[AArch64] Allow using emulated tls on platforms other than ELF

[mstorsjo]

Summary

This matches how it is done on X86.

This allows using emulated tls on windows; in MinGW environments, native tls isn't supported at the moment.

Set the right Data*bitsDirective to match the existing tests for other platforms. Make parts of the existing tests a regex, to allow matching .section .rdata for windows, to avoid having to duplicate the rest of the tests.

[compnerd]

Please add a MachO test as this enables emulated TLS on MachO as well.

lib/Target/AArch64/AArch64ISelLowering.cpp

   // 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.
   const GlobalAddressSDNode *GA = cast<GlobalAddressSDNode>(Op);
 
   TLSModel::Model Model = getTargetMachine().getTLSModel(GA->getGlobal());
 
-  if (DAG.getTarget().Options.EmulatedTLS)
-    return LowerToTLSEmulatedModel(GA, DAG);
-
   if (!EnableAArch64ELFLocalDynamicTLSGeneration) {
     if (Model == TLSModel::LocalDynamic)
       Model = TLSModel::GeneralDynamic;
   }
 
   SDValue TPOff;
   EVT PtrVT = getPointerTy(DAG.getDataLayout());
   SDLoc DL(Op);

 //  0000000000000014: 39400140  ldrb        w0,[x10,?msgHandlerGrabbed@@3_NA]
   Offset = DAG.getNode(AArch64ISD::LOADgot, DL, PtrVT, Offset);
   Offset = DAG.getNode(ISD::ADD, DL, PtrVT, TLS, Offset);
   return Offset;
 }
 
 SDValue AArch64TargetLowering::LowerGlobalTLSAddress(SDValue Op,
                                                      SelectionDAG &DAG) const {
+  const GlobalAddressSDNode *GA = cast<GlobalAddressSDNode>(Op);
+  if (DAG.getTarget().Options.EmulatedTLS)
+    return LowerToTLSEmulatedModel(GA, DAG);
+
   if (Subtarget->isTargetDarwin())
     return LowerDarwinGlobalTLSAddress(Op, DAG);
   if (Subtarget->isTargetELF())
     return LowerELFGlobalTLSAddress(Op, DAG);
   if (Subtarget->isTargetWindows())
     return LowerWindowsGlobalTLSAddress(Op, DAG);
 
   llvm_unreachable("Unexpected platform trying to use TLS");

lib/Target/AArch64/MCTargetDesc/AArch64MCAsmInfo.cpp

AArch64MCAsmInfoELF::AArch64MCAsmInfoELF(const Triple &T) {
   UseIntegratedAssembler = true;
 
   HasIdentDirective = true;
 }
 
 AArch64MCAsmInfoCOFF::AArch64MCAsmInfoCOFF() {
   PrivateGlobalPrefix = ".L";
   PrivateLabelPrefix = ".L";
+
+  Data16bitsDirective = "\t.hword\t";
+  Data32bitsDirective = "\t.word\t";
+  Data64bitsDirective = "\t.xword\t";
+
   AlignmentIsInBytes = false;
   SupportsDebugInformation = true;
   CodePointerSize = 8;
 }
 
 AArch64MCAsmInfoMicrosoftCOFF::AArch64MCAsmInfoMicrosoftCOFF() {
   CommentString = ";";
   ExceptionsType = ExceptionHandling::WinEH;
 }
 
 AArch64MCAsmInfoGNUCOFF::AArch64MCAsmInfoGNUCOFF() {
   CommentString = "//";
   ExceptionsType = ExceptionHandling::DwarfCFI;
 }

test/CodeGen/AArch64/emutls_generic.ll

 ; RUN: llc < %s -emulated-tls -mtriple=aarch64-linux-android -relocation-model=pic \
 ; RUN:     | FileCheck -check-prefix=ARM_64 %s
 ; RUN: llc < %s -emulated-tls -mtriple=aarch64-linux-android -relocation-model=pic -O3 \
 ; RUN:     | FileCheck -check-prefix=ARM_64 %s
 ; RUN: llc < %s -emulated-tls -mtriple=aarch64-linux-android -O3 \
 ; RUN:     | FileCheck -check-prefix=ARM_64 %s
+; RUN: llc < %s -emulated-tls -mtriple=aarch64-windows-gnu -O3 \
+; RUN:     | FileCheck -check-prefix=ARM_64 %s
 
 ; Make sure that TLS symbols are emitted in expected order.
 
 @external_x = external thread_local global i32, align 8
 @external_y = thread_local global i8 7, align 2
 @internal_y = internal thread_local global i64 9, align 16
 
 define i32* @get_external_x() {

 ; ARM_64:        .globl __emutls_v.external_y
 ; ARM_64:        .p2align 3
 ; ARM_64-LABEL:  __emutls_v.external_y:
 ; ARM_64-NEXT:   .xword 1
 ; ARM_64-NEXT:   .xword 2
 ; ARM_64-NEXT:   .xword 0
 ; ARM_64-NEXT:   .xword __emutls_t.external_y
 ; ARM_64-NOT:    __emutls_v.external_x:
-; ARM_64:        .section .rodata,
+; ARM_64:        .section .r{{o?}}data,
 ; ARM_64-LABEL:  __emutls_t.external_y:
 ; ARM_64-NEXT:   .byte 7
 ; ARM_64:        .data{{$}}
 ; ARM_64-NOT:    .globl __emutls_v
 ; ARM_64:        .p2align 3
 ; ARM_64-LABEL:  __emutls_v.internal_y:
 ; ARM_64-NEXT:   .xword 8
 ; ARM_64-NEXT:   .xword 16
 ; ARM_64-NEXT:   .xword 0
 ; ARM_64-NEXT:   .xword __emutls_t.internal_y
-; ARM_64:        .section .rodata,
+; ARM_64:        .section .r{{o?}}data,
 ; ARM_64-LABEL:  __emutls_t.internal_y:
 ; ARM_64-NEXT:   .xword 9