Index: lib/CodeGen/CGDecl.cpp
===================================================================
--- lib/CodeGen/CGDecl.cpp
+++ lib/CodeGen/CGDecl.cpp
@@ -1620,8 +1620,9 @@
   bool capturedByInit =
       Init && emission.IsEscapingByRef && isCapturedBy(D, Init);
 
-  Address Loc =
-      capturedByInit ? emission.Addr : emission.getObjectAddress(*this);
+  bool locIsByrefHeader = !capturedByInit;
+  const Address Loc =
+      locIsByrefHeader ? emission.getObjectAddress(*this) : emission.Addr;
 
   // Note: constexpr already initializes everything correctly.
   LangOptions::TrivialAutoVarInitKind trivialAutoVarInit =
@@ -1637,7 +1638,7 @@
       return;
 
     // Only initialize a __block's storage: we always initialize the header.
-    if (emission.IsEscapingByRef)
+    if (emission.IsEscapingByRef && !locIsByrefHeader)
       Loc = emitBlockByrefAddress(Loc, &D, /*follow=*/false);
 
     CharUnits Size = getContext().getTypeSizeInChars(type);
@@ -1744,10 +1745,9 @@
   }
 
   llvm::Type *BP = CGM.Int8Ty->getPointerTo(Loc.getAddressSpace());
-  if (Loc.getType() != BP)
-    Loc = Builder.CreateBitCast(Loc, BP);
-
-  emitStoresForConstant(CGM, D, Loc, isVolatile, Builder, constant);
+  emitStoresForConstant(
+      CGM, D, (Loc.getType() == BP) ? Loc : Builder.CreateBitCast(Loc, BP),
+      isVolatile, Builder, constant);
 }
 
 /// Emit an expression as an initializer for an object (variable, field, etc.)
Index: test/CodeGenCXX/trivial-auto-var-init.cpp
===================================================================
--- test/CodeGenCXX/trivial-auto-var-init.cpp
+++ test/CodeGenCXX/trivial-auto-var-init.cpp
@@ -45,14 +45,35 @@
 // PATTERN:       %captured1 = getelementptr inbounds %struct.__block_byref_captured, %struct.__block_byref_captured* %captured, i32 0, i32 4
 // PATTERN-NEXT:  store %struct.XYZ* inttoptr (i64 -6148914691236517206 to %struct.XYZ*), %struct.XYZ** %captured1, align 8
 // PATTERN:       %call = call %struct.XYZ* @create(
+using Block = void (^)();
+typedef struct XYZ {
+  Block block;
+} * xyz_t;
 void test_block_self_init() {
-  using Block = void (^)();
-  typedef struct XYZ {
-    Block block;
-  } * xyz_t;
   extern xyz_t create(Block block);
   __block xyz_t captured = create(^() {
-    (void)captured;
+    used(captured);
+  });
+}
+
+// Capturing with escape after initialization is also an edge case.
+//
+// UNINIT-LABEL:  test_block_captures_self_after_init(
+// ZERO-LABEL:    test_block_captures_self_after_init(
+// ZERO:          %block = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i8* }>, align 8
+// ZERO:          %captured1 = getelementptr inbounds %struct.__block_byref_captured.1, %struct.__block_byref_captured.1* %captured, i32 0, i32 4
+// ZERO-NEXT:     store %struct.XYZ* null, %struct.XYZ** %captured1, align 8
+// ZERO:          %call = call %struct.XYZ* @create(
+// PATTERN-LABEL: test_block_captures_self_after_init(
+// PATTERN:       %block = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i8* }>, align 8
+// PATTERN:       %captured1 = getelementptr inbounds %struct.__block_byref_captured.1, %struct.__block_byref_captured.1* %captured, i32 0, i32 4
+// PATTERN-NEXT:  store %struct.XYZ* inttoptr (i64 -6148914691236517206 to %struct.XYZ*), %struct.XYZ** %captured1, align 8
+// PATTERN:       %call = call %struct.XYZ* @create(
+void test_block_captures_self_after_init() {
+  extern xyz_t create(Block block);
+  __block xyz_t captured;
+  captured = create(^() {
+    used(captured);
   });
 }