Index: lib/CodeGen/AsmPrinter/AsmPrinter.cpp
===================================================================
--- lib/CodeGen/AsmPrinter/AsmPrinter.cpp
+++ lib/CodeGen/AsmPrinter/AsmPrinter.cpp
@@ -388,6 +388,12 @@
   assert(!(IsEmuTLSVar && GV->hasCommonLinkage()) &&
          "No emulated TLS variables in the common section");
 
+  // When in emulated TLS mode, skip __emutls_v.* variables.
+  // __emutls_v.xyz and __emutls_t.xyz are emitted in place of xyz.
+  // __emutls_t.xyz is not in the symbol table.
+  if (TM.Options.EmulatedTLS && GV->getName().startswith("__emutls_v."))
+    return;
+
   if (GV->hasInitializer()) {
     // Check to see if this is a special global used by LLVM, if so, emit it.
     if (EmitSpecialLLVMGlobal(GV))
Index: lib/CodeGen/SelectionDAG/TargetLowering.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -3072,9 +3072,19 @@
   Module *VariableModule = const_cast<Module*>(GA->getGlobal()->getParent());
   StringRef EmuTlsVarName(NameString);
   GlobalVariable *EmuTlsVar = VariableModule->getNamedGlobal(EmuTlsVarName);
-  if (!EmuTlsVar)
+  if (!EmuTlsVar) {
     EmuTlsVar = dyn_cast_or_null<GlobalVariable>(
         VariableModule->getOrInsertGlobal(EmuTlsVarName, VoidPtrType));
+    // EmuTlsVar should have the same linkage as its TLS variable.
+    // getOrInsertGlobal always creates new ExternalLinkage variable.
+    EmuTlsVar->setLinkage(GA->getGlobal()->getLinkage());
+    if (!EmuTlsVar->hasInitializer() &&
+        dyn_cast<GlobalVariable>(GA->getGlobal())->hasInitializer()) {
+      // A fake initializer is necessary to pass through all verification phases.
+      // Real initializer is computed later from the TLS variable.
+      EmuTlsVar->setInitializer(ConstantPointerNull::get(VoidPtrType));
+    }
+  }
   Entry.Node = DAG.getGlobalAddress(EmuTlsVar, dl, PtrVT);
   Entry.Ty = VoidPtrType;
   Args.push_back(Entry);
Index: test/CodeGen/AArch64/emutls.ll
===================================================================
--- test/CodeGen/AArch64/emutls.ll
+++ test/CodeGen/AArch64/emutls.ll
@@ -54,59 +54,88 @@
   ret i32* @i1
 }
 
+define i32 @f5() nounwind {
+; ARM64-LABEL: f5:
+; ARM64:        adrp x0, __emutls_v.i3
+; ARM64:        add x0, x0, :lo12:__emutls_v.i3
+; ARM64-NEXT:   bl __emutls_get_address
+; ARM64-NEXT:   ldr w0, [x0]
+
+entry:
+  %tmp1 = load i32, i32* @i3
+  ret i32 %tmp1
+}
+
+define i32* @f6() {
+; ARM64-LABEL: f6:
+; ARM64:        adrp x0, __emutls_v.i3
+; ARM64:        add x0, x0, :lo12:__emutls_v.i3
+; ARM64-NEXT:   bl __emutls_get_address
+; ARM64-NEXT:   ldp x29, x30, [sp]
+
+entry:
+  ret i32* @i3
+}
+
+
 ;;;;;;;;;;;;;; 64-bit __emutls_v. and __emutls_t.
 
-; ARM64       .section .data.rel.local,
+; ARM64:      .data{{$}}
+; ARM64:      .globl __emutls_v.i1
 ; ARM64-LABEL: __emutls_v.i1:
 ; ARM64-NEXT: .xword 4
 ; ARM64-NEXT: .xword 4
 ; ARM64-NEXT: .xword 0
 ; ARM64-NEXT: .xword __emutls_t.i1
 
-; ARM64       .section .rodata,
+; ARM64:      .section .rodata,
 ; ARM64-LABEL: __emutls_t.i1:
 ; ARM64-NEXT: .word 15
 
 ; ARM64-NOT:   __emutls_v.i2
 
-; ARM64       .section .data.rel.local,
+; ARM64:      .data{{$}}
+; ARM64-NOT:  .globl
 ; ARM64-LABEL: __emutls_v.i3:
 ; ARM64-NEXT: .xword 4
 ; ARM64-NEXT: .xword 4
 ; ARM64-NEXT: .xword 0
 ; ARM64-NEXT: .xword __emutls_t.i3
 
-; ARM64       .section .rodata,
+; ARM64:      .section .rodata,
 ; ARM64-LABEL: __emutls_t.i3:
 ; ARM64-NEXT: .word 15
 
-; ARM64       .section .data.rel.local,
+; ARM64:      .hidden __emutls_v.i4
+; ARM64:      .data{{$}}
+; ARM64:      .globl __emutls_v.i4
 ; ARM64-LABEL: __emutls_v.i4:
 ; ARM64-NEXT: .xword 4
 ; ARM64-NEXT: .xword 4
 ; ARM64-NEXT: .xword 0
 ; ARM64-NEXT: .xword __emutls_t.i4
 
-; ARM64       .section .rodata,
+; ARM64:      .section .rodata,
 ; ARM64-LABEL: __emutls_t.i4:
 ; ARM64-NEXT: .word 15
 
 ; ARM64-NOT:   __emutls_v.i5:
-; ARM64       .hidden __emutls_v.i5
+; ARM64:      .hidden __emutls_v.i5
 ; ARM64-NOT:   __emutls_v.i5:
 
-; ARM64       .section .data.rel.local,
+; ARM64:      .data{{$}}
+; ARM64:      .globl __emutls_v.s1
 ; ARM64-LABEL: __emutls_v.s1:
 ; ARM64-NEXT: .xword 2
 ; ARM64-NEXT: .xword 2
 ; ARM64-NEXT: .xword 0
 ; ARM64-NEXT: .xword __emutls_t.s1
 
-; ARM64       .section .rodata,
+; ARM64:      .section .rodata,
 ; ARM64-LABEL: __emutls_t.s1:
 ; ARM64-NEXT: .hword 15
 
-; ARM64       .section .data.rel.local,
+; ARM64:      .data{{$}}
 ; ARM64-LABEL: __emutls_v.b1:
 ; ARM64-NEXT: .xword 1
 ; ARM64-NEXT: .xword 1
Index: test/CodeGen/AArch64/emutls_generic.ll
===================================================================
--- test/CodeGen/AArch64/emutls_generic.ll
+++ test/CodeGen/AArch64/emutls_generic.ll
@@ -37,6 +37,8 @@
 ; ARM_64:      __emutls_get_address
 ; ARM_64-NOT:   __emutls_t.external_x
 ; ARM_64-NOT:   __emutls_v.external_x:
+; ARM_64:        .data{{$}}
+; ARM_64:        .globl __emutls_v.external_y
 ; ARM_64:        .align 3
 ; ARM_64-LABEL:  __emutls_v.external_y:
 ; ARM_64-NEXT:   .xword 1
@@ -47,7 +49,8 @@
 ; ARM_64:        .section .rodata,
 ; ARM_64-LABEL:  __emutls_t.external_y:
 ; ARM_64-NEXT:   .byte 7
-; ARM_64:        .data
+; ARM_64:        .data{{$}}
+; ARM_64-NOT:    .globl __emutls_v
 ; ARM_64:        .align 3
 ; ARM_64-LABEL:  __emutls_v.internal_y:
 ; ARM_64-NEXT:   .xword 8
Index: test/CodeGen/ARM/emutls.ll
===================================================================
--- test/CodeGen/ARM/emutls.ll
+++ test/CodeGen/ARM/emutls.ll
@@ -13,6 +13,7 @@
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl my_emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
+; ARM32:        .long my_emutls_v_xyz(GOT_PREL)
 
 entry:
   %call = call i8* @my_emutls_get_address(i8* bitcast (i8** @my_emutls_v_xyz to i8*))
@@ -35,6 +36,7 @@
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
+; ARM32:        .long __emutls_v.i1(GOT_PREL)
 
 entry:
   %tmp1 = load i32, i32* @i1
@@ -47,6 +49,7 @@
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
+; ARM32:        .long __emutls_v.i1(GOT_PREL)
 
 entry:
   ret i32* @i1
@@ -58,6 +61,7 @@
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
+; ARM32:        .long __emutls_v.i2(GOT_PREL)
 
 entry:
   %tmp1 = load i32, i32* @i2
@@ -70,6 +74,7 @@
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
+; ARM32:        .long __emutls_v.i2(GOT_PREL)
 
 entry:
   ret i32* @i2
@@ -78,9 +83,10 @@
 define i32 @f5() nounwind {
 ; ARM32-LABEL: f5:
 ; ARM32:        ldr r0,
-; ARM32:        ldr r0, [pc, r0]
+; ARM32:        add	r0, pc, r0
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
+; ARM32:        .long __emutls_v.i3-
 
 entry:
   %tmp1 = load i32, i32* @i3
@@ -90,9 +96,10 @@
 define i32* @f6() {
 ; ARM32-LABEL: f6:
 ; ARM32:        ldr r0,
-; ARM32:        ldr r0, [pc, r0]
+; ARM32:        add	r0, pc, r0
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
+; ARM32:        .long __emutls_v.i3-
 
 entry:
   ret i32* @i3
@@ -104,6 +111,7 @@
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   ldr r0, [r0]
+; ARM32:        .long __emutls_v.i4(GOT_PREL)
 
 entry:
   %tmp1 = load i32, i32* @i4
@@ -116,6 +124,7 @@
 ; ARM32:        ldr r0, [pc, r0]
 ; ARM32-NEXT:   bl __emutls_get_address(PLT)
 ; ARM32-NEXT:   pop
+; ARM32:        .long __emutls_v.i4(GOT_PREL)
 
 entry:
   ret i32* @i4
@@ -198,46 +207,50 @@
 
 ;;;;;;;;;;;;;; 32-bit __emutls_v. and __emutls_t.
 
-; ARM32       .section .data.rel.local,
+; ARM32:      .data{{$}}
+; ARM32:      .globl __emutls_v.i1
 ; ARM32-LABEL: __emutls_v.i1:
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 0
 ; ARM32-NEXT: .long __emutls_t.i1
 
-; ARM32       .section .rodata,
+; ARM32:      .section .rodata,
 ; ARM32-LABEL: __emutls_t.i1:
 ; ARM32-NEXT: .long 15
 
 ; ARM32-NOT:   __emutls_v.i2
 
-; ARM32       .section .data.rel.local,
+; ARM32:      .data{{$}}
+; ARM32-NOT:  .globl
 ; ARM32-LABEL: __emutls_v.i3:
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 0
 ; ARM32-NEXT: .long __emutls_t.i3
 
-; ARM32       .section .rodata,
+; ARM32:      .section .rodata,
 ; ARM32-LABEL: __emutls_t.i3:
 ; ARM32-NEXT: .long 15
 
-; ARM32       .section .data.rel.local,
+; ARM32:      .data{{$}}
+; ARM32:      .globl __emutls_v.i4
 ; ARM32-LABEL: __emutls_v.i4:
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 0
 ; ARM32-NEXT: .long __emutls_t.i4
 
-; ARM32       .section .rodata,
+; ARM32:      .section .rodata,
 ; ARM32-LABEL: __emutls_t.i4:
 ; ARM32-NEXT: .long 15
 
 ; ARM32-NOT:   __emutls_v.i5:
-; ARM32       .hidden __emutls_v.i5
+; ARM32:      .hidden __emutls_v.i5
 ; ARM32-NOT:   __emutls_v.i5:
 
-; ARM32 .section .data.rel.local,
+; ARM32:      .data{{$}}
+; ARM32:      .globl __emutls_v.s1
 ; ARM32-LABEL: __emutls_v.s1:
 ; ARM32-NEXT: .long 2
 ; ARM32-NEXT: .long 2
@@ -248,7 +261,8 @@
 ; ARM32-LABEL: __emutls_t.s1:
 ; ARM32-NEXT: .short 15
 
-; ARM32 .section .data.rel.local,
+; ARM32:      .data{{$}}
+; ARM32:      .globl __emutls_v.b1
 ; ARM32-LABEL: __emutls_v.b1:
 ; ARM32-NEXT: .long 1
 ; ARM32-NEXT: .long 1
Index: test/CodeGen/ARM/emutls_generic.ll
===================================================================
--- test/CodeGen/ARM/emutls_generic.ll
+++ test/CodeGen/ARM/emutls_generic.ll
@@ -35,11 +35,12 @@
 ; ARM_32:        bl __emutls_get_address
 ; ARM_32:        .long __emutls_v.external_y
 ; ARM_32-LABEL:  get_internal_y:
-; ARM_32:      bl __emutls_get_address
-; ARM_32:      .long __emutls_v.internal_y
-; ARM_32-NOT:   __emutls_t.external_x
-; ARM_32-NOT:   __emutls_v.external_x:
-; ARM_32:        .data
+; ARM_32:        bl __emutls_get_address
+; ARM_32:        .long __emutls_v.internal_y
+; ARM_32-NOT:    __emutls_t.external_x
+; ARM_32-NOT:    __emutls_v.external_x:
+; ARM_32:        .data{{$}}
+; ARM_32:        .globl __emutls_v.external_y
 ; ARM_32:        .align 2
 ; ARM_32-LABEL:  __emutls_v.external_y:
 ; ARM_32-NEXT:   .long 1
@@ -49,7 +50,8 @@
 ; ARM_32:        .section .rodata,
 ; ARM_32-LABEL:  __emutls_t.external_y:
 ; ARM_32-NEXT:   .byte 7
-; ARM_32:        .data
+; ARM_32:        .data{{$}}
+; ARM_32-NOT:    .globl
 ; ARM_32:        .align 2
 ; ARM_32-LABEL:  __emutls_v.internal_y:
 ; ARM_32-NEXT:   .long 8
Index: test/CodeGen/X86/emutls-pic.ll
===================================================================
--- test/CodeGen/X86/emutls-pic.ll
+++ test/CodeGen/X86/emutls-pic.ll
@@ -82,28 +82,29 @@
 }
 
 ; X32-LABEL: f5:
-; X32:      movl __emutls_v.j@GOT(%ebx), %eax
+; X32:      leal __emutls_v.j@GOTOFF(%ebx), %eax
 ; X32-NEXT: movl %eax, (%esp)
 ; X32-NEXT: calll __emutls_get_address@PLT
 ; X32-NEXT: movl (%eax), %esi
-; X32-NEXT: movl __emutls_v.k@GOT(%ebx), %eax
+; X32-NEXT: leal __emutls_v.k@GOTOFF(%ebx), %eax
 ; X32-NEXT: movl %eax, (%esp)
 ; X32-NEXT: calll __emutls_get_address@PLT
 ; X32-NEXT: addl (%eax), %esi
 ; X32-NEXT: movl %esi, %eax
 
 ; X64-LABEL: f5:
-; X64:      movq __emutls_v.j@GOTPCREL(%rip), %rdi
+; X64:      leaq __emutls_v.j(%rip), %rdi
 ; X64-NEXT: callq __emutls_get_address@PLT
 ; X64-NEXT: movl (%rax), %ebx
-; X64-NEXT: movq __emutls_v.k@GOTPCREL(%rip), %rdi
+; X64-NEXT: leaq __emutls_v.k(%rip), %rdi
 ; X64-NEXT: callq __emutls_get_address@PLT
 ; X64-NEXT: addl (%rax), %ebx
 ; X64-NEXT: movl %ebx, %eax
 
 ;;;;; 32-bit targets
 
-; X32:      .data
+; X32:      .data{{$}}
+; X32:      .globl __emutls_v.i
 ; X32-LABEL: __emutls_v.i:
 ; X32-NEXT: .long 4
 ; X32-NEXT: .long 4
@@ -114,7 +115,8 @@
 ; X32-LABEL: __emutls_t.i:
 ; X32-NEXT: .long 15
 
-; X32:      .data
+; X32:      .data{{$}}
+; X32-NOT:  .globl
 ; X32-LABEL: __emutls_v.j:
 ; X32-NEXT: .long 4
 ; X32-NEXT: .long 4
@@ -125,7 +127,8 @@
 ; X32-LABEL: __emutls_t.j:
 ; X32-NEXT: .long 42
 
-; X32:      .data
+; X32:      .data{{$}}
+; X32-NOT:  .globl
 ; X32-LABEL: __emutls_v.k:
 ; X32-NEXT: .long 4
 ; X32-NEXT: .long 8
@@ -136,7 +139,8 @@
 
 ;;;;; 64-bit targets
 
-; X64:      .data
+; X64:      .data{{$}}
+; X64:      .globl __emutls_v.i
 ; X64-LABEL: __emutls_v.i:
 ; X64-NEXT: .quad 4
 ; X64-NEXT: .quad 4
@@ -147,7 +151,8 @@
 ; X64-LABEL: __emutls_t.i:
 ; X64-NEXT: .long 15
 
-; X64:      .data
+; X64:      .data{{$}}
+; X64-NOT:  .globl
 ; X64-LABEL: __emutls_v.j:
 ; X64-NEXT: .quad 4
 ; X64-NEXT: .quad 4
@@ -158,7 +163,8 @@
 ; X64-LABEL: __emutls_t.j:
 ; X64-NEXT: .long 42
 
-; X64:      .data
+; X64:      .data{{$}}
+; X64-NOT:  .globl
 ; X64-LABEL: __emutls_v.k:
 ; X64-NEXT: .quad 4
 ; X64-NEXT: .quad 8
Index: test/CodeGen/X86/emutls_generic.ll
===================================================================
--- test/CodeGen/X86/emutls_generic.ll
+++ test/CodeGen/X86/emutls_generic.ll
@@ -45,17 +45,18 @@
 ; CHECK:       __emutls_t.internal_y
 
 ; X86_32-LABEL:  get_external_x:
-; X86_32:        movl __emutls_v.external_x
+; X86_32:        movl __emutls_v.external_x@GOT(%ebx)
 ; X86_32:        calll __emutls_get_address
 ; X86_32-LABEL:  get_external_y:
-; X86_32:        movl __emutls_v.external_y
+; X86_32:        movl __emutls_v.external_y@GOT(%ebx)
 ; X86_32:        calll __emutls_get_address
 ; X86_32-LABEL:  get_internal_y:
-; X86_32:      movl __emutls_v.internal_y
-; X86_32:      calll __emutls_get_address
-; X86_32-NOT:   __emutls_t.external_x
-; X86_32-NOT:   __emutls_v.external_x:
-; X86_32:        .data
+; X86_32:        leal __emutls_v.internal_y@GOTOFF(%ebx)
+; X86_32:        calll __emutls_get_address
+; X86_32-NOT:    __emutls_t.external_x
+; X86_32-NOT:    __emutls_v.external_x:
+; X86_32:        .data{{$}}
+; X86_32:        .globl __emutls_v.external_y
 ; X86_32:        .align 4
 ; X86_32-LABEL:  __emutls_v.external_y:
 ; X86_32-NEXT:   .long 1
@@ -65,7 +66,8 @@
 ; X86_32:        .section .rodata,
 ; X86_32-LABEL:  __emutls_t.external_y:
 ; X86_32-NEXT:   .byte 7
-; X86_32:        .data
+; X86_32:        .data{{$}}
+; X86_32-NOT:    .globl
 ; X86_32:        .align 4
 ; X86_32-LABEL:  __emutls_v.internal_y:
 ; X86_32-NEXT:   .long 8
@@ -75,16 +77,17 @@
 ; X86_32-LABEL:  __emutls_t.internal_y:
 ; X86_32-NEXT:   .quad 9
 ; X86_64-LABEL:  get_external_x:
-; X86_64:      __emutls_v.external_x
-; X86_64:      __emutls_get_address
+; X86_64:        __emutls_v.external_x@GOTPCREL(%rip)
+; X86_64:        __emutls_get_address
 ; X86_64-LABEL:  get_external_y:
-; X86_64:      __emutls_v.external_y
-; X86_64:      __emutls_get_address
+; X86_64:        __emutls_v.external_y@GOTPCREL(%rip)
+; X86_64:        __emutls_get_address
 ; X86_64-LABEL:  get_internal_y:
-; X86_64:      __emutls_v.internal_y
-; X86_64:      __emutls_get_address
-; X86_64-NOT:   __emutls_t.external_x
-; X86_64-NOT:   __emutls_v.external_x:
+; X86_64:        __emutls_v.internal_y(%rip)
+; X86_64:        __emutls_get_address
+; X86_64-NOT:    __emutls_t.external_x
+; X86_64-NOT:    __emutls_v.external_x:
+; X86_64:        .globl __emutls_v.external_y
 ; X86_64:        .align 8
 ; X86_64-LABEL:  __emutls_v.external_y:
 ; X86_64-NEXT:   .quad 1
@@ -95,7 +98,8 @@
 ; X86_64:        .section .rodata,
 ; X86_64-LABEL:  __emutls_t.external_y:
 ; X86_64-NEXT:   .byte 7
-; X86_64:        .data
+; X86_64:        .data{{$}}
+; X86_64-NOT:    .globl
 ; X86_64:        .align 8
 ; X86_64-LABEL:  __emutls_v.internal_y:
 ; X86_64-NEXT:   .quad 8