diff --git a/clang/lib/CodeGen/CGObjC.cpp b/clang/lib/CodeGen/CGObjC.cpp
--- a/clang/lib/CodeGen/CGObjC.cpp
+++ b/clang/lib/CodeGen/CGObjC.cpp
@@ -23,6 +23,7 @@
 #include "clang/Basic/Diagnostic.h"
 #include "clang/CodeGen/CGFunctionInfo.h"
 #include "llvm/ADT/STLExtras.h"
+#include "llvm/Analysis/ObjCARCUtil.h"
 #include "llvm/BinaryFormat/MachO.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/InlineAsm.h"
@@ -2078,6 +2079,15 @@
   EmitNounwindRuntimeCall(fn, values);
 }
 
+/// Emit a call to "clang.arc.noop.use", which consumes the result of a call
+/// that has operand bundle "clang.arc.rv".
+void CodeGenFunction::EmitARCNoopIntrinsicUse(ArrayRef<llvm::Value *> values) {
+  llvm::Function *&fn = CGM.getObjCEntrypoints().clang_arc_noop_use;
+  if (!fn)
+    fn = CGM.getIntrinsic(llvm::Intrinsic::objc_clang_arc_noop_use);
+  EmitNounwindRuntimeCall(fn, values);
+}
+
 static void setARCRuntimeFunctionLinkage(CodeGenModule &CGM, llvm::Value *RTF) {
   if (auto *F = dyn_cast<llvm::Function>(RTF)) {
     // If the target runtime doesn't naturally support ARC, emit weak
@@ -2304,10 +2314,11 @@
     // with this marker yet, so leave a breadcrumb for the ARC
     // optimizer to pick up.
     } else {
-      const char *markerKey = "clang.arc.retainAutoreleasedReturnValueMarker";
-      if (!CGF.CGM.getModule().getModuleFlag(markerKey)) {
+      const char *retainRVMarkerKey = llvm::objcarc::getRVMarkerModuleFlagStr();
+      if (!CGF.CGM.getModule().getModuleFlag(retainRVMarkerKey)) {
         auto *str = llvm::MDString::get(CGF.getLLVMContext(), assembly);
-        CGF.CGM.getModule().addModuleFlag(llvm::Module::Error, markerKey, str);
+        CGF.CGM.getModule().addModuleFlag(llvm::Module::Error,
+                                          retainRVMarkerKey, str);
       }
     }
   }
@@ -2317,6 +2328,46 @@
     CGF.Builder.CreateCall(marker, None, CGF.getBundlesForFunclet(marker));
 }
 
+static llvm::Value *emitOptimizedARCReturnCall(llvm::Value *value,
+                                               bool IsRetainRV,
+                                               CodeGenFunction &CGF) {
+  emitAutoreleasedReturnValueMarker(CGF);
+
+  // Add operand bundle "clang.arc.rv" to the call instead of emitting retainRV
+  // or claimRV calls in the IR. We currently do this only when the optimization
+  // level isn't -O0 since global-isel, which is currently run at -O0, doesn't
+  // know about the operand bundle.
+
+  // FIXME: Do this when the target isn't aarch64.
+  if (CGF.CGM.getCodeGenOpts().OptimizationLevel > 0 &&
+      CGF.CGM.getTarget().getTriple().isAArch64()) {
+    llvm::Value *bundleArgs[] = {llvm::ConstantInt::get(
+        CGF.Int64Ty, llvm::objcarc::getRVOperandBundleEnum(IsRetainRV))};
+    SmallVector<llvm::OperandBundleDef, 1> bundles;
+    bundles.emplace_back("clang.arc.rv", bundleArgs);
+    auto *oldCall = cast<llvm::CallBase>(value);
+    llvm::CallBase *newCall = llvm::CallBase::Create(oldCall, bundles, oldCall);
+    newCall->copyMetadata(*oldCall);
+    oldCall->replaceAllUsesWith(newCall);
+    oldCall->eraseFromParent();
+    CGF.EmitARCNoopIntrinsicUse(newCall);
+    return newCall;
+  }
+
+  bool isNoTail =
+      CGF.CGM.getTargetCodeGenInfo().markARCOptimizedReturnCallsAsNoTail();
+  llvm::CallInst::TailCallKind tailKind =
+      isNoTail ? llvm::CallInst::TCK_NoTail : llvm::CallInst::TCK_None;
+  ObjCEntrypoints &EPs = CGF.CGM.getObjCEntrypoints();
+  llvm::Function *&EP = IsRetainRV
+                            ? EPs.objc_retainAutoreleasedReturnValue
+                            : EPs.objc_unsafeClaimAutoreleasedReturnValue;
+  llvm::Intrinsic::ID IID =
+      IsRetainRV ? llvm::Intrinsic::objc_retainAutoreleasedReturnValue
+                 : llvm::Intrinsic::objc_unsafeClaimAutoreleasedReturnValue;
+  return emitARCValueOperation(CGF, value, nullptr, EP, IID, tailKind);
+}
+
 /// Retain the given object which is the result of a function call.
 ///   call i8* \@objc_retainAutoreleasedReturnValue(i8* %value)
 ///
@@ -2324,15 +2375,7 @@
 /// call with completely different semantics.
 llvm::Value *
 CodeGenFunction::EmitARCRetainAutoreleasedReturnValue(llvm::Value *value) {
-  emitAutoreleasedReturnValueMarker(*this);
-  llvm::CallInst::TailCallKind tailKind =
-      CGM.getTargetCodeGenInfo().markARCOptimizedReturnCallsAsNoTail()
-          ? llvm::CallInst::TCK_NoTail
-          : llvm::CallInst::TCK_None;
-  return emitARCValueOperation(
-      *this, value, nullptr,
-      CGM.getObjCEntrypoints().objc_retainAutoreleasedReturnValue,
-      llvm::Intrinsic::objc_retainAutoreleasedReturnValue, tailKind);
+  return emitOptimizedARCReturnCall(value, true, *this);
 }
 
 /// Claim a possibly-autoreleased return value at +0.  This is only
@@ -2344,15 +2387,7 @@
 ///   call i8* \@objc_unsafeClaimAutoreleasedReturnValue(i8* %value)
 llvm::Value *
 CodeGenFunction::EmitARCUnsafeClaimAutoreleasedReturnValue(llvm::Value *value) {
-  emitAutoreleasedReturnValueMarker(*this);
-  llvm::CallInst::TailCallKind tailKind =
-      CGM.getTargetCodeGenInfo().markARCOptimizedReturnCallsAsNoTail()
-          ? llvm::CallInst::TCK_NoTail
-          : llvm::CallInst::TCK_None;
-  return emitARCValueOperation(
-      *this, value, nullptr,
-      CGM.getObjCEntrypoints().objc_unsafeClaimAutoreleasedReturnValue,
-      llvm::Intrinsic::objc_unsafeClaimAutoreleasedReturnValue, tailKind);
+  return emitOptimizedARCReturnCall(value, false, *this);
 }
 
 /// Release the given object.
diff --git a/clang/lib/CodeGen/CodeGenFunction.h b/clang/lib/CodeGen/CodeGenFunction.h
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -4202,6 +4202,8 @@
 
   void EmitARCIntrinsicUse(ArrayRef<llvm::Value*> values);
 
+  void EmitARCNoopIntrinsicUse(ArrayRef<llvm::Value *> values);
+
   static Destroyer destroyARCStrongImprecise;
   static Destroyer destroyARCStrongPrecise;
   static Destroyer destroyARCWeak;
diff --git a/clang/lib/CodeGen/CodeGenModule.h b/clang/lib/CodeGen/CodeGenModule.h
--- a/clang/lib/CodeGen/CodeGenModule.h
+++ b/clang/lib/CodeGen/CodeGenModule.h
@@ -210,6 +210,9 @@
 
   /// void clang.arc.use(...);
   llvm::Function *clang_arc_use;
+
+  /// void clang.arc.noop.use(...);
+  llvm::Function *clang_arc_noop_use;
 };
 
 /// This class records statistics on instrumentation based profiling.
diff --git a/clang/test/CodeGenObjC/arc-rv-attr.m b/clang/test/CodeGenObjC/arc-rv-attr.m
new file mode 100644
--- /dev/null
+++ b/clang/test/CodeGenObjC/arc-rv-attr.m
@@ -0,0 +1,177 @@
+// RUN: %clang_cc1 -triple arm64-apple-ios9 -fobjc-runtime=ios-9.0 -fobjc-arc -O -disable-llvm-passes -emit-llvm -o - %s | FileCheck %s -check-prefix=CHECK
+
+@class A;
+
+A *makeA(void);
+
+void test_assign() {
+  __unsafe_unretained id x;
+  x = makeA();
+}
+// CHECK-LABEL: define{{.*}} void @test_assign()
+// CHECK:         [[X:%.*]] = alloca i8*
+// CHECK:         [[T0:%.*]] = call [[A:.*]]* @makeA() [ "clang.arc.rv"(i64 1) ]
+// CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use({{.*}} [[T0]])
+// CHECK-NEXT:    [[T1:%.*]] = bitcast [[A]]* [[T0]] to i8*
+// CHECK-NEXT:    store i8* [[T1]], i8** [[X]]
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    ret void
+
+void test_assign_assign() {
+  __unsafe_unretained id x, y;
+  x = y = makeA();
+}
+// CHECK-LABEL: define{{.*}} void @test_assign_assign()
+// CHECK:         [[X:%.*]] = alloca i8*
+// CHECK:         [[Y:%.*]] = alloca i8*
+// CHECK:         [[T0:%.*]] = call [[A]]* @makeA() [ "clang.arc.rv"(i64 1) ]
+// CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use({{.*}} [[T0]])
+// CHECK-NEXT:    [[T1:%.*]] = bitcast [[A]]* [[T0]] to i8*
+// CHECK-NEXT:    store i8* [[T1]], i8** [[Y]]
+// CHECK-NEXT:    store i8* [[T1]], i8** [[X]]
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    ret void
+
+void test_strong_assign_assign() {
+  __strong id x;
+  __unsafe_unretained id y;
+  x = y = makeA();
+}
+// CHECK-LABEL: define{{.*}} void @test_strong_assign_assign()
+// CHECK:         [[X:%.*]] = alloca i8*
+// CHECK:         [[Y:%.*]] = alloca i8*
+// CHECK:         [[T0:%.*]] = call [[A]]* @makeA() [ "clang.arc.rv"(i64 0) ]
+// CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use({{.*}} [[T0]])
+// CHECK-NEXT:    [[T1:%.*]] = bitcast [[A]]* [[T0]] to i8*
+// CHECK-NEXT:    store i8* [[T1]], i8** [[Y]]
+// CHECK-NEXT:    [[OLD:%.*]] = load i8*, i8** [[X]]
+// CHECK-NEXT:    store i8* [[T1]], i8** [[X]]
+// CHECK-NEXT:    call void @llvm.objc.release(i8* [[OLD]]
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    [[T0:%.*]] = load i8*, i8** [[X]]
+// CHECK-NEXT:    call void @llvm.objc.release(i8* [[T0]])
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    ret void
+
+void test_assign_strong_assign() {
+  __unsafe_unretained id x;
+  __strong id y;
+  x = y = makeA();
+}
+// CHECK-LABEL: define{{.*}} void @test_assign_strong_assign()
+// CHECK:         [[X:%.*]] = alloca i8*
+// CHECK:         [[Y:%.*]] = alloca i8*
+// CHECK:         [[T0:%.*]] = call [[A]]* @makeA() [ "clang.arc.rv"(i64 0) ]
+// CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use({{.*}} [[T0]])
+// CHECK-NEXT:    [[T1:%.*]] = bitcast [[A]]* [[T0]] to i8*
+// CHECK-NEXT:    [[OLD:%.*]] = load i8*, i8** [[Y]]
+// CHECK-NEXT:    store i8* [[T1]], i8** [[Y]]
+// CHECK-NEXT:    call void @llvm.objc.release(i8* [[OLD]]
+// CHECK-NEXT:    store i8* [[T1]], i8** [[X]]
+// CHECK-NEXT:    [[T0:%.*]] = load i8*, i8** [[Y]]
+// CHECK-NEXT:    call void @llvm.objc.release(i8* [[T0]])
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    ret void
+
+void test_init() {
+  __unsafe_unretained id x = makeA();
+}
+// CHECK-LABEL: define{{.*}} void @test_init()
+// CHECK:         [[X:%.*]] = alloca i8*
+// CHECK:         [[T0:%.*]] = call [[A]]* @makeA() [ "clang.arc.rv"(i64 1) ]
+// CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use({{.*}} [[T0]])
+// CHECK-NEXT:    [[T1:%.*]] = bitcast [[A]]* [[T0]] to i8*
+// CHECK-NEXT:    store i8* [[T1]], i8** [[X]]
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    ret void
+
+void test_init_assignment() {
+  __unsafe_unretained id x;
+  __unsafe_unretained id y = x = makeA();
+}
+// CHECK-LABEL: define{{.*}} void @test_init_assignment()
+// CHECK:         [[X:%.*]] = alloca i8*
+// CHECK:         [[Y:%.*]] = alloca i8*
+// CHECK:         [[T0:%.*]] = call [[A]]* @makeA() [ "clang.arc.rv"(i64 1) ]
+// CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use({{.*}} [[T0]])
+// CHECK-NEXT:    [[T1:%.*]] = bitcast [[A]]* [[T0]] to i8*
+// CHECK-NEXT:    store i8* [[T1]], i8** [[X]]
+// CHECK-NEXT:    store i8* [[T1]], i8** [[Y]]
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    ret void
+
+void test_strong_init_assignment() {
+  __unsafe_unretained id x;
+  __strong id y = x = makeA();
+}
+// CHECK-LABEL: define{{.*}} void @test_strong_init_assignment()
+// CHECK:         [[X:%.*]] = alloca i8*
+// CHECK:         [[Y:%.*]] = alloca i8*
+// CHECK:         [[T0:%.*]] = call [[A]]* @makeA() [ "clang.arc.rv"(i64 0) ]
+// CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use({{.*}} [[T0]])
+// CHECK-NEXT:    [[T1:%.*]] = bitcast [[A]]* [[T0]] to i8*
+// CHECK-NEXT:    store i8* [[T1]], i8** [[X]]
+// CHECK-NEXT:    store i8* [[T1]], i8** [[Y]]
+// CHECK-NEXT:    [[T0:%.*]] = load i8*, i8** [[Y]]
+// CHECK-NEXT:    call void @llvm.objc.release(i8* [[T0]])
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    ret void
+
+void test_init_strong_assignment() {
+  __strong id x;
+  __unsafe_unretained id y = x = makeA();
+}
+// CHECK-LABEL: define{{.*}} void @test_init_strong_assignment()
+// CHECK:         [[X:%.*]] = alloca i8*
+// CHECK:         [[Y:%.*]] = alloca i8*
+// CHECK:         [[T0:%.*]] = call [[A]]* @makeA() [ "clang.arc.rv"(i64 0) ]
+// CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use({{.*}} [[T0]])
+// CHECK-NEXT:    [[T1:%.*]] = bitcast [[A]]* [[T0]] to i8*
+// CHECK-NEXT:    [[OLD:%.*]] = load i8*, i8** [[X]]
+// CHECK-NEXT:    store i8* [[T1]], i8** [[X]]
+// CHECK-NEXT:    call void @llvm.objc.release(i8* [[OLD]])
+// CHECK-NEXT:    store i8* [[T1]], i8** [[Y]]
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    [[T0:%.*]] = load i8*, i8** [[X]]
+// CHECK-NEXT:    call void @llvm.objc.release(i8* [[T0]])
+// CHECK-NEXT:    bitcast
+// CHECK-NEXT:    lifetime.end
+// CHECK-NEXT:    ret void
+
+void test_ignored() {
+  makeA();
+}
+// CHECK-LABEL: define{{.*}} void @test_ignored()
+// CHECK:         [[T0:%.*]] = call [[A]]* @makeA() [ "clang.arc.rv"(i64 1) ]
+// CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use({{.*}} [[T0]])
+// CHECK-NEXT:    ret void
+
+void test_cast_to_void() {
+  (void) makeA();
+}
+// CHECK-LABEL: define{{.*}} void @test_cast_to_void()
+// CHECK:         [[T0:%.*]] = call [[A]]* @makeA() [ "clang.arc.rv"(i64 1) ]
+// CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use({{.*}} [[T0]])
+// CHECK-NEXT:    ret void
+
+// This is always at the end of the module.
+
+// CHECK-OPTIMIZED: !llvm.module.flags = !{!0,
+// CHECK-OPTIMIZED: !0 = !{i32 1, !"clang.arc.retainAutoreleasedReturnValueMarker", !"mov{{.*}}marker for objc_retainAutoreleaseReturnValue"}
diff --git a/clang/test/CodeGenObjC/arc-unsafeclaim.m b/clang/test/CodeGenObjC/arc-unsafeclaim.m
--- a/clang/test/CodeGenObjC/arc-unsafeclaim.m
+++ b/clang/test/CodeGenObjC/arc-unsafeclaim.m
@@ -4,11 +4,10 @@
 //   Make sure it works on x86-32.
 // RUN: %clang_cc1 -triple i386-apple-darwin11 -fobjc-runtime=macosx-fragile-10.11 -fobjc-arc -emit-llvm -o - %s | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-UNOPTIMIZED -check-prefix=CHECK-MARKED -check-prefix=CALL
 
-//   Make sure it works on ARM.
+//   Make sure it works on ARM64.
 // RUN: %clang_cc1 -triple arm64-apple-ios9 -fobjc-runtime=ios-9.0 -fobjc-arc -emit-llvm -o - %s | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-UNOPTIMIZED -check-prefix=CHECK-MARKED -check-prefix=CALL
-// RUN: %clang_cc1 -triple arm64-apple-ios9 -fobjc-runtime=ios-9.0 -fobjc-arc -O -disable-llvm-passes -emit-llvm -o - %s | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-OPTIMIZED -check-prefix=CALL
 
-//   Make sure it works on ARM64.
+//   Make sure it works on ARM.
 // RUN: %clang_cc1 -triple armv7-apple-ios9 -fobjc-runtime=ios-9.0 -fobjc-arc -emit-llvm -o - %s | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-UNOPTIMIZED -check-prefix=CHECK-MARKED -check-prefix=CALL
 // RUN: %clang_cc1 -triple armv7-apple-ios9 -fobjc-runtime=ios-9.0 -fobjc-arc -O -disable-llvm-passes -emit-llvm -o - %s | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-OPTIMIZED -check-prefix=CALL
 
diff --git a/llvm/include/llvm/Analysis/ObjCARCUtil.h b/llvm/include/llvm/Analysis/ObjCARCUtil.h
new file mode 100644
--- /dev/null
+++ b/llvm/include/llvm/Analysis/ObjCARCUtil.h
@@ -0,0 +1,48 @@
+//===- ObjCARCUtil.h - ObjC ARC Utility Functions ---------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+/// \file
+/// This file defines ARC utility functions which are used by various parts of
+/// the compiler.
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_ANALYSIS_OBJCARCUTIL_H
+#define LLVM_LIB_ANALYSIS_OBJCARCUTIL_H
+
+#include "llvm/IR/InstrTypes.h"
+#include "llvm/IR/LLVMContext.h"
+
+namespace llvm {
+namespace objcarc {
+
+static inline const char *getRVMarkerModuleFlagStr() {
+  return "clang.arc.retainAutoreleasedReturnValueMarker";
+}
+
+enum RVOperandBundle : unsigned { RVOB_Retain, RVOB_Claim };
+
+static RVOperandBundle getRVOperandBundleEnum(bool IsRetain) {
+  return IsRetain ? RVOB_Retain : RVOB_Claim;
+}
+
+static inline bool hasRVOpBundle(const CallBase *CB, bool IsRetain) {
+  auto B = CB->getOperandBundle(LLVMContext::OB_clang_arc_rv);
+  if (!B.hasValue())
+    return false;
+  return cast<llvm::ConstantInt>(B->Inputs[0])->getZExtValue() ==
+         getRVOperandBundleEnum(IsRetain);
+}
+
+static inline bool hasRVOpBundle(const CallBase *CB) {
+  return CB->getOperandBundle(LLVMContext::OB_clang_arc_rv).hasValue();
+}
+
+} // end namespace objcarc
+} // end namespace llvm
+
+#endif
diff --git a/llvm/include/llvm/IR/InstrTypes.h b/llvm/include/llvm/IR/InstrTypes.h
--- a/llvm/include/llvm/IR/InstrTypes.h
+++ b/llvm/include/llvm/IR/InstrTypes.h
@@ -1214,6 +1214,15 @@
   static CallBase *Create(CallBase *CB, ArrayRef<OperandBundleDef> Bundles,
                           Instruction *InsertPt = nullptr);
 
+  /// Create a clone of \p CB with operand bundle \p OB added.
+  static CallBase *addOperandBundle(CallBase *CB, uint32_t ID,
+                                    OperandBundleDef OB,
+                                    Instruction *InsertPt = nullptr);
+
+  /// Create a clone of \p CB with operand bundle \p ID removed.
+  static CallBase *removeOperandBundle(CallBase *CB, uint32_t ID,
+                                       Instruction *InsertPt = nullptr);
+
   static bool classof(const Instruction *I) {
     return I->getOpcode() == Instruction::Call ||
            I->getOpcode() == Instruction::Invoke ||
diff --git a/llvm/include/llvm/IR/Intrinsics.td b/llvm/include/llvm/IR/Intrinsics.td
--- a/llvm/include/llvm/IR/Intrinsics.td
+++ b/llvm/include/llvm/IR/Intrinsics.td
@@ -446,6 +446,9 @@
                                                          llvm_ptr_ty]>;
 def int_objc_clang_arc_use                  : Intrinsic<[],
                                                         [llvm_vararg_ty]>;
+def int_objc_clang_arc_noop_use : DefaultAttrsIntrinsic<[],
+                                                        [llvm_vararg_ty],
+                                                        [IntrInaccessibleMemOnly]>;
 def int_objc_unsafeClaimAutoreleasedReturnValue : Intrinsic<[llvm_ptr_ty],
                                                             [llvm_ptr_ty]>;
 def int_objc_retainedObject                 : Intrinsic<[llvm_ptr_ty],
diff --git a/llvm/include/llvm/IR/LLVMContext.h b/llvm/include/llvm/IR/LLVMContext.h
--- a/llvm/include/llvm/IR/LLVMContext.h
+++ b/llvm/include/llvm/IR/LLVMContext.h
@@ -93,6 +93,7 @@
     OB_cfguardtarget = 3, // "cfguardtarget"
     OB_preallocated = 4,  // "preallocated"
     OB_gc_live = 5,       // "gc-live"
+    OB_clang_arc_rv = 6,  // "clang.arc.rv"
   };
 
   /// getMDKindID - Return a unique non-zero ID for the specified metadata kind.
diff --git a/llvm/lib/Analysis/ObjCARCInstKind.cpp b/llvm/lib/Analysis/ObjCARCInstKind.cpp
--- a/llvm/lib/Analysis/ObjCARCInstKind.cpp
+++ b/llvm/lib/Analysis/ObjCARCInstKind.cpp
@@ -140,6 +140,7 @@
     return ARCInstKind::User;
   case Intrinsic::objc_sync_exit:
     return ARCInstKind::User;
+  case Intrinsic::objc_clang_arc_noop_use:
   case Intrinsic::objc_arc_annotation_topdown_bbstart:
   case Intrinsic::objc_arc_annotation_topdown_bbend:
   case Intrinsic::objc_arc_annotation_bottomup_bbstart:
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -2782,11 +2782,10 @@
 
   // Deopt bundles are lowered in LowerCallSiteWithDeoptBundle, and we don't
   // have to do anything here to lower funclet bundles.
-  assert(!I.hasOperandBundlesOtherThan({LLVMContext::OB_deopt,
-                                        LLVMContext::OB_gc_transition,
-                                        LLVMContext::OB_gc_live,
-                                        LLVMContext::OB_funclet,
-                                        LLVMContext::OB_cfguardtarget}) &&
+  assert(!I.hasOperandBundlesOtherThan(
+             {LLVMContext::OB_deopt, LLVMContext::OB_gc_transition,
+              LLVMContext::OB_gc_live, LLVMContext::OB_funclet,
+              LLVMContext::OB_cfguardtarget, LLVMContext::OB_clang_arc_rv}) &&
          "Cannot lower invokes with arbitrary operand bundles yet!");
 
   const Value *Callee(I.getCalledOperand());
@@ -7851,7 +7850,8 @@
   // CFGuardTarget bundles are lowered in LowerCallTo.
   assert(!I.hasOperandBundlesOtherThan(
              {LLVMContext::OB_deopt, LLVMContext::OB_funclet,
-              LLVMContext::OB_cfguardtarget, LLVMContext::OB_preallocated}) &&
+              LLVMContext::OB_cfguardtarget, LLVMContext::OB_preallocated,
+              LLVMContext::OB_clang_arc_rv}) &&
          "Cannot lower calls with arbitrary operand bundles!");
 
   SDValue Callee = getValue(I.getCalledOperand());
diff --git a/llvm/lib/IR/AutoUpgrade.cpp b/llvm/lib/IR/AutoUpgrade.cpp
--- a/llvm/lib/IR/AutoUpgrade.cpp
+++ b/llvm/lib/IR/AutoUpgrade.cpp
@@ -14,14 +14,15 @@
 
 #include "llvm/IR/AutoUpgrade.h"
 #include "llvm/ADT/StringSwitch.h"
+#include "llvm/Analysis/ObjCARCUtil.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DIBuilder.h"
 #include "llvm/IR/DebugInfo.h"
 #include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/IRBuilder.h"
-#include "llvm/IR/Instruction.h"
 #include "llvm/IR/InstVisitor.h"
+#include "llvm/IR/Instruction.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/IntrinsicsAArch64.h"
@@ -3996,7 +3997,7 @@
 /// returns true if module is modified.
 static bool UpgradeRetainReleaseMarker(Module &M) {
   bool Changed = false;
-  const char *MarkerKey = "clang.arc.retainAutoreleasedReturnValueMarker";
+  const char *MarkerKey = objcarc::getRVMarkerModuleFlagStr();
   NamedMDNode *ModRetainReleaseMarker = M.getNamedMetadata(MarkerKey);
   if (ModRetainReleaseMarker) {
     MDNode *Op = ModRetainReleaseMarker->getOperand(0);
diff --git a/llvm/lib/IR/Instructions.cpp b/llvm/lib/IR/Instructions.cpp
--- a/llvm/lib/IR/Instructions.cpp
+++ b/llvm/lib/IR/Instructions.cpp
@@ -424,6 +424,35 @@
   return *Current;
 }
 
+CallBase *CallBase::addOperandBundle(CallBase *CB, uint32_t ID,
+                                     OperandBundleDef OB,
+                                     Instruction *InsertPt) {
+  if (CB->getOperandBundle(ID))
+    return CB;
+
+  SmallVector<llvm::OperandBundleDef, 1> Bundles;
+  CB->getOperandBundlesAsDefs(Bundles);
+  Bundles.push_back(OB);
+  return Create(CB, Bundles, InsertPt);
+}
+
+CallBase *CallBase::removeOperandBundle(CallBase *CB, uint32_t ID,
+                                        Instruction *InsertPt) {
+  SmallVector<llvm::OperandBundleDef, 1> Bundles;
+  bool CreateNew = false;
+
+  for (unsigned I = 0, E = CB->getNumOperandBundles(); I != E; ++I) {
+    auto Bundle = CB->getOperandBundleAt(I);
+    if (Bundle.getTagID() == ID) {
+      CreateNew = true;
+      continue;
+    }
+    Bundles.emplace_back(Bundle);
+  }
+
+  return CreateNew ? Create(CB, Bundles, InsertPt) : CB;
+}
+
 //===----------------------------------------------------------------------===//
 //                        CallInst Implementation
 //===----------------------------------------------------------------------===//
diff --git a/llvm/lib/IR/LLVMContext.cpp b/llvm/lib/IR/LLVMContext.cpp
--- a/llvm/lib/IR/LLVMContext.cpp
+++ b/llvm/lib/IR/LLVMContext.cpp
@@ -78,6 +78,11 @@
          "gc-transition operand bundle id drifted!");
   (void)GCLiveEntry;
 
+  auto *ClangARCRVEntry = pImpl->getOrInsertBundleTag("clang.arc.rv");
+  assert(ClangARCRVEntry->second == LLVMContext::OB_clang_arc_rv &&
+         "clang.arc.rv operand bundle id drifted!");
+  (void)ClangARCRVEntry;
+
   SyncScope::ID SingleThreadSSID =
       pImpl->getOrInsertSyncScopeID("singlethread");
   assert(SingleThreadSSID == SyncScope::SingleThread &&
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -29,6 +29,7 @@
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Triple.h"
 #include "llvm/ADT/Twine.h"
+#include "llvm/Analysis/ObjCARCUtil.h"
 #include "llvm/Analysis/VectorUtils.h"
 #include "llvm/CodeGen/CallingConvLower.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
@@ -5647,11 +5648,11 @@
   }
 
   unsigned CallOpc = AArch64ISD::CALL;
-  // Calls marked with "rv_marker" are special. They should be expanded to the
-  // call, directly followed by a special marker sequence. Use the CALL_RVMARKER
-  // to do that.
-  if (CLI.CB && CLI.CB->hasRetAttr("rv_marker")) {
-    assert(!IsTailCall && "tail calls cannot be marked with rv_marker");
+  // Calls with operand bundle "clang.arc.rv" are special. They should be
+  // expanded to the call, directly followed by a special marker sequence. Use
+  // the CALL_RVMARKER to do that.
+  if (CLI.CB && objcarc::hasRVOpBundle(CLI.CB)) {
+    assert(!IsTailCall && "tail calls cannot be marked with clang.arc.rv");
     CallOpc = AArch64ISD::CALL_RVMARKER;
   }
 
diff --git a/llvm/lib/Transforms/ObjCARC/ARCRuntimeEntryPoints.h b/llvm/lib/Transforms/ObjCARC/ARCRuntimeEntryPoints.h
--- a/llvm/lib/Transforms/ObjCARC/ARCRuntimeEntryPoints.h
+++ b/llvm/lib/Transforms/ObjCARC/ARCRuntimeEntryPoints.h
@@ -42,6 +42,7 @@
   Autorelease,
   StoreStrong,
   RetainRV,
+  ClaimRV,
   RetainAutorelease,
   RetainAutoreleaseRV,
 };
@@ -61,6 +62,7 @@
     Autorelease = nullptr;
     StoreStrong = nullptr;
     RetainRV = nullptr;
+    ClaimRV = nullptr;
     RetainAutorelease = nullptr;
     RetainAutoreleaseRV = nullptr;
   }
@@ -85,6 +87,9 @@
     case ARCRuntimeEntryPointKind::RetainRV:
       return getIntrinsicEntryPoint(RetainRV,
                                 Intrinsic::objc_retainAutoreleasedReturnValue);
+    case ARCRuntimeEntryPointKind::ClaimRV:
+      return getIntrinsicEntryPoint(
+          ClaimRV, Intrinsic::objc_unsafeClaimAutoreleasedReturnValue);
     case ARCRuntimeEntryPointKind::RetainAutorelease:
       return getIntrinsicEntryPoint(RetainAutorelease,
                                     Intrinsic::objc_retainAutorelease);
@@ -121,6 +126,9 @@
   /// Declaration for objc_retainAutoreleasedReturnValue().
   Function *RetainRV = nullptr;
 
+  /// Declaration for objc_unsafeClaimAutoreleasedReturnValue().
+  Function *ClaimRV = nullptr;
+
   /// Declaration for objc_retainAutorelease().
   Function *RetainAutorelease = nullptr;
 
diff --git a/llvm/lib/Transforms/ObjCARC/ObjCARC.h b/llvm/lib/Transforms/ObjCARC/ObjCARC.h
--- a/llvm/lib/Transforms/ObjCARC/ObjCARC.h
+++ b/llvm/lib/Transforms/ObjCARC/ObjCARC.h
@@ -22,7 +22,10 @@
 #ifndef LLVM_LIB_TRANSFORMS_OBJCARC_OBJCARC_H
 #define LLVM_LIB_TRANSFORMS_OBJCARC_OBJCARC_H
 
+#include "ARCRuntimeEntryPoints.h"
+#include "llvm/Analysis/EHPersonalities.h"
 #include "llvm/Analysis/ObjCARCAnalysisUtils.h"
+#include "llvm/Analysis/ObjCARCUtil.h"
 #include "llvm/Transforms/Utils/Local.h"
 
 namespace llvm {
@@ -87,6 +90,67 @@
   }
 }
 
+static inline MDString *getRVInstMarker(Module &M) {
+  const char *MarkerKey = getRVMarkerModuleFlagStr();
+  return dyn_cast_or_null<MDString>(M.getModuleFlag(MarkerKey));
+}
+
+/// Create a call instruction with the correct funclet token. This should be
+/// called instead of calling CallInst::Create directly unless the call is
+/// going to be removed from the IR before WinEHPrepare.
+CallInst *createCallInstWithColors(
+    FunctionCallee Func, ArrayRef<Value *> Args, const Twine &NameStr,
+    Instruction *InsertBefore,
+    const DenseMap<BasicBlock *, ColorVector> &BlockColors);
+
+class BundledRetainClaimRVs {
+public:
+  BundledRetainClaimRVs(ARCRuntimeEntryPoints &P, bool ContractPass)
+      : EP(P), ContractPass(ContractPass) {}
+  ~BundledRetainClaimRVs();
+
+  /// Insert a retainRV/claimRV call to the normal destination blocks of invokes
+  /// with operand bundle "clang.arc.rv". If the edge to the normal destination
+  /// block is a critical edge, split it.
+  std::pair<bool, bool> insertAfterInvokes(Function &F, DominatorTree *DT);
+
+  /// Insert a retainRV/claimRV call.
+  CallInst *insertRVCall(Instruction *InsertPt, CallBase *AnnotatedCall);
+
+  /// Insert a retainRV/claimRV call with colors.
+  CallInst *insertRVCallWithColors(
+      Instruction *InsertPt, CallBase *AnnotatedCall,
+      const DenseMap<BasicBlock *, ColorVector> &BlockColors);
+
+  /// See if an instruction is a bundled retainRV/claimRV call.
+  bool contains(const Instruction *I) const {
+    if (auto *CI = dyn_cast<CallInst>(I))
+      return RVCalls.count(CI);
+    return false;
+  }
+
+  /// Remove a retainRV/claimRV call entirely.
+  void eraseInst(CallInst *CI) {
+    auto It = RVCalls.find(CI);
+    if (It != RVCalls.end()) {
+      auto *NewCall = CallBase::removeOperandBundle(
+          It->second, LLVMContext::OB_clang_arc_rv, It->second);
+      NewCall->copyMetadata(*It->second);
+      It->second->replaceAllUsesWith(NewCall);
+      It->second->eraseFromParent();
+      RVCalls.erase(It);
+    }
+    EraseInstruction(CI);
+  }
+
+private:
+  /// A map of inserted retainRV/claimRV calls to annotated calls/invokes.
+  DenseMap<CallInst *, CallBase *> RVCalls;
+
+  ARCRuntimeEntryPoints &EP;
+  bool ContractPass;
+};
+
 } // end namespace objcarc
 } // end namespace llvm
 
diff --git a/llvm/lib/Transforms/ObjCARC/ObjCARC.cpp b/llvm/lib/Transforms/ObjCARC/ObjCARC.cpp
--- a/llvm/lib/Transforms/ObjCARC/ObjCARC.cpp
+++ b/llvm/lib/Transforms/ObjCARC/ObjCARC.cpp
@@ -14,7 +14,12 @@
 
 #include "ObjCARC.h"
 #include "llvm-c/Initialization.h"
+#include "llvm/Analysis/ObjCARCUtil.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/InlineAsm.h"
+#include "llvm/IR/Instructions.h"
 #include "llvm/InitializePasses.h"
+#include "llvm/Transforms/Utils/BasicBlockUtils.h"
 
 namespace llvm {
   class PassRegistry;
@@ -37,3 +42,91 @@
 void LLVMInitializeObjCARCOpts(LLVMPassRegistryRef R) {
   initializeObjCARCOpts(*unwrap(R));
 }
+
+CallInst *llvm::objcarc::createCallInstWithColors(
+    FunctionCallee Func, ArrayRef<Value *> Args, const Twine &NameStr,
+    Instruction *InsertBefore,
+    const DenseMap<BasicBlock *, ColorVector> &BlockColors) {
+  FunctionType *FTy = Func.getFunctionType();
+  Value *Callee = Func.getCallee();
+  SmallVector<OperandBundleDef, 1> OpBundles;
+
+  if (!BlockColors.empty()) {
+    const ColorVector &CV = BlockColors.find(InsertBefore->getParent())->second;
+    assert(CV.size() == 1 && "non-unique color for block!");
+    Instruction *EHPad = CV.front()->getFirstNonPHI();
+    if (EHPad->isEHPad())
+      OpBundles.emplace_back("funclet", EHPad);
+  }
+
+  return CallInst::Create(FTy, Callee, Args, OpBundles, NameStr, InsertBefore);
+}
+
+std::pair<bool, bool>
+BundledRetainClaimRVs::insertAfterInvokes(Function &F, DominatorTree *DT) {
+  bool Changed = false, CFGChanged = false;
+
+  for (BasicBlock &BB : F) {
+    auto *I = dyn_cast<InvokeInst>(BB.getTerminator());
+
+    if (!I)
+      continue;
+
+    if (!objcarc::hasRVOpBundle(I))
+      continue;
+
+    BasicBlock *DestBB = I->getNormalDest();
+
+    if (!DestBB->getSinglePredecessor()) {
+      assert(I->getSuccessor(0) == DestBB &&
+             "the normal dest is expected to be the first successor");
+      DestBB = llvm::SplitCriticalEdge(I, 0, CriticalEdgeSplittingOptions(DT));
+      CFGChanged = true;
+    }
+
+    // We don't have to call insertRVCallWithColors since DestBB is the normal
+    // destination of the invoke.
+    insertRVCall(&*DestBB->getFirstInsertionPt(), I);
+    Changed = true;
+  }
+
+  return std::make_pair(Changed, CFGChanged);
+}
+
+CallInst *BundledRetainClaimRVs::insertRVCall(Instruction *InsertPt,
+                                              CallBase *AnnotatedCall) {
+  DenseMap<BasicBlock *, ColorVector> BlockColors;
+  return insertRVCallWithColors(InsertPt, AnnotatedCall, BlockColors);
+}
+
+CallInst *BundledRetainClaimRVs::insertRVCallWithColors(
+    Instruction *InsertPt, CallBase *AnnotatedCall,
+    const DenseMap<BasicBlock *, ColorVector> &BlockColors) {
+  IRBuilder<> Builder(InsertPt);
+  bool IsRetainRV = objcarc::hasRVOpBundle(AnnotatedCall, true);
+  Function *Func = EP.get(IsRetainRV ? ARCRuntimeEntryPointKind::RetainRV
+                                     : ARCRuntimeEntryPointKind::ClaimRV);
+  Type *ParamTy = Func->getArg(0)->getType();
+  Value *CallArg = Builder.CreateBitCast(AnnotatedCall, ParamTy);
+  auto *Call =
+      createCallInstWithColors(Func, CallArg, "", InsertPt, BlockColors);
+  RVCalls[Call] = AnnotatedCall;
+  return Call;
+}
+
+BundledRetainClaimRVs::~BundledRetainClaimRVs() {
+  if (ContractPass) {
+    // At this point, we know that the annotated calls can't be tail calls as
+    // they are followed by marker instructions and retainRV/claimRV calls. Mark
+    // them as notail, so that the backend knows these calls can't be tail
+    // calls.
+    for (auto P : RVCalls)
+      if (auto *CI = dyn_cast<CallInst>(P.second))
+        CI->setTailCallKind(CallInst::TCK_NoTail);
+  } else {
+    for (auto P : RVCalls)
+      EraseInstruction(P.first);
+  }
+
+  RVCalls.clear();
+}
diff --git a/llvm/lib/Transforms/ObjCARC/ObjCARCContract.cpp b/llvm/lib/Transforms/ObjCARC/ObjCARCContract.cpp
--- a/llvm/lib/Transforms/ObjCARC/ObjCARCContract.cpp
+++ b/llvm/lib/Transforms/ObjCARC/ObjCARCContract.cpp
@@ -32,6 +32,7 @@
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/AliasAnalysis.h"
 #include "llvm/Analysis/EHPersonalities.h"
+#include "llvm/Analysis/ObjCARCUtil.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/InlineAsm.h"
 #include "llvm/IR/InstIterator.h"
@@ -63,13 +64,12 @@
 
 class ObjCARCContract {
   bool Changed;
+  bool CFGChanged;
   AAResults *AA;
   DominatorTree *DT;
   ProvenanceAnalysis PA;
   ARCRuntimeEntryPoints EP;
-
-  /// A flag indicating whether this optimization pass should run.
-  bool Run;
+  BundledRetainClaimRVs *BundledInsts = nullptr;
 
   /// The inline asm string to insert between calls and RetainRV calls to make
   /// the optimization work on targets which need it.
@@ -98,6 +98,7 @@
 public:
   bool init(Module &M);
   bool run(Function &F, AAResults *AA, DominatorTree *DT);
+  bool hasCFGChanged() const { return CFGChanged; }
 };
 
 class ObjCARCContractLegacyPass : public FunctionPass {
@@ -304,32 +305,6 @@
   return Retain;
 }
 
-/// Create a call instruction with the correct funclet token. Should be used
-/// instead of calling CallInst::Create directly.
-static CallInst *
-createCallInst(FunctionType *FTy, Value *Func, ArrayRef<Value *> Args,
-               const Twine &NameStr, Instruction *InsertBefore,
-               const DenseMap<BasicBlock *, ColorVector> &BlockColors) {
-  SmallVector<OperandBundleDef, 1> OpBundles;
-  if (!BlockColors.empty()) {
-    const ColorVector &CV = BlockColors.find(InsertBefore->getParent())->second;
-    assert(CV.size() == 1 && "non-unique color for block!");
-    Instruction *EHPad = CV.front()->getFirstNonPHI();
-    if (EHPad->isEHPad())
-      OpBundles.emplace_back("funclet", EHPad);
-  }
-
-  return CallInst::Create(FTy, Func, Args, OpBundles, NameStr, InsertBefore);
-}
-
-static CallInst *
-createCallInst(FunctionCallee Func, ArrayRef<Value *> Args, const Twine &NameStr,
-               Instruction *InsertBefore,
-               const DenseMap<BasicBlock *, ColorVector> &BlockColors) {
-  return createCallInst(Func.getFunctionType(), Func.getCallee(), Args, NameStr,
-                        InsertBefore, BlockColors);
-}
-
 /// Attempt to merge an objc_release with a store, load, and objc_retain to form
 /// an objc_storeStrong. An objc_storeStrong:
 ///
@@ -411,7 +386,8 @@
   if (Args[1]->getType() != I8X)
     Args[1] = new BitCastInst(Args[1], I8X, "", Store);
   Function *Decl = EP.get(ARCRuntimeEntryPointKind::StoreStrong);
-  CallInst *StoreStrong = createCallInst(Decl, Args, "", Store, BlockColors);
+  CallInst *StoreStrong =
+      objcarc::createCallInstWithColors(Decl, Args, "", Store, BlockColors);
   StoreStrong->setDoesNotThrow();
   StoreStrong->setDebugLoc(Store->getDebugLoc());
 
@@ -456,9 +432,14 @@
   case ARCInstKind::RetainRV:
   case ARCInstKind::ClaimRV: {
     // If we're compiling for a target which needs a special inline-asm
-    // marker to do the return value optimization, insert it now.
+    // marker to do the return value optimization and the retainRV/claimRV call
+    // wasn't bundled with a call, insert the marker now.
     if (!RVInstMarker)
       return false;
+
+    if (BundledInsts->contains(Inst))
+      return false;
+
     BasicBlock::iterator BBI = Inst->getIterator();
     BasicBlock *InstParent = Inst->getParent();
 
@@ -486,7 +467,7 @@
                          RVInstMarker->getString(),
                          /*Constraints=*/"", /*hasSideEffects=*/true);
 
-      createCallInst(IA, None, "", Inst, BlockColors);
+      objcarc::createCallInstWithColors(IA, None, "", Inst, BlockColors);
     }
   decline_rv_optimization:
     return false;
@@ -525,6 +506,12 @@
     Inst->eraseFromParent();
     return true;
   default:
+    if (auto *CI = dyn_cast<CallInst>(Inst))
+      if (CI->getIntrinsicID() == Intrinsic::objc_clang_arc_noop_use) {
+        // Remove calls to @llvm.objc.clang.arc.noop.use(...).
+        Changed = true;
+        CI->eraseFromParent();
+      }
     return true;
   }
 }
@@ -534,16 +521,10 @@
 //===----------------------------------------------------------------------===//
 
 bool ObjCARCContract::init(Module &M) {
-  // If nothing in the Module uses ARC, don't do anything.
-  Run = ModuleHasARC(M);
-  if (!Run)
-    return false;
-
   EP.init(&M);
 
   // Initialize RVInstMarker.
-  const char *MarkerKey = "clang.arc.retainAutoreleasedReturnValueMarker";
-  RVInstMarker = dyn_cast_or_null<MDString>(M.getModuleFlag(MarkerKey));
+  RVInstMarker = getRVInstMarker(M);
 
   return false;
 }
@@ -552,14 +533,16 @@
   if (!EnableARCOpts)
     return false;
 
-  // If nothing in the Module uses ARC, don't do anything.
-  if (!Run)
-    return false;
-
-  Changed = false;
+  Changed = CFGChanged = false;
   AA = A;
   DT = D;
   PA.setAA(A);
+  BundledRetainClaimRVs BRV(EP, true);
+  BundledInsts = &BRV;
+
+  std::pair<bool, bool> R = BundledInsts->insertAfterInvokes(F, DT);
+  Changed |= R.first;
+  CFGChanged |= R.second;
 
   DenseMap<BasicBlock *, ColorVector> BlockColors;
   if (F.hasPersonalityFn() &&
@@ -584,6 +567,13 @@
 
     LLVM_DEBUG(dbgs() << "Visiting: " << *Inst << "\n");
 
+    if (auto *CI = dyn_cast<CallInst>(Inst))
+      if (objcarc::hasRVOpBundle(CI)) {
+        BundledInsts->insertRVCallWithColors(&*I, CI, BlockColors);
+        --I;
+        Changed = true;
+      }
+
     // First try to peephole Inst. If there is nothing further we can do in
     // terms of undoing objc-arc-expand, process the next inst.
     if (tryToPeepholeInstruction(F, Inst, I, TailOkForStoreStrongs,
@@ -733,7 +723,6 @@
 void ObjCARCContractLegacyPass::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.addRequired<AAResultsWrapperPass>();
   AU.addRequired<DominatorTreeWrapperPass>();
-  AU.setPreservesCFG();
 }
 
 Pass *llvm::createObjCARCContractPass() {
@@ -757,9 +746,11 @@
 
   bool Changed = OCAC.run(F, &AM.getResult<AAManager>(F),
                           &AM.getResult<DominatorTreeAnalysis>(F));
+  bool CFGChanged = OCAC.hasCFGChanged();
   if (Changed) {
     PreservedAnalyses PA;
-    PA.preserveSet<CFGAnalyses>();
+    if (!CFGChanged)
+      PA.preserveSet<CFGAnalyses>();
     return PA;
   }
   return PreservedAnalyses::all();
diff --git a/llvm/lib/Transforms/ObjCARC/ObjCARCOpts.cpp b/llvm/lib/Transforms/ObjCARC/ObjCARCOpts.cpp
--- a/llvm/lib/Transforms/ObjCARC/ObjCARCOpts.cpp
+++ b/llvm/lib/Transforms/ObjCARC/ObjCARCOpts.cpp
@@ -41,6 +41,7 @@
 #include "llvm/Analysis/ObjCARCAliasAnalysis.h"
 #include "llvm/Analysis/ObjCARCAnalysisUtils.h"
 #include "llvm/Analysis/ObjCARCInstKind.h"
+#include "llvm/Analysis/ObjCARCUtil.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/CFG.h"
 #include "llvm/IR/Constant.h"
@@ -483,6 +484,7 @@
   /// The main ARC optimization pass.
 class ObjCARCOpt {
   bool Changed;
+  bool CFGChanged;
   ProvenanceAnalysis PA;
 
   /// A cache of references to runtime entry point constants.
@@ -492,8 +494,7 @@
   /// MDKind identifiers.
   ARCMDKindCache MDKindCache;
 
-  /// A flag indicating whether this optimization pass should run.
-  bool Run;
+  BundledRetainClaimRVs *BundledInsts = nullptr;
 
   /// A flag indicating whether the optimization that removes or moves
   /// retain/release pairs should be performed.
@@ -573,6 +574,7 @@
     void init(Module &M);
     bool run(Function &F, AAResults &AA);
     void releaseMemory();
+    bool hasCFGChanged() const { return CFGChanged; }
 };
 
 /// The main ARC optimization pass.
@@ -610,8 +612,6 @@
 void ObjCARCOptLegacyPass::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.addRequired<ObjCARCAAWrapperPass>();
   AU.addRequired<AAResultsWrapperPass>();
-  // ARC optimization doesn't currently split critical edges.
-  AU.setPreservesCFG();
 }
 
 /// Turn objc_retainAutoreleasedReturnValue into objc_retain if the operand is
@@ -640,6 +640,9 @@
     }
   }
 
+  assert(!BundledInsts->contains(RetainRV) &&
+         "a bundled retainRV's argument should be a call");
+
   // Turn it to a plain objc_retain.
   Changed = true;
   ++NumPeeps;
@@ -661,6 +664,9 @@
     Function &F, DenseMap<BasicBlock *, ColorVector> &BlockColors,
     Instruction *Inst, const Value *&Arg, ARCInstKind Class,
     Instruction *AutoreleaseRV, const Value *&AutoreleaseRVArg) {
+  if (BundledInsts->contains(Inst))
+    return false;
+
   // Must be in the same basic block.
   assert(Inst->getParent() == AutoreleaseRV->getParent());
 
@@ -844,6 +850,12 @@
   for (inst_iterator I = inst_begin(&F), E = inst_end(&F); I != E; ) {
     Instruction *Inst = &*I++;
 
+    if (auto *CI = dyn_cast<CallInst>(Inst))
+      if (objcarc::hasRVOpBundle(CI)) {
+        BundledInsts->insertRVCall(&*I, CI);
+        Changed = true;
+      }
+
     ARCInstKind Class = GetBasicARCInstKind(Inst);
 
     // Skip this loop if this instruction isn't itself an ARC intrinsic.
@@ -922,6 +934,11 @@
   // We can delete this call if it takes an inert value.
   SmallPtrSet<Value *, 1> VisitedPhis;
 
+  if (BundledInsts->contains(Inst)) {
+    UsedInThisFunction |= 1 << unsigned(Class);
+    return;
+  }
+
   if (IsNoopOnGlobal(Class))
     if (isInertARCValue(Inst->getOperand(0), VisitedPhis)) {
       if (!Inst->getType()->isVoidTy())
@@ -1542,7 +1559,7 @@
     if (Ptr == Arg)
       continue; // Handled above.
     TopDownPtrState &S = MI->second;
-    if (S.HandlePotentialAlterRefCount(Inst, Ptr, PA, Class))
+    if (S.HandlePotentialAlterRefCount(Inst, Ptr, PA, Class, *BundledInsts))
       continue;
 
     S.HandlePotentialUse(Inst, Ptr, PA, Class);
@@ -2343,7 +2360,7 @@
     ++NumRets;
     LLVM_DEBUG(dbgs() << "Erasing: " << *Retain << "\nErasing: " << *Autorelease
                       << "\n");
-    EraseInstruction(Retain);
+    BundledInsts->eraseInst(Retain);
     EraseInstruction(Autorelease);
   }
 }
@@ -2376,11 +2393,6 @@
   if (!EnableARCOpts)
     return;
 
-  // If nothing in the Module uses ARC, don't do anything.
-  Run = ModuleHasARC(M);
-  if (!Run)
-    return;
-
   // Intuitively, objc_retain and others are nocapture, however in practice
   // they are not, because they return their argument value. And objc_release
   // calls finalizers which can have arbitrary side effects.
@@ -2394,16 +2406,18 @@
   if (!EnableARCOpts)
     return false;
 
-  // If nothing in the Module uses ARC, don't do anything.
-  if (!Run)
-    return false;
-
-  Changed = false;
+  Changed = CFGChanged = false;
+  BundledRetainClaimRVs BRV(EP, false);
+  BundledInsts = &BRV;
 
   LLVM_DEBUG(dbgs() << "<<< ObjCARCOpt: Visiting Function: " << F.getName()
                     << " >>>"
                        "\n");
 
+  std::pair<bool, bool> R = BundledInsts->insertAfterInvokes(F, nullptr);
+  Changed |= R.first;
+  CFGChanged |= R.second;
+
   PA.setAA(&AA);
 
 #ifndef NDEBUG
@@ -2468,9 +2482,11 @@
   OCAO.init(*F.getParent());
 
   bool Changed = OCAO.run(F, AM.getResult<AAManager>(F));
+  bool CFGChanged = OCAO.hasCFGChanged();
   if (Changed) {
     PreservedAnalyses PA;
-    PA.preserveSet<CFGAnalyses>();
+    if (!CFGChanged)
+      PA.preserveSet<CFGAnalyses>();
     return PA;
   }
   return PreservedAnalyses::all();
diff --git a/llvm/lib/Transforms/ObjCARC/PtrState.h b/llvm/lib/Transforms/ObjCARC/PtrState.h
--- a/llvm/lib/Transforms/ObjCARC/PtrState.h
+++ b/llvm/lib/Transforms/ObjCARC/PtrState.h
@@ -31,6 +31,7 @@
 namespace objcarc {
 
 class ARCMDKindCache;
+class BundledRetainClaimRVs;
 class ProvenanceAnalysis;
 
 /// \enum Sequence
@@ -202,7 +203,8 @@
                           ProvenanceAnalysis &PA, ARCInstKind Class);
 
   bool HandlePotentialAlterRefCount(Instruction *Inst, const Value *Ptr,
-                                    ProvenanceAnalysis &PA, ARCInstKind Class);
+                                    ProvenanceAnalysis &PA, ARCInstKind Class,
+                                    const BundledRetainClaimRVs &BundledRVs);
 };
 
 } // end namespace objcarc
diff --git a/llvm/lib/Transforms/ObjCARC/PtrState.cpp b/llvm/lib/Transforms/ObjCARC/PtrState.cpp
--- a/llvm/lib/Transforms/ObjCARC/PtrState.cpp
+++ b/llvm/lib/Transforms/ObjCARC/PtrState.cpp
@@ -11,6 +11,7 @@
 #include "ObjCARC.h"
 #include "llvm/Analysis/ObjCARCAnalysisUtils.h"
 #include "llvm/Analysis/ObjCARCInstKind.h"
+#include "llvm/Analysis/ObjCARCUtil.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
@@ -280,6 +281,12 @@
       InsertAfter = skipDebugIntrinsics(InsertAfter);
 
     InsertReverseInsertPt(&*InsertAfter);
+
+    // Don't insert anything between a call/invoke with operand bundle
+    // "clang.arc.rv" and the retainRV/claimRV call that uses the call result.
+    if (auto *CB = dyn_cast<CallBase>(Inst))
+      if (objcarc::hasRVOpBundle(CB))
+        SetCFGHazardAfflicted(true);
   };
 
   // Check for possible direct uses.
@@ -377,10 +384,9 @@
   llvm_unreachable("Sequence unknown enum value");
 }
 
-bool TopDownPtrState::HandlePotentialAlterRefCount(Instruction *Inst,
-                                                   const Value *Ptr,
-                                                   ProvenanceAnalysis &PA,
-                                                   ARCInstKind Class) {
+bool TopDownPtrState::HandlePotentialAlterRefCount(
+    Instruction *Inst, const Value *Ptr, ProvenanceAnalysis &PA,
+    ARCInstKind Class, const BundledRetainClaimRVs &BundledRVs) {
   // Check for possible releases. Treat clang.arc.use as a releasing instruction
   // to prevent sinking a retain past it.
   if (!CanDecrementRefCount(Inst, Ptr, PA, Class) &&
@@ -396,6 +402,11 @@
     assert(!HasReverseInsertPts());
     InsertReverseInsertPt(Inst);
 
+    // Don't insert anything between a call/invoke with operand bundle
+    // "clang.arc.rv" and the retainRV/claimRV call that uses the call result.
+    if (BundledRVs.contains(Inst))
+      SetCFGHazardAfflicted(true);
+
     // One call can't cause a transition from S_Retain to S_CanRelease
     // and S_CanRelease to S_Use. If we've made the first transition,
     // we're done.
diff --git a/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp b/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp
--- a/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp
+++ b/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp
@@ -247,7 +247,9 @@
           isa<PseudoProbeInst>(&I))
         continue;
 
-      bool IsNoTail = CI->isNoTailCall() || CI->hasOperandBundles();
+      // Special-case operand bundle "clang.arc.rv".
+      bool IsNoTail = CI->isNoTailCall() || CI->hasOperandBundlesOtherThan(
+                                                LLVMContext::OB_clang_arc_rv);
 
       if (!IsNoTail && CI->doesNotAccessMemory()) {
         // A call to a readnone function whose arguments are all things computed
diff --git a/llvm/lib/Transforms/Utils/InlineFunction.cpp b/llvm/lib/Transforms/Utils/InlineFunction.cpp
--- a/llvm/lib/Transforms/Utils/InlineFunction.cpp
+++ b/llvm/lib/Transforms/Utils/InlineFunction.cpp
@@ -27,8 +27,9 @@
 #include "llvm/Analysis/CaptureTracking.h"
 #include "llvm/Analysis/EHPersonalities.h"
 #include "llvm/Analysis/InstructionSimplify.h"
+#include "llvm/Analysis/ObjCARCAnalysisUtils.h"
+#include "llvm/Analysis/ObjCARCUtil.h"
 #include "llvm/Analysis/ProfileSummaryInfo.h"
-#include "llvm/Transforms/Utils/Local.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/Analysis/VectorUtils.h"
 #include "llvm/IR/Argument.h"
@@ -61,6 +62,7 @@
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Transforms/Utils/AssumeBundleBuilder.h"
 #include "llvm/Transforms/Utils/Cloning.h"
+#include "llvm/Transforms/Utils/Local.h"
 #include "llvm/Transforms/Utils/ValueMapper.h"
 #include <algorithm>
 #include <cassert>
@@ -1644,6 +1646,98 @@
   }
 }
 
+/// An operand bundle "clang.arc.rv" on a call indicates the call result is
+/// implicitly consumed by a call to retainRV or claimRV immediately after the
+/// call. This function inlines the retainRV/claimRV calls.
+///
+/// There are three cases to consider:
+///
+/// 1. If there is a call to autoreleasaeRV that takes a pointer to the returned
+///    object in the callee return block, the autoreleaseRV call and the
+///    retainRV/claimRV call in the caller cancel out. If the call in the caller
+///    is a claimRV call, a call to objc_release is emitted.
+///
+/// 2. If there is a call in the callee return block that doesn't have operand
+///    bundle "clang.arc.rv", the operand bundle on the original call is
+///    transferred to the call in the callee.
+///
+/// 3. Otherwise, a call to objc_retain is inserted if the call in the caller is
+///    a retainRV call.
+static void
+inlineRetainOrClaimRVCalls(CallBase &CB,
+                           const SmallVectorImpl<ReturnInst *> &Returns) {
+  Module *Mod = CB.getParent()->getParent()->getParent();
+  bool IsRetainRV = objcarc::hasRVOpBundle(&CB, true), IsClaimRV = !IsRetainRV;
+
+  for (auto *RI : Returns) {
+    Value *RetOpnd = llvm::objcarc::GetRCIdentityRoot(RI->getOperand(0));
+    BasicBlock::reverse_iterator I = ++(RI->getIterator().getReverse());
+    BasicBlock::reverse_iterator EI = RI->getParent()->rend();
+    bool InsertRetainCall = IsRetainRV;
+    IRBuilder<> Builder(RI->getContext());
+
+    // Walk backwards through the basic block looking for either a matching
+    // autoreleaseRV call or an unannotated call.
+    for (; I != EI;) {
+      auto CurI = I++;
+
+      // Ignore casts.
+      if (isa<CastInst>(*CurI))
+        continue;
+
+      if (auto *II = dyn_cast<IntrinsicInst>(&*CurI)) {
+        if (II->getIntrinsicID() == Intrinsic::objc_autoreleaseReturnValue &&
+            II->hasNUses(0) &&
+            llvm::objcarc::GetRCIdentityRoot(II->getOperand(0)) == RetOpnd) {
+          // If we've found a matching authoreleaseRV call:
+          // - If the call is annotated with claimRV, insert a call to
+          //   objc_release and erase the autoreleaseRV call.
+          // - If the call is annotated with retainRV, just erase the
+          //   autoreleaseRV call.
+          if (IsClaimRV) {
+            Builder.SetInsertPoint(II);
+            Function *IFn =
+                Intrinsic::getDeclaration(Mod, Intrinsic::objc_release);
+            Value *BC =
+                Builder.CreateBitCast(RetOpnd, IFn->getArg(0)->getType());
+            Builder.CreateCall(IFn, BC, "");
+          }
+          II->eraseFromParent();
+          InsertRetainCall = false;
+        }
+      } else if (auto *CI = dyn_cast<CallInst>(&*CurI)) {
+        if (llvm::objcarc::GetRCIdentityRoot(CI) == RetOpnd &&
+            !objcarc::hasRVOpBundle(CI)) {
+          // If we've found an unannotated call that defines RetOpnd, add a
+          // "clang.arc.rv" operand bundle.
+          llvm::Value *BundleArgs[] = {llvm::ConstantInt::get(
+              Builder.getInt64Ty(),
+              llvm::objcarc::getRVOperandBundleEnum(IsRetainRV))};
+          OperandBundleDef OB("clang.arc.rv", BundleArgs);
+          auto *NewCall = CallBase::addOperandBundle(
+              CI, LLVMContext::OB_clang_arc_rv, OB, CI);
+          NewCall->copyMetadata(*CI);
+          CI->replaceAllUsesWith(NewCall);
+          CI->eraseFromParent();
+          InsertRetainCall = false;
+        }
+      }
+
+      break;
+    }
+
+    if (InsertRetainCall) {
+      // The call has operand bundle "clang.arc.rv"="retain" and we've failed to
+      // find a matching autoreleaseRV or an annotated call in the callee. Emit
+      // a call to objc_retain.
+      Builder.SetInsertPoint(RI);
+      Function *IFn = Intrinsic::getDeclaration(Mod, Intrinsic::objc_retain);
+      Value *BC = Builder.CreateBitCast(RetOpnd, IFn->getArg(0)->getType());
+      Builder.CreateCall(IFn, BC, "");
+    }
+  }
+}
+
 /// This function inlines the called function into the basic block of the
 /// caller. This returns false if it is not possible to inline this call.
 /// The program is still in a well defined state if this occurs though.
@@ -1681,6 +1775,8 @@
       // ... and "funclet" operand bundles.
       if (Tag == LLVMContext::OB_funclet)
         continue;
+      if (Tag == LLVMContext::OB_clang_arc_rv)
+        continue;
 
       return InlineResult::failure("unsupported operand bundle");
     }
@@ -1847,6 +1943,10 @@
     // Remember the first block that is newly cloned over.
     FirstNewBlock = LastBlock; ++FirstNewBlock;
 
+    // Insert retainRV/clainRV runtime calls.
+    if (objcarc::hasRVOpBundle(&CB))
+      inlineRetainOrClaimRVCalls(CB, Returns);
+
     if (IFI.CallerBFI != nullptr && IFI.CalleeBFI != nullptr)
       // Update the BFI of blocks cloned into the caller.
       updateCallerBFI(OrigBB, VMap, IFI.CallerBFI, IFI.CalleeBFI,
diff --git a/llvm/test/Bitcode/operand-bundles-bc-analyzer.ll b/llvm/test/Bitcode/operand-bundles-bc-analyzer.ll
--- a/llvm/test/Bitcode/operand-bundles-bc-analyzer.ll
+++ b/llvm/test/Bitcode/operand-bundles-bc-analyzer.ll
@@ -9,6 +9,7 @@
 ; CHECK-NEXT:    <OPERAND_BUNDLE_TAG
 ; CHECK-NEXT:    <OPERAND_BUNDLE_TAG
 ; CHECK-NEXT:    <OPERAND_BUNDLE_TAG
+; CHECK-NEXT:    <OPERAND_BUNDLE_TAG
 ; CHECK-NEXT:  </OPERAND_BUNDLE_TAGS_BLOCK
 
 ; CHECK:   <FUNCTION_BLOCK
diff --git a/llvm/test/CodeGen/AArch64/call-rv-marker.ll b/llvm/test/CodeGen/AArch64/call-rv-marker.ll
--- a/llvm/test/CodeGen/AArch64/call-rv-marker.ll
+++ b/llvm/test/CodeGen/AArch64/call-rv-marker.ll
@@ -33,7 +33,7 @@
 ; GISEL-NOT:       mov x29, x29
 ;
 entry:
-  %call = call "rv_marker" i8* @foo1()
+  %call = call i8* @foo1() [ "clang.arc.rv"(i64 0) ]
   ret i8* %call
 }
 
@@ -49,7 +49,7 @@
 entry:
   %tobool.not = icmp eq i32 %c, 0
   %.sink = select i1 %tobool.not, i32 2, i32 1
-  %call1 = call "rv_marker" i8* @foo0(i32 %.sink)
+  %call1 = call i8* @foo0(i32 %.sink) [ "clang.arc.rv"(i64 0) ]
   tail call void @foo2(i8* %call1)
   ret void
 }
@@ -61,7 +61,7 @@
 ; SELDAG-NEXT:   mov x29, x29
 ;
 entry:
-  %call = call "rv_marker" i8* @foo1()
+  %call = call i8* @foo1() [ "clang.arc.rv"(i64 0) ]
   invoke void @objc_object(i8* %call) #5
           to label %invoke.cont unwind label %lpad
 
@@ -87,7 +87,7 @@
   %s = alloca %struct.S, align 1
   %0 = getelementptr inbounds %struct.S, %struct.S* %s, i64 0, i32 0
   call void @llvm.lifetime.start.p0i8(i64 1, i8* nonnull %0) #2
-  %call = invoke "rv_marker" i8* @foo1()
+  %call = invoke i8* @foo1() [ "clang.arc.rv"(i64 0) ]
           to label %invoke.cont unwind label %lpad
 
 invoke.cont:                                      ; preds = %entry
@@ -127,7 +127,7 @@
 ;
 entry:
   %0 = load i8* ()*, i8* ()** @fptr, align 8
-  %call = call "rv_marker" i8* %0()
+  %call = call i8* %0() [ "clang.arc.rv"(i64 0) ]
   tail call void @foo2(i8* %call)
   ret i8* %call
 }
@@ -142,7 +142,7 @@
 ; CHECK-NEXT:   bl  foo
 ; SELDAG-NEXT:  mov x29, x29
 ; GISEL-NOT:    mov x29, x29
-  call "rv_marker" void @foo(i64 %c, i64 %b, i64 %a)
+  call void @foo(i64 %c, i64 %b, i64 %a) [ "clang.arc.rv"(i64 0) ]
   ret void
 }
 
diff --git a/llvm/test/Transforms/DeadArgElim/deadretval.ll b/llvm/test/Transforms/DeadArgElim/deadretval.ll
--- a/llvm/test/Transforms/DeadArgElim/deadretval.ll
+++ b/llvm/test/Transforms/DeadArgElim/deadretval.ll
@@ -1,4 +1,8 @@
-; RUN: opt < %s -deadargelim -S | not grep DEAD
+; RUN: opt < %s -deadargelim -S | FileCheck %s
+
+@g0 = global i8 0, align 8
+
+; CHECK-NOT: DEAD
 
 ; Dead arg only used by dead retval
 define internal i32 @test(i32 %DEADARG) {
@@ -16,3 +20,22 @@
         ret i32 %Y
 }
 
+; The callee function's return type shouldn't be changed if the call result is
+; used.
+
+; CHECK-LABEL: define internal i8* @callee4()
+
+define internal i8* @callee4(i8* %a0) {
+  ret i8* @g0;
+}
+
+declare void @llvm.objc.clang.arc.noop.use(...)
+
+; CHECK-LABEL: define i8* @test4(
+; CHECK: tail call i8* @callee4() [ "clang.arc.rv"(i64 0) ]
+
+define i8* @test4() {
+  %call = tail call i8* @callee4(i8* @g0) [ "clang.arc.rv"(i64 0) ]
+  call void (...) @llvm.objc.clang.arc.noop.use(i8* %call)
+  ret i8* @g0
+}
diff --git a/llvm/test/Transforms/Inline/inline-retainRV-call.ll b/llvm/test/Transforms/Inline/inline-retainRV-call.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/Inline/inline-retainRV-call.ll
@@ -0,0 +1,175 @@
+; RUN: opt < %s -inline -S | FileCheck %s
+
+@g0 = global i8* null, align 8
+declare i8* @foo0()
+
+define i8* @callee0_autoreleaseRV() {
+  %call = call i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+  %1 = tail call i8* @llvm.objc.autoreleaseReturnValue(i8* %call)
+  ret i8* %call
+}
+
+; CHECK-LABEL: define void @test0_autoreleaseRV(
+; CHECK: call i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+
+define void @test0_autoreleaseRV() {
+  %call = call i8* @callee0_autoreleaseRV() [ "clang.arc.rv"(i64 0) ]
+  ret void
+}
+
+; CHECK-LABEL: define void @test0_claimRV_autoreleaseRV(
+; CHECK: %[[CALL:.*]] = call i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+; CHECK: call void @llvm.objc.release(i8* %[[CALL]])
+; CHECK-NEXT: ret void
+
+define void @test0_claimRV_autoreleaseRV() {
+  %call = call i8* @callee0_autoreleaseRV() [ "clang.arc.rv"(i64 1) ]
+  ret void
+}
+
+; CHECK-LABEL: define void @test1_autoreleaseRV(
+; CHECK: invoke i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+
+define void @test1_autoreleaseRV() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  %call = invoke i8* @callee0_autoreleaseRV() [ "clang.arc.rv"(i64 0) ]
+          to label %invoke.cont unwind label %lpad
+
+invoke.cont:
+  ret void
+
+lpad:
+  %0 = landingpad { i8*, i32 }
+          cleanup
+  resume { i8*, i32 } undef
+}
+
+; CHECK-LABEL: define void @test1_claimRV_autoreleaseRV(
+; CHECK: %[[INVOKE:.*]] = invoke i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+; CHECK: call void @llvm.objc.release(i8* %[[INVOKE]])
+; CHECK-NEXT: br
+
+define void @test1_claimRV_autoreleaseRV() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  %call = invoke i8* @callee0_autoreleaseRV() [ "clang.arc.rv"(i64 1) ]
+          to label %invoke.cont unwind label %lpad
+
+invoke.cont:
+  ret void
+
+lpad:
+  %0 = landingpad { i8*, i32 }
+          cleanup
+  resume { i8*, i32 } undef
+}
+
+define i8* @callee1_no_autoreleaseRV() {
+  %call = call i8* @foo0()
+  ret i8* %call
+}
+
+; CHECK-LABEL: define void @test2_no_autoreleaseRV(
+; CHECK: call i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+; CHECK-NEXT: ret void
+
+define void @test2_no_autoreleaseRV() {
+  %call = call i8* @callee1_no_autoreleaseRV() [ "clang.arc.rv"(i64 0) ]
+  ret void
+}
+
+; CHECK-LABEL: define void @test2_claimRV_no_autoreleaseRV(
+; CHECK: call i8* @foo0() [ "clang.arc.rv"(i64 1) ]
+; CHECK-NEXT: ret void
+
+define void @test2_claimRV_no_autoreleaseRV() {
+  %call = call i8* @callee1_no_autoreleaseRV() [ "clang.arc.rv"(i64 1) ]
+  ret void
+}
+
+; CHECK-LABEL: define void @test3_no_autoreleaseRV(
+; CHECK: invoke i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+
+define void @test3_no_autoreleaseRV() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  %call = invoke i8* @callee1_no_autoreleaseRV() [ "clang.arc.rv"(i64 0) ]
+          to label %invoke.cont unwind label %lpad
+
+invoke.cont:
+  ret void
+
+lpad:
+  %0 = landingpad { i8*, i32 }
+          cleanup
+  resume { i8*, i32 } undef
+}
+
+define i8* @callee2_nocall() {
+  %1 = load i8*, i8** @g0, align 8
+  ret i8* %1
+}
+
+; Check that a call to @llvm.objc.retain is inserted if there is no matching
+; autoreleaseRV call or a call.
+
+; CHECK-LABEL: define void @test4_nocall(
+; CHECK: %[[V0:.*]] = load i8*, i8** @g0,
+; CHECK-NEXT: call i8* @llvm.objc.retain(i8* %[[V0]])
+; CHECK-NEXT: ret void
+
+define void @test4_nocall() {
+  %call = call i8* @callee2_nocall() [ "clang.arc.rv"(i64 0) ]
+  ret void
+}
+
+; CHECK-LABEL: define void @test4_claimRV_nocall(
+; CHECK: %[[V0:.*]] = load i8*, i8** @g0,
+; CHECK-NEXT: ret void
+
+define void @test4_claimRV_nocall() {
+  %call = call i8* @callee2_nocall() [ "clang.arc.rv"(i64 1) ]
+  ret void
+}
+
+; Check that a call to @llvm.objc.retain is inserted if call to @foo already has
+; the attribute. I'm not sure this will happen in practice.
+
+define i8* @callee3_marker() {
+  %1 = call i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+  ret i8* %1
+}
+
+; CHECK-LABEL: define void @test5(
+; CHECK: %[[V0:.*]] = call i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+; CHECK-NEXT: call i8* @llvm.objc.retain(i8* %[[V0]])
+; CHECK-NEXT: ret void
+
+define void @test5() {
+  %call = call i8* @callee3_marker() [ "clang.arc.rv"(i64 0) ]
+  ret void
+}
+
+; Don't pair up an autoreleaseRV in the callee and an retainRV in the caller
+; if there is an instruction between the ret instruction and the call to
+; autoreleaseRV that isn't a cast instruction.
+
+define i8* @callee0_autoreleaseRV2() {
+  %call = call i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+  %1 = tail call i8* @llvm.objc.autoreleaseReturnValue(i8* %call)
+  store i8* null, i8** @g0
+  ret i8* %call
+}
+
+; CHECK-LABEL: define void @test6(
+; CHECK: %[[V0:.*]] = call i8* @foo0() [ "clang.arc.rv"(i64 0) ]
+; CHECK: call i8* @llvm.objc.autoreleaseReturnValue(i8* %[[V0]])
+; CHECK: store i8* null, i8** @g0, align 8
+; CHECK: call i8* @llvm.objc.retain(i8* %[[V0]])
+; CHECK-NEXT: ret void
+
+define void @test6() {
+  %call = call i8* @callee0_autoreleaseRV2() [ "clang.arc.rv"(i64 0) ]
+  ret void
+}
+
+declare i8* @llvm.objc.autoreleaseReturnValue(i8*)
+declare i32 @__gxx_personality_v0(...)
diff --git a/llvm/test/Transforms/ObjCARC/contract-marker-funclet.ll b/llvm/test/Transforms/ObjCARC/contract-marker-funclet.ll
--- a/llvm/test/Transforms/ObjCARC/contract-marker-funclet.ll
+++ b/llvm/test/Transforms/ObjCARC/contract-marker-funclet.ll
@@ -10,6 +10,16 @@
 ;   }
 ; }
 
+; CHECK-LABEL: define void @"\01?g@@YAXXZ"()
+; CHECK-LABEL: catch
+; CHECK: call void asm sideeffect "movl{{.*}}%ebp, %ebp{{.*}}", ""() [ "funclet"(token %1) ]
+
+; CHECK-LABEL: catch.1
+; CHECK: call void asm sideeffect "movl{{.*}}%ebp, %ebp{{.*}}", ""() [ "funclet"(token %1) ]
+
+; CHECK-LABEL: invoke.cont
+; CHECK: call void asm sideeffect "movl{{.*}}%ebp, %ebp{{.*}}", ""(){{$}}
+
 define void @"\01?g@@YAXXZ"() personality i8* bitcast (i32 (...)* @__CxxFrameHandler3 to i8*) {
 entry:
   %call = invoke i8* @"\01?f@@YAPAUobjc_object@@XZ"()
@@ -40,23 +50,41 @@
   ret void
 }
 
+; CHECK-LABEL: define dso_local void @"?test_attr_claimRV@@YAXXZ"()
+; CHECK: %[[CALL4:.*]] = notail call i8* @"?noexcept_func@@YAPAUobjc_object@@XZ"() [ "clang.arc.rv"(i64 1) ]
+; CHECK: call i8* @llvm.objc.unsafeClaimAutoreleasedReturnValue(i8* %[[CALL4]])
+
+; CHECK: %[[V1:.*]] = cleanuppad
+; CHECK: %[[CALL:.*]] = notail call i8* @"?noexcept_func@@YAPAUobjc_object@@XZ"() [ "funclet"(token %[[V1]]), "clang.arc.rv"(i64 1) ]
+; CHECK: call i8* @llvm.objc.unsafeClaimAutoreleasedReturnValue(i8* %[[CALL]]) [ "funclet"(token %[[V1]]) ]
+
+define dso_local void @"?test_attr_claimRV@@YAXXZ"() local_unnamed_addr #0 personality i8* bitcast (i32 (...)* @__CxxFrameHandler3 to i8*) {
+entry:
+  invoke void @"?foo@@YAXXZ"()
+          to label %invoke.cont unwind label %ehcleanup
+
+invoke.cont:                                      ; preds = %entry
+  %call.i4 = tail call i8* @"?noexcept_func@@YAPAUobjc_object@@XZ"() #2 [ "clang.arc.rv"(i64 1) ]
+  ret void
+
+ehcleanup:                                        ; preds = %entry
+  %0 = cleanuppad within none []
+  %call.i = call i8* @"?noexcept_func@@YAPAUobjc_object@@XZ"() #2 [ "funclet"(token %0), "clang.arc.rv"(i64 1) ]
+  cleanupret from %0 unwind to caller
+}
+
 declare i8* @"\01?f@@YAPAUobjc_object@@XZ"()
 
 declare i32 @__CxxFrameHandler3(...)
 
+declare void @"?foo@@YAXXZ"()
+declare i8* @"?noexcept_func@@YAPAUobjc_object@@XZ"()
+
 declare dllimport i8* @llvm.objc.retainAutoreleasedReturnValue(i8*)
+declare i8* @llvm.objc.unsafeClaimAutoreleasedReturnValue(i8*)
 
 declare dllimport void @llvm.objc.release(i8*)
 
 !llvm.module.flags = !{!0}
 
 !0 = !{i32 1, !"clang.arc.retainAutoreleasedReturnValueMarker", !"movl\09%ebp, %ebp\09\09// marker for objc_retainAutoreleaseReturnValue"}
-
-; CHECK-LABEL: catch
-; CHECK: call void asm sideeffect "movl{{.*}}%ebp, %ebp{{.*}}", ""() [ "funclet"(token %1) ]
-
-; CHECK-LABEL: catch.1
-; CHECK: call void asm sideeffect "movl{{.*}}%ebp, %ebp{{.*}}", ""() [ "funclet"(token %1) ]
-
-; CHECK-LABEL: invoke.cont
-; CHECK: call void asm sideeffect "movl{{.*}}%ebp, %ebp{{.*}}", ""(){{$}}
diff --git a/llvm/test/Transforms/ObjCARC/contract-rv-attr.ll b/llvm/test/Transforms/ObjCARC/contract-rv-attr.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/ObjCARC/contract-rv-attr.ll
@@ -0,0 +1,63 @@
+; RUN: opt -objc-arc-contract -S < %s | FileCheck %s
+; RUN: opt -passes=objc-arc-contract -S < %s | FileCheck %s
+
+; CHECK-LABEL: define void @test0() {
+; CHECK: %[[CALL:.*]] = notail call i8* @foo() [ "clang.arc.rv"(i64 0) ]
+; CHECK: call i8* @llvm.objc.retainAutoreleasedReturnValue(i8* %[[CALL]])
+
+define void @test0() {
+  %call1 = call i8* @foo() [ "clang.arc.rv"(i64 0) ]
+  ret void
+}
+
+; CHECK-LABEL: define void @test1() {
+; CHECK: %[[CALL:.*]] = notail call i8* @foo() [ "clang.arc.rv"(i64 1) ]
+; CHECK: call i8* @llvm.objc.unsafeClaimAutoreleasedReturnValue(i8* %[[CALL]])
+
+define void @test1() {
+  %call1 = call i8* @foo() [ "clang.arc.rv"(i64 1) ]
+  ret void
+}
+
+; CHECK-LABEL:define i8* @test2(
+; CHECK: %[[CALL1:.*]] = invoke i8* @foo() [ "clang.arc.rv"(i64 0) ]
+
+; CHECK: %[[V0:.*]] = call i8* @llvm.objc.retainAutoreleasedReturnValue(i8* %[[CALL1]])
+; CHECK-NEXT: br
+
+; CHECK: %[[CALL3:.*]] = invoke i8* @foo() [ "clang.arc.rv"(i64 0) ]
+
+; CHECK: %[[V2:.*]] = call i8* @llvm.objc.retainAutoreleasedReturnValue(i8* %[[CALL3]])
+; CHECK-NEXT: br
+
+; CHECK: %[[RETVAL:.*]] = phi i8* [ %[[V0]], {{.*}} ], [ %[[V2]], {{.*}} ]
+; CHECK: ret i8* %[[RETVAL]]
+
+define i8* @test2(i1 zeroext %b) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  br i1 %b, label %if.then, label %if.end
+
+if.then:
+  %call1 = invoke i8* @foo() [ "clang.arc.rv"(i64 0) ]
+          to label %cleanup unwind label %lpad
+
+lpad:
+  %0 = landingpad { i8*, i32 }
+          cleanup
+  resume { i8*, i32 } undef
+
+if.end:
+  %call3 = invoke i8* @foo() [ "clang.arc.rv"(i64 0) ]
+          to label %cleanup unwind label %lpad
+
+cleanup:
+  %retval.0 = phi i8* [ %call1, %if.then ], [ %call3, %if.end ]
+  ret i8* %retval.0
+}
+
+declare i8* @foo()
+declare i32 @__gxx_personality_v0(...)
+
+!llvm.module.flags = !{!0}
+
+!0 = !{i32 1, !"clang.arc.retainAutoreleasedReturnValueMarker", !"mov\09fp, fp\09\09// marker for objc_retainAutoreleaseReturnValue"}
diff --git a/llvm/test/Transforms/ObjCARC/contract.ll b/llvm/test/Transforms/ObjCARC/contract.ll
--- a/llvm/test/Transforms/ObjCARC/contract.ll
+++ b/llvm/test/Transforms/ObjCARC/contract.ll
@@ -227,7 +227,15 @@
   ret void
 }
 
+; CHECK-LABEL: define void @test14(
+; CHECK-NOT: clang.arc.noop.use
+; CHECK: ret void
+define void @test14(i8* %a, i8* %b) {
+  call void (...) @llvm.objc.clang.arc.noop.use(i8* %a, i8* %b) nounwind
+  ret void
+}
 
 declare void @llvm.objc.clang.arc.use(...) nounwind
+declare void @llvm.objc.clang.arc.noop.use(...) nounwind
 
 ; CHECK: attributes [[NUW]] = { nounwind }
diff --git a/llvm/test/Transforms/ObjCARC/intrinsic-use.ll b/llvm/test/Transforms/ObjCARC/intrinsic-use.ll
--- a/llvm/test/Transforms/ObjCARC/intrinsic-use.ll
+++ b/llvm/test/Transforms/ObjCARC/intrinsic-use.ll
@@ -8,8 +8,10 @@
 declare i8* @llvm.objc.autorelease(i8*)
 
 declare void @llvm.objc.clang.arc.use(...)
+declare void @llvm.objc.clang.arc.noop.use(...)
 
 declare void @test0_helper(i8*, i8**)
+declare void @can_release(i8*)
 
 ; Ensure that we honor clang.arc.use as a use and don't miscompile
 ; the reduced test case from <rdar://13195034>.
@@ -108,6 +110,21 @@
   ret void
 }
 
+; ARC optimizer should be able to safely remove the retain/release pair as the
+; call to @llvm.objc.clang.arc.noop.use is a no-op.
+
+; CHECK-LABEL: define void @test_arc_noop_use(
+; CHECK-NEXT:    call void @can_release(i8* %x)
+; CHECK-NEXT:    call void (...) @llvm.objc.clang.arc.noop.use(
+; CHECK-NEXT:    ret void
+
+define void @test_arc_noop_use(i8** %out, i8* %x) {
+  call i8* @llvm.objc.retain(i8* %x)
+  call void @can_release(i8* %x)
+  call void (...) @llvm.objc.clang.arc.noop.use(i8* %x)
+  call void @llvm.objc.release(i8* %x), !clang.imprecise_release !0
+  ret void
+}
 
 !0 = !{}
 
diff --git a/llvm/test/Transforms/ObjCARC/rv.ll b/llvm/test/Transforms/ObjCARC/rv.ll
--- a/llvm/test/Transforms/ObjCARC/rv.ll
+++ b/llvm/test/Transforms/ObjCARC/rv.ll
@@ -452,6 +452,29 @@
   ret i8* %v3
 }
 
+; Remove operand bundle "clang.arc.rv" and the autoreleaseRV call if the call
+; is a tail call.
+
+; CHECK-LABEL: define i8* @test31(
+; CHECK: %[[CALL:.*]] = tail call i8* @returner()
+; CHECK: ret i8* %[[CALL]]
+
+define i8* @test31() {
+  %call = tail call i8* @returner() [ "clang.arc.rv"(i64 0) ]
+  %1 = call i8* @llvm.objc.autoreleaseReturnValue(i8* %call)
+  ret i8* %1
+}
+
+; CHECK-LABEL: define i8* @test32(
+; CHECK: %[[CALL:.*]] = call i8* @returner() [ "clang.arc.rv"(i64 0) ]
+; CHECK: call i8* @llvm.objc.autoreleaseReturnValue(i8* %[[CALL]])
+
+define i8* @test32() {
+  %call = call i8* @returner() [ "clang.arc.rv"(i64 0) ]
+  %1 = call i8* @llvm.objc.autoreleaseReturnValue(i8* %call)
+  ret i8* %1
+}
+
 !0 = !{}
 
 ; CHECK: attributes [[NUW]] = { nounwind }
diff --git a/llvm/test/Transforms/TailCallElim/deopt-bundle.ll b/llvm/test/Transforms/TailCallElim/operand-bundles.ll
rename from llvm/test/Transforms/TailCallElim/deopt-bundle.ll
rename to llvm/test/Transforms/TailCallElim/operand-bundles.ll
--- a/llvm/test/Transforms/TailCallElim/deopt-bundle.ll
+++ b/llvm/test/Transforms/TailCallElim/operand-bundles.ll
@@ -55,3 +55,13 @@
 exit:
   ret void
 }
+
+; CHECK-LABEL: @test_clang_arc_rv(
+; CHECK: tail call i8* @getObj(
+
+declare i8* @getObj()
+
+define i8* @test_clang_arc_rv() {
+  %r = call i8* @getObj() [ "clang.arc.rv"(i64 0) ]
+  ret i8* %r
+}