Index: include/clang/Driver/Options.td
===================================================================
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -1594,6 +1594,7 @@
 def no__dead__strip__inits__and__terms : Flag<["-"], "no_dead_strip_inits_and_terms">;
 def nobuiltininc : Flag<["-"], "nobuiltininc">, Flags<[CC1Option]>,
   HelpText<"Disable builtin #include directories">;
+def nocudainc : Flag<["-"], "nocudainc">;
 def nodefaultlibs : Flag<["-"], "nodefaultlibs">;
 def nofixprebinding : Flag<["-"], "nofixprebinding">;
 def nolibc : Flag<["-"], "nolibc">;
Index: include/clang/Driver/ToolChain.h
===================================================================
--- include/clang/Driver/ToolChain.h
+++ include/clang/Driver/ToolChain.h
@@ -393,6 +393,10 @@
   virtual void addProfileRTLibs(const llvm::opt::ArgList &Args,
                                 llvm::opt::ArgStringList &CmdArgs) const;
 
+  /// \brief Add arguments to use system-specific CUDA includes.
+  virtual void AddCudaIncludeArgs(const llvm::opt::ArgList &DriverArgs,
+                                  llvm::opt::ArgStringList &CC1Args) const;
+
   /// \brief Return sanitizers which are available in this toolchain.
   virtual SanitizerMask getSupportedSanitizers() const;
 };
Index: lib/Driver/ToolChain.cpp
===================================================================
--- lib/Driver/ToolChain.cpp
+++ lib/Driver/ToolChain.cpp
@@ -657,3 +657,6 @@
     Res |= CFIICall;
   return Res;
 }
+
+void ToolChain::AddCudaIncludeArgs(const ArgList &DriverArgs,
+                                   ArgStringList &CC1Args) const {}
Index: lib/Driver/ToolChains.h
===================================================================
--- lib/Driver/ToolChains.h
+++ lib/Driver/ToolChains.h
@@ -784,6 +784,8 @@
   void AddClangCXXStdlibIncludeArgs(
       const llvm::opt::ArgList &DriverArgs,
       llvm::opt::ArgStringList &CC1Args) const override;
+  void AddCudaIncludeArgs(const llvm::opt::ArgList &DriverArgs,
+                          llvm::opt::ArgStringList &CC1Args) const override;
   bool isPIEDefault() const override;
   SanitizerMask getSupportedSanitizers() const override;
   void addProfileRTLibs(const llvm::opt::ArgList &Args,
Index: lib/Driver/ToolChains.cpp
===================================================================
--- lib/Driver/ToolChains.cpp
+++ lib/Driver/ToolChains.cpp
@@ -3950,6 +3950,15 @@
   }
 }
 
+void Linux::AddCudaIncludeArgs(const ArgList &DriverArgs,
+                               ArgStringList &CC1Args) const {
+  if (DriverArgs.hasArg(options::OPT_nocudainc))
+    return;
+
+  if (CudaInstallation.isValid())
+    addSystemInclude(DriverArgs, CC1Args, CudaInstallation.getIncludePath());
+}
+
 bool Linux::isPIEDefault() const { return getSanitizerArgs().requiresPIE(); }
 
 SanitizerMask Linux::getSupportedSanitizers() const {
Index: lib/Driver/Tools.h
===================================================================
--- lib/Driver/Tools.h
+++ lib/Driver/Tools.h
@@ -57,7 +57,8 @@
                                const Driver &D, const llvm::opt::ArgList &Args,
                                llvm::opt::ArgStringList &CmdArgs,
                                const InputInfo &Output,
-                               const InputInfoList &Inputs) const;
+                               const InputInfoList &Inputs,
+                               const ToolChain *AuxToolChain) const;
 
   void AddAArch64TargetArgs(const llvm::opt::ArgList &Args,
                             llvm::opt::ArgStringList &CmdArgs) const;
Index: lib/Driver/Tools.cpp
===================================================================
--- lib/Driver/Tools.cpp
+++ lib/Driver/Tools.cpp
@@ -278,7 +278,8 @@
                                     const Driver &D, const ArgList &Args,
                                     ArgStringList &CmdArgs,
                                     const InputInfo &Output,
-                                    const InputInfoList &Inputs) const {
+                                    const InputInfoList &Inputs,
+                                    const ToolChain *AuxToolChain) const {
   Arg *A;
 
   CheckPreprocessingOptions(D, Args);
@@ -471,11 +472,20 @@
   addDirectoryList(Args, CmdArgs, "-objcxx-isystem", "OBJCPLUS_INCLUDE_PATH");
 
   // Add C++ include arguments, if needed.
-  if (types::isCXX(Inputs[0].getType()))
+  if (types::isCXX(Inputs[0].getType())) {
     getToolChain().AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
+    if (AuxToolChain)
+      AuxToolChain->AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
+  }
 
   // Add system include arguments.
   getToolChain().AddClangSystemIncludeArgs(Args, CmdArgs);
+  if (AuxToolChain)
+      AuxToolChain->AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
+
+  // Add CUDA include arguments, if needed.
+  if (types::isCuda(Inputs[0].getType()))
+    getToolChain().AddCudaIncludeArgs(Args, CmdArgs);
 }
 
 // FIXME: Move to target hook.
@@ -3254,8 +3264,8 @@
   CmdArgs.push_back("-triple");
   CmdArgs.push_back(Args.MakeArgString(TripleStr));
 
+  const ToolChain *AuxToolChain = nullptr;
   if (IsCuda) {
-    const ToolChain *AuxToolChain;
     if (&getToolChain() == C.getCudaDeviceToolChain())
       AuxToolChain = C.getCudaHostToolChain();
     else if (&getToolChain() == C.getCudaHostToolChain())
@@ -3266,6 +3276,7 @@
       CmdArgs.push_back("-aux-triple");
       CmdArgs.push_back(Args.MakeArgString(AuxToolChain->getTriple().str()));
     }
+    CmdArgs.push_back("-fcuda-target-overloads");
   }
 
   if (Triple.isOSWindows() && (Triple.getArch() == llvm::Triple::arm ||
@@ -4073,7 +4084,8 @@
   //
   // FIXME: Support -fpreprocessed
   if (types::getPreprocessedType(InputType) != types::TY_INVALID)
-    AddPreprocessingOptions(C, JA, D, Args, CmdArgs, Output, Inputs);
+    AddPreprocessingOptions(C, JA, D, Args, CmdArgs, Output, Inputs,
+                            AuxToolChain);
 
   // Don't warn about "clang -c -DPIC -fPIC test.i" because libtool.m4 assumes
   // that "The compiler can only warn and ignore the option if not recognized".
Index: test/Driver/cuda-detect.cu
===================================================================
--- test/Driver/cuda-detect.cu
+++ test/Driver/cuda-detect.cu
@@ -1,10 +1,34 @@
 // REQUIRES: clang-driver
 // REQUIRES: x86-registered-target
+// REQUIRES: nvptx-registered-target
 //
+// # Check that we properly detect CUDA installation.
 // RUN: %clang -v --target=i386-unknown-linux \
-// RUN:   --sysroot=/tmp/no-cuda-there 2>&1 | FileCheck %s -check-prefix NOCUDA
+// RUN:   --sysroot=%S/no-cuda-there 2>&1 | FileCheck %s -check-prefix NOCUDA
+// RUN: %clang -v --target=i386-unknown-linux \
+// RUN:   --sysroot=%S/Inputs/CUDA 2>&1 | FileCheck %s
 // RUN: %clang -v --target=i386-unknown-linux \
 // RUN:   --cuda-path=%S/Inputs/CUDA/usr/local/cuda 2>&1 | FileCheck %s
 
+// Verify that CUDA include path gets added
+// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
+// RUN:   --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN:   | FileCheck %s -check-prefix COMMON -check-prefix CUDAINC
+// Verify that -nocudainc disables CUDA include paths.
+// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
+// RUN:   -nocudainc --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN:   | FileCheck %s -check-prefix COMMON -check-prefix NOCUDAINC
+// We should not add any CUDA include paths if there's no valid CUDA installation
+// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
+// RUN:   --cuda-path=%S/no-cuda-there %s 2>&1 \
+// RUN:   | FileCheck %s -check-prefix COMMON -check-prefix NOCUDAINC
+
 // CHECK: Found CUDA installation: {{.*}}/Inputs/CUDA/usr/local/cuda
 // NOCUDA-NOT: Found CUDA installation:
+
+// COMMON: "-triple" "nvptx-nvidia-cuda"
+// COMMON-SAME: "-fcuda-is-device"
+// CUDAINC-SAME: "-internal-isystem" "{{.*}}/Inputs/CUDA/usr/local/cuda/include"
+// NOCUDAINC-NOT: "-internal-isystem" "{{.*}}/cuda/include"
+// COMMON-SAME: "-x" "cuda"
+