Index: clang/lib/Driver/Tools.cpp
===================================================================
--- clang/lib/Driver/Tools.cpp
+++ clang/lib/Driver/Tools.cpp
@@ -410,6 +410,13 @@
     }
   }
 
+  // Add offload include arguments specific for CUDA.  This must happen before
+  // we -I or -include anything else, because we must pick up the CUDA headers
+  // from the particular CUDA installation, rather than from e.g.
+  // /usr/local/include.
+  if (JA.isOffloading(Action::OFK_Cuda))
+    getToolChain().AddCudaIncludeArgs(Args, CmdArgs);
+
   // Add -i* options, and automatically translate to
   // -include-pch/-include-pth for transparent PCH support. It's
   // wonky, but we include looking for .gch so we can support seamless
@@ -607,10 +614,6 @@
     // For IAMCU add special include arguments.
     getToolChain().AddIAMCUIncludeArgs(Args, CmdArgs);
   }
-
-  // Add offload include arguments specific for CUDA if that is required.
-  if (JA.isOffloading(Action::OFK_Cuda))
-    getToolChain().AddCudaIncludeArgs(Args, CmdArgs);
 }
 
 // FIXME: Move to target hook.
Index: clang/test/Driver/cuda-detect.cu
===================================================================
--- clang/test/Driver/cuda-detect.cu
+++ clang/test/Driver/cuda-detect.cu
@@ -61,4 +61,7 @@
 // NOCUDAINC-NOT: "-internal-isystem" "{{.*}}/cuda/include"
 // CUDAINC-SAME: "-include" "__clang_cuda_runtime_wrapper.h"
 // NOCUDAINC-NOT: "-include" "__clang_cuda_runtime_wrapper.h"
+// -internal-externc-isystem flags must come *after* the cuda include flags,
+// because we must search the cuda include directory first.
+// CUDAINC-SAME: "-internal-externc-isystem"
 // COMMON-SAME: "-x" "cuda"