Modules: Cache PCMs in memory and avoid a use-after-free

Clang's internal build system for implicit modules uses lock files to
ensure that after a process writes a PCM it will read the same one back
in (without contention from other -cc1 commands).  Since PCMs are read
from disk repeatedly while invalidating, building, and importing, the
lock is not released quickly.  Furthermore, the LockFileManager is not
robust in every environment.  Other -cc1 commands can stall until
timeout (after about eight minutes).

This commit changes the lock file from being necessary for correctness
to a (possibly dubious) performance hack.  The remaining benefit is to
reduce duplicate work in competing -cc1 commands which depend on the
same module.  Follow-up commits will change the internal build system to
continue after a timeout, and reduce the timeout.  Perhaps we should
reconsider blocking at all.

This also fixes a use-after-free, when one part of a compilation
validates a PCM and starts using it, and another tries to swap out the
PCM for something new.

The PCMCache is a new type called MemoryBufferCache, which saves memory
buffers based on their filename.  Its ownership is shared by the
CompilerInstance and ModuleManager.

  - The ModuleManager stores PCMs there that it loads from disk, never
    touching the disk if the cache is hot.

  - When modules fail to validate, they're removed from the cache.

  - When a CompilerInstance is spawned to build a new module, each
    already-loaded PCM is assumed to be valid, and is frozen to avoid
    the use-after-free.

  - Any newly-built module is written directly to the cache to avoid the
    round-trip to the filesystem, making lock files unnecessary for
    correctness.

Original patch by Manman Ren; most testcases by Adrian Prantl!

llvm-svn: 298165

2 files changed, 27 insertions, 10 deletions

diff --git a/clang/lib/Frontend/ASTUnit.cpp b/clang/lib/Frontend/ASTUnit.cpp
index ac5c7ca3be3..952992a9e8b 100644
--- a/clang/lib/Frontend/ASTUnit.cpp
+++ b/clang/lib/Frontend/ASTUnit.cpp
@@ -18,6 +18,7 @@
 #include "clang/AST/StmtVisitor.h"
 #include "clang/AST/TypeOrdering.h"
 #include "clang/Basic/Diagnostic.h"
+#include "clang/Basic/MemoryBufferCache.h"
 #include "clang/Basic/TargetInfo.h"
 #include "clang/Basic/TargetOptions.h"
 #include "clang/Basic/VirtualFileSystem.h"
@@ -185,7 +186,8 @@ struct ASTUnit::ASTWriterData {
   llvm::BitstreamWriter Stream;
   ASTWriter Writer;
 
-  ASTWriterData() : Stream(Buffer), Writer(Stream, Buffer, {}) {}
+  ASTWriterData(MemoryBufferCache &PCMCache)
+      : Stream(Buffer), Writer(Stream, Buffer, PCMCache, {}) {}
 };
 
 void ASTUnit::clearFileLevelDecls() {
@@ -681,6 +683,7 @@ std::unique_ptr<ASTUnit> ASTUnit::LoadFromASTFile(
   AST->SourceMgr = new SourceManager(AST->getDiagnostics(),
                                      AST->getFileManager(),
                                      UserFilesAreVolatile);
+  AST->PCMCache = new MemoryBufferCache;
   AST->HSOpts = std::make_shared<HeaderSearchOptions>();
   AST->HSOpts->ModuleFormat = PCHContainerRdr.getFormat();
   AST->HeaderInfo.reset(new HeaderSearch(AST->HSOpts,
@@ -701,7 +704,7 @@ std::unique_ptr<ASTUnit> ASTUnit::LoadFromASTFile(
 
   AST->PP = std::make_shared<Preprocessor>(
       std::move(PPOpts), AST->getDiagnostics(), AST->ASTFileLangOpts,
-      AST->getSourceManager(), HeaderInfo, *AST,
+      AST->getSourceManager(), *AST->PCMCache, HeaderInfo, *AST,
       /*IILookup=*/nullptr,
       /*OwnsHeaderSearch=*/false);
   Preprocessor &PP = *AST->PP;
@@ -1727,6 +1730,7 @@ ASTUnit::create(std::shared_ptr<CompilerInvocation> CI,
   AST->UserFilesAreVolatile = UserFilesAreVolatile;
   AST->SourceMgr = new SourceManager(AST->getDiagnostics(), *AST->FileMgr,
                                      UserFilesAreVolatile);
+  AST->PCMCache = new MemoryBufferCache;
 
   return AST;
 }
@@ -1997,6 +2001,7 @@ ASTUnit *ASTUnit::LoadFromCommandLine(
   if (!VFS)
     return nullptr;
   AST->FileMgr = new FileManager(AST->FileSystemOpts, VFS);
+  AST->PCMCache = new MemoryBufferCache;
   AST->OnlyLocalDecls = OnlyLocalDecls;
   AST->CaptureDiagnostics = CaptureDiagnostics;
   AST->TUKind = TUKind;
@@ -2008,7 +2013,7 @@ ASTUnit *ASTUnit::LoadFromCommandLine(
   AST->StoredDiagnostics.swap(StoredDiagnostics);
   AST->Invocation = CI;
   if (ForSerialization)
-    AST->WriterData.reset(new ASTWriterData());
+    AST->WriterData.reset(new ASTWriterData(*AST->PCMCache));
   // Zero out now to ease cleanup during crash recovery.
   CI = nullptr;
   Diags = nullptr;
@@ -2523,7 +2528,8 @@ bool ASTUnit::serialize(raw_ostream &OS) {
 
   SmallString<128> Buffer;
   llvm::BitstreamWriter Stream(Buffer);
-  ASTWriter Writer(Stream, Buffer, {});
+  MemoryBufferCache PCMCache;
+  ASTWriter Writer(Stream, Buffer, PCMCache, {});
   return serializeUnit(Writer, Buffer, getSema(), hasErrors, OS);
 }
 
diff --git a/clang/lib/Frontend/CompilerInstance.cpp b/clang/lib/Frontend/CompilerInstance.cpp
index a0e81f01f9b..4841c103f61 100644
--- a/clang/lib/Frontend/CompilerInstance.cpp
+++ b/clang/lib/Frontend/CompilerInstance.cpp
@@ -13,6 +13,7 @@
 #include "clang/AST/Decl.h"
 #include "clang/Basic/Diagnostic.h"
 #include "clang/Basic/FileManager.h"
+#include "clang/Basic/MemoryBufferCache.h"
 #include "clang/Basic/SourceManager.h"
 #include "clang/Basic/TargetInfo.h"
 #include "clang/Basic/Version.h"
@@ -55,9 +56,15 @@ using namespace clang;
 
 CompilerInstance::CompilerInstance(
     std::shared_ptr<PCHContainerOperations> PCHContainerOps,
-    bool BuildingModule)
-    : ModuleLoader(BuildingModule), Invocation(new CompilerInvocation()),
-      ThePCHContainerOperations(std::move(PCHContainerOps)) {}
+    MemoryBufferCache *SharedPCMCache)
+    : ModuleLoader(/* BuildingModule = */ SharedPCMCache),
+      Invocation(new CompilerInvocation()),
+      PCMCache(SharedPCMCache ? SharedPCMCache : new MemoryBufferCache),
+      ThePCHContainerOperations(std::move(PCHContainerOps)) {
+  // Don't allow this to invalidate buffers in use by others.
+  if (SharedPCMCache)
+    getPCMCache().finalizeCurrentBuffers();
+}
 
 CompilerInstance::~CompilerInstance() {
   assert(OutputFiles.empty() && "Still output files in flight?");
@@ -128,6 +135,8 @@ IntrusiveRefCntPtr<ASTReader> CompilerInstance::getModuleManager() const {
   return ModuleManager;
 }
 void CompilerInstance::setModuleManager(IntrusiveRefCntPtr<ASTReader> Reader) {
+  assert(PCMCache.get() == &Reader->getModuleManager().getPCMCache() &&
+         "Expected ASTReader to use the same PCM cache");
   ModuleManager = std::move(Reader);
 }
 
@@ -370,7 +379,7 @@ void CompilerInstance::createPreprocessor(TranslationUnitKind TUKind) {
                        getDiagnostics(), getLangOpts(), &getTarget());
   PP = std::make_shared<Preprocessor>(
       Invocation->getPreprocessorOptsPtr(), getDiagnostics(), getLangOpts(),
-      getSourceManager(), *HeaderInfo, *this, PTHMgr,
+      getSourceManager(), getPCMCache(), *HeaderInfo, *this, PTHMgr,
       /*OwnsHeaderSearch=*/true, TUKind);
   PP->Initialize(getTarget(), getAuxTarget());
 
@@ -1073,9 +1082,11 @@ static bool compileModuleImpl(CompilerInstance &ImportingInstance,
          Invocation->getModuleHash() && "Module hash mismatch!");
   
   // Construct a compiler instance that will be used to actually create the
-  // module.
+  // module.  Since we're sharing a PCMCache,
+  // CompilerInstance::CompilerInstance is responsible for finalizing the
+  // buffers to prevent use-after-frees.
   CompilerInstance Instance(ImportingInstance.getPCHContainerOperations(),
-                            /*BuildingModule=*/true);
+                            &ImportingInstance.getPreprocessor().getPCMCache());
   auto &Inv = *Invocation;
   Instance.setInvocation(std::move(Invocation));