Add an (optional) identification block in the bitcode

Processing bitcode from a different LLVM version can lead to
unexpected behavior. The LLVM project guarantees autoupdating
bitcode from a previous minor revision for the same major, but
can't make any promise when reading bitcode generated from a
either a non-released LLVM, a vendor toolchain, or a "future"
LLVM release. This patch aims at being more user-friendly and
allows a bitcode produce to emit an optional block at the
beginning of the bitcode that will contains an opaque string
intended to describe the bitcode producer information. The
bitcode reader will dump this information alongside any error it
reports.

The optional block also includes an "epoch" number, monotonically
increasing when incompatible changes are made to the bitcode. The
reader will reject bitcode whose epoch is different from the one
expected.

Differential Revision: http://reviews.llvm.org/D13666

From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 251325

include/llvm/Bitcode/LLVMBitCodes.h

@@ -23,33 +23,50 @@
 namespace llvm {
 namespace bitc {
   // The only top-level block type defined is for a module.
-  enum BlockIDs {
-    // Blocks
-    MODULE_BLOCK_ID          = FIRST_APPLICATION_BLOCKID,
+enum BlockIDs {
+  // Blocks
+  MODULE_BLOCK_ID = FIRST_APPLICATION_BLOCKID,
 
-    // Module sub-block id's.
-    PARAMATTR_BLOCK_ID,
-    PARAMATTR_GROUP_BLOCK_ID,
+  // Module sub-block id's.
+  PARAMATTR_BLOCK_ID,
+  PARAMATTR_GROUP_BLOCK_ID,
 
-    CONSTANTS_BLOCK_ID,
-    FUNCTION_BLOCK_ID,
+  CONSTANTS_BLOCK_ID,
+  FUNCTION_BLOCK_ID,
 
-    UNUSED_ID1,
+  // Block intended to contains information on the bitcode versioning.
+  // Can be used to provide better error messages when we fail to parse a
+  // bitcode file.
+  IDENTIFICATION_BLOCK_ID,
 
-    VALUE_SYMTAB_BLOCK_ID,
-    METADATA_BLOCK_ID,
-    METADATA_ATTACHMENT_ID,
+  VALUE_SYMTAB_BLOCK_ID,
+  METADATA_BLOCK_ID,
+  METADATA_ATTACHMENT_ID,
 
-    TYPE_BLOCK_ID_NEW,
+  TYPE_BLOCK_ID_NEW,
 
-    USELIST_BLOCK_ID,
+  USELIST_BLOCK_ID,
 
-    MODULE_STRTAB_BLOCK_ID,
-    FUNCTION_SUMMARY_BLOCK_ID,
+  MODULE_STRTAB_BLOCK_ID,
+  FUNCTION_SUMMARY_BLOCK_ID,
 
-    OPERAND_BUNDLE_TAGS_BLOCK_ID
-  };
+  OPERAND_BUNDLE_TAGS_BLOCK_ID
+};
 
+/// Idenfitication block contains a string that describes the producer details,
+/// and an epoch that defines the auto-upgrade capability.
+enum IdentificationCodes {
+  IDENTIFICATION_CODE_STRING = 1, // IDENTIFICATION:      [strchr x N]
+  IDENTIFICATION_CODE_EPOCH = 2,  // EPOCH:               [epoch#]
+};
+
+/// The epoch that defines the auto-upgrade compatibility for the bitcode.
+///
+/// LLVM guarantees in a major release that a minor release can read bitcode
+/// generated by previous minor releases. We translate this by making the reader
+/// accepting only bitcode with the same epoch, except for the X.0 release which
+/// also accepts N-1.
+enum { BITCODE_CURRENT_EPOCH = 0 };
 
   /// MODULE blocks have a number of optional fields and subblocks.
   enum ModuleCodes {

lib/Bitcode/Reader/BitcodeReader.cpp

@@ -152,6 +152,8 @@ class BitcodeReader : public GVMaterializer {
   uint64_t LastFunctionBlockBit = 0;
   bool SeenValueSymbolTable = false;
   unsigned VSTOffset = 0;
+  // Contains an arbitrary and optional string identifying the bitcode producer
+  std::string ProducerIdentification;
 
   std::vector<Type*> TypeList;
   BitcodeReaderValueList ValueList;
@@ -273,6 +275,11 @@ public:
   void setStripDebugInfo() override;
 
 private:
+  /// Parse the "IDENTIFICATION_BLOCK_ID" block, populate the
+  // ProducerIdentification data member, and do some basic enforcement on the
+  // "epoch" encoded in the bitcode.
+  std::error_code parseBitcodeVersion();
+
   std::vector<StructType *> IdentifiedStructTypes;
   StructType *createIdentifiedStructType(LLVMContext &Context, StringRef Name);
   StructType *createIdentifiedStructType(LLVMContext &Context);
@@ -518,10 +525,21 @@ static std::error_code error(DiagnosticHandlerFunction DiagnosticHandler,
 }
 
 std::error_code BitcodeReader::error(BitcodeError E, const Twine &Message) {
+  if (!ProducerIdentification.empty()) {
+    Twine MsgWithID = Message + " (Producer: '" + ProducerIdentification +
+                      "' Reader: 'LLVM " + LLVM_VERSION_STRING "')";
+    return ::error(DiagnosticHandler, make_error_code(E), MsgWithID);
+  }
   return ::error(DiagnosticHandler, make_error_code(E), Message);
 }
 
 std::error_code BitcodeReader::error(const Twine &Message) {
+  if (!ProducerIdentification.empty()) {
+    Twine MsgWithID = Message + " (Producer: '" + ProducerIdentification +
+                      "' Reader: 'LLVM " + LLVM_VERSION_STRING "')";
+    return ::error(DiagnosticHandler,
+                   make_error_code(BitcodeError::CorruptedBitcode), MsgWithID);
+  }
   return ::error(DiagnosticHandler,
                  make_error_code(BitcodeError::CorruptedBitcode), Message);
 }
@@ -3061,6 +3079,50 @@ std::error_code BitcodeReader::rememberAndSkipFunctionBodies() {
   }
 }
 
+std::error_code BitcodeReader::parseBitcodeVersion() {
+  if (Stream.EnterSubBlock(bitc::IDENTIFICATION_BLOCK_ID))
+    return error("Invalid record");
+
+  // Read all the records.
+  SmallVector<uint64_t, 64> Record;
+  while (1) {
+    BitstreamEntry Entry = Stream.advance();
+
+    switch (Entry.Kind) {
+    default:
+    case BitstreamEntry::Error:
+      return error("Malformed block");
+    case BitstreamEntry::EndBlock:
+      return std::error_code();
+    case BitstreamEntry::Record:
+      // The interesting case.
+      break;
+    }
+
+    // Read a record.
+    Record.clear();
+    unsigned BitCode = Stream.readRecord(Entry.ID, Record);
+    switch (BitCode) {
+    default: // Default behavior: reject
+      return error("Invalid value");
+    case bitc::IDENTIFICATION_CODE_STRING: { // IDENTIFICATION:      [strchr x
+                                             // N]
+      convertToString(Record, 0, ProducerIdentification);
+      break;
+    }
+    case bitc::IDENTIFICATION_CODE_EPOCH: { // EPOCH:      [epoch#]
+      unsigned epoch = (unsigned)Record[0];
+      if (epoch != bitc::BITCODE_CURRENT_EPOCH) {
+        auto BitcodeEpoch = std::to_string(epoch);
+        auto CurrentEpoch = std::to_string(bitc::BITCODE_CURRENT_EPOCH);
+        return error(Twine("Incompatible epoch: Bitcode '") + BitcodeEpoch +
+                     "' vs current: '" + CurrentEpoch + "'");
+      }
+    }
+    }
+  }
+}
+
 std::error_code BitcodeReader::parseModule(uint64_t ResumeBit,
                                            bool ShouldLazyLoadMetadata) {
   if (ResumeBit)
@@ -3552,6 +3614,11 @@ BitcodeReader::parseBitcodeInto(std::unique_ptr<DataStreamer> Streamer,
     if (Entry.Kind != BitstreamEntry::SubBlock)
       return error("Malformed block");
 
+    if (Entry.ID == bitc::IDENTIFICATION_BLOCK_ID) {
+      parseBitcodeVersion();
+      continue;
+    }
+
     if (Entry.ID == bitc::MODULE_BLOCK_ID)
       return parseModule(0, ShouldLazyLoadMetadata);
 

lib/Bitcode/Writer/BitcodeWriter.cpp

@@ -2829,6 +2829,29 @@ static void WriteCombinedFunctionSummary(const FunctionInfoIndex &I,
   Stream.ExitBlock();
 }
 
+// Create the "IDENTIFICATION_BLOCK_ID" containing a single string with the
+// current llvm version, and a record for the epoch number.
+static void WriteIdentificationBlock(const Module *M, BitstreamWriter &Stream) {
+  Stream.EnterSubblock(bitc::IDENTIFICATION_BLOCK_ID, 5);
+
+  // Write the "user readable" string identifying the bitcode producer
+  BitCodeAbbrev *Abbv = new BitCodeAbbrev();
+  Abbv->Add(BitCodeAbbrevOp(bitc::IDENTIFICATION_CODE_STRING));
+  Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array));
+  Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Char6));
+  auto StringAbbrev = Stream.EmitAbbrev(Abbv);
+  WriteStringRecord(bitc::IDENTIFICATION_CODE_STRING,
+                    "LLVM" LLVM_VERSION_STRING, StringAbbrev, Stream);
+
+  // Write the epoch version
+  Abbv = new BitCodeAbbrev();
+  Abbv->Add(BitCodeAbbrevOp(bitc::IDENTIFICATION_CODE_EPOCH));
+  Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6));
+  SmallVector<unsigned, 1> Vals = {bitc::BITCODE_CURRENT_EPOCH};
+  Stream.EmitRecord(bitc::IDENTIFICATION_CODE_EPOCH, Vals);
+  Stream.ExitBlock();
+}
+
 /// WriteModule - Emit the specified module to the bitstream.
 static void WriteModule(const Module *M, BitstreamWriter &Stream,
                         bool ShouldPreserveUseListOrder,
@@ -3000,6 +3023,8 @@ void llvm::WriteBitcodeToFile(const Module *M, raw_ostream &Out,
     // Emit the file header.
     WriteBitcodeHeader(Stream);
 
+    WriteIdentificationBlock(M, Stream);
+
     // Emit the module.
     WriteModule(M, Stream, ShouldPreserveUseListOrder, BitcodeStartBit,
                 EmitFunctionSummary);

test/Bitcode/identification.ll

@@ -0,0 +1,6 @@
+; Check that a block "IDENTIFICATION_BLOCK_ID" is emitted.
+;RUN: llvm-as < %s | llvm-bcanalyzer -dump | FileCheck %s
+;CHECK: <IDENTIFICATION_BLOCK_ID
+;CHECK-NEXT: <STRING
+;CHECK-NEXT: <EPOCH
+;CHECK-NEXT: </IDENTIFICATION_BLOCK_ID

tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp

@@ -110,6 +110,8 @@ static const char *GetBlockName(unsigned BlockID,
   case bitc::TYPE_BLOCK_ID_NEW:        return "TYPE_BLOCK_ID";
   case bitc::CONSTANTS_BLOCK_ID:       return "CONSTANTS_BLOCK";
   case bitc::FUNCTION_BLOCK_ID:        return "FUNCTION_BLOCK";
+  case bitc::IDENTIFICATION_BLOCK_ID:
+    return "IDENTIFICATION_BLOCK_ID";
   case bitc::VALUE_SYMTAB_BLOCK_ID:    return "VALUE_SYMTAB";
   case bitc::METADATA_BLOCK_ID:        return "METADATA_BLOCK";
   case bitc::METADATA_ATTACHMENT_ID:   return "METADATA_ATTACHMENT_BLOCK";
@@ -170,6 +172,13 @@ static const char *GetCodeName(unsigned CodeID, unsigned BlockID,
       STRINGIFY_CODE(MODULE_CODE, GCNAME)
       STRINGIFY_CODE(MODULE_CODE, VSTOFFSET)
     }
+  case bitc::IDENTIFICATION_BLOCK_ID:
+    switch (CodeID) {
+    default:
+      return nullptr;
+      STRINGIFY_CODE(IDENTIFICATION_CODE, STRING)
+      STRINGIFY_CODE(IDENTIFICATION_CODE, EPOCH)
+    }
   case bitc::PARAMATTR_BLOCK_ID:
     switch (CodeID) {
     default: return nullptr;