diff --git a/clang/include/clang/AST/Decl.h b/clang/include/clang/AST/Decl.h
index 526e210..2499efb 100644
--- a/clang/include/clang/AST/Decl.h
+++ b/clang/include/clang/AST/Decl.h
@@ -4008,6 +4008,13 @@
   bool doesNotEscape() const { return BlockDeclBits.DoesNotEscape; }
   void setDoesNotEscape(bool B = true) { BlockDeclBits.DoesNotEscape = B; }
 
+  bool canAvoidCopyToHeap() const {
+    return BlockDeclBits.CanAvoidCopyToHeap;
+  }
+  void setCanAvoidCopyToHeap(bool B = true) {
+    BlockDeclBits.CanAvoidCopyToHeap = B;
+  }
+
   bool capturesVariable(const VarDecl *var) const;
 
   void setCaptures(ASTContext &Context, ArrayRef<Capture> Captures,
diff --git a/clang/include/clang/AST/DeclBase.h b/clang/include/clang/AST/DeclBase.h
index 9117f53..4b63e54 100644
--- a/clang/include/clang/AST/DeclBase.h
+++ b/clang/include/clang/AST/DeclBase.h
@@ -1665,6 +1665,11 @@
     /// A bit that indicates this block is passed directly to a function as a
     /// non-escaping parameter.
     uint64_t DoesNotEscape : 1;
+
+    /// A bit that indicates whether it's possible to avoid coying this block to
+    /// the heap when it initializes or is assigned to a local variable with
+    /// automatic storage.
+    uint64_t CanAvoidCopyToHeap : 1;
   };
 
   /// Number of non-inherited bits in BlockDeclBitfields.
diff --git a/clang/lib/AST/Decl.cpp b/clang/lib/AST/Decl.cpp
index 4f49bd7..78501f5 100644
--- a/clang/lib/AST/Decl.cpp
+++ b/clang/lib/AST/Decl.cpp
@@ -4265,6 +4265,7 @@
   setBlockMissingReturnType(true);
   setIsConversionFromLambda(false);
   setDoesNotEscape(false);
+  setCanAvoidCopyToHeap(false);
 }
 
 void BlockDecl::setParams(ArrayRef<ParmVarDecl *> NewParamInfo) {
diff --git a/clang/lib/CodeGen/CGObjC.cpp b/clang/lib/CodeGen/CGObjC.cpp
index fba1a53..7063517 100644
--- a/clang/lib/CodeGen/CGObjC.cpp
+++ b/clang/lib/CodeGen/CGObjC.cpp
@@ -2871,6 +2871,7 @@
   Result visit(const Expr *e);
   Result visitCastExpr(const CastExpr *e);
   Result visitPseudoObjectExpr(const PseudoObjectExpr *e);
+  Result visitBlockExpr(const BlockExpr *e);
   Result visitBinaryOperator(const BinaryOperator *e);
   Result visitBinAssign(const BinaryOperator *e);
   Result visitBinAssignUnsafeUnretained(const BinaryOperator *e);
@@ -2947,6 +2948,12 @@
 }
 
 template <typename Impl, typename Result>
+Result ARCExprEmitter<Impl, Result>::visitBlockExpr(const BlockExpr *e) {
+  // The default implementation just forwards the expression to visitExpr.
+  return asImpl().visitExpr(e);
+}
+
+template <typename Impl, typename Result>
 Result ARCExprEmitter<Impl,Result>::visitCastExpr(const CastExpr *e) {
   switch (e->getCastKind()) {
 
@@ -3089,7 +3096,8 @@
   // Look through pseudo-object expressions.
   } else if (const PseudoObjectExpr *pseudo = dyn_cast<PseudoObjectExpr>(e)) {
     return asImpl().visitPseudoObjectExpr(pseudo);
-  }
+  } else if (auto *be = dyn_cast<BlockExpr>(e))
+    return asImpl().visitBlockExpr(be);
 
   return asImpl().visitExpr(e);
 }
@@ -3124,6 +3132,15 @@
     return TryEmitResult(result, true);
   }
 
+  TryEmitResult visitBlockExpr(const BlockExpr *e) {
+    TryEmitResult result = visitExpr(e);
+    // Avoid the block-retain if this is a block literal that doesn't need to be
+    // copied to the heap.
+    if (e->getBlockDecl()->canAvoidCopyToHeap())
+      result.setInt(true);
+    return result;
+  }
+
   /// Block extends are net +0.  Naively, we could just recurse on
   /// the subexpression, but actually we need to ensure that the
   /// value is copied as a block, so there's a little filter here.
diff --git a/clang/lib/Sema/SemaDecl.cpp b/clang/lib/Sema/SemaDecl.cpp
index cbef0e2..2078caa0 100644
--- a/clang/lib/Sema/SemaDecl.cpp
+++ b/clang/lib/Sema/SemaDecl.cpp
@@ -11257,6 +11257,11 @@
           << Culprit->getSourceRange();
       }
     }
+
+    if (auto *E = dyn_cast<ExprWithCleanups>(Init))
+      if (auto *BE = dyn_cast<BlockExpr>(E->getSubExpr()->IgnoreParens()))
+        if (VDecl->hasLocalStorage())
+          BE->getBlockDecl()->setCanAvoidCopyToHeap();
   } else if (VDecl->isStaticDataMember() && !VDecl->isInline() &&
              VDecl->getLexicalDeclContext()->isRecord()) {
     // This is an in-class initialization for a static data member, e.g.,
diff --git a/clang/lib/Sema/SemaExpr.cpp b/clang/lib/Sema/SemaExpr.cpp
index e91115a..266120d 100644
--- a/clang/lib/Sema/SemaExpr.cpp
+++ b/clang/lib/Sema/SemaExpr.cpp
@@ -12443,6 +12443,25 @@
     if (!ResultTy.isNull()) {
       DiagnoseSelfAssignment(*this, LHS.get(), RHS.get(), OpLoc, true);
       DiagnoseSelfMove(LHS.get(), RHS.get(), OpLoc);
+
+      // Avoid copying a block to the heap if the block is assigned to a local
+      // auto variable that is declared in the same scope as the block. This
+      // optimization is unsafe if the local variable is declared in an outer
+      // scope. For example:
+      //
+      // BlockTy b;
+      // {
+      //   b = ^{...};
+      // }
+      // // It is unsafe to invoke the block here if it wasn't copied to the
+      // // heap.
+      // b();
+
+      if (auto *BE = dyn_cast<BlockExpr>(RHS.get()->IgnoreParens()))
+        if (auto *DRE = dyn_cast<DeclRefExpr>(LHS.get()->IgnoreParens()))
+          if (auto *VD = dyn_cast<VarDecl>(DRE->getDecl()))
+            if (VD->hasLocalStorage() && getCurScope()->isDeclScope(VD))
+              BE->getBlockDecl()->setCanAvoidCopyToHeap();
     }
     RecordModifiableNonNullParam(*this, LHS.get());
     break;
diff --git a/clang/lib/Serialization/ASTReaderDecl.cpp b/clang/lib/Serialization/ASTReaderDecl.cpp
index 6d02f4d..fb56170 100644
--- a/clang/lib/Serialization/ASTReaderDecl.cpp
+++ b/clang/lib/Serialization/ASTReaderDecl.cpp
@@ -1479,6 +1479,7 @@
   BD->setBlockMissingReturnType(Record.readInt());
   BD->setIsConversionFromLambda(Record.readInt());
   BD->setDoesNotEscape(Record.readInt());
+  BD->setCanAvoidCopyToHeap(Record.readInt());
 
   bool capturesCXXThis = Record.readInt();
   unsigned numCaptures = Record.readInt();
diff --git a/clang/lib/Serialization/ASTWriterDecl.cpp b/clang/lib/Serialization/ASTWriterDecl.cpp
index ff0c56b..6de1320 100644
--- a/clang/lib/Serialization/ASTWriterDecl.cpp
+++ b/clang/lib/Serialization/ASTWriterDecl.cpp
@@ -1110,6 +1110,7 @@
   Record.push_back(D->blockMissingReturnType());
   Record.push_back(D->isConversionFromLambda());
   Record.push_back(D->doesNotEscape());
+  Record.push_back(D->canAvoidCopyToHeap());
   Record.push_back(D->capturesCXXThis());
   Record.push_back(D->getNumCaptures());
   for (const auto &capture : D->captures()) {
diff --git a/clang/test/CodeGenObjC/arc-block-copy-escape.m b/clang/test/CodeGenObjC/arc-block-copy-escape.m
index 3823a95..9e409ce 100644
--- a/clang/test/CodeGenObjC/arc-block-copy-escape.m
+++ b/clang/test/CodeGenObjC/arc-block-copy-escape.m
@@ -9,14 +9,14 @@
 void test0(int i) {
   block_t block = ^{ use_int(i); };
   // CHECK-LABEL:   define {{.*}}void @test0(
-  // CHECK:     call {{.*}}i8* @llvm.objc.retainBlock(i8* {{%.*}}) [[NUW:#[0-9]+]], !clang.arc.copy_on_escape
+  // CHECK-NOT: @llvm.objc.retainBlock(
   // CHECK:     ret void
 }
 
 void test1(int i) {
   id block = ^{ use_int(i); };
   // CHECK-LABEL:   define {{.*}}void @test1(
-  // CHECK:     call {{.*}}i8* @llvm.objc.retainBlock(i8* {{%.*}}) [[NUW]]
+  // CHECK:     call {{.*}}i8* @llvm.objc.retainBlock(i8* {{%.*}}) [[NUW:#[0-9]+]]
   // CHECK-NOT: !clang.arc.copy_on_escape
   // CHECK:     ret void
 }
diff --git a/clang/test/CodeGenObjC/arc-blocks.m b/clang/test/CodeGenObjC/arc-blocks.m
index 49da992..47e2723 100644
--- a/clang/test/CodeGenObjC/arc-blocks.m
+++ b/clang/test/CodeGenObjC/arc-blocks.m
@@ -338,20 +338,19 @@
   __block void (^block)(void) = ^{ block(); };
   // CHECK-LABEL:    define void @test10a()
   // CHECK:      [[BYREF:%.*]] = alloca [[BYREF_T:%.*]],
+  // CHECK:      [[BLOCK1:%.*]] = alloca <{ i8*, i32, i32, i8*, %[[STRUCT_BLOCK_DESCRIPTOR]]*, i8* }>, align 8
 
   // Zero-initialization before running the initializer.
   // CHECK:      [[T0:%.*]] = getelementptr inbounds [[BYREF_T]], [[BYREF_T]]* [[BYREF]], i32 0, i32 6
   // CHECK-NEXT: store void ()* null, void ()** [[T0]], align 8
 
   // Run the initializer as an assignment.
-  // CHECK:      [[T0:%.*]] = bitcast void ()* {{%.*}} to i8*
-  // CHECK-NEXT: [[T1:%.*]] = call i8* @llvm.objc.retainBlock(i8* [[T0]])
-  // CHECK-NEXT: [[T2:%.*]] = bitcast i8* [[T1]] to void ()*
+  // CHECK:      [[T2:%.*]] = bitcast <{ i8*, i32, i32, i8*, %[[STRUCT_BLOCK_DESCRIPTOR]]*, i8* }>* [[BLOCK1]] to void ()*
   // CHECK-NEXT: [[T3:%.*]] = getelementptr inbounds [[BYREF_T]], [[BYREF_T]]* [[BYREF]], i32 0, i32 1
   // CHECK-NEXT: [[T4:%.*]] = load [[BYREF_T]]*, [[BYREF_T]]** [[T3]]
   // CHECK-NEXT: [[T5:%.*]] = getelementptr inbounds [[BYREF_T]], [[BYREF_T]]* [[T4]], i32 0, i32 6
   // CHECK-NEXT: [[T6:%.*]] = load void ()*, void ()** [[T5]], align 8
-  // CHECK-NEXT: store void ()* {{%.*}}, void ()** [[T5]], align 8
+  // CHECK-NEXT: store void ()* [[T2]], void ()** [[T5]], align 8
   // CHECK-NEXT: [[T7:%.*]] = bitcast void ()* [[T6]] to i8*
   // CHECK-NEXT: call void @llvm.objc.release(i8* [[T7]])
 
@@ -401,6 +400,7 @@
 
   // CHECK-LABEL:    define void @test10b()
   // CHECK:      [[BYREF:%.*]] = alloca [[BYREF_T:%.*]],
+  // CHECK:      [[BLOCK3:%.*]] = alloca <{ i8*, i32, i32, i8*, %[[STRUCT_BLOCK_DESCRIPTOR]]*, i8* }>, align 8
 
   // Zero-initialize.
   // CHECK:      [[T0:%.*]] = getelementptr inbounds [[BYREF_T]], [[BYREF_T]]* [[BYREF]], i32 0, i32 6
@@ -409,14 +409,12 @@
   // CHECK-NEXT: [[SLOT:%.*]] = getelementptr inbounds [[BYREF_T]], [[BYREF_T]]* [[BYREF]], i32 0, i32 6
 
   // The assignment.
-  // CHECK:      [[T0:%.*]] = bitcast void ()* {{%.*}} to i8*
-  // CHECK-NEXT: [[T1:%.*]] = call i8* @llvm.objc.retainBlock(i8* [[T0]])
-  // CHECK-NEXT: [[T2:%.*]] = bitcast i8* [[T1]] to void ()*
+  // CHECK:      [[T2:%.*]] = bitcast <{ i8*, i32, i32, i8*, %[[STRUCT_BLOCK_DESCRIPTOR]]*, i8* }>* [[BLOCK3]] to void ()*
   // CHECK-NEXT: [[T3:%.*]] = getelementptr inbounds [[BYREF_T]], [[BYREF_T]]* [[BYREF]], i32 0, i32 1
   // CHECK-NEXT: [[T4:%.*]] = load [[BYREF_T]]*, [[BYREF_T]]** [[T3]]
   // CHECK-NEXT: [[T5:%.*]] = getelementptr inbounds [[BYREF_T]], [[BYREF_T]]* [[T4]], i32 0, i32 6
   // CHECK-NEXT: [[T6:%.*]] = load void ()*, void ()** [[T5]], align 8
-  // CHECK-NEXT: store void ()* {{%.*}}, void ()** [[T5]], align 8
+  // CHECK-NEXT: store void ()* [[T2]], void ()** [[T5]], align 8
   // CHECK-NEXT: [[T7:%.*]] = bitcast void ()* [[T6]] to i8*
   // CHECK-NEXT: call void @llvm.objc.release(i8* [[T7]])
 
diff --git a/clang/test/CodeGenObjCXX/arc-blocks.mm b/clang/test/CodeGenObjCXX/arc-blocks.mm
index ec0c124..24697cf 100644
--- a/clang/test/CodeGenObjCXX/arc-blocks.mm
+++ b/clang/test/CodeGenObjCXX/arc-blocks.mm
@@ -201,3 +201,123 @@
   ^{ (void)t0; (void)t1; (void)t2; (void)t3; (void)t4; (void)t5; };
 }
 }
+
+// Test that calls to @llvm.objc.retainBlock aren't emitted in some cases.
+
+namespace test_block_retain {
+  typedef void (^BlockTy)();
+
+  void foo1(id);
+
+// CHECK-LABEL: define void @_ZN17test_block_retain14initializationEP11objc_object(
+// CHECK-NOT: @llvm.objc.retainBlock(
+  void initialization(id a) {
+    BlockTy b0 = ^{ foo1(a); };
+    BlockTy b1 = (^{ foo1(a); });
+    b0();
+    b1();
+  }
+
+// CHECK-LABEL: define void @_ZN17test_block_retain20initializationStaticEP11objc_object(
+// CHECK: @llvm.objc.retainBlock(
+  void initializationStatic(id a) {
+    static BlockTy b0 = ^{ foo1(a); };
+    b0();
+  }
+
+// CHECK-LABEL: define void @_ZN17test_block_retain15initialization2EP11objc_object
+// CHECK: %[[B0:.*]] = alloca void ()*, align 8
+// CHECK: %[[B1:.*]] = alloca void ()*, align 8
+// CHECK: load void ()*, void ()** %[[B0]], align 8
+// CHECK-NOT: @llvm.objc.retainBlock
+// CHECK: %[[V9:.*]] = load void ()*, void ()** %[[B0]], align 8
+// CHECK: %[[V10:.*]] = bitcast void ()* %[[V9]] to i8*
+// CHECK: %[[V11:.*]] = call i8* @llvm.objc.retainBlock(i8* %[[V10]])
+// CHECK: %[[V12:.*]] = bitcast i8* %[[V11]] to void ()*
+// CHECK: store void ()* %[[V12]], void ()** %[[B1]], align 8
+  void initialization2(id a) {
+    BlockTy b0 = ^{ foo1(a); };
+    b0();
+    BlockTy b1 = b0; // can't optimize this yet.
+    b1();
+  }
+
+// CHECK-LABEL: define void @_ZN17test_block_retain10assignmentEP11objc_object(
+// CHECK-NOT: @llvm.objc.retainBlock(
+  void assignment(id a) {
+    BlockTy b0;
+    (b0) = ^{ foo1(a); };
+    b0();
+    b0 = (^{ foo1(a); });
+    b0();
+  }
+
+// CHECK-LABEL: define void @_ZN17test_block_retain16assignmentStaticEP11objc_object(
+// CHECK: @llvm.objc.retainBlock(
+  void assignmentStatic(id a) {
+    static BlockTy b0;
+    b0 = ^{ foo1(a); };
+    b0();
+  }
+
+// CHECK-LABEL: define void @_ZN17test_block_retain21assignmentConditionalEP11objc_objectb(
+// CHECK: @llvm.objc.retainBlock(
+  void assignmentConditional(id a, bool c) {
+    BlockTy b0;
+    if (c)
+      // can't optimize this since 'b0' is declared in the outer scope.
+      b0 = ^{ foo1(a); };
+    b0();
+  }
+
+// CHECK-LABEL: define void @_ZN17test_block_retain11assignment2EP11objc_object(
+// CHECK: %[[B0:.*]] = alloca void ()*, align 8
+// CHECK: %[[B1:.*]] = alloca void ()*, align 8
+// CHECK-NOT: @llvm.objc.retainBlock
+// CHECK: store void ()* null, void ()** %[[B1]], align 8
+// CHECK: %[[V9:.*]] = load void ()*, void ()** %[[B0]], align 8
+// CHECK: %[[V10:.*]] = bitcast void ()* %[[V9]] to i8*
+// CHECK: %[[V11:.*]] = call i8* @llvm.objc.retainBlock(i8* %[[V10]]
+// CHECK: %[[V12:.*]] = bitcast i8* %[[V11]] to void ()*
+// CHECK: store void ()* %[[V12]], void ()** %[[B1]], align 8
+  void assignment2(id a) {
+    BlockTy b0 = ^{ foo1(a); };
+    b0();
+    BlockTy b1;
+    b1 = b0; // can't optimize this yet.
+    b1();
+  }
+
+// We cannot remove the call to @llvm.objc.retainBlock if the variable is of type id.
+
+// CHECK: define void @_ZN17test_block_retain21initializationObjCPtrEP11objc_object(
+// CHECK: alloca i8*, align 8
+// CHECK: %[[B0:.*]] = alloca i8*, align 8
+// CHECK: %[[BLOCK:.*]] = alloca <{ i8*, i32, i32, i8*, %[[STRUCT_BLOCK_DESCRIPTOR]]*, i8* }>, align 8
+// CHECK: %[[V3:.*]] = bitcast <{ i8*, i32, i32, i8*, %[[STRUCT_BLOCK_DESCRIPTOR]]*, i8* }>* %[[BLOCK]] to void ()*
+// CHECK: %[[V4:.*]] = bitcast void ()* %[[V3]] to i8*
+// CHECK: %[[V5:.*]] = call i8* @llvm.objc.retainBlock(i8* %[[V4]])
+// CHECK: %[[V6:.*]] = bitcast i8* %[[V5]] to void ()*
+// CHECK: %[[V7:.*]] = bitcast void ()* %[[V6]] to i8*
+// CHECK: store i8* %[[V7]], i8** %[[B0]], align 8
+  void initializationObjCPtr(id a) {
+    id b0 = ^{ foo1(a); };
+    ((BlockTy)b0)();
+  }
+
+// CHECK: define void @_ZN17test_block_retain17assignmentObjCPtrEP11objc_object(
+// CHECK: %[[B0:.*]] = alloca void ()*, align 8
+// CHECK: %[[B1:.*]] = alloca i8*, align 8
+// CHECK: %[[V4:.*]] = load void ()*, void ()** %[[B0]], align 8
+// CHECK: %[[V5:.*]] = bitcast void ()* %[[V4]] to i8*
+// CHECK: %[[V6:.*]] = call i8* @llvm.objc.retainBlock(i8* %[[V5]])
+// CHECK: %[[V7:.*]] = bitcast i8* %[[V6]] to void ()*
+// CHECK: %[[V8:.*]] = bitcast void ()* %[[V7]] to i8*
+// CHECK: store i8* %[[V8]], i8** %[[B1]], align 8
+  void assignmentObjCPtr(id a) {
+    BlockTy b0 = ^{ foo1(a); };
+    id b1;
+    b1 = b0;
+    ((BlockTy)b1)();
+  }
+}
diff --git a/clang/test/PCH/arc-blocks.mm b/clang/test/PCH/arc-blocks.mm
new file mode 100644
index 0000000..74b7e47
--- /dev/null
+++ b/clang/test/PCH/arc-blocks.mm
@@ -0,0 +1,49 @@
+// RUN: %clang_cc1 -fobjc-arc -fblocks -std=c++1y -emit-pch %s -o %t
+// RUN: %clang_cc1 -fobjc-arc -fblocks -std=c++1y -include-pch %t -emit-llvm -o - %s | FileCheck %s
+
+#ifndef HEADER_INCLUDED
+#define HEADER_INCLUDED
+
+namespace test_block_retain {
+  typedef void (^BlockTy)();
+  void foo1(id);
+
+  inline void initialization(id a) {
+    // Call to @llvm.objc.retainBlock isn't needed.
+    BlockTy b0 = ^{ foo1(a); };
+    b0();
+  }
+
+  inline void assignmentConditional(id a, bool c) {
+    BlockTy b0;
+    if (c)
+      // @llvm.objc.retainBlock is called since 'b0' is declared in the outer scope.
+      b0 = ^{ foo1(a); };
+    b0();
+  }
+}
+
+#else
+
+// CHECK: %[[STRUCT_BLOCK_DESCRIPTOR:.*]] = type { i64, i64 }
+
+namespace test_block_retain {
+// CHECK-LABEL: define linkonce_odr void @_ZN17test_block_retain14initializationEP11objc_object(
+// CHECK-NOT: call i8* @llvm.objc.retainBlock(
+
+  void test_initialization(id a) {
+    initialization(a);
+  }
+
+// CHECK-LABEL: define void @_ZN17test_block_retain26test_assignmentConditionalEP11objc_objectb(
+// CHECK: %[[BLOCK:.*]] = alloca <{ i8*, i32, i32, i8*, %[[STRUCT_BLOCK_DESCRIPTOR]]*, i8* }>, align 8
+// CHECK: %[[V4:.*]] = bitcast <{ i8*, i32, i32, i8*, %[[STRUCT_BLOCK_DESCRIPTOR]]*, i8* }>* %[[BLOCK]] to void ()*
+// CHECK: %[[V5:.*]] = bitcast void ()* %[[V4]] to i8*
+// CHECK: call i8* @llvm.objc.retainBlock(i8* %[[V5]])
+
+  void test_assignmentConditional(id a, bool c) {
+    assignmentConditional(a, c);
+  }
+}
+
+#endif