[clangd] Indexing of standard library

This provides a nice "warm start" with all headers indexed, not just those included so far. The standard library is indexed after a preamble is parsed, using that file's configuration. The result is pushed into the dynamic index. If we later see a higher language version, we reindex it. It's configurable as Index.StandardLibrary, off by default for now. Based on D105177 by @kuhnel Fixes clangd/clangd#618 Differential Revision: https://reviews.llvm.org/D115232
llvm · May 17, 2022 · ecaa4d9 · ecaa4d9
1 parent 8430b82
commit ecaa4d9
Show file tree

Hide file tree

Showing 18 changed files with 713 additions and 21 deletions.
diff --git a/clang-tools-extra/clangd/CMakeLists.txt b/clang-tools-extra/clangd/CMakeLists.txt
@@ -119,6 +119,7 @@ add_clang_library(clangDaemon
   index/Ref.cpp
   index/Relation.cpp
   index/Serialization.cpp
+  index/StdLib.cpp
   index/Symbol.cpp
   index/SymbolCollector.cpp
   index/SymbolID.cpp

diff --git a/clang-tools-extra/clangd/ClangdServer.cpp b/clang-tools-extra/clangd/ClangdServer.cpp
@@ -26,6 +26,7 @@
 #include "index/CanonicalIncludes.h"
 #include "index/FileIndex.h"
 #include "index/Merge.h"
+#include "index/StdLib.h"
 #include "refactor/Rename.h"
 #include "refactor/Tweak.h"
 #include "support/Cancellation.h"
@@ -59,16 +60,39 @@ namespace {
 // Update the FileIndex with new ASTs and plumb the diagnostics responses.
 struct UpdateIndexCallbacks : public ParsingCallbacks {
   UpdateIndexCallbacks(FileIndex *FIndex,
-                       ClangdServer::Callbacks *ServerCallbacks)
-      : FIndex(FIndex), ServerCallbacks(ServerCallbacks) {}
+                       ClangdServer::Callbacks *ServerCallbacks,
+                       const ThreadsafeFS &TFS, AsyncTaskRunner *Tasks)
+      : FIndex(FIndex), ServerCallbacks(ServerCallbacks), TFS(TFS),
+        Tasks(Tasks) {}
 
-  void onPreambleAST(PathRef Path, llvm::StringRef Version, ASTContext &Ctx,
+  void onPreambleAST(PathRef Path, llvm::StringRef Version,
+                     const CompilerInvocation &CI, ASTContext &Ctx,
                      Preprocessor &PP,
                      const CanonicalIncludes &CanonIncludes) override {
+    // If this preamble uses a standard library we haven't seen yet, index it.
+    if (FIndex)
+      if (auto Loc = Stdlib.add(*CI.getLangOpts(), PP.getHeaderSearchInfo()))
+        indexStdlib(CI, std::move(*Loc));
+
     if (FIndex)
       FIndex->updatePreamble(Path, Version, Ctx, PP, CanonIncludes);
   }
 
+  void indexStdlib(const CompilerInvocation &CI, StdLibLocation Loc) {
+    auto Task = [this, LO(*CI.getLangOpts()), Loc(std::move(Loc)),
+                 CI(std::make_unique<CompilerInvocation>(CI))]() mutable {
+      IndexFileIn IF;
+      IF.Symbols = indexStandardLibrary(std::move(CI), Loc, TFS);
+      if (Stdlib.isBest(LO))
+        FIndex->updatePreamble(std::move(IF));
+    };
+    if (Tasks)
+      // This doesn't have a semaphore to enforce -j, but it's rare.
+      Tasks->runAsync("IndexStdlib", std::move(Task));
+    else
+      Task();
+  }
+
   void onMainAST(PathRef Path, ParsedAST &AST, PublishFn Publish) override {
     if (FIndex)
       FIndex->updateMain(Path, AST);
@@ -103,6 +127,9 @@ struct UpdateIndexCallbacks : public ParsingCallbacks {
 private:
   FileIndex *FIndex;
   ClangdServer::Callbacks *ServerCallbacks;
+  const ThreadsafeFS &TFS;
+  StdLibSet Stdlib;
+  AsyncTaskRunner *Tasks;
 };
 
 class DraftStoreFS : public ThreadsafeFS {
@@ -154,12 +181,15 @@ ClangdServer::ClangdServer(const GlobalCompilationDatabase &CDB,
       Transient(Opts.ImplicitCancellation ? TUScheduler::InvalidateOnUpdate
                                           : TUScheduler::NoInvalidation),
       DirtyFS(std::make_unique<DraftStoreFS>(TFS, DraftMgr)) {
+  if (Opts.AsyncThreadsCount != 0)
+    IndexTasks.emplace();
   // Pass a callback into `WorkScheduler` to extract symbols from a newly
   // parsed file and rebuild the file index synchronously each time an AST
   // is parsed.
-  WorkScheduler.emplace(
-      CDB, TUScheduler::Options(Opts),
-      std::make_unique<UpdateIndexCallbacks>(DynamicIdx.get(), Callbacks));
+  WorkScheduler.emplace(CDB, TUScheduler::Options(Opts),
+                        std::make_unique<UpdateIndexCallbacks>(
+                            DynamicIdx.get(), Callbacks, TFS,
+                            IndexTasks ? IndexTasks.getPointer() : nullptr));
   // Adds an index to the stack, at higher priority than existing indexes.
   auto AddIndex = [&](SymbolIndex *Idx) {
     if (this->Index != nullptr) {
@@ -975,6 +1005,9 @@ ClangdServer::blockUntilIdleForTest(llvm::Optional<double> TimeoutSeconds) {
   // and we're blocking the main thread.
   if (!WorkScheduler->blockUntilIdle(timeoutSeconds(TimeoutSeconds)))
     return false;
+  // TUScheduler is the only thing that starts background indexing work.
+  if (IndexTasks && !IndexTasks->wait(timeoutSeconds(TimeoutSeconds)))
+    return false;
 
   // Unfortunately we don't have strict topological order between the rest of
   // the components. E.g. CDB broadcast triggers backrgound indexing.

diff --git a/clang-tools-extra/clangd/ClangdServer.h b/clang-tools-extra/clangd/ClangdServer.h
@@ -427,6 +427,7 @@ class ClangdServer {
   mutable std::mutex CachedCompletionFuzzyFindRequestMutex;
 
   llvm::Optional<std::string> WorkspaceRoot;
+  llvm::Optional<AsyncTaskRunner> IndexTasks; // for stdlib indexing.
   llvm::Optional<TUScheduler> WorkScheduler;
   // Invalidation policy used for actions that we assume are "transient".
   TUScheduler::ASTActionInvalidation Transient;

diff --git a/clang-tools-extra/clangd/Config.h b/clang-tools-extra/clangd/Config.h
@@ -81,11 +81,12 @@ struct Config {
     /// forward-slashes.
     std::string MountPoint;
   };
-  /// Controls background-index behavior.
+  /// Controls index behavior.
   struct {
-    /// Whether this TU should be indexed.
+    /// Whether this TU should be background-indexed.
     BackgroundPolicy Background = BackgroundPolicy::Build;
     ExternalIndexSpec External;
+    bool StandardLibrary = false;
   } Index;
 
   enum UnusedIncludesPolicy { Strict, None };

diff --git a/clang-tools-extra/clangd/ConfigCompile.cpp b/clang-tools-extra/clangd/ConfigCompile.cpp
@@ -332,6 +332,11 @@ struct FragmentCompiler {
     }
     if (F.External)
       compile(std::move(**F.External), F.External->Range);
+    if (F.StandardLibrary)
+      Out.Apply.push_back(
+          [Val(**F.StandardLibrary)](const Params &, Config &C) {
+            C.Index.StandardLibrary = Val;
+          });
   }
 
   void compile(Fragment::IndexBlock::ExternalBlock &&External,

diff --git a/clang-tools-extra/clangd/ConfigFragment.h b/clang-tools-extra/clangd/ConfigFragment.h
@@ -199,6 +199,9 @@ struct Fragment {
       llvm::Optional<Located<std::string>> MountPoint;
     };
     llvm::Optional<Located<ExternalBlock>> External;
+    // Whether the standard library visible from this file should be indexed.
+    // This makes all standard library symbols available, included or not.
+    llvm::Optional<Located<bool>> StandardLibrary;
   };
   IndexBlock Index;
 

diff --git a/clang-tools-extra/clangd/ConfigYAML.cpp b/clang-tools-extra/clangd/ConfigYAML.cpp
@@ -184,6 +184,10 @@ class Parser {
       F.External.emplace(std::move(External));
       F.External->Range = N.getSourceRange();
     });
+    Dict.handle("StandardLibrary", [&](Node &N) {
+      if (auto StandardLibrary = boolValue(N, "StandardLibrary"))
+        F.StandardLibrary = *StandardLibrary;
+    });
     Dict.parse(N);
   }
 

diff --git a/clang-tools-extra/clangd/TUScheduler.cpp b/clang-tools-extra/clangd/TUScheduler.cpp
@@ -1013,9 +1013,10 @@ void PreambleThread::build(Request Req) {
   bool IsFirstPreamble = !LatestBuild;
   LatestBuild = clang::clangd::buildPreamble(
       FileName, *Req.CI, Inputs, StoreInMemory,
-      [this, Version(Inputs.Version)](ASTContext &Ctx, Preprocessor &PP,
-                                      const CanonicalIncludes &CanonIncludes) {
-        Callbacks.onPreambleAST(FileName, Version, Ctx, PP, CanonIncludes);
+      [&](ASTContext &Ctx, Preprocessor &PP,
+          const CanonicalIncludes &CanonIncludes) {
+        Callbacks.onPreambleAST(FileName, Inputs.Version, *Req.CI, Ctx, PP,
+                                CanonIncludes);
       },
       &Stats);
   if (!LatestBuild)

diff --git a/clang-tools-extra/clangd/TUScheduler.h b/clang-tools-extra/clangd/TUScheduler.h
@@ -133,8 +133,8 @@ class ParsingCallbacks {
   /// contains only AST nodes from the #include directives at the start of the
   /// file. AST node in the current file should be observed on onMainAST call.
   virtual void onPreambleAST(PathRef Path, llvm::StringRef Version,
-                             ASTContext &Ctx, Preprocessor &PP,
-                             const CanonicalIncludes &) {}
+                             const CompilerInvocation &CI, ASTContext &Ctx,
+                             Preprocessor &PP, const CanonicalIncludes &) {}
 
   /// The argument function is run under the critical section guarding against
   /// races when closing the files.

diff --git a/clang-tools-extra/clangd/index/FileIndex.cpp b/clang-tools-extra/clangd/index/FileIndex.cpp
@@ -425,12 +425,7 @@ FileIndex::FileIndex()
       MainFileSymbols(IndexContents::All),
       MainFileIndex(std::make_unique<MemIndex>()) {}
 
-void FileIndex::updatePreamble(PathRef Path, llvm::StringRef Version,
-                               ASTContext &AST, Preprocessor &PP,
-                               const CanonicalIncludes &Includes) {
-  IndexFileIn IF;
-  std::tie(IF.Symbols, std::ignore, IF.Relations) =
-      indexHeaderSymbols(Version, AST, PP, Includes);
+void FileIndex::updatePreamble(IndexFileIn IF) {
   FileShardedIndex ShardedIndex(std::move(IF));
   for (auto Uri : ShardedIndex.getAllSources()) {
     auto IF = ShardedIndex.getShard(Uri);
@@ -461,6 +456,15 @@ void FileIndex::updatePreamble(PathRef Path, llvm::StringRef Version,
   }
 }
 
+void FileIndex::updatePreamble(PathRef Path, llvm::StringRef Version,
+                               ASTContext &AST, Preprocessor &PP,
+                               const CanonicalIncludes &Includes) {
+  IndexFileIn IF;
+  std::tie(IF.Symbols, std::ignore, IF.Relations) =
+      indexHeaderSymbols(Version, AST, PP, Includes);
+  updatePreamble(std::move(IF));
+}
+
 void FileIndex::updateMain(PathRef Path, ParsedAST &AST) {
   auto Contents = indexMainDecls(AST);
   MainFileSymbols.update(

diff --git a/clang-tools-extra/clangd/index/FileIndex.h b/clang-tools-extra/clangd/index/FileIndex.h
@@ -114,6 +114,7 @@ class FileIndex : public MergedIndex {
   /// and macros in \p PP.
   void updatePreamble(PathRef Path, llvm::StringRef Version, ASTContext &AST,
                       Preprocessor &PP, const CanonicalIncludes &Includes);
+  void updatePreamble(IndexFileIn);
 
   /// Update symbols and references from main file \p Path with
   /// `indexMainDecls`.