Index: lib/CodeGen/CGCall.cpp
===================================================================
--- lib/CodeGen/CGCall.cpp
+++ lib/CodeGen/CGCall.cpp
@@ -2277,6 +2277,18 @@
 
 /// Heuristically search for a dominating store to the return-value slot.
 static llvm::StoreInst *findDominatingStoreToReturnValue(CodeGenFunction &CGF) {
+  // Check if a User is a store which pointerOperand is the ReturnValue.
+  // We are looking for stores to the ReturnValue, not for stores of the
+  // ReturnValue to some other location.
+  auto getStoreIfValid = [&CGF](llvm::User *U) -> llvm::StoreInst * {
+    auto *SI = dyn_cast<llvm::StoreInst>(U);
+    if (!SI || SI->getPointerOperand() != CGF.ReturnValue)
+      return nullptr;
+    // These aren't actually possible for non-coerced returns, and we
+    // only care about non-coerced returns on this code path.
+    assert(!SI->isAtomic() && !SI->isVolatile());
+    return SI;
+  };
   // If there are multiple uses of the return-value slot, just check
   // for something immediately preceding the IP.  Sometimes this can
   // happen with how we generate implicit-returns; it can also happen
@@ -2305,21 +2317,12 @@
       break;
     }
 
-    llvm::StoreInst *store = dyn_cast<llvm::StoreInst>(I);
-    if (!store) return nullptr;
-    if (store->getPointerOperand() != CGF.ReturnValue) return nullptr;
-    assert(!store->isAtomic() && !store->isVolatile()); // see below
-    return store;
+    return getStoreIfValid(I);
   }
 
-  llvm::StoreInst *store =
-    dyn_cast<llvm::StoreInst>(CGF.ReturnValue->user_back());
+  llvm::StoreInst *store = getStoreIfValid(CGF.ReturnValue->user_back());
   if (!store) return nullptr;
 
-  // These aren't actually possible for non-coerced returns, and we
-  // only care about non-coerced returns on this code path.
-  assert(!store->isAtomic() && !store->isVolatile());
-
   // Now do a first-and-dirty dominance check: just walk up the
   // single-predecessors chain from the current insertion point.
   llvm::BasicBlock *StoreBB = store->getParent();
Index: test/CodeGen/arm_function_epilog.cpp
===================================================================
--- /dev/null
+++ test/CodeGen/arm_function_epilog.cpp
@@ -0,0 +1,17 @@
+// REQUIRES: arm-registered-target
+// RUN: %clang_cc1 -triple armv7-none-linux-androideabi -target-abi aapcs-linux -mfloat-abi hard -x c++ -emit-llvm %s -o - | FileCheck %s
+
+struct Vec2 {
+    union { struct { float x, y; };
+            float data[2];
+    };
+};
+
+// CHECK: define arm_aapcs_vfpcc %struct.Vec2 @_Z7getVec2v()
+// CHECK: ret %struct.Vec2
+Vec2 getVec2() {
+    Vec2 out;
+    union { Vec2* v; unsigned char* u; } x;
+    x.v = &out;
+    return out;
+}