x8, lsrc
+; CHECK-NEXT:    adr x9, lptr
+; CHECK-NEXT:    ldrb w8, [x8]
+; CHECK-NEXT:    ldr x9, [x9]
+; CHECK-NEXT:    strb w8, [x9]
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: bar3:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x8, lsrc
+; CHECK-GLOBISEL-NEXT:    adr x9, lptr
+; CHECK-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-GLOBISEL-NEXT:    ldr x9, [x9]
+; CHECK-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: bar3:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    adr x8, lsrc
+; CHECK-PIC-NEXT:    adr x9, lptr
+; CHECK-PIC-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-NEXT:    ldr x9, [x9]
+; CHECK-PIC-NEXT:    strb w8, [x9]
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: bar3:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    adr x8, lsrc
+; CHECK-PIC-GLOBISEL-NEXT:    adr x9, lptr
+; CHECK-PIC-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x9, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+  %0 = load i8, i8* @lsrc, align 4
+  %1 = load i8*, i8** @lptr, align 8
+  store i8 %0, i8* %1, align 1
+  ret void
+}
+
+
+@lbsrc = internal global [65536 x i8] zeroinitializer, align 4
+@lbdst = internal global [65536 x i8] zeroinitializer, align 4
+
+define void @baz1() {
+; CHECK-LABEL: baz1:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x8, lbsrc
+; CHECK-NEXT:    ldrb w8, [x8]
+; CHECK-NEXT:    adr x9, lbdst
+; CHECK-NEXT:    strb w8, [x9]
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: baz1:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x8, lbsrc
+; CHECK-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-GLOBISEL-NEXT:    adr x9, lbdst
+; CHECK-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: baz1:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    adr x8, lbsrc
+; CHECK-PIC-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-NEXT:    adr x9, lbdst
+; CHECK-PIC-NEXT:    strb w8, [x9]
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: baz1:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    adr x8, lbsrc
+; CHECK-PIC-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-GLOBISEL-NEXT:    adr x9, lbdst
+; CHECK-PIC-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+  %0 = load i8, i8* getelementptr inbounds ([65536 x i8], [65536 x i8]* @lbsrc, i64 0, i64 0), align 4
+  store i8 %0, i8* getelementptr inbounds ([65536 x i8], [65536 x i8]* @lbdst, i64 0, i64 0), align 4
+  ret void
+}
+
+define void @baz2() {
+; CHECK-LABEL: baz2:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x8, lptr
+; CHECK-NEXT:    adr x9, lbdst
+; CHECK-NEXT:    str x9, [x8]
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: baz2:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x8, lbdst
+; CHECK-GLOBISEL-NEXT:    adr x9, lptr
+; CHECK-GLOBISEL-NEXT:    str x8, [x9]
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: baz2:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    adr x8, lptr
+; CHECK-PIC-NEXT:    adr x9, lbdst
+; CHECK-PIC-NEXT:    str x9, [x8]
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: baz2:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    adr x8, lbdst
+; CHECK-PIC-GLOBISEL-NEXT:    adr x9, lptr
+; CHECK-PIC-GLOBISEL-NEXT:    str x8, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+  store i8* getelementptr inbounds ([65536 x i8], [65536 x i8]* @lbdst, i64 0, i64 0), i8** @lptr, align 8
+  ret void
+}
+
+define void @baz3() {
+; FIXME: Needn't adr lptr
+;
+; CHECK-LABEL: baz3:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x8, lbsrc
+; CHECK-NEXT:    adr x9, lptr
+; CHECK-NEXT:    ldrb w8, [x8]
+; CHECK-NEXT:    ldr x9, [x9]
+; CHECK-NEXT:    strb w8, [x9]
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: baz3:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x8, lbsrc
+; CHECK-GLOBISEL-NEXT:    adr x9, lptr
+; CHECK-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-GLOBISEL-NEXT:    ldr x9, [x9]
+; CHECK-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: baz3:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    adr x8, lbsrc
+; CHECK-PIC-NEXT:    adr x9, lptr
+; CHECK-PIC-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-NEXT:    ldr x9, [x9]
+; CHECK-PIC-NEXT:    strb w8, [x9]
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: baz3:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    adr x8, lbsrc
+; CHECK-PIC-GLOBISEL-NEXT:    adr x9, lptr
+; CHECK-PIC-GLOBISEL-NEXT:    ldrb w8, [x8]
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x9, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    strb w8, [x9]
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+  %0 = load i8, i8* getelementptr inbounds ([65536 x i8], [65536 x i8]* @lbsrc, i64 0, i64 0), align 4
+  %1 = load i8*, i8** @lptr, align 8
+  store i8 %0, i8* %1, align 1
+  ret void
+}
+
+
+declare void @func(...)
+
+define i8* @externfuncaddr() {
+; CHECK-LABEL: externfuncaddr:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x0, func
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: externfuncaddr:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x0, func
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: externfuncaddr:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    ldr x0, :got:func
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: externfuncaddr:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x0, :got:func
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+      ret i8* bitcast (void (...)* @func to i8*)
+}
+
+define i8* @localfuncaddr() {
+; CHECK-LABEL: localfuncaddr:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    adr x0, externfuncaddr
+; CHECK-NEXT:    ret
+;
+; CHECK-GLOBISEL-LABEL: localfuncaddr:
+; CHECK-GLOBISEL:       // %bb.0: // %entry
+; CHECK-GLOBISEL-NEXT:    adr x0, externfuncaddr
+; CHECK-GLOBISEL-NEXT:    ret
+;
+; CHECK-PIC-LABEL: localfuncaddr:
+; CHECK-PIC:       // %bb.0: // %entry
+; CHECK-PIC-NEXT:    ldr x0, :got:externfuncaddr
+; CHECK-PIC-NEXT:    ret
+;
+; CHECK-PIC-GLOBISEL-LABEL: localfuncaddr:
+; CHECK-PIC-GLOBISEL:       // %bb.0: // %entry
+; CHECK-PIC-GLOBISEL-NEXT:    ldr x0, :got:externfuncaddr
+; CHECK-PIC-GLOBISEL-NEXT:    ret
+entry:
+      ret i8* bitcast (i8* ()* @externfuncaddr to i8*)
+}
+

llvm/test/CodeGen/AArch64/tiny_supported.ll

@@ -0,0 +1,13 @@
+; RUN: llc -verify-machineinstrs -o - -mtriple=aarch64-none-linux-gnu -code-model=tiny < %s 2>&1 | FileCheck %s
+; RUN: llc -verify-machineinstrs -o - -mtriple=aarch64-none-eabi -code-model=tiny < %s 2>&1 | FileCheck %s
+; RUN: not llc -verify-machineinstrs -o - -mtriple=arm64-apple-darwin -code-model=tiny < %s 2>&1 | FileCheck %s --check-prefix=NOTINY
+; RUN: not llc -verify-machineinstrs -o - -mtriple=arm64-apple-ios -code-model=tiny < %s 2>&1 | FileCheck %s --check-prefix=NOTINY
+; RUN: not llc -verify-machineinstrs -o - -mtriple=aarch64-unknown-windows-msvc -code-model=tiny < %s 2>&1 | FileCheck %s --check-prefix=NOTINY
+
+; CHECK-NOT:   tiny code model is only supported on ELF
+; CHECK-LABEL:   foo
+; NOTINY:   tiny code model is only supported on ELF
+
+define void @foo() {
+  ret void
+}

llvm/test/MC/AArch64/basic-a64-diagnostics.s

@@ -3315,17 +3315,25 @@
 //------------------------------------------------------------------------------
 
         adr sp, loc             // expects xzr
+        adr x0, :got:loc        // bad relocation type
         adrp x3, #20            // Immediate unaligned
         adrp w2, loc            // 64-bit register needed
+        adrp x5, :got_lo12:loc  // bad relocation type
 // CHECK-ERROR: error: invalid operand for instruction
 // CHECK-ERROR-NEXT:         adr sp, loc
 // CHECK-ERROR-NEXT:             ^
+// CHECK-ERROR-NEXT: error: unexpected adr label
+// CHECK-ERROR-NEXT:         adr x0, :got:loc
+// CHECK-ERROR-NEXT:             ^
 // CHECK-ERROR-NEXT: error: expected label or encodable integer pc offset
 // CHECK-ERROR-NEXT:         adrp x3, #20
 // CHECK-ERROR-NEXT:                  ^
 // CHECK-ERROR-NEXT: error: invalid operand for instruction
 // CHECK-ERROR-NEXT:         adrp w2, loc
 // CHECK-ERROR-NEXT:              ^
+// CHECK-ERROR-NEXT: error: page or gotpage label reference expected
+// CHECK-ERROR-NEXT:         adrp x5, :got_lo12:loc
+// CHECK-ERROR-NEXT:             ^
 
         adr x9, #1048576
         adr x2, #-1048577