Index: lib/CodeGen/CGDecl.cpp
===================================================================
--- lib/CodeGen/CGDecl.cpp
+++ lib/CodeGen/CGDecl.cpp
@@ -1633,11 +1633,15 @@
                   ? LangOptions::TrivialAutoVarInitKind::Uninitialized
                   : getContext().getLangOpts().getTrivialAutoVarInit()));
 
-  auto initializeWhatIsTechnicallyUninitialized = [&]() {
+  auto initializeWhatIsTechnicallyUninitialized = [&](Address Loc) {
     if (trivialAutoVarInit ==
         LangOptions::TrivialAutoVarInitKind::Uninitialized)
       return;
 
+    // Only initialize a __block's storage: we always initialize the header.
+    if (emission.IsEscapingByRef)
+      Loc = emitBlockByrefAddress(Loc, &D, /*follow=*/false);
+
     CharUnits Size = getContext().getTypeSizeInChars(type);
     if (!Size.isZero()) {
       switch (trivialAutoVarInit) {
@@ -1714,7 +1718,7 @@
   };
 
   if (isTrivialInitializer(Init)) {
-    initializeWhatIsTechnicallyUninitialized();
+    initializeWhatIsTechnicallyUninitialized(Loc);
     return;
   }
 
@@ -1728,7 +1732,7 @@
   }
 
   if (!constant) {
-    initializeWhatIsTechnicallyUninitialized();
+    initializeWhatIsTechnicallyUninitialized(Loc);
     LValue lv = MakeAddrLValue(Loc, type);
     lv.setNonGC(true);
     return EmitExprAsInit(Init, &D, lv, capturedByInit);
Index: test/CodeGenCXX/trivial-auto-var-init.cpp
===================================================================
--- test/CodeGenCXX/trivial-auto-var-init.cpp
+++ test/CodeGenCXX/trivial-auto-var-init.cpp
@@ -30,6 +30,32 @@
   used(block);
 }
 
+// Using the variable being initialized is typically UB in C, but for blocks we
+// can be nice: they imply extra book-keeping and we can do the auto-init before
+// any of said book-keeping.
+//
+// UNINIT-LABEL:  test_block_self_init(
+// ZERO-LABEL:    test_block_self_init(
+// ZERO:          %block = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i8* }>, align 8
+// ZERO:          %captured1 = getelementptr inbounds %struct.__block_byref_captured, %struct.__block_byref_captured* %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_self_init(
+// PATTERN:       %block = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i8* }>, align 8
+// 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(
+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;
+  });
+}
+
 // This type of code is currently not handled by zero / pattern initialization.
 // The test will break when that is fixed.
 // UNINIT-LABEL:  test_goto_unreachable_value(