[clang-tools-extra] [clangd] [C++20] [Modules] Add scanning cache (PR #125988)

[Chuanqi Xu via cfe-commits]

================
@@ -380,30 +381,114 @@ llvm::SmallVector<StringRef> getAllRequiredModules(ProjectModules &MDB,
   return ModuleNames;
 }
 
+class CachingProjectModules : public ProjectModules {
+public:
+  CachingProjectModules(const GlobalCompilationDatabase &CDB) : CDB(CDB) {}
+
+  std::vector<std::string> getRequiredModules(PathRef File) override {
+    std::unique_ptr<ProjectModules> MDB = CDB.getProjectModules(File);
+    if (!MDB) {
+      elog("Failed to get Project Modules information for {0}", File);
+      return {};
+    }
+    return MDB->getRequiredModules(File);
+  }
+
+  std::string getModuleNameForSource(PathRef File) override {
+    std::unique_ptr<ProjectModules> MDB = CDB.getProjectModules(File);
+    if (!MDB) {
+      elog("Failed to get Project Modules information for {0}", File);
+      return {};
+    }
+    return MDB->getModuleNameForSource(File);
+  }
+
+  void setCommandMangler(CommandMangler M) override {
+    // GlobalCompilationDatabase::getProjectModules() will set mangler
+    // for the underlying ProjectModules.
+  }
+
+  std::string getSourceForModuleName(llvm::StringRef ModuleName,
+                                     PathRef RequiredSrcFile) override {
+    std::string CachedResult;
+    {
+      std::lock_guard<std::mutex> Lock(CacheMutex);
+      auto Iter = ModuleNameToSourceCache.find(ModuleName);
+      if (Iter != ModuleNameToSourceCache.end())
+        CachedResult = Iter->second;
+    }
+
+    std::unique_ptr<ProjectModules> MDB =
+        CDB.getProjectModules(RequiredSrcFile);
+    if (!MDB) {
+      elog("Failed to get Project Modules information for {0}",
+           RequiredSrcFile);
+      return {};
+    }
+
+    // Verify Cached Result by seeing if the source declaring the same module
+    // as we query.
+    if (!CachedResult.empty()) {
+      std::string ModuleNameOfCachedSource =
+          MDB->getModuleNameForSource(CachedResult);
+      if (ModuleNameOfCachedSource == ModuleName)
+        return CachedResult;
+      else {
+        // Cached Result is invalid. Clear it.
+
+        std::lock_guard<std::mutex> Lock(CacheMutex);
+        ModuleNameToSourceCache.erase(ModuleName);
+      }
+    }
+
+    auto Result = MDB->getSourceForModuleName(ModuleName, RequiredSrcFile);
----------------
ChuanqiXu9 wrote:

Thanks for pointing this out. After thinking it again, I feel it might be easier to only store a module-name-to-source cache in the ModulesBuilder (Instead of the CachingProjectModules). And then we will construct the CachingProjectModules in `ModulesBuilder::ModulesBuilderImpl::getOrBuildModuleFile` with the cache and the ProjectModules from CDB. So we won't have the concern now. The lifetime of CachingProjectModules is the same with the previous approach.

https://github.com/llvm/llvm-project/pull/125988