Index: lib/CodeGen/TargetInfo.cpp
===================================================================
--- lib/CodeGen/TargetInfo.cpp
+++ lib/CodeGen/TargetInfo.cpp
@@ -223,6 +223,23 @@
   return Addr;
 }
 
+static Address emitRoundPointerUpToAlignment(CodeGenFunction &CGF,
+                                             llvm::Value *OverflowArgArea,
+                                             CharUnits Align) {
+  llvm::Value *PtrAsInt = OverflowArgArea;
+  // OverflowArgArea = (OverflowArgArea + Align - 1) & -Align;
+  PtrAsInt = CGF.Builder.CreatePtrToInt(PtrAsInt, CGF.IntPtrTy);
+  PtrAsInt = CGF.Builder.CreateAdd(PtrAsInt,
+        llvm::ConstantInt::get(CGF.IntPtrTy, Align.getQuantity() - 1));
+  llvm::Value *Mask = llvm::ConstantInt::get(CGF.Int32Ty,
+                                             -Align.getQuantity());
+  PtrAsInt = CGF.Builder.CreateAnd(PtrAsInt, Mask);
+  PtrAsInt = CGF.Builder.CreateIntToPtr(PtrAsInt,
+                                        OverflowArgArea->getType(),
+                                        "overflow_arg_area.align");
+  return Address(PtrAsInt, Align);
+}
+
 /// Emit va_arg for a platform using the common void* representation,
 /// where arguments are simply emitted in an array of slots on the stack.
 ///
@@ -3543,9 +3560,14 @@
       Builder.CreateStructGEP(VAList, 3, CharUnits::fromQuantity(4));
     Address OverflowArea(Builder.CreateLoad(OverflowAreaAddr),
                          OverflowAreaAlign);
-
-    // The current address is the address of the varargs element.
-    // FIXME: do we not need to round up to alignment?
+    // Round up address of argument to alignment
+    llvm::Value *OverflowArgArea = OverflowArea.getPointer();
+    CharUnits Align = CGF.getContext().getTypeAlignInChars(Ty);
+    if (Align > OverflowAreaAlign) {
+      OverflowArea = emitRoundPointerUpToAlignment(CGF, OverflowArgArea,
+                                                   Align);
+    }
+ 
     MemAddr = Builder.CreateElementBitCast(OverflowArea, DirectTy);
 
     // Increase the overflow area.
Index: test/CodeGen/ppc-varargs-struct.c
===================================================================
--- test/CodeGen/ppc-varargs-struct.c
+++ test/CodeGen/ppc-varargs-struct.c
@@ -39,9 +39,13 @@
 // CHECK-PPC:[[USING_OVERFLOW]]
 // CHECK-PPC-NEXT:  [[OVERFLOW_AREA_P:%[0-9]+]] = getelementptr inbounds %struct.__va_list_tag, %struct.__va_list_tag* [[ARRAYDECAY]], i32 0, i32 3
 // CHECK-PPC-NEXT:  [[OVERFLOW_AREA:%.+]] = load i8*, i8** [[OVERFLOW_AREA_P]], align 4
-// CHECK-PPC-NEXT:  [[MEMADDR:%.+]] = bitcast i8* [[OVERFLOW_AREA]] to %struct.x**
-// CHECK-PPC-NEXT:  [[NEW_OVERFLOW_AREA:%[0-9]+]] = getelementptr inbounds i8, i8* [[OVERFLOW_AREA]], i32 4
-// CHECK-PPC-NEXT:  store i8* [[NEW_OVERFLOW_AREA]], i8** [[OVERFLOW_AREA_P]]
+// CHECK-PPC-NEXT:  %{{[0-9]+}} =  ptrtoint i8* %{{[0-9]+}} to i32
+// CHECK-PPC-NEXT:  %{{[0-9]+}} = add i32 %{{[0-9]+}}, 7
+// CHECK-PPC-NEXT:  %{{[0-9]+}} = and i32 %{{[0-9]+}}, -8
+// CHECK-PPC-NEXT:  %overflow_arg_area.align = inttoptr i32 %{{[0-9]+}} to i8*
+// CHECK-PPC-NEXT:  [[MEMADDR:%.+]] = bitcast i8* %overflow_arg_area.align to %struct.x**
+// CHECK-PPC-NEXT:  [[NEW_OVERFLOW_AREA:%[0-9]+]] = getelementptr inbounds i8, i8* %overflow_arg_area.align, i32 4
+// CHECK-PPC-NEXT:  store i8* [[NEW_OVERFLOW_AREA:%[0-9]+]], i8** [[OVERFLOW_AREA_P]], align 4
 // CHECK-PPC-NEXT:  br label %[[CONT]]
 //
 // CHECK-PPC:[[CONT]]