[CodeView] Refactor / Rewrite TypeSerializer and TypeTableBuilder.

The motivation behind this patch is that future directions require us to
be able to compute the hash value of records independently of actually
using them for de-duplication.

The current structure of TypeSerializer / TypeTableBuilder being a
single entry point that takes an unserialized type record, and then
hashes and de-duplicates it is not flexible enough to allow this.

At the same time, the existing TypeSerializer is already extremely
complex for this very reason -- it tries to be too many things. In
addition to serializing, hashing, and de-duplicating, ti also supports
splitting up field list records and adding continuations. All of this
functionality crammed into this one class makes it very complicated to
work with and hard to maintain.

To solve all of these problems, I've re-written everything from scratch
and split the functionality into separate pieces that can easily be
reused. The end result is that one class TypeSerializer is turned into 3
new classes SimpleTypeSerializer, ContinuationRecordBuilder, and
TypeTableBuilder, each of which in isolation is simple and
straightforward.

A quick summary of these new classes and their responsibilities are:

- SimpleTypeSerializer : Turns a non-FieldList leaf type into a series of
  bytes. Does not do any hashing. Every time you call it, it will
  re-serialize and return bytes again. The same instance can be re-used
  over and over to avoid re-allocations, and in exchange for this
  optimization the bytes returned by the serializer only live until the
  caller attempts to serialize a new record.

- ContinuationRecordBuilder : Turns a FieldList-like record into a series
  of fragments. Does not do any hashing. Like SimpleTypeSerializer,
  returns references to privately owned bytes, so the storage is
  invalidated as soon as the caller tries to re-use the instance. Works
  equally well for LF_FIELDLIST as it does for LF_METHODLIST, solving a
  long-standing theoretical limitation of the previous implementation.

- TypeTableBuilder : Accepts sequences of bytes that the user has already
  serialized, and inserts them by de-duplicating with a hash table. For
  the sake of convenience and efficiency, this class internally stores a
  SimpleTypeSerializer so that it can accept unserialized records. The
  same is not true of ContinuationRecordBuilder. The user is required to
  create their own instance of ContinuationRecordBuilder.

Differential Revision: https://reviews.llvm.org/D40518

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319198 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 20 insertions, 24 deletions

diff --git a/lib/ObjectYAML/CodeViewYAMLTypes.cpp b/lib/ObjectYAML/CodeViewYAMLTypes.cpp
index 81046b21786..84b52b463c4 100644
--- a/lib/ObjectYAML/CodeViewYAMLTypes.cpp
+++ b/lib/ObjectYAML/CodeViewYAMLTypes.cpp
@@ -20,6 +20,7 @@
 #include "llvm/DebugInfo/CodeView/CVTypeVisitor.h"
 #include "llvm/DebugInfo/CodeView/CodeView.h"
 #include "llvm/DebugInfo/CodeView/CodeViewError.h"
+#include "llvm/DebugInfo/CodeView/ContinuationRecordBuilder.h"
 #include "llvm/DebugInfo/CodeView/TypeDeserializer.h"
 #include "llvm/DebugInfo/CodeView/TypeIndex.h"
 #include "llvm/DebugInfo/CodeView/TypeTableBuilder.h"
@@ -82,7 +83,7 @@ struct LeafRecordBase {
   virtual ~LeafRecordBase() = default;
 
   virtual void map(yaml::IO &io) = 0;
-  virtual CVType toCodeViewRecord(TypeTableBuilder &TTB) const = 0;
+  virtual CVType toCodeViewRecord(TypeTableBuilder &TS) const = 0;
   virtual Error fromCodeViewRecord(CVType Type) = 0;
 };
 
@@ -96,9 +97,9 @@ template <typename T> struct LeafRecordImpl : public LeafRecordBase {
     return TypeDeserializer::deserializeAs<T>(Type, Record);
   }
 
-  CVType toCodeViewRecord(TypeTableBuilder &TTB) const override {
-    TTB.writeKnownType(Record);
-    return CVType(Kind, TTB.records().back());
+  CVType toCodeViewRecord(TypeTableBuilder &TS) const override {
+    TS.writeLeafType(Record);
+    return CVType(Kind, TS.records().back());
   }
 
   mutable T Record;
@@ -108,7 +109,7 @@ template <> struct LeafRecordImpl<FieldListRecord> : public LeafRecordBase {
   explicit LeafRecordImpl(TypeLeafKind K) : LeafRecordBase(K) {}
 
   void map(yaml::IO &io) override;
-  CVType toCodeViewRecord(TypeTableBuilder &TTB) const override;
+  CVType toCodeViewRecord(TypeTableBuilder &TS) const override;
   Error fromCodeViewRecord(CVType Type) override;
 
   std::vector<MemberRecord> Members;
@@ -121,7 +122,7 @@ struct MemberRecordBase {
   virtual ~MemberRecordBase() = default;
 
   virtual void map(yaml::IO &io) = 0;
-  virtual void writeTo(FieldListRecordBuilder &FLRB) = 0;
+  virtual void writeTo(ContinuationRecordBuilder &CRB) = 0;
 };
 
 template <typename T> struct MemberRecordImpl : public MemberRecordBase {
@@ -130,8 +131,8 @@ template <typename T> struct MemberRecordImpl : public MemberRecordBase {
 
   void map(yaml::IO &io) override;
 
-  void writeTo(FieldListRecordBuilder &FLRB) override {
-    FLRB.writeMemberType(Record);
+  void writeTo(ContinuationRecordBuilder &CRB) override {
+    CRB.writeMemberType(Record);
   }
 
   mutable T Record;
@@ -489,14 +490,14 @@ Error LeafRecordImpl<FieldListRecord>::fromCodeViewRecord(CVType Type) {
 }
 
 CVType
-LeafRecordImpl<FieldListRecord>::toCodeViewRecord(TypeTableBuilder &TTB) const {
-  FieldListRecordBuilder FLRB(TTB);
-  FLRB.begin();
+LeafRecordImpl<FieldListRecord>::toCodeViewRecord(TypeTableBuilder &TS) const {
+  ContinuationRecordBuilder CRB;
+  CRB.begin(ContinuationRecordKind::FieldList);
   for (const auto &Member : Members) {
-    Member.Member->writeTo(FLRB);
+    Member.Member->writeTo(CRB);
   }
-  FLRB.end(true);
-  return CVType(Kind, TTB.records().back());
+  TS.insertRecord(CRB);
+  return CVType(Kind, TS.records().back());
 }
 
 void MappingTraits<OneMethodRecord>::mapping(IO &io, OneMethodRecord &Record) {
@@ -681,13 +682,8 @@ Expected<LeafRecord> LeafRecord::fromCodeViewRecord(CVType Type) {
   return make_error<CodeViewError>(cv_error_code::corrupt_record);
 }
 
-CVType LeafRecord::toCodeViewRecord(BumpPtrAllocator &Alloc) const {
-  TypeTableBuilder TTB(Alloc);
-  return Leaf->toCodeViewRecord(TTB);
-}
-
-CVType LeafRecord::toCodeViewRecord(TypeTableBuilder &TTB) const {
-  return Leaf->toCodeViewRecord(TTB);
+CVType LeafRecord::toCodeViewRecord(TypeTableBuilder &Serializer) const {
+  return Leaf->toCodeViewRecord(Serializer);
 }
 
 namespace llvm {
@@ -786,10 +782,10 @@ llvm::CodeViewYAML::fromDebugT(ArrayRef<uint8_t> DebugT) {
 
 ArrayRef<uint8_t> llvm::CodeViewYAML::toDebugT(ArrayRef<LeafRecord> Leafs,
                                                BumpPtrAllocator &Alloc) {
-  TypeTableBuilder TTB(Alloc, false);
+  TypeTableBuilder TS(Alloc, false);
   uint32_t Size = sizeof(uint32_t);
   for (const auto &Leaf : Leafs) {
-    CVType T = Leaf.toCodeViewRecord(TTB);
+    CVType T = Leaf.Leaf->toCodeViewRecord(TS);
     Size += T.length();
     assert(T.length() % 4 == 0 && "Improper type record alignment!");
   }
@@ -798,7 +794,7 @@ ArrayRef<uint8_t> llvm::CodeViewYAML::toDebugT(ArrayRef<LeafRecord> Leafs,
   BinaryStreamWriter Writer(Output, support::little);
   ExitOnError Err("Error writing type record to .debug$T section");
   Err(Writer.writeInteger<uint32_t>(COFF::DEBUG_SECTION_MAGIC));
-  for (const auto &R : TTB.records()) {
+  for (const auto &R : TS.records()) {
     Err(Writer.writeBytes(R));
   }
   assert(Writer.bytesRemaining() == 0 && "Didn't write all type record bytes!");