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

[Joseph Huber via cfe-commits]

https://github.com/jhuber6 updated https://github.com/llvm/llvm-project/pull/73030

>From ee43e8f9ae90bcd70d46b17cfecb854711a4b1ce Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn at outlook.com>
Date: Tue, 21 Nov 2023 13:45:10 -0600
Subject: [PATCH] [Clang][NVPTX] Allow passing arguments to the linker while
 standalone

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
---
 clang/lib/Driver/ToolChains/Cuda.cpp          | 43 +++++++++----------
 clang/test/Driver/cuda-cross-compiling.c      |  8 ++++
 .../ClangLinkerWrapper.cpp                    |  4 +-
 3 files changed, 32 insertions(+), 23 deletions(-)

diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index e95ff98e6c940f..5ef8b4455c23f1 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -611,35 +611,34 @@ 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 12d0af3b45f32f..5a52496838813e 100644
--- a/clang/test/Driver/cuda-cross-compiling.c
+++ b/clang/test/Driver/cuda-cross-compiling.c
@@ -77,3 +77,11 @@
 // 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,a,b -### %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=LINKER-ARGS %s
+
+// LINKER-ARGS: nvlink{{.*}}"-v"{{.*}}"a" "b"
diff --git a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
index bafe8ace60d1ce..03fb0a7d64552e 100644
--- a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
+++ b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
@@ -385,9 +385,11 @@ 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);