diff --git a/clang/lib/Driver/ToolChains/Arch/ARM.h b/clang/lib/Driver/ToolChains/Arch/ARM.h
--- a/clang/lib/Driver/ToolChains/Arch/ARM.h
+++ b/clang/lib/Driver/ToolChains/Arch/ARM.h
@@ -48,13 +48,15 @@
 };
 
 FloatABI getARMFloatABI(const ToolChain &TC, const llvm::opt::ArgList &Args);
-ReadTPMode getReadTPMode(const ToolChain &TC, const llvm::opt::ArgList &Args);
+FloatABI getARMFloatABI(const Driver &D, const llvm::Triple &Triple,
+                        const llvm::opt::ArgList &Args);
+ReadTPMode getReadTPMode(const Driver &D, const llvm::opt::ArgList &Args);
 
 bool useAAPCSForMachO(const llvm::Triple &T);
 void getARMArchCPUFromArgs(const llvm::opt::ArgList &Args,
                            llvm::StringRef &Arch, llvm::StringRef &CPU,
                            bool FromAs = false);
-void getARMTargetFeatures(const ToolChain &TC, const llvm::Triple &Triple,
+void getARMTargetFeatures(const Driver &D, const llvm::Triple &Triple,
                           const llvm::opt::ArgList &Args,
                           llvm::opt::ArgStringList &CmdArgs,
                           std::vector<llvm::StringRef> &Features, bool ForAS);
diff --git a/clang/lib/Driver/ToolChains/Arch/ARM.cpp b/clang/lib/Driver/ToolChains/Arch/ARM.cpp
--- a/clang/lib/Driver/ToolChains/Arch/ARM.cpp
+++ b/clang/lib/Driver/ToolChains/Arch/ARM.cpp
@@ -137,9 +137,8 @@
 }
 
 // Select mode for reading thread pointer (-mtp=soft/cp15).
-arm::ReadTPMode arm::getReadTPMode(const ToolChain &TC, const ArgList &Args) {
+arm::ReadTPMode arm::getReadTPMode(const Driver &D, const ArgList &Args) {
   if (Arg *A = Args.getLastArg(options::OPT_mtp_mode_EQ)) {
-    const Driver &D = TC.getDriver();
     arm::ReadTPMode ThreadPointer =
         llvm::StringSwitch<arm::ReadTPMode>(A->getValue())
             .Case("cp15", ReadTPMode::Cp15)
@@ -156,11 +155,14 @@
   return ReadTPMode::Soft;
 }
 
+arm::FloatABI arm::getARMFloatABI(const ToolChain &TC, const ArgList &Args) {
+  return arm::getARMFloatABI(TC.getDriver(), TC.getEffectiveTriple(), Args);
+}
+
 // Select the float ABI as determined by -msoft-float, -mhard-float, and
 // -mfloat-abi=.
-arm::FloatABI arm::getARMFloatABI(const ToolChain &TC, const ArgList &Args) {
-  const Driver &D = TC.getDriver();
-  const llvm::Triple &Triple = TC.getEffectiveTriple();
+arm::FloatABI arm::getARMFloatABI(const Driver &D, const llvm::Triple &Triple,
+                                  const ArgList &Args) {
   auto SubArch = getARMSubArchVersionNumber(Triple);
   arm::FloatABI ABI = FloatABI::Invalid;
   if (Arg *A =
@@ -276,18 +278,13 @@
   return ABI;
 }
 
-void arm::getARMTargetFeatures(const ToolChain &TC,
-                               const llvm::Triple &Triple,
-                               const ArgList &Args,
-                               ArgStringList &CmdArgs,
-                               std::vector<StringRef> &Features,
-                               bool ForAS) {
-  const Driver &D = TC.getDriver();
-
+void arm::getARMTargetFeatures(const Driver &D, const llvm::Triple &Triple,
+                               const ArgList &Args, ArgStringList &CmdArgs,
+                               std::vector<StringRef> &Features, bool ForAS) {
   bool KernelOrKext =
       Args.hasArg(options::OPT_mkernel, options::OPT_fapple_kext);
-  arm::FloatABI ABI = arm::getARMFloatABI(TC, Args);
-  arm::ReadTPMode ThreadPointer = arm::getReadTPMode(TC, Args);
+  arm::FloatABI ABI = arm::getARMFloatABI(D, Triple, Args);
+  arm::ReadTPMode ThreadPointer = arm::getReadTPMode(D, Args);
   const Arg *WaCPU = nullptr, *WaFPU = nullptr;
   const Arg *WaHDiv = nullptr, *WaArch = nullptr;
 
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -326,7 +326,7 @@
   case llvm::Triple::armeb:
   case llvm::Triple::thumb:
   case llvm::Triple::thumbeb:
-    arm::getARMTargetFeatures(TC, Triple, Args, CmdArgs, Features, ForAS);
+    arm::getARMTargetFeatures(D, Triple, Args, CmdArgs, Features, ForAS);
     break;
 
   case llvm::Triple::ppc:
diff --git a/clang/test/Driver/cuda-simple.cu b/clang/test/Driver/cuda-simple.cu
--- a/clang/test/Driver/cuda-simple.cu
+++ b/clang/test/Driver/cuda-simple.cu
@@ -1,7 +1,6 @@
 // Verify that we can parse a simple CUDA file with or without -save-temps
 // http://llvm.org/PR22936
 // RUN: %clang -nocudainc -nocudalib -Werror -fsyntax-only -c %s
-// XFAIL: arm
 //
 // Verify that we pass -x cuda-cpp-output to compiler after
 // preprocessing a CUDA file