[clang][modules] Cache loads of modules imported by PCH

During explicit modular build, PCM files are typically specified via the `-fmodule-file=<path>` command-line option. Early during the compilation, Clang uses the `ASTReader` to read their contents and caches the result so that the module isn't loaded implicitly later on. A listener is attached to the `ASTReader` to collect names of the modules read from the PCM files. However, if the PCM has already been loaded previously via PCH:
1. the `ASTReader` doesn't do anything for the second time,
2. the listener is not invoked at all,
3. the module load result is not cached,
4. the compilation fails when attempting to load the module implicitly later on.

This patch solves this problem by attaching the listener to the `ASTReader` for PCH reading as well.

Reviewed By: dexonsmith

Differential Revision: https://reviews.llvm.org/D111560

Author: jansvoboda11

clang/lib/Frontend/CompilerInstance.cpp

@@ -565,29 +565,26 @@ namespace {
 // We mark these as known and redirect any attempt to load that module to
 // the files we were handed.
 struct ReadModuleNames : ASTReaderListener {
-  CompilerInstance &CI;
+  Preprocessor &PP;
   llvm::SmallVector<IdentifierInfo*, 8> LoadedModules;
 
-  ReadModuleNames(CompilerInstance &CI) : CI(CI) {}
+  ReadModuleNames(Preprocessor &PP) : PP(PP) {}
 
   void ReadModuleName(StringRef ModuleName) override {
-    LoadedModules.push_back(
-        CI.getPreprocessor().getIdentifierInfo(ModuleName));
+    LoadedModules.push_back(PP.getIdentifierInfo(ModuleName));
   }
 
   void registerAll() {
-    ModuleMap &MM = CI.getPreprocessor().getHeaderSearchInfo().getModuleMap();
+    ModuleMap &MM = PP.getHeaderSearchInfo().getModuleMap();
     for (auto *II : LoadedModules)
       MM.cacheModuleLoad(*II, MM.findModule(II->getName()));
     LoadedModules.clear();
   }
 
   void markAllUnavailable() {
     for (auto *II : LoadedModules) {
-      if (Module *M = CI.getPreprocessor()
-                          .getHeaderSearchInfo()
-                          .getModuleMap()
-                          .findModule(II->getName())) {
+      if (Module *M = PP.getHeaderSearchInfo().getModuleMap().findModule(
+              II->getName())) {
         M->HasIncompatibleModuleFile = true;
 
         // Mark module as available if the only reason it was unavailable
@@ -652,6 +649,11 @@ IntrusiveRefCntPtr<ASTReader> CompilerInstance::createPCHExternalASTSource(
   for (auto &Listener : DependencyCollectors)
     Listener->attachToASTReader(*Reader);
 
+  auto Listener = std::make_unique<ReadModuleNames>(PP);
+  auto &ListenerRef = *Listener;
+  ASTReader::ListenerScope ReadModuleNamesListener(*Reader,
+                                                   std::move(Listener));
+
   switch (Reader->ReadAST(Path,
                           Preamble ? serialization::MK_Preamble
                                    : serialization::MK_PCH,
@@ -661,6 +663,7 @@ IntrusiveRefCntPtr<ASTReader> CompilerInstance::createPCHExternalASTSource(
     // Set the predefines buffer as suggested by the PCH reader. Typically, the
     // predefines buffer will be empty.
     PP.setPredefines(Reader->getSuggestedPredefines());
+    ListenerRef.registerAll();
     return Reader;
 
   case ASTReader::Failure:
@@ -676,6 +679,7 @@ IntrusiveRefCntPtr<ASTReader> CompilerInstance::createPCHExternalASTSource(
     break;
   }
 
+  ListenerRef.markAllUnavailable();
   Context.setExternalSource(nullptr);
   return nullptr;
 }
@@ -1706,7 +1710,7 @@ bool CompilerInstance::loadModuleFile(StringRef FileName) {
                                           SourceLocation())
         <= DiagnosticsEngine::Warning;
 
-  auto Listener = std::make_unique<ReadModuleNames>(*this);
+  auto Listener = std::make_unique<ReadModuleNames>(*PP);
   auto &ListenerRef = *Listener;
   ASTReader::ListenerScope ReadModuleNamesListener(*TheASTReader,
                                                    std::move(Listener));

clang/lib/Tooling/DependencyScanning/DependencyScanningTool.cpp

@@ -38,7 +38,7 @@ FullDependencies::getAdditionalArgsWithoutModulePaths() const {
   };
 
   for (const PrebuiltModuleDep &PMD : PrebuiltModuleDeps) {
-    Args.push_back("-fmodule-file=" + PMD.ModuleName + "=" + PMD.PCMFile);
+    Args.push_back("-fmodule-file=" + PMD.PCMFile);
     Args.push_back("-fmodule-map-file=" + PMD.ModuleMapFile);
   }
 

clang/test/ClangScanDeps/modules-pch.c

@@ -229,8 +229,7 @@
 // CHECK-TU-WITH-COMMON-NEXT:       "command-line": [
 // CHECK-TU-WITH-COMMON-NEXT:         "-fno-implicit-modules",
 // CHECK-TU-WITH-COMMON-NEXT:         "-fno-implicit-module-maps",
-// FIXME: Figure out why we need `=ModCommon2` here for Clang to pick up the PCM.
-// CHECK-TU-WITH-COMMON-NEXT:         "-fmodule-file=ModCommon2=[[PREFIX]]/build/{{.*}}/ModCommon2-{{.*}}.pcm",
+// CHECK-TU-WITH-COMMON-NEXT:         "-fmodule-file=[[PREFIX]]/build/{{.*}}/ModCommon2-{{.*}}.pcm",
 // CHECK-TU-WITH-COMMON-NEXT:         "-fmodule-map-file=[[PREFIX]]/module.modulemap"
 // CHECK-TU-WITH-COMMON-NEXT:         "-fmodule-file=[[PREFIX]]/build/[[HASH_MOD_TU_WITH_COMMON]]/ModTUWithCommon-{{.*}}.pcm",
 // CHECK-TU-WITH-COMMON-NEXT:         "-fmodule-map-file=[[PREFIX]]/module.modulemap"

clang/test/Modules/Inputs/pch-shared-module/mod.h

@@ -0,0 +1 @@
+module mod { header "mod.h" }

clang/test/Modules/Inputs/pch-shared-module/module.modulemap

@@ -0,0 +1 @@
+#include "mod.h"

clang/test/Modules/Inputs/pch-shared-module/pch.h

@@ -0,0 +1,14 @@
+// rm -rf %t && mkdir %t
+
+// RUN: %clang_cc1 -fmodules -emit-module -fmodule-name=mod %S/Inputs/pch-shared-module/module.modulemap -o %t/mod.pcm
+
+// RUN: %clang_cc1 -fmodules -emit-pch %S/Inputs/pch-shared-module/pch.h -o %t/pch.h.gch \
+// RUN:   -fmodule-file=%t/mod.pcm -fmodule-map-file=%S/Inputs/pch-shared-module/module.modulemap
+
+// Check that `mod.pcm` is loaded correctly, even though it's imported by the PCH as well.
+// RUN: %clang_cc1 -fmodules -fsyntax-only %s -include-pch %t/pch.h.gch -I %S/Inputs/pch-shared-module \
+// RUN:   -fmodule-file=%t/mod.pcm -fmodule-map-file=%S/Inputs/pch-shared-module/module.modulemap -verify
+
+#include "mod.h"
+
+// expected-no-diagnostics