[Preprocessor] Do not expand macros if the input is already preprocessed (#137665)

Preprocessing the preprocessor output again interacts poorly with some
flag combinations when we perform a separate preprocessing stage. In our
case, `-no-integrated-cpp -dD` triggered this issue; but I guess that
other flags could also trigger problems (`-save-temps` instead of
`-no-integrated-cpp`).

Full context (which is quite weird I'll admit):

* To cache OpenCL kernel compilation results, we use the
`-no-integrated-cpp` for the driver to generate a separate preprocessing
command (`clang -E`) before the rest of the compilation.
* Some OpenCL C language features are implemented as macro definitions
(in `opencl-c-base.h`). The semantic analysis queries the preprocessor
to check if these are defined or not, for example, when we checks if a
builtin is available when using `-fdeclare-opencl-builtins`.
* To preserve these `#define` directives, on the preprocessor's output,
we use `-dD`. However, other `#define` directives are also maintained
besides OpenCL ones; which triggers the issue shown in this PR.

A better fix for our particular case could have been to move the
language features implemented as macros into some sort of a flag to be
used together with `-fdeclare-opencl-builtins`.
But I also thought that not preprocessing preprocessor outputs seemed
like something desirable. I hope to work on this on a follow up.

Author: jmmartinez

clang/include/clang/Frontend/FrontendAction.h

@@ -84,6 +84,8 @@ class FrontendAction {
   /// \return True on success; on failure ExecutionAction() and
   /// EndSourceFileAction() will not be called.
   virtual bool BeginSourceFileAction(CompilerInstance &CI) {
+    if (CurrentInput.isPreprocessed())
+      CI.getPreprocessor().SetMacroExpansionOnlyInDirectives();
     return true;
   }
 
@@ -98,7 +100,11 @@ class FrontendAction {
   ///
   /// This is guaranteed to only be called following a successful call to
   /// BeginSourceFileAction (and BeginSourceFile).
-  virtual void EndSourceFileAction() {}
+  virtual void EndSourceFileAction() {
+    if (CurrentInput.isPreprocessed())
+      // Reset the preprocessor macro expansion to the default.
+      getCompilerInstance().getPreprocessor().SetEnableMacroExpansion();
+  }
 
   /// Callback at the end of processing a single input, to determine
   /// if the output files should be erased or not.

clang/include/clang/Lex/Preprocessor.h

@@ -1847,6 +1847,10 @@ class Preprocessor {
     MacroExpansionInDirectivesOverride = true;
   }
 
+  void SetEnableMacroExpansion() {
+    DisableMacroExpansion = MacroExpansionInDirectivesOverride = false;
+  }
+
   /// Peeks ahead N tokens and returns that token without consuming any
   /// tokens.
   ///

clang/lib/CodeGen/CodeGenAction.cpp

@@ -908,6 +908,8 @@ bool CodeGenAction::loadLinkModules(CompilerInstance &CI) {
 bool CodeGenAction::hasIRSupport() const { return true; }
 
 void CodeGenAction::EndSourceFileAction() {
+  ASTFrontendAction::EndSourceFileAction();
+
   // If the consumer creation failed, do nothing.
   if (!getCompilerInstance().hasASTConsumer())
     return;
@@ -932,7 +934,7 @@ CodeGenerator *CodeGenAction::getCodeGenerator() const {
 bool CodeGenAction::BeginSourceFileAction(CompilerInstance &CI) {
   if (CI.getFrontendOpts().GenReducedBMI)
     CI.getLangOpts().setCompilingModule(LangOptions::CMK_ModuleInterface);
-  return true;
+  return ASTFrontendAction::BeginSourceFileAction(CI);
 }
 
 static std::unique_ptr<raw_pwrite_stream>

clang/lib/Frontend/FrontendActions.cpp

@@ -181,7 +181,7 @@ bool GeneratePCHAction::shouldEraseOutputFiles() {
 
 bool GeneratePCHAction::BeginSourceFileAction(CompilerInstance &CI) {
   CI.getLangOpts().CompilingPCH = true;
-  return true;
+  return ASTFrontendAction::BeginSourceFileAction(CI);
 }
 
 std::vector<std::unique_ptr<ASTConsumer>>

clang/lib/Frontend/Rewrite/FrontendActions.cpp

@@ -103,12 +103,13 @@ bool FixItAction::BeginSourceFileAction(CompilerInstance &CI) {
   }
   Rewriter.reset(new FixItRewriter(CI.getDiagnostics(), CI.getSourceManager(),
                                    CI.getLangOpts(), FixItOpts.get()));
-  return true;
+  return ASTFrontendAction::BeginSourceFileAction(CI);
 }
 
 void FixItAction::EndSourceFileAction() {
   // Otherwise rewrite all files.
   Rewriter->WriteFixedFiles();
+  ASTFrontendAction::EndSourceFileAction();
 }
 
 bool FixItRecompile::BeginInvocation(CompilerInstance &CI) {
@@ -298,7 +299,7 @@ bool RewriteIncludesAction::BeginSourceFileAction(CompilerInstance &CI) {
         std::make_unique<RewriteImportsListener>(CI, OutputStream));
   }
 
-  return true;
+  return PreprocessorFrontendAction::BeginSourceFileAction(CI);
 }
 
 void RewriteIncludesAction::ExecuteAction() {

clang/test/Preprocessor/preprocess-cpp-output.c

@@ -0,0 +1,10 @@
+// RUN: %clang_cc1 -E -x c %s | FileCheck %s --check-prefixes=EXPANDED
+// RUN: %clang_cc1 -E -x cpp-output %s | FileCheck %s --check-prefixes=NOT-EXPANDED
+
+// EXPANDED: void __attribute__((__attribute__((always_inline)))) foo()
+// NOT-EXPANDED: void __attribute__((always_inline)) foo()
+
+#define always_inline __attribute__((always_inline))
+void __attribute__((always_inline)) foo() {
+    return 4;
+}

clang/test/Preprocessor/preprocess-pragma-cpp-output.c

@@ -0,0 +1,21 @@
+// RUN: %clang_cc1 -E -x c %s | FileCheck %s
+// RUN: %clang_cc1 -x c -fsyntax-only %s -verify
+// RUN: %clang_cc1 -x cpp-output -fsyntax-only -verify %s
+// expected-no-diagnostics
+
+// The preprocessor does not expand macro-identifiers in #pragma directives.
+// When we preprocess & parse the code, clang expands the macros in directives.
+// When we parse already preprocessed code, clang still has to expand the
+// macros in the directives.
+// This means that we're not always able to parse the preprocessor's output
+// without preserving the definitions (-dD).
+
+#define FACTOR 4
+
+void foo() {
+    // CHECK: #pragma unroll FACTOR
+    #pragma unroll FACTOR
+    for(;;) {
+    }
+    return;
+}