Modules: Use hash of PCM content for SIGNATURE

Change ASTFileSignature from a random 32-bit number to the hash of the
PCM content.

  - Move definition ASTFileSignature to Basic/Module.h so Module and
    ASTSourceDescriptor can use it.

  - Change the signature from uint64_t to std::array<uint32_t,5>.

  - Stop using (saving/reading) the size and modification time of PCM
    files when there is a valid SIGNATURE.

  - Add UNHASHED_CONTROL_BLOCK, and use it to store the SIGNATURE record
    and other records that shouldn't affect the hash.  Because implicit
    modules reuses the same file for multiple levels of -Werror, this
    includes DIAGNOSTIC_OPTIONS and DIAG_PRAGMA_MAPPINGS.

This helps to solve a PCH + implicit Modules dependency issue: PCH files
are handled by the external build system, whereas implicit modules are
handled by internal compiler build system.  This prevents invalidating a
PCH when the compiler overwrites a PCM file with the same content
(modulo the diagnostic differences).

Design and original patch by Manman Ren!

llvm-svn: 297655

4 files changed, 316 insertions, 111 deletions

diff --git a/clang/lib/Serialization/ASTReader.cpp b/clang/lib/Serialization/ASTReader.cpp
index 648c7b48ed8..be0cc9ab1a8 100644
--- a/clang/lib/Serialization/ASTReader.cpp
+++ b/clang/lib/Serialization/ASTReader.cpp
@@ -2163,7 +2163,7 @@ static bool isDiagnosedResult(ASTReader::ASTReadResult ARR, unsigned Caps) {
 ASTReader::ASTReadResult ASTReader::ReadOptionsBlock(
     BitstreamCursor &Stream, unsigned ClientLoadCapabilities,
     bool AllowCompatibleConfigurationMismatch, ASTReaderListener &Listener,
-    std::string &SuggestedPredefines, bool ValidateDiagnosticOptions) {
+    std::string &SuggestedPredefines) {
   if (Stream.EnterSubBlock(OPTIONS_BLOCK_ID))
     return Failure;
 
@@ -2205,15 +2205,6 @@ ASTReader::ASTReadResult ASTReader::ReadOptionsBlock(
       break;
     }
 
-    case DIAGNOSTIC_OPTIONS: {
-      bool Complain = (ClientLoadCapabilities & ARR_OutOfDate) == 0;
-      if (ValidateDiagnosticOptions &&
-          !AllowCompatibleConfigurationMismatch &&
-          ParseDiagnosticOptions(Record, Complain, Listener))
-        return OutOfDate;
-      break;
-    }
-
     case FILE_SYSTEM_OPTIONS: {
       bool Complain = (ClientLoadCapabilities & ARR_ConfigurationMismatch) == 0;
       if (!AllowCompatibleConfigurationMismatch &&
@@ -2254,6 +2245,23 @@ ASTReader::ReadControlBlock(ModuleFile &F,
     return Failure;
   }
 
+  // Lambda to read the unhashed control block the first time it's called.
+  //
+  // For PCM files, the unhashed control block cannot be read until after the
+  // MODULE_NAME record.  However, PCH files have no MODULE_NAME, and yet still
+  // need to look ahead before reading the IMPORTS record.  For consistency,
+  // this block is always read somehow (see BitstreamEntry::EndBlock).
+  bool HasReadUnhashedControlBlock = false;
+  auto readUnhashedControlBlockOnce = [&]() {
+    if (!HasReadUnhashedControlBlock) {
+      HasReadUnhashedControlBlock = true;
+      if (ASTReadResult Result =
+              readUnhashedControlBlock(F, ImportedBy, ClientLoadCapabilities))
+        return Result;
+    }
+    return Success;
+  };
+
   // Read all of the records and blocks in the control block.
   RecordData Record;
   unsigned NumInputs = 0;
@@ -2266,6 +2274,11 @@ ASTReader::ReadControlBlock(ModuleFile &F,
       Error("malformed block record in AST file");
       return Failure;
     case llvm::BitstreamEntry::EndBlock: {
+      // Validate the module before returning.  This call catches an AST with
+      // no module name and no imports.
+      if (ASTReadResult Result = readUnhashedControlBlockOnce())
+        return Result;
+
       // Validate input files.
       const HeaderSearchOptions &HSOpts =
           PP.getHeaderSearchInfo().getHeaderSearchOpts();
@@ -2337,13 +2350,10 @@ ASTReader::ReadControlBlock(ModuleFile &F,
           // FIXME: Allow this for files explicitly specified with -include-pch.
           bool AllowCompatibleConfigurationMismatch =
               F.Kind == MK_ExplicitModule || F.Kind == MK_PrebuiltModule;
-          const HeaderSearchOptions &HSOpts =
-              PP.getHeaderSearchInfo().getHeaderSearchOpts();
 
           Result = ReadOptionsBlock(Stream, ClientLoadCapabilities,
                                     AllowCompatibleConfigurationMismatch,
-                                    *Listener, SuggestedPredefines,
-                                    HSOpts.ModulesValidateDiagnosticOptions);
+                                    *Listener, SuggestedPredefines);
           if (Result == Failure) {
             Error("malformed block record in AST file");
             return Result;
@@ -2417,12 +2427,13 @@ ASTReader::ReadControlBlock(ModuleFile &F,
       break;
     }
 
-    case SIGNATURE:
-      assert((!F.Signature || F.Signature == Record[0]) && "signature changed");
-      F.Signature = Record[0];
-      break;
-
     case IMPORTS: {
+      // Validate the AST before processing any imports (otherwise, untangling
+      // them can be error-prone and expensive).  A module will have a name and
+      // will already have been validated, but this catches the PCH case.
+      if (ASTReadResult Result = readUnhashedControlBlockOnce())
+        return Result;
+
       // Load each of the imported PCH files.
       unsigned Idx = 0, N = Record.size();
       while (Idx < N) {
@@ -2435,7 +2446,10 @@ ASTReader::ReadControlBlock(ModuleFile &F,
             ReadUntranslatedSourceLocation(Record[Idx++]);
         off_t StoredSize = (off_t)Record[Idx++];
         time_t StoredModTime = (time_t)Record[Idx++];
-        ASTFileSignature StoredSignature = Record[Idx++];
+        ASTFileSignature StoredSignature = {
+            {{(uint32_t)Record[Idx++], (uint32_t)Record[Idx++],
+              (uint32_t)Record[Idx++], (uint32_t)Record[Idx++],
+              (uint32_t)Record[Idx++]}}};
         auto ImportedFile = ReadPath(F, Record, Idx);
 
         // If our client can't cope with us being out of date, we can't cope with
@@ -2487,6 +2501,12 @@ ASTReader::ReadControlBlock(ModuleFile &F,
       F.ModuleName = Blob;
       if (Listener)
         Listener->ReadModuleName(F.ModuleName);
+
+      // Validate the AST as soon as we have a name so we can exit early on
+      // failure.
+      if (ASTReadResult Result = readUnhashedControlBlockOnce())
+        return Result;
+
       break;
 
     case MODULE_DIRECTORY: {
@@ -3076,14 +3096,6 @@ ASTReader::ReadASTBlock(ModuleFile &F, unsigned ClientLoadCapabilities) {
       F.ObjCCategories.swap(Record);
       break;
 
-    case DIAG_PRAGMA_MAPPINGS:
-      if (F.PragmaDiagMappings.empty())
-        F.PragmaDiagMappings.swap(Record);
-      else
-        F.PragmaDiagMappings.insert(F.PragmaDiagMappings.end(),
-                                    Record.begin(), Record.end());
-      break;
-
     case CUDA_SPECIAL_DECL_REFS:
       // Later tables overwrite earlier ones.
       // FIXME: Modules will have trouble with this.
@@ -3657,10 +3669,10 @@ ASTReader::ASTReadResult ASTReader::ReadAST(StringRef FileName,
 
   unsigned NumModules = ModuleMgr.size();
   SmallVector<ImportedModule, 4> Loaded;
-  switch(ASTReadResult ReadResult = ReadASTCore(FileName, Type, ImportLoc,
-                                                /*ImportedBy=*/nullptr, Loaded,
-                                                0, 0, 0,
-                                                ClientLoadCapabilities)) {
+  switch (ASTReadResult ReadResult =
+              ReadASTCore(FileName, Type, ImportLoc,
+                          /*ImportedBy=*/nullptr, Loaded, 0, 0,
+                          ASTFileSignature(), ClientLoadCapabilities)) {
   case Failure:
   case Missing:
   case OutOfDate:
@@ -4021,6 +4033,12 @@ ASTReader::ReadASTCore(StringRef FileName,
       Loaded.push_back(ImportedModule(M, ImportedBy, ImportLoc));
       return Success;
 
+    case UNHASHED_CONTROL_BLOCK_ID:
+      // This block is handled using look-ahead during ReadControlBlock.  We
+      // shouldn't get here!
+      Error("malformed block record in AST file");
+      return Failure;
+
     default:
       if (Stream.SkipBlock()) {
         Error("malformed block record in AST file");
@@ -4033,6 +4051,93 @@ ASTReader::ReadASTCore(StringRef FileName,
   return Success;
 }
 
+ASTReader::ASTReadResult
+ASTReader::readUnhashedControlBlock(ModuleFile &F, bool WasImportedBy,
+                                    unsigned ClientLoadCapabilities) {
+  const HeaderSearchOptions &HSOpts =
+      PP.getHeaderSearchInfo().getHeaderSearchOpts();
+  bool AllowCompatibleConfigurationMismatch =
+      F.Kind == MK_ExplicitModule || F.Kind == MK_PrebuiltModule;
+
+  ASTReadResult Result = readUnhashedControlBlockImpl(
+      &F, F.Data, ClientLoadCapabilities, AllowCompatibleConfigurationMismatch,
+      Listener.get(),
+      WasImportedBy ? false : HSOpts.ModulesValidateDiagnosticOptions);
+
+  if (DisableValidation || WasImportedBy ||
+      (AllowConfigurationMismatch && Result == ConfigurationMismatch))
+    return Success;
+
+  if (Result == Failure)
+    Error("malformed block record in AST file");
+
+  return Result;
+}
+
+ASTReader::ASTReadResult ASTReader::readUnhashedControlBlockImpl(
+    ModuleFile *F, llvm::StringRef StreamData, unsigned ClientLoadCapabilities,
+    bool AllowCompatibleConfigurationMismatch, ASTReaderListener *Listener,
+    bool ValidateDiagnosticOptions) {
+  // Initialize a stream.
+  BitstreamCursor Stream(StreamData);
+
+  // Sniff for the signature.
+  if (!startsWithASTFileMagic(Stream))
+    return Failure;
+
+  // Scan for the UNHASHED_CONTROL_BLOCK_ID block.
+  if (SkipCursorToBlock(Stream, UNHASHED_CONTROL_BLOCK_ID))
+    return Failure;
+
+  // Read all of the records in the options block.
+  RecordData Record;
+  ASTReadResult Result = Success;
+  while (1) {
+    llvm::BitstreamEntry Entry = Stream.advance();
+
+    switch (Entry.Kind) {
+    case llvm::BitstreamEntry::Error:
+    case llvm::BitstreamEntry::SubBlock:
+      return Failure;
+
+    case llvm::BitstreamEntry::EndBlock:
+      return Result;
+
+    case llvm::BitstreamEntry::Record:
+      // The interesting case.
+      break;
+    }
+
+    // Read and process a record.
+    Record.clear();
+    switch (
+        (UnhashedControlBlockRecordTypes)Stream.readRecord(Entry.ID, Record)) {
+    case SIGNATURE: {
+      if (F)
+        std::copy(Record.begin(), Record.end(), F->Signature.data());
+      break;
+    }
+    case DIAGNOSTIC_OPTIONS: {
+      bool Complain = (ClientLoadCapabilities & ARR_OutOfDate) == 0;
+      if (Listener && ValidateDiagnosticOptions &&
+          !AllowCompatibleConfigurationMismatch &&
+          ParseDiagnosticOptions(Record, Complain, *Listener))
+        return OutOfDate;
+      break;
+    }
+    case DIAG_PRAGMA_MAPPINGS:
+      if (!F)
+        break;
+      if (F->PragmaDiagMappings.empty())
+        F->PragmaDiagMappings.swap(Record);
+      else
+        F->PragmaDiagMappings.insert(F->PragmaDiagMappings.end(),
+                                     Record.begin(), Record.end());
+      break;
+    }
+  }
+}
+
 /// Parse a record and blob containing module file extension metadata.
 static bool parseModuleFileExtensionMetadata(
               const SmallVectorImpl<uint64_t> &Record,
@@ -4249,23 +4354,24 @@ void ASTReader::finalizeForWriting() {
 static ASTFileSignature readASTFileSignature(StringRef PCH) {
   BitstreamCursor Stream(PCH);
   if (!startsWithASTFileMagic(Stream))
-    return 0;
+    return ASTFileSignature();
 
-  // Scan for the CONTROL_BLOCK_ID block.
-  if (SkipCursorToBlock(Stream, CONTROL_BLOCK_ID))
-    return 0;
+  // Scan for the UNHASHED_CONTROL_BLOCK_ID block.
+  if (SkipCursorToBlock(Stream, UNHASHED_CONTROL_BLOCK_ID))
+    return ASTFileSignature();
 
-  // Scan for SIGNATURE inside the control block.
+  // Scan for SIGNATURE inside the diagnostic options block.
   ASTReader::RecordData Record;
   while (true) {
     llvm::BitstreamEntry Entry = Stream.advanceSkippingSubblocks();
     if (Entry.Kind != llvm::BitstreamEntry::Record)
-      return 0;
+      return ASTFileSignature();
 
     Record.clear();
     StringRef Blob;
     if (SIGNATURE == Stream.readRecord(Entry.ID, Record, &Blob))
-      return Record[0];
+      return {{{(uint32_t)Record[0], (uint32_t)Record[1], (uint32_t)Record[2],
+                (uint32_t)Record[3], (uint32_t)Record[4]}}};
   }
 }
 
@@ -4384,7 +4490,8 @@ bool ASTReader::readASTFileControlBlock(
   }
 
   // Initialize the stream
-  BitstreamCursor Stream(PCHContainerRdr.ExtractPCH(**Buffer));
+  StringRef Bytes = PCHContainerRdr.ExtractPCH(**Buffer);
+  BitstreamCursor Stream(Bytes);
 
   // Sniff for the signature.
   if (!startsWithASTFileMagic(Stream))
@@ -4412,8 +4519,7 @@ bool ASTReader::readASTFileControlBlock(
         std::string IgnoredSuggestedPredefines;
         if (ReadOptionsBlock(Stream, ARR_ConfigurationMismatch | ARR_OutOfDate,
                              /*AllowCompatibleConfigurationMismatch*/ false,
-                             Listener, IgnoredSuggestedPredefines,
-                             ValidateDiagnosticOptions) != Success)
+                             Listener, IgnoredSuggestedPredefines) != Success)
           return true;
         break;
       }
@@ -4534,6 +4640,7 @@ bool ASTReader::readASTFileControlBlock(
 
   // Look for module file extension blocks, if requested.
   if (FindModuleFileExtensions) {
+    BitstreamCursor SavedStream = Stream;
     while (!SkipCursorToBlock(Stream, EXTENSION_BLOCK_ID)) {
       bool DoneWithExtensionBlock = false;
       while (!DoneWithExtensionBlock) {
@@ -4572,8 +4679,16 @@ bool ASTReader::readASTFileControlBlock(
        }
       }
     }
+    Stream = SavedStream;
   }
 
+  // Scan for the UNHASHED_CONTROL_BLOCK_ID block.
+  if (readUnhashedControlBlockImpl(
+          nullptr, Bytes, ARR_ConfigurationMismatch | ARR_OutOfDate,
+          /*AllowCompatibleConfigurationMismatch*/ false, &Listener,
+          ValidateDiagnosticOptions) != Success)
+    return true;
+
   return false;
 }
 
diff --git a/clang/lib/Serialization/ASTWriter.cpp b/clang/lib/Serialization/ASTWriter.cpp
index cdc1cf5bcb0..b13a4e1ff4b 100644
--- a/clang/lib/Serialization/ASTWriter.cpp
+++ b/clang/lib/Serialization/ASTWriter.cpp
@@ -18,8 +18,8 @@
 #include "clang/AST/ASTContext.h"
 #include "clang/AST/ASTUnresolvedSet.h"
 #include "clang/AST/Decl.h"
-#include "clang/AST/DeclContextInternals.h"
 #include "clang/AST/DeclCXX.h"
+#include "clang/AST/DeclContextInternals.h"
 #include "clang/AST/DeclFriend.h"
 #include "clang/AST/DeclTemplate.h"
 #include "clang/AST/Expr.h"
@@ -33,8 +33,8 @@
 #include "clang/Basic/DiagnosticOptions.h"
 #include "clang/Basic/FileManager.h"
 #include "clang/Basic/FileSystemOptions.h"
-#include "clang/Basic/LangOptions.h"
 #include "clang/Basic/LLVM.h"
+#include "clang/Basic/LangOptions.h"
 #include "clang/Basic/Module.h"
 #include "clang/Basic/ObjCRuntime.h"
 #include "clang/Basic/SourceManager.h"
@@ -64,9 +64,9 @@
 #include "llvm/ADT/Hashing.h"
 #include "llvm/ADT/IntrusiveRefCntPtr.h"
 #include "llvm/ADT/Optional.h"
+#include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallString.h"
-#include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/Bitcode/BitCodes.h"
 #include "llvm/Bitcode/BitstreamWriter.h"
@@ -79,6 +79,7 @@
 #include "llvm/Support/OnDiskHashTable.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/Process.h"
+#include "llvm/Support/SHA1.h"
 #include "llvm/Support/raw_ostream.h"
 #include <algorithm>
 #include <cassert>
@@ -1016,7 +1017,6 @@ void ASTWriter::WriteBlockInfoBlock() {
   // Control Block.
   BLOCK(CONTROL_BLOCK);
   RECORD(METADATA);
-  RECORD(SIGNATURE);
   RECORD(MODULE_NAME);
   RECORD(MODULE_DIRECTORY);
   RECORD(MODULE_MAP_FILE);
@@ -1029,7 +1029,6 @@ void ASTWriter::WriteBlockInfoBlock() {
   BLOCK(OPTIONS_BLOCK);
   RECORD(LANGUAGE_OPTIONS);
   RECORD(TARGET_OPTIONS);
-  RECORD(DIAGNOSTIC_OPTIONS);
   RECORD(FILE_SYSTEM_OPTIONS);
   RECORD(HEADER_SEARCH_OPTIONS);
   RECORD(PREPROCESSOR_OPTIONS);
@@ -1065,7 +1064,6 @@ void ASTWriter::WriteBlockInfoBlock() {
   RECORD(UPDATE_VISIBLE);
   RECORD(DECL_UPDATE_OFFSETS);
   RECORD(DECL_UPDATES);
-  RECORD(DIAG_PRAGMA_MAPPINGS);
   RECORD(CUDA_SPECIAL_DECL_REFS);
   RECORD(HEADER_SEARCH_TABLE);
   RECORD(FP_PRAGMA_OPTIONS);
@@ -1258,6 +1256,11 @@ void ASTWriter::WriteBlockInfoBlock() {
   BLOCK(EXTENSION_BLOCK);
   RECORD(EXTENSION_METADATA);
 
+  BLOCK(UNHASHED_CONTROL_BLOCK);
+  RECORD(SIGNATURE);
+  RECORD(DIAGNOSTIC_OPTIONS);
+  RECORD(DIAG_PRAGMA_MAPPINGS);
+
 #undef RECORD
 #undef BLOCK
   Stream.ExitBlock();
@@ -1320,21 +1323,73 @@ adjustFilenameForRelocatableAST(const char *Filename, StringRef BaseDir) {
   return Filename + Pos;
 }
 
-static ASTFileSignature getSignature() {
-  while (true) {
-    if (ASTFileSignature S = llvm::sys::Process::GetRandomNumber())
-      return S;
-    // Rely on GetRandomNumber to eventually return non-zero...
+ASTFileSignature ASTWriter::createSignature(StringRef Bytes) {
+  // Calculate the hash till start of UNHASHED_CONTROL_BLOCK.
+  llvm::SHA1 Hasher;
+  Hasher.update(ArrayRef<uint8_t>(Bytes.bytes_begin(), Bytes.size()));
+  auto Hash = Hasher.result();
+
+  // Convert to an array [5*i32].
+  ASTFileSignature Signature;
+  auto LShift = [&](unsigned char Val, unsigned Shift) {
+    return (uint32_t)Val << Shift;
+  };
+  for (int I = 0; I != 5; ++I)
+    Signature[I] = LShift(Hash[I * 4 + 0], 24) | LShift(Hash[I * 4 + 1], 16) |
+                   LShift(Hash[I * 4 + 2], 8) | LShift(Hash[I * 4 + 3], 0);
+
+  return Signature;
+}
+
+ASTFileSignature ASTWriter::writeUnhashedControlBlock(Preprocessor &PP,
+                                                      ASTContext &Context) {
+  // Flush first to prepare the PCM hash (signature).
+  Stream.FlushToWord();
+  auto StartOfUnhashedControl = Stream.GetCurrentBitNo() >> 3;
+
+  // Enter the block and prepare to write records.
+  RecordData Record;
+  Stream.EnterSubblock(UNHASHED_CONTROL_BLOCK_ID, 5);
+
+  // For implicit modules, write the hash of the PCM as its signature.
+  ASTFileSignature Signature;
+  if (WritingModule &&
+      PP.getHeaderSearchInfo().getHeaderSearchOpts().ModulesHashContent) {
+    Signature = createSignature(StringRef(Buffer.begin(), StartOfUnhashedControl));
+    Record.append(Signature.begin(), Signature.end());
+    Stream.EmitRecord(SIGNATURE, Record);
+    Record.clear();
   }
+
+  // Diagnostic options.
+  const auto &Diags = Context.getDiagnostics();
+  const DiagnosticOptions &DiagOpts = Diags.getDiagnosticOptions();
+#define DIAGOPT(Name, Bits, Default) Record.push_back(DiagOpts.Name);
+#define ENUM_DIAGOPT(Name, Type, Bits, Default)                                \
+  Record.push_back(static_cast<unsigned>(DiagOpts.get##Name()));
+#include "clang/Basic/DiagnosticOptions.def"
+  Record.push_back(DiagOpts.Warnings.size());
+  for (unsigned I = 0, N = DiagOpts.Warnings.size(); I != N; ++I)
+    AddString(DiagOpts.Warnings[I], Record);
+  Record.push_back(DiagOpts.Remarks.size());
+  for (unsigned I = 0, N = DiagOpts.Remarks.size(); I != N; ++I)
+    AddString(DiagOpts.Remarks[I], Record);
+  // Note: we don't serialize the log or serialization file names, because they
+  // are generally transient files and will almost always be overridden.
+  Stream.EmitRecord(DIAGNOSTIC_OPTIONS, Record);
+
+  // Write out the diagnostic/pragma mappings.
+  WritePragmaDiagnosticMappings(Diags, /* IsModule = */ WritingModule);
+
+  // Leave the options block.
+  Stream.ExitBlock();
+  return Signature;
 }
 
 /// \brief Write the control block.
-uint64_t ASTWriter::WriteControlBlock(Preprocessor &PP,
-                                      ASTContext &Context,
-                                      StringRef isysroot,
-                                      const std::string &OutputFile) {
-  ASTFileSignature Signature = 0;
-
+void ASTWriter::WriteControlBlock(Preprocessor &PP, ASTContext &Context,
+                                  StringRef isysroot,
+                                  const std::string &OutputFile) {
   using namespace llvm;
   Stream.EnterSubblock(CONTROL_BLOCK_ID, 5);
   RecordData Record;
@@ -1362,15 +1417,6 @@ uint64_t ASTWriter::WriteControlBlock(Preprocessor &PP,
                               getClangFullRepositoryVersion());
   }
   if (WritingModule) {
-    // For implicit modules we output a signature that we can use to ensure
-    // duplicate module builds don't collide in the cache as their output order
-    // is non-deterministic.
-    // FIXME: Remove this when output is deterministic.
-    if (Context.getLangOpts().ImplicitModules) {
-      Signature = getSignature();
-      RecordData::value_type Record[] = {Signature};
-      Stream.EmitRecord(SIGNATURE, Record);
-    }
 
     // Module name
     auto Abbrev = std::make_shared<BitCodeAbbrev>();
@@ -1443,9 +1489,15 @@ uint64_t ASTWriter::WriteControlBlock(Preprocessor &PP,
 
       Record.push_back((unsigned)M.Kind); // FIXME: Stable encoding
       AddSourceLocation(M.ImportLoc, Record);
-      Record.push_back(M.File->getSize());
-      Record.push_back(getTimestampForOutput(M.File));
-      Record.push_back(M.Signature);
+
+      // If we have calculated signature, there is no need to store
+      // the size or timestamp.
+      Record.push_back(M.Signature ? 0 : M.File->getSize());
+      Record.push_back(M.Signature ? 0 : getTimestampForOutput(M.File));
+
+      for (auto I : M.Signature)
+        Record.push_back(I);
+
       AddPath(M.FileName, Record);
     }
     Stream.EmitRecord(IMPORTS, Record);
@@ -1508,24 +1560,6 @@ uint64_t ASTWriter::WriteControlBlock(Preprocessor &PP,
   }
   Stream.EmitRecord(TARGET_OPTIONS, Record);
 
-  // Diagnostic options.
-  Record.clear();
-  const DiagnosticOptions &DiagOpts
-    = Context.getDiagnostics().getDiagnosticOptions();
-#define DIAGOPT(Name, Bits, Default) Record.push_back(DiagOpts.Name);
-#define ENUM_DIAGOPT(Name, Type, Bits, Default) \
-  Record.push_back(static_cast<unsigned>(DiagOpts.get##Name()));
-#include "clang/Basic/DiagnosticOptions.def"
-  Record.push_back(DiagOpts.Warnings.size());
-  for (unsigned I = 0, N = DiagOpts.Warnings.size(); I != N; ++I)
-    AddString(DiagOpts.Warnings[I], Record);
-  Record.push_back(DiagOpts.Remarks.size());
-  for (unsigned I = 0, N = DiagOpts.Remarks.size(); I != N; ++I)
-    AddString(DiagOpts.Remarks[I], Record);
-  // Note: we don't serialize the log or serialization file names, because they
-  // are generally transient files and will almost always be overridden.
-  Stream.EmitRecord(DIAGNOSTIC_OPTIONS, Record);
-
   // File system options.
   Record.clear();
   const FileSystemOptions &FSOpts =
@@ -1639,7 +1673,6 @@ uint64_t ASTWriter::WriteControlBlock(Preprocessor &PP,
                   PP.getHeaderSearchInfo().getHeaderSearchOpts(),
                   PP.getLangOpts().Modules);
   Stream.ExitBlock();
-  return Signature;
 }
 
 namespace  {
@@ -4267,9 +4300,10 @@ void ASTWriter::SetSelectorOffset(Selector Sel, uint32_t Offset) {
 }
 
 ASTWriter::ASTWriter(llvm::BitstreamWriter &Stream,
+                     SmallVectorImpl<char> &Buffer,
                      ArrayRef<std::shared_ptr<ModuleFileExtension>> Extensions,
                      bool IncludeTimestamps)
-    : Stream(Stream), IncludeTimestamps(IncludeTimestamps) {
+    : Stream(Stream), Buffer(Buffer), IncludeTimestamps(IncludeTimestamps) {
   for (const auto &Ext : Extensions) {
     if (auto Writer = Ext->createExtensionWriter(*this))
       ModuleFileExtensionWriters.push_back(std::move(Writer));
@@ -4289,9 +4323,10 @@ time_t ASTWriter::getTimestampForOutput(const FileEntry *E) const {
   return IncludeTimestamps ? E->getModificationTime() : 0;
 }
 
-uint64_t ASTWriter::WriteAST(Sema &SemaRef, const std::string &OutputFile,
-                             Module *WritingModule, StringRef isysroot,
-                             bool hasErrors) {
+ASTFileSignature ASTWriter::WriteAST(Sema &SemaRef,
+                                     const std::string &OutputFile,
+                                     Module *WritingModule, StringRef isysroot,
+                                     bool hasErrors) {
   WritingAST = true;
 
   ASTHasCompilerErrors = hasErrors;
@@ -4327,9 +4362,9 @@ static void AddLazyVectorDecls(ASTWriter &Writer, Vector &Vec,
   }
 }
 
-uint64_t ASTWriter::WriteASTCore(Sema &SemaRef, StringRef isysroot,
-                                 const std::string &OutputFile,
-                                 Module *WritingModule) {
+ASTFileSignature ASTWriter::WriteASTCore(Sema &SemaRef, StringRef isysroot,
+                                         const std::string &OutputFile,
+                                         Module *WritingModule) {
   using namespace llvm;
 
   bool isModule = WritingModule != nullptr;
@@ -4477,7 +4512,7 @@ uint64_t ASTWriter::WriteASTCore(Sema &SemaRef, StringRef isysroot,
   }
 
   // Write the control block
-  uint64_t Signature = WriteControlBlock(PP, Context, isysroot, OutputFile);
+  WriteControlBlock(PP, Context, isysroot, OutputFile);
 
   // Write the remaining AST contents.
   Stream.EnterSubblock(AST_BLOCK_ID, 5);
@@ -4694,7 +4729,6 @@ uint64_t ASTWriter::WriteASTCore(Sema &SemaRef, StringRef isysroot,
   WriteOpenCLExtensionTypes(SemaRef);
   WriteOpenCLExtensionDecls(SemaRef);
   WriteCUDAPragmas(SemaRef);
-  WritePragmaDiagnosticMappings(Context.getDiagnostics(), isModule);
 
   // If we're emitting a module, write out the submodule information.  
   if (WritingModule)
@@ -4823,7 +4857,7 @@ uint64_t ASTWriter::WriteASTCore(Sema &SemaRef, StringRef isysroot,
   for (const auto &ExtWriter : ModuleFileExtensionWriters)
     WriteModuleFileExtension(SemaRef, *ExtWriter);
 
-  return Signature;
+  return writeUnhashedControlBlock(PP, Context);
 }
 
 void ASTWriter::WriteDeclUpdatesBlocks(RecordDataImpl &OffsetsRecord) {
diff --git a/clang/lib/Serialization/GeneratePCH.cpp b/clang/lib/Serialization/GeneratePCH.cpp
index 7f1b75055b4..141a5594aed 100644
--- a/clang/lib/Serialization/GeneratePCH.cpp
+++ b/clang/lib/Serialization/GeneratePCH.cpp
@@ -28,7 +28,7 @@ PCHGenerator::PCHGenerator(
     bool AllowASTWithErrors, bool IncludeTimestamps)
     : PP(PP), OutputFile(OutputFile), isysroot(isysroot.str()),
       SemaPtr(nullptr), Buffer(Buffer), Stream(Buffer->Data),
-      Writer(Stream, Extensions, IncludeTimestamps),
+      Writer(Stream, Buffer->Data, Extensions, IncludeTimestamps),
       AllowASTWithErrors(AllowASTWithErrors) {
   Buffer->IsComplete = false;
 }
diff --git a/clang/lib/Serialization/GlobalModuleIndex.cpp b/clang/lib/Serialization/GlobalModuleIndex.cpp
index ae5796ede12..6978e7e0977 100644
--- a/clang/lib/Serialization/GlobalModuleIndex.cpp
+++ b/clang/lib/Serialization/GlobalModuleIndex.cpp
@@ -376,6 +376,15 @@ namespace {
     /// \brief The set of modules on which this module depends. Each entry is
     /// a module ID.
     SmallVector<unsigned, 4> Dependencies;
+    ASTFileSignature Signature;
+  };
+
+  struct ImportedModuleFileInfo {
+    off_t StoredSize;
+    time_t StoredModTime;
+    ASTFileSignature StoredSignature;
+    ImportedModuleFileInfo(off_t Size, time_t ModTime, ASTFileSignature Sig)
+        : StoredSize(Size), StoredModTime(ModTime), StoredSignature(Sig) {}
   };
 
   /// \brief Builder that generates the global module index file.
@@ -383,12 +392,20 @@ namespace {
     FileManager &FileMgr;
     const PCHContainerReader &PCHContainerRdr;
 
-    /// \brief Mapping from files to module file information.
+    /// Mapping from files to module file information.
     typedef llvm::MapVector<const FileEntry *, ModuleFileInfo> ModuleFilesMap;
 
-    /// \brief Information about each of the known module files.
+    /// Information about each of the known module files.
     ModuleFilesMap ModuleFiles;
 
+    /// \brief Mapping from the imported module file to the imported
+    /// information.
+    typedef std::multimap<const FileEntry *, ImportedModuleFileInfo>
+        ImportedModuleFilesMap;
+
+    /// \brief Information about each importing of a module file.
+    ImportedModuleFilesMap ImportedModuleFiles;
+
     /// \brief Mapping from identifiers to the list of module file IDs that
     /// consider this identifier to be interesting.
     typedef llvm::StringMap<SmallVector<unsigned, 2> > InterestingIdentifierMap;
@@ -424,7 +441,8 @@ namespace {
     bool loadModuleFile(const FileEntry *File);
 
     /// \brief Write the index to the given bitstream.
-    void writeIndex(llvm::BitstreamWriter &Stream);
+    /// \returns true if an error occurred, false otherwise.
+    bool writeIndex(llvm::BitstreamWriter &Stream);
   };
 }
 
@@ -515,7 +533,7 @@ bool GlobalModuleIndexBuilder::loadModuleFile(const FileEntry *File) {
   unsigned ID = getModuleFileInfo(File).ID;
 
   // Search for the blocks and records we care about.
-  enum { Other, ControlBlock, ASTBlock } State = Other;
+  enum { Other, ControlBlock, ASTBlock, DiagnosticOptionsBlock } State = Other;
   bool Done = false;
   while (!Done) {
     llvm::BitstreamEntry Entry = InStream.advance();
@@ -553,6 +571,15 @@ bool GlobalModuleIndexBuilder::loadModuleFile(const FileEntry *File) {
         continue;
       }
 
+      if (Entry.ID == UNHASHED_CONTROL_BLOCK_ID) {
+        if (InStream.EnterSubBlock(UNHASHED_CONTROL_BLOCK_ID))
+          return true;
+
+        // Found the Diagnostic Options block.
+        State = DiagnosticOptionsBlock;
+        continue;
+      }
+
       if (InStream.SkipBlock())
         return true;
 
@@ -587,7 +614,10 @@ bool GlobalModuleIndexBuilder::loadModuleFile(const FileEntry *File) {
 
         // Skip the stored signature.
         // FIXME: we could read the signature out of the import and validate it.
-        Idx++;
+        ASTFileSignature StoredSignature = {
+            {{(uint32_t)Record[Idx++], (uint32_t)Record[Idx++],
+              (uint32_t)Record[Idx++], (uint32_t)Record[Idx++],
+              (uint32_t)Record[Idx++]}}};
 
         // Retrieve the imported file name.
         unsigned Length = Record[Idx++];
@@ -599,11 +629,16 @@ bool GlobalModuleIndexBuilder::loadModuleFile(const FileEntry *File) {
         const FileEntry *DependsOnFile
           = FileMgr.getFile(ImportedFile, /*openFile=*/false,
                             /*cacheFailure=*/false);
-        if (!DependsOnFile ||
-            (StoredSize != DependsOnFile->getSize()) ||
-            (StoredModTime != DependsOnFile->getModificationTime()))
+
+        if (!DependsOnFile)
           return true;
 
+        // Save the information in ImportedModuleFileInfo so we can verify after
+        // loading all pcms.
+        ImportedModuleFiles.insert(std::make_pair(
+            DependsOnFile, ImportedModuleFileInfo(StoredSize, StoredModTime,
+                                                  StoredSignature)));
+
         // Record the dependency.
         unsigned DependsOnID = getModuleFileInfo(DependsOnFile).ID;
         getModuleFileInfo(File).Dependencies.push_back(DependsOnID);
@@ -632,6 +667,12 @@ bool GlobalModuleIndexBuilder::loadModuleFile(const FileEntry *File) {
       }
     }
 
+    // Get Signature.
+    if (State == DiagnosticOptionsBlock && Code == SIGNATURE)
+      getModuleFileInfo(File).Signature = {
+          {{(uint32_t)Record[0], (uint32_t)Record[1], (uint32_t)Record[2],
+            (uint32_t)Record[3], (uint32_t)Record[4]}}};
+
     // We don't care about this record.
   }
 
@@ -680,7 +721,20 @@ public:
 
 }
 
-void GlobalModuleIndexBuilder::writeIndex(llvm::BitstreamWriter &Stream) {
+bool GlobalModuleIndexBuilder::writeIndex(llvm::BitstreamWriter &Stream) {
+  for (auto MapEntry : ImportedModuleFiles) {
+    auto *File = MapEntry.first;
+    ImportedModuleFileInfo &Info = MapEntry.second;
+    if (getModuleFileInfo(File).Signature) {
+      if (getModuleFileInfo(File).Signature != Info.StoredSignature)
+        // Verify Signature.
+        return true;
+    } else if (Info.StoredSize != File->getSize() ||
+               Info.StoredModTime != File->getModificationTime())
+      // Verify Size and ModTime.
+      return true;
+  }
+
   using namespace llvm;
   
   // Emit the file header.
@@ -756,6 +810,7 @@ void GlobalModuleIndexBuilder::writeIndex(llvm::BitstreamWriter &Stream) {
   }
 
   Stream.ExitBlock();
+  return false;
 }
 
 GlobalModuleIndex::ErrorCode
@@ -816,7 +871,8 @@ GlobalModuleIndex::writeIndex(FileManager &FileMgr,
   SmallVector<char, 16> OutputBuffer;
   {
     llvm::BitstreamWriter OutputStream(OutputBuffer);
-    Builder.writeIndex(OutputStream);
+    if (Builder.writeIndex(OutputStream))
+      return EC_IOError;
   }
 
   // Write the global index file to a temporary file.