[CUDA] Include CUDA headers before anything else.

[jlebar]

Summary

There's no point to --cuda-path if we then go and include /usr/include
first. And if you install the right packages, Ubuntu will install (very
old) CUDA headers there.

[tra]

OK. This should help with PR26966.

clang/lib/Driver/Tools.cpp

if (A->getOption().matches(options::OPT_MQ)) {
       CmdArgs.push_back(Args.MakeArgString(Quoted));
 
       // -MT flag - no change
     } else {
       A->render(Args, CmdArgs);
     }
   }
 
+  // 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
   // replacement into a build system already set up to be generating
   // .gch files.
   int YcIndex = -1, YuIndex = -1;
   {
     int AI = -1;
if (!IsIAMCU)
     forAllAssociatedToolChains(C, JA, getToolChain(),
                                [&Args, &CmdArgs](const ToolChain &TC) {
                                  TC.AddClangSystemIncludeArgs(Args, CmdArgs);
                                });
   else {
     // 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.
 static bool isSignedCharDefault(const llvm::Triple &Triple) {
   switch (Triple.getArch()) {
   default:
     return true;
 

clang/test/Driver/cuda-detect.cu

 // LIBDEVICE35-SAME: libdevice.compute_35.10.bc
 // NOLIBDEVICE-NOT: libdevice.compute_{{.*}}.bc
 // LIBDEVICE-SAME: "-target-feature" "+ptx42"
 // NOLIBDEVICE-NOT: "-target-feature" "+ptx42"
 // CUDAINC-SAME: "-internal-isystem" "{{.*}}/Inputs/CUDA/usr/local/cuda/include"
 // 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"