Index: lib/CodeGen/CGCall.cpp
===================================================================
--- lib/CodeGen/CGCall.cpp
+++ lib/CodeGen/CGCall.cpp
@@ -644,11 +644,13 @@
   llvm::Type *FirstElt = SrcSTy->getElementType(0);
 
   // If the first elt is at least as large as what we're looking for, or if the
-  // first element is the same size as the whole struct, we can enter it.
+  // first element is the same size as the whole struct, we can enter it. Use
+  // the store size and not the alloca size here to ensure we will actually load
+  // the whole object
   uint64_t FirstEltSize =
-    CGF.CGM.getDataLayout().getTypeAllocSize(FirstElt);
+    CGF.CGM.getDataLayout().getTypeStoreSize(FirstElt);
   if (FirstEltSize < DstSize &&
-      FirstEltSize < CGF.CGM.getDataLayout().getTypeAllocSize(SrcSTy))
+      FirstEltSize < CGF.CGM.getDataLayout().getTypeStoreSize(SrcSTy))
     return SrcPtr;
 
   // GEP into the first element.
Index: test/CodeGen/24-bit.c
===================================================================
--- test/CodeGen/24-bit.c
+++ test/CodeGen/24-bit.c
@@ -0,0 +1,14 @@
+// RUN:  %clang_cc1 -triple x86_64-linux-gnu -emit-llvm -O0 -o - %s | FileCheck %s
+
+static union ibtt2
+{
+  struct ibtt0 { signed ibt0:10; unsigned short ibt1; } ibt5;
+  struct ibtt1 { signed ibt2:3; signed ibt3:9; signed ibt4:9; } ibt6;
+} ibt15 = {{267, 15266}};
+
+void callee_ibt0f(union ibtt2 ibtp5);
+
+void test(void) {
+// CHECK: = load i32*
+  callee_ibt0f(ibt15);
+}
Index: test/CodeGen/arm64-be-bitfield.c
===================================================================
--- test/CodeGen/arm64-be-bitfield.c
+++ test/CodeGen/arm64-be-bitfield.c
@@ -1,9 +1,14 @@
-// RUN:  %clang_cc1 -triple aarch64_be-linux-gnu -ffreestanding -emit-llvm -O0 -o - %s | FileCheck %s
+// RUN:  %clang_cc1 -triple aarch64_be-linux-gnu -ffreestanding -emit-llvm -O0 -o - %s | FileCheck --check-prefix IR %s
+// RUN:  %clang_cc1 -triple aarch64_be-linux-gnu -ffreestanding -S -O1 -o - %s | FileCheck --check-prefix ARM %s
 
 struct bt3 { signed b2:10; signed b3:10; } b16;
 
-// The correct right-shift amount is 40 bits for big endian.
+// Get the high 32-bits and then shift appropriately for big-endian.
 signed callee_b0f(struct bt3 bp11) {
-// CHECK: = lshr i64 %{{.*}}, 40
+// IR: callee_b0f(i64 [[ARG:%.*]])
+// IR: store i64 [[ARG]], i64* [[PTR:%.*]]
+// IR: [[BITCAST:%.*]] = bitcast i64* [[PTR]] to i8*
+// IR: call void @llvm.memcpy.p0i8.p0i8.i64(i8* {{.*}}, i8* [[BITCAST]], i64 4
+// ARM: asr x0, x0, #54
   return bp11.b2;
 }