diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -607,36 +607,43 @@
       continue;
     }
 
-    // Currently, we only pass the input files to the linker, we do not pass
-    // any libraries that may be valid only for the host.
-    if (!II.isFilename())
-      continue;
-
     // The 'nvlink' application performs RDC-mode linking when given a '.o'
     // file and device linking when given a '.cubin' file. We always want to
     // perform device linking, so just rename any '.o' files.
     // FIXME: This should hopefully be removed if NVIDIA updates their tooling.
-    auto InputFile = getToolChain().getInputFilename(II);
-    if (llvm::sys::path::extension(InputFile) != ".cubin") {
-      // If there are no actions above this one then this is direct input and we
-      // can copy it. Otherwise the input is internal so a `.cubin` file should
-      // exist.
-      if (II.getAction() && II.getAction()->getInputs().size() == 0) {
-        const char *CubinF =
-            Args.MakeArgString(getToolChain().getDriver().GetTemporaryPath(
-                llvm::sys::path::stem(InputFile), "cubin"));
-        if (std::error_code EC =
-                llvm::sys::fs::copy_file(InputFile, C.addTempFile(CubinF)))
-          continue;
+    if (II.isFilename()) {
+      auto InputFile = getToolChain().getInputFilename(II);
+      if (llvm::sys::path::extension(InputFile) != ".cubin") {
+        // If there are no actions above this one then this is direct input and
+        // we can copy it. Otherwise the input is internal so a `.cubin` file
+        // should exist.
+        if (II.getAction() && II.getAction()->getInputs().size() == 0) {
+          const char *CubinF =
+              Args.MakeArgString(getToolChain().getDriver().GetTemporaryPath(
+                  llvm::sys::path::stem(InputFile), "cubin"));
+          if (std::error_code EC =
+                  llvm::sys::fs::copy_file(InputFile, C.addTempFile(CubinF)))
+            continue;
 
-        CmdArgs.push_back(CubinF);
+          CmdArgs.push_back(CubinF);
+        } else {
+          SmallString<256> Filename(InputFile);
+          llvm::sys::path::replace_extension(Filename, "cubin");
+          CmdArgs.push_back(Args.MakeArgString(Filename));
+        }
       } else {
-        SmallString<256> Filename(InputFile);
-        llvm::sys::path::replace_extension(Filename, "cubin");
-        CmdArgs.push_back(Args.MakeArgString(Filename));
+        CmdArgs.push_back(Args.MakeArgString(InputFile));
       }
-    } else {
-      CmdArgs.push_back(Args.MakeArgString(InputFile));
+      continue;
+    } else if (!II.isNothing()) {
+      // This option is commonly passed by LLVM by default, but isn't supported
+      // by nvlink.
+      if (llvm::any_of(II.getInputArg().getValues(), [](StringRef Arg) {
+            return Arg.equals("--color-diagnostics");
+          }))
+        continue;
+      // Render any remaining arguments as input to nvlink.
+      II.getInputArg().renderAsInput(Args, CmdArgs);
     }
   }
 
diff --git a/clang/test/Driver/cuda-cross-compiling.c b/clang/test/Driver/cuda-cross-compiling.c
--- a/clang/test/Driver/cuda-cross-compiling.c
+++ b/clang/test/Driver/cuda-cross-compiling.c
@@ -77,3 +77,12 @@
 // RUN:   | FileCheck -check-prefix=LOWERING %s
 
 // LOWERING: -cc1" "-triple" "nvptx64-nvidia-cuda" {{.*}} "-mllvm" "--nvptx-lower-global-ctor-dtor"
+
+//
+// Test passing arguments directly to nvlink.
+//
+// RUN: %clang -target nvptx64-nvidia-cuda -Wl,-v -Wl,--color-diagnostics -### %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=LINKER-ARGS %s
+
+// LINKER-ARGS: nvlink{{.*}}"-v"
+// LINKER-ARGS-NOT: nvlink{{.*}}"--color-diagnostics"