From 1cf95bffb64726acbe0e0505c923ad1f2fa803e2 Mon Sep 17 00:00:00 2001
From: Jonas Rembser <jonas.rembser@cern.ch>
Date: Tue, 8 Sep 2026 11:19:05 +0000
Subject: [PATCH] [build] Add CPPJIT_EXTRA_INTERPRETER_ARGS for packagers

The embedded clang probes well-known prefixes for the host toolchain's
headers. Where a distribution does not lay its toolchain out that way --
Nix, Guix, any relocatable prefix -- the probe comes up empty and the
interpreter fails at its first #include, with no recourse short of
patching the wrapper. Bake the search paths in at configure time
instead. CppInterOp still appends CPPINTEROP_EXTRA_INTERPRETER_ARGS
after them, so the runtime can add to the baked arguments.

The value is escaped for the string literal it lands in, so a Windows
include path survives the preprocessor, and a ';' is rejected as CMake's
list separator. Report a failed interpreter creation while here: a
rejected argument left CreateInterpreter returning nullptr while
LoadCppInterOp reported success, and the first code to assume an
interpreter segfaulted.
---
 CMakeLists.txt                  | 16 ++++++++++++++++
 src/interop/interop_wrapper.cxx | 19 ++++++++++++++++---
 2 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/CMakeLists.txt b/CMakeLists.txt
index c3f8ed8..543c035 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -14,6 +14,8 @@ set(CPPINTEROP_GIT_REPOSITORY "https://github.com/compiler-research/CppInterOp.g
 set(CPPINTEROP_GIT_TAG "9802d61921ad5688ae42e4e628d754fc1192244d" CACHE STRING "")
 set(CPPINTEROP_SOURCE_DIR "" CACHE PATH
     "Override default CppInterOp built by ExternalProject_Add, with a path to local CppInterOp source")
+set(CPPJIT_EXTRA_INTERPRETER_ARGS "" CACHE STRING
+    "Space-separated arguments passed at interpreter creation")
 
 # The full Development component requires libpython, which manylinux
 # images do not ship and extension modules do not need.
@@ -78,6 +80,20 @@ target_compile_definitions(cppjit PRIVATE
     CPPJIT_CLANG_INCLUDE_DIR="${CPPJIT_INTEROP_CLANG_DIR}"
 )
 
+# The value lands in a string literal, so backslashes and quotes must survive
+# the preprocessor; a ";" cannot be carried through CMake at all.
+if(CPPJIT_EXTRA_INTERPRETER_ARGS)
+    if("${CPPJIT_EXTRA_INTERPRETER_ARGS}" MATCHES ";")
+        message(FATAL_ERROR
+            "CPPJIT_EXTRA_INTERPRETER_ARGS must not contain ';', CMake's list separator")
+    endif()
+    string(REPLACE "\\" "\\\\" _cppjit_extra_args "${CPPJIT_EXTRA_INTERPRETER_ARGS}")
+    string(REPLACE "\"" "\\\"" _cppjit_extra_args "${_cppjit_extra_args}")
+    target_compile_definitions(cppjit PRIVATE
+        CPPJIT_EXTRA_INTERPRETER_ARGS="${_cppjit_extra_args}"
+    )
+endif()
+
 target_include_directories(cppjit PRIVATE
     # src/ itself resolves the public "cpyrt/*.h" spellings against the
     # flattened src/cpyrt/ directory
diff --git a/src/interop/interop_wrapper.cxx b/src/interop/interop_wrapper.cxx
index d29dada..765f1a0 100644
--- a/src/interop/interop_wrapper.cxx
+++ b/src/interop/interop_wrapper.cxx
@@ -131,8 +131,8 @@ static bool loadDispatchAPI(const InterOpPaths& Paths) {
   return true;
 }
 
-// CppInterOp itself appends CPPINTEROP_EXTRA_INTERPRETER_ARGS inside
-// CreateInterpreter, so nothing needs to be forwarded from here.
+// CppInterOp appends the CPPINTEROP_EXTRA_INTERPRETER_ARGS environment
+// variable itself, so only build-time arguments are forwarded from here.
 static interop::TInterp_t
 acquireOrCreateInterpreter(const InterOpPaths& Paths) {
   if (auto existingInterp = Cpp::GetInterpreter())
@@ -154,6 +154,16 @@ acquireOrCreateInterpreter(const InterOpPaths& Paths) {
     args.push_back("-resource-dir");
     args.push_back(resourceDir.c_str());
   }
+#ifdef CPPJIT_EXTRA_INTERPRETER_ARGS
+  // Space-split like CppInterOp's CPPINTEROP_EXTRA_INTERPRETER_ARGS, which
+  // CreateInterpreter appends after these.
+  std::vector<std::string> bakedArgs;
+  std::istringstream bakedStream(CPPJIT_EXTRA_INTERPRETER_ARGS);
+  for (std::string arg; bakedStream >> arg;)
+    bakedArgs.push_back(arg);
+  for (const std::string& arg : bakedArgs)
+    args.push_back(arg.c_str());
+#endif
   return Cpp::CreateInterpreter(args, /*GpuArgs=*/{});
 }
 
@@ -246,7 +256,10 @@ extern "C" int LoadCppInterOp() {
     if (!loadDispatchAPI(Paths))
       return;
 
-    acquireOrCreateInterpreter(Paths);
+    if (!acquireOrCreateInterpreter(Paths)) {
+      std::cerr << "[cppjit] Failed to create interpreter" << std::endl;
+      return;
+    }
     configureInterpreter(Paths);
     preloadHeaders();
     defineRuntimeHelpers();