diff --git a/llvm/include/llvm/CodeGen/AsmPrinter.h b/llvm/include/llvm/CodeGen/AsmPrinter.h
--- a/llvm/include/llvm/CodeGen/AsmPrinter.h
+++ b/llvm/include/llvm/CodeGen/AsmPrinter.h
@@ -244,6 +244,11 @@
 
   MCSymbol *getSymbol(const GlobalValue *GV) const;
 
+  /// Similar to getSymbol() but preferred for references. On ELF, this uses a
+  /// local symbol if a reference to GV is guaranteed to be resolved to the
+  /// definition in the same module.
+  MCSymbol *getSymbolPreferLocal(const GlobalValue &GV) const;
+
   //===------------------------------------------------------------------===//
   // XRay instrumentation implementation.
   //===------------------------------------------------------------------===//
diff --git a/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp b/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
--- a/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
@@ -450,6 +450,15 @@
   return TM.getSymbol(GV);
 }
 
+MCSymbol *AsmPrinter::getSymbolPreferLocal(const GlobalValue &GV) const {
+  // On ELF, use .Lfoo$local if GV is a non-interposable GlobalObject definion.
+  if (TM.getTargetTriple().isOSBinFormatELF() &&
+      GlobalObject::isExternalLinkage(GV.getLinkage()) && GV.isDSOLocal() &&
+      !GV.isDeclaration() && isa<GlobalObject>(GV))
+    return getSymbolWithGlobalValueBase(&GV, "$local");
+  return TM.getSymbol(&GV);
+}
+
 /// EmitGlobalVariable - Emit the specified global variable to the .s file.
 void AsmPrinter::EmitGlobalVariable(const GlobalVariable *GV) {
   bool IsEmuTLSVar = TM.useEmulatedTLS() && GV->isThreadLocal();
@@ -631,6 +640,9 @@
   EmitAlignment(Alignment, GV);
 
   OutStreamer->EmitLabel(EmittedInitSym);
+  MCSymbol *LocalAlias = getSymbolPreferLocal(*GV);
+  if (LocalAlias != EmittedInitSym)
+    OutStreamer->EmitLabel(LocalAlias);
 
   EmitGlobalConstant(GV->getParent()->getDataLayout(), GV->getInitializer());
 
@@ -752,7 +764,14 @@
     report_fatal_error("'" + Twine(CurrentFnSym->getName()) +
                        "' label emitted multiple times to assembly file");
 
-  return OutStreamer->EmitLabel(CurrentFnSym);
+  OutStreamer->EmitLabel(CurrentFnSym);
+
+  if (TM.getTargetTriple().isOSBinFormatELF()) {
+    const Function &F = MF->getFunction();
+    MCSymbol *Sym = getSymbolPreferLocal(F);
+    if (Sym != CurrentFnSym)
+      OutStreamer->EmitLabel(Sym);
+  }
 }
 
 /// emitComments - Pretty-print comments for instructions.
diff --git a/llvm/test/CodeGen/AArch64/emutls.ll b/llvm/test/CodeGen/AArch64/emutls.ll
--- a/llvm/test/CodeGen/AArch64/emutls.ll
+++ b/llvm/test/CodeGen/AArch64/emutls.ll
@@ -155,6 +155,7 @@
 ; ARM64:      .data{{$}}
 ; ARM64:      .globl __emutls_v.i4
 ; ARM64-LABEL: __emutls_v.i4:
+; ARM64-NEXT: .L__emutls_v.i4$local:
 ; ARM64-NEXT: .xword 4
 ; ARM64-NEXT: .xword 4
 ; ARM64-NEXT: .xword 0
@@ -162,6 +163,7 @@
 
 ; ARM64:      .section .rodata,
 ; ARM64-LABEL: __emutls_t.i4:
+; ARM64-NEXT: .L__emutls_t.i4$local:
 ; ARM64-NEXT: .word 15
 
 ; ARM64-NOT:   __emutls_v.i5:
diff --git a/llvm/test/CodeGen/AArch64/machine-outliner-retaddr-sign-sp-mod.ll b/llvm/test/CodeGen/AArch64/machine-outliner-retaddr-sign-sp-mod.ll
--- a/llvm/test/CodeGen/AArch64/machine-outliner-retaddr-sign-sp-mod.ll
+++ b/llvm/test/CodeGen/AArch64/machine-outliner-retaddr-sign-sp-mod.ll
@@ -4,6 +4,7 @@
 @v = common dso_local global i32* null, align 8
 
 ; CHECK-LABEL:  foo:                                    // @foo
+; CHECK-NEXT:   .Lfoo$local:
 ; CHECK-NEXT:   // %bb.0:                               // %entry
 ; CHECK-NEXT:       paciasp
 ; CHECK-NOT:        OUTLINED_FUNCTION_
@@ -22,6 +23,7 @@
 }
 
 ; CHECK-LABEL:  bar:                                    // @bar
+; CHECK-NEXT:   .Lbar$local:
 ; CHECK-NEXT:   // %bb.0:                               // %entry
 ; CHECK-NEXT:       paciasp
 ; CHECK-NOT:        OUTLINED_FUNCTION_
diff --git a/llvm/test/CodeGen/AMDGPU/r600-constant-array-fixup.ll b/llvm/test/CodeGen/AMDGPU/r600-constant-array-fixup.ll
--- a/llvm/test/CodeGen/AMDGPU/r600-constant-array-fixup.ll
+++ b/llvm/test/CodeGen/AMDGPU/r600-constant-array-fixup.ll
@@ -4,13 +4,13 @@
 
 ; CHECK: Relocations [
 ; CHECK: Section (3) .rel.text {
-; CHECK: 0x58 R_AMDGPU_ABS32 arr 0x0
+; CHECK: 0x58 R_AMDGPU_ABS32 .text 0x0
 ; CHECK: }
 ; CHECK: ]
 
 ; CHECK: Symbol {
 ; CHECK: Name: arr (11)
-; CHECK: Value: 0x0
+; CHECK: Value: 0x70
 ; CHECK: Size: 16
 ; CHECK: Binding: Local (0x0)
 ; CHECK: Type: Object (0x1)
diff --git a/llvm/test/CodeGen/ARM/emutls.ll b/llvm/test/CodeGen/ARM/emutls.ll
--- a/llvm/test/CodeGen/ARM/emutls.ll
+++ b/llvm/test/CodeGen/ARM/emutls.ll
@@ -238,6 +238,7 @@
 ; ARM32:      .data{{$}}
 ; ARM32:      .globl __emutls_v.i4
 ; ARM32-LABEL: __emutls_v.i4:
+; ARM32-NEXT:  .L__emutls_v.i4$local:
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 4
 ; ARM32-NEXT: .long 0
@@ -245,6 +246,7 @@
 
 ; ARM32:      .section .rodata,
 ; ARM32-LABEL: __emutls_t.i4:
+; ARM32-NEXT:  .L__emutls_t.i4$local:
 ; ARM32-NEXT: .long 15
 
 ; ARM32-NOT:   __emutls_v.i5:
diff --git a/llvm/test/CodeGen/X86/emutls.ll b/llvm/test/CodeGen/X86/emutls.ll
--- a/llvm/test/CodeGen/X86/emutls.ll
+++ b/llvm/test/CodeGen/X86/emutls.ll
@@ -275,6 +275,7 @@
 
 ; X32       .section .data.rel.local,
 ; X32-LABEL: __emutls_v.i4:
+; X32-NEXT: .L__emutls_v.i4$local:
 ; X32-NEXT: .long 4
 ; X32-NEXT: .long 4
 ; X32-NEXT: .long 0
@@ -282,6 +283,7 @@
 
 ; X32       .section .rodata,
 ; X32-LABEL: __emutls_t.i4:
+; X32-NEXT: .L__emutls_t.i4$local:
 ; X32-NEXT: .long 15
 
 ; X32-NOT:   __emutls_v.i5:
@@ -336,6 +338,7 @@
 
 ; X64       .section .data.rel.local,
 ; X64-LABEL: __emutls_v.i4:
+; X64-NEXT: .L__emutls_v.i4$local:
 ; X64-NEXT: .quad 4
 ; X64-NEXT: .quad 4
 ; X64-NEXT: .quad 0
@@ -343,6 +346,7 @@
 
 ; X64       .section .rodata,
 ; X64-LABEL: __emutls_t.i4:
+; X64-NEXT: .L__emutls_t.i4$local:
 ; X64-NEXT: .long 15
 
 ; X64-NOT:   __emutls_v.i5:
diff --git a/llvm/test/CodeGen/X86/linux-preemption.ll b/llvm/test/CodeGen/X86/linux-preemption.ll
--- a/llvm/test/CodeGen/X86/linux-preemption.ll
+++ b/llvm/test/CodeGen/X86/linux-preemption.ll
@@ -1,9 +1,9 @@
-; RUN: llc -mtriple x86_64-pc-linux \
-; RUN:     -relocation-model=static  < %s | FileCheck --check-prefix=STATIC %s
-; RUN: llc -mtriple x86_64-pc-linux \
-; RUN:     -relocation-model=pic             < %s | FileCheck %s
-; RUN: llc -mtriple x86_64-pc-linux \
-; RUN:     -relocation-model=dynamic-no-pic  < %s | FileCheck %s
+; RUN: llc -mtriple x86_64-pc-linux -relocation-model=static < %s | \
+; RUN:   FileCheck --check-prefixes=COMMON,STATIC %s
+; RUN: llc -mtriple x86_64-pc-linux -relocation-model=pic < %s | \
+; RUN:   FileCheck --check-prefixes=COMMON,CHECK %s
+; RUN: llc -mtriple x86_64-pc-linux -relocation-model=dynamic-no-pic < %s | \
+; RUN:   FileCheck --check-prefixes=COMMON,CHECK %s
 
 ; 32 bits
 
@@ -40,6 +40,8 @@
 define i32* @get_strong_local_global() {
   ret i32* @strong_local_global
 }
+; COMMON:     strong_local_global:
+; COMMON-NEXT .Lstrong_local_global:
 ; CHECK: leaq strong_local_global(%rip), %rax
 ; STATIC: movl $strong_local_global, %eax
 ; CHECK32: leal strong_local_global@GOTOFF(%eax), %eax