Index: clang/lib/CodeGen/MicrosoftCXXABI.cpp
===================================================================
--- clang/lib/CodeGen/MicrosoftCXXABI.cpp
+++ clang/lib/CodeGen/MicrosoftCXXABI.cpp
@@ -401,7 +401,7 @@
       ArrayRef<const VarDecl *> CXXThreadLocalInitVars) override;
 
   bool usesThreadWrapperFunction(const VarDecl *VD) const override {
-    return false;
+    return true;
   }
   LValue EmitThreadLocalVarDeclLValue(CodeGenFunction &CGF, const VarDecl *VD,
                                       QualType LValType) override;
@@ -2397,11 +2397,83 @@
   }
 }
 
+static llvm::GlobalValue *getTlsGuardVar(CodeGenModule &CGM) {
+  llvm::Type *VTy = llvm::Type::getInt8Ty(CGM.getLLVMContext());
+  llvm::Constant *TlsGuardConstant =
+      CGM.CreateRuntimeVariable(VTy, "__tls_guard");
+  llvm::GlobalValue *TlsGuard = cast<llvm::GlobalValue>(TlsGuardConstant);
+
+  TlsGuard->setThreadLocal(true);
+
+  return TlsGuard;
+}
+
+static llvm::FunctionCallee getDynTlsOnDemandInitFn(CodeGenModule &CGM) {
+  llvm::FunctionType *FTy =
+      llvm::FunctionType::get(llvm::Type::getVoidTy(CGM.getLLVMContext()), {},
+                              /*isVarArg=*/false);
+  return CGM.CreateRuntimeFunction(
+      FTy, "__dyn_tls_on_demand_init",
+      llvm::AttributeList::get(CGM.getLLVMContext(),
+                               llvm::AttributeList::FunctionIndex,
+                               llvm::Attribute::NoUnwind),
+      /*Local=*/true);
+}
+
+static void emitTlsGuardCheck(CodeGenFunction &CGF, llvm::GlobalValue *TlsGuard,
+                              llvm::BasicBlock *DynInitBB,
+                              llvm::BasicBlock *ContinueBB) {
+  llvm::LoadInst *TlsGuardValue =
+      CGF.Builder.CreateLoad(Address(TlsGuard, CharUnits::One()));
+  llvm::Value *CmpResult =
+      CGF.Builder.CreateICmpEQ(TlsGuardValue, CGF.Builder.getInt8(0));
+  CGF.Builder.CreateCondBr(CmpResult, DynInitBB, ContinueBB);
+}
+
+static void emitDynamicTlsInitialization(CodeGenFunction &CGF,
+                                         llvm::GlobalValue *TlsGuard,
+                                         llvm::BasicBlock *ContinueBB) {
+  CGF.Builder.CreateStore(CGF.Builder.getInt8(1),
+                          Address(TlsGuard, CharUnits::One()));
+
+  llvm::FunctionCallee Initializer = getDynTlsOnDemandInitFn(CGF.CGM);
+  llvm::Function *InitializerFunction =
+      cast<llvm::Function>(Initializer.getCallee());
+  llvm::CallInst *CallVal = CGF.Builder.CreateCall(InitializerFunction);
+  CallVal->setCallingConv(InitializerFunction->getCallingConv());
+
+  CGF.Builder.CreateBr(ContinueBB);
+}
+
 LValue MicrosoftCXXABI::EmitThreadLocalVarDeclLValue(CodeGenFunction &CGF,
                                                      const VarDecl *VD,
                                                      QualType LValType) {
-  CGF.CGM.ErrorUnsupported(VD, "thread wrappers");
-  return LValue();
+  llvm::BasicBlock *DynInitBB =
+      CGF.createBasicBlock("dyntls.dyn_init", CGF.CurFn);
+  llvm::BasicBlock *ContinueBB =
+      CGF.createBasicBlock("dyntls.continue", CGF.CurFn);
+
+  llvm::GlobalValue *TlsGuard = getTlsGuardVar(CGF.CGM);
+
+  emitTlsGuardCheck(CGF, TlsGuard, DynInitBB, ContinueBB);
+  CGF.Builder.SetInsertPoint(DynInitBB);
+  emitDynamicTlsInitialization(CGF, TlsGuard, ContinueBB);
+  CGF.Builder.SetInsertPoint(ContinueBB);
+
+  llvm::Value *V = CGF.CGM.GetAddrOfGlobalVar(VD);
+  llvm::Type *RealVarTy = CGF.getTypes().ConvertTypeForMem(VD->getType());
+
+  unsigned AS = cast<llvm::PointerType>(V->getType())->getAddressSpace();
+  V = CGF.Builder.CreateBitCast(V, RealVarTy->getPointerTo(AS));
+
+  CharUnits Alignment = CGF.getContext().getDeclAlign(VD);
+  Address Addr(V, Alignment);
+
+  LValue LV = VD->getType()->isReferenceType()
+                  ? CGF.EmitLoadOfReferenceLValue(Addr, VD->getType(),
+                                                  AlignmentSource::Decl)
+                  : CGF.MakeAddrLValue(Addr, LValType, AlignmentSource::Decl);
+  return LV;
 }
 
 static ConstantAddress getInitThreadEpochPtr(CodeGenModule &CGM) {
Index: clang/test/CodeGenCXX/ms-thread_local.cpp
===================================================================
--- clang/test/CodeGenCXX/ms-thread_local.cpp
+++ clang/test/CodeGenCXX/ms-thread_local.cpp
@@ -17,10 +17,20 @@
 
 // CHECK-DAG: @"?b@@3UA@@A" = dso_local thread_local global %struct.A zeroinitializer, align 1
 // CHECK-DAG: @"__tls_init$initializer$" = internal constant void ()* @__tls_init, section ".CRT$XDU"
+// CHECK-DAG: @__tls_guard = external dso_local thread_local global i8
 // CHECK-LD-DAG: @"?b@@3UA@@A" = dso_local thread_local(localdynamic) global %struct.A zeroinitializer, align 1
 // CHECK-LD-DAG: @"__tls_init$initializer$" = internal constant void ()* @__tls_init, section ".CRT$XDU"
+// CHECK-LD-DAG: @__tls_guard = external dso_local thread_local global i8
 thread_local A b;
 
+// CHECK-LABEL: declare dso_local void @__dyn_tls_on_demand_init()
+// CHECK-LD-LABEL: declare dso_local void @__dyn_tls_on_demand_init()
+
+// CHECK-LABEL: define dso_local void @"?f@@YA?AUA@@XZ"(%struct.A* noalias sret(%struct.A) align 1 %agg.result)
+// CHECK: call void @__dyn_tls_on_demand_init()
+// CHECK-LD-LABEL: define dso_local void @"?f@@YA?AUA@@XZ"(%struct.A* noalias sret(%struct.A) align 1 %agg.result)
+// CHECK-LD: call void @__dyn_tls_on_demand_init()
+
 // CHECK-LABEL: define internal void @__tls_init()
 // CHECK: call void @"??__Eb@@YAXXZ"
 // CHECK-LD-LABEL: define internal void @__tls_init()