2017-05-13 03:18:12 +08:00
|
|
|
//===- llvm/unittest/DebugInfo/CodeView/RandomAccessVisitorTest.cpp -------===//
|
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2017-12-01 02:39:50 +08:00
|
|
|
#include "llvm/DebugInfo/CodeView/AppendingTypeTableBuilder.h"
|
2017-05-13 03:18:12 +08:00
|
|
|
#include "llvm/DebugInfo/CodeView/CVTypeVisitor.h"
|
2017-05-20 03:26:58 +08:00
|
|
|
#include "llvm/DebugInfo/CodeView/LazyRandomTypeCollection.h"
|
2017-05-13 03:18:12 +08:00
|
|
|
#include "llvm/DebugInfo/CodeView/TypeRecord.h"
|
|
|
|
#include "llvm/DebugInfo/CodeView/TypeRecordMapping.h"
|
|
|
|
#include "llvm/DebugInfo/CodeView/TypeVisitorCallbacks.h"
|
|
|
|
#include "llvm/DebugInfo/PDB/Native/RawTypes.h"
|
|
|
|
#include "llvm/Support/Allocator.h"
|
|
|
|
#include "llvm/Support/BinaryItemStream.h"
|
|
|
|
#include "llvm/Support/Error.h"
|
2017-06-15 00:41:50 +08:00
|
|
|
#include "llvm/Testing/Support/Error.h"
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
#include "gtest/gtest.h"
|
|
|
|
|
|
|
|
using namespace llvm;
|
|
|
|
using namespace llvm::codeview;
|
|
|
|
using namespace llvm::pdb;
|
|
|
|
|
|
|
|
namespace llvm {
|
|
|
|
namespace codeview {
|
|
|
|
inline bool operator==(const ArrayRecord &R1, const ArrayRecord &R2) {
|
|
|
|
if (R1.ElementType != R2.ElementType)
|
|
|
|
return false;
|
|
|
|
if (R1.IndexType != R2.IndexType)
|
|
|
|
return false;
|
|
|
|
if (R1.Name != R2.Name)
|
|
|
|
return false;
|
|
|
|
if (R1.Size != R2.Size)
|
|
|
|
return false;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
inline bool operator!=(const ArrayRecord &R1, const ArrayRecord &R2) {
|
|
|
|
return !(R1 == R2);
|
|
|
|
}
|
|
|
|
|
|
|
|
inline bool operator==(const CVType &R1, const CVType &R2) {
|
|
|
|
if (R1.Type != R2.Type)
|
|
|
|
return false;
|
|
|
|
if (R1.RecordData != R2.RecordData)
|
|
|
|
return false;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
inline bool operator!=(const CVType &R1, const CVType &R2) {
|
|
|
|
return !(R1 == R2);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
namespace llvm {
|
|
|
|
template <> struct BinaryItemTraits<CVType> {
|
|
|
|
static size_t length(const CVType &Item) { return Item.length(); }
|
|
|
|
static ArrayRef<uint8_t> bytes(const CVType &Item) { return Item.data(); }
|
|
|
|
};
|
|
|
|
}
|
|
|
|
|
|
|
|
namespace {
|
|
|
|
|
|
|
|
class MockCallbacks : public TypeVisitorCallbacks {
|
|
|
|
public:
|
|
|
|
virtual Error visitTypeBegin(CVType &CVR, TypeIndex Index) {
|
|
|
|
Indices.push_back(Index);
|
|
|
|
return Error::success();
|
|
|
|
}
|
|
|
|
virtual Error visitKnownRecord(CVType &CVR, ArrayRecord &AR) {
|
|
|
|
VisitedRecords.push_back(AR);
|
|
|
|
RawRecords.push_back(CVR);
|
|
|
|
return Error::success();
|
|
|
|
}
|
|
|
|
|
|
|
|
uint32_t count() const {
|
|
|
|
assert(Indices.size() == RawRecords.size());
|
|
|
|
assert(Indices.size() == VisitedRecords.size());
|
|
|
|
return Indices.size();
|
|
|
|
}
|
|
|
|
std::vector<TypeIndex> Indices;
|
|
|
|
std::vector<CVType> RawRecords;
|
|
|
|
std::vector<ArrayRecord> VisitedRecords;
|
|
|
|
};
|
|
|
|
|
|
|
|
class RandomAccessVisitorTest : public testing::Test {
|
|
|
|
public:
|
|
|
|
RandomAccessVisitorTest() {}
|
|
|
|
|
|
|
|
static void SetUpTestCase() {
|
|
|
|
GlobalState = llvm::make_unique<GlobalTestState>();
|
|
|
|
|
2017-12-01 02:39:50 +08:00
|
|
|
AppendingTypeTableBuilder Builder(GlobalState->Allocator);
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
uint32_t Offset = 0;
|
|
|
|
for (int I = 0; I < 11; ++I) {
|
|
|
|
ArrayRecord AR(TypeRecordKind::Array);
|
|
|
|
AR.ElementType = TypeIndex::Int32();
|
|
|
|
AR.IndexType = TypeIndex::UInt32();
|
|
|
|
AR.Size = I;
|
|
|
|
std::string Name;
|
|
|
|
raw_string_ostream Stream(Name);
|
|
|
|
Stream << "Array [" << I << "]";
|
|
|
|
AR.Name = GlobalState->Strings.save(Stream.str());
|
|
|
|
GlobalState->Records.push_back(AR);
|
[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
llvm-svn: 319198
2017-11-29 02:33:17 +08:00
|
|
|
GlobalState->Indices.push_back(Builder.writeLeafType(AR));
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
CVType Type(TypeLeafKind::LF_ARRAY, Builder.records().back());
|
|
|
|
GlobalState->TypeVector.push_back(Type);
|
|
|
|
|
|
|
|
GlobalState->AllOffsets.push_back(
|
|
|
|
{GlobalState->Indices.back(), ulittle32_t(Offset)});
|
|
|
|
Offset += Type.length();
|
|
|
|
}
|
|
|
|
|
|
|
|
GlobalState->ItemStream.setItems(GlobalState->TypeVector);
|
|
|
|
GlobalState->TypeArray = VarStreamArray<CVType>(GlobalState->ItemStream);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void TearDownTestCase() { GlobalState.reset(); }
|
|
|
|
|
|
|
|
void SetUp() override {
|
|
|
|
TestState = llvm::make_unique<PerTestState>();
|
|
|
|
}
|
|
|
|
|
|
|
|
void TearDown() override { TestState.reset(); }
|
|
|
|
|
|
|
|
protected:
|
2017-05-20 03:26:58 +08:00
|
|
|
bool ValidateDatabaseRecord(LazyRandomTypeCollection &Types, uint32_t Index) {
|
2017-05-13 03:18:12 +08:00
|
|
|
TypeIndex TI = TypeIndex::fromArrayIndex(Index);
|
2017-05-20 03:26:58 +08:00
|
|
|
if (!Types.contains(TI))
|
2017-05-13 03:18:12 +08:00
|
|
|
return false;
|
2017-05-20 03:26:58 +08:00
|
|
|
if (GlobalState->TypeVector[Index] != Types.getType(TI))
|
2017-05-13 03:18:12 +08:00
|
|
|
return false;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool ValidateVisitedRecord(uint32_t VisitationOrder,
|
|
|
|
uint32_t GlobalArrayIndex) {
|
|
|
|
TypeIndex TI = TypeIndex::fromArrayIndex(GlobalArrayIndex);
|
|
|
|
if (TI != TestState->Callbacks.Indices[VisitationOrder])
|
|
|
|
return false;
|
|
|
|
|
|
|
|
if (GlobalState->TypeVector[TI.toArrayIndex()] !=
|
|
|
|
TestState->Callbacks.RawRecords[VisitationOrder])
|
|
|
|
return false;
|
|
|
|
|
|
|
|
if (GlobalState->Records[TI.toArrayIndex()] !=
|
|
|
|
TestState->Callbacks.VisitedRecords[VisitationOrder])
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct GlobalTestState {
|
|
|
|
GlobalTestState() : Strings(Allocator), ItemStream(llvm::support::little) {}
|
|
|
|
|
|
|
|
BumpPtrAllocator Allocator;
|
|
|
|
StringSaver Strings;
|
|
|
|
|
|
|
|
std::vector<ArrayRecord> Records;
|
|
|
|
std::vector<TypeIndex> Indices;
|
|
|
|
std::vector<TypeIndexOffset> AllOffsets;
|
|
|
|
std::vector<CVType> TypeVector;
|
|
|
|
BinaryItemStream<CVType> ItemStream;
|
|
|
|
VarStreamArray<CVType> TypeArray;
|
|
|
|
|
|
|
|
MutableBinaryByteStream Stream;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct PerTestState {
|
|
|
|
FixedStreamArray<TypeIndexOffset> Offsets;
|
|
|
|
|
|
|
|
MockCallbacks Callbacks;
|
|
|
|
};
|
|
|
|
|
|
|
|
FixedStreamArray<TypeIndexOffset>
|
|
|
|
createPartialOffsets(MutableBinaryByteStream &Storage,
|
|
|
|
std::initializer_list<uint32_t> Indices) {
|
|
|
|
|
|
|
|
uint32_t Count = Indices.size();
|
|
|
|
uint32_t Size = Count * sizeof(TypeIndexOffset);
|
|
|
|
uint8_t *Buffer = GlobalState->Allocator.Allocate<uint8_t>(Size);
|
|
|
|
MutableArrayRef<uint8_t> Bytes(Buffer, Size);
|
|
|
|
Storage = MutableBinaryByteStream(Bytes, support::little);
|
|
|
|
BinaryStreamWriter Writer(Storage);
|
|
|
|
for (const auto I : Indices)
|
|
|
|
consumeError(Writer.writeObject(GlobalState->AllOffsets[I]));
|
|
|
|
|
|
|
|
BinaryStreamReader Reader(Storage);
|
|
|
|
FixedStreamArray<TypeIndexOffset> Result;
|
|
|
|
consumeError(Reader.readArray(Result, Count));
|
|
|
|
return Result;
|
|
|
|
}
|
|
|
|
|
|
|
|
static std::unique_ptr<GlobalTestState> GlobalState;
|
|
|
|
std::unique_ptr<PerTestState> TestState;
|
|
|
|
};
|
|
|
|
|
|
|
|
std::unique_ptr<RandomAccessVisitorTest::GlobalTestState>
|
|
|
|
RandomAccessVisitorTest::GlobalState;
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(RandomAccessVisitorTest, MultipleVisits) {
|
|
|
|
TestState->Offsets = createPartialOffsets(GlobalState->Stream, {0, 8});
|
2017-05-20 03:26:58 +08:00
|
|
|
LazyRandomTypeCollection Types(GlobalState->TypeArray,
|
|
|
|
GlobalState->TypeVector.size(),
|
|
|
|
TestState->Offsets);
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
std::vector<uint32_t> IndicesToVisit = {5, 5, 5};
|
|
|
|
|
|
|
|
for (uint32_t I : IndicesToVisit) {
|
|
|
|
TypeIndex TI = TypeIndex::fromArrayIndex(I);
|
2017-05-20 03:26:58 +08:00
|
|
|
CVType T = Types.getType(TI);
|
2017-06-15 00:41:50 +08:00
|
|
|
EXPECT_THAT_ERROR(codeview::visitTypeRecord(T, TI, TestState->Callbacks),
|
|
|
|
Succeeded());
|
2017-05-13 03:18:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// [0,8) should be present
|
2017-05-20 03:26:58 +08:00
|
|
|
EXPECT_EQ(8u, Types.size());
|
2017-05-13 03:18:12 +08:00
|
|
|
for (uint32_t I = 0; I < 8; ++I)
|
2017-05-20 03:26:58 +08:00
|
|
|
EXPECT_TRUE(ValidateDatabaseRecord(Types, I));
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
// 5, 5, 5
|
2017-05-13 08:11:39 +08:00
|
|
|
EXPECT_EQ(3u, TestState->Callbacks.count());
|
2017-05-13 03:18:12 +08:00
|
|
|
for (auto I : enumerate(IndicesToVisit))
|
|
|
|
EXPECT_TRUE(ValidateVisitedRecord(I.index(), I.value()));
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(RandomAccessVisitorTest, DescendingWithinChunk) {
|
|
|
|
// Visit multiple items from the same "chunk" in reverse order. In this
|
|
|
|
// example, it's 7 then 4 then 2. At the end, all records from 0 to 7 should
|
|
|
|
// be known by the database, but only 2, 4, and 7 should have been visited.
|
|
|
|
TestState->Offsets = createPartialOffsets(GlobalState->Stream, {0, 8});
|
|
|
|
|
|
|
|
std::vector<uint32_t> IndicesToVisit = {7, 4, 2};
|
|
|
|
|
2017-05-20 03:26:58 +08:00
|
|
|
LazyRandomTypeCollection Types(GlobalState->TypeArray,
|
|
|
|
GlobalState->TypeVector.size(),
|
|
|
|
TestState->Offsets);
|
2017-05-13 03:18:12 +08:00
|
|
|
for (uint32_t I : IndicesToVisit) {
|
|
|
|
TypeIndex TI = TypeIndex::fromArrayIndex(I);
|
2017-05-20 03:26:58 +08:00
|
|
|
CVType T = Types.getType(TI);
|
2017-06-15 00:41:50 +08:00
|
|
|
EXPECT_THAT_ERROR(codeview::visitTypeRecord(T, TI, TestState->Callbacks),
|
|
|
|
Succeeded());
|
2017-05-13 03:18:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// [0, 7]
|
2017-05-20 03:26:58 +08:00
|
|
|
EXPECT_EQ(8u, Types.size());
|
2017-05-13 03:18:12 +08:00
|
|
|
for (uint32_t I = 0; I < 8; ++I)
|
2017-05-20 03:26:58 +08:00
|
|
|
EXPECT_TRUE(ValidateDatabaseRecord(Types, I));
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
// 2, 4, 7
|
2017-05-13 08:11:39 +08:00
|
|
|
EXPECT_EQ(3u, TestState->Callbacks.count());
|
2017-05-13 03:18:12 +08:00
|
|
|
for (auto I : enumerate(IndicesToVisit))
|
|
|
|
EXPECT_TRUE(ValidateVisitedRecord(I.index(), I.value()));
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(RandomAccessVisitorTest, AscendingWithinChunk) {
|
|
|
|
// * Visit multiple items from the same chunk in ascending order, ensuring
|
|
|
|
// that intermediate items are not visited. In the below example, it's
|
|
|
|
// 5 -> 6 -> 7 which come from the [4,8) chunk.
|
|
|
|
TestState->Offsets = createPartialOffsets(GlobalState->Stream, {0, 8});
|
|
|
|
|
|
|
|
std::vector<uint32_t> IndicesToVisit = {2, 4, 7};
|
|
|
|
|
2017-05-20 03:26:58 +08:00
|
|
|
LazyRandomTypeCollection Types(GlobalState->TypeArray,
|
|
|
|
GlobalState->TypeVector.size(),
|
|
|
|
TestState->Offsets);
|
2017-05-13 03:18:12 +08:00
|
|
|
for (uint32_t I : IndicesToVisit) {
|
|
|
|
TypeIndex TI = TypeIndex::fromArrayIndex(I);
|
2017-05-20 03:26:58 +08:00
|
|
|
CVType T = Types.getType(TI);
|
2017-06-15 00:41:50 +08:00
|
|
|
EXPECT_THAT_ERROR(codeview::visitTypeRecord(T, TI, TestState->Callbacks),
|
|
|
|
Succeeded());
|
2017-05-13 03:18:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// [0, 7]
|
2017-05-20 03:26:58 +08:00
|
|
|
EXPECT_EQ(8u, Types.size());
|
2017-05-13 03:18:12 +08:00
|
|
|
for (uint32_t I = 0; I < 8; ++I)
|
2017-05-20 03:26:58 +08:00
|
|
|
EXPECT_TRUE(ValidateDatabaseRecord(Types, I));
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
// 2, 4, 7
|
2017-05-13 08:11:39 +08:00
|
|
|
EXPECT_EQ(3u, TestState->Callbacks.count());
|
2017-05-13 03:18:12 +08:00
|
|
|
for (auto &I : enumerate(IndicesToVisit))
|
|
|
|
EXPECT_TRUE(ValidateVisitedRecord(I.index(), I.value()));
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(RandomAccessVisitorTest, StopPrematurelyInChunk) {
|
|
|
|
// * Don't visit the last item in one chunk, ensuring that visitation stops
|
|
|
|
// at the record you specify, and the chunk is only partially visited.
|
|
|
|
// In the below example, this is tested by visiting 0 and 1 but not 2,
|
|
|
|
// all from the [0,3) chunk.
|
|
|
|
TestState->Offsets = createPartialOffsets(GlobalState->Stream, {0, 8});
|
|
|
|
|
|
|
|
std::vector<uint32_t> IndicesToVisit = {0, 1, 2};
|
|
|
|
|
2017-05-20 03:26:58 +08:00
|
|
|
LazyRandomTypeCollection Types(GlobalState->TypeArray,
|
|
|
|
GlobalState->TypeVector.size(),
|
|
|
|
TestState->Offsets);
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
for (uint32_t I : IndicesToVisit) {
|
|
|
|
TypeIndex TI = TypeIndex::fromArrayIndex(I);
|
2017-05-20 03:26:58 +08:00
|
|
|
CVType T = Types.getType(TI);
|
2017-06-15 00:41:50 +08:00
|
|
|
EXPECT_THAT_ERROR(codeview::visitTypeRecord(T, TI, TestState->Callbacks),
|
|
|
|
Succeeded());
|
2017-05-13 03:18:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// [0, 8) should be visited.
|
2017-05-20 03:26:58 +08:00
|
|
|
EXPECT_EQ(8u, Types.size());
|
2017-05-13 03:18:12 +08:00
|
|
|
for (uint32_t I = 0; I < 8; ++I)
|
2017-05-20 03:26:58 +08:00
|
|
|
EXPECT_TRUE(ValidateDatabaseRecord(Types, I));
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
// [0, 2]
|
2017-05-13 08:11:39 +08:00
|
|
|
EXPECT_EQ(3u, TestState->Callbacks.count());
|
2017-05-13 03:18:12 +08:00
|
|
|
for (auto I : enumerate(IndicesToVisit))
|
|
|
|
EXPECT_TRUE(ValidateVisitedRecord(I.index(), I.value()));
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(RandomAccessVisitorTest, InnerChunk) {
|
|
|
|
// Test that when a request comes from a chunk in the middle of the partial
|
|
|
|
// offsets array, that items from surrounding chunks are not visited or
|
|
|
|
// added to the database.
|
|
|
|
TestState->Offsets = createPartialOffsets(GlobalState->Stream, {0, 4, 9});
|
|
|
|
|
|
|
|
std::vector<uint32_t> IndicesToVisit = {5, 7};
|
|
|
|
|
2017-05-20 03:26:58 +08:00
|
|
|
LazyRandomTypeCollection Types(GlobalState->TypeArray,
|
|
|
|
GlobalState->TypeVector.size(),
|
|
|
|
TestState->Offsets);
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
for (uint32_t I : IndicesToVisit) {
|
|
|
|
TypeIndex TI = TypeIndex::fromArrayIndex(I);
|
2017-05-20 03:26:58 +08:00
|
|
|
CVType T = Types.getType(TI);
|
2017-06-15 00:41:50 +08:00
|
|
|
EXPECT_THAT_ERROR(codeview::visitTypeRecord(T, TI, TestState->Callbacks),
|
|
|
|
Succeeded());
|
2017-05-13 03:18:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// [4, 9)
|
2017-05-20 03:26:58 +08:00
|
|
|
EXPECT_EQ(5u, Types.size());
|
2017-05-13 03:18:12 +08:00
|
|
|
for (uint32_t I = 4; I < 9; ++I)
|
2017-05-20 03:26:58 +08:00
|
|
|
EXPECT_TRUE(ValidateDatabaseRecord(Types, I));
|
2017-05-13 03:18:12 +08:00
|
|
|
|
|
|
|
// 5, 7
|
2017-05-13 08:11:39 +08:00
|
|
|
EXPECT_EQ(2u, TestState->Callbacks.count());
|
2017-05-13 03:18:12 +08:00
|
|
|
for (auto &I : enumerate(IndicesToVisit))
|
|
|
|
EXPECT_TRUE(ValidateVisitedRecord(I.index(), I.value()));
|
|
|
|
}
|
[CodeView] Fix random access of type names.
Suppose we had a type index offsets array with a boundary at type index
N. Then you request the name of the type with index N+1, and that name
requires the name of index N-1 (think a parameter list, for example). We
didn't handle this, and we would print something like (<unknown UDT>,
<unknown UDT>).
The fix for this is not entirely trivial, and speaks to a larger
problem. I think we need to kill TypeDatabase, or at the very least kill
TypeDatabaseVisitor. We need a thing that doesn't do any caching
whatsoever, just given a type index it can compute the type name "the
slow way". The reason for the bug is that we don't have anything like
that. Everything goes through the type database, and if we've visited a
record, then we're "done". It doesn't know how to do the expensive thing
of re-visiting dependent records if they've not yet been visited.
What I've done here is more or less copied the code (albeit greatly
simplified) from TypeDatabaseVisitor, but wrapped it in an interface
that just returns a std::string. The logic of caching the name is now in
LazyRandomTypeCollection. Eventually I'd like to move the record
database here as well and the visited record bitfield here as well, at
which point we can actually just delete TypeDatabase. I don't see any
reason for it if a "sequential" collection is just a special case of a
random access collection with an empty partial offsets array.
Differential Revision: https://reviews.llvm.org/D34297
llvm-svn: 305612
2017-06-17 07:42:44 +08:00
|
|
|
|
|
|
|
TEST_F(RandomAccessVisitorTest, CrossChunkName) {
|
2017-12-01 02:39:50 +08:00
|
|
|
AppendingTypeTableBuilder Builder(GlobalState->Allocator);
|
[CodeView] Fix random access of type names.
Suppose we had a type index offsets array with a boundary at type index
N. Then you request the name of the type with index N+1, and that name
requires the name of index N-1 (think a parameter list, for example). We
didn't handle this, and we would print something like (<unknown UDT>,
<unknown UDT>).
The fix for this is not entirely trivial, and speaks to a larger
problem. I think we need to kill TypeDatabase, or at the very least kill
TypeDatabaseVisitor. We need a thing that doesn't do any caching
whatsoever, just given a type index it can compute the type name "the
slow way". The reason for the bug is that we don't have anything like
that. Everything goes through the type database, and if we've visited a
record, then we're "done". It doesn't know how to do the expensive thing
of re-visiting dependent records if they've not yet been visited.
What I've done here is more or less copied the code (albeit greatly
simplified) from TypeDatabaseVisitor, but wrapped it in an interface
that just returns a std::string. The logic of caching the name is now in
LazyRandomTypeCollection. Eventually I'd like to move the record
database here as well and the visited record bitfield here as well, at
which point we can actually just delete TypeDatabase. I don't see any
reason for it if a "sequential" collection is just a special case of a
random access collection with an empty partial offsets array.
Differential Revision: https://reviews.llvm.org/D34297
llvm-svn: 305612
2017-06-17 07:42:44 +08:00
|
|
|
|
|
|
|
// TypeIndex 0
|
|
|
|
ClassRecord Class(TypeRecordKind::Class);
|
|
|
|
Class.Name = "FooClass";
|
|
|
|
Class.Options = ClassOptions::None;
|
|
|
|
Class.MemberCount = 0;
|
2017-06-20 05:59:09 +08:00
|
|
|
Class.Size = 4U;
|
[CodeView] Fix random access of type names.
Suppose we had a type index offsets array with a boundary at type index
N. Then you request the name of the type with index N+1, and that name
requires the name of index N-1 (think a parameter list, for example). We
didn't handle this, and we would print something like (<unknown UDT>,
<unknown UDT>).
The fix for this is not entirely trivial, and speaks to a larger
problem. I think we need to kill TypeDatabase, or at the very least kill
TypeDatabaseVisitor. We need a thing that doesn't do any caching
whatsoever, just given a type index it can compute the type name "the
slow way". The reason for the bug is that we don't have anything like
that. Everything goes through the type database, and if we've visited a
record, then we're "done". It doesn't know how to do the expensive thing
of re-visiting dependent records if they've not yet been visited.
What I've done here is more or less copied the code (albeit greatly
simplified) from TypeDatabaseVisitor, but wrapped it in an interface
that just returns a std::string. The logic of caching the name is now in
LazyRandomTypeCollection. Eventually I'd like to move the record
database here as well and the visited record bitfield here as well, at
which point we can actually just delete TypeDatabase. I don't see any
reason for it if a "sequential" collection is just a special case of a
random access collection with an empty partial offsets array.
Differential Revision: https://reviews.llvm.org/D34297
llvm-svn: 305612
2017-06-17 07:42:44 +08:00
|
|
|
Class.DerivationList = TypeIndex::fromArrayIndex(0);
|
|
|
|
Class.FieldList = TypeIndex::fromArrayIndex(0);
|
|
|
|
Class.VTableShape = TypeIndex::fromArrayIndex(0);
|
[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
llvm-svn: 319198
2017-11-29 02:33:17 +08:00
|
|
|
TypeIndex IndexZero = Builder.writeLeafType(Class);
|
[CodeView] Fix random access of type names.
Suppose we had a type index offsets array with a boundary at type index
N. Then you request the name of the type with index N+1, and that name
requires the name of index N-1 (think a parameter list, for example). We
didn't handle this, and we would print something like (<unknown UDT>,
<unknown UDT>).
The fix for this is not entirely trivial, and speaks to a larger
problem. I think we need to kill TypeDatabase, or at the very least kill
TypeDatabaseVisitor. We need a thing that doesn't do any caching
whatsoever, just given a type index it can compute the type name "the
slow way". The reason for the bug is that we don't have anything like
that. Everything goes through the type database, and if we've visited a
record, then we're "done". It doesn't know how to do the expensive thing
of re-visiting dependent records if they've not yet been visited.
What I've done here is more or less copied the code (albeit greatly
simplified) from TypeDatabaseVisitor, but wrapped it in an interface
that just returns a std::string. The logic of caching the name is now in
LazyRandomTypeCollection. Eventually I'd like to move the record
database here as well and the visited record bitfield here as well, at
which point we can actually just delete TypeDatabase. I don't see any
reason for it if a "sequential" collection is just a special case of a
random access collection with an empty partial offsets array.
Differential Revision: https://reviews.llvm.org/D34297
llvm-svn: 305612
2017-06-17 07:42:44 +08:00
|
|
|
|
|
|
|
// TypeIndex 1 refers to type index 0.
|
|
|
|
ModifierRecord Modifier(TypeRecordKind::Modifier);
|
|
|
|
Modifier.ModifiedType = TypeIndex::fromArrayIndex(0);
|
|
|
|
Modifier.Modifiers = ModifierOptions::Const;
|
[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
llvm-svn: 319198
2017-11-29 02:33:17 +08:00
|
|
|
TypeIndex IndexOne = Builder.writeLeafType(Modifier);
|
[CodeView] Fix random access of type names.
Suppose we had a type index offsets array with a boundary at type index
N. Then you request the name of the type with index N+1, and that name
requires the name of index N-1 (think a parameter list, for example). We
didn't handle this, and we would print something like (<unknown UDT>,
<unknown UDT>).
The fix for this is not entirely trivial, and speaks to a larger
problem. I think we need to kill TypeDatabase, or at the very least kill
TypeDatabaseVisitor. We need a thing that doesn't do any caching
whatsoever, just given a type index it can compute the type name "the
slow way". The reason for the bug is that we don't have anything like
that. Everything goes through the type database, and if we've visited a
record, then we're "done". It doesn't know how to do the expensive thing
of re-visiting dependent records if they've not yet been visited.
What I've done here is more or less copied the code (albeit greatly
simplified) from TypeDatabaseVisitor, but wrapped it in an interface
that just returns a std::string. The logic of caching the name is now in
LazyRandomTypeCollection. Eventually I'd like to move the record
database here as well and the visited record bitfield here as well, at
which point we can actually just delete TypeDatabase. I don't see any
reason for it if a "sequential" collection is just a special case of a
random access collection with an empty partial offsets array.
Differential Revision: https://reviews.llvm.org/D34297
llvm-svn: 305612
2017-06-17 07:42:44 +08:00
|
|
|
|
|
|
|
// set up a type stream that refers to the above two serialized records.
|
|
|
|
std::vector<CVType> TypeArray;
|
|
|
|
TypeArray.push_back(
|
|
|
|
CVType(static_cast<TypeLeafKind>(Class.Kind), Builder.records()[0]));
|
|
|
|
TypeArray.push_back(
|
|
|
|
CVType(static_cast<TypeLeafKind>(Modifier.Kind), Builder.records()[1]));
|
|
|
|
BinaryItemStream<CVType> ItemStream(llvm::support::little);
|
|
|
|
ItemStream.setItems(TypeArray);
|
|
|
|
VarStreamArray<CVType> TypeStream(ItemStream);
|
|
|
|
|
|
|
|
// Figure out the byte offset of the second item.
|
|
|
|
auto ItemOneIter = TypeStream.begin();
|
|
|
|
++ItemOneIter;
|
|
|
|
|
|
|
|
// Set up a partial offsets buffer that contains the first and second items
|
|
|
|
// in separate chunks.
|
|
|
|
std::vector<TypeIndexOffset> TIO;
|
|
|
|
TIO.push_back({IndexZero, ulittle32_t(0u)});
|
|
|
|
TIO.push_back({IndexOne, ulittle32_t(ItemOneIter.offset())});
|
|
|
|
ArrayRef<uint8_t> Buffer(reinterpret_cast<const uint8_t *>(TIO.data()),
|
|
|
|
TIO.size() * sizeof(TypeIndexOffset));
|
|
|
|
|
|
|
|
BinaryStreamReader Reader(Buffer, llvm::support::little);
|
|
|
|
FixedStreamArray<TypeIndexOffset> PartialOffsets;
|
|
|
|
ASSERT_THAT_ERROR(Reader.readArray(PartialOffsets, 2), Succeeded());
|
|
|
|
|
|
|
|
LazyRandomTypeCollection Types(TypeStream, 2, PartialOffsets);
|
|
|
|
|
|
|
|
StringRef Name = Types.getTypeName(IndexOne);
|
|
|
|
EXPECT_EQ("const FooClass", Name);
|
2017-07-18 04:28:06 +08:00
|
|
|
}
|