[Clang][NVPTX] Allow passing arguments to the linker while standalone (#73030)

Summary:
We support standalone compilation for the NVPTX architecture using
'nvlink' as our linker. Because of the special handling required to
transform input files to cubins, as nvlink expects for some reason, we
didn't use the standard AddLinkerInput method. However, this also meant
that we weren't forwarding options passed with -Wl to the linker. Add
this support in for the standalone toolchain path.

Revived from https://reviews.llvm.org/D149978

3 files changed, 32 insertions, 24 deletions

diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index ed5924c..94d4982 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -623,35 +623,34 @@ void NVPTX::Linker::ConstructJob(Compilation &C, const JobAction &JA,
       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 (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 (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));
+    } else if (!II.isNothing()) {
+      II.getInputArg().renderAsInput(Args, CmdArgs);
     }
   }
 
diff --git a/clang/test/Driver/cuda-cross-compiling.c b/clang/test/Driver/cuda-cross-compiling.c
index 6c9e2ca..2505835 100644
--- a/clang/test/Driver/cuda-cross-compiling.c
+++ b/clang/test/Driver/cuda-cross-compiling.c
@@ -69,6 +69,13 @@
 // 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,a,b -### %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=LINKER-ARGS %s
+
+// LINKER-ARGS: nvlink{{.*}}"-v"{{.*}}"a" "b"
+
 // Tests for handling a missing architecture.
 //
 // RUN: not %clang -target nvptx64-nvidia-cuda %s -### 2>&1 \
@@ -80,4 +87,4 @@
 // RUN: %clang -target nvptx64-nvidia-cuda -flto -c %s -### 2>&1 \
 // RUN:   | FileCheck -check-prefix=GENERIC %s
 
-// GENERIC-NOT: -cc1" "-triple" "nvptx64-nvidia-cuda" {{.*}} "-target-cpu"
+// GENERIC-NOT: -cc1" "-triple" "nvptx64-nvidia-cuda" {{.*}} "-target-cpu"
\ No newline at end of file
diff --git a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
index 095cf5e..576e8f2 100644
--- a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
+++ b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
@@ -454,9 +454,11 @@ Expected<StringRef> clang(ArrayRef<StringRef> InputFiles, const ArgList &Args) {
       Triple.isAMDGPU() ? Args.MakeArgString("-mcpu=" + Arch)
                         : Args.MakeArgString("-march=" + Arch),
       Args.MakeArgString("-" + OptLevel),
-      "-Wl,--no-undefined",
   };
 
+  if (!Triple.isNVPTX())
+    CmdArgs.push_back("-Wl,--no-undefined");
+
   for (StringRef InputFile : InputFiles)
     CmdArgs.push_back(InputFile);