Index: docs/UsersManual.rst
===================================================================
--- docs/UsersManual.rst
+++ docs/UsersManual.rst
@@ -1157,6 +1157,13 @@
    efficient model can be used. The TLS model can be overridden per
    variable using the ``tls_model`` attribute.
 
+.. option:: -femulated-tls
+
+   Select emulated TLS model, which overrides all -ftls-model choices.
+
+   In emulated TLS mode, all access to TLS variables are converted to
+   calls to __emutls_get_address in the runtime library.
+
 .. option:: -mhwdiv=[values]
 
    Select the ARM modes (arm or thumb) that support hardware division
Index: include/clang/Driver/Options.td
===================================================================
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -510,6 +510,9 @@
 def feliminate_unused_debug_symbols : Flag<["-"], "feliminate-unused-debug-symbols">, Group<f_Group>;
 def femit_all_decls : Flag<["-"], "femit-all-decls">, Group<f_Group>, Flags<[CC1Option]>,
   HelpText<"Emit all declarations, even if unused">;
+def femulated_tls : Flag<["-"], "femulated-tls">, Group<f_Group>, Flags<[CC1Option]>,
+  HelpText<"Use emutls functions to access thread_local variables">;
+def fno_emulated_tls : Flag<["-"], "fno-emulated-tls">, Group<f_Group>, Flags<[CC1Option]>;
 def fencoding_EQ : Joined<["-"], "fencoding=">, Group<f_Group>;
 def ferror_limit_EQ : Joined<["-"], "ferror-limit=">, Group<f_Group>, Flags<[CoreOption]>;
 def fexceptions : Flag<["-"], "fexceptions">, Group<f_Group>, Flags<[CC1Option, CoreOption]>,
Index: include/clang/Frontend/CodeGenOptions.def
===================================================================
--- include/clang/Frontend/CodeGenOptions.def
+++ include/clang/Frontend/CodeGenOptions.def
@@ -57,6 +57,7 @@
 CODEGENOPT(EmitGcovArcs      , 1, 0) ///< Emit coverage data files, aka. GCDA.
 CODEGENOPT(EmitGcovNotes     , 1, 0) ///< Emit coverage "notes" files, aka GCNO.
 CODEGENOPT(EmitOpenCLArgMetadata , 1, 0) ///< Emit OpenCL kernel arg metadata.
+CODEGENOPT(EmulatedTLS       , 1, 0) ///< Set when -femulated-tls is enabled.
 /// \brief FP_CONTRACT mode (on/off/fast).
 ENUM_CODEGENOPT(FPContractMode, FPContractModeKind, 2, FPC_On)
 CODEGENOPT(ForbidGuardVariables , 1, 0) ///< Issue errors if C++ guard variables
Index: lib/CodeGen/BackendUtil.cpp
===================================================================
--- lib/CodeGen/BackendUtil.cpp
+++ lib/CodeGen/BackendUtil.cpp
@@ -541,6 +541,7 @@
   Options.FunctionSections = CodeGenOpts.FunctionSections;
   Options.DataSections = CodeGenOpts.DataSections;
   Options.UniqueSectionNames = CodeGenOpts.UniqueSectionNames;
+  Options.EmulatedTLS = CodeGenOpts.EmulatedTLS;
 
   Options.MCOptions.MCRelaxAll = CodeGenOpts.RelaxAll;
   Options.MCOptions.MCSaveTempLabels = CodeGenOpts.SaveTempLabels;
Index: lib/Driver/Tools.cpp
===================================================================
--- lib/Driver/Tools.cpp
+++ lib/Driver/Tools.cpp
@@ -3952,6 +3952,8 @@
   Args.AddLastArg(CmdArgs, options::OPT_fstandalone_debug);
   Args.AddLastArg(CmdArgs, options::OPT_fno_standalone_debug);
   Args.AddLastArg(CmdArgs, options::OPT_fno_operator_names);
+  Args.AddLastArg(CmdArgs, options::OPT_femulated_tls);
+  Args.AddLastArg(CmdArgs, options::OPT_fno_emulated_tls);
   // AltiVec language extensions aren't relevant for assembling.
   if (!isa<PreprocessJobAction>(JA) || Output.getType() != types::TY_PP_Asm)
     Args.AddLastArg(CmdArgs, options::OPT_faltivec);
Index: lib/Frontend/CompilerInvocation.cpp
===================================================================
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -592,6 +592,9 @@
     }
   }
 
+  Opts.EmulatedTLS =
+      Args.hasFlag(OPT_femulated_tls, OPT_fno_emulated_tls, false);
+
   if (Arg *A = Args.getLastArg(OPT_ftlsmodel_EQ)) {
     StringRef Name = A->getValue();
     unsigned Model = llvm::StringSwitch<unsigned>(Name)
Index: test/CodeGen/tls-model.c
===================================================================
--- test/CodeGen/tls-model.c
+++ test/CodeGen/tls-model.c
@@ -3,7 +3,21 @@
 // RUN: %clang_cc1 %s -triple x86_64-pc-linux-gnu -ftls-model=local-dynamic -emit-llvm -o - | FileCheck %s -check-prefix=CHECK-LD
 // RUN: %clang_cc1 %s -triple x86_64-pc-linux-gnu -ftls-model=initial-exec -emit-llvm -o - | FileCheck %s -check-prefix=CHECK-IE
 // RUN: %clang_cc1 %s -triple x86_64-pc-linux-gnu -ftls-model=local-exec -emit-llvm -o - | FileCheck %s -check-prefix=CHECK-LE
+//
+// RUN: %clang %s -target x86_64-pc-linux-gnu -v -femulated-tls -S -emit-llvm -o - 2>&1 | \
+// RUN:     FileCheck %s -check-prefix=EMU -check-prefix=CHECK-GD
+// RUN: %clang %s -target x86_64-pc-linux-gnu -v -fno-emulated-tls -S -emit-llvm -o - 2>&1 | \
+// RUN:     FileCheck %s -check-prefix=NOEMU -check-prefix=CHECK-GD
+// RUN: %clang %s -target x86_64-linux-android -v -S -emit-llvm -o - 2>&1 | \
+// RUN:     FileCheck %s -check-prefix=DEFAULT -check-prefix=CHECK-GD
 
+// EMU: -cc1 {{.*}} -femulated-tls
+// NOEMU: -cc1 {{.*}} -fno-emulated-tls
+// DEFAULT-NOT: -cc1 {{.*}} -femulated-tls
+// DEFAULT-NOT: -cc1 {{.*}} -fno-emulated-tls
+
+int z1 = 0;
+int z2;
 int __thread x;
 int f() {
   static int __thread y;
@@ -11,18 +25,29 @@
 }
 int __thread __attribute__((tls_model("initial-exec"))) z;
 
+// Note that unlike normal C uninitialized global variables,
+// uninitialized TLS variables do NOT have COMMON linkage.
+
+// CHECK-GD: @z1 = global i32 0
 // CHECK-GD: @f.y = internal thread_local global i32 0
+// CHECK-GD: @z2 = common global i32 0
 // CHECK-GD: @x = thread_local global i32 0
 // CHECK-GD: @z = thread_local(initialexec) global i32 0
 
+// CHECK-LD: @z1 = global i32 0
 // CHECK-LD: @f.y = internal thread_local(localdynamic) global i32 0
+// CHECK-LD: @z2 = common global i32 0
 // CHECK-LD: @x = thread_local(localdynamic) global i32 0
 // CHECK-LD: @z = thread_local(initialexec) global i32 0
 
+// CHECK-IE: @z1 = global i32 0
 // CHECK-IE: @f.y = internal thread_local(initialexec) global i32 0
+// CHECK-IE: @z2 = common global i32 0
 // CHECK-IE: @x = thread_local(initialexec) global i32 0
 // CHECK-IE: @z = thread_local(initialexec) global i32 0
 
+// CHECK-LE: @z1 = global i32 0
 // CHECK-LE: @f.y = internal thread_local(localexec) global i32 0
+// CHECK-LE: @z2 = common global i32 0
 // CHECK-LE: @x = thread_local(localexec) global i32 0
 // CHECK-LE: @z = thread_local(initialexec) global i32 0
Index: test/CodeGenCXX/cxx11-thread-local.cpp
===================================================================
--- test/CodeGenCXX/cxx11-thread-local.cpp
+++ test/CodeGenCXX/cxx11-thread-local.cpp
@@ -1,4 +1,9 @@
 // RUN: %clang_cc1 -std=c++11 -emit-llvm %s -o - -triple x86_64-linux-gnu | FileCheck %s
+// RUN: %clang -std=c++11 -v -femulated-tls -S -emit-llvm %s -o - \
+// RUN:     -target x86_64-linux-gnu 2>&1 | FileCheck --check-prefix=CHECK --check-prefix=EMU %s
+
+// Check if the -femulated-tls option is passed to cc1.
+// EMU: -cc1 {{.*}} -femulated-tls
 
 int f();
 int g();